Conditions | 218 |
Total Lines | 920 |
Code Lines | 545 |
Lines | 0 |
Ratio | 0 % |
Tests | 397 |
CRAP Score | 218 |
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 | # Copyright 2014-2020 by Christopher C. Little. |
||
90 | def encode(self, word: str) -> str: |
||
91 | """Return the Double Metaphone code for a word. |
||
92 | |||
93 | Parameters |
||
94 | ---------- |
||
95 | word : str |
||
96 | 1 | The word to transform |
|
97 | |||
98 | 1 | Returns |
|
99 | ------- |
||
100 | str |
||
101 | The Double Metaphone value(s) |
||
102 | |||
103 | Examples |
||
104 | -------- |
||
105 | >>> pe = DoubleMetaphone() |
||
106 | >>> pe.encode('Christopher') |
||
107 | 'KRSTFR,' |
||
108 | >>> pe.encode('Niall') |
||
109 | 'NL,' |
||
110 | >>> pe.encode('Smith') |
||
111 | 'SM0,XMT' |
||
112 | >>> pe.encode('Schmidt') |
||
113 | 'XMT,SMT' |
||
114 | |||
115 | |||
116 | .. versionadded:: 0.1.0 |
||
117 | .. versionchanged:: 0.3.6 |
||
118 | Encapsulated in class |
||
119 | .. versionchanged:: 0.6.0 |
||
120 | Made return a str only (comma-separated) |
||
121 | |||
122 | """ |
||
123 | primary = '' |
||
124 | secondary = '' |
||
125 | |||
126 | def _slavo_germanic() -> bool: |
||
127 | """Return True if the word appears to be Slavic or Germanic. |
||
128 | |||
129 | 1 | Returns |
|
130 | 1 | ------- |
|
131 | bool |
||
132 | 1 | True if the word appears to be Slavic or Germanic |
|
133 | |||
134 | .. versionadded:: 0.1.0 |
||
135 | |||
136 | """ |
||
137 | if 'W' in word or 'K' in word or 'CZ' in word: |
||
138 | return True |
||
139 | return False |
||
140 | |||
141 | def _metaph_add(pri: str, sec: str = '') -> Tuple[str, str]: |
||
142 | """Return a new metaphone tuple with the supplied elements. |
||
143 | 1 | ||
144 | 1 | Parameters |
|
145 | 1 | ---------- |
|
146 | pri : str |
||
147 | 1 | The primary element |
|
148 | sec : str |
||
149 | The secondary element |
||
150 | |||
151 | Returns |
||
152 | ------- |
||
153 | tuple |
||
154 | A new metaphone tuple with the supplied elements |
||
155 | |||
156 | .. versionadded:: 0.1.0 |
||
157 | |||
158 | """ |
||
159 | newpri = primary |
||
160 | newsec = secondary |
||
161 | if pri: |
||
162 | newpri += pri |
||
163 | if sec: |
||
164 | if sec != ' ': |
||
165 | 1 | newsec += sec |
|
166 | 1 | else: |
|
167 | 1 | newsec += pri |
|
168 | 1 | return newpri, newsec |
|
169 | 1 | ||
170 | 1 | def _is_vowel(pos: int) -> bool: |
|
171 | 1 | """Return True if the character at word[pos] is a vowel. |
|
172 | |||
173 | 1 | Parameters |
|
174 | 1 | ---------- |
|
175 | pos : int |
||
176 | 1 | Position in the word |
|
177 | |||
178 | Returns |
||
179 | ------- |
||
180 | bool |
||
181 | True if the character is a vowel |
||
182 | |||
183 | .. versionadded:: 0.1.0 |
||
184 | |||
185 | """ |
||
186 | if pos >= 0 and word[pos] in {'A', 'E', 'I', 'O', 'U', 'Y'}: |
||
187 | return True |
||
188 | return False |
||
189 | |||
190 | def _get_at(pos: int) -> str: |
||
191 | """Return the character at word[pos]. |
||
192 | 1 | ||
193 | 1 | Parameters |
|
194 | 1 | ---------- |
|
195 | pos : int |
||
196 | 1 | Position in the word |
|
197 | |||
198 | Returns |
||
199 | ------- |
||
200 | str |
||
201 | Character at word[pos] |
||
202 | |||
203 | .. versionadded:: 0.1.0 |
||
204 | |||
205 | """ |
||
206 | return word[pos] |
||
207 | |||
208 | def _string_at(pos: int, slen: int, substrings: Set[str]) -> bool: |
||
209 | """Return True if word[pos:pos+slen] is in substrings. |
||
210 | |||
211 | Parameters |
||
212 | 1 | ---------- |
|
213 | pos : int |
||
214 | 1 | Position in the word |
|
215 | slen : int |
||
216 | Substring length |
||
217 | substrings : set |
||
218 | Substrings to search |
||
219 | |||
220 | Returns |
||
221 | ------- |
||
222 | bool |
||
223 | True if word[pos:pos+slen] is in substrings |
||
224 | |||
225 | .. versionadded:: 0.1.0 |
||
226 | |||
227 | """ |
||
228 | if pos < 0: |
||
229 | return False |
||
230 | return word[pos : pos + slen] in substrings |
||
231 | |||
232 | current = 0 |
||
233 | length = len(word) |
||
234 | 1 | if length < 1: |
|
235 | 1 | return ',' |
|
236 | 1 | last = length - 1 |
|
237 | |||
238 | 1 | word = word.upper() |
|
239 | 1 | ||
240 | 1 | # Pad the original string so that we can index beyond the edge of the |
|
241 | 1 | # world |
|
242 | 1 | word += ' ' |
|
243 | |||
244 | 1 | # Skip these when at start of word |
|
245 | 1 | if word[0:2] in {'GN', 'KN', 'PN', 'WR', 'PS'}: |
|
246 | current += 1 |
||
247 | |||
248 | # Initial 'X' is pronounced 'Z' e.g. 'Xavier' |
||
249 | 1 | if _get_at(0) == 'X': |
|
250 | primary, secondary = _metaph_add('S') # 'Z' maps to 'S' |
||
251 | current += 1 |
||
252 | 1 | ||
253 | 1 | # Main loop |
|
254 | while True: |
||
255 | if current >= length: |
||
256 | 1 | break |
|
257 | 1 | ||
258 | 1 | if _get_at(current) in {'A', 'E', 'I', 'O', 'U', 'Y'}: |
|
259 | if current == 0: |
||
260 | # All init vowels now map to 'A' |
||
261 | 1 | primary, secondary = _metaph_add('A') |
|
262 | 1 | current += 1 |
|
263 | 1 | continue |
|
264 | |||
265 | 1 | elif _get_at(current) == 'B': |
|
266 | 1 | # "-mb", e.g", "dumb", already skipped over... |
|
267 | primary, secondary = _metaph_add('P') |
||
268 | 1 | if _get_at(current + 1) == 'B': |
|
269 | 1 | current += 2 |
|
270 | 1 | else: |
|
271 | current += 1 |
||
272 | 1 | continue |
|
273 | |||
274 | 1 | elif _get_at(current) == 'Ç': |
|
275 | 1 | primary, secondary = _metaph_add('S') |
|
276 | 1 | current += 1 |
|
277 | continue |
||
278 | 1 | ||
279 | 1 | elif _get_at(current) == 'C': |
|
280 | # Various Germanic |
||
281 | 1 | if ( |
|
282 | 1 | current > 1 |
|
283 | 1 | and not _is_vowel(current - 2) |
|
284 | 1 | and _string_at((current - 1), 3, {'ACH'}) |
|
285 | and ( |
||
286 | 1 | (_get_at(current + 2) != 'I') |
|
287 | and ( |
||
288 | 1 | (_get_at(current + 2) != 'E') |
|
289 | or _string_at( |
||
290 | (current - 2), 6, {'BACHER', 'MACHER'} |
||
291 | ) |
||
292 | ) |
||
293 | ) |
||
294 | ): |
||
295 | primary, secondary = _metaph_add('K') |
||
296 | current += 2 |
||
297 | continue |
||
298 | |||
299 | # Special case 'caesar' |
||
300 | elif current == 0 and _string_at(current, 6, {'CAESAR'}): |
||
301 | primary, secondary = _metaph_add('S') |
||
302 | 1 | current += 2 |
|
303 | 1 | continue |
|
304 | 1 | ||
305 | # Italian 'chianti' |
||
306 | elif _string_at(current, 4, {'CHIA'}): |
||
307 | 1 | primary, secondary = _metaph_add('K') |
|
308 | 1 | current += 2 |
|
309 | 1 | continue |
|
310 | 1 | ||
311 | elif _string_at(current, 2, {'CH'}): |
||
312 | # Find 'Michael' |
||
313 | 1 | if current > 0 and _string_at(current, 4, {'CHAE'}): |
|
314 | 1 | primary, secondary = _metaph_add('K', 'X') |
|
315 | 1 | current += 2 |
|
316 | 1 | continue |
|
317 | |||
318 | 1 | # Greek roots e.g. 'chemistry', 'chorus' |
|
319 | elif ( |
||
320 | 1 | current == 0 |
|
321 | 1 | and ( |
|
322 | 1 | _string_at((current + 1), 5, {'HARAC', 'HARIS'}) |
|
323 | 1 | or _string_at( |
|
324 | (current + 1), 3, {'HOR', 'HYM', 'HIA', 'HEM'} |
||
325 | ) |
||
326 | 1 | ) |
|
327 | and not _string_at(0, 5, {'CHORE'}) |
||
328 | ): |
||
329 | primary, secondary = _metaph_add('K') |
||
330 | current += 2 |
||
331 | continue |
||
332 | |||
333 | # Germanic, Greek, or otherwise 'ch' for 'kh' sound |
||
334 | elif ( |
||
335 | ( |
||
336 | 1 | _string_at(0, 4, {'VAN ', 'VON '}) |
|
337 | 1 | or _string_at(0, 3, {'SCH'}) |
|
338 | 1 | ) |
|
339 | # 'architect but not 'arch', 'orchestra', 'orchid' |
||
340 | or _string_at( |
||
341 | 1 | (current - 2), 6, {'ORCHES', 'ARCHIT', 'ORCHID'} |
|
342 | ) |
||
343 | or _string_at((current + 2), 1, {'T', 'S'}) |
||
344 | or ( |
||
345 | ( |
||
346 | _string_at( |
||
347 | (current - 1), 1, {'A', 'O', 'U', 'E'} |
||
348 | ) |
||
349 | or (current == 0) |
||
350 | ) |
||
351 | # e.g., 'wachtler', 'wechsler', but not 'tichner' |
||
352 | and _string_at( |
||
353 | (current + 2), |
||
354 | 1, |
||
355 | { |
||
356 | 'L', |
||
357 | 'R', |
||
358 | 'N', |
||
359 | 'M', |
||
360 | 'B', |
||
361 | 'H', |
||
362 | 'F', |
||
363 | 'V', |
||
364 | 'W', |
||
365 | ' ', |
||
366 | }, |
||
367 | ) |
||
368 | ) |
||
369 | ): |
||
370 | primary, secondary = _metaph_add('K') |
||
371 | |||
372 | else: |
||
373 | if current > 0: |
||
374 | if _string_at(0, 2, {'MC'}): |
||
375 | # e.g., "McHugh" |
||
376 | primary, secondary = _metaph_add('K') |
||
377 | else: |
||
378 | primary, secondary = _metaph_add('X', 'K') |
||
379 | 1 | else: |
|
380 | primary, secondary = _metaph_add('X') |
||
381 | |||
382 | 1 | current += 2 |
|
383 | 1 | continue |
|
384 | |||
385 | 1 | # e.g, 'czerny' |
|
386 | elif _string_at(current, 2, {'CZ'}) and not _string_at( |
||
387 | 1 | (current - 2), 4, {'WICZ'} |
|
388 | ): |
||
389 | 1 | primary, secondary = _metaph_add('S', 'X') |
|
390 | current += 2 |
||
391 | 1 | continue |
|
392 | 1 | ||
393 | # e.g., 'focaccia' |
||
394 | elif _string_at((current + 1), 3, {'CIA'}): |
||
395 | 1 | primary, secondary = _metaph_add('X') |
|
396 | current += 3 |
||
397 | |||
398 | 1 | # double 'C', but not if e.g. 'McClellan' |
|
399 | 1 | elif _string_at(current, 2, {'CC'}) and not ( |
|
400 | 1 | (current == 1) and (_get_at(0) == 'M') |
|
401 | ): |
||
402 | # 'bellocchio' but not 'bacchus' |
||
403 | 1 | if _string_at( |
|
404 | 1 | (current + 2), 1, {'I', 'E', 'H'} |
|
405 | 1 | ) and not _string_at((current + 2), 2, {'HU'}): |
|
406 | # 'accident', 'accede' 'succeed' |
||
407 | if ( |
||
408 | 1 | (current == 1) and _get_at(current - 1) == 'A' |
|
409 | ) or _string_at((current - 1), 5, {'UCCEE', 'UCCES'}): |
||
410 | primary, secondary = _metaph_add('KS') |
||
411 | # 'bacci', 'bertucci', other italian |
||
412 | 1 | else: |
|
413 | primary, secondary = _metaph_add('X') |
||
414 | current += 3 |
||
415 | continue |
||
416 | 1 | else: # Pierce's rule |
|
417 | primary, secondary = _metaph_add('K') |
||
418 | current += 2 |
||
419 | 1 | continue |
|
420 | |||
421 | elif _string_at(current, 2, {'CK', 'CG', 'CQ'}): |
||
422 | 1 | primary, secondary = _metaph_add('K') |
|
423 | 1 | current += 2 |
|
424 | 1 | continue |
|
425 | |||
426 | 1 | elif _string_at(current, 2, {'CI', 'CE', 'CY'}): |
|
427 | 1 | # Italian vs. English |
|
428 | 1 | if _string_at(current, 3, {'CIO', 'CIE', 'CIA'}): |
|
429 | primary, secondary = _metaph_add('S', 'X') |
||
430 | 1 | else: |
|
431 | 1 | primary, secondary = _metaph_add('S') |
|
432 | 1 | current += 2 |
|
433 | 1 | continue |
|
434 | |||
435 | 1 | # else |
|
436 | else: |
||
437 | 1 | primary, secondary = _metaph_add('K') |
|
438 | 1 | ||
439 | # name sent in 'mac caffrey', 'mac gregor |
||
440 | 1 | if _string_at((current + 1), 2, {' C', ' Q', ' G'}): |
|
441 | 1 | current += 3 |
|
442 | 1 | elif _string_at( |
|
443 | (current + 1), 1, {'C', 'K', 'Q'} |
||
444 | ) and not _string_at((current + 1), 2, {'CE', 'CI'}): |
||
445 | current += 2 |
||
446 | 1 | else: |
|
447 | current += 1 |
||
448 | continue |
||
449 | 1 | ||
450 | 1 | elif _get_at(current) == 'D': |
|
451 | 1 | if _string_at(current, 2, {'DG'}): |
|
452 | if _string_at((current + 2), 1, {'I', 'E', 'Y'}): |
||
453 | # e.g. 'edge' |
||
454 | 1 | primary, secondary = _metaph_add('J') |
|
455 | current += 3 |
||
456 | 1 | continue |
|
457 | 1 | else: |
|
458 | # e.g. 'edgar' |
||
459 | 1 | primary, secondary = _metaph_add('TK') |
|
460 | 1 | current += 2 |
|
461 | 1 | continue |
|
462 | |||
463 | 1 | elif _string_at(current, 2, {'DT', 'DD'}): |
|
464 | 1 | primary, secondary = _metaph_add('T') |
|
465 | 1 | current += 2 |
|
466 | continue |
||
467 | |||
468 | 1 | # else |
|
469 | 1 | else: |
|
470 | 1 | primary, secondary = _metaph_add('T') |
|
471 | current += 1 |
||
472 | 1 | continue |
|
473 | 1 | ||
474 | 1 | elif _get_at(current) == 'F': |
|
475 | 1 | if _get_at(current + 1) == 'F': |
|
476 | current += 2 |
||
477 | else: |
||
478 | current += 1 |
||
479 | 1 | primary, secondary = _metaph_add('F') |
|
480 | 1 | continue |
|
481 | 1 | ||
482 | elif _get_at(current) == 'G': |
||
483 | 1 | if _get_at(current + 1) == 'H': |
|
484 | 1 | if (current > 0) and not _is_vowel(current - 1): |
|
485 | 1 | primary, secondary = _metaph_add('K') |
|
486 | current += 2 |
||
487 | 1 | continue |
|
488 | 1 | ||
489 | 1 | # 'ghislane', ghiradelli |
|
490 | elif current == 0: |
||
491 | 1 | if _get_at(current + 2) == 'I': |
|
492 | 1 | primary, secondary = _metaph_add('J') |
|
493 | 1 | else: |
|
494 | 1 | primary, secondary = _metaph_add('K') |
|
495 | 1 | current += 2 |
|
496 | 1 | continue |
|
497 | |||
498 | # Parker's rule (with some further refinements) - |
||
499 | 1 | # e.g., 'hugh' |
|
500 | 1 | elif ( |
|
501 | 1 | ( |
|
502 | (current > 1) |
||
503 | 1 | and _string_at((current - 2), 1, {'B', 'H', 'D'}) |
|
504 | 1 | ) |
|
505 | 1 | # e.g., 'bough' |
|
506 | or ( |
||
507 | (current > 2) |
||
508 | and _string_at((current - 3), 1, {'B', 'H', 'D'}) |
||
509 | 1 | ) |
|
510 | # e.g., 'broughton' |
||
511 | or ( |
||
512 | (current > 3) |
||
513 | and _string_at((current - 4), 1, {'B', 'H'}) |
||
514 | ) |
||
515 | ): |
||
516 | current += 2 |
||
517 | continue |
||
518 | else: |
||
519 | # e.g. 'laugh', 'McLaughlin', 'cough', |
||
520 | # 'gough', 'rough', 'tough' |
||
521 | if ( |
||
522 | (current > 2) |
||
523 | and (_get_at(current - 1) == 'U') |
||
524 | and ( |
||
525 | _string_at( |
||
526 | (current - 3), 1, {'C', 'G', 'L', 'R', 'T'} |
||
527 | 1 | ) |
|
528 | 1 | ) |
|
529 | ): |
||
530 | primary, secondary = _metaph_add('F') |
||
531 | elif (current > 0) and _get_at(current - 1) != 'I': |
||
532 | 1 | primary, secondary = _metaph_add('K') |
|
533 | current += 2 |
||
534 | continue |
||
535 | |||
536 | elif _get_at(current + 1) == 'N': |
||
537 | if ( |
||
538 | (current == 1) |
||
539 | and _is_vowel(0) |
||
540 | and not _slavo_germanic() |
||
541 | 1 | ): |
|
542 | 1 | primary, secondary = _metaph_add('KN', 'N') |
|
543 | 1 | # not e.g. 'cagney' |
|
544 | 1 | elif ( |
|
545 | 1 | not _string_at((current + 2), 2, {'EY'}) |
|
546 | and (_get_at(current + 1) != 'Y') |
||
547 | 1 | and not _slavo_germanic() |
|
548 | 1 | ): |
|
549 | primary, secondary = _metaph_add('N', 'KN') |
||
550 | else: |
||
551 | primary, secondary = _metaph_add('KN') |
||
552 | current += 2 |
||
553 | 1 | continue |
|
554 | |||
555 | 1 | # 'tagliaro' |
|
556 | elif ( |
||
557 | _string_at((current + 1), 2, {'LI'}) |
||
558 | and not _slavo_germanic() |
||
559 | ): |
||
560 | 1 | primary, secondary = _metaph_add('KL', 'L') |
|
561 | current += 2 |
||
562 | 1 | continue |
|
563 | 1 | ||
564 | 1 | # -ges-, -gep-, -gel-, -gie- at beginning |
|
565 | elif (current == 0) and ( |
||
566 | (_get_at(current + 1) == 'Y') |
||
567 | 1 | or _string_at( |
|
568 | (current + 1), |
||
569 | 2, |
||
570 | { |
||
571 | 1 | 'ES', |
|
572 | 1 | 'EP', |
|
573 | 1 | 'EB', |
|
574 | 'EL', |
||
575 | 'EY', |
||
576 | 1 | 'IB', |
|
577 | 'IL', |
||
578 | 'IN', |
||
579 | 'IE', |
||
580 | 'EI', |
||
581 | 'ER', |
||
582 | }, |
||
583 | ) |
||
584 | ): |
||
585 | primary, secondary = _metaph_add('K', 'J') |
||
586 | current += 2 |
||
587 | continue |
||
588 | |||
589 | # -ger-, -gy- |
||
590 | elif ( |
||
591 | ( |
||
592 | _string_at((current + 1), 2, {'ER'}) |
||
593 | or (_get_at(current + 1) == 'Y') |
||
594 | ) |
||
595 | and not _string_at(0, 6, {'DANGER', 'RANGER', 'MANGER'}) |
||
596 | 1 | and not _string_at((current - 1), 1, {'E', 'I'}) |
|
597 | 1 | and not _string_at((current - 1), 3, {'RGY', 'OGY'}) |
|
598 | 1 | ): |
|
599 | primary, secondary = _metaph_add('K', 'J') |
||
600 | current += 2 |
||
601 | 1 | continue |
|
602 | |||
603 | # italian e.g, 'biaggi' |
||
604 | elif _string_at( |
||
605 | (current + 1), 1, {'E', 'I', 'Y'} |
||
606 | ) or _string_at((current - 1), 4, {'AGGI', 'OGGI'}): |
||
607 | # obvious germanic |
||
608 | if ( |
||
609 | _string_at(0, 4, {'VAN ', 'VON '}) |
||
610 | 1 | or _string_at(0, 3, {'SCH'}) |
|
611 | 1 | ) or _string_at((current + 1), 2, {'ET'}): |
|
612 | 1 | primary, secondary = _metaph_add('K') |
|
613 | elif _string_at((current + 1), 4, {'IER '}): |
||
614 | primary, secondary = _metaph_add('J') |
||
615 | 1 | else: |
|
616 | primary, secondary = _metaph_add('J', 'K') |
||
617 | current += 2 |
||
618 | continue |
||
619 | 1 | ||
620 | else: |
||
621 | if _get_at(current + 1) == 'G': |
||
622 | current += 2 |
||
623 | 1 | else: |
|
624 | 1 | current += 1 |
|
625 | 1 | primary, secondary = _metaph_add('K') |
|
626 | continue |
||
627 | 1 | ||
628 | 1 | elif _get_at(current) == 'H': |
|
629 | 1 | # only keep if first & before vowel or btw. 2 vowels |
|
630 | if ((current == 0) or _is_vowel(current - 1)) and _is_vowel( |
||
631 | current + 1 |
||
632 | 1 | ): |
|
633 | 1 | primary, secondary = _metaph_add('H') |
|
634 | current += 2 |
||
635 | 1 | else: # also takes care of 'HH' |
|
636 | 1 | current += 1 |
|
637 | 1 | continue |
|
638 | |||
639 | 1 | elif _get_at(current) == 'J': |
|
640 | # obvious spanish, 'jose', 'san jacinto' |
||
641 | 1 | if _string_at(current, 4, {'JOSE'}) or _string_at( |
|
642 | 0, 4, {'SAN '} |
||
643 | ): |
||
644 | 1 | if ( |
|
645 | 1 | (current == 0) and (_get_at(current + 4) == ' ') |
|
646 | ) or _string_at(0, 4, {'SAN '}): |
||
647 | 1 | primary, secondary = _metaph_add('H') |
|
648 | 1 | else: |
|
649 | primary, secondary = _metaph_add('J', 'H') |
||
650 | 1 | current += 1 |
|
651 | continue |
||
652 | 1 | ||
653 | elif (current == 0) and not _string_at(current, 4, {'JOSE'}): |
||
654 | # Yankelovich/Jankelowicz |
||
655 | 1 | primary, secondary = _metaph_add('J', 'A') |
|
656 | # Spanish pron. of e.g. 'bajador' |
||
657 | elif ( |
||
658 | 1 | _is_vowel(current - 1) |
|
659 | and not _slavo_germanic() |
||
660 | 1 | and ( |
|
661 | 1 | (_get_at(current + 1) == 'A') |
|
662 | 1 | or (_get_at(current + 1) == 'O') |
|
663 | ) |
||
664 | 1 | ): |
|
665 | primary, secondary = _metaph_add('J', 'H') |
||
666 | 1 | elif current == last: |
|
667 | primary, secondary = _metaph_add('J', ' ') |
||
668 | 1 | elif not _string_at( |
|
669 | (current + 1), 1, {'L', 'T', 'K', 'S', 'N', 'M', 'B', 'Z'} |
||
670 | ) and not _string_at((current - 1), 1, {'S', 'K', 'L'}): |
||
671 | primary, secondary = _metaph_add('J') |
||
672 | |||
673 | if _get_at(current + 1) == 'J': # it could happen! |
||
674 | current += 2 |
||
675 | else: |
||
676 | 1 | current += 1 |
|
677 | 1 | continue |
|
678 | 1 | ||
679 | 1 | elif _get_at(current) == 'K': |
|
680 | if _get_at(current + 1) == 'K': |
||
681 | current += 2 |
||
682 | 1 | else: |
|
683 | current += 1 |
||
684 | 1 | primary, secondary = _metaph_add('K') |
|
685 | 1 | continue |
|
686 | |||
687 | 1 | elif _get_at(current) == 'L': |
|
688 | 1 | if _get_at(current + 1) == 'L': |
|
689 | # Spanish e.g. 'cabrillo', 'gallegos' |
||
690 | 1 | if ( |
|
691 | 1 | (current == (length - 3)) |
|
692 | 1 | and _string_at( |
|
693 | (current - 1), 4, {'ILLO', 'ILLA', 'ALLE'} |
||
694 | 1 | ) |
|
695 | 1 | ) or ( |
|
696 | 1 | ( |
|
697 | _string_at((last - 1), 2, {'AS', 'OS'}) |
||
698 | 1 | or _string_at(last, 1, {'A', 'O'}) |
|
699 | 1 | ) |
|
700 | and _string_at((current - 1), 4, {'ALLE'}) |
||
701 | 1 | ): |
|
702 | primary, secondary = _metaph_add('L', ' ') |
||
703 | current += 2 |
||
704 | continue |
||
705 | current += 2 |
||
706 | else: |
||
707 | current += 1 |
||
708 | primary, secondary = _metaph_add('L') |
||
709 | continue |
||
710 | |||
711 | elif _get_at(current) == 'M': |
||
712 | if ( |
||
713 | 1 | ( |
|
714 | 1 | _string_at((current - 1), 3, {'UMB'}) |
|
715 | 1 | and ( |
|
716 | 1 | ((current + 1) == last) |
|
717 | or _string_at((current + 2), 2, {'ER'}) |
||
718 | 1 | ) |
|
719 | 1 | ) |
|
720 | 1 | # 'dumb', 'thumb' |
|
721 | or (_get_at(current + 1) == 'M') |
||
722 | 1 | ): |
|
723 | 1 | current += 2 |
|
724 | else: |
||
725 | current += 1 |
||
726 | primary, secondary = _metaph_add('M') |
||
727 | continue |
||
728 | |||
729 | elif _get_at(current) == 'N': |
||
730 | if _get_at(current + 1) == 'N': |
||
731 | current += 2 |
||
732 | else: |
||
733 | current += 1 |
||
734 | primary, secondary = _metaph_add('N') |
||
735 | 1 | continue |
|
736 | |||
737 | 1 | elif _get_at(current) == 'Ñ': |
|
738 | 1 | current += 1 |
|
739 | 1 | primary, secondary = _metaph_add('N') |
|
740 | continue |
||
741 | 1 | ||
742 | 1 | elif _get_at(current) == 'P': |
|
743 | 1 | if _get_at(current + 1) == 'H': |
|
744 | primary, secondary = _metaph_add('F') |
||
745 | 1 | current += 2 |
|
746 | 1 | continue |
|
747 | 1 | ||
748 | # also account for "campbell", "raspberry" |
||
749 | 1 | elif _string_at((current + 1), 1, {'P', 'B'}): |
|
750 | 1 | current += 2 |
|
751 | 1 | else: |
|
752 | 1 | current += 1 |
|
753 | primary, secondary = _metaph_add('P') |
||
754 | 1 | continue |
|
755 | 1 | ||
756 | 1 | elif _get_at(current) == 'Q': |
|
757 | 1 | if _get_at(current + 1) == 'Q': |
|
758 | 1 | current += 2 |
|
759 | else: |
||
760 | current += 1 |
||
761 | 1 | primary, secondary = _metaph_add('K') |
|
762 | 1 | continue |
|
763 | |||
764 | 1 | elif _get_at(current) == 'R': |
|
765 | 1 | # french e.g. 'rogier', but exclude 'hochmeier' |
|
766 | 1 | if ( |
|
767 | (current == last) |
||
768 | 1 | and not _slavo_germanic() |
|
769 | 1 | and _string_at((current - 2), 2, {'IE'}) |
|
770 | 1 | and not _string_at((current - 4), 2, {'ME', 'MA'}) |
|
771 | ): |
||
772 | 1 | primary, secondary = _metaph_add('', 'R') |
|
773 | 1 | else: |
|
774 | 1 | primary, secondary = _metaph_add('R') |
|
775 | |||
776 | 1 | if _get_at(current + 1) == 'R': |
|
777 | current += 2 |
||
778 | 1 | else: |
|
779 | current += 1 |
||
780 | continue |
||
781 | |||
782 | elif _get_at(current) == 'S': |
||
783 | # special cases 'island', 'isle', 'carlisle', 'carlysle' |
||
784 | 1 | if _string_at((current - 1), 3, {'ISL', 'YSL'}): |
|
785 | current += 1 |
||
786 | 1 | continue |
|
787 | |||
788 | 1 | # special case 'sugar-' |
|
789 | 1 | elif (current == 0) and _string_at(current, 5, {'SUGAR'}): |
|
790 | primary, secondary = _metaph_add('X', 'S') |
||
791 | 1 | current += 1 |
|
792 | 1 | continue |
|
793 | |||
794 | 1 | elif _string_at(current, 2, {'SH'}): |
|
795 | # Germanic |
||
796 | 1 | if _string_at( |
|
797 | 1 | (current + 1), 4, {'HEIM', 'HOEK', 'HOLM', 'HOLZ'} |
|
798 | 1 | ): |
|
799 | primary, secondary = _metaph_add('S') |
||
800 | else: |
||
801 | 1 | primary, secondary = _metaph_add('X') |
|
802 | 1 | current += 2 |
|
803 | 1 | continue |
|
804 | 1 | ||
805 | # Italian & Armenian |
||
806 | 1 | elif _string_at(current, 3, {'SIO', 'SIA'}) or _string_at( |
|
807 | current, 4, {'SIAN'} |
||
808 | 1 | ): |
|
809 | if not _slavo_germanic(): |
||
810 | primary, secondary = _metaph_add('S', 'X') |
||
811 | 1 | else: |
|
812 | primary, secondary = _metaph_add('S') |
||
813 | 1 | current += 3 |
|
814 | 1 | continue |
|
815 | 1 | ||
816 | # German & anglicisations, e.g. 'smith' match 'schmidt', |
||
817 | # 'snider' match 'schneider' |
||
818 | 1 | # also, -sz- in Slavic language although in Hungarian it is |
|
819 | # pronounced 's' |
||
820 | elif ( |
||
821 | 1 | (current == 0) |
|
822 | 1 | and _string_at((current + 1), 1, {'M', 'N', 'L', 'W'}) |
|
823 | ) or _string_at((current + 1), 1, {'Z'}): |
||
824 | 1 | primary, secondary = _metaph_add('S', 'X') |
|
825 | 1 | if _string_at((current + 1), 1, {'Z'}): |
|
826 | 1 | current += 2 |
|
827 | else: |
||
828 | current += 1 |
||
829 | continue |
||
830 | |||
831 | elif _string_at(current, 2, {'SC'}): |
||
832 | 1 | # Schlesinger's rule |
|
833 | if _get_at(current + 2) == 'H': |
||
834 | # dutch origin, e.g. 'school', 'schooner' |
||
835 | if _string_at( |
||
836 | 1 | (current + 3), |
|
837 | 1 | 2, |
|
838 | 1 | {'OO', 'ER', 'EN', 'UY', 'ED', 'EM'}, |
|
839 | ): |
||
840 | 1 | # 'schermerhorn', 'schenker' |
|
841 | 1 | if _string_at((current + 3), 2, {'ER', 'EN'}): |
|
842 | primary, secondary = _metaph_add('X', 'SK') |
||
843 | 1 | else: |
|
844 | primary, secondary = _metaph_add('SK') |
||
845 | 1 | current += 3 |
|
846 | continue |
||
847 | 1 | else: |
|
848 | if ( |
||
849 | (current == 0) |
||
850 | and not _is_vowel(3) |
||
851 | and (_get_at(3) != 'W') |
||
852 | ): |
||
853 | 1 | primary, secondary = _metaph_add('X', 'S') |
|
854 | 1 | else: |
|
855 | primary, secondary = _metaph_add('X') |
||
856 | 1 | current += 3 |
|
857 | 1 | continue |
|
858 | 1 | ||
859 | elif _string_at((current + 2), 1, {'I', 'E', 'Y'}): |
||
860 | 1 | primary, secondary = _metaph_add('S') |
|
861 | current += 3 |
||
862 | continue |
||
863 | |||
864 | # else |
||
865 | 1 | else: |
|
866 | primary, secondary = _metaph_add('SK') |
||
867 | 1 | current += 3 |
|
868 | 1 | continue |
|
869 | 1 | ||
870 | else: |
||
871 | 1 | # french e.g. 'resnais', 'artois' |
|
872 | 1 | if (current == last) and _string_at( |
|
873 | 1 | (current - 2), 2, {'AI', 'OI'} |
|
874 | 1 | ): |
|
875 | primary, secondary = _metaph_add('', 'S') |
||
876 | else: |
||
877 | primary, secondary = _metaph_add('S') |
||
878 | 1 | ||
879 | 1 | if _string_at((current + 1), 1, {'S', 'Z'}): |
|
880 | 1 | current += 2 |
|
881 | else: |
||
882 | current += 1 |
||
883 | continue |
||
884 | 1 | ||
885 | elif _get_at(current) == 'T': |
||
886 | if _string_at(current, 4, {'TION'}): |
||
887 | 1 | primary, secondary = _metaph_add('X') |
|
888 | current += 3 |
||
889 | 1 | continue |
|
890 | |||
891 | 1 | elif _string_at(current, 3, {'TIA', 'TCH'}): |
|
892 | 1 | primary, secondary = _metaph_add('X') |
|
893 | current += 3 |
||
894 | 1 | continue |
|
895 | 1 | ||
896 | elif _string_at(current, 2, {'TH'}) or _string_at( |
||
897 | 1 | current, 3, {'TTH'} |
|
898 | 1 | ): |
|
899 | 1 | # special case 'thomas', 'thames' or germanic |
|
900 | 1 | if ( |
|
901 | 1 | _string_at((current + 2), 2, {'OM', 'AM'}) |
|
902 | or _string_at(0, 4, {'VAN ', 'VON '}) |
||
903 | 1 | or _string_at(0, 3, {'SCH'}) |
|
904 | 1 | ): |
|
905 | 1 | primary, secondary = _metaph_add('T') |
|
906 | 1 | else: |
|
907 | primary, secondary = _metaph_add('0', 'T') |
||
908 | 1 | current += 2 |
|
909 | continue |
||
910 | |||
911 | elif _string_at((current + 1), 1, {'T', 'D'}): |
||
912 | 1 | current += 2 |
|
913 | else: |
||
914 | current += 1 |
||
915 | primary, secondary = _metaph_add('T') |
||
916 | continue |
||
917 | 1 | ||
918 | elif _get_at(current) == 'V': |
||
919 | 1 | if _get_at(current + 1) == 'V': |
|
920 | 1 | current += 2 |
|
921 | 1 | else: |
|
922 | current += 1 |
||
923 | 1 | primary, secondary = _metaph_add('F') |
|
924 | 1 | continue |
|
925 | |||
926 | 1 | elif _get_at(current) == 'W': |
|
927 | 1 | # can also be in middle of word |
|
928 | 1 | if _string_at(current, 2, {'WR'}): |
|
929 | primary, secondary = _metaph_add('R') |
||
930 | 1 | current += 2 |
|
931 | 1 | continue |
|
932 | 1 | elif (current == 0) and ( |
|
933 | _is_vowel(current + 1) or _string_at(current, 2, {'WH'}) |
||
934 | 1 | ): |
|
935 | 1 | # Wasserman should match Vasserman |
|
936 | 1 | if _is_vowel(current + 1): |
|
937 | primary, secondary = _metaph_add('A', 'F') |
||
938 | 1 | else: |
|
939 | # need Uomo to match Womo |
||
940 | 1 | primary, secondary = _metaph_add('A') |
|
941 | 1 | ||
942 | 1 | # Arnow should match Arnoff |
|
943 | 1 | if ( |
|
944 | 1 | ((current == last) and _is_vowel(current - 1)) |
|
945 | or _string_at( |
||
946 | (current - 1), 5, {'EWSKI', 'EWSKY', 'OWSKI', 'OWSKY'} |
||
947 | ) |
||
948 | 1 | or _string_at(0, 3, {'SCH'}) |
|
949 | 1 | ): |
|
950 | primary, secondary = _metaph_add('', 'F') |
||
951 | current += 1 |
||
952 | 1 | continue |
|
953 | # Polish e.g. 'filipowicz' |
||
954 | elif _string_at(current, 4, {'WICZ', 'WITZ'}): |
||
955 | 1 | primary, secondary = _metaph_add('TS', 'FX') |
|
956 | current += 4 |
||
957 | continue |
||
958 | # else skip it |
||
959 | else: |
||
960 | current += 1 |
||
961 | continue |
||
962 | 1 | ||
963 | 1 | elif _get_at(current) == 'X': |
|
964 | 1 | # French e.g. breaux |
|
965 | if not ( |
||
966 | 1 | (current == last) |
|
967 | 1 | and ( |
|
968 | 1 | _string_at((current - 3), 3, {'IAU', 'EAU'}) |
|
969 | 1 | or _string_at((current - 2), 2, {'AU', 'OU'}) |
|
970 | ) |
||
971 | ): |
||
972 | 1 | primary, secondary = _metaph_add('KS') |
|
973 | 1 | ||
974 | if _string_at((current + 1), 1, {'C', 'X'}): |
||
975 | 1 | current += 2 |
|
976 | else: |
||
977 | 1 | current += 1 |
|
978 | continue |
||
979 | |||
980 | elif _get_at(current) == 'Z': |
||
981 | # Chinese Pinyin e.g. 'zhao' |
||
982 | if _get_at(current + 1) == 'H': |
||
983 | primary, secondary = _metaph_add('J') |
||
984 | 1 | current += 2 |
|
985 | continue |
||
986 | 1 | elif _string_at((current + 1), 2, {'ZO', 'ZI', 'ZA'}) or ( |
|
987 | 1 | _slavo_germanic() |
|
988 | and ((current > 0) and _get_at(current - 1) != 'T') |
||
989 | 1 | ): |
|
990 | 1 | primary, secondary = _metaph_add('S', 'TS') |
|
991 | else: |
||
992 | 1 | primary, secondary = _metaph_add('S') |
|
993 | |||
994 | 1 | if _get_at(current + 1) == 'Z': |
|
995 | 1 | current += 2 |
|
996 | 1 | else: |
|
997 | 1 | current += 1 |
|
998 | 1 | continue |
|
999 | |||
1000 | else: |
||
1001 | current += 1 |
||
1002 | 1 | ||
1003 | if self._max_length > 0: |
||
1004 | 1 | primary = primary[: self._max_length] |
|
1005 | secondary = secondary[: self._max_length] |
||
1006 | 1 | if primary == secondary: |
|
1007 | 1 | secondary = '' |
|
1008 | |||
1009 | 1 | return ','.join((primary, secondary)) |
|
1010 | 1 | ||
1016 |