From 705e118cb1c1506151ff707a7648a5fa2978cda9 Mon Sep 17 00:00:00 2001
From: Fil <fil@rezo.net>
Date: Wed, 12 Mar 2003 01:12:28 +0000
Subject: [PATCH] gros boulot sur les charsets.
---
ecrire/inc_charsets.php3 | 510 ++++++++++++++++----------------------
ecrire/inc_documents.php3 | 2 +-
ecrire/inc_index.php3 | 4 +-
ecrire/inc_sites.php3 | 7 +-
ecrire/inc_version.php3 | 4 +-
spip_image.php3 | 5 +-
6 files changed, 226 insertions(+), 306 deletions(-)
diff --git a/ecrire/inc_charsets.php3 b/ecrire/inc_charsets.php3
index a87de32a9f..b4155dca8d 100644
--- a/ecrire/inc_charsets.php3
+++ b/ecrire/inc_charsets.php3
@@ -5,182 +5,210 @@
if (defined("_ECRIRE_INC_CHARSETS")) return;
define("_ECRIRE_INC_CHARSETS", "1");
-function filtrer_entites($texte) { // html -> texte, a completer
-
- // NB en php4 il suffirait d'utiliser get_html_translation_table/array_flip
- // HTML_ENTITIES
- $trans_iso = array(
- '¡' => "\xa1",
- '¢' => "\xa2",
- '£' => "\xa3",
- '¤' => "\xa4",
- '¥' => "\xa5",
- '¦' => "\xa6",
- '§' => "\xa7",
- '¨' => "\xa8",
- 'ª' => "\xaa",
- '«' => "\xab",
- '¬' => "\xac",
- '­' => "\xad",
- '¯' => "\xaf",
- '°' => "\xb0",
- '±' => "\xb1",
- '²' => "\xb2",
- '³' => "\xb3",
- '´' => "\xb4",
- 'µ' => "\xb5",
- '¶' => "\xb6",
- '·' => "\xb7",
- '¸' => "\xb8",
- '¹' => "\xb9",
- 'º' => "\xba",
- '»' => "\xbb",
- '¿' => "\xbf",
- 'À' => "\xc0",
- 'Á' => "\xc1",
- 'Â' => "\xc2",
- 'Ã' => "\xc3",
- 'Ä' => "\xc4",
- 'Å' => "\xc5",
- 'Æ' => "\xc6",
- 'Ç' => "\xc7",
- 'È' => "\xc8",
- 'É' => "\xc9",
- 'Ê' => "\xca",
- 'Ë' => "\xcb",
- 'Ì' => "\xcc",
- 'Í' => "\xcd",
- 'Î' => "\xce",
- 'Ï' => "\xcf",
- 'Ð' => "\xd0",
- 'Ñ' => "\xd1",
- 'Ò' => "\xd2",
- 'Ó' => "\xd3",
- 'Ô' => "\xd4",
- 'Õ' => "\xd5",
- 'Ö' => "\xd6",
- '×' => "\xd7",
- 'Ø' => "\xd8",
- 'Ù' => "\xd9",
- 'Ú' => "\xda",
- 'Û' => "\xdb",
- 'Ü' => "\xdc",
- 'Ý' => "\xdd",
- 'Þ' => "\xde",
- 'ß' => "\xdf",
- 'à' => "\xe0",
- 'á' => "\xe1",
- 'â' => "\xe2",
- 'ã' => "\xe3",
- 'ä' => "\xe4",
- 'å' => "\xe5",
- 'æ' => "\xe6",
- 'ç' => "\xe7",
- 'è' => "\xe8",
- 'é' => "\xe9",
- 'ê' => "\xea",
- 'ë' => "\xeb",
- 'ì' => "\xec",
- 'í' => "\xed",
- 'î' => "\xee",
- 'ï' => "\xef",
- 'ð' => "\xf0",
- 'ñ' => "\xf1",
- 'ò' => "\xf2",
- 'ó' => "\xf3",
- 'ô' => "\xf4",
- 'õ' => "\xf5",
- 'ö' => "\xf6",
- '÷' => "\xf7",
- 'ø' => "\xf8",
- 'ù' => "\xf9",
- 'ú' => "\xfa",
- 'û' => "\xfb",
- 'ü' => "\xfc",
- 'ý' => "\xfd",
- 'þ' => "\xfe"
- );
-
- $trans = array (
- ' ' => " ",
- '©' => "(c)",
- '®' => "(r)",
- '¼' => "1/4",
- '½' => "1/2",
- '¾' => "3/4",
- '&' => '&',
- '"' => '"',
- ''' => "'",
- '<' => '<',
- '>' => '>'
- );
-
- $texte = strtr2 ($texte, $trans);
-
- $charset = lire_meta('charset');
- if ($charset == 'iso-8859-1') // recuperer les caracteres iso-latin
- $texte = strtr2 ($texte, $trans_iso);
- else if (($charset == 'utf-8') OR ($charset == 'windows-1251')) // autres charsets supportes
- {
- // 1. recuperer les caracteres binaires en Ӓ
- $texte = entites_unicode($texte);
- // 2. les é en iso-8859-1
- $texte = strtr2 ($texte, $trans_iso);
- // 3. les iso en é
- $texte = iso_8859_1_to_unicode($texte);
- // 4. le tout dans le charset cible
- $texte = unicode2charset($texte);
- }
- return $texte;
-}
+/* charsets supportes :
+ iso-8859-1 ; utf-8 ;
+ windows-1251 = CP1251 ;
+*/
+function load_charset ($charset = 'AUTO') {
+ if ($charset == 'AUTO')
+ $charset = lire_meta('charset');
-// strtr (string $texte, array $trans) = emuler le php4
-function strtr2 ($texte, $trans) {
- global $flag_strtr2;
+ if (is_array($GLOBALS['CHARSET'][$charset]))
+ return $GLOBALS['CHARSET'][$charset];
+
+ switch($charset) {
+ case 'utf-8':
+ return $GLOBALS['CHARSET'][$charset] = array();
+
+ // iso latin 1
+ case 'iso-8859-1':
+ case '':
+ return $GLOBALS['CHARSET'][$charset] = array (
+ 128=>128, 129=>129, 130=>130, 131=>131, 132=>132, 133=>133, 134=>134, 135=>135,
+ 136=>136, 137=>137, 138=>138, 139=>139, 140=>140, 141=>141, 142=>142, 143=>143,
+ 144=>144, 145=>145, 146=>146, 147=>147, 148=>148, 149=>149, 150=>150, 151=>151,
+ 152=>152, 153=>153, 154=>154, 155=>155, 156=>156, 157=>157, 158=>158, 159=>159,
+ 160=>160, 161=>161, 162=>162, 163=>163, 164=>164, 165=>165, 166=>166, 167=>167,
+ 168=>168, 169=>169, 170=>170, 171=>171, 172=>172, 173=>173, 174=>174, 175=>175,
+ 176=>176, 177=>177, 178=>178, 179=>179, 180=>180, 181=>181, 182=>182, 183=>183,
+ 184=>184, 185=>185, 186=>186, 187=>187, 188=>188, 189=>189, 190=>190, 191=>191,
+ 192=>192, 193=>193, 194=>194, 195=>195, 196=>196, 197=>197, 198=>198, 199=>199,
+ 200=>200, 201=>201, 202=>202, 203=>203, 204=>204, 205=>205, 206=>206, 207=>207,
+ 208=>208, 209=>209, 210=>210, 211=>211, 212=>212, 213=>213, 214=>214, 215=>215,
+ 216=>216, 217=>217, 218=>218, 219=>219, 220=>220, 221=>221, 222=>222, 223=>223,
+ 224=>224, 225=>225, 226=>226, 227=>227, 228=>228, 229=>229, 230=>230, 231=>231,
+ 232=>232, 233=>233, 234=>234, 235=>235, 236=>236, 237=>237, 238=>238, 239=>239,
+ 240=>240, 241=>241, 242=>242, 243=>243, 244=>244, 245=>245, 246=>246, 247=>247,
+ 248=>248, 249=>249, 250=>250, 251=>251, 252=>252, 253=>253, 254=>254, 255=>255,
+ 256=>256
+ );
+
+
+ // iso latin 15 - Gaetan Ryckeboer <gryckeboer@virtual-net.fr>
+ case 'iso-8859-15':
+ $trans = load_charset('iso-8859-1');
+ $trans[164]=8364;
+ $trans[166]=352;
+ $trans[168]=353;
+ $trans[180]=381;
+ $trans[184]=382;
+ $trans[188]=338;
+ $trans[189]=339;
+ $trans[190]=376;
+ return $GLOBALS['CHARSET'][$charset] = $trans;
+
+
+ // cyrillic - ref. http://czyborra.com/charsets/cyrillic.html
+ case 'windows-1251':
+ case 'CP1251':
+ return $GLOBALS['CHARSET'][$charset] = array (
+ 0x80=>0x0402, 0x81=>0x0403, 0x82=>0x201A, 0x83=>0x0453, 0x84=>0x201E,
+ 0x85=>0x2026, 0x86=>0x2020, 0x87=>0x2021, 0x88=>0x20AC, 0x89=>0x2030,
+ 0x8A=>0x0409, 0x8B=>0x2039, 0x8C=>0x040A, 0x8D=>0x040C, 0x8E=>0x040B,
+ 0x8F=>0x040F, 0x90=>0x0452, 0x91=>0x2018, 0x92=>0x2019, 0x93=>0x201C,
+ 0x94=>0x201D, 0x95=>0x2022, 0x96=>0x2013, 0x97=>0x2014, 0x99=>0x2122,
+ 0x9A=>0x0459, 0x9B=>0x203A, 0x9C=>0x045A, 0x9D=>0x045C, 0x9E=>0x045B,
+ 0x9F=>0x045F, 0xA0=>0x00A0, 0xA1=>0x040E, 0xA2=>0x045E, 0xA3=>0x0408,
+ 0xA4=>0x00A4, 0xA5=>0x0490, 0xA6=>0x00A6, 0xA7=>0x00A7, 0xA8=>0x0401,
+ 0xA9=>0x00A9, 0xAA=>0x0404, 0xAB=>0x00AB, 0xAC=>0x00AC, 0xAD=>0x00AD,
+ 0xAE=>0x00AE, 0xAF=>0x0407, 0xB0=>0x00B0, 0xB1=>0x00B1, 0xB2=>0x0406,
+ 0xB3=>0x0456, 0xB4=>0x0491, 0xB5=>0x00B5, 0xB6=>0x00B6, 0xB7=>0x00B7,
+ 0xB8=>0x0451, 0xB9=>0x2116, 0xBA=>0x0454, 0xBB=>0x00BB, 0xBC=>0x0458,
+ 0xBD=>0x0405, 0xBE=>0x0455, 0xBF=>0x0457, 0xC0=>0x0410, 0xC1=>0x0411,
+ 0xC2=>0x0412, 0xC3=>0x0413, 0xC4=>0x0414, 0xC5=>0x0415, 0xC6=>0x0416,
+ 0xC7=>0x0417, 0xC8=>0x0418, 0xC9=>0x0419, 0xCA=>0x041A, 0xCB=>0x041B,
+ 0xCC=>0x041C, 0xCD=>0x041D, 0xCE=>0x041E, 0xCF=>0x041F, 0xD0=>0x0420,
+ 0xD1=>0x0421, 0xD2=>0x0422, 0xD3=>0x0423, 0xD4=>0x0424, 0xD5=>0x0425,
+ 0xD6=>0x0426, 0xD7=>0x0427, 0xD8=>0x0428, 0xD9=>0x0429, 0xDA=>0x042A,
+ 0xDB=>0x042B, 0xDC=>0x042C, 0xDD=>0x042D, 0xDE=>0x042E, 0xDF=>0x042F,
+ 0xE0=>0x0430, 0xE1=>0x0431, 0xE2=>0x0432, 0xE3=>0x0433, 0xE4=>0x0434,
+ 0xE5=>0x0435, 0xE6=>0x0436, 0xE7=>0x0437, 0xE8=>0x0438, 0xE9=>0x0439,
+ 0xEA=>0x043A, 0xEB=>0x043B, 0xEC=>0x043C, 0xED=>0x043D, 0xEE=>0x043E,
+ 0xEF=>0x043F, 0xF0=>0x0440, 0xF1=>0x0441, 0xF2=>0x0442, 0xF3=>0x0443,
+ 0xF4=>0x0444, 0xF5=>0x0445, 0xF6=>0x0446, 0xF7=>0x0447, 0xF8=>0x0448,
+ 0xF9=>0x0449, 0xFA=>0x044A, 0xFB=>0x044B, 0xFC=>0x044C, 0xFD=>0x044D,
+ 0xFE=>0x044E, 0xFF=>0x044F); // fin windows-1251
+
+
+ // ------------------------------------------------------------------
+
+ // cas particulier pour les entites html (a completer eventuellement)
+ case 'html':
+ return $GLOBALS['CHARSET'][$charset] = array (
+ 'cent'=>'¢', 'pound'=>'£', 'curren'=>'¤', 'yen'=>'¥', 'brvbar'=>'¦',
+ 'sect'=>'§', 'uml'=>'¨', 'ordf'=>'ª', 'laquo'=>'«', 'not'=>'¬',
+ 'shy'=>'­', 'macr'=>'¯', 'deg'=>'°', 'plusmn'=>'±', 'sup2'=>'²',
+ 'sup3'=>'³', 'acute'=>'´', 'micro'=>'µ', 'para'=>'¶', 'middot'=>'·',
+ 'cedil'=>'¸', 'sup1'=>'¹', 'ordm'=>'º', 'raquo'=>'»', 'iquest'=>'¿',
+ 'Agrave'=>'À', 'Aacute'=>'Á', 'Acirc'=>'Â', 'Atilde'=>'Ã', 'Auml'=>'Ä',
+ 'Aring'=>'Å', 'AElig'=>'Æ', 'Ccedil'=>'Ç', 'Egrave'=>'È', 'Eacute'=>'É',
+ 'Ecirc'=>'Ê', 'Euml'=>'Ë', 'Igrave'=>'Ì', 'Iacute'=>'Í', 'Icirc'=>'Î',
+ 'Iuml'=>'Ï', 'ETH'=>'Ð', 'Ntilde'=>'Ñ', 'Ograve'=>'Ò', 'Oacute'=>'Ó',
+ 'Ocirc'=>'Ô', 'Otilde'=>'Õ', 'Ouml'=>'Ö', 'times'=>'×', 'Oslash'=>'Ø',
+ 'Ugrave'=>'Ù', 'Uacute'=>'Ú', 'Ucirc'=>'Û', 'Uuml'=>'Ü', 'Yacute'=>'Ý',
+ 'THORN'=>'Þ', 'szlig'=>'ß', 'agrave'=>'à', 'aacute'=>'á', 'acirc'=>'â',
+ 'atilde'=>'ã', 'auml'=>'ä', 'aring'=>'å', 'aelig'=>'æ', 'ccedil'=>'ç',
+ 'egrave'=>'è', 'eacute'=>'é', 'ecirc'=>'ê', 'euml'=>'ë', 'igrave'=>'ì',
+ 'iacute'=>'í', 'icirc'=>'î', 'iuml'=>'ï', 'eth'=>'ð', 'ntilde'=>'ñ',
+ 'ograve'=>'ò', 'oacute'=>'ó', 'ocirc'=>'ô', 'otilde'=>'õ', 'ouml'=>'ö',
+ 'divide'=>'÷', 'oslash'=>'ø', 'ugrave'=>'ù', 'uacute'=>'ú',
+ 'ucirc'=>'û', 'uuml'=>'ü', 'yacute'=>'ý', 'thorn'=>'þ',
+ 'nbsp' => " ", 'copy' => "(c)", 'reg' => "(r)", 'frac14' => "1/4",
+ 'frac12' => "1/2", 'frac34' => "3/4", 'amp' => '&', 'quot' => '"',
+ 'apos' => "'", 'lt' => '<', 'gt' => '>'
+ );
+
+ // cas particulier pour la translitteration
+ case 'translit':
+ return $GLOBALS['CHARSET'][$charset] = array (
+ // latin
+ 128=>'euro', 131=>'f', 140=>'OE', 153=>'TM', 156=>'oe', 159=>'Y', 160=>' ',
+ 161=>'�', 162=>'c', 163=>'L', 164=>'O', 165=>'yen',166=>'|',
+ 167=>'p',169=>'(c)', 171=>'<<',172=>'-',173=>'-',174=>'(R)',
+ 176=>'o',177=>'+-',181=>'mu',182=>'p',183=>'.',187=>'>>', 192=>'A',
+ 193=>'A', 194=>'A', 195=>'A', 196=>'A', 197=>'A', 198=>'AE', 199=>'C',
+ 200=>'E', 201=>'E', 202=>'E', 203=>'E', 204=>'I', 205=>'I', 206=>'I',
+ 207=>'I', 209=>'N', 210=>'O', 211=>'O', 212=>'O', 213=>'O', 214=>'O',
+ 216=>'O', 217=>'U', 218=>'U', 219=>'U', 220=>'U', 223=>'B', 224=>'a',
+ 225=>'a', 226=>'a', 227=>'a', 228=>'a', 229=>'a', 230=>'ae', 231=>'c',
+ 232=>'e', 233=>'e', 234=>'e', 235=>'e', 236=>'i', 237=>'i', 238=>'i',
+ 239=>'i', 241=>'n', 242=>'o', 243=>'o', 244=>'o', 245=>'o', 246=>'o',
+ 248=>'o', 249=>'u', 250=>'u', 251=>'u', 252=>'u', 255=>'y',
+
+ // cyrillique
+ 1026=>'D%', 1027=>'G%', 8218=>'\'', 1107=>'g%', 8222=>'"', 8230=>'...',
+ 8224=>'/-', 8225=>'/=', 8364=>'EUR', 8240=>'0/00', 1033=>'LJ',
+ 8249=>'<', 1034=>'NJ', 1036=>'KJ', 1035=>'Ts', 1039=>'DZ', 1106=>'d%',
+ 8216=>'`', 8217=>'\'', 8220=>'"', 8221=>'"', 8226=>' o ', 8211=>'-',
+ 8212=>'--', 8212=>'~', 8482=>'(TM)', 1113=>'lj', 8250=>'>', 1114=>'nj',
+ 1116=>'kj', 1115=>'ts', 1119=>'dz', 1038=>'V%', 1118=>'v%', 1032=>'J%',
+ 1168=>'G3', 1025=>'IO', 1028=>'IE', 1031=>'YI', 1030=>'II',
+ 1110=>'ii', 1169=>'g3', 1105=>'io', 8470=>'No.', 1108=>'ie',
+ 1112=>'j%', 1029=>'DS', 1109=>'ds', 1111=>'yi', 1040=>'A', 1041=>'B',
+ 1042=>'V', 1043=>'G', 1044=>'D', 1045=>'E', 1046=>'ZH', 1047=>'Z',
+ 1048=>'I', 1049=>'J', 1050=>'K', 1051=>'L', 1052=>'M', 1053=>'N',
+ 1054=>'O', 1055=>'P', 1056=>'R', 1057=>'S', 1058=>'T', 1059=>'U',
+ 1060=>'F', 1061=>'H', 1062=>'C', 1063=>'CH', 1064=>'SH', 1065=>'SCH',
+ 1066=>'"', 1067=>'Y', 1068=>'\'', 1069=>'`E', 1070=>'YU', 1071=>'YA',
+ 1072=>'a', 1073=>'b', 1074=>'v', 1075=>'g', 1076=>'d', 1077=>'e',
+ 1078=>'zh', 1079=>'z', 1080=>'i', 1081=>'j', 1082=>'k', 1083=>'l',
+ 1084=>'m', 1085=>'n', 1086=>'o', 1087=>'p', 1088=>'r', 1089=>'s',
+ 1090=>'t', 1091=>'u', 1092=>'f', 1093=>'h', 1094=>'c', 1095=>'ch',
+ 1096=>'sh', 1097=>'sch', 1098=>'"', 1099=>'y', 1100=>'\'', 1101=>'`e',
+ 1102=>'yu', 1103=>'ya'
+ );
+
+ default:
+ spip_log("erreur charset $charset non supporte");
+ return $GLOBALS['CHARSET'][$charset] = array();
- if ($flag_strtr2)
- return strtr($texte,$trans);
- else {
- reset ($trans);
- while (list($entite, $remplace) = each ($trans))
- $texte = ereg_replace($entite, $remplace, $texte);
- return $texte;
}
}
+// transformer les é en unicode
+function filtrer_entites($texte) {
+ $trans = load_charset('html');
+ while (eregi('&([a-z][a-z0-9]+);', $texte, $regs) AND !$vu[$i = $regs[1]]) {
+ $vu[$i] = true;
+ if ($s = $trans[$i])
+ $texte = ereg_replace($regs[0], $s, $texte);
+ }
+
+ // remettre le tout dans le charset cible
+ $texte = unicode2charset($texte);
+ return $texte;
+}
+
// transforme une chaine en entites unicode 
-function entites_unicode($chaine, $charset='AUTO') {
+function entites_unicode($chaine, $charset='AUTO', $forcer = false) {
if ($charset == 'AUTO')
$charset=lire_meta('charset');
switch($charset) {
- case 'iso-8859-1':
- // On commente cet appel tant qu'il reste des spip v<1.5 dans la nature
- // $chaine = iso_8859_1_to_unicode($chaine);
- break;
- // FORCE-iso-8859-1 passe le message suivant : on VEUT la conversion, meme
- // si elle est desactivee dans entites_unicode pour maintenir (temporairement)
- // la lisibilite de notre backend sur des SPIP v<1.5
- case 'FORCE-iso-8859-1':
- $chaine = iso_8859_1_to_unicode($chaine);
- break;
-
case 'utf-8':
- $chaine = utf_8_to_unicode($chaine);
+ return utf_8_to_unicode($chaine);
break;
- case 'windows-1251':
- $chaine = windows_1251_to_unicode($chaine);
- break;
-
- default:
- break;
+ case 'iso-8859-1':
+ // On commente cet appel tant qu'il reste des spip v<1.5 dans la nature
+ // pour que le filtre |entites_unicode donne des backends lisibles sur ces spips.
+ if (!$forcer) return $chaine;
+ default:
+ $trans = load_charset($charset);
+ $s = '';
+ $len = strlen($chaine);
+ for ($p = 0; $p <= $len; $c = substr($chaine,$p++,1)) {
+ if ((($i=ord($c))>127) and ($j=$trans[$i]))
+ $s .= "&#$j;";
+ else
+ $s .= $c;
+ }
+ return $s;
}
- return $chaine;
}
// transforme les entites unicode  dans le charset courant
@@ -190,45 +218,23 @@ function unicode2charset($chaine, $charset='AUTO') {
switch($charset) {
- case 'iso-8859-1':
- $chaine = unicode_to_iso_8859_1($chaine);
- break;
-
case 'utf-8':
- $chaine = unicode_to_utf_8($chaine);
+ return unicode_to_utf_8($chaine);
break;
- case 'windows-1251':
- $chaine = unicode_to_windows_1251($chaine);
- break;
-
default:
- break;
+ $trans = load_charset($charset);
+ while (list($chr,$uni) = each($trans)) // array_flip
+ $ttrans[$uni] = $chr;
+ while (ereg('�*([0-9]+);', $chaine, $regs) AND !$vu[$i = intval($regs[1])]) {
+ $vu[$i] = true;
+ if ($s = $ttrans[$i])
+ $chaine = ereg_replace($regs[0], $s, $chaine);
+ }
+ return $chaine;
}
- return $chaine;
}
-//
-// Il faut deux fonctions par charset : charset->unicode et unicode->charset
-//
-
-// ISO-8859-1
-function iso_8859_1_to_unicode($chaine) {
- while ($i = ord(substr($chaine,$p++)))
- if ($i>127)
- $s .= "&#$i;";
- else
- $s .= chr($i);
- return $s;
-}
-function unicode_to_iso_8859_1($chaine) {
- while (ereg('&#([0-9]+);', $chaine, $regs) AND !$vu[$regs[1]]) {
- $vu[$regs[1]] = true;
- if ($regs[1] < 256)
- $chaine = ereg_replace($regs[0], chr($regs[1]), $chaine);
- }
- return $chaine;
-}
// UTF-8
function utf_8_to_unicode($source) {
@@ -306,8 +312,9 @@ function utf_8_to_unicode($source) {
return $encodedString;
}
+
function unicode_to_utf_8($chaine) {
- while (ereg('&#([0-9]+);', $chaine, $regs) AND !$vu[$regs[1]]) {
+ while (ereg('�*([0-9]+);', $chaine, $regs) AND !$vu[$regs[1]]) {
$num = $regs[1];
$vu[$num] = true;
if($num<128) $s = chr($num); // Ce bloc provient de php.net, auteur Ronen
@@ -321,58 +328,6 @@ function unicode_to_utf_8($chaine) {
}
-// WINDOWS-1251 (CYRILLIQUE)
-function load_windows_1251() {
- // extrait de la table
- // http://www.slav.helsinki.fi/atk/codepages/win1251.html
- static $table;
- if(is_array($table))
- return $table;
- else
- return $table = array(
- chr(129)=>'Ѓ',chr(131)=>'ѓ',chr(138)=>'Љ',chr(140)=>'Њ',chr(141)=>'Ќ',
- chr(142)=>'Ћ',chr(143)=>'Џ',chr(144)=>'ђ',chr(154)=>'љ',chr(156)=>'њ',
- chr(157)=>'ќ',chr(158)=>'ћ',chr(159)=>'џ',chr(161)=>'Ў',chr(162)=>'ў',
- chr(163)=>'Ј',chr(165)=>'Ґ',chr(168)=>'Ё',chr(170)=>'Є',chr(175)=>'Ї',
- chr(178)=>'І',chr(179)=>'і',chr(180)=>'ґ',chr(184)=>'ё',chr(186)=>'є',
- chr(188)=>'ј',chr(189)=>'Ѕ',chr(190)=>'ѕ',chr(191)=>'ї',chr(192)=>'А',
- chr(193)=>'Б',chr(194)=>'В',chr(195)=>'Г',chr(196)=>'Д',chr(197)=>'Е',
- chr(198)=>'Ж',chr(199)=>'З',chr(200)=>'И',chr(201)=>'Й',chr(202)=>'К',
- chr(203)=>'Л',chr(204)=>'М',chr(205)=>'Н',chr(206)=>'О',chr(207)=>'П',
- chr(208)=>'Р',chr(209)=>'С',chr(210)=>'Т',chr(211)=>'У',chr(212)=>'Ф',
- chr(213)=>'Х',chr(214)=>'Ц',chr(215)=>'Ч',chr(216)=>'Ш',chr(217)=>'Щ',
- chr(218)=>'Ъ',chr(219)=>'Ы',chr(220)=>'Ь',chr(221)=>'Э',chr(222)=>'Ю',
- chr(223)=>'Я',chr(224)=>'а',chr(225)=>'б',chr(226)=>'в',chr(227)=>'г',
- chr(228)=>'д',chr(229)=>'е',chr(230)=>'ж',chr(231)=>'з',chr(232)=>'и',
- chr(233)=>'й',chr(234)=>'к',chr(235)=>'л',chr(236)=>'м',chr(237)=>'н',
- chr(238)=>'о',chr(239)=>'п',chr(240)=>'р',chr(241)=>'с',chr(242)=>'т',
- chr(243)=>'у',chr(244)=>'ф',chr(245)=>'х',chr(246)=>'ц',chr(247)=>'ч',
- chr(248)=>'ш',chr(249)=>'щ',chr(250)=>'ъ',chr(251)=>'ы',chr(252)=>'ь',
- chr(253)=>'э',chr(254)=>'ю',chr(255)=>'я'
- );
-}
-function windows_1251_to_unicode($chaine) {
- $trans = load_windows_1251();
- while ($i = substr($chaine,$p++,1))
- if ($t = $trans[$i])
- $s .= $t;
- else
- $s .= $i;
- return $s;
-}
-function unicode_to_windows_1251($chaine) {
- $trans = load_windows_1251();
- while (list($chr,$uni) = each($trans)) // array_flip
- $ttrans[$uni] = $chr;
- while (ereg('&#([0-9]+);', $chaine, $regs) AND !$vu[$regs[1]]) {
- $vu[$regs[1]] = true;
- if ($ttrans[$regs[0]])
- $chaine = ereg_replace($regs[0], $ttrans[$regs[0]], $chaine);
- }
- return $chaine;
-}
-
-
//
// Translitteration charset => ascii (pour l'indexation)
//
@@ -380,58 +335,23 @@ function translitteration ($texte, $charset='AUTO') {
if ($charset == 'AUTO')
$charset = lire_meta('charset');
- if ($charset == 'iso-8859-1') {
- $texte = translit_iso8859_1($texte);
- } else if ($charset == 'windows-1251') {
- $texte = translit_windows_1251($texte);
- } else if ($GLOBALS['flag_iconv']
- AND ($iconv = @iconv(strtoupper($charset), 'ASCII//TRANSLIT', $texte))
- AND !ereg('^\?+$',$iconv))
- $texte = $iconv;
- return $texte;
-}
-
-function translit_iso8859_1($texte) {
- // Merci a phpDig (Antoine Bajolet) pour la fonction originale
- $accents =
- /* A */ chr(192).chr(193).chr(194).chr(195).chr(196).chr(197).
- /* a */ chr(224).chr(225).chr(226).chr(227).chr(228).chr(229).
- /* O */ chr(210).chr(211).chr(212).chr(213).chr(214).chr(216).
- /* o */ chr(242).chr(243).chr(244).chr(245).chr(246).chr(248).
- /* E */ chr(200).chr(201).chr(202).chr(203).
- /* e */ chr(232).chr(233).chr(234).chr(235).
- /* Cc */ chr(199).chr(231).
- /* I */ chr(204).chr(205).chr(206).chr(207).
- /* i */ chr(236).chr(237).chr(238).chr(239).
- /* U */ chr(217).chr(218).chr(219).chr(220).
- /* u */ chr(249).chr(250).chr(251).chr(252).
- /* yNn */ chr(255).chr(209).chr(241);
- return strtr($texte,
- $accents,
- "AAAAAAaaaaaaOOOOOOooooooEEEEeeeeCcIIIIiiiiUUUUuuuuyNn");
-}
-
-function translit_windows_1251($texte) {
- $code = array (
- 128=>'D',129=>'G',136=>'euro',138=>'LJ',140=>'NJ',141=>'KJ',142=>'Ts',143=>'DZ',144=>'d',149=>'o',
- 154=>'lj',156=>'nj',157=>'kj',158=>'ts',159=>'dz',161=>'V',162=>'v',163=>'J',165=>'G',168=>'IO',
- 170=>'IE',175=>'YI',178=>'II',179=>'ii',180=>'g',181=>'mu',184=>'io',186=>'ie',188=>'j',189=>'DS',
- 190=>'ds',191=>'yi',192=>'A',193=>'B',194=>'V',195=>'G',196=>'D',197=>'E',198=>'ZH',199=>'Z',
- 200=>'I',201=>'J',202=>'K',203=>'L',204=>'M',205=>'N',206=>'O',207=>'P',208=>'R',209=>'S',210=>'T',
- 211=>'U',212=>'F',213=>'H',214=>'C',215=>'CH',216=>'SH',217=>'SCH',218=>'_',219=>'Y',220=>'_',
- 221=>'e',222=>'YU',223=>'YA',224=>'a',225=>'b',226=>'v',227=>'g',228=>'d',229=>'e',230=>'zh',
- 231=>'z',232=>'i',233=>'j',234=>'k',235=>'l',236=>'m',237=>'n',238=>'o',239=>'p',240=>'r',241=>'s',
- 242=>'t',243=>'u',244=>'f',245=>'h',246=>'c',247=>'ch',248=>'sh',249=>'sch',250=>' ',251=>'y',
- 252=>'_',253=>'E',254=>'yu',255=>'ya');
-
- for ($i=0; $i<strlen($texte);$i++) {
- $d = substr($texte,$i,1);
- if ($c = $code[ord($d)])
- $ret .= $c;
- else
- $ret .= $d;
+ // 1. passer en unicode
+ $texte = entites_unicode(filtrer_entites($texte), $charset, true);
+
+ // 2. translitterer
+ $trans = load_charset('translit');
+ while (ereg('�*([0-9]+);', $texte, $regs) AND !$vu[$i = $regs[1]]) {
+ $vu[$i] = true;
+ if ($s = $trans[$i])
+ $texte = ereg_replace($regs[0], $s, $texte);
+ // on va tenter de trouver la translitteration ailleurs
+ // - dans iconv par exemple
+ else if ($GLOBALS['flag_iconv'] AND ($iconv = @iconv($charset, 'ASCII//TRANSLIT', $texte)) AND !ereg('^\?+$',$iconv)) {
+ $GLOBALS['CHARSET']['translit'][$i] = $iconv;
+ $texte = ereg_replace($regs[0], $iconv, $texte);
+ }
}
- return $ret;
+ return $texte;
}
-?>
\ No newline at end of file
+?>
diff --git a/ecrire/inc_documents.php3 b/ecrire/inc_documents.php3
index f85a9f2d4a..6f39a4d534 100644
--- a/ecrire/inc_documents.php3
+++ b/ecrire/inc_documents.php3
@@ -411,7 +411,7 @@ function afficher_documents_non_inclus($id_article, $type = "article", $flag_mod
/// Ajouter nouveau document/image
echo debut_cadre_enfonce("doc-24.gif",false,"creer.gif");
- echo "<div style='padding: 2px; background-color: $couleur_claire; text-align: ".$GLOBALS['spip_lang_right']."; color: black;'>";
+ echo "<div style='padding: 2px; background-color: $couleur_claire; text-align: ".$GLOBALS['spip_lang_left']."; color: black;'>";
echo bouton_block_invisible("ajouter_document");
if ($type == "rubrique") echo "<b><font size=1>"._T('titre_publier_document')."</font></b>".aide("ins_doc");
else echo "<b><font size=1>"._T('titre_joindre_document')."</font></b>".aide("ins_doc");
diff --git a/ecrire/inc_index.php3 b/ecrire/inc_index.php3
index ef78228b84..f0635b1f71 100644
--- a/ecrire/inc_index.php3
+++ b/ecrire/inc_index.php3
@@ -7,12 +7,12 @@ define("_ECRIRE_INC_INDEX", "1");
function nettoyer_chaine_indexation($texte) {
include_ecrire("inc_charsets.php3");
- return strtr(strtolower(translitteration($texte)), '\'"',' ');
+ return eregi_replace("[^A-Z0-9_-]","",strtolower(translitteration($texte)));
}
// Merci a Herve Lefebvre pour son apport sur cette fonction
function separateurs_indexation() {
- return "].,;`:*'\"?!\r\n\t\\/\~(){}[|&@<>$%#".
+ return "].,`:*'\"?!\r\n\t\\/\~(){}[|@<>$%".
chr(187).chr(171).chr(133).chr(145).chr(146).chr(180).chr(147).chr(148);
}
diff --git a/ecrire/inc_sites.php3 b/ecrire/inc_sites.php3
index cfb633f7ba..70f9beb085 100644
--- a/ecrire/inc_sites.php3
+++ b/ecrire/inc_sites.php3
@@ -88,13 +88,14 @@ function recuperer_page($url) {
function transcoder_page($texte) {
// Si le backend precise son charset et que celui-ci est connu de SPIP,
- // decoder puis rencoder
+ // decoder puis recoder
if (eregi('<\\?xml[[:space:]][^>]*(utf-8)', $texte, $regs)) {
$charset_page = $regs[1];
$texte = unicode2charset(entites_unicode($texte, $charset_page));
}
- // Si le backend ne precise pas, on considere qu'il est iso-8859-1
- else $texte = unicode2charset(entites_unicode($texte, 'FORCE-iso-8859-1'));
+ // Si le backend ne precise pas, on considere qu'il est iso-8859-1 : il faut
+ // alors forcer la conversion
+ else $texte = unicode2charset(entites_unicode($texte, 'iso-8859-1', true));
return $texte;
}
diff --git a/ecrire/inc_version.php3 b/ecrire/inc_version.php3
index 544b3e25c4..66a17e121f 100644
--- a/ecrire/inc_version.php3
+++ b/ecrire/inc_version.php3
@@ -245,8 +245,8 @@ function spip_setcookie ($name='', $value='', $expire=0, $path='', $domain='', $
$name = ereg_replace ('^spip', $GLOBALS['cookie_prefix'], $name);
// patch safari beta 51-60
- if (!$path AND eregi("Safari", $GLOBALS['HTTP_USER_AGENT']))
- $path = ereg_replace("/[^/]+$", "/", $GLOBALS['REQUEST_URI']);
+ if (!$path AND eregi("Safari", $GLOBALS['HTTP_USER_AGENT']))
+ $path = ereg_replace("/[^/]+$", "/", $GLOBALS['REQUEST_URI']);
if ($secure)
@setcookie ($name, $value, $expire, $path, $domain, $secure);
diff --git a/spip_image.php3 b/spip_image.php3
index 3a5e135841..6f6d46af5c 100644
--- a/spip_image.php3
+++ b/spip_image.php3
@@ -3,7 +3,7 @@
include ("ecrire/inc_version.php3");
include_ecrire("inc_filtres.php3");
-include_ecrire("inc_index.php3");
+include_ecrire("inc_charsets.php3");
include_ecrire("inc_meta.php3");
include_ecrire("inc_admin.php3");
include_local("inc-cache.php3");
@@ -281,8 +281,7 @@ function ajout_doc($orig, $source, $dest, $mode, $id_document, $doc_vignette='',
$dest = 'IMG/';
if (creer_repertoire('IMG', $ext))
$dest .= $ext.'/';
- $dest .= ereg_replace("[^.a-zA-Z0-9_=-]+", "_",
- nettoyer_chaine_indexation(ereg_replace("\.([^.]+)$", "", supprimer_tags(basename($orig)))));
+ $dest .= ereg_replace("[^.a-zA-Z0-9_=-]+", "_", translitteration(ereg_replace("\.([^.]+)$", "", supprimer_tags(basename($orig)))));
$n = 0;
while (file_exists($newFile = $dest.($n++ ? '-'.$n : '').'.'.$ext));
$dest_path = $newFile;
--
GitLab