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

git-svn-id: http://piwigo.org/svn/branches/branch-1_7@2125 68402e56-0260-453c-a942-63ccdbb3a9ee

1 files changed, 155 insertions, 86 deletions

diff --git a/include/functions.inc.php b/include/functions.inc.php
index aee815866..5f448cdd1 100644
--- a/include/functions.inc.php
+++ b/include/functions.inc.php
@@ -298,27 +298,169 @@ function get_picture_size( $original_width, $original_height,
   return $picture_size;
 }
 
+/* Returns true if the string appears to be encoded in UTF-8. (from wordpress)
+ * @param string Str
+ */
+function seems_utf8($Str) { # by bmorel at ssi dot fr
+  for ($i=0; $i<strlen($Str); $i++) {
+    if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb
+    elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb
+    elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb
+    elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb
+    elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb
+    elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b
+    else return false; # Does not match any model
+    for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
+      if ((++$i == strlen($Str)) || ((ord($Str[$i]) & 0xC0) != 0x80))
+      return false;
+    }
+  }
+  return true;
+}
+
+/* Remove accents from a UTF-8 or ISO-859-1 string (from wordpress)
+ * @param string sstring - an UTF-8 or ISO-8859-1 string
+ */
+function remove_accents($string)
+{
+  if ( !preg_match('/[\x80-\xff]/', $string) )
+    return $string;
+
+  if (seems_utf8($string)) {
+    $chars = array(
+    // Decompositions for Latin-1 Supplement
+    chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
+    chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
+    chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
+    chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
+    chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
+    chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
+    chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
+    chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
+    chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
+    chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
+    chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
+    chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
+    chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
+    chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
+    chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
+    chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
+    chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
+    chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
+    chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
+    chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
+    chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
+    chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',
+    chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',
+    chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',
+    chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',
+    chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',
+    chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',
+    chr(195).chr(191) => 'y',
+    // Decompositions for Latin Extended-A
+    chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
+    chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
+    chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
+    chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
+    chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
+    chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
+    chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
+    chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
+    chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
+    chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
+    chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
+    chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
+    chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
+    chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
+    chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
+    chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
+    chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
+    chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
+    chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
+    chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
+    chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
+    chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
+    chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
+    chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
+    chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
+    chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
+    chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
+    chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
+    chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
+    chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
+    chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
+    chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
+    chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
+    chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
+    chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
+    chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
+    chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
+    chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
+    chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
+    chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
+    chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
+    chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
+    chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
+    chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
+    chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
+    chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
+    chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
+    chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
+    chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
+    chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
+    chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
+    chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
+    chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
+    chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
+    chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
+    chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
+    chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
+    chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
+    chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
+    chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
+    chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
+    chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
+    chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
+    chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
+    // Euro Sign
+    chr(226).chr(130).chr(172) => 'E',
+    // GBP (Pound) Sign
+    chr(194).chr(163) => '');
+
+    $string = strtr($string, $chars);
+  } else {
+    // Assume ISO-8859-1 if not UTF-8
+    $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
+      .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
+      .chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
+      .chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
+      .chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
+      .chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
+      .chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
+      .chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
+      .chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
+      .chr(252).chr(253).chr(255);
+
+    $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
+
+    $string = strtr($string, $chars['in'], $chars['out']);
+    $double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
+    $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
+    $string = str_replace($double_chars['in'], $double_chars['out'], $string);
+  }
+
+  return $string;
+}
+
 /**
  * simplify a string to insert it into an URL
  *
- * based on str2url function from Dotclear
- *
  * @param string
  * @return string
  */
 function str2url($str)
 {
-  $str = strtr(
-    $str,
-    'ÀÁÂÃÄÅàáâãäåÇçÒÓÔÕÖØòóôõöøÈÉÊËèéêëÌÍÎÏìíîïÙÚÛÜùúûü¾ÝÿýÑñ',
-    'AAAAAAaaaaaaCcOOOOOOooooooEEEEeeeeIIIIiiiiUUUUuuuuYYyyNn'
-    );
-
-  $str = str_replace('Æ', 'AE', $str);
-  $str = str_replace('æ', 'ae', $str);
-  $str = str_replace('¼', 'OE', $str);
-  $str = str_replace('½', 'oe', $str);
-
+  $str = remove_accents($str);
   $str = preg_replace('/[^a-z0-9_\s\'\:\/\[\],-]/','',strtolower($str));
   $str = preg_replace('/[\s\'\:\/\[\],-]+/',' ',trim($str));
   $res = str_replace(' ','_',$str);
@@ -354,61 +496,6 @@ function get_languages()
   return $languages;
 }
 
-/**
- * replaces the $search into <span style="$style">$search</span> in the
- * given $string.
- *
- * case insensitive replacements, does not replace characters in HTML tags
- *
- * @param string $string
- * @param string $search
- * @param string $style
- * @return string
- */
-function add_style( $string, $search, $style )
-{
-  //return $string;
-  $return_string = '';
-  $remaining = $string;
-
-  $start = 0;
-  $end = 0;
-  $start = strpos ( $remaining, '<' );
-  $end   = strpos ( $remaining, '>' );
-  while ( is_numeric( $start ) and is_numeric( $end ) )
-  {
-    $treatment = substr ( $remaining, 0, $start );
-    $treatment = preg_replace( '/('.$search.')/i',
-                               '<span style="'.$style.'">\\0</span>',
-                               $treatment );
-    $return_string.= $treatment.substr( $remaining, $start, $end-$start+1 );
-    $remaining = substr ( $remaining, $end + 1, strlen( $remaining ) );
-    $start = strpos ( $remaining, '<' );
-    $end   = strpos ( $remaining, '>' );
-  }
-  $treatment = preg_replace( '/('.$search.')/i',
-                             '<span style="'.$style.'">\\0</span>',
-                             $remaining );
-  $return_string.= $treatment;
-
-  return $return_string;
-}
-
-// replace_search replaces a searched words array string by the search in
-// another style for the given $string.
-function replace_search( $string, $search )
-{
-  // FIXME : with new advanced search, this function needs a rewrite
-  return $string;
-
-  $words = explode( ',', $search );
-  $style = 'background-color:white;color:red;';
-  foreach ( $words as $word ) {
-    $string = add_style( $string, $word, $style );
-  }
-  return $string;
-}
-
 function pwg_log($image_id = null, $image_type = null)
 {
   global $conf, $user, $page;
@@ -1113,24 +1200,6 @@ function l10n_args($key_args, $sep = "\n")
 }
 
 /**
- * Translate string in string ascii7bits
- * It's possible to do that with iconv_substr
- * but this fonction is not avaible on all the providers.
- *
- * @param string str
- * @return string
- */
-function str_translate_to_ascii7bits($str)
-{
-  global $lang_table_translate_ascii7bits;
-
-  $src_table = array_keys($lang_table_translate_ascii7bits);
-  $dst_table = array_values($lang_table_translate_ascii7bits);
-
-  return str_replace($src_table , $dst_table, $str);
-}
-
-/**
  * returns the corresponding value from $themeconf if existing. Else, the
  * key is returned
  *