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
# Try strings of repeated characters, Full Unicode (version 13) version
7
#
8
# Number of candidates = 143,532 x length
9
#
10
# Note that these modes will handle --max-len differently than normal: They
11
# will consider number of characters as opposed to number of bytes. This
12
# means you can naturally just use e.g. --max-len=3 for generating all
13
# three-character candidates (which may be up to 12 bytes each).
14
#
15
# Also note that for UTF-16 formats, the resulting plaintext size within the
16
# format will be up to four bytes (two 16-bit words) due to use of surrogates
17
# for characters above U+FFFF. This means a format which normally handles up
18
# to 27 characters may be limited to only 13 characters, worst case.
19
#
20
# Note that the (newer) cracking mode --subsets=full-unicode is way faster than
21
# this external mode, although not as easy to adapt to smaller portions of the
22
# Unicode space.  See doc/SUBSETS
23

24
[List.External:Repeats32]
25
int minlength, maxlength, maxc, length, c;
26
int charset[0x24000];
27

28
void init()
29
{
30
	int i;
31

32
	# Trigger UTF-32 handling in External mode
33
	utf32 = 1;
34

35
	if (req_minlen)
36
		minlength = req_minlen;
37
	else
38
		minlength = 1;
39

40
	if (req_maxlen)
41
		maxlength = req_maxlen;
42
	else
43
		maxlength = cipher_limit;
44

45
/*
46
 * This defines the character set. This is auto-generated from UnicodeData.txt
47
 * and we skip control characters.
48
 */
49
	i = 0;
50
// 0000..007F; Basic Latin
51
	c = 0x20;		// from SPACE
52
	while (c <= 0x7e)	// ..to TILDE
53
		charset[i++] = c++;
54
// 0080..00FF; Latin-1 Supplement
55
	c = 0xa0;		// from NO-BREAK SPACE
56
	while (c <= 0xff)	// ..to LATIN SMALL LETTER Y WITH DIAERESIS
57
		charset[i++] = c++;
58
// 0100..017F; Latin Extended-A
59
	c = 0x100;		// from LATIN CAPITAL LETTER A WITH MACRON
60
	while (c <= 0x17f)	// ..to LATIN SMALL LETTER LONG S
61
		charset[i++] = c++;
62
// 0180..024F; Latin Extended-B
63
	c = 0x180;		// from LATIN SMALL LETTER B WITH STROKE
64
	while (c <= 0x24f)	// ..to LATIN SMALL LETTER Y WITH STROKE
65
		charset[i++] = c++;
66
// 0250..02AF; IPA Extensions
67
	c = 0x250;		// from LATIN SMALL LETTER TURNED A
68
	while (c <= 0x2af)	// ..to LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL
69
		charset[i++] = c++;
70
// 02B0..02FF; Spacing Modifier Letters
71
	c = 0x2b0;		// from MODIFIER LETTER SMALL H
72
	while (c <= 0x2ff)	// ..to MODIFIER LETTER LOW LEFT ARROW
73
		charset[i++] = c++;
74
// 0300..036F; Combining Diacritical Marks
75
	c = 0x300;		// from COMBINING GRAVE ACCENT
76
	while (c <= 0x36f)	// ..to COMBINING LATIN SMALL LETTER X
77
		charset[i++] = c++;
78
// 0370..03FF; Greek and Coptic
79
	c = 0x370;		// from GREEK CAPITAL LETTER HETA
80
	while (c <= 0x377)	// ..to GREEK SMALL LETTER PAMPHYLIAN DIGAMMA
81
		charset[i++] = c++;
82
	c = 0x37a;		// from GREEK YPOGEGRAMMENI
83
	while (c <= 0x37f)	// ..to GREEK CAPITAL LETTER YOT
84
		charset[i++] = c++;
85
	c = 0x384;		// from GREEK TONOS
86
	while (c <= 0x38a)	// ..to GREEK CAPITAL LETTER IOTA WITH TONOS
87
		charset[i++] = c++;
88
	c = 0x38e;		// from GREEK CAPITAL LETTER UPSILON WITH TONOS
89
	while (c <= 0x3a1)	// ..to GREEK CAPITAL LETTER RHO
90
		charset[i++] = c++;
91
	c = 0x3a3;		// from GREEK CAPITAL LETTER SIGMA
92
	while (c <= 0x3ff)	// ..to GREEK CAPITAL REVERSED DOTTED LUNATE SIGMA SYMBOL
93
		charset[i++] = c++;
94
// 0400..04FF; Cyrillic
95
	c = 0x400;		// from CYRILLIC CAPITAL LETTER IE WITH GRAVE
96
	while (c <= 0x4ff)	// ..to CYRILLIC SMALL LETTER HA WITH STROKE
97
		charset[i++] = c++;
98
// 0500..052F; Cyrillic Supplement
99
	c = 0x500;		// from CYRILLIC CAPITAL LETTER KOMI DE
100
	while (c <= 0x52f)	// ..to CYRILLIC SMALL LETTER EL WITH DESCENDER
101
		charset[i++] = c++;
102
// 0530..058F; Armenian
103
	c = 0x531;		// from ARMENIAN CAPITAL LETTER AYB
104
	while (c <= 0x556)	// ..to ARMENIAN CAPITAL LETTER FEH
105
		charset[i++] = c++;
106
	c = 0x559;		// from ARMENIAN MODIFIER LETTER LEFT HALF RING
107
	while (c <= 0x58a)	// ..to ARMENIAN HYPHEN
108
		charset[i++] = c++;
109
	charset[i++] = 0x58d;	// RIGHT-FACING ARMENIAN ETERNITY SIGN
110
	charset[i++] = 0x58f;	// ARMENIAN DRAM SIGN
111
// 0590..05FF; Hebrew
112
	c = 0x591;		// from HEBREW ACCENT ETNAHTA
113
	while (c <= 0x5c7)	// ..to HEBREW POINT QAMATS QATAN
114
		charset[i++] = c++;
115
	c = 0x5d0;		// from HEBREW LETTER ALEF
116
	while (c <= 0x5ea)	// ..to HEBREW LETTER TAV
117
		charset[i++] = c++;
118
	c = 0x5ef;		// from HEBREW YOD TRIANGLE
119
	while (c <= 0x5f4)	// ..to HEBREW PUNCTUATION GERSHAYIM
120
		charset[i++] = c++;
121
// 0600..06FF; Arabic
122
	c = 0x600;		// from ARABIC NUMBER SIGN
123
	while (c <= 0x61c)	// ..to ARABIC LETTER MARK
124
		charset[i++] = c++;
125
	c = 0x61e;		// from ARABIC TRIPLE DOT PUNCTUATION MARK
126
	while (c <= 0x6ff)	// ..to ARABIC LETTER HEH WITH INVERTED V
127
		charset[i++] = c++;
128
// 0700..074F; Syriac
129
	c = 0x700;		// from SYRIAC END OF PARAGRAPH
130
	while (c <= 0x70d)	// ..to SYRIAC HARKLEAN ASTERISCUS
131
		charset[i++] = c++;
132
	c = 0x70f;		// from SYRIAC ABBREVIATION MARK
133
	while (c <= 0x74a)	// ..to SYRIAC BARREKH
134
		charset[i++] = c++;
135
	charset[i++] = 0x74d;	// SYRIAC LETTER SOGDIAN ZHAIN
136
	charset[i++] = 0x74f;	// SYRIAC LETTER SOGDIAN FE
137
// 0750..077F; Arabic Supplement
138
	c = 0x750;		// from ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW
139
	while (c <= 0x77f)	// ..to ARABIC LETTER KAF WITH TWO DOTS ABOVE
140
		charset[i++] = c++;
141
// 0780..07BF; Thaana
142
	c = 0x780;		// from THAANA LETTER HAA
143
	while (c <= 0x7b1)	// ..to THAANA LETTER NAA
144
		charset[i++] = c++;
145
// 07C0..07FF; NKo
146
	c = 0x7c0;		// from NKO DIGIT ZERO
147
	while (c <= 0x7fa)	// ..to NKO LAJANYALAN
148
		charset[i++] = c++;
149
	charset[i++] = 0x7fd;	// NKO DANTAYALAN
150
	charset[i++] = 0x7ff;	// NKO TAMAN SIGN
151
// 0800..083F; Samaritan
152
	c = 0x800;		// from SAMARITAN LETTER ALAF
153
	while (c <= 0x82d)	// ..to SAMARITAN MARK NEQUDAA
154
		charset[i++] = c++;
155
	c = 0x830;		// from SAMARITAN PUNCTUATION NEQUDAA
156
	while (c <= 0x83e)	// ..to SAMARITAN PUNCTUATION ANNAAU
157
		charset[i++] = c++;
158
// 0840..085F; Mandaic
159
	c = 0x840;		// from MANDAIC LETTER HALQA
160
	while (c <= 0x85b)	// ..to MANDAIC GEMINATION MARK
161
		charset[i++] = c++;
162
	charset[i++] = 0x85e;	// MANDAIC PUNCTUATION
163
// 0860..086F; Syriac Supplement
164
	c = 0x860;		// from SYRIAC LETTER MALAYALAM NGA
165
	while (c <= 0x86a)	// ..to SYRIAC LETTER MALAYALAM SSA
166
		charset[i++] = c++;
167
// 08A0..08FF; Arabic Extended-A
168
	c = 0x8a0;		// from ARABIC LETTER BEH WITH SMALL V BELOW
169
	while (c <= 0x8b4)	// ..to ARABIC LETTER KAF WITH DOT BELOW
170
		charset[i++] = c++;
171
	c = 0x8b6;		// from ARABIC LETTER BEH WITH SMALL MEEM ABOVE
172
	while (c <= 0x8c7)	// ..to ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE
173
		charset[i++] = c++;
174
	c = 0x8d3;		// from ARABIC SMALL LOW WAW
175
	while (c <= 0x8ff)	// ..to ARABIC MARK SIDEWAYS NOON GHUNNA
176
		charset[i++] = c++;
177
// 0900..097F; Devanagari
178
	c = 0x900;		// from DEVANAGARI SIGN INVERTED CANDRABINDU
179
	while (c <= 0x97f)	// ..to DEVANAGARI LETTER BBA
180
		charset[i++] = c++;
181
// 0980..09FF; Bengali
182
	c = 0x980;		// from BENGALI ANJI
183
	while (c <= 0x983)	// ..to BENGALI SIGN VISARGA
184
		charset[i++] = c++;
185
	c = 0x985;		// from BENGALI LETTER A
186
	while (c <= 0x98c)	// ..to BENGALI LETTER VOCALIC L
187
		charset[i++] = c++;
188
	charset[i++] = 0x98f;	// BENGALI LETTER E
189
	charset[i++] = 0x990;	// BENGALI LETTER AI
190
	c = 0x993;		// from BENGALI LETTER O
191
	while (c <= 0x9a8)	// ..to BENGALI LETTER NA
192
		charset[i++] = c++;
193
	c = 0x9aa;		// from BENGALI LETTER PA
194
	while (c <= 0x9b0)	// ..to BENGALI LETTER RA
195
		charset[i++] = c++;
196
	c = 0x9b6;		// from BENGALI LETTER SHA
197
	while (c <= 0x9b9)	// ..to BENGALI LETTER HA
198
		charset[i++] = c++;
199
	c = 0x9bc;		// from BENGALI SIGN NUKTA
200
	while (c <= 0x9c4)	// ..to BENGALI VOWEL SIGN VOCALIC RR
201
		charset[i++] = c++;
202
	charset[i++] = 0x9c7;	// BENGALI VOWEL SIGN E
203
	charset[i++] = 0x9c8;	// BENGALI VOWEL SIGN AI
204
	c = 0x9cb;		// from BENGALI VOWEL SIGN O
205
	while (c <= 0x9ce)	// ..to BENGALI LETTER KHANDA TA
206
		charset[i++] = c++;
207
	charset[i++] = 0x9dc;	// BENGALI LETTER RRA
208
	charset[i++] = 0x9dd;	// BENGALI LETTER RHA
209
	c = 0x9df;		// from BENGALI LETTER YYA
210
	while (c <= 0x9e3)	// ..to BENGALI VOWEL SIGN VOCALIC LL
211
		charset[i++] = c++;
212
	c = 0x9e6;		// from BENGALI DIGIT ZERO
213
	while (c <= 0x9fe)	// ..to BENGALI SANDHI MARK
214
		charset[i++] = c++;
215
// 0A00..0A7F; Gurmukhi
216
	charset[i++] = 0xa01;	// GURMUKHI SIGN ADAK BINDI
217
	charset[i++] = 0xa03;	// GURMUKHI SIGN VISARGA
218
	c = 0xa05;		// from GURMUKHI LETTER A
219
	while (c <= 0xa0a)	// ..to GURMUKHI LETTER UU
220
		charset[i++] = c++;
221
	charset[i++] = 0xa0f;	// GURMUKHI LETTER EE
222
	charset[i++] = 0xa10;	// GURMUKHI LETTER AI
223
	c = 0xa13;		// from GURMUKHI LETTER OO
224
	while (c <= 0xa28)	// ..to GURMUKHI LETTER NA
225
		charset[i++] = c++;
226
	c = 0xa2a;		// from GURMUKHI LETTER PA
227
	while (c <= 0xa30)	// ..to GURMUKHI LETTER RA
228
		charset[i++] = c++;
229
	charset[i++] = 0xa32;	// GURMUKHI LETTER LA
230
	charset[i++] = 0xa33;	// GURMUKHI LETTER LLA
231
	charset[i++] = 0xa35;	// GURMUKHI LETTER VA
232
	charset[i++] = 0xa36;	// GURMUKHI LETTER SHA
233
	charset[i++] = 0xa38;	// GURMUKHI LETTER SA
234
	charset[i++] = 0xa39;	// GURMUKHI LETTER HA
235
	c = 0xa3e;		// from GURMUKHI VOWEL SIGN AA
236
	while (c <= 0xa42)	// ..to GURMUKHI VOWEL SIGN UU
237
		charset[i++] = c++;
238
	charset[i++] = 0xa47;	// GURMUKHI VOWEL SIGN EE
239
	charset[i++] = 0xa48;	// GURMUKHI VOWEL SIGN AI
240
	charset[i++] = 0xa4b;	// GURMUKHI VOWEL SIGN OO
241
	charset[i++] = 0xa4d;	// GURMUKHI SIGN VIRAMA
242
	c = 0xa59;		// from GURMUKHI LETTER KHHA
243
	while (c <= 0xa5c)	// ..to GURMUKHI LETTER RRA
244
		charset[i++] = c++;
245
	c = 0xa66;		// from GURMUKHI DIGIT ZERO
246
	while (c <= 0xa76)	// ..to GURMUKHI ABBREVIATION SIGN
247
		charset[i++] = c++;
248
// 0A80..0AFF; Gujarati
249
	charset[i++] = 0xa81;	// GUJARATI SIGN CANDRABINDU
250
	charset[i++] = 0xa83;	// GUJARATI SIGN VISARGA
251
	c = 0xa85;		// from GUJARATI LETTER A
252
	while (c <= 0xa8d)	// ..to GUJARATI VOWEL CANDRA E
253
		charset[i++] = c++;
254
	charset[i++] = 0xa8f;	// GUJARATI LETTER E
255
	charset[i++] = 0xa91;	// GUJARATI VOWEL CANDRA O
256
	c = 0xa93;		// from GUJARATI LETTER O
257
	while (c <= 0xaa8)	// ..to GUJARATI LETTER NA
258
		charset[i++] = c++;
259
	c = 0xaaa;		// from GUJARATI LETTER PA
260
	while (c <= 0xab0)	// ..to GUJARATI LETTER RA
261
		charset[i++] = c++;
262
	charset[i++] = 0xab2;	// GUJARATI LETTER LA
263
	charset[i++] = 0xab3;	// GUJARATI LETTER LLA
264
	c = 0xab5;		// from GUJARATI LETTER VA
265
	while (c <= 0xab9)	// ..to GUJARATI LETTER HA
266
		charset[i++] = c++;
267
	c = 0xabc;		// from GUJARATI SIGN NUKTA
268
	while (c <= 0xac5)	// ..to GUJARATI VOWEL SIGN CANDRA E
269
		charset[i++] = c++;
270
	charset[i++] = 0xac7;	// GUJARATI VOWEL SIGN E
271
	charset[i++] = 0xac9;	// GUJARATI VOWEL SIGN CANDRA O
272
	charset[i++] = 0xacb;	// GUJARATI VOWEL SIGN O
273
	charset[i++] = 0xacd;	// GUJARATI SIGN VIRAMA
274
	c = 0xae0;		// from GUJARATI LETTER VOCALIC RR
275
	while (c <= 0xae3)	// ..to GUJARATI VOWEL SIGN VOCALIC LL
276
		charset[i++] = c++;
277
	c = 0xae6;		// from GUJARATI DIGIT ZERO
278
	while (c <= 0xaf1)	// ..to GUJARATI RUPEE SIGN
279
		charset[i++] = c++;
280
	c = 0xaf9;		// from GUJARATI LETTER ZHA
281
	while (c <= 0xaff)	// ..to GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
282
		charset[i++] = c++;
283
// 0B00..0B7F; Oriya
284
	charset[i++] = 0xb01;	// ORIYA SIGN CANDRABINDU
285
	charset[i++] = 0xb03;	// ORIYA SIGN VISARGA
286
	c = 0xb05;		// from ORIYA LETTER A
287
	while (c <= 0xb0c)	// ..to ORIYA LETTER VOCALIC L
288
		charset[i++] = c++;
289
	charset[i++] = 0xb0f;	// ORIYA LETTER E
290
	charset[i++] = 0xb10;	// ORIYA LETTER AI
291
	c = 0xb13;		// from ORIYA LETTER O
292
	while (c <= 0xb28)	// ..to ORIYA LETTER NA
293
		charset[i++] = c++;
294
	c = 0xb2a;		// from ORIYA LETTER PA
295
	while (c <= 0xb30)	// ..to ORIYA LETTER RA
296
		charset[i++] = c++;
297
	charset[i++] = 0xb32;	// ORIYA LETTER LA
298
	charset[i++] = 0xb33;	// ORIYA LETTER LLA
299
	c = 0xb35;		// from ORIYA LETTER VA
300
	while (c <= 0xb39)	// ..to ORIYA LETTER HA
301
		charset[i++] = c++;
302
	c = 0xb3c;		// from ORIYA SIGN NUKTA
303
	while (c <= 0xb44)	// ..to ORIYA VOWEL SIGN VOCALIC RR
304
		charset[i++] = c++;
305
	charset[i++] = 0xb47;	// ORIYA VOWEL SIGN E
306
	charset[i++] = 0xb48;	// ORIYA VOWEL SIGN AI
307
	charset[i++] = 0xb4b;	// ORIYA VOWEL SIGN O
308
	charset[i++] = 0xb4d;	// ORIYA SIGN VIRAMA
309
	charset[i++] = 0xb55;	// ORIYA SIGN OVERLINE
310
	charset[i++] = 0xb57;	// ORIYA AU LENGTH MARK
311
	charset[i++] = 0xb5c;	// ORIYA LETTER RRA
312
	charset[i++] = 0xb5d;	// ORIYA LETTER RHA
313
	c = 0xb5f;		// from ORIYA LETTER YYA
314
	while (c <= 0xb63)	// ..to ORIYA VOWEL SIGN VOCALIC LL
315
		charset[i++] = c++;
316
	c = 0xb66;		// from ORIYA DIGIT ZERO
317
	while (c <= 0xb77)	// ..to ORIYA FRACTION THREE SIXTEENTHS
318
		charset[i++] = c++;
319
// 0B80..0BFF; Tamil
320
	charset[i++] = 0xb82;	// TAMIL SIGN ANUSVARA
321
	charset[i++] = 0xb83;	// TAMIL SIGN VISARGA
322
	c = 0xb85;		// from TAMIL LETTER A
323
	while (c <= 0xb8a)	// ..to TAMIL LETTER UU
324
		charset[i++] = c++;
325
	charset[i++] = 0xb8e;	// TAMIL LETTER E
326
	charset[i++] = 0xb90;	// TAMIL LETTER AI
327
	c = 0xb92;		// from TAMIL LETTER O
328
	while (c <= 0xb95)	// ..to TAMIL LETTER KA
329
		charset[i++] = c++;
330
	charset[i++] = 0xb99;	// TAMIL LETTER NGA
331
	charset[i++] = 0xb9a;	// TAMIL LETTER CA
332
	charset[i++] = 0xb9e;	// TAMIL LETTER NYA
333
	charset[i++] = 0xb9f;	// TAMIL LETTER TTA
334
	charset[i++] = 0xba3;	// TAMIL LETTER NNA
335
	charset[i++] = 0xba4;	// TAMIL LETTER TA
336
	charset[i++] = 0xba8;	// TAMIL LETTER NA
337
	charset[i++] = 0xbaa;	// TAMIL LETTER PA
338
	c = 0xbae;		// from TAMIL LETTER MA
339
	while (c <= 0xbb9)	// ..to TAMIL LETTER HA
340
		charset[i++] = c++;
341
	c = 0xbbe;		// from TAMIL VOWEL SIGN AA
342
	while (c <= 0xbc2)	// ..to TAMIL VOWEL SIGN UU
343
		charset[i++] = c++;
344
	charset[i++] = 0xbc6;	// TAMIL VOWEL SIGN E
345
	charset[i++] = 0xbc8;	// TAMIL VOWEL SIGN AI
346
	c = 0xbca;		// from TAMIL VOWEL SIGN O
347
	while (c <= 0xbcd)	// ..to TAMIL SIGN VIRAMA
348
		charset[i++] = c++;
349
	c = 0xbe6;		// from TAMIL DIGIT ZERO
350
	while (c <= 0xbfa)	// ..to TAMIL NUMBER SIGN
351
		charset[i++] = c++;
352
// 0C00..0C7F; Telugu
353
	c = 0xc00;		// from TELUGU SIGN COMBINING CANDRABINDU ABOVE
354
	while (c <= 0xc0c)	// ..to TELUGU LETTER VOCALIC L
355
		charset[i++] = c++;
356
	charset[i++] = 0xc0e;	// TELUGU LETTER E
357
	charset[i++] = 0xc10;	// TELUGU LETTER AI
358
	c = 0xc12;		// from TELUGU LETTER O
359
	while (c <= 0xc28)	// ..to TELUGU LETTER NA
360
		charset[i++] = c++;
361
	c = 0xc2a;		// from TELUGU LETTER PA
362
	while (c <= 0xc39)	// ..to TELUGU LETTER HA
363
		charset[i++] = c++;
364
	c = 0xc3d;		// from TELUGU SIGN AVAGRAHA
365
	while (c <= 0xc44)	// ..to TELUGU VOWEL SIGN VOCALIC RR
366
		charset[i++] = c++;
367
	charset[i++] = 0xc46;	// TELUGU VOWEL SIGN E
368
	charset[i++] = 0xc48;	// TELUGU VOWEL SIGN AI
369
	c = 0xc4a;		// from TELUGU VOWEL SIGN O
370
	while (c <= 0xc4d)	// ..to TELUGU SIGN VIRAMA
371
		charset[i++] = c++;
372
	charset[i++] = 0xc55;	// TELUGU LENGTH MARK
373
	charset[i++] = 0xc56;	// TELUGU AI LENGTH MARK
374
	charset[i++] = 0xc58;	// TELUGU LETTER TSA
375
	charset[i++] = 0xc5a;	// TELUGU LETTER RRRA
376
	c = 0xc60;		// from TELUGU LETTER VOCALIC RR
377
	while (c <= 0xc63)	// ..to TELUGU VOWEL SIGN VOCALIC LL
378
		charset[i++] = c++;
379
	c = 0xc66;		// from TELUGU DIGIT ZERO
380
	while (c <= 0xc6f)	// ..to TELUGU DIGIT NINE
381
		charset[i++] = c++;
382
	c = 0xc77;		// from TELUGU SIGN SIDDHAM
383
	while (c <= 0xc7f)	// ..to TELUGU SIGN TUUMU
384
		charset[i++] = c++;
385
// 0C80..0CFF; Kannada
386
	c = 0xc80;		// from KANNADA SIGN SPACING CANDRABINDU
387
	while (c <= 0xc8c)	// ..to KANNADA LETTER VOCALIC L
388
		charset[i++] = c++;
389
	charset[i++] = 0xc8e;	// KANNADA LETTER E
390
	charset[i++] = 0xc90;	// KANNADA LETTER AI
391
	c = 0xc92;		// from KANNADA LETTER O
392
	while (c <= 0xca8)	// ..to KANNADA LETTER NA
393
		charset[i++] = c++;
394
	c = 0xcaa;		// from KANNADA LETTER PA
395
	while (c <= 0xcb3)	// ..to KANNADA LETTER LLA
396
		charset[i++] = c++;
397
	c = 0xcb5;		// from KANNADA LETTER VA
398
	while (c <= 0xcb9)	// ..to KANNADA LETTER HA
399
		charset[i++] = c++;
400
	c = 0xcbc;		// from KANNADA SIGN NUKTA
401
	while (c <= 0xcc4)	// ..to KANNADA VOWEL SIGN VOCALIC RR
402
		charset[i++] = c++;
403
	charset[i++] = 0xcc6;	// KANNADA VOWEL SIGN E
404
	charset[i++] = 0xcc8;	// KANNADA VOWEL SIGN AI
405
	c = 0xcca;		// from KANNADA VOWEL SIGN O
406
	while (c <= 0xccd)	// ..to KANNADA SIGN VIRAMA
407
		charset[i++] = c++;
408
	charset[i++] = 0xcd5;	// KANNADA LENGTH MARK
409
	charset[i++] = 0xcd6;	// KANNADA AI LENGTH MARK
410
	c = 0xce0;		// from KANNADA LETTER VOCALIC RR
411
	while (c <= 0xce3)	// ..to KANNADA VOWEL SIGN VOCALIC LL
412
		charset[i++] = c++;
413
	c = 0xce6;		// from KANNADA DIGIT ZERO
414
	while (c <= 0xcef)	// ..to KANNADA DIGIT NINE
415
		charset[i++] = c++;
416
	charset[i++] = 0xcf1;	// KANNADA SIGN JIHVAMULIYA
417
	charset[i++] = 0xcf2;	// KANNADA SIGN UPADHMANIYA
418
// 0D00..0D7F; Malayalam
419
	c = 0xd00;		// from MALAYALAM SIGN COMBINING ANUSVARA ABOVE
420
	while (c <= 0xd0c)	// ..to MALAYALAM LETTER VOCALIC L
421
		charset[i++] = c++;
422
	charset[i++] = 0xd0e;	// MALAYALAM LETTER E
423
	charset[i++] = 0xd10;	// MALAYALAM LETTER AI
424
	c = 0xd12;		// from MALAYALAM LETTER O
425
	while (c <= 0xd44)	// ..to MALAYALAM VOWEL SIGN VOCALIC RR
426
		charset[i++] = c++;
427
	charset[i++] = 0xd46;	// MALAYALAM VOWEL SIGN E
428
	charset[i++] = 0xd48;	// MALAYALAM VOWEL SIGN AI
429
	c = 0xd4a;		// from MALAYALAM VOWEL SIGN O
430
	while (c <= 0xd4f)	// ..to MALAYALAM SIGN PARA
431
		charset[i++] = c++;
432
	c = 0xd54;		// from MALAYALAM LETTER CHILLU M
433
	while (c <= 0xd63)	// ..to MALAYALAM VOWEL SIGN VOCALIC LL
434
		charset[i++] = c++;
435
	c = 0xd66;		// from MALAYALAM DIGIT ZERO
436
	while (c <= 0xd7f)	// ..to MALAYALAM LETTER CHILLU K
437
		charset[i++] = c++;
438
// 0D80..0DFF; Sinhala
439
	charset[i++] = 0xd81;	// SINHALA SIGN CANDRABINDU
440
	charset[i++] = 0xd83;	// SINHALA SIGN VISARGAYA
441
	c = 0xd85;		// from SINHALA LETTER AYANNA
442
	while (c <= 0xd96)	// ..to SINHALA LETTER AUYANNA
443
		charset[i++] = c++;
444
	c = 0xd9a;		// from SINHALA LETTER ALPAPRAANA KAYANNA
445
	while (c <= 0xdb1)	// ..to SINHALA LETTER DANTAJA NAYANNA
446
		charset[i++] = c++;
447
	c = 0xdb3;		// from SINHALA LETTER SANYAKA DAYANNA
448
	while (c <= 0xdbb)	// ..to SINHALA LETTER RAYANNA
449
		charset[i++] = c++;
450
	c = 0xdc0;		// from SINHALA LETTER VAYANNA
451
	while (c <= 0xdc6)	// ..to SINHALA LETTER FAYANNA
452
		charset[i++] = c++;
453
	c = 0xdcf;		// from SINHALA VOWEL SIGN AELA-PILLA
454
	while (c <= 0xdd4)	// ..to SINHALA VOWEL SIGN KETTI PAA-PILLA
455
		charset[i++] = c++;
456
	c = 0xdd8;		// from SINHALA VOWEL SIGN GAETTA-PILLA
457
	while (c <= 0xddf)	// ..to SINHALA VOWEL SIGN GAYANUKITTA
458
		charset[i++] = c++;
459
	c = 0xde6;		// from SINHALA LITH DIGIT ZERO
460
	while (c <= 0xdef)	// ..to SINHALA LITH DIGIT NINE
461
		charset[i++] = c++;
462
	charset[i++] = 0xdf2;	// SINHALA VOWEL SIGN DIGA GAETTA-PILLA
463
	charset[i++] = 0xdf4;	// SINHALA PUNCTUATION KUNDDALIYA
464
// 0E00..0E7F; Thai
465
	c = 0xe01;		// from THAI CHARACTER KO KAI
466
	while (c <= 0xe3a)	// ..to THAI CHARACTER PHINTHU
467
		charset[i++] = c++;
468
	c = 0xe3f;		// from THAI CURRENCY SYMBOL BAHT
469
	while (c <= 0xe5b)	// ..to THAI CHARACTER KHOMUT
470
		charset[i++] = c++;
471
// 0E80..0EFF; Lao
472
	charset[i++] = 0xe81;	// LAO LETTER KO
473
	charset[i++] = 0xe82;	// LAO LETTER KHO SUNG
474
	c = 0xe86;		// from LAO LETTER PALI GHA
475
	while (c <= 0xe8a)	// ..to LAO LETTER SO TAM
476
		charset[i++] = c++;
477
	c = 0xe8c;		// from LAO LETTER PALI JHA
478
	while (c <= 0xea3)	// ..to LAO LETTER LO LING
479
		charset[i++] = c++;
480
	c = 0xea7;		// from LAO LETTER WO
481
	while (c <= 0xebd)	// ..to LAO SEMIVOWEL SIGN NYO
482
		charset[i++] = c++;
483
	c = 0xec0;		// from LAO VOWEL SIGN E
484
	while (c <= 0xec4)	// ..to LAO VOWEL SIGN AI
485
		charset[i++] = c++;
486
	c = 0xec8;		// from LAO TONE MAI EK
487
	while (c <= 0xecd)	// ..to LAO NIGGAHITA
488
		charset[i++] = c++;
489
	c = 0xed0;		// from LAO DIGIT ZERO
490
	while (c <= 0xed9)	// ..to LAO DIGIT NINE
491
		charset[i++] = c++;
492
	c = 0xedc;		// from LAO HO NO
493
	while (c <= 0xedf)	// ..to LAO LETTER KHMU NYO
494
		charset[i++] = c++;
495
// 0F00..0FFF; Tibetan
496
	c = 0xf00;		// from TIBETAN SYLLABLE OM
497
	while (c <= 0xf47)	// ..to TIBETAN LETTER JA
498
		charset[i++] = c++;
499
	c = 0xf49;		// from TIBETAN LETTER NYA
500
	while (c <= 0xf6c)	// ..to TIBETAN LETTER RRA
501
		charset[i++] = c++;
502
	c = 0xf71;		// from TIBETAN VOWEL SIGN AA
503
	while (c <= 0xf97)	// ..to TIBETAN SUBJOINED LETTER JA
504
		charset[i++] = c++;
505
	c = 0xf99;		// from TIBETAN SUBJOINED LETTER NYA
506
	while (c <= 0xfbc)	// ..to TIBETAN SUBJOINED LETTER FIXED-FORM RA
507
		charset[i++] = c++;
508
	c = 0xfbe;		// from TIBETAN KU RU KHA
509
	while (c <= 0xfcc)	// ..to TIBETAN SYMBOL NOR BU BZHI -KHYIL
510
		charset[i++] = c++;
511
	c = 0xfce;		// from TIBETAN SIGN RDEL NAG RDEL DKAR
512
	while (c <= 0xfda)	// ..to TIBETAN MARK TRAILING MCHAN RTAGS
513
		charset[i++] = c++;
514
// 1000..109F; Myanmar
515
	c = 0x1000;		// from MYANMAR LETTER KA
516
	while (c <= 0x109f)	// ..to MYANMAR SYMBOL SHAN EXCLAMATION
517
		charset[i++] = c++;
518
// 10A0..10FF; Georgian
519
	c = 0x10a0;		// from GEORGIAN CAPITAL LETTER AN
520
	while (c <= 0x10c5)	// ..to GEORGIAN CAPITAL LETTER HOE
521
		charset[i++] = c++;
522
	c = 0x10d0;		// from GEORGIAN LETTER AN
523
	while (c <= 0x10ff)	// ..to GEORGIAN LETTER LABIAL SIGN
524
		charset[i++] = c++;
525
// 1100..11FF; Hangul Jamo
526
	c = 0x1100;		// from HANGUL CHOSEONG KIYEOK
527
	while (c <= 0x11ff)	// ..to HANGUL JONGSEONG SSANGNIEUN
528
		charset[i++] = c++;
529
// 1200..137F; Ethiopic
530
	c = 0x1200;		// from ETHIOPIC SYLLABLE HA
531
	while (c <= 0x1248)	// ..to ETHIOPIC SYLLABLE QWA
532
		charset[i++] = c++;
533
	c = 0x124a;		// from ETHIOPIC SYLLABLE QWI
534
	while (c <= 0x124d)	// ..to ETHIOPIC SYLLABLE QWE
535
		charset[i++] = c++;
536
	c = 0x1250;		// from ETHIOPIC SYLLABLE QHA
537
	while (c <= 0x1256)	// ..to ETHIOPIC SYLLABLE QHO
538
		charset[i++] = c++;
539
	c = 0x125a;		// from ETHIOPIC SYLLABLE QHWI
540
	while (c <= 0x125d)	// ..to ETHIOPIC SYLLABLE QHWE
541
		charset[i++] = c++;
542
	c = 0x1260;		// from ETHIOPIC SYLLABLE BA
543
	while (c <= 0x1288)	// ..to ETHIOPIC SYLLABLE XWA
544
		charset[i++] = c++;
545
	c = 0x128a;		// from ETHIOPIC SYLLABLE XWI
546
	while (c <= 0x128d)	// ..to ETHIOPIC SYLLABLE XWE
547
		charset[i++] = c++;
548
	c = 0x1290;		// from ETHIOPIC SYLLABLE NA
549
	while (c <= 0x12b0)	// ..to ETHIOPIC SYLLABLE KWA
550
		charset[i++] = c++;
551
	c = 0x12b2;		// from ETHIOPIC SYLLABLE KWI
552
	while (c <= 0x12b5)	// ..to ETHIOPIC SYLLABLE KWE
553
		charset[i++] = c++;
554
	c = 0x12b8;		// from ETHIOPIC SYLLABLE KXA
555
	while (c <= 0x12be)	// ..to ETHIOPIC SYLLABLE KXO
556
		charset[i++] = c++;
557
	c = 0x12c2;		// from ETHIOPIC SYLLABLE KXWI
558
	while (c <= 0x12c5)	// ..to ETHIOPIC SYLLABLE KXWE
559
		charset[i++] = c++;
560
	c = 0x12c8;		// from ETHIOPIC SYLLABLE WA
561
	while (c <= 0x12d6)	// ..to ETHIOPIC SYLLABLE PHARYNGEAL O
562
		charset[i++] = c++;
563
	c = 0x12d8;		// from ETHIOPIC SYLLABLE ZA
564
	while (c <= 0x1310)	// ..to ETHIOPIC SYLLABLE GWA
565
		charset[i++] = c++;
566
	c = 0x1312;		// from ETHIOPIC SYLLABLE GWI
567
	while (c <= 0x1315)	// ..to ETHIOPIC SYLLABLE GWE
568
		charset[i++] = c++;
569
	c = 0x1318;		// from ETHIOPIC SYLLABLE GGA
570
	while (c <= 0x135a)	// ..to ETHIOPIC SYLLABLE FYA
571
		charset[i++] = c++;
572
	c = 0x135d;		// from ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK
573
	while (c <= 0x137c)	// ..to ETHIOPIC NUMBER TEN THOUSAND
574
		charset[i++] = c++;
575
// 1380..139F; Ethiopic Supplement
576
	c = 0x1380;		// from ETHIOPIC SYLLABLE SEBATBEIT MWA
577
	while (c <= 0x1399)	// ..to ETHIOPIC TONAL MARK KURT
578
		charset[i++] = c++;
579
// 13A0..13FF; Cherokee
580
	c = 0x13a0;		// from CHEROKEE LETTER A
581
	while (c <= 0x13f5)	// ..to CHEROKEE LETTER MV
582
		charset[i++] = c++;
583
	c = 0x13f8;		// from CHEROKEE SMALL LETTER YE
584
	while (c <= 0x13fd)	// ..to CHEROKEE SMALL LETTER MV
585
		charset[i++] = c++;
586
// 1400..167F; Unified Canadian Aboriginal Syllabics
587
	c = 0x1400;		// from CANADIAN SYLLABICS HYPHEN
588
	while (c <= 0x167f)	// ..to CANADIAN SYLLABICS BLACKFOOT W
589
		charset[i++] = c++;
590
// 1680..169F; Ogham
591
	c = 0x1680;		// from OGHAM SPACE MARK
592
	while (c <= 0x169c)	// ..to OGHAM REVERSED FEATHER MARK
593
		charset[i++] = c++;
594
// 16A0..16FF; Runic
595
	c = 0x16a0;		// from RUNIC LETTER FEHU FEOH FE F
596
	while (c <= 0x16f8)	// ..to RUNIC LETTER FRANKS CASKET AESC
597
		charset[i++] = c++;
598
// 1700..171F; Tagalog
599
	c = 0x1700;		// from TAGALOG LETTER A
600
	while (c <= 0x170c)	// ..to TAGALOG LETTER YA
601
		charset[i++] = c++;
602
	c = 0x170e;		// from TAGALOG LETTER LA
603
	while (c <= 0x1714)	// ..to TAGALOG SIGN VIRAMA
604
		charset[i++] = c++;
605
// 1720..173F; Hanunoo
606
	c = 0x1720;		// from HANUNOO LETTER A
607
	while (c <= 0x1736)	// ..to PHILIPPINE DOUBLE PUNCTUATION
608
		charset[i++] = c++;
609
// 1740..175F; Buhid
610
	c = 0x1740;		// from BUHID LETTER A
611
	while (c <= 0x1753)	// ..to BUHID VOWEL SIGN U
612
		charset[i++] = c++;
613
// 1760..177F; Tagbanwa
614
	c = 0x1760;		// from TAGBANWA LETTER A
615
	while (c <= 0x176c)	// ..to TAGBANWA LETTER YA
616
		charset[i++] = c++;
617
	charset[i++] = 0x176e;	// TAGBANWA LETTER LA
618
	charset[i++] = 0x1770;	// TAGBANWA LETTER SA
619
	charset[i++] = 0x1772;	// TAGBANWA VOWEL SIGN I
620
	charset[i++] = 0x1773;	// TAGBANWA VOWEL SIGN U
621
// 1780..17FF; Khmer
622
	c = 0x1780;		// from KHMER LETTER KA
623
	while (c <= 0x17dd)	// ..to KHMER SIGN ATTHACAN
624
		charset[i++] = c++;
625
	c = 0x17e0;		// from KHMER DIGIT ZERO
626
	while (c <= 0x17e9)	// ..to KHMER DIGIT NINE
627
		charset[i++] = c++;
628
	c = 0x17f0;		// from KHMER SYMBOL LEK ATTAK SON
629
	while (c <= 0x17f9)	// ..to KHMER SYMBOL LEK ATTAK PRAM-BUON
630
		charset[i++] = c++;
631
// 1800..18AF; Mongolian
632
	c = 0x1800;		// from MONGOLIAN BIRGA
633
	while (c <= 0x180e)	// ..to MONGOLIAN VOWEL SEPARATOR
634
		charset[i++] = c++;
635
	c = 0x1810;		// from MONGOLIAN DIGIT ZERO
636
	while (c <= 0x1819)	// ..to MONGOLIAN DIGIT NINE
637
		charset[i++] = c++;
638
	c = 0x1820;		// from MONGOLIAN LETTER A
639
	while (c <= 0x1878)	// ..to MONGOLIAN LETTER CHA WITH TWO DOTS
640
		charset[i++] = c++;
641
	c = 0x1880;		// from MONGOLIAN LETTER ALI GALI ANUSVARA ONE
642
	while (c <= 0x18aa)	// ..to MONGOLIAN LETTER MANCHU ALI GALI LHA
643
		charset[i++] = c++;
644
// 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
645
	c = 0x18b0;		// from CANADIAN SYLLABICS OY
646
	while (c <= 0x18f5)	// ..to CANADIAN SYLLABICS CARRIER DENTAL S
647
		charset[i++] = c++;
648
// 1900..194F; Limbu
649
	c = 0x1900;		// from LIMBU VOWEL-CARRIER LETTER
650
	while (c <= 0x191e)	// ..to LIMBU LETTER TRA
651
		charset[i++] = c++;
652
	c = 0x1920;		// from LIMBU VOWEL SIGN A
653
	while (c <= 0x192b)	// ..to LIMBU SUBJOINED LETTER WA
654
		charset[i++] = c++;
655
	c = 0x1930;		// from LIMBU SMALL LETTER KA
656
	while (c <= 0x193b)	// ..to LIMBU SIGN SA-I
657
		charset[i++] = c++;
658
	c = 0x1944;		// from LIMBU EXCLAMATION MARK
659
	while (c <= 0x194f)	// ..to LIMBU DIGIT NINE
660
		charset[i++] = c++;
661
// 1950..197F; Tai Le
662
	c = 0x1950;		// from TAI LE LETTER KA
663
	while (c <= 0x196d)	// ..to TAI LE LETTER AI
664
		charset[i++] = c++;
665
	c = 0x1970;		// from TAI LE LETTER TONE-2
666
	while (c <= 0x1974)	// ..to TAI LE LETTER TONE-6
667
		charset[i++] = c++;
668
// 1980..19DF; New Tai Lue
669
	c = 0x1980;		// from NEW TAI LUE LETTER HIGH QA
670
	while (c <= 0x19ab)	// ..to NEW TAI LUE LETTER LOW SUA
671
		charset[i++] = c++;
672
	c = 0x19b0;		// from NEW TAI LUE VOWEL SIGN VOWEL SHORTENER
673
	while (c <= 0x19c9)	// ..to NEW TAI LUE TONE MARK-2
674
		charset[i++] = c++;
675
	c = 0x19d0;		// from NEW TAI LUE DIGIT ZERO
676
	while (c <= 0x19da)	// ..to NEW TAI LUE THAM DIGIT ONE
677
		charset[i++] = c++;
678
	charset[i++] = 0x19de;	// NEW TAI LUE SIGN LAE
679
	charset[i++] = 0x19df;	// NEW TAI LUE SIGN LAEV
680
// 19E0..19FF; Khmer Symbols
681
	c = 0x19e0;		// from KHMER SYMBOL PATHAMASAT
682
	while (c <= 0x19ff)	// ..to KHMER SYMBOL DAP-PRAM ROC
683
		charset[i++] = c++;
684
// 1A00..1A1F; Buginese
685
	c = 0x1a00;		// from BUGINESE LETTER KA
686
	while (c <= 0x1a1b)	// ..to BUGINESE VOWEL SIGN AE
687
		charset[i++] = c++;
688
	charset[i++] = 0x1a1e;	// BUGINESE PALLAWA
689
	charset[i++] = 0x1a1f;	// BUGINESE END OF SECTION
690
// 1A20..1AAF; Tai Tham
691
	c = 0x1a20;		// from TAI THAM LETTER HIGH KA
692
	while (c <= 0x1a5e)	// ..to TAI THAM CONSONANT SIGN SA
693
		charset[i++] = c++;
694
	c = 0x1a60;		// from TAI THAM SIGN SAKOT
695
	while (c <= 0x1a7c)	// ..to TAI THAM SIGN KHUEN-LUE KARAN
696
		charset[i++] = c++;
697
	c = 0x1a7f;		// from TAI THAM COMBINING CRYPTOGRAMMIC DOT
698
	while (c <= 0x1a89)	// ..to TAI THAM HORA DIGIT NINE
699
		charset[i++] = c++;
700
	c = 0x1a90;		// from TAI THAM THAM DIGIT ZERO
701
	while (c <= 0x1a99)	// ..to TAI THAM THAM DIGIT NINE
702
		charset[i++] = c++;
703
	c = 0x1aa0;		// from TAI THAM SIGN WIANG
704
	while (c <= 0x1aad)	// ..to TAI THAM SIGN CAANG
705
		charset[i++] = c++;
706
// 1AB0..1AFF; Combining Diacritical Marks Extended
707
	c = 0x1ab0;		// from COMBINING DOUBLED CIRCUMFLEX ACCENT
708
	while (c <= 0x1ac0)	// ..to COMBINING LATIN SMALL LETTER TURNED W BELOW
709
		charset[i++] = c++;
710
// 1B00..1B7F; Balinese
711
	c = 0x1b00;		// from BALINESE SIGN ULU RICEM
712
	while (c <= 0x1b4b)	// ..to BALINESE LETTER ASYURA SASAK
713
		charset[i++] = c++;
714
	c = 0x1b50;		// from BALINESE DIGIT ZERO
715
	while (c <= 0x1b7c)	// ..to BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING
716
		charset[i++] = c++;
717
// 1B80..1BBF; Sundanese
718
	c = 0x1b80;		// from SUNDANESE SIGN PANYECEK
719
	while (c <= 0x1bbf)	// ..to SUNDANESE LETTER FINAL M
720
		charset[i++] = c++;
721
// 1BC0..1BFF; Batak
722
	c = 0x1bc0;		// from BATAK LETTER A
723
	while (c <= 0x1bf3)	// ..to BATAK PANONGONAN
724
		charset[i++] = c++;
725
	c = 0x1bfc;		// from BATAK SYMBOL BINDU NA METEK
726
	while (c <= 0x1bff)	// ..to BATAK SYMBOL BINDU PANGOLAT
727
		charset[i++] = c++;
728
// 1C00..1C4F; Lepcha
729
	c = 0x1c00;		// from LEPCHA LETTER KA
730
	while (c <= 0x1c37)	// ..to LEPCHA SIGN NUKTA
731
		charset[i++] = c++;
732
	c = 0x1c3b;		// from LEPCHA PUNCTUATION TA-ROL
733
	while (c <= 0x1c49)	// ..to LEPCHA DIGIT NINE
734
		charset[i++] = c++;
735
	charset[i++] = 0x1c4d;	// LEPCHA LETTER TTA
736
	charset[i++] = 0x1c4f;	// LEPCHA LETTER DDA
737
// 1C50..1C7F; Ol Chiki
738
	c = 0x1c50;		// from OL CHIKI DIGIT ZERO
739
	while (c <= 0x1c7f)	// ..to OL CHIKI PUNCTUATION DOUBLE MUCAAD
740
		charset[i++] = c++;
741
// 1C80..1C8F; Cyrillic Extended-C
742
	c = 0x1c80;		// from CYRILLIC SMALL LETTER ROUNDED VE
743
	while (c <= 0x1c88)	// ..to CYRILLIC SMALL LETTER UNBLENDED UK
744
		charset[i++] = c++;
745
// 1C90..1CBF; Georgian Extended
746
	c = 0x1c90;		// from GEORGIAN MTAVRULI CAPITAL LETTER AN
747
	while (c <= 0x1cba)	// ..to GEORGIAN MTAVRULI CAPITAL LETTER AIN
748
		charset[i++] = c++;
749
	charset[i++] = 0x1cbd;	// GEORGIAN MTAVRULI CAPITAL LETTER AEN
750
	charset[i++] = 0x1cbf;	// GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN
751
// 1CC0..1CCF; Sundanese Supplement
752
	c = 0x1cc0;		// from SUNDANESE PUNCTUATION BINDU SURYA
753
	while (c <= 0x1cc7)	// ..to SUNDANESE PUNCTUATION BINDU BA SATANGA
754
		charset[i++] = c++;
755
// 1CD0..1CFF; Vedic Extensions
756
	c = 0x1cd0;		// from VEDIC TONE KARSHANA
757
	while (c <= 0x1cfa)	// ..to VEDIC SIGN DOUBLE ANUSVARA ANTARGOMUKHA
758
		charset[i++] = c++;
759
// 1D00..1D7F; Phonetic Extensions
760
	c = 0x1d00;		// from LATIN LETTER SMALL CAPITAL A
761
	while (c <= 0x1d7f)	// ..to LATIN SMALL LETTER UPSILON WITH STROKE
762
		charset[i++] = c++;
763
// 1D80..1DBF; Phonetic Extensions Supplement
764
	c = 0x1d80;		// from LATIN SMALL LETTER B WITH PALATAL HOOK
765
	while (c <= 0x1dbf)	// ..to MODIFIER LETTER SMALL THETA
766
		charset[i++] = c++;
767
// 1DC0..1DFF; Combining Diacritical Marks Supplement
768
	c = 0x1dc0;		// from COMBINING DOTTED GRAVE ACCENT
769
	while (c <= 0x1df9)	// ..to COMBINING WIDE INVERTED BRIDGE BELOW
770
		charset[i++] = c++;
771
	c = 0x1dfb;		// from COMBINING DELETION MARK
772
	while (c <= 0x1dff)	// ..to COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
773
		charset[i++] = c++;
774
// 1E00..1EFF; Latin Extended Additional
775
	c = 0x1e00;		// from LATIN CAPITAL LETTER A WITH RING BELOW
776
	while (c <= 0x1eff)	// ..to LATIN SMALL LETTER Y WITH LOOP
777
		charset[i++] = c++;
778
// 1F00..1FFF; Greek Extended
779
	c = 0x1f00;		// from GREEK SMALL LETTER ALPHA WITH PSILI
780
	while (c <= 0x1f15)	// ..to GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
781
		charset[i++] = c++;
782
	c = 0x1f18;		// from GREEK CAPITAL LETTER EPSILON WITH PSILI
783
	while (c <= 0x1f1d)	// ..to GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
784
		charset[i++] = c++;
785
	c = 0x1f20;		// from GREEK SMALL LETTER ETA WITH PSILI
786
	while (c <= 0x1f45)	// ..to GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA
787
		charset[i++] = c++;
788
	c = 0x1f48;		// from GREEK CAPITAL LETTER OMICRON WITH PSILI
789
	while (c <= 0x1f4d)	// ..to GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA
790
		charset[i++] = c++;
791
	c = 0x1f50;		// from GREEK SMALL LETTER UPSILON WITH PSILI
792
	while (c <= 0x1f57)	// ..to GREEK SMALL LETTER UPSILON WITH DASIA AND PERISPOMENI
793
		charset[i++] = c++;
794
	c = 0x1f5f;		// from GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI
795
	while (c <= 0x1f7d)	// ..to GREEK SMALL LETTER OMEGA WITH OXIA
796
		charset[i++] = c++;
797
	c = 0x1f80;		// from GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
798
	while (c <= 0x1fb4)	// ..to GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
799
		charset[i++] = c++;
800
	c = 0x1fb6;		// from GREEK SMALL LETTER ALPHA WITH PERISPOMENI
801
	while (c <= 0x1fc4)	// ..to GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
802
		charset[i++] = c++;
803
	c = 0x1fc6;		// from GREEK SMALL LETTER ETA WITH PERISPOMENI
804
	while (c <= 0x1fd3)	// ..to GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
805
		charset[i++] = c++;
806
	c = 0x1fd6;		// from GREEK SMALL LETTER IOTA WITH PERISPOMENI
807
	while (c <= 0x1fdb)	// ..to GREEK CAPITAL LETTER IOTA WITH OXIA
808
		charset[i++] = c++;
809
	c = 0x1fdd;		// from GREEK DASIA AND VARIA
810
	while (c <= 0x1fef)	// ..to GREEK VARIA
811
		charset[i++] = c++;
812
	charset[i++] = 0x1ff2;	// GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
813
	charset[i++] = 0x1ff4;	// GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
814
	c = 0x1ff6;		// from GREEK SMALL LETTER OMEGA WITH PERISPOMENI
815
	while (c <= 0x1ffe)	// ..to GREEK DASIA
816
		charset[i++] = c++;
817
// 2000..206F; General Punctuation
818
	c = 0x2000;		// from EN QUAD
819
	while (c <= 0x2064)	// ..to INVISIBLE PLUS
820
		charset[i++] = c++;
821
	c = 0x2066;		// from LEFT-TO-RIGHT ISOLATE
822
	while (c <= 0x206f)	// ..to NOMINAL DIGIT SHAPES
823
		charset[i++] = c++;
824
// 2070..209F; Superscripts and Subscripts
825
	charset[i++] = 0x2070;	// SUPERSCRIPT ZERO
826
	charset[i++] = 0x2071;	// SUPERSCRIPT LATIN SMALL LETTER I
827
	c = 0x2074;		// from SUPERSCRIPT FOUR
828
	while (c <= 0x208e)	// ..to SUBSCRIPT RIGHT PARENTHESIS
829
		charset[i++] = c++;
830
	c = 0x2090;		// from LATIN SUBSCRIPT SMALL LETTER A
831
	while (c <= 0x209c)	// ..to LATIN SUBSCRIPT SMALL LETTER T
832
		charset[i++] = c++;
833
// 20A0..20CF; Currency Symbols
834
	c = 0x20a0;		// from EURO-CURRENCY SIGN
835
	while (c <= 0x20bf)	// ..to BITCOIN SIGN
836
		charset[i++] = c++;
837
// 20D0..20FF; Combining Diacritical Marks for Symbols
838
	c = 0x20d0;		// from COMBINING LEFT HARPOON ABOVE
839
	while (c <= 0x20f0)	// ..to COMBINING ASTERISK ABOVE
840
		charset[i++] = c++;
841
// 2100..214F; Letterlike Symbols
842
	c = 0x2100;		// from ACCOUNT OF
843
	while (c <= 0x214f)	// ..to SYMBOL FOR SAMARITAN SOURCE
844
		charset[i++] = c++;
845
// 2150..218F; Number Forms
846
	c = 0x2150;		// from VULGAR FRACTION ONE SEVENTH
847
	while (c <= 0x218b)	// ..to TURNED DIGIT THREE
848
		charset[i++] = c++;
849
// 2190..21FF; Arrows
850
	c = 0x2190;		// from LEFTWARDS ARROW
851
	while (c <= 0x21ff)	// ..to LEFT RIGHT OPEN-HEADED ARROW
852
		charset[i++] = c++;
853
// 2200..22FF; Mathematical Operators
854
	c = 0x2200;		// from FOR ALL
855
	while (c <= 0x22ff)	// ..to Z NOTATION BAG MEMBERSHIP
856
		charset[i++] = c++;
857
// 2300..23FF; Miscellaneous Technical
858
	c = 0x2300;		// from DIAMETER SIGN
859
	while (c <= 0x23ff)	// ..to OBSERVER EYE SYMBOL
860
		charset[i++] = c++;
861
// 2400..243F; Control Pictures
862
	c = 0x2400;		// from SYMBOL FOR NULL
863
	while (c <= 0x2426)	// ..to SYMBOL FOR SUBSTITUTE FORM TWO
864
		charset[i++] = c++;
865
// 2440..245F; Optical Character Recognition
866
	c = 0x2440;		// from OCR HOOK
867
	while (c <= 0x244a)	// ..to OCR DOUBLE BACKSLASH
868
		charset[i++] = c++;
869
// 2460..24FF; Enclosed Alphanumerics
870
	c = 0x2460;		// from CIRCLED DIGIT ONE
871
	while (c <= 0x24ff)	// ..to NEGATIVE CIRCLED DIGIT ZERO
872
		charset[i++] = c++;
873
// 2500..257F; Box Drawing
874
	c = 0x2500;		// from BOX DRAWINGS LIGHT HORIZONTAL
875
	while (c <= 0x257f)	// ..to BOX DRAWINGS HEAVY UP AND LIGHT DOWN
876
		charset[i++] = c++;
877
// 2580..259F; Block Elements
878
	c = 0x2580;		// from UPPER HALF BLOCK
879
	while (c <= 0x259f)	// ..to QUADRANT UPPER RIGHT AND LOWER LEFT AND LOWER RIGHT
880
		charset[i++] = c++;
881
// 25A0..25FF; Geometric Shapes
882
	c = 0x25a0;		// from BLACK SQUARE
883
	while (c <= 0x25ff)	// ..to LOWER RIGHT TRIANGLE
884
		charset[i++] = c++;
885
// 2600..26FF; Miscellaneous Symbols
886
	c = 0x2600;		// from BLACK SUN WITH RAYS
887
	while (c <= 0x26ff)	// ..to WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE
888
		charset[i++] = c++;
889
// 2700..27BF; Dingbats
890
	c = 0x2700;		// from BLACK SAFETY SCISSORS
891
	while (c <= 0x27bf)	// ..to DOUBLE CURLY LOOP
892
		charset[i++] = c++;
893
// 27C0..27EF; Miscellaneous Mathematical Symbols-A
894
	c = 0x27c0;		// from THREE DIMENSIONAL ANGLE
895
	while (c <= 0x27ef)	// ..to MATHEMATICAL RIGHT FLATTENED PARENTHESIS
896
		charset[i++] = c++;
897
// 27F0..27FF; Supplemental Arrows-A
898
	c = 0x27f0;		// from UPWARDS QUADRUPLE ARROW
899
	while (c <= 0x27ff)	// ..to LONG RIGHTWARDS SQUIGGLE ARROW
900
		charset[i++] = c++;
901
// 2800..28FF; Braille Patterns
902
	c = 0x2800;		// from BRAILLE PATTERN BLANK
903
	while (c <= 0x28ff)	// ..to BRAILLE PATTERN DOTS-12345678
904
		charset[i++] = c++;
905
// 2900..297F; Supplemental Arrows-B
906
	c = 0x2900;		// from RIGHTWARDS TWO-HEADED ARROW WITH VERTICAL STROKE
907
	while (c <= 0x297f)	// ..to DOWN FISH TAIL
908
		charset[i++] = c++;
909
// 2980..29FF; Miscellaneous Mathematical Symbols-B
910
	c = 0x2980;		// from TRIPLE VERTICAL BAR DELIMITER
911
	while (c <= 0x29ff)	// ..to MINY
912
		charset[i++] = c++;
913
// 2A00..2AFF; Supplemental Mathematical Operators
914
	c = 0x2a00;		// from N-ARY CIRCLED DOT OPERATOR
915
	while (c <= 0x2aff)	// ..to N-ARY WHITE VERTICAL BAR
916
		charset[i++] = c++;
917
// 2B00..2BFF; Miscellaneous Symbols and Arrows
918
	c = 0x2b00;		// from NORTH EAST WHITE ARROW
919
	while (c <= 0x2b73)	// ..to DOWNWARDS TRIANGLE-HEADED ARROW TO BAR
920
		charset[i++] = c++;
921
	c = 0x2b76;		// from NORTH WEST TRIANGLE-HEADED ARROW TO BAR
922
	while (c <= 0x2b95)	// ..to RIGHTWARDS BLACK ARROW
923
		charset[i++] = c++;
924
	c = 0x2b97;		// from SYMBOL FOR TYPE A ELECTRONICS
925
	while (c <= 0x2bff)	// ..to HELLSCHREIBER PAUSE SYMBOL
926
		charset[i++] = c++;
927
// 2C00..2C5F; Glagolitic
928
	c = 0x2c00;		// from GLAGOLITIC CAPITAL LETTER AZU
929
	while (c <= 0x2c2e)	// ..to GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
930
		charset[i++] = c++;
931
	c = 0x2c30;		// from GLAGOLITIC SMALL LETTER AZU
932
	while (c <= 0x2c5e)	// ..to GLAGOLITIC SMALL LETTER LATINATE MYSLITE
933
		charset[i++] = c++;
934
// 2C60..2C7F; Latin Extended-C
935
	c = 0x2c60;		// from LATIN CAPITAL LETTER L WITH DOUBLE BAR
936
	while (c <= 0x2c7f)	// ..to LATIN CAPITAL LETTER Z WITH SWASH TAIL
937
		charset[i++] = c++;
938
// 2C80..2CFF; Coptic
939
	c = 0x2c80;		// from COPTIC CAPITAL LETTER ALFA
940
	while (c <= 0x2cf3)	// ..to COPTIC SMALL LETTER BOHAIRIC KHEI
941
		charset[i++] = c++;
942
	c = 0x2cf9;		// from COPTIC OLD NUBIAN FULL STOP
943
	while (c <= 0x2cff)	// ..to COPTIC MORPHOLOGICAL DIVIDER
944
		charset[i++] = c++;
945
// 2D00..2D2F; Georgian Supplement
946
	c = 0x2d00;		// from GEORGIAN SMALL LETTER AN
947
	while (c <= 0x2d25)	// ..to GEORGIAN SMALL LETTER HOE
948
		charset[i++] = c++;
949
	c = 0x2d27;		// from GEORGIAN SMALL LETTER YN
950
	while (c <= 0x2d2d)	// ..to GEORGIAN SMALL LETTER AEN
951
		charset[i++] = c++;
952
// 2D30..2D7F; Tifinagh
953
	c = 0x2d30;		// from TIFINAGH LETTER YA
954
	while (c <= 0x2d67)	// ..to TIFINAGH LETTER YO
955
		charset[i++] = c++;
956
	charset[i++] = 0x2d6f;	// TIFINAGH MODIFIER LETTER LABIALIZATION MARK
957
	charset[i++] = 0x2d70;	// TIFINAGH SEPARATOR MARK
958
	charset[i++] = 0x2d7f;	// TIFINAGH CONSONANT JOINER
959
// 2D80..2DDF; Ethiopic Extended
960
	c = 0x2d80;		// from ETHIOPIC SYLLABLE LOA
961
	while (c <= 0x2d96)	// ..to ETHIOPIC SYLLABLE GGWE
962
		charset[i++] = c++;
963
	c = 0x2da0;		// from ETHIOPIC SYLLABLE SSA
964
	while (c <= 0x2da6)	// ..to ETHIOPIC SYLLABLE SSO
965
		charset[i++] = c++;
966
	c = 0x2da8;		// from ETHIOPIC SYLLABLE CCA
967
	while (c <= 0x2dae)	// ..to ETHIOPIC SYLLABLE CCO
968
		charset[i++] = c++;
969
	c = 0x2db0;		// from ETHIOPIC SYLLABLE ZZA
970
	while (c <= 0x2db6)	// ..to ETHIOPIC SYLLABLE ZZO
971
		charset[i++] = c++;
972
	c = 0x2db8;		// from ETHIOPIC SYLLABLE CCHA
973
	while (c <= 0x2dbe)	// ..to ETHIOPIC SYLLABLE CCHO
974
		charset[i++] = c++;
975
	c = 0x2dc0;		// from ETHIOPIC SYLLABLE QYA
976
	while (c <= 0x2dc6)	// ..to ETHIOPIC SYLLABLE QYO
977
		charset[i++] = c++;
978
	c = 0x2dc8;		// from ETHIOPIC SYLLABLE KYA
979
	while (c <= 0x2dce)	// ..to ETHIOPIC SYLLABLE KYO
980
		charset[i++] = c++;
981
	c = 0x2dd0;		// from ETHIOPIC SYLLABLE XYA
982
	while (c <= 0x2dd6)	// ..to ETHIOPIC SYLLABLE XYO
983
		charset[i++] = c++;
984
	c = 0x2dd8;		// from ETHIOPIC SYLLABLE GYA
985
	while (c <= 0x2dde)	// ..to ETHIOPIC SYLLABLE GYO
986
		charset[i++] = c++;
987
// 2DE0..2DFF; Cyrillic Extended-A
988
	c = 0x2de0;		// from COMBINING CYRILLIC LETTER BE
989
	while (c <= 0x2dff)	// ..to COMBINING CYRILLIC LETTER IOTIFIED BIG YUS
990
		charset[i++] = c++;
991
// 2E00..2E7F; Supplemental Punctuation
992
	c = 0x2e00;		// from RIGHT ANGLE SUBSTITUTION MARKER
993
	while (c <= 0x2e52)	// ..to TIRONIAN SIGN CAPITAL ET
994
		charset[i++] = c++;
995
// 2E80..2EFF; CJK Radicals Supplement
996
	c = 0x2e80;		// from CJK RADICAL REPEAT
997
	while (c <= 0x2e99)	// ..to CJK RADICAL RAP
998
		charset[i++] = c++;
999
	c = 0x2e9b;		// from CJK RADICAL CHOKE
1000
	while (c <= 0x2ef3)	// ..to CJK RADICAL C-SIMPLIFIED TURTLE
1001
		charset[i++] = c++;
1002
// 2F00..2FDF; Kangxi Radicals
1003
	c = 0x2f00;		// from KANGXI RADICAL ONE
1004
	while (c <= 0x2fd5)	// ..to KANGXI RADICAL FLUTE
1005
		charset[i++] = c++;
1006
// 2FF0..2FFF; Ideographic Description Characters
1007
	c = 0x2ff0;		// from IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT
1008
	while (c <= 0x2ffb)	// ..to IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
1009
		charset[i++] = c++;
1010
// 3000..303F; CJK Symbols and Punctuation
1011
	c = 0x3000;		// from IDEOGRAPHIC SPACE
1012
	while (c <= 0x303f)	// ..to IDEOGRAPHIC HALF FILL SPACE
1013
		charset[i++] = c++;
1014
// 3040..309F; Hiragana
1015
	c = 0x3041;		// from HIRAGANA LETTER SMALL A
1016
	while (c <= 0x3096)	// ..to HIRAGANA LETTER SMALL KE
1017
		charset[i++] = c++;
1018
	c = 0x3099;		// from COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK
1019
	while (c <= 0x309f)	// ..to HIRAGANA DIGRAPH YORI
1020
		charset[i++] = c++;
1021
// 30A0..30FF; Katakana
1022
	c = 0x30a0;		// from KATAKANA-HIRAGANA DOUBLE HYPHEN
1023
	while (c <= 0x30ff)	// ..to KATAKANA DIGRAPH KOTO
1024
		charset[i++] = c++;
1025
// 3100..312F; Bopomofo
1026
	c = 0x3105;		// from BOPOMOFO LETTER B
1027
	while (c <= 0x312f)	// ..to BOPOMOFO LETTER NN
1028
		charset[i++] = c++;
1029
// 3130..318F; Hangul Compatibility Jamo
1030
	c = 0x3131;		// from HANGUL LETTER KIYEOK
1031
	while (c <= 0x318e)	// ..to HANGUL LETTER ARAEAE
1032
		charset[i++] = c++;
1033
// 3190..319F; Kanbun
1034
	c = 0x3190;		// from IDEOGRAPHIC ANNOTATION LINKING MARK
1035
	while (c <= 0x319f)	// ..to IDEOGRAPHIC ANNOTATION MAN MARK
1036
		charset[i++] = c++;
1037
// 31A0..31BF; Bopomofo Extended
1038
	c = 0x31a0;		// from BOPOMOFO LETTER BU
1039
	while (c <= 0x31bf)	// ..to BOPOMOFO LETTER AH
1040
		charset[i++] = c++;
1041
// 31C0..31EF; CJK Strokes
1042
	c = 0x31c0;		// from CJK STROKE T
1043
	while (c <= 0x31e3)	// ..to CJK STROKE Q
1044
		charset[i++] = c++;
1045
// 31F0..31FF; Katakana Phonetic Extensions
1046
	c = 0x31f0;		// from KATAKANA LETTER SMALL KU
1047
	while (c <= 0x31ff)	// ..to KATAKANA LETTER SMALL RO
1048
		charset[i++] = c++;
1049
// 3200..32FF; Enclosed CJK Letters and Months
1050
	c = 0x3200;		// from PARENTHESIZED HANGUL KIYEOK
1051
	while (c <= 0x321e)	// ..to PARENTHESIZED KOREAN CHARACTER O HU
1052
		charset[i++] = c++;
1053
	c = 0x3220;		// from PARENTHESIZED IDEOGRAPH ONE
1054
	while (c <= 0x32ff)	// ..to SQUARE ERA NAME REIWA
1055
		charset[i++] = c++;
1056
// 3300..33FF; CJK Compatibility
1057
	c = 0x3300;		// from SQUARE APAATO
1058
	while (c <= 0x33ff)	// ..to SQUARE GAL
1059
		charset[i++] = c++;
1060
// 3400..4DBF; CJK Unified Ideographs Extension A
1061
	c = 0x3400;		// from <CJK Ideograph Extension A, First>
1062
	while (c <= 0x4dbf)	// ..to <CJK Ideograph Extension A, Last>
1063
		charset[i++] = c++;
1064
// 4DC0..4DFF; Yijing Hexagram Symbols
1065
	c = 0x4dc0;		// from HEXAGRAM FOR THE CREATIVE HEAVEN
1066
	while (c <= 0x4dff)	// ..to HEXAGRAM FOR BEFORE COMPLETION
1067
		charset[i++] = c++;
1068
// 4E00..9FFF; CJK Unified Ideographs
1069
	c = 0x4e00;		// from <CJK Ideograph, First>
1070
	while (c <= 0x9ffc)	// ..to <CJK Ideograph, Last>
1071
		charset[i++] = c++;
1072
// A000..A48F; Yi Syllables
1073
	c = 0xa000;		// from YI SYLLABLE IT
1074
	while (c <= 0xa48c)	// ..to YI SYLLABLE YYR
1075
		charset[i++] = c++;
1076
// A490..A4CF; Yi Radicals
1077
	c = 0xa490;		// from YI RADICAL QOT
1078
	while (c <= 0xa4c6)	// ..to YI RADICAL KE
1079
		charset[i++] = c++;
1080
// A4D0..A4FF; Lisu
1081
	c = 0xa4d0;		// from LISU LETTER BA
1082
	while (c <= 0xa4ff)	// ..to LISU PUNCTUATION FULL STOP
1083
		charset[i++] = c++;
1084
// A500..A63F; Vai
1085
	c = 0xa500;		// from VAI SYLLABLE EE
1086
	while (c <= 0xa62b)	// ..to VAI SYLLABLE NDOLE DO
1087
		charset[i++] = c++;
1088
// A640..A69F; Cyrillic Extended-B
1089
	c = 0xa640;		// from CYRILLIC CAPITAL LETTER ZEMLYA
1090
	while (c <= 0xa69f)	// ..to COMBINING CYRILLIC LETTER IOTIFIED E
1091
		charset[i++] = c++;
1092
// A6A0..A6FF; Bamum
1093
	c = 0xa6a0;		// from BAMUM LETTER A
1094
	while (c <= 0xa6f7)	// ..to BAMUM QUESTION MARK
1095
		charset[i++] = c++;
1096
// A700..A71F; Modifier Tone Letters
1097
	c = 0xa700;		// from MODIFIER LETTER CHINESE TONE YIN PING
1098
	while (c <= 0xa71f)	// ..to MODIFIER LETTER LOW INVERTED EXCLAMATION MARK
1099
		charset[i++] = c++;
1100
// A720..A7FF; Latin Extended-D
1101
	c = 0xa720;		// from MODIFIER LETTER STRESS AND HIGH TONE
1102
	while (c <= 0xa7bf)	// ..to LATIN SMALL LETTER GLOTTAL U
1103
		charset[i++] = c++;
1104
	c = 0xa7c2;		// from LATIN CAPITAL LETTER ANGLICANA W
1105
	while (c <= 0xa7ca)	// ..to LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY
1106
		charset[i++] = c++;
1107
	c = 0xa7f5;		// from LATIN CAPITAL LETTER REVERSED HALF H
1108
	while (c <= 0xa7ff)	// ..to LATIN EPIGRAPHIC LETTER ARCHAIC M
1109
		charset[i++] = c++;
1110
// A800..A82F; Syloti Nagri
1111
	c = 0xa800;		// from SYLOTI NAGRI LETTER A
1112
	while (c <= 0xa82c)	// ..to SYLOTI NAGRI SIGN ALTERNATE HASANTA
1113
		charset[i++] = c++;
1114
// A830..A83F; Common Indic Number Forms
1115
	c = 0xa830;		// from NORTH INDIC FRACTION ONE QUARTER
1116
	while (c <= 0xa839)	// ..to NORTH INDIC QUANTITY MARK
1117
		charset[i++] = c++;
1118
// A840..A87F; Phags-pa
1119
	c = 0xa840;		// from PHAGS-PA LETTER KA
1120
	while (c <= 0xa877)	// ..to PHAGS-PA MARK DOUBLE SHAD
1121
		charset[i++] = c++;
1122
// A880..A8DF; Saurashtra
1123
	c = 0xa880;		// from SAURASHTRA SIGN ANUSVARA
1124
	while (c <= 0xa8c5)	// ..to SAURASHTRA SIGN CANDRABINDU
1125
		charset[i++] = c++;
1126
	c = 0xa8ce;		// from SAURASHTRA DANDA
1127
	while (c <= 0xa8d9)	// ..to SAURASHTRA DIGIT NINE
1128
		charset[i++] = c++;
1129
// A8E0..A8FF; Devanagari Extended
1130
	c = 0xa8e0;		// from COMBINING DEVANAGARI DIGIT ZERO
1131
	while (c <= 0xa8ff)	// ..to DEVANAGARI VOWEL SIGN AY
1132
		charset[i++] = c++;
1133
// A900..A92F; Kayah Li
1134
	c = 0xa900;		// from KAYAH LI DIGIT ZERO
1135
	while (c <= 0xa92f)	// ..to KAYAH LI SIGN SHYA
1136
		charset[i++] = c++;
1137
// A930..A95F; Rejang
1138
	c = 0xa930;		// from REJANG LETTER KA
1139
	while (c <= 0xa953)	// ..to REJANG VIRAMA
1140
		charset[i++] = c++;
1141
	charset[i++] = 0xa95f;	// REJANG SECTION MARK
1142
// A960..A97F; Hangul Jamo Extended-A
1143
	c = 0xa960;		// from HANGUL CHOSEONG TIKEUT-MIEUM
1144
	while (c <= 0xa97c)	// ..to HANGUL CHOSEONG SSANGYEORINHIEUH
1145
		charset[i++] = c++;
1146
// A980..A9DF; Javanese
1147
	c = 0xa980;		// from JAVANESE SIGN PANYANGGA
1148
	while (c <= 0xa9cd)	// ..to JAVANESE TURNED PADA PISELEH
1149
		charset[i++] = c++;
1150
	c = 0xa9cf;		// from JAVANESE PANGRANGKEP
1151
	while (c <= 0xa9d9)	// ..to JAVANESE DIGIT NINE
1152
		charset[i++] = c++;
1153
	charset[i++] = 0xa9de;	// JAVANESE PADA TIRTA TUMETES
1154
	charset[i++] = 0xa9df;	// JAVANESE PADA ISEN-ISEN
1155
// A9E0..A9FF; Myanmar Extended-B
1156
	c = 0xa9e0;		// from MYANMAR LETTER SHAN GHA
1157
	while (c <= 0xa9fe)	// ..to MYANMAR LETTER TAI LAING BHA
1158
		charset[i++] = c++;
1159
// AA00..AA5F; Cham
1160
	c = 0xaa00;		// from CHAM LETTER A
1161
	while (c <= 0xaa36)	// ..to CHAM CONSONANT SIGN WA
1162
		charset[i++] = c++;
1163
	c = 0xaa40;		// from CHAM LETTER FINAL K
1164
	while (c <= 0xaa4d)	// ..to CHAM CONSONANT SIGN FINAL H
1165
		charset[i++] = c++;
1166
	c = 0xaa50;		// from CHAM DIGIT ZERO
1167
	while (c <= 0xaa59)	// ..to CHAM DIGIT NINE
1168
		charset[i++] = c++;
1169
	c = 0xaa5c;		// from CHAM PUNCTUATION SPIRAL
1170
	while (c <= 0xaa5f)	// ..to CHAM PUNCTUATION TRIPLE DANDA
1171
		charset[i++] = c++;
1172
// AA60..AA7F; Myanmar Extended-A
1173
	c = 0xaa60;		// from MYANMAR LETTER KHAMTI GA
1174
	while (c <= 0xaa7f)	// ..to MYANMAR LETTER SHWE PALAUNG SHA
1175
		charset[i++] = c++;
1176
// AA80..AADF; Tai Viet
1177
	c = 0xaa80;		// from TAI VIET LETTER LOW KO
1178
	while (c <= 0xaac2)	// ..to TAI VIET TONE MAI SONG
1179
		charset[i++] = c++;
1180
	c = 0xaadb;		// from TAI VIET SYMBOL KON
1181
	while (c <= 0xaadf)	// ..to TAI VIET SYMBOL KOI KOI
1182
		charset[i++] = c++;
1183
// AAE0..AAFF; Meetei Mayek Extensions
1184
	c = 0xaae0;		// from MEETEI MAYEK LETTER E
1185
	while (c <= 0xaaf6)	// ..to MEETEI MAYEK VIRAMA
1186
		charset[i++] = c++;
1187
// AB00..AB2F; Ethiopic Extended-A
1188
	c = 0xab01;		// from ETHIOPIC SYLLABLE TTHU
1189
	while (c <= 0xab06)	// ..to ETHIOPIC SYLLABLE TTHO
1190
		charset[i++] = c++;
1191
	c = 0xab09;		// from ETHIOPIC SYLLABLE DDHU
1192
	while (c <= 0xab0e)	// ..to ETHIOPIC SYLLABLE DDHO
1193
		charset[i++] = c++;
1194
	c = 0xab11;		// from ETHIOPIC SYLLABLE DZU
1195
	while (c <= 0xab16)	// ..to ETHIOPIC SYLLABLE DZO
1196
		charset[i++] = c++;
1197
	c = 0xab20;		// from ETHIOPIC SYLLABLE CCHHA
1198
	while (c <= 0xab26)	// ..to ETHIOPIC SYLLABLE CCHHO
1199
		charset[i++] = c++;
1200
	c = 0xab28;		// from ETHIOPIC SYLLABLE BBA
1201
	while (c <= 0xab2e)	// ..to ETHIOPIC SYLLABLE BBO
1202
		charset[i++] = c++;
1203
// AB30..AB6F; Latin Extended-E
1204
	c = 0xab30;		// from LATIN SMALL LETTER BARRED ALPHA
1205
	while (c <= 0xab6b)	// ..to MODIFIER LETTER RIGHT TACK
1206
		charset[i++] = c++;
1207
// AB70..ABBF; Cherokee Supplement
1208
	c = 0xab70;		// from CHEROKEE SMALL LETTER A
1209
	while (c <= 0xabbf)	// ..to CHEROKEE SMALL LETTER YA
1210
		charset[i++] = c++;
1211
// ABC0..ABFF; Meetei Mayek
1212
	c = 0xabc0;		// from MEETEI MAYEK LETTER KOK
1213
	while (c <= 0xabed)	// ..to MEETEI MAYEK APUN IYEK
1214
		charset[i++] = c++;
1215
	c = 0xabf0;		// from MEETEI MAYEK DIGIT ZERO
1216
	while (c <= 0xabf9)	// ..to MEETEI MAYEK DIGIT NINE
1217
		charset[i++] = c++;
1218
// AC00..D7AF; Hangul Syllables
1219
	c = 0xac00;		// from <Hangul Syllable, First>
1220
	while (c <= 0xd7a3)	// ..to <Hangul Syllable, Last>
1221
		charset[i++] = c++;
1222
// D7B0..D7FF; Hangul Jamo Extended-B
1223
	c = 0xd7b0;		// from HANGUL JUNGSEONG O-YEO
1224
	while (c <= 0xd7c6)	// ..to HANGUL JUNGSEONG ARAEA-E
1225
		charset[i++] = c++;
1226
	c = 0xd7cb;		// from HANGUL JONGSEONG NIEUN-RIEUL
1227
	while (c <= 0xd7fb)	// ..to HANGUL JONGSEONG PHIEUPH-THIEUTH
1228
		charset[i++] = c++;
1229
// D800..DB7F; High Surrogates
1230
// DB80..DBFF; High Private Use Surrogates
1231
// DC00..DFFF; Low Surrogates
1232
// E000..F8FF; Private Use Area
1233
// F900..FAFF; CJK Compatibility Ideographs
1234
	c = 0xf900;		// from CJK COMPATIBILITY IDEOGRAPH-F900
1235
	while (c <= 0xfa6d)	// ..to CJK COMPATIBILITY IDEOGRAPH-FA6D
1236
		charset[i++] = c++;
1237
	c = 0xfa70;		// from CJK COMPATIBILITY IDEOGRAPH-FA70
1238
	while (c <= 0xfad9)	// ..to CJK COMPATIBILITY IDEOGRAPH-FAD9
1239
		charset[i++] = c++;
1240
// FB00..FB4F; Alphabetic Presentation Forms
1241
	c = 0xfb00;		// from LATIN SMALL LIGATURE FF
1242
	while (c <= 0xfb06)	// ..to LATIN SMALL LIGATURE ST
1243
		charset[i++] = c++;
1244
	c = 0xfb13;		// from ARMENIAN SMALL LIGATURE MEN NOW
1245
	while (c <= 0xfb17)	// ..to ARMENIAN SMALL LIGATURE MEN XEH
1246
		charset[i++] = c++;
1247
	c = 0xfb1d;		// from HEBREW LETTER YOD WITH HIRIQ
1248
	while (c <= 0xfb36)	// ..to HEBREW LETTER ZAYIN WITH DAGESH
1249
		charset[i++] = c++;
1250
	c = 0xfb38;		// from HEBREW LETTER TET WITH DAGESH
1251
	while (c <= 0xfb3c)	// ..to HEBREW LETTER LAMED WITH DAGESH
1252
		charset[i++] = c++;
1253
	charset[i++] = 0xfb40;	// HEBREW LETTER NUN WITH DAGESH
1254
	charset[i++] = 0xfb41;	// HEBREW LETTER SAMEKH WITH DAGESH
1255
	charset[i++] = 0xfb43;	// HEBREW LETTER FINAL PE WITH DAGESH
1256
	charset[i++] = 0xfb44;	// HEBREW LETTER PE WITH DAGESH
1257
	c = 0xfb46;		// from HEBREW LETTER TSADI WITH DAGESH
1258
	while (c <= 0xfb4f)	// ..to HEBREW LIGATURE ALEF LAMED
1259
		charset[i++] = c++;
1260
// FB50..FDFF; Arabic Presentation Forms-A
1261
	c = 0xfb50;		// from ARABIC LETTER ALEF WASLA ISOLATED FORM
1262
	while (c <= 0xfbc1)	// ..to ARABIC SYMBOL SMALL TAH BELOW
1263
		charset[i++] = c++;
1264
	c = 0xfbd3;		// from ARABIC LETTER NG ISOLATED FORM
1265
	while (c <= 0xfd3f)	// ..to ORNATE RIGHT PARENTHESIS
1266
		charset[i++] = c++;
1267
	c = 0xfd50;		// from ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM
1268
	while (c <= 0xfd8f)	// ..to ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM
1269
		charset[i++] = c++;
1270
	c = 0xfd92;		// from ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM
1271
	while (c <= 0xfdc7)	// ..to ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM
1272
		charset[i++] = c++;
1273
	c = 0xfdf0;		// from ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM
1274
	while (c <= 0xfdfd)	// ..to ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM
1275
		charset[i++] = c++;
1276
// FE00..FE0F; Variation Selectors
1277
	c = 0xfe00;		// from VARIATION SELECTOR-1
1278
	while (c <= 0xfe0f)	// ..to VARIATION SELECTOR-16
1279
		charset[i++] = c++;
1280
// FE10..FE1F; Vertical Forms
1281
	c = 0xfe10;		// from PRESENTATION FORM FOR VERTICAL COMMA
1282
	while (c <= 0xfe19)	// ..to PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS
1283
		charset[i++] = c++;
1284
// FE20..FE2F; Combining Half Marks
1285
	c = 0xfe20;		// from COMBINING LIGATURE LEFT HALF
1286
	while (c <= 0xfe2f)	// ..to COMBINING CYRILLIC TITLO RIGHT HALF
1287
		charset[i++] = c++;
1288
// FE30..FE4F; CJK Compatibility Forms
1289
	c = 0xfe30;		// from PRESENTATION FORM FOR VERTICAL TWO DOT LEADER
1290
	while (c <= 0xfe4f)	// ..to WAVY LOW LINE
1291
		charset[i++] = c++;
1292
// FE50..FE6F; Small Form Variants
1293
	charset[i++] = 0xfe50;	// SMALL COMMA
1294
	charset[i++] = 0xfe52;	// SMALL FULL STOP
1295
	c = 0xfe54;		// from SMALL SEMICOLON
1296
	while (c <= 0xfe66)	// ..to SMALL EQUALS SIGN
1297
		charset[i++] = c++;
1298
	c = 0xfe68;		// from SMALL REVERSE SOLIDUS
1299
	while (c <= 0xfe6b)	// ..to SMALL COMMERCIAL AT
1300
		charset[i++] = c++;
1301
// FE70..FEFF; Arabic Presentation Forms-B
1302
	c = 0xfe70;		// from ARABIC FATHATAN ISOLATED FORM
1303
	while (c <= 0xfe74)	// ..to ARABIC KASRATAN ISOLATED FORM
1304
		charset[i++] = c++;
1305
	c = 0xfe76;		// from ARABIC FATHA ISOLATED FORM
1306
	while (c <= 0xfefc)	// ..to ARABIC LIGATURE LAM WITH ALEF FINAL FORM
1307
		charset[i++] = c++;
1308
	charset[i++] = 0xfeff;	// ZERO WIDTH NO-BREAK SPACE
1309
// FF00..FFEF; Halfwidth and Fullwidth Forms
1310
	c = 0xff01;		// from FULLWIDTH EXCLAMATION MARK
1311
	while (c <= 0xffbe)	// ..to HALFWIDTH HANGUL LETTER HIEUH
1312
		charset[i++] = c++;
1313
	c = 0xffc2;		// from HALFWIDTH HANGUL LETTER A
1314
	while (c <= 0xffc7)	// ..to HALFWIDTH HANGUL LETTER E
1315
		charset[i++] = c++;
1316
	c = 0xffca;		// from HALFWIDTH HANGUL LETTER YEO
1317
	while (c <= 0xffcf)	// ..to HALFWIDTH HANGUL LETTER OE
1318
		charset[i++] = c++;
1319
	c = 0xffd2;		// from HALFWIDTH HANGUL LETTER YO
1320
	while (c <= 0xffd7)	// ..to HALFWIDTH HANGUL LETTER YU
1321
		charset[i++] = c++;
1322
	charset[i++] = 0xffda;	// HALFWIDTH HANGUL LETTER EU
1323
	charset[i++] = 0xffdc;	// HALFWIDTH HANGUL LETTER I
1324
	c = 0xffe0;		// from FULLWIDTH CENT SIGN
1325
	while (c <= 0xffe6)	// ..to FULLWIDTH WON SIGN
1326
		charset[i++] = c++;
1327
	c = 0xffe8;		// from HALFWIDTH FORMS LIGHT VERTICAL
1328
	while (c <= 0xffee)	// ..to HALFWIDTH WHITE CIRCLE
1329
		charset[i++] = c++;
1330
// FFF0..FFFF; Specials
1331
	c = 0xfff9;		// from INTERLINEAR ANNOTATION ANCHOR
1332
	while (c <= 0xfffd)	// ..to REPLACEMENT CHARACTER
1333
		charset[i++] = c++;
1334
// 10000..1007F; Linear B Syllabary
1335
	c = 0x10000;		// from LINEAR B SYLLABLE B008 A
1336
	while (c <= 0x1000b)	// ..to LINEAR B SYLLABLE B046 JE
1337
		charset[i++] = c++;
1338
	c = 0x1000d;		// from LINEAR B SYLLABLE B036 JO
1339
	while (c <= 0x10026)	// ..to LINEAR B SYLLABLE B032 QO
1340
		charset[i++] = c++;
1341
	c = 0x10028;		// from LINEAR B SYLLABLE B060 RA
1342
	while (c <= 0x1003a)	// ..to LINEAR B SYLLABLE B042 WO
1343
		charset[i++] = c++;
1344
	charset[i++] = 0x1003c;	// LINEAR B SYLLABLE B017 ZA
1345
	charset[i++] = 0x1003d;	// LINEAR B SYLLABLE B074 ZE
1346
	c = 0x1003f;		// from LINEAR B SYLLABLE B020 ZO
1347
	while (c <= 0x1004d)	// ..to LINEAR B SYLLABLE B091 TWO
1348
		charset[i++] = c++;
1349
	c = 0x10050;		// from LINEAR B SYMBOL B018
1350
	while (c <= 0x1005d)	// ..to LINEAR B SYMBOL B089
1351
		charset[i++] = c++;
1352
// 10080..100FF; Linear B Ideograms
1353
	c = 0x10080;		// from LINEAR B IDEOGRAM B100 MAN
1354
	while (c <= 0x100fa)	// ..to LINEAR B IDEOGRAM VESSEL B305
1355
		charset[i++] = c++;
1356
// 10100..1013F; Aegean Numbers
1357
	charset[i++] = 0x10100;	// AEGEAN WORD SEPARATOR LINE
1358
	charset[i++] = 0x10102;	// AEGEAN CHECK MARK
1359
	c = 0x10107;		// from AEGEAN NUMBER ONE
1360
	while (c <= 0x10133)	// ..to AEGEAN NUMBER NINETY THOUSAND
1361
		charset[i++] = c++;
1362
	c = 0x10137;		// from AEGEAN WEIGHT BASE UNIT
1363
	while (c <= 0x1013f)	// ..to AEGEAN MEASURE THIRD SUBUNIT
1364
		charset[i++] = c++;
1365
// 10140..1018F; Ancient Greek Numbers
1366
	c = 0x10140;		// from GREEK ACROPHONIC ATTIC ONE QUARTER
1367
	while (c <= 0x1018e)	// ..to NOMISMA SIGN
1368
		charset[i++] = c++;
1369
// 10190..101CF; Ancient Symbols
1370
	c = 0x10190;		// from ROMAN SEXTANS SIGN
1371
	while (c <= 0x1019c)	// ..to ASCIA SYMBOL
1372
		charset[i++] = c++;
1373
	charset[i++] = 0x101a0;	// GREEK SYMBOL TAU RHO
1374
// 101D0..101FF; Phaistos Disc
1375
	c = 0x101d0;		// from PHAISTOS DISC SIGN PEDESTRIAN
1376
	while (c <= 0x101fd)	// ..to PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE
1377
		charset[i++] = c++;
1378
// 10280..1029F; Lycian
1379
	c = 0x10280;		// from LYCIAN LETTER A
1380
	while (c <= 0x1029c)	// ..to LYCIAN LETTER X
1381
		charset[i++] = c++;
1382
// 102A0..102DF; Carian
1383
	c = 0x102a0;		// from CARIAN LETTER A
1384
	while (c <= 0x102d0)	// ..to CARIAN LETTER UUU3
1385
		charset[i++] = c++;
1386
// 102E0..102FF; Coptic Epact Numbers
1387
	c = 0x102e0;		// from COPTIC EPACT THOUSANDS MARK
1388
	while (c <= 0x102fb)	// ..to COPTIC EPACT NUMBER NINE HUNDRED
1389
		charset[i++] = c++;
1390
// 10300..1032F; Old Italic
1391
	c = 0x10300;		// from OLD ITALIC LETTER A
1392
	while (c <= 0x10323)	// ..to OLD ITALIC NUMERAL FIFTY
1393
		charset[i++] = c++;
1394
	charset[i++] = 0x1032d;	// OLD ITALIC LETTER YE
1395
	charset[i++] = 0x1032f;	// OLD ITALIC LETTER SOUTHERN TSE
1396
// 10330..1034F; Gothic
1397
	c = 0x10330;		// from GOTHIC LETTER AHSA
1398
	while (c <= 0x1034a)	// ..to GOTHIC LETTER NINE HUNDRED
1399
		charset[i++] = c++;
1400
// 10350..1037F; Old Permic
1401
	c = 0x10350;		// from OLD PERMIC LETTER AN
1402
	while (c <= 0x1037a)	// ..to COMBINING OLD PERMIC LETTER SII
1403
		charset[i++] = c++;
1404
// 10380..1039F; Ugaritic
1405
	c = 0x10380;		// from UGARITIC LETTER ALPA
1406
	while (c <= 0x1039d)	// ..to UGARITIC LETTER SSU
1407
		charset[i++] = c++;
1408
	charset[i++] = 0x1039f;	// UGARITIC WORD DIVIDER
1409
// 103A0..103DF; Old Persian
1410
	c = 0x103a0;		// from OLD PERSIAN SIGN A
1411
	while (c <= 0x103c3)	// ..to OLD PERSIAN SIGN HA
1412
		charset[i++] = c++;
1413
	c = 0x103c8;		// from OLD PERSIAN SIGN AURAMAZDAA
1414
	while (c <= 0x103d5)	// ..to OLD PERSIAN NUMBER HUNDRED
1415
		charset[i++] = c++;
1416
// 10400..1044F; Deseret
1417
	c = 0x10400;		// from DESERET CAPITAL LETTER LONG I
1418
	while (c <= 0x1044f)	// ..to DESERET SMALL LETTER EW
1419
		charset[i++] = c++;
1420
// 10450..1047F; Shavian
1421
	c = 0x10450;		// from SHAVIAN LETTER PEEP
1422
	while (c <= 0x1047f)	// ..to SHAVIAN LETTER YEW
1423
		charset[i++] = c++;
1424
// 10480..104AF; Osmanya
1425
	c = 0x10480;		// from OSMANYA LETTER ALEF
1426
	while (c <= 0x1049d)	// ..to OSMANYA LETTER OO
1427
		charset[i++] = c++;
1428
	c = 0x104a0;		// from OSMANYA DIGIT ZERO
1429
	while (c <= 0x104a9)	// ..to OSMANYA DIGIT NINE
1430
		charset[i++] = c++;
1431
// 104B0..104FF; Osage
1432
	c = 0x104b0;		// from OSAGE CAPITAL LETTER A
1433
	while (c <= 0x104d3)	// ..to OSAGE CAPITAL LETTER ZHA
1434
		charset[i++] = c++;
1435
	c = 0x104d8;		// from OSAGE SMALL LETTER A
1436
	while (c <= 0x104fb)	// ..to OSAGE SMALL LETTER ZHA
1437
		charset[i++] = c++;
1438
// 10500..1052F; Elbasan
1439
	c = 0x10500;		// from ELBASAN LETTER A
1440
	while (c <= 0x10527)	// ..to ELBASAN LETTER KHE
1441
		charset[i++] = c++;
1442
// 10530..1056F; Caucasian Albanian
1443
	c = 0x10530;		// from CAUCASIAN ALBANIAN LETTER ALT
1444
	while (c <= 0x10563)	// ..to CAUCASIAN ALBANIAN LETTER KIW
1445
		charset[i++] = c++;
1446
	charset[i++] = 0x1056f;	// CAUCASIAN ALBANIAN CITATION MARK
1447
// 10600..1077F; Linear A
1448
	c = 0x10600;		// from LINEAR A SIGN AB001
1449
	while (c <= 0x10736)	// ..to LINEAR A SIGN A664
1450
		charset[i++] = c++;
1451
	c = 0x10740;		// from LINEAR A SIGN A701 A
1452
	while (c <= 0x10755)	// ..to LINEAR A SIGN A732 JE
1453
		charset[i++] = c++;
1454
	c = 0x10760;		// from LINEAR A SIGN A800
1455
	while (c <= 0x10767)	// ..to LINEAR A SIGN A807
1456
		charset[i++] = c++;
1457
// 10800..1083F; Cypriot Syllabary
1458
	c = 0x10800;		// from CYPRIOT SYLLABLE A
1459
	while (c <= 0x10805)	// ..to CYPRIOT SYLLABLE JA
1460
		charset[i++] = c++;
1461
	c = 0x1080a;		// from CYPRIOT SYLLABLE KA
1462
	while (c <= 0x10835)	// ..to CYPRIOT SYLLABLE WO
1463
		charset[i++] = c++;
1464
	charset[i++] = 0x10837;	// CYPRIOT SYLLABLE XA
1465
	charset[i++] = 0x10838;	// CYPRIOT SYLLABLE XE
1466
	c = 0x1083c;		// from CYPRIOT SYLLABLE ZA
1467
	while (c <= 0x1083f)	// ..to CYPRIOT SYLLABLE ZO
1468
		charset[i++] = c++;
1469
// 10840..1085F; Imperial Aramaic
1470
	c = 0x10840;		// from IMPERIAL ARAMAIC LETTER ALEPH
1471
	while (c <= 0x10855)	// ..to IMPERIAL ARAMAIC LETTER TAW
1472
		charset[i++] = c++;
1473
	c = 0x10857;		// from IMPERIAL ARAMAIC SECTION SIGN
1474
	while (c <= 0x1085f)	// ..to IMPERIAL ARAMAIC NUMBER TEN THOUSAND
1475
		charset[i++] = c++;
1476
// 10860..1087F; Palmyrene
1477
	c = 0x10860;		// from PALMYRENE LETTER ALEPH
1478
	while (c <= 0x1087f)	// ..to PALMYRENE NUMBER TWENTY
1479
		charset[i++] = c++;
1480
// 10880..108AF; Nabataean
1481
	c = 0x10880;		// from NABATAEAN LETTER FINAL ALEPH
1482
	while (c <= 0x1089e)	// ..to NABATAEAN LETTER TAW
1483
		charset[i++] = c++;
1484
	c = 0x108a7;		// from NABATAEAN NUMBER ONE
1485
	while (c <= 0x108af)	// ..to NABATAEAN NUMBER ONE HUNDRED
1486
		charset[i++] = c++;
1487
// 108E0..108FF; Hatran
1488
	c = 0x108e0;		// from HATRAN LETTER ALEPH
1489
	while (c <= 0x108f2)	// ..to HATRAN LETTER QOPH
1490
		charset[i++] = c++;
1491
	charset[i++] = 0x108f4;	// HATRAN LETTER SHIN
1492
	charset[i++] = 0x108f5;	// HATRAN LETTER TAW
1493
	c = 0x108fb;		// from HATRAN NUMBER ONE
1494
	while (c <= 0x108ff)	// ..to HATRAN NUMBER ONE HUNDRED
1495
		charset[i++] = c++;
1496
// 10900..1091F; Phoenician
1497
	c = 0x10900;		// from PHOENICIAN LETTER ALF
1498
	while (c <= 0x1091b)	// ..to PHOENICIAN NUMBER THREE
1499
		charset[i++] = c++;
1500
	charset[i++] = 0x1091f;	// PHOENICIAN WORD SEPARATOR
1501
// 10920..1093F; Lydian
1502
	c = 0x10920;		// from LYDIAN LETTER A
1503
	while (c <= 0x10939)	// ..to LYDIAN LETTER C
1504
		charset[i++] = c++;
1505
	charset[i++] = 0x1093f;	// LYDIAN TRIANGULAR MARK
1506
// 10980..1099F; Meroitic Hieroglyphs
1507
	c = 0x10980;		// from MEROITIC HIEROGLYPHIC LETTER A
1508
	while (c <= 0x1099f)	// ..to MEROITIC HIEROGLYPHIC SYMBOL VIDJ-2
1509
		charset[i++] = c++;
1510
// 109A0..109FF; Meroitic Cursive
1511
	c = 0x109a0;		// from MEROITIC CURSIVE LETTER A
1512
	while (c <= 0x109b7)	// ..to MEROITIC CURSIVE LETTER DA
1513
		charset[i++] = c++;
1514
	c = 0x109bc;		// from MEROITIC CURSIVE FRACTION ELEVEN TWELFTHS
1515
	while (c <= 0x109cf)	// ..to MEROITIC CURSIVE NUMBER SEVENTY
1516
		charset[i++] = c++;
1517
	c = 0x109d2;		// from MEROITIC CURSIVE NUMBER ONE HUNDRED
1518
	while (c <= 0x109ff)	// ..to MEROITIC CURSIVE FRACTION TEN TWELFTHS
1519
		charset[i++] = c++;
1520
// 10A00..10A5F; Kharoshthi
1521
	c = 0x10a00;		// from KHAROSHTHI LETTER A
1522
	while (c <= 0x10a03)	// ..to KHAROSHTHI VOWEL SIGN VOCALIC R
1523
		charset[i++] = c++;
1524
	charset[i++] = 0x10a05;	// KHAROSHTHI VOWEL SIGN E
1525
	charset[i++] = 0x10a06;	// KHAROSHTHI VOWEL SIGN O
1526
	c = 0x10a0c;		// from KHAROSHTHI VOWEL LENGTH MARK
1527
	while (c <= 0x10a13)	// ..to KHAROSHTHI LETTER GHA
1528
		charset[i++] = c++;
1529
	charset[i++] = 0x10a15;	// KHAROSHTHI LETTER CA
1530
	charset[i++] = 0x10a17;	// KHAROSHTHI LETTER JA
1531
	c = 0x10a19;		// from KHAROSHTHI LETTER NYA
1532
	while (c <= 0x10a35)	// ..to KHAROSHTHI LETTER VHA
1533
		charset[i++] = c++;
1534
	charset[i++] = 0x10a38;	// KHAROSHTHI SIGN BAR ABOVE
1535
	charset[i++] = 0x10a3a;	// KHAROSHTHI SIGN DOT BELOW
1536
	c = 0x10a3f;		// from KHAROSHTHI VIRAMA
1537
	while (c <= 0x10a48)	// ..to KHAROSHTHI FRACTION ONE HALF
1538
		charset[i++] = c++;
1539
	c = 0x10a50;		// from KHAROSHTHI PUNCTUATION DOT
1540
	while (c <= 0x10a58)	// ..to KHAROSHTHI PUNCTUATION LINES
1541
		charset[i++] = c++;
1542
// 10A60..10A7F; Old South Arabian
1543
	c = 0x10a60;		// from OLD SOUTH ARABIAN LETTER HE
1544
	while (c <= 0x10a7f)	// ..to OLD SOUTH ARABIAN NUMERIC INDICATOR
1545
		charset[i++] = c++;
1546
// 10A80..10A9F; Old North Arabian
1547
	c = 0x10a80;		// from OLD NORTH ARABIAN LETTER HEH
1548
	while (c <= 0x10a9f)	// ..to OLD NORTH ARABIAN NUMBER TWENTY
1549
		charset[i++] = c++;
1550
// 10AC0..10AFF; Manichaean
1551
	c = 0x10ac0;		// from MANICHAEAN LETTER ALEPH
1552
	while (c <= 0x10ae6)	// ..to MANICHAEAN ABBREVIATION MARK BELOW
1553
		charset[i++] = c++;
1554
	c = 0x10aeb;		// from MANICHAEAN NUMBER ONE
1555
	while (c <= 0x10af6)	// ..to MANICHAEAN PUNCTUATION LINE FILLER
1556
		charset[i++] = c++;
1557
// 10B00..10B3F; Avestan
1558
	c = 0x10b00;		// from AVESTAN LETTER A
1559
	while (c <= 0x10b35)	// ..to AVESTAN LETTER HE
1560
		charset[i++] = c++;
1561
	c = 0x10b39;		// from AVESTAN ABBREVIATION MARK
1562
	while (c <= 0x10b3f)	// ..to LARGE ONE RING OVER TWO RINGS PUNCTUATION
1563
		charset[i++] = c++;
1564
// 10B40..10B5F; Inscriptional Parthian
1565
	c = 0x10b40;		// from INSCRIPTIONAL PARTHIAN LETTER ALEPH
1566
	while (c <= 0x10b55)	// ..to INSCRIPTIONAL PARTHIAN LETTER TAW
1567
		charset[i++] = c++;
1568
	c = 0x10b58;		// from INSCRIPTIONAL PARTHIAN NUMBER ONE
1569
	while (c <= 0x10b5f)	// ..to INSCRIPTIONAL PARTHIAN NUMBER ONE THOUSAND
1570
		charset[i++] = c++;
1571
// 10B60..10B7F; Inscriptional Pahlavi
1572
	c = 0x10b60;		// from INSCRIPTIONAL PAHLAVI LETTER ALEPH
1573
	while (c <= 0x10b72)	// ..to INSCRIPTIONAL PAHLAVI LETTER TAW
1574
		charset[i++] = c++;
1575
	c = 0x10b78;		// from INSCRIPTIONAL PAHLAVI NUMBER ONE
1576
	while (c <= 0x10b7f)	// ..to INSCRIPTIONAL PAHLAVI NUMBER ONE THOUSAND
1577
		charset[i++] = c++;
1578
// 10B80..10BAF; Psalter Pahlavi
1579
	c = 0x10b80;		// from PSALTER PAHLAVI LETTER ALEPH
1580
	while (c <= 0x10b91)	// ..to PSALTER PAHLAVI LETTER TAW
1581
		charset[i++] = c++;
1582
	c = 0x10b99;		// from PSALTER PAHLAVI SECTION MARK
1583
	while (c <= 0x10b9c)	// ..to PSALTER PAHLAVI FOUR DOTS WITH DOT
1584
		charset[i++] = c++;
1585
	c = 0x10ba9;		// from PSALTER PAHLAVI NUMBER ONE
1586
	while (c <= 0x10baf)	// ..to PSALTER PAHLAVI NUMBER ONE HUNDRED
1587
		charset[i++] = c++;
1588
// 10C00..10C4F; Old Turkic
1589
	c = 0x10c00;		// from OLD TURKIC LETTER ORKHON A
1590
	while (c <= 0x10c48)	// ..to OLD TURKIC LETTER ORKHON BASH
1591
		charset[i++] = c++;
1592
// 10C80..10CFF; Old Hungarian
1593
	c = 0x10c80;		// from OLD HUNGARIAN CAPITAL LETTER A
1594
	while (c <= 0x10cb2)	// ..to OLD HUNGARIAN CAPITAL LETTER US
1595
		charset[i++] = c++;
1596
	c = 0x10cc0;		// from OLD HUNGARIAN SMALL LETTER A
1597
	while (c <= 0x10cf2)	// ..to OLD HUNGARIAN SMALL LETTER US
1598
		charset[i++] = c++;
1599
	c = 0x10cfa;		// from OLD HUNGARIAN NUMBER ONE
1600
	while (c <= 0x10cff)	// ..to OLD HUNGARIAN NUMBER ONE THOUSAND
1601
		charset[i++] = c++;
1602
// 10D00..10D3F; Hanifi Rohingya
1603
	c = 0x10d00;		// from HANIFI ROHINGYA LETTER A
1604
	while (c <= 0x10d27)	// ..to HANIFI ROHINGYA SIGN TASSI
1605
		charset[i++] = c++;
1606
	c = 0x10d30;		// from HANIFI ROHINGYA DIGIT ZERO
1607
	while (c <= 0x10d39)	// ..to HANIFI ROHINGYA DIGIT NINE
1608
		charset[i++] = c++;
1609
// 10E60..10E7F; Rumi Numeral Symbols
1610
	c = 0x10e60;		// from RUMI DIGIT ONE
1611
	while (c <= 0x10e7e)	// ..to RUMI FRACTION TWO THIRDS
1612
		charset[i++] = c++;
1613
// 10E80..10EBF; Yezidi
1614
	c = 0x10e80;		// from YEZIDI LETTER ELIF
1615
	while (c <= 0x10ea9)	// ..to YEZIDI LETTER ET
1616
		charset[i++] = c++;
1617
	charset[i++] = 0x10eab;	// YEZIDI COMBINING HAMZA MARK
1618
	charset[i++] = 0x10ead;	// YEZIDI HYPHENATION MARK
1619
	charset[i++] = 0x10eb0;	// YEZIDI LETTER LAM WITH DOT ABOVE
1620
	charset[i++] = 0x10eb1;	// YEZIDI LETTER YOT WITH CIRCUMFLEX ABOVE
1621
// 10F00..10F2F; Old Sogdian
1622
	c = 0x10f00;		// from OLD SOGDIAN LETTER ALEPH
1623
	while (c <= 0x10f27)	// ..to OLD SOGDIAN LIGATURE AYIN-DALETH
1624
		charset[i++] = c++;
1625
// 10F30..10F6F; Sogdian
1626
	c = 0x10f30;		// from SOGDIAN LETTER ALEPH
1627
	while (c <= 0x10f59)	// ..to SOGDIAN PUNCTUATION HALF CIRCLE WITH DOT
1628
		charset[i++] = c++;
1629
// 10FB0..10FDF; Chorasmian
1630
	c = 0x10fb0;		// from CHORASMIAN LETTER ALEPH
1631
	while (c <= 0x10fcb)	// ..to CHORASMIAN NUMBER ONE HUNDRED
1632
		charset[i++] = c++;
1633
// 10FE0..10FFF; Elymaic
1634
	c = 0x10fe0;		// from ELYMAIC LETTER ALEPH
1635
	while (c <= 0x10ff6)	// ..to ELYMAIC LIGATURE ZAYIN-YODH
1636
		charset[i++] = c++;
1637
// 11000..1107F; Brahmi
1638
	c = 0x11000;		// from BRAHMI SIGN CANDRABINDU
1639
	while (c <= 0x1104d)	// ..to BRAHMI PUNCTUATION LOTUS
1640
		charset[i++] = c++;
1641
	c = 0x11052;		// from BRAHMI NUMBER ONE
1642
	while (c <= 0x1106f)	// ..to BRAHMI DIGIT NINE
1643
		charset[i++] = c++;
1644
	charset[i++] = 0x1107f;	// BRAHMI NUMBER JOINER
1645
// 11080..110CF; Kaithi
1646
	c = 0x11080;		// from KAITHI SIGN CANDRABINDU
1647
	while (c <= 0x110c1)	// ..to KAITHI DOUBLE DANDA
1648
		charset[i++] = c++;
1649
	charset[i++] = 0x110cd;	// KAITHI NUMBER SIGN ABOVE
1650
// 110D0..110FF; Sora Sompeng
1651
	c = 0x110d0;		// from SORA SOMPENG LETTER SAH
1652
	while (c <= 0x110e8)	// ..to SORA SOMPENG LETTER MAE
1653
		charset[i++] = c++;
1654
	c = 0x110f0;		// from SORA SOMPENG DIGIT ZERO
1655
	while (c <= 0x110f9)	// ..to SORA SOMPENG DIGIT NINE
1656
		charset[i++] = c++;
1657
// 11100..1114F; Chakma
1658
	c = 0x11100;		// from CHAKMA SIGN CANDRABINDU
1659
	while (c <= 0x11134)	// ..to CHAKMA MAAYYAA
1660
		charset[i++] = c++;
1661
	c = 0x11136;		// from CHAKMA DIGIT ZERO
1662
	while (c <= 0x11147)	// ..to CHAKMA LETTER VAA
1663
		charset[i++] = c++;
1664
// 11150..1117F; Mahajani
1665
	c = 0x11150;		// from MAHAJANI LETTER A
1666
	while (c <= 0x11176)	// ..to MAHAJANI LIGATURE SHRI
1667
		charset[i++] = c++;
1668
// 11180..111DF; Sharada
1669
	c = 0x11180;		// from SHARADA SIGN CANDRABINDU
1670
	while (c <= 0x111df)	// ..to SHARADA SECTION MARK-2
1671
		charset[i++] = c++;
1672
// 111E0..111FF; Sinhala Archaic Numbers
1673
	c = 0x111e1;		// from SINHALA ARCHAIC DIGIT ONE
1674
	while (c <= 0x111f4)	// ..to SINHALA ARCHAIC NUMBER ONE THOUSAND
1675
		charset[i++] = c++;
1676
// 11200..1124F; Khojki
1677
	c = 0x11200;		// from KHOJKI LETTER A
1678
	while (c <= 0x11211)	// ..to KHOJKI LETTER JJA
1679
		charset[i++] = c++;
1680
	c = 0x11213;		// from KHOJKI LETTER NYA
1681
	while (c <= 0x1123e)	// ..to KHOJKI SIGN SUKUN
1682
		charset[i++] = c++;
1683
// 11280..112AF; Multani
1684
	c = 0x11280;		// from MULTANI LETTER A
1685
	while (c <= 0x11286)	// ..to MULTANI LETTER GA
1686
		charset[i++] = c++;
1687
	c = 0x1128a;		// from MULTANI LETTER CA
1688
	while (c <= 0x1128d)	// ..to MULTANI LETTER JJA
1689
		charset[i++] = c++;
1690
	c = 0x1128f;		// from MULTANI LETTER NYA
1691
	while (c <= 0x1129d)	// ..to MULTANI LETTER BA
1692
		charset[i++] = c++;
1693
	c = 0x1129f;		// from MULTANI LETTER BHA
1694
	while (c <= 0x112a9)	// ..to MULTANI SECTION MARK
1695
		charset[i++] = c++;
1696
// 112B0..112FF; Khudawadi
1697
	c = 0x112b0;		// from KHUDAWADI LETTER A
1698
	while (c <= 0x112ea)	// ..to KHUDAWADI SIGN VIRAMA
1699
		charset[i++] = c++;
1700
	c = 0x112f0;		// from KHUDAWADI DIGIT ZERO
1701
	while (c <= 0x112f9)	// ..to KHUDAWADI DIGIT NINE
1702
		charset[i++] = c++;
1703
// 11300..1137F; Grantha
1704
	c = 0x11300;		// from GRANTHA SIGN COMBINING ANUSVARA ABOVE
1705
	while (c <= 0x11303)	// ..to GRANTHA SIGN VISARGA
1706
		charset[i++] = c++;
1707
	c = 0x11305;		// from GRANTHA LETTER A
1708
	while (c <= 0x1130c)	// ..to GRANTHA LETTER VOCALIC L
1709
		charset[i++] = c++;
1710
	charset[i++] = 0x1130f;	// GRANTHA LETTER EE
1711
	charset[i++] = 0x11310;	// GRANTHA LETTER AI
1712
	c = 0x11313;		// from GRANTHA LETTER OO
1713
	while (c <= 0x11328)	// ..to GRANTHA LETTER NA
1714
		charset[i++] = c++;
1715
	c = 0x1132a;		// from GRANTHA LETTER PA
1716
	while (c <= 0x11330)	// ..to GRANTHA LETTER RA
1717
		charset[i++] = c++;
1718
	charset[i++] = 0x11332;	// GRANTHA LETTER LA
1719
	charset[i++] = 0x11333;	// GRANTHA LETTER LLA
1720
	c = 0x11335;		// from GRANTHA LETTER VA
1721
	while (c <= 0x11339)	// ..to GRANTHA LETTER HA
1722
		charset[i++] = c++;
1723
	c = 0x1133b;		// from COMBINING BINDU BELOW
1724
	while (c <= 0x11344)	// ..to GRANTHA VOWEL SIGN VOCALIC RR
1725
		charset[i++] = c++;
1726
	charset[i++] = 0x11347;	// GRANTHA VOWEL SIGN EE
1727
	charset[i++] = 0x11348;	// GRANTHA VOWEL SIGN AI
1728
	charset[i++] = 0x1134b;	// GRANTHA VOWEL SIGN OO
1729
	charset[i++] = 0x1134d;	// GRANTHA SIGN VIRAMA
1730
	c = 0x1135d;		// from GRANTHA SIGN PLUTA
1731
	while (c <= 0x11363)	// ..to GRANTHA VOWEL SIGN VOCALIC LL
1732
		charset[i++] = c++;
1733
	c = 0x11366;		// from COMBINING GRANTHA DIGIT ZERO
1734
	while (c <= 0x1136c)	// ..to COMBINING GRANTHA DIGIT SIX
1735
		charset[i++] = c++;
1736
	c = 0x11370;		// from COMBINING GRANTHA LETTER A
1737
	while (c <= 0x11374)	// ..to COMBINING GRANTHA LETTER PA
1738
		charset[i++] = c++;
1739
// 11400..1147F; Newa
1740
	c = 0x11400;		// from NEWA LETTER A
1741
	while (c <= 0x1145b)	// ..to NEWA PLACEHOLDER MARK
1742
		charset[i++] = c++;
1743
	c = 0x1145d;		// from NEWA INSERTION SIGN
1744
	while (c <= 0x11461)	// ..to NEWA SIGN UPADHMANIYA
1745
		charset[i++] = c++;
1746
// 11480..114DF; Tirhuta
1747
	c = 0x11480;		// from TIRHUTA ANJI
1748
	while (c <= 0x114c7)	// ..to TIRHUTA OM
1749
		charset[i++] = c++;
1750
	c = 0x114d0;		// from TIRHUTA DIGIT ZERO
1751
	while (c <= 0x114d9)	// ..to TIRHUTA DIGIT NINE
1752
		charset[i++] = c++;
1753
// 11580..115FF; Siddham
1754
	c = 0x11580;		// from SIDDHAM LETTER A
1755
	while (c <= 0x115b5)	// ..to SIDDHAM VOWEL SIGN VOCALIC RR
1756
		charset[i++] = c++;
1757
	c = 0x115b8;		// from SIDDHAM VOWEL SIGN E
1758
	while (c <= 0x115dd)	// ..to SIDDHAM VOWEL SIGN ALTERNATE UU
1759
		charset[i++] = c++;
1760
// 11600..1165F; Modi
1761
	c = 0x11600;		// from MODI LETTER A
1762
	while (c <= 0x11644)	// ..to MODI SIGN HUVA
1763
		charset[i++] = c++;
1764
	c = 0x11650;		// from MODI DIGIT ZERO
1765
	while (c <= 0x11659)	// ..to MODI DIGIT NINE
1766
		charset[i++] = c++;
1767
// 11660..1167F; Mongolian Supplement
1768
	c = 0x11660;		// from MONGOLIAN BIRGA WITH ORNAMENT
1769
	while (c <= 0x1166c)	// ..to MONGOLIAN TURNED SWIRL BIRGA WITH DOUBLE ORNAMENT
1770
		charset[i++] = c++;
1771
// 11680..116CF; Takri
1772
	c = 0x11680;		// from TAKRI LETTER A
1773
	while (c <= 0x116b8)	// ..to TAKRI LETTER ARCHAIC KHA
1774
		charset[i++] = c++;
1775
	c = 0x116c0;		// from TAKRI DIGIT ZERO
1776
	while (c <= 0x116c9)	// ..to TAKRI DIGIT NINE
1777
		charset[i++] = c++;
1778
// 11700..1173F; Ahom
1779
	c = 0x11700;		// from AHOM LETTER KA
1780
	while (c <= 0x1171a)	// ..to AHOM LETTER ALTERNATE BA
1781
		charset[i++] = c++;
1782
	c = 0x1171d;		// from AHOM CONSONANT SIGN MEDIAL LA
1783
	while (c <= 0x1172b)	// ..to AHOM SIGN KILLER
1784
		charset[i++] = c++;
1785
	c = 0x11730;		// from AHOM DIGIT ZERO
1786
	while (c <= 0x1173f)	// ..to AHOM SYMBOL VI
1787
		charset[i++] = c++;
1788
// 11800..1184F; Dogra
1789
	c = 0x11800;		// from DOGRA LETTER A
1790
	while (c <= 0x1183b)	// ..to DOGRA ABBREVIATION SIGN
1791
		charset[i++] = c++;
1792
// 118A0..118FF; Warang Citi
1793
	c = 0x118a0;		// from WARANG CITI CAPITAL LETTER NGAA
1794
	while (c <= 0x118f2)	// ..to WARANG CITI NUMBER NINETY
1795
		charset[i++] = c++;
1796
	charset[i++] = 0x118ff;	// WARANG CITI OM
1797
// 11900..1195F; Dives Akuru
1798
	c = 0x11900;		// from DIVES AKURU LETTER A
1799
	while (c <= 0x11906)	// ..to DIVES AKURU LETTER E
1800
		charset[i++] = c++;
1801
	c = 0x1190c;		// from DIVES AKURU LETTER KA
1802
	while (c <= 0x11913)	// ..to DIVES AKURU LETTER JA
1803
		charset[i++] = c++;
1804
	charset[i++] = 0x11915;	// DIVES AKURU LETTER NYA
1805
	charset[i++] = 0x11916;	// DIVES AKURU LETTER TTA
1806
	c = 0x11918;		// from DIVES AKURU LETTER DDA
1807
	while (c <= 0x11935)	// ..to DIVES AKURU VOWEL SIGN E
1808
		charset[i++] = c++;
1809
	charset[i++] = 0x11937;	// DIVES AKURU VOWEL SIGN AI
1810
	charset[i++] = 0x11938;	// DIVES AKURU VOWEL SIGN O
1811
	c = 0x1193b;		// from DIVES AKURU SIGN ANUSVARA
1812
	while (c <= 0x11946)	// ..to DIVES AKURU END OF TEXT MARK
1813
		charset[i++] = c++;
1814
	c = 0x11950;		// from DIVES AKURU DIGIT ZERO
1815
	while (c <= 0x11959)	// ..to DIVES AKURU DIGIT NINE
1816
		charset[i++] = c++;
1817
// 119A0..119FF; Nandinagari
1818
	c = 0x119a0;		// from NANDINAGARI LETTER A
1819
	while (c <= 0x119a7)	// ..to NANDINAGARI LETTER VOCALIC RR
1820
		charset[i++] = c++;
1821
	c = 0x119aa;		// from NANDINAGARI LETTER E
1822
	while (c <= 0x119d7)	// ..to NANDINAGARI VOWEL SIGN VOCALIC RR
1823
		charset[i++] = c++;
1824
	c = 0x119da;		// from NANDINAGARI VOWEL SIGN E
1825
	while (c <= 0x119e4)	// ..to NANDINAGARI VOWEL SIGN PRISHTHAMATRA E
1826
		charset[i++] = c++;
1827
// 11A00..11A4F; Zanabazar Square
1828
	c = 0x11a00;		// from ZANABAZAR SQUARE LETTER A
1829
	while (c <= 0x11a47)	// ..to ZANABAZAR SQUARE SUBJOINER
1830
		charset[i++] = c++;
1831
// 11A50..11AAF; Soyombo
1832
	c = 0x11a50;		// from SOYOMBO LETTER A
1833
	while (c <= 0x11aa2)	// ..to SOYOMBO TERMINAL MARK-2
1834
		charset[i++] = c++;
1835
// 11AC0..11AFF; Pau Cin Hau
1836
	c = 0x11ac0;		// from PAU CIN HAU LETTER PA
1837
	while (c <= 0x11af8)	// ..to PAU CIN HAU GLOTTAL STOP FINAL
1838
		charset[i++] = c++;
1839
// 11C00..11C6F; Bhaiksuki
1840
	c = 0x11c00;		// from BHAIKSUKI LETTER A
1841
	while (c <= 0x11c08)	// ..to BHAIKSUKI LETTER VOCALIC L
1842
		charset[i++] = c++;
1843
	c = 0x11c0a;		// from BHAIKSUKI LETTER E
1844
	while (c <= 0x11c36)	// ..to BHAIKSUKI VOWEL SIGN VOCALIC L
1845
		charset[i++] = c++;
1846
	c = 0x11c38;		// from BHAIKSUKI VOWEL SIGN E
1847
	while (c <= 0x11c45)	// ..to BHAIKSUKI GAP FILLER-2
1848
		charset[i++] = c++;
1849
	c = 0x11c50;		// from BHAIKSUKI DIGIT ZERO
1850
	while (c <= 0x11c6c)	// ..to BHAIKSUKI HUNDREDS UNIT MARK
1851
		charset[i++] = c++;
1852
// 11C70..11CBF; Marchen
1853
	c = 0x11c70;		// from MARCHEN HEAD MARK
1854
	while (c <= 0x11c8f)	// ..to MARCHEN LETTER A
1855
		charset[i++] = c++;
1856
	c = 0x11c92;		// from MARCHEN SUBJOINED LETTER KA
1857
	while (c <= 0x11ca7)	// ..to MARCHEN SUBJOINED LETTER ZA
1858
		charset[i++] = c++;
1859
	c = 0x11ca9;		// from MARCHEN SUBJOINED LETTER YA
1860
	while (c <= 0x11cb6)	// ..to MARCHEN SIGN CANDRABINDU
1861
		charset[i++] = c++;
1862
// 11D00..11D5F; Masaram Gondi
1863
	c = 0x11d00;		// from MASARAM GONDI LETTER A
1864
	while (c <= 0x11d06)	// ..to MASARAM GONDI LETTER E
1865
		charset[i++] = c++;
1866
	charset[i++] = 0x11d08;	// MASARAM GONDI LETTER AI
1867
	charset[i++] = 0x11d09;	// MASARAM GONDI LETTER O
1868
	c = 0x11d0b;		// from MASARAM GONDI LETTER AU
1869
	while (c <= 0x11d36)	// ..to MASARAM GONDI VOWEL SIGN VOCALIC R
1870
		charset[i++] = c++;
1871
	charset[i++] = 0x11d3c;	// MASARAM GONDI VOWEL SIGN AI
1872
	charset[i++] = 0x11d3d;	// MASARAM GONDI VOWEL SIGN O
1873
	c = 0x11d3f;		// from MASARAM GONDI VOWEL SIGN AU
1874
	while (c <= 0x11d47)	// ..to MASARAM GONDI RA-KARA
1875
		charset[i++] = c++;
1876
	c = 0x11d50;		// from MASARAM GONDI DIGIT ZERO
1877
	while (c <= 0x11d59)	// ..to MASARAM GONDI DIGIT NINE
1878
		charset[i++] = c++;
1879
// 11D60..11DAF; Gunjala Gondi
1880
	c = 0x11d60;		// from GUNJALA GONDI LETTER A
1881
	while (c <= 0x11d65)	// ..to GUNJALA GONDI LETTER UU
1882
		charset[i++] = c++;
1883
	charset[i++] = 0x11d67;	// GUNJALA GONDI LETTER EE
1884
	charset[i++] = 0x11d68;	// GUNJALA GONDI LETTER AI
1885
	c = 0x11d6a;		// from GUNJALA GONDI LETTER OO
1886
	while (c <= 0x11d8e)	// ..to GUNJALA GONDI VOWEL SIGN UU
1887
		charset[i++] = c++;
1888
	charset[i++] = 0x11d90;	// GUNJALA GONDI VOWEL SIGN EE
1889
	charset[i++] = 0x11d91;	// GUNJALA GONDI VOWEL SIGN AI
1890
	c = 0x11d93;		// from GUNJALA GONDI VOWEL SIGN OO
1891
	while (c <= 0x11d98)	// ..to GUNJALA GONDI OM
1892
		charset[i++] = c++;
1893
	c = 0x11da0;		// from GUNJALA GONDI DIGIT ZERO
1894
	while (c <= 0x11da9)	// ..to GUNJALA GONDI DIGIT NINE
1895
		charset[i++] = c++;
1896
// 11EE0..11EFF; Makasar
1897
	c = 0x11ee0;		// from MAKASAR LETTER KA
1898
	while (c <= 0x11ef8)	// ..to MAKASAR END OF SECTION
1899
		charset[i++] = c++;
1900
// 11FB0..11FBF; Lisu Supplement
1901
	charset[i++] = 0x11fb0;	// LISU LETTER YHA
1902
// 11FC0..11FFF; Tamil Supplement
1903
	c = 0x11fc0;		// from TAMIL FRACTION ONE THREE-HUNDRED-AND-TWENTIETH
1904
	while (c <= 0x11ff1)	// ..to TAMIL SIGN VAKAIYARAA
1905
		charset[i++] = c++;
1906
	charset[i++] = 0x11fff;	// TAMIL PUNCTUATION END OF TEXT
1907
// 12000..123FF; Cuneiform
1908
	c = 0x12000;		// from CUNEIFORM SIGN A
1909
	while (c <= 0x12399)	// ..to CUNEIFORM SIGN U U
1910
		charset[i++] = c++;
1911
// 12400..1247F; Cuneiform Numbers and Punctuation
1912
	c = 0x12400;		// from CUNEIFORM NUMERIC SIGN TWO ASH
1913
	while (c <= 0x1246e)	// ..to CUNEIFORM NUMERIC SIGN NINE U VARIANT FORM
1914
		charset[i++] = c++;
1915
	c = 0x12470;		// from CUNEIFORM PUNCTUATION SIGN OLD ASSYRIAN WORD DIVIDER
1916
	while (c <= 0x12474)	// ..to CUNEIFORM PUNCTUATION SIGN DIAGONAL QUADCOLON
1917
		charset[i++] = c++;
1918
// 12480..1254F; Early Dynastic Cuneiform
1919
	c = 0x12480;		// from CUNEIFORM SIGN AB TIMES NUN TENU
1920
	while (c <= 0x12543)	// ..to CUNEIFORM SIGN ZU5 TIMES THREE DISH TENU
1921
		charset[i++] = c++;
1922
// 13000..1342F; Egyptian Hieroglyphs
1923
	c = 0x13000;		// from EGYPTIAN HIEROGLYPH A001
1924
	while (c <= 0x1342e)	// ..to EGYPTIAN HIEROGLYPH AA032
1925
		charset[i++] = c++;
1926
// 13430..1343F; Egyptian Hieroglyph Format Controls
1927
	c = 0x13430;		// from EGYPTIAN HIEROGLYPH VERTICAL JOINER
1928
	while (c <= 0x13438)	// ..to EGYPTIAN HIEROGLYPH END SEGMENT
1929
		charset[i++] = c++;
1930
// 14400..1467F; Anatolian Hieroglyphs
1931
	c = 0x14400;		// from ANATOLIAN HIEROGLYPH A001
1932
	while (c <= 0x14646)	// ..to ANATOLIAN HIEROGLYPH A530
1933
		charset[i++] = c++;
1934
// 16800..16A3F; Bamum Supplement
1935
	c = 0x16800;		// from BAMUM LETTER PHASE-A NGKUE MFON
1936
	while (c <= 0x16a38)	// ..to BAMUM LETTER PHASE-F VUEQ
1937
		charset[i++] = c++;
1938
// 16A40..16A6F; Mro
1939
	c = 0x16a40;		// from MRO LETTER TA
1940
	while (c <= 0x16a5e)	// ..to MRO LETTER TEK
1941
		charset[i++] = c++;
1942
	c = 0x16a60;		// from MRO DIGIT ZERO
1943
	while (c <= 0x16a69)	// ..to MRO DIGIT NINE
1944
		charset[i++] = c++;
1945
	charset[i++] = 0x16a6e;	// MRO DANDA
1946
	charset[i++] = 0x16a6f;	// MRO DOUBLE DANDA
1947
// 16AD0..16AFF; Bassa Vah
1948
	c = 0x16ad0;		// from BASSA VAH LETTER ENNI
1949
	while (c <= 0x16aed)	// ..to BASSA VAH LETTER I
1950
		charset[i++] = c++;
1951
	c = 0x16af0;		// from BASSA VAH COMBINING HIGH TONE
1952
	while (c <= 0x16af5)	// ..to BASSA VAH FULL STOP
1953
		charset[i++] = c++;
1954
// 16B00..16B8F; Pahawh Hmong
1955
	c = 0x16b00;		// from PAHAWH HMONG VOWEL KEEB
1956
	while (c <= 0x16b45)	// ..to PAHAWH HMONG SIGN CIM TSOV ROG
1957
		charset[i++] = c++;
1958
	c = 0x16b50;		// from PAHAWH HMONG DIGIT ZERO
1959
	while (c <= 0x16b59)	// ..to PAHAWH HMONG DIGIT NINE
1960
		charset[i++] = c++;
1961
	c = 0x16b5b;		// from PAHAWH HMONG NUMBER TENS
1962
	while (c <= 0x16b61)	// ..to PAHAWH HMONG NUMBER TRILLIONS
1963
		charset[i++] = c++;
1964
	c = 0x16b63;		// from PAHAWH HMONG SIGN VOS LUB
1965
	while (c <= 0x16b77)	// ..to PAHAWH HMONG SIGN CIM NRES TOS
1966
		charset[i++] = c++;
1967
	c = 0x16b7d;		// from PAHAWH HMONG CLAN SIGN TSHEEJ
1968
	while (c <= 0x16b8f)	// ..to PAHAWH HMONG CLAN SIGN VWJ
1969
		charset[i++] = c++;
1970
// 16E40..16E9F; Medefaidrin
1971
	c = 0x16e40;		// from MEDEFAIDRIN CAPITAL LETTER M
1972
	while (c <= 0x16e9a)	// ..to MEDEFAIDRIN EXCLAMATION OH
1973
		charset[i++] = c++;
1974
// 16F00..16F9F; Miao
1975
	c = 0x16f00;		// from MIAO LETTER PA
1976
	while (c <= 0x16f4a)	// ..to MIAO LETTER RTE
1977
		charset[i++] = c++;
1978
	c = 0x16f4f;		// from MIAO SIGN CONSONANT MODIFIER BAR
1979
	while (c <= 0x16f87)	// ..to MIAO VOWEL SIGN UI
1980
		charset[i++] = c++;
1981
	c = 0x16f8f;		// from MIAO TONE RIGHT
1982
	while (c <= 0x16f9f)	// ..to MIAO LETTER REFORMED TONE-8
1983
		charset[i++] = c++;
1984
// 16FE0..16FFF; Ideographic Symbols and Punctuation
1985
	c = 0x16fe0;		// from TANGUT ITERATION MARK
1986
	while (c <= 0x16fe4)	// ..to KHITAN SMALL SCRIPT FILLER
1987
		charset[i++] = c++;
1988
	charset[i++] = 0x16ff0;	// VIETNAMESE ALTERNATE READING MARK CA
1989
	charset[i++] = 0x16ff1;	// VIETNAMESE ALTERNATE READING MARK NHAY
1990
// 17000..187FF; Tangut
1991
	c = 0x17000;		// from <Tangut Ideograph, First>
1992
	while (c <= 0x187f7)	// ..to <Tangut Ideograph, Last>
1993
		charset[i++] = c++;
1994
// 18800..18AFF; Tangut Components
1995
	c = 0x18800;		// from TANGUT COMPONENT-001
1996
	while (c <= 0x18aff)	// ..to TANGUT COMPONENT-768
1997
		charset[i++] = c++;
1998
// 18B00..18CFF; Khitan Small Script
1999
	c = 0x18b00;		// from KHITAN SMALL SCRIPT CHARACTER-18B00
2000
	while (c <= 0x18cd5)	// ..to KHITAN SMALL SCRIPT CHARACTER-18CD5
2001
		charset[i++] = c++;
2002
// 18D00..18D8F; Tangut Supplement
2003
	c = 0x18d00;		// from <Tangut Ideograph Supplement, First>
2004
	while (c <= 0x18d08)	// ..to <Tangut Ideograph Supplement, Last>
2005
		charset[i++] = c++;
2006
// 1B000..1B0FF; Kana Supplement
2007
	c = 0x1b000;		// from KATAKANA LETTER ARCHAIC E
2008
	while (c <= 0x1b0ff)	// ..to HENTAIGANA LETTER RE-2
2009
		charset[i++] = c++;
2010
// 1B100..1B12F; Kana Extended-A
2011
	c = 0x1b100;		// from HENTAIGANA LETTER RE-3
2012
	while (c <= 0x1b11e)	// ..to HENTAIGANA LETTER N-MU-MO-2
2013
		charset[i++] = c++;
2014
// 1B130..1B16F; Small Kana Extension
2015
	charset[i++] = 0x1b150;	// HIRAGANA LETTER SMALL WI
2016
	charset[i++] = 0x1b152;	// HIRAGANA LETTER SMALL WO
2017
	c = 0x1b164;		// from KATAKANA LETTER SMALL WI
2018
	while (c <= 0x1b167)	// ..to KATAKANA LETTER SMALL N
2019
		charset[i++] = c++;
2020
// 1B170..1B2FF; Nushu
2021
	c = 0x1b170;		// from NUSHU CHARACTER-1B170
2022
	while (c <= 0x1b2fb)	// ..to NUSHU CHARACTER-1B2FB
2023
		charset[i++] = c++;
2024
// 1BC00..1BC9F; Duployan
2025
	c = 0x1bc00;		// from DUPLOYAN LETTER H
2026
	while (c <= 0x1bc6a)	// ..to DUPLOYAN LETTER VOCALIC M
2027
		charset[i++] = c++;
2028
	c = 0x1bc70;		// from DUPLOYAN AFFIX LEFT HORIZONTAL SECANT
2029
	while (c <= 0x1bc7c)	// ..to DUPLOYAN AFFIX ATTACHED TANGENT HOOK
2030
		charset[i++] = c++;
2031
	c = 0x1bc80;		// from DUPLOYAN AFFIX HIGH ACUTE
2032
	while (c <= 0x1bc88)	// ..to DUPLOYAN AFFIX HIGH VERTICAL
2033
		charset[i++] = c++;
2034
	c = 0x1bc90;		// from DUPLOYAN AFFIX LOW ACUTE
2035
	while (c <= 0x1bc99)	// ..to DUPLOYAN AFFIX LOW ARROW
2036
		charset[i++] = c++;
2037
	c = 0x1bc9c;		// from DUPLOYAN SIGN O WITH CROSS
2038
	while (c <= 0x1bc9f)	// ..to DUPLOYAN PUNCTUATION CHINOOK FULL STOP
2039
		charset[i++] = c++;
2040
// 1BCA0..1BCAF; Shorthand Format Controls
2041
	c = 0x1bca0;		// from SHORTHAND FORMAT LETTER OVERLAP
2042
	while (c <= 0x1bca3)	// ..to SHORTHAND FORMAT UP STEP
2043
		charset[i++] = c++;
2044
// 1D000..1D0FF; Byzantine Musical Symbols
2045
	c = 0x1d000;		// from BYZANTINE MUSICAL SYMBOL PSILI
2046
	while (c <= 0x1d0f5)	// ..to BYZANTINE MUSICAL SYMBOL GORGON NEO KATO
2047
		charset[i++] = c++;
2048
// 1D100..1D1FF; Musical Symbols
2049
	c = 0x1d100;		// from MUSICAL SYMBOL SINGLE BARLINE
2050
	while (c <= 0x1d126)	// ..to MUSICAL SYMBOL DRUM CLEF-2
2051
		charset[i++] = c++;
2052
	c = 0x1d129;		// from MUSICAL SYMBOL MULTIPLE MEASURE REST
2053
	while (c <= 0x1d1e8)	// ..to MUSICAL SYMBOL KIEVAN FLAT SIGN
2054
		charset[i++] = c++;
2055
// 1D200..1D24F; Ancient Greek Musical Notation
2056
	c = 0x1d200;		// from GREEK VOCAL NOTATION SYMBOL-1
2057
	while (c <= 0x1d245)	// ..to GREEK MUSICAL LEIMMA
2058
		charset[i++] = c++;
2059
// 1D2E0..1D2FF; Mayan Numerals
2060
	c = 0x1d2e0;		// from MAYAN NUMERAL ZERO
2061
	while (c <= 0x1d2f3)	// ..to MAYAN NUMERAL NINETEEN
2062
		charset[i++] = c++;
2063
// 1D300..1D35F; Tai Xuan Jing Symbols
2064
	c = 0x1d300;		// from MONOGRAM FOR EARTH
2065
	while (c <= 0x1d356)	// ..to TETRAGRAM FOR FOSTERING
2066
		charset[i++] = c++;
2067
// 1D360..1D37F; Counting Rod Numerals
2068
	c = 0x1d360;		// from COUNTING ROD UNIT DIGIT ONE
2069
	while (c <= 0x1d378)	// ..to TALLY MARK FIVE
2070
		charset[i++] = c++;
2071
// 1D400..1D7FF; Mathematical Alphanumeric Symbols
2072
	c = 0x1d400;		// from MATHEMATICAL BOLD CAPITAL A
2073
	while (c <= 0x1d454)	// ..to MATHEMATICAL ITALIC SMALL G
2074
		charset[i++] = c++;
2075
	c = 0x1d456;		// from MATHEMATICAL ITALIC SMALL I
2076
	while (c <= 0x1d49c)	// ..to MATHEMATICAL SCRIPT CAPITAL A
2077
		charset[i++] = c++;
2078
	charset[i++] = 0x1d49e;	// MATHEMATICAL SCRIPT CAPITAL C
2079
	charset[i++] = 0x1d49f;	// MATHEMATICAL SCRIPT CAPITAL D
2080
	charset[i++] = 0x1d4a5;	// MATHEMATICAL SCRIPT CAPITAL J
2081
	charset[i++] = 0x1d4a6;	// MATHEMATICAL SCRIPT CAPITAL K
2082
	c = 0x1d4a9;		// from MATHEMATICAL SCRIPT CAPITAL N
2083
	while (c <= 0x1d4ac)	// ..to MATHEMATICAL SCRIPT CAPITAL Q
2084
		charset[i++] = c++;
2085
	c = 0x1d4ae;		// from MATHEMATICAL SCRIPT CAPITAL S
2086
	while (c <= 0x1d4b9)	// ..to MATHEMATICAL SCRIPT SMALL D
2087
		charset[i++] = c++;
2088
	c = 0x1d4bd;		// from MATHEMATICAL SCRIPT SMALL H
2089
	while (c <= 0x1d4c3)	// ..to MATHEMATICAL SCRIPT SMALL N
2090
		charset[i++] = c++;
2091
	c = 0x1d4c5;		// from MATHEMATICAL SCRIPT SMALL P
2092
	while (c <= 0x1d505)	// ..to MATHEMATICAL FRAKTUR CAPITAL B
2093
		charset[i++] = c++;
2094
	c = 0x1d507;		// from MATHEMATICAL FRAKTUR CAPITAL D
2095
	while (c <= 0x1d50a)	// ..to MATHEMATICAL FRAKTUR CAPITAL G
2096
		charset[i++] = c++;
2097
	c = 0x1d50d;		// from MATHEMATICAL FRAKTUR CAPITAL J
2098
	while (c <= 0x1d514)	// ..to MATHEMATICAL FRAKTUR CAPITAL Q
2099
		charset[i++] = c++;
2100
	c = 0x1d516;		// from MATHEMATICAL FRAKTUR CAPITAL S
2101
	while (c <= 0x1d51c)	// ..to MATHEMATICAL FRAKTUR CAPITAL Y
2102
		charset[i++] = c++;
2103
	c = 0x1d51e;		// from MATHEMATICAL FRAKTUR SMALL A
2104
	while (c <= 0x1d539)	// ..to MATHEMATICAL DOUBLE-STRUCK CAPITAL B
2105
		charset[i++] = c++;
2106
	c = 0x1d53b;		// from MATHEMATICAL DOUBLE-STRUCK CAPITAL D
2107
	while (c <= 0x1d53e)	// ..to MATHEMATICAL DOUBLE-STRUCK CAPITAL G
2108
		charset[i++] = c++;
2109
	c = 0x1d540;		// from MATHEMATICAL DOUBLE-STRUCK CAPITAL I
2110
	while (c <= 0x1d544)	// ..to MATHEMATICAL DOUBLE-STRUCK CAPITAL M
2111
		charset[i++] = c++;
2112
	c = 0x1d54a;		// from MATHEMATICAL DOUBLE-STRUCK CAPITAL S
2113
	while (c <= 0x1d550)	// ..to MATHEMATICAL DOUBLE-STRUCK CAPITAL Y
2114
		charset[i++] = c++;
2115
	c = 0x1d552;		// from MATHEMATICAL DOUBLE-STRUCK SMALL A
2116
	while (c <= 0x1d6a5)	// ..to MATHEMATICAL ITALIC SMALL DOTLESS J
2117
		charset[i++] = c++;
2118
	c = 0x1d6a8;		// from MATHEMATICAL BOLD CAPITAL ALPHA
2119
	while (c <= 0x1d7cb)	// ..to MATHEMATICAL BOLD SMALL DIGAMMA
2120
		charset[i++] = c++;
2121
	c = 0x1d7ce;		// from MATHEMATICAL BOLD DIGIT ZERO
2122
	while (c <= 0x1d7ff)	// ..to MATHEMATICAL MONOSPACE DIGIT NINE
2123
		charset[i++] = c++;
2124
// 1D800..1DAAF; Sutton SignWriting
2125
	c = 0x1d800;		// from SIGNWRITING HAND-FIST INDEX
2126
	while (c <= 0x1da8b)	// ..to SIGNWRITING PARENTHESIS
2127
		charset[i++] = c++;
2128
	c = 0x1da9b;		// from SIGNWRITING FILL MODIFIER-2
2129
	while (c <= 0x1da9f)	// ..to SIGNWRITING FILL MODIFIER-6
2130
		charset[i++] = c++;
2131
	c = 0x1daa1;		// from SIGNWRITING ROTATION MODIFIER-2
2132
	while (c <= 0x1daaf)	// ..to SIGNWRITING ROTATION MODIFIER-16
2133
		charset[i++] = c++;
2134
// 1E000..1E02F; Glagolitic Supplement
2135
	c = 0x1e000;		// from COMBINING GLAGOLITIC LETTER AZU
2136
	while (c <= 0x1e006)	// ..to COMBINING GLAGOLITIC LETTER ZHIVETE
2137
		charset[i++] = c++;
2138
	c = 0x1e008;		// from COMBINING GLAGOLITIC LETTER ZEMLJA
2139
	while (c <= 0x1e018)	// ..to COMBINING GLAGOLITIC LETTER HERU
2140
		charset[i++] = c++;
2141
	c = 0x1e01b;		// from COMBINING GLAGOLITIC LETTER SHTA
2142
	while (c <= 0x1e021)	// ..to COMBINING GLAGOLITIC LETTER YATI
2143
		charset[i++] = c++;
2144
	charset[i++] = 0x1e023;	// COMBINING GLAGOLITIC LETTER YU
2145
	charset[i++] = 0x1e024;	// COMBINING GLAGOLITIC LETTER SMALL YUS
2146
	c = 0x1e026;		// from COMBINING GLAGOLITIC LETTER YO
2147
	while (c <= 0x1e02a)	// ..to COMBINING GLAGOLITIC LETTER FITA
2148
		charset[i++] = c++;
2149
// 1E100..1E14F; Nyiakeng Puachue Hmong
2150
	c = 0x1e100;		// from NYIAKENG PUACHUE HMONG LETTER MA
2151
	while (c <= 0x1e12c)	// ..to NYIAKENG PUACHUE HMONG LETTER W
2152
		charset[i++] = c++;
2153
	c = 0x1e130;		// from NYIAKENG PUACHUE HMONG TONE-B
2154
	while (c <= 0x1e13d)	// ..to NYIAKENG PUACHUE HMONG SYLLABLE LENGTHENER
2155
		charset[i++] = c++;
2156
	c = 0x1e140;		// from NYIAKENG PUACHUE HMONG DIGIT ZERO
2157
	while (c <= 0x1e149)	// ..to NYIAKENG PUACHUE HMONG DIGIT NINE
2158
		charset[i++] = c++;
2159
	charset[i++] = 0x1e14e;	// NYIAKENG PUACHUE HMONG LOGOGRAM NYAJ
2160
	charset[i++] = 0x1e14f;	// NYIAKENG PUACHUE HMONG CIRCLED CA
2161
// 1E2C0..1E2FF; Wancho
2162
	c = 0x1e2c0;		// from WANCHO LETTER AA
2163
	while (c <= 0x1e2f9)	// ..to WANCHO DIGIT NINE
2164
		charset[i++] = c++;
2165
	charset[i++] = 0x1e2ff;	// WANCHO NGUN SIGN
2166
// 1E800..1E8DF; Mende Kikakui
2167
	c = 0x1e800;		// from MENDE KIKAKUI SYLLABLE M001 KI
2168
	while (c <= 0x1e8c4)	// ..to MENDE KIKAKUI SYLLABLE M060 NYON
2169
		charset[i++] = c++;
2170
	c = 0x1e8c7;		// from MENDE KIKAKUI DIGIT ONE
2171
	while (c <= 0x1e8d6)	// ..to MENDE KIKAKUI COMBINING NUMBER MILLIONS
2172
		charset[i++] = c++;
2173
// 1E900..1E95F; Adlam
2174
	c = 0x1e900;		// from ADLAM CAPITAL LETTER ALIF
2175
	while (c <= 0x1e94b)	// ..to ADLAM NASALIZATION MARK
2176
		charset[i++] = c++;
2177
	c = 0x1e950;		// from ADLAM DIGIT ZERO
2178
	while (c <= 0x1e959)	// ..to ADLAM DIGIT NINE
2179
		charset[i++] = c++;
2180
	charset[i++] = 0x1e95e;	// ADLAM INITIAL EXCLAMATION MARK
2181
	charset[i++] = 0x1e95f;	// ADLAM INITIAL QUESTION MARK
2182
// 1EC70..1ECBF; Indic Siyaq Numbers
2183
	c = 0x1ec71;		// from INDIC SIYAQ NUMBER ONE
2184
	while (c <= 0x1ecb4)	// ..to INDIC SIYAQ ALTERNATE LAKH MARK
2185
		charset[i++] = c++;
2186
// 1ED00..1ED4F; Ottoman Siyaq Numbers
2187
	c = 0x1ed01;		// from OTTOMAN SIYAQ NUMBER ONE
2188
	while (c <= 0x1ed3d)	// ..to OTTOMAN SIYAQ FRACTION ONE SIXTH
2189
		charset[i++] = c++;
2190
// 1EE00..1EEFF; Arabic Mathematical Alphabetic Symbols
2191
	c = 0x1ee00;		// from ARABIC MATHEMATICAL ALEF
2192
	while (c <= 0x1ee03)	// ..to ARABIC MATHEMATICAL DAL
2193
		charset[i++] = c++;
2194
	c = 0x1ee05;		// from ARABIC MATHEMATICAL WAW
2195
	while (c <= 0x1ee1f)	// ..to ARABIC MATHEMATICAL DOTLESS QAF
2196
		charset[i++] = c++;
2197
	charset[i++] = 0x1ee21;	// ARABIC MATHEMATICAL INITIAL BEH
2198
	charset[i++] = 0x1ee22;	// ARABIC MATHEMATICAL INITIAL JEEM
2199
	c = 0x1ee29;		// from ARABIC MATHEMATICAL INITIAL YEH
2200
	while (c <= 0x1ee32)	// ..to ARABIC MATHEMATICAL INITIAL QAF
2201
		charset[i++] = c++;
2202
	c = 0x1ee34;		// from ARABIC MATHEMATICAL INITIAL SHEEN
2203
	while (c <= 0x1ee37)	// ..to ARABIC MATHEMATICAL INITIAL KHAH
2204
		charset[i++] = c++;
2205
	charset[i++] = 0x1ee4d;	// ARABIC MATHEMATICAL TAILED NOON
2206
	charset[i++] = 0x1ee4f;	// ARABIC MATHEMATICAL TAILED AIN
2207
	charset[i++] = 0x1ee51;	// ARABIC MATHEMATICAL TAILED SAD
2208
	charset[i++] = 0x1ee52;	// ARABIC MATHEMATICAL TAILED QAF
2209
	charset[i++] = 0x1ee61;	// ARABIC MATHEMATICAL STRETCHED BEH
2210
	charset[i++] = 0x1ee62;	// ARABIC MATHEMATICAL STRETCHED JEEM
2211
	c = 0x1ee67;		// from ARABIC MATHEMATICAL STRETCHED HAH
2212
	while (c <= 0x1ee6a)	// ..to ARABIC MATHEMATICAL STRETCHED KAF
2213
		charset[i++] = c++;
2214
	c = 0x1ee6c;		// from ARABIC MATHEMATICAL STRETCHED MEEM
2215
	while (c <= 0x1ee72)	// ..to ARABIC MATHEMATICAL STRETCHED QAF
2216
		charset[i++] = c++;
2217
	c = 0x1ee74;		// from ARABIC MATHEMATICAL STRETCHED SHEEN
2218
	while (c <= 0x1ee77)	// ..to ARABIC MATHEMATICAL STRETCHED KHAH
2219
		charset[i++] = c++;
2220
	c = 0x1ee79;		// from ARABIC MATHEMATICAL STRETCHED DAD
2221
	while (c <= 0x1ee7c)	// ..to ARABIC MATHEMATICAL STRETCHED DOTLESS BEH
2222
		charset[i++] = c++;
2223
	c = 0x1ee80;		// from ARABIC MATHEMATICAL LOOPED ALEF
2224
	while (c <= 0x1ee89)	// ..to ARABIC MATHEMATICAL LOOPED YEH
2225
		charset[i++] = c++;
2226
	c = 0x1ee8b;		// from ARABIC MATHEMATICAL LOOPED LAM
2227
	while (c <= 0x1ee9b)	// ..to ARABIC MATHEMATICAL LOOPED GHAIN
2228
		charset[i++] = c++;
2229
	charset[i++] = 0x1eea1;	// ARABIC MATHEMATICAL DOUBLE-STRUCK BEH
2230
	charset[i++] = 0x1eea3;	// ARABIC MATHEMATICAL DOUBLE-STRUCK DAL
2231
	c = 0x1eea5;		// from ARABIC MATHEMATICAL DOUBLE-STRUCK WAW
2232
	while (c <= 0x1eea9)	// ..to ARABIC MATHEMATICAL DOUBLE-STRUCK YEH
2233
		charset[i++] = c++;
2234
	c = 0x1eeab;		// from ARABIC MATHEMATICAL DOUBLE-STRUCK LAM
2235
	while (c <= 0x1eebb)	// ..to ARABIC MATHEMATICAL DOUBLE-STRUCK GHAIN
2236
		charset[i++] = c++;
2237
	charset[i++] = 0x1eef0;	// ARABIC MATHEMATICAL OPERATOR MEEM WITH HAH WITH TATWEEL
2238
	charset[i++] = 0x1eef1;	// ARABIC MATHEMATICAL OPERATOR HAH WITH DAL
2239
// 1F000..1F02F; Mahjong Tiles
2240
	c = 0x1f000;		// from MAHJONG TILE EAST WIND
2241
	while (c <= 0x1f02b)	// ..to MAHJONG TILE BACK
2242
		charset[i++] = c++;
2243
// 1F030..1F09F; Domino Tiles
2244
	c = 0x1f030;		// from DOMINO TILE HORIZONTAL BACK
2245
	while (c <= 0x1f093)	// ..to DOMINO TILE VERTICAL-06-06
2246
		charset[i++] = c++;
2247
// 1F0A0..1F0FF; Playing Cards
2248
	c = 0x1f0a0;		// from PLAYING CARD BACK
2249
	while (c <= 0x1f0ae)	// ..to PLAYING CARD KING OF SPADES
2250
		charset[i++] = c++;
2251
	c = 0x1f0b1;		// from PLAYING CARD ACE OF HEARTS
2252
	while (c <= 0x1f0bf)	// ..to PLAYING CARD RED JOKER
2253
		charset[i++] = c++;
2254
	c = 0x1f0c1;		// from PLAYING CARD ACE OF DIAMONDS
2255
	while (c <= 0x1f0cf)	// ..to PLAYING CARD BLACK JOKER
2256
		charset[i++] = c++;
2257
	c = 0x1f0d1;		// from PLAYING CARD ACE OF CLUBS
2258
	while (c <= 0x1f0f5)	// ..to PLAYING CARD TRUMP-21
2259
		charset[i++] = c++;
2260
// 1F100..1F1FF; Enclosed Alphanumeric Supplement
2261
	c = 0x1f100;		// from DIGIT ZERO FULL STOP
2262
	while (c <= 0x1f1ad)	// ..to MASK WORK SYMBOL
2263
		charset[i++] = c++;
2264
	c = 0x1f1e6;		// from REGIONAL INDICATOR SYMBOL LETTER A
2265
	while (c <= 0x1f1ff)	// ..to REGIONAL INDICATOR SYMBOL LETTER Z
2266
		charset[i++] = c++;
2267
// 1F200..1F2FF; Enclosed Ideographic Supplement
2268
	charset[i++] = 0x1f200;	// SQUARE HIRAGANA HOKA
2269
	charset[i++] = 0x1f202;	// SQUARED KATAKANA SA
2270
	c = 0x1f210;		// from SQUARED CJK UNIFIED IDEOGRAPH-624B
2271
	while (c <= 0x1f23b)	// ..to SQUARED CJK UNIFIED IDEOGRAPH-914D
2272
		charset[i++] = c++;
2273
	c = 0x1f240;		// from TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-672C
2274
	while (c <= 0x1f248)	// ..to TORTOISE SHELL BRACKETED CJK UNIFIED IDEOGRAPH-6557
2275
		charset[i++] = c++;
2276
	charset[i++] = 0x1f250;	// CIRCLED IDEOGRAPH ADVANTAGE
2277
	charset[i++] = 0x1f251;	// CIRCLED IDEOGRAPH ACCEPT
2278
	c = 0x1f260;		// from ROUNDED SYMBOL FOR FU
2279
	while (c <= 0x1f265)	// ..to ROUNDED SYMBOL FOR CAI
2280
		charset[i++] = c++;
2281
// 1F300..1F5FF; Miscellaneous Symbols and Pictographs
2282
	c = 0x1f300;		// from CYCLONE
2283
	while (c <= 0x1f5ff)	// ..to MOYAI
2284
		charset[i++] = c++;
2285
// 1F600..1F64F; Emoticons
2286
	c = 0x1f600;		// from GRINNING FACE
2287
	while (c <= 0x1f64f)	// ..to PERSON WITH FOLDED HANDS
2288
		charset[i++] = c++;
2289
// 1F650..1F67F; Ornamental Dingbats
2290
	c = 0x1f650;		// from NORTH WEST POINTING LEAF
2291
	while (c <= 0x1f67f)	// ..to REVERSE CHECKER BOARD
2292
		charset[i++] = c++;
2293
// 1F680..1F6FF; Transport and Map Symbols
2294
	c = 0x1f680;		// from ROCKET
2295
	while (c <= 0x1f6d7)	// ..to ELEVATOR
2296
		charset[i++] = c++;
2297
	c = 0x1f6e0;		// from HAMMER AND WRENCH
2298
	while (c <= 0x1f6ec)	// ..to AIRPLANE ARRIVING
2299
		charset[i++] = c++;
2300
	c = 0x1f6f0;		// from SATELLITE
2301
	while (c <= 0x1f6fc)	// ..to ROLLER SKATE
2302
		charset[i++] = c++;
2303
// 1F700..1F77F; Alchemical Symbols
2304
	c = 0x1f700;		// from ALCHEMICAL SYMBOL FOR QUINTESSENCE
2305
	while (c <= 0x1f773)	// ..to ALCHEMICAL SYMBOL FOR HALF OUNCE
2306
		charset[i++] = c++;
2307
// 1F780..1F7FF; Geometric Shapes Extended
2308
	c = 0x1f780;		// from BLACK LEFT-POINTING ISOSCELES RIGHT TRIANGLE
2309
	while (c <= 0x1f7d8)	// ..to NEGATIVE CIRCLED SQUARE
2310
		charset[i++] = c++;
2311
	c = 0x1f7e0;		// from LARGE ORANGE CIRCLE
2312
	while (c <= 0x1f7eb)	// ..to LARGE BROWN SQUARE
2313
		charset[i++] = c++;
2314
// 1F800..1F8FF; Supplemental Arrows-C
2315
	c = 0x1f800;		// from LEFTWARDS ARROW WITH SMALL TRIANGLE ARROWHEAD
2316
	while (c <= 0x1f80b)	// ..to DOWNWARDS ARROW WITH LARGE TRIANGLE ARROWHEAD
2317
		charset[i++] = c++;
2318
	c = 0x1f810;		// from LEFTWARDS ARROW WITH SMALL EQUILATERAL ARROWHEAD
2319
	while (c <= 0x1f847)	// ..to DOWNWARDS HEAVY ARROW
2320
		charset[i++] = c++;
2321
	c = 0x1f850;		// from LEFTWARDS SANS-SERIF ARROW
2322
	while (c <= 0x1f859)	// ..to UP DOWN SANS-SERIF ARROW
2323
		charset[i++] = c++;
2324
	c = 0x1f860;		// from WIDE-HEADED LEFTWARDS LIGHT BARB ARROW
2325
	while (c <= 0x1f887)	// ..to WIDE-HEADED SOUTH WEST VERY HEAVY BARB ARROW
2326
		charset[i++] = c++;
2327
	c = 0x1f890;		// from LEFTWARDS TRIANGLE ARROWHEAD
2328
	while (c <= 0x1f8ad)	// ..to WHITE ARROW SHAFT WIDTH TWO THIRDS
2329
		charset[i++] = c++;
2330
	charset[i++] = 0x1f8b0;	// ARROW POINTING UPWARDS THEN NORTH WEST
2331
	charset[i++] = 0x1f8b1;	// ARROW POINTING RIGHTWARDS THEN CURVING SOUTH WEST
2332
// 1F900..1F9FF; Supplemental Symbols and Pictographs
2333
	c = 0x1f900;		// from CIRCLED CROSS FORMEE WITH FOUR DOTS
2334
	while (c <= 0x1f978)	// ..to DISGUISED FACE
2335
		charset[i++] = c++;
2336
	c = 0x1f97a;		// from FACE WITH PLEADING EYES
2337
	while (c <= 0x1f9cb)	// ..to BUBBLE TEA
2338
		charset[i++] = c++;
2339
	c = 0x1f9cd;		// from STANDING PERSON
2340
	while (c <= 0x1f9ff)	// ..to NAZAR AMULET
2341
		charset[i++] = c++;
2342
// 1FA00..1FA6F; Chess Symbols
2343
	c = 0x1fa00;		// from NEUTRAL CHESS KING
2344
	while (c <= 0x1fa53)	// ..to BLACK CHESS KNIGHT-BISHOP
2345
		charset[i++] = c++;
2346
	c = 0x1fa60;		// from XIANGQI RED GENERAL
2347
	while (c <= 0x1fa6d)	// ..to XIANGQI BLACK SOLDIER
2348
		charset[i++] = c++;
2349
// 1FA70..1FAFF; Symbols and Pictographs Extended-A
2350
	c = 0x1fa70;		// from BALLET SHOES
2351
	while (c <= 0x1fa74)	// ..to THONG SANDAL
2352
		charset[i++] = c++;
2353
	charset[i++] = 0x1fa78;	// DROP OF BLOOD
2354
	charset[i++] = 0x1fa7a;	// STETHOSCOPE
2355
	c = 0x1fa80;		// from YO-YO
2356
	while (c <= 0x1fa86)	// ..to NESTING DOLLS
2357
		charset[i++] = c++;
2358
	c = 0x1fa90;		// from RINGED PLANET
2359
	while (c <= 0x1faa8)	// ..to ROCK
2360
		charset[i++] = c++;
2361
	c = 0x1fab0;		// from FLY
2362
	while (c <= 0x1fab6)	// ..to FEATHER
2363
		charset[i++] = c++;
2364
	charset[i++] = 0x1fac0;	// ANATOMICAL HEART
2365
	charset[i++] = 0x1fac2;	// PEOPLE HUGGING
2366
	c = 0x1fad0;		// from BLUEBERRIES
2367
	while (c <= 0x1fad6)	// ..to TEAPOT
2368
		charset[i++] = c++;
2369
// 1FB00..1FBFF; Symbols for Legacy Computing
2370
	c = 0x1fb00;		// from BLOCK SEXTANT-1
2371
	while (c <= 0x1fb92)	// ..to UPPER HALF INVERSE MEDIUM SHADE AND LOWER HALF BLOCK
2372
		charset[i++] = c++;
2373
	c = 0x1fb94;		// from LEFT HALF INVERSE MEDIUM SHADE AND RIGHT HALF BLOCK
2374
	while (c <= 0x1fbca)	// ..to WHITE UP-POINTING CHEVRON
2375
		charset[i++] = c++;
2376
	c = 0x1fbf0;		// from SEGMENTED DIGIT ZERO
2377
	while (c <= 0x1fbf9)	// ..to SEGMENTED DIGIT NINE
2378
		charset[i++] = c++;
2379
// 20000..2A6DF; CJK Unified Ideographs Extension B
2380
	c = 0x20000;		// from <CJK Ideograph Extension B, First>
2381
	while (c <= 0x2a6dd)	// ..to <CJK Ideograph Extension B, Last>
2382
		charset[i++] = c++;
2383
// 2A700..2B73F; CJK Unified Ideographs Extension C
2384
	c = 0x2a700;		// from <CJK Ideograph Extension C, First>
2385
	while (c <= 0x2b734)	// ..to <CJK Ideograph Extension C, Last>
2386
		charset[i++] = c++;
2387
// 2B740..2B81F; CJK Unified Ideographs Extension D
2388
	c = 0x2b740;		// from <CJK Ideograph Extension D, First>
2389
	while (c <= 0x2b81d)	// ..to <CJK Ideograph Extension D, Last>
2390
		charset[i++] = c++;
2391
// 2B820..2CEAF; CJK Unified Ideographs Extension E
2392
	c = 0x2b820;		// from <CJK Ideograph Extension E, First>
2393
	while (c <= 0x2cea1)	// ..to <CJK Ideograph Extension E, Last>
2394
		charset[i++] = c++;
2395
// 2CEB0..2EBEF; CJK Unified Ideographs Extension F
2396
	c = 0x2ceb0;		// from <CJK Ideograph Extension F, First>
2397
	while (c <= 0x2ebe0)	// ..to <CJK Ideograph Extension F, Last>
2398
		charset[i++] = c++;
2399
// 2F800..2FA1F; CJK Compatibility Ideographs Supplement
2400
	c = 0x2f800;		// from CJK COMPATIBILITY IDEOGRAPH-2F800
2401
	while (c <= 0x2fa1d)	// ..to CJK COMPATIBILITY IDEOGRAPH-2FA1D
2402
		charset[i++] = c++;
2403
// 30000..3134F; CJK Unified Ideographs Extension G
2404
	c = 0x30000;		// from <CJK Ideograph Extension G, First>
2405
	while (c <= 0x3134a)	// ..to <CJK Ideograph Extension G, Last>
2406
		charset[i++] = c++;
2407
// E0000..E007F; Tags
2408
	c = 0xe0020;		// from TAG SPACE
2409
	while (c <= 0xe007f)	// ..to CANCEL TAG
2410
		charset[i++] = c++;
2411
// E0100..E01EF; Variation Selectors Supplement
2412
// F0000..FFFFF; Supplementary Private Use Area-A
2413
// 100000..10FFFF; Supplementary Private Use Area-B
2414

2415
/* Zero-terminate it, and cache the first character */
2416
	charset[maxc = i] = 0;
2417

2418
	length = minlength; c = 0;
2419

2420
/* We must init word with dummy data, it doesn't get set until filter() */
2421
	word = 1;
2422
}
2423

2424
void generate()
2425
{
2426
	int i, cl, wl;
2427

2428
	if (target_utf8) {
2429
		cl = 1;
2430
		if (charset[c] >= 0x80) {
2431
			cl++;
2432
			if (charset[c] >= 0x0800)
2433
				cl++;
2434
			if (charset[c] >= 0x10000)
2435
				cl++;
2436
			wl = length * cl;
2437
			if (wl > cipher_limit) {
2438
				c = 0;
2439
				if (++length > maxlength) {
2440
					word = 0;
2441
					return;
2442
				}
2443
				cl = 1;
2444
				if (charset[0] >= 0x80) {
2445
					cl++;
2446
					if (charset[0] >= 0x0800)
2447
						cl++;
2448
					if (charset[0] >= 0x10000)
2449
						cl++;
2450
					wl = length * cl;
2451
					if (wl > cipher_limit) {
2452
						word = 0;
2453
						return;
2454
					}
2455
				}
2456
			}
2457
		}
2458
	}
2459

2460
	i = 0;
2461
	while (i < length)
2462
		word[i++] = charset[c];
2463
	word[i] = 0;
2464

2465
	if (++c < maxc)
2466
		return;
2467

2468
	c = 0;
2469
	if (++length > maxlength)
2470
		length = 0; // Will NUL out the next "word" and thus terminate
2471

2472
	return;
2473
}
2474

2475
/* Reset length & c */
2476
void restore()
2477
{
2478
	length = 0;
2479

2480
	while (word[length]) {
2481
		length++;
2482
	}
2483
	c = word[0];
2484
}
2485

2486