# $Id: roff.charmap,v 1.6 2004/08/13 01:32:23 stevecheng Exp $

# 

# unicodetoroff.xml - map Unicode chars to roff escape sequences.

# 

# Author: Michael Smith <smith@sideshowbarker.net>

# Created: 2004-01-27

# Version: 1.00.0

# Date: $Date: 2004/08/13 01:32:23 $

# RCS Id: $Id: roff.charmap,v 1.6 2004/08/13 01:32:23 stevecheng Exp $

# URL: http://docbook.sf.net/projects/xsl/

# 

# Copyright 2004 Michael Smith

# 

# 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.

# 

# ***************************************************************

# Commentary

# ***************************************************************

# This file maps a small subset of Unicode characters (around 800

# or so) to corresponding roff espace sequences. Use it when you

# need to convert Unicode (UTF-8 or UTF-16) encoded XML content

# to roff (e.g., to generate "portable" man-page output).

# 

# Although the format follows the "character map" format

# specified in the XSLT 2.0 working draft[1], it can be used with

# an appropriate XSLT 1.0 stylesheet and any XSLT 1.0 processor.

# 

# [1] http://www.w3.org/TR/xslt20/#character-maps

# 

# In order to make the character map more readable, it uses the

# following "extension attributes" (in the "unichar" namespace):

# 

# - unichar:name = ISO character name (e.g., "YEN SIGN")

# - unichar:entity = ISO entity name (e.g., "yen")

# 

# Use of such extension attributes is permitted by the XSLT 2.0

# spec; see the "Extension Attributes" section[2].

# 

# [2] http://www.w3.org/TR/xslt20/#extension-attributes

# 

# The initial version of this file (before the "string" mappings

# were added) was generated by taking the "unichars.el" file from

# Norm Walsh's "xmlunicode.el"[3] elisp distro, and running a

# script on it to convert it to XML.

# 

# ***************************************************************

# Acknowledgements

# ***************************************************************

# References used in selecting roff mappings:

# 

# - groff_char(7) man page[3]

# - groff info file[4]; in particular, the "Page Motions" node[5]

# - tables in "Character Sets" chapter of "XML In a Nutshell"[6]

# 

# [3] http://www.linux.se/showMan.php?TITLE=groff_char&SECTION=7

# [4] http://www.fifi.org/cgi-bin/info2www?(groff)

# [5] http://www.fifi.org/cgi-bin/info2www?(groff)Page+Motions

# [6] http://www.ibiblio.org/xml/books/xian2/

# 

# The idea for doing this in XML/XSLT came from working with

# Steve Cheng’s docbook2x package[7] - in particular, the

# "utf8trans" utility and character-map system in that package.

# 

# [7] http://docbook2x.sourceforge.net/

# 

# ################################################################# 

# *****************************************************************

# Begin: Latin-1/ISO-8859-1

# x00a0 to x00ff

# **************************************************************** 

# no-break space can be written two ways in roff; the difference,

# according to the "Page Motions" node in the groff info page, is:

# 

# "\ " =

# "An unbreakable and unpaddable (i.e. not expanded during filling)

# space."

# 

# "\~" =

# "An unbreakable space that stretches like a normal

# inter-word space when a line is adjusted." 

# 

# Unfortunately, roff seems to do some weird things with long

# lines that only have words separated by "\~" spaces, so it's

# safer just to stick with the "\ " space

# 

a0 \ 

a1 \(r!

a2 \(ct

a3 \(Po

a4 \(Cs

a5 \(Ye

a6 \(bb

a7 \(sc

a8 \(ad

a9 \(co

aa \(Of

ab \(Fo

ac \(no

# groff_char(7) man page says: "the soft hyphen control character

# (prints as itself).  groff never use this character for output

# (thus it is omitted in the table below); the input character 173

# is onto \%." 

ad \%

ae \(rg

af \(a-

b0 \(de

b1 \(+-

b2 \(S2

b3 \(S3

b4 \(aa

b5 \(mc

b6 \(ps

# according to groff_char(7), I think the escape string \(pc

# "periodcentered" could also be used for middot; not sure which

# is better, but "md" mnemonic is a better fit :-)

# 

b7 \(md

b8 \(ac

b9 \(S1

ba \(Om

bb \(Fc

bc \(14

bd \(12

be \(34

bf \(r?

c0 \(`A

c1 \('A

c2 \(^A

c3 \(~A

c4 \(:A

c5 \(oA

c6 \(AE

c7 \(,C

c8 \(`E

c9 \('E

ca \(^E

cb \(:E

cc \(`I

cd \('I

ce \(^I

cf \(:I

d0 \(-D

d1 \(~N

d2 \(`O

d3 \('O

d4 \(^O

d5 \(~O

d6 \(:O

d7 \(mu

d8 \(/O

d9 \(`U

da \('U

db \(^U

dc \(:U

dd \('Y

de \(TP

df \(ss

e0 \(`a

e1 \('a

e2 \(^a

e3 \(~a

e4 \(:a

e5 \(oa

e6 \(ae

e7 \(,c

e8 \(`e

e9 \('e

ea \(^e

eb \(:e

ec \(`i

ed \('i

ee \(^i

ef \(:i

f0 \(Sd

f1 \(~n

f2 \(`o

f3 \('o

f4 \(^o

f5 \(~o

f6 \(:o

f7 \(di

f8 \(/o

f9 \(`u

fa \('u

fb \(^u

fc \(:u

fd \('y

fe \(Tp

ff \(:y

# ****************************************************************

# End: Latin-1/ISO-8859-1

# **************************************************************** 

# ****************************************************************

# Begin:

# 

# - x0100 to x017f (Latin Extended-A)

# - x0180 to x023f (Latin Extended-B)

# - x0250 to x02ad (IPA Extensions)

# - x02b0 to x02ee (Spacing Modifier Letters)

# - x0300 to x036f (Combining Diacritical Marks)

# 

# Other than the following exceptions, characters in these

# blocks don't have any roff equivalents

# **************************************************************** 

131 \(.i

132 \(IJ

133 \(ij

141 \(/L

142 \(/l

152 \(OE

153 \(oe

192 \(Fn

2c6 \(a^

2c7 \(ac

2c9 \(a-

2d8 \(ab

# there does not seem to by any roff equivalent for "dot above"

# 

# character="˙"

# unichar:name="DOT ABOVE"

# unichar:entity="dot"

# />

# 

2da \(ao

2db \(ho

# groff_char(7) man page calls Unicode x02dd a "Hungarian umlaut"

# 

2dd \(a"

# ****************************************************************

# End:

# - Latin Extended-A

# - Latin Extended-B

# - IPA Extensions

# - Spacing Modifier Letters

# - Combining Diacritical Marks

# **************************************************************** 

# ****************************************************************

# Begin: Greek and Coptic

# x0370 to x03ff

# **************************************************************** 

391 \(*A)

392 \(*B

393 \(*G

394 \(*D

395 \(*E

396 \(*Z

397 \(*Y

398 \(*H

399 \(*I

39a \(*K

39b \(*L

39c \(*M

39d \(*N

39e \(*C

39f \(*O

3a0 \(*P

3a1 \(*R

3a3 \(*S

3a4 \(*T

3a5 \(*U

3a6 \(*F

3a7 \(*X

3a8 \(*Q

3a9 \(*W

3aa \(*I

3ab \(*U

3ac \(*a

3ad \(*e

3ae \(*y

3af \(*i

3b0 \(*u

3b1 \(*a

3b2 \(*b

3b3 \(*g

3b4 \(*d

3b5 \(*e

3b6 \(*z

3b7 \(*y

3b8 \(*h

3b9 \(*i

3ba \(*k

3bb \(*l

3bc \(*m

3bd \(*n

3be \(*c

3bf \(*o

3c0 \(*p

3c1 \(*r

3c2 \(ts

3c3 \(*s

3c4 \(*t

3c5 \(*u

3c6 \(*f

3c7 \(*x

3c8 \(*q

3c9 \(*w

3ca \(*i

3cb \(*u

3cc \(*o

3cd \(*u

3ce \(*w

3d0 \(*B

3d1 \(+h

3d2 \(*U

3d3 \(*U

3d4 \(*U

3d5 \(+f

3d6 \(+p

# no mappings for remaining chars x03d7 to x03ef 

3f0 (*k

3f1 \(*r

3f2 \(*s

3f4 \(*H

3f5 \(*e

3f6 \(*e

# ****************************************************************

# End: Greek and Coptic

# **************************************************************** 

# !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

# Cyrillic

# x0400 to x04ff

# 

# - do nothing -

# !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! 

# *****************************************************************

# Begin: General Punctuation

# x2000 to x206f

# **************************************************************** 

# first, Spaces of various widths 

# Note: There does not seem to be either a real em space or en

# space in roff; to approximate them, this character map assumes

# that in most fonts, an en space is about the same as the width of

# a digit (in roff, "\0"), so an em space (which by definition is

# equal to the width of two en spaces) is about the same as the

# width of two digits (thus, in roff, "\0\0") 

2000 \0

2001 \0\0

2002 \0

2003 \0\0

# roughly same width as a normal space 

2004  

# roughly same width as a normal space 

2005  

# roughly same width as a normal space 

2006  

# same as roff "digit" space 

2007 \0

# punctuation space in most fonts is actually closer to a normal

# space than it is to a thin space 

2008  

# Note: Not sure how best to deal with thin space, because the

# roff thin space, "\^", prints as a zero-width space in TTY

# output. However, it seems that, unlike a hair space, a thin

# space, at 1/12 of an em, is still recognizable to most people

# as a space, so treating it as zero-width seems wrong. So, for

# the sake of making TTY output look OK, just substitute with a

# normal space; but real roff escape is "\(\^" 

2009  

# I don't think there's a standard definition of what a hair

# space is; some guides just say it's "less than 1/5 of an em" or

# that it's "narrower than a thin space"; seems like in practice,

# it's *a lot* narrower than a thin space, to the point where

# it's close to being a non-space, so here it's substitute with

# roff equivalent of a zero-width joiner 

200a \&

# map to roff "zero-width break point"  

200b \:

# map to roff "zero-width break point"  

200c \:

# groff docs seem ambiguous about whether \& is a joiner and

# prevents breaks, but, based on testing, seems like it does 

200d \&

# non-visible 

# 

# character="‎"

# unichar:name="LEFT-TO-RIGHT MARK"

# />

# 

# character="‏"

# unichar:name="RIGHT-TO-LEFT MARK"

# />

# 

# .................................................... 

# next, hyphens and various dashes, bars, underscores  

2010 \(hy

2011 \&-\&

# roughly same width as en dash 

2012 \(en

2013 \(en

2014 \(em

# seems roughly same width as em dash 

2015 \(em

2016 \(bv\(bv

# no double-underscore in roff; so just make it a single

# underscore 

2017 _

# .................................................... 

# various quotation marks 

2018 \(oq

2019 \(cq

201a \(bq

# no roff equiv; treat same as lsquo 

201b \(oq

201c \(lq

201d \(rq

201e \(Bq

# no roff equiv; treat same as rdquo 

201f \(rq

# .................................................... 

# various symbols 

2020 \(dg

2021 \(dd

2022 \(bu

# no roff equiv 

2023 >\&

# no roff equiv 

2024 \&.

# no roff equiv 

2025 \&..

# no roff equiv 

2026 \&...

2027 \%

# Begin x2028 to x202e - no idea what to do with these

# 

# character="
"

# unichar:name="LINE SEPARATOR"

# />

# 

# character="
"

# unichar:name="PARAGRAPH SEPARATOR"

# />

# 

# character="‪"

# unichar:name="LEFT-TO-RIGHT EMBEDDING"

# />

# 

# character="‫"

# unichar:name="RIGHT-TO-LEFT EMBEDDING"

# />

# 

# character="‬"

# unichar:name="POP DIRECTIONAL FORMATTING"

# />

# 

# character="‭"

# unichar:name="LEFT-TO-RIGHT OVERRIDE"

# />

# 

# character="‮"

# unichar:name="RIGHT-TO-LEFT OVERRIDE"

# />

# End x2028 to x202e - no idea what to do with these 

# seems like "narrow" nbsp is basically the same as a no-break

# space 

202f \ 

2030 \(%0

# no roff equiv; no idea what to do with it

# 

# character="‱"

# unichar:name="PER TEN THOUSAND SIGN"

# />

# 

2032 \(fm

2033 \(sd

2034 \(sd\(fm

# no idea for these 

# 

# character="‵"

# unichar:name="REVERSED PRIME"

# unichar:entity="bprime"

# />

# 

# character="‶"

# unichar:name="REVERSED DOUBLE PRIME"

# />

# 

# character="‷"

# unichar:name="REVERSED TRIPLE PRIME"

# />

# 

# there is no low caret in roff 

2038 ^

2039 \(fo

203a \(fc

# not in roff 

203b *

203c !!

203d ?!

203e \(rn

203f \(ul

# not in roff 

2040 \(rn

# not in roff 

2041 ^

# not in roff 

2042 *

# not in roff; just make bold hyphen 

2043 \fB-\fR

2044 \(sl

# not in roff 

2045 [

# not in roff 

2046 ]

2047 ??

2048 ?!

2049 !?

# not in roff 

204a 7

# not in roff; just replace with un-reversed pilcrow 

204b \(ps

# not in roff; just make regular bullet 

204c \(bu

# not in roff; just make regular bullet 

204d \(bu

204e *

# ...............................................................

# Remaining General Punctuation

# from x2050 to x206f

# only map a couple of these

# .............................................................. 

# basically same as a normal space 

205f  

# no idea how this is different than a zero-width joiner 

2060 \&

# *****************************************************************

# End: General Punctuation

# **************************************************************** 

# *****************************************************************

# Begin: Superscripts and Subscripts

# x2070 to x209f

# For superscripts, just do a^n thing

# For subscripts, just do a_n

# **************************************************************** 

2070 ^0

2071 ^i

2074 ^4

2075 ^5

2076 ^6

2077 ^7

2078 ^8

2079 ^9

207a ^+

207b ^-

207c ^=

207d ^(

207e ^)

207f ^n

2080 _0

2081 _1

2082 _2

2083 _3

2084 _4

2085 _5

2086 _6

2087 _7

2088 _8

2089 _9

208a _+

208b _-

208c _=

208d _(

208e _)

# *****************************************************************

# End: Superscripts and Subscripts

# x2070 to x209f

# **************************************************************** 

# *****************************************************************

# Begin: Currency Symbols

# x20a0 to x20b1

# No mappings for any of these; just spell out

# **************************************************************** 

20a0 EUR

20a1 COLON

20a2 CRUZEIRO

20a3 FRANC

20a4 LIRA

20a5 MILL

20a6 NAIRA

20a7 PESETA

20a8 RUPEE

20a9 WON

20aa SHEQEL

20ab DONG

20ac EUR

20ad KIP

20ae TUGRIK

20af DRACHMA

20b0 ?

20b1 PESO

# *****************************************************************

# End: Currency Symbols

# x20a0 to x20b1

# **************************************************************** 

# !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

# Combining Diacritical Marks for Symbols

# x20do to x20ff

# 

# - do nothing -

# !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! 

# *****************************************************************

# Begin: Letterlike Symbols

# x2100 to x214b

# 

# No mappings for any of these, and nothing appropriate for most

# of them; so, just spell out the ones that we can

# **************************************************************** 

2103 \(deC

2105 c/o

2109 \(deF

# roff Ifraktur 

2111 \(Im

2113 l

2116 No.

2118 \(wp

211c \(Re

211e Rx

2120 sm

2122 \(tm

2126 \(*W

212a K

212b \(oA

2135 \(Ah

# *****************************************************************

# End: Letterlike Symbols

# x2100 to x214b

# **************************************************************** 

# *****************************************************************

# Begin: Number Forms

# x2150 to x218f

# 

# No mappings for any of these, and nothing appropriate for most

# of them; so, just spell out the ones that we can

# **************************************************************** 

2153 1/3

2154 2/3

2155 1/5

2156 2/5

2157 3/5

2158 4/5

2159 1/6

215a 5/6

215b 1/8

215c 3/8

215d 5/8

215e 7/8

215f 1/

2160 I

2161 II

2162 III

2163 IV

2164 V

2165 VI

2166 VII

2167 VIII

2168 IX

2169 X

216a XI

216b XII

216c L

216d C

216e D

216f M

2170 i

2171 ii

2172 iii

2173 iv

2174 v

2175 vi

2176 vii

2177 viii

2178 ix

2179 x

217a xi

217b xii

217c l

217d c

217e d

217f m

2180 CD

# *****************************************************************

# End: Number Forms

# x2150 to x218f

# **************************************************************** 

# *****************************************************************

# Begin: Arrows

# x2190 to x21ff

# **************************************************************** 

2190 \(<-

2191 \(ua

2192 \(->

2193 \(da

2194 \(<>

2195 \(va

21b5 \(CR

21d0 \(la

21d1 \(uA

21d2 \(rA

21d3 \(dA

21d4 \(hA

# no roff equiv; render same as single arrow 

21d5 \(va

# *****************************************************************

# Begin: Mathematical Operators

# x2200 to x22ff

# **************************************************************** 

2200 \(fa

2201 C

2202 \(pd

2203 \(te

# no roff equiv 

# 

# character="∄"

# unichar:name="THERE DOES NOT EXIST"

# unichar:entity="nexist"

# />

# 

2205 \(es

2206 \(*D

2207 \(gr

2208 \(mo

2209 \(nm

220a \(mo

220b \(st

# not in roff 

# 

# character="∌"

# unichar:name="DOES NOT CONTAIN AS MEMBER"

# />

# 

220d \(st

# not in roff

# 

# character="∎"

# unichar:name="END OF PROOF"

# />

# 

220f \(product

# not in roff

# 

# character="∐"

# unichar:name="N-ARY COPRODUCT"

# unichar:entity="coprod"

# />

# 

2211 \(sum

2212 \-

2213 \(+-

# not in roff

# 

# character="∔"

# unichar:name="DOT PLUS"

# unichar:entity="plusdo"

# />

# 

2215 \(f/

# not in roff

# 

# character="∖"

# unichar:name="SET MINUS"

# unichar:entity="setmn"

# />

# 

2217 \(**

# not in roff

# 

# character="∘"

# unichar:name="RING OPERATOR"

# unichar:entity="compfn"

# />

# 

2219 \(bu

221a \(sr

# not in roff

# 

# character="∛"

# unichar:name="CUBE ROOT"

# />

# 

# character="∜"

# unichar:name="FOURTH ROOT"

# />

# 

221d \(pt

221e \(if

# not in roff

# 

# character="∟"

# unichar:name="RIGHT ANGLE"

# unichar:entity="ang90"

# />

# 

2220 \(/_

# 0x2221 to 0x2226 not in roff;

# but fake a parallel sign with vert bars

2225 \(bv\(bv

2227 \(AN

2228 \(OR

2229 \(ca

222a \(cu

222b \(is

222c \(is\(is

222d \(is\(is\(is

# 0x222e to 0x2233 not in roff 

2234 \(tf

# not in roff

# 

# character="∵"

# unichar:name="BECAUSE"

# unichar:entity="becaus"

# />

# 

2236 :