"Fossies" - the Fresh Open Source Software Archive

Member "latex2html-2002-2-1/versions/latin6.pl" (29 Nov 2002, 11272 Bytes) of archive /linux/www/latex2html-2002-2-1.tar.gz:


As a special service "Fossies" has tried to format the requested source page into HTML format (assuming markdown format). Alternatively you can here view or download the uninterpreted source code file. A member file download can also be achieved by clicking within a package contents listing on the according byte size field.

File: latin6.pl

Version 0.1, December 19, 1997

includes lower –> uppercase conversion tables

#

ISO_8859-10 encoding information

#

Copyright © 1995 by Ross Moore

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-8859-10”; $INPUTENC=‘latin6’; # empty implies ‘latin1’

Character ranges for lower –> upper-case conversion

$sclower = “\261-\266\270-\274\276\277\340-\376”; $scupper = “\241-\246\250-\254\256\257\300-\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_tl { join(‘’, &iso_map(“t”, “strok”), $[0]);} sub do_cmd_TL { join(‘’, &iso_map(“T”, “strok”), $[0]);} 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_ng { join(‘’, &iso_map(“eng”, “”), $[0]);} sub do_cmd_NG { join(‘’, &iso_map(“ENG”, “”), $[0]);} sub do_cmd_kra { join(‘’, &iso_map(“k”, “green”), $[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]);}

%iso_8859_10_character_map = ( ‘Aacute’, ‘Á’, # capital A, acute accent ‘Acirc’, ‘Â’, # capital A, circumflex accent ‘AElig’, ‘Æ’, # capital AE diphthong (ligature) ‘Aogon’, ‘¡’, # capital A, ogonek accent ‘Amacr’, ‘À’, # capital A, macron accent ‘Aring’, ‘Å’, # capital A, ring ‘Atilde’, ‘Ã’, # capital A, tilde ‘Auml’, ‘Ä’, # capital A, dieresis or umlaut mark
‘Ccaron’, ‘È’, # capital C, caron accent ‘Dstrok’, ‘©’, # capital D, stroke ‘ETH’, ‘Ð’, # capital Eth, Icelandic ‘Eacute’, ‘É’, # capital E, acute accent ‘Edot’, ‘Ì’, # capital E, dot above ‘Eng’, ‘¯’, # capital Eng (Sami) ‘Eogon’, ‘Ê’, # capital E, ogonek accent ‘Emacr’, ‘ª’, # capital E, macron accent ‘Euml’, ‘Ë’, # capital E, dieresis or umlaut mark ‘Gcedil’, ‘£’, # capital G, cedilla accent ‘Iacute’, ‘Í’, # capital I, acute accent ‘Icirc’, ‘Î’, # capital I, circumflex accent ‘Imacr’, ‘¤’, # capital I, macron accent ‘Iogon’, ‘Ç’, # capital I, ogonek accent ‘Itilde’, ‘¥’, # capital I, tilde accent ‘Iuml’, ‘Ï’, # capital I, dieresis or umlaut mark ‘Lcedil’, ‘¨’, # capital L, cedil accent ‘Kcedil’, ‘¦’, # capital K, cedilla accent ‘Ncedil’, ‘Ñ’, # capital N, cedil accent ‘Oacute’, ‘Ó’, # capital O, acute accent ‘Ocirc’, ‘Ô’, # capital O, circumflex accent ‘Omacr’, ‘Ò’, # capital O, macron accent ‘Oslash’, ‘Ø’, # capital O, slash ‘Otilde’, ‘Õ’, # capital O, tilde ‘Ouml’, ‘Ö’, # capital O, dieresis or umlaut mark ‘Racute’, ‘À’, # capital R, acute accent ‘Rcedil’, ‘£’, # capital R, cedilla accent ‘Scaron’, ‘ª’, # capital S, caron accent ‘Tstrok’, ‘«’, # capital T, stroke ‘Uacute’, ‘Ú’, # capital U, acute accent ‘Ucirc’, ‘Û’, # capital U, circumflex accent ‘Umacr’, ‘®’, # capital U, macron accent ‘Uogon’, ‘Ù’, # capital U, ogonek accent ‘Utilde’, ‘×’, # capital U, tilde accent ‘Uuml’, ‘Ü’, # capital U, dieresis or umlaut mark ‘Yacute’, ‘Ý’, # capital Y, acute accent ‘Zcaron’, ‘¬’, # capital Z, caron accent ‘aacute’, ‘á’, # small a, acute accent ‘acirc’, ‘â’, # small a, circumflex accent ‘aelig’, ‘æ’, # small ae diphthong (ligature) ‘amacr’, ‘à’, # small a, macron accent ‘amp’, ‘&’, # ampersand ‘aogon’, ‘±’, # small a, ogonek accent ‘aring’, ‘å’, # small a, ring ‘atilde’, ‘ã’, # small a, tilde ‘auml’, ‘ä’, # small a, dieresis or umlaut mark
‘ccaron’, ‘è’, # small c, caron accent ‘dstrok’, ‘¹’, # small d, stroke ‘eacute’, ‘é’, # small e, acute accent ‘edot’, ‘ì’, # small e, dot above ‘emacr’, ‘º’, # small e, macron accent ‘eogon’, ‘ê’, # small e, ogonek accent ‘emdash’, ‘½’, # em-dash ‘endash’, ‘­’, # en-dash ‘eng’, ‘¿’, # small eng (Sami) ‘eth’, ‘ð’, # small eth, Icelandic ‘euml’, ‘ë’, # small e, dieresis or umlaut mark ‘gcedil’, ‘³’, # small g, cedilla accent ‘gt’, ‘>’, # greater than ‘iacute’, ‘í’, # small i, acute accent ‘icirc’, ‘î’, # small i, circumflex accent ‘imacr’, ‘´’, # small i, macron accent ‘iogon’, ‘ç’, # small i, ogonek accent ‘itilde’, ‘µ’, # small i, tilde accent ‘iuml’, ‘ï’, # small i, dieresis or umlaut mark ‘kcedil’, ‘¶’, # small k, cedilla accent ‘kgreen’, ‘¢’, # small kra (Greenlandic) ‘lcedil’, ‘¸’, # small l, cedil accent ‘lt’, ‘<’, # less than ‘ncedil’, ‘ñ’, # small n, cedil accent ‘oacute’, ‘ó’, # small o, acute accent ‘ocirc’, ‘ô’, # small o, circumflex accent ‘omacr’, ‘ò’, # small o, macron accent ‘oslash’, ‘ø’, # small o, slash ‘otilde’, ‘õ’, # small o, tilde ‘ouml’, ‘ö’, # small o, dieresis or umlaut mark ‘quot’, ‘"’, # double quote ‘racute’, ‘à’, # small r, acute accent ‘rcedil’, ‘³’, # small r, cedilla accent ‘scaron’, ‘º’, # small s, caron accent ‘szlig’, ‘ß’, # small sharp s, German (sz ligature) ‘tstrok’, ‘»’, # small t, stroke ‘uacute’, ‘ú’, # small u, acute accent ‘ucirc’, ‘û’, # small u, circumflex accent ‘umacr’, ‘¾’, # small u, macron accent ‘uogon’, ‘ù’, # small u, ogonek accent ‘utilde’, ‘÷’, # small u, tilde accent ‘uuml’, ‘ü’, # small u, dieresis or umlaut mark ‘yacute’, ‘ý’, # small y, acute accent ‘zcaron’, ‘¼’, # small z, caron accent

These do not have HTML mnemonic names …

   'nbsp', '&#160;',      # non-breaking space
   'sect', '&#167;',      # section mark

These are character types without arguments …

'grave' , "`",
'circ', '^',
'tilde', '&#126;',
'deg', '&#176;',
);

%iso_8859_10_character_map_inv = ( ‘>’ , ‘\ensuremath{>}’, ‘<’ , ‘\ensuremath{<}’, ‘&’ , ‘&’, ‘^’ , ‘\^{}’, ‘~’ , ‘\~{}’, ‘"’ , ‘“’,

 '&#160;' , '\\nobreakspace{}',
 '&#161;' , '\\k{A}',
 '&#162;' , '\\={E}',
 '&#163;' , '\\c{G}',
 '&#164;' , '\\={I}',
 '&#165;' , '\\~{I}',
 '&#166;' , '\\c{K}',
 '&#167;' , '\\S{}',
 '&#168;' , '\\c{L}',
 '&#169;' , '\\DH{}',
 '&#170;' , '\\v{S}',
 '&#171;' , '\\TL{}',
 '&#172;' , '\\v{Z}',
 '&#173;' , '{--}',
 '&#174;' , '\\={U}',
 '&#175;' , '\\NG{}',
 '&#176;' , '\\r{}',
 '&#177;' , '\\k{a}',
 '&#178;' , '\\={e}',
 '&#179;' , '\\c{g}',
 '&#180;' , '\\={\i}',
 '&#181;' , '\\~{\i}',
 '&#182;' , '\\c{k}',
 '&#183;' , '\\cdot{}',
 '&#184;' , '\\c{l}',
 '&#185;' , '\\dh{}',
 '&#186;' , '\\v{s}',
 '&#187;' , '\\tl{}',
 '&#188;' , '\\v{z}',
 '&#189;' , '{---}',
 '&#190;' , '\\={u}',
 '&#191;' , '\\ng{}',
 '&#192;' , '\\={A}',
 '&#193;' , '\\\'{A}',
 '&#194;' , '\\^{A}',
 '&#195;' , '\\~{A}',
 '&#196;' , '\\"{A}',
 '&#197;' , '\\r{A}',
 '&#198;' , '\\AE{}',
 '&#199;' , '\\k{I}',
 '&#200;' , '\\v{C}',
 '&#201;' , '\\\'{E}',
 '&#202;' , '\\k{E}',
 '&#203;' , '\\"{E}',
 '&#204;' , '\\dot{E}',
 '&#205;' , '\\\'{I}',
 '&#206;' , '\\^{I}',
 '&#207;' , '\\"{I}',
 '&#208;' , '\\DH{}',
 '&#209;' , '\\c{N}',
 '&#210;' , '\\={O}',
 '&#211;' , '\\\'{O}',
 '&#212;' , '\\^{O}',
 '&#213;' , '\\~{O}',
 '&#214;' , '\\"{O}',
 '&#215;' , '\\~{U}',
 '&#216;' , '\\O{}',
 '&#217;' , '\\k{U}',
 '&#218;' , '\\\'{U}',
 '&#219;' , '\\^{U}',
 '&#220;' , '\\"{U}',
 '&#221;' , '\\\'{Y}',
 '&#222;' , '\\TH{}',
 '&#223;' , '\\ss{}',
 '&#224;' , '\\={a}',
 '&#225;' , '\\\'{a}',
 '&#226;' , '\\^{a}',
 '&#227;' , '\\~{a}',
 '&#228;' , '\\"{a}',
 '&#229;' , '\\r{a}',
 '&#230;' , '\\ae{}',
 '&#231;' , '\\k{\i}',
 '&#232;' , '\\v{c}',
 '&#233;' , '\\\'{e}',
 '&#234;' , '\\k{e}',
 '&#235;' , '\\"{e}',
 '&#236;' , '\\dot{e}',
 '&#237;' , '\\\'{\\i}',
 '&#238;' , '\\^{\\i}',
 '&#239;' , '\\"{\i}',
 '&#240;' , '\\dh{}',
 '&#241;' , '\\c{n}',
 '&#242;' , '\\={o}',
 '&#243;' , '\\\'{o}',
 '&#244;' , '\\^{o}',
 '&#245;' , '\\~{o}',
 '&#246;' , '\\"{o}',
 '&#247;' , '\\~{u}',
 '&#248;' , '\\o{}',
 '&#249;' , '\\k{u}',
 '&#250;' , '\\\'{u}',
 '&#251;' , '\\^{u}',
 '&#252;' , '\\"{u}',
 '&#253;' , '\\\'{y}',
 '&#254;' , '\\th{}',
 '&#255;' , '\\kra{}'

);

1;