chrislit /
abydos
| Conditions | 219 |
| Total Lines | 916 |
| Code Lines | 548 |
| Lines | 0 |
| Ratio | 0 % |
| Tests | 406 |
| CRAP Score | 219 |
| Changes | 0 | ||
Small methods make your code easier to understand, in particular if combined with a good name. Besides, if your method is small, finding a good name is usually much easier.
For example, if you find yourself adding comments to a method's body, this is usually a good sign to extract the commented part to a new method, and use the comment as a starting point when coming up with a good name for this new method.
Commonly applied refactorings include:
If many parameters/temporary variables are present:
Complex classes like abydos.phonetic._double_metaphone.DoubleMetaphone.encode() often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
| 1 | # -*- coding: utf-8 -*- |
||
| 43 | 1 | def encode(self, word, max_length=-1): |
|
| 44 | """Return the Double Metaphone code for a word. |
||
| 45 | |||
| 46 | Parameters |
||
| 47 | ---------- |
||
| 48 | word : str |
||
| 49 | The word to transform |
||
| 50 | max_length : int |
||
| 51 | The maximum length of the returned Double Metaphone codes (defaults |
||
| 52 | to unlmited, but in Philips' original implementation this was 4) |
||
| 53 | |||
| 54 | Returns |
||
| 55 | ------- |
||
| 56 | tuple |
||
| 57 | The Double Metaphone value(s) |
||
| 58 | |||
| 59 | Examples |
||
| 60 | -------- |
||
| 61 | >>> pe = DoubleMetaphone() |
||
| 62 | >>> pe.encode('Christopher') |
||
| 63 | ('KRSTFR', '') |
||
| 64 | >>> pe.encode('Niall') |
||
| 65 | ('NL', '') |
||
| 66 | >>> pe.encode('Smith') |
||
| 67 | ('SM0', 'XMT') |
||
| 68 | >>> pe.encode('Schmidt') |
||
| 69 | ('XMT', 'SMT') |
||
| 70 | |||
| 71 | """ |
||
| 72 | # Require a max_length of at least 4 |
||
| 73 | 1 | if max_length != -1: |
|
| 74 | 1 | max_length = max(4, max_length) |
|
| 75 | |||
| 76 | 1 | primary = '' |
|
| 77 | 1 | secondary = '' |
|
| 78 | |||
| 79 | 1 | def _slavo_germanic(): |
|
| 80 | """Return True if the word appears to be Slavic or Germanic. |
||
| 81 | |||
| 82 | Returns |
||
| 83 | ------- |
||
| 84 | bool |
||
| 85 | True if the word appears to be Slavic or Germanic |
||
| 86 | |||
| 87 | """ |
||
| 88 | 1 | if 'W' in word or 'K' in word or 'CZ' in word: |
|
| 89 | 1 | return True |
|
| 90 | 1 | return False |
|
| 91 | |||
| 92 | 1 | def _metaph_add(pri, sec=''): |
|
| 93 | """Return a new metaphone tuple with the supplied elements. |
||
| 94 | |||
| 95 | Parameters |
||
| 96 | ---------- |
||
| 97 | pri : str |
||
| 98 | The primary element |
||
| 99 | sec : str |
||
| 100 | The secondary element |
||
| 101 | |||
| 102 | Returns |
||
| 103 | ------- |
||
| 104 | tuple |
||
| 105 | A new metaphone tuple with the supplied elements |
||
| 106 | |||
| 107 | """ |
||
| 108 | 1 | newpri = primary |
|
| 109 | 1 | newsec = secondary |
|
| 110 | 1 | if pri: |
|
| 111 | 1 | newpri += pri |
|
| 112 | 1 | if sec: |
|
| 113 | 1 | if sec != ' ': |
|
| 114 | 1 | newsec += sec |
|
| 115 | else: |
||
| 116 | 1 | newsec += pri |
|
| 117 | 1 | return newpri, newsec |
|
| 118 | |||
| 119 | 1 | def _is_vowel(pos): |
|
| 120 | """Return True if the character at word[pos] is a vowel. |
||
| 121 | |||
| 122 | Parameters |
||
| 123 | ---------- |
||
| 124 | pos : int |
||
| 125 | Position in the word |
||
| 126 | |||
| 127 | Returns |
||
| 128 | ------- |
||
| 129 | bool |
||
| 130 | True if the character is a vowel |
||
| 131 | |||
| 132 | """ |
||
| 133 | 1 | if pos >= 0 and word[pos] in {'A', 'E', 'I', 'O', 'U', 'Y'}: |
|
| 134 | 1 | return True |
|
| 135 | 1 | return False |
|
| 136 | |||
| 137 | 1 | def _get_at(pos): |
|
| 138 | """Return the character at word[pos]. |
||
| 139 | |||
| 140 | Parameters |
||
| 141 | ---------- |
||
| 142 | pos : int |
||
| 143 | Position in the word |
||
| 144 | |||
| 145 | Returns |
||
| 146 | ------- |
||
| 147 | str |
||
| 148 | Character at word[pos] |
||
| 149 | |||
| 150 | """ |
||
| 151 | 1 | return word[pos] |
|
| 152 | |||
| 153 | 1 | def _string_at(pos, slen, substrings): |
|
| 154 | """Return True if word[pos:pos+slen] is in substrings. |
||
| 155 | |||
| 156 | Parameters |
||
| 157 | ---------- |
||
| 158 | pos : int |
||
| 159 | Position in the word |
||
| 160 | slen : int |
||
| 161 | Substring length |
||
| 162 | substrings : set |
||
| 163 | Substrings to search |
||
| 164 | |||
| 165 | Returns |
||
| 166 | ------- |
||
| 167 | bool |
||
| 168 | True if word[pos:pos+slen] is in substrings |
||
| 169 | |||
| 170 | """ |
||
| 171 | 1 | if pos < 0: |
|
| 172 | 1 | return False |
|
| 173 | 1 | return word[pos : pos + slen] in substrings |
|
| 174 | |||
| 175 | 1 | current = 0 |
|
| 176 | 1 | length = len(word) |
|
| 177 | 1 | if length < 1: |
|
| 178 | 1 | return '', '' |
|
| 179 | 1 | last = length - 1 |
|
| 180 | |||
| 181 | 1 | word = word.upper() |
|
| 182 | 1 | word = word.replace('ß', 'SS') |
|
| 183 | |||
| 184 | # Pad the original string so that we can index beyond the edge of the |
||
| 185 | # world |
||
| 186 | 1 | word += ' ' |
|
| 187 | |||
| 188 | # Skip these when at start of word |
||
| 189 | 1 | if word[0:2] in {'GN', 'KN', 'PN', 'WR', 'PS'}: |
|
| 190 | 1 | current += 1 |
|
| 191 | |||
| 192 | # Initial 'X' is pronounced 'Z' e.g. 'Xavier' |
||
| 193 | 1 | if _get_at(0) == 'X': |
|
| 194 | 1 | primary, secondary = _metaph_add('S') # 'Z' maps to 'S' |
|
| 195 | 1 | current += 1 |
|
| 196 | |||
| 197 | # Main loop |
||
| 198 | 1 | while True: |
|
| 199 | 1 | if current >= length: |
|
| 200 | 1 | break |
|
| 201 | |||
| 202 | 1 | if _get_at(current) in {'A', 'E', 'I', 'O', 'U', 'Y'}: |
|
| 203 | 1 | if current == 0: |
|
| 204 | # All init vowels now map to 'A' |
||
| 205 | 1 | primary, secondary = _metaph_add('A') |
|
| 206 | 1 | current += 1 |
|
| 207 | 1 | continue |
|
| 208 | |||
| 209 | 1 | elif _get_at(current) == 'B': |
|
| 210 | # "-mb", e.g", "dumb", already skipped over... |
||
| 211 | 1 | primary, secondary = _metaph_add('P') |
|
| 212 | 1 | if _get_at(current + 1) == 'B': |
|
| 213 | 1 | current += 2 |
|
| 214 | else: |
||
| 215 | 1 | current += 1 |
|
| 216 | 1 | continue |
|
| 217 | |||
| 218 | 1 | elif _get_at(current) == 'Ç': |
|
| 219 | 1 | primary, secondary = _metaph_add('S') |
|
| 220 | 1 | current += 1 |
|
| 221 | 1 | continue |
|
| 222 | |||
| 223 | 1 | elif _get_at(current) == 'C': |
|
| 224 | # Various Germanic |
||
| 225 | 1 | if ( |
|
| 226 | current > 1 |
||
| 227 | and not _is_vowel(current - 2) |
||
| 228 | and _string_at((current - 1), 3, {'ACH'}) |
||
| 229 | and ( |
||
| 230 | (_get_at(current + 2) != 'I') |
||
| 231 | and ( |
||
| 232 | (_get_at(current + 2) != 'E') |
||
| 233 | or _string_at( |
||
| 234 | (current - 2), 6, {'BACHER', 'MACHER'} |
||
| 235 | ) |
||
| 236 | ) |
||
| 237 | ) |
||
| 238 | ): |
||
| 239 | 1 | primary, secondary = _metaph_add('K') |
|
| 240 | 1 | current += 2 |
|
| 241 | 1 | continue |
|
| 242 | |||
| 243 | # Special case 'caesar' |
||
| 244 | 1 | elif current == 0 and _string_at(current, 6, {'CAESAR'}): |
|
| 245 | 1 | primary, secondary = _metaph_add('S') |
|
| 246 | 1 | current += 2 |
|
| 247 | 1 | continue |
|
| 248 | |||
| 249 | # Italian 'chianti' |
||
| 250 | 1 | elif _string_at(current, 4, {'CHIA'}): |
|
| 251 | 1 | primary, secondary = _metaph_add('K') |
|
| 252 | 1 | current += 2 |
|
| 253 | 1 | continue |
|
| 254 | |||
| 255 | 1 | elif _string_at(current, 2, {'CH'}): |
|
| 256 | # Find 'Michael' |
||
| 257 | 1 | if current > 0 and _string_at(current, 4, {'CHAE'}): |
|
| 258 | 1 | primary, secondary = _metaph_add('K', 'X') |
|
| 259 | 1 | current += 2 |
|
| 260 | 1 | continue |
|
| 261 | |||
| 262 | # Greek roots e.g. 'chemistry', 'chorus' |
||
| 263 | 1 | elif ( |
|
| 264 | current == 0 |
||
| 265 | and ( |
||
| 266 | _string_at((current + 1), 5, {'HARAC', 'HARIS'}) |
||
| 267 | or _string_at( |
||
| 268 | (current + 1), 3, {'HOR', 'HYM', 'HIA', 'HEM'} |
||
| 269 | ) |
||
| 270 | ) |
||
| 271 | and not _string_at(0, 5, {'CHORE'}) |
||
| 272 | ): |
||
| 273 | 1 | primary, secondary = _metaph_add('K') |
|
| 274 | 1 | current += 2 |
|
| 275 | 1 | continue |
|
| 276 | |||
| 277 | # Germanic, Greek, or otherwise 'ch' for 'kh' sound |
||
| 278 | 1 | elif ( |
|
| 279 | ( |
||
| 280 | _string_at(0, 4, {'VAN ', 'VON '}) |
||
| 281 | or _string_at(0, 3, {'SCH'}) |
||
| 282 | ) |
||
| 283 | or |
||
| 284 | # 'architect but not 'arch', 'orchestra', 'orchid' |
||
| 285 | _string_at( |
||
| 286 | (current - 2), 6, {'ORCHES', 'ARCHIT', 'ORCHID'} |
||
| 287 | ) |
||
| 288 | or _string_at((current + 2), 1, {'T', 'S'}) |
||
| 289 | or ( |
||
| 290 | ( |
||
| 291 | _string_at( |
||
| 292 | (current - 1), 1, {'A', 'O', 'U', 'E'} |
||
| 293 | ) |
||
| 294 | or (current == 0) |
||
| 295 | ) |
||
| 296 | and |
||
| 297 | # e.g., 'wachtler', 'wechsler', but not 'tichner' |
||
| 298 | _string_at( |
||
| 299 | (current + 2), |
||
| 300 | 1, |
||
| 301 | { |
||
| 302 | 'L', |
||
| 303 | 'R', |
||
| 304 | 'N', |
||
| 305 | 'M', |
||
| 306 | 'B', |
||
| 307 | 'H', |
||
| 308 | 'F', |
||
| 309 | 'V', |
||
| 310 | 'W', |
||
| 311 | ' ', |
||
| 312 | }, |
||
| 313 | ) |
||
| 314 | ) |
||
| 315 | ): |
||
| 316 | 1 | primary, secondary = _metaph_add('K') |
|
| 317 | |||
| 318 | else: |
||
| 319 | 1 | if current > 0: |
|
| 320 | 1 | if _string_at(0, 2, {'MC'}): |
|
| 321 | # e.g., "McHugh" |
||
| 322 | 1 | primary, secondary = _metaph_add('K') |
|
| 323 | else: |
||
| 324 | 1 | primary, secondary = _metaph_add('X', 'K') |
|
| 325 | else: |
||
| 326 | 1 | primary, secondary = _metaph_add('X') |
|
| 327 | |||
| 328 | 1 | current += 2 |
|
| 329 | 1 | continue |
|
| 330 | |||
| 331 | # e.g, 'czerny' |
||
| 332 | 1 | elif _string_at(current, 2, {'CZ'}) and not _string_at( |
|
| 333 | (current - 2), 4, {'WICZ'} |
||
| 334 | ): |
||
| 335 | 1 | primary, secondary = _metaph_add('S', 'X') |
|
| 336 | 1 | current += 2 |
|
| 337 | 1 | continue |
|
| 338 | |||
| 339 | # e.g., 'focaccia' |
||
| 340 | 1 | elif _string_at((current + 1), 3, {'CIA'}): |
|
| 341 | 1 | primary, secondary = _metaph_add('X') |
|
| 342 | 1 | current += 3 |
|
| 343 | |||
| 344 | # double 'C', but not if e.g. 'McClellan' |
||
| 345 | 1 | elif _string_at(current, 2, {'CC'}) and not ( |
|
| 346 | (current == 1) and (_get_at(0) == 'M') |
||
| 347 | ): |
||
| 348 | # 'bellocchio' but not 'bacchus' |
||
| 349 | 1 | if _string_at( |
|
| 350 | (current + 2), 1, {'I', 'E', 'H'} |
||
| 351 | ) and not _string_at((current + 2), 2, {'HU'}): |
||
| 352 | # 'accident', 'accede' 'succeed' |
||
| 353 | 1 | if ( |
|
| 354 | (current == 1) and _get_at(current - 1) == 'A' |
||
| 355 | ) or _string_at((current - 1), 5, {'UCCEE', 'UCCES'}): |
||
| 356 | 1 | primary, secondary = _metaph_add('KS') |
|
| 357 | # 'bacci', 'bertucci', other italian |
||
| 358 | else: |
||
| 359 | 1 | primary, secondary = _metaph_add('X') |
|
| 360 | 1 | current += 3 |
|
| 361 | 1 | continue |
|
| 362 | else: # Pierce's rule |
||
| 363 | 1 | primary, secondary = _metaph_add('K') |
|
| 364 | 1 | current += 2 |
|
| 365 | 1 | continue |
|
| 366 | |||
| 367 | 1 | elif _string_at(current, 2, {'CK', 'CG', 'CQ'}): |
|
| 368 | 1 | primary, secondary = _metaph_add('K') |
|
| 369 | 1 | current += 2 |
|
| 370 | 1 | continue |
|
| 371 | |||
| 372 | 1 | elif _string_at(current, 2, {'CI', 'CE', 'CY'}): |
|
| 373 | # Italian vs. English |
||
| 374 | 1 | if _string_at(current, 3, {'CIO', 'CIE', 'CIA'}): |
|
| 375 | 1 | primary, secondary = _metaph_add('S', 'X') |
|
| 376 | else: |
||
| 377 | 1 | primary, secondary = _metaph_add('S') |
|
| 378 | 1 | current += 2 |
|
| 379 | 1 | continue |
|
| 380 | |||
| 381 | # else |
||
| 382 | else: |
||
| 383 | 1 | primary, secondary = _metaph_add('K') |
|
| 384 | |||
| 385 | # name sent in 'mac caffrey', 'mac gregor |
||
| 386 | 1 | if _string_at((current + 1), 2, {' C', ' Q', ' G'}): |
|
| 387 | 1 | current += 3 |
|
| 388 | 1 | elif _string_at( |
|
| 389 | (current + 1), 1, {'C', 'K', 'Q'} |
||
| 390 | ) and not _string_at((current + 1), 2, {'CE', 'CI'}): |
||
| 391 | 1 | current += 2 |
|
| 392 | else: |
||
| 393 | 1 | current += 1 |
|
| 394 | 1 | continue |
|
| 395 | |||
| 396 | 1 | elif _get_at(current) == 'D': |
|
| 397 | 1 | if _string_at(current, 2, {'DG'}): |
|
| 398 | 1 | if _string_at((current + 2), 1, {'I', 'E', 'Y'}): |
|
| 399 | # e.g. 'edge' |
||
| 400 | 1 | primary, secondary = _metaph_add('J') |
|
| 401 | 1 | current += 3 |
|
| 402 | 1 | continue |
|
| 403 | else: |
||
| 404 | # e.g. 'edgar' |
||
| 405 | 1 | primary, secondary = _metaph_add('TK') |
|
| 406 | 1 | current += 2 |
|
| 407 | 1 | continue |
|
| 408 | |||
| 409 | 1 | elif _string_at(current, 2, {'DT', 'DD'}): |
|
| 410 | 1 | primary, secondary = _metaph_add('T') |
|
| 411 | 1 | current += 2 |
|
| 412 | 1 | continue |
|
| 413 | |||
| 414 | # else |
||
| 415 | else: |
||
| 416 | 1 | primary, secondary = _metaph_add('T') |
|
| 417 | 1 | current += 1 |
|
| 418 | 1 | continue |
|
| 419 | |||
| 420 | 1 | elif _get_at(current) == 'F': |
|
| 421 | 1 | if _get_at(current + 1) == 'F': |
|
| 422 | 1 | current += 2 |
|
| 423 | else: |
||
| 424 | 1 | current += 1 |
|
| 425 | 1 | primary, secondary = _metaph_add('F') |
|
| 426 | 1 | continue |
|
| 427 | |||
| 428 | 1 | elif _get_at(current) == 'G': |
|
| 429 | 1 | if _get_at(current + 1) == 'H': |
|
| 430 | 1 | if (current > 0) and not _is_vowel(current - 1): |
|
| 431 | 1 | primary, secondary = _metaph_add('K') |
|
| 432 | 1 | current += 2 |
|
| 433 | 1 | continue |
|
| 434 | |||
| 435 | # 'ghislane', ghiradelli |
||
| 436 | 1 | elif current == 0: |
|
| 437 | 1 | if _get_at(current + 2) == 'I': |
|
| 438 | 1 | primary, secondary = _metaph_add('J') |
|
| 439 | else: |
||
| 440 | 1 | primary, secondary = _metaph_add('K') |
|
| 441 | 1 | current += 2 |
|
| 442 | 1 | continue |
|
| 443 | |||
| 444 | # Parker's rule (with some further refinements) - |
||
| 445 | # e.g., 'hugh' |
||
| 446 | 1 | elif ( |
|
| 447 | ( |
||
| 448 | (current > 1) |
||
| 449 | and _string_at((current - 2), 1, {'B', 'H', 'D'}) |
||
| 450 | ) |
||
| 451 | or |
||
| 452 | # e.g., 'bough' |
||
| 453 | ( |
||
| 454 | (current > 2) |
||
| 455 | and _string_at((current - 3), 1, {'B', 'H', 'D'}) |
||
| 456 | ) |
||
| 457 | or |
||
| 458 | # e.g., 'broughton' |
||
| 459 | ( |
||
| 460 | (current > 3) |
||
| 461 | and _string_at((current - 4), 1, {'B', 'H'}) |
||
| 462 | ) |
||
| 463 | ): |
||
| 464 | 1 | current += 2 |
|
| 465 | 1 | continue |
|
| 466 | else: |
||
| 467 | # e.g. 'laugh', 'McLaughlin', 'cough', |
||
| 468 | # 'gough', 'rough', 'tough' |
||
| 469 | 1 | if ( |
|
| 470 | (current > 2) |
||
| 471 | and (_get_at(current - 1) == 'U') |
||
| 472 | and ( |
||
| 473 | _string_at( |
||
| 474 | (current - 3), 1, {'C', 'G', 'L', 'R', 'T'} |
||
| 475 | ) |
||
| 476 | ) |
||
| 477 | ): |
||
| 478 | 1 | primary, secondary = _metaph_add('F') |
|
| 479 | 1 | elif (current > 0) and _get_at(current - 1) != 'I': |
|
| 480 | 1 | primary, secondary = _metaph_add('K') |
|
| 481 | 1 | current += 2 |
|
| 482 | 1 | continue |
|
| 483 | |||
| 484 | 1 | elif _get_at(current + 1) == 'N': |
|
| 485 | 1 | if ( |
|
| 486 | (current == 1) |
||
| 487 | and _is_vowel(0) |
||
| 488 | and not _slavo_germanic() |
||
| 489 | ): |
||
| 490 | 1 | primary, secondary = _metaph_add('KN', 'N') |
|
| 491 | # not e.g. 'cagney' |
||
| 492 | 1 | elif ( |
|
| 493 | not _string_at((current + 2), 2, {'EY'}) |
||
| 494 | and (_get_at(current + 1) != 'Y') |
||
| 495 | and not _slavo_germanic() |
||
| 496 | ): |
||
| 497 | 1 | primary, secondary = _metaph_add('N', 'KN') |
|
| 498 | else: |
||
| 499 | 1 | primary, secondary = _metaph_add('KN') |
|
| 500 | 1 | current += 2 |
|
| 501 | 1 | continue |
|
| 502 | |||
| 503 | # 'tagliaro' |
||
| 504 | 1 | elif ( |
|
| 505 | _string_at((current + 1), 2, {'LI'}) |
||
| 506 | and not _slavo_germanic() |
||
| 507 | ): |
||
| 508 | 1 | primary, secondary = _metaph_add('KL', 'L') |
|
| 509 | 1 | current += 2 |
|
| 510 | 1 | continue |
|
| 511 | |||
| 512 | # -ges-, -gep-, -gel-, -gie- at beginning |
||
| 513 | 1 | elif (current == 0) and ( |
|
| 514 | (_get_at(current + 1) == 'Y') |
||
| 515 | or _string_at( |
||
| 516 | (current + 1), |
||
| 517 | 2, |
||
| 518 | { |
||
| 519 | 'ES', |
||
| 520 | 'EP', |
||
| 521 | 'EB', |
||
| 522 | 'EL', |
||
| 523 | 'EY', |
||
| 524 | 'IB', |
||
| 525 | 'IL', |
||
| 526 | 'IN', |
||
| 527 | 'IE', |
||
| 528 | 'EI', |
||
| 529 | 'ER', |
||
| 530 | }, |
||
| 531 | ) |
||
| 532 | ): |
||
| 533 | 1 | primary, secondary = _metaph_add('K', 'J') |
|
| 534 | 1 | current += 2 |
|
| 535 | 1 | continue |
|
| 536 | |||
| 537 | # -ger-, -gy- |
||
| 538 | 1 | elif ( |
|
| 539 | ( |
||
| 540 | _string_at((current + 1), 2, {'ER'}) |
||
| 541 | or (_get_at(current + 1) == 'Y') |
||
| 542 | ) |
||
| 543 | and not _string_at(0, 6, {'DANGER', 'RANGER', 'MANGER'}) |
||
| 544 | and not _string_at((current - 1), 1, {'E', 'I'}) |
||
| 545 | and not _string_at((current - 1), 3, {'RGY', 'OGY'}) |
||
| 546 | ): |
||
| 547 | 1 | primary, secondary = _metaph_add('K', 'J') |
|
| 548 | 1 | current += 2 |
|
| 549 | 1 | continue |
|
| 550 | |||
| 551 | # italian e.g, 'biaggi' |
||
| 552 | 1 | elif _string_at( |
|
| 553 | (current + 1), 1, {'E', 'I', 'Y'} |
||
| 554 | ) or _string_at((current - 1), 4, {'AGGI', 'OGGI'}): |
||
| 555 | # obvious germanic |
||
| 556 | 1 | if ( |
|
| 557 | _string_at(0, 4, {'VAN ', 'VON '}) |
||
| 558 | or _string_at(0, 3, {'SCH'}) |
||
| 559 | ) or _string_at((current + 1), 2, {'ET'}): |
||
| 560 | 1 | primary, secondary = _metaph_add('K') |
|
| 561 | 1 | elif _string_at((current + 1), 4, {'IER '}): |
|
| 562 | 1 | primary, secondary = _metaph_add('J') |
|
| 563 | else: |
||
| 564 | 1 | primary, secondary = _metaph_add('J', 'K') |
|
| 565 | 1 | current += 2 |
|
| 566 | 1 | continue |
|
| 567 | |||
| 568 | else: |
||
| 569 | 1 | if _get_at(current + 1) == 'G': |
|
| 570 | 1 | current += 2 |
|
| 571 | else: |
||
| 572 | 1 | current += 1 |
|
| 573 | 1 | primary, secondary = _metaph_add('K') |
|
| 574 | 1 | continue |
|
| 575 | |||
| 576 | 1 | elif _get_at(current) == 'H': |
|
| 577 | # only keep if first & before vowel or btw. 2 vowels |
||
| 578 | 1 | if ((current == 0) or _is_vowel(current - 1)) and _is_vowel( |
|
| 579 | current + 1 |
||
| 580 | ): |
||
| 581 | 1 | primary, secondary = _metaph_add('H') |
|
| 582 | 1 | current += 2 |
|
| 583 | else: # also takes care of 'HH' |
||
| 584 | 1 | current += 1 |
|
| 585 | 1 | continue |
|
| 586 | |||
| 587 | 1 | elif _get_at(current) == 'J': |
|
| 588 | # obvious spanish, 'jose', 'san jacinto' |
||
| 589 | 1 | if _string_at(current, 4, {'JOSE'}) or _string_at( |
|
| 590 | 0, 4, {'SAN '} |
||
| 591 | ): |
||
| 592 | 1 | if ( |
|
| 593 | (current == 0) and (_get_at(current + 4) == ' ') |
||
| 594 | ) or _string_at(0, 4, {'SAN '}): |
||
| 595 | 1 | primary, secondary = _metaph_add('H') |
|
| 596 | else: |
||
| 597 | 1 | primary, secondary = _metaph_add('J', 'H') |
|
| 598 | 1 | current += 1 |
|
| 599 | 1 | continue |
|
| 600 | |||
| 601 | 1 | elif (current == 0) and not _string_at(current, 4, {'JOSE'}): |
|
| 602 | # Yankelovich/Jankelowicz |
||
| 603 | 1 | primary, secondary = _metaph_add('J', 'A') |
|
| 604 | # Spanish pron. of e.g. 'bajador' |
||
| 605 | 1 | elif ( |
|
| 606 | _is_vowel(current - 1) |
||
| 607 | and not _slavo_germanic() |
||
| 608 | and ( |
||
| 609 | (_get_at(current + 1) == 'A') |
||
| 610 | or (_get_at(current + 1) == 'O') |
||
| 611 | ) |
||
| 612 | ): |
||
| 613 | 1 | primary, secondary = _metaph_add('J', 'H') |
|
| 614 | 1 | elif current == last: |
|
| 615 | 1 | primary, secondary = _metaph_add('J', ' ') |
|
| 616 | 1 | elif not _string_at( |
|
| 617 | (current + 1), 1, {'L', 'T', 'K', 'S', 'N', 'M', 'B', 'Z'} |
||
| 618 | ) and not _string_at((current - 1), 1, {'S', 'K', 'L'}): |
||
| 619 | 1 | primary, secondary = _metaph_add('J') |
|
| 620 | |||
| 621 | 1 | if _get_at(current + 1) == 'J': # it could happen! |
|
| 622 | 1 | current += 2 |
|
| 623 | else: |
||
| 624 | 1 | current += 1 |
|
| 625 | 1 | continue |
|
| 626 | |||
| 627 | 1 | elif _get_at(current) == 'K': |
|
| 628 | 1 | if _get_at(current + 1) == 'K': |
|
| 629 | 1 | current += 2 |
|
| 630 | else: |
||
| 631 | 1 | current += 1 |
|
| 632 | 1 | primary, secondary = _metaph_add('K') |
|
| 633 | 1 | continue |
|
| 634 | |||
| 635 | 1 | elif _get_at(current) == 'L': |
|
| 636 | 1 | if _get_at(current + 1) == 'L': |
|
| 637 | # Spanish e.g. 'cabrillo', 'gallegos' |
||
| 638 | 1 | if ( |
|
| 639 | (current == (length - 3)) |
||
| 640 | and _string_at( |
||
| 641 | (current - 1), 4, {'ILLO', 'ILLA', 'ALLE'} |
||
| 642 | ) |
||
| 643 | ) or ( |
||
| 644 | ( |
||
| 645 | _string_at((last - 1), 2, {'AS', 'OS'}) |
||
| 646 | or _string_at(last, 1, {'A', 'O'}) |
||
| 647 | ) |
||
| 648 | and _string_at((current - 1), 4, {'ALLE'}) |
||
| 649 | ): |
||
| 650 | 1 | primary, secondary = _metaph_add('L', ' ') |
|
| 651 | 1 | current += 2 |
|
| 652 | 1 | continue |
|
| 653 | 1 | current += 2 |
|
| 654 | else: |
||
| 655 | 1 | current += 1 |
|
| 656 | 1 | primary, secondary = _metaph_add('L') |
|
| 657 | 1 | continue |
|
| 658 | |||
| 659 | 1 | elif _get_at(current) == 'M': |
|
| 660 | 1 | if ( |
|
| 661 | ( |
||
| 662 | _string_at((current - 1), 3, {'UMB'}) |
||
| 663 | and ( |
||
| 664 | ((current + 1) == last) |
||
| 665 | or _string_at((current + 2), 2, {'ER'}) |
||
| 666 | ) |
||
| 667 | ) |
||
| 668 | or |
||
| 669 | # 'dumb', 'thumb' |
||
| 670 | (_get_at(current + 1) == 'M') |
||
| 671 | ): |
||
| 672 | 1 | current += 2 |
|
| 673 | else: |
||
| 674 | 1 | current += 1 |
|
| 675 | 1 | primary, secondary = _metaph_add('M') |
|
| 676 | 1 | continue |
|
| 677 | |||
| 678 | 1 | elif _get_at(current) == 'N': |
|
| 679 | 1 | if _get_at(current + 1) == 'N': |
|
| 680 | 1 | current += 2 |
|
| 681 | else: |
||
| 682 | 1 | current += 1 |
|
| 683 | 1 | primary, secondary = _metaph_add('N') |
|
| 684 | 1 | continue |
|
| 685 | |||
| 686 | 1 | elif _get_at(current) == 'Ñ': |
|
| 687 | 1 | current += 1 |
|
| 688 | 1 | primary, secondary = _metaph_add('N') |
|
| 689 | 1 | continue |
|
| 690 | |||
| 691 | 1 | elif _get_at(current) == 'P': |
|
| 692 | 1 | if _get_at(current + 1) == 'H': |
|
| 693 | 1 | primary, secondary = _metaph_add('F') |
|
| 694 | 1 | current += 2 |
|
| 695 | 1 | continue |
|
| 696 | |||
| 697 | # also account for "campbell", "raspberry" |
||
| 698 | 1 | elif _string_at((current + 1), 1, {'P', 'B'}): |
|
| 699 | 1 | current += 2 |
|
| 700 | else: |
||
| 701 | 1 | current += 1 |
|
| 702 | 1 | primary, secondary = _metaph_add('P') |
|
| 703 | 1 | continue |
|
| 704 | |||
| 705 | 1 | elif _get_at(current) == 'Q': |
|
| 706 | 1 | if _get_at(current + 1) == 'Q': |
|
| 707 | 1 | current += 2 |
|
| 708 | else: |
||
| 709 | 1 | current += 1 |
|
| 710 | 1 | primary, secondary = _metaph_add('K') |
|
| 711 | 1 | continue |
|
| 712 | |||
| 713 | 1 | elif _get_at(current) == 'R': |
|
| 714 | # french e.g. 'rogier', but exclude 'hochmeier' |
||
| 715 | 1 | if ( |
|
| 716 | (current == last) |
||
| 717 | and not _slavo_germanic() |
||
| 718 | and _string_at((current - 2), 2, {'IE'}) |
||
| 719 | and not _string_at((current - 4), 2, {'ME', 'MA'}) |
||
| 720 | ): |
||
| 721 | 1 | primary, secondary = _metaph_add('', 'R') |
|
| 722 | else: |
||
| 723 | 1 | primary, secondary = _metaph_add('R') |
|
| 724 | |||
| 725 | 1 | if _get_at(current + 1) == 'R': |
|
| 726 | 1 | current += 2 |
|
| 727 | else: |
||
| 728 | 1 | current += 1 |
|
| 729 | 1 | continue |
|
| 730 | |||
| 731 | 1 | elif _get_at(current) == 'S': |
|
| 732 | # special cases 'island', 'isle', 'carlisle', 'carlysle' |
||
| 733 | 1 | if _string_at((current - 1), 3, {'ISL', 'YSL'}): |
|
| 734 | 1 | current += 1 |
|
| 735 | 1 | continue |
|
| 736 | |||
| 737 | # special case 'sugar-' |
||
| 738 | 1 | elif (current == 0) and _string_at(current, 5, {'SUGAR'}): |
|
| 739 | 1 | primary, secondary = _metaph_add('X', 'S') |
|
| 740 | 1 | current += 1 |
|
| 741 | 1 | continue |
|
| 742 | |||
| 743 | 1 | elif _string_at(current, 2, {'SH'}): |
|
| 744 | # Germanic |
||
| 745 | 1 | if _string_at( |
|
| 746 | (current + 1), 4, {'HEIM', 'HOEK', 'HOLM', 'HOLZ'} |
||
| 747 | ): |
||
| 748 | 1 | primary, secondary = _metaph_add('S') |
|
| 749 | else: |
||
| 750 | 1 | primary, secondary = _metaph_add('X') |
|
| 751 | 1 | current += 2 |
|
| 752 | 1 | continue |
|
| 753 | |||
| 754 | # Italian & Armenian |
||
| 755 | 1 | elif _string_at(current, 3, {'SIO', 'SIA'}) or _string_at( |
|
| 756 | current, 4, {'SIAN'} |
||
| 757 | ): |
||
| 758 | 1 | if not _slavo_germanic(): |
|
| 759 | 1 | primary, secondary = _metaph_add('S', 'X') |
|
| 760 | else: |
||
| 761 | 1 | primary, secondary = _metaph_add('S') |
|
| 762 | 1 | current += 3 |
|
| 763 | 1 | continue |
|
| 764 | |||
| 765 | # German & anglicisations, e.g. 'smith' match 'schmidt', |
||
| 766 | # 'snider' match 'schneider' |
||
| 767 | # also, -sz- in Slavic language although in Hungarian it is |
||
| 768 | # pronounced 's' |
||
| 769 | 1 | elif ( |
|
| 770 | (current == 0) |
||
| 771 | and _string_at((current + 1), 1, {'M', 'N', 'L', 'W'}) |
||
| 772 | ) or _string_at((current + 1), 1, {'Z'}): |
||
| 773 | 1 | primary, secondary = _metaph_add('S', 'X') |
|
| 774 | 1 | if _string_at((current + 1), 1, {'Z'}): |
|
| 775 | 1 | current += 2 |
|
| 776 | else: |
||
| 777 | 1 | current += 1 |
|
| 778 | 1 | continue |
|
| 779 | |||
| 780 | 1 | elif _string_at(current, 2, {'SC'}): |
|
| 781 | # Schlesinger's rule |
||
| 782 | 1 | if _get_at(current + 2) == 'H': |
|
| 783 | # dutch origin, e.g. 'school', 'schooner' |
||
| 784 | 1 | if _string_at( |
|
| 785 | (current + 3), |
||
| 786 | 2, |
||
| 787 | {'OO', 'ER', 'EN', 'UY', 'ED', 'EM'}, |
||
| 788 | ): |
||
| 789 | # 'schermerhorn', 'schenker' |
||
| 790 | 1 | if _string_at((current + 3), 2, {'ER', 'EN'}): |
|
| 791 | 1 | primary, secondary = _metaph_add('X', 'SK') |
|
| 792 | else: |
||
| 793 | 1 | primary, secondary = _metaph_add('SK') |
|
| 794 | 1 | current += 3 |
|
| 795 | 1 | continue |
|
| 796 | else: |
||
| 797 | 1 | if ( |
|
| 798 | (current == 0) |
||
| 799 | and not _is_vowel(3) |
||
| 800 | and (_get_at(3) != 'W') |
||
| 801 | ): |
||
| 802 | 1 | primary, secondary = _metaph_add('X', 'S') |
|
| 803 | else: |
||
| 804 | 1 | primary, secondary = _metaph_add('X') |
|
| 805 | 1 | current += 3 |
|
| 806 | 1 | continue |
|
| 807 | |||
| 808 | 1 | elif _string_at((current + 2), 1, {'I', 'E', 'Y'}): |
|
| 809 | 1 | primary, secondary = _metaph_add('S') |
|
| 810 | 1 | current += 3 |
|
| 811 | 1 | continue |
|
| 812 | |||
| 813 | # else |
||
| 814 | else: |
||
| 815 | 1 | primary, secondary = _metaph_add('SK') |
|
| 816 | 1 | current += 3 |
|
| 817 | 1 | continue |
|
| 818 | |||
| 819 | else: |
||
| 820 | # french e.g. 'resnais', 'artois' |
||
| 821 | 1 | if (current == last) and _string_at( |
|
| 822 | (current - 2), 2, {'AI', 'OI'} |
||
| 823 | ): |
||
| 824 | 1 | primary, secondary = _metaph_add('', 'S') |
|
| 825 | else: |
||
| 826 | 1 | primary, secondary = _metaph_add('S') |
|
| 827 | |||
| 828 | 1 | if _string_at((current + 1), 1, {'S', 'Z'}): |
|
| 829 | 1 | current += 2 |
|
| 830 | else: |
||
| 831 | 1 | current += 1 |
|
| 832 | 1 | continue |
|
| 833 | |||
| 834 | 1 | elif _get_at(current) == 'T': |
|
| 835 | 1 | if _string_at(current, 4, {'TION'}): |
|
| 836 | 1 | primary, secondary = _metaph_add('X') |
|
| 837 | 1 | current += 3 |
|
| 838 | 1 | continue |
|
| 839 | |||
| 840 | 1 | elif _string_at(current, 3, {'TIA', 'TCH'}): |
|
| 841 | 1 | primary, secondary = _metaph_add('X') |
|
| 842 | 1 | current += 3 |
|
| 843 | 1 | continue |
|
| 844 | |||
| 845 | 1 | elif _string_at(current, 2, {'TH'}) or _string_at( |
|
| 846 | current, 3, {'TTH'} |
||
| 847 | ): |
||
| 848 | # special case 'thomas', 'thames' or germanic |
||
| 849 | 1 | if ( |
|
| 850 | _string_at((current + 2), 2, {'OM', 'AM'}) |
||
| 851 | or _string_at(0, 4, {'VAN ', 'VON '}) |
||
| 852 | or _string_at(0, 3, {'SCH'}) |
||
| 853 | ): |
||
| 854 | 1 | primary, secondary = _metaph_add('T') |
|
| 855 | else: |
||
| 856 | 1 | primary, secondary = _metaph_add('0', 'T') |
|
| 857 | 1 | current += 2 |
|
| 858 | 1 | continue |
|
| 859 | |||
| 860 | 1 | elif _string_at((current + 1), 1, {'T', 'D'}): |
|
| 861 | 1 | current += 2 |
|
| 862 | else: |
||
| 863 | 1 | current += 1 |
|
| 864 | 1 | primary, secondary = _metaph_add('T') |
|
| 865 | 1 | continue |
|
| 866 | |||
| 867 | 1 | elif _get_at(current) == 'V': |
|
| 868 | 1 | if _get_at(current + 1) == 'V': |
|
| 869 | 1 | current += 2 |
|
| 870 | else: |
||
| 871 | 1 | current += 1 |
|
| 872 | 1 | primary, secondary = _metaph_add('F') |
|
| 873 | 1 | continue |
|
| 874 | |||
| 875 | 1 | elif _get_at(current) == 'W': |
|
| 876 | # can also be in middle of word |
||
| 877 | 1 | if _string_at(current, 2, {'WR'}): |
|
| 878 | 1 | primary, secondary = _metaph_add('R') |
|
| 879 | 1 | current += 2 |
|
| 880 | 1 | continue |
|
| 881 | 1 | elif (current == 0) and ( |
|
| 882 | _is_vowel(current + 1) or _string_at(current, 2, {'WH'}) |
||
| 883 | ): |
||
| 884 | # Wasserman should match Vasserman |
||
| 885 | 1 | if _is_vowel(current + 1): |
|
| 886 | 1 | primary, secondary = _metaph_add('A', 'F') |
|
| 887 | else: |
||
| 888 | # need Uomo to match Womo |
||
| 889 | 1 | primary, secondary = _metaph_add('A') |
|
| 890 | |||
| 891 | # Arnow should match Arnoff |
||
| 892 | 1 | if ( |
|
| 893 | ((current == last) and _is_vowel(current - 1)) |
||
| 894 | or _string_at( |
||
| 895 | (current - 1), 5, {'EWSKI', 'EWSKY', 'OWSKI', 'OWSKY'} |
||
| 896 | ) |
||
| 897 | or _string_at(0, 3, {'SCH'}) |
||
| 898 | ): |
||
| 899 | 1 | primary, secondary = _metaph_add('', 'F') |
|
| 900 | 1 | current += 1 |
|
| 901 | 1 | continue |
|
| 902 | # Polish e.g. 'filipowicz' |
||
| 903 | 1 | elif _string_at(current, 4, {'WICZ', 'WITZ'}): |
|
| 904 | 1 | primary, secondary = _metaph_add('TS', 'FX') |
|
| 905 | 1 | current += 4 |
|
| 906 | 1 | continue |
|
| 907 | # else skip it |
||
| 908 | else: |
||
| 909 | 1 | current += 1 |
|
| 910 | 1 | continue |
|
| 911 | |||
| 912 | 1 | elif _get_at(current) == 'X': |
|
| 913 | # French e.g. breaux |
||
| 914 | 1 | if not ( |
|
| 915 | (current == last) |
||
| 916 | and ( |
||
| 917 | _string_at((current - 3), 3, {'IAU', 'EAU'}) |
||
| 918 | or _string_at((current - 2), 2, {'AU', 'OU'}) |
||
| 919 | ) |
||
| 920 | ): |
||
| 921 | 1 | primary, secondary = _metaph_add('KS') |
|
| 922 | |||
| 923 | 1 | if _string_at((current + 1), 1, {'C', 'X'}): |
|
| 924 | 1 | current += 2 |
|
| 925 | else: |
||
| 926 | 1 | current += 1 |
|
| 927 | 1 | continue |
|
| 928 | |||
| 929 | 1 | elif _get_at(current) == 'Z': |
|
| 930 | # Chinese Pinyin e.g. 'zhao' |
||
| 931 | 1 | if _get_at(current + 1) == 'H': |
|
| 932 | 1 | primary, secondary = _metaph_add('J') |
|
| 933 | 1 | current += 2 |
|
| 934 | 1 | continue |
|
| 935 | 1 | elif _string_at((current + 1), 2, {'ZO', 'ZI', 'ZA'}) or ( |
|
| 936 | _slavo_germanic() |
||
| 937 | and ((current > 0) and _get_at(current - 1) != 'T') |
||
| 938 | ): |
||
| 939 | 1 | primary, secondary = _metaph_add('S', 'TS') |
|
| 940 | else: |
||
| 941 | 1 | primary, secondary = _metaph_add('S') |
|
| 942 | |||
| 943 | 1 | if _get_at(current + 1) == 'Z': |
|
| 944 | 1 | current += 2 |
|
| 945 | else: |
||
| 946 | 1 | current += 1 |
|
| 947 | 1 | continue |
|
| 948 | |||
| 949 | else: |
||
| 950 | 1 | current += 1 |
|
| 951 | |||
| 952 | 1 | if max_length > 0: |
|
| 953 | 1 | primary = primary[:max_length] |
|
| 954 | 1 | secondary = secondary[:max_length] |
|
| 955 | 1 | if primary == secondary: |
|
| 956 | 1 | secondary = '' |
|
| 957 | |||
| 958 | 1 | return primary, secondary |
|
| 959 | |||
| 998 |
Loading history...