WordPressを読む 25-3 /blog/wp-includes/formatting.php 3
2014/12/09
目次
/blog/wp-includes/formatting.php 3
関数 remove_accents()
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 | function remove_accents($string) { if ( !preg_match('/[\x80-\xff]/', $string) ) return $string; if (seems_utf8($string)) { $chars = array( // Decompositions for Latin-1 Supplement chr(194).chr(170) => 'a', chr(194).chr(186) => 'o', 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(134) => 'AE',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(144) => 'D', 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(158) => 'TH',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(166) => 'ae',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(176) => 'd', 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(184) => '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(190) => 'th', chr(195).chr(191) => 'y', chr(195).chr(152) => 'O', // 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', // Decompositions for Latin Extended-B chr(200).chr(152) => 'S', chr(200).chr(153) => 's', chr(200).chr(154) => 'T', chr(200).chr(155) => 't', // Euro Sign chr(226).chr(130).chr(172) => 'E', // GBP (Pound) Sign chr(194).chr(163) => '', // Vowels with diacritic (Vietnamese) // unmarked chr(198).chr(160) => 'O', chr(198).chr(161) => 'o', chr(198).chr(175) => 'U', chr(198).chr(176) => 'u', // grave accent chr(225).chr(186).chr(166) => 'A', chr(225).chr(186).chr(167) => 'a', chr(225).chr(186).chr(176) => 'A', chr(225).chr(186).chr(177) => 'a', chr(225).chr(187).chr(128) => 'E', chr(225).chr(187).chr(129) => 'e', chr(225).chr(187).chr(146) => 'O', chr(225).chr(187).chr(147) => 'o', chr(225).chr(187).chr(156) => 'O', chr(225).chr(187).chr(157) => 'o', chr(225).chr(187).chr(170) => 'U', chr(225).chr(187).chr(171) => 'u', chr(225).chr(187).chr(178) => 'Y', chr(225).chr(187).chr(179) => 'y', // hook chr(225).chr(186).chr(162) => 'A', chr(225).chr(186).chr(163) => 'a', chr(225).chr(186).chr(168) => 'A', chr(225).chr(186).chr(169) => 'a', chr(225).chr(186).chr(178) => 'A', chr(225).chr(186).chr(179) => 'a', chr(225).chr(186).chr(186) => 'E', chr(225).chr(186).chr(187) => 'e', chr(225).chr(187).chr(130) => 'E', chr(225).chr(187).chr(131) => 'e', chr(225).chr(187).chr(136) => 'I', chr(225).chr(187).chr(137) => 'i', chr(225).chr(187).chr(142) => 'O', chr(225).chr(187).chr(143) => 'o', chr(225).chr(187).chr(148) => 'O', chr(225).chr(187).chr(149) => 'o', chr(225).chr(187).chr(158) => 'O', chr(225).chr(187).chr(159) => 'o', chr(225).chr(187).chr(166) => 'U', chr(225).chr(187).chr(167) => 'u', chr(225).chr(187).chr(172) => 'U', chr(225).chr(187).chr(173) => 'u', chr(225).chr(187).chr(182) => 'Y', chr(225).chr(187).chr(183) => 'y', // tilde chr(225).chr(186).chr(170) => 'A', chr(225).chr(186).chr(171) => 'a', chr(225).chr(186).chr(180) => 'A', chr(225).chr(186).chr(181) => 'a', chr(225).chr(186).chr(188) => 'E', chr(225).chr(186).chr(189) => 'e', chr(225).chr(187).chr(132) => 'E', chr(225).chr(187).chr(133) => 'e', chr(225).chr(187).chr(150) => 'O', chr(225).chr(187).chr(151) => 'o', chr(225).chr(187).chr(160) => 'O', chr(225).chr(187).chr(161) => 'o', chr(225).chr(187).chr(174) => 'U', chr(225).chr(187).chr(175) => 'u', chr(225).chr(187).chr(184) => 'Y', chr(225).chr(187).chr(185) => 'y', // acute accent chr(225).chr(186).chr(164) => 'A', chr(225).chr(186).chr(165) => 'a', chr(225).chr(186).chr(174) => 'A', chr(225).chr(186).chr(175) => 'a', chr(225).chr(186).chr(190) => 'E', chr(225).chr(186).chr(191) => 'e', chr(225).chr(187).chr(144) => 'O', chr(225).chr(187).chr(145) => 'o', chr(225).chr(187).chr(154) => 'O', chr(225).chr(187).chr(155) => 'o', chr(225).chr(187).chr(168) => 'U', chr(225).chr(187).chr(169) => 'u', // dot below chr(225).chr(186).chr(160) => 'A', chr(225).chr(186).chr(161) => 'a', chr(225).chr(186).chr(172) => 'A', chr(225).chr(186).chr(173) => 'a', chr(225).chr(186).chr(182) => 'A', chr(225).chr(186).chr(183) => 'a', chr(225).chr(186).chr(184) => 'E', chr(225).chr(186).chr(185) => 'e', chr(225).chr(187).chr(134) => 'E', chr(225).chr(187).chr(135) => 'e', chr(225).chr(187).chr(138) => 'I', chr(225).chr(187).chr(139) => 'i', chr(225).chr(187).chr(140) => 'O', chr(225).chr(187).chr(141) => 'o', chr(225).chr(187).chr(152) => 'O', chr(225).chr(187).chr(153) => 'o', chr(225).chr(187).chr(162) => 'O', chr(225).chr(187).chr(163) => 'o', chr(225).chr(187).chr(164) => 'U', chr(225).chr(187).chr(165) => 'u', chr(225).chr(187).chr(176) => 'U', chr(225).chr(187).chr(177) => 'u', chr(225).chr(187).chr(180) => 'Y', chr(225).chr(187).chr(181) => 'y', // Vowels with diacritic (Chinese, Hanyu Pinyin) chr(201).chr(145) => 'a', // macron chr(199).chr(149) => 'U', chr(199).chr(150) => 'u', // acute accent chr(199).chr(151) => 'U', chr(199).chr(152) => 'u', // caron chr(199).chr(141) => 'A', chr(199).chr(142) => 'a', chr(199).chr(143) => 'I', chr(199).chr(144) => 'i', chr(199).chr(145) => 'O', chr(199).chr(146) => 'o', chr(199).chr(147) => 'U', chr(199).chr(148) => 'u', chr(199).chr(153) => 'U', chr(199).chr(154) => 'u', // grave accent chr(199).chr(155) => 'U', chr(199).chr(156) => 'u', ); // Used for locale-specific rules $locale = get_locale(); if ( 'de_DE' == $locale ) { $chars[ chr(195).chr(132) ] = 'Ae'; $chars[ chr(195).chr(164) ] = 'ae'; $chars[ chr(195).chr(150) ] = 'Oe'; $chars[ chr(195).chr(182) ] = 'oe'; $chars[ chr(195).chr(156) ] = 'Ue'; $chars[ chr(195).chr(188) ] = 'ue'; $chars[ chr(195).chr(159) ] = 'ss'; } elseif ( 'da_DK' === $locale ) { $chars[ chr(195).chr(134) ] = 'Ae'; $chars[ chr(195).chr(166) ] = 'ae'; $chars[ chr(195).chr(152) ] = 'Oe'; $chars[ chr(195).chr(184) ] = 'oe'; $chars[ chr(195).chr(133) ] = 'Aa'; $chars[ chr(195).chr(165) ] = 'aa'; } $string = strtr($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; } |
関数 sanitize_file_name()
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | function sanitize_file_name( $filename ) { $filename_raw = $filename; $special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", chr(0)); $special_chars = apply_filters( 'sanitize_file_name_chars', $special_chars, $filename_raw ); $filename = preg_replace( "#\x{00a0}#siu", ' ', $filename ); $filename = str_replace($special_chars, '', $filename); $filename = str_replace( array( '%20', '+' ), '-', $filename ); $filename = preg_replace('/[\s-]+/', '-', $filename); $filename = trim($filename, '.-_'); // Split the filename into a base and extension[s] $parts = explode('.', $filename); // Return if only one extension if ( count( $parts ) <= 2 ) { return apply_filters( 'sanitize_file_name', $filename, $filename_raw ); } // Process multiple extensions $filename = array_shift($parts); $extension = array_pop($parts); $mimes = get_allowed_mime_types(); foreach ( (array) $parts as $part) { $filename .= '.' . $part; if ( preg_match("/^[a-zA-Z]{2,5}\d?$/", $part) ) { $allowed = false; foreach ( $mimes as $ext_preg => $mime_match ) { $ext_preg = '!^(' . $ext_preg . ')$!i'; if ( preg_match( $ext_preg, $part ) ) { $allowed = true; break; } } if ( !$allowed ) $filename .= '_'; } } $filename .= '.' . $extension; /** This filter is documented in wp-includes/formatting.php */ return apply_filters('sanitize_file_name', $filename, $filename_raw); } |
関数 sanitize_user()
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 | function sanitize_user( $username, $strict = false ) { $raw_username = $username; $username = wp_strip_all_tags( $username ); $username = remove_accents( $username ); // Kill octets $username = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '', $username ); $username = preg_replace( '/&.+?;/', '', $username ); // Kill entities // If strict, reduce to ASCII for max portability. if ( $strict ) $username = preg_replace( '|[^a-z0-9 _.\-@]|i', '', $username ); $username = trim( $username ); // Consolidate contiguous whitespace $username = preg_replace( '|\s+|', ' ', $username ); return apply_filters( 'sanitize_user', $username, $raw_username, $strict ); } |
関数 sanitize_key()
1 2 3 4 5 6 7 | function sanitize_key( $key ) { $raw_key = $key; $key = strtolower( $key ); $key = preg_replace( '/[^a-z0-9_\-]/', '', $key ); return apply_filters( 'sanitize_key', $key, $raw_key ); } |
関数 sanitize_title()
1 2 3 4 5 6 7 8 9 10 11 12 13 | function sanitize_title( $title, $fallback_title = '', $context = 'save' ) { $raw_title = $title; if ( 'save' == $context ) $title = remove_accents($title); $title = apply_filters( 'sanitize_title', $title, $raw_title, $context ); if ( '' === $title || false === $title ) $title = $fallback_title; return $title; } |
関数 sanitize_title_for_query()
1 2 3 | function sanitize_title_for_query( $title ) { return sanitize_title( $title, '', 'query' ); } |
関数 sanitize_title_with_dashes()
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 | function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) { $title = strip_tags($title); // Preserve escaped octets. $title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title); // Remove percent signs that are not part of an octet. $title = str_replace('%', '', $title); // Restore octets. $title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title); if (seems_utf8($title)) { if (function_exists('mb_strtolower')) { $title = mb_strtolower($title, 'UTF-8'); } $title = utf8_uri_encode($title, 200); } $title = strtolower($title); $title = preg_replace('/&.+?;/', '', $title); // kill entities $title = str_replace('.', '-', $title); if ( 'save' == $context ) { // Convert nbsp, ndash and mdash to hyphens $title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title ); // Strip these characters entirely $title = str_replace( array( // iexcl and iquest '%c2%a1', '%c2%bf', // angle quotes '%c2%ab', '%c2%bb', '%e2%80%b9', '%e2%80%ba', // curly quotes '%e2%80%98', '%e2%80%99', '%e2%80%9c', '%e2%80%9d', '%e2%80%9a', '%e2%80%9b', '%e2%80%9e', '%e2%80%9f', // copy, reg, deg, hellip and trade '%c2%a9', '%c2%ae', '%c2%b0', '%e2%80%a6', '%e2%84%a2', // acute accents '%c2%b4', '%cb%8a', '%cc%81', '%cd%81', // grave accent, macron, caron '%cc%80', '%cc%84', '%cc%8c', ), '', $title ); // Convert times to x $title = str_replace( '%c3%97', 'x', $title ); } $title = preg_replace('/[^%a-z0-9 _-]/', '', $title); $title = preg_replace('/\s+/', '-', $title); $title = preg_replace('|-+|', '-', $title); $title = trim($title, '-'); return $title; } |
関数 sanitize_sql_orderby()
1 2 3 4 5 6 | function sanitize_sql_orderby( $orderby ){ preg_match('/^\s*([a-z0-9_]+(\s+(ASC|DESC))?(\s*,\s*|\s*$))+|^\s*RAND\(\s*\)\s*$/i', $orderby, $obmatches); if ( !$obmatches ) return false; return $orderby; } |
関数 sanitize_html_class()
1 2 3 4 5 6 7 8 9 10 11 | function sanitize_html_class( $class, $fallback = '' ) { //Strip out any % encoded octets $sanitized = preg_replace( '|%[a-fA-F0-9][a-fA-F0-9]|', '', $class ); //Limit to A-Z,a-z,0-9,_,- $sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $sanitized ); if ( '' == $sanitized ) $sanitized = $fallback; return apply_filters( 'sanitize_html_class', $sanitized, $class, $fallback ); } |