### File: latin2.pl ### Version 0.1, October 25, 1997 ### Written by Ross Moore ### Version 0.2, November 1, 1997 ### extended to include macros in LaTeX's latin2.def ### Version 0.3, December 12, 1997 ### includes lower --> uppercase conversion tables ### ### ISO_8859-2 encoding information ### ### extracted from i18n.pl contains... ### Language definitions for HTML 2.1 (I18N, Internationalization) ### Written by Marcus E. Hennecke ### Version 0.3, March 6, 1996 ### Version 0.2, February 2, 1996 ## Copyright (C) 1995 by Marcus E. Hennecke ## This program is free software; you can redistribute it and/or modify ## it under the terms of the GNU General Public License as published by ## the Free Software Foundation; either version 2 of the License, or ## (at your option) any later version. ## This program 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 General Public License for more details. ## You should have received a copy of the GNU General Public License ## along with this program; if not, write to the Free Software ## Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. $CHARSET = "iso-8859-2"; $INPUTENC = 'latin2'; #Character ranges for lower --> upper-case conversion $sclower = "\\261\\263\\265\\266\\271-\\274\\276\\277\\340-\\366\\370-\\376"; $scupper = "\\241\\243\\245\\246\\251-\\254\\256\\257\\300-\\326\\330-\\336"; #extra pattern match preceding lower --> upper-case conversion $scextra = "s/\\337/ss/g"; %extra_small_caps = ( '223' , 'ss' ); %low_entities = ( '177', '161' # ,'178', '162' ,'179', '163' # ,'180', '164' ,'181', '165' ,'182', '166' # ,'183', '167' # ,'184', '168' ,'185', '169' ,'186', '170' ,'187', '171' ,'188', '172' # ,'189', '173' ,'190', '174' ,'191', '175' ,'224', '192' ,'225', '193' ,'226', '194' ,'227', '195' ,'228', '196' ,'229', '197' ,'230', '198' ,'231', '199' ,'232', '200' ,'233', '201' ,'234', '202' ,'235', '203' ,'236', '204' ,'237', '205' ,'238', '206' ,'239', '207' ,'240', '208' ,'241', '209' ,'242', '210' ,'243', '211' ,'244', '212' ,'245', '213' ,'246', '214' # ,'247', '215' ,'248', '216' ,'249', '217' ,'250', '218' ,'251', '219' ,'252', '220' ,'253', '221' ,'254', '222' # ,'255', '223' ); sub do_cmd_l { join('', &iso_map("l", "strok"), $_[0]);} sub do_cmd_L { join('', &iso_map("L", "strok"), $_[0]);} # inhibit later wrapping for an image $raw_arg_cmds{'l'} = $raw_arg_cmds{'L'} = -1 ; sub do_cmd_dh { join('', &iso_map("d", "strok"), $_[0]);} sub do_cmd_DH { join('', &iso_map("D", "strok"), $_[0]);} sub do_cmd_ss { join('', &iso_map("sz", "lig"), $_[0]);} sub do_cmd_textcurrency { join('', &iso_map("curren", ""), $_[0]);} sub do_cmd_mathdegree { join('', &iso_map("deg", ""), $_[0]);} sub do_cmd_S { join('', &iso_map("sect", ""), $_[0]);} sub do_cmd_div { join('', &iso_map("divide", ""), $_[0]);} sub do_cmd_times { join('', &iso_map("times", ""), $_[0]);} sub do_cmd_minus { join('', &iso_map("shy", ""), $_[0]);} sub do_cmd_cdot { join('', &iso_map("middot", ""), $_[0]);} %iso_8859_2_character_map = ( 'Aacute', 'Á', # capital A, acute accent 'Abreve', 'Ã', # capital A, breve accent 'Acirc', 'Â', # capital A, circumflex accent 'Aogon', '¡', # capital A, ogonek accent 'Auml', 'Ä', # capital A, dieresis or umlaut mark 'Cacute', 'Æ', # capital C, acute accent 'Ccaron', 'È', # capital C, caron accent 'Ccedil', 'Ç', # capital C, cedilla 'Dcaron', 'Ï', # capital D, caron accent 'Dstrok', 'Ð', # capital D, stroke 'ETH', 'Ð', # capital Eth, Icelandic 'Eacute', 'É', # capital E, acute accent 'Ecaron', 'Ì', # capital E, caron accent 'Eogon', 'Ê', # capital E, ogonek accent 'Euml', 'Ë', # capital E, dieresis or umlaut mark 'Iacute', 'Í', # capital I, acute accent 'Icirc', 'Î', # capital I, circumflex accent 'Lacute', 'Å', # capital L, acute accent 'Lcaron', '¥', # capital L, caron accent 'Lstrok', '£', # capital L, stroke 'Nacute', 'Ñ', # capital N, acute accent 'Ncaron', 'Ò', # capital N, caron accent 'Oacute', 'Ó', # capital O, acute accent 'Ocirc', 'Ô', # capital O, circumflex accent 'Odblac', 'Õ', # capital O, double accute accent 'Ouml', 'Ö', # capital O, dieresis or umlaut mark 'Racute', 'À', # capital R, acute accent 'Rcaron', 'Ø', # capital R, caron accent 'Sacute', '¦', # capital S, acute accent 'Scaron', '©', # capital S, caron accent 'Scedil', 'ª', # capital S, cedil accent 'Tcaron', '«', # capital T, caron accent 'Tcedil', 'Þ', # capital T, cedil accent 'Uacute', 'Ú', # capital U, acute accent 'Udblac', 'Û', # capital U, double acute accent 'Uring', 'Ù', # capital U, ring 'Uuml', 'Ü', # capital U, dieresis or umlaut mark 'Yacute', 'Ý', # capital Y, acute accent 'Zacute', '¬', # capital Z, acute accent 'Zdot', '¯', # capital Z, dot above 'Zcaron', '®', # capital Z, caron accent 'aacute', 'á', # small a, acute accent 'abreve', 'ã', # small a, breve accent 'acirc', 'â', # small a, circumflex accent 'amp', '&', # ampersand 'aogon', '±', # small a, ogonek accent 'auml', 'ä', # small a, dieresis or umlaut mark 'cacute', 'æ', # small c, acute accent 'ccaron', 'è', # small c, caron accent 'ccedil', 'ç', # small c, cedilla 'dcaron', 'ï', # small d, caron accent 'dstrok', 'ð', # small d, stroke 'eacute', 'é', # small e, acute accent 'ecaron', 'ì', # small e, caron accent 'eogon', 'ê', # small e, ogonek accent 'eth', 'ð', # small eth, Icelandic 'euml', 'ë', # small e, dieresis or umlaut mark 'gt', '>', # greater than 'iacute', 'í', # small i, acute accent 'icirc', 'î', # small i, circumflex accent 'lacute', 'å', # small l, acute accent 'lcaron', 'µ', # small l, caron accent 'lstrok', '³', # small l, stroke 'lt', '<', # less than 'nacute', 'ñ', # small n, acute accent 'ncaron', 'ò', # small n, caron accent 'oacute', 'ó', # small o, acute accent 'ocirc', 'ô', # small o, circumflex accent 'odblac', 'õ', # small o, double accute accent 'ouml', 'ö', # small o, dieresis or umlaut mark 'quot', '"', # double quote 'racute', 'à', # small r, acute accent 'rcaron', 'ø', # small r, caron accent 'sacute', '¶', # small s, acute accent 'scaron', '¹', # small s, caron accent 'scedil', 'º', # small s, cedil accent 'szlig', 'ß', # small sharp s, German (sz ligature) 'tcaron', '»', # small t, caron accent 'tcedil', 'þ', # small t, cedil accent 'uacute', 'ú', # small u, acute accent 'udblac', 'û', # small u, double acute accent 'uring', 'ù', # small u, ring 'uuml', 'ü', # small u, dieresis or umlaut mark 'yacute', 'ý', # small y, acute accent 'zacute', '¼', # small z, acute accent 'zdot', '¿', # small z, dot above 'zcaron', '¾', # small z, caron accent # These do not have HTML mnemonic names ... 'nbsp', ' ', # non-breaking space 'curren', '¤', # currency sign 'sect', '§', # section mark 'times', '×', 'divide', '÷', # These are character types without arguments ... 'grave' , "`", 'circ', '^', 'tilde', '~', 'breve', '¢', 'uml', '¨', 'deg', '°', 'ogon', '²', 'acute' , "´", 'caron', '·', 'cedil', "¸", 'dblac', "½", 'dot', 'ÿ' ); %iso_8859_2_character_map_inv = ( '>' , '\\ensuremath{>}', '<' , '\\ensuremath{<}', '&' , '&', '^' , '\\^{}', '~' , '\\~{}', '"' , '"', ' ' , '\\nobreakspace{}', '¡' , '\\k{A}', '¢' , '\\u{}', '£' , '\\L{}', '¤' , '\\textcurrency{}', '¥' , '\\v{L}', '¦' , '\\\'{S}', '§' , '\\S{}', '¨' , '\\"{}', '©' , '\\v{S}', 'ª' , '\\c{S}', '«' , '\\v{T}', '¬' , '\\\'{Z}', '­' , '\\-', '®' , '\\v{Z}', '¯' , '\\.{Z}', '°' , '\\r{}', '±' , '\\k{a}', '²' , '\\k{ }', '³' , '\\l{}', '´' , '\\\'{}', 'µ' , '\\v{l}', '¶' , '\\\'{s}', '·' , '\\v{}', '¸' , '\\c{ }', '¹' , '\\v{s}', 'º' , '\\c{s}', '»' , '\\v{t}', '¼' , '\\\'{z}', '½' , '\\H{}', '¾' , '\\v{z}', '¿' , '\\.{z}', 'À' , '\\\'{R}', 'Á' , '\\\'{A}', 'Â' , '\\^{A}', 'Ã' , '\\u{A}', 'Ä' , '\\"{A}', 'Å' , '\\\'{L}', 'Æ' , '\\\'{C}', 'Ç' , '\\c{C}', 'È' , '\\v{C}', 'É' , '\\\'{E}', 'Ê' , '\\k{E}', 'Ë' , '\\"{E}', 'Ì' , '\\v{E}', 'Í' , '\\\'{I}', 'Î' , '\\^{I}', 'Ï' , '\\v{D}', 'Ð' , '\\DH{}', 'Ñ' , '\\\'{N}', 'Ò' , '\\v{N}', 'Ó' , '\\\'{O}', 'Ô' , '\\^{O}', 'Õ' , '\\H{O}', 'Ö' , '\\"{O}', '×' , '\\ensuremath{\\times}', 'Ø' , '\\v{R}', 'Ù' , '\\r{U}', 'Ú' , '\\\'{U}', 'Û' , '\\H{U}', 'Ü' , '\\"{U}', 'Ý' , '\\\'{Y}', 'Þ' , '\\c{T}', 'ß' , '\\ss{}', 'à' , '\\\'{r}', 'á' , '\\\'{a}', 'â' , '\\^{a}', 'ã' , '\\u{a}', 'ä' , '\\"{a}', 'å' , '\\\'{l}', 'æ' , '\\\'{c}', 'ç' , '\\c{c}', 'è' , '\\v{c}', 'é' , '\\\'{e}', 'ê' , '\\k{e}', 'ë' , '\\"{e}', 'ì' , '\\v{e}', 'í' , '\\\'{\\i}', 'î' , '\\^{\\i}', 'ï' , '\\v{d}', 'ð' , '\\dh{}', 'ñ' , '\\\'{n}', 'ò' , '\\v{n}', 'ó' , '\\\'{o}', 'ô' , '\\^{o}', 'õ' , '\\H{o}', 'ö' , '\\"{o}', '÷' , '\\ensuremath{\\div}', 'ø' , '\\v{r}', 'ù' , '\\r{u}', 'ú' , '\\\'{u}', 'û' , '\\H{u}', 'ü' , '\\"{u}', 'ý' , '\\\'{y}', 'þ' , '\\c{t}', 'ÿ' , '\\.{}' ); 1;