transliterate 0.0.1

Sign up to get free protection for your applications and to get access to all the features.
@@ -0,0 +1,4 @@
1
+ *.gem
2
+ .bundle
3
+ Gemfile.lock
4
+ pkg/*
data/Gemfile ADDED
@@ -0,0 +1,4 @@
1
+ source "http://rubygems.org"
2
+
3
+ # Specify your gem's dependencies in transliterate.gemspec
4
+ gemspec
@@ -0,0 +1 @@
1
+ require 'bundler/gem_tasks'
@@ -0,0 +1,6 @@
1
+ require "transliterate/version"
2
+ require 'transliterate/convert_utils'
3
+
4
+ module Transliterate
5
+
6
+ end
@@ -0,0 +1,1972 @@
1
+ class ConvertUtils
2
+ module Helper
3
+ def convert_for_search(method_name)
4
+ self.send(method_name) && ConvertUtils.convert(self.send(method_name)).downcase
5
+ end
6
+
7
+ def convert(s)
8
+ ConvertUtils.convert(s)
9
+ end
10
+
11
+ def method_missing(method_id, *arguments, &block)
12
+ if method_id.to_s =~ /^searchable_(.*)$/
13
+ ConvertUtils.convert self.send($1.to_sym)
14
+ else
15
+ super
16
+ end
17
+ end
18
+ end
19
+
20
+ class << self
21
+ def expand m
22
+ h = {}
23
+ m.each do |k, v|
24
+ k.each do |u|
25
+ h[u.hex] = v.unpack("U*")
26
+ end
27
+ end
28
+ h
29
+ end
30
+ end
31
+
32
+ UNICODE_TO_ASCII = expand({
33
+ [
34
+ '00C0', # À [LATIN CAPITAL LETTER A WITH GRAVE]
35
+ '00C1', # Á [LATIN CAPITAL LETTER A WITH ACUTE]
36
+ '00C2', # Â [LATIN CAPITAL LETTER A WITH CIRCUMFLEX]
37
+ '00C3', # Ã [LATIN CAPITAL LETTER A WITH TILDE]
38
+ '00C4', # Ä [LATIN CAPITAL LETTER A WITH DIAERESIS]
39
+ '00C5', # Å [LATIN CAPITAL LETTER A WITH RING ABOVE]
40
+ '0100', # Ā [LATIN CAPITAL LETTER A WITH MACRON]
41
+ '0102', # Ă [LATIN CAPITAL LETTER A WITH BREVE]
42
+ '0104', # Ą [LATIN CAPITAL LETTER A WITH OGONEK]
43
+ '018F', # Ə http://en.wikipedia.org/wiki/Schwa [LATIN CAPITAL LETTER SCHWA]
44
+ '01CD', # Ǎ [LATIN CAPITAL LETTER A WITH CARON]
45
+ '01DE', # Ǟ [LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON]
46
+ '01E0', # Ǡ [LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON]
47
+ '01FA', # Ǻ [LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE]
48
+ '0200', # Ȁ [LATIN CAPITAL LETTER A WITH DOUBLE GRAVE]
49
+ '0202', # Ȃ [LATIN CAPITAL LETTER A WITH INVERTED BREVE]
50
+ '0226', # Ȧ [LATIN CAPITAL LETTER A WITH DOT ABOVE]
51
+ '023A', # Ⱥ [LATIN CAPITAL LETTER A WITH STROKE]
52
+ '1D00', # ᴀ [LATIN LETTER SMALL CAPITAL A]
53
+ '1E00', # Ḁ [LATIN CAPITAL LETTER A WITH RING BELOW]
54
+ '1EA0', # Ạ [LATIN CAPITAL LETTER A WITH DOT BELOW]
55
+ '1EA2', # Ả [LATIN CAPITAL LETTER A WITH HOOK ABOVE]
56
+ '1EA4', # Ấ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE]
57
+ '1EA6', # Ầ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE]
58
+ '1EA8', # Ẩ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE]
59
+ '1EAA', # Ẫ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE]
60
+ '1EAC', # Ậ [LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW]
61
+ '1EAE', # Ắ [LATIN CAPITAL LETTER A WITH BREVE AND ACUTE]
62
+ '1EB0', # Ằ [LATIN CAPITAL LETTER A WITH BREVE AND GRAVE]
63
+ '1EB2', # Ẳ [LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE]
64
+ '1EB4', # Ẵ [LATIN CAPITAL LETTER A WITH BREVE AND TILDE]
65
+ '1EB6', # Ặ [LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW]
66
+ '24B6', # Ⓐ [CIRCLED LATIN CAPITAL LETTER A]
67
+ 'FF21' # A [FULLWIDTH LATIN CAPITAL LETTER A]
68
+ ] => 'A',
69
+ [
70
+
71
+ '00E0', # à [LATIN SMALL LETTER A WITH GRAVE]
72
+ '00E1', # á [LATIN SMALL LETTER A WITH ACUTE]
73
+ '00E2', # â [LATIN SMALL LETTER A WITH CIRCUMFLEX]
74
+ '00E3', # ã [LATIN SMALL LETTER A WITH TILDE]
75
+ '00E4', # ä [LATIN SMALL LETTER A WITH DIAERESIS]
76
+ '00E5', # å [LATIN SMALL LETTER A WITH RING ABOVE]
77
+ '0101', # ā [LATIN SMALL LETTER A WITH MACRON]
78
+ '0103', # ă [LATIN SMALL LETTER A WITH BREVE]
79
+ '0105', # ą [LATIN SMALL LETTER A WITH OGONEK]
80
+ '01CE', # ǎ [LATIN SMALL LETTER A WITH CARON]
81
+ '01DF', # ǟ [LATIN SMALL LETTER A WITH DIAERESIS AND MACRON]
82
+ '01E1', # ǡ [LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON]
83
+ '01FB', # ǻ [LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE]
84
+ '0201', # ȁ [LATIN SMALL LETTER A WITH DOUBLE GRAVE]
85
+ '0203', # ȃ [LATIN SMALL LETTER A WITH INVERTED BREVE]
86
+ '0227', # ȧ [LATIN SMALL LETTER A WITH DOT ABOVE]
87
+ '0250', # ɐ [LATIN SMALL LETTER TURNED A]
88
+ '0259', # ə [LATIN SMALL LETTER SCHWA]
89
+ '025A', # ɚ [LATIN SMALL LETTER SCHWA WITH HOOK]
90
+ '1D8F', # ᶏ [LATIN SMALL LETTER A WITH RETROFLEX HOOK]
91
+ '1D95', # ᶕ [LATIN SMALL LETTER SCHWA WITH RETROFLEX HOOK]
92
+ '1E01', # ạ [LATIN SMALL LETTER A WITH RING BELOW]
93
+ '1E9A', # ả [LATIN SMALL LETTER A WITH RIGHT HALF RING]
94
+ '1EA1', # ạ [LATIN SMALL LETTER A WITH DOT BELOW]
95
+ '1EA3', # ả [LATIN SMALL LETTER A WITH HOOK ABOVE]
96
+ '1EA5', # ấ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE]
97
+ '1EA7', # ầ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE]
98
+ '1EA9', # ẩ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE]
99
+ '1EAB', # ẫ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE]
100
+ '1EAD', # ậ [LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW]
101
+ '1EAF', # ắ [LATIN SMALL LETTER A WITH BREVE AND ACUTE]
102
+ '1EB1', # ằ [LATIN SMALL LETTER A WITH BREVE AND GRAVE]
103
+ '1EB3', # ẳ [LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE]
104
+ '1EB5', # ẵ [LATIN SMALL LETTER A WITH BREVE AND TILDE]
105
+ '1EB7', # ặ [LATIN SMALL LETTER A WITH BREVE AND DOT BELOW]
106
+ '2090', # ₐ [LATIN SUBSCRIPT SMALL LETTER A]
107
+ '2094', # ₔ [LATIN SUBSCRIPT SMALL LETTER SCHWA]
108
+ '24D0', # ⓐ [CIRCLED LATIN SMALL LETTER A]
109
+ '2C65', # ⱥ [LATIN SMALL LETTER A WITH STROKE]
110
+ '2C6F', # Ɐ [LATIN CAPITAL LETTER TURNED A]
111
+ 'FF41' # a [FULLWIDTH LATIN SMALL LETTER A]
112
+ ] => 'a',
113
+ [
114
+
115
+ 'A732' # Ꜳ [LATIN CAPITAL LETTER AA]
116
+ ] => 'A',
117
+ [
118
+ ] => 'A',
119
+ [
120
+
121
+ '00C6', # Æ [LATIN CAPITAL LETTER AE]
122
+ '01E2', # Ǣ [LATIN CAPITAL LETTER AE WITH MACRON]
123
+ '01FC', # Ǽ [LATIN CAPITAL LETTER AE WITH ACUTE]
124
+ '1D01' # ᴁ [LATIN LETTER SMALL CAPITAL AE]
125
+ ] => 'AE',
126
+ [
127
+
128
+ 'A734' # Ꜵ [LATIN CAPITAL LETTER AO]
129
+ ] => 'AO',
130
+ [
131
+
132
+ 'A736' # Ꜷ [LATIN CAPITAL LETTER AU]
133
+ ] => 'AU',
134
+ [
135
+
136
+ 'A738', # Ꜹ [LATIN CAPITAL LETTER AV]
137
+ 'A73A' # Ꜻ [LATIN CAPITAL LETTER AV WITH HORIZONTAL BAR]
138
+ ] => 'AV',
139
+ [
140
+
141
+ 'A73C' # Ꜽ [LATIN CAPITAL LETTER AY]
142
+ ] => 'AY',
143
+ [
144
+
145
+ '249C' # ⒜ [PARENTHESIZED LATIN SMALL LETTER A]
146
+ ] => '(a)',
147
+ [
148
+
149
+ 'A733' # ꜳ [LATIN SMALL LETTER AA]
150
+ ] => 'aa',
151
+ [
152
+
153
+ '00E6', # æ [LATIN SMALL LETTER AE]
154
+ '01E3', # ǣ [LATIN SMALL LETTER AE WITH MACRON]
155
+ '01FD', # ǽ [LATIN SMALL LETTER AE WITH ACUTE]
156
+ '1D02' # ᴂ [LATIN SMALL LETTER TURNED AE]
157
+ ] => 'ae',
158
+ [
159
+
160
+ 'A735' # ꜵ [LATIN SMALL LETTER AO]
161
+ ] => 'ao',
162
+ [
163
+
164
+ 'A737' # ꜷ [LATIN SMALL LETTER AU]
165
+ ] => 'au',
166
+ [
167
+
168
+ 'A739', # ꜹ [LATIN SMALL LETTER AV]
169
+ 'A73B' # ꜻ [LATIN SMALL LETTER AV WITH HORIZONTAL BAR]
170
+ ] => 'av',
171
+ [
172
+
173
+ 'A73D' # ꜽ [LATIN SMALL LETTER AY]
174
+ ] => 'ay',
175
+ [
176
+
177
+ '0181', # Ɓ [LATIN CAPITAL LETTER B WITH HOOK]
178
+ '0182', # Ƃ [LATIN CAPITAL LETTER B WITH TOPBAR]
179
+ '0243', # Ƀ [LATIN CAPITAL LETTER B WITH STROKE]
180
+ '0299', # ʙ [LATIN LETTER SMALL CAPITAL B]
181
+ '1D03', # ᴃ [LATIN LETTER SMALL CAPITAL BARRED B]
182
+ '1E02', # Ḃ [LATIN CAPITAL LETTER B WITH DOT ABOVE]
183
+ '1E04', # Ḅ [LATIN CAPITAL LETTER B WITH DOT BELOW]
184
+ '1E06', # Ḇ [LATIN CAPITAL LETTER B WITH LINE BELOW]
185
+ '24B7', # Ⓑ [CIRCLED LATIN CAPITAL LETTER B]
186
+ 'FF22' # B [FULLWIDTH LATIN CAPITAL LETTER B]
187
+ ] => 'B',
188
+ [
189
+
190
+ '0180', # ƀ [LATIN SMALL LETTER B WITH STROKE]
191
+ '0183', # ƃ [LATIN SMALL LETTER B WITH TOPBAR]
192
+ '0253', # ɓ [LATIN SMALL LETTER B WITH HOOK]
193
+ '1D6C', # ᵬ [LATIN SMALL LETTER B WITH MIDDLE TILDE]
194
+ '1D80', # ᶀ [LATIN SMALL LETTER B WITH PALATAL HOOK]
195
+ '1E03', # ḃ [LATIN SMALL LETTER B WITH DOT ABOVE]
196
+ '1E05', # ḅ [LATIN SMALL LETTER B WITH DOT BELOW]
197
+ '1E07', # ḇ [LATIN SMALL LETTER B WITH LINE BELOW]
198
+ '24D1', # ⓑ [CIRCLED LATIN SMALL LETTER B]
199
+ 'FF42' # b [FULLWIDTH LATIN SMALL LETTER B]
200
+ ] => 'b',
201
+ [
202
+
203
+ '249D' # ⒝ [PARENTHESIZED LATIN SMALL LETTER B]
204
+ ] => '(b)',
205
+ [
206
+
207
+ '00C7', # Ç [LATIN CAPITAL LETTER C WITH CEDILLA]
208
+ '0106', # Ć [LATIN CAPITAL LETTER C WITH ACUTE]
209
+ '0108', # Ĉ [LATIN CAPITAL LETTER C WITH CIRCUMFLEX]
210
+ '010A', # Ċ [LATIN CAPITAL LETTER C WITH DOT ABOVE]
211
+ '010C', # Č [LATIN CAPITAL LETTER C WITH CARON]
212
+ '0187', # Ƈ [LATIN CAPITAL LETTER C WITH HOOK]
213
+ '023B', # Ȼ [LATIN CAPITAL LETTER C WITH STROKE]
214
+ '0297', # ʗ [LATIN LETTER STRETCHED C]
215
+ '1D04', # ᴄ [LATIN LETTER SMALL CAPITAL C]
216
+ '1E08', # Ḉ [LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE]
217
+ '24B8', # Ⓒ [CIRCLED LATIN CAPITAL LETTER C]
218
+ 'FF23' # C [FULLWIDTH LATIN CAPITAL LETTER C]
219
+ ] => 'C',
220
+ [
221
+
222
+ '00E7', # ç [LATIN SMALL LETTER C WITH CEDILLA]
223
+ '0107', # ć [LATIN SMALL LETTER C WITH ACUTE]
224
+ '0109', # ĉ [LATIN SMALL LETTER C WITH CIRCUMFLEX]
225
+ '010B', # ċ [LATIN SMALL LETTER C WITH DOT ABOVE]
226
+ '010D', # č [LATIN SMALL LETTER C WITH CARON]
227
+ '0188', # ƈ [LATIN SMALL LETTER C WITH HOOK]
228
+ '023C', # ȼ [LATIN SMALL LETTER C WITH STROKE]
229
+ '0255', # ɕ [LATIN SMALL LETTER C WITH CURL]
230
+ '1E09', # ḉ [LATIN SMALL LETTER C WITH CEDILLA AND ACUTE]
231
+ '2184', # ↄ [LATIN SMALL LETTER REVERSED C]
232
+ '24D2', # ⓒ [CIRCLED LATIN SMALL LETTER C]
233
+ 'A73E', # Ꜿ [LATIN CAPITAL LETTER REVERSED C WITH DOT]
234
+ 'A73F', # ꜿ [LATIN SMALL LETTER REVERSED C WITH DOT]
235
+ 'FF43' # c [FULLWIDTH LATIN SMALL LETTER C]
236
+ ] => 'c',
237
+ [
238
+
239
+ '249E' # ⒞ [PARENTHESIZED LATIN SMALL LETTER C]
240
+ ] => '(c)',
241
+ [
242
+
243
+ '00D0', # Ð [LATIN CAPITAL LETTER ETH]
244
+ '010E', # Ď [LATIN CAPITAL LETTER D WITH CARON]
245
+ '0110', # Đ [LATIN CAPITAL LETTER D WITH STROKE]
246
+ '0189', # Ɖ [LATIN CAPITAL LETTER AFRICAN D]
247
+ '018A', # Ɗ [LATIN CAPITAL LETTER D WITH HOOK]
248
+ '018B', # Ƌ [LATIN CAPITAL LETTER D WITH TOPBAR]
249
+ '1D05', # ᴅ [LATIN LETTER SMALL CAPITAL D]
250
+ '1D06', # ᴆ [LATIN LETTER SMALL CAPITAL ETH]
251
+ '1E0A', # Ḋ [LATIN CAPITAL LETTER D WITH DOT ABOVE]
252
+ '1E0C', # Ḍ [LATIN CAPITAL LETTER D WITH DOT BELOW]
253
+ '1E0E', # Ḏ [LATIN CAPITAL LETTER D WITH LINE BELOW]
254
+ '1E10', # Ḑ [LATIN CAPITAL LETTER D WITH CEDILLA]
255
+ '1E12', # Ḓ [LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW]
256
+ '24B9', # Ⓓ [CIRCLED LATIN CAPITAL LETTER D]
257
+ 'A779', # Ꝺ [LATIN CAPITAL LETTER INSULAR D]
258
+ 'FF24' # D [FULLWIDTH LATIN CAPITAL LETTER D]
259
+ ] => 'D',
260
+ [
261
+
262
+ '00F0', # ð [LATIN SMALL LETTER ETH]
263
+ '010F', # ď [LATIN SMALL LETTER D WITH CARON]
264
+ '0111', # đ [LATIN SMALL LETTER D WITH STROKE]
265
+ '018C', # ƌ [LATIN SMALL LETTER D WITH TOPBAR]
266
+ '0221', # ȡ [LATIN SMALL LETTER D WITH CURL]
267
+ '0256', # ɖ [LATIN SMALL LETTER D WITH TAIL]
268
+ '0257', # ɗ [LATIN SMALL LETTER D WITH HOOK]
269
+ '1D6D', # ᵭ [LATIN SMALL LETTER D WITH MIDDLE TILDE]
270
+ '1D81', # ᶁ [LATIN SMALL LETTER D WITH PALATAL HOOK]
271
+ '1D91', # ᶑ [LATIN SMALL LETTER D WITH HOOK AND TAIL]
272
+ '1E0B', # ḋ [LATIN SMALL LETTER D WITH DOT ABOVE]
273
+ '1E0D', # ḍ [LATIN SMALL LETTER D WITH DOT BELOW]
274
+ '1E0F', # ḏ [LATIN SMALL LETTER D WITH LINE BELOW]
275
+ '1E11', # ḑ [LATIN SMALL LETTER D WITH CEDILLA]
276
+ '1E13', # ḓ [LATIN SMALL LETTER D WITH CIRCUMFLEX BELOW]
277
+ '24D3', # ⓓ [CIRCLED LATIN SMALL LETTER D]
278
+ 'A77A', # ꝺ [LATIN SMALL LETTER INSULAR D]
279
+ 'FF44' # d [FULLWIDTH LATIN SMALL LETTER D]
280
+ ] => 'd',
281
+ [
282
+
283
+ '01C4', # DŽ [LATIN CAPITAL LETTER DZ WITH CARON]
284
+ '01F1' # DZ [LATIN CAPITAL LETTER DZ]
285
+ ] => 'DZ',
286
+ [
287
+
288
+ '01C5', # Dž [LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON]
289
+ '01F2' # Dz [LATIN CAPITAL LETTER D WITH SMALL LETTER Z]
290
+ ] => 'Dz',
291
+ [
292
+
293
+ '249F' # ⒟ [PARENTHESIZED LATIN SMALL LETTER D]
294
+ ] => '(d)',
295
+ [
296
+
297
+ '0238' # ȸ [LATIN SMALL LETTER DB DIGRAPH]
298
+ ] => 'db',
299
+ [
300
+
301
+ '01C6', # dž [LATIN SMALL LETTER DZ WITH CARON]
302
+ '01F3', # dz [LATIN SMALL LETTER DZ]
303
+ '02A3', # ʣ [LATIN SMALL LETTER DZ DIGRAPH]
304
+ '02A5' # ʥ [LATIN SMALL LETTER DZ DIGRAPH WITH CURL]
305
+ ] => 'dz',
306
+ [
307
+
308
+ '00C8', # È [LATIN CAPITAL LETTER E WITH GRAVE]
309
+ '00C9', # É [LATIN CAPITAL LETTER E WITH ACUTE]
310
+ '00CA', # Ê [LATIN CAPITAL LETTER E WITH CIRCUMFLEX]
311
+ '00CB', # Ë [LATIN CAPITAL LETTER E WITH DIAERESIS]
312
+ '0112', # Ē [LATIN CAPITAL LETTER E WITH MACRON]
313
+ '0114', # Ĕ [LATIN CAPITAL LETTER E WITH BREVE]
314
+ '0116', # Ė [LATIN CAPITAL LETTER E WITH DOT ABOVE]
315
+ '0118', # Ę [LATIN CAPITAL LETTER E WITH OGONEK]
316
+ '011A', # Ě [LATIN CAPITAL LETTER E WITH CARON]
317
+ '018E', # Ǝ [LATIN CAPITAL LETTER REVERSED E]
318
+ '0190', # Ɛ [LATIN CAPITAL LETTER OPEN E]
319
+ '0204', # Ȅ [LATIN CAPITAL LETTER E WITH DOUBLE GRAVE]
320
+ '0206', # Ȇ [LATIN CAPITAL LETTER E WITH INVERTED BREVE]
321
+ '0228', # Ȩ [LATIN CAPITAL LETTER E WITH CEDILLA]
322
+ '0246', # Ɇ [LATIN CAPITAL LETTER E WITH STROKE]
323
+ '1D07', # ᴇ [LATIN LETTER SMALL CAPITAL E]
324
+ '1E14', # Ḕ [LATIN CAPITAL LETTER E WITH MACRON AND GRAVE]
325
+ '1E16', # Ḗ [LATIN CAPITAL LETTER E WITH MACRON AND ACUTE]
326
+ '1E18', # Ḙ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW]
327
+ '1E1A', # Ḛ [LATIN CAPITAL LETTER E WITH TILDE BELOW]
328
+ '1E1C', # Ḝ [LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE]
329
+ '1EB8', # Ẹ [LATIN CAPITAL LETTER E WITH DOT BELOW]
330
+ '1EBA', # Ẻ [LATIN CAPITAL LETTER E WITH HOOK ABOVE]
331
+ '1EBC', # Ẽ [LATIN CAPITAL LETTER E WITH TILDE]
332
+ '1EBE', # Ế [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE]
333
+ '1EC0', # Ề [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE]
334
+ '1EC2', # Ể [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE]
335
+ '1EC4', # Ễ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE]
336
+ '1EC6', # Ệ [LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW]
337
+ '24BA', # Ⓔ [CIRCLED LATIN CAPITAL LETTER E]
338
+ '2C7B', # ⱻ [LATIN LETTER SMALL CAPITAL TURNED E]
339
+ 'FF25' # E [FULLWIDTH LATIN CAPITAL LETTER E]
340
+ ] => 'E',
341
+ [
342
+
343
+ '00E8', # è [LATIN SMALL LETTER E WITH GRAVE]
344
+ '00E9', # é [LATIN SMALL LETTER E WITH ACUTE]
345
+ '00EA', # ê [LATIN SMALL LETTER E WITH CIRCUMFLEX]
346
+ '00EB', # ë [LATIN SMALL LETTER E WITH DIAERESIS]
347
+ '0113', # ē [LATIN SMALL LETTER E WITH MACRON]
348
+ '0115', # ĕ [LATIN SMALL LETTER E WITH BREVE]
349
+ '0117', # ė [LATIN SMALL LETTER E WITH DOT ABOVE]
350
+ '0119', # ę [LATIN SMALL LETTER E WITH OGONEK]
351
+ '011B', # ě [LATIN SMALL LETTER E WITH CARON]
352
+ '01DD', # ǝ [LATIN SMALL LETTER TURNED E]
353
+ '0205', # ȅ [LATIN SMALL LETTER E WITH DOUBLE GRAVE]
354
+ '0207', # ȇ [LATIN SMALL LETTER E WITH INVERTED BREVE]
355
+ '0229', # ȩ [LATIN SMALL LETTER E WITH CEDILLA]
356
+ '0247', # ɇ [LATIN SMALL LETTER E WITH STROKE]
357
+ '0258', # ɘ [LATIN SMALL LETTER REVERSED E]
358
+ '025B', # ɛ [LATIN SMALL LETTER OPEN E]
359
+ '025C', # ɜ [LATIN SMALL LETTER REVERSED OPEN E]
360
+ '025D', # ɝ [LATIN SMALL LETTER REVERSED OPEN E WITH HOOK]
361
+ '025E', # ɞ [LATIN SMALL LETTER CLOSED REVERSED OPEN E]
362
+ '029A', # ʚ [LATIN SMALL LETTER CLOSED OPEN E]
363
+ '1D08', # ᴈ [LATIN SMALL LETTER TURNED OPEN E]
364
+ '1D92', # ᶒ [LATIN SMALL LETTER E WITH RETROFLEX HOOK]
365
+ '1D93', # ᶓ [LATIN SMALL LETTER OPEN E WITH RETROFLEX HOOK]
366
+ '1D94', # ᶔ [LATIN SMALL LETTER REVERSED OPEN E WITH RETROFLEX HOOK]
367
+ '1E15', # ḕ [LATIN SMALL LETTER E WITH MACRON AND GRAVE]
368
+ '1E17', # ḗ [LATIN SMALL LETTER E WITH MACRON AND ACUTE]
369
+ '1E19', # ḙ [LATIN SMALL LETTER E WITH CIRCUMFLEX BELOW]
370
+ '1E1B', # ḛ [LATIN SMALL LETTER E WITH TILDE BELOW]
371
+ '1E1D', # ḝ [LATIN SMALL LETTER E WITH CEDILLA AND BREVE]
372
+ '1EB9', # ẹ [LATIN SMALL LETTER E WITH DOT BELOW]
373
+ '1EBB', # ẻ [LATIN SMALL LETTER E WITH HOOK ABOVE]
374
+ '1EBD', # ẽ [LATIN SMALL LETTER E WITH TILDE]
375
+ '1EBF', # ế [LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE]
376
+ '1EC1', # ề [LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE]
377
+ '1EC3', # ể [LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE]
378
+ '1EC5', # ễ [LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE]
379
+ '1EC7', # ệ [LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW]
380
+ '2091', # ₑ [LATIN SUBSCRIPT SMALL LETTER E]
381
+ '24D4', # ⓔ [CIRCLED LATIN SMALL LETTER E]
382
+ '2C78', # ⱸ [LATIN SMALL LETTER E WITH NOTCH]
383
+ 'FF45' # e [FULLWIDTH LATIN SMALL LETTER E]
384
+ ] => 'e',
385
+ [
386
+
387
+ '24A0' # ⒠ [PARENTHESIZED LATIN SMALL LETTER E]
388
+ ] => '(e)',
389
+ [
390
+
391
+ '0191', # Ƒ [LATIN CAPITAL LETTER F WITH HOOK]
392
+ '1E1E', # Ḟ [LATIN CAPITAL LETTER F WITH DOT ABOVE]
393
+ '24BB', # Ⓕ [CIRCLED LATIN CAPITAL LETTER F]
394
+ 'A730', # ꜰ [LATIN LETTER SMALL CAPITAL F]
395
+ 'A77B', # Ꝼ [LATIN CAPITAL LETTER INSULAR F]
396
+ 'A7FB', # ꟻ [LATIN EPIGRAPHIC LETTER REVERSED F]
397
+ 'FF26' # F [FULLWIDTH LATIN CAPITAL LETTER F]
398
+ ] => 'F',
399
+ [
400
+
401
+ '0192', # ƒ [LATIN SMALL LETTER F WITH HOOK]
402
+ '1D6E', # ᵮ [LATIN SMALL LETTER F WITH MIDDLE TILDE]
403
+ '1D82', # ᶂ [LATIN SMALL LETTER F WITH PALATAL HOOK]
404
+ '1E1F', # ḟ [LATIN SMALL LETTER F WITH DOT ABOVE]
405
+ '1E9B', # ẛ [LATIN SMALL LETTER LONG S WITH DOT ABOVE]
406
+ '24D5', # ⓕ [CIRCLED LATIN SMALL LETTER F]
407
+ 'A77C', # ꝼ [LATIN SMALL LETTER INSULAR F]
408
+ 'FF46' # f [FULLWIDTH LATIN SMALL LETTER F]
409
+ ] => 'f',
410
+ [
411
+
412
+ '24A1' # ⒡ [PARENTHESIZED LATIN SMALL LETTER F]
413
+ ] => '(f)',
414
+ [
415
+
416
+ 'FB00' # ff [LATIN SMALL LIGATURE FF]
417
+ ] => 'ff',
418
+ [
419
+
420
+ 'FB03' # ffi [LATIN SMALL LIGATURE FFI]
421
+ ] => 'ffi',
422
+ [
423
+
424
+ 'FB04' # ffl [LATIN SMALL LIGATURE FFL]
425
+ ] => 'ffl',
426
+ [
427
+
428
+ 'FB01' # fi [LATIN SMALL LIGATURE FI]
429
+ ] => 'fi',
430
+ [
431
+
432
+ 'FB02' # fl [LATIN SMALL LIGATURE FL]
433
+ ] => 'fl',
434
+ [
435
+
436
+ '011C', # Ĝ [LATIN CAPITAL LETTER G WITH CIRCUMFLEX]
437
+ '011E', # Ğ [LATIN CAPITAL LETTER G WITH BREVE]
438
+ '0120', # Ġ [LATIN CAPITAL LETTER G WITH DOT ABOVE]
439
+ '0122', # Ģ [LATIN CAPITAL LETTER G WITH CEDILLA]
440
+ '0193', # Ɠ [LATIN CAPITAL LETTER G WITH HOOK]
441
+ '01E4', # Ǥ [LATIN CAPITAL LETTER G WITH STROKE]
442
+ '01E5', # ǥ [LATIN SMALL LETTER G WITH STROKE]
443
+ '01E6', # Ǧ [LATIN CAPITAL LETTER G WITH CARON]
444
+ '01E7', # ǧ [LATIN SMALL LETTER G WITH CARON]
445
+ '01F4', # Ǵ [LATIN CAPITAL LETTER G WITH ACUTE]
446
+ '0262', # ɢ [LATIN LETTER SMALL CAPITAL G]
447
+ '029B', # ʛ [LATIN LETTER SMALL CAPITAL G WITH HOOK]
448
+ '1E20', # Ḡ [LATIN CAPITAL LETTER G WITH MACRON]
449
+ '24BC', # Ⓖ [CIRCLED LATIN CAPITAL LETTER G]
450
+ 'A77D', # Ᵹ [LATIN CAPITAL LETTER INSULAR G]
451
+ 'A77E', # Ꝿ [LATIN CAPITAL LETTER TURNED INSULAR G]
452
+ 'FF27' # G [FULLWIDTH LATIN CAPITAL LETTER G]
453
+ ] => 'G',
454
+ [
455
+
456
+ '011D', # ĝ [LATIN SMALL LETTER G WITH CIRCUMFLEX]
457
+ '011F', # ğ [LATIN SMALL LETTER G WITH BREVE]
458
+ '0121', # ġ [LATIN SMALL LETTER G WITH DOT ABOVE]
459
+ '0123', # ģ [LATIN SMALL LETTER G WITH CEDILLA]
460
+ '01F5', # ǵ [LATIN SMALL LETTER G WITH ACUTE]
461
+ '0260', # ɠ [LATIN SMALL LETTER G WITH HOOK]
462
+ '0261', # ɡ [LATIN SMALL LETTER SCRIPT G]
463
+ '1D77', # ᵷ [LATIN SMALL LETTER TURNED G]
464
+ '1D79', # ᵹ [LATIN SMALL LETTER INSULAR G]
465
+ '1D83', # ᶃ [LATIN SMALL LETTER G WITH PALATAL HOOK]
466
+ '1E21', # ḡ [LATIN SMALL LETTER G WITH MACRON]
467
+ '24D6', # ⓖ [CIRCLED LATIN SMALL LETTER G]
468
+ 'A77F', # ꝿ [LATIN SMALL LETTER TURNED INSULAR G]
469
+ 'FF47' # g [FULLWIDTH LATIN SMALL LETTER G]
470
+ ] => 'g',
471
+ [
472
+
473
+ '24A2' # ⒢ [PARENTHESIZED LATIN SMALL LETTER G]
474
+ ] => '(g)',
475
+ [
476
+
477
+ '0124', # Ĥ [LATIN CAPITAL LETTER H WITH CIRCUMFLEX]
478
+ '0126', # Ħ [LATIN CAPITAL LETTER H WITH STROKE]
479
+ '021E', # Ȟ [LATIN CAPITAL LETTER H WITH CARON]
480
+ '029C', # ʜ [LATIN LETTER SMALL CAPITAL H]
481
+ '1E22', # Ḣ [LATIN CAPITAL LETTER H WITH DOT ABOVE]
482
+ '1E24', # Ḥ [LATIN CAPITAL LETTER H WITH DOT BELOW]
483
+ '1E26', # Ḧ [LATIN CAPITAL LETTER H WITH DIAERESIS]
484
+ '1E28', # Ḩ [LATIN CAPITAL LETTER H WITH CEDILLA]
485
+ '1E2A', # Ḫ [LATIN CAPITAL LETTER H WITH BREVE BELOW]
486
+ '24BD', # Ⓗ [CIRCLED LATIN CAPITAL LETTER H]
487
+ '2C67', # Ⱨ [LATIN CAPITAL LETTER H WITH DESCENDER]
488
+ '2C75', # Ⱶ [LATIN CAPITAL LETTER HALF H]
489
+ 'FF28' # H [FULLWIDTH LATIN CAPITAL LETTER H]
490
+ ] => 'H',
491
+ [
492
+
493
+ '0125', # ĥ [LATIN SMALL LETTER H WITH CIRCUMFLEX]
494
+ '0127', # ħ [LATIN SMALL LETTER H WITH STROKE]
495
+ '021F', # ȟ [LATIN SMALL LETTER H WITH CARON]
496
+ '0265', # ɥ [LATIN SMALL LETTER TURNED H]
497
+ '0266', # ɦ [LATIN SMALL LETTER H WITH HOOK]
498
+ '02AE', # ʮ [LATIN SMALL LETTER TURNED H WITH FISHHOOK]
499
+ '02AF', # ʯ [LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL]
500
+ '1E23', # ḣ [LATIN SMALL LETTER H WITH DOT ABOVE]
501
+ '1E25', # ḥ [LATIN SMALL LETTER H WITH DOT BELOW]
502
+ '1E27', # ḧ [LATIN SMALL LETTER H WITH DIAERESIS]
503
+ '1E29', # ḩ [LATIN SMALL LETTER H WITH CEDILLA]
504
+ '1E2B', # ḫ [LATIN SMALL LETTER H WITH BREVE BELOW]
505
+ '1E96', # ẖ [LATIN SMALL LETTER H WITH LINE BELOW]
506
+ '24D7', # ⓗ [CIRCLED LATIN SMALL LETTER H]
507
+ '2C68', # ⱨ [LATIN SMALL LETTER H WITH DESCENDER]
508
+ '2C76', # ⱶ [LATIN SMALL LETTER HALF H]
509
+ 'FF48' # h [FULLWIDTH LATIN SMALL LETTER H]
510
+ ] => 'h',
511
+ [
512
+
513
+ '01F6' # Ƕ http://en.wikipedia.org/wiki/Hwair [LATIN CAPITAL LETTER HWAIR]
514
+ ] => 'HV',
515
+ [
516
+
517
+ '24A3' # ⒣ [PARENTHESIZED LATIN SMALL LETTER H]
518
+ ] => '(h)',
519
+ [
520
+
521
+ '0195' # ƕ [LATIN SMALL LETTER HV]
522
+ ] => 'hv',
523
+ [
524
+
525
+ '00CC', # Ì [LATIN CAPITAL LETTER I WITH GRAVE]
526
+ '00CD', # Í [LATIN CAPITAL LETTER I WITH ACUTE]
527
+ '00CE', # Î [LATIN CAPITAL LETTER I WITH CIRCUMFLEX]
528
+ '00CF', # Ï [LATIN CAPITAL LETTER I WITH DIAERESIS]
529
+ '0128', # Ĩ [LATIN CAPITAL LETTER I WITH TILDE]
530
+ '012A', # Ī [LATIN CAPITAL LETTER I WITH MACRON]
531
+ '012C', # Ĭ [LATIN CAPITAL LETTER I WITH BREVE]
532
+ '012E', # Į [LATIN CAPITAL LETTER I WITH OGONEK]
533
+ '0130', # İ [LATIN CAPITAL LETTER I WITH DOT ABOVE]
534
+ '0196', # Ɩ [LATIN CAPITAL LETTER IOTA]
535
+ '0197', # Ɨ [LATIN CAPITAL LETTER I WITH STROKE]
536
+ '01CF', # Ǐ [LATIN CAPITAL LETTER I WITH CARON]
537
+ '0208', # Ȉ [LATIN CAPITAL LETTER I WITH DOUBLE GRAVE]
538
+ '020A', # Ȋ [LATIN CAPITAL LETTER I WITH INVERTED BREVE]
539
+ '026A', # ɪ [LATIN LETTER SMALL CAPITAL I]
540
+ '1D7B', # ᵻ [LATIN SMALL CAPITAL LETTER I WITH STROKE]
541
+ '1E2C', # Ḭ [LATIN CAPITAL LETTER I WITH TILDE BELOW]
542
+ '1E2E', # Ḯ [LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE]
543
+ '1EC8', # Ỉ [LATIN CAPITAL LETTER I WITH HOOK ABOVE]
544
+ '1ECA', # Ị [LATIN CAPITAL LETTER I WITH DOT BELOW]
545
+ '24BE', # Ⓘ [CIRCLED LATIN CAPITAL LETTER I]
546
+ 'A7FE', # ꟾ [LATIN EPIGRAPHIC LETTER I LONGA]
547
+ 'FF29' # I [FULLWIDTH LATIN CAPITAL LETTER I]
548
+ ] => 'I',
549
+ [
550
+
551
+ '00EC', # ì [LATIN SMALL LETTER I WITH GRAVE]
552
+ '00ED', # í [LATIN SMALL LETTER I WITH ACUTE]
553
+ '00EE', # î [LATIN SMALL LETTER I WITH CIRCUMFLEX]
554
+ '00EF', # ï [LATIN SMALL LETTER I WITH DIAERESIS]
555
+ '0129', # ĩ [LATIN SMALL LETTER I WITH TILDE]
556
+ '012B', # ī [LATIN SMALL LETTER I WITH MACRON]
557
+ '012D', # ĭ [LATIN SMALL LETTER I WITH BREVE]
558
+ '012F', # į [LATIN SMALL LETTER I WITH OGONEK]
559
+ '0131', # ı [LATIN SMALL LETTER DOTLESS I]
560
+ '01D0', # ǐ [LATIN SMALL LETTER I WITH CARON]
561
+ '0209', # ȉ [LATIN SMALL LETTER I WITH DOUBLE GRAVE]
562
+ '020B', # ȋ [LATIN SMALL LETTER I WITH INVERTED BREVE]
563
+ '0268', # ɨ [LATIN SMALL LETTER I WITH STROKE]
564
+ '1D09', # ᴉ [LATIN SMALL LETTER TURNED I]
565
+ '1D62', # ᵢ [LATIN SUBSCRIPT SMALL LETTER I]
566
+ '1D7C', # ᵼ [LATIN SMALL LETTER IOTA WITH STROKE]
567
+ '1D96', # ᶖ [LATIN SMALL LETTER I WITH RETROFLEX HOOK]
568
+ '1E2D', # ḭ [LATIN SMALL LETTER I WITH TILDE BELOW]
569
+ '1E2F', # ḯ [LATIN SMALL LETTER I WITH DIAERESIS AND ACUTE]
570
+ '1EC9', # ỉ [LATIN SMALL LETTER I WITH HOOK ABOVE]
571
+ '1ECB', # ị [LATIN SMALL LETTER I WITH DOT BELOW]
572
+ '2071', # ⁱ [SUPERSCRIPT LATIN SMALL LETTER I]
573
+ '24D8', # ⓘ [CIRCLED LATIN SMALL LETTER I]
574
+ 'FF49' # i [FULLWIDTH LATIN SMALL LETTER I]
575
+ ] => 'i',
576
+ [
577
+
578
+ '0132' # IJ [LATIN CAPITAL LIGATURE IJ]
579
+ ] => 'IJ',
580
+ [
581
+
582
+ '24A4' # ⒤ [PARENTHESIZED LATIN SMALL LETTER I]
583
+ ] => '(i)',
584
+ [
585
+
586
+ '0133' # ij [LATIN SMALL LIGATURE IJ]
587
+ ] => 'ij',
588
+ [
589
+
590
+ '0134', # Ĵ [LATIN CAPITAL LETTER J WITH CIRCUMFLEX]
591
+ '0248', # Ɉ [LATIN CAPITAL LETTER J WITH STROKE]
592
+ '1D0A', # ᴊ [LATIN LETTER SMALL CAPITAL J]
593
+ '24BF', # Ⓙ [CIRCLED LATIN CAPITAL LETTER J]
594
+ 'FF2A' # J [FULLWIDTH LATIN CAPITAL LETTER J]
595
+ ] => 'J',
596
+ [
597
+
598
+ '0135', # ĵ [LATIN SMALL LETTER J WITH CIRCUMFLEX]
599
+ '01F0', # ǰ [LATIN SMALL LETTER J WITH CARON]
600
+ '0237', # ȷ [LATIN SMALL LETTER DOTLESS J]
601
+ '0249', # ɉ [LATIN SMALL LETTER J WITH STROKE]
602
+ '025F', # ɟ [LATIN SMALL LETTER DOTLESS J WITH STROKE]
603
+ '0284', # ʄ [LATIN SMALL LETTER DOTLESS J WITH STROKE AND HOOK]
604
+ '029D', # ʝ [LATIN SMALL LETTER J WITH CROSSED-TAIL]
605
+ '24D9', # ⓙ [CIRCLED LATIN SMALL LETTER J]
606
+ '2C7C', # ⱼ [LATIN SUBSCRIPT SMALL LETTER J]
607
+ 'FF4A' # j [FULLWIDTH LATIN SMALL LETTER J]
608
+ ] => 'j',
609
+ [
610
+
611
+ '24A5' # ⒥ [PARENTHESIZED LATIN SMALL LETTER J]
612
+ ] => '(j)',
613
+ [
614
+
615
+ '0136', # Ķ [LATIN CAPITAL LETTER K WITH CEDILLA]
616
+ '0198', # Ƙ [LATIN CAPITAL LETTER K WITH HOOK]
617
+ '01E8', # Ǩ [LATIN CAPITAL LETTER K WITH CARON]
618
+ '1D0B', # ᴋ [LATIN LETTER SMALL CAPITAL K]
619
+ '1E30', # Ḱ [LATIN CAPITAL LETTER K WITH ACUTE]
620
+ '1E32', # Ḳ [LATIN CAPITAL LETTER K WITH DOT BELOW]
621
+ '1E34', # Ḵ [LATIN CAPITAL LETTER K WITH LINE BELOW]
622
+ '24C0', # Ⓚ [CIRCLED LATIN CAPITAL LETTER K]
623
+ '2C69', # Ⱪ [LATIN CAPITAL LETTER K WITH DESCENDER]
624
+ 'A740', # Ꝁ [LATIN CAPITAL LETTER K WITH STROKE]
625
+ 'A742', # Ꝃ [LATIN CAPITAL LETTER K WITH DIAGONAL STROKE]
626
+ 'A744', # Ꝅ [LATIN CAPITAL LETTER K WITH STROKE AND DIAGONAL STROKE]
627
+ 'FF2B' # K [FULLWIDTH LATIN CAPITAL LETTER K]
628
+ ] => 'K',
629
+ [
630
+
631
+ '0137', # ķ [LATIN SMALL LETTER K WITH CEDILLA]
632
+ '0199', # ƙ [LATIN SMALL LETTER K WITH HOOK]
633
+ '01E9', # ǩ [LATIN SMALL LETTER K WITH CARON]
634
+ '029E', # ʞ [LATIN SMALL LETTER TURNED K]
635
+ '1D84', # ᶄ [LATIN SMALL LETTER K WITH PALATAL HOOK]
636
+ '1E31', # ḱ [LATIN SMALL LETTER K WITH ACUTE]
637
+ '1E33', # ḳ [LATIN SMALL LETTER K WITH DOT BELOW]
638
+ '1E35', # ḵ [LATIN SMALL LETTER K WITH LINE BELOW]
639
+ '24DA', # ⓚ [CIRCLED LATIN SMALL LETTER K]
640
+ '2C6A', # ⱪ [LATIN SMALL LETTER K WITH DESCENDER]
641
+ 'A741', # ꝁ [LATIN SMALL LETTER K WITH STROKE]
642
+ 'A743', # ꝃ [LATIN SMALL LETTER K WITH DIAGONAL STROKE]
643
+ 'A745', # ꝅ [LATIN SMALL LETTER K WITH STROKE AND DIAGONAL STROKE]
644
+ 'FF4B' # k [FULLWIDTH LATIN SMALL LETTER K]
645
+ ] => 'k',
646
+ [
647
+
648
+ '24A6' # ⒦ [PARENTHESIZED LATIN SMALL LETTER K]
649
+ ] => '(k)',
650
+ [
651
+
652
+ '0139', # Ĺ [LATIN CAPITAL LETTER L WITH ACUTE]
653
+ '013B', # Ļ [LATIN CAPITAL LETTER L WITH CEDILLA]
654
+ '013D', # Ľ [LATIN CAPITAL LETTER L WITH CARON]
655
+ '013F', # Ŀ [LATIN CAPITAL LETTER L WITH MIDDLE DOT]
656
+ '0141', # Ł [LATIN CAPITAL LETTER L WITH STROKE]
657
+ '023D', # Ƚ [LATIN CAPITAL LETTER L WITH BAR]
658
+ '029F', # ʟ [LATIN LETTER SMALL CAPITAL L]
659
+ '1D0C', # ᴌ [LATIN LETTER SMALL CAPITAL L WITH STROKE]
660
+ '1E36', # Ḷ [LATIN CAPITAL LETTER L WITH DOT BELOW]
661
+ '1E38', # Ḹ [LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON]
662
+ '1E3A', # Ḻ [LATIN CAPITAL LETTER L WITH LINE BELOW]
663
+ '1E3C', # Ḽ [LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW]
664
+ '24C1', # Ⓛ [CIRCLED LATIN CAPITAL LETTER L]
665
+ '2C60', # Ⱡ [LATIN CAPITAL LETTER L WITH DOUBLE BAR]
666
+ '2C62', # Ɫ [LATIN CAPITAL LETTER L WITH MIDDLE TILDE]
667
+ 'A746', # Ꝇ [LATIN CAPITAL LETTER BROKEN L]
668
+ 'A748', # Ꝉ [LATIN CAPITAL LETTER L WITH HIGH STROKE]
669
+ 'A780', # Ꞁ [LATIN CAPITAL LETTER TURNED L]
670
+ 'FF2C' # L [FULLWIDTH LATIN CAPITAL LETTER L]
671
+ ] => 'L',
672
+ [
673
+
674
+ '013A', # ĺ [LATIN SMALL LETTER L WITH ACUTE]
675
+ '013C', # ļ [LATIN SMALL LETTER L WITH CEDILLA]
676
+ '013E', # ľ [LATIN SMALL LETTER L WITH CARON]
677
+ '0140', # ŀ [LATIN SMALL LETTER L WITH MIDDLE DOT]
678
+ '0142', # ł [LATIN SMALL LETTER L WITH STROKE]
679
+ '019A', # ƚ [LATIN SMALL LETTER L WITH BAR]
680
+ '0234', # ȴ [LATIN SMALL LETTER L WITH CURL]
681
+ '026B', # ɫ [LATIN SMALL LETTER L WITH MIDDLE TILDE]
682
+ '026C', # ɬ [LATIN SMALL LETTER L WITH BELT]
683
+ '026D', # ɭ [LATIN SMALL LETTER L WITH RETROFLEX HOOK]
684
+ '1D85', # ᶅ [LATIN SMALL LETTER L WITH PALATAL HOOK]
685
+ '1E37', # ḷ [LATIN SMALL LETTER L WITH DOT BELOW]
686
+ '1E39', # ḹ [LATIN SMALL LETTER L WITH DOT BELOW AND MACRON]
687
+ '1E3B', # ḻ [LATIN SMALL LETTER L WITH LINE BELOW]
688
+ '1E3D', # ḽ [LATIN SMALL LETTER L WITH CIRCUMFLEX BELOW]
689
+ '24DB', # ⓛ [CIRCLED LATIN SMALL LETTER L]
690
+ '2C61', # ⱡ [LATIN SMALL LETTER L WITH DOUBLE BAR]
691
+ 'A747', # ꝇ [LATIN SMALL LETTER BROKEN L]
692
+ 'A749', # ꝉ [LATIN SMALL LETTER L WITH HIGH STROKE]
693
+ 'A781', # ꞁ [LATIN SMALL LETTER TURNED L]
694
+ 'FF4C' # l [FULLWIDTH LATIN SMALL LETTER L]
695
+ ] => 'l',
696
+ [
697
+
698
+ '01C7' # LJ [LATIN CAPITAL LETTER LJ]
699
+ ] => 'LJ',
700
+ [
701
+
702
+ '1EFA' # Ỻ [LATIN CAPITAL LETTER MIDDLE-WELSH LL]
703
+ ] => 'LL',
704
+ [
705
+
706
+ '01C8' # Lj [LATIN CAPITAL LETTER L WITH SMALL LETTER J]
707
+ ] => 'Lj',
708
+ [
709
+
710
+ '24A7' # ⒧ [PARENTHESIZED LATIN SMALL LETTER L]
711
+ ] => '(l)',
712
+ [
713
+
714
+ '01C9' # lj [LATIN SMALL LETTER LJ]
715
+ ] => 'lj',
716
+ [
717
+
718
+ '1EFB' # ỻ [LATIN SMALL LETTER MIDDLE-WELSH LL]
719
+ ] => 'll',
720
+ [
721
+
722
+ '02AA' # ʪ [LATIN SMALL LETTER LS DIGRAPH]
723
+ ] => 'ls',
724
+ [
725
+
726
+ '02AB' # ʫ [LATIN SMALL LETTER LZ DIGRAPH]
727
+ ] => 'lz',
728
+ [
729
+
730
+ '019C', # Ɯ [LATIN CAPITAL LETTER TURNED M]
731
+ '1D0D', # ᴍ [LATIN LETTER SMALL CAPITAL M]
732
+ '1E3E', # Ḿ [LATIN CAPITAL LETTER M WITH ACUTE]
733
+ '1E40', # Ṁ [LATIN CAPITAL LETTER M WITH DOT ABOVE]
734
+ '1E42', # Ṃ [LATIN CAPITAL LETTER M WITH DOT BELOW]
735
+ '24C2', # Ⓜ [CIRCLED LATIN CAPITAL LETTER M]
736
+ '2C6E', # Ɱ [LATIN CAPITAL LETTER M WITH HOOK]
737
+ 'A7FD', # ꟽ [LATIN EPIGRAPHIC LETTER INVERTED M]
738
+ 'A7FF', # ꟿ [LATIN EPIGRAPHIC LETTER ARCHAIC M]
739
+ 'FF2D' # M [FULLWIDTH LATIN CAPITAL LETTER M]
740
+ ] => 'M',
741
+ [
742
+
743
+ '026F', # ɯ [LATIN SMALL LETTER TURNED M]
744
+ '0270', # ɰ [LATIN SMALL LETTER TURNED M WITH LONG LEG]
745
+ '0271', # ɱ [LATIN SMALL LETTER M WITH HOOK]
746
+ '1D6F', # ᵯ [LATIN SMALL LETTER M WITH MIDDLE TILDE]
747
+ '1D86', # ᶆ [LATIN SMALL LETTER M WITH PALATAL HOOK]
748
+ '1E3F', # ḿ [LATIN SMALL LETTER M WITH ACUTE]
749
+ '1E41', # ṁ [LATIN SMALL LETTER M WITH DOT ABOVE]
750
+ '1E43', # ṃ [LATIN SMALL LETTER M WITH DOT BELOW]
751
+ '24DC', # ⓜ [CIRCLED LATIN SMALL LETTER M]
752
+ 'FF4D' # m [FULLWIDTH LATIN SMALL LETTER M]
753
+ ] => 'm',
754
+ [
755
+
756
+ '24A8' # ⒨ [PARENTHESIZED LATIN SMALL LETTER M]
757
+ ] => '(m)',
758
+ [
759
+
760
+ '00D1', # Ñ [LATIN CAPITAL LETTER N WITH TILDE]
761
+ '0143', # Ń [LATIN CAPITAL LETTER N WITH ACUTE]
762
+ '0145', # Ņ [LATIN CAPITAL LETTER N WITH CEDILLA]
763
+ '0147', # Ň [LATIN CAPITAL LETTER N WITH CARON]
764
+ '014A', # Ŋ http://en.wikipedia.org/wiki/Eng_(letter) [LATIN CAPITAL LETTER ENG]
765
+ '019D', # Ɲ [LATIN CAPITAL LETTER N WITH LEFT HOOK]
766
+ '01F8', # Ǹ [LATIN CAPITAL LETTER N WITH GRAVE]
767
+ '0220', # Ƞ [LATIN CAPITAL LETTER N WITH LONG RIGHT LEG]
768
+ '0274', # ɴ [LATIN LETTER SMALL CAPITAL N]
769
+ '1D0E', # ᴎ [LATIN LETTER SMALL CAPITAL REVERSED N]
770
+ '1E44', # Ṅ [LATIN CAPITAL LETTER N WITH DOT ABOVE]
771
+ '1E46', # Ṇ [LATIN CAPITAL LETTER N WITH DOT BELOW]
772
+ '1E48', # Ṉ [LATIN CAPITAL LETTER N WITH LINE BELOW]
773
+ '1E4A', # Ṋ [LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW]
774
+ '24C3', # Ⓝ [CIRCLED LATIN CAPITAL LETTER N]
775
+ 'FF2E' # N [FULLWIDTH LATIN CAPITAL LETTER N]
776
+ ] => 'N',
777
+ [
778
+
779
+ '00F1', # ñ [LATIN SMALL LETTER N WITH TILDE]
780
+ '0144', # ń [LATIN SMALL LETTER N WITH ACUTE]
781
+ '0146', # ņ [LATIN SMALL LETTER N WITH CEDILLA]
782
+ '0148', # ň [LATIN SMALL LETTER N WITH CARON]
783
+ '0149', # ʼn [LATIN SMALL LETTER N PRECEDED BY APOSTROPHE]
784
+ '014B', # ŋ http://en.wikipedia.org/wiki/Eng_(letter) [LATIN SMALL LETTER ENG]
785
+ '019E', # ƞ [LATIN SMALL LETTER N WITH LONG RIGHT LEG]
786
+ '01F9', # ǹ [LATIN SMALL LETTER N WITH GRAVE]
787
+ '0235', # ȵ [LATIN SMALL LETTER N WITH CURL]
788
+ '0272', # ɲ [LATIN SMALL LETTER N WITH LEFT HOOK]
789
+ '0273', # ɳ [LATIN SMALL LETTER N WITH RETROFLEX HOOK]
790
+ '1D70', # ᵰ [LATIN SMALL LETTER N WITH MIDDLE TILDE]
791
+ '1D87', # ᶇ [LATIN SMALL LETTER N WITH PALATAL HOOK]
792
+ '1E45', # ṅ [LATIN SMALL LETTER N WITH DOT ABOVE]
793
+ '1E47', # ṇ [LATIN SMALL LETTER N WITH DOT BELOW]
794
+ '1E49', # ṉ [LATIN SMALL LETTER N WITH LINE BELOW]
795
+ '1E4B', # ṋ [LATIN SMALL LETTER N WITH CIRCUMFLEX BELOW]
796
+ '207F', # ⁿ [SUPERSCRIPT LATIN SMALL LETTER N]
797
+ '24DD', # ⓝ [CIRCLED LATIN SMALL LETTER N]
798
+ 'FF4E' # n [FULLWIDTH LATIN SMALL LETTER N]
799
+ ] => 'n',
800
+ [
801
+
802
+ '01CA' # NJ [LATIN CAPITAL LETTER NJ]
803
+ ] => 'NJ',
804
+ [
805
+
806
+ '01CB' # Nj [LATIN CAPITAL LETTER N WITH SMALL LETTER J]
807
+ ] => 'Nj',
808
+ [
809
+
810
+ '24A9' # ⒩ [PARENTHESIZED LATIN SMALL LETTER N]
811
+ ] => '(n)',
812
+ [
813
+
814
+ '01CC' # nj [LATIN SMALL LETTER NJ]
815
+ ] => 'nj',
816
+ [
817
+
818
+ '00D2', # Ò [LATIN CAPITAL LETTER O WITH GRAVE]
819
+ '00D3', # Ó [LATIN CAPITAL LETTER O WITH ACUTE]
820
+ '00D4', # Ô [LATIN CAPITAL LETTER O WITH CIRCUMFLEX]
821
+ '00D5', # Õ [LATIN CAPITAL LETTER O WITH TILDE]
822
+ '00D6', # Ö [LATIN CAPITAL LETTER O WITH DIAERESIS]
823
+ '00D8', # Ø [LATIN CAPITAL LETTER O WITH STROKE]
824
+ '014C', # Ō [LATIN CAPITAL LETTER O WITH MACRON]
825
+ '014E', # Ŏ [LATIN CAPITAL LETTER O WITH BREVE]
826
+ '0150', # Ő [LATIN CAPITAL LETTER O WITH DOUBLE ACUTE]
827
+ '0186', # Ɔ [LATIN CAPITAL LETTER OPEN O]
828
+ '019F', # Ɵ [LATIN CAPITAL LETTER O WITH MIDDLE TILDE]
829
+ '01A0', # Ơ [LATIN CAPITAL LETTER O WITH HORN]
830
+ '01D1', # Ǒ [LATIN CAPITAL LETTER O WITH CARON]
831
+ '01EA', # Ǫ [LATIN CAPITAL LETTER O WITH OGONEK]
832
+ '01EC', # Ǭ [LATIN CAPITAL LETTER O WITH OGONEK AND MACRON]
833
+ '01FE', # Ǿ [LATIN CAPITAL LETTER O WITH STROKE AND ACUTE]
834
+ '020C', # Ȍ [LATIN CAPITAL LETTER O WITH DOUBLE GRAVE]
835
+ '020E', # Ȏ [LATIN CAPITAL LETTER O WITH INVERTED BREVE]
836
+ '022A', # Ȫ [LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON]
837
+ '022C', # Ȭ [LATIN CAPITAL LETTER O WITH TILDE AND MACRON]
838
+ '022E', # Ȯ [LATIN CAPITAL LETTER O WITH DOT ABOVE]
839
+ '0230', # Ȱ [LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON]
840
+ '1D0F', # ᴏ [LATIN LETTER SMALL CAPITAL O]
841
+ '1D10', # ᴐ [LATIN LETTER SMALL CAPITAL OPEN O]
842
+ '1E4C', # Ṍ [LATIN CAPITAL LETTER O WITH TILDE AND ACUTE]
843
+ '1E4E', # Ṏ [LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS]
844
+ '1E50', # Ṑ [LATIN CAPITAL LETTER O WITH MACRON AND GRAVE]
845
+ '1E52', # Ṓ [LATIN CAPITAL LETTER O WITH MACRON AND ACUTE]
846
+ '1ECC', # Ọ [LATIN CAPITAL LETTER O WITH DOT BELOW]
847
+ '1ECE', # Ỏ [LATIN CAPITAL LETTER O WITH HOOK ABOVE]
848
+ '1ED0', # Ố [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE]
849
+ '1ED2', # Ồ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE]
850
+ '1ED4', # Ổ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE]
851
+ '1ED6', # Ỗ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE]
852
+ '1ED8', # Ộ [LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW]
853
+ '1EDA', # Ớ [LATIN CAPITAL LETTER O WITH HORN AND ACUTE]
854
+ '1EDC', # Ờ [LATIN CAPITAL LETTER O WITH HORN AND GRAVE]
855
+ '1EDE', # Ở [LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE]
856
+ '1EE0', # Ỡ [LATIN CAPITAL LETTER O WITH HORN AND TILDE]
857
+ '1EE2', # Ợ [LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW]
858
+ '24C4', # Ⓞ [CIRCLED LATIN CAPITAL LETTER O]
859
+ 'A74A', # Ꝋ [LATIN CAPITAL LETTER O WITH LONG STROKE OVERLAY]
860
+ 'A74C', # Ꝍ [LATIN CAPITAL LETTER O WITH LOOP]
861
+ 'FF2F' # O [FULLWIDTH LATIN CAPITAL LETTER O]
862
+ ] => 'O',
863
+ [
864
+
865
+ '00F2', # ò [LATIN SMALL LETTER O WITH GRAVE]
866
+ '00F3', # ó [LATIN SMALL LETTER O WITH ACUTE]
867
+ '00F4', # ô [LATIN SMALL LETTER O WITH CIRCUMFLEX]
868
+ '00F5', # õ [LATIN SMALL LETTER O WITH TILDE]
869
+ '00F6', # ö [LATIN SMALL LETTER O WITH DIAERESIS]
870
+ '00F8', # ø [LATIN SMALL LETTER O WITH STROKE]
871
+ '014D', # ō [LATIN SMALL LETTER O WITH MACRON]
872
+ '014F', # ŏ [LATIN SMALL LETTER O WITH BREVE]
873
+ '0151', # ő [LATIN SMALL LETTER O WITH DOUBLE ACUTE]
874
+ '01A1', # ơ [LATIN SMALL LETTER O WITH HORN]
875
+ '01D2', # ǒ [LATIN SMALL LETTER O WITH CARON]
876
+ '01EB', # ǫ [LATIN SMALL LETTER O WITH OGONEK]
877
+ '01ED', # ǭ [LATIN SMALL LETTER O WITH OGONEK AND MACRON]
878
+ '01FF', # ǿ [LATIN SMALL LETTER O WITH STROKE AND ACUTE]
879
+ '020D', # ȍ [LATIN SMALL LETTER O WITH DOUBLE GRAVE]
880
+ '020F', # ȏ [LATIN SMALL LETTER O WITH INVERTED BREVE]
881
+ '022B', # ȫ [LATIN SMALL LETTER O WITH DIAERESIS AND MACRON]
882
+ '022D', # ȭ [LATIN SMALL LETTER O WITH TILDE AND MACRON]
883
+ '022F', # ȯ [LATIN SMALL LETTER O WITH DOT ABOVE]
884
+ '0231', # ȱ [LATIN SMALL LETTER O WITH DOT ABOVE AND MACRON]
885
+ '0254', # ɔ [LATIN SMALL LETTER OPEN O]
886
+ '0275', # ɵ [LATIN SMALL LETTER BARRED O]
887
+ '1D16', # ᴖ [LATIN SMALL LETTER TOP HALF O]
888
+ '1D17', # ᴗ [LATIN SMALL LETTER BOTTOM HALF O]
889
+ '1D97', # ᶗ [LATIN SMALL LETTER OPEN O WITH RETROFLEX HOOK]
890
+ '1E4D', # ṍ [LATIN SMALL LETTER O WITH TILDE AND ACUTE]
891
+ '1E4F', # ṏ [LATIN SMALL LETTER O WITH TILDE AND DIAERESIS]
892
+ '1E51', # ṑ [LATIN SMALL LETTER O WITH MACRON AND GRAVE]
893
+ '1E53', # ṓ [LATIN SMALL LETTER O WITH MACRON AND ACUTE]
894
+ '1ECD', # ọ [LATIN SMALL LETTER O WITH DOT BELOW]
895
+ '1ECF', # ỏ [LATIN SMALL LETTER O WITH HOOK ABOVE]
896
+ '1ED1', # ố [LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE]
897
+ '1ED3', # ồ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE]
898
+ '1ED5', # ổ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE]
899
+ '1ED7', # ỗ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE]
900
+ '1ED9', # ộ [LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW]
901
+ '1EDB', # ớ [LATIN SMALL LETTER O WITH HORN AND ACUTE]
902
+ '1EDD', # ờ [LATIN SMALL LETTER O WITH HORN AND GRAVE]
903
+ '1EDF', # ở [LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE]
904
+ '1EE1', # ỡ [LATIN SMALL LETTER O WITH HORN AND TILDE]
905
+ '1EE3', # ợ [LATIN SMALL LETTER O WITH HORN AND DOT BELOW]
906
+ '2092', # ₒ [LATIN SUBSCRIPT SMALL LETTER O]
907
+ '24DE', # ⓞ [CIRCLED LATIN SMALL LETTER O]
908
+ '2C7A', # ⱺ [LATIN SMALL LETTER O WITH LOW RING INSIDE]
909
+ 'A74B', # ꝋ [LATIN SMALL LETTER O WITH LONG STROKE OVERLAY]
910
+ 'A74D', # ꝍ [LATIN SMALL LETTER O WITH LOOP]
911
+ 'FF4F' # o [FULLWIDTH LATIN SMALL LETTER O]
912
+ ] => 'o',
913
+ [
914
+
915
+ '0152', # Π[LATIN CAPITAL LIGATURE OE]
916
+ '0276' # ɶ [LATIN LETTER SMALL CAPITAL OE]
917
+ ] => 'OE',
918
+ [
919
+
920
+ 'A74E' # Ꝏ [LATIN CAPITAL LETTER OO]
921
+ ] => 'OO',
922
+ [
923
+
924
+ '0222', # Ȣ http://en.wikipedia.org/wiki/OU [LATIN CAPITAL LETTER OU]
925
+ '1D15' # ᴕ [LATIN LETTER SMALL CAPITAL OU]
926
+ ] => 'OU',
927
+ [
928
+
929
+ '24AA' # ⒪ [PARENTHESIZED LATIN SMALL LETTER O]
930
+ ] => '(o)',
931
+ [
932
+
933
+ '0153', # œ [LATIN SMALL LIGATURE OE]
934
+ '1D14' # ᴔ [LATIN SMALL LETTER TURNED OE]
935
+ ] => 'oe',
936
+ [
937
+
938
+ 'A74F' # ꝏ [LATIN SMALL LETTER OO]
939
+ ] => 'oo',
940
+ [
941
+
942
+ '0223' # ȣ http://en.wikipedia.org/wiki/OU [LATIN SMALL LETTER OU]
943
+ ] => 'ou',
944
+ [
945
+
946
+ '01A4', # Ƥ [LATIN CAPITAL LETTER P WITH HOOK]
947
+ '1D18', # ᴘ [LATIN LETTER SMALL CAPITAL P]
948
+ '1E54', # Ṕ [LATIN CAPITAL LETTER P WITH ACUTE]
949
+ '1E56', # Ṗ [LATIN CAPITAL LETTER P WITH DOT ABOVE]
950
+ '24C5', # Ⓟ [CIRCLED LATIN CAPITAL LETTER P]
951
+ '2C63', # Ᵽ [LATIN CAPITAL LETTER P WITH STROKE]
952
+ 'A750', # Ꝑ [LATIN CAPITAL LETTER P WITH STROKE THROUGH DESCENDER]
953
+ 'A752', # Ꝓ [LATIN CAPITAL LETTER P WITH FLOURISH]
954
+ 'A754', # Ꝕ [LATIN CAPITAL LETTER P WITH SQUIRREL TAIL]
955
+ 'FF30' # P [FULLWIDTH LATIN CAPITAL LETTER P]
956
+ ] => 'P',
957
+ [
958
+
959
+ '01A5', # ƥ [LATIN SMALL LETTER P WITH HOOK]
960
+ '1D71', # ᵱ [LATIN SMALL LETTER P WITH MIDDLE TILDE]
961
+ '1D7D', # ᵽ [LATIN SMALL LETTER P WITH STROKE]
962
+ '1D88', # ᶈ [LATIN SMALL LETTER P WITH PALATAL HOOK]
963
+ '1E55', # ṕ [LATIN SMALL LETTER P WITH ACUTE]
964
+ '1E57', # ṗ [LATIN SMALL LETTER P WITH DOT ABOVE]
965
+ '24DF', # ⓟ [CIRCLED LATIN SMALL LETTER P]
966
+ 'A751', # ꝑ [LATIN SMALL LETTER P WITH STROKE THROUGH DESCENDER]
967
+ 'A753', # ꝓ [LATIN SMALL LETTER P WITH FLOURISH]
968
+ 'A755', # ꝕ [LATIN SMALL LETTER P WITH SQUIRREL TAIL]
969
+ 'A7FC', # ꟼ [LATIN EPIGRAPHIC LETTER REVERSED P]
970
+ 'FF50' # p [FULLWIDTH LATIN SMALL LETTER P]
971
+ ] => 'p',
972
+ [
973
+
974
+ '24AB' # ⒫ [PARENTHESIZED LATIN SMALL LETTER P]
975
+ ] => '(p)',
976
+ [
977
+
978
+ '024A', # Ɋ [LATIN CAPITAL LETTER SMALL Q WITH HOOK TAIL]
979
+ '24C6', # Ⓠ [CIRCLED LATIN CAPITAL LETTER Q]
980
+ 'A756', # Ꝗ [LATIN CAPITAL LETTER Q WITH STROKE THROUGH DESCENDER]
981
+ 'A758', # Ꝙ [LATIN CAPITAL LETTER Q WITH DIAGONAL STROKE]
982
+ 'FF31' # Q [FULLWIDTH LATIN CAPITAL LETTER Q]
983
+ ] => 'Q',
984
+ [
985
+
986
+ '0138', # ĸ http://en.wikipedia.org/wiki/Kra_(letter) [LATIN SMALL LETTER KRA]
987
+ '024B', # ɋ [LATIN SMALL LETTER Q WITH HOOK TAIL]
988
+ '02A0', # ʠ [LATIN SMALL LETTER Q WITH HOOK]
989
+ '24E0', # ⓠ [CIRCLED LATIN SMALL LETTER Q]
990
+ 'A757', # ꝗ [LATIN SMALL LETTER Q WITH STROKE THROUGH DESCENDER]
991
+ 'A759', # ꝙ [LATIN SMALL LETTER Q WITH DIAGONAL STROKE]
992
+ 'FF51' # q [FULLWIDTH LATIN SMALL LETTER Q]
993
+ ] => 'q',
994
+ [
995
+
996
+ '24AC' # ⒬ [PARENTHESIZED LATIN SMALL LETTER Q]
997
+ ] => '(q)',
998
+ [
999
+
1000
+ '0239' # ȹ [LATIN SMALL LETTER QP DIGRAPH]
1001
+ ] => 'qp',
1002
+ [
1003
+
1004
+ '0154', # Ŕ [LATIN CAPITAL LETTER R WITH ACUTE]
1005
+ '0156', # Ŗ [LATIN CAPITAL LETTER R WITH CEDILLA]
1006
+ '0158', # Ř [LATIN CAPITAL LETTER R WITH CARON]
1007
+ '0210', # Ȓ [LATIN CAPITAL LETTER R WITH DOUBLE GRAVE]
1008
+ '0212', # Ȓ [LATIN CAPITAL LETTER R WITH INVERTED BREVE]
1009
+ '024C', # Ɍ [LATIN CAPITAL LETTER R WITH STROKE]
1010
+ '0280', # ʀ [LATIN LETTER SMALL CAPITAL R]
1011
+ '0281', # ʁ [LATIN LETTER SMALL CAPITAL INVERTED R]
1012
+ '1D19', # ᴙ [LATIN LETTER SMALL CAPITAL REVERSED R]
1013
+ '1D1A', # ᴚ [LATIN LETTER SMALL CAPITAL TURNED R]
1014
+ '1E58', # Ṙ [LATIN CAPITAL LETTER R WITH DOT ABOVE]
1015
+ '1E5A', # Ṛ [LATIN CAPITAL LETTER R WITH DOT BELOW]
1016
+ '1E5C', # Ṝ [LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON]
1017
+ '1E5E', # Ṟ [LATIN CAPITAL LETTER R WITH LINE BELOW]
1018
+ '24C7', # Ⓡ [CIRCLED LATIN CAPITAL LETTER R]
1019
+ '2C64', # Ɽ [LATIN CAPITAL LETTER R WITH TAIL]
1020
+ 'A75A', # Ꝛ [LATIN CAPITAL LETTER R ROTUNDA]
1021
+ 'A782', # Ꞃ [LATIN CAPITAL LETTER INSULAR R]
1022
+ 'FF32' # R [FULLWIDTH LATIN CAPITAL LETTER R]
1023
+ ] => 'R',
1024
+ [
1025
+
1026
+ '0155', # ŕ [LATIN SMALL LETTER R WITH ACUTE]
1027
+ '0157', # ŗ [LATIN SMALL LETTER R WITH CEDILLA]
1028
+ '0159', # ř [LATIN SMALL LETTER R WITH CARON]
1029
+ '0211', # ȑ [LATIN SMALL LETTER R WITH DOUBLE GRAVE]
1030
+ '0213', # ȓ [LATIN SMALL LETTER R WITH INVERTED BREVE]
1031
+ '024D', # ɍ [LATIN SMALL LETTER R WITH STROKE]
1032
+ '027C', # ɼ [LATIN SMALL LETTER R WITH LONG LEG]
1033
+ '027D', # ɽ [LATIN SMALL LETTER R WITH TAIL]
1034
+ '027E', # ɾ [LATIN SMALL LETTER R WITH FISHHOOK]
1035
+ '027F', # ɿ [LATIN SMALL LETTER REVERSED R WITH FISHHOOK]
1036
+ '1D63', # ᵣ [LATIN SUBSCRIPT SMALL LETTER R]
1037
+ '1D72', # ᵲ [LATIN SMALL LETTER R WITH MIDDLE TILDE]
1038
+ '1D73', # ᵳ [LATIN SMALL LETTER R WITH FISHHOOK AND MIDDLE TILDE]
1039
+ '1D89', # ᶉ [LATIN SMALL LETTER R WITH PALATAL HOOK]
1040
+ '1E59', # ṙ [LATIN SMALL LETTER R WITH DOT ABOVE]
1041
+ '1E5B', # ṛ [LATIN SMALL LETTER R WITH DOT BELOW]
1042
+ '1E5D', # ṝ [LATIN SMALL LETTER R WITH DOT BELOW AND MACRON]
1043
+ '1E5F', # ṟ [LATIN SMALL LETTER R WITH LINE BELOW]
1044
+ '24E1', # ⓡ [CIRCLED LATIN SMALL LETTER R]
1045
+ 'A75B', # ꝛ [LATIN SMALL LETTER R ROTUNDA]
1046
+ 'A783', # ꞃ [LATIN SMALL LETTER INSULAR R]
1047
+ 'FF52' # r [FULLWIDTH LATIN SMALL LETTER R]
1048
+ ] => 'r',
1049
+ [
1050
+
1051
+ '24AD' # ⒭ [PARENTHESIZED LATIN SMALL LETTER R]
1052
+ ] => '(r)',
1053
+ [
1054
+
1055
+ '015A', # Ś [LATIN CAPITAL LETTER S WITH ACUTE]
1056
+ '015C', # Ŝ [LATIN CAPITAL LETTER S WITH CIRCUMFLEX]
1057
+ '015E', # Ş [LATIN CAPITAL LETTER S WITH CEDILLA]
1058
+ '0160', # Š [LATIN CAPITAL LETTER S WITH CARON]
1059
+ '0218', # Ș [LATIN CAPITAL LETTER S WITH COMMA BELOW]
1060
+ '1E60', # Ṡ [LATIN CAPITAL LETTER S WITH DOT ABOVE]
1061
+ '1E62', # Ṣ [LATIN CAPITAL LETTER S WITH DOT BELOW]
1062
+ '1E64', # Ṥ [LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE]
1063
+ '1E66', # Ṧ [LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE]
1064
+ '1E68', # Ṩ [LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE]
1065
+ '24C8', # Ⓢ [CIRCLED LATIN CAPITAL LETTER S]
1066
+ 'A731', # ꜱ [LATIN LETTER SMALL CAPITAL S]
1067
+ 'A785', # ꞅ [LATIN SMALL LETTER INSULAR S]
1068
+ 'FF33' # S [FULLWIDTH LATIN CAPITAL LETTER S]
1069
+ ] => 'S',
1070
+ [
1071
+
1072
+ '015B', # ś [LATIN SMALL LETTER S WITH ACUTE]
1073
+ '015D', # ŝ [LATIN SMALL LETTER S WITH CIRCUMFLEX]
1074
+ '015F', # ş [LATIN SMALL LETTER S WITH CEDILLA]
1075
+ '0161', # š [LATIN SMALL LETTER S WITH CARON]
1076
+ '017F', # ſ http://en.wikipedia.org/wiki/Long_S [LATIN SMALL LETTER LONG S]
1077
+ '0219', # ș [LATIN SMALL LETTER S WITH COMMA BELOW]
1078
+ '023F', # ȿ [LATIN SMALL LETTER S WITH SWASH TAIL]
1079
+ '0282', # ʂ [LATIN SMALL LETTER S WITH HOOK]
1080
+ '1D74', # ᵴ [LATIN SMALL LETTER S WITH MIDDLE TILDE]
1081
+ '1D8A', # ᶊ [LATIN SMALL LETTER S WITH PALATAL HOOK]
1082
+ '1E61', # ṡ [LATIN SMALL LETTER S WITH DOT ABOVE]
1083
+ '1E63', # ṣ [LATIN SMALL LETTER S WITH DOT BELOW]
1084
+ '1E65', # ṥ [LATIN SMALL LETTER S WITH ACUTE AND DOT ABOVE]
1085
+ '1E67', # ṧ [LATIN SMALL LETTER S WITH CARON AND DOT ABOVE]
1086
+ '1E69', # ṩ [LATIN SMALL LETTER S WITH DOT BELOW AND DOT ABOVE]
1087
+ '1E9C', # ẜ [LATIN SMALL LETTER LONG S WITH DIAGONAL STROKE]
1088
+ '1E9D', # ẝ [LATIN SMALL LETTER LONG S WITH HIGH STROKE]
1089
+ '24E2', # ⓢ [CIRCLED LATIN SMALL LETTER S]
1090
+ 'A784', # Ꞅ [LATIN CAPITAL LETTER INSULAR S]
1091
+ 'FF53' # s [FULLWIDTH LATIN SMALL LETTER S]
1092
+ ] => 's',
1093
+ [
1094
+
1095
+ '1E9E' # ẞ [LATIN CAPITAL LETTER SHARP S]
1096
+ ] => 'SS',
1097
+ [
1098
+
1099
+ '24AE' # ⒮ [PARENTHESIZED LATIN SMALL LETTER S]
1100
+ ] => '(s)',
1101
+ [
1102
+
1103
+ '00DF' # ß [LATIN SMALL LETTER SHARP S]
1104
+ ] => 'ss',
1105
+ [
1106
+
1107
+ 'FB06' # st [LATIN SMALL LIGATURE ST]
1108
+ ] => 'st',
1109
+ [
1110
+
1111
+ '0162', # Ţ [LATIN CAPITAL LETTER T WITH CEDILLA]
1112
+ '0164', # Ť [LATIN CAPITAL LETTER T WITH CARON]
1113
+ '0166', # Ŧ [LATIN CAPITAL LETTER T WITH STROKE]
1114
+ '01AC', # Ƭ [LATIN CAPITAL LETTER T WITH HOOK]
1115
+ '01AE', # Ʈ [LATIN CAPITAL LETTER T WITH RETROFLEX HOOK]
1116
+ '021A', # Ț [LATIN CAPITAL LETTER T WITH COMMA BELOW]
1117
+ '023E', # Ⱦ [LATIN CAPITAL LETTER T WITH DIAGONAL STROKE]
1118
+ '1D1B', # ᴛ [LATIN LETTER SMALL CAPITAL T]
1119
+ '1E6A', # Ṫ [LATIN CAPITAL LETTER T WITH DOT ABOVE]
1120
+ '1E6C', # Ṭ [LATIN CAPITAL LETTER T WITH DOT BELOW]
1121
+ '1E6E', # Ṯ [LATIN CAPITAL LETTER T WITH LINE BELOW]
1122
+ '1E70', # Ṱ [LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW]
1123
+ '24C9', # Ⓣ [CIRCLED LATIN CAPITAL LETTER T]
1124
+ 'A786', # Ꞇ [LATIN CAPITAL LETTER INSULAR T]
1125
+ 'FF34' # T [FULLWIDTH LATIN CAPITAL LETTER T]
1126
+ ] => 'T',
1127
+ [
1128
+
1129
+ '0163', # ţ [LATIN SMALL LETTER T WITH CEDILLA]
1130
+ '0165', # ť [LATIN SMALL LETTER T WITH CARON]
1131
+ '0167', # ŧ [LATIN SMALL LETTER T WITH STROKE]
1132
+ '01AB', # ƫ [LATIN SMALL LETTER T WITH PALATAL HOOK]
1133
+ '01AD', # ƭ [LATIN SMALL LETTER T WITH HOOK]
1134
+ '021B', # ț [LATIN SMALL LETTER T WITH COMMA BELOW]
1135
+ '0236', # ȶ [LATIN SMALL LETTER T WITH CURL]
1136
+ '0287', # ʇ [LATIN SMALL LETTER TURNED T]
1137
+ '0288', # ʈ [LATIN SMALL LETTER T WITH RETROFLEX HOOK]
1138
+ '1D75', # ᵵ [LATIN SMALL LETTER T WITH MIDDLE TILDE]
1139
+ '1E6B', # ṫ [LATIN SMALL LETTER T WITH DOT ABOVE]
1140
+ '1E6D', # ṭ [LATIN SMALL LETTER T WITH DOT BELOW]
1141
+ '1E6F', # ṯ [LATIN SMALL LETTER T WITH LINE BELOW]
1142
+ '1E71', # ṱ [LATIN SMALL LETTER T WITH CIRCUMFLEX BELOW]
1143
+ '1E97', # ẗ [LATIN SMALL LETTER T WITH DIAERESIS]
1144
+ '24E3', # ⓣ [CIRCLED LATIN SMALL LETTER T]
1145
+ '2C66', # ⱦ [LATIN SMALL LETTER T WITH DIAGONAL STROKE]
1146
+ 'FF54' # t [FULLWIDTH LATIN SMALL LETTER T]
1147
+ ] => 't',
1148
+ [
1149
+
1150
+ '00DE', # Þ [LATIN CAPITAL LETTER THORN]
1151
+ 'A766' # Ꝧ [LATIN CAPITAL LETTER THORN WITH STROKE THROUGH DESCENDER]
1152
+ ] => 'TH',
1153
+ [
1154
+
1155
+ 'A728' # Ꜩ [LATIN CAPITAL LETTER TZ]
1156
+ ] => 'TZ',
1157
+ [
1158
+
1159
+ '24AF' # ⒯ [PARENTHESIZED LATIN SMALL LETTER T]
1160
+ ] => '(t)',
1161
+ [
1162
+
1163
+ '02A8' # ʨ [LATIN SMALL LETTER TC DIGRAPH WITH CURL]
1164
+ ] => 'tc',
1165
+ [
1166
+
1167
+ '00FE', # þ [LATIN SMALL LETTER THORN]
1168
+ '1D7A', # ᵺ [LATIN SMALL LETTER TH WITH STRIKETHROUGH]
1169
+ 'A767' # ꝧ [LATIN SMALL LETTER THORN WITH STROKE THROUGH DESCENDER]
1170
+ ] => 'th',
1171
+ [
1172
+
1173
+ '02A6' # ʦ [LATIN SMALL LETTER TS DIGRAPH]
1174
+ ] => 'ts',
1175
+ [
1176
+
1177
+ 'A729' # ꜩ [LATIN SMALL LETTER TZ]
1178
+ ] => 'tz',
1179
+ [
1180
+
1181
+ '00D9', # Ù [LATIN CAPITAL LETTER U WITH GRAVE]
1182
+ '00DA', # Ú [LATIN CAPITAL LETTER U WITH ACUTE]
1183
+ '00DB', # Û [LATIN CAPITAL LETTER U WITH CIRCUMFLEX]
1184
+ '00DC', # Ü [LATIN CAPITAL LETTER U WITH DIAERESIS]
1185
+ '0168', # Ũ [LATIN CAPITAL LETTER U WITH TILDE]
1186
+ '016A', # Ū [LATIN CAPITAL LETTER U WITH MACRON]
1187
+ '016C', # Ŭ [LATIN CAPITAL LETTER U WITH BREVE]
1188
+ '016E', # Ů [LATIN CAPITAL LETTER U WITH RING ABOVE]
1189
+ '0170', # Ű [LATIN CAPITAL LETTER U WITH DOUBLE ACUTE]
1190
+ '0172', # Ų [LATIN CAPITAL LETTER U WITH OGONEK]
1191
+ '01AF', # Ư [LATIN CAPITAL LETTER U WITH HORN]
1192
+ '01D3', # Ǔ [LATIN CAPITAL LETTER U WITH CARON]
1193
+ '01D5', # Ǖ [LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON]
1194
+ '01D7', # Ǘ [LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE]
1195
+ '01D9', # Ǚ [LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON]
1196
+ '01DB', # Ǜ [LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE]
1197
+ '0214', # Ȕ [LATIN CAPITAL LETTER U WITH DOUBLE GRAVE]
1198
+ '0216', # Ȗ [LATIN CAPITAL LETTER U WITH INVERTED BREVE]
1199
+ '0244', # Ʉ [LATIN CAPITAL LETTER U BAR]
1200
+ '1D1C', # ᴜ [LATIN LETTER SMALL CAPITAL U]
1201
+ '1D7E', # ᵾ [LATIN SMALL CAPITAL LETTER U WITH STROKE]
1202
+ '1E72', # Ṳ [LATIN CAPITAL LETTER U WITH DIAERESIS BELOW]
1203
+ '1E74', # Ṵ [LATIN CAPITAL LETTER U WITH TILDE BELOW]
1204
+ '1E76', # Ṷ [LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW]
1205
+ '1E78', # Ṹ [LATIN CAPITAL LETTER U WITH TILDE AND ACUTE]
1206
+ '1E7A', # Ṻ [LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS]
1207
+ '1EE4', # Ụ [LATIN CAPITAL LETTER U WITH DOT BELOW]
1208
+ '1EE6', # Ủ [LATIN CAPITAL LETTER U WITH HOOK ABOVE]
1209
+ '1EE8', # Ứ [LATIN CAPITAL LETTER U WITH HORN AND ACUTE]
1210
+ '1EEA', # Ừ [LATIN CAPITAL LETTER U WITH HORN AND GRAVE]
1211
+ '1EEC', # Ử [LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE]
1212
+ '1EEE', # Ữ [LATIN CAPITAL LETTER U WITH HORN AND TILDE]
1213
+ '1EF0', # Ự [LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW]
1214
+ '24CA', # Ⓤ [CIRCLED LATIN CAPITAL LETTER U]
1215
+ 'FF35' # U [FULLWIDTH LATIN CAPITAL LETTER U]
1216
+ ] => 'U',
1217
+ [
1218
+
1219
+ '00F9', # ù [LATIN SMALL LETTER U WITH GRAVE]
1220
+ '00FA', # ú [LATIN SMALL LETTER U WITH ACUTE]
1221
+ '00FB', # û [LATIN SMALL LETTER U WITH CIRCUMFLEX]
1222
+ '00FC', # ü [LATIN SMALL LETTER U WITH DIAERESIS]
1223
+ '0169', # ũ [LATIN SMALL LETTER U WITH TILDE]
1224
+ '016B', # ū [LATIN SMALL LETTER U WITH MACRON]
1225
+ '016D', # ŭ [LATIN SMALL LETTER U WITH BREVE]
1226
+ '016F', # ů [LATIN SMALL LETTER U WITH RING ABOVE]
1227
+ '0171', # ű [LATIN SMALL LETTER U WITH DOUBLE ACUTE]
1228
+ '0173', # ų [LATIN SMALL LETTER U WITH OGONEK]
1229
+ '01B0', # ư [LATIN SMALL LETTER U WITH HORN]
1230
+ '01D4', # ǔ [LATIN SMALL LETTER U WITH CARON]
1231
+ '01D6', # ǖ [LATIN SMALL LETTER U WITH DIAERESIS AND MACRON]
1232
+ '01D8', # ǘ [LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE]
1233
+ '01DA', # ǚ [LATIN SMALL LETTER U WITH DIAERESIS AND CARON]
1234
+ '01DC', # ǜ [LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE]
1235
+ '0215', # ȕ [LATIN SMALL LETTER U WITH DOUBLE GRAVE]
1236
+ '0217', # ȗ [LATIN SMALL LETTER U WITH INVERTED BREVE]
1237
+ '0289', # ʉ [LATIN SMALL LETTER U BAR]
1238
+ '1D64', # ᵤ [LATIN SUBSCRIPT SMALL LETTER U]
1239
+ '1D99', # ᶙ [LATIN SMALL LETTER U WITH RETROFLEX HOOK]
1240
+ '1E73', # ṳ [LATIN SMALL LETTER U WITH DIAERESIS BELOW]
1241
+ '1E75', # ṵ [LATIN SMALL LETTER U WITH TILDE BELOW]
1242
+ '1E77', # ṷ [LATIN SMALL LETTER U WITH CIRCUMFLEX BELOW]
1243
+ '1E79', # ṹ [LATIN SMALL LETTER U WITH TILDE AND ACUTE]
1244
+ '1E7B', # ṻ [LATIN SMALL LETTER U WITH MACRON AND DIAERESIS]
1245
+ '1EE5', # ụ [LATIN SMALL LETTER U WITH DOT BELOW]
1246
+ '1EE7', # ủ [LATIN SMALL LETTER U WITH HOOK ABOVE]
1247
+ '1EE9', # ứ [LATIN SMALL LETTER U WITH HORN AND ACUTE]
1248
+ '1EEB', # ừ [LATIN SMALL LETTER U WITH HORN AND GRAVE]
1249
+ '1EED', # ử [LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE]
1250
+ '1EEF', # ữ [LATIN SMALL LETTER U WITH HORN AND TILDE]
1251
+ '1EF1', # ự [LATIN SMALL LETTER U WITH HORN AND DOT BELOW]
1252
+ '24E4', # ⓤ [CIRCLED LATIN SMALL LETTER U]
1253
+ 'FF55' # u [FULLWIDTH LATIN SMALL LETTER U]
1254
+ ] => 'u',
1255
+ [
1256
+
1257
+ '24B0' # ⒰ [PARENTHESIZED LATIN SMALL LETTER U]
1258
+ ] => '(u)',
1259
+ [
1260
+
1261
+ '1D6B' # ᵫ [LATIN SMALL LETTER UE]
1262
+ ] => 'ue',
1263
+ [
1264
+
1265
+ '01B2', # Ʋ [LATIN CAPITAL LETTER V WITH HOOK]
1266
+ '0245', # Ʌ [LATIN CAPITAL LETTER TURNED V]
1267
+ '1D20', # ᴠ [LATIN LETTER SMALL CAPITAL V]
1268
+ '1E7C', # Ṽ [LATIN CAPITAL LETTER V WITH TILDE]
1269
+ '1E7E', # Ṿ [LATIN CAPITAL LETTER V WITH DOT BELOW]
1270
+ '1EFC', # Ỽ [LATIN CAPITAL LETTER MIDDLE-WELSH V]
1271
+ '24CB', # Ⓥ [CIRCLED LATIN CAPITAL LETTER V]
1272
+ 'A75E', # Ꝟ [LATIN CAPITAL LETTER V WITH DIAGONAL STROKE]
1273
+ 'A768', # Ꝩ [LATIN CAPITAL LETTER VEND]
1274
+ 'FF36' # V [FULLWIDTH LATIN CAPITAL LETTER V]
1275
+ ] => 'V',
1276
+ [
1277
+
1278
+ '028B', # ʋ [LATIN SMALL LETTER V WITH HOOK]
1279
+ '028C', # ʌ [LATIN SMALL LETTER TURNED V]
1280
+ '1D65', # ᵥ [LATIN SUBSCRIPT SMALL LETTER V]
1281
+ '1D8C', # ᶌ [LATIN SMALL LETTER V WITH PALATAL HOOK]
1282
+ '1E7D', # ṽ [LATIN SMALL LETTER V WITH TILDE]
1283
+ '1E7F', # ṿ [LATIN SMALL LETTER V WITH DOT BELOW]
1284
+ '24E5', # ⓥ [CIRCLED LATIN SMALL LETTER V]
1285
+ '2C71', # ⱱ [LATIN SMALL LETTER V WITH RIGHT HOOK]
1286
+ '2C74', # ⱴ [LATIN SMALL LETTER V WITH CURL]
1287
+ 'A75F', # ꝟ [LATIN SMALL LETTER V WITH DIAGONAL STROKE]
1288
+ 'FF56' # v [FULLWIDTH LATIN SMALL LETTER V]
1289
+ ] => 'v',
1290
+ [
1291
+
1292
+ 'A760' # Ꝡ [LATIN CAPITAL LETTER VY]
1293
+ ] => 'VY',
1294
+ [
1295
+
1296
+ '24B1' # ⒱ [PARENTHESIZED LATIN SMALL LETTER V]
1297
+ ] => '(v)',
1298
+ [
1299
+
1300
+ 'A761' # ꝡ [LATIN SMALL LETTER VY]
1301
+ ] => 'vy',
1302
+ [
1303
+
1304
+ '0174', # Ŵ [LATIN CAPITAL LETTER W WITH CIRCUMFLEX]
1305
+ '01F7', # Ƿ http://en.wikipedia.org/wiki/Wynn [LATIN CAPITAL LETTER WYNN]
1306
+ '1D21', # ᴡ [LATIN LETTER SMALL CAPITAL W]
1307
+ '1E80', # Ẁ [LATIN CAPITAL LETTER W WITH GRAVE]
1308
+ '1E82', # Ẃ [LATIN CAPITAL LETTER W WITH ACUTE]
1309
+ '1E84', # Ẅ [LATIN CAPITAL LETTER W WITH DIAERESIS]
1310
+ '1E86', # Ẇ [LATIN CAPITAL LETTER W WITH DOT ABOVE]
1311
+ '1E88', # Ẉ [LATIN CAPITAL LETTER W WITH DOT BELOW]
1312
+ '24CC', # Ⓦ [CIRCLED LATIN CAPITAL LETTER W]
1313
+ '2C72', # Ⱳ [LATIN CAPITAL LETTER W WITH HOOK]
1314
+ 'FF37' # W [FULLWIDTH LATIN CAPITAL LETTER W]
1315
+ ] => 'W',
1316
+ [
1317
+
1318
+ '0175', # ŵ [LATIN SMALL LETTER W WITH CIRCUMFLEX]
1319
+ '01BF', # ƿ http://en.wikipedia.org/wiki/Wynn [LATIN LETTER WYNN]
1320
+ '028D', # ʍ [LATIN SMALL LETTER TURNED W]
1321
+ '1E81', # ẁ [LATIN SMALL LETTER W WITH GRAVE]
1322
+ '1E83', # ẃ [LATIN SMALL LETTER W WITH ACUTE]
1323
+ '1E85', # ẅ [LATIN SMALL LETTER W WITH DIAERESIS]
1324
+ '1E87', # ẇ [LATIN SMALL LETTER W WITH DOT ABOVE]
1325
+ '1E89', # ẉ [LATIN SMALL LETTER W WITH DOT BELOW]
1326
+ '1E98', # ẘ [LATIN SMALL LETTER W WITH RING ABOVE]
1327
+ '24E6', # ⓦ [CIRCLED LATIN SMALL LETTER W]
1328
+ '2C73', # ⱳ [LATIN SMALL LETTER W WITH HOOK]
1329
+ 'FF57' # w [FULLWIDTH LATIN SMALL LETTER W]
1330
+ ] => 'w',
1331
+ [
1332
+
1333
+ '24B2' # ⒲ [PARENTHESIZED LATIN SMALL LETTER W]
1334
+ ] => '(w)',
1335
+ [
1336
+
1337
+ '1E8A', # Ẋ [LATIN CAPITAL LETTER X WITH DOT ABOVE]
1338
+ '1E8C', # Ẍ [LATIN CAPITAL LETTER X WITH DIAERESIS]
1339
+ '24CD', # Ⓧ [CIRCLED LATIN CAPITAL LETTER X]
1340
+ 'FF38' # X [FULLWIDTH LATIN CAPITAL LETTER X]
1341
+ ] => 'X',
1342
+ [
1343
+
1344
+ '1D8D', # ᶍ [LATIN SMALL LETTER X WITH PALATAL HOOK]
1345
+ '1E8B', # ẋ [LATIN SMALL LETTER X WITH DOT ABOVE]
1346
+ '1E8D', # ẍ [LATIN SMALL LETTER X WITH DIAERESIS]
1347
+ '2093', # ₓ [LATIN SUBSCRIPT SMALL LETTER X]
1348
+ '24E7', # ⓧ [CIRCLED LATIN SMALL LETTER X]
1349
+ 'FF58' # x [FULLWIDTH LATIN SMALL LETTER X]
1350
+ ] => 'x',
1351
+ [
1352
+
1353
+ '24B3' # ⒳ [PARENTHESIZED LATIN SMALL LETTER X]
1354
+ ] => '(x)',
1355
+ [
1356
+
1357
+ '00DD', # Ý [LATIN CAPITAL LETTER Y WITH ACUTE]
1358
+ '0176', # Ŷ [LATIN CAPITAL LETTER Y WITH CIRCUMFLEX]
1359
+ '0178', # Ÿ [LATIN CAPITAL LETTER Y WITH DIAERESIS]
1360
+ '01B3', # Ƴ [LATIN CAPITAL LETTER Y WITH HOOK]
1361
+ '0232', # Ȳ [LATIN CAPITAL LETTER Y WITH MACRON]
1362
+ '024E', # Ɏ [LATIN CAPITAL LETTER Y WITH STROKE]
1363
+ '028F', # ʏ [LATIN LETTER SMALL CAPITAL Y]
1364
+ '1E8E', # Ẏ [LATIN CAPITAL LETTER Y WITH DOT ABOVE]
1365
+ '1EF2', # Ỳ [LATIN CAPITAL LETTER Y WITH GRAVE]
1366
+ '1EF4', # Ỵ [LATIN CAPITAL LETTER Y WITH DOT BELOW]
1367
+ '1EF6', # Ỷ [LATIN CAPITAL LETTER Y WITH HOOK ABOVE]
1368
+ '1EF8', # Ỹ [LATIN CAPITAL LETTER Y WITH TILDE]
1369
+ '1EFE', # Ỿ [LATIN CAPITAL LETTER Y WITH LOOP]
1370
+ '24CE', # Ⓨ [CIRCLED LATIN CAPITAL LETTER Y]
1371
+ 'FF39' # Y [FULLWIDTH LATIN CAPITAL LETTER Y]
1372
+ ] => 'Y',
1373
+ [
1374
+
1375
+ '00FD', # ý [LATIN SMALL LETTER Y WITH ACUTE]
1376
+ '00FF', # ÿ [LATIN SMALL LETTER Y WITH DIAERESIS]
1377
+ '0177', # ŷ [LATIN SMALL LETTER Y WITH CIRCUMFLEX]
1378
+ '01B4', # ƴ [LATIN SMALL LETTER Y WITH HOOK]
1379
+ '0233', # ȳ [LATIN SMALL LETTER Y WITH MACRON]
1380
+ '024F', # ɏ [LATIN SMALL LETTER Y WITH STROKE]
1381
+ '028E', # ʎ [LATIN SMALL LETTER TURNED Y]
1382
+ '1E8F', # ẏ [LATIN SMALL LETTER Y WITH DOT ABOVE]
1383
+ '1E99', # ẙ [LATIN SMALL LETTER Y WITH RING ABOVE]
1384
+ '1EF3', # ỳ [LATIN SMALL LETTER Y WITH GRAVE]
1385
+ '1EF5', # ỵ [LATIN SMALL LETTER Y WITH DOT BELOW]
1386
+ '1EF7', # ỷ [LATIN SMALL LETTER Y WITH HOOK ABOVE]
1387
+ '1EF9', # ỹ [LATIN SMALL LETTER Y WITH TILDE]
1388
+ '1EFF', # ỿ [LATIN SMALL LETTER Y WITH LOOP]
1389
+ '24E8', # ⓨ [CIRCLED LATIN SMALL LETTER Y]
1390
+ 'FF59' # y [FULLWIDTH LATIN SMALL LETTER Y]
1391
+ ] => 'y',
1392
+ [
1393
+
1394
+ '24B4' # ⒴ [PARENTHESIZED LATIN SMALL LETTER Y]
1395
+ ] => '(y)',
1396
+ [
1397
+
1398
+ '0179', # Ź [LATIN CAPITAL LETTER Z WITH ACUTE]
1399
+ '017B', # Ż [LATIN CAPITAL LETTER Z WITH DOT ABOVE]
1400
+ '017D', # Ž [LATIN CAPITAL LETTER Z WITH CARON]
1401
+ '01B5', # Ƶ [LATIN CAPITAL LETTER Z WITH STROKE]
1402
+ '021C', # Ȝ http://en.wikipedia.org/wiki/Yogh [LATIN CAPITAL LETTER YOGH]
1403
+ '0224', # Ȥ [LATIN CAPITAL LETTER Z WITH HOOK]
1404
+ '1D22', # ᴢ [LATIN LETTER SMALL CAPITAL Z]
1405
+ '1E90', # Ẑ [LATIN CAPITAL LETTER Z WITH CIRCUMFLEX]
1406
+ '1E92', # Ẓ [LATIN CAPITAL LETTER Z WITH DOT BELOW]
1407
+ '1E94', # Ẕ [LATIN CAPITAL LETTER Z WITH LINE BELOW]
1408
+ '24CF', # Ⓩ [CIRCLED LATIN CAPITAL LETTER Z]
1409
+ '2C6B', # Ⱬ [LATIN CAPITAL LETTER Z WITH DESCENDER]
1410
+ 'A762', # Ꝣ [LATIN CAPITAL LETTER VISIGOTHIC Z]
1411
+ 'FF3A' # Z [FULLWIDTH LATIN CAPITAL LETTER Z]
1412
+ ] => 'Z',
1413
+ [
1414
+
1415
+ '017A', # ź [LATIN SMALL LETTER Z WITH ACUTE]
1416
+ '017C', # ż [LATIN SMALL LETTER Z WITH DOT ABOVE]
1417
+ '017E', # ž [LATIN SMALL LETTER Z WITH CARON]
1418
+ '01B6', # ƶ [LATIN SMALL LETTER Z WITH STROKE]
1419
+ '021D', # ȝ http://en.wikipedia.org/wiki/Yogh [LATIN SMALL LETTER YOGH]
1420
+ '0225', # ȥ [LATIN SMALL LETTER Z WITH HOOK]
1421
+ '0240', # ɀ [LATIN SMALL LETTER Z WITH SWASH TAIL]
1422
+ '0290', # ʐ [LATIN SMALL LETTER Z WITH RETROFLEX HOOK]
1423
+ '0291', # ʑ [LATIN SMALL LETTER Z WITH CURL]
1424
+ '1D76', # ᵶ [LATIN SMALL LETTER Z WITH MIDDLE TILDE]
1425
+ '1D8E', # ᶎ [LATIN SMALL LETTER Z WITH PALATAL HOOK]
1426
+ '1E91', # ẑ [LATIN SMALL LETTER Z WITH CIRCUMFLEX]
1427
+ '1E93', # ẓ [LATIN SMALL LETTER Z WITH DOT BELOW]
1428
+ '1E95', # ẕ [LATIN SMALL LETTER Z WITH LINE BELOW]
1429
+ '24E9', # ⓩ [CIRCLED LATIN SMALL LETTER Z]
1430
+ '2C6C', # ⱬ [LATIN SMALL LETTER Z WITH DESCENDER]
1431
+ 'A763', # ꝣ [LATIN SMALL LETTER VISIGOTHIC Z]
1432
+ 'FF5A' # z [FULLWIDTH LATIN SMALL LETTER Z]
1433
+ ] => 'z',
1434
+ [
1435
+
1436
+ '24B5' # ⒵ [PARENTHESIZED LATIN SMALL LETTER Z]
1437
+ ] => '(z)',
1438
+ [
1439
+
1440
+ '2070', # ⁰ [SUPERSCRIPT ZERO]
1441
+ '2080', # ₀ [SUBSCRIPT ZERO]
1442
+ '24EA', # ⓪ [CIRCLED DIGIT ZERO]
1443
+ '24FF', # ⓿ [NEGATIVE CIRCLED DIGIT ZERO]
1444
+ 'FF10' # 0 [FULLWIDTH DIGIT ZERO]
1445
+ ] => '0',
1446
+ [
1447
+
1448
+ '00B9', # ¹ [SUPERSCRIPT ONE]
1449
+ '2081', # ₁ [SUBSCRIPT ONE]
1450
+ '2460', # ① [CIRCLED DIGIT ONE]
1451
+ '24F5', # ⓵ [DOUBLE CIRCLED DIGIT ONE]
1452
+ '2776', # ❶ [DINGBAT NEGATIVE CIRCLED DIGIT ONE]
1453
+ '2780', # ➀ [DINGBAT CIRCLED SANS-SERIF DIGIT ONE]
1454
+ '278A', # ➊ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT ONE]
1455
+ 'FF11' # 1 [FULLWIDTH DIGIT ONE]
1456
+ ] => '1',
1457
+ [
1458
+
1459
+ '2488' # ⒈ [DIGIT ONE FULL STOP]
1460
+ ] => '1.',
1461
+ [
1462
+
1463
+ '2474' # ⑴ [PARENTHESIZED DIGIT ONE]
1464
+ ] => '(1)',
1465
+ [
1466
+
1467
+ '00B2', # ² [SUPERSCRIPT TWO]
1468
+ '2082', # ₂ [SUBSCRIPT TWO]
1469
+ '2461', # ② [CIRCLED DIGIT TWO]
1470
+ '24F6', # ⓶ [DOUBLE CIRCLED DIGIT TWO]
1471
+ '2777', # ❷ [DINGBAT NEGATIVE CIRCLED DIGIT TWO]
1472
+ '2781', # ➁ [DINGBAT CIRCLED SANS-SERIF DIGIT TWO]
1473
+ '278B', # ➋ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT TWO]
1474
+ 'FF12' # 2 [FULLWIDTH DIGIT TWO]
1475
+ ] => '2',
1476
+ [
1477
+
1478
+ '2489' # ⒉ [DIGIT TWO FULL STOP]
1479
+ ] => '2.',
1480
+ [
1481
+
1482
+ '2475' # ⑵ [PARENTHESIZED DIGIT TWO]
1483
+ ] => '(2)',
1484
+ [
1485
+
1486
+ '00B3', # ³ [SUPERSCRIPT THREE]
1487
+ '2083', # ₃ [SUBSCRIPT THREE]
1488
+ '2462', # ③ [CIRCLED DIGIT THREE]
1489
+ '24F7', # ⓷ [DOUBLE CIRCLED DIGIT THREE]
1490
+ '2778', # ❸ [DINGBAT NEGATIVE CIRCLED DIGIT THREE]
1491
+ '2782', # ➂ [DINGBAT CIRCLED SANS-SERIF DIGIT THREE]
1492
+ '278C', # ➌ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT THREE]
1493
+ 'FF13' # 3 [FULLWIDTH DIGIT THREE]
1494
+ ] => '3',
1495
+ [
1496
+
1497
+ '248A' # ⒊ [DIGIT THREE FULL STOP]
1498
+ ] => '3.',
1499
+ [
1500
+
1501
+ '2476' # ⑶ [PARENTHESIZED DIGIT THREE]
1502
+ ] => '(3)',
1503
+ [
1504
+
1505
+ '2074', # ⁴ [SUPERSCRIPT FOUR]
1506
+ '2084', # ₄ [SUBSCRIPT FOUR]
1507
+ '2463', # ④ [CIRCLED DIGIT FOUR]
1508
+ '24F8', # ⓸ [DOUBLE CIRCLED DIGIT FOUR]
1509
+ '2779', # ❹ [DINGBAT NEGATIVE CIRCLED DIGIT FOUR]
1510
+ '2783', # ➃ [DINGBAT CIRCLED SANS-SERIF DIGIT FOUR]
1511
+ '278D', # ➍ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FOUR]
1512
+ 'FF14' # 4 [FULLWIDTH DIGIT FOUR]
1513
+ ] => '4',
1514
+ [
1515
+
1516
+ '248B' # ⒋ [DIGIT FOUR FULL STOP]
1517
+ ] => '4.',
1518
+ [
1519
+
1520
+ '2477' # ⑷ [PARENTHESIZED DIGIT FOUR]
1521
+ ] => '(4)',
1522
+ [
1523
+
1524
+ '2075', # ⁵ [SUPERSCRIPT FIVE]
1525
+ '2085', # ₅ [SUBSCRIPT FIVE]
1526
+ '2464', # ⑤ [CIRCLED DIGIT FIVE]
1527
+ '24F9', # ⓹ [DOUBLE CIRCLED DIGIT FIVE]
1528
+ '277A', # ❺ [DINGBAT NEGATIVE CIRCLED DIGIT FIVE]
1529
+ '2784', # ➄ [DINGBAT CIRCLED SANS-SERIF DIGIT FIVE]
1530
+ '278E', # ➎ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT FIVE]
1531
+ 'FF15' # 5 [FULLWIDTH DIGIT FIVE]
1532
+ ] => '5',
1533
+ [
1534
+
1535
+ '248C' # ⒌ [DIGIT FIVE FULL STOP]
1536
+ ] => '5.',
1537
+ [
1538
+
1539
+ '2478' # ⑸ [PARENTHESIZED DIGIT FIVE]
1540
+ ] => '(5)',
1541
+ [
1542
+
1543
+ '2076', # ⁶ [SUPERSCRIPT SIX]
1544
+ '2086', # ₆ [SUBSCRIPT SIX]
1545
+ '2465', # ⑥ [CIRCLED DIGIT SIX]
1546
+ '24FA', # ⓺ [DOUBLE CIRCLED DIGIT SIX]
1547
+ '277B', # ❻ [DINGBAT NEGATIVE CIRCLED DIGIT SIX]
1548
+ '2785', # ➅ [DINGBAT CIRCLED SANS-SERIF DIGIT SIX]
1549
+ '278F', # ➏ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SIX]
1550
+ 'FF16' # 6 [FULLWIDTH DIGIT SIX]
1551
+ ] => '6',
1552
+ [
1553
+
1554
+ '248D' # ⒍ [DIGIT SIX FULL STOP]
1555
+ ] => '6.',
1556
+ [
1557
+
1558
+ '2479' # ⑹ [PARENTHESIZED DIGIT SIX]
1559
+ ] => '(6)',
1560
+ [
1561
+
1562
+ '2077', # ⁷ [SUPERSCRIPT SEVEN]
1563
+ '2087', # ₇ [SUBSCRIPT SEVEN]
1564
+ '2466', # ⑦ [CIRCLED DIGIT SEVEN]
1565
+ '24FB', # ⓻ [DOUBLE CIRCLED DIGIT SEVEN]
1566
+ '277C', # ❼ [DINGBAT NEGATIVE CIRCLED DIGIT SEVEN]
1567
+ '2786', # ➆ [DINGBAT CIRCLED SANS-SERIF DIGIT SEVEN]
1568
+ '2790', # ➐ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT SEVEN]
1569
+ 'FF17' # 7 [FULLWIDTH DIGIT SEVEN]
1570
+ ] => '7',
1571
+ [
1572
+
1573
+ '248E' # ⒎ [DIGIT SEVEN FULL STOP]
1574
+ ] => '7.',
1575
+ [
1576
+
1577
+ '247A' # ⑺ [PARENTHESIZED DIGIT SEVEN]
1578
+ ] => '(7=)',
1579
+ [
1580
+
1581
+ '2078', # ⁸ [SUPERSCRIPT EIGHT]
1582
+ '2088', # ₈ [SUBSCRIPT EIGHT]
1583
+ '2467', # ⑧ [CIRCLED DIGIT EIGHT]
1584
+ '24FC', # ⓼ [DOUBLE CIRCLED DIGIT EIGHT]
1585
+ '277D', # ❽ [DINGBAT NEGATIVE CIRCLED DIGIT EIGHT]
1586
+ '2787', # ➇ [DINGBAT CIRCLED SANS-SERIF DIGIT EIGHT]
1587
+ '2791', # ➑ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT EIGHT]
1588
+ 'FF18' # 8 [FULLWIDTH DIGIT EIGHT]
1589
+ ] => '8',
1590
+ [
1591
+
1592
+ '248F' # ⒏ [DIGIT EIGHT FULL STOP]
1593
+ ] => '8.',
1594
+ [
1595
+
1596
+ '247B' # ⑻ [PARENTHESIZED DIGIT EIGHT]
1597
+ ] => '(8)',
1598
+ [
1599
+
1600
+ '2079', # ⁹ [SUPERSCRIPT NINE]
1601
+ '2089', # ₉ [SUBSCRIPT NINE]
1602
+ '2468', # ⑨ [CIRCLED DIGIT NINE]
1603
+ '24FD', # ⓽ [DOUBLE CIRCLED DIGIT NINE]
1604
+ '277E', # ❾ [DINGBAT NEGATIVE CIRCLED DIGIT NINE]
1605
+ '2788', # ➈ [DINGBAT CIRCLED SANS-SERIF DIGIT NINE]
1606
+ '2792', # ➒ [DINGBAT NEGATIVE CIRCLED SANS-SERIF DIGIT NINE]
1607
+ 'FF19' # 9 [FULLWIDTH DIGIT NINE]
1608
+ ] => '9',
1609
+ [
1610
+
1611
+ '2490' # ⒐ [DIGIT NINE FULL STOP]
1612
+ ] => '9.',
1613
+ [
1614
+
1615
+ '247C' # ⑼ [PARENTHESIZED DIGIT NINE]
1616
+ ] => '(9)',
1617
+ [
1618
+
1619
+ '2469', # ⑩ [CIRCLED NUMBER TEN]
1620
+ '24FE', # ⓾ [DOUBLE CIRCLED NUMBER TEN]
1621
+ '277F', # ❿ [DINGBAT NEGATIVE CIRCLED NUMBER TEN]
1622
+ '2789', # ➉ [DINGBAT CIRCLED SANS-SERIF NUMBER TEN]
1623
+ '2793' # ➓ [DINGBAT NEGATIVE CIRCLED SANS-SERIF NUMBER TEN]
1624
+ ] => '10',
1625
+ [
1626
+
1627
+ '2491' # ⒑ [NUMBER TEN FULL STOP]
1628
+ ] => '10.',
1629
+ [
1630
+
1631
+ '247D' # ⑽ [PARENTHESIZED NUMBER TEN]
1632
+ ] => '(10)',
1633
+ [
1634
+
1635
+ '246A', # ⑪ [CIRCLED NUMBER ELEVEN]
1636
+ '24EB' # ⓫ [NEGATIVE CIRCLED NUMBER ELEVEN]
1637
+ ] => '11',
1638
+ [
1639
+
1640
+ '2492' # ⒒ [NUMBER ELEVEN FULL STOP]
1641
+ ] => '11.',
1642
+ [
1643
+
1644
+ '247E' # ⑾ [PARENTHESIZED NUMBER ELEVEN]
1645
+ ] => '(11)',
1646
+ [
1647
+
1648
+ '246B', # ⑫ [CIRCLED NUMBER TWELVE]
1649
+ '24EC' # ⓬ [NEGATIVE CIRCLED NUMBER TWELVE]
1650
+ ] => '12',
1651
+ [
1652
+
1653
+ '2493' # ⒓ [NUMBER TWELVE FULL STOP]
1654
+ ] => '12.',
1655
+ [
1656
+
1657
+ '247F' # ⑿ [PARENTHESIZED NUMBER TWELVE]
1658
+ ] => '(12)',
1659
+ [
1660
+
1661
+ '246C', # ⑬ [CIRCLED NUMBER THIRTEEN]
1662
+ '24ED' # ⓭ [NEGATIVE CIRCLED NUMBER THIRTEEN]
1663
+ ] => '13',
1664
+ [
1665
+
1666
+ '2494' # ⒔ [NUMBER THIRTEEN FULL STOP]
1667
+ ] => '13.',
1668
+ [
1669
+
1670
+ '2480' # ⒀ [PARENTHESIZED NUMBER THIRTEEN]
1671
+ ] => '(13)',
1672
+ [
1673
+
1674
+ '246D', # ⑭ [CIRCLED NUMBER FOURTEEN]
1675
+ '24EE' # ⓮ [NEGATIVE CIRCLED NUMBER FOURTEEN]
1676
+ ] => '14',
1677
+ [
1678
+
1679
+ '2495' # ⒕ [NUMBER FOURTEEN FULL STOP]
1680
+ ] => '14.',
1681
+ [
1682
+
1683
+ '2481' # ⒁ [PARENTHESIZED NUMBER FOURTEEN]
1684
+ ] => '(14)',
1685
+ [
1686
+
1687
+ '246E', # ⑮ [CIRCLED NUMBER FIFTEEN]
1688
+ '24EF' # ⓯ [NEGATIVE CIRCLED NUMBER FIFTEEN]
1689
+ ] => '15',
1690
+ [
1691
+
1692
+ '2496' # ⒖ [NUMBER FIFTEEN FULL STOP]
1693
+ ] => '15.',
1694
+ [
1695
+
1696
+ '2482' # ⒂ [PARENTHESIZED NUMBER FIFTEEN]
1697
+ ] => '(15)',
1698
+ [
1699
+
1700
+ '246F', # ⑯ [CIRCLED NUMBER SIXTEEN]
1701
+ '24F0' # ⓰ [NEGATIVE CIRCLED NUMBER SIXTEEN]
1702
+ ] => '16',
1703
+ [
1704
+
1705
+ '2497' # ⒗ [NUMBER SIXTEEN FULL STOP]
1706
+ ] => '16.',
1707
+ [
1708
+
1709
+ '2483' # ⒃ [PARENTHESIZED NUMBER SIXTEEN]
1710
+ ] => '(16)',
1711
+ [
1712
+
1713
+ '2470', # ⑰ [CIRCLED NUMBER SEVENTEEN]
1714
+ '24F1' # ⓱ [NEGATIVE CIRCLED NUMBER SEVENTEEN]
1715
+ ] => '17',
1716
+ [
1717
+
1718
+ '2498' # ⒘ [NUMBER SEVENTEEN FULL STOP]
1719
+ ] => '17.',
1720
+ [
1721
+
1722
+ '2484' # ⒄ [PARENTHESIZED NUMBER SEVENTEEN]
1723
+ ] => '(17)',
1724
+ [
1725
+
1726
+ '2471', # ⑱ [CIRCLED NUMBER EIGHTEEN]
1727
+ '24F2' # ⓲ [NEGATIVE CIRCLED NUMBER EIGHTEEN]
1728
+ ] => '18',
1729
+ [
1730
+
1731
+ '2499' # ⒙ [NUMBER EIGHTEEN FULL STOP]
1732
+ ] => '18.',
1733
+ [
1734
+
1735
+ '2485' # ⒅ [PARENTHESIZED NUMBER EIGHTEEN]
1736
+ ] => '(18)',
1737
+ [
1738
+
1739
+ '2472', # ⑲ [CIRCLED NUMBER NINETEEN]
1740
+ '24F3' # ⓳ [NEGATIVE CIRCLED NUMBER NINETEEN]
1741
+ ] => '19',
1742
+ [
1743
+
1744
+ '249A' # ⒚ [NUMBER NINETEEN FULL STOP]
1745
+ ] => '19.',
1746
+ [
1747
+
1748
+ '2486' # ⒆ [PARENTHESIZED NUMBER NINETEEN]
1749
+ ] => '(19)',
1750
+ [
1751
+
1752
+ '2473', # ⑳ [CIRCLED NUMBER TWENTY]
1753
+ '24F4' # ⓴ [NEGATIVE CIRCLED NUMBER TWENTY]
1754
+ ] => '20',
1755
+ [
1756
+
1757
+ '249B' # ⒛ [NUMBER TWENTY FULL STOP]
1758
+ ] => '20.',
1759
+ [
1760
+
1761
+ '2487' # ⒇ [PARENTHESIZED NUMBER TWENTY]
1762
+ ] => '(20)',
1763
+ [
1764
+
1765
+ '00AB', # « [LEFT-POINTING DOUBLE ANGLE QUOTATION MARK]
1766
+ '00BB', # » [RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK]
1767
+ '201C', # “ [LEFT DOUBLE QUOTATION MARK]
1768
+ '201D', # ” [RIGHT DOUBLE QUOTATION MARK]
1769
+ '201E', # „ [DOUBLE LOW-9 QUOTATION MARK]
1770
+ '2033', # ″ [DOUBLE PRIME]
1771
+ '2036', # ‶ [REVERSED DOUBLE PRIME]
1772
+ '275D', # ❝ [HEAVY DOUBLE TURNED COMMA QUOTATION MARK ORNAMENT]
1773
+ '275E', # ❞ [HEAVY DOUBLE COMMA QUOTATION MARK ORNAMENT]
1774
+ '276E', # ❮ [HEAVY LEFT-POINTING ANGLE QUOTATION MARK ORNAMENT]
1775
+ '276F', # ❯ [HEAVY RIGHT-POINTING ANGLE QUOTATION MARK ORNAMENT]
1776
+ 'FF02' # " [FULLWIDTH QUOTATION MARK]
1777
+ ] => '"',
1778
+ [
1779
+
1780
+ '2018', # ‘ [LEFT SINGLE QUOTATION MARK]
1781
+ '2019', # ’ [RIGHT SINGLE QUOTATION MARK]
1782
+ '201A', # ‚ [SINGLE LOW-9 QUOTATION MARK]
1783
+ '201B', # ‛ [SINGLE HIGH-REVERSED-9 QUOTATION MARK]
1784
+ '2032', # ′ [PRIME]
1785
+ '2035', # ‵ [REVERSED PRIME]
1786
+ '2039', # ‹ [SINGLE LEFT-POINTING ANGLE QUOTATION MARK]
1787
+ '203A', # › [SINGLE RIGHT-POINTING ANGLE QUOTATION MARK]
1788
+ '275B', # ❛ [HEAVY SINGLE TURNED COMMA QUOTATION MARK ORNAMENT]
1789
+ '275C', # ❜ [HEAVY SINGLE COMMA QUOTATION MARK ORNAMENT]
1790
+ 'FF07' # ' [FULLWIDTH APOSTROPHE]
1791
+ ] => '\'',
1792
+ [
1793
+
1794
+ '2010', # ‐ [HYPHEN]
1795
+ '2011', # ‑ [NON-BREAKING HYPHEN]
1796
+ '2012', # ‒ [FIGURE DASH]
1797
+ '2013', # – [EN DASH]
1798
+ '2014', # — [EM DASH]
1799
+ '207B', # ⁻ [SUPERSCRIPT MINUS]
1800
+ '208B', # ₋ [SUBSCRIPT MINUS]
1801
+ 'FF0D' # - [FULLWIDTH HYPHEN-MINUS]
1802
+ ] => '-',
1803
+ [
1804
+
1805
+ '2045', # ⁅ [LEFT SQUARE BRACKET WITH QUILL]
1806
+ '2772', # ❲ [LIGHT LEFT TORTOISE SHELL BRACKET ORNAMENT]
1807
+ 'FF3B' # [ [FULLWIDTH LEFT SQUARE BRACKET]
1808
+ ] => '[',
1809
+ [
1810
+
1811
+ '2046', # ⁆ [RIGHT SQUARE BRACKET WITH QUILL]
1812
+ '2773', # ❳ [LIGHT RIGHT TORTOISE SHELL BRACKET ORNAMENT]
1813
+ 'FF3D' # ] [FULLWIDTH RIGHT SQUARE BRACKET]
1814
+ ] => ']',
1815
+ [
1816
+
1817
+ '207D', # ⁽ [SUPERSCRIPT LEFT PARENTHESIS]
1818
+ '208D', # ₍ [SUBSCRIPT LEFT PARENTHESIS]
1819
+ '2768', # ❨ [MEDIUM LEFT PARENTHESIS ORNAMENT]
1820
+ '276A', # ❪ [MEDIUM FLATTENED LEFT PARENTHESIS ORNAMENT]
1821
+ 'FF08' # ( [FULLWIDTH LEFT PARENTHESIS]
1822
+ ] => '(',
1823
+ [
1824
+
1825
+ '2E28' # ⸨ [LEFT DOUBLE PARENTHESIS]
1826
+ ] => '((',
1827
+ [
1828
+
1829
+ '207E', # ⁾ [SUPERSCRIPT RIGHT PARENTHESIS]
1830
+ '208E', # ₎ [SUBSCRIPT RIGHT PARENTHESIS]
1831
+ '2769', # ❩ [MEDIUM RIGHT PARENTHESIS ORNAMENT]
1832
+ '276B', # ❫ [MEDIUM FLATTENED RIGHT PARENTHESIS ORNAMENT]
1833
+ 'FF09' # ) [FULLWIDTH RIGHT PARENTHESIS]
1834
+ ] => ')',
1835
+ [
1836
+
1837
+ '2E29' # ⸩ [RIGHT DOUBLE PARENTHESIS]
1838
+ ] => '))',
1839
+ [
1840
+
1841
+ '276C', # ❬ [MEDIUM LEFT-POINTING ANGLE BRACKET ORNAMENT]
1842
+ '2770', # ❰ [HEAVY LEFT-POINTING ANGLE BRACKET ORNAMENT]
1843
+ 'FF1C' # < [FULLWIDTH LESS-THAN SIGN]
1844
+ ] => '<',
1845
+ [
1846
+
1847
+ '276D', # ❭ [MEDIUM RIGHT-POINTING ANGLE BRACKET ORNAMENT]
1848
+ '2771', # ❱ [HEAVY RIGHT-POINTING ANGLE BRACKET ORNAMENT]
1849
+ 'FF1E' # > [FULLWIDTH GREATER-THAN SIGN]
1850
+ ] => '>',
1851
+ [
1852
+
1853
+ '2774', # ❴ [MEDIUM LEFT CURLY BRACKET ORNAMENT]
1854
+ 'FF5B' # { [FULLWIDTH LEFT CURLY BRACKET]
1855
+ ] => '{',
1856
+ [
1857
+
1858
+ '2775', # ❵ [MEDIUM RIGHT CURLY BRACKET ORNAMENT]
1859
+ 'FF5D' # } [FULLWIDTH RIGHT CURLY BRACKET]
1860
+ ] => '}',
1861
+ [
1862
+
1863
+ '207A', # ⁺ [SUPERSCRIPT PLUS SIGN]
1864
+ '208A', # ₊ [SUBSCRIPT PLUS SIGN]
1865
+ 'FF0B' # + [FULLWIDTH PLUS SIGN]
1866
+ ] => '+',
1867
+ [
1868
+
1869
+ '207C', # ⁼ [SUPERSCRIPT EQUALS SIGN]
1870
+ '208C', # ₌ [SUBSCRIPT EQUALS SIGN]
1871
+ 'FF1D' # = [FULLWIDTH EQUALS SIGN]
1872
+ ] => '=',
1873
+ [
1874
+
1875
+ 'FF01' # ! [FULLWIDTH EXCLAMATION MARK]
1876
+ ] => '!',
1877
+ [
1878
+
1879
+ '203C' # ‼ [DOUBLE EXCLAMATION MARK]
1880
+ ] => '!!',
1881
+ [
1882
+
1883
+ '2049' # ⁉ [EXCLAMATION QUESTION MARK]
1884
+ ] => '!?',
1885
+ [
1886
+
1887
+ 'FF03' # # [FULLWIDTH NUMBER SIGN]
1888
+ ] => '#',
1889
+ [
1890
+
1891
+ 'FF04' # $ [FULLWIDTH DOLLAR SIGN]
1892
+ ] => '$',
1893
+ [
1894
+
1895
+ '2052', # ⁒ [COMMERCIAL MINUS SIGN]
1896
+ 'FF05' # % [FULLWIDTH PERCENT SIGN]
1897
+ ] => '%',
1898
+ [
1899
+
1900
+ 'FF06' # & [FULLWIDTH AMPERSAND]
1901
+ ] => '&',
1902
+ [
1903
+
1904
+ '204E', # ⁎ [LOW ASTERISK]
1905
+ 'FF0A' # * [FULLWIDTH ASTERISK]
1906
+ ] => '*',
1907
+ [
1908
+
1909
+ 'FF0C' # , [FULLWIDTH COMMA]
1910
+ ] => ',',
1911
+ [
1912
+
1913
+ 'FF0E' # . [FULLWIDTH FULL STOP]
1914
+ ] => '.',
1915
+ [
1916
+
1917
+ '2044', # ⁄ [FRACTION SLASH]
1918
+ 'FF0F' # / [FULLWIDTH SOLIDUS]
1919
+ ] => '/',
1920
+ [
1921
+
1922
+ 'FF1A' # : [FULLWIDTH COLON]
1923
+ ] => ':',
1924
+ [
1925
+
1926
+ '204F', # ⁏ [REVERSED SEMICOLON]
1927
+ 'FF1B' # ; [FULLWIDTH SEMICOLON]
1928
+ ] => ';',
1929
+ [
1930
+
1931
+ 'FF1F' # ? [FULLWIDTH QUESTION MARK]
1932
+ ] => '?',
1933
+ [
1934
+
1935
+ '2047' # ⁇ [DOUBLE QUESTION MARK]
1936
+ ] => '??',
1937
+ [
1938
+
1939
+ '2048' # ⁈ [QUESTION EXCLAMATION MARK]
1940
+ ] => '?!',
1941
+ [
1942
+
1943
+ 'FF20' # @ [FULLWIDTH COMMERCIAL AT]
1944
+ ] => '@',
1945
+ [
1946
+
1947
+ 'FF3C' # \ [FULLWIDTH REVERSE SOLIDUS]
1948
+ ] => '\\',
1949
+ [
1950
+
1951
+ '2038', # ‸ [CARET]
1952
+ 'FF3E' # ^ [FULLWIDTH CIRCUMFLEX ACCENT]
1953
+ ] => '^',
1954
+ [
1955
+
1956
+ 'FF3F' # _ [FULLWIDTH LOW LINE]
1957
+ ] => '_',
1958
+ [
1959
+
1960
+ '2053', # ⁓ [SWUNG DASH]
1961
+ 'FF5E' # ~ [FULLWIDTH TILDE]
1962
+ ] => '~'
1963
+
1964
+ })
1965
+
1966
+
1967
+ def self.convert s
1968
+ s.unpack("U*").map do |unicode_code_point|
1969
+ UNICODE_TO_ASCII[unicode_code_point] || unicode_code_point
1970
+ end.flatten.pack("U*").downcase unless s.nil?
1971
+ end
1972
+ end