source: gs3-extensions/solr/trunk/src/conf/mapping-FoldToASCII.txt@ 29135

Last change on this file since 29135 was 29135, checked in by ak19, 10 years ago

Part of port from lucene3.3.0 to lucene4.7.2. Solr related. conf and lib folders for solr4.7.2.

File size: 76.7 KB
Line 
1# The ASF licenses this file to You under the Apache License, Version 2.0
2# (the "License"); you may not use this file except in compliance with
3# the License. You may obtain a copy of the License at
4#
5# http://www.apache.org/licenses/LICENSE-2.0
6#
7# Unless required by applicable law or agreed to in writing, software
8# distributed under the License is distributed on an "AS IS" BASIS,
9# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
10# See the License for the specific language governing permissions and
11# limitations under the License.
12
13
14# This map converts alphabetic, numeric, and symbolic Unicode characters
15# which are not in the first 127 ASCII characters (the "Basic Latin" Unicode
16# block) into their ASCII equivalents, if one exists.
17#
18# Characters from the following Unicode blocks are converted; however, only
19# those characters with reasonable ASCII alternatives are converted:
20#
21# - C1 Controls and Latin-1 Supplement: http://www.unicode.org/charts/PDF/U0080.pdf
22# - Latin Extended-A: http://www.unicode.org/charts/PDF/U0100.pdf
23# - Latin Extended-B: http://www.unicode.org/charts/PDF/U0180.pdf
24# - Latin Extended Additional: http://www.unicode.org/charts/PDF/U1E00.pdf
25# - Latin Extended-C: http://www.unicode.org/charts/PDF/U2C60.pdf
26# - Latin Extended-D: http://www.unicode.org/charts/PDF/UA720.pdf
27# - IPA Extensions: http://www.unicode.org/charts/PDF/U0250.pdf
28# - Phonetic Extensions: http://www.unicode.org/charts/PDF/U1D00.pdf
29# - Phonetic Extensions Supplement: http://www.unicode.org/charts/PDF/U1D80.pdf
30# - General Punctuation: http://www.unicode.org/charts/PDF/U2000.pdf
31# - Superscripts and Subscripts: http://www.unicode.org/charts/PDF/U2070.pdf
32# - Enclosed Alphanumerics: http://www.unicode.org/charts/PDF/U2460.pdf
33# - Dingbats: http://www.unicode.org/charts/PDF/U2700.pdf
34# - Supplemental Punctuation: http://www.unicode.org/charts/PDF/U2E00.pdf
35# - Alphabetic Presentation Forms: http://www.unicode.org/charts/PDF/UFB00.pdf
36# - Halfwidth and Fullwidth Forms: http://www.unicode.org/charts/PDF/UFF00.pdf
37#
38# See: http://en.wikipedia.org/wiki/Latin_characters_in_Unicode
39#
40# The set of character conversions supported by this map is a superset of
41# those supported by the map represented by mapping-ISOLatin1Accent.txt.
42#
43# See the bottom of this file for the Perl script used to generate the contents
44# of this file (without this header) from ASCIIFoldingFilter.java.
45
46
47# Syntax:
48# "source" => "target"
49# "source".length() > 0 (source cannot be empty.)
50# "target".length() >= 0 (target can be empty.)
51
52
53# À [LATIN CAPITAL LETTER A WITH GRAVE]
54"\u00C0" => "A"
55
56# Á [LATIN CAPITAL LETTER A WITH ACUTE]
57"\u00C1" => "A"
58
59# Â [LATIN CAPITAL LETTER A WITH CIRCUMFLEX]
60"\u00C2" => "A"
61
62# Ã [LATIN CAPITAL LETTER A WITH TILDE]
63"\u00C3" => "A"
64
65# Ä [LATIN CAPITAL LETTER A WITH DIAERESIS]
66"\u00C4" => "A"
67
68# Å
69 [LATIN CAPITAL LETTER A WITH RING ABOVE]
70"\u00C5" => "A"
71
72# Ā [LATIN CAPITAL LETTER A WITH MACRON]
73"\u0100" => "A"
74
75# Ă [LATIN CAPITAL LETTER A WITH BREVE]
76"\u0102" => "A"
77
78# Ą [LATIN CAPITAL LETTER A WITH OGONEK]
79"\u0104" => "A"
80
81# Ə http://en.wikipedia.org/wiki/Schwa [LATIN CAPITAL LETTER SCHWA]
82"\u018F" => "A"
83
84# Ǎ [LATIN CAPITAL LETTER A WITH CARON]
85"\u01CD" => "A"
86
87# Ǟ [LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON]
88"\u01DE" => "A"
89
90# Ç  [LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON]
91"\u01E0" => "A"
92
93# Ǻ [LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE]
94"\u01FA" => "A"
95
96# Ȁ [LATIN CAPITAL LETTER A WITH DOUBLE GRAVE]
97"\u0200" => "A"
98
99# Ȃ [LATIN CAPITAL LETTER A WITH INVERTED BREVE]
100"\u0202" => "A"
101
102# ÈŠ [LATIN CAPITAL LETTER A WITH DOT ABOVE]
103"\u0226" => "A"
104
105# Ⱥ [LATIN CAPITAL LETTER A WITH STROKE]
106"\u023A" => "A"
107
108# ᮀ [LATIN LETTER SMALL CAPITAL A]
109"\u1D00" => "A"
110
111# ᾀ [LATIN CAPITAL LETTER A WITH RING BELOW]
112"\u1E00" => "A"
113
114# Ạ [LATIN CAPITAL LETTER A WITH DOT BELOW]
115"\u1EA0" => "A"
116
117# Ả [LATIN CAPITAL LETTER A WITH HOOK ABOVE]
118"\u1EA2" => "A"
119
120# Ẁ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE]
121"\u1EA4" => "A"
122
123# Ẋ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE]
124"\u1EA6" => "A"
125
126# ẚ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE]
127"\u1EA8" => "A"
128
129# Ẫ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE]
130"\u1EAA" => "A"
131
132# Ậ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW]
133"\u1EAC" => "A"
134
135# Ắ [LATIN CAPITAL LETTER A WITH BREVE AND ACUTE]
136"\u1EAE" => "A"
137
138# Ằ [LATIN CAPITAL LETTER A WITH BREVE AND GRAVE]
139"\u1EB0" => "A"
140
141# Ẳ [LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE]
142"\u1EB2" => "A"
143
144# Ẏ [LATIN CAPITAL LETTER A WITH BREVE AND TILDE]
145"\u1EB4" => "A"
146
147# Ặ [LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW]
148"\u1EB6" => "A"
149
150# Ⓐ [CIRCLED LATIN CAPITAL LETTER A]
151"\u24B6" => "A"
152
153#  [FULLWIDTH LATIN CAPITAL LETTER A]
154"\uFF21" => "A"
155
156# à [LATIN SMALL LETTER A WITH GRAVE]
157"\u00E0" => "a"
158
159# á [LATIN SMALL LETTER A WITH ACUTE]
160"\u00E1" => "a"
161
162# â [LATIN SMALL LETTER A WITH CIRCUMFLEX]
163"\u00E2" => "a"
164
165# ã [LATIN SMALL LETTER A WITH TILDE]
166"\u00E3" => "a"
167
168# À [LATIN SMALL LETTER A WITH DIAERESIS]
169"\u00E4" => "a"
170
171# å [LATIN SMALL LETTER A WITH RING ABOVE]
172"\u00E5" => "a"
173
174# ā [LATIN SMALL LETTER A WITH MACRON]
175"\u0101" => "a"
176
177# ă [LATIN SMALL LETTER A WITH BREVE]
178"\u0103" => "a"
179
180# ą
181 [LATIN SMALL LETTER A WITH OGONEK]
182"\u0105" => "a"
183
184# ǎ [LATIN SMALL LETTER A WITH CARON]
185"\u01CE" => "a"
186
187# ǟ [LATIN SMALL LETTER A WITH DIAERESIS AND MACRON]
188"\u01DF" => "a"
189
190# Ç¡ [LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON]
191"\u01E1" => "a"
192
193# Ç» [LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE]
194"\u01FB" => "a"
195
196# ȁ [LATIN SMALL LETTER A WITH DOUBLE GRAVE]
197"\u0201" => "a"
198
199# ȃ [LATIN SMALL LETTER A WITH INVERTED BREVE]
200"\u0203" => "a"
201
202# ȧ [LATIN SMALL LETTER A WITH DOT ABOVE]
203"\u0227" => "a"
204
205# ɐ [LATIN SMALL LETTER TURNED A]
206"\u0250" => "a"
207
208# ə [LATIN SMALL LETTER SCHWA]
209"\u0259" => "a"
210
211# ɚ [LATIN SMALL LETTER SCHWA WITH HOOK]
212"\u025A" => "a"
213
214# ᶏ [LATIN SMALL LETTER A WITH RETROFLEX HOOK]
215"\u1D8F" => "a"
216
217# ᶕ [LATIN SMALL LETTER SCHWA WITH RETROFLEX HOOK]
218"\u1D95" => "a"
219
220# ạ [LATIN SMALL LETTER A WITH RING BELOW]
221"\u1E01" => "a"
222
223# ả [LATIN SMALL LETTER A WITH RIGHT HALF RING]
224"\u1E9A" => "a"
225
226# ạ [LATIN SMALL LETTER A WITH DOT BELOW]
227"\u1EA1" => "a"
228
229# ả [LATIN SMALL LETTER A WITH HOOK ABOVE]
230"\u1EA3" => "a"
231
232# ấ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE]
233"\u1EA5" => "a"
234
235# ầ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE]
236"\u1EA7" => "a"
237
238# ẩ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE]
239"\u1EA9" => "a"
240
241# ẫ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE]
242"\u1EAB" => "a"
243
244# ậ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW]
245"\u1EAD" => "a"
246
247# ắ [LATIN SMALL LETTER A WITH BREVE AND ACUTE]
248"\u1EAF" => "a"
249
250# ằ [LATIN SMALL LETTER A WITH BREVE AND GRAVE]
251"\u1EB1" => "a"
252
253# ẳ [LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE]
254"\u1EB3" => "a"
255
256# ẵ [LATIN SMALL LETTER A WITH BREVE AND TILDE]
257"\u1EB5" => "a"
258
259# ặ [LATIN SMALL LETTER A WITH BREVE AND DOT BELOW]
260"\u1EB7" => "a"
261
262# ₐ [LATIN SUBSCRIPT SMALL LETTER A]
263"\u2090" => "a"
264
265# ₔ [LATIN SUBSCRIPT SMALL LETTER SCHWA]
266"\u2094" => "a"
267
268# ⓐ [CIRCLED LATIN SMALL LETTER A]
269"\u24D0" => "a"
270
271# â±¥ [LATIN SMALL LETTER A WITH STROKE]
272"\u2C65" => "a"
273
274# Ɐ [LATIN CAPITAL LETTER TURNED A]
275"\u2C6F" => "a"
276
277#  [FULLWIDTH LATIN SMALL LETTER A]
278"\uFF41" => "a"
279
280# Ꜳ [LATIN CAPITAL LETTER AA]
281"\uA732" => "AA"
282
283# Æ [LATIN CAPITAL LETTER AE]
284"\u00C6" => "AE"
285
286# Ǣ [LATIN CAPITAL LETTER AE WITH MACRON]
287"\u01E2" => "AE"
288
289# nj [LATIN CAPITAL LETTER AE WITH ACUTE]
290"\u01FC" => "AE"
291
292# ᎁ [LATIN LETTER SMALL CAPITAL AE]
293"\u1D01" => "AE"
294
295# ꜎ [LATIN CAPITAL LETTER AO]
296"\uA734" => "AO"
297
298# Ꜷ [LATIN CAPITAL LETTER AU]
299"\uA736" => "AU"
300
301# ꜞ [LATIN CAPITAL LETTER AV]
302"\uA738" => "AV"
303
304# Ꜻ [LATIN CAPITAL LETTER AV WITH HORIZONTAL BAR]
305"\uA73A" => "AV"
306
307# ꜌ [LATIN CAPITAL LETTER AY]
308"\uA73C" => "AY"
309
310# ⒜ [PARENTHESIZED LATIN SMALL LETTER A]
311"\u249C" => "(a)"
312
313# ꜳ [LATIN SMALL LETTER AA]
314"\uA733" => "aa"
315
316# Ê [LATIN SMALL LETTER AE]
317"\u00E6" => "ae"
318
319# ǣ [LATIN SMALL LETTER AE WITH MACRON]
320"\u01E3" => "ae"
321
322# ǜ [LATIN SMALL LETTER AE WITH ACUTE]
323"\u01FD" => "ae"
324
325# ᮂ [LATIN SMALL LETTER TURNED AE]
326"\u1D02" => "ae"
327
328# ꜵ [LATIN SMALL LETTER AO]
329"\uA735" => "ao"
330
331# ꜷ [LATIN SMALL LETTER AU]
332"\uA737" => "au"
333
334# ꜹ [LATIN SMALL LETTER AV]
335"\uA739" => "av"
336
337# ꜻ [LATIN SMALL LETTER AV WITH HORIZONTAL BAR]
338"\uA73B" => "av"
339
340# ꜜ [LATIN SMALL LETTER AY]
341"\uA73D" => "ay"
342
343# Ɓ [LATIN CAPITAL LETTER B WITH HOOK]
344"\u0181" => "B"
345
346# Ƃ [LATIN CAPITAL LETTER B WITH TOPBAR]
347"\u0182" => "B"
348
349# Ƀ [LATIN CAPITAL LETTER B WITH STROKE]
350"\u0243" => "B"
351
352# ʙ [LATIN LETTER SMALL CAPITAL B]
353"\u0299" => "B"
354
355# ᎃ [LATIN LETTER SMALL CAPITAL BARRED B]
356"\u1D03" => "B"
357
358# ᾂ [LATIN CAPITAL LETTER B WITH DOT ABOVE]
359"\u1E02" => "B"
360
361# ᾄ [LATIN CAPITAL LETTER B WITH DOT BELOW]
362"\u1E04" => "B"
363
364# ᾆ [LATIN CAPITAL LETTER B WITH LINE BELOW]
365"\u1E06" => "B"
366
367# Ⓑ [CIRCLED LATIN CAPITAL LETTER B]
368"\u24B7" => "B"
369
370#  [FULLWIDTH LATIN CAPITAL LETTER B]
371"\uFF22" => "B"
372
373# ƀ [LATIN SMALL LETTER B WITH STROKE]
374"\u0180" => "b"
375
376# ƃ [LATIN SMALL LETTER B WITH TOPBAR]
377"\u0183" => "b"
378
379# ɓ [LATIN SMALL LETTER B WITH HOOK]
380"\u0253" => "b"
381
382# ᵬ [LATIN SMALL LETTER B WITH MIDDLE TILDE]
383"\u1D6C" => "b"
384
385# ᶀ [LATIN SMALL LETTER B WITH PALATAL HOOK]
386"\u1D80" => "b"
387
388# ឃ [LATIN SMALL LETTER B WITH DOT ABOVE]
389"\u1E03" => "b"
390
391# ᾅ
392 [LATIN SMALL LETTER B WITH DOT BELOW]
393"\u1E05" => "b"
394
395# ᾇ [LATIN SMALL LETTER B WITH LINE BELOW]
396"\u1E07" => "b"
397
398# ⓑ [CIRCLED LATIN SMALL LETTER B]
399"\u24D1" => "b"
400
401#  [FULLWIDTH LATIN SMALL LETTER B]
402"\uFF42" => "b"
403
404# ⒝ [PARENTHESIZED LATIN SMALL LETTER B]
405"\u249D" => "(b)"
406
407# Ç [LATIN CAPITAL LETTER C WITH CEDILLA]
408"\u00C7" => "C"
409
410# Ć [LATIN CAPITAL LETTER C WITH ACUTE]
411"\u0106" => "C"
412
413# Ĉ [LATIN CAPITAL LETTER C WITH CIRCUMFLEX]
414"\u0108" => "C"
415
416# Ċ [LATIN CAPITAL LETTER C WITH DOT ABOVE]
417"\u010A" => "C"
418
419# Č [LATIN CAPITAL LETTER C WITH CARON]
420"\u010C" => "C"
421
422# Ƈ [LATIN CAPITAL LETTER C WITH HOOK]
423"\u0187" => "C"
424
425# È» [LATIN CAPITAL LETTER C WITH STROKE]
426"\u023B" => "C"
427
428# ʗ [LATIN LETTER STRETCHED C]
429"\u0297" => "C"
430
431# ᮄ [LATIN LETTER SMALL CAPITAL C]
432"\u1D04" => "C"
433
434# ឈ [LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE]
435"\u1E08" => "C"
436
437# Ⓘ [CIRCLED LATIN CAPITAL LETTER C]
438"\u24B8" => "C"
439
440#  [FULLWIDTH LATIN CAPITAL LETTER C]
441"\uFF23" => "C"
442
443# ç [LATIN SMALL LETTER C WITH CEDILLA]
444"\u00E7" => "c"
445
446# ć [LATIN SMALL LETTER C WITH ACUTE]
447"\u0107" => "c"
448
449# ĉ [LATIN SMALL LETTER C WITH CIRCUMFLEX]
450"\u0109" => "c"
451
452# ċ [LATIN SMALL LETTER C WITH DOT ABOVE]
453"\u010B" => "c"
454
455# č [LATIN SMALL LETTER C WITH CARON]
456"\u010D" => "c"
457
458# ƈ [LATIN SMALL LETTER C WITH HOOK]
459"\u0188" => "c"
460
461# Ȍ [LATIN SMALL LETTER C WITH STROKE]
462"\u023C" => "c"
463
464# ɕ [LATIN SMALL LETTER C WITH CURL]
465"\u0255" => "c"
466
467# ᾉ [LATIN SMALL LETTER C WITH CEDILLA AND ACUTE]
468"\u1E09" => "c"
469
470# ↄ [LATIN SMALL LETTER REVERSED C]
471"\u2184" => "c"
472
473# ⓒ [CIRCLED LATIN SMALL LETTER C]
474"\u24D2" => "c"
475
476# ꜟ [LATIN CAPITAL LETTER REVERSED C WITH DOT]
477"\uA73E" => "c"
478
479# ꜿ [LATIN SMALL LETTER REVERSED C WITH DOT]
480"\uA73F" => "c"
481
482#  [FULLWIDTH LATIN SMALL LETTER C]
483"\uFF43" => "c"
484
485# ⒞ [PARENTHESIZED LATIN SMALL LETTER C]
486"\u249E" => "(c)"
487
488# Ð [LATIN CAPITAL LETTER ETH]
489"\u00D0" => "D"
490
491# Ď [LATIN CAPITAL LETTER D WITH CARON]
492"\u010E" => "D"
493
494# Đ [LATIN CAPITAL LETTER D WITH STROKE]
495"\u0110" => "D"
496
497# Ɖ [LATIN CAPITAL LETTER AFRICAN D]
498"\u0189" => "D"
499
500# Ɗ [LATIN CAPITAL LETTER D WITH HOOK]
501"\u018A" => "D"
502
503# Ƌ [LATIN CAPITAL LETTER D WITH TOPBAR]
504"\u018B" => "D"
505
506# ᮅ
507 [LATIN LETTER SMALL CAPITAL D]
508"\u1D05" => "D"
509
510# ᮆ [LATIN LETTER SMALL CAPITAL ETH]
511"\u1D06" => "D"
512
513# ᾊ [LATIN CAPITAL LETTER D WITH DOT ABOVE]
514"\u1E0A" => "D"
515
516# ᾌ [LATIN CAPITAL LETTER D WITH DOT BELOW]
517"\u1E0C" => "D"
518
519# ᾎ [LATIN CAPITAL LETTER D WITH LINE BELOW]
520"\u1E0E" => "D"
521
522# ថ [LATIN CAPITAL LETTER D WITH CEDILLA]
523"\u1E10" => "D"
524
525# ᾒ [LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW]
526"\u1E12" => "D"
527
528# Ⓓ [CIRCLED LATIN CAPITAL LETTER D]
529"\u24B9" => "D"
530
531# Ꝺ [LATIN CAPITAL LETTER INSULAR D]
532"\uA779" => "D"
533
534#  [FULLWIDTH LATIN CAPITAL LETTER D]
535"\uFF24" => "D"
536
537# ð [LATIN SMALL LETTER ETH]
538"\u00F0" => "d"
539
540# ď [LATIN SMALL LETTER D WITH CARON]
541"\u010F" => "d"
542
543# đ [LATIN SMALL LETTER D WITH STROKE]
544"\u0111" => "d"
545
546# ƌ [LATIN SMALL LETTER D WITH TOPBAR]
547"\u018C" => "d"
548
549# È¡ [LATIN SMALL LETTER D WITH CURL]
550"\u0221" => "d"
551
552# ɖ [LATIN SMALL LETTER D WITH TAIL]
553"\u0256" => "d"
554
555# ɗ [LATIN SMALL LETTER D WITH HOOK]
556"\u0257" => "d"
557
558# áµ­ [LATIN SMALL LETTER D WITH MIDDLE TILDE]
559"\u1D6D" => "d"
560
561# ᶁ [LATIN SMALL LETTER D WITH PALATAL HOOK]
562"\u1D81" => "d"
563
564# ᶑ [LATIN SMALL LETTER D WITH HOOK AND TAIL]
565"\u1D91" => "d"
566
567# ᾋ [LATIN SMALL LETTER D WITH DOT ABOVE]
568"\u1E0B" => "d"
569
570# ឍ [LATIN SMALL LETTER D WITH DOT BELOW]
571"\u1E0D" => "d"
572
573# ត [LATIN SMALL LETTER D WITH LINE BELOW]
574"\u1E0F" => "d"
575
576# ᾑ [LATIN SMALL LETTER D WITH CEDILLA]
577"\u1E11" => "d"
578
579# ᾓ [LATIN SMALL LETTER D WITH CIRCUMFLEX BELOW]
580"\u1E13" => "d"
581
582# ⓓ [CIRCLED LATIN SMALL LETTER D]
583"\u24D3" => "d"
584
585# ꝺ [LATIN SMALL LETTER INSULAR D]
586"\uA77A" => "d"
587
588#  [FULLWIDTH LATIN SMALL LETTER D]
589"\uFF44" => "d"
590
591# DŽ [LATIN CAPITAL LETTER DZ WITH CARON]
592"\u01C4" => "DZ"
593
594# DZ [LATIN CAPITAL LETTER DZ]
595"\u01F1" => "DZ"
596
597# Dž
598 [LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON]
599"\u01C5" => "Dz"
600
601# Dz [LATIN CAPITAL LETTER D WITH SMALL LETTER Z]
602"\u01F2" => "Dz"
603
604# ⒟ [PARENTHESIZED LATIN SMALL LETTER D]
605"\u249F" => "(d)"
606
607# Èž [LATIN SMALL LETTER DB DIGRAPH]
608"\u0238" => "db"
609
610# dž [LATIN SMALL LETTER DZ WITH CARON]
611"\u01C6" => "dz"
612
613# dz [LATIN SMALL LETTER DZ]
614"\u01F3" => "dz"
615
616# ʣ [LATIN SMALL LETTER DZ DIGRAPH]
617"\u02A3" => "dz"
618
619# ʥ [LATIN SMALL LETTER DZ DIGRAPH WITH CURL]
620"\u02A5" => "dz"
621
622# È [LATIN CAPITAL LETTER E WITH GRAVE]
623"\u00C8" => "E"
624
625# É [LATIN CAPITAL LETTER E WITH ACUTE]
626"\u00C9" => "E"
627
628# Ê [LATIN CAPITAL LETTER E WITH CIRCUMFLEX]
629"\u00CA" => "E"
630
631# Ë [LATIN CAPITAL LETTER E WITH DIAERESIS]
632"\u00CB" => "E"
633
634# Ē [LATIN CAPITAL LETTER E WITH MACRON]
635"\u0112" => "E"
636
637# Ĕ [LATIN CAPITAL LETTER E WITH BREVE]
638"\u0114" => "E"
639
640# Ė [LATIN CAPITAL LETTER E WITH DOT ABOVE]
641"\u0116" => "E"
642
643# Ę [LATIN CAPITAL LETTER E WITH OGONEK]
644"\u0118" => "E"
645
646# Ě [LATIN CAPITAL LETTER E WITH CARON]
647"\u011A" => "E"
648
649# Ǝ [LATIN CAPITAL LETTER REVERSED E]
650"\u018E" => "E"
651
652# Ɛ [LATIN CAPITAL LETTER OPEN E]
653"\u0190" => "E"
654
655# Ȅ [LATIN CAPITAL LETTER E WITH DOUBLE GRAVE]
656"\u0204" => "E"
657
658# Ȇ [LATIN CAPITAL LETTER E WITH INVERTED BREVE]
659"\u0206" => "E"
660
661# Èš [LATIN CAPITAL LETTER E WITH CEDILLA]
662"\u0228" => "E"
663
664# Ɇ [LATIN CAPITAL LETTER E WITH STROKE]
665"\u0246" => "E"
666
667# ᮇ [LATIN LETTER SMALL CAPITAL E]
668"\u1D07" => "E"
669
670# ᾔ [LATIN CAPITAL LETTER E WITH MACRON AND GRAVE]
671"\u1E14" => "E"
672
673# ᾖ [LATIN CAPITAL LETTER E WITH MACRON AND ACUTE]
674"\u1E16" => "E"
675
676# ម [LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW]
677"\u1E18" => "E"
678
679# ᾚ [LATIN CAPITAL LETTER E WITH TILDE BELOW]
680"\u1E1A" => "E"
681
682# ᾜ [LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE]
683"\u1E1C" => "E"
684
685# ẞ [LATIN CAPITAL LETTER E WITH DOT BELOW]
686"\u1EB8" => "E"
687
688# Ẻ [LATIN CAPITAL LETTER E WITH HOOK ABOVE]
689"\u1EBA" => "E"
690
691# Ẍ [LATIN CAPITAL LETTER E WITH TILDE]
692"\u1EBC" => "E"
693
694# ẟ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE]
695"\u1EBE" => "E"
696
697# Ề [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE]
698"\u1EC0" => "E"
699
700# Ể [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE]
701"\u1EC2" => "E"
702
703# Ễ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE]
704"\u1EC4" => "E"
705
706# Ệ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW]
707"\u1EC6" => "E"
708
709# Ⓔ [CIRCLED LATIN CAPITAL LETTER E]
710"\u24BA" => "E"
711
712# â±» [LATIN LETTER SMALL CAPITAL TURNED E]
713"\u2C7B" => "E"
714
715#  [FULLWIDTH LATIN CAPITAL LETTER E]
716"\uFF25" => "E"
717
718# Ú [LATIN SMALL LETTER E WITH GRAVE]
719"\u00E8" => "e"
720
721# é [LATIN SMALL LETTER E WITH ACUTE]
722"\u00E9" => "e"
723
724# ê [LATIN SMALL LETTER E WITH CIRCUMFLEX]
725"\u00EA" => "e"
726
727# ë [LATIN SMALL LETTER E WITH DIAERESIS]
728"\u00EB" => "e"
729
730# ē [LATIN SMALL LETTER E WITH MACRON]
731"\u0113" => "e"
732
733# ĕ [LATIN SMALL LETTER E WITH BREVE]
734"\u0115" => "e"
735
736# ė [LATIN SMALL LETTER E WITH DOT ABOVE]
737"\u0117" => "e"
738
739# ę [LATIN SMALL LETTER E WITH OGONEK]
740"\u0119" => "e"
741
742# ě [LATIN SMALL LETTER E WITH CARON]
743"\u011B" => "e"
744
745# ǝ [LATIN SMALL LETTER TURNED E]
746"\u01DD" => "e"
747
748# ȅ
749 [LATIN SMALL LETTER E WITH DOUBLE GRAVE]
750"\u0205" => "e"
751
752# ȇ [LATIN SMALL LETTER E WITH INVERTED BREVE]
753"\u0207" => "e"
754
755# È© [LATIN SMALL LETTER E WITH CEDILLA]
756"\u0229" => "e"
757
758# ɇ [LATIN SMALL LETTER E WITH STROKE]
759"\u0247" => "e"
760
761# ɘ [LATIN SMALL LETTER REVERSED E]
762"\u0258" => "e"
763
764# ɛ [LATIN SMALL LETTER OPEN E]
765"\u025B" => "e"
766
767# ɜ [LATIN SMALL LETTER REVERSED OPEN E]
768"\u025C" => "e"
769
770# ɝ [LATIN SMALL LETTER REVERSED OPEN E WITH HOOK]
771"\u025D" => "e"
772
773# ɞ [LATIN SMALL LETTER CLOSED REVERSED OPEN E]
774"\u025E" => "e"
775
776# ʚ [LATIN SMALL LETTER CLOSED OPEN E]
777"\u029A" => "e"
778
779# ᎈ [LATIN SMALL LETTER TURNED OPEN E]
780"\u1D08" => "e"
781
782# ᶒ [LATIN SMALL LETTER E WITH RETROFLEX HOOK]
783"\u1D92" => "e"
784
785# ᶓ [LATIN SMALL LETTER OPEN E WITH RETROFLEX HOOK]
786"\u1D93" => "e"
787
788# ᶔ [LATIN SMALL LETTER REVERSED OPEN E WITH RETROFLEX HOOK]
789"\u1D94" => "e"
790
791# ᾕ [LATIN SMALL LETTER E WITH MACRON AND GRAVE]
792"\u1E15" => "e"
793
794# ᾗ [LATIN SMALL LETTER E WITH MACRON AND ACUTE]
795"\u1E17" => "e"
796
797# ᾙ [LATIN SMALL LETTER E WITH CIRCUMFLEX BELOW]
798"\u1E19" => "e"
799
800# ᾛ [LATIN SMALL LETTER E WITH TILDE BELOW]
801"\u1E1B" => "e"
802
803# ឝ [LATIN SMALL LETTER E WITH CEDILLA AND BREVE]
804"\u1E1D" => "e"
805
806# ẹ [LATIN SMALL LETTER E WITH DOT BELOW]
807"\u1EB9" => "e"
808
809# ẻ [LATIN SMALL LETTER E WITH HOOK ABOVE]
810"\u1EBB" => "e"
811
812# ẜ [LATIN SMALL LETTER E WITH TILDE]
813"\u1EBD" => "e"
814
815# ế [LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE]
816"\u1EBF" => "e"
817
818# ề [LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE]
819"\u1EC1" => "e"
820
821# ể [LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE]
822"\u1EC3" => "e"
823
824# ễ
825 [LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE]
826"\u1EC5" => "e"
827
828# ệ [LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW]
829"\u1EC7" => "e"
830
831# ₑ [LATIN SUBSCRIPT SMALL LETTER E]
832"\u2091" => "e"
833
834# ⓔ [CIRCLED LATIN SMALL LETTER E]
835"\u24D4" => "e"
836
837# ⱞ [LATIN SMALL LETTER E WITH NOTCH]
838"\u2C78" => "e"
839
840# 
841 [FULLWIDTH LATIN SMALL LETTER E]
842"\uFF45" => "e"
843
844# ⒠ [PARENTHESIZED LATIN SMALL LETTER E]
845"\u24A0" => "(e)"
846
847# Ƒ [LATIN CAPITAL LETTER F WITH HOOK]
848"\u0191" => "F"
849
850# ᾞ [LATIN CAPITAL LETTER F WITH DOT ABOVE]
851"\u1E1E" => "F"
852
853# Ⓕ [CIRCLED LATIN CAPITAL LETTER F]
854"\u24BB" => "F"
855
856# ꜰ [LATIN LETTER SMALL CAPITAL F]
857"\uA730" => "F"
858
859# Ꝼ [LATIN CAPITAL LETTER INSULAR F]
860"\uA77B" => "F"
861
862# ꟻ [LATIN EPIGRAPHIC LETTER REVERSED F]
863"\uA7FB" => "F"
864
865#  [FULLWIDTH LATIN CAPITAL LETTER F]
866"\uFF26" => "F"
867
868# ƒ [LATIN SMALL LETTER F WITH HOOK]
869"\u0192" => "f"
870
871# áµ® [LATIN SMALL LETTER F WITH MIDDLE TILDE]
872"\u1D6E" => "f"
873
874# ᶂ [LATIN SMALL LETTER F WITH PALATAL HOOK]
875"\u1D82" => "f"
876
877# ᾟ [LATIN SMALL LETTER F WITH DOT ABOVE]
878"\u1E1F" => "f"
879
880# ẛ [LATIN SMALL LETTER LONG S WITH DOT ABOVE]
881"\u1E9B" => "f"
882
883# ⓕ [CIRCLED LATIN SMALL LETTER F]
884"\u24D5" => "f"
885
886# Ꝍ [LATIN SMALL LETTER INSULAR F]
887"\uA77C" => "f"
888
889#  [FULLWIDTH LATIN SMALL LETTER F]
890"\uFF46" => "f"
891
892# ⒡ [PARENTHESIZED LATIN SMALL LETTER F]
893"\u24A1" => "(f)"
894
895# ff [LATIN SMALL LIGATURE FF]
896"\uFB00" => "ff"
897
898# ffi [LATIN SMALL LIGATURE FFI]
899"\uFB03" => "ffi"
900
901# ffl [LATIN SMALL LIGATURE FFL]
902"\uFB04" => "ffl"
903
904# fi [LATIN SMALL LIGATURE FI]
905"\uFB01" => "fi"
906
907# fl [LATIN SMALL LIGATURE FL]
908"\uFB02" => "fl"
909
910# Ĝ [LATIN CAPITAL LETTER G WITH CIRCUMFLEX]
911"\u011C" => "G"
912
913# Ğ [LATIN CAPITAL LETTER G WITH BREVE]
914"\u011E" => "G"
915
916# Ä  [LATIN CAPITAL LETTER G WITH DOT ABOVE]
917"\u0120" => "G"
918
919# Ģ [LATIN CAPITAL LETTER G WITH CEDILLA]
920"\u0122" => "G"
921
922# Ɠ [LATIN CAPITAL LETTER G WITH HOOK]
923"\u0193" => "G"
924
925# ǀ [LATIN CAPITAL LETTER G WITH STROKE]
926"\u01E4" => "G"
927
928# ǥ [LATIN SMALL LETTER G WITH STROKE]
929"\u01E5" => "G"
930
931# ÇŠ [LATIN CAPITAL LETTER G WITH CARON]
932"\u01E6" => "G"
933
934# ǧ [LATIN SMALL LETTER G WITH CARON]
935"\u01E7" => "G"
936
937# ÇŽ [LATIN CAPITAL LETTER G WITH ACUTE]
938"\u01F4" => "G"
939
940# ɢ [LATIN LETTER SMALL CAPITAL G]
941"\u0262" => "G"
942
943# ʛ [LATIN LETTER SMALL CAPITAL G WITH HOOK]
944"\u029B" => "G"
945
946# áž  [LATIN CAPITAL LETTER G WITH MACRON]
947"\u1E20" => "G"
948
949# ⒌ [CIRCLED LATIN CAPITAL LETTER G]
950"\u24BC" => "G"
951
952# Ꝝ [LATIN CAPITAL LETTER INSULAR G]
953"\uA77D" => "G"
954
955# ꝟ [LATIN CAPITAL LETTER TURNED INSULAR G]
956"\uA77E" => "G"
957
958#  [FULLWIDTH LATIN CAPITAL LETTER G]
959"\uFF27" => "G"
960
961# ĝ [LATIN SMALL LETTER G WITH CIRCUMFLEX]
962"\u011D" => "g"
963
964# ğ [LATIN SMALL LETTER G WITH BREVE]
965"\u011F" => "g"
966
967# Ä¡ [LATIN SMALL LETTER G WITH DOT ABOVE]
968"\u0121" => "g"
969
970# ģ [LATIN SMALL LETTER G WITH CEDILLA]
971"\u0123" => "g"
972
973# ǵ [LATIN SMALL LETTER G WITH ACUTE]
974"\u01F5" => "g"
975
976# É  [LATIN SMALL LETTER G WITH HOOK]
977"\u0260" => "g"
978
979# É¡ [LATIN SMALL LETTER SCRIPT G]
980"\u0261" => "g"
981
982# áµ· [LATIN SMALL LETTER TURNED G]
983"\u1D77" => "g"
984
985# áµ¹ [LATIN SMALL LETTER INSULAR G]
986"\u1D79" => "g"
987
988# ᶃ [LATIN SMALL LETTER G WITH PALATAL HOOK]
989"\u1D83" => "g"
990
991# áž¡ [LATIN SMALL LETTER G WITH MACRON]
992"\u1E21" => "g"
993
994# ⓖ [CIRCLED LATIN SMALL LETTER G]
995"\u24D6" => "g"
996
997# ꝿ [LATIN SMALL LETTER TURNED INSULAR G]
998"\uA77F" => "g"
999
1000#  [FULLWIDTH LATIN SMALL LETTER G]
1001"\uFF47" => "g"
1002
1003# ⒢ [PARENTHESIZED LATIN SMALL LETTER G]
1004"\u24A2" => "(g)"
1005
1006# Ā [LATIN CAPITAL LETTER H WITH CIRCUMFLEX]
1007"\u0124" => "H"
1008
1009# ÄŠ [LATIN CAPITAL LETTER H WITH STROKE]
1010"\u0126" => "H"
1011
1012# Ȟ [LATIN CAPITAL LETTER H WITH CARON]
1013"\u021E" => "H"
1014
1015# ʜ [LATIN LETTER SMALL CAPITAL H]
1016"\u029C" => "H"
1017
1018# អ [LATIN CAPITAL LETTER H WITH DOT ABOVE]
1019"\u1E22" => "H"
1020
1021# ក [LATIN CAPITAL LETTER H WITH DOT BELOW]
1022"\u1E24" => "H"
1023
1024# ដ [LATIN CAPITAL LETTER H WITH DIAERESIS]
1025"\u1E26" => "H"
1026
1027# ážš [LATIN CAPITAL LETTER H WITH CEDILLA]
1028"\u1E28" => "H"
1029
1030# ឪ [LATIN CAPITAL LETTER H WITH BREVE BELOW]
1031"\u1E2A" => "H"
1032
1033# ⒜ [CIRCLED LATIN CAPITAL LETTER H]
1034"\u24BD" => "H"
1035
1036# Ⱨ [LATIN CAPITAL LETTER H WITH DESCENDER]
1037"\u2C67" => "H"
1038
1039# â±µ [LATIN CAPITAL LETTER HALF H]
1040"\u2C75" => "H"
1041
1042#  [FULLWIDTH LATIN CAPITAL LETTER H]
1043"\uFF28" => "H"
1044
1045# ĥ [LATIN SMALL LETTER H WITH CIRCUMFLEX]
1046"\u0125" => "h"
1047
1048# ħ [LATIN SMALL LETTER H WITH STROKE]
1049"\u0127" => "h"
1050
1051# ȟ [LATIN SMALL LETTER H WITH CARON]
1052"\u021F" => "h"
1053
1054# ɥ [LATIN SMALL LETTER TURNED H]
1055"\u0265" => "h"
1056
1057# ÉŠ [LATIN SMALL LETTER H WITH HOOK]
1058"\u0266" => "h"
1059
1060# Ê® [LATIN SMALL LETTER TURNED H WITH FISHHOOK]
1061"\u02AE" => "h"
1062
1063# ʯ [LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL]
1064"\u02AF" => "h"
1065
1066# ឣ [LATIN SMALL LETTER H WITH DOT ABOVE]
1067"\u1E23" => "h"
1068
1069# ឥ [LATIN SMALL LETTER H WITH DOT BELOW]
1070"\u1E25" => "h"
1071
1072# ឧ [LATIN SMALL LETTER H WITH DIAERESIS]
1073"\u1E27" => "h"
1074
1075# áž© [LATIN SMALL LETTER H WITH CEDILLA]
1076"\u1E29" => "h"
1077
1078# áž« [LATIN SMALL LETTER H WITH BREVE BELOW]
1079"\u1E2B" => "h"
1080
1081# ẖ [LATIN SMALL LETTER H WITH LINE BELOW]
1082"\u1E96" => "h"
1083
1084# ⓗ [CIRCLED LATIN SMALL LETTER H]
1085"\u24D7" => "h"
1086
1087# ⱚ [LATIN SMALL LETTER H WITH DESCENDER]
1088"\u2C68" => "h"
1089
1090# ⱶ [LATIN SMALL LETTER HALF H]
1091"\u2C76" => "h"
1092
1093#  [FULLWIDTH LATIN SMALL LETTER H]
1094"\uFF48" => "h"
1095
1096# Ƕ http://en.wikipedia.org/wiki/Hwair [LATIN CAPITAL LETTER HWAIR]
1097"\u01F6" => "HV"
1098
1099# ⒣ [PARENTHESIZED LATIN SMALL LETTER H]
1100"\u24A3" => "(h)"
1101
1102# ƕ [LATIN SMALL LETTER HV]
1103"\u0195" => "hv"
1104
1105# Ì [LATIN CAPITAL LETTER I WITH GRAVE]
1106"\u00CC" => "I"
1107
1108# Í [LATIN CAPITAL LETTER I WITH ACUTE]
1109"\u00CD" => "I"
1110
1111# Î [LATIN CAPITAL LETTER I WITH CIRCUMFLEX]
1112"\u00CE" => "I"
1113
1114# Ï [LATIN CAPITAL LETTER I WITH DIAERESIS]
1115"\u00CF" => "I"
1116
1117# Äš [LATIN CAPITAL LETTER I WITH TILDE]
1118"\u0128" => "I"
1119
1120# Ī [LATIN CAPITAL LETTER I WITH MACRON]
1121"\u012A" => "I"
1122
1123# Ĭ [LATIN CAPITAL LETTER I WITH BREVE]
1124"\u012C" => "I"
1125
1126# Ä® [LATIN CAPITAL LETTER I WITH OGONEK]
1127"\u012E" => "I"
1128
1129# Ä° [LATIN CAPITAL LETTER I WITH DOT ABOVE]
1130"\u0130" => "I"
1131
1132# Ɩ [LATIN CAPITAL LETTER IOTA]
1133"\u0196" => "I"
1134
1135# Ɨ [LATIN CAPITAL LETTER I WITH STROKE]
1136"\u0197" => "I"
1137
1138# Ǐ [LATIN CAPITAL LETTER I WITH CARON]
1139"\u01CF" => "I"
1140
1141# Ȉ [LATIN CAPITAL LETTER I WITH DOUBLE GRAVE]
1142"\u0208" => "I"
1143
1144# Ȋ [LATIN CAPITAL LETTER I WITH INVERTED BREVE]
1145"\u020A" => "I"
1146
1147# ɪ [LATIN LETTER SMALL CAPITAL I]
1148"\u026A" => "I"
1149
1150# áµ» [LATIN SMALL CAPITAL LETTER I WITH STROKE]
1151"\u1D7B" => "I"
1152
1153# ឬ [LATIN CAPITAL LETTER I WITH TILDE BELOW]
1154"\u1E2C" => "I"
1155
1156# áž® [LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE]
1157"\u1E2E" => "I"
1158
1159# Ỉ [LATIN CAPITAL LETTER I WITH HOOK ABOVE]
1160"\u1EC8" => "I"
1161
1162# Ị [LATIN CAPITAL LETTER I WITH DOT BELOW]
1163"\u1ECA" => "I"
1164
1165# â’Ÿ [CIRCLED LATIN CAPITAL LETTER I]
1166"\u24BE" => "I"
1167
1168# ꟟ [LATIN EPIGRAPHIC LETTER I LONGA]
1169"\uA7FE" => "I"
1170
1171#  [FULLWIDTH LATIN CAPITAL LETTER I]
1172"\uFF29" => "I"
1173
1174# ì [LATIN SMALL LETTER I WITH GRAVE]
1175"\u00EC" => "i"
1176
1177# í [LATIN SMALL LETTER I WITH ACUTE]
1178"\u00ED" => "i"
1179
1180# î [LATIN SMALL LETTER I WITH CIRCUMFLEX]
1181"\u00EE" => "i"
1182
1183# ï [LATIN SMALL LETTER I WITH DIAERESIS]
1184"\u00EF" => "i"
1185
1186# Ä© [LATIN SMALL LETTER I WITH TILDE]
1187"\u0129" => "i"
1188
1189# Ä« [LATIN SMALL LETTER I WITH MACRON]
1190"\u012B" => "i"
1191
1192# Ä­ [LATIN SMALL LETTER I WITH BREVE]
1193"\u012D" => "i"
1194
1195# į [LATIN SMALL LETTER I WITH OGONEK]
1196"\u012F" => "i"
1197
1198# ı [LATIN SMALL LETTER DOTLESS I]
1199"\u0131" => "i"
1200
1201# ǐ [LATIN SMALL LETTER I WITH CARON]
1202"\u01D0" => "i"
1203
1204# ȉ [LATIN SMALL LETTER I WITH DOUBLE GRAVE]
1205"\u0209" => "i"
1206
1207# ȋ [LATIN SMALL LETTER I WITH INVERTED BREVE]
1208"\u020B" => "i"
1209
1210# Éš [LATIN SMALL LETTER I WITH STROKE]
1211"\u0268" => "i"
1212
1213# ᮉ [LATIN SMALL LETTER TURNED I]
1214"\u1D09" => "i"
1215
1216# áµ¢ [LATIN SUBSCRIPT SMALL LETTER I]
1217"\u1D62" => "i"
1218
1219# ᵌ [LATIN SMALL LETTER IOTA WITH STROKE]
1220"\u1D7C" => "i"
1221
1222# ᶖ [LATIN SMALL LETTER I WITH RETROFLEX HOOK]
1223"\u1D96" => "i"
1224
1225# áž­ [LATIN SMALL LETTER I WITH TILDE BELOW]
1226"\u1E2D" => "i"
1227
1228# ឯ [LATIN SMALL LETTER I WITH DIAERESIS AND ACUTE]
1229"\u1E2F" => "i"
1230
1231# ỉ [LATIN SMALL LETTER I WITH HOOK ABOVE]
1232"\u1EC9" => "i"
1233
1234# ị [LATIN SMALL LETTER I WITH DOT BELOW]
1235"\u1ECB" => "i"
1236
1237# ⁱ [SUPERSCRIPT LATIN SMALL LETTER I]
1238"\u2071" => "i"
1239
1240# ⓘ [CIRCLED LATIN SMALL LETTER I]
1241"\u24D8" => "i"
1242
1243#  [FULLWIDTH LATIN SMALL LETTER I]
1244"\uFF49" => "i"
1245
1246# IJ [LATIN CAPITAL LIGATURE IJ]
1247"\u0132" => "IJ"
1248
1249# â’€ [PARENTHESIZED LATIN SMALL LETTER I]
1250"\u24A4" => "(i)"
1251
1252# ij [LATIN SMALL LIGATURE IJ]
1253"\u0133" => "ij"
1254
1255# ÄŽ [LATIN CAPITAL LETTER J WITH CIRCUMFLEX]
1256"\u0134" => "J"
1257
1258# Ɉ [LATIN CAPITAL LETTER J WITH STROKE]
1259"\u0248" => "J"
1260
1261# ᮊ [LATIN LETTER SMALL CAPITAL J]
1262"\u1D0A" => "J"
1263
1264# Ⓙ [CIRCLED LATIN CAPITAL LETTER J]
1265"\u24BF" => "J"
1266
1267#  [FULLWIDTH LATIN CAPITAL LETTER J]
1268"\uFF2A" => "J"
1269
1270# ĵ [LATIN SMALL LETTER J WITH CIRCUMFLEX]
1271"\u0135" => "j"
1272
1273# Ç° [LATIN SMALL LETTER J WITH CARON]
1274"\u01F0" => "j"
1275
1276# È· [LATIN SMALL LETTER DOTLESS J]
1277"\u0237" => "j"
1278
1279# ɉ [LATIN SMALL LETTER J WITH STROKE]
1280"\u0249" => "j"
1281
1282# ɟ [LATIN SMALL LETTER DOTLESS J WITH STROKE]
1283"\u025F" => "j"
1284
1285# ʄ [LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK]
1286"\u0284" => "j"
1287
1288# ʝ [LATIN SMALL LETTER J WITH CROSSED-TAIL]
1289"\u029D" => "j"
1290
1291# ⓙ [CIRCLED LATIN SMALL LETTER J]
1292"\u24D9" => "j"
1293
1294# ⱌ [LATIN SUBSCRIPT SMALL LETTER J]
1295"\u2C7C" => "j"
1296
1297#  [FULLWIDTH LATIN SMALL LETTER J]
1298"\uFF4A" => "j"
1299
1300# ⒥ [PARENTHESIZED LATIN SMALL LETTER J]
1301"\u24A5" => "(j)"
1302
1303# Ķ [LATIN CAPITAL LETTER K WITH CEDILLA]
1304"\u0136" => "K"
1305
1306# Ƙ [LATIN CAPITAL LETTER K WITH HOOK]
1307"\u0198" => "K"
1308
1309# Çš [LATIN CAPITAL LETTER K WITH CARON]
1310"\u01E8" => "K"
1311
1312# ᮋ [LATIN LETTER SMALL CAPITAL K]
1313"\u1D0B" => "K"
1314
1315# áž° [LATIN CAPITAL LETTER K WITH ACUTE]
1316"\u1E30" => "K"
1317
1318# áž² [LATIN CAPITAL LETTER K WITH DOT BELOW]
1319"\u1E32" => "K"
1320
1321# ណ [LATIN CAPITAL LETTER K WITH LINE BELOW]
1322"\u1E34" => "K"
1323
1324# Ⓚ [CIRCLED LATIN CAPITAL LETTER K]
1325"\u24C0" => "K"
1326
1327# Ⱪ [LATIN CAPITAL LETTER K WITH DESCENDER]
1328"\u2C69" => "K"
1329
1330# Ꝁ [LATIN CAPITAL LETTER K WITH STROKE]
1331"\uA740" => "K"
1332
1333# Ꝃ [LATIN CAPITAL LETTER K WITH DIAGONAL STROKE]
1334"\uA742" => "K"
1335
1336# Ꝅ [LATIN CAPITAL LETTER K WITH STROKE AND DIAGONAL STROKE]
1337"\uA744" => "K"
1338
1339#  [FULLWIDTH LATIN CAPITAL LETTER K]
1340"\uFF2B" => "K"
1341
1342# Ä· [LATIN SMALL LETTER K WITH CEDILLA]
1343"\u0137" => "k"
1344
1345# ƙ [LATIN SMALL LETTER K WITH HOOK]
1346"\u0199" => "k"
1347
1348# Ç© [LATIN SMALL LETTER K WITH CARON]
1349"\u01E9" => "k"
1350
1351# ʞ [LATIN SMALL LETTER TURNED K]
1352"\u029E" => "k"
1353
1354# ᶄ [LATIN SMALL LETTER K WITH PALATAL HOOK]
1355"\u1D84" => "k"
1356
1357# áž± [LATIN SMALL LETTER K WITH ACUTE]
1358"\u1E31" => "k"
1359
1360# áž³ [LATIN SMALL LETTER K WITH DOT BELOW]
1361"\u1E33" => "k"
1362
1363# ážµ [LATIN SMALL LETTER K WITH LINE BELOW]
1364"\u1E35" => "k"
1365
1366# ⓚ [CIRCLED LATIN SMALL LETTER K]
1367"\u24DA" => "k"
1368
1369# ⱪ [LATIN SMALL LETTER K WITH DESCENDER]
1370"\u2C6A" => "k"
1371
1372# ꝁ [LATIN SMALL LETTER K WITH STROKE]
1373"\uA741" => "k"
1374
1375# ꝃ [LATIN SMALL LETTER K WITH DIAGONAL STROKE]
1376"\uA743" => "k"
1377
1378# ꝅ
1379 [LATIN SMALL LETTER K WITH STROKE AND DIAGONAL STROKE]
1380"\uA745" => "k"
1381
1382#  [FULLWIDTH LATIN SMALL LETTER K]
1383"\uFF4B" => "k"
1384
1385# ⒩ [PARENTHESIZED LATIN SMALL LETTER K]
1386"\u24A6" => "(k)"
1387
1388# Ĺ [LATIN CAPITAL LETTER L WITH ACUTE]
1389"\u0139" => "L"
1390
1391# Ä» [LATIN CAPITAL LETTER L WITH CEDILLA]
1392"\u013B" => "L"
1393
1394# Ĝ [LATIN CAPITAL LETTER L WITH CARON]
1395"\u013D" => "L"
1396
1397# Ä¿ [LATIN CAPITAL LETTER L WITH MIDDLE DOT]
1398"\u013F" => "L"
1399
1400# Ł [LATIN CAPITAL LETTER L WITH STROKE]
1401"\u0141" => "L"
1402
1403# Ȝ [LATIN CAPITAL LETTER L WITH BAR]
1404"\u023D" => "L"
1405
1406# ʟ [LATIN LETTER SMALL CAPITAL L]
1407"\u029F" => "L"
1408
1409# ᮌ [LATIN LETTER SMALL CAPITAL L WITH STROKE]
1410"\u1D0C" => "L"
1411
1412# ា [LATIN CAPITAL LETTER L WITH DOT BELOW]
1413"\u1E36" => "L"
1414
1415# ážž [LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON]
1416"\u1E38" => "L"
1417
1418# ឺ [LATIN CAPITAL LETTER L WITH LINE BELOW]
1419"\u1E3A" => "L"
1420
1421# ឌ [LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW]
1422"\u1E3C" => "L"
1423
1424# Ⓛ [CIRCLED LATIN CAPITAL LETTER L]
1425"\u24C1" => "L"
1426
1427# â±  [LATIN CAPITAL LETTER L WITH DOUBLE BAR]
1428"\u2C60" => "L"
1429
1430# â±¢ [LATIN CAPITAL LETTER L WITH MIDDLE TILDE]
1431"\u2C62" => "L"
1432
1433# Ꝇ [LATIN CAPITAL LETTER BROKEN L]
1434"\uA746" => "L"
1435
1436# Ꝉ [LATIN CAPITAL LETTER L WITH HIGH STROKE]
1437"\uA748" => "L"
1438
1439# Ꞁ [LATIN CAPITAL LETTER TURNED L]
1440"\uA780" => "L"
1441
1442#  [FULLWIDTH LATIN CAPITAL LETTER L]
1443"\uFF2C" => "L"
1444
1445# ĺ [LATIN SMALL LETTER L WITH ACUTE]
1446"\u013A" => "l"
1447
1448# Č [LATIN SMALL LETTER L WITH CEDILLA]
1449"\u013C" => "l"
1450
1451# ÄŸ [LATIN SMALL LETTER L WITH CARON]
1452"\u013E" => "l"
1453
1454# ŀ [LATIN SMALL LETTER L WITH MIDDLE DOT]
1455"\u0140" => "l"
1456
1457# ł [LATIN SMALL LETTER L WITH STROKE]
1458"\u0142" => "l"
1459
1460# ƚ [LATIN SMALL LETTER L WITH BAR]
1461"\u019A" => "l"
1462
1463# ÈŽ [LATIN SMALL LETTER L WITH CURL]
1464"\u0234" => "l"
1465
1466# É« [LATIN SMALL LETTER L WITH MIDDLE TILDE]
1467"\u026B" => "l"
1468
1469# ɬ [LATIN SMALL LETTER L WITH BELT]
1470"\u026C" => "l"
1471
1472# É­ [LATIN SMALL LETTER L WITH RETROFLEX HOOK]
1473"\u026D" => "l"
1474
1475# ᶅ
1476 [LATIN SMALL LETTER L WITH PALATAL HOOK]
1477"\u1D85" => "l"
1478
1479# áž· [LATIN SMALL LETTER L WITH DOT BELOW]
1480"\u1E37" => "l"
1481
1482# áž¹ [LATIN SMALL LETTER L WITH DOT BELOW AND MACRON]
1483"\u1E39" => "l"
1484
1485# áž» [LATIN SMALL LETTER L WITH LINE BELOW]
1486"\u1E3B" => "l"
1487
1488# វ [LATIN SMALL LETTER L WITH CIRCUMFLEX BELOW]
1489"\u1E3D" => "l"
1490
1491# ⓛ [CIRCLED LATIN SMALL LETTER L]
1492"\u24DB" => "l"
1493
1494# ⱡ [LATIN SMALL LETTER L WITH DOUBLE BAR]
1495"\u2C61" => "l"
1496
1497# ꝇ [LATIN SMALL LETTER BROKEN L]
1498"\uA747" => "l"
1499
1500# ꝉ [LATIN SMALL LETTER L WITH HIGH STROKE]
1501"\uA749" => "l"
1502
1503# ꞁ [LATIN SMALL LETTER TURNED L]
1504"\uA781" => "l"
1505
1506#  [FULLWIDTH LATIN SMALL LETTER L]
1507"\uFF4C" => "l"
1508
1509# LJ [LATIN CAPITAL LETTER LJ]
1510"\u01C7" => "LJ"
1511
1512# Ỻ [LATIN CAPITAL LETTER MIDDLE-WELSH LL]
1513"\u1EFA" => "LL"
1514
1515# Lj [LATIN CAPITAL LETTER L WITH SMALL LETTER J]
1516"\u01C8" => "Lj"
1517
1518# ⒧ [PARENTHESIZED LATIN SMALL LETTER L]
1519"\u24A7" => "(l)"
1520
1521# lj [LATIN SMALL LETTER LJ]
1522"\u01C9" => "lj"
1523
1524# á»» [LATIN SMALL LETTER MIDDLE-WELSH LL]
1525"\u1EFB" => "ll"
1526
1527# ʪ [LATIN SMALL LETTER LS DIGRAPH]
1528"\u02AA" => "ls"
1529
1530# Ê« [LATIN SMALL LETTER LZ DIGRAPH]
1531"\u02AB" => "lz"
1532
1533# Ɯ [LATIN CAPITAL LETTER TURNED M]
1534"\u019C" => "M"
1535
1536# ᎍ [LATIN LETTER SMALL CAPITAL M]
1537"\u1D0D" => "M"
1538
1539# ស [LATIN CAPITAL LETTER M WITH ACUTE]
1540"\u1E3E" => "M"
1541
1542# Ṁ [LATIN CAPITAL LETTER M WITH DOT ABOVE]
1543"\u1E40" => "M"
1544
1545# Ṃ [LATIN CAPITAL LETTER M WITH DOT BELOW]
1546"\u1E42" => "M"
1547
1548# Ⓜ [CIRCLED LATIN CAPITAL LETTER M]
1549"\u24C2" => "M"
1550
1551# â±® [LATIN CAPITAL LETTER M WITH HOOK]
1552"\u2C6E" => "M"
1553
1554# Ƛ [LATIN EPIGRAPHIC LETTER INVERTED M]
1555"\uA7FD" => "M"
1556
1557# ꟿ [LATIN EPIGRAPHIC LETTER ARCHAIC M]
1558"\uA7FF" => "M"
1559
1560#  [FULLWIDTH LATIN CAPITAL LETTER M]
1561"\uFF2D" => "M"
1562
1563# ɯ [LATIN SMALL LETTER TURNED M]
1564"\u026F" => "m"
1565
1566# É° [LATIN SMALL LETTER TURNED M WITH LONG LEG]
1567"\u0270" => "m"
1568
1569# ɱ [LATIN SMALL LETTER M WITH HOOK]
1570"\u0271" => "m"
1571
1572# ᵯ [LATIN SMALL LETTER M WITH MIDDLE TILDE]
1573"\u1D6F" => "m"
1574
1575# ᶆ [LATIN SMALL LETTER M WITH PALATAL HOOK]
1576"\u1D86" => "m"
1577
1578# áž¿ [LATIN SMALL LETTER M WITH ACUTE]
1579"\u1E3F" => "m"
1580
1581# ṁ [LATIN SMALL LETTER M WITH DOT ABOVE]
1582"\u1E41" => "m"
1583
1584# ṃ [LATIN SMALL LETTER M WITH DOT BELOW]
1585"\u1E43" => "m"
1586
1587# ⓜ [CIRCLED LATIN SMALL LETTER M]
1588"\u24DC" => "m"
1589
1590#  [FULLWIDTH LATIN SMALL LETTER M]
1591"\uFF4D" => "m"
1592
1593# Ⓓ [PARENTHESIZED LATIN SMALL LETTER M]
1594"\u24A8" => "(m)"
1595
1596# Ñ [LATIN CAPITAL LETTER N WITH TILDE]
1597"\u00D1" => "N"
1598
1599# Ń [LATIN CAPITAL LETTER N WITH ACUTE]
1600"\u0143" => "N"
1601
1602# Ņ
1603 [LATIN CAPITAL LETTER N WITH CEDILLA]
1604"\u0145" => "N"
1605
1606# Ň [LATIN CAPITAL LETTER N WITH CARON]
1607"\u0147" => "N"
1608
1609# Ŋ http://en.wikipedia.org/wiki/Eng_(letter) [LATIN CAPITAL LETTER ENG]
1610"\u014A" => "N"
1611
1612# Ɲ [LATIN CAPITAL LETTER N WITH LEFT HOOK]
1613"\u019D" => "N"
1614
1615# Çž [LATIN CAPITAL LETTER N WITH GRAVE]
1616"\u01F8" => "N"
1617
1618# È  [LATIN CAPITAL LETTER N WITH LONG RIGHT LEG]
1619"\u0220" => "N"
1620
1621# ÉŽ [LATIN LETTER SMALL CAPITAL N]
1622"\u0274" => "N"
1623
1624# ᮎ [LATIN LETTER SMALL CAPITAL REVERSED N]
1625"\u1D0E" => "N"
1626
1627# Ṅ [LATIN CAPITAL LETTER N WITH DOT ABOVE]
1628"\u1E44" => "N"
1629
1630# Ṇ [LATIN CAPITAL LETTER N WITH DOT BELOW]
1631"\u1E46" => "N"
1632
1633# Ṉ [LATIN CAPITAL LETTER N WITH LINE BELOW]
1634"\u1E48" => "N"
1635
1636# Ṋ [LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW]
1637"\u1E4A" => "N"
1638
1639# Ⓝ [CIRCLED LATIN CAPITAL LETTER N]
1640"\u24C3" => "N"
1641
1642#  [FULLWIDTH LATIN CAPITAL LETTER N]
1643"\uFF2E" => "N"
1644
1645# ñ [LATIN SMALL LETTER N WITH TILDE]
1646"\u00F1" => "n"
1647
1648# ń [LATIN SMALL LETTER N WITH ACUTE]
1649"\u0144" => "n"
1650
1651# ņ [LATIN SMALL LETTER N WITH CEDILLA]
1652"\u0146" => "n"
1653
1654# ň [LATIN SMALL LETTER N WITH CARON]
1655"\u0148" => "n"
1656
1657# ʼn [LATIN SMALL LETTER N PRECEDED BY APOSTROPHE]
1658"\u0149" => "n"
1659
1660# ŋ http://en.wikipedia.org/wiki/Eng_(letter) [LATIN SMALL LETTER ENG]
1661"\u014B" => "n"
1662
1663# ƞ [LATIN SMALL LETTER N WITH LONG RIGHT LEG]
1664"\u019E" => "n"
1665
1666# ǹ [LATIN SMALL LETTER N WITH GRAVE]
1667"\u01F9" => "n"
1668
1669# ȵ [LATIN SMALL LETTER N WITH CURL]
1670"\u0235" => "n"
1671
1672# ɲ [LATIN SMALL LETTER N WITH LEFT HOOK]
1673"\u0272" => "n"
1674
1675# ɳ [LATIN SMALL LETTER N WITH RETROFLEX HOOK]
1676"\u0273" => "n"
1677
1678# áµ° [LATIN SMALL LETTER N WITH MIDDLE TILDE]
1679"\u1D70" => "n"
1680
1681# ᶇ [LATIN SMALL LETTER N WITH PALATAL HOOK]
1682"\u1D87" => "n"
1683
1684# ṅ
1685 [LATIN SMALL LETTER N WITH DOT ABOVE]
1686"\u1E45" => "n"
1687
1688# ṇ [LATIN SMALL LETTER N WITH DOT BELOW]
1689"\u1E47" => "n"
1690
1691# ṉ [LATIN SMALL LETTER N WITH LINE BELOW]
1692"\u1E49" => "n"
1693
1694# ṋ [LATIN SMALL LETTER N WITH CIRCUMFLEX BELOW]
1695"\u1E4B" => "n"
1696
1697# ⁿ [SUPERSCRIPT LATIN SMALL LETTER N]
1698"\u207F" => "n"
1699
1700# ⓝ [CIRCLED LATIN SMALL LETTER N]
1701"\u24DD" => "n"
1702
1703#  [FULLWIDTH LATIN SMALL LETTER N]
1704"\uFF4E" => "n"
1705
1706# NJ [LATIN CAPITAL LETTER NJ]
1707"\u01CA" => "NJ"
1708
1709# Nj [LATIN CAPITAL LETTER N WITH SMALL LETTER J]
1710"\u01CB" => "Nj"
1711
1712# ⒩ [PARENTHESIZED LATIN SMALL LETTER N]
1713"\u24A9" => "(n)"
1714
1715# nj [LATIN SMALL LETTER NJ]
1716"\u01CC" => "nj"
1717
1718# Ò [LATIN CAPITAL LETTER O WITH GRAVE]
1719"\u00D2" => "O"
1720
1721# Ó [LATIN CAPITAL LETTER O WITH ACUTE]
1722"\u00D3" => "O"
1723
1724# Ô [LATIN CAPITAL LETTER O WITH CIRCUMFLEX]
1725"\u00D4" => "O"
1726
1727# Õ [LATIN CAPITAL LETTER O WITH TILDE]
1728"\u00D5" => "O"
1729
1730# Ö [LATIN CAPITAL LETTER O WITH DIAERESIS]
1731"\u00D6" => "O"
1732
1733# Ø [LATIN CAPITAL LETTER O WITH STROKE]
1734"\u00D8" => "O"
1735
1736# Ō [LATIN CAPITAL LETTER O WITH MACRON]
1737"\u014C" => "O"
1738
1739# Ŏ [LATIN CAPITAL LETTER O WITH BREVE]
1740"\u014E" => "O"
1741
1742# Ő [LATIN CAPITAL LETTER O WITH DOUBLE ACUTE]
1743"\u0150" => "O"
1744
1745# Ɔ [LATIN CAPITAL LETTER OPEN O]
1746"\u0186" => "O"
1747
1748# Ɵ [LATIN CAPITAL LETTER O WITH MIDDLE TILDE]
1749"\u019F" => "O"
1750
1751# Æ  [LATIN CAPITAL LETTER O WITH HORN]
1752"\u01A0" => "O"
1753
1754# Ǒ [LATIN CAPITAL LETTER O WITH CARON]
1755"\u01D1" => "O"
1756
1757# Ǫ [LATIN CAPITAL LETTER O WITH OGONEK]
1758"\u01EA" => "O"
1759
1760# Ǭ [LATIN CAPITAL LETTER O WITH OGONEK AND MACRON]
1761"\u01EC" => "O"
1762
1763# ÇŸ [LATIN CAPITAL LETTER O WITH STROKE AND ACUTE]
1764"\u01FE" => "O"
1765
1766# Ȍ [LATIN CAPITAL LETTER O WITH DOUBLE GRAVE]
1767"\u020C" => "O"
1768
1769# Ȏ [LATIN CAPITAL LETTER O WITH INVERTED BREVE]
1770"\u020E" => "O"
1771
1772# Ȫ [LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON]
1773"\u022A" => "O"
1774
1775# Ȭ [LATIN CAPITAL LETTER O WITH TILDE AND MACRON]
1776"\u022C" => "O"
1777
1778# È® [LATIN CAPITAL LETTER O WITH DOT ABOVE]
1779"\u022E" => "O"
1780
1781# È° [LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON]
1782"\u0230" => "O"
1783
1784# ᎏ [LATIN LETTER SMALL CAPITAL O]
1785"\u1D0F" => "O"
1786
1787# ᎐ [LATIN LETTER SMALL CAPITAL OPEN O]
1788"\u1D10" => "O"
1789
1790# Ṍ [LATIN CAPITAL LETTER O WITH TILDE AND ACUTE]
1791"\u1E4C" => "O"
1792
1793# Ṏ [LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS]
1794"\u1E4E" => "O"
1795
1796# Ṑ [LATIN CAPITAL LETTER O WITH MACRON AND GRAVE]
1797"\u1E50" => "O"
1798
1799# Ṓ [LATIN CAPITAL LETTER O WITH MACRON AND ACUTE]
1800"\u1E52" => "O"
1801
1802# Ọ [LATIN CAPITAL LETTER O WITH DOT BELOW]
1803"\u1ECC" => "O"
1804
1805# Ỏ [LATIN CAPITAL LETTER O WITH HOOK ABOVE]
1806"\u1ECE" => "O"
1807
1808# Ố [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE]
1809"\u1ED0" => "O"
1810
1811# Ồ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE]
1812"\u1ED2" => "O"
1813
1814# Ổ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE]
1815"\u1ED4" => "O"
1816
1817# Ỗ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE]
1818"\u1ED6" => "O"
1819
1820# Ộ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW]
1821"\u1ED8" => "O"
1822
1823# Ớ [LATIN CAPITAL LETTER O WITH HORN AND ACUTE]
1824"\u1EDA" => "O"
1825
1826# Ờ [LATIN CAPITAL LETTER O WITH HORN AND GRAVE]
1827"\u1EDC" => "O"
1828
1829# Ở [LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE]
1830"\u1EDE" => "O"
1831
1832# á»  [LATIN CAPITAL LETTER O WITH HORN AND TILDE]
1833"\u1EE0" => "O"
1834
1835# Ợ [LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW]
1836"\u1EE2" => "O"
1837
1838# Ⓞ [CIRCLED LATIN CAPITAL LETTER O]
1839"\u24C4" => "O"
1840
1841# Ꝋ [LATIN CAPITAL LETTER O WITH LONG STROKE OVERLAY]
1842"\uA74A" => "O"
1843
1844# Ꝍ [LATIN CAPITAL LETTER O WITH LOOP]
1845"\uA74C" => "O"
1846
1847#  [FULLWIDTH LATIN CAPITAL LETTER O]
1848"\uFF2F" => "O"
1849
1850# ò [LATIN SMALL LETTER O WITH GRAVE]
1851"\u00F2" => "o"
1852
1853# ó [LATIN SMALL LETTER O WITH ACUTE]
1854"\u00F3" => "o"
1855
1856# ÃŽ [LATIN SMALL LETTER O WITH CIRCUMFLEX]
1857"\u00F4" => "o"
1858
1859# õ [LATIN SMALL LETTER O WITH TILDE]
1860"\u00F5" => "o"
1861
1862# ö [LATIN SMALL LETTER O WITH DIAERESIS]
1863"\u00F6" => "o"
1864
1865# Þ [LATIN SMALL LETTER O WITH STROKE]
1866"\u00F8" => "o"
1867
1868# ō [LATIN SMALL LETTER O WITH MACRON]
1869"\u014D" => "o"
1870
1871# ŏ [LATIN SMALL LETTER O WITH BREVE]
1872"\u014F" => "o"
1873
1874# ő [LATIN SMALL LETTER O WITH DOUBLE ACUTE]
1875"\u0151" => "o"
1876
1877# Æ¡ [LATIN SMALL LETTER O WITH HORN]
1878"\u01A1" => "o"
1879
1880# ǒ [LATIN SMALL LETTER O WITH CARON]
1881"\u01D2" => "o"
1882
1883# Ç« [LATIN SMALL LETTER O WITH OGONEK]
1884"\u01EB" => "o"
1885
1886# Ç­ [LATIN SMALL LETTER O WITH OGONEK AND MACRON]
1887"\u01ED" => "o"
1888
1889# Ç¿ [LATIN SMALL LETTER O WITH STROKE AND ACUTE]
1890"\u01FF" => "o"
1891
1892# ȍ [LATIN SMALL LETTER O WITH DOUBLE GRAVE]
1893"\u020D" => "o"
1894
1895# ȏ [LATIN SMALL LETTER O WITH INVERTED BREVE]
1896"\u020F" => "o"
1897
1898# È« [LATIN SMALL LETTER O WITH DIAERESIS AND MACRON]
1899"\u022B" => "o"
1900
1901# È­ [LATIN SMALL LETTER O WITH TILDE AND MACRON]
1902"\u022D" => "o"
1903
1904# ȯ [LATIN SMALL LETTER O WITH DOT ABOVE]
1905"\u022F" => "o"
1906
1907# ȱ [LATIN SMALL LETTER O WITH DOT ABOVE AND MACRON]
1908"\u0231" => "o"
1909
1910# ɔ [LATIN SMALL LETTER OPEN O]
1911"\u0254" => "o"
1912
1913# ɵ [LATIN SMALL LETTER BARRED O]
1914"\u0275" => "o"
1915
1916# ᮖ [LATIN SMALL LETTER TOP HALF O]
1917"\u1D16" => "o"
1918
1919# ᮗ [LATIN SMALL LETTER BOTTOM HALF O]
1920"\u1D17" => "o"
1921
1922# ᶗ [LATIN SMALL LETTER OPEN O WITH RETROFLEX HOOK]
1923"\u1D97" => "o"
1924
1925# ṍ [LATIN SMALL LETTER O WITH TILDE AND ACUTE]
1926"\u1E4D" => "o"
1927
1928# ṏ [LATIN SMALL LETTER O WITH TILDE AND DIAERESIS]
1929"\u1E4F" => "o"
1930
1931# ṑ [LATIN SMALL LETTER O WITH MACRON AND GRAVE]
1932"\u1E51" => "o"
1933
1934# ṓ [LATIN SMALL LETTER O WITH MACRON AND ACUTE]
1935"\u1E53" => "o"
1936
1937# ọ [LATIN SMALL LETTER O WITH DOT BELOW]
1938"\u1ECD" => "o"
1939
1940# ỏ [LATIN SMALL LETTER O WITH HOOK ABOVE]
1941"\u1ECF" => "o"
1942
1943# ố [LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE]
1944"\u1ED1" => "o"
1945
1946# ồ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE]
1947"\u1ED3" => "o"
1948
1949# ổ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE]
1950"\u1ED5" => "o"
1951
1952# ỗ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE]
1953"\u1ED7" => "o"
1954
1955# ộ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW]
1956"\u1ED9" => "o"
1957
1958# ớ [LATIN SMALL LETTER O WITH HORN AND ACUTE]
1959"\u1EDB" => "o"
1960
1961# ờ [LATIN SMALL LETTER O WITH HORN AND GRAVE]
1962"\u1EDD" => "o"
1963
1964# ở [LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE]
1965"\u1EDF" => "o"
1966
1967# ỡ [LATIN SMALL LETTER O WITH HORN AND TILDE]
1968"\u1EE1" => "o"
1969
1970# ợ [LATIN SMALL LETTER O WITH HORN AND DOT BELOW]
1971"\u1EE3" => "o"
1972
1973# ₒ [LATIN SUBSCRIPT SMALL LETTER O]
1974"\u2092" => "o"
1975
1976# ⓞ [CIRCLED LATIN SMALL LETTER O]
1977"\u24DE" => "o"
1978
1979# ⱺ [LATIN SMALL LETTER O WITH LOW RING INSIDE]
1980"\u2C7A" => "o"
1981
1982# ꝋ [LATIN SMALL LETTER O WITH LONG STROKE OVERLAY]
1983"\uA74B" => "o"
1984
1985# ꝍ [LATIN SMALL LETTER O WITH LOOP]
1986"\uA74D" => "o"
1987
1988#  [FULLWIDTH LATIN SMALL LETTER O]
1989"\uFF4F" => "o"
1990
1991# Π[LATIN CAPITAL LIGATURE OE]
1992"\u0152" => "OE"
1993
1994# ɶ [LATIN LETTER SMALL CAPITAL OE]
1995"\u0276" => "OE"
1996
1997# Ꝏ [LATIN CAPITAL LETTER OO]
1998"\uA74E" => "OO"
1999
2000# Ȣ http://en.wikipedia.org/wiki/OU [LATIN CAPITAL LETTER OU]
2001"\u0222" => "OU"
2002
2003# ᮕ [LATIN LETTER SMALL CAPITAL OU]
2004"\u1D15" => "OU"
2005
2006# ⒪ [PARENTHESIZED LATIN SMALL LETTER O]
2007"\u24AA" => "(o)"
2008
2009# œ [LATIN SMALL LIGATURE OE]
2010"\u0153" => "oe"
2011
2012# ᮔ [LATIN SMALL LETTER TURNED OE]
2013"\u1D14" => "oe"
2014
2015# ꝏ [LATIN SMALL LETTER OO]
2016"\uA74F" => "oo"
2017
2018# ȣ http://en.wikipedia.org/wiki/OU [LATIN SMALL LETTER OU]
2019"\u0223" => "ou"
2020
2021# ƀ [LATIN CAPITAL LETTER P WITH HOOK]
2022"\u01A4" => "P"
2023
2024# ᎘ [LATIN LETTER SMALL CAPITAL P]
2025"\u1D18" => "P"
2026
2027# Ṕ [LATIN CAPITAL LETTER P WITH ACUTE]
2028"\u1E54" => "P"
2029
2030# Ṗ [LATIN CAPITAL LETTER P WITH DOT ABOVE]
2031"\u1E56" => "P"
2032
2033# Ⓟ
2034 [CIRCLED LATIN CAPITAL LETTER P]
2035"\u24C5" => "P"
2036
2037# â±£ [LATIN CAPITAL LETTER P WITH STROKE]
2038"\u2C63" => "P"
2039
2040# Ꝑ [LATIN CAPITAL LETTER P WITH STROKE THROUGH DESCENDER]
2041"\uA750" => "P"
2042
2043# Ꝓ [LATIN CAPITAL LETTER P WITH FLOURISH]
2044"\uA752" => "P"
2045
2046# Ꝕ [LATIN CAPITAL LETTER P WITH SQUIRREL TAIL]
2047"\uA754" => "P"
2048
2049#  [FULLWIDTH LATIN CAPITAL LETTER P]
2050"\uFF30" => "P"
2051
2052# ƥ [LATIN SMALL LETTER P WITH HOOK]
2053"\u01A5" => "p"
2054
2055# áµ± [LATIN SMALL LETTER P WITH MIDDLE TILDE]
2056"\u1D71" => "p"
2057
2058# ᵜ [LATIN SMALL LETTER P WITH STROKE]
2059"\u1D7D" => "p"
2060
2061# ᶈ [LATIN SMALL LETTER P WITH PALATAL HOOK]
2062"\u1D88" => "p"
2063
2064# ṕ [LATIN SMALL LETTER P WITH ACUTE]
2065"\u1E55" => "p"
2066
2067# ṗ [LATIN SMALL LETTER P WITH DOT ABOVE]
2068"\u1E57" => "p"
2069
2070# ⓟ [CIRCLED LATIN SMALL LETTER P]
2071"\u24DF" => "p"
2072
2073# ꝑ [LATIN SMALL LETTER P WITH STROKE THROUGH DESCENDER]
2074"\uA751" => "p"
2075
2076# ꝓ [LATIN SMALL LETTER P WITH FLOURISH]
2077"\uA753" => "p"
2078
2079# ꝕ [LATIN SMALL LETTER P WITH SQUIRREL TAIL]
2080"\uA755" => "p"
2081
2082# Ꟍ [LATIN EPIGRAPHIC LETTER REVERSED P]
2083"\uA7FC" => "p"
2084
2085#  [FULLWIDTH LATIN SMALL LETTER P]
2086"\uFF50" => "p"
2087
2088# ⒫ [PARENTHESIZED LATIN SMALL LETTER P]
2089"\u24AB" => "(p)"
2090
2091# Ɋ [LATIN CAPITAL LETTER SMALL Q WITH HOOK TAIL]
2092"\u024A" => "Q"
2093
2094# Ⓠ [CIRCLED LATIN CAPITAL LETTER Q]
2095"\u24C6" => "Q"
2096
2097# Ꝗ [LATIN CAPITAL LETTER Q WITH STROKE THROUGH DESCENDER]
2098"\uA756" => "Q"
2099
2100# Ꝙ [LATIN CAPITAL LETTER Q WITH DIAGONAL STROKE]
2101"\uA758" => "Q"
2102
2103#  [FULLWIDTH LATIN CAPITAL LETTER Q]
2104"\uFF31" => "Q"
2105
2106# Äž http://en.wikipedia.org/wiki/Kra_(letter) [LATIN SMALL LETTER KRA]
2107"\u0138" => "q"
2108
2109# ɋ [LATIN SMALL LETTER Q WITH HOOK TAIL]
2110"\u024B" => "q"
2111
2112# Ê  [LATIN SMALL LETTER Q WITH HOOK]
2113"\u02A0" => "q"
2114
2115# ⓠ [CIRCLED LATIN SMALL LETTER Q]
2116"\u24E0" => "q"
2117
2118# ꝗ [LATIN SMALL LETTER Q WITH STROKE THROUGH DESCENDER]
2119"\uA757" => "q"
2120
2121# ꝙ [LATIN SMALL LETTER Q WITH DIAGONAL STROKE]
2122"\uA759" => "q"
2123
2124#  [FULLWIDTH LATIN SMALL LETTER Q]
2125"\uFF51" => "q"
2126
2127# ⒬ [PARENTHESIZED LATIN SMALL LETTER Q]
2128"\u24AC" => "(q)"
2129
2130# ȹ [LATIN SMALL LETTER QP DIGRAPH]
2131"\u0239" => "qp"
2132
2133# Ŕ [LATIN CAPITAL LETTER R WITH ACUTE]
2134"\u0154" => "R"
2135
2136# Ŗ [LATIN CAPITAL LETTER R WITH CEDILLA]
2137"\u0156" => "R"
2138
2139# Ř [LATIN CAPITAL LETTER R WITH CARON]
2140"\u0158" => "R"
2141
2142# Ȓ [LATIN CAPITAL LETTER R WITH DOUBLE GRAVE]
2143"\u0210" => "R"
2144
2145# Ȓ [LATIN CAPITAL LETTER R WITH INVERTED BREVE]
2146"\u0212" => "R"
2147
2148# Ɍ [LATIN CAPITAL LETTER R WITH STROKE]
2149"\u024C" => "R"
2150
2151# ʀ [LATIN LETTER SMALL CAPITAL R]
2152"\u0280" => "R"
2153
2154# ʁ [LATIN LETTER SMALL CAPITAL INVERTED R]
2155"\u0281" => "R"
2156
2157# ᮙ [LATIN LETTER SMALL CAPITAL REVERSED R]
2158"\u1D19" => "R"
2159
2160# ᮚ [LATIN LETTER SMALL CAPITAL TURNED R]
2161"\u1D1A" => "R"
2162
2163# Ṙ [LATIN CAPITAL LETTER R WITH DOT ABOVE]
2164"\u1E58" => "R"
2165
2166# Ṛ [LATIN CAPITAL LETTER R WITH DOT BELOW]
2167"\u1E5A" => "R"
2168
2169# Ṝ [LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON]
2170"\u1E5C" => "R"
2171
2172# Ṟ [LATIN CAPITAL LETTER R WITH LINE BELOW]
2173"\u1E5E" => "R"
2174
2175# Ⓡ [CIRCLED LATIN CAPITAL LETTER R]
2176"\u24C7" => "R"
2177
2178# â±€ [LATIN CAPITAL LETTER R WITH TAIL]
2179"\u2C64" => "R"
2180
2181# Ꝛ [LATIN CAPITAL LETTER R ROTUNDA]
2182"\uA75A" => "R"
2183
2184# Ꞃ [LATIN CAPITAL LETTER INSULAR R]
2185"\uA782" => "R"
2186
2187#  [FULLWIDTH LATIN CAPITAL LETTER R]
2188"\uFF32" => "R"
2189
2190# ŕ [LATIN SMALL LETTER R WITH ACUTE]
2191"\u0155" => "r"
2192
2193# ŗ [LATIN SMALL LETTER R WITH CEDILLA]
2194"\u0157" => "r"
2195
2196# ř [LATIN SMALL LETTER R WITH CARON]
2197"\u0159" => "r"
2198
2199# ȑ [LATIN SMALL LETTER R WITH DOUBLE GRAVE]
2200"\u0211" => "r"
2201
2202# ȓ [LATIN SMALL LETTER R WITH INVERTED BREVE]
2203"\u0213" => "r"
2204
2205# ɍ [LATIN SMALL LETTER R WITH STROKE]
2206"\u024D" => "r"
2207
2208# Ɍ [LATIN SMALL LETTER R WITH LONG LEG]
2209"\u027C" => "r"
2210
2211# ɜ [LATIN SMALL LETTER R WITH TAIL]
2212"\u027D" => "r"
2213
2214# ÉŸ [LATIN SMALL LETTER R WITH FISHHOOK]
2215"\u027E" => "r"
2216
2217# É¿ [LATIN SMALL LETTER REVERSED R WITH FISHHOOK]
2218"\u027F" => "r"
2219
2220# áµ£ [LATIN SUBSCRIPT SMALL LETTER R]
2221"\u1D63" => "r"
2222
2223# áµ² [LATIN SMALL LETTER R WITH MIDDLE TILDE]
2224"\u1D72" => "r"
2225
2226# áµ³ [LATIN SMALL LETTER R WITH FISHHOOK AND MIDDLE TILDE]
2227"\u1D73" => "r"
2228
2229# ᶉ [LATIN SMALL LETTER R WITH PALATAL HOOK]
2230"\u1D89" => "r"
2231
2232# ṙ [LATIN SMALL LETTER R WITH DOT ABOVE]
2233"\u1E59" => "r"
2234
2235# ṛ [LATIN SMALL LETTER R WITH DOT BELOW]
2236"\u1E5B" => "r"
2237
2238# ṝ [LATIN SMALL LETTER R WITH DOT BELOW AND MACRON]
2239"\u1E5D" => "r"
2240
2241# ṟ [LATIN SMALL LETTER R WITH LINE BELOW]
2242"\u1E5F" => "r"
2243
2244# ⓡ [CIRCLED LATIN SMALL LETTER R]
2245"\u24E1" => "r"
2246
2247# ꝛ [LATIN SMALL LETTER R ROTUNDA]
2248"\uA75B" => "r"
2249
2250# ꞃ [LATIN SMALL LETTER INSULAR R]
2251"\uA783" => "r"
2252
2253#  [FULLWIDTH LATIN SMALL LETTER R]
2254"\uFF52" => "r"
2255
2256# ⒭ [PARENTHESIZED LATIN SMALL LETTER R]
2257"\u24AD" => "(r)"
2258
2259# Ś [LATIN CAPITAL LETTER S WITH ACUTE]
2260"\u015A" => "S"
2261
2262# Ŝ [LATIN CAPITAL LETTER S WITH CIRCUMFLEX]
2263"\u015C" => "S"
2264
2265# Ş [LATIN CAPITAL LETTER S WITH CEDILLA]
2266"\u015E" => "S"
2267
2268# Å  [LATIN CAPITAL LETTER S WITH CARON]
2269"\u0160" => "S"
2270
2271# Ș [LATIN CAPITAL LETTER S WITH COMMA BELOW]
2272"\u0218" => "S"
2273
2274# á¹  [LATIN CAPITAL LETTER S WITH DOT ABOVE]
2275"\u1E60" => "S"
2276
2277# á¹¢ [LATIN CAPITAL LETTER S WITH DOT BELOW]
2278"\u1E62" => "S"
2279
2280# á¹€ [LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE]
2281"\u1E64" => "S"
2282
2283# Ṋ [LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE]
2284"\u1E66" => "S"
2285
2286# Ṛ [LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE]
2287"\u1E68" => "S"
2288
2289# Ⓢ [CIRCLED LATIN CAPITAL LETTER S]
2290"\u24C8" => "S"
2291
2292# ꜱ [LATIN LETTER SMALL CAPITAL S]
2293"\uA731" => "S"
2294
2295# ꞅ
2296 [LATIN SMALL LETTER INSULAR S]
2297"\uA785" => "S"
2298
2299#  [FULLWIDTH LATIN CAPITAL LETTER S]
2300"\uFF33" => "S"
2301
2302# ś [LATIN SMALL LETTER S WITH ACUTE]
2303"\u015B" => "s"
2304
2305# ŝ [LATIN SMALL LETTER S WITH CIRCUMFLEX]
2306"\u015D" => "s"
2307
2308# ş [LATIN SMALL LETTER S WITH CEDILLA]
2309"\u015F" => "s"
2310
2311# Å¡ [LATIN SMALL LETTER S WITH CARON]
2312"\u0161" => "s"
2313
2314# Å¿ http://en.wikipedia.org/wiki/Long_S [LATIN SMALL LETTER LONG S]
2315"\u017F" => "s"
2316
2317# ș [LATIN SMALL LETTER S WITH COMMA BELOW]
2318"\u0219" => "s"
2319
2320# È¿ [LATIN SMALL LETTER S WITH SWASH TAIL]
2321"\u023F" => "s"
2322
2323# ʂ [LATIN SMALL LETTER S WITH HOOK]
2324"\u0282" => "s"
2325
2326# ᵎ [LATIN SMALL LETTER S WITH MIDDLE TILDE]
2327"\u1D74" => "s"
2328
2329# ᶊ [LATIN SMALL LETTER S WITH PALATAL HOOK]
2330"\u1D8A" => "s"
2331
2332# ṡ [LATIN SMALL LETTER S WITH DOT ABOVE]
2333"\u1E61" => "s"
2334
2335# á¹£ [LATIN SMALL LETTER S WITH DOT BELOW]
2336"\u1E63" => "s"
2337
2338# á¹¥ [LATIN SMALL LETTER S WITH ACUTE AND DOT ABOVE]
2339"\u1E65" => "s"
2340
2341# ṧ [LATIN SMALL LETTER S WITH CARON AND DOT ABOVE]
2342"\u1E67" => "s"
2343
2344# ṩ [LATIN SMALL LETTER S WITH DOT BELOW AND DOT ABOVE]
2345"\u1E69" => "s"
2346
2347# ẜ [LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE]
2348"\u1E9C" => "s"
2349
2350# ẝ [LATIN SMALL LETTER LONG S WITH HIGH STROKE]
2351"\u1E9D" => "s"
2352
2353# ⓢ [CIRCLED LATIN SMALL LETTER S]
2354"\u24E2" => "s"
2355
2356# Ꞅ [LATIN CAPITAL LETTER INSULAR S]
2357"\uA784" => "s"
2358
2359#  [FULLWIDTH LATIN SMALL LETTER S]
2360"\uFF53" => "s"
2361
2362# ẞ [LATIN CAPITAL LETTER SHARP S]
2363"\u1E9E" => "SS"
2364
2365# ⒮ [PARENTHESIZED LATIN SMALL LETTER S]
2366"\u24AE" => "(s)"
2367
2368# ß [LATIN SMALL LETTER SHARP S]
2369"\u00DF" => "ss"
2370
2371# st [LATIN SMALL LIGATURE ST]
2372"\uFB06" => "st"
2373
2374# Ţ [LATIN CAPITAL LETTER T WITH CEDILLA]
2375"\u0162" => "T"
2376
2377# ŀ [LATIN CAPITAL LETTER T WITH CARON]
2378"\u0164" => "T"
2379
2380# ÅŠ [LATIN CAPITAL LETTER T WITH STROKE]
2381"\u0166" => "T"
2382
2383# Ƭ [LATIN CAPITAL LETTER T WITH HOOK]
2384"\u01AC" => "T"
2385
2386# Æ® [LATIN CAPITAL LETTER T WITH RETROFLEX HOOK]
2387"\u01AE" => "T"
2388
2389# Ț [LATIN CAPITAL LETTER T WITH COMMA BELOW]
2390"\u021A" => "T"
2391
2392# ÈŸ [LATIN CAPITAL LETTER T WITH DIAGONAL STROKE]
2393"\u023E" => "T"
2394
2395# ᮛ [LATIN LETTER SMALL CAPITAL T]
2396"\u1D1B" => "T"
2397
2398# Ṫ [LATIN CAPITAL LETTER T WITH DOT ABOVE]
2399"\u1E6A" => "T"
2400
2401# Ṭ [LATIN CAPITAL LETTER T WITH DOT BELOW]
2402"\u1E6C" => "T"
2403
2404# á¹® [LATIN CAPITAL LETTER T WITH LINE BELOW]
2405"\u1E6E" => "T"
2406
2407# á¹° [LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW]
2408"\u1E70" => "T"
2409
2410# Ⓣ [CIRCLED LATIN CAPITAL LETTER T]
2411"\u24C9" => "T"
2412
2413# Ꞇ [LATIN CAPITAL LETTER INSULAR T]
2414"\uA786" => "T"
2415
2416#  [FULLWIDTH LATIN CAPITAL LETTER T]
2417"\uFF34" => "T"
2418
2419# ţ [LATIN SMALL LETTER T WITH CEDILLA]
2420"\u0163" => "t"
2421
2422# ť [LATIN SMALL LETTER T WITH CARON]
2423"\u0165" => "t"
2424
2425# ŧ [LATIN SMALL LETTER T WITH STROKE]
2426"\u0167" => "t"
2427
2428# Æ« [LATIN SMALL LETTER T WITH PALATAL HOOK]
2429"\u01AB" => "t"
2430
2431# Æ­ [LATIN SMALL LETTER T WITH HOOK]
2432"\u01AD" => "t"
2433
2434# ț [LATIN SMALL LETTER T WITH COMMA BELOW]
2435"\u021B" => "t"
2436
2437# ȶ [LATIN SMALL LETTER T WITH CURL]
2438"\u0236" => "t"
2439
2440# ʇ [LATIN SMALL LETTER TURNED T]
2441"\u0287" => "t"
2442
2443# ʈ [LATIN SMALL LETTER T WITH RETROFLEX HOOK]
2444"\u0288" => "t"
2445
2446# áµµ [LATIN SMALL LETTER T WITH MIDDLE TILDE]
2447"\u1D75" => "t"
2448
2449# ṫ [LATIN SMALL LETTER T WITH DOT ABOVE]
2450"\u1E6B" => "t"
2451
2452# á¹­ [LATIN SMALL LETTER T WITH DOT BELOW]
2453"\u1E6D" => "t"
2454
2455# ṯ [LATIN SMALL LETTER T WITH LINE BELOW]
2456"\u1E6F" => "t"
2457
2458# á¹± [LATIN SMALL LETTER T WITH CIRCUMFLEX BELOW]
2459"\u1E71" => "t"
2460
2461# ẗ [LATIN SMALL LETTER T WITH DIAERESIS]
2462"\u1E97" => "t"
2463
2464# ⓣ [CIRCLED LATIN SMALL LETTER T]
2465"\u24E3" => "t"
2466
2467# ⱊ [LATIN SMALL LETTER T WITH DIAGONAL STROKE]
2468"\u2C66" => "t"
2469
2470#  [FULLWIDTH LATIN SMALL LETTER T]
2471"\uFF54" => "t"
2472
2473# Þ [LATIN CAPITAL LETTER THORN]
2474"\u00DE" => "TH"
2475
2476# Ꝋ [LATIN CAPITAL LETTER THORN WITH STROKE THROUGH DESCENDER]
2477"\uA766" => "TH"
2478
2479# ꜚ [LATIN CAPITAL LETTER TZ]
2480"\uA728" => "TZ"
2481
2482# ⒯ [PARENTHESIZED LATIN SMALL LETTER T]
2483"\u24AF" => "(t)"
2484
2485# Êš [LATIN SMALL LETTER TC DIGRAPH WITH CURL]
2486"\u02A8" => "tc"
2487
2488# ß [LATIN SMALL LETTER THORN]
2489"\u00FE" => "th"
2490
2491# ᵺ [LATIN SMALL LETTER TH WITH STRIKETHROUGH]
2492"\u1D7A" => "th"
2493
2494# ꝧ [LATIN SMALL LETTER THORN WITH STROKE THROUGH DESCENDER]
2495"\uA767" => "th"
2496
2497# ÊŠ [LATIN SMALL LETTER TS DIGRAPH]
2498"\u02A6" => "ts"
2499
2500# ꜩ [LATIN SMALL LETTER TZ]
2501"\uA729" => "tz"
2502
2503# Ù [LATIN CAPITAL LETTER U WITH GRAVE]
2504"\u00D9" => "U"
2505
2506# Ú [LATIN CAPITAL LETTER U WITH ACUTE]
2507"\u00DA" => "U"
2508
2509# Û [LATIN CAPITAL LETTER U WITH CIRCUMFLEX]
2510"\u00DB" => "U"
2511
2512# Ü [LATIN CAPITAL LETTER U WITH DIAERESIS]
2513"\u00DC" => "U"
2514
2515# Åš [LATIN CAPITAL LETTER U WITH TILDE]
2516"\u0168" => "U"
2517
2518# Ū [LATIN CAPITAL LETTER U WITH MACRON]
2519"\u016A" => "U"
2520
2521# Ŭ [LATIN CAPITAL LETTER U WITH BREVE]
2522"\u016C" => "U"
2523
2524# Å® [LATIN CAPITAL LETTER U WITH RING ABOVE]
2525"\u016E" => "U"
2526
2527# Å° [LATIN CAPITAL LETTER U WITH DOUBLE ACUTE]
2528"\u0170" => "U"
2529
2530# Ų [LATIN CAPITAL LETTER U WITH OGONEK]
2531"\u0172" => "U"
2532
2533# Ư [LATIN CAPITAL LETTER U WITH HORN]
2534"\u01AF" => "U"
2535
2536# Ǔ [LATIN CAPITAL LETTER U WITH CARON]
2537"\u01D3" => "U"
2538
2539# Ǖ [LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON]
2540"\u01D5" => "U"
2541
2542# Ǘ [LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE]
2543"\u01D7" => "U"
2544
2545# Ǚ [LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON]
2546"\u01D9" => "U"
2547
2548# Ǜ [LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE]
2549"\u01DB" => "U"
2550
2551# Ȕ [LATIN CAPITAL LETTER U WITH DOUBLE GRAVE]
2552"\u0214" => "U"
2553
2554# Ȗ [LATIN CAPITAL LETTER U WITH INVERTED BREVE]
2555"\u0216" => "U"
2556
2557# Ʉ [LATIN CAPITAL LETTER U BAR]
2558"\u0244" => "U"
2559
2560# ᮜ [LATIN LETTER SMALL CAPITAL U]
2561"\u1D1C" => "U"
2562
2563# ᵟ [LATIN SMALL CAPITAL LETTER U WITH STROKE]
2564"\u1D7E" => "U"
2565
2566# á¹² [LATIN CAPITAL LETTER U WITH DIAERESIS BELOW]
2567"\u1E72" => "U"
2568
2569# Ṏ [LATIN CAPITAL LETTER U WITH TILDE BELOW]
2570"\u1E74" => "U"
2571
2572# Ṷ [LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW]
2573"\u1E76" => "U"
2574
2575# Ṟ [LATIN CAPITAL LETTER U WITH TILDE AND ACUTE]
2576"\u1E78" => "U"
2577
2578# Ṻ [LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS]
2579"\u1E7A" => "U"
2580
2581# Ề [LATIN CAPITAL LETTER U WITH DOT BELOW]
2582"\u1EE4" => "U"
2583
2584# Ị [LATIN CAPITAL LETTER U WITH HOOK ABOVE]
2585"\u1EE6" => "U"
2586
2587# Ớ [LATIN CAPITAL LETTER U WITH HORN AND ACUTE]
2588"\u1EE8" => "U"
2589
2590# Ừ [LATIN CAPITAL LETTER U WITH HORN AND GRAVE]
2591"\u1EEA" => "U"
2592
2593# Ử [LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE]
2594"\u1EEC" => "U"
2595
2596# á»® [LATIN CAPITAL LETTER U WITH HORN AND TILDE]
2597"\u1EEE" => "U"
2598
2599# á»° [LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW]
2600"\u1EF0" => "U"
2601
2602# Ⓤ [CIRCLED LATIN CAPITAL LETTER U]
2603"\u24CA" => "U"
2604
2605#  [FULLWIDTH LATIN CAPITAL LETTER U]
2606"\uFF35" => "U"
2607
2608# ù [LATIN SMALL LETTER U WITH GRAVE]
2609"\u00F9" => "u"
2610
2611# ú [LATIN SMALL LETTER U WITH ACUTE]
2612"\u00FA" => "u"
2613
2614# û [LATIN SMALL LETTER U WITH CIRCUMFLEX]
2615"\u00FB" => "u"
2616
2617# Ì [LATIN SMALL LETTER U WITH DIAERESIS]
2618"\u00FC" => "u"
2619
2620# Å© [LATIN SMALL LETTER U WITH TILDE]
2621"\u0169" => "u"
2622
2623# Å« [LATIN SMALL LETTER U WITH MACRON]
2624"\u016B" => "u"
2625
2626# Å­ [LATIN SMALL LETTER U WITH BREVE]
2627"\u016D" => "u"
2628
2629# ů [LATIN SMALL LETTER U WITH RING ABOVE]
2630"\u016F" => "u"
2631
2632# ű [LATIN SMALL LETTER U WITH DOUBLE ACUTE]
2633"\u0171" => "u"
2634
2635# ų [LATIN SMALL LETTER U WITH OGONEK]
2636"\u0173" => "u"
2637
2638# Æ° [LATIN SMALL LETTER U WITH HORN]
2639"\u01B0" => "u"
2640
2641# ǔ [LATIN SMALL LETTER U WITH CARON]
2642"\u01D4" => "u"
2643
2644# ǖ [LATIN SMALL LETTER U WITH DIAERESIS AND MACRON]
2645"\u01D6" => "u"
2646
2647# ǘ [LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE]
2648"\u01D8" => "u"
2649
2650# ǚ [LATIN SMALL LETTER U WITH DIAERESIS AND CARON]
2651"\u01DA" => "u"
2652
2653# ǜ [LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE]
2654"\u01DC" => "u"
2655
2656# ȕ [LATIN SMALL LETTER U WITH DOUBLE GRAVE]
2657"\u0215" => "u"
2658
2659# ȗ [LATIN SMALL LETTER U WITH INVERTED BREVE]
2660"\u0217" => "u"
2661
2662# ʉ [LATIN SMALL LETTER U BAR]
2663"\u0289" => "u"
2664
2665# áµ€ [LATIN SUBSCRIPT SMALL LETTER U]
2666"\u1D64" => "u"
2667
2668# ᶙ [LATIN SMALL LETTER U WITH RETROFLEX HOOK]
2669"\u1D99" => "u"
2670
2671# á¹³ [LATIN SMALL LETTER U WITH DIAERESIS BELOW]
2672"\u1E73" => "u"
2673
2674# á¹µ [LATIN SMALL LETTER U WITH TILDE BELOW]
2675"\u1E75" => "u"
2676
2677# á¹· [LATIN SMALL LETTER U WITH CIRCUMFLEX BELOW]
2678"\u1E77" => "u"
2679
2680# á¹¹ [LATIN SMALL LETTER U WITH TILDE AND ACUTE]
2681"\u1E79" => "u"
2682
2683# á¹» [LATIN SMALL LETTER U WITH MACRON AND DIAERESIS]
2684"\u1E7B" => "u"
2685
2686# ụ [LATIN SMALL LETTER U WITH DOT BELOW]
2687"\u1EE5" => "u"
2688
2689# ủ [LATIN SMALL LETTER U WITH HOOK ABOVE]
2690"\u1EE7" => "u"
2691
2692# ứ [LATIN SMALL LETTER U WITH HORN AND ACUTE]
2693"\u1EE9" => "u"
2694
2695# ừ [LATIN SMALL LETTER U WITH HORN AND GRAVE]
2696"\u1EEB" => "u"
2697
2698# á»­ [LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE]
2699"\u1EED" => "u"
2700
2701# ữ [LATIN SMALL LETTER U WITH HORN AND TILDE]
2702"\u1EEF" => "u"
2703
2704# á»± [LATIN SMALL LETTER U WITH HORN AND DOT BELOW]
2705"\u1EF1" => "u"
2706
2707# â“€ [CIRCLED LATIN SMALL LETTER U]
2708"\u24E4" => "u"
2709
2710#  [FULLWIDTH LATIN SMALL LETTER U]
2711"\uFF55" => "u"
2712
2713# ⒰ [PARENTHESIZED LATIN SMALL LETTER U]
2714"\u24B0" => "(u)"
2715
2716# ᵫ [LATIN SMALL LETTER UE]
2717"\u1D6B" => "ue"
2718
2719# Ʋ [LATIN CAPITAL LETTER V WITH HOOK]
2720"\u01B2" => "V"
2721
2722# Ʌ
2723 [LATIN CAPITAL LETTER TURNED V]
2724"\u0245" => "V"
2725
2726# Ꭰ [LATIN LETTER SMALL CAPITAL V]
2727"\u1D20" => "V"
2728
2729# Ṍ [LATIN CAPITAL LETTER V WITH TILDE]
2730"\u1E7C" => "V"
2731
2732# ṟ [LATIN CAPITAL LETTER V WITH DOT BELOW]
2733"\u1E7E" => "V"
2734
2735# Ọ [LATIN CAPITAL LETTER MIDDLE-WELSH V]
2736"\u1EFC" => "V"
2737
2738# Ⓥ [CIRCLED LATIN CAPITAL LETTER V]
2739"\u24CB" => "V"
2740
2741# Ꝟ [LATIN CAPITAL LETTER V WITH DIAGONAL STROKE]
2742"\uA75E" => "V"
2743
2744# Ꝛ [LATIN CAPITAL LETTER VEND]
2745"\uA768" => "V"
2746
2747#  [FULLWIDTH LATIN CAPITAL LETTER V]
2748"\uFF36" => "V"
2749
2750# ʋ [LATIN SMALL LETTER V WITH HOOK]
2751"\u028B" => "v"
2752
2753# ʌ [LATIN SMALL LETTER TURNED V]
2754"\u028C" => "v"
2755
2756# áµ¥ [LATIN SUBSCRIPT SMALL LETTER V]
2757"\u1D65" => "v"
2758
2759# ᶌ [LATIN SMALL LETTER V WITH PALATAL HOOK]
2760"\u1D8C" => "v"
2761
2762# Ṝ [LATIN SMALL LETTER V WITH TILDE]
2763"\u1E7D" => "v"
2764
2765# ṿ [LATIN SMALL LETTER V WITH DOT BELOW]
2766"\u1E7F" => "v"
2767
2768# ⓥ [CIRCLED LATIN SMALL LETTER V]
2769"\u24E5" => "v"
2770
2771# â±± [LATIN SMALL LETTER V WITH RIGHT HOOK]
2772"\u2C71" => "v"
2773
2774# ⱎ [LATIN SMALL LETTER V WITH CURL]
2775"\u2C74" => "v"
2776
2777# ꝟ [LATIN SMALL LETTER V WITH DIAGONAL STROKE]
2778"\uA75F" => "v"
2779
2780#  [FULLWIDTH LATIN SMALL LETTER V]
2781"\uFF56" => "v"
2782
2783# Ꝡ [LATIN CAPITAL LETTER VY]
2784"\uA760" => "VY"
2785
2786# ⒱ [PARENTHESIZED LATIN SMALL LETTER V]
2787"\u24B1" => "(v)"
2788
2789# ꝡ [LATIN SMALL LETTER VY]
2790"\uA761" => "vy"
2791
2792# ÅŽ [LATIN CAPITAL LETTER W WITH CIRCUMFLEX]
2793"\u0174" => "W"
2794
2795# Ç· http://en.wikipedia.org/wiki/Wynn [LATIN CAPITAL LETTER WYNN]
2796"\u01F7" => "W"
2797
2798# Ꭱ [LATIN LETTER SMALL CAPITAL W]
2799"\u1D21" => "W"
2800
2801# Ẁ [LATIN CAPITAL LETTER W WITH GRAVE]
2802"\u1E80" => "W"
2803
2804# Ẃ [LATIN CAPITAL LETTER W WITH ACUTE]
2805"\u1E82" => "W"
2806
2807# Ẅ [LATIN CAPITAL LETTER W WITH DIAERESIS]
2808"\u1E84" => "W"
2809
2810# Ẇ [LATIN CAPITAL LETTER W WITH DOT ABOVE]
2811"\u1E86" => "W"
2812
2813# Ẉ [LATIN CAPITAL LETTER W WITH DOT BELOW]
2814"\u1E88" => "W"
2815
2816# Ⓦ [CIRCLED LATIN CAPITAL LETTER W]
2817"\u24CC" => "W"
2818
2819# â±² [LATIN CAPITAL LETTER W WITH HOOK]
2820"\u2C72" => "W"
2821
2822#  [FULLWIDTH LATIN CAPITAL LETTER W]
2823"\uFF37" => "W"
2824
2825# ŵ [LATIN SMALL LETTER W WITH CIRCUMFLEX]
2826"\u0175" => "w"
2827
2828# Æ¿ http://en.wikipedia.org/wiki/Wynn [LATIN LETTER WYNN]
2829"\u01BF" => "w"
2830
2831# ʍ [LATIN SMALL LETTER TURNED W]
2832"\u028D" => "w"
2833
2834# ẁ [LATIN SMALL LETTER W WITH GRAVE]
2835"\u1E81" => "w"
2836
2837# ẃ [LATIN SMALL LETTER W WITH ACUTE]
2838"\u1E83" => "w"
2839
2840# ẅ
2841 [LATIN SMALL LETTER W WITH DIAERESIS]
2842"\u1E85" => "w"
2843
2844# ẇ [LATIN SMALL LETTER W WITH DOT ABOVE]
2845"\u1E87" => "w"
2846
2847# ẉ [LATIN SMALL LETTER W WITH DOT BELOW]
2848"\u1E89" => "w"
2849
2850# ẘ [LATIN SMALL LETTER W WITH RING ABOVE]
2851"\u1E98" => "w"
2852
2853# ⓩ [CIRCLED LATIN SMALL LETTER W]
2854"\u24E6" => "w"
2855
2856# â±³ [LATIN SMALL LETTER W WITH HOOK]
2857"\u2C73" => "w"
2858
2859#  [FULLWIDTH LATIN SMALL LETTER W]
2860"\uFF57" => "w"
2861
2862# ⒲ [PARENTHESIZED LATIN SMALL LETTER W]
2863"\u24B2" => "(w)"
2864
2865# Ẋ [LATIN CAPITAL LETTER X WITH DOT ABOVE]
2866"\u1E8A" => "X"
2867
2868# Ẍ [LATIN CAPITAL LETTER X WITH DIAERESIS]
2869"\u1E8C" => "X"
2870
2871# Ⓧ [CIRCLED LATIN CAPITAL LETTER X]
2872"\u24CD" => "X"
2873
2874#  [FULLWIDTH LATIN CAPITAL LETTER X]
2875"\uFF38" => "X"
2876
2877# ᶍ [LATIN SMALL LETTER X WITH PALATAL HOOK]
2878"\u1D8D" => "x"
2879
2880# ẋ [LATIN SMALL LETTER X WITH DOT ABOVE]
2881"\u1E8B" => "x"
2882
2883# ẍ [LATIN SMALL LETTER X WITH DIAERESIS]
2884"\u1E8D" => "x"
2885
2886# ₓ [LATIN SUBSCRIPT SMALL LETTER X]
2887"\u2093" => "x"
2888
2889# ⓧ [CIRCLED LATIN SMALL LETTER X]
2890"\u24E7" => "x"
2891
2892#  [FULLWIDTH LATIN SMALL LETTER X]
2893"\uFF58" => "x"
2894
2895# ⒳ [PARENTHESIZED LATIN SMALL LETTER X]
2896"\u24B3" => "(x)"
2897
2898# Ý [LATIN CAPITAL LETTER Y WITH ACUTE]
2899"\u00DD" => "Y"
2900
2901# Ŷ [LATIN CAPITAL LETTER Y WITH CIRCUMFLEX]
2902"\u0176" => "Y"
2903
2904# Åž [LATIN CAPITAL LETTER Y WITH DIAERESIS]
2905"\u0178" => "Y"
2906
2907# Ƴ [LATIN CAPITAL LETTER Y WITH HOOK]
2908"\u01B3" => "Y"
2909
2910# Ȳ [LATIN CAPITAL LETTER Y WITH MACRON]
2911"\u0232" => "Y"
2912
2913# Ɏ [LATIN CAPITAL LETTER Y WITH STROKE]
2914"\u024E" => "Y"
2915
2916# ʏ [LATIN LETTER SMALL CAPITAL Y]
2917"\u028F" => "Y"
2918
2919# Ẏ [LATIN CAPITAL LETTER Y WITH DOT ABOVE]
2920"\u1E8E" => "Y"
2921
2922# Ỳ [LATIN CAPITAL LETTER Y WITH GRAVE]
2923"\u1EF2" => "Y"
2924
2925# Ỏ [LATIN CAPITAL LETTER Y WITH DOT BELOW]
2926"\u1EF4" => "Y"
2927
2928# Ỷ [LATIN CAPITAL LETTER Y WITH HOOK ABOVE]
2929"\u1EF6" => "Y"
2930
2931# Ở [LATIN CAPITAL LETTER Y WITH TILDE]
2932"\u1EF8" => "Y"
2933
2934# ở [LATIN CAPITAL LETTER Y WITH LOOP]
2935"\u1EFE" => "Y"
2936
2937# Ⓨ [CIRCLED LATIN CAPITAL LETTER Y]
2938"\u24CE" => "Y"
2939
2940#  [FULLWIDTH LATIN CAPITAL LETTER Y]
2941"\uFF39" => "Y"
2942
2943# Ü [LATIN SMALL LETTER Y WITH ACUTE]
2944"\u00FD" => "y"
2945
2946# ÿ [LATIN SMALL LETTER Y WITH DIAERESIS]
2947"\u00FF" => "y"
2948
2949# Å· [LATIN SMALL LETTER Y WITH CIRCUMFLEX]
2950"\u0177" => "y"
2951
2952# ÆŽ [LATIN SMALL LETTER Y WITH HOOK]
2953"\u01B4" => "y"
2954
2955# ȳ [LATIN SMALL LETTER Y WITH MACRON]
2956"\u0233" => "y"
2957
2958# ɏ [LATIN SMALL LETTER Y WITH STROKE]
2959"\u024F" => "y"
2960
2961# ʎ [LATIN SMALL LETTER TURNED Y]
2962"\u028E" => "y"
2963
2964# ẏ [LATIN SMALL LETTER Y WITH DOT ABOVE]
2965"\u1E8F" => "y"
2966
2967# ẙ [LATIN SMALL LETTER Y WITH RING ABOVE]
2968"\u1E99" => "y"
2969
2970# ỳ [LATIN SMALL LETTER Y WITH GRAVE]
2971"\u1EF3" => "y"
2972
2973# ỵ [LATIN SMALL LETTER Y WITH DOT BELOW]
2974"\u1EF5" => "y"
2975
2976# á»· [LATIN SMALL LETTER Y WITH HOOK ABOVE]
2977"\u1EF7" => "y"
2978
2979# ỹ [LATIN SMALL LETTER Y WITH TILDE]
2980"\u1EF9" => "y"
2981
2982# ỿ [LATIN SMALL LETTER Y WITH LOOP]
2983"\u1EFF" => "y"
2984
2985# ⓹ [CIRCLED LATIN SMALL LETTER Y]
2986"\u24E8" => "y"
2987
2988#  [FULLWIDTH LATIN SMALL LETTER Y]
2989"\uFF59" => "y"
2990
2991# ⒮ [PARENTHESIZED LATIN SMALL LETTER Y]
2992"\u24B4" => "(y)"
2993
2994# Ź [LATIN CAPITAL LETTER Z WITH ACUTE]
2995"\u0179" => "Z"
2996
2997# Å» [LATIN CAPITAL LETTER Z WITH DOT ABOVE]
2998"\u017B" => "Z"
2999
3000# Ŝ [LATIN CAPITAL LETTER Z WITH CARON]
3001"\u017D" => "Z"
3002
3003# Ƶ [LATIN CAPITAL LETTER Z WITH STROKE]
3004"\u01B5" => "Z"
3005
3006# Ȝ http://en.wikipedia.org/wiki/Yogh [LATIN CAPITAL LETTER YOGH]
3007"\u021C" => "Z"
3008
3009# Ȁ [LATIN CAPITAL LETTER Z WITH HOOK]
3010"\u0224" => "Z"
3011
3012# Ꭲ [LATIN LETTER SMALL CAPITAL Z]
3013"\u1D22" => "Z"
3014
3015# Ẑ [LATIN CAPITAL LETTER Z WITH CIRCUMFLEX]
3016"\u1E90" => "Z"
3017
3018# Ẓ [LATIN CAPITAL LETTER Z WITH DOT BELOW]
3019"\u1E92" => "Z"
3020
3021# Ẕ [LATIN CAPITAL LETTER Z WITH LINE BELOW]
3022"\u1E94" => "Z"
3023
3024# Ⓩ [CIRCLED LATIN CAPITAL LETTER Z]
3025"\u24CF" => "Z"
3026
3027# Ⱬ [LATIN CAPITAL LETTER Z WITH DESCENDER]
3028"\u2C6B" => "Z"
3029
3030# Ꝣ [LATIN CAPITAL LETTER VISIGOTHIC Z]
3031"\uA762" => "Z"
3032
3033#  [FULLWIDTH LATIN CAPITAL LETTER Z]
3034"\uFF3A" => "Z"
3035
3036# ź [LATIN SMALL LETTER Z WITH ACUTE]
3037"\u017A" => "z"
3038
3039# Ō [LATIN SMALL LETTER Z WITH DOT ABOVE]
3040"\u017C" => "z"
3041
3042# ÅŸ [LATIN SMALL LETTER Z WITH CARON]
3043"\u017E" => "z"
3044
3045# ƶ [LATIN SMALL LETTER Z WITH STROKE]
3046"\u01B6" => "z"
3047
3048# ȝ http://en.wikipedia.org/wiki/Yogh [LATIN SMALL LETTER YOGH]
3049"\u021D" => "z"
3050
3051# ȥ [LATIN SMALL LETTER Z WITH HOOK]
3052"\u0225" => "z"
3053
3054# ɀ [LATIN SMALL LETTER Z WITH SWASH TAIL]
3055"\u0240" => "z"
3056
3057# ʐ [LATIN SMALL LETTER Z WITH RETROFLEX HOOK]
3058"\u0290" => "z"
3059
3060# ʑ [LATIN SMALL LETTER Z WITH CURL]
3061"\u0291" => "z"
3062
3063# ᵶ [LATIN SMALL LETTER Z WITH MIDDLE TILDE]
3064"\u1D76" => "z"
3065
3066# ᶎ [LATIN SMALL LETTER Z WITH PALATAL HOOK]
3067"\u1D8E" => "z"
3068
3069# ẑ [LATIN SMALL LETTER Z WITH CIRCUMFLEX]
3070"\u1E91" => "z"
3071
3072# ẓ [LATIN SMALL LETTER Z WITH DOT BELOW]
3073"\u1E93" => "z"
3074
3075# ẕ [LATIN SMALL LETTER Z WITH LINE BELOW]
3076"\u1E95" => "z"
3077
3078# ⓩ [CIRCLED LATIN SMALL LETTER Z]
3079"\u24E9" => "z"
3080
3081# ⱬ [LATIN SMALL LETTER Z WITH DESCENDER]
3082"\u2C6C" => "z"
3083
3084# ꝣ [LATIN SMALL LETTER VISIGOTHIC Z]
3085"\uA763" => "z"
3086
3087#  [FULLWIDTH LATIN SMALL LETTER Z]
3088"\uFF5A" => "z"
3089
3090# ⒵ [PARENTHESIZED LATIN SMALL LETTER Z]
3091"\u24B5" => "(z)"
3092
3093# ⁰ [SUPERSCRIPT ZERO]
3094"\u2070" => "0"
3095
3096# ₀ [SUBSCRIPT ZERO]
3097"\u2080" => "0"
3098
3099# ⓪ [CIRCLED DIGIT ZERO]
3100"\u24EA" => "0"
3101
3102# ⓿ [NEGATIVE CIRCLED DIGIT ZERO]
3103"\u24FF" => "0"
3104
3105#  [FULLWIDTH DIGIT ZERO]
3106"\uFF10" => "0"
3107
3108# ¹ [SUPERSCRIPT ONE]
3109"\u00B9" => "1"
3110
3111# ₁ [SUBSCRIPT ONE]
3112"\u2081" => "1"
3113
3114# ① [CIRCLED DIGIT ONE]
3115"\u2460" => "1"
3116
3117# ⓵ [DOUBLE CIRCLED DIGIT ONE]
3118"\u24F5" => "1"
3119
3120# ❶ [DINGBAT NEGATIVE CIRCLED DIGIT ONE]
3121"\u2776" => "1"
3122
3123# ➀ [DINGBAT CIRCLED SANS-SERIF DIGIT ONE]
3124"\u2780" => "1"
3125
3126# ➊ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ONE]
3127"\u278A" => "1"
3128
3129#  [FULLWIDTH DIGIT ONE]
3130"\uFF11" => "1"
3131
3132# ⒈ [DIGIT ONE FULL STOP]
3133"\u2488" => "1."
3134
3135# ⑮ [PARENTHESIZED DIGIT ONE]
3136"\u2474" => "(1)"
3137
3138# ² [SUPERSCRIPT TWO]
3139"\u00B2" => "2"
3140
3141# ₂ [SUBSCRIPT TWO]
3142"\u2082" => "2"
3143
3144# ② [CIRCLED DIGIT TWO]
3145"\u2461" => "2"
3146
3147# ⓶ [DOUBLE CIRCLED DIGIT TWO]
3148"\u24F6" => "2"
3149
3150# ❷ [DINGBAT NEGATIVE CIRCLED DIGIT TWO]
3151"\u2777" => "2"
3152
3153# ➁ [DINGBAT CIRCLED SANS-SERIF DIGIT TWO]
3154"\u2781" => "2"
3155
3156# ➋ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT TWO]
3157"\u278B" => "2"
3158
3159#  [FULLWIDTH DIGIT TWO]
3160"\uFF12" => "2"
3161
3162# ⒉ [DIGIT TWO FULL STOP]
3163"\u2489" => "2."
3164
3165# ⑵ [PARENTHESIZED DIGIT TWO]
3166"\u2475" => "(2)"
3167
3168# ³ [SUPERSCRIPT THREE]
3169"\u00B3" => "3"
3170
3171# ₃ [SUBSCRIPT THREE]
3172"\u2083" => "3"
3173
3174# ③ [CIRCLED DIGIT THREE]
3175"\u2462" => "3"
3176
3177# ⓷ [DOUBLE CIRCLED DIGIT THREE]
3178"\u24F7" => "3"
3179
3180# ❞ [DINGBAT NEGATIVE CIRCLED DIGIT THREE]
3181"\u2778" => "3"
3182
3183# ➂ [DINGBAT CIRCLED SANS-SERIF DIGIT THREE]
3184"\u2782" => "3"
3185
3186# ➌ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT THREE]
3187"\u278C" => "3"
3188
3189#  [FULLWIDTH DIGIT THREE]
3190"\uFF13" => "3"
3191
3192# ⒊ [DIGIT THREE FULL STOP]
3193"\u248A" => "3."
3194
3195# ⑶ [PARENTHESIZED DIGIT THREE]
3196"\u2476" => "(3)"
3197
3198# ⁎ [SUPERSCRIPT FOUR]
3199"\u2074" => "4"
3200
3201# ₄ [SUBSCRIPT FOUR]
3202"\u2084" => "4"
3203
3204# ④ [CIRCLED DIGIT FOUR]
3205"\u2463" => "4"
3206
3207# ⓾ [DOUBLE CIRCLED DIGIT FOUR]
3208"\u24F8" => "4"
3209
3210# ❹ [DINGBAT NEGATIVE CIRCLED DIGIT FOUR]
3211"\u2779" => "4"
3212
3213# ➃ [DINGBAT CIRCLED SANS-SERIF DIGIT FOUR]
3214"\u2783" => "4"
3215
3216# ➍ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FOUR]
3217"\u278D" => "4"
3218
3219#  [FULLWIDTH DIGIT FOUR]
3220"\uFF14" => "4"
3221
3222# ⒋ [DIGIT FOUR FULL STOP]
3223"\u248B" => "4."
3224
3225# ⑷ [PARENTHESIZED DIGIT FOUR]
3226"\u2477" => "(4)"
3227
3228# ⁵ [SUPERSCRIPT FIVE]
3229"\u2075" => "5"
3230
3231# ₅
3232 [SUBSCRIPT FIVE]
3233"\u2085" => "5"
3234
3235# â‘€ [CIRCLED DIGIT FIVE]
3236"\u2464" => "5"
3237
3238# ⓹ [DOUBLE CIRCLED DIGIT FIVE]
3239"\u24F9" => "5"
3240
3241# ❺ [DINGBAT NEGATIVE CIRCLED DIGIT FIVE]
3242"\u277A" => "5"
3243
3244# ➄ [DINGBAT CIRCLED SANS-SERIF DIGIT FIVE]
3245"\u2784" => "5"
3246
3247# ➎ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FIVE]
3248"\u278E" => "5"
3249
3250#  [FULLWIDTH DIGIT FIVE]
3251"\uFF15" => "5"
3252
3253# ⒌ [DIGIT FIVE FULL STOP]
3254"\u248C" => "5."
3255
3256# ⑾ [PARENTHESIZED DIGIT FIVE]
3257"\u2478" => "(5)"
3258
3259# ⁶ [SUPERSCRIPT SIX]
3260"\u2076" => "6"
3261
3262# ₆ [SUBSCRIPT SIX]
3263"\u2086" => "6"
3264
3265# ⑥ [CIRCLED DIGIT SIX]
3266"\u2465" => "6"
3267
3268# ⓺ [DOUBLE CIRCLED DIGIT SIX]
3269"\u24FA" => "6"
3270
3271# ❻ [DINGBAT NEGATIVE CIRCLED DIGIT SIX]
3272"\u277B" => "6"
3273
3274# ➅
3275 [DINGBAT CIRCLED SANS-SERIF DIGIT SIX]
3276"\u2785" => "6"
3277
3278# ➏ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SIX]
3279"\u278F" => "6"
3280
3281#  [FULLWIDTH DIGIT SIX]
3282"\uFF16" => "6"
3283
3284# ⒍ [DIGIT SIX FULL STOP]
3285"\u248D" => "6."
3286
3287# ⑹ [PARENTHESIZED DIGIT SIX]
3288"\u2479" => "(6)"
3289
3290# ⁷ [SUPERSCRIPT SEVEN]
3291"\u2077" => "7"
3292
3293# ₇ [SUBSCRIPT SEVEN]
3294"\u2087" => "7"
3295
3296# ⑩ [CIRCLED DIGIT SEVEN]
3297"\u2466" => "7"
3298
3299# ⓻ [DOUBLE CIRCLED DIGIT SEVEN]
3300"\u24FB" => "7"
3301
3302# ❌ [DINGBAT NEGATIVE CIRCLED DIGIT SEVEN]
3303"\u277C" => "7"
3304
3305# ➆ [DINGBAT CIRCLED SANS-SERIF DIGIT SEVEN]
3306"\u2786" => "7"
3307
3308# ➐ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SEVEN]
3309"\u2790" => "7"
3310
3311#  [FULLWIDTH DIGIT SEVEN]
3312"\uFF17" => "7"
3313
3314# ⒎ [DIGIT SEVEN FULL STOP]
3315"\u248E" => "7."
3316
3317# ⑺ [PARENTHESIZED DIGIT SEVEN]
3318"\u247A" => "(7)"
3319
3320# ⁞ [SUPERSCRIPT EIGHT]
3321"\u2078" => "8"
3322
3323# ₈ [SUBSCRIPT EIGHT]
3324"\u2088" => "8"
3325
3326# ⑧ [CIRCLED DIGIT EIGHT]
3327"\u2467" => "8"
3328
3329# Ⓦ [DOUBLE CIRCLED DIGIT EIGHT]
3330"\u24FC" => "8"
3331
3332# ❜ [DINGBAT NEGATIVE CIRCLED DIGIT EIGHT]
3333"\u277D" => "8"
3334
3335# ➇ [DINGBAT CIRCLED SANS-SERIF DIGIT EIGHT]
3336"\u2787" => "8"
3337
3338# ➑ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT EIGHT]
3339"\u2791" => "8"
3340
3341#  [FULLWIDTH DIGIT EIGHT]
3342"\uFF18" => "8"
3343
3344# ⒏ [DIGIT EIGHT FULL STOP]
3345"\u248F" => "8."
3346
3347# ⑻ [PARENTHESIZED DIGIT EIGHT]
3348"\u247B" => "(8)"
3349
3350# ⁹ [SUPERSCRIPT NINE]
3351"\u2079" => "9"
3352
3353# ₉ [SUBSCRIPT NINE]
3354"\u2089" => "9"
3355
3356# ⑹ [CIRCLED DIGIT NINE]
3357"\u2468" => "9"
3358
3359# ⓜ [DOUBLE CIRCLED DIGIT NINE]
3360"\u24FD" => "9"
3361
3362# ❟ [DINGBAT NEGATIVE CIRCLED DIGIT NINE]
3363"\u277E" => "9"
3364
3365# ➈ [DINGBAT CIRCLED SANS-SERIF DIGIT NINE]
3366"\u2788" => "9"
3367
3368# ➒ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT NINE]
3369"\u2792" => "9"
3370
3371#  [FULLWIDTH DIGIT NINE]
3372"\uFF19" => "9"
3373
3374# ⒐ [DIGIT NINE FULL STOP]
3375"\u2490" => "9."
3376
3377# ⑌ [PARENTHESIZED DIGIT NINE]
3378"\u247C" => "(9)"
3379
3380# ⑩ [CIRCLED NUMBER TEN]
3381"\u2469" => "10"
3382
3383# â“Ÿ [DOUBLE CIRCLED NUMBER TEN]
3384"\u24FE" => "10"
3385
3386# ❿ [DINGBAT NEGATIVE CIRCLED NUMBER TEN]
3387"\u277F" => "10"
3388
3389# ➉ [DINGBAT CIRCLED SANS-SERIF NUMBER TEN]
3390"\u2789" => "10"
3391
3392# ➓ [DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN]
3393"\u2793" => "10"
3394
3395# ⒑ [NUMBER TEN FULL STOP]
3396"\u2491" => "10."
3397
3398# ⑜ [PARENTHESIZED NUMBER TEN]
3399"\u247D" => "(10)"
3400
3401# ⑪ [CIRCLED NUMBER ELEVEN]
3402"\u246A" => "11"
3403
3404# ⓫ [NEGATIVE CIRCLED NUMBER ELEVEN]
3405"\u24EB" => "11"
3406
3407# ⒒ [NUMBER ELEVEN FULL STOP]
3408"\u2492" => "11."
3409
3410# â‘Ÿ [PARENTHESIZED NUMBER ELEVEN]
3411"\u247E" => "(11)"
3412
3413# ⑫ [CIRCLED NUMBER TWELVE]
3414"\u246B" => "12"
3415
3416# ⓬ [NEGATIVE CIRCLED NUMBER TWELVE]
3417"\u24EC" => "12"
3418
3419# ⒓ [NUMBER TWELVE FULL STOP]
3420"\u2493" => "12."
3421
3422# ⑿ [PARENTHESIZED NUMBER TWELVE]
3423"\u247F" => "(12)"
3424
3425# ⑬ [CIRCLED NUMBER THIRTEEN]
3426"\u246C" => "13"
3427
3428# ⓭ [NEGATIVE CIRCLED NUMBER THIRTEEN]
3429"\u24ED" => "13"
3430
3431# ⒔ [NUMBER THIRTEEN FULL STOP]
3432"\u2494" => "13."
3433
3434# ⒀ [PARENTHESIZED NUMBER THIRTEEN]
3435"\u2480" => "(13)"
3436
3437# ⑭ [CIRCLED NUMBER FOURTEEN]
3438"\u246D" => "14"
3439
3440# ⓮ [NEGATIVE CIRCLED NUMBER FOURTEEN]
3441"\u24EE" => "14"
3442
3443# ⒕ [NUMBER FOURTEEN FULL STOP]
3444"\u2495" => "14."
3445
3446# ⒁ [PARENTHESIZED NUMBER FOURTEEN]
3447"\u2481" => "(14)"
3448
3449# ⑮ [CIRCLED NUMBER FIFTEEN]
3450"\u246E" => "15"
3451
3452# ⓯ [NEGATIVE CIRCLED NUMBER FIFTEEN]
3453"\u24EF" => "15"
3454
3455# ⒖ [NUMBER FIFTEEN FULL STOP]
3456"\u2496" => "15."
3457
3458# ⒂ [PARENTHESIZED NUMBER FIFTEEN]
3459"\u2482" => "(15)"
3460
3461# ⑯ [CIRCLED NUMBER SIXTEEN]
3462"\u246F" => "16"
3463
3464# ⓰ [NEGATIVE CIRCLED NUMBER SIXTEEN]
3465"\u24F0" => "16"
3466
3467# ⒗ [NUMBER SIXTEEN FULL STOP]
3468"\u2497" => "16."
3469
3470# ⒃ [PARENTHESIZED NUMBER SIXTEEN]
3471"\u2483" => "(16)"
3472
3473# ⑰ [CIRCLED NUMBER SEVENTEEN]
3474"\u2470" => "17"
3475
3476# ⓱ [NEGATIVE CIRCLED NUMBER SEVENTEEN]
3477"\u24F1" => "17"
3478
3479# ⒘ [NUMBER SEVENTEEN FULL STOP]
3480"\u2498" => "17."
3481
3482# ⒄ [PARENTHESIZED NUMBER SEVENTEEN]
3483"\u2484" => "(17)"
3484
3485# ⑱ [CIRCLED NUMBER EIGHTEEN]
3486"\u2471" => "18"
3487
3488# ⓲ [NEGATIVE CIRCLED NUMBER EIGHTEEN]
3489"\u24F2" => "18"
3490
3491# ⒙ [NUMBER EIGHTEEN FULL STOP]
3492"\u2499" => "18."
3493
3494# ⒅
3495 [PARENTHESIZED NUMBER EIGHTEEN]
3496"\u2485" => "(18)"
3497
3498# ⑲ [CIRCLED NUMBER NINETEEN]
3499"\u2472" => "19"
3500
3501# ⓳ [NEGATIVE CIRCLED NUMBER NINETEEN]
3502"\u24F3" => "19"
3503
3504# ⒚ [NUMBER NINETEEN FULL STOP]
3505"\u249A" => "19."
3506
3507# ⒆ [PARENTHESIZED NUMBER NINETEEN]
3508"\u2486" => "(19)"
3509
3510# ⑳ [CIRCLED NUMBER TWENTY]
3511"\u2473" => "20"
3512
3513# ⓮ [NEGATIVE CIRCLED NUMBER TWENTY]
3514"\u24F4" => "20"
3515
3516# ⒛ [NUMBER TWENTY FULL STOP]
3517"\u249B" => "20."
3518
3519# ⒇ [PARENTHESIZED NUMBER TWENTY]
3520"\u2487" => "(20)"
3521
3522# « [LEFT-POINTING DOUBLE ANGLE QUOTATION MARK]
3523"\u00AB" => "\""
3524
3525# » [RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK]
3526"\u00BB" => "\""
3527
3528# “ [LEFT DOUBLE QUOTATION MARK]
3529"\u201C" => "\""
3530
3531# ” [RIGHT DOUBLE QUOTATION MARK]
3532"\u201D" => "\""
3533
3534# „ [DOUBLE LOW-9 QUOTATION MARK]
3535"\u201E" => "\""
3536
3537# ″ [DOUBLE PRIME]
3538"\u2033" => "\""
3539
3540# ‶ [REVERSED DOUBLE PRIME]
3541"\u2036" => "\""
3542
3543# ❝ [HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT]
3544"\u275D" => "\""
3545
3546# ❞ [HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT]
3547"\u275E" => "\""
3548
3549# ❮ [HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT]
3550"\u276E" => "\""
3551
3552# ❯ [HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT]
3553"\u276F" => "\""
3554
3555#  [FULLWIDTH QUOTATION MARK]
3556"\uFF02" => "\""
3557
3558# ‘ [LEFT SINGLE QUOTATION MARK]
3559"\u2018" => "\'"
3560
3561# ’ [RIGHT SINGLE QUOTATION MARK]
3562"\u2019" => "\'"
3563
3564# ‚ [SINGLE LOW-9 QUOTATION MARK]
3565"\u201A" => "\'"
3566
3567# ‛ [SINGLE HIGH-REVERSED-9 QUOTATION MARK]
3568"\u201B" => "\'"
3569
3570# ′ [PRIME]
3571"\u2032" => "\'"
3572
3573# ‵ [REVERSED PRIME]
3574"\u2035" => "\'"
3575
3576# ‹ [SINGLE LEFT-POINTING ANGLE QUOTATION MARK]
3577"\u2039" => "\'"
3578
3579# › [SINGLE RIGHT-POINTING ANGLE QUOTATION MARK]
3580"\u203A" => "\'"
3581
3582# ❛ [HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT]
3583"\u275B" => "\'"
3584
3585# ❜ [HEAVY SINGLE COMMA QUOTATION MARK ORNAMENT]
3586"\u275C" => "\'"
3587
3588#  [FULLWIDTH APOSTROPHE]
3589"\uFF07" => "\'"
3590
3591# ‐ [HYPHEN]
3592"\u2010" => "-"
3593
3594# ‑ [NON-BREAKING HYPHEN]
3595"\u2011" => "-"
3596
3597# ‒ [FIGURE DASH]
3598"\u2012" => "-"
3599
3600# – [EN DASH]
3601"\u2013" => "-"
3602
3603# — [EM DASH]
3604"\u2014" => "-"
3605
3606# ⁻ [SUPERSCRIPT MINUS]
3607"\u207B" => "-"
3608
3609# ₋ [SUBSCRIPT MINUS]
3610"\u208B" => "-"
3611
3612#  [FULLWIDTH HYPHEN-MINUS]
3613"\uFF0D" => "-"
3614
3615# ⁅
3616 [LEFT SQUARE BRACKET WITH QUILL]
3617"\u2045" => "["
3618
3619# ❲ [LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT]
3620"\u2772" => "["
3621
3622#  [FULLWIDTH LEFT SQUARE BRACKET]
3623"\uFF3B" => "["
3624
3625# ⁆ [RIGHT SQUARE BRACKET WITH QUILL]
3626"\u2046" => "]"
3627
3628# ❳ [LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT]
3629"\u2773" => "]"
3630
3631#  [FULLWIDTH RIGHT SQUARE BRACKET]
3632"\uFF3D" => "]"
3633
3634# ⁜ [SUPERSCRIPT LEFT PARENTHESIS]
3635"\u207D" => "("
3636
3637# ₍ [SUBSCRIPT LEFT PARENTHESIS]
3638"\u208D" => "("
3639
3640# ❚ [MEDIUM LEFT PARENTHESIS ORNAMENT]
3641"\u2768" => "("
3642
3643# ❪ [MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT]
3644"\u276A" => "("
3645
3646#  [FULLWIDTH LEFT PARENTHESIS]
3647"\uFF08" => "("
3648
3649# âžš [LEFT DOUBLE PARENTHESIS]
3650"\u2E28" => "(("
3651
3652#   [SUPERSCRIPT RIGHT PARENTHESIS]
3653"\u207E" => ")"
3654
3655# ₎ [SUBSCRIPT RIGHT PARENTHESIS]
3656"\u208E" => ")"
3657
3658# ❩ [MEDIUM RIGHT PARENTHESIS ORNAMENT]
3659"\u2769" => ")"
3660
3661# ❫ [MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT]
3662"\u276B" => ")"
3663
3664#  [FULLWIDTH RIGHT PARENTHESIS]
3665"\uFF09" => ")"
3666
3667# âž© [RIGHT DOUBLE PARENTHESIS]
3668"\u2E29" => "))"
3669
3670# ❬ [MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT]
3671"\u276C" => "<"
3672
3673# ❰ [HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT]
3674"\u2770" => "<"
3675
3676#  [FULLWIDTH LESS-THAN SIGN]
3677"\uFF1C" => "<"
3678
3679# ❭ [MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT]
3680"\u276D" => ">"
3681
3682# ❱ [HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT]
3683"\u2771" => ">"
3684
3685#  [FULLWIDTH GREATER-THAN SIGN]
3686"\uFF1E" => ">"
3687
3688# ❎ [MEDIUM LEFT CURLY BRACKET ORNAMENT]
3689"\u2774" => "{"
3690
3691#  [FULLWIDTH LEFT CURLY BRACKET]
3692"\uFF5B" => "{"
3693
3694# ❵ [MEDIUM RIGHT CURLY BRACKET ORNAMENT]
3695"\u2775" => "}"
3696
3697#  [FULLWIDTH RIGHT CURLY BRACKET]
3698"\uFF5D" => "}"
3699
3700# ⁺ [SUPERSCRIPT PLUS SIGN]
3701"\u207A" => "+"
3702
3703# ₊ [SUBSCRIPT PLUS SIGN]
3704"\u208A" => "+"
3705
3706#  [FULLWIDTH PLUS SIGN]
3707"\uFF0B" => "+"
3708
3709# ⁌ [SUPERSCRIPT EQUALS SIGN]
3710"\u207C" => "="
3711
3712# ₌ [SUBSCRIPT EQUALS SIGN]
3713"\u208C" => "="
3714
3715#  [FULLWIDTH EQUALS SIGN]
3716"\uFF1D" => "="
3717
3718#  [FULLWIDTH EXCLAMATION MARK]
3719"\uFF01" => "!"
3720
3721# ‌ [DOUBLE EXCLAMATION MARK]
3722"\u203C" => "!!"
3723
3724# ⁉ [EXCLAMATION QUESTION MARK]
3725"\u2049" => "!?"
3726
3727#  [FULLWIDTH NUMBER SIGN]
3728"\uFF03" => "#"
3729
3730#  [FULLWIDTH DOLLAR SIGN]
3731"\uFF04" => "$"
3732
3733# ⁒ [COMMERCIAL MINUS SIGN]
3734"\u2052" => "%"
3735
3736# 
3737 [FULLWIDTH PERCENT SIGN]
3738"\uFF05" => "%"
3739
3740#  [FULLWIDTH AMPERSAND]
3741"\uFF06" => "&"
3742
3743# ⁎ [LOW ASTERISK]
3744"\u204E" => "*"
3745
3746#  [FULLWIDTH ASTERISK]
3747"\uFF0A" => "*"
3748
3749#  [FULLWIDTH COMMA]
3750"\uFF0C" => ","
3751
3752#  [FULLWIDTH FULL STOP]
3753"\uFF0E" => "."
3754
3755# ⁄ [FRACTION SLASH]
3756"\u2044" => "/"
3757
3758#  [FULLWIDTH SOLIDUS]
3759"\uFF0F" => "/"
3760
3761#  [FULLWIDTH COLON]
3762"\uFF1A" => ":"
3763
3764# ⁏ [REVERSED SEMICOLON]
3765"\u204F" => ";"
3766
3767#  [FULLWIDTH SEMICOLON]
3768"\uFF1B" => ";"
3769
3770#  [FULLWIDTH QUESTION MARK]
3771"\uFF1F" => "?"
3772
3773# ⁇ [DOUBLE QUESTION MARK]
3774"\u2047" => "??"
3775
3776# ⁈ [QUESTION EXCLAMATION MARK]
3777"\u2048" => "?!"
3778
3779#  [FULLWIDTH COMMERCIAL AT]
3780"\uFF20" => "@"
3781
3782#  [FULLWIDTH REVERSE SOLIDUS]
3783"\uFF3C" => "\\"
3784
3785# ‾ [CARET]
3786"\u2038" => "^"
3787
3788#  [FULLWIDTH CIRCUMFLEX ACCENT]
3789"\uFF3E" => "^"
3790
3791#  [FULLWIDTH LOW LINE]
3792"\uFF3F" => "_"
3793
3794# ⁓ [SWUNG DASH]
3795"\u2053" => "~"
3796
3797#  [FULLWIDTH TILDE]
3798"\uFF5E" => "~"
3799
3800################################################################
3801# Below is the Perl script used to generate the above mappings #
3802# from ASCIIFoldingFilter.java: #
3803################################################################
3804#
3805# #!/usr/bin/perl
3806#
3807# use warnings;
3808# use strict;
3809#
3810# my @source_chars = ();
3811# my @source_char_descriptions = ();
3812# my $target = '';
3813#
3814# while (<>) {
3815# if (/case\s+'(\\u[A-F0-9]+)':\s*\/\/\s*(.*)/i) {
3816# push @source_chars, $1;
3817# push @source_char_descriptions, $2;
3818# next;
3819# }
3820# if (/output\[[^\]]+\]\s*=\s*'(\\'|\\\\|.)'/) {
3821# $target .= $1;
3822# next;
3823# }
3824# if (/break;/) {
3825# $target = "\\\"" if ($target eq '"');
3826# for my $source_char_num (0..$#source_chars) {
3827# print "# $source_char_descriptions[$source_char_num]\n";
3828# print "\"$source_chars[$source_char_num]\" => \"$target\"\n\n";
3829# }
3830# @source_chars = ();
3831# @source_char_descriptions = ();
3832# $target = '';
3833# }
3834# }
Note: See TracBrowser for help on using the repository browser.