Shortcuts on this page
r m x toggle line displays
j k next/prev highlighted chunk
0 (zero) top of page
1 (one) first highlighted chunk
1from __future__ import annotations
3from codecs import BOM_UTF8, BOM_UTF16_BE, BOM_UTF16_LE, BOM_UTF32_BE, BOM_UTF32_LE
4from encodings.aliases import aliases
5from re import IGNORECASE
6from re import compile as re_compile
8# Contain for each eligible encoding a list of/item bytes SIG/BOM
9ENCODING_MARKS: dict[str, bytes | list[bytes]] = {
10 "utf_8": BOM_UTF8,
11 "utf_7": [
12 b"\x2b\x2f\x76\x38",
13 b"\x2b\x2f\x76\x39",
14 b"\x2b\x2f\x76\x2b",
15 b"\x2b\x2f\x76\x2f",
16 ],
17 "gb18030": b"\x84\x31\x95\x33",
18 "utf_32": [BOM_UTF32_BE, BOM_UTF32_LE],
19 "utf_16": [BOM_UTF16_BE, BOM_UTF16_LE],
20}
22TOO_SMALL_SEQUENCE: int = 32
23TOO_BIG_SEQUENCE: int = int(10e6)
25UTF8_MAXIMAL_ALLOCATION: int = 1_112_064
27# Up-to-date Unicode ucd/17.0.0
28UNICODE_RANGES_COMBINED: dict[str, range] = {
29 "Control character": range(32),
30 "Basic Latin": range(32, 128),
31 "Latin-1 Supplement": range(128, 256),
32 "Latin Extended-A": range(256, 384),
33 "Latin Extended-B": range(384, 592),
34 "IPA Extensions": range(592, 688),
35 "Spacing Modifier Letters": range(688, 768),
36 "Combining Diacritical Marks": range(768, 880),
37 "Greek and Coptic": range(880, 1024),
38 "Cyrillic": range(1024, 1280),
39 "Cyrillic Supplement": range(1280, 1328),
40 "Armenian": range(1328, 1424),
41 "Hebrew": range(1424, 1536),
42 "Arabic": range(1536, 1792),
43 "Syriac": range(1792, 1872),
44 "Arabic Supplement": range(1872, 1920),
45 "Thaana": range(1920, 1984),
46 "NKo": range(1984, 2048),
47 "Samaritan": range(2048, 2112),
48 "Mandaic": range(2112, 2144),
49 "Syriac Supplement": range(2144, 2160),
50 "Arabic Extended-B": range(2160, 2208),
51 "Arabic Extended-A": range(2208, 2304),
52 "Devanagari": range(2304, 2432),
53 "Bengali": range(2432, 2560),
54 "Gurmukhi": range(2560, 2688),
55 "Gujarati": range(2688, 2816),
56 "Oriya": range(2816, 2944),
57 "Tamil": range(2944, 3072),
58 "Telugu": range(3072, 3200),
59 "Kannada": range(3200, 3328),
60 "Malayalam": range(3328, 3456),
61 "Sinhala": range(3456, 3584),
62 "Thai": range(3584, 3712),
63 "Lao": range(3712, 3840),
64 "Tibetan": range(3840, 4096),
65 "Myanmar": range(4096, 4256),
66 "Georgian": range(4256, 4352),
67 "Hangul Jamo": range(4352, 4608),
68 "Ethiopic": range(4608, 4992),
69 "Ethiopic Supplement": range(4992, 5024),
70 "Cherokee": range(5024, 5120),
71 "Unified Canadian Aboriginal Syllabics": range(5120, 5760),
72 "Ogham": range(5760, 5792),
73 "Runic": range(5792, 5888),
74 "Tagalog": range(5888, 5920),
75 "Hanunoo": range(5920, 5952),
76 "Buhid": range(5952, 5984),
77 "Tagbanwa": range(5984, 6016),
78 "Khmer": range(6016, 6144),
79 "Mongolian": range(6144, 6320),
80 "Unified Canadian Aboriginal Syllabics Extended": range(6320, 6400),
81 "Limbu": range(6400, 6480),
82 "Tai Le": range(6480, 6528),
83 "New Tai Lue": range(6528, 6624),
84 "Khmer Symbols": range(6624, 6656),
85 "Buginese": range(6656, 6688),
86 "Tai Tham": range(6688, 6832),
87 "Combining Diacritical Marks Extended": range(6832, 6912),
88 "Balinese": range(6912, 7040),
89 "Sundanese": range(7040, 7104),
90 "Batak": range(7104, 7168),
91 "Lepcha": range(7168, 7248),
92 "Ol Chiki": range(7248, 7296),
93 "Cyrillic Extended-C": range(7296, 7312),
94 "Georgian Extended": range(7312, 7360),
95 "Sundanese Supplement": range(7360, 7376),
96 "Vedic Extensions": range(7376, 7424),
97 "Phonetic Extensions": range(7424, 7552),
98 "Phonetic Extensions Supplement": range(7552, 7616),
99 "Combining Diacritical Marks Supplement": range(7616, 7680),
100 "Latin Extended Additional": range(7680, 7936),
101 "Greek Extended": range(7936, 8192),
102 "General Punctuation": range(8192, 8304),
103 "Superscripts and Subscripts": range(8304, 8352),
104 "Currency Symbols": range(8352, 8400),
105 "Combining Diacritical Marks for Symbols": range(8400, 8448),
106 "Letterlike Symbols": range(8448, 8528),
107 "Number Forms": range(8528, 8592),
108 "Arrows": range(8592, 8704),
109 "Mathematical Operators": range(8704, 8960),
110 "Miscellaneous Technical": range(8960, 9216),
111 "Control Pictures": range(9216, 9280),
112 "Optical Character Recognition": range(9280, 9312),
113 "Enclosed Alphanumerics": range(9312, 9472),
114 "Box Drawing": range(9472, 9600),
115 "Block Elements": range(9600, 9632),
116 "Geometric Shapes": range(9632, 9728),
117 "Miscellaneous Symbols": range(9728, 9984),
118 "Dingbats": range(9984, 10176),
119 "Miscellaneous Mathematical Symbols-A": range(10176, 10224),
120 "Supplemental Arrows-A": range(10224, 10240),
121 "Braille Patterns": range(10240, 10496),
122 "Supplemental Arrows-B": range(10496, 10624),
123 "Miscellaneous Mathematical Symbols-B": range(10624, 10752),
124 "Supplemental Mathematical Operators": range(10752, 11008),
125 "Miscellaneous Symbols and Arrows": range(11008, 11264),
126 "Glagolitic": range(11264, 11360),
127 "Latin Extended-C": range(11360, 11392),
128 "Coptic": range(11392, 11520),
129 "Georgian Supplement": range(11520, 11568),
130 "Tifinagh": range(11568, 11648),
131 "Ethiopic Extended": range(11648, 11744),
132 "Cyrillic Extended-A": range(11744, 11776),
133 "Supplemental Punctuation": range(11776, 11904),
134 "CJK Radicals Supplement": range(11904, 12032),
135 "Kangxi Radicals": range(12032, 12256),
136 "Ideographic Description Characters": range(12272, 12288),
137 "CJK Symbols and Punctuation": range(12288, 12352),
138 "Hiragana": range(12352, 12448),
139 "Katakana": range(12448, 12544),
140 "Bopomofo": range(12544, 12592),
141 "Hangul Compatibility Jamo": range(12592, 12688),
142 "Kanbun": range(12688, 12704),
143 "Bopomofo Extended": range(12704, 12736),
144 "CJK Strokes": range(12736, 12784),
145 "Katakana Phonetic Extensions": range(12784, 12800),
146 "Enclosed CJK Letters and Months": range(12800, 13056),
147 "CJK Compatibility": range(13056, 13312),
148 "CJK Unified Ideographs Extension A": range(13312, 19904),
149 "Yijing Hexagram Symbols": range(19904, 19968),
150 "CJK Unified Ideographs": range(19968, 40960),
151 "Yi Syllables": range(40960, 42128),
152 "Yi Radicals": range(42128, 42192),
153 "Lisu": range(42192, 42240),
154 "Vai": range(42240, 42560),
155 "Cyrillic Extended-B": range(42560, 42656),
156 "Bamum": range(42656, 42752),
157 "Modifier Tone Letters": range(42752, 42784),
158 "Latin Extended-D": range(42784, 43008),
159 "Syloti Nagri": range(43008, 43056),
160 "Common Indic Number Forms": range(43056, 43072),
161 "Phags-pa": range(43072, 43136),
162 "Saurashtra": range(43136, 43232),
163 "Devanagari Extended": range(43232, 43264),
164 "Kayah Li": range(43264, 43312),
165 "Rejang": range(43312, 43360),
166 "Hangul Jamo Extended-A": range(43360, 43392),
167 "Javanese": range(43392, 43488),
168 "Myanmar Extended-B": range(43488, 43520),
169 "Cham": range(43520, 43616),
170 "Myanmar Extended-A": range(43616, 43648),
171 "Tai Viet": range(43648, 43744),
172 "Meetei Mayek Extensions": range(43744, 43776),
173 "Ethiopic Extended-A": range(43776, 43824),
174 "Latin Extended-E": range(43824, 43888),
175 "Cherokee Supplement": range(43888, 43968),
176 "Meetei Mayek": range(43968, 44032),
177 "Hangul Syllables": range(44032, 55216),
178 "Hangul Jamo Extended-B": range(55216, 55296),
179 "High Surrogates": range(55296, 56192),
180 "High Private Use Surrogates": range(56192, 56320),
181 "Low Surrogates": range(56320, 57344),
182 "Private Use Area": range(57344, 63744),
183 "CJK Compatibility Ideographs": range(63744, 64256),
184 "Alphabetic Presentation Forms": range(64256, 64336),
185 "Arabic Presentation Forms-A": range(64336, 65024),
186 "Variation Selectors": range(65024, 65040),
187 "Vertical Forms": range(65040, 65056),
188 "Combining Half Marks": range(65056, 65072),
189 "CJK Compatibility Forms": range(65072, 65104),
190 "Small Form Variants": range(65104, 65136),
191 "Arabic Presentation Forms-B": range(65136, 65280),
192 "Halfwidth and Fullwidth Forms": range(65280, 65520),
193 "Specials": range(65520, 65536),
194 "Linear B Syllabary": range(65536, 65664),
195 "Linear B Ideograms": range(65664, 65792),
196 "Aegean Numbers": range(65792, 65856),
197 "Ancient Greek Numbers": range(65856, 65936),
198 "Ancient Symbols": range(65936, 66000),
199 "Phaistos Disc": range(66000, 66048),
200 "Lycian": range(66176, 66208),
201 "Carian": range(66208, 66272),
202 "Coptic Epact Numbers": range(66272, 66304),
203 "Old Italic": range(66304, 66352),
204 "Gothic": range(66352, 66384),
205 "Old Permic": range(66384, 66432),
206 "Ugaritic": range(66432, 66464),
207 "Old Persian": range(66464, 66528),
208 "Deseret": range(66560, 66640),
209 "Shavian": range(66640, 66688),
210 "Osmanya": range(66688, 66736),
211 "Osage": range(66736, 66816),
212 "Elbasan": range(66816, 66864),
213 "Caucasian Albanian": range(66864, 66928),
214 "Vithkuqi": range(66928, 67008),
215 "Todhri": range(67008, 67072),
216 "Linear A": range(67072, 67456),
217 "Latin Extended-F": range(67456, 67520),
218 "Cypriot Syllabary": range(67584, 67648),
219 "Imperial Aramaic": range(67648, 67680),
220 "Palmyrene": range(67680, 67712),
221 "Nabataean": range(67712, 67760),
222 "Hatran": range(67808, 67840),
223 "Phoenician": range(67840, 67872),
224 "Lydian": range(67872, 67904),
225 "Sidetic": range(67904, 67936),
226 "Meroitic Hieroglyphs": range(67968, 68000),
227 "Meroitic Cursive": range(68000, 68096),
228 "Kharoshthi": range(68096, 68192),
229 "Old South Arabian": range(68192, 68224),
230 "Old North Arabian": range(68224, 68256),
231 "Manichaean": range(68288, 68352),
232 "Avestan": range(68352, 68416),
233 "Inscriptional Parthian": range(68416, 68448),
234 "Inscriptional Pahlavi": range(68448, 68480),
235 "Psalter Pahlavi": range(68480, 68528),
236 "Old Turkic": range(68608, 68688),
237 "Old Hungarian": range(68736, 68864),
238 "Hanifi Rohingya": range(68864, 68928),
239 "Garay": range(68928, 69008),
240 "Rumi Numeral Symbols": range(69216, 69248),
241 "Yezidi": range(69248, 69312),
242 "Arabic Extended-C": range(69312, 69376),
243 "Old Sogdian": range(69376, 69424),
244 "Sogdian": range(69424, 69488),
245 "Old Uyghur": range(69488, 69552),
246 "Chorasmian": range(69552, 69600),
247 "Elymaic": range(69600, 69632),
248 "Brahmi": range(69632, 69760),
249 "Kaithi": range(69760, 69840),
250 "Sora Sompeng": range(69840, 69888),
251 "Chakma": range(69888, 69968),
252 "Mahajani": range(69968, 70016),
253 "Sharada": range(70016, 70112),
254 "Sinhala Archaic Numbers": range(70112, 70144),
255 "Khojki": range(70144, 70224),
256 "Multani": range(70272, 70320),
257 "Khudawadi": range(70320, 70400),
258 "Grantha": range(70400, 70528),
259 "Tulu-Tigalari": range(70528, 70656),
260 "Newa": range(70656, 70784),
261 "Tirhuta": range(70784, 70880),
262 "Siddham": range(71040, 71168),
263 "Modi": range(71168, 71264),
264 "Mongolian Supplement": range(71264, 71296),
265 "Takri": range(71296, 71376),
266 "Myanmar Extended-C": range(71376, 71424),
267 "Ahom": range(71424, 71504),
268 "Dogra": range(71680, 71760),
269 "Warang Citi": range(71840, 71936),
270 "Dives Akuru": range(71936, 72032),
271 "Nandinagari": range(72096, 72192),
272 "Zanabazar Square": range(72192, 72272),
273 "Soyombo": range(72272, 72368),
274 "Unified Canadian Aboriginal Syllabics Extended-A": range(72368, 72384),
275 "Pau Cin Hau": range(72384, 72448),
276 "Devanagari Extended-A": range(72448, 72544),
277 "Sharada Supplement": range(72544, 72576),
278 "Sunuwar": range(72640, 72704),
279 "Bhaiksuki": range(72704, 72816),
280 "Marchen": range(72816, 72896),
281 "Masaram Gondi": range(72960, 73056),
282 "Gunjala Gondi": range(73056, 73136),
283 "Tolong Siki": range(73136, 73200),
284 "Makasar": range(73440, 73472),
285 "Kawi": range(73472, 73568),
286 "Lisu Supplement": range(73648, 73664),
287 "Tamil Supplement": range(73664, 73728),
288 "Cuneiform": range(73728, 74752),
289 "Cuneiform Numbers and Punctuation": range(74752, 74880),
290 "Early Dynastic Cuneiform": range(74880, 75088),
291 "Cypro-Minoan": range(77712, 77824),
292 "Egyptian Hieroglyphs": range(77824, 78896),
293 "Egyptian Hieroglyph Format Controls": range(78896, 78944),
294 "Egyptian Hieroglyphs Extended-A": range(78944, 82944),
295 "Anatolian Hieroglyphs": range(82944, 83584),
296 "Gurung Khema": range(90368, 90432),
297 "Bamum Supplement": range(92160, 92736),
298 "Mro": range(92736, 92784),
299 "Tangsa": range(92784, 92880),
300 "Bassa Vah": range(92880, 92928),
301 "Pahawh Hmong": range(92928, 93072),
302 "Kirat Rai": range(93504, 93568),
303 "Medefaidrin": range(93760, 93856),
304 "Beria Erfe": range(93856, 93920),
305 "Miao": range(93952, 94112),
306 "Ideographic Symbols and Punctuation": range(94176, 94208),
307 "Tangut": range(94208, 100352),
308 "Tangut Components": range(100352, 101120),
309 "Khitan Small Script": range(101120, 101632),
310 "Tangut Supplement": range(101632, 101760),
311 "Tangut Components Supplement": range(101760, 101888),
312 "Kana Extended-B": range(110576, 110592),
313 "Kana Supplement": range(110592, 110848),
314 "Kana Extended-A": range(110848, 110896),
315 "Small Kana Extension": range(110896, 110960),
316 "Nushu": range(110960, 111360),
317 "Duployan": range(113664, 113824),
318 "Shorthand Format Controls": range(113824, 113840),
319 "Symbols for Legacy Computing Supplement": range(117760, 118464),
320 "Miscellaneous Symbols Supplement": range(118464, 118528),
321 "Znamenny Musical Notation": range(118528, 118736),
322 "Byzantine Musical Symbols": range(118784, 119040),
323 "Musical Symbols": range(119040, 119296),
324 "Ancient Greek Musical Notation": range(119296, 119376),
325 "Kaktovik Numerals": range(119488, 119520),
326 "Mayan Numerals": range(119520, 119552),
327 "Tai Xuan Jing Symbols": range(119552, 119648),
328 "Counting Rod Numerals": range(119648, 119680),
329 "Mathematical Alphanumeric Symbols": range(119808, 120832),
330 "Sutton SignWriting": range(120832, 121520),
331 "Latin Extended-G": range(122624, 122880),
332 "Glagolitic Supplement": range(122880, 122928),
333 "Cyrillic Extended-D": range(122928, 123024),
334 "Nyiakeng Puachue Hmong": range(123136, 123216),
335 "Toto": range(123536, 123584),
336 "Wancho": range(123584, 123648),
337 "Nag Mundari": range(124112, 124160),
338 "Ol Onal": range(124368, 124416),
339 "Tai Yo": range(124608, 124672),
340 "Ethiopic Extended-B": range(124896, 124928),
341 "Mende Kikakui": range(124928, 125152),
342 "Adlam": range(125184, 125280),
343 "Indic Siyaq Numbers": range(126064, 126144),
344 "Ottoman Siyaq Numbers": range(126208, 126288),
345 "Arabic Mathematical Alphabetic Symbols": range(126464, 126720),
346 "Mahjong Tiles": range(126976, 127024),
347 "Domino Tiles": range(127024, 127136),
348 "Playing Cards": range(127136, 127232),
349 "Enclosed Alphanumeric Supplement": range(127232, 127488),
350 "Enclosed Ideographic Supplement": range(127488, 127744),
351 "Miscellaneous Symbols and Pictographs": range(127744, 128512),
352 "Emoticons": range(128512, 128592),
353 "Ornamental Dingbats": range(128592, 128640),
354 "Transport and Map Symbols": range(128640, 128768),
355 "Alchemical Symbols": range(128768, 128896),
356 "Geometric Shapes Extended": range(128896, 129024),
357 "Supplemental Arrows-C": range(129024, 129280),
358 "Supplemental Symbols and Pictographs": range(129280, 129536),
359 "Chess Symbols": range(129536, 129648),
360 "Symbols and Pictographs Extended-A": range(129648, 129792),
361 "Symbols for Legacy Computing": range(129792, 130048),
362 "CJK Unified Ideographs Extension B": range(131072, 173792),
363 "CJK Unified Ideographs Extension C": range(173824, 177984),
364 "CJK Unified Ideographs Extension D": range(177984, 178208),
365 "CJK Unified Ideographs Extension E": range(178208, 183984),
366 "CJK Unified Ideographs Extension F": range(183984, 191472),
367 "CJK Unified Ideographs Extension I": range(191472, 192096),
368 "CJK Compatibility Ideographs Supplement": range(194560, 195104),
369 "CJK Unified Ideographs Extension G": range(196608, 201552),
370 "CJK Unified Ideographs Extension H": range(201552, 205744),
371 "CJK Unified Ideographs Extension J": range(205744, 210048),
372 "Tags": range(917504, 917632),
373 "Variation Selectors Supplement": range(917760, 918000),
374 "Supplementary Private Use Area-A": range(983040, 1048576),
375 "Supplementary Private Use Area-B": range(1048576, 1114112),
376}
378# Canonical family for every Unicode range above. Keep this exhaustive and
379# explicit: official block names are labels, not a grammar we should parse.
380_RANGE_FAMILIES: dict[str, str] = {
381 "Control character": "Control character",
382 "Basic Latin": "Latin",
383 "Latin-1 Supplement": "Latin",
384 "Latin Extended-A": "Latin",
385 "Latin Extended-B": "Latin",
386 "IPA Extensions": "IPA",
387 "Spacing Modifier Letters": "Spacing Modifier Letters",
388 "Combining Diacritical Marks": "Combining",
389 "Greek and Coptic": "Greek",
390 "Cyrillic": "Cyrillic",
391 "Cyrillic Supplement": "Cyrillic",
392 "Armenian": "Armenian",
393 "Hebrew": "Hebrew",
394 "Arabic": "Arabic",
395 "Syriac": "Syriac",
396 "Arabic Supplement": "Arabic",
397 "Thaana": "Thaana",
398 "NKo": "NKo",
399 "Samaritan": "Samaritan",
400 "Mandaic": "Mandaic",
401 "Syriac Supplement": "Syriac",
402 "Arabic Extended-B": "Arabic",
403 "Arabic Extended-A": "Arabic",
404 "Devanagari": "Devanagari",
405 "Bengali": "Bengali",
406 "Gurmukhi": "Gurmukhi",
407 "Gujarati": "Gujarati",
408 "Oriya": "Oriya",
409 "Tamil": "Tamil",
410 "Telugu": "Telugu",
411 "Kannada": "Kannada",
412 "Malayalam": "Malayalam",
413 "Sinhala": "Sinhala",
414 "Thai": "Thai",
415 "Lao": "Lao",
416 "Tibetan": "Tibetan",
417 "Myanmar": "Myanmar",
418 "Georgian": "Georgian",
419 "Hangul Jamo": "Hangul",
420 "Ethiopic": "Ethiopic",
421 "Ethiopic Supplement": "Ethiopic",
422 "Cherokee": "Cherokee",
423 "Unified Canadian Aboriginal Syllabics": "Unified Canadian Aboriginal Syllabics",
424 "Ogham": "Ogham",
425 "Runic": "Runic",
426 "Tagalog": "Tagalog",
427 "Hanunoo": "Hanunoo",
428 "Buhid": "Buhid",
429 "Tagbanwa": "Tagbanwa",
430 "Khmer": "Khmer",
431 "Mongolian": "Mongolian",
432 "Unified Canadian Aboriginal Syllabics Extended": "Unified Canadian Aboriginal Syllabics",
433 "Limbu": "Limbu",
434 "Tai Le": "Tai Le",
435 "New Tai Lue": "New Tai Lue",
436 "Khmer Symbols": "Khmer",
437 "Buginese": "Buginese",
438 "Tai Tham": "Tai Tham",
439 "Combining Diacritical Marks Extended": "Combining",
440 "Balinese": "Balinese",
441 "Sundanese": "Sundanese",
442 "Batak": "Batak",
443 "Lepcha": "Lepcha",
444 "Ol Chiki": "Ol Chiki",
445 "Cyrillic Extended-C": "Cyrillic",
446 "Georgian Extended": "Georgian",
447 "Sundanese Supplement": "Sundanese",
448 "Vedic Extensions": "Vedic",
449 "Phonetic Extensions": "Phonetic",
450 "Phonetic Extensions Supplement": "Phonetic",
451 "Combining Diacritical Marks Supplement": "Combining",
452 "Latin Extended Additional": "Latin",
453 "Greek Extended": "Greek",
454 "General Punctuation": "Punctuation",
455 "Superscripts and Subscripts": "Superscripts and Subscripts",
456 "Currency Symbols": "Currency Symbols",
457 "Combining Diacritical Marks for Symbols": "Combining",
458 "Letterlike Symbols": "Letterlike Symbols",
459 "Number Forms": "Number Forms",
460 "Arrows": "Arrows",
461 "Mathematical Operators": "Mathematical",
462 "Miscellaneous Technical": "Miscellaneous Technical",
463 "Control Pictures": "Control Pictures",
464 "Optical Character Recognition": "Optical Character Recognition",
465 "Enclosed Alphanumerics": "Enclosed Alphanumerics",
466 "Box Drawing": "Box Drawing",
467 "Block Elements": "Block Elements",
468 "Geometric Shapes": "Geometric Shapes",
469 "Miscellaneous Symbols": "Miscellaneous Symbols",
470 "Dingbats": "Dingbats",
471 "Miscellaneous Mathematical Symbols-A": "Mathematical",
472 "Supplemental Arrows-A": "Arrows",
473 "Braille Patterns": "Braille",
474 "Supplemental Arrows-B": "Arrows",
475 "Miscellaneous Mathematical Symbols-B": "Mathematical",
476 "Supplemental Mathematical Operators": "Mathematical",
477 "Miscellaneous Symbols and Arrows": "Miscellaneous Symbols and Arrows",
478 "Glagolitic": "Glagolitic",
479 "Latin Extended-C": "Latin",
480 "Coptic": "Coptic",
481 "Georgian Supplement": "Georgian",
482 "Tifinagh": "Tifinagh",
483 "Ethiopic Extended": "Ethiopic",
484 "Cyrillic Extended-A": "Cyrillic",
485 "Supplemental Punctuation": "Punctuation",
486 "CJK Radicals Supplement": "CJK",
487 "Kangxi Radicals": "CJK",
488 "Ideographic Description Characters": "CJK",
489 "CJK Symbols and Punctuation": "CJK",
490 "Hiragana": "Hiragana",
491 "Katakana": "Katakana",
492 "Bopomofo": "Bopomofo",
493 "Hangul Compatibility Jamo": "Hangul",
494 "Kanbun": "Kanbun",
495 "Bopomofo Extended": "Bopomofo",
496 "CJK Strokes": "CJK",
497 "Katakana Phonetic Extensions": "Katakana",
498 "Enclosed CJK Letters and Months": "CJK",
499 "CJK Compatibility": "CJK",
500 "CJK Unified Ideographs Extension A": "CJK",
501 "Yijing Hexagram Symbols": "Yijing Hexagram Symbols",
502 "CJK Unified Ideographs": "CJK",
503 "Yi Syllables": "Yi",
504 "Yi Radicals": "Yi",
505 "Lisu": "Lisu",
506 "Vai": "Vai",
507 "Cyrillic Extended-B": "Cyrillic",
508 "Bamum": "Bamum",
509 "Modifier Tone Letters": "Phonetic",
510 "Latin Extended-D": "Latin",
511 "Syloti Nagri": "Syloti Nagri",
512 "Common Indic Number Forms": "Common Indic Number Forms",
513 "Phags-pa": "Phags-pa",
514 "Saurashtra": "Saurashtra",
515 "Devanagari Extended": "Devanagari",
516 "Kayah Li": "Kayah Li",
517 "Rejang": "Rejang",
518 "Hangul Jamo Extended-A": "Hangul",
519 "Javanese": "Javanese",
520 "Myanmar Extended-B": "Myanmar",
521 "Cham": "Cham",
522 "Myanmar Extended-A": "Myanmar",
523 "Tai Viet": "Tai Viet",
524 "Meetei Mayek Extensions": "Meetei Mayek",
525 "Ethiopic Extended-A": "Ethiopic",
526 "Latin Extended-E": "Latin",
527 "Cherokee Supplement": "Cherokee",
528 "Meetei Mayek": "Meetei Mayek",
529 "Hangul Syllables": "Hangul",
530 "Hangul Jamo Extended-B": "Hangul",
531 "High Surrogates": "Surrogates",
532 "High Private Use Surrogates": "Surrogates",
533 "Low Surrogates": "Surrogates",
534 "Private Use Area": "Private Use",
535 "CJK Compatibility Ideographs": "CJK",
536 "Alphabetic Presentation Forms": "Alphabetic Presentation Forms",
537 "Arabic Presentation Forms-A": "Arabic",
538 "Variation Selectors": "Variation Selectors",
539 "Vertical Forms": "CJK",
540 "Combining Half Marks": "Combining",
541 "CJK Compatibility Forms": "CJK",
542 "Small Form Variants": "CJK",
543 "Arabic Presentation Forms-B": "Arabic",
544 "Halfwidth and Fullwidth Forms": "Halfwidth and Fullwidth Forms",
545 "Specials": "Specials",
546 "Linear B Syllabary": "Linear B",
547 "Linear B Ideograms": "Linear B",
548 "Aegean Numbers": "Aegean Numbers",
549 "Ancient Greek Numbers": "Greek",
550 "Ancient Symbols": "Ancient Symbols",
551 "Phaistos Disc": "Phaistos Disc",
552 "Lycian": "Lycian",
553 "Carian": "Carian",
554 "Coptic Epact Numbers": "Coptic",
555 "Old Italic": "Old Italic",
556 "Gothic": "Gothic",
557 "Old Permic": "Old Permic",
558 "Ugaritic": "Ugaritic",
559 "Old Persian": "Old Persian",
560 "Deseret": "Deseret",
561 "Shavian": "Shavian",
562 "Osmanya": "Osmanya",
563 "Osage": "Osage",
564 "Elbasan": "Elbasan",
565 "Caucasian Albanian": "Caucasian Albanian",
566 "Vithkuqi": "Vithkuqi",
567 "Todhri": "Todhri",
568 "Linear A": "Linear A",
569 "Latin Extended-F": "Latin",
570 "Cypriot Syllabary": "Cypriot",
571 "Imperial Aramaic": "Imperial Aramaic",
572 "Palmyrene": "Palmyrene",
573 "Nabataean": "Nabataean",
574 "Hatran": "Hatran",
575 "Phoenician": "Phoenician",
576 "Lydian": "Lydian",
577 "Sidetic": "Sidetic",
578 "Meroitic Hieroglyphs": "Meroitic",
579 "Meroitic Cursive": "Meroitic",
580 "Kharoshthi": "Kharoshthi",
581 "Old South Arabian": "Old South Arabian",
582 "Old North Arabian": "Old North Arabian",
583 "Manichaean": "Manichaean",
584 "Avestan": "Avestan",
585 "Inscriptional Parthian": "Parthian",
586 "Inscriptional Pahlavi": "Pahlavi",
587 "Psalter Pahlavi": "Pahlavi",
588 "Old Turkic": "Old Turkic",
589 "Old Hungarian": "Old Hungarian",
590 "Hanifi Rohingya": "Hanifi Rohingya",
591 "Garay": "Garay",
592 "Rumi Numeral Symbols": "Arabic",
593 "Yezidi": "Yezidi",
594 "Arabic Extended-C": "Arabic",
595 "Old Sogdian": "Sogdian",
596 "Sogdian": "Sogdian",
597 "Old Uyghur": "Old Uyghur",
598 "Chorasmian": "Chorasmian",
599 "Elymaic": "Elymaic",
600 "Brahmi": "Brahmi",
601 "Kaithi": "Kaithi",
602 "Sora Sompeng": "Sora Sompeng",
603 "Chakma": "Chakma",
604 "Mahajani": "Mahajani",
605 "Sharada": "Sharada",
606 "Sinhala Archaic Numbers": "Sinhala",
607 "Khojki": "Khojki",
608 "Multani": "Multani",
609 "Khudawadi": "Khudawadi",
610 "Grantha": "Grantha",
611 "Tulu-Tigalari": "Tulu-Tigalari",
612 "Newa": "Newa",
613 "Tirhuta": "Tirhuta",
614 "Siddham": "Siddham",
615 "Modi": "Modi",
616 "Mongolian Supplement": "Mongolian",
617 "Takri": "Takri",
618 "Myanmar Extended-C": "Myanmar",
619 "Ahom": "Ahom",
620 "Dogra": "Dogra",
621 "Warang Citi": "Warang Citi",
622 "Dives Akuru": "Dives Akuru",
623 "Nandinagari": "Nandinagari",
624 "Zanabazar Square": "Zanabazar Square",
625 "Soyombo": "Soyombo",
626 "Unified Canadian Aboriginal Syllabics Extended-A": "Unified Canadian Aboriginal Syllabics",
627 "Pau Cin Hau": "Pau Cin Hau",
628 "Devanagari Extended-A": "Devanagari",
629 "Sharada Supplement": "Sharada",
630 "Sunuwar": "Sunuwar",
631 "Bhaiksuki": "Bhaiksuki",
632 "Marchen": "Marchen",
633 "Masaram Gondi": "Masaram Gondi",
634 "Gunjala Gondi": "Gunjala Gondi",
635 "Tolong Siki": "Tolong Siki",
636 "Makasar": "Makasar",
637 "Kawi": "Kawi",
638 "Lisu Supplement": "Lisu",
639 "Tamil Supplement": "Tamil",
640 "Cuneiform": "Cuneiform",
641 "Cuneiform Numbers and Punctuation": "Cuneiform",
642 "Early Dynastic Cuneiform": "Cuneiform",
643 "Cypro-Minoan": "Cypro-Minoan",
644 "Egyptian Hieroglyphs": "Egyptian Hieroglyphs",
645 "Egyptian Hieroglyph Format Controls": "Egyptian Hieroglyphs",
646 "Egyptian Hieroglyphs Extended-A": "Egyptian Hieroglyphs",
647 "Anatolian Hieroglyphs": "Anatolian Hieroglyphs",
648 "Gurung Khema": "Gurung Khema",
649 "Bamum Supplement": "Bamum",
650 "Mro": "Mro",
651 "Tangsa": "Tangsa",
652 "Bassa Vah": "Bassa Vah",
653 "Pahawh Hmong": "Pahawh Hmong",
654 "Kirat Rai": "Kirat Rai",
655 "Medefaidrin": "Medefaidrin",
656 "Beria Erfe": "Beria Erfe",
657 "Miao": "Miao",
658 "Ideographic Symbols and Punctuation": "CJK",
659 "Tangut": "Tangut",
660 "Tangut Components": "Tangut",
661 "Khitan Small Script": "Khitan Small Script",
662 "Tangut Supplement": "Tangut",
663 "Tangut Components Supplement": "Tangut",
664 "Kana Extended-B": "Kana",
665 "Kana Supplement": "Kana",
666 "Kana Extended-A": "Kana",
667 "Small Kana Extension": "Kana",
668 "Nushu": "Nushu",
669 "Duployan": "Duployan",
670 "Shorthand Format Controls": "Shorthand Format Controls",
671 "Symbols for Legacy Computing Supplement": "Symbols for Legacy Computing",
672 "Miscellaneous Symbols Supplement": "Miscellaneous Symbols",
673 "Znamenny Musical Notation": "Znamenny Musical Notation",
674 "Byzantine Musical Symbols": "Byzantine Musical Symbols",
675 "Musical Symbols": "Musical Symbols",
676 "Ancient Greek Musical Notation": "Greek",
677 "Kaktovik Numerals": "Kaktovik Numerals",
678 "Mayan Numerals": "Mayan Numerals",
679 "Tai Xuan Jing Symbols": "Tai Xuan Jing Symbols",
680 "Counting Rod Numerals": "Counting Rod Numerals",
681 "Mathematical Alphanumeric Symbols": "Mathematical",
682 "Sutton SignWriting": "Sutton SignWriting",
683 "Latin Extended-G": "Latin",
684 "Glagolitic Supplement": "Glagolitic",
685 "Cyrillic Extended-D": "Cyrillic",
686 "Nyiakeng Puachue Hmong": "Nyiakeng Puachue Hmong",
687 "Toto": "Toto",
688 "Wancho": "Wancho",
689 "Nag Mundari": "Nag Mundari",
690 "Ol Onal": "Ol Onal",
691 "Tai Yo": "Tai Yo",
692 "Ethiopic Extended-B": "Ethiopic",
693 "Mende Kikakui": "Mende Kikakui",
694 "Adlam": "Adlam",
695 "Indic Siyaq Numbers": "Indic Siyaq Numbers",
696 "Ottoman Siyaq Numbers": "Ottoman Siyaq Numbers",
697 "Arabic Mathematical Alphabetic Symbols": "Arabic",
698 "Mahjong Tiles": "Mahjong Tiles",
699 "Domino Tiles": "Domino Tiles",
700 "Playing Cards": "Playing Cards",
701 "Enclosed Alphanumeric Supplement": "Enclosed Alphanumerics",
702 "Enclosed Ideographic Supplement": "CJK",
703 "Miscellaneous Symbols and Pictographs": "Pictographs",
704 "Emoticons": "Emoticons",
705 "Ornamental Dingbats": "Dingbats",
706 "Transport and Map Symbols": "Pictographs",
707 "Alchemical Symbols": "Alchemical Symbols",
708 "Geometric Shapes Extended": "Geometric Shapes",
709 "Supplemental Arrows-C": "Arrows",
710 "Supplemental Symbols and Pictographs": "Pictographs",
711 "Chess Symbols": "Chess Symbols",
712 "Symbols and Pictographs Extended-A": "Pictographs",
713 "Symbols for Legacy Computing": "Symbols for Legacy Computing",
714 "CJK Unified Ideographs Extension B": "CJK",
715 "CJK Unified Ideographs Extension C": "CJK",
716 "CJK Unified Ideographs Extension D": "CJK",
717 "CJK Unified Ideographs Extension E": "CJK",
718 "CJK Unified Ideographs Extension F": "CJK",
719 "CJK Unified Ideographs Extension I": "CJK",
720 "CJK Compatibility Ideographs Supplement": "CJK",
721 "CJK Unified Ideographs Extension G": "CJK",
722 "CJK Unified Ideographs Extension H": "CJK",
723 "CJK Unified Ideographs Extension J": "CJK",
724 "Tags": "Tags",
725 "Variation Selectors Supplement": "Variation Selectors",
726 "Supplementary Private Use Area-A": "Private Use",
727 "Supplementary Private Use Area-B": "Private Use",
728}
731class CompatibleFamillyRange:
732 __slots__ = ("_families",)
734 def __init__(self, familly_a: str, familly_b: str) -> None:
735 self._families: frozenset[str] = frozenset((familly_a, familly_b))
737 def __eq__(self, other: object) -> bool:
738 if not isinstance(other, CompatibleFamillyRange):
739 return NotImplemented
741 return self._families == other._families
743 def __hash__(self) -> int:
744 return hash(self._families)
747_COMPATIBLE_RANGE_FAMILIES: frozenset[CompatibleFamillyRange] = frozenset(
748 {
749 CompatibleFamillyRange("CJK", "Hiragana"),
750 CompatibleFamillyRange("CJK", "Katakana"),
751 CompatibleFamillyRange("CJK", "Kana"),
752 CompatibleFamillyRange("CJK", "Bopomofo"),
753 CompatibleFamillyRange("CJK", "Kanbun"),
754 CompatibleFamillyRange("Hiragana", "Katakana"),
755 CompatibleFamillyRange("Hiragana", "Kana"),
756 CompatibleFamillyRange("Katakana", "Kana"),
757 CompatibleFamillyRange("CJK", "Hangul"),
758 CompatibleFamillyRange("Latin", "IPA"),
759 CompatibleFamillyRange("Latin", "Phonetic"),
760 CompatibleFamillyRange("IPA", "Phonetic"),
761 CompatibleFamillyRange("Latin", "Spacing Modifier Letters"),
762 CompatibleFamillyRange("IPA", "Spacing Modifier Letters"),
763 CompatibleFamillyRange("Phonetic", "Spacing Modifier Letters"),
764 CompatibleFamillyRange("Alphabetic Presentation Forms", "Latin"),
765 CompatibleFamillyRange("Alphabetic Presentation Forms", "Armenian"),
766 CompatibleFamillyRange("Alphabetic Presentation Forms", "Hebrew"),
767 CompatibleFamillyRange("Halfwidth and Fullwidth Forms", "Latin"),
768 CompatibleFamillyRange("Halfwidth and Fullwidth Forms", "CJK"),
769 CompatibleFamillyRange("Halfwidth and Fullwidth Forms", "Hiragana"),
770 CompatibleFamillyRange("Halfwidth and Fullwidth Forms", "Katakana"),
771 CompatibleFamillyRange("Halfwidth and Fullwidth Forms", "Kana"),
772 CompatibleFamillyRange("Halfwidth and Fullwidth Forms", "Hangul"),
773 }
774)
776_COMPATIBLE_WITH_ANY_RANGE_FAMILIES: frozenset[str] = frozenset(
777 {"Combining", "Variation Selectors", "Emoticons", "Pictographs"}
778)
780_BASIC_LATIN_COMPATIBLE_RANGE_FAMILIES: frozenset[str] = frozenset(
781 {"CJK", "Hangul", "Hiragana", "Katakana", "Kana", "Bopomofo", "Kanbun"}
782)
785UNICODE_SECONDARY_RANGE_KEYWORD: list[str] = [
786 "Supplement",
787 "Extended",
788 "Extensions",
789 "Modifier",
790 "Marks",
791 "Punctuation",
792 "Symbols",
793 "Forms",
794 "Operators",
795 "Miscellaneous",
796 "Drawing",
797 "Block",
798 "Shapes",
799 "Supplemental",
800 "Tags",
801]
803RE_POSSIBLE_ENCODING_INDICATION = re_compile(
804 r"(?:(?:encoding)|(?:charset)|(?:coding))(?:[\:= ]{1,10})(?:[\"\']?)([a-zA-Z0-9\-_]+)(?:[\"\']?)",
805 IGNORECASE,
806)
808IANA_NO_ALIASES = [
809 "cp720",
810 "cp737",
811 "cp856",
812 "cp874",
813 "cp875",
814 "cp1006",
815 "koi8_r",
816 "koi8_t",
817 "koi8_u",
818]
820IANA_SUPPORTED: list[str] = sorted(
821 filter(
822 lambda x: not x.endswith("_codec") and x not in {"rot_13", "tactis", "mbcs"},
823 list(set(aliases.values())) + IANA_NO_ALIASES,
824 )
825)
827IANA_SUPPORTED_COUNT: int = len(IANA_SUPPORTED)
829# pre-computed code page that are similar using the function cp_similarity.
830IANA_SUPPORTED_SIMILAR: dict[str, list[str]] = {
831 "cp037": ["cp1026", "cp1140", "cp273", "cp500"],
832 "cp1026": ["cp037", "cp1140", "cp273", "cp500"],
833 "cp1125": ["cp866"],
834 "cp1140": ["cp037", "cp1026", "cp273", "cp500"],
835 "cp1250": ["iso8859_2"],
836 "cp1251": ["kz1048", "ptcp154"],
837 "cp1252": ["iso8859_15", "iso8859_9", "latin_1"],
838 "cp1253": ["iso8859_7"],
839 "cp1254": ["iso8859_15", "iso8859_9", "latin_1"],
840 "cp1257": ["iso8859_13"],
841 "cp273": ["cp037", "cp1026", "cp1140", "cp500"],
842 "cp437": ["cp850", "cp858", "cp860", "cp861", "cp862", "cp863", "cp865"],
843 "cp500": ["cp037", "cp1026", "cp1140", "cp273"],
844 "cp850": ["cp437", "cp857", "cp858", "cp865"],
845 "cp857": ["cp850", "cp858", "cp865"],
846 "cp858": ["cp437", "cp850", "cp857", "cp865"],
847 "cp860": ["cp437", "cp861", "cp862", "cp863", "cp865"],
848 "cp861": ["cp437", "cp860", "cp862", "cp863", "cp865"],
849 "cp862": ["cp437", "cp860", "cp861", "cp863", "cp865"],
850 "cp863": ["cp437", "cp860", "cp861", "cp862", "cp865"],
851 "cp865": ["cp437", "cp850", "cp857", "cp858", "cp860", "cp861", "cp862", "cp863"],
852 "cp866": ["cp1125"],
853 "iso8859_10": ["iso8859_14", "iso8859_15", "iso8859_4", "iso8859_9", "latin_1"],
854 "iso8859_11": ["tis_620"],
855 "iso8859_13": ["cp1257"],
856 "iso8859_14": [
857 "iso8859_10",
858 "iso8859_15",
859 "iso8859_16",
860 "iso8859_3",
861 "iso8859_9",
862 "latin_1",
863 ],
864 "iso8859_15": [
865 "cp1252",
866 "cp1254",
867 "iso8859_10",
868 "iso8859_14",
869 "iso8859_16",
870 "iso8859_3",
871 "iso8859_9",
872 "latin_1",
873 ],
874 "iso8859_16": [
875 "iso8859_14",
876 "iso8859_15",
877 "iso8859_2",
878 "iso8859_3",
879 "iso8859_9",
880 "latin_1",
881 ],
882 "iso8859_2": ["cp1250", "iso8859_16", "iso8859_4"],
883 "iso8859_3": ["iso8859_14", "iso8859_15", "iso8859_16", "iso8859_9", "latin_1"],
884 "iso8859_4": ["iso8859_10", "iso8859_2", "iso8859_9", "latin_1"],
885 "iso8859_7": ["cp1253"],
886 "iso8859_9": [
887 "cp1252",
888 "cp1254",
889 "cp1258",
890 "iso8859_10",
891 "iso8859_14",
892 "iso8859_15",
893 "iso8859_16",
894 "iso8859_3",
895 "iso8859_4",
896 "latin_1",
897 ],
898 "kz1048": ["cp1251", "ptcp154"],
899 "latin_1": [
900 "cp1252",
901 "cp1254",
902 "cp1258",
903 "iso8859_10",
904 "iso8859_14",
905 "iso8859_15",
906 "iso8859_16",
907 "iso8859_3",
908 "iso8859_4",
909 "iso8859_9",
910 ],
911 "mac_iceland": ["mac_roman", "mac_turkish"],
912 "mac_roman": ["mac_iceland", "mac_turkish"],
913 "mac_turkish": ["mac_iceland", "mac_roman"],
914 "ptcp154": ["cp1251", "kz1048"],
915 "tis_620": ["iso8859_11"],
916}
919CHARDET_CORRESPONDENCE: dict[str, str] = {
920 "iso2022_kr": "ISO-2022-KR",
921 "iso2022_jp": "ISO-2022-JP",
922 "euc_kr": "EUC-KR",
923 "tis_620": "TIS-620",
924 "utf_32": "UTF-32",
925 "euc_jp": "EUC-JP",
926 "koi8_r": "KOI8-R",
927 "iso8859_1": "ISO-8859-1",
928 "iso8859_2": "ISO-8859-2",
929 "iso8859_5": "ISO-8859-5",
930 "iso8859_6": "ISO-8859-6",
931 "iso8859_7": "ISO-8859-7",
932 "iso8859_8": "ISO-8859-8",
933 "utf_16": "UTF-16",
934 "cp855": "IBM855",
935 "mac_cyrillic": "MacCyrillic",
936 "gb2312": "GB2312",
937 "gb18030": "GB18030",
938 "cp932": "CP932",
939 "cp866": "IBM866",
940 "utf_8": "utf-8",
941 "utf_8_sig": "UTF-8-SIG",
942 "shift_jis": "SHIFT_JIS",
943 "big5": "Big5",
944 "cp1250": "windows-1250",
945 "cp1251": "windows-1251",
946 "cp1252": "Windows-1252",
947 "cp1253": "windows-1253",
948 "cp1255": "windows-1255",
949 "cp1256": "windows-1256",
950 "cp1254": "Windows-1254",
951 "cp949": "CP949",
952}
955COMMON_SAFE_ASCII_CHARACTERS: frozenset[str] = frozenset(
956 {
957 "<",
958 ">",
959 "=",
960 ":",
961 "/",
962 "&",
963 ";",
964 "{",
965 "}",
966 "[",
967 "]",
968 ",",
969 "|",
970 '"',
971 "-",
972 "(",
973 ")",
974 }
975)
977# Sample character sets — replace with full lists if needed
978COMMON_CHINESE_CHARACTERS = "的一是在不了有和人这中大为上个国我以要他时来用们生到作地于出就分对成会可主发年动同工也能下过子说产种面而方后多定行学法所民得经十三之进着等部度家电力里如水化高自二理起小物现实加量都两体制机当使点从业本去把性好应开它合还因由其些然前外天政四日那社义事平形相全表间样与关各重新线内数正心反你明看原又么利比或但质气第向道命此变条只没结解问意建月公无系军很情者最立代想已通并提直题党程展五果料象员革位入常文总次品式活设及管特件长求老头基资边流路级少图山统接知较将组见计别她手角期根论运农指几九区强放决西被干做必战先回则任取据处队南给色光门即保治北造百规热领七海口东导器压志世金增争济阶油思术极交受联什认六共权收证改清己美再采转更单风切打白教速花带安场身车例真务具万每目至达走积示议声报斗完类八离华名确才科张信马节话米整空元况今集温传土许步群广石记需段研界拉林律叫且究观越织装影算低持音众书布复容儿须际商非验连断深难近矿千周委素技备半办青省列习响约支般史感劳便团往酸历市克何除消构府太准精值号率族维划选标写存候毛亲快效斯院查江型眼王按格养易置派层片始却专状育厂京识适属圆包火住调满县局照参红细引听该铁价严龙飞"
980COMMON_JAPANESE_CHARACTERS = "日一国年大十二本中長出三時行見月分後前生五間上東四今金九入学高円子外八六下来気小七山話女北午百書先名川千水半男西電校語土木聞食車何南万毎白天母火右読友左休父雨"
982COMMON_KOREAN_CHARACTERS = "一二三四五六七八九十百千萬上下左右中人女子大小山川日月火水木金土父母天地國名年時文校學生"
984# Combine all into a frozenset
985COMMON_CJK_CHARACTERS = frozenset(
986 "".join(
987 [
988 COMMON_CHINESE_CHARACTERS,
989 COMMON_JAPANESE_CHARACTERS,
990 COMMON_KOREAN_CHARACTERS,
991 ]
992 )
993)
995KO_NAMES: frozenset[str] = frozenset({"johab", "cp949", "euc_kr"})
996ZH_NAMES: frozenset[str] = frozenset({"big5", "cp950", "big5hkscs", "hz"})
998# Logging LEVEL below DEBUG
999TRACE: int = 5
1002# Language label that contain the em dash "—"
1003# character are to be considered alternative seq to origin
1004FREQUENCIES: dict[str, list[str]] = {
1005 "English": [
1006 "e",
1007 "a",
1008 "t",
1009 "i",
1010 "o",
1011 "n",
1012 "s",
1013 "r",
1014 "h",
1015 "l",
1016 "d",
1017 "c",
1018 "u",
1019 "m",
1020 "f",
1021 "p",
1022 "g",
1023 "w",
1024 "y",
1025 "b",
1026 "v",
1027 "k",
1028 "x",
1029 "j",
1030 "z",
1031 "q",
1032 ],
1033 "English—": [
1034 "e",
1035 "a",
1036 "t",
1037 "i",
1038 "o",
1039 "n",
1040 "s",
1041 "r",
1042 "h",
1043 "l",
1044 "d",
1045 "c",
1046 "m",
1047 "u",
1048 "f",
1049 "p",
1050 "g",
1051 "w",
1052 "b",
1053 "y",
1054 "v",
1055 "k",
1056 "j",
1057 "x",
1058 "z",
1059 "q",
1060 ],
1061 "German": [
1062 "e",
1063 "n",
1064 "i",
1065 "r",
1066 "s",
1067 "t",
1068 "a",
1069 "d",
1070 "h",
1071 "u",
1072 "l",
1073 "g",
1074 "o",
1075 "c",
1076 "m",
1077 "b",
1078 "f",
1079 "k",
1080 "w",
1081 "z",
1082 "p",
1083 "v",
1084 "ü",
1085 "ä",
1086 "ö",
1087 "j",
1088 ],
1089 "French": [
1090 "e",
1091 "a",
1092 "s",
1093 "n",
1094 "i",
1095 "t",
1096 "r",
1097 "l",
1098 "u",
1099 "o",
1100 "d",
1101 "c",
1102 "p",
1103 "m",
1104 "é",
1105 "v",
1106 "g",
1107 "f",
1108 "b",
1109 "h",
1110 "q",
1111 "à",
1112 "x",
1113 "è",
1114 "y",
1115 "j",
1116 ],
1117 "Dutch": [
1118 "e",
1119 "n",
1120 "a",
1121 "i",
1122 "r",
1123 "t",
1124 "o",
1125 "d",
1126 "s",
1127 "l",
1128 "g",
1129 "h",
1130 "v",
1131 "m",
1132 "u",
1133 "k",
1134 "c",
1135 "p",
1136 "b",
1137 "w",
1138 "j",
1139 "z",
1140 "f",
1141 "y",
1142 "x",
1143 "ë",
1144 ],
1145 "Italian": [
1146 "e",
1147 "i",
1148 "a",
1149 "o",
1150 "n",
1151 "l",
1152 "t",
1153 "r",
1154 "s",
1155 "c",
1156 "d",
1157 "u",
1158 "p",
1159 "m",
1160 "g",
1161 "v",
1162 "f",
1163 "b",
1164 "z",
1165 "h",
1166 "q",
1167 "è",
1168 "à",
1169 "k",
1170 "y",
1171 "ò",
1172 ],
1173 "Polish": [
1174 "a",
1175 "i",
1176 "o",
1177 "e",
1178 "n",
1179 "r",
1180 "z",
1181 "w",
1182 "s",
1183 "c",
1184 "t",
1185 "k",
1186 "y",
1187 "d",
1188 "p",
1189 "m",
1190 "u",
1191 "l",
1192 "j",
1193 "ł",
1194 "g",
1195 "b",
1196 "h",
1197 "ą",
1198 "ę",
1199 "ó",
1200 ],
1201 "Spanish": [
1202 "e",
1203 "a",
1204 "o",
1205 "n",
1206 "s",
1207 "r",
1208 "i",
1209 "l",
1210 "d",
1211 "t",
1212 "c",
1213 "u",
1214 "m",
1215 "p",
1216 "b",
1217 "g",
1218 "v",
1219 "f",
1220 "y",
1221 "ó",
1222 "h",
1223 "q",
1224 "í",
1225 "j",
1226 "z",
1227 "á",
1228 ],
1229 "Russian": [
1230 "о",
1231 "е",
1232 "а",
1233 "и",
1234 "н",
1235 "т",
1236 "с",
1237 "р",
1238 "в",
1239 "л",
1240 "к",
1241 "м",
1242 "д",
1243 "п",
1244 "у",
1245 "г",
1246 "я",
1247 "ы",
1248 "з",
1249 "б",
1250 "й",
1251 "ь",
1252 "ч",
1253 "х",
1254 "ж",
1255 "ц",
1256 ],
1257 # Jap-Kanji
1258 "Japanese": [
1259 "日",
1260 "一",
1261 "人",
1262 "年",
1263 "大",
1264 "十",
1265 "二",
1266 "本",
1267 "中",
1268 "長",
1269 "出",
1270 "三",
1271 "時",
1272 "行",
1273 "見",
1274 "月",
1275 "分",
1276 "後",
1277 "前",
1278 "生",
1279 "五",
1280 "間",
1281 "上",
1282 "東",
1283 "四",
1284 "今",
1285 "金",
1286 "九",
1287 "入",
1288 "学",
1289 "高",
1290 "円",
1291 "子",
1292 "外",
1293 "八",
1294 "六",
1295 "下",
1296 "来",
1297 "気",
1298 "小",
1299 "七",
1300 "山",
1301 "話",
1302 "女",
1303 "北",
1304 "午",
1305 "百",
1306 "書",
1307 "先",
1308 "名",
1309 "川",
1310 "千",
1311 "水",
1312 "半",
1313 "男",
1314 "西",
1315 "電",
1316 "校",
1317 "語",
1318 "土",
1319 "木",
1320 "聞",
1321 "食",
1322 "車",
1323 "何",
1324 "南",
1325 "万",
1326 "毎",
1327 "白",
1328 "天",
1329 "母",
1330 "火",
1331 "右",
1332 "読",
1333 "友",
1334 "左",
1335 "休",
1336 "父",
1337 "雨",
1338 ],
1339 # Jap-Katakana
1340 "Japanese—": [
1341 "ー",
1342 "ン",
1343 "ス",
1344 "・",
1345 "ル",
1346 "ト",
1347 "リ",
1348 "イ",
1349 "ア",
1350 "ラ",
1351 "ッ",
1352 "ク",
1353 "ド",
1354 "シ",
1355 "レ",
1356 "ジ",
1357 "タ",
1358 "フ",
1359 "ロ",
1360 "カ",
1361 "テ",
1362 "マ",
1363 "ィ",
1364 "グ",
1365 "バ",
1366 "ム",
1367 "プ",
1368 "オ",
1369 "コ",
1370 "デ",
1371 "ニ",
1372 "ウ",
1373 "メ",
1374 "サ",
1375 "ビ",
1376 "ナ",
1377 "ブ",
1378 "ャ",
1379 "エ",
1380 "ュ",
1381 "チ",
1382 "キ",
1383 "ズ",
1384 "ダ",
1385 "パ",
1386 "ミ",
1387 "ェ",
1388 "ョ",
1389 "ハ",
1390 "セ",
1391 "ベ",
1392 "ガ",
1393 "モ",
1394 "ツ",
1395 "ネ",
1396 "ボ",
1397 "ソ",
1398 "ノ",
1399 "ァ",
1400 "ヴ",
1401 "ワ",
1402 "ポ",
1403 "ペ",
1404 "ピ",
1405 "ケ",
1406 "ゴ",
1407 "ギ",
1408 "ザ",
1409 "ホ",
1410 "ゲ",
1411 "ォ",
1412 "ヤ",
1413 "ヒ",
1414 "ユ",
1415 "ヨ",
1416 "ヘ",
1417 "ゼ",
1418 "ヌ",
1419 "ゥ",
1420 "ゾ",
1421 "ヶ",
1422 "ヂ",
1423 "ヲ",
1424 "ヅ",
1425 "ヵ",
1426 "ヱ",
1427 "ヰ",
1428 "ヮ",
1429 "ヽ",
1430 "゠",
1431 "ヾ",
1432 "ヷ",
1433 "ヿ",
1434 "ヸ",
1435 "ヹ",
1436 "ヺ",
1437 ],
1438 # Jap-Hiragana
1439 "Japanese——": [
1440 "の",
1441 "に",
1442 "る",
1443 "た",
1444 "と",
1445 "は",
1446 "し",
1447 "い",
1448 "を",
1449 "で",
1450 "て",
1451 "が",
1452 "な",
1453 "れ",
1454 "か",
1455 "ら",
1456 "さ",
1457 "っ",
1458 "り",
1459 "す",
1460 "あ",
1461 "も",
1462 "こ",
1463 "ま",
1464 "う",
1465 "く",
1466 "よ",
1467 "き",
1468 "ん",
1469 "め",
1470 "お",
1471 "け",
1472 "そ",
1473 "つ",
1474 "だ",
1475 "や",
1476 "え",
1477 "ど",
1478 "わ",
1479 "ち",
1480 "み",
1481 "せ",
1482 "じ",
1483 "ば",
1484 "へ",
1485 "び",
1486 "ず",
1487 "ろ",
1488 "ほ",
1489 "げ",
1490 "む",
1491 "べ",
1492 "ひ",
1493 "ょ",
1494 "ゆ",
1495 "ぶ",
1496 "ご",
1497 "ゃ",
1498 "ね",
1499 "ふ",
1500 "ぐ",
1501 "ぎ",
1502 "ぼ",
1503 "ゅ",
1504 "づ",
1505 "ざ",
1506 "ぞ",
1507 "ぬ",
1508 "ぜ",
1509 "ぱ",
1510 "ぽ",
1511 "ぷ",
1512 "ぴ",
1513 "ぃ",
1514 "ぁ",
1515 "ぇ",
1516 "ぺ",
1517 "ゞ",
1518 "ぢ",
1519 "ぉ",
1520 "ぅ",
1521 "ゐ",
1522 "ゝ",
1523 "ゑ",
1524 "゛",
1525 "゜",
1526 "ゎ",
1527 "ゔ",
1528 "゚",
1529 "ゟ",
1530 "゙",
1531 "ゕ",
1532 "ゖ",
1533 ],
1534 "Portuguese": [
1535 "a",
1536 "e",
1537 "o",
1538 "s",
1539 "i",
1540 "r",
1541 "d",
1542 "n",
1543 "t",
1544 "m",
1545 "u",
1546 "c",
1547 "l",
1548 "p",
1549 "g",
1550 "v",
1551 "b",
1552 "f",
1553 "h",
1554 "ã",
1555 "q",
1556 "é",
1557 "ç",
1558 "á",
1559 "z",
1560 "í",
1561 ],
1562 "Swedish": [
1563 "e",
1564 "a",
1565 "n",
1566 "r",
1567 "t",
1568 "s",
1569 "i",
1570 "l",
1571 "d",
1572 "o",
1573 "m",
1574 "k",
1575 "g",
1576 "v",
1577 "h",
1578 "f",
1579 "u",
1580 "p",
1581 "ä",
1582 "c",
1583 "b",
1584 "ö",
1585 "å",
1586 "y",
1587 "j",
1588 "x",
1589 ],
1590 "Chinese": [
1591 "的",
1592 "一",
1593 "是",
1594 "不",
1595 "了",
1596 "在",
1597 "人",
1598 "有",
1599 "我",
1600 "他",
1601 "这",
1602 "个",
1603 "们",
1604 "中",
1605 "来",
1606 "上",
1607 "大",
1608 "为",
1609 "和",
1610 "国",
1611 "地",
1612 "到",
1613 "以",
1614 "说",
1615 "时",
1616 "要",
1617 "就",
1618 "出",
1619 "会",
1620 "可",
1621 "也",
1622 "你",
1623 "对",
1624 "生",
1625 "能",
1626 "而",
1627 "子",
1628 "那",
1629 "得",
1630 "于",
1631 "着",
1632 "下",
1633 "自",
1634 "之",
1635 "年",
1636 "过",
1637 "发",
1638 "后",
1639 "作",
1640 "里",
1641 "用",
1642 "道",
1643 "行",
1644 "所",
1645 "然",
1646 "家",
1647 "种",
1648 "事",
1649 "成",
1650 "方",
1651 "多",
1652 "经",
1653 "么",
1654 "去",
1655 "法",
1656 "学",
1657 "如",
1658 "都",
1659 "同",
1660 "现",
1661 "当",
1662 "没",
1663 "动",
1664 "面",
1665 "起",
1666 "看",
1667 "定",
1668 "天",
1669 "分",
1670 "还",
1671 "进",
1672 "好",
1673 "小",
1674 "部",
1675 "其",
1676 "些",
1677 "主",
1678 "样",
1679 "理",
1680 "心",
1681 "她",
1682 "本",
1683 "前",
1684 "开",
1685 "但",
1686 "因",
1687 "只",
1688 "从",
1689 "想",
1690 "实",
1691 ],
1692 "Ukrainian": [
1693 "о",
1694 "а",
1695 "н",
1696 "і",
1697 "и",
1698 "р",
1699 "в",
1700 "т",
1701 "е",
1702 "с",
1703 "к",
1704 "л",
1705 "у",
1706 "д",
1707 "м",
1708 "п",
1709 "з",
1710 "я",
1711 "ь",
1712 "б",
1713 "г",
1714 "й",
1715 "ч",
1716 "х",
1717 "ц",
1718 "ї",
1719 ],
1720 "Norwegian": [
1721 "e",
1722 "r",
1723 "n",
1724 "t",
1725 "a",
1726 "s",
1727 "i",
1728 "o",
1729 "l",
1730 "d",
1731 "g",
1732 "k",
1733 "m",
1734 "v",
1735 "f",
1736 "p",
1737 "u",
1738 "b",
1739 "h",
1740 "å",
1741 "y",
1742 "j",
1743 "ø",
1744 "c",
1745 "æ",
1746 "w",
1747 ],
1748 "Finnish": [
1749 "a",
1750 "i",
1751 "n",
1752 "t",
1753 "e",
1754 "s",
1755 "l",
1756 "o",
1757 "u",
1758 "k",
1759 "ä",
1760 "m",
1761 "r",
1762 "v",
1763 "j",
1764 "h",
1765 "p",
1766 "y",
1767 "d",
1768 "ö",
1769 "g",
1770 "c",
1771 "b",
1772 "f",
1773 "w",
1774 "z",
1775 ],
1776 "Vietnamese": [
1777 "n",
1778 "h",
1779 "t",
1780 "i",
1781 "c",
1782 "g",
1783 "a",
1784 "o",
1785 "u",
1786 "m",
1787 "l",
1788 "r",
1789 "à",
1790 "đ",
1791 "s",
1792 "e",
1793 "v",
1794 "p",
1795 "b",
1796 "y",
1797 "ư",
1798 "d",
1799 "á",
1800 "k",
1801 "ộ",
1802 "ế",
1803 ],
1804 "Czech": [
1805 "o",
1806 "e",
1807 "a",
1808 "n",
1809 "t",
1810 "s",
1811 "i",
1812 "l",
1813 "v",
1814 "r",
1815 "k",
1816 "d",
1817 "u",
1818 "m",
1819 "p",
1820 "í",
1821 "c",
1822 "h",
1823 "z",
1824 "á",
1825 "y",
1826 "j",
1827 "b",
1828 "ě",
1829 "é",
1830 "ř",
1831 ],
1832 "Hungarian": [
1833 "e",
1834 "a",
1835 "t",
1836 "l",
1837 "s",
1838 "n",
1839 "k",
1840 "r",
1841 "i",
1842 "o",
1843 "z",
1844 "á",
1845 "é",
1846 "g",
1847 "m",
1848 "b",
1849 "y",
1850 "v",
1851 "d",
1852 "h",
1853 "u",
1854 "p",
1855 "j",
1856 "ö",
1857 "f",
1858 "c",
1859 ],
1860 "Korean": [
1861 "이",
1862 "다",
1863 "에",
1864 "의",
1865 "는",
1866 "로",
1867 "하",
1868 "을",
1869 "가",
1870 "고",
1871 "지",
1872 "서",
1873 "한",
1874 "은",
1875 "기",
1876 "으",
1877 "년",
1878 "대",
1879 "사",
1880 "시",
1881 "를",
1882 "리",
1883 "도",
1884 "인",
1885 "스",
1886 "일",
1887 ],
1888 "Indonesian": [
1889 "a",
1890 "n",
1891 "e",
1892 "i",
1893 "r",
1894 "t",
1895 "u",
1896 "s",
1897 "d",
1898 "k",
1899 "m",
1900 "l",
1901 "g",
1902 "p",
1903 "b",
1904 "o",
1905 "h",
1906 "y",
1907 "j",
1908 "c",
1909 "w",
1910 "f",
1911 "v",
1912 "z",
1913 "x",
1914 "q",
1915 ],
1916 "Turkish": [
1917 "a",
1918 "e",
1919 "i",
1920 "n",
1921 "r",
1922 "l",
1923 "ı",
1924 "k",
1925 "d",
1926 "t",
1927 "s",
1928 "m",
1929 "y",
1930 "u",
1931 "o",
1932 "b",
1933 "ü",
1934 "ş",
1935 "v",
1936 "g",
1937 "z",
1938 "h",
1939 "c",
1940 "p",
1941 "ç",
1942 "ğ",
1943 ],
1944 "Romanian": [
1945 "e",
1946 "i",
1947 "a",
1948 "r",
1949 "n",
1950 "t",
1951 "u",
1952 "l",
1953 "o",
1954 "c",
1955 "s",
1956 "d",
1957 "p",
1958 "m",
1959 "ă",
1960 "f",
1961 "v",
1962 "î",
1963 "g",
1964 "b",
1965 "ș",
1966 "ț",
1967 "z",
1968 "h",
1969 "â",
1970 "j",
1971 ],
1972 "Farsi": [
1973 "ا",
1974 "ی",
1975 "ر",
1976 "د",
1977 "ن",
1978 "ه",
1979 "و",
1980 "م",
1981 "ت",
1982 "ب",
1983 "س",
1984 "ل",
1985 "ک",
1986 "ش",
1987 "ز",
1988 "ف",
1989 "گ",
1990 "ع",
1991 "خ",
1992 "ق",
1993 "ج",
1994 "آ",
1995 "پ",
1996 "ح",
1997 "ط",
1998 "ص",
1999 ],
2000 "Arabic": [
2001 "ا",
2002 "ل",
2003 "ي",
2004 "م",
2005 "و",
2006 "ن",
2007 "ر",
2008 "ت",
2009 "ب",
2010 "ة",
2011 "ع",
2012 "د",
2013 "س",
2014 "ف",
2015 "ه",
2016 "ك",
2017 "ق",
2018 "أ",
2019 "ح",
2020 "ج",
2021 "ش",
2022 "ط",
2023 "ص",
2024 "ى",
2025 "خ",
2026 "إ",
2027 ],
2028 "Danish": [
2029 "e",
2030 "r",
2031 "n",
2032 "t",
2033 "a",
2034 "i",
2035 "s",
2036 "d",
2037 "l",
2038 "o",
2039 "g",
2040 "m",
2041 "k",
2042 "f",
2043 "v",
2044 "u",
2045 "b",
2046 "h",
2047 "p",
2048 "å",
2049 "y",
2050 "ø",
2051 "æ",
2052 "c",
2053 "j",
2054 "w",
2055 ],
2056 "Serbian": [
2057 "а",
2058 "и",
2059 "о",
2060 "е",
2061 "н",
2062 "р",
2063 "с",
2064 "у",
2065 "т",
2066 "к",
2067 "ј",
2068 "в",
2069 "д",
2070 "м",
2071 "п",
2072 "л",
2073 "г",
2074 "з",
2075 "б",
2076 "a",
2077 "i",
2078 "e",
2079 "o",
2080 "n",
2081 "ц",
2082 "ш",
2083 ],
2084 "Lithuanian": [
2085 "i",
2086 "a",
2087 "s",
2088 "o",
2089 "r",
2090 "e",
2091 "t",
2092 "n",
2093 "u",
2094 "k",
2095 "m",
2096 "l",
2097 "p",
2098 "v",
2099 "d",
2100 "j",
2101 "g",
2102 "ė",
2103 "b",
2104 "y",
2105 "ų",
2106 "š",
2107 "ž",
2108 "c",
2109 "ą",
2110 "į",
2111 ],
2112 "Slovene": [
2113 "e",
2114 "a",
2115 "i",
2116 "o",
2117 "n",
2118 "r",
2119 "s",
2120 "l",
2121 "t",
2122 "j",
2123 "v",
2124 "k",
2125 "d",
2126 "p",
2127 "m",
2128 "u",
2129 "z",
2130 "b",
2131 "g",
2132 "h",
2133 "č",
2134 "c",
2135 "š",
2136 "ž",
2137 "f",
2138 "y",
2139 ],
2140 "Slovak": [
2141 "o",
2142 "a",
2143 "e",
2144 "n",
2145 "i",
2146 "r",
2147 "v",
2148 "t",
2149 "s",
2150 "l",
2151 "k",
2152 "d",
2153 "m",
2154 "p",
2155 "u",
2156 "c",
2157 "h",
2158 "j",
2159 "b",
2160 "z",
2161 "á",
2162 "y",
2163 "ý",
2164 "í",
2165 "č",
2166 "é",
2167 ],
2168 "Hebrew": [
2169 "י",
2170 "ו",
2171 "ה",
2172 "ל",
2173 "ר",
2174 "ב",
2175 "ת",
2176 "מ",
2177 "א",
2178 "ש",
2179 "נ",
2180 "ע",
2181 "ם",
2182 "ד",
2183 "ק",
2184 "ח",
2185 "פ",
2186 "ס",
2187 "כ",
2188 "ג",
2189 "ט",
2190 "צ",
2191 "ן",
2192 "ז",
2193 "ך",
2194 ],
2195 "Bulgarian": [
2196 "а",
2197 "и",
2198 "о",
2199 "е",
2200 "н",
2201 "т",
2202 "р",
2203 "с",
2204 "в",
2205 "л",
2206 "к",
2207 "д",
2208 "п",
2209 "м",
2210 "з",
2211 "г",
2212 "я",
2213 "ъ",
2214 "у",
2215 "б",
2216 "ч",
2217 "ц",
2218 "й",
2219 "ж",
2220 "щ",
2221 "х",
2222 ],
2223 "Croatian": [
2224 "a",
2225 "i",
2226 "o",
2227 "e",
2228 "n",
2229 "r",
2230 "j",
2231 "s",
2232 "t",
2233 "u",
2234 "k",
2235 "l",
2236 "v",
2237 "d",
2238 "m",
2239 "p",
2240 "g",
2241 "z",
2242 "b",
2243 "c",
2244 "č",
2245 "h",
2246 "š",
2247 "ž",
2248 "ć",
2249 "f",
2250 ],
2251 "Hindi": [
2252 "क",
2253 "र",
2254 "स",
2255 "न",
2256 "त",
2257 "म",
2258 "ह",
2259 "प",
2260 "य",
2261 "ल",
2262 "व",
2263 "ज",
2264 "द",
2265 "ग",
2266 "ब",
2267 "श",
2268 "ट",
2269 "अ",
2270 "ए",
2271 "थ",
2272 "भ",
2273 "ड",
2274 "च",
2275 "ध",
2276 "ष",
2277 "इ",
2278 ],
2279 "Estonian": [
2280 "a",
2281 "i",
2282 "e",
2283 "s",
2284 "t",
2285 "l",
2286 "u",
2287 "n",
2288 "o",
2289 "k",
2290 "r",
2291 "d",
2292 "m",
2293 "v",
2294 "g",
2295 "p",
2296 "j",
2297 "h",
2298 "ä",
2299 "b",
2300 "õ",
2301 "ü",
2302 "f",
2303 "c",
2304 "ö",
2305 "y",
2306 ],
2307 "Thai": [
2308 "า",
2309 "น",
2310 "ร",
2311 "อ",
2312 "ก",
2313 "เ",
2314 "ง",
2315 "ม",
2316 "ย",
2317 "ล",
2318 "ว",
2319 "ด",
2320 "ท",
2321 "ส",
2322 "ต",
2323 "ะ",
2324 "ป",
2325 "บ",
2326 "ค",
2327 "ห",
2328 "แ",
2329 "จ",
2330 "พ",
2331 "ช",
2332 "ข",
2333 "ใ",
2334 ],
2335 "Greek": [
2336 "α",
2337 "τ",
2338 "ο",
2339 "ι",
2340 "ε",
2341 "ν",
2342 "ρ",
2343 "σ",
2344 "κ",
2345 "η",
2346 "π",
2347 "ς",
2348 "υ",
2349 "μ",
2350 "λ",
2351 "ί",
2352 "ό",
2353 "ά",
2354 "γ",
2355 "έ",
2356 "δ",
2357 "ή",
2358 "ω",
2359 "χ",
2360 "θ",
2361 "ύ",
2362 ],
2363 "Tamil": [
2364 "க",
2365 "த",
2366 "ப",
2367 "ட",
2368 "ர",
2369 "ம",
2370 "ல",
2371 "ன",
2372 "வ",
2373 "ற",
2374 "ய",
2375 "ள",
2376 "ச",
2377 "ந",
2378 "இ",
2379 "ண",
2380 "அ",
2381 "ஆ",
2382 "ழ",
2383 "ங",
2384 "எ",
2385 "உ",
2386 "ஒ",
2387 "ஸ",
2388 ],
2389 "Kazakh": [
2390 "а",
2391 "ы",
2392 "е",
2393 "н",
2394 "т",
2395 "р",
2396 "л",
2397 "і",
2398 "д",
2399 "с",
2400 "м",
2401 "қ",
2402 "к",
2403 "о",
2404 "б",
2405 "и",
2406 "у",
2407 "ғ",
2408 "ж",
2409 "ң",
2410 "з",
2411 "ш",
2412 "й",
2413 "п",
2414 "г",
2415 "ө",
2416 ],
2417}
2419LANGUAGE_SUPPORTED_COUNT: int = len(FREQUENCIES)
2421# Bit flags for unified character classification.
2422# A single unicodedata.name() call sets all relevant flags at once.
2423_LATIN: int = 1
2424_ACCENTUATED: int = 1 << 1
2425_CJK: int = 1 << 2
2426_HANGUL: int = 1 << 3
2427_KATAKANA: int = 1 << 4
2428_HIRAGANA: int = 1 << 5
2429_THAI: int = 1 << 6
2430_ARABIC: int = 1 << 7
2431_ARABIC_ISOLATED_FORM: int = 1 << 8
2432_HALFWIDTH_KATAKANA: int = 1 << 9
2433_LIGATURE: int = 1 << 10
2434_SUPERSCRIPT: int = 1 << 11
2435_SENTENCE_OPEN_PUNCTUATION: int = 1 << 12
2437_ACCENT_KEYWORDS: tuple[str, ...] = (
2438 "WITH GRAVE",
2439 "WITH ACUTE",
2440 "WITH CEDILLA",
2441 "WITH DIAERESIS",
2442 "WITH CIRCUMFLEX",
2443 "WITH TILDE",
2444 "WITH MACRON",
2445 "WITH RING ABOVE",
2446)
2448# Pre-built lookup structures for FREQUENCIES (computed once at import time).
2449# character -> rank mapping per language (replaces list .index() calls).
2450_FREQUENCIES_RANK: dict[str, dict[str, int]] = {
2451 lang: {char: rank for rank, char in enumerate(chars)}
2452 for lang, chars in FREQUENCIES.items()
2453}
2455# frozenset per language (avoids rebuilding set() per call).
2456_FREQUENCIES_SET: dict[str, frozenset[str]] = {
2457 lang: frozenset(chars) for lang, chars in FREQUENCIES.items()
2458}
2460# prebuilt list of secondary range names.
2461_SECONDARY_RANGE_NAMES: frozenset[str] = frozenset(
2462 range_name
2463 for range_name in UNICODE_RANGES_COMBINED
2464 if any(keyword in range_name for keyword in UNICODE_SECONDARY_RANGE_KEYWORD)
2465)
2467_KNOWN_MB_DECODERS: frozenset[str] = frozenset(
2468 {
2469 "utf_8",
2470 "utf_8_sig",
2471 "utf_16",
2472 "utf_16_be",
2473 "utf_16_le",
2474 "utf_32",
2475 "utf_32_le",
2476 "utf_32_be",
2477 "utf_7",
2478 }
2479)
2481_KNOWN_MB_CLASSES: frozenset[str] = frozenset(
2482 {
2483 "_codecs_cn",
2484 "_codecs_hk",
2485 "_codecs_iso2022",
2486 "_codecs_jp",
2487 "_codecs_kr",
2488 "_codecs_tw",
2489 }
2490)
2492_IANA_NAMES: dict[str, str] = {
2493 **aliases,
2494 **{iana_name: iana_name for iana_name in aliases.values()},
2495}
2496_MULTIBYTE_SEARCH_RADIUS: int = 32768