From 73899f1a8b478524dccf2f4e4b8d35aa51e4458b Mon Sep 17 00:00:00 2001 From: Packit Service Date: Dec 09 2020 19:07:27 +0000 Subject: Changes after running %prep ignore: true --- diff --git a/deps/http-parser/LICENSE-MIT b/deps/http-parser/LICENSE-MIT deleted file mode 100644 index 58010b3..0000000 --- a/deps/http-parser/LICENSE-MIT +++ /dev/null @@ -1,23 +0,0 @@ -http_parser.c is based on src/http/ngx_http_parse.c from NGINX copyright -Igor Sysoev. - -Additional changes are licensed under the same terms as NGINX and -copyright Joyent, Inc. and other Node contributors. All rights reserved. - -Permission is hereby granted, free of charge, to any person obtaining a copy -of this software and associated documentation files (the "Software"), to -deal in the Software without restriction, including without limitation the -rights to use, copy, modify, merge, publish, distribute, sublicense, and/or -sell copies of the Software, and to permit persons to whom the Software is -furnished to do so, subject to the following conditions: - -The above copyright notice and this permission notice shall be included in -all copies or substantial portions of the Software. - -THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR -IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, -FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE -AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER -LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING -FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS -IN THE SOFTWARE. diff --git a/deps/http-parser/http_parser.c b/deps/http-parser/http_parser.c deleted file mode 100644 index 27bdd20..0000000 --- a/deps/http-parser/http_parser.c +++ /dev/null @@ -1,2177 +0,0 @@ -/* Based on src/http/ngx_http_parse.c from NGINX copyright Igor Sysoev - * - * Additional changes are licensed under the same terms as NGINX and - * copyright Joyent, Inc. and other Node contributors. All rights reserved. - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ -#include "http_parser.h" -#include -#include -#include -#include -#include -#include - -#ifndef ULLONG_MAX -# define ULLONG_MAX ((uint64_t) -1) /* 2^64-1 */ -#endif - -#ifndef MIN -# define MIN(a,b) ((a) < (b) ? (a) : (b)) -#endif - -#ifndef ARRAY_SIZE -# define ARRAY_SIZE(a) (sizeof(a) / sizeof((a)[0])) -#endif - -#ifndef BIT_AT -# define BIT_AT(a, i) \ - (!!((unsigned int) (a)[(unsigned int) (i) >> 3] & \ - (1 << ((unsigned int) (i) & 7)))) -#endif - -#ifndef ELEM_AT -# define ELEM_AT(a, i, v) ((unsigned int) (i) < ARRAY_SIZE(a) ? (a)[(i)] : (v)) -#endif - -#define SET_ERRNO(e) \ -do { \ - parser->http_errno = (e); \ -} while(0) - - -/* Run the notify callback FOR, returning ER if it fails */ -#define CALLBACK_NOTIFY_(FOR, ER) \ -do { \ - assert(HTTP_PARSER_ERRNO(parser) == HPE_OK); \ - \ - if (settings->on_##FOR) { \ - if (0 != settings->on_##FOR(parser)) { \ - SET_ERRNO(HPE_CB_##FOR); \ - } \ - \ - /* We either errored above or got paused; get out */ \ - if (HTTP_PARSER_ERRNO(parser) != HPE_OK) { \ - return (ER); \ - } \ - } \ -} while (0) - -/* Run the notify callback FOR and consume the current byte */ -#define CALLBACK_NOTIFY(FOR) CALLBACK_NOTIFY_(FOR, p - data + 1) - -/* Run the notify callback FOR and don't consume the current byte */ -#define CALLBACK_NOTIFY_NOADVANCE(FOR) CALLBACK_NOTIFY_(FOR, p - data) - -/* Run data callback FOR with LEN bytes, returning ER if it fails */ -#define CALLBACK_DATA_(FOR, LEN, ER) \ -do { \ - assert(HTTP_PARSER_ERRNO(parser) == HPE_OK); \ - \ - if (FOR##_mark) { \ - if (settings->on_##FOR) { \ - if (0 != settings->on_##FOR(parser, FOR##_mark, (LEN))) { \ - SET_ERRNO(HPE_CB_##FOR); \ - } \ - \ - /* We either errored above or got paused; get out */ \ - if (HTTP_PARSER_ERRNO(parser) != HPE_OK) { \ - return (ER); \ - } \ - } \ - FOR##_mark = NULL; \ - } \ -} while (0) - -/* Run the data callback FOR and consume the current byte */ -#define CALLBACK_DATA(FOR) \ - CALLBACK_DATA_(FOR, p - FOR##_mark, p - data + 1) - -/* Run the data callback FOR and don't consume the current byte */ -#define CALLBACK_DATA_NOADVANCE(FOR) \ - CALLBACK_DATA_(FOR, p - FOR##_mark, p - data) - -/* Set the mark FOR; non-destructive if mark is already set */ -#define MARK(FOR) \ -do { \ - if (!FOR##_mark) { \ - FOR##_mark = p; \ - } \ -} while (0) - - -#define PROXY_CONNECTION "proxy-connection" -#define CONNECTION "connection" -#define CONTENT_LENGTH "content-length" -#define TRANSFER_ENCODING "transfer-encoding" -#define UPGRADE "upgrade" -#define CHUNKED "chunked" -#define KEEP_ALIVE "keep-alive" -#define CLOSE "close" - - -static const char *method_strings[] = - { -#define XX(num, name, string) #string, - HTTP_METHOD_MAP(XX) -#undef XX - }; - - -/* Tokens as defined by rfc 2616. Also lowercases them. - * token = 1* - * separators = "(" | ")" | "<" | ">" | "@" - * | "," | ";" | ":" | "\" | <"> - * | "/" | "[" | "]" | "?" | "=" - * | "{" | "}" | SP | HT - */ -static const char tokens[256] = { -/* 0 nul 1 soh 2 stx 3 etx 4 eot 5 enq 6 ack 7 bel */ - 0, 0, 0, 0, 0, 0, 0, 0, -/* 8 bs 9 ht 10 nl 11 vt 12 np 13 cr 14 so 15 si */ - 0, 0, 0, 0, 0, 0, 0, 0, -/* 16 dle 17 dc1 18 dc2 19 dc3 20 dc4 21 nak 22 syn 23 etb */ - 0, 0, 0, 0, 0, 0, 0, 0, -/* 24 can 25 em 26 sub 27 esc 28 fs 29 gs 30 rs 31 us */ - 0, 0, 0, 0, 0, 0, 0, 0, -/* 32 sp 33 ! 34 " 35 # 36 $ 37 % 38 & 39 ' */ - 0, '!', 0, '#', '$', '%', '&', '\'', -/* 40 ( 41 ) 42 * 43 + 44 , 45 - 46 . 47 / */ - 0, 0, '*', '+', 0, '-', '.', 0, -/* 48 0 49 1 50 2 51 3 52 4 53 5 54 6 55 7 */ - '0', '1', '2', '3', '4', '5', '6', '7', -/* 56 8 57 9 58 : 59 ; 60 < 61 = 62 > 63 ? */ - '8', '9', 0, 0, 0, 0, 0, 0, -/* 64 @ 65 A 66 B 67 C 68 D 69 E 70 F 71 G */ - 0, 'a', 'b', 'c', 'd', 'e', 'f', 'g', -/* 72 H 73 I 74 J 75 K 76 L 77 M 78 N 79 O */ - 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', -/* 80 P 81 Q 82 R 83 S 84 T 85 U 86 V 87 W */ - 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', -/* 88 X 89 Y 90 Z 91 [ 92 \ 93 ] 94 ^ 95 _ */ - 'x', 'y', 'z', 0, 0, 0, '^', '_', -/* 96 ` 97 a 98 b 99 c 100 d 101 e 102 f 103 g */ - '`', 'a', 'b', 'c', 'd', 'e', 'f', 'g', -/* 104 h 105 i 106 j 107 k 108 l 109 m 110 n 111 o */ - 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', -/* 112 p 113 q 114 r 115 s 116 t 117 u 118 v 119 w */ - 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', -/* 120 x 121 y 122 z 123 { 124 | 125 } 126 ~ 127 del */ - 'x', 'y', 'z', 0, '|', 0, '~', 0 }; - - -static const int8_t unhex[256] = - {-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 - ,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 - ,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 - , 0, 1, 2, 3, 4, 5, 6, 7, 8, 9,-1,-1,-1,-1,-1,-1 - ,-1,10,11,12,13,14,15,-1,-1,-1,-1,-1,-1,-1,-1,-1 - ,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 - ,-1,10,11,12,13,14,15,-1,-1,-1,-1,-1,-1,-1,-1,-1 - ,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1 - }; - - -#if HTTP_PARSER_STRICT -# define T(v) 0 -#else -# define T(v) v -#endif - - -static const uint8_t normal_url_char[32] = { -/* 0 nul 1 soh 2 stx 3 etx 4 eot 5 enq 6 ack 7 bel */ - 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0, -/* 8 bs 9 ht 10 nl 11 vt 12 np 13 cr 14 so 15 si */ - 0 | T(2) | 0 | 0 | T(16) | 0 | 0 | 0, -/* 16 dle 17 dc1 18 dc2 19 dc3 20 dc4 21 nak 22 syn 23 etb */ - 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0, -/* 24 can 25 em 26 sub 27 esc 28 fs 29 gs 30 rs 31 us */ - 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0, -/* 32 sp 33 ! 34 " 35 # 36 $ 37 % 38 & 39 ' */ - 0 | 2 | 4 | 0 | 16 | 32 | 64 | 128, -/* 40 ( 41 ) 42 * 43 + 44 , 45 - 46 . 47 / */ - 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, -/* 48 0 49 1 50 2 51 3 52 4 53 5 54 6 55 7 */ - 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, -/* 56 8 57 9 58 : 59 ; 60 < 61 = 62 > 63 ? */ - 1 | 2 | 4 | 8 | 16 | 32 | 64 | 0, -/* 64 @ 65 A 66 B 67 C 68 D 69 E 70 F 71 G */ - 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, -/* 72 H 73 I 74 J 75 K 76 L 77 M 78 N 79 O */ - 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, -/* 80 P 81 Q 82 R 83 S 84 T 85 U 86 V 87 W */ - 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, -/* 88 X 89 Y 90 Z 91 [ 92 \ 93 ] 94 ^ 95 _ */ - 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, -/* 96 ` 97 a 98 b 99 c 100 d 101 e 102 f 103 g */ - 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, -/* 104 h 105 i 106 j 107 k 108 l 109 m 110 n 111 o */ - 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, -/* 112 p 113 q 114 r 115 s 116 t 117 u 118 v 119 w */ - 1 | 2 | 4 | 8 | 16 | 32 | 64 | 128, -/* 120 x 121 y 122 z 123 { 124 | 125 } 126 ~ 127 del */ - 1 | 2 | 4 | 8 | 16 | 32 | 64 | 0, }; - -#undef T - -enum state - { s_dead = 1 /* important that this is > 0 */ - - , s_start_req_or_res - , s_res_or_resp_H - , s_start_res - , s_res_H - , s_res_HT - , s_res_HTT - , s_res_HTTP - , s_res_first_http_major - , s_res_http_major - , s_res_first_http_minor - , s_res_http_minor - , s_res_first_status_code - , s_res_status_code - , s_res_status - , s_res_line_almost_done - - , s_start_req - - , s_req_method - , s_req_spaces_before_url - , s_req_schema - , s_req_schema_slash - , s_req_schema_slash_slash - , s_req_server_start - , s_req_server - , s_req_server_with_at - , s_req_path - , s_req_query_string_start - , s_req_query_string - , s_req_fragment_start - , s_req_fragment - , s_req_http_start - , s_req_http_H - , s_req_http_HT - , s_req_http_HTT - , s_req_http_HTTP - , s_req_first_http_major - , s_req_http_major - , s_req_first_http_minor - , s_req_http_minor - , s_req_line_almost_done - - , s_header_field_start - , s_header_field - , s_header_value_start - , s_header_value - , s_header_value_lws - - , s_header_almost_done - - , s_chunk_size_start - , s_chunk_size - , s_chunk_parameters - , s_chunk_size_almost_done - - , s_headers_almost_done - , s_headers_done - - /* Important: 's_headers_done' must be the last 'header' state. All - * states beyond this must be 'body' states. It is used for overflow - * checking. See the PARSING_HEADER() macro. - */ - - , s_chunk_data - , s_chunk_data_almost_done - , s_chunk_data_done - - , s_body_identity - , s_body_identity_eof - - , s_message_done - }; - - -#define PARSING_HEADER(state) (state <= s_headers_done) - - -enum header_states - { h_general = 0 - , h_C - , h_CO - , h_CON - - , h_matching_connection - , h_matching_proxy_connection - , h_matching_content_length - , h_matching_transfer_encoding - , h_matching_upgrade - - , h_connection - , h_content_length - , h_transfer_encoding - , h_upgrade - - , h_matching_transfer_encoding_chunked - , h_matching_connection_keep_alive - , h_matching_connection_close - - , h_transfer_encoding_chunked - , h_connection_keep_alive - , h_connection_close - }; - -enum http_host_state - { - s_http_host_dead = 1 - , s_http_userinfo_start - , s_http_userinfo - , s_http_host_start - , s_http_host_v6_start - , s_http_host - , s_http_host_v6 - , s_http_host_v6_end - , s_http_host_port_start - , s_http_host_port -}; - -/* Macros for character classes; depends on strict-mode */ -#define CR '\r' -#define LF '\n' -#define LOWER(c) (unsigned char)(c | 0x20) -#define IS_ALPHA(c) (LOWER(c) >= 'a' && LOWER(c) <= 'z') -#define IS_NUM(c) ((c) >= '0' && (c) <= '9') -#define IS_ALPHANUM(c) (IS_ALPHA(c) || IS_NUM(c)) -#define IS_HEX(c) (IS_NUM(c) || (LOWER(c) >= 'a' && LOWER(c) <= 'f')) -#define IS_MARK(c) ((c) == '-' || (c) == '_' || (c) == '.' || \ - (c) == '!' || (c) == '~' || (c) == '*' || (c) == '\'' || (c) == '(' || \ - (c) == ')') -#define IS_USERINFO_CHAR(c) (IS_ALPHANUM(c) || IS_MARK(c) || (c) == '%' || \ - (c) == ';' || (c) == ':' || (c) == '&' || (c) == '=' || (c) == '+' || \ - (c) == '$' || (c) == ',') - -#if HTTP_PARSER_STRICT -#define TOKEN(c) (tokens[(unsigned char)c]) -#define IS_URL_CHAR(c) (BIT_AT(normal_url_char, (unsigned char)c)) -#define IS_HOST_CHAR(c) (IS_ALPHANUM(c) || (c) == '.' || (c) == '-') -#else -#define TOKEN(c) ((c == ' ') ? ' ' : tokens[(unsigned char)c]) -#define IS_URL_CHAR(c) \ - (BIT_AT(normal_url_char, (unsigned char)c) || ((c) & 0x80)) -#define IS_HOST_CHAR(c) \ - (IS_ALPHANUM(c) || (c) == '.' || (c) == '-' || (c) == '_') -#endif - - -#define start_state (parser->type == HTTP_REQUEST ? s_start_req : s_start_res) - - -#if HTTP_PARSER_STRICT -# define STRICT_CHECK(cond) \ -do { \ - if (cond) { \ - SET_ERRNO(HPE_STRICT); \ - goto error; \ - } \ -} while (0) -# define NEW_MESSAGE() (http_should_keep_alive(parser) ? start_state : s_dead) -#else -# define STRICT_CHECK(cond) -# define NEW_MESSAGE() start_state -#endif - - -/* Map errno values to strings for human-readable output */ -#define HTTP_STRERROR_GEN(n, s) { "HPE_" #n, s }, -static struct { - const char *name; - const char *description; -} http_strerror_tab[] = { - HTTP_ERRNO_MAP(HTTP_STRERROR_GEN) -}; -#undef HTTP_STRERROR_GEN - -int http_message_needs_eof(const http_parser *parser); - -/* Our URL parser. - * - * This is designed to be shared by http_parser_execute() for URL validation, - * hence it has a state transition + byte-for-byte interface. In addition, it - * is meant to be embedded in http_parser_parse_url(), which does the dirty - * work of turning state transitions URL components for its API. - * - * This function should only be invoked with non-space characters. It is - * assumed that the caller cares about (and can detect) the transition between - * URL and non-URL states by looking for these. - */ -static enum state -parse_url_char(enum state s, const char ch) -{ - if (ch == ' ' || ch == '\r' || ch == '\n') { - return s_dead; - } - -#if HTTP_PARSER_STRICT - if (ch == '\t' || ch == '\f') { - return s_dead; - } -#endif - - switch (s) { - case s_req_spaces_before_url: - /* Proxied requests are followed by scheme of an absolute URI (alpha). - * All methods except CONNECT are followed by '/' or '*'. - */ - - if (ch == '/' || ch == '*') { - return s_req_path; - } - - /* The schema must start with an alpha character. After that, it may - * consist of digits, '+', '-' or '.', followed by a ':'. - */ - if (IS_ALPHA(ch)) { - return s_req_schema; - } - - break; - - case s_req_schema: - if (IS_ALPHANUM(ch) || ch == '+' || ch == '-' || ch == '.') { - return s; - } - - if (ch == ':') { - return s_req_schema_slash; - } - - break; - - case s_req_schema_slash: - if (ch == '/') { - return s_req_schema_slash_slash; - } - - break; - - case s_req_schema_slash_slash: - if (ch == '/') { - return s_req_server_start; - } - - break; - - case s_req_server_with_at: - if (ch == '@') { - return s_dead; - } - - /* FALLTHROUGH */ - case s_req_server_start: - case s_req_server: - if (ch == '/') { - return s_req_path; - } - - if (ch == '?') { - return s_req_query_string_start; - } - - if (ch == '@') { - return s_req_server_with_at; - } - - if (IS_USERINFO_CHAR(ch) || ch == '[' || ch == ']') { - return s_req_server; - } - - break; - - case s_req_path: - if (IS_URL_CHAR(ch)) { - return s; - } - - switch (ch) { - case '?': - return s_req_query_string_start; - - case '#': - return s_req_fragment_start; - } - - break; - - case s_req_query_string_start: - case s_req_query_string: - if (IS_URL_CHAR(ch)) { - return s_req_query_string; - } - - switch (ch) { - case '?': - /* allow extra '?' in query string */ - return s_req_query_string; - - case '#': - return s_req_fragment_start; - } - - break; - - case s_req_fragment_start: - if (IS_URL_CHAR(ch)) { - return s_req_fragment; - } - - switch (ch) { - case '?': - return s_req_fragment; - - case '#': - return s; - } - - break; - - case s_req_fragment: - if (IS_URL_CHAR(ch)) { - return s; - } - - switch (ch) { - case '?': - case '#': - return s; - } - - break; - - default: - break; - } - - /* We should never fall out of the switch above unless there's an error */ - return s_dead; -} - -size_t http_parser_execute (http_parser *parser, - const http_parser_settings *settings, - const char *data, - size_t len) -{ - char c, ch; - int8_t unhex_val; - const char *p = data; - const char *header_field_mark = 0; - const char *header_value_mark = 0; - const char *url_mark = 0; - const char *body_mark = 0; - - /* We're in an error state. Don't bother doing anything. */ - if (HTTP_PARSER_ERRNO(parser) != HPE_OK) { - return 0; - } - - if (len == 0) { - switch (parser->state) { - case s_body_identity_eof: - /* Use of CALLBACK_NOTIFY() here would erroneously return 1 byte read if - * we got paused. - */ - CALLBACK_NOTIFY_NOADVANCE(message_complete); - return 0; - - case s_dead: - case s_start_req_or_res: - case s_start_res: - case s_start_req: - return 0; - - default: - SET_ERRNO(HPE_INVALID_EOF_STATE); - return 1; - } - } - - - if (parser->state == s_header_field) - header_field_mark = data; - if (parser->state == s_header_value) - header_value_mark = data; - switch (parser->state) { - case s_req_path: - case s_req_schema: - case s_req_schema_slash: - case s_req_schema_slash_slash: - case s_req_server_start: - case s_req_server: - case s_req_server_with_at: - case s_req_query_string_start: - case s_req_query_string: - case s_req_fragment_start: - case s_req_fragment: - url_mark = data; - break; - } - - for (p=data; p != data + len; p++) { - ch = *p; - - if (PARSING_HEADER(parser->state)) { - ++parser->nread; - /* Buffer overflow attack */ - if (parser->nread > HTTP_MAX_HEADER_SIZE) { - SET_ERRNO(HPE_HEADER_OVERFLOW); - goto error; - } - } - - reexecute_byte: - switch (parser->state) { - - case s_dead: - /* this state is used after a 'Connection: close' message - * the parser will error out if it reads another message - */ - if (ch == CR || ch == LF) - break; - - SET_ERRNO(HPE_CLOSED_CONNECTION); - goto error; - - case s_start_req_or_res: - { - if (ch == CR || ch == LF) - break; - parser->flags = 0; - parser->content_length = ULLONG_MAX; - - if (ch == 'H') { - parser->state = s_res_or_resp_H; - - CALLBACK_NOTIFY(message_begin); - } else { - parser->type = HTTP_REQUEST; - parser->state = s_start_req; - goto reexecute_byte; - } - - break; - } - - case s_res_or_resp_H: - if (ch == 'T') { - parser->type = HTTP_RESPONSE; - parser->state = s_res_HT; - } else { - if (ch != 'E') { - SET_ERRNO(HPE_INVALID_CONSTANT); - goto error; - } - - parser->type = HTTP_REQUEST; - parser->method = HTTP_HEAD; - parser->index = 2; - parser->state = s_req_method; - } - break; - - case s_start_res: - { - parser->flags = 0; - parser->content_length = ULLONG_MAX; - - switch (ch) { - case 'H': - parser->state = s_res_H; - break; - - case CR: - case LF: - break; - - default: - SET_ERRNO(HPE_INVALID_CONSTANT); - goto error; - } - - CALLBACK_NOTIFY(message_begin); - break; - } - - case s_res_H: - STRICT_CHECK(ch != 'T'); - parser->state = s_res_HT; - break; - - case s_res_HT: - STRICT_CHECK(ch != 'T'); - parser->state = s_res_HTT; - break; - - case s_res_HTT: - STRICT_CHECK(ch != 'P'); - parser->state = s_res_HTTP; - break; - - case s_res_HTTP: - STRICT_CHECK(ch != '/'); - parser->state = s_res_first_http_major; - break; - - case s_res_first_http_major: - if (ch < '0' || ch > '9') { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_major = ch - '0'; - parser->state = s_res_http_major; - break; - - /* major HTTP version or dot */ - case s_res_http_major: - { - if (ch == '.') { - parser->state = s_res_first_http_minor; - break; - } - - if (!IS_NUM(ch)) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_major *= 10; - parser->http_major += ch - '0'; - - if (parser->http_major > 999) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - break; - } - - /* first digit of minor HTTP version */ - case s_res_first_http_minor: - if (!IS_NUM(ch)) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_minor = ch - '0'; - parser->state = s_res_http_minor; - break; - - /* minor HTTP version or end of request line */ - case s_res_http_minor: - { - if (ch == ' ') { - parser->state = s_res_first_status_code; - break; - } - - if (!IS_NUM(ch)) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_minor *= 10; - parser->http_minor += ch - '0'; - - if (parser->http_minor > 999) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - break; - } - - case s_res_first_status_code: - { - if (!IS_NUM(ch)) { - if (ch == ' ') { - break; - } - - SET_ERRNO(HPE_INVALID_STATUS); - goto error; - } - parser->status_code = ch - '0'; - parser->state = s_res_status_code; - break; - } - - case s_res_status_code: - { - if (!IS_NUM(ch)) { - switch (ch) { - case ' ': - parser->state = s_res_status; - break; - case CR: - parser->state = s_res_line_almost_done; - break; - case LF: - parser->state = s_header_field_start; - break; - default: - SET_ERRNO(HPE_INVALID_STATUS); - goto error; - } - break; - } - - parser->status_code *= 10; - parser->status_code += ch - '0'; - - if (parser->status_code > 999) { - SET_ERRNO(HPE_INVALID_STATUS); - goto error; - } - - break; - } - - case s_res_status: - /* the human readable status. e.g. "NOT FOUND" - * we are not humans so just ignore this */ - if (ch == CR) { - parser->state = s_res_line_almost_done; - break; - } - - if (ch == LF) { - parser->state = s_header_field_start; - break; - } - break; - - case s_res_line_almost_done: - STRICT_CHECK(ch != LF); - parser->state = s_header_field_start; - break; - - case s_start_req: - { - if (ch == CR || ch == LF) - break; - parser->flags = 0; - parser->content_length = ULLONG_MAX; - - if (!IS_ALPHA(ch)) { - SET_ERRNO(HPE_INVALID_METHOD); - goto error; - } - - parser->method = (enum http_method) 0; - parser->index = 1; - switch (ch) { - case 'C': parser->method = HTTP_CONNECT; /* or COPY, CHECKOUT */ break; - case 'D': parser->method = HTTP_DELETE; break; - case 'G': parser->method = HTTP_GET; break; - case 'H': parser->method = HTTP_HEAD; break; - case 'L': parser->method = HTTP_LOCK; break; - case 'M': parser->method = HTTP_MKCOL; /* or MOVE, MKACTIVITY, MERGE, M-SEARCH */ break; - case 'N': parser->method = HTTP_NOTIFY; break; - case 'O': parser->method = HTTP_OPTIONS; break; - case 'P': parser->method = HTTP_POST; - /* or PROPFIND|PROPPATCH|PUT|PATCH|PURGE */ - break; - case 'R': parser->method = HTTP_REPORT; break; - case 'S': parser->method = HTTP_SUBSCRIBE; /* or SEARCH */ break; - case 'T': parser->method = HTTP_TRACE; break; - case 'U': parser->method = HTTP_UNLOCK; /* or UNSUBSCRIBE */ break; - default: - SET_ERRNO(HPE_INVALID_METHOD); - goto error; - } - parser->state = s_req_method; - - CALLBACK_NOTIFY(message_begin); - - break; - } - - case s_req_method: - { - const char *matcher; - if (ch == '\0') { - SET_ERRNO(HPE_INVALID_METHOD); - goto error; - } - - matcher = method_strings[parser->method]; - if (ch == ' ' && matcher[parser->index] == '\0') { - parser->state = s_req_spaces_before_url; - } else if (ch == matcher[parser->index]) { - ; /* nada */ - } else if (parser->method == HTTP_CONNECT) { - if (parser->index == 1 && ch == 'H') { - parser->method = HTTP_CHECKOUT; - } else if (parser->index == 2 && ch == 'P') { - parser->method = HTTP_COPY; - } else { - goto error; - } - } else if (parser->method == HTTP_MKCOL) { - if (parser->index == 1 && ch == 'O') { - parser->method = HTTP_MOVE; - } else if (parser->index == 1 && ch == 'E') { - parser->method = HTTP_MERGE; - } else if (parser->index == 1 && ch == '-') { - parser->method = HTTP_MSEARCH; - } else if (parser->index == 2 && ch == 'A') { - parser->method = HTTP_MKACTIVITY; - } else { - goto error; - } - } else if (parser->method == HTTP_SUBSCRIBE) { - if (parser->index == 1 && ch == 'E') { - parser->method = HTTP_SEARCH; - } else { - goto error; - } - } else if (parser->index == 1 && parser->method == HTTP_POST) { - if (ch == 'R') { - parser->method = HTTP_PROPFIND; /* or HTTP_PROPPATCH */ - } else if (ch == 'U') { - parser->method = HTTP_PUT; /* or HTTP_PURGE */ - } else if (ch == 'A') { - parser->method = HTTP_PATCH; - } else { - goto error; - } - } else if (parser->index == 2) { - if (parser->method == HTTP_PUT) { - if (ch == 'R') parser->method = HTTP_PURGE; - } else if (parser->method == HTTP_UNLOCK) { - if (ch == 'S') parser->method = HTTP_UNSUBSCRIBE; - } - } else if (parser->index == 4 && parser->method == HTTP_PROPFIND && ch == 'P') { - parser->method = HTTP_PROPPATCH; - } else { - SET_ERRNO(HPE_INVALID_METHOD); - goto error; - } - - ++parser->index; - break; - } - - case s_req_spaces_before_url: - { - if (ch == ' ') break; - - MARK(url); - if (parser->method == HTTP_CONNECT) { - parser->state = s_req_server_start; - } - - parser->state = parse_url_char((enum state)parser->state, ch); - if (parser->state == s_dead) { - SET_ERRNO(HPE_INVALID_URL); - goto error; - } - - break; - } - - case s_req_schema: - case s_req_schema_slash: - case s_req_schema_slash_slash: - case s_req_server_start: - { - switch (ch) { - /* No whitespace allowed here */ - case ' ': - case CR: - case LF: - SET_ERRNO(HPE_INVALID_URL); - goto error; - default: - parser->state = parse_url_char((enum state)parser->state, ch); - if (parser->state == s_dead) { - SET_ERRNO(HPE_INVALID_URL); - goto error; - } - } - - break; - } - - case s_req_server: - case s_req_server_with_at: - case s_req_path: - case s_req_query_string_start: - case s_req_query_string: - case s_req_fragment_start: - case s_req_fragment: - { - switch (ch) { - case ' ': - parser->state = s_req_http_start; - CALLBACK_DATA(url); - break; - case CR: - case LF: - parser->http_major = 0; - parser->http_minor = 9; - parser->state = (ch == CR) ? - s_req_line_almost_done : - s_header_field_start; - CALLBACK_DATA(url); - break; - default: - parser->state = parse_url_char((enum state)parser->state, ch); - if (parser->state == s_dead) { - SET_ERRNO(HPE_INVALID_URL); - goto error; - } - } - break; - } - - case s_req_http_start: - switch (ch) { - case 'H': - parser->state = s_req_http_H; - break; - case ' ': - break; - default: - SET_ERRNO(HPE_INVALID_CONSTANT); - goto error; - } - break; - - case s_req_http_H: - STRICT_CHECK(ch != 'T'); - parser->state = s_req_http_HT; - break; - - case s_req_http_HT: - STRICT_CHECK(ch != 'T'); - parser->state = s_req_http_HTT; - break; - - case s_req_http_HTT: - STRICT_CHECK(ch != 'P'); - parser->state = s_req_http_HTTP; - break; - - case s_req_http_HTTP: - STRICT_CHECK(ch != '/'); - parser->state = s_req_first_http_major; - break; - - /* first digit of major HTTP version */ - case s_req_first_http_major: - if (ch < '1' || ch > '9') { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_major = ch - '0'; - parser->state = s_req_http_major; - break; - - /* major HTTP version or dot */ - case s_req_http_major: - { - if (ch == '.') { - parser->state = s_req_first_http_minor; - break; - } - - if (!IS_NUM(ch)) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_major *= 10; - parser->http_major += ch - '0'; - - if (parser->http_major > 999) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - break; - } - - /* first digit of minor HTTP version */ - case s_req_first_http_minor: - if (!IS_NUM(ch)) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_minor = ch - '0'; - parser->state = s_req_http_minor; - break; - - /* minor HTTP version or end of request line */ - case s_req_http_minor: - { - if (ch == CR) { - parser->state = s_req_line_almost_done; - break; - } - - if (ch == LF) { - parser->state = s_header_field_start; - break; - } - - /* XXX allow spaces after digit? */ - - if (!IS_NUM(ch)) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - parser->http_minor *= 10; - parser->http_minor += ch - '0'; - - if (parser->http_minor > 999) { - SET_ERRNO(HPE_INVALID_VERSION); - goto error; - } - - break; - } - - /* end of request line */ - case s_req_line_almost_done: - { - if (ch != LF) { - SET_ERRNO(HPE_LF_EXPECTED); - goto error; - } - - parser->state = s_header_field_start; - break; - } - - case s_header_field_start: - { - if (ch == CR) { - parser->state = s_headers_almost_done; - break; - } - - if (ch == LF) { - /* they might be just sending \n instead of \r\n so this would be - * the second \n to denote the end of headers*/ - parser->state = s_headers_almost_done; - goto reexecute_byte; - } - - c = TOKEN(ch); - - if (!c) { - SET_ERRNO(HPE_INVALID_HEADER_TOKEN); - goto error; - } - - MARK(header_field); - - parser->index = 0; - parser->state = s_header_field; - - switch (c) { - case 'c': - parser->header_state = h_C; - break; - - case 'p': - parser->header_state = h_matching_proxy_connection; - break; - - case 't': - parser->header_state = h_matching_transfer_encoding; - break; - - case 'u': - parser->header_state = h_matching_upgrade; - break; - - default: - parser->header_state = h_general; - break; - } - break; - } - - case s_header_field: - { - c = TOKEN(ch); - - if (c) { - switch (parser->header_state) { - case h_general: - break; - - case h_C: - parser->index++; - parser->header_state = (c == 'o' ? h_CO : h_general); - break; - - case h_CO: - parser->index++; - parser->header_state = (c == 'n' ? h_CON : h_general); - break; - - case h_CON: - parser->index++; - switch (c) { - case 'n': - parser->header_state = h_matching_connection; - break; - case 't': - parser->header_state = h_matching_content_length; - break; - default: - parser->header_state = h_general; - break; - } - break; - - /* connection */ - - case h_matching_connection: - parser->index++; - if (parser->index > sizeof(CONNECTION)-1 - || c != CONNECTION[parser->index]) { - parser->header_state = h_general; - } else if (parser->index == sizeof(CONNECTION)-2) { - parser->header_state = h_connection; - } - break; - - /* proxy-connection */ - - case h_matching_proxy_connection: - parser->index++; - if (parser->index > sizeof(PROXY_CONNECTION)-1 - || c != PROXY_CONNECTION[parser->index]) { - parser->header_state = h_general; - } else if (parser->index == sizeof(PROXY_CONNECTION)-2) { - parser->header_state = h_connection; - } - break; - - /* content-length */ - - case h_matching_content_length: - parser->index++; - if (parser->index > sizeof(CONTENT_LENGTH)-1 - || c != CONTENT_LENGTH[parser->index]) { - parser->header_state = h_general; - } else if (parser->index == sizeof(CONTENT_LENGTH)-2) { - parser->header_state = h_content_length; - } - break; - - /* transfer-encoding */ - - case h_matching_transfer_encoding: - parser->index++; - if (parser->index > sizeof(TRANSFER_ENCODING)-1 - || c != TRANSFER_ENCODING[parser->index]) { - parser->header_state = h_general; - } else if (parser->index == sizeof(TRANSFER_ENCODING)-2) { - parser->header_state = h_transfer_encoding; - } - break; - - /* upgrade */ - - case h_matching_upgrade: - parser->index++; - if (parser->index > sizeof(UPGRADE)-1 - || c != UPGRADE[parser->index]) { - parser->header_state = h_general; - } else if (parser->index == sizeof(UPGRADE)-2) { - parser->header_state = h_upgrade; - } - break; - - case h_connection: - case h_content_length: - case h_transfer_encoding: - case h_upgrade: - if (ch != ' ') parser->header_state = h_general; - break; - - default: - assert(0 && "Unknown header_state"); - break; - } - break; - } - - if (ch == ':') { - parser->state = s_header_value_start; - CALLBACK_DATA(header_field); - break; - } - - if (ch == CR) { - parser->state = s_header_almost_done; - CALLBACK_DATA(header_field); - break; - } - - if (ch == LF) { - parser->state = s_header_field_start; - CALLBACK_DATA(header_field); - break; - } - - SET_ERRNO(HPE_INVALID_HEADER_TOKEN); - goto error; - } - - case s_header_value_start: - { - if (ch == ' ' || ch == '\t') break; - - MARK(header_value); - - parser->state = s_header_value; - parser->index = 0; - - if (ch == CR) { - parser->header_state = h_general; - parser->state = s_header_almost_done; - CALLBACK_DATA(header_value); - break; - } - - if (ch == LF) { - parser->state = s_header_field_start; - CALLBACK_DATA(header_value); - break; - } - - c = LOWER(ch); - - switch (parser->header_state) { - case h_upgrade: - parser->flags |= F_UPGRADE; - parser->header_state = h_general; - break; - - case h_transfer_encoding: - /* looking for 'Transfer-Encoding: chunked' */ - if ('c' == c) { - parser->header_state = h_matching_transfer_encoding_chunked; - } else { - parser->header_state = h_general; - } - break; - - case h_content_length: - if (!IS_NUM(ch)) { - SET_ERRNO(HPE_INVALID_CONTENT_LENGTH); - goto error; - } - - parser->content_length = ch - '0'; - break; - - case h_connection: - /* looking for 'Connection: keep-alive' */ - if (c == 'k') { - parser->header_state = h_matching_connection_keep_alive; - /* looking for 'Connection: close' */ - } else if (c == 'c') { - parser->header_state = h_matching_connection_close; - } else { - parser->header_state = h_general; - } - break; - - default: - parser->header_state = h_general; - break; - } - break; - } - - case s_header_value: - { - - if (ch == CR) { - parser->state = s_header_almost_done; - CALLBACK_DATA(header_value); - break; - } - - if (ch == LF) { - parser->state = s_header_almost_done; - CALLBACK_DATA_NOADVANCE(header_value); - goto reexecute_byte; - } - - c = LOWER(ch); - - switch (parser->header_state) { - case h_general: - break; - - case h_connection: - case h_transfer_encoding: - assert(0 && "Shouldn't get here."); - break; - - case h_content_length: - { - uint64_t t; - - if (ch == ' ') break; - - if (!IS_NUM(ch)) { - SET_ERRNO(HPE_INVALID_CONTENT_LENGTH); - goto error; - } - - t = parser->content_length; - t *= 10; - t += ch - '0'; - - /* Overflow? */ - if (t < parser->content_length || t == ULLONG_MAX) { - SET_ERRNO(HPE_INVALID_CONTENT_LENGTH); - goto error; - } - - parser->content_length = t; - break; - } - - /* Transfer-Encoding: chunked */ - case h_matching_transfer_encoding_chunked: - parser->index++; - if (parser->index > sizeof(CHUNKED)-1 - || c != CHUNKED[parser->index]) { - parser->header_state = h_general; - } else if (parser->index == sizeof(CHUNKED)-2) { - parser->header_state = h_transfer_encoding_chunked; - } - break; - - /* looking for 'Connection: keep-alive' */ - case h_matching_connection_keep_alive: - parser->index++; - if (parser->index > sizeof(KEEP_ALIVE)-1 - || c != KEEP_ALIVE[parser->index]) { - parser->header_state = h_general; - } else if (parser->index == sizeof(KEEP_ALIVE)-2) { - parser->header_state = h_connection_keep_alive; - } - break; - - /* looking for 'Connection: close' */ - case h_matching_connection_close: - parser->index++; - if (parser->index > sizeof(CLOSE)-1 || c != CLOSE[parser->index]) { - parser->header_state = h_general; - } else if (parser->index == sizeof(CLOSE)-2) { - parser->header_state = h_connection_close; - } - break; - - case h_transfer_encoding_chunked: - case h_connection_keep_alive: - case h_connection_close: - if (ch != ' ') parser->header_state = h_general; - break; - - default: - parser->state = s_header_value; - parser->header_state = h_general; - break; - } - break; - } - - case s_header_almost_done: - { - STRICT_CHECK(ch != LF); - - parser->state = s_header_value_lws; - - switch (parser->header_state) { - case h_connection_keep_alive: - parser->flags |= F_CONNECTION_KEEP_ALIVE; - break; - case h_connection_close: - parser->flags |= F_CONNECTION_CLOSE; - break; - case h_transfer_encoding_chunked: - parser->flags |= F_CHUNKED; - break; - default: - break; - } - - break; - } - - case s_header_value_lws: - { - if (ch == ' ' || ch == '\t') - parser->state = s_header_value_start; - else - { - parser->state = s_header_field_start; - goto reexecute_byte; - } - break; - } - - case s_headers_almost_done: - { - STRICT_CHECK(ch != LF); - - if (parser->flags & F_TRAILING) { - /* End of a chunked request */ - parser->state = NEW_MESSAGE(); - CALLBACK_NOTIFY(message_complete); - break; - } - - parser->state = s_headers_done; - - /* Set this here so that on_headers_complete() callbacks can see it */ - parser->upgrade = - (parser->flags & F_UPGRADE || parser->method == HTTP_CONNECT); - - /* Here we call the headers_complete callback. This is somewhat - * different than other callbacks because if the user returns 1, we - * will interpret that as saying that this message has no body. This - * is needed for the annoying case of recieving a response to a HEAD - * request. - * - * We'd like to use CALLBACK_NOTIFY_NOADVANCE() here but we cannot, so - * we have to simulate it by handling a change in errno below. - */ - if (settings->on_headers_complete) { - switch (settings->on_headers_complete(parser)) { - case 0: - break; - - case 1: - parser->flags |= F_SKIPBODY; - break; - - default: - SET_ERRNO(HPE_CB_headers_complete); - return p - data; /* Error */ - } - } - - if (HTTP_PARSER_ERRNO(parser) != HPE_OK) { - return p - data; - } - - goto reexecute_byte; - } - - case s_headers_done: - { - STRICT_CHECK(ch != LF); - - parser->nread = 0; - - /* Exit, the rest of the connect is in a different protocol. */ - if (parser->upgrade) { - parser->state = NEW_MESSAGE(); - CALLBACK_NOTIFY(message_complete); - return (p - data) + 1; - } - - if (parser->flags & F_SKIPBODY) { - parser->state = NEW_MESSAGE(); - CALLBACK_NOTIFY(message_complete); - } else if (parser->flags & F_CHUNKED) { - /* chunked encoding - ignore Content-Length header */ - parser->state = s_chunk_size_start; - } else { - if (parser->content_length == 0) { - /* Content-Length header given but zero: Content-Length: 0\r\n */ - parser->state = NEW_MESSAGE(); - CALLBACK_NOTIFY(message_complete); - } else if (parser->content_length != ULLONG_MAX) { - /* Content-Length header given and non-zero */ - parser->state = s_body_identity; - } else { - if (parser->type == HTTP_REQUEST || - !http_message_needs_eof(parser)) { - /* Assume content-length 0 - read the next */ - parser->state = NEW_MESSAGE(); - CALLBACK_NOTIFY(message_complete); - } else { - /* Read body until EOF */ - parser->state = s_body_identity_eof; - } - } - } - - break; - } - - case s_body_identity: - { - uint64_t to_read = MIN(parser->content_length, - (uint64_t) ((data + len) - p)); - - assert(parser->content_length != 0 - && parser->content_length != ULLONG_MAX); - - /* The difference between advancing content_length and p is because - * the latter will automaticaly advance on the next loop iteration. - * Further, if content_length ends up at 0, we want to see the last - * byte again for our message complete callback. - */ - MARK(body); - parser->content_length -= to_read; - p += to_read - 1; - - if (parser->content_length == 0) { - parser->state = s_message_done; - - /* Mimic CALLBACK_DATA_NOADVANCE() but with one extra byte. - * - * The alternative to doing this is to wait for the next byte to - * trigger the data callback, just as in every other case. The - * problem with this is that this makes it difficult for the test - * harness to distinguish between complete-on-EOF and - * complete-on-length. It's not clear that this distinction is - * important for applications, but let's keep it for now. - */ - CALLBACK_DATA_(body, p - body_mark + 1, p - data); - goto reexecute_byte; - } - - break; - } - - /* read until EOF */ - case s_body_identity_eof: - MARK(body); - p = data + len - 1; - - break; - - case s_message_done: - parser->state = NEW_MESSAGE(); - CALLBACK_NOTIFY(message_complete); - break; - - case s_chunk_size_start: - { - assert(parser->nread == 1); - assert(parser->flags & F_CHUNKED); - - unhex_val = unhex[(unsigned char)ch]; - if (unhex_val == -1) { - SET_ERRNO(HPE_INVALID_CHUNK_SIZE); - goto error; - } - - parser->content_length = unhex_val; - parser->state = s_chunk_size; - break; - } - - case s_chunk_size: - { - uint64_t t; - - assert(parser->flags & F_CHUNKED); - - if (ch == CR) { - parser->state = s_chunk_size_almost_done; - break; - } - - unhex_val = unhex[(unsigned char)ch]; - - if (unhex_val == -1) { - if (ch == ';' || ch == ' ') { - parser->state = s_chunk_parameters; - break; - } - - SET_ERRNO(HPE_INVALID_CHUNK_SIZE); - goto error; - } - - t = parser->content_length; - t *= 16; - t += unhex_val; - - /* Overflow? */ - if (t < parser->content_length || t == ULLONG_MAX) { - SET_ERRNO(HPE_INVALID_CONTENT_LENGTH); - goto error; - } - - parser->content_length = t; - break; - } - - case s_chunk_parameters: - { - assert(parser->flags & F_CHUNKED); - /* just ignore this. TODO check for overflow */ - if (ch == CR) { - parser->state = s_chunk_size_almost_done; - break; - } - break; - } - - case s_chunk_size_almost_done: - { - assert(parser->flags & F_CHUNKED); - STRICT_CHECK(ch != LF); - - parser->nread = 0; - - if (parser->content_length == 0) { - parser->flags |= F_TRAILING; - parser->state = s_header_field_start; - } else { - parser->state = s_chunk_data; - } - break; - } - - case s_chunk_data: - { - uint64_t to_read = MIN(parser->content_length, - (uint64_t) ((data + len) - p)); - - assert(parser->flags & F_CHUNKED); - assert(parser->content_length != 0 - && parser->content_length != ULLONG_MAX); - - /* See the explanation in s_body_identity for why the content - * length and data pointers are managed this way. - */ - MARK(body); - parser->content_length -= to_read; - p += to_read - 1; - - if (parser->content_length == 0) { - parser->state = s_chunk_data_almost_done; - } - - break; - } - - case s_chunk_data_almost_done: - assert(parser->flags & F_CHUNKED); - assert(parser->content_length == 0); - STRICT_CHECK(ch != CR); - parser->state = s_chunk_data_done; - CALLBACK_DATA(body); - break; - - case s_chunk_data_done: - assert(parser->flags & F_CHUNKED); - STRICT_CHECK(ch != LF); - parser->nread = 0; - parser->state = s_chunk_size_start; - break; - - default: - assert(0 && "unhandled state"); - SET_ERRNO(HPE_INVALID_INTERNAL_STATE); - goto error; - } - } - - /* Run callbacks for any marks that we have leftover after we ran our of - * bytes. There should be at most one of these set, so it's OK to invoke - * them in series (unset marks will not result in callbacks). - * - * We use the NOADVANCE() variety of callbacks here because 'p' has already - * overflowed 'data' and this allows us to correct for the off-by-one that - * we'd otherwise have (since CALLBACK_DATA() is meant to be run with a 'p' - * value that's in-bounds). - */ - - assert(((header_field_mark ? 1 : 0) + - (header_value_mark ? 1 : 0) + - (url_mark ? 1 : 0) + - (body_mark ? 1 : 0)) <= 1); - - CALLBACK_DATA_NOADVANCE(header_field); - CALLBACK_DATA_NOADVANCE(header_value); - CALLBACK_DATA_NOADVANCE(url); - CALLBACK_DATA_NOADVANCE(body); - - return len; - -error: - if (HTTP_PARSER_ERRNO(parser) == HPE_OK) { - SET_ERRNO(HPE_UNKNOWN); - } - - return (p - data); -} - - -/* Does the parser need to see an EOF to find the end of the message? */ -int -http_message_needs_eof (const http_parser *parser) -{ - if (parser->type == HTTP_REQUEST) { - return 0; - } - - /* See RFC 2616 section 4.4 */ - if (parser->status_code / 100 == 1 || /* 1xx e.g. Continue */ - parser->status_code == 204 || /* No Content */ - parser->status_code == 304 || /* Not Modified */ - parser->flags & F_SKIPBODY) { /* response to a HEAD request */ - return 0; - } - - if ((parser->flags & F_CHUNKED) || parser->content_length != ULLONG_MAX) { - return 0; - } - - return 1; -} - - -int -http_should_keep_alive (const http_parser *parser) -{ - if (parser->http_major > 0 && parser->http_minor > 0) { - /* HTTP/1.1 */ - if (parser->flags & F_CONNECTION_CLOSE) { - return 0; - } - } else { - /* HTTP/1.0 or earlier */ - if (!(parser->flags & F_CONNECTION_KEEP_ALIVE)) { - return 0; - } - } - - return !http_message_needs_eof(parser); -} - - -const char * -http_method_str (enum http_method m) -{ - return ELEM_AT(method_strings, m, ""); -} - - -void -http_parser_init (http_parser *parser, enum http_parser_type t) -{ - void *data = parser->data; /* preserve application data */ - memset(parser, 0, sizeof(*parser)); - parser->data = data; - parser->type = t; - parser->state = (t == HTTP_REQUEST ? s_start_req : (t == HTTP_RESPONSE ? s_start_res : s_start_req_or_res)); - parser->http_errno = HPE_OK; -} - -const char * -http_errno_name(enum http_errno err) { - assert(err < (sizeof(http_strerror_tab)/sizeof(http_strerror_tab[0]))); - return http_strerror_tab[err].name; -} - -const char * -http_errno_description(enum http_errno err) { - assert(err < (sizeof(http_strerror_tab)/sizeof(http_strerror_tab[0]))); - return http_strerror_tab[err].description; -} - -static enum http_host_state -http_parse_host_char(enum http_host_state s, const char ch) { - switch(s) { - case s_http_userinfo: - case s_http_userinfo_start: - if (ch == '@') { - return s_http_host_start; - } - - if (IS_USERINFO_CHAR(ch)) { - return s_http_userinfo; - } - break; - - case s_http_host_start: - if (ch == '[') { - return s_http_host_v6_start; - } - - if (IS_HOST_CHAR(ch)) { - return s_http_host; - } - - break; - - case s_http_host: - if (IS_HOST_CHAR(ch)) { - return s_http_host; - } - - /* FALLTHROUGH */ - case s_http_host_v6_end: - if (ch == ':') { - return s_http_host_port_start; - } - - break; - - case s_http_host_v6: - if (ch == ']') { - return s_http_host_v6_end; - } - - /* FALLTHROUGH */ - case s_http_host_v6_start: - if (IS_HEX(ch) || ch == ':') { - return s_http_host_v6; - } - - break; - - case s_http_host_port: - case s_http_host_port_start: - if (IS_NUM(ch)) { - return s_http_host_port; - } - - break; - - default: - break; - } - return s_http_host_dead; -} - -static int -http_parse_host(const char * buf, struct http_parser_url *u, int found_at) { - enum http_host_state s; - - const char *p; - size_t buflen = u->field_data[UF_HOST].off + u->field_data[UF_HOST].len; - - u->field_data[UF_HOST].len = 0; - - s = found_at ? s_http_userinfo_start : s_http_host_start; - - for (p = buf + u->field_data[UF_HOST].off; p < buf + buflen; p++) { - enum http_host_state new_s = http_parse_host_char(s, *p); - - if (new_s == s_http_host_dead) { - return 1; - } - - switch(new_s) { - case s_http_host: - if (s != s_http_host) { - u->field_data[UF_HOST].off = p - buf; - } - u->field_data[UF_HOST].len++; - break; - - case s_http_host_v6: - if (s != s_http_host_v6) { - u->field_data[UF_HOST].off = p - buf; - } - u->field_data[UF_HOST].len++; - break; - - case s_http_host_port: - if (s != s_http_host_port) { - u->field_data[UF_PORT].off = p - buf; - u->field_data[UF_PORT].len = 0; - u->field_set |= (1 << UF_PORT); - } - u->field_data[UF_PORT].len++; - break; - - case s_http_userinfo: - if (s != s_http_userinfo) { - u->field_data[UF_USERINFO].off = p - buf ; - u->field_data[UF_USERINFO].len = 0; - u->field_set |= (1 << UF_USERINFO); - } - u->field_data[UF_USERINFO].len++; - break; - - default: - break; - } - s = new_s; - } - - /* Make sure we don't end somewhere unexpected */ - switch (s) { - case s_http_host_start: - case s_http_host_v6_start: - case s_http_host_v6: - case s_http_host_port_start: - case s_http_userinfo: - case s_http_userinfo_start: - return 1; - default: - break; - } - - return 0; -} - -int -http_parser_parse_url(const char *buf, size_t buflen, int is_connect, - struct http_parser_url *u) -{ - enum state s; - const char *p; - enum http_parser_url_fields uf, old_uf; - int found_at = 0; - - u->port = u->field_set = 0; - s = is_connect ? s_req_server_start : s_req_spaces_before_url; - uf = old_uf = UF_MAX; - - for (p = buf; p < buf + buflen; p++) { - s = parse_url_char(s, *p); - - /* Figure out the next field that we're operating on */ - switch (s) { - case s_dead: - return 1; - - /* Skip delimeters */ - case s_req_schema_slash: - case s_req_schema_slash_slash: - case s_req_server_start: - case s_req_query_string_start: - case s_req_fragment_start: - continue; - - case s_req_schema: - uf = UF_SCHEMA; - break; - - case s_req_server_with_at: - found_at = 1; - - /* FALLTROUGH */ - case s_req_server: - uf = UF_HOST; - break; - - case s_req_path: - uf = UF_PATH; - break; - - case s_req_query_string: - uf = UF_QUERY; - break; - - case s_req_fragment: - uf = UF_FRAGMENT; - break; - - default: - assert(!"Unexpected state"); - return 1; - } - - /* Nothing's changed; soldier on */ - if (uf == old_uf) { - u->field_data[uf].len++; - continue; - } - - u->field_data[uf].off = p - buf; - u->field_data[uf].len = 1; - - u->field_set |= (1 << uf); - old_uf = uf; - } - - /* host must be present if there is a schema */ - /* parsing http:///toto will fail */ - if ((u->field_set & ((1 << UF_SCHEMA) | (1 << UF_HOST))) != 0) { - if (http_parse_host(buf, u, found_at) != 0) { - return 1; - } - } - - /* CONNECT requests can only contain "hostname:port" */ - if (is_connect && u->field_set != ((1 << UF_HOST)|(1 << UF_PORT))) { - return 1; - } - - if (u->field_set & (1 << UF_PORT)) { - /* Don't bother with endp; we've already validated the string */ - unsigned long v = strtoul(buf + u->field_data[UF_PORT].off, NULL, 10); - - /* Ports have a max value of 2^16 */ - if (v > 0xffff) { - return 1; - } - - u->port = (uint16_t) v; - } - - return 0; -} - -void -http_parser_pause(http_parser *parser, int paused) { - /* Users should only be pausing/unpausing a parser that is not in an error - * state. In non-debug builds, there's not much that we can do about this - * other than ignore it. - */ - if (HTTP_PARSER_ERRNO(parser) == HPE_OK || - HTTP_PARSER_ERRNO(parser) == HPE_PAUSED) { - SET_ERRNO((paused) ? HPE_PAUSED : HPE_OK); - } else { - assert(0 && "Attempting to pause parser in error state"); - } -} - -int -http_body_is_final(const struct http_parser *parser) { - return parser->state == s_message_done; -} diff --git a/deps/http-parser/http_parser.h b/deps/http-parser/http_parser.h deleted file mode 100644 index 67e1d95..0000000 --- a/deps/http-parser/http_parser.h +++ /dev/null @@ -1,305 +0,0 @@ -/* Copyright Joyent, Inc. and other Node contributors. All rights reserved. - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this software and associated documentation files (the "Software"), to - * deal in the Software without restriction, including without limitation the - * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or - * sell copies of the Software, and to permit persons to whom the Software is - * furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ -#ifndef http_parser_h -#define http_parser_h -#ifdef __cplusplus -extern "C" { -#endif - -#define HTTP_PARSER_VERSION_MAJOR 2 -#define HTTP_PARSER_VERSION_MINOR 0 - -#include -#if defined(_WIN32) && !defined(__MINGW32__) && (!defined(_MSC_VER) || _MSC_VER<1600) -#include -typedef __int8 int8_t; -typedef unsigned __int8 uint8_t; -typedef __int16 int16_t; -typedef unsigned __int16 uint16_t; -typedef __int32 int32_t; -typedef unsigned __int32 uint32_t; -typedef __int64 int64_t; -typedef unsigned __int64 uint64_t; -typedef SIZE_T size_t; -typedef SSIZE_T ssize_t; -#elif defined(__sun) || defined(__sun__) -#include -#else -#include -#endif - -/* Compile with -DHTTP_PARSER_STRICT=0 to make less checks, but run - * faster - */ -#ifndef HTTP_PARSER_STRICT -# define HTTP_PARSER_STRICT 1 -#endif - -/* Maximium header size allowed */ -#define HTTP_MAX_HEADER_SIZE (80*1024) - - -typedef struct http_parser http_parser; -typedef struct http_parser_settings http_parser_settings; - - -/* Callbacks should return non-zero to indicate an error. The parser will - * then halt execution. - * - * The one exception is on_headers_complete. In a HTTP_RESPONSE parser - * returning '1' from on_headers_complete will tell the parser that it - * should not expect a body. This is used when receiving a response to a - * HEAD request which may contain 'Content-Length' or 'Transfer-Encoding: - * chunked' headers that indicate the presence of a body. - * - * http_data_cb does not return data chunks. It will be call arbitrarally - * many times for each string. E.G. you might get 10 callbacks for "on_url" - * each providing just a few characters more data. - */ -typedef int (*http_data_cb) (http_parser*, const char *at, size_t length); -typedef int (*http_cb) (http_parser*); - - -/* Request Methods */ -#define HTTP_METHOD_MAP(XX) \ - XX(0, DELETE, DELETE) \ - XX(1, GET, GET) \ - XX(2, HEAD, HEAD) \ - XX(3, POST, POST) \ - XX(4, PUT, PUT) \ - /* pathological */ \ - XX(5, CONNECT, CONNECT) \ - XX(6, OPTIONS, OPTIONS) \ - XX(7, TRACE, TRACE) \ - /* webdav */ \ - XX(8, COPY, COPY) \ - XX(9, LOCK, LOCK) \ - XX(10, MKCOL, MKCOL) \ - XX(11, MOVE, MOVE) \ - XX(12, PROPFIND, PROPFIND) \ - XX(13, PROPPATCH, PROPPATCH) \ - XX(14, SEARCH, SEARCH) \ - XX(15, UNLOCK, UNLOCK) \ - /* subversion */ \ - XX(16, REPORT, REPORT) \ - XX(17, MKACTIVITY, MKACTIVITY) \ - XX(18, CHECKOUT, CHECKOUT) \ - XX(19, MERGE, MERGE) \ - /* upnp */ \ - XX(20, MSEARCH, M-SEARCH) \ - XX(21, NOTIFY, NOTIFY) \ - XX(22, SUBSCRIBE, SUBSCRIBE) \ - XX(23, UNSUBSCRIBE, UNSUBSCRIBE) \ - /* RFC-5789 */ \ - XX(24, PATCH, PATCH) \ - XX(25, PURGE, PURGE) \ - -enum http_method - { -#define XX(num, name, string) HTTP_##name = num, - HTTP_METHOD_MAP(XX) -#undef XX - }; - - -enum http_parser_type { HTTP_REQUEST, HTTP_RESPONSE, HTTP_BOTH }; - - -/* Flag values for http_parser.flags field */ -enum flags - { F_CHUNKED = 1 << 0 - , F_CONNECTION_KEEP_ALIVE = 1 << 1 - , F_CONNECTION_CLOSE = 1 << 2 - , F_TRAILING = 1 << 3 - , F_UPGRADE = 1 << 4 - , F_SKIPBODY = 1 << 5 - }; - - -/* Map for errno-related constants - * - * The provided argument should be a macro that takes 2 arguments. - */ -#define HTTP_ERRNO_MAP(XX) \ - /* No error */ \ - XX(OK, "success") \ - \ - /* Callback-related errors */ \ - XX(CB_message_begin, "the on_message_begin callback failed") \ - XX(CB_url, "the on_url callback failed") \ - XX(CB_header_field, "the on_header_field callback failed") \ - XX(CB_header_value, "the on_header_value callback failed") \ - XX(CB_headers_complete, "the on_headers_complete callback failed") \ - XX(CB_body, "the on_body callback failed") \ - XX(CB_message_complete, "the on_message_complete callback failed") \ - \ - /* Parsing-related errors */ \ - XX(INVALID_EOF_STATE, "stream ended at an unexpected time") \ - XX(HEADER_OVERFLOW, \ - "too many header bytes seen; overflow detected") \ - XX(CLOSED_CONNECTION, \ - "data received after completed connection: close message") \ - XX(INVALID_VERSION, "invalid HTTP version") \ - XX(INVALID_STATUS, "invalid HTTP status code") \ - XX(INVALID_METHOD, "invalid HTTP method") \ - XX(INVALID_URL, "invalid URL") \ - XX(INVALID_HOST, "invalid host") \ - XX(INVALID_PORT, "invalid port") \ - XX(INVALID_PATH, "invalid path") \ - XX(INVALID_QUERY_STRING, "invalid query string") \ - XX(INVALID_FRAGMENT, "invalid fragment") \ - XX(LF_EXPECTED, "LF character expected") \ - XX(INVALID_HEADER_TOKEN, "invalid character in header") \ - XX(INVALID_CONTENT_LENGTH, \ - "invalid character in content-length header") \ - XX(INVALID_CHUNK_SIZE, \ - "invalid character in chunk size header") \ - XX(INVALID_CONSTANT, "invalid constant string") \ - XX(INVALID_INTERNAL_STATE, "encountered unexpected internal state")\ - XX(STRICT, "strict mode assertion failed") \ - XX(PAUSED, "parser is paused") \ - XX(UNKNOWN, "an unknown error occurred") - - -/* Define HPE_* values for each errno value above */ -#define HTTP_ERRNO_GEN(n, s) HPE_##n, -enum http_errno { - HTTP_ERRNO_MAP(HTTP_ERRNO_GEN) -}; -#undef HTTP_ERRNO_GEN - - -/* Get an http_errno value from an http_parser */ -#define HTTP_PARSER_ERRNO(p) ((enum http_errno) (p)->http_errno) - - -struct http_parser { - /** PRIVATE **/ - unsigned char type : 2; /* enum http_parser_type */ - unsigned char flags : 6; /* F_* values from 'flags' enum; semi-public */ - unsigned char state; /* enum state from http_parser.c */ - unsigned char header_state; /* enum header_state from http_parser.c */ - unsigned char index; /* index into current matcher */ - - uint32_t nread; /* # bytes read in various scenarios */ - uint64_t content_length; /* # bytes in body (0 if no Content-Length header) */ - - /** READ-ONLY **/ - unsigned short http_major; - unsigned short http_minor; - unsigned short status_code; /* responses only */ - unsigned char method; /* requests only */ - unsigned char http_errno : 7; - - /* 1 = Upgrade header was present and the parser has exited because of that. - * 0 = No upgrade header present. - * Should be checked when http_parser_execute() returns in addition to - * error checking. - */ - unsigned char upgrade : 1; - - /** PUBLIC **/ - void *data; /* A pointer to get hook to the "connection" or "socket" object */ -}; - - -struct http_parser_settings { - http_cb on_message_begin; - http_data_cb on_url; - http_data_cb on_header_field; - http_data_cb on_header_value; - http_cb on_headers_complete; - http_data_cb on_body; - http_cb on_message_complete; -}; - - -enum http_parser_url_fields - { UF_SCHEMA = 0 - , UF_HOST = 1 - , UF_PORT = 2 - , UF_PATH = 3 - , UF_QUERY = 4 - , UF_FRAGMENT = 5 - , UF_USERINFO = 6 - , UF_MAX = 7 - }; - - -/* Result structure for http_parser_parse_url(). - * - * Callers should index into field_data[] with UF_* values iff field_set - * has the relevant (1 << UF_*) bit set. As a courtesy to clients (and - * because we probably have padding left over), we convert any port to - * a uint16_t. - */ -struct http_parser_url { - uint16_t field_set; /* Bitmask of (1 << UF_*) values */ - uint16_t port; /* Converted UF_PORT string */ - - struct { - uint16_t off; /* Offset into buffer in which field starts */ - uint16_t len; /* Length of run in buffer */ - } field_data[UF_MAX]; -}; - - -void http_parser_init(http_parser *parser, enum http_parser_type type); - - -size_t http_parser_execute(http_parser *parser, - const http_parser_settings *settings, - const char *data, - size_t len); - - -/* If http_should_keep_alive() in the on_headers_complete or - * on_message_complete callback returns 0, then this should be - * the last message on the connection. - * If you are the server, respond with the "Connection: close" header. - * If you are the client, close the connection. - */ -int http_should_keep_alive(const http_parser *parser); - -/* Returns a string version of the HTTP method. */ -const char *http_method_str(enum http_method m); - -/* Return a string name of the given error */ -const char *http_errno_name(enum http_errno err); - -/* Return a string description of the given error */ -const char *http_errno_description(enum http_errno err); - -/* Parse a URL; return nonzero on failure */ -int http_parser_parse_url(const char *buf, size_t buflen, - int is_connect, - struct http_parser_url *u); - -/* Pause or un-pause the parser; a nonzero value pauses */ -void http_parser_pause(http_parser *parser, int paused); - -/* Checks if this is the final chunk of the body. */ -int http_body_is_final(const http_parser *parser); - -#ifdef __cplusplus -} -#endif -#endif diff --git a/deps/regex/config.h b/deps/regex/config.h deleted file mode 100644 index 9537069..0000000 --- a/deps/regex/config.h +++ /dev/null @@ -1,7 +0,0 @@ -#ifndef _REGEX_CONFIG_H_ -#define _REGEX_CONFIG_H_ - -# define GAWK -# define NO_MBSUPPORT - -#endif diff --git a/deps/regex/regcomp.c b/deps/regex/regcomp.c deleted file mode 100644 index 43bffbc..0000000 --- a/deps/regex/regcomp.c +++ /dev/null @@ -1,3857 +0,0 @@ -/* Extended regular expression matching and search library. - Copyright (C) 2002-2007,2009,2010 Free Software Foundation, Inc. - This file is part of the GNU C Library. - Contributed by Isamu Hasegawa . - - The GNU C Library is free software; you can redistribute it and/or - modify it under the terms of the GNU Lesser General Public - License as published by the Free Software Foundation; either - version 2.1 of the License, or (at your option) any later version. - - The GNU C Library is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - Lesser General Public License for more details. - - You should have received a copy of the GNU Lesser General Public - License along with the GNU C Library; if not, write to the Free - Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301 USA. */ - -static reg_errcode_t re_compile_internal (regex_t *preg, const char * pattern, - size_t length, reg_syntax_t syntax); -static void re_compile_fastmap_iter (regex_t *bufp, - const re_dfastate_t *init_state, - char *fastmap); -static reg_errcode_t init_dfa (re_dfa_t *dfa, size_t pat_len); -#ifdef RE_ENABLE_I18N -static void free_charset (re_charset_t *cset); -#endif /* RE_ENABLE_I18N */ -static void free_workarea_compile (regex_t *preg); -static reg_errcode_t create_initial_state (re_dfa_t *dfa); -#ifdef RE_ENABLE_I18N -static void optimize_utf8 (re_dfa_t *dfa); -#endif -static reg_errcode_t analyze (regex_t *preg); -static reg_errcode_t preorder (bin_tree_t *root, - reg_errcode_t (fn (void *, bin_tree_t *)), - void *extra); -static reg_errcode_t postorder (bin_tree_t *root, - reg_errcode_t (fn (void *, bin_tree_t *)), - void *extra); -static reg_errcode_t optimize_subexps (void *extra, bin_tree_t *node); -static reg_errcode_t lower_subexps (void *extra, bin_tree_t *node); -static bin_tree_t *lower_subexp (reg_errcode_t *err, regex_t *preg, - bin_tree_t *node); -static reg_errcode_t calc_first (void *extra, bin_tree_t *node); -static reg_errcode_t calc_next (void *extra, bin_tree_t *node); -static reg_errcode_t link_nfa_nodes (void *extra, bin_tree_t *node); -static int duplicate_node (re_dfa_t *dfa, int org_idx, unsigned int constraint); -static int search_duplicated_node (const re_dfa_t *dfa, int org_node, - unsigned int constraint); -static reg_errcode_t calc_eclosure (re_dfa_t *dfa); -static reg_errcode_t calc_eclosure_iter (re_node_set *new_set, re_dfa_t *dfa, - int node, int root); -static reg_errcode_t calc_inveclosure (re_dfa_t *dfa); -static int fetch_number (re_string_t *input, re_token_t *token, - reg_syntax_t syntax); -static int peek_token (re_token_t *token, re_string_t *input, - reg_syntax_t syntax) internal_function; -static bin_tree_t *parse (re_string_t *regexp, regex_t *preg, - reg_syntax_t syntax, reg_errcode_t *err); -static bin_tree_t *parse_reg_exp (re_string_t *regexp, regex_t *preg, - re_token_t *token, reg_syntax_t syntax, - int nest, reg_errcode_t *err); -static bin_tree_t *parse_branch (re_string_t *regexp, regex_t *preg, - re_token_t *token, reg_syntax_t syntax, - int nest, reg_errcode_t *err); -static bin_tree_t *parse_expression (re_string_t *regexp, regex_t *preg, - re_token_t *token, reg_syntax_t syntax, - int nest, reg_errcode_t *err); -static bin_tree_t *parse_sub_exp (re_string_t *regexp, regex_t *preg, - re_token_t *token, reg_syntax_t syntax, - int nest, reg_errcode_t *err); -static bin_tree_t *parse_dup_op (bin_tree_t *dup_elem, re_string_t *regexp, - re_dfa_t *dfa, re_token_t *token, - reg_syntax_t syntax, reg_errcode_t *err); -static bin_tree_t *parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, - re_token_t *token, reg_syntax_t syntax, - reg_errcode_t *err); -static reg_errcode_t parse_bracket_element (bracket_elem_t *elem, - re_string_t *regexp, - re_token_t *token, int token_len, - re_dfa_t *dfa, - reg_syntax_t syntax, - int accept_hyphen); -static reg_errcode_t parse_bracket_symbol (bracket_elem_t *elem, - re_string_t *regexp, - re_token_t *token); -#ifdef RE_ENABLE_I18N -static reg_errcode_t build_equiv_class (bitset_t sbcset, - re_charset_t *mbcset, - int *equiv_class_alloc, - const unsigned char *name); -static reg_errcode_t build_charclass (RE_TRANSLATE_TYPE trans, - bitset_t sbcset, - re_charset_t *mbcset, - int *char_class_alloc, - const char *class_name, - reg_syntax_t syntax); -#else /* not RE_ENABLE_I18N */ -static reg_errcode_t build_equiv_class (bitset_t sbcset, - const unsigned char *name); -static reg_errcode_t build_charclass (RE_TRANSLATE_TYPE trans, - bitset_t sbcset, - const char *class_name, - reg_syntax_t syntax); -#endif /* not RE_ENABLE_I18N */ -static bin_tree_t *build_charclass_op (re_dfa_t *dfa, - RE_TRANSLATE_TYPE trans, - const char *class_name, - const char *extra, - int non_match, reg_errcode_t *err); -static bin_tree_t *create_tree (re_dfa_t *dfa, - bin_tree_t *left, bin_tree_t *right, - re_token_type_t type); -static bin_tree_t *create_token_tree (re_dfa_t *dfa, - bin_tree_t *left, bin_tree_t *right, - const re_token_t *token); -static bin_tree_t *duplicate_tree (const bin_tree_t *src, re_dfa_t *dfa); -static void free_token (re_token_t *node); -static reg_errcode_t free_tree (void *extra, bin_tree_t *node); -static reg_errcode_t mark_opt_subexp (void *extra, bin_tree_t *node); - -/* This table gives an error message for each of the error codes listed - in regex.h. Obviously the order here has to be same as there. - POSIX doesn't require that we do anything for REG_NOERROR, - but why not be nice? */ - -const char __re_error_msgid[] attribute_hidden = - { -#define REG_NOERROR_IDX 0 - gettext_noop ("Success") /* REG_NOERROR */ - "\0" -#define REG_NOMATCH_IDX (REG_NOERROR_IDX + sizeof "Success") - gettext_noop ("No match") /* REG_NOMATCH */ - "\0" -#define REG_BADPAT_IDX (REG_NOMATCH_IDX + sizeof "No match") - gettext_noop ("Invalid regular expression") /* REG_BADPAT */ - "\0" -#define REG_ECOLLATE_IDX (REG_BADPAT_IDX + sizeof "Invalid regular expression") - gettext_noop ("Invalid collation character") /* REG_ECOLLATE */ - "\0" -#define REG_ECTYPE_IDX (REG_ECOLLATE_IDX + sizeof "Invalid collation character") - gettext_noop ("Invalid character class name") /* REG_ECTYPE */ - "\0" -#define REG_EESCAPE_IDX (REG_ECTYPE_IDX + sizeof "Invalid character class name") - gettext_noop ("Trailing backslash") /* REG_EESCAPE */ - "\0" -#define REG_ESUBREG_IDX (REG_EESCAPE_IDX + sizeof "Trailing backslash") - gettext_noop ("Invalid back reference") /* REG_ESUBREG */ - "\0" -#define REG_EBRACK_IDX (REG_ESUBREG_IDX + sizeof "Invalid back reference") - gettext_noop ("Unmatched [ or [^") /* REG_EBRACK */ - "\0" -#define REG_EPAREN_IDX (REG_EBRACK_IDX + sizeof "Unmatched [ or [^") - gettext_noop ("Unmatched ( or \\(") /* REG_EPAREN */ - "\0" -#define REG_EBRACE_IDX (REG_EPAREN_IDX + sizeof "Unmatched ( or \\(") - gettext_noop ("Unmatched \\{") /* REG_EBRACE */ - "\0" -#define REG_BADBR_IDX (REG_EBRACE_IDX + sizeof "Unmatched \\{") - gettext_noop ("Invalid content of \\{\\}") /* REG_BADBR */ - "\0" -#define REG_ERANGE_IDX (REG_BADBR_IDX + sizeof "Invalid content of \\{\\}") - gettext_noop ("Invalid range end") /* REG_ERANGE */ - "\0" -#define REG_ESPACE_IDX (REG_ERANGE_IDX + sizeof "Invalid range end") - gettext_noop ("Memory exhausted") /* REG_ESPACE */ - "\0" -#define REG_BADRPT_IDX (REG_ESPACE_IDX + sizeof "Memory exhausted") - gettext_noop ("Invalid preceding regular expression") /* REG_BADRPT */ - "\0" -#define REG_EEND_IDX (REG_BADRPT_IDX + sizeof "Invalid preceding regular expression") - gettext_noop ("Premature end of regular expression") /* REG_EEND */ - "\0" -#define REG_ESIZE_IDX (REG_EEND_IDX + sizeof "Premature end of regular expression") - gettext_noop ("Regular expression too big") /* REG_ESIZE */ - "\0" -#define REG_ERPAREN_IDX (REG_ESIZE_IDX + sizeof "Regular expression too big") - gettext_noop ("Unmatched ) or \\)") /* REG_ERPAREN */ - }; - -const size_t __re_error_msgid_idx[] attribute_hidden = - { - REG_NOERROR_IDX, - REG_NOMATCH_IDX, - REG_BADPAT_IDX, - REG_ECOLLATE_IDX, - REG_ECTYPE_IDX, - REG_EESCAPE_IDX, - REG_ESUBREG_IDX, - REG_EBRACK_IDX, - REG_EPAREN_IDX, - REG_EBRACE_IDX, - REG_BADBR_IDX, - REG_ERANGE_IDX, - REG_ESPACE_IDX, - REG_BADRPT_IDX, - REG_EEND_IDX, - REG_ESIZE_IDX, - REG_ERPAREN_IDX - }; - -/* Entry points for GNU code. */ - - -#ifdef ZOS_USS - -/* For ZOS USS we must define btowc */ - -wchar_t -btowc (int c) -{ - wchar_t wtmp[2]; - char tmp[2]; - - tmp[0] = c; - tmp[1] = 0; - - mbtowc (wtmp, tmp, 1); - return wtmp[0]; -} -#endif - -/* re_compile_pattern is the GNU regular expression compiler: it - compiles PATTERN (of length LENGTH) and puts the result in BUFP. - Returns 0 if the pattern was valid, otherwise an error string. - - Assumes the `allocated' (and perhaps `buffer') and `translate' fields - are set in BUFP on entry. */ - -const char * -re_compile_pattern (const char *pattern, - size_t length, - struct re_pattern_buffer *bufp) -{ - reg_errcode_t ret; - - /* And GNU code determines whether or not to get register information - by passing null for the REGS argument to re_match, etc., not by - setting no_sub, unless RE_NO_SUB is set. */ - bufp->no_sub = !!(re_syntax_options & RE_NO_SUB); - - /* Match anchors at newline. */ - bufp->newline_anchor = 1; - - ret = re_compile_internal (bufp, pattern, length, re_syntax_options); - - if (!ret) - return NULL; - return gettext (__re_error_msgid + __re_error_msgid_idx[(int) ret]); -} -#ifdef _LIBC -weak_alias (__re_compile_pattern, re_compile_pattern) -#endif - -/* Set by `re_set_syntax' to the current regexp syntax to recognize. Can - also be assigned to arbitrarily: each pattern buffer stores its own - syntax, so it can be changed between regex compilations. */ -/* This has no initializer because initialized variables in Emacs - become read-only after dumping. */ -reg_syntax_t re_syntax_options; - - -/* Specify the precise syntax of regexps for compilation. This provides - for compatibility for various utilities which historically have - different, incompatible syntaxes. - - The argument SYNTAX is a bit mask comprised of the various bits - defined in regex.h. We return the old syntax. */ - -reg_syntax_t -re_set_syntax (reg_syntax_t syntax) -{ - reg_syntax_t ret = re_syntax_options; - - re_syntax_options = syntax; - return ret; -} -#ifdef _LIBC -weak_alias (__re_set_syntax, re_set_syntax) -#endif - -int -re_compile_fastmap (struct re_pattern_buffer *bufp) -{ - re_dfa_t *dfa = (re_dfa_t *) bufp->buffer; - char *fastmap = bufp->fastmap; - - memset (fastmap, '\0', sizeof (char) * SBC_MAX); - re_compile_fastmap_iter (bufp, dfa->init_state, fastmap); - if (dfa->init_state != dfa->init_state_word) - re_compile_fastmap_iter (bufp, dfa->init_state_word, fastmap); - if (dfa->init_state != dfa->init_state_nl) - re_compile_fastmap_iter (bufp, dfa->init_state_nl, fastmap); - if (dfa->init_state != dfa->init_state_begbuf) - re_compile_fastmap_iter (bufp, dfa->init_state_begbuf, fastmap); - bufp->fastmap_accurate = 1; - return 0; -} -#ifdef _LIBC -weak_alias (__re_compile_fastmap, re_compile_fastmap) -#endif - -static inline void -__attribute ((always_inline)) -re_set_fastmap (char *fastmap, int icase, int ch) -{ - fastmap[ch] = 1; - if (icase) - fastmap[tolower (ch)] = 1; -} - -/* Helper function for re_compile_fastmap. - Compile fastmap for the initial_state INIT_STATE. */ - -static void -re_compile_fastmap_iter (regex_t *bufp, const re_dfastate_t *init_state, - char *fastmap) -{ - volatile re_dfa_t *dfa = (re_dfa_t *) bufp->buffer; - int node_cnt; - int icase = (dfa->mb_cur_max == 1 && (bufp->syntax & RE_ICASE)); - for (node_cnt = 0; node_cnt < init_state->nodes.nelem; ++node_cnt) - { - int node = init_state->nodes.elems[node_cnt]; - re_token_type_t type = dfa->nodes[node].type; - - if (type == CHARACTER) - { - re_set_fastmap (fastmap, icase, dfa->nodes[node].opr.c); -#ifdef RE_ENABLE_I18N - if ((bufp->syntax & RE_ICASE) && dfa->mb_cur_max > 1) - { - unsigned char *buf = re_malloc (unsigned char, dfa->mb_cur_max), *p; - wchar_t wc; - mbstate_t state; - - p = buf; - *p++ = dfa->nodes[node].opr.c; - while (++node < dfa->nodes_len - && dfa->nodes[node].type == CHARACTER - && dfa->nodes[node].mb_partial) - *p++ = dfa->nodes[node].opr.c; - memset (&state, '\0', sizeof (state)); - if (__mbrtowc (&wc, (const char *) buf, p - buf, - &state) == p - buf - && (__wcrtomb ((char *) buf, towlower (wc), &state) - != (size_t) -1)) - re_set_fastmap (fastmap, 0, buf[0]); - re_free (buf); - } -#endif - } - else if (type == SIMPLE_BRACKET) - { - int i, ch; - for (i = 0, ch = 0; i < BITSET_WORDS; ++i) - { - int j; - bitset_word_t w = dfa->nodes[node].opr.sbcset[i]; - for (j = 0; j < BITSET_WORD_BITS; ++j, ++ch) - if (w & ((bitset_word_t) 1 << j)) - re_set_fastmap (fastmap, icase, ch); - } - } -#ifdef RE_ENABLE_I18N - else if (type == COMPLEX_BRACKET) - { - re_charset_t *cset = dfa->nodes[node].opr.mbcset; - int i; - -# ifdef _LIBC - /* See if we have to try all bytes which start multiple collation - elements. - e.g. In da_DK, we want to catch 'a' since "aa" is a valid - collation element, and don't catch 'b' since 'b' is - the only collation element which starts from 'b' (and - it is caught by SIMPLE_BRACKET). */ - if (_NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES) != 0 - && (cset->ncoll_syms || cset->nranges)) - { - const int32_t *table = (const int32_t *) - _NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEMB); - for (i = 0; i < SBC_MAX; ++i) - if (table[i] < 0) - re_set_fastmap (fastmap, icase, i); - } -# endif /* _LIBC */ - - /* See if we have to start the match at all multibyte characters, - i.e. where we would not find an invalid sequence. This only - applies to multibyte character sets; for single byte character - sets, the SIMPLE_BRACKET again suffices. */ - if (dfa->mb_cur_max > 1 - && (cset->nchar_classes || cset->non_match || cset->nranges -# ifdef _LIBC - || cset->nequiv_classes -# endif /* _LIBC */ - )) - { - unsigned char c = 0; - do - { - mbstate_t mbs; - memset (&mbs, 0, sizeof (mbs)); - if (__mbrtowc (NULL, (char *) &c, 1, &mbs) == (size_t) -2) - re_set_fastmap (fastmap, false, (int) c); - } - while (++c != 0); - } - - else - { - /* ... Else catch all bytes which can start the mbchars. */ - for (i = 0; i < cset->nmbchars; ++i) - { - char buf[256]; - mbstate_t state; - memset (&state, '\0', sizeof (state)); - if (__wcrtomb (buf, cset->mbchars[i], &state) != (size_t) -1) - re_set_fastmap (fastmap, icase, *(unsigned char *) buf); - if ((bufp->syntax & RE_ICASE) && dfa->mb_cur_max > 1) - { - if (__wcrtomb (buf, towlower (cset->mbchars[i]), &state) - != (size_t) -1) - re_set_fastmap (fastmap, false, *(unsigned char *) buf); - } - } - } - } -#endif /* RE_ENABLE_I18N */ - else if (type == OP_PERIOD -#ifdef RE_ENABLE_I18N - || type == OP_UTF8_PERIOD -#endif /* RE_ENABLE_I18N */ - || type == END_OF_RE) - { - memset (fastmap, '\1', sizeof (char) * SBC_MAX); - if (type == END_OF_RE) - bufp->can_be_null = 1; - return; - } - } -} - -/* Entry point for POSIX code. */ -/* regcomp takes a regular expression as a string and compiles it. - - PREG is a regex_t *. We do not expect any fields to be initialized, - since POSIX says we shouldn't. Thus, we set - - `buffer' to the compiled pattern; - `used' to the length of the compiled pattern; - `syntax' to RE_SYNTAX_POSIX_EXTENDED if the - REG_EXTENDED bit in CFLAGS is set; otherwise, to - RE_SYNTAX_POSIX_BASIC; - `newline_anchor' to REG_NEWLINE being set in CFLAGS; - `fastmap' to an allocated space for the fastmap; - `fastmap_accurate' to zero; - `re_nsub' to the number of subexpressions in PATTERN. - - PATTERN is the address of the pattern string. - - CFLAGS is a series of bits which affect compilation. - - If REG_EXTENDED is set, we use POSIX extended syntax; otherwise, we - use POSIX basic syntax. - - If REG_NEWLINE is set, then . and [^...] don't match newline. - Also, regexec will try a match beginning after every newline. - - If REG_ICASE is set, then we considers upper- and lowercase - versions of letters to be equivalent when matching. - - If REG_NOSUB is set, then when PREG is passed to regexec, that - routine will report only success or failure, and nothing about the - registers. - - It returns 0 if it succeeds, nonzero if it doesn't. (See regex.h for - the return codes and their meanings.) */ - -int -regcomp (regex_t *__restrict preg, - const char *__restrict pattern, - int cflags) -{ - reg_errcode_t ret; - reg_syntax_t syntax = ((cflags & REG_EXTENDED) ? RE_SYNTAX_POSIX_EXTENDED - : RE_SYNTAX_POSIX_BASIC); - - preg->buffer = NULL; - preg->allocated = 0; - preg->used = 0; - - /* Try to allocate space for the fastmap. */ - preg->fastmap = re_malloc (char, SBC_MAX); - if (BE (preg->fastmap == NULL, 0)) - return REG_ESPACE; - - syntax |= (cflags & REG_ICASE) ? RE_ICASE : 0; - - /* If REG_NEWLINE is set, newlines are treated differently. */ - if (cflags & REG_NEWLINE) - { /* REG_NEWLINE implies neither . nor [^...] match newline. */ - syntax &= ~RE_DOT_NEWLINE; - syntax |= RE_HAT_LISTS_NOT_NEWLINE; - /* It also changes the matching behavior. */ - preg->newline_anchor = 1; - } - else - preg->newline_anchor = 0; - preg->no_sub = !!(cflags & REG_NOSUB); - preg->translate = NULL; - - ret = re_compile_internal (preg, pattern, strlen (pattern), syntax); - - /* POSIX doesn't distinguish between an unmatched open-group and an - unmatched close-group: both are REG_EPAREN. */ - if (ret == REG_ERPAREN) - ret = REG_EPAREN; - - /* We have already checked preg->fastmap != NULL. */ - if (BE (ret == REG_NOERROR, 1)) - /* Compute the fastmap now, since regexec cannot modify the pattern - buffer. This function never fails in this implementation. */ - (void) re_compile_fastmap (preg); - else - { - /* Some error occurred while compiling the expression. */ - re_free (preg->fastmap); - preg->fastmap = NULL; - } - - return (int) ret; -} -#ifdef _LIBC -weak_alias (__regcomp, regcomp) -#endif - -/* Returns a message corresponding to an error code, ERRCODE, returned - from either regcomp or regexec. We don't use PREG here. */ - -size_t -regerror(int errcode, UNUSED const regex_t *__restrict preg, - char *__restrict errbuf, size_t errbuf_size) -{ - const char *msg; - size_t msg_size; - - if (BE (errcode < 0 - || errcode >= (int) (sizeof (__re_error_msgid_idx) - / sizeof (__re_error_msgid_idx[0])), 0)) - /* Only error codes returned by the rest of the code should be passed - to this routine. If we are given anything else, or if other regex - code generates an invalid error code, then the program has a bug. - Dump core so we can fix it. */ - abort (); - - msg = gettext (__re_error_msgid + __re_error_msgid_idx[errcode]); - - msg_size = strlen (msg) + 1; /* Includes the null. */ - - if (BE (errbuf_size != 0, 1)) - { - if (BE (msg_size > errbuf_size, 0)) - { - memcpy (errbuf, msg, errbuf_size - 1); - errbuf[errbuf_size - 1] = 0; - } - else - memcpy (errbuf, msg, msg_size); - } - - return msg_size; -} -#ifdef _LIBC -weak_alias (__regerror, regerror) -#endif - - -#ifdef RE_ENABLE_I18N -/* This static array is used for the map to single-byte characters when - UTF-8 is used. Otherwise we would allocate memory just to initialize - it the same all the time. UTF-8 is the preferred encoding so this is - a worthwhile optimization. */ -#if __GNUC__ >= 3 -static const bitset_t utf8_sb_map = { - /* Set the first 128 bits. */ - [0 ... 0x80 / BITSET_WORD_BITS - 1] = BITSET_WORD_MAX -}; -#else /* ! (__GNUC__ >= 3) */ -static bitset_t utf8_sb_map; -#endif /* __GNUC__ >= 3 */ -#endif /* RE_ENABLE_I18N */ - - -static void -free_dfa_content (re_dfa_t *dfa) -{ - unsigned int i; - int j; - - if (dfa->nodes) - for (i = 0; i < dfa->nodes_len; ++i) - free_token (dfa->nodes + i); - re_free (dfa->nexts); - for (i = 0; i < dfa->nodes_len; ++i) - { - if (dfa->eclosures != NULL) - re_node_set_free (dfa->eclosures + i); - if (dfa->inveclosures != NULL) - re_node_set_free (dfa->inveclosures + i); - if (dfa->edests != NULL) - re_node_set_free (dfa->edests + i); - } - re_free (dfa->edests); - re_free (dfa->eclosures); - re_free (dfa->inveclosures); - re_free (dfa->nodes); - - if (dfa->state_table) - for (i = 0; i <= dfa->state_hash_mask; ++i) - { - struct re_state_table_entry *entry = dfa->state_table + i; - for (j = 0; j < entry->num; ++j) - { - re_dfastate_t *state = entry->array[j]; - free_state (state); - } - re_free (entry->array); - } - re_free (dfa->state_table); -#ifdef RE_ENABLE_I18N - if (dfa->sb_char != utf8_sb_map) - re_free (dfa->sb_char); -#endif - re_free (dfa->subexp_map); -#ifdef DEBUG - re_free (dfa->re_str); -#endif - - re_free (dfa); -} - - -/* Free dynamically allocated space used by PREG. */ - -void -regfree (regex_t *preg) -{ - re_dfa_t *dfa = (re_dfa_t *) preg->buffer; - if (BE (dfa != NULL, 1)) - free_dfa_content (dfa); - preg->buffer = NULL; - preg->allocated = 0; - - re_free (preg->fastmap); - preg->fastmap = NULL; - - re_free (preg->translate); - preg->translate = NULL; -} -#ifdef _LIBC -weak_alias (__regfree, regfree) -#endif - -/* Entry points compatible with 4.2 BSD regex library. We don't define - them unless specifically requested. */ - -#if defined _REGEX_RE_COMP || defined _LIBC - -/* BSD has one and only one pattern buffer. */ -static struct re_pattern_buffer re_comp_buf; - -char * -# ifdef _LIBC -/* Make these definitions weak in libc, so POSIX programs can redefine - these names if they don't use our functions, and still use - regcomp/regexec above without link errors. */ -weak_function -# endif -re_comp (s) - const char *s; -{ - reg_errcode_t ret; - char *fastmap; - - if (!s) - { - if (!re_comp_buf.buffer) - return gettext ("No previous regular expression"); - return 0; - } - - if (re_comp_buf.buffer) - { - fastmap = re_comp_buf.fastmap; - re_comp_buf.fastmap = NULL; - __regfree (&re_comp_buf); - memset (&re_comp_buf, '\0', sizeof (re_comp_buf)); - re_comp_buf.fastmap = fastmap; - } - - if (re_comp_buf.fastmap == NULL) - { - re_comp_buf.fastmap = (char *) malloc (SBC_MAX); - if (re_comp_buf.fastmap == NULL) - return (char *) gettext (__re_error_msgid - + __re_error_msgid_idx[(int) REG_ESPACE]); - } - - /* Since `re_exec' always passes NULL for the `regs' argument, we - don't need to initialize the pattern buffer fields which affect it. */ - - /* Match anchors at newlines. */ - re_comp_buf.newline_anchor = 1; - - ret = re_compile_internal (&re_comp_buf, s, strlen (s), re_syntax_options); - - if (!ret) - return NULL; - - /* Yes, we're discarding `const' here if !HAVE_LIBINTL. */ - return (char *) gettext (__re_error_msgid + __re_error_msgid_idx[(int) ret]); -} - -#ifdef _LIBC -libc_freeres_fn (free_mem) -{ - __regfree (&re_comp_buf); -} -#endif - -#endif /* _REGEX_RE_COMP */ - -/* Internal entry point. - Compile the regular expression PATTERN, whose length is LENGTH. - SYNTAX indicate regular expression's syntax. */ - -static reg_errcode_t -re_compile_internal (regex_t *preg, const char * pattern, size_t length, - reg_syntax_t syntax) -{ - reg_errcode_t err = REG_NOERROR; - re_dfa_t *dfa; - re_string_t regexp; - - /* Initialize the pattern buffer. */ - preg->fastmap_accurate = 0; - preg->syntax = syntax; - preg->not_bol = preg->not_eol = 0; - preg->used = 0; - preg->re_nsub = 0; - preg->can_be_null = 0; - preg->regs_allocated = REGS_UNALLOCATED; - - /* Initialize the dfa. */ - dfa = (re_dfa_t *) preg->buffer; - if (BE (preg->allocated < sizeof (re_dfa_t), 0)) - { - /* If zero allocated, but buffer is non-null, try to realloc - enough space. This loses if buffer's address is bogus, but - that is the user's responsibility. If ->buffer is NULL this - is a simple allocation. */ - dfa = re_realloc (preg->buffer, re_dfa_t, 1); - if (dfa == NULL) - return REG_ESPACE; - preg->allocated = sizeof (re_dfa_t); - preg->buffer = (unsigned char *) dfa; - } - preg->used = sizeof (re_dfa_t); - - err = init_dfa (dfa, length); - if (BE (err != REG_NOERROR, 0)) - { - free_dfa_content (dfa); - preg->buffer = NULL; - preg->allocated = 0; - return err; - } -#ifdef DEBUG - /* Note: length+1 will not overflow since it is checked in init_dfa. */ - dfa->re_str = re_malloc (char, length + 1); - strncpy (dfa->re_str, pattern, length + 1); -#endif - - __libc_lock_init (dfa->lock); - - err = re_string_construct (®exp, pattern, length, preg->translate, - syntax & RE_ICASE, dfa); - if (BE (err != REG_NOERROR, 0)) - { - re_compile_internal_free_return: - free_workarea_compile (preg); - re_string_destruct (®exp); - free_dfa_content (dfa); - preg->buffer = NULL; - preg->allocated = 0; - return err; - } - - /* Parse the regular expression, and build a structure tree. */ - preg->re_nsub = 0; - dfa->str_tree = parse (®exp, preg, syntax, &err); - if (BE (dfa->str_tree == NULL, 0)) - goto re_compile_internal_free_return; - - /* Analyze the tree and create the nfa. */ - err = analyze (preg); - if (BE (err != REG_NOERROR, 0)) - goto re_compile_internal_free_return; - -#ifdef RE_ENABLE_I18N - /* If possible, do searching in single byte encoding to speed things up. */ - if (dfa->is_utf8 && !(syntax & RE_ICASE) && preg->translate == NULL) - optimize_utf8 (dfa); -#endif - - /* Then create the initial state of the dfa. */ - err = create_initial_state (dfa); - - /* Release work areas. */ - free_workarea_compile (preg); - re_string_destruct (®exp); - - if (BE (err != REG_NOERROR, 0)) - { - free_dfa_content (dfa); - preg->buffer = NULL; - preg->allocated = 0; - } - - return err; -} - -/* Initialize DFA. We use the length of the regular expression PAT_LEN - as the initial length of some arrays. */ - -static reg_errcode_t -init_dfa (re_dfa_t *dfa, size_t pat_len) -{ - unsigned int table_size; - - memset (dfa, '\0', sizeof (re_dfa_t)); - - /* Force allocation of str_tree_storage the first time. */ - dfa->str_tree_storage_idx = BIN_TREE_STORAGE_SIZE; - - /* Avoid overflows. */ - if (pat_len == SIZE_MAX) - return REG_ESPACE; - - dfa->nodes_alloc = pat_len + 1; - dfa->nodes = re_malloc (re_token_t, dfa->nodes_alloc); - - /* table_size = 2 ^ ceil(log pat_len) */ - for (table_size = 1; ; table_size <<= 1) - if (table_size > pat_len) - break; - - dfa->state_table = calloc (sizeof (struct re_state_table_entry), table_size); - dfa->state_hash_mask = table_size - 1; - - dfa->mb_cur_max = MB_CUR_MAX; -#ifdef _LIBC - if (dfa->mb_cur_max == 6 - && strcmp (_NL_CURRENT (LC_CTYPE, _NL_CTYPE_CODESET_NAME), "UTF-8") == 0) - dfa->is_utf8 = 1; - dfa->map_notascii = (_NL_CURRENT_WORD (LC_CTYPE, _NL_CTYPE_MAP_TO_NONASCII) - != 0); -#else - dfa->is_utf8 = 1; - /* We check exhaustively in the loop below if this charset is a - superset of ASCII. */ - dfa->map_notascii = 0; -#endif - -#ifdef RE_ENABLE_I18N - if (dfa->mb_cur_max > 1) - { - if (dfa->is_utf8) - { -#if !defined(__GNUC__) || __GNUC__ < 3 - static short utf8_sb_map_inited = 0; - - if (! utf8_sb_map_inited) - { - int i; - - utf8_sb_map_inited = 0; - for (i = 0; i <= 0x80 / BITSET_WORD_BITS - 1; i++) - utf8_sb_map[i] = BITSET_WORD_MAX; - } -#endif - dfa->sb_char = (re_bitset_ptr_t) utf8_sb_map; - } - else - { - int i, j, ch; - - dfa->sb_char = (re_bitset_ptr_t) calloc (sizeof (bitset_t), 1); - if (BE (dfa->sb_char == NULL, 0)) - return REG_ESPACE; - - /* Set the bits corresponding to single byte chars. */ - for (i = 0, ch = 0; i < BITSET_WORDS; ++i) - for (j = 0; j < BITSET_WORD_BITS; ++j, ++ch) - { - wint_t wch = __btowc (ch); - if (wch != WEOF) - dfa->sb_char[i] |= (bitset_word_t) 1 << j; -# ifndef _LIBC - if (isascii (ch) && wch != ch) - dfa->map_notascii = 1; -# endif - } - } - } -#endif - - if (BE (dfa->nodes == NULL || dfa->state_table == NULL, 0)) - return REG_ESPACE; - return REG_NOERROR; -} - -/* Initialize WORD_CHAR table, which indicate which character is - "word". In this case "word" means that it is the word construction - character used by some operators like "\<", "\>", etc. */ - -static void -internal_function -init_word_char (re_dfa_t *dfa) -{ - int i, j, ch; - dfa->word_ops_used = 1; - for (i = 0, ch = 0; i < BITSET_WORDS; ++i) - for (j = 0; j < BITSET_WORD_BITS; ++j, ++ch) - if (isalnum (ch) || ch == '_') - dfa->word_char[i] |= (bitset_word_t) 1 << j; -} - -/* Free the work area which are only used while compiling. */ - -static void -free_workarea_compile (regex_t *preg) -{ - re_dfa_t *dfa = (re_dfa_t *) preg->buffer; - bin_tree_storage_t *storage, *next; - for (storage = dfa->str_tree_storage; storage; storage = next) - { - next = storage->next; - re_free (storage); - } - dfa->str_tree_storage = NULL; - dfa->str_tree_storage_idx = BIN_TREE_STORAGE_SIZE; - dfa->str_tree = NULL; - re_free (dfa->org_indices); - dfa->org_indices = NULL; -} - -/* Create initial states for all contexts. */ - -static reg_errcode_t -create_initial_state (re_dfa_t *dfa) -{ - int first, i; - reg_errcode_t err; - re_node_set init_nodes; - - /* Initial states have the epsilon closure of the node which is - the first node of the regular expression. */ - first = dfa->str_tree->first->node_idx; - dfa->init_node = first; - err = re_node_set_init_copy (&init_nodes, dfa->eclosures + first); - if (BE (err != REG_NOERROR, 0)) - return err; - - /* The back-references which are in initial states can epsilon transit, - since in this case all of the subexpressions can be null. - Then we add epsilon closures of the nodes which are the next nodes of - the back-references. */ - if (dfa->nbackref > 0) - for (i = 0; i < init_nodes.nelem; ++i) - { - int node_idx = init_nodes.elems[i]; - re_token_type_t type = dfa->nodes[node_idx].type; - - int clexp_idx; - if (type != OP_BACK_REF) - continue; - for (clexp_idx = 0; clexp_idx < init_nodes.nelem; ++clexp_idx) - { - re_token_t *clexp_node; - clexp_node = dfa->nodes + init_nodes.elems[clexp_idx]; - if (clexp_node->type == OP_CLOSE_SUBEXP - && clexp_node->opr.idx == dfa->nodes[node_idx].opr.idx) - break; - } - if (clexp_idx == init_nodes.nelem) - continue; - - if (type == OP_BACK_REF) - { - int dest_idx = dfa->edests[node_idx].elems[0]; - if (!re_node_set_contains (&init_nodes, dest_idx)) - { - reg_errcode_t err = re_node_set_merge (&init_nodes, - dfa->eclosures - + dest_idx); - if (err != REG_NOERROR) - return err; - i = 0; - } - } - } - - /* It must be the first time to invoke acquire_state. */ - dfa->init_state = re_acquire_state_context (&err, dfa, &init_nodes, 0); - /* We don't check ERR here, since the initial state must not be NULL. */ - if (BE (dfa->init_state == NULL, 0)) - return err; - if (dfa->init_state->has_constraint) - { - dfa->init_state_word = re_acquire_state_context (&err, dfa, &init_nodes, - CONTEXT_WORD); - dfa->init_state_nl = re_acquire_state_context (&err, dfa, &init_nodes, - CONTEXT_NEWLINE); - dfa->init_state_begbuf = re_acquire_state_context (&err, dfa, - &init_nodes, - CONTEXT_NEWLINE - | CONTEXT_BEGBUF); - if (BE (dfa->init_state_word == NULL || dfa->init_state_nl == NULL - || dfa->init_state_begbuf == NULL, 0)) - return err; - } - else - dfa->init_state_word = dfa->init_state_nl - = dfa->init_state_begbuf = dfa->init_state; - - re_node_set_free (&init_nodes); - return REG_NOERROR; -} - -#ifdef RE_ENABLE_I18N -/* If it is possible to do searching in single byte encoding instead of UTF-8 - to speed things up, set dfa->mb_cur_max to 1, clear is_utf8 and change - DFA nodes where needed. */ - -static void -optimize_utf8 (re_dfa_t *dfa) -{ - int node, i, mb_chars = 0, has_period = 0; - - for (node = 0; node < dfa->nodes_len; ++node) - switch (dfa->nodes[node].type) - { - case CHARACTER: - if (dfa->nodes[node].opr.c >= 0x80) - mb_chars = 1; - break; - case ANCHOR: - switch (dfa->nodes[node].opr.ctx_type) - { - case LINE_FIRST: - case LINE_LAST: - case BUF_FIRST: - case BUF_LAST: - break; - default: - /* Word anchors etc. cannot be handled. It's okay to test - opr.ctx_type since constraints (for all DFA nodes) are - created by ORing one or more opr.ctx_type values. */ - return; - } - break; - case OP_PERIOD: - has_period = 1; - break; - case OP_BACK_REF: - case OP_ALT: - case END_OF_RE: - case OP_DUP_ASTERISK: - case OP_OPEN_SUBEXP: - case OP_CLOSE_SUBEXP: - break; - case COMPLEX_BRACKET: - return; - case SIMPLE_BRACKET: - /* Just double check. The non-ASCII range starts at 0x80. */ - assert (0x80 % BITSET_WORD_BITS == 0); - for (i = 0x80 / BITSET_WORD_BITS; i < BITSET_WORDS; ++i) - if (dfa->nodes[node].opr.sbcset[i]) - return; - break; - default: - abort (); - } - - if (mb_chars || has_period) - for (node = 0; node < dfa->nodes_len; ++node) - { - if (dfa->nodes[node].type == CHARACTER - && dfa->nodes[node].opr.c >= 0x80) - dfa->nodes[node].mb_partial = 0; - else if (dfa->nodes[node].type == OP_PERIOD) - dfa->nodes[node].type = OP_UTF8_PERIOD; - } - - /* The search can be in single byte locale. */ - dfa->mb_cur_max = 1; - dfa->is_utf8 = 0; - dfa->has_mb_node = dfa->nbackref > 0 || has_period; -} -#endif - -/* Analyze the structure tree, and calculate "first", "next", "edest", - "eclosure", and "inveclosure". */ - -static reg_errcode_t -analyze (regex_t *preg) -{ - re_dfa_t *dfa = (re_dfa_t *) preg->buffer; - reg_errcode_t ret; - - /* Allocate arrays. */ - dfa->nexts = re_malloc (int, dfa->nodes_alloc); - dfa->org_indices = re_malloc (int, dfa->nodes_alloc); - dfa->edests = re_malloc (re_node_set, dfa->nodes_alloc); - dfa->eclosures = re_malloc (re_node_set, dfa->nodes_alloc); - if (BE (dfa->nexts == NULL || dfa->org_indices == NULL || dfa->edests == NULL - || dfa->eclosures == NULL, 0)) - return REG_ESPACE; - - dfa->subexp_map = re_malloc (int, preg->re_nsub); - if (dfa->subexp_map != NULL) - { - unsigned int i; - for (i = 0; i < preg->re_nsub; i++) - dfa->subexp_map[i] = i; - preorder (dfa->str_tree, optimize_subexps, dfa); - for (i = 0; i < preg->re_nsub; i++) - if (dfa->subexp_map[i] != (int)i) - break; - if (i == preg->re_nsub) - { - free (dfa->subexp_map); - dfa->subexp_map = NULL; - } - } - - ret = postorder (dfa->str_tree, lower_subexps, preg); - if (BE (ret != REG_NOERROR, 0)) - return ret; - ret = postorder (dfa->str_tree, calc_first, dfa); - if (BE (ret != REG_NOERROR, 0)) - return ret; - preorder (dfa->str_tree, calc_next, dfa); - ret = preorder (dfa->str_tree, link_nfa_nodes, dfa); - if (BE (ret != REG_NOERROR, 0)) - return ret; - ret = calc_eclosure (dfa); - if (BE (ret != REG_NOERROR, 0)) - return ret; - - /* We only need this during the prune_impossible_nodes pass in regexec.c; - skip it if p_i_n will not run, as calc_inveclosure can be quadratic. */ - if ((!preg->no_sub && preg->re_nsub > 0 && dfa->has_plural_match) - || dfa->nbackref) - { - dfa->inveclosures = re_malloc (re_node_set, dfa->nodes_len); - if (BE (dfa->inveclosures == NULL, 0)) - return REG_ESPACE; - ret = calc_inveclosure (dfa); - } - - return ret; -} - -/* Our parse trees are very unbalanced, so we cannot use a stack to - implement parse tree visits. Instead, we use parent pointers and - some hairy code in these two functions. */ -static reg_errcode_t -postorder (bin_tree_t *root, reg_errcode_t (fn (void *, bin_tree_t *)), - void *extra) -{ - bin_tree_t *node, *prev; - - for (node = root; ; ) - { - /* Descend down the tree, preferably to the left (or to the right - if that's the only child). */ - while (node->left || node->right) - if (node->left) - node = node->left; - else - node = node->right; - - do - { - reg_errcode_t err = fn (extra, node); - if (BE (err != REG_NOERROR, 0)) - return err; - if (node->parent == NULL) - return REG_NOERROR; - prev = node; - node = node->parent; - } - /* Go up while we have a node that is reached from the right. */ - while (node->right == prev || node->right == NULL); - node = node->right; - } -} - -static reg_errcode_t -preorder (bin_tree_t *root, reg_errcode_t (fn (void *, bin_tree_t *)), - void *extra) -{ - bin_tree_t *node; - - for (node = root; ; ) - { - reg_errcode_t err = fn (extra, node); - if (BE (err != REG_NOERROR, 0)) - return err; - - /* Go to the left node, or up and to the right. */ - if (node->left) - node = node->left; - else - { - bin_tree_t *prev = NULL; - while (node->right == prev || node->right == NULL) - { - prev = node; - node = node->parent; - if (!node) - return REG_NOERROR; - } - node = node->right; - } - } -} - -/* Optimization pass: if a SUBEXP is entirely contained, strip it and tell - re_search_internal to map the inner one's opr.idx to this one's. Adjust - backreferences as well. Requires a preorder visit. */ -static reg_errcode_t -optimize_subexps (void *extra, bin_tree_t *node) -{ - re_dfa_t *dfa = (re_dfa_t *) extra; - - if (node->token.type == OP_BACK_REF && dfa->subexp_map) - { - int idx = node->token.opr.idx; - node->token.opr.idx = dfa->subexp_map[idx]; - dfa->used_bkref_map |= 1 << node->token.opr.idx; - } - - else if (node->token.type == SUBEXP - && node->left && node->left->token.type == SUBEXP) - { - int other_idx = node->left->token.opr.idx; - - node->left = node->left->left; - if (node->left) - node->left->parent = node; - - dfa->subexp_map[other_idx] = dfa->subexp_map[node->token.opr.idx]; - if (other_idx < BITSET_WORD_BITS) - dfa->used_bkref_map &= ~((bitset_word_t) 1 << other_idx); - } - - return REG_NOERROR; -} - -/* Lowering pass: Turn each SUBEXP node into the appropriate concatenation - of OP_OPEN_SUBEXP, the body of the SUBEXP (if any) and OP_CLOSE_SUBEXP. */ -static reg_errcode_t -lower_subexps (void *extra, bin_tree_t *node) -{ - regex_t *preg = (regex_t *) extra; - reg_errcode_t err = REG_NOERROR; - - if (node->left && node->left->token.type == SUBEXP) - { - node->left = lower_subexp (&err, preg, node->left); - if (node->left) - node->left->parent = node; - } - if (node->right && node->right->token.type == SUBEXP) - { - node->right = lower_subexp (&err, preg, node->right); - if (node->right) - node->right->parent = node; - } - - return err; -} - -static bin_tree_t * -lower_subexp (reg_errcode_t *err, regex_t *preg, bin_tree_t *node) -{ - re_dfa_t *dfa = (re_dfa_t *) preg->buffer; - bin_tree_t *body = node->left; - bin_tree_t *op, *cls, *tree1, *tree; - - if (preg->no_sub - /* We do not optimize empty subexpressions, because otherwise we may - have bad CONCAT nodes with NULL children. This is obviously not - very common, so we do not lose much. An example that triggers - this case is the sed "script" /\(\)/x. */ - && node->left != NULL - && (node->token.opr.idx >= BITSET_WORD_BITS - || !(dfa->used_bkref_map - & ((bitset_word_t) 1 << node->token.opr.idx)))) - return node->left; - - /* Convert the SUBEXP node to the concatenation of an - OP_OPEN_SUBEXP, the contents, and an OP_CLOSE_SUBEXP. */ - op = create_tree (dfa, NULL, NULL, OP_OPEN_SUBEXP); - cls = create_tree (dfa, NULL, NULL, OP_CLOSE_SUBEXP); - tree1 = body ? create_tree (dfa, body, cls, CONCAT) : cls; - tree = create_tree (dfa, op, tree1, CONCAT); - if (BE (tree == NULL || tree1 == NULL || op == NULL || cls == NULL, 0)) - { - *err = REG_ESPACE; - return NULL; - } - - op->token.opr.idx = cls->token.opr.idx = node->token.opr.idx; - op->token.opt_subexp = cls->token.opt_subexp = node->token.opt_subexp; - return tree; -} - -/* Pass 1 in building the NFA: compute FIRST and create unlinked automaton - nodes. Requires a postorder visit. */ -static reg_errcode_t -calc_first (void *extra, bin_tree_t *node) -{ - re_dfa_t *dfa = (re_dfa_t *) extra; - if (node->token.type == CONCAT) - { - node->first = node->left->first; - node->node_idx = node->left->node_idx; - } - else - { - node->first = node; - node->node_idx = re_dfa_add_node (dfa, node->token); - if (BE (node->node_idx == -1, 0)) - return REG_ESPACE; - if (node->token.type == ANCHOR) - dfa->nodes[node->node_idx].constraint = node->token.opr.ctx_type; - } - return REG_NOERROR; -} - -/* Pass 2: compute NEXT on the tree. Preorder visit. */ -static reg_errcode_t -calc_next (UNUSED void *extra, bin_tree_t *node) -{ - switch (node->token.type) - { - case OP_DUP_ASTERISK: - node->left->next = node; - break; - case CONCAT: - node->left->next = node->right->first; - node->right->next = node->next; - break; - default: - if (node->left) - node->left->next = node->next; - if (node->right) - node->right->next = node->next; - break; - } - return REG_NOERROR; -} - -/* Pass 3: link all DFA nodes to their NEXT node (any order will do). */ -static reg_errcode_t -link_nfa_nodes (void *extra, bin_tree_t *node) -{ - re_dfa_t *dfa = (re_dfa_t *) extra; - int idx = node->node_idx; - reg_errcode_t err = REG_NOERROR; - - switch (node->token.type) - { - case CONCAT: - break; - - case END_OF_RE: - assert (node->next == NULL); - break; - - case OP_DUP_ASTERISK: - case OP_ALT: - { - int left, right; - dfa->has_plural_match = 1; - if (node->left != NULL) - left = node->left->first->node_idx; - else - left = node->next->node_idx; - if (node->right != NULL) - right = node->right->first->node_idx; - else - right = node->next->node_idx; - assert (left > -1); - assert (right > -1); - err = re_node_set_init_2 (dfa->edests + idx, left, right); - } - break; - - case ANCHOR: - case OP_OPEN_SUBEXP: - case OP_CLOSE_SUBEXP: - err = re_node_set_init_1 (dfa->edests + idx, node->next->node_idx); - break; - - case OP_BACK_REF: - dfa->nexts[idx] = node->next->node_idx; - if (node->token.type == OP_BACK_REF) - err = re_node_set_init_1 (dfa->edests + idx, dfa->nexts[idx]); - break; - - default: - assert (!IS_EPSILON_NODE (node->token.type)); - dfa->nexts[idx] = node->next->node_idx; - break; - } - - return err; -} - -/* Duplicate the epsilon closure of the node ROOT_NODE. - Note that duplicated nodes have constraint INIT_CONSTRAINT in addition - to their own constraint. */ - -static reg_errcode_t -internal_function -duplicate_node_closure (re_dfa_t *dfa, int top_org_node, int top_clone_node, - int root_node, unsigned int init_constraint) -{ - int org_node, clone_node, ret; - unsigned int constraint = init_constraint; - for (org_node = top_org_node, clone_node = top_clone_node;;) - { - int org_dest, clone_dest; - if (dfa->nodes[org_node].type == OP_BACK_REF) - { - /* If the back reference epsilon-transit, its destination must - also have the constraint. Then duplicate the epsilon closure - of the destination of the back reference, and store it in - edests of the back reference. */ - org_dest = dfa->nexts[org_node]; - re_node_set_empty (dfa->edests + clone_node); - clone_dest = duplicate_node (dfa, org_dest, constraint); - if (BE (clone_dest == -1, 0)) - return REG_ESPACE; - dfa->nexts[clone_node] = dfa->nexts[org_node]; - ret = re_node_set_insert (dfa->edests + clone_node, clone_dest); - if (BE (ret < 0, 0)) - return REG_ESPACE; - } - else if (dfa->edests[org_node].nelem == 0) - { - /* In case of the node can't epsilon-transit, don't duplicate the - destination and store the original destination as the - destination of the node. */ - dfa->nexts[clone_node] = dfa->nexts[org_node]; - break; - } - else if (dfa->edests[org_node].nelem == 1) - { - /* In case of the node can epsilon-transit, and it has only one - destination. */ - org_dest = dfa->edests[org_node].elems[0]; - re_node_set_empty (dfa->edests + clone_node); - /* If the node is root_node itself, it means the epsilon clsoure - has a loop. Then tie it to the destination of the root_node. */ - if (org_node == root_node && clone_node != org_node) - { - ret = re_node_set_insert (dfa->edests + clone_node, org_dest); - if (BE (ret < 0, 0)) - return REG_ESPACE; - break; - } - /* In case of the node has another constraint, add it. */ - constraint |= dfa->nodes[org_node].constraint; - clone_dest = duplicate_node (dfa, org_dest, constraint); - if (BE (clone_dest == -1, 0)) - return REG_ESPACE; - ret = re_node_set_insert (dfa->edests + clone_node, clone_dest); - if (BE (ret < 0, 0)) - return REG_ESPACE; - } - else /* dfa->edests[org_node].nelem == 2 */ - { - /* In case of the node can epsilon-transit, and it has two - destinations. In the bin_tree_t and DFA, that's '|' and '*'. */ - org_dest = dfa->edests[org_node].elems[0]; - re_node_set_empty (dfa->edests + clone_node); - /* Search for a duplicated node which satisfies the constraint. */ - clone_dest = search_duplicated_node (dfa, org_dest, constraint); - if (clone_dest == -1) - { - /* There is no such duplicated node, create a new one. */ - reg_errcode_t err; - clone_dest = duplicate_node (dfa, org_dest, constraint); - if (BE (clone_dest == -1, 0)) - return REG_ESPACE; - ret = re_node_set_insert (dfa->edests + clone_node, clone_dest); - if (BE (ret < 0, 0)) - return REG_ESPACE; - err = duplicate_node_closure (dfa, org_dest, clone_dest, - root_node, constraint); - if (BE (err != REG_NOERROR, 0)) - return err; - } - else - { - /* There is a duplicated node which satisfies the constraint, - use it to avoid infinite loop. */ - ret = re_node_set_insert (dfa->edests + clone_node, clone_dest); - if (BE (ret < 0, 0)) - return REG_ESPACE; - } - - org_dest = dfa->edests[org_node].elems[1]; - clone_dest = duplicate_node (dfa, org_dest, constraint); - if (BE (clone_dest == -1, 0)) - return REG_ESPACE; - ret = re_node_set_insert (dfa->edests + clone_node, clone_dest); - if (BE (ret < 0, 0)) - return REG_ESPACE; - } - org_node = org_dest; - clone_node = clone_dest; - } - return REG_NOERROR; -} - -/* Search for a node which is duplicated from the node ORG_NODE, and - satisfies the constraint CONSTRAINT. */ - -static int -search_duplicated_node (const re_dfa_t *dfa, int org_node, - unsigned int constraint) -{ - int idx; - for (idx = dfa->nodes_len - 1; dfa->nodes[idx].duplicated && idx > 0; --idx) - { - if (org_node == dfa->org_indices[idx] - && constraint == dfa->nodes[idx].constraint) - return idx; /* Found. */ - } - return -1; /* Not found. */ -} - -/* Duplicate the node whose index is ORG_IDX and set the constraint CONSTRAINT. - Return the index of the new node, or -1 if insufficient storage is - available. */ - -static int -duplicate_node (re_dfa_t *dfa, int org_idx, unsigned int constraint) -{ - int dup_idx = re_dfa_add_node (dfa, dfa->nodes[org_idx]); - if (BE (dup_idx != -1, 1)) - { - dfa->nodes[dup_idx].constraint = constraint; - dfa->nodes[dup_idx].constraint |= dfa->nodes[org_idx].constraint; - dfa->nodes[dup_idx].duplicated = 1; - - /* Store the index of the original node. */ - dfa->org_indices[dup_idx] = org_idx; - } - return dup_idx; -} - -static reg_errcode_t -calc_inveclosure (re_dfa_t *dfa) -{ - int ret; - unsigned int src, idx; - for (idx = 0; idx < dfa->nodes_len; ++idx) - re_node_set_init_empty (dfa->inveclosures + idx); - - for (src = 0; src < dfa->nodes_len; ++src) - { - int *elems = dfa->eclosures[src].elems; - int idx; - for (idx = 0; idx < dfa->eclosures[src].nelem; ++idx) - { - ret = re_node_set_insert_last (dfa->inveclosures + elems[idx], src); - if (BE (ret == -1, 0)) - return REG_ESPACE; - } - } - - return REG_NOERROR; -} - -/* Calculate "eclosure" for all the node in DFA. */ - -static reg_errcode_t -calc_eclosure (re_dfa_t *dfa) -{ - size_t node_idx; - int incomplete; -#ifdef DEBUG - assert (dfa->nodes_len > 0); -#endif - incomplete = 0; - /* For each nodes, calculate epsilon closure. */ - for (node_idx = 0; ; ++node_idx) - { - reg_errcode_t err; - re_node_set eclosure_elem; - if (node_idx == dfa->nodes_len) - { - if (!incomplete) - break; - incomplete = 0; - node_idx = 0; - } - -#ifdef DEBUG - assert (dfa->eclosures[node_idx].nelem != -1); -#endif - - /* If we have already calculated, skip it. */ - if (dfa->eclosures[node_idx].nelem != 0) - continue; - /* Calculate epsilon closure of `node_idx'. */ - err = calc_eclosure_iter (&eclosure_elem, dfa, node_idx, 1); - if (BE (err != REG_NOERROR, 0)) - return err; - - if (dfa->eclosures[node_idx].nelem == 0) - { - incomplete = 1; - re_node_set_free (&eclosure_elem); - } - } - return REG_NOERROR; -} - -/* Calculate epsilon closure of NODE. */ - -static reg_errcode_t -calc_eclosure_iter (re_node_set *new_set, re_dfa_t *dfa, int node, int root) -{ - reg_errcode_t err; - int i; - re_node_set eclosure; - int ret; - int incomplete = 0; - err = re_node_set_alloc (&eclosure, dfa->edests[node].nelem + 1); - if (BE (err != REG_NOERROR, 0)) - return err; - - /* This indicates that we are calculating this node now. - We reference this value to avoid infinite loop. */ - dfa->eclosures[node].nelem = -1; - - /* If the current node has constraints, duplicate all nodes - since they must inherit the constraints. */ - if (dfa->nodes[node].constraint - && dfa->edests[node].nelem - && !dfa->nodes[dfa->edests[node].elems[0]].duplicated) - { - err = duplicate_node_closure (dfa, node, node, node, - dfa->nodes[node].constraint); - if (BE (err != REG_NOERROR, 0)) - return err; - } - - /* Expand each epsilon destination nodes. */ - if (IS_EPSILON_NODE(dfa->nodes[node].type)) - for (i = 0; i < dfa->edests[node].nelem; ++i) - { - re_node_set eclosure_elem; - int edest = dfa->edests[node].elems[i]; - /* If calculating the epsilon closure of `edest' is in progress, - return intermediate result. */ - if (dfa->eclosures[edest].nelem == -1) - { - incomplete = 1; - continue; - } - /* If we haven't calculated the epsilon closure of `edest' yet, - calculate now. Otherwise use calculated epsilon closure. */ - if (dfa->eclosures[edest].nelem == 0) - { - err = calc_eclosure_iter (&eclosure_elem, dfa, edest, 0); - if (BE (err != REG_NOERROR, 0)) - return err; - } - else - eclosure_elem = dfa->eclosures[edest]; - /* Merge the epsilon closure of `edest'. */ - err = re_node_set_merge (&eclosure, &eclosure_elem); - if (BE (err != REG_NOERROR, 0)) - return err; - /* If the epsilon closure of `edest' is incomplete, - the epsilon closure of this node is also incomplete. */ - if (dfa->eclosures[edest].nelem == 0) - { - incomplete = 1; - re_node_set_free (&eclosure_elem); - } - } - - /* An epsilon closure includes itself. */ - ret = re_node_set_insert (&eclosure, node); - if (BE (ret < 0, 0)) - return REG_ESPACE; - if (incomplete && !root) - dfa->eclosures[node].nelem = 0; - else - dfa->eclosures[node] = eclosure; - *new_set = eclosure; - return REG_NOERROR; -} - -/* Functions for token which are used in the parser. */ - -/* Fetch a token from INPUT. - We must not use this function inside bracket expressions. */ - -static void -internal_function -fetch_token (re_token_t *result, re_string_t *input, reg_syntax_t syntax) -{ - re_string_skip_bytes (input, peek_token (result, input, syntax)); -} - -/* Peek a token from INPUT, and return the length of the token. - We must not use this function inside bracket expressions. */ - -static int -internal_function -peek_token (re_token_t *token, re_string_t *input, reg_syntax_t syntax) -{ - unsigned char c; - - if (re_string_eoi (input)) - { - token->type = END_OF_RE; - return 0; - } - - c = re_string_peek_byte (input, 0); - token->opr.c = c; - - token->word_char = 0; -#ifdef RE_ENABLE_I18N - token->mb_partial = 0; - if (input->mb_cur_max > 1 && - !re_string_first_byte (input, re_string_cur_idx (input))) - { - token->type = CHARACTER; - token->mb_partial = 1; - return 1; - } -#endif - if (c == '\\') - { - unsigned char c2; - if (re_string_cur_idx (input) + 1 >= re_string_length (input)) - { - token->type = BACK_SLASH; - return 1; - } - - c2 = re_string_peek_byte_case (input, 1); - token->opr.c = c2; - token->type = CHARACTER; -#ifdef RE_ENABLE_I18N - if (input->mb_cur_max > 1) - { - wint_t wc = re_string_wchar_at (input, - re_string_cur_idx (input) + 1); - token->word_char = IS_WIDE_WORD_CHAR (wc) != 0; - } - else -#endif - token->word_char = IS_WORD_CHAR (c2) != 0; - - switch (c2) - { - case '|': - if (!(syntax & RE_LIMITED_OPS) && !(syntax & RE_NO_BK_VBAR)) - token->type = OP_ALT; - break; - case '1': case '2': case '3': case '4': case '5': - case '6': case '7': case '8': case '9': - if (!(syntax & RE_NO_BK_REFS)) - { - token->type = OP_BACK_REF; - token->opr.idx = c2 - '1'; - } - break; - case '<': - if (!(syntax & RE_NO_GNU_OPS)) - { - token->type = ANCHOR; - token->opr.ctx_type = WORD_FIRST; - } - break; - case '>': - if (!(syntax & RE_NO_GNU_OPS)) - { - token->type = ANCHOR; - token->opr.ctx_type = WORD_LAST; - } - break; - case 'b': - if (!(syntax & RE_NO_GNU_OPS)) - { - token->type = ANCHOR; - token->opr.ctx_type = WORD_DELIM; - } - break; - case 'B': - if (!(syntax & RE_NO_GNU_OPS)) - { - token->type = ANCHOR; - token->opr.ctx_type = NOT_WORD_DELIM; - } - break; - case 'w': - if (!(syntax & RE_NO_GNU_OPS)) - token->type = OP_WORD; - break; - case 'W': - if (!(syntax & RE_NO_GNU_OPS)) - token->type = OP_NOTWORD; - break; - case 's': - if (!(syntax & RE_NO_GNU_OPS)) - token->type = OP_SPACE; - break; - case 'S': - if (!(syntax & RE_NO_GNU_OPS)) - token->type = OP_NOTSPACE; - break; - case '`': - if (!(syntax & RE_NO_GNU_OPS)) - { - token->type = ANCHOR; - token->opr.ctx_type = BUF_FIRST; - } - break; - case '\'': - if (!(syntax & RE_NO_GNU_OPS)) - { - token->type = ANCHOR; - token->opr.ctx_type = BUF_LAST; - } - break; - case '(': - if (!(syntax & RE_NO_BK_PARENS)) - token->type = OP_OPEN_SUBEXP; - break; - case ')': - if (!(syntax & RE_NO_BK_PARENS)) - token->type = OP_CLOSE_SUBEXP; - break; - case '+': - if (!(syntax & RE_LIMITED_OPS) && (syntax & RE_BK_PLUS_QM)) - token->type = OP_DUP_PLUS; - break; - case '?': - if (!(syntax & RE_LIMITED_OPS) && (syntax & RE_BK_PLUS_QM)) - token->type = OP_DUP_QUESTION; - break; - case '{': - if ((syntax & RE_INTERVALS) && (!(syntax & RE_NO_BK_BRACES))) - token->type = OP_OPEN_DUP_NUM; - break; - case '}': - if ((syntax & RE_INTERVALS) && (!(syntax & RE_NO_BK_BRACES))) - token->type = OP_CLOSE_DUP_NUM; - break; - default: - break; - } - return 2; - } - - token->type = CHARACTER; -#ifdef RE_ENABLE_I18N - if (input->mb_cur_max > 1) - { - wint_t wc = re_string_wchar_at (input, re_string_cur_idx (input)); - token->word_char = IS_WIDE_WORD_CHAR (wc) != 0; - } - else -#endif - token->word_char = IS_WORD_CHAR (token->opr.c); - - switch (c) - { - case '\n': - if (syntax & RE_NEWLINE_ALT) - token->type = OP_ALT; - break; - case '|': - if (!(syntax & RE_LIMITED_OPS) && (syntax & RE_NO_BK_VBAR)) - token->type = OP_ALT; - break; - case '*': - token->type = OP_DUP_ASTERISK; - break; - case '+': - if (!(syntax & RE_LIMITED_OPS) && !(syntax & RE_BK_PLUS_QM)) - token->type = OP_DUP_PLUS; - break; - case '?': - if (!(syntax & RE_LIMITED_OPS) && !(syntax & RE_BK_PLUS_QM)) - token->type = OP_DUP_QUESTION; - break; - case '{': - if ((syntax & RE_INTERVALS) && (syntax & RE_NO_BK_BRACES)) - token->type = OP_OPEN_DUP_NUM; - break; - case '}': - if ((syntax & RE_INTERVALS) && (syntax & RE_NO_BK_BRACES)) - token->type = OP_CLOSE_DUP_NUM; - break; - case '(': - if (syntax & RE_NO_BK_PARENS) - token->type = OP_OPEN_SUBEXP; - break; - case ')': - if (syntax & RE_NO_BK_PARENS) - token->type = OP_CLOSE_SUBEXP; - break; - case '[': - token->type = OP_OPEN_BRACKET; - break; - case '.': - token->type = OP_PERIOD; - break; - case '^': - if (!(syntax & (RE_CONTEXT_INDEP_ANCHORS | RE_CARET_ANCHORS_HERE)) && - re_string_cur_idx (input) != 0) - { - char prev = re_string_peek_byte (input, -1); - if (!(syntax & RE_NEWLINE_ALT) || prev != '\n') - break; - } - token->type = ANCHOR; - token->opr.ctx_type = LINE_FIRST; - break; - case '$': - if (!(syntax & RE_CONTEXT_INDEP_ANCHORS) && - re_string_cur_idx (input) + 1 != re_string_length (input)) - { - re_token_t next; - re_string_skip_bytes (input, 1); - peek_token (&next, input, syntax); - re_string_skip_bytes (input, -1); - if (next.type != OP_ALT && next.type != OP_CLOSE_SUBEXP) - break; - } - token->type = ANCHOR; - token->opr.ctx_type = LINE_LAST; - break; - default: - break; - } - return 1; -} - -/* Peek a token from INPUT, and return the length of the token. - We must not use this function out of bracket expressions. */ - -static int -internal_function -peek_token_bracket (re_token_t *token, re_string_t *input, reg_syntax_t syntax) -{ - unsigned char c; - if (re_string_eoi (input)) - { - token->type = END_OF_RE; - return 0; - } - c = re_string_peek_byte (input, 0); - token->opr.c = c; - -#ifdef RE_ENABLE_I18N - if (input->mb_cur_max > 1 && - !re_string_first_byte (input, re_string_cur_idx (input))) - { - token->type = CHARACTER; - return 1; - } -#endif /* RE_ENABLE_I18N */ - - if (c == '\\' && (syntax & RE_BACKSLASH_ESCAPE_IN_LISTS) - && re_string_cur_idx (input) + 1 < re_string_length (input)) - { - /* In this case, '\' escape a character. */ - unsigned char c2; - re_string_skip_bytes (input, 1); - c2 = re_string_peek_byte (input, 0); - token->opr.c = c2; - token->type = CHARACTER; - return 1; - } - if (c == '[') /* '[' is a special char in a bracket exps. */ - { - unsigned char c2; - int token_len; - if (re_string_cur_idx (input) + 1 < re_string_length (input)) - c2 = re_string_peek_byte (input, 1); - else - c2 = 0; - token->opr.c = c2; - token_len = 2; - switch (c2) - { - case '.': - token->type = OP_OPEN_COLL_ELEM; - break; - case '=': - token->type = OP_OPEN_EQUIV_CLASS; - break; - case ':': - if (syntax & RE_CHAR_CLASSES) - { - token->type = OP_OPEN_CHAR_CLASS; - break; - } - /* else fall through. */ - default: - token->type = CHARACTER; - token->opr.c = c; - token_len = 1; - break; - } - return token_len; - } - switch (c) - { - case '-': - token->type = OP_CHARSET_RANGE; - break; - case ']': - token->type = OP_CLOSE_BRACKET; - break; - case '^': - token->type = OP_NON_MATCH_LIST; - break; - default: - token->type = CHARACTER; - } - return 1; -} - -/* Functions for parser. */ - -/* Entry point of the parser. - Parse the regular expression REGEXP and return the structure tree. - If an error is occured, ERR is set by error code, and return NULL. - This function build the following tree, from regular expression : - CAT - / \ - / \ - EOR - - CAT means concatenation. - EOR means end of regular expression. */ - -static bin_tree_t * -parse (re_string_t *regexp, regex_t *preg, reg_syntax_t syntax, - reg_errcode_t *err) -{ - re_dfa_t *dfa = (re_dfa_t *) preg->buffer; - bin_tree_t *tree, *eor, *root; - re_token_t current_token; - dfa->syntax = syntax; - fetch_token (¤t_token, regexp, syntax | RE_CARET_ANCHORS_HERE); - tree = parse_reg_exp (regexp, preg, ¤t_token, syntax, 0, err); - if (BE (*err != REG_NOERROR && tree == NULL, 0)) - return NULL; - eor = create_tree (dfa, NULL, NULL, END_OF_RE); - if (tree != NULL) - root = create_tree (dfa, tree, eor, CONCAT); - else - root = eor; - if (BE (eor == NULL || root == NULL, 0)) - { - *err = REG_ESPACE; - return NULL; - } - return root; -} - -/* This function build the following tree, from regular expression - |: - ALT - / \ - / \ - - - ALT means alternative, which represents the operator `|'. */ - -static bin_tree_t * -parse_reg_exp (re_string_t *regexp, regex_t *preg, re_token_t *token, - reg_syntax_t syntax, int nest, reg_errcode_t *err) -{ - re_dfa_t *dfa = (re_dfa_t *) preg->buffer; - bin_tree_t *tree, *branch = NULL; - tree = parse_branch (regexp, preg, token, syntax, nest, err); - if (BE (*err != REG_NOERROR && tree == NULL, 0)) - return NULL; - - while (token->type == OP_ALT) - { - fetch_token (token, regexp, syntax | RE_CARET_ANCHORS_HERE); - if (token->type != OP_ALT && token->type != END_OF_RE - && (nest == 0 || token->type != OP_CLOSE_SUBEXP)) - { - branch = parse_branch (regexp, preg, token, syntax, nest, err); - if (BE (*err != REG_NOERROR && branch == NULL, 0)) - return NULL; - } - else - branch = NULL; - tree = create_tree (dfa, tree, branch, OP_ALT); - if (BE (tree == NULL, 0)) - { - *err = REG_ESPACE; - return NULL; - } - } - return tree; -} - -/* This function build the following tree, from regular expression - : - CAT - / \ - / \ - - - CAT means concatenation. */ - -static bin_tree_t * -parse_branch (re_string_t *regexp, regex_t *preg, re_token_t *token, - reg_syntax_t syntax, int nest, reg_errcode_t *err) -{ - bin_tree_t *tree, *exp; - re_dfa_t *dfa = (re_dfa_t *) preg->buffer; - tree = parse_expression (regexp, preg, token, syntax, nest, err); - if (BE (*err != REG_NOERROR && tree == NULL, 0)) - return NULL; - - while (token->type != OP_ALT && token->type != END_OF_RE - && (nest == 0 || token->type != OP_CLOSE_SUBEXP)) - { - exp = parse_expression (regexp, preg, token, syntax, nest, err); - if (BE (*err != REG_NOERROR && exp == NULL, 0)) - { - return NULL; - } - if (tree != NULL && exp != NULL) - { - tree = create_tree (dfa, tree, exp, CONCAT); - if (tree == NULL) - { - *err = REG_ESPACE; - return NULL; - } - } - else if (tree == NULL) - tree = exp; - /* Otherwise exp == NULL, we don't need to create new tree. */ - } - return tree; -} - -/* This function build the following tree, from regular expression a*: - * - | - a -*/ - -static bin_tree_t * -parse_expression (re_string_t *regexp, regex_t *preg, re_token_t *token, - reg_syntax_t syntax, int nest, reg_errcode_t *err) -{ - re_dfa_t *dfa = (re_dfa_t *) preg->buffer; - bin_tree_t *tree; - switch (token->type) - { - case CHARACTER: - tree = create_token_tree (dfa, NULL, NULL, token); - if (BE (tree == NULL, 0)) - { - *err = REG_ESPACE; - return NULL; - } -#ifdef RE_ENABLE_I18N - if (dfa->mb_cur_max > 1) - { - while (!re_string_eoi (regexp) - && !re_string_first_byte (regexp, re_string_cur_idx (regexp))) - { - bin_tree_t *mbc_remain; - fetch_token (token, regexp, syntax); - mbc_remain = create_token_tree (dfa, NULL, NULL, token); - tree = create_tree (dfa, tree, mbc_remain, CONCAT); - if (BE (mbc_remain == NULL || tree == NULL, 0)) - { - *err = REG_ESPACE; - return NULL; - } - } - } -#endif - break; - case OP_OPEN_SUBEXP: - tree = parse_sub_exp (regexp, preg, token, syntax, nest + 1, err); - if (BE (*err != REG_NOERROR && tree == NULL, 0)) - return NULL; - break; - case OP_OPEN_BRACKET: - tree = parse_bracket_exp (regexp, dfa, token, syntax, err); - if (BE (*err != REG_NOERROR && tree == NULL, 0)) - return NULL; - break; - case OP_BACK_REF: - if (!BE (dfa->completed_bkref_map & (1 << token->opr.idx), 1)) - { - *err = REG_ESUBREG; - return NULL; - } - dfa->used_bkref_map |= 1 << token->opr.idx; - tree = create_token_tree (dfa, NULL, NULL, token); - if (BE (tree == NULL, 0)) - { - *err = REG_ESPACE; - return NULL; - } - ++dfa->nbackref; - dfa->has_mb_node = 1; - break; - case OP_OPEN_DUP_NUM: - if (syntax & RE_CONTEXT_INVALID_DUP) - { - *err = REG_BADRPT; - return NULL; - } - /* FALLTHROUGH */ - case OP_DUP_ASTERISK: - case OP_DUP_PLUS: - case OP_DUP_QUESTION: - if (syntax & RE_CONTEXT_INVALID_OPS) - { - *err = REG_BADRPT; - return NULL; - } - else if (syntax & RE_CONTEXT_INDEP_OPS) - { - fetch_token (token, regexp, syntax); - return parse_expression (regexp, preg, token, syntax, nest, err); - } - /* else fall through */ - case OP_CLOSE_SUBEXP: - if ((token->type == OP_CLOSE_SUBEXP) && - !(syntax & RE_UNMATCHED_RIGHT_PAREN_ORD)) - { - *err = REG_ERPAREN; - return NULL; - } - /* else fall through */ - case OP_CLOSE_DUP_NUM: - /* We treat it as a normal character. */ - - /* Then we can these characters as normal characters. */ - token->type = CHARACTER; - /* mb_partial and word_char bits should be initialized already - by peek_token. */ - tree = create_token_tree (dfa, NULL, NULL, token); - if (BE (tree == NULL, 0)) - { - *err = REG_ESPACE; - return NULL; - } - break; - case ANCHOR: - if ((token->opr.ctx_type - & (WORD_DELIM | NOT_WORD_DELIM | WORD_FIRST | WORD_LAST)) - && dfa->word_ops_used == 0) - init_word_char (dfa); - if (token->opr.ctx_type == WORD_DELIM - || token->opr.ctx_type == NOT_WORD_DELIM) - { - bin_tree_t *tree_first, *tree_last; - if (token->opr.ctx_type == WORD_DELIM) - { - token->opr.ctx_type = WORD_FIRST; - tree_first = create_token_tree (dfa, NULL, NULL, token); - token->opr.ctx_type = WORD_LAST; - } - else - { - token->opr.ctx_type = INSIDE_WORD; - tree_first = create_token_tree (dfa, NULL, NULL, token); - token->opr.ctx_type = INSIDE_NOTWORD; - } - tree_last = create_token_tree (dfa, NULL, NULL, token); - tree = create_tree (dfa, tree_first, tree_last, OP_ALT); - if (BE (tree_first == NULL || tree_last == NULL || tree == NULL, 0)) - { - *err = REG_ESPACE; - return NULL; - } - } - else - { - tree = create_token_tree (dfa, NULL, NULL, token); - if (BE (tree == NULL, 0)) - { - *err = REG_ESPACE; - return NULL; - } - } - /* We must return here, since ANCHORs can't be followed - by repetition operators. - eg. RE"^*" is invalid or "", - it must not be "". */ - fetch_token (token, regexp, syntax); - return tree; - case OP_PERIOD: - tree = create_token_tree (dfa, NULL, NULL, token); - if (BE (tree == NULL, 0)) - { - *err = REG_ESPACE; - return NULL; - } - if (dfa->mb_cur_max > 1) - dfa->has_mb_node = 1; - break; - case OP_WORD: - case OP_NOTWORD: - tree = build_charclass_op (dfa, regexp->trans, - "alnum", - "_", - token->type == OP_NOTWORD, err); - if (BE (*err != REG_NOERROR && tree == NULL, 0)) - return NULL; - break; - case OP_SPACE: - case OP_NOTSPACE: - tree = build_charclass_op (dfa, regexp->trans, - "space", - "", - token->type == OP_NOTSPACE, err); - if (BE (*err != REG_NOERROR && tree == NULL, 0)) - return NULL; - break; - case OP_ALT: - case END_OF_RE: - return NULL; - case BACK_SLASH: - *err = REG_EESCAPE; - return NULL; - default: - /* Must not happen? */ -#ifdef DEBUG - assert (0); -#endif - return NULL; - } - fetch_token (token, regexp, syntax); - - while (token->type == OP_DUP_ASTERISK || token->type == OP_DUP_PLUS - || token->type == OP_DUP_QUESTION || token->type == OP_OPEN_DUP_NUM) - { - tree = parse_dup_op (tree, regexp, dfa, token, syntax, err); - if (BE (*err != REG_NOERROR && tree == NULL, 0)) - return NULL; - /* In BRE consecutive duplications are not allowed. */ - if ((syntax & RE_CONTEXT_INVALID_DUP) - && (token->type == OP_DUP_ASTERISK - || token->type == OP_OPEN_DUP_NUM)) - { - *err = REG_BADRPT; - return NULL; - } - } - - return tree; -} - -/* This function build the following tree, from regular expression - (): - SUBEXP - | - -*/ - -static bin_tree_t * -parse_sub_exp (re_string_t *regexp, regex_t *preg, re_token_t *token, - reg_syntax_t syntax, int nest, reg_errcode_t *err) -{ - re_dfa_t *dfa = (re_dfa_t *) preg->buffer; - bin_tree_t *tree; - size_t cur_nsub; - cur_nsub = preg->re_nsub++; - - fetch_token (token, regexp, syntax | RE_CARET_ANCHORS_HERE); - - /* The subexpression may be a null string. */ - if (token->type == OP_CLOSE_SUBEXP) - tree = NULL; - else - { - tree = parse_reg_exp (regexp, preg, token, syntax, nest, err); - if (BE (*err == REG_NOERROR && token->type != OP_CLOSE_SUBEXP, 0)) - *err = REG_EPAREN; - if (BE (*err != REG_NOERROR, 0)) - return NULL; - } - - if (cur_nsub <= '9' - '1') - dfa->completed_bkref_map |= 1 << cur_nsub; - - tree = create_tree (dfa, tree, NULL, SUBEXP); - if (BE (tree == NULL, 0)) - { - *err = REG_ESPACE; - return NULL; - } - tree->token.opr.idx = cur_nsub; - return tree; -} - -/* This function parse repetition operators like "*", "+", "{1,3}" etc. */ - -static bin_tree_t * -parse_dup_op (bin_tree_t *elem, re_string_t *regexp, re_dfa_t *dfa, - re_token_t *token, reg_syntax_t syntax, reg_errcode_t *err) -{ - bin_tree_t *tree = NULL, *old_tree = NULL; - int i, start, end, start_idx = re_string_cur_idx (regexp); -#ifndef RE_TOKEN_INIT_BUG - re_token_t start_token = *token; -#else - re_token_t start_token; - - memcpy ((void *) &start_token, (void *) token, sizeof start_token); -#endif - - if (token->type == OP_OPEN_DUP_NUM) - { - end = 0; - start = fetch_number (regexp, token, syntax); - if (start == -1) - { - if (token->type == CHARACTER && token->opr.c == ',') - start = 0; /* We treat "{,m}" as "{0,m}". */ - else - { - *err = REG_BADBR; /* {} is invalid. */ - return NULL; - } - } - if (BE (start != -2, 1)) - { - /* We treat "{n}" as "{n,n}". */ - end = ((token->type == OP_CLOSE_DUP_NUM) ? start - : ((token->type == CHARACTER && token->opr.c == ',') - ? fetch_number (regexp, token, syntax) : -2)); - } - if (BE (start == -2 || end == -2, 0)) - { - /* Invalid sequence. */ - if (BE (!(syntax & RE_INVALID_INTERVAL_ORD), 0)) - { - if (token->type == END_OF_RE) - *err = REG_EBRACE; - else - *err = REG_BADBR; - - return NULL; - } - - /* If the syntax bit is set, rollback. */ - re_string_set_index (regexp, start_idx); - *token = start_token; - token->type = CHARACTER; - /* mb_partial and word_char bits should be already initialized by - peek_token. */ - return elem; - } - - if (BE ((end != -1 && start > end) || token->type != OP_CLOSE_DUP_NUM, 0)) - { - /* First number greater than second. */ - *err = REG_BADBR; - return NULL; - } - } - else - { - start = (token->type == OP_DUP_PLUS) ? 1 : 0; - end = (token->type == OP_DUP_QUESTION) ? 1 : -1; - } - - fetch_token (token, regexp, syntax); - - if (BE (elem == NULL, 0)) - return NULL; - if (BE (start == 0 && end == 0, 0)) - { - postorder (elem, free_tree, NULL); - return NULL; - } - - /* Extract "{n,m}" to "...{0,}". */ - if (BE (start > 0, 0)) - { - tree = elem; - for (i = 2; i <= start; ++i) - { - elem = duplicate_tree (elem, dfa); - tree = create_tree (dfa, tree, elem, CONCAT); - if (BE (elem == NULL || tree == NULL, 0)) - goto parse_dup_op_espace; - } - - if (start == end) - return tree; - - /* Duplicate ELEM before it is marked optional. */ - elem = duplicate_tree (elem, dfa); - old_tree = tree; - } - else - old_tree = NULL; - - if (elem->token.type == SUBEXP) - postorder (elem, mark_opt_subexp, (void *) (long) elem->token.opr.idx); - - tree = create_tree (dfa, elem, NULL, (end == -1 ? OP_DUP_ASTERISK : OP_ALT)); - if (BE (tree == NULL, 0)) - goto parse_dup_op_espace; - - /* This loop is actually executed only when end != -1, - to rewrite {0,n} as ((...?)?)?... We have - already created the start+1-th copy. */ - for (i = start + 2; i <= end; ++i) - { - elem = duplicate_tree (elem, dfa); - tree = create_tree (dfa, tree, elem, CONCAT); - if (BE (elem == NULL || tree == NULL, 0)) - goto parse_dup_op_espace; - - tree = create_tree (dfa, tree, NULL, OP_ALT); - if (BE (tree == NULL, 0)) - goto parse_dup_op_espace; - } - - if (old_tree) - tree = create_tree (dfa, old_tree, tree, CONCAT); - - return tree; - - parse_dup_op_espace: - *err = REG_ESPACE; - return NULL; -} - -/* Size of the names for collating symbol/equivalence_class/character_class. - I'm not sure, but maybe enough. */ -#define BRACKET_NAME_BUF_SIZE 32 - -#ifndef _LIBC - /* Local function for parse_bracket_exp only used in case of NOT _LIBC. - Build the range expression which starts from START_ELEM, and ends - at END_ELEM. The result are written to MBCSET and SBCSET. - RANGE_ALLOC is the allocated size of mbcset->range_starts, and - mbcset->range_ends, is a pointer argument sinse we may - update it. */ - -static reg_errcode_t -internal_function -# ifdef RE_ENABLE_I18N -build_range_exp (bitset_t sbcset, re_charset_t *mbcset, int *range_alloc, - bracket_elem_t *start_elem, bracket_elem_t *end_elem) -# else /* not RE_ENABLE_I18N */ -build_range_exp (bitset_t sbcset, bracket_elem_t *start_elem, - bracket_elem_t *end_elem) -# endif /* not RE_ENABLE_I18N */ -{ - unsigned int start_ch, end_ch; - /* Equivalence Classes and Character Classes can't be a range start/end. */ - if (BE (start_elem->type == EQUIV_CLASS || start_elem->type == CHAR_CLASS - || end_elem->type == EQUIV_CLASS || end_elem->type == CHAR_CLASS, - 0)) - return REG_ERANGE; - - /* We can handle no multi character collating elements without libc - support. */ - if (BE ((start_elem->type == COLL_SYM - && strlen ((char *) start_elem->opr.name) > 1) - || (end_elem->type == COLL_SYM - && strlen ((char *) end_elem->opr.name) > 1), 0)) - return REG_ECOLLATE; - -# ifdef RE_ENABLE_I18N - { - wchar_t wc; - wint_t start_wc; - wint_t end_wc; - wchar_t cmp_buf[6] = {L'\0', L'\0', L'\0', L'\0', L'\0', L'\0'}; - - start_ch = ((start_elem->type == SB_CHAR) ? start_elem->opr.ch - : ((start_elem->type == COLL_SYM) ? start_elem->opr.name[0] - : 0)); - end_ch = ((end_elem->type == SB_CHAR) ? end_elem->opr.ch - : ((end_elem->type == COLL_SYM) ? end_elem->opr.name[0] - : 0)); -#ifdef GAWK - /* - * Fedora Core 2, maybe others, have broken `btowc' that returns -1 - * for any value > 127. Sigh. Note that `start_ch' and `end_ch' are - * unsigned, so we don't have sign extension problems. - */ - start_wc = ((start_elem->type == SB_CHAR || start_elem->type == COLL_SYM) - ? start_ch : start_elem->opr.wch); - end_wc = ((end_elem->type == SB_CHAR || end_elem->type == COLL_SYM) - ? end_ch : end_elem->opr.wch); -#else - start_wc = ((start_elem->type == SB_CHAR || start_elem->type == COLL_SYM) - ? __btowc (start_ch) : start_elem->opr.wch); - end_wc = ((end_elem->type == SB_CHAR || end_elem->type == COLL_SYM) - ? __btowc (end_ch) : end_elem->opr.wch); -#endif - if (start_wc == WEOF || end_wc == WEOF) - return REG_ECOLLATE; - cmp_buf[0] = start_wc; - cmp_buf[4] = end_wc; - if (wcscoll (cmp_buf, cmp_buf + 4) > 0) - return REG_ERANGE; - - /* Got valid collation sequence values, add them as a new entry. - However, for !_LIBC we have no collation elements: if the - character set is single byte, the single byte character set - that we build below suffices. parse_bracket_exp passes - no MBCSET if dfa->mb_cur_max == 1. */ - if (mbcset) - { - /* Check the space of the arrays. */ - if (BE (*range_alloc == mbcset->nranges, 0)) - { - /* There is not enough space, need realloc. */ - wchar_t *new_array_start, *new_array_end; - int new_nranges; - - /* +1 in case of mbcset->nranges is 0. */ - new_nranges = 2 * mbcset->nranges + 1; - /* Use realloc since mbcset->range_starts and mbcset->range_ends - are NULL if *range_alloc == 0. */ - new_array_start = re_realloc (mbcset->range_starts, wchar_t, - new_nranges); - new_array_end = re_realloc (mbcset->range_ends, wchar_t, - new_nranges); - - if (BE (new_array_start == NULL || new_array_end == NULL, 0)) - return REG_ESPACE; - - mbcset->range_starts = new_array_start; - mbcset->range_ends = new_array_end; - *range_alloc = new_nranges; - } - - mbcset->range_starts[mbcset->nranges] = start_wc; - mbcset->range_ends[mbcset->nranges++] = end_wc; - } - - /* Build the table for single byte characters. */ - for (wc = 0; wc < SBC_MAX; ++wc) - { - cmp_buf[2] = wc; - if (wcscoll (cmp_buf, cmp_buf + 2) <= 0 - && wcscoll (cmp_buf + 2, cmp_buf + 4) <= 0) - bitset_set (sbcset, wc); - } - } -# else /* not RE_ENABLE_I18N */ - { - unsigned int ch; - start_ch = ((start_elem->type == SB_CHAR ) ? start_elem->opr.ch - : ((start_elem->type == COLL_SYM) ? start_elem->opr.name[0] - : 0)); - end_ch = ((end_elem->type == SB_CHAR ) ? end_elem->opr.ch - : ((end_elem->type == COLL_SYM) ? end_elem->opr.name[0] - : 0)); - if (start_ch > end_ch) - return REG_ERANGE; - /* Build the table for single byte characters. */ - for (ch = 0; ch < SBC_MAX; ++ch) - if (start_ch <= ch && ch <= end_ch) - bitset_set (sbcset, ch); - } -# endif /* not RE_ENABLE_I18N */ - return REG_NOERROR; -} -#endif /* not _LIBC */ - -#ifndef _LIBC -/* Helper function for parse_bracket_exp only used in case of NOT _LIBC.. - Build the collating element which is represented by NAME. - The result are written to MBCSET and SBCSET. - COLL_SYM_ALLOC is the allocated size of mbcset->coll_sym, is a - pointer argument since we may update it. */ - -static reg_errcode_t -internal_function -# ifdef RE_ENABLE_I18N -build_collating_symbol (bitset_t sbcset, re_charset_t *mbcset, - int *coll_sym_alloc, const unsigned char *name) -# else /* not RE_ENABLE_I18N */ -build_collating_symbol (bitset_t sbcset, const unsigned char *name) -# endif /* not RE_ENABLE_I18N */ -{ - size_t name_len = strlen ((const char *) name); - if (BE (name_len != 1, 0)) - return REG_ECOLLATE; - else - { - bitset_set (sbcset, name[0]); - return REG_NOERROR; - } -} -#endif /* not _LIBC */ - -/* This function parse bracket expression like "[abc]", "[a-c]", - "[[.a-a.]]" etc. */ - -static bin_tree_t * -parse_bracket_exp (re_string_t *regexp, re_dfa_t *dfa, re_token_t *token, - reg_syntax_t syntax, reg_errcode_t *err) -{ -#ifdef _LIBC - const unsigned char *collseqmb; - const char *collseqwc; - uint32_t nrules; - int32_t table_size; - const int32_t *symb_table; - const unsigned char *extra; - - /* Local function for parse_bracket_exp used in _LIBC environement. - Seek the collating symbol entry correspondings to NAME. - Return the index of the symbol in the SYMB_TABLE. */ - - auto inline int32_t - __attribute ((always_inline)) - seek_collating_symbol_entry (name, name_len) - const unsigned char *name; - size_t name_len; - { - int32_t hash = elem_hash ((const char *) name, name_len); - int32_t elem = hash % table_size; - if (symb_table[2 * elem] != 0) - { - int32_t second = hash % (table_size - 2) + 1; - - do - { - /* First compare the hashing value. */ - if (symb_table[2 * elem] == hash - /* Compare the length of the name. */ - && name_len == extra[symb_table[2 * elem + 1]] - /* Compare the name. */ - && memcmp (name, &extra[symb_table[2 * elem + 1] + 1], - name_len) == 0) - { - /* Yep, this is the entry. */ - break; - } - - /* Next entry. */ - elem += second; - } - while (symb_table[2 * elem] != 0); - } - return elem; - } - - /* Local function for parse_bracket_exp used in _LIBC environment. - Look up the collation sequence value of BR_ELEM. - Return the value if succeeded, UINT_MAX otherwise. */ - - auto inline unsigned int - __attribute ((always_inline)) - lookup_collation_sequence_value (br_elem) - bracket_elem_t *br_elem; - { - if (br_elem->type == SB_CHAR) - { - /* - if (MB_CUR_MAX == 1) - */ - if (nrules == 0) - return collseqmb[br_elem->opr.ch]; - else - { - wint_t wc = __btowc (br_elem->opr.ch); - return __collseq_table_lookup (collseqwc, wc); - } - } - else if (br_elem->type == MB_CHAR) - { - if (nrules != 0) - return __collseq_table_lookup (collseqwc, br_elem->opr.wch); - } - else if (br_elem->type == COLL_SYM) - { - size_t sym_name_len = strlen ((char *) br_elem->opr.name); - if (nrules != 0) - { - int32_t elem, idx; - elem = seek_collating_symbol_entry (br_elem->opr.name, - sym_name_len); - if (symb_table[2 * elem] != 0) - { - /* We found the entry. */ - idx = symb_table[2 * elem + 1]; - /* Skip the name of collating element name. */ - idx += 1 + extra[idx]; - /* Skip the byte sequence of the collating element. */ - idx += 1 + extra[idx]; - /* Adjust for the alignment. */ - idx = (idx + 3) & ~3; - /* Skip the multibyte collation sequence value. */ - idx += sizeof (unsigned int); - /* Skip the wide char sequence of the collating element. */ - idx += sizeof (unsigned int) * - (1 + *(unsigned int *) (extra + idx)); - /* Return the collation sequence value. */ - return *(unsigned int *) (extra + idx); - } - else if (symb_table[2 * elem] == 0 && sym_name_len == 1) - { - /* No valid character. Match it as a single byte - character. */ - return collseqmb[br_elem->opr.name[0]]; - } - } - else if (sym_name_len == 1) - return collseqmb[br_elem->opr.name[0]]; - } - return UINT_MAX; - } - - /* Local function for parse_bracket_exp used in _LIBC environement. - Build the range expression which starts from START_ELEM, and ends - at END_ELEM. The result are written to MBCSET and SBCSET. - RANGE_ALLOC is the allocated size of mbcset->range_starts, and - mbcset->range_ends, is a pointer argument sinse we may - update it. */ - - auto inline reg_errcode_t - __attribute ((always_inline)) - build_range_exp (sbcset, mbcset, range_alloc, start_elem, end_elem) - re_charset_t *mbcset; - int *range_alloc; - bitset_t sbcset; - bracket_elem_t *start_elem, *end_elem; - { - unsigned int ch; - uint32_t start_collseq; - uint32_t end_collseq; - - /* Equivalence Classes and Character Classes can't be a range - start/end. */ - if (BE (start_elem->type == EQUIV_CLASS || start_elem->type == CHAR_CLASS - || end_elem->type == EQUIV_CLASS || end_elem->type == CHAR_CLASS, - 0)) - return REG_ERANGE; - - start_collseq = lookup_collation_sequence_value (start_elem); - end_collseq = lookup_collation_sequence_value (end_elem); - /* Check start/end collation sequence values. */ - if (BE (start_collseq == UINT_MAX || end_collseq == UINT_MAX, 0)) - return REG_ECOLLATE; - if (BE ((syntax & RE_NO_EMPTY_RANGES) && start_collseq > end_collseq, 0)) - return REG_ERANGE; - - /* Got valid collation sequence values, add them as a new entry. - However, if we have no collation elements, and the character set - is single byte, the single byte character set that we - build below suffices. */ - if (nrules > 0 || dfa->mb_cur_max > 1) - { - /* Check the space of the arrays. */ - if (BE (*range_alloc == mbcset->nranges, 0)) - { - /* There is not enough space, need realloc. */ - uint32_t *new_array_start; - uint32_t *new_array_end; - int new_nranges; - - /* +1 in case of mbcset->nranges is 0. */ - new_nranges = 2 * mbcset->nranges + 1; - new_array_start = re_realloc (mbcset->range_starts, uint32_t, - new_nranges); - new_array_end = re_realloc (mbcset->range_ends, uint32_t, - new_nranges); - - if (BE (new_array_start == NULL || new_array_end == NULL, 0)) - return REG_ESPACE; - - mbcset->range_starts = new_array_start; - mbcset->range_ends = new_array_end; - *range_alloc = new_nranges; - } - - mbcset->range_starts[mbcset->nranges] = start_collseq; - mbcset->range_ends[mbcset->nranges++] = end_collseq; - } - - /* Build the table for single byte characters. */ - for (ch = 0; ch < SBC_MAX; ch++) - { - uint32_t ch_collseq; - /* - if (MB_CUR_MAX == 1) - */ - if (nrules == 0) - ch_collseq = collseqmb[ch]; - else - ch_collseq = __collseq_table_lookup (collseqwc, __btowc (ch)); - if (start_collseq <= ch_collseq && ch_collseq <= end_collseq) - bitset_set (sbcset, ch); - } - return REG_NOERROR; - } - - /* Local function for parse_bracket_exp used in _LIBC environement. - Build the collating element which is represented by NAME. - The result are written to MBCSET and SBCSET. - COLL_SYM_ALLOC is the allocated size of mbcset->coll_sym, is a - pointer argument sinse we may update it. */ - - auto inline reg_errcode_t - __attribute ((always_inline)) - build_collating_symbol (sbcset, mbcset, coll_sym_alloc, name) - re_charset_t *mbcset; - int *coll_sym_alloc; - bitset_t sbcset; - const unsigned char *name; - { - int32_t elem, idx; - size_t name_len = strlen ((const char *) name); - if (nrules != 0) - { - elem = seek_collating_symbol_entry (name, name_len); - if (symb_table[2 * elem] != 0) - { - /* We found the entry. */ - idx = symb_table[2 * elem + 1]; - /* Skip the name of collating element name. */ - idx += 1 + extra[idx]; - } - else if (symb_table[2 * elem] == 0 && name_len == 1) - { - /* No valid character, treat it as a normal - character. */ - bitset_set (sbcset, name[0]); - return REG_NOERROR; - } - else - return REG_ECOLLATE; - - /* Got valid collation sequence, add it as a new entry. */ - /* Check the space of the arrays. */ - if (BE (*coll_sym_alloc == mbcset->ncoll_syms, 0)) - { - /* Not enough, realloc it. */ - /* +1 in case of mbcset->ncoll_syms is 0. */ - int new_coll_sym_alloc = 2 * mbcset->ncoll_syms + 1; - /* Use realloc since mbcset->coll_syms is NULL - if *alloc == 0. */ - int32_t *new_coll_syms = re_realloc (mbcset->coll_syms, int32_t, - new_coll_sym_alloc); - if (BE (new_coll_syms == NULL, 0)) - return REG_ESPACE; - mbcset->coll_syms = new_coll_syms; - *coll_sym_alloc = new_coll_sym_alloc; - } - mbcset->coll_syms[mbcset->ncoll_syms++] = idx; - return REG_NOERROR; - } - else - { - if (BE (name_len != 1, 0)) - return REG_ECOLLATE; - else - { - bitset_set (sbcset, name[0]); - return REG_NOERROR; - } - } - } -#endif - - re_token_t br_token; - re_bitset_ptr_t sbcset; -#ifdef RE_ENABLE_I18N - re_charset_t *mbcset; - int coll_sym_alloc = 0, range_alloc = 0, mbchar_alloc = 0; - int equiv_class_alloc = 0, char_class_alloc = 0; -#endif /* not RE_ENABLE_I18N */ - int non_match = 0; - bin_tree_t *work_tree; - int token_len; - int first_round = 1; -#ifdef _LIBC - collseqmb = (const unsigned char *) - _NL_CURRENT (LC_COLLATE, _NL_COLLATE_COLLSEQMB); - nrules = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES); - if (nrules) - { - /* - if (MB_CUR_MAX > 1) - */ - collseqwc = _NL_CURRENT (LC_COLLATE, _NL_COLLATE_COLLSEQWC); - table_size = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_SYMB_HASH_SIZEMB); - symb_table = (const int32_t *) _NL_CURRENT (LC_COLLATE, - _NL_COLLATE_SYMB_TABLEMB); - extra = (const unsigned char *) _NL_CURRENT (LC_COLLATE, - _NL_COLLATE_SYMB_EXTRAMB); - } -#endif - sbcset = (re_bitset_ptr_t) calloc (sizeof (bitset_t), 1); -#ifdef RE_ENABLE_I18N - mbcset = (re_charset_t *) calloc (sizeof (re_charset_t), 1); -#endif /* RE_ENABLE_I18N */ -#ifdef RE_ENABLE_I18N - if (BE (sbcset == NULL || mbcset == NULL, 0)) -#else - if (BE (sbcset == NULL, 0)) -#endif /* RE_ENABLE_I18N */ - { - *err = REG_ESPACE; - return NULL; - } - - token_len = peek_token_bracket (token, regexp, syntax); - if (BE (token->type == END_OF_RE, 0)) - { - *err = REG_BADPAT; - goto parse_bracket_exp_free_return; - } - if (token->type == OP_NON_MATCH_LIST) - { -#ifdef RE_ENABLE_I18N - mbcset->non_match = 1; -#endif /* not RE_ENABLE_I18N */ - non_match = 1; - if (syntax & RE_HAT_LISTS_NOT_NEWLINE) - bitset_set (sbcset, '\n'); - re_string_skip_bytes (regexp, token_len); /* Skip a token. */ - token_len = peek_token_bracket (token, regexp, syntax); - if (BE (token->type == END_OF_RE, 0)) - { - *err = REG_BADPAT; - goto parse_bracket_exp_free_return; - } - } - - /* We treat the first ']' as a normal character. */ - if (token->type == OP_CLOSE_BRACKET) - token->type = CHARACTER; - - while (1) - { - bracket_elem_t start_elem, end_elem; - unsigned char start_name_buf[BRACKET_NAME_BUF_SIZE]; - unsigned char end_name_buf[BRACKET_NAME_BUF_SIZE]; - reg_errcode_t ret; - int token_len2 = 0, is_range_exp = 0; - re_token_t token2; - - start_elem.opr.name = start_name_buf; - ret = parse_bracket_element (&start_elem, regexp, token, token_len, dfa, - syntax, first_round); - if (BE (ret != REG_NOERROR, 0)) - { - *err = ret; - goto parse_bracket_exp_free_return; - } - first_round = 0; - - /* Get information about the next token. We need it in any case. */ - token_len = peek_token_bracket (token, regexp, syntax); - - /* Do not check for ranges if we know they are not allowed. */ - if (start_elem.type != CHAR_CLASS && start_elem.type != EQUIV_CLASS) - { - if (BE (token->type == END_OF_RE, 0)) - { - *err = REG_EBRACK; - goto parse_bracket_exp_free_return; - } - if (token->type == OP_CHARSET_RANGE) - { - re_string_skip_bytes (regexp, token_len); /* Skip '-'. */ - token_len2 = peek_token_bracket (&token2, regexp, syntax); - if (BE (token2.type == END_OF_RE, 0)) - { - *err = REG_EBRACK; - goto parse_bracket_exp_free_return; - } - if (token2.type == OP_CLOSE_BRACKET) - { - /* We treat the last '-' as a normal character. */ - re_string_skip_bytes (regexp, -token_len); - token->type = CHARACTER; - } - else - is_range_exp = 1; - } - } - - if (is_range_exp == 1) - { - end_elem.opr.name = end_name_buf; - ret = parse_bracket_element (&end_elem, regexp, &token2, token_len2, - dfa, syntax, 1); - if (BE (ret != REG_NOERROR, 0)) - { - *err = ret; - goto parse_bracket_exp_free_return; - } - - token_len = peek_token_bracket (token, regexp, syntax); - -#ifdef _LIBC - *err = build_range_exp (sbcset, mbcset, &range_alloc, - &start_elem, &end_elem); -#else -# ifdef RE_ENABLE_I18N - *err = build_range_exp (sbcset, - dfa->mb_cur_max > 1 ? mbcset : NULL, - &range_alloc, &start_elem, &end_elem); -# else - *err = build_range_exp (sbcset, &start_elem, &end_elem); -# endif -#endif /* RE_ENABLE_I18N */ - if (BE (*err != REG_NOERROR, 0)) - goto parse_bracket_exp_free_return; - } - else - { - switch (start_elem.type) - { - case SB_CHAR: - bitset_set (sbcset, start_elem.opr.ch); - break; -#ifdef RE_ENABLE_I18N - case MB_CHAR: - /* Check whether the array has enough space. */ - if (BE (mbchar_alloc == mbcset->nmbchars, 0)) - { - wchar_t *new_mbchars; - /* Not enough, realloc it. */ - /* +1 in case of mbcset->nmbchars is 0. */ - mbchar_alloc = 2 * mbcset->nmbchars + 1; - /* Use realloc since array is NULL if *alloc == 0. */ - new_mbchars = re_realloc (mbcset->mbchars, wchar_t, - mbchar_alloc); - if (BE (new_mbchars == NULL, 0)) - goto parse_bracket_exp_espace; - mbcset->mbchars = new_mbchars; - } - mbcset->mbchars[mbcset->nmbchars++] = start_elem.opr.wch; - break; -#endif /* RE_ENABLE_I18N */ - case EQUIV_CLASS: - *err = build_equiv_class (sbcset, -#ifdef RE_ENABLE_I18N - mbcset, &equiv_class_alloc, -#endif /* RE_ENABLE_I18N */ - start_elem.opr.name); - if (BE (*err != REG_NOERROR, 0)) - goto parse_bracket_exp_free_return; - break; - case COLL_SYM: - *err = build_collating_symbol (sbcset, -#ifdef RE_ENABLE_I18N - mbcset, &coll_sym_alloc, -#endif /* RE_ENABLE_I18N */ - start_elem.opr.name); - if (BE (*err != REG_NOERROR, 0)) - goto parse_bracket_exp_free_return; - break; - case CHAR_CLASS: - *err = build_charclass (regexp->trans, sbcset, -#ifdef RE_ENABLE_I18N - mbcset, &char_class_alloc, -#endif /* RE_ENABLE_I18N */ - (const char *) start_elem.opr.name, syntax); - if (BE (*err != REG_NOERROR, 0)) - goto parse_bracket_exp_free_return; - break; - default: - assert (0); - break; - } - } - if (BE (token->type == END_OF_RE, 0)) - { - *err = REG_EBRACK; - goto parse_bracket_exp_free_return; - } - if (token->type == OP_CLOSE_BRACKET) - break; - } - - re_string_skip_bytes (regexp, token_len); /* Skip a token. */ - - /* If it is non-matching list. */ - if (non_match) - bitset_not (sbcset); - -#ifdef RE_ENABLE_I18N - /* Ensure only single byte characters are set. */ - if (dfa->mb_cur_max > 1) - bitset_mask (sbcset, dfa->sb_char); - - if (mbcset->nmbchars || mbcset->ncoll_syms || mbcset->nequiv_classes - || mbcset->nranges || (dfa->mb_cur_max > 1 && (mbcset->nchar_classes - || mbcset->non_match))) - { - bin_tree_t *mbc_tree; - int sbc_idx; - /* Build a tree for complex bracket. */ - dfa->has_mb_node = 1; - br_token.type = COMPLEX_BRACKET; - br_token.opr.mbcset = mbcset; - mbc_tree = create_token_tree (dfa, NULL, NULL, &br_token); - if (BE (mbc_tree == NULL, 0)) - goto parse_bracket_exp_espace; - for (sbc_idx = 0; sbc_idx < BITSET_WORDS; ++sbc_idx) - if (sbcset[sbc_idx]) - break; - /* If there are no bits set in sbcset, there is no point - of having both SIMPLE_BRACKET and COMPLEX_BRACKET. */ - if (sbc_idx < BITSET_WORDS) - { - /* Build a tree for simple bracket. */ - br_token.type = SIMPLE_BRACKET; - br_token.opr.sbcset = sbcset; - work_tree = create_token_tree (dfa, NULL, NULL, &br_token); - if (BE (work_tree == NULL, 0)) - goto parse_bracket_exp_espace; - - /* Then join them by ALT node. */ - work_tree = create_tree (dfa, work_tree, mbc_tree, OP_ALT); - if (BE (work_tree == NULL, 0)) - goto parse_bracket_exp_espace; - } - else - { - re_free (sbcset); - work_tree = mbc_tree; - } - } - else -#endif /* not RE_ENABLE_I18N */ - { -#ifdef RE_ENABLE_I18N - free_charset (mbcset); -#endif - /* Build a tree for simple bracket. */ - br_token.type = SIMPLE_BRACKET; - br_token.opr.sbcset = sbcset; - work_tree = create_token_tree (dfa, NULL, NULL, &br_token); - if (BE (work_tree == NULL, 0)) - goto parse_bracket_exp_espace; - } - return work_tree; - - parse_bracket_exp_espace: - *err = REG_ESPACE; - parse_bracket_exp_free_return: - re_free (sbcset); -#ifdef RE_ENABLE_I18N - free_charset (mbcset); -#endif /* RE_ENABLE_I18N */ - return NULL; -} - -/* Parse an element in the bracket expression. */ - -static reg_errcode_t -parse_bracket_element (bracket_elem_t *elem, re_string_t *regexp, - re_token_t *token, int token_len, UNUSED re_dfa_t *dfa, - reg_syntax_t syntax, int accept_hyphen) -{ -#ifdef RE_ENABLE_I18N - int cur_char_size; - cur_char_size = re_string_char_size_at (regexp, re_string_cur_idx (regexp)); - if (cur_char_size > 1) - { - elem->type = MB_CHAR; - elem->opr.wch = re_string_wchar_at (regexp, re_string_cur_idx (regexp)); - re_string_skip_bytes (regexp, cur_char_size); - return REG_NOERROR; - } -#endif /* RE_ENABLE_I18N */ - re_string_skip_bytes (regexp, token_len); /* Skip a token. */ - if (token->type == OP_OPEN_COLL_ELEM || token->type == OP_OPEN_CHAR_CLASS - || token->type == OP_OPEN_EQUIV_CLASS) - return parse_bracket_symbol (elem, regexp, token); - if (BE (token->type == OP_CHARSET_RANGE, 0) && !accept_hyphen) - { - /* A '-' must only appear as anything but a range indicator before - the closing bracket. Everything else is an error. */ - re_token_t token2; - (void) peek_token_bracket (&token2, regexp, syntax); - if (token2.type != OP_CLOSE_BRACKET) - /* The actual error value is not standardized since this whole - case is undefined. But ERANGE makes good sense. */ - return REG_ERANGE; - } - elem->type = SB_CHAR; - elem->opr.ch = token->opr.c; - return REG_NOERROR; -} - -/* Parse a bracket symbol in the bracket expression. Bracket symbols are - such as [::], [..], and - [==]. */ - -static reg_errcode_t -parse_bracket_symbol (bracket_elem_t *elem, re_string_t *regexp, - re_token_t *token) -{ - unsigned char ch, delim = token->opr.c; - int i = 0; - if (re_string_eoi(regexp)) - return REG_EBRACK; - for (;; ++i) - { - if (i >= BRACKET_NAME_BUF_SIZE) - return REG_EBRACK; - if (token->type == OP_OPEN_CHAR_CLASS) - ch = re_string_fetch_byte_case (regexp); - else - ch = re_string_fetch_byte (regexp); - if (re_string_eoi(regexp)) - return REG_EBRACK; - if (ch == delim && re_string_peek_byte (regexp, 0) == ']') - break; - elem->opr.name[i] = ch; - } - re_string_skip_bytes (regexp, 1); - elem->opr.name[i] = '\0'; - switch (token->type) - { - case OP_OPEN_COLL_ELEM: - elem->type = COLL_SYM; - break; - case OP_OPEN_EQUIV_CLASS: - elem->type = EQUIV_CLASS; - break; - case OP_OPEN_CHAR_CLASS: - elem->type = CHAR_CLASS; - break; - default: - break; - } - return REG_NOERROR; -} - - /* Helper function for parse_bracket_exp. - Build the equivalence class which is represented by NAME. - The result are written to MBCSET and SBCSET. - EQUIV_CLASS_ALLOC is the allocated size of mbcset->equiv_classes, - is a pointer argument sinse we may update it. */ - -static reg_errcode_t -#ifdef RE_ENABLE_I18N -build_equiv_class (bitset_t sbcset, re_charset_t *mbcset, - int *equiv_class_alloc, const unsigned char *name) -#else /* not RE_ENABLE_I18N */ -build_equiv_class (bitset_t sbcset, const unsigned char *name) -#endif /* not RE_ENABLE_I18N */ -{ -#ifdef _LIBC - uint32_t nrules = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES); - if (nrules != 0) - { - const int32_t *table, *indirect; - const unsigned char *weights, *extra, *cp; - unsigned char char_buf[2]; - int32_t idx1, idx2; - unsigned int ch; - size_t len; - /* This #include defines a local function! */ -# include - /* Calculate the index for equivalence class. */ - cp = name; - table = (const int32_t *) _NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEMB); - weights = (const unsigned char *) _NL_CURRENT (LC_COLLATE, - _NL_COLLATE_WEIGHTMB); - extra = (const unsigned char *) _NL_CURRENT (LC_COLLATE, - _NL_COLLATE_EXTRAMB); - indirect = (const int32_t *) _NL_CURRENT (LC_COLLATE, - _NL_COLLATE_INDIRECTMB); - idx1 = findidx (&cp); - if (BE (idx1 == 0 || cp < name + strlen ((const char *) name), 0)) - /* This isn't a valid character. */ - return REG_ECOLLATE; - - /* Build single byte matcing table for this equivalence class. */ - char_buf[1] = (unsigned char) '\0'; - len = weights[idx1 & 0xffffff]; - for (ch = 0; ch < SBC_MAX; ++ch) - { - char_buf[0] = ch; - cp = char_buf; - idx2 = findidx (&cp); -/* - idx2 = table[ch]; -*/ - if (idx2 == 0) - /* This isn't a valid character. */ - continue; - /* Compare only if the length matches and the collation rule - index is the same. */ - if (len == weights[idx2 & 0xffffff] && (idx1 >> 24) == (idx2 >> 24)) - { - int cnt = 0; - - while (cnt <= len && - weights[(idx1 & 0xffffff) + 1 + cnt] - == weights[(idx2 & 0xffffff) + 1 + cnt]) - ++cnt; - - if (cnt > len) - bitset_set (sbcset, ch); - } - } - /* Check whether the array has enough space. */ - if (BE (*equiv_class_alloc == mbcset->nequiv_classes, 0)) - { - /* Not enough, realloc it. */ - /* +1 in case of mbcset->nequiv_classes is 0. */ - int new_equiv_class_alloc = 2 * mbcset->nequiv_classes + 1; - /* Use realloc since the array is NULL if *alloc == 0. */ - int32_t *new_equiv_classes = re_realloc (mbcset->equiv_classes, - int32_t, - new_equiv_class_alloc); - if (BE (new_equiv_classes == NULL, 0)) - return REG_ESPACE; - mbcset->equiv_classes = new_equiv_classes; - *equiv_class_alloc = new_equiv_class_alloc; - } - mbcset->equiv_classes[mbcset->nequiv_classes++] = idx1; - } - else -#endif /* _LIBC */ - { - if (BE (strlen ((const char *) name) != 1, 0)) - return REG_ECOLLATE; - bitset_set (sbcset, *name); - } - return REG_NOERROR; -} - - /* Helper function for parse_bracket_exp. - Build the character class which is represented by NAME. - The result are written to MBCSET and SBCSET. - CHAR_CLASS_ALLOC is the allocated size of mbcset->char_classes, - is a pointer argument sinse we may update it. */ - -static reg_errcode_t -#ifdef RE_ENABLE_I18N -build_charclass (RE_TRANSLATE_TYPE trans, bitset_t sbcset, - re_charset_t *mbcset, int *char_class_alloc, - const char *class_name, reg_syntax_t syntax) -#else /* not RE_ENABLE_I18N */ -build_charclass (RE_TRANSLATE_TYPE trans, bitset_t sbcset, - const char *class_name, reg_syntax_t syntax) -#endif /* not RE_ENABLE_I18N */ -{ - int i; - - /* In case of REG_ICASE "upper" and "lower" match the both of - upper and lower cases. */ - if ((syntax & RE_ICASE) - && (strcmp (class_name, "upper") == 0 || strcmp (class_name, "lower") == 0)) - class_name = "alpha"; - -#ifdef RE_ENABLE_I18N - /* Check the space of the arrays. */ - if (BE (*char_class_alloc == mbcset->nchar_classes, 0)) - { - /* Not enough, realloc it. */ - /* +1 in case of mbcset->nchar_classes is 0. */ - int new_char_class_alloc = 2 * mbcset->nchar_classes + 1; - /* Use realloc since array is NULL if *alloc == 0. */ - wctype_t *new_char_classes = re_realloc (mbcset->char_classes, wctype_t, - new_char_class_alloc); - if (BE (new_char_classes == NULL, 0)) - return REG_ESPACE; - mbcset->char_classes = new_char_classes; - *char_class_alloc = new_char_class_alloc; - } - mbcset->char_classes[mbcset->nchar_classes++] = __wctype (class_name); -#endif /* RE_ENABLE_I18N */ - -#define BUILD_CHARCLASS_LOOP(ctype_func) \ - do { \ - if (BE (trans != NULL, 0)) \ - { \ - for (i = 0; i < SBC_MAX; ++i) \ - if (ctype_func (i)) \ - bitset_set (sbcset, trans[i]); \ - } \ - else \ - { \ - for (i = 0; i < SBC_MAX; ++i) \ - if (ctype_func (i)) \ - bitset_set (sbcset, i); \ - } \ - } while (0) - - if (strcmp (class_name, "alnum") == 0) - BUILD_CHARCLASS_LOOP (isalnum); - else if (strcmp (class_name, "cntrl") == 0) - BUILD_CHARCLASS_LOOP (iscntrl); - else if (strcmp (class_name, "lower") == 0) - BUILD_CHARCLASS_LOOP (islower); - else if (strcmp (class_name, "space") == 0) - BUILD_CHARCLASS_LOOP (isspace); - else if (strcmp (class_name, "alpha") == 0) - BUILD_CHARCLASS_LOOP (isalpha); - else if (strcmp (class_name, "digit") == 0) - BUILD_CHARCLASS_LOOP (isdigit); - else if (strcmp (class_name, "print") == 0) - BUILD_CHARCLASS_LOOP (isprint); - else if (strcmp (class_name, "upper") == 0) - BUILD_CHARCLASS_LOOP (isupper); - else if (strcmp (class_name, "blank") == 0) -#ifndef GAWK - BUILD_CHARCLASS_LOOP (isblank); -#else - /* see comments above */ - BUILD_CHARCLASS_LOOP (is_blank); -#endif - else if (strcmp (class_name, "graph") == 0) - BUILD_CHARCLASS_LOOP (isgraph); - else if (strcmp (class_name, "punct") == 0) - BUILD_CHARCLASS_LOOP (ispunct); - else if (strcmp (class_name, "xdigit") == 0) - BUILD_CHARCLASS_LOOP (isxdigit); - else - return REG_ECTYPE; - - return REG_NOERROR; -} - -static bin_tree_t * -build_charclass_op (re_dfa_t *dfa, RE_TRANSLATE_TYPE trans, - const char *class_name, - const char *extra, int non_match, - reg_errcode_t *err) -{ - re_bitset_ptr_t sbcset; -#ifdef RE_ENABLE_I18N - re_charset_t *mbcset; - int alloc = 0; -#endif /* not RE_ENABLE_I18N */ - reg_errcode_t ret; - re_token_t br_token; - bin_tree_t *tree; - - sbcset = (re_bitset_ptr_t) calloc (sizeof (bitset_t), 1); -#ifdef RE_ENABLE_I18N - mbcset = (re_charset_t *) calloc (sizeof (re_charset_t), 1); -#endif /* RE_ENABLE_I18N */ - -#ifdef RE_ENABLE_I18N - if (BE (sbcset == NULL || mbcset == NULL, 0)) -#else /* not RE_ENABLE_I18N */ - if (BE (sbcset == NULL, 0)) -#endif /* not RE_ENABLE_I18N */ - { - *err = REG_ESPACE; - return NULL; - } - - if (non_match) - { -#ifdef RE_ENABLE_I18N - mbcset->non_match = 1; -#endif /* not RE_ENABLE_I18N */ - } - - /* We don't care the syntax in this case. */ - ret = build_charclass (trans, sbcset, -#ifdef RE_ENABLE_I18N - mbcset, &alloc, -#endif /* RE_ENABLE_I18N */ - class_name, 0); - - if (BE (ret != REG_NOERROR, 0)) - { - re_free (sbcset); -#ifdef RE_ENABLE_I18N - free_charset (mbcset); -#endif /* RE_ENABLE_I18N */ - *err = ret; - return NULL; - } - /* \w match '_' also. */ - for (; *extra; extra++) - bitset_set (sbcset, *extra); - - /* If it is non-matching list. */ - if (non_match) - bitset_not (sbcset); - -#ifdef RE_ENABLE_I18N - /* Ensure only single byte characters are set. */ - if (dfa->mb_cur_max > 1) - bitset_mask (sbcset, dfa->sb_char); -#endif - - /* Build a tree for simple bracket. */ - br_token.type = SIMPLE_BRACKET; - br_token.opr.sbcset = sbcset; - tree = create_token_tree (dfa, NULL, NULL, &br_token); - if (BE (tree == NULL, 0)) - goto build_word_op_espace; - -#ifdef RE_ENABLE_I18N - if (dfa->mb_cur_max > 1) - { - bin_tree_t *mbc_tree; - /* Build a tree for complex bracket. */ - br_token.type = COMPLEX_BRACKET; - br_token.opr.mbcset = mbcset; - dfa->has_mb_node = 1; - mbc_tree = create_token_tree (dfa, NULL, NULL, &br_token); - if (BE (mbc_tree == NULL, 0)) - goto build_word_op_espace; - /* Then join them by ALT node. */ - tree = create_tree (dfa, tree, mbc_tree, OP_ALT); - if (BE (mbc_tree != NULL, 1)) - return tree; - } - else - { - free_charset (mbcset); - return tree; - } -#else /* not RE_ENABLE_I18N */ - return tree; -#endif /* not RE_ENABLE_I18N */ - - build_word_op_espace: - re_free (sbcset); -#ifdef RE_ENABLE_I18N - free_charset (mbcset); -#endif /* RE_ENABLE_I18N */ - *err = REG_ESPACE; - return NULL; -} - -/* This is intended for the expressions like "a{1,3}". - Fetch a number from `input', and return the number. - Return -1, if the number field is empty like "{,1}". - Return -2, If an error is occured. */ - -static int -fetch_number (re_string_t *input, re_token_t *token, reg_syntax_t syntax) -{ - int num = -1; - unsigned char c; - while (1) - { - fetch_token (token, input, syntax); - c = token->opr.c; - if (BE (token->type == END_OF_RE, 0)) - return -2; - if (token->type == OP_CLOSE_DUP_NUM || c == ',') - break; - num = ((token->type != CHARACTER || c < '0' || '9' < c || num == -2) - ? -2 : ((num == -1) ? c - '0' : num * 10 + c - '0')); - num = (num > RE_DUP_MAX) ? -2 : num; - } - return num; -} - -#ifdef RE_ENABLE_I18N -static void -free_charset (re_charset_t *cset) -{ - re_free (cset->mbchars); -# ifdef _LIBC - re_free (cset->coll_syms); - re_free (cset->equiv_classes); - re_free (cset->range_starts); - re_free (cset->range_ends); -# endif - re_free (cset->char_classes); - re_free (cset); -} -#endif /* RE_ENABLE_I18N */ - -/* Functions for binary tree operation. */ - -/* Create a tree node. */ - -static bin_tree_t * -create_tree (re_dfa_t *dfa, bin_tree_t *left, bin_tree_t *right, - re_token_type_t type) -{ - re_token_t t; - t.type = type; - return create_token_tree (dfa, left, right, &t); -} - -static bin_tree_t * -create_token_tree (re_dfa_t *dfa, bin_tree_t *left, bin_tree_t *right, - const re_token_t *token) -{ - bin_tree_t *tree; - if (BE (dfa->str_tree_storage_idx == BIN_TREE_STORAGE_SIZE, 0)) - { - bin_tree_storage_t *storage = re_malloc (bin_tree_storage_t, 1); - - if (storage == NULL) - return NULL; - storage->next = dfa->str_tree_storage; - dfa->str_tree_storage = storage; - dfa->str_tree_storage_idx = 0; - } - tree = &dfa->str_tree_storage->data[dfa->str_tree_storage_idx++]; - - tree->parent = NULL; - tree->left = left; - tree->right = right; - tree->token = *token; - tree->token.duplicated = 0; - tree->token.opt_subexp = 0; - tree->first = NULL; - tree->next = NULL; - tree->node_idx = -1; - - if (left != NULL) - left->parent = tree; - if (right != NULL) - right->parent = tree; - return tree; -} - -/* Mark the tree SRC as an optional subexpression. - To be called from preorder or postorder. */ - -static reg_errcode_t -mark_opt_subexp (void *extra, bin_tree_t *node) -{ - int idx = (int) (long) extra; - if (node->token.type == SUBEXP && node->token.opr.idx == idx) - node->token.opt_subexp = 1; - - return REG_NOERROR; -} - -/* Free the allocated memory inside NODE. */ - -static void -free_token (re_token_t *node) -{ -#ifdef RE_ENABLE_I18N - if (node->type == COMPLEX_BRACKET && node->duplicated == 0) - free_charset (node->opr.mbcset); - else -#endif /* RE_ENABLE_I18N */ - if (node->type == SIMPLE_BRACKET && node->duplicated == 0) - re_free (node->opr.sbcset); -} - -/* Worker function for tree walking. Free the allocated memory inside NODE - and its children. */ - -static reg_errcode_t -free_tree (UNUSED void *extra, bin_tree_t *node) -{ - free_token (&node->token); - return REG_NOERROR; -} - - -/* Duplicate the node SRC, and return new node. This is a preorder - visit similar to the one implemented by the generic visitor, but - we need more infrastructure to maintain two parallel trees --- so, - it's easier to duplicate. */ - -static bin_tree_t * -duplicate_tree (const bin_tree_t *root, re_dfa_t *dfa) -{ - const bin_tree_t *node; - bin_tree_t *dup_root; - bin_tree_t **p_new = &dup_root, *dup_node = root->parent; - - for (node = root; ; ) - { - /* Create a new tree and link it back to the current parent. */ - *p_new = create_token_tree (dfa, NULL, NULL, &node->token); - if (*p_new == NULL) - return NULL; - (*p_new)->parent = dup_node; - (*p_new)->token.duplicated = 1; - dup_node = *p_new; - - /* Go to the left node, or up and to the right. */ - if (node->left) - { - node = node->left; - p_new = &dup_node->left; - } - else - { - const bin_tree_t *prev = NULL; - while (node->right == prev || node->right == NULL) - { - prev = node; - node = node->parent; - dup_node = dup_node->parent; - if (!node) - return dup_root; - } - node = node->right; - p_new = &dup_node->right; - } - } -} diff --git a/deps/regex/regex.c b/deps/regex/regex.c deleted file mode 100644 index 225a001..0000000 --- a/deps/regex/regex.c +++ /dev/null @@ -1,92 +0,0 @@ -/* Extended regular expression matching and search library. - Copyright (C) 2002, 2003, 2005 Free Software Foundation, Inc. - This file is part of the GNU C Library. - Contributed by Isamu Hasegawa . - - The GNU C Library is free software; you can redistribute it and/or - modify it under the terms of the GNU Lesser General Public - License as published by the Free Software Foundation; either - version 2.1 of the License, or (at your option) any later version. - - The GNU C Library is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - Lesser General Public License for more details. - - You should have received a copy of the GNU Lesser General Public - License along with the GNU C Library; if not, write to the Free - Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301 USA. */ - -#include "config.h" - -/* Make sure noone compiles this code with a C++ compiler. */ -#ifdef __cplusplus -# error "This is C code, use a C compiler" -#endif - -#ifdef _LIBC -/* We have to keep the namespace clean. */ -# define regfree(preg) __regfree (preg) -# define regexec(pr, st, nm, pm, ef) __regexec (pr, st, nm, pm, ef) -# define regcomp(preg, pattern, cflags) __regcomp (preg, pattern, cflags) -# define regerror(errcode, preg, errbuf, errbuf_size) \ - __regerror(errcode, preg, errbuf, errbuf_size) -# define re_set_registers(bu, re, nu, st, en) \ - __re_set_registers (bu, re, nu, st, en) -# define re_match_2(bufp, string1, size1, string2, size2, pos, regs, stop) \ - __re_match_2 (bufp, string1, size1, string2, size2, pos, regs, stop) -# define re_match(bufp, string, size, pos, regs) \ - __re_match (bufp, string, size, pos, regs) -# define re_search(bufp, string, size, startpos, range, regs) \ - __re_search (bufp, string, size, startpos, range, regs) -# define re_compile_pattern(pattern, length, bufp) \ - __re_compile_pattern (pattern, length, bufp) -# define re_set_syntax(syntax) __re_set_syntax (syntax) -# define re_search_2(bufp, st1, s1, st2, s2, startpos, range, regs, stop) \ - __re_search_2 (bufp, st1, s1, st2, s2, startpos, range, regs, stop) -# define re_compile_fastmap(bufp) __re_compile_fastmap (bufp) - -# include "../locale/localeinfo.h" -#endif - -#if defined (_MSC_VER) -#include /* for size_t */ -#endif - -/* On some systems, limits.h sets RE_DUP_MAX to a lower value than - GNU regex allows. Include it before , which correctly - #undefs RE_DUP_MAX and sets it to the right value. */ -#include - -#ifdef GAWK -#undef alloca -#define alloca alloca_is_bad_you_should_never_use_it -#endif -#include -#include "regex_internal.h" - -#include "regex_internal.c" - -#ifdef GAWK -# define bool int - -# ifndef true -# define true (1) -# endif - -# ifndef false -# define false (0) -# endif -#endif -#include "regcomp.c" -#include "regexec.c" - -/* Binary backward compatibility. */ -#if _LIBC -# include -# if SHLIB_COMPAT (libc, GLIBC_2_0, GLIBC_2_3) -link_warning (re_max_failures, "the 're_max_failures' variable is obsolete and will go away.") -int re_max_failures = 2000; -# endif -#endif diff --git a/deps/regex/regex.h b/deps/regex/regex.h deleted file mode 100644 index 61c9683..0000000 --- a/deps/regex/regex.h +++ /dev/null @@ -1,582 +0,0 @@ -#include -#include - -/* Definitions for data structures and routines for the regular - expression library. - Copyright (C) 1985,1989-93,1995-98,2000,2001,2002,2003,2005,2006,2008 - Free Software Foundation, Inc. - This file is part of the GNU C Library. - - The GNU C Library is free software; you can redistribute it and/or - modify it under the terms of the GNU Lesser General Public - License as published by the Free Software Foundation; either - version 2.1 of the License, or (at your option) any later version. - - The GNU C Library is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - Lesser General Public License for more details. - - You should have received a copy of the GNU Lesser General Public - License along with the GNU C Library; if not, write to the Free - Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301 USA. */ - -#ifndef _REGEX_H -#define _REGEX_H 1 - -#ifdef HAVE_STDDEF_H -#include -#endif - -#ifdef HAVE_SYS_TYPES_H -#include -#endif - -#ifndef _LIBC -#define __USE_GNU 1 -#endif - -/* Allow the use in C++ code. */ -#ifdef __cplusplus -extern "C" { -#endif - -/* The following two types have to be signed and unsigned integer type - wide enough to hold a value of a pointer. For most ANSI compilers - ptrdiff_t and size_t should be likely OK. Still size of these two - types is 2 for Microsoft C. Ugh... */ -typedef long int s_reg_t; -typedef unsigned long int active_reg_t; - -/* The following bits are used to determine the regexp syntax we - recognize. The set/not-set meanings are chosen so that Emacs syntax - remains the value 0. The bits are given in alphabetical order, and - the definitions shifted by one from the previous bit; thus, when we - add or remove a bit, only one other definition need change. */ -typedef unsigned long int reg_syntax_t; - -#ifdef __USE_GNU -/* If this bit is not set, then \ inside a bracket expression is literal. - If set, then such a \ quotes the following character. */ -# define RE_BACKSLASH_ESCAPE_IN_LISTS ((unsigned long int) 1) - -/* If this bit is not set, then + and ? are operators, and \+ and \? are - literals. - If set, then \+ and \? are operators and + and ? are literals. */ -# define RE_BK_PLUS_QM (RE_BACKSLASH_ESCAPE_IN_LISTS << 1) - -/* If this bit is set, then character classes are supported. They are: - [:alpha:], [:upper:], [:lower:], [:digit:], [:alnum:], [:xdigit:], - [:space:], [:print:], [:punct:], [:graph:], and [:cntrl:]. - If not set, then character classes are not supported. */ -# define RE_CHAR_CLASSES (RE_BK_PLUS_QM << 1) - -/* If this bit is set, then ^ and $ are always anchors (outside bracket - expressions, of course). - If this bit is not set, then it depends: - ^ is an anchor if it is at the beginning of a regular - expression or after an open-group or an alternation operator; - $ is an anchor if it is at the end of a regular expression, or - before a close-group or an alternation operator. - - This bit could be (re)combined with RE_CONTEXT_INDEP_OPS, because - POSIX draft 11.2 says that * etc. in leading positions is undefined. - We already implemented a previous draft which made those constructs - invalid, though, so we haven't changed the code back. */ -# define RE_CONTEXT_INDEP_ANCHORS (RE_CHAR_CLASSES << 1) - -/* If this bit is set, then special characters are always special - regardless of where they are in the pattern. - If this bit is not set, then special characters are special only in - some contexts; otherwise they are ordinary. Specifically, - * + ? and intervals are only special when not after the beginning, - open-group, or alternation operator. */ -# define RE_CONTEXT_INDEP_OPS (RE_CONTEXT_INDEP_ANCHORS << 1) - -/* If this bit is set, then *, +, ?, and { cannot be first in an re or - immediately after an alternation or begin-group operator. */ -# define RE_CONTEXT_INVALID_OPS (RE_CONTEXT_INDEP_OPS << 1) - -/* If this bit is set, then . matches newline. - If not set, then it doesn't. */ -# define RE_DOT_NEWLINE (RE_CONTEXT_INVALID_OPS << 1) - -/* If this bit is set, then . doesn't match NUL. - If not set, then it does. */ -# define RE_DOT_NOT_NULL (RE_DOT_NEWLINE << 1) - -/* If this bit is set, nonmatching lists [^...] do not match newline. - If not set, they do. */ -# define RE_HAT_LISTS_NOT_NEWLINE (RE_DOT_NOT_NULL << 1) - -/* If this bit is set, either \{...\} or {...} defines an - interval, depending on RE_NO_BK_BRACES. - If not set, \{, \}, {, and } are literals. */ -# define RE_INTERVALS (RE_HAT_LISTS_NOT_NEWLINE << 1) - -/* If this bit is set, +, ? and | aren't recognized as operators. - If not set, they are. */ -# define RE_LIMITED_OPS (RE_INTERVALS << 1) - -/* If this bit is set, newline is an alternation operator. - If not set, newline is literal. */ -# define RE_NEWLINE_ALT (RE_LIMITED_OPS << 1) - -/* If this bit is set, then `{...}' defines an interval, and \{ and \} - are literals. - If not set, then `\{...\}' defines an interval. */ -# define RE_NO_BK_BRACES (RE_NEWLINE_ALT << 1) - -/* If this bit is set, (...) defines a group, and \( and \) are literals. - If not set, \(...\) defines a group, and ( and ) are literals. */ -# define RE_NO_BK_PARENS (RE_NO_BK_BRACES << 1) - -/* If this bit is set, then \ matches . - If not set, then \ is a back-reference. */ -# define RE_NO_BK_REFS (RE_NO_BK_PARENS << 1) - -/* If this bit is set, then | is an alternation operator, and \| is literal. - If not set, then \| is an alternation operator, and | is literal. */ -# define RE_NO_BK_VBAR (RE_NO_BK_REFS << 1) - -/* If this bit is set, then an ending range point collating higher - than the starting range point, as in [z-a], is invalid. - If not set, then when ending range point collates higher than the - starting range point, the range is ignored. */ -# define RE_NO_EMPTY_RANGES (RE_NO_BK_VBAR << 1) - -/* If this bit is set, then an unmatched ) is ordinary. - If not set, then an unmatched ) is invalid. */ -# define RE_UNMATCHED_RIGHT_PAREN_ORD (RE_NO_EMPTY_RANGES << 1) - -/* If this bit is set, succeed as soon as we match the whole pattern, - without further backtracking. */ -# define RE_NO_POSIX_BACKTRACKING (RE_UNMATCHED_RIGHT_PAREN_ORD << 1) - -/* If this bit is set, do not process the GNU regex operators. - If not set, then the GNU regex operators are recognized. */ -# define RE_NO_GNU_OPS (RE_NO_POSIX_BACKTRACKING << 1) - -/* If this bit is set, a syntactically invalid interval is treated as - a string of ordinary characters. For example, the ERE 'a{1' is - treated as 'a\{1'. */ -# define RE_INVALID_INTERVAL_ORD (RE_NO_GNU_OPS << 1) - -/* If this bit is set, then ignore case when matching. - If not set, then case is significant. */ -# define RE_ICASE (RE_INVALID_INTERVAL_ORD << 1) - -/* This bit is used internally like RE_CONTEXT_INDEP_ANCHORS but only - for ^, because it is difficult to scan the regex backwards to find - whether ^ should be special. */ -# define RE_CARET_ANCHORS_HERE (RE_ICASE << 1) - -/* If this bit is set, then \{ cannot be first in an bre or - immediately after an alternation or begin-group operator. */ -# define RE_CONTEXT_INVALID_DUP (RE_CARET_ANCHORS_HERE << 1) - -/* If this bit is set, then no_sub will be set to 1 during - re_compile_pattern. */ -#define RE_NO_SUB (RE_CONTEXT_INVALID_DUP << 1) -#endif - -/* This global variable defines the particular regexp syntax to use (for - some interfaces). When a regexp is compiled, the syntax used is - stored in the pattern buffer, so changing this does not affect - already-compiled regexps. */ -extern reg_syntax_t re_syntax_options; - -#ifdef __USE_GNU -/* Define combinations of the above bits for the standard possibilities. - (The [[[ comments delimit what gets put into the Texinfo file, so - don't delete them!) */ -/* [[[begin syntaxes]]] */ -#define RE_SYNTAX_EMACS 0 - -#define RE_SYNTAX_AWK \ - (RE_BACKSLASH_ESCAPE_IN_LISTS | RE_DOT_NOT_NULL \ - | RE_NO_BK_PARENS | RE_NO_BK_REFS \ - | RE_NO_BK_VBAR | RE_NO_EMPTY_RANGES \ - | RE_DOT_NEWLINE | RE_CONTEXT_INDEP_ANCHORS \ - | RE_UNMATCHED_RIGHT_PAREN_ORD | RE_NO_GNU_OPS) - -#define RE_SYNTAX_GNU_AWK \ - ((RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS \ - | RE_INVALID_INTERVAL_ORD) \ - & ~(RE_DOT_NOT_NULL | RE_CONTEXT_INDEP_OPS \ - | RE_CONTEXT_INVALID_OPS )) - -#define RE_SYNTAX_POSIX_AWK \ - (RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS \ - | RE_INTERVALS | RE_NO_GNU_OPS \ - | RE_INVALID_INTERVAL_ORD) - -#define RE_SYNTAX_GREP \ - (RE_BK_PLUS_QM | RE_CHAR_CLASSES \ - | RE_HAT_LISTS_NOT_NEWLINE | RE_INTERVALS \ - | RE_NEWLINE_ALT) - -#define RE_SYNTAX_EGREP \ - (RE_CHAR_CLASSES | RE_CONTEXT_INDEP_ANCHORS \ - | RE_CONTEXT_INDEP_OPS | RE_HAT_LISTS_NOT_NEWLINE \ - | RE_NEWLINE_ALT | RE_NO_BK_PARENS \ - | RE_NO_BK_VBAR) - -#define RE_SYNTAX_POSIX_EGREP \ - (RE_SYNTAX_EGREP | RE_INTERVALS | RE_NO_BK_BRACES \ - | RE_INVALID_INTERVAL_ORD) - -/* P1003.2/D11.2, section 4.20.7.1, lines 5078ff. */ -#define RE_SYNTAX_ED RE_SYNTAX_POSIX_BASIC - -#define RE_SYNTAX_SED RE_SYNTAX_POSIX_BASIC - -/* Syntax bits common to both basic and extended POSIX regex syntax. */ -#define _RE_SYNTAX_POSIX_COMMON \ - (RE_CHAR_CLASSES | RE_DOT_NEWLINE | RE_DOT_NOT_NULL \ - | RE_INTERVALS | RE_NO_EMPTY_RANGES) - -#define RE_SYNTAX_POSIX_BASIC \ - (_RE_SYNTAX_POSIX_COMMON | RE_BK_PLUS_QM | RE_CONTEXT_INVALID_DUP) - -/* Differs from ..._POSIX_BASIC only in that RE_BK_PLUS_QM becomes - RE_LIMITED_OPS, i.e., \? \+ \| are not recognized. Actually, this - isn't minimal, since other operators, such as \`, aren't disabled. */ -#define RE_SYNTAX_POSIX_MINIMAL_BASIC \ - (_RE_SYNTAX_POSIX_COMMON | RE_LIMITED_OPS) - -#define RE_SYNTAX_POSIX_EXTENDED \ - (_RE_SYNTAX_POSIX_COMMON | RE_CONTEXT_INDEP_ANCHORS \ - | RE_CONTEXT_INDEP_OPS | RE_NO_BK_BRACES \ - | RE_NO_BK_PARENS | RE_NO_BK_VBAR \ - | RE_CONTEXT_INVALID_OPS | RE_UNMATCHED_RIGHT_PAREN_ORD) - -/* Differs from ..._POSIX_EXTENDED in that RE_CONTEXT_INDEP_OPS is - removed and RE_NO_BK_REFS is added. */ -#define RE_SYNTAX_POSIX_MINIMAL_EXTENDED \ - (_RE_SYNTAX_POSIX_COMMON | RE_CONTEXT_INDEP_ANCHORS \ - | RE_CONTEXT_INVALID_OPS | RE_NO_BK_BRACES \ - | RE_NO_BK_PARENS | RE_NO_BK_REFS \ - | RE_NO_BK_VBAR | RE_UNMATCHED_RIGHT_PAREN_ORD) -/* [[[end syntaxes]]] */ - -/* Maximum number of duplicates an interval can allow. Some systems - (erroneously) define this in other header files, but we want our - value, so remove any previous define. */ -# ifdef RE_DUP_MAX -# undef RE_DUP_MAX -# endif -/* If sizeof(int) == 2, then ((1 << 15) - 1) overflows. */ -# define RE_DUP_MAX (0x7fff) -#endif - - -/* POSIX `cflags' bits (i.e., information for `regcomp'). */ - -/* If this bit is set, then use extended regular expression syntax. - If not set, then use basic regular expression syntax. */ -#define REG_EXTENDED 1 - -/* If this bit is set, then ignore case when matching. - If not set, then case is significant. */ -#define REG_ICASE (REG_EXTENDED << 1) - -/* If this bit is set, then anchors do not match at newline - characters in the string. - If not set, then anchors do match at newlines. */ -#define REG_NEWLINE (REG_ICASE << 1) - -/* If this bit is set, then report only success or fail in regexec. - If not set, then returns differ between not matching and errors. */ -#define REG_NOSUB (REG_NEWLINE << 1) - - -/* POSIX `eflags' bits (i.e., information for regexec). */ - -/* If this bit is set, then the beginning-of-line operator doesn't match - the beginning of the string (presumably because it's not the - beginning of a line). - If not set, then the beginning-of-line operator does match the - beginning of the string. */ -#define REG_NOTBOL 1 - -/* Like REG_NOTBOL, except for the end-of-line. */ -#define REG_NOTEOL (1 << 1) - -/* Use PMATCH[0] to delimit the start and end of the search in the - buffer. */ -#define REG_STARTEND (1 << 2) - - -/* If any error codes are removed, changed, or added, update the - `re_error_msg' table in regex.c. */ -typedef enum -{ -#if defined _XOPEN_SOURCE || defined __USE_XOPEN2K - REG_ENOSYS = -1, /* This will never happen for this implementation. */ -#endif - - REG_NOERROR = 0, /* Success. */ - REG_NOMATCH, /* Didn't find a match (for regexec). */ - - /* POSIX regcomp return error codes. (In the order listed in the - standard.) */ - REG_BADPAT, /* Invalid pattern. */ - REG_ECOLLATE, /* Inalid collating element. */ - REG_ECTYPE, /* Invalid character class name. */ - REG_EESCAPE, /* Trailing backslash. */ - REG_ESUBREG, /* Invalid back reference. */ - REG_EBRACK, /* Unmatched left bracket. */ - REG_EPAREN, /* Parenthesis imbalance. */ - REG_EBRACE, /* Unmatched \{. */ - REG_BADBR, /* Invalid contents of \{\}. */ - REG_ERANGE, /* Invalid range end. */ - REG_ESPACE, /* Ran out of memory. */ - REG_BADRPT, /* No preceding re for repetition op. */ - - /* Error codes we've added. */ - REG_EEND, /* Premature end. */ - REG_ESIZE, /* Compiled pattern bigger than 2^16 bytes. */ - REG_ERPAREN /* Unmatched ) or \); not returned from regcomp. */ -} reg_errcode_t; - -/* This data structure represents a compiled pattern. Before calling - the pattern compiler, the fields `buffer', `allocated', `fastmap', - `translate', and `no_sub' can be set. After the pattern has been - compiled, the `re_nsub' field is available. All other fields are - private to the regex routines. */ - -#ifndef RE_TRANSLATE_TYPE -# define __RE_TRANSLATE_TYPE unsigned char * -# ifdef __USE_GNU -# define RE_TRANSLATE_TYPE __RE_TRANSLATE_TYPE -# endif -#endif - -#ifdef __USE_GNU -# define __REPB_PREFIX(name) name -#else -# define __REPB_PREFIX(name) __##name -#endif - -struct re_pattern_buffer -{ - /* Space that holds the compiled pattern. It is declared as - `unsigned char *' because its elements are sometimes used as - array indexes. */ - unsigned char *__REPB_PREFIX(buffer); - - /* Number of bytes to which `buffer' points. */ - unsigned long int __REPB_PREFIX(allocated); - - /* Number of bytes actually used in `buffer'. */ - unsigned long int __REPB_PREFIX(used); - - /* Syntax setting with which the pattern was compiled. */ - reg_syntax_t __REPB_PREFIX(syntax); - - /* Pointer to a fastmap, if any, otherwise zero. re_search uses the - fastmap, if there is one, to skip over impossible starting points - for matches. */ - char *__REPB_PREFIX(fastmap); - - /* Either a translate table to apply to all characters before - comparing them, or zero for no translation. The translation is - applied to a pattern when it is compiled and to a string when it - is matched. */ - __RE_TRANSLATE_TYPE __REPB_PREFIX(translate); - - /* Number of subexpressions found by the compiler. */ - size_t re_nsub; - - /* Zero if this pattern cannot match the empty string, one else. - Well, in truth it's used only in `re_search_2', to see whether or - not we should use the fastmap, so we don't set this absolutely - perfectly; see `re_compile_fastmap' (the `duplicate' case). */ - unsigned __REPB_PREFIX(can_be_null) : 1; - - /* If REGS_UNALLOCATED, allocate space in the `regs' structure - for `max (RE_NREGS, re_nsub + 1)' groups. - If REGS_REALLOCATE, reallocate space if necessary. - If REGS_FIXED, use what's there. */ -#ifdef __USE_GNU -# define REGS_UNALLOCATED 0 -# define REGS_REALLOCATE 1 -# define REGS_FIXED 2 -#endif - unsigned __REPB_PREFIX(regs_allocated) : 2; - - /* Set to zero when `regex_compile' compiles a pattern; set to one - by `re_compile_fastmap' if it updates the fastmap. */ - unsigned __REPB_PREFIX(fastmap_accurate) : 1; - - /* If set, `re_match_2' does not return information about - subexpressions. */ - unsigned __REPB_PREFIX(no_sub) : 1; - - /* If set, a beginning-of-line anchor doesn't match at the beginning - of the string. */ - unsigned __REPB_PREFIX(not_bol) : 1; - - /* Similarly for an end-of-line anchor. */ - unsigned __REPB_PREFIX(not_eol) : 1; - - /* If true, an anchor at a newline matches. */ - unsigned __REPB_PREFIX(newline_anchor) : 1; -}; - -typedef struct re_pattern_buffer regex_t; - -/* Type for byte offsets within the string. POSIX mandates this. */ -typedef int regoff_t; - - -#ifdef __USE_GNU -/* This is the structure we store register match data in. See - regex.texinfo for a full description of what registers match. */ -struct re_registers -{ - unsigned num_regs; - regoff_t *start; - regoff_t *end; -}; - - -/* If `regs_allocated' is REGS_UNALLOCATED in the pattern buffer, - `re_match_2' returns information about at least this many registers - the first time a `regs' structure is passed. */ -# ifndef RE_NREGS -# define RE_NREGS 30 -# endif -#endif - - -/* POSIX specification for registers. Aside from the different names than - `re_registers', POSIX uses an array of structures, instead of a - structure of arrays. */ -typedef struct -{ - regoff_t rm_so; /* Byte offset from string's start to substring's start. */ - regoff_t rm_eo; /* Byte offset from string's start to substring's end. */ -} regmatch_t; - -/* Declarations for routines. */ - -#ifdef __USE_GNU -/* Sets the current default syntax to SYNTAX, and return the old syntax. - You can also simply assign to the `re_syntax_options' variable. */ -extern reg_syntax_t re_set_syntax (reg_syntax_t __syntax); - -/* Compile the regular expression PATTERN, with length LENGTH - and syntax given by the global `re_syntax_options', into the buffer - BUFFER. Return NULL if successful, and an error string if not. */ -extern const char *re_compile_pattern (const char *__pattern, size_t __length, - struct re_pattern_buffer *__buffer); - - -/* Compile a fastmap for the compiled pattern in BUFFER; used to - accelerate searches. Return 0 if successful and -2 if was an - internal error. */ -extern int re_compile_fastmap (struct re_pattern_buffer *__buffer); - - -/* Search in the string STRING (with length LENGTH) for the pattern - compiled into BUFFER. Start searching at position START, for RANGE - characters. Return the starting position of the match, -1 for no - match, or -2 for an internal error. Also return register - information in REGS (if REGS and BUFFER->no_sub are nonzero). */ -extern int re_search (struct re_pattern_buffer *__buffer, const char *__cstring, - int __length, int __start, int __range, - struct re_registers *__regs); - - -/* Like `re_search', but search in the concatenation of STRING1 and - STRING2. Also, stop searching at index START + STOP. */ -extern int re_search_2 (struct re_pattern_buffer *__buffer, - const char *__string1, int __length1, - const char *__string2, int __length2, int __start, - int __range, struct re_registers *__regs, int __stop); - - -/* Like `re_search', but return how many characters in STRING the regexp - in BUFFER matched, starting at position START. */ -extern int re_match (struct re_pattern_buffer *__buffer, const char *__cstring, - int __length, int __start, struct re_registers *__regs); - - -/* Relates to `re_match' as `re_search_2' relates to `re_search'. */ -extern int re_match_2 (struct re_pattern_buffer *__buffer, - const char *__string1, int __length1, - const char *__string2, int __length2, int __start, - struct re_registers *__regs, int __stop); - - -/* Set REGS to hold NUM_REGS registers, storing them in STARTS and - ENDS. Subsequent matches using BUFFER and REGS will use this memory - for recording register information. STARTS and ENDS must be - allocated with malloc, and must each be at least `NUM_REGS * sizeof - (regoff_t)' bytes long. - - If NUM_REGS == 0, then subsequent matches should allocate their own - register data. - - Unless this function is called, the first search or match using - PATTERN_BUFFER will allocate its own register data, without - freeing the old data. */ -extern void re_set_registers (struct re_pattern_buffer *__buffer, - struct re_registers *__regs, - unsigned int __num_regs, - regoff_t *__starts, regoff_t *__ends); -#endif /* Use GNU */ - -#if defined _REGEX_RE_COMP || (defined _LIBC && defined __USE_BSD) -# ifndef _CRAY -/* 4.2 bsd compatibility. */ -extern char *re_comp (const char *); -extern int re_exec (const char *); -# endif -#endif - -/* GCC 2.95 and later have "__restrict"; C99 compilers have - "restrict", and "configure" may have defined "restrict". */ -#ifndef __restrict -# if ! (2 < __GNUC__ || (2 == __GNUC__ && 95 <= __GNUC_MINOR__)) -# if defined restrict || 199901L <= __STDC_VERSION__ -# define __restrict restrict -# else -# define __restrict -# endif -# endif -#endif -/* gcc 3.1 and up support the [restrict] syntax. */ -#ifndef __restrict_arr -# if (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 1)) \ - && !defined __GNUG__ -# define __restrict_arr __restrict -# else -# define __restrict_arr -# endif -#endif - -/* POSIX compatibility. */ -extern int regcomp (regex_t *__restrict __preg, - const char *__restrict __pattern, - int __cflags); - -extern int regexec (const regex_t *__restrict __preg, - const char *__restrict __cstring, size_t __nmatch, - regmatch_t __pmatch[__restrict_arr], - int __eflags); - -extern size_t regerror (int __errcode, const regex_t *__restrict __preg, - char *__restrict __errbuf, size_t __errbuf_size); - -extern void regfree (regex_t *__preg); - - -#ifdef __cplusplus -} -#endif /* C++ */ - -#endif /* regex.h */ diff --git a/deps/regex/regex_internal.c b/deps/regex/regex_internal.c deleted file mode 100644 index ad57c20..0000000 --- a/deps/regex/regex_internal.c +++ /dev/null @@ -1,1744 +0,0 @@ -/* Extended regular expression matching and search library. - Copyright (C) 2002-2006, 2010 Free Software Foundation, Inc. - This file is part of the GNU C Library. - Contributed by Isamu Hasegawa . - - The GNU C Library is free software; you can redistribute it and/or - modify it under the terms of the GNU Lesser General Public - License as published by the Free Software Foundation; either - version 2.1 of the License, or (at your option) any later version. - - The GNU C Library is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - Lesser General Public License for more details. - - You should have received a copy of the GNU Lesser General Public - License along with the GNU C Library; if not, write to the Free - Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301 USA. */ - -static void re_string_construct_common (const char *str, int len, - re_string_t *pstr, - RE_TRANSLATE_TYPE trans, int icase, - const re_dfa_t *dfa) internal_function; -static re_dfastate_t *create_ci_newstate (const re_dfa_t *dfa, - const re_node_set *nodes, - unsigned int hash) internal_function; -static re_dfastate_t *create_cd_newstate (const re_dfa_t *dfa, - const re_node_set *nodes, - unsigned int context, - unsigned int hash) internal_function; - -#ifdef GAWK -#undef MAX /* safety */ -static size_t -MAX(size_t a, size_t b) -{ - return (a > b ? a : b); -} -#endif - -/* Functions for string operation. */ - -/* This function allocate the buffers. It is necessary to call - re_string_reconstruct before using the object. */ - -static reg_errcode_t -internal_function -re_string_allocate (re_string_t *pstr, const char *str, int len, int init_len, - RE_TRANSLATE_TYPE trans, int icase, const re_dfa_t *dfa) -{ - reg_errcode_t ret; - int init_buf_len; - - /* Ensure at least one character fits into the buffers. */ - if (init_len < dfa->mb_cur_max) - init_len = dfa->mb_cur_max; - init_buf_len = (len + 1 < init_len) ? len + 1: init_len; - re_string_construct_common (str, len, pstr, trans, icase, dfa); - - ret = re_string_realloc_buffers (pstr, init_buf_len); - if (BE (ret != REG_NOERROR, 0)) - return ret; - - pstr->word_char = dfa->word_char; - pstr->word_ops_used = dfa->word_ops_used; - pstr->mbs = pstr->mbs_allocated ? pstr->mbs : (unsigned char *) str; - pstr->valid_len = (pstr->mbs_allocated || dfa->mb_cur_max > 1) ? 0 : len; - pstr->valid_raw_len = pstr->valid_len; - return REG_NOERROR; -} - -/* This function allocate the buffers, and initialize them. */ - -static reg_errcode_t -internal_function -re_string_construct (re_string_t *pstr, const char *str, int len, - RE_TRANSLATE_TYPE trans, int icase, const re_dfa_t *dfa) -{ - reg_errcode_t ret; - memset (pstr, '\0', sizeof (re_string_t)); - re_string_construct_common (str, len, pstr, trans, icase, dfa); - - if (len > 0) - { - ret = re_string_realloc_buffers (pstr, len + 1); - if (BE (ret != REG_NOERROR, 0)) - return ret; - } - pstr->mbs = pstr->mbs_allocated ? pstr->mbs : (unsigned char *) str; - - if (icase) - { -#ifdef RE_ENABLE_I18N - if (dfa->mb_cur_max > 1) - { - while (1) - { - ret = build_wcs_upper_buffer (pstr); - if (BE (ret != REG_NOERROR, 0)) - return ret; - if (pstr->valid_raw_len >= len) - break; - if (pstr->bufs_len > pstr->valid_len + dfa->mb_cur_max) - break; - ret = re_string_realloc_buffers (pstr, pstr->bufs_len * 2); - if (BE (ret != REG_NOERROR, 0)) - return ret; - } - } - else -#endif /* RE_ENABLE_I18N */ - build_upper_buffer (pstr); - } - else - { -#ifdef RE_ENABLE_I18N - if (dfa->mb_cur_max > 1) - build_wcs_buffer (pstr); - else -#endif /* RE_ENABLE_I18N */ - { - if (trans != NULL) - re_string_translate_buffer (pstr); - else - { - pstr->valid_len = pstr->bufs_len; - pstr->valid_raw_len = pstr->bufs_len; - } - } - } - - return REG_NOERROR; -} - -/* Helper functions for re_string_allocate, and re_string_construct. */ - -static reg_errcode_t -internal_function -re_string_realloc_buffers (re_string_t *pstr, int new_buf_len) -{ -#ifdef RE_ENABLE_I18N - if (pstr->mb_cur_max > 1) - { - wint_t *new_wcs; - - /* Avoid overflow in realloc. */ - const size_t max_object_size = MAX (sizeof (wint_t), sizeof (int)); - if (BE (SIZE_MAX / max_object_size < new_buf_len, 0)) - return REG_ESPACE; - - new_wcs = re_realloc (pstr->wcs, wint_t, new_buf_len); - if (BE (new_wcs == NULL, 0)) - return REG_ESPACE; - pstr->wcs = new_wcs; - if (pstr->offsets != NULL) - { - int *new_offsets = re_realloc (pstr->offsets, int, new_buf_len); - if (BE (new_offsets == NULL, 0)) - return REG_ESPACE; - pstr->offsets = new_offsets; - } - } -#endif /* RE_ENABLE_I18N */ - if (pstr->mbs_allocated) - { - unsigned char *new_mbs = re_realloc (pstr->mbs, unsigned char, - new_buf_len); - if (BE (new_mbs == NULL, 0)) - return REG_ESPACE; - pstr->mbs = new_mbs; - } - pstr->bufs_len = new_buf_len; - return REG_NOERROR; -} - - -static void -internal_function -re_string_construct_common (const char *str, int len, re_string_t *pstr, - RE_TRANSLATE_TYPE trans, int icase, - const re_dfa_t *dfa) -{ - pstr->raw_mbs = (const unsigned char *) str; - pstr->len = len; - pstr->raw_len = len; - pstr->trans = trans; - pstr->icase = icase ? 1 : 0; - pstr->mbs_allocated = (trans != NULL || icase); - pstr->mb_cur_max = dfa->mb_cur_max; - pstr->is_utf8 = dfa->is_utf8; - pstr->map_notascii = dfa->map_notascii; - pstr->stop = pstr->len; - pstr->raw_stop = pstr->stop; -} - -#ifdef RE_ENABLE_I18N - -/* Build wide character buffer PSTR->WCS. - If the byte sequence of the string are: - (0), (1), (0), (1), - Then wide character buffer will be: - , WEOF , , WEOF , - We use WEOF for padding, they indicate that the position isn't - a first byte of a multibyte character. - - Note that this function assumes PSTR->VALID_LEN elements are already - built and starts from PSTR->VALID_LEN. */ - -static void -internal_function -build_wcs_buffer (re_string_t *pstr) -{ -#ifdef _LIBC - unsigned char buf[MB_LEN_MAX]; - assert (MB_LEN_MAX >= pstr->mb_cur_max); -#else - unsigned char buf[64]; -#endif - mbstate_t prev_st; - int byte_idx, end_idx, remain_len; - size_t mbclen; - - /* Build the buffers from pstr->valid_len to either pstr->len or - pstr->bufs_len. */ - end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len; - for (byte_idx = pstr->valid_len; byte_idx < end_idx;) - { - wchar_t wc; - const char *p; - - remain_len = end_idx - byte_idx; - prev_st = pstr->cur_state; - /* Apply the translation if we need. */ - if (BE (pstr->trans != NULL, 0)) - { - int i, ch; - - for (i = 0; i < pstr->mb_cur_max && i < remain_len; ++i) - { - ch = pstr->raw_mbs [pstr->raw_mbs_idx + byte_idx + i]; - buf[i] = pstr->mbs[byte_idx + i] = pstr->trans[ch]; - } - p = (const char *) buf; - } - else - p = (const char *) pstr->raw_mbs + pstr->raw_mbs_idx + byte_idx; - mbclen = __mbrtowc (&wc, p, remain_len, &pstr->cur_state); - if (BE (mbclen == (size_t) -2, 0)) - { - /* The buffer doesn't have enough space, finish to build. */ - pstr->cur_state = prev_st; - break; - } - else if (BE (mbclen == (size_t) -1 || mbclen == 0, 0)) - { - /* We treat these cases as a singlebyte character. */ - mbclen = 1; - wc = (wchar_t) pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]; - if (BE (pstr->trans != NULL, 0)) - wc = pstr->trans[wc]; - pstr->cur_state = prev_st; - } - - /* Write wide character and padding. */ - pstr->wcs[byte_idx++] = wc; - /* Write paddings. */ - for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;) - pstr->wcs[byte_idx++] = WEOF; - } - pstr->valid_len = byte_idx; - pstr->valid_raw_len = byte_idx; -} - -/* Build wide character buffer PSTR->WCS like build_wcs_buffer, - but for REG_ICASE. */ - -static reg_errcode_t -internal_function -build_wcs_upper_buffer (re_string_t *pstr) -{ - mbstate_t prev_st; - int src_idx, byte_idx, end_idx, remain_len; - size_t mbclen; -#ifdef _LIBC - char buf[MB_LEN_MAX]; - assert (MB_LEN_MAX >= pstr->mb_cur_max); -#else - char buf[64]; -#endif - - byte_idx = pstr->valid_len; - end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len; - - /* The following optimization assumes that ASCII characters can be - mapped to wide characters with a simple cast. */ - if (! pstr->map_notascii && pstr->trans == NULL && !pstr->offsets_needed) - { - while (byte_idx < end_idx) - { - wchar_t wc; - - if (isascii (pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]) - && mbsinit (&pstr->cur_state)) - { - /* In case of a singlebyte character. */ - pstr->mbs[byte_idx] - = toupper (pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]); - /* The next step uses the assumption that wchar_t is encoded - ASCII-safe: all ASCII values can be converted like this. */ - pstr->wcs[byte_idx] = (wchar_t) pstr->mbs[byte_idx]; - ++byte_idx; - continue; - } - - remain_len = end_idx - byte_idx; - prev_st = pstr->cur_state; - mbclen = __mbrtowc (&wc, - ((const char *) pstr->raw_mbs + pstr->raw_mbs_idx - + byte_idx), remain_len, &pstr->cur_state); - if (BE (mbclen + 2 > 2, 1)) - { - wchar_t wcu = wc; - if (iswlower (wc)) - { - size_t mbcdlen; - - wcu = towupper (wc); - mbcdlen = wcrtomb (buf, wcu, &prev_st); - if (BE (mbclen == mbcdlen, 1)) - memcpy (pstr->mbs + byte_idx, buf, mbclen); - else - { - src_idx = byte_idx; - goto offsets_needed; - } - } - else - memcpy (pstr->mbs + byte_idx, - pstr->raw_mbs + pstr->raw_mbs_idx + byte_idx, mbclen); - pstr->wcs[byte_idx++] = wcu; - /* Write paddings. */ - for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;) - pstr->wcs[byte_idx++] = WEOF; - } - else if (mbclen == (size_t) -1 || mbclen == 0) - { - /* It is an invalid character or '\0'. Just use the byte. */ - int ch = pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]; - pstr->mbs[byte_idx] = ch; - /* And also cast it to wide char. */ - pstr->wcs[byte_idx++] = (wchar_t) ch; - if (BE (mbclen == (size_t) -1, 0)) - pstr->cur_state = prev_st; - } - else - { - /* The buffer doesn't have enough space, finish to build. */ - pstr->cur_state = prev_st; - break; - } - } - pstr->valid_len = byte_idx; - pstr->valid_raw_len = byte_idx; - return REG_NOERROR; - } - else - for (src_idx = pstr->valid_raw_len; byte_idx < end_idx;) - { - wchar_t wc; - const char *p; - offsets_needed: - remain_len = end_idx - byte_idx; - prev_st = pstr->cur_state; - if (BE (pstr->trans != NULL, 0)) - { - int i, ch; - - for (i = 0; i < pstr->mb_cur_max && i < remain_len; ++i) - { - ch = pstr->raw_mbs [pstr->raw_mbs_idx + src_idx + i]; - buf[i] = pstr->trans[ch]; - } - p = (const char *) buf; - } - else - p = (const char *) pstr->raw_mbs + pstr->raw_mbs_idx + src_idx; - mbclen = __mbrtowc (&wc, p, remain_len, &pstr->cur_state); - if (BE (mbclen + 2 > 2, 1)) - { - wchar_t wcu = wc; - if (iswlower (wc)) - { - size_t mbcdlen; - - wcu = towupper (wc); - mbcdlen = wcrtomb ((char *) buf, wcu, &prev_st); - if (BE (mbclen == mbcdlen, 1)) - memcpy (pstr->mbs + byte_idx, buf, mbclen); - else if (mbcdlen != (size_t) -1) - { - size_t i; - - if (byte_idx + mbcdlen > pstr->bufs_len) - { - pstr->cur_state = prev_st; - break; - } - - if (pstr->offsets == NULL) - { - pstr->offsets = re_malloc (int, pstr->bufs_len); - - if (pstr->offsets == NULL) - return REG_ESPACE; - } - if (!pstr->offsets_needed) - { - for (i = 0; i < (size_t) byte_idx; ++i) - pstr->offsets[i] = i; - pstr->offsets_needed = 1; - } - - memcpy (pstr->mbs + byte_idx, buf, mbcdlen); - pstr->wcs[byte_idx] = wcu; - pstr->offsets[byte_idx] = src_idx; - for (i = 1; i < mbcdlen; ++i) - { - pstr->offsets[byte_idx + i] - = src_idx + (i < mbclen ? i : mbclen - 1); - pstr->wcs[byte_idx + i] = WEOF; - } - pstr->len += mbcdlen - mbclen; - if (pstr->raw_stop > src_idx) - pstr->stop += mbcdlen - mbclen; - end_idx = (pstr->bufs_len > pstr->len) - ? pstr->len : pstr->bufs_len; - byte_idx += mbcdlen; - src_idx += mbclen; - continue; - } - else - memcpy (pstr->mbs + byte_idx, p, mbclen); - } - else - memcpy (pstr->mbs + byte_idx, p, mbclen); - - if (BE (pstr->offsets_needed != 0, 0)) - { - size_t i; - for (i = 0; i < mbclen; ++i) - pstr->offsets[byte_idx + i] = src_idx + i; - } - src_idx += mbclen; - - pstr->wcs[byte_idx++] = wcu; - /* Write paddings. */ - for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;) - pstr->wcs[byte_idx++] = WEOF; - } - else if (mbclen == (size_t) -1 || mbclen == 0) - { - /* It is an invalid character or '\0'. Just use the byte. */ - int ch = pstr->raw_mbs[pstr->raw_mbs_idx + src_idx]; - - if (BE (pstr->trans != NULL, 0)) - ch = pstr->trans [ch]; - pstr->mbs[byte_idx] = ch; - - if (BE (pstr->offsets_needed != 0, 0)) - pstr->offsets[byte_idx] = src_idx; - ++src_idx; - - /* And also cast it to wide char. */ - pstr->wcs[byte_idx++] = (wchar_t) ch; - if (BE (mbclen == (size_t) -1, 0)) - pstr->cur_state = prev_st; - } - else - { - /* The buffer doesn't have enough space, finish to build. */ - pstr->cur_state = prev_st; - break; - } - } - pstr->valid_len = byte_idx; - pstr->valid_raw_len = src_idx; - return REG_NOERROR; -} - -/* Skip characters until the index becomes greater than NEW_RAW_IDX. - Return the index. */ - -static int -internal_function -re_string_skip_chars (re_string_t *pstr, int new_raw_idx, wint_t *last_wc) -{ - mbstate_t prev_st; - int rawbuf_idx; - size_t mbclen; - wint_t wc = WEOF; - - /* Skip the characters which are not necessary to check. */ - for (rawbuf_idx = pstr->raw_mbs_idx + pstr->valid_raw_len; - rawbuf_idx < new_raw_idx;) - { - wchar_t wc2; - int remain_len = pstr->len - rawbuf_idx; - prev_st = pstr->cur_state; - mbclen = __mbrtowc (&wc2, (const char *) pstr->raw_mbs + rawbuf_idx, - remain_len, &pstr->cur_state); - if (BE (mbclen == (size_t) -2 || mbclen == (size_t) -1 || mbclen == 0, 0)) - { - /* We treat these cases as a single byte character. */ - if (mbclen == 0 || remain_len == 0) - wc = L'\0'; - else - wc = *(unsigned char *) (pstr->raw_mbs + rawbuf_idx); - mbclen = 1; - pstr->cur_state = prev_st; - } - else - wc = (wint_t) wc2; - /* Then proceed the next character. */ - rawbuf_idx += mbclen; - } - *last_wc = (wint_t) wc; - return rawbuf_idx; -} -#endif /* RE_ENABLE_I18N */ - -/* Build the buffer PSTR->MBS, and apply the translation if we need. - This function is used in case of REG_ICASE. */ - -static void -internal_function -build_upper_buffer (re_string_t *pstr) -{ - int char_idx, end_idx; - end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len; - - for (char_idx = pstr->valid_len; char_idx < end_idx; ++char_idx) - { - int ch = pstr->raw_mbs[pstr->raw_mbs_idx + char_idx]; - if (BE (pstr->trans != NULL, 0)) - ch = pstr->trans[ch]; - if (islower (ch)) - pstr->mbs[char_idx] = toupper (ch); - else - pstr->mbs[char_idx] = ch; - } - pstr->valid_len = char_idx; - pstr->valid_raw_len = char_idx; -} - -/* Apply TRANS to the buffer in PSTR. */ - -static void -internal_function -re_string_translate_buffer (re_string_t *pstr) -{ - int buf_idx, end_idx; - end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len; - - for (buf_idx = pstr->valid_len; buf_idx < end_idx; ++buf_idx) - { - int ch = pstr->raw_mbs[pstr->raw_mbs_idx + buf_idx]; - pstr->mbs[buf_idx] = pstr->trans[ch]; - } - - pstr->valid_len = buf_idx; - pstr->valid_raw_len = buf_idx; -} - -/* This function re-construct the buffers. - Concretely, convert to wide character in case of pstr->mb_cur_max > 1, - convert to upper case in case of REG_ICASE, apply translation. */ - -static reg_errcode_t -internal_function -re_string_reconstruct (re_string_t *pstr, int idx, int eflags) -{ - int offset = idx - pstr->raw_mbs_idx; - if (BE (offset < 0, 0)) - { - /* Reset buffer. */ -#ifdef RE_ENABLE_I18N - if (pstr->mb_cur_max > 1) - memset (&pstr->cur_state, '\0', sizeof (mbstate_t)); -#endif /* RE_ENABLE_I18N */ - pstr->len = pstr->raw_len; - pstr->stop = pstr->raw_stop; - pstr->valid_len = 0; - pstr->raw_mbs_idx = 0; - pstr->valid_raw_len = 0; - pstr->offsets_needed = 0; - pstr->tip_context = ((eflags & REG_NOTBOL) ? CONTEXT_BEGBUF - : CONTEXT_NEWLINE | CONTEXT_BEGBUF); - if (!pstr->mbs_allocated) - pstr->mbs = (unsigned char *) pstr->raw_mbs; - offset = idx; - } - - if (BE (offset != 0, 1)) - { - /* Should the already checked characters be kept? */ - if (BE (offset < pstr->valid_raw_len, 1)) - { - /* Yes, move them to the front of the buffer. */ -#ifdef RE_ENABLE_I18N - if (BE (pstr->offsets_needed, 0)) - { - int low = 0, high = pstr->valid_len, mid; - do - { - mid = (high + low) / 2; - if (pstr->offsets[mid] > offset) - high = mid; - else if (pstr->offsets[mid] < offset) - low = mid + 1; - else - break; - } - while (low < high); - if (pstr->offsets[mid] < offset) - ++mid; - pstr->tip_context = re_string_context_at (pstr, mid - 1, - eflags); - /* This can be quite complicated, so handle specially - only the common and easy case where the character with - different length representation of lower and upper - case is present at or after offset. */ - if (pstr->valid_len > offset - && mid == offset && pstr->offsets[mid] == offset) - { - memmove (pstr->wcs, pstr->wcs + offset, - (pstr->valid_len - offset) * sizeof (wint_t)); - memmove (pstr->mbs, pstr->mbs + offset, pstr->valid_len - offset); - pstr->valid_len -= offset; - pstr->valid_raw_len -= offset; - for (low = 0; low < pstr->valid_len; low++) - pstr->offsets[low] = pstr->offsets[low + offset] - offset; - } - else - { - /* Otherwise, just find out how long the partial multibyte - character at offset is and fill it with WEOF/255. */ - pstr->len = pstr->raw_len - idx + offset; - pstr->stop = pstr->raw_stop - idx + offset; - pstr->offsets_needed = 0; - while (mid > 0 && pstr->offsets[mid - 1] == offset) - --mid; - while (mid < pstr->valid_len) - if (pstr->wcs[mid] != WEOF) - break; - else - ++mid; - if (mid == pstr->valid_len) - pstr->valid_len = 0; - else - { - pstr->valid_len = pstr->offsets[mid] - offset; - if (pstr->valid_len) - { - for (low = 0; low < pstr->valid_len; ++low) - pstr->wcs[low] = WEOF; - memset (pstr->mbs, 255, pstr->valid_len); - } - } - pstr->valid_raw_len = pstr->valid_len; - } - } - else -#endif - { - pstr->tip_context = re_string_context_at (pstr, offset - 1, - eflags); -#ifdef RE_ENABLE_I18N - if (pstr->mb_cur_max > 1) - memmove (pstr->wcs, pstr->wcs + offset, - (pstr->valid_len - offset) * sizeof (wint_t)); -#endif /* RE_ENABLE_I18N */ - if (BE (pstr->mbs_allocated, 0)) - memmove (pstr->mbs, pstr->mbs + offset, - pstr->valid_len - offset); - pstr->valid_len -= offset; - pstr->valid_raw_len -= offset; -#if DEBUG - assert (pstr->valid_len > 0); -#endif - } - } - else - { -#ifdef RE_ENABLE_I18N - /* No, skip all characters until IDX. */ - int prev_valid_len = pstr->valid_len; - - if (BE (pstr->offsets_needed, 0)) - { - pstr->len = pstr->raw_len - idx + offset; - pstr->stop = pstr->raw_stop - idx + offset; - pstr->offsets_needed = 0; - } -#endif - pstr->valid_len = 0; -#ifdef RE_ENABLE_I18N - if (pstr->mb_cur_max > 1) - { - int wcs_idx; - wint_t wc = WEOF; - - if (pstr->is_utf8) - { - const unsigned char *raw, *p, *end; - - /* Special case UTF-8. Multi-byte chars start with any - byte other than 0x80 - 0xbf. */ - raw = pstr->raw_mbs + pstr->raw_mbs_idx; - end = raw + (offset - pstr->mb_cur_max); - if (end < pstr->raw_mbs) - end = pstr->raw_mbs; - p = raw + offset - 1; -#ifdef _LIBC - /* We know the wchar_t encoding is UCS4, so for the simple - case, ASCII characters, skip the conversion step. */ - if (isascii (*p) && BE (pstr->trans == NULL, 1)) - { - memset (&pstr->cur_state, '\0', sizeof (mbstate_t)); - /* pstr->valid_len = 0; */ - wc = (wchar_t) *p; - } - else -#endif - for (; p >= end; --p) - if ((*p & 0xc0) != 0x80) - { - mbstate_t cur_state; - wchar_t wc2; - int mlen = raw + pstr->len - p; - unsigned char buf[6]; - size_t mbclen; - - if (BE (pstr->trans != NULL, 0)) - { - int i = mlen < 6 ? mlen : 6; - while (--i >= 0) - buf[i] = pstr->trans[p[i]]; - } - /* XXX Don't use mbrtowc, we know which conversion - to use (UTF-8 -> UCS4). */ - memset (&cur_state, 0, sizeof (cur_state)); - mbclen = __mbrtowc (&wc2, (const char *) p, mlen, - &cur_state); - if (raw + offset - p <= mbclen - && mbclen < (size_t) -2) - { - memset (&pstr->cur_state, '\0', - sizeof (mbstate_t)); - pstr->valid_len = mbclen - (raw + offset - p); - wc = wc2; - } - break; - } - } - - if (wc == WEOF) - pstr->valid_len = re_string_skip_chars (pstr, idx, &wc) - idx; - if (wc == WEOF) - pstr->tip_context - = re_string_context_at (pstr, prev_valid_len - 1, eflags); - else - pstr->tip_context = ((BE (pstr->word_ops_used != 0, 0) - && IS_WIDE_WORD_CHAR (wc)) - ? CONTEXT_WORD - : ((IS_WIDE_NEWLINE (wc) - && pstr->newline_anchor) - ? CONTEXT_NEWLINE : 0)); - if (BE (pstr->valid_len, 0)) - { - for (wcs_idx = 0; wcs_idx < pstr->valid_len; ++wcs_idx) - pstr->wcs[wcs_idx] = WEOF; - if (pstr->mbs_allocated) - memset (pstr->mbs, 255, pstr->valid_len); - } - pstr->valid_raw_len = pstr->valid_len; - } - else -#endif /* RE_ENABLE_I18N */ - { - int c = pstr->raw_mbs[pstr->raw_mbs_idx + offset - 1]; - pstr->valid_raw_len = 0; - if (pstr->trans) - c = pstr->trans[c]; - pstr->tip_context = (bitset_contain (pstr->word_char, c) - ? CONTEXT_WORD - : ((IS_NEWLINE (c) && pstr->newline_anchor) - ? CONTEXT_NEWLINE : 0)); - } - } - if (!BE (pstr->mbs_allocated, 0)) - pstr->mbs += offset; - } - pstr->raw_mbs_idx = idx; - pstr->len -= offset; - pstr->stop -= offset; - - /* Then build the buffers. */ -#ifdef RE_ENABLE_I18N - if (pstr->mb_cur_max > 1) - { - if (pstr->icase) - { - reg_errcode_t ret = build_wcs_upper_buffer (pstr); - if (BE (ret != REG_NOERROR, 0)) - return ret; - } - else - build_wcs_buffer (pstr); - } - else -#endif /* RE_ENABLE_I18N */ - if (BE (pstr->mbs_allocated, 0)) - { - if (pstr->icase) - build_upper_buffer (pstr); - else if (pstr->trans != NULL) - re_string_translate_buffer (pstr); - } - else - pstr->valid_len = pstr->len; - - pstr->cur_idx = 0; - return REG_NOERROR; -} - -static unsigned char -internal_function __attribute ((pure)) -re_string_peek_byte_case (const re_string_t *pstr, int idx) -{ - int ch, off; - - /* Handle the common (easiest) cases first. */ - if (BE (!pstr->mbs_allocated, 1)) - return re_string_peek_byte (pstr, idx); - -#ifdef RE_ENABLE_I18N - if (pstr->mb_cur_max > 1 - && ! re_string_is_single_byte_char (pstr, pstr->cur_idx + idx)) - return re_string_peek_byte (pstr, idx); -#endif - - off = pstr->cur_idx + idx; -#ifdef RE_ENABLE_I18N - if (pstr->offsets_needed) - off = pstr->offsets[off]; -#endif - - ch = pstr->raw_mbs[pstr->raw_mbs_idx + off]; - -#ifdef RE_ENABLE_I18N - /* Ensure that e.g. for tr_TR.UTF-8 BACKSLASH DOTLESS SMALL LETTER I - this function returns CAPITAL LETTER I instead of first byte of - DOTLESS SMALL LETTER I. The latter would confuse the parser, - since peek_byte_case doesn't advance cur_idx in any way. */ - if (pstr->offsets_needed && !isascii (ch)) - return re_string_peek_byte (pstr, idx); -#endif - - return ch; -} - -static unsigned char -internal_function __attribute ((pure)) -re_string_fetch_byte_case (re_string_t *pstr) -{ - if (BE (!pstr->mbs_allocated, 1)) - return re_string_fetch_byte (pstr); - -#ifdef RE_ENABLE_I18N - if (pstr->offsets_needed) - { - int off, ch; - - /* For tr_TR.UTF-8 [[:islower:]] there is - [[: CAPITAL LETTER I WITH DOT lower:]] in mbs. Skip - in that case the whole multi-byte character and return - the original letter. On the other side, with - [[: DOTLESS SMALL LETTER I return [[:I, as doing - anything else would complicate things too much. */ - - if (!re_string_first_byte (pstr, pstr->cur_idx)) - return re_string_fetch_byte (pstr); - - off = pstr->offsets[pstr->cur_idx]; - ch = pstr->raw_mbs[pstr->raw_mbs_idx + off]; - - if (! isascii (ch)) - return re_string_fetch_byte (pstr); - - re_string_skip_bytes (pstr, - re_string_char_size_at (pstr, pstr->cur_idx)); - return ch; - } -#endif - - return pstr->raw_mbs[pstr->raw_mbs_idx + pstr->cur_idx++]; -} - -static void -internal_function -re_string_destruct (re_string_t *pstr) -{ -#ifdef RE_ENABLE_I18N - re_free (pstr->wcs); - re_free (pstr->offsets); -#endif /* RE_ENABLE_I18N */ - if (pstr->mbs_allocated) - re_free (pstr->mbs); -} - -/* Return the context at IDX in INPUT. */ - -static unsigned int -internal_function -re_string_context_at (const re_string_t *input, int idx, int eflags) -{ - int c; - if (BE (idx < 0, 0)) - /* In this case, we use the value stored in input->tip_context, - since we can't know the character in input->mbs[-1] here. */ - return input->tip_context; - if (BE (idx == input->len, 0)) - return ((eflags & REG_NOTEOL) ? CONTEXT_ENDBUF - : CONTEXT_NEWLINE | CONTEXT_ENDBUF); -#ifdef RE_ENABLE_I18N - if (input->mb_cur_max > 1) - { - wint_t wc; - int wc_idx = idx; - while(input->wcs[wc_idx] == WEOF) - { -#ifdef DEBUG - /* It must not happen. */ - assert (wc_idx >= 0); -#endif - --wc_idx; - if (wc_idx < 0) - return input->tip_context; - } - wc = input->wcs[wc_idx]; - if (BE (input->word_ops_used != 0, 0) && IS_WIDE_WORD_CHAR (wc)) - return CONTEXT_WORD; - return (IS_WIDE_NEWLINE (wc) && input->newline_anchor - ? CONTEXT_NEWLINE : 0); - } - else -#endif - { - c = re_string_byte_at (input, idx); - if (bitset_contain (input->word_char, c)) - return CONTEXT_WORD; - return IS_NEWLINE (c) && input->newline_anchor ? CONTEXT_NEWLINE : 0; - } -} - -/* Functions for set operation. */ - -static reg_errcode_t -internal_function -re_node_set_alloc (re_node_set *set, int size) -{ - /* - * ADR: valgrind says size can be 0, which then doesn't - * free the block of size 0. Harumph. This seems - * to work ok, though. - */ - if (size == 0) - { - memset(set, 0, sizeof(*set)); - return REG_NOERROR; - } - set->alloc = size; - set->nelem = 0; - set->elems = re_malloc (int, size); - if (BE (set->elems == NULL, 0)) - return REG_ESPACE; - return REG_NOERROR; -} - -static reg_errcode_t -internal_function -re_node_set_init_1 (re_node_set *set, int elem) -{ - set->alloc = 1; - set->nelem = 1; - set->elems = re_malloc (int, 1); - if (BE (set->elems == NULL, 0)) - { - set->alloc = set->nelem = 0; - return REG_ESPACE; - } - set->elems[0] = elem; - return REG_NOERROR; -} - -static reg_errcode_t -internal_function -re_node_set_init_2 (re_node_set *set, int elem1, int elem2) -{ - set->alloc = 2; - set->elems = re_malloc (int, 2); - if (BE (set->elems == NULL, 0)) - return REG_ESPACE; - if (elem1 == elem2) - { - set->nelem = 1; - set->elems[0] = elem1; - } - else - { - set->nelem = 2; - if (elem1 < elem2) - { - set->elems[0] = elem1; - set->elems[1] = elem2; - } - else - { - set->elems[0] = elem2; - set->elems[1] = elem1; - } - } - return REG_NOERROR; -} - -static reg_errcode_t -internal_function -re_node_set_init_copy (re_node_set *dest, const re_node_set *src) -{ - dest->nelem = src->nelem; - if (src->nelem > 0) - { - dest->alloc = dest->nelem; - dest->elems = re_malloc (int, dest->alloc); - if (BE (dest->elems == NULL, 0)) - { - dest->alloc = dest->nelem = 0; - return REG_ESPACE; - } - memcpy (dest->elems, src->elems, src->nelem * sizeof (int)); - } - else - re_node_set_init_empty (dest); - return REG_NOERROR; -} - -/* Calculate the intersection of the sets SRC1 and SRC2. And merge it to - DEST. Return value indicate the error code or REG_NOERROR if succeeded. - Note: We assume dest->elems is NULL, when dest->alloc is 0. */ - -static reg_errcode_t -internal_function -re_node_set_add_intersect (re_node_set *dest, const re_node_set *src1, - const re_node_set *src2) -{ - int i1, i2, is, id, delta, sbase; - if (src1->nelem == 0 || src2->nelem == 0) - return REG_NOERROR; - - /* We need dest->nelem + 2 * elems_in_intersection; this is a - conservative estimate. */ - if (src1->nelem + src2->nelem + dest->nelem > dest->alloc) - { - int new_alloc = src1->nelem + src2->nelem + dest->alloc; - int *new_elems = re_realloc (dest->elems, int, new_alloc); - if (BE (new_elems == NULL, 0)) - return REG_ESPACE; - dest->elems = new_elems; - dest->alloc = new_alloc; - } - - /* Find the items in the intersection of SRC1 and SRC2, and copy - into the top of DEST those that are not already in DEST itself. */ - sbase = dest->nelem + src1->nelem + src2->nelem; - i1 = src1->nelem - 1; - i2 = src2->nelem - 1; - id = dest->nelem - 1; - for (;;) - { - if (src1->elems[i1] == src2->elems[i2]) - { - /* Try to find the item in DEST. Maybe we could binary search? */ - while (id >= 0 && dest->elems[id] > src1->elems[i1]) - --id; - - if (id < 0 || dest->elems[id] != src1->elems[i1]) - dest->elems[--sbase] = src1->elems[i1]; - - if (--i1 < 0 || --i2 < 0) - break; - } - - /* Lower the highest of the two items. */ - else if (src1->elems[i1] < src2->elems[i2]) - { - if (--i2 < 0) - break; - } - else - { - if (--i1 < 0) - break; - } - } - - id = dest->nelem - 1; - is = dest->nelem + src1->nelem + src2->nelem - 1; - delta = is - sbase + 1; - - /* Now copy. When DELTA becomes zero, the remaining - DEST elements are already in place; this is more or - less the same loop that is in re_node_set_merge. */ - dest->nelem += delta; - if (delta > 0 && id >= 0) - for (;;) - { - if (dest->elems[is] > dest->elems[id]) - { - /* Copy from the top. */ - dest->elems[id + delta--] = dest->elems[is--]; - if (delta == 0) - break; - } - else - { - /* Slide from the bottom. */ - dest->elems[id + delta] = dest->elems[id]; - if (--id < 0) - break; - } - } - - /* Copy remaining SRC elements. */ - memcpy (dest->elems, dest->elems + sbase, delta * sizeof (int)); - - return REG_NOERROR; -} - -/* Calculate the union set of the sets SRC1 and SRC2. And store it to - DEST. Return value indicate the error code or REG_NOERROR if succeeded. */ - -static reg_errcode_t -internal_function -re_node_set_init_union (re_node_set *dest, const re_node_set *src1, - const re_node_set *src2) -{ - int i1, i2, id; - if (src1 != NULL && src1->nelem > 0 && src2 != NULL && src2->nelem > 0) - { - dest->alloc = src1->nelem + src2->nelem; - dest->elems = re_malloc (int, dest->alloc); - if (BE (dest->elems == NULL, 0)) - return REG_ESPACE; - } - else - { - if (src1 != NULL && src1->nelem > 0) - return re_node_set_init_copy (dest, src1); - else if (src2 != NULL && src2->nelem > 0) - return re_node_set_init_copy (dest, src2); - else - re_node_set_init_empty (dest); - return REG_NOERROR; - } - for (i1 = i2 = id = 0 ; i1 < src1->nelem && i2 < src2->nelem ;) - { - if (src1->elems[i1] > src2->elems[i2]) - { - dest->elems[id++] = src2->elems[i2++]; - continue; - } - if (src1->elems[i1] == src2->elems[i2]) - ++i2; - dest->elems[id++] = src1->elems[i1++]; - } - if (i1 < src1->nelem) - { - memcpy (dest->elems + id, src1->elems + i1, - (src1->nelem - i1) * sizeof (int)); - id += src1->nelem - i1; - } - else if (i2 < src2->nelem) - { - memcpy (dest->elems + id, src2->elems + i2, - (src2->nelem - i2) * sizeof (int)); - id += src2->nelem - i2; - } - dest->nelem = id; - return REG_NOERROR; -} - -/* Calculate the union set of the sets DEST and SRC. And store it to - DEST. Return value indicate the error code or REG_NOERROR if succeeded. */ - -static reg_errcode_t -internal_function -re_node_set_merge (re_node_set *dest, const re_node_set *src) -{ - int is, id, sbase, delta; - if (src == NULL || src->nelem == 0) - return REG_NOERROR; - if (dest->alloc < 2 * src->nelem + dest->nelem) - { - int new_alloc = 2 * (src->nelem + dest->alloc); - int *new_buffer = re_realloc (dest->elems, int, new_alloc); - if (BE (new_buffer == NULL, 0)) - return REG_ESPACE; - dest->elems = new_buffer; - dest->alloc = new_alloc; - } - - if (BE (dest->nelem == 0, 0)) - { - dest->nelem = src->nelem; - memcpy (dest->elems, src->elems, src->nelem * sizeof (int)); - return REG_NOERROR; - } - - /* Copy into the top of DEST the items of SRC that are not - found in DEST. Maybe we could binary search in DEST? */ - for (sbase = dest->nelem + 2 * src->nelem, - is = src->nelem - 1, id = dest->nelem - 1; is >= 0 && id >= 0; ) - { - if (dest->elems[id] == src->elems[is]) - is--, id--; - else if (dest->elems[id] < src->elems[is]) - dest->elems[--sbase] = src->elems[is--]; - else /* if (dest->elems[id] > src->elems[is]) */ - --id; - } - - if (is >= 0) - { - /* If DEST is exhausted, the remaining items of SRC must be unique. */ - sbase -= is + 1; - memcpy (dest->elems + sbase, src->elems, (is + 1) * sizeof (int)); - } - - id = dest->nelem - 1; - is = dest->nelem + 2 * src->nelem - 1; - delta = is - sbase + 1; - if (delta == 0) - return REG_NOERROR; - - /* Now copy. When DELTA becomes zero, the remaining - DEST elements are already in place. */ - dest->nelem += delta; - for (;;) - { - if (dest->elems[is] > dest->elems[id]) - { - /* Copy from the top. */ - dest->elems[id + delta--] = dest->elems[is--]; - if (delta == 0) - break; - } - else - { - /* Slide from the bottom. */ - dest->elems[id + delta] = dest->elems[id]; - if (--id < 0) - { - /* Copy remaining SRC elements. */ - memcpy (dest->elems, dest->elems + sbase, - delta * sizeof (int)); - break; - } - } - } - - return REG_NOERROR; -} - -/* Insert the new element ELEM to the re_node_set* SET. - SET should not already have ELEM. - return -1 if an error is occured, return 1 otherwise. */ - -static int -internal_function -re_node_set_insert (re_node_set *set, int elem) -{ - int idx; - /* In case the set is empty. */ - if (set->alloc == 0) - { - if (BE (re_node_set_init_1 (set, elem) == REG_NOERROR, 1)) - return 1; - else - return -1; - } - - if (BE (set->nelem, 0) == 0) - { - /* We already guaranteed above that set->alloc != 0. */ - set->elems[0] = elem; - ++set->nelem; - return 1; - } - - /* Realloc if we need. */ - if (set->alloc == set->nelem) - { - int *new_elems; - set->alloc = set->alloc * 2; - new_elems = re_realloc (set->elems, int, set->alloc); - if (BE (new_elems == NULL, 0)) - return -1; - set->elems = new_elems; - } - - /* Move the elements which follows the new element. Test the - first element separately to skip a check in the inner loop. */ - if (elem < set->elems[0]) - { - idx = 0; - for (idx = set->nelem; idx > 0; idx--) - set->elems[idx] = set->elems[idx - 1]; - } - else - { - for (idx = set->nelem; set->elems[idx - 1] > elem; idx--) - set->elems[idx] = set->elems[idx - 1]; - } - - /* Insert the new element. */ - set->elems[idx] = elem; - ++set->nelem; - return 1; -} - -/* Insert the new element ELEM to the re_node_set* SET. - SET should not already have any element greater than or equal to ELEM. - Return -1 if an error is occured, return 1 otherwise. */ - -static int -internal_function -re_node_set_insert_last (re_node_set *set, int elem) -{ - /* Realloc if we need. */ - if (set->alloc == set->nelem) - { - int *new_elems; - set->alloc = (set->alloc + 1) * 2; - new_elems = re_realloc (set->elems, int, set->alloc); - if (BE (new_elems == NULL, 0)) - return -1; - set->elems = new_elems; - } - - /* Insert the new element. */ - set->elems[set->nelem++] = elem; - return 1; -} - -/* Compare two node sets SET1 and SET2. - return 1 if SET1 and SET2 are equivalent, return 0 otherwise. */ - -static int -internal_function __attribute ((pure)) -re_node_set_compare (const re_node_set *set1, const re_node_set *set2) -{ - int i; - if (set1 == NULL || set2 == NULL || set1->nelem != set2->nelem) - return 0; - for (i = set1->nelem ; --i >= 0 ; ) - if (set1->elems[i] != set2->elems[i]) - return 0; - return 1; -} - -/* Return (idx + 1) if SET contains the element ELEM, return 0 otherwise. */ - -static int -internal_function __attribute ((pure)) -re_node_set_contains (const re_node_set *set, int elem) -{ - unsigned int idx, right, mid; - if (set->nelem <= 0) - return 0; - - /* Binary search the element. */ - idx = 0; - right = set->nelem - 1; - while (idx < right) - { - mid = (idx + right) / 2; - if (set->elems[mid] < elem) - idx = mid + 1; - else - right = mid; - } - return set->elems[idx] == elem ? idx + 1 : 0; -} - -static void -internal_function -re_node_set_remove_at (re_node_set *set, int idx) -{ - if (idx < 0 || idx >= set->nelem) - return; - --set->nelem; - for (; idx < set->nelem; idx++) - set->elems[idx] = set->elems[idx + 1]; -} - - -/* Add the token TOKEN to dfa->nodes, and return the index of the token. - Or return -1, if an error will be occured. */ - -static int -internal_function -re_dfa_add_node (re_dfa_t *dfa, re_token_t token) -{ - if (BE (dfa->nodes_len >= dfa->nodes_alloc, 0)) - { - size_t new_nodes_alloc = dfa->nodes_alloc * 2; - int *new_nexts, *new_indices; - re_node_set *new_edests, *new_eclosures; - re_token_t *new_nodes; - - /* Avoid overflows in realloc. */ - const size_t max_object_size = MAX (sizeof (re_token_t), - MAX (sizeof (re_node_set), - sizeof (int))); - if (BE (SIZE_MAX / max_object_size < new_nodes_alloc, 0)) - return -1; - - new_nodes = re_realloc (dfa->nodes, re_token_t, new_nodes_alloc); - if (BE (new_nodes == NULL, 0)) - return -1; - dfa->nodes = new_nodes; - new_nexts = re_realloc (dfa->nexts, int, new_nodes_alloc); - new_indices = re_realloc (dfa->org_indices, int, new_nodes_alloc); - new_edests = re_realloc (dfa->edests, re_node_set, new_nodes_alloc); - new_eclosures = re_realloc (dfa->eclosures, re_node_set, new_nodes_alloc); - if (BE (new_nexts == NULL || new_indices == NULL - || new_edests == NULL || new_eclosures == NULL, 0)) - return -1; - dfa->nexts = new_nexts; - dfa->org_indices = new_indices; - dfa->edests = new_edests; - dfa->eclosures = new_eclosures; - dfa->nodes_alloc = new_nodes_alloc; - } - dfa->nodes[dfa->nodes_len] = token; - dfa->nodes[dfa->nodes_len].constraint = 0; -#ifdef RE_ENABLE_I18N - dfa->nodes[dfa->nodes_len].accept_mb = - (token.type == OP_PERIOD && dfa->mb_cur_max > 1) || token.type == COMPLEX_BRACKET; -#endif - dfa->nexts[dfa->nodes_len] = -1; - re_node_set_init_empty (dfa->edests + dfa->nodes_len); - re_node_set_init_empty (dfa->eclosures + dfa->nodes_len); - return dfa->nodes_len++; -} - -static inline unsigned int -internal_function -calc_state_hash (const re_node_set *nodes, unsigned int context) -{ - unsigned int hash = nodes->nelem + context; - int i; - for (i = 0 ; i < nodes->nelem ; i++) - hash += nodes->elems[i]; - return hash; -} - -/* Search for the state whose node_set is equivalent to NODES. - Return the pointer to the state, if we found it in the DFA. - Otherwise create the new one and return it. In case of an error - return NULL and set the error code in ERR. - Note: - We assume NULL as the invalid state, then it is possible that - return value is NULL and ERR is REG_NOERROR. - - We never return non-NULL value in case of any errors, it is for - optimization. */ - -static re_dfastate_t * -internal_function -re_acquire_state (reg_errcode_t *err, const re_dfa_t *dfa, - const re_node_set *nodes) -{ - unsigned int hash; - re_dfastate_t *new_state; - struct re_state_table_entry *spot; - int i; - if (BE (nodes->nelem == 0, 0)) - { - *err = REG_NOERROR; - return NULL; - } - hash = calc_state_hash (nodes, 0); - spot = dfa->state_table + (hash & dfa->state_hash_mask); - - for (i = 0 ; i < spot->num ; i++) - { - re_dfastate_t *state = spot->array[i]; - if (hash != state->hash) - continue; - if (re_node_set_compare (&state->nodes, nodes)) - return state; - } - - /* There are no appropriate state in the dfa, create the new one. */ - new_state = create_ci_newstate (dfa, nodes, hash); - if (BE (new_state == NULL, 0)) - *err = REG_ESPACE; - - return new_state; -} - -/* Search for the state whose node_set is equivalent to NODES and - whose context is equivalent to CONTEXT. - Return the pointer to the state, if we found it in the DFA. - Otherwise create the new one and return it. In case of an error - return NULL and set the error code in ERR. - Note: - We assume NULL as the invalid state, then it is possible that - return value is NULL and ERR is REG_NOERROR. - - We never return non-NULL value in case of any errors, it is for - optimization. */ - -static re_dfastate_t * -internal_function -re_acquire_state_context (reg_errcode_t *err, const re_dfa_t *dfa, - const re_node_set *nodes, unsigned int context) -{ - unsigned int hash; - re_dfastate_t *new_state; - struct re_state_table_entry *spot; - int i; - if (nodes->nelem == 0) - { - *err = REG_NOERROR; - return NULL; - } - hash = calc_state_hash (nodes, context); - spot = dfa->state_table + (hash & dfa->state_hash_mask); - - for (i = 0 ; i < spot->num ; i++) - { - re_dfastate_t *state = spot->array[i]; - if (state->hash == hash - && state->context == context - && re_node_set_compare (state->entrance_nodes, nodes)) - return state; - } - /* There are no appropriate state in `dfa', create the new one. */ - new_state = create_cd_newstate (dfa, nodes, context, hash); - if (BE (new_state == NULL, 0)) - *err = REG_ESPACE; - - return new_state; -} - -/* Finish initialization of the new state NEWSTATE, and using its hash value - HASH put in the appropriate bucket of DFA's state table. Return value - indicates the error code if failed. */ - -static reg_errcode_t -register_state (const re_dfa_t *dfa, re_dfastate_t *newstate, - unsigned int hash) -{ - struct re_state_table_entry *spot; - reg_errcode_t err; - int i; - - newstate->hash = hash; - err = re_node_set_alloc (&newstate->non_eps_nodes, newstate->nodes.nelem); - if (BE (err != REG_NOERROR, 0)) - return REG_ESPACE; - for (i = 0; i < newstate->nodes.nelem; i++) - { - int elem = newstate->nodes.elems[i]; - if (!IS_EPSILON_NODE (dfa->nodes[elem].type)) - if (re_node_set_insert_last (&newstate->non_eps_nodes, elem) < 0) - return REG_ESPACE; - } - - spot = dfa->state_table + (hash & dfa->state_hash_mask); - if (BE (spot->alloc <= spot->num, 0)) - { - int new_alloc = 2 * spot->num + 2; - re_dfastate_t **new_array = re_realloc (spot->array, re_dfastate_t *, - new_alloc); - if (BE (new_array == NULL, 0)) - return REG_ESPACE; - spot->array = new_array; - spot->alloc = new_alloc; - } - spot->array[spot->num++] = newstate; - return REG_NOERROR; -} - -static void -free_state (re_dfastate_t *state) -{ - re_node_set_free (&state->non_eps_nodes); - re_node_set_free (&state->inveclosure); - if (state->entrance_nodes != &state->nodes) - { - re_node_set_free (state->entrance_nodes); - re_free (state->entrance_nodes); - } - re_node_set_free (&state->nodes); - re_free (state->word_trtable); - re_free (state->trtable); - re_free (state); -} - -/* Create the new state which is independ of contexts. - Return the new state if succeeded, otherwise return NULL. */ - -static re_dfastate_t * -internal_function -create_ci_newstate (const re_dfa_t *dfa, const re_node_set *nodes, - unsigned int hash) -{ - int i; - reg_errcode_t err; - re_dfastate_t *newstate; - - newstate = (re_dfastate_t *) calloc (sizeof (re_dfastate_t), 1); - if (BE (newstate == NULL, 0)) - return NULL; - err = re_node_set_init_copy (&newstate->nodes, nodes); - if (BE (err != REG_NOERROR, 0)) - { - re_free (newstate); - return NULL; - } - - newstate->entrance_nodes = &newstate->nodes; - for (i = 0 ; i < nodes->nelem ; i++) - { - re_token_t *node = dfa->nodes + nodes->elems[i]; - re_token_type_t type = node->type; - if (type == CHARACTER && !node->constraint) - continue; -#ifdef RE_ENABLE_I18N - newstate->accept_mb |= node->accept_mb; -#endif /* RE_ENABLE_I18N */ - - /* If the state has the halt node, the state is a halt state. */ - if (type == END_OF_RE) - newstate->halt = 1; - else if (type == OP_BACK_REF) - newstate->has_backref = 1; - else if (type == ANCHOR || node->constraint) - newstate->has_constraint = 1; - } - err = register_state (dfa, newstate, hash); - if (BE (err != REG_NOERROR, 0)) - { - free_state (newstate); - newstate = NULL; - } - return newstate; -} - -/* Create the new state which is depend on the context CONTEXT. - Return the new state if succeeded, otherwise return NULL. */ - -static re_dfastate_t * -internal_function -create_cd_newstate (const re_dfa_t *dfa, const re_node_set *nodes, - unsigned int context, unsigned int hash) -{ - int i, nctx_nodes = 0; - reg_errcode_t err; - re_dfastate_t *newstate; - - newstate = (re_dfastate_t *) calloc (sizeof (re_dfastate_t), 1); - if (BE (newstate == NULL, 0)) - return NULL; - err = re_node_set_init_copy (&newstate->nodes, nodes); - if (BE (err != REG_NOERROR, 0)) - { - re_free (newstate); - return NULL; - } - - newstate->context = context; - newstate->entrance_nodes = &newstate->nodes; - - for (i = 0 ; i < nodes->nelem ; i++) - { - re_token_t *node = dfa->nodes + nodes->elems[i]; - re_token_type_t type = node->type; - unsigned int constraint = node->constraint; - - if (type == CHARACTER && !constraint) - continue; -#ifdef RE_ENABLE_I18N - newstate->accept_mb |= node->accept_mb; -#endif /* RE_ENABLE_I18N */ - - /* If the state has the halt node, the state is a halt state. */ - if (type == END_OF_RE) - newstate->halt = 1; - else if (type == OP_BACK_REF) - newstate->has_backref = 1; - - if (constraint) - { - if (newstate->entrance_nodes == &newstate->nodes) - { - newstate->entrance_nodes = re_malloc (re_node_set, 1); - if (BE (newstate->entrance_nodes == NULL, 0)) - { - free_state (newstate); - return NULL; - } - if (re_node_set_init_copy (newstate->entrance_nodes, nodes) - != REG_NOERROR) - return NULL; - nctx_nodes = 0; - newstate->has_constraint = 1; - } - - if (NOT_SATISFY_PREV_CONSTRAINT (constraint,context)) - { - re_node_set_remove_at (&newstate->nodes, i - nctx_nodes); - ++nctx_nodes; - } - } - } - err = register_state (dfa, newstate, hash); - if (BE (err != REG_NOERROR, 0)) - { - free_state (newstate); - newstate = NULL; - } - return newstate; -} diff --git a/deps/regex/regex_internal.h b/deps/regex/regex_internal.h deleted file mode 100644 index 53ccebe..0000000 --- a/deps/regex/regex_internal.h +++ /dev/null @@ -1,819 +0,0 @@ -/* Extended regular expression matching and search library. - Copyright (C) 2002-2005, 2007, 2008, 2010 Free Software Foundation, Inc. - This file is part of the GNU C Library. - Contributed by Isamu Hasegawa . - - The GNU C Library is free software; you can redistribute it and/or - modify it under the terms of the GNU Lesser General Public - License as published by the Free Software Foundation; either - version 2.1 of the License, or (at your option) any later version. - - The GNU C Library is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - Lesser General Public License for more details. - - You should have received a copy of the GNU Lesser General Public - License along with the GNU C Library; if not, write to the Free - Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA - 02111-1307 USA. */ - -#ifndef _REGEX_INTERNAL_H -#define _REGEX_INTERNAL_H 1 - -#include -#include -#include -#include -#include - -#ifndef UNUSED -# ifdef __GNUC__ -# define UNUSED __attribute__((unused)) -# else -# define UNUSED -# endif -#endif - -#if defined HAVE_LANGINFO_H || defined HAVE_LANGINFO_CODESET || defined _LIBC -# include -#endif -#if defined HAVE_LOCALE_H || defined _LIBC -# include -#endif -#if defined HAVE_WCHAR_H || defined _LIBC -# include -#endif /* HAVE_WCHAR_H || _LIBC */ -#if defined HAVE_WCTYPE_H || defined _LIBC -# include -#endif /* HAVE_WCTYPE_H || _LIBC */ -#if defined HAVE_STDBOOL_H || defined _LIBC -# include -#endif /* HAVE_STDBOOL_H || _LIBC */ -#if !defined(ZOS_USS) -#if defined HAVE_STDINT_H || defined _LIBC -# include -#endif /* HAVE_STDINT_H || _LIBC */ -#endif /* !ZOS_USS */ -#if defined _LIBC -# include -#else -# define __libc_lock_define(CLASS,NAME) -# define __libc_lock_init(NAME) do { } while (0) -# define __libc_lock_lock(NAME) do { } while (0) -# define __libc_lock_unlock(NAME) do { } while (0) -#endif - -#ifndef GAWK -/* In case that the system doesn't have isblank(). */ -#if !defined _LIBC && !defined HAVE_ISBLANK && !defined isblank -# define isblank(ch) ((ch) == ' ' || (ch) == '\t') -#endif -#else /* GAWK */ -/* - * This is a mess. On glibc systems you have to define - * a magic constant to get isblank() out of , since it's - * a C99 function. To heck with all that and borrow a page from - * dfa.c's book. - */ - -static int -is_blank (int c) -{ - return (c == ' ' || c == '\t'); -} -#endif /* GAWK */ - -#ifdef _LIBC -# ifndef _RE_DEFINE_LOCALE_FUNCTIONS -# define _RE_DEFINE_LOCALE_FUNCTIONS 1 -# include -# include -# include -# endif -#endif - -/* This is for other GNU distributions with internationalized messages. */ -#if (HAVE_LIBINTL_H && ENABLE_NLS) || defined _LIBC -# include -# ifdef _LIBC -# undef gettext -# define gettext(msgid) \ - INTUSE(__dcgettext) (_libc_intl_domainname, msgid, LC_MESSAGES) -# endif -#else -# define gettext(msgid) (msgid) -#endif - -#ifndef gettext_noop -/* This define is so xgettext can find the internationalizable - strings. */ -# define gettext_noop(String) String -#endif - -/* For loser systems without the definition. */ -#ifndef SIZE_MAX -# define SIZE_MAX ((size_t) -1) -#endif - -#ifndef NO_MBSUPPORT -#include "mbsupport.h" /* gawk */ -#endif -#ifndef MB_CUR_MAX -#define MB_CUR_MAX 1 -#endif - -#if (defined MBS_SUPPORT) || _LIBC -# define RE_ENABLE_I18N -#endif - -#if __GNUC__ >= 3 -# define BE(expr, val) __builtin_expect (expr, val) -#else -# define BE(expr, val) (expr) -# ifdef inline -# undef inline -# endif -# define inline -#endif - -/* Number of single byte character. */ -#define SBC_MAX 256 - -#define COLL_ELEM_LEN_MAX 8 - -/* The character which represents newline. */ -#define NEWLINE_CHAR '\n' -#define WIDE_NEWLINE_CHAR L'\n' - -/* Rename to standard API for using out of glibc. */ -#ifndef _LIBC -# ifdef __wctype -# undef __wctype -# endif -# define __wctype wctype -# ifdef __iswctype -# undef __iswctype -# endif -# define __iswctype iswctype -# define __btowc btowc -# define __mbrtowc mbrtowc -#undef __mempcpy /* GAWK */ -# define __mempcpy mempcpy -# define __wcrtomb wcrtomb -# define __regfree regfree -# define attribute_hidden -#endif /* not _LIBC */ - -#ifdef __GNUC__ -# define __attribute(arg) __attribute__ (arg) -#else -# define __attribute(arg) -#endif - -extern const char __re_error_msgid[] attribute_hidden; -extern const size_t __re_error_msgid_idx[] attribute_hidden; - -/* An integer used to represent a set of bits. It must be unsigned, - and must be at least as wide as unsigned int. */ -typedef unsigned long int bitset_word_t; -/* All bits set in a bitset_word_t. */ -#define BITSET_WORD_MAX ULONG_MAX -/* Number of bits in a bitset_word_t. Cast to int as most code use it - * like that for counting */ -#define BITSET_WORD_BITS ((int)(sizeof (bitset_word_t) * CHAR_BIT)) -/* Number of bitset_word_t in a bit_set. */ -#define BITSET_WORDS (SBC_MAX / BITSET_WORD_BITS) -typedef bitset_word_t bitset_t[BITSET_WORDS]; -typedef bitset_word_t *re_bitset_ptr_t; -typedef const bitset_word_t *re_const_bitset_ptr_t; - -#define bitset_set(set,i) \ - (set[i / BITSET_WORD_BITS] |= (bitset_word_t) 1 << i % BITSET_WORD_BITS) -#define bitset_clear(set,i) \ - (set[i / BITSET_WORD_BITS] &= ~((bitset_word_t) 1 << i % BITSET_WORD_BITS)) -#define bitset_contain(set,i) \ - (set[i / BITSET_WORD_BITS] & ((bitset_word_t) 1 << i % BITSET_WORD_BITS)) -#define bitset_empty(set) memset (set, '\0', sizeof (bitset_t)) -#define bitset_set_all(set) memset (set, '\xff', sizeof (bitset_t)) -#define bitset_copy(dest,src) memcpy (dest, src, sizeof (bitset_t)) - -#define PREV_WORD_CONSTRAINT 0x0001 -#define PREV_NOTWORD_CONSTRAINT 0x0002 -#define NEXT_WORD_CONSTRAINT 0x0004 -#define NEXT_NOTWORD_CONSTRAINT 0x0008 -#define PREV_NEWLINE_CONSTRAINT 0x0010 -#define NEXT_NEWLINE_CONSTRAINT 0x0020 -#define PREV_BEGBUF_CONSTRAINT 0x0040 -#define NEXT_ENDBUF_CONSTRAINT 0x0080 -#define WORD_DELIM_CONSTRAINT 0x0100 -#define NOT_WORD_DELIM_CONSTRAINT 0x0200 - -typedef enum -{ - INSIDE_WORD = PREV_WORD_CONSTRAINT | NEXT_WORD_CONSTRAINT, - WORD_FIRST = PREV_NOTWORD_CONSTRAINT | NEXT_WORD_CONSTRAINT, - WORD_LAST = PREV_WORD_CONSTRAINT | NEXT_NOTWORD_CONSTRAINT, - INSIDE_NOTWORD = PREV_NOTWORD_CONSTRAINT | NEXT_NOTWORD_CONSTRAINT, - LINE_FIRST = PREV_NEWLINE_CONSTRAINT, - LINE_LAST = NEXT_NEWLINE_CONSTRAINT, - BUF_FIRST = PREV_BEGBUF_CONSTRAINT, - BUF_LAST = NEXT_ENDBUF_CONSTRAINT, - WORD_DELIM = WORD_DELIM_CONSTRAINT, - NOT_WORD_DELIM = NOT_WORD_DELIM_CONSTRAINT -} re_context_type; - -typedef struct -{ - int alloc; - int nelem; - int *elems; -} re_node_set; - -typedef enum -{ - NON_TYPE = 0, - - /* Node type, These are used by token, node, tree. */ - CHARACTER = 1, - END_OF_RE = 2, - SIMPLE_BRACKET = 3, - OP_BACK_REF = 4, - OP_PERIOD = 5, -#ifdef RE_ENABLE_I18N - COMPLEX_BRACKET = 6, - OP_UTF8_PERIOD = 7, -#endif /* RE_ENABLE_I18N */ - - /* We define EPSILON_BIT as a macro so that OP_OPEN_SUBEXP is used - when the debugger shows values of this enum type. */ -#define EPSILON_BIT 8 - OP_OPEN_SUBEXP = EPSILON_BIT | 0, - OP_CLOSE_SUBEXP = EPSILON_BIT | 1, - OP_ALT = EPSILON_BIT | 2, - OP_DUP_ASTERISK = EPSILON_BIT | 3, - ANCHOR = EPSILON_BIT | 4, - - /* Tree type, these are used only by tree. */ - CONCAT = 16, - SUBEXP = 17, - - /* Token type, these are used only by token. */ - OP_DUP_PLUS = 18, - OP_DUP_QUESTION, - OP_OPEN_BRACKET, - OP_CLOSE_BRACKET, - OP_CHARSET_RANGE, - OP_OPEN_DUP_NUM, - OP_CLOSE_DUP_NUM, - OP_NON_MATCH_LIST, - OP_OPEN_COLL_ELEM, - OP_CLOSE_COLL_ELEM, - OP_OPEN_EQUIV_CLASS, - OP_CLOSE_EQUIV_CLASS, - OP_OPEN_CHAR_CLASS, - OP_CLOSE_CHAR_CLASS, - OP_WORD, - OP_NOTWORD, - OP_SPACE, - OP_NOTSPACE, - BACK_SLASH - -} re_token_type_t; - -#ifdef RE_ENABLE_I18N -typedef struct -{ - /* Multibyte characters. */ - wchar_t *mbchars; - - /* Collating symbols. */ -# ifdef _LIBC - int32_t *coll_syms; -# endif - - /* Equivalence classes. */ -# ifdef _LIBC - int32_t *equiv_classes; -# endif - - /* Range expressions. */ -# ifdef _LIBC - uint32_t *range_starts; - uint32_t *range_ends; -# else /* not _LIBC */ - wchar_t *range_starts; - wchar_t *range_ends; -# endif /* not _LIBC */ - - /* Character classes. */ - wctype_t *char_classes; - - /* If this character set is the non-matching list. */ - unsigned int non_match : 1; - - /* # of multibyte characters. */ - int nmbchars; - - /* # of collating symbols. */ - int ncoll_syms; - - /* # of equivalence classes. */ - int nequiv_classes; - - /* # of range expressions. */ - int nranges; - - /* # of character classes. */ - int nchar_classes; -} re_charset_t; -#endif /* RE_ENABLE_I18N */ - -typedef struct -{ - union - { - unsigned char c; /* for CHARACTER */ - re_bitset_ptr_t sbcset; /* for SIMPLE_BRACKET */ -#ifdef RE_ENABLE_I18N - re_charset_t *mbcset; /* for COMPLEX_BRACKET */ -#endif /* RE_ENABLE_I18N */ - int idx; /* for BACK_REF */ - re_context_type ctx_type; /* for ANCHOR */ - } opr; -#if __GNUC__ >= 2 - re_token_type_t type : 8; -#else - re_token_type_t type; -#endif - unsigned int constraint : 10; /* context constraint */ - unsigned int duplicated : 1; - unsigned int opt_subexp : 1; -#ifdef RE_ENABLE_I18N - unsigned int accept_mb : 1; - /* These 2 bits can be moved into the union if needed (e.g. if running out - of bits; move opr.c to opr.c.c and move the flags to opr.c.flags). */ - unsigned int mb_partial : 1; -#endif - unsigned int word_char : 1; -} re_token_t; - -#define IS_EPSILON_NODE(type) ((type) & EPSILON_BIT) - -struct re_string_t -{ - /* Indicate the raw buffer which is the original string passed as an - argument of regexec(), re_search(), etc.. */ - const unsigned char *raw_mbs; - /* Store the multibyte string. In case of "case insensitive mode" like - REG_ICASE, upper cases of the string are stored, otherwise MBS points - the same address that RAW_MBS points. */ - unsigned char *mbs; -#ifdef RE_ENABLE_I18N - /* Store the wide character string which is corresponding to MBS. */ - wint_t *wcs; - int *offsets; - mbstate_t cur_state; -#endif - /* Index in RAW_MBS. Each character mbs[i] corresponds to - raw_mbs[raw_mbs_idx + i]. */ - int raw_mbs_idx; - /* The length of the valid characters in the buffers. */ - int valid_len; - /* The corresponding number of bytes in raw_mbs array. */ - int valid_raw_len; - /* The length of the buffers MBS and WCS. */ - int bufs_len; - /* The index in MBS, which is updated by re_string_fetch_byte. */ - int cur_idx; - /* length of RAW_MBS array. */ - int raw_len; - /* This is RAW_LEN - RAW_MBS_IDX + VALID_LEN - VALID_RAW_LEN. */ - int len; - /* End of the buffer may be shorter than its length in the cases such - as re_match_2, re_search_2. Then, we use STOP for end of the buffer - instead of LEN. */ - int raw_stop; - /* This is RAW_STOP - RAW_MBS_IDX adjusted through OFFSETS. */ - int stop; - - /* The context of mbs[0]. We store the context independently, since - the context of mbs[0] may be different from raw_mbs[0], which is - the beginning of the input string. */ - unsigned int tip_context; - /* The translation passed as a part of an argument of re_compile_pattern. */ - RE_TRANSLATE_TYPE trans; - /* Copy of re_dfa_t's word_char. */ - re_const_bitset_ptr_t word_char; - /* 1 if REG_ICASE. */ - unsigned char icase; - unsigned char is_utf8; - unsigned char map_notascii; - unsigned char mbs_allocated; - unsigned char offsets_needed; - unsigned char newline_anchor; - unsigned char word_ops_used; - int mb_cur_max; -}; -typedef struct re_string_t re_string_t; - - -struct re_dfa_t; -typedef struct re_dfa_t re_dfa_t; - -#ifndef _LIBC -# ifdef __i386__ -# define internal_function __attribute ((regparm (3), stdcall)) -# else -# define internal_function -# endif -#endif - -#ifndef NOT_IN_libc -static reg_errcode_t re_string_realloc_buffers (re_string_t *pstr, - int new_buf_len) - internal_function; -# ifdef RE_ENABLE_I18N -static void build_wcs_buffer (re_string_t *pstr) internal_function; -static reg_errcode_t build_wcs_upper_buffer (re_string_t *pstr) - internal_function; -# endif /* RE_ENABLE_I18N */ -static void build_upper_buffer (re_string_t *pstr) internal_function; -static void re_string_translate_buffer (re_string_t *pstr) internal_function; -static unsigned int re_string_context_at (const re_string_t *input, int idx, - int eflags) - internal_function __attribute ((pure)); -#endif -#define re_string_peek_byte(pstr, offset) \ - ((pstr)->mbs[(pstr)->cur_idx + offset]) -#define re_string_fetch_byte(pstr) \ - ((pstr)->mbs[(pstr)->cur_idx++]) -#define re_string_first_byte(pstr, idx) \ - ((idx) == (pstr)->valid_len || (pstr)->wcs[idx] != WEOF) -#define re_string_is_single_byte_char(pstr, idx) \ - ((pstr)->wcs[idx] != WEOF && ((pstr)->valid_len == (idx) + 1 \ - || (pstr)->wcs[(idx) + 1] != WEOF)) -#define re_string_eoi(pstr) ((pstr)->stop <= (pstr)->cur_idx) -#define re_string_cur_idx(pstr) ((pstr)->cur_idx) -#define re_string_get_buffer(pstr) ((pstr)->mbs) -#define re_string_length(pstr) ((pstr)->len) -#define re_string_byte_at(pstr,idx) ((pstr)->mbs[idx]) -#define re_string_skip_bytes(pstr,idx) ((pstr)->cur_idx += (idx)) -#define re_string_set_index(pstr,idx) ((pstr)->cur_idx = (idx)) - -#ifndef _LIBC -# if HAVE_ALLOCA -# if (_MSC_VER) -# include -# define __libc_use_alloca(n) 0 -# else -# include -/* The OS usually guarantees only one guard page at the bottom of the stack, - and a page size can be as small as 4096 bytes. So we cannot safely - allocate anything larger than 4096 bytes. Also care for the possibility - of a few compiler-allocated temporary stack slots. */ -# define __libc_use_alloca(n) ((n) < 4032) -# endif -# else -/* alloca is implemented with malloc, so just use malloc. */ -# define __libc_use_alloca(n) 0 -# endif -#endif - -#define re_malloc(t,n) ((t *) malloc ((n) * sizeof (t))) -/* SunOS 4.1.x realloc doesn't accept null pointers: pre-Standard C. Sigh. */ -#define re_realloc(p,t,n) ((p != NULL) ? (t *) realloc (p,(n)*sizeof(t)) : (t *) calloc(n,sizeof(t))) -#define re_free(p) free (p) - -struct bin_tree_t -{ - struct bin_tree_t *parent; - struct bin_tree_t *left; - struct bin_tree_t *right; - struct bin_tree_t *first; - struct bin_tree_t *next; - - re_token_t token; - - /* `node_idx' is the index in dfa->nodes, if `type' == 0. - Otherwise `type' indicate the type of this node. */ - int node_idx; -}; -typedef struct bin_tree_t bin_tree_t; - -#define BIN_TREE_STORAGE_SIZE \ - ((1024 - sizeof (void *)) / sizeof (bin_tree_t)) - -struct bin_tree_storage_t -{ - struct bin_tree_storage_t *next; - bin_tree_t data[BIN_TREE_STORAGE_SIZE]; -}; -typedef struct bin_tree_storage_t bin_tree_storage_t; - -#define CONTEXT_WORD 1 -#define CONTEXT_NEWLINE (CONTEXT_WORD << 1) -#define CONTEXT_BEGBUF (CONTEXT_NEWLINE << 1) -#define CONTEXT_ENDBUF (CONTEXT_BEGBUF << 1) - -#define IS_WORD_CONTEXT(c) ((c) & CONTEXT_WORD) -#define IS_NEWLINE_CONTEXT(c) ((c) & CONTEXT_NEWLINE) -#define IS_BEGBUF_CONTEXT(c) ((c) & CONTEXT_BEGBUF) -#define IS_ENDBUF_CONTEXT(c) ((c) & CONTEXT_ENDBUF) -#define IS_ORDINARY_CONTEXT(c) ((c) == 0) - -#define IS_WORD_CHAR(ch) (isalnum (ch) || (ch) == '_') -#define IS_NEWLINE(ch) ((ch) == NEWLINE_CHAR) -#define IS_WIDE_WORD_CHAR(ch) (iswalnum (ch) || (ch) == L'_') -#define IS_WIDE_NEWLINE(ch) ((ch) == WIDE_NEWLINE_CHAR) - -#define NOT_SATISFY_PREV_CONSTRAINT(constraint,context) \ - ((((constraint) & PREV_WORD_CONSTRAINT) && !IS_WORD_CONTEXT (context)) \ - || ((constraint & PREV_NOTWORD_CONSTRAINT) && IS_WORD_CONTEXT (context)) \ - || ((constraint & PREV_NEWLINE_CONSTRAINT) && !IS_NEWLINE_CONTEXT (context))\ - || ((constraint & PREV_BEGBUF_CONSTRAINT) && !IS_BEGBUF_CONTEXT (context))) - -#define NOT_SATISFY_NEXT_CONSTRAINT(constraint,context) \ - ((((constraint) & NEXT_WORD_CONSTRAINT) && !IS_WORD_CONTEXT (context)) \ - || (((constraint) & NEXT_NOTWORD_CONSTRAINT) && IS_WORD_CONTEXT (context)) \ - || (((constraint) & NEXT_NEWLINE_CONSTRAINT) && !IS_NEWLINE_CONTEXT (context)) \ - || (((constraint) & NEXT_ENDBUF_CONSTRAINT) && !IS_ENDBUF_CONTEXT (context))) - -struct re_dfastate_t -{ - unsigned int hash; - re_node_set nodes; - re_node_set non_eps_nodes; - re_node_set inveclosure; - re_node_set *entrance_nodes; - struct re_dfastate_t **trtable, **word_trtable; - unsigned int context : 4; - unsigned int halt : 1; - /* If this state can accept `multi byte'. - Note that we refer to multibyte characters, and multi character - collating elements as `multi byte'. */ - unsigned int accept_mb : 1; - /* If this state has backreference node(s). */ - unsigned int has_backref : 1; - unsigned int has_constraint : 1; -}; -typedef struct re_dfastate_t re_dfastate_t; - -struct re_state_table_entry -{ - int num; - int alloc; - re_dfastate_t **array; -}; - -/* Array type used in re_sub_match_last_t and re_sub_match_top_t. */ - -typedef struct -{ - int next_idx; - int alloc; - re_dfastate_t **array; -} state_array_t; - -/* Store information about the node NODE whose type is OP_CLOSE_SUBEXP. */ - -typedef struct -{ - int node; - int str_idx; /* The position NODE match at. */ - state_array_t path; -} re_sub_match_last_t; - -/* Store information about the node NODE whose type is OP_OPEN_SUBEXP. - And information about the node, whose type is OP_CLOSE_SUBEXP, - corresponding to NODE is stored in LASTS. */ - -typedef struct -{ - int str_idx; - int node; - state_array_t *path; - int alasts; /* Allocation size of LASTS. */ - int nlasts; /* The number of LASTS. */ - re_sub_match_last_t **lasts; -} re_sub_match_top_t; - -struct re_backref_cache_entry -{ - int node; - int str_idx; - int subexp_from; - int subexp_to; - char more; - char unused; - unsigned short int eps_reachable_subexps_map; -}; - -typedef struct -{ - /* The string object corresponding to the input string. */ - re_string_t input; -#if defined _LIBC || (defined __STDC_VERSION__ && __STDC_VERSION__ >= 199901L) - const re_dfa_t *const dfa; -#else - const re_dfa_t *dfa; -#endif - /* EFLAGS of the argument of regexec. */ - int eflags; - /* Where the matching ends. */ - int match_last; - int last_node; - /* The state log used by the matcher. */ - re_dfastate_t **state_log; - int state_log_top; - /* Back reference cache. */ - int nbkref_ents; - int abkref_ents; - struct re_backref_cache_entry *bkref_ents; - int max_mb_elem_len; - int nsub_tops; - int asub_tops; - re_sub_match_top_t **sub_tops; -} re_match_context_t; - -typedef struct -{ - re_dfastate_t **sifted_states; - re_dfastate_t **limited_states; - int last_node; - int last_str_idx; - re_node_set limits; -} re_sift_context_t; - -struct re_fail_stack_ent_t -{ - int idx; - int node; - regmatch_t *regs; - re_node_set eps_via_nodes; -}; - -struct re_fail_stack_t -{ - int num; - int alloc; - struct re_fail_stack_ent_t *stack; -}; - -struct re_dfa_t -{ - re_token_t *nodes; - size_t nodes_alloc; - size_t nodes_len; - int *nexts; - int *org_indices; - re_node_set *edests; - re_node_set *eclosures; - re_node_set *inveclosures; - struct re_state_table_entry *state_table; - re_dfastate_t *init_state; - re_dfastate_t *init_state_word; - re_dfastate_t *init_state_nl; - re_dfastate_t *init_state_begbuf; - bin_tree_t *str_tree; - bin_tree_storage_t *str_tree_storage; - re_bitset_ptr_t sb_char; - int str_tree_storage_idx; - - /* number of subexpressions `re_nsub' is in regex_t. */ - unsigned int state_hash_mask; - int init_node; - int nbackref; /* The number of backreference in this dfa. */ - - /* Bitmap expressing which backreference is used. */ - bitset_word_t used_bkref_map; - bitset_word_t completed_bkref_map; - - unsigned int has_plural_match : 1; - /* If this dfa has "multibyte node", which is a backreference or - a node which can accept multibyte character or multi character - collating element. */ - unsigned int has_mb_node : 1; - unsigned int is_utf8 : 1; - unsigned int map_notascii : 1; - unsigned int word_ops_used : 1; - int mb_cur_max; - bitset_t word_char; - reg_syntax_t syntax; - int *subexp_map; -#ifdef DEBUG - char* re_str; -#endif -#if defined _LIBC - __libc_lock_define (, lock) -#endif -}; - -#define re_node_set_init_empty(set) memset (set, '\0', sizeof (re_node_set)) -#define re_node_set_remove(set,id) \ - (re_node_set_remove_at (set, re_node_set_contains (set, id) - 1)) -#define re_node_set_empty(p) ((p)->nelem = 0) -#define re_node_set_free(set) re_free ((set)->elems) - - -typedef enum -{ - SB_CHAR, - MB_CHAR, - EQUIV_CLASS, - COLL_SYM, - CHAR_CLASS -} bracket_elem_type; - -typedef struct -{ - bracket_elem_type type; - union - { - unsigned char ch; - unsigned char *name; - wchar_t wch; - } opr; -} bracket_elem_t; - - -/* Inline functions for bitset operation. */ -static inline void -bitset_not (bitset_t set) -{ - int bitset_i; - for (bitset_i = 0; bitset_i < BITSET_WORDS; ++bitset_i) - set[bitset_i] = ~set[bitset_i]; -} - -static inline void -bitset_merge (bitset_t dest, const bitset_t src) -{ - int bitset_i; - for (bitset_i = 0; bitset_i < BITSET_WORDS; ++bitset_i) - dest[bitset_i] |= src[bitset_i]; -} - -static inline void -bitset_mask (bitset_t dest, const bitset_t src) -{ - int bitset_i; - for (bitset_i = 0; bitset_i < BITSET_WORDS; ++bitset_i) - dest[bitset_i] &= src[bitset_i]; -} - -#ifdef RE_ENABLE_I18N -/* Inline functions for re_string. */ -static inline int -internal_function __attribute ((pure)) -re_string_char_size_at (const re_string_t *pstr, int idx) -{ - int byte_idx; - if (pstr->mb_cur_max == 1) - return 1; - for (byte_idx = 1; idx + byte_idx < pstr->valid_len; ++byte_idx) - if (pstr->wcs[idx + byte_idx] != WEOF) - break; - return byte_idx; -} - -static inline wint_t -internal_function __attribute ((pure)) -re_string_wchar_at (const re_string_t *pstr, int idx) -{ - if (pstr->mb_cur_max == 1) - return (wint_t) pstr->mbs[idx]; - return (wint_t) pstr->wcs[idx]; -} - -# ifndef NOT_IN_libc -static int -internal_function __attribute ((pure)) -re_string_elem_size_at (const re_string_t *pstr, int idx) -{ -# ifdef _LIBC - const unsigned char *p, *extra; - const int32_t *table, *indirect; - int32_t tmp; -# include - uint_fast32_t nrules = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES); - - if (nrules != 0) - { - table = (const int32_t *) _NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEMB); - extra = (const unsigned char *) - _NL_CURRENT (LC_COLLATE, _NL_COLLATE_EXTRAMB); - indirect = (const int32_t *) _NL_CURRENT (LC_COLLATE, - _NL_COLLATE_INDIRECTMB); - p = pstr->mbs + idx; - tmp = findidx (&p); - return p - pstr->mbs - idx; - } - else -# endif /* _LIBC */ - return 1; -} -# endif -#endif /* RE_ENABLE_I18N */ - -#endif /* _REGEX_INTERNAL_H */ diff --git a/deps/regex/regexec.c b/deps/regex/regexec.c deleted file mode 100644 index 0a1602e..0000000 --- a/deps/regex/regexec.c +++ /dev/null @@ -1,4369 +0,0 @@ -/* Extended regular expression matching and search library. - Copyright (C) 2002-2005, 2007, 2009, 2010 Free Software Foundation, Inc. - This file is part of the GNU C Library. - Contributed by Isamu Hasegawa . - - The GNU C Library is free software; you can redistribute it and/or - modify it under the terms of the GNU Lesser General Public - License as published by the Free Software Foundation; either - version 2.1 of the License, or (at your option) any later version. - - The GNU C Library is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - Lesser General Public License for more details. - - You should have received a copy of the GNU Lesser General Public - License along with the GNU C Library; if not, write to the Free - Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA - 02110-1301 USA. */ - -static reg_errcode_t match_ctx_init (re_match_context_t *cache, int eflags, - int n) internal_function; -static void match_ctx_clean (re_match_context_t *mctx) internal_function; -static void match_ctx_free (re_match_context_t *cache) internal_function; -static reg_errcode_t match_ctx_add_entry (re_match_context_t *cache, int node, - int str_idx, int from, int to) - internal_function; -static int search_cur_bkref_entry (const re_match_context_t *mctx, int str_idx) - internal_function; -static reg_errcode_t match_ctx_add_subtop (re_match_context_t *mctx, int node, - int str_idx) internal_function; -static re_sub_match_last_t * match_ctx_add_sublast (re_sub_match_top_t *subtop, - int node, int str_idx) - internal_function; -static void sift_ctx_init (re_sift_context_t *sctx, re_dfastate_t **sifted_sts, - re_dfastate_t **limited_sts, int last_node, - int last_str_idx) - internal_function; -static reg_errcode_t re_search_internal (const regex_t *preg, - const char *string, int length, - int start, int range, int stop, - size_t nmatch, regmatch_t pmatch[], - int eflags); -static int re_search_2_stub (struct re_pattern_buffer *bufp, - const char *string1, int length1, - const char *string2, int length2, - int start, int range, struct re_registers *regs, - int stop, int ret_len); -static int re_search_stub (struct re_pattern_buffer *bufp, - const char *string, int length, int start, - int range, int stop, struct re_registers *regs, - int ret_len); -static unsigned re_copy_regs (struct re_registers *regs, regmatch_t *pmatch, - unsigned int nregs, int regs_allocated); -static reg_errcode_t prune_impossible_nodes (re_match_context_t *mctx); -static int check_matching (re_match_context_t *mctx, int fl_longest_match, - int *p_match_first) internal_function; -static int check_halt_state_context (const re_match_context_t *mctx, - const re_dfastate_t *state, int idx) - internal_function; -static void update_regs (const re_dfa_t *dfa, regmatch_t *pmatch, - regmatch_t *prev_idx_match, int cur_node, - int cur_idx, int nmatch) internal_function; -static reg_errcode_t push_fail_stack (struct re_fail_stack_t *fs, - int str_idx, int dest_node, int nregs, - regmatch_t *regs, - re_node_set *eps_via_nodes) - internal_function; -static reg_errcode_t set_regs (const regex_t *preg, - const re_match_context_t *mctx, - size_t nmatch, regmatch_t *pmatch, - int fl_backtrack) internal_function; -static reg_errcode_t free_fail_stack_return (struct re_fail_stack_t *fs) - internal_function; - -#ifdef RE_ENABLE_I18N -static int sift_states_iter_mb (const re_match_context_t *mctx, - re_sift_context_t *sctx, - int node_idx, int str_idx, int max_str_idx) - internal_function; -#endif /* RE_ENABLE_I18N */ -static reg_errcode_t sift_states_backward (const re_match_context_t *mctx, - re_sift_context_t *sctx) - internal_function; -static reg_errcode_t build_sifted_states (const re_match_context_t *mctx, - re_sift_context_t *sctx, int str_idx, - re_node_set *cur_dest) - internal_function; -static reg_errcode_t update_cur_sifted_state (const re_match_context_t *mctx, - re_sift_context_t *sctx, - int str_idx, - re_node_set *dest_nodes) - internal_function; -static reg_errcode_t add_epsilon_src_nodes (const re_dfa_t *dfa, - re_node_set *dest_nodes, - const re_node_set *candidates) - internal_function; -static int check_dst_limits (const re_match_context_t *mctx, - re_node_set *limits, - int dst_node, int dst_idx, int src_node, - int src_idx) internal_function; -static int check_dst_limits_calc_pos_1 (const re_match_context_t *mctx, - int boundaries, int subexp_idx, - int from_node, int bkref_idx) - internal_function; -static int check_dst_limits_calc_pos (const re_match_context_t *mctx, - int limit, int subexp_idx, - int node, int str_idx, - int bkref_idx) internal_function; -static reg_errcode_t check_subexp_limits (const re_dfa_t *dfa, - re_node_set *dest_nodes, - const re_node_set *candidates, - re_node_set *limits, - struct re_backref_cache_entry *bkref_ents, - int str_idx) internal_function; -static reg_errcode_t sift_states_bkref (const re_match_context_t *mctx, - re_sift_context_t *sctx, - int str_idx, const re_node_set *candidates) - internal_function; -static reg_errcode_t merge_state_array (const re_dfa_t *dfa, - re_dfastate_t **dst, - re_dfastate_t **src, int num) - internal_function; -static re_dfastate_t *find_recover_state (reg_errcode_t *err, - re_match_context_t *mctx) internal_function; -static re_dfastate_t *transit_state (reg_errcode_t *err, - re_match_context_t *mctx, - re_dfastate_t *state) internal_function; -static re_dfastate_t *merge_state_with_log (reg_errcode_t *err, - re_match_context_t *mctx, - re_dfastate_t *next_state) - internal_function; -static reg_errcode_t check_subexp_matching_top (re_match_context_t *mctx, - re_node_set *cur_nodes, - int str_idx) internal_function; -#if 0 -static re_dfastate_t *transit_state_sb (reg_errcode_t *err, - re_match_context_t *mctx, - re_dfastate_t *pstate) - internal_function; -#endif -#ifdef RE_ENABLE_I18N -static reg_errcode_t transit_state_mb (re_match_context_t *mctx, - re_dfastate_t *pstate) - internal_function; -#endif /* RE_ENABLE_I18N */ -static reg_errcode_t transit_state_bkref (re_match_context_t *mctx, - const re_node_set *nodes) - internal_function; -static reg_errcode_t get_subexp (re_match_context_t *mctx, - int bkref_node, int bkref_str_idx) - internal_function; -static reg_errcode_t get_subexp_sub (re_match_context_t *mctx, - const re_sub_match_top_t *sub_top, - re_sub_match_last_t *sub_last, - int bkref_node, int bkref_str) - internal_function; -static int find_subexp_node (const re_dfa_t *dfa, const re_node_set *nodes, - int subexp_idx, int type) internal_function; -static reg_errcode_t check_arrival (re_match_context_t *mctx, - state_array_t *path, int top_node, - int top_str, int last_node, int last_str, - int type) internal_function; -static reg_errcode_t check_arrival_add_next_nodes (re_match_context_t *mctx, - int str_idx, - re_node_set *cur_nodes, - re_node_set *next_nodes) - internal_function; -static reg_errcode_t check_arrival_expand_ecl (const re_dfa_t *dfa, - re_node_set *cur_nodes, - int ex_subexp, int type) - internal_function; -static reg_errcode_t check_arrival_expand_ecl_sub (const re_dfa_t *dfa, - re_node_set *dst_nodes, - int target, int ex_subexp, - int type) internal_function; -static reg_errcode_t expand_bkref_cache (re_match_context_t *mctx, - re_node_set *cur_nodes, int cur_str, - int subexp_num, int type) - internal_function; -static int build_trtable (const re_dfa_t *dfa, - re_dfastate_t *state) internal_function; -#ifdef RE_ENABLE_I18N -static int check_node_accept_bytes (const re_dfa_t *dfa, int node_idx, - const re_string_t *input, int idx) - internal_function; -# ifdef _LIBC -static unsigned int find_collation_sequence_value (const unsigned char *mbs, - size_t name_len) - internal_function; -# endif /* _LIBC */ -#endif /* RE_ENABLE_I18N */ -static int group_nodes_into_DFAstates (const re_dfa_t *dfa, - const re_dfastate_t *state, - re_node_set *states_node, - bitset_t *states_ch) internal_function; -static int check_node_accept (const re_match_context_t *mctx, - const re_token_t *node, int idx) - internal_function; -static reg_errcode_t extend_buffers (re_match_context_t *mctx) - internal_function; - -/* Entry point for POSIX code. */ - -/* regexec searches for a given pattern, specified by PREG, in the - string STRING. - - If NMATCH is zero or REG_NOSUB was set in the cflags argument to - `regcomp', we ignore PMATCH. Otherwise, we assume PMATCH has at - least NMATCH elements, and we set them to the offsets of the - corresponding matched substrings. - - EFLAGS specifies `execution flags' which affect matching: if - REG_NOTBOL is set, then ^ does not match at the beginning of the - string; if REG_NOTEOL is set, then $ does not match at the end. - - We return 0 if we find a match and REG_NOMATCH if not. */ - -int -regexec ( - const regex_t *__restrict preg, - const char *__restrict string, - size_t nmatch, - regmatch_t pmatch[], - int eflags) -{ - reg_errcode_t err; - int start, length; - - if (eflags & ~(REG_NOTBOL | REG_NOTEOL | REG_STARTEND)) - return REG_BADPAT; - - if (eflags & REG_STARTEND) - { - start = pmatch[0].rm_so; - length = pmatch[0].rm_eo; - } - else - { - start = 0; - length = strlen (string); - } - - __libc_lock_lock (dfa->lock); - if (preg->no_sub) - err = re_search_internal (preg, string, length, start, length - start, - length, 0, NULL, eflags); - else - err = re_search_internal (preg, string, length, start, length - start, - length, nmatch, pmatch, eflags); - __libc_lock_unlock (dfa->lock); - return err != REG_NOERROR; -} - -#ifdef _LIBC -# include -versioned_symbol (libc, __regexec, regexec, GLIBC_2_3_4); - -# if SHLIB_COMPAT (libc, GLIBC_2_0, GLIBC_2_3_4) -__typeof__ (__regexec) __compat_regexec; - -int -attribute_compat_text_section -__compat_regexec (const regex_t *__restrict preg, - const char *__restrict string, size_t nmatch, - regmatch_t pmatch[], int eflags) -{ - return regexec (preg, string, nmatch, pmatch, - eflags & (REG_NOTBOL | REG_NOTEOL)); -} -compat_symbol (libc, __compat_regexec, regexec, GLIBC_2_0); -# endif -#endif - -/* Entry points for GNU code. */ - -/* re_match, re_search, re_match_2, re_search_2 - - The former two functions operate on STRING with length LENGTH, - while the later two operate on concatenation of STRING1 and STRING2 - with lengths LENGTH1 and LENGTH2, respectively. - - re_match() matches the compiled pattern in BUFP against the string, - starting at index START. - - re_search() first tries matching at index START, then it tries to match - starting from index START + 1, and so on. The last start position tried - is START + RANGE. (Thus RANGE = 0 forces re_search to operate the same - way as re_match().) - - The parameter STOP of re_{match,search}_2 specifies that no match exceeding - the first STOP characters of the concatenation of the strings should be - concerned. - - If REGS is not NULL, and BUFP->no_sub is not set, the offsets of the match - and all groups is stroed in REGS. (For the "_2" variants, the offsets are - computed relative to the concatenation, not relative to the individual - strings.) - - On success, re_match* functions return the length of the match, re_search* - return the position of the start of the match. Return value -1 means no - match was found and -2 indicates an internal error. */ - -int -re_match (struct re_pattern_buffer *bufp, - const char *string, - int length, - int start, - struct re_registers *regs) -{ - return re_search_stub (bufp, string, length, start, 0, length, regs, 1); -} -#ifdef _LIBC -weak_alias (__re_match, re_match) -#endif - -int -re_search (struct re_pattern_buffer *bufp, - const char *string, - int length, int start, int range, - struct re_registers *regs) -{ - return re_search_stub (bufp, string, length, start, range, length, regs, 0); -} -#ifdef _LIBC -weak_alias (__re_search, re_search) -#endif - -int -re_match_2 (struct re_pattern_buffer *bufp, - const char *string1, int length1, - const char *string2, int length2, int start, - struct re_registers *regs, int stop) -{ - return re_search_2_stub (bufp, string1, length1, string2, length2, - start, 0, regs, stop, 1); -} -#ifdef _LIBC -weak_alias (__re_match_2, re_match_2) -#endif - -int -re_search_2 (struct re_pattern_buffer *bufp, - const char *string1, int length1, - const char *string2, int length2, int start, - int range, struct re_registers *regs, int stop) -{ - return re_search_2_stub (bufp, string1, length1, string2, length2, - start, range, regs, stop, 0); -} -#ifdef _LIBC -weak_alias (__re_search_2, re_search_2) -#endif - -static int -re_search_2_stub (struct re_pattern_buffer *bufp, - const char *string1, int length1, - const char *string2, int length2, int start, - int range, struct re_registers *regs, - int stop, int ret_len) -{ - const char *str; - int rval; - int len = length1 + length2; - int free_str = 0; - - if (BE (length1 < 0 || length2 < 0 || stop < 0, 0)) - return -2; - - /* Concatenate the strings. */ - if (length2 > 0) - if (length1 > 0) - { - char *s = re_malloc (char, len); - - if (BE (s == NULL, 0)) - return -2; - memcpy (s, string1, length1); - memcpy (s + length1, string2, length2); - str = s; - free_str = 1; - } - else - str = string2; - else - str = string1; - - rval = re_search_stub (bufp, str, len, start, range, stop, regs, ret_len); - if (free_str) - re_free ((char *) str); - return rval; -} - -/* The parameters have the same meaning as those of re_search. - Additional parameters: - If RET_LEN is nonzero the length of the match is returned (re_match style); - otherwise the position of the match is returned. */ - -static int -re_search_stub (struct re_pattern_buffer *bufp, - const char *string, int length, int start, - int range, int stop, - struct re_registers *regs, int ret_len) -{ - reg_errcode_t result; - regmatch_t *pmatch; - int nregs, rval; - int eflags = 0; - - /* Check for out-of-range. */ - if (BE (start < 0 || start > length, 0)) - return -1; - if (BE (start + range > length, 0)) - range = length - start; - else if (BE (start + range < 0, 0)) - range = -start; - - __libc_lock_lock (dfa->lock); - - eflags |= (bufp->not_bol) ? REG_NOTBOL : 0; - eflags |= (bufp->not_eol) ? REG_NOTEOL : 0; - - /* Compile fastmap if we haven't yet. */ - if (range > 0 && bufp->fastmap != NULL && !bufp->fastmap_accurate) - re_compile_fastmap (bufp); - - if (BE (bufp->no_sub, 0)) - regs = NULL; - - /* We need at least 1 register. */ - if (regs == NULL) - nregs = 1; - else if (BE (bufp->regs_allocated == REGS_FIXED && - regs->num_regs < bufp->re_nsub + 1, 0)) - { - nregs = regs->num_regs; - if (BE (nregs < 1, 0)) - { - /* Nothing can be copied to regs. */ - regs = NULL; - nregs = 1; - } - } - else - nregs = bufp->re_nsub + 1; - pmatch = re_malloc (regmatch_t, nregs); - if (BE (pmatch == NULL, 0)) - { - rval = -2; - goto out; - } - - result = re_search_internal (bufp, string, length, start, range, stop, - nregs, pmatch, eflags); - - rval = 0; - - /* I hope we needn't fill ther regs with -1's when no match was found. */ - if (result != REG_NOERROR) - rval = -1; - else if (regs != NULL) - { - /* If caller wants register contents data back, copy them. */ - bufp->regs_allocated = re_copy_regs (regs, pmatch, nregs, - bufp->regs_allocated); - if (BE (bufp->regs_allocated == REGS_UNALLOCATED, 0)) - rval = -2; - } - - if (BE (rval == 0, 1)) - { - if (ret_len) - { - assert (pmatch[0].rm_so == start); - rval = pmatch[0].rm_eo - start; - } - else - rval = pmatch[0].rm_so; - } - re_free (pmatch); - out: - __libc_lock_unlock (dfa->lock); - return rval; -} - -static unsigned -re_copy_regs (struct re_registers *regs, - regmatch_t *pmatch, - unsigned int nregs, int regs_allocated) -{ - int rval = REGS_REALLOCATE; - unsigned int i; - unsigned int need_regs = nregs + 1; - /* We need one extra element beyond `num_regs' for the `-1' marker GNU code - uses. */ - - /* Have the register data arrays been allocated? */ - if (regs_allocated == REGS_UNALLOCATED) - { /* No. So allocate them with malloc. */ - regs->start = re_malloc (regoff_t, need_regs); - if (BE (regs->start == NULL, 0)) - return REGS_UNALLOCATED; - regs->end = re_malloc (regoff_t, need_regs); - if (BE (regs->end == NULL, 0)) - { - re_free (regs->start); - return REGS_UNALLOCATED; - } - regs->num_regs = need_regs; - } - else if (regs_allocated == REGS_REALLOCATE) - { /* Yes. If we need more elements than were already - allocated, reallocate them. If we need fewer, just - leave it alone. */ - if (BE (need_regs > regs->num_regs, 0)) - { - regoff_t *new_start = re_realloc (regs->start, regoff_t, need_regs); - regoff_t *new_end; - if (BE (new_start == NULL, 0)) - return REGS_UNALLOCATED; - new_end = re_realloc (regs->end, regoff_t, need_regs); - if (BE (new_end == NULL, 0)) - { - re_free (new_start); - return REGS_UNALLOCATED; - } - regs->start = new_start; - regs->end = new_end; - regs->num_regs = need_regs; - } - } - else - { - assert (regs_allocated == REGS_FIXED); - /* This function may not be called with REGS_FIXED and nregs too big. */ - assert (regs->num_regs >= nregs); - rval = REGS_FIXED; - } - - /* Copy the regs. */ - for (i = 0; i < nregs; ++i) - { - regs->start[i] = pmatch[i].rm_so; - regs->end[i] = pmatch[i].rm_eo; - } - for ( ; i < regs->num_regs; ++i) - regs->start[i] = regs->end[i] = -1; - - return rval; -} - -/* Set REGS to hold NUM_REGS registers, storing them in STARTS and - ENDS. Subsequent matches using PATTERN_BUFFER and REGS will use - this memory for recording register information. STARTS and ENDS - must be allocated using the malloc library routine, and must each - be at least NUM_REGS * sizeof (regoff_t) bytes long. - - If NUM_REGS == 0, then subsequent matches should allocate their own - register data. - - Unless this function is called, the first search or match using - PATTERN_BUFFER will allocate its own register data, without - freeing the old data. */ - -void -re_set_registers (struct re_pattern_buffer *bufp, - struct re_registers *regs, - unsigned num_regs, - regoff_t *starts, - regoff_t *ends) -{ - if (num_regs) - { - bufp->regs_allocated = REGS_REALLOCATE; - regs->num_regs = num_regs; - regs->start = starts; - regs->end = ends; - } - else - { - bufp->regs_allocated = REGS_UNALLOCATED; - regs->num_regs = 0; - regs->start = regs->end = (regoff_t *) 0; - } -} -#ifdef _LIBC -weak_alias (__re_set_registers, re_set_registers) -#endif - -/* Entry points compatible with 4.2 BSD regex library. We don't define - them unless specifically requested. */ - -#if defined _REGEX_RE_COMP || defined _LIBC -int -# ifdef _LIBC -weak_function -# endif -re_exec (s) - const char *s; -{ - return 0 == regexec (&re_comp_buf, s, 0, NULL, 0); -} -#endif /* _REGEX_RE_COMP */ - -/* Internal entry point. */ - -/* Searches for a compiled pattern PREG in the string STRING, whose - length is LENGTH. NMATCH, PMATCH, and EFLAGS have the same - mingings with regexec. START, and RANGE have the same meanings - with re_search. - Return REG_NOERROR if we find a match, and REG_NOMATCH if not, - otherwise return the error code. - Note: We assume front end functions already check ranges. - (START + RANGE >= 0 && START + RANGE <= LENGTH) */ - -static reg_errcode_t -re_search_internal (const regex_t *preg, - const char *string, - int length, int start, int range, int stop, - size_t nmatch, regmatch_t pmatch[], - int eflags) -{ - reg_errcode_t err; - const re_dfa_t *dfa = (const re_dfa_t *) preg->buffer; - int left_lim, right_lim, incr; - int fl_longest_match, match_first, match_kind, match_last = -1; - unsigned int extra_nmatch; - int sb, ch; -#if defined _LIBC || (defined __STDC_VERSION__ && __STDC_VERSION__ >= 199901L) - re_match_context_t mctx = { .dfa = dfa }; -#else - re_match_context_t mctx; -#endif - char *fastmap = (preg->fastmap != NULL && preg->fastmap_accurate - && range && !preg->can_be_null) ? preg->fastmap : NULL; - RE_TRANSLATE_TYPE t = preg->translate; - -#if !(defined _LIBC || (defined __STDC_VERSION__ && __STDC_VERSION__ >= 199901L)) - memset (&mctx, '\0', sizeof (re_match_context_t)); - mctx.dfa = dfa; -#endif - - extra_nmatch = (nmatch > preg->re_nsub) ? nmatch - (preg->re_nsub + 1) : 0; - nmatch -= extra_nmatch; - - /* Check if the DFA haven't been compiled. */ - if (BE (preg->used == 0 || dfa->init_state == NULL - || dfa->init_state_word == NULL || dfa->init_state_nl == NULL - || dfa->init_state_begbuf == NULL, 0)) - return REG_NOMATCH; - -#ifdef DEBUG - /* We assume front-end functions already check them. */ - assert (start + range >= 0 && start + range <= length); -#endif - - /* If initial states with non-begbuf contexts have no elements, - the regex must be anchored. If preg->newline_anchor is set, - we'll never use init_state_nl, so do not check it. */ - if (dfa->init_state->nodes.nelem == 0 - && dfa->init_state_word->nodes.nelem == 0 - && (dfa->init_state_nl->nodes.nelem == 0 - || !preg->newline_anchor)) - { - if (start != 0 && start + range != 0) - return REG_NOMATCH; - start = range = 0; - } - - /* We must check the longest matching, if nmatch > 0. */ - fl_longest_match = (nmatch != 0 || dfa->nbackref); - - err = re_string_allocate (&mctx.input, string, length, dfa->nodes_len + 1, - preg->translate, preg->syntax & RE_ICASE, dfa); - if (BE (err != REG_NOERROR, 0)) - goto free_return; - mctx.input.stop = stop; - mctx.input.raw_stop = stop; - mctx.input.newline_anchor = preg->newline_anchor; - - err = match_ctx_init (&mctx, eflags, dfa->nbackref * 2); - if (BE (err != REG_NOERROR, 0)) - goto free_return; - - /* We will log all the DFA states through which the dfa pass, - if nmatch > 1, or this dfa has "multibyte node", which is a - back-reference or a node which can accept multibyte character or - multi character collating element. */ - if (nmatch > 1 || dfa->has_mb_node) - { - /* Avoid overflow. */ - if (BE (SIZE_MAX / sizeof (re_dfastate_t *) <= (size_t)mctx.input.bufs_len, 0)) - { - err = REG_ESPACE; - goto free_return; - } - - mctx.state_log = re_malloc (re_dfastate_t *, mctx.input.bufs_len + 1); - if (BE (mctx.state_log == NULL, 0)) - { - err = REG_ESPACE; - goto free_return; - } - } - else - mctx.state_log = NULL; - - match_first = start; - mctx.input.tip_context = (eflags & REG_NOTBOL) ? CONTEXT_BEGBUF - : CONTEXT_NEWLINE | CONTEXT_BEGBUF; - - /* Check incrementally whether of not the input string match. */ - incr = (range < 0) ? -1 : 1; - left_lim = (range < 0) ? start + range : start; - right_lim = (range < 0) ? start : start + range; - sb = dfa->mb_cur_max == 1; - match_kind = - (fastmap - ? ((sb || !(preg->syntax & RE_ICASE || t) ? 4 : 0) - | (range >= 0 ? 2 : 0) - | (t != NULL ? 1 : 0)) - : 8); - - for (;; match_first += incr) - { - err = REG_NOMATCH; - if (match_first < left_lim || right_lim < match_first) - goto free_return; - - /* Advance as rapidly as possible through the string, until we - find a plausible place to start matching. This may be done - with varying efficiency, so there are various possibilities: - only the most common of them are specialized, in order to - save on code size. We use a switch statement for speed. */ - switch (match_kind) - { - case 8: - /* No fastmap. */ - break; - - case 7: - /* Fastmap with single-byte translation, match forward. */ - while (BE (match_first < right_lim, 1) - && !fastmap[t[(unsigned char) string[match_first]]]) - ++match_first; - goto forward_match_found_start_or_reached_end; - - case 6: - /* Fastmap without translation, match forward. */ - while (BE (match_first < right_lim, 1) - && !fastmap[(unsigned char) string[match_first]]) - ++match_first; - - forward_match_found_start_or_reached_end: - if (BE (match_first == right_lim, 0)) - { - ch = match_first >= length - ? 0 : (unsigned char) string[match_first]; - if (!fastmap[t ? t[ch] : ch]) - goto free_return; - } - break; - - case 4: - case 5: - /* Fastmap without multi-byte translation, match backwards. */ - while (match_first >= left_lim) - { - ch = match_first >= length - ? 0 : (unsigned char) string[match_first]; - if (fastmap[t ? t[ch] : ch]) - break; - --match_first; - } - if (match_first < left_lim) - goto free_return; - break; - - default: - /* In this case, we can't determine easily the current byte, - since it might be a component byte of a multibyte - character. Then we use the constructed buffer instead. */ - for (;;) - { - /* If MATCH_FIRST is out of the valid range, reconstruct the - buffers. */ - unsigned int offset = match_first - mctx.input.raw_mbs_idx; - if (BE (offset >= (unsigned int) mctx.input.valid_raw_len, 0)) - { - err = re_string_reconstruct (&mctx.input, match_first, - eflags); - if (BE (err != REG_NOERROR, 0)) - goto free_return; - - offset = match_first - mctx.input.raw_mbs_idx; - } - /* If MATCH_FIRST is out of the buffer, leave it as '\0'. - Note that MATCH_FIRST must not be smaller than 0. */ - ch = (match_first >= length - ? 0 : re_string_byte_at (&mctx.input, offset)); - if (fastmap[ch]) - break; - match_first += incr; - if (match_first < left_lim || match_first > right_lim) - { - err = REG_NOMATCH; - goto free_return; - } - } - break; - } - - /* Reconstruct the buffers so that the matcher can assume that - the matching starts from the beginning of the buffer. */ - err = re_string_reconstruct (&mctx.input, match_first, eflags); - if (BE (err != REG_NOERROR, 0)) - goto free_return; - -#ifdef RE_ENABLE_I18N - /* Don't consider this char as a possible match start if it part, - yet isn't the head, of a multibyte character. */ - if (!sb && !re_string_first_byte (&mctx.input, 0)) - continue; -#endif - - /* It seems to be appropriate one, then use the matcher. */ - /* We assume that the matching starts from 0. */ - mctx.state_log_top = mctx.nbkref_ents = mctx.max_mb_elem_len = 0; - match_last = check_matching (&mctx, fl_longest_match, - range >= 0 ? &match_first : NULL); - if (match_last != -1) - { - if (BE (match_last == -2, 0)) - { - err = REG_ESPACE; - goto free_return; - } - else - { - mctx.match_last = match_last; - if ((!preg->no_sub && nmatch > 1) || dfa->nbackref) - { - re_dfastate_t *pstate = mctx.state_log[match_last]; - mctx.last_node = check_halt_state_context (&mctx, pstate, - match_last); - } - if ((!preg->no_sub && nmatch > 1 && dfa->has_plural_match) - || dfa->nbackref) - { - err = prune_impossible_nodes (&mctx); - if (err == REG_NOERROR) - break; - if (BE (err != REG_NOMATCH, 0)) - goto free_return; - match_last = -1; - } - else - break; /* We found a match. */ - } - } - - match_ctx_clean (&mctx); - } - -#ifdef DEBUG - assert (match_last != -1); - assert (err == REG_NOERROR); -#endif - - /* Set pmatch[] if we need. */ - if (nmatch > 0) - { - unsigned int reg_idx; - - /* Initialize registers. */ - for (reg_idx = 1; reg_idx < nmatch; ++reg_idx) - pmatch[reg_idx].rm_so = pmatch[reg_idx].rm_eo = -1; - - /* Set the points where matching start/end. */ - pmatch[0].rm_so = 0; - pmatch[0].rm_eo = mctx.match_last; - - if (!preg->no_sub && nmatch > 1) - { - err = set_regs (preg, &mctx, nmatch, pmatch, - dfa->has_plural_match && dfa->nbackref > 0); - if (BE (err != REG_NOERROR, 0)) - goto free_return; - } - - /* At last, add the offset to the each registers, since we slided - the buffers so that we could assume that the matching starts - from 0. */ - for (reg_idx = 0; reg_idx < nmatch; ++reg_idx) - if (pmatch[reg_idx].rm_so != -1) - { -#ifdef RE_ENABLE_I18N - if (BE (mctx.input.offsets_needed != 0, 0)) - { - pmatch[reg_idx].rm_so = - (pmatch[reg_idx].rm_so == mctx.input.valid_len - ? mctx.input.valid_raw_len - : mctx.input.offsets[pmatch[reg_idx].rm_so]); - pmatch[reg_idx].rm_eo = - (pmatch[reg_idx].rm_eo == mctx.input.valid_len - ? mctx.input.valid_raw_len - : mctx.input.offsets[pmatch[reg_idx].rm_eo]); - } -#else - assert (mctx.input.offsets_needed == 0); -#endif - pmatch[reg_idx].rm_so += match_first; - pmatch[reg_idx].rm_eo += match_first; - } - for (reg_idx = 0; reg_idx < extra_nmatch; ++reg_idx) - { - pmatch[nmatch + reg_idx].rm_so = -1; - pmatch[nmatch + reg_idx].rm_eo = -1; - } - - if (dfa->subexp_map) - for (reg_idx = 0; reg_idx + 1 < nmatch; reg_idx++) - if (dfa->subexp_map[reg_idx] != (int)reg_idx) - { - pmatch[reg_idx + 1].rm_so - = pmatch[dfa->subexp_map[reg_idx] + 1].rm_so; - pmatch[reg_idx + 1].rm_eo - = pmatch[dfa->subexp_map[reg_idx] + 1].rm_eo; - } - } - - free_return: - re_free (mctx.state_log); - if (dfa->nbackref) - match_ctx_free (&mctx); - re_string_destruct (&mctx.input); - return err; -} - -static reg_errcode_t -prune_impossible_nodes (re_match_context_t *mctx) -{ - const re_dfa_t *const dfa = mctx->dfa; - int halt_node, match_last; - reg_errcode_t ret; - re_dfastate_t **sifted_states; - re_dfastate_t **lim_states = NULL; - re_sift_context_t sctx; -#ifdef DEBUG - assert (mctx->state_log != NULL); -#endif - match_last = mctx->match_last; - halt_node = mctx->last_node; - - /* Avoid overflow. */ - if (BE (SIZE_MAX / sizeof (re_dfastate_t *) <= (size_t)match_last, 0)) - return REG_ESPACE; - - sifted_states = re_malloc (re_dfastate_t *, match_last + 1); - if (BE (sifted_states == NULL, 0)) - { - ret = REG_ESPACE; - goto free_return; - } - if (dfa->nbackref) - { - lim_states = re_malloc (re_dfastate_t *, match_last + 1); - if (BE (lim_states == NULL, 0)) - { - ret = REG_ESPACE; - goto free_return; - } - while (1) - { - memset (lim_states, '\0', - sizeof (re_dfastate_t *) * (match_last + 1)); - sift_ctx_init (&sctx, sifted_states, lim_states, halt_node, - match_last); - ret = sift_states_backward (mctx, &sctx); - re_node_set_free (&sctx.limits); - if (BE (ret != REG_NOERROR, 0)) - goto free_return; - if (sifted_states[0] != NULL || lim_states[0] != NULL) - break; - do - { - --match_last; - if (match_last < 0) - { - ret = REG_NOMATCH; - goto free_return; - } - } while (mctx->state_log[match_last] == NULL - || !mctx->state_log[match_last]->halt); - halt_node = check_halt_state_context (mctx, - mctx->state_log[match_last], - match_last); - } - ret = merge_state_array (dfa, sifted_states, lim_states, - match_last + 1); - re_free (lim_states); - lim_states = NULL; - if (BE (ret != REG_NOERROR, 0)) - goto free_return; - } - else - { - sift_ctx_init (&sctx, sifted_states, lim_states, halt_node, match_last); - ret = sift_states_backward (mctx, &sctx); - re_node_set_free (&sctx.limits); - if (BE (ret != REG_NOERROR, 0)) - goto free_return; - if (sifted_states[0] == NULL) - { - ret = REG_NOMATCH; - goto free_return; - } - } - re_free (mctx->state_log); - mctx->state_log = sifted_states; - sifted_states = NULL; - mctx->last_node = halt_node; - mctx->match_last = match_last; - ret = REG_NOERROR; - free_return: - re_free (sifted_states); - re_free (lim_states); - return ret; -} - -/* Acquire an initial state and return it. - We must select appropriate initial state depending on the context, - since initial states may have constraints like "\<", "^", etc.. */ - -static inline re_dfastate_t * -__attribute ((always_inline)) internal_function -acquire_init_state_context (reg_errcode_t *err, const re_match_context_t *mctx, - int idx) -{ - const re_dfa_t *const dfa = mctx->dfa; - if (dfa->init_state->has_constraint) - { - unsigned int context; - context = re_string_context_at (&mctx->input, idx - 1, mctx->eflags); - if (IS_WORD_CONTEXT (context)) - return dfa->init_state_word; - else if (IS_ORDINARY_CONTEXT (context)) - return dfa->init_state; - else if (IS_BEGBUF_CONTEXT (context) && IS_NEWLINE_CONTEXT (context)) - return dfa->init_state_begbuf; - else if (IS_NEWLINE_CONTEXT (context)) - return dfa->init_state_nl; - else if (IS_BEGBUF_CONTEXT (context)) - { - /* It is relatively rare case, then calculate on demand. */ - return re_acquire_state_context (err, dfa, - dfa->init_state->entrance_nodes, - context); - } - else - /* Must not happen? */ - return dfa->init_state; - } - else - return dfa->init_state; -} - -/* Check whether the regular expression match input string INPUT or not, - and return the index where the matching end, return -1 if not match, - or return -2 in case of an error. - FL_LONGEST_MATCH means we want the POSIX longest matching. - If P_MATCH_FIRST is not NULL, and the match fails, it is set to the - next place where we may want to try matching. - Note that the matcher assume that the maching starts from the current - index of the buffer. */ - -static int -internal_function -check_matching (re_match_context_t *mctx, int fl_longest_match, - int *p_match_first) -{ - const re_dfa_t *const dfa = mctx->dfa; - reg_errcode_t err; - int match = 0; - int match_last = -1; - int cur_str_idx = re_string_cur_idx (&mctx->input); - re_dfastate_t *cur_state; - int at_init_state = p_match_first != NULL; - int next_start_idx = cur_str_idx; - - err = REG_NOERROR; - cur_state = acquire_init_state_context (&err, mctx, cur_str_idx); - /* An initial state must not be NULL (invalid). */ - if (BE (cur_state == NULL, 0)) - { - assert (err == REG_ESPACE); - return -2; - } - - if (mctx->state_log != NULL) - { - mctx->state_log[cur_str_idx] = cur_state; - - /* Check OP_OPEN_SUBEXP in the initial state in case that we use them - later. E.g. Processing back references. */ - if (BE (dfa->nbackref, 0)) - { - at_init_state = 0; - err = check_subexp_matching_top (mctx, &cur_state->nodes, 0); - if (BE (err != REG_NOERROR, 0)) - return err; - - if (cur_state->has_backref) - { - err = transit_state_bkref (mctx, &cur_state->nodes); - if (BE (err != REG_NOERROR, 0)) - return err; - } - } - } - - /* If the RE accepts NULL string. */ - if (BE (cur_state->halt, 0)) - { - if (!cur_state->has_constraint - || check_halt_state_context (mctx, cur_state, cur_str_idx)) - { - if (!fl_longest_match) - return cur_str_idx; - else - { - match_last = cur_str_idx; - match = 1; - } - } - } - - while (!re_string_eoi (&mctx->input)) - { - re_dfastate_t *old_state = cur_state; - int next_char_idx = re_string_cur_idx (&mctx->input) + 1; - - if (BE (next_char_idx >= mctx->input.bufs_len, 0) - || (BE (next_char_idx >= mctx->input.valid_len, 0) - && mctx->input.valid_len < mctx->input.len)) - { - err = extend_buffers (mctx); - if (BE (err != REG_NOERROR, 0)) - { - assert (err == REG_ESPACE); - return -2; - } - } - - cur_state = transit_state (&err, mctx, cur_state); - if (mctx->state_log != NULL) - cur_state = merge_state_with_log (&err, mctx, cur_state); - - if (cur_state == NULL) - { - /* Reached the invalid state or an error. Try to recover a valid - state using the state log, if available and if we have not - already found a valid (even if not the longest) match. */ - if (BE (err != REG_NOERROR, 0)) - return -2; - - if (mctx->state_log == NULL - || (match && !fl_longest_match) - || (cur_state = find_recover_state (&err, mctx)) == NULL) - break; - } - - if (BE (at_init_state, 0)) - { - if (old_state == cur_state) - next_start_idx = next_char_idx; - else - at_init_state = 0; - } - - if (cur_state->halt) - { - /* Reached a halt state. - Check the halt state can satisfy the current context. */ - if (!cur_state->has_constraint - || check_halt_state_context (mctx, cur_state, - re_string_cur_idx (&mctx->input))) - { - /* We found an appropriate halt state. */ - match_last = re_string_cur_idx (&mctx->input); - match = 1; - - /* We found a match, do not modify match_first below. */ - p_match_first = NULL; - if (!fl_longest_match) - break; - } - } - } - - if (p_match_first) - *p_match_first += next_start_idx; - - return match_last; -} - -/* Check NODE match the current context. */ - -static int -internal_function -check_halt_node_context (const re_dfa_t *dfa, int node, unsigned int context) -{ - re_token_type_t type = dfa->nodes[node].type; - unsigned int constraint = dfa->nodes[node].constraint; - if (type != END_OF_RE) - return 0; - if (!constraint) - return 1; - if (NOT_SATISFY_NEXT_CONSTRAINT (constraint, context)) - return 0; - return 1; -} - -/* Check the halt state STATE match the current context. - Return 0 if not match, if the node, STATE has, is a halt node and - match the context, return the node. */ - -static int -internal_function -check_halt_state_context (const re_match_context_t *mctx, - const re_dfastate_t *state, int idx) -{ - int i; - unsigned int context; -#ifdef DEBUG - assert (state->halt); -#endif - context = re_string_context_at (&mctx->input, idx, mctx->eflags); - for (i = 0; i < state->nodes.nelem; ++i) - if (check_halt_node_context (mctx->dfa, state->nodes.elems[i], context)) - return state->nodes.elems[i]; - return 0; -} - -/* Compute the next node to which "NFA" transit from NODE("NFA" is a NFA - corresponding to the DFA). - Return the destination node, and update EPS_VIA_NODES, return -1 in case - of errors. */ - -static int -internal_function -proceed_next_node (const re_match_context_t *mctx, int nregs, regmatch_t *regs, - int *pidx, int node, re_node_set *eps_via_nodes, - struct re_fail_stack_t *fs) -{ - const re_dfa_t *const dfa = mctx->dfa; - int i, err; - if (IS_EPSILON_NODE (dfa->nodes[node].type)) - { - re_node_set *cur_nodes = &mctx->state_log[*pidx]->nodes; - re_node_set *edests = &dfa->edests[node]; - int dest_node; - err = re_node_set_insert (eps_via_nodes, node); - if (BE (err < 0, 0)) - return -2; - /* Pick up a valid destination, or return -1 if none is found. */ - for (dest_node = -1, i = 0; i < edests->nelem; ++i) - { - int candidate = edests->elems[i]; - if (!re_node_set_contains (cur_nodes, candidate)) - continue; - if (dest_node == -1) - dest_node = candidate; - - else - { - /* In order to avoid infinite loop like "(a*)*", return the second - epsilon-transition if the first was already considered. */ - if (re_node_set_contains (eps_via_nodes, dest_node)) - return candidate; - - /* Otherwise, push the second epsilon-transition on the fail stack. */ - else if (fs != NULL - && push_fail_stack (fs, *pidx, candidate, nregs, regs, - eps_via_nodes)) - return -2; - - /* We know we are going to exit. */ - break; - } - } - return dest_node; - } - else - { - int naccepted = 0; - re_token_type_t type = dfa->nodes[node].type; - -#ifdef RE_ENABLE_I18N - if (dfa->nodes[node].accept_mb) - naccepted = check_node_accept_bytes (dfa, node, &mctx->input, *pidx); - else -#endif /* RE_ENABLE_I18N */ - if (type == OP_BACK_REF) - { - int subexp_idx = dfa->nodes[node].opr.idx + 1; - naccepted = regs[subexp_idx].rm_eo - regs[subexp_idx].rm_so; - if (fs != NULL) - { - if (regs[subexp_idx].rm_so == -1 || regs[subexp_idx].rm_eo == -1) - return -1; - else if (naccepted) - { - char *buf = (char *) re_string_get_buffer (&mctx->input); - if (memcmp (buf + regs[subexp_idx].rm_so, buf + *pidx, - naccepted) != 0) - return -1; - } - } - - if (naccepted == 0) - { - int dest_node; - err = re_node_set_insert (eps_via_nodes, node); - if (BE (err < 0, 0)) - return -2; - dest_node = dfa->edests[node].elems[0]; - if (re_node_set_contains (&mctx->state_log[*pidx]->nodes, - dest_node)) - return dest_node; - } - } - - if (naccepted != 0 - || check_node_accept (mctx, dfa->nodes + node, *pidx)) - { - int dest_node = dfa->nexts[node]; - *pidx = (naccepted == 0) ? *pidx + 1 : *pidx + naccepted; - if (fs && (*pidx > mctx->match_last || mctx->state_log[*pidx] == NULL - || !re_node_set_contains (&mctx->state_log[*pidx]->nodes, - dest_node))) - return -1; - re_node_set_empty (eps_via_nodes); - return dest_node; - } - } - return -1; -} - -static reg_errcode_t -internal_function -push_fail_stack (struct re_fail_stack_t *fs, int str_idx, int dest_node, - int nregs, regmatch_t *regs, re_node_set *eps_via_nodes) -{ - reg_errcode_t err; - int num = fs->num++; - if (fs->num == fs->alloc) - { - struct re_fail_stack_ent_t *new_array; - new_array = realloc (fs->stack, (sizeof (struct re_fail_stack_ent_t) - * fs->alloc * 2)); - if (new_array == NULL) - return REG_ESPACE; - fs->alloc *= 2; - fs->stack = new_array; - } - fs->stack[num].idx = str_idx; - fs->stack[num].node = dest_node; - fs->stack[num].regs = re_malloc (regmatch_t, nregs); - if (fs->stack[num].regs == NULL) - return REG_ESPACE; - memcpy (fs->stack[num].regs, regs, sizeof (regmatch_t) * nregs); - err = re_node_set_init_copy (&fs->stack[num].eps_via_nodes, eps_via_nodes); - return err; -} - -static int -internal_function -pop_fail_stack (struct re_fail_stack_t *fs, int *pidx, int nregs, - regmatch_t *regs, re_node_set *eps_via_nodes) -{ - int num = --fs->num; - assert (num >= 0); - *pidx = fs->stack[num].idx; - memcpy (regs, fs->stack[num].regs, sizeof (regmatch_t) * nregs); - re_node_set_free (eps_via_nodes); - re_free (fs->stack[num].regs); - *eps_via_nodes = fs->stack[num].eps_via_nodes; - return fs->stack[num].node; -} - -/* Set the positions where the subexpressions are starts/ends to registers - PMATCH. - Note: We assume that pmatch[0] is already set, and - pmatch[i].rm_so == pmatch[i].rm_eo == -1 for 0 < i < nmatch. */ - -static reg_errcode_t -internal_function -set_regs (const regex_t *preg, const re_match_context_t *mctx, size_t nmatch, - regmatch_t *pmatch, int fl_backtrack) -{ - const re_dfa_t *dfa = (const re_dfa_t *) preg->buffer; - int idx, cur_node; - re_node_set eps_via_nodes; - struct re_fail_stack_t *fs; - struct re_fail_stack_t fs_body = { 0, 2, NULL }; - regmatch_t *prev_idx_match; - int prev_idx_match_malloced = 0; - -#ifdef DEBUG - assert (nmatch > 1); - assert (mctx->state_log != NULL); -#endif - if (fl_backtrack) - { - fs = &fs_body; - fs->stack = re_malloc (struct re_fail_stack_ent_t, fs->alloc); - if (fs->stack == NULL) - return REG_ESPACE; - } - else - fs = NULL; - - cur_node = dfa->init_node; - re_node_set_init_empty (&eps_via_nodes); - -#ifdef HAVE_ALLOCA - if (__libc_use_alloca (nmatch * sizeof (regmatch_t))) - prev_idx_match = (regmatch_t *) alloca (nmatch * sizeof (regmatch_t)); - else -#endif - { - prev_idx_match = re_malloc (regmatch_t, nmatch); - if (prev_idx_match == NULL) - { - free_fail_stack_return (fs); - return REG_ESPACE; - } - prev_idx_match_malloced = 1; - } - memcpy (prev_idx_match, pmatch, sizeof (regmatch_t) * nmatch); - - for (idx = pmatch[0].rm_so; idx <= pmatch[0].rm_eo ;) - { - update_regs (dfa, pmatch, prev_idx_match, cur_node, idx, nmatch); - - if (idx == pmatch[0].rm_eo && cur_node == mctx->last_node) - { - unsigned int reg_idx; - if (fs) - { - for (reg_idx = 0; reg_idx < nmatch; ++reg_idx) - if (pmatch[reg_idx].rm_so > -1 && pmatch[reg_idx].rm_eo == -1) - break; - if (reg_idx == nmatch) - { - re_node_set_free (&eps_via_nodes); - if (prev_idx_match_malloced) - re_free (prev_idx_match); - return free_fail_stack_return (fs); - } - cur_node = pop_fail_stack (fs, &idx, nmatch, pmatch, - &eps_via_nodes); - } - else - { - re_node_set_free (&eps_via_nodes); - if (prev_idx_match_malloced) - re_free (prev_idx_match); - return REG_NOERROR; - } - } - - /* Proceed to next node. */ - cur_node = proceed_next_node (mctx, nmatch, pmatch, &idx, cur_node, - &eps_via_nodes, fs); - - if (BE (cur_node < 0, 0)) - { - if (BE (cur_node == -2, 0)) - { - re_node_set_free (&eps_via_nodes); - if (prev_idx_match_malloced) - re_free (prev_idx_match); - free_fail_stack_return (fs); - return REG_ESPACE; - } - if (fs) - cur_node = pop_fail_stack (fs, &idx, nmatch, pmatch, - &eps_via_nodes); - else - { - re_node_set_free (&eps_via_nodes); - if (prev_idx_match_malloced) - re_free (prev_idx_match); - return REG_NOMATCH; - } - } - } - re_node_set_free (&eps_via_nodes); - if (prev_idx_match_malloced) - re_free (prev_idx_match); - return free_fail_stack_return (fs); -} - -static reg_errcode_t -internal_function -free_fail_stack_return (struct re_fail_stack_t *fs) -{ - if (fs) - { - int fs_idx; - for (fs_idx = 0; fs_idx < fs->num; ++fs_idx) - { - re_node_set_free (&fs->stack[fs_idx].eps_via_nodes); - re_free (fs->stack[fs_idx].regs); - } - re_free (fs->stack); - } - return REG_NOERROR; -} - -static void -internal_function -update_regs (const re_dfa_t *dfa, regmatch_t *pmatch, - regmatch_t *prev_idx_match, int cur_node, int cur_idx, int nmatch) -{ - int type = dfa->nodes[cur_node].type; - if (type == OP_OPEN_SUBEXP) - { - int reg_num = dfa->nodes[cur_node].opr.idx + 1; - - /* We are at the first node of this sub expression. */ - if (reg_num < nmatch) - { - pmatch[reg_num].rm_so = cur_idx; - pmatch[reg_num].rm_eo = -1; - } - } - else if (type == OP_CLOSE_SUBEXP) - { - int reg_num = dfa->nodes[cur_node].opr.idx + 1; - if (reg_num < nmatch) - { - /* We are at the last node of this sub expression. */ - if (pmatch[reg_num].rm_so < cur_idx) - { - pmatch[reg_num].rm_eo = cur_idx; - /* This is a non-empty match or we are not inside an optional - subexpression. Accept this right away. */ - memcpy (prev_idx_match, pmatch, sizeof (regmatch_t) * nmatch); - } - else - { - if (dfa->nodes[cur_node].opt_subexp - && prev_idx_match[reg_num].rm_so != -1) - /* We transited through an empty match for an optional - subexpression, like (a?)*, and this is not the subexp's - first match. Copy back the old content of the registers - so that matches of an inner subexpression are undone as - well, like in ((a?))*. */ - memcpy (pmatch, prev_idx_match, sizeof (regmatch_t) * nmatch); - else - /* We completed a subexpression, but it may be part of - an optional one, so do not update PREV_IDX_MATCH. */ - pmatch[reg_num].rm_eo = cur_idx; - } - } - } -} - -/* This function checks the STATE_LOG from the SCTX->last_str_idx to 0 - and sift the nodes in each states according to the following rules. - Updated state_log will be wrote to STATE_LOG. - - Rules: We throw away the Node `a' in the STATE_LOG[STR_IDX] if... - 1. When STR_IDX == MATCH_LAST(the last index in the state_log): - If `a' isn't the LAST_NODE and `a' can't epsilon transit to - the LAST_NODE, we throw away the node `a'. - 2. When 0 <= STR_IDX < MATCH_LAST and `a' accepts - string `s' and transit to `b': - i. If 'b' isn't in the STATE_LOG[STR_IDX+strlen('s')], we throw - away the node `a'. - ii. If 'b' is in the STATE_LOG[STR_IDX+strlen('s')] but 'b' is - thrown away, we throw away the node `a'. - 3. When 0 <= STR_IDX < MATCH_LAST and 'a' epsilon transit to 'b': - i. If 'b' isn't in the STATE_LOG[STR_IDX], we throw away the - node `a'. - ii. If 'b' is in the STATE_LOG[STR_IDX] but 'b' is thrown away, - we throw away the node `a'. */ - -#define STATE_NODE_CONTAINS(state,node) \ - ((state) != NULL && re_node_set_contains (&(state)->nodes, node)) - -static reg_errcode_t -internal_function -sift_states_backward (const re_match_context_t *mctx, re_sift_context_t *sctx) -{ - reg_errcode_t err; - int null_cnt = 0; - int str_idx = sctx->last_str_idx; - re_node_set cur_dest; - -#ifdef DEBUG - assert (mctx->state_log != NULL && mctx->state_log[str_idx] != NULL); -#endif - - /* Build sifted state_log[str_idx]. It has the nodes which can epsilon - transit to the last_node and the last_node itself. */ - err = re_node_set_init_1 (&cur_dest, sctx->last_node); - if (BE (err != REG_NOERROR, 0)) - return err; - err = update_cur_sifted_state (mctx, sctx, str_idx, &cur_dest); - if (BE (err != REG_NOERROR, 0)) - goto free_return; - - /* Then check each states in the state_log. */ - while (str_idx > 0) - { - /* Update counters. */ - null_cnt = (sctx->sifted_states[str_idx] == NULL) ? null_cnt + 1 : 0; - if (null_cnt > mctx->max_mb_elem_len) - { - memset (sctx->sifted_states, '\0', - sizeof (re_dfastate_t *) * str_idx); - re_node_set_free (&cur_dest); - return REG_NOERROR; - } - re_node_set_empty (&cur_dest); - --str_idx; - - if (mctx->state_log[str_idx]) - { - err = build_sifted_states (mctx, sctx, str_idx, &cur_dest); - if (BE (err != REG_NOERROR, 0)) - goto free_return; - } - - /* Add all the nodes which satisfy the following conditions: - - It can epsilon transit to a node in CUR_DEST. - - It is in CUR_SRC. - And update state_log. */ - err = update_cur_sifted_state (mctx, sctx, str_idx, &cur_dest); - if (BE (err != REG_NOERROR, 0)) - goto free_return; - } - err = REG_NOERROR; - free_return: - re_node_set_free (&cur_dest); - return err; -} - -static reg_errcode_t -internal_function -build_sifted_states (const re_match_context_t *mctx, re_sift_context_t *sctx, - int str_idx, re_node_set *cur_dest) -{ - const re_dfa_t *const dfa = mctx->dfa; - const re_node_set *cur_src = &mctx->state_log[str_idx]->non_eps_nodes; - int i; - - /* Then build the next sifted state. - We build the next sifted state on `cur_dest', and update - `sifted_states[str_idx]' with `cur_dest'. - Note: - `cur_dest' is the sifted state from `state_log[str_idx + 1]'. - `cur_src' points the node_set of the old `state_log[str_idx]' - (with the epsilon nodes pre-filtered out). */ - for (i = 0; i < cur_src->nelem; i++) - { - int prev_node = cur_src->elems[i]; - int naccepted = 0; - int ret; - -#ifdef DEBUG - re_token_type_t type = dfa->nodes[prev_node].type; - assert (!IS_EPSILON_NODE (type)); -#endif -#ifdef RE_ENABLE_I18N - /* If the node may accept `multi byte'. */ - if (dfa->nodes[prev_node].accept_mb) - naccepted = sift_states_iter_mb (mctx, sctx, prev_node, - str_idx, sctx->last_str_idx); -#endif /* RE_ENABLE_I18N */ - - /* We don't check backreferences here. - See update_cur_sifted_state(). */ - if (!naccepted - && check_node_accept (mctx, dfa->nodes + prev_node, str_idx) - && STATE_NODE_CONTAINS (sctx->sifted_states[str_idx + 1], - dfa->nexts[prev_node])) - naccepted = 1; - - if (naccepted == 0) - continue; - - if (sctx->limits.nelem) - { - int to_idx = str_idx + naccepted; - if (check_dst_limits (mctx, &sctx->limits, - dfa->nexts[prev_node], to_idx, - prev_node, str_idx)) - continue; - } - ret = re_node_set_insert (cur_dest, prev_node); - if (BE (ret == -1, 0)) - return REG_ESPACE; - } - - return REG_NOERROR; -} - -/* Helper functions. */ - -static reg_errcode_t -internal_function -clean_state_log_if_needed (re_match_context_t *mctx, int next_state_log_idx) -{ - int top = mctx->state_log_top; - - if (next_state_log_idx >= mctx->input.bufs_len - || (next_state_log_idx >= mctx->input.valid_len - && mctx->input.valid_len < mctx->input.len)) - { - reg_errcode_t err; - err = extend_buffers (mctx); - if (BE (err != REG_NOERROR, 0)) - return err; - } - - if (top < next_state_log_idx) - { - memset (mctx->state_log + top + 1, '\0', - sizeof (re_dfastate_t *) * (next_state_log_idx - top)); - mctx->state_log_top = next_state_log_idx; - } - return REG_NOERROR; -} - -static reg_errcode_t -internal_function -merge_state_array (const re_dfa_t *dfa, re_dfastate_t **dst, - re_dfastate_t **src, int num) -{ - int st_idx; - reg_errcode_t err; - for (st_idx = 0; st_idx < num; ++st_idx) - { - if (dst[st_idx] == NULL) - dst[st_idx] = src[st_idx]; - else if (src[st_idx] != NULL) - { - re_node_set merged_set; - err = re_node_set_init_union (&merged_set, &dst[st_idx]->nodes, - &src[st_idx]->nodes); - if (BE (err != REG_NOERROR, 0)) - return err; - dst[st_idx] = re_acquire_state (&err, dfa, &merged_set); - re_node_set_free (&merged_set); - if (BE (err != REG_NOERROR, 0)) - return err; - } - } - return REG_NOERROR; -} - -static reg_errcode_t -internal_function -update_cur_sifted_state (const re_match_context_t *mctx, - re_sift_context_t *sctx, int str_idx, - re_node_set *dest_nodes) -{ - const re_dfa_t *const dfa = mctx->dfa; - reg_errcode_t err = REG_NOERROR; - const re_node_set *candidates; - candidates = ((mctx->state_log[str_idx] == NULL) ? NULL - : &mctx->state_log[str_idx]->nodes); - - if (dest_nodes->nelem == 0) - sctx->sifted_states[str_idx] = NULL; - else - { - if (candidates) - { - /* At first, add the nodes which can epsilon transit to a node in - DEST_NODE. */ - err = add_epsilon_src_nodes (dfa, dest_nodes, candidates); - if (BE (err != REG_NOERROR, 0)) - return err; - - /* Then, check the limitations in the current sift_context. */ - if (sctx->limits.nelem) - { - err = check_subexp_limits (dfa, dest_nodes, candidates, &sctx->limits, - mctx->bkref_ents, str_idx); - if (BE (err != REG_NOERROR, 0)) - return err; - } - } - - sctx->sifted_states[str_idx] = re_acquire_state (&err, dfa, dest_nodes); - if (BE (err != REG_NOERROR, 0)) - return err; - } - - if (candidates && mctx->state_log[str_idx]->has_backref) - { - err = sift_states_bkref (mctx, sctx, str_idx, candidates); - if (BE (err != REG_NOERROR, 0)) - return err; - } - return REG_NOERROR; -} - -static reg_errcode_t -internal_function -add_epsilon_src_nodes (const re_dfa_t *dfa, re_node_set *dest_nodes, - const re_node_set *candidates) -{ - reg_errcode_t err = REG_NOERROR; - int i; - - re_dfastate_t *state = re_acquire_state (&err, dfa, dest_nodes); - if (BE (err != REG_NOERROR, 0)) - return err; - - if (!state->inveclosure.alloc) - { - err = re_node_set_alloc (&state->inveclosure, dest_nodes->nelem); - if (BE (err != REG_NOERROR, 0)) - return REG_ESPACE; - for (i = 0; i < dest_nodes->nelem; i++) - { - err = re_node_set_merge (&state->inveclosure, - dfa->inveclosures + dest_nodes->elems[i]); - if (BE (err != REG_NOERROR, 0)) - return REG_ESPACE; - } - } - return re_node_set_add_intersect (dest_nodes, candidates, - &state->inveclosure); -} - -static reg_errcode_t -internal_function -sub_epsilon_src_nodes (const re_dfa_t *dfa, int node, re_node_set *dest_nodes, - const re_node_set *candidates) -{ - int ecl_idx; - reg_errcode_t err; - re_node_set *inv_eclosure = dfa->inveclosures + node; - re_node_set except_nodes; - re_node_set_init_empty (&except_nodes); - for (ecl_idx = 0; ecl_idx < inv_eclosure->nelem; ++ecl_idx) - { - int cur_node = inv_eclosure->elems[ecl_idx]; - if (cur_node == node) - continue; - if (IS_EPSILON_NODE (dfa->nodes[cur_node].type)) - { - int edst1 = dfa->edests[cur_node].elems[0]; - int edst2 = ((dfa->edests[cur_node].nelem > 1) - ? dfa->edests[cur_node].elems[1] : -1); - if ((!re_node_set_contains (inv_eclosure, edst1) - && re_node_set_contains (dest_nodes, edst1)) - || (edst2 > 0 - && !re_node_set_contains (inv_eclosure, edst2) - && re_node_set_contains (dest_nodes, edst2))) - { - err = re_node_set_add_intersect (&except_nodes, candidates, - dfa->inveclosures + cur_node); - if (BE (err != REG_NOERROR, 0)) - { - re_node_set_free (&except_nodes); - return err; - } - } - } - } - for (ecl_idx = 0; ecl_idx < inv_eclosure->nelem; ++ecl_idx) - { - int cur_node = inv_eclosure->elems[ecl_idx]; - if (!re_node_set_contains (&except_nodes, cur_node)) - { - int idx = re_node_set_contains (dest_nodes, cur_node) - 1; - re_node_set_remove_at (dest_nodes, idx); - } - } - re_node_set_free (&except_nodes); - return REG_NOERROR; -} - -static int -internal_function -check_dst_limits (const re_match_context_t *mctx, re_node_set *limits, - int dst_node, int dst_idx, int src_node, int src_idx) -{ - const re_dfa_t *const dfa = mctx->dfa; - int lim_idx, src_pos, dst_pos; - - int dst_bkref_idx = search_cur_bkref_entry (mctx, dst_idx); - int src_bkref_idx = search_cur_bkref_entry (mctx, src_idx); - for (lim_idx = 0; lim_idx < limits->nelem; ++lim_idx) - { - int subexp_idx; - struct re_backref_cache_entry *ent; - ent = mctx->bkref_ents + limits->elems[lim_idx]; - subexp_idx = dfa->nodes[ent->node].opr.idx; - - dst_pos = check_dst_limits_calc_pos (mctx, limits->elems[lim_idx], - subexp_idx, dst_node, dst_idx, - dst_bkref_idx); - src_pos = check_dst_limits_calc_pos (mctx, limits->elems[lim_idx], - subexp_idx, src_node, src_idx, - src_bkref_idx); - - /* In case of: - ( ) - ( ) - ( ) */ - if (src_pos == dst_pos) - continue; /* This is unrelated limitation. */ - else - return 1; - } - return 0; -} - -static int -internal_function -check_dst_limits_calc_pos_1 (const re_match_context_t *mctx, int boundaries, - int subexp_idx, int from_node, int bkref_idx) -{ - const re_dfa_t *const dfa = mctx->dfa; - const re_node_set *eclosures = dfa->eclosures + from_node; - int node_idx; - - /* Else, we are on the boundary: examine the nodes on the epsilon - closure. */ - for (node_idx = 0; node_idx < eclosures->nelem; ++node_idx) - { - int node = eclosures->elems[node_idx]; - switch (dfa->nodes[node].type) - { - case OP_BACK_REF: - if (bkref_idx != -1) - { - struct re_backref_cache_entry *ent = mctx->bkref_ents + bkref_idx; - do - { - int dst, cpos; - - if (ent->node != node) - continue; - - if (subexp_idx < BITSET_WORD_BITS - && !(ent->eps_reachable_subexps_map - & ((bitset_word_t) 1 << subexp_idx))) - continue; - - /* Recurse trying to reach the OP_OPEN_SUBEXP and - OP_CLOSE_SUBEXP cases below. But, if the - destination node is the same node as the source - node, don't recurse because it would cause an - infinite loop: a regex that exhibits this behavior - is ()\1*\1* */ - dst = dfa->edests[node].elems[0]; - if (dst == from_node) - { - if (boundaries & 1) - return -1; - else /* if (boundaries & 2) */ - return 0; - } - - cpos = - check_dst_limits_calc_pos_1 (mctx, boundaries, subexp_idx, - dst, bkref_idx); - if (cpos == -1 /* && (boundaries & 1) */) - return -1; - if (cpos == 0 && (boundaries & 2)) - return 0; - - if (subexp_idx < BITSET_WORD_BITS) - ent->eps_reachable_subexps_map - &= ~((bitset_word_t) 1 << subexp_idx); - } - while (ent++->more); - } - break; - - case OP_OPEN_SUBEXP: - if ((boundaries & 1) && subexp_idx == dfa->nodes[node].opr.idx) - return -1; - break; - - case OP_CLOSE_SUBEXP: - if ((boundaries & 2) && subexp_idx == dfa->nodes[node].opr.idx) - return 0; - break; - - default: - break; - } - } - - return (boundaries & 2) ? 1 : 0; -} - -static int -internal_function -check_dst_limits_calc_pos (const re_match_context_t *mctx, int limit, - int subexp_idx, int from_node, int str_idx, - int bkref_idx) -{ - struct re_backref_cache_entry *lim = mctx->bkref_ents + limit; - int boundaries; - - /* If we are outside the range of the subexpression, return -1 or 1. */ - if (str_idx < lim->subexp_from) - return -1; - - if (lim->subexp_to < str_idx) - return 1; - - /* If we are within the subexpression, return 0. */ - boundaries = (str_idx == lim->subexp_from); - boundaries |= (str_idx == lim->subexp_to) << 1; - if (boundaries == 0) - return 0; - - /* Else, examine epsilon closure. */ - return check_dst_limits_calc_pos_1 (mctx, boundaries, subexp_idx, - from_node, bkref_idx); -} - -/* Check the limitations of sub expressions LIMITS, and remove the nodes - which are against limitations from DEST_NODES. */ - -static reg_errcode_t -internal_function -check_subexp_limits (const re_dfa_t *dfa, re_node_set *dest_nodes, - const re_node_set *candidates, re_node_set *limits, - struct re_backref_cache_entry *bkref_ents, int str_idx) -{ - reg_errcode_t err; - int node_idx, lim_idx; - - for (lim_idx = 0; lim_idx < limits->nelem; ++lim_idx) - { - int subexp_idx; - struct re_backref_cache_entry *ent; - ent = bkref_ents + limits->elems[lim_idx]; - - if (str_idx <= ent->subexp_from || ent->str_idx < str_idx) - continue; /* This is unrelated limitation. */ - - subexp_idx = dfa->nodes[ent->node].opr.idx; - if (ent->subexp_to == str_idx) - { - int ops_node = -1; - int cls_node = -1; - for (node_idx = 0; node_idx < dest_nodes->nelem; ++node_idx) - { - int node = dest_nodes->elems[node_idx]; - re_token_type_t type = dfa->nodes[node].type; - if (type == OP_OPEN_SUBEXP - && subexp_idx == dfa->nodes[node].opr.idx) - ops_node = node; - else if (type == OP_CLOSE_SUBEXP - && subexp_idx == dfa->nodes[node].opr.idx) - cls_node = node; - } - - /* Check the limitation of the open subexpression. */ - /* Note that (ent->subexp_to = str_idx != ent->subexp_from). */ - if (ops_node >= 0) - { - err = sub_epsilon_src_nodes (dfa, ops_node, dest_nodes, - candidates); - if (BE (err != REG_NOERROR, 0)) - return err; - } - - /* Check the limitation of the close subexpression. */ - if (cls_node >= 0) - for (node_idx = 0; node_idx < dest_nodes->nelem; ++node_idx) - { - int node = dest_nodes->elems[node_idx]; - if (!re_node_set_contains (dfa->inveclosures + node, - cls_node) - && !re_node_set_contains (dfa->eclosures + node, - cls_node)) - { - /* It is against this limitation. - Remove it form the current sifted state. */ - err = sub_epsilon_src_nodes (dfa, node, dest_nodes, - candidates); - if (BE (err != REG_NOERROR, 0)) - return err; - --node_idx; - } - } - } - else /* (ent->subexp_to != str_idx) */ - { - for (node_idx = 0; node_idx < dest_nodes->nelem; ++node_idx) - { - int node = dest_nodes->elems[node_idx]; - re_token_type_t type = dfa->nodes[node].type; - if (type == OP_CLOSE_SUBEXP || type == OP_OPEN_SUBEXP) - { - if (subexp_idx != dfa->nodes[node].opr.idx) - continue; - /* It is against this limitation. - Remove it form the current sifted state. */ - err = sub_epsilon_src_nodes (dfa, node, dest_nodes, - candidates); - if (BE (err != REG_NOERROR, 0)) - return err; - } - } - } - } - return REG_NOERROR; -} - -static reg_errcode_t -internal_function -sift_states_bkref (const re_match_context_t *mctx, re_sift_context_t *sctx, - int str_idx, const re_node_set *candidates) -{ - const re_dfa_t *const dfa = mctx->dfa; - reg_errcode_t err; - int node_idx, node; - re_sift_context_t local_sctx; - int first_idx = search_cur_bkref_entry (mctx, str_idx); - - if (first_idx == -1) - return REG_NOERROR; - - local_sctx.sifted_states = NULL; /* Mark that it hasn't been initialized. */ - - for (node_idx = 0; node_idx < candidates->nelem; ++node_idx) - { - int enabled_idx; - re_token_type_t type; - struct re_backref_cache_entry *entry; - node = candidates->elems[node_idx]; - type = dfa->nodes[node].type; - /* Avoid infinite loop for the REs like "()\1+". */ - if (node == sctx->last_node && str_idx == sctx->last_str_idx) - continue; - if (type != OP_BACK_REF) - continue; - - entry = mctx->bkref_ents + first_idx; - enabled_idx = first_idx; - do - { - int subexp_len; - int to_idx; - int dst_node; - int ret; - re_dfastate_t *cur_state; - - if (entry->node != node) - continue; - subexp_len = entry->subexp_to - entry->subexp_from; - to_idx = str_idx + subexp_len; - dst_node = (subexp_len ? dfa->nexts[node] - : dfa->edests[node].elems[0]); - - if (to_idx > sctx->last_str_idx - || sctx->sifted_states[to_idx] == NULL - || !STATE_NODE_CONTAINS (sctx->sifted_states[to_idx], dst_node) - || check_dst_limits (mctx, &sctx->limits, node, - str_idx, dst_node, to_idx)) - continue; - - if (local_sctx.sifted_states == NULL) - { - local_sctx = *sctx; - err = re_node_set_init_copy (&local_sctx.limits, &sctx->limits); - if (BE (err != REG_NOERROR, 0)) - goto free_return; - } - local_sctx.last_node = node; - local_sctx.last_str_idx = str_idx; - ret = re_node_set_insert (&local_sctx.limits, enabled_idx); - if (BE (ret < 0, 0)) - { - err = REG_ESPACE; - goto free_return; - } - cur_state = local_sctx.sifted_states[str_idx]; - err = sift_states_backward (mctx, &local_sctx); - if (BE (err != REG_NOERROR, 0)) - goto free_return; - if (sctx->limited_states != NULL) - { - err = merge_state_array (dfa, sctx->limited_states, - local_sctx.sifted_states, - str_idx + 1); - if (BE (err != REG_NOERROR, 0)) - goto free_return; - } - local_sctx.sifted_states[str_idx] = cur_state; - re_node_set_remove (&local_sctx.limits, enabled_idx); - - /* mctx->bkref_ents may have changed, reload the pointer. */ - entry = mctx->bkref_ents + enabled_idx; - } - while (enabled_idx++, entry++->more); - } - err = REG_NOERROR; - free_return: - if (local_sctx.sifted_states != NULL) - { - re_node_set_free (&local_sctx.limits); - } - - return err; -} - - -#ifdef RE_ENABLE_I18N -static int -internal_function -sift_states_iter_mb (const re_match_context_t *mctx, re_sift_context_t *sctx, - int node_idx, int str_idx, int max_str_idx) -{ - const re_dfa_t *const dfa = mctx->dfa; - int naccepted; - /* Check the node can accept `multi byte'. */ - naccepted = check_node_accept_bytes (dfa, node_idx, &mctx->input, str_idx); - if (naccepted > 0 && str_idx + naccepted <= max_str_idx && - !STATE_NODE_CONTAINS (sctx->sifted_states[str_idx + naccepted], - dfa->nexts[node_idx])) - /* The node can't accept the `multi byte', or the - destination was already thrown away, then the node - could't accept the current input `multi byte'. */ - naccepted = 0; - /* Otherwise, it is sure that the node could accept - `naccepted' bytes input. */ - return naccepted; -} -#endif /* RE_ENABLE_I18N */ - - -/* Functions for state transition. */ - -/* Return the next state to which the current state STATE will transit by - accepting the current input byte, and update STATE_LOG if necessary. - If STATE can accept a multibyte char/collating element/back reference - update the destination of STATE_LOG. */ - -static re_dfastate_t * -internal_function -transit_state (reg_errcode_t *err, re_match_context_t *mctx, - re_dfastate_t *state) -{ - re_dfastate_t **trtable; - unsigned char ch; - -#ifdef RE_ENABLE_I18N - /* If the current state can accept multibyte. */ - if (BE (state->accept_mb, 0)) - { - *err = transit_state_mb (mctx, state); - if (BE (*err != REG_NOERROR, 0)) - return NULL; - } -#endif /* RE_ENABLE_I18N */ - - /* Then decide the next state with the single byte. */ -#if 0 - if (0) - /* don't use transition table */ - return transit_state_sb (err, mctx, state); -#endif - - /* Use transition table */ - ch = re_string_fetch_byte (&mctx->input); - for (;;) - { - trtable = state->trtable; - if (BE (trtable != NULL, 1)) - return trtable[ch]; - - trtable = state->word_trtable; - if (BE (trtable != NULL, 1)) - { - unsigned int context; - context - = re_string_context_at (&mctx->input, - re_string_cur_idx (&mctx->input) - 1, - mctx->eflags); - if (IS_WORD_CONTEXT (context)) - return trtable[ch + SBC_MAX]; - else - return trtable[ch]; - } - - if (!build_trtable (mctx->dfa, state)) - { - *err = REG_ESPACE; - return NULL; - } - - /* Retry, we now have a transition table. */ - } -} - -/* Update the state_log if we need */ -re_dfastate_t * -internal_function -merge_state_with_log (reg_errcode_t *err, re_match_context_t *mctx, - re_dfastate_t *next_state) -{ - const re_dfa_t *const dfa = mctx->dfa; - int cur_idx = re_string_cur_idx (&mctx->input); - - if (cur_idx > mctx->state_log_top) - { - mctx->state_log[cur_idx] = next_state; - mctx->state_log_top = cur_idx; - } - else if (mctx->state_log[cur_idx] == 0) - { - mctx->state_log[cur_idx] = next_state; - } - else - { - re_dfastate_t *pstate; - unsigned int context; - re_node_set next_nodes, *log_nodes, *table_nodes = NULL; - /* If (state_log[cur_idx] != 0), it implies that cur_idx is - the destination of a multibyte char/collating element/ - back reference. Then the next state is the union set of - these destinations and the results of the transition table. */ - pstate = mctx->state_log[cur_idx]; - log_nodes = pstate->entrance_nodes; - if (next_state != NULL) - { - table_nodes = next_state->entrance_nodes; - *err = re_node_set_init_union (&next_nodes, table_nodes, - log_nodes); - if (BE (*err != REG_NOERROR, 0)) - return NULL; - } - else - next_nodes = *log_nodes; - /* Note: We already add the nodes of the initial state, - then we don't need to add them here. */ - - context = re_string_context_at (&mctx->input, - re_string_cur_idx (&mctx->input) - 1, - mctx->eflags); - next_state = mctx->state_log[cur_idx] - = re_acquire_state_context (err, dfa, &next_nodes, context); - /* We don't need to check errors here, since the return value of - this function is next_state and ERR is already set. */ - - if (table_nodes != NULL) - re_node_set_free (&next_nodes); - } - - if (BE (dfa->nbackref, 0) && next_state != NULL) - { - /* Check OP_OPEN_SUBEXP in the current state in case that we use them - later. We must check them here, since the back references in the - next state might use them. */ - *err = check_subexp_matching_top (mctx, &next_state->nodes, - cur_idx); - if (BE (*err != REG_NOERROR, 0)) - return NULL; - - /* If the next state has back references. */ - if (next_state->has_backref) - { - *err = transit_state_bkref (mctx, &next_state->nodes); - if (BE (*err != REG_NOERROR, 0)) - return NULL; - next_state = mctx->state_log[cur_idx]; - } - } - - return next_state; -} - -/* Skip bytes in the input that correspond to part of a - multi-byte match, then look in the log for a state - from which to restart matching. */ -re_dfastate_t * -internal_function -find_recover_state (reg_errcode_t *err, re_match_context_t *mctx) -{ - re_dfastate_t *cur_state; - do - { - int max = mctx->state_log_top; - int cur_str_idx = re_string_cur_idx (&mctx->input); - - do - { - if (++cur_str_idx > max) - return NULL; - re_string_skip_bytes (&mctx->input, 1); - } - while (mctx->state_log[cur_str_idx] == NULL); - - cur_state = merge_state_with_log (err, mctx, NULL); - } - while (*err == REG_NOERROR && cur_state == NULL); - return cur_state; -} - -/* Helper functions for transit_state. */ - -/* From the node set CUR_NODES, pick up the nodes whose types are - OP_OPEN_SUBEXP and which have corresponding back references in the regular - expression. And register them to use them later for evaluating the - correspoding back references. */ - -static reg_errcode_t -internal_function -check_subexp_matching_top (re_match_context_t *mctx, re_node_set *cur_nodes, - int str_idx) -{ - const re_dfa_t *const dfa = mctx->dfa; - int node_idx; - reg_errcode_t err; - - /* TODO: This isn't efficient. - Because there might be more than one nodes whose types are - OP_OPEN_SUBEXP and whose index is SUBEXP_IDX, we must check all - nodes. - E.g. RE: (a){2} */ - for (node_idx = 0; node_idx < cur_nodes->nelem; ++node_idx) - { - int node = cur_nodes->elems[node_idx]; - if (dfa->nodes[node].type == OP_OPEN_SUBEXP - && dfa->nodes[node].opr.idx < BITSET_WORD_BITS - && (dfa->used_bkref_map - & ((bitset_word_t) 1 << dfa->nodes[node].opr.idx))) - { - err = match_ctx_add_subtop (mctx, node, str_idx); - if (BE (err != REG_NOERROR, 0)) - return err; - } - } - return REG_NOERROR; -} - -#if 0 -/* Return the next state to which the current state STATE will transit by - accepting the current input byte. */ - -static re_dfastate_t * -transit_state_sb (reg_errcode_t *err, re_match_context_t *mctx, - re_dfastate_t *state) -{ - const re_dfa_t *const dfa = mctx->dfa; - re_node_set next_nodes; - re_dfastate_t *next_state; - int node_cnt, cur_str_idx = re_string_cur_idx (&mctx->input); - unsigned int context; - - *err = re_node_set_alloc (&next_nodes, state->nodes.nelem + 1); - if (BE (*err != REG_NOERROR, 0)) - return NULL; - for (node_cnt = 0; node_cnt < state->nodes.nelem; ++node_cnt) - { - int cur_node = state->nodes.elems[node_cnt]; - if (check_node_accept (mctx, dfa->nodes + cur_node, cur_str_idx)) - { - *err = re_node_set_merge (&next_nodes, - dfa->eclosures + dfa->nexts[cur_node]); - if (BE (*err != REG_NOERROR, 0)) - { - re_node_set_free (&next_nodes); - return NULL; - } - } - } - context = re_string_context_at (&mctx->input, cur_str_idx, mctx->eflags); - next_state = re_acquire_state_context (err, dfa, &next_nodes, context); - /* We don't need to check errors here, since the return value of - this function is next_state and ERR is already set. */ - - re_node_set_free (&next_nodes); - re_string_skip_bytes (&mctx->input, 1); - return next_state; -} -#endif - -#ifdef RE_ENABLE_I18N -static reg_errcode_t -internal_function -transit_state_mb (re_match_context_t *mctx, re_dfastate_t *pstate) -{ - const re_dfa_t *const dfa = mctx->dfa; - reg_errcode_t err; - int i; - - for (i = 0; i < pstate->nodes.nelem; ++i) - { - re_node_set dest_nodes, *new_nodes; - int cur_node_idx = pstate->nodes.elems[i]; - int naccepted, dest_idx; - unsigned int context; - re_dfastate_t *dest_state; - - if (!dfa->nodes[cur_node_idx].accept_mb) - continue; - - if (dfa->nodes[cur_node_idx].constraint) - { - context = re_string_context_at (&mctx->input, - re_string_cur_idx (&mctx->input), - mctx->eflags); - if (NOT_SATISFY_NEXT_CONSTRAINT (dfa->nodes[cur_node_idx].constraint, - context)) - continue; - } - - /* How many bytes the node can accept? */ - naccepted = check_node_accept_bytes (dfa, cur_node_idx, &mctx->input, - re_string_cur_idx (&mctx->input)); - if (naccepted == 0) - continue; - - /* The node can accepts `naccepted' bytes. */ - dest_idx = re_string_cur_idx (&mctx->input) + naccepted; - mctx->max_mb_elem_len = ((mctx->max_mb_elem_len < naccepted) ? naccepted - : mctx->max_mb_elem_len); - err = clean_state_log_if_needed (mctx, dest_idx); - if (BE (err != REG_NOERROR, 0)) - return err; -#ifdef DEBUG - assert (dfa->nexts[cur_node_idx] != -1); -#endif - new_nodes = dfa->eclosures + dfa->nexts[cur_node_idx]; - - dest_state = mctx->state_log[dest_idx]; - if (dest_state == NULL) - dest_nodes = *new_nodes; - else - { - err = re_node_set_init_union (&dest_nodes, - dest_state->entrance_nodes, new_nodes); - if (BE (err != REG_NOERROR, 0)) - return err; - } - context = re_string_context_at (&mctx->input, dest_idx - 1, - mctx->eflags); - mctx->state_log[dest_idx] - = re_acquire_state_context (&err, dfa, &dest_nodes, context); - if (dest_state != NULL) - re_node_set_free (&dest_nodes); - if (BE (mctx->state_log[dest_idx] == NULL && err != REG_NOERROR, 0)) - return err; - } - return REG_NOERROR; -} -#endif /* RE_ENABLE_I18N */ - -static reg_errcode_t -internal_function -transit_state_bkref (re_match_context_t *mctx, const re_node_set *nodes) -{ - const re_dfa_t *const dfa = mctx->dfa; - reg_errcode_t err; - int i; - int cur_str_idx = re_string_cur_idx (&mctx->input); - - for (i = 0; i < nodes->nelem; ++i) - { - int dest_str_idx, prev_nelem, bkc_idx; - int node_idx = nodes->elems[i]; - unsigned int context; - const re_token_t *node = dfa->nodes + node_idx; - re_node_set *new_dest_nodes; - - /* Check whether `node' is a backreference or not. */ - if (node->type != OP_BACK_REF) - continue; - - if (node->constraint) - { - context = re_string_context_at (&mctx->input, cur_str_idx, - mctx->eflags); - if (NOT_SATISFY_NEXT_CONSTRAINT (node->constraint, context)) - continue; - } - - /* `node' is a backreference. - Check the substring which the substring matched. */ - bkc_idx = mctx->nbkref_ents; - err = get_subexp (mctx, node_idx, cur_str_idx); - if (BE (err != REG_NOERROR, 0)) - goto free_return; - - /* And add the epsilon closures (which is `new_dest_nodes') of - the backreference to appropriate state_log. */ -#ifdef DEBUG - assert (dfa->nexts[node_idx] != -1); -#endif - for (; bkc_idx < mctx->nbkref_ents; ++bkc_idx) - { - int subexp_len; - re_dfastate_t *dest_state; - struct re_backref_cache_entry *bkref_ent; - bkref_ent = mctx->bkref_ents + bkc_idx; - if (bkref_ent->node != node_idx || bkref_ent->str_idx != cur_str_idx) - continue; - subexp_len = bkref_ent->subexp_to - bkref_ent->subexp_from; - new_dest_nodes = (subexp_len == 0 - ? dfa->eclosures + dfa->edests[node_idx].elems[0] - : dfa->eclosures + dfa->nexts[node_idx]); - dest_str_idx = (cur_str_idx + bkref_ent->subexp_to - - bkref_ent->subexp_from); - context = re_string_context_at (&mctx->input, dest_str_idx - 1, - mctx->eflags); - dest_state = mctx->state_log[dest_str_idx]; - prev_nelem = ((mctx->state_log[cur_str_idx] == NULL) ? 0 - : mctx->state_log[cur_str_idx]->nodes.nelem); - /* Add `new_dest_node' to state_log. */ - if (dest_state == NULL) - { - mctx->state_log[dest_str_idx] - = re_acquire_state_context (&err, dfa, new_dest_nodes, - context); - if (BE (mctx->state_log[dest_str_idx] == NULL - && err != REG_NOERROR, 0)) - goto free_return; - } - else - { - re_node_set dest_nodes; - err = re_node_set_init_union (&dest_nodes, - dest_state->entrance_nodes, - new_dest_nodes); - if (BE (err != REG_NOERROR, 0)) - { - re_node_set_free (&dest_nodes); - goto free_return; - } - mctx->state_log[dest_str_idx] - = re_acquire_state_context (&err, dfa, &dest_nodes, context); - re_node_set_free (&dest_nodes); - if (BE (mctx->state_log[dest_str_idx] == NULL - && err != REG_NOERROR, 0)) - goto free_return; - } - /* We need to check recursively if the backreference can epsilon - transit. */ - if (subexp_len == 0 - && mctx->state_log[cur_str_idx]->nodes.nelem > prev_nelem) - { - err = check_subexp_matching_top (mctx, new_dest_nodes, - cur_str_idx); - if (BE (err != REG_NOERROR, 0)) - goto free_return; - err = transit_state_bkref (mctx, new_dest_nodes); - if (BE (err != REG_NOERROR, 0)) - goto free_return; - } - } - } - err = REG_NOERROR; - free_return: - return err; -} - -/* Enumerate all the candidates which the backreference BKREF_NODE can match - at BKREF_STR_IDX, and register them by match_ctx_add_entry(). - Note that we might collect inappropriate candidates here. - However, the cost of checking them strictly here is too high, then we - delay these checking for prune_impossible_nodes(). */ - -static reg_errcode_t -internal_function -get_subexp (re_match_context_t *mctx, int bkref_node, int bkref_str_idx) -{ - const re_dfa_t *const dfa = mctx->dfa; - int subexp_num, sub_top_idx; - const char *buf = (const char *) re_string_get_buffer (&mctx->input); - /* Return if we have already checked BKREF_NODE at BKREF_STR_IDX. */ - int cache_idx = search_cur_bkref_entry (mctx, bkref_str_idx); - if (cache_idx != -1) - { - const struct re_backref_cache_entry *entry - = mctx->bkref_ents + cache_idx; - do - if (entry->node == bkref_node) - return REG_NOERROR; /* We already checked it. */ - while (entry++->more); - } - - subexp_num = dfa->nodes[bkref_node].opr.idx; - - /* For each sub expression */ - for (sub_top_idx = 0; sub_top_idx < mctx->nsub_tops; ++sub_top_idx) - { - reg_errcode_t err; - re_sub_match_top_t *sub_top = mctx->sub_tops[sub_top_idx]; - re_sub_match_last_t *sub_last; - int sub_last_idx, sl_str, bkref_str_off; - - if (dfa->nodes[sub_top->node].opr.idx != subexp_num) - continue; /* It isn't related. */ - - sl_str = sub_top->str_idx; - bkref_str_off = bkref_str_idx; - /* At first, check the last node of sub expressions we already - evaluated. */ - for (sub_last_idx = 0; sub_last_idx < sub_top->nlasts; ++sub_last_idx) - { - int sl_str_diff; - sub_last = sub_top->lasts[sub_last_idx]; - sl_str_diff = sub_last->str_idx - sl_str; - /* The matched string by the sub expression match with the substring - at the back reference? */ - if (sl_str_diff > 0) - { - if (BE (bkref_str_off + sl_str_diff > mctx->input.valid_len, 0)) - { - /* Not enough chars for a successful match. */ - if (bkref_str_off + sl_str_diff > mctx->input.len) - break; - - err = clean_state_log_if_needed (mctx, - bkref_str_off - + sl_str_diff); - if (BE (err != REG_NOERROR, 0)) - return err; - buf = (const char *) re_string_get_buffer (&mctx->input); - } - if (memcmp (buf + bkref_str_off, buf + sl_str, sl_str_diff) != 0) - /* We don't need to search this sub expression any more. */ - break; - } - bkref_str_off += sl_str_diff; - sl_str += sl_str_diff; - err = get_subexp_sub (mctx, sub_top, sub_last, bkref_node, - bkref_str_idx); - - /* Reload buf, since the preceding call might have reallocated - the buffer. */ - buf = (const char *) re_string_get_buffer (&mctx->input); - - if (err == REG_NOMATCH) - continue; - if (BE (err != REG_NOERROR, 0)) - return err; - } - - if (sub_last_idx < sub_top->nlasts) - continue; - if (sub_last_idx > 0) - ++sl_str; - /* Then, search for the other last nodes of the sub expression. */ - for (; sl_str <= bkref_str_idx; ++sl_str) - { - int cls_node, sl_str_off; - const re_node_set *nodes; - sl_str_off = sl_str - sub_top->str_idx; - /* The matched string by the sub expression match with the substring - at the back reference? */ - if (sl_str_off > 0) - { - if (BE (bkref_str_off >= mctx->input.valid_len, 0)) - { - /* If we are at the end of the input, we cannot match. */ - if (bkref_str_off >= mctx->input.len) - break; - - err = extend_buffers (mctx); - if (BE (err != REG_NOERROR, 0)) - return err; - - buf = (const char *) re_string_get_buffer (&mctx->input); - } - if (buf [bkref_str_off++] != buf[sl_str - 1]) - break; /* We don't need to search this sub expression - any more. */ - } - if (mctx->state_log[sl_str] == NULL) - continue; - /* Does this state have a ')' of the sub expression? */ - nodes = &mctx->state_log[sl_str]->nodes; - cls_node = find_subexp_node (dfa, nodes, subexp_num, - OP_CLOSE_SUBEXP); - if (cls_node == -1) - continue; /* No. */ - if (sub_top->path == NULL) - { - sub_top->path = calloc (sizeof (state_array_t), - sl_str - sub_top->str_idx + 1); - if (sub_top->path == NULL) - return REG_ESPACE; - } - /* Can the OP_OPEN_SUBEXP node arrive the OP_CLOSE_SUBEXP node - in the current context? */ - err = check_arrival (mctx, sub_top->path, sub_top->node, - sub_top->str_idx, cls_node, sl_str, - OP_CLOSE_SUBEXP); - if (err == REG_NOMATCH) - continue; - if (BE (err != REG_NOERROR, 0)) - return err; - sub_last = match_ctx_add_sublast (sub_top, cls_node, sl_str); - if (BE (sub_last == NULL, 0)) - return REG_ESPACE; - err = get_subexp_sub (mctx, sub_top, sub_last, bkref_node, - bkref_str_idx); - if (err == REG_NOMATCH) - continue; - } - } - return REG_NOERROR; -} - -/* Helper functions for get_subexp(). */ - -/* Check SUB_LAST can arrive to the back reference BKREF_NODE at BKREF_STR. - If it can arrive, register the sub expression expressed with SUB_TOP - and SUB_LAST. */ - -static reg_errcode_t -internal_function -get_subexp_sub (re_match_context_t *mctx, const re_sub_match_top_t *sub_top, - re_sub_match_last_t *sub_last, int bkref_node, int bkref_str) -{ - reg_errcode_t err; - int to_idx; - /* Can the subexpression arrive the back reference? */ - err = check_arrival (mctx, &sub_last->path, sub_last->node, - sub_last->str_idx, bkref_node, bkref_str, - OP_OPEN_SUBEXP); - if (err != REG_NOERROR) - return err; - err = match_ctx_add_entry (mctx, bkref_node, bkref_str, sub_top->str_idx, - sub_last->str_idx); - if (BE (err != REG_NOERROR, 0)) - return err; - to_idx = bkref_str + sub_last->str_idx - sub_top->str_idx; - return clean_state_log_if_needed (mctx, to_idx); -} - -/* Find the first node which is '(' or ')' and whose index is SUBEXP_IDX. - Search '(' if FL_OPEN, or search ')' otherwise. - TODO: This function isn't efficient... - Because there might be more than one nodes whose types are - OP_OPEN_SUBEXP and whose index is SUBEXP_IDX, we must check all - nodes. - E.g. RE: (a){2} */ - -static int -internal_function -find_subexp_node (const re_dfa_t *dfa, const re_node_set *nodes, - int subexp_idx, int type) -{ - int cls_idx; - for (cls_idx = 0; cls_idx < nodes->nelem; ++cls_idx) - { - int cls_node = nodes->elems[cls_idx]; - const re_token_t *node = dfa->nodes + cls_node; - if (node->type == type - && node->opr.idx == subexp_idx) - return cls_node; - } - return -1; -} - -/* Check whether the node TOP_NODE at TOP_STR can arrive to the node - LAST_NODE at LAST_STR. We record the path onto PATH since it will be - heavily reused. - Return REG_NOERROR if it can arrive, or REG_NOMATCH otherwise. */ - -static reg_errcode_t -internal_function -check_arrival (re_match_context_t *mctx, state_array_t *path, int top_node, - int top_str, int last_node, int last_str, int type) -{ - const re_dfa_t *const dfa = mctx->dfa; - reg_errcode_t err = REG_NOERROR; - int subexp_num, backup_cur_idx, str_idx, null_cnt; - re_dfastate_t *cur_state = NULL; - re_node_set *cur_nodes, next_nodes; - re_dfastate_t **backup_state_log; - unsigned int context; - - subexp_num = dfa->nodes[top_node].opr.idx; - /* Extend the buffer if we need. */ - if (BE (path->alloc < last_str + mctx->max_mb_elem_len + 1, 0)) - { - re_dfastate_t **new_array; - int old_alloc = path->alloc; - path->alloc += last_str + mctx->max_mb_elem_len + 1; - new_array = re_realloc (path->array, re_dfastate_t *, path->alloc); - if (BE (new_array == NULL, 0)) - { - path->alloc = old_alloc; - return REG_ESPACE; - } - path->array = new_array; - memset (new_array + old_alloc, '\0', - sizeof (re_dfastate_t *) * (path->alloc - old_alloc)); - } - - str_idx = path->next_idx ? path->next_idx : top_str; - - /* Temporary modify MCTX. */ - backup_state_log = mctx->state_log; - backup_cur_idx = mctx->input.cur_idx; - mctx->state_log = path->array; - mctx->input.cur_idx = str_idx; - - /* Setup initial node set. */ - context = re_string_context_at (&mctx->input, str_idx - 1, mctx->eflags); - if (str_idx == top_str) - { - err = re_node_set_init_1 (&next_nodes, top_node); - if (BE (err != REG_NOERROR, 0)) - return err; - err = check_arrival_expand_ecl (dfa, &next_nodes, subexp_num, type); - if (BE (err != REG_NOERROR, 0)) - { - re_node_set_free (&next_nodes); - return err; - } - } - else - { - cur_state = mctx->state_log[str_idx]; - if (cur_state && cur_state->has_backref) - { - err = re_node_set_init_copy (&next_nodes, &cur_state->nodes); - if (BE (err != REG_NOERROR, 0)) - return err; - } - else - re_node_set_init_empty (&next_nodes); - } - if (str_idx == top_str || (cur_state && cur_state->has_backref)) - { - if (next_nodes.nelem) - { - err = expand_bkref_cache (mctx, &next_nodes, str_idx, - subexp_num, type); - if (BE (err != REG_NOERROR, 0)) - { - re_node_set_free (&next_nodes); - return err; - } - } - cur_state = re_acquire_state_context (&err, dfa, &next_nodes, context); - if (BE (cur_state == NULL && err != REG_NOERROR, 0)) - { - re_node_set_free (&next_nodes); - return err; - } - mctx->state_log[str_idx] = cur_state; - } - - for (null_cnt = 0; str_idx < last_str && null_cnt <= mctx->max_mb_elem_len;) - { - re_node_set_empty (&next_nodes); - if (mctx->state_log[str_idx + 1]) - { - err = re_node_set_merge (&next_nodes, - &mctx->state_log[str_idx + 1]->nodes); - if (BE (err != REG_NOERROR, 0)) - { - re_node_set_free (&next_nodes); - return err; - } - } - if (cur_state) - { - err = check_arrival_add_next_nodes (mctx, str_idx, - &cur_state->non_eps_nodes, - &next_nodes); - if (BE (err != REG_NOERROR, 0)) - { - re_node_set_free (&next_nodes); - return err; - } - } - ++str_idx; - if (next_nodes.nelem) - { - err = check_arrival_expand_ecl (dfa, &next_nodes, subexp_num, type); - if (BE (err != REG_NOERROR, 0)) - { - re_node_set_free (&next_nodes); - return err; - } - err = expand_bkref_cache (mctx, &next_nodes, str_idx, - subexp_num, type); - if (BE (err != REG_NOERROR, 0)) - { - re_node_set_free (&next_nodes); - return err; - } - } - context = re_string_context_at (&mctx->input, str_idx - 1, mctx->eflags); - cur_state = re_acquire_state_context (&err, dfa, &next_nodes, context); - if (BE (cur_state == NULL && err != REG_NOERROR, 0)) - { - re_node_set_free (&next_nodes); - return err; - } - mctx->state_log[str_idx] = cur_state; - null_cnt = cur_state == NULL ? null_cnt + 1 : 0; - } - re_node_set_free (&next_nodes); - cur_nodes = (mctx->state_log[last_str] == NULL ? NULL - : &mctx->state_log[last_str]->nodes); - path->next_idx = str_idx; - - /* Fix MCTX. */ - mctx->state_log = backup_state_log; - mctx->input.cur_idx = backup_cur_idx; - - /* Then check the current node set has the node LAST_NODE. */ - if (cur_nodes != NULL && re_node_set_contains (cur_nodes, last_node)) - return REG_NOERROR; - - return REG_NOMATCH; -} - -/* Helper functions for check_arrival. */ - -/* Calculate the destination nodes of CUR_NODES at STR_IDX, and append them - to NEXT_NODES. - TODO: This function is similar to the functions transit_state*(), - however this function has many additional works. - Can't we unify them? */ - -static reg_errcode_t -internal_function -check_arrival_add_next_nodes (re_match_context_t *mctx, int str_idx, - re_node_set *cur_nodes, re_node_set *next_nodes) -{ - const re_dfa_t *const dfa = mctx->dfa; - int result; - int cur_idx; -#ifdef RE_ENABLE_I18N - reg_errcode_t err = REG_NOERROR; -#endif - re_node_set union_set; - re_node_set_init_empty (&union_set); - for (cur_idx = 0; cur_idx < cur_nodes->nelem; ++cur_idx) - { - int naccepted = 0; - int cur_node = cur_nodes->elems[cur_idx]; -#ifdef DEBUG - re_token_type_t type = dfa->nodes[cur_node].type; - assert (!IS_EPSILON_NODE (type)); -#endif -#ifdef RE_ENABLE_I18N - /* If the node may accept `multi byte'. */ - if (dfa->nodes[cur_node].accept_mb) - { - naccepted = check_node_accept_bytes (dfa, cur_node, &mctx->input, - str_idx); - if (naccepted > 1) - { - re_dfastate_t *dest_state; - int next_node = dfa->nexts[cur_node]; - int next_idx = str_idx + naccepted; - dest_state = mctx->state_log[next_idx]; - re_node_set_empty (&union_set); - if (dest_state) - { - err = re_node_set_merge (&union_set, &dest_state->nodes); - if (BE (err != REG_NOERROR, 0)) - { - re_node_set_free (&union_set); - return err; - } - } - result = re_node_set_insert (&union_set, next_node); - if (BE (result < 0, 0)) - { - re_node_set_free (&union_set); - return REG_ESPACE; - } - mctx->state_log[next_idx] = re_acquire_state (&err, dfa, - &union_set); - if (BE (mctx->state_log[next_idx] == NULL - && err != REG_NOERROR, 0)) - { - re_node_set_free (&union_set); - return err; - } - } - } -#endif /* RE_ENABLE_I18N */ - if (naccepted - || check_node_accept (mctx, dfa->nodes + cur_node, str_idx)) - { - result = re_node_set_insert (next_nodes, dfa->nexts[cur_node]); - if (BE (result < 0, 0)) - { - re_node_set_free (&union_set); - return REG_ESPACE; - } - } - } - re_node_set_free (&union_set); - return REG_NOERROR; -} - -/* For all the nodes in CUR_NODES, add the epsilon closures of them to - CUR_NODES, however exclude the nodes which are: - - inside the sub expression whose number is EX_SUBEXP, if FL_OPEN. - - out of the sub expression whose number is EX_SUBEXP, if !FL_OPEN. -*/ - -static reg_errcode_t -internal_function -check_arrival_expand_ecl (const re_dfa_t *dfa, re_node_set *cur_nodes, - int ex_subexp, int type) -{ - reg_errcode_t err; - int idx, outside_node; - re_node_set new_nodes; -#ifdef DEBUG - assert (cur_nodes->nelem); -#endif - err = re_node_set_alloc (&new_nodes, cur_nodes->nelem); - if (BE (err != REG_NOERROR, 0)) - return err; - /* Create a new node set NEW_NODES with the nodes which are epsilon - closures of the node in CUR_NODES. */ - - for (idx = 0; idx < cur_nodes->nelem; ++idx) - { - int cur_node = cur_nodes->elems[idx]; - const re_node_set *eclosure = dfa->eclosures + cur_node; - outside_node = find_subexp_node (dfa, eclosure, ex_subexp, type); - if (outside_node == -1) - { - /* There are no problematic nodes, just merge them. */ - err = re_node_set_merge (&new_nodes, eclosure); - if (BE (err != REG_NOERROR, 0)) - { - re_node_set_free (&new_nodes); - return err; - } - } - else - { - /* There are problematic nodes, re-calculate incrementally. */ - err = check_arrival_expand_ecl_sub (dfa, &new_nodes, cur_node, - ex_subexp, type); - if (BE (err != REG_NOERROR, 0)) - { - re_node_set_free (&new_nodes); - return err; - } - } - } - re_node_set_free (cur_nodes); - *cur_nodes = new_nodes; - return REG_NOERROR; -} - -/* Helper function for check_arrival_expand_ecl. - Check incrementally the epsilon closure of TARGET, and if it isn't - problematic append it to DST_NODES. */ - -static reg_errcode_t -internal_function -check_arrival_expand_ecl_sub (const re_dfa_t *dfa, re_node_set *dst_nodes, - int target, int ex_subexp, int type) -{ - int cur_node; - for (cur_node = target; !re_node_set_contains (dst_nodes, cur_node);) - { - int err; - - if (dfa->nodes[cur_node].type == type - && dfa->nodes[cur_node].opr.idx == ex_subexp) - { - if (type == OP_CLOSE_SUBEXP) - { - err = re_node_set_insert (dst_nodes, cur_node); - if (BE (err == -1, 0)) - return REG_ESPACE; - } - break; - } - err = re_node_set_insert (dst_nodes, cur_node); - if (BE (err == -1, 0)) - return REG_ESPACE; - if (dfa->edests[cur_node].nelem == 0) - break; - if (dfa->edests[cur_node].nelem == 2) - { - err = check_arrival_expand_ecl_sub (dfa, dst_nodes, - dfa->edests[cur_node].elems[1], - ex_subexp, type); - if (BE (err != REG_NOERROR, 0)) - return err; - } - cur_node = dfa->edests[cur_node].elems[0]; - } - return REG_NOERROR; -} - - -/* For all the back references in the current state, calculate the - destination of the back references by the appropriate entry - in MCTX->BKREF_ENTS. */ - -static reg_errcode_t -internal_function -expand_bkref_cache (re_match_context_t *mctx, re_node_set *cur_nodes, - int cur_str, int subexp_num, int type) -{ - const re_dfa_t *const dfa = mctx->dfa; - reg_errcode_t err; - int cache_idx_start = search_cur_bkref_entry (mctx, cur_str); - struct re_backref_cache_entry *ent; - - if (cache_idx_start == -1) - return REG_NOERROR; - - restart: - ent = mctx->bkref_ents + cache_idx_start; - do - { - int to_idx, next_node; - - /* Is this entry ENT is appropriate? */ - if (!re_node_set_contains (cur_nodes, ent->node)) - continue; /* No. */ - - to_idx = cur_str + ent->subexp_to - ent->subexp_from; - /* Calculate the destination of the back reference, and append it - to MCTX->STATE_LOG. */ - if (to_idx == cur_str) - { - /* The backreference did epsilon transit, we must re-check all the - node in the current state. */ - re_node_set new_dests; - reg_errcode_t err2, err3; - next_node = dfa->edests[ent->node].elems[0]; - if (re_node_set_contains (cur_nodes, next_node)) - continue; - err = re_node_set_init_1 (&new_dests, next_node); - err2 = check_arrival_expand_ecl (dfa, &new_dests, subexp_num, type); - err3 = re_node_set_merge (cur_nodes, &new_dests); - re_node_set_free (&new_dests); - if (BE (err != REG_NOERROR || err2 != REG_NOERROR - || err3 != REG_NOERROR, 0)) - { - err = (err != REG_NOERROR ? err - : (err2 != REG_NOERROR ? err2 : err3)); - return err; - } - /* TODO: It is still inefficient... */ - goto restart; - } - else - { - re_node_set union_set; - next_node = dfa->nexts[ent->node]; - if (mctx->state_log[to_idx]) - { - int ret; - if (re_node_set_contains (&mctx->state_log[to_idx]->nodes, - next_node)) - continue; - err = re_node_set_init_copy (&union_set, - &mctx->state_log[to_idx]->nodes); - ret = re_node_set_insert (&union_set, next_node); - if (BE (err != REG_NOERROR || ret < 0, 0)) - { - re_node_set_free (&union_set); - err = err != REG_NOERROR ? err : REG_ESPACE; - return err; - } - } - else - { - err = re_node_set_init_1 (&union_set, next_node); - if (BE (err != REG_NOERROR, 0)) - return err; - } - mctx->state_log[to_idx] = re_acquire_state (&err, dfa, &union_set); - re_node_set_free (&union_set); - if (BE (mctx->state_log[to_idx] == NULL - && err != REG_NOERROR, 0)) - return err; - } - } - while (ent++->more); - return REG_NOERROR; -} - -/* Build transition table for the state. - Return 1 if succeeded, otherwise return NULL. */ - -static int -internal_function -build_trtable (const re_dfa_t *dfa, re_dfastate_t *state) -{ - reg_errcode_t err; - int i, j, ch, need_word_trtable = 0; - bitset_word_t elem, mask; - bool dests_node_malloced = false; - bool dest_states_malloced = false; - int ndests; /* Number of the destination states from `state'. */ - re_dfastate_t **trtable; - re_dfastate_t **dest_states = NULL, **dest_states_word, **dest_states_nl; - re_node_set follows, *dests_node; - bitset_t *dests_ch; - bitset_t acceptable; - - struct dests_alloc - { - re_node_set dests_node[SBC_MAX]; - bitset_t dests_ch[SBC_MAX]; - } *dests_alloc; - - /* We build DFA states which corresponds to the destination nodes - from `state'. `dests_node[i]' represents the nodes which i-th - destination state contains, and `dests_ch[i]' represents the - characters which i-th destination state accepts. */ -#ifdef HAVE_ALLOCA - if (__libc_use_alloca (sizeof (struct dests_alloc))) - dests_alloc = (struct dests_alloc *) alloca (sizeof (struct dests_alloc)); - else -#endif - { - dests_alloc = re_malloc (struct dests_alloc, 1); - if (BE (dests_alloc == NULL, 0)) - return 0; - dests_node_malloced = true; - } - dests_node = dests_alloc->dests_node; - dests_ch = dests_alloc->dests_ch; - - /* Initialize transiton table. */ - state->word_trtable = state->trtable = NULL; - - /* At first, group all nodes belonging to `state' into several - destinations. */ - ndests = group_nodes_into_DFAstates (dfa, state, dests_node, dests_ch); - if (BE (ndests <= 0, 0)) - { - if (dests_node_malloced) - free (dests_alloc); - /* Return 0 in case of an error, 1 otherwise. */ - if (ndests == 0) - { - state->trtable = (re_dfastate_t **) - calloc (sizeof (re_dfastate_t *), SBC_MAX); - return 1; - } - return 0; - } - - err = re_node_set_alloc (&follows, ndests + 1); - if (BE (err != REG_NOERROR, 0)) - goto out_free; - - /* Avoid arithmetic overflow in size calculation. */ - if (BE ((((SIZE_MAX - (sizeof (re_node_set) + sizeof (bitset_t)) * SBC_MAX) - / (3 * sizeof (re_dfastate_t *))) - < (size_t)ndests), - 0)) - goto out_free; - -#ifdef HAVE_ALLOCA - if (__libc_use_alloca ((sizeof (re_node_set) + sizeof (bitset_t)) * SBC_MAX - + ndests * 3 * sizeof (re_dfastate_t *))) - dest_states = (re_dfastate_t **) - alloca (ndests * 3 * sizeof (re_dfastate_t *)); - else -#endif - { - dest_states = (re_dfastate_t **) - malloc (ndests * 3 * sizeof (re_dfastate_t *)); - if (BE (dest_states == NULL, 0)) - { -out_free: - if (dest_states_malloced) - free (dest_states); - re_node_set_free (&follows); - for (i = 0; i < ndests; ++i) - re_node_set_free (dests_node + i); - if (dests_node_malloced) - free (dests_alloc); - return 0; - } - dest_states_malloced = true; - } - dest_states_word = dest_states + ndests; - dest_states_nl = dest_states_word + ndests; - bitset_empty (acceptable); - - /* Then build the states for all destinations. */ - for (i = 0; i < ndests; ++i) - { - int next_node; - re_node_set_empty (&follows); - /* Merge the follows of this destination states. */ - for (j = 0; j < dests_node[i].nelem; ++j) - { - next_node = dfa->nexts[dests_node[i].elems[j]]; - if (next_node != -1) - { - err = re_node_set_merge (&follows, dfa->eclosures + next_node); - if (BE (err != REG_NOERROR, 0)) - goto out_free; - } - } - dest_states[i] = re_acquire_state_context (&err, dfa, &follows, 0); - if (BE (dest_states[i] == NULL && err != REG_NOERROR, 0)) - goto out_free; - /* If the new state has context constraint, - build appropriate states for these contexts. */ - if (dest_states[i]->has_constraint) - { - dest_states_word[i] = re_acquire_state_context (&err, dfa, &follows, - CONTEXT_WORD); - if (BE (dest_states_word[i] == NULL && err != REG_NOERROR, 0)) - goto out_free; - - if (dest_states[i] != dest_states_word[i] && dfa->mb_cur_max > 1) - need_word_trtable = 1; - - dest_states_nl[i] = re_acquire_state_context (&err, dfa, &follows, - CONTEXT_NEWLINE); - if (BE (dest_states_nl[i] == NULL && err != REG_NOERROR, 0)) - goto out_free; - } - else - { - dest_states_word[i] = dest_states[i]; - dest_states_nl[i] = dest_states[i]; - } - bitset_merge (acceptable, dests_ch[i]); - } - - if (!BE (need_word_trtable, 0)) - { - /* We don't care about whether the following character is a word - character, or we are in a single-byte character set so we can - discern by looking at the character code: allocate a - 256-entry transition table. */ - trtable = state->trtable = - (re_dfastate_t **) calloc (sizeof (re_dfastate_t *), SBC_MAX); - if (BE (trtable == NULL, 0)) - goto out_free; - - /* For all characters ch...: */ - for (i = 0; i < BITSET_WORDS; ++i) - for (ch = i * BITSET_WORD_BITS, elem = acceptable[i], mask = 1; - elem; - mask <<= 1, elem >>= 1, ++ch) - if (BE (elem & 1, 0)) - { - /* There must be exactly one destination which accepts - character ch. See group_nodes_into_DFAstates. */ - for (j = 0; (dests_ch[j][i] & mask) == 0; ++j) - ; - - /* j-th destination accepts the word character ch. */ - if (dfa->word_char[i] & mask) - trtable[ch] = dest_states_word[j]; - else - trtable[ch] = dest_states[j]; - } - } - else - { - /* We care about whether the following character is a word - character, and we are in a multi-byte character set: discern - by looking at the character code: build two 256-entry - transition tables, one starting at trtable[0] and one - starting at trtable[SBC_MAX]. */ - trtable = state->word_trtable = - (re_dfastate_t **) calloc (sizeof (re_dfastate_t *), 2 * SBC_MAX); - if (BE (trtable == NULL, 0)) - goto out_free; - - /* For all characters ch...: */ - for (i = 0; i < BITSET_WORDS; ++i) - for (ch = i * BITSET_WORD_BITS, elem = acceptable[i], mask = 1; - elem; - mask <<= 1, elem >>= 1, ++ch) - if (BE (elem & 1, 0)) - { - /* There must be exactly one destination which accepts - character ch. See group_nodes_into_DFAstates. */ - for (j = 0; (dests_ch[j][i] & mask) == 0; ++j) - ; - - /* j-th destination accepts the word character ch. */ - trtable[ch] = dest_states[j]; - trtable[ch + SBC_MAX] = dest_states_word[j]; - } - } - - /* new line */ - if (bitset_contain (acceptable, NEWLINE_CHAR)) - { - /* The current state accepts newline character. */ - for (j = 0; j < ndests; ++j) - if (bitset_contain (dests_ch[j], NEWLINE_CHAR)) - { - /* k-th destination accepts newline character. */ - trtable[NEWLINE_CHAR] = dest_states_nl[j]; - if (need_word_trtable) - trtable[NEWLINE_CHAR + SBC_MAX] = dest_states_nl[j]; - /* There must be only one destination which accepts - newline. See group_nodes_into_DFAstates. */ - break; - } - } - - if (dest_states_malloced) - free (dest_states); - - re_node_set_free (&follows); - for (i = 0; i < ndests; ++i) - re_node_set_free (dests_node + i); - - if (dests_node_malloced) - free (dests_alloc); - - return 1; -} - -/* Group all nodes belonging to STATE into several destinations. - Then for all destinations, set the nodes belonging to the destination - to DESTS_NODE[i] and set the characters accepted by the destination - to DEST_CH[i]. This function return the number of destinations. */ - -static int -internal_function -group_nodes_into_DFAstates (const re_dfa_t *dfa, const re_dfastate_t *state, - re_node_set *dests_node, bitset_t *dests_ch) -{ - reg_errcode_t err; - int result; - int i, j, k; - int ndests; /* Number of the destinations from `state'. */ - bitset_t accepts; /* Characters a node can accept. */ - const re_node_set *cur_nodes = &state->nodes; - bitset_empty (accepts); - ndests = 0; - - /* For all the nodes belonging to `state', */ - for (i = 0; i < cur_nodes->nelem; ++i) - { - re_token_t *node = &dfa->nodes[cur_nodes->elems[i]]; - re_token_type_t type = node->type; - unsigned int constraint = node->constraint; - - /* Enumerate all single byte character this node can accept. */ - if (type == CHARACTER) - bitset_set (accepts, node->opr.c); - else if (type == SIMPLE_BRACKET) - { - bitset_merge (accepts, node->opr.sbcset); - } - else if (type == OP_PERIOD) - { -#ifdef RE_ENABLE_I18N - if (dfa->mb_cur_max > 1) - bitset_merge (accepts, dfa->sb_char); - else -#endif - bitset_set_all (accepts); - if (!(dfa->syntax & RE_DOT_NEWLINE)) - bitset_clear (accepts, '\n'); - if (dfa->syntax & RE_DOT_NOT_NULL) - bitset_clear (accepts, '\0'); - } -#ifdef RE_ENABLE_I18N - else if (type == OP_UTF8_PERIOD) - { - memset (accepts, '\xff', sizeof (bitset_t) / 2); - if (!(dfa->syntax & RE_DOT_NEWLINE)) - bitset_clear (accepts, '\n'); - if (dfa->syntax & RE_DOT_NOT_NULL) - bitset_clear (accepts, '\0'); - } -#endif - else - continue; - - /* Check the `accepts' and sift the characters which are not - match it the context. */ - if (constraint) - { - if (constraint & NEXT_NEWLINE_CONSTRAINT) - { - bool accepts_newline = bitset_contain (accepts, NEWLINE_CHAR); - bitset_empty (accepts); - if (accepts_newline) - bitset_set (accepts, NEWLINE_CHAR); - else - continue; - } - if (constraint & NEXT_ENDBUF_CONSTRAINT) - { - bitset_empty (accepts); - continue; - } - - if (constraint & NEXT_WORD_CONSTRAINT) - { - bitset_word_t any_set = 0; - if (type == CHARACTER && !node->word_char) - { - bitset_empty (accepts); - continue; - } -#ifdef RE_ENABLE_I18N - if (dfa->mb_cur_max > 1) - for (j = 0; j < BITSET_WORDS; ++j) - any_set |= (accepts[j] &= (dfa->word_char[j] | ~dfa->sb_char[j])); - else -#endif - for (j = 0; j < BITSET_WORDS; ++j) - any_set |= (accepts[j] &= dfa->word_char[j]); - if (!any_set) - continue; - } - if (constraint & NEXT_NOTWORD_CONSTRAINT) - { - bitset_word_t any_set = 0; - if (type == CHARACTER && node->word_char) - { - bitset_empty (accepts); - continue; - } -#ifdef RE_ENABLE_I18N - if (dfa->mb_cur_max > 1) - for (j = 0; j < BITSET_WORDS; ++j) - any_set |= (accepts[j] &= ~(dfa->word_char[j] & dfa->sb_char[j])); - else -#endif - for (j = 0; j < BITSET_WORDS; ++j) - any_set |= (accepts[j] &= ~dfa->word_char[j]); - if (!any_set) - continue; - } - } - - /* Then divide `accepts' into DFA states, or create a new - state. Above, we make sure that accepts is not empty. */ - for (j = 0; j < ndests; ++j) - { - bitset_t intersec; /* Intersection sets, see below. */ - bitset_t remains; - /* Flags, see below. */ - bitset_word_t has_intersec, not_subset, not_consumed; - - /* Optimization, skip if this state doesn't accept the character. */ - if (type == CHARACTER && !bitset_contain (dests_ch[j], node->opr.c)) - continue; - - /* Enumerate the intersection set of this state and `accepts'. */ - has_intersec = 0; - for (k = 0; k < BITSET_WORDS; ++k) - has_intersec |= intersec[k] = accepts[k] & dests_ch[j][k]; - /* And skip if the intersection set is empty. */ - if (!has_intersec) - continue; - - /* Then check if this state is a subset of `accepts'. */ - not_subset = not_consumed = 0; - for (k = 0; k < BITSET_WORDS; ++k) - { - not_subset |= remains[k] = ~accepts[k] & dests_ch[j][k]; - not_consumed |= accepts[k] = accepts[k] & ~dests_ch[j][k]; - } - - /* If this state isn't a subset of `accepts', create a - new group state, which has the `remains'. */ - if (not_subset) - { - bitset_copy (dests_ch[ndests], remains); - bitset_copy (dests_ch[j], intersec); - err = re_node_set_init_copy (dests_node + ndests, &dests_node[j]); - if (BE (err != REG_NOERROR, 0)) - goto error_return; - ++ndests; - } - - /* Put the position in the current group. */ - result = re_node_set_insert (&dests_node[j], cur_nodes->elems[i]); - if (BE (result < 0, 0)) - goto error_return; - - /* If all characters are consumed, go to next node. */ - if (!not_consumed) - break; - } - /* Some characters remain, create a new group. */ - if (j == ndests) - { - bitset_copy (dests_ch[ndests], accepts); - err = re_node_set_init_1 (dests_node + ndests, cur_nodes->elems[i]); - if (BE (err != REG_NOERROR, 0)) - goto error_return; - ++ndests; - bitset_empty (accepts); - } - } - return ndests; - error_return: - for (j = 0; j < ndests; ++j) - re_node_set_free (dests_node + j); - return -1; -} - -#ifdef RE_ENABLE_I18N -/* Check how many bytes the node `dfa->nodes[node_idx]' accepts. - Return the number of the bytes the node accepts. - STR_IDX is the current index of the input string. - - This function handles the nodes which can accept one character, or - one collating element like '.', '[a-z]', opposite to the other nodes - can only accept one byte. */ - -static int -internal_function -check_node_accept_bytes (const re_dfa_t *dfa, int node_idx, - const re_string_t *input, int str_idx) -{ - const re_token_t *node = dfa->nodes + node_idx; - int char_len, elem_len; - int i; - wint_t wc; - - if (BE (node->type == OP_UTF8_PERIOD, 0)) - { - unsigned char c = re_string_byte_at (input, str_idx), d; - if (BE (c < 0xc2, 1)) - return 0; - - if (str_idx + 2 > input->len) - return 0; - - d = re_string_byte_at (input, str_idx + 1); - if (c < 0xe0) - return (d < 0x80 || d > 0xbf) ? 0 : 2; - else if (c < 0xf0) - { - char_len = 3; - if (c == 0xe0 && d < 0xa0) - return 0; - } - else if (c < 0xf8) - { - char_len = 4; - if (c == 0xf0 && d < 0x90) - return 0; - } - else if (c < 0xfc) - { - char_len = 5; - if (c == 0xf8 && d < 0x88) - return 0; - } - else if (c < 0xfe) - { - char_len = 6; - if (c == 0xfc && d < 0x84) - return 0; - } - else - return 0; - - if (str_idx + char_len > input->len) - return 0; - - for (i = 1; i < char_len; ++i) - { - d = re_string_byte_at (input, str_idx + i); - if (d < 0x80 || d > 0xbf) - return 0; - } - return char_len; - } - - char_len = re_string_char_size_at (input, str_idx); - if (node->type == OP_PERIOD) - { - if (char_len <= 1) - return 0; - /* FIXME: I don't think this if is needed, as both '\n' - and '\0' are char_len == 1. */ - /* '.' accepts any one character except the following two cases. */ - if ((!(dfa->syntax & RE_DOT_NEWLINE) && - re_string_byte_at (input, str_idx) == '\n') || - ((dfa->syntax & RE_DOT_NOT_NULL) && - re_string_byte_at (input, str_idx) == '\0')) - return 0; - return char_len; - } - - elem_len = re_string_elem_size_at (input, str_idx); - wc = __btowc(*(input->mbs+str_idx)); - if (((elem_len <= 1 && char_len <= 1) || char_len == 0) && (wc != WEOF && wc < SBC_MAX)) - return 0; - - if (node->type == COMPLEX_BRACKET) - { - const re_charset_t *cset = node->opr.mbcset; -# ifdef _LIBC - const unsigned char *pin - = ((const unsigned char *) re_string_get_buffer (input) + str_idx); - int j; - uint32_t nrules; -# endif /* _LIBC */ - int match_len = 0; - wchar_t wc = ((cset->nranges || cset->nchar_classes || cset->nmbchars) - ? re_string_wchar_at (input, str_idx) : 0); - - /* match with multibyte character? */ - for (i = 0; i < cset->nmbchars; ++i) - if (wc == cset->mbchars[i]) - { - match_len = char_len; - goto check_node_accept_bytes_match; - } - /* match with character_class? */ - for (i = 0; i < cset->nchar_classes; ++i) - { - wctype_t wt = cset->char_classes[i]; - if (__iswctype (wc, wt)) - { - match_len = char_len; - goto check_node_accept_bytes_match; - } - } - -# ifdef _LIBC - nrules = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES); - if (nrules != 0) - { - unsigned int in_collseq = 0; - const int32_t *table, *indirect; - const unsigned char *weights, *extra; - const char *collseqwc; - /* This #include defines a local function! */ -# include - - /* match with collating_symbol? */ - if (cset->ncoll_syms) - extra = (const unsigned char *) - _NL_CURRENT (LC_COLLATE, _NL_COLLATE_SYMB_EXTRAMB); - for (i = 0; i < cset->ncoll_syms; ++i) - { - const unsigned char *coll_sym = extra + cset->coll_syms[i]; - /* Compare the length of input collating element and - the length of current collating element. */ - if (*coll_sym != elem_len) - continue; - /* Compare each bytes. */ - for (j = 0; j < *coll_sym; j++) - if (pin[j] != coll_sym[1 + j]) - break; - if (j == *coll_sym) - { - /* Match if every bytes is equal. */ - match_len = j; - goto check_node_accept_bytes_match; - } - } - - if (cset->nranges) - { - if (elem_len <= char_len) - { - collseqwc = _NL_CURRENT (LC_COLLATE, _NL_COLLATE_COLLSEQWC); - in_collseq = __collseq_table_lookup (collseqwc, wc); - } - else - in_collseq = find_collation_sequence_value (pin, elem_len); - } - /* match with range expression? */ - for (i = 0; i < cset->nranges; ++i) - if (cset->range_starts[i] <= in_collseq - && in_collseq <= cset->range_ends[i]) - { - match_len = elem_len; - goto check_node_accept_bytes_match; - } - - /* match with equivalence_class? */ - if (cset->nequiv_classes) - { - const unsigned char *cp = pin; - table = (const int32_t *) - _NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEMB); - weights = (const unsigned char *) - _NL_CURRENT (LC_COLLATE, _NL_COLLATE_WEIGHTMB); - extra = (const unsigned char *) - _NL_CURRENT (LC_COLLATE, _NL_COLLATE_EXTRAMB); - indirect = (const int32_t *) - _NL_CURRENT (LC_COLLATE, _NL_COLLATE_INDIRECTMB); - int32_t idx = findidx (&cp); - if (idx > 0) - for (i = 0; i < cset->nequiv_classes; ++i) - { - int32_t equiv_class_idx = cset->equiv_classes[i]; - size_t weight_len = weights[idx & 0xffffff]; - if (weight_len == weights[equiv_class_idx & 0xffffff] - && (idx >> 24) == (equiv_class_idx >> 24)) - { - int cnt = 0; - - idx &= 0xffffff; - equiv_class_idx &= 0xffffff; - - while (cnt <= weight_len - && (weights[equiv_class_idx + 1 + cnt] - == weights[idx + 1 + cnt])) - ++cnt; - if (cnt > weight_len) - { - match_len = elem_len; - goto check_node_accept_bytes_match; - } - } - } - } - } - else -# endif /* _LIBC */ - { - /* match with range expression? */ -#if __GNUC__ >= 2 - wchar_t cmp_buf[] = {L'\0', L'\0', wc, L'\0', L'\0', L'\0'}; -#else - wchar_t cmp_buf[] = {L'\0', L'\0', L'\0', L'\0', L'\0', L'\0'}; - cmp_buf[2] = wc; -#endif - for (i = 0; i < cset->nranges; ++i) - { - cmp_buf[0] = cset->range_starts[i]; - cmp_buf[4] = cset->range_ends[i]; - if (wcscoll (cmp_buf, cmp_buf + 2) <= 0 - && wcscoll (cmp_buf + 2, cmp_buf + 4) <= 0) - { - match_len = char_len; - goto check_node_accept_bytes_match; - } - } - } - check_node_accept_bytes_match: - if (!cset->non_match) - return match_len; - else - { - if (match_len > 0) - return 0; - else - return (elem_len > char_len) ? elem_len : char_len; - } - } - return 0; -} - -# ifdef _LIBC -static unsigned int -internal_function -find_collation_sequence_value (const unsigned char *mbs, size_t mbs_len) -{ - uint32_t nrules = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES); - if (nrules == 0) - { - if (mbs_len == 1) - { - /* No valid character. Match it as a single byte character. */ - const unsigned char *collseq = (const unsigned char *) - _NL_CURRENT (LC_COLLATE, _NL_COLLATE_COLLSEQMB); - return collseq[mbs[0]]; - } - return UINT_MAX; - } - else - { - int32_t idx; - const unsigned char *extra = (const unsigned char *) - _NL_CURRENT (LC_COLLATE, _NL_COLLATE_SYMB_EXTRAMB); - int32_t extrasize = (const unsigned char *) - _NL_CURRENT (LC_COLLATE, _NL_COLLATE_SYMB_EXTRAMB + 1) - extra; - - for (idx = 0; idx < extrasize;) - { - int mbs_cnt, found = 0; - int32_t elem_mbs_len; - /* Skip the name of collating element name. */ - idx = idx + extra[idx] + 1; - elem_mbs_len = extra[idx++]; - if (mbs_len == elem_mbs_len) - { - for (mbs_cnt = 0; mbs_cnt < elem_mbs_len; ++mbs_cnt) - if (extra[idx + mbs_cnt] != mbs[mbs_cnt]) - break; - if (mbs_cnt == elem_mbs_len) - /* Found the entry. */ - found = 1; - } - /* Skip the byte sequence of the collating element. */ - idx += elem_mbs_len; - /* Adjust for the alignment. */ - idx = (idx + 3) & ~3; - /* Skip the collation sequence value. */ - idx += sizeof (uint32_t); - /* Skip the wide char sequence of the collating element. */ - idx = idx + sizeof (uint32_t) * (extra[idx] + 1); - /* If we found the entry, return the sequence value. */ - if (found) - return *(uint32_t *) (extra + idx); - /* Skip the collation sequence value. */ - idx += sizeof (uint32_t); - } - return UINT_MAX; - } -} -# endif /* _LIBC */ -#endif /* RE_ENABLE_I18N */ - -/* Check whether the node accepts the byte which is IDX-th - byte of the INPUT. */ - -static int -internal_function -check_node_accept (const re_match_context_t *mctx, const re_token_t *node, - int idx) -{ - unsigned char ch; - ch = re_string_byte_at (&mctx->input, idx); - switch (node->type) - { - case CHARACTER: - if (node->opr.c != ch) - return 0; - break; - - case SIMPLE_BRACKET: - if (!bitset_contain (node->opr.sbcset, ch)) - return 0; - break; - -#ifdef RE_ENABLE_I18N - case OP_UTF8_PERIOD: - if (ch >= 0x80) - return 0; - /* FALLTHROUGH */ -#endif - case OP_PERIOD: - if ((ch == '\n' && !(mctx->dfa->syntax & RE_DOT_NEWLINE)) - || (ch == '\0' && (mctx->dfa->syntax & RE_DOT_NOT_NULL))) - return 0; - break; - - default: - return 0; - } - - if (node->constraint) - { - /* The node has constraints. Check whether the current context - satisfies the constraints. */ - unsigned int context = re_string_context_at (&mctx->input, idx, - mctx->eflags); - if (NOT_SATISFY_NEXT_CONSTRAINT (node->constraint, context)) - return 0; - } - - return 1; -} - -/* Extend the buffers, if the buffers have run out. */ - -static reg_errcode_t -internal_function -extend_buffers (re_match_context_t *mctx) -{ - reg_errcode_t ret; - re_string_t *pstr = &mctx->input; - - /* Avoid overflow. */ - if (BE (INT_MAX / 2 / sizeof (re_dfastate_t *) <= (size_t)pstr->bufs_len, 0)) - return REG_ESPACE; - - /* Double the lengthes of the buffers. */ - ret = re_string_realloc_buffers (pstr, pstr->bufs_len * 2); - if (BE (ret != REG_NOERROR, 0)) - return ret; - - if (mctx->state_log != NULL) - { - /* And double the length of state_log. */ - /* XXX We have no indication of the size of this buffer. If this - allocation fail we have no indication that the state_log array - does not have the right size. */ - re_dfastate_t **new_array = re_realloc (mctx->state_log, re_dfastate_t *, - pstr->bufs_len + 1); - if (BE (new_array == NULL, 0)) - return REG_ESPACE; - mctx->state_log = new_array; - } - - /* Then reconstruct the buffers. */ - if (pstr->icase) - { -#ifdef RE_ENABLE_I18N - if (pstr->mb_cur_max > 1) - { - ret = build_wcs_upper_buffer (pstr); - if (BE (ret != REG_NOERROR, 0)) - return ret; - } - else -#endif /* RE_ENABLE_I18N */ - build_upper_buffer (pstr); - } - else - { -#ifdef RE_ENABLE_I18N - if (pstr->mb_cur_max > 1) - build_wcs_buffer (pstr); - else -#endif /* RE_ENABLE_I18N */ - { - if (pstr->trans != NULL) - re_string_translate_buffer (pstr); - } - } - return REG_NOERROR; -} - - -/* Functions for matching context. */ - -/* Initialize MCTX. */ - -static reg_errcode_t -internal_function -match_ctx_init (re_match_context_t *mctx, int eflags, int n) -{ - mctx->eflags = eflags; - mctx->match_last = -1; - if (n > 0) - { - mctx->bkref_ents = re_malloc (struct re_backref_cache_entry, n); - mctx->sub_tops = re_malloc (re_sub_match_top_t *, n); - if (BE (mctx->bkref_ents == NULL || mctx->sub_tops == NULL, 0)) - return REG_ESPACE; - } - /* Already zero-ed by the caller. - else - mctx->bkref_ents = NULL; - mctx->nbkref_ents = 0; - mctx->nsub_tops = 0; */ - mctx->abkref_ents = n; - mctx->max_mb_elem_len = 1; - mctx->asub_tops = n; - return REG_NOERROR; -} - -/* Clean the entries which depend on the current input in MCTX. - This function must be invoked when the matcher changes the start index - of the input, or changes the input string. */ - -static void -internal_function -match_ctx_clean (re_match_context_t *mctx) -{ - int st_idx; - for (st_idx = 0; st_idx < mctx->nsub_tops; ++st_idx) - { - int sl_idx; - re_sub_match_top_t *top = mctx->sub_tops[st_idx]; - for (sl_idx = 0; sl_idx < top->nlasts; ++sl_idx) - { - re_sub_match_last_t *last = top->lasts[sl_idx]; - re_free (last->path.array); - re_free (last); - } - re_free (top->lasts); - if (top->path) - { - re_free (top->path->array); - re_free (top->path); - } - free (top); - } - - mctx->nsub_tops = 0; - mctx->nbkref_ents = 0; -} - -/* Free all the memory associated with MCTX. */ - -static void -internal_function -match_ctx_free (re_match_context_t *mctx) -{ - /* First, free all the memory associated with MCTX->SUB_TOPS. */ - match_ctx_clean (mctx); - re_free (mctx->sub_tops); - re_free (mctx->bkref_ents); -} - -/* Add a new backreference entry to MCTX. - Note that we assume that caller never call this function with duplicate - entry, and call with STR_IDX which isn't smaller than any existing entry. -*/ - -static reg_errcode_t -internal_function -match_ctx_add_entry (re_match_context_t *mctx, int node, int str_idx, int from, - int to) -{ - if (mctx->nbkref_ents >= mctx->abkref_ents) - { - struct re_backref_cache_entry* new_entry; - new_entry = re_realloc (mctx->bkref_ents, struct re_backref_cache_entry, - mctx->abkref_ents * 2); - if (BE (new_entry == NULL, 0)) - { - re_free (mctx->bkref_ents); - return REG_ESPACE; - } - mctx->bkref_ents = new_entry; - memset (mctx->bkref_ents + mctx->nbkref_ents, '\0', - sizeof (struct re_backref_cache_entry) * mctx->abkref_ents); - mctx->abkref_ents *= 2; - } - if (mctx->nbkref_ents > 0 - && mctx->bkref_ents[mctx->nbkref_ents - 1].str_idx == str_idx) - mctx->bkref_ents[mctx->nbkref_ents - 1].more = 1; - - mctx->bkref_ents[mctx->nbkref_ents].node = node; - mctx->bkref_ents[mctx->nbkref_ents].str_idx = str_idx; - mctx->bkref_ents[mctx->nbkref_ents].subexp_from = from; - mctx->bkref_ents[mctx->nbkref_ents].subexp_to = to; - - /* This is a cache that saves negative results of check_dst_limits_calc_pos. - If bit N is clear, means that this entry won't epsilon-transition to - an OP_OPEN_SUBEXP or OP_CLOSE_SUBEXP for the N+1-th subexpression. If - it is set, check_dst_limits_calc_pos_1 will recurse and try to find one - such node. - - A backreference does not epsilon-transition unless it is empty, so set - to all zeros if FROM != TO. */ - mctx->bkref_ents[mctx->nbkref_ents].eps_reachable_subexps_map - = (from == to ? ~0 : 0); - - mctx->bkref_ents[mctx->nbkref_ents++].more = 0; - if (mctx->max_mb_elem_len < to - from) - mctx->max_mb_elem_len = to - from; - return REG_NOERROR; -} - -/* Search for the first entry which has the same str_idx, or -1 if none is - found. Note that MCTX->BKREF_ENTS is already sorted by MCTX->STR_IDX. */ - -static int -internal_function -search_cur_bkref_entry (const re_match_context_t *mctx, int str_idx) -{ - int left, right, mid, last; - last = right = mctx->nbkref_ents; - for (left = 0; left < right;) - { - mid = (left + right) / 2; - if (mctx->bkref_ents[mid].str_idx < str_idx) - left = mid + 1; - else - right = mid; - } - if (left < last && mctx->bkref_ents[left].str_idx == str_idx) - return left; - else - return -1; -} - -/* Register the node NODE, whose type is OP_OPEN_SUBEXP, and which matches - at STR_IDX. */ - -static reg_errcode_t -internal_function -match_ctx_add_subtop (re_match_context_t *mctx, int node, int str_idx) -{ -#ifdef DEBUG - assert (mctx->sub_tops != NULL); - assert (mctx->asub_tops > 0); -#endif - if (BE (mctx->nsub_tops == mctx->asub_tops, 0)) - { - int new_asub_tops = mctx->asub_tops * 2; - re_sub_match_top_t **new_array = re_realloc (mctx->sub_tops, - re_sub_match_top_t *, - new_asub_tops); - if (BE (new_array == NULL, 0)) - return REG_ESPACE; - mctx->sub_tops = new_array; - mctx->asub_tops = new_asub_tops; - } - mctx->sub_tops[mctx->nsub_tops] = calloc (1, sizeof (re_sub_match_top_t)); - if (BE (mctx->sub_tops[mctx->nsub_tops] == NULL, 0)) - return REG_ESPACE; - mctx->sub_tops[mctx->nsub_tops]->node = node; - mctx->sub_tops[mctx->nsub_tops++]->str_idx = str_idx; - return REG_NOERROR; -} - -/* Register the node NODE, whose type is OP_CLOSE_SUBEXP, and which matches - at STR_IDX, whose corresponding OP_OPEN_SUBEXP is SUB_TOP. */ - -static re_sub_match_last_t * -internal_function -match_ctx_add_sublast (re_sub_match_top_t *subtop, int node, int str_idx) -{ - re_sub_match_last_t *new_entry; - if (BE (subtop->nlasts == subtop->alasts, 0)) - { - int new_alasts = 2 * subtop->alasts + 1; - re_sub_match_last_t **new_array = re_realloc (subtop->lasts, - re_sub_match_last_t *, - new_alasts); - if (BE (new_array == NULL, 0)) - return NULL; - subtop->lasts = new_array; - subtop->alasts = new_alasts; - } - new_entry = calloc (1, sizeof (re_sub_match_last_t)); - if (BE (new_entry != NULL, 1)) - { - subtop->lasts[subtop->nlasts] = new_entry; - new_entry->node = node; - new_entry->str_idx = str_idx; - ++subtop->nlasts; - } - return new_entry; -} - -static void -internal_function -sift_ctx_init (re_sift_context_t *sctx, re_dfastate_t **sifted_sts, - re_dfastate_t **limited_sts, int last_node, int last_str_idx) -{ - sctx->sifted_states = sifted_sts; - sctx->limited_states = limited_sts; - sctx->last_node = last_node; - sctx->last_str_idx = last_str_idx; - re_node_set_init_empty (&sctx->limits); -} diff --git a/deps/winhttp/urlmon.h b/deps/winhttp/urlmon.h deleted file mode 100644 index 4143d50..0000000 --- a/deps/winhttp/urlmon.h +++ /dev/null @@ -1,45 +0,0 @@ -/* - * Copyright (C) the libgit2 contributors. All rights reserved. - * - * This file is part of libgit2, distributed under the GNU GPL v2 with - * a Linking Exception. For full terms see the included COPYING file. - */ - -#if defined(__MINGW_VERSION) || defined(__MINGW32_VERSION) - -#ifndef __CUSTOM_URLMON_H -#define __CUSTOM_URLMON_H - -typedef struct IInternetSecurityManager IInternetSecurityManager; - -typedef struct IInternetSecurityManagerVtbl -{ - HRESULT(STDMETHODCALLTYPE *QueryInterface)(IInternetSecurityManager *, REFIID, void **); - ULONG(STDMETHODCALLTYPE *AddRef)(IInternetSecurityManager *); - ULONG(STDMETHODCALLTYPE *Release)(IInternetSecurityManager *); - LPVOID SetSecuritySite; - LPVOID GetSecuritySite; - HRESULT(STDMETHODCALLTYPE *MapUrlToZone)(IInternetSecurityManager *, LPCWSTR, DWORD *, DWORD); - LPVOID GetSecurityId; - LPVOID ProcessUrlAction; - LPVOID QueryCustomPolicy; - LPVOID SetZoneMapping; - LPVOID GetZoneMappings; -} IInternetSecurityManagerVtbl; - -struct IInternetSecurityManager -{ - CONST_VTBL struct IInternetSecurityManagerVtbl *lpVtbl; -}; - -#define URLZONE_LOCAL_MACHINE 0 -#define URLZONE_INTRANET 1 -#define URLZONE_TRUSTED 2 - -#endif /* __CUSTOM_URLMON_H */ - -#else - -#include_next - -#endif diff --git a/deps/winhttp/winhttp.def b/deps/winhttp/winhttp.def deleted file mode 100644 index eecce59..0000000 --- a/deps/winhttp/winhttp.def +++ /dev/null @@ -1,29 +0,0 @@ -LIBRARY WINHTTP -EXPORTS -WinHttpAddRequestHeaders@16 -WinHttpCheckPlatform@0 -WinHttpCloseHandle@4 -WinHttpConnect@16 -WinHttpCrackUrl@16 -WinHttpCreateUrl@16 -WinHttpDetectAutoProxyConfigUrl@8 -WinHttpGetDefaultProxyConfiguration@4 -WinHttpGetIEProxyConfigForCurrentUser@4 -WinHttpGetProxyForUrl@16 -WinHttpOpen@20 -WinHttpOpenRequest@28 -WinHttpQueryAuthSchemes@16 -WinHttpQueryDataAvailable@8 -WinHttpQueryHeaders@24 -WinHttpQueryOption@16 -WinHttpReadData@16 -WinHttpReceiveResponse@8 -WinHttpSendRequest@28 -WinHttpSetCredentials@24 -WinHttpSetDefaultProxyConfiguration@4 -WinHttpSetOption@16 -WinHttpSetStatusCallback@16 -WinHttpSetTimeouts@20 -WinHttpTimeFromSystemTime@8 -WinHttpTimeToSystemTime@8 -WinHttpWriteData@16 diff --git a/deps/winhttp/winhttp.h b/deps/winhttp/winhttp.h deleted file mode 100644 index b7fef1c..0000000 --- a/deps/winhttp/winhttp.h +++ /dev/null @@ -1,594 +0,0 @@ -/* - * Copyright (C) 2007 Francois Gouget - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA - */ - -#if defined(__MINGW_VERSION) || defined(__MINGW32_VERSION) - -#ifndef __WINE_WINHTTP_H -#define __WINE_WINHTTP_H - -#ifdef _WIN64 -#include -#else -#include -#endif - -#define WINHTTPAPI -#define BOOLAPI WINHTTPAPI BOOL WINAPI - - -typedef LPVOID HINTERNET; -typedef HINTERNET *LPHINTERNET; - -#define INTERNET_DEFAULT_PORT 0 -#define INTERNET_DEFAULT_HTTP_PORT 80 -#define INTERNET_DEFAULT_HTTPS_PORT 443 -typedef WORD INTERNET_PORT; -typedef INTERNET_PORT *LPINTERNET_PORT; - -#define INTERNET_SCHEME_HTTP 1 -#define INTERNET_SCHEME_HTTPS 2 -typedef int INTERNET_SCHEME, *LPINTERNET_SCHEME; - -#define ICU_ESCAPE 0x80000000 - -/* flags for WinHttpOpen */ -#define WINHTTP_FLAG_ASYNC 0x10000000 - -/* flags for WinHttpOpenRequest */ -#define WINHTTP_FLAG_ESCAPE_PERCENT 0x00000004 -#define WINHTTP_FLAG_NULL_CODEPAGE 0x00000008 -#define WINHTTP_FLAG_ESCAPE_DISABLE 0x00000040 -#define WINHTTP_FLAG_ESCAPE_DISABLE_QUERY 0x00000080 -#define WINHTTP_FLAG_BYPASS_PROXY_CACHE 0x00000100 -#define WINHTTP_FLAG_REFRESH WINHTTP_FLAG_BYPASS_PROXY_CACHE -#define WINHTTP_FLAG_SECURE 0x00800000 - -#define WINHTTP_ACCESS_TYPE_DEFAULT_PROXY 0 -#define WINHTTP_ACCESS_TYPE_NO_PROXY 1 -#define WINHTTP_ACCESS_TYPE_NAMED_PROXY 3 - -#define WINHTTP_NO_PROXY_NAME NULL -#define WINHTTP_NO_PROXY_BYPASS NULL - -#define WINHTTP_NO_REFERER NULL -#define WINHTTP_DEFAULT_ACCEPT_TYPES NULL - -#define WINHTTP_NO_ADDITIONAL_HEADERS NULL -#define WINHTTP_NO_REQUEST_DATA NULL - -#define WINHTTP_HEADER_NAME_BY_INDEX NULL -#define WINHTTP_NO_OUTPUT_BUFFER NULL -#define WINHTTP_NO_HEADER_INDEX NULL - -#define WINHTTP_ADDREQ_INDEX_MASK 0x0000FFFF -#define WINHTTP_ADDREQ_FLAGS_MASK 0xFFFF0000 -#define WINHTTP_ADDREQ_FLAG_ADD_IF_NEW 0x10000000 -#define WINHTTP_ADDREQ_FLAG_ADD 0x20000000 -#define WINHTTP_ADDREQ_FLAG_COALESCE_WITH_COMMA 0x40000000 -#define WINHTTP_ADDREQ_FLAG_COALESCE_WITH_SEMICOLON 0x01000000 -#define WINHTTP_ADDREQ_FLAG_COALESCE WINHTTP_ADDREQ_FLAG_COALESCE_WITH_COMMA -#define WINHTTP_ADDREQ_FLAG_REPLACE 0x80000000 - -#define WINHTTP_IGNORE_REQUEST_TOTAL_LENGTH 0 - -/* flags for WinHttp{Set/Query}Options */ -#define WINHTTP_FIRST_OPTION WINHTTP_OPTION_CALLBACK -#define WINHTTP_OPTION_CALLBACK 1 -#define WINHTTP_OPTION_RESOLVE_TIMEOUT 2 -#define WINHTTP_OPTION_CONNECT_TIMEOUT 3 -#define WINHTTP_OPTION_CONNECT_RETRIES 4 -#define WINHTTP_OPTION_SEND_TIMEOUT 5 -#define WINHTTP_OPTION_RECEIVE_TIMEOUT 6 -#define WINHTTP_OPTION_RECEIVE_RESPONSE_TIMEOUT 7 -#define WINHTTP_OPTION_HANDLE_TYPE 9 -#define WINHTTP_OPTION_READ_BUFFER_SIZE 12 -#define WINHTTP_OPTION_WRITE_BUFFER_SIZE 13 -#define WINHTTP_OPTION_PARENT_HANDLE 21 -#define WINHTTP_OPTION_EXTENDED_ERROR 24 -#define WINHTTP_OPTION_SECURITY_FLAGS 31 -#define WINHTTP_OPTION_SECURITY_CERTIFICATE_STRUCT 32 -#define WINHTTP_OPTION_URL 34 -#define WINHTTP_OPTION_SECURITY_KEY_BITNESS 36 -#define WINHTTP_OPTION_PROXY 38 -#define WINHTTP_OPTION_USER_AGENT 41 -#define WINHTTP_OPTION_CONTEXT_VALUE 45 -#define WINHTTP_OPTION_CLIENT_CERT_CONTEXT 47 -#define WINHTTP_OPTION_REQUEST_PRIORITY 58 -#define WINHTTP_OPTION_HTTP_VERSION 59 -#define WINHTTP_OPTION_DISABLE_FEATURE 63 -#define WINHTTP_OPTION_CODEPAGE 68 -#define WINHTTP_OPTION_MAX_CONNS_PER_SERVER 73 -#define WINHTTP_OPTION_MAX_CONNS_PER_1_0_SERVER 74 -#define WINHTTP_OPTION_AUTOLOGON_POLICY 77 -#define WINHTTP_OPTION_SERVER_CERT_CONTEXT 78 -#define WINHTTP_OPTION_ENABLE_FEATURE 79 -#define WINHTTP_OPTION_WORKER_THREAD_COUNT 80 -#define WINHTTP_OPTION_PASSPORT_COBRANDING_TEXT 81 -#define WINHTTP_OPTION_PASSPORT_COBRANDING_URL 82 -#define WINHTTP_OPTION_CONFIGURE_PASSPORT_AUTH 83 -#define WINHTTP_OPTION_SECURE_PROTOCOLS 84 -#define WINHTTP_OPTION_ENABLETRACING 85 -#define WINHTTP_OPTION_PASSPORT_SIGN_OUT 86 -#define WINHTTP_OPTION_PASSPORT_RETURN_URL 87 -#define WINHTTP_OPTION_REDIRECT_POLICY 88 -#define WINHTTP_OPTION_MAX_HTTP_AUTOMATIC_REDIRECTS 89 -#define WINHTTP_OPTION_MAX_HTTP_STATUS_CONTINUE 90 -#define WINHTTP_OPTION_MAX_RESPONSE_HEADER_SIZE 91 -#define WINHTTP_OPTION_MAX_RESPONSE_DRAIN_SIZE 92 -#define WINHTTP_OPTION_CONNECTION_INFO 93 -#define WINHTTP_OPTION_CLIENT_CERT_ISSUER_LIST 94 -#define WINHTTP_OPTION_SPN 96 -#define WINHTTP_OPTION_GLOBAL_PROXY_CREDS 97 -#define WINHTTP_OPTION_GLOBAL_SERVER_CREDS 98 -#define WINHTTP_OPTION_UNLOAD_NOTIFY_EVENT 99 -#define WINHTTP_OPTION_REJECT_USERPWD_IN_URL 100 -#define WINHTTP_OPTION_USE_GLOBAL_SERVER_CREDENTIALS 101 -#define WINHTTP_LAST_OPTION WINHTTP_OPTION_USE_GLOBAL_SERVER_CREDENTIALS -#define WINHTTP_OPTION_USERNAME 0x1000 -#define WINHTTP_OPTION_PASSWORD 0x1001 -#define WINHTTP_OPTION_PROXY_USERNAME 0x1002 -#define WINHTTP_OPTION_PROXY_PASSWORD 0x1003 - -#define WINHTTP_CONNS_PER_SERVER_UNLIMITED 0xFFFFFFFF - -#define WINHTTP_AUTOLOGON_SECURITY_LEVEL_MEDIUM 0 -#define WINHTTP_AUTOLOGON_SECURITY_LEVEL_LOW 1 -#define WINHTTP_AUTOLOGON_SECURITY_LEVEL_HIGH 2 -#define WINHTTP_AUTOLOGON_SECURITY_LEVEL_DEFAULT WINHTTP_AUTOLOGON_SECURITY_LEVEL_MEDIUM - -#define WINHTTP_OPTION_REDIRECT_POLICY_NEVER 0 -#define WINHTTP_OPTION_REDIRECT_POLICY_DISALLOW_HTTPS_TO_HTTP 1 -#define WINHTTP_OPTION_REDIRECT_POLICY_ALWAYS 2 -#define WINHTTP_OPTION_REDIRECT_POLICY_LAST WINHTTP_OPTION_REDIRECT_POLICY_ALWAYS -#define WINHTTP_OPTION_REDIRECT_POLICY_DEFAULT WINHTTP_OPTION_REDIRECT_POLICY_DISALLOW_HTTPS_TO_HTTP - -#define WINHTTP_DISABLE_PASSPORT_AUTH 0x00000000 -#define WINHTTP_ENABLE_PASSPORT_AUTH 0x10000000 -#define WINHTTP_DISABLE_PASSPORT_KEYRING 0x20000000 -#define WINHTTP_ENABLE_PASSPORT_KEYRING 0x40000000 - -#define WINHTTP_DISABLE_COOKIES 0x00000001 -#define WINHTTP_DISABLE_REDIRECTS 0x00000002 -#define WINHTTP_DISABLE_AUTHENTICATION 0x00000004 -#define WINHTTP_DISABLE_KEEP_ALIVE 0x00000008 -#define WINHTTP_ENABLE_SSL_REVOCATION 0x00000001 -#define WINHTTP_ENABLE_SSL_REVERT_IMPERSONATION 0x00000002 -#define WINHTTP_DISABLE_SPN_SERVER_PORT 0x00000000 -#define WINHTTP_ENABLE_SPN_SERVER_PORT 0x00000001 -#define WINHTTP_OPTION_SPN_MASK WINHTTP_ENABLE_SPN_SERVER_PORT - -/* Options for WinHttpOpenRequest */ -#define WINHTTP_NO_REFERER NULL -#define WINHTTP_DEFAULT_ACCEPT_TYPES NULL - -/* Options for WinHttpSendRequest */ -#define WINHTTP_NO_ADDITIONAL_HEADERS NULL -#define WINHTTP_NO_REQUEST_DATA NULL - -/* WinHTTP error codes */ -#define WINHTTP_ERROR_BASE 12000 -#define ERROR_WINHTTP_OUT_OF_HANDLES (WINHTTP_ERROR_BASE + 1) -#define ERROR_WINHTTP_TIMEOUT (WINHTTP_ERROR_BASE + 2) -#define ERROR_WINHTTP_INTERNAL_ERROR (WINHTTP_ERROR_BASE + 4) -#define ERROR_WINHTTP_INVALID_URL (WINHTTP_ERROR_BASE + 5) -#define ERROR_WINHTTP_UNRECOGNIZED_SCHEME (WINHTTP_ERROR_BASE + 6) -#define ERROR_WINHTTP_NAME_NOT_RESOLVED (WINHTTP_ERROR_BASE + 7) -#define ERROR_WINHTTP_INVALID_OPTION (WINHTTP_ERROR_BASE + 9) -#define ERROR_WINHTTP_OPTION_NOT_SETTABLE (WINHTTP_ERROR_BASE + 11) -#define ERROR_WINHTTP_SHUTDOWN (WINHTTP_ERROR_BASE + 12) -#define ERROR_WINHTTP_LOGIN_FAILURE (WINHTTP_ERROR_BASE + 15) -#define ERROR_WINHTTP_OPERATION_CANCELLED (WINHTTP_ERROR_BASE + 17) -#define ERROR_WINHTTP_INCORRECT_HANDLE_TYPE (WINHTTP_ERROR_BASE + 18) -#define ERROR_WINHTTP_INCORRECT_HANDLE_STATE (WINHTTP_ERROR_BASE + 19) -#define ERROR_WINHTTP_CANNOT_CONNECT (WINHTTP_ERROR_BASE + 29) -#define ERROR_WINHTTP_CONNECTION_ERROR (WINHTTP_ERROR_BASE + 30) -#define ERROR_WINHTTP_RESEND_REQUEST (WINHTTP_ERROR_BASE + 32) -#define ERROR_WINHTTP_SECURE_CERT_DATE_INVALID (WINHTTP_ERROR_BASE + 37) -#define ERROR_WINHTTP_SECURE_CERT_CN_INVALID (WINHTTP_ERROR_BASE + 38) -#define ERROR_WINHTTP_CLIENT_AUTH_CERT_NEEDED (WINHTTP_ERROR_BASE + 44) -#define ERROR_WINHTTP_SECURE_INVALID_CA (WINHTTP_ERROR_BASE + 45) -#define ERROR_WINHTTP_SECURE_CERT_REV_FAILED (WINHTTP_ERROR_BASE + 57) -#define ERROR_WINHTTP_CANNOT_CALL_BEFORE_OPEN (WINHTTP_ERROR_BASE + 100) -#define ERROR_WINHTTP_CANNOT_CALL_BEFORE_SEND (WINHTTP_ERROR_BASE + 101) -#define ERROR_WINHTTP_CANNOT_CALL_AFTER_SEND (WINHTTP_ERROR_BASE + 102) -#define ERROR_WINHTTP_CANNOT_CALL_AFTER_OPEN (WINHTTP_ERROR_BASE + 103) -#define ERROR_WINHTTP_HEADER_NOT_FOUND (WINHTTP_ERROR_BASE + 150) -#define ERROR_WINHTTP_INVALID_SERVER_RESPONSE (WINHTTP_ERROR_BASE + 152) -#define ERROR_WINHTTP_INVALID_HEADER (WINHTTP_ERROR_BASE + 153) -#define ERROR_WINHTTP_INVALID_QUERY_REQUEST (WINHTTP_ERROR_BASE + 154) -#define ERROR_WINHTTP_HEADER_ALREADY_EXISTS (WINHTTP_ERROR_BASE + 155) -#define ERROR_WINHTTP_REDIRECT_FAILED (WINHTTP_ERROR_BASE + 156) -#define ERROR_WINHTTP_SECURE_CHANNEL_ERROR (WINHTTP_ERROR_BASE + 157) -#define ERROR_WINHTTP_BAD_AUTO_PROXY_SCRIPT (WINHTTP_ERROR_BASE + 166) -#define ERROR_WINHTTP_UNABLE_TO_DOWNLOAD_SCRIPT (WINHTTP_ERROR_BASE + 167) -#define ERROR_WINHTTP_SECURE_INVALID_CERT (WINHTTP_ERROR_BASE + 169) -#define ERROR_WINHTTP_SECURE_CERT_REVOKED (WINHTTP_ERROR_BASE + 170) -#define ERROR_WINHTTP_NOT_INITIALIZED (WINHTTP_ERROR_BASE + 172) -#define ERROR_WINHTTP_SECURE_FAILURE (WINHTTP_ERROR_BASE + 175) -#define ERROR_WINHTTP_AUTO_PROXY_SERVICE_ERROR (WINHTTP_ERROR_BASE + 178) -#define ERROR_WINHTTP_SECURE_CERT_WRONG_USAGE (WINHTTP_ERROR_BASE + 179) -#define ERROR_WINHTTP_AUTODETECTION_FAILED (WINHTTP_ERROR_BASE + 180) -#define ERROR_WINHTTP_HEADER_COUNT_EXCEEDED (WINHTTP_ERROR_BASE + 181) -#define ERROR_WINHTTP_HEADER_SIZE_OVERFLOW (WINHTTP_ERROR_BASE + 182) -#define ERROR_WINHTTP_CHUNKED_ENCODING_HEADER_SIZE_OVERFLOW (WINHTTP_ERROR_BASE + 183) -#define ERROR_WINHTTP_RESPONSE_DRAIN_OVERFLOW (WINHTTP_ERROR_BASE + 184) -#define ERROR_WINHTTP_CLIENT_CERT_NO_PRIVATE_KEY (WINHTTP_ERROR_BASE + 185) -#define ERROR_WINHTTP_CLIENT_CERT_NO_ACCESS_PRIVATE_KEY (WINHTTP_ERROR_BASE + 186) -#define WINHTTP_ERROR_LAST (WINHTTP_ERROR_BASE + 186) - -/* WinHttp status codes */ -#define HTTP_STATUS_CONTINUE 100 -#define HTTP_STATUS_SWITCH_PROTOCOLS 101 -#define HTTP_STATUS_OK 200 -#define HTTP_STATUS_CREATED 201 -#define HTTP_STATUS_ACCEPTED 202 -#define HTTP_STATUS_PARTIAL 203 -#define HTTP_STATUS_NO_CONTENT 204 -#define HTTP_STATUS_RESET_CONTENT 205 -#define HTTP_STATUS_PARTIAL_CONTENT 206 -#define HTTP_STATUS_WEBDAV_MULTI_STATUS 207 -#define HTTP_STATUS_AMBIGUOUS 300 -#define HTTP_STATUS_MOVED 301 -#define HTTP_STATUS_REDIRECT 302 -#define HTTP_STATUS_REDIRECT_METHOD 303 -#define HTTP_STATUS_NOT_MODIFIED 304 -#define HTTP_STATUS_USE_PROXY 305 -#define HTTP_STATUS_REDIRECT_KEEP_VERB 307 -#define HTTP_STATUS_BAD_REQUEST 400 -#define HTTP_STATUS_DENIED 401 -#define HTTP_STATUS_PAYMENT_REQ 402 -#define HTTP_STATUS_FORBIDDEN 403 -#define HTTP_STATUS_NOT_FOUND 404 -#define HTTP_STATUS_BAD_METHOD 405 -#define HTTP_STATUS_NONE_ACCEPTABLE 406 -#define HTTP_STATUS_PROXY_AUTH_REQ 407 -#define HTTP_STATUS_REQUEST_TIMEOUT 408 -#define HTTP_STATUS_CONFLICT 409 -#define HTTP_STATUS_GONE 410 -#define HTTP_STATUS_LENGTH_REQUIRED 411 -#define HTTP_STATUS_PRECOND_FAILED 412 -#define HTTP_STATUS_REQUEST_TOO_LARGE 413 -#define HTTP_STATUS_URI_TOO_LONG 414 -#define HTTP_STATUS_UNSUPPORTED_MEDIA 415 -#define HTTP_STATUS_RETRY_WITH 449 -#define HTTP_STATUS_SERVER_ERROR 500 -#define HTTP_STATUS_NOT_SUPPORTED 501 -#define HTTP_STATUS_BAD_GATEWAY 502 -#define HTTP_STATUS_SERVICE_UNAVAIL 503 -#define HTTP_STATUS_GATEWAY_TIMEOUT 504 -#define HTTP_STATUS_VERSION_NOT_SUP 505 -#define HTTP_STATUS_FIRST HTTP_STATUS_CONTINUE -#define HTTP_STATUS_LAST HTTP_STATUS_VERSION_NOT_SUP - -#define SECURITY_FLAG_IGNORE_UNKNOWN_CA 0x00000100 -#define SECURITY_FLAG_IGNORE_CERT_DATE_INVALID 0x00002000 -#define SECURITY_FLAG_IGNORE_CERT_CN_INVALID 0x00001000 -#define SECURITY_FLAG_IGNORE_CERT_WRONG_USAGE 0x00000200 -#define SECURITY_FLAG_SECURE 0x00000001 -#define SECURITY_FLAG_STRENGTH_WEAK 0x10000000 -#define SECURITY_FLAG_STRENGTH_MEDIUM 0x40000000 -#define SECURITY_FLAG_STRENGTH_STRONG 0x20000000 - -#define ICU_NO_ENCODE 0x20000000 -#define ICU_DECODE 0x10000000 -#define ICU_NO_META 0x08000000 -#define ICU_ENCODE_SPACES_ONLY 0x04000000 -#define ICU_BROWSER_MODE 0x02000000 -#define ICU_ENCODE_PERCENT 0x00001000 - -/* Query flags */ -#define WINHTTP_QUERY_MIME_VERSION 0 -#define WINHTTP_QUERY_CONTENT_TYPE 1 -#define WINHTTP_QUERY_CONTENT_TRANSFER_ENCODING 2 -#define WINHTTP_QUERY_CONTENT_ID 3 -#define WINHTTP_QUERY_CONTENT_DESCRIPTION 4 -#define WINHTTP_QUERY_CONTENT_LENGTH 5 -#define WINHTTP_QUERY_CONTENT_LANGUAGE 6 -#define WINHTTP_QUERY_ALLOW 7 -#define WINHTTP_QUERY_PUBLIC 8 -#define WINHTTP_QUERY_DATE 9 -#define WINHTTP_QUERY_EXPIRES 10 -#define WINHTTP_QUERY_LAST_MODIFIED 11 -#define WINHTTP_QUERY_MESSAGE_ID 12 -#define WINHTTP_QUERY_URI 13 -#define WINHTTP_QUERY_DERIVED_FROM 14 -#define WINHTTP_QUERY_COST 15 -#define WINHTTP_QUERY_LINK 16 -#define WINHTTP_QUERY_PRAGMA 17 -#define WINHTTP_QUERY_VERSION 18 -#define WINHTTP_QUERY_STATUS_CODE 19 -#define WINHTTP_QUERY_STATUS_TEXT 20 -#define WINHTTP_QUERY_RAW_HEADERS 21 -#define WINHTTP_QUERY_RAW_HEADERS_CRLF 22 -#define WINHTTP_QUERY_CONNECTION 23 -#define WINHTTP_QUERY_ACCEPT 24 -#define WINHTTP_QUERY_ACCEPT_CHARSET 25 -#define WINHTTP_QUERY_ACCEPT_ENCODING 26 -#define WINHTTP_QUERY_ACCEPT_LANGUAGE 27 -#define WINHTTP_QUERY_AUTHORIZATION 28 -#define WINHTTP_QUERY_CONTENT_ENCODING 29 -#define WINHTTP_QUERY_FORWARDED 30 -#define WINHTTP_QUERY_FROM 31 -#define WINHTTP_QUERY_IF_MODIFIED_SINCE 32 -#define WINHTTP_QUERY_LOCATION 33 -#define WINHTTP_QUERY_ORIG_URI 34 -#define WINHTTP_QUERY_REFERER 35 -#define WINHTTP_QUERY_RETRY_AFTER 36 -#define WINHTTP_QUERY_SERVER 37 -#define WINHTTP_QUERY_TITLE 38 -#define WINHTTP_QUERY_USER_AGENT 39 -#define WINHTTP_QUERY_WWW_AUTHENTICATE 40 -#define WINHTTP_QUERY_PROXY_AUTHENTICATE 41 -#define WINHTTP_QUERY_ACCEPT_RANGES 42 -#define WINHTTP_QUERY_SET_COOKIE 43 -#define WINHTTP_QUERY_COOKIE 44 -#define WINHTTP_QUERY_REQUEST_METHOD 45 -#define WINHTTP_QUERY_REFRESH 46 -#define WINHTTP_QUERY_CONTENT_DISPOSITION 47 -#define WINHTTP_QUERY_AGE 48 -#define WINHTTP_QUERY_CACHE_CONTROL 49 -#define WINHTTP_QUERY_CONTENT_BASE 50 -#define WINHTTP_QUERY_CONTENT_LOCATION 51 -#define WINHTTP_QUERY_CONTENT_MD5 52 -#define WINHTTP_QUERY_CONTENT_RANGE 53 -#define WINHTTP_QUERY_ETAG 54 -#define WINHTTP_QUERY_HOST 55 -#define WINHTTP_QUERY_IF_MATCH 56 -#define WINHTTP_QUERY_IF_NONE_MATCH 57 -#define WINHTTP_QUERY_IF_RANGE 58 -#define WINHTTP_QUERY_IF_UNMODIFIED_SINCE 59 -#define WINHTTP_QUERY_MAX_FORWARDS 60 -#define WINHTTP_QUERY_PROXY_AUTHORIZATION 61 -#define WINHTTP_QUERY_RANGE 62 -#define WINHTTP_QUERY_TRANSFER_ENCODING 63 -#define WINHTTP_QUERY_UPGRADE 64 -#define WINHTTP_QUERY_VARY 65 -#define WINHTTP_QUERY_VIA 66 -#define WINHTTP_QUERY_WARNING 67 -#define WINHTTP_QUERY_EXPECT 68 -#define WINHTTP_QUERY_PROXY_CONNECTION 69 -#define WINHTTP_QUERY_UNLESS_MODIFIED_SINCE 70 -#define WINHTTP_QUERY_PROXY_SUPPORT 75 -#define WINHTTP_QUERY_AUTHENTICATION_INFO 76 -#define WINHTTP_QUERY_PASSPORT_URLS 77 -#define WINHTTP_QUERY_PASSPORT_CONFIG 78 -#define WINHTTP_QUERY_MAX 78 -#define WINHTTP_QUERY_CUSTOM 65535 -#define WINHTTP_QUERY_FLAG_REQUEST_HEADERS 0x80000000 -#define WINHTTP_QUERY_FLAG_SYSTEMTIME 0x40000000 -#define WINHTTP_QUERY_FLAG_NUMBER 0x20000000 - -/* Callback options */ -#define WINHTTP_CALLBACK_STATUS_RESOLVING_NAME 0x00000001 -#define WINHTTP_CALLBACK_STATUS_NAME_RESOLVED 0x00000002 -#define WINHTTP_CALLBACK_STATUS_CONNECTING_TO_SERVER 0x00000004 -#define WINHTTP_CALLBACK_STATUS_CONNECTED_TO_SERVER 0x00000008 -#define WINHTTP_CALLBACK_STATUS_SENDING_REQUEST 0x00000010 -#define WINHTTP_CALLBACK_STATUS_REQUEST_SENT 0x00000020 -#define WINHTTP_CALLBACK_STATUS_RECEIVING_RESPONSE 0x00000040 -#define WINHTTP_CALLBACK_STATUS_RESPONSE_RECEIVED 0x00000080 -#define WINHTTP_CALLBACK_STATUS_CLOSING_CONNECTION 0x00000100 -#define WINHTTP_CALLBACK_STATUS_CONNECTION_CLOSED 0x00000200 -#define WINHTTP_CALLBACK_STATUS_HANDLE_CREATED 0x00000400 -#define WINHTTP_CALLBACK_STATUS_HANDLE_CLOSING 0x00000800 -#define WINHTTP_CALLBACK_STATUS_DETECTING_PROXY 0x00001000 -#define WINHTTP_CALLBACK_STATUS_REDIRECT 0x00004000 -#define WINHTTP_CALLBACK_STATUS_INTERMEDIATE_RESPONSE 0x00008000 -#define WINHTTP_CALLBACK_STATUS_SECURE_FAILURE 0x00010000 -#define WINHTTP_CALLBACK_STATUS_HEADERS_AVAILABLE 0x00020000 -#define WINHTTP_CALLBACK_STATUS_DATA_AVAILABLE 0x00040000 -#define WINHTTP_CALLBACK_STATUS_READ_COMPLETE 0x00080000 -#define WINHTTP_CALLBACK_STATUS_WRITE_COMPLETE 0x00100000 -#define WINHTTP_CALLBACK_STATUS_REQUEST_ERROR 0x00200000 -#define WINHTTP_CALLBACK_STATUS_SENDREQUEST_COMPLETE 0x00400000 -#define WINHTTP_CALLBACK_FLAG_RESOLVE_NAME (WINHTTP_CALLBACK_STATUS_RESOLVING_NAME | WINHTTP_CALLBACK_STATUS_NAME_RESOLVED) -#define WINHTTP_CALLBACK_FLAG_CONNECT_TO_SERVER (WINHTTP_CALLBACK_STATUS_CONNECTING_TO_SERVER | WINHTTP_CALLBACK_STATUS_CONNECTED_TO_SERVER) -#define WINHTTP_CALLBACK_FLAG_SEND_REQUEST (WINHTTP_CALLBACK_STATUS_SENDING_REQUEST | WINHTTP_CALLBACK_STATUS_REQUEST_SENT) -#define WINHTTP_CALLBACK_FLAG_RECEIVE_RESPONSE (WINHTTP_CALLBACK_STATUS_RECEIVING_RESPONSE | WINHTTP_CALLBACK_STATUS_RESPONSE_RECEIVED) -#define WINHTTP_CALLBACK_FLAG_CLOSE_CONNECTION (WINHTTP_CALLBACK_STATUS_CLOSING_CONNECTION | WINHTTP_CALLBACK_STATUS_CONNECTION_CLOSED) -#define WINHTTP_CALLBACK_FLAG_HANDLES (WINHTTP_CALLBACK_STATUS_HANDLE_CREATED | WINHTTP_CALLBACK_STATUS_HANDLE_CLOSING) -#define WINHTTP_CALLBACK_FLAG_DETECTING_PROXY WINHTTP_CALLBACK_STATUS_DETECTING_PROXY -#define WINHTTP_CALLBACK_FLAG_REDIRECT WINHTTP_CALLBACK_STATUS_REDIRECT -#define WINHTTP_CALLBACK_FLAG_INTERMEDIATE_RESPONSE WINHTTP_CALLBACK_STATUS_INTERMEDIATE_RESPONSE -#define WINHTTP_CALLBACK_FLAG_SECURE_FAILURE WINHTTP_CALLBACK_STATUS_SECURE_FAILURE -#define WINHTTP_CALLBACK_FLAG_SENDREQUEST_COMPLETE WINHTTP_CALLBACK_STATUS_SENDREQUEST_COMPLETE -#define WINHTTP_CALLBACK_FLAG_HEADERS_AVAILABLE WINHTTP_CALLBACK_STATUS_HEADERS_AVAILABLE -#define WINHTTP_CALLBACK_FLAG_DATA_AVAILABLE WINHTTP_CALLBACK_STATUS_DATA_AVAILABLE -#define WINHTTP_CALLBACK_FLAG_READ_COMPLETE WINHTTP_CALLBACK_STATUS_READ_COMPLETE -#define WINHTTP_CALLBACK_FLAG_WRITE_COMPLETE WINHTTP_CALLBACK_STATUS_WRITE_COMPLETE -#define WINHTTP_CALLBACK_FLAG_REQUEST_ERROR WINHTTP_CALLBACK_STATUS_REQUEST_ERROR -#define WINHTTP_CALLBACK_FLAG_ALL_COMPLETIONS (WINHTTP_CALLBACK_STATUS_SENDREQUEST_COMPLETE | WINHTTP_CALLBACK_STATUS_HEADERS_AVAILABLE \ - | WINHTTP_CALLBACK_STATUS_DATA_AVAILABLE | WINHTTP_CALLBACK_STATUS_READ_COMPLETE \ - | WINHTTP_CALLBACK_STATUS_WRITE_COMPLETE | WINHTTP_CALLBACK_STATUS_REQUEST_ERROR) -#define WINHTTP_CALLBACK_FLAG_ALL_NOTIFICATIONS 0xffffffff -#define WINHTTP_INVALID_STATUS_CALLBACK ((WINHTTP_STATUS_CALLBACK)(-1)) - -#define API_RECEIVE_RESPONSE (1) -#define API_QUERY_DATA_AVAILABLE (2) -#define API_READ_DATA (3) -#define API_WRITE_DATA (4) -#define API_SEND_REQUEST (5) - -#define WINHTTP_HANDLE_TYPE_SESSION 1 -#define WINHTTP_HANDLE_TYPE_CONNECT 2 -#define WINHTTP_HANDLE_TYPE_REQUEST 3 - -#define WINHTTP_CALLBACK_STATUS_FLAG_CERT_REV_FAILED 0x00000001 -#define WINHTTP_CALLBACK_STATUS_FLAG_INVALID_CERT 0x00000002 -#define WINHTTP_CALLBACK_STATUS_FLAG_CERT_REVOKED 0x00000004 -#define WINHTTP_CALLBACK_STATUS_FLAG_INVALID_CA 0x00000008 -#define WINHTTP_CALLBACK_STATUS_FLAG_CERT_CN_INVALID 0x00000010 -#define WINHTTP_CALLBACK_STATUS_FLAG_CERT_DATE_INVALID 0x00000020 -#define WINHTTP_CALLBACK_STATUS_FLAG_CERT_WRONG_USAGE 0x00000040 -#define WINHTTP_CALLBACK_STATUS_FLAG_SECURITY_CHANNEL_ERROR 0x80000000 - -#define WINHTTP_FLAG_SECURE_PROTOCOL_SSL2 0x00000008 -#define WINHTTP_FLAG_SECURE_PROTOCOL_SSL3 0x00000020 -#define WINHTTP_FLAG_SECURE_PROTOCOL_TLS1 0x00000080 -#define WINHTTP_FLAG_SECURE_PROTOCOL_TLS1_1 0x00000200 -#define WINHTTP_FLAG_SECURE_PROTOCOL_TLS1_2 0x00000800 -#define WINHTTP_FLAG_SECURE_PROTOCOL_ALL (WINHTTP_FLAG_SECURE_PROTOCOL_SSL2 | WINHTTP_FLAG_SECURE_PROTOCOL_SSL3 | WINHTTP_FLAG_SECURE_PROTOCOL_TLS1) - -#define WINHTTP_AUTH_SCHEME_BASIC 0x00000001 -#define WINHTTP_AUTH_SCHEME_NTLM 0x00000002 -#define WINHTTP_AUTH_SCHEME_PASSPORT 0x00000004 -#define WINHTTP_AUTH_SCHEME_DIGEST 0x00000008 -#define WINHTTP_AUTH_SCHEME_NEGOTIATE 0x00000010 - -#define WINHTTP_AUTH_TARGET_SERVER 0x00000000 -#define WINHTTP_AUTH_TARGET_PROXY 0x00000001 - -#define WINHTTP_TIME_FORMAT_BUFSIZE 62 - -typedef struct -{ - DWORD dwStructSize; - LPWSTR lpszScheme; - DWORD dwSchemeLength; - INTERNET_SCHEME nScheme; - LPWSTR lpszHostName; - DWORD dwHostNameLength; - INTERNET_PORT nPort; - LPWSTR lpszUserName; - DWORD dwUserNameLength; - LPWSTR lpszPassword; - DWORD dwPasswordLength; - LPWSTR lpszUrlPath; - DWORD dwUrlPathLength; - LPWSTR lpszExtraInfo; - DWORD dwExtraInfoLength; -} URL_COMPONENTS, *LPURL_COMPONENTS; -typedef URL_COMPONENTS URL_COMPONENTSW; -typedef LPURL_COMPONENTS LPURL_COMPONENTSW; - -typedef struct -{ - DWORD_PTR dwResult; - DWORD dwError; -} WINHTTP_ASYNC_RESULT, *LPWINHTTP_ASYNC_RESULT; - -typedef struct -{ - FILETIME ftExpiry; - FILETIME ftStart; - LPWSTR lpszSubjectInfo; - LPWSTR lpszIssuerInfo; - LPWSTR lpszProtocolName; - LPWSTR lpszSignatureAlgName; - LPWSTR lpszEncryptionAlgName; - DWORD dwKeySize; -} WINHTTP_CERTIFICATE_INFO; - -typedef struct -{ - DWORD dwAccessType; - LPWSTR lpszProxy; - LPWSTR lpszProxyBypass; -} WINHTTP_PROXY_INFO, *LPWINHTTP_PROXY_INFO; -typedef WINHTTP_PROXY_INFO WINHTTP_PROXY_INFOW; -typedef LPWINHTTP_PROXY_INFO LPWINHTTP_PROXY_INFOW; - -typedef struct -{ - BOOL fAutoDetect; - LPWSTR lpszAutoConfigUrl; - LPWSTR lpszProxy; - LPWSTR lpszProxyBypass; -} WINHTTP_CURRENT_USER_IE_PROXY_CONFIG; - -typedef VOID (CALLBACK *WINHTTP_STATUS_CALLBACK)(HINTERNET,DWORD_PTR,DWORD,LPVOID,DWORD); - -#define WINHTTP_AUTO_DETECT_TYPE_DHCP 0x00000001 -#define WINHTTP_AUTO_DETECT_TYPE_DNS_A 0x00000002 - -#define WINHTTP_AUTOPROXY_AUTO_DETECT 0x00000001 -#define WINHTTP_AUTOPROXY_CONFIG_URL 0x00000002 -#define WINHTTP_AUTOPROXY_RUN_INPROCESS 0x00010000 -#define WINHTTP_AUTOPROXY_RUN_OUTPROCESS_ONLY 0x00020000 - -typedef struct -{ - DWORD dwFlags; - DWORD dwAutoDetectFlags; - LPCWSTR lpszAutoConfigUrl; - LPVOID lpvReserved; - DWORD dwReserved; - BOOL fAutoLogonIfChallenged; -} WINHTTP_AUTOPROXY_OPTIONS; - -typedef struct -{ - DWORD dwMajorVersion; - DWORD dwMinorVersion; -} HTTP_VERSION_INFO, *LPHTTP_VERSION_INFO; - -#ifdef _WS2DEF_ -typedef struct -{ - DWORD cbSize; - SOCKADDR_STORAGE LocalAddress; - SOCKADDR_STORAGE RemoteAddress; -} WINHTTP_CONNECTION_INFO; -#endif - -#ifdef __cplusplus -extern "C" { -#endif - -BOOL WINAPI WinHttpAddRequestHeaders(HINTERNET,LPCWSTR,DWORD,DWORD); -BOOL WINAPI WinHttpDetectAutoProxyConfigUrl(DWORD,LPWSTR*); -BOOL WINAPI WinHttpCheckPlatform(void); -BOOL WINAPI WinHttpCloseHandle(HINTERNET); -HINTERNET WINAPI WinHttpConnect(HINTERNET,LPCWSTR,INTERNET_PORT,DWORD); -BOOL WINAPI WinHttpCrackUrl(LPCWSTR,DWORD,DWORD,LPURL_COMPONENTS); -BOOL WINAPI WinHttpCreateUrl(LPURL_COMPONENTS,DWORD,LPWSTR,LPDWORD); -BOOL WINAPI WinHttpGetDefaultProxyConfiguration(WINHTTP_PROXY_INFO*); -BOOL WINAPI WinHttpGetIEProxyConfigForCurrentUser(WINHTTP_CURRENT_USER_IE_PROXY_CONFIG*); -BOOL WINAPI WinHttpGetProxyForUrl(HINTERNET,LPCWSTR,WINHTTP_AUTOPROXY_OPTIONS*,WINHTTP_PROXY_INFO*); -HINTERNET WINAPI WinHttpOpen(LPCWSTR,DWORD,LPCWSTR,LPCWSTR,DWORD); -HINTERNET WINAPI WinHttpOpenRequest(HINTERNET,LPCWSTR,LPCWSTR,LPCWSTR,LPCWSTR,LPCWSTR*,DWORD); -BOOL WINAPI WinHttpQueryAuthParams(HINTERNET,DWORD,LPVOID*); -BOOL WINAPI WinHttpQueryAuthSchemes(HINTERNET,LPDWORD,LPDWORD,LPDWORD); -BOOL WINAPI WinHttpQueryDataAvailable(HINTERNET,LPDWORD); -BOOL WINAPI WinHttpQueryHeaders(HINTERNET,DWORD,LPCWSTR,LPVOID,LPDWORD,LPDWORD); -BOOL WINAPI WinHttpQueryOption(HINTERNET,DWORD,LPVOID,LPDWORD); -BOOL WINAPI WinHttpReadData(HINTERNET,LPVOID,DWORD,LPDWORD); -BOOL WINAPI WinHttpReceiveResponse(HINTERNET,LPVOID); -BOOL WINAPI WinHttpSendRequest(HINTERNET,LPCWSTR,DWORD,LPVOID,DWORD,DWORD,DWORD_PTR); -BOOL WINAPI WinHttpSetDefaultProxyConfiguration(WINHTTP_PROXY_INFO*); -BOOL WINAPI WinHttpSetCredentials(HINTERNET,DWORD,DWORD,LPCWSTR,LPCWSTR,LPVOID); -BOOL WINAPI WinHttpSetOption(HINTERNET,DWORD,LPVOID,DWORD); -WINHTTP_STATUS_CALLBACK WINAPI WinHttpSetStatusCallback(HINTERNET,WINHTTP_STATUS_CALLBACK,DWORD,DWORD_PTR); -BOOL WINAPI WinHttpSetTimeouts(HINTERNET,int,int,int,int); -BOOL WINAPI WinHttpTimeFromSystemTime(const SYSTEMTIME *,LPWSTR); -BOOL WINAPI WinHttpTimeToSystemTime(LPCWSTR,SYSTEMTIME*); -BOOL WINAPI WinHttpWriteData(HINTERNET,LPCVOID,DWORD,LPDWORD); - -#ifdef __cplusplus -} -#endif - -#include - -#endif /* __WINE_WINHTTP_H */ - -#else - -#include_next - -#endif diff --git a/deps/winhttp/winhttp64.def b/deps/winhttp/winhttp64.def deleted file mode 100644 index bfad3a0..0000000 --- a/deps/winhttp/winhttp64.def +++ /dev/null @@ -1,29 +0,0 @@ -LIBRARY WINHTTP -EXPORTS -WinHttpAddRequestHeaders -WinHttpCheckPlatform -WinHttpCloseHandle -WinHttpConnect -WinHttpCrackUrl -WinHttpCreateUrl -WinHttpDetectAutoProxyConfigUrl -WinHttpGetDefaultProxyConfiguration -WinHttpGetIEProxyConfigForCurrentUser -WinHttpGetProxyForUrl -WinHttpOpen -WinHttpOpenRequest -WinHttpQueryAuthSchemes -WinHttpQueryDataAvailable -WinHttpQueryHeaders -WinHttpQueryOption -WinHttpReadData -WinHttpReceiveResponse -WinHttpSendRequest -WinHttpSetCredentials -WinHttpSetDefaultProxyConfiguration -WinHttpSetOption -WinHttpSetStatusCallback -WinHttpSetTimeouts -WinHttpTimeFromSystemTime -WinHttpTimeToSystemTime -WinHttpWriteData diff --git a/deps/zlib/adler32.c b/deps/zlib/adler32.c deleted file mode 100644 index d0be438..0000000 --- a/deps/zlib/adler32.c +++ /dev/null @@ -1,186 +0,0 @@ -/* adler32.c -- compute the Adler-32 checksum of a data stream - * Copyright (C) 1995-2011, 2016 Mark Adler - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -/* @(#) $Id$ */ - -#include "zutil.h" - -local uLong adler32_combine_ OF((uLong adler1, uLong adler2, z_off64_t len2)); - -#define BASE 65521U /* largest prime smaller than 65536 */ -#define NMAX 5552 -/* NMAX is the largest n such that 255n(n+1)/2 + (n+1)(BASE-1) <= 2^32-1 */ - -#define DO1(buf,i) {adler += (buf)[i]; sum2 += adler;} -#define DO2(buf,i) DO1(buf,i); DO1(buf,i+1); -#define DO4(buf,i) DO2(buf,i); DO2(buf,i+2); -#define DO8(buf,i) DO4(buf,i); DO4(buf,i+4); -#define DO16(buf) DO8(buf,0); DO8(buf,8); - -/* use NO_DIVIDE if your processor does not do division in hardware -- - try it both ways to see which is faster */ -#ifdef NO_DIVIDE -/* note that this assumes BASE is 65521, where 65536 % 65521 == 15 - (thank you to John Reiser for pointing this out) */ -# define CHOP(a) \ - do { \ - unsigned long tmp = a >> 16; \ - a &= 0xffffUL; \ - a += (tmp << 4) - tmp; \ - } while (0) -# define MOD28(a) \ - do { \ - CHOP(a); \ - if (a >= BASE) a -= BASE; \ - } while (0) -# define MOD(a) \ - do { \ - CHOP(a); \ - MOD28(a); \ - } while (0) -# define MOD63(a) \ - do { /* this assumes a is not negative */ \ - z_off64_t tmp = a >> 32; \ - a &= 0xffffffffL; \ - a += (tmp << 8) - (tmp << 5) + tmp; \ - tmp = a >> 16; \ - a &= 0xffffL; \ - a += (tmp << 4) - tmp; \ - tmp = a >> 16; \ - a &= 0xffffL; \ - a += (tmp << 4) - tmp; \ - if (a >= BASE) a -= BASE; \ - } while (0) -#else -# define MOD(a) a %= BASE -# define MOD28(a) a %= BASE -# define MOD63(a) a %= BASE -#endif - -/* ========================================================================= */ -uLong ZEXPORT adler32_z(adler, buf, len) - uLong adler; - const Bytef *buf; - z_size_t len; -{ - unsigned long sum2; - unsigned n; - - /* split Adler-32 into component sums */ - sum2 = (adler >> 16) & 0xffff; - adler &= 0xffff; - - /* in case user likes doing a byte at a time, keep it fast */ - if (len == 1) { - adler += buf[0]; - if (adler >= BASE) - adler -= BASE; - sum2 += adler; - if (sum2 >= BASE) - sum2 -= BASE; - return adler | (sum2 << 16); - } - - /* initial Adler-32 value (deferred check for len == 1 speed) */ - if (buf == Z_NULL) - return 1L; - - /* in case short lengths are provided, keep it somewhat fast */ - if (len < 16) { - while (len--) { - adler += *buf++; - sum2 += adler; - } - if (adler >= BASE) - adler -= BASE; - MOD28(sum2); /* only added so many BASE's */ - return adler | (sum2 << 16); - } - - /* do length NMAX blocks -- requires just one modulo operation */ - while (len >= NMAX) { - len -= NMAX; - n = NMAX / 16; /* NMAX is divisible by 16 */ - do { - DO16(buf); /* 16 sums unrolled */ - buf += 16; - } while (--n); - MOD(adler); - MOD(sum2); - } - - /* do remaining bytes (less than NMAX, still just one modulo) */ - if (len) { /* avoid modulos if none remaining */ - while (len >= 16) { - len -= 16; - DO16(buf); - buf += 16; - } - while (len--) { - adler += *buf++; - sum2 += adler; - } - MOD(adler); - MOD(sum2); - } - - /* return recombined sums */ - return adler | (sum2 << 16); -} - -/* ========================================================================= */ -uLong ZEXPORT adler32(adler, buf, len) - uLong adler; - const Bytef *buf; - uInt len; -{ - return adler32_z(adler, buf, len); -} - -/* ========================================================================= */ -local uLong adler32_combine_(adler1, adler2, len2) - uLong adler1; - uLong adler2; - z_off64_t len2; -{ - unsigned long sum1; - unsigned long sum2; - unsigned rem; - - /* for negative len, return invalid adler32 as a clue for debugging */ - if (len2 < 0) - return 0xffffffffUL; - - /* the derivation of this formula is left as an exercise for the reader */ - MOD63(len2); /* assumes len2 >= 0 */ - rem = (unsigned)len2; - sum1 = adler1 & 0xffff; - sum2 = rem * sum1; - MOD(sum2); - sum1 += (adler2 & 0xffff) + BASE - 1; - sum2 += ((adler1 >> 16) & 0xffff) + ((adler2 >> 16) & 0xffff) + BASE - rem; - if (sum1 >= BASE) sum1 -= BASE; - if (sum1 >= BASE) sum1 -= BASE; - if (sum2 >= ((unsigned long)BASE << 1)) sum2 -= ((unsigned long)BASE << 1); - if (sum2 >= BASE) sum2 -= BASE; - return sum1 | (sum2 << 16); -} - -/* ========================================================================= */ -uLong ZEXPORT adler32_combine(adler1, adler2, len2) - uLong adler1; - uLong adler2; - z_off_t len2; -{ - return adler32_combine_(adler1, adler2, len2); -} - -uLong ZEXPORT adler32_combine64(adler1, adler2, len2) - uLong adler1; - uLong adler2; - z_off64_t len2; -{ - return adler32_combine_(adler1, adler2, len2); -} diff --git a/deps/zlib/crc32.c b/deps/zlib/crc32.c deleted file mode 100644 index 9580440..0000000 --- a/deps/zlib/crc32.c +++ /dev/null @@ -1,442 +0,0 @@ -/* crc32.c -- compute the CRC-32 of a data stream - * Copyright (C) 1995-2006, 2010, 2011, 2012, 2016 Mark Adler - * For conditions of distribution and use, see copyright notice in zlib.h - * - * Thanks to Rodney Brown for his contribution of faster - * CRC methods: exclusive-oring 32 bits of data at a time, and pre-computing - * tables for updating the shift register in one step with three exclusive-ors - * instead of four steps with four exclusive-ors. This results in about a - * factor of two increase in speed on a Power PC G4 (PPC7455) using gcc -O3. - */ - -/* @(#) $Id$ */ - -/* - Note on the use of DYNAMIC_CRC_TABLE: there is no mutex or semaphore - protection on the static variables used to control the first-use generation - of the crc tables. Therefore, if you #define DYNAMIC_CRC_TABLE, you should - first call get_crc_table() to initialize the tables before allowing more than - one thread to use crc32(). - - DYNAMIC_CRC_TABLE and MAKECRCH can be #defined to write out crc32.h. - */ - -#ifdef MAKECRCH -# include -# ifndef DYNAMIC_CRC_TABLE -# define DYNAMIC_CRC_TABLE -# endif /* !DYNAMIC_CRC_TABLE */ -#endif /* MAKECRCH */ - -#include "zutil.h" /* for STDC and FAR definitions */ - -/* Definitions for doing the crc four data bytes at a time. */ -#if !defined(NOBYFOUR) && defined(Z_U4) -# define BYFOUR -#endif -#ifdef BYFOUR - local unsigned long crc32_little OF((unsigned long, - const unsigned char FAR *, z_size_t)); - local unsigned long crc32_big OF((unsigned long, - const unsigned char FAR *, z_size_t)); -# define TBLS 8 -#else -# define TBLS 1 -#endif /* BYFOUR */ - -/* Local functions for crc concatenation */ -local unsigned long gf2_matrix_times OF((unsigned long *mat, - unsigned long vec)); -local void gf2_matrix_square OF((unsigned long *square, unsigned long *mat)); -local uLong crc32_combine_ OF((uLong crc1, uLong crc2, z_off64_t len2)); - - -#ifdef DYNAMIC_CRC_TABLE - -local volatile int crc_table_empty = 1; -local z_crc_t FAR crc_table[TBLS][256]; -local void make_crc_table OF((void)); -#ifdef MAKECRCH - local void write_table OF((FILE *, const z_crc_t FAR *)); -#endif /* MAKECRCH */ -/* - Generate tables for a byte-wise 32-bit CRC calculation on the polynomial: - x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x+1. - - Polynomials over GF(2) are represented in binary, one bit per coefficient, - with the lowest powers in the most significant bit. Then adding polynomials - is just exclusive-or, and multiplying a polynomial by x is a right shift by - one. If we call the above polynomial p, and represent a byte as the - polynomial q, also with the lowest power in the most significant bit (so the - byte 0xb1 is the polynomial x^7+x^3+x+1), then the CRC is (q*x^32) mod p, - where a mod b means the remainder after dividing a by b. - - This calculation is done using the shift-register method of multiplying and - taking the remainder. The register is initialized to zero, and for each - incoming bit, x^32 is added mod p to the register if the bit is a one (where - x^32 mod p is p+x^32 = x^26+...+1), and the register is multiplied mod p by - x (which is shifting right by one and adding x^32 mod p if the bit shifted - out is a one). We start with the highest power (least significant bit) of - q and repeat for all eight bits of q. - - The first table is simply the CRC of all possible eight bit values. This is - all the information needed to generate CRCs on data a byte at a time for all - combinations of CRC register values and incoming bytes. The remaining tables - allow for word-at-a-time CRC calculation for both big-endian and little- - endian machines, where a word is four bytes. -*/ -local void make_crc_table() -{ - z_crc_t c; - int n, k; - z_crc_t poly; /* polynomial exclusive-or pattern */ - /* terms of polynomial defining this crc (except x^32): */ - static volatile int first = 1; /* flag to limit concurrent making */ - static const unsigned char p[] = {0,1,2,4,5,7,8,10,11,12,16,22,23,26}; - - /* See if another task is already doing this (not thread-safe, but better - than nothing -- significantly reduces duration of vulnerability in - case the advice about DYNAMIC_CRC_TABLE is ignored) */ - if (first) { - first = 0; - - /* make exclusive-or pattern from polynomial (0xedb88320UL) */ - poly = 0; - for (n = 0; n < (int)(sizeof(p)/sizeof(unsigned char)); n++) - poly |= (z_crc_t)1 << (31 - p[n]); - - /* generate a crc for every 8-bit value */ - for (n = 0; n < 256; n++) { - c = (z_crc_t)n; - for (k = 0; k < 8; k++) - c = c & 1 ? poly ^ (c >> 1) : c >> 1; - crc_table[0][n] = c; - } - -#ifdef BYFOUR - /* generate crc for each value followed by one, two, and three zeros, - and then the byte reversal of those as well as the first table */ - for (n = 0; n < 256; n++) { - c = crc_table[0][n]; - crc_table[4][n] = ZSWAP32(c); - for (k = 1; k < 4; k++) { - c = crc_table[0][c & 0xff] ^ (c >> 8); - crc_table[k][n] = c; - crc_table[k + 4][n] = ZSWAP32(c); - } - } -#endif /* BYFOUR */ - - crc_table_empty = 0; - } - else { /* not first */ - /* wait for the other guy to finish (not efficient, but rare) */ - while (crc_table_empty) - ; - } - -#ifdef MAKECRCH - /* write out CRC tables to crc32.h */ - { - FILE *out; - - out = fopen("crc32.h", "w"); - if (out == NULL) return; - fprintf(out, "/* crc32.h -- tables for rapid CRC calculation\n"); - fprintf(out, " * Generated automatically by crc32.c\n */\n\n"); - fprintf(out, "local const z_crc_t FAR "); - fprintf(out, "crc_table[TBLS][256] =\n{\n {\n"); - write_table(out, crc_table[0]); -# ifdef BYFOUR - fprintf(out, "#ifdef BYFOUR\n"); - for (k = 1; k < 8; k++) { - fprintf(out, " },\n {\n"); - write_table(out, crc_table[k]); - } - fprintf(out, "#endif\n"); -# endif /* BYFOUR */ - fprintf(out, " }\n};\n"); - fclose(out); - } -#endif /* MAKECRCH */ -} - -#ifdef MAKECRCH -local void write_table(out, table) - FILE *out; - const z_crc_t FAR *table; -{ - int n; - - for (n = 0; n < 256; n++) - fprintf(out, "%s0x%08lxUL%s", n % 5 ? "" : " ", - (unsigned long)(table[n]), - n == 255 ? "\n" : (n % 5 == 4 ? ",\n" : ", ")); -} -#endif /* MAKECRCH */ - -#else /* !DYNAMIC_CRC_TABLE */ -/* ======================================================================== - * Tables of CRC-32s of all single-byte values, made by make_crc_table(). - */ -#include "crc32.h" -#endif /* DYNAMIC_CRC_TABLE */ - -/* ========================================================================= - * This function can be used by asm versions of crc32() - */ -const z_crc_t FAR * ZEXPORT get_crc_table() -{ -#ifdef DYNAMIC_CRC_TABLE - if (crc_table_empty) - make_crc_table(); -#endif /* DYNAMIC_CRC_TABLE */ - return (const z_crc_t FAR *)crc_table; -} - -/* ========================================================================= */ -#define DO1 crc = crc_table[0][((int)crc ^ (*buf++)) & 0xff] ^ (crc >> 8) -#define DO8 DO1; DO1; DO1; DO1; DO1; DO1; DO1; DO1 - -/* ========================================================================= */ -unsigned long ZEXPORT crc32_z(crc, buf, len) - unsigned long crc; - const unsigned char FAR *buf; - z_size_t len; -{ - if (buf == Z_NULL) return 0UL; - -#ifdef DYNAMIC_CRC_TABLE - if (crc_table_empty) - make_crc_table(); -#endif /* DYNAMIC_CRC_TABLE */ - -#ifdef BYFOUR - if (sizeof(void *) == sizeof(ptrdiff_t)) { - z_crc_t endian; - - endian = 1; - if (*((unsigned char *)(&endian))) - return crc32_little(crc, buf, len); - else - return crc32_big(crc, buf, len); - } -#endif /* BYFOUR */ - crc = crc ^ 0xffffffffUL; - while (len >= 8) { - DO8; - len -= 8; - } - if (len) do { - DO1; - } while (--len); - return crc ^ 0xffffffffUL; -} - -/* ========================================================================= */ -unsigned long ZEXPORT crc32(crc, buf, len) - unsigned long crc; - const unsigned char FAR *buf; - uInt len; -{ - return crc32_z(crc, buf, len); -} - -#ifdef BYFOUR - -/* - This BYFOUR code accesses the passed unsigned char * buffer with a 32-bit - integer pointer type. This violates the strict aliasing rule, where a - compiler can assume, for optimization purposes, that two pointers to - fundamentally different types won't ever point to the same memory. This can - manifest as a problem only if one of the pointers is written to. This code - only reads from those pointers. So long as this code remains isolated in - this compilation unit, there won't be a problem. For this reason, this code - should not be copied and pasted into a compilation unit in which other code - writes to the buffer that is passed to these routines. - */ - -/* ========================================================================= */ -#define DOLIT4 c ^= *buf4++; \ - c = crc_table[3][c & 0xff] ^ crc_table[2][(c >> 8) & 0xff] ^ \ - crc_table[1][(c >> 16) & 0xff] ^ crc_table[0][c >> 24] -#define DOLIT32 DOLIT4; DOLIT4; DOLIT4; DOLIT4; DOLIT4; DOLIT4; DOLIT4; DOLIT4 - -/* ========================================================================= */ -local unsigned long crc32_little(crc, buf, len) - unsigned long crc; - const unsigned char FAR *buf; - z_size_t len; -{ - register z_crc_t c; - register const z_crc_t FAR *buf4; - - c = (z_crc_t)crc; - c = ~c; - while (len && ((ptrdiff_t)buf & 3)) { - c = crc_table[0][(c ^ *buf++) & 0xff] ^ (c >> 8); - len--; - } - - buf4 = (const z_crc_t FAR *)(const void FAR *)buf; - while (len >= 32) { - DOLIT32; - len -= 32; - } - while (len >= 4) { - DOLIT4; - len -= 4; - } - buf = (const unsigned char FAR *)buf4; - - if (len) do { - c = crc_table[0][(c ^ *buf++) & 0xff] ^ (c >> 8); - } while (--len); - c = ~c; - return (unsigned long)c; -} - -/* ========================================================================= */ -#define DOBIG4 c ^= *buf4++; \ - c = crc_table[4][c & 0xff] ^ crc_table[5][(c >> 8) & 0xff] ^ \ - crc_table[6][(c >> 16) & 0xff] ^ crc_table[7][c >> 24] -#define DOBIG32 DOBIG4; DOBIG4; DOBIG4; DOBIG4; DOBIG4; DOBIG4; DOBIG4; DOBIG4 - -/* ========================================================================= */ -local unsigned long crc32_big(crc, buf, len) - unsigned long crc; - const unsigned char FAR *buf; - z_size_t len; -{ - register z_crc_t c; - register const z_crc_t FAR *buf4; - - c = ZSWAP32((z_crc_t)crc); - c = ~c; - while (len && ((ptrdiff_t)buf & 3)) { - c = crc_table[4][(c >> 24) ^ *buf++] ^ (c << 8); - len--; - } - - buf4 = (const z_crc_t FAR *)(const void FAR *)buf; - while (len >= 32) { - DOBIG32; - len -= 32; - } - while (len >= 4) { - DOBIG4; - len -= 4; - } - buf = (const unsigned char FAR *)buf4; - - if (len) do { - c = crc_table[4][(c >> 24) ^ *buf++] ^ (c << 8); - } while (--len); - c = ~c; - return (unsigned long)(ZSWAP32(c)); -} - -#endif /* BYFOUR */ - -#define GF2_DIM 32 /* dimension of GF(2) vectors (length of CRC) */ - -/* ========================================================================= */ -local unsigned long gf2_matrix_times(mat, vec) - unsigned long *mat; - unsigned long vec; -{ - unsigned long sum; - - sum = 0; - while (vec) { - if (vec & 1) - sum ^= *mat; - vec >>= 1; - mat++; - } - return sum; -} - -/* ========================================================================= */ -local void gf2_matrix_square(square, mat) - unsigned long *square; - unsigned long *mat; -{ - int n; - - for (n = 0; n < GF2_DIM; n++) - square[n] = gf2_matrix_times(mat, mat[n]); -} - -/* ========================================================================= */ -local uLong crc32_combine_(crc1, crc2, len2) - uLong crc1; - uLong crc2; - z_off64_t len2; -{ - int n; - unsigned long row; - unsigned long even[GF2_DIM]; /* even-power-of-two zeros operator */ - unsigned long odd[GF2_DIM]; /* odd-power-of-two zeros operator */ - - /* degenerate case (also disallow negative lengths) */ - if (len2 <= 0) - return crc1; - - /* put operator for one zero bit in odd */ - odd[0] = 0xedb88320UL; /* CRC-32 polynomial */ - row = 1; - for (n = 1; n < GF2_DIM; n++) { - odd[n] = row; - row <<= 1; - } - - /* put operator for two zero bits in even */ - gf2_matrix_square(even, odd); - - /* put operator for four zero bits in odd */ - gf2_matrix_square(odd, even); - - /* apply len2 zeros to crc1 (first square will put the operator for one - zero byte, eight zero bits, in even) */ - do { - /* apply zeros operator for this bit of len2 */ - gf2_matrix_square(even, odd); - if (len2 & 1) - crc1 = gf2_matrix_times(even, crc1); - len2 >>= 1; - - /* if no more bits set, then done */ - if (len2 == 0) - break; - - /* another iteration of the loop with odd and even swapped */ - gf2_matrix_square(odd, even); - if (len2 & 1) - crc1 = gf2_matrix_times(odd, crc1); - len2 >>= 1; - - /* if no more bits set, then done */ - } while (len2 != 0); - - /* return combined crc */ - crc1 ^= crc2; - return crc1; -} - -/* ========================================================================= */ -uLong ZEXPORT crc32_combine(crc1, crc2, len2) - uLong crc1; - uLong crc2; - z_off_t len2; -{ - return crc32_combine_(crc1, crc2, len2); -} - -uLong ZEXPORT crc32_combine64(crc1, crc2, len2) - uLong crc1; - uLong crc2; - z_off64_t len2; -{ - return crc32_combine_(crc1, crc2, len2); -} diff --git a/deps/zlib/crc32.h b/deps/zlib/crc32.h deleted file mode 100644 index 9e0c778..0000000 --- a/deps/zlib/crc32.h +++ /dev/null @@ -1,441 +0,0 @@ -/* crc32.h -- tables for rapid CRC calculation - * Generated automatically by crc32.c - */ - -local const z_crc_t FAR crc_table[TBLS][256] = -{ - { - 0x00000000UL, 0x77073096UL, 0xee0e612cUL, 0x990951baUL, 0x076dc419UL, - 0x706af48fUL, 0xe963a535UL, 0x9e6495a3UL, 0x0edb8832UL, 0x79dcb8a4UL, - 0xe0d5e91eUL, 0x97d2d988UL, 0x09b64c2bUL, 0x7eb17cbdUL, 0xe7b82d07UL, - 0x90bf1d91UL, 0x1db71064UL, 0x6ab020f2UL, 0xf3b97148UL, 0x84be41deUL, - 0x1adad47dUL, 0x6ddde4ebUL, 0xf4d4b551UL, 0x83d385c7UL, 0x136c9856UL, - 0x646ba8c0UL, 0xfd62f97aUL, 0x8a65c9ecUL, 0x14015c4fUL, 0x63066cd9UL, - 0xfa0f3d63UL, 0x8d080df5UL, 0x3b6e20c8UL, 0x4c69105eUL, 0xd56041e4UL, - 0xa2677172UL, 0x3c03e4d1UL, 0x4b04d447UL, 0xd20d85fdUL, 0xa50ab56bUL, - 0x35b5a8faUL, 0x42b2986cUL, 0xdbbbc9d6UL, 0xacbcf940UL, 0x32d86ce3UL, - 0x45df5c75UL, 0xdcd60dcfUL, 0xabd13d59UL, 0x26d930acUL, 0x51de003aUL, - 0xc8d75180UL, 0xbfd06116UL, 0x21b4f4b5UL, 0x56b3c423UL, 0xcfba9599UL, - 0xb8bda50fUL, 0x2802b89eUL, 0x5f058808UL, 0xc60cd9b2UL, 0xb10be924UL, - 0x2f6f7c87UL, 0x58684c11UL, 0xc1611dabUL, 0xb6662d3dUL, 0x76dc4190UL, - 0x01db7106UL, 0x98d220bcUL, 0xefd5102aUL, 0x71b18589UL, 0x06b6b51fUL, - 0x9fbfe4a5UL, 0xe8b8d433UL, 0x7807c9a2UL, 0x0f00f934UL, 0x9609a88eUL, - 0xe10e9818UL, 0x7f6a0dbbUL, 0x086d3d2dUL, 0x91646c97UL, 0xe6635c01UL, - 0x6b6b51f4UL, 0x1c6c6162UL, 0x856530d8UL, 0xf262004eUL, 0x6c0695edUL, - 0x1b01a57bUL, 0x8208f4c1UL, 0xf50fc457UL, 0x65b0d9c6UL, 0x12b7e950UL, - 0x8bbeb8eaUL, 0xfcb9887cUL, 0x62dd1ddfUL, 0x15da2d49UL, 0x8cd37cf3UL, - 0xfbd44c65UL, 0x4db26158UL, 0x3ab551ceUL, 0xa3bc0074UL, 0xd4bb30e2UL, - 0x4adfa541UL, 0x3dd895d7UL, 0xa4d1c46dUL, 0xd3d6f4fbUL, 0x4369e96aUL, - 0x346ed9fcUL, 0xad678846UL, 0xda60b8d0UL, 0x44042d73UL, 0x33031de5UL, - 0xaa0a4c5fUL, 0xdd0d7cc9UL, 0x5005713cUL, 0x270241aaUL, 0xbe0b1010UL, - 0xc90c2086UL, 0x5768b525UL, 0x206f85b3UL, 0xb966d409UL, 0xce61e49fUL, - 0x5edef90eUL, 0x29d9c998UL, 0xb0d09822UL, 0xc7d7a8b4UL, 0x59b33d17UL, - 0x2eb40d81UL, 0xb7bd5c3bUL, 0xc0ba6cadUL, 0xedb88320UL, 0x9abfb3b6UL, - 0x03b6e20cUL, 0x74b1d29aUL, 0xead54739UL, 0x9dd277afUL, 0x04db2615UL, - 0x73dc1683UL, 0xe3630b12UL, 0x94643b84UL, 0x0d6d6a3eUL, 0x7a6a5aa8UL, - 0xe40ecf0bUL, 0x9309ff9dUL, 0x0a00ae27UL, 0x7d079eb1UL, 0xf00f9344UL, - 0x8708a3d2UL, 0x1e01f268UL, 0x6906c2feUL, 0xf762575dUL, 0x806567cbUL, - 0x196c3671UL, 0x6e6b06e7UL, 0xfed41b76UL, 0x89d32be0UL, 0x10da7a5aUL, - 0x67dd4accUL, 0xf9b9df6fUL, 0x8ebeeff9UL, 0x17b7be43UL, 0x60b08ed5UL, - 0xd6d6a3e8UL, 0xa1d1937eUL, 0x38d8c2c4UL, 0x4fdff252UL, 0xd1bb67f1UL, - 0xa6bc5767UL, 0x3fb506ddUL, 0x48b2364bUL, 0xd80d2bdaUL, 0xaf0a1b4cUL, - 0x36034af6UL, 0x41047a60UL, 0xdf60efc3UL, 0xa867df55UL, 0x316e8eefUL, - 0x4669be79UL, 0xcb61b38cUL, 0xbc66831aUL, 0x256fd2a0UL, 0x5268e236UL, - 0xcc0c7795UL, 0xbb0b4703UL, 0x220216b9UL, 0x5505262fUL, 0xc5ba3bbeUL, - 0xb2bd0b28UL, 0x2bb45a92UL, 0x5cb36a04UL, 0xc2d7ffa7UL, 0xb5d0cf31UL, - 0x2cd99e8bUL, 0x5bdeae1dUL, 0x9b64c2b0UL, 0xec63f226UL, 0x756aa39cUL, - 0x026d930aUL, 0x9c0906a9UL, 0xeb0e363fUL, 0x72076785UL, 0x05005713UL, - 0x95bf4a82UL, 0xe2b87a14UL, 0x7bb12baeUL, 0x0cb61b38UL, 0x92d28e9bUL, - 0xe5d5be0dUL, 0x7cdcefb7UL, 0x0bdbdf21UL, 0x86d3d2d4UL, 0xf1d4e242UL, - 0x68ddb3f8UL, 0x1fda836eUL, 0x81be16cdUL, 0xf6b9265bUL, 0x6fb077e1UL, - 0x18b74777UL, 0x88085ae6UL, 0xff0f6a70UL, 0x66063bcaUL, 0x11010b5cUL, - 0x8f659effUL, 0xf862ae69UL, 0x616bffd3UL, 0x166ccf45UL, 0xa00ae278UL, - 0xd70dd2eeUL, 0x4e048354UL, 0x3903b3c2UL, 0xa7672661UL, 0xd06016f7UL, - 0x4969474dUL, 0x3e6e77dbUL, 0xaed16a4aUL, 0xd9d65adcUL, 0x40df0b66UL, - 0x37d83bf0UL, 0xa9bcae53UL, 0xdebb9ec5UL, 0x47b2cf7fUL, 0x30b5ffe9UL, - 0xbdbdf21cUL, 0xcabac28aUL, 0x53b39330UL, 0x24b4a3a6UL, 0xbad03605UL, - 0xcdd70693UL, 0x54de5729UL, 0x23d967bfUL, 0xb3667a2eUL, 0xc4614ab8UL, - 0x5d681b02UL, 0x2a6f2b94UL, 0xb40bbe37UL, 0xc30c8ea1UL, 0x5a05df1bUL, - 0x2d02ef8dUL -#ifdef BYFOUR - }, - { - 0x00000000UL, 0x191b3141UL, 0x32366282UL, 0x2b2d53c3UL, 0x646cc504UL, - 0x7d77f445UL, 0x565aa786UL, 0x4f4196c7UL, 0xc8d98a08UL, 0xd1c2bb49UL, - 0xfaefe88aUL, 0xe3f4d9cbUL, 0xacb54f0cUL, 0xb5ae7e4dUL, 0x9e832d8eUL, - 0x87981ccfUL, 0x4ac21251UL, 0x53d92310UL, 0x78f470d3UL, 0x61ef4192UL, - 0x2eaed755UL, 0x37b5e614UL, 0x1c98b5d7UL, 0x05838496UL, 0x821b9859UL, - 0x9b00a918UL, 0xb02dfadbUL, 0xa936cb9aUL, 0xe6775d5dUL, 0xff6c6c1cUL, - 0xd4413fdfUL, 0xcd5a0e9eUL, 0x958424a2UL, 0x8c9f15e3UL, 0xa7b24620UL, - 0xbea97761UL, 0xf1e8e1a6UL, 0xe8f3d0e7UL, 0xc3de8324UL, 0xdac5b265UL, - 0x5d5daeaaUL, 0x44469febUL, 0x6f6bcc28UL, 0x7670fd69UL, 0x39316baeUL, - 0x202a5aefUL, 0x0b07092cUL, 0x121c386dUL, 0xdf4636f3UL, 0xc65d07b2UL, - 0xed705471UL, 0xf46b6530UL, 0xbb2af3f7UL, 0xa231c2b6UL, 0x891c9175UL, - 0x9007a034UL, 0x179fbcfbUL, 0x0e848dbaUL, 0x25a9de79UL, 0x3cb2ef38UL, - 0x73f379ffUL, 0x6ae848beUL, 0x41c51b7dUL, 0x58de2a3cUL, 0xf0794f05UL, - 0xe9627e44UL, 0xc24f2d87UL, 0xdb541cc6UL, 0x94158a01UL, 0x8d0ebb40UL, - 0xa623e883UL, 0xbf38d9c2UL, 0x38a0c50dUL, 0x21bbf44cUL, 0x0a96a78fUL, - 0x138d96ceUL, 0x5ccc0009UL, 0x45d73148UL, 0x6efa628bUL, 0x77e153caUL, - 0xbabb5d54UL, 0xa3a06c15UL, 0x888d3fd6UL, 0x91960e97UL, 0xded79850UL, - 0xc7cca911UL, 0xece1fad2UL, 0xf5facb93UL, 0x7262d75cUL, 0x6b79e61dUL, - 0x4054b5deUL, 0x594f849fUL, 0x160e1258UL, 0x0f152319UL, 0x243870daUL, - 0x3d23419bUL, 0x65fd6ba7UL, 0x7ce65ae6UL, 0x57cb0925UL, 0x4ed03864UL, - 0x0191aea3UL, 0x188a9fe2UL, 0x33a7cc21UL, 0x2abcfd60UL, 0xad24e1afUL, - 0xb43fd0eeUL, 0x9f12832dUL, 0x8609b26cUL, 0xc94824abUL, 0xd05315eaUL, - 0xfb7e4629UL, 0xe2657768UL, 0x2f3f79f6UL, 0x362448b7UL, 0x1d091b74UL, - 0x04122a35UL, 0x4b53bcf2UL, 0x52488db3UL, 0x7965de70UL, 0x607eef31UL, - 0xe7e6f3feUL, 0xfefdc2bfUL, 0xd5d0917cUL, 0xcccba03dUL, 0x838a36faUL, - 0x9a9107bbUL, 0xb1bc5478UL, 0xa8a76539UL, 0x3b83984bUL, 0x2298a90aUL, - 0x09b5fac9UL, 0x10aecb88UL, 0x5fef5d4fUL, 0x46f46c0eUL, 0x6dd93fcdUL, - 0x74c20e8cUL, 0xf35a1243UL, 0xea412302UL, 0xc16c70c1UL, 0xd8774180UL, - 0x9736d747UL, 0x8e2de606UL, 0xa500b5c5UL, 0xbc1b8484UL, 0x71418a1aUL, - 0x685abb5bUL, 0x4377e898UL, 0x5a6cd9d9UL, 0x152d4f1eUL, 0x0c367e5fUL, - 0x271b2d9cUL, 0x3e001cddUL, 0xb9980012UL, 0xa0833153UL, 0x8bae6290UL, - 0x92b553d1UL, 0xddf4c516UL, 0xc4eff457UL, 0xefc2a794UL, 0xf6d996d5UL, - 0xae07bce9UL, 0xb71c8da8UL, 0x9c31de6bUL, 0x852aef2aUL, 0xca6b79edUL, - 0xd37048acUL, 0xf85d1b6fUL, 0xe1462a2eUL, 0x66de36e1UL, 0x7fc507a0UL, - 0x54e85463UL, 0x4df36522UL, 0x02b2f3e5UL, 0x1ba9c2a4UL, 0x30849167UL, - 0x299fa026UL, 0xe4c5aeb8UL, 0xfdde9ff9UL, 0xd6f3cc3aUL, 0xcfe8fd7bUL, - 0x80a96bbcUL, 0x99b25afdUL, 0xb29f093eUL, 0xab84387fUL, 0x2c1c24b0UL, - 0x350715f1UL, 0x1e2a4632UL, 0x07317773UL, 0x4870e1b4UL, 0x516bd0f5UL, - 0x7a468336UL, 0x635db277UL, 0xcbfad74eUL, 0xd2e1e60fUL, 0xf9ccb5ccUL, - 0xe0d7848dUL, 0xaf96124aUL, 0xb68d230bUL, 0x9da070c8UL, 0x84bb4189UL, - 0x03235d46UL, 0x1a386c07UL, 0x31153fc4UL, 0x280e0e85UL, 0x674f9842UL, - 0x7e54a903UL, 0x5579fac0UL, 0x4c62cb81UL, 0x8138c51fUL, 0x9823f45eUL, - 0xb30ea79dUL, 0xaa1596dcUL, 0xe554001bUL, 0xfc4f315aUL, 0xd7626299UL, - 0xce7953d8UL, 0x49e14f17UL, 0x50fa7e56UL, 0x7bd72d95UL, 0x62cc1cd4UL, - 0x2d8d8a13UL, 0x3496bb52UL, 0x1fbbe891UL, 0x06a0d9d0UL, 0x5e7ef3ecUL, - 0x4765c2adUL, 0x6c48916eUL, 0x7553a02fUL, 0x3a1236e8UL, 0x230907a9UL, - 0x0824546aUL, 0x113f652bUL, 0x96a779e4UL, 0x8fbc48a5UL, 0xa4911b66UL, - 0xbd8a2a27UL, 0xf2cbbce0UL, 0xebd08da1UL, 0xc0fdde62UL, 0xd9e6ef23UL, - 0x14bce1bdUL, 0x0da7d0fcUL, 0x268a833fUL, 0x3f91b27eUL, 0x70d024b9UL, - 0x69cb15f8UL, 0x42e6463bUL, 0x5bfd777aUL, 0xdc656bb5UL, 0xc57e5af4UL, - 0xee530937UL, 0xf7483876UL, 0xb809aeb1UL, 0xa1129ff0UL, 0x8a3fcc33UL, - 0x9324fd72UL - }, - { - 0x00000000UL, 0x01c26a37UL, 0x0384d46eUL, 0x0246be59UL, 0x0709a8dcUL, - 0x06cbc2ebUL, 0x048d7cb2UL, 0x054f1685UL, 0x0e1351b8UL, 0x0fd13b8fUL, - 0x0d9785d6UL, 0x0c55efe1UL, 0x091af964UL, 0x08d89353UL, 0x0a9e2d0aUL, - 0x0b5c473dUL, 0x1c26a370UL, 0x1de4c947UL, 0x1fa2771eUL, 0x1e601d29UL, - 0x1b2f0bacUL, 0x1aed619bUL, 0x18abdfc2UL, 0x1969b5f5UL, 0x1235f2c8UL, - 0x13f798ffUL, 0x11b126a6UL, 0x10734c91UL, 0x153c5a14UL, 0x14fe3023UL, - 0x16b88e7aUL, 0x177ae44dUL, 0x384d46e0UL, 0x398f2cd7UL, 0x3bc9928eUL, - 0x3a0bf8b9UL, 0x3f44ee3cUL, 0x3e86840bUL, 0x3cc03a52UL, 0x3d025065UL, - 0x365e1758UL, 0x379c7d6fUL, 0x35dac336UL, 0x3418a901UL, 0x3157bf84UL, - 0x3095d5b3UL, 0x32d36beaUL, 0x331101ddUL, 0x246be590UL, 0x25a98fa7UL, - 0x27ef31feUL, 0x262d5bc9UL, 0x23624d4cUL, 0x22a0277bUL, 0x20e69922UL, - 0x2124f315UL, 0x2a78b428UL, 0x2bbade1fUL, 0x29fc6046UL, 0x283e0a71UL, - 0x2d711cf4UL, 0x2cb376c3UL, 0x2ef5c89aUL, 0x2f37a2adUL, 0x709a8dc0UL, - 0x7158e7f7UL, 0x731e59aeUL, 0x72dc3399UL, 0x7793251cUL, 0x76514f2bUL, - 0x7417f172UL, 0x75d59b45UL, 0x7e89dc78UL, 0x7f4bb64fUL, 0x7d0d0816UL, - 0x7ccf6221UL, 0x798074a4UL, 0x78421e93UL, 0x7a04a0caUL, 0x7bc6cafdUL, - 0x6cbc2eb0UL, 0x6d7e4487UL, 0x6f38fadeUL, 0x6efa90e9UL, 0x6bb5866cUL, - 0x6a77ec5bUL, 0x68315202UL, 0x69f33835UL, 0x62af7f08UL, 0x636d153fUL, - 0x612bab66UL, 0x60e9c151UL, 0x65a6d7d4UL, 0x6464bde3UL, 0x662203baUL, - 0x67e0698dUL, 0x48d7cb20UL, 0x4915a117UL, 0x4b531f4eUL, 0x4a917579UL, - 0x4fde63fcUL, 0x4e1c09cbUL, 0x4c5ab792UL, 0x4d98dda5UL, 0x46c49a98UL, - 0x4706f0afUL, 0x45404ef6UL, 0x448224c1UL, 0x41cd3244UL, 0x400f5873UL, - 0x4249e62aUL, 0x438b8c1dUL, 0x54f16850UL, 0x55330267UL, 0x5775bc3eUL, - 0x56b7d609UL, 0x53f8c08cUL, 0x523aaabbUL, 0x507c14e2UL, 0x51be7ed5UL, - 0x5ae239e8UL, 0x5b2053dfUL, 0x5966ed86UL, 0x58a487b1UL, 0x5deb9134UL, - 0x5c29fb03UL, 0x5e6f455aUL, 0x5fad2f6dUL, 0xe1351b80UL, 0xe0f771b7UL, - 0xe2b1cfeeUL, 0xe373a5d9UL, 0xe63cb35cUL, 0xe7fed96bUL, 0xe5b86732UL, - 0xe47a0d05UL, 0xef264a38UL, 0xeee4200fUL, 0xeca29e56UL, 0xed60f461UL, - 0xe82fe2e4UL, 0xe9ed88d3UL, 0xebab368aUL, 0xea695cbdUL, 0xfd13b8f0UL, - 0xfcd1d2c7UL, 0xfe976c9eUL, 0xff5506a9UL, 0xfa1a102cUL, 0xfbd87a1bUL, - 0xf99ec442UL, 0xf85cae75UL, 0xf300e948UL, 0xf2c2837fUL, 0xf0843d26UL, - 0xf1465711UL, 0xf4094194UL, 0xf5cb2ba3UL, 0xf78d95faUL, 0xf64fffcdUL, - 0xd9785d60UL, 0xd8ba3757UL, 0xdafc890eUL, 0xdb3ee339UL, 0xde71f5bcUL, - 0xdfb39f8bUL, 0xddf521d2UL, 0xdc374be5UL, 0xd76b0cd8UL, 0xd6a966efUL, - 0xd4efd8b6UL, 0xd52db281UL, 0xd062a404UL, 0xd1a0ce33UL, 0xd3e6706aUL, - 0xd2241a5dUL, 0xc55efe10UL, 0xc49c9427UL, 0xc6da2a7eUL, 0xc7184049UL, - 0xc25756ccUL, 0xc3953cfbUL, 0xc1d382a2UL, 0xc011e895UL, 0xcb4dafa8UL, - 0xca8fc59fUL, 0xc8c97bc6UL, 0xc90b11f1UL, 0xcc440774UL, 0xcd866d43UL, - 0xcfc0d31aUL, 0xce02b92dUL, 0x91af9640UL, 0x906dfc77UL, 0x922b422eUL, - 0x93e92819UL, 0x96a63e9cUL, 0x976454abUL, 0x9522eaf2UL, 0x94e080c5UL, - 0x9fbcc7f8UL, 0x9e7eadcfUL, 0x9c381396UL, 0x9dfa79a1UL, 0x98b56f24UL, - 0x99770513UL, 0x9b31bb4aUL, 0x9af3d17dUL, 0x8d893530UL, 0x8c4b5f07UL, - 0x8e0de15eUL, 0x8fcf8b69UL, 0x8a809decUL, 0x8b42f7dbUL, 0x89044982UL, - 0x88c623b5UL, 0x839a6488UL, 0x82580ebfUL, 0x801eb0e6UL, 0x81dcdad1UL, - 0x8493cc54UL, 0x8551a663UL, 0x8717183aUL, 0x86d5720dUL, 0xa9e2d0a0UL, - 0xa820ba97UL, 0xaa6604ceUL, 0xaba46ef9UL, 0xaeeb787cUL, 0xaf29124bUL, - 0xad6fac12UL, 0xacadc625UL, 0xa7f18118UL, 0xa633eb2fUL, 0xa4755576UL, - 0xa5b73f41UL, 0xa0f829c4UL, 0xa13a43f3UL, 0xa37cfdaaUL, 0xa2be979dUL, - 0xb5c473d0UL, 0xb40619e7UL, 0xb640a7beUL, 0xb782cd89UL, 0xb2cddb0cUL, - 0xb30fb13bUL, 0xb1490f62UL, 0xb08b6555UL, 0xbbd72268UL, 0xba15485fUL, - 0xb853f606UL, 0xb9919c31UL, 0xbcde8ab4UL, 0xbd1ce083UL, 0xbf5a5edaUL, - 0xbe9834edUL - }, - { - 0x00000000UL, 0xb8bc6765UL, 0xaa09c88bUL, 0x12b5afeeUL, 0x8f629757UL, - 0x37def032UL, 0x256b5fdcUL, 0x9dd738b9UL, 0xc5b428efUL, 0x7d084f8aUL, - 0x6fbde064UL, 0xd7018701UL, 0x4ad6bfb8UL, 0xf26ad8ddUL, 0xe0df7733UL, - 0x58631056UL, 0x5019579fUL, 0xe8a530faUL, 0xfa109f14UL, 0x42acf871UL, - 0xdf7bc0c8UL, 0x67c7a7adUL, 0x75720843UL, 0xcdce6f26UL, 0x95ad7f70UL, - 0x2d111815UL, 0x3fa4b7fbUL, 0x8718d09eUL, 0x1acfe827UL, 0xa2738f42UL, - 0xb0c620acUL, 0x087a47c9UL, 0xa032af3eUL, 0x188ec85bUL, 0x0a3b67b5UL, - 0xb28700d0UL, 0x2f503869UL, 0x97ec5f0cUL, 0x8559f0e2UL, 0x3de59787UL, - 0x658687d1UL, 0xdd3ae0b4UL, 0xcf8f4f5aUL, 0x7733283fUL, 0xeae41086UL, - 0x525877e3UL, 0x40edd80dUL, 0xf851bf68UL, 0xf02bf8a1UL, 0x48979fc4UL, - 0x5a22302aUL, 0xe29e574fUL, 0x7f496ff6UL, 0xc7f50893UL, 0xd540a77dUL, - 0x6dfcc018UL, 0x359fd04eUL, 0x8d23b72bUL, 0x9f9618c5UL, 0x272a7fa0UL, - 0xbafd4719UL, 0x0241207cUL, 0x10f48f92UL, 0xa848e8f7UL, 0x9b14583dUL, - 0x23a83f58UL, 0x311d90b6UL, 0x89a1f7d3UL, 0x1476cf6aUL, 0xaccaa80fUL, - 0xbe7f07e1UL, 0x06c36084UL, 0x5ea070d2UL, 0xe61c17b7UL, 0xf4a9b859UL, - 0x4c15df3cUL, 0xd1c2e785UL, 0x697e80e0UL, 0x7bcb2f0eUL, 0xc377486bUL, - 0xcb0d0fa2UL, 0x73b168c7UL, 0x6104c729UL, 0xd9b8a04cUL, 0x446f98f5UL, - 0xfcd3ff90UL, 0xee66507eUL, 0x56da371bUL, 0x0eb9274dUL, 0xb6054028UL, - 0xa4b0efc6UL, 0x1c0c88a3UL, 0x81dbb01aUL, 0x3967d77fUL, 0x2bd27891UL, - 0x936e1ff4UL, 0x3b26f703UL, 0x839a9066UL, 0x912f3f88UL, 0x299358edUL, - 0xb4446054UL, 0x0cf80731UL, 0x1e4da8dfUL, 0xa6f1cfbaUL, 0xfe92dfecUL, - 0x462eb889UL, 0x549b1767UL, 0xec277002UL, 0x71f048bbUL, 0xc94c2fdeUL, - 0xdbf98030UL, 0x6345e755UL, 0x6b3fa09cUL, 0xd383c7f9UL, 0xc1366817UL, - 0x798a0f72UL, 0xe45d37cbUL, 0x5ce150aeUL, 0x4e54ff40UL, 0xf6e89825UL, - 0xae8b8873UL, 0x1637ef16UL, 0x048240f8UL, 0xbc3e279dUL, 0x21e91f24UL, - 0x99557841UL, 0x8be0d7afUL, 0x335cb0caUL, 0xed59b63bUL, 0x55e5d15eUL, - 0x47507eb0UL, 0xffec19d5UL, 0x623b216cUL, 0xda874609UL, 0xc832e9e7UL, - 0x708e8e82UL, 0x28ed9ed4UL, 0x9051f9b1UL, 0x82e4565fUL, 0x3a58313aUL, - 0xa78f0983UL, 0x1f336ee6UL, 0x0d86c108UL, 0xb53aa66dUL, 0xbd40e1a4UL, - 0x05fc86c1UL, 0x1749292fUL, 0xaff54e4aUL, 0x322276f3UL, 0x8a9e1196UL, - 0x982bbe78UL, 0x2097d91dUL, 0x78f4c94bUL, 0xc048ae2eUL, 0xd2fd01c0UL, - 0x6a4166a5UL, 0xf7965e1cUL, 0x4f2a3979UL, 0x5d9f9697UL, 0xe523f1f2UL, - 0x4d6b1905UL, 0xf5d77e60UL, 0xe762d18eUL, 0x5fdeb6ebUL, 0xc2098e52UL, - 0x7ab5e937UL, 0x680046d9UL, 0xd0bc21bcUL, 0x88df31eaUL, 0x3063568fUL, - 0x22d6f961UL, 0x9a6a9e04UL, 0x07bda6bdUL, 0xbf01c1d8UL, 0xadb46e36UL, - 0x15080953UL, 0x1d724e9aUL, 0xa5ce29ffUL, 0xb77b8611UL, 0x0fc7e174UL, - 0x9210d9cdUL, 0x2aacbea8UL, 0x38191146UL, 0x80a57623UL, 0xd8c66675UL, - 0x607a0110UL, 0x72cfaefeUL, 0xca73c99bUL, 0x57a4f122UL, 0xef189647UL, - 0xfdad39a9UL, 0x45115eccUL, 0x764dee06UL, 0xcef18963UL, 0xdc44268dUL, - 0x64f841e8UL, 0xf92f7951UL, 0x41931e34UL, 0x5326b1daUL, 0xeb9ad6bfUL, - 0xb3f9c6e9UL, 0x0b45a18cUL, 0x19f00e62UL, 0xa14c6907UL, 0x3c9b51beUL, - 0x842736dbUL, 0x96929935UL, 0x2e2efe50UL, 0x2654b999UL, 0x9ee8defcUL, - 0x8c5d7112UL, 0x34e11677UL, 0xa9362eceUL, 0x118a49abUL, 0x033fe645UL, - 0xbb838120UL, 0xe3e09176UL, 0x5b5cf613UL, 0x49e959fdUL, 0xf1553e98UL, - 0x6c820621UL, 0xd43e6144UL, 0xc68bceaaUL, 0x7e37a9cfUL, 0xd67f4138UL, - 0x6ec3265dUL, 0x7c7689b3UL, 0xc4caeed6UL, 0x591dd66fUL, 0xe1a1b10aUL, - 0xf3141ee4UL, 0x4ba87981UL, 0x13cb69d7UL, 0xab770eb2UL, 0xb9c2a15cUL, - 0x017ec639UL, 0x9ca9fe80UL, 0x241599e5UL, 0x36a0360bUL, 0x8e1c516eUL, - 0x866616a7UL, 0x3eda71c2UL, 0x2c6fde2cUL, 0x94d3b949UL, 0x090481f0UL, - 0xb1b8e695UL, 0xa30d497bUL, 0x1bb12e1eUL, 0x43d23e48UL, 0xfb6e592dUL, - 0xe9dbf6c3UL, 0x516791a6UL, 0xccb0a91fUL, 0x740cce7aUL, 0x66b96194UL, - 0xde0506f1UL - }, - { - 0x00000000UL, 0x96300777UL, 0x2c610eeeUL, 0xba510999UL, 0x19c46d07UL, - 0x8ff46a70UL, 0x35a563e9UL, 0xa395649eUL, 0x3288db0eUL, 0xa4b8dc79UL, - 0x1ee9d5e0UL, 0x88d9d297UL, 0x2b4cb609UL, 0xbd7cb17eUL, 0x072db8e7UL, - 0x911dbf90UL, 0x6410b71dUL, 0xf220b06aUL, 0x4871b9f3UL, 0xde41be84UL, - 0x7dd4da1aUL, 0xebe4dd6dUL, 0x51b5d4f4UL, 0xc785d383UL, 0x56986c13UL, - 0xc0a86b64UL, 0x7af962fdUL, 0xecc9658aUL, 0x4f5c0114UL, 0xd96c0663UL, - 0x633d0ffaUL, 0xf50d088dUL, 0xc8206e3bUL, 0x5e10694cUL, 0xe44160d5UL, - 0x727167a2UL, 0xd1e4033cUL, 0x47d4044bUL, 0xfd850dd2UL, 0x6bb50aa5UL, - 0xfaa8b535UL, 0x6c98b242UL, 0xd6c9bbdbUL, 0x40f9bcacUL, 0xe36cd832UL, - 0x755cdf45UL, 0xcf0dd6dcUL, 0x593dd1abUL, 0xac30d926UL, 0x3a00de51UL, - 0x8051d7c8UL, 0x1661d0bfUL, 0xb5f4b421UL, 0x23c4b356UL, 0x9995bacfUL, - 0x0fa5bdb8UL, 0x9eb80228UL, 0x0888055fUL, 0xb2d90cc6UL, 0x24e90bb1UL, - 0x877c6f2fUL, 0x114c6858UL, 0xab1d61c1UL, 0x3d2d66b6UL, 0x9041dc76UL, - 0x0671db01UL, 0xbc20d298UL, 0x2a10d5efUL, 0x8985b171UL, 0x1fb5b606UL, - 0xa5e4bf9fUL, 0x33d4b8e8UL, 0xa2c90778UL, 0x34f9000fUL, 0x8ea80996UL, - 0x18980ee1UL, 0xbb0d6a7fUL, 0x2d3d6d08UL, 0x976c6491UL, 0x015c63e6UL, - 0xf4516b6bUL, 0x62616c1cUL, 0xd8306585UL, 0x4e0062f2UL, 0xed95066cUL, - 0x7ba5011bUL, 0xc1f40882UL, 0x57c40ff5UL, 0xc6d9b065UL, 0x50e9b712UL, - 0xeab8be8bUL, 0x7c88b9fcUL, 0xdf1ddd62UL, 0x492dda15UL, 0xf37cd38cUL, - 0x654cd4fbUL, 0x5861b24dUL, 0xce51b53aUL, 0x7400bca3UL, 0xe230bbd4UL, - 0x41a5df4aUL, 0xd795d83dUL, 0x6dc4d1a4UL, 0xfbf4d6d3UL, 0x6ae96943UL, - 0xfcd96e34UL, 0x468867adUL, 0xd0b860daUL, 0x732d0444UL, 0xe51d0333UL, - 0x5f4c0aaaUL, 0xc97c0dddUL, 0x3c710550UL, 0xaa410227UL, 0x10100bbeUL, - 0x86200cc9UL, 0x25b56857UL, 0xb3856f20UL, 0x09d466b9UL, 0x9fe461ceUL, - 0x0ef9de5eUL, 0x98c9d929UL, 0x2298d0b0UL, 0xb4a8d7c7UL, 0x173db359UL, - 0x810db42eUL, 0x3b5cbdb7UL, 0xad6cbac0UL, 0x2083b8edUL, 0xb6b3bf9aUL, - 0x0ce2b603UL, 0x9ad2b174UL, 0x3947d5eaUL, 0xaf77d29dUL, 0x1526db04UL, - 0x8316dc73UL, 0x120b63e3UL, 0x843b6494UL, 0x3e6a6d0dUL, 0xa85a6a7aUL, - 0x0bcf0ee4UL, 0x9dff0993UL, 0x27ae000aUL, 0xb19e077dUL, 0x44930ff0UL, - 0xd2a30887UL, 0x68f2011eUL, 0xfec20669UL, 0x5d5762f7UL, 0xcb676580UL, - 0x71366c19UL, 0xe7066b6eUL, 0x761bd4feUL, 0xe02bd389UL, 0x5a7ada10UL, - 0xcc4add67UL, 0x6fdfb9f9UL, 0xf9efbe8eUL, 0x43beb717UL, 0xd58eb060UL, - 0xe8a3d6d6UL, 0x7e93d1a1UL, 0xc4c2d838UL, 0x52f2df4fUL, 0xf167bbd1UL, - 0x6757bca6UL, 0xdd06b53fUL, 0x4b36b248UL, 0xda2b0dd8UL, 0x4c1b0aafUL, - 0xf64a0336UL, 0x607a0441UL, 0xc3ef60dfUL, 0x55df67a8UL, 0xef8e6e31UL, - 0x79be6946UL, 0x8cb361cbUL, 0x1a8366bcUL, 0xa0d26f25UL, 0x36e26852UL, - 0x95770cccUL, 0x03470bbbUL, 0xb9160222UL, 0x2f260555UL, 0xbe3bbac5UL, - 0x280bbdb2UL, 0x925ab42bUL, 0x046ab35cUL, 0xa7ffd7c2UL, 0x31cfd0b5UL, - 0x8b9ed92cUL, 0x1daede5bUL, 0xb0c2649bUL, 0x26f263ecUL, 0x9ca36a75UL, - 0x0a936d02UL, 0xa906099cUL, 0x3f360eebUL, 0x85670772UL, 0x13570005UL, - 0x824abf95UL, 0x147ab8e2UL, 0xae2bb17bUL, 0x381bb60cUL, 0x9b8ed292UL, - 0x0dbed5e5UL, 0xb7efdc7cUL, 0x21dfdb0bUL, 0xd4d2d386UL, 0x42e2d4f1UL, - 0xf8b3dd68UL, 0x6e83da1fUL, 0xcd16be81UL, 0x5b26b9f6UL, 0xe177b06fUL, - 0x7747b718UL, 0xe65a0888UL, 0x706a0fffUL, 0xca3b0666UL, 0x5c0b0111UL, - 0xff9e658fUL, 0x69ae62f8UL, 0xd3ff6b61UL, 0x45cf6c16UL, 0x78e20aa0UL, - 0xeed20dd7UL, 0x5483044eUL, 0xc2b30339UL, 0x612667a7UL, 0xf71660d0UL, - 0x4d476949UL, 0xdb776e3eUL, 0x4a6ad1aeUL, 0xdc5ad6d9UL, 0x660bdf40UL, - 0xf03bd837UL, 0x53aebca9UL, 0xc59ebbdeUL, 0x7fcfb247UL, 0xe9ffb530UL, - 0x1cf2bdbdUL, 0x8ac2bacaUL, 0x3093b353UL, 0xa6a3b424UL, 0x0536d0baUL, - 0x9306d7cdUL, 0x2957de54UL, 0xbf67d923UL, 0x2e7a66b3UL, 0xb84a61c4UL, - 0x021b685dUL, 0x942b6f2aUL, 0x37be0bb4UL, 0xa18e0cc3UL, 0x1bdf055aUL, - 0x8def022dUL - }, - { - 0x00000000UL, 0x41311b19UL, 0x82623632UL, 0xc3532d2bUL, 0x04c56c64UL, - 0x45f4777dUL, 0x86a75a56UL, 0xc796414fUL, 0x088ad9c8UL, 0x49bbc2d1UL, - 0x8ae8effaUL, 0xcbd9f4e3UL, 0x0c4fb5acUL, 0x4d7eaeb5UL, 0x8e2d839eUL, - 0xcf1c9887UL, 0x5112c24aUL, 0x1023d953UL, 0xd370f478UL, 0x9241ef61UL, - 0x55d7ae2eUL, 0x14e6b537UL, 0xd7b5981cUL, 0x96848305UL, 0x59981b82UL, - 0x18a9009bUL, 0xdbfa2db0UL, 0x9acb36a9UL, 0x5d5d77e6UL, 0x1c6c6cffUL, - 0xdf3f41d4UL, 0x9e0e5acdUL, 0xa2248495UL, 0xe3159f8cUL, 0x2046b2a7UL, - 0x6177a9beUL, 0xa6e1e8f1UL, 0xe7d0f3e8UL, 0x2483dec3UL, 0x65b2c5daUL, - 0xaaae5d5dUL, 0xeb9f4644UL, 0x28cc6b6fUL, 0x69fd7076UL, 0xae6b3139UL, - 0xef5a2a20UL, 0x2c09070bUL, 0x6d381c12UL, 0xf33646dfUL, 0xb2075dc6UL, - 0x715470edUL, 0x30656bf4UL, 0xf7f32abbUL, 0xb6c231a2UL, 0x75911c89UL, - 0x34a00790UL, 0xfbbc9f17UL, 0xba8d840eUL, 0x79dea925UL, 0x38efb23cUL, - 0xff79f373UL, 0xbe48e86aUL, 0x7d1bc541UL, 0x3c2ade58UL, 0x054f79f0UL, - 0x447e62e9UL, 0x872d4fc2UL, 0xc61c54dbUL, 0x018a1594UL, 0x40bb0e8dUL, - 0x83e823a6UL, 0xc2d938bfUL, 0x0dc5a038UL, 0x4cf4bb21UL, 0x8fa7960aUL, - 0xce968d13UL, 0x0900cc5cUL, 0x4831d745UL, 0x8b62fa6eUL, 0xca53e177UL, - 0x545dbbbaUL, 0x156ca0a3UL, 0xd63f8d88UL, 0x970e9691UL, 0x5098d7deUL, - 0x11a9ccc7UL, 0xd2fae1ecUL, 0x93cbfaf5UL, 0x5cd76272UL, 0x1de6796bUL, - 0xdeb55440UL, 0x9f844f59UL, 0x58120e16UL, 0x1923150fUL, 0xda703824UL, - 0x9b41233dUL, 0xa76bfd65UL, 0xe65ae67cUL, 0x2509cb57UL, 0x6438d04eUL, - 0xa3ae9101UL, 0xe29f8a18UL, 0x21cca733UL, 0x60fdbc2aUL, 0xafe124adUL, - 0xeed03fb4UL, 0x2d83129fUL, 0x6cb20986UL, 0xab2448c9UL, 0xea1553d0UL, - 0x29467efbUL, 0x687765e2UL, 0xf6793f2fUL, 0xb7482436UL, 0x741b091dUL, - 0x352a1204UL, 0xf2bc534bUL, 0xb38d4852UL, 0x70de6579UL, 0x31ef7e60UL, - 0xfef3e6e7UL, 0xbfc2fdfeUL, 0x7c91d0d5UL, 0x3da0cbccUL, 0xfa368a83UL, - 0xbb07919aUL, 0x7854bcb1UL, 0x3965a7a8UL, 0x4b98833bUL, 0x0aa99822UL, - 0xc9fab509UL, 0x88cbae10UL, 0x4f5def5fUL, 0x0e6cf446UL, 0xcd3fd96dUL, - 0x8c0ec274UL, 0x43125af3UL, 0x022341eaUL, 0xc1706cc1UL, 0x804177d8UL, - 0x47d73697UL, 0x06e62d8eUL, 0xc5b500a5UL, 0x84841bbcUL, 0x1a8a4171UL, - 0x5bbb5a68UL, 0x98e87743UL, 0xd9d96c5aUL, 0x1e4f2d15UL, 0x5f7e360cUL, - 0x9c2d1b27UL, 0xdd1c003eUL, 0x120098b9UL, 0x533183a0UL, 0x9062ae8bUL, - 0xd153b592UL, 0x16c5f4ddUL, 0x57f4efc4UL, 0x94a7c2efUL, 0xd596d9f6UL, - 0xe9bc07aeUL, 0xa88d1cb7UL, 0x6bde319cUL, 0x2aef2a85UL, 0xed796bcaUL, - 0xac4870d3UL, 0x6f1b5df8UL, 0x2e2a46e1UL, 0xe136de66UL, 0xa007c57fUL, - 0x6354e854UL, 0x2265f34dUL, 0xe5f3b202UL, 0xa4c2a91bUL, 0x67918430UL, - 0x26a09f29UL, 0xb8aec5e4UL, 0xf99fdefdUL, 0x3accf3d6UL, 0x7bfde8cfUL, - 0xbc6ba980UL, 0xfd5ab299UL, 0x3e099fb2UL, 0x7f3884abUL, 0xb0241c2cUL, - 0xf1150735UL, 0x32462a1eUL, 0x73773107UL, 0xb4e17048UL, 0xf5d06b51UL, - 0x3683467aUL, 0x77b25d63UL, 0x4ed7facbUL, 0x0fe6e1d2UL, 0xccb5ccf9UL, - 0x8d84d7e0UL, 0x4a1296afUL, 0x0b238db6UL, 0xc870a09dUL, 0x8941bb84UL, - 0x465d2303UL, 0x076c381aUL, 0xc43f1531UL, 0x850e0e28UL, 0x42984f67UL, - 0x03a9547eUL, 0xc0fa7955UL, 0x81cb624cUL, 0x1fc53881UL, 0x5ef42398UL, - 0x9da70eb3UL, 0xdc9615aaUL, 0x1b0054e5UL, 0x5a314ffcUL, 0x996262d7UL, - 0xd85379ceUL, 0x174fe149UL, 0x567efa50UL, 0x952dd77bUL, 0xd41ccc62UL, - 0x138a8d2dUL, 0x52bb9634UL, 0x91e8bb1fUL, 0xd0d9a006UL, 0xecf37e5eUL, - 0xadc26547UL, 0x6e91486cUL, 0x2fa05375UL, 0xe836123aUL, 0xa9070923UL, - 0x6a542408UL, 0x2b653f11UL, 0xe479a796UL, 0xa548bc8fUL, 0x661b91a4UL, - 0x272a8abdUL, 0xe0bccbf2UL, 0xa18dd0ebUL, 0x62defdc0UL, 0x23efe6d9UL, - 0xbde1bc14UL, 0xfcd0a70dUL, 0x3f838a26UL, 0x7eb2913fUL, 0xb924d070UL, - 0xf815cb69UL, 0x3b46e642UL, 0x7a77fd5bUL, 0xb56b65dcUL, 0xf45a7ec5UL, - 0x370953eeUL, 0x763848f7UL, 0xb1ae09b8UL, 0xf09f12a1UL, 0x33cc3f8aUL, - 0x72fd2493UL - }, - { - 0x00000000UL, 0x376ac201UL, 0x6ed48403UL, 0x59be4602UL, 0xdca80907UL, - 0xebc2cb06UL, 0xb27c8d04UL, 0x85164f05UL, 0xb851130eUL, 0x8f3bd10fUL, - 0xd685970dUL, 0xe1ef550cUL, 0x64f91a09UL, 0x5393d808UL, 0x0a2d9e0aUL, - 0x3d475c0bUL, 0x70a3261cUL, 0x47c9e41dUL, 0x1e77a21fUL, 0x291d601eUL, - 0xac0b2f1bUL, 0x9b61ed1aUL, 0xc2dfab18UL, 0xf5b56919UL, 0xc8f23512UL, - 0xff98f713UL, 0xa626b111UL, 0x914c7310UL, 0x145a3c15UL, 0x2330fe14UL, - 0x7a8eb816UL, 0x4de47a17UL, 0xe0464d38UL, 0xd72c8f39UL, 0x8e92c93bUL, - 0xb9f80b3aUL, 0x3cee443fUL, 0x0b84863eUL, 0x523ac03cUL, 0x6550023dUL, - 0x58175e36UL, 0x6f7d9c37UL, 0x36c3da35UL, 0x01a91834UL, 0x84bf5731UL, - 0xb3d59530UL, 0xea6bd332UL, 0xdd011133UL, 0x90e56b24UL, 0xa78fa925UL, - 0xfe31ef27UL, 0xc95b2d26UL, 0x4c4d6223UL, 0x7b27a022UL, 0x2299e620UL, - 0x15f32421UL, 0x28b4782aUL, 0x1fdeba2bUL, 0x4660fc29UL, 0x710a3e28UL, - 0xf41c712dUL, 0xc376b32cUL, 0x9ac8f52eUL, 0xada2372fUL, 0xc08d9a70UL, - 0xf7e75871UL, 0xae591e73UL, 0x9933dc72UL, 0x1c259377UL, 0x2b4f5176UL, - 0x72f11774UL, 0x459bd575UL, 0x78dc897eUL, 0x4fb64b7fUL, 0x16080d7dUL, - 0x2162cf7cUL, 0xa4748079UL, 0x931e4278UL, 0xcaa0047aUL, 0xfdcac67bUL, - 0xb02ebc6cUL, 0x87447e6dUL, 0xdefa386fUL, 0xe990fa6eUL, 0x6c86b56bUL, - 0x5bec776aUL, 0x02523168UL, 0x3538f369UL, 0x087faf62UL, 0x3f156d63UL, - 0x66ab2b61UL, 0x51c1e960UL, 0xd4d7a665UL, 0xe3bd6464UL, 0xba032266UL, - 0x8d69e067UL, 0x20cbd748UL, 0x17a11549UL, 0x4e1f534bUL, 0x7975914aUL, - 0xfc63de4fUL, 0xcb091c4eUL, 0x92b75a4cUL, 0xa5dd984dUL, 0x989ac446UL, - 0xaff00647UL, 0xf64e4045UL, 0xc1248244UL, 0x4432cd41UL, 0x73580f40UL, - 0x2ae64942UL, 0x1d8c8b43UL, 0x5068f154UL, 0x67023355UL, 0x3ebc7557UL, - 0x09d6b756UL, 0x8cc0f853UL, 0xbbaa3a52UL, 0xe2147c50UL, 0xd57ebe51UL, - 0xe839e25aUL, 0xdf53205bUL, 0x86ed6659UL, 0xb187a458UL, 0x3491eb5dUL, - 0x03fb295cUL, 0x5a456f5eUL, 0x6d2fad5fUL, 0x801b35e1UL, 0xb771f7e0UL, - 0xeecfb1e2UL, 0xd9a573e3UL, 0x5cb33ce6UL, 0x6bd9fee7UL, 0x3267b8e5UL, - 0x050d7ae4UL, 0x384a26efUL, 0x0f20e4eeUL, 0x569ea2ecUL, 0x61f460edUL, - 0xe4e22fe8UL, 0xd388ede9UL, 0x8a36abebUL, 0xbd5c69eaUL, 0xf0b813fdUL, - 0xc7d2d1fcUL, 0x9e6c97feUL, 0xa90655ffUL, 0x2c101afaUL, 0x1b7ad8fbUL, - 0x42c49ef9UL, 0x75ae5cf8UL, 0x48e900f3UL, 0x7f83c2f2UL, 0x263d84f0UL, - 0x115746f1UL, 0x944109f4UL, 0xa32bcbf5UL, 0xfa958df7UL, 0xcdff4ff6UL, - 0x605d78d9UL, 0x5737bad8UL, 0x0e89fcdaUL, 0x39e33edbUL, 0xbcf571deUL, - 0x8b9fb3dfUL, 0xd221f5ddUL, 0xe54b37dcUL, 0xd80c6bd7UL, 0xef66a9d6UL, - 0xb6d8efd4UL, 0x81b22dd5UL, 0x04a462d0UL, 0x33cea0d1UL, 0x6a70e6d3UL, - 0x5d1a24d2UL, 0x10fe5ec5UL, 0x27949cc4UL, 0x7e2adac6UL, 0x494018c7UL, - 0xcc5657c2UL, 0xfb3c95c3UL, 0xa282d3c1UL, 0x95e811c0UL, 0xa8af4dcbUL, - 0x9fc58fcaUL, 0xc67bc9c8UL, 0xf1110bc9UL, 0x740744ccUL, 0x436d86cdUL, - 0x1ad3c0cfUL, 0x2db902ceUL, 0x4096af91UL, 0x77fc6d90UL, 0x2e422b92UL, - 0x1928e993UL, 0x9c3ea696UL, 0xab546497UL, 0xf2ea2295UL, 0xc580e094UL, - 0xf8c7bc9fUL, 0xcfad7e9eUL, 0x9613389cUL, 0xa179fa9dUL, 0x246fb598UL, - 0x13057799UL, 0x4abb319bUL, 0x7dd1f39aUL, 0x3035898dUL, 0x075f4b8cUL, - 0x5ee10d8eUL, 0x698bcf8fUL, 0xec9d808aUL, 0xdbf7428bUL, 0x82490489UL, - 0xb523c688UL, 0x88649a83UL, 0xbf0e5882UL, 0xe6b01e80UL, 0xd1dadc81UL, - 0x54cc9384UL, 0x63a65185UL, 0x3a181787UL, 0x0d72d586UL, 0xa0d0e2a9UL, - 0x97ba20a8UL, 0xce0466aaUL, 0xf96ea4abUL, 0x7c78ebaeUL, 0x4b1229afUL, - 0x12ac6fadUL, 0x25c6adacUL, 0x1881f1a7UL, 0x2feb33a6UL, 0x765575a4UL, - 0x413fb7a5UL, 0xc429f8a0UL, 0xf3433aa1UL, 0xaafd7ca3UL, 0x9d97bea2UL, - 0xd073c4b5UL, 0xe71906b4UL, 0xbea740b6UL, 0x89cd82b7UL, 0x0cdbcdb2UL, - 0x3bb10fb3UL, 0x620f49b1UL, 0x55658bb0UL, 0x6822d7bbUL, 0x5f4815baUL, - 0x06f653b8UL, 0x319c91b9UL, 0xb48adebcUL, 0x83e01cbdUL, 0xda5e5abfUL, - 0xed3498beUL - }, - { - 0x00000000UL, 0x6567bcb8UL, 0x8bc809aaUL, 0xeeafb512UL, 0x5797628fUL, - 0x32f0de37UL, 0xdc5f6b25UL, 0xb938d79dUL, 0xef28b4c5UL, 0x8a4f087dUL, - 0x64e0bd6fUL, 0x018701d7UL, 0xb8bfd64aUL, 0xddd86af2UL, 0x3377dfe0UL, - 0x56106358UL, 0x9f571950UL, 0xfa30a5e8UL, 0x149f10faUL, 0x71f8ac42UL, - 0xc8c07bdfUL, 0xada7c767UL, 0x43087275UL, 0x266fcecdUL, 0x707fad95UL, - 0x1518112dUL, 0xfbb7a43fUL, 0x9ed01887UL, 0x27e8cf1aUL, 0x428f73a2UL, - 0xac20c6b0UL, 0xc9477a08UL, 0x3eaf32a0UL, 0x5bc88e18UL, 0xb5673b0aUL, - 0xd00087b2UL, 0x6938502fUL, 0x0c5fec97UL, 0xe2f05985UL, 0x8797e53dUL, - 0xd1878665UL, 0xb4e03addUL, 0x5a4f8fcfUL, 0x3f283377UL, 0x8610e4eaUL, - 0xe3775852UL, 0x0dd8ed40UL, 0x68bf51f8UL, 0xa1f82bf0UL, 0xc49f9748UL, - 0x2a30225aUL, 0x4f579ee2UL, 0xf66f497fUL, 0x9308f5c7UL, 0x7da740d5UL, - 0x18c0fc6dUL, 0x4ed09f35UL, 0x2bb7238dUL, 0xc518969fUL, 0xa07f2a27UL, - 0x1947fdbaUL, 0x7c204102UL, 0x928ff410UL, 0xf7e848a8UL, 0x3d58149bUL, - 0x583fa823UL, 0xb6901d31UL, 0xd3f7a189UL, 0x6acf7614UL, 0x0fa8caacUL, - 0xe1077fbeUL, 0x8460c306UL, 0xd270a05eUL, 0xb7171ce6UL, 0x59b8a9f4UL, - 0x3cdf154cUL, 0x85e7c2d1UL, 0xe0807e69UL, 0x0e2fcb7bUL, 0x6b4877c3UL, - 0xa20f0dcbUL, 0xc768b173UL, 0x29c70461UL, 0x4ca0b8d9UL, 0xf5986f44UL, - 0x90ffd3fcUL, 0x7e5066eeUL, 0x1b37da56UL, 0x4d27b90eUL, 0x284005b6UL, - 0xc6efb0a4UL, 0xa3880c1cUL, 0x1ab0db81UL, 0x7fd76739UL, 0x9178d22bUL, - 0xf41f6e93UL, 0x03f7263bUL, 0x66909a83UL, 0x883f2f91UL, 0xed589329UL, - 0x546044b4UL, 0x3107f80cUL, 0xdfa84d1eUL, 0xbacff1a6UL, 0xecdf92feUL, - 0x89b82e46UL, 0x67179b54UL, 0x027027ecUL, 0xbb48f071UL, 0xde2f4cc9UL, - 0x3080f9dbUL, 0x55e74563UL, 0x9ca03f6bUL, 0xf9c783d3UL, 0x176836c1UL, - 0x720f8a79UL, 0xcb375de4UL, 0xae50e15cUL, 0x40ff544eUL, 0x2598e8f6UL, - 0x73888baeUL, 0x16ef3716UL, 0xf8408204UL, 0x9d273ebcUL, 0x241fe921UL, - 0x41785599UL, 0xafd7e08bUL, 0xcab05c33UL, 0x3bb659edUL, 0x5ed1e555UL, - 0xb07e5047UL, 0xd519ecffUL, 0x6c213b62UL, 0x094687daUL, 0xe7e932c8UL, - 0x828e8e70UL, 0xd49eed28UL, 0xb1f95190UL, 0x5f56e482UL, 0x3a31583aUL, - 0x83098fa7UL, 0xe66e331fUL, 0x08c1860dUL, 0x6da63ab5UL, 0xa4e140bdUL, - 0xc186fc05UL, 0x2f294917UL, 0x4a4ef5afUL, 0xf3762232UL, 0x96119e8aUL, - 0x78be2b98UL, 0x1dd99720UL, 0x4bc9f478UL, 0x2eae48c0UL, 0xc001fdd2UL, - 0xa566416aUL, 0x1c5e96f7UL, 0x79392a4fUL, 0x97969f5dUL, 0xf2f123e5UL, - 0x05196b4dUL, 0x607ed7f5UL, 0x8ed162e7UL, 0xebb6de5fUL, 0x528e09c2UL, - 0x37e9b57aUL, 0xd9460068UL, 0xbc21bcd0UL, 0xea31df88UL, 0x8f566330UL, - 0x61f9d622UL, 0x049e6a9aUL, 0xbda6bd07UL, 0xd8c101bfUL, 0x366eb4adUL, - 0x53090815UL, 0x9a4e721dUL, 0xff29cea5UL, 0x11867bb7UL, 0x74e1c70fUL, - 0xcdd91092UL, 0xa8beac2aUL, 0x46111938UL, 0x2376a580UL, 0x7566c6d8UL, - 0x10017a60UL, 0xfeaecf72UL, 0x9bc973caUL, 0x22f1a457UL, 0x479618efUL, - 0xa939adfdUL, 0xcc5e1145UL, 0x06ee4d76UL, 0x6389f1ceUL, 0x8d2644dcUL, - 0xe841f864UL, 0x51792ff9UL, 0x341e9341UL, 0xdab12653UL, 0xbfd69aebUL, - 0xe9c6f9b3UL, 0x8ca1450bUL, 0x620ef019UL, 0x07694ca1UL, 0xbe519b3cUL, - 0xdb362784UL, 0x35999296UL, 0x50fe2e2eUL, 0x99b95426UL, 0xfcdee89eUL, - 0x12715d8cUL, 0x7716e134UL, 0xce2e36a9UL, 0xab498a11UL, 0x45e63f03UL, - 0x208183bbUL, 0x7691e0e3UL, 0x13f65c5bUL, 0xfd59e949UL, 0x983e55f1UL, - 0x2106826cUL, 0x44613ed4UL, 0xaace8bc6UL, 0xcfa9377eUL, 0x38417fd6UL, - 0x5d26c36eUL, 0xb389767cUL, 0xd6eecac4UL, 0x6fd61d59UL, 0x0ab1a1e1UL, - 0xe41e14f3UL, 0x8179a84bUL, 0xd769cb13UL, 0xb20e77abUL, 0x5ca1c2b9UL, - 0x39c67e01UL, 0x80fea99cUL, 0xe5991524UL, 0x0b36a036UL, 0x6e511c8eUL, - 0xa7166686UL, 0xc271da3eUL, 0x2cde6f2cUL, 0x49b9d394UL, 0xf0810409UL, - 0x95e6b8b1UL, 0x7b490da3UL, 0x1e2eb11bUL, 0x483ed243UL, 0x2d596efbUL, - 0xc3f6dbe9UL, 0xa6916751UL, 0x1fa9b0ccUL, 0x7ace0c74UL, 0x9461b966UL, - 0xf10605deUL -#endif - } -}; diff --git a/deps/zlib/deflate.c b/deps/zlib/deflate.c deleted file mode 100644 index 1ec7614..0000000 --- a/deps/zlib/deflate.c +++ /dev/null @@ -1,2163 +0,0 @@ -/* deflate.c -- compress data using the deflation algorithm - * Copyright (C) 1995-2017 Jean-loup Gailly and Mark Adler - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -/* - * ALGORITHM - * - * The "deflation" process depends on being able to identify portions - * of the input text which are identical to earlier input (within a - * sliding window trailing behind the input currently being processed). - * - * The most straightforward technique turns out to be the fastest for - * most input files: try all possible matches and select the longest. - * The key feature of this algorithm is that insertions into the string - * dictionary are very simple and thus fast, and deletions are avoided - * completely. Insertions are performed at each input character, whereas - * string matches are performed only when the previous match ends. So it - * is preferable to spend more time in matches to allow very fast string - * insertions and avoid deletions. The matching algorithm for small - * strings is inspired from that of Rabin & Karp. A brute force approach - * is used to find longer strings when a small match has been found. - * A similar algorithm is used in comic (by Jan-Mark Wams) and freeze - * (by Leonid Broukhis). - * A previous version of this file used a more sophisticated algorithm - * (by Fiala and Greene) which is guaranteed to run in linear amortized - * time, but has a larger average cost, uses more memory and is patented. - * However the F&G algorithm may be faster for some highly redundant - * files if the parameter max_chain_length (described below) is too large. - * - * ACKNOWLEDGEMENTS - * - * The idea of lazy evaluation of matches is due to Jan-Mark Wams, and - * I found it in 'freeze' written by Leonid Broukhis. - * Thanks to many people for bug reports and testing. - * - * REFERENCES - * - * Deutsch, L.P.,"DEFLATE Compressed Data Format Specification". - * Available in http://tools.ietf.org/html/rfc1951 - * - * A description of the Rabin and Karp algorithm is given in the book - * "Algorithms" by R. Sedgewick, Addison-Wesley, p252. - * - * Fiala,E.R., and Greene,D.H. - * Data Compression with Finite Windows, Comm.ACM, 32,4 (1989) 490-595 - * - */ - -/* @(#) $Id$ */ - -#include "deflate.h" - -const char deflate_copyright[] = - " deflate 1.2.11 Copyright 1995-2017 Jean-loup Gailly and Mark Adler "; -/* - If you use the zlib library in a product, an acknowledgment is welcome - in the documentation of your product. If for some reason you cannot - include such an acknowledgment, I would appreciate that you keep this - copyright string in the executable of your product. - */ - -/* =========================================================================== - * Function prototypes. - */ -typedef enum { - need_more, /* block not completed, need more input or more output */ - block_done, /* block flush performed */ - finish_started, /* finish started, need only more output at next deflate */ - finish_done /* finish done, accept no more input or output */ -} block_state; - -typedef block_state (*compress_func) OF((deflate_state *s, int flush)); -/* Compression function. Returns the block state after the call. */ - -local int deflateStateCheck OF((z_streamp strm)); -local void slide_hash OF((deflate_state *s)); -local void fill_window OF((deflate_state *s)); -local block_state deflate_stored OF((deflate_state *s, int flush)); -local block_state deflate_fast OF((deflate_state *s, int flush)); -#ifndef FASTEST -local block_state deflate_slow OF((deflate_state *s, int flush)); -#endif -local block_state deflate_rle OF((deflate_state *s, int flush)); -local block_state deflate_huff OF((deflate_state *s, int flush)); -local void lm_init OF((deflate_state *s)); -local void putShortMSB OF((deflate_state *s, uInt b)); -local void flush_pending OF((z_streamp strm)); -local unsigned read_buf OF((z_streamp strm, Bytef *buf, unsigned size)); -#ifdef ASMV -# pragma message("Assembler code may have bugs -- use at your own risk") - void match_init OF((void)); /* asm code initialization */ - uInt longest_match OF((deflate_state *s, IPos cur_match)); -#else -local uInt longest_match OF((deflate_state *s, IPos cur_match)); -#endif - -#ifdef ZLIB_DEBUG -local void check_match OF((deflate_state *s, IPos start, IPos match, - int length)); -#endif - -/* =========================================================================== - * Local data - */ - -#define NIL 0 -/* Tail of hash chains */ - -#ifndef TOO_FAR -# define TOO_FAR 4096 -#endif -/* Matches of length 3 are discarded if their distance exceeds TOO_FAR */ - -/* Values for max_lazy_match, good_match and max_chain_length, depending on - * the desired pack level (0..9). The values given below have been tuned to - * exclude worst case performance for pathological files. Better values may be - * found for specific files. - */ -typedef struct config_s { - ush good_length; /* reduce lazy search above this match length */ - ush max_lazy; /* do not perform lazy search above this match length */ - ush nice_length; /* quit search above this match length */ - ush max_chain; - compress_func func; -} config; - -#ifdef FASTEST -local const config configuration_table[2] = { -/* good lazy nice chain */ -/* 0 */ {0, 0, 0, 0, deflate_stored}, /* store only */ -/* 1 */ {4, 4, 8, 4, deflate_fast}}; /* max speed, no lazy matches */ -#else -local const config configuration_table[10] = { -/* good lazy nice chain */ -/* 0 */ {0, 0, 0, 0, deflate_stored}, /* store only */ -/* 1 */ {4, 4, 8, 4, deflate_fast}, /* max speed, no lazy matches */ -/* 2 */ {4, 5, 16, 8, deflate_fast}, -/* 3 */ {4, 6, 32, 32, deflate_fast}, - -/* 4 */ {4, 4, 16, 16, deflate_slow}, /* lazy matches */ -/* 5 */ {8, 16, 32, 32, deflate_slow}, -/* 6 */ {8, 16, 128, 128, deflate_slow}, -/* 7 */ {8, 32, 128, 256, deflate_slow}, -/* 8 */ {32, 128, 258, 1024, deflate_slow}, -/* 9 */ {32, 258, 258, 4096, deflate_slow}}; /* max compression */ -#endif - -/* Note: the deflate() code requires max_lazy >= MIN_MATCH and max_chain >= 4 - * For deflate_fast() (levels <= 3) good is ignored and lazy has a different - * meaning. - */ - -/* rank Z_BLOCK between Z_NO_FLUSH and Z_PARTIAL_FLUSH */ -#define RANK(f) (((f) * 2) - ((f) > 4 ? 9 : 0)) - -/* =========================================================================== - * Update a hash value with the given input byte - * IN assertion: all calls to UPDATE_HASH are made with consecutive input - * characters, so that a running hash key can be computed from the previous - * key instead of complete recalculation each time. - */ -#define UPDATE_HASH(s,h,c) (h = (((h)<hash_shift) ^ (c)) & s->hash_mask) - - -/* =========================================================================== - * Insert string str in the dictionary and set match_head to the previous head - * of the hash chain (the most recent string with same hash key). Return - * the previous length of the hash chain. - * If this file is compiled with -DFASTEST, the compression level is forced - * to 1, and no hash chains are maintained. - * IN assertion: all calls to INSERT_STRING are made with consecutive input - * characters and the first MIN_MATCH bytes of str are valid (except for - * the last MIN_MATCH-1 bytes of the input file). - */ -#ifdef FASTEST -#define INSERT_STRING(s, str, match_head) \ - (UPDATE_HASH(s, s->ins_h, s->window[(str) + (MIN_MATCH-1)]), \ - match_head = s->head[s->ins_h], \ - s->head[s->ins_h] = (Pos)(str)) -#else -#define INSERT_STRING(s, str, match_head) \ - (UPDATE_HASH(s, s->ins_h, s->window[(str) + (MIN_MATCH-1)]), \ - match_head = s->prev[(str) & s->w_mask] = s->head[s->ins_h], \ - s->head[s->ins_h] = (Pos)(str)) -#endif - -/* =========================================================================== - * Initialize the hash table (avoiding 64K overflow for 16 bit systems). - * prev[] will be initialized on the fly. - */ -#define CLEAR_HASH(s) \ - s->head[s->hash_size-1] = NIL; \ - zmemzero((Bytef *)s->head, (unsigned)(s->hash_size-1)*sizeof(*s->head)); - -/* =========================================================================== - * Slide the hash table when sliding the window down (could be avoided with 32 - * bit values at the expense of memory usage). We slide even when level == 0 to - * keep the hash table consistent if we switch back to level > 0 later. - */ -local void slide_hash(s) - deflate_state *s; -{ - unsigned n, m; - Posf *p; - uInt wsize = s->w_size; - - n = s->hash_size; - p = &s->head[n]; - do { - m = *--p; - *p = (Pos)(m >= wsize ? m - wsize : NIL); - } while (--n); - n = wsize; -#ifndef FASTEST - p = &s->prev[n]; - do { - m = *--p; - *p = (Pos)(m >= wsize ? m - wsize : NIL); - /* If n is not on any hash chain, prev[n] is garbage but - * its value will never be used. - */ - } while (--n); -#endif -} - -/* ========================================================================= */ -int ZEXPORT deflateInit_(strm, level, version, stream_size) - z_streamp strm; - int level; - const char *version; - int stream_size; -{ - return deflateInit2_(strm, level, Z_DEFLATED, MAX_WBITS, DEF_MEM_LEVEL, - Z_DEFAULT_STRATEGY, version, stream_size); - /* To do: ignore strm->next_in if we use it as window */ -} - -/* ========================================================================= */ -int ZEXPORT deflateInit2_(strm, level, method, windowBits, memLevel, strategy, - version, stream_size) - z_streamp strm; - int level; - int method; - int windowBits; - int memLevel; - int strategy; - const char *version; - int stream_size; -{ - deflate_state *s; - int wrap = 1; - static const char my_version[] = ZLIB_VERSION; - - ushf *overlay; - /* We overlay pending_buf and d_buf+l_buf. This works since the average - * output size for (length,distance) codes is <= 24 bits. - */ - - if (version == Z_NULL || version[0] != my_version[0] || - stream_size != sizeof(z_stream)) { - return Z_VERSION_ERROR; - } - if (strm == Z_NULL) return Z_STREAM_ERROR; - - strm->msg = Z_NULL; - if (strm->zalloc == (alloc_func)0) { -#ifdef Z_SOLO - return Z_STREAM_ERROR; -#else - strm->zalloc = zcalloc; - strm->opaque = (voidpf)0; -#endif - } - if (strm->zfree == (free_func)0) -#ifdef Z_SOLO - return Z_STREAM_ERROR; -#else - strm->zfree = zcfree; -#endif - -#ifdef FASTEST - if (level != 0) level = 1; -#else - if (level == Z_DEFAULT_COMPRESSION) level = 6; -#endif - - if (windowBits < 0) { /* suppress zlib wrapper */ - wrap = 0; - windowBits = -windowBits; - } -#ifdef GZIP - else if (windowBits > 15) { - wrap = 2; /* write gzip wrapper instead */ - windowBits -= 16; - } -#endif - if (memLevel < 1 || memLevel > MAX_MEM_LEVEL || method != Z_DEFLATED || - windowBits < 8 || windowBits > 15 || level < 0 || level > 9 || - strategy < 0 || strategy > Z_FIXED || (windowBits == 8 && wrap != 1)) { - return Z_STREAM_ERROR; - } - if (windowBits == 8) windowBits = 9; /* until 256-byte window bug fixed */ - s = (deflate_state *) ZALLOC(strm, 1, sizeof(deflate_state)); - if (s == Z_NULL) return Z_MEM_ERROR; - strm->state = (struct internal_state FAR *)s; - s->strm = strm; - s->status = INIT_STATE; /* to pass state test in deflateReset() */ - - s->wrap = wrap; - s->gzhead = Z_NULL; - s->w_bits = (uInt)windowBits; - s->w_size = 1 << s->w_bits; - s->w_mask = s->w_size - 1; - - s->hash_bits = (uInt)memLevel + 7; - s->hash_size = 1 << s->hash_bits; - s->hash_mask = s->hash_size - 1; - s->hash_shift = ((s->hash_bits+MIN_MATCH-1)/MIN_MATCH); - - s->window = (Bytef *) ZALLOC(strm, s->w_size, 2*sizeof(Byte)); - s->prev = (Posf *) ZALLOC(strm, s->w_size, sizeof(Pos)); - s->head = (Posf *) ZALLOC(strm, s->hash_size, sizeof(Pos)); - - s->high_water = 0; /* nothing written to s->window yet */ - - s->lit_bufsize = 1 << (memLevel + 6); /* 16K elements by default */ - - overlay = (ushf *) ZALLOC(strm, s->lit_bufsize, sizeof(ush)+2); - s->pending_buf = (uchf *) overlay; - s->pending_buf_size = (ulg)s->lit_bufsize * (sizeof(ush)+2L); - - if (s->window == Z_NULL || s->prev == Z_NULL || s->head == Z_NULL || - s->pending_buf == Z_NULL) { - s->status = FINISH_STATE; - strm->msg = ERR_MSG(Z_MEM_ERROR); - deflateEnd (strm); - return Z_MEM_ERROR; - } - s->d_buf = overlay + s->lit_bufsize/sizeof(ush); - s->l_buf = s->pending_buf + (1+sizeof(ush))*s->lit_bufsize; - - s->level = level; - s->strategy = strategy; - s->method = (Byte)method; - - return deflateReset(strm); -} - -/* ========================================================================= - * Check for a valid deflate stream state. Return 0 if ok, 1 if not. - */ -local int deflateStateCheck (strm) - z_streamp strm; -{ - deflate_state *s; - if (strm == Z_NULL || - strm->zalloc == (alloc_func)0 || strm->zfree == (free_func)0) - return 1; - s = strm->state; - if (s == Z_NULL || s->strm != strm || (s->status != INIT_STATE && -#ifdef GZIP - s->status != GZIP_STATE && -#endif - s->status != EXTRA_STATE && - s->status != NAME_STATE && - s->status != COMMENT_STATE && - s->status != HCRC_STATE && - s->status != BUSY_STATE && - s->status != FINISH_STATE)) - return 1; - return 0; -} - -/* ========================================================================= */ -int ZEXPORT deflateSetDictionary (strm, dictionary, dictLength) - z_streamp strm; - const Bytef *dictionary; - uInt dictLength; -{ - deflate_state *s; - uInt str, n; - int wrap; - unsigned avail; - z_const unsigned char *next; - - if (deflateStateCheck(strm) || dictionary == Z_NULL) - return Z_STREAM_ERROR; - s = strm->state; - wrap = s->wrap; - if (wrap == 2 || (wrap == 1 && s->status != INIT_STATE) || s->lookahead) - return Z_STREAM_ERROR; - - /* when using zlib wrappers, compute Adler-32 for provided dictionary */ - if (wrap == 1) - strm->adler = adler32(strm->adler, dictionary, dictLength); - s->wrap = 0; /* avoid computing Adler-32 in read_buf */ - - /* if dictionary would fill window, just replace the history */ - if (dictLength >= s->w_size) { - if (wrap == 0) { /* already empty otherwise */ - CLEAR_HASH(s); - s->strstart = 0; - s->block_start = 0L; - s->insert = 0; - } - dictionary += dictLength - s->w_size; /* use the tail */ - dictLength = s->w_size; - } - - /* insert dictionary into window and hash */ - avail = strm->avail_in; - next = strm->next_in; - strm->avail_in = dictLength; - strm->next_in = (z_const Bytef *)dictionary; - fill_window(s); - while (s->lookahead >= MIN_MATCH) { - str = s->strstart; - n = s->lookahead - (MIN_MATCH-1); - do { - UPDATE_HASH(s, s->ins_h, s->window[str + MIN_MATCH-1]); -#ifndef FASTEST - s->prev[str & s->w_mask] = s->head[s->ins_h]; -#endif - s->head[s->ins_h] = (Pos)str; - str++; - } while (--n); - s->strstart = str; - s->lookahead = MIN_MATCH-1; - fill_window(s); - } - s->strstart += s->lookahead; - s->block_start = (long)s->strstart; - s->insert = s->lookahead; - s->lookahead = 0; - s->match_length = s->prev_length = MIN_MATCH-1; - s->match_available = 0; - strm->next_in = next; - strm->avail_in = avail; - s->wrap = wrap; - return Z_OK; -} - -/* ========================================================================= */ -int ZEXPORT deflateGetDictionary (strm, dictionary, dictLength) - z_streamp strm; - Bytef *dictionary; - uInt *dictLength; -{ - deflate_state *s; - uInt len; - - if (deflateStateCheck(strm)) - return Z_STREAM_ERROR; - s = strm->state; - len = s->strstart + s->lookahead; - if (len > s->w_size) - len = s->w_size; - if (dictionary != Z_NULL && len) - zmemcpy(dictionary, s->window + s->strstart + s->lookahead - len, len); - if (dictLength != Z_NULL) - *dictLength = len; - return Z_OK; -} - -/* ========================================================================= */ -int ZEXPORT deflateResetKeep (strm) - z_streamp strm; -{ - deflate_state *s; - - if (deflateStateCheck(strm)) { - return Z_STREAM_ERROR; - } - - strm->total_in = strm->total_out = 0; - strm->msg = Z_NULL; /* use zfree if we ever allocate msg dynamically */ - strm->data_type = Z_UNKNOWN; - - s = (deflate_state *)strm->state; - s->pending = 0; - s->pending_out = s->pending_buf; - - if (s->wrap < 0) { - s->wrap = -s->wrap; /* was made negative by deflate(..., Z_FINISH); */ - } - s->status = -#ifdef GZIP - s->wrap == 2 ? GZIP_STATE : -#endif - s->wrap ? INIT_STATE : BUSY_STATE; - strm->adler = -#ifdef GZIP - s->wrap == 2 ? crc32(0L, Z_NULL, 0) : -#endif - adler32(0L, Z_NULL, 0); - s->last_flush = Z_NO_FLUSH; - - _tr_init(s); - - return Z_OK; -} - -/* ========================================================================= */ -int ZEXPORT deflateReset (strm) - z_streamp strm; -{ - int ret; - - ret = deflateResetKeep(strm); - if (ret == Z_OK) - lm_init(strm->state); - return ret; -} - -/* ========================================================================= */ -int ZEXPORT deflateSetHeader (strm, head) - z_streamp strm; - gz_headerp head; -{ - if (deflateStateCheck(strm) || strm->state->wrap != 2) - return Z_STREAM_ERROR; - strm->state->gzhead = head; - return Z_OK; -} - -/* ========================================================================= */ -int ZEXPORT deflatePending (strm, pending, bits) - unsigned *pending; - int *bits; - z_streamp strm; -{ - if (deflateStateCheck(strm)) return Z_STREAM_ERROR; - if (pending != Z_NULL) - *pending = strm->state->pending; - if (bits != Z_NULL) - *bits = strm->state->bi_valid; - return Z_OK; -} - -/* ========================================================================= */ -int ZEXPORT deflatePrime (strm, bits, value) - z_streamp strm; - int bits; - int value; -{ - deflate_state *s; - int put; - - if (deflateStateCheck(strm)) return Z_STREAM_ERROR; - s = strm->state; - if ((Bytef *)(s->d_buf) < s->pending_out + ((Buf_size + 7) >> 3)) - return Z_BUF_ERROR; - do { - put = Buf_size - s->bi_valid; - if (put > bits) - put = bits; - s->bi_buf |= (ush)((value & ((1 << put) - 1)) << s->bi_valid); - s->bi_valid += put; - _tr_flush_bits(s); - value >>= put; - bits -= put; - } while (bits); - return Z_OK; -} - -/* ========================================================================= */ -int ZEXPORT deflateParams(strm, level, strategy) - z_streamp strm; - int level; - int strategy; -{ - deflate_state *s; - compress_func func; - - if (deflateStateCheck(strm)) return Z_STREAM_ERROR; - s = strm->state; - -#ifdef FASTEST - if (level != 0) level = 1; -#else - if (level == Z_DEFAULT_COMPRESSION) level = 6; -#endif - if (level < 0 || level > 9 || strategy < 0 || strategy > Z_FIXED) { - return Z_STREAM_ERROR; - } - func = configuration_table[s->level].func; - - if ((strategy != s->strategy || func != configuration_table[level].func) && - s->high_water) { - /* Flush the last buffer: */ - int err = deflate(strm, Z_BLOCK); - if (err == Z_STREAM_ERROR) - return err; - if (strm->avail_out == 0) - return Z_BUF_ERROR; - } - if (s->level != level) { - if (s->level == 0 && s->matches != 0) { - if (s->matches == 1) - slide_hash(s); - else - CLEAR_HASH(s); - s->matches = 0; - } - s->level = level; - s->max_lazy_match = configuration_table[level].max_lazy; - s->good_match = configuration_table[level].good_length; - s->nice_match = configuration_table[level].nice_length; - s->max_chain_length = configuration_table[level].max_chain; - } - s->strategy = strategy; - return Z_OK; -} - -/* ========================================================================= */ -int ZEXPORT deflateTune(strm, good_length, max_lazy, nice_length, max_chain) - z_streamp strm; - int good_length; - int max_lazy; - int nice_length; - int max_chain; -{ - deflate_state *s; - - if (deflateStateCheck(strm)) return Z_STREAM_ERROR; - s = strm->state; - s->good_match = (uInt)good_length; - s->max_lazy_match = (uInt)max_lazy; - s->nice_match = nice_length; - s->max_chain_length = (uInt)max_chain; - return Z_OK; -} - -/* ========================================================================= - * For the default windowBits of 15 and memLevel of 8, this function returns - * a close to exact, as well as small, upper bound on the compressed size. - * They are coded as constants here for a reason--if the #define's are - * changed, then this function needs to be changed as well. The return - * value for 15 and 8 only works for those exact settings. - * - * For any setting other than those defaults for windowBits and memLevel, - * the value returned is a conservative worst case for the maximum expansion - * resulting from using fixed blocks instead of stored blocks, which deflate - * can emit on compressed data for some combinations of the parameters. - * - * This function could be more sophisticated to provide closer upper bounds for - * every combination of windowBits and memLevel. But even the conservative - * upper bound of about 14% expansion does not seem onerous for output buffer - * allocation. - */ -uLong ZEXPORT deflateBound(strm, sourceLen) - z_streamp strm; - uLong sourceLen; -{ - deflate_state *s; - uLong complen, wraplen; - - /* conservative upper bound for compressed data */ - complen = sourceLen + - ((sourceLen + 7) >> 3) + ((sourceLen + 63) >> 6) + 5; - - /* if can't get parameters, return conservative bound plus zlib wrapper */ - if (deflateStateCheck(strm)) - return complen + 6; - - /* compute wrapper length */ - s = strm->state; - switch (s->wrap) { - case 0: /* raw deflate */ - wraplen = 0; - break; - case 1: /* zlib wrapper */ - wraplen = 6 + (s->strstart ? 4 : 0); - break; -#ifdef GZIP - case 2: /* gzip wrapper */ - wraplen = 18; - if (s->gzhead != Z_NULL) { /* user-supplied gzip header */ - Bytef *str; - if (s->gzhead->extra != Z_NULL) - wraplen += 2 + s->gzhead->extra_len; - str = s->gzhead->name; - if (str != Z_NULL) - do { - wraplen++; - } while (*str++); - str = s->gzhead->comment; - if (str != Z_NULL) - do { - wraplen++; - } while (*str++); - if (s->gzhead->hcrc) - wraplen += 2; - } - break; -#endif - default: /* for compiler happiness */ - wraplen = 6; - } - - /* if not default parameters, return conservative bound */ - if (s->w_bits != 15 || s->hash_bits != 8 + 7) - return complen + wraplen; - - /* default settings: return tight bound for that case */ - return sourceLen + (sourceLen >> 12) + (sourceLen >> 14) + - (sourceLen >> 25) + 13 - 6 + wraplen; -} - -/* ========================================================================= - * Put a short in the pending buffer. The 16-bit value is put in MSB order. - * IN assertion: the stream state is correct and there is enough room in - * pending_buf. - */ -local void putShortMSB (s, b) - deflate_state *s; - uInt b; -{ - put_byte(s, (Byte)(b >> 8)); - put_byte(s, (Byte)(b & 0xff)); -} - -/* ========================================================================= - * Flush as much pending output as possible. All deflate() output, except for - * some deflate_stored() output, goes through this function so some - * applications may wish to modify it to avoid allocating a large - * strm->next_out buffer and copying into it. (See also read_buf()). - */ -local void flush_pending(strm) - z_streamp strm; -{ - unsigned len; - deflate_state *s = strm->state; - - _tr_flush_bits(s); - len = s->pending; - if (len > strm->avail_out) len = strm->avail_out; - if (len == 0) return; - - zmemcpy(strm->next_out, s->pending_out, len); - strm->next_out += len; - s->pending_out += len; - strm->total_out += len; - strm->avail_out -= len; - s->pending -= len; - if (s->pending == 0) { - s->pending_out = s->pending_buf; - } -} - -/* =========================================================================== - * Update the header CRC with the bytes s->pending_buf[beg..s->pending - 1]. - */ -#define HCRC_UPDATE(beg) \ - do { \ - if (s->gzhead->hcrc && s->pending > (beg)) \ - strm->adler = crc32(strm->adler, s->pending_buf + (beg), \ - s->pending - (beg)); \ - } while (0) - -/* ========================================================================= */ -int ZEXPORT deflate (strm, flush) - z_streamp strm; - int flush; -{ - int old_flush; /* value of flush param for previous deflate call */ - deflate_state *s; - - if (deflateStateCheck(strm) || flush > Z_BLOCK || flush < 0) { - return Z_STREAM_ERROR; - } - s = strm->state; - - if (strm->next_out == Z_NULL || - (strm->avail_in != 0 && strm->next_in == Z_NULL) || - (s->status == FINISH_STATE && flush != Z_FINISH)) { - ERR_RETURN(strm, Z_STREAM_ERROR); - } - if (strm->avail_out == 0) ERR_RETURN(strm, Z_BUF_ERROR); - - old_flush = s->last_flush; - s->last_flush = flush; - - /* Flush as much pending output as possible */ - if (s->pending != 0) { - flush_pending(strm); - if (strm->avail_out == 0) { - /* Since avail_out is 0, deflate will be called again with - * more output space, but possibly with both pending and - * avail_in equal to zero. There won't be anything to do, - * but this is not an error situation so make sure we - * return OK instead of BUF_ERROR at next call of deflate: - */ - s->last_flush = -1; - return Z_OK; - } - - /* Make sure there is something to do and avoid duplicate consecutive - * flushes. For repeated and useless calls with Z_FINISH, we keep - * returning Z_STREAM_END instead of Z_BUF_ERROR. - */ - } else if (strm->avail_in == 0 && RANK(flush) <= RANK(old_flush) && - flush != Z_FINISH) { - ERR_RETURN(strm, Z_BUF_ERROR); - } - - /* User must not provide more input after the first FINISH: */ - if (s->status == FINISH_STATE && strm->avail_in != 0) { - ERR_RETURN(strm, Z_BUF_ERROR); - } - - /* Write the header */ - if (s->status == INIT_STATE) { - /* zlib header */ - uInt header = (Z_DEFLATED + ((s->w_bits-8)<<4)) << 8; - uInt level_flags; - - if (s->strategy >= Z_HUFFMAN_ONLY || s->level < 2) - level_flags = 0; - else if (s->level < 6) - level_flags = 1; - else if (s->level == 6) - level_flags = 2; - else - level_flags = 3; - header |= (level_flags << 6); - if (s->strstart != 0) header |= PRESET_DICT; - header += 31 - (header % 31); - - putShortMSB(s, header); - - /* Save the adler32 of the preset dictionary: */ - if (s->strstart != 0) { - putShortMSB(s, (uInt)(strm->adler >> 16)); - putShortMSB(s, (uInt)(strm->adler & 0xffff)); - } - strm->adler = adler32(0L, Z_NULL, 0); - s->status = BUSY_STATE; - - /* Compression must start with an empty pending buffer */ - flush_pending(strm); - if (s->pending != 0) { - s->last_flush = -1; - return Z_OK; - } - } -#ifdef GZIP - if (s->status == GZIP_STATE) { - /* gzip header */ - strm->adler = crc32(0L, Z_NULL, 0); - put_byte(s, 31); - put_byte(s, 139); - put_byte(s, 8); - if (s->gzhead == Z_NULL) { - put_byte(s, 0); - put_byte(s, 0); - put_byte(s, 0); - put_byte(s, 0); - put_byte(s, 0); - put_byte(s, s->level == 9 ? 2 : - (s->strategy >= Z_HUFFMAN_ONLY || s->level < 2 ? - 4 : 0)); - put_byte(s, OS_CODE); - s->status = BUSY_STATE; - - /* Compression must start with an empty pending buffer */ - flush_pending(strm); - if (s->pending != 0) { - s->last_flush = -1; - return Z_OK; - } - } - else { - put_byte(s, (s->gzhead->text ? 1 : 0) + - (s->gzhead->hcrc ? 2 : 0) + - (s->gzhead->extra == Z_NULL ? 0 : 4) + - (s->gzhead->name == Z_NULL ? 0 : 8) + - (s->gzhead->comment == Z_NULL ? 0 : 16) - ); - put_byte(s, (Byte)(s->gzhead->time & 0xff)); - put_byte(s, (Byte)((s->gzhead->time >> 8) & 0xff)); - put_byte(s, (Byte)((s->gzhead->time >> 16) & 0xff)); - put_byte(s, (Byte)((s->gzhead->time >> 24) & 0xff)); - put_byte(s, s->level == 9 ? 2 : - (s->strategy >= Z_HUFFMAN_ONLY || s->level < 2 ? - 4 : 0)); - put_byte(s, s->gzhead->os & 0xff); - if (s->gzhead->extra != Z_NULL) { - put_byte(s, s->gzhead->extra_len & 0xff); - put_byte(s, (s->gzhead->extra_len >> 8) & 0xff); - } - if (s->gzhead->hcrc) - strm->adler = crc32(strm->adler, s->pending_buf, - s->pending); - s->gzindex = 0; - s->status = EXTRA_STATE; - } - } - if (s->status == EXTRA_STATE) { - if (s->gzhead->extra != Z_NULL) { - ulg beg = s->pending; /* start of bytes to update crc */ - uInt left = (s->gzhead->extra_len & 0xffff) - s->gzindex; - while (s->pending + left > s->pending_buf_size) { - uInt copy = s->pending_buf_size - s->pending; - zmemcpy(s->pending_buf + s->pending, - s->gzhead->extra + s->gzindex, copy); - s->pending = s->pending_buf_size; - HCRC_UPDATE(beg); - s->gzindex += copy; - flush_pending(strm); - if (s->pending != 0) { - s->last_flush = -1; - return Z_OK; - } - beg = 0; - left -= copy; - } - zmemcpy(s->pending_buf + s->pending, - s->gzhead->extra + s->gzindex, left); - s->pending += left; - HCRC_UPDATE(beg); - s->gzindex = 0; - } - s->status = NAME_STATE; - } - if (s->status == NAME_STATE) { - if (s->gzhead->name != Z_NULL) { - ulg beg = s->pending; /* start of bytes to update crc */ - int val; - do { - if (s->pending == s->pending_buf_size) { - HCRC_UPDATE(beg); - flush_pending(strm); - if (s->pending != 0) { - s->last_flush = -1; - return Z_OK; - } - beg = 0; - } - val = s->gzhead->name[s->gzindex++]; - put_byte(s, val); - } while (val != 0); - HCRC_UPDATE(beg); - s->gzindex = 0; - } - s->status = COMMENT_STATE; - } - if (s->status == COMMENT_STATE) { - if (s->gzhead->comment != Z_NULL) { - ulg beg = s->pending; /* start of bytes to update crc */ - int val; - do { - if (s->pending == s->pending_buf_size) { - HCRC_UPDATE(beg); - flush_pending(strm); - if (s->pending != 0) { - s->last_flush = -1; - return Z_OK; - } - beg = 0; - } - val = s->gzhead->comment[s->gzindex++]; - put_byte(s, val); - } while (val != 0); - HCRC_UPDATE(beg); - } - s->status = HCRC_STATE; - } - if (s->status == HCRC_STATE) { - if (s->gzhead->hcrc) { - if (s->pending + 2 > s->pending_buf_size) { - flush_pending(strm); - if (s->pending != 0) { - s->last_flush = -1; - return Z_OK; - } - } - put_byte(s, (Byte)(strm->adler & 0xff)); - put_byte(s, (Byte)((strm->adler >> 8) & 0xff)); - strm->adler = crc32(0L, Z_NULL, 0); - } - s->status = BUSY_STATE; - - /* Compression must start with an empty pending buffer */ - flush_pending(strm); - if (s->pending != 0) { - s->last_flush = -1; - return Z_OK; - } - } -#endif - - /* Start a new block or continue the current one. - */ - if (strm->avail_in != 0 || s->lookahead != 0 || - (flush != Z_NO_FLUSH && s->status != FINISH_STATE)) { - block_state bstate; - - bstate = s->level == 0 ? deflate_stored(s, flush) : - s->strategy == Z_HUFFMAN_ONLY ? deflate_huff(s, flush) : - s->strategy == Z_RLE ? deflate_rle(s, flush) : - (*(configuration_table[s->level].func))(s, flush); - - if (bstate == finish_started || bstate == finish_done) { - s->status = FINISH_STATE; - } - if (bstate == need_more || bstate == finish_started) { - if (strm->avail_out == 0) { - s->last_flush = -1; /* avoid BUF_ERROR next call, see above */ - } - return Z_OK; - /* If flush != Z_NO_FLUSH && avail_out == 0, the next call - * of deflate should use the same flush parameter to make sure - * that the flush is complete. So we don't have to output an - * empty block here, this will be done at next call. This also - * ensures that for a very small output buffer, we emit at most - * one empty block. - */ - } - if (bstate == block_done) { - if (flush == Z_PARTIAL_FLUSH) { - _tr_align(s); - } else if (flush != Z_BLOCK) { /* FULL_FLUSH or SYNC_FLUSH */ - _tr_stored_block(s, (char*)0, 0L, 0); - /* For a full flush, this empty block will be recognized - * as a special marker by inflate_sync(). - */ - if (flush == Z_FULL_FLUSH) { - CLEAR_HASH(s); /* forget history */ - if (s->lookahead == 0) { - s->strstart = 0; - s->block_start = 0L; - s->insert = 0; - } - } - } - flush_pending(strm); - if (strm->avail_out == 0) { - s->last_flush = -1; /* avoid BUF_ERROR at next call, see above */ - return Z_OK; - } - } - } - - if (flush != Z_FINISH) return Z_OK; - if (s->wrap <= 0) return Z_STREAM_END; - - /* Write the trailer */ -#ifdef GZIP - if (s->wrap == 2) { - put_byte(s, (Byte)(strm->adler & 0xff)); - put_byte(s, (Byte)((strm->adler >> 8) & 0xff)); - put_byte(s, (Byte)((strm->adler >> 16) & 0xff)); - put_byte(s, (Byte)((strm->adler >> 24) & 0xff)); - put_byte(s, (Byte)(strm->total_in & 0xff)); - put_byte(s, (Byte)((strm->total_in >> 8) & 0xff)); - put_byte(s, (Byte)((strm->total_in >> 16) & 0xff)); - put_byte(s, (Byte)((strm->total_in >> 24) & 0xff)); - } - else -#endif - { - putShortMSB(s, (uInt)(strm->adler >> 16)); - putShortMSB(s, (uInt)(strm->adler & 0xffff)); - } - flush_pending(strm); - /* If avail_out is zero, the application will call deflate again - * to flush the rest. - */ - if (s->wrap > 0) s->wrap = -s->wrap; /* write the trailer only once! */ - return s->pending != 0 ? Z_OK : Z_STREAM_END; -} - -/* ========================================================================= */ -int ZEXPORT deflateEnd (strm) - z_streamp strm; -{ - int status; - - if (deflateStateCheck(strm)) return Z_STREAM_ERROR; - - status = strm->state->status; - - /* Deallocate in reverse order of allocations: */ - TRY_FREE(strm, strm->state->pending_buf); - TRY_FREE(strm, strm->state->head); - TRY_FREE(strm, strm->state->prev); - TRY_FREE(strm, strm->state->window); - - ZFREE(strm, strm->state); - strm->state = Z_NULL; - - return status == BUSY_STATE ? Z_DATA_ERROR : Z_OK; -} - -/* ========================================================================= - * Copy the source state to the destination state. - * To simplify the source, this is not supported for 16-bit MSDOS (which - * doesn't have enough memory anyway to duplicate compression states). - */ -int ZEXPORT deflateCopy (dest, source) - z_streamp dest; - z_streamp source; -{ -#ifdef MAXSEG_64K - return Z_STREAM_ERROR; -#else - deflate_state *ds; - deflate_state *ss; - ushf *overlay; - - - if (deflateStateCheck(source) || dest == Z_NULL) { - return Z_STREAM_ERROR; - } - - ss = source->state; - - zmemcpy((voidpf)dest, (voidpf)source, sizeof(z_stream)); - - ds = (deflate_state *) ZALLOC(dest, 1, sizeof(deflate_state)); - if (ds == Z_NULL) return Z_MEM_ERROR; - dest->state = (struct internal_state FAR *) ds; - zmemcpy((voidpf)ds, (voidpf)ss, sizeof(deflate_state)); - ds->strm = dest; - - ds->window = (Bytef *) ZALLOC(dest, ds->w_size, 2*sizeof(Byte)); - ds->prev = (Posf *) ZALLOC(dest, ds->w_size, sizeof(Pos)); - ds->head = (Posf *) ZALLOC(dest, ds->hash_size, sizeof(Pos)); - overlay = (ushf *) ZALLOC(dest, ds->lit_bufsize, sizeof(ush)+2); - ds->pending_buf = (uchf *) overlay; - - if (ds->window == Z_NULL || ds->prev == Z_NULL || ds->head == Z_NULL || - ds->pending_buf == Z_NULL) { - deflateEnd (dest); - return Z_MEM_ERROR; - } - /* following zmemcpy do not work for 16-bit MSDOS */ - zmemcpy(ds->window, ss->window, ds->w_size * 2 * sizeof(Byte)); - zmemcpy((voidpf)ds->prev, (voidpf)ss->prev, ds->w_size * sizeof(Pos)); - zmemcpy((voidpf)ds->head, (voidpf)ss->head, ds->hash_size * sizeof(Pos)); - zmemcpy(ds->pending_buf, ss->pending_buf, (uInt)ds->pending_buf_size); - - ds->pending_out = ds->pending_buf + (ss->pending_out - ss->pending_buf); - ds->d_buf = overlay + ds->lit_bufsize/sizeof(ush); - ds->l_buf = ds->pending_buf + (1+sizeof(ush))*ds->lit_bufsize; - - ds->l_desc.dyn_tree = ds->dyn_ltree; - ds->d_desc.dyn_tree = ds->dyn_dtree; - ds->bl_desc.dyn_tree = ds->bl_tree; - - return Z_OK; -#endif /* MAXSEG_64K */ -} - -/* =========================================================================== - * Read a new buffer from the current input stream, update the adler32 - * and total number of bytes read. All deflate() input goes through - * this function so some applications may wish to modify it to avoid - * allocating a large strm->next_in buffer and copying from it. - * (See also flush_pending()). - */ -local unsigned read_buf(strm, buf, size) - z_streamp strm; - Bytef *buf; - unsigned size; -{ - unsigned len = strm->avail_in; - - if (len > size) len = size; - if (len == 0) return 0; - - strm->avail_in -= len; - - zmemcpy(buf, strm->next_in, len); - if (strm->state->wrap == 1) { - strm->adler = adler32(strm->adler, buf, len); - } -#ifdef GZIP - else if (strm->state->wrap == 2) { - strm->adler = crc32(strm->adler, buf, len); - } -#endif - strm->next_in += len; - strm->total_in += len; - - return len; -} - -/* =========================================================================== - * Initialize the "longest match" routines for a new zlib stream - */ -local void lm_init (s) - deflate_state *s; -{ - s->window_size = (ulg)2L*s->w_size; - - CLEAR_HASH(s); - - /* Set the default configuration parameters: - */ - s->max_lazy_match = configuration_table[s->level].max_lazy; - s->good_match = configuration_table[s->level].good_length; - s->nice_match = configuration_table[s->level].nice_length; - s->max_chain_length = configuration_table[s->level].max_chain; - - s->strstart = 0; - s->block_start = 0L; - s->lookahead = 0; - s->insert = 0; - s->match_length = s->prev_length = MIN_MATCH-1; - s->match_available = 0; - s->ins_h = 0; -#ifndef FASTEST -#ifdef ASMV - match_init(); /* initialize the asm code */ -#endif -#endif -} - -#ifndef FASTEST -/* =========================================================================== - * Set match_start to the longest match starting at the given string and - * return its length. Matches shorter or equal to prev_length are discarded, - * in which case the result is equal to prev_length and match_start is - * garbage. - * IN assertions: cur_match is the head of the hash chain for the current - * string (strstart) and its distance is <= MAX_DIST, and prev_length >= 1 - * OUT assertion: the match length is not greater than s->lookahead. - */ -#ifndef ASMV -/* For 80x86 and 680x0, an optimized version will be provided in match.asm or - * match.S. The code will be functionally equivalent. - */ -local uInt longest_match(s, cur_match) - deflate_state *s; - IPos cur_match; /* current match */ -{ - unsigned chain_length = s->max_chain_length;/* max hash chain length */ - register Bytef *scan = s->window + s->strstart; /* current string */ - register Bytef *match; /* matched string */ - register int len; /* length of current match */ - int best_len = (int)s->prev_length; /* best match length so far */ - int nice_match = s->nice_match; /* stop if match long enough */ - IPos limit = s->strstart > (IPos)MAX_DIST(s) ? - s->strstart - (IPos)MAX_DIST(s) : NIL; - /* Stop when cur_match becomes <= limit. To simplify the code, - * we prevent matches with the string of window index 0. - */ - Posf *prev = s->prev; - uInt wmask = s->w_mask; - -#ifdef UNALIGNED_OK - /* Compare two bytes at a time. Note: this is not always beneficial. - * Try with and without -DUNALIGNED_OK to check. - */ - register Bytef *strend = s->window + s->strstart + MAX_MATCH - 1; - register ush scan_start = *(ushf*)scan; - register ush scan_end = *(ushf*)(scan+best_len-1); -#else - register Bytef *strend = s->window + s->strstart + MAX_MATCH; - register Byte scan_end1 = scan[best_len-1]; - register Byte scan_end = scan[best_len]; -#endif - - /* The code is optimized for HASH_BITS >= 8 and MAX_MATCH-2 multiple of 16. - * It is easy to get rid of this optimization if necessary. - */ - Assert(s->hash_bits >= 8 && MAX_MATCH == 258, "Code too clever"); - - /* Do not waste too much time if we already have a good match: */ - if (s->prev_length >= s->good_match) { - chain_length >>= 2; - } - /* Do not look for matches beyond the end of the input. This is necessary - * to make deflate deterministic. - */ - if ((uInt)nice_match > s->lookahead) nice_match = (int)s->lookahead; - - Assert((ulg)s->strstart <= s->window_size-MIN_LOOKAHEAD, "need lookahead"); - - do { - Assert(cur_match < s->strstart, "no future"); - match = s->window + cur_match; - - /* Skip to next match if the match length cannot increase - * or if the match length is less than 2. Note that the checks below - * for insufficient lookahead only occur occasionally for performance - * reasons. Therefore uninitialized memory will be accessed, and - * conditional jumps will be made that depend on those values. - * However the length of the match is limited to the lookahead, so - * the output of deflate is not affected by the uninitialized values. - */ -#if (defined(UNALIGNED_OK) && MAX_MATCH == 258) - /* This code assumes sizeof(unsigned short) == 2. Do not use - * UNALIGNED_OK if your compiler uses a different size. - */ - if (*(ushf*)(match+best_len-1) != scan_end || - *(ushf*)match != scan_start) continue; - - /* It is not necessary to compare scan[2] and match[2] since they are - * always equal when the other bytes match, given that the hash keys - * are equal and that HASH_BITS >= 8. Compare 2 bytes at a time at - * strstart+3, +5, ... up to strstart+257. We check for insufficient - * lookahead only every 4th comparison; the 128th check will be made - * at strstart+257. If MAX_MATCH-2 is not a multiple of 8, it is - * necessary to put more guard bytes at the end of the window, or - * to check more often for insufficient lookahead. - */ - Assert(scan[2] == match[2], "scan[2]?"); - scan++, match++; - do { - } while (*(ushf*)(scan+=2) == *(ushf*)(match+=2) && - *(ushf*)(scan+=2) == *(ushf*)(match+=2) && - *(ushf*)(scan+=2) == *(ushf*)(match+=2) && - *(ushf*)(scan+=2) == *(ushf*)(match+=2) && - scan < strend); - /* The funny "do {}" generates better code on most compilers */ - - /* Here, scan <= window+strstart+257 */ - Assert(scan <= s->window+(unsigned)(s->window_size-1), "wild scan"); - if (*scan == *match) scan++; - - len = (MAX_MATCH - 1) - (int)(strend-scan); - scan = strend - (MAX_MATCH-1); - -#else /* UNALIGNED_OK */ - - if (match[best_len] != scan_end || - match[best_len-1] != scan_end1 || - *match != *scan || - *++match != scan[1]) continue; - - /* The check at best_len-1 can be removed because it will be made - * again later. (This heuristic is not always a win.) - * It is not necessary to compare scan[2] and match[2] since they - * are always equal when the other bytes match, given that - * the hash keys are equal and that HASH_BITS >= 8. - */ - scan += 2, match++; - Assert(*scan == *match, "match[2]?"); - - /* We check for insufficient lookahead only every 8th comparison; - * the 256th check will be made at strstart+258. - */ - do { - } while (*++scan == *++match && *++scan == *++match && - *++scan == *++match && *++scan == *++match && - *++scan == *++match && *++scan == *++match && - *++scan == *++match && *++scan == *++match && - scan < strend); - - Assert(scan <= s->window+(unsigned)(s->window_size-1), "wild scan"); - - len = MAX_MATCH - (int)(strend - scan); - scan = strend - MAX_MATCH; - -#endif /* UNALIGNED_OK */ - - if (len > best_len) { - s->match_start = cur_match; - best_len = len; - if (len >= nice_match) break; -#ifdef UNALIGNED_OK - scan_end = *(ushf*)(scan+best_len-1); -#else - scan_end1 = scan[best_len-1]; - scan_end = scan[best_len]; -#endif - } - } while ((cur_match = prev[cur_match & wmask]) > limit - && --chain_length != 0); - - if ((uInt)best_len <= s->lookahead) return (uInt)best_len; - return s->lookahead; -} -#endif /* ASMV */ - -#else /* FASTEST */ - -/* --------------------------------------------------------------------------- - * Optimized version for FASTEST only - */ -local uInt longest_match(s, cur_match) - deflate_state *s; - IPos cur_match; /* current match */ -{ - register Bytef *scan = s->window + s->strstart; /* current string */ - register Bytef *match; /* matched string */ - register int len; /* length of current match */ - register Bytef *strend = s->window + s->strstart + MAX_MATCH; - - /* The code is optimized for HASH_BITS >= 8 and MAX_MATCH-2 multiple of 16. - * It is easy to get rid of this optimization if necessary. - */ - Assert(s->hash_bits >= 8 && MAX_MATCH == 258, "Code too clever"); - - Assert((ulg)s->strstart <= s->window_size-MIN_LOOKAHEAD, "need lookahead"); - - Assert(cur_match < s->strstart, "no future"); - - match = s->window + cur_match; - - /* Return failure if the match length is less than 2: - */ - if (match[0] != scan[0] || match[1] != scan[1]) return MIN_MATCH-1; - - /* The check at best_len-1 can be removed because it will be made - * again later. (This heuristic is not always a win.) - * It is not necessary to compare scan[2] and match[2] since they - * are always equal when the other bytes match, given that - * the hash keys are equal and that HASH_BITS >= 8. - */ - scan += 2, match += 2; - Assert(*scan == *match, "match[2]?"); - - /* We check for insufficient lookahead only every 8th comparison; - * the 256th check will be made at strstart+258. - */ - do { - } while (*++scan == *++match && *++scan == *++match && - *++scan == *++match && *++scan == *++match && - *++scan == *++match && *++scan == *++match && - *++scan == *++match && *++scan == *++match && - scan < strend); - - Assert(scan <= s->window+(unsigned)(s->window_size-1), "wild scan"); - - len = MAX_MATCH - (int)(strend - scan); - - if (len < MIN_MATCH) return MIN_MATCH - 1; - - s->match_start = cur_match; - return (uInt)len <= s->lookahead ? (uInt)len : s->lookahead; -} - -#endif /* FASTEST */ - -#ifdef ZLIB_DEBUG - -#define EQUAL 0 -/* result of memcmp for equal strings */ - -/* =========================================================================== - * Check that the match at match_start is indeed a match. - */ -local void check_match(s, start, match, length) - deflate_state *s; - IPos start, match; - int length; -{ - /* check that the match is indeed a match */ - if (zmemcmp(s->window + match, - s->window + start, length) != EQUAL) { - fprintf(stderr, " start %u, match %u, length %d\n", - start, match, length); - do { - fprintf(stderr, "%c%c", s->window[match++], s->window[start++]); - } while (--length != 0); - z_error("invalid match"); - } - if (z_verbose > 1) { - fprintf(stderr,"\\[%d,%d]", start-match, length); - do { putc(s->window[start++], stderr); } while (--length != 0); - } -} -#else -# define check_match(s, start, match, length) -#endif /* ZLIB_DEBUG */ - -/* =========================================================================== - * Fill the window when the lookahead becomes insufficient. - * Updates strstart and lookahead. - * - * IN assertion: lookahead < MIN_LOOKAHEAD - * OUT assertions: strstart <= window_size-MIN_LOOKAHEAD - * At least one byte has been read, or avail_in == 0; reads are - * performed for at least two bytes (required for the zip translate_eol - * option -- not supported here). - */ -local void fill_window(s) - deflate_state *s; -{ - unsigned n; - unsigned more; /* Amount of free space at the end of the window. */ - uInt wsize = s->w_size; - - Assert(s->lookahead < MIN_LOOKAHEAD, "already enough lookahead"); - - do { - more = (unsigned)(s->window_size -(ulg)s->lookahead -(ulg)s->strstart); - - /* Deal with !@#$% 64K limit: */ - if (sizeof(int) <= 2) { - if (more == 0 && s->strstart == 0 && s->lookahead == 0) { - more = wsize; - - } else if (more == (unsigned)(-1)) { - /* Very unlikely, but possible on 16 bit machine if - * strstart == 0 && lookahead == 1 (input done a byte at time) - */ - more--; - } - } - - /* If the window is almost full and there is insufficient lookahead, - * move the upper half to the lower one to make room in the upper half. - */ - if (s->strstart >= wsize+MAX_DIST(s)) { - - zmemcpy(s->window, s->window+wsize, (unsigned)wsize - more); - s->match_start -= wsize; - s->strstart -= wsize; /* we now have strstart >= MAX_DIST */ - s->block_start -= (long) wsize; - slide_hash(s); - more += wsize; - } - if (s->strm->avail_in == 0) break; - - /* If there was no sliding: - * strstart <= WSIZE+MAX_DIST-1 && lookahead <= MIN_LOOKAHEAD - 1 && - * more == window_size - lookahead - strstart - * => more >= window_size - (MIN_LOOKAHEAD-1 + WSIZE + MAX_DIST-1) - * => more >= window_size - 2*WSIZE + 2 - * In the BIG_MEM or MMAP case (not yet supported), - * window_size == input_size + MIN_LOOKAHEAD && - * strstart + s->lookahead <= input_size => more >= MIN_LOOKAHEAD. - * Otherwise, window_size == 2*WSIZE so more >= 2. - * If there was sliding, more >= WSIZE. So in all cases, more >= 2. - */ - Assert(more >= 2, "more < 2"); - - n = read_buf(s->strm, s->window + s->strstart + s->lookahead, more); - s->lookahead += n; - - /* Initialize the hash value now that we have some input: */ - if (s->lookahead + s->insert >= MIN_MATCH) { - uInt str = s->strstart - s->insert; - s->ins_h = s->window[str]; - UPDATE_HASH(s, s->ins_h, s->window[str + 1]); -#if MIN_MATCH != 3 - Call UPDATE_HASH() MIN_MATCH-3 more times -#endif - while (s->insert) { - UPDATE_HASH(s, s->ins_h, s->window[str + MIN_MATCH-1]); -#ifndef FASTEST - s->prev[str & s->w_mask] = s->head[s->ins_h]; -#endif - s->head[s->ins_h] = (Pos)str; - str++; - s->insert--; - if (s->lookahead + s->insert < MIN_MATCH) - break; - } - } - /* If the whole input has less than MIN_MATCH bytes, ins_h is garbage, - * but this is not important since only literal bytes will be emitted. - */ - - } while (s->lookahead < MIN_LOOKAHEAD && s->strm->avail_in != 0); - - /* If the WIN_INIT bytes after the end of the current data have never been - * written, then zero those bytes in order to avoid memory check reports of - * the use of uninitialized (or uninitialised as Julian writes) bytes by - * the longest match routines. Update the high water mark for the next - * time through here. WIN_INIT is set to MAX_MATCH since the longest match - * routines allow scanning to strstart + MAX_MATCH, ignoring lookahead. - */ - if (s->high_water < s->window_size) { - ulg curr = s->strstart + (ulg)(s->lookahead); - ulg init; - - if (s->high_water < curr) { - /* Previous high water mark below current data -- zero WIN_INIT - * bytes or up to end of window, whichever is less. - */ - init = s->window_size - curr; - if (init > WIN_INIT) - init = WIN_INIT; - zmemzero(s->window + curr, (unsigned)init); - s->high_water = curr + init; - } - else if (s->high_water < (ulg)curr + WIN_INIT) { - /* High water mark at or above current data, but below current data - * plus WIN_INIT -- zero out to current data plus WIN_INIT, or up - * to end of window, whichever is less. - */ - init = (ulg)curr + WIN_INIT - s->high_water; - if (init > s->window_size - s->high_water) - init = s->window_size - s->high_water; - zmemzero(s->window + s->high_water, (unsigned)init); - s->high_water += init; - } - } - - Assert((ulg)s->strstart <= s->window_size - MIN_LOOKAHEAD, - "not enough room for search"); -} - -/* =========================================================================== - * Flush the current block, with given end-of-file flag. - * IN assertion: strstart is set to the end of the current match. - */ -#define FLUSH_BLOCK_ONLY(s, last) { \ - _tr_flush_block(s, (s->block_start >= 0L ? \ - (charf *)&s->window[(unsigned)s->block_start] : \ - (charf *)Z_NULL), \ - (ulg)((long)s->strstart - s->block_start), \ - (last)); \ - s->block_start = s->strstart; \ - flush_pending(s->strm); \ - Tracev((stderr,"[FLUSH]")); \ -} - -/* Same but force premature exit if necessary. */ -#define FLUSH_BLOCK(s, last) { \ - FLUSH_BLOCK_ONLY(s, last); \ - if (s->strm->avail_out == 0) return (last) ? finish_started : need_more; \ -} - -/* Maximum stored block length in deflate format (not including header). */ -#define MAX_STORED 65535 - -/* Minimum of a and b. */ -#define MIN(a, b) ((a) > (b) ? (b) : (a)) - -/* =========================================================================== - * Copy without compression as much as possible from the input stream, return - * the current block state. - * - * In case deflateParams() is used to later switch to a non-zero compression - * level, s->matches (otherwise unused when storing) keeps track of the number - * of hash table slides to perform. If s->matches is 1, then one hash table - * slide will be done when switching. If s->matches is 2, the maximum value - * allowed here, then the hash table will be cleared, since two or more slides - * is the same as a clear. - * - * deflate_stored() is written to minimize the number of times an input byte is - * copied. It is most efficient with large input and output buffers, which - * maximizes the opportunites to have a single copy from next_in to next_out. - */ -local block_state deflate_stored(s, flush) - deflate_state *s; - int flush; -{ - /* Smallest worthy block size when not flushing or finishing. By default - * this is 32K. This can be as small as 507 bytes for memLevel == 1. For - * large input and output buffers, the stored block size will be larger. - */ - unsigned min_block = MIN(s->pending_buf_size - 5, s->w_size); - - /* Copy as many min_block or larger stored blocks directly to next_out as - * possible. If flushing, copy the remaining available input to next_out as - * stored blocks, if there is enough space. - */ - unsigned len, left, have, last = 0; - unsigned used = s->strm->avail_in; - do { - /* Set len to the maximum size block that we can copy directly with the - * available input data and output space. Set left to how much of that - * would be copied from what's left in the window. - */ - len = MAX_STORED; /* maximum deflate stored block length */ - have = (s->bi_valid + 42) >> 3; /* number of header bytes */ - if (s->strm->avail_out < have) /* need room for header */ - break; - /* maximum stored block length that will fit in avail_out: */ - have = s->strm->avail_out - have; - left = s->strstart - s->block_start; /* bytes left in window */ - if (len > (ulg)left + s->strm->avail_in) - len = left + s->strm->avail_in; /* limit len to the input */ - if (len > have) - len = have; /* limit len to the output */ - - /* If the stored block would be less than min_block in length, or if - * unable to copy all of the available input when flushing, then try - * copying to the window and the pending buffer instead. Also don't - * write an empty block when flushing -- deflate() does that. - */ - if (len < min_block && ((len == 0 && flush != Z_FINISH) || - flush == Z_NO_FLUSH || - len != left + s->strm->avail_in)) - break; - - /* Make a dummy stored block in pending to get the header bytes, - * including any pending bits. This also updates the debugging counts. - */ - last = flush == Z_FINISH && len == left + s->strm->avail_in ? 1 : 0; - _tr_stored_block(s, (char *)0, 0L, last); - - /* Replace the lengths in the dummy stored block with len. */ - s->pending_buf[s->pending - 4] = len; - s->pending_buf[s->pending - 3] = len >> 8; - s->pending_buf[s->pending - 2] = ~len; - s->pending_buf[s->pending - 1] = ~len >> 8; - - /* Write the stored block header bytes. */ - flush_pending(s->strm); - -#ifdef ZLIB_DEBUG - /* Update debugging counts for the data about to be copied. */ - s->compressed_len += len << 3; - s->bits_sent += len << 3; -#endif - - /* Copy uncompressed bytes from the window to next_out. */ - if (left) { - if (left > len) - left = len; - zmemcpy(s->strm->next_out, s->window + s->block_start, left); - s->strm->next_out += left; - s->strm->avail_out -= left; - s->strm->total_out += left; - s->block_start += left; - len -= left; - } - - /* Copy uncompressed bytes directly from next_in to next_out, updating - * the check value. - */ - if (len) { - read_buf(s->strm, s->strm->next_out, len); - s->strm->next_out += len; - s->strm->avail_out -= len; - s->strm->total_out += len; - } - } while (last == 0); - - /* Update the sliding window with the last s->w_size bytes of the copied - * data, or append all of the copied data to the existing window if less - * than s->w_size bytes were copied. Also update the number of bytes to - * insert in the hash tables, in the event that deflateParams() switches to - * a non-zero compression level. - */ - used -= s->strm->avail_in; /* number of input bytes directly copied */ - if (used) { - /* If any input was used, then no unused input remains in the window, - * therefore s->block_start == s->strstart. - */ - if (used >= s->w_size) { /* supplant the previous history */ - s->matches = 2; /* clear hash */ - zmemcpy(s->window, s->strm->next_in - s->w_size, s->w_size); - s->strstart = s->w_size; - } - else { - if (s->window_size - s->strstart <= used) { - /* Slide the window down. */ - s->strstart -= s->w_size; - zmemcpy(s->window, s->window + s->w_size, s->strstart); - if (s->matches < 2) - s->matches++; /* add a pending slide_hash() */ - } - zmemcpy(s->window + s->strstart, s->strm->next_in - used, used); - s->strstart += used; - } - s->block_start = s->strstart; - s->insert += MIN(used, s->w_size - s->insert); - } - if (s->high_water < s->strstart) - s->high_water = s->strstart; - - /* If the last block was written to next_out, then done. */ - if (last) - return finish_done; - - /* If flushing and all input has been consumed, then done. */ - if (flush != Z_NO_FLUSH && flush != Z_FINISH && - s->strm->avail_in == 0 && (long)s->strstart == s->block_start) - return block_done; - - /* Fill the window with any remaining input. */ - have = s->window_size - s->strstart - 1; - if (s->strm->avail_in > have && s->block_start >= (long)s->w_size) { - /* Slide the window down. */ - s->block_start -= s->w_size; - s->strstart -= s->w_size; - zmemcpy(s->window, s->window + s->w_size, s->strstart); - if (s->matches < 2) - s->matches++; /* add a pending slide_hash() */ - have += s->w_size; /* more space now */ - } - if (have > s->strm->avail_in) - have = s->strm->avail_in; - if (have) { - read_buf(s->strm, s->window + s->strstart, have); - s->strstart += have; - } - if (s->high_water < s->strstart) - s->high_water = s->strstart; - - /* There was not enough avail_out to write a complete worthy or flushed - * stored block to next_out. Write a stored block to pending instead, if we - * have enough input for a worthy block, or if flushing and there is enough - * room for the remaining input as a stored block in the pending buffer. - */ - have = (s->bi_valid + 42) >> 3; /* number of header bytes */ - /* maximum stored block length that will fit in pending: */ - have = MIN(s->pending_buf_size - have, MAX_STORED); - min_block = MIN(have, s->w_size); - left = s->strstart - s->block_start; - if (left >= min_block || - ((left || flush == Z_FINISH) && flush != Z_NO_FLUSH && - s->strm->avail_in == 0 && left <= have)) { - len = MIN(left, have); - last = flush == Z_FINISH && s->strm->avail_in == 0 && - len == left ? 1 : 0; - _tr_stored_block(s, (charf *)s->window + s->block_start, len, last); - s->block_start += len; - flush_pending(s->strm); - } - - /* We've done all we can with the available input and output. */ - return last ? finish_started : need_more; -} - -/* =========================================================================== - * Compress as much as possible from the input stream, return the current - * block state. - * This function does not perform lazy evaluation of matches and inserts - * new strings in the dictionary only for unmatched strings or for short - * matches. It is used only for the fast compression options. - */ -local block_state deflate_fast(s, flush) - deflate_state *s; - int flush; -{ - IPos hash_head; /* head of the hash chain */ - int bflush; /* set if current block must be flushed */ - - for (;;) { - /* Make sure that we always have enough lookahead, except - * at the end of the input file. We need MAX_MATCH bytes - * for the next match, plus MIN_MATCH bytes to insert the - * string following the next match. - */ - if (s->lookahead < MIN_LOOKAHEAD) { - fill_window(s); - if (s->lookahead < MIN_LOOKAHEAD && flush == Z_NO_FLUSH) { - return need_more; - } - if (s->lookahead == 0) break; /* flush the current block */ - } - - /* Insert the string window[strstart .. strstart+2] in the - * dictionary, and set hash_head to the head of the hash chain: - */ - hash_head = NIL; - if (s->lookahead >= MIN_MATCH) { - INSERT_STRING(s, s->strstart, hash_head); - } - - /* Find the longest match, discarding those <= prev_length. - * At this point we have always match_length < MIN_MATCH - */ - if (hash_head != NIL && s->strstart - hash_head <= MAX_DIST(s)) { - /* To simplify the code, we prevent matches with the string - * of window index 0 (in particular we have to avoid a match - * of the string with itself at the start of the input file). - */ - s->match_length = longest_match (s, hash_head); - /* longest_match() sets match_start */ - } - if (s->match_length >= MIN_MATCH) { - check_match(s, s->strstart, s->match_start, s->match_length); - - _tr_tally_dist(s, s->strstart - s->match_start, - s->match_length - MIN_MATCH, bflush); - - s->lookahead -= s->match_length; - - /* Insert new strings in the hash table only if the match length - * is not too large. This saves time but degrades compression. - */ -#ifndef FASTEST - if (s->match_length <= s->max_insert_length && - s->lookahead >= MIN_MATCH) { - s->match_length--; /* string at strstart already in table */ - do { - s->strstart++; - INSERT_STRING(s, s->strstart, hash_head); - /* strstart never exceeds WSIZE-MAX_MATCH, so there are - * always MIN_MATCH bytes ahead. - */ - } while (--s->match_length != 0); - s->strstart++; - } else -#endif - { - s->strstart += s->match_length; - s->match_length = 0; - s->ins_h = s->window[s->strstart]; - UPDATE_HASH(s, s->ins_h, s->window[s->strstart+1]); -#if MIN_MATCH != 3 - Call UPDATE_HASH() MIN_MATCH-3 more times -#endif - /* If lookahead < MIN_MATCH, ins_h is garbage, but it does not - * matter since it will be recomputed at next deflate call. - */ - } - } else { - /* No match, output a literal byte */ - Tracevv((stderr,"%c", s->window[s->strstart])); - _tr_tally_lit (s, s->window[s->strstart], bflush); - s->lookahead--; - s->strstart++; - } - if (bflush) FLUSH_BLOCK(s, 0); - } - s->insert = s->strstart < MIN_MATCH-1 ? s->strstart : MIN_MATCH-1; - if (flush == Z_FINISH) { - FLUSH_BLOCK(s, 1); - return finish_done; - } - if (s->last_lit) - FLUSH_BLOCK(s, 0); - return block_done; -} - -#ifndef FASTEST -/* =========================================================================== - * Same as above, but achieves better compression. We use a lazy - * evaluation for matches: a match is finally adopted only if there is - * no better match at the next window position. - */ -local block_state deflate_slow(s, flush) - deflate_state *s; - int flush; -{ - IPos hash_head; /* head of hash chain */ - int bflush; /* set if current block must be flushed */ - - /* Process the input block. */ - for (;;) { - /* Make sure that we always have enough lookahead, except - * at the end of the input file. We need MAX_MATCH bytes - * for the next match, plus MIN_MATCH bytes to insert the - * string following the next match. - */ - if (s->lookahead < MIN_LOOKAHEAD) { - fill_window(s); - if (s->lookahead < MIN_LOOKAHEAD && flush == Z_NO_FLUSH) { - return need_more; - } - if (s->lookahead == 0) break; /* flush the current block */ - } - - /* Insert the string window[strstart .. strstart+2] in the - * dictionary, and set hash_head to the head of the hash chain: - */ - hash_head = NIL; - if (s->lookahead >= MIN_MATCH) { - INSERT_STRING(s, s->strstart, hash_head); - } - - /* Find the longest match, discarding those <= prev_length. - */ - s->prev_length = s->match_length, s->prev_match = s->match_start; - s->match_length = MIN_MATCH-1; - - if (hash_head != NIL && s->prev_length < s->max_lazy_match && - s->strstart - hash_head <= MAX_DIST(s)) { - /* To simplify the code, we prevent matches with the string - * of window index 0 (in particular we have to avoid a match - * of the string with itself at the start of the input file). - */ - s->match_length = longest_match (s, hash_head); - /* longest_match() sets match_start */ - - if (s->match_length <= 5 && (s->strategy == Z_FILTERED -#if TOO_FAR <= 32767 - || (s->match_length == MIN_MATCH && - s->strstart - s->match_start > TOO_FAR) -#endif - )) { - - /* If prev_match is also MIN_MATCH, match_start is garbage - * but we will ignore the current match anyway. - */ - s->match_length = MIN_MATCH-1; - } - } - /* If there was a match at the previous step and the current - * match is not better, output the previous match: - */ - if (s->prev_length >= MIN_MATCH && s->match_length <= s->prev_length) { - uInt max_insert = s->strstart + s->lookahead - MIN_MATCH; - /* Do not insert strings in hash table beyond this. */ - - check_match(s, s->strstart-1, s->prev_match, s->prev_length); - - _tr_tally_dist(s, s->strstart -1 - s->prev_match, - s->prev_length - MIN_MATCH, bflush); - - /* Insert in hash table all strings up to the end of the match. - * strstart-1 and strstart are already inserted. If there is not - * enough lookahead, the last two strings are not inserted in - * the hash table. - */ - s->lookahead -= s->prev_length-1; - s->prev_length -= 2; - do { - if (++s->strstart <= max_insert) { - INSERT_STRING(s, s->strstart, hash_head); - } - } while (--s->prev_length != 0); - s->match_available = 0; - s->match_length = MIN_MATCH-1; - s->strstart++; - - if (bflush) FLUSH_BLOCK(s, 0); - - } else if (s->match_available) { - /* If there was no match at the previous position, output a - * single literal. If there was a match but the current match - * is longer, truncate the previous match to a single literal. - */ - Tracevv((stderr,"%c", s->window[s->strstart-1])); - _tr_tally_lit(s, s->window[s->strstart-1], bflush); - if (bflush) { - FLUSH_BLOCK_ONLY(s, 0); - } - s->strstart++; - s->lookahead--; - if (s->strm->avail_out == 0) return need_more; - } else { - /* There is no previous match to compare with, wait for - * the next step to decide. - */ - s->match_available = 1; - s->strstart++; - s->lookahead--; - } - } - Assert (flush != Z_NO_FLUSH, "no flush?"); - if (s->match_available) { - Tracevv((stderr,"%c", s->window[s->strstart-1])); - _tr_tally_lit(s, s->window[s->strstart-1], bflush); - s->match_available = 0; - } - s->insert = s->strstart < MIN_MATCH-1 ? s->strstart : MIN_MATCH-1; - if (flush == Z_FINISH) { - FLUSH_BLOCK(s, 1); - return finish_done; - } - if (s->last_lit) - FLUSH_BLOCK(s, 0); - return block_done; -} -#endif /* FASTEST */ - -/* =========================================================================== - * For Z_RLE, simply look for runs of bytes, generate matches only of distance - * one. Do not maintain a hash table. (It will be regenerated if this run of - * deflate switches away from Z_RLE.) - */ -local block_state deflate_rle(s, flush) - deflate_state *s; - int flush; -{ - int bflush; /* set if current block must be flushed */ - uInt prev; /* byte at distance one to match */ - Bytef *scan, *strend; /* scan goes up to strend for length of run */ - - for (;;) { - /* Make sure that we always have enough lookahead, except - * at the end of the input file. We need MAX_MATCH bytes - * for the longest run, plus one for the unrolled loop. - */ - if (s->lookahead <= MAX_MATCH) { - fill_window(s); - if (s->lookahead <= MAX_MATCH && flush == Z_NO_FLUSH) { - return need_more; - } - if (s->lookahead == 0) break; /* flush the current block */ - } - - /* See how many times the previous byte repeats */ - s->match_length = 0; - if (s->lookahead >= MIN_MATCH && s->strstart > 0) { - scan = s->window + s->strstart - 1; - prev = *scan; - if (prev == *++scan && prev == *++scan && prev == *++scan) { - strend = s->window + s->strstart + MAX_MATCH; - do { - } while (prev == *++scan && prev == *++scan && - prev == *++scan && prev == *++scan && - prev == *++scan && prev == *++scan && - prev == *++scan && prev == *++scan && - scan < strend); - s->match_length = MAX_MATCH - (uInt)(strend - scan); - if (s->match_length > s->lookahead) - s->match_length = s->lookahead; - } - Assert(scan <= s->window+(uInt)(s->window_size-1), "wild scan"); - } - - /* Emit match if have run of MIN_MATCH or longer, else emit literal */ - if (s->match_length >= MIN_MATCH) { - check_match(s, s->strstart, s->strstart - 1, s->match_length); - - _tr_tally_dist(s, 1, s->match_length - MIN_MATCH, bflush); - - s->lookahead -= s->match_length; - s->strstart += s->match_length; - s->match_length = 0; - } else { - /* No match, output a literal byte */ - Tracevv((stderr,"%c", s->window[s->strstart])); - _tr_tally_lit (s, s->window[s->strstart], bflush); - s->lookahead--; - s->strstart++; - } - if (bflush) FLUSH_BLOCK(s, 0); - } - s->insert = 0; - if (flush == Z_FINISH) { - FLUSH_BLOCK(s, 1); - return finish_done; - } - if (s->last_lit) - FLUSH_BLOCK(s, 0); - return block_done; -} - -/* =========================================================================== - * For Z_HUFFMAN_ONLY, do not look for matches. Do not maintain a hash table. - * (It will be regenerated if this run of deflate switches away from Huffman.) - */ -local block_state deflate_huff(s, flush) - deflate_state *s; - int flush; -{ - int bflush; /* set if current block must be flushed */ - - for (;;) { - /* Make sure that we have a literal to write. */ - if (s->lookahead == 0) { - fill_window(s); - if (s->lookahead == 0) { - if (flush == Z_NO_FLUSH) - return need_more; - break; /* flush the current block */ - } - } - - /* Output a literal byte */ - s->match_length = 0; - Tracevv((stderr,"%c", s->window[s->strstart])); - _tr_tally_lit (s, s->window[s->strstart], bflush); - s->lookahead--; - s->strstart++; - if (bflush) FLUSH_BLOCK(s, 0); - } - s->insert = 0; - if (flush == Z_FINISH) { - FLUSH_BLOCK(s, 1); - return finish_done; - } - if (s->last_lit) - FLUSH_BLOCK(s, 0); - return block_done; -} diff --git a/deps/zlib/deflate.h b/deps/zlib/deflate.h deleted file mode 100644 index 23ecdd3..0000000 --- a/deps/zlib/deflate.h +++ /dev/null @@ -1,349 +0,0 @@ -/* deflate.h -- internal compression state - * Copyright (C) 1995-2016 Jean-loup Gailly - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -/* WARNING: this file should *not* be used by applications. It is - part of the implementation of the compression library and is - subject to change. Applications should only use zlib.h. - */ - -/* @(#) $Id$ */ - -#ifndef DEFLATE_H -#define DEFLATE_H - -#include "zutil.h" - -/* define NO_GZIP when compiling if you want to disable gzip header and - trailer creation by deflate(). NO_GZIP would be used to avoid linking in - the crc code when it is not needed. For shared libraries, gzip encoding - should be left enabled. */ -#ifndef NO_GZIP -# define GZIP -#endif - -/* =========================================================================== - * Internal compression state. - */ - -#define LENGTH_CODES 29 -/* number of length codes, not counting the special END_BLOCK code */ - -#define LITERALS 256 -/* number of literal bytes 0..255 */ - -#define L_CODES (LITERALS+1+LENGTH_CODES) -/* number of Literal or Length codes, including the END_BLOCK code */ - -#define D_CODES 30 -/* number of distance codes */ - -#define BL_CODES 19 -/* number of codes used to transfer the bit lengths */ - -#define HEAP_SIZE (2*L_CODES+1) -/* maximum heap size */ - -#define MAX_BITS 15 -/* All codes must not exceed MAX_BITS bits */ - -#define Buf_size 16 -/* size of bit buffer in bi_buf */ - -#define INIT_STATE 42 /* zlib header -> BUSY_STATE */ -#ifdef GZIP -# define GZIP_STATE 57 /* gzip header -> BUSY_STATE | EXTRA_STATE */ -#endif -#define EXTRA_STATE 69 /* gzip extra block -> NAME_STATE */ -#define NAME_STATE 73 /* gzip file name -> COMMENT_STATE */ -#define COMMENT_STATE 91 /* gzip comment -> HCRC_STATE */ -#define HCRC_STATE 103 /* gzip header CRC -> BUSY_STATE */ -#define BUSY_STATE 113 /* deflate -> FINISH_STATE */ -#define FINISH_STATE 666 /* stream complete */ -/* Stream status */ - - -/* Data structure describing a single value and its code string. */ -typedef struct ct_data_s { - union { - ush freq; /* frequency count */ - ush code; /* bit string */ - } fc; - union { - ush dad; /* father node in Huffman tree */ - ush len; /* length of bit string */ - } dl; -} FAR ct_data; - -#define Freq fc.freq -#define Code fc.code -#define Dad dl.dad -#define Len dl.len - -typedef struct static_tree_desc_s static_tree_desc; - -typedef struct tree_desc_s { - ct_data *dyn_tree; /* the dynamic tree */ - int max_code; /* largest code with non zero frequency */ - const static_tree_desc *stat_desc; /* the corresponding static tree */ -} FAR tree_desc; - -typedef ush Pos; -typedef Pos FAR Posf; -typedef unsigned IPos; - -/* A Pos is an index in the character window. We use short instead of int to - * save space in the various tables. IPos is used only for parameter passing. - */ - -typedef struct internal_state { - z_streamp strm; /* pointer back to this zlib stream */ - int status; /* as the name implies */ - Bytef *pending_buf; /* output still pending */ - ulg pending_buf_size; /* size of pending_buf */ - Bytef *pending_out; /* next pending byte to output to the stream */ - ulg pending; /* nb of bytes in the pending buffer */ - int wrap; /* bit 0 true for zlib, bit 1 true for gzip */ - gz_headerp gzhead; /* gzip header information to write */ - ulg gzindex; /* where in extra, name, or comment */ - Byte method; /* can only be DEFLATED */ - int last_flush; /* value of flush param for previous deflate call */ - - /* used by deflate.c: */ - - uInt w_size; /* LZ77 window size (32K by default) */ - uInt w_bits; /* log2(w_size) (8..16) */ - uInt w_mask; /* w_size - 1 */ - - Bytef *window; - /* Sliding window. Input bytes are read into the second half of the window, - * and move to the first half later to keep a dictionary of at least wSize - * bytes. With this organization, matches are limited to a distance of - * wSize-MAX_MATCH bytes, but this ensures that IO is always - * performed with a length multiple of the block size. Also, it limits - * the window size to 64K, which is quite useful on MSDOS. - * To do: use the user input buffer as sliding window. - */ - - ulg window_size; - /* Actual size of window: 2*wSize, except when the user input buffer - * is directly used as sliding window. - */ - - Posf *prev; - /* Link to older string with same hash index. To limit the size of this - * array to 64K, this link is maintained only for the last 32K strings. - * An index in this array is thus a window index modulo 32K. - */ - - Posf *head; /* Heads of the hash chains or NIL. */ - - uInt ins_h; /* hash index of string to be inserted */ - uInt hash_size; /* number of elements in hash table */ - uInt hash_bits; /* log2(hash_size) */ - uInt hash_mask; /* hash_size-1 */ - - uInt hash_shift; - /* Number of bits by which ins_h must be shifted at each input - * step. It must be such that after MIN_MATCH steps, the oldest - * byte no longer takes part in the hash key, that is: - * hash_shift * MIN_MATCH >= hash_bits - */ - - long block_start; - /* Window position at the beginning of the current output block. Gets - * negative when the window is moved backwards. - */ - - uInt match_length; /* length of best match */ - IPos prev_match; /* previous match */ - int match_available; /* set if previous match exists */ - uInt strstart; /* start of string to insert */ - uInt match_start; /* start of matching string */ - uInt lookahead; /* number of valid bytes ahead in window */ - - uInt prev_length; - /* Length of the best match at previous step. Matches not greater than this - * are discarded. This is used in the lazy match evaluation. - */ - - uInt max_chain_length; - /* To speed up deflation, hash chains are never searched beyond this - * length. A higher limit improves compression ratio but degrades the - * speed. - */ - - uInt max_lazy_match; - /* Attempt to find a better match only when the current match is strictly - * smaller than this value. This mechanism is used only for compression - * levels >= 4. - */ -# define max_insert_length max_lazy_match - /* Insert new strings in the hash table only if the match length is not - * greater than this length. This saves time but degrades compression. - * max_insert_length is used only for compression levels <= 3. - */ - - int level; /* compression level (1..9) */ - int strategy; /* favor or force Huffman coding*/ - - uInt good_match; - /* Use a faster search when the previous match is longer than this */ - - int nice_match; /* Stop searching when current match exceeds this */ - - /* used by trees.c: */ - /* Didn't use ct_data typedef below to suppress compiler warning */ - struct ct_data_s dyn_ltree[HEAP_SIZE]; /* literal and length tree */ - struct ct_data_s dyn_dtree[2*D_CODES+1]; /* distance tree */ - struct ct_data_s bl_tree[2*BL_CODES+1]; /* Huffman tree for bit lengths */ - - struct tree_desc_s l_desc; /* desc. for literal tree */ - struct tree_desc_s d_desc; /* desc. for distance tree */ - struct tree_desc_s bl_desc; /* desc. for bit length tree */ - - ush bl_count[MAX_BITS+1]; - /* number of codes at each bit length for an optimal tree */ - - int heap[2*L_CODES+1]; /* heap used to build the Huffman trees */ - int heap_len; /* number of elements in the heap */ - int heap_max; /* element of largest frequency */ - /* The sons of heap[n] are heap[2*n] and heap[2*n+1]. heap[0] is not used. - * The same heap array is used to build all trees. - */ - - uch depth[2*L_CODES+1]; - /* Depth of each subtree used as tie breaker for trees of equal frequency - */ - - uchf *l_buf; /* buffer for literals or lengths */ - - uInt lit_bufsize; - /* Size of match buffer for literals/lengths. There are 4 reasons for - * limiting lit_bufsize to 64K: - * - frequencies can be kept in 16 bit counters - * - if compression is not successful for the first block, all input - * data is still in the window so we can still emit a stored block even - * when input comes from standard input. (This can also be done for - * all blocks if lit_bufsize is not greater than 32K.) - * - if compression is not successful for a file smaller than 64K, we can - * even emit a stored file instead of a stored block (saving 5 bytes). - * This is applicable only for zip (not gzip or zlib). - * - creating new Huffman trees less frequently may not provide fast - * adaptation to changes in the input data statistics. (Take for - * example a binary file with poorly compressible code followed by - * a highly compressible string table.) Smaller buffer sizes give - * fast adaptation but have of course the overhead of transmitting - * trees more frequently. - * - I can't count above 4 - */ - - uInt last_lit; /* running index in l_buf */ - - ushf *d_buf; - /* Buffer for distances. To simplify the code, d_buf and l_buf have - * the same number of elements. To use different lengths, an extra flag - * array would be necessary. - */ - - ulg opt_len; /* bit length of current block with optimal trees */ - ulg static_len; /* bit length of current block with static trees */ - uInt matches; /* number of string matches in current block */ - uInt insert; /* bytes at end of window left to insert */ - -#ifdef ZLIB_DEBUG - ulg compressed_len; /* total bit length of compressed file mod 2^32 */ - ulg bits_sent; /* bit length of compressed data sent mod 2^32 */ -#endif - - ush bi_buf; - /* Output buffer. bits are inserted starting at the bottom (least - * significant bits). - */ - int bi_valid; - /* Number of valid bits in bi_buf. All bits above the last valid bit - * are always zero. - */ - - ulg high_water; - /* High water mark offset in window for initialized bytes -- bytes above - * this are set to zero in order to avoid memory check warnings when - * longest match routines access bytes past the input. This is then - * updated to the new high water mark. - */ - -} FAR deflate_state; - -/* Output a byte on the stream. - * IN assertion: there is enough room in pending_buf. - */ -#define put_byte(s, c) {s->pending_buf[s->pending++] = (Bytef)(c);} - - -#define MIN_LOOKAHEAD (MAX_MATCH+MIN_MATCH+1) -/* Minimum amount of lookahead, except at the end of the input file. - * See deflate.c for comments about the MIN_MATCH+1. - */ - -#define MAX_DIST(s) ((s)->w_size-MIN_LOOKAHEAD) -/* In order to simplify the code, particularly on 16 bit machines, match - * distances are limited to MAX_DIST instead of WSIZE. - */ - -#define WIN_INIT MAX_MATCH -/* Number of bytes after end of data in window to initialize in order to avoid - memory checker errors from longest match routines */ - - /* in trees.c */ -void ZLIB_INTERNAL _tr_init OF((deflate_state *s)); -int ZLIB_INTERNAL _tr_tally OF((deflate_state *s, unsigned dist, unsigned lc)); -void ZLIB_INTERNAL _tr_flush_block OF((deflate_state *s, charf *buf, - ulg stored_len, int last)); -void ZLIB_INTERNAL _tr_flush_bits OF((deflate_state *s)); -void ZLIB_INTERNAL _tr_align OF((deflate_state *s)); -void ZLIB_INTERNAL _tr_stored_block OF((deflate_state *s, charf *buf, - ulg stored_len, int last)); - -#define d_code(dist) \ - ((dist) < 256 ? _dist_code[dist] : _dist_code[256+((dist)>>7)]) -/* Mapping from a distance to a distance code. dist is the distance - 1 and - * must not have side effects. _dist_code[256] and _dist_code[257] are never - * used. - */ - -#ifndef ZLIB_DEBUG -/* Inline versions of _tr_tally for speed: */ - -#if defined(GEN_TREES_H) || !defined(STDC) - extern uch ZLIB_INTERNAL _length_code[]; - extern uch ZLIB_INTERNAL _dist_code[]; -#else - extern const uch ZLIB_INTERNAL _length_code[]; - extern const uch ZLIB_INTERNAL _dist_code[]; -#endif - -# define _tr_tally_lit(s, c, flush) \ - { uch cc = (c); \ - s->d_buf[s->last_lit] = 0; \ - s->l_buf[s->last_lit++] = cc; \ - s->dyn_ltree[cc].Freq++; \ - flush = (s->last_lit == s->lit_bufsize-1); \ - } -# define _tr_tally_dist(s, distance, length, flush) \ - { uch len = (uch)(length); \ - ush dist = (ush)(distance); \ - s->d_buf[s->last_lit] = dist; \ - s->l_buf[s->last_lit++] = len; \ - dist--; \ - s->dyn_ltree[_length_code[len]+LITERALS+1].Freq++; \ - s->dyn_dtree[d_code(dist)].Freq++; \ - flush = (s->last_lit == s->lit_bufsize-1); \ - } -#else -# define _tr_tally_lit(s, c, flush) flush = _tr_tally(s, 0, c) -# define _tr_tally_dist(s, distance, length, flush) \ - flush = _tr_tally(s, distance, length) -#endif - -#endif /* DEFLATE_H */ diff --git a/deps/zlib/gzguts.h b/deps/zlib/gzguts.h deleted file mode 100644 index 990a4d2..0000000 --- a/deps/zlib/gzguts.h +++ /dev/null @@ -1,218 +0,0 @@ -/* gzguts.h -- zlib internal header definitions for gz* operations - * Copyright (C) 2004, 2005, 2010, 2011, 2012, 2013, 2016 Mark Adler - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -#ifdef _LARGEFILE64_SOURCE -# ifndef _LARGEFILE_SOURCE -# define _LARGEFILE_SOURCE 1 -# endif -# ifdef _FILE_OFFSET_BITS -# undef _FILE_OFFSET_BITS -# endif -#endif - -#ifdef HAVE_HIDDEN -# define ZLIB_INTERNAL __attribute__((visibility ("hidden"))) -#else -# define ZLIB_INTERNAL -#endif - -#include -#include "zlib.h" -#ifdef STDC -# include -# include -# include -#endif - -#ifndef _POSIX_SOURCE -# define _POSIX_SOURCE -#endif -#include - -#ifdef _WIN32 -# include -#endif - -#if defined(__TURBOC__) || defined(_MSC_VER) || defined(_WIN32) -# include -#endif - -#if defined(_WIN32) || defined(__CYGWIN__) -# define WIDECHAR -#endif - -#ifdef WINAPI_FAMILY -# define open _open -# define read _read -# define write _write -# define close _close -#endif - -#ifdef NO_DEFLATE /* for compatibility with old definition */ -# define NO_GZCOMPRESS -#endif - -#if defined(STDC99) || (defined(__TURBOC__) && __TURBOC__ >= 0x550) -# ifndef HAVE_VSNPRINTF -# define HAVE_VSNPRINTF -# endif -#endif - -#if defined(__CYGWIN__) -# ifndef HAVE_VSNPRINTF -# define HAVE_VSNPRINTF -# endif -#endif - -#if defined(MSDOS) && defined(__BORLANDC__) && (BORLANDC > 0x410) -# ifndef HAVE_VSNPRINTF -# define HAVE_VSNPRINTF -# endif -#endif - -#ifndef HAVE_VSNPRINTF -# ifdef MSDOS -/* vsnprintf may exist on some MS-DOS compilers (DJGPP?), - but for now we just assume it doesn't. */ -# define NO_vsnprintf -# endif -# ifdef __TURBOC__ -# define NO_vsnprintf -# endif -# ifdef WIN32 -/* In Win32, vsnprintf is available as the "non-ANSI" _vsnprintf. */ -# if !defined(vsnprintf) && !defined(NO_vsnprintf) -# if !defined(_MSC_VER) || ( defined(_MSC_VER) && _MSC_VER < 1500 ) -# define vsnprintf _vsnprintf -# endif -# endif -# endif -# ifdef __SASC -# define NO_vsnprintf -# endif -# ifdef VMS -# define NO_vsnprintf -# endif -# ifdef __OS400__ -# define NO_vsnprintf -# endif -# ifdef __MVS__ -# define NO_vsnprintf -# endif -#endif - -/* unlike snprintf (which is required in C99), _snprintf does not guarantee - null termination of the result -- however this is only used in gzlib.c where - the result is assured to fit in the space provided */ -#if defined(_MSC_VER) && _MSC_VER < 1900 -# define snprintf _snprintf -#endif - -#ifndef local -# define local static -#endif -/* since "static" is used to mean two completely different things in C, we - define "local" for the non-static meaning of "static", for readability - (compile with -Dlocal if your debugger can't find static symbols) */ - -/* gz* functions always use library allocation functions */ -#ifndef STDC - extern voidp malloc OF((uInt size)); - extern void free OF((voidpf ptr)); -#endif - -/* get errno and strerror definition */ -#if defined UNDER_CE -# include -# define zstrerror() gz_strwinerror((DWORD)GetLastError()) -#else -# ifndef NO_STRERROR -# include -# define zstrerror() strerror(errno) -# else -# define zstrerror() "stdio error (consult errno)" -# endif -#endif - -/* provide prototypes for these when building zlib without LFS */ -#if !defined(_LARGEFILE64_SOURCE) || _LFS64_LARGEFILE-0 == 0 - ZEXTERN gzFile ZEXPORT gzopen64 OF((const char *, const char *)); - ZEXTERN z_off64_t ZEXPORT gzseek64 OF((gzFile, z_off64_t, int)); - ZEXTERN z_off64_t ZEXPORT gztell64 OF((gzFile)); - ZEXTERN z_off64_t ZEXPORT gzoffset64 OF((gzFile)); -#endif - -/* default memLevel */ -#if MAX_MEM_LEVEL >= 8 -# define DEF_MEM_LEVEL 8 -#else -# define DEF_MEM_LEVEL MAX_MEM_LEVEL -#endif - -/* default i/o buffer size -- double this for output when reading (this and - twice this must be able to fit in an unsigned type) */ -#define GZBUFSIZE 8192 - -/* gzip modes, also provide a little integrity check on the passed structure */ -#define GZ_NONE 0 -#define GZ_READ 7247 -#define GZ_WRITE 31153 -#define GZ_APPEND 1 /* mode set to GZ_WRITE after the file is opened */ - -/* values for gz_state how */ -#define LOOK 0 /* look for a gzip header */ -#define COPY 1 /* copy input directly */ -#define GZIP 2 /* decompress a gzip stream */ - -/* internal gzip file state data structure */ -typedef struct { - /* exposed contents for gzgetc() macro */ - struct gzFile_s x; /* "x" for exposed */ - /* x.have: number of bytes available at x.next */ - /* x.next: next output data to deliver or write */ - /* x.pos: current position in uncompressed data */ - /* used for both reading and writing */ - int mode; /* see gzip modes above */ - int fd; /* file descriptor */ - char *path; /* path or fd for error messages */ - unsigned size; /* buffer size, zero if not allocated yet */ - unsigned want; /* requested buffer size, default is GZBUFSIZE */ - unsigned char *in; /* input buffer (double-sized when writing) */ - unsigned char *out; /* output buffer (double-sized when reading) */ - int direct; /* 0 if processing gzip, 1 if transparent */ - /* just for reading */ - int how; /* 0: get header, 1: copy, 2: decompress */ - z_off64_t start; /* where the gzip data started, for rewinding */ - int eof; /* true if end of input file reached */ - int past; /* true if read requested past end */ - /* just for writing */ - int level; /* compression level */ - int strategy; /* compression strategy */ - /* seek request */ - z_off64_t skip; /* amount to skip (already rewound if backwards) */ - int seek; /* true if seek request pending */ - /* error information */ - int err; /* error code */ - char *msg; /* error message */ - /* zlib inflate or deflate stream */ - z_stream strm; /* stream structure in-place (not a pointer) */ -} gz_state; -typedef gz_state FAR *gz_statep; - -/* shared functions */ -void ZLIB_INTERNAL gz_error OF((gz_statep, int, const char *)); -#if defined UNDER_CE -char ZLIB_INTERNAL *gz_strwinerror OF((DWORD error)); -#endif - -/* GT_OFF(x), where x is an unsigned value, is true if x > maximum z_off64_t - value -- needed when comparing unsigned to z_off64_t, which is signed - (possible z_off64_t types off_t, off64_t, and long are all signed) */ -#ifdef INT_MAX -# define GT_OFF(x) (sizeof(int) == sizeof(z_off64_t) && (x) > INT_MAX) -#else -unsigned ZLIB_INTERNAL gz_intmax OF((void)); -# define GT_OFF(x) (sizeof(int) == sizeof(z_off64_t) && (x) > gz_intmax()) -#endif diff --git a/deps/zlib/infback.c b/deps/zlib/infback.c deleted file mode 100644 index 59679ec..0000000 --- a/deps/zlib/infback.c +++ /dev/null @@ -1,640 +0,0 @@ -/* infback.c -- inflate using a call-back interface - * Copyright (C) 1995-2016 Mark Adler - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -/* - This code is largely copied from inflate.c. Normally either infback.o or - inflate.o would be linked into an application--not both. The interface - with inffast.c is retained so that optimized assembler-coded versions of - inflate_fast() can be used with either inflate.c or infback.c. - */ - -#include "zutil.h" -#include "inftrees.h" -#include "inflate.h" -#include "inffast.h" - -/* function prototypes */ -local void fixedtables OF((struct inflate_state FAR *state)); - -/* - strm provides memory allocation functions in zalloc and zfree, or - Z_NULL to use the library memory allocation functions. - - windowBits is in the range 8..15, and window is a user-supplied - window and output buffer that is 2**windowBits bytes. - */ -int ZEXPORT inflateBackInit_(strm, windowBits, window, version, stream_size) -z_streamp strm; -int windowBits; -unsigned char FAR *window; -const char *version; -int stream_size; -{ - struct inflate_state FAR *state; - - if (version == Z_NULL || version[0] != ZLIB_VERSION[0] || - stream_size != (int)(sizeof(z_stream))) - return Z_VERSION_ERROR; - if (strm == Z_NULL || window == Z_NULL || - windowBits < 8 || windowBits > 15) - return Z_STREAM_ERROR; - strm->msg = Z_NULL; /* in case we return an error */ - if (strm->zalloc == (alloc_func)0) { -#ifdef Z_SOLO - return Z_STREAM_ERROR; -#else - strm->zalloc = zcalloc; - strm->opaque = (voidpf)0; -#endif - } - if (strm->zfree == (free_func)0) -#ifdef Z_SOLO - return Z_STREAM_ERROR; -#else - strm->zfree = zcfree; -#endif - state = (struct inflate_state FAR *)ZALLOC(strm, 1, - sizeof(struct inflate_state)); - if (state == Z_NULL) return Z_MEM_ERROR; - Tracev((stderr, "inflate: allocated\n")); - strm->state = (struct internal_state FAR *)state; - state->dmax = 32768U; - state->wbits = (uInt)windowBits; - state->wsize = 1U << windowBits; - state->window = window; - state->wnext = 0; - state->whave = 0; - return Z_OK; -} - -/* - Return state with length and distance decoding tables and index sizes set to - fixed code decoding. Normally this returns fixed tables from inffixed.h. - If BUILDFIXED is defined, then instead this routine builds the tables the - first time it's called, and returns those tables the first time and - thereafter. This reduces the size of the code by about 2K bytes, in - exchange for a little execution time. However, BUILDFIXED should not be - used for threaded applications, since the rewriting of the tables and virgin - may not be thread-safe. - */ -local void fixedtables(state) -struct inflate_state FAR *state; -{ -#ifdef BUILDFIXED - static int virgin = 1; - static code *lenfix, *distfix; - static code fixed[544]; - - /* build fixed huffman tables if first call (may not be thread safe) */ - if (virgin) { - unsigned sym, bits; - static code *next; - - /* literal/length table */ - sym = 0; - while (sym < 144) state->lens[sym++] = 8; - while (sym < 256) state->lens[sym++] = 9; - while (sym < 280) state->lens[sym++] = 7; - while (sym < 288) state->lens[sym++] = 8; - next = fixed; - lenfix = next; - bits = 9; - inflate_table(LENS, state->lens, 288, &(next), &(bits), state->work); - - /* distance table */ - sym = 0; - while (sym < 32) state->lens[sym++] = 5; - distfix = next; - bits = 5; - inflate_table(DISTS, state->lens, 32, &(next), &(bits), state->work); - - /* do this just once */ - virgin = 0; - } -#else /* !BUILDFIXED */ -# include "inffixed.h" -#endif /* BUILDFIXED */ - state->lencode = lenfix; - state->lenbits = 9; - state->distcode = distfix; - state->distbits = 5; -} - -/* Macros for inflateBack(): */ - -/* Load returned state from inflate_fast() */ -#define LOAD() \ - do { \ - put = strm->next_out; \ - left = strm->avail_out; \ - next = strm->next_in; \ - have = strm->avail_in; \ - hold = state->hold; \ - bits = state->bits; \ - } while (0) - -/* Set state from registers for inflate_fast() */ -#define RESTORE() \ - do { \ - strm->next_out = put; \ - strm->avail_out = left; \ - strm->next_in = next; \ - strm->avail_in = have; \ - state->hold = hold; \ - state->bits = bits; \ - } while (0) - -/* Clear the input bit accumulator */ -#define INITBITS() \ - do { \ - hold = 0; \ - bits = 0; \ - } while (0) - -/* Assure that some input is available. If input is requested, but denied, - then return a Z_BUF_ERROR from inflateBack(). */ -#define PULL() \ - do { \ - if (have == 0) { \ - have = in(in_desc, &next); \ - if (have == 0) { \ - next = Z_NULL; \ - ret = Z_BUF_ERROR; \ - goto inf_leave; \ - } \ - } \ - } while (0) - -/* Get a byte of input into the bit accumulator, or return from inflateBack() - with an error if there is no input available. */ -#define PULLBYTE() \ - do { \ - PULL(); \ - have--; \ - hold += (unsigned long)(*next++) << bits; \ - bits += 8; \ - } while (0) - -/* Assure that there are at least n bits in the bit accumulator. If there is - not enough available input to do that, then return from inflateBack() with - an error. */ -#define NEEDBITS(n) \ - do { \ - while (bits < (unsigned)(n)) \ - PULLBYTE(); \ - } while (0) - -/* Return the low n bits of the bit accumulator (n < 16) */ -#define BITS(n) \ - ((unsigned)hold & ((1U << (n)) - 1)) - -/* Remove n bits from the bit accumulator */ -#define DROPBITS(n) \ - do { \ - hold >>= (n); \ - bits -= (unsigned)(n); \ - } while (0) - -/* Remove zero to seven bits as needed to go to a byte boundary */ -#define BYTEBITS() \ - do { \ - hold >>= bits & 7; \ - bits -= bits & 7; \ - } while (0) - -/* Assure that some output space is available, by writing out the window - if it's full. If the write fails, return from inflateBack() with a - Z_BUF_ERROR. */ -#define ROOM() \ - do { \ - if (left == 0) { \ - put = state->window; \ - left = state->wsize; \ - state->whave = left; \ - if (out(out_desc, put, left)) { \ - ret = Z_BUF_ERROR; \ - goto inf_leave; \ - } \ - } \ - } while (0) - -/* - strm provides the memory allocation functions and window buffer on input, - and provides information on the unused input on return. For Z_DATA_ERROR - returns, strm will also provide an error message. - - in() and out() are the call-back input and output functions. When - inflateBack() needs more input, it calls in(). When inflateBack() has - filled the window with output, or when it completes with data in the - window, it calls out() to write out the data. The application must not - change the provided input until in() is called again or inflateBack() - returns. The application must not change the window/output buffer until - inflateBack() returns. - - in() and out() are called with a descriptor parameter provided in the - inflateBack() call. This parameter can be a structure that provides the - information required to do the read or write, as well as accumulated - information on the input and output such as totals and check values. - - in() should return zero on failure. out() should return non-zero on - failure. If either in() or out() fails, than inflateBack() returns a - Z_BUF_ERROR. strm->next_in can be checked for Z_NULL to see whether it - was in() or out() that caused in the error. Otherwise, inflateBack() - returns Z_STREAM_END on success, Z_DATA_ERROR for an deflate format - error, or Z_MEM_ERROR if it could not allocate memory for the state. - inflateBack() can also return Z_STREAM_ERROR if the input parameters - are not correct, i.e. strm is Z_NULL or the state was not initialized. - */ -int ZEXPORT inflateBack(strm, in, in_desc, out, out_desc) -z_streamp strm; -in_func in; -void FAR *in_desc; -out_func out; -void FAR *out_desc; -{ - struct inflate_state FAR *state; - z_const unsigned char FAR *next; /* next input */ - unsigned char FAR *put; /* next output */ - unsigned have, left; /* available input and output */ - unsigned long hold; /* bit buffer */ - unsigned bits; /* bits in bit buffer */ - unsigned copy; /* number of stored or match bytes to copy */ - unsigned char FAR *from; /* where to copy match bytes from */ - code here; /* current decoding table entry */ - code last; /* parent table entry */ - unsigned len; /* length to copy for repeats, bits to drop */ - int ret; /* return code */ - static const unsigned short order[19] = /* permutation of code lengths */ - {16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15}; - - /* Check that the strm exists and that the state was initialized */ - if (strm == Z_NULL || strm->state == Z_NULL) - return Z_STREAM_ERROR; - state = (struct inflate_state FAR *)strm->state; - - /* Reset the state */ - strm->msg = Z_NULL; - state->mode = TYPE; - state->last = 0; - state->whave = 0; - next = strm->next_in; - have = next != Z_NULL ? strm->avail_in : 0; - hold = 0; - bits = 0; - put = state->window; - left = state->wsize; - - /* Inflate until end of block marked as last */ - for (;;) - switch (state->mode) { - case TYPE: - /* determine and dispatch block type */ - if (state->last) { - BYTEBITS(); - state->mode = DONE; - break; - } - NEEDBITS(3); - state->last = BITS(1); - DROPBITS(1); - switch (BITS(2)) { - case 0: /* stored block */ - Tracev((stderr, "inflate: stored block%s\n", - state->last ? " (last)" : "")); - state->mode = STORED; - break; - case 1: /* fixed block */ - fixedtables(state); - Tracev((stderr, "inflate: fixed codes block%s\n", - state->last ? " (last)" : "")); - state->mode = LEN; /* decode codes */ - break; - case 2: /* dynamic block */ - Tracev((stderr, "inflate: dynamic codes block%s\n", - state->last ? " (last)" : "")); - state->mode = TABLE; - break; - case 3: - strm->msg = (char *)"invalid block type"; - state->mode = BAD; - } - DROPBITS(2); - break; - - case STORED: - /* get and verify stored block length */ - BYTEBITS(); /* go to byte boundary */ - NEEDBITS(32); - if ((hold & 0xffff) != ((hold >> 16) ^ 0xffff)) { - strm->msg = (char *)"invalid stored block lengths"; - state->mode = BAD; - break; - } - state->length = (unsigned)hold & 0xffff; - Tracev((stderr, "inflate: stored length %u\n", - state->length)); - INITBITS(); - - /* copy stored block from input to output */ - while (state->length != 0) { - copy = state->length; - PULL(); - ROOM(); - if (copy > have) copy = have; - if (copy > left) copy = left; - zmemcpy(put, next, copy); - have -= copy; - next += copy; - left -= copy; - put += copy; - state->length -= copy; - } - Tracev((stderr, "inflate: stored end\n")); - state->mode = TYPE; - break; - - case TABLE: - /* get dynamic table entries descriptor */ - NEEDBITS(14); - state->nlen = BITS(5) + 257; - DROPBITS(5); - state->ndist = BITS(5) + 1; - DROPBITS(5); - state->ncode = BITS(4) + 4; - DROPBITS(4); -#ifndef PKZIP_BUG_WORKAROUND - if (state->nlen > 286 || state->ndist > 30) { - strm->msg = (char *)"too many length or distance symbols"; - state->mode = BAD; - break; - } -#endif - Tracev((stderr, "inflate: table sizes ok\n")); - - /* get code length code lengths (not a typo) */ - state->have = 0; - while (state->have < state->ncode) { - NEEDBITS(3); - state->lens[order[state->have++]] = (unsigned short)BITS(3); - DROPBITS(3); - } - while (state->have < 19) - state->lens[order[state->have++]] = 0; - state->next = state->codes; - state->lencode = (code const FAR *)(state->next); - state->lenbits = 7; - ret = inflate_table(CODES, state->lens, 19, &(state->next), - &(state->lenbits), state->work); - if (ret) { - strm->msg = (char *)"invalid code lengths set"; - state->mode = BAD; - break; - } - Tracev((stderr, "inflate: code lengths ok\n")); - - /* get length and distance code code lengths */ - state->have = 0; - while (state->have < state->nlen + state->ndist) { - for (;;) { - here = state->lencode[BITS(state->lenbits)]; - if ((unsigned)(here.bits) <= bits) break; - PULLBYTE(); - } - if (here.val < 16) { - DROPBITS(here.bits); - state->lens[state->have++] = here.val; - } - else { - if (here.val == 16) { - NEEDBITS(here.bits + 2); - DROPBITS(here.bits); - if (state->have == 0) { - strm->msg = (char *)"invalid bit length repeat"; - state->mode = BAD; - break; - } - len = (unsigned)(state->lens[state->have - 1]); - copy = 3 + BITS(2); - DROPBITS(2); - } - else if (here.val == 17) { - NEEDBITS(here.bits + 3); - DROPBITS(here.bits); - len = 0; - copy = 3 + BITS(3); - DROPBITS(3); - } - else { - NEEDBITS(here.bits + 7); - DROPBITS(here.bits); - len = 0; - copy = 11 + BITS(7); - DROPBITS(7); - } - if (state->have + copy > state->nlen + state->ndist) { - strm->msg = (char *)"invalid bit length repeat"; - state->mode = BAD; - break; - } - while (copy--) - state->lens[state->have++] = (unsigned short)len; - } - } - - /* handle error breaks in while */ - if (state->mode == BAD) break; - - /* check for end-of-block code (better have one) */ - if (state->lens[256] == 0) { - strm->msg = (char *)"invalid code -- missing end-of-block"; - state->mode = BAD; - break; - } - - /* build code tables -- note: do not change the lenbits or distbits - values here (9 and 6) without reading the comments in inftrees.h - concerning the ENOUGH constants, which depend on those values */ - state->next = state->codes; - state->lencode = (code const FAR *)(state->next); - state->lenbits = 9; - ret = inflate_table(LENS, state->lens, state->nlen, &(state->next), - &(state->lenbits), state->work); - if (ret) { - strm->msg = (char *)"invalid literal/lengths set"; - state->mode = BAD; - break; - } - state->distcode = (code const FAR *)(state->next); - state->distbits = 6; - ret = inflate_table(DISTS, state->lens + state->nlen, state->ndist, - &(state->next), &(state->distbits), state->work); - if (ret) { - strm->msg = (char *)"invalid distances set"; - state->mode = BAD; - break; - } - Tracev((stderr, "inflate: codes ok\n")); - state->mode = LEN; - - case LEN: - /* use inflate_fast() if we have enough input and output */ - if (have >= 6 && left >= 258) { - RESTORE(); - if (state->whave < state->wsize) - state->whave = state->wsize - left; - inflate_fast(strm, state->wsize); - LOAD(); - break; - } - - /* get a literal, length, or end-of-block code */ - for (;;) { - here = state->lencode[BITS(state->lenbits)]; - if ((unsigned)(here.bits) <= bits) break; - PULLBYTE(); - } - if (here.op && (here.op & 0xf0) == 0) { - last = here; - for (;;) { - here = state->lencode[last.val + - (BITS(last.bits + last.op) >> last.bits)]; - if ((unsigned)(last.bits + here.bits) <= bits) break; - PULLBYTE(); - } - DROPBITS(last.bits); - } - DROPBITS(here.bits); - state->length = (unsigned)here.val; - - /* process literal */ - if (here.op == 0) { - Tracevv((stderr, here.val >= 0x20 && here.val < 0x7f ? - "inflate: literal '%c'\n" : - "inflate: literal 0x%02x\n", here.val)); - ROOM(); - *put++ = (unsigned char)(state->length); - left--; - state->mode = LEN; - break; - } - - /* process end of block */ - if (here.op & 32) { - Tracevv((stderr, "inflate: end of block\n")); - state->mode = TYPE; - break; - } - - /* invalid code */ - if (here.op & 64) { - strm->msg = (char *)"invalid literal/length code"; - state->mode = BAD; - break; - } - - /* length code -- get extra bits, if any */ - state->extra = (unsigned)(here.op) & 15; - if (state->extra != 0) { - NEEDBITS(state->extra); - state->length += BITS(state->extra); - DROPBITS(state->extra); - } - Tracevv((stderr, "inflate: length %u\n", state->length)); - - /* get distance code */ - for (;;) { - here = state->distcode[BITS(state->distbits)]; - if ((unsigned)(here.bits) <= bits) break; - PULLBYTE(); - } - if ((here.op & 0xf0) == 0) { - last = here; - for (;;) { - here = state->distcode[last.val + - (BITS(last.bits + last.op) >> last.bits)]; - if ((unsigned)(last.bits + here.bits) <= bits) break; - PULLBYTE(); - } - DROPBITS(last.bits); - } - DROPBITS(here.bits); - if (here.op & 64) { - strm->msg = (char *)"invalid distance code"; - state->mode = BAD; - break; - } - state->offset = (unsigned)here.val; - - /* get distance extra bits, if any */ - state->extra = (unsigned)(here.op) & 15; - if (state->extra != 0) { - NEEDBITS(state->extra); - state->offset += BITS(state->extra); - DROPBITS(state->extra); - } - if (state->offset > state->wsize - (state->whave < state->wsize ? - left : 0)) { - strm->msg = (char *)"invalid distance too far back"; - state->mode = BAD; - break; - } - Tracevv((stderr, "inflate: distance %u\n", state->offset)); - - /* copy match from window to output */ - do { - ROOM(); - copy = state->wsize - state->offset; - if (copy < left) { - from = put + copy; - copy = left - copy; - } - else { - from = put - state->offset; - copy = left; - } - if (copy > state->length) copy = state->length; - state->length -= copy; - left -= copy; - do { - *put++ = *from++; - } while (--copy); - } while (state->length != 0); - break; - - case DONE: - /* inflate stream terminated properly -- write leftover output */ - ret = Z_STREAM_END; - if (left < state->wsize) { - if (out(out_desc, state->window, state->wsize - left)) - ret = Z_BUF_ERROR; - } - goto inf_leave; - - case BAD: - ret = Z_DATA_ERROR; - goto inf_leave; - - default: /* can't happen, but makes compilers happy */ - ret = Z_STREAM_ERROR; - goto inf_leave; - } - - /* Return unused input */ - inf_leave: - strm->next_in = next; - strm->avail_in = have; - return ret; -} - -int ZEXPORT inflateBackEnd(strm) -z_streamp strm; -{ - if (strm == Z_NULL || strm->state == Z_NULL || strm->zfree == (free_func)0) - return Z_STREAM_ERROR; - ZFREE(strm, strm->state); - strm->state = Z_NULL; - Tracev((stderr, "inflate: end\n")); - return Z_OK; -} diff --git a/deps/zlib/inffast.c b/deps/zlib/inffast.c deleted file mode 100644 index 0dbd1db..0000000 --- a/deps/zlib/inffast.c +++ /dev/null @@ -1,323 +0,0 @@ -/* inffast.c -- fast decoding - * Copyright (C) 1995-2017 Mark Adler - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -#include "zutil.h" -#include "inftrees.h" -#include "inflate.h" -#include "inffast.h" - -#ifdef ASMINF -# pragma message("Assembler code may have bugs -- use at your own risk") -#else - -/* - Decode literal, length, and distance codes and write out the resulting - literal and match bytes until either not enough input or output is - available, an end-of-block is encountered, or a data error is encountered. - When large enough input and output buffers are supplied to inflate(), for - example, a 16K input buffer and a 64K output buffer, more than 95% of the - inflate execution time is spent in this routine. - - Entry assumptions: - - state->mode == LEN - strm->avail_in >= 6 - strm->avail_out >= 258 - start >= strm->avail_out - state->bits < 8 - - On return, state->mode is one of: - - LEN -- ran out of enough output space or enough available input - TYPE -- reached end of block code, inflate() to interpret next block - BAD -- error in block data - - Notes: - - - The maximum input bits used by a length/distance pair is 15 bits for the - length code, 5 bits for the length extra, 15 bits for the distance code, - and 13 bits for the distance extra. This totals 48 bits, or six bytes. - Therefore if strm->avail_in >= 6, then there is enough input to avoid - checking for available input while decoding. - - - The maximum bytes that a single length/distance pair can output is 258 - bytes, which is the maximum length that can be coded. inflate_fast() - requires strm->avail_out >= 258 for each loop to avoid checking for - output space. - */ -void ZLIB_INTERNAL inflate_fast(strm, start) -z_streamp strm; -unsigned start; /* inflate()'s starting value for strm->avail_out */ -{ - struct inflate_state FAR *state; - z_const unsigned char FAR *in; /* local strm->next_in */ - z_const unsigned char FAR *last; /* have enough input while in < last */ - unsigned char FAR *out; /* local strm->next_out */ - unsigned char FAR *beg; /* inflate()'s initial strm->next_out */ - unsigned char FAR *end; /* while out < end, enough space available */ -#ifdef INFLATE_STRICT - unsigned dmax; /* maximum distance from zlib header */ -#endif - unsigned wsize; /* window size or zero if not using window */ - unsigned whave; /* valid bytes in the window */ - unsigned wnext; /* window write index */ - unsigned char FAR *window; /* allocated sliding window, if wsize != 0 */ - unsigned long hold; /* local strm->hold */ - unsigned bits; /* local strm->bits */ - code const FAR *lcode; /* local strm->lencode */ - code const FAR *dcode; /* local strm->distcode */ - unsigned lmask; /* mask for first level of length codes */ - unsigned dmask; /* mask for first level of distance codes */ - code here; /* retrieved table entry */ - unsigned op; /* code bits, operation, extra bits, or */ - /* window position, window bytes to copy */ - unsigned len; /* match length, unused bytes */ - unsigned dist; /* match distance */ - unsigned char FAR *from; /* where to copy match from */ - - /* copy state to local variables */ - state = (struct inflate_state FAR *)strm->state; - in = strm->next_in; - last = in + (strm->avail_in - 5); - out = strm->next_out; - beg = out - (start - strm->avail_out); - end = out + (strm->avail_out - 257); -#ifdef INFLATE_STRICT - dmax = state->dmax; -#endif - wsize = state->wsize; - whave = state->whave; - wnext = state->wnext; - window = state->window; - hold = state->hold; - bits = state->bits; - lcode = state->lencode; - dcode = state->distcode; - lmask = (1U << state->lenbits) - 1; - dmask = (1U << state->distbits) - 1; - - /* decode literals and length/distances until end-of-block or not enough - input data or output space */ - do { - if (bits < 15) { - hold += (unsigned long)(*in++) << bits; - bits += 8; - hold += (unsigned long)(*in++) << bits; - bits += 8; - } - here = lcode[hold & lmask]; - dolen: - op = (unsigned)(here.bits); - hold >>= op; - bits -= op; - op = (unsigned)(here.op); - if (op == 0) { /* literal */ - Tracevv((stderr, here.val >= 0x20 && here.val < 0x7f ? - "inflate: literal '%c'\n" : - "inflate: literal 0x%02x\n", here.val)); - *out++ = (unsigned char)(here.val); - } - else if (op & 16) { /* length base */ - len = (unsigned)(here.val); - op &= 15; /* number of extra bits */ - if (op) { - if (bits < op) { - hold += (unsigned long)(*in++) << bits; - bits += 8; - } - len += (unsigned)hold & ((1U << op) - 1); - hold >>= op; - bits -= op; - } - Tracevv((stderr, "inflate: length %u\n", len)); - if (bits < 15) { - hold += (unsigned long)(*in++) << bits; - bits += 8; - hold += (unsigned long)(*in++) << bits; - bits += 8; - } - here = dcode[hold & dmask]; - dodist: - op = (unsigned)(here.bits); - hold >>= op; - bits -= op; - op = (unsigned)(here.op); - if (op & 16) { /* distance base */ - dist = (unsigned)(here.val); - op &= 15; /* number of extra bits */ - if (bits < op) { - hold += (unsigned long)(*in++) << bits; - bits += 8; - if (bits < op) { - hold += (unsigned long)(*in++) << bits; - bits += 8; - } - } - dist += (unsigned)hold & ((1U << op) - 1); -#ifdef INFLATE_STRICT - if (dist > dmax) { - strm->msg = (char *)"invalid distance too far back"; - state->mode = BAD; - break; - } -#endif - hold >>= op; - bits -= op; - Tracevv((stderr, "inflate: distance %u\n", dist)); - op = (unsigned)(out - beg); /* max distance in output */ - if (dist > op) { /* see if copy from window */ - op = dist - op; /* distance back in window */ - if (op > whave) { - if (state->sane) { - strm->msg = - (char *)"invalid distance too far back"; - state->mode = BAD; - break; - } -#ifdef INFLATE_ALLOW_INVALID_DISTANCE_TOOFAR_ARRR - if (len <= op - whave) { - do { - *out++ = 0; - } while (--len); - continue; - } - len -= op - whave; - do { - *out++ = 0; - } while (--op > whave); - if (op == 0) { - from = out - dist; - do { - *out++ = *from++; - } while (--len); - continue; - } -#endif - } - from = window; - if (wnext == 0) { /* very common case */ - from += wsize - op; - if (op < len) { /* some from window */ - len -= op; - do { - *out++ = *from++; - } while (--op); - from = out - dist; /* rest from output */ - } - } - else if (wnext < op) { /* wrap around window */ - from += wsize + wnext - op; - op -= wnext; - if (op < len) { /* some from end of window */ - len -= op; - do { - *out++ = *from++; - } while (--op); - from = window; - if (wnext < len) { /* some from start of window */ - op = wnext; - len -= op; - do { - *out++ = *from++; - } while (--op); - from = out - dist; /* rest from output */ - } - } - } - else { /* contiguous in window */ - from += wnext - op; - if (op < len) { /* some from window */ - len -= op; - do { - *out++ = *from++; - } while (--op); - from = out - dist; /* rest from output */ - } - } - while (len > 2) { - *out++ = *from++; - *out++ = *from++; - *out++ = *from++; - len -= 3; - } - if (len) { - *out++ = *from++; - if (len > 1) - *out++ = *from++; - } - } - else { - from = out - dist; /* copy direct from output */ - do { /* minimum length is three */ - *out++ = *from++; - *out++ = *from++; - *out++ = *from++; - len -= 3; - } while (len > 2); - if (len) { - *out++ = *from++; - if (len > 1) - *out++ = *from++; - } - } - } - else if ((op & 64) == 0) { /* 2nd level distance code */ - here = dcode[here.val + (hold & ((1U << op) - 1))]; - goto dodist; - } - else { - strm->msg = (char *)"invalid distance code"; - state->mode = BAD; - break; - } - } - else if ((op & 64) == 0) { /* 2nd level length code */ - here = lcode[here.val + (hold & ((1U << op) - 1))]; - goto dolen; - } - else if (op & 32) { /* end-of-block */ - Tracevv((stderr, "inflate: end of block\n")); - state->mode = TYPE; - break; - } - else { - strm->msg = (char *)"invalid literal/length code"; - state->mode = BAD; - break; - } - } while (in < last && out < end); - - /* return unused bytes (on entry, bits < 8, so in won't go too far back) */ - len = bits >> 3; - in -= len; - bits -= len << 3; - hold &= (1U << bits) - 1; - - /* update state and return */ - strm->next_in = in; - strm->next_out = out; - strm->avail_in = (unsigned)(in < last ? 5 + (last - in) : 5 - (in - last)); - strm->avail_out = (unsigned)(out < end ? - 257 + (end - out) : 257 - (out - end)); - state->hold = hold; - state->bits = bits; - return; -} - -/* - inflate_fast() speedups that turned out slower (on a PowerPC G3 750CXe): - - Using bit fields for code structure - - Different op definition to avoid & for extra bits (do & for table bits) - - Three separate decoding do-loops for direct, window, and wnext == 0 - - Special case for distance > 1 copies to do overlapped load and store copy - - Explicit branch predictions (based on measured branch probabilities) - - Deferring match copy and interspersed it with decoding subsequent codes - - Swapping literal/length else - - Swapping window/direct else - - Larger unrolled copy loops (three is about right) - - Moving len -= 3 statement into middle of loop - */ - -#endif /* !ASMINF */ diff --git a/deps/zlib/inffast.h b/deps/zlib/inffast.h deleted file mode 100644 index e5c1aa4..0000000 --- a/deps/zlib/inffast.h +++ /dev/null @@ -1,11 +0,0 @@ -/* inffast.h -- header to use inffast.c - * Copyright (C) 1995-2003, 2010 Mark Adler - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -/* WARNING: this file should *not* be used by applications. It is - part of the implementation of the compression library and is - subject to change. Applications should only use zlib.h. - */ - -void ZLIB_INTERNAL inflate_fast OF((z_streamp strm, unsigned start)); diff --git a/deps/zlib/inffixed.h b/deps/zlib/inffixed.h deleted file mode 100644 index d628327..0000000 --- a/deps/zlib/inffixed.h +++ /dev/null @@ -1,94 +0,0 @@ - /* inffixed.h -- table for decoding fixed codes - * Generated automatically by makefixed(). - */ - - /* WARNING: this file should *not* be used by applications. - It is part of the implementation of this library and is - subject to change. Applications should only use zlib.h. - */ - - static const code lenfix[512] = { - {96,7,0},{0,8,80},{0,8,16},{20,8,115},{18,7,31},{0,8,112},{0,8,48}, - {0,9,192},{16,7,10},{0,8,96},{0,8,32},{0,9,160},{0,8,0},{0,8,128}, - {0,8,64},{0,9,224},{16,7,6},{0,8,88},{0,8,24},{0,9,144},{19,7,59}, - {0,8,120},{0,8,56},{0,9,208},{17,7,17},{0,8,104},{0,8,40},{0,9,176}, - {0,8,8},{0,8,136},{0,8,72},{0,9,240},{16,7,4},{0,8,84},{0,8,20}, - {21,8,227},{19,7,43},{0,8,116},{0,8,52},{0,9,200},{17,7,13},{0,8,100}, - {0,8,36},{0,9,168},{0,8,4},{0,8,132},{0,8,68},{0,9,232},{16,7,8}, - {0,8,92},{0,8,28},{0,9,152},{20,7,83},{0,8,124},{0,8,60},{0,9,216}, - {18,7,23},{0,8,108},{0,8,44},{0,9,184},{0,8,12},{0,8,140},{0,8,76}, - {0,9,248},{16,7,3},{0,8,82},{0,8,18},{21,8,163},{19,7,35},{0,8,114}, - {0,8,50},{0,9,196},{17,7,11},{0,8,98},{0,8,34},{0,9,164},{0,8,2}, - {0,8,130},{0,8,66},{0,9,228},{16,7,7},{0,8,90},{0,8,26},{0,9,148}, - {20,7,67},{0,8,122},{0,8,58},{0,9,212},{18,7,19},{0,8,106},{0,8,42}, - {0,9,180},{0,8,10},{0,8,138},{0,8,74},{0,9,244},{16,7,5},{0,8,86}, - {0,8,22},{64,8,0},{19,7,51},{0,8,118},{0,8,54},{0,9,204},{17,7,15}, - {0,8,102},{0,8,38},{0,9,172},{0,8,6},{0,8,134},{0,8,70},{0,9,236}, - {16,7,9},{0,8,94},{0,8,30},{0,9,156},{20,7,99},{0,8,126},{0,8,62}, - {0,9,220},{18,7,27},{0,8,110},{0,8,46},{0,9,188},{0,8,14},{0,8,142}, - {0,8,78},{0,9,252},{96,7,0},{0,8,81},{0,8,17},{21,8,131},{18,7,31}, - {0,8,113},{0,8,49},{0,9,194},{16,7,10},{0,8,97},{0,8,33},{0,9,162}, - {0,8,1},{0,8,129},{0,8,65},{0,9,226},{16,7,6},{0,8,89},{0,8,25}, - {0,9,146},{19,7,59},{0,8,121},{0,8,57},{0,9,210},{17,7,17},{0,8,105}, - {0,8,41},{0,9,178},{0,8,9},{0,8,137},{0,8,73},{0,9,242},{16,7,4}, - {0,8,85},{0,8,21},{16,8,258},{19,7,43},{0,8,117},{0,8,53},{0,9,202}, - {17,7,13},{0,8,101},{0,8,37},{0,9,170},{0,8,5},{0,8,133},{0,8,69}, - {0,9,234},{16,7,8},{0,8,93},{0,8,29},{0,9,154},{20,7,83},{0,8,125}, - {0,8,61},{0,9,218},{18,7,23},{0,8,109},{0,8,45},{0,9,186},{0,8,13}, - {0,8,141},{0,8,77},{0,9,250},{16,7,3},{0,8,83},{0,8,19},{21,8,195}, - {19,7,35},{0,8,115},{0,8,51},{0,9,198},{17,7,11},{0,8,99},{0,8,35}, - {0,9,166},{0,8,3},{0,8,131},{0,8,67},{0,9,230},{16,7,7},{0,8,91}, - {0,8,27},{0,9,150},{20,7,67},{0,8,123},{0,8,59},{0,9,214},{18,7,19}, - {0,8,107},{0,8,43},{0,9,182},{0,8,11},{0,8,139},{0,8,75},{0,9,246}, - {16,7,5},{0,8,87},{0,8,23},{64,8,0},{19,7,51},{0,8,119},{0,8,55}, - {0,9,206},{17,7,15},{0,8,103},{0,8,39},{0,9,174},{0,8,7},{0,8,135}, - {0,8,71},{0,9,238},{16,7,9},{0,8,95},{0,8,31},{0,9,158},{20,7,99}, - {0,8,127},{0,8,63},{0,9,222},{18,7,27},{0,8,111},{0,8,47},{0,9,190}, - {0,8,15},{0,8,143},{0,8,79},{0,9,254},{96,7,0},{0,8,80},{0,8,16}, - {20,8,115},{18,7,31},{0,8,112},{0,8,48},{0,9,193},{16,7,10},{0,8,96}, - {0,8,32},{0,9,161},{0,8,0},{0,8,128},{0,8,64},{0,9,225},{16,7,6}, - {0,8,88},{0,8,24},{0,9,145},{19,7,59},{0,8,120},{0,8,56},{0,9,209}, - {17,7,17},{0,8,104},{0,8,40},{0,9,177},{0,8,8},{0,8,136},{0,8,72}, - {0,9,241},{16,7,4},{0,8,84},{0,8,20},{21,8,227},{19,7,43},{0,8,116}, - {0,8,52},{0,9,201},{17,7,13},{0,8,100},{0,8,36},{0,9,169},{0,8,4}, - {0,8,132},{0,8,68},{0,9,233},{16,7,8},{0,8,92},{0,8,28},{0,9,153}, - {20,7,83},{0,8,124},{0,8,60},{0,9,217},{18,7,23},{0,8,108},{0,8,44}, - {0,9,185},{0,8,12},{0,8,140},{0,8,76},{0,9,249},{16,7,3},{0,8,82}, - {0,8,18},{21,8,163},{19,7,35},{0,8,114},{0,8,50},{0,9,197},{17,7,11}, - {0,8,98},{0,8,34},{0,9,165},{0,8,2},{0,8,130},{0,8,66},{0,9,229}, - {16,7,7},{0,8,90},{0,8,26},{0,9,149},{20,7,67},{0,8,122},{0,8,58}, - {0,9,213},{18,7,19},{0,8,106},{0,8,42},{0,9,181},{0,8,10},{0,8,138}, - {0,8,74},{0,9,245},{16,7,5},{0,8,86},{0,8,22},{64,8,0},{19,7,51}, - {0,8,118},{0,8,54},{0,9,205},{17,7,15},{0,8,102},{0,8,38},{0,9,173}, - {0,8,6},{0,8,134},{0,8,70},{0,9,237},{16,7,9},{0,8,94},{0,8,30}, - {0,9,157},{20,7,99},{0,8,126},{0,8,62},{0,9,221},{18,7,27},{0,8,110}, - {0,8,46},{0,9,189},{0,8,14},{0,8,142},{0,8,78},{0,9,253},{96,7,0}, - {0,8,81},{0,8,17},{21,8,131},{18,7,31},{0,8,113},{0,8,49},{0,9,195}, - {16,7,10},{0,8,97},{0,8,33},{0,9,163},{0,8,1},{0,8,129},{0,8,65}, - {0,9,227},{16,7,6},{0,8,89},{0,8,25},{0,9,147},{19,7,59},{0,8,121}, - {0,8,57},{0,9,211},{17,7,17},{0,8,105},{0,8,41},{0,9,179},{0,8,9}, - {0,8,137},{0,8,73},{0,9,243},{16,7,4},{0,8,85},{0,8,21},{16,8,258}, - {19,7,43},{0,8,117},{0,8,53},{0,9,203},{17,7,13},{0,8,101},{0,8,37}, - {0,9,171},{0,8,5},{0,8,133},{0,8,69},{0,9,235},{16,7,8},{0,8,93}, - {0,8,29},{0,9,155},{20,7,83},{0,8,125},{0,8,61},{0,9,219},{18,7,23}, - {0,8,109},{0,8,45},{0,9,187},{0,8,13},{0,8,141},{0,8,77},{0,9,251}, - {16,7,3},{0,8,83},{0,8,19},{21,8,195},{19,7,35},{0,8,115},{0,8,51}, - {0,9,199},{17,7,11},{0,8,99},{0,8,35},{0,9,167},{0,8,3},{0,8,131}, - {0,8,67},{0,9,231},{16,7,7},{0,8,91},{0,8,27},{0,9,151},{20,7,67}, - {0,8,123},{0,8,59},{0,9,215},{18,7,19},{0,8,107},{0,8,43},{0,9,183}, - {0,8,11},{0,8,139},{0,8,75},{0,9,247},{16,7,5},{0,8,87},{0,8,23}, - {64,8,0},{19,7,51},{0,8,119},{0,8,55},{0,9,207},{17,7,15},{0,8,103}, - {0,8,39},{0,9,175},{0,8,7},{0,8,135},{0,8,71},{0,9,239},{16,7,9}, - {0,8,95},{0,8,31},{0,9,159},{20,7,99},{0,8,127},{0,8,63},{0,9,223}, - {18,7,27},{0,8,111},{0,8,47},{0,9,191},{0,8,15},{0,8,143},{0,8,79}, - {0,9,255} - }; - - static const code distfix[32] = { - {16,5,1},{23,5,257},{19,5,17},{27,5,4097},{17,5,5},{25,5,1025}, - {21,5,65},{29,5,16385},{16,5,3},{24,5,513},{20,5,33},{28,5,8193}, - {18,5,9},{26,5,2049},{22,5,129},{64,5,0},{16,5,2},{23,5,385}, - {19,5,25},{27,5,6145},{17,5,7},{25,5,1537},{21,5,97},{29,5,24577}, - {16,5,4},{24,5,769},{20,5,49},{28,5,12289},{18,5,13},{26,5,3073}, - {22,5,193},{64,5,0} - }; diff --git a/deps/zlib/inflate.c b/deps/zlib/inflate.c deleted file mode 100644 index ac333e8..0000000 --- a/deps/zlib/inflate.c +++ /dev/null @@ -1,1561 +0,0 @@ -/* inflate.c -- zlib decompression - * Copyright (C) 1995-2016 Mark Adler - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -/* - * Change history: - * - * 1.2.beta0 24 Nov 2002 - * - First version -- complete rewrite of inflate to simplify code, avoid - * creation of window when not needed, minimize use of window when it is - * needed, make inffast.c even faster, implement gzip decoding, and to - * improve code readability and style over the previous zlib inflate code - * - * 1.2.beta1 25 Nov 2002 - * - Use pointers for available input and output checking in inffast.c - * - Remove input and output counters in inffast.c - * - Change inffast.c entry and loop from avail_in >= 7 to >= 6 - * - Remove unnecessary second byte pull from length extra in inffast.c - * - Unroll direct copy to three copies per loop in inffast.c - * - * 1.2.beta2 4 Dec 2002 - * - Change external routine names to reduce potential conflicts - * - Correct filename to inffixed.h for fixed tables in inflate.c - * - Make hbuf[] unsigned char to match parameter type in inflate.c - * - Change strm->next_out[-state->offset] to *(strm->next_out - state->offset) - * to avoid negation problem on Alphas (64 bit) in inflate.c - * - * 1.2.beta3 22 Dec 2002 - * - Add comments on state->bits assertion in inffast.c - * - Add comments on op field in inftrees.h - * - Fix bug in reuse of allocated window after inflateReset() - * - Remove bit fields--back to byte structure for speed - * - Remove distance extra == 0 check in inflate_fast()--only helps for lengths - * - Change post-increments to pre-increments in inflate_fast(), PPC biased? - * - Add compile time option, POSTINC, to use post-increments instead (Intel?) - * - Make MATCH copy in inflate() much faster for when inflate_fast() not used - * - Use local copies of stream next and avail values, as well as local bit - * buffer and bit count in inflate()--for speed when inflate_fast() not used - * - * 1.2.beta4 1 Jan 2003 - * - Split ptr - 257 statements in inflate_table() to avoid compiler warnings - * - Move a comment on output buffer sizes from inffast.c to inflate.c - * - Add comments in inffast.c to introduce the inflate_fast() routine - * - Rearrange window copies in inflate_fast() for speed and simplification - * - Unroll last copy for window match in inflate_fast() - * - Use local copies of window variables in inflate_fast() for speed - * - Pull out common wnext == 0 case for speed in inflate_fast() - * - Make op and len in inflate_fast() unsigned for consistency - * - Add FAR to lcode and dcode declarations in inflate_fast() - * - Simplified bad distance check in inflate_fast() - * - Added inflateBackInit(), inflateBack(), and inflateBackEnd() in new - * source file infback.c to provide a call-back interface to inflate for - * programs like gzip and unzip -- uses window as output buffer to avoid - * window copying - * - * 1.2.beta5 1 Jan 2003 - * - Improved inflateBack() interface to allow the caller to provide initial - * input in strm. - * - Fixed stored blocks bug in inflateBack() - * - * 1.2.beta6 4 Jan 2003 - * - Added comments in inffast.c on effectiveness of POSTINC - * - Typecasting all around to reduce compiler warnings - * - Changed loops from while (1) or do {} while (1) to for (;;), again to - * make compilers happy - * - Changed type of window in inflateBackInit() to unsigned char * - * - * 1.2.beta7 27 Jan 2003 - * - Changed many types to unsigned or unsigned short to avoid warnings - * - Added inflateCopy() function - * - * 1.2.0 9 Mar 2003 - * - Changed inflateBack() interface to provide separate opaque descriptors - * for the in() and out() functions - * - Changed inflateBack() argument and in_func typedef to swap the length - * and buffer address return values for the input function - * - Check next_in and next_out for Z_NULL on entry to inflate() - * - * The history for versions after 1.2.0 are in ChangeLog in zlib distribution. - */ - -#include "zutil.h" -#include "inftrees.h" -#include "inflate.h" -#include "inffast.h" - -#ifdef MAKEFIXED -# ifndef BUILDFIXED -# define BUILDFIXED -# endif -#endif - -/* function prototypes */ -local int inflateStateCheck OF((z_streamp strm)); -local void fixedtables OF((struct inflate_state FAR *state)); -local int updatewindow OF((z_streamp strm, const unsigned char FAR *end, - unsigned copy)); -#ifdef BUILDFIXED - void makefixed OF((void)); -#endif -local unsigned syncsearch OF((unsigned FAR *have, const unsigned char FAR *buf, - unsigned len)); - -local int inflateStateCheck(strm) -z_streamp strm; -{ - struct inflate_state FAR *state; - if (strm == Z_NULL || - strm->zalloc == (alloc_func)0 || strm->zfree == (free_func)0) - return 1; - state = (struct inflate_state FAR *)strm->state; - if (state == Z_NULL || state->strm != strm || - state->mode < HEAD || state->mode > SYNC) - return 1; - return 0; -} - -int ZEXPORT inflateResetKeep(strm) -z_streamp strm; -{ - struct inflate_state FAR *state; - - if (inflateStateCheck(strm)) return Z_STREAM_ERROR; - state = (struct inflate_state FAR *)strm->state; - strm->total_in = strm->total_out = state->total = 0; - strm->msg = Z_NULL; - if (state->wrap) /* to support ill-conceived Java test suite */ - strm->adler = state->wrap & 1; - state->mode = HEAD; - state->last = 0; - state->havedict = 0; - state->dmax = 32768U; - state->head = Z_NULL; - state->hold = 0; - state->bits = 0; - state->lencode = state->distcode = state->next = state->codes; - state->sane = 1; - state->back = -1; - Tracev((stderr, "inflate: reset\n")); - return Z_OK; -} - -int ZEXPORT inflateReset(strm) -z_streamp strm; -{ - struct inflate_state FAR *state; - - if (inflateStateCheck(strm)) return Z_STREAM_ERROR; - state = (struct inflate_state FAR *)strm->state; - state->wsize = 0; - state->whave = 0; - state->wnext = 0; - return inflateResetKeep(strm); -} - -int ZEXPORT inflateReset2(strm, windowBits) -z_streamp strm; -int windowBits; -{ - int wrap; - struct inflate_state FAR *state; - - /* get the state */ - if (inflateStateCheck(strm)) return Z_STREAM_ERROR; - state = (struct inflate_state FAR *)strm->state; - - /* extract wrap request from windowBits parameter */ - if (windowBits < 0) { - wrap = 0; - windowBits = -windowBits; - } - else { - wrap = (windowBits >> 4) + 5; -#ifdef GUNZIP - if (windowBits < 48) - windowBits &= 15; -#endif - } - - /* set number of window bits, free window if different */ - if (windowBits && (windowBits < 8 || windowBits > 15)) - return Z_STREAM_ERROR; - if (state->window != Z_NULL && state->wbits != (unsigned)windowBits) { - ZFREE(strm, state->window); - state->window = Z_NULL; - } - - /* update state and reset the rest of it */ - state->wrap = wrap; - state->wbits = (unsigned)windowBits; - return inflateReset(strm); -} - -int ZEXPORT inflateInit2_(strm, windowBits, version, stream_size) -z_streamp strm; -int windowBits; -const char *version; -int stream_size; -{ - int ret; - struct inflate_state FAR *state; - - if (version == Z_NULL || version[0] != ZLIB_VERSION[0] || - stream_size != (int)(sizeof(z_stream))) - return Z_VERSION_ERROR; - if (strm == Z_NULL) return Z_STREAM_ERROR; - strm->msg = Z_NULL; /* in case we return an error */ - if (strm->zalloc == (alloc_func)0) { -#ifdef Z_SOLO - return Z_STREAM_ERROR; -#else - strm->zalloc = zcalloc; - strm->opaque = (voidpf)0; -#endif - } - if (strm->zfree == (free_func)0) -#ifdef Z_SOLO - return Z_STREAM_ERROR; -#else - strm->zfree = zcfree; -#endif - state = (struct inflate_state FAR *) - ZALLOC(strm, 1, sizeof(struct inflate_state)); - if (state == Z_NULL) return Z_MEM_ERROR; - Tracev((stderr, "inflate: allocated\n")); - strm->state = (struct internal_state FAR *)state; - state->strm = strm; - state->window = Z_NULL; - state->mode = HEAD; /* to pass state test in inflateReset2() */ - ret = inflateReset2(strm, windowBits); - if (ret != Z_OK) { - ZFREE(strm, state); - strm->state = Z_NULL; - } - return ret; -} - -int ZEXPORT inflateInit_(strm, version, stream_size) -z_streamp strm; -const char *version; -int stream_size; -{ - return inflateInit2_(strm, DEF_WBITS, version, stream_size); -} - -int ZEXPORT inflatePrime(strm, bits, value) -z_streamp strm; -int bits; -int value; -{ - struct inflate_state FAR *state; - - if (inflateStateCheck(strm)) return Z_STREAM_ERROR; - state = (struct inflate_state FAR *)strm->state; - if (bits < 0) { - state->hold = 0; - state->bits = 0; - return Z_OK; - } - if (bits > 16 || state->bits + (uInt)bits > 32) return Z_STREAM_ERROR; - value &= (1L << bits) - 1; - state->hold += (unsigned)value << state->bits; - state->bits += (uInt)bits; - return Z_OK; -} - -/* - Return state with length and distance decoding tables and index sizes set to - fixed code decoding. Normally this returns fixed tables from inffixed.h. - If BUILDFIXED is defined, then instead this routine builds the tables the - first time it's called, and returns those tables the first time and - thereafter. This reduces the size of the code by about 2K bytes, in - exchange for a little execution time. However, BUILDFIXED should not be - used for threaded applications, since the rewriting of the tables and virgin - may not be thread-safe. - */ -local void fixedtables(state) -struct inflate_state FAR *state; -{ -#ifdef BUILDFIXED - static int virgin = 1; - static code *lenfix, *distfix; - static code fixed[544]; - - /* build fixed huffman tables if first call (may not be thread safe) */ - if (virgin) { - unsigned sym, bits; - static code *next; - - /* literal/length table */ - sym = 0; - while (sym < 144) state->lens[sym++] = 8; - while (sym < 256) state->lens[sym++] = 9; - while (sym < 280) state->lens[sym++] = 7; - while (sym < 288) state->lens[sym++] = 8; - next = fixed; - lenfix = next; - bits = 9; - inflate_table(LENS, state->lens, 288, &(next), &(bits), state->work); - - /* distance table */ - sym = 0; - while (sym < 32) state->lens[sym++] = 5; - distfix = next; - bits = 5; - inflate_table(DISTS, state->lens, 32, &(next), &(bits), state->work); - - /* do this just once */ - virgin = 0; - } -#else /* !BUILDFIXED */ -# include "inffixed.h" -#endif /* BUILDFIXED */ - state->lencode = lenfix; - state->lenbits = 9; - state->distcode = distfix; - state->distbits = 5; -} - -#ifdef MAKEFIXED -#include - -/* - Write out the inffixed.h that is #include'd above. Defining MAKEFIXED also - defines BUILDFIXED, so the tables are built on the fly. makefixed() writes - those tables to stdout, which would be piped to inffixed.h. A small program - can simply call makefixed to do this: - - void makefixed(void); - - int main(void) - { - makefixed(); - return 0; - } - - Then that can be linked with zlib built with MAKEFIXED defined and run: - - a.out > inffixed.h - */ -void makefixed() -{ - unsigned low, size; - struct inflate_state state; - - fixedtables(&state); - puts(" /* inffixed.h -- table for decoding fixed codes"); - puts(" * Generated automatically by makefixed()."); - puts(" */"); - puts(""); - puts(" /* WARNING: this file should *not* be used by applications."); - puts(" It is part of the implementation of this library and is"); - puts(" subject to change. Applications should only use zlib.h."); - puts(" */"); - puts(""); - size = 1U << 9; - printf(" static const code lenfix[%u] = {", size); - low = 0; - for (;;) { - if ((low % 7) == 0) printf("\n "); - printf("{%u,%u,%d}", (low & 127) == 99 ? 64 : state.lencode[low].op, - state.lencode[low].bits, state.lencode[low].val); - if (++low == size) break; - putchar(','); - } - puts("\n };"); - size = 1U << 5; - printf("\n static const code distfix[%u] = {", size); - low = 0; - for (;;) { - if ((low % 6) == 0) printf("\n "); - printf("{%u,%u,%d}", state.distcode[low].op, state.distcode[low].bits, - state.distcode[low].val); - if (++low == size) break; - putchar(','); - } - puts("\n };"); -} -#endif /* MAKEFIXED */ - -/* - Update the window with the last wsize (normally 32K) bytes written before - returning. If window does not exist yet, create it. This is only called - when a window is already in use, or when output has been written during this - inflate call, but the end of the deflate stream has not been reached yet. - It is also called to create a window for dictionary data when a dictionary - is loaded. - - Providing output buffers larger than 32K to inflate() should provide a speed - advantage, since only the last 32K of output is copied to the sliding window - upon return from inflate(), and since all distances after the first 32K of - output will fall in the output data, making match copies simpler and faster. - The advantage may be dependent on the size of the processor's data caches. - */ -local int updatewindow(strm, end, copy) -z_streamp strm; -const Bytef *end; -unsigned copy; -{ - struct inflate_state FAR *state; - unsigned dist; - - state = (struct inflate_state FAR *)strm->state; - - /* if it hasn't been done already, allocate space for the window */ - if (state->window == Z_NULL) { - state->window = (unsigned char FAR *) - ZALLOC(strm, 1U << state->wbits, - sizeof(unsigned char)); - if (state->window == Z_NULL) return 1; - } - - /* if window not in use yet, initialize */ - if (state->wsize == 0) { - state->wsize = 1U << state->wbits; - state->wnext = 0; - state->whave = 0; - } - - /* copy state->wsize or less output bytes into the circular window */ - if (copy >= state->wsize) { - zmemcpy(state->window, end - state->wsize, state->wsize); - state->wnext = 0; - state->whave = state->wsize; - } - else { - dist = state->wsize - state->wnext; - if (dist > copy) dist = copy; - zmemcpy(state->window + state->wnext, end - copy, dist); - copy -= dist; - if (copy) { - zmemcpy(state->window, end - copy, copy); - state->wnext = copy; - state->whave = state->wsize; - } - else { - state->wnext += dist; - if (state->wnext == state->wsize) state->wnext = 0; - if (state->whave < state->wsize) state->whave += dist; - } - } - return 0; -} - -/* Macros for inflate(): */ - -/* check function to use adler32() for zlib or crc32() for gzip */ -#ifdef GUNZIP -# define UPDATE(check, buf, len) \ - (state->flags ? crc32(check, buf, len) : adler32(check, buf, len)) -#else -# define UPDATE(check, buf, len) adler32(check, buf, len) -#endif - -/* check macros for header crc */ -#ifdef GUNZIP -# define CRC2(check, word) \ - do { \ - hbuf[0] = (unsigned char)(word); \ - hbuf[1] = (unsigned char)((word) >> 8); \ - check = crc32(check, hbuf, 2); \ - } while (0) - -# define CRC4(check, word) \ - do { \ - hbuf[0] = (unsigned char)(word); \ - hbuf[1] = (unsigned char)((word) >> 8); \ - hbuf[2] = (unsigned char)((word) >> 16); \ - hbuf[3] = (unsigned char)((word) >> 24); \ - check = crc32(check, hbuf, 4); \ - } while (0) -#endif - -/* Load registers with state in inflate() for speed */ -#define LOAD() \ - do { \ - put = strm->next_out; \ - left = strm->avail_out; \ - next = strm->next_in; \ - have = strm->avail_in; \ - hold = state->hold; \ - bits = state->bits; \ - } while (0) - -/* Restore state from registers in inflate() */ -#define RESTORE() \ - do { \ - strm->next_out = put; \ - strm->avail_out = left; \ - strm->next_in = next; \ - strm->avail_in = have; \ - state->hold = hold; \ - state->bits = bits; \ - } while (0) - -/* Clear the input bit accumulator */ -#define INITBITS() \ - do { \ - hold = 0; \ - bits = 0; \ - } while (0) - -/* Get a byte of input into the bit accumulator, or return from inflate() - if there is no input available. */ -#define PULLBYTE() \ - do { \ - if (have == 0) goto inf_leave; \ - have--; \ - hold += (unsigned long)(*next++) << bits; \ - bits += 8; \ - } while (0) - -/* Assure that there are at least n bits in the bit accumulator. If there is - not enough available input to do that, then return from inflate(). */ -#define NEEDBITS(n) \ - do { \ - while (bits < (unsigned)(n)) \ - PULLBYTE(); \ - } while (0) - -/* Return the low n bits of the bit accumulator (n < 16) */ -#define BITS(n) \ - ((unsigned)hold & ((1U << (n)) - 1)) - -/* Remove n bits from the bit accumulator */ -#define DROPBITS(n) \ - do { \ - hold >>= (n); \ - bits -= (unsigned)(n); \ - } while (0) - -/* Remove zero to seven bits as needed to go to a byte boundary */ -#define BYTEBITS() \ - do { \ - hold >>= bits & 7; \ - bits -= bits & 7; \ - } while (0) - -/* - inflate() uses a state machine to process as much input data and generate as - much output data as possible before returning. The state machine is - structured roughly as follows: - - for (;;) switch (state) { - ... - case STATEn: - if (not enough input data or output space to make progress) - return; - ... make progress ... - state = STATEm; - break; - ... - } - - so when inflate() is called again, the same case is attempted again, and - if the appropriate resources are provided, the machine proceeds to the - next state. The NEEDBITS() macro is usually the way the state evaluates - whether it can proceed or should return. NEEDBITS() does the return if - the requested bits are not available. The typical use of the BITS macros - is: - - NEEDBITS(n); - ... do something with BITS(n) ... - DROPBITS(n); - - where NEEDBITS(n) either returns from inflate() if there isn't enough - input left to load n bits into the accumulator, or it continues. BITS(n) - gives the low n bits in the accumulator. When done, DROPBITS(n) drops - the low n bits off the accumulator. INITBITS() clears the accumulator - and sets the number of available bits to zero. BYTEBITS() discards just - enough bits to put the accumulator on a byte boundary. After BYTEBITS() - and a NEEDBITS(8), then BITS(8) would return the next byte in the stream. - - NEEDBITS(n) uses PULLBYTE() to get an available byte of input, or to return - if there is no input available. The decoding of variable length codes uses - PULLBYTE() directly in order to pull just enough bytes to decode the next - code, and no more. - - Some states loop until they get enough input, making sure that enough - state information is maintained to continue the loop where it left off - if NEEDBITS() returns in the loop. For example, want, need, and keep - would all have to actually be part of the saved state in case NEEDBITS() - returns: - - case STATEw: - while (want < need) { - NEEDBITS(n); - keep[want++] = BITS(n); - DROPBITS(n); - } - state = STATEx; - case STATEx: - - As shown above, if the next state is also the next case, then the break - is omitted. - - A state may also return if there is not enough output space available to - complete that state. Those states are copying stored data, writing a - literal byte, and copying a matching string. - - When returning, a "goto inf_leave" is used to update the total counters, - update the check value, and determine whether any progress has been made - during that inflate() call in order to return the proper return code. - Progress is defined as a change in either strm->avail_in or strm->avail_out. - When there is a window, goto inf_leave will update the window with the last - output written. If a goto inf_leave occurs in the middle of decompression - and there is no window currently, goto inf_leave will create one and copy - output to the window for the next call of inflate(). - - In this implementation, the flush parameter of inflate() only affects the - return code (per zlib.h). inflate() always writes as much as possible to - strm->next_out, given the space available and the provided input--the effect - documented in zlib.h of Z_SYNC_FLUSH. Furthermore, inflate() always defers - the allocation of and copying into a sliding window until necessary, which - provides the effect documented in zlib.h for Z_FINISH when the entire input - stream available. So the only thing the flush parameter actually does is: - when flush is set to Z_FINISH, inflate() cannot return Z_OK. Instead it - will return Z_BUF_ERROR if it has not reached the end of the stream. - */ - -int ZEXPORT inflate(strm, flush) -z_streamp strm; -int flush; -{ - struct inflate_state FAR *state; - z_const unsigned char FAR *next; /* next input */ - unsigned char FAR *put; /* next output */ - unsigned have, left; /* available input and output */ - unsigned long hold; /* bit buffer */ - unsigned bits; /* bits in bit buffer */ - unsigned in, out; /* save starting available input and output */ - unsigned copy; /* number of stored or match bytes to copy */ - unsigned char FAR *from; /* where to copy match bytes from */ - code here; /* current decoding table entry */ - code last; /* parent table entry */ - unsigned len; /* length to copy for repeats, bits to drop */ - int ret; /* return code */ -#ifdef GUNZIP - unsigned char hbuf[4]; /* buffer for gzip header crc calculation */ -#endif - static const unsigned short order[19] = /* permutation of code lengths */ - {16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15}; - - if (inflateStateCheck(strm) || strm->next_out == Z_NULL || - (strm->next_in == Z_NULL && strm->avail_in != 0)) - return Z_STREAM_ERROR; - - state = (struct inflate_state FAR *)strm->state; - if (state->mode == TYPE) state->mode = TYPEDO; /* skip check */ - LOAD(); - in = have; - out = left; - ret = Z_OK; - for (;;) - switch (state->mode) { - case HEAD: - if (state->wrap == 0) { - state->mode = TYPEDO; - break; - } - NEEDBITS(16); -#ifdef GUNZIP - if ((state->wrap & 2) && hold == 0x8b1f) { /* gzip header */ - if (state->wbits == 0) - state->wbits = 15; - state->check = crc32(0L, Z_NULL, 0); - CRC2(state->check, hold); - INITBITS(); - state->mode = FLAGS; - break; - } - state->flags = 0; /* expect zlib header */ - if (state->head != Z_NULL) - state->head->done = -1; - if (!(state->wrap & 1) || /* check if zlib header allowed */ -#else - if ( -#endif - ((BITS(8) << 8) + (hold >> 8)) % 31) { - strm->msg = (char *)"incorrect header check"; - state->mode = BAD; - break; - } - if (BITS(4) != Z_DEFLATED) { - strm->msg = (char *)"unknown compression method"; - state->mode = BAD; - break; - } - DROPBITS(4); - len = BITS(4) + 8; - if (state->wbits == 0) - state->wbits = len; - if (len > 15 || len > state->wbits) { - strm->msg = (char *)"invalid window size"; - state->mode = BAD; - break; - } - state->dmax = 1U << len; - Tracev((stderr, "inflate: zlib header ok\n")); - strm->adler = state->check = adler32(0L, Z_NULL, 0); - state->mode = hold & 0x200 ? DICTID : TYPE; - INITBITS(); - break; -#ifdef GUNZIP - case FLAGS: - NEEDBITS(16); - state->flags = (int)(hold); - if ((state->flags & 0xff) != Z_DEFLATED) { - strm->msg = (char *)"unknown compression method"; - state->mode = BAD; - break; - } - if (state->flags & 0xe000) { - strm->msg = (char *)"unknown header flags set"; - state->mode = BAD; - break; - } - if (state->head != Z_NULL) - state->head->text = (int)((hold >> 8) & 1); - if ((state->flags & 0x0200) && (state->wrap & 4)) - CRC2(state->check, hold); - INITBITS(); - state->mode = TIME; - case TIME: - NEEDBITS(32); - if (state->head != Z_NULL) - state->head->time = hold; - if ((state->flags & 0x0200) && (state->wrap & 4)) - CRC4(state->check, hold); - INITBITS(); - state->mode = OS; - case OS: - NEEDBITS(16); - if (state->head != Z_NULL) { - state->head->xflags = (int)(hold & 0xff); - state->head->os = (int)(hold >> 8); - } - if ((state->flags & 0x0200) && (state->wrap & 4)) - CRC2(state->check, hold); - INITBITS(); - state->mode = EXLEN; - case EXLEN: - if (state->flags & 0x0400) { - NEEDBITS(16); - state->length = (unsigned)(hold); - if (state->head != Z_NULL) - state->head->extra_len = (unsigned)hold; - if ((state->flags & 0x0200) && (state->wrap & 4)) - CRC2(state->check, hold); - INITBITS(); - } - else if (state->head != Z_NULL) - state->head->extra = Z_NULL; - state->mode = EXTRA; - case EXTRA: - if (state->flags & 0x0400) { - copy = state->length; - if (copy > have) copy = have; - if (copy) { - if (state->head != Z_NULL && - state->head->extra != Z_NULL) { - len = state->head->extra_len - state->length; - zmemcpy(state->head->extra + len, next, - len + copy > state->head->extra_max ? - state->head->extra_max - len : copy); - } - if ((state->flags & 0x0200) && (state->wrap & 4)) - state->check = crc32(state->check, next, copy); - have -= copy; - next += copy; - state->length -= copy; - } - if (state->length) goto inf_leave; - } - state->length = 0; - state->mode = NAME; - case NAME: - if (state->flags & 0x0800) { - if (have == 0) goto inf_leave; - copy = 0; - do { - len = (unsigned)(next[copy++]); - if (state->head != Z_NULL && - state->head->name != Z_NULL && - state->length < state->head->name_max) - state->head->name[state->length++] = (Bytef)len; - } while (len && copy < have); - if ((state->flags & 0x0200) && (state->wrap & 4)) - state->check = crc32(state->check, next, copy); - have -= copy; - next += copy; - if (len) goto inf_leave; - } - else if (state->head != Z_NULL) - state->head->name = Z_NULL; - state->length = 0; - state->mode = COMMENT; - case COMMENT: - if (state->flags & 0x1000) { - if (have == 0) goto inf_leave; - copy = 0; - do { - len = (unsigned)(next[copy++]); - if (state->head != Z_NULL && - state->head->comment != Z_NULL && - state->length < state->head->comm_max) - state->head->comment[state->length++] = (Bytef)len; - } while (len && copy < have); - if ((state->flags & 0x0200) && (state->wrap & 4)) - state->check = crc32(state->check, next, copy); - have -= copy; - next += copy; - if (len) goto inf_leave; - } - else if (state->head != Z_NULL) - state->head->comment = Z_NULL; - state->mode = HCRC; - case HCRC: - if (state->flags & 0x0200) { - NEEDBITS(16); - if ((state->wrap & 4) && hold != (state->check & 0xffff)) { - strm->msg = (char *)"header crc mismatch"; - state->mode = BAD; - break; - } - INITBITS(); - } - if (state->head != Z_NULL) { - state->head->hcrc = (int)((state->flags >> 9) & 1); - state->head->done = 1; - } - strm->adler = state->check = crc32(0L, Z_NULL, 0); - state->mode = TYPE; - break; -#endif - case DICTID: - NEEDBITS(32); - strm->adler = state->check = ZSWAP32(hold); - INITBITS(); - state->mode = DICT; - case DICT: - if (state->havedict == 0) { - RESTORE(); - return Z_NEED_DICT; - } - strm->adler = state->check = adler32(0L, Z_NULL, 0); - state->mode = TYPE; - case TYPE: - if (flush == Z_BLOCK || flush == Z_TREES) goto inf_leave; - case TYPEDO: - if (state->last) { - BYTEBITS(); - state->mode = CHECK; - break; - } - NEEDBITS(3); - state->last = BITS(1); - DROPBITS(1); - switch (BITS(2)) { - case 0: /* stored block */ - Tracev((stderr, "inflate: stored block%s\n", - state->last ? " (last)" : "")); - state->mode = STORED; - break; - case 1: /* fixed block */ - fixedtables(state); - Tracev((stderr, "inflate: fixed codes block%s\n", - state->last ? " (last)" : "")); - state->mode = LEN_; /* decode codes */ - if (flush == Z_TREES) { - DROPBITS(2); - goto inf_leave; - } - break; - case 2: /* dynamic block */ - Tracev((stderr, "inflate: dynamic codes block%s\n", - state->last ? " (last)" : "")); - state->mode = TABLE; - break; - case 3: - strm->msg = (char *)"invalid block type"; - state->mode = BAD; - } - DROPBITS(2); - break; - case STORED: - BYTEBITS(); /* go to byte boundary */ - NEEDBITS(32); - if ((hold & 0xffff) != ((hold >> 16) ^ 0xffff)) { - strm->msg = (char *)"invalid stored block lengths"; - state->mode = BAD; - break; - } - state->length = (unsigned)hold & 0xffff; - Tracev((stderr, "inflate: stored length %u\n", - state->length)); - INITBITS(); - state->mode = COPY_; - if (flush == Z_TREES) goto inf_leave; - case COPY_: - state->mode = COPY; - case COPY: - copy = state->length; - if (copy) { - if (copy > have) copy = have; - if (copy > left) copy = left; - if (copy == 0) goto inf_leave; - zmemcpy(put, next, copy); - have -= copy; - next += copy; - left -= copy; - put += copy; - state->length -= copy; - break; - } - Tracev((stderr, "inflate: stored end\n")); - state->mode = TYPE; - break; - case TABLE: - NEEDBITS(14); - state->nlen = BITS(5) + 257; - DROPBITS(5); - state->ndist = BITS(5) + 1; - DROPBITS(5); - state->ncode = BITS(4) + 4; - DROPBITS(4); -#ifndef PKZIP_BUG_WORKAROUND - if (state->nlen > 286 || state->ndist > 30) { - strm->msg = (char *)"too many length or distance symbols"; - state->mode = BAD; - break; - } -#endif - Tracev((stderr, "inflate: table sizes ok\n")); - state->have = 0; - state->mode = LENLENS; - case LENLENS: - while (state->have < state->ncode) { - NEEDBITS(3); - state->lens[order[state->have++]] = (unsigned short)BITS(3); - DROPBITS(3); - } - while (state->have < 19) - state->lens[order[state->have++]] = 0; - state->next = state->codes; - state->lencode = (const code FAR *)(state->next); - state->lenbits = 7; - ret = inflate_table(CODES, state->lens, 19, &(state->next), - &(state->lenbits), state->work); - if (ret) { - strm->msg = (char *)"invalid code lengths set"; - state->mode = BAD; - break; - } - Tracev((stderr, "inflate: code lengths ok\n")); - state->have = 0; - state->mode = CODELENS; - case CODELENS: - while (state->have < state->nlen + state->ndist) { - for (;;) { - here = state->lencode[BITS(state->lenbits)]; - if ((unsigned)(here.bits) <= bits) break; - PULLBYTE(); - } - if (here.val < 16) { - DROPBITS(here.bits); - state->lens[state->have++] = here.val; - } - else { - if (here.val == 16) { - NEEDBITS(here.bits + 2); - DROPBITS(here.bits); - if (state->have == 0) { - strm->msg = (char *)"invalid bit length repeat"; - state->mode = BAD; - break; - } - len = state->lens[state->have - 1]; - copy = 3 + BITS(2); - DROPBITS(2); - } - else if (here.val == 17) { - NEEDBITS(here.bits + 3); - DROPBITS(here.bits); - len = 0; - copy = 3 + BITS(3); - DROPBITS(3); - } - else { - NEEDBITS(here.bits + 7); - DROPBITS(here.bits); - len = 0; - copy = 11 + BITS(7); - DROPBITS(7); - } - if (state->have + copy > state->nlen + state->ndist) { - strm->msg = (char *)"invalid bit length repeat"; - state->mode = BAD; - break; - } - while (copy--) - state->lens[state->have++] = (unsigned short)len; - } - } - - /* handle error breaks in while */ - if (state->mode == BAD) break; - - /* check for end-of-block code (better have one) */ - if (state->lens[256] == 0) { - strm->msg = (char *)"invalid code -- missing end-of-block"; - state->mode = BAD; - break; - } - - /* build code tables -- note: do not change the lenbits or distbits - values here (9 and 6) without reading the comments in inftrees.h - concerning the ENOUGH constants, which depend on those values */ - state->next = state->codes; - state->lencode = (const code FAR *)(state->next); - state->lenbits = 9; - ret = inflate_table(LENS, state->lens, state->nlen, &(state->next), - &(state->lenbits), state->work); - if (ret) { - strm->msg = (char *)"invalid literal/lengths set"; - state->mode = BAD; - break; - } - state->distcode = (const code FAR *)(state->next); - state->distbits = 6; - ret = inflate_table(DISTS, state->lens + state->nlen, state->ndist, - &(state->next), &(state->distbits), state->work); - if (ret) { - strm->msg = (char *)"invalid distances set"; - state->mode = BAD; - break; - } - Tracev((stderr, "inflate: codes ok\n")); - state->mode = LEN_; - if (flush == Z_TREES) goto inf_leave; - case LEN_: - state->mode = LEN; - case LEN: - if (have >= 6 && left >= 258) { - RESTORE(); - inflate_fast(strm, out); - LOAD(); - if (state->mode == TYPE) - state->back = -1; - break; - } - state->back = 0; - for (;;) { - here = state->lencode[BITS(state->lenbits)]; - if ((unsigned)(here.bits) <= bits) break; - PULLBYTE(); - } - if (here.op && (here.op & 0xf0) == 0) { - last = here; - for (;;) { - here = state->lencode[last.val + - (BITS(last.bits + last.op) >> last.bits)]; - if ((unsigned)(last.bits + here.bits) <= bits) break; - PULLBYTE(); - } - DROPBITS(last.bits); - state->back += last.bits; - } - DROPBITS(here.bits); - state->back += here.bits; - state->length = (unsigned)here.val; - if ((int)(here.op) == 0) { - Tracevv((stderr, here.val >= 0x20 && here.val < 0x7f ? - "inflate: literal '%c'\n" : - "inflate: literal 0x%02x\n", here.val)); - state->mode = LIT; - break; - } - if (here.op & 32) { - Tracevv((stderr, "inflate: end of block\n")); - state->back = -1; - state->mode = TYPE; - break; - } - if (here.op & 64) { - strm->msg = (char *)"invalid literal/length code"; - state->mode = BAD; - break; - } - state->extra = (unsigned)(here.op) & 15; - state->mode = LENEXT; - case LENEXT: - if (state->extra) { - NEEDBITS(state->extra); - state->length += BITS(state->extra); - DROPBITS(state->extra); - state->back += state->extra; - } - Tracevv((stderr, "inflate: length %u\n", state->length)); - state->was = state->length; - state->mode = DIST; - case DIST: - for (;;) { - here = state->distcode[BITS(state->distbits)]; - if ((unsigned)(here.bits) <= bits) break; - PULLBYTE(); - } - if ((here.op & 0xf0) == 0) { - last = here; - for (;;) { - here = state->distcode[last.val + - (BITS(last.bits + last.op) >> last.bits)]; - if ((unsigned)(last.bits + here.bits) <= bits) break; - PULLBYTE(); - } - DROPBITS(last.bits); - state->back += last.bits; - } - DROPBITS(here.bits); - state->back += here.bits; - if (here.op & 64) { - strm->msg = (char *)"invalid distance code"; - state->mode = BAD; - break; - } - state->offset = (unsigned)here.val; - state->extra = (unsigned)(here.op) & 15; - state->mode = DISTEXT; - case DISTEXT: - if (state->extra) { - NEEDBITS(state->extra); - state->offset += BITS(state->extra); - DROPBITS(state->extra); - state->back += state->extra; - } -#ifdef INFLATE_STRICT - if (state->offset > state->dmax) { - strm->msg = (char *)"invalid distance too far back"; - state->mode = BAD; - break; - } -#endif - Tracevv((stderr, "inflate: distance %u\n", state->offset)); - state->mode = MATCH; - case MATCH: - if (left == 0) goto inf_leave; - copy = out - left; - if (state->offset > copy) { /* copy from window */ - copy = state->offset - copy; - if (copy > state->whave) { - if (state->sane) { - strm->msg = (char *)"invalid distance too far back"; - state->mode = BAD; - break; - } -#ifdef INFLATE_ALLOW_INVALID_DISTANCE_TOOFAR_ARRR - Trace((stderr, "inflate.c too far\n")); - copy -= state->whave; - if (copy > state->length) copy = state->length; - if (copy > left) copy = left; - left -= copy; - state->length -= copy; - do { - *put++ = 0; - } while (--copy); - if (state->length == 0) state->mode = LEN; - break; -#endif - } - if (copy > state->wnext) { - copy -= state->wnext; - from = state->window + (state->wsize - copy); - } - else - from = state->window + (state->wnext - copy); - if (copy > state->length) copy = state->length; - } - else { /* copy from output */ - from = put - state->offset; - copy = state->length; - } - if (copy > left) copy = left; - left -= copy; - state->length -= copy; - do { - *put++ = *from++; - } while (--copy); - if (state->length == 0) state->mode = LEN; - break; - case LIT: - if (left == 0) goto inf_leave; - *put++ = (unsigned char)(state->length); - left--; - state->mode = LEN; - break; - case CHECK: - if (state->wrap) { - NEEDBITS(32); - out -= left; - strm->total_out += out; - state->total += out; - if ((state->wrap & 4) && out) - strm->adler = state->check = - UPDATE(state->check, put - out, out); - out = left; - if ((state->wrap & 4) && ( -#ifdef GUNZIP - state->flags ? hold : -#endif - ZSWAP32(hold)) != state->check) { - strm->msg = (char *)"incorrect data check"; - state->mode = BAD; - break; - } - INITBITS(); - Tracev((stderr, "inflate: check matches trailer\n")); - } -#ifdef GUNZIP - state->mode = LENGTH; - case LENGTH: - if (state->wrap && state->flags) { - NEEDBITS(32); - if (hold != (state->total & 0xffffffffUL)) { - strm->msg = (char *)"incorrect length check"; - state->mode = BAD; - break; - } - INITBITS(); - Tracev((stderr, "inflate: length matches trailer\n")); - } -#endif - state->mode = DONE; - case DONE: - ret = Z_STREAM_END; - goto inf_leave; - case BAD: - ret = Z_DATA_ERROR; - goto inf_leave; - case MEM: - return Z_MEM_ERROR; - case SYNC: - default: - return Z_STREAM_ERROR; - } - - /* - Return from inflate(), updating the total counts and the check value. - If there was no progress during the inflate() call, return a buffer - error. Call updatewindow() to create and/or update the window state. - Note: a memory error from inflate() is non-recoverable. - */ - inf_leave: - RESTORE(); - if (state->wsize || (out != strm->avail_out && state->mode < BAD && - (state->mode < CHECK || flush != Z_FINISH))) - if (updatewindow(strm, strm->next_out, out - strm->avail_out)) { - state->mode = MEM; - return Z_MEM_ERROR; - } - in -= strm->avail_in; - out -= strm->avail_out; - strm->total_in += in; - strm->total_out += out; - state->total += out; - if ((state->wrap & 4) && out) - strm->adler = state->check = - UPDATE(state->check, strm->next_out - out, out); - strm->data_type = (int)state->bits + (state->last ? 64 : 0) + - (state->mode == TYPE ? 128 : 0) + - (state->mode == LEN_ || state->mode == COPY_ ? 256 : 0); - if (((in == 0 && out == 0) || flush == Z_FINISH) && ret == Z_OK) - ret = Z_BUF_ERROR; - return ret; -} - -int ZEXPORT inflateEnd(strm) -z_streamp strm; -{ - struct inflate_state FAR *state; - if (inflateStateCheck(strm)) - return Z_STREAM_ERROR; - state = (struct inflate_state FAR *)strm->state; - if (state->window != Z_NULL) ZFREE(strm, state->window); - ZFREE(strm, strm->state); - strm->state = Z_NULL; - Tracev((stderr, "inflate: end\n")); - return Z_OK; -} - -int ZEXPORT inflateGetDictionary(strm, dictionary, dictLength) -z_streamp strm; -Bytef *dictionary; -uInt *dictLength; -{ - struct inflate_state FAR *state; - - /* check state */ - if (inflateStateCheck(strm)) return Z_STREAM_ERROR; - state = (struct inflate_state FAR *)strm->state; - - /* copy dictionary */ - if (state->whave && dictionary != Z_NULL) { - zmemcpy(dictionary, state->window + state->wnext, - state->whave - state->wnext); - zmemcpy(dictionary + state->whave - state->wnext, - state->window, state->wnext); - } - if (dictLength != Z_NULL) - *dictLength = state->whave; - return Z_OK; -} - -int ZEXPORT inflateSetDictionary(strm, dictionary, dictLength) -z_streamp strm; -const Bytef *dictionary; -uInt dictLength; -{ - struct inflate_state FAR *state; - unsigned long dictid; - int ret; - - /* check state */ - if (inflateStateCheck(strm)) return Z_STREAM_ERROR; - state = (struct inflate_state FAR *)strm->state; - if (state->wrap != 0 && state->mode != DICT) - return Z_STREAM_ERROR; - - /* check for correct dictionary identifier */ - if (state->mode == DICT) { - dictid = adler32(0L, Z_NULL, 0); - dictid = adler32(dictid, dictionary, dictLength); - if (dictid != state->check) - return Z_DATA_ERROR; - } - - /* copy dictionary to window using updatewindow(), which will amend the - existing dictionary if appropriate */ - ret = updatewindow(strm, dictionary + dictLength, dictLength); - if (ret) { - state->mode = MEM; - return Z_MEM_ERROR; - } - state->havedict = 1; - Tracev((stderr, "inflate: dictionary set\n")); - return Z_OK; -} - -int ZEXPORT inflateGetHeader(strm, head) -z_streamp strm; -gz_headerp head; -{ - struct inflate_state FAR *state; - - /* check state */ - if (inflateStateCheck(strm)) return Z_STREAM_ERROR; - state = (struct inflate_state FAR *)strm->state; - if ((state->wrap & 2) == 0) return Z_STREAM_ERROR; - - /* save header structure */ - state->head = head; - head->done = 0; - return Z_OK; -} - -/* - Search buf[0..len-1] for the pattern: 0, 0, 0xff, 0xff. Return when found - or when out of input. When called, *have is the number of pattern bytes - found in order so far, in 0..3. On return *have is updated to the new - state. If on return *have equals four, then the pattern was found and the - return value is how many bytes were read including the last byte of the - pattern. If *have is less than four, then the pattern has not been found - yet and the return value is len. In the latter case, syncsearch() can be - called again with more data and the *have state. *have is initialized to - zero for the first call. - */ -local unsigned syncsearch(have, buf, len) -unsigned FAR *have; -const unsigned char FAR *buf; -unsigned len; -{ - unsigned got; - unsigned next; - - got = *have; - next = 0; - while (next < len && got < 4) { - if ((int)(buf[next]) == (got < 2 ? 0 : 0xff)) - got++; - else if (buf[next]) - got = 0; - else - got = 4 - got; - next++; - } - *have = got; - return next; -} - -int ZEXPORT inflateSync(strm) -z_streamp strm; -{ - unsigned len; /* number of bytes to look at or looked at */ - unsigned long in, out; /* temporary to save total_in and total_out */ - unsigned char buf[4]; /* to restore bit buffer to byte string */ - struct inflate_state FAR *state; - - /* check parameters */ - if (inflateStateCheck(strm)) return Z_STREAM_ERROR; - state = (struct inflate_state FAR *)strm->state; - if (strm->avail_in == 0 && state->bits < 8) return Z_BUF_ERROR; - - /* if first time, start search in bit buffer */ - if (state->mode != SYNC) { - state->mode = SYNC; - state->hold <<= state->bits & 7; - state->bits -= state->bits & 7; - len = 0; - while (state->bits >= 8) { - buf[len++] = (unsigned char)(state->hold); - state->hold >>= 8; - state->bits -= 8; - } - state->have = 0; - syncsearch(&(state->have), buf, len); - } - - /* search available input */ - len = syncsearch(&(state->have), strm->next_in, strm->avail_in); - strm->avail_in -= len; - strm->next_in += len; - strm->total_in += len; - - /* return no joy or set up to restart inflate() on a new block */ - if (state->have != 4) return Z_DATA_ERROR; - in = strm->total_in; out = strm->total_out; - inflateReset(strm); - strm->total_in = in; strm->total_out = out; - state->mode = TYPE; - return Z_OK; -} - -/* - Returns true if inflate is currently at the end of a block generated by - Z_SYNC_FLUSH or Z_FULL_FLUSH. This function is used by one PPP - implementation to provide an additional safety check. PPP uses - Z_SYNC_FLUSH but removes the length bytes of the resulting empty stored - block. When decompressing, PPP checks that at the end of input packet, - inflate is waiting for these length bytes. - */ -int ZEXPORT inflateSyncPoint(strm) -z_streamp strm; -{ - struct inflate_state FAR *state; - - if (inflateStateCheck(strm)) return Z_STREAM_ERROR; - state = (struct inflate_state FAR *)strm->state; - return state->mode == STORED && state->bits == 0; -} - -int ZEXPORT inflateCopy(dest, source) -z_streamp dest; -z_streamp source; -{ - struct inflate_state FAR *state; - struct inflate_state FAR *copy; - unsigned char FAR *window; - unsigned wsize; - - /* check input */ - if (inflateStateCheck(source) || dest == Z_NULL) - return Z_STREAM_ERROR; - state = (struct inflate_state FAR *)source->state; - - /* allocate space */ - copy = (struct inflate_state FAR *) - ZALLOC(source, 1, sizeof(struct inflate_state)); - if (copy == Z_NULL) return Z_MEM_ERROR; - window = Z_NULL; - if (state->window != Z_NULL) { - window = (unsigned char FAR *) - ZALLOC(source, 1U << state->wbits, sizeof(unsigned char)); - if (window == Z_NULL) { - ZFREE(source, copy); - return Z_MEM_ERROR; - } - } - - /* copy state */ - zmemcpy((voidpf)dest, (voidpf)source, sizeof(z_stream)); - zmemcpy((voidpf)copy, (voidpf)state, sizeof(struct inflate_state)); - copy->strm = dest; - if (state->lencode >= state->codes && - state->lencode <= state->codes + ENOUGH - 1) { - copy->lencode = copy->codes + (state->lencode - state->codes); - copy->distcode = copy->codes + (state->distcode - state->codes); - } - copy->next = copy->codes + (state->next - state->codes); - if (window != Z_NULL) { - wsize = 1U << state->wbits; - zmemcpy(window, state->window, wsize); - } - copy->window = window; - dest->state = (struct internal_state FAR *)copy; - return Z_OK; -} - -int ZEXPORT inflateUndermine(strm, subvert) -z_streamp strm; -int subvert; -{ - struct inflate_state FAR *state; - - if (inflateStateCheck(strm)) return Z_STREAM_ERROR; - state = (struct inflate_state FAR *)strm->state; -#ifdef INFLATE_ALLOW_INVALID_DISTANCE_TOOFAR_ARRR - state->sane = !subvert; - return Z_OK; -#else - (void)subvert; - state->sane = 1; - return Z_DATA_ERROR; -#endif -} - -int ZEXPORT inflateValidate(strm, check) -z_streamp strm; -int check; -{ - struct inflate_state FAR *state; - - if (inflateStateCheck(strm)) return Z_STREAM_ERROR; - state = (struct inflate_state FAR *)strm->state; - if (check) - state->wrap |= 4; - else - state->wrap &= ~4; - return Z_OK; -} - -long ZEXPORT inflateMark(strm) -z_streamp strm; -{ - struct inflate_state FAR *state; - - if (inflateStateCheck(strm)) - return -(1L << 16); - state = (struct inflate_state FAR *)strm->state; - return (long)(((unsigned long)((long)state->back)) << 16) + - (state->mode == COPY ? state->length : - (state->mode == MATCH ? state->was - state->length : 0)); -} - -unsigned long ZEXPORT inflateCodesUsed(strm) -z_streamp strm; -{ - struct inflate_state FAR *state; - if (inflateStateCheck(strm)) return (unsigned long)-1; - state = (struct inflate_state FAR *)strm->state; - return (unsigned long)(state->next - state->codes); -} diff --git a/deps/zlib/inflate.h b/deps/zlib/inflate.h deleted file mode 100644 index a46cce6..0000000 --- a/deps/zlib/inflate.h +++ /dev/null @@ -1,125 +0,0 @@ -/* inflate.h -- internal inflate state definition - * Copyright (C) 1995-2016 Mark Adler - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -/* WARNING: this file should *not* be used by applications. It is - part of the implementation of the compression library and is - subject to change. Applications should only use zlib.h. - */ - -/* define NO_GZIP when compiling if you want to disable gzip header and - trailer decoding by inflate(). NO_GZIP would be used to avoid linking in - the crc code when it is not needed. For shared libraries, gzip decoding - should be left enabled. */ -#ifndef NO_GZIP -# define GUNZIP -#endif - -/* Possible inflate modes between inflate() calls */ -typedef enum { - HEAD = 16180, /* i: waiting for magic header */ - FLAGS, /* i: waiting for method and flags (gzip) */ - TIME, /* i: waiting for modification time (gzip) */ - OS, /* i: waiting for extra flags and operating system (gzip) */ - EXLEN, /* i: waiting for extra length (gzip) */ - EXTRA, /* i: waiting for extra bytes (gzip) */ - NAME, /* i: waiting for end of file name (gzip) */ - COMMENT, /* i: waiting for end of comment (gzip) */ - HCRC, /* i: waiting for header crc (gzip) */ - DICTID, /* i: waiting for dictionary check value */ - DICT, /* waiting for inflateSetDictionary() call */ - TYPE, /* i: waiting for type bits, including last-flag bit */ - TYPEDO, /* i: same, but skip check to exit inflate on new block */ - STORED, /* i: waiting for stored size (length and complement) */ - COPY_, /* i/o: same as COPY below, but only first time in */ - COPY, /* i/o: waiting for input or output to copy stored block */ - TABLE, /* i: waiting for dynamic block table lengths */ - LENLENS, /* i: waiting for code length code lengths */ - CODELENS, /* i: waiting for length/lit and distance code lengths */ - LEN_, /* i: same as LEN below, but only first time in */ - LEN, /* i: waiting for length/lit/eob code */ - LENEXT, /* i: waiting for length extra bits */ - DIST, /* i: waiting for distance code */ - DISTEXT, /* i: waiting for distance extra bits */ - MATCH, /* o: waiting for output space to copy string */ - LIT, /* o: waiting for output space to write literal */ - CHECK, /* i: waiting for 32-bit check value */ - LENGTH, /* i: waiting for 32-bit length (gzip) */ - DONE, /* finished check, done -- remain here until reset */ - BAD, /* got a data error -- remain here until reset */ - MEM, /* got an inflate() memory error -- remain here until reset */ - SYNC /* looking for synchronization bytes to restart inflate() */ -} inflate_mode; - -/* - State transitions between above modes - - - (most modes can go to BAD or MEM on error -- not shown for clarity) - - Process header: - HEAD -> (gzip) or (zlib) or (raw) - (gzip) -> FLAGS -> TIME -> OS -> EXLEN -> EXTRA -> NAME -> COMMENT -> - HCRC -> TYPE - (zlib) -> DICTID or TYPE - DICTID -> DICT -> TYPE - (raw) -> TYPEDO - Read deflate blocks: - TYPE -> TYPEDO -> STORED or TABLE or LEN_ or CHECK - STORED -> COPY_ -> COPY -> TYPE - TABLE -> LENLENS -> CODELENS -> LEN_ - LEN_ -> LEN - Read deflate codes in fixed or dynamic block: - LEN -> LENEXT or LIT or TYPE - LENEXT -> DIST -> DISTEXT -> MATCH -> LEN - LIT -> LEN - Process trailer: - CHECK -> LENGTH -> DONE - */ - -/* State maintained between inflate() calls -- approximately 7K bytes, not - including the allocated sliding window, which is up to 32K bytes. */ -struct inflate_state { - z_streamp strm; /* pointer back to this zlib stream */ - inflate_mode mode; /* current inflate mode */ - int last; /* true if processing last block */ - int wrap; /* bit 0 true for zlib, bit 1 true for gzip, - bit 2 true to validate check value */ - int havedict; /* true if dictionary provided */ - int flags; /* gzip header method and flags (0 if zlib) */ - unsigned dmax; /* zlib header max distance (INFLATE_STRICT) */ - unsigned long check; /* protected copy of check value */ - unsigned long total; /* protected copy of output count */ - gz_headerp head; /* where to save gzip header information */ - /* sliding window */ - unsigned wbits; /* log base 2 of requested window size */ - unsigned wsize; /* window size or zero if not using window */ - unsigned whave; /* valid bytes in the window */ - unsigned wnext; /* window write index */ - unsigned char FAR *window; /* allocated sliding window, if needed */ - /* bit accumulator */ - unsigned long hold; /* input bit accumulator */ - unsigned bits; /* number of bits in "in" */ - /* for string and stored block copying */ - unsigned length; /* literal or length of data to copy */ - unsigned offset; /* distance back to copy string from */ - /* for table and code decoding */ - unsigned extra; /* extra bits needed */ - /* fixed and dynamic code tables */ - code const FAR *lencode; /* starting table for length/literal codes */ - code const FAR *distcode; /* starting table for distance codes */ - unsigned lenbits; /* index bits for lencode */ - unsigned distbits; /* index bits for distcode */ - /* dynamic table building */ - unsigned ncode; /* number of code length code lengths */ - unsigned nlen; /* number of length code lengths */ - unsigned ndist; /* number of distance code lengths */ - unsigned have; /* number of code lengths in lens[] */ - code FAR *next; /* next available space in codes[] */ - unsigned short lens[320]; /* temporary storage for code lengths */ - unsigned short work[288]; /* work area for code table building */ - code codes[ENOUGH]; /* space for code tables */ - int sane; /* if false, allow invalid distance too far */ - int back; /* bits back of last unprocessed length/lit */ - unsigned was; /* initial length of match */ -}; diff --git a/deps/zlib/inftrees.c b/deps/zlib/inftrees.c deleted file mode 100644 index 2ea08fc..0000000 --- a/deps/zlib/inftrees.c +++ /dev/null @@ -1,304 +0,0 @@ -/* inftrees.c -- generate Huffman trees for efficient decoding - * Copyright (C) 1995-2017 Mark Adler - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -#include "zutil.h" -#include "inftrees.h" - -#define MAXBITS 15 - -const char inflate_copyright[] = - " inflate 1.2.11 Copyright 1995-2017 Mark Adler "; -/* - If you use the zlib library in a product, an acknowledgment is welcome - in the documentation of your product. If for some reason you cannot - include such an acknowledgment, I would appreciate that you keep this - copyright string in the executable of your product. - */ - -/* - Build a set of tables to decode the provided canonical Huffman code. - The code lengths are lens[0..codes-1]. The result starts at *table, - whose indices are 0..2^bits-1. work is a writable array of at least - lens shorts, which is used as a work area. type is the type of code - to be generated, CODES, LENS, or DISTS. On return, zero is success, - -1 is an invalid code, and +1 means that ENOUGH isn't enough. table - on return points to the next available entry's address. bits is the - requested root table index bits, and on return it is the actual root - table index bits. It will differ if the request is greater than the - longest code or if it is less than the shortest code. - */ -int ZLIB_INTERNAL inflate_table(type, lens, codes, table, bits, work) -codetype type; -unsigned short FAR *lens; -unsigned codes; -code FAR * FAR *table; -unsigned FAR *bits; -unsigned short FAR *work; -{ - unsigned len; /* a code's length in bits */ - unsigned sym; /* index of code symbols */ - unsigned min, max; /* minimum and maximum code lengths */ - unsigned root; /* number of index bits for root table */ - unsigned curr; /* number of index bits for current table */ - unsigned drop; /* code bits to drop for sub-table */ - int left; /* number of prefix codes available */ - unsigned used; /* code entries in table used */ - unsigned huff; /* Huffman code */ - unsigned incr; /* for incrementing code, index */ - unsigned fill; /* index for replicating entries */ - unsigned low; /* low bits for current root entry */ - unsigned mask; /* mask for low root bits */ - code here; /* table entry for duplication */ - code FAR *next; /* next available space in table */ - const unsigned short FAR *base; /* base value table to use */ - const unsigned short FAR *extra; /* extra bits table to use */ - unsigned match; /* use base and extra for symbol >= match */ - unsigned short count[MAXBITS+1]; /* number of codes of each length */ - unsigned short offs[MAXBITS+1]; /* offsets in table for each length */ - static const unsigned short lbase[31] = { /* Length codes 257..285 base */ - 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31, - 35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0}; - static const unsigned short lext[31] = { /* Length codes 257..285 extra */ - 16, 16, 16, 16, 16, 16, 16, 16, 17, 17, 17, 17, 18, 18, 18, 18, - 19, 19, 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 16, 77, 202}; - static const unsigned short dbase[32] = { /* Distance codes 0..29 base */ - 1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193, - 257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145, - 8193, 12289, 16385, 24577, 0, 0}; - static const unsigned short dext[32] = { /* Distance codes 0..29 extra */ - 16, 16, 16, 16, 17, 17, 18, 18, 19, 19, 20, 20, 21, 21, 22, 22, - 23, 23, 24, 24, 25, 25, 26, 26, 27, 27, - 28, 28, 29, 29, 64, 64}; - - /* - Process a set of code lengths to create a canonical Huffman code. The - code lengths are lens[0..codes-1]. Each length corresponds to the - symbols 0..codes-1. The Huffman code is generated by first sorting the - symbols by length from short to long, and retaining the symbol order - for codes with equal lengths. Then the code starts with all zero bits - for the first code of the shortest length, and the codes are integer - increments for the same length, and zeros are appended as the length - increases. For the deflate format, these bits are stored backwards - from their more natural integer increment ordering, and so when the - decoding tables are built in the large loop below, the integer codes - are incremented backwards. - - This routine assumes, but does not check, that all of the entries in - lens[] are in the range 0..MAXBITS. The caller must assure this. - 1..MAXBITS is interpreted as that code length. zero means that that - symbol does not occur in this code. - - The codes are sorted by computing a count of codes for each length, - creating from that a table of starting indices for each length in the - sorted table, and then entering the symbols in order in the sorted - table. The sorted table is work[], with that space being provided by - the caller. - - The length counts are used for other purposes as well, i.e. finding - the minimum and maximum length codes, determining if there are any - codes at all, checking for a valid set of lengths, and looking ahead - at length counts to determine sub-table sizes when building the - decoding tables. - */ - - /* accumulate lengths for codes (assumes lens[] all in 0..MAXBITS) */ - for (len = 0; len <= MAXBITS; len++) - count[len] = 0; - for (sym = 0; sym < codes; sym++) - count[lens[sym]]++; - - /* bound code lengths, force root to be within code lengths */ - root = *bits; - for (max = MAXBITS; max >= 1; max--) - if (count[max] != 0) break; - if (root > max) root = max; - if (max == 0) { /* no symbols to code at all */ - here.op = (unsigned char)64; /* invalid code marker */ - here.bits = (unsigned char)1; - here.val = (unsigned short)0; - *(*table)++ = here; /* make a table to force an error */ - *(*table)++ = here; - *bits = 1; - return 0; /* no symbols, but wait for decoding to report error */ - } - for (min = 1; min < max; min++) - if (count[min] != 0) break; - if (root < min) root = min; - - /* check for an over-subscribed or incomplete set of lengths */ - left = 1; - for (len = 1; len <= MAXBITS; len++) { - left <<= 1; - left -= count[len]; - if (left < 0) return -1; /* over-subscribed */ - } - if (left > 0 && (type == CODES || max != 1)) - return -1; /* incomplete set */ - - /* generate offsets into symbol table for each length for sorting */ - offs[1] = 0; - for (len = 1; len < MAXBITS; len++) - offs[len + 1] = offs[len] + count[len]; - - /* sort symbols by length, by symbol order within each length */ - for (sym = 0; sym < codes; sym++) - if (lens[sym] != 0) work[offs[lens[sym]]++] = (unsigned short)sym; - - /* - Create and fill in decoding tables. In this loop, the table being - filled is at next and has curr index bits. The code being used is huff - with length len. That code is converted to an index by dropping drop - bits off of the bottom. For codes where len is less than drop + curr, - those top drop + curr - len bits are incremented through all values to - fill the table with replicated entries. - - root is the number of index bits for the root table. When len exceeds - root, sub-tables are created pointed to by the root entry with an index - of the low root bits of huff. This is saved in low to check for when a - new sub-table should be started. drop is zero when the root table is - being filled, and drop is root when sub-tables are being filled. - - When a new sub-table is needed, it is necessary to look ahead in the - code lengths to determine what size sub-table is needed. The length - counts are used for this, and so count[] is decremented as codes are - entered in the tables. - - used keeps track of how many table entries have been allocated from the - provided *table space. It is checked for LENS and DIST tables against - the constants ENOUGH_LENS and ENOUGH_DISTS to guard against changes in - the initial root table size constants. See the comments in inftrees.h - for more information. - - sym increments through all symbols, and the loop terminates when - all codes of length max, i.e. all codes, have been processed. This - routine permits incomplete codes, so another loop after this one fills - in the rest of the decoding tables with invalid code markers. - */ - - /* set up for code type */ - switch (type) { - case CODES: - base = extra = work; /* dummy value--not used */ - match = 20; - break; - case LENS: - base = lbase; - extra = lext; - match = 257; - break; - default: /* DISTS */ - base = dbase; - extra = dext; - match = 0; - } - - /* initialize state for loop */ - huff = 0; /* starting code */ - sym = 0; /* starting code symbol */ - len = min; /* starting code length */ - next = *table; /* current table to fill in */ - curr = root; /* current table index bits */ - drop = 0; /* current bits to drop from code for index */ - low = (unsigned)(-1); /* trigger new sub-table when len > root */ - used = 1U << root; /* use root table entries */ - mask = used - 1; /* mask for comparing low */ - - /* check available table space */ - if ((type == LENS && used > ENOUGH_LENS) || - (type == DISTS && used > ENOUGH_DISTS)) - return 1; - - /* process all codes and make table entries */ - for (;;) { - /* create table entry */ - here.bits = (unsigned char)(len - drop); - if (work[sym] + 1U < match) { - here.op = (unsigned char)0; - here.val = work[sym]; - } - else if (work[sym] >= match) { - here.op = (unsigned char)(extra[work[sym] - match]); - here.val = base[work[sym] - match]; - } - else { - here.op = (unsigned char)(32 + 64); /* end of block */ - here.val = 0; - } - - /* replicate for those indices with low len bits equal to huff */ - incr = 1U << (len - drop); - fill = 1U << curr; - min = fill; /* save offset to next table */ - do { - fill -= incr; - next[(huff >> drop) + fill] = here; - } while (fill != 0); - - /* backwards increment the len-bit code huff */ - incr = 1U << (len - 1); - while (huff & incr) - incr >>= 1; - if (incr != 0) { - huff &= incr - 1; - huff += incr; - } - else - huff = 0; - - /* go to next symbol, update count, len */ - sym++; - if (--(count[len]) == 0) { - if (len == max) break; - len = lens[work[sym]]; - } - - /* create new sub-table if needed */ - if (len > root && (huff & mask) != low) { - /* if first time, transition to sub-tables */ - if (drop == 0) - drop = root; - - /* increment past last table */ - next += min; /* here min is 1 << curr */ - - /* determine length of next table */ - curr = len - drop; - left = (int)(1 << curr); - while (curr + drop < max) { - left -= count[curr + drop]; - if (left <= 0) break; - curr++; - left <<= 1; - } - - /* check for enough space */ - used += 1U << curr; - if ((type == LENS && used > ENOUGH_LENS) || - (type == DISTS && used > ENOUGH_DISTS)) - return 1; - - /* point entry in root table to sub-table */ - low = huff & mask; - (*table)[low].op = (unsigned char)curr; - (*table)[low].bits = (unsigned char)root; - (*table)[low].val = (unsigned short)(next - *table); - } - } - - /* fill in remaining table entry if code is incomplete (guaranteed to have - at most one remaining entry, since if the code is incomplete, the - maximum code length that was allowed to get this far is one bit) */ - if (huff != 0) { - here.op = (unsigned char)64; /* invalid code marker */ - here.bits = (unsigned char)(len - drop); - here.val = (unsigned short)0; - next[huff] = here; - } - - /* set return parameters */ - *table += used; - *bits = root; - return 0; -} diff --git a/deps/zlib/inftrees.h b/deps/zlib/inftrees.h deleted file mode 100644 index baa53a0..0000000 --- a/deps/zlib/inftrees.h +++ /dev/null @@ -1,62 +0,0 @@ -/* inftrees.h -- header to use inftrees.c - * Copyright (C) 1995-2005, 2010 Mark Adler - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -/* WARNING: this file should *not* be used by applications. It is - part of the implementation of the compression library and is - subject to change. Applications should only use zlib.h. - */ - -/* Structure for decoding tables. Each entry provides either the - information needed to do the operation requested by the code that - indexed that table entry, or it provides a pointer to another - table that indexes more bits of the code. op indicates whether - the entry is a pointer to another table, a literal, a length or - distance, an end-of-block, or an invalid code. For a table - pointer, the low four bits of op is the number of index bits of - that table. For a length or distance, the low four bits of op - is the number of extra bits to get after the code. bits is - the number of bits in this code or part of the code to drop off - of the bit buffer. val is the actual byte to output in the case - of a literal, the base length or distance, or the offset from - the current table to the next table. Each entry is four bytes. */ -typedef struct { - unsigned char op; /* operation, extra bits, table bits */ - unsigned char bits; /* bits in this part of the code */ - unsigned short val; /* offset in table or code value */ -} code; - -/* op values as set by inflate_table(): - 00000000 - literal - 0000tttt - table link, tttt != 0 is the number of table index bits - 0001eeee - length or distance, eeee is the number of extra bits - 01100000 - end of block - 01000000 - invalid code - */ - -/* Maximum size of the dynamic table. The maximum number of code structures is - 1444, which is the sum of 852 for literal/length codes and 592 for distance - codes. These values were found by exhaustive searches using the program - examples/enough.c found in the zlib distribtution. The arguments to that - program are the number of symbols, the initial root table size, and the - maximum bit length of a code. "enough 286 9 15" for literal/length codes - returns returns 852, and "enough 30 6 15" for distance codes returns 592. - The initial root table size (9 or 6) is found in the fifth argument of the - inflate_table() calls in inflate.c and infback.c. If the root table size is - changed, then these maximum sizes would be need to be recalculated and - updated. */ -#define ENOUGH_LENS 852 -#define ENOUGH_DISTS 592 -#define ENOUGH (ENOUGH_LENS+ENOUGH_DISTS) - -/* Type of code to build for inflate_table() */ -typedef enum { - CODES, - LENS, - DISTS -} codetype; - -int ZLIB_INTERNAL inflate_table OF((codetype type, unsigned short FAR *lens, - unsigned codes, code FAR * FAR *table, - unsigned FAR *bits, unsigned short FAR *work)); diff --git a/deps/zlib/trees.c b/deps/zlib/trees.c deleted file mode 100644 index 50cf4b4..0000000 --- a/deps/zlib/trees.c +++ /dev/null @@ -1,1203 +0,0 @@ -/* trees.c -- output deflated data using Huffman coding - * Copyright (C) 1995-2017 Jean-loup Gailly - * detect_data_type() function provided freely by Cosmin Truta, 2006 - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -/* - * ALGORITHM - * - * The "deflation" process uses several Huffman trees. The more - * common source values are represented by shorter bit sequences. - * - * Each code tree is stored in a compressed form which is itself - * a Huffman encoding of the lengths of all the code strings (in - * ascending order by source values). The actual code strings are - * reconstructed from the lengths in the inflate process, as described - * in the deflate specification. - * - * REFERENCES - * - * Deutsch, L.P.,"'Deflate' Compressed Data Format Specification". - * Available in ftp.uu.net:/pub/archiving/zip/doc/deflate-1.1.doc - * - * Storer, James A. - * Data Compression: Methods and Theory, pp. 49-50. - * Computer Science Press, 1988. ISBN 0-7167-8156-5. - * - * Sedgewick, R. - * Algorithms, p290. - * Addison-Wesley, 1983. ISBN 0-201-06672-6. - */ - -/* @(#) $Id$ */ - -/* #define GEN_TREES_H */ - -#include "deflate.h" - -#ifdef ZLIB_DEBUG -# include -#endif - -/* =========================================================================== - * Constants - */ - -#define MAX_BL_BITS 7 -/* Bit length codes must not exceed MAX_BL_BITS bits */ - -#define END_BLOCK 256 -/* end of block literal code */ - -#define REP_3_6 16 -/* repeat previous bit length 3-6 times (2 bits of repeat count) */ - -#define REPZ_3_10 17 -/* repeat a zero length 3-10 times (3 bits of repeat count) */ - -#define REPZ_11_138 18 -/* repeat a zero length 11-138 times (7 bits of repeat count) */ - -local const int extra_lbits[LENGTH_CODES] /* extra bits for each length code */ - = {0,0,0,0,0,0,0,0,1,1,1,1,2,2,2,2,3,3,3,3,4,4,4,4,5,5,5,5,0}; - -local const int extra_dbits[D_CODES] /* extra bits for each distance code */ - = {0,0,0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7,8,8,9,9,10,10,11,11,12,12,13,13}; - -local const int extra_blbits[BL_CODES]/* extra bits for each bit length code */ - = {0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,2,3,7}; - -local const uch bl_order[BL_CODES] - = {16,17,18,0,8,7,9,6,10,5,11,4,12,3,13,2,14,1,15}; -/* The lengths of the bit length codes are sent in order of decreasing - * probability, to avoid transmitting the lengths for unused bit length codes. - */ - -/* =========================================================================== - * Local data. These are initialized only once. - */ - -#define DIST_CODE_LEN 512 /* see definition of array dist_code below */ - -#if defined(GEN_TREES_H) || !defined(STDC) -/* non ANSI compilers may not accept trees.h */ - -local ct_data static_ltree[L_CODES+2]; -/* The static literal tree. Since the bit lengths are imposed, there is no - * need for the L_CODES extra codes used during heap construction. However - * The codes 286 and 287 are needed to build a canonical tree (see _tr_init - * below). - */ - -local ct_data static_dtree[D_CODES]; -/* The static distance tree. (Actually a trivial tree since all codes use - * 5 bits.) - */ - -uch _dist_code[DIST_CODE_LEN]; -/* Distance codes. The first 256 values correspond to the distances - * 3 .. 258, the last 256 values correspond to the top 8 bits of - * the 15 bit distances. - */ - -uch _length_code[MAX_MATCH-MIN_MATCH+1]; -/* length code for each normalized match length (0 == MIN_MATCH) */ - -local int base_length[LENGTH_CODES]; -/* First normalized length for each code (0 = MIN_MATCH) */ - -local int base_dist[D_CODES]; -/* First normalized distance for each code (0 = distance of 1) */ - -#else -# include "trees.h" -#endif /* GEN_TREES_H */ - -struct static_tree_desc_s { - const ct_data *static_tree; /* static tree or NULL */ - const intf *extra_bits; /* extra bits for each code or NULL */ - int extra_base; /* base index for extra_bits */ - int elems; /* max number of elements in the tree */ - int max_length; /* max bit length for the codes */ -}; - -local const static_tree_desc static_l_desc = -{static_ltree, extra_lbits, LITERALS+1, L_CODES, MAX_BITS}; - -local const static_tree_desc static_d_desc = -{static_dtree, extra_dbits, 0, D_CODES, MAX_BITS}; - -local const static_tree_desc static_bl_desc = -{(const ct_data *)0, extra_blbits, 0, BL_CODES, MAX_BL_BITS}; - -/* =========================================================================== - * Local (static) routines in this file. - */ - -local void tr_static_init OF((void)); -local void init_block OF((deflate_state *s)); -local void pqdownheap OF((deflate_state *s, ct_data *tree, int k)); -local void gen_bitlen OF((deflate_state *s, tree_desc *desc)); -local void gen_codes OF((ct_data *tree, int max_code, ushf *bl_count)); -local void build_tree OF((deflate_state *s, tree_desc *desc)); -local void scan_tree OF((deflate_state *s, ct_data *tree, int max_code)); -local void send_tree OF((deflate_state *s, ct_data *tree, int max_code)); -local int build_bl_tree OF((deflate_state *s)); -local void send_all_trees OF((deflate_state *s, int lcodes, int dcodes, - int blcodes)); -local void compress_block OF((deflate_state *s, const ct_data *ltree, - const ct_data *dtree)); -local int detect_data_type OF((deflate_state *s)); -local unsigned bi_reverse OF((unsigned value, int length)); -local void bi_windup OF((deflate_state *s)); -local void bi_flush OF((deflate_state *s)); - -#ifdef GEN_TREES_H -local void gen_trees_header OF((void)); -#endif - -#ifndef ZLIB_DEBUG -# define send_code(s, c, tree) send_bits(s, tree[c].Code, tree[c].Len) - /* Send a code of the given tree. c and tree must not have side effects */ - -#else /* !ZLIB_DEBUG */ -# define send_code(s, c, tree) \ - { if (z_verbose>2) fprintf(stderr,"\ncd %3d ",(c)); \ - send_bits(s, tree[c].Code, tree[c].Len); } -#endif - -/* =========================================================================== - * Output a short LSB first on the stream. - * IN assertion: there is enough room in pendingBuf. - */ -#define put_short(s, w) { \ - put_byte(s, (uch)((w) & 0xff)); \ - put_byte(s, (uch)((ush)(w) >> 8)); \ -} - -/* =========================================================================== - * Send a value on a given number of bits. - * IN assertion: length <= 16 and value fits in length bits. - */ -#ifdef ZLIB_DEBUG -local void send_bits OF((deflate_state *s, int value, int length)); - -local void send_bits(s, value, length) - deflate_state *s; - int value; /* value to send */ - int length; /* number of bits */ -{ - Tracevv((stderr," l %2d v %4x ", length, value)); - Assert(length > 0 && length <= 15, "invalid length"); - s->bits_sent += (ulg)length; - - /* If not enough room in bi_buf, use (valid) bits from bi_buf and - * (16 - bi_valid) bits from value, leaving (width - (16-bi_valid)) - * unused bits in value. - */ - if (s->bi_valid > (int)Buf_size - length) { - s->bi_buf |= (ush)value << s->bi_valid; - put_short(s, s->bi_buf); - s->bi_buf = (ush)value >> (Buf_size - s->bi_valid); - s->bi_valid += length - Buf_size; - } else { - s->bi_buf |= (ush)value << s->bi_valid; - s->bi_valid += length; - } -} -#else /* !ZLIB_DEBUG */ - -#define send_bits(s, value, length) \ -{ int len = length;\ - if (s->bi_valid > (int)Buf_size - len) {\ - int val = (int)value;\ - s->bi_buf |= (ush)val << s->bi_valid;\ - put_short(s, s->bi_buf);\ - s->bi_buf = (ush)val >> (Buf_size - s->bi_valid);\ - s->bi_valid += len - Buf_size;\ - } else {\ - s->bi_buf |= (ush)(value) << s->bi_valid;\ - s->bi_valid += len;\ - }\ -} -#endif /* ZLIB_DEBUG */ - - -/* the arguments must not have side effects */ - -/* =========================================================================== - * Initialize the various 'constant' tables. - */ -local void tr_static_init() -{ -#if defined(GEN_TREES_H) || !defined(STDC) - static int static_init_done = 0; - int n; /* iterates over tree elements */ - int bits; /* bit counter */ - int length; /* length value */ - int code; /* code value */ - int dist; /* distance index */ - ush bl_count[MAX_BITS+1]; - /* number of codes at each bit length for an optimal tree */ - - if (static_init_done) return; - - /* For some embedded targets, global variables are not initialized: */ -#ifdef NO_INIT_GLOBAL_POINTERS - static_l_desc.static_tree = static_ltree; - static_l_desc.extra_bits = extra_lbits; - static_d_desc.static_tree = static_dtree; - static_d_desc.extra_bits = extra_dbits; - static_bl_desc.extra_bits = extra_blbits; -#endif - - /* Initialize the mapping length (0..255) -> length code (0..28) */ - length = 0; - for (code = 0; code < LENGTH_CODES-1; code++) { - base_length[code] = length; - for (n = 0; n < (1< dist code (0..29) */ - dist = 0; - for (code = 0 ; code < 16; code++) { - base_dist[code] = dist; - for (n = 0; n < (1<>= 7; /* from now on, all distances are divided by 128 */ - for ( ; code < D_CODES; code++) { - base_dist[code] = dist << 7; - for (n = 0; n < (1<<(extra_dbits[code]-7)); n++) { - _dist_code[256 + dist++] = (uch)code; - } - } - Assert (dist == 256, "tr_static_init: 256+dist != 512"); - - /* Construct the codes of the static literal tree */ - for (bits = 0; bits <= MAX_BITS; bits++) bl_count[bits] = 0; - n = 0; - while (n <= 143) static_ltree[n++].Len = 8, bl_count[8]++; - while (n <= 255) static_ltree[n++].Len = 9, bl_count[9]++; - while (n <= 279) static_ltree[n++].Len = 7, bl_count[7]++; - while (n <= 287) static_ltree[n++].Len = 8, bl_count[8]++; - /* Codes 286 and 287 do not exist, but we must include them in the - * tree construction to get a canonical Huffman tree (longest code - * all ones) - */ - gen_codes((ct_data *)static_ltree, L_CODES+1, bl_count); - - /* The static distance tree is trivial: */ - for (n = 0; n < D_CODES; n++) { - static_dtree[n].Len = 5; - static_dtree[n].Code = bi_reverse((unsigned)n, 5); - } - static_init_done = 1; - -# ifdef GEN_TREES_H - gen_trees_header(); -# endif -#endif /* defined(GEN_TREES_H) || !defined(STDC) */ -} - -/* =========================================================================== - * Genererate the file trees.h describing the static trees. - */ -#ifdef GEN_TREES_H -# ifndef ZLIB_DEBUG -# include -# endif - -# define SEPARATOR(i, last, width) \ - ((i) == (last)? "\n};\n\n" : \ - ((i) % (width) == (width)-1 ? ",\n" : ", ")) - -void gen_trees_header() -{ - FILE *header = fopen("trees.h", "w"); - int i; - - Assert (header != NULL, "Can't open trees.h"); - fprintf(header, - "/* header created automatically with -DGEN_TREES_H */\n\n"); - - fprintf(header, "local const ct_data static_ltree[L_CODES+2] = {\n"); - for (i = 0; i < L_CODES+2; i++) { - fprintf(header, "{{%3u},{%3u}}%s", static_ltree[i].Code, - static_ltree[i].Len, SEPARATOR(i, L_CODES+1, 5)); - } - - fprintf(header, "local const ct_data static_dtree[D_CODES] = {\n"); - for (i = 0; i < D_CODES; i++) { - fprintf(header, "{{%2u},{%2u}}%s", static_dtree[i].Code, - static_dtree[i].Len, SEPARATOR(i, D_CODES-1, 5)); - } - - fprintf(header, "const uch ZLIB_INTERNAL _dist_code[DIST_CODE_LEN] = {\n"); - for (i = 0; i < DIST_CODE_LEN; i++) { - fprintf(header, "%2u%s", _dist_code[i], - SEPARATOR(i, DIST_CODE_LEN-1, 20)); - } - - fprintf(header, - "const uch ZLIB_INTERNAL _length_code[MAX_MATCH-MIN_MATCH+1]= {\n"); - for (i = 0; i < MAX_MATCH-MIN_MATCH+1; i++) { - fprintf(header, "%2u%s", _length_code[i], - SEPARATOR(i, MAX_MATCH-MIN_MATCH, 20)); - } - - fprintf(header, "local const int base_length[LENGTH_CODES] = {\n"); - for (i = 0; i < LENGTH_CODES; i++) { - fprintf(header, "%1u%s", base_length[i], - SEPARATOR(i, LENGTH_CODES-1, 20)); - } - - fprintf(header, "local const int base_dist[D_CODES] = {\n"); - for (i = 0; i < D_CODES; i++) { - fprintf(header, "%5u%s", base_dist[i], - SEPARATOR(i, D_CODES-1, 10)); - } - - fclose(header); -} -#endif /* GEN_TREES_H */ - -/* =========================================================================== - * Initialize the tree data structures for a new zlib stream. - */ -void ZLIB_INTERNAL _tr_init(s) - deflate_state *s; -{ - tr_static_init(); - - s->l_desc.dyn_tree = s->dyn_ltree; - s->l_desc.stat_desc = &static_l_desc; - - s->d_desc.dyn_tree = s->dyn_dtree; - s->d_desc.stat_desc = &static_d_desc; - - s->bl_desc.dyn_tree = s->bl_tree; - s->bl_desc.stat_desc = &static_bl_desc; - - s->bi_buf = 0; - s->bi_valid = 0; -#ifdef ZLIB_DEBUG - s->compressed_len = 0L; - s->bits_sent = 0L; -#endif - - /* Initialize the first block of the first file: */ - init_block(s); -} - -/* =========================================================================== - * Initialize a new block. - */ -local void init_block(s) - deflate_state *s; -{ - int n; /* iterates over tree elements */ - - /* Initialize the trees. */ - for (n = 0; n < L_CODES; n++) s->dyn_ltree[n].Freq = 0; - for (n = 0; n < D_CODES; n++) s->dyn_dtree[n].Freq = 0; - for (n = 0; n < BL_CODES; n++) s->bl_tree[n].Freq = 0; - - s->dyn_ltree[END_BLOCK].Freq = 1; - s->opt_len = s->static_len = 0L; - s->last_lit = s->matches = 0; -} - -#define SMALLEST 1 -/* Index within the heap array of least frequent node in the Huffman tree */ - - -/* =========================================================================== - * Remove the smallest element from the heap and recreate the heap with - * one less element. Updates heap and heap_len. - */ -#define pqremove(s, tree, top) \ -{\ - top = s->heap[SMALLEST]; \ - s->heap[SMALLEST] = s->heap[s->heap_len--]; \ - pqdownheap(s, tree, SMALLEST); \ -} - -/* =========================================================================== - * Compares to subtrees, using the tree depth as tie breaker when - * the subtrees have equal frequency. This minimizes the worst case length. - */ -#define smaller(tree, n, m, depth) \ - (tree[n].Freq < tree[m].Freq || \ - (tree[n].Freq == tree[m].Freq && depth[n] <= depth[m])) - -/* =========================================================================== - * Restore the heap property by moving down the tree starting at node k, - * exchanging a node with the smallest of its two sons if necessary, stopping - * when the heap property is re-established (each father smaller than its - * two sons). - */ -local void pqdownheap(s, tree, k) - deflate_state *s; - ct_data *tree; /* the tree to restore */ - int k; /* node to move down */ -{ - int v = s->heap[k]; - int j = k << 1; /* left son of k */ - while (j <= s->heap_len) { - /* Set j to the smallest of the two sons: */ - if (j < s->heap_len && - smaller(tree, s->heap[j+1], s->heap[j], s->depth)) { - j++; - } - /* Exit if v is smaller than both sons */ - if (smaller(tree, v, s->heap[j], s->depth)) break; - - /* Exchange v with the smallest son */ - s->heap[k] = s->heap[j]; k = j; - - /* And continue down the tree, setting j to the left son of k */ - j <<= 1; - } - s->heap[k] = v; -} - -/* =========================================================================== - * Compute the optimal bit lengths for a tree and update the total bit length - * for the current block. - * IN assertion: the fields freq and dad are set, heap[heap_max] and - * above are the tree nodes sorted by increasing frequency. - * OUT assertions: the field len is set to the optimal bit length, the - * array bl_count contains the frequencies for each bit length. - * The length opt_len is updated; static_len is also updated if stree is - * not null. - */ -local void gen_bitlen(s, desc) - deflate_state *s; - tree_desc *desc; /* the tree descriptor */ -{ - ct_data *tree = desc->dyn_tree; - int max_code = desc->max_code; - const ct_data *stree = desc->stat_desc->static_tree; - const intf *extra = desc->stat_desc->extra_bits; - int base = desc->stat_desc->extra_base; - int max_length = desc->stat_desc->max_length; - int h; /* heap index */ - int n, m; /* iterate over the tree elements */ - int bits; /* bit length */ - int xbits; /* extra bits */ - ush f; /* frequency */ - int overflow = 0; /* number of elements with bit length too large */ - - for (bits = 0; bits <= MAX_BITS; bits++) s->bl_count[bits] = 0; - - /* In a first pass, compute the optimal bit lengths (which may - * overflow in the case of the bit length tree). - */ - tree[s->heap[s->heap_max]].Len = 0; /* root of the heap */ - - for (h = s->heap_max+1; h < HEAP_SIZE; h++) { - n = s->heap[h]; - bits = tree[tree[n].Dad].Len + 1; - if (bits > max_length) bits = max_length, overflow++; - tree[n].Len = (ush)bits; - /* We overwrite tree[n].Dad which is no longer needed */ - - if (n > max_code) continue; /* not a leaf node */ - - s->bl_count[bits]++; - xbits = 0; - if (n >= base) xbits = extra[n-base]; - f = tree[n].Freq; - s->opt_len += (ulg)f * (unsigned)(bits + xbits); - if (stree) s->static_len += (ulg)f * (unsigned)(stree[n].Len + xbits); - } - if (overflow == 0) return; - - Tracev((stderr,"\nbit length overflow\n")); - /* This happens for example on obj2 and pic of the Calgary corpus */ - - /* Find the first bit length which could increase: */ - do { - bits = max_length-1; - while (s->bl_count[bits] == 0) bits--; - s->bl_count[bits]--; /* move one leaf down the tree */ - s->bl_count[bits+1] += 2; /* move one overflow item as its brother */ - s->bl_count[max_length]--; - /* The brother of the overflow item also moves one step up, - * but this does not affect bl_count[max_length] - */ - overflow -= 2; - } while (overflow > 0); - - /* Now recompute all bit lengths, scanning in increasing frequency. - * h is still equal to HEAP_SIZE. (It is simpler to reconstruct all - * lengths instead of fixing only the wrong ones. This idea is taken - * from 'ar' written by Haruhiko Okumura.) - */ - for (bits = max_length; bits != 0; bits--) { - n = s->bl_count[bits]; - while (n != 0) { - m = s->heap[--h]; - if (m > max_code) continue; - if ((unsigned) tree[m].Len != (unsigned) bits) { - Tracev((stderr,"code %d bits %d->%d\n", m, tree[m].Len, bits)); - s->opt_len += ((ulg)bits - tree[m].Len) * tree[m].Freq; - tree[m].Len = (ush)bits; - } - n--; - } - } -} - -/* =========================================================================== - * Generate the codes for a given tree and bit counts (which need not be - * optimal). - * IN assertion: the array bl_count contains the bit length statistics for - * the given tree and the field len is set for all tree elements. - * OUT assertion: the field code is set for all tree elements of non - * zero code length. - */ -local void gen_codes (tree, max_code, bl_count) - ct_data *tree; /* the tree to decorate */ - int max_code; /* largest code with non zero frequency */ - ushf *bl_count; /* number of codes at each bit length */ -{ - ush next_code[MAX_BITS+1]; /* next code value for each bit length */ - unsigned code = 0; /* running code value */ - int bits; /* bit index */ - int n; /* code index */ - - /* The distribution counts are first used to generate the code values - * without bit reversal. - */ - for (bits = 1; bits <= MAX_BITS; bits++) { - code = (code + bl_count[bits-1]) << 1; - next_code[bits] = (ush)code; - } - /* Check that the bit counts in bl_count are consistent. The last code - * must be all ones. - */ - Assert (code + bl_count[MAX_BITS]-1 == (1<dyn_tree; - const ct_data *stree = desc->stat_desc->static_tree; - int elems = desc->stat_desc->elems; - int n, m; /* iterate over heap elements */ - int max_code = -1; /* largest code with non zero frequency */ - int node; /* new node being created */ - - /* Construct the initial heap, with least frequent element in - * heap[SMALLEST]. The sons of heap[n] are heap[2*n] and heap[2*n+1]. - * heap[0] is not used. - */ - s->heap_len = 0, s->heap_max = HEAP_SIZE; - - for (n = 0; n < elems; n++) { - if (tree[n].Freq != 0) { - s->heap[++(s->heap_len)] = max_code = n; - s->depth[n] = 0; - } else { - tree[n].Len = 0; - } - } - - /* The pkzip format requires that at least one distance code exists, - * and that at least one bit should be sent even if there is only one - * possible code. So to avoid special checks later on we force at least - * two codes of non zero frequency. - */ - while (s->heap_len < 2) { - node = s->heap[++(s->heap_len)] = (max_code < 2 ? ++max_code : 0); - tree[node].Freq = 1; - s->depth[node] = 0; - s->opt_len--; if (stree) s->static_len -= stree[node].Len; - /* node is 0 or 1 so it does not have extra bits */ - } - desc->max_code = max_code; - - /* The elements heap[heap_len/2+1 .. heap_len] are leaves of the tree, - * establish sub-heaps of increasing lengths: - */ - for (n = s->heap_len/2; n >= 1; n--) pqdownheap(s, tree, n); - - /* Construct the Huffman tree by repeatedly combining the least two - * frequent nodes. - */ - node = elems; /* next internal node of the tree */ - do { - pqremove(s, tree, n); /* n = node of least frequency */ - m = s->heap[SMALLEST]; /* m = node of next least frequency */ - - s->heap[--(s->heap_max)] = n; /* keep the nodes sorted by frequency */ - s->heap[--(s->heap_max)] = m; - - /* Create a new node father of n and m */ - tree[node].Freq = tree[n].Freq + tree[m].Freq; - s->depth[node] = (uch)((s->depth[n] >= s->depth[m] ? - s->depth[n] : s->depth[m]) + 1); - tree[n].Dad = tree[m].Dad = (ush)node; -#ifdef DUMP_BL_TREE - if (tree == s->bl_tree) { - fprintf(stderr,"\nnode %d(%d), sons %d(%d) %d(%d)", - node, tree[node].Freq, n, tree[n].Freq, m, tree[m].Freq); - } -#endif - /* and insert the new node in the heap */ - s->heap[SMALLEST] = node++; - pqdownheap(s, tree, SMALLEST); - - } while (s->heap_len >= 2); - - s->heap[--(s->heap_max)] = s->heap[SMALLEST]; - - /* At this point, the fields freq and dad are set. We can now - * generate the bit lengths. - */ - gen_bitlen(s, (tree_desc *)desc); - - /* The field len is now set, we can generate the bit codes */ - gen_codes ((ct_data *)tree, max_code, s->bl_count); -} - -/* =========================================================================== - * Scan a literal or distance tree to determine the frequencies of the codes - * in the bit length tree. - */ -local void scan_tree (s, tree, max_code) - deflate_state *s; - ct_data *tree; /* the tree to be scanned */ - int max_code; /* and its largest code of non zero frequency */ -{ - int n; /* iterates over all tree elements */ - int prevlen = -1; /* last emitted length */ - int curlen; /* length of current code */ - int nextlen = tree[0].Len; /* length of next code */ - int count = 0; /* repeat count of the current code */ - int max_count = 7; /* max repeat count */ - int min_count = 4; /* min repeat count */ - - if (nextlen == 0) max_count = 138, min_count = 3; - tree[max_code+1].Len = (ush)0xffff; /* guard */ - - for (n = 0; n <= max_code; n++) { - curlen = nextlen; nextlen = tree[n+1].Len; - if (++count < max_count && curlen == nextlen) { - continue; - } else if (count < min_count) { - s->bl_tree[curlen].Freq += count; - } else if (curlen != 0) { - if (curlen != prevlen) s->bl_tree[curlen].Freq++; - s->bl_tree[REP_3_6].Freq++; - } else if (count <= 10) { - s->bl_tree[REPZ_3_10].Freq++; - } else { - s->bl_tree[REPZ_11_138].Freq++; - } - count = 0; prevlen = curlen; - if (nextlen == 0) { - max_count = 138, min_count = 3; - } else if (curlen == nextlen) { - max_count = 6, min_count = 3; - } else { - max_count = 7, min_count = 4; - } - } -} - -/* =========================================================================== - * Send a literal or distance tree in compressed form, using the codes in - * bl_tree. - */ -local void send_tree (s, tree, max_code) - deflate_state *s; - ct_data *tree; /* the tree to be scanned */ - int max_code; /* and its largest code of non zero frequency */ -{ - int n; /* iterates over all tree elements */ - int prevlen = -1; /* last emitted length */ - int curlen; /* length of current code */ - int nextlen = tree[0].Len; /* length of next code */ - int count = 0; /* repeat count of the current code */ - int max_count = 7; /* max repeat count */ - int min_count = 4; /* min repeat count */ - - /* tree[max_code+1].Len = -1; */ /* guard already set */ - if (nextlen == 0) max_count = 138, min_count = 3; - - for (n = 0; n <= max_code; n++) { - curlen = nextlen; nextlen = tree[n+1].Len; - if (++count < max_count && curlen == nextlen) { - continue; - } else if (count < min_count) { - do { send_code(s, curlen, s->bl_tree); } while (--count != 0); - - } else if (curlen != 0) { - if (curlen != prevlen) { - send_code(s, curlen, s->bl_tree); count--; - } - Assert(count >= 3 && count <= 6, " 3_6?"); - send_code(s, REP_3_6, s->bl_tree); send_bits(s, count-3, 2); - - } else if (count <= 10) { - send_code(s, REPZ_3_10, s->bl_tree); send_bits(s, count-3, 3); - - } else { - send_code(s, REPZ_11_138, s->bl_tree); send_bits(s, count-11, 7); - } - count = 0; prevlen = curlen; - if (nextlen == 0) { - max_count = 138, min_count = 3; - } else if (curlen == nextlen) { - max_count = 6, min_count = 3; - } else { - max_count = 7, min_count = 4; - } - } -} - -/* =========================================================================== - * Construct the Huffman tree for the bit lengths and return the index in - * bl_order of the last bit length code to send. - */ -local int build_bl_tree(s) - deflate_state *s; -{ - int max_blindex; /* index of last bit length code of non zero freq */ - - /* Determine the bit length frequencies for literal and distance trees */ - scan_tree(s, (ct_data *)s->dyn_ltree, s->l_desc.max_code); - scan_tree(s, (ct_data *)s->dyn_dtree, s->d_desc.max_code); - - /* Build the bit length tree: */ - build_tree(s, (tree_desc *)(&(s->bl_desc))); - /* opt_len now includes the length of the tree representations, except - * the lengths of the bit lengths codes and the 5+5+4 bits for the counts. - */ - - /* Determine the number of bit length codes to send. The pkzip format - * requires that at least 4 bit length codes be sent. (appnote.txt says - * 3 but the actual value used is 4.) - */ - for (max_blindex = BL_CODES-1; max_blindex >= 3; max_blindex--) { - if (s->bl_tree[bl_order[max_blindex]].Len != 0) break; - } - /* Update opt_len to include the bit length tree and counts */ - s->opt_len += 3*((ulg)max_blindex+1) + 5+5+4; - Tracev((stderr, "\ndyn trees: dyn %ld, stat %ld", - s->opt_len, s->static_len)); - - return max_blindex; -} - -/* =========================================================================== - * Send the header for a block using dynamic Huffman trees: the counts, the - * lengths of the bit length codes, the literal tree and the distance tree. - * IN assertion: lcodes >= 257, dcodes >= 1, blcodes >= 4. - */ -local void send_all_trees(s, lcodes, dcodes, blcodes) - deflate_state *s; - int lcodes, dcodes, blcodes; /* number of codes for each tree */ -{ - int rank; /* index in bl_order */ - - Assert (lcodes >= 257 && dcodes >= 1 && blcodes >= 4, "not enough codes"); - Assert (lcodes <= L_CODES && dcodes <= D_CODES && blcodes <= BL_CODES, - "too many codes"); - Tracev((stderr, "\nbl counts: ")); - send_bits(s, lcodes-257, 5); /* not +255 as stated in appnote.txt */ - send_bits(s, dcodes-1, 5); - send_bits(s, blcodes-4, 4); /* not -3 as stated in appnote.txt */ - for (rank = 0; rank < blcodes; rank++) { - Tracev((stderr, "\nbl code %2d ", bl_order[rank])); - send_bits(s, s->bl_tree[bl_order[rank]].Len, 3); - } - Tracev((stderr, "\nbl tree: sent %ld", s->bits_sent)); - - send_tree(s, (ct_data *)s->dyn_ltree, lcodes-1); /* literal tree */ - Tracev((stderr, "\nlit tree: sent %ld", s->bits_sent)); - - send_tree(s, (ct_data *)s->dyn_dtree, dcodes-1); /* distance tree */ - Tracev((stderr, "\ndist tree: sent %ld", s->bits_sent)); -} - -/* =========================================================================== - * Send a stored block - */ -void ZLIB_INTERNAL _tr_stored_block(s, buf, stored_len, last) - deflate_state *s; - charf *buf; /* input block */ - ulg stored_len; /* length of input block */ - int last; /* one if this is the last block for a file */ -{ - send_bits(s, (STORED_BLOCK<<1)+last, 3); /* send block type */ - bi_windup(s); /* align on byte boundary */ - put_short(s, (ush)stored_len); - put_short(s, (ush)~stored_len); - zmemcpy(s->pending_buf + s->pending, (Bytef *)buf, stored_len); - s->pending += stored_len; -#ifdef ZLIB_DEBUG - s->compressed_len = (s->compressed_len + 3 + 7) & (ulg)~7L; - s->compressed_len += (stored_len + 4) << 3; - s->bits_sent += 2*16; - s->bits_sent += stored_len<<3; -#endif -} - -/* =========================================================================== - * Flush the bits in the bit buffer to pending output (leaves at most 7 bits) - */ -void ZLIB_INTERNAL _tr_flush_bits(s) - deflate_state *s; -{ - bi_flush(s); -} - -/* =========================================================================== - * Send one empty static block to give enough lookahead for inflate. - * This takes 10 bits, of which 7 may remain in the bit buffer. - */ -void ZLIB_INTERNAL _tr_align(s) - deflate_state *s; -{ - send_bits(s, STATIC_TREES<<1, 3); - send_code(s, END_BLOCK, static_ltree); -#ifdef ZLIB_DEBUG - s->compressed_len += 10L; /* 3 for block type, 7 for EOB */ -#endif - bi_flush(s); -} - -/* =========================================================================== - * Determine the best encoding for the current block: dynamic trees, static - * trees or store, and write out the encoded block. - */ -void ZLIB_INTERNAL _tr_flush_block(s, buf, stored_len, last) - deflate_state *s; - charf *buf; /* input block, or NULL if too old */ - ulg stored_len; /* length of input block */ - int last; /* one if this is the last block for a file */ -{ - ulg opt_lenb, static_lenb; /* opt_len and static_len in bytes */ - int max_blindex = 0; /* index of last bit length code of non zero freq */ - - /* Build the Huffman trees unless a stored block is forced */ - if (s->level > 0) { - - /* Check if the file is binary or text */ - if (s->strm->data_type == Z_UNKNOWN) - s->strm->data_type = detect_data_type(s); - - /* Construct the literal and distance trees */ - build_tree(s, (tree_desc *)(&(s->l_desc))); - Tracev((stderr, "\nlit data: dyn %ld, stat %ld", s->opt_len, - s->static_len)); - - build_tree(s, (tree_desc *)(&(s->d_desc))); - Tracev((stderr, "\ndist data: dyn %ld, stat %ld", s->opt_len, - s->static_len)); - /* At this point, opt_len and static_len are the total bit lengths of - * the compressed block data, excluding the tree representations. - */ - - /* Build the bit length tree for the above two trees, and get the index - * in bl_order of the last bit length code to send. - */ - max_blindex = build_bl_tree(s); - - /* Determine the best encoding. Compute the block lengths in bytes. */ - opt_lenb = (s->opt_len+3+7)>>3; - static_lenb = (s->static_len+3+7)>>3; - - Tracev((stderr, "\nopt %lu(%lu) stat %lu(%lu) stored %lu lit %u ", - opt_lenb, s->opt_len, static_lenb, s->static_len, stored_len, - s->last_lit)); - - if (static_lenb <= opt_lenb) opt_lenb = static_lenb; - - } else { - Assert(buf != (char*)0, "lost buf"); - opt_lenb = static_lenb = stored_len + 5; /* force a stored block */ - } - -#ifdef FORCE_STORED - if (buf != (char*)0) { /* force stored block */ -#else - if (stored_len+4 <= opt_lenb && buf != (char*)0) { - /* 4: two words for the lengths */ -#endif - /* The test buf != NULL is only necessary if LIT_BUFSIZE > WSIZE. - * Otherwise we can't have processed more than WSIZE input bytes since - * the last block flush, because compression would have been - * successful. If LIT_BUFSIZE <= WSIZE, it is never too late to - * transform a block into a stored block. - */ - _tr_stored_block(s, buf, stored_len, last); - -#ifdef FORCE_STATIC - } else if (static_lenb >= 0) { /* force static trees */ -#else - } else if (s->strategy == Z_FIXED || static_lenb == opt_lenb) { -#endif - send_bits(s, (STATIC_TREES<<1)+last, 3); - compress_block(s, (const ct_data *)static_ltree, - (const ct_data *)static_dtree); -#ifdef ZLIB_DEBUG - s->compressed_len += 3 + s->static_len; -#endif - } else { - send_bits(s, (DYN_TREES<<1)+last, 3); - send_all_trees(s, s->l_desc.max_code+1, s->d_desc.max_code+1, - max_blindex+1); - compress_block(s, (const ct_data *)s->dyn_ltree, - (const ct_data *)s->dyn_dtree); -#ifdef ZLIB_DEBUG - s->compressed_len += 3 + s->opt_len; -#endif - } - Assert (s->compressed_len == s->bits_sent, "bad compressed size"); - /* The above check is made mod 2^32, for files larger than 512 MB - * and uLong implemented on 32 bits. - */ - init_block(s); - - if (last) { - bi_windup(s); -#ifdef ZLIB_DEBUG - s->compressed_len += 7; /* align on byte boundary */ -#endif - } - Tracev((stderr,"\ncomprlen %lu(%lu) ", s->compressed_len>>3, - s->compressed_len-7*last)); -} - -/* =========================================================================== - * Save the match info and tally the frequency counts. Return true if - * the current block must be flushed. - */ -int ZLIB_INTERNAL _tr_tally (s, dist, lc) - deflate_state *s; - unsigned dist; /* distance of matched string */ - unsigned lc; /* match length-MIN_MATCH or unmatched char (if dist==0) */ -{ - s->d_buf[s->last_lit] = (ush)dist; - s->l_buf[s->last_lit++] = (uch)lc; - if (dist == 0) { - /* lc is the unmatched char */ - s->dyn_ltree[lc].Freq++; - } else { - s->matches++; - /* Here, lc is the match length - MIN_MATCH */ - dist--; /* dist = match distance - 1 */ - Assert((ush)dist < (ush)MAX_DIST(s) && - (ush)lc <= (ush)(MAX_MATCH-MIN_MATCH) && - (ush)d_code(dist) < (ush)D_CODES, "_tr_tally: bad match"); - - s->dyn_ltree[_length_code[lc]+LITERALS+1].Freq++; - s->dyn_dtree[d_code(dist)].Freq++; - } - -#ifdef TRUNCATE_BLOCK - /* Try to guess if it is profitable to stop the current block here */ - if ((s->last_lit & 0x1fff) == 0 && s->level > 2) { - /* Compute an upper bound for the compressed length */ - ulg out_length = (ulg)s->last_lit*8L; - ulg in_length = (ulg)((long)s->strstart - s->block_start); - int dcode; - for (dcode = 0; dcode < D_CODES; dcode++) { - out_length += (ulg)s->dyn_dtree[dcode].Freq * - (5L+extra_dbits[dcode]); - } - out_length >>= 3; - Tracev((stderr,"\nlast_lit %u, in %ld, out ~%ld(%ld%%) ", - s->last_lit, in_length, out_length, - 100L - out_length*100L/in_length)); - if (s->matches < s->last_lit/2 && out_length < in_length/2) return 1; - } -#endif - return (s->last_lit == s->lit_bufsize-1); - /* We avoid equality with lit_bufsize because of wraparound at 64K - * on 16 bit machines and because stored blocks are restricted to - * 64K-1 bytes. - */ -} - -/* =========================================================================== - * Send the block data compressed using the given Huffman trees - */ -local void compress_block(s, ltree, dtree) - deflate_state *s; - const ct_data *ltree; /* literal tree */ - const ct_data *dtree; /* distance tree */ -{ - unsigned dist; /* distance of matched string */ - int lc; /* match length or unmatched char (if dist == 0) */ - unsigned lx = 0; /* running index in l_buf */ - unsigned code; /* the code to send */ - int extra; /* number of extra bits to send */ - - if (s->last_lit != 0) do { - dist = s->d_buf[lx]; - lc = s->l_buf[lx++]; - if (dist == 0) { - send_code(s, lc, ltree); /* send a literal byte */ - Tracecv(isgraph(lc), (stderr," '%c' ", lc)); - } else { - /* Here, lc is the match length - MIN_MATCH */ - code = _length_code[lc]; - send_code(s, code+LITERALS+1, ltree); /* send the length code */ - extra = extra_lbits[code]; - if (extra != 0) { - lc -= base_length[code]; - send_bits(s, lc, extra); /* send the extra length bits */ - } - dist--; /* dist is now the match distance - 1 */ - code = d_code(dist); - Assert (code < D_CODES, "bad d_code"); - - send_code(s, code, dtree); /* send the distance code */ - extra = extra_dbits[code]; - if (extra != 0) { - dist -= (unsigned)base_dist[code]; - send_bits(s, dist, extra); /* send the extra distance bits */ - } - } /* literal or match pair ? */ - - /* Check that the overlay between pending_buf and d_buf+l_buf is ok: */ - Assert((uInt)(s->pending) < s->lit_bufsize + 2*lx, - "pendingBuf overflow"); - - } while (lx < s->last_lit); - - send_code(s, END_BLOCK, ltree); -} - -/* =========================================================================== - * Check if the data type is TEXT or BINARY, using the following algorithm: - * - TEXT if the two conditions below are satisfied: - * a) There are no non-portable control characters belonging to the - * "black list" (0..6, 14..25, 28..31). - * b) There is at least one printable character belonging to the - * "white list" (9 {TAB}, 10 {LF}, 13 {CR}, 32..255). - * - BINARY otherwise. - * - The following partially-portable control characters form a - * "gray list" that is ignored in this detection algorithm: - * (7 {BEL}, 8 {BS}, 11 {VT}, 12 {FF}, 26 {SUB}, 27 {ESC}). - * IN assertion: the fields Freq of dyn_ltree are set. - */ -local int detect_data_type(s) - deflate_state *s; -{ - /* black_mask is the bit mask of black-listed bytes - * set bits 0..6, 14..25, and 28..31 - * 0xf3ffc07f = binary 11110011111111111100000001111111 - */ - unsigned long black_mask = 0xf3ffc07fUL; - int n; - - /* Check for non-textual ("black-listed") bytes. */ - for (n = 0; n <= 31; n++, black_mask >>= 1) - if ((black_mask & 1) && (s->dyn_ltree[n].Freq != 0)) - return Z_BINARY; - - /* Check for textual ("white-listed") bytes. */ - if (s->dyn_ltree[9].Freq != 0 || s->dyn_ltree[10].Freq != 0 - || s->dyn_ltree[13].Freq != 0) - return Z_TEXT; - for (n = 32; n < LITERALS; n++) - if (s->dyn_ltree[n].Freq != 0) - return Z_TEXT; - - /* There are no "black-listed" or "white-listed" bytes: - * this stream either is empty or has tolerated ("gray-listed") bytes only. - */ - return Z_BINARY; -} - -/* =========================================================================== - * Reverse the first len bits of a code, using straightforward code (a faster - * method would use a table) - * IN assertion: 1 <= len <= 15 - */ -local unsigned bi_reverse(code, len) - unsigned code; /* the value to invert */ - int len; /* its bit length */ -{ - register unsigned res = 0; - do { - res |= code & 1; - code >>= 1, res <<= 1; - } while (--len > 0); - return res >> 1; -} - -/* =========================================================================== - * Flush the bit buffer, keeping at most 7 bits in it. - */ -local void bi_flush(s) - deflate_state *s; -{ - if (s->bi_valid == 16) { - put_short(s, s->bi_buf); - s->bi_buf = 0; - s->bi_valid = 0; - } else if (s->bi_valid >= 8) { - put_byte(s, (Byte)s->bi_buf); - s->bi_buf >>= 8; - s->bi_valid -= 8; - } -} - -/* =========================================================================== - * Flush the bit buffer and align the output on a byte boundary - */ -local void bi_windup(s) - deflate_state *s; -{ - if (s->bi_valid > 8) { - put_short(s, s->bi_buf); - } else if (s->bi_valid > 0) { - put_byte(s, (Byte)s->bi_buf); - } - s->bi_buf = 0; - s->bi_valid = 0; -#ifdef ZLIB_DEBUG - s->bits_sent = (s->bits_sent+7) & ~7; -#endif -} diff --git a/deps/zlib/trees.h b/deps/zlib/trees.h deleted file mode 100644 index d35639d..0000000 --- a/deps/zlib/trees.h +++ /dev/null @@ -1,128 +0,0 @@ -/* header created automatically with -DGEN_TREES_H */ - -local const ct_data static_ltree[L_CODES+2] = { -{{ 12},{ 8}}, {{140},{ 8}}, {{ 76},{ 8}}, {{204},{ 8}}, {{ 44},{ 8}}, -{{172},{ 8}}, {{108},{ 8}}, {{236},{ 8}}, {{ 28},{ 8}}, {{156},{ 8}}, -{{ 92},{ 8}}, {{220},{ 8}}, {{ 60},{ 8}}, {{188},{ 8}}, {{124},{ 8}}, -{{252},{ 8}}, {{ 2},{ 8}}, {{130},{ 8}}, {{ 66},{ 8}}, {{194},{ 8}}, -{{ 34},{ 8}}, {{162},{ 8}}, {{ 98},{ 8}}, {{226},{ 8}}, {{ 18},{ 8}}, -{{146},{ 8}}, {{ 82},{ 8}}, {{210},{ 8}}, {{ 50},{ 8}}, {{178},{ 8}}, -{{114},{ 8}}, {{242},{ 8}}, {{ 10},{ 8}}, {{138},{ 8}}, {{ 74},{ 8}}, -{{202},{ 8}}, {{ 42},{ 8}}, {{170},{ 8}}, {{106},{ 8}}, {{234},{ 8}}, -{{ 26},{ 8}}, {{154},{ 8}}, {{ 90},{ 8}}, {{218},{ 8}}, {{ 58},{ 8}}, -{{186},{ 8}}, {{122},{ 8}}, {{250},{ 8}}, {{ 6},{ 8}}, {{134},{ 8}}, -{{ 70},{ 8}}, {{198},{ 8}}, {{ 38},{ 8}}, {{166},{ 8}}, {{102},{ 8}}, -{{230},{ 8}}, {{ 22},{ 8}}, {{150},{ 8}}, {{ 86},{ 8}}, {{214},{ 8}}, -{{ 54},{ 8}}, {{182},{ 8}}, {{118},{ 8}}, {{246},{ 8}}, {{ 14},{ 8}}, -{{142},{ 8}}, {{ 78},{ 8}}, {{206},{ 8}}, {{ 46},{ 8}}, {{174},{ 8}}, -{{110},{ 8}}, {{238},{ 8}}, {{ 30},{ 8}}, {{158},{ 8}}, {{ 94},{ 8}}, -{{222},{ 8}}, {{ 62},{ 8}}, {{190},{ 8}}, {{126},{ 8}}, {{254},{ 8}}, -{{ 1},{ 8}}, {{129},{ 8}}, {{ 65},{ 8}}, {{193},{ 8}}, {{ 33},{ 8}}, -{{161},{ 8}}, {{ 97},{ 8}}, {{225},{ 8}}, {{ 17},{ 8}}, {{145},{ 8}}, -{{ 81},{ 8}}, {{209},{ 8}}, {{ 49},{ 8}}, {{177},{ 8}}, {{113},{ 8}}, -{{241},{ 8}}, {{ 9},{ 8}}, {{137},{ 8}}, {{ 73},{ 8}}, {{201},{ 8}}, -{{ 41},{ 8}}, {{169},{ 8}}, {{105},{ 8}}, {{233},{ 8}}, {{ 25},{ 8}}, -{{153},{ 8}}, {{ 89},{ 8}}, {{217},{ 8}}, {{ 57},{ 8}}, {{185},{ 8}}, -{{121},{ 8}}, {{249},{ 8}}, {{ 5},{ 8}}, {{133},{ 8}}, {{ 69},{ 8}}, -{{197},{ 8}}, {{ 37},{ 8}}, {{165},{ 8}}, {{101},{ 8}}, {{229},{ 8}}, -{{ 21},{ 8}}, {{149},{ 8}}, {{ 85},{ 8}}, {{213},{ 8}}, {{ 53},{ 8}}, -{{181},{ 8}}, {{117},{ 8}}, {{245},{ 8}}, {{ 13},{ 8}}, {{141},{ 8}}, -{{ 77},{ 8}}, {{205},{ 8}}, {{ 45},{ 8}}, {{173},{ 8}}, {{109},{ 8}}, -{{237},{ 8}}, {{ 29},{ 8}}, {{157},{ 8}}, {{ 93},{ 8}}, {{221},{ 8}}, -{{ 61},{ 8}}, {{189},{ 8}}, {{125},{ 8}}, {{253},{ 8}}, {{ 19},{ 9}}, -{{275},{ 9}}, {{147},{ 9}}, {{403},{ 9}}, {{ 83},{ 9}}, {{339},{ 9}}, -{{211},{ 9}}, {{467},{ 9}}, {{ 51},{ 9}}, {{307},{ 9}}, {{179},{ 9}}, -{{435},{ 9}}, {{115},{ 9}}, {{371},{ 9}}, {{243},{ 9}}, {{499},{ 9}}, -{{ 11},{ 9}}, {{267},{ 9}}, {{139},{ 9}}, {{395},{ 9}}, {{ 75},{ 9}}, -{{331},{ 9}}, {{203},{ 9}}, {{459},{ 9}}, {{ 43},{ 9}}, {{299},{ 9}}, -{{171},{ 9}}, {{427},{ 9}}, {{107},{ 9}}, {{363},{ 9}}, {{235},{ 9}}, -{{491},{ 9}}, {{ 27},{ 9}}, {{283},{ 9}}, {{155},{ 9}}, {{411},{ 9}}, -{{ 91},{ 9}}, {{347},{ 9}}, {{219},{ 9}}, {{475},{ 9}}, {{ 59},{ 9}}, -{{315},{ 9}}, {{187},{ 9}}, {{443},{ 9}}, {{123},{ 9}}, {{379},{ 9}}, -{{251},{ 9}}, {{507},{ 9}}, {{ 7},{ 9}}, {{263},{ 9}}, {{135},{ 9}}, -{{391},{ 9}}, {{ 71},{ 9}}, {{327},{ 9}}, {{199},{ 9}}, {{455},{ 9}}, -{{ 39},{ 9}}, {{295},{ 9}}, {{167},{ 9}}, {{423},{ 9}}, {{103},{ 9}}, -{{359},{ 9}}, {{231},{ 9}}, {{487},{ 9}}, {{ 23},{ 9}}, {{279},{ 9}}, -{{151},{ 9}}, {{407},{ 9}}, {{ 87},{ 9}}, {{343},{ 9}}, {{215},{ 9}}, -{{471},{ 9}}, {{ 55},{ 9}}, {{311},{ 9}}, {{183},{ 9}}, {{439},{ 9}}, -{{119},{ 9}}, {{375},{ 9}}, {{247},{ 9}}, {{503},{ 9}}, {{ 15},{ 9}}, -{{271},{ 9}}, {{143},{ 9}}, {{399},{ 9}}, {{ 79},{ 9}}, {{335},{ 9}}, -{{207},{ 9}}, {{463},{ 9}}, {{ 47},{ 9}}, {{303},{ 9}}, {{175},{ 9}}, -{{431},{ 9}}, {{111},{ 9}}, {{367},{ 9}}, {{239},{ 9}}, {{495},{ 9}}, -{{ 31},{ 9}}, {{287},{ 9}}, {{159},{ 9}}, {{415},{ 9}}, {{ 95},{ 9}}, -{{351},{ 9}}, {{223},{ 9}}, {{479},{ 9}}, {{ 63},{ 9}}, {{319},{ 9}}, -{{191},{ 9}}, {{447},{ 9}}, {{127},{ 9}}, {{383},{ 9}}, {{255},{ 9}}, -{{511},{ 9}}, {{ 0},{ 7}}, {{ 64},{ 7}}, {{ 32},{ 7}}, {{ 96},{ 7}}, -{{ 16},{ 7}}, {{ 80},{ 7}}, {{ 48},{ 7}}, {{112},{ 7}}, {{ 8},{ 7}}, -{{ 72},{ 7}}, {{ 40},{ 7}}, {{104},{ 7}}, {{ 24},{ 7}}, {{ 88},{ 7}}, -{{ 56},{ 7}}, {{120},{ 7}}, {{ 4},{ 7}}, {{ 68},{ 7}}, {{ 36},{ 7}}, -{{100},{ 7}}, {{ 20},{ 7}}, {{ 84},{ 7}}, {{ 52},{ 7}}, {{116},{ 7}}, -{{ 3},{ 8}}, {{131},{ 8}}, {{ 67},{ 8}}, {{195},{ 8}}, {{ 35},{ 8}}, -{{163},{ 8}}, {{ 99},{ 8}}, {{227},{ 8}} -}; - -local const ct_data static_dtree[D_CODES] = { -{{ 0},{ 5}}, {{16},{ 5}}, {{ 8},{ 5}}, {{24},{ 5}}, {{ 4},{ 5}}, -{{20},{ 5}}, {{12},{ 5}}, {{28},{ 5}}, {{ 2},{ 5}}, {{18},{ 5}}, -{{10},{ 5}}, {{26},{ 5}}, {{ 6},{ 5}}, {{22},{ 5}}, {{14},{ 5}}, -{{30},{ 5}}, {{ 1},{ 5}}, {{17},{ 5}}, {{ 9},{ 5}}, {{25},{ 5}}, -{{ 5},{ 5}}, {{21},{ 5}}, {{13},{ 5}}, {{29},{ 5}}, {{ 3},{ 5}}, -{{19},{ 5}}, {{11},{ 5}}, {{27},{ 5}}, {{ 7},{ 5}}, {{23},{ 5}} -}; - -const uch ZLIB_INTERNAL _dist_code[DIST_CODE_LEN] = { - 0, 1, 2, 3, 4, 4, 5, 5, 6, 6, 6, 6, 7, 7, 7, 7, 8, 8, 8, 8, - 8, 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, -10, 10, 10, 10, 10, 10, 10, 10, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, -11, 11, 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, -12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 13, 13, 13, 13, -13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, -13, 13, 13, 13, 13, 13, 13, 13, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, -14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, -14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, -14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 15, 15, 15, 15, 15, 15, 15, 15, -15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, -15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, -15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 0, 0, 16, 17, -18, 18, 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 22, 22, 22, 22, 22, 22, 22, 22, -23, 23, 23, 23, 23, 23, 23, 23, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, -24, 24, 24, 24, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, -26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, -26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 27, 27, 27, 27, 27, 27, 27, 27, -27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, -27, 27, 27, 27, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, -28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, -28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, 28, -28, 28, 28, 28, 28, 28, 28, 28, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, -29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, -29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, -29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29, 29 -}; - -const uch ZLIB_INTERNAL _length_code[MAX_MATCH-MIN_MATCH+1]= { - 0, 1, 2, 3, 4, 5, 6, 7, 8, 8, 9, 9, 10, 10, 11, 11, 12, 12, 12, 12, -13, 13, 13, 13, 14, 14, 14, 14, 15, 15, 15, 15, 16, 16, 16, 16, 16, 16, 16, 16, -17, 17, 17, 17, 17, 17, 17, 17, 18, 18, 18, 18, 18, 18, 18, 18, 19, 19, 19, 19, -19, 19, 19, 19, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, -21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 22, 22, 22, 22, -22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 22, 23, 23, 23, 23, 23, 23, 23, 23, -23, 23, 23, 23, 23, 23, 23, 23, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, -24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, 24, -25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, -25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 26, 26, 26, 26, 26, 26, 26, 26, -26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, 26, -26, 26, 26, 26, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, -27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 27, 28 -}; - -local const int base_length[LENGTH_CODES] = { -0, 1, 2, 3, 4, 5, 6, 7, 8, 10, 12, 14, 16, 20, 24, 28, 32, 40, 48, 56, -64, 80, 96, 112, 128, 160, 192, 224, 0 -}; - -local const int base_dist[D_CODES] = { - 0, 1, 2, 3, 4, 6, 8, 12, 16, 24, - 32, 48, 64, 96, 128, 192, 256, 384, 512, 768, - 1024, 1536, 2048, 3072, 4096, 6144, 8192, 12288, 16384, 24576 -}; - diff --git a/deps/zlib/zconf.h b/deps/zlib/zconf.h deleted file mode 100644 index 5e1d68a..0000000 --- a/deps/zlib/zconf.h +++ /dev/null @@ -1,534 +0,0 @@ -/* zconf.h -- configuration of the zlib compression library - * Copyright (C) 1995-2016 Jean-loup Gailly, Mark Adler - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -/* @(#) $Id$ */ - -#ifndef ZCONF_H -#define ZCONF_H - -/* - * If you *really* need a unique prefix for all types and library functions, - * compile with -DZ_PREFIX. The "standard" zlib should be compiled without it. - * Even better than compiling with -DZ_PREFIX would be to use configure to set - * this permanently in zconf.h using "./configure --zprefix". - */ -#ifdef Z_PREFIX /* may be set to #if 1 by ./configure */ -# define Z_PREFIX_SET - -/* all linked symbols and init macros */ -# define _dist_code z__dist_code -# define _length_code z__length_code -# define _tr_align z__tr_align -# define _tr_flush_bits z__tr_flush_bits -# define _tr_flush_block z__tr_flush_block -# define _tr_init z__tr_init -# define _tr_stored_block z__tr_stored_block -# define _tr_tally z__tr_tally -# define adler32 z_adler32 -# define adler32_combine z_adler32_combine -# define adler32_combine64 z_adler32_combine64 -# define adler32_z z_adler32_z -# ifndef Z_SOLO -# define compress z_compress -# define compress2 z_compress2 -# define compressBound z_compressBound -# endif -# define crc32 z_crc32 -# define crc32_combine z_crc32_combine -# define crc32_combine64 z_crc32_combine64 -# define crc32_z z_crc32_z -# define deflate z_deflate -# define deflateBound z_deflateBound -# define deflateCopy z_deflateCopy -# define deflateEnd z_deflateEnd -# define deflateGetDictionary z_deflateGetDictionary -# define deflateInit z_deflateInit -# define deflateInit2 z_deflateInit2 -# define deflateInit2_ z_deflateInit2_ -# define deflateInit_ z_deflateInit_ -# define deflateParams z_deflateParams -# define deflatePending z_deflatePending -# define deflatePrime z_deflatePrime -# define deflateReset z_deflateReset -# define deflateResetKeep z_deflateResetKeep -# define deflateSetDictionary z_deflateSetDictionary -# define deflateSetHeader z_deflateSetHeader -# define deflateTune z_deflateTune -# define deflate_copyright z_deflate_copyright -# define get_crc_table z_get_crc_table -# ifndef Z_SOLO -# define gz_error z_gz_error -# define gz_intmax z_gz_intmax -# define gz_strwinerror z_gz_strwinerror -# define gzbuffer z_gzbuffer -# define gzclearerr z_gzclearerr -# define gzclose z_gzclose -# define gzclose_r z_gzclose_r -# define gzclose_w z_gzclose_w -# define gzdirect z_gzdirect -# define gzdopen z_gzdopen -# define gzeof z_gzeof -# define gzerror z_gzerror -# define gzflush z_gzflush -# define gzfread z_gzfread -# define gzfwrite z_gzfwrite -# define gzgetc z_gzgetc -# define gzgetc_ z_gzgetc_ -# define gzgets z_gzgets -# define gzoffset z_gzoffset -# define gzoffset64 z_gzoffset64 -# define gzopen z_gzopen -# define gzopen64 z_gzopen64 -# ifdef _WIN32 -# define gzopen_w z_gzopen_w -# endif -# define gzprintf z_gzprintf -# define gzputc z_gzputc -# define gzputs z_gzputs -# define gzread z_gzread -# define gzrewind z_gzrewind -# define gzseek z_gzseek -# define gzseek64 z_gzseek64 -# define gzsetparams z_gzsetparams -# define gztell z_gztell -# define gztell64 z_gztell64 -# define gzungetc z_gzungetc -# define gzvprintf z_gzvprintf -# define gzwrite z_gzwrite -# endif -# define inflate z_inflate -# define inflateBack z_inflateBack -# define inflateBackEnd z_inflateBackEnd -# define inflateBackInit z_inflateBackInit -# define inflateBackInit_ z_inflateBackInit_ -# define inflateCodesUsed z_inflateCodesUsed -# define inflateCopy z_inflateCopy -# define inflateEnd z_inflateEnd -# define inflateGetDictionary z_inflateGetDictionary -# define inflateGetHeader z_inflateGetHeader -# define inflateInit z_inflateInit -# define inflateInit2 z_inflateInit2 -# define inflateInit2_ z_inflateInit2_ -# define inflateInit_ z_inflateInit_ -# define inflateMark z_inflateMark -# define inflatePrime z_inflatePrime -# define inflateReset z_inflateReset -# define inflateReset2 z_inflateReset2 -# define inflateResetKeep z_inflateResetKeep -# define inflateSetDictionary z_inflateSetDictionary -# define inflateSync z_inflateSync -# define inflateSyncPoint z_inflateSyncPoint -# define inflateUndermine z_inflateUndermine -# define inflateValidate z_inflateValidate -# define inflate_copyright z_inflate_copyright -# define inflate_fast z_inflate_fast -# define inflate_table z_inflate_table -# ifndef Z_SOLO -# define uncompress z_uncompress -# define uncompress2 z_uncompress2 -# endif -# define zError z_zError -# ifndef Z_SOLO -# define zcalloc z_zcalloc -# define zcfree z_zcfree -# endif -# define zlibCompileFlags z_zlibCompileFlags -# define zlibVersion z_zlibVersion - -/* all zlib typedefs in zlib.h and zconf.h */ -# define Byte z_Byte -# define Bytef z_Bytef -# define alloc_func z_alloc_func -# define charf z_charf -# define free_func z_free_func -# ifndef Z_SOLO -# define gzFile z_gzFile -# endif -# define gz_header z_gz_header -# define gz_headerp z_gz_headerp -# define in_func z_in_func -# define intf z_intf -# define out_func z_out_func -# define uInt z_uInt -# define uIntf z_uIntf -# define uLong z_uLong -# define uLongf z_uLongf -# define voidp z_voidp -# define voidpc z_voidpc -# define voidpf z_voidpf - -/* all zlib structs in zlib.h and zconf.h */ -# define gz_header_s z_gz_header_s -# define internal_state z_internal_state - -#endif - -#if defined(__MSDOS__) && !defined(MSDOS) -# define MSDOS -#endif -#if (defined(OS_2) || defined(__OS2__)) && !defined(OS2) -# define OS2 -#endif -#if defined(_WINDOWS) && !defined(WINDOWS) -# define WINDOWS -#endif -#if defined(_WIN32) || defined(_WIN32_WCE) || defined(__WIN32__) -# ifndef WIN32 -# define WIN32 -# endif -#endif -#if (defined(MSDOS) || defined(OS2) || defined(WINDOWS)) && !defined(WIN32) -# if !defined(__GNUC__) && !defined(__FLAT__) && !defined(__386__) -# ifndef SYS16BIT -# define SYS16BIT -# endif -# endif -#endif - -/* - * Compile with -DMAXSEG_64K if the alloc function cannot allocate more - * than 64k bytes at a time (needed on systems with 16-bit int). - */ -#ifdef SYS16BIT -# define MAXSEG_64K -#endif -#ifdef MSDOS -# define UNALIGNED_OK -#endif - -#ifdef __STDC_VERSION__ -# ifndef STDC -# define STDC -# endif -# if __STDC_VERSION__ >= 199901L -# ifndef STDC99 -# define STDC99 -# endif -# endif -#endif -#if !defined(STDC) && (defined(__STDC__) || defined(__cplusplus)) -# define STDC -#endif -#if !defined(STDC) && (defined(__GNUC__) || defined(__BORLANDC__)) -# define STDC -#endif -#if !defined(STDC) && (defined(MSDOS) || defined(WINDOWS) || defined(WIN32)) -# define STDC -#endif -#if !defined(STDC) && (defined(OS2) || defined(__HOS_AIX__)) -# define STDC -#endif - -#if defined(__OS400__) && !defined(STDC) /* iSeries (formerly AS/400). */ -# define STDC -#endif - -#ifndef STDC -# ifndef const /* cannot use !defined(STDC) && !defined(const) on Mac */ -# define const /* note: need a more gentle solution here */ -# endif -#endif - -#if defined(ZLIB_CONST) && !defined(z_const) -# define z_const const -#else -# define z_const -#endif - -#ifdef Z_SOLO - typedef unsigned long z_size_t; -#else -# define z_longlong long long -# if defined(NO_SIZE_T) - typedef unsigned NO_SIZE_T z_size_t; -# elif defined(STDC) -# include - typedef size_t z_size_t; -# else - typedef unsigned long z_size_t; -# endif -# undef z_longlong -#endif - -/* Maximum value for memLevel in deflateInit2 */ -#ifndef MAX_MEM_LEVEL -# ifdef MAXSEG_64K -# define MAX_MEM_LEVEL 8 -# else -# define MAX_MEM_LEVEL 9 -# endif -#endif - -/* Maximum value for windowBits in deflateInit2 and inflateInit2. - * WARNING: reducing MAX_WBITS makes minigzip unable to extract .gz files - * created by gzip. (Files created by minigzip can still be extracted by - * gzip.) - */ -#ifndef MAX_WBITS -# define MAX_WBITS 15 /* 32K LZ77 window */ -#endif - -/* The memory requirements for deflate are (in bytes): - (1 << (windowBits+2)) + (1 << (memLevel+9)) - that is: 128K for windowBits=15 + 128K for memLevel = 8 (default values) - plus a few kilobytes for small objects. For example, if you want to reduce - the default memory requirements from 256K to 128K, compile with - make CFLAGS="-O -DMAX_WBITS=14 -DMAX_MEM_LEVEL=7" - Of course this will generally degrade compression (there's no free lunch). - - The memory requirements for inflate are (in bytes) 1 << windowBits - that is, 32K for windowBits=15 (default value) plus about 7 kilobytes - for small objects. -*/ - - /* Type declarations */ - -#ifndef OF /* function prototypes */ -# ifdef STDC -# define OF(args) args -# else -# define OF(args) () -# endif -#endif - -#ifndef Z_ARG /* function prototypes for stdarg */ -# if defined(STDC) || defined(Z_HAVE_STDARG_H) -# define Z_ARG(args) args -# else -# define Z_ARG(args) () -# endif -#endif - -/* The following definitions for FAR are needed only for MSDOS mixed - * model programming (small or medium model with some far allocations). - * This was tested only with MSC; for other MSDOS compilers you may have - * to define NO_MEMCPY in zutil.h. If you don't need the mixed model, - * just define FAR to be empty. - */ -#ifdef SYS16BIT -# if defined(M_I86SM) || defined(M_I86MM) - /* MSC small or medium model */ -# define SMALL_MEDIUM -# ifdef _MSC_VER -# define FAR _far -# else -# define FAR far -# endif -# endif -# if (defined(__SMALL__) || defined(__MEDIUM__)) - /* Turbo C small or medium model */ -# define SMALL_MEDIUM -# ifdef __BORLANDC__ -# define FAR _far -# else -# define FAR far -# endif -# endif -#endif - -#if defined(WINDOWS) || defined(WIN32) - /* If building or using zlib as a DLL, define ZLIB_DLL. - * This is not mandatory, but it offers a little performance increase. - */ -# ifdef ZLIB_DLL -# if defined(WIN32) && (!defined(__BORLANDC__) || (__BORLANDC__ >= 0x500)) -# ifdef ZLIB_INTERNAL -# define ZEXTERN extern __declspec(dllexport) -# else -# define ZEXTERN extern __declspec(dllimport) -# endif -# endif -# endif /* ZLIB_DLL */ - /* If building or using zlib with the WINAPI/WINAPIV calling convention, - * define ZLIB_WINAPI. - * Caution: the standard ZLIB1.DLL is NOT compiled using ZLIB_WINAPI. - */ -# ifdef ZLIB_WINAPI -# ifdef FAR -# undef FAR -# endif -# include - /* No need for _export, use ZLIB.DEF instead. */ - /* For complete Windows compatibility, use WINAPI, not __stdcall. */ -# define ZEXPORT WINAPI -# ifdef WIN32 -# define ZEXPORTVA WINAPIV -# else -# define ZEXPORTVA FAR CDECL -# endif -# endif -#endif - -#if defined (__BEOS__) -# ifdef ZLIB_DLL -# ifdef ZLIB_INTERNAL -# define ZEXPORT __declspec(dllexport) -# define ZEXPORTVA __declspec(dllexport) -# else -# define ZEXPORT __declspec(dllimport) -# define ZEXPORTVA __declspec(dllimport) -# endif -# endif -#endif - -#ifndef ZEXTERN -# define ZEXTERN extern -#endif -#ifndef ZEXPORT -# define ZEXPORT -#endif -#ifndef ZEXPORTVA -# define ZEXPORTVA -#endif - -#ifndef FAR -# define FAR -#endif - -#if !defined(__MACTYPES__) -typedef unsigned char Byte; /* 8 bits */ -#endif -typedef unsigned int uInt; /* 16 bits or more */ -typedef unsigned long uLong; /* 32 bits or more */ - -#ifdef SMALL_MEDIUM - /* Borland C/C++ and some old MSC versions ignore FAR inside typedef */ -# define Bytef Byte FAR -#else - typedef Byte FAR Bytef; -#endif -typedef char FAR charf; -typedef int FAR intf; -typedef uInt FAR uIntf; -typedef uLong FAR uLongf; - -#ifdef STDC - typedef void const *voidpc; - typedef void FAR *voidpf; - typedef void *voidp; -#else - typedef Byte const *voidpc; - typedef Byte FAR *voidpf; - typedef Byte *voidp; -#endif - -#if !defined(Z_U4) && !defined(Z_SOLO) && defined(STDC) -# include -# if (UINT_MAX == 0xffffffffUL) -# define Z_U4 unsigned -# elif (ULONG_MAX == 0xffffffffUL) -# define Z_U4 unsigned long -# elif (USHRT_MAX == 0xffffffffUL) -# define Z_U4 unsigned short -# endif -#endif - -#ifdef Z_U4 - typedef Z_U4 z_crc_t; -#else - typedef unsigned long z_crc_t; -#endif - -#ifdef HAVE_UNISTD_H /* may be set to #if 1 by ./configure */ -# define Z_HAVE_UNISTD_H -#endif - -#ifdef HAVE_STDARG_H /* may be set to #if 1 by ./configure */ -# define Z_HAVE_STDARG_H -#endif - -#ifdef STDC -# ifndef Z_SOLO -# include /* for off_t */ -# endif -#endif - -#if defined(STDC) || defined(Z_HAVE_STDARG_H) -# ifndef Z_SOLO -# include /* for va_list */ -# endif -#endif - -#ifdef _WIN32 -# ifndef Z_SOLO -# include /* for wchar_t */ -# endif -#endif - -/* a little trick to accommodate both "#define _LARGEFILE64_SOURCE" and - * "#define _LARGEFILE64_SOURCE 1" as requesting 64-bit operations, (even - * though the former does not conform to the LFS document), but considering - * both "#undef _LARGEFILE64_SOURCE" and "#define _LARGEFILE64_SOURCE 0" as - * equivalently requesting no 64-bit operations - */ -#if defined(_LARGEFILE64_SOURCE) && -_LARGEFILE64_SOURCE - -1 == 1 -# undef _LARGEFILE64_SOURCE -#endif - -#if defined(__WATCOMC__) && !defined(Z_HAVE_UNISTD_H) -# define Z_HAVE_UNISTD_H -#endif -#ifndef Z_SOLO -# if defined(Z_HAVE_UNISTD_H) || defined(_LARGEFILE64_SOURCE) -# include /* for SEEK_*, off_t, and _LFS64_LARGEFILE */ -# ifdef VMS -# include /* for off_t */ -# endif -# ifndef z_off_t -# define z_off_t off_t -# endif -# endif -#endif - -#if defined(_LFS64_LARGEFILE) && _LFS64_LARGEFILE-0 -# define Z_LFS64 -#endif - -#if defined(_LARGEFILE64_SOURCE) && defined(Z_LFS64) -# define Z_LARGE64 -#endif - -#if defined(_FILE_OFFSET_BITS) && _FILE_OFFSET_BITS-0 == 64 && defined(Z_LFS64) -# define Z_WANT64 -#endif - -#if !defined(SEEK_SET) && !defined(Z_SOLO) -# define SEEK_SET 0 /* Seek from beginning of file. */ -# define SEEK_CUR 1 /* Seek from current position. */ -# define SEEK_END 2 /* Set file pointer to EOF plus "offset" */ -#endif - -#ifndef z_off_t -# define z_off_t long -#endif - -#if !defined(_WIN32) && defined(Z_LARGE64) -# define z_off64_t off64_t -#else -# if defined(_WIN32) && !defined(__GNUC__) && !defined(Z_SOLO) -# define z_off64_t __int64 -# else -# define z_off64_t z_off_t -# endif -#endif - -/* MVS linker does not support external names larger than 8 bytes */ -#if defined(__MVS__) - #pragma map(deflateInit_,"DEIN") - #pragma map(deflateInit2_,"DEIN2") - #pragma map(deflateEnd,"DEEND") - #pragma map(deflateBound,"DEBND") - #pragma map(inflateInit_,"ININ") - #pragma map(inflateInit2_,"ININ2") - #pragma map(inflateEnd,"INEND") - #pragma map(inflateSync,"INSY") - #pragma map(inflateSetDictionary,"INSEDI") - #pragma map(compressBound,"CMBND") - #pragma map(inflate_table,"INTABL") - #pragma map(inflate_fast,"INFA") - #pragma map(inflate_copyright,"INCOPY") -#endif - -#endif /* ZCONF_H */ diff --git a/deps/zlib/zlib.h b/deps/zlib/zlib.h deleted file mode 100644 index f09cdaf..0000000 --- a/deps/zlib/zlib.h +++ /dev/null @@ -1,1912 +0,0 @@ -/* zlib.h -- interface of the 'zlib' general purpose compression library - version 1.2.11, January 15th, 2017 - - Copyright (C) 1995-2017 Jean-loup Gailly and Mark Adler - - This software is provided 'as-is', without any express or implied - warranty. In no event will the authors be held liable for any damages - arising from the use of this software. - - Permission is granted to anyone to use this software for any purpose, - including commercial applications, and to alter it and redistribute it - freely, subject to the following restrictions: - - 1. The origin of this software must not be misrepresented; you must not - claim that you wrote the original software. If you use this software - in a product, an acknowledgment in the product documentation would be - appreciated but is not required. - 2. Altered source versions must be plainly marked as such, and must not be - misrepresented as being the original software. - 3. This notice may not be removed or altered from any source distribution. - - Jean-loup Gailly Mark Adler - jloup@gzip.org madler@alumni.caltech.edu - - - The data format used by the zlib library is described by RFCs (Request for - Comments) 1950 to 1952 in the files http://tools.ietf.org/html/rfc1950 - (zlib format), rfc1951 (deflate format) and rfc1952 (gzip format). -*/ - -#ifndef ZLIB_H -#define ZLIB_H - -#include "zconf.h" - -#ifdef __cplusplus -extern "C" { -#endif - -#define ZLIB_VERSION "1.2.11" -#define ZLIB_VERNUM 0x12b0 -#define ZLIB_VER_MAJOR 1 -#define ZLIB_VER_MINOR 2 -#define ZLIB_VER_REVISION 11 -#define ZLIB_VER_SUBREVISION 0 - -/* - The 'zlib' compression library provides in-memory compression and - decompression functions, including integrity checks of the uncompressed data. - This version of the library supports only one compression method (deflation) - but other algorithms will be added later and will have the same stream - interface. - - Compression can be done in a single step if the buffers are large enough, - or can be done by repeated calls of the compression function. In the latter - case, the application must provide more input and/or consume the output - (providing more output space) before each call. - - The compressed data format used by default by the in-memory functions is - the zlib format, which is a zlib wrapper documented in RFC 1950, wrapped - around a deflate stream, which is itself documented in RFC 1951. - - The library also supports reading and writing files in gzip (.gz) format - with an interface similar to that of stdio using the functions that start - with "gz". The gzip format is different from the zlib format. gzip is a - gzip wrapper, documented in RFC 1952, wrapped around a deflate stream. - - This library can optionally read and write gzip and raw deflate streams in - memory as well. - - The zlib format was designed to be compact and fast for use in memory - and on communications channels. The gzip format was designed for single- - file compression on file systems, has a larger header than zlib to maintain - directory information, and uses a different, slower check method than zlib. - - The library does not install any signal handler. The decoder checks - the consistency of the compressed data, so the library should never crash - even in the case of corrupted input. -*/ - -typedef voidpf (*alloc_func) OF((voidpf opaque, uInt items, uInt size)); -typedef void (*free_func) OF((voidpf opaque, voidpf address)); - -struct internal_state; - -typedef struct z_stream_s { - z_const Bytef *next_in; /* next input byte */ - uInt avail_in; /* number of bytes available at next_in */ - uLong total_in; /* total number of input bytes read so far */ - - Bytef *next_out; /* next output byte will go here */ - uInt avail_out; /* remaining free space at next_out */ - uLong total_out; /* total number of bytes output so far */ - - z_const char *msg; /* last error message, NULL if no error */ - struct internal_state FAR *state; /* not visible by applications */ - - alloc_func zalloc; /* used to allocate the internal state */ - free_func zfree; /* used to free the internal state */ - voidpf opaque; /* private data object passed to zalloc and zfree */ - - int data_type; /* best guess about the data type: binary or text - for deflate, or the decoding state for inflate */ - uLong adler; /* Adler-32 or CRC-32 value of the uncompressed data */ - uLong reserved; /* reserved for future use */ -} z_stream; - -typedef z_stream FAR *z_streamp; - -/* - gzip header information passed to and from zlib routines. See RFC 1952 - for more details on the meanings of these fields. -*/ -typedef struct gz_header_s { - int text; /* true if compressed data believed to be text */ - uLong time; /* modification time */ - int xflags; /* extra flags (not used when writing a gzip file) */ - int os; /* operating system */ - Bytef *extra; /* pointer to extra field or Z_NULL if none */ - uInt extra_len; /* extra field length (valid if extra != Z_NULL) */ - uInt extra_max; /* space at extra (only when reading header) */ - Bytef *name; /* pointer to zero-terminated file name or Z_NULL */ - uInt name_max; /* space at name (only when reading header) */ - Bytef *comment; /* pointer to zero-terminated comment or Z_NULL */ - uInt comm_max; /* space at comment (only when reading header) */ - int hcrc; /* true if there was or will be a header crc */ - int done; /* true when done reading gzip header (not used - when writing a gzip file) */ -} gz_header; - -typedef gz_header FAR *gz_headerp; - -/* - The application must update next_in and avail_in when avail_in has dropped - to zero. It must update next_out and avail_out when avail_out has dropped - to zero. The application must initialize zalloc, zfree and opaque before - calling the init function. All other fields are set by the compression - library and must not be updated by the application. - - The opaque value provided by the application will be passed as the first - parameter for calls of zalloc and zfree. This can be useful for custom - memory management. The compression library attaches no meaning to the - opaque value. - - zalloc must return Z_NULL if there is not enough memory for the object. - If zlib is used in a multi-threaded application, zalloc and zfree must be - thread safe. In that case, zlib is thread-safe. When zalloc and zfree are - Z_NULL on entry to the initialization function, they are set to internal - routines that use the standard library functions malloc() and free(). - - On 16-bit systems, the functions zalloc and zfree must be able to allocate - exactly 65536 bytes, but will not be required to allocate more than this if - the symbol MAXSEG_64K is defined (see zconf.h). WARNING: On MSDOS, pointers - returned by zalloc for objects of exactly 65536 bytes *must* have their - offset normalized to zero. The default allocation function provided by this - library ensures this (see zutil.c). To reduce memory requirements and avoid - any allocation of 64K objects, at the expense of compression ratio, compile - the library with -DMAX_WBITS=14 (see zconf.h). - - The fields total_in and total_out can be used for statistics or progress - reports. After compression, total_in holds the total size of the - uncompressed data and may be saved for use by the decompressor (particularly - if the decompressor wants to decompress everything in a single step). -*/ - - /* constants */ - -#define Z_NO_FLUSH 0 -#define Z_PARTIAL_FLUSH 1 -#define Z_SYNC_FLUSH 2 -#define Z_FULL_FLUSH 3 -#define Z_FINISH 4 -#define Z_BLOCK 5 -#define Z_TREES 6 -/* Allowed flush values; see deflate() and inflate() below for details */ - -#define Z_OK 0 -#define Z_STREAM_END 1 -#define Z_NEED_DICT 2 -#define Z_ERRNO (-1) -#define Z_STREAM_ERROR (-2) -#define Z_DATA_ERROR (-3) -#define Z_MEM_ERROR (-4) -#define Z_BUF_ERROR (-5) -#define Z_VERSION_ERROR (-6) -/* Return codes for the compression/decompression functions. Negative values - * are errors, positive values are used for special but normal events. - */ - -#define Z_NO_COMPRESSION 0 -#define Z_BEST_SPEED 1 -#define Z_BEST_COMPRESSION 9 -#define Z_DEFAULT_COMPRESSION (-1) -/* compression levels */ - -#define Z_FILTERED 1 -#define Z_HUFFMAN_ONLY 2 -#define Z_RLE 3 -#define Z_FIXED 4 -#define Z_DEFAULT_STRATEGY 0 -/* compression strategy; see deflateInit2() below for details */ - -#define Z_BINARY 0 -#define Z_TEXT 1 -#define Z_ASCII Z_TEXT /* for compatibility with 1.2.2 and earlier */ -#define Z_UNKNOWN 2 -/* Possible values of the data_type field for deflate() */ - -#define Z_DEFLATED 8 -/* The deflate compression method (the only one supported in this version) */ - -#define Z_NULL 0 /* for initializing zalloc, zfree, opaque */ - -#define zlib_version zlibVersion() -/* for compatibility with versions < 1.0.2 */ - - - /* basic functions */ - -ZEXTERN const char * ZEXPORT zlibVersion OF((void)); -/* The application can compare zlibVersion and ZLIB_VERSION for consistency. - If the first character differs, the library code actually used is not - compatible with the zlib.h header file used by the application. This check - is automatically made by deflateInit and inflateInit. - */ - -/* -ZEXTERN int ZEXPORT deflateInit OF((z_streamp strm, int level)); - - Initializes the internal stream state for compression. The fields - zalloc, zfree and opaque must be initialized before by the caller. If - zalloc and zfree are set to Z_NULL, deflateInit updates them to use default - allocation functions. - - The compression level must be Z_DEFAULT_COMPRESSION, or between 0 and 9: - 1 gives best speed, 9 gives best compression, 0 gives no compression at all - (the input data is simply copied a block at a time). Z_DEFAULT_COMPRESSION - requests a default compromise between speed and compression (currently - equivalent to level 6). - - deflateInit returns Z_OK if success, Z_MEM_ERROR if there was not enough - memory, Z_STREAM_ERROR if level is not a valid compression level, or - Z_VERSION_ERROR if the zlib library version (zlib_version) is incompatible - with the version assumed by the caller (ZLIB_VERSION). msg is set to null - if there is no error message. deflateInit does not perform any compression: - this will be done by deflate(). -*/ - - -ZEXTERN int ZEXPORT deflate OF((z_streamp strm, int flush)); -/* - deflate compresses as much data as possible, and stops when the input - buffer becomes empty or the output buffer becomes full. It may introduce - some output latency (reading input without producing any output) except when - forced to flush. - - The detailed semantics are as follows. deflate performs one or both of the - following actions: - - - Compress more input starting at next_in and update next_in and avail_in - accordingly. If not all input can be processed (because there is not - enough room in the output buffer), next_in and avail_in are updated and - processing will resume at this point for the next call of deflate(). - - - Generate more output starting at next_out and update next_out and avail_out - accordingly. This action is forced if the parameter flush is non zero. - Forcing flush frequently degrades the compression ratio, so this parameter - should be set only when necessary. Some output may be provided even if - flush is zero. - - Before the call of deflate(), the application should ensure that at least - one of the actions is possible, by providing more input and/or consuming more - output, and updating avail_in or avail_out accordingly; avail_out should - never be zero before the call. The application can consume the compressed - output when it wants, for example when the output buffer is full (avail_out - == 0), or after each call of deflate(). If deflate returns Z_OK and with - zero avail_out, it must be called again after making room in the output - buffer because there might be more output pending. See deflatePending(), - which can be used if desired to determine whether or not there is more ouput - in that case. - - Normally the parameter flush is set to Z_NO_FLUSH, which allows deflate to - decide how much data to accumulate before producing output, in order to - maximize compression. - - If the parameter flush is set to Z_SYNC_FLUSH, all pending output is - flushed to the output buffer and the output is aligned on a byte boundary, so - that the decompressor can get all input data available so far. (In - particular avail_in is zero after the call if enough output space has been - provided before the call.) Flushing may degrade compression for some - compression algorithms and so it should be used only when necessary. This - completes the current deflate block and follows it with an empty stored block - that is three bits plus filler bits to the next byte, followed by four bytes - (00 00 ff ff). - - If flush is set to Z_PARTIAL_FLUSH, all pending output is flushed to the - output buffer, but the output is not aligned to a byte boundary. All of the - input data so far will be available to the decompressor, as for Z_SYNC_FLUSH. - This completes the current deflate block and follows it with an empty fixed - codes block that is 10 bits long. This assures that enough bytes are output - in order for the decompressor to finish the block before the empty fixed - codes block. - - If flush is set to Z_BLOCK, a deflate block is completed and emitted, as - for Z_SYNC_FLUSH, but the output is not aligned on a byte boundary, and up to - seven bits of the current block are held to be written as the next byte after - the next deflate block is completed. In this case, the decompressor may not - be provided enough bits at this point in order to complete decompression of - the data provided so far to the compressor. It may need to wait for the next - block to be emitted. This is for advanced applications that need to control - the emission of deflate blocks. - - If flush is set to Z_FULL_FLUSH, all output is flushed as with - Z_SYNC_FLUSH, and the compression state is reset so that decompression can - restart from this point if previous compressed data has been damaged or if - random access is desired. Using Z_FULL_FLUSH too often can seriously degrade - compression. - - If deflate returns with avail_out == 0, this function must be called again - with the same value of the flush parameter and more output space (updated - avail_out), until the flush is complete (deflate returns with non-zero - avail_out). In the case of a Z_FULL_FLUSH or Z_SYNC_FLUSH, make sure that - avail_out is greater than six to avoid repeated flush markers due to - avail_out == 0 on return. - - If the parameter flush is set to Z_FINISH, pending input is processed, - pending output is flushed and deflate returns with Z_STREAM_END if there was - enough output space. If deflate returns with Z_OK or Z_BUF_ERROR, this - function must be called again with Z_FINISH and more output space (updated - avail_out) but no more input data, until it returns with Z_STREAM_END or an - error. After deflate has returned Z_STREAM_END, the only possible operations - on the stream are deflateReset or deflateEnd. - - Z_FINISH can be used in the first deflate call after deflateInit if all the - compression is to be done in a single step. In order to complete in one - call, avail_out must be at least the value returned by deflateBound (see - below). Then deflate is guaranteed to return Z_STREAM_END. If not enough - output space is provided, deflate will not return Z_STREAM_END, and it must - be called again as described above. - - deflate() sets strm->adler to the Adler-32 checksum of all input read - so far (that is, total_in bytes). If a gzip stream is being generated, then - strm->adler will be the CRC-32 checksum of the input read so far. (See - deflateInit2 below.) - - deflate() may update strm->data_type if it can make a good guess about - the input data type (Z_BINARY or Z_TEXT). If in doubt, the data is - considered binary. This field is only for information purposes and does not - affect the compression algorithm in any manner. - - deflate() returns Z_OK if some progress has been made (more input - processed or more output produced), Z_STREAM_END if all input has been - consumed and all output has been produced (only when flush is set to - Z_FINISH), Z_STREAM_ERROR if the stream state was inconsistent (for example - if next_in or next_out was Z_NULL or the state was inadvertently written over - by the application), or Z_BUF_ERROR if no progress is possible (for example - avail_in or avail_out was zero). Note that Z_BUF_ERROR is not fatal, and - deflate() can be called again with more input and more output space to - continue compressing. -*/ - - -ZEXTERN int ZEXPORT deflateEnd OF((z_streamp strm)); -/* - All dynamically allocated data structures for this stream are freed. - This function discards any unprocessed input and does not flush any pending - output. - - deflateEnd returns Z_OK if success, Z_STREAM_ERROR if the - stream state was inconsistent, Z_DATA_ERROR if the stream was freed - prematurely (some input or output was discarded). In the error case, msg - may be set but then points to a static string (which must not be - deallocated). -*/ - - -/* -ZEXTERN int ZEXPORT inflateInit OF((z_streamp strm)); - - Initializes the internal stream state for decompression. The fields - next_in, avail_in, zalloc, zfree and opaque must be initialized before by - the caller. In the current version of inflate, the provided input is not - read or consumed. The allocation of a sliding window will be deferred to - the first call of inflate (if the decompression does not complete on the - first call). If zalloc and zfree are set to Z_NULL, inflateInit updates - them to use default allocation functions. - - inflateInit returns Z_OK if success, Z_MEM_ERROR if there was not enough - memory, Z_VERSION_ERROR if the zlib library version is incompatible with the - version assumed by the caller, or Z_STREAM_ERROR if the parameters are - invalid, such as a null pointer to the structure. msg is set to null if - there is no error message. inflateInit does not perform any decompression. - Actual decompression will be done by inflate(). So next_in, and avail_in, - next_out, and avail_out are unused and unchanged. The current - implementation of inflateInit() does not process any header information -- - that is deferred until inflate() is called. -*/ - - -ZEXTERN int ZEXPORT inflate OF((z_streamp strm, int flush)); -/* - inflate decompresses as much data as possible, and stops when the input - buffer becomes empty or the output buffer becomes full. It may introduce - some output latency (reading input without producing any output) except when - forced to flush. - - The detailed semantics are as follows. inflate performs one or both of the - following actions: - - - Decompress more input starting at next_in and update next_in and avail_in - accordingly. If not all input can be processed (because there is not - enough room in the output buffer), then next_in and avail_in are updated - accordingly, and processing will resume at this point for the next call of - inflate(). - - - Generate more output starting at next_out and update next_out and avail_out - accordingly. inflate() provides as much output as possible, until there is - no more input data or no more space in the output buffer (see below about - the flush parameter). - - Before the call of inflate(), the application should ensure that at least - one of the actions is possible, by providing more input and/or consuming more - output, and updating the next_* and avail_* values accordingly. If the - caller of inflate() does not provide both available input and available - output space, it is possible that there will be no progress made. The - application can consume the uncompressed output when it wants, for example - when the output buffer is full (avail_out == 0), or after each call of - inflate(). If inflate returns Z_OK and with zero avail_out, it must be - called again after making room in the output buffer because there might be - more output pending. - - The flush parameter of inflate() can be Z_NO_FLUSH, Z_SYNC_FLUSH, Z_FINISH, - Z_BLOCK, or Z_TREES. Z_SYNC_FLUSH requests that inflate() flush as much - output as possible to the output buffer. Z_BLOCK requests that inflate() - stop if and when it gets to the next deflate block boundary. When decoding - the zlib or gzip format, this will cause inflate() to return immediately - after the header and before the first block. When doing a raw inflate, - inflate() will go ahead and process the first block, and will return when it - gets to the end of that block, or when it runs out of data. - - The Z_BLOCK option assists in appending to or combining deflate streams. - To assist in this, on return inflate() always sets strm->data_type to the - number of unused bits in the last byte taken from strm->next_in, plus 64 if - inflate() is currently decoding the last block in the deflate stream, plus - 128 if inflate() returned immediately after decoding an end-of-block code or - decoding the complete header up to just before the first byte of the deflate - stream. The end-of-block will not be indicated until all of the uncompressed - data from that block has been written to strm->next_out. The number of - unused bits may in general be greater than seven, except when bit 7 of - data_type is set, in which case the number of unused bits will be less than - eight. data_type is set as noted here every time inflate() returns for all - flush options, and so can be used to determine the amount of currently - consumed input in bits. - - The Z_TREES option behaves as Z_BLOCK does, but it also returns when the - end of each deflate block header is reached, before any actual data in that - block is decoded. This allows the caller to determine the length of the - deflate block header for later use in random access within a deflate block. - 256 is added to the value of strm->data_type when inflate() returns - immediately after reaching the end of the deflate block header. - - inflate() should normally be called until it returns Z_STREAM_END or an - error. However if all decompression is to be performed in a single step (a - single call of inflate), the parameter flush should be set to Z_FINISH. In - this case all pending input is processed and all pending output is flushed; - avail_out must be large enough to hold all of the uncompressed data for the - operation to complete. (The size of the uncompressed data may have been - saved by the compressor for this purpose.) The use of Z_FINISH is not - required to perform an inflation in one step. However it may be used to - inform inflate that a faster approach can be used for the single inflate() - call. Z_FINISH also informs inflate to not maintain a sliding window if the - stream completes, which reduces inflate's memory footprint. If the stream - does not complete, either because not all of the stream is provided or not - enough output space is provided, then a sliding window will be allocated and - inflate() can be called again to continue the operation as if Z_NO_FLUSH had - been used. - - In this implementation, inflate() always flushes as much output as - possible to the output buffer, and always uses the faster approach on the - first call. So the effects of the flush parameter in this implementation are - on the return value of inflate() as noted below, when inflate() returns early - when Z_BLOCK or Z_TREES is used, and when inflate() avoids the allocation of - memory for a sliding window when Z_FINISH is used. - - If a preset dictionary is needed after this call (see inflateSetDictionary - below), inflate sets strm->adler to the Adler-32 checksum of the dictionary - chosen by the compressor and returns Z_NEED_DICT; otherwise it sets - strm->adler to the Adler-32 checksum of all output produced so far (that is, - total_out bytes) and returns Z_OK, Z_STREAM_END or an error code as described - below. At the end of the stream, inflate() checks that its computed Adler-32 - checksum is equal to that saved by the compressor and returns Z_STREAM_END - only if the checksum is correct. - - inflate() can decompress and check either zlib-wrapped or gzip-wrapped - deflate data. The header type is detected automatically, if requested when - initializing with inflateInit2(). Any information contained in the gzip - header is not retained unless inflateGetHeader() is used. When processing - gzip-wrapped deflate data, strm->adler32 is set to the CRC-32 of the output - produced so far. The CRC-32 is checked against the gzip trailer, as is the - uncompressed length, modulo 2^32. - - inflate() returns Z_OK if some progress has been made (more input processed - or more output produced), Z_STREAM_END if the end of the compressed data has - been reached and all uncompressed output has been produced, Z_NEED_DICT if a - preset dictionary is needed at this point, Z_DATA_ERROR if the input data was - corrupted (input stream not conforming to the zlib format or incorrect check - value, in which case strm->msg points to a string with a more specific - error), Z_STREAM_ERROR if the stream structure was inconsistent (for example - next_in or next_out was Z_NULL, or the state was inadvertently written over - by the application), Z_MEM_ERROR if there was not enough memory, Z_BUF_ERROR - if no progress was possible or if there was not enough room in the output - buffer when Z_FINISH is used. Note that Z_BUF_ERROR is not fatal, and - inflate() can be called again with more input and more output space to - continue decompressing. If Z_DATA_ERROR is returned, the application may - then call inflateSync() to look for a good compression block if a partial - recovery of the data is to be attempted. -*/ - - -ZEXTERN int ZEXPORT inflateEnd OF((z_streamp strm)); -/* - All dynamically allocated data structures for this stream are freed. - This function discards any unprocessed input and does not flush any pending - output. - - inflateEnd returns Z_OK if success, or Z_STREAM_ERROR if the stream state - was inconsistent. -*/ - - - /* Advanced functions */ - -/* - The following functions are needed only in some special applications. -*/ - -/* -ZEXTERN int ZEXPORT deflateInit2 OF((z_streamp strm, - int level, - int method, - int windowBits, - int memLevel, - int strategy)); - - This is another version of deflateInit with more compression options. The - fields next_in, zalloc, zfree and opaque must be initialized before by the - caller. - - The method parameter is the compression method. It must be Z_DEFLATED in - this version of the library. - - The windowBits parameter is the base two logarithm of the window size - (the size of the history buffer). It should be in the range 8..15 for this - version of the library. Larger values of this parameter result in better - compression at the expense of memory usage. The default value is 15 if - deflateInit is used instead. - - For the current implementation of deflate(), a windowBits value of 8 (a - window size of 256 bytes) is not supported. As a result, a request for 8 - will result in 9 (a 512-byte window). In that case, providing 8 to - inflateInit2() will result in an error when the zlib header with 9 is - checked against the initialization of inflate(). The remedy is to not use 8 - with deflateInit2() with this initialization, or at least in that case use 9 - with inflateInit2(). - - windowBits can also be -8..-15 for raw deflate. In this case, -windowBits - determines the window size. deflate() will then generate raw deflate data - with no zlib header or trailer, and will not compute a check value. - - windowBits can also be greater than 15 for optional gzip encoding. Add - 16 to windowBits to write a simple gzip header and trailer around the - compressed data instead of a zlib wrapper. The gzip header will have no - file name, no extra data, no comment, no modification time (set to zero), no - header crc, and the operating system will be set to the appropriate value, - if the operating system was determined at compile time. If a gzip stream is - being written, strm->adler is a CRC-32 instead of an Adler-32. - - For raw deflate or gzip encoding, a request for a 256-byte window is - rejected as invalid, since only the zlib header provides a means of - transmitting the window size to the decompressor. - - The memLevel parameter specifies how much memory should be allocated - for the internal compression state. memLevel=1 uses minimum memory but is - slow and reduces compression ratio; memLevel=9 uses maximum memory for - optimal speed. The default value is 8. See zconf.h for total memory usage - as a function of windowBits and memLevel. - - The strategy parameter is used to tune the compression algorithm. Use the - value Z_DEFAULT_STRATEGY for normal data, Z_FILTERED for data produced by a - filter (or predictor), Z_HUFFMAN_ONLY to force Huffman encoding only (no - string match), or Z_RLE to limit match distances to one (run-length - encoding). Filtered data consists mostly of small values with a somewhat - random distribution. In this case, the compression algorithm is tuned to - compress them better. The effect of Z_FILTERED is to force more Huffman - coding and less string matching; it is somewhat intermediate between - Z_DEFAULT_STRATEGY and Z_HUFFMAN_ONLY. Z_RLE is designed to be almost as - fast as Z_HUFFMAN_ONLY, but give better compression for PNG image data. The - strategy parameter only affects the compression ratio but not the - correctness of the compressed output even if it is not set appropriately. - Z_FIXED prevents the use of dynamic Huffman codes, allowing for a simpler - decoder for special applications. - - deflateInit2 returns Z_OK if success, Z_MEM_ERROR if there was not enough - memory, Z_STREAM_ERROR if any parameter is invalid (such as an invalid - method), or Z_VERSION_ERROR if the zlib library version (zlib_version) is - incompatible with the version assumed by the caller (ZLIB_VERSION). msg is - set to null if there is no error message. deflateInit2 does not perform any - compression: this will be done by deflate(). -*/ - -ZEXTERN int ZEXPORT deflateSetDictionary OF((z_streamp strm, - const Bytef *dictionary, - uInt dictLength)); -/* - Initializes the compression dictionary from the given byte sequence - without producing any compressed output. When using the zlib format, this - function must be called immediately after deflateInit, deflateInit2 or - deflateReset, and before any call of deflate. When doing raw deflate, this - function must be called either before any call of deflate, or immediately - after the completion of a deflate block, i.e. after all input has been - consumed and all output has been delivered when using any of the flush - options Z_BLOCK, Z_PARTIAL_FLUSH, Z_SYNC_FLUSH, or Z_FULL_FLUSH. The - compressor and decompressor must use exactly the same dictionary (see - inflateSetDictionary). - - The dictionary should consist of strings (byte sequences) that are likely - to be encountered later in the data to be compressed, with the most commonly - used strings preferably put towards the end of the dictionary. Using a - dictionary is most useful when the data to be compressed is short and can be - predicted with good accuracy; the data can then be compressed better than - with the default empty dictionary. - - Depending on the size of the compression data structures selected by - deflateInit or deflateInit2, a part of the dictionary may in effect be - discarded, for example if the dictionary is larger than the window size - provided in deflateInit or deflateInit2. Thus the strings most likely to be - useful should be put at the end of the dictionary, not at the front. In - addition, the current implementation of deflate will use at most the window - size minus 262 bytes of the provided dictionary. - - Upon return of this function, strm->adler is set to the Adler-32 value - of the dictionary; the decompressor may later use this value to determine - which dictionary has been used by the compressor. (The Adler-32 value - applies to the whole dictionary even if only a subset of the dictionary is - actually used by the compressor.) If a raw deflate was requested, then the - Adler-32 value is not computed and strm->adler is not set. - - deflateSetDictionary returns Z_OK if success, or Z_STREAM_ERROR if a - parameter is invalid (e.g. dictionary being Z_NULL) or the stream state is - inconsistent (for example if deflate has already been called for this stream - or if not at a block boundary for raw deflate). deflateSetDictionary does - not perform any compression: this will be done by deflate(). -*/ - -ZEXTERN int ZEXPORT deflateGetDictionary OF((z_streamp strm, - Bytef *dictionary, - uInt *dictLength)); -/* - Returns the sliding dictionary being maintained by deflate. dictLength is - set to the number of bytes in the dictionary, and that many bytes are copied - to dictionary. dictionary must have enough space, where 32768 bytes is - always enough. If deflateGetDictionary() is called with dictionary equal to - Z_NULL, then only the dictionary length is returned, and nothing is copied. - Similary, if dictLength is Z_NULL, then it is not set. - - deflateGetDictionary() may return a length less than the window size, even - when more than the window size in input has been provided. It may return up - to 258 bytes less in that case, due to how zlib's implementation of deflate - manages the sliding window and lookahead for matches, where matches can be - up to 258 bytes long. If the application needs the last window-size bytes of - input, then that would need to be saved by the application outside of zlib. - - deflateGetDictionary returns Z_OK on success, or Z_STREAM_ERROR if the - stream state is inconsistent. -*/ - -ZEXTERN int ZEXPORT deflateCopy OF((z_streamp dest, - z_streamp source)); -/* - Sets the destination stream as a complete copy of the source stream. - - This function can be useful when several compression strategies will be - tried, for example when there are several ways of pre-processing the input - data with a filter. The streams that will be discarded should then be freed - by calling deflateEnd. Note that deflateCopy duplicates the internal - compression state which can be quite large, so this strategy is slow and can - consume lots of memory. - - deflateCopy returns Z_OK if success, Z_MEM_ERROR if there was not - enough memory, Z_STREAM_ERROR if the source stream state was inconsistent - (such as zalloc being Z_NULL). msg is left unchanged in both source and - destination. -*/ - -ZEXTERN int ZEXPORT deflateReset OF((z_streamp strm)); -/* - This function is equivalent to deflateEnd followed by deflateInit, but - does not free and reallocate the internal compression state. The stream - will leave the compression level and any other attributes that may have been - set unchanged. - - deflateReset returns Z_OK if success, or Z_STREAM_ERROR if the source - stream state was inconsistent (such as zalloc or state being Z_NULL). -*/ - -ZEXTERN int ZEXPORT deflateParams OF((z_streamp strm, - int level, - int strategy)); -/* - Dynamically update the compression level and compression strategy. The - interpretation of level and strategy is as in deflateInit2(). This can be - used to switch between compression and straight copy of the input data, or - to switch to a different kind of input data requiring a different strategy. - If the compression approach (which is a function of the level) or the - strategy is changed, and if any input has been consumed in a previous - deflate() call, then the input available so far is compressed with the old - level and strategy using deflate(strm, Z_BLOCK). There are three approaches - for the compression levels 0, 1..3, and 4..9 respectively. The new level - and strategy will take effect at the next call of deflate(). - - If a deflate(strm, Z_BLOCK) is performed by deflateParams(), and it does - not have enough output space to complete, then the parameter change will not - take effect. In this case, deflateParams() can be called again with the - same parameters and more output space to try again. - - In order to assure a change in the parameters on the first try, the - deflate stream should be flushed using deflate() with Z_BLOCK or other flush - request until strm.avail_out is not zero, before calling deflateParams(). - Then no more input data should be provided before the deflateParams() call. - If this is done, the old level and strategy will be applied to the data - compressed before deflateParams(), and the new level and strategy will be - applied to the the data compressed after deflateParams(). - - deflateParams returns Z_OK on success, Z_STREAM_ERROR if the source stream - state was inconsistent or if a parameter was invalid, or Z_BUF_ERROR if - there was not enough output space to complete the compression of the - available input data before a change in the strategy or approach. Note that - in the case of a Z_BUF_ERROR, the parameters are not changed. A return - value of Z_BUF_ERROR is not fatal, in which case deflateParams() can be - retried with more output space. -*/ - -ZEXTERN int ZEXPORT deflateTune OF((z_streamp strm, - int good_length, - int max_lazy, - int nice_length, - int max_chain)); -/* - Fine tune deflate's internal compression parameters. This should only be - used by someone who understands the algorithm used by zlib's deflate for - searching for the best matching string, and even then only by the most - fanatic optimizer trying to squeeze out the last compressed bit for their - specific input data. Read the deflate.c source code for the meaning of the - max_lazy, good_length, nice_length, and max_chain parameters. - - deflateTune() can be called after deflateInit() or deflateInit2(), and - returns Z_OK on success, or Z_STREAM_ERROR for an invalid deflate stream. - */ - -ZEXTERN uLong ZEXPORT deflateBound OF((z_streamp strm, - uLong sourceLen)); -/* - deflateBound() returns an upper bound on the compressed size after - deflation of sourceLen bytes. It must be called after deflateInit() or - deflateInit2(), and after deflateSetHeader(), if used. This would be used - to allocate an output buffer for deflation in a single pass, and so would be - called before deflate(). If that first deflate() call is provided the - sourceLen input bytes, an output buffer allocated to the size returned by - deflateBound(), and the flush value Z_FINISH, then deflate() is guaranteed - to return Z_STREAM_END. Note that it is possible for the compressed size to - be larger than the value returned by deflateBound() if flush options other - than Z_FINISH or Z_NO_FLUSH are used. -*/ - -ZEXTERN int ZEXPORT deflatePending OF((z_streamp strm, - unsigned *pending, - int *bits)); -/* - deflatePending() returns the number of bytes and bits of output that have - been generated, but not yet provided in the available output. The bytes not - provided would be due to the available output space having being consumed. - The number of bits of output not provided are between 0 and 7, where they - await more bits to join them in order to fill out a full byte. If pending - or bits are Z_NULL, then those values are not set. - - deflatePending returns Z_OK if success, or Z_STREAM_ERROR if the source - stream state was inconsistent. - */ - -ZEXTERN int ZEXPORT deflatePrime OF((z_streamp strm, - int bits, - int value)); -/* - deflatePrime() inserts bits in the deflate output stream. The intent - is that this function is used to start off the deflate output with the bits - leftover from a previous deflate stream when appending to it. As such, this - function can only be used for raw deflate, and must be used before the first - deflate() call after a deflateInit2() or deflateReset(). bits must be less - than or equal to 16, and that many of the least significant bits of value - will be inserted in the output. - - deflatePrime returns Z_OK if success, Z_BUF_ERROR if there was not enough - room in the internal buffer to insert the bits, or Z_STREAM_ERROR if the - source stream state was inconsistent. -*/ - -ZEXTERN int ZEXPORT deflateSetHeader OF((z_streamp strm, - gz_headerp head)); -/* - deflateSetHeader() provides gzip header information for when a gzip - stream is requested by deflateInit2(). deflateSetHeader() may be called - after deflateInit2() or deflateReset() and before the first call of - deflate(). The text, time, os, extra field, name, and comment information - in the provided gz_header structure are written to the gzip header (xflag is - ignored -- the extra flags are set according to the compression level). The - caller must assure that, if not Z_NULL, name and comment are terminated with - a zero byte, and that if extra is not Z_NULL, that extra_len bytes are - available there. If hcrc is true, a gzip header crc is included. Note that - the current versions of the command-line version of gzip (up through version - 1.3.x) do not support header crc's, and will report that it is a "multi-part - gzip file" and give up. - - If deflateSetHeader is not used, the default gzip header has text false, - the time set to zero, and os set to 255, with no extra, name, or comment - fields. The gzip header is returned to the default state by deflateReset(). - - deflateSetHeader returns Z_OK if success, or Z_STREAM_ERROR if the source - stream state was inconsistent. -*/ - -/* -ZEXTERN int ZEXPORT inflateInit2 OF((z_streamp strm, - int windowBits)); - - This is another version of inflateInit with an extra parameter. The - fields next_in, avail_in, zalloc, zfree and opaque must be initialized - before by the caller. - - The windowBits parameter is the base two logarithm of the maximum window - size (the size of the history buffer). It should be in the range 8..15 for - this version of the library. The default value is 15 if inflateInit is used - instead. windowBits must be greater than or equal to the windowBits value - provided to deflateInit2() while compressing, or it must be equal to 15 if - deflateInit2() was not used. If a compressed stream with a larger window - size is given as input, inflate() will return with the error code - Z_DATA_ERROR instead of trying to allocate a larger window. - - windowBits can also be zero to request that inflate use the window size in - the zlib header of the compressed stream. - - windowBits can also be -8..-15 for raw inflate. In this case, -windowBits - determines the window size. inflate() will then process raw deflate data, - not looking for a zlib or gzip header, not generating a check value, and not - looking for any check values for comparison at the end of the stream. This - is for use with other formats that use the deflate compressed data format - such as zip. Those formats provide their own check values. If a custom - format is developed using the raw deflate format for compressed data, it is - recommended that a check value such as an Adler-32 or a CRC-32 be applied to - the uncompressed data as is done in the zlib, gzip, and zip formats. For - most applications, the zlib format should be used as is. Note that comments - above on the use in deflateInit2() applies to the magnitude of windowBits. - - windowBits can also be greater than 15 for optional gzip decoding. Add - 32 to windowBits to enable zlib and gzip decoding with automatic header - detection, or add 16 to decode only the gzip format (the zlib format will - return a Z_DATA_ERROR). If a gzip stream is being decoded, strm->adler is a - CRC-32 instead of an Adler-32. Unlike the gunzip utility and gzread() (see - below), inflate() will not automatically decode concatenated gzip streams. - inflate() will return Z_STREAM_END at the end of the gzip stream. The state - would need to be reset to continue decoding a subsequent gzip stream. - - inflateInit2 returns Z_OK if success, Z_MEM_ERROR if there was not enough - memory, Z_VERSION_ERROR if the zlib library version is incompatible with the - version assumed by the caller, or Z_STREAM_ERROR if the parameters are - invalid, such as a null pointer to the structure. msg is set to null if - there is no error message. inflateInit2 does not perform any decompression - apart from possibly reading the zlib header if present: actual decompression - will be done by inflate(). (So next_in and avail_in may be modified, but - next_out and avail_out are unused and unchanged.) The current implementation - of inflateInit2() does not process any header information -- that is - deferred until inflate() is called. -*/ - -ZEXTERN int ZEXPORT inflateSetDictionary OF((z_streamp strm, - const Bytef *dictionary, - uInt dictLength)); -/* - Initializes the decompression dictionary from the given uncompressed byte - sequence. This function must be called immediately after a call of inflate, - if that call returned Z_NEED_DICT. The dictionary chosen by the compressor - can be determined from the Adler-32 value returned by that call of inflate. - The compressor and decompressor must use exactly the same dictionary (see - deflateSetDictionary). For raw inflate, this function can be called at any - time to set the dictionary. If the provided dictionary is smaller than the - window and there is already data in the window, then the provided dictionary - will amend what's there. The application must insure that the dictionary - that was used for compression is provided. - - inflateSetDictionary returns Z_OK if success, Z_STREAM_ERROR if a - parameter is invalid (e.g. dictionary being Z_NULL) or the stream state is - inconsistent, Z_DATA_ERROR if the given dictionary doesn't match the - expected one (incorrect Adler-32 value). inflateSetDictionary does not - perform any decompression: this will be done by subsequent calls of - inflate(). -*/ - -ZEXTERN int ZEXPORT inflateGetDictionary OF((z_streamp strm, - Bytef *dictionary, - uInt *dictLength)); -/* - Returns the sliding dictionary being maintained by inflate. dictLength is - set to the number of bytes in the dictionary, and that many bytes are copied - to dictionary. dictionary must have enough space, where 32768 bytes is - always enough. If inflateGetDictionary() is called with dictionary equal to - Z_NULL, then only the dictionary length is returned, and nothing is copied. - Similary, if dictLength is Z_NULL, then it is not set. - - inflateGetDictionary returns Z_OK on success, or Z_STREAM_ERROR if the - stream state is inconsistent. -*/ - -ZEXTERN int ZEXPORT inflateSync OF((z_streamp strm)); -/* - Skips invalid compressed data until a possible full flush point (see above - for the description of deflate with Z_FULL_FLUSH) can be found, or until all - available input is skipped. No output is provided. - - inflateSync searches for a 00 00 FF FF pattern in the compressed data. - All full flush points have this pattern, but not all occurrences of this - pattern are full flush points. - - inflateSync returns Z_OK if a possible full flush point has been found, - Z_BUF_ERROR if no more input was provided, Z_DATA_ERROR if no flush point - has been found, or Z_STREAM_ERROR if the stream structure was inconsistent. - In the success case, the application may save the current current value of - total_in which indicates where valid compressed data was found. In the - error case, the application may repeatedly call inflateSync, providing more - input each time, until success or end of the input data. -*/ - -ZEXTERN int ZEXPORT inflateCopy OF((z_streamp dest, - z_streamp source)); -/* - Sets the destination stream as a complete copy of the source stream. - - This function can be useful when randomly accessing a large stream. The - first pass through the stream can periodically record the inflate state, - allowing restarting inflate at those points when randomly accessing the - stream. - - inflateCopy returns Z_OK if success, Z_MEM_ERROR if there was not - enough memory, Z_STREAM_ERROR if the source stream state was inconsistent - (such as zalloc being Z_NULL). msg is left unchanged in both source and - destination. -*/ - -ZEXTERN int ZEXPORT inflateReset OF((z_streamp strm)); -/* - This function is equivalent to inflateEnd followed by inflateInit, - but does not free and reallocate the internal decompression state. The - stream will keep attributes that may have been set by inflateInit2. - - inflateReset returns Z_OK if success, or Z_STREAM_ERROR if the source - stream state was inconsistent (such as zalloc or state being Z_NULL). -*/ - -ZEXTERN int ZEXPORT inflateReset2 OF((z_streamp strm, - int windowBits)); -/* - This function is the same as inflateReset, but it also permits changing - the wrap and window size requests. The windowBits parameter is interpreted - the same as it is for inflateInit2. If the window size is changed, then the - memory allocated for the window is freed, and the window will be reallocated - by inflate() if needed. - - inflateReset2 returns Z_OK if success, or Z_STREAM_ERROR if the source - stream state was inconsistent (such as zalloc or state being Z_NULL), or if - the windowBits parameter is invalid. -*/ - -ZEXTERN int ZEXPORT inflatePrime OF((z_streamp strm, - int bits, - int value)); -/* - This function inserts bits in the inflate input stream. The intent is - that this function is used to start inflating at a bit position in the - middle of a byte. The provided bits will be used before any bytes are used - from next_in. This function should only be used with raw inflate, and - should be used before the first inflate() call after inflateInit2() or - inflateReset(). bits must be less than or equal to 16, and that many of the - least significant bits of value will be inserted in the input. - - If bits is negative, then the input stream bit buffer is emptied. Then - inflatePrime() can be called again to put bits in the buffer. This is used - to clear out bits leftover after feeding inflate a block description prior - to feeding inflate codes. - - inflatePrime returns Z_OK if success, or Z_STREAM_ERROR if the source - stream state was inconsistent. -*/ - -ZEXTERN long ZEXPORT inflateMark OF((z_streamp strm)); -/* - This function returns two values, one in the lower 16 bits of the return - value, and the other in the remaining upper bits, obtained by shifting the - return value down 16 bits. If the upper value is -1 and the lower value is - zero, then inflate() is currently decoding information outside of a block. - If the upper value is -1 and the lower value is non-zero, then inflate is in - the middle of a stored block, with the lower value equaling the number of - bytes from the input remaining to copy. If the upper value is not -1, then - it is the number of bits back from the current bit position in the input of - the code (literal or length/distance pair) currently being processed. In - that case the lower value is the number of bytes already emitted for that - code. - - A code is being processed if inflate is waiting for more input to complete - decoding of the code, or if it has completed decoding but is waiting for - more output space to write the literal or match data. - - inflateMark() is used to mark locations in the input data for random - access, which may be at bit positions, and to note those cases where the - output of a code may span boundaries of random access blocks. The current - location in the input stream can be determined from avail_in and data_type - as noted in the description for the Z_BLOCK flush parameter for inflate. - - inflateMark returns the value noted above, or -65536 if the provided - source stream state was inconsistent. -*/ - -ZEXTERN int ZEXPORT inflateGetHeader OF((z_streamp strm, - gz_headerp head)); -/* - inflateGetHeader() requests that gzip header information be stored in the - provided gz_header structure. inflateGetHeader() may be called after - inflateInit2() or inflateReset(), and before the first call of inflate(). - As inflate() processes the gzip stream, head->done is zero until the header - is completed, at which time head->done is set to one. If a zlib stream is - being decoded, then head->done is set to -1 to indicate that there will be - no gzip header information forthcoming. Note that Z_BLOCK or Z_TREES can be - used to force inflate() to return immediately after header processing is - complete and before any actual data is decompressed. - - The text, time, xflags, and os fields are filled in with the gzip header - contents. hcrc is set to true if there is a header CRC. (The header CRC - was valid if done is set to one.) If extra is not Z_NULL, then extra_max - contains the maximum number of bytes to write to extra. Once done is true, - extra_len contains the actual extra field length, and extra contains the - extra field, or that field truncated if extra_max is less than extra_len. - If name is not Z_NULL, then up to name_max characters are written there, - terminated with a zero unless the length is greater than name_max. If - comment is not Z_NULL, then up to comm_max characters are written there, - terminated with a zero unless the length is greater than comm_max. When any - of extra, name, or comment are not Z_NULL and the respective field is not - present in the header, then that field is set to Z_NULL to signal its - absence. This allows the use of deflateSetHeader() with the returned - structure to duplicate the header. However if those fields are set to - allocated memory, then the application will need to save those pointers - elsewhere so that they can be eventually freed. - - If inflateGetHeader is not used, then the header information is simply - discarded. The header is always checked for validity, including the header - CRC if present. inflateReset() will reset the process to discard the header - information. The application would need to call inflateGetHeader() again to - retrieve the header from the next gzip stream. - - inflateGetHeader returns Z_OK if success, or Z_STREAM_ERROR if the source - stream state was inconsistent. -*/ - -/* -ZEXTERN int ZEXPORT inflateBackInit OF((z_streamp strm, int windowBits, - unsigned char FAR *window)); - - Initialize the internal stream state for decompression using inflateBack() - calls. The fields zalloc, zfree and opaque in strm must be initialized - before the call. If zalloc and zfree are Z_NULL, then the default library- - derived memory allocation routines are used. windowBits is the base two - logarithm of the window size, in the range 8..15. window is a caller - supplied buffer of that size. Except for special applications where it is - assured that deflate was used with small window sizes, windowBits must be 15 - and a 32K byte window must be supplied to be able to decompress general - deflate streams. - - See inflateBack() for the usage of these routines. - - inflateBackInit will return Z_OK on success, Z_STREAM_ERROR if any of - the parameters are invalid, Z_MEM_ERROR if the internal state could not be - allocated, or Z_VERSION_ERROR if the version of the library does not match - the version of the header file. -*/ - -typedef unsigned (*in_func) OF((void FAR *, - z_const unsigned char FAR * FAR *)); -typedef int (*out_func) OF((void FAR *, unsigned char FAR *, unsigned)); - -ZEXTERN int ZEXPORT inflateBack OF((z_streamp strm, - in_func in, void FAR *in_desc, - out_func out, void FAR *out_desc)); -/* - inflateBack() does a raw inflate with a single call using a call-back - interface for input and output. This is potentially more efficient than - inflate() for file i/o applications, in that it avoids copying between the - output and the sliding window by simply making the window itself the output - buffer. inflate() can be faster on modern CPUs when used with large - buffers. inflateBack() trusts the application to not change the output - buffer passed by the output function, at least until inflateBack() returns. - - inflateBackInit() must be called first to allocate the internal state - and to initialize the state with the user-provided window buffer. - inflateBack() may then be used multiple times to inflate a complete, raw - deflate stream with each call. inflateBackEnd() is then called to free the - allocated state. - - A raw deflate stream is one with no zlib or gzip header or trailer. - This routine would normally be used in a utility that reads zip or gzip - files and writes out uncompressed files. The utility would decode the - header and process the trailer on its own, hence this routine expects only - the raw deflate stream to decompress. This is different from the default - behavior of inflate(), which expects a zlib header and trailer around the - deflate stream. - - inflateBack() uses two subroutines supplied by the caller that are then - called by inflateBack() for input and output. inflateBack() calls those - routines until it reads a complete deflate stream and writes out all of the - uncompressed data, or until it encounters an error. The function's - parameters and return types are defined above in the in_func and out_func - typedefs. inflateBack() will call in(in_desc, &buf) which should return the - number of bytes of provided input, and a pointer to that input in buf. If - there is no input available, in() must return zero -- buf is ignored in that - case -- and inflateBack() will return a buffer error. inflateBack() will - call out(out_desc, buf, len) to write the uncompressed data buf[0..len-1]. - out() should return zero on success, or non-zero on failure. If out() - returns non-zero, inflateBack() will return with an error. Neither in() nor - out() are permitted to change the contents of the window provided to - inflateBackInit(), which is also the buffer that out() uses to write from. - The length written by out() will be at most the window size. Any non-zero - amount of input may be provided by in(). - - For convenience, inflateBack() can be provided input on the first call by - setting strm->next_in and strm->avail_in. If that input is exhausted, then - in() will be called. Therefore strm->next_in must be initialized before - calling inflateBack(). If strm->next_in is Z_NULL, then in() will be called - immediately for input. If strm->next_in is not Z_NULL, then strm->avail_in - must also be initialized, and then if strm->avail_in is not zero, input will - initially be taken from strm->next_in[0 .. strm->avail_in - 1]. - - The in_desc and out_desc parameters of inflateBack() is passed as the - first parameter of in() and out() respectively when they are called. These - descriptors can be optionally used to pass any information that the caller- - supplied in() and out() functions need to do their job. - - On return, inflateBack() will set strm->next_in and strm->avail_in to - pass back any unused input that was provided by the last in() call. The - return values of inflateBack() can be Z_STREAM_END on success, Z_BUF_ERROR - if in() or out() returned an error, Z_DATA_ERROR if there was a format error - in the deflate stream (in which case strm->msg is set to indicate the nature - of the error), or Z_STREAM_ERROR if the stream was not properly initialized. - In the case of Z_BUF_ERROR, an input or output error can be distinguished - using strm->next_in which will be Z_NULL only if in() returned an error. If - strm->next_in is not Z_NULL, then the Z_BUF_ERROR was due to out() returning - non-zero. (in() will always be called before out(), so strm->next_in is - assured to be defined if out() returns non-zero.) Note that inflateBack() - cannot return Z_OK. -*/ - -ZEXTERN int ZEXPORT inflateBackEnd OF((z_streamp strm)); -/* - All memory allocated by inflateBackInit() is freed. - - inflateBackEnd() returns Z_OK on success, or Z_STREAM_ERROR if the stream - state was inconsistent. -*/ - -ZEXTERN uLong ZEXPORT zlibCompileFlags OF((void)); -/* Return flags indicating compile-time options. - - Type sizes, two bits each, 00 = 16 bits, 01 = 32, 10 = 64, 11 = other: - 1.0: size of uInt - 3.2: size of uLong - 5.4: size of voidpf (pointer) - 7.6: size of z_off_t - - Compiler, assembler, and debug options: - 8: ZLIB_DEBUG - 9: ASMV or ASMINF -- use ASM code - 10: ZLIB_WINAPI -- exported functions use the WINAPI calling convention - 11: 0 (reserved) - - One-time table building (smaller code, but not thread-safe if true): - 12: BUILDFIXED -- build static block decoding tables when needed - 13: DYNAMIC_CRC_TABLE -- build CRC calculation tables when needed - 14,15: 0 (reserved) - - Library content (indicates missing functionality): - 16: NO_GZCOMPRESS -- gz* functions cannot compress (to avoid linking - deflate code when not needed) - 17: NO_GZIP -- deflate can't write gzip streams, and inflate can't detect - and decode gzip streams (to avoid linking crc code) - 18-19: 0 (reserved) - - Operation variations (changes in library functionality): - 20: PKZIP_BUG_WORKAROUND -- slightly more permissive inflate - 21: FASTEST -- deflate algorithm with only one, lowest compression level - 22,23: 0 (reserved) - - The sprintf variant used by gzprintf (zero is best): - 24: 0 = vs*, 1 = s* -- 1 means limited to 20 arguments after the format - 25: 0 = *nprintf, 1 = *printf -- 1 means gzprintf() not secure! - 26: 0 = returns value, 1 = void -- 1 means inferred string length returned - - Remainder: - 27-31: 0 (reserved) - */ - -#ifndef Z_SOLO - - /* utility functions */ - -/* - The following utility functions are implemented on top of the basic - stream-oriented functions. To simplify the interface, some default options - are assumed (compression level and memory usage, standard memory allocation - functions). The source code of these utility functions can be modified if - you need special options. -*/ - -ZEXTERN int ZEXPORT compress OF((Bytef *dest, uLongf *destLen, - const Bytef *source, uLong sourceLen)); -/* - Compresses the source buffer into the destination buffer. sourceLen is - the byte length of the source buffer. Upon entry, destLen is the total size - of the destination buffer, which must be at least the value returned by - compressBound(sourceLen). Upon exit, destLen is the actual size of the - compressed data. compress() is equivalent to compress2() with a level - parameter of Z_DEFAULT_COMPRESSION. - - compress returns Z_OK if success, Z_MEM_ERROR if there was not - enough memory, Z_BUF_ERROR if there was not enough room in the output - buffer. -*/ - -ZEXTERN int ZEXPORT compress2 OF((Bytef *dest, uLongf *destLen, - const Bytef *source, uLong sourceLen, - int level)); -/* - Compresses the source buffer into the destination buffer. The level - parameter has the same meaning as in deflateInit. sourceLen is the byte - length of the source buffer. Upon entry, destLen is the total size of the - destination buffer, which must be at least the value returned by - compressBound(sourceLen). Upon exit, destLen is the actual size of the - compressed data. - - compress2 returns Z_OK if success, Z_MEM_ERROR if there was not enough - memory, Z_BUF_ERROR if there was not enough room in the output buffer, - Z_STREAM_ERROR if the level parameter is invalid. -*/ - -ZEXTERN uLong ZEXPORT compressBound OF((uLong sourceLen)); -/* - compressBound() returns an upper bound on the compressed size after - compress() or compress2() on sourceLen bytes. It would be used before a - compress() or compress2() call to allocate the destination buffer. -*/ - -ZEXTERN int ZEXPORT uncompress OF((Bytef *dest, uLongf *destLen, - const Bytef *source, uLong sourceLen)); -/* - Decompresses the source buffer into the destination buffer. sourceLen is - the byte length of the source buffer. Upon entry, destLen is the total size - of the destination buffer, which must be large enough to hold the entire - uncompressed data. (The size of the uncompressed data must have been saved - previously by the compressor and transmitted to the decompressor by some - mechanism outside the scope of this compression library.) Upon exit, destLen - is the actual size of the uncompressed data. - - uncompress returns Z_OK if success, Z_MEM_ERROR if there was not - enough memory, Z_BUF_ERROR if there was not enough room in the output - buffer, or Z_DATA_ERROR if the input data was corrupted or incomplete. In - the case where there is not enough room, uncompress() will fill the output - buffer with the uncompressed data up to that point. -*/ - -ZEXTERN int ZEXPORT uncompress2 OF((Bytef *dest, uLongf *destLen, - const Bytef *source, uLong *sourceLen)); -/* - Same as uncompress, except that sourceLen is a pointer, where the - length of the source is *sourceLen. On return, *sourceLen is the number of - source bytes consumed. -*/ - - /* gzip file access functions */ - -/* - This library supports reading and writing files in gzip (.gz) format with - an interface similar to that of stdio, using the functions that start with - "gz". The gzip format is different from the zlib format. gzip is a gzip - wrapper, documented in RFC 1952, wrapped around a deflate stream. -*/ - -typedef struct gzFile_s *gzFile; /* semi-opaque gzip file descriptor */ - -/* -ZEXTERN gzFile ZEXPORT gzopen OF((const char *path, const char *mode)); - - Opens a gzip (.gz) file for reading or writing. The mode parameter is as - in fopen ("rb" or "wb") but can also include a compression level ("wb9") or - a strategy: 'f' for filtered data as in "wb6f", 'h' for Huffman-only - compression as in "wb1h", 'R' for run-length encoding as in "wb1R", or 'F' - for fixed code compression as in "wb9F". (See the description of - deflateInit2 for more information about the strategy parameter.) 'T' will - request transparent writing or appending with no compression and not using - the gzip format. - - "a" can be used instead of "w" to request that the gzip stream that will - be written be appended to the file. "+" will result in an error, since - reading and writing to the same gzip file is not supported. The addition of - "x" when writing will create the file exclusively, which fails if the file - already exists. On systems that support it, the addition of "e" when - reading or writing will set the flag to close the file on an execve() call. - - These functions, as well as gzip, will read and decode a sequence of gzip - streams in a file. The append function of gzopen() can be used to create - such a file. (Also see gzflush() for another way to do this.) When - appending, gzopen does not test whether the file begins with a gzip stream, - nor does it look for the end of the gzip streams to begin appending. gzopen - will simply append a gzip stream to the existing file. - - gzopen can be used to read a file which is not in gzip format; in this - case gzread will directly read from the file without decompression. When - reading, this will be detected automatically by looking for the magic two- - byte gzip header. - - gzopen returns NULL if the file could not be opened, if there was - insufficient memory to allocate the gzFile state, or if an invalid mode was - specified (an 'r', 'w', or 'a' was not provided, or '+' was provided). - errno can be checked to determine if the reason gzopen failed was that the - file could not be opened. -*/ - -ZEXTERN gzFile ZEXPORT gzdopen OF((int fd, const char *mode)); -/* - gzdopen associates a gzFile with the file descriptor fd. File descriptors - are obtained from calls like open, dup, creat, pipe or fileno (if the file - has been previously opened with fopen). The mode parameter is as in gzopen. - - The next call of gzclose on the returned gzFile will also close the file - descriptor fd, just like fclose(fdopen(fd, mode)) closes the file descriptor - fd. If you want to keep fd open, use fd = dup(fd_keep); gz = gzdopen(fd, - mode);. The duplicated descriptor should be saved to avoid a leak, since - gzdopen does not close fd if it fails. If you are using fileno() to get the - file descriptor from a FILE *, then you will have to use dup() to avoid - double-close()ing the file descriptor. Both gzclose() and fclose() will - close the associated file descriptor, so they need to have different file - descriptors. - - gzdopen returns NULL if there was insufficient memory to allocate the - gzFile state, if an invalid mode was specified (an 'r', 'w', or 'a' was not - provided, or '+' was provided), or if fd is -1. The file descriptor is not - used until the next gz* read, write, seek, or close operation, so gzdopen - will not detect if fd is invalid (unless fd is -1). -*/ - -ZEXTERN int ZEXPORT gzbuffer OF((gzFile file, unsigned size)); -/* - Set the internal buffer size used by this library's functions. The - default buffer size is 8192 bytes. This function must be called after - gzopen() or gzdopen(), and before any other calls that read or write the - file. The buffer memory allocation is always deferred to the first read or - write. Three times that size in buffer space is allocated. A larger buffer - size of, for example, 64K or 128K bytes will noticeably increase the speed - of decompression (reading). - - The new buffer size also affects the maximum length for gzprintf(). - - gzbuffer() returns 0 on success, or -1 on failure, such as being called - too late. -*/ - -ZEXTERN int ZEXPORT gzsetparams OF((gzFile file, int level, int strategy)); -/* - Dynamically update the compression level or strategy. See the description - of deflateInit2 for the meaning of these parameters. Previously provided - data is flushed before the parameter change. - - gzsetparams returns Z_OK if success, Z_STREAM_ERROR if the file was not - opened for writing, Z_ERRNO if there is an error writing the flushed data, - or Z_MEM_ERROR if there is a memory allocation error. -*/ - -ZEXTERN int ZEXPORT gzread OF((gzFile file, voidp buf, unsigned len)); -/* - Reads the given number of uncompressed bytes from the compressed file. If - the input file is not in gzip format, gzread copies the given number of - bytes into the buffer directly from the file. - - After reaching the end of a gzip stream in the input, gzread will continue - to read, looking for another gzip stream. Any number of gzip streams may be - concatenated in the input file, and will all be decompressed by gzread(). - If something other than a gzip stream is encountered after a gzip stream, - that remaining trailing garbage is ignored (and no error is returned). - - gzread can be used to read a gzip file that is being concurrently written. - Upon reaching the end of the input, gzread will return with the available - data. If the error code returned by gzerror is Z_OK or Z_BUF_ERROR, then - gzclearerr can be used to clear the end of file indicator in order to permit - gzread to be tried again. Z_OK indicates that a gzip stream was completed - on the last gzread. Z_BUF_ERROR indicates that the input file ended in the - middle of a gzip stream. Note that gzread does not return -1 in the event - of an incomplete gzip stream. This error is deferred until gzclose(), which - will return Z_BUF_ERROR if the last gzread ended in the middle of a gzip - stream. Alternatively, gzerror can be used before gzclose to detect this - case. - - gzread returns the number of uncompressed bytes actually read, less than - len for end of file, or -1 for error. If len is too large to fit in an int, - then nothing is read, -1 is returned, and the error state is set to - Z_STREAM_ERROR. -*/ - -ZEXTERN z_size_t ZEXPORT gzfread OF((voidp buf, z_size_t size, z_size_t nitems, - gzFile file)); -/* - Read up to nitems items of size size from file to buf, otherwise operating - as gzread() does. This duplicates the interface of stdio's fread(), with - size_t request and return types. If the library defines size_t, then - z_size_t is identical to size_t. If not, then z_size_t is an unsigned - integer type that can contain a pointer. - - gzfread() returns the number of full items read of size size, or zero if - the end of the file was reached and a full item could not be read, or if - there was an error. gzerror() must be consulted if zero is returned in - order to determine if there was an error. If the multiplication of size and - nitems overflows, i.e. the product does not fit in a z_size_t, then nothing - is read, zero is returned, and the error state is set to Z_STREAM_ERROR. - - In the event that the end of file is reached and only a partial item is - available at the end, i.e. the remaining uncompressed data length is not a - multiple of size, then the final partial item is nevetheless read into buf - and the end-of-file flag is set. The length of the partial item read is not - provided, but could be inferred from the result of gztell(). This behavior - is the same as the behavior of fread() implementations in common libraries, - but it prevents the direct use of gzfread() to read a concurrently written - file, reseting and retrying on end-of-file, when size is not 1. -*/ - -ZEXTERN int ZEXPORT gzwrite OF((gzFile file, - voidpc buf, unsigned len)); -/* - Writes the given number of uncompressed bytes into the compressed file. - gzwrite returns the number of uncompressed bytes written or 0 in case of - error. -*/ - -ZEXTERN z_size_t ZEXPORT gzfwrite OF((voidpc buf, z_size_t size, - z_size_t nitems, gzFile file)); -/* - gzfwrite() writes nitems items of size size from buf to file, duplicating - the interface of stdio's fwrite(), with size_t request and return types. If - the library defines size_t, then z_size_t is identical to size_t. If not, - then z_size_t is an unsigned integer type that can contain a pointer. - - gzfwrite() returns the number of full items written of size size, or zero - if there was an error. If the multiplication of size and nitems overflows, - i.e. the product does not fit in a z_size_t, then nothing is written, zero - is returned, and the error state is set to Z_STREAM_ERROR. -*/ - -ZEXTERN int ZEXPORTVA gzprintf Z_ARG((gzFile file, const char *format, ...)); -/* - Converts, formats, and writes the arguments to the compressed file under - control of the format string, as in fprintf. gzprintf returns the number of - uncompressed bytes actually written, or a negative zlib error code in case - of error. The number of uncompressed bytes written is limited to 8191, or - one less than the buffer size given to gzbuffer(). The caller should assure - that this limit is not exceeded. If it is exceeded, then gzprintf() will - return an error (0) with nothing written. In this case, there may also be a - buffer overflow with unpredictable consequences, which is possible only if - zlib was compiled with the insecure functions sprintf() or vsprintf() - because the secure snprintf() or vsnprintf() functions were not available. - This can be determined using zlibCompileFlags(). -*/ - -ZEXTERN int ZEXPORT gzputs OF((gzFile file, const char *s)); -/* - Writes the given null-terminated string to the compressed file, excluding - the terminating null character. - - gzputs returns the number of characters written, or -1 in case of error. -*/ - -ZEXTERN char * ZEXPORT gzgets OF((gzFile file, char *buf, int len)); -/* - Reads bytes from the compressed file until len-1 characters are read, or a - newline character is read and transferred to buf, or an end-of-file - condition is encountered. If any characters are read or if len == 1, the - string is terminated with a null character. If no characters are read due - to an end-of-file or len < 1, then the buffer is left untouched. - - gzgets returns buf which is a null-terminated string, or it returns NULL - for end-of-file or in case of error. If there was an error, the contents at - buf are indeterminate. -*/ - -ZEXTERN int ZEXPORT gzputc OF((gzFile file, int c)); -/* - Writes c, converted to an unsigned char, into the compressed file. gzputc - returns the value that was written, or -1 in case of error. -*/ - -ZEXTERN int ZEXPORT gzgetc OF((gzFile file)); -/* - Reads one byte from the compressed file. gzgetc returns this byte or -1 - in case of end of file or error. This is implemented as a macro for speed. - As such, it does not do all of the checking the other functions do. I.e. - it does not check to see if file is NULL, nor whether the structure file - points to has been clobbered or not. -*/ - -ZEXTERN int ZEXPORT gzungetc OF((int c, gzFile file)); -/* - Push one character back onto the stream to be read as the first character - on the next read. At least one character of push-back is allowed. - gzungetc() returns the character pushed, or -1 on failure. gzungetc() will - fail if c is -1, and may fail if a character has been pushed but not read - yet. If gzungetc is used immediately after gzopen or gzdopen, at least the - output buffer size of pushed characters is allowed. (See gzbuffer above.) - The pushed character will be discarded if the stream is repositioned with - gzseek() or gzrewind(). -*/ - -ZEXTERN int ZEXPORT gzflush OF((gzFile file, int flush)); -/* - Flushes all pending output into the compressed file. The parameter flush - is as in the deflate() function. The return value is the zlib error number - (see function gzerror below). gzflush is only permitted when writing. - - If the flush parameter is Z_FINISH, the remaining data is written and the - gzip stream is completed in the output. If gzwrite() is called again, a new - gzip stream will be started in the output. gzread() is able to read such - concatenated gzip streams. - - gzflush should be called only when strictly necessary because it will - degrade compression if called too often. -*/ - -/* -ZEXTERN z_off_t ZEXPORT gzseek OF((gzFile file, - z_off_t offset, int whence)); - - Sets the starting position for the next gzread or gzwrite on the given - compressed file. The offset represents a number of bytes in the - uncompressed data stream. The whence parameter is defined as in lseek(2); - the value SEEK_END is not supported. - - If the file is opened for reading, this function is emulated but can be - extremely slow. If the file is opened for writing, only forward seeks are - supported; gzseek then compresses a sequence of zeroes up to the new - starting position. - - gzseek returns the resulting offset location as measured in bytes from - the beginning of the uncompressed stream, or -1 in case of error, in - particular if the file is opened for writing and the new starting position - would be before the current position. -*/ - -ZEXTERN int ZEXPORT gzrewind OF((gzFile file)); -/* - Rewinds the given file. This function is supported only for reading. - - gzrewind(file) is equivalent to (int)gzseek(file, 0L, SEEK_SET) -*/ - -/* -ZEXTERN z_off_t ZEXPORT gztell OF((gzFile file)); - - Returns the starting position for the next gzread or gzwrite on the given - compressed file. This position represents a number of bytes in the - uncompressed data stream, and is zero when starting, even if appending or - reading a gzip stream from the middle of a file using gzdopen(). - - gztell(file) is equivalent to gzseek(file, 0L, SEEK_CUR) -*/ - -/* -ZEXTERN z_off_t ZEXPORT gzoffset OF((gzFile file)); - - Returns the current offset in the file being read or written. This offset - includes the count of bytes that precede the gzip stream, for example when - appending or when using gzdopen() for reading. When reading, the offset - does not include as yet unused buffered input. This information can be used - for a progress indicator. On error, gzoffset() returns -1. -*/ - -ZEXTERN int ZEXPORT gzeof OF((gzFile file)); -/* - Returns true (1) if the end-of-file indicator has been set while reading, - false (0) otherwise. Note that the end-of-file indicator is set only if the - read tried to go past the end of the input, but came up short. Therefore, - just like feof(), gzeof() may return false even if there is no more data to - read, in the event that the last read request was for the exact number of - bytes remaining in the input file. This will happen if the input file size - is an exact multiple of the buffer size. - - If gzeof() returns true, then the read functions will return no more data, - unless the end-of-file indicator is reset by gzclearerr() and the input file - has grown since the previous end of file was detected. -*/ - -ZEXTERN int ZEXPORT gzdirect OF((gzFile file)); -/* - Returns true (1) if file is being copied directly while reading, or false - (0) if file is a gzip stream being decompressed. - - If the input file is empty, gzdirect() will return true, since the input - does not contain a gzip stream. - - If gzdirect() is used immediately after gzopen() or gzdopen() it will - cause buffers to be allocated to allow reading the file to determine if it - is a gzip file. Therefore if gzbuffer() is used, it should be called before - gzdirect(). - - When writing, gzdirect() returns true (1) if transparent writing was - requested ("wT" for the gzopen() mode), or false (0) otherwise. (Note: - gzdirect() is not needed when writing. Transparent writing must be - explicitly requested, so the application already knows the answer. When - linking statically, using gzdirect() will include all of the zlib code for - gzip file reading and decompression, which may not be desired.) -*/ - -ZEXTERN int ZEXPORT gzclose OF((gzFile file)); -/* - Flushes all pending output if necessary, closes the compressed file and - deallocates the (de)compression state. Note that once file is closed, you - cannot call gzerror with file, since its structures have been deallocated. - gzclose must not be called more than once on the same file, just as free - must not be called more than once on the same allocation. - - gzclose will return Z_STREAM_ERROR if file is not valid, Z_ERRNO on a - file operation error, Z_MEM_ERROR if out of memory, Z_BUF_ERROR if the - last read ended in the middle of a gzip stream, or Z_OK on success. -*/ - -ZEXTERN int ZEXPORT gzclose_r OF((gzFile file)); -ZEXTERN int ZEXPORT gzclose_w OF((gzFile file)); -/* - Same as gzclose(), but gzclose_r() is only for use when reading, and - gzclose_w() is only for use when writing or appending. The advantage to - using these instead of gzclose() is that they avoid linking in zlib - compression or decompression code that is not used when only reading or only - writing respectively. If gzclose() is used, then both compression and - decompression code will be included the application when linking to a static - zlib library. -*/ - -ZEXTERN const char * ZEXPORT gzerror OF((gzFile file, int *errnum)); -/* - Returns the error message for the last error which occurred on the given - compressed file. errnum is set to zlib error number. If an error occurred - in the file system and not in the compression library, errnum is set to - Z_ERRNO and the application may consult errno to get the exact error code. - - The application must not modify the returned string. Future calls to - this function may invalidate the previously returned string. If file is - closed, then the string previously returned by gzerror will no longer be - available. - - gzerror() should be used to distinguish errors from end-of-file for those - functions above that do not distinguish those cases in their return values. -*/ - -ZEXTERN void ZEXPORT gzclearerr OF((gzFile file)); -/* - Clears the error and end-of-file flags for file. This is analogous to the - clearerr() function in stdio. This is useful for continuing to read a gzip - file that is being written concurrently. -*/ - -#endif /* !Z_SOLO */ - - /* checksum functions */ - -/* - These functions are not related to compression but are exported - anyway because they might be useful in applications using the compression - library. -*/ - -ZEXTERN uLong ZEXPORT adler32 OF((uLong adler, const Bytef *buf, uInt len)); -/* - Update a running Adler-32 checksum with the bytes buf[0..len-1] and - return the updated checksum. If buf is Z_NULL, this function returns the - required initial value for the checksum. - - An Adler-32 checksum is almost as reliable as a CRC-32 but can be computed - much faster. - - Usage example: - - uLong adler = adler32(0L, Z_NULL, 0); - - while (read_buffer(buffer, length) != EOF) { - adler = adler32(adler, buffer, length); - } - if (adler != original_adler) error(); -*/ - -ZEXTERN uLong ZEXPORT adler32_z OF((uLong adler, const Bytef *buf, - z_size_t len)); -/* - Same as adler32(), but with a size_t length. -*/ - -/* -ZEXTERN uLong ZEXPORT adler32_combine OF((uLong adler1, uLong adler2, - z_off_t len2)); - - Combine two Adler-32 checksums into one. For two sequences of bytes, seq1 - and seq2 with lengths len1 and len2, Adler-32 checksums were calculated for - each, adler1 and adler2. adler32_combine() returns the Adler-32 checksum of - seq1 and seq2 concatenated, requiring only adler1, adler2, and len2. Note - that the z_off_t type (like off_t) is a signed integer. If len2 is - negative, the result has no meaning or utility. -*/ - -ZEXTERN uLong ZEXPORT crc32 OF((uLong crc, const Bytef *buf, uInt len)); -/* - Update a running CRC-32 with the bytes buf[0..len-1] and return the - updated CRC-32. If buf is Z_NULL, this function returns the required - initial value for the crc. Pre- and post-conditioning (one's complement) is - performed within this function so it shouldn't be done by the application. - - Usage example: - - uLong crc = crc32(0L, Z_NULL, 0); - - while (read_buffer(buffer, length) != EOF) { - crc = crc32(crc, buffer, length); - } - if (crc != original_crc) error(); -*/ - -ZEXTERN uLong ZEXPORT crc32_z OF((uLong adler, const Bytef *buf, - z_size_t len)); -/* - Same as crc32(), but with a size_t length. -*/ - -/* -ZEXTERN uLong ZEXPORT crc32_combine OF((uLong crc1, uLong crc2, z_off_t len2)); - - Combine two CRC-32 check values into one. For two sequences of bytes, - seq1 and seq2 with lengths len1 and len2, CRC-32 check values were - calculated for each, crc1 and crc2. crc32_combine() returns the CRC-32 - check value of seq1 and seq2 concatenated, requiring only crc1, crc2, and - len2. -*/ - - - /* various hacks, don't look :) */ - -/* deflateInit and inflateInit are macros to allow checking the zlib version - * and the compiler's view of z_stream: - */ -ZEXTERN int ZEXPORT deflateInit_ OF((z_streamp strm, int level, - const char *version, int stream_size)); -ZEXTERN int ZEXPORT inflateInit_ OF((z_streamp strm, - const char *version, int stream_size)); -ZEXTERN int ZEXPORT deflateInit2_ OF((z_streamp strm, int level, int method, - int windowBits, int memLevel, - int strategy, const char *version, - int stream_size)); -ZEXTERN int ZEXPORT inflateInit2_ OF((z_streamp strm, int windowBits, - const char *version, int stream_size)); -ZEXTERN int ZEXPORT inflateBackInit_ OF((z_streamp strm, int windowBits, - unsigned char FAR *window, - const char *version, - int stream_size)); -#ifdef Z_PREFIX_SET -# define z_deflateInit(strm, level) \ - deflateInit_((strm), (level), ZLIB_VERSION, (int)sizeof(z_stream)) -# define z_inflateInit(strm) \ - inflateInit_((strm), ZLIB_VERSION, (int)sizeof(z_stream)) -# define z_deflateInit2(strm, level, method, windowBits, memLevel, strategy) \ - deflateInit2_((strm),(level),(method),(windowBits),(memLevel),\ - (strategy), ZLIB_VERSION, (int)sizeof(z_stream)) -# define z_inflateInit2(strm, windowBits) \ - inflateInit2_((strm), (windowBits), ZLIB_VERSION, \ - (int)sizeof(z_stream)) -# define z_inflateBackInit(strm, windowBits, window) \ - inflateBackInit_((strm), (windowBits), (window), \ - ZLIB_VERSION, (int)sizeof(z_stream)) -#else -# define deflateInit(strm, level) \ - deflateInit_((strm), (level), ZLIB_VERSION, (int)sizeof(z_stream)) -# define inflateInit(strm) \ - inflateInit_((strm), ZLIB_VERSION, (int)sizeof(z_stream)) -# define deflateInit2(strm, level, method, windowBits, memLevel, strategy) \ - deflateInit2_((strm),(level),(method),(windowBits),(memLevel),\ - (strategy), ZLIB_VERSION, (int)sizeof(z_stream)) -# define inflateInit2(strm, windowBits) \ - inflateInit2_((strm), (windowBits), ZLIB_VERSION, \ - (int)sizeof(z_stream)) -# define inflateBackInit(strm, windowBits, window) \ - inflateBackInit_((strm), (windowBits), (window), \ - ZLIB_VERSION, (int)sizeof(z_stream)) -#endif - -#ifndef Z_SOLO - -/* gzgetc() macro and its supporting function and exposed data structure. Note - * that the real internal state is much larger than the exposed structure. - * This abbreviated structure exposes just enough for the gzgetc() macro. The - * user should not mess with these exposed elements, since their names or - * behavior could change in the future, perhaps even capriciously. They can - * only be used by the gzgetc() macro. You have been warned. - */ -struct gzFile_s { - unsigned have; - unsigned char *next; - z_off64_t pos; -}; -ZEXTERN int ZEXPORT gzgetc_ OF((gzFile file)); /* backward compatibility */ -#ifdef Z_PREFIX_SET -# undef z_gzgetc -# define z_gzgetc(g) \ - ((g)->have ? ((g)->have--, (g)->pos++, *((g)->next)++) : (gzgetc)(g)) -#else -# define gzgetc(g) \ - ((g)->have ? ((g)->have--, (g)->pos++, *((g)->next)++) : (gzgetc)(g)) -#endif - -/* provide 64-bit offset functions if _LARGEFILE64_SOURCE defined, and/or - * change the regular functions to 64 bits if _FILE_OFFSET_BITS is 64 (if - * both are true, the application gets the *64 functions, and the regular - * functions are changed to 64 bits) -- in case these are set on systems - * without large file support, _LFS64_LARGEFILE must also be true - */ -#ifdef Z_LARGE64 - ZEXTERN gzFile ZEXPORT gzopen64 OF((const char *, const char *)); - ZEXTERN z_off64_t ZEXPORT gzseek64 OF((gzFile, z_off64_t, int)); - ZEXTERN z_off64_t ZEXPORT gztell64 OF((gzFile)); - ZEXTERN z_off64_t ZEXPORT gzoffset64 OF((gzFile)); - ZEXTERN uLong ZEXPORT adler32_combine64 OF((uLong, uLong, z_off64_t)); - ZEXTERN uLong ZEXPORT crc32_combine64 OF((uLong, uLong, z_off64_t)); -#endif - -#if !defined(ZLIB_INTERNAL) && defined(Z_WANT64) -# ifdef Z_PREFIX_SET -# define z_gzopen z_gzopen64 -# define z_gzseek z_gzseek64 -# define z_gztell z_gztell64 -# define z_gzoffset z_gzoffset64 -# define z_adler32_combine z_adler32_combine64 -# define z_crc32_combine z_crc32_combine64 -# else -# define gzopen gzopen64 -# define gzseek gzseek64 -# define gztell gztell64 -# define gzoffset gzoffset64 -# define adler32_combine adler32_combine64 -# define crc32_combine crc32_combine64 -# endif -# ifndef Z_LARGE64 - ZEXTERN gzFile ZEXPORT gzopen64 OF((const char *, const char *)); - ZEXTERN z_off_t ZEXPORT gzseek64 OF((gzFile, z_off_t, int)); - ZEXTERN z_off_t ZEXPORT gztell64 OF((gzFile)); - ZEXTERN z_off_t ZEXPORT gzoffset64 OF((gzFile)); - ZEXTERN uLong ZEXPORT adler32_combine64 OF((uLong, uLong, z_off_t)); - ZEXTERN uLong ZEXPORT crc32_combine64 OF((uLong, uLong, z_off_t)); -# endif -#else - ZEXTERN gzFile ZEXPORT gzopen OF((const char *, const char *)); - ZEXTERN z_off_t ZEXPORT gzseek OF((gzFile, z_off_t, int)); - ZEXTERN z_off_t ZEXPORT gztell OF((gzFile)); - ZEXTERN z_off_t ZEXPORT gzoffset OF((gzFile)); - ZEXTERN uLong ZEXPORT adler32_combine OF((uLong, uLong, z_off_t)); - ZEXTERN uLong ZEXPORT crc32_combine OF((uLong, uLong, z_off_t)); -#endif - -#else /* Z_SOLO */ - - ZEXTERN uLong ZEXPORT adler32_combine OF((uLong, uLong, z_off_t)); - ZEXTERN uLong ZEXPORT crc32_combine OF((uLong, uLong, z_off_t)); - -#endif /* !Z_SOLO */ - -/* undocumented functions */ -ZEXTERN const char * ZEXPORT zError OF((int)); -ZEXTERN int ZEXPORT inflateSyncPoint OF((z_streamp)); -ZEXTERN const z_crc_t FAR * ZEXPORT get_crc_table OF((void)); -ZEXTERN int ZEXPORT inflateUndermine OF((z_streamp, int)); -ZEXTERN int ZEXPORT inflateValidate OF((z_streamp, int)); -ZEXTERN unsigned long ZEXPORT inflateCodesUsed OF ((z_streamp)); -ZEXTERN int ZEXPORT inflateResetKeep OF((z_streamp)); -ZEXTERN int ZEXPORT deflateResetKeep OF((z_streamp)); -#if (defined(_WIN32) || defined(__CYGWIN__)) && !defined(Z_SOLO) -ZEXTERN gzFile ZEXPORT gzopen_w OF((const wchar_t *path, - const char *mode)); -#endif -#if defined(STDC) || defined(Z_HAVE_STDARG_H) -# ifndef Z_SOLO -ZEXTERN int ZEXPORTVA gzvprintf Z_ARG((gzFile file, - const char *format, - va_list va)); -# endif -#endif - -#ifdef __cplusplus -} -#endif - -#endif /* ZLIB_H */ diff --git a/deps/zlib/zutil.c b/deps/zlib/zutil.c deleted file mode 100644 index a76c6b0..0000000 --- a/deps/zlib/zutil.c +++ /dev/null @@ -1,325 +0,0 @@ -/* zutil.c -- target dependent utility functions for the compression library - * Copyright (C) 1995-2017 Jean-loup Gailly - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -/* @(#) $Id$ */ - -#include "zutil.h" -#ifndef Z_SOLO -# include "gzguts.h" -#endif - -z_const char * const z_errmsg[10] = { - (z_const char *)"need dictionary", /* Z_NEED_DICT 2 */ - (z_const char *)"stream end", /* Z_STREAM_END 1 */ - (z_const char *)"", /* Z_OK 0 */ - (z_const char *)"file error", /* Z_ERRNO (-1) */ - (z_const char *)"stream error", /* Z_STREAM_ERROR (-2) */ - (z_const char *)"data error", /* Z_DATA_ERROR (-3) */ - (z_const char *)"insufficient memory", /* Z_MEM_ERROR (-4) */ - (z_const char *)"buffer error", /* Z_BUF_ERROR (-5) */ - (z_const char *)"incompatible version",/* Z_VERSION_ERROR (-6) */ - (z_const char *)"" -}; - - -const char * ZEXPORT zlibVersion() -{ - return ZLIB_VERSION; -} - -uLong ZEXPORT zlibCompileFlags() -{ - uLong flags; - - flags = 0; - switch ((int)(sizeof(uInt))) { - case 2: break; - case 4: flags += 1; break; - case 8: flags += 2; break; - default: flags += 3; - } - switch ((int)(sizeof(uLong))) { - case 2: break; - case 4: flags += 1 << 2; break; - case 8: flags += 2 << 2; break; - default: flags += 3 << 2; - } - switch ((int)(sizeof(voidpf))) { - case 2: break; - case 4: flags += 1 << 4; break; - case 8: flags += 2 << 4; break; - default: flags += 3 << 4; - } - switch ((int)(sizeof(z_off_t))) { - case 2: break; - case 4: flags += 1 << 6; break; - case 8: flags += 2 << 6; break; - default: flags += 3 << 6; - } -#ifdef ZLIB_DEBUG - flags += 1 << 8; -#endif -#if defined(ASMV) || defined(ASMINF) - flags += 1 << 9; -#endif -#ifdef ZLIB_WINAPI - flags += 1 << 10; -#endif -#ifdef BUILDFIXED - flags += 1 << 12; -#endif -#ifdef DYNAMIC_CRC_TABLE - flags += 1 << 13; -#endif -#ifdef NO_GZCOMPRESS - flags += 1L << 16; -#endif -#ifdef NO_GZIP - flags += 1L << 17; -#endif -#ifdef PKZIP_BUG_WORKAROUND - flags += 1L << 20; -#endif -#ifdef FASTEST - flags += 1L << 21; -#endif -#if defined(STDC) || defined(Z_HAVE_STDARG_H) -# ifdef NO_vsnprintf - flags += 1L << 25; -# ifdef HAS_vsprintf_void - flags += 1L << 26; -# endif -# else -# ifdef HAS_vsnprintf_void - flags += 1L << 26; -# endif -# endif -#else - flags += 1L << 24; -# ifdef NO_snprintf - flags += 1L << 25; -# ifdef HAS_sprintf_void - flags += 1L << 26; -# endif -# else -# ifdef HAS_snprintf_void - flags += 1L << 26; -# endif -# endif -#endif - return flags; -} - -#ifdef ZLIB_DEBUG -#include -# ifndef verbose -# define verbose 0 -# endif -int ZLIB_INTERNAL z_verbose = verbose; - -void ZLIB_INTERNAL z_error (m) - char *m; -{ - fprintf(stderr, "%s\n", m); - exit(1); -} -#endif - -/* exported to allow conversion of error code to string for compress() and - * uncompress() - */ -const char * ZEXPORT zError(err) - int err; -{ - return ERR_MSG(err); -} - -#if defined(_WIN32_WCE) - /* The Microsoft C Run-Time Library for Windows CE doesn't have - * errno. We define it as a global variable to simplify porting. - * Its value is always 0 and should not be used. - */ - int errno = 0; -#endif - -#ifndef HAVE_MEMCPY - -void ZLIB_INTERNAL zmemcpy(dest, source, len) - Bytef* dest; - const Bytef* source; - uInt len; -{ - if (len == 0) return; - do { - *dest++ = *source++; /* ??? to be unrolled */ - } while (--len != 0); -} - -int ZLIB_INTERNAL zmemcmp(s1, s2, len) - const Bytef* s1; - const Bytef* s2; - uInt len; -{ - uInt j; - - for (j = 0; j < len; j++) { - if (s1[j] != s2[j]) return 2*(s1[j] > s2[j])-1; - } - return 0; -} - -void ZLIB_INTERNAL zmemzero(dest, len) - Bytef* dest; - uInt len; -{ - if (len == 0) return; - do { - *dest++ = 0; /* ??? to be unrolled */ - } while (--len != 0); -} -#endif - -#ifndef Z_SOLO - -#ifdef SYS16BIT - -#ifdef __TURBOC__ -/* Turbo C in 16-bit mode */ - -# define MY_ZCALLOC - -/* Turbo C malloc() does not allow dynamic allocation of 64K bytes - * and farmalloc(64K) returns a pointer with an offset of 8, so we - * must fix the pointer. Warning: the pointer must be put back to its - * original form in order to free it, use zcfree(). - */ - -#define MAX_PTR 10 -/* 10*64K = 640K */ - -local int next_ptr = 0; - -typedef struct ptr_table_s { - voidpf org_ptr; - voidpf new_ptr; -} ptr_table; - -local ptr_table table[MAX_PTR]; -/* This table is used to remember the original form of pointers - * to large buffers (64K). Such pointers are normalized with a zero offset. - * Since MSDOS is not a preemptive multitasking OS, this table is not - * protected from concurrent access. This hack doesn't work anyway on - * a protected system like OS/2. Use Microsoft C instead. - */ - -voidpf ZLIB_INTERNAL zcalloc (voidpf opaque, unsigned items, unsigned size) -{ - voidpf buf; - ulg bsize = (ulg)items*size; - - (void)opaque; - - /* If we allocate less than 65520 bytes, we assume that farmalloc - * will return a usable pointer which doesn't have to be normalized. - */ - if (bsize < 65520L) { - buf = farmalloc(bsize); - if (*(ush*)&buf != 0) return buf; - } else { - buf = farmalloc(bsize + 16L); - } - if (buf == NULL || next_ptr >= MAX_PTR) return NULL; - table[next_ptr].org_ptr = buf; - - /* Normalize the pointer to seg:0 */ - *((ush*)&buf+1) += ((ush)((uch*)buf-0) + 15) >> 4; - *(ush*)&buf = 0; - table[next_ptr++].new_ptr = buf; - return buf; -} - -void ZLIB_INTERNAL zcfree (voidpf opaque, voidpf ptr) -{ - int n; - - (void)opaque; - - if (*(ush*)&ptr != 0) { /* object < 64K */ - farfree(ptr); - return; - } - /* Find the original pointer */ - for (n = 0; n < next_ptr; n++) { - if (ptr != table[n].new_ptr) continue; - - farfree(table[n].org_ptr); - while (++n < next_ptr) { - table[n-1] = table[n]; - } - next_ptr--; - return; - } - Assert(0, "zcfree: ptr not found"); -} - -#endif /* __TURBOC__ */ - - -#ifdef M_I86 -/* Microsoft C in 16-bit mode */ - -# define MY_ZCALLOC - -#if (!defined(_MSC_VER) || (_MSC_VER <= 600)) -# define _halloc halloc -# define _hfree hfree -#endif - -voidpf ZLIB_INTERNAL zcalloc (voidpf opaque, uInt items, uInt size) -{ - (void)opaque; - return _halloc((long)items, size); -} - -void ZLIB_INTERNAL zcfree (voidpf opaque, voidpf ptr) -{ - (void)opaque; - _hfree(ptr); -} - -#endif /* M_I86 */ - -#endif /* SYS16BIT */ - - -#ifndef MY_ZCALLOC /* Any system without a special alloc function */ - -#ifndef STDC -extern voidp malloc OF((uInt size)); -extern voidp calloc OF((uInt items, uInt size)); -extern void free OF((voidpf ptr)); -#endif - -voidpf ZLIB_INTERNAL zcalloc (opaque, items, size) - voidpf opaque; - unsigned items; - unsigned size; -{ - (void)opaque; - return sizeof(uInt) > 2 ? (voidpf)malloc(items * size) : - (voidpf)calloc(items, size); -} - -void ZLIB_INTERNAL zcfree (opaque, ptr) - voidpf opaque; - voidpf ptr; -{ - (void)opaque; - free(ptr); -} - -#endif /* MY_ZCALLOC */ - -#endif /* !Z_SOLO */ diff --git a/deps/zlib/zutil.h b/deps/zlib/zutil.h deleted file mode 100644 index b079ea6..0000000 --- a/deps/zlib/zutil.h +++ /dev/null @@ -1,271 +0,0 @@ -/* zutil.h -- internal interface and configuration of the compression library - * Copyright (C) 1995-2016 Jean-loup Gailly, Mark Adler - * For conditions of distribution and use, see copyright notice in zlib.h - */ - -/* WARNING: this file should *not* be used by applications. It is - part of the implementation of the compression library and is - subject to change. Applications should only use zlib.h. - */ - -/* @(#) $Id$ */ - -#ifndef ZUTIL_H -#define ZUTIL_H - -#ifdef HAVE_HIDDEN -# define ZLIB_INTERNAL __attribute__((visibility ("hidden"))) -#else -# define ZLIB_INTERNAL -#endif - -#include "zlib.h" - -#if defined(STDC) && !defined(Z_SOLO) -# if !(defined(_WIN32_WCE) && defined(_MSC_VER)) -# include -# endif -# include -# include -#endif - -#ifdef Z_SOLO - typedef long ptrdiff_t; /* guess -- will be caught if guess is wrong */ -#endif - -#ifndef local -# define local static -#endif -/* since "static" is used to mean two completely different things in C, we - define "local" for the non-static meaning of "static", for readability - (compile with -Dlocal if your debugger can't find static symbols) */ - -typedef unsigned char uch; -typedef uch FAR uchf; -typedef unsigned short ush; -typedef ush FAR ushf; -typedef unsigned long ulg; - -extern z_const char * const z_errmsg[10]; /* indexed by 2-zlib_error */ -/* (size given to avoid silly warnings with Visual C++) */ - -#define ERR_MSG(err) z_errmsg[Z_NEED_DICT-(err)] - -#define ERR_RETURN(strm,err) \ - return (strm->msg = ERR_MSG(err), (err)) -/* To be used only when the state is known to be valid */ - - /* common constants */ - -#ifndef DEF_WBITS -# define DEF_WBITS MAX_WBITS -#endif -/* default windowBits for decompression. MAX_WBITS is for compression only */ - -#if MAX_MEM_LEVEL >= 8 -# define DEF_MEM_LEVEL 8 -#else -# define DEF_MEM_LEVEL MAX_MEM_LEVEL -#endif -/* default memLevel */ - -#define STORED_BLOCK 0 -#define STATIC_TREES 1 -#define DYN_TREES 2 -/* The three kinds of block type */ - -#define MIN_MATCH 3 -#define MAX_MATCH 258 -/* The minimum and maximum match lengths */ - -#define PRESET_DICT 0x20 /* preset dictionary flag in zlib header */ - - /* target dependencies */ - -#if defined(MSDOS) || (defined(WINDOWS) && !defined(WIN32)) -# define OS_CODE 0x00 -# ifndef Z_SOLO -# if defined(__TURBOC__) || defined(__BORLANDC__) -# if (__STDC__ == 1) && (defined(__LARGE__) || defined(__COMPACT__)) - /* Allow compilation with ANSI keywords only enabled */ - void _Cdecl farfree( void *block ); - void *_Cdecl farmalloc( unsigned long nbytes ); -# else -# include -# endif -# else /* MSC or DJGPP */ -# include -# endif -# endif -#endif - -#ifdef AMIGA -# define OS_CODE 1 -#endif - -#if defined(VAXC) || defined(VMS) -# define OS_CODE 2 -# define F_OPEN(name, mode) \ - fopen((name), (mode), "mbc=60", "ctx=stm", "rfm=fix", "mrs=512") -#endif - -#ifdef __370__ -# if __TARGET_LIB__ < 0x20000000 -# define OS_CODE 4 -# elif __TARGET_LIB__ < 0x40000000 -# define OS_CODE 11 -# else -# define OS_CODE 8 -# endif -#endif - -#if defined(ATARI) || defined(atarist) -# define OS_CODE 5 -#endif - -#ifdef OS2 -# define OS_CODE 6 -# if defined(M_I86) && !defined(Z_SOLO) -# include -# endif -#endif - -#if defined(MACOS) || defined(TARGET_OS_MAC) -# define OS_CODE 7 -# ifndef Z_SOLO -# if defined(__MWERKS__) && __dest_os != __be_os && __dest_os != __win32_os -# include /* for fdopen */ -# else -# ifndef fdopen -# define fdopen(fd,mode) NULL /* No fdopen() */ -# endif -# endif -# endif -#endif - -#ifdef __acorn -# define OS_CODE 13 -#endif - -#if defined(WIN32) && !defined(__CYGWIN__) -# define OS_CODE 10 -#endif - -#ifdef _BEOS_ -# define OS_CODE 16 -#endif - -#ifdef __TOS_OS400__ -# define OS_CODE 18 -#endif - -#ifdef __APPLE__ -# define OS_CODE 19 -#endif - -#if defined(_BEOS_) || defined(RISCOS) -# define fdopen(fd,mode) NULL /* No fdopen() */ -#endif - -#if (defined(_MSC_VER) && (_MSC_VER > 600)) && !defined __INTERIX -# if defined(_WIN32_WCE) -# define fdopen(fd,mode) NULL /* No fdopen() */ -# ifndef _PTRDIFF_T_DEFINED - typedef int ptrdiff_t; -# define _PTRDIFF_T_DEFINED -# endif -# else -# define fdopen(fd,type) _fdopen(fd,type) -# endif -#endif - -#if defined(__BORLANDC__) && !defined(MSDOS) - #pragma warn -8004 - #pragma warn -8008 - #pragma warn -8066 -#endif - -/* provide prototypes for these when building zlib without LFS */ -#if !defined(_WIN32) && \ - (!defined(_LARGEFILE64_SOURCE) || _LFS64_LARGEFILE-0 == 0) - ZEXTERN uLong ZEXPORT adler32_combine64 OF((uLong, uLong, z_off_t)); - ZEXTERN uLong ZEXPORT crc32_combine64 OF((uLong, uLong, z_off_t)); -#endif - - /* common defaults */ - -#ifndef OS_CODE -# define OS_CODE 3 /* assume Unix */ -#endif - -#ifndef F_OPEN -# define F_OPEN(name, mode) fopen((name), (mode)) -#endif - - /* functions */ - -#if defined(pyr) || defined(Z_SOLO) -# define NO_MEMCPY -#endif -#if defined(SMALL_MEDIUM) && !defined(_MSC_VER) && !defined(__SC__) - /* Use our own functions for small and medium model with MSC <= 5.0. - * You may have to use the same strategy for Borland C (untested). - * The __SC__ check is for Symantec. - */ -# define NO_MEMCPY -#endif -#if defined(STDC) && !defined(HAVE_MEMCPY) && !defined(NO_MEMCPY) -# define HAVE_MEMCPY -#endif -#ifdef HAVE_MEMCPY -# ifdef SMALL_MEDIUM /* MSDOS small or medium model */ -# define zmemcpy _fmemcpy -# define zmemcmp _fmemcmp -# define zmemzero(dest, len) _fmemset(dest, 0, len) -# else -# define zmemcpy memcpy -# define zmemcmp memcmp -# define zmemzero(dest, len) memset(dest, 0, len) -# endif -#else - void ZLIB_INTERNAL zmemcpy OF((Bytef* dest, const Bytef* source, uInt len)); - int ZLIB_INTERNAL zmemcmp OF((const Bytef* s1, const Bytef* s2, uInt len)); - void ZLIB_INTERNAL zmemzero OF((Bytef* dest, uInt len)); -#endif - -/* Diagnostic functions */ -#ifdef ZLIB_DEBUG -# include - extern int ZLIB_INTERNAL z_verbose; - extern void ZLIB_INTERNAL z_error OF((char *m)); -# define Assert(cond,msg) {if(!(cond)) z_error(msg);} -# define Trace(x) {if (z_verbose>=0) fprintf x ;} -# define Tracev(x) {if (z_verbose>0) fprintf x ;} -# define Tracevv(x) {if (z_verbose>1) fprintf x ;} -# define Tracec(c,x) {if (z_verbose>0 && (c)) fprintf x ;} -# define Tracecv(c,x) {if (z_verbose>1 && (c)) fprintf x ;} -#else -# define Assert(cond,msg) -# define Trace(x) -# define Tracev(x) -# define Tracevv(x) -# define Tracec(c,x) -# define Tracecv(c,x) -#endif - -#ifndef Z_SOLO - voidpf ZLIB_INTERNAL zcalloc OF((voidpf opaque, unsigned items, - unsigned size)); - void ZLIB_INTERNAL zcfree OF((voidpf opaque, voidpf ptr)); -#endif - -#define ZALLOC(strm, items, size) \ - (*((strm)->zalloc))((strm)->opaque, (items), (size)) -#define ZFREE(strm, addr) (*((strm)->zfree))((strm)->opaque, (voidpf)(addr)) -#define TRY_FREE(s, p) {if (p) ZFREE(s, p);} - -/* Reverse the bytes in a 32-bit value */ -#define ZSWAP32(q) ((((q) >> 24) & 0xff) + (((q) >> 8) & 0xff00) + \ - (((q) & 0xff00) << 8) + (((q) & 0xff) << 24)) - -#endif /* ZUTIL_H */ diff --git a/examples/.gitignore b/examples/.gitignore deleted file mode 100644 index 0e49159..0000000 --- a/examples/.gitignore +++ /dev/null @@ -1,15 +0,0 @@ -general -showindex -diff -rev-list -blame -cat-file -init -log -rev-parse -remote -status -tag -for-each-ref -describe -*.dSYM diff --git a/examples/network/.gitignore b/examples/network/.gitignore deleted file mode 100644 index 1b48e66..0000000 --- a/examples/network/.gitignore +++ /dev/null @@ -1 +0,0 @@ -/git2