WT_I18N::languageName('af'), "ar" => WT_I18N::languageName('ar'), "cs" => WT_I18N::languageName('cs'), "da" => WT_I18N::languageName('da'), "de" => WT_I18N::languageName('de'), "el" => WT_I18N::languageName('el'), "en" => WT_I18N::languageName('en'), "es" => WT_I18N::languageName('es'), "eu" => WT_I18N::languageName('eu'), "fi" => WT_I18N::languageName('fi'), "fr" => WT_I18N::languageName('fr'), "gd" => WT_I18N::languageName('gd'), "haw" => WT_I18N::languageName('haw'), "he" => WT_I18N::languageName('he'), "hu" => WT_I18N::languageName('hu'), "is" => WT_I18N::languageName('is'), "it" => WT_I18N::languageName('it'), "lt" => WT_I18N::languageName('lt'), "nl" => WT_I18N::languageName('nl'), "nn" => WT_I18N::languageName('nn'), "pl" => WT_I18N::languageName('pl'), "pt" => WT_I18N::languageName('pt'), "ru" => WT_I18N::languageName('ru'), "sk" => WT_I18N::languageName('sk'), "sl" => WT_I18N::languageName('sl'), "sv" => WT_I18N::languageName('sv'), "tr" => WT_I18N::languageName('tr'), "vi" => WT_I18N::languageName('vi'), ); switch ($language_filter) { case "af": // Afrikaans $ucspecialchars = array( "È" => "È", "É" => "É", "Ê" => "Ê", "Ë" => "Ë", "Î" => "Î", "Ï" => "Ï", "Ô" => "Ô", "Û" => "Û", ); $lcspecialchars = array( "è" => "è", "é" => "é", "ê" => "ê", "ë" => "ë", "î" => "î", "ï" => "ï", "ô" => "ô", "û" => "û", "ʼn" => "ʼn", // n preceded by apostrophe ); break; case "cs": // Ceština $ucspecialchars = array( "Á" => "Á", "Ą" => "Ą", // A cedille "Ä" => "Ä", "É" => "É", "Ę" => "Ę", // E cedille "Ě" => "Ě", // E hachek "Í" => "Í", "Ó" => "Ó", "Ô" => "Ô", "Ú" => "Ú", "Ů" => "Ů", // U ring "Ý" => "Ý", "Č" => "Č", // C hachek "Ĺ" => "Ĺ", // L acute "Ň" => "Ň", // N hachek "Ŕ" => "Ŕ", // R acute "Ř" => "Ř", // R hachek "Š" => "Š", // S hachek "Ž" => "Ž", // Z hachek ); $lcspecialchars = array( "á" => "á", "ą" => "ą", // a cedille "ä" => "ä", "é" => "é", "ę" => "ę", // e cedille "ě" => "ě", // e hachek "í" => "í", "ó" => "ó", "ô" => "ô", "ú" => "ú", "ů" => "ů", // u ring "ý" => "ý", "č" => "č", // c hachek "ď" => "ď", // ď d apostrophe - shows incorrectly as d hacheck - d "ť" => "ť", // t apostrophe "ĺ" => "ĺ", // l acute "ň" => "ň", // n hachek "ŕ" => "ŕ", // r acute "ř" => "ř", // r hachek "š" => "š", // s hachek "ž" => "ž", // z hachek ); break; case "sk": // Slovenčina $ucspecialchars = array( "Á" => "Á", "Ä" => "Ä", "Č" => "Č", // C hachek "Ď" => "Ď", // D hachek "É" => "É", "Ě" => "Ě", // E hachek "Í" => "Í", "Ĺ" => "Ĺ", // L acute "Ľ" => "Ľ", // L hachek "Ň" => "Ň", // N hachek "Ó" => "Ó", "Ô" => "Ô", "Ŕ" => "Ŕ", // R acute "Ř" => "Ř", // R hachek "Š" => "Š", // S hachek "Ť" => "Ť", // T hachek "Ú" => "Ú", "Ů" => "Ů", // U ring "Ý" => "Ý", "Ž" => "Ž", // Z hachek ); $lcspecialchars = array( "á" => "á", "ä" => "ä", "č" => "č", // c hachek "ď" => "ď", // d hacheck "é" => "é", "ě" => "ě", // e hachek "í" => "í", "ĺ" => "ĺ", // l acute "ľ" => "ľ", // l hachek "ň" => "ň", // n hachek "ó" => "ó", "ô" => "ô", "ŕ" => "ŕ", // r acute "ř" => "ř", // r hachek "š" => "š", // s hachek "ť" => "ť", // t hachek "ú" => "ú", "ů" => "ů", // u ring "ý" => "ý", "ž" => "ž", // z hachek ); break; case "da": // Dansk $ucspecialchars = array( "Å" => "Å", "Æ" => "Æ", "É" => "É", "Ø" => "Ø", "Á" => "Á", "Í" => "Í", "Ó" => "Ó", "Ú" => "Ú", "Ý" => "Ý", ); $lcspecialchars = array( "å" => "å", "æ" => "æ", "é" => "é", "ø" => "ø", "á" => "á", "í" => "í", "ó" => "ó", "ú" => "ú", "ý" => "ý", ); break; case "de": // Deutsch $ucspecialchars = array( "Ä" => "Ä", "Ö" => "Ö", "Ü" => "Ü", "À" => "À", "É" => "É", ); $lcspecialchars = array( "ä" => "ä", "ö" => "ö", "ü" => "ü", "à" => "à", "é" => "é", "ß" => "ß", ); break; case "en": // English -- limited copy of the default case (Western European set) $ucspecialchars = array( "À" => "À", "Á" => "Á", "Â" => "Â", "Ã" => "Ã", "Ä" => "Ä", "Å" => "Å", "Æ" => "Æ", "Ç" => "Ç", "Ð" => "Ð", // capital Eth "È" => "È", "É" => "É", "Ê" => "Ê", "Ë" => "Ë", "Ì" => "Ì", "Í" => "Í", "Î" => "Î", "Ï" => "Ï", "IJ" => "IJ", // ligature IJ "Ñ" => "Ñ", "Ò" => "Ò", "Ó" => "Ó", "Ô" => "Ô", "Õ" => "Õ", "Ö" => "Ö", "Œ" => "Œ", "Ø" => "Ø", "Þ" => "Þ", // capital Thorn "Ù" => "Ù", "Ú" => "Ú", "Û" => "Û", "Ü" => "Ü", "Ý" => "Ý", "Ÿ" => "Ÿ", ); $lcspecialchars = array( "à" => "à", "á" => "á", "â" => "â", "ã" => "ã", "ä" => "ä", "å" => "å", "æ" => "æ", "ç" => "ç", "ð" => "ð", // lower-case Thorn "è" => "è", "é" => "é", "ê" => "ê", "ë" => "ë", "ì" => "ì", "í" => "í", "î" => "î", "ï" => "ï", "ij" => "ij", // ligature ij "ñ" => "ñ", "ò" => "ò", "ó" => "ó", "ô" => "ô", "õ" => "õ", "ö" => "ö", "œ" => "œ", "ø" => "ø", "þ" => "þ", // lower-case Eth "ù" => "ù", "ú" => "ú", "û" => "û", "ü" => "ü", "ý" => "ý", "ÿ" => "ÿ", "ß" => "ß", ); break; case "es": // Español $ucspecialchars = array( "Á" => "Á", "É" => "É", "Í" => "Í", "Ñ" => "Ñ", "Ó" => "Ó", "Ú" => "Ú", "Ü" => "Ü", "Ç" => "Ç", ); $lcspecialchars = array( "á" => "á", "é" => "é", "í" => "í", "ñ" => "ñ", "ó" => "ó", "ú" => "ú", "ü" => "ü", "ç" => "ç", ); break; case "eu": // Euskara $ucspecialchars = array( "Ç" => "Ç", ); $lcspecialchars = array( "ç" => "ç", ); break; case "fr": // Français $ucspecialchars = array( "À" => "À", "Â" => "Â", "Æ" => "Æ", "Ç" => "Ç", "È" => "È", "É" => "É", "Ê" => "Ê", "Ë" => "Ë", "Î" => "Î", "Ï" => "Ï", "Ô" => "Ô", "Œ" => "Œ", "Ù" => "Ù", "Û" => "Û", "Ü" => "Ü", "Ÿ" => "Ÿ", ); $lcspecialchars = array( "à" => "à", "â" => "â", "æ" => "æ", "ç" => "ç", "è" => "è", "é" => "é", "ê" => "ê", "ë" => "ë", "î" => "î", "ï" => "ï", "ô" => "ô", "œ" => "œ", "ù" => "ù", "û" => "û", "ü" => "ü", "ÿ" => "ÿ", ); break; case "gd-ie": // Gaeilge $ucspecialchars = array( "Á" => "Á", "É" => "É", "Í" => "Í", "Ó" => "Ó", "Ú" => "Ú", ); $lcspecialchars = array( "á" => "á", "é" => "é", "í" => "í", "ó" => "ó", "ú" => "ú", ); break; case "is": // Íslenska $ucspecialchars = array( "Á" => "Á", "Æ" => "Æ", "Ð" => "Ð", "É" => "É", "Í" => "Í", "Ó" => "Ó", "Ö" => "Ö", "Þ" => "Þ", "Ú" => "Ú", "Ý" => "Ý", ); $lcspecialchars = array( "á" => "á", "æ" => "æ", "ð" => "ð", "é" => "é", "í" => "í", "ó" => "ó", "ö" => "ö", "þ" => "þ", "ú" => "ú", "ý" => "ý", ); break; case "it": // Italiano $ucspecialchars = array( "À" => "À", "È" => "È", "É" => "É", "Ì" => "Ì", "Í" => "Í", "Ò" => "Ò", "Ó" => "Ó", "Ù" => "Ù", "Ú" => "Ú", "Ï" => "Ï", ); $lcspecialchars = array( "à" => "à", "è" => "è", "é" => "é", "ì" => "ì", "í" => "í", "ò" => "ò", "ó" => "ó", "ù" => "ù", "ú" => "ú", "ï" => "ï", ); break; case "hu": // Magyar $ucspecialchars = array( "Á" => "Á", "É" => "É", "Í" => "Í", "Ó" => "Ó", "Ö" => "Ö", "Ő" => "Ő", // O with double acute "Ú" => "Ú", "Ü" => "Ü", "Ű" => "Ű", // U with double acute ); $lcspecialchars = array( "á" => "á", "é" => "é", "í" => "í", "ó" => "ó", "ö" => "ö", "ő" => "ő", // o with double acute "ú" => "ú", "ü" => "ü", "ű" => "ű", // u with double acute ); break; case "lt": // Lithuanian $ucspecialchars = array( "Ą" => "Ą", // A cedille "Č" => "Č", // C with hachek/caron "Ę" => "Ę", // E cedille "Ė" => "Ė", // E with dot above "Į" => "Į", // I with ogonek "Š" => "Š", // S hachek "Ų" => "Ų", // U with ogonek "Ū" => "Ū", // U with macron "Ž" => "Ž", // Z hachek ); $lcspecialchars = array( "ą" => "ą", // a cedille "č" => "č", // c hachek/caron "ę" => "ę", // e cedille "ė" => "ė", // e with dot above "į" => "į", // i with ogonek "š" => "š", // s hachek "ų" => "ų", // u with ogonek "ū" => "ū", // u with macron "ž" => "ž", // z hachek ); break; case "nl": // Nederlands $ucspecialchars = array( "Á" => "Á", "Â" => "Â", "È" => "È", "É" => "É", "Ê" => "Ê", "Ë" => "Ë", "Í" => "Í", "Ï" => "Ï", "IJ" => "IJ", // ligature IJ "Ó" => "Ó", "Ô" => "Ô", "Ö" => "Ö", "Ú" => "Ú", "Ù" => "Ù", "Ä" => "Ä", "Û" => "Û", "Ü" => "Ü", ); $lcspecialchars = array( "á" => "á", "â" => "â", "è" => "è", "é" => "é", "ê" => "ê", "ë" => "ë", "í" => "í", "ï" => "ï", "ij" => "ij", // ligature ij "ó" => "ó", "ô" => "ô", "ö" => "ö", "ú" => "ú", "ù" => "ù", "ä" => "ä", "û" => "û", "ü" => "ü", ); break; case "no": // Norsk $ucspecialchars = array( "Æ" => "Æ", "Ø" => "Ø", "Å" => "Å", "À" => "À", "É" => "É", "Ê" => "Ê", "Ó" => "Ó", "Ò" => "Ò", "Ô" => "Ô", ); $lcspecialchars = array( "æ" => "æ", "ø" => "ø", "å" => "å", "à" => "à", "é" => "é", "ê" => "ê", "ó" => "ó", "ò" => "ò", "ô" => "ô", ); break; case "hawaiian": // 'Olelo Hawai'i $ucspecialchars = array( "Ā" => "Ā", // A with macron "Ē" => "Ē", // E with macron "Ī" => "Ī", // I with macron "Ō" => "Ō", // O with macron "Ū" => "Ū", // U with macron "‘" => "‘", // ‘okina ('okina) - new unicode ʻ ); $lcspecialchars = array( "ā" => "ā", // a with macron "ē" => "ē", // e with macron "ī" => "ī", // i with macron "ō" => "ō", // o with macron "ū" => "ū", // u with macron "‘" => "‘", // ‘okina ('okina) - new unicode ʻ ); break; case "pl": // Polski $ucspecialchars = array( "Ą" => "Ą", // A with ogonek "Ć" => "Ć", // C with acute "Ę" => "Ę", // E with ogonek "Ł" => "Ł", // L with stroke "Ń" => "Ń", // N with acute "Ó" => "Ó", "Ś" => "Ś", // S with acute "Ź" => "Ź", // Z with acute "Ż" => "Ż", // Z with dot above ); $lcspecialchars = array( "ą" => "ą", // a with ogonek "ć" => "ć", // c with acute "ę" => "ę", // e with ogonek "ł" => "ł", // l with stroke "ń" => "ń", // n with acute "ó" => "ó", "ś" => "ś", // s with acute "ź" => "ź", // z with acute "ż" => "ż", // z with dot above ); break; case "pt": // Portuguese $ucspecialchars = array( "À" => "À", "Á" => "Á", "Â" => "Â", "Ã" => "Ã", "Ç" => "Ç", "É" => "É", "Ê" => "Ê", "Í" => "Í", "Ó" => "Ó", "Ô" => "Ô", "Õ" => "Õ", "Ú" => "Ú", "Ü" => "Ü", "È" => "È", "Ò" => "Ò", ); $lcspecialchars = array( "à" => "à", "á" => "á", "â" => "â", "ã" => "ã", "ç" => "ç", "é" => "é", "ê" => "ê", "í" => "í", "ó" => "ó", "ô" => "ô", "õ" => "õ", "ú" => "ú", "ü" => "ü", "è" => "è", "ò" => "ò", ); break; case "sl": // Slovenšcina $ucspecialchars = array( "Č" => "Č", // C with caron "Š" => "Š", // S with caron "Ž" => "Ž", // Z with caron "Ć" => "Ć", // C with acute "Đ" => "Ð", // D with stroke "Ä" => "Ä", "Ö" => "Ö", "Ü" => "Ü", ); $lcspecialchars = array( "č" => "č", // c with caron "š" => "š", // s with caron "ž" => "ž", // z with caron "ć" => "ć", // c with acute "đ" => "đ", // d with stroke "ä" => "ä", "ö" => "ö", "ü" => "ü", ); break; case "fi": // Suomi $ucspecialchars = array( "Ä" => "Ä", "Ö" => "Ö", "Å" => "Å", "Š" => "Š", "Ž" => "Ž", ); $lcspecialchars = array( "ä" => "ä", "ö" => "ö", "å" => "å", "š" => "š", "ž" => "ž", ); break; case "sv": // Svenska $ucspecialchars = array( "Ä" => "Ä", "Å" => "Å", "É" => "É", "Ö" => "Ö", "Á" => "Á", "Ë" => "Ë", "Ü" => "Ü", ); $lcspecialchars = array( "ä" => "ä", "å" => "å", "é" => "é", "ö" => "ö", "á" => "á", "ë" => "ë", "ü" => "ü", ); break; case "tr": // Türkçe $ucspecialchars = array( "Â" => "Â", "Ç" => "Ç", "Ğ" => "Ğ", // G with breve "Î" => "Î", "İ" => "İ", // I with dot above "Ö" => "Ö", "Ş" => "Ş", // S with cedilla "Û" => "Û", "Ü" => "Ü", ); $lcspecialchars = array( "â" => "â", "ç" => "ç", "ğ" => "ğ", // g with breve "î" => "î", "ı" => "ı", // i without dot above "ö" => "ö", "ş" => "ş", // s with cedilla "û" => "û", "ü" => "ü", ); break; case "el": // greek $ucspecialchars = array( "Ά" => "Ά", "Α" => "Α", "Β" => "Β", // G with breve "Γ" => "Γ", "Δ" => "Δ", // I with dot above "Έ" => "Έ", "Ε" => "Ε", // S with cedilla "Ζ" => "Ζ", "Η" => "Η", "Θ" => "Θ", "Ί" => "Ί", "Ϊ" => "Ϊ", "Ι" => "Ι", "Κ" => "Κ", "Λ" => "Λ", "Μ" => "Μ", "Ν" => "Ν", "Ξ" => "Ξ", "Ό" => "Ό", "Ο" => "Ο", "Π" => "Π", "Ρ" => "Ρ", "Σ" => "Σ", "Τ" => "Τ", "Ύ" => "Ύ", "Ϋ" => "Ϋ", "Υ" => "Υ", "Φ" => "Φ", "Χ" => "Χ", "Ψ" => "Ψ", "Ώ" => "Ώ", "Ω" => "Ω" ); $lcspecialchars = array( "ά" => "ά", "α" => "α", "β" => "β", // g with breve "γ" => "γ", "δ" => "δ", // i without dot above "έ" => "έ", "ε" => "ε", // s with cedilla "ζ" => "ζ", "η" => "η", "θ" => "θ", "ί" => "ί", "ϊ" => "ϊ", "ΐ" => "ΐ", "ι" => "ι", "κ" => "κ", "λ" => "λ", "μ" => "μ", "ν" => "ν", "ξ" => "ξ", "ό" => "ό", "ο" => "ο", "π" => "π", "ρ" => "ρ", "σ" => "σ", "ς" => "ς", "τ" => "τ", "ύ" => "ύ", "ϋ" => "ϋ", "ΰ" => "ΰ", "υ" => "υ", "φ" => "φ", "χ" => "χ", "ψ" => "ψ", "ώ" => "ώ", "ω" => "ω", ); break; case "he": // hebrew $ucspecialchars = array( "א" => "א", "ב" => "ב", "ג" => "ג", "ד" => "ד", "ה" => "ה", "ו" => "ו", "ז" => "ז", "ח" => "ח", "ט" => "ט", "י" => "י", "כ" => "כ", "ך" => "ך", "ל" => "ל", "מ" => "מ", "ם" => "ם", "נ" => "נ", "ן" => "ן", "ס" => "ס", "ע" => "ע", "פ" => "פ", "ף" => "ף", "צ" => "צ", "ץ" => "ץ", "ק" => "ק", "ר" => "ר", "ש" => "ש", "ת" => "ת" ); $lcspecialchars = array( "א" => "א", "ב" => "ב", "ג" => "ג", "ד" => "ד", "ה" => "ה", "ו" => "ו", "ז" => "ז", "ח" => "ח", "ט" => "ט", "י" => "י", "כ" => "כ", "ך" => "ך", "ל" => "ל", "מ" => "מ", "ם" => "ם", "נ" => "נ", "ן" => "ן", "ס" => "ס", "ע" => "ע", "פ" => "פ", "ף" => "ף", "צ" => "צ", "ץ" => "ץ", "ק" => "ק", "ר" => "ר", "ש" => "ש", "ת" => "ת" ); break; case "ar": // arabic $ucspecialchars = array( "ا" => "ا", "ب" => "ب", "ت" => "ت", "ث" => "ث", "ج" => "ج", "ح" => "ح", "خ" => "خ", "د" => "د", "ذ" => "ذ", "ر" => "ر", "ز" => "ز", "س" => "س", "ش" => "ش", "ص" => "ص", "ض" => "ض", "ط" => "ط", "ظ" => "ظ", "ع" => "ع", "غ" => "غ", "ف" => "ف", "ق" => "ق", "ك" => "ك", "ل" => "ل", "م" => "م", "ن" => "ن", "ه" => "ه", "و" => "و", "ي" => "ي", "آ" => "آ", "ة" => "ة", "ى" => "ى", "ی" => "ی" ); $lcspecialchars = array( "ا" => "ا", "ب" => "ب", "ت" => "ت", "ث" => "ث", "ج" => "ج", "ح" => "ح", "خ" => "خ", "د" => "د", "ذ" => "ذ", "ر" => "ر", "ز" => "ز", "س" => "س", "ش" => "ش", "ص" => "ص", "ض" => "ض", "ط" => "ط", "ظ" => "ظ", "ع" => "ع", "غ" => "غ", "ف" => "ف", "ق" => "ق", "ك" => "ك", "ل" => "ل", "م" => "م", "ن" => "ن", "ه" => "ه", "و" => "و", "ي" => "ي", "آ" => "آ", "ة" => "ة", "ى" => "ى", "ی" => "ی" ); break; case "ru": // russian $ucspecialchars = array( "А" => "А", "Б" => "Б", "В" => "В", "Г" => "Г", "Д" => "Д", "Е" => "Е", "Ё" => "Ё", "Ж" => "Ж", "З" => "З", "И" => "И", "Й" => "Й", "К" => "К", "Л" => "Л", "М" => "М", "Н" => "Н", "О" => "О", "П" => "П", "Р" => "Р", "С" => "С", "Т" => "Т", "У" => "У", "Ф" => "Ф", "Х" => "Х", "Ц" => "Ц", "Ч" => "Ч", "Ш" => "Ш", "Щ" => "Щ", "Ъ" => "Ъ", "Ы" => "Ы", "Ь" => "Ь", "Э" => "Э", "Ю" => "Ю", "Я" => "Я" ); $lcspecialchars = array( "а" => "а", "б" => "б", "в" => "в", "г" => "г", "д" => "д", "е" => "е", "ё" => "ё", "ж" => "ж", "з" => "з", "и" => "и", "й" => "й", "к" => "к", "л" => "л", "м" => "м", "н" => "н", "о" => "о", "п" => "п", "р" => "р", "с" => "с", "т" => "т", "у" => "у", "ф" => "ф", "х" => "х", "ц" => "ц", "ч" => "ч", "ш" => "ш", "щ" => "щ", "ъ" => "ъ", "ы" => "ы", "ь" => "ь", "э" => "э", "ю" => "ю", "я" => "я" ); break; case "vi": // vietnamese $ucspecialchars = array( "À" => "À", // A with grave "Á" => "Á", // A with acute "Â" => "Â", // A with circumflex "Ã" => "Ã", // A with tilde "Ạ" => "Ạ", // A with dot below "Ả" => "Ả", // A with hook above "Ă" => "Ă", // A with breve "Ấ" => "Ấ", // A with circumflex and acute "Ầ" => "Ầ", // A with circumflex and grave "Ẫ" => "Ẫ", // A with circumflex and tilde "Ậ" => "Ậ", // A with circumflex and dot below "Ắ" => "Ắ", // A with breve and acute "Ằ" => "Ằ", // A with breve and grave "Ẳ" => "Ẳ", // A with breve and hook above "Ẵ" => "Ẵ", // A with breve and tilde "Ặ" => "Ặ", // A with breve and dot below "Đ" => "Đ", // D with stroke "È" => "È", // E with grave "É" => "É", // E with acute "Ê" => "Ê", // E with circumflex "Ẹ" => "Ẹ", // E with dot below "Ẻ" => "Ẻ", // E with hook above "Ẽ" => "Ẽ", // E with tilde "Ế" => "Ế", // E with circumflex and acute "Ề" => "Ề", // E with circumflex and grave "Ể" => "Ể", // E with circumflex and hook above "Ễ" => "Ễ", // E with circumflex and tilde "Ệ" => "Ệ", // E with circumflex and dot below "Ì" => "Ì", // I with grave "Í" => "Í", // I with acute "Ĩ" => "Ĩ", // I with tilde "Ỉ" => "Ỉ", // I with hook above "Ị" => "Ị", // I with dot below "Ò" => "Ò", // O with grave "Ó" => "Ó", // O with acute "Ô" => "Ô", // O with circumflex "Õ" => "Õ", // O with tilde "Ơ" => "Ơ", // O with horn "Ọ" => "Ọ", // O with dot below "Ỏ" => "Ỏ", // O with hook above "Ố" => "Ố", // O with circumflex and acute "Ồ" => "Ồ", // O with circumflex and grave "Ổ" => "Ổ", // O with circumflex and hook above "Ỗ" => "Ỗ", // O with circumflex and tilde "Ộ" => "Ộ", // O with circumflex and dot below "Ớ" => "Ớ", // O with horn and acute "Ờ" => "Ờ", // O with horn and grave "Ở" => "Ở", // O with horn and hook above "Ỡ" => "Ỡ", // O with horn and tilde "Ợ" => "Ợ", // O with horn and dot below "Ù" => "Ù", // U with grave "Ú" => "Ú", // U with acute "Ũ" => "Ũ", // U with tilde "Ư" => "Ư", // U with horn "Ụ" => "Ụ", // U with dot below "Ủ" => "Ủ", // U with hook above "Ứ" => "Ứ", // U with horn and acute "Ừ" => "Ừ", // U with horn and grave "Ử" => "Ử", // U with horn and hook above "Ữ" => "Ữ", // U with horn and tilde "Ự" => "Ự", // U with horn and dot below "Ý" => "Ý", // Y with acute "Ỳ" => "Ỳ", // Y with grave "Ỵ" => "Ỵ", // Y with dot below "Ỷ" => "Ỷ", // Y with hook above "Ỹ" => "Ỹ", // Y with tilde ); $lcspecialchars = array( "à" => "à", // a with grave "á" => "á", // a with acute "â" => "â", // a with circumflex "ã" => "ã", // a with tilde "ạ" => "ạ", // a with dot below "ả" => "ả", // a with hook above "ă" => "ă", // a with breve "ấ" => "ấ", // a with circumflex and acute "ầ" => "ầ", // a with circumflex and grave "ẫ" => "ẫ", // a with circumflex and tilde "ậ" => "ậ", // a with circumflex and dot below "ắ" => "ắ", // a with breve and acute "ằ" => "ằ", // a with breve and grave "ẳ" => "ẳ", // a with breve and hook above "ẵ" => "ẵ", // a with breve and tilde "ặ" => "ặ", // a with breve and dot below "đ" => "đ", // d with stroke "è" => "è", // e with grave "é" => "é", // e with acute "ê" => "ê", // e with circumflex "ẹ" => "ẹ", // e with dot below "ẻ" => "ẻ", // e with hook above "ẽ" => "ẽ", // e with tilde "ế" => "ế", // e with circumflex and acute "ề" => "ề", // e with circumflex and grave "ể" => "ể", // e with circumflex and hook above "ễ" => "ễ", // e with circumflex and tilde "ệ" => "ệ", // e with circumflex and dot below "ì" => "ì", // i with grave "í" => "í", // i with acute "ĩ" => "ĩ", // i with tilde "ỉ" => "ỉ", // i with hook above "ị" => "ị", // i with dot below "ò" => "ò", // o with grave "ó" => "ó", // o with acute "ô" => "ô", // o with circumflex "õ" => "õ", // o with tilde "ơ" => "ơ", // o with horn "ọ" => "ọ", // o with dot below "ỏ" => "ỏ", // o with hook above "ố" => "ố", // o with circumflex and acute "ồ" => "ồ", // o with circumflex and grave "ổ" => "ổ", // o with circumflex and hook above "ỗ" => "ỗ", // o with circumflex and tilde "ộ" => "ộ", // o with circumflex and dot below "ớ" => "ớ", // o with horn and acute "ờ" => "ờ", // o with horn and grave "ở" => "ở", // o with horn and hook above "ỡ" => "ỡ", // o with horn and tilde "ợ" => "ợ", // o with horn and dot below "ù" => "ù", // u with grave "ú" => "ú", // u with acute "ũ" => "ũ", // u with tilde "ư" => "ư", // u with horn "ụ" => "ụ", // u with dot below "ủ" => "ủ", // u with hook above "ứ" => "ứ", // u with horn and acute "ừ" => "ừ", // u with horn and grave "ử" => "ử", // u with horn and hook above "ữ" => "ữ", // u with horn and tilde "ự" => "ự", // u with horn and dot below "ý" => "ý", // y with acute "ỳ" => "ỳ", // y with grave "ỵ" => "ỵ", // y with dot below "ỷ" => "ỷ", // y with hook above "ỹ" => "ỹ", // y with tilde ); break; default: // list all $ucspecialchars = array( "À" => "À", "Á" => "Á", "Â" => "Â", "Ã" => "Ã", "Ä" => "Ä", "Å" => "Å", "Ą" => "Ą", // A cedille "Ā" => "Ā", // A with macron "Æ" => "Æ", "Ç" => "Ç", "Č" => "Č", // C with hachek/caron "Ć" => "Ć", // C with acute "Ð" => "Ð", // eth "Đ" => "Ð", // D with stroke "Ď" => "Ď", // D hachek "È" => "È", "É" => "É", "Ê" => "Ê", "Ë" => "Ë", "Ę" => "Ę", // E cedille "Ě" => "Ě", // E hachek "Ē" => "Ē", // E with macron "Ğ" => "Ğ", // G with breve "Ì" => "Ì", "Í" => "Í", "Î" => "Î", "Ï" => "Ï", "İ" => "İ", // I with dot above "Ī" => "Ī", // I with macron "IJ" => "IJ", // ligature IJ "Ĺ" => "Ĺ", // L acute "Ľ" => "Ľ", // L hachek "Ł" => "Ł", // L with stroke "Ñ" => "Ñ", "Ň" => "Ň", // N hachek "Ń" => "Ń", // N with acute "Ò" => "Ò", "Ó" => "Ó", "Ô" => "Ô", "Õ" => "Õ", "Ö" => "Ö", "Ő" => "Ő", // O with double acute "Ō" => "Ō", // O with macron "Œ" => "Œ", "Ø" => "Ø", "Ŕ" => "Ŕ", // R acute "Ř" => "Ř", // R hachek "Š" => "Š", // S hachek "Ś" => "Ś", // S with acute "Ş" => "Ş", // S with cedilla "Ť" => "Ť", // T hachek "Ù" => "Ù", "Ú" => "Ú", "Û" => "Û", "Ü" => "Ü", "Ů" => "Ů", // U ring "Ű" => "Ű", // U with double acute "Ū" => "Ū", // U with macron "Ý" => "Ý", "Þ" => "Þ", "Ÿ" => "Ÿ", "Ž" => "Ž", // Z hachek "Ź" => "Ź", // Z with acute "Ż" => "Ż", // Z with dot above "‘" => "‘", // ‘okina ('okina) - new unicode ʻ ); $lcspecialchars = array( "à" => "à", "á" => "á", "â" => "â", "ã" => "ã", "ä" => "ä", "å" => "å", "ą" => "ą", // a cedille "ā" => "ā", // a with macron "æ" => "æ", "ç" => "ç", "č" => "č", // c hachek/caron "ć" => "ć", // c with acute "ď" => "ď", // d hacheck "đ" => "đ", // d with stroke "ð" => "ð", "è" => "è", "é" => "é", "ê" => "ê", "ë" => "ë", "ę" => "ę", // e cedille "ě" => "ě", // e hachek "ē" => "ē", // e with macron "ğ" => "ğ", // g with breve "ì" => "ì", "í" => "í", "î" => "î", "ï" => "ï", "ı" => "ı", // i without dot above "ī" => "ī", // i with macron "ij" => "ij", // ligature ij "ĺ" => "ĺ", // l acute "ľ" => "ľ", // l hachek "ł" => "ł", // l with stroke "ñ" => "ñ", "ʼn" => "ʼn", // n preceded by apostrophe "ň" => "ň", // n hachek "ń" => "ń", // n with acute "ò" => "ò", "ó" => "ó", "ô" => "ô", "õ" => "õ", "ö" => "ö", "ő" => "ő", // o with double acute "ō" => "ō", // o with macron "œ" => "œ", "ø" => "ø", "ŕ" => "ŕ", // r acute "ř" => "ř", // r hachek "š" => "š", // s hachek "ś" => "ś", // s with acute "ş" => "ş", // s with cedilla "ß" => "ß", "ť" => "ť", // t apostrophe "ù" => "ù", "ú" => "ú", "û" => "û", "ü" => "ü", "ů" => "ů", // u ring "ű" => "ű", // u with double acute "ū" => "ū", // u with macron "ý" => "ý", "þ" => "þ", "ÿ" => "ÿ", "ž" => "ž", // z hachek "ź" => "ź", // z with acute "ż" => "ż", // z with dot above "‘" => "‘", // ‘okina ('okina) - new unicode ʻ ); } $otherspecialchars = array( "¡" => "¡", "¿" => "¿", "„" => "„", "“" => "“", "”" => "”", "‚" => "‚", "‛" => "‛", "‘" => "‘", "’" => "’", "«" => "«", "»" => "»", "‹" => "‹", "›" => "›", "–" => "–", // en-dash (e.g. for ranges, such as 1979–1980) "ª" => "ª", // feminine ordinal (nª) "º" => "º", // masculine ordinal (nº) "€" => "€", "¢" => "¢", "£" => "£", "¥" => "¥", "©" => "©", "°" => "°", // degree symbol "†" => "†", "‡" => "‡", "§" => "§", "¶" => "¶", );