Ignore:
Timestamp:
Oct 9, 2007, 1:13:56 AM (17 years ago)
Author:
rvelices
Message:

merge revisions 2121, 2122 and 2123 from trunk to branch-1_7

  • function str2url is compatible with utf-8
  • removed some old code (useless)
  • remove str_translate_to_ascii7bits and lang_table_translate_ascii7bits
  • mail subject and address names can contain accentuated characters
File:
1 edited

Legend:

Unmodified
Added
Removed
  • branches/branch-1_7/include/functions.inc.php

    r2088 r2125  
    299299}
    300300
     301/* Returns true if the string appears to be encoded in UTF-8. (from wordpress)
     302 * @param string Str
     303 */
     304function seems_utf8($Str) { # by bmorel at ssi dot fr
     305  for ($i=0; $i<strlen($Str); $i++) {
     306    if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb
     307    elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb
     308    elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb
     309    elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb
     310    elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb
     311    elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b
     312    else return false; # Does not match any model
     313    for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
     314      if ((++$i == strlen($Str)) || ((ord($Str[$i]) & 0xC0) != 0x80))
     315      return false;
     316    }
     317  }
     318  return true;
     319}
     320
     321/* Remove accents from a UTF-8 or ISO-859-1 string (from wordpress)
     322 * @param string sstring - an UTF-8 or ISO-8859-1 string
     323 */
     324function remove_accents($string)
     325{
     326  if ( !preg_match('/[\x80-\xff]/', $string) )
     327    return $string;
     328
     329  if (seems_utf8($string)) {
     330    $chars = array(
     331    // Decompositions for Latin-1 Supplement
     332    chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
     333    chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
     334    chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
     335    chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
     336    chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
     337    chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
     338    chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
     339    chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
     340    chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
     341    chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
     342    chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
     343    chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
     344    chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
     345    chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
     346    chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
     347    chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
     348    chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
     349    chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
     350    chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
     351    chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
     352    chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
     353    chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',
     354    chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',
     355    chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',
     356    chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',
     357    chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',
     358    chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',
     359    chr(195).chr(191) => 'y',
     360    // Decompositions for Latin Extended-A
     361    chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
     362    chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
     363    chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
     364    chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
     365    chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
     366    chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
     367    chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
     368    chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
     369    chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
     370    chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
     371    chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
     372    chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
     373    chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
     374    chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
     375    chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
     376    chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
     377    chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
     378    chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
     379    chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
     380    chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
     381    chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
     382    chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
     383    chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
     384    chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
     385    chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
     386    chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
     387    chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
     388    chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
     389    chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
     390    chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
     391    chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
     392    chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
     393    chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
     394    chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
     395    chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
     396    chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
     397    chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
     398    chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
     399    chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
     400    chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
     401    chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
     402    chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
     403    chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
     404    chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
     405    chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
     406    chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
     407    chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
     408    chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
     409    chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
     410    chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
     411    chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
     412    chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
     413    chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
     414    chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
     415    chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
     416    chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
     417    chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
     418    chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
     419    chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
     420    chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
     421    chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
     422    chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
     423    chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
     424    chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
     425    // Euro Sign
     426    chr(226).chr(130).chr(172) => 'E',
     427    // GBP (Pound) Sign
     428    chr(194).chr(163) => '');
     429
     430    $string = strtr($string, $chars);
     431  } else {
     432    // Assume ISO-8859-1 if not UTF-8
     433    $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
     434      .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
     435      .chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
     436      .chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
     437      .chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
     438      .chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
     439      .chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
     440      .chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
     441      .chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
     442      .chr(252).chr(253).chr(255);
     443
     444    $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
     445
     446    $string = strtr($string, $chars['in'], $chars['out']);
     447    $double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
     448    $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
     449    $string = str_replace($double_chars['in'], $double_chars['out'], $string);
     450  }
     451
     452  return $string;
     453}
     454
    301455/**
    302456 * simplify a string to insert it into an URL
    303  *
    304  * based on str2url function from Dotclear
    305457 *
    306458 * @param string
     
    309461function str2url($str)
    310462{
    311   $str = strtr(
    312     $str,
    313     'ÀÁÂÃÄÅàáâãäåÇçÒÓÔÕÖØòóôõöøÈÉÊËèéêëÌÍÎÏìíîïÙÚÛÜùúûü¾ÝÿýÑñ',
    314     'AAAAAAaaaaaaCcOOOOOOooooooEEEEeeeeIIIIiiiiUUUUuuuuYYyyNn'
    315     );
    316 
    317   $str = str_replace('Æ', 'AE', $str);
    318   $str = str_replace('æ', 'ae', $str);
    319   $str = str_replace('¼', 'OE', $str);
    320   $str = str_replace('½', 'oe', $str);
    321 
     463  $str = remove_accents($str);
    322464  $str = preg_replace('/[^a-z0-9_\s\'\:\/\[\],-]/','',strtolower($str));
    323465  $str = preg_replace('/[\s\'\:\/\[\],-]+/',' ',trim($str));
     
    353495
    354496  return $languages;
    355 }
    356 
    357 /**
    358  * replaces the $search into <span style="$style">$search</span> in the
    359  * given $string.
    360  *
    361  * case insensitive replacements, does not replace characters in HTML tags
    362  *
    363  * @param string $string
    364  * @param string $search
    365  * @param string $style
    366  * @return string
    367  */
    368 function add_style( $string, $search, $style )
    369 {
    370   //return $string;
    371   $return_string = '';
    372   $remaining = $string;
    373 
    374   $start = 0;
    375   $end = 0;
    376   $start = strpos ( $remaining, '<' );
    377   $end   = strpos ( $remaining, '>' );
    378   while ( is_numeric( $start ) and is_numeric( $end ) )
    379   {
    380     $treatment = substr ( $remaining, 0, $start );
    381     $treatment = preg_replace( '/('.$search.')/i',
    382                                '<span style="'.$style.'">\\0</span>',
    383                                $treatment );
    384     $return_string.= $treatment.substr( $remaining, $start, $end-$start+1 );
    385     $remaining = substr ( $remaining, $end + 1, strlen( $remaining ) );
    386     $start = strpos ( $remaining, '<' );
    387     $end   = strpos ( $remaining, '>' );
    388   }
    389   $treatment = preg_replace( '/('.$search.')/i',
    390                              '<span style="'.$style.'">\\0</span>',
    391                              $remaining );
    392   $return_string.= $treatment;
    393 
    394   return $return_string;
    395 }
    396 
    397 // replace_search replaces a searched words array string by the search in
    398 // another style for the given $string.
    399 function replace_search( $string, $search )
    400 {
    401   // FIXME : with new advanced search, this function needs a rewrite
    402   return $string;
    403 
    404   $words = explode( ',', $search );
    405   $style = 'background-color:white;color:red;';
    406   foreach ( $words as $word ) {
    407     $string = add_style( $string, $word, $style );
    408   }
    409   return $string;
    410497}
    411498
     
    11141201
    11151202/**
    1116  * Translate string in string ascii7bits
    1117  * It's possible to do that with iconv_substr
    1118  * but this fonction is not avaible on all the providers.
    1119  *
    1120  * @param string str
    1121  * @return string
    1122  */
    1123 function str_translate_to_ascii7bits($str)
    1124 {
    1125   global $lang_table_translate_ascii7bits;
    1126 
    1127   $src_table = array_keys($lang_table_translate_ascii7bits);
    1128   $dst_table = array_values($lang_table_translate_ascii7bits);
    1129 
    1130   return str_replace($src_table , $dst_table, $str);
    1131 }
    1132 
    1133 /**
    11341203 * returns the corresponding value from $themeconf if existing. Else, the
    11351204 * key is returned
Note: See TracChangeset for help on using the changeset viewer.