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, Unicode (version 13) BMP version
7
#
8
# Number of candidates = 55,387 x max-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 9 bytes each).
14
#
15
# Note that the (newer) cracking mode --subsets=full-unicode is way faster than
16
# this external mode, although not as easy to adapt to smaller portions of the
17
# Unicode space.  See doc/SUBSETS
18

19
[List.External:Repeats16]
20
int minlength, maxlength, maxc, length, c;
21
int charset[0x10000];
22

23
void init()
24
{
25
	int i;
26

27
	# Trigger UTF-32 handling in External mode
28
	utf32 = 1;
29

30
	if (req_minlen)
31
		minlength = req_minlen;
32
	else
33
		minlength = 1;
34

35
	if (req_maxlen)
36
		maxlength = req_maxlen;
37
	else
38
		maxlength = cipher_limit;
39

40
/*
41
 * This defines the character set. This is auto-generated from UnicodeData.txt
42
 * and we skip control characters.
43
 */
44
	i = 0;
45
// 0000..007F; Basic Latin
46
	c = 0x20;		// from SPACE
47
	while (c <= 0x7e)	// ..to TILDE
48
		charset[i++] = c++;
49
// 0080..00FF; Latin-1 Supplement
50
	c = 0xa0;		// from NO-BREAK SPACE
51
	while (c <= 0xff)	// ..to LATIN SMALL LETTER Y WITH DIAERESIS
52
		charset[i++] = c++;
53
// 0100..017F; Latin Extended-A
54
	c = 0x100;		// from LATIN CAPITAL LETTER A WITH MACRON
55
	while (c <= 0x17f)	// ..to LATIN SMALL LETTER LONG S
56
		charset[i++] = c++;
57
// 0180..024F; Latin Extended-B
58
	c = 0x180;		// from LATIN SMALL LETTER B WITH STROKE
59
	while (c <= 0x24f)	// ..to LATIN SMALL LETTER Y WITH STROKE
60
		charset[i++] = c++;
61
// 0250..02AF; IPA Extensions
62
	c = 0x250;		// from LATIN SMALL LETTER TURNED A
63
	while (c <= 0x2af)	// ..to LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL
64
		charset[i++] = c++;
65
// 02B0..02FF; Spacing Modifier Letters
66
	c = 0x2b0;		// from MODIFIER LETTER SMALL H
67
	while (c <= 0x2ff)	// ..to MODIFIER LETTER LOW LEFT ARROW
68
		charset[i++] = c++;
69
// 0300..036F; Combining Diacritical Marks
70
	c = 0x300;		// from COMBINING GRAVE ACCENT
71
	while (c <= 0x36f)	// ..to COMBINING LATIN SMALL LETTER X
72
		charset[i++] = c++;
73
// 0370..03FF; Greek and Coptic
74
	c = 0x370;		// from GREEK CAPITAL LETTER HETA
75
	while (c <= 0x377)	// ..to GREEK SMALL LETTER PAMPHYLIAN DIGAMMA
76
		charset[i++] = c++;
77
	c = 0x37a;		// from GREEK YPOGEGRAMMENI
78
	while (c <= 0x37f)	// ..to GREEK CAPITAL LETTER YOT
79
		charset[i++] = c++;
80
	c = 0x384;		// from GREEK TONOS
81
	while (c <= 0x38a)	// ..to GREEK CAPITAL LETTER IOTA WITH TONOS
82
		charset[i++] = c++;
83
	c = 0x38e;		// from GREEK CAPITAL LETTER UPSILON WITH TONOS
84
	while (c <= 0x3a1)	// ..to GREEK CAPITAL LETTER RHO
85
		charset[i++] = c++;
86
	c = 0x3a3;		// from GREEK CAPITAL LETTER SIGMA
87
	while (c <= 0x3ff)	// ..to GREEK CAPITAL REVERSED DOTTED LUNATE SIGMA SYMBOL
88
		charset[i++] = c++;
89
// 0400..04FF; Cyrillic
90
	c = 0x400;		// from CYRILLIC CAPITAL LETTER IE WITH GRAVE
91
	while (c <= 0x4ff)	// ..to CYRILLIC SMALL LETTER HA WITH STROKE
92
		charset[i++] = c++;
93
// 0500..052F; Cyrillic Supplement
94
	c = 0x500;		// from CYRILLIC CAPITAL LETTER KOMI DE
95
	while (c <= 0x52f)	// ..to CYRILLIC SMALL LETTER EL WITH DESCENDER
96
		charset[i++] = c++;
97
// 0530..058F; Armenian
98
	c = 0x531;		// from ARMENIAN CAPITAL LETTER AYB
99
	while (c <= 0x556)	// ..to ARMENIAN CAPITAL LETTER FEH
100
		charset[i++] = c++;
101
	c = 0x559;		// from ARMENIAN MODIFIER LETTER LEFT HALF RING
102
	while (c <= 0x58a)	// ..to ARMENIAN HYPHEN
103
		charset[i++] = c++;
104
	charset[i++] = 0x58d;	// RIGHT-FACING ARMENIAN ETERNITY SIGN
105
	charset[i++] = 0x58f;	// ARMENIAN DRAM SIGN
106
// 0590..05FF; Hebrew
107
	c = 0x591;		// from HEBREW ACCENT ETNAHTA
108
	while (c <= 0x5c7)	// ..to HEBREW POINT QAMATS QATAN
109
		charset[i++] = c++;
110
	c = 0x5d0;		// from HEBREW LETTER ALEF
111
	while (c <= 0x5ea)	// ..to HEBREW LETTER TAV
112
		charset[i++] = c++;
113
	c = 0x5ef;		// from HEBREW YOD TRIANGLE
114
	while (c <= 0x5f4)	// ..to HEBREW PUNCTUATION GERSHAYIM
115
		charset[i++] = c++;
116
// 0600..06FF; Arabic
117
	c = 0x600;		// from ARABIC NUMBER SIGN
118
	while (c <= 0x61c)	// ..to ARABIC LETTER MARK
119
		charset[i++] = c++;
120
	c = 0x61e;		// from ARABIC TRIPLE DOT PUNCTUATION MARK
121
	while (c <= 0x6ff)	// ..to ARABIC LETTER HEH WITH INVERTED V
122
		charset[i++] = c++;
123
// 0700..074F; Syriac
124
	c = 0x700;		// from SYRIAC END OF PARAGRAPH
125
	while (c <= 0x70d)	// ..to SYRIAC HARKLEAN ASTERISCUS
126
		charset[i++] = c++;
127
	c = 0x70f;		// from SYRIAC ABBREVIATION MARK
128
	while (c <= 0x74a)	// ..to SYRIAC BARREKH
129
		charset[i++] = c++;
130
	charset[i++] = 0x74d;	// SYRIAC LETTER SOGDIAN ZHAIN
131
	charset[i++] = 0x74f;	// SYRIAC LETTER SOGDIAN FE
132
// 0750..077F; Arabic Supplement
133
	c = 0x750;		// from ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW
134
	while (c <= 0x77f)	// ..to ARABIC LETTER KAF WITH TWO DOTS ABOVE
135
		charset[i++] = c++;
136
// 0780..07BF; Thaana
137
	c = 0x780;		// from THAANA LETTER HAA
138
	while (c <= 0x7b1)	// ..to THAANA LETTER NAA
139
		charset[i++] = c++;
140
// 07C0..07FF; NKo
141
	c = 0x7c0;		// from NKO DIGIT ZERO
142
	while (c <= 0x7fa)	// ..to NKO LAJANYALAN
143
		charset[i++] = c++;
144
	charset[i++] = 0x7fd;	// NKO DANTAYALAN
145
	charset[i++] = 0x7ff;	// NKO TAMAN SIGN
146
// 0800..083F; Samaritan
147
	c = 0x800;		// from SAMARITAN LETTER ALAF
148
	while (c <= 0x82d)	// ..to SAMARITAN MARK NEQUDAA
149
		charset[i++] = c++;
150
	c = 0x830;		// from SAMARITAN PUNCTUATION NEQUDAA
151
	while (c <= 0x83e)	// ..to SAMARITAN PUNCTUATION ANNAAU
152
		charset[i++] = c++;
153
// 0840..085F; Mandaic
154
	c = 0x840;		// from MANDAIC LETTER HALQA
155
	while (c <= 0x85b)	// ..to MANDAIC GEMINATION MARK
156
		charset[i++] = c++;
157
	charset[i++] = 0x85e;	// MANDAIC PUNCTUATION
158
// 0860..086F; Syriac Supplement
159
	c = 0x860;		// from SYRIAC LETTER MALAYALAM NGA
160
	while (c <= 0x86a)	// ..to SYRIAC LETTER MALAYALAM SSA
161
		charset[i++] = c++;
162
// 08A0..08FF; Arabic Extended-A
163
	c = 0x8a0;		// from ARABIC LETTER BEH WITH SMALL V BELOW
164
	while (c <= 0x8b4)	// ..to ARABIC LETTER KAF WITH DOT BELOW
165
		charset[i++] = c++;
166
	c = 0x8b6;		// from ARABIC LETTER BEH WITH SMALL MEEM ABOVE
167
	while (c <= 0x8c7)	// ..to ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE
168
		charset[i++] = c++;
169
	c = 0x8d3;		// from ARABIC SMALL LOW WAW
170
	while (c <= 0x8ff)	// ..to ARABIC MARK SIDEWAYS NOON GHUNNA
171
		charset[i++] = c++;
172
// 0900..097F; Devanagari
173
	c = 0x900;		// from DEVANAGARI SIGN INVERTED CANDRABINDU
174
	while (c <= 0x97f)	// ..to DEVANAGARI LETTER BBA
175
		charset[i++] = c++;
176
// 0980..09FF; Bengali
177
	c = 0x980;		// from BENGALI ANJI
178
	while (c <= 0x983)	// ..to BENGALI SIGN VISARGA
179
		charset[i++] = c++;
180
	c = 0x985;		// from BENGALI LETTER A
181
	while (c <= 0x98c)	// ..to BENGALI LETTER VOCALIC L
182
		charset[i++] = c++;
183
	charset[i++] = 0x98f;	// BENGALI LETTER E
184
	charset[i++] = 0x990;	// BENGALI LETTER AI
185
	c = 0x993;		// from BENGALI LETTER O
186
	while (c <= 0x9a8)	// ..to BENGALI LETTER NA
187
		charset[i++] = c++;
188
	c = 0x9aa;		// from BENGALI LETTER PA
189
	while (c <= 0x9b0)	// ..to BENGALI LETTER RA
190
		charset[i++] = c++;
191
	c = 0x9b6;		// from BENGALI LETTER SHA
192
	while (c <= 0x9b9)	// ..to BENGALI LETTER HA
193
		charset[i++] = c++;
194
	c = 0x9bc;		// from BENGALI SIGN NUKTA
195
	while (c <= 0x9c4)	// ..to BENGALI VOWEL SIGN VOCALIC RR
196
		charset[i++] = c++;
197
	charset[i++] = 0x9c7;	// BENGALI VOWEL SIGN E
198
	charset[i++] = 0x9c8;	// BENGALI VOWEL SIGN AI
199
	c = 0x9cb;		// from BENGALI VOWEL SIGN O
200
	while (c <= 0x9ce)	// ..to BENGALI LETTER KHANDA TA
201
		charset[i++] = c++;
202
	charset[i++] = 0x9dc;	// BENGALI LETTER RRA
203
	charset[i++] = 0x9dd;	// BENGALI LETTER RHA
204
	c = 0x9df;		// from BENGALI LETTER YYA
205
	while (c <= 0x9e3)	// ..to BENGALI VOWEL SIGN VOCALIC LL
206
		charset[i++] = c++;
207
	c = 0x9e6;		// from BENGALI DIGIT ZERO
208
	while (c <= 0x9fe)	// ..to BENGALI SANDHI MARK
209
		charset[i++] = c++;
210
// 0A00..0A7F; Gurmukhi
211
	charset[i++] = 0xa01;	// GURMUKHI SIGN ADAK BINDI
212
	charset[i++] = 0xa03;	// GURMUKHI SIGN VISARGA
213
	c = 0xa05;		// from GURMUKHI LETTER A
214
	while (c <= 0xa0a)	// ..to GURMUKHI LETTER UU
215
		charset[i++] = c++;
216
	charset[i++] = 0xa0f;	// GURMUKHI LETTER EE
217
	charset[i++] = 0xa10;	// GURMUKHI LETTER AI
218
	c = 0xa13;		// from GURMUKHI LETTER OO
219
	while (c <= 0xa28)	// ..to GURMUKHI LETTER NA
220
		charset[i++] = c++;
221
	c = 0xa2a;		// from GURMUKHI LETTER PA
222
	while (c <= 0xa30)	// ..to GURMUKHI LETTER RA
223
		charset[i++] = c++;
224
	charset[i++] = 0xa32;	// GURMUKHI LETTER LA
225
	charset[i++] = 0xa33;	// GURMUKHI LETTER LLA
226
	charset[i++] = 0xa35;	// GURMUKHI LETTER VA
227
	charset[i++] = 0xa36;	// GURMUKHI LETTER SHA
228
	charset[i++] = 0xa38;	// GURMUKHI LETTER SA
229
	charset[i++] = 0xa39;	// GURMUKHI LETTER HA
230
	c = 0xa3e;		// from GURMUKHI VOWEL SIGN AA
231
	while (c <= 0xa42)	// ..to GURMUKHI VOWEL SIGN UU
232
		charset[i++] = c++;
233
	charset[i++] = 0xa47;	// GURMUKHI VOWEL SIGN EE
234
	charset[i++] = 0xa48;	// GURMUKHI VOWEL SIGN AI
235
	charset[i++] = 0xa4b;	// GURMUKHI VOWEL SIGN OO
236
	charset[i++] = 0xa4d;	// GURMUKHI SIGN VIRAMA
237
	c = 0xa59;		// from GURMUKHI LETTER KHHA
238
	while (c <= 0xa5c)	// ..to GURMUKHI LETTER RRA
239
		charset[i++] = c++;
240
	c = 0xa66;		// from GURMUKHI DIGIT ZERO
241
	while (c <= 0xa76)	// ..to GURMUKHI ABBREVIATION SIGN
242
		charset[i++] = c++;
243
// 0A80..0AFF; Gujarati
244
	charset[i++] = 0xa81;	// GUJARATI SIGN CANDRABINDU
245
	charset[i++] = 0xa83;	// GUJARATI SIGN VISARGA
246
	c = 0xa85;		// from GUJARATI LETTER A
247
	while (c <= 0xa8d)	// ..to GUJARATI VOWEL CANDRA E
248
		charset[i++] = c++;
249
	charset[i++] = 0xa8f;	// GUJARATI LETTER E
250
	charset[i++] = 0xa91;	// GUJARATI VOWEL CANDRA O
251
	c = 0xa93;		// from GUJARATI LETTER O
252
	while (c <= 0xaa8)	// ..to GUJARATI LETTER NA
253
		charset[i++] = c++;
254
	c = 0xaaa;		// from GUJARATI LETTER PA
255
	while (c <= 0xab0)	// ..to GUJARATI LETTER RA
256
		charset[i++] = c++;
257
	charset[i++] = 0xab2;	// GUJARATI LETTER LA
258
	charset[i++] = 0xab3;	// GUJARATI LETTER LLA
259
	c = 0xab5;		// from GUJARATI LETTER VA
260
	while (c <= 0xab9)	// ..to GUJARATI LETTER HA
261
		charset[i++] = c++;
262
	c = 0xabc;		// from GUJARATI SIGN NUKTA
263
	while (c <= 0xac5)	// ..to GUJARATI VOWEL SIGN CANDRA E
264
		charset[i++] = c++;
265
	charset[i++] = 0xac7;	// GUJARATI VOWEL SIGN E
266
	charset[i++] = 0xac9;	// GUJARATI VOWEL SIGN CANDRA O
267
	charset[i++] = 0xacb;	// GUJARATI VOWEL SIGN O
268
	charset[i++] = 0xacd;	// GUJARATI SIGN VIRAMA
269
	c = 0xae0;		// from GUJARATI LETTER VOCALIC RR
270
	while (c <= 0xae3)	// ..to GUJARATI VOWEL SIGN VOCALIC LL
271
		charset[i++] = c++;
272
	c = 0xae6;		// from GUJARATI DIGIT ZERO
273
	while (c <= 0xaf1)	// ..to GUJARATI RUPEE SIGN
274
		charset[i++] = c++;
275
	c = 0xaf9;		// from GUJARATI LETTER ZHA
276
	while (c <= 0xaff)	// ..to GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
277
		charset[i++] = c++;
278
// 0B00..0B7F; Oriya
279
	charset[i++] = 0xb01;	// ORIYA SIGN CANDRABINDU
280
	charset[i++] = 0xb03;	// ORIYA SIGN VISARGA
281
	c = 0xb05;		// from ORIYA LETTER A
282
	while (c <= 0xb0c)	// ..to ORIYA LETTER VOCALIC L
283
		charset[i++] = c++;
284
	charset[i++] = 0xb0f;	// ORIYA LETTER E
285
	charset[i++] = 0xb10;	// ORIYA LETTER AI
286
	c = 0xb13;		// from ORIYA LETTER O
287
	while (c <= 0xb28)	// ..to ORIYA LETTER NA
288
		charset[i++] = c++;
289
	c = 0xb2a;		// from ORIYA LETTER PA
290
	while (c <= 0xb30)	// ..to ORIYA LETTER RA
291
		charset[i++] = c++;
292
	charset[i++] = 0xb32;	// ORIYA LETTER LA
293
	charset[i++] = 0xb33;	// ORIYA LETTER LLA
294
	c = 0xb35;		// from ORIYA LETTER VA
295
	while (c <= 0xb39)	// ..to ORIYA LETTER HA
296
		charset[i++] = c++;
297
	c = 0xb3c;		// from ORIYA SIGN NUKTA
298
	while (c <= 0xb44)	// ..to ORIYA VOWEL SIGN VOCALIC RR
299
		charset[i++] = c++;
300
	charset[i++] = 0xb47;	// ORIYA VOWEL SIGN E
301
	charset[i++] = 0xb48;	// ORIYA VOWEL SIGN AI
302
	charset[i++] = 0xb4b;	// ORIYA VOWEL SIGN O
303
	charset[i++] = 0xb4d;	// ORIYA SIGN VIRAMA
304
	charset[i++] = 0xb55;	// ORIYA SIGN OVERLINE
305
	charset[i++] = 0xb57;	// ORIYA AU LENGTH MARK
306
	charset[i++] = 0xb5c;	// ORIYA LETTER RRA
307
	charset[i++] = 0xb5d;	// ORIYA LETTER RHA
308
	c = 0xb5f;		// from ORIYA LETTER YYA
309
	while (c <= 0xb63)	// ..to ORIYA VOWEL SIGN VOCALIC LL
310
		charset[i++] = c++;
311
	c = 0xb66;		// from ORIYA DIGIT ZERO
312
	while (c <= 0xb77)	// ..to ORIYA FRACTION THREE SIXTEENTHS
313
		charset[i++] = c++;
314
// 0B80..0BFF; Tamil
315
	charset[i++] = 0xb82;	// TAMIL SIGN ANUSVARA
316
	charset[i++] = 0xb83;	// TAMIL SIGN VISARGA
317
	c = 0xb85;		// from TAMIL LETTER A
318
	while (c <= 0xb8a)	// ..to TAMIL LETTER UU
319
		charset[i++] = c++;
320
	charset[i++] = 0xb8e;	// TAMIL LETTER E
321
	charset[i++] = 0xb90;	// TAMIL LETTER AI
322
	c = 0xb92;		// from TAMIL LETTER O
323
	while (c <= 0xb95)	// ..to TAMIL LETTER KA
324
		charset[i++] = c++;
325
	charset[i++] = 0xb99;	// TAMIL LETTER NGA
326
	charset[i++] = 0xb9a;	// TAMIL LETTER CA
327
	charset[i++] = 0xb9e;	// TAMIL LETTER NYA
328
	charset[i++] = 0xb9f;	// TAMIL LETTER TTA
329
	charset[i++] = 0xba3;	// TAMIL LETTER NNA
330
	charset[i++] = 0xba4;	// TAMIL LETTER TA
331
	charset[i++] = 0xba8;	// TAMIL LETTER NA
332
	charset[i++] = 0xbaa;	// TAMIL LETTER PA
333
	c = 0xbae;		// from TAMIL LETTER MA
334
	while (c <= 0xbb9)	// ..to TAMIL LETTER HA
335
		charset[i++] = c++;
336
	c = 0xbbe;		// from TAMIL VOWEL SIGN AA
337
	while (c <= 0xbc2)	// ..to TAMIL VOWEL SIGN UU
338
		charset[i++] = c++;
339
	charset[i++] = 0xbc6;	// TAMIL VOWEL SIGN E
340
	charset[i++] = 0xbc8;	// TAMIL VOWEL SIGN AI
341
	c = 0xbca;		// from TAMIL VOWEL SIGN O
342
	while (c <= 0xbcd)	// ..to TAMIL SIGN VIRAMA
343
		charset[i++] = c++;
344
	c = 0xbe6;		// from TAMIL DIGIT ZERO
345
	while (c <= 0xbfa)	// ..to TAMIL NUMBER SIGN
346
		charset[i++] = c++;
347
// 0C00..0C7F; Telugu
348
	c = 0xc00;		// from TELUGU SIGN COMBINING CANDRABINDU ABOVE
349
	while (c <= 0xc0c)	// ..to TELUGU LETTER VOCALIC L
350
		charset[i++] = c++;
351
	charset[i++] = 0xc0e;	// TELUGU LETTER E
352
	charset[i++] = 0xc10;	// TELUGU LETTER AI
353
	c = 0xc12;		// from TELUGU LETTER O
354
	while (c <= 0xc28)	// ..to TELUGU LETTER NA
355
		charset[i++] = c++;
356
	c = 0xc2a;		// from TELUGU LETTER PA
357
	while (c <= 0xc39)	// ..to TELUGU LETTER HA
358
		charset[i++] = c++;
359
	c = 0xc3d;		// from TELUGU SIGN AVAGRAHA
360
	while (c <= 0xc44)	// ..to TELUGU VOWEL SIGN VOCALIC RR
361
		charset[i++] = c++;
362
	charset[i++] = 0xc46;	// TELUGU VOWEL SIGN E
363
	charset[i++] = 0xc48;	// TELUGU VOWEL SIGN AI
364
	c = 0xc4a;		// from TELUGU VOWEL SIGN O
365
	while (c <= 0xc4d)	// ..to TELUGU SIGN VIRAMA
366
		charset[i++] = c++;
367
	charset[i++] = 0xc55;	// TELUGU LENGTH MARK
368
	charset[i++] = 0xc56;	// TELUGU AI LENGTH MARK
369
	charset[i++] = 0xc58;	// TELUGU LETTER TSA
370
	charset[i++] = 0xc5a;	// TELUGU LETTER RRRA
371
	c = 0xc60;		// from TELUGU LETTER VOCALIC RR
372
	while (c <= 0xc63)	// ..to TELUGU VOWEL SIGN VOCALIC LL
373
		charset[i++] = c++;
374
	c = 0xc66;		// from TELUGU DIGIT ZERO
375
	while (c <= 0xc6f)	// ..to TELUGU DIGIT NINE
376
		charset[i++] = c++;
377
	c = 0xc77;		// from TELUGU SIGN SIDDHAM
378
	while (c <= 0xc7f)	// ..to TELUGU SIGN TUUMU
379
		charset[i++] = c++;
380
// 0C80..0CFF; Kannada
381
	c = 0xc80;		// from KANNADA SIGN SPACING CANDRABINDU
382
	while (c <= 0xc8c)	// ..to KANNADA LETTER VOCALIC L
383
		charset[i++] = c++;
384
	charset[i++] = 0xc8e;	// KANNADA LETTER E
385
	charset[i++] = 0xc90;	// KANNADA LETTER AI
386
	c = 0xc92;		// from KANNADA LETTER O
387
	while (c <= 0xca8)	// ..to KANNADA LETTER NA
388
		charset[i++] = c++;
389
	c = 0xcaa;		// from KANNADA LETTER PA
390
	while (c <= 0xcb3)	// ..to KANNADA LETTER LLA
391
		charset[i++] = c++;
392
	c = 0xcb5;		// from KANNADA LETTER VA
393
	while (c <= 0xcb9)	// ..to KANNADA LETTER HA
394
		charset[i++] = c++;
395
	c = 0xcbc;		// from KANNADA SIGN NUKTA
396
	while (c <= 0xcc4)	// ..to KANNADA VOWEL SIGN VOCALIC RR
397
		charset[i++] = c++;
398
	charset[i++] = 0xcc6;	// KANNADA VOWEL SIGN E
399
	charset[i++] = 0xcc8;	// KANNADA VOWEL SIGN AI
400
	c = 0xcca;		// from KANNADA VOWEL SIGN O
401
	while (c <= 0xccd)	// ..to KANNADA SIGN VIRAMA
402
		charset[i++] = c++;
403
	charset[i++] = 0xcd5;	// KANNADA LENGTH MARK
404
	charset[i++] = 0xcd6;	// KANNADA AI LENGTH MARK
405
	c = 0xce0;		// from KANNADA LETTER VOCALIC RR
406
	while (c <= 0xce3)	// ..to KANNADA VOWEL SIGN VOCALIC LL
407
		charset[i++] = c++;
408
	c = 0xce6;		// from KANNADA DIGIT ZERO
409
	while (c <= 0xcef)	// ..to KANNADA DIGIT NINE
410
		charset[i++] = c++;
411
	charset[i++] = 0xcf1;	// KANNADA SIGN JIHVAMULIYA
412
	charset[i++] = 0xcf2;	// KANNADA SIGN UPADHMANIYA
413
// 0D00..0D7F; Malayalam
414
	c = 0xd00;		// from MALAYALAM SIGN COMBINING ANUSVARA ABOVE
415
	while (c <= 0xd0c)	// ..to MALAYALAM LETTER VOCALIC L
416
		charset[i++] = c++;
417
	charset[i++] = 0xd0e;	// MALAYALAM LETTER E
418
	charset[i++] = 0xd10;	// MALAYALAM LETTER AI
419
	c = 0xd12;		// from MALAYALAM LETTER O
420
	while (c <= 0xd44)	// ..to MALAYALAM VOWEL SIGN VOCALIC RR
421
		charset[i++] = c++;
422
	charset[i++] = 0xd46;	// MALAYALAM VOWEL SIGN E
423
	charset[i++] = 0xd48;	// MALAYALAM VOWEL SIGN AI
424
	c = 0xd4a;		// from MALAYALAM VOWEL SIGN O
425
	while (c <= 0xd4f)	// ..to MALAYALAM SIGN PARA
426
		charset[i++] = c++;
427
	c = 0xd54;		// from MALAYALAM LETTER CHILLU M
428
	while (c <= 0xd63)	// ..to MALAYALAM VOWEL SIGN VOCALIC LL
429
		charset[i++] = c++;
430
	c = 0xd66;		// from MALAYALAM DIGIT ZERO
431
	while (c <= 0xd7f)	// ..to MALAYALAM LETTER CHILLU K
432
		charset[i++] = c++;
433
// 0D80..0DFF; Sinhala
434
	charset[i++] = 0xd81;	// SINHALA SIGN CANDRABINDU
435
	charset[i++] = 0xd83;	// SINHALA SIGN VISARGAYA
436
	c = 0xd85;		// from SINHALA LETTER AYANNA
437
	while (c <= 0xd96)	// ..to SINHALA LETTER AUYANNA
438
		charset[i++] = c++;
439
	c = 0xd9a;		// from SINHALA LETTER ALPAPRAANA KAYANNA
440
	while (c <= 0xdb1)	// ..to SINHALA LETTER DANTAJA NAYANNA
441
		charset[i++] = c++;
442
	c = 0xdb3;		// from SINHALA LETTER SANYAKA DAYANNA
443
	while (c <= 0xdbb)	// ..to SINHALA LETTER RAYANNA
444
		charset[i++] = c++;
445
	c = 0xdc0;		// from SINHALA LETTER VAYANNA
446
	while (c <= 0xdc6)	// ..to SINHALA LETTER FAYANNA
447
		charset[i++] = c++;
448
	c = 0xdcf;		// from SINHALA VOWEL SIGN AELA-PILLA
449
	while (c <= 0xdd4)	// ..to SINHALA VOWEL SIGN KETTI PAA-PILLA
450
		charset[i++] = c++;
451
	c = 0xdd8;		// from SINHALA VOWEL SIGN GAETTA-PILLA
452
	while (c <= 0xddf)	// ..to SINHALA VOWEL SIGN GAYANUKITTA
453
		charset[i++] = c++;
454
	c = 0xde6;		// from SINHALA LITH DIGIT ZERO
455
	while (c <= 0xdef)	// ..to SINHALA LITH DIGIT NINE
456
		charset[i++] = c++;
457
	charset[i++] = 0xdf2;	// SINHALA VOWEL SIGN DIGA GAETTA-PILLA
458
	charset[i++] = 0xdf4;	// SINHALA PUNCTUATION KUNDDALIYA
459
// 0E00..0E7F; Thai
460
	c = 0xe01;		// from THAI CHARACTER KO KAI
461
	while (c <= 0xe3a)	// ..to THAI CHARACTER PHINTHU
462
		charset[i++] = c++;
463
	c = 0xe3f;		// from THAI CURRENCY SYMBOL BAHT
464
	while (c <= 0xe5b)	// ..to THAI CHARACTER KHOMUT
465
		charset[i++] = c++;
466
// 0E80..0EFF; Lao
467
	charset[i++] = 0xe81;	// LAO LETTER KO
468
	charset[i++] = 0xe82;	// LAO LETTER KHO SUNG
469
	c = 0xe86;		// from LAO LETTER PALI GHA
470
	while (c <= 0xe8a)	// ..to LAO LETTER SO TAM
471
		charset[i++] = c++;
472
	c = 0xe8c;		// from LAO LETTER PALI JHA
473
	while (c <= 0xea3)	// ..to LAO LETTER LO LING
474
		charset[i++] = c++;
475
	c = 0xea7;		// from LAO LETTER WO
476
	while (c <= 0xebd)	// ..to LAO SEMIVOWEL SIGN NYO
477
		charset[i++] = c++;
478
	c = 0xec0;		// from LAO VOWEL SIGN E
479
	while (c <= 0xec4)	// ..to LAO VOWEL SIGN AI
480
		charset[i++] = c++;
481
	c = 0xec8;		// from LAO TONE MAI EK
482
	while (c <= 0xecd)	// ..to LAO NIGGAHITA
483
		charset[i++] = c++;
484
	c = 0xed0;		// from LAO DIGIT ZERO
485
	while (c <= 0xed9)	// ..to LAO DIGIT NINE
486
		charset[i++] = c++;
487
	c = 0xedc;		// from LAO HO NO
488
	while (c <= 0xedf)	// ..to LAO LETTER KHMU NYO
489
		charset[i++] = c++;
490
// 0F00..0FFF; Tibetan
491
	c = 0xf00;		// from TIBETAN SYLLABLE OM
492
	while (c <= 0xf47)	// ..to TIBETAN LETTER JA
493
		charset[i++] = c++;
494
	c = 0xf49;		// from TIBETAN LETTER NYA
495
	while (c <= 0xf6c)	// ..to TIBETAN LETTER RRA
496
		charset[i++] = c++;
497
	c = 0xf71;		// from TIBETAN VOWEL SIGN AA
498
	while (c <= 0xf97)	// ..to TIBETAN SUBJOINED LETTER JA
499
		charset[i++] = c++;
500
	c = 0xf99;		// from TIBETAN SUBJOINED LETTER NYA
501
	while (c <= 0xfbc)	// ..to TIBETAN SUBJOINED LETTER FIXED-FORM RA
502
		charset[i++] = c++;
503
	c = 0xfbe;		// from TIBETAN KU RU KHA
504
	while (c <= 0xfcc)	// ..to TIBETAN SYMBOL NOR BU BZHI -KHYIL
505
		charset[i++] = c++;
506
	c = 0xfce;		// from TIBETAN SIGN RDEL NAG RDEL DKAR
507
	while (c <= 0xfda)	// ..to TIBETAN MARK TRAILING MCHAN RTAGS
508
		charset[i++] = c++;
509
// 1000..109F; Myanmar
510
	c = 0x1000;		// from MYANMAR LETTER KA
511
	while (c <= 0x109f)	// ..to MYANMAR SYMBOL SHAN EXCLAMATION
512
		charset[i++] = c++;
513
// 10A0..10FF; Georgian
514
	c = 0x10a0;		// from GEORGIAN CAPITAL LETTER AN
515
	while (c <= 0x10c5)	// ..to GEORGIAN CAPITAL LETTER HOE
516
		charset[i++] = c++;
517
	c = 0x10d0;		// from GEORGIAN LETTER AN
518
	while (c <= 0x10ff)	// ..to GEORGIAN LETTER LABIAL SIGN
519
		charset[i++] = c++;
520
// 1100..11FF; Hangul Jamo
521
	c = 0x1100;		// from HANGUL CHOSEONG KIYEOK
522
	while (c <= 0x11ff)	// ..to HANGUL JONGSEONG SSANGNIEUN
523
		charset[i++] = c++;
524
// 1200..137F; Ethiopic
525
	c = 0x1200;		// from ETHIOPIC SYLLABLE HA
526
	while (c <= 0x1248)	// ..to ETHIOPIC SYLLABLE QWA
527
		charset[i++] = c++;
528
	c = 0x124a;		// from ETHIOPIC SYLLABLE QWI
529
	while (c <= 0x124d)	// ..to ETHIOPIC SYLLABLE QWE
530
		charset[i++] = c++;
531
	c = 0x1250;		// from ETHIOPIC SYLLABLE QHA
532
	while (c <= 0x1256)	// ..to ETHIOPIC SYLLABLE QHO
533
		charset[i++] = c++;
534
	c = 0x125a;		// from ETHIOPIC SYLLABLE QHWI
535
	while (c <= 0x125d)	// ..to ETHIOPIC SYLLABLE QHWE
536
		charset[i++] = c++;
537
	c = 0x1260;		// from ETHIOPIC SYLLABLE BA
538
	while (c <= 0x1288)	// ..to ETHIOPIC SYLLABLE XWA
539
		charset[i++] = c++;
540
	c = 0x128a;		// from ETHIOPIC SYLLABLE XWI
541
	while (c <= 0x128d)	// ..to ETHIOPIC SYLLABLE XWE
542
		charset[i++] = c++;
543
	c = 0x1290;		// from ETHIOPIC SYLLABLE NA
544
	while (c <= 0x12b0)	// ..to ETHIOPIC SYLLABLE KWA
545
		charset[i++] = c++;
546
	c = 0x12b2;		// from ETHIOPIC SYLLABLE KWI
547
	while (c <= 0x12b5)	// ..to ETHIOPIC SYLLABLE KWE
548
		charset[i++] = c++;
549
	c = 0x12b8;		// from ETHIOPIC SYLLABLE KXA
550
	while (c <= 0x12be)	// ..to ETHIOPIC SYLLABLE KXO
551
		charset[i++] = c++;
552
	c = 0x12c2;		// from ETHIOPIC SYLLABLE KXWI
553
	while (c <= 0x12c5)	// ..to ETHIOPIC SYLLABLE KXWE
554
		charset[i++] = c++;
555
	c = 0x12c8;		// from ETHIOPIC SYLLABLE WA
556
	while (c <= 0x12d6)	// ..to ETHIOPIC SYLLABLE PHARYNGEAL O
557
		charset[i++] = c++;
558
	c = 0x12d8;		// from ETHIOPIC SYLLABLE ZA
559
	while (c <= 0x1310)	// ..to ETHIOPIC SYLLABLE GWA
560
		charset[i++] = c++;
561
	c = 0x1312;		// from ETHIOPIC SYLLABLE GWI
562
	while (c <= 0x1315)	// ..to ETHIOPIC SYLLABLE GWE
563
		charset[i++] = c++;
564
	c = 0x1318;		// from ETHIOPIC SYLLABLE GGA
565
	while (c <= 0x135a)	// ..to ETHIOPIC SYLLABLE FYA
566
		charset[i++] = c++;
567
	c = 0x135d;		// from ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK
568
	while (c <= 0x137c)	// ..to ETHIOPIC NUMBER TEN THOUSAND
569
		charset[i++] = c++;
570
// 1380..139F; Ethiopic Supplement
571
	c = 0x1380;		// from ETHIOPIC SYLLABLE SEBATBEIT MWA
572
	while (c <= 0x1399)	// ..to ETHIOPIC TONAL MARK KURT
573
		charset[i++] = c++;
574
// 13A0..13FF; Cherokee
575
	c = 0x13a0;		// from CHEROKEE LETTER A
576
	while (c <= 0x13f5)	// ..to CHEROKEE LETTER MV
577
		charset[i++] = c++;
578
	c = 0x13f8;		// from CHEROKEE SMALL LETTER YE
579
	while (c <= 0x13fd)	// ..to CHEROKEE SMALL LETTER MV
580
		charset[i++] = c++;
581
// 1400..167F; Unified Canadian Aboriginal Syllabics
582
	c = 0x1400;		// from CANADIAN SYLLABICS HYPHEN
583
	while (c <= 0x167f)	// ..to CANADIAN SYLLABICS BLACKFOOT W
584
		charset[i++] = c++;
585
// 1680..169F; Ogham
586
	c = 0x1680;		// from OGHAM SPACE MARK
587
	while (c <= 0x169c)	// ..to OGHAM REVERSED FEATHER MARK
588
		charset[i++] = c++;
589
// 16A0..16FF; Runic
590
	c = 0x16a0;		// from RUNIC LETTER FEHU FEOH FE F
591
	while (c <= 0x16f8)	// ..to RUNIC LETTER FRANKS CASKET AESC
592
		charset[i++] = c++;
593
// 1700..171F; Tagalog
594
	c = 0x1700;		// from TAGALOG LETTER A
595
	while (c <= 0x170c)	// ..to TAGALOG LETTER YA
596
		charset[i++] = c++;
597
	c = 0x170e;		// from TAGALOG LETTER LA
598
	while (c <= 0x1714)	// ..to TAGALOG SIGN VIRAMA
599
		charset[i++] = c++;
600
// 1720..173F; Hanunoo
601
	c = 0x1720;		// from HANUNOO LETTER A
602
	while (c <= 0x1736)	// ..to PHILIPPINE DOUBLE PUNCTUATION
603
		charset[i++] = c++;
604
// 1740..175F; Buhid
605
	c = 0x1740;		// from BUHID LETTER A
606
	while (c <= 0x1753)	// ..to BUHID VOWEL SIGN U
607
		charset[i++] = c++;
608
// 1760..177F; Tagbanwa
609
	c = 0x1760;		// from TAGBANWA LETTER A
610
	while (c <= 0x176c)	// ..to TAGBANWA LETTER YA
611
		charset[i++] = c++;
612
	charset[i++] = 0x176e;	// TAGBANWA LETTER LA
613
	charset[i++] = 0x1770;	// TAGBANWA LETTER SA
614
	charset[i++] = 0x1772;	// TAGBANWA VOWEL SIGN I
615
	charset[i++] = 0x1773;	// TAGBANWA VOWEL SIGN U
616
// 1780..17FF; Khmer
617
	c = 0x1780;		// from KHMER LETTER KA
618
	while (c <= 0x17dd)	// ..to KHMER SIGN ATTHACAN
619
		charset[i++] = c++;
620
	c = 0x17e0;		// from KHMER DIGIT ZERO
621
	while (c <= 0x17e9)	// ..to KHMER DIGIT NINE
622
		charset[i++] = c++;
623
	c = 0x17f0;		// from KHMER SYMBOL LEK ATTAK SON
624
	while (c <= 0x17f9)	// ..to KHMER SYMBOL LEK ATTAK PRAM-BUON
625
		charset[i++] = c++;
626
// 1800..18AF; Mongolian
627
	c = 0x1800;		// from MONGOLIAN BIRGA
628
	while (c <= 0x180e)	// ..to MONGOLIAN VOWEL SEPARATOR
629
		charset[i++] = c++;
630
	c = 0x1810;		// from MONGOLIAN DIGIT ZERO
631
	while (c <= 0x1819)	// ..to MONGOLIAN DIGIT NINE
632
		charset[i++] = c++;
633
	c = 0x1820;		// from MONGOLIAN LETTER A
634
	while (c <= 0x1878)	// ..to MONGOLIAN LETTER CHA WITH TWO DOTS
635
		charset[i++] = c++;
636
	c = 0x1880;		// from MONGOLIAN LETTER ALI GALI ANUSVARA ONE
637
	while (c <= 0x18aa)	// ..to MONGOLIAN LETTER MANCHU ALI GALI LHA
638
		charset[i++] = c++;
639
// 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
640
	c = 0x18b0;		// from CANADIAN SYLLABICS OY
641
	while (c <= 0x18f5)	// ..to CANADIAN SYLLABICS CARRIER DENTAL S
642
		charset[i++] = c++;
643
// 1900..194F; Limbu
644
	c = 0x1900;		// from LIMBU VOWEL-CARRIER LETTER
645
	while (c <= 0x191e)	// ..to LIMBU LETTER TRA
646
		charset[i++] = c++;
647
	c = 0x1920;		// from LIMBU VOWEL SIGN A
648
	while (c <= 0x192b)	// ..to LIMBU SUBJOINED LETTER WA
649
		charset[i++] = c++;
650
	c = 0x1930;		// from LIMBU SMALL LETTER KA
651
	while (c <= 0x193b)	// ..to LIMBU SIGN SA-I
652
		charset[i++] = c++;
653
	c = 0x1944;		// from LIMBU EXCLAMATION MARK
654
	while (c <= 0x194f)	// ..to LIMBU DIGIT NINE
655
		charset[i++] = c++;
656
// 1950..197F; Tai Le
657
	c = 0x1950;		// from TAI LE LETTER KA
658
	while (c <= 0x196d)	// ..to TAI LE LETTER AI
659
		charset[i++] = c++;
660
	c = 0x1970;		// from TAI LE LETTER TONE-2
661
	while (c <= 0x1974)	// ..to TAI LE LETTER TONE-6
662
		charset[i++] = c++;
663
// 1980..19DF; New Tai Lue
664
	c = 0x1980;		// from NEW TAI LUE LETTER HIGH QA
665
	while (c <= 0x19ab)	// ..to NEW TAI LUE LETTER LOW SUA
666
		charset[i++] = c++;
667
	c = 0x19b0;		// from NEW TAI LUE VOWEL SIGN VOWEL SHORTENER
668
	while (c <= 0x19c9)	// ..to NEW TAI LUE TONE MARK-2
669
		charset[i++] = c++;
670
	c = 0x19d0;		// from NEW TAI LUE DIGIT ZERO
671
	while (c <= 0x19da)	// ..to NEW TAI LUE THAM DIGIT ONE
672
		charset[i++] = c++;
673
	charset[i++] = 0x19de;	// NEW TAI LUE SIGN LAE
674
	charset[i++] = 0x19df;	// NEW TAI LUE SIGN LAEV
675
// 19E0..19FF; Khmer Symbols
676
	c = 0x19e0;		// from KHMER SYMBOL PATHAMASAT
677
	while (c <= 0x19ff)	// ..to KHMER SYMBOL DAP-PRAM ROC
678
		charset[i++] = c++;
679
// 1A00..1A1F; Buginese
680
	c = 0x1a00;		// from BUGINESE LETTER KA
681
	while (c <= 0x1a1b)	// ..to BUGINESE VOWEL SIGN AE
682
		charset[i++] = c++;
683
	charset[i++] = 0x1a1e;	// BUGINESE PALLAWA
684
	charset[i++] = 0x1a1f;	// BUGINESE END OF SECTION
685
// 1A20..1AAF; Tai Tham
686
	c = 0x1a20;		// from TAI THAM LETTER HIGH KA
687
	while (c <= 0x1a5e)	// ..to TAI THAM CONSONANT SIGN SA
688
		charset[i++] = c++;
689
	c = 0x1a60;		// from TAI THAM SIGN SAKOT
690
	while (c <= 0x1a7c)	// ..to TAI THAM SIGN KHUEN-LUE KARAN
691
		charset[i++] = c++;
692
	c = 0x1a7f;		// from TAI THAM COMBINING CRYPTOGRAMMIC DOT
693
	while (c <= 0x1a89)	// ..to TAI THAM HORA DIGIT NINE
694
		charset[i++] = c++;
695
	c = 0x1a90;		// from TAI THAM THAM DIGIT ZERO
696
	while (c <= 0x1a99)	// ..to TAI THAM THAM DIGIT NINE
697
		charset[i++] = c++;
698
	c = 0x1aa0;		// from TAI THAM SIGN WIANG
699
	while (c <= 0x1aad)	// ..to TAI THAM SIGN CAANG
700
		charset[i++] = c++;
701
// 1AB0..1AFF; Combining Diacritical Marks Extended
702
	c = 0x1ab0;		// from COMBINING DOUBLED CIRCUMFLEX ACCENT
703
	while (c <= 0x1ac0)	// ..to COMBINING LATIN SMALL LETTER TURNED W BELOW
704
		charset[i++] = c++;
705
// 1B00..1B7F; Balinese
706
	c = 0x1b00;		// from BALINESE SIGN ULU RICEM
707
	while (c <= 0x1b4b)	// ..to BALINESE LETTER ASYURA SASAK
708
		charset[i++] = c++;
709
	c = 0x1b50;		// from BALINESE DIGIT ZERO
710
	while (c <= 0x1b7c)	// ..to BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING
711
		charset[i++] = c++;
712
// 1B80..1BBF; Sundanese
713
	c = 0x1b80;		// from SUNDANESE SIGN PANYECEK
714
	while (c <= 0x1bbf)	// ..to SUNDANESE LETTER FINAL M
715
		charset[i++] = c++;
716
// 1BC0..1BFF; Batak
717
	c = 0x1bc0;		// from BATAK LETTER A
718
	while (c <= 0x1bf3)	// ..to BATAK PANONGONAN
719
		charset[i++] = c++;
720
	c = 0x1bfc;		// from BATAK SYMBOL BINDU NA METEK
721
	while (c <= 0x1bff)	// ..to BATAK SYMBOL BINDU PANGOLAT
722
		charset[i++] = c++;
723
// 1C00..1C4F; Lepcha
724
	c = 0x1c00;		// from LEPCHA LETTER KA
725
	while (c <= 0x1c37)	// ..to LEPCHA SIGN NUKTA
726
		charset[i++] = c++;
727
	c = 0x1c3b;		// from LEPCHA PUNCTUATION TA-ROL
728
	while (c <= 0x1c49)	// ..to LEPCHA DIGIT NINE
729
		charset[i++] = c++;
730
	charset[i++] = 0x1c4d;	// LEPCHA LETTER TTA
731
	charset[i++] = 0x1c4f;	// LEPCHA LETTER DDA
732
// 1C50..1C7F; Ol Chiki
733
	c = 0x1c50;		// from OL CHIKI DIGIT ZERO
734
	while (c <= 0x1c7f)	// ..to OL CHIKI PUNCTUATION DOUBLE MUCAAD
735
		charset[i++] = c++;
736
// 1C80..1C8F; Cyrillic Extended-C
737
	c = 0x1c80;		// from CYRILLIC SMALL LETTER ROUNDED VE
738
	while (c <= 0x1c88)	// ..to CYRILLIC SMALL LETTER UNBLENDED UK
739
		charset[i++] = c++;
740
// 1C90..1CBF; Georgian Extended
741
	c = 0x1c90;		// from GEORGIAN MTAVRULI CAPITAL LETTER AN
742
	while (c <= 0x1cba)	// ..to GEORGIAN MTAVRULI CAPITAL LETTER AIN
743
		charset[i++] = c++;
744
	charset[i++] = 0x1cbd;	// GEORGIAN MTAVRULI CAPITAL LETTER AEN
745
	charset[i++] = 0x1cbf;	// GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN
746
// 1CC0..1CCF; Sundanese Supplement
747
	c = 0x1cc0;		// from SUNDANESE PUNCTUATION BINDU SURYA
748
	while (c <= 0x1cc7)	// ..to SUNDANESE PUNCTUATION BINDU BA SATANGA
749
		charset[i++] = c++;
750
// 1CD0..1CFF; Vedic Extensions
751
	c = 0x1cd0;		// from VEDIC TONE KARSHANA
752
	while (c <= 0x1cfa)	// ..to VEDIC SIGN DOUBLE ANUSVARA ANTARGOMUKHA
753
		charset[i++] = c++;
754
// 1D00..1D7F; Phonetic Extensions
755
	c = 0x1d00;		// from LATIN LETTER SMALL CAPITAL A
756
	while (c <= 0x1d7f)	// ..to LATIN SMALL LETTER UPSILON WITH STROKE
757
		charset[i++] = c++;
758
// 1D80..1DBF; Phonetic Extensions Supplement
759
	c = 0x1d80;		// from LATIN SMALL LETTER B WITH PALATAL HOOK
760
	while (c <= 0x1dbf)	// ..to MODIFIER LETTER SMALL THETA
761
		charset[i++] = c++;
762
// 1DC0..1DFF; Combining Diacritical Marks Supplement
763
	c = 0x1dc0;		// from COMBINING DOTTED GRAVE ACCENT
764
	while (c <= 0x1df9)	// ..to COMBINING WIDE INVERTED BRIDGE BELOW
765
		charset[i++] = c++;
766
	c = 0x1dfb;		// from COMBINING DELETION MARK
767
	while (c <= 0x1dff)	// ..to COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
768
		charset[i++] = c++;
769
// 1E00..1EFF; Latin Extended Additional
770
	c = 0x1e00;		// from LATIN CAPITAL LETTER A WITH RING BELOW
771
	while (c <= 0x1eff)	// ..to LATIN SMALL LETTER Y WITH LOOP
772
		charset[i++] = c++;
773
// 1F00..1FFF; Greek Extended
774
	c = 0x1f00;		// from GREEK SMALL LETTER ALPHA WITH PSILI
775
	while (c <= 0x1f15)	// ..to GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
776
		charset[i++] = c++;
777
	c = 0x1f18;		// from GREEK CAPITAL LETTER EPSILON WITH PSILI
778
	while (c <= 0x1f1d)	// ..to GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
779
		charset[i++] = c++;
780
	c = 0x1f20;		// from GREEK SMALL LETTER ETA WITH PSILI
781
	while (c <= 0x1f45)	// ..to GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA
782
		charset[i++] = c++;
783
	c = 0x1f48;		// from GREEK CAPITAL LETTER OMICRON WITH PSILI
784
	while (c <= 0x1f4d)	// ..to GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA
785
		charset[i++] = c++;
786
	c = 0x1f50;		// from GREEK SMALL LETTER UPSILON WITH PSILI
787
	while (c <= 0x1f57)	// ..to GREEK SMALL LETTER UPSILON WITH DASIA AND PERISPOMENI
788
		charset[i++] = c++;
789
	c = 0x1f5f;		// from GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI
790
	while (c <= 0x1f7d)	// ..to GREEK SMALL LETTER OMEGA WITH OXIA
791
		charset[i++] = c++;
792
	c = 0x1f80;		// from GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
793
	while (c <= 0x1fb4)	// ..to GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
794
		charset[i++] = c++;
795
	c = 0x1fb6;		// from GREEK SMALL LETTER ALPHA WITH PERISPOMENI
796
	while (c <= 0x1fc4)	// ..to GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
797
		charset[i++] = c++;
798
	c = 0x1fc6;		// from GREEK SMALL LETTER ETA WITH PERISPOMENI
799
	while (c <= 0x1fd3)	// ..to GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
800
		charset[i++] = c++;
801
	c = 0x1fd6;		// from GREEK SMALL LETTER IOTA WITH PERISPOMENI
802
	while (c <= 0x1fdb)	// ..to GREEK CAPITAL LETTER IOTA WITH OXIA
803
		charset[i++] = c++;
804
	c = 0x1fdd;		// from GREEK DASIA AND VARIA
805
	while (c <= 0x1fef)	// ..to GREEK VARIA
806
		charset[i++] = c++;
807
	charset[i++] = 0x1ff2;	// GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
808
	charset[i++] = 0x1ff4;	// GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
809
	c = 0x1ff6;		// from GREEK SMALL LETTER OMEGA WITH PERISPOMENI
810
	while (c <= 0x1ffe)	// ..to GREEK DASIA
811
		charset[i++] = c++;
812
// 2000..206F; General Punctuation
813
	c = 0x2000;		// from EN QUAD
814
	while (c <= 0x2064)	// ..to INVISIBLE PLUS
815
		charset[i++] = c++;
816
	c = 0x2066;		// from LEFT-TO-RIGHT ISOLATE
817
	while (c <= 0x206f)	// ..to NOMINAL DIGIT SHAPES
818
		charset[i++] = c++;
819
// 2070..209F; Superscripts and Subscripts
820
	charset[i++] = 0x2070;	// SUPERSCRIPT ZERO
821
	charset[i++] = 0x2071;	// SUPERSCRIPT LATIN SMALL LETTER I
822
	c = 0x2074;		// from SUPERSCRIPT FOUR
823
	while (c <= 0x208e)	// ..to SUBSCRIPT RIGHT PARENTHESIS
824
		charset[i++] = c++;
825
	c = 0x2090;		// from LATIN SUBSCRIPT SMALL LETTER A
826
	while (c <= 0x209c)	// ..to LATIN SUBSCRIPT SMALL LETTER T
827
		charset[i++] = c++;
828
// 20A0..20CF; Currency Symbols
829
	c = 0x20a0;		// from EURO-CURRENCY SIGN
830
	while (c <= 0x20bf)	// ..to BITCOIN SIGN
831
		charset[i++] = c++;
832
// 20D0..20FF; Combining Diacritical Marks for Symbols
833
	c = 0x20d0;		// from COMBINING LEFT HARPOON ABOVE
834
	while (c <= 0x20f0)	// ..to COMBINING ASTERISK ABOVE
835
		charset[i++] = c++;
836
// 2100..214F; Letterlike Symbols
837
	c = 0x2100;		// from ACCOUNT OF
838
	while (c <= 0x214f)	// ..to SYMBOL FOR SAMARITAN SOURCE
839
		charset[i++] = c++;
840
// 2150..218F; Number Forms
841
	c = 0x2150;		// from VULGAR FRACTION ONE SEVENTH
842
	while (c <= 0x218b)	// ..to TURNED DIGIT THREE
843
		charset[i++] = c++;
844
// 2190..21FF; Arrows
845
	c = 0x2190;		// from LEFTWARDS ARROW
846
	while (c <= 0x21ff)	// ..to LEFT RIGHT OPEN-HEADED ARROW
847
		charset[i++] = c++;
848
// 2200..22FF; Mathematical Operators
849
	c = 0x2200;		// from FOR ALL
850
	while (c <= 0x22ff)	// ..to Z NOTATION BAG MEMBERSHIP
851
		charset[i++] = c++;
852
// 2300..23FF; Miscellaneous Technical
853
	c = 0x2300;		// from DIAMETER SIGN
854
	while (c <= 0x23ff)	// ..to OBSERVER EYE SYMBOL
855
		charset[i++] = c++;
856
// 2400..243F; Control Pictures
857
	c = 0x2400;		// from SYMBOL FOR NULL
858
	while (c <= 0x2426)	// ..to SYMBOL FOR SUBSTITUTE FORM TWO
859
		charset[i++] = c++;
860
// 2440..245F; Optical Character Recognition
861
	c = 0x2440;		// from OCR HOOK
862
	while (c <= 0x244a)	// ..to OCR DOUBLE BACKSLASH
863
		charset[i++] = c++;
864
// 2460..24FF; Enclosed Alphanumerics
865
	c = 0x2460;		// from CIRCLED DIGIT ONE
866
	while (c <= 0x24ff)	// ..to NEGATIVE CIRCLED DIGIT ZERO
867
		charset[i++] = c++;
868
// 2500..257F; Box Drawing
869
	c = 0x2500;		// from BOX DRAWINGS LIGHT HORIZONTAL
870
	while (c <= 0x257f)	// ..to BOX DRAWINGS HEAVY UP AND LIGHT DOWN
871
		charset[i++] = c++;
872
// 2580..259F; Block Elements
873
	c = 0x2580;		// from UPPER HALF BLOCK
874
	while (c <= 0x259f)	// ..to QUADRANT UPPER RIGHT AND LOWER LEFT AND LOWER RIGHT
875
		charset[i++] = c++;
876
// 25A0..25FF; Geometric Shapes
877
	c = 0x25a0;		// from BLACK SQUARE
878
	while (c <= 0x25ff)	// ..to LOWER RIGHT TRIANGLE
879
		charset[i++] = c++;
880
// 2600..26FF; Miscellaneous Symbols
881
	c = 0x2600;		// from BLACK SUN WITH RAYS
882
	while (c <= 0x26ff)	// ..to WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE
883
		charset[i++] = c++;
884
// 2700..27BF; Dingbats
885
	c = 0x2700;		// from BLACK SAFETY SCISSORS
886
	while (c <= 0x27bf)	// ..to DOUBLE CURLY LOOP
887
		charset[i++] = c++;
888
// 27C0..27EF; Miscellaneous Mathematical Symbols-A
889
	c = 0x27c0;		// from THREE DIMENSIONAL ANGLE
890
	while (c <= 0x27ef)	// ..to MATHEMATICAL RIGHT FLATTENED PARENTHESIS
891
		charset[i++] = c++;
892
// 27F0..27FF; Supplemental Arrows-A
893
	c = 0x27f0;		// from UPWARDS QUADRUPLE ARROW
894
	while (c <= 0x27ff)	// ..to LONG RIGHTWARDS SQUIGGLE ARROW
895
		charset[i++] = c++;
896
// 2800..28FF; Braille Patterns
897
	c = 0x2800;		// from BRAILLE PATTERN BLANK
898
	while (c <= 0x28ff)	// ..to BRAILLE PATTERN DOTS-12345678
899
		charset[i++] = c++;
900
// 2900..297F; Supplemental Arrows-B
901
	c = 0x2900;		// from RIGHTWARDS TWO-HEADED ARROW WITH VERTICAL STROKE
902
	while (c <= 0x297f)	// ..to DOWN FISH TAIL
903
		charset[i++] = c++;
904
// 2980..29FF; Miscellaneous Mathematical Symbols-B
905
	c = 0x2980;		// from TRIPLE VERTICAL BAR DELIMITER
906
	while (c <= 0x29ff)	// ..to MINY
907
		charset[i++] = c++;
908
// 2A00..2AFF; Supplemental Mathematical Operators
909
	c = 0x2a00;		// from N-ARY CIRCLED DOT OPERATOR
910
	while (c <= 0x2aff)	// ..to N-ARY WHITE VERTICAL BAR
911
		charset[i++] = c++;
912
// 2B00..2BFF; Miscellaneous Symbols and Arrows
913
	c = 0x2b00;		// from NORTH EAST WHITE ARROW
914
	while (c <= 0x2b73)	// ..to DOWNWARDS TRIANGLE-HEADED ARROW TO BAR
915
		charset[i++] = c++;
916
	c = 0x2b76;		// from NORTH WEST TRIANGLE-HEADED ARROW TO BAR
917
	while (c <= 0x2b95)	// ..to RIGHTWARDS BLACK ARROW
918
		charset[i++] = c++;
919
	c = 0x2b97;		// from SYMBOL FOR TYPE A ELECTRONICS
920
	while (c <= 0x2bff)	// ..to HELLSCHREIBER PAUSE SYMBOL
921
		charset[i++] = c++;
922
// 2C00..2C5F; Glagolitic
923
	c = 0x2c00;		// from GLAGOLITIC CAPITAL LETTER AZU
924
	while (c <= 0x2c2e)	// ..to GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
925
		charset[i++] = c++;
926
	c = 0x2c30;		// from GLAGOLITIC SMALL LETTER AZU
927
	while (c <= 0x2c5e)	// ..to GLAGOLITIC SMALL LETTER LATINATE MYSLITE
928
		charset[i++] = c++;
929
// 2C60..2C7F; Latin Extended-C
930
	c = 0x2c60;		// from LATIN CAPITAL LETTER L WITH DOUBLE BAR
931
	while (c <= 0x2c7f)	// ..to LATIN CAPITAL LETTER Z WITH SWASH TAIL
932
		charset[i++] = c++;
933
// 2C80..2CFF; Coptic
934
	c = 0x2c80;		// from COPTIC CAPITAL LETTER ALFA
935
	while (c <= 0x2cf3)	// ..to COPTIC SMALL LETTER BOHAIRIC KHEI
936
		charset[i++] = c++;
937
	c = 0x2cf9;		// from COPTIC OLD NUBIAN FULL STOP
938
	while (c <= 0x2cff)	// ..to COPTIC MORPHOLOGICAL DIVIDER
939
		charset[i++] = c++;
940
// 2D00..2D2F; Georgian Supplement
941
	c = 0x2d00;		// from GEORGIAN SMALL LETTER AN
942
	while (c <= 0x2d25)	// ..to GEORGIAN SMALL LETTER HOE
943
		charset[i++] = c++;
944
	c = 0x2d27;		// from GEORGIAN SMALL LETTER YN
945
	while (c <= 0x2d2d)	// ..to GEORGIAN SMALL LETTER AEN
946
		charset[i++] = c++;
947
// 2D30..2D7F; Tifinagh
948
	c = 0x2d30;		// from TIFINAGH LETTER YA
949
	while (c <= 0x2d67)	// ..to TIFINAGH LETTER YO
950
		charset[i++] = c++;
951
	charset[i++] = 0x2d6f;	// TIFINAGH MODIFIER LETTER LABIALIZATION MARK
952
	charset[i++] = 0x2d70;	// TIFINAGH SEPARATOR MARK
953
	charset[i++] = 0x2d7f;	// TIFINAGH CONSONANT JOINER
954
// 2D80..2DDF; Ethiopic Extended
955
	c = 0x2d80;		// from ETHIOPIC SYLLABLE LOA
956
	while (c <= 0x2d96)	// ..to ETHIOPIC SYLLABLE GGWE
957
		charset[i++] = c++;
958
	c = 0x2da0;		// from ETHIOPIC SYLLABLE SSA
959
	while (c <= 0x2da6)	// ..to ETHIOPIC SYLLABLE SSO
960
		charset[i++] = c++;
961
	c = 0x2da8;		// from ETHIOPIC SYLLABLE CCA
962
	while (c <= 0x2dae)	// ..to ETHIOPIC SYLLABLE CCO
963
		charset[i++] = c++;
964
	c = 0x2db0;		// from ETHIOPIC SYLLABLE ZZA
965
	while (c <= 0x2db6)	// ..to ETHIOPIC SYLLABLE ZZO
966
		charset[i++] = c++;
967
	c = 0x2db8;		// from ETHIOPIC SYLLABLE CCHA
968
	while (c <= 0x2dbe)	// ..to ETHIOPIC SYLLABLE CCHO
969
		charset[i++] = c++;
970
	c = 0x2dc0;		// from ETHIOPIC SYLLABLE QYA
971
	while (c <= 0x2dc6)	// ..to ETHIOPIC SYLLABLE QYO
972
		charset[i++] = c++;
973
	c = 0x2dc8;		// from ETHIOPIC SYLLABLE KYA
974
	while (c <= 0x2dce)	// ..to ETHIOPIC SYLLABLE KYO
975
		charset[i++] = c++;
976
	c = 0x2dd0;		// from ETHIOPIC SYLLABLE XYA
977
	while (c <= 0x2dd6)	// ..to ETHIOPIC SYLLABLE XYO
978
		charset[i++] = c++;
979
	c = 0x2dd8;		// from ETHIOPIC SYLLABLE GYA
980
	while (c <= 0x2dde)	// ..to ETHIOPIC SYLLABLE GYO
981
		charset[i++] = c++;
982
// 2DE0..2DFF; Cyrillic Extended-A
983
	c = 0x2de0;		// from COMBINING CYRILLIC LETTER BE
984
	while (c <= 0x2dff)	// ..to COMBINING CYRILLIC LETTER IOTIFIED BIG YUS
985
		charset[i++] = c++;
986
// 2E00..2E7F; Supplemental Punctuation
987
	c = 0x2e00;		// from RIGHT ANGLE SUBSTITUTION MARKER
988
	while (c <= 0x2e52)	// ..to TIRONIAN SIGN CAPITAL ET
989
		charset[i++] = c++;
990
// 2E80..2EFF; CJK Radicals Supplement
991
	c = 0x2e80;		// from CJK RADICAL REPEAT
992
	while (c <= 0x2e99)	// ..to CJK RADICAL RAP
993
		charset[i++] = c++;
994
	c = 0x2e9b;		// from CJK RADICAL CHOKE
995
	while (c <= 0x2ef3)	// ..to CJK RADICAL C-SIMPLIFIED TURTLE
996
		charset[i++] = c++;
997
// 2F00..2FDF; Kangxi Radicals
998
	c = 0x2f00;		// from KANGXI RADICAL ONE
999
	while (c <= 0x2fd5)	// ..to KANGXI RADICAL FLUTE
1000
		charset[i++] = c++;
1001
// 2FF0..2FFF; Ideographic Description Characters
1002
	c = 0x2ff0;		// from IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT
1003
	while (c <= 0x2ffb)	// ..to IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
1004
		charset[i++] = c++;
1005
// 3000..303F; CJK Symbols and Punctuation
1006
	c = 0x3000;		// from IDEOGRAPHIC SPACE
1007
	while (c <= 0x303f)	// ..to IDEOGRAPHIC HALF FILL SPACE
1008
		charset[i++] = c++;
1009
// 3040..309F; Hiragana
1010
	c = 0x3041;		// from HIRAGANA LETTER SMALL A
1011
	while (c <= 0x3096)	// ..to HIRAGANA LETTER SMALL KE
1012
		charset[i++] = c++;
1013
	c = 0x3099;		// from COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK
1014
	while (c <= 0x309f)	// ..to HIRAGANA DIGRAPH YORI
1015
		charset[i++] = c++;
1016
// 30A0..30FF; Katakana
1017
	c = 0x30a0;		// from KATAKANA-HIRAGANA DOUBLE HYPHEN
1018
	while (c <= 0x30ff)	// ..to KATAKANA DIGRAPH KOTO
1019
		charset[i++] = c++;
1020
// 3100..312F; Bopomofo
1021
	c = 0x3105;		// from BOPOMOFO LETTER B
1022
	while (c <= 0x312f)	// ..to BOPOMOFO LETTER NN
1023
		charset[i++] = c++;
1024
// 3130..318F; Hangul Compatibility Jamo
1025
	c = 0x3131;		// from HANGUL LETTER KIYEOK
1026
	while (c <= 0x318e)	// ..to HANGUL LETTER ARAEAE
1027
		charset[i++] = c++;
1028
// 3190..319F; Kanbun
1029
	c = 0x3190;		// from IDEOGRAPHIC ANNOTATION LINKING MARK
1030
	while (c <= 0x319f)	// ..to IDEOGRAPHIC ANNOTATION MAN MARK
1031
		charset[i++] = c++;
1032
// 31A0..31BF; Bopomofo Extended
1033
	c = 0x31a0;		// from BOPOMOFO LETTER BU
1034
	while (c <= 0x31bf)	// ..to BOPOMOFO LETTER AH
1035
		charset[i++] = c++;
1036
// 31C0..31EF; CJK Strokes
1037
	c = 0x31c0;		// from CJK STROKE T
1038
	while (c <= 0x31e3)	// ..to CJK STROKE Q
1039
		charset[i++] = c++;
1040
// 31F0..31FF; Katakana Phonetic Extensions
1041
	c = 0x31f0;		// from KATAKANA LETTER SMALL KU
1042
	while (c <= 0x31ff)	// ..to KATAKANA LETTER SMALL RO
1043
		charset[i++] = c++;
1044
// 3200..32FF; Enclosed CJK Letters and Months
1045
	c = 0x3200;		// from PARENTHESIZED HANGUL KIYEOK
1046
	while (c <= 0x321e)	// ..to PARENTHESIZED KOREAN CHARACTER O HU
1047
		charset[i++] = c++;
1048
	c = 0x3220;		// from PARENTHESIZED IDEOGRAPH ONE
1049
	while (c <= 0x32ff)	// ..to SQUARE ERA NAME REIWA
1050
		charset[i++] = c++;
1051
// 3300..33FF; CJK Compatibility
1052
	c = 0x3300;		// from SQUARE APAATO
1053
	while (c <= 0x33ff)	// ..to SQUARE GAL
1054
		charset[i++] = c++;
1055
// 3400..4DBF; CJK Unified Ideographs Extension A
1056
	c = 0x3400;		// from <CJK Ideograph Extension A, First>
1057
	while (c <= 0x4dbf)	// ..to <CJK Ideograph Extension A, Last>
1058
		charset[i++] = c++;
1059
// 4DC0..4DFF; Yijing Hexagram Symbols
1060
	c = 0x4dc0;		// from HEXAGRAM FOR THE CREATIVE HEAVEN
1061
	while (c <= 0x4dff)	// ..to HEXAGRAM FOR BEFORE COMPLETION
1062
		charset[i++] = c++;
1063
// 4E00..9FFF; CJK Unified Ideographs
1064
	c = 0x4e00;		// from <CJK Ideograph, First>
1065
	while (c <= 0x9ffc)	// ..to <CJK Ideograph, Last>
1066
		charset[i++] = c++;
1067
// A000..A48F; Yi Syllables
1068
	c = 0xa000;		// from YI SYLLABLE IT
1069
	while (c <= 0xa48c)	// ..to YI SYLLABLE YYR
1070
		charset[i++] = c++;
1071
// A490..A4CF; Yi Radicals
1072
	c = 0xa490;		// from YI RADICAL QOT
1073
	while (c <= 0xa4c6)	// ..to YI RADICAL KE
1074
		charset[i++] = c++;
1075
// A4D0..A4FF; Lisu
1076
	c = 0xa4d0;		// from LISU LETTER BA
1077
	while (c <= 0xa4ff)	// ..to LISU PUNCTUATION FULL STOP
1078
		charset[i++] = c++;
1079
// A500..A63F; Vai
1080
	c = 0xa500;		// from VAI SYLLABLE EE
1081
	while (c <= 0xa62b)	// ..to VAI SYLLABLE NDOLE DO
1082
		charset[i++] = c++;
1083
// A640..A69F; Cyrillic Extended-B
1084
	c = 0xa640;		// from CYRILLIC CAPITAL LETTER ZEMLYA
1085
	while (c <= 0xa69f)	// ..to COMBINING CYRILLIC LETTER IOTIFIED E
1086
		charset[i++] = c++;
1087
// A6A0..A6FF; Bamum
1088
	c = 0xa6a0;		// from BAMUM LETTER A
1089
	while (c <= 0xa6f7)	// ..to BAMUM QUESTION MARK
1090
		charset[i++] = c++;
1091
// A700..A71F; Modifier Tone Letters
1092
	c = 0xa700;		// from MODIFIER LETTER CHINESE TONE YIN PING
1093
	while (c <= 0xa71f)	// ..to MODIFIER LETTER LOW INVERTED EXCLAMATION MARK
1094
		charset[i++] = c++;
1095
// A720..A7FF; Latin Extended-D
1096
	c = 0xa720;		// from MODIFIER LETTER STRESS AND HIGH TONE
1097
	while (c <= 0xa7bf)	// ..to LATIN SMALL LETTER GLOTTAL U
1098
		charset[i++] = c++;
1099
	c = 0xa7c2;		// from LATIN CAPITAL LETTER ANGLICANA W
1100
	while (c <= 0xa7ca)	// ..to LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY
1101
		charset[i++] = c++;
1102
	c = 0xa7f5;		// from LATIN CAPITAL LETTER REVERSED HALF H
1103
	while (c <= 0xa7ff)	// ..to LATIN EPIGRAPHIC LETTER ARCHAIC M
1104
		charset[i++] = c++;
1105
// A800..A82F; Syloti Nagri
1106
	c = 0xa800;		// from SYLOTI NAGRI LETTER A
1107
	while (c <= 0xa82c)	// ..to SYLOTI NAGRI SIGN ALTERNATE HASANTA
1108
		charset[i++] = c++;
1109
// A830..A83F; Common Indic Number Forms
1110
	c = 0xa830;		// from NORTH INDIC FRACTION ONE QUARTER
1111
	while (c <= 0xa839)	// ..to NORTH INDIC QUANTITY MARK
1112
		charset[i++] = c++;
1113
// A840..A87F; Phags-pa
1114
	c = 0xa840;		// from PHAGS-PA LETTER KA
1115
	while (c <= 0xa877)	// ..to PHAGS-PA MARK DOUBLE SHAD
1116
		charset[i++] = c++;
1117
// A880..A8DF; Saurashtra
1118
	c = 0xa880;		// from SAURASHTRA SIGN ANUSVARA
1119
	while (c <= 0xa8c5)	// ..to SAURASHTRA SIGN CANDRABINDU
1120
		charset[i++] = c++;
1121
	c = 0xa8ce;		// from SAURASHTRA DANDA
1122
	while (c <= 0xa8d9)	// ..to SAURASHTRA DIGIT NINE
1123
		charset[i++] = c++;
1124
// A8E0..A8FF; Devanagari Extended
1125
	c = 0xa8e0;		// from COMBINING DEVANAGARI DIGIT ZERO
1126
	while (c <= 0xa8ff)	// ..to DEVANAGARI VOWEL SIGN AY
1127
		charset[i++] = c++;
1128
// A900..A92F; Kayah Li
1129
	c = 0xa900;		// from KAYAH LI DIGIT ZERO
1130
	while (c <= 0xa92f)	// ..to KAYAH LI SIGN SHYA
1131
		charset[i++] = c++;
1132
// A930..A95F; Rejang
1133
	c = 0xa930;		// from REJANG LETTER KA
1134
	while (c <= 0xa953)	// ..to REJANG VIRAMA
1135
		charset[i++] = c++;
1136
	charset[i++] = 0xa95f;	// REJANG SECTION MARK
1137
// A960..A97F; Hangul Jamo Extended-A
1138
	c = 0xa960;		// from HANGUL CHOSEONG TIKEUT-MIEUM
1139
	while (c <= 0xa97c)	// ..to HANGUL CHOSEONG SSANGYEORINHIEUH
1140
		charset[i++] = c++;
1141
// A980..A9DF; Javanese
1142
	c = 0xa980;		// from JAVANESE SIGN PANYANGGA
1143
	while (c <= 0xa9cd)	// ..to JAVANESE TURNED PADA PISELEH
1144
		charset[i++] = c++;
1145
	c = 0xa9cf;		// from JAVANESE PANGRANGKEP
1146
	while (c <= 0xa9d9)	// ..to JAVANESE DIGIT NINE
1147
		charset[i++] = c++;
1148
	charset[i++] = 0xa9de;	// JAVANESE PADA TIRTA TUMETES
1149
	charset[i++] = 0xa9df;	// JAVANESE PADA ISEN-ISEN
1150
// A9E0..A9FF; Myanmar Extended-B
1151
	c = 0xa9e0;		// from MYANMAR LETTER SHAN GHA
1152
	while (c <= 0xa9fe)	// ..to MYANMAR LETTER TAI LAING BHA
1153
		charset[i++] = c++;
1154
// AA00..AA5F; Cham
1155
	c = 0xaa00;		// from CHAM LETTER A
1156
	while (c <= 0xaa36)	// ..to CHAM CONSONANT SIGN WA
1157
		charset[i++] = c++;
1158
	c = 0xaa40;		// from CHAM LETTER FINAL K
1159
	while (c <= 0xaa4d)	// ..to CHAM CONSONANT SIGN FINAL H
1160
		charset[i++] = c++;
1161
	c = 0xaa50;		// from CHAM DIGIT ZERO
1162
	while (c <= 0xaa59)	// ..to CHAM DIGIT NINE
1163
		charset[i++] = c++;
1164
	c = 0xaa5c;		// from CHAM PUNCTUATION SPIRAL
1165
	while (c <= 0xaa5f)	// ..to CHAM PUNCTUATION TRIPLE DANDA
1166
		charset[i++] = c++;
1167
// AA60..AA7F; Myanmar Extended-A
1168
	c = 0xaa60;		// from MYANMAR LETTER KHAMTI GA
1169
	while (c <= 0xaa7f)	// ..to MYANMAR LETTER SHWE PALAUNG SHA
1170
		charset[i++] = c++;
1171
// AA80..AADF; Tai Viet
1172
	c = 0xaa80;		// from TAI VIET LETTER LOW KO
1173
	while (c <= 0xaac2)	// ..to TAI VIET TONE MAI SONG
1174
		charset[i++] = c++;
1175
	c = 0xaadb;		// from TAI VIET SYMBOL KON
1176
	while (c <= 0xaadf)	// ..to TAI VIET SYMBOL KOI KOI
1177
		charset[i++] = c++;
1178
// AAE0..AAFF; Meetei Mayek Extensions
1179
	c = 0xaae0;		// from MEETEI MAYEK LETTER E
1180
	while (c <= 0xaaf6)	// ..to MEETEI MAYEK VIRAMA
1181
		charset[i++] = c++;
1182
// AB00..AB2F; Ethiopic Extended-A
1183
	c = 0xab01;		// from ETHIOPIC SYLLABLE TTHU
1184
	while (c <= 0xab06)	// ..to ETHIOPIC SYLLABLE TTHO
1185
		charset[i++] = c++;
1186
	c = 0xab09;		// from ETHIOPIC SYLLABLE DDHU
1187
	while (c <= 0xab0e)	// ..to ETHIOPIC SYLLABLE DDHO
1188
		charset[i++] = c++;
1189
	c = 0xab11;		// from ETHIOPIC SYLLABLE DZU
1190
	while (c <= 0xab16)	// ..to ETHIOPIC SYLLABLE DZO
1191
		charset[i++] = c++;
1192
	c = 0xab20;		// from ETHIOPIC SYLLABLE CCHHA
1193
	while (c <= 0xab26)	// ..to ETHIOPIC SYLLABLE CCHHO
1194
		charset[i++] = c++;
1195
	c = 0xab28;		// from ETHIOPIC SYLLABLE BBA
1196
	while (c <= 0xab2e)	// ..to ETHIOPIC SYLLABLE BBO
1197
		charset[i++] = c++;
1198
// AB30..AB6F; Latin Extended-E
1199
	c = 0xab30;		// from LATIN SMALL LETTER BARRED ALPHA
1200
	while (c <= 0xab6b)	// ..to MODIFIER LETTER RIGHT TACK
1201
		charset[i++] = c++;
1202
// AB70..ABBF; Cherokee Supplement
1203
	c = 0xab70;		// from CHEROKEE SMALL LETTER A
1204
	while (c <= 0xabbf)	// ..to CHEROKEE SMALL LETTER YA
1205
		charset[i++] = c++;
1206
// ABC0..ABFF; Meetei Mayek
1207
	c = 0xabc0;		// from MEETEI MAYEK LETTER KOK
1208
	while (c <= 0xabed)	// ..to MEETEI MAYEK APUN IYEK
1209
		charset[i++] = c++;
1210
	c = 0xabf0;		// from MEETEI MAYEK DIGIT ZERO
1211
	while (c <= 0xabf9)	// ..to MEETEI MAYEK DIGIT NINE
1212
		charset[i++] = c++;
1213
// AC00..D7AF; Hangul Syllables
1214
	c = 0xac00;		// from <Hangul Syllable, First>
1215
	while (c <= 0xd7a3)	// ..to <Hangul Syllable, Last>
1216
		charset[i++] = c++;
1217
// D7B0..D7FF; Hangul Jamo Extended-B
1218
	c = 0xd7b0;		// from HANGUL JUNGSEONG O-YEO
1219
	while (c <= 0xd7c6)	// ..to HANGUL JUNGSEONG ARAEA-E
1220
		charset[i++] = c++;
1221
	c = 0xd7cb;		// from HANGUL JONGSEONG NIEUN-RIEUL
1222
	while (c <= 0xd7fb)	// ..to HANGUL JONGSEONG PHIEUPH-THIEUTH
1223
		charset[i++] = c++;
1224
// D800..DB7F; High Surrogates
1225
// DB80..DBFF; High Private Use Surrogates
1226
// DC00..DFFF; Low Surrogates
1227
// E000..F8FF; Private Use Area
1228
// F900..FAFF; CJK Compatibility Ideographs
1229
	c = 0xf900;		// from CJK COMPATIBILITY IDEOGRAPH-F900
1230
	while (c <= 0xfa6d)	// ..to CJK COMPATIBILITY IDEOGRAPH-FA6D
1231
		charset[i++] = c++;
1232
	c = 0xfa70;		// from CJK COMPATIBILITY IDEOGRAPH-FA70
1233
	while (c <= 0xfad9)	// ..to CJK COMPATIBILITY IDEOGRAPH-FAD9
1234
		charset[i++] = c++;
1235
// FB00..FB4F; Alphabetic Presentation Forms
1236
	c = 0xfb00;		// from LATIN SMALL LIGATURE FF
1237
	while (c <= 0xfb06)	// ..to LATIN SMALL LIGATURE ST
1238
		charset[i++] = c++;
1239
	c = 0xfb13;		// from ARMENIAN SMALL LIGATURE MEN NOW
1240
	while (c <= 0xfb17)	// ..to ARMENIAN SMALL LIGATURE MEN XEH
1241
		charset[i++] = c++;
1242
	c = 0xfb1d;		// from HEBREW LETTER YOD WITH HIRIQ
1243
	while (c <= 0xfb36)	// ..to HEBREW LETTER ZAYIN WITH DAGESH
1244
		charset[i++] = c++;
1245
	c = 0xfb38;		// from HEBREW LETTER TET WITH DAGESH
1246
	while (c <= 0xfb3c)	// ..to HEBREW LETTER LAMED WITH DAGESH
1247
		charset[i++] = c++;
1248
	charset[i++] = 0xfb40;	// HEBREW LETTER NUN WITH DAGESH
1249
	charset[i++] = 0xfb41;	// HEBREW LETTER SAMEKH WITH DAGESH
1250
	charset[i++] = 0xfb43;	// HEBREW LETTER FINAL PE WITH DAGESH
1251
	charset[i++] = 0xfb44;	// HEBREW LETTER PE WITH DAGESH
1252
	c = 0xfb46;		// from HEBREW LETTER TSADI WITH DAGESH
1253
	while (c <= 0xfb4f)	// ..to HEBREW LIGATURE ALEF LAMED
1254
		charset[i++] = c++;
1255
// FB50..FDFF; Arabic Presentation Forms-A
1256
	c = 0xfb50;		// from ARABIC LETTER ALEF WASLA ISOLATED FORM
1257
	while (c <= 0xfbc1)	// ..to ARABIC SYMBOL SMALL TAH BELOW
1258
		charset[i++] = c++;
1259
	c = 0xfbd3;		// from ARABIC LETTER NG ISOLATED FORM
1260
	while (c <= 0xfd3f)	// ..to ORNATE RIGHT PARENTHESIS
1261
		charset[i++] = c++;
1262
	c = 0xfd50;		// from ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM
1263
	while (c <= 0xfd8f)	// ..to ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM
1264
		charset[i++] = c++;
1265
	c = 0xfd92;		// from ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM
1266
	while (c <= 0xfdc7)	// ..to ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM
1267
		charset[i++] = c++;
1268
	c = 0xfdf0;		// from ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM
1269
	while (c <= 0xfdfd)	// ..to ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM
1270
		charset[i++] = c++;
1271
// FE00..FE0F; Variation Selectors
1272
	c = 0xfe00;		// from VARIATION SELECTOR-1
1273
	while (c <= 0xfe0f)	// ..to VARIATION SELECTOR-16
1274
		charset[i++] = c++;
1275
// FE10..FE1F; Vertical Forms
1276
	c = 0xfe10;		// from PRESENTATION FORM FOR VERTICAL COMMA
1277
	while (c <= 0xfe19)	// ..to PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS
1278
		charset[i++] = c++;
1279
// FE20..FE2F; Combining Half Marks
1280
	c = 0xfe20;		// from COMBINING LIGATURE LEFT HALF
1281
	while (c <= 0xfe2f)	// ..to COMBINING CYRILLIC TITLO RIGHT HALF
1282
		charset[i++] = c++;
1283
// FE30..FE4F; CJK Compatibility Forms
1284
	c = 0xfe30;		// from PRESENTATION FORM FOR VERTICAL TWO DOT LEADER
1285
	while (c <= 0xfe4f)	// ..to WAVY LOW LINE
1286
		charset[i++] = c++;
1287
// FE50..FE6F; Small Form Variants
1288
	charset[i++] = 0xfe50;	// SMALL COMMA
1289
	charset[i++] = 0xfe52;	// SMALL FULL STOP
1290
	c = 0xfe54;		// from SMALL SEMICOLON
1291
	while (c <= 0xfe66)	// ..to SMALL EQUALS SIGN
1292
		charset[i++] = c++;
1293
	c = 0xfe68;		// from SMALL REVERSE SOLIDUS
1294
	while (c <= 0xfe6b)	// ..to SMALL COMMERCIAL AT
1295
		charset[i++] = c++;
1296
// FE70..FEFF; Arabic Presentation Forms-B
1297
	c = 0xfe70;		// from ARABIC FATHATAN ISOLATED FORM
1298
	while (c <= 0xfe74)	// ..to ARABIC KASRATAN ISOLATED FORM
1299
		charset[i++] = c++;
1300
	c = 0xfe76;		// from ARABIC FATHA ISOLATED FORM
1301
	while (c <= 0xfefc)	// ..to ARABIC LIGATURE LAM WITH ALEF FINAL FORM
1302
		charset[i++] = c++;
1303
	charset[i++] = 0xfeff;	// ZERO WIDTH NO-BREAK SPACE
1304
// FF00..FFEF; Halfwidth and Fullwidth Forms
1305
	c = 0xff01;		// from FULLWIDTH EXCLAMATION MARK
1306
	while (c <= 0xffbe)	// ..to HALFWIDTH HANGUL LETTER HIEUH
1307
		charset[i++] = c++;
1308
	c = 0xffc2;		// from HALFWIDTH HANGUL LETTER A
1309
	while (c <= 0xffc7)	// ..to HALFWIDTH HANGUL LETTER E
1310
		charset[i++] = c++;
1311
	c = 0xffca;		// from HALFWIDTH HANGUL LETTER YEO
1312
	while (c <= 0xffcf)	// ..to HALFWIDTH HANGUL LETTER OE
1313
		charset[i++] = c++;
1314
	c = 0xffd2;		// from HALFWIDTH HANGUL LETTER YO
1315
	while (c <= 0xffd7)	// ..to HALFWIDTH HANGUL LETTER YU
1316
		charset[i++] = c++;
1317
	charset[i++] = 0xffda;	// HALFWIDTH HANGUL LETTER EU
1318
	charset[i++] = 0xffdc;	// HALFWIDTH HANGUL LETTER I
1319
	c = 0xffe0;		// from FULLWIDTH CENT SIGN
1320
	while (c <= 0xffe6)	// ..to FULLWIDTH WON SIGN
1321
		charset[i++] = c++;
1322
	c = 0xffe8;		// from HALFWIDTH FORMS LIGHT VERTICAL
1323
	while (c <= 0xffee)	// ..to HALFWIDTH WHITE CIRCLE
1324
		charset[i++] = c++;
1325
// FFF0..FFFF; Specials
1326
	c = 0xfff9;		// from INTERLINEAR ANNOTATION ANCHOR
1327
	while (c <= 0xfffd)	// ..to REPLACEMENT CHARACTER
1328
		charset[i++] = c++;
1329

1330
/* Zero-terminate it, and cache the first character */
1331
	charset[maxc = i] = 0;
1332

1333
	length = minlength; c = 0;
1334

1335
/* We must init word with dummy data, it doesn't get set until filter() */
1336
	word = 1;
1337
}
1338

1339
void generate()
1340
{
1341
	int i, cl, wl;
1342

1343
	if (target_utf8) {
1344
		cl = 1;
1345
		if (charset[c] >= 0x80) {
1346
			cl++;
1347
			if (charset[c] >= 0x0800)
1348
				cl++;
1349
			wl = length * cl;
1350
			if (wl > cipher_limit) {
1351
				c = 0;
1352
				if (++length > maxlength) {
1353
					word = 0;
1354
					return;
1355
				}
1356
				cl = 1;
1357
				if (charset[0] >= 0x80) {
1358
					cl++;
1359
					if (charset[0] >= 0x0800)
1360
						cl++;
1361
					wl = length * cl;
1362
					if (wl > cipher_limit) {
1363
						word = 0;
1364
						return;
1365
					}
1366
				}
1367
			}
1368
		}
1369
	}
1370

1371
	i = 0;
1372
	while (i < length)
1373
		word[i++] = charset[c];
1374
	word[i] = 0;
1375

1376
	if (++c < maxc)
1377
		return;
1378

1379
	c = 0;
1380
	if (++length > maxlength)
1381
		length = 0; // Will NUL out the next "word" and thus terminate
1382

1383
	return;
1384
}
1385

1386
/* Reset length & c */
1387
void restore()
1388
{
1389
	length = 0;
1390

1391
	while (word[length]) {
1392
		length++;
1393
	}
1394
	c = word[0];
1395
}
1396

1397