Spaces:
Runtime error
Runtime error
File size: 11,285 Bytes
e50fe35 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 |
#
# Copyright (c) 2013-present, Anoop Kunchukuttan
# All rights reserved.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.
#
## language codes
LC_TA='ta'
SCRIPT_RANGES={
'pa':[0x0a00,0x0a7f] ,
'gu':[0x0a80,0x0aff] ,
'or':[0x0b00,0x0b7f] ,
'ta':[0x0b80,0x0bff] ,
'te':[0x0c00,0x0c7f] ,
'kn':[0x0c80,0x0cff] ,
'ml':[0x0d00,0x0d7f] ,
'si':[0x0d80,0x0dff] ,
'hi':[0x0900,0x097f] ,
'mr':[0x0900,0x097f] ,
'kK':[0x0900,0x097f] ,
'sa':[0x0900,0x097f] ,
'ne':[0x0900,0x097f] ,
'sd':[0x0900,0x097f] ,
'bn':[0x0980,0x09ff] ,
'as':[0x0980,0x09ff] ,
}
DRAVIDIAN_LANGUAGES=['ta', 'te', 'kn', 'ml',]
IE_LANGUAGES=['hi', 'mr', 'kK', 'sa', 'ne', 'sd', 'bn', 'as', 'pa', 'gu', 'or', 'si', ]
DANDA_DELIM_LANGUAGES=['as','bn','hi','ne','or','pa','sa','sd']
URDU_RANGES=[
[0x0600,0x06ff],
[0x0750,0x077f],
[0xfb50,0xfdff],
[0xfe70,0xfeff],
]
COORDINATED_RANGE_START_INCLUSIVE=0
COORDINATED_RANGE_END_INCLUSIVE=0x6f
NUMERIC_OFFSET_START=0x66
NUMERIC_OFFSET_END=0x6f
HALANTA_OFFSET=0x4d
AUM_OFFSET=0x50
NUKTA_OFFSET=0x3c
RUPEE_SIGN=0x20b9
DANDA=0x0964
DOUBLE_DANDA=0x0965
#TODO: add missing fricatives and approximants
VELAR_RANGE=[0x15,0x19]
PALATAL_RANGE=[0x1a,0x1e]
RETROFLEX_RANGE=[0x1f,0x23]
DENTAL_RANGE=[0x24,0x29]
LABIAL_RANGE=[0x2a,0x2e]
# verify
VOICED_LIST=[0x17,0x18,0x1c,0x1d,0x21,0x22,0x26,0x27,0x2c,0x2d]
UNVOICED_LIST=[0x15,0x16,0x1a,0x1b,0x1f,0x20,0x24,0x25,0x2a,0x2b] #TODO: add sibilants/sonorants
ASPIRATED_LIST=[0x16,0x18,0x1b,0x1d,0x20,0x22,0x25,0x27,0x2b,0x2d]
UNASPIRATED_LIST=[0x15,0x17,0x1a,0x1c,0x1f,0x21,0x24,0x26,0x2a,0x2c]
NASAL_LIST=[0x19,0x1e,0x23,0x28,0x29,0x2d]
FRICATIVE_LIST=[0x36,0x37,0x38]
APPROXIMANT_LIST=[0x2f,0x30,0x31,0x32,0x33,0x34,0x35]
#TODO: ha has to be properly categorized
def is_danda_delim(lang):
"""
Returns True if danda/double danda is a possible delimiter for the language
"""
return lang in DANDA_DELIM_LANGUAGES
def get_offset(c,lang):
"""
Applicable to Brahmi derived Indic scripts
"""
return ord(c)-SCRIPT_RANGES[lang][0]
def offset_to_char(c,lang):
"""
Applicable to Brahmi derived Indic scripts
"""
return chr(c+SCRIPT_RANGES[lang][0])
def in_coordinated_range(c_offset):
"""
Applicable to Brahmi derived Indic scripts
"""
return (c_offset>=COORDINATED_RANGE_START_INCLUSIVE and c_offset<=COORDINATED_RANGE_END_INCLUSIVE)
def is_indiclang_char(c,lang):
"""
Applicable to Brahmi derived Indic scripts
"""
o=get_offset(c,lang)
return (o>=0 and o<=0x7f) or ord(c)==DANDA or ord(c)==DOUBLE_DANDA
# def is_vowel(c,lang):
# """
# Is the character a vowel
# """
# o=get_offset(c,lang)
# return (o>=0x04 and o<=0x14)
# def is_vowel_sign(c,lang):
# """
# Is the character a vowel sign (maatraa)
# """
# o=get_offset(c,lang)
# return (o>=0x3e and o<=0x4c)
# def is_halanta(c,lang):
# """
# Is the character the halanta character
# """
# o=get_offset(c,lang)
# return (o==HALANTA_OFFSET)
# def is_nukta(c,lang):
# """
# Is the character the halanta character
# """
# o=get_offset(c,lang)
# return (o==NUKTA_OFFSET)
# def is_aum(c,lang):
# """
# Is the character a vowel sign (maatraa)
# """
# o=get_offset(c,lang)
# return (o==AUM_OFFSET)
# def is_consonant(c,lang):
# """
# Is the character a consonant
# """
# o=get_offset(c,lang)
# return (o>=0x15 and o<=0x39)
# def is_velar(c,lang):
# """
# Is the character a velar
# """
# o=get_offset(c,lang)
# return (o>=VELAR_RANGE[0] and o<=VELAR_RANGE[1])
# def is_palatal(c,lang):
# """
# Is the character a palatal
# """
# o=get_offset(c,lang)
# return (o>=PALATAL_RANGE[0] and o<=PALATAL_RANGE[1])
# def is_retroflex(c,lang):
# """
# Is the character a retroflex
# """
# o=get_offset(c,lang)
# return (o>=RETROFLEX_RANGE[0] and o<=RETROFLEX_RANGE[1])
# def is_dental(c,lang):
# """
# Is the character a dental
# """
# o=get_offset(c,lang)
# return (o>=DENTAL_RANGE[0] and o<=DENTAL_RANGE[1])
# def is_labial(c,lang):
# """
# Is the character a labial
# """
# o=get_offset(c,lang)
# return (o>=LABIAL_RANGE[0] and o<=LABIAL_RANGE[1])
# def is_voiced(c,lang):
# """
# Is the character a voiced consonant
# """
# o=get_offset(c,lang)
# return o in VOICED_LIST
# def is_unvoiced(c,lang):
# """
# Is the character a unvoiced consonant
# """
# o=get_offset(c,lang)
# return o in UNVOICED_LIST
# def is_aspirated(c,lang):
# """
# Is the character a aspirated consonant
# """
# o=get_offset(c,lang)
# return o in ASPIRATED_LIST
# def is_unaspirated(c,lang):
# """
# Is the character a unaspirated consonant
# """
# o=get_offset(c,lang)
# return o in UNASPIRATED_LIST
# def is_nasal(c,lang):
# """
# Is the character a nasal consonant
# """
# o=get_offset(c,lang)
# return o in NASAL_LIST
# def is_fricative(c,lang):
# """
# Is the character a fricative consonant
# """
# o=get_offset(c,lang)
# return o in FRICATIVE_LIST
# def is_approximant(c,lang):
# """
# Is the character an approximant consonant
# """
# o=get_offset(c,lang)
# return o in APPROXIMANT_LIST
# def is_number(c,lang):
# """
# Is the character a number
# """
# o=get_offset(c,lang)
# return (o>=0x66 and o<=0x6f)
def is_vowel(c,lang):
"""
Is the character a vowel
"""
o=get_offset(c,lang)
return (o>=0x04 and o<=0x14)
def is_vowel_sign(c,lang):
"""
Is the character a vowel sign (maatraa)
"""
o=get_offset(c,lang)
return (o>=0x3e and o<=0x4c)
def is_halanta(c,lang):
"""
Is the character the halanta character
"""
o=get_offset(c,lang)
return (o==HALANTA_OFFSET)
def is_nukta(c,lang):
"""
Is the character the halanta character
"""
o=get_offset(c,lang)
return (o==NUKTA_OFFSET)
def is_aum(c,lang):
"""
Is the character a vowel sign (maatraa)
"""
o=get_offset(c,lang)
return (o==AUM_OFFSET)
def is_consonant(c,lang):
"""
Is the character a consonant
"""
o=get_offset(c,lang)
return (o>=0x15 and o<=0x39)
def is_velar(c,lang):
"""
Is the character a velar
"""
o=get_offset(c,lang)
return (o>=VELAR_RANGE[0] and o<=VELAR_RANGE[1])
def is_palatal(c,lang):
"""
Is the character a palatal
"""
o=get_offset(c,lang)
return (o>=PALATAL_RANGE[0] and o<=PALATAL_RANGE[1])
def is_retroflex(c,lang):
"""
Is the character a retroflex
"""
o=get_offset(c,lang)
return (o>=RETROFLEX_RANGE[0] and o<=RETROFLEX_RANGE[1])
def is_dental(c,lang):
"""
Is the character a dental
"""
o=get_offset(c,lang)
return (o>=DENTAL_RANGE[0] and o<=DENTAL_RANGE[1])
def is_labial(c,lang):
"""
Is the character a labial
"""
o=get_offset(c,lang)
return (o>=LABIAL_RANGE[0] and o<=LABIAL_RANGE[1])
def is_voiced(c,lang):
"""
Is the character a voiced consonant
"""
o=get_offset(c,lang)
return o in VOICED_LIST
def is_unvoiced(c,lang):
"""
Is the character a unvoiced consonant
"""
o=get_offset(c,lang)
return o in UNVOICED_LIST
def is_aspirated(c,lang):
"""
Is the character a aspirated consonant
"""
o=get_offset(c,lang)
return o in ASPIRATED_LIST
def is_unaspirated(c,lang):
"""
Is the character a unaspirated consonant
"""
o=get_offset(c,lang)
return o in UNASPIRATED_LIST
def is_nasal(c,lang):
"""
Is the character a nasal consonant
"""
o=get_offset(c,lang)
return o in NASAL_LIST
def is_fricative(c,lang):
"""
Is the character a fricative consonant
"""
o=get_offset(c,lang)
return o in FRICATIVE_LIST
def is_approximant(c,lang):
"""
Is the character an approximant consonant
"""
o=get_offset(c,lang)
return o in APPROXIMANT_LIST
def is_number(c,lang):
"""
Is the character a number
"""
o=get_offset(c,lang)
return (o>=0x66 and o<=0x6f)
##################################################
def is_vowel_offset(c_offset):
"""
Is the offset a vowel
"""
return (c_offset>=0x04 and c_offset<=0x14)
def is_vowel_sign_offset(c_offset):
"""
Is the offset a vowel sign (maatraa)
"""
return (c_offset>=0x3e and c_offset<=0x4c)
def is_halanta_offset(c_offset):
"""
Is the offset the halanta offset
"""
return (c_offset==HALANTA_OFFSET)
def is_nukta_offset(c_offset):
"""
Is the offset the halanta offset
"""
return (c_offset==NUKTA_OFFSET)
def is_aum_offset(c_offset):
"""
Is the offset a vowel sign (maatraa)
"""
return (c_offset==AUM_OFFSET)
def is_consonant_offset(c_offset):
"""
Is the offset a consonant
"""
return (c_offset>=0x15 and c_offset<=0x39)
def is_velar_offset(c_offset):
"""
Is the offset a velar
"""
return (c_offset>=VELAR_RANGE[0] and c_offset<=VELAR_RANGE[1])
def is_palatal_offset(c_offset):
"""
Is the offset a palatal
"""
return (c_offset>=PALATAL_RANGE[0] and c_offset<=PALATAL_RANGE[1])
def is_retroflex_offset(c_offset):
"""
Is the offset a retroflex
"""
return (c_offset>=RETROFLEX_RANGE[0] and c_offset<=RETROFLEX_RANGE[1])
def is_dental_offset(c_offset):
"""
Is the offset a dental
"""
return (c_offset>=DENTAL_RANGE[0] and c_offset<=DENTAL_RANGE[1])
def is_labial_offset(c_offset):
"""
Is the offset a labial
"""
return (c_offset>=LABIAL_RANGE[0] and c_offset<=LABIAL_RANGE[1])
def is_voiced_offset(c_offset):
"""
Is the offset a voiced consonant
"""
return c_offset in VOICED_LIST
def is_unvoiced_offset(c_offset):
"""
Is the offset a unvoiced consonant
"""
return c_offset in UNVOICED_LIST
def is_aspirated_offset(c_offset):
"""
Is the offset a aspirated consonant
"""
return c_offset in ASPIRATED_LIST
def is_unaspirated_offset(c_offset):
"""
Is the offset a unaspirated consonant
"""
return c_offset in UNASPIRATED_LIST
def is_nasal_offset(c_offset):
"""
Is the offset a nasal consonant
"""
return c_offset in NASAL_LIST
def is_fricative_offset(c_offset):
"""
Is the offset a fricative consonant
"""
return c_offset in FRICATIVE_LIST
def is_approximant_offset(c_offset):
"""
Is the offset an approximant consonant
"""
return c_offset in APPROXIMANT_LIST
def is_number_offset(c_offset):
"""
Is the offset a number
"""
return (c_offset>=0x66 and c_offset<=0x6f)
|