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

1
# This  software is Copyright (c) 2012-2020 magnum, and it is hereby
2
# released to the general public under the following terms:
3
# Redistribution and use in source and binary forms, with or without
4
# modification, are permitted.
5
#
6
# Generic implementation of "dumb" exhaustive search of Unicode BMP.
7
# Default is to try *all* allocated characters in the BMP of Unicode v13
8
# (there's 55,387 of them). Even if a fast format can exhaust two characters
9
# in 15 minutes, three characters would take 1.5 years...
10
#
11
# Note that these modes will handle --max-len differently than normal: They
12
# will consider number of characters as opposed to number of bytes. This
13
# means you can naturally just use e.g. --max-len=3 for generating all
14
# three-character candidates (which may be up to 9 bytes each).
15
#
16
# Note that the (newer) cracking mode --subsets=full-unicode is way faster than
17
# this external mode, although not as easy to adapt to smaller portions of the
18
# Unicode space.  See doc/SUBSETS
19

20
[List.External:Dumb16]
21
int maxlength;            // Maximum password length to try
22
int last;                 // Last character position, zero-based
23
int lastid;               // Character index in the last position
24
int id[0x7f];             // Current character indices for other positions
25
int charset[0x10000], c0; // Characters
26

27
void init()
28
{
29
	int minlength;
30
	int i, c;
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
	if (req_maxlen)
40
		maxlength = req_maxlen;
41
	else
42
		maxlength = 2;
43

44
/*
45
 * This defines the character set. This is auto-generated from UnicodeData.txt
46
 * and we skip control characters.
47
 */
48
	i = 0;
49
// 0000..007F; Basic Latin
50
	c = 0x20;		// from SPACE
51
	while (c <= 0x7e)	// ..to TILDE
52
		charset[i++] = c++;
53
// 0080..00FF; Latin-1 Supplement
54
	c = 0xa0;		// from NO-BREAK SPACE
55
	while (c <= 0xff)	// ..to LATIN SMALL LETTER Y WITH DIAERESIS
56
		charset[i++] = c++;
57
// 0100..017F; Latin Extended-A
58
	c = 0x100;		// from LATIN CAPITAL LETTER A WITH MACRON
59
	while (c <= 0x17f)	// ..to LATIN SMALL LETTER LONG S
60
		charset[i++] = c++;
61
// 0180..024F; Latin Extended-B
62
	c = 0x180;		// from LATIN SMALL LETTER B WITH STROKE
63
	while (c <= 0x24f)	// ..to LATIN SMALL LETTER Y WITH STROKE
64
		charset[i++] = c++;
65
// 0250..02AF; IPA Extensions
66
	c = 0x250;		// from LATIN SMALL LETTER TURNED A
67
	while (c <= 0x2af)	// ..to LATIN SMALL LETTER TURNED H WITH FISHHOOK AND TAIL
68
		charset[i++] = c++;
69
// 02B0..02FF; Spacing Modifier Letters
70
	c = 0x2b0;		// from MODIFIER LETTER SMALL H
71
	while (c <= 0x2ff)	// ..to MODIFIER LETTER LOW LEFT ARROW
72
		charset[i++] = c++;
73
// 0300..036F; Combining Diacritical Marks
74
	c = 0x300;		// from COMBINING GRAVE ACCENT
75
	while (c <= 0x36f)	// ..to COMBINING LATIN SMALL LETTER X
76
		charset[i++] = c++;
77
// 0370..03FF; Greek and Coptic
78
	c = 0x370;		// from GREEK CAPITAL LETTER HETA
79
	while (c <= 0x377)	// ..to GREEK SMALL LETTER PAMPHYLIAN DIGAMMA
80
		charset[i++] = c++;
81
	c = 0x37a;		// from GREEK YPOGEGRAMMENI
82
	while (c <= 0x37f)	// ..to GREEK CAPITAL LETTER YOT
83
		charset[i++] = c++;
84
	c = 0x384;		// from GREEK TONOS
85
	while (c <= 0x38a)	// ..to GREEK CAPITAL LETTER IOTA WITH TONOS
86
		charset[i++] = c++;
87
	c = 0x38e;		// from GREEK CAPITAL LETTER UPSILON WITH TONOS
88
	while (c <= 0x3a1)	// ..to GREEK CAPITAL LETTER RHO
89
		charset[i++] = c++;
90
	c = 0x3a3;		// from GREEK CAPITAL LETTER SIGMA
91
	while (c <= 0x3ff)	// ..to GREEK CAPITAL REVERSED DOTTED LUNATE SIGMA SYMBOL
92
		charset[i++] = c++;
93
// 0400..04FF; Cyrillic
94
	c = 0x400;		// from CYRILLIC CAPITAL LETTER IE WITH GRAVE
95
	while (c <= 0x4ff)	// ..to CYRILLIC SMALL LETTER HA WITH STROKE
96
		charset[i++] = c++;
97
// 0500..052F; Cyrillic Supplement
98
	c = 0x500;		// from CYRILLIC CAPITAL LETTER KOMI DE
99
	while (c <= 0x52f)	// ..to CYRILLIC SMALL LETTER EL WITH DESCENDER
100
		charset[i++] = c++;
101
// 0530..058F; Armenian
102
	c = 0x531;		// from ARMENIAN CAPITAL LETTER AYB
103
	while (c <= 0x556)	// ..to ARMENIAN CAPITAL LETTER FEH
104
		charset[i++] = c++;
105
	c = 0x559;		// from ARMENIAN MODIFIER LETTER LEFT HALF RING
106
	while (c <= 0x58a)	// ..to ARMENIAN HYPHEN
107
		charset[i++] = c++;
108
	charset[i++] = 0x58d;	// RIGHT-FACING ARMENIAN ETERNITY SIGN
109
	charset[i++] = 0x58f;	// ARMENIAN DRAM SIGN
110
// 0590..05FF; Hebrew
111
	c = 0x591;		// from HEBREW ACCENT ETNAHTA
112
	while (c <= 0x5c7)	// ..to HEBREW POINT QAMATS QATAN
113
		charset[i++] = c++;
114
	c = 0x5d0;		// from HEBREW LETTER ALEF
115
	while (c <= 0x5ea)	// ..to HEBREW LETTER TAV
116
		charset[i++] = c++;
117
	c = 0x5ef;		// from HEBREW YOD TRIANGLE
118
	while (c <= 0x5f4)	// ..to HEBREW PUNCTUATION GERSHAYIM
119
		charset[i++] = c++;
120
// 0600..06FF; Arabic
121
	c = 0x600;		// from ARABIC NUMBER SIGN
122
	while (c <= 0x61c)	// ..to ARABIC LETTER MARK
123
		charset[i++] = c++;
124
	c = 0x61e;		// from ARABIC TRIPLE DOT PUNCTUATION MARK
125
	while (c <= 0x6ff)	// ..to ARABIC LETTER HEH WITH INVERTED V
126
		charset[i++] = c++;
127
// 0700..074F; Syriac
128
	c = 0x700;		// from SYRIAC END OF PARAGRAPH
129
	while (c <= 0x70d)	// ..to SYRIAC HARKLEAN ASTERISCUS
130
		charset[i++] = c++;
131
	c = 0x70f;		// from SYRIAC ABBREVIATION MARK
132
	while (c <= 0x74a)	// ..to SYRIAC BARREKH
133
		charset[i++] = c++;
134
	charset[i++] = 0x74d;	// SYRIAC LETTER SOGDIAN ZHAIN
135
	charset[i++] = 0x74f;	// SYRIAC LETTER SOGDIAN FE
136
// 0750..077F; Arabic Supplement
137
	c = 0x750;		// from ARABIC LETTER BEH WITH THREE DOTS HORIZONTALLY BELOW
138
	while (c <= 0x77f)	// ..to ARABIC LETTER KAF WITH TWO DOTS ABOVE
139
		charset[i++] = c++;
140
// 0780..07BF; Thaana
141
	c = 0x780;		// from THAANA LETTER HAA
142
	while (c <= 0x7b1)	// ..to THAANA LETTER NAA
143
		charset[i++] = c++;
144
// 07C0..07FF; NKo
145
	c = 0x7c0;		// from NKO DIGIT ZERO
146
	while (c <= 0x7fa)	// ..to NKO LAJANYALAN
147
		charset[i++] = c++;
148
	charset[i++] = 0x7fd;	// NKO DANTAYALAN
149
	charset[i++] = 0x7ff;	// NKO TAMAN SIGN
150
// 0800..083F; Samaritan
151
	c = 0x800;		// from SAMARITAN LETTER ALAF
152
	while (c <= 0x82d)	// ..to SAMARITAN MARK NEQUDAA
153
		charset[i++] = c++;
154
	c = 0x830;		// from SAMARITAN PUNCTUATION NEQUDAA
155
	while (c <= 0x83e)	// ..to SAMARITAN PUNCTUATION ANNAAU
156
		charset[i++] = c++;
157
// 0840..085F; Mandaic
158
	c = 0x840;		// from MANDAIC LETTER HALQA
159
	while (c <= 0x85b)	// ..to MANDAIC GEMINATION MARK
160
		charset[i++] = c++;
161
	charset[i++] = 0x85e;	// MANDAIC PUNCTUATION
162
// 0860..086F; Syriac Supplement
163
	c = 0x860;		// from SYRIAC LETTER MALAYALAM NGA
164
	while (c <= 0x86a)	// ..to SYRIAC LETTER MALAYALAM SSA
165
		charset[i++] = c++;
166
// 08A0..08FF; Arabic Extended-A
167
	c = 0x8a0;		// from ARABIC LETTER BEH WITH SMALL V BELOW
168
	while (c <= 0x8b4)	// ..to ARABIC LETTER KAF WITH DOT BELOW
169
		charset[i++] = c++;
170
	c = 0x8b6;		// from ARABIC LETTER BEH WITH SMALL MEEM ABOVE
171
	while (c <= 0x8c7)	// ..to ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE
172
		charset[i++] = c++;
173
	c = 0x8d3;		// from ARABIC SMALL LOW WAW
174
	while (c <= 0x8ff)	// ..to ARABIC MARK SIDEWAYS NOON GHUNNA
175
		charset[i++] = c++;
176
// 0900..097F; Devanagari
177
	c = 0x900;		// from DEVANAGARI SIGN INVERTED CANDRABINDU
178
	while (c <= 0x97f)	// ..to DEVANAGARI LETTER BBA
179
		charset[i++] = c++;
180
// 0980..09FF; Bengali
181
	c = 0x980;		// from BENGALI ANJI
182
	while (c <= 0x983)	// ..to BENGALI SIGN VISARGA
183
		charset[i++] = c++;
184
	c = 0x985;		// from BENGALI LETTER A
185
	while (c <= 0x98c)	// ..to BENGALI LETTER VOCALIC L
186
		charset[i++] = c++;
187
	charset[i++] = 0x98f;	// BENGALI LETTER E
188
	charset[i++] = 0x990;	// BENGALI LETTER AI
189
	c = 0x993;		// from BENGALI LETTER O
190
	while (c <= 0x9a8)	// ..to BENGALI LETTER NA
191
		charset[i++] = c++;
192
	c = 0x9aa;		// from BENGALI LETTER PA
193
	while (c <= 0x9b0)	// ..to BENGALI LETTER RA
194
		charset[i++] = c++;
195
	c = 0x9b6;		// from BENGALI LETTER SHA
196
	while (c <= 0x9b9)	// ..to BENGALI LETTER HA
197
		charset[i++] = c++;
198
	c = 0x9bc;		// from BENGALI SIGN NUKTA
199
	while (c <= 0x9c4)	// ..to BENGALI VOWEL SIGN VOCALIC RR
200
		charset[i++] = c++;
201
	charset[i++] = 0x9c7;	// BENGALI VOWEL SIGN E
202
	charset[i++] = 0x9c8;	// BENGALI VOWEL SIGN AI
203
	c = 0x9cb;		// from BENGALI VOWEL SIGN O
204
	while (c <= 0x9ce)	// ..to BENGALI LETTER KHANDA TA
205
		charset[i++] = c++;
206
	charset[i++] = 0x9dc;	// BENGALI LETTER RRA
207
	charset[i++] = 0x9dd;	// BENGALI LETTER RHA
208
	c = 0x9df;		// from BENGALI LETTER YYA
209
	while (c <= 0x9e3)	// ..to BENGALI VOWEL SIGN VOCALIC LL
210
		charset[i++] = c++;
211
	c = 0x9e6;		// from BENGALI DIGIT ZERO
212
	while (c <= 0x9fe)	// ..to BENGALI SANDHI MARK
213
		charset[i++] = c++;
214
// 0A00..0A7F; Gurmukhi
215
	charset[i++] = 0xa01;	// GURMUKHI SIGN ADAK BINDI
216
	charset[i++] = 0xa03;	// GURMUKHI SIGN VISARGA
217
	c = 0xa05;		// from GURMUKHI LETTER A
218
	while (c <= 0xa0a)	// ..to GURMUKHI LETTER UU
219
		charset[i++] = c++;
220
	charset[i++] = 0xa0f;	// GURMUKHI LETTER EE
221
	charset[i++] = 0xa10;	// GURMUKHI LETTER AI
222
	c = 0xa13;		// from GURMUKHI LETTER OO
223
	while (c <= 0xa28)	// ..to GURMUKHI LETTER NA
224
		charset[i++] = c++;
225
	c = 0xa2a;		// from GURMUKHI LETTER PA
226
	while (c <= 0xa30)	// ..to GURMUKHI LETTER RA
227
		charset[i++] = c++;
228
	charset[i++] = 0xa32;	// GURMUKHI LETTER LA
229
	charset[i++] = 0xa33;	// GURMUKHI LETTER LLA
230
	charset[i++] = 0xa35;	// GURMUKHI LETTER VA
231
	charset[i++] = 0xa36;	// GURMUKHI LETTER SHA
232
	charset[i++] = 0xa38;	// GURMUKHI LETTER SA
233
	charset[i++] = 0xa39;	// GURMUKHI LETTER HA
234
	c = 0xa3e;		// from GURMUKHI VOWEL SIGN AA
235
	while (c <= 0xa42)	// ..to GURMUKHI VOWEL SIGN UU
236
		charset[i++] = c++;
237
	charset[i++] = 0xa47;	// GURMUKHI VOWEL SIGN EE
238
	charset[i++] = 0xa48;	// GURMUKHI VOWEL SIGN AI
239
	charset[i++] = 0xa4b;	// GURMUKHI VOWEL SIGN OO
240
	charset[i++] = 0xa4d;	// GURMUKHI SIGN VIRAMA
241
	c = 0xa59;		// from GURMUKHI LETTER KHHA
242
	while (c <= 0xa5c)	// ..to GURMUKHI LETTER RRA
243
		charset[i++] = c++;
244
	c = 0xa66;		// from GURMUKHI DIGIT ZERO
245
	while (c <= 0xa76)	// ..to GURMUKHI ABBREVIATION SIGN
246
		charset[i++] = c++;
247
// 0A80..0AFF; Gujarati
248
	charset[i++] = 0xa81;	// GUJARATI SIGN CANDRABINDU
249
	charset[i++] = 0xa83;	// GUJARATI SIGN VISARGA
250
	c = 0xa85;		// from GUJARATI LETTER A
251
	while (c <= 0xa8d)	// ..to GUJARATI VOWEL CANDRA E
252
		charset[i++] = c++;
253
	charset[i++] = 0xa8f;	// GUJARATI LETTER E
254
	charset[i++] = 0xa91;	// GUJARATI VOWEL CANDRA O
255
	c = 0xa93;		// from GUJARATI LETTER O
256
	while (c <= 0xaa8)	// ..to GUJARATI LETTER NA
257
		charset[i++] = c++;
258
	c = 0xaaa;		// from GUJARATI LETTER PA
259
	while (c <= 0xab0)	// ..to GUJARATI LETTER RA
260
		charset[i++] = c++;
261
	charset[i++] = 0xab2;	// GUJARATI LETTER LA
262
	charset[i++] = 0xab3;	// GUJARATI LETTER LLA
263
	c = 0xab5;		// from GUJARATI LETTER VA
264
	while (c <= 0xab9)	// ..to GUJARATI LETTER HA
265
		charset[i++] = c++;
266
	c = 0xabc;		// from GUJARATI SIGN NUKTA
267
	while (c <= 0xac5)	// ..to GUJARATI VOWEL SIGN CANDRA E
268
		charset[i++] = c++;
269
	charset[i++] = 0xac7;	// GUJARATI VOWEL SIGN E
270
	charset[i++] = 0xac9;	// GUJARATI VOWEL SIGN CANDRA O
271
	charset[i++] = 0xacb;	// GUJARATI VOWEL SIGN O
272
	charset[i++] = 0xacd;	// GUJARATI SIGN VIRAMA
273
	c = 0xae0;		// from GUJARATI LETTER VOCALIC RR
274
	while (c <= 0xae3)	// ..to GUJARATI VOWEL SIGN VOCALIC LL
275
		charset[i++] = c++;
276
	c = 0xae6;		// from GUJARATI DIGIT ZERO
277
	while (c <= 0xaf1)	// ..to GUJARATI RUPEE SIGN
278
		charset[i++] = c++;
279
	c = 0xaf9;		// from GUJARATI LETTER ZHA
280
	while (c <= 0xaff)	// ..to GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE
281
		charset[i++] = c++;
282
// 0B00..0B7F; Oriya
283
	charset[i++] = 0xb01;	// ORIYA SIGN CANDRABINDU
284
	charset[i++] = 0xb03;	// ORIYA SIGN VISARGA
285
	c = 0xb05;		// from ORIYA LETTER A
286
	while (c <= 0xb0c)	// ..to ORIYA LETTER VOCALIC L
287
		charset[i++] = c++;
288
	charset[i++] = 0xb0f;	// ORIYA LETTER E
289
	charset[i++] = 0xb10;	// ORIYA LETTER AI
290
	c = 0xb13;		// from ORIYA LETTER O
291
	while (c <= 0xb28)	// ..to ORIYA LETTER NA
292
		charset[i++] = c++;
293
	c = 0xb2a;		// from ORIYA LETTER PA
294
	while (c <= 0xb30)	// ..to ORIYA LETTER RA
295
		charset[i++] = c++;
296
	charset[i++] = 0xb32;	// ORIYA LETTER LA
297
	charset[i++] = 0xb33;	// ORIYA LETTER LLA
298
	c = 0xb35;		// from ORIYA LETTER VA
299
	while (c <= 0xb39)	// ..to ORIYA LETTER HA
300
		charset[i++] = c++;
301
	c = 0xb3c;		// from ORIYA SIGN NUKTA
302
	while (c <= 0xb44)	// ..to ORIYA VOWEL SIGN VOCALIC RR
303
		charset[i++] = c++;
304
	charset[i++] = 0xb47;	// ORIYA VOWEL SIGN E
305
	charset[i++] = 0xb48;	// ORIYA VOWEL SIGN AI
306
	charset[i++] = 0xb4b;	// ORIYA VOWEL SIGN O
307
	charset[i++] = 0xb4d;	// ORIYA SIGN VIRAMA
308
	charset[i++] = 0xb55;	// ORIYA SIGN OVERLINE
309
	charset[i++] = 0xb57;	// ORIYA AU LENGTH MARK
310
	charset[i++] = 0xb5c;	// ORIYA LETTER RRA
311
	charset[i++] = 0xb5d;	// ORIYA LETTER RHA
312
	c = 0xb5f;		// from ORIYA LETTER YYA
313
	while (c <= 0xb63)	// ..to ORIYA VOWEL SIGN VOCALIC LL
314
		charset[i++] = c++;
315
	c = 0xb66;		// from ORIYA DIGIT ZERO
316
	while (c <= 0xb77)	// ..to ORIYA FRACTION THREE SIXTEENTHS
317
		charset[i++] = c++;
318
// 0B80..0BFF; Tamil
319
	charset[i++] = 0xb82;	// TAMIL SIGN ANUSVARA
320
	charset[i++] = 0xb83;	// TAMIL SIGN VISARGA
321
	c = 0xb85;		// from TAMIL LETTER A
322
	while (c <= 0xb8a)	// ..to TAMIL LETTER UU
323
		charset[i++] = c++;
324
	charset[i++] = 0xb8e;	// TAMIL LETTER E
325
	charset[i++] = 0xb90;	// TAMIL LETTER AI
326
	c = 0xb92;		// from TAMIL LETTER O
327
	while (c <= 0xb95)	// ..to TAMIL LETTER KA
328
		charset[i++] = c++;
329
	charset[i++] = 0xb99;	// TAMIL LETTER NGA
330
	charset[i++] = 0xb9a;	// TAMIL LETTER CA
331
	charset[i++] = 0xb9e;	// TAMIL LETTER NYA
332
	charset[i++] = 0xb9f;	// TAMIL LETTER TTA
333
	charset[i++] = 0xba3;	// TAMIL LETTER NNA
334
	charset[i++] = 0xba4;	// TAMIL LETTER TA
335
	charset[i++] = 0xba8;	// TAMIL LETTER NA
336
	charset[i++] = 0xbaa;	// TAMIL LETTER PA
337
	c = 0xbae;		// from TAMIL LETTER MA
338
	while (c <= 0xbb9)	// ..to TAMIL LETTER HA
339
		charset[i++] = c++;
340
	c = 0xbbe;		// from TAMIL VOWEL SIGN AA
341
	while (c <= 0xbc2)	// ..to TAMIL VOWEL SIGN UU
342
		charset[i++] = c++;
343
	charset[i++] = 0xbc6;	// TAMIL VOWEL SIGN E
344
	charset[i++] = 0xbc8;	// TAMIL VOWEL SIGN AI
345
	c = 0xbca;		// from TAMIL VOWEL SIGN O
346
	while (c <= 0xbcd)	// ..to TAMIL SIGN VIRAMA
347
		charset[i++] = c++;
348
	c = 0xbe6;		// from TAMIL DIGIT ZERO
349
	while (c <= 0xbfa)	// ..to TAMIL NUMBER SIGN
350
		charset[i++] = c++;
351
// 0C00..0C7F; Telugu
352
	c = 0xc00;		// from TELUGU SIGN COMBINING CANDRABINDU ABOVE
353
	while (c <= 0xc0c)	// ..to TELUGU LETTER VOCALIC L
354
		charset[i++] = c++;
355
	charset[i++] = 0xc0e;	// TELUGU LETTER E
356
	charset[i++] = 0xc10;	// TELUGU LETTER AI
357
	c = 0xc12;		// from TELUGU LETTER O
358
	while (c <= 0xc28)	// ..to TELUGU LETTER NA
359
		charset[i++] = c++;
360
	c = 0xc2a;		// from TELUGU LETTER PA
361
	while (c <= 0xc39)	// ..to TELUGU LETTER HA
362
		charset[i++] = c++;
363
	c = 0xc3d;		// from TELUGU SIGN AVAGRAHA
364
	while (c <= 0xc44)	// ..to TELUGU VOWEL SIGN VOCALIC RR
365
		charset[i++] = c++;
366
	charset[i++] = 0xc46;	// TELUGU VOWEL SIGN E
367
	charset[i++] = 0xc48;	// TELUGU VOWEL SIGN AI
368
	c = 0xc4a;		// from TELUGU VOWEL SIGN O
369
	while (c <= 0xc4d)	// ..to TELUGU SIGN VIRAMA
370
		charset[i++] = c++;
371
	charset[i++] = 0xc55;	// TELUGU LENGTH MARK
372
	charset[i++] = 0xc56;	// TELUGU AI LENGTH MARK
373
	charset[i++] = 0xc58;	// TELUGU LETTER TSA
374
	charset[i++] = 0xc5a;	// TELUGU LETTER RRRA
375
	c = 0xc60;		// from TELUGU LETTER VOCALIC RR
376
	while (c <= 0xc63)	// ..to TELUGU VOWEL SIGN VOCALIC LL
377
		charset[i++] = c++;
378
	c = 0xc66;		// from TELUGU DIGIT ZERO
379
	while (c <= 0xc6f)	// ..to TELUGU DIGIT NINE
380
		charset[i++] = c++;
381
	c = 0xc77;		// from TELUGU SIGN SIDDHAM
382
	while (c <= 0xc7f)	// ..to TELUGU SIGN TUUMU
383
		charset[i++] = c++;
384
// 0C80..0CFF; Kannada
385
	c = 0xc80;		// from KANNADA SIGN SPACING CANDRABINDU
386
	while (c <= 0xc8c)	// ..to KANNADA LETTER VOCALIC L
387
		charset[i++] = c++;
388
	charset[i++] = 0xc8e;	// KANNADA LETTER E
389
	charset[i++] = 0xc90;	// KANNADA LETTER AI
390
	c = 0xc92;		// from KANNADA LETTER O
391
	while (c <= 0xca8)	// ..to KANNADA LETTER NA
392
		charset[i++] = c++;
393
	c = 0xcaa;		// from KANNADA LETTER PA
394
	while (c <= 0xcb3)	// ..to KANNADA LETTER LLA
395
		charset[i++] = c++;
396
	c = 0xcb5;		// from KANNADA LETTER VA
397
	while (c <= 0xcb9)	// ..to KANNADA LETTER HA
398
		charset[i++] = c++;
399
	c = 0xcbc;		// from KANNADA SIGN NUKTA
400
	while (c <= 0xcc4)	// ..to KANNADA VOWEL SIGN VOCALIC RR
401
		charset[i++] = c++;
402
	charset[i++] = 0xcc6;	// KANNADA VOWEL SIGN E
403
	charset[i++] = 0xcc8;	// KANNADA VOWEL SIGN AI
404
	c = 0xcca;		// from KANNADA VOWEL SIGN O
405
	while (c <= 0xccd)	// ..to KANNADA SIGN VIRAMA
406
		charset[i++] = c++;
407
	charset[i++] = 0xcd5;	// KANNADA LENGTH MARK
408
	charset[i++] = 0xcd6;	// KANNADA AI LENGTH MARK
409
	c = 0xce0;		// from KANNADA LETTER VOCALIC RR
410
	while (c <= 0xce3)	// ..to KANNADA VOWEL SIGN VOCALIC LL
411
		charset[i++] = c++;
412
	c = 0xce6;		// from KANNADA DIGIT ZERO
413
	while (c <= 0xcef)	// ..to KANNADA DIGIT NINE
414
		charset[i++] = c++;
415
	charset[i++] = 0xcf1;	// KANNADA SIGN JIHVAMULIYA
416
	charset[i++] = 0xcf2;	// KANNADA SIGN UPADHMANIYA
417
// 0D00..0D7F; Malayalam
418
	c = 0xd00;		// from MALAYALAM SIGN COMBINING ANUSVARA ABOVE
419
	while (c <= 0xd0c)	// ..to MALAYALAM LETTER VOCALIC L
420
		charset[i++] = c++;
421
	charset[i++] = 0xd0e;	// MALAYALAM LETTER E
422
	charset[i++] = 0xd10;	// MALAYALAM LETTER AI
423
	c = 0xd12;		// from MALAYALAM LETTER O
424
	while (c <= 0xd44)	// ..to MALAYALAM VOWEL SIGN VOCALIC RR
425
		charset[i++] = c++;
426
	charset[i++] = 0xd46;	// MALAYALAM VOWEL SIGN E
427
	charset[i++] = 0xd48;	// MALAYALAM VOWEL SIGN AI
428
	c = 0xd4a;		// from MALAYALAM VOWEL SIGN O
429
	while (c <= 0xd4f)	// ..to MALAYALAM SIGN PARA
430
		charset[i++] = c++;
431
	c = 0xd54;		// from MALAYALAM LETTER CHILLU M
432
	while (c <= 0xd63)	// ..to MALAYALAM VOWEL SIGN VOCALIC LL
433
		charset[i++] = c++;
434
	c = 0xd66;		// from MALAYALAM DIGIT ZERO
435
	while (c <= 0xd7f)	// ..to MALAYALAM LETTER CHILLU K
436
		charset[i++] = c++;
437
// 0D80..0DFF; Sinhala
438
	charset[i++] = 0xd81;	// SINHALA SIGN CANDRABINDU
439
	charset[i++] = 0xd83;	// SINHALA SIGN VISARGAYA
440
	c = 0xd85;		// from SINHALA LETTER AYANNA
441
	while (c <= 0xd96)	// ..to SINHALA LETTER AUYANNA
442
		charset[i++] = c++;
443
	c = 0xd9a;		// from SINHALA LETTER ALPAPRAANA KAYANNA
444
	while (c <= 0xdb1)	// ..to SINHALA LETTER DANTAJA NAYANNA
445
		charset[i++] = c++;
446
	c = 0xdb3;		// from SINHALA LETTER SANYAKA DAYANNA
447
	while (c <= 0xdbb)	// ..to SINHALA LETTER RAYANNA
448
		charset[i++] = c++;
449
	c = 0xdc0;		// from SINHALA LETTER VAYANNA
450
	while (c <= 0xdc6)	// ..to SINHALA LETTER FAYANNA
451
		charset[i++] = c++;
452
	c = 0xdcf;		// from SINHALA VOWEL SIGN AELA-PILLA
453
	while (c <= 0xdd4)	// ..to SINHALA VOWEL SIGN KETTI PAA-PILLA
454
		charset[i++] = c++;
455
	c = 0xdd8;		// from SINHALA VOWEL SIGN GAETTA-PILLA
456
	while (c <= 0xddf)	// ..to SINHALA VOWEL SIGN GAYANUKITTA
457
		charset[i++] = c++;
458
	c = 0xde6;		// from SINHALA LITH DIGIT ZERO
459
	while (c <= 0xdef)	// ..to SINHALA LITH DIGIT NINE
460
		charset[i++] = c++;
461
	charset[i++] = 0xdf2;	// SINHALA VOWEL SIGN DIGA GAETTA-PILLA
462
	charset[i++] = 0xdf4;	// SINHALA PUNCTUATION KUNDDALIYA
463
// 0E00..0E7F; Thai
464
	c = 0xe01;		// from THAI CHARACTER KO KAI
465
	while (c <= 0xe3a)	// ..to THAI CHARACTER PHINTHU
466
		charset[i++] = c++;
467
	c = 0xe3f;		// from THAI CURRENCY SYMBOL BAHT
468
	while (c <= 0xe5b)	// ..to THAI CHARACTER KHOMUT
469
		charset[i++] = c++;
470
// 0E80..0EFF; Lao
471
	charset[i++] = 0xe81;	// LAO LETTER KO
472
	charset[i++] = 0xe82;	// LAO LETTER KHO SUNG
473
	c = 0xe86;		// from LAO LETTER PALI GHA
474
	while (c <= 0xe8a)	// ..to LAO LETTER SO TAM
475
		charset[i++] = c++;
476
	c = 0xe8c;		// from LAO LETTER PALI JHA
477
	while (c <= 0xea3)	// ..to LAO LETTER LO LING
478
		charset[i++] = c++;
479
	c = 0xea7;		// from LAO LETTER WO
480
	while (c <= 0xebd)	// ..to LAO SEMIVOWEL SIGN NYO
481
		charset[i++] = c++;
482
	c = 0xec0;		// from LAO VOWEL SIGN E
483
	while (c <= 0xec4)	// ..to LAO VOWEL SIGN AI
484
		charset[i++] = c++;
485
	c = 0xec8;		// from LAO TONE MAI EK
486
	while (c <= 0xecd)	// ..to LAO NIGGAHITA
487
		charset[i++] = c++;
488
	c = 0xed0;		// from LAO DIGIT ZERO
489
	while (c <= 0xed9)	// ..to LAO DIGIT NINE
490
		charset[i++] = c++;
491
	c = 0xedc;		// from LAO HO NO
492
	while (c <= 0xedf)	// ..to LAO LETTER KHMU NYO
493
		charset[i++] = c++;
494
// 0F00..0FFF; Tibetan
495
	c = 0xf00;		// from TIBETAN SYLLABLE OM
496
	while (c <= 0xf47)	// ..to TIBETAN LETTER JA
497
		charset[i++] = c++;
498
	c = 0xf49;		// from TIBETAN LETTER NYA
499
	while (c <= 0xf6c)	// ..to TIBETAN LETTER RRA
500
		charset[i++] = c++;
501
	c = 0xf71;		// from TIBETAN VOWEL SIGN AA
502
	while (c <= 0xf97)	// ..to TIBETAN SUBJOINED LETTER JA
503
		charset[i++] = c++;
504
	c = 0xf99;		// from TIBETAN SUBJOINED LETTER NYA
505
	while (c <= 0xfbc)	// ..to TIBETAN SUBJOINED LETTER FIXED-FORM RA
506
		charset[i++] = c++;
507
	c = 0xfbe;		// from TIBETAN KU RU KHA
508
	while (c <= 0xfcc)	// ..to TIBETAN SYMBOL NOR BU BZHI -KHYIL
509
		charset[i++] = c++;
510
	c = 0xfce;		// from TIBETAN SIGN RDEL NAG RDEL DKAR
511
	while (c <= 0xfda)	// ..to TIBETAN MARK TRAILING MCHAN RTAGS
512
		charset[i++] = c++;
513
// 1000..109F; Myanmar
514
	c = 0x1000;		// from MYANMAR LETTER KA
515
	while (c <= 0x109f)	// ..to MYANMAR SYMBOL SHAN EXCLAMATION
516
		charset[i++] = c++;
517
// 10A0..10FF; Georgian
518
	c = 0x10a0;		// from GEORGIAN CAPITAL LETTER AN
519
	while (c <= 0x10c5)	// ..to GEORGIAN CAPITAL LETTER HOE
520
		charset[i++] = c++;
521
	c = 0x10d0;		// from GEORGIAN LETTER AN
522
	while (c <= 0x10ff)	// ..to GEORGIAN LETTER LABIAL SIGN
523
		charset[i++] = c++;
524
// 1100..11FF; Hangul Jamo
525
	c = 0x1100;		// from HANGUL CHOSEONG KIYEOK
526
	while (c <= 0x11ff)	// ..to HANGUL JONGSEONG SSANGNIEUN
527
		charset[i++] = c++;
528
// 1200..137F; Ethiopic
529
	c = 0x1200;		// from ETHIOPIC SYLLABLE HA
530
	while (c <= 0x1248)	// ..to ETHIOPIC SYLLABLE QWA
531
		charset[i++] = c++;
532
	c = 0x124a;		// from ETHIOPIC SYLLABLE QWI
533
	while (c <= 0x124d)	// ..to ETHIOPIC SYLLABLE QWE
534
		charset[i++] = c++;
535
	c = 0x1250;		// from ETHIOPIC SYLLABLE QHA
536
	while (c <= 0x1256)	// ..to ETHIOPIC SYLLABLE QHO
537
		charset[i++] = c++;
538
	c = 0x125a;		// from ETHIOPIC SYLLABLE QHWI
539
	while (c <= 0x125d)	// ..to ETHIOPIC SYLLABLE QHWE
540
		charset[i++] = c++;
541
	c = 0x1260;		// from ETHIOPIC SYLLABLE BA
542
	while (c <= 0x1288)	// ..to ETHIOPIC SYLLABLE XWA
543
		charset[i++] = c++;
544
	c = 0x128a;		// from ETHIOPIC SYLLABLE XWI
545
	while (c <= 0x128d)	// ..to ETHIOPIC SYLLABLE XWE
546
		charset[i++] = c++;
547
	c = 0x1290;		// from ETHIOPIC SYLLABLE NA
548
	while (c <= 0x12b0)	// ..to ETHIOPIC SYLLABLE KWA
549
		charset[i++] = c++;
550
	c = 0x12b2;		// from ETHIOPIC SYLLABLE KWI
551
	while (c <= 0x12b5)	// ..to ETHIOPIC SYLLABLE KWE
552
		charset[i++] = c++;
553
	c = 0x12b8;		// from ETHIOPIC SYLLABLE KXA
554
	while (c <= 0x12be)	// ..to ETHIOPIC SYLLABLE KXO
555
		charset[i++] = c++;
556
	c = 0x12c2;		// from ETHIOPIC SYLLABLE KXWI
557
	while (c <= 0x12c5)	// ..to ETHIOPIC SYLLABLE KXWE
558
		charset[i++] = c++;
559
	c = 0x12c8;		// from ETHIOPIC SYLLABLE WA
560
	while (c <= 0x12d6)	// ..to ETHIOPIC SYLLABLE PHARYNGEAL O
561
		charset[i++] = c++;
562
	c = 0x12d8;		// from ETHIOPIC SYLLABLE ZA
563
	while (c <= 0x1310)	// ..to ETHIOPIC SYLLABLE GWA
564
		charset[i++] = c++;
565
	c = 0x1312;		// from ETHIOPIC SYLLABLE GWI
566
	while (c <= 0x1315)	// ..to ETHIOPIC SYLLABLE GWE
567
		charset[i++] = c++;
568
	c = 0x1318;		// from ETHIOPIC SYLLABLE GGA
569
	while (c <= 0x135a)	// ..to ETHIOPIC SYLLABLE FYA
570
		charset[i++] = c++;
571
	c = 0x135d;		// from ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK
572
	while (c <= 0x137c)	// ..to ETHIOPIC NUMBER TEN THOUSAND
573
		charset[i++] = c++;
574
// 1380..139F; Ethiopic Supplement
575
	c = 0x1380;		// from ETHIOPIC SYLLABLE SEBATBEIT MWA
576
	while (c <= 0x1399)	// ..to ETHIOPIC TONAL MARK KURT
577
		charset[i++] = c++;
578
// 13A0..13FF; Cherokee
579
	c = 0x13a0;		// from CHEROKEE LETTER A
580
	while (c <= 0x13f5)	// ..to CHEROKEE LETTER MV
581
		charset[i++] = c++;
582
	c = 0x13f8;		// from CHEROKEE SMALL LETTER YE
583
	while (c <= 0x13fd)	// ..to CHEROKEE SMALL LETTER MV
584
		charset[i++] = c++;
585
// 1400..167F; Unified Canadian Aboriginal Syllabics
586
	c = 0x1400;		// from CANADIAN SYLLABICS HYPHEN
587
	while (c <= 0x167f)	// ..to CANADIAN SYLLABICS BLACKFOOT W
588
		charset[i++] = c++;
589
// 1680..169F; Ogham
590
	c = 0x1680;		// from OGHAM SPACE MARK
591
	while (c <= 0x169c)	// ..to OGHAM REVERSED FEATHER MARK
592
		charset[i++] = c++;
593
// 16A0..16FF; Runic
594
	c = 0x16a0;		// from RUNIC LETTER FEHU FEOH FE F
595
	while (c <= 0x16f8)	// ..to RUNIC LETTER FRANKS CASKET AESC
596
		charset[i++] = c++;
597
// 1700..171F; Tagalog
598
	c = 0x1700;		// from TAGALOG LETTER A
599
	while (c <= 0x170c)	// ..to TAGALOG LETTER YA
600
		charset[i++] = c++;
601
	c = 0x170e;		// from TAGALOG LETTER LA
602
	while (c <= 0x1714)	// ..to TAGALOG SIGN VIRAMA
603
		charset[i++] = c++;
604
// 1720..173F; Hanunoo
605
	c = 0x1720;		// from HANUNOO LETTER A
606
	while (c <= 0x1736)	// ..to PHILIPPINE DOUBLE PUNCTUATION
607
		charset[i++] = c++;
608
// 1740..175F; Buhid
609
	c = 0x1740;		// from BUHID LETTER A
610
	while (c <= 0x1753)	// ..to BUHID VOWEL SIGN U
611
		charset[i++] = c++;
612
// 1760..177F; Tagbanwa
613
	c = 0x1760;		// from TAGBANWA LETTER A
614
	while (c <= 0x176c)	// ..to TAGBANWA LETTER YA
615
		charset[i++] = c++;
616
	charset[i++] = 0x176e;	// TAGBANWA LETTER LA
617
	charset[i++] = 0x1770;	// TAGBANWA LETTER SA
618
	charset[i++] = 0x1772;	// TAGBANWA VOWEL SIGN I
619
	charset[i++] = 0x1773;	// TAGBANWA VOWEL SIGN U
620
// 1780..17FF; Khmer
621
	c = 0x1780;		// from KHMER LETTER KA
622
	while (c <= 0x17dd)	// ..to KHMER SIGN ATTHACAN
623
		charset[i++] = c++;
624
	c = 0x17e0;		// from KHMER DIGIT ZERO
625
	while (c <= 0x17e9)	// ..to KHMER DIGIT NINE
626
		charset[i++] = c++;
627
	c = 0x17f0;		// from KHMER SYMBOL LEK ATTAK SON
628
	while (c <= 0x17f9)	// ..to KHMER SYMBOL LEK ATTAK PRAM-BUON
629
		charset[i++] = c++;
630
// 1800..18AF; Mongolian
631
	c = 0x1800;		// from MONGOLIAN BIRGA
632
	while (c <= 0x180e)	// ..to MONGOLIAN VOWEL SEPARATOR
633
		charset[i++] = c++;
634
	c = 0x1810;		// from MONGOLIAN DIGIT ZERO
635
	while (c <= 0x1819)	// ..to MONGOLIAN DIGIT NINE
636
		charset[i++] = c++;
637
	c = 0x1820;		// from MONGOLIAN LETTER A
638
	while (c <= 0x1878)	// ..to MONGOLIAN LETTER CHA WITH TWO DOTS
639
		charset[i++] = c++;
640
	c = 0x1880;		// from MONGOLIAN LETTER ALI GALI ANUSVARA ONE
641
	while (c <= 0x18aa)	// ..to MONGOLIAN LETTER MANCHU ALI GALI LHA
642
		charset[i++] = c++;
643
// 18B0..18FF; Unified Canadian Aboriginal Syllabics Extended
644
	c = 0x18b0;		// from CANADIAN SYLLABICS OY
645
	while (c <= 0x18f5)	// ..to CANADIAN SYLLABICS CARRIER DENTAL S
646
		charset[i++] = c++;
647
// 1900..194F; Limbu
648
	c = 0x1900;		// from LIMBU VOWEL-CARRIER LETTER
649
	while (c <= 0x191e)	// ..to LIMBU LETTER TRA
650
		charset[i++] = c++;
651
	c = 0x1920;		// from LIMBU VOWEL SIGN A
652
	while (c <= 0x192b)	// ..to LIMBU SUBJOINED LETTER WA
653
		charset[i++] = c++;
654
	c = 0x1930;		// from LIMBU SMALL LETTER KA
655
	while (c <= 0x193b)	// ..to LIMBU SIGN SA-I
656
		charset[i++] = c++;
657
	c = 0x1944;		// from LIMBU EXCLAMATION MARK
658
	while (c <= 0x194f)	// ..to LIMBU DIGIT NINE
659
		charset[i++] = c++;
660
// 1950..197F; Tai Le
661
	c = 0x1950;		// from TAI LE LETTER KA
662
	while (c <= 0x196d)	// ..to TAI LE LETTER AI
663
		charset[i++] = c++;
664
	c = 0x1970;		// from TAI LE LETTER TONE-2
665
	while (c <= 0x1974)	// ..to TAI LE LETTER TONE-6
666
		charset[i++] = c++;
667
// 1980..19DF; New Tai Lue
668
	c = 0x1980;		// from NEW TAI LUE LETTER HIGH QA
669
	while (c <= 0x19ab)	// ..to NEW TAI LUE LETTER LOW SUA
670
		charset[i++] = c++;
671
	c = 0x19b0;		// from NEW TAI LUE VOWEL SIGN VOWEL SHORTENER
672
	while (c <= 0x19c9)	// ..to NEW TAI LUE TONE MARK-2
673
		charset[i++] = c++;
674
	c = 0x19d0;		// from NEW TAI LUE DIGIT ZERO
675
	while (c <= 0x19da)	// ..to NEW TAI LUE THAM DIGIT ONE
676
		charset[i++] = c++;
677
	charset[i++] = 0x19de;	// NEW TAI LUE SIGN LAE
678
	charset[i++] = 0x19df;	// NEW TAI LUE SIGN LAEV
679
// 19E0..19FF; Khmer Symbols
680
	c = 0x19e0;		// from KHMER SYMBOL PATHAMASAT
681
	while (c <= 0x19ff)	// ..to KHMER SYMBOL DAP-PRAM ROC
682
		charset[i++] = c++;
683
// 1A00..1A1F; Buginese
684
	c = 0x1a00;		// from BUGINESE LETTER KA
685
	while (c <= 0x1a1b)	// ..to BUGINESE VOWEL SIGN AE
686
		charset[i++] = c++;
687
	charset[i++] = 0x1a1e;	// BUGINESE PALLAWA
688
	charset[i++] = 0x1a1f;	// BUGINESE END OF SECTION
689
// 1A20..1AAF; Tai Tham
690
	c = 0x1a20;		// from TAI THAM LETTER HIGH KA
691
	while (c <= 0x1a5e)	// ..to TAI THAM CONSONANT SIGN SA
692
		charset[i++] = c++;
693
	c = 0x1a60;		// from TAI THAM SIGN SAKOT
694
	while (c <= 0x1a7c)	// ..to TAI THAM SIGN KHUEN-LUE KARAN
695
		charset[i++] = c++;
696
	c = 0x1a7f;		// from TAI THAM COMBINING CRYPTOGRAMMIC DOT
697
	while (c <= 0x1a89)	// ..to TAI THAM HORA DIGIT NINE
698
		charset[i++] = c++;
699
	c = 0x1a90;		// from TAI THAM THAM DIGIT ZERO
700
	while (c <= 0x1a99)	// ..to TAI THAM THAM DIGIT NINE
701
		charset[i++] = c++;
702
	c = 0x1aa0;		// from TAI THAM SIGN WIANG
703
	while (c <= 0x1aad)	// ..to TAI THAM SIGN CAANG
704
		charset[i++] = c++;
705
// 1AB0..1AFF; Combining Diacritical Marks Extended
706
	c = 0x1ab0;		// from COMBINING DOUBLED CIRCUMFLEX ACCENT
707
	while (c <= 0x1ac0)	// ..to COMBINING LATIN SMALL LETTER TURNED W BELOW
708
		charset[i++] = c++;
709
// 1B00..1B7F; Balinese
710
	c = 0x1b00;		// from BALINESE SIGN ULU RICEM
711
	while (c <= 0x1b4b)	// ..to BALINESE LETTER ASYURA SASAK
712
		charset[i++] = c++;
713
	c = 0x1b50;		// from BALINESE DIGIT ZERO
714
	while (c <= 0x1b7c)	// ..to BALINESE MUSICAL SYMBOL LEFT-HAND OPEN PING
715
		charset[i++] = c++;
716
// 1B80..1BBF; Sundanese
717
	c = 0x1b80;		// from SUNDANESE SIGN PANYECEK
718
	while (c <= 0x1bbf)	// ..to SUNDANESE LETTER FINAL M
719
		charset[i++] = c++;
720
// 1BC0..1BFF; Batak
721
	c = 0x1bc0;		// from BATAK LETTER A
722
	while (c <= 0x1bf3)	// ..to BATAK PANONGONAN
723
		charset[i++] = c++;
724
	c = 0x1bfc;		// from BATAK SYMBOL BINDU NA METEK
725
	while (c <= 0x1bff)	// ..to BATAK SYMBOL BINDU PANGOLAT
726
		charset[i++] = c++;
727
// 1C00..1C4F; Lepcha
728
	c = 0x1c00;		// from LEPCHA LETTER KA
729
	while (c <= 0x1c37)	// ..to LEPCHA SIGN NUKTA
730
		charset[i++] = c++;
731
	c = 0x1c3b;		// from LEPCHA PUNCTUATION TA-ROL
732
	while (c <= 0x1c49)	// ..to LEPCHA DIGIT NINE
733
		charset[i++] = c++;
734
	charset[i++] = 0x1c4d;	// LEPCHA LETTER TTA
735
	charset[i++] = 0x1c4f;	// LEPCHA LETTER DDA
736
// 1C50..1C7F; Ol Chiki
737
	c = 0x1c50;		// from OL CHIKI DIGIT ZERO
738
	while (c <= 0x1c7f)	// ..to OL CHIKI PUNCTUATION DOUBLE MUCAAD
739
		charset[i++] = c++;
740
// 1C80..1C8F; Cyrillic Extended-C
741
	c = 0x1c80;		// from CYRILLIC SMALL LETTER ROUNDED VE
742
	while (c <= 0x1c88)	// ..to CYRILLIC SMALL LETTER UNBLENDED UK
743
		charset[i++] = c++;
744
// 1C90..1CBF; Georgian Extended
745
	c = 0x1c90;		// from GEORGIAN MTAVRULI CAPITAL LETTER AN
746
	while (c <= 0x1cba)	// ..to GEORGIAN MTAVRULI CAPITAL LETTER AIN
747
		charset[i++] = c++;
748
	charset[i++] = 0x1cbd;	// GEORGIAN MTAVRULI CAPITAL LETTER AEN
749
	charset[i++] = 0x1cbf;	// GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN
750
// 1CC0..1CCF; Sundanese Supplement
751
	c = 0x1cc0;		// from SUNDANESE PUNCTUATION BINDU SURYA
752
	while (c <= 0x1cc7)	// ..to SUNDANESE PUNCTUATION BINDU BA SATANGA
753
		charset[i++] = c++;
754
// 1CD0..1CFF; Vedic Extensions
755
	c = 0x1cd0;		// from VEDIC TONE KARSHANA
756
	while (c <= 0x1cfa)	// ..to VEDIC SIGN DOUBLE ANUSVARA ANTARGOMUKHA
757
		charset[i++] = c++;
758
// 1D00..1D7F; Phonetic Extensions
759
	c = 0x1d00;		// from LATIN LETTER SMALL CAPITAL A
760
	while (c <= 0x1d7f)	// ..to LATIN SMALL LETTER UPSILON WITH STROKE
761
		charset[i++] = c++;
762
// 1D80..1DBF; Phonetic Extensions Supplement
763
	c = 0x1d80;		// from LATIN SMALL LETTER B WITH PALATAL HOOK
764
	while (c <= 0x1dbf)	// ..to MODIFIER LETTER SMALL THETA
765
		charset[i++] = c++;
766
// 1DC0..1DFF; Combining Diacritical Marks Supplement
767
	c = 0x1dc0;		// from COMBINING DOTTED GRAVE ACCENT
768
	while (c <= 0x1df9)	// ..to COMBINING WIDE INVERTED BRIDGE BELOW
769
		charset[i++] = c++;
770
	c = 0x1dfb;		// from COMBINING DELETION MARK
771
	while (c <= 0x1dff)	// ..to COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW
772
		charset[i++] = c++;
773
// 1E00..1EFF; Latin Extended Additional
774
	c = 0x1e00;		// from LATIN CAPITAL LETTER A WITH RING BELOW
775
	while (c <= 0x1eff)	// ..to LATIN SMALL LETTER Y WITH LOOP
776
		charset[i++] = c++;
777
// 1F00..1FFF; Greek Extended
778
	c = 0x1f00;		// from GREEK SMALL LETTER ALPHA WITH PSILI
779
	while (c <= 0x1f15)	// ..to GREEK SMALL LETTER EPSILON WITH DASIA AND OXIA
780
		charset[i++] = c++;
781
	c = 0x1f18;		// from GREEK CAPITAL LETTER EPSILON WITH PSILI
782
	while (c <= 0x1f1d)	// ..to GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA
783
		charset[i++] = c++;
784
	c = 0x1f20;		// from GREEK SMALL LETTER ETA WITH PSILI
785
	while (c <= 0x1f45)	// ..to GREEK SMALL LETTER OMICRON WITH DASIA AND OXIA
786
		charset[i++] = c++;
787
	c = 0x1f48;		// from GREEK CAPITAL LETTER OMICRON WITH PSILI
788
	while (c <= 0x1f4d)	// ..to GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA
789
		charset[i++] = c++;
790
	c = 0x1f50;		// from GREEK SMALL LETTER UPSILON WITH PSILI
791
	while (c <= 0x1f57)	// ..to GREEK SMALL LETTER UPSILON WITH DASIA AND PERISPOMENI
792
		charset[i++] = c++;
793
	c = 0x1f5f;		// from GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI
794
	while (c <= 0x1f7d)	// ..to GREEK SMALL LETTER OMEGA WITH OXIA
795
		charset[i++] = c++;
796
	c = 0x1f80;		// from GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
797
	while (c <= 0x1fb4)	// ..to GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
798
		charset[i++] = c++;
799
	c = 0x1fb6;		// from GREEK SMALL LETTER ALPHA WITH PERISPOMENI
800
	while (c <= 0x1fc4)	// ..to GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
801
		charset[i++] = c++;
802
	c = 0x1fc6;		// from GREEK SMALL LETTER ETA WITH PERISPOMENI
803
	while (c <= 0x1fd3)	// ..to GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
804
		charset[i++] = c++;
805
	c = 0x1fd6;		// from GREEK SMALL LETTER IOTA WITH PERISPOMENI
806
	while (c <= 0x1fdb)	// ..to GREEK CAPITAL LETTER IOTA WITH OXIA
807
		charset[i++] = c++;
808
	c = 0x1fdd;		// from GREEK DASIA AND VARIA
809
	while (c <= 0x1fef)	// ..to GREEK VARIA
810
		charset[i++] = c++;
811
	charset[i++] = 0x1ff2;	// GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
812
	charset[i++] = 0x1ff4;	// GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
813
	c = 0x1ff6;		// from GREEK SMALL LETTER OMEGA WITH PERISPOMENI
814
	while (c <= 0x1ffe)	// ..to GREEK DASIA
815
		charset[i++] = c++;
816
// 2000..206F; General Punctuation
817
	c = 0x2000;		// from EN QUAD
818
	while (c <= 0x2064)	// ..to INVISIBLE PLUS
819
		charset[i++] = c++;
820
	c = 0x2066;		// from LEFT-TO-RIGHT ISOLATE
821
	while (c <= 0x206f)	// ..to NOMINAL DIGIT SHAPES
822
		charset[i++] = c++;
823
// 2070..209F; Superscripts and Subscripts
824
	charset[i++] = 0x2070;	// SUPERSCRIPT ZERO
825
	charset[i++] = 0x2071;	// SUPERSCRIPT LATIN SMALL LETTER I
826
	c = 0x2074;		// from SUPERSCRIPT FOUR
827
	while (c <= 0x208e)	// ..to SUBSCRIPT RIGHT PARENTHESIS
828
		charset[i++] = c++;
829
	c = 0x2090;		// from LATIN SUBSCRIPT SMALL LETTER A
830
	while (c <= 0x209c)	// ..to LATIN SUBSCRIPT SMALL LETTER T
831
		charset[i++] = c++;
832
// 20A0..20CF; Currency Symbols
833
	c = 0x20a0;		// from EURO-CURRENCY SIGN
834
	while (c <= 0x20bf)	// ..to BITCOIN SIGN
835
		charset[i++] = c++;
836
// 20D0..20FF; Combining Diacritical Marks for Symbols
837
	c = 0x20d0;		// from COMBINING LEFT HARPOON ABOVE
838
	while (c <= 0x20f0)	// ..to COMBINING ASTERISK ABOVE
839
		charset[i++] = c++;
840
// 2100..214F; Letterlike Symbols
841
	c = 0x2100;		// from ACCOUNT OF
842
	while (c <= 0x214f)	// ..to SYMBOL FOR SAMARITAN SOURCE
843
		charset[i++] = c++;
844
// 2150..218F; Number Forms
845
	c = 0x2150;		// from VULGAR FRACTION ONE SEVENTH
846
	while (c <= 0x218b)	// ..to TURNED DIGIT THREE
847
		charset[i++] = c++;
848
// 2190..21FF; Arrows
849
	c = 0x2190;		// from LEFTWARDS ARROW
850
	while (c <= 0x21ff)	// ..to LEFT RIGHT OPEN-HEADED ARROW
851
		charset[i++] = c++;
852
// 2200..22FF; Mathematical Operators
853
	c = 0x2200;		// from FOR ALL
854
	while (c <= 0x22ff)	// ..to Z NOTATION BAG MEMBERSHIP
855
		charset[i++] = c++;
856
// 2300..23FF; Miscellaneous Technical
857
	c = 0x2300;		// from DIAMETER SIGN
858
	while (c <= 0x23ff)	// ..to OBSERVER EYE SYMBOL
859
		charset[i++] = c++;
860
// 2400..243F; Control Pictures
861
	c = 0x2400;		// from SYMBOL FOR NULL
862
	while (c <= 0x2426)	// ..to SYMBOL FOR SUBSTITUTE FORM TWO
863
		charset[i++] = c++;
864
// 2440..245F; Optical Character Recognition
865
	c = 0x2440;		// from OCR HOOK
866
	while (c <= 0x244a)	// ..to OCR DOUBLE BACKSLASH
867
		charset[i++] = c++;
868
// 2460..24FF; Enclosed Alphanumerics
869
	c = 0x2460;		// from CIRCLED DIGIT ONE
870
	while (c <= 0x24ff)	// ..to NEGATIVE CIRCLED DIGIT ZERO
871
		charset[i++] = c++;
872
// 2500..257F; Box Drawing
873
	c = 0x2500;		// from BOX DRAWINGS LIGHT HORIZONTAL
874
	while (c <= 0x257f)	// ..to BOX DRAWINGS HEAVY UP AND LIGHT DOWN
875
		charset[i++] = c++;
876
// 2580..259F; Block Elements
877
	c = 0x2580;		// from UPPER HALF BLOCK
878
	while (c <= 0x259f)	// ..to QUADRANT UPPER RIGHT AND LOWER LEFT AND LOWER RIGHT
879
		charset[i++] = c++;
880
// 25A0..25FF; Geometric Shapes
881
	c = 0x25a0;		// from BLACK SQUARE
882
	while (c <= 0x25ff)	// ..to LOWER RIGHT TRIANGLE
883
		charset[i++] = c++;
884
// 2600..26FF; Miscellaneous Symbols
885
	c = 0x2600;		// from BLACK SUN WITH RAYS
886
	while (c <= 0x26ff)	// ..to WHITE FLAG WITH HORIZONTAL MIDDLE BLACK STRIPE
887
		charset[i++] = c++;
888
// 2700..27BF; Dingbats
889
	c = 0x2700;		// from BLACK SAFETY SCISSORS
890
	while (c <= 0x27bf)	// ..to DOUBLE CURLY LOOP
891
		charset[i++] = c++;
892
// 27C0..27EF; Miscellaneous Mathematical Symbols-A
893
	c = 0x27c0;		// from THREE DIMENSIONAL ANGLE
894
	while (c <= 0x27ef)	// ..to MATHEMATICAL RIGHT FLATTENED PARENTHESIS
895
		charset[i++] = c++;
896
// 27F0..27FF; Supplemental Arrows-A
897
	c = 0x27f0;		// from UPWARDS QUADRUPLE ARROW
898
	while (c <= 0x27ff)	// ..to LONG RIGHTWARDS SQUIGGLE ARROW
899
		charset[i++] = c++;
900
// 2800..28FF; Braille Patterns
901
	c = 0x2800;		// from BRAILLE PATTERN BLANK
902
	while (c <= 0x28ff)	// ..to BRAILLE PATTERN DOTS-12345678
903
		charset[i++] = c++;
904
// 2900..297F; Supplemental Arrows-B
905
	c = 0x2900;		// from RIGHTWARDS TWO-HEADED ARROW WITH VERTICAL STROKE
906
	while (c <= 0x297f)	// ..to DOWN FISH TAIL
907
		charset[i++] = c++;
908
// 2980..29FF; Miscellaneous Mathematical Symbols-B
909
	c = 0x2980;		// from TRIPLE VERTICAL BAR DELIMITER
910
	while (c <= 0x29ff)	// ..to MINY
911
		charset[i++] = c++;
912
// 2A00..2AFF; Supplemental Mathematical Operators
913
	c = 0x2a00;		// from N-ARY CIRCLED DOT OPERATOR
914
	while (c <= 0x2aff)	// ..to N-ARY WHITE VERTICAL BAR
915
		charset[i++] = c++;
916
// 2B00..2BFF; Miscellaneous Symbols and Arrows
917
	c = 0x2b00;		// from NORTH EAST WHITE ARROW
918
	while (c <= 0x2b73)	// ..to DOWNWARDS TRIANGLE-HEADED ARROW TO BAR
919
		charset[i++] = c++;
920
	c = 0x2b76;		// from NORTH WEST TRIANGLE-HEADED ARROW TO BAR
921
	while (c <= 0x2b95)	// ..to RIGHTWARDS BLACK ARROW
922
		charset[i++] = c++;
923
	c = 0x2b97;		// from SYMBOL FOR TYPE A ELECTRONICS
924
	while (c <= 0x2bff)	// ..to HELLSCHREIBER PAUSE SYMBOL
925
		charset[i++] = c++;
926
// 2C00..2C5F; Glagolitic
927
	c = 0x2c00;		// from GLAGOLITIC CAPITAL LETTER AZU
928
	while (c <= 0x2c2e)	// ..to GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE
929
		charset[i++] = c++;
930
	c = 0x2c30;		// from GLAGOLITIC SMALL LETTER AZU
931
	while (c <= 0x2c5e)	// ..to GLAGOLITIC SMALL LETTER LATINATE MYSLITE
932
		charset[i++] = c++;
933
// 2C60..2C7F; Latin Extended-C
934
	c = 0x2c60;		// from LATIN CAPITAL LETTER L WITH DOUBLE BAR
935
	while (c <= 0x2c7f)	// ..to LATIN CAPITAL LETTER Z WITH SWASH TAIL
936
		charset[i++] = c++;
937
// 2C80..2CFF; Coptic
938
	c = 0x2c80;		// from COPTIC CAPITAL LETTER ALFA
939
	while (c <= 0x2cf3)	// ..to COPTIC SMALL LETTER BOHAIRIC KHEI
940
		charset[i++] = c++;
941
	c = 0x2cf9;		// from COPTIC OLD NUBIAN FULL STOP
942
	while (c <= 0x2cff)	// ..to COPTIC MORPHOLOGICAL DIVIDER
943
		charset[i++] = c++;
944
// 2D00..2D2F; Georgian Supplement
945
	c = 0x2d00;		// from GEORGIAN SMALL LETTER AN
946
	while (c <= 0x2d25)	// ..to GEORGIAN SMALL LETTER HOE
947
		charset[i++] = c++;
948
	c = 0x2d27;		// from GEORGIAN SMALL LETTER YN
949
	while (c <= 0x2d2d)	// ..to GEORGIAN SMALL LETTER AEN
950
		charset[i++] = c++;
951
// 2D30..2D7F; Tifinagh
952
	c = 0x2d30;		// from TIFINAGH LETTER YA
953
	while (c <= 0x2d67)	// ..to TIFINAGH LETTER YO
954
		charset[i++] = c++;
955
	charset[i++] = 0x2d6f;	// TIFINAGH MODIFIER LETTER LABIALIZATION MARK
956
	charset[i++] = 0x2d70;	// TIFINAGH SEPARATOR MARK
957
	charset[i++] = 0x2d7f;	// TIFINAGH CONSONANT JOINER
958
// 2D80..2DDF; Ethiopic Extended
959
	c = 0x2d80;		// from ETHIOPIC SYLLABLE LOA
960
	while (c <= 0x2d96)	// ..to ETHIOPIC SYLLABLE GGWE
961
		charset[i++] = c++;
962
	c = 0x2da0;		// from ETHIOPIC SYLLABLE SSA
963
	while (c <= 0x2da6)	// ..to ETHIOPIC SYLLABLE SSO
964
		charset[i++] = c++;
965
	c = 0x2da8;		// from ETHIOPIC SYLLABLE CCA
966
	while (c <= 0x2dae)	// ..to ETHIOPIC SYLLABLE CCO
967
		charset[i++] = c++;
968
	c = 0x2db0;		// from ETHIOPIC SYLLABLE ZZA
969
	while (c <= 0x2db6)	// ..to ETHIOPIC SYLLABLE ZZO
970
		charset[i++] = c++;
971
	c = 0x2db8;		// from ETHIOPIC SYLLABLE CCHA
972
	while (c <= 0x2dbe)	// ..to ETHIOPIC SYLLABLE CCHO
973
		charset[i++] = c++;
974
	c = 0x2dc0;		// from ETHIOPIC SYLLABLE QYA
975
	while (c <= 0x2dc6)	// ..to ETHIOPIC SYLLABLE QYO
976
		charset[i++] = c++;
977
	c = 0x2dc8;		// from ETHIOPIC SYLLABLE KYA
978
	while (c <= 0x2dce)	// ..to ETHIOPIC SYLLABLE KYO
979
		charset[i++] = c++;
980
	c = 0x2dd0;		// from ETHIOPIC SYLLABLE XYA
981
	while (c <= 0x2dd6)	// ..to ETHIOPIC SYLLABLE XYO
982
		charset[i++] = c++;
983
	c = 0x2dd8;		// from ETHIOPIC SYLLABLE GYA
984
	while (c <= 0x2dde)	// ..to ETHIOPIC SYLLABLE GYO
985
		charset[i++] = c++;
986
// 2DE0..2DFF; Cyrillic Extended-A
987
	c = 0x2de0;		// from COMBINING CYRILLIC LETTER BE
988
	while (c <= 0x2dff)	// ..to COMBINING CYRILLIC LETTER IOTIFIED BIG YUS
989
		charset[i++] = c++;
990
// 2E00..2E7F; Supplemental Punctuation
991
	c = 0x2e00;		// from RIGHT ANGLE SUBSTITUTION MARKER
992
	while (c <= 0x2e52)	// ..to TIRONIAN SIGN CAPITAL ET
993
		charset[i++] = c++;
994
// 2E80..2EFF; CJK Radicals Supplement
995
	c = 0x2e80;		// from CJK RADICAL REPEAT
996
	while (c <= 0x2e99)	// ..to CJK RADICAL RAP
997
		charset[i++] = c++;
998
	c = 0x2e9b;		// from CJK RADICAL CHOKE
999
	while (c <= 0x2ef3)	// ..to CJK RADICAL C-SIMPLIFIED TURTLE
1000
		charset[i++] = c++;
1001
// 2F00..2FDF; Kangxi Radicals
1002
	c = 0x2f00;		// from KANGXI RADICAL ONE
1003
	while (c <= 0x2fd5)	// ..to KANGXI RADICAL FLUTE
1004
		charset[i++] = c++;
1005
// 2FF0..2FFF; Ideographic Description Characters
1006
	c = 0x2ff0;		// from IDEOGRAPHIC DESCRIPTION CHARACTER LEFT TO RIGHT
1007
	while (c <= 0x2ffb)	// ..to IDEOGRAPHIC DESCRIPTION CHARACTER OVERLAID
1008
		charset[i++] = c++;
1009
// 3000..303F; CJK Symbols and Punctuation
1010
	c = 0x3000;		// from IDEOGRAPHIC SPACE
1011
	while (c <= 0x303f)	// ..to IDEOGRAPHIC HALF FILL SPACE
1012
		charset[i++] = c++;
1013
// 3040..309F; Hiragana
1014
	c = 0x3041;		// from HIRAGANA LETTER SMALL A
1015
	while (c <= 0x3096)	// ..to HIRAGANA LETTER SMALL KE
1016
		charset[i++] = c++;
1017
	c = 0x3099;		// from COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK
1018
	while (c <= 0x309f)	// ..to HIRAGANA DIGRAPH YORI
1019
		charset[i++] = c++;
1020
// 30A0..30FF; Katakana
1021
	c = 0x30a0;		// from KATAKANA-HIRAGANA DOUBLE HYPHEN
1022
	while (c <= 0x30ff)	// ..to KATAKANA DIGRAPH KOTO
1023
		charset[i++] = c++;
1024
// 3100..312F; Bopomofo
1025
	c = 0x3105;		// from BOPOMOFO LETTER B
1026
	while (c <= 0x312f)	// ..to BOPOMOFO LETTER NN
1027
		charset[i++] = c++;
1028
// 3130..318F; Hangul Compatibility Jamo
1029
	c = 0x3131;		// from HANGUL LETTER KIYEOK
1030
	while (c <= 0x318e)	// ..to HANGUL LETTER ARAEAE
1031
		charset[i++] = c++;
1032
// 3190..319F; Kanbun
1033
	c = 0x3190;		// from IDEOGRAPHIC ANNOTATION LINKING MARK
1034
	while (c <= 0x319f)	// ..to IDEOGRAPHIC ANNOTATION MAN MARK
1035
		charset[i++] = c++;
1036
// 31A0..31BF; Bopomofo Extended
1037
	c = 0x31a0;		// from BOPOMOFO LETTER BU
1038
	while (c <= 0x31bf)	// ..to BOPOMOFO LETTER AH
1039
		charset[i++] = c++;
1040
// 31C0..31EF; CJK Strokes
1041
	c = 0x31c0;		// from CJK STROKE T
1042
	while (c <= 0x31e3)	// ..to CJK STROKE Q
1043
		charset[i++] = c++;
1044
// 31F0..31FF; Katakana Phonetic Extensions
1045
	c = 0x31f0;		// from KATAKANA LETTER SMALL KU
1046
	while (c <= 0x31ff)	// ..to KATAKANA LETTER SMALL RO
1047
		charset[i++] = c++;
1048
// 3200..32FF; Enclosed CJK Letters and Months
1049
	c = 0x3200;		// from PARENTHESIZED HANGUL KIYEOK
1050
	while (c <= 0x321e)	// ..to PARENTHESIZED KOREAN CHARACTER O HU
1051
		charset[i++] = c++;
1052
	c = 0x3220;		// from PARENTHESIZED IDEOGRAPH ONE
1053
	while (c <= 0x32ff)	// ..to SQUARE ERA NAME REIWA
1054
		charset[i++] = c++;
1055
// 3300..33FF; CJK Compatibility
1056
	c = 0x3300;		// from SQUARE APAATO
1057
	while (c <= 0x33ff)	// ..to SQUARE GAL
1058
		charset[i++] = c++;
1059
// 3400..4DBF; CJK Unified Ideographs Extension A
1060
	c = 0x3400;		// from <CJK Ideograph Extension A, First>
1061
	while (c <= 0x4dbf)	// ..to <CJK Ideograph Extension A, Last>
1062
		charset[i++] = c++;
1063
// 4DC0..4DFF; Yijing Hexagram Symbols
1064
	c = 0x4dc0;		// from HEXAGRAM FOR THE CREATIVE HEAVEN
1065
	while (c <= 0x4dff)	// ..to HEXAGRAM FOR BEFORE COMPLETION
1066
		charset[i++] = c++;
1067
// 4E00..9FFF; CJK Unified Ideographs
1068
	c = 0x4e00;		// from <CJK Ideograph, First>
1069
	while (c <= 0x9ffc)	// ..to <CJK Ideograph, Last>
1070
		charset[i++] = c++;
1071
// A000..A48F; Yi Syllables
1072
	c = 0xa000;		// from YI SYLLABLE IT
1073
	while (c <= 0xa48c)	// ..to YI SYLLABLE YYR
1074
		charset[i++] = c++;
1075
// A490..A4CF; Yi Radicals
1076
	c = 0xa490;		// from YI RADICAL QOT
1077
	while (c <= 0xa4c6)	// ..to YI RADICAL KE
1078
		charset[i++] = c++;
1079
// A4D0..A4FF; Lisu
1080
	c = 0xa4d0;		// from LISU LETTER BA
1081
	while (c <= 0xa4ff)	// ..to LISU PUNCTUATION FULL STOP
1082
		charset[i++] = c++;
1083
// A500..A63F; Vai
1084
	c = 0xa500;		// from VAI SYLLABLE EE
1085
	while (c <= 0xa62b)	// ..to VAI SYLLABLE NDOLE DO
1086
		charset[i++] = c++;
1087
// A640..A69F; Cyrillic Extended-B
1088
	c = 0xa640;		// from CYRILLIC CAPITAL LETTER ZEMLYA
1089
	while (c <= 0xa69f)	// ..to COMBINING CYRILLIC LETTER IOTIFIED E
1090
		charset[i++] = c++;
1091
// A6A0..A6FF; Bamum
1092
	c = 0xa6a0;		// from BAMUM LETTER A
1093
	while (c <= 0xa6f7)	// ..to BAMUM QUESTION MARK
1094
		charset[i++] = c++;
1095
// A700..A71F; Modifier Tone Letters
1096
	c = 0xa700;		// from MODIFIER LETTER CHINESE TONE YIN PING
1097
	while (c <= 0xa71f)	// ..to MODIFIER LETTER LOW INVERTED EXCLAMATION MARK
1098
		charset[i++] = c++;
1099
// A720..A7FF; Latin Extended-D
1100
	c = 0xa720;		// from MODIFIER LETTER STRESS AND HIGH TONE
1101
	while (c <= 0xa7bf)	// ..to LATIN SMALL LETTER GLOTTAL U
1102
		charset[i++] = c++;
1103
	c = 0xa7c2;		// from LATIN CAPITAL LETTER ANGLICANA W
1104
	while (c <= 0xa7ca)	// ..to LATIN SMALL LETTER S WITH SHORT STROKE OVERLAY
1105
		charset[i++] = c++;
1106
	c = 0xa7f5;		// from LATIN CAPITAL LETTER REVERSED HALF H
1107
	while (c <= 0xa7ff)	// ..to LATIN EPIGRAPHIC LETTER ARCHAIC M
1108
		charset[i++] = c++;
1109
// A800..A82F; Syloti Nagri
1110
	c = 0xa800;		// from SYLOTI NAGRI LETTER A
1111
	while (c <= 0xa82c)	// ..to SYLOTI NAGRI SIGN ALTERNATE HASANTA
1112
		charset[i++] = c++;
1113
// A830..A83F; Common Indic Number Forms
1114
	c = 0xa830;		// from NORTH INDIC FRACTION ONE QUARTER
1115
	while (c <= 0xa839)	// ..to NORTH INDIC QUANTITY MARK
1116
		charset[i++] = c++;
1117
// A840..A87F; Phags-pa
1118
	c = 0xa840;		// from PHAGS-PA LETTER KA
1119
	while (c <= 0xa877)	// ..to PHAGS-PA MARK DOUBLE SHAD
1120
		charset[i++] = c++;
1121
// A880..A8DF; Saurashtra
1122
	c = 0xa880;		// from SAURASHTRA SIGN ANUSVARA
1123
	while (c <= 0xa8c5)	// ..to SAURASHTRA SIGN CANDRABINDU
1124
		charset[i++] = c++;
1125
	c = 0xa8ce;		// from SAURASHTRA DANDA
1126
	while (c <= 0xa8d9)	// ..to SAURASHTRA DIGIT NINE
1127
		charset[i++] = c++;
1128
// A8E0..A8FF; Devanagari Extended
1129
	c = 0xa8e0;		// from COMBINING DEVANAGARI DIGIT ZERO
1130
	while (c <= 0xa8ff)	// ..to DEVANAGARI VOWEL SIGN AY
1131
		charset[i++] = c++;
1132
// A900..A92F; Kayah Li
1133
	c = 0xa900;		// from KAYAH LI DIGIT ZERO
1134
	while (c <= 0xa92f)	// ..to KAYAH LI SIGN SHYA
1135
		charset[i++] = c++;
1136
// A930..A95F; Rejang
1137
	c = 0xa930;		// from REJANG LETTER KA
1138
	while (c <= 0xa953)	// ..to REJANG VIRAMA
1139
		charset[i++] = c++;
1140
	charset[i++] = 0xa95f;	// REJANG SECTION MARK
1141
// A960..A97F; Hangul Jamo Extended-A
1142
	c = 0xa960;		// from HANGUL CHOSEONG TIKEUT-MIEUM
1143
	while (c <= 0xa97c)	// ..to HANGUL CHOSEONG SSANGYEORINHIEUH
1144
		charset[i++] = c++;
1145
// A980..A9DF; Javanese
1146
	c = 0xa980;		// from JAVANESE SIGN PANYANGGA
1147
	while (c <= 0xa9cd)	// ..to JAVANESE TURNED PADA PISELEH
1148
		charset[i++] = c++;
1149
	c = 0xa9cf;		// from JAVANESE PANGRANGKEP
1150
	while (c <= 0xa9d9)	// ..to JAVANESE DIGIT NINE
1151
		charset[i++] = c++;
1152
	charset[i++] = 0xa9de;	// JAVANESE PADA TIRTA TUMETES
1153
	charset[i++] = 0xa9df;	// JAVANESE PADA ISEN-ISEN
1154
// A9E0..A9FF; Myanmar Extended-B
1155
	c = 0xa9e0;		// from MYANMAR LETTER SHAN GHA
1156
	while (c <= 0xa9fe)	// ..to MYANMAR LETTER TAI LAING BHA
1157
		charset[i++] = c++;
1158
// AA00..AA5F; Cham
1159
	c = 0xaa00;		// from CHAM LETTER A
1160
	while (c <= 0xaa36)	// ..to CHAM CONSONANT SIGN WA
1161
		charset[i++] = c++;
1162
	c = 0xaa40;		// from CHAM LETTER FINAL K
1163
	while (c <= 0xaa4d)	// ..to CHAM CONSONANT SIGN FINAL H
1164
		charset[i++] = c++;
1165
	c = 0xaa50;		// from CHAM DIGIT ZERO
1166
	while (c <= 0xaa59)	// ..to CHAM DIGIT NINE
1167
		charset[i++] = c++;
1168
	c = 0xaa5c;		// from CHAM PUNCTUATION SPIRAL
1169
	while (c <= 0xaa5f)	// ..to CHAM PUNCTUATION TRIPLE DANDA
1170
		charset[i++] = c++;
1171
// AA60..AA7F; Myanmar Extended-A
1172
	c = 0xaa60;		// from MYANMAR LETTER KHAMTI GA
1173
	while (c <= 0xaa7f)	// ..to MYANMAR LETTER SHWE PALAUNG SHA
1174
		charset[i++] = c++;
1175
// AA80..AADF; Tai Viet
1176
	c = 0xaa80;		// from TAI VIET LETTER LOW KO
1177
	while (c <= 0xaac2)	// ..to TAI VIET TONE MAI SONG
1178
		charset[i++] = c++;
1179
	c = 0xaadb;		// from TAI VIET SYMBOL KON
1180
	while (c <= 0xaadf)	// ..to TAI VIET SYMBOL KOI KOI
1181
		charset[i++] = c++;
1182
// AAE0..AAFF; Meetei Mayek Extensions
1183
	c = 0xaae0;		// from MEETEI MAYEK LETTER E
1184
	while (c <= 0xaaf6)	// ..to MEETEI MAYEK VIRAMA
1185
		charset[i++] = c++;
1186
// AB00..AB2F; Ethiopic Extended-A
1187
	c = 0xab01;		// from ETHIOPIC SYLLABLE TTHU
1188
	while (c <= 0xab06)	// ..to ETHIOPIC SYLLABLE TTHO
1189
		charset[i++] = c++;
1190
	c = 0xab09;		// from ETHIOPIC SYLLABLE DDHU
1191
	while (c <= 0xab0e)	// ..to ETHIOPIC SYLLABLE DDHO
1192
		charset[i++] = c++;
1193
	c = 0xab11;		// from ETHIOPIC SYLLABLE DZU
1194
	while (c <= 0xab16)	// ..to ETHIOPIC SYLLABLE DZO
1195
		charset[i++] = c++;
1196
	c = 0xab20;		// from ETHIOPIC SYLLABLE CCHHA
1197
	while (c <= 0xab26)	// ..to ETHIOPIC SYLLABLE CCHHO
1198
		charset[i++] = c++;
1199
	c = 0xab28;		// from ETHIOPIC SYLLABLE BBA
1200
	while (c <= 0xab2e)	// ..to ETHIOPIC SYLLABLE BBO
1201
		charset[i++] = c++;
1202
// AB30..AB6F; Latin Extended-E
1203
	c = 0xab30;		// from LATIN SMALL LETTER BARRED ALPHA
1204
	while (c <= 0xab6b)	// ..to MODIFIER LETTER RIGHT TACK
1205
		charset[i++] = c++;
1206
// AB70..ABBF; Cherokee Supplement
1207
	c = 0xab70;		// from CHEROKEE SMALL LETTER A
1208
	while (c <= 0xabbf)	// ..to CHEROKEE SMALL LETTER YA
1209
		charset[i++] = c++;
1210
// ABC0..ABFF; Meetei Mayek
1211
	c = 0xabc0;		// from MEETEI MAYEK LETTER KOK
1212
	while (c <= 0xabed)	// ..to MEETEI MAYEK APUN IYEK
1213
		charset[i++] = c++;
1214
	c = 0xabf0;		// from MEETEI MAYEK DIGIT ZERO
1215
	while (c <= 0xabf9)	// ..to MEETEI MAYEK DIGIT NINE
1216
		charset[i++] = c++;
1217
// AC00..D7AF; Hangul Syllables
1218
	c = 0xac00;		// from <Hangul Syllable, First>
1219
	while (c <= 0xd7a3)	// ..to <Hangul Syllable, Last>
1220
		charset[i++] = c++;
1221
// D7B0..D7FF; Hangul Jamo Extended-B
1222
	c = 0xd7b0;		// from HANGUL JUNGSEONG O-YEO
1223
	while (c <= 0xd7c6)	// ..to HANGUL JUNGSEONG ARAEA-E
1224
		charset[i++] = c++;
1225
	c = 0xd7cb;		// from HANGUL JONGSEONG NIEUN-RIEUL
1226
	while (c <= 0xd7fb)	// ..to HANGUL JONGSEONG PHIEUPH-THIEUTH
1227
		charset[i++] = c++;
1228
// D800..DB7F; High Surrogates
1229
// DB80..DBFF; High Private Use Surrogates
1230
// DC00..DFFF; Low Surrogates
1231
// E000..F8FF; Private Use Area
1232
// F900..FAFF; CJK Compatibility Ideographs
1233
	c = 0xf900;		// from CJK COMPATIBILITY IDEOGRAPH-F900
1234
	while (c <= 0xfa6d)	// ..to CJK COMPATIBILITY IDEOGRAPH-FA6D
1235
		charset[i++] = c++;
1236
	c = 0xfa70;		// from CJK COMPATIBILITY IDEOGRAPH-FA70
1237
	while (c <= 0xfad9)	// ..to CJK COMPATIBILITY IDEOGRAPH-FAD9
1238
		charset[i++] = c++;
1239
// FB00..FB4F; Alphabetic Presentation Forms
1240
	c = 0xfb00;		// from LATIN SMALL LIGATURE FF
1241
	while (c <= 0xfb06)	// ..to LATIN SMALL LIGATURE ST
1242
		charset[i++] = c++;
1243
	c = 0xfb13;		// from ARMENIAN SMALL LIGATURE MEN NOW
1244
	while (c <= 0xfb17)	// ..to ARMENIAN SMALL LIGATURE MEN XEH
1245
		charset[i++] = c++;
1246
	c = 0xfb1d;		// from HEBREW LETTER YOD WITH HIRIQ
1247
	while (c <= 0xfb36)	// ..to HEBREW LETTER ZAYIN WITH DAGESH
1248
		charset[i++] = c++;
1249
	c = 0xfb38;		// from HEBREW LETTER TET WITH DAGESH
1250
	while (c <= 0xfb3c)	// ..to HEBREW LETTER LAMED WITH DAGESH
1251
		charset[i++] = c++;
1252
	charset[i++] = 0xfb40;	// HEBREW LETTER NUN WITH DAGESH
1253
	charset[i++] = 0xfb41;	// HEBREW LETTER SAMEKH WITH DAGESH
1254
	charset[i++] = 0xfb43;	// HEBREW LETTER FINAL PE WITH DAGESH
1255
	charset[i++] = 0xfb44;	// HEBREW LETTER PE WITH DAGESH
1256
	c = 0xfb46;		// from HEBREW LETTER TSADI WITH DAGESH
1257
	while (c <= 0xfb4f)	// ..to HEBREW LIGATURE ALEF LAMED
1258
		charset[i++] = c++;
1259
// FB50..FDFF; Arabic Presentation Forms-A
1260
	c = 0xfb50;		// from ARABIC LETTER ALEF WASLA ISOLATED FORM
1261
	while (c <= 0xfbc1)	// ..to ARABIC SYMBOL SMALL TAH BELOW
1262
		charset[i++] = c++;
1263
	c = 0xfbd3;		// from ARABIC LETTER NG ISOLATED FORM
1264
	while (c <= 0xfd3f)	// ..to ORNATE RIGHT PARENTHESIS
1265
		charset[i++] = c++;
1266
	c = 0xfd50;		// from ARABIC LIGATURE TEH WITH JEEM WITH MEEM INITIAL FORM
1267
	while (c <= 0xfd8f)	// ..to ARABIC LIGATURE MEEM WITH KHAH WITH MEEM INITIAL FORM
1268
		charset[i++] = c++;
1269
	c = 0xfd92;		// from ARABIC LIGATURE MEEM WITH JEEM WITH KHAH INITIAL FORM
1270
	while (c <= 0xfdc7)	// ..to ARABIC LIGATURE NOON WITH JEEM WITH YEH FINAL FORM
1271
		charset[i++] = c++;
1272
	c = 0xfdf0;		// from ARABIC LIGATURE SALLA USED AS KORANIC STOP SIGN ISOLATED FORM
1273
	while (c <= 0xfdfd)	// ..to ARABIC LIGATURE BISMILLAH AR-RAHMAN AR-RAHEEM
1274
		charset[i++] = c++;
1275
// FE00..FE0F; Variation Selectors
1276
	c = 0xfe00;		// from VARIATION SELECTOR-1
1277
	while (c <= 0xfe0f)	// ..to VARIATION SELECTOR-16
1278
		charset[i++] = c++;
1279
// FE10..FE1F; Vertical Forms
1280
	c = 0xfe10;		// from PRESENTATION FORM FOR VERTICAL COMMA
1281
	while (c <= 0xfe19)	// ..to PRESENTATION FORM FOR VERTICAL HORIZONTAL ELLIPSIS
1282
		charset[i++] = c++;
1283
// FE20..FE2F; Combining Half Marks
1284
	c = 0xfe20;		// from COMBINING LIGATURE LEFT HALF
1285
	while (c <= 0xfe2f)	// ..to COMBINING CYRILLIC TITLO RIGHT HALF
1286
		charset[i++] = c++;
1287
// FE30..FE4F; CJK Compatibility Forms
1288
	c = 0xfe30;		// from PRESENTATION FORM FOR VERTICAL TWO DOT LEADER
1289
	while (c <= 0xfe4f)	// ..to WAVY LOW LINE
1290
		charset[i++] = c++;
1291
// FE50..FE6F; Small Form Variants
1292
	charset[i++] = 0xfe50;	// SMALL COMMA
1293
	charset[i++] = 0xfe52;	// SMALL FULL STOP
1294
	c = 0xfe54;		// from SMALL SEMICOLON
1295
	while (c <= 0xfe66)	// ..to SMALL EQUALS SIGN
1296
		charset[i++] = c++;
1297
	c = 0xfe68;		// from SMALL REVERSE SOLIDUS
1298
	while (c <= 0xfe6b)	// ..to SMALL COMMERCIAL AT
1299
		charset[i++] = c++;
1300
// FE70..FEFF; Arabic Presentation Forms-B
1301
	c = 0xfe70;		// from ARABIC FATHATAN ISOLATED FORM
1302
	while (c <= 0xfe74)	// ..to ARABIC KASRATAN ISOLATED FORM
1303
		charset[i++] = c++;
1304
	c = 0xfe76;		// from ARABIC FATHA ISOLATED FORM
1305
	while (c <= 0xfefc)	// ..to ARABIC LIGATURE LAM WITH ALEF FINAL FORM
1306
		charset[i++] = c++;
1307
	charset[i++] = 0xfeff;	// ZERO WIDTH NO-BREAK SPACE
1308
// FF00..FFEF; Halfwidth and Fullwidth Forms
1309
	c = 0xff01;		// from FULLWIDTH EXCLAMATION MARK
1310
	while (c <= 0xffbe)	// ..to HALFWIDTH HANGUL LETTER HIEUH
1311
		charset[i++] = c++;
1312
	c = 0xffc2;		// from HALFWIDTH HANGUL LETTER A
1313
	while (c <= 0xffc7)	// ..to HALFWIDTH HANGUL LETTER E
1314
		charset[i++] = c++;
1315
	c = 0xffca;		// from HALFWIDTH HANGUL LETTER YEO
1316
	while (c <= 0xffcf)	// ..to HALFWIDTH HANGUL LETTER OE
1317
		charset[i++] = c++;
1318
	c = 0xffd2;		// from HALFWIDTH HANGUL LETTER YO
1319
	while (c <= 0xffd7)	// ..to HALFWIDTH HANGUL LETTER YU
1320
		charset[i++] = c++;
1321
	charset[i++] = 0xffda;	// HALFWIDTH HANGUL LETTER EU
1322
	charset[i++] = 0xffdc;	// HALFWIDTH HANGUL LETTER I
1323
	c = 0xffe0;		// from FULLWIDTH CENT SIGN
1324
	while (c <= 0xffe6)	// ..to FULLWIDTH WON SIGN
1325
		charset[i++] = c++;
1326
	c = 0xffe8;		// from HALFWIDTH FORMS LIGHT VERTICAL
1327
	while (c <= 0xffee)	// ..to HALFWIDTH WHITE CIRCLE
1328
		charset[i++] = c++;
1329
// FFF0..FFFF; Specials
1330
	c = 0xfff9;		// from INTERLINEAR ANNOTATION ANCHOR
1331
	while (c <= 0xfffd)	// ..to REPLACEMENT CHARACTER
1332
		charset[i++] = c++;
1333

1334
/* Zero-terminate it, and cache the first character */
1335
	charset[i] = 0;
1336
	c0 = charset[0];
1337

1338
	last = minlength - 1;
1339
	i = 0;
1340
	while (i <= last) {
1341
		id[i] = 0;
1342
		word[i++] = c0;
1343
	}
1344
	lastid = -1;
1345
	word[i] = 0;
1346

1347
/* We must init word with dummy data, it doesn't get set until filter() */
1348
	word = 1;
1349
}
1350

1351
void generate()
1352
{
1353
	int i;
1354

1355
/* Handle the typical case specially */
1356
	if (word[last] = charset[++lastid]) return;
1357

1358
	lastid = 0;
1359
	word[i = last] = c0;
1360
	while (i--) {			// Have a preceding position?
1361
		if (word[i] = charset[++id[i]]) return;
1362
		id[i] = 0;
1363
		word[i] = c0;
1364
	}
1365

1366
	if (++last < maxlength) {	// Next length?
1367
		id[last] = lastid = 0;
1368
		word[last] = c0;
1369
		word[last + 1] = 0;
1370
	} else				// We're done
1371
		word = 0;
1372
}
1373

1374
void restore()
1375
{
1376
	int i, c;
1377

1378
	/* Calculate the current length and infer the character indices */
1379
	last = 0;
1380
	while (c = word[last]) {
1381
		i = 0; while (charset[i] != c && charset[i]) i++;
1382
		if (!charset[i]) i = 0;	// Not found
1383
		id[last++] = i;
1384
	}
1385
	lastid = id[--last];
1386
}
1387

1388