romanization support in utf8 library

This patch addes basic romanization support to the utf-8 library. It
converts non-latin languages to ASCII.

The transliteration tables used where gathered from various places
on the net. I do not speak any of those languages so I can't say how
good they are. Any recommendations and fixes are welcome!

This can be enabled for ID cleaning by setting the deaccent option to 2.
It is also used in the XHTML renderer to generate section ids based
on the header titles. Leading digits and any remaining non-ASCII chars
are removed as well. This is the first step to make section ID always
XHTML compatible. Making sure they are unique is not implemented yet.

darcs-hash:20060210200627-7ad00-61a633563bb92a00ef4a3f699d73117139cbf367.gz

4 files changed, 193 insertions, 5 deletions

diff --git a/conf/dokuwiki.php b/conf/dokuwiki.php
index 9b027ea7f..afdbdf3a0 100644
--- a/conf/dokuwiki.php
+++ b/conf/dokuwiki.php
@@ -34,7 +34,7 @@ $conf['toptoclevel'] = 1;                 //Level starting with and below to inc
 $conf['maxtoclevel'] = 3;                 //Up to which level include into AutoTOC (max. 5)
 $conf['maxseclevel'] = 3;                 //Up to which level create editable sections (max. 5)
 $conf['camelcase']   = 0;                 //Use CamelCase for linking? (I don't like it) 0|1
-$conf['deaccent']    = 1;                 //convert accented chars to unaccented ones in pagenames?
+$conf['deaccent']    = 1;                 //deaccented chars in pagenames (1) or romanize (2) or keep (0)?
 $conf['useheading']  = 0;                 //use the first heading in a page as its name
 $conf['refcheck']    = 1;                 //check for references before deleting media files
 $conf['refshow']     = 0;                 //how many references should be shown, 5 is a good value
diff --git a/inc/pageutils.php b/inc/pageutils.php
index 73be0a3a8..53e5b2aba 100644
--- a/inc/pageutils.php
+++ b/inc/pageutils.php
@@ -65,8 +65,10 @@ function getID($param='id',$clean=true){
  * converted to unaccented ones
  *
  * @author Andreas Gohr <andi@splitbrain.org>
+ * @param  string  $id    The pageid to clean
+ * @param  boolean $ascii Force ASCII
  */
-function cleanID($id){
+function cleanID($id,$ascii=false){
   global $conf;
   global $lang;
   static $sepcharpat = null;
@@ -86,11 +88,14 @@ function cleanID($id){
     $id = strtr($id,'/',$sepchar);
   }
 
-  if($conf['deaccent']) $id = utf8_deaccent($id,-1);
+  if($conf['deaccent'] == 2 || $ascii) $id = utf8_romanize($id); 
+  if($conf['deaccent'] || $ascii) $id = utf8_deaccent($id,-1);
 
   //remove specials
   $id = utf8_stripspecials($id,$sepchar,'\*');
 
+  if($ascii) $id = utf8_strip($id);
+
   //clean up
   $id = preg_replace($sepcharpat,$sepchar,$id);
   $id = preg_replace('#:+#',':',$id);
diff --git a/inc/parser/xhtml.php b/inc/parser/xhtml.php
index 31246125b..5e898ab36 100644
--- a/inc/parser/xhtml.php
+++ b/inc/parser/xhtml.php
@@ -967,8 +967,14 @@ class Doku_Renderer_xhtml extends Doku_Renderer {
         return htmlspecialchars($string);
     }
     
+    /**
+     * Creates a linkid from a headline
+     */
     function _headerToLink($title) {
-        return str_replace(':','',cleanID($title));
+        $title = str_replace(':','',cleanID($title,true));
+        $title = ltrim($title,'0123456789');
+        if(empty($title)) $title='section';
+        return $title;
     }
 
     /**
diff --git a/inc/utf8.php b/inc/utf8.php
index 46d30f85d..723c470bb 100644
--- a/inc/utf8.php
+++ b/inc/utf8.php
@@ -288,6 +288,18 @@ function utf8_deaccent($string,$case=0){
 }
 
 /**
+ * Romanize a non-latin string
+ *
+ * @author Andreas Gohr <andi@splitbrain.org>
+ */
+function utf8_romanize($string){
+  if(utf8_isASCII($string)) return $string; //nothing to do
+
+  global $UTF8_ROMANIZATION;
+  return strtr($string,$UTF8_ROMANIZATION);
+}
+
+/**
  * Removes special characters (nonalphanumeric) from a UTF-8 string
  *
  * This function adds the controlchars 0x00 to 0x19 to the array of
@@ -462,7 +474,7 @@ function utf16be_to_utf8(&$str) {
  *
  * @author Andreas Gohr <andi@splitbrain.org>
  */
-$UTF8_LOWER_TO_UPPER = array(
+static $UTF8_LOWER_TO_UPPER = array(
   0x0061=>0x0041, 0x03C6=>0x03A6, 0x0163=>0x0162, 0x00E5=>0x00C5, 0x0062=>0x0042,
   0x013A=>0x0139, 0x00E1=>0x00C1, 0x0142=>0x0141, 0x03CD=>0x038E, 0x0101=>0x0100,
   0x0491=>0x0490, 0x03B4=>0x0394, 0x015B=>0x015A, 0x0064=>0x0044, 0x03B3=>0x0393,
@@ -639,5 +651,170 @@ $UTF8_SPECIAL_CHARS = array(
 	0xf8fb, 0xf8fc, 0xf8fd, 0xf8fe, 0xfe7c, 0xfe7d,
 );
 
+/**
+ * Romanization lookup table
+ *
+ * This lookup tables provides a way to transform strings written in a language
+ * different from the ones based upon latin letters into plain ASCII.
+ *
+ * Please note: this is not a scientific transliteration table. It only works
+ * oneway from nonlatin to ASCII and it works by simple character replacement
+ * only. Specialities of each language are not supported.
+ *
+ * @author Andreas Gohr <andi@splitbrain.org>
+ * @author Vitaly Blokhin <vitinfo@vitn.com>
+ * @link   http://www.uconv.com/translit.htm
+ * @author Bisqwit <bisqwit@iki.fi>
+ * @link   http://kanjidict.stc.cx/hiragana.php?src=2
+ * @link   http://www.translatum.gr/converter/greek-transliteration.htm
+ * @link   http://en.wikipedia.org/wiki/Royal_Thai_General_System_of_Transcription
+ * @link   http://www.btranslations.com/resources/romanization/korean.asp
+ */
+$UTF8_ROMANIZATION = array(
+  //russian cyrillic
+  'а'=>'a','А'=>'A','б'=>'b','Б'=>'B','в'=>'v','В'=>'V','г'=>'g','Г'=>'G',
+  'д'=>'d','Д'=>'D','е'=>'e','Е'=>'E','ё'=>'jo','Ё'=>'Jo','ж'=>'zh','Ж'=>'Zh',
+  'з'=>'z','З'=>'Z','и'=>'i','И'=>'I','й'=>'j','Й'=>'J','к'=>'k','К'=>'K',
+  'л'=>'l','Л'=>'L','м'=>'m','М'=>'M','н'=>'n','Н'=>'N','о'=>'o','О'=>'O',
+  'п'=>'p','П'=>'P','р'=>'r','Р'=>'R','с'=>'s','С'=>'S','т'=>'t','Т'=>'T',
+  'у'=>'u','У'=>'U','ф'=>'f','Ф'=>'F','х'=>'x','Х'=>'X','ц'=>'c','Ц'=>'C',
+  'ч'=>'ch','Ч'=>'Ch','ш'=>'sh','Ш'=>'Sh','щ'=>'th','Щ'=>'Th','ъ'=>'qh',
+  'Ъ'=>'Qh','ы'=>'y','Ы'=>'Y','ь'=>'q','Ь'=>'Q','э'=>'eh','Э'=>'Eh','ю'=>'ju',
+  'Ю'=>'Ju','я'=>'ja','Я'=>'Ja',
+  // Ukrainian cyrillic
+  'Ґ'=>'Gh','ґ'=>'gh','Є'=>'Je','є'=>'je','І'=>'I','і'=>'i','Ї'=>'Ji','ї'=>'ji',
+  // Georgian
+  'ა'=>'a','ბ'=>'b','გ'=>'g','დ'=>'d','ე'=>'e','ვ'=>'v','ზ'=>'z','თ'=>'th',
+  'ი'=>'i','კ'=>'p','ლ'=>'l','მ'=>'m','ნ'=>'n','ო'=>'o','პ'=>'p','ჟ'=>'zh',
+  'რ'=>'r','ს'=>'s','ტ'=>'t','უ'=>'u','ფ'=>'ph','ქ'=>'kh','ღ'=>'gh','ყ'=>'q',
+  'შ'=>'sh','ჩ'=>'ch','ც'=>'c','ძ'=>'dh','წ'=>'w','ჭ'=>'j','ხ'=>'x','ჯ'=>'jh',
+  'ჰ'=>'xh',
+  //Sanskrit
+  'अ'=>'a','आ'=>'ah','इ'=>'i','ई'=>'ih','उ'=>'u','ऊ'=>'uh','ऋ'=>'ry',
+  'ॠ'=>'ryh','ऌ'=>'ly','ॡ'=>'lyh','ए'=>'e','ऐ'=>'ay','ओ'=>'o','औ'=>'aw',
+  'अं'=>'amh','अः'=>'aq','क'=>'k','ख'=>'kh','ग'=>'g','घ'=>'gh','ङ'=>'nh',
+  'च'=>'c','छ'=>'ch','ज'=>'j','झ'=>'jh','ञ'=>'ny','ट'=>'tq','ठ'=>'tqh',
+  'ड'=>'dq','ढ'=>'dqh','ण'=>'nq','त'=>'t','थ'=>'th','द'=>'d','ध'=>'dh',
+  'न'=>'n','प'=>'p','फ'=>'ph','ब'=>'b','भ'=>'bh','म'=>'m','य'=>'z','र'=>'r',
+  'ल'=>'l','व'=>'v','श'=>'sh','ष'=>'sqh','स'=>'s','ह'=>'x',
+  //Hebrew
+  'ב'=>'a','ג'=>'b','ד'=>'g','ה'=>'d','ו'=>'x','ז'=>'v','ח'=>'kh','ט'=>'th',
+  'י'=>'y','ך'=>'k','כ'=>'k','ל'=>'l','ם'=>'m','מ'=>'m','ן'=>'n','נ'=>'n',
+  'ס'=>'s','ע'=>'ah','ף'=>'p','פ'=>'p','ץ'=>'c','צ'=>'c','ק'=>'q','ר'=>'r',
+  'ש'=>'sh','ת'=>'t',
+  //Arabic
+  'ا'=>'a','ب'=>'b','ت'=>'t','ث'=>'th','ج'=>'g','ح'=>'xh','خ'=>'x','د'=>'d',
+  'ذ'=>'dh','ر'=>'r','ز'=>'z','س'=>'s','ش'=>'sh','ص'=>'s\'','ض'=>'d\'',
+  'ط'=>'t\'','ظ'=>'z\'','ع'=>'y','غ'=>'gh','ف'=>'f','ق'=>'q','ك'=>'k',
+  'ل'=>'l','م'=>'m','ن'=>'n','ه'=>'x\'','و'=>'u','ي'=>'i',
+
+  // Japanese hiragana
+  'あ'=>'a','え'=>'e','い'=>'i','お'=>'o','う'=>'u','ば'=>'ba','べ'=>'be',
+  'び'=>'bi','ぼ'=>'bo','ぶ'=>'bu','し'=>'ci','だ'=>'da','で'=>'de','ぢ'=>'di',
+  'ど'=>'do','づ'=>'du','ふぁ'=>'fa','ふぇ'=>'fe','ふぃ'=>'fi','ふぉ'=>'fo',
+  'ふ'=>'fu','が'=>'ga','げ'=>'ge','ぎ'=>'gi','ご'=>'go','ぐ'=>'gu','は'=>'ha',
+  'へ'=>'he','ひ'=>'hi','ほ'=>'ho','ふ'=>'hu','じゃ'=>'ja','じぇ'=>'je',
+  'じ'=>'ji','じょ'=>'jo','じゅ'=>'ju','か'=>'ka','け'=>'ke','き'=>'ki',
+  'こ'=>'ko','く'=>'ku','ら'=>'la','れ'=>'le','り'=>'li','ろ'=>'lo','る'=>'lu',
+  'ま'=>'ma','め'=>'me','み'=>'mi','も'=>'mo','む'=>'mu','な'=>'na','ね'=>'ne',
+  'に'=>'ni','の'=>'no','ぬ'=>'nu','ぱ'=>'pa','ぺ'=>'pe','ぴ'=>'pi','ぽ'=>'po',
+  'ぷ'=>'pu','ら'=>'ra','れ'=>'re','り'=>'ri','ろ'=>'ro','る'=>'ru','さ'=>'sa',
+  'せ'=>'se','し'=>'si','そ'=>'so','す'=>'su','た'=>'ta','て'=>'te','ち'=>'ti',
+  'と'=>'to','つ'=>'tu','ヴぁ'=>'va','ヴぇ'=>'ve','ヴぃ'=>'vi','ヴぉ'=>'vo',
+  'ヴ'=>'vu','わ'=>'wa','うぇ'=>'we','うぃ'=>'wi','を'=>'wo','や'=>'ya','いぇ'=>'ye',
+  'い'=>'yi','よ'=>'yo','ゆ'=>'yu','ざ'=>'za','ぜ'=>'ze','じ'=>'zi','ぞ'=>'zo',
+  'ず'=>'zu','びゃ'=>'bya','びぇ'=>'bye','びぃ'=>'byi','びょ'=>'byo','びゅ'=>'byu',
+  'ちゃ'=>'cha','ちぇ'=>'che','ち'=>'chi','ちょ'=>'cho','ちゅ'=>'chu','ちゃ'=>'cya',
+  'ちぇ'=>'cye','ちぃ'=>'cyi','ちょ'=>'cyo','ちゅ'=>'cyu','でゃ'=>'dha','でぇ'=>'dhe',
+  'でぃ'=>'dhi','でょ'=>'dho','でゅ'=>'dhu','どぁ'=>'dwa','どぇ'=>'dwe','どぃ'=>'dwi',
+  'どぉ'=>'dwo','どぅ'=>'dwu','ぢゃ'=>'dya','ぢぇ'=>'dye','ぢぃ'=>'dyi','ぢょ'=>'dyo',
+  'ぢゅ'=>'dyu','ぢ'=>'dzi','ふぁ'=>'fwa','ふぇ'=>'fwe','ふぃ'=>'fwi','ふぉ'=>'fwo',
+  'ふぅ'=>'fwu','ふゃ'=>'fya','ふぇ'=>'fye','ふぃ'=>'fyi','ふょ'=>'fyo','ふゅ'=>'fyu',
+  'ぎゃ'=>'gya','ぎぇ'=>'gye','ぎぃ'=>'gyi','ぎょ'=>'gyo','ぎゅ'=>'gyu','ひゃ'=>'hya',
+  'ひぇ'=>'hye','ひぃ'=>'hyi','ひょ'=>'hyo','ひゅ'=>'hyu','じゃ'=>'jya','じぇ'=>'jye',
+  'じぃ'=>'jyi','じょ'=>'jyo','じゅ'=>'jyu','きゃ'=>'kya','きぇ'=>'kye','きぃ'=>'kyi',
+  'きょ'=>'kyo','きゅ'=>'kyu','りゃ'=>'lya','りぇ'=>'lye','りぃ'=>'lyi','りょ'=>'lyo',
+  'りゅ'=>'lyu','みゃ'=>'mya','みぇ'=>'mye','みぃ'=>'myi','みょ'=>'myo','みゅ'=>'myu',
+  'ん'=>'n','にゃ'=>'nya','にぇ'=>'nye','にぃ'=>'nyi','にょ'=>'nyo','にゅ'=>'nyu',
+  'ぴゃ'=>'pya','ぴぇ'=>'pye','ぴぃ'=>'pyi','ぴょ'=>'pyo','ぴゅ'=>'pyu','りゃ'=>'rya',
+  'りぇ'=>'rye','りぃ'=>'ryi','りょ'=>'ryo','りゅ'=>'ryu','しゃ'=>'sha','しぇ'=>'she',
+  'し'=>'shi','しょ'=>'sho','しゅ'=>'shu','すぁ'=>'swa','すぇ'=>'swe','すぃ'=>'swi',
+  'すぉ'=>'swo','すぅ'=>'swu','しゃ'=>'sya','しぇ'=>'sye','しぃ'=>'syi','しょ'=>'syo',
+  'しゅ'=>'syu','てゃ'=>'tha','てぇ'=>'the','てぃ'=>'thi','てょ'=>'tho','てゅ'=>'thu',
+  'つゃ'=>'tsa','つぇ'=>'tse','つぃ'=>'tsi','つょ'=>'tso','つ'=>'tsu','とぁ'=>'twa',
+  'とぇ'=>'twe','とぃ'=>'twi','とぉ'=>'two','とぅ'=>'twu','ちゃ'=>'tya','ちぇ'=>'tye',
+  'ちぃ'=>'tyi','ちょ'=>'tyo','ちゅ'=>'tyu','ヴゃ'=>'vya','ヴぇ'=>'vye','ヴぃ'=>'vyi',
+  'ヴょ'=>'vyo','ヴゅ'=>'vyu','うぁ'=>'wha','うぇ'=>'whe','うぃ'=>'whi','うぉ'=>'who',
+  'うぅ'=>'whu','ゑ'=>'wye','ゐ'=>'wyi','じゃ'=>'zha','じぇ'=>'zhe','じぃ'=>'zhi',
+  'じょ'=>'zho','じゅ'=>'zhu','じゃ'=>'zya','じぇ'=>'zye','じぃ'=>'zyi','じょ'=>'zyo',
+  'じゅ'=>'zyu',
+  // Japanese katakana
+  'ア'=>'a','エ'=>'e','イ'=>'i','オ'=>'o','ウ'=>'u','バ'=>'ba','ベ'=>'be','ビ'=>'bi',
+  'ボ'=>'bo','ブ'=>'bu','シ'=>'ci','ダ'=>'da','デ'=>'de','ヂ'=>'di','ド'=>'do',
+  'ヅ'=>'du','ファ'=>'fa','フェ'=>'fe','フィ'=>'fi','フォ'=>'fo','フ'=>'fu','ガ'=>'ga',
+  'ゲ'=>'ge','ギ'=>'gi','ゴ'=>'go','グ'=>'gu','ハ'=>'ha','ヘ'=>'he','ヒ'=>'hi','ホ'=>'ho',
+  'フ'=>'hu','ジャ'=>'ja','ジェ'=>'je','ジ'=>'ji','ジョ'=>'jo','ジュ'=>'ju','カ'=>'ka',
+  'ケ'=>'ke','キ'=>'ki','コ'=>'ko','ク'=>'ku','ラ'=>'la','レ'=>'le','リ'=>'li','ロ'=>'lo',
+  'ル'=>'lu','マ'=>'ma','メ'=>'me','ミ'=>'mi','モ'=>'mo','ム'=>'mu','ナ'=>'na','ネ'=>'ne',
+  'ニ'=>'ni','ノ'=>'no','ヌ'=>'nu','パ'=>'pa','ペ'=>'pe','ピ'=>'pi','ポ'=>'po','プ'=>'pu',
+  'ラ'=>'ra','レ'=>'re','リ'=>'ri','ロ'=>'ro','ル'=>'ru','サ'=>'sa','セ'=>'se','シ'=>'si',
+  'ソ'=>'so','ス'=>'su','タ'=>'ta','テ'=>'te','チ'=>'ti','ト'=>'to','ツ'=>'tu','ヴァ'=>'va',
+  'ヴェ'=>'ve','ヴィ'=>'vi','ヴォ'=>'vo','ヴ'=>'vu','ワ'=>'wa','ウェ'=>'we','ウィ'=>'wi',
+  'ヲ'=>'wo','ヤ'=>'ya','イェ'=>'ye','イ'=>'yi','ヨ'=>'yo','ユ'=>'yu','ザ'=>'za','ゼ'=>'ze',
+  'ジ'=>'zi','ゾ'=>'zo','ズ'=>'zu','ビャ'=>'bya','ビェ'=>'bye','ビィ'=>'byi','ビョ'=>'byo',
+  'ビュ'=>'byu','チャ'=>'cha','チェ'=>'che','チ'=>'chi','チョ'=>'cho','チュ'=>'chu',
+  'チャ'=>'cya','チェ'=>'cye','チィ'=>'cyi','チョ'=>'cyo','チュ'=>'cyu','デャ'=>'dha',
+  'デェ'=>'dhe','ディ'=>'dhi','デョ'=>'dho','デュ'=>'dhu','ドァ'=>'dwa','ドェ'=>'dwe',
+  'ドィ'=>'dwi','ドォ'=>'dwo','ドゥ'=>'dwu','ヂャ'=>'dya','ヂェ'=>'dye','ヂィ'=>'dyi',
+  'ヂョ'=>'dyo','ヂュ'=>'dyu','ヂ'=>'dzi','ファ'=>'fwa','フェ'=>'fwe','フィ'=>'fwi',
+  'フォ'=>'fwo','フゥ'=>'fwu','フャ'=>'fya','フェ'=>'fye','フィ'=>'fyi','フョ'=>'fyo',
+  'フュ'=>'fyu','ギャ'=>'gya','ギェ'=>'gye','ギィ'=>'gyi','ギョ'=>'gyo','ギュ'=>'gyu',
+  'ヒャ'=>'hya','ヒェ'=>'hye','ヒィ'=>'hyi','ヒョ'=>'hyo','ヒュ'=>'hyu','ジャ'=>'jya',
+  'ジェ'=>'jye','ジィ'=>'jyi','ジョ'=>'jyo','ジュ'=>'jyu','キャ'=>'kya','キェ'=>'kye',
+  'キィ'=>'kyi','キョ'=>'kyo','キュ'=>'kyu','リャ'=>'lya','リェ'=>'lye','リィ'=>'lyi',
+  'リョ'=>'lyo','リュ'=>'lyu','ミャ'=>'mya','ミェ'=>'mye','ミィ'=>'myi','ミョ'=>'myo',
+  'ミュ'=>'myu','ン'=>'n','ニャ'=>'nya','ニェ'=>'nye','ニィ'=>'nyi','ニョ'=>'nyo',
+  'ニュ'=>'nyu','ピャ'=>'pya','ピェ'=>'pye','ピィ'=>'pyi','ピョ'=>'pyo','ピュ'=>'pyu',
+  'リャ'=>'rya','リェ'=>'rye','リィ'=>'ryi','リョ'=>'ryo','リュ'=>'ryu','シャ'=>'sha',
+  'シェ'=>'she','シ'=>'shi','ショ'=>'sho','シュ'=>'shu','スァ'=>'swa','スェ'=>'swe',
+  'スィ'=>'swi','スォ'=>'swo','スゥ'=>'swu','シャ'=>'sya','シェ'=>'sye','シィ'=>'syi',
+  'ショ'=>'syo','シュ'=>'syu','テャ'=>'tha','テェ'=>'the','ティ'=>'thi','テョ'=>'tho',
+  'テュ'=>'thu','ツャ'=>'tsa','ツェ'=>'tse','ツィ'=>'tsi','ツョ'=>'tso','ツ'=>'tsu',
+  'トァ'=>'twa','トェ'=>'twe','トィ'=>'twi','トォ'=>'two','トゥ'=>'twu','チャ'=>'tya',
+  'チェ'=>'tye','チィ'=>'tyi','チョ'=>'tyo','チュ'=>'tyu','ヴャ'=>'vya','ヴェ'=>'vye',
+  'ヴィ'=>'vyi','ヴョ'=>'vyo','ヴュ'=>'vyu','ウァ'=>'wha','ウェ'=>'whe','ウィ'=>'whi',
+  'ウォ'=>'who','ウゥ'=>'whu','ヱ'=>'wye','ヰ'=>'wyi','ジャ'=>'zha','ジェ'=>'zhe',
+  'ジィ'=>'zhi','ジョ'=>'zho','ジュ'=>'zhu','ジャ'=>'zya','ジェ'=>'zye','ジィ'=>'zyi',
+  'ジョ'=>'zyo','ジュ'=>'zyu',
+  
+  // "Greeklish"
+  'Γ'=>'G','Δ'=>'E','Θ'=>'Th','Λ'=>'L','Ξ'=>'X','Π'=>'P','Σ'=>'S','Φ'=>'F','Ψ'=>'Ps',
+  'γ'=>'g','δ'=>'e','θ'=>'th','λ'=>'l','ξ'=>'x','π'=>'p','σ'=>'s','φ'=>'f','ψ'=>'ps',
+
+  // Thai
+  'ก'=>'k','ข'=>'kh','ฃ'=>'kh','ค'=>'kh','ฅ'=>'kh','ฆ'=>'kh','ง'=>'ng','จ'=>'ch',
+  'ฉ'=>'ch','ช'=>'ch','ซ'=>'s','ฌ'=>'ch','ญ'=>'y','ฎ'=>'d','ฏ'=>'t','ฐ'=>'th',
+  'ฑ'=>'d','ฒ'=>'th','ณ'=>'n','ด'=>'d','ต'=>'t','ถ'=>'th','ท'=>'th','ธ'=>'th',
+  'น'=>'n','บ'=>'b','ป'=>'p','ผ'=>'ph','ฝ'=>'f','พ'=>'ph','ฟ'=>'f','ภ'=>'ph',
+  'ม'=>'m','ย'=>'y','ร'=>'r','ฤ'=>'rue','ฤๅ'=>'rue','ล'=>'l','ฦ'=>'lue',
+  'ฦๅ'=>'lue','ว'=>'w','ศ'=>'s','ษ'=>'s','ส'=>'s','ห'=>'h','ฬ'=>'l','ฮ'=>'h',
+  'ะ'=>'a','–ั'=>'a','รร'=>'a','า'=>'a','รร'=>'an','ำ'=>'am','–ิ'=>'i','–ี'=>'i',
+  '–ึ'=>'ue','–ื'=>'ue','–ุ'=>'u','–ู'=>'u','เะ'=>'e','เ–็'=>'e','เ'=>'e','แะ'=>'ae',
+  'แ'=>'ae','โะ'=>'o','โ'=>'o','เาะ'=>'o','อ'=>'o','เอะ'=>'oe','เ–ิ'=>'oe',
+  'เอ'=>'oe','เ–ียะ'=>'ia','เ–ีย'=>'ia','เ–ือะ'=>'uea','เ–ือ'=>'uea','–ัวะ'=>'ua',
+  '–ัว'=>'ua','ว'=>'ua','ใ'=>'ai','ไ'=>'ai','–ัย'=>'ai','ไย'=>'ai','าย'=>'ai',
+  'เา'=>'ao','าว'=>'ao','–ุย'=>'ui','โย'=>'oi','อย'=>'oi','เย'=>'oei','เ–ือย'=>'ueai',
+  'วย'=>'uai','–ิว'=>'io','เ–็ว'=>'eo','เว'=>'eo','แ–็ว'=>'aeo','แว'=>'aeo',
+  'เ–ียว'=>'iao',
+
+  // Korean
+  'ㄱ'=>'k','ㅋ'=>'kh','ㄲ'=>'kk','ㄷ'=>'t','ㅌ'=>'th','ㄸ'=>'tt','ㅂ'=>'p',
+  'ㅍ'=>'ph','ㅃ'=>'pp','ㅈ'=>'c','ㅊ'=>'ch','ㅉ'=>'cc','ㅅ'=>'s','ㅆ'=>'ss',
+  'ㅎ'=>'h','ㅇ'=>'ng','ㄴ'=>'n','ㄹ'=>'l','ㅁ'=>'m', 'ㅏ'=>'a','ㅓ'=>'e','ㅗ'=>'o',
+  'ㅜ'=>'wu','ㅡ'=>'u','ㅣ'=>'i','ㅐ'=>'ay','ㅔ'=>'ey','ㅚ'=>'oy','ㅘ'=>'wa','ㅝ'=>'we',
+  'ㅟ'=>'wi','ㅙ'=>'way','ㅞ'=>'wey','ㅢ'=>'uy','ㅑ'=>'ya','ㅕ'=>'ye','ㅛ'=>'oy',
+  'ㅠ'=>'yu','ㅒ'=>'yay','ㅖ'=>'yey',
+);
 
 //Setup VIM: ex: et ts=2 enc=utf-8 :
+