1 package org.apache.lucene.analysis;
4 * Licensed to the Apache Software Foundation (ASF) under one or more
5 * contributor license agreements. See the NOTICE file distributed with
6 * this work for additional information regarding copyright ownership.
7 * The ASF licenses this file to You under the Apache License, Version 2.0
8 * (the "License"); you may not use this file except in compliance with
9 * the License. You may obtain a copy of the License at
11 * http://www.apache.org/licenses/LICENSE-2.0
13 * Unless required by applicable law or agreed to in writing, software
14 * distributed under the License is distributed on an "AS IS" BASIS,
15 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 * See the License for the specific language governing permissions and
17 * limitations under the License.
20 import org.apache.lucene.analysis.MockTokenizer;
21 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
22 import java.io.StringReader;
23 import java.util.List;
24 import java.util.ArrayList;
25 import java.util.Iterator;
27 public class TestASCIIFoldingFilter extends BaseTokenStreamTestCase {
29 // testLain1Accents() is a copy of TestLatin1AccentFilter.testU().
30 public void testLatin1Accents() throws Exception {
31 TokenStream stream = new MockTokenizer(new StringReader
32 ("Des mot clés À LA CHAÎNE À Á Â Ã Ä Å Æ Ç È É Ê Ë Ì Í Î Ï IJ Ð Ñ"
33 +" Ò Ó Ô Õ Ö Ø Œ Þ Ù Ú Û Ü Ý Ÿ à á â ã ä å æ ç è é ê ë ì í î ï ij"
34 +" ð ñ ò ó ô õ ö ø œ ß þ ù ú û ü ý ÿ fi fl"), MockTokenizer.WHITESPACE, false);
35 ASCIIFoldingFilter filter = new ASCIIFoldingFilter(stream);
37 CharTermAttribute termAtt = filter.getAttribute(CharTermAttribute.class);
39 assertTermEquals("Des", filter, termAtt);
40 assertTermEquals("mot", filter, termAtt);
41 assertTermEquals("cles", filter, termAtt);
42 assertTermEquals("A", filter, termAtt);
43 assertTermEquals("LA", filter, termAtt);
44 assertTermEquals("CHAINE", filter, termAtt);
45 assertTermEquals("A", filter, termAtt);
46 assertTermEquals("A", filter, termAtt);
47 assertTermEquals("A", filter, termAtt);
48 assertTermEquals("A", filter, termAtt);
49 assertTermEquals("A", filter, termAtt);
50 assertTermEquals("A", filter, termAtt);
51 assertTermEquals("AE", filter, termAtt);
52 assertTermEquals("C", filter, termAtt);
53 assertTermEquals("E", filter, termAtt);
54 assertTermEquals("E", filter, termAtt);
55 assertTermEquals("E", filter, termAtt);
56 assertTermEquals("E", filter, termAtt);
57 assertTermEquals("I", filter, termAtt);
58 assertTermEquals("I", filter, termAtt);
59 assertTermEquals("I", filter, termAtt);
60 assertTermEquals("I", filter, termAtt);
61 assertTermEquals("IJ", filter, termAtt);
62 assertTermEquals("D", filter, termAtt);
63 assertTermEquals("N", filter, termAtt);
64 assertTermEquals("O", filter, termAtt);
65 assertTermEquals("O", filter, termAtt);
66 assertTermEquals("O", filter, termAtt);
67 assertTermEquals("O", filter, termAtt);
68 assertTermEquals("O", filter, termAtt);
69 assertTermEquals("O", filter, termAtt);
70 assertTermEquals("OE", filter, termAtt);
71 assertTermEquals("TH", filter, termAtt);
72 assertTermEquals("U", filter, termAtt);
73 assertTermEquals("U", filter, termAtt);
74 assertTermEquals("U", filter, termAtt);
75 assertTermEquals("U", filter, termAtt);
76 assertTermEquals("Y", filter, termAtt);
77 assertTermEquals("Y", filter, termAtt);
78 assertTermEquals("a", filter, termAtt);
79 assertTermEquals("a", filter, termAtt);
80 assertTermEquals("a", filter, termAtt);
81 assertTermEquals("a", filter, termAtt);
82 assertTermEquals("a", filter, termAtt);
83 assertTermEquals("a", filter, termAtt);
84 assertTermEquals("ae", filter, termAtt);
85 assertTermEquals("c", filter, termAtt);
86 assertTermEquals("e", filter, termAtt);
87 assertTermEquals("e", filter, termAtt);
88 assertTermEquals("e", filter, termAtt);
89 assertTermEquals("e", filter, termAtt);
90 assertTermEquals("i", filter, termAtt);
91 assertTermEquals("i", filter, termAtt);
92 assertTermEquals("i", filter, termAtt);
93 assertTermEquals("i", filter, termAtt);
94 assertTermEquals("ij", filter, termAtt);
95 assertTermEquals("d", filter, termAtt);
96 assertTermEquals("n", filter, termAtt);
97 assertTermEquals("o", filter, termAtt);
98 assertTermEquals("o", filter, termAtt);
99 assertTermEquals("o", filter, termAtt);
100 assertTermEquals("o", filter, termAtt);
101 assertTermEquals("o", filter, termAtt);
102 assertTermEquals("o", filter, termAtt);
103 assertTermEquals("oe", filter, termAtt);
104 assertTermEquals("ss", filter, termAtt);
105 assertTermEquals("th", filter, termAtt);
106 assertTermEquals("u", filter, termAtt);
107 assertTermEquals("u", filter, termAtt);
108 assertTermEquals("u", filter, termAtt);
109 assertTermEquals("u", filter, termAtt);
110 assertTermEquals("y", filter, termAtt);
111 assertTermEquals("y", filter, termAtt);
112 assertTermEquals("fi", filter, termAtt);
113 assertTermEquals("fl", filter, termAtt);
114 assertFalse(filter.incrementToken());
118 // The following Perl script generated the foldings[] array automatically
119 // from ASCIIFoldingFilter.java:
121 // ============== begin get.test.cases.pl ==============
126 // my $file = "ASCIIFoldingFilter.java";
127 // my $output = "testcases.txt";
131 // open IN, "<:utf8", $file || die "Error opening input file '$file': $!";
132 // open OUT, ">:utf8", $output || die "Error opening output file '$output': $!";
134 // while (my $line = <IN>) {
136 // # case '\u0133': // <char> <maybe URL> [ description ]
137 // if ($line =~ /case\s+'\\u(....)':.*\[([^\]]+)\]/) {
140 // $codes{$code} = $desc;
142 // # output[outputPos++] = 'A';
143 // elsif ($line =~ /output\[outputPos\+\+\] = '(.+)';/) {
144 // my $output_char = $1;
145 // $folded .= $output_char;
147 // elsif ($line =~ /break;/ && length($folded) > 0) {
149 // for my $code (sort { hex($a) <=> hex($b) } keys %codes) {
150 // my $desc = $codes{$code};
152 // print OUT '+ ' if (not $first);
154 // print OUT '"', chr(hex($code)), qq!" // U+$code: $desc\n!;
156 // print OUT qq! ,"$folded", // Folded result\n\n!;
163 // ============== end get.test.cases.pl ==============
165 public void testAllFoldings() throws Exception {
166 // Alternating strings of:
167 // 1. All non-ASCII characters to be folded, concatenated together as a
169 // 2. The string of ASCII characters to which each of the above
170 // characters should be folded.
171 String[] foldings = {
172 "À" // U+00C0: LATIN CAPITAL LETTER A WITH GRAVE
173 + "Á" // U+00C1: LATIN CAPITAL LETTER A WITH ACUTE
174 + "Â" // U+00C2: LATIN CAPITAL LETTER A WITH CIRCUMFLEX
175 + "Ã" // U+00C3: LATIN CAPITAL LETTER A WITH TILDE
176 + "Ä" // U+00C4: LATIN CAPITAL LETTER A WITH DIAERESIS
177 + "Å" // U+00C5: LATIN CAPITAL LETTER A WITH RING ABOVE
178 + "Ā" // U+0100: LATIN CAPITAL LETTER A WITH MACRON
179 + "Ă" // U+0102: LATIN CAPITAL LETTER A WITH BREVE
180 + "Ą" // U+0104: LATIN CAPITAL LETTER A WITH OGONEK
181 + "Ə" // U+018F: LATIN CAPITAL LETTER SCHWA
182 + "Ǎ" // U+01CD: LATIN CAPITAL LETTER A WITH CARON
183 + "Ǟ" // U+01DE: LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON
184 + "Ǡ" // U+01E0: LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON
185 + "Ǻ" // U+01FA: LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE
186 + "Ȁ" // U+0200: LATIN CAPITAL LETTER A WITH DOUBLE GRAVE
187 + "Ȃ" // U+0202: LATIN CAPITAL LETTER A WITH INVERTED BREVE
188 + "Ȧ" // U+0226: LATIN CAPITAL LETTER A WITH DOT ABOVE
189 + "Ⱥ" // U+023A: LATIN CAPITAL LETTER A WITH STROKE
190 + "ᴀ" // U+1D00: LATIN LETTER SMALL CAPITAL A
191 + "Ḁ" // U+1E00: LATIN CAPITAL LETTER A WITH RING BELOW
192 + "Ạ" // U+1EA0: LATIN CAPITAL LETTER A WITH DOT BELOW
193 + "Ả" // U+1EA2: LATIN CAPITAL LETTER A WITH HOOK ABOVE
194 + "Ấ" // U+1EA4: LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE
195 + "Ầ" // U+1EA6: LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE
196 + "Ẩ" // U+1EA8: LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE
197 + "Ẫ" // U+1EAA: LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE
198 + "Ậ" // U+1EAC: LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW
199 + "Ắ" // U+1EAE: LATIN CAPITAL LETTER A WITH BREVE AND ACUTE
200 + "Ằ" // U+1EB0: LATIN CAPITAL LETTER A WITH BREVE AND GRAVE
201 + "Ẳ" // U+1EB2: LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE
202 + "Ẵ" // U+1EB4: LATIN CAPITAL LETTER A WITH BREVE AND TILDE
203 + "Ặ" // U+1EB6: LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW
204 + "Ⓐ" // U+24B6: CIRCLED LATIN CAPITAL LETTER A
205 + "A" // U+FF21: FULLWIDTH LATIN CAPITAL LETTER A
206 ,"A", // Folded result
208 "à" // U+00E0: LATIN SMALL LETTER A WITH GRAVE
209 + "á" // U+00E1: LATIN SMALL LETTER A WITH ACUTE
210 + "â" // U+00E2: LATIN SMALL LETTER A WITH CIRCUMFLEX
211 + "ã" // U+00E3: LATIN SMALL LETTER A WITH TILDE
212 + "ä" // U+00E4: LATIN SMALL LETTER A WITH DIAERESIS
213 + "å" // U+00E5: LATIN SMALL LETTER A WITH RING ABOVE
214 + "ā" // U+0101: LATIN SMALL LETTER A WITH MACRON
215 + "ă" // U+0103: LATIN SMALL LETTER A WITH BREVE
216 + "ą" // U+0105: LATIN SMALL LETTER A WITH OGONEK
217 + "ǎ" // U+01CE: LATIN SMALL LETTER A WITH CARON
218 + "ǟ" // U+01DF: LATIN SMALL LETTER A WITH DIAERESIS AND MACRON
219 + "ǡ" // U+01E1: LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON
220 + "ǻ" // U+01FB: LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE
221 + "ȁ" // U+0201: LATIN SMALL LETTER A WITH DOUBLE GRAVE
222 + "ȃ" // U+0203: LATIN SMALL LETTER A WITH INVERTED BREVE
223 + "ȧ" // U+0227: LATIN SMALL LETTER A WITH DOT ABOVE
224 + "ɐ" // U+0250: LATIN SMALL LETTER TURNED A
225 + "ə" // U+0259: LATIN SMALL LETTER SCHWA
226 + "ɚ" // U+025A: LATIN SMALL LETTER SCHWA WITH HOOK
227 + "ᶏ" // U+1D8F: LATIN SMALL LETTER A WITH RETROFLEX HOOK
228 + "ḁ" // U+1E01: LATIN SMALL LETTER A WITH RING BELOW
229 + "ᶕ" // U+1D95: LATIN SMALL LETTER SCHWA WITH RETROFLEX HOOK
230 + "ẚ" // U+1E9A: LATIN SMALL LETTER A WITH RIGHT HALF RING
231 + "ạ" // U+1EA1: LATIN SMALL LETTER A WITH DOT BELOW
232 + "ả" // U+1EA3: LATIN SMALL LETTER A WITH HOOK ABOVE
233 + "ấ" // U+1EA5: LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE
234 + "ầ" // U+1EA7: LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE
235 + "ẩ" // U+1EA9: LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE
236 + "ẫ" // U+1EAB: LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE
237 + "ậ" // U+1EAD: LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW
238 + "ắ" // U+1EAF: LATIN SMALL LETTER A WITH BREVE AND ACUTE
239 + "ằ" // U+1EB1: LATIN SMALL LETTER A WITH BREVE AND GRAVE
240 + "ẳ" // U+1EB3: LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE
241 + "ẵ" // U+1EB5: LATIN SMALL LETTER A WITH BREVE AND TILDE
242 + "ặ" // U+1EB7: LATIN SMALL LETTER A WITH BREVE AND DOT BELOW
243 + "ₐ" // U+2090: LATIN SUBSCRIPT SMALL LETTER A
244 + "ₔ" // U+2094: LATIN SUBSCRIPT SMALL LETTER SCHWA
245 + "ⓐ" // U+24D0: CIRCLED LATIN SMALL LETTER A
246 + "ⱥ" // U+2C65: LATIN SMALL LETTER A WITH STROKE
247 + "Ɐ" // U+2C6F: LATIN CAPITAL LETTER TURNED A
248 + "a" // U+FF41: FULLWIDTH LATIN SMALL LETTER A
249 ,"a", // Folded result
251 "Ꜳ" // U+A732: LATIN CAPITAL LETTER AA
252 ,"AA", // Folded result
254 "Æ" // U+00C6: LATIN CAPITAL LETTER AE
255 + "Ǣ" // U+01E2: LATIN CAPITAL LETTER AE WITH MACRON
256 + "Ǽ" // U+01FC: LATIN CAPITAL LETTER AE WITH ACUTE
257 + "ᴁ" // U+1D01: LATIN LETTER SMALL CAPITAL AE
258 ,"AE", // Folded result
260 "Ꜵ" // U+A734: LATIN CAPITAL LETTER AO
261 ,"AO", // Folded result
263 "Ꜷ" // U+A736: LATIN CAPITAL LETTER AU
264 ,"AU", // Folded result
266 "Ꜹ" // U+A738: LATIN CAPITAL LETTER AV
267 + "Ꜻ" // U+A73A: LATIN CAPITAL LETTER AV WITH HORIZONTAL BAR
268 ,"AV", // Folded result
270 "Ꜽ" // U+A73C: LATIN CAPITAL LETTER AY
271 ,"AY", // Folded result
273 "⒜" // U+249C: PARENTHESIZED LATIN SMALL LETTER A
274 ,"(a)", // Folded result
276 "ꜳ" // U+A733: LATIN SMALL LETTER AA
277 ,"aa", // Folded result
279 "æ" // U+00E6: LATIN SMALL LETTER AE
280 + "ǣ" // U+01E3: LATIN SMALL LETTER AE WITH MACRON
281 + "ǽ" // U+01FD: LATIN SMALL LETTER AE WITH ACUTE
282 + "ᴂ" // U+1D02: LATIN SMALL LETTER TURNED AE
283 ,"ae", // Folded result
285 "ꜵ" // U+A735: LATIN SMALL LETTER AO
286 ,"ao", // Folded result
288 "ꜷ" // U+A737: LATIN SMALL LETTER AU
289 ,"au", // Folded result
291 "ꜹ" // U+A739: LATIN SMALL LETTER AV
292 + "ꜻ" // U+A73B: LATIN SMALL LETTER AV WITH HORIZONTAL BAR
293 ,"av", // Folded result
295 "ꜽ" // U+A73D: LATIN SMALL LETTER AY
296 ,"ay", // Folded result
298 "Ɓ" // U+0181: LATIN CAPITAL LETTER B WITH HOOK
299 + "Ƃ" // U+0182: LATIN CAPITAL LETTER B WITH TOPBAR
300 + "Ƀ" // U+0243: LATIN CAPITAL LETTER B WITH STROKE
301 + "ʙ" // U+0299: LATIN LETTER SMALL CAPITAL B
302 + "ᴃ" // U+1D03: LATIN LETTER SMALL CAPITAL BARRED B
303 + "Ḃ" // U+1E02: LATIN CAPITAL LETTER B WITH DOT ABOVE
304 + "Ḅ" // U+1E04: LATIN CAPITAL LETTER B WITH DOT BELOW
305 + "Ḇ" // U+1E06: LATIN CAPITAL LETTER B WITH LINE BELOW
306 + "Ⓑ" // U+24B7: CIRCLED LATIN CAPITAL LETTER B
307 + "B" // U+FF22: FULLWIDTH LATIN CAPITAL LETTER B
308 ,"B", // Folded result
310 "ƀ" // U+0180: LATIN SMALL LETTER B WITH STROKE
311 + "ƃ" // U+0183: LATIN SMALL LETTER B WITH TOPBAR
312 + "ɓ" // U+0253: LATIN SMALL LETTER B WITH HOOK
313 + "ᵬ" // U+1D6C: LATIN SMALL LETTER B WITH MIDDLE TILDE
314 + "ᶀ" // U+1D80: LATIN SMALL LETTER B WITH PALATAL HOOK
315 + "ḃ" // U+1E03: LATIN SMALL LETTER B WITH DOT ABOVE
316 + "ḅ" // U+1E05: LATIN SMALL LETTER B WITH DOT BELOW
317 + "ḇ" // U+1E07: LATIN SMALL LETTER B WITH LINE BELOW
318 + "ⓑ" // U+24D1: CIRCLED LATIN SMALL LETTER B
319 + "b" // U+FF42: FULLWIDTH LATIN SMALL LETTER B
320 ,"b", // Folded result
322 "⒝" // U+249D: PARENTHESIZED LATIN SMALL LETTER B
323 ,"(b)", // Folded result
325 "Ç" // U+00C7: LATIN CAPITAL LETTER C WITH CEDILLA
326 + "Ć" // U+0106: LATIN CAPITAL LETTER C WITH ACUTE
327 + "Ĉ" // U+0108: LATIN CAPITAL LETTER C WITH CIRCUMFLEX
328 + "Ċ" // U+010A: LATIN CAPITAL LETTER C WITH DOT ABOVE
329 + "Č" // U+010C: LATIN CAPITAL LETTER C WITH CARON
330 + "Ƈ" // U+0187: LATIN CAPITAL LETTER C WITH HOOK
331 + "Ȼ" // U+023B: LATIN CAPITAL LETTER C WITH STROKE
332 + "ʗ" // U+0297: LATIN LETTER STRETCHED C
333 + "ᴄ" // U+1D04: LATIN LETTER SMALL CAPITAL C
334 + "Ḉ" // U+1E08: LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE
335 + "Ⓒ" // U+24B8: CIRCLED LATIN CAPITAL LETTER C
336 + "C" // U+FF23: FULLWIDTH LATIN CAPITAL LETTER C
337 ,"C", // Folded result
339 "ç" // U+00E7: LATIN SMALL LETTER C WITH CEDILLA
340 + "ć" // U+0107: LATIN SMALL LETTER C WITH ACUTE
341 + "ĉ" // U+0109: LATIN SMALL LETTER C WITH CIRCUMFLEX
342 + "ċ" // U+010B: LATIN SMALL LETTER C WITH DOT ABOVE
343 + "č" // U+010D: LATIN SMALL LETTER C WITH CARON
344 + "ƈ" // U+0188: LATIN SMALL LETTER C WITH HOOK
345 + "ȼ" // U+023C: LATIN SMALL LETTER C WITH STROKE
346 + "ɕ" // U+0255: LATIN SMALL LETTER C WITH CURL
347 + "ḉ" // U+1E09: LATIN SMALL LETTER C WITH CEDILLA AND ACUTE
348 + "ↄ" // U+2184: LATIN SMALL LETTER REVERSED C
349 + "ⓒ" // U+24D2: CIRCLED LATIN SMALL LETTER C
350 + "Ꜿ" // U+A73E: LATIN CAPITAL LETTER REVERSED C WITH DOT
351 + "ꜿ" // U+A73F: LATIN SMALL LETTER REVERSED C WITH DOT
352 + "c" // U+FF43: FULLWIDTH LATIN SMALL LETTER C
353 ,"c", // Folded result
355 "⒞" // U+249E: PARENTHESIZED LATIN SMALL LETTER C
356 ,"(c)", // Folded result
358 "Ð" // U+00D0: LATIN CAPITAL LETTER ETH
359 + "Ď" // U+010E: LATIN CAPITAL LETTER D WITH CARON
360 + "Đ" // U+0110: LATIN CAPITAL LETTER D WITH STROKE
361 + "Ɖ" // U+0189: LATIN CAPITAL LETTER AFRICAN D
362 + "Ɗ" // U+018A: LATIN CAPITAL LETTER D WITH HOOK
363 + "Ƌ" // U+018B: LATIN CAPITAL LETTER D WITH TOPBAR
364 + "ᴅ" // U+1D05: LATIN LETTER SMALL CAPITAL D
365 + "ᴆ" // U+1D06: LATIN LETTER SMALL CAPITAL ETH
366 + "Ḋ" // U+1E0A: LATIN CAPITAL LETTER D WITH DOT ABOVE
367 + "Ḍ" // U+1E0C: LATIN CAPITAL LETTER D WITH DOT BELOW
368 + "Ḏ" // U+1E0E: LATIN CAPITAL LETTER D WITH LINE BELOW
369 + "Ḑ" // U+1E10: LATIN CAPITAL LETTER D WITH CEDILLA
370 + "Ḓ" // U+1E12: LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW
371 + "Ⓓ" // U+24B9: CIRCLED LATIN CAPITAL LETTER D
372 + "Ꝺ" // U+A779: LATIN CAPITAL LETTER INSULAR D
373 + "D" // U+FF24: FULLWIDTH LATIN CAPITAL LETTER D
374 ,"D", // Folded result
376 "ð" // U+00F0: LATIN SMALL LETTER ETH
377 + "ď" // U+010F: LATIN SMALL LETTER D WITH CARON
378 + "đ" // U+0111: LATIN SMALL LETTER D WITH STROKE
379 + "ƌ" // U+018C: LATIN SMALL LETTER D WITH TOPBAR
380 + "ȡ" // U+0221: LATIN SMALL LETTER D WITH CURL
381 + "ɖ" // U+0256: LATIN SMALL LETTER D WITH TAIL
382 + "ɗ" // U+0257: LATIN SMALL LETTER D WITH HOOK
383 + "ᵭ" // U+1D6D: LATIN SMALL LETTER D WITH MIDDLE TILDE
384 + "ᶁ" // U+1D81: LATIN SMALL LETTER D WITH PALATAL HOOK
385 + "ᶑ" // U+1D91: LATIN SMALL LETTER D WITH HOOK AND TAIL
386 + "ḋ" // U+1E0B: LATIN SMALL LETTER D WITH DOT ABOVE
387 + "ḍ" // U+1E0D: LATIN SMALL LETTER D WITH DOT BELOW
388 + "ḏ" // U+1E0F: LATIN SMALL LETTER D WITH LINE BELOW
389 + "ḑ" // U+1E11: LATIN SMALL LETTER D WITH CEDILLA
390 + "ḓ" // U+1E13: LATIN SMALL LETTER D WITH CIRCUMFLEX BELOW
391 + "ⓓ" // U+24D3: CIRCLED LATIN SMALL LETTER D
392 + "ꝺ" // U+A77A: LATIN SMALL LETTER INSULAR D
393 + "d" // U+FF44: FULLWIDTH LATIN SMALL LETTER D
394 ,"d", // Folded result
396 "DŽ" // U+01C4: LATIN CAPITAL LETTER DZ WITH CARON
397 + "DZ" // U+01F1: LATIN CAPITAL LETTER DZ
398 ,"DZ", // Folded result
400 "Dž" // U+01C5: LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON
401 + "Dz" // U+01F2: LATIN CAPITAL LETTER D WITH SMALL LETTER Z
402 ,"Dz", // Folded result
404 "⒟" // U+249F: PARENTHESIZED LATIN SMALL LETTER D
405 ,"(d)", // Folded result
407 "ȸ" // U+0238: LATIN SMALL LETTER DB DIGRAPH
408 ,"db", // Folded result
410 "dž" // U+01C6: LATIN SMALL LETTER DZ WITH CARON
411 + "dz" // U+01F3: LATIN SMALL LETTER DZ
412 + "ʣ" // U+02A3: LATIN SMALL LETTER DZ DIGRAPH
413 + "ʥ" // U+02A5: LATIN SMALL LETTER DZ DIGRAPH WITH CURL
414 ,"dz", // Folded result
416 "È" // U+00C8: LATIN CAPITAL LETTER E WITH GRAVE
417 + "É" // U+00C9: LATIN CAPITAL LETTER E WITH ACUTE
418 + "Ê" // U+00CA: LATIN CAPITAL LETTER E WITH CIRCUMFLEX
419 + "Ë" // U+00CB: LATIN CAPITAL LETTER E WITH DIAERESIS
420 + "Ē" // U+0112: LATIN CAPITAL LETTER E WITH MACRON
421 + "Ĕ" // U+0114: LATIN CAPITAL LETTER E WITH BREVE
422 + "Ė" // U+0116: LATIN CAPITAL LETTER E WITH DOT ABOVE
423 + "Ę" // U+0118: LATIN CAPITAL LETTER E WITH OGONEK
424 + "Ě" // U+011A: LATIN CAPITAL LETTER E WITH CARON
425 + "Ǝ" // U+018E: LATIN CAPITAL LETTER REVERSED E
426 + "Ɛ" // U+0190: LATIN CAPITAL LETTER OPEN E
427 + "Ȅ" // U+0204: LATIN CAPITAL LETTER E WITH DOUBLE GRAVE
428 + "Ȇ" // U+0206: LATIN CAPITAL LETTER E WITH INVERTED BREVE
429 + "Ȩ" // U+0228: LATIN CAPITAL LETTER E WITH CEDILLA
430 + "Ɇ" // U+0246: LATIN CAPITAL LETTER E WITH STROKE
431 + "ᴇ" // U+1D07: LATIN LETTER SMALL CAPITAL E
432 + "Ḕ" // U+1E14: LATIN CAPITAL LETTER E WITH MACRON AND GRAVE
433 + "Ḗ" // U+1E16: LATIN CAPITAL LETTER E WITH MACRON AND ACUTE
434 + "Ḙ" // U+1E18: LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW
435 + "Ḛ" // U+1E1A: LATIN CAPITAL LETTER E WITH TILDE BELOW
436 + "Ḝ" // U+1E1C: LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE
437 + "Ẹ" // U+1EB8: LATIN CAPITAL LETTER E WITH DOT BELOW
438 + "Ẻ" // U+1EBA: LATIN CAPITAL LETTER E WITH HOOK ABOVE
439 + "Ẽ" // U+1EBC: LATIN CAPITAL LETTER E WITH TILDE
440 + "Ế" // U+1EBE: LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE
441 + "Ề" // U+1EC0: LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE
442 + "Ể" // U+1EC2: LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE
443 + "Ễ" // U+1EC4: LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE
444 + "Ệ" // U+1EC6: LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW
445 + "Ⓔ" // U+24BA: CIRCLED LATIN CAPITAL LETTER E
446 + "ⱻ" // U+2C7B: LATIN LETTER SMALL CAPITAL TURNED E
447 + "E" // U+FF25: FULLWIDTH LATIN CAPITAL LETTER E
448 ,"E", // Folded result
450 "è" // U+00E8: LATIN SMALL LETTER E WITH GRAVE
451 + "é" // U+00E9: LATIN SMALL LETTER E WITH ACUTE
452 + "ê" // U+00EA: LATIN SMALL LETTER E WITH CIRCUMFLEX
453 + "ë" // U+00EB: LATIN SMALL LETTER E WITH DIAERESIS
454 + "ē" // U+0113: LATIN SMALL LETTER E WITH MACRON
455 + "ĕ" // U+0115: LATIN SMALL LETTER E WITH BREVE
456 + "ė" // U+0117: LATIN SMALL LETTER E WITH DOT ABOVE
457 + "ę" // U+0119: LATIN SMALL LETTER E WITH OGONEK
458 + "ě" // U+011B: LATIN SMALL LETTER E WITH CARON
459 + "ǝ" // U+01DD: LATIN SMALL LETTER TURNED E
460 + "ȅ" // U+0205: LATIN SMALL LETTER E WITH DOUBLE GRAVE
461 + "ȇ" // U+0207: LATIN SMALL LETTER E WITH INVERTED BREVE
462 + "ȩ" // U+0229: LATIN SMALL LETTER E WITH CEDILLA
463 + "ɇ" // U+0247: LATIN SMALL LETTER E WITH STROKE
464 + "ɘ" // U+0258: LATIN SMALL LETTER REVERSED E
465 + "ɛ" // U+025B: LATIN SMALL LETTER OPEN E
466 + "ɜ" // U+025C: LATIN SMALL LETTER REVERSED OPEN E
467 + "ɝ" // U+025D: LATIN SMALL LETTER REVERSED OPEN E WITH HOOK
468 + "ɞ" // U+025E: LATIN SMALL LETTER CLOSED REVERSED OPEN E
469 + "ʚ" // U+029A: LATIN SMALL LETTER CLOSED OPEN E
470 + "ᴈ" // U+1D08: LATIN SMALL LETTER TURNED OPEN E
471 + "ᶒ" // U+1D92: LATIN SMALL LETTER E WITH RETROFLEX HOOK
472 + "ᶓ" // U+1D93: LATIN SMALL LETTER OPEN E WITH RETROFLEX HOOK
473 + "ᶔ" // U+1D94: LATIN SMALL LETTER REVERSED OPEN E WITH RETROFLEX HOOK
474 + "ḕ" // U+1E15: LATIN SMALL LETTER E WITH MACRON AND GRAVE
475 + "ḗ" // U+1E17: LATIN SMALL LETTER E WITH MACRON AND ACUTE
476 + "ḙ" // U+1E19: LATIN SMALL LETTER E WITH CIRCUMFLEX BELOW
477 + "ḛ" // U+1E1B: LATIN SMALL LETTER E WITH TILDE BELOW
478 + "ḝ" // U+1E1D: LATIN SMALL LETTER E WITH CEDILLA AND BREVE
479 + "ẹ" // U+1EB9: LATIN SMALL LETTER E WITH DOT BELOW
480 + "ẻ" // U+1EBB: LATIN SMALL LETTER E WITH HOOK ABOVE
481 + "ẽ" // U+1EBD: LATIN SMALL LETTER E WITH TILDE
482 + "ế" // U+1EBF: LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE
483 + "ề" // U+1EC1: LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE
484 + "ể" // U+1EC3: LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE
485 + "ễ" // U+1EC5: LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE
486 + "ệ" // U+1EC7: LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW
487 + "ₑ" // U+2091: LATIN SUBSCRIPT SMALL LETTER E
488 + "ⓔ" // U+24D4: CIRCLED LATIN SMALL LETTER E
489 + "ⱸ" // U+2C78: LATIN SMALL LETTER E WITH NOTCH
490 + "e" // U+FF45: FULLWIDTH LATIN SMALL LETTER E
491 ,"e", // Folded result
493 "⒠" // U+24A0: PARENTHESIZED LATIN SMALL LETTER E
494 ,"(e)", // Folded result
496 "Ƒ" // U+0191: LATIN CAPITAL LETTER F WITH HOOK
497 + "Ḟ" // U+1E1E: LATIN CAPITAL LETTER F WITH DOT ABOVE
498 + "Ⓕ" // U+24BB: CIRCLED LATIN CAPITAL LETTER F
499 + "ꜰ" // U+A730: LATIN LETTER SMALL CAPITAL F
500 + "Ꝼ" // U+A77B: LATIN CAPITAL LETTER INSULAR F
501 + "ꟻ" // U+A7FB: LATIN EPIGRAPHIC LETTER REVERSED F
502 + "F" // U+FF26: FULLWIDTH LATIN CAPITAL LETTER F
503 ,"F", // Folded result
505 "ƒ" // U+0192: LATIN SMALL LETTER F WITH HOOK
506 + "ᵮ" // U+1D6E: LATIN SMALL LETTER F WITH MIDDLE TILDE
507 + "ᶂ" // U+1D82: LATIN SMALL LETTER F WITH PALATAL HOOK
508 + "ḟ" // U+1E1F: LATIN SMALL LETTER F WITH DOT ABOVE
509 + "ẛ" // U+1E9B: LATIN SMALL LETTER LONG S WITH DOT ABOVE
510 + "ⓕ" // U+24D5: CIRCLED LATIN SMALL LETTER F
511 + "ꝼ" // U+A77C: LATIN SMALL LETTER INSULAR F
512 + "f" // U+FF46: FULLWIDTH LATIN SMALL LETTER F
513 ,"f", // Folded result
515 "⒡" // U+24A1: PARENTHESIZED LATIN SMALL LETTER F
516 ,"(f)", // Folded result
518 "ff" // U+FB00: LATIN SMALL LIGATURE FF
519 ,"ff", // Folded result
521 "ffi" // U+FB03: LATIN SMALL LIGATURE FFI
522 ,"ffi", // Folded result
524 "ffl" // U+FB04: LATIN SMALL LIGATURE FFL
525 ,"ffl", // Folded result
527 "fi" // U+FB01: LATIN SMALL LIGATURE FI
528 ,"fi", // Folded result
530 "fl" // U+FB02: LATIN SMALL LIGATURE FL
531 ,"fl", // Folded result
533 "Ĝ" // U+011C: LATIN CAPITAL LETTER G WITH CIRCUMFLEX
534 + "Ğ" // U+011E: LATIN CAPITAL LETTER G WITH BREVE
535 + "Ġ" // U+0120: LATIN CAPITAL LETTER G WITH DOT ABOVE
536 + "Ģ" // U+0122: LATIN CAPITAL LETTER G WITH CEDILLA
537 + "Ɠ" // U+0193: LATIN CAPITAL LETTER G WITH HOOK
538 + "Ǥ" // U+01E4: LATIN CAPITAL LETTER G WITH STROKE
539 + "ǥ" // U+01E5: LATIN SMALL LETTER G WITH STROKE
540 + "Ǧ" // U+01E6: LATIN CAPITAL LETTER G WITH CARON
541 + "ǧ" // U+01E7: LATIN SMALL LETTER G WITH CARON
542 + "Ǵ" // U+01F4: LATIN CAPITAL LETTER G WITH ACUTE
543 + "ɢ" // U+0262: LATIN LETTER SMALL CAPITAL G
544 + "ʛ" // U+029B: LATIN LETTER SMALL CAPITAL G WITH HOOK
545 + "Ḡ" // U+1E20: LATIN CAPITAL LETTER G WITH MACRON
546 + "Ⓖ" // U+24BC: CIRCLED LATIN CAPITAL LETTER G
547 + "Ᵹ" // U+A77D: LATIN CAPITAL LETTER INSULAR G
548 + "Ꝿ" // U+A77E: LATIN CAPITAL LETTER TURNED INSULAR G
549 + "G" // U+FF27: FULLWIDTH LATIN CAPITAL LETTER G
550 ,"G", // Folded result
552 "ĝ" // U+011D: LATIN SMALL LETTER G WITH CIRCUMFLEX
553 + "ğ" // U+011F: LATIN SMALL LETTER G WITH BREVE
554 + "ġ" // U+0121: LATIN SMALL LETTER G WITH DOT ABOVE
555 + "ģ" // U+0123: LATIN SMALL LETTER G WITH CEDILLA
556 + "ǵ" // U+01F5: LATIN SMALL LETTER G WITH ACUTE
557 + "ɠ" // U+0260: LATIN SMALL LETTER G WITH HOOK
558 + "ɡ" // U+0261: LATIN SMALL LETTER SCRIPT G
559 + "ᵷ" // U+1D77: LATIN SMALL LETTER TURNED G
560 + "ᵹ" // U+1D79: LATIN SMALL LETTER INSULAR G
561 + "ᶃ" // U+1D83: LATIN SMALL LETTER G WITH PALATAL HOOK
562 + "ḡ" // U+1E21: LATIN SMALL LETTER G WITH MACRON
563 + "ⓖ" // U+24D6: CIRCLED LATIN SMALL LETTER G
564 + "ꝿ" // U+A77F: LATIN SMALL LETTER TURNED INSULAR G
565 + "g" // U+FF47: FULLWIDTH LATIN SMALL LETTER G
566 ,"g", // Folded result
568 "⒢" // U+24A2: PARENTHESIZED LATIN SMALL LETTER G
569 ,"(g)", // Folded result
571 "Ĥ" // U+0124: LATIN CAPITAL LETTER H WITH CIRCUMFLEX
572 + "Ħ" // U+0126: LATIN CAPITAL LETTER H WITH STROKE
573 + "Ȟ" // U+021E: LATIN CAPITAL LETTER H WITH CARON
574 + "ʜ" // U+029C: LATIN LETTER SMALL CAPITAL H
575 + "Ḣ" // U+1E22: LATIN CAPITAL LETTER H WITH DOT ABOVE
576 + "Ḥ" // U+1E24: LATIN CAPITAL LETTER H WITH DOT BELOW
577 + "Ḧ" // U+1E26: LATIN CAPITAL LETTER H WITH DIAERESIS
578 + "Ḩ" // U+1E28: LATIN CAPITAL LETTER H WITH CEDILLA
579 + "Ḫ" // U+1E2A: LATIN CAPITAL LETTER H WITH BREVE BELOW
580 + "Ⓗ" // U+24BD: CIRCLED LATIN CAPITAL LETTER H
581 + "Ⱨ" // U+2C67: LATIN CAPITAL LETTER H WITH DESCENDER
582 + "Ⱶ" // U+2C75: LATIN CAPITAL LETTER HALF H
583 + "H" // U+FF28: FULLWIDTH LATIN CAPITAL LETTER H
584 ,"H", // Folded result
586 "ĥ" // U+0125: LATIN SMALL LETTER H WITH CIRCUMFLEX
587 + "ħ" // U+0127: LATIN SMALL LETTER H WITH STROKE
588 + "ȟ" // U+021F: LATIN SMALL LETTER H WITH CARON
589 + "ɥ" // U+0265: LATIN SMALL LETTER TURNED H
590 + "ɦ" // U+0266: LATIN SMALL LETTER H WITH HOOK
591 + "ʮ" // U+02AE: LATIN SMALL LETTER TURNED H WITH FISHHOOK
592 + "ʯ" // U+02AF: LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL
593 + "ḣ" // U+1E23: LATIN SMALL LETTER H WITH DOT ABOVE
594 + "ḥ" // U+1E25: LATIN SMALL LETTER H WITH DOT BELOW
595 + "ḧ" // U+1E27: LATIN SMALL LETTER H WITH DIAERESIS
596 + "ḩ" // U+1E29: LATIN SMALL LETTER H WITH CEDILLA
597 + "ḫ" // U+1E2B: LATIN SMALL LETTER H WITH BREVE BELOW
598 + "ẖ" // U+1E96: LATIN SMALL LETTER H WITH LINE BELOW
599 + "ⓗ" // U+24D7: CIRCLED LATIN SMALL LETTER H
600 + "ⱨ" // U+2C68: LATIN SMALL LETTER H WITH DESCENDER
601 + "ⱶ" // U+2C76: LATIN SMALL LETTER HALF H
602 + "h" // U+FF48: FULLWIDTH LATIN SMALL LETTER H
603 ,"h", // Folded result
605 "Ƕ" // U+01F6: LATIN CAPITAL LETTER HWAIR
606 ,"HV", // Folded result
608 "⒣" // U+24A3: PARENTHESIZED LATIN SMALL LETTER H
609 ,"(h)", // Folded result
611 "ƕ" // U+0195: LATIN SMALL LETTER HV
612 ,"hv", // Folded result
614 "Ì" // U+00CC: LATIN CAPITAL LETTER I WITH GRAVE
615 + "Í" // U+00CD: LATIN CAPITAL LETTER I WITH ACUTE
616 + "Î" // U+00CE: LATIN CAPITAL LETTER I WITH CIRCUMFLEX
617 + "Ï" // U+00CF: LATIN CAPITAL LETTER I WITH DIAERESIS
618 + "Ĩ" // U+0128: LATIN CAPITAL LETTER I WITH TILDE
619 + "Ī" // U+012A: LATIN CAPITAL LETTER I WITH MACRON
620 + "Ĭ" // U+012C: LATIN CAPITAL LETTER I WITH BREVE
621 + "Į" // U+012E: LATIN CAPITAL LETTER I WITH OGONEK
622 + "İ" // U+0130: LATIN CAPITAL LETTER I WITH DOT ABOVE
623 + "Ɩ" // U+0196: LATIN CAPITAL LETTER IOTA
624 + "Ɨ" // U+0197: LATIN CAPITAL LETTER I WITH STROKE
625 + "Ǐ" // U+01CF: LATIN CAPITAL LETTER I WITH CARON
626 + "Ȉ" // U+0208: LATIN CAPITAL LETTER I WITH DOUBLE GRAVE
627 + "Ȋ" // U+020A: LATIN CAPITAL LETTER I WITH INVERTED BREVE
628 + "ɪ" // U+026A: LATIN LETTER SMALL CAPITAL I
629 + "ᵻ" // U+1D7B: LATIN SMALL CAPITAL LETTER I WITH STROKE
630 + "Ḭ" // U+1E2C: LATIN CAPITAL LETTER I WITH TILDE BELOW
631 + "Ḯ" // U+1E2E: LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE
632 + "Ỉ" // U+1EC8: LATIN CAPITAL LETTER I WITH HOOK ABOVE
633 + "Ị" // U+1ECA: LATIN CAPITAL LETTER I WITH DOT BELOW
634 + "Ⓘ" // U+24BE: CIRCLED LATIN CAPITAL LETTER I
635 + "ꟾ" // U+A7FE: LATIN EPIGRAPHIC LETTER I LONGA
636 + "I" // U+FF29: FULLWIDTH LATIN CAPITAL LETTER I
637 ,"I", // Folded result
639 "ì" // U+00EC: LATIN SMALL LETTER I WITH GRAVE
640 + "í" // U+00ED: LATIN SMALL LETTER I WITH ACUTE
641 + "î" // U+00EE: LATIN SMALL LETTER I WITH CIRCUMFLEX
642 + "ï" // U+00EF: LATIN SMALL LETTER I WITH DIAERESIS
643 + "ĩ" // U+0129: LATIN SMALL LETTER I WITH TILDE
644 + "ī" // U+012B: LATIN SMALL LETTER I WITH MACRON
645 + "ĭ" // U+012D: LATIN SMALL LETTER I WITH BREVE
646 + "į" // U+012F: LATIN SMALL LETTER I WITH OGONEK
647 + "ı" // U+0131: LATIN SMALL LETTER DOTLESS I
648 + "ǐ" // U+01D0: LATIN SMALL LETTER I WITH CARON
649 + "ȉ" // U+0209: LATIN SMALL LETTER I WITH DOUBLE GRAVE
650 + "ȋ" // U+020B: LATIN SMALL LETTER I WITH INVERTED BREVE
651 + "ɨ" // U+0268: LATIN SMALL LETTER I WITH STROKE
652 + "ᴉ" // U+1D09: LATIN SMALL LETTER TURNED I
653 + "ᵢ" // U+1D62: LATIN SUBSCRIPT SMALL LETTER I
654 + "ᵼ" // U+1D7C: LATIN SMALL LETTER IOTA WITH STROKE
655 + "ᶖ" // U+1D96: LATIN SMALL LETTER I WITH RETROFLEX HOOK
656 + "ḭ" // U+1E2D: LATIN SMALL LETTER I WITH TILDE BELOW
657 + "ḯ" // U+1E2F: LATIN SMALL LETTER I WITH DIAERESIS AND ACUTE
658 + "ỉ" // U+1EC9: LATIN SMALL LETTER I WITH HOOK ABOVE
659 + "ị" // U+1ECB: LATIN SMALL LETTER I WITH DOT BELOW
660 + "ⁱ" // U+2071: SUPERSCRIPT LATIN SMALL LETTER I
661 + "ⓘ" // U+24D8: CIRCLED LATIN SMALL LETTER I
662 + "i" // U+FF49: FULLWIDTH LATIN SMALL LETTER I
663 ,"i", // Folded result
665 "IJ" // U+0132: LATIN CAPITAL LIGATURE IJ
666 ,"IJ", // Folded result
668 "⒤" // U+24A4: PARENTHESIZED LATIN SMALL LETTER I
669 ,"(i)", // Folded result
671 "ij" // U+0133: LATIN SMALL LIGATURE IJ
672 ,"ij", // Folded result
674 "Ĵ" // U+0134: LATIN CAPITAL LETTER J WITH CIRCUMFLEX
675 + "Ɉ" // U+0248: LATIN CAPITAL LETTER J WITH STROKE
676 + "ᴊ" // U+1D0A: LATIN LETTER SMALL CAPITAL J
677 + "Ⓙ" // U+24BF: CIRCLED LATIN CAPITAL LETTER J
678 + "J" // U+FF2A: FULLWIDTH LATIN CAPITAL LETTER J
679 ,"J", // Folded result
681 "ĵ" // U+0135: LATIN SMALL LETTER J WITH CIRCUMFLEX
682 + "ǰ" // U+01F0: LATIN SMALL LETTER J WITH CARON
683 + "ȷ" // U+0237: LATIN SMALL LETTER DOTLESS J
684 + "ɉ" // U+0249: LATIN SMALL LETTER J WITH STROKE
685 + "ɟ" // U+025F: LATIN SMALL LETTER DOTLESS J WITH STROKE
686 + "ʄ" // U+0284: LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK
687 + "ʝ" // U+029D: LATIN SMALL LETTER J WITH CROSSED-TAIL
688 + "ⓙ" // U+24D9: CIRCLED LATIN SMALL LETTER J
689 + "ⱼ" // U+2C7C: LATIN SUBSCRIPT SMALL LETTER J
690 + "j" // U+FF4A: FULLWIDTH LATIN SMALL LETTER J
691 ,"j", // Folded result
693 "⒥" // U+24A5: PARENTHESIZED LATIN SMALL LETTER J
694 ,"(j)", // Folded result
696 "Ķ" // U+0136: LATIN CAPITAL LETTER K WITH CEDILLA
697 + "Ƙ" // U+0198: LATIN CAPITAL LETTER K WITH HOOK
698 + "Ǩ" // U+01E8: LATIN CAPITAL LETTER K WITH CARON
699 + "ᴋ" // U+1D0B: LATIN LETTER SMALL CAPITAL K
700 + "Ḱ" // U+1E30: LATIN CAPITAL LETTER K WITH ACUTE
701 + "Ḳ" // U+1E32: LATIN CAPITAL LETTER K WITH DOT BELOW
702 + "Ḵ" // U+1E34: LATIN CAPITAL LETTER K WITH LINE BELOW
703 + "Ⓚ" // U+24C0: CIRCLED LATIN CAPITAL LETTER K
704 + "Ⱪ" // U+2C69: LATIN CAPITAL LETTER K WITH DESCENDER
705 + "Ꝁ" // U+A740: LATIN CAPITAL LETTER K WITH STROKE
706 + "Ꝃ" // U+A742: LATIN CAPITAL LETTER K WITH DIAGONAL STROKE
707 + "Ꝅ" // U+A744: LATIN CAPITAL LETTER K WITH STROKE AND DIAGONAL STROKE
708 + "K" // U+FF2B: FULLWIDTH LATIN CAPITAL LETTER K
709 ,"K", // Folded result
711 "ķ" // U+0137: LATIN SMALL LETTER K WITH CEDILLA
712 + "ƙ" // U+0199: LATIN SMALL LETTER K WITH HOOK
713 + "ǩ" // U+01E9: LATIN SMALL LETTER K WITH CARON
714 + "ʞ" // U+029E: LATIN SMALL LETTER TURNED K
715 + "ᶄ" // U+1D84: LATIN SMALL LETTER K WITH PALATAL HOOK
716 + "ḱ" // U+1E31: LATIN SMALL LETTER K WITH ACUTE
717 + "ḳ" // U+1E33: LATIN SMALL LETTER K WITH DOT BELOW
718 + "ḵ" // U+1E35: LATIN SMALL LETTER K WITH LINE BELOW
719 + "ⓚ" // U+24DA: CIRCLED LATIN SMALL LETTER K
720 + "ⱪ" // U+2C6A: LATIN SMALL LETTER K WITH DESCENDER
721 + "ꝁ" // U+A741: LATIN SMALL LETTER K WITH STROKE
722 + "ꝃ" // U+A743: LATIN SMALL LETTER K WITH DIAGONAL STROKE
723 + "ꝅ" // U+A745: LATIN SMALL LETTER K WITH STROKE AND DIAGONAL STROKE
724 + "k" // U+FF4B: FULLWIDTH LATIN SMALL LETTER K
725 ,"k", // Folded result
727 "⒦" // U+24A6: PARENTHESIZED LATIN SMALL LETTER K
728 ,"(k)", // Folded result
730 "Ĺ" // U+0139: LATIN CAPITAL LETTER L WITH ACUTE
731 + "Ļ" // U+013B: LATIN CAPITAL LETTER L WITH CEDILLA
732 + "Ľ" // U+013D: LATIN CAPITAL LETTER L WITH CARON
733 + "Ŀ" // U+013F: LATIN CAPITAL LETTER L WITH MIDDLE DOT
734 + "Ł" // U+0141: LATIN CAPITAL LETTER L WITH STROKE
735 + "Ƚ" // U+023D: LATIN CAPITAL LETTER L WITH BAR
736 + "ʟ" // U+029F: LATIN LETTER SMALL CAPITAL L
737 + "ᴌ" // U+1D0C: LATIN LETTER SMALL CAPITAL L WITH STROKE
738 + "Ḷ" // U+1E36: LATIN CAPITAL LETTER L WITH DOT BELOW
739 + "Ḹ" // U+1E38: LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON
740 + "Ḻ" // U+1E3A: LATIN CAPITAL LETTER L WITH LINE BELOW
741 + "Ḽ" // U+1E3C: LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW
742 + "Ⓛ" // U+24C1: CIRCLED LATIN CAPITAL LETTER L
743 + "Ⱡ" // U+2C60: LATIN CAPITAL LETTER L WITH DOUBLE BAR
744 + "Ɫ" // U+2C62: LATIN CAPITAL LETTER L WITH MIDDLE TILDE
745 + "Ꝇ" // U+A746: LATIN CAPITAL LETTER BROKEN L
746 + "Ꝉ" // U+A748: LATIN CAPITAL LETTER L WITH HIGH STROKE
747 + "Ꞁ" // U+A780: LATIN CAPITAL LETTER TURNED L
748 + "L" // U+FF2C: FULLWIDTH LATIN CAPITAL LETTER L
749 ,"L", // Folded result
751 "ĺ" // U+013A: LATIN SMALL LETTER L WITH ACUTE
752 + "ļ" // U+013C: LATIN SMALL LETTER L WITH CEDILLA
753 + "ľ" // U+013E: LATIN SMALL LETTER L WITH CARON
754 + "ŀ" // U+0140: LATIN SMALL LETTER L WITH MIDDLE DOT
755 + "ł" // U+0142: LATIN SMALL LETTER L WITH STROKE
756 + "ƚ" // U+019A: LATIN SMALL LETTER L WITH BAR
757 + "ȴ" // U+0234: LATIN SMALL LETTER L WITH CURL
758 + "ɫ" // U+026B: LATIN SMALL LETTER L WITH MIDDLE TILDE
759 + "ɬ" // U+026C: LATIN SMALL LETTER L WITH BELT
760 + "ɭ" // U+026D: LATIN SMALL LETTER L WITH RETROFLEX HOOK
761 + "ᶅ" // U+1D85: LATIN SMALL LETTER L WITH PALATAL HOOK
762 + "ḷ" // U+1E37: LATIN SMALL LETTER L WITH DOT BELOW
763 + "ḹ" // U+1E39: LATIN SMALL LETTER L WITH DOT BELOW AND MACRON
764 + "ḻ" // U+1E3B: LATIN SMALL LETTER L WITH LINE BELOW
765 + "ḽ" // U+1E3D: LATIN SMALL LETTER L WITH CIRCUMFLEX BELOW
766 + "ⓛ" // U+24DB: CIRCLED LATIN SMALL LETTER L
767 + "ⱡ" // U+2C61: LATIN SMALL LETTER L WITH DOUBLE BAR
768 + "ꝇ" // U+A747: LATIN SMALL LETTER BROKEN L
769 + "ꝉ" // U+A749: LATIN SMALL LETTER L WITH HIGH STROKE
770 + "ꞁ" // U+A781: LATIN SMALL LETTER TURNED L
771 + "l" // U+FF4C: FULLWIDTH LATIN SMALL LETTER L
772 ,"l", // Folded result
774 "LJ" // U+01C7: LATIN CAPITAL LETTER LJ
775 ,"LJ", // Folded result
777 "Ỻ" // U+1EFA: LATIN CAPITAL LETTER MIDDLE-WELSH LL
778 ,"LL", // Folded result
780 "Lj" // U+01C8: LATIN CAPITAL LETTER L WITH SMALL LETTER J
781 ,"Lj", // Folded result
783 "⒧" // U+24A7: PARENTHESIZED LATIN SMALL LETTER L
784 ,"(l)", // Folded result
786 "lj" // U+01C9: LATIN SMALL LETTER LJ
787 ,"lj", // Folded result
789 "ỻ" // U+1EFB: LATIN SMALL LETTER MIDDLE-WELSH LL
790 ,"ll", // Folded result
792 "ʪ" // U+02AA: LATIN SMALL LETTER LS DIGRAPH
793 ,"ls", // Folded result
795 "ʫ" // U+02AB: LATIN SMALL LETTER LZ DIGRAPH
796 ,"lz", // Folded result
798 "Ɯ" // U+019C: LATIN CAPITAL LETTER TURNED M
799 + "ᴍ" // U+1D0D: LATIN LETTER SMALL CAPITAL M
800 + "Ḿ" // U+1E3E: LATIN CAPITAL LETTER M WITH ACUTE
801 + "Ṁ" // U+1E40: LATIN CAPITAL LETTER M WITH DOT ABOVE
802 + "Ṃ" // U+1E42: LATIN CAPITAL LETTER M WITH DOT BELOW
803 + "Ⓜ" // U+24C2: CIRCLED LATIN CAPITAL LETTER M
804 + "Ɱ" // U+2C6E: LATIN CAPITAL LETTER M WITH HOOK
805 + "ꟽ" // U+A7FD: LATIN EPIGRAPHIC LETTER INVERTED M
806 + "ꟿ" // U+A7FF: LATIN EPIGRAPHIC LETTER ARCHAIC M
807 + "M" // U+FF2D: FULLWIDTH LATIN CAPITAL LETTER M
808 ,"M", // Folded result
810 "ɯ" // U+026F: LATIN SMALL LETTER TURNED M
811 + "ɰ" // U+0270: LATIN SMALL LETTER TURNED M WITH LONG LEG
812 + "ɱ" // U+0271: LATIN SMALL LETTER M WITH HOOK
813 + "ᵯ" // U+1D6F: LATIN SMALL LETTER M WITH MIDDLE TILDE
814 + "ᶆ" // U+1D86: LATIN SMALL LETTER M WITH PALATAL HOOK
815 + "ḿ" // U+1E3F: LATIN SMALL LETTER M WITH ACUTE
816 + "ṁ" // U+1E41: LATIN SMALL LETTER M WITH DOT ABOVE
817 + "ṃ" // U+1E43: LATIN SMALL LETTER M WITH DOT BELOW
818 + "ⓜ" // U+24DC: CIRCLED LATIN SMALL LETTER M
819 + "m" // U+FF4D: FULLWIDTH LATIN SMALL LETTER M
820 ,"m", // Folded result
822 "⒨" // U+24A8: PARENTHESIZED LATIN SMALL LETTER M
823 ,"(m)", // Folded result
825 "Ñ" // U+00D1: LATIN CAPITAL LETTER N WITH TILDE
826 + "Ń" // U+0143: LATIN CAPITAL LETTER N WITH ACUTE
827 + "Ņ" // U+0145: LATIN CAPITAL LETTER N WITH CEDILLA
828 + "Ň" // U+0147: LATIN CAPITAL LETTER N WITH CARON
829 + "Ŋ" // U+014A: LATIN CAPITAL LETTER ENG
830 + "Ɲ" // U+019D: LATIN CAPITAL LETTER N WITH LEFT HOOK
831 + "Ǹ" // U+01F8: LATIN CAPITAL LETTER N WITH GRAVE
832 + "Ƞ" // U+0220: LATIN CAPITAL LETTER N WITH LONG RIGHT LEG
833 + "ɴ" // U+0274: LATIN LETTER SMALL CAPITAL N
834 + "ᴎ" // U+1D0E: LATIN LETTER SMALL CAPITAL REVERSED N
835 + "Ṅ" // U+1E44: LATIN CAPITAL LETTER N WITH DOT ABOVE
836 + "Ṇ" // U+1E46: LATIN CAPITAL LETTER N WITH DOT BELOW
837 + "Ṉ" // U+1E48: LATIN CAPITAL LETTER N WITH LINE BELOW
838 + "Ṋ" // U+1E4A: LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW
839 + "Ⓝ" // U+24C3: CIRCLED LATIN CAPITAL LETTER N
840 + "N" // U+FF2E: FULLWIDTH LATIN CAPITAL LETTER N
841 ,"N", // Folded result
843 "ñ" // U+00F1: LATIN SMALL LETTER N WITH TILDE
844 + "ń" // U+0144: LATIN SMALL LETTER N WITH ACUTE
845 + "ņ" // U+0146: LATIN SMALL LETTER N WITH CEDILLA
846 + "ň" // U+0148: LATIN SMALL LETTER N WITH CARON
847 + "ʼn" // U+0149: LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
848 + "ŋ" // U+014B: LATIN SMALL LETTER ENG
849 + "ƞ" // U+019E: LATIN SMALL LETTER N WITH LONG RIGHT LEG
850 + "ǹ" // U+01F9: LATIN SMALL LETTER N WITH GRAVE
851 + "ȵ" // U+0235: LATIN SMALL LETTER N WITH CURL
852 + "ɲ" // U+0272: LATIN SMALL LETTER N WITH LEFT HOOK
853 + "ɳ" // U+0273: LATIN SMALL LETTER N WITH RETROFLEX HOOK
854 + "ᵰ" // U+1D70: LATIN SMALL LETTER N WITH MIDDLE TILDE
855 + "ᶇ" // U+1D87: LATIN SMALL LETTER N WITH PALATAL HOOK
856 + "ṅ" // U+1E45: LATIN SMALL LETTER N WITH DOT ABOVE
857 + "ṇ" // U+1E47: LATIN SMALL LETTER N WITH DOT BELOW
858 + "ṉ" // U+1E49: LATIN SMALL LETTER N WITH LINE BELOW
859 + "ṋ" // U+1E4B: LATIN SMALL LETTER N WITH CIRCUMFLEX BELOW
860 + "ⁿ" // U+207F: SUPERSCRIPT LATIN SMALL LETTER N
861 + "ⓝ" // U+24DD: CIRCLED LATIN SMALL LETTER N
862 + "n" // U+FF4E: FULLWIDTH LATIN SMALL LETTER N
863 ,"n", // Folded result
865 "NJ" // U+01CA: LATIN CAPITAL LETTER NJ
866 ,"NJ", // Folded result
868 "Nj" // U+01CB: LATIN CAPITAL LETTER N WITH SMALL LETTER J
869 ,"Nj", // Folded result
871 "⒩" // U+24A9: PARENTHESIZED LATIN SMALL LETTER N
872 ,"(n)", // Folded result
874 "nj" // U+01CC: LATIN SMALL LETTER NJ
875 ,"nj", // Folded result
877 "Ò" // U+00D2: LATIN CAPITAL LETTER O WITH GRAVE
878 + "Ó" // U+00D3: LATIN CAPITAL LETTER O WITH ACUTE
879 + "Ô" // U+00D4: LATIN CAPITAL LETTER O WITH CIRCUMFLEX
880 + "Õ" // U+00D5: LATIN CAPITAL LETTER O WITH TILDE
881 + "Ö" // U+00D6: LATIN CAPITAL LETTER O WITH DIAERESIS
882 + "Ø" // U+00D8: LATIN CAPITAL LETTER O WITH STROKE
883 + "Ō" // U+014C: LATIN CAPITAL LETTER O WITH MACRON
884 + "Ŏ" // U+014E: LATIN CAPITAL LETTER O WITH BREVE
885 + "Ő" // U+0150: LATIN CAPITAL LETTER O WITH DOUBLE ACUTE
886 + "Ɔ" // U+0186: LATIN CAPITAL LETTER OPEN O
887 + "Ɵ" // U+019F: LATIN CAPITAL LETTER O WITH MIDDLE TILDE
888 + "Ơ" // U+01A0: LATIN CAPITAL LETTER O WITH HORN
889 + "Ǒ" // U+01D1: LATIN CAPITAL LETTER O WITH CARON
890 + "Ǫ" // U+01EA: LATIN CAPITAL LETTER O WITH OGONEK
891 + "Ǭ" // U+01EC: LATIN CAPITAL LETTER O WITH OGONEK AND MACRON
892 + "Ǿ" // U+01FE: LATIN CAPITAL LETTER O WITH STROKE AND ACUTE
893 + "Ȍ" // U+020C: LATIN CAPITAL LETTER O WITH DOUBLE GRAVE
894 + "Ȏ" // U+020E: LATIN CAPITAL LETTER O WITH INVERTED BREVE
895 + "Ȫ" // U+022A: LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON
896 + "Ȭ" // U+022C: LATIN CAPITAL LETTER O WITH TILDE AND MACRON
897 + "Ȯ" // U+022E: LATIN CAPITAL LETTER O WITH DOT ABOVE
898 + "Ȱ" // U+0230: LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON
899 + "ᴏ" // U+1D0F: LATIN LETTER SMALL CAPITAL O
900 + "ᴐ" // U+1D10: LATIN LETTER SMALL CAPITAL OPEN O
901 + "Ṍ" // U+1E4C: LATIN CAPITAL LETTER O WITH TILDE AND ACUTE
902 + "Ṏ" // U+1E4E: LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS
903 + "Ṑ" // U+1E50: LATIN CAPITAL LETTER O WITH MACRON AND GRAVE
904 + "Ṓ" // U+1E52: LATIN CAPITAL LETTER O WITH MACRON AND ACUTE
905 + "Ọ" // U+1ECC: LATIN CAPITAL LETTER O WITH DOT BELOW
906 + "Ỏ" // U+1ECE: LATIN CAPITAL LETTER O WITH HOOK ABOVE
907 + "Ố" // U+1ED0: LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE
908 + "Ồ" // U+1ED2: LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE
909 + "Ổ" // U+1ED4: LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE
910 + "Ỗ" // U+1ED6: LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE
911 + "Ộ" // U+1ED8: LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW
912 + "Ớ" // U+1EDA: LATIN CAPITAL LETTER O WITH HORN AND ACUTE
913 + "Ờ" // U+1EDC: LATIN CAPITAL LETTER O WITH HORN AND GRAVE
914 + "Ở" // U+1EDE: LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE
915 + "Ỡ" // U+1EE0: LATIN CAPITAL LETTER O WITH HORN AND TILDE
916 + "Ợ" // U+1EE2: LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW
917 + "Ⓞ" // U+24C4: CIRCLED LATIN CAPITAL LETTER O
918 + "Ꝋ" // U+A74A: LATIN CAPITAL LETTER O WITH LONG STROKE OVERLAY
919 + "Ꝍ" // U+A74C: LATIN CAPITAL LETTER O WITH LOOP
920 + "O" // U+FF2F: FULLWIDTH LATIN CAPITAL LETTER O
921 ,"O", // Folded result
923 "ò" // U+00F2: LATIN SMALL LETTER O WITH GRAVE
924 + "ó" // U+00F3: LATIN SMALL LETTER O WITH ACUTE
925 + "ô" // U+00F4: LATIN SMALL LETTER O WITH CIRCUMFLEX
926 + "õ" // U+00F5: LATIN SMALL LETTER O WITH TILDE
927 + "ö" // U+00F6: LATIN SMALL LETTER O WITH DIAERESIS
928 + "ø" // U+00F8: LATIN SMALL LETTER O WITH STROKE
929 + "ō" // U+014D: LATIN SMALL LETTER O WITH MACRON
930 + "ŏ" // U+014F: LATIN SMALL LETTER O WITH BREVE
931 + "ő" // U+0151: LATIN SMALL LETTER O WITH DOUBLE ACUTE
932 + "ơ" // U+01A1: LATIN SMALL LETTER O WITH HORN
933 + "ǒ" // U+01D2: LATIN SMALL LETTER O WITH CARON
934 + "ǫ" // U+01EB: LATIN SMALL LETTER O WITH OGONEK
935 + "ǭ" // U+01ED: LATIN SMALL LETTER O WITH OGONEK AND MACRON
936 + "ǿ" // U+01FF: LATIN SMALL LETTER O WITH STROKE AND ACUTE
937 + "ȍ" // U+020D: LATIN SMALL LETTER O WITH DOUBLE GRAVE
938 + "ȏ" // U+020F: LATIN SMALL LETTER O WITH INVERTED BREVE
939 + "ȫ" // U+022B: LATIN SMALL LETTER O WITH DIAERESIS AND MACRON
940 + "ȭ" // U+022D: LATIN SMALL LETTER O WITH TILDE AND MACRON
941 + "ȯ" // U+022F: LATIN SMALL LETTER O WITH DOT ABOVE
942 + "ȱ" // U+0231: LATIN SMALL LETTER O WITH DOT ABOVE AND MACRON
943 + "ɔ" // U+0254: LATIN SMALL LETTER OPEN O
944 + "ɵ" // U+0275: LATIN SMALL LETTER BARRED O
945 + "ᴖ" // U+1D16: LATIN SMALL LETTER TOP HALF O
946 + "ᴗ" // U+1D17: LATIN SMALL LETTER BOTTOM HALF O
947 + "ᶗ" // U+1D97: LATIN SMALL LETTER OPEN O WITH RETROFLEX HOOK
948 + "ṍ" // U+1E4D: LATIN SMALL LETTER O WITH TILDE AND ACUTE
949 + "ṏ" // U+1E4F: LATIN SMALL LETTER O WITH TILDE AND DIAERESIS
950 + "ṑ" // U+1E51: LATIN SMALL LETTER O WITH MACRON AND GRAVE
951 + "ṓ" // U+1E53: LATIN SMALL LETTER O WITH MACRON AND ACUTE
952 + "ọ" // U+1ECD: LATIN SMALL LETTER O WITH DOT BELOW
953 + "ỏ" // U+1ECF: LATIN SMALL LETTER O WITH HOOK ABOVE
954 + "ố" // U+1ED1: LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE
955 + "ồ" // U+1ED3: LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE
956 + "ổ" // U+1ED5: LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE
957 + "ỗ" // U+1ED7: LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE
958 + "ộ" // U+1ED9: LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW
959 + "ớ" // U+1EDB: LATIN SMALL LETTER O WITH HORN AND ACUTE
960 + "ờ" // U+1EDD: LATIN SMALL LETTER O WITH HORN AND GRAVE
961 + "ở" // U+1EDF: LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE
962 + "ỡ" // U+1EE1: LATIN SMALL LETTER O WITH HORN AND TILDE
963 + "ợ" // U+1EE3: LATIN SMALL LETTER O WITH HORN AND DOT BELOW
964 + "ₒ" // U+2092: LATIN SUBSCRIPT SMALL LETTER O
965 + "ⓞ" // U+24DE: CIRCLED LATIN SMALL LETTER O
966 + "ⱺ" // U+2C7A: LATIN SMALL LETTER O WITH LOW RING INSIDE
967 + "ꝋ" // U+A74B: LATIN SMALL LETTER O WITH LONG STROKE OVERLAY
968 + "ꝍ" // U+A74D: LATIN SMALL LETTER O WITH LOOP
969 + "o" // U+FF4F: FULLWIDTH LATIN SMALL LETTER O
970 ,"o", // Folded result
972 "Œ" // U+0152: LATIN CAPITAL LIGATURE OE
973 + "ɶ" // U+0276: LATIN LETTER SMALL CAPITAL OE
974 ,"OE", // Folded result
976 "Ꝏ" // U+A74E: LATIN CAPITAL LETTER OO
977 ,"OO", // Folded result
979 "Ȣ" // U+0222: LATIN CAPITAL LETTER OU
980 + "ᴕ" // U+1D15: LATIN LETTER SMALL CAPITAL OU
981 ,"OU", // Folded result
983 "⒪" // U+24AA: PARENTHESIZED LATIN SMALL LETTER O
984 ,"(o)", // Folded result
986 "œ" // U+0153: LATIN SMALL LIGATURE OE
987 + "ᴔ" // U+1D14: LATIN SMALL LETTER TURNED OE
988 ,"oe", // Folded result
990 "ꝏ" // U+A74F: LATIN SMALL LETTER OO
991 ,"oo", // Folded result
993 "ȣ" // U+0223: LATIN SMALL LETTER OU
994 ,"ou", // Folded result
996 "Ƥ" // U+01A4: LATIN CAPITAL LETTER P WITH HOOK
997 + "ᴘ" // U+1D18: LATIN LETTER SMALL CAPITAL P
998 + "Ṕ" // U+1E54: LATIN CAPITAL LETTER P WITH ACUTE
999 + "Ṗ" // U+1E56: LATIN CAPITAL LETTER P WITH DOT ABOVE
1000 + "Ⓟ" // U+24C5: CIRCLED LATIN CAPITAL LETTER P
1001 + "Ᵽ" // U+2C63: LATIN CAPITAL LETTER P WITH STROKE
1002 + "Ꝑ" // U+A750: LATIN CAPITAL LETTER P WITH STROKE THROUGH DESCENDER
1003 + "Ꝓ" // U+A752: LATIN CAPITAL LETTER P WITH FLOURISH
1004 + "Ꝕ" // U+A754: LATIN CAPITAL LETTER P WITH SQUIRREL TAIL
1005 + "P" // U+FF30: FULLWIDTH LATIN CAPITAL LETTER P
1006 ,"P", // Folded result
1008 "ƥ" // U+01A5: LATIN SMALL LETTER P WITH HOOK
1009 + "ᵱ" // U+1D71: LATIN SMALL LETTER P WITH MIDDLE TILDE
1010 + "ᵽ" // U+1D7D: LATIN SMALL LETTER P WITH STROKE
1011 + "ᶈ" // U+1D88: LATIN SMALL LETTER P WITH PALATAL HOOK
1012 + "ṕ" // U+1E55: LATIN SMALL LETTER P WITH ACUTE
1013 + "ṗ" // U+1E57: LATIN SMALL LETTER P WITH DOT ABOVE
1014 + "ⓟ" // U+24DF: CIRCLED LATIN SMALL LETTER P
1015 + "ꝑ" // U+A751: LATIN SMALL LETTER P WITH STROKE THROUGH DESCENDER
1016 + "ꝓ" // U+A753: LATIN SMALL LETTER P WITH FLOURISH
1017 + "ꝕ" // U+A755: LATIN SMALL LETTER P WITH SQUIRREL TAIL
1018 + "ꟼ" // U+A7FC: LATIN EPIGRAPHIC LETTER REVERSED P
1019 + "p" // U+FF50: FULLWIDTH LATIN SMALL LETTER P
1020 ,"p", // Folded result
1022 "⒫" // U+24AB: PARENTHESIZED LATIN SMALL LETTER P
1023 ,"(p)", // Folded result
1025 "Ɋ" // U+024A: LATIN CAPITAL LETTER SMALL Q WITH HOOK TAIL
1026 + "Ⓠ" // U+24C6: CIRCLED LATIN CAPITAL LETTER Q
1027 + "Ꝗ" // U+A756: LATIN CAPITAL LETTER Q WITH STROKE THROUGH DESCENDER
1028 + "Ꝙ" // U+A758: LATIN CAPITAL LETTER Q WITH DIAGONAL STROKE
1029 + "Q" // U+FF31: FULLWIDTH LATIN CAPITAL LETTER Q
1030 ,"Q", // Folded result
1032 "ĸ" // U+0138: LATIN SMALL LETTER KRA
1033 + "ɋ" // U+024B: LATIN SMALL LETTER Q WITH HOOK TAIL
1034 + "ʠ" // U+02A0: LATIN SMALL LETTER Q WITH HOOK
1035 + "ⓠ" // U+24E0: CIRCLED LATIN SMALL LETTER Q
1036 + "ꝗ" // U+A757: LATIN SMALL LETTER Q WITH STROKE THROUGH DESCENDER
1037 + "ꝙ" // U+A759: LATIN SMALL LETTER Q WITH DIAGONAL STROKE
1038 + "q" // U+FF51: FULLWIDTH LATIN SMALL LETTER Q
1039 ,"q", // Folded result
1041 "⒬" // U+24AC: PARENTHESIZED LATIN SMALL LETTER Q
1042 ,"(q)", // Folded result
1044 "ȹ" // U+0239: LATIN SMALL LETTER QP DIGRAPH
1045 ,"qp", // Folded result
1047 "Ŕ" // U+0154: LATIN CAPITAL LETTER R WITH ACUTE
1048 + "Ŗ" // U+0156: LATIN CAPITAL LETTER R WITH CEDILLA
1049 + "Ř" // U+0158: LATIN CAPITAL LETTER R WITH CARON
1050 + "Ȑ" // U+0210: LATIN CAPITAL LETTER R WITH DOUBLE GRAVE
1051 + "Ȓ" // U+0212: LATIN CAPITAL LETTER R WITH INVERTED BREVE
1052 + "Ɍ" // U+024C: LATIN CAPITAL LETTER R WITH STROKE
1053 + "ʀ" // U+0280: LATIN LETTER SMALL CAPITAL R
1054 + "ʁ" // U+0281: LATIN LETTER SMALL CAPITAL INVERTED R
1055 + "ᴙ" // U+1D19: LATIN LETTER SMALL CAPITAL REVERSED R
1056 + "ᴚ" // U+1D1A: LATIN LETTER SMALL CAPITAL TURNED R
1057 + "Ṙ" // U+1E58: LATIN CAPITAL LETTER R WITH DOT ABOVE
1058 + "Ṛ" // U+1E5A: LATIN CAPITAL LETTER R WITH DOT BELOW
1059 + "Ṝ" // U+1E5C: LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON
1060 + "Ṟ" // U+1E5E: LATIN CAPITAL LETTER R WITH LINE BELOW
1061 + "Ⓡ" // U+24C7: CIRCLED LATIN CAPITAL LETTER R
1062 + "Ɽ" // U+2C64: LATIN CAPITAL LETTER R WITH TAIL
1063 + "Ꝛ" // U+A75A: LATIN CAPITAL LETTER R ROTUNDA
1064 + "Ꞃ" // U+A782: LATIN CAPITAL LETTER INSULAR R
1065 + "R" // U+FF32: FULLWIDTH LATIN CAPITAL LETTER R
1066 ,"R", // Folded result
1068 "ŕ" // U+0155: LATIN SMALL LETTER R WITH ACUTE
1069 + "ŗ" // U+0157: LATIN SMALL LETTER R WITH CEDILLA
1070 + "ř" // U+0159: LATIN SMALL LETTER R WITH CARON
1071 + "ȑ" // U+0211: LATIN SMALL LETTER R WITH DOUBLE GRAVE
1072 + "ȓ" // U+0213: LATIN SMALL LETTER R WITH INVERTED BREVE
1073 + "ɍ" // U+024D: LATIN SMALL LETTER R WITH STROKE
1074 + "ɼ" // U+027C: LATIN SMALL LETTER R WITH LONG LEG
1075 + "ɽ" // U+027D: LATIN SMALL LETTER R WITH TAIL
1076 + "ɾ" // U+027E: LATIN SMALL LETTER R WITH FISHHOOK
1077 + "ɿ" // U+027F: LATIN SMALL LETTER REVERSED R WITH FISHHOOK
1078 + "ᵣ" // U+1D63: LATIN SUBSCRIPT SMALL LETTER R
1079 + "ᵲ" // U+1D72: LATIN SMALL LETTER R WITH MIDDLE TILDE
1080 + "ᵳ" // U+1D73: LATIN SMALL LETTER R WITH FISHHOOK AND MIDDLE TILDE
1081 + "ᶉ" // U+1D89: LATIN SMALL LETTER R WITH PALATAL HOOK
1082 + "ṙ" // U+1E59: LATIN SMALL LETTER R WITH DOT ABOVE
1083 + "ṛ" // U+1E5B: LATIN SMALL LETTER R WITH DOT BELOW
1084 + "ṝ" // U+1E5D: LATIN SMALL LETTER R WITH DOT BELOW AND MACRON
1085 + "ṟ" // U+1E5F: LATIN SMALL LETTER R WITH LINE BELOW
1086 + "ⓡ" // U+24E1: CIRCLED LATIN SMALL LETTER R
1087 + "ꝛ" // U+A75B: LATIN SMALL LETTER R ROTUNDA
1088 + "ꞃ" // U+A783: LATIN SMALL LETTER INSULAR R
1089 + "r" // U+FF52: FULLWIDTH LATIN SMALL LETTER R
1090 ,"r", // Folded result
1092 "⒭" // U+24AD: PARENTHESIZED LATIN SMALL LETTER R
1093 ,"(r)", // Folded result
1095 "Ś" // U+015A: LATIN CAPITAL LETTER S WITH ACUTE
1096 + "Ŝ" // U+015C: LATIN CAPITAL LETTER S WITH CIRCUMFLEX
1097 + "Ş" // U+015E: LATIN CAPITAL LETTER S WITH CEDILLA
1098 + "Š" // U+0160: LATIN CAPITAL LETTER S WITH CARON
1099 + "Ș" // U+0218: LATIN CAPITAL LETTER S WITH COMMA BELOW
1100 + "Ṡ" // U+1E60: LATIN CAPITAL LETTER S WITH DOT ABOVE
1101 + "Ṣ" // U+1E62: LATIN CAPITAL LETTER S WITH DOT BELOW
1102 + "Ṥ" // U+1E64: LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE
1103 + "Ṧ" // U+1E66: LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE
1104 + "Ṩ" // U+1E68: LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE
1105 + "Ⓢ" // U+24C8: CIRCLED LATIN CAPITAL LETTER S
1106 + "ꜱ" // U+A731: LATIN LETTER SMALL CAPITAL S
1107 + "ꞅ" // U+A785: LATIN SMALL LETTER INSULAR S
1108 + "S" // U+FF33: FULLWIDTH LATIN CAPITAL LETTER S
1109 ,"S", // Folded result
1111 "ś" // U+015B: LATIN SMALL LETTER S WITH ACUTE
1112 + "ŝ" // U+015D: LATIN SMALL LETTER S WITH CIRCUMFLEX
1113 + "ş" // U+015F: LATIN SMALL LETTER S WITH CEDILLA
1114 + "š" // U+0161: LATIN SMALL LETTER S WITH CARON
1115 + "ſ" // U+017F: LATIN SMALL LETTER LONG S
1116 + "ș" // U+0219: LATIN SMALL LETTER S WITH COMMA BELOW
1117 + "ȿ" // U+023F: LATIN SMALL LETTER S WITH SWASH TAIL
1118 + "ʂ" // U+0282: LATIN SMALL LETTER S WITH HOOK
1119 + "ᵴ" // U+1D74: LATIN SMALL LETTER S WITH MIDDLE TILDE
1120 + "ᶊ" // U+1D8A: LATIN SMALL LETTER S WITH PALATAL HOOK
1121 + "ṡ" // U+1E61: LATIN SMALL LETTER S WITH DOT ABOVE
1122 + "ṣ" // U+1E63: LATIN SMALL LETTER S WITH DOT BELOW
1123 + "ṥ" // U+1E65: LATIN SMALL LETTER S WITH ACUTE AND DOT ABOVE
1124 + "ṧ" // U+1E67: LATIN SMALL LETTER S WITH CARON AND DOT ABOVE
1125 + "ṩ" // U+1E69: LATIN SMALL LETTER S WITH DOT BELOW AND DOT ABOVE
1126 + "ẜ" // U+1E9C: LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE
1127 + "ẝ" // U+1E9D: LATIN SMALL LETTER LONG S WITH HIGH STROKE
1128 + "ⓢ" // U+24E2: CIRCLED LATIN SMALL LETTER S
1129 + "Ꞅ" // U+A784: LATIN CAPITAL LETTER INSULAR S
1130 + "s" // U+FF53: FULLWIDTH LATIN SMALL LETTER S
1131 ,"s", // Folded result
1133 "ẞ" // U+1E9E: LATIN CAPITAL LETTER SHARP S
1134 ,"SS", // Folded result
1136 "⒮" // U+24AE: PARENTHESIZED LATIN SMALL LETTER S
1137 ,"(s)", // Folded result
1139 "ß" // U+00DF: LATIN SMALL LETTER SHARP S
1140 ,"ss", // Folded result
1142 "st" // U+FB06: LATIN SMALL LIGATURE ST
1143 ,"st", // Folded result
1145 "Ţ" // U+0162: LATIN CAPITAL LETTER T WITH CEDILLA
1146 + "Ť" // U+0164: LATIN CAPITAL LETTER T WITH CARON
1147 + "Ŧ" // U+0166: LATIN CAPITAL LETTER T WITH STROKE
1148 + "Ƭ" // U+01AC: LATIN CAPITAL LETTER T WITH HOOK
1149 + "Ʈ" // U+01AE: LATIN CAPITAL LETTER T WITH RETROFLEX HOOK
1150 + "Ț" // U+021A: LATIN CAPITAL LETTER T WITH COMMA BELOW
1151 + "Ⱦ" // U+023E: LATIN CAPITAL LETTER T WITH DIAGONAL STROKE
1152 + "ᴛ" // U+1D1B: LATIN LETTER SMALL CAPITAL T
1153 + "Ṫ" // U+1E6A: LATIN CAPITAL LETTER T WITH DOT ABOVE
1154 + "Ṭ" // U+1E6C: LATIN CAPITAL LETTER T WITH DOT BELOW
1155 + "Ṯ" // U+1E6E: LATIN CAPITAL LETTER T WITH LINE BELOW
1156 + "Ṱ" // U+1E70: LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW
1157 + "Ⓣ" // U+24C9: CIRCLED LATIN CAPITAL LETTER T
1158 + "Ꞇ" // U+A786: LATIN CAPITAL LETTER INSULAR T
1159 + "T" // U+FF34: FULLWIDTH LATIN CAPITAL LETTER T
1160 ,"T", // Folded result
1162 "ţ" // U+0163: LATIN SMALL LETTER T WITH CEDILLA
1163 + "ť" // U+0165: LATIN SMALL LETTER T WITH CARON
1164 + "ŧ" // U+0167: LATIN SMALL LETTER T WITH STROKE
1165 + "ƫ" // U+01AB: LATIN SMALL LETTER T WITH PALATAL HOOK
1166 + "ƭ" // U+01AD: LATIN SMALL LETTER T WITH HOOK
1167 + "ț" // U+021B: LATIN SMALL LETTER T WITH COMMA BELOW
1168 + "ȶ" // U+0236: LATIN SMALL LETTER T WITH CURL
1169 + "ʇ" // U+0287: LATIN SMALL LETTER TURNED T
1170 + "ʈ" // U+0288: LATIN SMALL LETTER T WITH RETROFLEX HOOK
1171 + "ᵵ" // U+1D75: LATIN SMALL LETTER T WITH MIDDLE TILDE
1172 + "ṫ" // U+1E6B: LATIN SMALL LETTER T WITH DOT ABOVE
1173 + "ṭ" // U+1E6D: LATIN SMALL LETTER T WITH DOT BELOW
1174 + "ṯ" // U+1E6F: LATIN SMALL LETTER T WITH LINE BELOW
1175 + "ṱ" // U+1E71: LATIN SMALL LETTER T WITH CIRCUMFLEX BELOW
1176 + "ẗ" // U+1E97: LATIN SMALL LETTER T WITH DIAERESIS
1177 + "ⓣ" // U+24E3: CIRCLED LATIN SMALL LETTER T
1178 + "ⱦ" // U+2C66: LATIN SMALL LETTER T WITH DIAGONAL STROKE
1179 + "t" // U+FF54: FULLWIDTH LATIN SMALL LETTER T
1180 ,"t", // Folded result
1182 "Þ" // U+00DE: LATIN CAPITAL LETTER THORN
1183 + "Ꝧ" // U+A766: LATIN CAPITAL LETTER THORN WITH STROKE THROUGH DESCENDER
1184 ,"TH", // Folded result
1186 "Ꜩ" // U+A728: LATIN CAPITAL LETTER TZ
1187 ,"TZ", // Folded result
1189 "⒯" // U+24AF: PARENTHESIZED LATIN SMALL LETTER T
1190 ,"(t)", // Folded result
1192 "ʨ" // U+02A8: LATIN SMALL LETTER TC DIGRAPH WITH CURL
1193 ,"tc", // Folded result
1195 "þ" // U+00FE: LATIN SMALL LETTER THORN
1196 + "ᵺ" // U+1D7A: LATIN SMALL LETTER TH WITH STRIKETHROUGH
1197 + "ꝧ" // U+A767: LATIN SMALL LETTER THORN WITH STROKE THROUGH DESCENDER
1198 ,"th", // Folded result
1200 "ʦ" // U+02A6: LATIN SMALL LETTER TS DIGRAPH
1201 ,"ts", // Folded result
1203 "ꜩ" // U+A729: LATIN SMALL LETTER TZ
1204 ,"tz", // Folded result
1206 "Ù" // U+00D9: LATIN CAPITAL LETTER U WITH GRAVE
1207 + "Ú" // U+00DA: LATIN CAPITAL LETTER U WITH ACUTE
1208 + "Û" // U+00DB: LATIN CAPITAL LETTER U WITH CIRCUMFLEX
1209 + "Ü" // U+00DC: LATIN CAPITAL LETTER U WITH DIAERESIS
1210 + "Ũ" // U+0168: LATIN CAPITAL LETTER U WITH TILDE
1211 + "Ū" // U+016A: LATIN CAPITAL LETTER U WITH MACRON
1212 + "Ŭ" // U+016C: LATIN CAPITAL LETTER U WITH BREVE
1213 + "Ů" // U+016E: LATIN CAPITAL LETTER U WITH RING ABOVE
1214 + "Ű" // U+0170: LATIN CAPITAL LETTER U WITH DOUBLE ACUTE
1215 + "Ų" // U+0172: LATIN CAPITAL LETTER U WITH OGONEK
1216 + "Ư" // U+01AF: LATIN CAPITAL LETTER U WITH HORN
1217 + "Ǔ" // U+01D3: LATIN CAPITAL LETTER U WITH CARON
1218 + "Ǖ" // U+01D5: LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON
1219 + "Ǘ" // U+01D7: LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE
1220 + "Ǚ" // U+01D9: LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON
1221 + "Ǜ" // U+01DB: LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE
1222 + "Ȕ" // U+0214: LATIN CAPITAL LETTER U WITH DOUBLE GRAVE
1223 + "Ȗ" // U+0216: LATIN CAPITAL LETTER U WITH INVERTED BREVE
1224 + "Ʉ" // U+0244: LATIN CAPITAL LETTER U BAR
1225 + "ᴜ" // U+1D1C: LATIN LETTER SMALL CAPITAL U
1226 + "ᵾ" // U+1D7E: LATIN SMALL CAPITAL LETTER U WITH STROKE
1227 + "Ṳ" // U+1E72: LATIN CAPITAL LETTER U WITH DIAERESIS BELOW
1228 + "Ṵ" // U+1E74: LATIN CAPITAL LETTER U WITH TILDE BELOW
1229 + "Ṷ" // U+1E76: LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW
1230 + "Ṹ" // U+1E78: LATIN CAPITAL LETTER U WITH TILDE AND ACUTE
1231 + "Ṻ" // U+1E7A: LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS
1232 + "Ụ" // U+1EE4: LATIN CAPITAL LETTER U WITH DOT BELOW
1233 + "Ủ" // U+1EE6: LATIN CAPITAL LETTER U WITH HOOK ABOVE
1234 + "Ứ" // U+1EE8: LATIN CAPITAL LETTER U WITH HORN AND ACUTE
1235 + "Ừ" // U+1EEA: LATIN CAPITAL LETTER U WITH HORN AND GRAVE
1236 + "Ử" // U+1EEC: LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE
1237 + "Ữ" // U+1EEE: LATIN CAPITAL LETTER U WITH HORN AND TILDE
1238 + "Ự" // U+1EF0: LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW
1239 + "Ⓤ" // U+24CA: CIRCLED LATIN CAPITAL LETTER U
1240 + "U" // U+FF35: FULLWIDTH LATIN CAPITAL LETTER U
1241 ,"U", // Folded result
1243 "ù" // U+00F9: LATIN SMALL LETTER U WITH GRAVE
1244 + "ú" // U+00FA: LATIN SMALL LETTER U WITH ACUTE
1245 + "û" // U+00FB: LATIN SMALL LETTER U WITH CIRCUMFLEX
1246 + "ü" // U+00FC: LATIN SMALL LETTER U WITH DIAERESIS
1247 + "ũ" // U+0169: LATIN SMALL LETTER U WITH TILDE
1248 + "ū" // U+016B: LATIN SMALL LETTER U WITH MACRON
1249 + "ŭ" // U+016D: LATIN SMALL LETTER U WITH BREVE
1250 + "ů" // U+016F: LATIN SMALL LETTER U WITH RING ABOVE
1251 + "ű" // U+0171: LATIN SMALL LETTER U WITH DOUBLE ACUTE
1252 + "ų" // U+0173: LATIN SMALL LETTER U WITH OGONEK
1253 + "ư" // U+01B0: LATIN SMALL LETTER U WITH HORN
1254 + "ǔ" // U+01D4: LATIN SMALL LETTER U WITH CARON
1255 + "ǖ" // U+01D6: LATIN SMALL LETTER U WITH DIAERESIS AND MACRON
1256 + "ǘ" // U+01D8: LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE
1257 + "ǚ" // U+01DA: LATIN SMALL LETTER U WITH DIAERESIS AND CARON
1258 + "ǜ" // U+01DC: LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE
1259 + "ȕ" // U+0215: LATIN SMALL LETTER U WITH DOUBLE GRAVE
1260 + "ȗ" // U+0217: LATIN SMALL LETTER U WITH INVERTED BREVE
1261 + "ʉ" // U+0289: LATIN SMALL LETTER U BAR
1262 + "ᵤ" // U+1D64: LATIN SUBSCRIPT SMALL LETTER U
1263 + "ᶙ" // U+1D99: LATIN SMALL LETTER U WITH RETROFLEX HOOK
1264 + "ṳ" // U+1E73: LATIN SMALL LETTER U WITH DIAERESIS BELOW
1265 + "ṵ" // U+1E75: LATIN SMALL LETTER U WITH TILDE BELOW
1266 + "ṷ" // U+1E77: LATIN SMALL LETTER U WITH CIRCUMFLEX BELOW
1267 + "ṹ" // U+1E79: LATIN SMALL LETTER U WITH TILDE AND ACUTE
1268 + "ṻ" // U+1E7B: LATIN SMALL LETTER U WITH MACRON AND DIAERESIS
1269 + "ụ" // U+1EE5: LATIN SMALL LETTER U WITH DOT BELOW
1270 + "ủ" // U+1EE7: LATIN SMALL LETTER U WITH HOOK ABOVE
1271 + "ứ" // U+1EE9: LATIN SMALL LETTER U WITH HORN AND ACUTE
1272 + "ừ" // U+1EEB: LATIN SMALL LETTER U WITH HORN AND GRAVE
1273 + "ử" // U+1EED: LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE
1274 + "ữ" // U+1EEF: LATIN SMALL LETTER U WITH HORN AND TILDE
1275 + "ự" // U+1EF1: LATIN SMALL LETTER U WITH HORN AND DOT BELOW
1276 + "ⓤ" // U+24E4: CIRCLED LATIN SMALL LETTER U
1277 + "u" // U+FF55: FULLWIDTH LATIN SMALL LETTER U
1278 ,"u", // Folded result
1280 "⒰" // U+24B0: PARENTHESIZED LATIN SMALL LETTER U
1281 ,"(u)", // Folded result
1283 "ᵫ" // U+1D6B: LATIN SMALL LETTER UE
1284 ,"ue", // Folded result
1286 "Ʋ" // U+01B2: LATIN CAPITAL LETTER V WITH HOOK
1287 + "Ʌ" // U+0245: LATIN CAPITAL LETTER TURNED V
1288 + "ᴠ" // U+1D20: LATIN LETTER SMALL CAPITAL V
1289 + "Ṽ" // U+1E7C: LATIN CAPITAL LETTER V WITH TILDE
1290 + "Ṿ" // U+1E7E: LATIN CAPITAL LETTER V WITH DOT BELOW
1291 + "Ỽ" // U+1EFC: LATIN CAPITAL LETTER MIDDLE-WELSH V
1292 + "Ⓥ" // U+24CB: CIRCLED LATIN CAPITAL LETTER V
1293 + "Ꝟ" // U+A75E: LATIN CAPITAL LETTER V WITH DIAGONAL STROKE
1294 + "Ꝩ" // U+A768: LATIN CAPITAL LETTER VEND
1295 + "V" // U+FF36: FULLWIDTH LATIN CAPITAL LETTER V
1296 ,"V", // Folded result
1298 "ʋ" // U+028B: LATIN SMALL LETTER V WITH HOOK
1299 + "ʌ" // U+028C: LATIN SMALL LETTER TURNED V
1300 + "ᵥ" // U+1D65: LATIN SUBSCRIPT SMALL LETTER V
1301 + "ᶌ" // U+1D8C: LATIN SMALL LETTER V WITH PALATAL HOOK
1302 + "ṽ" // U+1E7D: LATIN SMALL LETTER V WITH TILDE
1303 + "ṿ" // U+1E7F: LATIN SMALL LETTER V WITH DOT BELOW
1304 + "ⓥ" // U+24E5: CIRCLED LATIN SMALL LETTER V
1305 + "ⱱ" // U+2C71: LATIN SMALL LETTER V WITH RIGHT HOOK
1306 + "ⱴ" // U+2C74: LATIN SMALL LETTER V WITH CURL
1307 + "ꝟ" // U+A75F: LATIN SMALL LETTER V WITH DIAGONAL STROKE
1308 + "v" // U+FF56: FULLWIDTH LATIN SMALL LETTER V
1309 ,"v", // Folded result
1311 "Ꝡ" // U+A760: LATIN CAPITAL LETTER VY
1312 ,"VY", // Folded result
1314 "⒱" // U+24B1: PARENTHESIZED LATIN SMALL LETTER V
1315 ,"(v)", // Folded result
1317 "ꝡ" // U+A761: LATIN SMALL LETTER VY
1318 ,"vy", // Folded result
1320 "Ŵ" // U+0174: LATIN CAPITAL LETTER W WITH CIRCUMFLEX
1321 + "Ƿ" // U+01F7: LATIN CAPITAL LETTER WYNN
1322 + "ᴡ" // U+1D21: LATIN LETTER SMALL CAPITAL W
1323 + "Ẁ" // U+1E80: LATIN CAPITAL LETTER W WITH GRAVE
1324 + "Ẃ" // U+1E82: LATIN CAPITAL LETTER W WITH ACUTE
1325 + "Ẅ" // U+1E84: LATIN CAPITAL LETTER W WITH DIAERESIS
1326 + "Ẇ" // U+1E86: LATIN CAPITAL LETTER W WITH DOT ABOVE
1327 + "Ẉ" // U+1E88: LATIN CAPITAL LETTER W WITH DOT BELOW
1328 + "Ⓦ" // U+24CC: CIRCLED LATIN CAPITAL LETTER W
1329 + "Ⱳ" // U+2C72: LATIN CAPITAL LETTER W WITH HOOK
1330 + "W" // U+FF37: FULLWIDTH LATIN CAPITAL LETTER W
1331 ,"W", // Folded result
1333 "ŵ" // U+0175: LATIN SMALL LETTER W WITH CIRCUMFLEX
1334 + "ƿ" // U+01BF: LATIN LETTER WYNN
1335 + "ʍ" // U+028D: LATIN SMALL LETTER TURNED W
1336 + "ẁ" // U+1E81: LATIN SMALL LETTER W WITH GRAVE
1337 + "ẃ" // U+1E83: LATIN SMALL LETTER W WITH ACUTE
1338 + "ẅ" // U+1E85: LATIN SMALL LETTER W WITH DIAERESIS
1339 + "ẇ" // U+1E87: LATIN SMALL LETTER W WITH DOT ABOVE
1340 + "ẉ" // U+1E89: LATIN SMALL LETTER W WITH DOT BELOW
1341 + "ẘ" // U+1E98: LATIN SMALL LETTER W WITH RING ABOVE
1342 + "ⓦ" // U+24E6: CIRCLED LATIN SMALL LETTER W
1343 + "ⱳ" // U+2C73: LATIN SMALL LETTER W WITH HOOK
1344 + "w" // U+FF57: FULLWIDTH LATIN SMALL LETTER W
1345 ,"w", // Folded result
1347 "⒲" // U+24B2: PARENTHESIZED LATIN SMALL LETTER W
1348 ,"(w)", // Folded result
1350 "Ẋ" // U+1E8A: LATIN CAPITAL LETTER X WITH DOT ABOVE
1351 + "Ẍ" // U+1E8C: LATIN CAPITAL LETTER X WITH DIAERESIS
1352 + "Ⓧ" // U+24CD: CIRCLED LATIN CAPITAL LETTER X
1353 + "X" // U+FF38: FULLWIDTH LATIN CAPITAL LETTER X
1354 ,"X", // Folded result
1356 "ᶍ" // U+1D8D: LATIN SMALL LETTER X WITH PALATAL HOOK
1357 + "ẋ" // U+1E8B: LATIN SMALL LETTER X WITH DOT ABOVE
1358 + "ẍ" // U+1E8D: LATIN SMALL LETTER X WITH DIAERESIS
1359 + "ₓ" // U+2093: LATIN SUBSCRIPT SMALL LETTER X
1360 + "ⓧ" // U+24E7: CIRCLED LATIN SMALL LETTER X
1361 + "x" // U+FF58: FULLWIDTH LATIN SMALL LETTER X
1362 ,"x", // Folded result
1364 "⒳" // U+24B3: PARENTHESIZED LATIN SMALL LETTER X
1365 ,"(x)", // Folded result
1367 "Ý" // U+00DD: LATIN CAPITAL LETTER Y WITH ACUTE
1368 + "Ŷ" // U+0176: LATIN CAPITAL LETTER Y WITH CIRCUMFLEX
1369 + "Ÿ" // U+0178: LATIN CAPITAL LETTER Y WITH DIAERESIS
1370 + "Ƴ" // U+01B3: LATIN CAPITAL LETTER Y WITH HOOK
1371 + "Ȳ" // U+0232: LATIN CAPITAL LETTER Y WITH MACRON
1372 + "Ɏ" // U+024E: LATIN CAPITAL LETTER Y WITH STROKE
1373 + "ʏ" // U+028F: LATIN LETTER SMALL CAPITAL Y
1374 + "Ẏ" // U+1E8E: LATIN CAPITAL LETTER Y WITH DOT ABOVE
1375 + "Ỳ" // U+1EF2: LATIN CAPITAL LETTER Y WITH GRAVE
1376 + "Ỵ" // U+1EF4: LATIN CAPITAL LETTER Y WITH DOT BELOW
1377 + "Ỷ" // U+1EF6: LATIN CAPITAL LETTER Y WITH HOOK ABOVE
1378 + "Ỹ" // U+1EF8: LATIN CAPITAL LETTER Y WITH TILDE
1379 + "Ỿ" // U+1EFE: LATIN CAPITAL LETTER Y WITH LOOP
1380 + "Ⓨ" // U+24CE: CIRCLED LATIN CAPITAL LETTER Y
1381 + "Y" // U+FF39: FULLWIDTH LATIN CAPITAL LETTER Y
1382 ,"Y", // Folded result
1384 "ý" // U+00FD: LATIN SMALL LETTER Y WITH ACUTE
1385 + "ÿ" // U+00FF: LATIN SMALL LETTER Y WITH DIAERESIS
1386 + "ŷ" // U+0177: LATIN SMALL LETTER Y WITH CIRCUMFLEX
1387 + "ƴ" // U+01B4: LATIN SMALL LETTER Y WITH HOOK
1388 + "ȳ" // U+0233: LATIN SMALL LETTER Y WITH MACRON
1389 + "ɏ" // U+024F: LATIN SMALL LETTER Y WITH STROKE
1390 + "ʎ" // U+028E: LATIN SMALL LETTER TURNED Y
1391 + "ẏ" // U+1E8F: LATIN SMALL LETTER Y WITH DOT ABOVE
1392 + "ẙ" // U+1E99: LATIN SMALL LETTER Y WITH RING ABOVE
1393 + "ỳ" // U+1EF3: LATIN SMALL LETTER Y WITH GRAVE
1394 + "ỵ" // U+1EF5: LATIN SMALL LETTER Y WITH DOT BELOW
1395 + "ỷ" // U+1EF7: LATIN SMALL LETTER Y WITH HOOK ABOVE
1396 + "ỹ" // U+1EF9: LATIN SMALL LETTER Y WITH TILDE
1397 + "ỿ" // U+1EFF: LATIN SMALL LETTER Y WITH LOOP
1398 + "ⓨ" // U+24E8: CIRCLED LATIN SMALL LETTER Y
1399 + "y" // U+FF59: FULLWIDTH LATIN SMALL LETTER Y
1400 ,"y", // Folded result
1402 "⒴" // U+24B4: PARENTHESIZED LATIN SMALL LETTER Y
1403 ,"(y)", // Folded result
1405 "Ź" // U+0179: LATIN CAPITAL LETTER Z WITH ACUTE
1406 + "Ż" // U+017B: LATIN CAPITAL LETTER Z WITH DOT ABOVE
1407 + "Ž" // U+017D: LATIN CAPITAL LETTER Z WITH CARON
1408 + "Ƶ" // U+01B5: LATIN CAPITAL LETTER Z WITH STROKE
1409 + "Ȝ" // U+021C: LATIN CAPITAL LETTER YOGH
1410 + "Ȥ" // U+0224: LATIN CAPITAL LETTER Z WITH HOOK
1411 + "ᴢ" // U+1D22: LATIN LETTER SMALL CAPITAL Z
1412 + "Ẑ" // U+1E90: LATIN CAPITAL LETTER Z WITH CIRCUMFLEX
1413 + "Ẓ" // U+1E92: LATIN CAPITAL LETTER Z WITH DOT BELOW
1414 + "Ẕ" // U+1E94: LATIN CAPITAL LETTER Z WITH LINE BELOW
1415 + "Ⓩ" // U+24CF: CIRCLED LATIN CAPITAL LETTER Z
1416 + "Ⱬ" // U+2C6B: LATIN CAPITAL LETTER Z WITH DESCENDER
1417 + "Ꝣ" // U+A762: LATIN CAPITAL LETTER VISIGOTHIC Z
1418 + "Z" // U+FF3A: FULLWIDTH LATIN CAPITAL LETTER Z
1419 ,"Z", // Folded result
1421 "ź" // U+017A: LATIN SMALL LETTER Z WITH ACUTE
1422 + "ż" // U+017C: LATIN SMALL LETTER Z WITH DOT ABOVE
1423 + "ž" // U+017E: LATIN SMALL LETTER Z WITH CARON
1424 + "ƶ" // U+01B6: LATIN SMALL LETTER Z WITH STROKE
1425 + "ȝ" // U+021D: LATIN SMALL LETTER YOGH
1426 + "ȥ" // U+0225: LATIN SMALL LETTER Z WITH HOOK
1427 + "ɀ" // U+0240: LATIN SMALL LETTER Z WITH SWASH TAIL
1428 + "ʐ" // U+0290: LATIN SMALL LETTER Z WITH RETROFLEX HOOK
1429 + "ʑ" // U+0291: LATIN SMALL LETTER Z WITH CURL
1430 + "ᵶ" // U+1D76: LATIN SMALL LETTER Z WITH MIDDLE TILDE
1431 + "ᶎ" // U+1D8E: LATIN SMALL LETTER Z WITH PALATAL HOOK
1432 + "ẑ" // U+1E91: LATIN SMALL LETTER Z WITH CIRCUMFLEX
1433 + "ẓ" // U+1E93: LATIN SMALL LETTER Z WITH DOT BELOW
1434 + "ẕ" // U+1E95: LATIN SMALL LETTER Z WITH LINE BELOW
1435 + "ⓩ" // U+24E9: CIRCLED LATIN SMALL LETTER Z
1436 + "ⱬ" // U+2C6C: LATIN SMALL LETTER Z WITH DESCENDER
1437 + "ꝣ" // U+A763: LATIN SMALL LETTER VISIGOTHIC Z
1438 + "z" // U+FF5A: FULLWIDTH LATIN SMALL LETTER Z
1439 ,"z", // Folded result
1441 "⒵" // U+24B5: PARENTHESIZED LATIN SMALL LETTER Z
1442 ,"(z)", // Folded result
1444 "⁰" // U+2070: SUPERSCRIPT ZERO
1445 + "₀" // U+2080: SUBSCRIPT ZERO
1446 + "⓪" // U+24EA: CIRCLED DIGIT ZERO
1447 + "⓿" // U+24FF: NEGATIVE CIRCLED DIGIT ZERO
1448 + "0" // U+FF10: FULLWIDTH DIGIT ZERO
1449 ,"0", // Folded result
1451 "¹" // U+00B9: SUPERSCRIPT ONE
1452 + "₁" // U+2081: SUBSCRIPT ONE
1453 + "①" // U+2460: CIRCLED DIGIT ONE
1454 + "⓵" // U+24F5: DOUBLE CIRCLED DIGIT ONE
1455 + "❶" // U+2776: DINGBAT NEGATIVE CIRCLED DIGIT ONE
1456 + "➀" // U+2780: DINGBAT CIRCLED SANS-SERIF DIGIT ONE
1457 + "➊" // U+278A: DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ONE
1458 + "1" // U+FF11: FULLWIDTH DIGIT ONE
1459 ,"1", // Folded result
1461 "⒈" // U+2488: DIGIT ONE FULL STOP
1462 ,"1.", // Folded result
1464 "⑴" // U+2474: PARENTHESIZED DIGIT ONE
1465 ,"(1)", // Folded result
1467 "²" // U+00B2: SUPERSCRIPT TWO
1468 + "₂" // U+2082: SUBSCRIPT TWO
1469 + "②" // U+2461: CIRCLED DIGIT TWO
1470 + "⓶" // U+24F6: DOUBLE CIRCLED DIGIT TWO
1471 + "❷" // U+2777: DINGBAT NEGATIVE CIRCLED DIGIT TWO
1472 + "➁" // U+2781: DINGBAT CIRCLED SANS-SERIF DIGIT TWO
1473 + "➋" // U+278B: DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT TWO
1474 + "2" // U+FF12: FULLWIDTH DIGIT TWO
1475 ,"2", // Folded result
1477 "⒉" // U+2489: DIGIT TWO FULL STOP
1478 ,"2.", // Folded result
1480 "⑵" // U+2475: PARENTHESIZED DIGIT TWO
1481 ,"(2)", // Folded result
1483 "³" // U+00B3: SUPERSCRIPT THREE
1484 + "₃" // U+2083: SUBSCRIPT THREE
1485 + "③" // U+2462: CIRCLED DIGIT THREE
1486 + "⓷" // U+24F7: DOUBLE CIRCLED DIGIT THREE
1487 + "❸" // U+2778: DINGBAT NEGATIVE CIRCLED DIGIT THREE
1488 + "➂" // U+2782: DINGBAT CIRCLED SANS-SERIF DIGIT THREE
1489 + "➌" // U+278C: DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT THREE
1490 + "3" // U+FF13: FULLWIDTH DIGIT THREE
1491 ,"3", // Folded result
1493 "⒊" // U+248A: DIGIT THREE FULL STOP
1494 ,"3.", // Folded result
1496 "⑶" // U+2476: PARENTHESIZED DIGIT THREE
1497 ,"(3)", // Folded result
1499 "⁴" // U+2074: SUPERSCRIPT FOUR
1500 + "₄" // U+2084: SUBSCRIPT FOUR
1501 + "④" // U+2463: CIRCLED DIGIT FOUR
1502 + "⓸" // U+24F8: DOUBLE CIRCLED DIGIT FOUR
1503 + "❹" // U+2779: DINGBAT NEGATIVE CIRCLED DIGIT FOUR
1504 + "➃" // U+2783: DINGBAT CIRCLED SANS-SERIF DIGIT FOUR
1505 + "➍" // U+278D: DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FOUR
1506 + "4" // U+FF14: FULLWIDTH DIGIT FOUR
1507 ,"4", // Folded result
1509 "⒋" // U+248B: DIGIT FOUR FULL STOP
1510 ,"4.", // Folded result
1512 "⑷" // U+2477: PARENTHESIZED DIGIT FOUR
1513 ,"(4)", // Folded result
1515 "⁵" // U+2075: SUPERSCRIPT FIVE
1516 + "₅" // U+2085: SUBSCRIPT FIVE
1517 + "⑤" // U+2464: CIRCLED DIGIT FIVE
1518 + "⓹" // U+24F9: DOUBLE CIRCLED DIGIT FIVE
1519 + "❺" // U+277A: DINGBAT NEGATIVE CIRCLED DIGIT FIVE
1520 + "➄" // U+2784: DINGBAT CIRCLED SANS-SERIF DIGIT FIVE
1521 + "➎" // U+278E: DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FIVE
1522 + "5" // U+FF15: FULLWIDTH DIGIT FIVE
1523 ,"5", // Folded result
1525 "⒌" // U+248C: DIGIT FIVE FULL STOP
1526 ,"5.", // Folded result
1528 "⑸" // U+2478: PARENTHESIZED DIGIT FIVE
1529 ,"(5)", // Folded result
1531 "⁶" // U+2076: SUPERSCRIPT SIX
1532 + "₆" // U+2086: SUBSCRIPT SIX
1533 + "⑥" // U+2465: CIRCLED DIGIT SIX
1534 + "⓺" // U+24FA: DOUBLE CIRCLED DIGIT SIX
1535 + "❻" // U+277B: DINGBAT NEGATIVE CIRCLED DIGIT SIX
1536 + "➅" // U+2785: DINGBAT CIRCLED SANS-SERIF DIGIT SIX
1537 + "➏" // U+278F: DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SIX
1538 + "6" // U+FF16: FULLWIDTH DIGIT SIX
1539 ,"6", // Folded result
1541 "⒍" // U+248D: DIGIT SIX FULL STOP
1542 ,"6.", // Folded result
1544 "⑹" // U+2479: PARENTHESIZED DIGIT SIX
1545 ,"(6)", // Folded result
1547 "⁷" // U+2077: SUPERSCRIPT SEVEN
1548 + "₇" // U+2087: SUBSCRIPT SEVEN
1549 + "⑦" // U+2466: CIRCLED DIGIT SEVEN
1550 + "⓻" // U+24FB: DOUBLE CIRCLED DIGIT SEVEN
1551 + "❼" // U+277C: DINGBAT NEGATIVE CIRCLED DIGIT SEVEN
1552 + "➆" // U+2786: DINGBAT CIRCLED SANS-SERIF DIGIT SEVEN
1553 + "➐" // U+2790: DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SEVEN
1554 + "7" // U+FF17: FULLWIDTH DIGIT SEVEN
1555 ,"7", // Folded result
1557 "⒎" // U+248E: DIGIT SEVEN FULL STOP
1558 ,"7.", // Folded result
1560 "⑺" // U+247A: PARENTHESIZED DIGIT SEVEN
1561 ,"(7)", // Folded result
1563 "⁸" // U+2078: SUPERSCRIPT EIGHT
1564 + "₈" // U+2088: SUBSCRIPT EIGHT
1565 + "⑧" // U+2467: CIRCLED DIGIT EIGHT
1566 + "⓼" // U+24FC: DOUBLE CIRCLED DIGIT EIGHT
1567 + "❽" // U+277D: DINGBAT NEGATIVE CIRCLED DIGIT EIGHT
1568 + "➇" // U+2787: DINGBAT CIRCLED SANS-SERIF DIGIT EIGHT
1569 + "➑" // U+2791: DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT EIGHT
1570 + "8" // U+FF18: FULLWIDTH DIGIT EIGHT
1571 ,"8", // Folded result
1573 "⒏" // U+248F: DIGIT EIGHT FULL STOP
1574 ,"8.", // Folded result
1576 "⑻" // U+247B: PARENTHESIZED DIGIT EIGHT
1577 ,"(8)", // Folded result
1579 "⁹" // U+2079: SUPERSCRIPT NINE
1580 + "₉" // U+2089: SUBSCRIPT NINE
1581 + "⑨" // U+2468: CIRCLED DIGIT NINE
1582 + "⓽" // U+24FD: DOUBLE CIRCLED DIGIT NINE
1583 + "❾" // U+277E: DINGBAT NEGATIVE CIRCLED DIGIT NINE
1584 + "➈" // U+2788: DINGBAT CIRCLED SANS-SERIF DIGIT NINE
1585 + "➒" // U+2792: DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT NINE
1586 + "9" // U+FF19: FULLWIDTH DIGIT NINE
1587 ,"9", // Folded result
1589 "⒐" // U+2490: DIGIT NINE FULL STOP
1590 ,"9.", // Folded result
1592 "⑼" // U+247C: PARENTHESIZED DIGIT NINE
1593 ,"(9)", // Folded result
1595 "⑩" // U+2469: CIRCLED NUMBER TEN
1596 + "⓾" // U+24FE: DOUBLE CIRCLED NUMBER TEN
1597 + "❿" // U+277F: DINGBAT NEGATIVE CIRCLED NUMBER TEN
1598 + "➉" // U+2789: DINGBAT CIRCLED SANS-SERIF NUMBER TEN
1599 + "➓" // U+2793: DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN
1600 ,"10", // Folded result
1602 "⒑" // U+2491: NUMBER TEN FULL STOP
1603 ,"10.", // Folded result
1605 "⑽" // U+247D: PARENTHESIZED NUMBER TEN
1606 ,"(10)", // Folded result
1608 "⑪" // U+246A: CIRCLED NUMBER ELEVEN
1609 + "⓫" // U+24EB: NEGATIVE CIRCLED NUMBER ELEVEN
1610 ,"11", // Folded result
1612 "⒒" // U+2492: NUMBER ELEVEN FULL STOP
1613 ,"11.", // Folded result
1615 "⑾" // U+247E: PARENTHESIZED NUMBER ELEVEN
1616 ,"(11)", // Folded result
1618 "⑫" // U+246B: CIRCLED NUMBER TWELVE
1619 + "⓬" // U+24EC: NEGATIVE CIRCLED NUMBER TWELVE
1620 ,"12", // Folded result
1622 "⒓" // U+2493: NUMBER TWELVE FULL STOP
1623 ,"12.", // Folded result
1625 "⑿" // U+247F: PARENTHESIZED NUMBER TWELVE
1626 ,"(12)", // Folded result
1628 "⑬" // U+246C: CIRCLED NUMBER THIRTEEN
1629 + "⓭" // U+24ED: NEGATIVE CIRCLED NUMBER THIRTEEN
1630 ,"13", // Folded result
1632 "⒔" // U+2494: NUMBER THIRTEEN FULL STOP
1633 ,"13.", // Folded result
1635 "⒀" // U+2480: PARENTHESIZED NUMBER THIRTEEN
1636 ,"(13)", // Folded result
1638 "⑭" // U+246D: CIRCLED NUMBER FOURTEEN
1639 + "⓮" // U+24EE: NEGATIVE CIRCLED NUMBER FOURTEEN
1640 ,"14", // Folded result
1642 "⒕" // U+2495: NUMBER FOURTEEN FULL STOP
1643 ,"14.", // Folded result
1645 "⒁" // U+2481: PARENTHESIZED NUMBER FOURTEEN
1646 ,"(14)", // Folded result
1648 "⑮" // U+246E: CIRCLED NUMBER FIFTEEN
1649 + "⓯" // U+24EF: NEGATIVE CIRCLED NUMBER FIFTEEN
1650 ,"15", // Folded result
1652 "⒖" // U+2496: NUMBER FIFTEEN FULL STOP
1653 ,"15.", // Folded result
1655 "⒂" // U+2482: PARENTHESIZED NUMBER FIFTEEN
1656 ,"(15)", // Folded result
1658 "⑯" // U+246F: CIRCLED NUMBER SIXTEEN
1659 + "⓰" // U+24F0: NEGATIVE CIRCLED NUMBER SIXTEEN
1660 ,"16", // Folded result
1662 "⒗" // U+2497: NUMBER SIXTEEN FULL STOP
1663 ,"16.", // Folded result
1665 "⒃" // U+2483: PARENTHESIZED NUMBER SIXTEEN
1666 ,"(16)", // Folded result
1668 "⑰" // U+2470: CIRCLED NUMBER SEVENTEEN
1669 + "⓱" // U+24F1: NEGATIVE CIRCLED NUMBER SEVENTEEN
1670 ,"17", // Folded result
1672 "⒘" // U+2498: NUMBER SEVENTEEN FULL STOP
1673 ,"17.", // Folded result
1675 "⒄" // U+2484: PARENTHESIZED NUMBER SEVENTEEN
1676 ,"(17)", // Folded result
1678 "⑱" // U+2471: CIRCLED NUMBER EIGHTEEN
1679 + "⓲" // U+24F2: NEGATIVE CIRCLED NUMBER EIGHTEEN
1680 ,"18", // Folded result
1682 "⒙" // U+2499: NUMBER EIGHTEEN FULL STOP
1683 ,"18.", // Folded result
1685 "⒅" // U+2485: PARENTHESIZED NUMBER EIGHTEEN
1686 ,"(18)", // Folded result
1688 "⑲" // U+2472: CIRCLED NUMBER NINETEEN
1689 + "⓳" // U+24F3: NEGATIVE CIRCLED NUMBER NINETEEN
1690 ,"19", // Folded result
1692 "⒚" // U+249A: NUMBER NINETEEN FULL STOP
1693 ,"19.", // Folded result
1695 "⒆" // U+2486: PARENTHESIZED NUMBER NINETEEN
1696 ,"(19)", // Folded result
1698 "⑳" // U+2473: CIRCLED NUMBER TWENTY
1699 + "⓴" // U+24F4: NEGATIVE CIRCLED NUMBER TWENTY
1700 ,"20", // Folded result
1702 "⒛" // U+249B: NUMBER TWENTY FULL STOP
1703 ,"20.", // Folded result
1705 "⒇" // U+2487: PARENTHESIZED NUMBER TWENTY
1706 ,"(20)", // Folded result
1708 "«" // U+00AB: LEFT-POINTING DOUBLE ANGLE QUOTATION MARK
1709 + "»" // U+00BB: RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK
1710 + "“" // U+201C: LEFT DOUBLE QUOTATION MARK
1711 + "”" // U+201D: RIGHT DOUBLE QUOTATION MARK
1712 + "„" // U+201E: DOUBLE LOW-9 QUOTATION MARK
1713 + "″" // U+2033: DOUBLE PRIME
1714 + "‶" // U+2036: REVERSED DOUBLE PRIME
1715 + "❝" // U+275D: HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT
1716 + "❞" // U+275E: HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT
1717 + "❮" // U+276E: HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT
1718 + "❯" // U+276F: HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT
1719 + """ // U+FF02: FULLWIDTH QUOTATION MARK
1720 ,"\"", // Folded result
1722 "‘" // U+2018: LEFT SINGLE QUOTATION MARK
1723 + "’" // U+2019: RIGHT SINGLE QUOTATION MARK
1724 + "‚" // U+201A: SINGLE LOW-9 QUOTATION MARK
1725 + "‛" // U+201B: SINGLE HIGH-REVERSED-9 QUOTATION MARK
1726 + "′" // U+2032: PRIME
1727 + "‵" // U+2035: REVERSED PRIME
1728 + "‹" // U+2039: SINGLE LEFT-POINTING ANGLE QUOTATION MARK
1729 + "›" // U+203A: SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
1730 + "❛" // U+275B: HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT
1731 + "❜" // U+275C: HEAVY SINGLE COMMA QUOTATION MARK ORNAMENT
1732 + "'" // U+FF07: FULLWIDTH APOSTROPHE
1733 ,"'", // Folded result
1735 "‐" // U+2010: HYPHEN
1736 + "‑" // U+2011: NON-BREAKING HYPHEN
1737 + "‒" // U+2012: FIGURE DASH
1738 + "–" // U+2013: EN DASH
1739 + "—" // U+2014: EM DASH
1740 + "⁻" // U+207B: SUPERSCRIPT MINUS
1741 + "₋" // U+208B: SUBSCRIPT MINUS
1742 + "-" // U+FF0D: FULLWIDTH HYPHEN-MINUS
1743 ,"-", // Folded result
1745 "⁅" // U+2045: LEFT SQUARE BRACKET WITH QUILL
1746 + "❲" // U+2772: LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT
1747 + "[" // U+FF3B: FULLWIDTH LEFT SQUARE BRACKET
1748 ,"[", // Folded result
1750 "⁆" // U+2046: RIGHT SQUARE BRACKET WITH QUILL
1751 + "❳" // U+2773: LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT
1752 + "]" // U+FF3D: FULLWIDTH RIGHT SQUARE BRACKET
1753 ,"]", // Folded result
1755 "⁽" // U+207D: SUPERSCRIPT LEFT PARENTHESIS
1756 + "₍" // U+208D: SUBSCRIPT LEFT PARENTHESIS
1757 + "❨" // U+2768: MEDIUM LEFT PARENTHESIS ORNAMENT
1758 + "❪" // U+276A: MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT
1759 + "(" // U+FF08: FULLWIDTH LEFT PARENTHESIS
1760 ,"(", // Folded result
1762 "⸨" // U+2E28: LEFT DOUBLE PARENTHESIS
1763 ,"((", // Folded result
1765 "⁾" // U+207E: SUPERSCRIPT RIGHT PARENTHESIS
1766 + "₎" // U+208E: SUBSCRIPT RIGHT PARENTHESIS
1767 + "❩" // U+2769: MEDIUM RIGHT PARENTHESIS ORNAMENT
1768 + "❫" // U+276B: MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT
1769 + ")" // U+FF09: FULLWIDTH RIGHT PARENTHESIS
1770 ,")", // Folded result
1772 "⸩" // U+2E29: RIGHT DOUBLE PARENTHESIS
1773 ,"))", // Folded result
1775 "❬" // U+276C: MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT
1776 + "❰" // U+2770: HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT
1777 + "<" // U+FF1C: FULLWIDTH LESS-THAN SIGN
1778 ,"<", // Folded result
1780 "❭" // U+276D: MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT
1781 + "❱" // U+2771: HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT
1782 + ">" // U+FF1E: FULLWIDTH GREATER-THAN SIGN
1783 ,">", // Folded result
1785 "❴" // U+2774: MEDIUM LEFT CURLY BRACKET ORNAMENT
1786 + "{" // U+FF5B: FULLWIDTH LEFT CURLY BRACKET
1787 ,"{", // Folded result
1789 "❵" // U+2775: MEDIUM RIGHT CURLY BRACKET ORNAMENT
1790 + "}" // U+FF5D: FULLWIDTH RIGHT CURLY BRACKET
1791 ,"}", // Folded result
1793 "⁺" // U+207A: SUPERSCRIPT PLUS SIGN
1794 + "₊" // U+208A: SUBSCRIPT PLUS SIGN
1795 + "+" // U+FF0B: FULLWIDTH PLUS SIGN
1796 ,"+", // Folded result
1798 "⁼" // U+207C: SUPERSCRIPT EQUALS SIGN
1799 + "₌" // U+208C: SUBSCRIPT EQUALS SIGN
1800 + "=" // U+FF1D: FULLWIDTH EQUALS SIGN
1801 ,"=", // Folded result
1803 "!" // U+FF01: FULLWIDTH EXCLAMATION MARK
1804 ,"!", // Folded result
1806 "‼" // U+203C: DOUBLE EXCLAMATION MARK
1807 ,"!!", // Folded result
1809 "⁉" // U+2049: EXCLAMATION QUESTION MARK
1810 ,"!?", // Folded result
1812 "#" // U+FF03: FULLWIDTH NUMBER SIGN
1813 ,"#", // Folded result
1815 "$" // U+FF04: FULLWIDTH DOLLAR SIGN
1816 ,"$", // Folded result
1818 "⁒" // U+2052: COMMERCIAL MINUS SIGN
1819 + "%" // U+FF05: FULLWIDTH PERCENT SIGN
1820 ,"%", // Folded result
1822 "&" // U+FF06: FULLWIDTH AMPERSAND
1823 ,"&", // Folded result
1825 "⁎" // U+204E: LOW ASTERISK
1826 + "*" // U+FF0A: FULLWIDTH ASTERISK
1827 ,"*", // Folded result
1829 "," // U+FF0C: FULLWIDTH COMMA
1830 ,",", // Folded result
1832 "." // U+FF0E: FULLWIDTH FULL STOP
1833 ,".", // Folded result
1835 "⁄" // U+2044: FRACTION SLASH
1836 + "/" // U+FF0F: FULLWIDTH SOLIDUS
1837 ,"/", // Folded result
1839 ":" // U+FF1A: FULLWIDTH COLON
1840 ,":", // Folded result
1842 "⁏" // U+204F: REVERSED SEMICOLON
1843 + ";" // U+FF1B: FULLWIDTH SEMICOLON
1844 ,";", // Folded result
1846 "?" // U+FF1F: FULLWIDTH QUESTION MARK
1847 ,"?", // Folded result
1849 "⁇" // U+2047: DOUBLE QUESTION MARK
1850 ,"??", // Folded result
1852 "⁈" // U+2048: QUESTION EXCLAMATION MARK
1853 ,"?!", // Folded result
1855 "@" // U+FF20: FULLWIDTH COMMERCIAL AT
1856 ,"@", // Folded result
1858 "\" // U+FF3C: FULLWIDTH REVERSE SOLIDUS
1859 ,"\\", // Folded result
1861 "‸" // U+2038: CARET
1862 + "^" // U+FF3E: FULLWIDTH CIRCUMFLEX ACCENT
1863 ,"^", // Folded result
1865 "_" // U+FF3F: FULLWIDTH LOW LINE
1866 ,"_", // Folded result
1868 "⁓" // U+2053: SWUNG DASH
1869 + "~" // U+FF5E: FULLWIDTH TILDE
1870 ,"~", // Folded result
1873 // Construct input text and expected output tokens
1874 List<String> expectedOutputTokens = new ArrayList<String>();
1875 StringBuilder inputText = new StringBuilder();
1876 for (int n = 0 ; n < foldings.length ; n += 2) {
1878 inputText.append(' '); // Space between tokens
1880 inputText.append(foldings[n]);
1882 // Construct the expected output token: the ASCII string to fold to,
1883 // duplicated as many times as the number of characters in the input text.
1884 StringBuilder expected = new StringBuilder();
1885 int numChars = foldings[n].length();
1886 for (int m = 0 ; m < numChars; ++m) {
1887 expected.append(foldings[n + 1]);
1889 expectedOutputTokens.add(expected.toString());
1892 TokenStream stream = new MockTokenizer(new StringReader(inputText.toString()), MockTokenizer.WHITESPACE, false);
1893 ASCIIFoldingFilter filter = new ASCIIFoldingFilter(stream);
1894 CharTermAttribute termAtt = filter.getAttribute(CharTermAttribute.class);
1895 Iterator<String> expectedIter = expectedOutputTokens.iterator();
1897 while (expectedIter.hasNext()) {
1898 assertTermEquals(expectedIter.next(), filter, termAtt);
1900 assertFalse(filter.incrementToken());
1903 void assertTermEquals(String expected, TokenStream stream, CharTermAttribute termAtt) throws Exception {
1904 assertTrue(stream.incrementToken());
1905 assertEquals(expected, termAtt.toString());