CoCalc provides the best real-time collaborative environment for Jupyter Notebooks, LaTeX documents, and SageMath, scalable from individual users to large groups and classes!

1
# This  software is Copyright (c) 2012-2020 magnum, and it is hereby
2
# released to the general public under the following terms:
3
# Redistribution and use in source and binary forms, with or without
4
# modification, are permitted.
5
#
6
# Generic implementation of "dumb" exhaustive search of FULL Unicode.
7
# Default is to try *all* allocated characters in Unicode v13 (there's
8
# 143,532 of them). Even if a fast format can exhaust two characters in one
9
# hour, three characters would take 12 years...
10
#
11
# Note that these modes will handle --max-len differently than normal: They
12
# will consider number of characters as opposed to number of bytes. This
13
# means you can naturally just use e.g. --max-len=3 for generating all
14
# three-character candidates (which may be up to 12 bytes each).
15
#
16
# Also note that for UTF-16 formats, the resulting plaintext size within the
17
# format will be up to four bytes (two 16-bit words) due to use of surrogates
18
# for characters above U+FFFF. This means a format which normally handles up
19
# to 27 characters may be limited to only 13 characters, worst case.
20
#
21
# Note that the (newer) cracking mode --subsets=full-unicode is way faster than
22
# this external mode, although not as easy to adapt to smaller portions of the
23
# Unicode space.  See doc/SUBSETS
24

25
[List.External:Dumb32]
26
int maxlength;            // Maximum password length to try
27
int last;                 // Last character position, zero-based
28
int lastid;               // Character index in the last position
29
int id[0x7f];             // Current character indices for other positions
30
int charset[0x24000], c0; // Characters
31

32
void init()
33
{
34
	int minlength;
35
	int i, c;
36

37
	# Trigger UTF-32 handling in External mode
38
	utf32 = 1;
39

40
	if (req_minlen)
41
		minlength = req_minlen;
42
	else
43
		minlength = 1;
44
	if (req_maxlen)
45
		maxlength = req_maxlen;
46
	else
47
		maxlength = 2;
48

49
/*
50
 * This defines the character set. This is auto-generated from UnicodeData.txt
51
 * and we skip control characters.
52
 */
53
	i = 0;
54
// 0000..007F; Basic Latin
55
	c = 0x20;		// from SPACE
56
	while (c <= 0x7e)	// ..to TILDE
57
		charset[i++] = c++;
58
// 0080..00FF; Latin-1 Supplement
59
	c = 0xa0;		// from NO-BREAK SPACE
60
	while (c <= 0xff)	// ..to LATIN SMALL LETTER Y WITH DIAERESIS
61
		charset[i++] = c++;
62
// 0100..017F; Latin Extended-A
63
	c = 0x100;		// from LATIN CAPITAL LETTER A WITH MACRON
64
	while (c <= 0x17f)	// ..to LATIN SMALL LETTER LONG S
65
		charset[i++] = c++;
66
// 0180..024F; Latin Extended-B
67
	c = 0x180;		// from LATIN SMALL LETTER B WITH STROKE
68
	while (c <= 0x24f)	// ..to LATIN SMALL LETTER Y WITH STROKE
69
		charset[i++] = c++;
70
// 0250..02AF; IPA Extensions
71
	c = 0x250;		// from LATIN SMALL LETTER TURNED A
72
	while (c <= 0x2af)	// ..to LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL
73
		charset[i++] = c++;
74
// 02B0..02FF; Spacing Modifier Letters
75
	c = 0x2b0;		// from MODIFIER LETTER SMALL H
76
	while (c <= 0x2ff)	// ..to MODIFIER LETTER LOW LEFT ARROW
77
		charset[i++] = c++;
78
// 0300..036F; Combining Diacritical Marks
79
	c = 0x300;		// from COMBINING GRAVE ACCENT
80
	while (c <= 0x36f)	// ..to COMBINING LATIN SMALL LETTER X
81
		charset[i++] = c++;
82
// 0370..03FF; Greek and Coptic
83
	c = 0x370;		// from GREEK CAPITAL LETTER HETA
84
	while (c <= 0x377)	// ..to GREEK SMALL LETTER PAMPHYLIAN DIGAMMA
85
		charset[i++] = c++;
86
	c = 0x37a;		// from GREEK YPOGEGRAMMENI
87
	while (c <= 0x37f)	// ..to GREEK CAPITAL LETTER YOT
88
		charset[i++] = c++;
89
	c = 0x384;		// from GREEK TONOS
90
	while (c <= 0x38a)	// ..to GREEK CAPITAL LETTER IOTA WITH TONOS
91
		charset[i++] = c++;
92
	c = 0x38e;		// from GREEK CAPITAL LETTER UPSILON WITH TONOS
93
	while (c <= 0x3a1)	// ..to GREEK CAPITAL LETTER RHO
94
		charset[i++] = c++;
95
	c = 0x3a3;		// from GREEK CAPITAL LETTER SIGMA
96
	while (c <= 0x3ff)	// ..to GREEK CAPITAL REVERSED DOTTED LUNATE SIGMA SYMBOL
97
		charset[i++] = c++;
98
// 0400..04FF; Cyrillic
99
	c = 0x400;		// from CYRILLIC CAPITAL LETTER IE WITH GRAVE
100
	while (c <= 0x4ff)	// ..to CYRILLIC SMALL LETTER HA WITH STROKE
101
		charset[i++] = c++;
102
// 0500..052F; Cyrillic Supplement
103
	c = 0x500;		// from CYRILLIC CAPITAL LETTER KOMI DE
104
	while (c <= 0x52f)	// ..to CYRILLIC SMALL LETTER EL WITH DESCENDER
105
		charset[i++] = c++;
106
// 0530..058F; Armenian
107
	c = 0x531;		// from ARMENIAN CAPITAL LETTER AYB
108
	while (c <= 0x556)	// ..to ARMENIAN CAPITAL LETTER FEH
109
		charset[i++] = c++;
110
	c = 0x559;		// from ARMENIAN MODIFIER LETTER LEFT HALF RING
111
	while (c <= 0x58a)	// ..to ARMENIAN HYPHEN
112
		charset[i++] = c++;
113
	charset[i++] = 0x58d;	// RIGHT-FACING ARMENIAN ETERNITY SIGN
114
	charset[i++] = 0x58f;	// ARMENIAN DRAM SIGN
115
// 0590..05FF; Hebrew
116
	c = 0x591;		// from HEBREW ACCENT ETNAHTA
117
	while (c <= 0x5c7)	// ..to HEBREW POINT QAMATS QATAN
118
		charset[i++] = c++;
119
	c = 0x5d0;		// from HEBREW LETTER ALEF
120
	while (c <= 0x5ea)	// ..to HEBREW LETTER TAV
121
		charset[i++] = c++;
122
	c = 0x5ef;		// from HEBREW YOD TRIANGLE
123
	while (c <= 0x5f4)	// ..to HEBREW PUNCTUATION GERSHAYIM
124
		charset[i++] = c++;
125
// 0600..06FF; Arabic
126
	c = 0x600;		// from ARABIC NUMBER SIGN
127
	while (c <= 0x61c)	// ..to ARABIC LETTER MARK
128
		charset[i++] = c++;
129
	c = 0x61e;		// from ARABIC TRIPLE DOT PUNCTUATION MARK
130
	while (c <= 0x6ff)	// ..to ARABIC LETTER HEH WITH INVERTED V
131
		charset[i++] = c++;
132
// 0700..074F; Syriac
133
	c = 0x700;		// from SYRIAC END OF PARAGRAPH
134
	while (c <= 0x70d)	// ..to SYRIAC HARKLEAN ASTERISCUS
135
		charset[i++] = c++;
136
	c = 0x70f;		// from SYRIAC ABBREVIATION MARK
137
	while (c <= 0x74a)	// ..to SYRIAC BARREKH
138
		charset[i++] = c++;
139
	charset[i++] = 0x74d;	// SYRIAC LETTER SOGDIAN ZHAIN
140
	charset[i++] = 0x74f;	// SYRIAC LETTER SOGDIAN FE
141
// 0750..077F; Arabic Supplement
142
	c = 0x750;		// from ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW
143
	while (c <= 0x77f)	// ..to ARABIC LETTER KAF WITH TWO DOTS ABOVE
144
		charset[i++] = c++;
145
// 0780..07BF; Thaana
146
	c = 0x780;		// from THAANA LETTER HAA
147
	while (c <= 0x7b1)	// ..to THAANA LETTER NAA
148
		charset[i++] = c++;
149
// 07C0..07FF; NKo
150
	c = 0x7c0;		// from NKO DIGIT ZERO
151
	while (c <= 0x7fa)	// ..to NKO LAJANYALAN
152
		charset[i++] = c++;
153
	charset[i++] = 0x7fd;	// NKO DANTAYALAN
154
	charset[i++] = 0x7ff;	// NKO TAMAN SIGN
155
// 0800..083F; Samaritan
156
	c = 0x800;		// from SAMARITAN LETTER ALAF
157
	while (c <= 0x82d)	// ..to SAMARITAN MARK NEQUDAA
158
		charset[i++] = c++;
159
	c = 0x830;		// from SAMARITAN PUNCTUATION NEQUDAA
160
	while (c <= 0x83e)	// ..to SAMARITAN PUNCTUATION ANNAAU
161
		charset[i++] = c++;
162
// 0840..085F; Mandaic
163
	c = 0x840;		// from MANDAIC LETTER HALQA
164
	while (c <= 0x85b)	// ..to MANDAIC GEMINATION MARK
165
		charset[i++] = c++;
166
	charset[i++] = 0x85e;	// MANDAIC PUNCTUATION
167
// 0860..086F; Syriac Supplement
168
	c = 0x860;		// from SYRIAC LETTER MALAYALAM NGA
169
	while (c <= 0x86a)	// ..to SYRIAC LETTER MALAYALAM SSA
170
		charset[i++] = c++;
171
// 08A0..08FF; Arabic Extended-A
172
	c = 0x8a0;		// from ARABIC LETTER BEH WITH SMALL V BELOW
173
	while (c <= 0x8b4)	// ..to ARABIC LETTER KAF WITH DOT BELOW
174
		charset[i++] = c++;
175
	c = 0x8b6;		// from ARABIC LETTER BEH WITH SMALL MEEM ABOVE
176
	while (c <= 0x8c7)	// ..to ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE
177
		charset[i++] = c++;
178
	c = 0x8d3;		// from ARABIC SMALL LOW WAW
179
	while (c <= 0x8ff)	// ..to ARABIC MARK SIDEWAYS NOON GHUNNA
180
		charset[i++] = c++;
181
// 0900..097F; Devanagari
182
	c = 0x900;		// from DEVANAGARI SIGN INVERTED CANDRABINDU
183
	while (c <= 0x97f)	// ..to DEVANAGARI LETTER BBA
184
		charset[i++] = c++;
185
// 0980..09FF; Bengali
186
	c = 0x980;		// from BENGALI ANJI
187
	while (c <= 0x983)	// ..to BENGALI SIGN VISARGA
188
		charset[i++] = c++;
189
	c = 0x985;		// from BENGALI LETTER A
190
	while (c <= 0x98c)	// ..to BENGALI LETTER VOCALIC L
191
		charset[i++] = c++;
192
	charset[i++] = 0x98f;	// BENGALI LETTER E
193
	charset[i++] = 0x990;	// BENGALI LETTER AI
194
	c = 0x993;		// from BENGALI LETTER O
195
	while (c <= 0x9a8)	// ..to BENGALI LETTER NA
196
		charset[i++] = c++;
197
	c = 0x9aa;		// from BENGALI LETTER PA
198
	while (c <= 0x9b0)	// ..to BENGALI LETTER RA
199
		charset[i++] = c++;
200
	c = 0x9b6;		// from BENGALI LETTER SHA
201
	while (c <= 0x9b9)	// ..to BENGALI LETTER HA
202
		charset[i++] = c++;
203
	c = 0x9bc;		// from BENGALI SIGN NUKTA
204
	while (c <= 0x9c4)	// ..to BENGALI VOWEL SIGN VOCALIC RR
205
		charset[i++] = c++;
206
	charset[i++] = 0x9c7;	// BENGALI VOWEL SIGN E
207
	charset[i++] = 0x9c8;	// BENGALI VOWEL SIGN AI
208
	c = 0x9cb;		// from BENGALI VOWEL SIGN O
209
	while (c <= 0x9ce)	// ..to BENGALI LETTER KHANDA TA
210
		charset[i++] = c++;
211
	charset[i++] = 0x9dc;	// BENGALI LETTER RRA
212
	charset[i++] = 0x9dd;	// BENGALI LETTER RHA
213
	c = 0x9df;		// from BENGALI LETTER YYA
214
	while (c <= 0x9e3)	// ..to BENGALI VOWEL SIGN VOCALIC LL
215
		charset[i++] = c++;
216
	c = 0x9e6;		// from BENGALI DIGIT ZERO
217
	while (c <= 0x9fe)	// ..to BENGALI SANDHI MARK
218
		charset[i++] = c++;
219
// 0A00..0A7F; Gurmukhi
220
	charset[i++] = 0xa01;	// GURMUKHI SIGN ADAK BINDI
221
	charset[i++] = 0xa03;	// GURMUKHI SIGN VISARGA
222
	c = 0xa05;		// from GURMUKHI LETTER A
223
	while (c <= 0xa0a)	// ..to GURMUKHI LETTER UU
224
		charset[i++] = c++;
225
	charset[i++] = 0xa0f;	// GURMUKHI LETTER EE
226
	charset[i++] = 0xa10;	// GURMUKHI LETTER AI
227
	c = 0xa13;		// from GURMUKHI LETTER OO
228
	while (c <= 0xa28)	// ..to GURMUKHI LETTER NA
229
		charset[i++] = c++;
230
	c = 0xa2a;		// from GURMUKHI LETTER PA
231
	while (c <= 0xa30)	// ..to GURMUKHI LETTER RA
232
		charset[i++] = c++;
233
	charset[i++] = 0xa32;	// GURMUKHI LETTER LA
234
	charset[i++] = 0xa33;	// GURMUKHI LETTER LLA
235
	charset[i++] = 0xa35;	// GURMUKHI LETTER VA
236
	charset[i++] = 0xa36;	// GURMUKHI LETTER SHA
237
	charset[i++] = 0xa38;	// GURMUKHI LETTER SA
238
	charset[i++] = 0xa39;	// GURMUKHI LETTER HA
239
	c = 0xa3e;		// from GURMUKHI VOWEL SIGN AA
240
	while (c <= 0xa42)	// ..to GURMUKHI VOWEL SIGN UU
241
		charset[i++] = c++;
242
	charset[i++] = 0xa47;	// GURMUKHI VOWEL SIGN EE
243
	charset[i++] = 0xa48;	// GURMUKHI VOWEL SIGN AI
244
	charset[i++] = 0xa4b;	// GURMUKHI VOWEL SIGN OO
245
	charset[i++] = 0xa4d;	// GURMUKHI SIGN VIRAMA
246
	c = 0xa59;		// from GURMUKHI LETTER KHHA
247
	while (c <= 0xa5c)	// ..to GURMUKHI LETTER RRA
248
		charset[i++] = c++;
249
	c = 0xa66;		// from GURMUKHI DIGIT ZERO
250
	while (c <= 0xa76)	// ..to GURMUKHI ABBREVIATION SIGN
251
		charset[i++] = c++;
252
// 0A80..0AFF; Gujarati
253
	charset[i++] = 0xa81;	// GUJARATI SIGN CANDRABINDU
254
	charset[i++] = 0xa83;	// GUJARATI SIGN VISARGA
255
	c = 0xa85;		// from GUJARATI LETTER A
256
	while (c <= 0xa8d)	// ..to GUJARATI VOWEL CANDRA E
257
		charset[i++] = c++;
258
	charset[i++] = 0xa8f;	// GUJARATI LETTER E
259
	charset[i++] = 0xa91;	// GUJARATI VOWEL CANDRA O
260
	c = 0xa93;		// from GUJARATI LETTER O
261
	while (c <= 0xaa8)	// ..to GUJARATI LETTER NA
262
		charset[i++] = c++;
263
	c = 0xaaa;		// from GUJARATI LETTER PA
264
	while (c <= 0xab0)	// ..to GUJARATI LETTER RA
265
		charset[i++] = c++;
266
	charset[i++] = 0xab2;	// GUJARATI LETTER LA
267
	charset[i++] = 0xab3;	// GUJARATI LETTER LLA
268
	c = 0xab5;		// from GUJARATI LETTER VA
269
	while (c <= 0xab9)	// ..to GUJARATI LETTER HA
270
		charset[i++] = c++;
271
	c = 0xabc;		// from GUJARATI SIGN NUKTA
272
	while (c <= 0xac5)	// ..to GUJARATI VOWEL SIGN CANDRA E
273
		charset[i++] = c++;
274
	charset[i++] = 0xac7;	// GUJARATI VOWEL SIGN E
275
	charset[i++] = 0xac9;	// GUJARATI VOWEL SIGN CANDRA O
276
	charset[i++] = 0xacb;	// GUJARATI VOWEL SIGN O
277
	charset[i++] = 0xacd;	// GUJARATI SIGN VIRAMA
278
	c = 0xae0;		// from GUJARATI LETTER VOCALIC RR
279
	while (c <= 0xae3)	// ..to GUJARATI VOWEL SIGN VOCALIC LL
280
		charset[i++] = c++;
281
	c = 0xae6;		// from GUJARATI DIGIT ZERO
282
	while (c <= 0xaf1)	// ..to GUJARATI RUPEE SIGN
283
		charset[i++] = c++;
284
	c = 0xaf9;		// from GUJARATI LETTER ZHA
285
	while (c <= 0xaff)	// ..to GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
286
		charset[i++] = c++;
287
// 0B00..0B7F; Oriya
288
	charset[i++] = 0xb01;	// ORIYA SIGN CANDRABINDU
289
	charset[i++] = 0xb03;	// ORIYA SIGN VISARGA
290
	c = 0xb05;		// from ORIYA LETTER A
291
	while (c <= 0xb0c)	// ..to ORIYA LETTER VOCALIC L
292
		charset[i++] = c++;
293
	charset[i++] = 0xb0f;	// ORIYA LETTER E
294
	charset[i++] = 0xb10;	// ORIYA LETTER AI
295
	c = 0xb13;		// from ORIYA LETTER O
296
	while (c <= 0xb28)	// ..to ORIYA LETTER NA
297
		charset[i++] = c++;
298
	c = 0xb2a;		// from ORIYA LETTER PA
299
	while (c <= 0xb30)	// ..to ORIYA LETTER RA
300
		charset[i++] = c++;
301
	charset[i++] = 0xb32;	// ORIYA LETTER LA
302
	charset[i++] = 0xb33;	// ORIYA LETTER LLA
303
	c = 0xb35;		// from ORIYA LETTER VA
304
	while (c <= 0xb39)	// ..to ORIYA LETTER HA
305
		charset[i++] = c++;
306
	c = 0xb3c;		// from ORIYA SIGN NUKTA
307
	while (c <= 0xb44)	// ..to ORIYA VOWEL SIGN VOCALIC RR
308
		charset[i++] = c++;
309
	charset[i++] = 0xb47;	// ORIYA VOWEL SIGN E
310
	charset[i++] = 0xb48;	// ORIYA VOWEL SIGN AI
311
	charset[i++] = 0xb4b;	// ORIYA VOWEL SIGN O
312
	charset[i++] = 0xb4d;	// ORIYA SIGN VIRAMA
313
	charset[i++] = 0xb55;	// ORIYA SIGN OVERLINE
314
	charset[i++] = 0xb57;	// ORIYA AU LENGTH MARK
315
	charset[i++] = 0xb5c;	// ORIYA LETTER RRA
316
	charset[i++] = 0xb5d;	// ORIYA LETTER RHA
317
	c = 0xb5f;		// from ORIYA LETTER YYA
318
	while (c <= 0xb63)	// ..to ORIYA VOWEL SIGN VOCALIC LL
319
		charset[i++] = c++;
320
	c = 0xb66;		// from ORIYA DIGIT ZERO
321
	while (c <= 0xb77)	// ..to ORIYA FRACTION THREE SIXTEENTHS
322
		charset[i++] = c++;
323
// 0B80..0BFF; Tamil
324
	charset[i++] = 0xb82;	// TAMIL SIGN ANUSVARA
325
	charset[i++] = 0xb83;	// TAMIL SIGN VISARGA
326
	c = 0xb85;		// from TAMIL LETTER A
327
	while (c <= 0xb8a)	// ..to TAMIL LETTER UU
328
		charset[i++] = c++;
329
	charset[i++] = 0xb8e;	// TAMIL LETTER E
330
	charset[i++] = 0xb90;	// TAMIL LETTER AI
331
	c = 0xb92;		// from TAMIL LETTER O
332
	while (c <= 0xb95)	// ..to TAMIL LETTER KA
333
		charset[i++] = c++;
334
	charset[i++] = 0xb99;	// TAMIL LETTER NGA
335
	charset[i++] = 0xb9a;	// TAMIL LETTER CA
336
	charset[i++] = 0xb9e;	// TAMIL LETTER NYA
337
	charset[i++] = 0xb9f;	// TAMIL LETTER TTA
338
	charset[i++] = 0xba3;	// TAMIL LETTER NNA
339
	charset[i++] = 0xba4;	// TAMIL LETTER TA
340
	charset[i++] = 0xba8;	// TAMIL LETTER NA
341
	charset[i++] = 0xbaa;	// TAMIL LETTER PA
342
	c = 0xbae;		// from TAMIL LETTER MA
343
	while (c <= 0xbb9)	// ..to TAMIL LETTER HA
344
		charset[i++] = c++;
345
	c = 0xbbe;		// from TAMIL VOWEL SIGN AA
346
	while (c <= 0xbc2)	// ..to TAMIL VOWEL SIGN UU
347
		charset[i++] = c++;
348
	charset[i++] = 0xbc6;	// TAMIL VOWEL SIGN E
349
	charset[i++] = 0xbc8;	// TAMIL VOWEL SIGN AI
350
	c = 0xbca;		// from TAMIL VOWEL SIGN O
351
	while (c <= 0xbcd)	// ..to TAMIL SIGN VIRAMA
352
		charset[i++] = c++;
353
	c = 0xbe6;		// from TAMIL DIGIT ZERO
354
	while (c <= 0xbfa)	// ..to TAMIL NUMBER SIGN
355
		charset[i++] = c++;
356
// 0C00..0C7F; Telugu
357
	c = 0xc00;		// from TELUGU SIGN COMBINING CANDRABINDU ABOVE
358
	while (c <= 0xc0c)	// ..to TELUGU LETTER VOCALIC L
359
		charset[i++] = c++;
360
	charset[i++] = 0xc0e;	// TELUGU LETTER E
361
	charset[i++] = 0xc10;	// TELUGU LETTER AI
362
	c = 0xc12;		// from TELUGU LETTER O
363
	while (c <= 0xc28)	// ..to TELUGU LETTER NA
364
		charset[i++] = c++;
365
	c = 0xc2a;		// from TELUGU LETTER PA
366
	while (c <= 0xc39)	// ..to TELUGU LETTER HA
367
		charset[i++] = c++;
368
	c = 0xc3d;		// from TELUGU SIGN AVAGRAHA
369
	while (c <= 0xc44)	// ..to TELUGU VOWEL SIGN VOCALIC RR
370
		charset[i++] = c++;
371
	charset[i++] = 0xc46;	// TELUGU VOWEL SIGN E
372
	charset[i++] = 0xc48;	// TELUGU VOWEL SIGN AI
373
	c = 0xc4a;		// from TELUGU VOWEL SIGN O
374
	while (c <= 0xc4d)	// ..to TELUGU SIGN VIRAMA
375
		charset[i++] = c++;
376
	charset[i++] = 0xc55;	// TELUGU LENGTH MARK
377
	charset[i++] = 0xc56;	// TELUGU AI LENGTH MARK
378
	charset[i++] = 0xc58;	// TELUGU LETTER TSA
379
	charset[i++] = 0xc5a;	// TELUGU LETTER RRRA
380
	c = 0xc60;		// from TELUGU LETTER VOCALIC RR
381
	while (c <= 0xc63)	// ..to TELUGU VOWEL SIGN VOCALIC LL
382
		charset[i++] = c++;
383
	c = 0xc66;		// from TELUGU DIGIT ZERO
384
	while (c <= 0xc6f)	// ..to TELUGU DIGIT NINE
385
		charset[i++] = c++;
386
	c = 0xc77;		// from TELUGU SIGN SIDDHAM
387
	while (c <= 0xc7f)	// ..to TELUGU SIGN TUUMU
388
		charset[i++] = c++;
389
// 0C80..0CFF; Kannada
390
	c = 0xc80;		// from KANNADA SIGN SPACING CANDRABINDU
391
	while (c <= 0xc8c)	// ..to KANNADA LETTER VOCALIC L
392
		charset[i++] = c++;
393
	charset[i++] = 0xc8e;	// KANNADA LETTER E
394
	charset[i++] = 0xc90;	// KANNADA LETTER AI
395
	c = 0xc92;		// from KANNADA LETTER O
396
	while (c <= 0xca8)	// ..to KANNADA LETTER NA
397
		charset[i++] = c++;
398
	c = 0xcaa;		// from KANNADA LETTER PA
399
	while (c <= 0xcb3)	// ..to KANNADA LETTER LLA
400
		charset[i++] = c++;
401
	c = 0xcb5;		// from KANNADA LETTER VA
402
	while (c <= 0xcb9)	// ..to KANNADA LETTER HA
403
		charset[i++] = c++;
404
	c = 0xcbc;		// from KANNADA SIGN NUKTA
405
	while (c <= 0xcc4)	// ..to KANNADA VOWEL SIGN VOCALIC RR
406
		charset[i++] = c++;
407
	charset[i++] = 0xcc6;	// KANNADA VOWEL SIGN E
408
	charset[i++] = 0xcc8;	// KANNADA VOWEL SIGN AI
409
	c = 0xcca;		// from KANNADA VOWEL SIGN O
410
	while (c <= 0xccd)	// ..to KANNADA SIGN VIRAMA
411
		charset[i++] = c++;
412
	charset[i++] = 0xcd5;	// KANNADA LENGTH MARK
413
	charset[i++] = 0xcd6;	// KANNADA AI LENGTH MARK
414
	c = 0xce0;		// from KANNADA LETTER VOCALIC RR
415
	while (c <= 0xce3)	// ..to KANNADA VOWEL SIGN VOCALIC LL
416
		charset[i++] = c++;
417
	c = 0xce6;		// from KANNADA DIGIT ZERO
418
	while (c <= 0xcef)	// ..to KANNADA DIGIT NINE
419
		charset[i++] = c++;
420
	charset[i++] = 0xcf1;	// KANNADA SIGN JIHVAMULIYA
421
	charset[i++] = 0xcf2;	// KANNADA SIGN UPADHMANIYA
422
// 0D00..0D7F; Malayalam
423
	c = 0xd00;		// from MALAYALAM SIGN COMBINING ANUSVARA ABOVE
424
	while (c <= 0xd0c)	// ..to MALAYALAM LETTER VOCALIC L
425
		charset[i++] = c++;
426
	charset[i++] = 0xd0e;	// MALAYALAM LETTER E
427
	charset[i++] = 0xd10;	// MALAYALAM LETTER AI
428
	c = 0xd12;		// from MALAYALAM LETTER O
429
	while (c <= 0xd44)	// ..to MALAYALAM VOWEL SIGN VOCALIC RR
430
		charset[i++] = c++;
431
	charset[i++] = 0xd46;	// MALAYALAM VOWEL SIGN E
432
	charset[i++] = 0xd48;	// MALAYALAM VOWEL SIGN AI
433
	c = 0xd4a;		// from MALAYALAM VOWEL SIGN O
434
	while (c <= 0xd4f)	// ..to MALAYALAM SIGN PARA
435
		charset[i++] = c++;
436
	c = 0xd54;		// from MALAYALAM LETTER CHILLU M
437
	while (c <= 0xd63)	// ..to MALAYALAM VOWEL SIGN VOCALIC LL
438
		charset[i++] = c++;
439
	c = 0xd66;		// from MALAYALAM DIGIT ZERO
440
	while (c <= 0xd7f)	// ..to MALAYALAM LETTER CHILLU K
441
		charset[i++] = c++;
442
// 0D80..0DFF; Sinhala
443
	charset[i++] = 0xd81;	// SINHALA SIGN CANDRABINDU
444
	charset[i++] = 0xd83;	// SINHALA SIGN VISARGAYA
445
	c = 0xd85;		// from SINHALA LETTER AYANNA
446
	while (c <= 0xd96)	// ..to SINHALA LETTER AUYANNA
447
		charset[i++] = c++;
448
	c = 0xd9a;		// from SINHALA LETTER ALPAPRAANA KAYANNA
449
	while (c <= 0xdb1)	// ..to SINHALA LETTER DANTAJA NAYANNA
450
		charset[i++] = c++;
451
	c = 0xdb3;		// from SINHALA LETTER SANYAKA DAYANNA
452
	while (c <= 0xdbb)	// ..to SINHALA LETTER RAYANNA
453
		charset[i++] = c++;
454
	c = 0xdc0;		// from SINHALA LETTER VAYANNA
455
	while (c <= 0xdc6)	// ..to SINHALA LETTER FAYANNA
456
		charset[i++] = c++;
457
	c = 0xdcf;		// from SINHALA VOWEL SIGN AELA-PILLA
458
	while (c <= 0xdd4)	// ..to SINHALA VOWEL SIGN KETTI PAA-PILLA
459
		charset[i++] = c++;
460
	c = 0xdd8;		// from SINHALA VOWEL SIGN GAETTA-PILLA
461
	while (c <= 0xddf)	// ..to SINHALA VOWEL SIGN GAYANUKITTA
462
		charset[i++] = c++;
463
	c = 0xde6;		// from SINHALA LITH DIGIT ZERO
464
	while (c <= 0xdef)	// ..to SINHALA LITH DIGIT NINE
465
		charset[i++] = c++;
466
	charset[i++] = 0xdf2;	// SINHALA VOWEL SIGN DIGA GAETTA-PILLA
467
	charset[i++] = 0xdf4;	// SINHALA PUNCTUATION KUNDDALIYA
468
// 0E00..0E7F; Thai
469
	c = 0xe01;		// from THAI CHARACTER KO KAI
470
	while (c <= 0xe3a)	// ..to THAI CHARACTER PHINTHU
471
		charset[i++] = c++;
472
	c = 0xe3f;		// from THAI CURRENCY SYMBOL BAHT
473
	while (c <= 0xe5b)	// ..to THAI CHARACTER KHOMUT
474
		charset[i++] = c++;
475
// 0E80..0EFF; Lao
476
	charset[i++] = 0xe81;	// LAO LETTER KO
477
	charset[i++] = 0xe82;	// LAO LETTER KHO SUNG
478
	c = 0xe86;		// from LAO LETTER PALI GHA
479
	while (c <= 0xe8a)	// ..to LAO LETTER SO TAM
480
		charset[i++] = c++;
481
	c = 0xe8c;		// from LAO LETTER PALI JHA
482
	while (c <= 0xea3)	// ..to LAO LETTER LO LING
483
		charset[i++] = c++;
484
	c = 0xea7;		// from LAO LETTER WO
485
	while (c <= 0xebd)	// ..to LAO SEMIVOWEL SIGN NYO
486
		charset[i++] = c++;
487
	c = 0xec0;		// from LAO VOWEL SIGN E
488
	while (c <= 0xec4)	// ..to LAO VOWEL SIGN AI
489
		charset[i++] = c++;
490
	c = 0xec8;		// from LAO TONE MAI EK
491
	while (c <= 0xecd)	// ..to LAO NIGGAHITA
492
		charset[i++] = c++;
493
	c = 0xed0;		// from LAO DIGIT ZERO
494
	while (c <= 0xed9)	// ..to LAO DIGIT NINE
495
		charset[i++] = c++;
496
	c = 0xedc;		// from LAO HO NO
497
	while (c <= 0xedf)	// ..to LAO LETTER KHMU NYO
498
		charset[i++] = c++;
499
// 0F00..0FFF; Tibetan
500
	c = 0xf00;		// from TIBETAN SYLLABLE OM
501
	while (c <= 0xf47)	// ..to TIBETAN LETTER JA
502
		charset[i++] = c++;
503
	c = 0xf49;		// from TIBETAN LETTER NYA
504
	while (c <= 0xf6c)	// ..to TIBETAN LETTER RRA
505
		charset[i++] = c++;
506
	c = 0xf71;		// from TIBETAN VOWEL SIGN AA
507
	while (c <= 0xf97)	// ..to TIBETAN SUBJOINED LETTER JA
508
		charset[i++] = c++;
509
	c = 0xf99;		// from TIBETAN SUBJOINED LETTER NYA
510
	while (c <= 0xfbc)	// ..to TIBETAN SUBJOINED LETTER FIXED-FORM RA
511
		charset[i++] = c++;
512
	c = 0xfbe;		// from TIBETAN KU RU KHA
513
	while (c <= 0xfcc)	// ..to TIBETAN SYMBOL NOR BU BZHI -KHYIL
514
		charset[i++] = c++;
515
	c = 0xfce;		// from TIBETAN SIGN RDEL NAG RDEL DKAR
516
	while (c <= 0xfda)	// ..to TIBETAN MARK TRAILING MCHAN RTAGS
517
		charset[i++] = c++;
518
// 1000..109F; Myanmar
519
	c = 0x1000;		// from MYANMAR LETTER KA
520
	while (c <= 0x109f)	// ..to MYANMAR SYMBOL SHAN EXCLAMATION
521
		charset[i++] = c++;
522
// 10A0..10FF; Georgian
523
	c = 0x10a0;		// from GEORGIAN CAPITAL LETTER AN
524
	while (c <= 0x10c5)	// ..to GEORGIAN CAPITAL LETTER HOE
525
		charset[i++] = c++;
526
	c = 0x10d0;		// from GEORGIAN LETTER AN
527
	while (c <= 0x10ff)	// ..to GEORGIAN LETTER LABIAL SIGN
528
		charset[i++] = c++;
529
// 1100..11FF; Hangul Jamo
530
	c = 0x1100;		// from HANGUL CHOSEONG KIYEOK
531
	while (c <= 0x11ff)	// ..to HANGUL JONGSEONG SSANGNIEUN
532
		charset[i++] = c++;
533
// 1200..137F; Ethiopic
534
	c = 0x1200;		// from ETHIOPIC SYLLABLE HA
535
	while (c <= 0x1248)	// ..to ETHIOPIC SYLLABLE QWA
536
		charset[i++] = c++;
537
	c = 0x124a;		// from ETHIOPIC SYLLABLE QWI
538
	while (c <= 0x124d)	// ..to ETHIOPIC SYLLABLE QWE
539
		charset[i++] = c++;
540
	c = 0x1250;		// from ETHIOPIC SYLLABLE QHA
541
	while (c <= 0x1256)	// ..to ETHIOPIC SYLLABLE QHO
542
		charset[i++] = c++;
543
	c = 0x125a;		// from ETHIOPIC SYLLABLE QHWI
544
	while (c <= 0x125d)	// ..to ETHIOPIC SYLLABLE QHWE
545
		charset[i++] = c++;
546
	c = 0x1260;		// from ETHIOPIC SYLLABLE BA
547
	while (c <= 0x1288)	// ..to ETHIOPIC SYLLABLE XWA
548
		charset[i++] = c++;
549
	c = 0x128a;		// from ETHIOPIC SYLLABLE XWI
550
	while (c <= 0x128d)	// ..to ETHIOPIC SYLLABLE XWE
551
		charset[i++] = c++;
552
	c = 0x1290;		// from ETHIOPIC SYLLABLE NA
553
	while (c <= 0x12b0)	// ..to ETHIOPIC SYLLABLE KWA
554
		charset[i++] = c++;
555
	c = 0x12b2;		// from ETHIOPIC SYLLABLE KWI
556
	while (c <= 0x12b5)	// ..to ETHIOPIC SYLLABLE KWE
557
		charset[i++] = c++;
558
	c = 0x12b8;		// from ETHIOPIC SYLLABLE KXA
559
	while (c <= 0x12be)	// ..to ETHIOPIC SYLLABLE KXO
560
		charset[i++] = c++;
561
	c = 0x12c2;		// from ETHIOPIC SYLLABLE KXWI
562
	while (c <= 0x12c5)	// ..to ETHIOPIC SYLLABLE KXWE
563
		charset[i++] = c++;
564
	c = 0x12c8;		// from ETHIOPIC SYLLABLE WA
565
	while (c <= 0x12d6)	// ..to ETHIOPIC SYLLABLE PHARYNGEAL O
566
		charset[i++] = c++;
567
	c = 0x12d8;		// from ETHIOPIC SYLLABLE ZA
568
	while (c <= 0x1310)	// ..to ETHIOPIC SYLLABLE GWA
569
		charset[i++] = c++;
570
	c = 0x1312;		// from ETHIOPIC SYLLABLE GWI
571
	while (c <= 0x1315)	// ..to ETHIOPIC SYLLABLE GWE
572
		charset[i++] = c++;
573
	c = 0x1318;		// from ETHIOPIC SYLLABLE GGA
574
	while (c <= 0x135a)	// ..to ETHIOPIC SYLLABLE FYA
575
		charset[i++] = c++;
576
	c = 0x135d;		// from ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK
577
	while (c <= 0x137c)	// ..to ETHIOPIC NUMBER TEN THOUSAND
578
		charset[i++] = c++;
579
// 1380..139F; Ethiopic Supplement
580
	c = 0x1380;		// from ETHIOPIC SYLLABLE SEBATBEIT MWA
581
	while (c <= 0x1399)	// ..to ETHIOPIC TONAL MARK KURT
582
		charset[i++] = c++;
583
// 13A0..13FF; Cherokee
584
	c = 0x13a0;		// from CHEROKEE LETTER A
585
	while (c <= 0x13f5)	// ..to CHEROKEE LETTER MV
586
		charset[i++] = c++;
587
	c = 0x13f8;		// from CHEROKEE SMALL LETTER YE
588
	while (c <= 0x13fd)	// ..to CHEROKEE SMALL LETTER MV
589
		charset[i++] = c++;
590
// 1400..167F; Unified Canadian Aboriginal Syllabics
591
	c = 0x1400;		// from CANADIAN SYLLABICS HYPHEN
592
	while (c <= 0x167f)	// ..to CANADIAN SYLLABICS BLACKFOOT W
593
		charset[i++] = c++;
594
// 1680..169F; Ogham
595
	c = 0x1680;		// from OGHAM SPACE MARK
596
	while (c <= 0x169c)	// ..to OGHAM REVERSED FEATHER MARK
597
		charset[i++] = c++;
598
// 16A0..16FF; Runic
599
	c = 0x16a0;		// from RUNIC LETTER FEHU FEOH FE F
600
	while (c <= 0x16f8)	// ..to RUNIC LETTER FRANKS CASKET AESC
601
		charset[i++] = c++;
602
// 1700..171F; Tagalog
603
	c = 0x1700;		// from TAGALOG LETTER A
604
	while (c <= 0x170c)	// ..to TAGALOG LETTER YA
605
		charset[i++] = c++;
606
	c = 0x170e;		// from TAGALOG LETTER LA
607
	while (c <= 0x1714)	// ..to TAGALOG SIGN VIRAMA
608
		charset[i++] = c++;
609
// 1720..173F; Hanunoo
610
	c = 0x1720;		// from HANUNOO LETTER A
611
	while (c <= 0x1736)	// ..to PHILIPPINE DOUBLE PUNCTUATION
612
		charset[i++] = c++;
613
// 1740..175F; Buhid
614
	c = 0x1740;		// from BUHID LETTER A
615
	while (c <= 0x1753)	// ..to BUHID VOWEL SIGN U
616
		charset[i++] = c++;
617
// 1760..177F; Tagbanwa
618
	c = 0x1760;		// from TAGBANWA LETTER A
619
	while (c <= 0x176c)	// ..to TAGBANWA LETTER YA
620
		charset[i++] = c++;
621
	charset[i++] = 0x176e;	// TAGBANWA LETTER LA
622
	charset[i++] = 0x1770;	// TAGBANWA LETTER SA
623
	charset[i++] = 0x1772;	// TAGBANWA VOWEL SIGN I
624
	charset[i++] = 0x1773;	// TAGBANWA VOWEL SIGN U
625
// 1780..17FF; Khmer
626
	c = 0x1780;		// from KHMER LETTER KA
627
	while (c <= 0x17dd)	// ..to KHMER SIGN ATTHACAN
628
		charset[i++] = c++;
629
	c = 0x17e0;		// from KHMER DIGIT ZERO
630
	while (c <= 0x17e9)	// ..to KHMER DIGIT NINE
631
		charset[i++] = c++;
632
	c = 0x17f0;		// from KHMER SYMBOL LEK ATTAK SON
633
	while (c <= 0x17f9)	// ..to KHMER SYMBOL LEK ATTAK PRAM-BUON
634
		charset[i++] = c++;
635
// 1800..18AF; Mongolian
636
	c = 0x1800;		// from MONGOLIAN BIRGA
637
	while (c <= 0x180e)	// ..to MONGOLIAN VOWEL SEPARATOR
638
		charset[i++] = c++;
639
	c = 0x1810;		// from MONGOLIAN DIGIT ZERO
640
	while (c <= 0x1819)	// ..to MONGOLIAN DIGIT NINE
641
		charset[i++] = c++;
642
	c = 0x1820;		// from MONGOLIAN LETTER A
643
	while (c <= 0x1878)	// ..to MONGOLIAN LETTER CHA WITH TWO DOTS
644
		charset[i++] = c++;
645
	c = 0x1880;		// from MONGOLIAN LETTER ALI GALI ANUSVARA ONE
646
	while (c <= 0x18aa)	// ..to MONGOLIAN LETTER MANCHU ALI GALI LHA
647
		charset[i++] = c++;
648
// 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
649
	c = 0x18b0;		// from CANADIAN SYLLABICS OY
650
	while (c <= 0x18f5)	// ..to CANADIAN SYLLABICS CARRIER DENTAL S
651
		charset[i++] = c++;
652
// 1900..194F; Limbu
653
	c = 0x1900;		// from LIMBU VOWEL-CARRIER LETTER
654
	while (c <= 0x191e)	// ..to LIMBU LETTER TRA
655
		charset[i++] = c++;
656
	c = 0x1920;		// from LIMBU VOWEL SIGN A
657
	while (c <= 0x192b)	// ..to LIMBU SUBJOINED LETTER WA
658
		charset[i++] = c++;
659
	c = 0x1930;		// from LIMBU SMALL LETTER KA
660
	while (c <= 0x193b)	// ..to LIMBU SIGN SA-I
661
		charset[i++] = c++;
662
	c = 0x1944;		// from LIMBU EXCLAMATION MARK
663
	while (c <= 0x194f)	// ..to LIMBU DIGIT NINE
664
		charset[i++] = c++;
665
// 1950..197F; Tai Le
666
	c = 0x1950;		// from TAI LE LETTER KA
667
	while (c <= 0x196d)	// ..to TAI LE LETTER AI
668
		charset[i++] = c++;
669
	c = 0x1970;		// from TAI LE LETTER TONE-2
670
	while (c <= 0x1974)	// ..to TAI LE LETTER TONE-6
671
		charset[i++] = c++;
672
// 1980..19DF; New Tai Lue
673
	c = 0x1980;		// from NEW TAI LUE LETTER HIGH QA
674
	while (c <= 0x19ab)	// ..to NEW TAI LUE LETTER LOW SUA
675
		charset[i++] = c++;
676
	c = 0x19b0;		// from NEW TAI LUE VOWEL SIGN VOWEL SHORTENER
677
	while (c <= 0x19c9)	// ..to NEW TAI LUE TONE MARK-2
678
		charset[i++] = c++;
679
	c = 0x19d0;		// from NEW TAI LUE DIGIT ZERO
680
	while (c <= 0x19da)	// ..to NEW TAI LUE THAM DIGIT ONE
681
		charset[i++] = c++;
682
	charset[i++] = 0x19de;	// NEW TAI LUE SIGN LAE
683
	charset[i++] = 0x19df;	// NEW TAI LUE SIGN LAEV
684
// 19E0..19FF; Khmer Symbols
685
	c = 0x19e0;		// from KHMER SYMBOL PATHAMASAT
686
	while (c <= 0x19ff)	// ..to KHMER SYMBOL DAP-PRAM ROC
687
		charset[i++] = c++;
688
// 1A00..1A1F; Buginese
689
	c = 0x1a00;		// from BUGINESE LETTER KA
690
	while (c <= 0x1a1b)	// ..to BUGINESE VOWEL SIGN AE
691
		charset[i++] = c++;
692
	charset[i++] = 0x1a1e;	// BUGINESE PALLAWA
693
	charset[i++] = 0x1a1f;	// BUGINESE END OF SECTION
694
// 1A20..1AAF; Tai Tham
695
	c = 0x1a20;		// from TAI THAM LETTER HIGH KA
696
	while (c <= 0x1a5e)	// ..to TAI THAM CONSONANT SIGN SA
697
		charset[i++] = c++;
698
	c = 0x1a60;		// from TAI THAM SIGN SAKOT
699
	while (c <= 0x1a7c)	// ..to TAI THAM SIGN KHUEN-LUE KARAN
700
		charset[i++] = c++;
701
	c = 0x1a7f;		// from TAI THAM COMBINING CRYPTOGRAMMIC DOT
702
	while (c <= 0x1a89)	// ..to TAI THAM HORA DIGIT NINE
703
		charset[i++] = c++;
704
	c = 0x1a90;		// from TAI THAM THAM DIGIT ZERO
705
	while (c <= 0x1a99)	// ..to TAI THAM THAM DIGIT NINE
706
		charset[i++] = c++;
707
	c = 0x1aa0;		// from TAI THAM SIGN WIANG
708
	while (c <= 0x1aad)	// ..to TAI THAM SIGN CAANG
709
		charset[i++] = c++;
710
// 1AB0..1AFF; Combining Diacritical Marks Extended
711
	c = 0x1ab0;		// from COMBINING DOUBLED CIRCUMFLEX ACCENT
712
	while (c <= 0x1ac0)	// ..to COMBINING LATIN SMALL LETTER TURNED W BELOW
713
		charset[i++] = c++;
714
// 1B00..1B7F; Balinese
715
	c = 0x1b00;		// from BALINESE SIGN ULU RICEM
716
	while (c <= 0x1b4b)	// ..to BALINESE LETTER ASYURA SASAK
717
		charset[i++] = c++;
718
	c = 0x1b50;		// from BALINESE DIGIT ZERO
719
	while (c <= 0x1b7c)	// ..to BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING
720
		charset[i++] = c++;
721
// 1B80..1BBF; Sundanese
722
	c = 0x1b80;		// from SUNDANESE SIGN PANYECEK
723
	while (c <= 0x1bbf)	// ..to SUNDANESE LETTER FINAL M
724
		charset[i++] = c++;
725
// 1BC0..1BFF; Batak
726
	c = 0x1bc0;		// from BATAK LETTER A
727
	while (c <= 0x1bf3)	// ..to BATAK PANONGONAN
728
		charset[i++] = c++;
729
	c = 0x1bfc;		// from BATAK SYMBOL BINDU NA METEK
730
	while (c <= 0x1bff)	// ..to BATAK SYMBOL BINDU PANGOLAT
731
		charset[i++] = c++;
732
// 1C00..1C4F; Lepcha
733
	c = 0x1c00;		// from LEPCHA LETTER KA
734
	while (c <= 0x1c37)	// ..to LEPCHA SIGN NUKTA
735
		charset[i++] = c++;
736
	c = 0x1c3b;		// from LEPCHA PUNCTUATION TA-ROL
737
	while (c <= 0x1c49)	// ..to LEPCHA DIGIT NINE
738
		charset[i++] = c++;
739
	charset[i++] = 0x1c4d;	// LEPCHA LETTER TTA
740
	charset[i++] = 0x1c4f;	// LEPCHA LETTER DDA
741
// 1C50..1C7F; Ol Chiki
742
	c = 0x1c50;		// from OL CHIKI DIGIT ZERO
743
	while (c <= 0x1c7f)	// ..to OL CHIKI PUNCTUATION DOUBLE MUCAAD
744
		charset[i++] = c++;
745
// 1C80..1C8F; Cyrillic Extended-C
746
	c = 0x1c80;		// from CYRILLIC SMALL LETTER ROUNDED VE
747
	while (c <= 0x1c88)	// ..to CYRILLIC SMALL LETTER UNBLENDED UK
748
		charset[i++] = c++;
749
// 1C90..1CBF; Georgian Extended
750
	c = 0x1c90;		// from GEORGIAN MTAVRULI CAPITAL LETTER AN
751
	while (c <= 0x1cba)	// ..to GEORGIAN MTAVRULI CAPITAL LETTER AIN
752
		charset[i++] = c++;
753
	charset[i++] = 0x1cbd;	// GEORGIAN MTAVRULI CAPITAL LETTER AEN
754
	charset[i++] = 0x1cbf;	// GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN
755
// 1CC0..1CCF; Sundanese Supplement
756
	c = 0x1cc0;		// from SUNDANESE PUNCTUATION BINDU SURYA
757
	while (c <= 0x1cc7)	// ..to SUNDANESE PUNCTUATION BINDU BA SATANGA
758
		charset[i++] = c++;
759
// 1CD0..1CFF; Vedic Extensions
760
	c = 0x1cd0;		// from VEDIC TONE KARSHANA
761
	while (c <= 0x1cfa)	// ..to VEDIC SIGN DOUBLE ANUSVARA ANTARGOMUKHA
762
		charset[i++] = c++;
763
// 1D00..1D7F; Phonetic Extensions
764
	c = 0x1d00;		// from LATIN LETTER SMALL CAPITAL A
765
	while (c <= 0x1d7f)	// ..to LATIN SMALL LETTER UPSILON WITH STROKE
766
		charset[i++] = c++;
767
// 1D80..1DBF; Phonetic Extensions Supplement
768
	c = 0x1d80;		// from LATIN SMALL LETTER B WITH PALATAL HOOK
769
	while (c <= 0x1dbf)	// ..to MODIFIER LETTER SMALL THETA
770
		charset[i++] = c++;
771
// 1DC0..1DFF; Combining Diacritical Marks Supplement
772
	c = 0x1dc0;		// from COMBINING DOTTED GRAVE ACCENT
773
	while (c <= 0x1df9)	// ..to COMBINING WIDE INVERTED BRIDGE BELOW
774
		charset[i++] = c++;
775
	c = 0x1dfb;		// from COMBINING DELETION MARK
776
	while (c <= 0x1dff)	// ..to COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
777
		charset[i++] = c++;
778
// 1E00..1EFF; Latin Extended Additional
779
	c = 0x1e00;		// from LATIN CAPITAL LETTER A WITH RING BELOW
780
	while (c <= 0x1eff)	// ..to LATIN SMALL LETTER Y WITH LOOP
781
		charset[i++] = c++;
782
// 1F00..1FFF; Greek Extended
783
	c = 0x1f00;		// from GREEK SMALL LETTER ALPHA WITH PSILI
784
	while (c <= 0x1f15)	// ..to GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
785
		charset[i++] = c++;
786
	c = 0x1f18;		// from GREEK CAPITAL LETTER EPSILON WITH PSILI
787
	while (c <= 0x1f1d)	// ..to GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
788
		charset[i++] = c++;
789
	c = 0x1f20;		// from GREEK SMALL LETTER ETA WITH PSILI
790
	while (c <= 0x1f45)	// ..to GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA
791
		charset[i++] = c++;
792
	c = 0x1f48;		// from GREEK CAPITAL LETTER OMICRON WITH PSILI
793
	while (c <= 0x1f4d)	// ..to GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA
794
		charset[i++] = c++;
795
	c = 0x1f50;		// from GREEK SMALL LETTER UPSILON WITH PSILI
796
	while (c <= 0x1f57)	// ..to GREEK SMALL LETTER UPSILON WITH DASIA AND PERISPOMENI
797
		charset[i++] = c++;
798
	c = 0x1f5f;		// from GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI
799
	while (c <= 0x1f7d)	// ..to GREEK SMALL LETTER OMEGA WITH OXIA
800
		charset[i++] = c++;
801
	c = 0x1f80;		// from GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
802
	while (c <= 0x1fb4)	// ..to GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
803
		charset[i++] = c++;
804
	c = 0x1fb6;		// from GREEK SMALL LETTER ALPHA WITH PERISPOMENI
805
	while (c <= 0x1fc4)	// ..to GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
806
		charset[i++] = c++;
807
	c = 0x1fc6;		// from GREEK SMALL LETTER ETA WITH PERISPOMENI
808
	while (c <= 0x1fd3)	// ..to GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
809
		charset[i++] = c++;
810
	c = 0x1fd6;		// from GREEK SMALL LETTER IOTA WITH PERISPOMENI
811
	while (c <= 0x1fdb)	// ..to GREEK CAPITAL LETTER IOTA WITH OXIA
812
		charset[i++] = c++;
813
	c = 0x1fdd;		// from GREEK DASIA AND VARIA
814
	while (c <= 0x1fef)	// ..to GREEK VARIA
815
		charset[i++] = c++;
816
	charset[i++] = 0x1ff2;	// GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
817
	charset[i++] = 0x1ff4;	// GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
818
	c = 0x1ff6;		// from GREEK SMALL LETTER OMEGA WITH PERISPOMENI
819
	while (c <= 0x1ffe)	// ..to GREEK DASIA
820
		charset[i++] = c++;
821
// 2000..206F; General Punctuation
822
	c = 0x2000;		// from EN QUAD
823
	while (c <= 0x2064)	// ..to INVISIBLE PLUS
824
		charset[i++] = c++;
825
	c = 0x2066;		// from LEFT-TO-RIGHT ISOLATE
826
	while (c <= 0x206f)	// ..to NOMINAL DIGIT SHAPES
827
		charset[i++] = c++;
828
// 2070..209F; Superscripts and Subscripts
829
	charset[i++] = 0x2070;	// SUPERSCRIPT ZERO
830
	charset[i++] = 0x2071;	// SUPERSCRIPT LATIN SMALL LETTER I
831
	c = 0x2074;		// from SUPERSCRIPT FOUR
832
	while (c <= 0x208e)	// ..to SUBSCRIPT RIGHT PARENTHESIS
833
		charset[i++] = c++;
834
	c = 0x2090;		// from LATIN SUBSCRIPT SMALL LETTER A
835
	while (c <= 0x209c)	// ..to LATIN SUBSCRIPT SMALL LETTER T
836
		charset[i++] = c++;
837
// 20A0..20CF; Currency Symbols
838
	c = 0x20a0;		// from EURO-CURRENCY SIGN
839
	while (c <= 0x20bf)	// ..to BITCOIN SIGN
840
		charset[i++] = c++;
841
// 20D0..20FF; Combining Diacritical Marks for Symbols
842
	c = 0x20d0;		// from COMBINING LEFT HARPOON ABOVE
843
	while (c <= 0x20f0)	// ..to COMBINING ASTERISK ABOVE
844
		charset[i++] = c++;
845
// 2100..214F; Letterlike Symbols
846
	c = 0x2100;		// from ACCOUNT OF
847
	while (c <= 0x214f)	// ..to SYMBOL FOR SAMARITAN SOURCE
848
		charset[i++] = c++;
849
// 2150..218F; Number Forms
850
	c = 0x2150;		// from VULGAR FRACTION ONE SEVENTH
851
	while (c <= 0x218b)	// ..to TURNED DIGIT THREE
852
		charset[i++] = c++;
853
// 2190..21FF; Arrows
854
	c = 0x2190;		// from LEFTWARDS ARROW
855
	while (c <= 0x21ff)	// ..to LEFT RIGHT OPEN-HEADED ARROW
856
		charset[i++] = c++;
857
// 2200..22FF; Mathematical Operators
858
	c = 0x2200;		// from FOR ALL
859
	while (c <= 0x22ff)	// ..to Z NOTATION BAG MEMBERSHIP
860
		charset[i++] = c++;
861
// 2300..23FF; Miscellaneous Technical
862
	c = 0x2300;		// from DIAMETER SIGN
863
	while (c <= 0x23ff)	// ..to OBSERVER EYE SYMBOL
864
		charset[i++] = c++;
865
// 2400..243F; Control Pictures
866
	c = 0x2400;		// from SYMBOL FOR NULL
867
	while (c <= 0x2426)	// ..to SYMBOL FOR SUBSTITUTE FORM TWO
868
		charset[i++] = c++;
869
// 2440..245F; Optical Character Recognition
870
	c = 0x2440;		// from OCR HOOK
871
	while (c <= 0x244a)	// ..to OCR DOUBLE BACKSLASH
872
		charset[i++] = c++;
873
// 2460..24FF; Enclosed Alphanumerics
874
	c = 0x2460;		// from CIRCLED DIGIT ONE
875
	while (c <= 0x24ff)	// ..to NEGATIVE CIRCLED DIGIT ZERO
876
		charset[i++] = c++;
877
// 2500..257F; Box Drawing
878
	c = 0x2500;		// from BOX DRAWINGS LIGHT HORIZONTAL
879
	while (c <= 0x257f)	// ..to BOX DRAWINGS HEAVY UP AND LIGHT DOWN
880
		charset[i++] = c++;
881
// 2580..259F; Block Elements
882
	c = 0x2580;		// from UPPER HALF BLOCK
883
	while (c <= 0x259f)	// ..to QUADRANT UPPER RIGHT AND LOWER LEFT AND LOWER RIGHT
884
		charset[i++] = c++;
885
// 25A0..25FF; Geometric Shapes
886
	c = 0x25a0;		// from BLACK SQUARE
887
	while (c <= 0x25ff)	// ..to LOWER RIGHT TRIANGLE
888
		charset[i++] = c++;
889
// 2600..26FF; Miscellaneous Symbols
890
	c = 0x2600;		// from BLACK SUN WITH RAYS
891
	while (c <= 0x26ff)	// ..to WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE
892
		charset[i++] = c++;
893
// 2700..27BF; Dingbats
894
	c = 0x2700;		// from BLACK SAFETY SCISSORS
895
	while (c <= 0x27bf)	// ..to DOUBLE CURLY LOOP
896
		charset[i++] = c++;
897
// 27C0..27EF; Miscellaneous Mathematical Symbols-A
898
	c = 0x27c0;		// from THREE DIMENSIONAL ANGLE
899
	while (c <= 0x27ef)	// ..to MATHEMATICAL RIGHT FLATTENED PARENTHESIS
900
		charset[i++] = c++;
901
// 27F0..27FF; Supplemental Arrows-A
902
	c = 0x27f0;		// from UPWARDS QUADRUPLE ARROW
903
	while (c <= 0x27ff)	// ..to LONG RIGHTWARDS SQUIGGLE ARROW
904
		charset[i++] = c++;
905
// 2800..28FF; Braille Patterns
906
	c = 0x2800;		// from BRAILLE PATTERN BLANK
907
	while (c <= 0x28ff)	// ..to BRAILLE PATTERN DOTS-12345678
908
		charset[i++] = c++;
909
// 2900..297F; Supplemental Arrows-B
910
	c = 0x2900;		// from RIGHTWARDS TWO-HEADED ARROW WITH VERTICAL STROKE
911
	while (c <= 0x297f)	// ..to DOWN FISH TAIL
912
		charset[i++] = c++;
913
// 2980..29FF; Miscellaneous Mathematical Symbols-B
914
	c = 0x2980;		// from TRIPLE VERTICAL BAR DELIMITER
915
	while (c <= 0x29ff)	// ..to MINY
916
		charset[i++] = c++;
917
// 2A00..2AFF; Supplemental Mathematical Operators
918
	c = 0x2a00;		// from N-ARY CIRCLED DOT OPERATOR
919
	while (c <= 0x2aff)	// ..to N-ARY WHITE VERTICAL BAR
920
		charset[i++] = c++;
921
// 2B00..2BFF; Miscellaneous Symbols and Arrows
922
	c = 0x2b00;		// from NORTH EAST WHITE ARROW
923
	while (c <= 0x2b73)	// ..to DOWNWARDS TRIANGLE-HEADED ARROW TO BAR
924
		charset[i++] = c++;
925
	c = 0x2b76;		// from NORTH WEST TRIANGLE-HEADED ARROW TO BAR
926
	while (c <= 0x2b95)	// ..to RIGHTWARDS BLACK ARROW
927
		charset[i++] = c++;
928
	c = 0x2b97;		// from SYMBOL FOR TYPE A ELECTRONICS
929
	while (c <= 0x2bff)	// ..to HELLSCHREIBER PAUSE SYMBOL
930
		charset[i++] = c++;
931
// 2C00..2C5F; Glagolitic
932
	c = 0x2c00;		// from GLAGOLITIC CAPITAL LETTER AZU
933
	while (c <= 0x2c2e)	// ..to GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
934
		charset[i++] = c++;
935
	c = 0x2c30;		// from GLAGOLITIC SMALL LETTER AZU
936
	while (c <= 0x2c5e)	// ..to GLAGOLITIC SMALL LETTER LATINATE MYSLITE
937
		charset[i++] = c++;
938
// 2C60..2C7F; Latin Extended-C
939
	c = 0x2c60;		// from LATIN CAPITAL LETTER L WITH DOUBLE BAR
940
	while (c <= 0x2c7f)	// ..to LATIN CAPITAL LETTER Z WITH SWASH TAIL
941
		charset[i++] = c++;
942
// 2C80..2CFF; Coptic
943
	c = 0x2c80;		// from COPTIC CAPITAL LETTER ALFA
944
	while (c <= 0x2cf3)	// ..to COPTIC SMALL LETTER BOHAIRIC KHEI
945
		charset[i++] = c++;
946
	c = 0x2cf9;		// from COPTIC OLD NUBIAN FULL STOP
947
	while (c <= 0x2cff)	// ..to COPTIC MORPHOLOGICAL DIVIDER
948
		charset[i++] = c++;
949
// 2D00..2D2F; Georgian Supplement
950
	c = 0x2d00;		// from GEORGIAN SMALL LETTER AN
951
	while (c <= 0x2d25)	// ..to GEORGIAN SMALL LETTER HOE
952
		charset[i++] = c++;
953
	c = 0x2d27;		// from GEORGIAN SMALL LETTER YN
954
	while (c <= 0x2d2d)	// ..to GEORGIAN SMALL LETTER AEN
955
		charset[i++] = c++;
956
// 2D30..2D7F; Tifinagh
957
	c = 0x2d30;		// from TIFINAGH LETTER YA
958
	while (c <= 0x2d67)	// ..to TIFINAGH LETTER YO
959
		charset[i++] = c++;
960
	charset[i++] = 0x2d6f;	// TIFINAGH MODIFIER LETTER LABIALIZATION MARK
961
	charset[i++] = 0x2d70;	// TIFINAGH SEPARATOR MARK
962
	charset[i++] = 0x2d7f;	// TIFINAGH CONSONANT JOINER
963
// 2D80..2DDF; Ethiopic Extended
964
	c = 0x2d80;		// from ETHIOPIC SYLLABLE LOA
965
	while (c <= 0x2d96)	// ..to ETHIOPIC SYLLABLE GGWE
966
		charset[i++] = c++;
967
	c = 0x2da0;		// from ETHIOPIC SYLLABLE SSA
968
	while (c <= 0x2da6)	// ..to ETHIOPIC SYLLABLE SSO
969
		charset[i++] = c++;
970
	c = 0x2da8;		// from ETHIOPIC SYLLABLE CCA
971
	while (c <= 0x2dae)	// ..to ETHIOPIC SYLLABLE CCO
972
		charset[i++] = c++;
973
	c = 0x2db0;		// from ETHIOPIC SYLLABLE ZZA
974
	while (c <= 0x2db6)	// ..to ETHIOPIC SYLLABLE ZZO
975
		charset[i++] = c++;
976
	c = 0x2db8;		// from ETHIOPIC SYLLABLE CCHA
977
	while (c <= 0x2dbe)	// ..to ETHIOPIC SYLLABLE CCHO
978
		charset[i++] = c++;
979
	c = 0x2dc0;		// from ETHIOPIC SYLLABLE QYA
980
	while (c <= 0x2dc6)	// ..to ETHIOPIC SYLLABLE QYO
981
		charset[i++] = c++;
982
	c = 0x2dc8;		// from ETHIOPIC SYLLABLE KYA
983
	while (c <= 0x2dce)	// ..to ETHIOPIC SYLLABLE KYO
984
		charset[i++] = c++;
985
	c = 0x2dd0;		// from ETHIOPIC SYLLABLE XYA
986
	while (c <= 0x2dd6)	// ..to ETHIOPIC SYLLABLE XYO
987
		charset[i++] = c++;
988
	c = 0x2dd8;		// from ETHIOPIC SYLLABLE GYA
989
	while (c <= 0x2dde)	// ..to ETHIOPIC SYLLABLE GYO
990
		charset[i++] = c++;
991
// 2DE0..2DFF; Cyrillic Extended-A
992
	c = 0x2de0;		// from COMBINING CYRILLIC LETTER BE
993
	while (c <= 0x2dff)	// ..to COMBINING CYRILLIC LETTER IOTIFIED BIG YUS
994
		charset[i++] = c++;
995
// 2E00..2E7F; Supplemental Punctuation
996
	c = 0x2e00;		// from RIGHT ANGLE SUBSTITUTION MARKER
997
	while (c <= 0x2e52)	// ..to TIRONIAN SIGN CAPITAL ET
998
		charset[i++] = c++;
999
// 2E80..2EFF; CJK Radicals Supplement
1000
	c = 0x2e80;		// from CJK RADICAL REPEAT
1001
	while (c <= 0x2e99)	// ..to CJK RADICAL RAP
1002
		charset[i++] = c++;
1003
	c = 0x2e9b;		// from CJK RADICAL CHOKE
1004
	while (c <= 0x2ef3)	// ..to CJK RADICAL C-SIMPLIFIED TURTLE
1005
		charset[i++] = c++;
1006
// 2F00..2FDF; Kangxi Radicals
1007
	c = 0x2f00;		// from KANGXI RADICAL ONE
1008
	while (c <= 0x2fd5)	// ..to KANGXI RADICAL FLUTE
1009
		charset[i++] = c++;
1010
// 2FF0..2FFF; Ideographic Description Characters
1011
	c = 0x2ff0;		// from IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT
1012
	while (c <= 0x2ffb)	// ..to IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
1013
		charset[i++] = c++;
1014
// 3000..303F; CJK Symbols and Punctuation
1015
	c = 0x3000;		// from IDEOGRAPHIC SPACE
1016
	while (c <= 0x303f)	// ..to IDEOGRAPHIC HALF FILL SPACE
1017
		charset[i++] = c++;
1018
// 3040..309F; Hiragana
1019
	c = 0x3041;		// from HIRAGANA LETTER SMALL A
1020
	while (c <= 0x3096)	// ..to HIRAGANA LETTER SMALL KE
1021
		charset[i++] = c++;
1022
	c = 0x3099;		// from COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK
1023
	while (c <= 0x309f)	// ..to HIRAGANA DIGRAPH YORI
1024
		charset[i++] = c++;
1025
// 30A0..30FF; Katakana
1026
	c = 0x30a0;		// from KATAKANA-HIRAGANA DOUBLE HYPHEN
1027
	while (c <= 0x30ff)	// ..to KATAKANA DIGRAPH KOTO
1028
		charset[i++] = c++;
1029
// 3100..312F; Bopomofo
1030
	c = 0x3105;		// from BOPOMOFO LETTER B
1031
	while (c <= 0x312f)	// ..to BOPOMOFO LETTER NN
1032
		charset[i++] = c++;
1033
// 3130..318F; Hangul Compatibility Jamo
1034
	c = 0x3131;		// from HANGUL LETTER KIYEOK
1035
	while (c <= 0x318e)	// ..to HANGUL LETTER ARAEAE
1036
		charset[i++] = c++;
1037
// 3190..319F; Kanbun
1038
	c = 0x3190;		// from IDEOGRAPHIC ANNOTATION LINKING MARK
1039
	while (c <= 0x319f)	// ..to IDEOGRAPHIC ANNOTATION MAN MARK
1040
		charset[i++] = c++;
1041
// 31A0..31BF; Bopomofo Extended
1042
	c = 0x31a0;		// from BOPOMOFO LETTER BU
1043
	while (c <= 0x31bf)	// ..to BOPOMOFO LETTER AH
1044
		charset[i++] = c++;
1045
// 31C0..31EF; CJK Strokes
1046
	c = 0x31c0;		// from CJK STROKE T
1047
	while (c <= 0x31e3)	// ..to CJK STROKE Q
1048
		charset[i++] = c++;
1049
// 31F0..31FF; Katakana Phonetic Extensions
1050
	c = 0x31f0;		// from KATAKANA LETTER SMALL KU
1051
	while (c <= 0x31ff)	// ..to KATAKANA LETTER SMALL RO
1052
		charset[i++] = c++;
1053
// 3200..32FF; Enclosed CJK Letters and Months
1054
	c = 0x3200;		// from PARENTHESIZED HANGUL KIYEOK
1055
	while (c <= 0x321e)	// ..to PARENTHESIZED KOREAN CHARACTER O HU
1056
		charset[i++] = c++;
1057
	c = 0x3220;		// from PARENTHESIZED IDEOGRAPH ONE
1058
	while (c <= 0x32ff)	// ..to SQUARE ERA NAME REIWA
1059
		charset[i++] = c++;
1060
// 3300..33FF; CJK Compatibility
1061
	c = 0x3300;		// from SQUARE APAATO
1062
	while (c <= 0x33ff)	// ..to SQUARE GAL
1063
		charset[i++] = c++;
1064
// 3400..4DBF; CJK Unified Ideographs Extension A
1065
	c = 0x3400;		// from <CJK Ideograph Extension A, First>
1066
	while (c <= 0x4dbf)	// ..to <CJK Ideograph Extension A, Last>
1067
		charset[i++] = c++;
1068
// 4DC0..4DFF; Yijing Hexagram Symbols
1069
	c = 0x4dc0;		// from HEXAGRAM FOR THE CREATIVE HEAVEN
1070
	while (c <= 0x4dff)	// ..to HEXAGRAM FOR BEFORE COMPLETION
1071
		charset[i++] = c++;
1072
// 4E00..9FFF; CJK Unified Ideographs
1073
	c = 0x4e00;		// from <CJK Ideograph, First>
1074
	while (c <= 0x9ffc)	// ..to <CJK Ideograph, Last>
1075
		charset[i++] = c++;
1076
// A000..A48F; Yi Syllables
1077
	c = 0xa000;		// from YI SYLLABLE IT
1078
	while (c <= 0xa48c)	// ..to YI SYLLABLE YYR
1079
		charset[i++] = c++;
1080
// A490..A4CF; Yi Radicals
1081
	c = 0xa490;		// from YI RADICAL QOT
1082
	while (c <= 0xa4c6)	// ..to YI RADICAL KE
1083
		charset[i++] = c++;
1084
// A4D0..A4FF; Lisu
1085
	c = 0xa4d0;		// from LISU LETTER BA
1086
	while (c <= 0xa4ff)	// ..to LISU PUNCTUATION FULL STOP
1087
		charset[i++] = c++;
1088
// A500..A63F; Vai
1089
	c = 0xa500;		// from VAI SYLLABLE EE
1090
	while (c <= 0xa62b)	// ..to VAI SYLLABLE NDOLE DO
1091
		charset[i++] = c++;
1092
// A640..A69F; Cyrillic Extended-B
1093
	c = 0xa640;		// from CYRILLIC CAPITAL LETTER ZEMLYA
1094
	while (c <= 0xa69f)	// ..to COMBINING CYRILLIC LETTER IOTIFIED E
1095
		charset[i++] = c++;
1096
// A6A0..A6FF; Bamum
1097
	c = 0xa6a0;		// from BAMUM LETTER A
1098
	while (c <= 0xa6f7)	// ..to BAMUM QUESTION MARK
1099
		charset[i++] = c++;
1100
// A700..A71F; Modifier Tone Letters
1101
	c = 0xa700;		// from MODIFIER LETTER CHINESE TONE YIN PING
1102
	while (c <= 0xa71f)	// ..to MODIFIER LETTER LOW INVERTED EXCLAMATION MARK
1103
		charset[i++] = c++;
1104
// A720..A7FF; Latin Extended-D
1105
	c = 0xa720;		// from MODIFIER LETTER STRESS AND HIGH TONE
1106
	while (c <= 0xa7bf)	// ..to LATIN SMALL LETTER GLOTTAL U
1107
		charset[i++] = c++;
1108
	c = 0xa7c2;		// from LATIN CAPITAL LETTER ANGLICANA W
1109
	while (c <= 0xa7ca)	// ..to LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY
1110
		charset[i++] = c++;
1111
	c = 0xa7f5;		// from LATIN CAPITAL LETTER REVERSED HALF H
1112
	while (c <= 0xa7ff)	// ..to LATIN EPIGRAPHIC LETTER ARCHAIC M
1113
		charset[i++] = c++;
1114
// A800..A82F; Syloti Nagri
1115
	c = 0xa800;		// from SYLOTI NAGRI LETTER A
1116
	while (c <= 0xa82c)	// ..to SYLOTI NAGRI SIGN ALTERNATE HASANTA
1117
		charset[i++] = c++;
1118
// A830..A83F; Common Indic Number Forms
1119
	c = 0xa830;		// from NORTH INDIC FRACTION ONE QUARTER
1120
	while (c <= 0xa839)	// ..to NORTH INDIC QUANTITY MARK
1121
		charset[i++] = c++;
1122
// A840..A87F; Phags-pa
1123
	c = 0xa840;		// from PHAGS-PA LETTER KA
1124
	while (c <= 0xa877)	// ..to PHAGS-PA MARK DOUBLE SHAD
1125
		charset[i++] = c++;
1126
// A880..A8DF; Saurashtra
1127
	c = 0xa880;		// from SAURASHTRA SIGN ANUSVARA
1128
	while (c <= 0xa8c5)	// ..to SAURASHTRA SIGN CANDRABINDU
1129
		charset[i++] = c++;
1130
	c = 0xa8ce;		// from SAURASHTRA DANDA
1131
	while (c <= 0xa8d9)	// ..to SAURASHTRA DIGIT NINE
1132
		charset[i++] = c++;
1133
// A8E0..A8FF; Devanagari Extended
1134
	c = 0xa8e0;		// from COMBINING DEVANAGARI DIGIT ZERO
1135
	while (c <= 0xa8ff)	// ..to DEVANAGARI VOWEL SIGN AY
1136
		charset[i++] = c++;
1137
// A900..A92F; Kayah Li
1138
	c = 0xa900;		// from KAYAH LI DIGIT ZERO
1139
	while (c <= 0xa92f)	// ..to KAYAH LI SIGN SHYA
1140
		charset[i++] = c++;
1141
// A930..A95F; Rejang
1142
	c = 0xa930;		// from REJANG LETTER KA
1143
	while (c <= 0xa953)	// ..to REJANG VIRAMA
1144
		charset[i++] = c++;
1145
	charset[i++] = 0xa95f;	// REJANG SECTION MARK
1146
// A960..A97F; Hangul Jamo Extended-A
1147
	c = 0xa960;		// from HANGUL CHOSEONG TIKEUT-MIEUM
1148
	while (c <= 0xa97c)	// ..to HANGUL CHOSEONG SSANGYEORINHIEUH
1149
		charset[i++] = c++;
1150
// A980..A9DF; Javanese
1151
	c = 0xa980;		// from JAVANESE SIGN PANYANGGA
1152
	while (c <= 0xa9cd)	// ..to JAVANESE TURNED PADA PISELEH
1153
		charset[i++] = c++;
1154
	c = 0xa9cf;		// from JAVANESE PANGRANGKEP
1155
	while (c <= 0xa9d9)	// ..to JAVANESE DIGIT NINE
1156
		charset[i++] = c++;
1157
	charset[i++] = 0xa9de;	// JAVANESE PADA TIRTA TUMETES
1158
	charset[i++] = 0xa9df;	// JAVANESE PADA ISEN-ISEN
1159
// A9E0..A9FF; Myanmar Extended-B
1160
	c = 0xa9e0;		// from MYANMAR LETTER SHAN GHA
1161
	while (c <= 0xa9fe)	// ..to MYANMAR LETTER TAI LAING BHA
1162
		charset[i++] = c++;
1163
// AA00..AA5F; Cham
1164
	c = 0xaa00;		// from CHAM LETTER A
1165
	while (c <= 0xaa36)	// ..to CHAM CONSONANT SIGN WA
1166
		charset[i++] = c++;
1167
	c = 0xaa40;		// from CHAM LETTER FINAL K
1168
	while (c <= 0xaa4d)	// ..to CHAM CONSONANT SIGN FINAL H
1169
		charset[i++] = c++;
1170
	c = 0xaa50;		// from CHAM DIGIT ZERO
1171
	while (c <= 0xaa59)	// ..to CHAM DIGIT NINE
1172
		charset[i++] = c++;
1173
	c = 0xaa5c;		// from CHAM PUNCTUATION SPIRAL
1174
	while (c <= 0xaa5f)	// ..to CHAM PUNCTUATION TRIPLE DANDA
1175
		charset[i++] = c++;
1176
// AA60..AA7F; Myanmar Extended-A
1177
	c = 0xaa60;		// from MYANMAR LETTER KHAMTI GA
1178
	while (c <= 0xaa7f)	// ..to MYANMAR LETTER SHWE PALAUNG SHA
1179
		charset[i++] = c++;
1180
// AA80..AADF; Tai Viet
1181
	c = 0xaa80;		// from TAI VIET LETTER LOW KO
1182
	while (c <= 0xaac2)	// ..to TAI VIET TONE MAI SONG
1183
		charset[i++] = c++;
1184
	c = 0xaadb;		// from TAI VIET SYMBOL KON
1185
	while (c <= 0xaadf)	// ..to TAI VIET SYMBOL KOI KOI
1186
		charset[i++] = c++;
1187
// AAE0..AAFF; Meetei Mayek Extensions
1188
	c = 0xaae0;		// from MEETEI MAYEK LETTER E
1189
	while (c <= 0xaaf6)	// ..to MEETEI MAYEK VIRAMA
1190
		charset[i++] = c++;
1191
// AB00..AB2F; Ethiopic Extended-A
1192
	c = 0xab01;		// from ETHIOPIC SYLLABLE TTHU
1193
	while (c <= 0xab06)	// ..to ETHIOPIC SYLLABLE TTHO
1194
		charset[i++] = c++;
1195
	c = 0xab09;		// from ETHIOPIC SYLLABLE DDHU
1196
	while (c <= 0xab0e)	// ..to ETHIOPIC SYLLABLE DDHO
1197
		charset[i++] = c++;
1198
	c = 0xab11;		// from ETHIOPIC SYLLABLE DZU
1199
	while (c <= 0xab16)	// ..to ETHIOPIC SYLLABLE DZO
1200
		charset[i++] = c++;
1201
	c = 0xab20;		// from ETHIOPIC SYLLABLE CCHHA
1202
	while (c <= 0xab26)	// ..to ETHIOPIC SYLLABLE CCHHO
1203
		charset[i++] = c++;
1204
	c = 0xab28;		// from ETHIOPIC SYLLABLE BBA
1205
	while (c <= 0xab2e)	// ..to ETHIOPIC SYLLABLE BBO
1206
		charset[i++] = c++;
1207
// AB30..AB6F; Latin Extended-E
1208
	c = 0xab30;		// from LATIN SMALL LETTER BARRED ALPHA
1209
	while (c <= 0xab6b)	// ..to MODIFIER LETTER RIGHT TACK
1210
		charset[i++] = c++;
1211
// AB70..ABBF; Cherokee Supplement
1212
	c = 0xab70;		// from CHEROKEE SMALL LETTER A
1213
	while (c <= 0xabbf)	// ..to CHEROKEE SMALL LETTER YA
1214
		charset[i++] = c++;
1215
// ABC0..ABFF; Meetei Mayek
1216
	c = 0xabc0;		// from MEETEI MAYEK LETTER KOK
1217
	while (c <= 0xabed)	// ..to MEETEI MAYEK APUN IYEK
1218
		charset[i++] = c++;
1219
	c = 0xabf0;		// from MEETEI MAYEK DIGIT ZERO
1220
	while (c <= 0xabf9)	// ..to MEETEI MAYEK DIGIT NINE
1221
		charset[i++] = c++;
1222
// AC00..D7AF; Hangul Syllables
1223
	c = 0xac00;		// from <Hangul Syllable, First>
1224
	while (c <= 0xd7a3)	// ..to <Hangul Syllable, Last>
1225
		charset[i++] = c++;
1226
// D7B0..D7FF; Hangul Jamo Extended-B
1227
	c = 0xd7b0;		// from HANGUL JUNGSEONG O-YEO
1228
	while (c <= 0xd7c6)	// ..to HANGUL JUNGSEONG ARAEA-E
1229
		charset[i++] = c++;
1230
	c = 0xd7cb;		// from HANGUL JONGSEONG NIEUN-RIEUL
1231
	while (c <= 0xd7fb)	// ..to HANGUL JONGSEONG PHIEUPH-THIEUTH
1232
		charset[i++] = c++;
1233
// D800..DB7F; High Surrogates
1234
// DB80..DBFF; High Private Use Surrogates
1235
// DC00..DFFF; Low Surrogates
1236
// E000..F8FF; Private Use Area
1237
// F900..FAFF; CJK Compatibility Ideographs
1238
	c = 0xf900;		// from CJK COMPATIBILITY IDEOGRAPH-F900
1239
	while (c <= 0xfa6d)	// ..to CJK COMPATIBILITY IDEOGRAPH-FA6D
1240
		charset[i++] = c++;
1241
	c = 0xfa70;		// from CJK COMPATIBILITY IDEOGRAPH-FA70
1242
	while (c <= 0xfad9)	// ..to CJK COMPATIBILITY IDEOGRAPH-FAD9
1243
		charset[i++] = c++;
1244
// FB00..FB4F; Alphabetic Presentation Forms
1245
	c = 0xfb00;		// from LATIN SMALL LIGATURE FF
1246
	while (c <= 0xfb06)	// ..to LATIN SMALL LIGATURE ST
1247
		charset[i++] = c++;
1248
	c = 0xfb13;		// from ARMENIAN SMALL LIGATURE MEN NOW
1249
	while (c <= 0xfb17)	// ..to ARMENIAN SMALL LIGATURE MEN XEH
1250
		charset[i++] = c++;
1251
	c = 0xfb1d;		// from HEBREW LETTER YOD WITH HIRIQ
1252
	while (c <= 0xfb36)	// ..to HEBREW LETTER ZAYIN WITH DAGESH
1253
		charset[i++] = c++;
1254
	c = 0xfb38;		// from HEBREW LETTER TET WITH DAGESH
1255
	while (c <= 0xfb3c)	// ..to HEBREW LETTER LAMED WITH DAGESH
1256
		charset[i++] = c++;
1257
	charset[i++] = 0xfb40;	// HEBREW LETTER NUN WITH DAGESH
1258
	charset[i++] = 0xfb41;	// HEBREW LETTER SAMEKH WITH DAGESH
1259
	charset[i++] = 0xfb43;	// HEBREW LETTER FINAL PE WITH DAGESH
1260
	charset[i++] = 0xfb44;	// HEBREW LETTER PE WITH DAGESH
1261
	c = 0xfb46;		// from HEBREW LETTER TSADI WITH DAGESH
1262
	while (c <= 0xfb4f)	// ..to HEBREW LIGATURE ALEF LAMED
1263
		charset[i++] = c++;
1264
// FB50..FDFF; Arabic Presentation Forms-A
1265
	c = 0xfb50;		// from ARABIC LETTER ALEF WASLA ISOLATED FORM
1266
	while (c <= 0xfbc1)	// ..to ARABIC SYMBOL SMALL TAH BELOW
1267
		charset[i++] = c++;
1268
	c = 0xfbd3;		// from ARABIC LETTER NG ISOLATED FORM
1269
	while (c <= 0xfd3f)	// ..to ORNATE RIGHT PARENTHESIS
1270
		charset[i++] = c++;
1271
	c = 0xfd50;		// from ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM
1272
	while (c <= 0xfd8f)	// ..to ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM
1273
		charset[i++] = c++;
1274
	c = 0xfd92;		// from ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM
1275
	while (c <= 0xfdc7)	// ..to ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM
1276
		charset[i++] = c++;
1277
	c = 0xfdf0;		// from ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM
1278
	while (c <= 0xfdfd)	// ..to ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM
1279
		charset[i++] = c++;
1280
// FE00..FE0F; Variation Selectors
1281
	c = 0xfe00;		// from VARIATION SELECTOR-1
1282
	while (c <= 0xfe0f)	// ..to VARIATION SELECTOR-16
1283
		charset[i++] = c++;
1284
// FE10..FE1F; Vertical Forms
1285
	c = 0xfe10;		// from PRESENTATION FORM FOR VERTICAL COMMA
1286
	while (c <= 0xfe19)	// ..to PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS
1287
		charset[i++] = c++;
1288
// FE20..FE2F; Combining Half Marks
1289
	c = 0xfe20;		// from COMBINING LIGATURE LEFT HALF
1290
	while (c <= 0xfe2f)	// ..to COMBINING CYRILLIC TITLO RIGHT HALF
1291
		charset[i++] = c++;
1292
// FE30..FE4F; CJK Compatibility Forms
1293
	c = 0xfe30;		// from PRESENTATION FORM FOR VERTICAL TWO DOT LEADER
1294
	while (c <= 0xfe4f)	// ..to WAVY LOW LINE
1295
		charset[i++] = c++;
1296
// FE50..FE6F; Small Form Variants
1297
	charset[i++] = 0xfe50;	// SMALL COMMA
1298
	charset[i++] = 0xfe52;	// SMALL FULL STOP
1299
	c = 0xfe54;		// from SMALL SEMICOLON
1300
	while (c <= 0xfe66)	// ..to SMALL EQUALS SIGN
1301
		charset[i++] = c++;
1302
	c = 0xfe68;		// from SMALL REVERSE SOLIDUS
1303
	while (c <= 0xfe6b)	// ..to SMALL COMMERCIAL AT
1304
		charset[i++] = c++;
1305
// FE70..FEFF; Arabic Presentation Forms-B
1306
	c = 0xfe70;		// from ARABIC FATHATAN ISOLATED FORM
1307
	while (c <= 0xfe74)	// ..to ARABIC KASRATAN ISOLATED FORM
1308
		charset[i++] = c++;
1309
	c = 0xfe76;		// from ARABIC FATHA ISOLATED FORM
1310
	while (c <= 0xfefc)	// ..to ARABIC LIGATURE LAM WITH ALEF FINAL FORM
1311
		charset[i++] = c++;
1312
	charset[i++] = 0xfeff;	// ZERO WIDTH NO-BREAK SPACE
1313
// FF00..FFEF; Halfwidth and Fullwidth Forms
1314
	c = 0xff01;		// from FULLWIDTH EXCLAMATION MARK
1315
	while (c <= 0xffbe)	// ..to HALFWIDTH HANGUL LETTER HIEUH
1316
		charset[i++] = c++;
1317
	c = 0xffc2;		// from HALFWIDTH HANGUL LETTER A
1318
	while (c <= 0xffc7)	// ..to HALFWIDTH HANGUL LETTER E
1319
		charset[i++] = c++;
1320
	c = 0xffca;		// from HALFWIDTH HANGUL LETTER YEO
1321
	while (c <= 0xffcf)	// ..to HALFWIDTH HANGUL LETTER OE
1322
		charset[i++] = c++;
1323
	c = 0xffd2;		// from HALFWIDTH HANGUL LETTER YO
1324
	while (c <= 0xffd7)	// ..to HALFWIDTH HANGUL LETTER YU
1325
		charset[i++] = c++;
1326
	charset[i++] = 0xffda;	// HALFWIDTH HANGUL LETTER EU
1327
	charset[i++] = 0xffdc;	// HALFWIDTH HANGUL LETTER I
1328
	c = 0xffe0;		// from FULLWIDTH CENT SIGN
1329
	while (c <= 0xffe6)	// ..to FULLWIDTH WON SIGN
1330
		charset[i++] = c++;
1331
	c = 0xffe8;		// from HALFWIDTH FORMS LIGHT VERTICAL
1332
	while (c <= 0xffee)	// ..to HALFWIDTH WHITE CIRCLE
1333
		charset[i++] = c++;
1334
// FFF0..FFFF; Specials
1335
	c = 0xfff9;		// from INTERLINEAR ANNOTATION ANCHOR
1336
	while (c <= 0xfffd)	// ..to REPLACEMENT CHARACTER
1337
		charset[i++] = c++;
1338
// 10000..1007F; Linear B Syllabary
1339
	c = 0x10000;		// from LINEAR B SYLLABLE B008 A
1340
	while (c <= 0x1000b)	// ..to LINEAR B SYLLABLE B046 JE
1341
		charset[i++] = c++;
1342
	c = 0x1000d;		// from LINEAR B SYLLABLE B036 JO
1343
	while (c <= 0x10026)	// ..to LINEAR B SYLLABLE B032 QO
1344
		charset[i++] = c++;
1345
	c = 0x10028;		// from LINEAR B SYLLABLE B060 RA
1346
	while (c <= 0x1003a)	// ..to LINEAR B SYLLABLE B042 WO
1347
		charset[i++] = c++;
1348
	charset[i++] = 0x1003c;	// LINEAR B SYLLABLE B017 ZA
1349
	charset[i++] = 0x1003d;	// LINEAR B SYLLABLE B074 ZE
1350
	c = 0x1003f;		// from LINEAR B SYLLABLE B020 ZO
1351
	while (c <= 0x1004d)	// ..to LINEAR B SYLLABLE B091 TWO
1352
		charset[i++] = c++;
1353
	c = 0x10050;		// from LINEAR B SYMBOL B018
1354
	while (c <= 0x1005d)	// ..to LINEAR B SYMBOL B089
1355
		charset[i++] = c++;
1356
// 10080..100FF; Linear B Ideograms
1357
	c = 0x10080;		// from LINEAR B IDEOGRAM B100 MAN
1358
	while (c <= 0x100fa)	// ..to LINEAR B IDEOGRAM VESSEL B305
1359
		charset[i++] = c++;
1360
// 10100..1013F; Aegean Numbers
1361
	charset[i++] = 0x10100;	// AEGEAN WORD SEPARATOR LINE
1362
	charset[i++] = 0x10102;	// AEGEAN CHECK MARK
1363
	c = 0x10107;		// from AEGEAN NUMBER ONE
1364
	while (c <= 0x10133)	// ..to AEGEAN NUMBER NINETY THOUSAND
1365
		charset[i++] = c++;
1366
	c = 0x10137;		// from AEGEAN WEIGHT BASE UNIT
1367
	while (c <= 0x1013f)	// ..to AEGEAN MEASURE THIRD SUBUNIT
1368
		charset[i++] = c++;
1369
// 10140..1018F; Ancient Greek Numbers
1370
	c = 0x10140;		// from GREEK ACROPHONIC ATTIC ONE QUARTER
1371
	while (c <= 0x1018e)	// ..to NOMISMA SIGN
1372
		charset[i++] = c++;
1373
// 10190..101CF; Ancient Symbols
1374
	c = 0x10190;		// from ROMAN SEXTANS SIGN
1375
	while (c <= 0x1019c)	// ..to ASCIA SYMBOL
1376
		charset[i++] = c++;
1377
	charset[i++] = 0x101a0;	// GREEK SYMBOL TAU RHO
1378
// 101D0..101FF; Phaistos Disc
1379
	c = 0x101d0;		// from PHAISTOS DISC SIGN PEDESTRIAN
1380
	while (c <= 0x101fd)	// ..to PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
1381
		charset[i++] = c++;
1382
// 10280..1029F; Lycian
1383
	c = 0x10280;		// from LYCIAN LETTER A
1384
	while (c <= 0x1029c)	// ..to LYCIAN LETTER X
1385
		charset[i++] = c++;
1386
// 102A0..102DF; Carian
1387
	c = 0x102a0;		// from CARIAN LETTER A
1388
	while (c <= 0x102d0)	// ..to CARIAN LETTER UUU3
1389
		charset[i++] = c++;
1390
// 102E0..102FF; Coptic Epact Numbers
1391
	c = 0x102e0;		// from COPTIC EPACT THOUSANDS MARK
1392
	while (c <= 0x102fb)	// ..to COPTIC EPACT NUMBER NINE HUNDRED
1393
		charset[i++] = c++;
1394
// 10300..1032F; Old Italic
1395
	c = 0x10300;		// from OLD ITALIC LETTER A
1396
	while (c <= 0x10323)	// ..to OLD ITALIC NUMERAL FIFTY
1397
		charset[i++] = c++;
1398
	charset[i++] = 0x1032d;	// OLD ITALIC LETTER YE
1399
	charset[i++] = 0x1032f;	// OLD ITALIC LETTER SOUTHERN TSE
1400
// 10330..1034F; Gothic
1401
	c = 0x10330;		// from GOTHIC LETTER AHSA
1402
	while (c <= 0x1034a)	// ..to GOTHIC LETTER NINE HUNDRED
1403
		charset[i++] = c++;
1404
// 10350..1037F; Old Permic
1405
	c = 0x10350;		// from OLD PERMIC LETTER AN
1406
	while (c <= 0x1037a)	// ..to COMBINING OLD PERMIC LETTER SII
1407
		charset[i++] = c++;
1408
// 10380..1039F; Ugaritic
1409
	c = 0x10380;		// from UGARITIC LETTER ALPA
1410
	while (c <= 0x1039d)	// ..to UGARITIC LETTER SSU
1411
		charset[i++] = c++;
1412
	charset[i++] = 0x1039f;	// UGARITIC WORD DIVIDER
1413
// 103A0..103DF; Old Persian
1414
	c = 0x103a0;		// from OLD PERSIAN SIGN A
1415
	while (c <= 0x103c3)	// ..to OLD PERSIAN SIGN HA
1416
		charset[i++] = c++;
1417
	c = 0x103c8;		// from OLD PERSIAN SIGN AURAMAZDAA
1418
	while (c <= 0x103d5)	// ..to OLD PERSIAN NUMBER HUNDRED
1419
		charset[i++] = c++;
1420
// 10400..1044F; Deseret
1421
	c = 0x10400;		// from DESERET CAPITAL LETTER LONG I
1422
	while (c <= 0x1044f)	// ..to DESERET SMALL LETTER EW
1423
		charset[i++] = c++;
1424
// 10450..1047F; Shavian
1425
	c = 0x10450;		// from SHAVIAN LETTER PEEP
1426
	while (c <= 0x1047f)	// ..to SHAVIAN LETTER YEW
1427
		charset[i++] = c++;
1428
// 10480..104AF; Osmanya
1429
	c = 0x10480;		// from OSMANYA LETTER ALEF
1430
	while (c <= 0x1049d)	// ..to OSMANYA LETTER OO
1431
		charset[i++] = c++;
1432
	c = 0x104a0;		// from OSMANYA DIGIT ZERO
1433
	while (c <= 0x104a9)	// ..to OSMANYA DIGIT NINE
1434
		charset[i++] = c++;
1435
// 104B0..104FF; Osage
1436
	c = 0x104b0;		// from OSAGE CAPITAL LETTER A
1437
	while (c <= 0x104d3)	// ..to OSAGE CAPITAL LETTER ZHA
1438
		charset[i++] = c++;
1439
	c = 0x104d8;		// from OSAGE SMALL LETTER A
1440
	while (c <= 0x104fb)	// ..to OSAGE SMALL LETTER ZHA
1441
		charset[i++] = c++;
1442
// 10500..1052F; Elbasan
1443
	c = 0x10500;		// from ELBASAN LETTER A
1444
	while (c <= 0x10527)	// ..to ELBASAN LETTER KHE
1445
		charset[i++] = c++;
1446
// 10530..1056F; Caucasian Albanian
1447
	c = 0x10530;		// from CAUCASIAN ALBANIAN LETTER ALT
1448
	while (c <= 0x10563)	// ..to CAUCASIAN ALBANIAN LETTER KIW
1449
		charset[i++] = c++;
1450
	charset[i++] = 0x1056f;	// CAUCASIAN ALBANIAN CITATION MARK
1451
// 10600..1077F; Linear A
1452
	c = 0x10600;		// from LINEAR A SIGN AB001
1453
	while (c <= 0x10736)	// ..to LINEAR A SIGN A664
1454
		charset[i++] = c++;
1455
	c = 0x10740;		// from LINEAR A SIGN A701 A
1456
	while (c <= 0x10755)	// ..to LINEAR A SIGN A732 JE
1457
		charset[i++] = c++;
1458
	c = 0x10760;		// from LINEAR A SIGN A800
1459
	while (c <= 0x10767)	// ..to LINEAR A SIGN A807
1460
		charset[i++] = c++;
1461
// 10800..1083F; Cypriot Syllabary
1462
	c = 0x10800;		// from CYPRIOT SYLLABLE A
1463
	while (c <= 0x10805)	// ..to CYPRIOT SYLLABLE JA
1464
		charset[i++] = c++;
1465
	c = 0x1080a;		// from CYPRIOT SYLLABLE KA
1466
	while (c <= 0x10835)	// ..to CYPRIOT SYLLABLE WO
1467
		charset[i++] = c++;
1468
	charset[i++] = 0x10837;	// CYPRIOT SYLLABLE XA
1469
	charset[i++] = 0x10838;	// CYPRIOT SYLLABLE XE
1470
	c = 0x1083c;		// from CYPRIOT SYLLABLE ZA
1471
	while (c <= 0x1083f)	// ..to CYPRIOT SYLLABLE ZO
1472
		charset[i++] = c++;
1473
// 10840..1085F; Imperial Aramaic
1474
	c = 0x10840;		// from IMPERIAL ARAMAIC LETTER ALEPH
1475
	while (c <= 0x10855)	// ..to IMPERIAL ARAMAIC LETTER TAW
1476
		charset[i++] = c++;
1477
	c = 0x10857;		// from IMPERIAL ARAMAIC SECTION SIGN
1478
	while (c <= 0x1085f)	// ..to IMPERIAL ARAMAIC NUMBER TEN THOUSAND
1479
		charset[i++] = c++;
1480
// 10860..1087F; Palmyrene
1481
	c = 0x10860;		// from PALMYRENE LETTER ALEPH
1482
	while (c <= 0x1087f)	// ..to PALMYRENE NUMBER TWENTY
1483
		charset[i++] = c++;
1484
// 10880..108AF; Nabataean
1485
	c = 0x10880;		// from NABATAEAN LETTER FINAL ALEPH
1486
	while (c <= 0x1089e)	// ..to NABATAEAN LETTER TAW
1487
		charset[i++] = c++;
1488
	c = 0x108a7;		// from NABATAEAN NUMBER ONE
1489
	while (c <= 0x108af)	// ..to NABATAEAN NUMBER ONE HUNDRED
1490
		charset[i++] = c++;
1491
// 108E0..108FF; Hatran
1492
	c = 0x108e0;		// from HATRAN LETTER ALEPH
1493
	while (c <= 0x108f2)	// ..to HATRAN LETTER QOPH
1494
		charset[i++] = c++;
1495
	charset[i++] = 0x108f4;	// HATRAN LETTER SHIN
1496
	charset[i++] = 0x108f5;	// HATRAN LETTER TAW
1497
	c = 0x108fb;		// from HATRAN NUMBER ONE
1498
	while (c <= 0x108ff)	// ..to HATRAN NUMBER ONE HUNDRED
1499
		charset[i++] = c++;
1500
// 10900..1091F; Phoenician
1501
	c = 0x10900;		// from PHOENICIAN LETTER ALF
1502
	while (c <= 0x1091b)	// ..to PHOENICIAN NUMBER THREE
1503
		charset[i++] = c++;
1504
	charset[i++] = 0x1091f;	// PHOENICIAN WORD SEPARATOR
1505
// 10920..1093F; Lydian
1506
	c = 0x10920;		// from LYDIAN LETTER A
1507
	while (c <= 0x10939)	// ..to LYDIAN LETTER C
1508
		charset[i++] = c++;
1509
	charset[i++] = 0x1093f;	// LYDIAN TRIANGULAR MARK
1510
// 10980..1099F; Meroitic Hieroglyphs
1511
	c = 0x10980;		// from MEROITIC HIEROGLYPHIC LETTER A
1512
	while (c <= 0x1099f)	// ..to MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2
1513
		charset[i++] = c++;
1514
// 109A0..109FF; Meroitic Cursive
1515
	c = 0x109a0;		// from MEROITIC CURSIVE LETTER A
1516
	while (c <= 0x109b7)	// ..to MEROITIC CURSIVE LETTER DA
1517
		charset[i++] = c++;
1518
	c = 0x109bc;		// from MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS
1519
	while (c <= 0x109cf)	// ..to MEROITIC CURSIVE NUMBER SEVENTY
1520
		charset[i++] = c++;
1521
	c = 0x109d2;		// from MEROITIC CURSIVE NUMBER ONE HUNDRED
1522
	while (c <= 0x109ff)	// ..to MEROITIC CURSIVE FRACTION TEN TWELFTHS
1523
		charset[i++] = c++;
1524
// 10A00..10A5F; Kharoshthi
1525
	c = 0x10a00;		// from KHAROSHTHI LETTER A
1526
	while (c <= 0x10a03)	// ..to KHAROSHTHI VOWEL SIGN VOCALIC R
1527
		charset[i++] = c++;
1528
	charset[i++] = 0x10a05;	// KHAROSHTHI VOWEL SIGN E
1529
	charset[i++] = 0x10a06;	// KHAROSHTHI VOWEL SIGN O
1530
	c = 0x10a0c;		// from KHAROSHTHI VOWEL LENGTH MARK
1531
	while (c <= 0x10a13)	// ..to KHAROSHTHI LETTER GHA
1532
		charset[i++] = c++;
1533
	charset[i++] = 0x10a15;	// KHAROSHTHI LETTER CA
1534
	charset[i++] = 0x10a17;	// KHAROSHTHI LETTER JA
1535
	c = 0x10a19;		// from KHAROSHTHI LETTER NYA
1536
	while (c <= 0x10a35)	// ..to KHAROSHTHI LETTER VHA
1537
		charset[i++] = c++;
1538
	charset[i++] = 0x10a38;	// KHAROSHTHI SIGN BAR ABOVE
1539
	charset[i++] = 0x10a3a;	// KHAROSHTHI SIGN DOT BELOW
1540
	c = 0x10a3f;		// from KHAROSHTHI VIRAMA
1541
	while (c <= 0x10a48)	// ..to KHAROSHTHI FRACTION ONE HALF
1542
		charset[i++] = c++;
1543
	c = 0x10a50;		// from KHAROSHTHI PUNCTUATION DOT
1544
	while (c <= 0x10a58)	// ..to KHAROSHTHI PUNCTUATION LINES
1545
		charset[i++] = c++;
1546
// 10A60..10A7F; Old South Arabian
1547
	c = 0x10a60;		// from OLD SOUTH ARABIAN LETTER HE
1548
	while (c <= 0x10a7f)	// ..to OLD SOUTH ARABIAN NUMERIC INDICATOR
1549
		charset[i++] = c++;
1550
// 10A80..10A9F; Old North Arabian
1551
	c = 0x10a80;		// from OLD NORTH ARABIAN LETTER HEH
1552
	while (c <= 0x10a9f)	// ..to OLD NORTH ARABIAN NUMBER TWENTY
1553
		charset[i++] = c++;
1554
// 10AC0..10AFF; Manichaean
1555
	c = 0x10ac0;		// from MANICHAEAN LETTER ALEPH
1556
	while (c <= 0x10ae6)	// ..to MANICHAEAN ABBREVIATION MARK BELOW
1557
		charset[i++] = c++;
1558
	c = 0x10aeb;		// from MANICHAEAN NUMBER ONE
1559
	while (c <= 0x10af6)	// ..to MANICHAEAN PUNCTUATION LINE FILLER
1560
		charset[i++] = c++;
1561
// 10B00..10B3F; Avestan
1562
	c = 0x10b00;		// from AVESTAN LETTER A
1563
	while (c <= 0x10b35)	// ..to AVESTAN LETTER HE
1564
		charset[i++] = c++;
1565
	c = 0x10b39;		// from AVESTAN ABBREVIATION MARK
1566
	while (c <= 0x10b3f)	// ..to LARGE ONE RING OVER TWO RINGS PUNCTUATION
1567
		charset[i++] = c++;
1568
// 10B40..10B5F; Inscriptional Parthian
1569
	c = 0x10b40;		// from INSCRIPTIONAL PARTHIAN LETTER ALEPH
1570
	while (c <= 0x10b55)	// ..to INSCRIPTIONAL PARTHIAN LETTER TAW
1571
		charset[i++] = c++;
1572
	c = 0x10b58;		// from INSCRIPTIONAL PARTHIAN NUMBER ONE
1573
	while (c <= 0x10b5f)	// ..to INSCRIPTIONAL PARTHIAN NUMBER ONE THOUSAND
1574
		charset[i++] = c++;
1575
// 10B60..10B7F; Inscriptional Pahlavi
1576
	c = 0x10b60;		// from INSCRIPTIONAL PAHLAVI LETTER ALEPH
1577
	while (c <= 0x10b72)	// ..to INSCRIPTIONAL PAHLAVI LETTER TAW
1578
		charset[i++] = c++;
1579
	c = 0x10b78;		// from INSCRIPTIONAL PAHLAVI NUMBER ONE
1580
	while (c <= 0x10b7f)	// ..to INSCRIPTIONAL PAHLAVI NUMBER ONE THOUSAND
1581
		charset[i++] = c++;
1582
// 10B80..10BAF; Psalter Pahlavi
1583
	c = 0x10b80;		// from PSALTER PAHLAVI LETTER ALEPH
1584
	while (c <= 0x10b91)	// ..to PSALTER PAHLAVI LETTER TAW
1585
		charset[i++] = c++;
1586
	c = 0x10b99;		// from PSALTER PAHLAVI SECTION MARK
1587
	while (c <= 0x10b9c)	// ..to PSALTER PAHLAVI FOUR DOTS WITH DOT
1588
		charset[i++] = c++;
1589
	c = 0x10ba9;		// from PSALTER PAHLAVI NUMBER ONE
1590
	while (c <= 0x10baf)	// ..to PSALTER PAHLAVI NUMBER ONE HUNDRED
1591
		charset[i++] = c++;
1592
// 10C00..10C4F; Old Turkic
1593
	c = 0x10c00;		// from OLD TURKIC LETTER ORKHON A
1594
	while (c <= 0x10c48)	// ..to OLD TURKIC LETTER ORKHON BASH
1595
		charset[i++] = c++;
1596
// 10C80..10CFF; Old Hungarian
1597
	c = 0x10c80;		// from OLD HUNGARIAN CAPITAL LETTER A
1598
	while (c <= 0x10cb2)	// ..to OLD HUNGARIAN CAPITAL LETTER US
1599
		charset[i++] = c++;
1600
	c = 0x10cc0;		// from OLD HUNGARIAN SMALL LETTER A
1601
	while (c <= 0x10cf2)	// ..to OLD HUNGARIAN SMALL LETTER US
1602
		charset[i++] = c++;
1603
	c = 0x10cfa;		// from OLD HUNGARIAN NUMBER ONE
1604
	while (c <= 0x10cff)	// ..to OLD HUNGARIAN NUMBER ONE THOUSAND
1605
		charset[i++] = c++;
1606
// 10D00..10D3F; Hanifi Rohingya
1607
	c = 0x10d00;		// from HANIFI ROHINGYA LETTER A
1608
	while (c <= 0x10d27)	// ..to HANIFI ROHINGYA SIGN TASSI
1609
		charset[i++] = c++;
1610
	c = 0x10d30;		// from HANIFI ROHINGYA DIGIT ZERO
1611
	while (c <= 0x10d39)	// ..to HANIFI ROHINGYA DIGIT NINE
1612
		charset[i++] = c++;
1613
// 10E60..10E7F; Rumi Numeral Symbols
1614
	c = 0x10e60;		// from RUMI DIGIT ONE
1615
	while (c <= 0x10e7e)	// ..to RUMI FRACTION TWO THIRDS
1616
		charset[i++] = c++;
1617
// 10E80..10EBF; Yezidi
1618
	c = 0x10e80;		// from YEZIDI LETTER ELIF
1619
	while (c <= 0x10ea9)	// ..to YEZIDI LETTER ET
1620
		charset[i++] = c++;
1621
	charset[i++] = 0x10eab;	// YEZIDI COMBINING HAMZA MARK
1622
	charset[i++] = 0x10ead;	// YEZIDI HYPHENATION MARK
1623
	charset[i++] = 0x10eb0;	// YEZIDI LETTER LAM WITH DOT ABOVE
1624
	charset[i++] = 0x10eb1;	// YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE
1625
// 10F00..10F2F; Old Sogdian
1626
	c = 0x10f00;		// from OLD SOGDIAN LETTER ALEPH
1627
	while (c <= 0x10f27)	// ..to OLD SOGDIAN LIGATURE AYIN-DALETH
1628
		charset[i++] = c++;
1629
// 10F30..10F6F; Sogdian
1630
	c = 0x10f30;		// from SOGDIAN LETTER ALEPH
1631
	while (c <= 0x10f59)	// ..to SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
1632
		charset[i++] = c++;
1633
// 10FB0..10FDF; Chorasmian
1634
	c = 0x10fb0;		// from CHORASMIAN LETTER ALEPH
1635
	while (c <= 0x10fcb)	// ..to CHORASMIAN NUMBER ONE HUNDRED
1636
		charset[i++] = c++;
1637
// 10FE0..10FFF; Elymaic
1638
	c = 0x10fe0;		// from ELYMAIC LETTER ALEPH
1639
	while (c <= 0x10ff6)	// ..to ELYMAIC LIGATURE ZAYIN-YODH
1640
		charset[i++] = c++;
1641
// 11000..1107F; Brahmi
1642
	c = 0x11000;		// from BRAHMI SIGN CANDRABINDU
1643
	while (c <= 0x1104d)	// ..to BRAHMI PUNCTUATION LOTUS
1644
		charset[i++] = c++;
1645
	c = 0x11052;		// from BRAHMI NUMBER ONE
1646
	while (c <= 0x1106f)	// ..to BRAHMI DIGIT NINE
1647
		charset[i++] = c++;
1648
	charset[i++] = 0x1107f;	// BRAHMI NUMBER JOINER
1649
// 11080..110CF; Kaithi
1650
	c = 0x11080;		// from KAITHI SIGN CANDRABINDU
1651
	while (c <= 0x110c1)	// ..to KAITHI DOUBLE DANDA
1652
		charset[i++] = c++;
1653
	charset[i++] = 0x110cd;	// KAITHI NUMBER SIGN ABOVE
1654
// 110D0..110FF; Sora Sompeng
1655
	c = 0x110d0;		// from SORA SOMPENG LETTER SAH
1656
	while (c <= 0x110e8)	// ..to SORA SOMPENG LETTER MAE
1657
		charset[i++] = c++;
1658
	c = 0x110f0;		// from SORA SOMPENG DIGIT ZERO
1659
	while (c <= 0x110f9)	// ..to SORA SOMPENG DIGIT NINE
1660
		charset[i++] = c++;
1661
// 11100..1114F; Chakma
1662
	c = 0x11100;		// from CHAKMA SIGN CANDRABINDU
1663
	while (c <= 0x11134)	// ..to CHAKMA MAAYYAA
1664
		charset[i++] = c++;
1665
	c = 0x11136;		// from CHAKMA DIGIT ZERO
1666
	while (c <= 0x11147)	// ..to CHAKMA LETTER VAA
1667
		charset[i++] = c++;
1668
// 11150..1117F; Mahajani
1669
	c = 0x11150;		// from MAHAJANI LETTER A
1670
	while (c <= 0x11176)	// ..to MAHAJANI LIGATURE SHRI
1671
		charset[i++] = c++;
1672
// 11180..111DF; Sharada
1673
	c = 0x11180;		// from SHARADA SIGN CANDRABINDU
1674
	while (c <= 0x111df)	// ..to SHARADA SECTION MARK-2
1675
		charset[i++] = c++;
1676
// 111E0..111FF; Sinhala Archaic Numbers
1677
	c = 0x111e1;		// from SINHALA ARCHAIC DIGIT ONE
1678
	while (c <= 0x111f4)	// ..to SINHALA ARCHAIC NUMBER ONE THOUSAND
1679
		charset[i++] = c++;
1680
// 11200..1124F; Khojki
1681
	c = 0x11200;		// from KHOJKI LETTER A
1682
	while (c <= 0x11211)	// ..to KHOJKI LETTER JJA
1683
		charset[i++] = c++;
1684
	c = 0x11213;		// from KHOJKI LETTER NYA
1685
	while (c <= 0x1123e)	// ..to KHOJKI SIGN SUKUN
1686
		charset[i++] = c++;
1687
// 11280..112AF; Multani
1688
	c = 0x11280;		// from MULTANI LETTER A
1689
	while (c <= 0x11286)	// ..to MULTANI LETTER GA
1690
		charset[i++] = c++;
1691
	c = 0x1128a;		// from MULTANI LETTER CA
1692
	while (c <= 0x1128d)	// ..to MULTANI LETTER JJA
1693
		charset[i++] = c++;
1694
	c = 0x1128f;		// from MULTANI LETTER NYA
1695
	while (c <= 0x1129d)	// ..to MULTANI LETTER BA
1696
		charset[i++] = c++;
1697
	c = 0x1129f;		// from MULTANI LETTER BHA
1698
	while (c <= 0x112a9)	// ..to MULTANI SECTION MARK
1699
		charset[i++] = c++;
1700
// 112B0..112FF; Khudawadi
1701
	c = 0x112b0;		// from KHUDAWADI LETTER A
1702
	while (c <= 0x112ea)	// ..to KHUDAWADI SIGN VIRAMA
1703
		charset[i++] = c++;
1704
	c = 0x112f0;		// from KHUDAWADI DIGIT ZERO
1705
	while (c <= 0x112f9)	// ..to KHUDAWADI DIGIT NINE
1706
		charset[i++] = c++;
1707
// 11300..1137F; Grantha
1708
	c = 0x11300;		// from GRANTHA SIGN COMBINING ANUSVARA ABOVE
1709
	while (c <= 0x11303)	// ..to GRANTHA SIGN VISARGA
1710
		charset[i++] = c++;
1711
	c = 0x11305;		// from GRANTHA LETTER A
1712
	while (c <= 0x1130c)	// ..to GRANTHA LETTER VOCALIC L
1713
		charset[i++] = c++;
1714
	charset[i++] = 0x1130f;	// GRANTHA LETTER EE
1715
	charset[i++] = 0x11310;	// GRANTHA LETTER AI
1716
	c = 0x11313;		// from GRANTHA LETTER OO
1717
	while (c <= 0x11328)	// ..to GRANTHA LETTER NA
1718
		charset[i++] = c++;
1719
	c = 0x1132a;		// from GRANTHA LETTER PA
1720
	while (c <= 0x11330)	// ..to GRANTHA LETTER RA
1721
		charset[i++] = c++;
1722
	charset[i++] = 0x11332;	// GRANTHA LETTER LA
1723
	charset[i++] = 0x11333;	// GRANTHA LETTER LLA
1724
	c = 0x11335;		// from GRANTHA LETTER VA
1725
	while (c <= 0x11339)	// ..to GRANTHA LETTER HA
1726
		charset[i++] = c++;
1727
	c = 0x1133b;		// from COMBINING BINDU BELOW
1728
	while (c <= 0x11344)	// ..to GRANTHA VOWEL SIGN VOCALIC RR
1729
		charset[i++] = c++;
1730
	charset[i++] = 0x11347;	// GRANTHA VOWEL SIGN EE
1731
	charset[i++] = 0x11348;	// GRANTHA VOWEL SIGN AI
1732
	charset[i++] = 0x1134b;	// GRANTHA VOWEL SIGN OO
1733
	charset[i++] = 0x1134d;	// GRANTHA SIGN VIRAMA
1734
	c = 0x1135d;		// from GRANTHA SIGN PLUTA
1735
	while (c <= 0x11363)	// ..to GRANTHA VOWEL SIGN VOCALIC LL
1736
		charset[i++] = c++;
1737
	c = 0x11366;		// from COMBINING GRANTHA DIGIT ZERO
1738
	while (c <= 0x1136c)	// ..to COMBINING GRANTHA DIGIT SIX
1739
		charset[i++] = c++;
1740
	c = 0x11370;		// from COMBINING GRANTHA LETTER A
1741
	while (c <= 0x11374)	// ..to COMBINING GRANTHA LETTER PA
1742
		charset[i++] = c++;
1743
// 11400..1147F; Newa
1744
	c = 0x11400;		// from NEWA LETTER A
1745
	while (c <= 0x1145b)	// ..to NEWA PLACEHOLDER MARK
1746
		charset[i++] = c++;
1747
	c = 0x1145d;		// from NEWA INSERTION SIGN
1748
	while (c <= 0x11461)	// ..to NEWA SIGN UPADHMANIYA
1749
		charset[i++] = c++;
1750
// 11480..114DF; Tirhuta
1751
	c = 0x11480;		// from TIRHUTA ANJI
1752
	while (c <= 0x114c7)	// ..to TIRHUTA OM
1753
		charset[i++] = c++;
1754
	c = 0x114d0;		// from TIRHUTA DIGIT ZERO
1755
	while (c <= 0x114d9)	// ..to TIRHUTA DIGIT NINE
1756
		charset[i++] = c++;
1757
// 11580..115FF; Siddham
1758
	c = 0x11580;		// from SIDDHAM LETTER A
1759
	while (c <= 0x115b5)	// ..to SIDDHAM VOWEL SIGN VOCALIC RR
1760
		charset[i++] = c++;
1761
	c = 0x115b8;		// from SIDDHAM VOWEL SIGN E
1762
	while (c <= 0x115dd)	// ..to SIDDHAM VOWEL SIGN ALTERNATE UU
1763
		charset[i++] = c++;
1764
// 11600..1165F; Modi
1765
	c = 0x11600;		// from MODI LETTER A
1766
	while (c <= 0x11644)	// ..to MODI SIGN HUVA
1767
		charset[i++] = c++;
1768
	c = 0x11650;		// from MODI DIGIT ZERO
1769
	while (c <= 0x11659)	// ..to MODI DIGIT NINE
1770
		charset[i++] = c++;
1771
// 11660..1167F; Mongolian Supplement
1772
	c = 0x11660;		// from MONGOLIAN BIRGA WITH ORNAMENT
1773
	while (c <= 0x1166c)	// ..to MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT
1774
		charset[i++] = c++;
1775
// 11680..116CF; Takri
1776
	c = 0x11680;		// from TAKRI LETTER A
1777
	while (c <= 0x116b8)	// ..to TAKRI LETTER ARCHAIC KHA
1778
		charset[i++] = c++;
1779
	c = 0x116c0;		// from TAKRI DIGIT ZERO
1780
	while (c <= 0x116c9)	// ..to TAKRI DIGIT NINE
1781
		charset[i++] = c++;
1782
// 11700..1173F; Ahom
1783
	c = 0x11700;		// from AHOM LETTER KA
1784
	while (c <= 0x1171a)	// ..to AHOM LETTER ALTERNATE BA
1785
		charset[i++] = c++;
1786
	c = 0x1171d;		// from AHOM CONSONANT SIGN MEDIAL LA
1787
	while (c <= 0x1172b)	// ..to AHOM SIGN KILLER
1788
		charset[i++] = c++;
1789
	c = 0x11730;		// from AHOM DIGIT ZERO
1790
	while (c <= 0x1173f)	// ..to AHOM SYMBOL VI
1791
		charset[i++] = c++;
1792
// 11800..1184F; Dogra
1793
	c = 0x11800;		// from DOGRA LETTER A
1794
	while (c <= 0x1183b)	// ..to DOGRA ABBREVIATION SIGN
1795
		charset[i++] = c++;
1796
// 118A0..118FF; Warang Citi
1797
	c = 0x118a0;		// from WARANG CITI CAPITAL LETTER NGAA
1798
	while (c <= 0x118f2)	// ..to WARANG CITI NUMBER NINETY
1799
		charset[i++] = c++;
1800
	charset[i++] = 0x118ff;	// WARANG CITI OM
1801
// 11900..1195F; Dives Akuru
1802
	c = 0x11900;		// from DIVES AKURU LETTER A
1803
	while (c <= 0x11906)	// ..to DIVES AKURU LETTER E
1804
		charset[i++] = c++;
1805
	c = 0x1190c;		// from DIVES AKURU LETTER KA
1806
	while (c <= 0x11913)	// ..to DIVES AKURU LETTER JA
1807
		charset[i++] = c++;
1808
	charset[i++] = 0x11915;	// DIVES AKURU LETTER NYA
1809
	charset[i++] = 0x11916;	// DIVES AKURU LETTER TTA
1810
	c = 0x11918;		// from DIVES AKURU LETTER DDA
1811
	while (c <= 0x11935)	// ..to DIVES AKURU VOWEL SIGN E
1812
		charset[i++] = c++;
1813
	charset[i++] = 0x11937;	// DIVES AKURU VOWEL SIGN AI
1814
	charset[i++] = 0x11938;	// DIVES AKURU VOWEL SIGN O
1815
	c = 0x1193b;		// from DIVES AKURU SIGN ANUSVARA
1816
	while (c <= 0x11946)	// ..to DIVES AKURU END OF TEXT MARK
1817
		charset[i++] = c++;
1818
	c = 0x11950;		// from DIVES AKURU DIGIT ZERO
1819
	while (c <= 0x11959)	// ..to DIVES AKURU DIGIT NINE
1820
		charset[i++] = c++;
1821
// 119A0..119FF; Nandinagari
1822
	c = 0x119a0;		// from NANDINAGARI LETTER A
1823
	while (c <= 0x119a7)	// ..to NANDINAGARI LETTER VOCALIC RR
1824
		charset[i++] = c++;
1825
	c = 0x119aa;		// from NANDINAGARI LETTER E
1826
	while (c <= 0x119d7)	// ..to NANDINAGARI VOWEL SIGN VOCALIC RR
1827
		charset[i++] = c++;
1828
	c = 0x119da;		// from NANDINAGARI VOWEL SIGN E
1829
	while (c <= 0x119e4)	// ..to NANDINAGARI VOWEL SIGN PRISHTHAMATRA E
1830
		charset[i++] = c++;
1831
// 11A00..11A4F; Zanabazar Square
1832
	c = 0x11a00;		// from ZANABAZAR SQUARE LETTER A
1833
	while (c <= 0x11a47)	// ..to ZANABAZAR SQUARE SUBJOINER
1834
		charset[i++] = c++;
1835
// 11A50..11AAF; Soyombo
1836
	c = 0x11a50;		// from SOYOMBO LETTER A
1837
	while (c <= 0x11aa2)	// ..to SOYOMBO TERMINAL MARK-2
1838
		charset[i++] = c++;
1839
// 11AC0..11AFF; Pau Cin Hau
1840
	c = 0x11ac0;		// from PAU CIN HAU LETTER PA
1841
	while (c <= 0x11af8)	// ..to PAU CIN HAU GLOTTAL STOP FINAL
1842
		charset[i++] = c++;
1843
// 11C00..11C6F; Bhaiksuki
1844
	c = 0x11c00;		// from BHAIKSUKI LETTER A
1845
	while (c <= 0x11c08)	// ..to BHAIKSUKI LETTER VOCALIC L
1846
		charset[i++] = c++;
1847
	c = 0x11c0a;		// from BHAIKSUKI LETTER E
1848
	while (c <= 0x11c36)	// ..to BHAIKSUKI VOWEL SIGN VOCALIC L
1849
		charset[i++] = c++;
1850
	c = 0x11c38;		// from BHAIKSUKI VOWEL SIGN E
1851
	while (c <= 0x11c45)	// ..to BHAIKSUKI GAP FILLER-2
1852
		charset[i++] = c++;
1853
	c = 0x11c50;		// from BHAIKSUKI DIGIT ZERO
1854
	while (c <= 0x11c6c)	// ..to BHAIKSUKI HUNDREDS UNIT MARK
1855
		charset[i++] = c++;
1856
// 11C70..11CBF; Marchen
1857
	c = 0x11c70;		// from MARCHEN HEAD MARK
1858
	while (c <= 0x11c8f)	// ..to MARCHEN LETTER A
1859
		charset[i++] = c++;
1860
	c = 0x11c92;		// from MARCHEN SUBJOINED LETTER KA
1861
	while (c <= 0x11ca7)	// ..to MARCHEN SUBJOINED LETTER ZA
1862
		charset[i++] = c++;
1863
	c = 0x11ca9;		// from MARCHEN SUBJOINED LETTER YA
1864
	while (c <= 0x11cb6)	// ..to MARCHEN SIGN CANDRABINDU
1865
		charset[i++] = c++;
1866
// 11D00..11D5F; Masaram Gondi
1867
	c = 0x11d00;		// from MASARAM GONDI LETTER A
1868
	while (c <= 0x11d06)	// ..to MASARAM GONDI LETTER E
1869
		charset[i++] = c++;
1870
	charset[i++] = 0x11d08;	// MASARAM GONDI LETTER AI
1871
	charset[i++] = 0x11d09;	// MASARAM GONDI LETTER O
1872
	c = 0x11d0b;		// from MASARAM GONDI LETTER AU
1873
	while (c <= 0x11d36)	// ..to MASARAM GONDI VOWEL SIGN VOCALIC R
1874
		charset[i++] = c++;
1875
	charset[i++] = 0x11d3c;	// MASARAM GONDI VOWEL SIGN AI
1876
	charset[i++] = 0x11d3d;	// MASARAM GONDI VOWEL SIGN O
1877
	c = 0x11d3f;		// from MASARAM GONDI VOWEL SIGN AU
1878
	while (c <= 0x11d47)	// ..to MASARAM GONDI RA-KARA
1879
		charset[i++] = c++;
1880
	c = 0x11d50;		// from MASARAM GONDI DIGIT ZERO
1881
	while (c <= 0x11d59)	// ..to MASARAM GONDI DIGIT NINE
1882
		charset[i++] = c++;
1883
// 11D60..11DAF; Gunjala Gondi
1884
	c = 0x11d60;		// from GUNJALA GONDI LETTER A
1885
	while (c <= 0x11d65)	// ..to GUNJALA GONDI LETTER UU
1886
		charset[i++] = c++;
1887
	charset[i++] = 0x11d67;	// GUNJALA GONDI LETTER EE
1888
	charset[i++] = 0x11d68;	// GUNJALA GONDI LETTER AI
1889
	c = 0x11d6a;		// from GUNJALA GONDI LETTER OO
1890
	while (c <= 0x11d8e)	// ..to GUNJALA GONDI VOWEL SIGN UU
1891
		charset[i++] = c++;
1892
	charset[i++] = 0x11d90;	// GUNJALA GONDI VOWEL SIGN EE
1893
	charset[i++] = 0x11d91;	// GUNJALA GONDI VOWEL SIGN AI
1894
	c = 0x11d93;		// from GUNJALA GONDI VOWEL SIGN OO
1895
	while (c <= 0x11d98)	// ..to GUNJALA GONDI OM
1896
		charset[i++] = c++;
1897
	c = 0x11da0;		// from GUNJALA GONDI DIGIT ZERO
1898
	while (c <= 0x11da9)	// ..to GUNJALA GONDI DIGIT NINE
1899
		charset[i++] = c++;
1900
// 11EE0..11EFF; Makasar
1901
	c = 0x11ee0;		// from MAKASAR LETTER KA
1902
	while (c <= 0x11ef8)	// ..to MAKASAR END OF SECTION
1903
		charset[i++] = c++;
1904
// 11FB0..11FBF; Lisu Supplement
1905
	charset[i++] = 0x11fb0;	// LISU LETTER YHA
1906
// 11FC0..11FFF; Tamil Supplement
1907
	c = 0x11fc0;		// from TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH
1908
	while (c <= 0x11ff1)	// ..to TAMIL SIGN VAKAIYARAA
1909
		charset[i++] = c++;
1910
	charset[i++] = 0x11fff;	// TAMIL PUNCTUATION END OF TEXT
1911
// 12000..123FF; Cuneiform
1912
	c = 0x12000;		// from CUNEIFORM SIGN A
1913
	while (c <= 0x12399)	// ..to CUNEIFORM SIGN U U
1914
		charset[i++] = c++;
1915
// 12400..1247F; Cuneiform Numbers and Punctuation
1916
	c = 0x12400;		// from CUNEIFORM NUMERIC SIGN TWO ASH
1917
	while (c <= 0x1246e)	// ..to CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
1918
		charset[i++] = c++;
1919
	c = 0x12470;		// from CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER
1920
	while (c <= 0x12474)	// ..to CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
1921
		charset[i++] = c++;
1922
// 12480..1254F; Early Dynastic Cuneiform
1923
	c = 0x12480;		// from CUNEIFORM SIGN AB TIMES NUN TENU
1924
	while (c <= 0x12543)	// ..to CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
1925
		charset[i++] = c++;
1926
// 13000..1342F; Egyptian Hieroglyphs
1927
	c = 0x13000;		// from EGYPTIAN HIEROGLYPH A001
1928
	while (c <= 0x1342e)	// ..to EGYPTIAN HIEROGLYPH AA032
1929
		charset[i++] = c++;
1930
// 13430..1343F; Egyptian Hieroglyph Format Controls
1931
	c = 0x13430;		// from EGYPTIAN HIEROGLYPH VERTICAL JOINER
1932
	while (c <= 0x13438)	// ..to EGYPTIAN HIEROGLYPH END SEGMENT
1933
		charset[i++] = c++;
1934
// 14400..1467F; Anatolian Hieroglyphs
1935
	c = 0x14400;		// from ANATOLIAN HIEROGLYPH A001
1936
	while (c <= 0x14646)	// ..to ANATOLIAN HIEROGLYPH A530
1937
		charset[i++] = c++;
1938
// 16800..16A3F; Bamum Supplement
1939
	c = 0x16800;		// from BAMUM LETTER PHASE-A NGKUE MFON
1940
	while (c <= 0x16a38)	// ..to BAMUM LETTER PHASE-F VUEQ
1941
		charset[i++] = c++;
1942
// 16A40..16A6F; Mro
1943
	c = 0x16a40;		// from MRO LETTER TA
1944
	while (c <= 0x16a5e)	// ..to MRO LETTER TEK
1945
		charset[i++] = c++;
1946
	c = 0x16a60;		// from MRO DIGIT ZERO
1947
	while (c <= 0x16a69)	// ..to MRO DIGIT NINE
1948
		charset[i++] = c++;
1949
	charset[i++] = 0x16a6e;	// MRO DANDA
1950
	charset[i++] = 0x16a6f;	// MRO DOUBLE DANDA
1951
// 16AD0..16AFF; Bassa Vah
1952
	c = 0x16ad0;		// from BASSA VAH LETTER ENNI
1953
	while (c <= 0x16aed)	// ..to BASSA VAH LETTER I
1954
		charset[i++] = c++;
1955
	c = 0x16af0;		// from BASSA VAH COMBINING HIGH TONE
1956
	while (c <= 0x16af5)	// ..to BASSA VAH FULL STOP
1957
		charset[i++] = c++;
1958
// 16B00..16B8F; Pahawh Hmong
1959
	c = 0x16b00;		// from PAHAWH HMONG VOWEL KEEB
1960
	while (c <= 0x16b45)	// ..to PAHAWH HMONG SIGN CIM TSOV ROG
1961
		charset[i++] = c++;
1962
	c = 0x16b50;		// from PAHAWH HMONG DIGIT ZERO
1963
	while (c <= 0x16b59)	// ..to PAHAWH HMONG DIGIT NINE
1964
		charset[i++] = c++;
1965
	c = 0x16b5b;		// from PAHAWH HMONG NUMBER TENS
1966
	while (c <= 0x16b61)	// ..to PAHAWH HMONG NUMBER TRILLIONS
1967
		charset[i++] = c++;
1968
	c = 0x16b63;		// from PAHAWH HMONG SIGN VOS LUB
1969
	while (c <= 0x16b77)	// ..to PAHAWH HMONG SIGN CIM NRES TOS
1970
		charset[i++] = c++;
1971
	c = 0x16b7d;		// from PAHAWH HMONG CLAN SIGN TSHEEJ
1972
	while (c <= 0x16b8f)	// ..to PAHAWH HMONG CLAN SIGN VWJ
1973
		charset[i++] = c++;
1974
// 16E40..16E9F; Medefaidrin
1975
	c = 0x16e40;		// from MEDEFAIDRIN CAPITAL LETTER M
1976
	while (c <= 0x16e9a)	// ..to MEDEFAIDRIN EXCLAMATION OH
1977
		charset[i++] = c++;
1978
// 16F00..16F9F; Miao
1979
	c = 0x16f00;		// from MIAO LETTER PA
1980
	while (c <= 0x16f4a)	// ..to MIAO LETTER RTE
1981
		charset[i++] = c++;
1982
	c = 0x16f4f;		// from MIAO SIGN CONSONANT MODIFIER BAR
1983
	while (c <= 0x16f87)	// ..to MIAO VOWEL SIGN UI
1984
		charset[i++] = c++;
1985
	c = 0x16f8f;		// from MIAO TONE RIGHT
1986
	while (c <= 0x16f9f)	// ..to MIAO LETTER REFORMED TONE-8
1987
		charset[i++] = c++;
1988
// 16FE0..16FFF; Ideographic Symbols and Punctuation
1989
	c = 0x16fe0;		// from TANGUT ITERATION MARK
1990
	while (c <= 0x16fe4)	// ..to KHITAN SMALL SCRIPT FILLER
1991
		charset[i++] = c++;
1992
	charset[i++] = 0x16ff0;	// VIETNAMESE ALTERNATE READING MARK CA
1993
	charset[i++] = 0x16ff1;	// VIETNAMESE ALTERNATE READING MARK NHAY
1994
// 17000..187FF; Tangut
1995
	c = 0x17000;		// from <Tangut Ideograph, First>
1996
	while (c <= 0x187f7)	// ..to <Tangut Ideograph, Last>
1997
		charset[i++] = c++;
1998
// 18800..18AFF; Tangut Components
1999
	c = 0x18800;		// from TANGUT COMPONENT-001
2000
	while (c <= 0x18aff)	// ..to TANGUT COMPONENT-768
2001
		charset[i++] = c++;
2002
// 18B00..18CFF; Khitan Small Script
2003
	c = 0x18b00;		// from KHITAN SMALL SCRIPT CHARACTER-18B00
2004
	while (c <= 0x18cd5)	// ..to KHITAN SMALL SCRIPT CHARACTER-18CD5
2005
		charset[i++] = c++;
2006
// 18D00..18D8F; Tangut Supplement
2007
	c = 0x18d00;		// from <Tangut Ideograph Supplement, First>
2008
	while (c <= 0x18d08)	// ..to <Tangut Ideograph Supplement, Last>
2009
		charset[i++] = c++;
2010
// 1B000..1B0FF; Kana Supplement
2011
	c = 0x1b000;		// from KATAKANA LETTER ARCHAIC E
2012
	while (c <= 0x1b0ff)	// ..to HENTAIGANA LETTER RE-2
2013
		charset[i++] = c++;
2014
// 1B100..1B12F; Kana Extended-A
2015
	c = 0x1b100;		// from HENTAIGANA LETTER RE-3
2016
	while (c <= 0x1b11e)	// ..to HENTAIGANA LETTER N-MU-MO-2
2017
		charset[i++] = c++;
2018
// 1B130..1B16F; Small Kana Extension
2019
	charset[i++] = 0x1b150;	// HIRAGANA LETTER SMALL WI
2020
	charset[i++] = 0x1b152;	// HIRAGANA LETTER SMALL WO
2021
	c = 0x1b164;		// from KATAKANA LETTER SMALL WI
2022
	while (c <= 0x1b167)	// ..to KATAKANA LETTER SMALL N
2023
		charset[i++] = c++;
2024
// 1B170..1B2FF; Nushu
2025
	c = 0x1b170;		// from NUSHU CHARACTER-1B170
2026
	while (c <= 0x1b2fb)	// ..to NUSHU CHARACTER-1B2FB
2027
		charset[i++] = c++;
2028
// 1BC00..1BC9F; Duployan
2029
	c = 0x1bc00;		// from DUPLOYAN LETTER H
2030
	while (c <= 0x1bc6a)	// ..to DUPLOYAN LETTER VOCALIC M
2031
		charset[i++] = c++;
2032
	c = 0x1bc70;		// from DUPLOYAN AFFIX LEFT HORIZONTAL SECANT
2033
	while (c <= 0x1bc7c)	// ..to DUPLOYAN AFFIX ATTACHED TANGENT HOOK
2034
		charset[i++] = c++;
2035
	c = 0x1bc80;		// from DUPLOYAN AFFIX HIGH ACUTE
2036
	while (c <= 0x1bc88)	// ..to DUPLOYAN AFFIX HIGH VERTICAL
2037
		charset[i++] = c++;
2038
	c = 0x1bc90;		// from DUPLOYAN AFFIX LOW ACUTE
2039
	while (c <= 0x1bc99)	// ..to DUPLOYAN AFFIX LOW ARROW
2040
		charset[i++] = c++;
2041
	c = 0x1bc9c;		// from DUPLOYAN SIGN O WITH CROSS
2042
	while (c <= 0x1bc9f)	// ..to DUPLOYAN PUNCTUATION CHINOOK FULL STOP
2043
		charset[i++] = c++;
2044
// 1BCA0..1BCAF; Shorthand Format Controls
2045
	c = 0x1bca0;		// from SHORTHAND FORMAT LETTER OVERLAP
2046
	while (c <= 0x1bca3)	// ..to SHORTHAND FORMAT UP STEP
2047
		charset[i++] = c++;
2048
// 1D000..1D0FF; Byzantine Musical Symbols
2049
	c = 0x1d000;		// from BYZANTINE MUSICAL SYMBOL PSILI
2050
	while (c <= 0x1d0f5)	// ..to BYZANTINE MUSICAL SYMBOL GORGON NEO KATO
2051
		charset[i++] = c++;
2052
// 1D100..1D1FF; Musical Symbols
2053
	c = 0x1d100;		// from MUSICAL SYMBOL SINGLE BARLINE
2054
	while (c <= 0x1d126)	// ..to MUSICAL SYMBOL DRUM CLEF-2
2055
		charset[i++] = c++;
2056
	c = 0x1d129;		// from MUSICAL SYMBOL MULTIPLE MEASURE REST
2057
	while (c <= 0x1d1e8)	// ..to MUSICAL SYMBOL KIEVAN FLAT SIGN
2058
		charset[i++] = c++;
2059
// 1D200..1D24F; Ancient Greek Musical Notation
2060
	c = 0x1d200;		// from GREEK VOCAL NOTATION SYMBOL-1
2061
	while (c <= 0x1d245)	// ..to GREEK MUSICAL LEIMMA
2062
		charset[i++] = c++;
2063
// 1D2E0..1D2FF; Mayan Numerals
2064
	c = 0x1d2e0;		// from MAYAN NUMERAL ZERO
2065
	while (c <= 0x1d2f3)	// ..to MAYAN NUMERAL NINETEEN
2066
		charset[i++] = c++;
2067
// 1D300..1D35F; Tai Xuan Jing Symbols
2068
	c = 0x1d300;		// from MONOGRAM FOR EARTH
2069
	while (c <= 0x1d356)	// ..to TETRAGRAM FOR FOSTERING
2070
		charset[i++] = c++;
2071
// 1D360..1D37F; Counting Rod Numerals
2072
	c = 0x1d360;		// from COUNTING ROD UNIT DIGIT ONE
2073
	while (c <= 0x1d378)	// ..to TALLY MARK FIVE
2074
		charset[i++] = c++;
2075
// 1D400..1D7FF; Mathematical Alphanumeric Symbols
2076
	c = 0x1d400;		// from MATHEMATICAL BOLD CAPITAL A
2077
	while (c <= 0x1d454)	// ..to MATHEMATICAL ITALIC SMALL G
2078
		charset[i++] = c++;
2079
	c = 0x1d456;		// from MATHEMATICAL ITALIC SMALL I
2080
	while (c <= 0x1d49c)	// ..to MATHEMATICAL SCRIPT CAPITAL A
2081
		charset[i++] = c++;
2082
	charset[i++] = 0x1d49e;	// MATHEMATICAL SCRIPT CAPITAL C
2083
	charset[i++] = 0x1d49f;	// MATHEMATICAL SCRIPT CAPITAL D
2084
	charset[i++] = 0x1d4a5;	// MATHEMATICAL SCRIPT CAPITAL J
2085
	charset[i++] = 0x1d4a6;	// MATHEMATICAL SCRIPT CAPITAL K
2086
	c = 0x1d4a9;		// from MATHEMATICAL SCRIPT CAPITAL N
2087
	while (c <= 0x1d4ac)	// ..to MATHEMATICAL SCRIPT CAPITAL Q
2088
		charset[i++] = c++;
2089
	c = 0x1d4ae;		// from MATHEMATICAL SCRIPT CAPITAL S
2090
	while (c <= 0x1d4b9)	// ..to MATHEMATICAL SCRIPT SMALL D
2091
		charset[i++] = c++;
2092
	c = 0x1d4bd;		// from MATHEMATICAL SCRIPT SMALL H
2093
	while (c <= 0x1d4c3)	// ..to MATHEMATICAL SCRIPT SMALL N
2094
		charset[i++] = c++;
2095
	c = 0x1d4c5;		// from MATHEMATICAL SCRIPT SMALL P
2096
	while (c <= 0x1d505)	// ..to MATHEMATICAL FRAKTUR CAPITAL B
2097
		charset[i++] = c++;
2098
	c = 0x1d507;		// from MATHEMATICAL FRAKTUR CAPITAL D
2099
	while (c <= 0x1d50a)	// ..to MATHEMATICAL FRAKTUR CAPITAL G
2100
		charset[i++] = c++;
2101
	c = 0x1d50d;		// from MATHEMATICAL FRAKTUR CAPITAL J
2102
	while (c <= 0x1d514)	// ..to MATHEMATICAL FRAKTUR CAPITAL Q
2103
		charset[i++] = c++;
2104
	c = 0x1d516;		// from MATHEMATICAL FRAKTUR CAPITAL S
2105
	while (c <= 0x1d51c)	// ..to MATHEMATICAL FRAKTUR CAPITAL Y
2106
		charset[i++] = c++;
2107
	c = 0x1d51e;		// from MATHEMATICAL FRAKTUR SMALL A
2108
	while (c <= 0x1d539)	// ..to MATHEMATICAL DOUBLE-STRUCK CAPITAL B
2109
		charset[i++] = c++;
2110
	c = 0x1d53b;		// from MATHEMATICAL DOUBLE-STRUCK CAPITAL D
2111
	while (c <= 0x1d53e)	// ..to MATHEMATICAL DOUBLE-STRUCK CAPITAL G
2112
		charset[i++] = c++;
2113
	c = 0x1d540;		// from MATHEMATICAL DOUBLE-STRUCK CAPITAL I
2114
	while (c <= 0x1d544)	// ..to MATHEMATICAL DOUBLE-STRUCK CAPITAL M
2115
		charset[i++] = c++;
2116
	c = 0x1d54a;		// from MATHEMATICAL DOUBLE-STRUCK CAPITAL S
2117
	while (c <= 0x1d550)	// ..to MATHEMATICAL DOUBLE-STRUCK CAPITAL Y
2118
		charset[i++] = c++;
2119
	c = 0x1d552;		// from MATHEMATICAL DOUBLE-STRUCK SMALL A
2120
	while (c <= 0x1d6a5)	// ..to MATHEMATICAL ITALIC SMALL DOTLESS J
2121
		charset[i++] = c++;
2122
	c = 0x1d6a8;		// from MATHEMATICAL BOLD CAPITAL ALPHA
2123
	while (c <= 0x1d7cb)	// ..to MATHEMATICAL BOLD SMALL DIGAMMA
2124
		charset[i++] = c++;
2125
	c = 0x1d7ce;		// from MATHEMATICAL BOLD DIGIT ZERO
2126
	while (c <= 0x1d7ff)	// ..to MATHEMATICAL MONOSPACE DIGIT NINE
2127
		charset[i++] = c++;
2128
// 1D800..1DAAF; Sutton SignWriting
2129
	c = 0x1d800;		// from SIGNWRITING HAND-FIST INDEX
2130
	while (c <= 0x1da8b)	// ..to SIGNWRITING PARENTHESIS
2131
		charset[i++] = c++;
2132
	c = 0x1da9b;		// from SIGNWRITING FILL MODIFIER-2
2133
	while (c <= 0x1da9f)	// ..to SIGNWRITING FILL MODIFIER-6
2134
		charset[i++] = c++;
2135
	c = 0x1daa1;		// from SIGNWRITING ROTATION MODIFIER-2
2136
	while (c <= 0x1daaf)	// ..to SIGNWRITING ROTATION MODIFIER-16
2137
		charset[i++] = c++;
2138
// 1E000..1E02F; Glagolitic Supplement
2139
	c = 0x1e000;		// from COMBINING GLAGOLITIC LETTER AZU
2140
	while (c <= 0x1e006)	// ..to COMBINING GLAGOLITIC LETTER ZHIVETE
2141
		charset[i++] = c++;
2142
	c = 0x1e008;		// from COMBINING GLAGOLITIC LETTER ZEMLJA
2143
	while (c <= 0x1e018)	// ..to COMBINING GLAGOLITIC LETTER HERU
2144
		charset[i++] = c++;
2145
	c = 0x1e01b;		// from COMBINING GLAGOLITIC LETTER SHTA
2146
	while (c <= 0x1e021)	// ..to COMBINING GLAGOLITIC LETTER YATI
2147
		charset[i++] = c++;
2148
	charset[i++] = 0x1e023;	// COMBINING GLAGOLITIC LETTER YU
2149
	charset[i++] = 0x1e024;	// COMBINING GLAGOLITIC LETTER SMALL YUS
2150
	c = 0x1e026;		// from COMBINING GLAGOLITIC LETTER YO
2151
	while (c <= 0x1e02a)	// ..to COMBINING GLAGOLITIC LETTER FITA
2152
		charset[i++] = c++;
2153
// 1E100..1E14F; Nyiakeng Puachue Hmong
2154
	c = 0x1e100;		// from NYIAKENG PUACHUE HMONG LETTER MA
2155
	while (c <= 0x1e12c)	// ..to NYIAKENG PUACHUE HMONG LETTER W
2156
		charset[i++] = c++;
2157
	c = 0x1e130;		// from NYIAKENG PUACHUE HMONG TONE-B
2158
	while (c <= 0x1e13d)	// ..to NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
2159
		charset[i++] = c++;
2160
	c = 0x1e140;		// from NYIAKENG PUACHUE HMONG DIGIT ZERO
2161
	while (c <= 0x1e149)	// ..to NYIAKENG PUACHUE HMONG DIGIT NINE
2162
		charset[i++] = c++;
2163
	charset[i++] = 0x1e14e;	// NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ
2164
	charset[i++] = 0x1e14f;	// NYIAKENG PUACHUE HMONG CIRCLED CA
2165
// 1E2C0..1E2FF; Wancho
2166
	c = 0x1e2c0;		// from WANCHO LETTER AA
2167
	while (c <= 0x1e2f9)	// ..to WANCHO DIGIT NINE
2168
		charset[i++] = c++;
2169
	charset[i++] = 0x1e2ff;	// WANCHO NGUN SIGN
2170
// 1E800..1E8DF; Mende Kikakui
2171
	c = 0x1e800;		// from MENDE KIKAKUI SYLLABLE M001 KI
2172
	while (c <= 0x1e8c4)	// ..to MENDE KIKAKUI SYLLABLE M060 NYON
2173
		charset[i++] = c++;
2174
	c = 0x1e8c7;		// from MENDE KIKAKUI DIGIT ONE
2175
	while (c <= 0x1e8d6)	// ..to MENDE KIKAKUI COMBINING NUMBER MILLIONS
2176
		charset[i++] = c++;
2177
// 1E900..1E95F; Adlam
2178
	c = 0x1e900;		// from ADLAM CAPITAL LETTER ALIF
2179
	while (c <= 0x1e94b)	// ..to ADLAM NASALIZATION MARK
2180
		charset[i++] = c++;
2181
	c = 0x1e950;		// from ADLAM DIGIT ZERO
2182
	while (c <= 0x1e959)	// ..to ADLAM DIGIT NINE
2183
		charset[i++] = c++;
2184
	charset[i++] = 0x1e95e;	// ADLAM INITIAL EXCLAMATION MARK
2185
	charset[i++] = 0x1e95f;	// ADLAM INITIAL QUESTION MARK
2186
// 1EC70..1ECBF; Indic Siyaq Numbers
2187
	c = 0x1ec71;		// from INDIC SIYAQ NUMBER ONE
2188
	while (c <= 0x1ecb4)	// ..to INDIC SIYAQ ALTERNATE LAKH MARK
2189
		charset[i++] = c++;
2190
// 1ED00..1ED4F; Ottoman Siyaq Numbers
2191
	c = 0x1ed01;		// from OTTOMAN SIYAQ NUMBER ONE
2192
	while (c <= 0x1ed3d)	// ..to OTTOMAN SIYAQ FRACTION ONE SIXTH
2193
		charset[i++] = c++;
2194
// 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
2195
	c = 0x1ee00;		// from ARABIC MATHEMATICAL ALEF
2196
	while (c <= 0x1ee03)	// ..to ARABIC MATHEMATICAL DAL
2197
		charset[i++] = c++;
2198
	c = 0x1ee05;		// from ARABIC MATHEMATICAL WAW
2199
	while (c <= 0x1ee1f)	// ..to ARABIC MATHEMATICAL DOTLESS QAF
2200
		charset[i++] = c++;
2201
	charset[i++] = 0x1ee21;	// ARABIC MATHEMATICAL INITIAL BEH
2202
	charset[i++] = 0x1ee22;	// ARABIC MATHEMATICAL INITIAL JEEM
2203
	c = 0x1ee29;		// from ARABIC MATHEMATICAL INITIAL YEH
2204
	while (c <= 0x1ee32)	// ..to ARABIC MATHEMATICAL INITIAL QAF
2205
		charset[i++] = c++;
2206
	c = 0x1ee34;		// from ARABIC MATHEMATICAL INITIAL SHEEN
2207
	while (c <= 0x1ee37)	// ..to ARABIC MATHEMATICAL INITIAL KHAH
2208
		charset[i++] = c++;
2209
	charset[i++] = 0x1ee4d;	// ARABIC MATHEMATICAL TAILED NOON
2210
	charset[i++] = 0x1ee4f;	// ARABIC MATHEMATICAL TAILED AIN
2211
	charset[i++] = 0x1ee51;	// ARABIC MATHEMATICAL TAILED SAD
2212
	charset[i++] = 0x1ee52;	// ARABIC MATHEMATICAL TAILED QAF
2213
	charset[i++] = 0x1ee61;	// ARABIC MATHEMATICAL STRETCHED BEH
2214
	charset[i++] = 0x1ee62;	// ARABIC MATHEMATICAL STRETCHED JEEM
2215
	c = 0x1ee67;		// from ARABIC MATHEMATICAL STRETCHED HAH
2216
	while (c <= 0x1ee6a)	// ..to ARABIC MATHEMATICAL STRETCHED KAF
2217
		charset[i++] = c++;
2218
	c = 0x1ee6c;		// from ARABIC MATHEMATICAL STRETCHED MEEM
2219
	while (c <= 0x1ee72)	// ..to ARABIC MATHEMATICAL STRETCHED QAF
2220
		charset[i++] = c++;
2221
	c = 0x1ee74;		// from ARABIC MATHEMATICAL STRETCHED SHEEN
2222
	while (c <= 0x1ee77)	// ..to ARABIC MATHEMATICAL STRETCHED KHAH
2223
		charset[i++] = c++;
2224
	c = 0x1ee79;		// from ARABIC MATHEMATICAL STRETCHED DAD
2225
	while (c <= 0x1ee7c)	// ..to ARABIC MATHEMATICAL STRETCHED DOTLESS BEH
2226
		charset[i++] = c++;
2227
	c = 0x1ee80;		// from ARABIC MATHEMATICAL LOOPED ALEF
2228
	while (c <= 0x1ee89)	// ..to ARABIC MATHEMATICAL LOOPED YEH
2229
		charset[i++] = c++;
2230
	c = 0x1ee8b;		// from ARABIC MATHEMATICAL LOOPED LAM
2231
	while (c <= 0x1ee9b)	// ..to ARABIC MATHEMATICAL LOOPED GHAIN
2232
		charset[i++] = c++;
2233
	charset[i++] = 0x1eea1;	// ARABIC MATHEMATICAL DOUBLE-STRUCK BEH
2234
	charset[i++] = 0x1eea3;	// ARABIC MATHEMATICAL DOUBLE-STRUCK DAL
2235
	c = 0x1eea5;		// from ARABIC MATHEMATICAL DOUBLE-STRUCK WAW
2236
	while (c <= 0x1eea9)	// ..to ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
2237
		charset[i++] = c++;
2238
	c = 0x1eeab;		// from ARABIC MATHEMATICAL DOUBLE-STRUCK LAM
2239
	while (c <= 0x1eebb)	// ..to ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
2240
		charset[i++] = c++;
2241
	charset[i++] = 0x1eef0;	// ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL
2242
	charset[i++] = 0x1eef1;	// ARABIC MATHEMATICAL OPERATOR HAH WITH DAL
2243
// 1F000..1F02F; Mahjong Tiles
2244
	c = 0x1f000;		// from MAHJONG TILE EAST WIND
2245
	while (c <= 0x1f02b)	// ..to MAHJONG TILE BACK
2246
		charset[i++] = c++;
2247
// 1F030..1F09F; Domino Tiles
2248
	c = 0x1f030;		// from DOMINO TILE HORIZONTAL BACK
2249
	while (c <= 0x1f093)	// ..to DOMINO TILE VERTICAL-06-06
2250
		charset[i++] = c++;
2251
// 1F0A0..1F0FF; Playing Cards
2252
	c = 0x1f0a0;		// from PLAYING CARD BACK
2253
	while (c <= 0x1f0ae)	// ..to PLAYING CARD KING OF SPADES
2254
		charset[i++] = c++;
2255
	c = 0x1f0b1;		// from PLAYING CARD ACE OF HEARTS
2256
	while (c <= 0x1f0bf)	// ..to PLAYING CARD RED JOKER
2257
		charset[i++] = c++;
2258
	c = 0x1f0c1;		// from PLAYING CARD ACE OF DIAMONDS
2259
	while (c <= 0x1f0cf)	// ..to PLAYING CARD BLACK JOKER
2260
		charset[i++] = c++;
2261
	c = 0x1f0d1;		// from PLAYING CARD ACE OF CLUBS
2262
	while (c <= 0x1f0f5)	// ..to PLAYING CARD TRUMP-21
2263
		charset[i++] = c++;
2264
// 1F100..1F1FF; Enclosed Alphanumeric Supplement
2265
	c = 0x1f100;		// from DIGIT ZERO FULL STOP
2266
	while (c <= 0x1f1ad)	// ..to MASK WORK SYMBOL
2267
		charset[i++] = c++;
2268
	c = 0x1f1e6;		// from REGIONAL INDICATOR SYMBOL LETTER A
2269
	while (c <= 0x1f1ff)	// ..to REGIONAL INDICATOR SYMBOL LETTER Z
2270
		charset[i++] = c++;
2271
// 1F200..1F2FF; Enclosed Ideographic Supplement
2272
	charset[i++] = 0x1f200;	// SQUARE HIRAGANA HOKA
2273
	charset[i++] = 0x1f202;	// SQUARED KATAKANA SA
2274
	c = 0x1f210;		// from SQUARED CJK UNIFIED IDEOGRAPH-624B
2275
	while (c <= 0x1f23b)	// ..to SQUARED CJK UNIFIED IDEOGRAPH-914D
2276
		charset[i++] = c++;
2277
	c = 0x1f240;		// from TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C
2278
	while (c <= 0x1f248)	// ..to TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
2279
		charset[i++] = c++;
2280
	charset[i++] = 0x1f250;	// CIRCLED IDEOGRAPH ADVANTAGE
2281
	charset[i++] = 0x1f251;	// CIRCLED IDEOGRAPH ACCEPT
2282
	c = 0x1f260;		// from ROUNDED SYMBOL FOR FU
2283
	while (c <= 0x1f265)	// ..to ROUNDED SYMBOL FOR CAI
2284
		charset[i++] = c++;
2285
// 1F300..1F5FF; Miscellaneous Symbols and Pictographs
2286
	c = 0x1f300;		// from CYCLONE
2287
	while (c <= 0x1f5ff)	// ..to MOYAI
2288
		charset[i++] = c++;
2289
// 1F600..1F64F; Emoticons
2290
	c = 0x1f600;		// from GRINNING FACE
2291
	while (c <= 0x1f64f)	// ..to PERSON WITH FOLDED HANDS
2292
		charset[i++] = c++;
2293
// 1F650..1F67F; Ornamental Dingbats
2294
	c = 0x1f650;		// from NORTH WEST POINTING LEAF
2295
	while (c <= 0x1f67f)	// ..to REVERSE CHECKER BOARD
2296
		charset[i++] = c++;
2297
// 1F680..1F6FF; Transport and Map Symbols
2298
	c = 0x1f680;		// from ROCKET
2299
	while (c <= 0x1f6d7)	// ..to ELEVATOR
2300
		charset[i++] = c++;
2301
	c = 0x1f6e0;		// from HAMMER AND WRENCH
2302
	while (c <= 0x1f6ec)	// ..to AIRPLANE ARRIVING
2303
		charset[i++] = c++;
2304
	c = 0x1f6f0;		// from SATELLITE
2305
	while (c <= 0x1f6fc)	// ..to ROLLER SKATE
2306
		charset[i++] = c++;
2307
// 1F700..1F77F; Alchemical Symbols
2308
	c = 0x1f700;		// from ALCHEMICAL SYMBOL FOR QUINTESSENCE
2309
	while (c <= 0x1f773)	// ..to ALCHEMICAL SYMBOL FOR HALF OUNCE
2310
		charset[i++] = c++;
2311
// 1F780..1F7FF; Geometric Shapes Extended
2312
	c = 0x1f780;		// from BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE
2313
	while (c <= 0x1f7d8)	// ..to NEGATIVE CIRCLED SQUARE
2314
		charset[i++] = c++;
2315
	c = 0x1f7e0;		// from LARGE ORANGE CIRCLE
2316
	while (c <= 0x1f7eb)	// ..to LARGE BROWN SQUARE
2317
		charset[i++] = c++;
2318
// 1F800..1F8FF; Supplemental Arrows-C
2319
	c = 0x1f800;		// from LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD
2320
	while (c <= 0x1f80b)	// ..to DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
2321
		charset[i++] = c++;
2322
	c = 0x1f810;		// from LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD
2323
	while (c <= 0x1f847)	// ..to DOWNWARDS HEAVY ARROW
2324
		charset[i++] = c++;
2325
	c = 0x1f850;		// from LEFTWARDS SANS-SERIF ARROW
2326
	while (c <= 0x1f859)	// ..to UP DOWN SANS-SERIF ARROW
2327
		charset[i++] = c++;
2328
	c = 0x1f860;		// from WIDE-HEADED LEFTWARDS LIGHT BARB ARROW
2329
	while (c <= 0x1f887)	// ..to WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
2330
		charset[i++] = c++;
2331
	c = 0x1f890;		// from LEFTWARDS TRIANGLE ARROWHEAD
2332
	while (c <= 0x1f8ad)	// ..to WHITE ARROW SHAFT WIDTH TWO THIRDS
2333
		charset[i++] = c++;
2334
	charset[i++] = 0x1f8b0;	// ARROW POINTING UPWARDS THEN NORTH WEST
2335
	charset[i++] = 0x1f8b1;	// ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST
2336
// 1F900..1F9FF; Supplemental Symbols and Pictographs
2337
	c = 0x1f900;		// from CIRCLED CROSS FORMEE WITH FOUR DOTS
2338
	while (c <= 0x1f978)	// ..to DISGUISED FACE
2339
		charset[i++] = c++;
2340
	c = 0x1f97a;		// from FACE WITH PLEADING EYES
2341
	while (c <= 0x1f9cb)	// ..to BUBBLE TEA
2342
		charset[i++] = c++;
2343
	c = 0x1f9cd;		// from STANDING PERSON
2344
	while (c <= 0x1f9ff)	// ..to NAZAR AMULET
2345
		charset[i++] = c++;
2346
// 1FA00..1FA6F; Chess Symbols
2347
	c = 0x1fa00;		// from NEUTRAL CHESS KING
2348
	while (c <= 0x1fa53)	// ..to BLACK CHESS KNIGHT-BISHOP
2349
		charset[i++] = c++;
2350
	c = 0x1fa60;		// from XIANGQI RED GENERAL
2351
	while (c <= 0x1fa6d)	// ..to XIANGQI BLACK SOLDIER
2352
		charset[i++] = c++;
2353
// 1FA70..1FAFF; Symbols and Pictographs Extended-A
2354
	c = 0x1fa70;		// from BALLET SHOES
2355
	while (c <= 0x1fa74)	// ..to THONG SANDAL
2356
		charset[i++] = c++;
2357
	charset[i++] = 0x1fa78;	// DROP OF BLOOD
2358
	charset[i++] = 0x1fa7a;	// STETHOSCOPE
2359
	c = 0x1fa80;		// from YO-YO
2360
	while (c <= 0x1fa86)	// ..to NESTING DOLLS
2361
		charset[i++] = c++;
2362
	c = 0x1fa90;		// from RINGED PLANET
2363
	while (c <= 0x1faa8)	// ..to ROCK
2364
		charset[i++] = c++;
2365
	c = 0x1fab0;		// from FLY
2366
	while (c <= 0x1fab6)	// ..to FEATHER
2367
		charset[i++] = c++;
2368
	charset[i++] = 0x1fac0;	// ANATOMICAL HEART
2369
	charset[i++] = 0x1fac2;	// PEOPLE HUGGING
2370
	c = 0x1fad0;		// from BLUEBERRIES
2371
	while (c <= 0x1fad6)	// ..to TEAPOT
2372
		charset[i++] = c++;
2373
// 1FB00..1FBFF; Symbols for Legacy Computing
2374
	c = 0x1fb00;		// from BLOCK SEXTANT-1
2375
	while (c <= 0x1fb92)	// ..to UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK
2376
		charset[i++] = c++;
2377
	c = 0x1fb94;		// from LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK
2378
	while (c <= 0x1fbca)	// ..to WHITE UP-POINTING CHEVRON
2379
		charset[i++] = c++;
2380
	c = 0x1fbf0;		// from SEGMENTED DIGIT ZERO
2381
	while (c <= 0x1fbf9)	// ..to SEGMENTED DIGIT NINE
2382
		charset[i++] = c++;
2383
// 20000..2A6DF; CJK Unified Ideographs Extension B
2384
	c = 0x20000;		// from <CJK Ideograph Extension B, First>
2385
	while (c <= 0x2a6dd)	// ..to <CJK Ideograph Extension B, Last>
2386
		charset[i++] = c++;
2387
// 2A700..2B73F; CJK Unified Ideographs Extension C
2388
	c = 0x2a700;		// from <CJK Ideograph Extension C, First>
2389
	while (c <= 0x2b734)	// ..to <CJK Ideograph Extension C, Last>
2390
		charset[i++] = c++;
2391
// 2B740..2B81F; CJK Unified Ideographs Extension D
2392
	c = 0x2b740;		// from <CJK Ideograph Extension D, First>
2393
	while (c <= 0x2b81d)	// ..to <CJK Ideograph Extension D, Last>
2394
		charset[i++] = c++;
2395
// 2B820..2CEAF; CJK Unified Ideographs Extension E
2396
	c = 0x2b820;		// from <CJK Ideograph Extension E, First>
2397
	while (c <= 0x2cea1)	// ..to <CJK Ideograph Extension E, Last>
2398
		charset[i++] = c++;
2399
// 2CEB0..2EBEF; CJK Unified Ideographs Extension F
2400
	c = 0x2ceb0;		// from <CJK Ideograph Extension F, First>
2401
	while (c <= 0x2ebe0)	// ..to <CJK Ideograph Extension F, Last>
2402
		charset[i++] = c++;
2403
// 2F800..2FA1F; CJK Compatibility Ideographs Supplement
2404
	c = 0x2f800;		// from CJK COMPATIBILITY IDEOGRAPH-2F800
2405
	while (c <= 0x2fa1d)	// ..to CJK COMPATIBILITY IDEOGRAPH-2FA1D
2406
		charset[i++] = c++;
2407
// 30000..3134F; CJK Unified Ideographs Extension G
2408
	c = 0x30000;		// from <CJK Ideograph Extension G, First>
2409
	while (c <= 0x3134a)	// ..to <CJK Ideograph Extension G, Last>
2410
		charset[i++] = c++;
2411
// E0000..E007F; Tags
2412
	c = 0xe0020;		// from TAG SPACE
2413
	while (c <= 0xe007f)	// ..to CANCEL TAG
2414
		charset[i++] = c++;
2415
// E0100..E01EF; Variation Selectors Supplement
2416
// F0000..FFFFF; Supplementary Private Use Area-A
2417
// 100000..10FFFF; Supplementary Private Use Area-B
2418

2419
/* Zero-terminate it, and cache the first character */
2420
	charset[i] = 0;
2421
	c0 = charset[0];
2422

2423
	last = minlength - 1;
2424
	i = 0;
2425
	while (i <= last) {
2426
		id[i] = 0;
2427
		word[i++] = c0;
2428
	}
2429
	lastid = -1;
2430
	word[i] = 0;
2431

2432
/* We must init word with dummy data, it doesn't get set until filter() */
2433
	word = 1;
2434
}
2435

2436
void generate()
2437
{
2438
	int i;
2439

2440
/* Handle the typical case specially */
2441
	if (word[last] = charset[++lastid]) return;
2442

2443
	lastid = 0;
2444
	word[i = last] = c0;
2445
	while (i--) {			// Have a preceding position?
2446
		if (word[i] = charset[++id[i]]) return;
2447
		id[i] = 0;
2448
		word[i] = c0;
2449
	}
2450

2451
	if (++last < maxlength) {	// Next length?
2452
		id[last] = lastid = 0;
2453
		word[last] = c0;
2454
		word[last + 1] = 0;
2455
	} else				// We're done
2456
		word = 0;
2457
}
2458

2459
void restore()
2460
{
2461
	int i, c;
2462

2463
	/* Calculate the current length and infer the character indices */
2464
	last = 0;
2465
	while (c = word[last]) {
2466
		i = 0; while (charset[i] != c && charset[i]) i++;
2467
		if (!charset[i]) i = 0;	// Not found
2468
		id[last++] = i;
2469
	}
2470
	lastid = id[--last];
2471
}
2472

2473