/*

 * entities.c

 *

 * Copyright (c) Chris Putnam 2003-2018

 *

 * Source code released under the GPL version 2

 *

 */

#include <stdio.h>

#include <string.h>

#include <ctype.h>

#include "entities.h"

/* HTML 4.0 entities */

typedef struct entities {

	char html[20];

	unsigned int unicode;

} entities;

entities html_entities[] = {

	/* Special Entities */

	{ """,     34 },  /* quotation mark */

	{ "&",      38 },  /* ampersand */

	{ "'",     39 },  /* apostrophe (note not defined in HTML) */

	{ "(",     40 },  /* left parenthesis */

	{ ")",     41 },  /* right parenthesis */

	{ "‐",   45 },  /* hyphen */

	{ "<",       60 },  /* less-than sign */

	{ ">",       62 },  /* greater-than sign */

	{ "?",    63 },  /* question mark */

	{ "Œ",   338 },  /* Latin cap ligature OE */

	{ "œ",   339 },  /* Latin small ligature OE */

	{ "Š",  352 },  /* Latin cap S with caron */

	{ "š",  353 },  /* Latin cap S with caron */

	{ "Ÿ",    376 },  /* Latin cap y with diaeresis */

	{ "ˆ",    710 },  /* modifier letter circumflex */

	{ "˜",   732 },  /* small tilde */

	{ " ",   8194 }, /* en space */

	{ " ",   8195 }, /* em space */

	{ " ", 8201 }, /* thin space */

	{ "‌",   8204 }, /* zero width non-joiner */

	{ "‍",    8205 }, /* zero width joiner */

	{ "‎",    8206 }, /* left-to-right mark */

	{ "‏",    8207 }, /* right-to-left mark */

	{ "–",  8211 }, /* en dash */

	{ "—",  8212 }, /* em dash */

	{ "‘",  8216 }, /* left single quotation mark */

	{ "’",  8217 }, /* right single quot. mark */

	{ "‚",  8218 }, /* single low-9 quot. mark */

	{ "“",  8220 }, /* left double quot. mark */

	{ "”",  8221 }, /* right double quot. mark */

	{ "„",  8222 }, /* double low-9 quot. mark */

	{ "†", 8224 }, /* dagger */

	{ "‡", 8225 }, /* double dagger */

	{ "‰", 8240 }, /* per mille sign */

	{ "‹", 8249 }, /* sin. left angle quot mark */

	{ "›", 8250 }, /* sin. right angle quot mark */

	{ "€",   8364 }, /* euro sign */

	/* Symbols and Greek characters */

	{ "ƒ",    402 }, /* small f with hook = function */

	{ "Α",   913 }, /* capital alpha */

	{ "Β",    914 }, /* capital beta */

	{ "Γ",   915 }, /* capital gamma */

	{ "Δ",   916 }, /* capital delta */

	{ "Ε", 917 }, /* capital epsilon */

	{ "Ζ",    918 }, /* capital zeta */

	{ "Η",     919 }, /* capital eta */

	{ "Θ",   920 }, /* capital theta */

	{ "Ι",    921 }, /* capital iota */

	{ "Κ",   922 }, /* capital kappa */

	{ "Λ",  923 }, /* capital lambda */

	{ "Μ",      924 }, /* capital mu */

	{ "Ν",      925 }, /* capital nu */

	{ "Ξ",      926 }, /* capital xi */

	{ "Ο", 927 }, /* capital omicron */

	{ "Π",      928 }, /* capital pi */

	{ "Ρ",     929 }, /* capital rho */

	{ "Σ",   931 }, /* capital sigma */

	{ "Τ",     932 }, /* capital tau */

	{ "Υ", 933 }, /* capital upsilon */

	{ "Φ",     934 }, /* capital phi */

	{ "Χ",     935 }, /* capital chi */

	{ "Ψ",     936 }, /* capital psi */

	{ "Ω",   937 }, /* capital omega */

	{ "α",   945 }, /* small alpha */

	{ "β",    946 }, /* small beta */

	{ "γ",   947 }, /* small gamma */

	{ "δ",   948 }, /* small delta */

	{ "ε", 949 }, /* small epsilon */

	{ "ζ",    950 }, /* small zeta */

	{ "η",     951 }, /* small eta */

	{ "θ",   952 }, /* small theta */

	{ "ι",    953 }, /* small iota */

	{ "κ",   954 }, /* small kappa */

	{ "λ",  955 }, /* small lambda */

	{ "μ",      956 }, /* small mu */

	{ "ν",      957 }, /* small nu */

	{ "ξ",      958 }, /* small xi */

	{ "ο", 959 }, /* small omicron */

	{ "π",      960 }, /* small pi */

	{ "ρ",     961 }, /* small rho */

	{ "ς",  962 }, /* small final sigma */

	{ "σ",   963 }, /* small simga */

	{ "τ",     964 }, /* small tau */

	{ "υ", 965 }, /* small upsilon */

	{ "φ",     966 }, /* small phi */

	{ "χ",     967 }, /* small chi */

	{ "ψ",     968 }, /* small psi */

	{ "ω",   969 }, /* small omega */

	{ "ϑ",977 }, /* small theta symbol */

	{ "ϒ",   978 }, /* small upsilon with hook */

	{ "ϖ",     982 }, /* pi symbol */

	{ "•",   8226 }, /* bullet = small blk circle */

	{ "…", 8230 }, /* horizontal ellipsis */

	{ "′",  8242 }, /* prime = minutes = feet */

	{ "″",  8243 }, /* double prime */

	{ "‾",  8254 }, /* overline */

	{ "⁄",  8260 }, /* fraction slash */

	{ "℘", 8472 }, /* Weierstrass p = power set */

	{ "ℑ",  8465 }, /* imaginary part-black cap I */

	{ "ℜ",   8476 }, /* real part-black cap R */

	{ "™",  8482 }, /* trademark sign */

	{ "ℵ",8501 }, /* alef symbol */

	{ "←",   8592 }, /* left arrow */

	{ "↑",   8593 }, /* up arrow */

	{ "→",   8594 }, /* right arrow */

	{ "↓",   8595 }, /* down arrow */

	{ "↔",   8596 }, /* left/right arrow */

	{ "↵",  8629 }, /* down arrow with corner left */

	{ "⇐",   8656 }, /* left double arrow */

	{ "⇑",   8657 }, /* up double arrow */

	{ "⇒",   8658 }, /* up double arrow */

	{ "⇓",   8659 }, /* up double arrow */

	{ "⇔",   8660 }, /* up double arrow */

	{ "∀", 8704}, /* for all */

	{ "∂",   8706}, /* partial differential */

	{ "∃",  8707}, /* there exists */

	{ "∅",  8709}, /* empty set */

	{ "∇",  8711}, /* nabla=backwards difference */

	{ "∈",   8712}, /* element of */

	{ "∉",  8713}, /* not an element of */

	{ "∋",     8715}, /* contains as member */

	{ "∏",   8719}, /* n-ary product */

	{ "∑",    8721}, /* n-ary summation */

	{ "−",  8722}, /* minuss sign */

	{ "∗", 8727}, /* asterisk operator */

	{ "√",  8730}, /* square root */

	{ "∝",   8733}, /* proportional to */

	{ "∞",  8734}, /* infinity */

	{ "∠",    8736}, /* angle */

	{ "∧",    8743}, /* logical and */

	{ "∨",     8744}, /* logical or */

	{ "∩",    8745}, /* intersection */

	{ "∪",    8746}, /* union */

	{ "∫",    8747}, /* integral */

	{ "∴", 8756}, /* therefore */

	{ "∼",    8764}, /* tilde operator */

	{ "≅",   8773}, /* approximately equal to */

	{ "≈",  8776}, /* asymptotic to */

	{ "≠",     8800}, /* not equal to */

	{ "≡",  8801}, /* identical to */

	{ "≤",     8804}, /* less-than or equal to */

	{ "≥",     8805}, /* greater-than or equal to */

	{ "⊂",    8834}, /* subset of */

	{ "⊃",    8835}, /* superset of */

	{ "⊄",   8836}, /* not a subset of */

	{ "⊆",   8838}, /* subset of or equal to */

	{ "⊇",   8839}, /* superset of or equal to */

	{ "⊕",  8853}, /* circled plus = direct sum */

	{ "⊗", 8855}, /* circled times = vec prod */

	{ "⊥",   8869}, /* perpendicular */

	{ "⋅",   8901}, /* dot operator */

	{ "⌈",  8968}, /* left ceiling */

	{ "⌉",  8969}, /* right ceiling */

	{ "⌊", 8970}, /* left floor */

	{ "⌋", 8971}, /* right floor */

	{ "⟨",   9001}, /* left angle bracket */

	{ "⟩",   9002}, /* right angle bracket */

	{ "◊",    9674}, /* lozenge */

	{ "♠", 9824}, /* spades */

	{ "♣",  9827}, /* clubs */

	{ "♥", 9829}, /* hearts */

	{ "♦",  9830}, /* diamonds */

	/* Latin-1 */

	{ " ",    32 },  /* non-breaking space */

	{ "¡",  161 },  /* inverted exclamation mark */

	{ "¢",   162 },  /* cent sign */

	{ "£",  163 },  /* pound sign */

	{ "¤", 164 },  /* currency sign */

	{ "¥",    165 },  /* yen sign */

	{ "¦", 166 },  /* broken vertical bar */

	{ "§",   167 },  /* section sign */

	{ "¨",    168 },  /* diaeresis - spacing diaeresis */

	{ "©",   169 },  /* copyright sign */

	{ "ª",   170 },  /* feminine ordinal indicator */

	{ "«",  171 },  /* left-pointing guillemet */

	{ "¬",    172 },  /* not sign */

	{ "­",    173 },  /* soft (discretionary) hyphen */

	{ "®",    174 },  /* registered sign */

	{ "¯",   175 },  /* macron = overline */

	{ "°",    176 },  /* degree sign */

	{ "±", 177 },  /* plus-minus sign */

	{ "²",   178 },  /* superscript two */

	{ "³",   179 },  /* superscript three */

	{ "´",  180 },  /* acute accent = spacing acute */

	{ "µ",  181 },  /* micro sign */

	{ "¶",   182 },  /* pilcrow (paragraph) sign */

	{ "·", 183 },  /* middle dot (georgian comma) */

	{ "¸",  184 },  /* cedilla = spacing cedilla */

	{ "¹",   185 },  /* superscript one */

	{ "º",   186 },  /* masculine ordinal indicator */

	{ "»",  187 },  /* right pointing guillemet */

	{ "¼", 188 },  /* 1/4 */

	{ "½", 189 },  /* 1/2 */

	{ "¾", 190 },  /* 3/4 */

	{ "¿", 191 },  /* inverted question mark */

	{ "À", 192 },  /* cap A with grave */

	{ "Á", 193 },  /* cap A with acute */

	{ "Â",  194 },  /* cap A with circumflex */

	{ "Ã", 195 },  /* cap A with tilde */

	{ "Ä",   196 },  /* cap A with diaeresis */

	{ "Å",  197 },  /* cap A with ring */

	{ "Æ",  198 },  /* cap AE ligature */

	{ "Ç", 199 },  /* cap C with cedilla */

	{ "È", 200 },  /* cap E with grave */

	{ "É", 201 },  /* cap E with acute */

	{ "Ê",  202 },  /* cap E with circumflex */

	{ "Ë",   203 },  /* cap E with diaeresis */

	{ "Ì", 204 },  /* cap I with grave */

	{ "Í", 205 },  /* cap I with acute */

	{ "Î",  206 },  /* cap I with circumflex */

	{ "Ï",   207 },  /* cap I with diaeresis */

	{ "Ð",    208 },  /* cap letter ETH */

	{ "Ñ", 209 },  /* cap N with tilde */

	{ "Ò", 210 },  /* cap O with grave */

	{ "Ó", 211 },  /* cap O with acute */

	{ "Ô",  212 },  /* cap O with circumflex */

	{ "Õ", 213 },  /* cap O with tilde */

	{ "Ö",   214 },  /* cap O with diaeresis */

	{ "×",  215 },  /* multiplication sign */

	{ "Ø", 216 },  /* cap O with stroke */

	{ "Ù", 217 },  /* cap U with grave */

	{ "Ú", 218 },  /* cap U with acute */

	{ "Û",  219 },  /* cap U with circumflex */

	{ "Ü",   220 },  /* cap U with diaeresis */

	{ "Ý", 221 },  /* cap Y with acute */

	{ "Þ",  222 },  /* cap letter THORN */

	{ "ß",  223 },  /* small sharp s = ess-zed */

	{ "à", 224 },  /* small a with grave */

	{ "á", 225 },  /* small a with acute */

	{ "â",  226 },  /* small a with cirucmflex */

	{ "ã", 227 },  /* small a with tilde */

	{ "&amu;;",   228 },  /* small a with diaeresis */

	{ "å",  229 },  /* small a with ring */

	{ "æ",  230 },  /* small ligature ae */

	{ "ç", 231 },  /* small c with cedilla */

	{ "è", 232 },  /* small e with grave */

	{ "é", 233 },  /* small e with acute */

	{ "ê",  234 },  /* small e with circumflex */

	{ "&emu;;",   235 },  /* small e with diaeresis */

	{ "ì", 236 },  /* small i with grave */

	{ "í", 237 },  /* small i with acute */

	{ "î",  238 },  /* small i with circumflex */

	{ "ï",   239 },  /* small i with diaeresis */

	{ "ð",    240 },  /* latin small letter eth */

	{ "ñ", 241 },  /* small n with tilde */

	{ "ò", 242 },  /* small o with grave */

	{ "ó", 243 },  /* small o with acute */

	{ "ô",  244 },  /* small o with circumflex */

	{ "õ", 245 },  /* small o with tilde */

	{ "ö",   246 },  /* small o with diaeresis */

	{ "÷", 247 },  /* division sign */

	{ "ø", 248 },  /* small o with slash */

	{ "ù", 249 },  /* small u with grave */

	{ "ú", 250 },  /* small u with acute */

	{ "û",  251 },  /* small u with circumflex */

	{ "ü",   252 },  /* small u with diaeresis */

	{ "ý", 253 },  /* small y with acute */

	{ "þ",  254 },  /* latin small letter thorn */

	{ "ÿ",   255 },  /* small y with diaeresis */

};

static unsigned int

decode_html_entity( char *s, unsigned int *pi, int *err )

{

	int nhtml_entities = sizeof( html_entities ) / sizeof( entities );

	char *e;

	int i, n=-1, len;

	for ( i=0; i

		e = &(html_entities[i].html[0]);

		len = strlen( e );

		if ( !strncasecmp( &(s[*pi]), e, len ) ) {

			n = i;

			*pi += len;

		}

	}

	if ( n==-1 ) {

		*err = 1;

		return '&';

	} else {

		*err = 0;

		return html_entities[n].unicode;

	}

}

/*

 * decode decimal entity

 *

 *    extract a decimal entity from &#NNNN;

 *    s[*pi] points to the '&' character

 */

static unsigned int

decode_decimal_entity( char *s, unsigned int *pi, int *err )

{

	unsigned int c = 0, d;

	int i = *pi, j = 2;

	while ( isdigit( (unsigned char)s[i+j] ) ) {

		d = s[i+j] - '0';

		c = 10 * c + d;

		j++;

	}

	if ( s[i+j]!=';' ) *err = 1;

	else *pi = i+j+1;

	return c;

}

/*

 * decode hex entity

 *

 *    extract a hex entity from &#xNNNN;

 *    s[*pi] points to the '&' character

 */

static unsigned int

decode_hex_entity( char *s, unsigned int *pi, int *err )

{

	unsigned int c = 0, d;

	int i = *pi, j = 3;

	while ( isxdigit( (unsigned char)s[i+j] ) ) {

		if ( isdigit( (unsigned char)s[i+j] ) ) d = s[i+j]-'0';

		else d = toupper((unsigned char)s[i+j])-'A' + 10;

		c = 16 * c + d;

		j++;

	}

	if ( s[i+j]!=';' ) *err = 1;

	else *pi = i+j+1;

	return c;

}

/*

 * decode numeric entity

 *

 *    extract a numeric entity from &#NNN; or &#xNNNN;

 *

 *    In XML, the "x" in hexadecimal entries should be lowercase,

 *    but we'll be generous and accept "X" as well.

 */

static unsigned int

decode_numeric_entity( char *s, unsigned int *pi, int *err )

{

	unsigned int c;

	*err = 0;

	if ( s[*pi+2]!='x' && s[*pi+2]!='X' ) c = decode_decimal_entity( s, pi, err );

	else c = decode_hex_entity( s, pi, err );

	if ( *err ) {

		*pi = *pi + 1;

		c = '&';

	}

	return c;

}

/*

 * decode entity

 *    extract entity from  &mmmm;

 *

 * where &mmmm; is one of

 * - &#nnnn; is code point in decimal form

 * - &#xhhhh; is code point in hexadecimal form (note "x" is lowercase in XML)

 * - &mmmm; corresponds to a pre-defined XML entity, e.g. &quote for quotations

 *

 */

unsigned int

decode_entity( char *s, unsigned int *pi, int *unicode, int *err )

{

	unsigned int c = '&';

	*unicode = 0;

	if ( s[*pi]!='&' ) {

		*err = 1;  /* need to start with ampersand */

		c = s[*pi];

	} else *err = 0;

	if ( !*err ) {

		if ( s[*pi+1]=='#' ) c = decode_numeric_entity( s, pi, err );

		else {

			c = decode_html_entity( s, pi, err );

			*unicode = 1;

		}

	}

	if ( *err ) *pi = *pi + 1;

	return c;

}