You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucenenet.apache.org by di...@apache.org on 2009/11/08 14:36:43 UTC
svn commit: r833874 [2/3] - in /incubator/lucene.net/trunk/C#/src:
Lucene.Net/Analysis/ Lucene.Net/Analysis/Tokenattributes/ Lucene.Net/Util/
Test/Analysis/ Test/Analysis/Tokenattributes/
Modified: incubator/lucene.net/trunk/C#/src/Test/Analysis/TestASCIIFoldingFilter.cs
URL: http://svn.apache.org/viewvc/incubator/lucene.net/trunk/C%23/src/Test/Analysis/TestASCIIFoldingFilter.cs?rev=833874&r1=833873&r2=833874&view=diff
==============================================================================
--- incubator/lucene.net/trunk/C#/src/Test/Analysis/TestASCIIFoldingFilter.cs (original)
+++ incubator/lucene.net/trunk/C#/src/Test/Analysis/TestASCIIFoldingFilter.cs Sun Nov 8 13:36:42 2009
@@ -32,7 +32,11 @@
[Test]
public virtual void TestLatin1Accents()
{
- TokenStream stream = new WhitespaceTokenizer(new System.IO.StringReader("Des mot clés Ã⬠LA CHAÃŽNE Ã⬠�? Ãâ ÃÆ Ãâ Ã⦠Ãâ Ãâ¡ ÃË Ãâ° ÃÅ Ã⹠Ê�? ÃŽ �? ò �? Ãâ" + " Ãâ Ãâ Ãâ Ã⢠Ãâ ÃË Ã
â Þ Ã⢠ÃÅ¡ Ã⺠�? Ã
¸ àá â ã ä ÃÂ¥ æ ç è é ê ë ì àî ï ó" + " ð ñ ò ó ô õ ö ø Ã
â ß þ ù ú û ü ý ÿ �? ï¬â"));
+ TokenStream stream = new WhitespaceTokenizer(new System.IO.StringReader(
+ "Des mot clés à LA CHAÃNE à à à à à Ã
à à à à à à à à à à IJ à Ã" +
+ " à à à à à à Šà à à à à à Ÿ à á â ã ä å æ ç è é ê ë ì à î ï ij" +
+ " ð ñ ò ó ô õ ö ø Šà þ ù ú û ü ý ÿ ï¬ ï¬")
+ );
ASCIIFoldingFilter filter = new ASCIIFoldingFilter(stream);
TermAttribute termAtt = (TermAttribute) filter.GetAttribute(typeof(TermAttribute));
@@ -171,12 +175,1708 @@
// single string.
// 2. The string of ASCII characters to which each of the above
// characters should be folded.
- System.String[] foldings = new System.String[]{"Ãâ¬" + "�?" + "Ãâ" + "ÃÆ" + "Ãâ" + "Ãâ¦" + "Ãâ¬" + "Ãâ" + "Ãâ" + "�?" + "�?" + "Þ" + "à" + "ú" + "Ãâ¬" + "Ãâ" + "æ" + "ú" + "á´â¬" + "á¸â¬" + "Ạ" + "Ả" + "Ấ" + "Ầ" + "Ẩ" + "Ẫ" + "Ậ" + "Ắ" + "Ằ" + "Ẳ" + "Ẵ" + "Ặ" + "ââ¶" + "A", "A", "à" + "á" + "â" + "ã" + "ä" + "ÃÂ¥" + "�?" + "ÃÆ" + "Ãâ¦" + "ÃŽ" + "ß" + "á" + "û" + "�?" + "ÃÆ" + "ç" + "�?" + "Ãâ¢" + "ÃÅ¡" + "�?" + "�?" + "á¶â¢" + "ẚ" + "ạ" + "ả" + "ấ" + "
ầ" + "ẩ" + "ẫ" + "áºÂ" + "ắ" + "ằ" + "ẳ" + "ẵ" + "ặ" + "�?" + "âââ" + "�?" + "â±¥" + "Ɐ" + "�?", "a", "êŲ", "AA", "Ãâ " + "â" + "ü" + "�?", "AE", "êÅ´", "AO", "êŶ", "AU", "êŸ" + "êź", "AV", "êż", "AY", "ââÅ", "(a)", "êų", "aa", "æ" + "ã" + "ý" + "á´â", "ae", "êŵ", "ao", "êÅ·", "au", "êŹ" + "êÅ»", "av", "êŽ", "ay", "�?" + "Ãâ" + "ÃÆ" + "Ãâ¢" + "á´Æ" + "á¸â" + "á¸â" + "á¸â " + "ââ·" + "ï¼¢", "B", "Ãâ¬" + "ÃÆ" + "Ãâ" + "ᵬ" + "á¶â¬" + "á¸Æ" + "á¸â¦" + "á¸â¡" + "ââ
â" + "ï½â", "b", "�?", "(b)", "Ãâ¡" + "Ãâ " + "ÃË" + "ÃÅ " + "ÃÅ" + "Ãâ¡" + "û" + "Ãâ" + "á´â" + "á¸Ë" + "ââ¸" + "ï¼£", "C", "ç" + "Ãâ¡" + "Ãâ°" + "Ãâ¹" + "�?" + "ÃË" + "ü" + "Ãâ¢" + "á¸â°" + "ââ â" + "âââ" + "êž" + "êÅ¿" + "ï½Æ", "c", "ââž", "(c)", "�?" + "ÃŽ" + "�?" + "Ãâ°" + "ÃÅ " + "Ãâ¹" + "á´â¦" + "á´â " + "Ḋ" + "á¸Å" + "Ḏ" + "�?" + "á¸â" + "ââ¹" + "�?�" + "D", "D", "ð" + "�?" + "Ãâ" + "ÃÅ" + "á" + "Ãâ" + "Ãâ" + "áµÂ" + "�?" + "á¶â" + "á¸â¹" + "�?" + "Ã
¯Â¿Â½?" + "á¸â" + "á¸â" + "âââ" + "�?�" + "ï½â", "d", "Ãâ" + "ñ", "DZ", "Ãâ¦" + "ò", "Dz", "ââŸ", "(d)", "ø", "db", "Ãâ " + "ó" + "ã" + "ÃÂ¥", "dz", "ÃË" + "Ãâ°" + "ÃÅ " + "Ãâ¹" + "Ãâ" + "Ãâ" + "Ãâ" + "ÃË" + "ÃÅ¡" + "ÃŽ" + "�?" + "Ãâ" + "Ãâ " + "è" + "Ãâ " + "á´â¡" + "á¸â" + "á¸â" + "á¸Ë" + "Ḛ" + "á¸Å" + "Ẹ" + "Ẻ" + "Ẽ" + "Ế" + "á»â¬" + "á»â" + "á»â" + "á»â " + "ââº" + "â±»" + "ï¼¥", "E", "è" + "é" + "ê" + "ë" + "Ãâ" + "Ãâ¢" + "Ãâ" + "Ãâ¢" + "Ãâº" + "�?" + "Ãâ¦" + "Ãâ
¡" + "é" + "Ãâ¡" + "ÃË" + "Ãâº" + "ÃÅ" + "�?" + "Þ" + "ÃÅ¡" +
- "á´Ë" + "á¶â" + "á¶â" + "á¶â" + "á¸â¢" + "á¸â" + "á¸â¢" + "á¸âº" + "�?" + "ẹ" + "ẻ" + "ẽ" + "ế" + "�?" + "á»Æ" + "á»â¦" + "á»â¡" + "âââ" + "âââ" + "ⱸ" + "ï½â¦", "e", "ââ ", "(e)", "Ãâ" + "Ḟ" + "ââ»" + "êÅ°" + "�?�" + "ꟻ" + "F", "F", "Ãâ" + "áµ®" + "á¶â" + "ḟ" + "áºâº" + "âââ¢" + "�?�" + "ï½â ", "f", "ââ¡", "(f)", "ï¬â¬", "ff", "ï¬Æ", "ffi", "ï¬â", "ffl", "�?", "fi", "ï¬â", "fl", "ÃÅ" + "Þ" + "à" + "â" + "Ãâ" + "ä" + "ÃÂ¥" + "æ" + "ç" + "ô
" + "â" + "Ãâº" + "Ḡ" + "ââ¼" + "�?�" + "�?�" + "G", "G", "�?" + "ß" + "á" + "ã" + "õ" + "à" + "á" + "áµ·" + "áµ¹" + "á¶Æ" + "ḡ" + "âââ" + "�?�" + "ï½â¡", "g", "ââ¢", "(g)", "ä" + "æ" + "Þ" + "ÃÅ" + "Ḣ" + "Ḥ" + "Ḧ" + "Ḩ" + "Ḫ" + "ââ½" + "Ⱨ" + "â±µ" + "H", "H", "ÃÂ¥" + "ç" + "ß" + "ÃÂ¥" + "æ" + "î" + "ï" + "ḣ" + "ḥ" + "ḧ" + "ḩ" + "ḫ" + "áºâ" + "âââ" + "ⱨ" + "ⱶ" + "ï½Ë", "h", "ö", "HV", "ââ£", "(h)", "Ãâ¢", "hv", "ÃÅ" + "�?" + "
ÃŽ" + "�?" + "è" + "ê" + "ì" + "î" + "ð" + "Ãâ" + "Ãâ" + "�?" + "ÃË" + "ÃÅ " + "ê" + "áµ»" + "Ḭ" + "Ḯ" + "á»Ë" + "Ị" + "ââ¾" + "ꟾ" + "I", "I", "ì" + "ÃÂ" + "î" + "ï" + "é" + "ë" + "ÃÂ" + "ï" + "ñ" + "�?" + "Ãâ°" + "Ãâ¹" + "è" + "á´â°" + "áµ¢" + "áµ¼" + "á¶â" + "á¸Â" + "ḯ" + "á»â°" + "á»â¹" + "�?�" + "ââË" + "ï½â°", "i", "ò", "IJ", "ââ¤", "(i)", "ó", "ij", "ô" + "ÃË" + "á´Š" + "ââ¿" + "J", "J", "õ" + "ð" + "÷" + "Ãâ°" + "ß" + "Ãâ" + "�?" + "âââ¢" + "â�
�±Â¼" + "j", "j", "ââÂ¥", "(j)", "ö" + "ÃË" + "è" + "á´â¹" + "Ḱ" + "Ḳ" + "Ḵ" + "âââ¬" + "Ⱪ" + "�?�" + "�?�" + "�?�" + "K", "K", "÷" + "Ãâ¢" + "é" + "Þ" + "á¶â" + "ḱ" + "ḳ" + "ḵ" + "ââÅ¡" + "ⱪ" + "�??" + "�?�" + "�?�" + "ï½â¹", "k", "ââ¦", "(k)", "ù" + "û" + "ý" + "ÿ" + "�?" + "ý" + "ß" + "á´Å" + "Ḷ" + "Ḹ" + "Ḻ" + "Ḽ" + "�?" + "â± " + "â±¢" + "�?�" + "�?�" + "êžâ¬" + "L", "L", "ú" + "ü" + "þ" + "Ã
â¬" +
"Ã
â" + "ÃÅ¡" + "ô" + "ë" + "ì" + "ÃÂ" + "á¶â¦" + "ḷ" + "ḹ" + "ḻ" + "ḽ" + "âââº" + "ⱡ" +
- "�?�" + "�?�" + "�?" + "ï½Å", "l", "Ãâ¡", "LJ", "Ỻ", "LL", "ÃË", "Lj", "ââ§", "(l)", "Ãâ°", "lj", "á»»", "ll", "ê", "ls", "ë", "lz", "ÃÅ" + "�?" + "Ḿ" + "á¹â¬" + "á¹â" + "âââ" + "â±®" + "ꟽ" + "ꟿ" + "ï¼Â", "M", "ï" + "ð" + "ñ" + "ᵯ" + "á¶â " + "ḿ" + "�?" + "á¹Æ" + "ââÅ" + "�?", "m", "ââ¨", "(m)", "Ãâ" + "Ã
Æ" + "Ã
â¦" + "Ã
â¡" + "Ã
Å " + "�?" + "ø" + "à" + "ô" + "á´Ž" + "á¹â" + "á¹â " + "á¹Ë" + "Ṋ" + "ââÆ" + "ï¼®", "N", "ñ" + "Ã
â" + "Ã
â " + "Ã
Ë" + "Ã
â°" + "Ã
â¹" + "ÃÅ�
�" + "ù" + "õ" + "ò" + "ó" + "áµ°" + "á¶â¡" + "á¹â¦" + "á¹â¡" + "á¹â°" + "á¹â¹" + "�?�" + "�?" + "n", "n", "ÃÅ ", "NJ", "Ãâ¹", "Nj", "ââ©", "(n)", "ÃÅ", "nj", "Ãâ" + "Ãâ" + "Ãâ" + "Ãâ¢" + "Ãâ" + "ÃË" + "Ã
Å" + "Ã
Ž" + "�?" + "Ãâ " + "ß" + "à" + "Ãâ" + "ê" + "ì" + "þ" + "ÃÅ" + "ÃŽ" + "ê" + "ì" + "î" + "ð" + "�?" + "�?" + "á¹Å" + "Ṏ" + "�?" + "á¹â" + "á»Å" + "Ỏ" + "�?" + "á»â" + "á»â" + "á»â" + "á»Ë" + "Ớ" + "á»Å" + "Ở" + "á» " + "Ợ" + "âââ" + "�?�
" + "�?�" + "O", "O", "ò" + "ó" + "ô" + "õ" + "ö" + "ø" + "�?" + "�?" + "Ã
â" + "á" + "Ãâ" + "ë" + "ÃÂ" + "ÿ" + "�?" + "�?" + "ë" + "ÃÂ" + "ï" + "ñ" + "Ãâ" + "õ" + "á´â" + "á´â" + "á¶â" + "�?" + "�?" + "á¹â" + "á¹â" + "�?" + "�?" + "á»â" + "á»â" + "á»â¢" + "á»â" + "á»â¢" + "á»âº" + "�?" + "ở" + "ỡ" + "ợ" + "âââ" + "ââž" + "ⱺ" + "�?�" + "�??" + "�?", "o", "Ã
â" + "ö", "OE", "�?�", "OO", "â" + "á´â¢", "OU", "ââª", "(o)", "Ã
â" +
"á´â", "oe", "�??", "oo", "ã", "ou", "ä" + "á´Ë" + "á¹â" + "á¹â" + "âââ¦" + "â±£" + "�??" + "�?�" + "�?�" + "ï¼°", "P", "ÃÂ¥" + "áµ±" + "áµ½" + "á¶Ë" + "á¹â¢" + "á¹â" + "ââŸ" + "�?�" + "�?�" + "�?�" + "ꟼ" + "�?", "p", "ââ«", "(p)", "ÃÅ " + "âââ " + "�?�" + "�?�" + "ï¼±", "Q", "ø" + "Ãâ¹" + "à" + "ââ " + "�?�" + "�?�" + "ï½â", "q", "ââ¬", "(q)", "ù", "qp", "Ã
â" + "Ã
â" + "Ã
Ë" + "�?" + "Ãâ" + "ÃÅ" + "Ãâ¬" + "�?" + "á´â¢" +
"á´š" + "á¹Ë" + "Ṛ" + "á¹Å" + "Ṟ" + "âââ¡" + "Ɽ" + "�?�" + "êžâ" + "ï¼²", "R", "Ã
â¢" +
- "Ã
â" + "Ã
â¢" + "Ãâ" + "Ãâ" + "�?" + "ü" + "ý" + "þ" + "ÿ" + "áµ£" + "áµ²" + "áµ³" + "á¶â°" + "á¹â¢" + "á¹âº" + "�?" + "ṟ" + "ââ¡" + "�?�" + "êžÆ" + "ï½â", "r", "ââÂ", "(r)", "Ã
Å¡" + "Ã
Å" + "Ã
ž" + "Ã
 " + "ÃË" + "á¹ " + "á¹¢" + "Ṥ" + "Ṧ" + "Ṩ" + "ââË" + "êű" + "êžâ¦" + "ï¼³", "S", "Ã
âº" + "�?" + "Ã
Ÿ" + "Ã
¡" + "Ã
¿" + "Ãâ¢" + "ÿ" + "Ãâ" + "áµ´" + "ᶊ" + "ṡ" + "á¹£" + "á¹¥" + "ṧ" + "ṩ" + "áºÅ" + "�?" + "ââ¢" + "êžâ" + "ï½â", "s", "ẞ", "SS", "ââ®", "(
s)", "ß", "ss", "ï¬â ", "st", "Ã
¢" + "Ã
¤" + "Ã
¦" + "ì" + "î" + "ÃÅ¡" + "þ" + "á´âº" + "Ṫ" + "Ṭ" + "á¹®" + "á¹°" + "âââ°" + "êžâ " + "ï¼´", "T", "Ã
£" + "Ã
Â¥" + "Ã
§" + "ë" + "ÃÂ" + "Ãâº" + "ö" + "Ãâ¡" + "ÃË" + "áµµ" + "ṫ" + "á¹Â" + "ṯ" + "á¹±" + "áºâ" + "ââ£" + "ⱦ" + "ï½â", "t", "Þ" + "�?�", "TH", "êŨ", "TZ", "ââ¯", "(t)", "è", "tc", "þ" + "ᵺ" + "�?�", "th", "æ", "ts", "êÅ©", "tz", "Ãâ¢" + "ÃÅ¡" + "Ãâº" + "ÃÅ" + "Ã
¨" + "Ã
ª" + "Ã
¬" + "Ã
®" + "Ã
°" + "Ã
²" + "ï" + "Ãâ" + "Ãâ¢" + "Ãâ" + "Ãâ
¢" + "Ãâº" + "Ãâ" + "Ãâ" + "Ãâ" + "á´Å" + "áµ¾" + "á¹²" + "á¹´" + "Ṷ" + "Ṹ" + "Ṻ" + "Ụ" + "Ủ" + "Ứ" + "Ừ" + "Ử" + "á»®" + "á»°" + "ââÅ " + "ï¼µ", "U", "ù" + "ú" + "û" + "ü" + "Ã
©" + "Ã
«" + "Ã
Â" + "Ã
¯" + "Ã
±" + "Ã
³" + "ð" + "Ãâ" + "Ãâ" + "ÃË" + "ÃÅ¡" + "ÃÅ" + "Ãâ¢" + "Ãâ" + "Ãâ°" + "ᵤ" + "á¶â¢" + "á¹³" + "á¹µ" + "á¹·" + "á¹¹" + "á¹»" + "ụ" + "ủ" + "ứ" + "ừ" + "á»Â" + "ữ" + "á»±" + "ââ¤" + "ï½â¢", "u", "ââ°", "(u)", "ᵫ", "ue", "ò" + "Ãâ¦" + "á´ " + "á¹¼"
+ "á¹¾" + "Ỽ" + "âââ¹" + "�?�" + "�?�" + "V", "V", "Ãâ¹" + "ÃÅ" + "áµ¥" + "á¶Å" + "á¹½" + "ṿ" + "ââÂ¥" + "â±±" + "â±´" + "�?�" + "ï½â", "v", "�?�", "VY", "ââ±", "(v)", "�?�", "vy", "Ã
´" + "÷" + "á´¡" + "áºâ¬" + "áºâ" + "áºâ" + "áºâ " + "áºË" + "ââÅ" + "â±²" + "ï¼·", "W", "Ã
µ" + "ÿ" + "�?" + "�?" + "áºÆ" + "áºâ¦" + "áºâ¡" + "áºâ°" + "áºË" + "ââ¦" + "â±³" + "ï½â", "w", "ââ²", "(w)", "Ẋ" + "áºÅ" + "�?" + "X", "X", "�?" + "áºâ¹" + "�
?" + "âââ" + "ââ§" + "ï½Ë", "x", "ââ³", "(x)", "�?" + "Ã
¶" + "Ã
¸" + "ó" + "ò" + "ÃŽ" +
- "�?" + "Ẏ" + "Ỳ" + "á»´" + "Ỷ" + "Ỹ" + "Ỿ" + "ââŽ" + "ï¼¹", "Y", "ý" + "ÿ" + "Ã
·" + "ô" + "ó" + "�?" + "ÃŽ" + "�?" + "áºâ¢" + "ỳ" + "ỵ" + "á»·" + "ỹ" + "ỿ" + "ââ¨" + "ï½â¢", "y", "ââ´", "(y)", "Ã
¹" + "Ã
»" + "Ã
½" + "õ" + "ÃÅ" + "ä" + "á´¢" + "�?" + "áºâ" + "áºâ" + "�?" + "Ⱬ" + "�?�" + "Z", "Z", "Ã
º" + "Ã
¼" + "Ã
¾" + "ö" + "�?" + "ÃÂ¥" + "Ãâ¬" + "�?" + "Ãâ" + "ᵶ" + "ᶎ" + "áºâ" + "áºâ" + "áºâ¢" + "ââ©" + "ⱬ" + "�?�" + "z",
"z", "ââµ", "(z)", "�?�" + "âââ¬" + "ââª" + "ââ¿" + "�?", "0", "ù" + "�?" + "ââ " + "ââµ" + "�?�" + "âžâ¬" + "➊" + "ï¼â", "1", "ââË", "1.", "ââ´", "(1)", "ò" + "âââ" + "ââ¡" + "ââ¶" + "�?�" + "�?" + "âžâ¹" + "ï¼â", "2", "âââ°", "2.", "ââµ", "(2)", "ó" + "ââÆ" + "ââ¢" + "ââ·" + "�?�" + "âžâ" + "âžÅ" + "ï¼â", "3", "ââÅ ", "3.", "ââ¶", "(3)", "�?�" + "âââ" + "ââ£" + "ââ¸" + "�?�" + "âžÆ" + "�?" + "ï¼â", "4", "âââ¹", "4.", "ââ·"
, "(4)", "�?�" + "âââ¦" + "ââ¤" + "ââ¹" + "�?�" + "âžâ" + "➎" + "ï¼â¢", "5", "ââÅ", "5.", "ââ¸", "(5)", "�?�" + "âââ " + "ââÂ¥" + "ââº" + "�?�" + "âžâ¦" + "�?" + "ï¼â", "6", "�?", "6.", "ââ¹", "(6)", "�?�" + "âââ¡" + "ââ¦" + "ââ»" + "�?�" + "âžâ " + "�?" + "ï¼â", "7", "ââŽ", "7.", "ââº", "(7)", "�?�" + "ââË" + "ââ§" + "ââ¼" + "�?�" + "âžâ¡" + "âžâ" + "ï¼Ë", "8", "�?", "8.", "ââ»", "(8)", "�?�" + "âââ°" + "ââ¨" + "Ã�
�â½" + "�?�" + "âžË" + "âžâ" + "ï¼â¢", "9", "�?", "9.", "ââ¼", "(9)", "ââ©" + "ââ¾" + "�?�" + "âžâ°" + "âžâ", "10", "âââ", "10.", "ââ½", "(10)", "ââª" + "ââ«", "11", "âââ", "11.", "ââ¾", "(11)", "ââ«" + "ââ¬", "12", "âââ", "12.", "ââ¿", "(12)", "ââ¬" + "ââÂ", "13", "âââ", "13.", "âââ¬", "(13)", "ââÂ" + "ââ®", "14", "âââ¢", "14.", "�?", "(14)", "ââ®" + "ââ¯", "15", "âââ", "15.", "âââ", "(15)", "ââ¯" + "ââ°", "16", "âââ", "16.", "ââÆ", "(16)", "ââ°" + "ââ±", "17", "ââË", "17.", "âââ", "(17)"
, "ââ±" + "ââ²", "18", "âââ¢", "18.", "âââ¦", "(18)", "ââ²" + "ââ³", "19", "ââÅ¡", "19.", "âââ ", "(19)", "ââ³" + "ââ´", "20", "âââº",
- "20.", "âââ¡", "(20)", "ë" + "û" + "ââ¬Å" + "�?" + "ââ¬Å¾" + "ââ¬Â³" + "ââ¬Â¶" + "�??" + "�?�" + "�?�" + "�?�" + "ï¼â", "\"", "ââ¬Ë" + "ââ¬â¢" + "ââ¬Å¡" + "ââ¬âº" + "ââ¬Â²" + "ââ¬Âµ" + "ââ¬Â¹" + "ââ¬Âº" + "�?�" + "�?�" + "ï¼â¡", "'", "�?" + "ââ¬â" + "ââ¬â" + "ââ¬â" + "ââ¬â" + "�?�" + "âââ¹" + "�?", "-", "�?�" + "�?�" + "ï¼»", "[", "�?�" + "�?�" + "ï¼½", "]", "�?�" + "�?" + "�?�" + "�?�" + "ï¼Ë
", "(", "⸨", "((", "�?�" + "ââŽ" + "�?�" + "�?�" + "ï¼â°", ")", "⸩", "))", "�?�" + "�?�" + "ï¼Å", "<", "�?�" + "�?�" + ">", ">", "�?�" + "ï½âº", "{", "�?�" + "�?", "}", "�?�" + "ââÅ " + "ï¼â¹", "+", "�?�" + "ââÅ" + "�?", "=", "�?", "!", "ââ¬Â¼", "!!", "�?�", "!?", "ï¼Æ", "#", "ï¼â", "$", "�?�" + "ï¼â¦", "%", "ï¼â ", "&", "�?�" + "*", "*", "ï¼Å", ",", ".", ".", "�?�" + "�?", "/", ":", ":", "�??" + "ï¼
âº", ";", "?", "?", "�?�", "??", "�?�", "?!", "ï¼ ", "@", "ï¼¼", "\\", "ââ¬Â¸" + "ï¼¾", "^", "_", "_", "�?�" + "~", "~"};
+ System.String[] foldings = new System.String[]
+ {
+ "Ã" // U+00C0: LATIN CAPITAL LETTER A WITH GRAVE
+ + "Ã" // U+00C1: LATIN CAPITAL LETTER A WITH ACUTE
+ + "Ã" // U+00C2: LATIN CAPITAL LETTER A WITH CIRCUMFLEX
+ + "Ã" // U+00C3: LATIN CAPITAL LETTER A WITH TILDE
+ + "Ã" // U+00C4: LATIN CAPITAL LETTER A WITH DIAERESIS
+ + "Ã
" // U+00C5: LATIN CAPITAL LETTER A WITH RING ABOVE
+ + "Ä" // U+0100: LATIN CAPITAL LETTER A WITH MACRON
+ + "Ä" // U+0102: LATIN CAPITAL LETTER A WITH BREVE
+ + "Ä" // U+0104: LATIN CAPITAL LETTER A WITH OGONEK
+ + "Æ" // U+018F: LATIN CAPITAL LETTER SCHWA
+ + "Ç" // U+01CD: LATIN CAPITAL LETTER A WITH CARON
+ + "Ç" // U+01DE: LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON
+ + "Ç " // U+01E0: LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON
+ + "Ǻ" // U+01FA: LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE
+ + "È" // U+0200: LATIN CAPITAL LETTER A WITH DOUBLE GRAVE
+ + "È" // U+0202: LATIN CAPITAL LETTER A WITH INVERTED BREVE
+ + "Ȧ" // U+0226: LATIN CAPITAL LETTER A WITH DOT ABOVE
+ + "Ⱥ" // U+023A: LATIN CAPITAL LETTER A WITH STROKE
+ + "á´" // U+1D00: LATIN LETTER SMALL CAPITAL A
+ + "á¸" // U+1E00: LATIN CAPITAL LETTER A WITH RING BELOW
+ + "Ạ" // U+1EA0: LATIN CAPITAL LETTER A WITH DOT BELOW
+ + "Ả" // U+1EA2: LATIN CAPITAL LETTER A WITH HOOK ABOVE
+ + "Ấ" // U+1EA4: LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE
+ + "Ầ" // U+1EA6: LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE
+ + "Ẩ" // U+1EA8: LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE
+ + "Ẫ" // U+1EAA: LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE
+ + "Ậ" // U+1EAC: LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW
+ + "Ắ" // U+1EAE: LATIN CAPITAL LETTER A WITH BREVE AND ACUTE
+ + "Ằ" // U+1EB0: LATIN CAPITAL LETTER A WITH BREVE AND GRAVE
+ + "Ẳ" // U+1EB2: LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE
+ + "Ẵ" // U+1EB4: LATIN CAPITAL LETTER A WITH BREVE AND TILDE
+ + "Ặ" // U+1EB6: LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW
+ + "â¶" // U+24B6: CIRCLED LATIN CAPITAL LETTER A
+ + "A" // U+FF21: FULLWIDTH LATIN CAPITAL LETTER A
+ ,"A", // Folded result
+
+ "Ã " // U+00E0: LATIN SMALL LETTER A WITH GRAVE
+ + "á" // U+00E1: LATIN SMALL LETTER A WITH ACUTE
+ + "â" // U+00E2: LATIN SMALL LETTER A WITH CIRCUMFLEX
+ + "ã" // U+00E3: LATIN SMALL LETTER A WITH TILDE
+ + "ä" // U+00E4: LATIN SMALL LETTER A WITH DIAERESIS
+ + "Ã¥" // U+00E5: LATIN SMALL LETTER A WITH RING ABOVE
+ + "Ä" // U+0101: LATIN SMALL LETTER A WITH MACRON
+ + "Ä" // U+0103: LATIN SMALL LETTER A WITH BREVE
+ + "Ä
" // U+0105: LATIN SMALL LETTER A WITH OGONEK
+ + "Ç" // U+01CE: LATIN SMALL LETTER A WITH CARON
+ + "Ç" // U+01DF: LATIN SMALL LETTER A WITH DIAERESIS AND MACRON
+ + "Ç¡" // U+01E1: LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON
+ + "Ç»" // U+01FB: LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE
+ + "È" // U+0201: LATIN SMALL LETTER A WITH DOUBLE GRAVE
+ + "È" // U+0203: LATIN SMALL LETTER A WITH INVERTED BREVE
+ + "ȧ" // U+0227: LATIN SMALL LETTER A WITH DOT ABOVE
+ + "É" // U+0250: LATIN SMALL LETTER TURNED A
+ + "É" // U+0259: LATIN SMALL LETTER SCHWA
+ + "É" // U+025A: LATIN SMALL LETTER SCHWA WITH HOOK
+ + "á¶" // U+1D8F: LATIN SMALL LETTER A WITH RETROFLEX HOOK
+ + "á¸" // U+1E01: LATIN SMALL LETTER A WITH RING BELOW
+ + "á¶" // U+1D95: LATIN SMALL LETTER SCHWA WITH RETROFLEX HOOK
+ + "áº" // U+1E9A: LATIN SMALL LETTER A WITH RIGHT HALF RING
+ + "ạ" // U+1EA1: LATIN SMALL LETTER A WITH DOT BELOW
+ + "ả" // U+1EA3: LATIN SMALL LETTER A WITH HOOK ABOVE
+ + "ấ" // U+1EA5: LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE
+ + "ầ" // U+1EA7: LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE
+ + "ẩ" // U+1EA9: LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE
+ + "ẫ" // U+1EAB: LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE
+ + "áº" // U+1EAD: LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW
+ + "ắ" // U+1EAF: LATIN SMALL LETTER A WITH BREVE AND ACUTE
+ + "ằ" // U+1EB1: LATIN SMALL LETTER A WITH BREVE AND GRAVE
+ + "ẳ" // U+1EB3: LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE
+ + "ẵ" // U+1EB5: LATIN SMALL LETTER A WITH BREVE AND TILDE
+ + "ặ" // U+1EB7: LATIN SMALL LETTER A WITH BREVE AND DOT BELOW
+ + "â" // U+2090: LATIN SUBSCRIPT SMALL LETTER A
+ + "â" // U+2094: LATIN SUBSCRIPT SMALL LETTER SCHWA
+ + "â" // U+24D0: CIRCLED LATIN SMALL LETTER A
+ + "â±¥" // U+2C65: LATIN SMALL LETTER A WITH STROKE
+ + "Ɐ" // U+2C6F: LATIN CAPITAL LETTER TURNED A
+ + "ï½" // U+FF41: FULLWIDTH LATIN SMALL LETTER A
+ ,"a", // Folded result
+
+ "ê²" // U+A732: LATIN CAPITAL LETTER AA
+ ,"AA", // Folded result
+
+ "Ã" // U+00C6: LATIN CAPITAL LETTER AE
+ + "Ç¢" // U+01E2: LATIN CAPITAL LETTER AE WITH MACRON
+ + "Ǽ" // U+01FC: LATIN CAPITAL LETTER AE WITH ACUTE
+ + "á´" // U+1D01: LATIN LETTER SMALL CAPITAL AE
+ ,"AE", // Folded result
+
+ "ê´" // U+A734: LATIN CAPITAL LETTER AO
+ ,"AO", // Folded result
+
+ "ê¶" // U+A736: LATIN CAPITAL LETTER AU
+ ,"AU", // Folded result
+
+ "ê¸" // U+A738: LATIN CAPITAL LETTER AV
+ + "êº" // U+A73A: LATIN CAPITAL LETTER AV WITH HORIZONTAL BAR
+ ,"AV", // Folded result
+
+ "ê¼" // U+A73C: LATIN CAPITAL LETTER AY
+ ,"AY", // Folded result
+
+ "â" // U+249C: PARENTHESIZED LATIN SMALL LETTER A
+ ,"(a)", // Folded result
+
+ "ê³" // U+A733: LATIN SMALL LETTER AA
+ ,"aa", // Folded result
+
+ "æ" // U+00E6: LATIN SMALL LETTER AE
+ + "Ç£" // U+01E3: LATIN SMALL LETTER AE WITH MACRON
+ + "ǽ" // U+01FD: LATIN SMALL LETTER AE WITH ACUTE
+ + "á´" // U+1D02: LATIN SMALL LETTER TURNED AE
+ ,"ae", // Folded result
+
+ "êµ" // U+A735: LATIN SMALL LETTER AO
+ ,"ao", // Folded result
+
+ "ê·" // U+A737: LATIN SMALL LETTER AU
+ ,"au", // Folded result
+
+ "ê¹" // U+A739: LATIN SMALL LETTER AV
+ + "ê»" // U+A73B: LATIN SMALL LETTER AV WITH HORIZONTAL BAR
+ ,"av", // Folded result
+
+ "ê½" // U+A73D: LATIN SMALL LETTER AY
+ ,"ay", // Folded result
+
+ "Æ" // U+0181: LATIN CAPITAL LETTER B WITH HOOK
+ + "Æ" // U+0182: LATIN CAPITAL LETTER B WITH TOPBAR
+ + "É" // U+0243: LATIN CAPITAL LETTER B WITH STROKE
+ + "Ê" // U+0299: LATIN LETTER SMALL CAPITAL B
+ + "á´" // U+1D03: LATIN LETTER SMALL CAPITAL BARRED B
+ + "á¸" // U+1E02: LATIN CAPITAL LETTER B WITH DOT ABOVE
+ + "á¸" // U+1E04: LATIN CAPITAL LETTER B WITH DOT BELOW
+ + "á¸" // U+1E06: LATIN CAPITAL LETTER B WITH LINE BELOW
+ + "â·" // U+24B7: CIRCLED LATIN CAPITAL LETTER B
+ + "ï¼¢" // U+FF22: FULLWIDTH LATIN CAPITAL LETTER B
+ ,"B", // Folded result
+
+ "Æ" // U+0180: LATIN SMALL LETTER B WITH STROKE
+ + "Æ" // U+0183: LATIN SMALL LETTER B WITH TOPBAR
+ + "É" // U+0253: LATIN SMALL LETTER B WITH HOOK
+ + "ᵬ" // U+1D6C: LATIN SMALL LETTER B WITH MIDDLE TILDE
+ + "á¶" // U+1D80: LATIN SMALL LETTER B WITH PALATAL HOOK
+ + "á¸" // U+1E03: LATIN SMALL LETTER B WITH DOT ABOVE
+ + "á¸
" // U+1E05: LATIN SMALL LETTER B WITH DOT BELOW
+ + "á¸" // U+1E07: LATIN SMALL LETTER B WITH LINE BELOW
+ + "â" // U+24D1: CIRCLED LATIN SMALL LETTER B
+ + "ï½" // U+FF42: FULLWIDTH LATIN SMALL LETTER B
+ ,"b", // Folded result
+
+ "â" // U+249D: PARENTHESIZED LATIN SMALL LETTER B
+ ,"(b)", // Folded result
+
+ "Ã" // U+00C7: LATIN CAPITAL LETTER C WITH CEDILLA
+ + "Ä" // U+0106: LATIN CAPITAL LETTER C WITH ACUTE
+ + "Ä" // U+0108: LATIN CAPITAL LETTER C WITH CIRCUMFLEX
+ + "Ä" // U+010A: LATIN CAPITAL LETTER C WITH DOT ABOVE
+ + "Ä" // U+010C: LATIN CAPITAL LETTER C WITH CARON
+ + "Æ" // U+0187: LATIN CAPITAL LETTER C WITH HOOK
+ + "È»" // U+023B: LATIN CAPITAL LETTER C WITH STROKE
+ + "Ê" // U+0297: LATIN LETTER STRETCHED C
+ + "á´" // U+1D04: LATIN LETTER SMALL CAPITAL C
+ + "á¸" // U+1E08: LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE
+ + "â¸" // U+24B8: CIRCLED LATIN CAPITAL LETTER C
+ + "ï¼£" // U+FF23: FULLWIDTH LATIN CAPITAL LETTER C
+ ,"C", // Folded result
+
+ "ç" // U+00E7: LATIN SMALL LETTER C WITH CEDILLA
+ + "Ä" // U+0107: LATIN SMALL LETTER C WITH ACUTE
+ + "Ä" // U+0109: LATIN SMALL LETTER C WITH CIRCUMFLEX
+ + "Ä" // U+010B: LATIN SMALL LETTER C WITH DOT ABOVE
+ + "Ä" // U+010D: LATIN SMALL LETTER C WITH CARON
+ + "Æ" // U+0188: LATIN SMALL LETTER C WITH HOOK
+ + "ȼ" // U+023C: LATIN SMALL LETTER C WITH STROKE
+ + "É" // U+0255: LATIN SMALL LETTER C WITH CURL
+ + "á¸" // U+1E09: LATIN SMALL LETTER C WITH CEDILLA AND ACUTE
+ + "â" // U+2184: LATIN SMALL LETTER REVERSED C
+ + "â" // U+24D2: CIRCLED LATIN SMALL LETTER C
+ + "ê¾" // U+A73E: LATIN CAPITAL LETTER REVERSED C WITH DOT
+ + "ê¿" // U+A73F: LATIN SMALL LETTER REVERSED C WITH DOT
+ + "ï½" // U+FF43: FULLWIDTH LATIN SMALL LETTER C
+ ,"c", // Folded result
+
+ "â" // U+249E: PARENTHESIZED LATIN SMALL LETTER C
+ ,"(c)", // Folded result
+
+ "Ã" // U+00D0: LATIN CAPITAL LETTER ETH
+ + "Ä" // U+010E: LATIN CAPITAL LETTER D WITH CARON
+ + "Ä" // U+0110: LATIN CAPITAL LETTER D WITH STROKE
+ + "Æ" // U+0189: LATIN CAPITAL LETTER AFRICAN D
+ + "Æ" // U+018A: LATIN CAPITAL LETTER D WITH HOOK
+ + "Æ" // U+018B: LATIN CAPITAL LETTER D WITH TOPBAR
+ + "á´
" // U+1D05: LATIN LETTER SMALL CAPITAL D
+ + "á´" // U+1D06: LATIN LETTER SMALL CAPITAL ETH
+ + "á¸" // U+1E0A: LATIN CAPITAL LETTER D WITH DOT ABOVE
+ + "á¸" // U+1E0C: LATIN CAPITAL LETTER D WITH DOT BELOW
+ + "á¸" // U+1E0E: LATIN CAPITAL LETTER D WITH LINE BELOW
+ + "á¸" // U+1E10: LATIN CAPITAL LETTER D WITH CEDILLA
+ + "á¸" // U+1E12: LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW
+ + "â¹" // U+24B9: CIRCLED LATIN CAPITAL LETTER D
+ + "ê¹" // U+A779: LATIN CAPITAL LETTER INSULAR D
+ + "D" // U+FF24: FULLWIDTH LATIN CAPITAL LETTER D
+ ,"D", // Folded result
+
+ "ð" // U+00F0: LATIN SMALL LETTER ETH
+ + "Ä" // U+010F: LATIN SMALL LETTER D WITH CARON
+ + "Ä" // U+0111: LATIN SMALL LETTER D WITH STROKE
+ + "Æ" // U+018C: LATIN SMALL LETTER D WITH TOPBAR
+ + "È¡" // U+0221: LATIN SMALL LETTER D WITH CURL
+ + "É" // U+0256: LATIN SMALL LETTER D WITH TAIL
+ + "É" // U+0257: LATIN SMALL LETTER D WITH HOOK
+ + "áµ" // U+1D6D: LATIN SMALL LETTER D WITH MIDDLE TILDE
+ + "á¶" // U+1D81: LATIN SMALL LETTER D WITH PALATAL HOOK
+ + "á¶" // U+1D91: LATIN SMALL LETTER D WITH HOOK AND TAIL
+ + "á¸" // U+1E0B: LATIN SMALL LETTER D WITH DOT ABOVE
+ + "á¸" // U+1E0D: LATIN SMALL LETTER D WITH DOT BELOW
+ + "á¸" // U+1E0F: LATIN SMALL LETTER D WITH LINE BELOW
+ + "á¸" // U+1E11: LATIN SMALL LETTER D WITH CEDILLA
+ + "á¸" // U+1E13: LATIN SMALL LETTER D WITH CIRCUMFLEX BELOW
+ + "â" // U+24D3: CIRCLED LATIN SMALL LETTER D
+ + "êº" // U+A77A: LATIN SMALL LETTER INSULAR D
+ + "ï½" // U+FF44: FULLWIDTH LATIN SMALL LETTER D
+ ,"d", // Folded result
+
+ "Ç" // U+01C4: LATIN CAPITAL LETTER DZ WITH CARON
+ + "DZ" // U+01F1: LATIN CAPITAL LETTER DZ
+ ,"DZ", // Folded result
+
+ "Ç
" // U+01C5: LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON
+ + "Dz" // U+01F2: LATIN CAPITAL LETTER D WITH SMALL LETTER Z
+ ,"Dz", // Folded result
+
+ "â" // U+249F: PARENTHESIZED LATIN SMALL LETTER D
+ ,"(d)", // Folded result
+
+ "ȸ" // U+0238: LATIN SMALL LETTER DB DIGRAPH
+ ,"db", // Folded result
+
+ "Ç" // U+01C6: LATIN SMALL LETTER DZ WITH CARON
+ + "dz" // U+01F3: LATIN SMALL LETTER DZ
+ + "Ê£" // U+02A3: LATIN SMALL LETTER DZ DIGRAPH
+ + "Ê¥" // U+02A5: LATIN SMALL LETTER DZ DIGRAPH WITH CURL
+ ,"dz", // Folded result
+
+ "Ã" // U+00C8: LATIN CAPITAL LETTER E WITH GRAVE
+ + "Ã" // U+00C9: LATIN CAPITAL LETTER E WITH ACUTE
+ + "Ã" // U+00CA: LATIN CAPITAL LETTER E WITH CIRCUMFLEX
+ + "Ã" // U+00CB: LATIN CAPITAL LETTER E WITH DIAERESIS
+ + "Ä" // U+0112: LATIN CAPITAL LETTER E WITH MACRON
+ + "Ä" // U+0114: LATIN CAPITAL LETTER E WITH BREVE
+ + "Ä" // U+0116: LATIN CAPITAL LETTER E WITH DOT ABOVE
+ + "Ä" // U+0118: LATIN CAPITAL LETTER E WITH OGONEK
+ + "Ä" // U+011A: LATIN CAPITAL LETTER E WITH CARON
+ + "Æ" // U+018E: LATIN CAPITAL LETTER REVERSED E
+ + "Æ" // U+0190: LATIN CAPITAL LETTER OPEN E
+ + "È" // U+0204: LATIN CAPITAL LETTER E WITH DOUBLE GRAVE
+ + "È" // U+0206: LATIN CAPITAL LETTER E WITH INVERTED BREVE
+ + "Ȩ" // U+0228: LATIN CAPITAL LETTER E WITH CEDILLA
+ + "É" // U+0246: LATIN CAPITAL LETTER E WITH STROKE
+ + "á´" // U+1D07: LATIN LETTER SMALL CAPITAL E
+ + "á¸" // U+1E14: LATIN CAPITAL LETTER E WITH MACRON AND GRAVE
+ + "á¸" // U+1E16: LATIN CAPITAL LETTER E WITH MACRON AND ACUTE
+ + "á¸" // U+1E18: LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW
+ + "á¸" // U+1E1A: LATIN CAPITAL LETTER E WITH TILDE BELOW
+ + "á¸" // U+1E1C: LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE
+ + "Ẹ" // U+1EB8: LATIN CAPITAL LETTER E WITH DOT BELOW
+ + "Ẻ" // U+1EBA: LATIN CAPITAL LETTER E WITH HOOK ABOVE
+ + "Ẽ" // U+1EBC: LATIN CAPITAL LETTER E WITH TILDE
+ + "Ế" // U+1EBE: LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE
+ + "á»" // U+1EC0: LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE
+ + "á»" // U+1EC2: LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE
+ + "á»" // U+1EC4: LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE
+ + "á»" // U+1EC6: LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW
+ + "âº" // U+24BA: CIRCLED LATIN CAPITAL LETTER E
+ + "â±»" // U+2C7B: LATIN LETTER SMALL CAPITAL TURNED E
+ + "ï¼¥" // U+FF25: FULLWIDTH LATIN CAPITAL LETTER E
+ ,"E", // Folded result
+
+ "è" // U+00E8: LATIN SMALL LETTER E WITH GRAVE
+ + "é" // U+00E9: LATIN SMALL LETTER E WITH ACUTE
+ + "ê" // U+00EA: LATIN SMALL LETTER E WITH CIRCUMFLEX
+ + "ë" // U+00EB: LATIN SMALL LETTER E WITH DIAERESIS
+ + "Ä" // U+0113: LATIN SMALL LETTER E WITH MACRON
+ + "Ä" // U+0115: LATIN SMALL LETTER E WITH BREVE
+ + "Ä" // U+0117: LATIN SMALL LETTER E WITH DOT ABOVE
+ + "Ä" // U+0119: LATIN SMALL LETTER E WITH OGONEK
+ + "Ä" // U+011B: LATIN SMALL LETTER E WITH CARON
+ + "Ç" // U+01DD: LATIN SMALL LETTER TURNED E
+ + "È
" // U+0205: LATIN SMALL LETTER E WITH DOUBLE GRAVE
+ + "È" // U+0207: LATIN SMALL LETTER E WITH INVERTED BREVE
+ + "È©" // U+0229: LATIN SMALL LETTER E WITH CEDILLA
+ + "É" // U+0247: LATIN SMALL LETTER E WITH STROKE
+ + "É" // U+0258: LATIN SMALL LETTER REVERSED E
+ + "É" // U+025B: LATIN SMALL LETTER OPEN E
+ + "É" // U+025C: LATIN SMALL LETTER REVERSED OPEN E
+ + "É" // U+025D: LATIN SMALL LETTER REVERSED OPEN E WITH HOOK
+ + "É" // U+025E: LATIN SMALL LETTER CLOSED REVERSED OPEN E
+ + "Ê" // U+029A: LATIN SMALL LETTER CLOSED OPEN E
+ + "á´" // U+1D08: LATIN SMALL LETTER TURNED OPEN E
+ + "á¶" // U+1D92: LATIN SMALL LETTER E WITH RETROFLEX HOOK
+ + "á¶" // U+1D93: LATIN SMALL LETTER OPEN E WITH RETROFLEX HOOK
+ + "á¶" // U+1D94: LATIN SMALL LETTER REVERSED OPEN E WITH RETROFLEX HOOK
+ + "á¸" // U+1E15: LATIN SMALL LETTER E WITH MACRON AND GRAVE
+ + "á¸" // U+1E17: LATIN SMALL LETTER E WITH MACRON AND ACUTE
+ + "á¸" // U+1E19: LATIN SMALL LETTER E WITH CIRCUMFLEX BELOW
+ + "á¸" // U+1E1B: LATIN SMALL LETTER E WITH TILDE BELOW
+ + "á¸" // U+1E1D: LATIN SMALL LETTER E WITH CEDILLA AND BREVE
+ + "ẹ" // U+1EB9: LATIN SMALL LETTER E WITH DOT BELOW
+ + "ẻ" // U+1EBB: LATIN SMALL LETTER E WITH HOOK ABOVE
+ + "ẽ" // U+1EBD: LATIN SMALL LETTER E WITH TILDE
+ + "ế" // U+1EBF: LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE
+ + "á»" // U+1EC1: LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE
+ + "á»" // U+1EC3: LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE
+ + "á»
" // U+1EC5: LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE
+ + "á»" // U+1EC7: LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW
+ + "â" // U+2091: LATIN SUBSCRIPT SMALL LETTER E
+ + "â" // U+24D4: CIRCLED LATIN SMALL LETTER E
+ + "ⱸ" // U+2C78: LATIN SMALL LETTER E WITH NOTCH
+ + "ï½
" // U+FF45: FULLWIDTH LATIN SMALL LETTER E
+ ,"e", // Folded result
+
+ "â " // U+24A0: PARENTHESIZED LATIN SMALL LETTER E
+ ,"(e)", // Folded result
+
+ "Æ" // U+0191: LATIN CAPITAL LETTER F WITH HOOK
+ + "á¸" // U+1E1E: LATIN CAPITAL LETTER F WITH DOT ABOVE
+ + "â»" // U+24BB: CIRCLED LATIN CAPITAL LETTER F
+ + "ê°" // U+A730: LATIN LETTER SMALL CAPITAL F
+ + "ê»" // U+A77B: LATIN CAPITAL LETTER INSULAR F
+ + "ê»" // U+A7FB: LATIN EPIGRAPHIC LETTER REVERSED F
+ + "F" // U+FF26: FULLWIDTH LATIN CAPITAL LETTER F
+ ,"F", // Folded result
+
+ "Æ" // U+0192: LATIN SMALL LETTER F WITH HOOK
+ + "áµ®" // U+1D6E: LATIN SMALL LETTER F WITH MIDDLE TILDE
+ + "á¶" // U+1D82: LATIN SMALL LETTER F WITH PALATAL HOOK
+ + "á¸" // U+1E1F: LATIN SMALL LETTER F WITH DOT ABOVE
+ + "áº" // U+1E9B: LATIN SMALL LETTER LONG S WITH DOT ABOVE
+ + "â" // U+24D5: CIRCLED LATIN SMALL LETTER F
+ + "ê¼" // U+A77C: LATIN SMALL LETTER INSULAR F
+ + "ï½" // U+FF46: FULLWIDTH LATIN SMALL LETTER F
+ ,"f", // Folded result
+
+ "â¡" // U+24A1: PARENTHESIZED LATIN SMALL LETTER F
+ ,"(f)", // Folded result
+
+ "ï¬" // U+FB00: LATIN SMALL LIGATURE FF
+ ,"ff", // Folded result
+
+ "ï¬" // U+FB03: LATIN SMALL LIGATURE FFI
+ ,"ffi", // Folded result
+
+ "ï¬" // U+FB04: LATIN SMALL LIGATURE FFL
+ ,"ffl", // Folded result
+
+ "ï¬" // U+FB01: LATIN SMALL LIGATURE FI
+ ,"fi", // Folded result
+
+ "ï¬" // U+FB02: LATIN SMALL LIGATURE FL
+ ,"fl", // Folded result
+
+ "Ä" // U+011C: LATIN CAPITAL LETTER G WITH CIRCUMFLEX
+ + "Ä" // U+011E: LATIN CAPITAL LETTER G WITH BREVE
+ + "Ä " // U+0120: LATIN CAPITAL LETTER G WITH DOT ABOVE
+ + "Ä¢" // U+0122: LATIN CAPITAL LETTER G WITH CEDILLA
+ + "Æ" // U+0193: LATIN CAPITAL LETTER G WITH HOOK
+ + "Ǥ" // U+01E4: LATIN CAPITAL LETTER G WITH STROKE
+ + "Ç¥" // U+01E5: LATIN SMALL LETTER G WITH STROKE
+ + "Ǧ" // U+01E6: LATIN CAPITAL LETTER G WITH CARON
+ + "ǧ" // U+01E7: LATIN SMALL LETTER G WITH CARON
+ + "Ç´" // U+01F4: LATIN CAPITAL LETTER G WITH ACUTE
+ + "É¢" // U+0262: LATIN LETTER SMALL CAPITAL G
+ + "Ê" // U+029B: LATIN LETTER SMALL CAPITAL G WITH HOOK
+ + "Ḡ" // U+1E20: LATIN CAPITAL LETTER G WITH MACRON
+ + "â¼" // U+24BC: CIRCLED LATIN CAPITAL LETTER G
+ + "ê½" // U+A77D: LATIN CAPITAL LETTER INSULAR G
+ + "ê¾" // U+A77E: LATIN CAPITAL LETTER TURNED INSULAR G
+ + "G" // U+FF27: FULLWIDTH LATIN CAPITAL LETTER G
+ ,"G", // Folded result
+
+ "Ä" // U+011D: LATIN SMALL LETTER G WITH CIRCUMFLEX
+ + "Ä" // U+011F: LATIN SMALL LETTER G WITH BREVE
+ + "Ä¡" // U+0121: LATIN SMALL LETTER G WITH DOT ABOVE
+ + "Ä£" // U+0123: LATIN SMALL LETTER G WITH CEDILLA
+ + "ǵ" // U+01F5: LATIN SMALL LETTER G WITH ACUTE
+ + "É " // U+0260: LATIN SMALL LETTER G WITH HOOK
+ + "É¡" // U+0261: LATIN SMALL LETTER SCRIPT G
+ + "áµ·" // U+1D77: LATIN SMALL LETTER TURNED G
+ + "áµ¹" // U+1D79: LATIN SMALL LETTER INSULAR G
+ + "á¶" // U+1D83: LATIN SMALL LETTER G WITH PALATAL HOOK
+ + "ḡ" // U+1E21: LATIN SMALL LETTER G WITH MACRON
+ + "â" // U+24D6: CIRCLED LATIN SMALL LETTER G
+ + "ê¿" // U+A77F: LATIN SMALL LETTER TURNED INSULAR G
+ + "ï½" // U+FF47: FULLWIDTH LATIN SMALL LETTER G
+ ,"g", // Folded result
+
+ "â¢" // U+24A2: PARENTHESIZED LATIN SMALL LETTER G
+ ,"(g)", // Folded result
+
+ "Ĥ" // U+0124: LATIN CAPITAL LETTER H WITH CIRCUMFLEX
+ + "Ħ" // U+0126: LATIN CAPITAL LETTER H WITH STROKE
+ + "È" // U+021E: LATIN CAPITAL LETTER H WITH CARON
+ + "Ê" // U+029C: LATIN LETTER SMALL CAPITAL H
+ + "Ḣ" // U+1E22: LATIN CAPITAL LETTER H WITH DOT ABOVE
+ + "Ḥ" // U+1E24: LATIN CAPITAL LETTER H WITH DOT BELOW
+ + "Ḧ" // U+1E26: LATIN CAPITAL LETTER H WITH DIAERESIS
+ + "Ḩ" // U+1E28: LATIN CAPITAL LETTER H WITH CEDILLA
+ + "Ḫ" // U+1E2A: LATIN CAPITAL LETTER H WITH BREVE BELOW
+ + "â½" // U+24BD: CIRCLED LATIN CAPITAL LETTER H
+ + "Ⱨ" // U+2C67: LATIN CAPITAL LETTER H WITH DESCENDER
+ + "â±µ" // U+2C75: LATIN CAPITAL LETTER HALF H
+ + "H" // U+FF28: FULLWIDTH LATIN CAPITAL LETTER H
+ ,"H", // Folded result
+
+ "Ä¥" // U+0125: LATIN SMALL LETTER H WITH CIRCUMFLEX
+ + "ħ" // U+0127: LATIN SMALL LETTER H WITH STROKE
+ + "È" // U+021F: LATIN SMALL LETTER H WITH CARON
+ + "É¥" // U+0265: LATIN SMALL LETTER TURNED H
+ + "ɦ" // U+0266: LATIN SMALL LETTER H WITH HOOK
+ + "Ê®" // U+02AE: LATIN SMALL LETTER TURNED H WITH FISHHOOK
+ + "ʯ" // U+02AF: LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL
+ + "ḣ" // U+1E23: LATIN SMALL LETTER H WITH DOT ABOVE
+ + "ḥ" // U+1E25: LATIN SMALL LETTER H WITH DOT BELOW
+ + "ḧ" // U+1E27: LATIN SMALL LETTER H WITH DIAERESIS
+ + "ḩ" // U+1E29: LATIN SMALL LETTER H WITH CEDILLA
+ + "ḫ" // U+1E2B: LATIN SMALL LETTER H WITH BREVE BELOW
+ + "áº" // U+1E96: LATIN SMALL LETTER H WITH LINE BELOW
+ + "â" // U+24D7: CIRCLED LATIN SMALL LETTER H
+ + "ⱨ" // U+2C68: LATIN SMALL LETTER H WITH DESCENDER
+ + "ⱶ" // U+2C76: LATIN SMALL LETTER HALF H
+ + "ï½" // U+FF48: FULLWIDTH LATIN SMALL LETTER H
+ ,"h", // Folded result
+
+ "Ƕ" // U+01F6: LATIN CAPITAL LETTER HWAIR
+ ,"HV", // Folded result
+
+ "â£" // U+24A3: PARENTHESIZED LATIN SMALL LETTER H
+ ,"(h)", // Folded result
+
+ "Æ" // U+0195: LATIN SMALL LETTER HV
+ ,"hv", // Folded result
+
+ "Ã" // U+00CC: LATIN CAPITAL LETTER I WITH GRAVE
+ + "Ã" // U+00CD: LATIN CAPITAL LETTER I WITH ACUTE
+ + "Ã" // U+00CE: LATIN CAPITAL LETTER I WITH CIRCUMFLEX
+ + "Ã" // U+00CF: LATIN CAPITAL LETTER I WITH DIAERESIS
+ + "Ĩ" // U+0128: LATIN CAPITAL LETTER I WITH TILDE
+ + "Ī" // U+012A: LATIN CAPITAL LETTER I WITH MACRON
+ + "Ĭ" // U+012C: LATIN CAPITAL LETTER I WITH BREVE
+ + "Ä®" // U+012E: LATIN CAPITAL LETTER I WITH OGONEK
+ + "Ä°" // U+0130: LATIN CAPITAL LETTER I WITH DOT ABOVE
+ + "Æ" // U+0196: LATIN CAPITAL LETTER IOTA
+ + "Æ" // U+0197: LATIN CAPITAL LETTER I WITH STROKE
+ + "Ç" // U+01CF: LATIN CAPITAL LETTER I WITH CARON
+ + "È" // U+0208: LATIN CAPITAL LETTER I WITH DOUBLE GRAVE
+ + "È" // U+020A: LATIN CAPITAL LETTER I WITH INVERTED BREVE
+ + "ɪ" // U+026A: LATIN LETTER SMALL CAPITAL I
+ + "áµ»" // U+1D7B: LATIN SMALL CAPITAL LETTER I WITH STROKE
+ + "Ḭ" // U+1E2C: LATIN CAPITAL LETTER I WITH TILDE BELOW
+ + "Ḯ" // U+1E2E: LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE
+ + "á»" // U+1EC8: LATIN CAPITAL LETTER I WITH HOOK ABOVE
+ + "á»" // U+1ECA: LATIN CAPITAL LETTER I WITH DOT BELOW
+ + "â¾" // U+24BE: CIRCLED LATIN CAPITAL LETTER I
+ + "ê¾" // U+A7FE: LATIN EPIGRAPHIC LETTER I LONGA
+ + "I" // U+FF29: FULLWIDTH LATIN CAPITAL LETTER I
+ ,"I", // Folded result
+
+ "ì" // U+00EC: LATIN SMALL LETTER I WITH GRAVE
+ + "Ã" // U+00ED: LATIN SMALL LETTER I WITH ACUTE
+ + "î" // U+00EE: LATIN SMALL LETTER I WITH CIRCUMFLEX
+ + "ï" // U+00EF: LATIN SMALL LETTER I WITH DIAERESIS
+ + "Ä©" // U+0129: LATIN SMALL LETTER I WITH TILDE
+ + "Ä«" // U+012B: LATIN SMALL LETTER I WITH MACRON
+ + "Ä" // U+012D: LATIN SMALL LETTER I WITH BREVE
+ + "į" // U+012F: LATIN SMALL LETTER I WITH OGONEK
+ + "ı" // U+0131: LATIN SMALL LETTER DOTLESS I
+ + "Ç" // U+01D0: LATIN SMALL LETTER I WITH CARON
+ + "È" // U+0209: LATIN SMALL LETTER I WITH DOUBLE GRAVE
+ + "È" // U+020B: LATIN SMALL LETTER I WITH INVERTED BREVE
+ + "ɨ" // U+0268: LATIN SMALL LETTER I WITH STROKE
+ + "á´" // U+1D09: LATIN SMALL LETTER TURNED I
+ + "áµ¢" // U+1D62: LATIN SUBSCRIPT SMALL LETTER I
+ + "áµ¼" // U+1D7C: LATIN SMALL LETTER IOTA WITH STROKE
+ + "á¶" // U+1D96: LATIN SMALL LETTER I WITH RETROFLEX HOOK
+ + "á¸" // U+1E2D: LATIN SMALL LETTER I WITH TILDE BELOW
+ + "ḯ" // U+1E2F: LATIN SMALL LETTER I WITH DIAERESIS AND ACUTE
+ + "á»" // U+1EC9: LATIN SMALL LETTER I WITH HOOK ABOVE
+ + "á»" // U+1ECB: LATIN SMALL LETTER I WITH DOT BELOW
+ + "â±" // U+2071: SUPERSCRIPT LATIN SMALL LETTER I
+ + "â" // U+24D8: CIRCLED LATIN SMALL LETTER I
+ + "ï½" // U+FF49: FULLWIDTH LATIN SMALL LETTER I
+ ,"i", // Folded result
+
+ "IJ" // U+0132: LATIN CAPITAL LIGATURE IJ
+ ,"IJ", // Folded result
+
+ "â¤" // U+24A4: PARENTHESIZED LATIN SMALL LETTER I
+ ,"(i)", // Folded result
+
+ "ij" // U+0133: LATIN SMALL LIGATURE IJ
+ ,"ij", // Folded result
+
+ "Ä´" // U+0134: LATIN CAPITAL LETTER J WITH CIRCUMFLEX
+ + "É" // U+0248: LATIN CAPITAL LETTER J WITH STROKE
+ + "á´" // U+1D0A: LATIN LETTER SMALL CAPITAL J
+ + "â¿" // U+24BF: CIRCLED LATIN CAPITAL LETTER J
+ + "J" // U+FF2A: FULLWIDTH LATIN CAPITAL LETTER J
+ ,"J", // Folded result
+
+ "ĵ" // U+0135: LATIN SMALL LETTER J WITH CIRCUMFLEX
+ + "Ç°" // U+01F0: LATIN SMALL LETTER J WITH CARON
+ + "È·" // U+0237: LATIN SMALL LETTER DOTLESS J
+ + "É" // U+0249: LATIN SMALL LETTER J WITH STROKE
+ + "É" // U+025F: LATIN SMALL LETTER DOTLESS J WITH STROKE
+ + "Ê" // U+0284: LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK
+ + "Ê" // U+029D: LATIN SMALL LETTER J WITH CROSSED-TAIL
+ + "â" // U+24D9: CIRCLED LATIN SMALL LETTER J
+ + "â±¼" // U+2C7C: LATIN SUBSCRIPT SMALL LETTER J
+ + "ï½" // U+FF4A: FULLWIDTH LATIN SMALL LETTER J
+ ,"j", // Folded result
+
+ "â¥" // U+24A5: PARENTHESIZED LATIN SMALL LETTER J
+ ,"(j)", // Folded result
+
+ "Ķ" // U+0136: LATIN CAPITAL LETTER K WITH CEDILLA
+ + "Æ" // U+0198: LATIN CAPITAL LETTER K WITH HOOK
+ + "Ǩ" // U+01E8: LATIN CAPITAL LETTER K WITH CARON
+ + "á´" // U+1D0B: LATIN LETTER SMALL CAPITAL K
+ + "Ḱ" // U+1E30: LATIN CAPITAL LETTER K WITH ACUTE
+ + "Ḳ" // U+1E32: LATIN CAPITAL LETTER K WITH DOT BELOW
+ + "Ḵ" // U+1E34: LATIN CAPITAL LETTER K WITH LINE BELOW
+ + "â" // U+24C0: CIRCLED LATIN CAPITAL LETTER K
+ + "Ⱪ" // U+2C69: LATIN CAPITAL LETTER K WITH DESCENDER
+ + "ê" // U+A740: LATIN CAPITAL LETTER K WITH STROKE
+ + "ê" // U+A742: LATIN CAPITAL LETTER K WITH DIAGONAL STROKE
+ + "ê" // U+A744: LATIN CAPITAL LETTER K WITH STROKE AND DIAGONAL STROKE
+ + "K" // U+FF2B: FULLWIDTH LATIN CAPITAL LETTER K
+ ,"K", // Folded result
+
+ "Ä·" // U+0137: LATIN SMALL LETTER K WITH CEDILLA
+ + "Æ" // U+0199: LATIN SMALL LETTER K WITH HOOK
+ + "Ç©" // U+01E9: LATIN SMALL LETTER K WITH CARON
+ + "Ê" // U+029E: LATIN SMALL LETTER TURNED K
+ + "á¶" // U+1D84: LATIN SMALL LETTER K WITH PALATAL HOOK
+ + "ḱ" // U+1E31: LATIN SMALL LETTER K WITH ACUTE
+ + "ḳ" // U+1E33: LATIN SMALL LETTER K WITH DOT BELOW
+ + "ḵ" // U+1E35: LATIN SMALL LETTER K WITH LINE BELOW
+ + "â" // U+24DA: CIRCLED LATIN SMALL LETTER K
+ + "ⱪ" // U+2C6A: LATIN SMALL LETTER K WITH DESCENDER
+ + "ê" // U+A741: LATIN SMALL LETTER K WITH STROKE
+ + "ê" // U+A743: LATIN SMALL LETTER K WITH DIAGONAL STROKE
+ + "ê
" // U+A745: LATIN SMALL LETTER K WITH STROKE AND DIAGONAL STROKE
+ + "ï½" // U+FF4B: FULLWIDTH LATIN SMALL LETTER K
+ ,"k", // Folded result
+
+ "â¦" // U+24A6: PARENTHESIZED LATIN SMALL LETTER K
+ ,"(k)", // Folded result
+
+ "Ĺ" // U+0139: LATIN CAPITAL LETTER L WITH ACUTE
+ + "Ä»" // U+013B: LATIN CAPITAL LETTER L WITH CEDILLA
+ + "Ľ" // U+013D: LATIN CAPITAL LETTER L WITH CARON
+ + "Ä¿" // U+013F: LATIN CAPITAL LETTER L WITH MIDDLE DOT
+ + "Å" // U+0141: LATIN CAPITAL LETTER L WITH STROKE
+ + "Ƚ" // U+023D: LATIN CAPITAL LETTER L WITH BAR
+ + "Ê" // U+029F: LATIN LETTER SMALL CAPITAL L
+ + "á´" // U+1D0C: LATIN LETTER SMALL CAPITAL L WITH STROKE
+ + "Ḷ" // U+1E36: LATIN CAPITAL LETTER L WITH DOT BELOW
+ + "Ḹ" // U+1E38: LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON
+ + "Ḻ" // U+1E3A: LATIN CAPITAL LETTER L WITH LINE BELOW
+ + "Ḽ" // U+1E3C: LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW
+ + "â" // U+24C1: CIRCLED LATIN CAPITAL LETTER L
+ + "â± " // U+2C60: LATIN CAPITAL LETTER L WITH DOUBLE BAR
+ + "â±¢" // U+2C62: LATIN CAPITAL LETTER L WITH MIDDLE TILDE
+ + "ê" // U+A746: LATIN CAPITAL LETTER BROKEN L
+ + "ê" // U+A748: LATIN CAPITAL LETTER L WITH HIGH STROKE
+ + "ê" // U+A780: LATIN CAPITAL LETTER TURNED L
+ + "L" // U+FF2C: FULLWIDTH LATIN CAPITAL LETTER L
+ ,"L", // Folded result
+
+ "ĺ" // U+013A: LATIN SMALL LETTER L WITH ACUTE
+ + "ļ" // U+013C: LATIN SMALL LETTER L WITH CEDILLA
+ + "ľ" // U+013E: LATIN SMALL LETTER L WITH CARON
+ + "Å" // U+0140: LATIN SMALL LETTER L WITH MIDDLE DOT
+ + "Å" // U+0142: LATIN SMALL LETTER L WITH STROKE
+ + "Æ" // U+019A: LATIN SMALL LETTER L WITH BAR
+ + "È´" // U+0234: LATIN SMALL LETTER L WITH CURL
+ + "É«" // U+026B: LATIN SMALL LETTER L WITH MIDDLE TILDE
+ + "ɬ" // U+026C: LATIN SMALL LETTER L WITH BELT
+ + "É" // U+026D: LATIN SMALL LETTER L WITH RETROFLEX HOOK
+ + "á¶
" // U+1D85: LATIN SMALL LETTER L WITH PALATAL HOOK
+ + "ḷ" // U+1E37: LATIN SMALL LETTER L WITH DOT BELOW
+ + "ḹ" // U+1E39: LATIN SMALL LETTER L WITH DOT BELOW AND MACRON
+ + "ḻ" // U+1E3B: LATIN SMALL LETTER L WITH LINE BELOW
+ + "ḽ" // U+1E3D: LATIN SMALL LETTER L WITH CIRCUMFLEX BELOW
+ + "â" // U+24DB: CIRCLED LATIN SMALL LETTER L
+ + "ⱡ" // U+2C61: LATIN SMALL LETTER L WITH DOUBLE BAR
+ + "ê" // U+A747: LATIN SMALL LETTER BROKEN L
+ + "ê" // U+A749: LATIN SMALL LETTER L WITH HIGH STROKE
+ + "ê" // U+A781: LATIN SMALL LETTER TURNED L
+ + "ï½" // U+FF4C: FULLWIDTH LATIN SMALL LETTER L
+ ,"l", // Folded result
+
+ "Ç" // U+01C7: LATIN CAPITAL LETTER LJ
+ ,"LJ", // Folded result
+
+ "Ỻ" // U+1EFA: LATIN CAPITAL LETTER MIDDLE-WELSH LL
+ ,"LL", // Folded result
+
+ "Ç" // U+01C8: LATIN CAPITAL LETTER L WITH SMALL LETTER J
+ ,"Lj", // Folded result
+
+ "â§" // U+24A7: PARENTHESIZED LATIN SMALL LETTER L
+ ,"(l)", // Folded result
+
+ "Ç" // U+01C9: LATIN SMALL LETTER LJ
+ ,"lj", // Folded result
+
+ "á»»" // U+1EFB: LATIN SMALL LETTER MIDDLE-WELSH LL
+ ,"ll", // Folded result
+
+ "ʪ" // U+02AA: LATIN SMALL LETTER LS DIGRAPH
+ ,"ls", // Folded result
+
+ "Ê«" // U+02AB: LATIN SMALL LETTER LZ DIGRAPH
+ ,"lz", // Folded result
+
+ "Æ" // U+019C: LATIN CAPITAL LETTER TURNED M
+ + "á´" // U+1D0D: LATIN LETTER SMALL CAPITAL M
+ + "Ḿ" // U+1E3E: LATIN CAPITAL LETTER M WITH ACUTE
+ + "á¹" // U+1E40: LATIN CAPITAL LETTER M WITH DOT ABOVE
+ + "á¹" // U+1E42: LATIN CAPITAL LETTER M WITH DOT BELOW
+ + "â" // U+24C2: CIRCLED LATIN CAPITAL LETTER M
+ + "â±®" // U+2C6E: LATIN CAPITAL LETTER M WITH HOOK
+ + "ê½" // U+A7FD: LATIN EPIGRAPHIC LETTER INVERTED M
+ + "ê¿" // U+A7FF: LATIN EPIGRAPHIC LETTER ARCHAIC M
+ + "ï¼" // U+FF2D: FULLWIDTH LATIN CAPITAL LETTER M
+ ,"M", // Folded result
+
+ "ɯ" // U+026F: LATIN SMALL LETTER TURNED M
+ + "É°" // U+0270: LATIN SMALL LETTER TURNED M WITH LONG LEG
+ + "ɱ" // U+0271: LATIN SMALL LETTER M WITH HOOK
+ + "ᵯ" // U+1D6F: LATIN SMALL LETTER M WITH MIDDLE TILDE
+ + "á¶" // U+1D86: LATIN SMALL LETTER M WITH PALATAL HOOK
+ + "ḿ" // U+1E3F: LATIN SMALL LETTER M WITH ACUTE
+ + "á¹" // U+1E41: LATIN SMALL LETTER M WITH DOT ABOVE
+ + "á¹" // U+1E43: LATIN SMALL LETTER M WITH DOT BELOW
+ + "â" // U+24DC: CIRCLED LATIN SMALL LETTER M
+ + "ï½" // U+FF4D: FULLWIDTH LATIN SMALL LETTER M
+ ,"m", // Folded result
+
+ "â¨" // U+24A8: PARENTHESIZED LATIN SMALL LETTER M
+ ,"(m)", // Folded result
+
+ "Ã" // U+00D1: LATIN CAPITAL LETTER N WITH TILDE
+ + "Å" // U+0143: LATIN CAPITAL LETTER N WITH ACUTE
+ + "Å
" // U+0145: LATIN CAPITAL LETTER N WITH CEDILLA
+ + "Å" // U+0147: LATIN CAPITAL LETTER N WITH CARON
+ + "Å" // U+014A: LATIN CAPITAL LETTER ENG
+ + "Æ" // U+019D: LATIN CAPITAL LETTER N WITH LEFT HOOK
+ + "Ǹ" // U+01F8: LATIN CAPITAL LETTER N WITH GRAVE
+ + "È " // U+0220: LATIN CAPITAL LETTER N WITH LONG RIGHT LEG
+ + "É´" // U+0274: LATIN LETTER SMALL CAPITAL N
+ + "á´" // U+1D0E: LATIN LETTER SMALL CAPITAL REVERSED N
+ + "á¹" // U+1E44: LATIN CAPITAL LETTER N WITH DOT ABOVE
+ + "á¹" // U+1E46: LATIN CAPITAL LETTER N WITH DOT BELOW
+ + "á¹" // U+1E48: LATIN CAPITAL LETTER N WITH LINE BELOW
+ + "á¹" // U+1E4A: LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW
+ + "â" // U+24C3: CIRCLED LATIN CAPITAL LETTER N
+ + "ï¼®" // U+FF2E: FULLWIDTH LATIN CAPITAL LETTER N
+ ,"N", // Folded result
+
+ "ñ" // U+00F1: LATIN SMALL LETTER N WITH TILDE
+ + "Å" // U+0144: LATIN SMALL LETTER N WITH ACUTE
+ + "Å" // U+0146: LATIN SMALL LETTER N WITH CEDILLA
+ + "Å" // U+0148: LATIN SMALL LETTER N WITH CARON
+ + "Å" // U+0149: LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
+ + "Å" // U+014B: LATIN SMALL LETTER ENG
+ + "Æ" // U+019E: LATIN SMALL LETTER N WITH LONG RIGHT LEG
+ + "ǹ" // U+01F9: LATIN SMALL LETTER N WITH GRAVE
+ + "ȵ" // U+0235: LATIN SMALL LETTER N WITH CURL
+ + "ɲ" // U+0272: LATIN SMALL LETTER N WITH LEFT HOOK
+ + "ɳ" // U+0273: LATIN SMALL LETTER N WITH RETROFLEX HOOK
+ + "áµ°" // U+1D70: LATIN SMALL LETTER N WITH MIDDLE TILDE
+ + "á¶" // U+1D87: LATIN SMALL LETTER N WITH PALATAL HOOK
+ + "á¹
" // U+1E45: LATIN SMALL LETTER N WITH DOT ABOVE
+ + "á¹" // U+1E47: LATIN SMALL LETTER N WITH DOT BELOW
+ + "á¹" // U+1E49: LATIN SMALL LETTER N WITH LINE BELOW
+ + "á¹" // U+1E4B: LATIN SMALL LETTER N WITH CIRCUMFLEX BELOW
+ + "â¿" // U+207F: SUPERSCRIPT LATIN SMALL LETTER N
+ + "â" // U+24DD: CIRCLED LATIN SMALL LETTER N
+ + "ï½" // U+FF4E: FULLWIDTH LATIN SMALL LETTER N
+ ,"n", // Folded result
+
+ "Ç" // U+01CA: LATIN CAPITAL LETTER NJ
+ ,"NJ", // Folded result
+
+ "Ç" // U+01CB: LATIN CAPITAL LETTER N WITH SMALL LETTER J
+ ,"Nj", // Folded result
+
+ "â©" // U+24A9: PARENTHESIZED LATIN SMALL LETTER N
+ ,"(n)", // Folded result
+
+ "Ç" // U+01CC: LATIN SMALL LETTER NJ
+ ,"nj", // Folded result
+
+ "Ã" // U+00D2: LATIN CAPITAL LETTER O WITH GRAVE
+ + "Ã" // U+00D3: LATIN CAPITAL LETTER O WITH ACUTE
+ + "Ã" // U+00D4: LATIN CAPITAL LETTER O WITH CIRCUMFLEX
+ + "Ã" // U+00D5: LATIN CAPITAL LETTER O WITH TILDE
+ + "Ã" // U+00D6: LATIN CAPITAL LETTER O WITH DIAERESIS
+ + "Ã" // U+00D8: LATIN CAPITAL LETTER O WITH STROKE
+ + "Å" // U+014C: LATIN CAPITAL LETTER O WITH MACRON
+ + "Å" // U+014E: LATIN CAPITAL LETTER O WITH BREVE
+ + "Å" // U+0150: LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
+ + "Æ" // U+0186: LATIN CAPITAL LETTER OPEN O
+ + "Æ" // U+019F: LATIN CAPITAL LETTER O WITH MIDDLE TILDE
+ + "Æ " // U+01A0: LATIN CAPITAL LETTER O WITH HORN
+ + "Ç" // U+01D1: LATIN CAPITAL LETTER O WITH CARON
+ + "Ǫ" // U+01EA: LATIN CAPITAL LETTER O WITH OGONEK
+ + "Ǭ" // U+01EC: LATIN CAPITAL LETTER O WITH OGONEK AND MACRON
+ + "Ǿ" // U+01FE: LATIN CAPITAL LETTER O WITH STROKE AND ACUTE
+ + "È" // U+020C: LATIN CAPITAL LETTER O WITH DOUBLE GRAVE
+ + "È" // U+020E: LATIN CAPITAL LETTER O WITH INVERTED BREVE
+ + "Ȫ" // U+022A: LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON
+ + "Ȭ" // U+022C: LATIN CAPITAL LETTER O WITH TILDE AND MACRON
+ + "È®" // U+022E: LATIN CAPITAL LETTER O WITH DOT ABOVE
+ + "È°" // U+0230: LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON
+ + "á´" // U+1D0F: LATIN LETTER SMALL CAPITAL O
+ + "á´" // U+1D10: LATIN LETTER SMALL CAPITAL OPEN O
+ + "á¹" // U+1E4C: LATIN CAPITAL LETTER O WITH TILDE AND ACUTE
+ + "á¹" // U+1E4E: LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS
+ + "á¹" // U+1E50: LATIN CAPITAL LETTER O WITH MACRON AND GRAVE
+ + "á¹" // U+1E52: LATIN CAPITAL LETTER O WITH MACRON AND ACUTE
+ + "á»" // U+1ECC: LATIN CAPITAL LETTER O WITH DOT BELOW
+ + "á»" // U+1ECE: LATIN CAPITAL LETTER O WITH HOOK ABOVE
+ + "á»" // U+1ED0: LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE
+ + "á»" // U+1ED2: LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE
+ + "á»" // U+1ED4: LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE
+ + "á»" // U+1ED6: LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE
+ + "á»" // U+1ED8: LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW
+ + "á»" // U+1EDA: LATIN CAPITAL LETTER O WITH HORN AND ACUTE
+ + "á»" // U+1EDC: LATIN CAPITAL LETTER O WITH HORN AND GRAVE
+ + "á»" // U+1EDE: LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE
+ + "á» " // U+1EE0: LATIN CAPITAL LETTER O WITH HORN AND TILDE
+ + "Ợ" // U+1EE2: LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW
+ + "â" // U+24C4: CIRCLED LATIN CAPITAL LETTER O
+ + "ê" // U+A74A: LATIN CAPITAL LETTER O WITH LONG STROKE OVERLAY
+ + "ê" // U+A74C: LATIN CAPITAL LETTER O WITH LOOP
+ + "O" // U+FF2F: FULLWIDTH LATIN CAPITAL LETTER O
+ ,"O", // Folded result
+
+ "ò" // U+00F2: LATIN SMALL LETTER O WITH GRAVE
+ + "ó" // U+00F3: LATIN SMALL LETTER O WITH ACUTE
+ + "ô" // U+00F4: LATIN SMALL LETTER O WITH CIRCUMFLEX
+ + "õ" // U+00F5: LATIN SMALL LETTER O WITH TILDE
+ + "ö" // U+00F6: LATIN SMALL LETTER O WITH DIAERESIS
+ + "ø" // U+00F8: LATIN SMALL LETTER O WITH STROKE
+ + "Å" // U+014D: LATIN SMALL LETTER O WITH MACRON
+ + "Å" // U+014F: LATIN SMALL LETTER O WITH BREVE
+ + "Å" // U+0151: LATIN SMALL LETTER O WITH DOUBLE ACUTE
+ + "Æ¡" // U+01A1: LATIN SMALL LETTER O WITH HORN
+ + "Ç" // U+01D2: LATIN SMALL LETTER O WITH CARON
+ + "Ç«" // U+01EB: LATIN SMALL LETTER O WITH OGONEK
+ + "Ç" // U+01ED: LATIN SMALL LETTER O WITH OGONEK AND MACRON
+ + "Ç¿" // U+01FF: LATIN SMALL LETTER O WITH STROKE AND ACUTE
+ + "È" // U+020D: LATIN SMALL LETTER O WITH DOUBLE GRAVE
+ + "È" // U+020F: LATIN SMALL LETTER O WITH INVERTED BREVE
+ + "È«" // U+022B: LATIN SMALL LETTER O WITH DIAERESIS AND MACRON
+ + "È" // U+022D: LATIN SMALL LETTER O WITH TILDE AND MACRON
+ + "ȯ" // U+022F: LATIN SMALL LETTER O WITH DOT ABOVE
+ + "ȱ" // U+0231: LATIN SMALL LETTER O WITH DOT ABOVE AND MACRON
+ + "É" // U+0254: LATIN SMALL LETTER OPEN O
+ + "ɵ" // U+0275: LATIN SMALL LETTER BARRED O
+ + "á´" // U+1D16: LATIN SMALL LETTER TOP HALF O
+ + "á´" // U+1D17: LATIN SMALL LETTER BOTTOM HALF O
+ + "á¶" // U+1D97: LATIN SMALL LETTER OPEN O WITH RETROFLEX HOOK
+ + "á¹" // U+1E4D: LATIN SMALL LETTER O WITH TILDE AND ACUTE
+ + "á¹" // U+1E4F: LATIN SMALL LETTER O WITH TILDE AND DIAERESIS
+ + "á¹" // U+1E51: LATIN SMALL LETTER O WITH MACRON AND GRAVE
+ + "á¹" // U+1E53: LATIN SMALL LETTER O WITH MACRON AND ACUTE
+ + "á»" // U+1ECD: LATIN SMALL LETTER O WITH DOT BELOW
+ + "á»" // U+1ECF: LATIN SMALL LETTER O WITH HOOK ABOVE
+ + "á»" // U+1ED1: LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE
+ + "á»" // U+1ED3: LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE
+ + "á»" // U+1ED5: LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE
+ + "á»" // U+1ED7: LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE
+ + "á»" // U+1ED9: LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW
+ + "á»" // U+1EDB: LATIN SMALL LETTER O WITH HORN AND ACUTE
+ + "á»" // U+1EDD: LATIN SMALL LETTER O WITH HORN AND GRAVE
+ + "á»" // U+1EDF: LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE
+ + "ỡ" // U+1EE1: LATIN SMALL LETTER O WITH HORN AND TILDE
+ + "ợ" // U+1EE3: LATIN SMALL LETTER O WITH HORN AND DOT BELOW
+ + "â" // U+2092: LATIN SUBSCRIPT SMALL LETTER O
+ + "â" // U+24DE: CIRCLED LATIN SMALL LETTER O
+ + "ⱺ" // U+2C7A: LATIN SMALL LETTER O WITH LOW RING INSIDE
+ + "ê" // U+A74B: LATIN SMALL LETTER O WITH LONG STROKE OVERLAY
+ + "ê" // U+A74D: LATIN SMALL LETTER O WITH LOOP
+ + "ï½" // U+FF4F: FULLWIDTH LATIN SMALL LETTER O
+ ,"o", // Folded result
+
+ "Å" // U+0152: LATIN CAPITAL LIGATURE OE
+ + "ɶ" // U+0276: LATIN LETTER SMALL CAPITAL OE
+ ,"OE", // Folded result
+
+ "ê" // U+A74E: LATIN CAPITAL LETTER OO
+ ,"OO", // Folded result
+
+ "È¢" // U+0222: LATIN CAPITAL LETTER OU
+ + "á´" // U+1D15: LATIN LETTER SMALL CAPITAL OU
+ ,"OU", // Folded result
+
+ "âª" // U+24AA: PARENTHESIZED LATIN SMALL LETTER O
+ ,"(o)", // Folded result
+
+ "Å" // U+0153: LATIN SMALL LIGATURE OE
+ + "á´" // U+1D14: LATIN SMALL LETTER TURNED OE
+ ,"oe", // Folded result
+
+ "ê" // U+A74F: LATIN SMALL LETTER OO
+ ,"oo", // Folded result
+
+ "È£" // U+0223: LATIN SMALL LETTER OU
+ ,"ou", // Folded result
+
+ "Ƥ" // U+01A4: LATIN CAPITAL LETTER P WITH HOOK
+ + "á´" // U+1D18: LATIN LETTER SMALL CAPITAL P
+ + "á¹" // U+1E54: LATIN CAPITAL LETTER P WITH ACUTE
+ + "á¹" // U+1E56: LATIN CAPITAL LETTER P WITH DOT ABOVE
+ + "â
" // U+24C5: CIRCLED LATIN CAPITAL LETTER P
+ + "â±£" // U+2C63: LATIN CAPITAL LETTER P WITH STROKE
+ + "ê" // U+A750: LATIN CAPITAL LETTER P WITH STROKE THROUGH DESCENDER
+ + "ê" // U+A752: LATIN CAPITAL LETTER P WITH FLOURISH
+ + "ê" // U+A754: LATIN CAPITAL LETTER P WITH SQUIRREL TAIL
+ + "ï¼°" // U+FF30: FULLWIDTH LATIN CAPITAL LETTER P
+ ,"P", // Folded result
+
+ "Æ¥" // U+01A5: LATIN SMALL LETTER P WITH HOOK
+ + "áµ±" // U+1D71: LATIN SMALL LETTER P WITH MIDDLE TILDE
+ + "áµ½" // U+1D7D: LATIN SMALL LETTER P WITH STROKE
+ + "á¶" // U+1D88: LATIN SMALL LETTER P WITH PALATAL HOOK
+ + "á¹" // U+1E55: LATIN SMALL LETTER P WITH ACUTE
+ + "á¹" // U+1E57: LATIN SMALL LETTER P WITH DOT ABOVE
+ + "â" // U+24DF: CIRCLED LATIN SMALL LETTER P
+ + "ê" // U+A751: LATIN SMALL LETTER P WITH STROKE THROUGH DESCENDER
+ + "ê" // U+A753: LATIN SMALL LETTER P WITH FLOURISH
+ + "ê" // U+A755: LATIN SMALL LETTER P WITH SQUIRREL TAIL
+ + "ê¼" // U+A7FC: LATIN EPIGRAPHIC LETTER REVERSED P
+ + "ï½" // U+FF50: FULLWIDTH LATIN SMALL LETTER P
+ ,"p", // Folded result
+
+ "â«" // U+24AB: PARENTHESIZED LATIN SMALL LETTER P
+ ,"(p)", // Folded result
+
+ "É" // U+024A: LATIN CAPITAL LETTER SMALL Q WITH HOOK TAIL
+ + "â" // U+24C6: CIRCLED LATIN CAPITAL LETTER Q
+ + "ê" // U+A756: LATIN CAPITAL LETTER Q WITH STROKE THROUGH DESCENDER
+ + "ê" // U+A758: LATIN CAPITAL LETTER Q WITH DIAGONAL STROKE
+ + "ï¼±" // U+FF31: FULLWIDTH LATIN CAPITAL LETTER Q
+ ,"Q", // Folded result
+
+ "ĸ" // U+0138: LATIN SMALL LETTER KRA
+ + "É" // U+024B: LATIN SMALL LETTER Q WITH HOOK TAIL
+ + "Ê " // U+02A0: LATIN SMALL LETTER Q WITH HOOK
+ + "â " // U+24E0: CIRCLED LATIN SMALL LETTER Q
+ + "ê" // U+A757: LATIN SMALL LETTER Q WITH STROKE THROUGH DESCENDER
+ + "ê" // U+A759: LATIN SMALL LETTER Q WITH DIAGONAL STROKE
+ + "ï½" // U+FF51: FULLWIDTH LATIN SMALL LETTER Q
+ ,"q", // Folded result
+
+ "â¬" // U+24AC: PARENTHESIZED LATIN SMALL LETTER Q
+ ,"(q)", // Folded result
+
+ "ȹ" // U+0239: LATIN SMALL LETTER QP DIGRAPH
+ ,"qp", // Folded result
+
+ "Å" // U+0154: LATIN CAPITAL LETTER R WITH ACUTE
+ + "Å" // U+0156: LATIN CAPITAL LETTER R WITH CEDILLA
+ + "Å" // U+0158: LATIN CAPITAL LETTER R WITH CARON
+ + "È" // U+0210: LATIN CAPITAL LETTER R WITH DOUBLE GRAVE
+ + "È" // U+0212: LATIN CAPITAL LETTER R WITH INVERTED BREVE
+ + "É" // U+024C: LATIN CAPITAL LETTER R WITH STROKE
+ + "Ê" // U+0280: LATIN LETTER SMALL CAPITAL R
+ + "Ê" // U+0281: LATIN LETTER SMALL CAPITAL INVERTED R
+ + "á´" // U+1D19: LATIN LETTER SMALL CAPITAL REVERSED R
+ + "á´" // U+1D1A: LATIN LETTER SMALL CAPITAL TURNED R
+ + "á¹" // U+1E58: LATIN CAPITAL LETTER R WITH DOT ABOVE
+ + "á¹" // U+1E5A: LATIN CAPITAL LETTER R WITH DOT BELOW
+ + "á¹" // U+1E5C: LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON
+ + "á¹" // U+1E5E: LATIN CAPITAL LETTER R WITH LINE BELOW
+ + "â" // U+24C7: CIRCLED LATIN CAPITAL LETTER R
+ + "Ɽ" // U+2C64: LATIN CAPITAL LETTER R WITH TAIL
+ + "ê" // U+A75A: LATIN CAPITAL LETTER R ROTUNDA
+ + "ê" // U+A782: LATIN CAPITAL LETTER INSULAR R
+ + "ï¼²" // U+FF32: FULLWIDTH LATIN CAPITAL LETTER R
+ ,"R", // Folded result
+
+ "Å" // U+0155: LATIN SMALL LETTER R WITH ACUTE
+ + "Å" // U+0157: LATIN SMALL LETTER R WITH CEDILLA
+ + "Å" // U+0159: LATIN SMALL LETTER R WITH CARON
+ + "È" // U+0211: LATIN SMALL LETTER R WITH DOUBLE GRAVE
+ + "È" // U+0213: LATIN SMALL LETTER R WITH INVERTED BREVE
+ + "É" // U+024D: LATIN SMALL LETTER R WITH STROKE
+ + "ɼ" // U+027C: LATIN SMALL LETTER R WITH LONG LEG
+ + "ɽ" // U+027D: LATIN SMALL LETTER R WITH TAIL
+ + "ɾ" // U+027E: LATIN SMALL LETTER R WITH FISHHOOK
+ + "É¿" // U+027F: LATIN SMALL LETTER REVERSED R WITH FISHHOOK
+ + "áµ£" // U+1D63: LATIN SUBSCRIPT SMALL LETTER R
+ + "áµ²" // U+1D72: LATIN SMALL LETTER R WITH MIDDLE TILDE
+ + "áµ³" // U+1D73: LATIN SMALL LETTER R WITH FISHHOOK AND MIDDLE TILDE
+ + "á¶" // U+1D89: LATIN SMALL LETTER R WITH PALATAL HOOK
+ + "á¹" // U+1E59: LATIN SMALL LETTER R WITH DOT ABOVE
+ + "á¹" // U+1E5B: LATIN SMALL LETTER R WITH DOT BELOW
+ + "á¹" // U+1E5D: LATIN SMALL LETTER R WITH DOT BELOW AND MACRON
+ + "á¹" // U+1E5F: LATIN SMALL LETTER R WITH LINE BELOW
+ + "â¡" // U+24E1: CIRCLED LATIN SMALL LETTER R
+ + "ê" // U+A75B: LATIN SMALL LETTER R ROTUNDA
+ + "ê" // U+A783: LATIN SMALL LETTER INSULAR R
+ + "ï½" // U+FF52: FULLWIDTH LATIN SMALL LETTER R
+ ,"r", // Folded result
+
+ "â" // U+24AD: PARENTHESIZED LATIN SMALL LETTER R
+ ,"(r)", // Folded result
+
+ "Å" // U+015A: LATIN CAPITAL LETTER S WITH ACUTE
+ + "Å" // U+015C: LATIN CAPITAL LETTER S WITH CIRCUMFLEX
+ + "Å" // U+015E: LATIN CAPITAL LETTER S WITH CEDILLA
+ + "Å " // U+0160: LATIN CAPITAL LETTER S WITH CARON
+ + "È" // U+0218: LATIN CAPITAL LETTER S WITH COMMA BELOW
+ + "á¹ " // U+1E60: LATIN CAPITAL LETTER S WITH DOT ABOVE
+ + "á¹¢" // U+1E62: LATIN CAPITAL LETTER S WITH DOT BELOW
+ + "Ṥ" // U+1E64: LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE
+ + "Ṧ" // U+1E66: LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE
+ + "Ṩ" // U+1E68: LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE
+ + "â" // U+24C8: CIRCLED LATIN CAPITAL LETTER S
+ + "ê±" // U+A731: LATIN LETTER SMALL CAPITAL S
+ + "ê
" // U+A785: LATIN SMALL LETTER INSULAR S
+ + "ï¼³" // U+FF33: FULLWIDTH LATIN CAPITAL LETTER S
+ ,"S", // Folded result
+
+ "Å" // U+015B: LATIN SMALL LETTER S WITH ACUTE
+ + "Å" // U+015D: LATIN SMALL LETTER S WITH CIRCUMFLEX
+ + "Å" // U+015F: LATIN SMALL LETTER S WITH CEDILLA
+ + "Å¡" // U+0161: LATIN SMALL LETTER S WITH CARON
+ + "Å¿" // U+017F: LATIN SMALL LETTER LONG S
+ + "È" // U+0219: LATIN SMALL LETTER S WITH COMMA BELOW
+ + "È¿" // U+023F: LATIN SMALL LETTER S WITH SWASH TAIL
+ + "Ê" // U+0282: LATIN SMALL LETTER S WITH HOOK
+ + "áµ´" // U+1D74: LATIN SMALL LETTER S WITH MIDDLE TILDE
+ + "á¶" // U+1D8A: LATIN SMALL LETTER S WITH PALATAL HOOK
+ + "ṡ" // U+1E61: LATIN SMALL LETTER S WITH DOT ABOVE
+ + "á¹£" // U+1E63: LATIN SMALL LETTER S WITH DOT BELOW
+ + "á¹¥" // U+1E65: LATIN SMALL LETTER S WITH ACUTE AND DOT ABOVE
+ + "ṧ" // U+1E67: LATIN SMALL LETTER S WITH CARON AND DOT ABOVE
+ + "ṩ" // U+1E69: LATIN SMALL LETTER S WITH DOT BELOW AND DOT ABOVE
+ + "áº" // U+1E9C: LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE
+ + "áº" // U+1E9D: LATIN SMALL LETTER LONG S WITH HIGH STROKE
+ + "â¢" // U+24E2: CIRCLED LATIN SMALL LETTER S
+ + "ê" // U+A784: LATIN CAPITAL LETTER INSULAR S
+ + "ï½" // U+FF53: FULLWIDTH LATIN SMALL LETTER S
+ ,"s", // Folded result
+
+ "áº" // U+1E9E: LATIN CAPITAL LETTER SHARP S
+ ,"SS", // Folded result
+
+ "â®" // U+24AE: PARENTHESIZED LATIN SMALL LETTER S
+ ,"(s)", // Folded result
+
+ "Ã" // U+00DF: LATIN SMALL LETTER SHARP S
+ ,"ss", // Folded result
+
+ "ï¬" // U+FB06: LATIN SMALL LIGATURE ST
+ ,"st", // Folded result
+
+ "Å¢" // U+0162: LATIN CAPITAL LETTER T WITH CEDILLA
+ + "Ť" // U+0164: LATIN CAPITAL LETTER T WITH CARON
+ + "Ŧ" // U+0166: LATIN CAPITAL LETTER T WITH STROKE
+ + "Ƭ" // U+01AC: LATIN CAPITAL LETTER T WITH HOOK
+ + "Æ®" // U+01AE: LATIN CAPITAL LETTER T WITH RETROFLEX HOOK
+ + "È" // U+021A: LATIN CAPITAL LETTER T WITH COMMA BELOW
+ + "Ⱦ" // U+023E: LATIN CAPITAL LETTER T WITH DIAGONAL STROKE
+ + "á´" // U+1D1B: LATIN LETTER SMALL CAPITAL T
+ + "Ṫ" // U+1E6A: LATIN CAPITAL LETTER T WITH DOT ABOVE
+ + "Ṭ" // U+1E6C: LATIN CAPITAL LETTER T WITH DOT BELOW
+ + "á¹®" // U+1E6E: LATIN CAPITAL LETTER T WITH LINE BELOW
+ + "á¹°" // U+1E70: LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW
+ + "â" // U+24C9: CIRCLED LATIN CAPITAL LETTER T
+ + "ê" // U+A786: LATIN CAPITAL LETTER INSULAR T
+ + "ï¼´" // U+FF34: FULLWIDTH LATIN CAPITAL LETTER T
+ ,"T", // Folded result
+
+ "Å£" // U+0163: LATIN SMALL LETTER T WITH CEDILLA
+ + "Å¥" // U+0165: LATIN SMALL LETTER T WITH CARON
+ + "ŧ" // U+0167: LATIN SMALL LETTER T WITH STROKE
+ + "Æ«" // U+01AB: LATIN SMALL LETTER T WITH PALATAL HOOK
+ + "Æ" // U+01AD: LATIN SMALL LETTER T WITH HOOK
+ + "È" // U+021B: LATIN SMALL LETTER T WITH COMMA BELOW
+ + "ȶ" // U+0236: LATIN SMALL LETTER T WITH CURL
+ + "Ê" // U+0287: LATIN SMALL LETTER TURNED T
+ + "Ê" // U+0288: LATIN SMALL LETTER T WITH RETROFLEX HOOK
+ + "áµµ" // U+1D75: LATIN SMALL LETTER T WITH MIDDLE TILDE
+ + "ṫ" // U+1E6B: LATIN SMALL LETTER T WITH DOT ABOVE
+ + "á¹" // U+1E6D: LATIN SMALL LETTER T WITH DOT BELOW
+ + "ṯ" // U+1E6F: LATIN SMALL LETTER T WITH LINE BELOW
+ + "á¹±" // U+1E71: LATIN SMALL LETTER T WITH CIRCUMFLEX BELOW
+ + "áº" // U+1E97: LATIN SMALL LETTER T WITH DIAERESIS
+ + "â£" // U+24E3: CIRCLED LATIN SMALL LETTER T
+ + "ⱦ" // U+2C66: LATIN SMALL LETTER T WITH DIAGONAL STROKE
+ + "ï½" // U+FF54: FULLWIDTH LATIN SMALL LETTER T
+ ,"t", // Folded result
+
+ "Ã" // U+00DE: LATIN CAPITAL LETTER THORN
+ + "ê¦" // U+A766: LATIN CAPITAL LETTER THORN WITH STROKE THROUGH DESCENDER
+ ,"TH", // Folded result
+
+ "ê¨" // U+A728: LATIN CAPITAL LETTER TZ
+ ,"TZ", // Folded result
+
+ "â¯" // U+24AF: PARENTHESIZED LATIN SMALL LETTER T
+ ,"(t)", // Folded result
+
+ "ʨ" // U+02A8: LATIN SMALL LETTER TC DIGRAPH WITH CURL
+ ,"tc", // Folded result
+
+ "þ" // U+00FE: LATIN SMALL LETTER THORN
+ + "ᵺ" // U+1D7A: LATIN SMALL LETTER TH WITH STRIKETHROUGH
+ + "ê§" // U+A767: LATIN SMALL LETTER THORN WITH STROKE THROUGH DESCENDER
+ ,"th", // Folded result
+
+ "ʦ" // U+02A6: LATIN SMALL LETTER TS DIGRAPH
+ ,"ts", // Folded result
+
+ "ê©" // U+A729: LATIN SMALL LETTER TZ
+ ,"tz", // Folded result
+
+ "Ã" // U+00D9: LATIN CAPITAL LETTER U WITH GRAVE
+ + "Ã" // U+00DA: LATIN CAPITAL LETTER U WITH ACUTE
+ + "Ã" // U+00DB: LATIN CAPITAL LETTER U WITH CIRCUMFLEX
+ + "Ã" // U+00DC: LATIN CAPITAL LETTER U WITH DIAERESIS
+ + "Ũ" // U+0168: LATIN CAPITAL LETTER U WITH TILDE
+ + "Ū" // U+016A: LATIN CAPITAL LETTER U WITH MACRON
+ + "Ŭ" // U+016C: LATIN CAPITAL LETTER U WITH BREVE
+ + "Å®" // U+016E: LATIN CAPITAL LETTER U WITH RING ABOVE
+ + "Å°" // U+0170: LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
+ + "Ų" // U+0172: LATIN CAPITAL LETTER U WITH OGONEK
+ + "Ư" // U+01AF: LATIN CAPITAL LETTER U WITH HORN
+ + "Ç" // U+01D3: LATIN CAPITAL LETTER U WITH CARON
+ + "Ç" // U+01D5: LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON
+ + "Ç" // U+01D7: LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE
+ + "Ç" // U+01D9: LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON
+ + "Ç" // U+01DB: LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE
+ + "È" // U+0214: LATIN CAPITAL LETTER U WITH DOUBLE GRAVE
+ + "È" // U+0216: LATIN CAPITAL LETTER U WITH INVERTED BREVE
+ + "É" // U+0244: LATIN CAPITAL LETTER U BAR
+ + "á´" // U+1D1C: LATIN LETTER SMALL CAPITAL U
+ + "áµ¾" // U+1D7E: LATIN SMALL CAPITAL LETTER U WITH STROKE
+ + "á¹²" // U+1E72: LATIN CAPITAL LETTER U WITH DIAERESIS BELOW
+ + "á¹´" // U+1E74: LATIN CAPITAL LETTER U WITH TILDE BELOW
+ + "Ṷ" // U+1E76: LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW
+ + "Ṹ" // U+1E78: LATIN CAPITAL LETTER U WITH TILDE AND ACUTE
+ + "Ṻ" // U+1E7A: LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS
+ + "Ụ" // U+1EE4: LATIN CAPITAL LETTER U WITH DOT BELOW
+ + "Ủ" // U+1EE6: LATIN CAPITAL LETTER U WITH HOOK ABOVE
+ + "Ứ" // U+1EE8: LATIN CAPITAL LETTER U WITH HORN AND ACUTE
+ + "Ừ" // U+1EEA: LATIN CAPITAL LETTER U WITH HORN AND GRAVE
+ + "Ử" // U+1EEC: LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE
+ + "á»®" // U+1EEE: LATIN CAPITAL LETTER U WITH HORN AND TILDE
+ + "á»°" // U+1EF0: LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW
+ + "â" // U+24CA: CIRCLED LATIN CAPITAL LETTER U
+ + "ï¼µ" // U+FF35: FULLWIDTH LATIN CAPITAL LETTER U
+ ,"U", // Folded result
+
+ "ù" // U+00F9: LATIN SMALL LETTER U WITH GRAVE
+ + "ú" // U+00FA: LATIN SMALL LETTER U WITH ACUTE
+ + "û" // U+00FB: LATIN SMALL LETTER U WITH CIRCUMFLEX
+ + "ü" // U+00FC: LATIN SMALL LETTER U WITH DIAERESIS
+ + "Å©" // U+0169: LATIN SMALL LETTER U WITH TILDE
+ + "Å«" // U+016B: LATIN SMALL LETTER U WITH MACRON
+ + "Å" // U+016D: LATIN SMALL LETTER U WITH BREVE
+ + "ů" // U+016F: LATIN SMALL LETTER U WITH RING ABOVE
+ + "ű" // U+0171: LATIN SMALL LETTER U WITH DOUBLE ACUTE
+ + "ų" // U+0173: LATIN SMALL LETTER U WITH OGONEK
+ + "Æ°" // U+01B0: LATIN SMALL LETTER U WITH HORN
+ + "Ç" // U+01D4: LATIN SMALL LETTER U WITH CARON
+ + "Ç" // U+01D6: LATIN SMALL LETTER U WITH DIAERESIS AND MACRON
+ + "Ç" // U+01D8: LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE
+ + "Ç" // U+01DA: LATIN SMALL LETTER U WITH DIAERESIS AND CARON
+ + "Ç" // U+01DC: LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE
+ + "È" // U+0215: LATIN SMALL LETTER U WITH DOUBLE GRAVE
+ + "È" // U+0217: LATIN SMALL LETTER U WITH INVERTED BREVE
+ + "Ê" // U+0289: LATIN SMALL LETTER U BAR
+ + "ᵤ" // U+1D64: LATIN SUBSCRIPT SMALL LETTER U
+ + "á¶" // U+1D99: LATIN SMALL LETTER U WITH RETROFLEX HOOK
+ + "á¹³" // U+1E73: LATIN SMALL LETTER U WITH DIAERESIS BELOW
+ + "á¹µ" // U+1E75: LATIN SMALL LETTER U WITH TILDE BELOW
+ + "á¹·" // U+1E77: LATIN SMALL LETTER U WITH CIRCUMFLEX BELOW
+ + "á¹¹" // U+1E79: LATIN SMALL LETTER U WITH TILDE AND ACUTE
+ + "á¹»" // U+1E7B: LATIN SMALL LETTER U WITH MACRON AND DIAERESIS
+ + "ụ" // U+1EE5: LATIN SMALL LETTER U WITH DOT BELOW
+ + "ủ" // U+1EE7: LATIN SMALL LETTER U WITH HOOK ABOVE
+ + "ứ" // U+1EE9: LATIN SMALL LETTER U WITH HORN AND ACUTE
+ + "ừ" // U+1EEB: LATIN SMALL LETTER U WITH HORN AND GRAVE
+ + "á»" // U+1EED: LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE
+ + "ữ" // U+1EEF: LATIN SMALL LETTER U WITH HORN AND TILDE
+ + "á»±" // U+1EF1: LATIN SMALL LETTER U WITH HORN AND DOT BELOW
+ + "â¤" // U+24E4: CIRCLED LATIN SMALL LETTER U
+ + "ï½" // U+FF55: FULLWIDTH LATIN SMALL LETTER U
+ ,"u", // Folded result
+
+ "â°" // U+24B0: PARENTHESIZED LATIN SMALL LETTER U
+ ,"(u)", // Folded result
+
+ "ᵫ" // U+1D6B: LATIN SMALL LETTER UE
+ ,"ue", // Folded result
+
+ "Ʋ" // U+01B2: LATIN CAPITAL LETTER V WITH HOOK
+ + "É
" // U+0245: LATIN CAPITAL LETTER TURNED V
+ + "á´ " // U+1D20: LATIN LETTER SMALL CAPITAL V
+ + "á¹¼" // U+1E7C: LATIN CAPITAL LETTER V WITH TILDE
+ + "á¹¾" // U+1E7E: LATIN CAPITAL LETTER V WITH DOT BELOW
+ + "Ỽ" // U+1EFC: LATIN CAPITAL LETTER MIDDLE-WELSH V
+ + "â" // U+24CB: CIRCLED LATIN CAPITAL LETTER V
+ + "ê" // U+A75E: LATIN CAPITAL LETTER V WITH DIAGONAL STROKE
+ + "ê¨" // U+A768: LATIN CAPITAL LETTER VEND
+ + "V" // U+FF36: FULLWIDTH LATIN CAPITAL LETTER V
+ ,"V", // Folded result
+
+ "Ê" // U+028B: LATIN SMALL LETTER V WITH HOOK
+ + "Ê" // U+028C: LATIN SMALL LETTER TURNED V
+ + "áµ¥" // U+1D65: LATIN SUBSCRIPT SMALL LETTER V
+ + "á¶" // U+1D8C: LATIN SMALL LETTER V WITH PALATAL HOOK
+ + "á¹½" // U+1E7D: LATIN SMALL LETTER V WITH TILDE
+ + "ṿ" // U+1E7F: LATIN SMALL LETTER V WITH DOT BELOW
+ + "â¥" // U+24E5: CIRCLED LATIN SMALL LETTER V
+ + "â±±" // U+2C71: LATIN SMALL LETTER V WITH RIGHT HOOK
+ + "â±´" // U+2C74: LATIN SMALL LETTER V WITH CURL
+ + "ê" // U+A75F: LATIN SMALL LETTER V WITH DIAGONAL STROKE
+ + "ï½" // U+FF56: FULLWIDTH LATIN SMALL LETTER V
+ ,"v", // Folded result
+
[... 565 lines stripped ...]