diff --git includes/unicode.entities.inc includes/unicode.entities.inc deleted file mode 100644 index 7b0a490..0000000 --- includes/unicode.entities.inc +++ /dev/null @@ -1,266 +0,0 @@ - 'Á', - 'á' => 'á', - 'Â' => 'Â', - 'â' => 'â', - '´' => '´', - 'Æ' => 'Æ', - 'æ' => 'æ', - 'À' => 'À', - 'à' => 'à', - 'ℵ' => 'ℵ', - 'Α' => 'Α', - 'α' => 'α', - '&' => '&', - '∧' => '∧', - '∠' => '∠', - 'Å' => 'Å', - 'å' => 'å', - '≈' => '≈', - 'Ã' => 'Ã', - 'ã' => 'ã', - 'Ä' => 'Ä', - 'ä' => 'ä', - '„' => '„', - 'Β' => 'Β', - 'β' => 'β', - '¦' => '¦', - '•' => '•', - '∩' => '∩', - 'Ç' => 'Ç', - 'ç' => 'ç', - '¸' => '¸', - '¢' => '¢', - 'Χ' => 'Χ', - 'χ' => 'χ', - 'ˆ' => 'ˆ', - '♣' => '♣', - '≅' => '≅', - '©' => '©', - '↵' => '↵', - '∪' => '∪', - '¤' => '¤', - '†' => '†', - '‡' => '‡', - '↓' => '↓', - '⇓' => '⇓', - '°' => '°', - 'Δ' => 'Δ', - 'δ' => 'δ', - '♦' => '♦', - '÷' => '÷', - 'É' => 'É', - 'é' => 'é', - 'Ê' => 'Ê', - 'ê' => 'ê', - 'È' => 'È', - 'è' => 'è', - '∅' => '∅', - ' ' => ' ', - ' ' => ' ', - 'Ε' => 'Ε', - 'ε' => 'ε', - '≡' => '≡', - 'Η' => 'Η', - 'η' => 'η', - 'Ð' => 'Ð', - 'ð' => 'ð', - 'Ë' => 'Ë', - 'ë' => 'ë', - '€' => '€', - '∃' => '∃', - 'ƒ' => 'ƒ', - '∀' => '∀', - '½' => '½', - '¼' => '¼', - '¾' => '¾', - '⁄' => '⁄', - 'Γ' => 'Γ', - 'γ' => 'γ', - '≥' => '≥', - '↔' => '↔', - '⇔' => '⇔', - '♥' => '♥', - '…' => '…', - 'Í' => 'Í', - 'í' => 'í', - 'Î' => 'Î', - 'î' => 'î', - '¡' => '¡', - 'Ì' => 'Ì', - 'ì' => 'ì', - 'ℑ' => 'ℑ', - '∞' => '∞', - '∫' => '∫', - 'Ι' => 'Ι', - 'ι' => 'ι', - '¿' => '¿', - '∈' => '∈', - 'Ï' => 'Ï', - 'ï' => 'ï', - 'Κ' => 'Κ', - 'κ' => 'κ', - 'Λ' => 'Λ', - 'λ' => 'λ', - '⟨' => '〈', - '«' => '«', - '←' => '←', - '⇐' => '⇐', - '⌈' => '⌈', - '“' => '“', - '≤' => '≤', - '⌊' => '⌊', - '∗' => '∗', - '◊' => '◊', - '‎' => '‎', - '‹' => '‹', - '‘' => '‘', - '¯' => '¯', - '—' => '—', - 'µ' => 'µ', - '·' => '·', - '−' => '−', - 'Μ' => 'Μ', - 'μ' => 'μ', - '∇' => '∇', - ' ' => ' ', - '–' => '–', - '≠' => '≠', - '∋' => '∋', - '¬' => '¬', - '∉' => '∉', - '⊄' => '⊄', - 'Ñ' => 'Ñ', - 'ñ' => 'ñ', - 'Ν' => 'Ν', - 'ν' => 'ν', - 'Ó' => 'Ó', - 'ó' => 'ó', - 'Ô' => 'Ô', - 'ô' => 'ô', - 'Œ' => 'Œ', - 'œ' => 'œ', - 'Ò' => 'Ò', - 'ò' => 'ò', - '‾' => '‾', - 'Ω' => 'Ω', - 'ω' => 'ω', - 'Ο' => 'Ο', - 'ο' => 'ο', - '⊕' => '⊕', - '∨' => '∨', - 'ª' => 'ª', - 'º' => 'º', - 'Ø' => 'Ø', - 'ø' => 'ø', - 'Õ' => 'Õ', - 'õ' => 'õ', - '⊗' => '⊗', - 'Ö' => 'Ö', - 'ö' => 'ö', - '¶' => '¶', - '∂' => '∂', - '‰' => '‰', - '⊥' => '⊥', - 'Φ' => 'Φ', - 'φ' => 'φ', - 'Π' => 'Π', - 'π' => 'π', - 'ϖ' => 'ϖ', - '±' => '±', - '£' => '£', - '′' => '′', - '″' => '″', - '∏' => '∏', - '∝' => '∝', - 'Ψ' => 'Ψ', - 'ψ' => 'ψ', - '√' => '√', - '⟩' => '〉', - '»' => '»', - '→' => '→', - '⇒' => '⇒', - '⌉' => '⌉', - '”' => '”', - 'ℜ' => 'ℜ', - '®' => '®', - '⌋' => '⌋', - 'Ρ' => 'Ρ', - 'ρ' => 'ρ', - '‏' => '‏', - '›' => '›', - '’' => '’', - '‚' => '‚', - 'Š' => 'Š', - 'š' => 'š', - '⋅' => '⋅', - '§' => '§', - '­' => '­', - 'Σ' => 'Σ', - 'σ' => 'σ', - 'ς' => 'ς', - '∼' => '∼', - '♠' => '♠', - '⊂' => '⊂', - '⊆' => '⊆', - '∑' => '∑', - '¹' => '¹', - '²' => '²', - '³' => '³', - '⊃' => '⊃', - '⊇' => '⊇', - 'ß' => 'ß', - 'Τ' => 'Τ', - 'τ' => 'τ', - '∴' => '∴', - 'Θ' => 'Θ', - 'θ' => 'θ', - 'ϑ' => 'ϑ', - ' ' => ' ', - 'Þ' => 'Þ', - 'þ' => 'þ', - '˜' => '˜', - '×' => '×', - '™' => '™', - 'Ú' => 'Ú', - 'ú' => 'ú', - '↑' => '↑', - '⇑' => '⇑', - 'Û' => 'Û', - 'û' => 'û', - 'Ù' => 'Ù', - 'ù' => 'ù', - '¨' => '¨', - 'ϒ' => 'ϒ', - 'Υ' => 'Υ', - 'υ' => 'υ', - 'Ü' => 'Ü', - 'ü' => 'ü', - '℘' => '℘', - 'Ξ' => 'Ξ', - 'ξ' => 'ξ', - 'Ý' => 'Ý', - 'ý' => 'ý', - '¥' => '¥', - 'ÿ' => 'ÿ', - 'Ÿ' => 'Ÿ', - 'Ζ' => 'Ζ', - 'ζ' => 'ζ', - '‍' => '‍', - '‌' => '‌', - '>' => '>', - '<' => '<', - '"' => '"', - // Add apostrophe (XML). - ''' => "'", -); diff --git includes/unicode.inc includes/unicode.inc index 24cc6bb..544b164 100644 --- includes/unicode.inc +++ includes/unicode.inc @@ -422,94 +422,12 @@ function _mime_header_decode($matches) { * * @param $text * The text to decode entities in. - * @param $exclude - * An array of characters which should not be decoded. For example, - * array('<', '&', '"'). This affects both named and numerical entities. * * @return * The input $text, with all HTML entities decoded once. */ -function decode_entities($text, $exclude = array()) { - // Flip the exclude list so that we can do quick lookups later. - $exclude = array_flip($exclude); - - // Prepare the callback function. - _decode_entities(NULL, $exclude); - - // Use a regexp to select all entities in one pass, to avoid decoding - // double-escaped entities twice. - return preg_replace_callback('/&(#x?)?([A-Za-z0-9]+);/', '_decode_entities', $text); -} - -/** - * Helper function for decode_entities - * - * @param $matches - * An array of matches found by preg_replace_callback(). Elements 0, 1, and 2 - * of $matches must be the original entity, its prefix, and its codepoint. - * @param $set_exclude - * An array of entities that should be excluded from decoding. This should - * only be set during a preparatory call before preg_replace_callback(). - * - * @return - * The decoded entity for a given match, or the original encoded entity if - * the entity is in the list of excluded entities. - */ -function _decode_entities($matches = NULL, $set_exclude = NULL) { - static $html_entities, $exclude; - if (!isset($html_entities)) { - include DRUPAL_ROOT . '/includes/unicode.entities.inc'; - } - if (isset($set_exclude)) { - // This is a preparatory call. - $exclude = $set_exclude; - return; - } - list($original, $prefix, $codepoint) = $matches; - // Named entity - if (!$prefix) { - // A named entity not in the exclude list. - if (isset($html_entities[$original]) && !isset($exclude[$html_entities[$original]])) { - return $html_entities[$original]; - } - else { - return $original; - } - } - // Hexadecimal numerical entity - if ($prefix == '#x') { - $codepoint = base_convert($codepoint, 16, 10); - } - // Decimal numerical entity (strip leading zeros to avoid PHP octal notation) - else { - $codepoint = preg_replace('/^0+/', '', $codepoint); - } - // Encode codepoint as UTF-8 bytes - if ($codepoint < 0x80) { - $str = chr($codepoint); - } - elseif ($codepoint < 0x800) { - $str = chr(0xC0 | ($codepoint >> 6)) - . chr(0x80 | ($codepoint & 0x3F)); - } - elseif ($codepoint < 0x10000) { - $str = chr(0xE0 | ( $codepoint >> 12)) - . chr(0x80 | (($codepoint >> 6) & 0x3F)) - . chr(0x80 | ( $codepoint & 0x3F)); - } - elseif ($codepoint < 0x200000) { - $str = chr(0xF0 | ( $codepoint >> 18)) - . chr(0x80 | (($codepoint >> 12) & 0x3F)) - . chr(0x80 | (($codepoint >> 6) & 0x3F)) - . chr(0x80 | ( $codepoint & 0x3F)); - } - // Check for excluded characters - if (isset($exclude[$str])) { - return $original; - } - else { - return $str; - } +function decode_entities($text) { + return html_entity_decode($text, ENT_QUOTES, 'UTF-8'); } /** diff --git modules/simpletest/tests/unicode.test modules/simpletest/tests/unicode.test index a449d5a..af48ba9 100644 --- modules/simpletest/tests/unicode.test +++ modules/simpletest/tests/unicode.test @@ -218,36 +218,6 @@ class UnicodeUnitTest extends DrupalWebTestCase { } } - function testDecodeEntitiesExclusion() { - $testcase = array( - 'Drupal' => 'Drupal', - '