fixed alignment of folder list title text
[squirrelmail.git] / functions / i18n.php
CommitLineData
59177427 1<?php
1fd97780 2
35586184 3/**
d3bab52e 4 * SquirrelMail internationalization functions
35586184 5 *
2ba706ef 6 * Copyright (c) 1999-2004 The SquirrelMail Project Team
35586184 7 * Licensed under the GNU GPL. For full terms see the file COPYING.
8 *
9 * This file contains variuos functions that are needed to do
10 * internationalization of SquirrelMail.
11 *
12 * Internally the output character set is used. Other characters are
13 * encoded using Unicode entities according to HTML 4.0.
14 *
a8a1c36d 15 * @version $Id$
d6c32258 16 * @package squirrelmail
a8a1c36d 17 * @subpackage i18n
35586184 18 */
19
d6c32258 20/** Everything uses global.php... */
961ca3d8 21require_once(SM_PATH . 'functions/global.php');
22
d6c32258 23/**
51468260 24 * Converts string from given charset to charset, that can be displayed by user translation.
25 *
26 * Function by default returns html encoded strings, if translation uses different encoding.
27 * If Japanese translation is used - function returns string converted to euc-jp
28 * If iconv or recode functions are enabled and translation uses utf-8 - function returns utf-8 encoded string.
29 * If $charset is not supported - function returns unconverted string.
d6c32258 30 *
51468260 31 * sanitizing of html tags is also done by this function.
32 *
d6c32258 33 * @param string $charset
34 * @param string $string Text to be decoded
51468260 35 * @return string decoded string
d6c32258 36 */
a2a7852b 37function charset_decode ($charset, $string) {
3ec81e63 38 global $languages, $squirrelmail_language, $default_charset;
edf2c0ba 39 global $use_php_recode, $use_php_iconv, $agresive_decoding;
a2a7852b 40
3714db45 41 if (isset($languages[$squirrelmail_language]['XTRA_CODE']) &&
42 function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) {
6fbd125b 43 $string = $languages[$squirrelmail_language]['XTRA_CODE']('decode', $string);
44 }
b05c8961 45
3ec81e63 46 $charset = strtolower($charset);
47
48 set_my_charset();
49
50 // Variables that allow to use functions without function_exist() calls
edf2c0ba 51 if (! isset($use_php_recode) || $use_php_recode=="" ) {
03db90bc 52 $use_php_recode=false; }
edf2c0ba 53 if (! isset($use_php_iconv) || $use_php_iconv=="" ) {
54 $use_php_iconv=false; }
3ec81e63 55
56 // Don't do conversion if charset is the same.
57 if ( $charset == strtolower($default_charset) )
58 return htmlspecialchars($string);
59
60 // catch iso-8859-8-i thing
61 if ( $charset == "iso-8859-8-i" )
62 $charset = "iso-8859-8";
63
64 /*
65 * Recode converts html special characters automatically if you use
66 * 'charset..html' decoding. There is no documented way to put -d option
67 * into php recode function call.
68 */
69 if ( $use_php_recode ) {
70 if ( $default_charset == "utf-8" ) {
03db90bc 71 // other charsets can be converted to utf-8 without loss.
72 // and output string is smaller
73 $string = recode_string($charset . "..utf-8",$string);
74 return htmlspecialchars($string);
3ec81e63 75 } else {
03db90bc 76 $string = recode_string($charset . "..html",$string);
77 // recode does not convert single quote, htmlspecialchars does.
78 $string = str_replace("'", '&#039;', $string);
79 return $string;
3ec81e63 80 }
81 }
82
83 // iconv functions does not have html target and can be used only with utf-8
84 if ( $use_php_iconv && $default_charset=='utf-8') {
85 $string = iconv($charset,$default_charset,$string);
86 return htmlspecialchars($string);
87 }
88
89 // If we don't use recode and iconv, we'll do it old way.
90
a2a7852b 91 /* All HTML special characters are 7 bit and can be replaced first */
cef054e4 92
098ea084 93 $string = htmlspecialchars ($string);
a2a7852b 94
5dd23dac 95 /* controls cpu and memory intensive decoding cycles */
edf2c0ba 96 if (! isset($agresive_decoding) || $agresive_decoding=="" ) {
97 $agresive_decoding=false; }
5dd23dac 98
b142de74 99 $decode=fixcharset($charset);
100 $decodefile=SM_PATH . 'functions/decode/' . $decode . '.php';
101 if (file_exists($decodefile)) {
03db90bc 102 include_once($decodefile);
103 $ret = call_user_func('charset_decode_'.$decode, $string);
a2a7852b 104 } else {
03db90bc 105 $ret = $string;
a2a7852b 106 }
107 return( $ret );
108}
03db90bc 109
b142de74 110/**
d3bab52e 111 * Converts html string to given charset
112 * @param string $string
113 * @param string $charset
78be8403 114 * @param boolean $htmlencode keep htmlspecialchars encoding
d3bab52e 115 * @param string
116 */
78be8403 117function charset_encode($string,$charset,$htmlencode=true) {
d3bab52e 118 global $default_charset;
119
78be8403 120 // Undo html special chars
121 if (! $htmlencode ) {
122 $string = str_replace(array('&amp;','&gt;','&lt;','&quot;'),array('&','>','<','"'),$string);
123 }
124
d3bab52e 125 $encode=fixcharset($charset);
126 $encodefile=SM_PATH . 'functions/encode/' . $encode . '.php';
127 if (file_exists($encodefile)) {
128 include_once($encodefile);
129 $ret = call_user_func('charset_encode_'.$encode, $string);
130 } else {
131 $ret = $string;
132 }
133 return( $ret );
134}
135
136/**
137 * Combined decoding and encoding functions
138 *
139 * If conversion is done to charset different that utf-8, unsupported symbols
140 * will be replaced with question marks.
141 * @param string $in_charset initial charset
142 * @param string $string string that has to be converted
143 * @param string $out_charset final charset
78be8403 144 * @param boolean $htmlencode keep htmlspecialchars encoding
d3bab52e 145 * @return string converted string
146 */
78be8403 147function charset_convert($in_charset,$string,$out_charset,$htmlencode=true) {
d3bab52e 148 $string=charset_decode($in_charset,$string);
78be8403 149 $string=charset_encode($string,$out_charset,$htmlencode);
d3bab52e 150 return $string;
151}
152
153/**
b142de74 154 * Makes charset name suitable for decoding cycles
155 *
156 * @param string $charset Name of charset
157 * @return string $charset Adjusted name of charset
158 */
159function fixcharset($charset) {
160 // minus removed from function names
161 $charset=str_replace('-','_',$charset);
162
163 // windows-125x and cp125x charsets
164 $charset=str_replace('windows_','cp',$charset);
a2a7852b 165
b142de74 166 // ibm > cp
167 $charset=str_replace('ibm','cp',$charset);
168
169 // iso-8859-8-i -> iso-8859-8
170 // use same cycle until I'll find differences
171 $charset=str_replace('iso_8859_8_i','iso_8859_8',$charset);
172
173 return $charset;
174}
a2a7852b 175
51468260 176/**
a2a7852b 177 * Set up the language to be output
178 * if $do_search is true, then scan the browser information
179 * for a possible language that we know
51468260 180 *
181 * Function sets system locale environment (LC_ALL, LANG, LANGUAGE),
182 * gettext translation bindings and html header information.
183 *
5679405c 184 * Function returns error codes, if there is some fatal error.
51468260 185 * 0 = no error,
186 * 1 = mbstring support is not present,
187 * 2 = mbstring support is not present, user's translation reverted to en_US.
188 *
189 * @param string $sm_language translation used by user's interface
190 * @param bool $do_search use browser's preferred language detection functions. Defaults to false.
191 * @param bool $default set $sm_language to $squirrelmail_default_language if language detection fails or language is not set. Defaults to false.
192 * @return int function execution error codes.
a2a7852b 193 */
67a8c90a 194function set_up_language($sm_language, $do_search = false, $default = false) {
a2a7852b 195
196 static $SetupAlready = 0;
9eb0fbd4 197 global $use_gettext, $languages,
a2a7852b 198 $squirrelmail_language, $squirrelmail_default_language,
51468260 199 $sm_notAlias, $username, $data_dir;
a2a7852b 200
201 if ($SetupAlready) {
202 return;
203 }
a65846a7 204
5c920668 205 $SetupAlready = TRUE;
961ca3d8 206 sqgetGlobalVar('HTTP_ACCEPT_LANGUAGE', $accept_lang, SQ_SERVER);
a2a7852b 207
961ca3d8 208 if ($do_search && ! $sm_language && isset($accept_lang)) {
209 $sm_language = substr($accept_lang, 0, 2);
a2a7852b 210 }
66d7950f 211
67a8c90a 212 if ((!$sm_language||$default) && isset($squirrelmail_default_language)) {
a2a7852b 213 $squirrelmail_language = $squirrelmail_default_language;
66d7950f 214 $sm_language = $squirrelmail_default_language;
a2a7852b 215 }
216 $sm_notAlias = $sm_language;
3ec81e63 217
218 // Catching removed translation
219 // System reverts to English translation if user prefs contain translation
2ba706ef 220 // that is not available in $languages array
3ec81e63 221 if (!isset($languages[$sm_notAlias])) {
222 $sm_notAlias="en_US";
223 }
224
a2a7852b 225 while (isset($languages[$sm_notAlias]['ALIAS'])) {
226 $sm_notAlias = $languages[$sm_notAlias]['ALIAS'];
227 }
228
88cb1b4d 229 if ( isset($sm_language) &&
5c920668 230 $use_gettext &&
231 $sm_language != '' &&
232 isset($languages[$sm_notAlias]['CHARSET']) ) {
a65846a7 233 bindtextdomain( 'squirrelmail', SM_PATH . 'locale/' );
88cb1b4d 234 textdomain( 'squirrelmail' );
03db90bc 235 if (function_exists('bind_textdomain_codeset')) {
236 if ($sm_notAlias == 'ja_JP') {
237 bind_textdomain_codeset ("squirrelmail", 'EUC-JP');
a5970d71 238 } else {
03db90bc 239 bind_textdomain_codeset ("squirrelmail", $languages[$sm_notAlias]['CHARSET'] );
240 }
241 }
242 if (isset($languages[$sm_notAlias]['LOCALE'])){
243 $longlocale=$languages[$sm_notAlias]['LOCALE'];
244 } else {
245 $longlocale=$sm_notAlias;
246 }
88cb1b4d 247 if ( !ini_get('safe_mode') &&
f2374580 248 getenv( 'LC_ALL' ) != $longlocale ) {
249 putenv( "LC_ALL=$longlocale" );
250 putenv( "LANG=$longlocale" );
251 putenv( "LANGUAGE=$longlocale" );
a2a7852b 252 }
03db90bc 253 setlocale(LC_ALL, $longlocale);
254
255 // Set text direction/alignment variables
256 if (isset($languages[$sm_notAlias]['DIR']) &&
257 $languages[$sm_notAlias]['DIR'] == 'rtl') {
258 /**
259 * Text direction
260 * @global string $text_direction
261 */
262 $text_direction='rtl';
263 /**
264 * Left alignment
265 * @global string $left_align
266 */
267 $left_align='right';
268 /**
269 * Right alignment
270 * @global string $right_align
271 */
272 $right_align='left';
273 } else {
274 $text_direction='ltr';
275 $left_align='left';
276 $right_align='right';
277 }
278
279 $squirrelmail_language = $sm_notAlias;
a5970d71 280 if ($squirrelmail_language == 'ja_JP') {
b05c8961 281 header ('Content-Type: text/html; charset=EUC-JP');
282 if (!function_exists('mb_internal_encoding')) {
03db90bc 283 // Error messages can't be displayed here
284 $error = 1;
285 // Revert to English if possible.
286 if (function_exists('setPref') && $username!='' && $data_dir!="") {
287 setPref($data_dir, $username, 'language', "en_US");
288 $error = 2;
289 }
290 // stop further execution in order not to get php errors on mb_internal_encoding().
291 return $error;
e842b215 292 }
293 if (function_exists('mb_language')) {
294 mb_language('Japanese');
b05c8961 295 }
296 mb_internal_encoding('EUC-JP');
297 mb_http_output('pass');
298 } else {
5c920668 299 header( 'Content-Type: text/html; charset=' . $languages[$sm_notAlias]['CHARSET'] );
a2a7852b 300 }
301}
51468260 302 return 0;
b05c8961 303}
a2a7852b 304
51468260 305/**
306 * Sets default_charset variable according to the one that is used by user's translations.
307 *
308 * Function changes global $default_charset variable in order to be sure, that it
309 * contains charset used by user's translation. Sanity of $squirrelmail_default_language
310 * and $default_charset combination provided in SquirrelMail config is also tested.
311 *
312 * There can be a $default_charset setting in the
313 * config.php file, but the user may have a different language
314 * selected for a user interface. This function checks the
315 * language selected by the user and tags the outgoing messages
316 * with the appropriate charset corresponding to the language
317 * selection. This is "more right" (tm), than just stamping the
318 * message blindly with the system-wide $default_charset.
319 */
a2a7852b 320function set_my_charset(){
94965562 321 global $data_dir, $username, $default_charset, $languages, $squirrelmail_default_language;
88cb1b4d 322
a2a7852b 323 $my_language = getPref($data_dir, $username, 'language');
5c920668 324 if (!$my_language) {
94965562 325 $my_language = $squirrelmail_default_language ;
5c920668 326 }
3ec81e63 327 // Catch removed translation
328 if (!isset($languages[$my_language])) {
329 $my_language="en_US";
330 }
a2a7852b 331 while (isset($languages[$my_language]['ALIAS'])) {
f7e8861e 332 $my_language = $languages[$my_language]['ALIAS'];
a2a7852b 333 }
5c920668 334 $my_charset = $languages[$my_language]['CHARSET'];
a2a7852b 335 if ($my_charset) {
336 $default_charset = $my_charset;
337 }
338}
339
a2a7852b 340/* ------------------------------ main --------------------------- */
341
5c920668 342global $squirrelmail_language, $languages, $use_gettext;
343
a2a7852b 344if (! isset($squirrelmail_language)) {
345 $squirrelmail_language = '';
346}
347
51468260 348/**
349 * Array specifies the available translations.
350 *
351 * Structure of array:
352 * $languages['language']['variable'] = 'value'
353 *
354 * Possible 'variable' names:
355 * NAME - Translation name in English
356 * CHARSET - Encoding used by translation
357 * ALIAS - used when 'language' is only short name and 'value' should provide long language name
358 * ALTNAME - Native translation name. Any 8bit symbols must be html encoded.
359 * LOCALE - Full locale name (in xx_XX.charset format)
360 * DIR - Text direction. Used to define Right-to-Left languages. Possible values 'rtl' or 'ltr'. If undefined - defaults to 'ltr'
361 * XTRA_CODE - translation uses special functions. 'value' provides name of that extra function
362 *
363 * Each 'language' definition requires NAME+CHARSET or ALIAS variables.
364 *
365 * @name $languages
a8a1c36d 366 * @global array $languages
51468260 367 */
a8fa8e33 368$languages['bg_BG']['NAME'] = 'Bulgarian';
369$languages['bg_BG']['ALTNAME'] = '&#1041;&#1098;&#1083;&#1075;&#1072;&#1088;&#1089;&#1082;&#1080;';
370$languages['bg_BG']['CHARSET'] = 'windows-1251';
c30be3cf 371$languages['bg_BG']['LOCALE'] = 'bg_BG.CP1251';
a8fa8e33 372$languages['bg']['ALIAS'] = 'bg_BG';
373
374$languages['ca_ES']['NAME'] = 'Catalan';
375$languages['ca_ES']['CHARSET'] = 'iso-8859-1';
a00d341d 376$languages['ca_ES']['LOCALE'] = 'ca_ES.ISO8859-1';
a8fa8e33 377$languages['ca']['ALIAS'] = 'ca_ES';
378
379$languages['cs_CZ']['NAME'] = 'Czech';
380$languages['cs_CZ']['ALTNAME'] = '&#268;e&scaron;tina';
381$languages['cs_CZ']['CHARSET'] = 'iso-8859-2';
a00d341d 382$languages['cs_CZ']['LOCALE'] = 'cs_CZ.ISO8859-2';
a8fa8e33 383$languages['cs']['ALIAS'] = 'cs_CZ';
384
385$languages['cy_GB']['NAME'] = 'Welsh';
386$languages['cy_GB']['ALTNAME'] = 'Cymraeg';
387$languages['cy_GB']['CHARSET'] = 'iso-8859-1';
a00d341d 388$languages['cy_GB']['LOCALE'] = 'cy_GB.ISO8859-1';
a8fa8e33 389$languages['cy']['ALIAS'] = 'cy_GB';
390
391// Danish locale is da_DK.
392$languages['da_DK']['NAME'] = 'Danish';
393$languages['da_DK']['ALTNAME'] = 'Dansk';
394$languages['da_DK']['CHARSET'] = 'iso-8859-1';
a00d341d 395$languages['da_DK']['LOCALE'] = 'da_DK.ISO8859-1';
a8fa8e33 396$languages['da']['ALIAS'] = 'da_DK';
397
398$languages['de_DE']['NAME'] = 'German';
399$languages['de_DE']['ALTNAME'] = 'Deutsch';
400$languages['de_DE']['CHARSET'] = 'iso-8859-1';
a00d341d 401$languages['de_DE']['LOCALE'] = 'de_DE.ISO8859-1';
a8fa8e33 402$languages['de']['ALIAS'] = 'de_DE';
403
404$languages['el_GR']['NAME'] = 'Greek';
405$languages['el_GR']['ALTNAME'] = '&Epsilon;&lambda;&lambda;&eta;&nu;&iota;&kappa;&#940;';
406$languages['el_GR']['CHARSET'] = 'iso-8859-7';
a00d341d 407$languages['el_GR']['LOCALE'] = 'el_GR.ISO8859-7';
a8fa8e33 408$languages['el']['ALIAS'] = 'el_GR';
a2a7852b 409
3bb3d83b 410$languages['en_GB']['NAME'] = 'British';
411$languages['en_GB']['CHARSET'] = 'iso-8859-15';
a00d341d 412$languages['en_GB']['LOCALE'] = 'en_GB.ISO8859-15';
3bb3d83b 413
5c920668 414$languages['en_US']['NAME'] = 'English';
415$languages['en_US']['CHARSET'] = 'iso-8859-1';
a00d341d 416$languages['en_US']['LOCALE'] = 'en_US.ISO8859-1';
5c920668 417$languages['en']['ALIAS'] = 'en_US';
a2a7852b 418
a8fa8e33 419$languages['es_ES']['NAME'] = 'Spanish';
420$languages['es_ES']['ALTNAME'] = 'Espa&ntilde;ol';
421$languages['es_ES']['CHARSET'] = 'iso-8859-1';
a00d341d 422$languages['es_ES']['LOCALE'] = 'es_ES.ISO8859-1';
a8fa8e33 423$languages['es']['ALIAS'] = 'es_ES';
424
425$languages['et_EE']['NAME'] = 'Estonian';
426$languages['et_EE']['CHARSET'] = 'iso-8859-15';
a00d341d 427$languages['et_EE']['LOCALE'] = 'et_EE.ISO8859-15';
a8fa8e33 428$languages['et']['ALIAS'] = 'et_EE';
429
2d268514 430$languages['eu_ES']['NAME'] = 'Basque';
431$languages['eu_ES']['CHARSET'] = 'iso-8859-1';
432$languages['eu_ES']['LOCALE'] = 'eu_ES.ISO8859-1';
433$languages['eu']['ALIAS'] = 'eu_ES';
434
a8fa8e33 435$languages['fo_FO']['NAME'] = 'Faroese';
436$languages['fo_FO']['CHARSET'] = 'iso-8859-1';
a00d341d 437$languages['fo_FO']['LOCALE'] = 'fo_FO.ISO8859-1';
a8fa8e33 438$languages['fo']['ALIAS'] = 'fo_FO';
439
440$languages['fi_FI']['NAME'] = 'Finnish';
441$languages['fi_FI']['ALTNAME'] = 'Suomi';
442$languages['fi_FI']['CHARSET'] = 'iso-8859-1';
a00d341d 443$languages['fi_FI']['LOCALE'] = 'fi_FI.ISO8859-1';
a8fa8e33 444$languages['fi']['ALIAS'] = 'fi_FI';
445
446$languages['fr_FR']['NAME'] = 'French';
447$languages['fr_FR']['ALTNAME'] = 'Fran&#231;ais';
448$languages['fr_FR']['CHARSET'] = 'iso-8859-1';
a00d341d 449$languages['fr_FR']['LOCALE'] = 'fr_FR.ISO8859-1';
a8fa8e33 450$languages['fr']['ALIAS'] = 'fr_FR';
451
452$languages['hr_HR']['NAME'] = 'Croatian';
453$languages['hr_HR']['CHARSET'] = 'iso-8859-2';
a00d341d 454$languages['hr_HR']['LOCALE'] = 'hr_HR.ISO8859-2';
a8fa8e33 455$languages['hr']['ALIAS'] = 'hr_HR';
456
457$languages['hu_HU']['NAME'] = 'Hungarian';
458$languages['hu_HU']['ALTNAME'] = 'Magyar';
459$languages['hu_HU']['CHARSET'] = 'iso-8859-2';
a00d341d 460$languages['hu_HU']['LOCALE'] = 'hu_HU.ISO8859-2';
a8fa8e33 461$languages['hu']['ALIAS'] = 'hu_HU';
462
463$languages['id_ID']['NAME'] = 'Indonesian';
464$languages['id_ID']['ALTNAME'] = 'Bahasa Indonesia';
465$languages['id_ID']['CHARSET'] = 'iso-8859-1';
a00d341d 466$languages['id_ID']['LOCALE'] = 'id_ID.ISO8859-1';
a8fa8e33 467$languages['id']['ALIAS'] = 'id_ID';
468
469$languages['is_IS']['NAME'] = 'Icelandic';
470$languages['is_IS']['ALTNAME'] = '&Iacute;slenska';
471$languages['is_IS']['CHARSET'] = 'iso-8859-1';
a00d341d 472$languages['is_IS']['LOCALE'] = 'is_IS.ISO8859-1';
a8fa8e33 473$languages['is']['ALIAS'] = 'is_IS';
474
475$languages['it_IT']['NAME'] = 'Italian';
476$languages['it_IT']['CHARSET'] = 'iso-8859-1';
a00d341d 477$languages['it_IT']['LOCALE'] = 'it_IT.ISO8859-1';
a8fa8e33 478$languages['it']['ALIAS'] = 'it_IT';
479
480$languages['ja_JP']['NAME'] = 'Japanese';
481$languages['ja_JP']['ALTNAME'] = '&#26085;&#26412;&#35486;';
482$languages['ja_JP']['CHARSET'] = 'iso-2022-jp';
51468260 483$languages['ja_JP']['LOCALE'] = 'ja_JP.EUC-JP';
a8fa8e33 484$languages['ja_JP']['XTRA_CODE'] = 'japanese_charset_xtra';
485$languages['ja']['ALIAS'] = 'ja_JP';
486
487$languages['ko_KR']['NAME'] = 'Korean';
488$languages['ko_KR']['CHARSET'] = 'euc-KR';
c30be3cf 489$languages['ko_KR']['LOCALE'] = 'ko_KR.EUC-KR';
1c9787d6 490// Function does not provide all needed options
491// $languages['ko_KR']['XTRA_CODE'] = 'korean_charset_xtra';
a8fa8e33 492$languages['ko']['ALIAS'] = 'ko_KR';
493
494$languages['lt_LT']['NAME'] = 'Lithuanian';
495$languages['lt_LT']['ALTNAME'] = 'Lietuvi&#371;';
496$languages['lt_LT']['CHARSET'] = 'utf-8';
497$languages['lt_LT']['LOCALE'] = 'lt_LT.UTF-8';
498$languages['lt']['ALIAS'] = 'lt_LT';
499
500$languages['nl_NL']['NAME'] = 'Dutch';
501$languages['nl_NL']['ALTNAME'] = 'Nederlands';
502$languages['nl_NL']['CHARSET'] = 'iso-8859-1';
a00d341d 503$languages['nl_NL']['LOCALE'] = 'nl_NL.ISO8859-1';
a8fa8e33 504$languages['nl']['ALIAS'] = 'nl_NL';
505
506$languages['ms_MY']['NAME'] = 'Malay';
507$languages['ms_MY']['ALTNAME'] = 'Bahasa Melayu';
508$languages['ms_MY']['CHARSET'] = 'iso-8859-1';
a00d341d 509$languages['ms_MY']['LOCALE'] = 'ms_MY.ISO8859-1';
a8fa8e33 510$languages['my']['ALIAS'] = 'ms_MY';
511
850db3c8 512$languages['nb_NO']['NAME'] = 'Norwegian (Bokm&aring;l)';
513$languages['nb_NO']['ALTNAME'] = 'Norsk (Bokm&aring;l)';
514$languages['nb_NO']['CHARSET'] = 'iso-8859-1';
a00d341d 515$languages['nb_NO']['LOCALE'] = 'nb_NO.ISO8859-1';
850db3c8 516$languages['nb']['ALIAS'] = 'nb_NO';
a8fa8e33 517
518$languages['nn_NO']['NAME'] = 'Norwegian (Nynorsk)';
519$languages['nn_NO']['ALTNAME'] = 'Norsk (Nynorsk)';
520$languages['nn_NO']['CHARSET'] = 'iso-8859-1';
a00d341d 521$languages['nn_NO']['LOCALE'] = 'nn_NO.ISO8859-1';
a8fa8e33 522
523$languages['pl_PL']['NAME'] = 'Polish';
524$languages['pl_PL']['ALTNAME'] = 'Polski';
525$languages['pl_PL']['CHARSET'] = 'iso-8859-2';
a00d341d 526$languages['pl_PL']['LOCALE'] = 'pl_PL.ISO8859-2';
a8fa8e33 527$languages['pl']['ALIAS'] = 'pl_PL';
528
529$languages['pt_PT']['NAME'] = 'Portuguese (Portugal)';
530$languages['pt_PT']['CHARSET'] = 'iso-8859-1';
a00d341d 531$languages['pt_PT']['LOCALE'] = 'pt_PT.ISO8859-1';
a8fa8e33 532$languages['pt']['ALIAS'] = 'pt_PT';
533
534$languages['pt_BR']['NAME'] = 'Portuguese (Brazil)';
535$languages['pt_BR']['ALTNAME'] = 'Portugu&ecirc;s do Brasil';
536$languages['pt_BR']['CHARSET'] = 'iso-8859-1';
a00d341d 537$languages['pt_BR']['LOCALE'] = 'pt_BR.ISO8859-1';
a8fa8e33 538
539$languages['ro_RO']['NAME'] = 'Romanian';
540$languages['ro_RO']['ALTNAME'] = 'Rom&acirc;n&#259;';
541$languages['ro_RO']['CHARSET'] = 'iso-8859-2';
a00d341d 542$languages['ro_RO']['LOCALE'] = 'ro_RO.ISO8859-2';
a8fa8e33 543$languages['ro']['ALIAS'] = 'ro_RO';
544
545$languages['ru_RU']['NAME'] = 'Russian';
546$languages['ru_RU']['ALTNAME'] = '&#1056;&#1091;&#1089;&#1089;&#1082;&#1080;&#1081;';
547$languages['ru_RU']['CHARSET'] = 'utf-8';
c30be3cf 548$languages['ru_RU']['LOCALE'] = 'ru_RU.UTF-8';
a8fa8e33 549$languages['ru']['ALIAS'] = 'ru_RU';
550
c30be3cf 551$languages['sk_SK']['NAME'] = 'Slovak';
552$languages['sk_SK']['CHARSET'] = 'iso-8859-2';
a00d341d 553$languages['sk_SK']['LOCALE'] = 'sk_SK.ISO8859-2';
c30be3cf 554$languages['sk']['ALIAS'] = 'sk_SK';
a8fa8e33 555
556$languages['sl_SI']['NAME'] = 'Slovenian';
557$languages['sl_SI']['ALTNAME'] = 'Sloven&scaron;&#269;ina';
558$languages['sl_SI']['CHARSET'] = 'iso-8859-2';
a00d341d 559$languages['sl_SI']['LOCALE'] = 'sl_SI.ISO8859-2';
a8fa8e33 560$languages['sl']['ALIAS'] = 'sl_SI';
561
562$languages['sr_YU']['NAME'] = 'Serbian';
563$languages['sr_YU']['ALTNAME'] = 'Srpski';
564$languages['sr_YU']['CHARSET'] = 'iso-8859-2';
a00d341d 565$languages['sr_YU']['LOCALE'] = 'sr_YU.ISO8859-2';
a8fa8e33 566$languages['sr']['ALIAS'] = 'sr_YU';
567
568$languages['sv_SE']['NAME'] = 'Swedish';
569$languages['sv_SE']['ALTNAME'] = 'Svenska';
570$languages['sv_SE']['CHARSET'] = 'iso-8859-1';
a00d341d 571$languages['sv_SE']['LOCALE'] = 'sv_SE.ISO8859-1';
a8fa8e33 572$languages['sv']['ALIAS'] = 'sv_SE';
573
574$languages['th_TH']['NAME'] = 'Thai';
575$languages['th_TH']['CHARSET'] = 'tis-620';
c30be3cf 576$languages['th_TH']['LOCALE'] = 'th_TH.TIS-620';
a8fa8e33 577$languages['th']['ALIAS'] = 'th_TH';
578
551a09c7 579$languages['tl_PH']['NAME'] = 'Tagalog';
580$languages['tl_PH']['CHARSET'] = 'iso-8859-1';
a00d341d 581$languages['tl_PH']['LOCALE'] = 'tl_PH.ISO8859-1';
551a09c7 582$languages['tl']['ALIAS'] = 'tl_PH';
583
a8fa8e33 584$languages['tr_TR']['NAME'] = 'Turkish';
585$languages['tr_TR']['CHARSET'] = 'iso-8859-9';
a00d341d 586$languages['tr_TR']['LOCALE'] = 'tr_TR.ISO8859-9';
a8fa8e33 587$languages['tr']['ALIAS'] = 'tr_TR';
588
589$languages['zh_TW']['NAME'] = 'Chinese Trad';
590$languages['zh_TW']['CHARSET'] = 'big5';
c30be3cf 591$languages['zh_TW']['LOCALE'] = 'zh_TW.BIG5';
a8fa8e33 592$languages['tw']['ALIAS'] = 'zh_TW';
593
594$languages['zh_CN']['NAME'] = 'Chinese Simp';
595$languages['zh_CN']['CHARSET'] = 'gb2312';
c30be3cf 596$languages['zh_CN']['LOCALE'] = 'zh_CN.GB2312';
a8fa8e33 597$languages['cn']['ALIAS'] = 'zh_CN';
060c9483 598
a8fa8e33 599$languages['uk_UA']['NAME'] = 'Ukrainian';
600$languages['uk_UA']['CHARSET'] = 'koi8-u';
c30be3cf 601$languages['uk_UA']['LOCALE'] = 'uk_UA.KOI8-U';
a8fa8e33 602$languages['uk']['ALIAS'] = 'uk_UA';
c30be3cf 603
604$languages['ru_UA']['NAME'] = 'Russian (Ukrainian)';
605$languages['ru_UA']['CHARSET'] = 'koi8-r';
606$languages['ru_UA']['LOCALE'] = 'ru_UA.KOI8-R';
607
87c6b544 608/*
850db3c8 609$languages['vi_VN']['NAME'] = 'Vietnamese';
610$languages['vi_VN']['CHARSET'] = 'utf-8';
611$languages['vi']['ALIAS'] = 'vi_VN';
87c6b544 612*/
a8fa8e33 613
d3b57948 614// Right to left languages
a8fa8e33 615$languages['ar']['NAME'] = 'Arabic';
616$languages['ar']['CHARSET'] = 'windows-1256';
617$languages['ar']['DIR'] = 'rtl';
618
4417eead 619$languages['fa_IR']['NAME'] = 'Farsi';
620$languages['fa_IR']['CHARSET'] = 'utf-8';
621$languages['fa_IR']['DIR'] = 'rtl';
622$languages['fa_IR']['LOCALE'] = 'fa_IR.UTF-8';
623$languages['fa']['ALIAS'] = 'fa_IR';
624
a8fa8e33 625$languages['he_IL']['NAME'] = 'Hebrew';
626$languages['he_IL']['CHARSET'] = 'windows-1255';
c30be3cf 627$languages['he_IL']['LOCALE'] = 'he_IL.CP1255';
a8fa8e33 628$languages['he_IL']['DIR'] = 'rtl';
629$languages['he']['ALIAS'] = 'he_IL';
d3b57948 630
5c920668 631/* Detect whether gettext is installed. */
a2a7852b 632$gettext_flags = 0;
633if (function_exists('_')) {
634 $gettext_flags += 1;
635}
636if (function_exists('bindtextdomain')) {
637 $gettext_flags += 2;
638}
639if (function_exists('textdomain')) {
640 $gettext_flags += 4;
641}
642
5c920668 643/* If gettext is fully loaded, cool */
a2a7852b 644if ($gettext_flags == 7) {
645 $use_gettext = true;
646}
5c920668 647/* If we can fake gettext, try that */
a2a7852b 648elseif ($gettext_flags == 0) {
649 $use_gettext = true;
e7ab8c9d 650 include_once(SM_PATH . 'functions/gettext.php');
a2a7852b 651} else {
5c920668 652 /* Uh-ho. A weird install */
a2a7852b 653 if (! $gettext_flags & 1) {
03db90bc 654 /**
655 * Function is used as replacement in broken installs
656 * @ignore
657 */
a2a7852b 658 function _($str) {
659 return $str;
660 }
661 }
662 if (! $gettext_flags & 2) {
03db90bc 663 /**
664 * Function is used as replacement in broken installs
665 * @ignore
666 */
a2a7852b 667 function bindtextdomain() {
668 return;
669 }
670 }
671 if (! $gettext_flags & 4) {
03db90bc 672 /**
673 * Function is used as replacemet in broken installs
674 * @ignore
675 */
a2a7852b 676 function textdomain() {
677 return;
678 }
679 }
680}
681
1d33e35e 682
51468260 683/**
1d33e35e 684 * Japanese charset extra function
685 *
51468260 686 * Action performed by function is defined by first argument.
687 * Default return value is defined by second argument.
688 * Use of third argument depends on action.
689 *
a8a1c36d 690 * @param string $action action performed by this function.
51468260 691 * possible values:
03db90bc 692 * decode - convert returned string to euc-jp. third argument unused
693 * encode - convert returned string to jis. third argument unused
694 * strimwidth - third argument=$width. trims string to $width symbols.
695 * encodeheader - create base64 encoded header in iso-2022-jp. third argument unused
696 * decodeheader - return human readable string from mime header. string is returned in euc-jp. third argument unused
697 * downloadfilename - third argument $useragent. Arguments provide browser info. Returns shift-jis or euc-jp encoded file name
698 * wordwrap - third argument=$wrap. wraps text at $wrap symbols
699 * utf7-imap_encode - returns string converted from euc-jp to utf7-imap. third argument unused
700 * utf7-imap_decode - returns string converted from utf7-imap to euc-jp. third argument unused
a8a1c36d 701 * @param string $ret default return value
1d33e35e 702 */
703function japanese_charset_xtra() {
704 $ret = func_get_arg(1); /* default return value */
705 if (function_exists('mb_detect_encoding')) {
706 switch (func_get_arg(0)) { /* action */
707 case 'decode':
e842b215 708 $detect_encoding = @mb_detect_encoding($ret);
1d33e35e 709 if ($detect_encoding == 'JIS' ||
710 $detect_encoding == 'EUC-JP' ||
e842b215 711 $detect_encoding == 'SJIS' ||
712 $detect_encoding == 'UTF-8') {
1d33e35e 713
e842b215 714 $ret = mb_convert_kana(mb_convert_encoding($ret, 'EUC-JP', 'AUTO'), "KV");
1d33e35e 715 }
716 break;
717 case 'encode':
e842b215 718 $detect_encoding = @mb_detect_encoding($ret);
1d33e35e 719 if ($detect_encoding == 'JIS' ||
720 $detect_encoding == 'EUC-JP' ||
e842b215 721 $detect_encoding == 'SJIS' ||
722 $detect_encoding == 'UTF-8') {
1d33e35e 723
e842b215 724 $ret = mb_convert_encoding(mb_convert_kana($ret, "KV"), 'JIS', 'AUTO');
1d33e35e 725 }
726 break;
727 case 'strimwidth':
728 $width = func_get_arg(2);
729 $ret = mb_strimwidth($ret, 0, $width, '...');
730 break;
731 case 'encodeheader':
8ba05cbe 732 $result = '';
733 if (strlen($ret) > 0) {
734 $tmpstr = mb_substr($ret, 0, 1);
735 $prevcsize = strlen($tmpstr);
736 for ($i = 1; $i < mb_strlen($ret); $i++) {
737 $tmp = mb_substr($ret, $i, 1);
738 if (strlen($tmp) == $prevcsize) {
739 $tmpstr .= $tmp;
740 } else {
741 if ($prevcsize == 1) {
742 $result .= $tmpstr;
743 } else {
e842b215 744 $result .= str_replace(' ', '',
745 mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
8ba05cbe 746 }
747 $tmpstr = $tmp;
748 $prevcsize = strlen($tmp);
749 }
750 }
751 if (strlen($tmpstr)) {
752 if (strlen(mb_substr($tmpstr, 0, 1)) == 1)
753 $result .= $tmpstr;
754 else
e842b215 755 $result .= str_replace(' ', '',
756 mb_encode_mimeheader($tmpstr,'iso-2022-jp','B',''));
8ba05cbe 757 }
758 }
759 $ret = $result;
1d33e35e 760 break;
761 case 'decodeheader':
762 $ret = str_replace("\t", "", $ret);
763 if (eregi('=\\?([^?]+)\\?(q|b)\\?([^?]+)\\?=', $ret))
e842b215 764 $ret = @mb_decode_mimeheader($ret);
765 $ret = @mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
1d33e35e 766 break;
767 case 'downloadfilename':
768 $useragent = func_get_arg(2);
769 if (strstr($useragent, 'Windows') !== false ||
770 strstr($useragent, 'Mac_') !== false) {
771 $ret = mb_convert_encoding($ret, 'SJIS', 'AUTO');
772 } else {
773 $ret = mb_convert_encoding($ret, 'EUC-JP', 'AUTO');
774}
775 break;
e842b215 776 case 'wordwrap':
777 $no_begin = "\x21\x25\x29\x2c\x2e\x3a\x3b\x3f\x5d\x7d\xa1\xf1\xa1\xeb\xa1" .
778 "\xc7\xa1\xc9\xa2\xf3\xa1\xec\xa1\xed\xa1\xee\xa1\xa2\xa1\xa3\xa1\xb9" .
779 "\xa1\xd3\xa1\xd5\xa1\xd7\xa1\xd9\xa1\xdb\xa1\xcd\xa4\xa1\xa4\xa3\xa4" .
780 "\xa5\xa4\xa7\xa4\xa9\xa4\xc3\xa4\xe3\xa4\xe5\xa4\xe7\xa4\xee\xa1\xab" .
781 "\xa1\xac\xa1\xb5\xa1\xb6\xa5\xa1\xa5\xa3\xa5\xa5\xa5\xa7\xa5\xa9\xa5" .
782 "\xc3\xa5\xe3\xa5\xe5\xa5\xe7\xa5\xee\xa5\xf5\xa5\xf6\xa1\xa6\xa1\xbc" .
783 "\xa1\xb3\xa1\xb4\xa1\xaa\xa1\xf3\xa1\xcb\xa1\xa4\xa1\xa5\xa1\xa7\xa1" .
784 "\xa8\xa1\xa9\xa1\xcf\xa1\xd1";
785 $no_end = "\x5c\x24\x28\x5b\x7b\xa1\xf2\x5c\xa1\xc6\xa1\xc8\xa1\xd2\xa1" .
786 "\xd4\xa1\xd6\xa1\xd8\xa1\xda\xa1\xcc\xa1\xf0\xa1\xca\xa1\xce\xa1\xd0\xa1\xef";
787 $wrap = func_get_arg(2);
788
789 if (strlen($ret) >= $wrap &&
790 substr($ret, 0, 1) != '>' &&
791 strpos($ret, 'http://') === FALSE &&
792 strpos($ret, 'https://') === FALSE &&
793 strpos($ret, 'ftp://') === FALSE) {
794
795 $ret = mb_convert_kana($ret, "KV");
796
797 $line_new = '';
798 $ptr = 0;
799
800 while ($ptr < strlen($ret) - 1) {
801 $l = mb_strcut($ret, $ptr, $wrap);
802 $ptr += strlen($l);
803 $tmp = $l;
804
805 $l = mb_strcut($ret, $ptr, 2);
806 while (strlen($l) != 0 && mb_strpos($no_begin, $l) !== FALSE ) {
807 $tmp .= $l;
808 $ptr += strlen($l);
809 $l = mb_strcut($ret, $ptr, 1);
810 }
811 $line_new .= $tmp;
812 if ($ptr < strlen($ret) - 1)
813 $line_new .= "\n";
814 }
815 $ret = $line_new;
816 }
817 break;
818 case 'utf7-imap_encode':
819 $ret = mb_convert_encoding($ret, 'UTF7-IMAP', 'EUC-JP');
820 break;
821 case 'utf7-imap_decode':
822 $ret = mb_convert_encoding($ret, 'EUC-JP', 'UTF7-IMAP');
823 break;
1d33e35e 824 }
825 }
826 return $ret;
827}
828
829
51468260 830/**
831 * Korean charset extra functions
832 *
833 * Action performed by function is defined by first argument.
834 * Default return value is defined by second argument.
835 *
836 * @param string action performed by this function.
837 * possible values:
03db90bc 838 * downloadfilename - Hangul(Korean Character) Attached File Name Fix.
51468260 839 * @param string default return value
1d33e35e 840 */
841function korean_charset_xtra() {
842
843 $ret = func_get_arg(1); /* default return value */
844 if (func_get_arg(0) == 'downloadfilename') { /* action */
845 $ret = str_replace("\x0D\x0A", '', $ret); /* Hanmail's CR/LF Clear */
846 for ($i=0;$i<strlen($ret);$i++) {
847 if ($ret[$i] >= "\xA1" && $ret[$i] <= "\xFE") { /* 0xA1 - 0XFE are Valid */
848 $i++;
849 continue;
850 } else if (($ret[$i] >= 'a' && $ret[$i] <= 'z') || /* From Original ereg_replace in download.php */
851 ($ret[$i] >= 'A' && $ret[$i] <= 'Z') ||
852 ($ret[$i] == '.') || ($ret[$i] == '-')) {
853 continue;
854 } else {
855 $ret[$i] = '_';
856 }
857 }
858
859 }
1d33e35e 860 return $ret;
861}
862
db08d0c3 863/**
864 * Replaces non-braking spaces inserted by some browsers with regular space
865 *
9af9c0a2 866 * This function can be used to replace non-braking space symbols
867 * that are inserted in forms by some browsers instead of normal
868 * space symbol.
db08d0c3 869 *
870 * @param string $string Text that needs to be cleaned
871 * @param string $charset Charset used in text
872 * @return string Cleaned text
9af9c0a2 873 */
874function cleanup_nbsp($string,$charset) {
875
876 // reduce number of case statements
877 if (stristr('iso-8859-',substr($charset,0,9))){
878 $output_charset="iso-8859-x";
879 }
880 if (stristr('windows-125',substr($charset,0,11))){
881 $output_charset="cp125x";
882 }
883 if (stristr('koi8',substr($charset,0,4))){
884 $output_charset="koi8-x";
885 }
886 if (! isset($output_charset)){
887 $output_charset=strtolower($charset);
888 }
889
890// where is non-braking space symbol
891switch($output_charset):
892 case "iso-8859-x":
97b9c02f 893 case "cp125x":
894 case "iso-2022-jp":
9af9c0a2 895 $nbsp="\xA0";
896 break;
9af9c0a2 897 case "koi8-x":
898 $nbsp="\x9A";
899 break;
900 case "utf-8":
901 $nbsp="\xC2\xA0";
902 break;
9af9c0a2 903 default:
904 // don't change string if charset is unmatched
905 return $string;
906endswitch;
907
908// return space instead of non-braking space.
909 return str_replace($nbsp,' ',$string);
910}
4e519821 911
db08d0c3 912/**
913 * Function informs if it is safe to convert given charset to the one that is used by user.
914 *
915 * It is safe to use conversion only if user uses utf-8 encoding and when
916 * converted charset is similar to the one that is used by user.
917 *
918 * @param string $input_charset Charset of text that needs to be converted
919 * @return bool is it possible to convert to user's charset
920 */
4e519821 921function is_conversion_safe($input_charset) {
922 global $languages, $sm_notAlias, $default_charset;
923
924 // convert to lower case
925 $input_charset = strtolower($input_charset);
926
927 // Is user's locale Unicode based ?
928 if ( $default_charset == "utf-8" ) {
929 return true;
930 }
931
932 // Charsets that are similar
933switch ($default_charset):
934case "windows-1251":
935 if ( $input_charset == "iso-8859-5" ||
03db90bc 936 $input_charset == "koi8-r" ||
937 $input_charset == "koi8-u" ) {
4e519821 938 return true;
939 } else {
940 return false;
941 }
942case "windows-1257":
943 if ( $input_charset == "iso-8859-13" ||
03db90bc 944 $input_charset == "iso-8859-4" ) {
4e519821 945 return true;
946 } else {
947 return false;
948 }
949case "iso-8859-4":
950 if ( $input_charset == "iso-8859-13" ||
03db90bc 951 $input_charset == "windows-1257" ) {
4e519821 952 return true;
953 } else {
954 return false;
955 }
956case "iso-8859-5":
957 if ( $input_charset == "windows-1251" ||
03db90bc 958 $input_charset == "koi8-r" ||
959 $input_charset == "koi8-u" ) {
4e519821 960 return true;
961 } else {
962 return false;
963 }
964case "iso-8859-13":
965 if ( $input_charset == "iso-8859-4" ||
966 $input_charset == "windows-1257" ) {
967 return true;
968 } else {
969 return false;
970 }
971case "koi8-r":
972 if ( $input_charset == "windows-1251" ||
03db90bc 973 $input_charset == "iso-8859-5" ||
974 $input_charset == "koi8-u" ) {
4e519821 975 return true;
976 } else {
977 return false;
978 }
979case "koi8-u":
980 if ( $input_charset == "windows-1251" ||
03db90bc 981 $input_charset == "iso-8859-5" ||
982 $input_charset == "koi8-r" ) {
4e519821 983 return true;
984 } else {
985 return false;
986 }
987default:
988 return false;
989endswitch;
990}
51468260 991?>