Conditions | 219 |
Total Lines | 892 |
Code Lines | 549 |
Lines | 0 |
Ratio | 0 % |
Tests | 407 |
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._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 -*- |
||
282 | 1 | def encode(self, word, max_length=-1): |
|
283 | """Return the Double Metaphone code for a word. |
||
284 | |||
285 | Args: |
||
286 | word (str): The word to transform |
||
287 | max_length (int): The maximum length of the returned Double |
||
288 | Metaphone codes (defaults to 64, but in Philips' original |
||
289 | implementation this was 4) |
||
290 | |||
291 | Returns: |
||
292 | tuple: The Double Metaphone value(s) |
||
293 | |||
294 | Examples: |
||
295 | >>> pe = DoubleMetaphone() |
||
296 | >>> pe.encode('Christopher') |
||
297 | ('KRSTFR', '') |
||
298 | >>> pe.encode('Niall') |
||
299 | ('NL', '') |
||
300 | >>> pe.encode('Smith') |
||
301 | ('SM0', 'XMT') |
||
302 | >>> pe.encode('Schmidt') |
||
303 | ('XMT', 'SMT') |
||
304 | |||
305 | """ |
||
306 | # Require a max_length of at least 4 |
||
307 | 1 | if max_length != -1: |
|
308 | 1 | max_length = max(4, max_length) |
|
309 | else: |
||
310 | 1 | max_length = 64 |
|
311 | |||
312 | 1 | primary = '' |
|
313 | 1 | secondary = '' |
|
314 | |||
315 | 1 | def _slavo_germanic(): |
|
316 | """Return True if the word appears to be Slavic or Germanic. |
||
317 | |||
318 | Returns: |
||
319 | bool: True if the word appears to be Slavic or Germanic |
||
320 | |||
321 | """ |
||
322 | 1 | if 'W' in word or 'K' in word or 'CZ' in word: |
|
323 | 1 | return True |
|
324 | 1 | return False |
|
325 | |||
326 | 1 | def _metaph_add(pri, sec=''): |
|
327 | """Return a new metaphone tuple with the supplied elements. |
||
328 | |||
329 | Args: |
||
330 | pri (str): The primary element |
||
331 | sec (str): The secondary element |
||
332 | |||
333 | Returns: |
||
334 | tuple: A new metaphone tuple with the supplied elements |
||
335 | |||
336 | """ |
||
337 | 1 | newpri = primary |
|
338 | 1 | newsec = secondary |
|
339 | 1 | if pri: |
|
340 | 1 | newpri += pri |
|
341 | 1 | if sec: |
|
342 | 1 | if sec != ' ': |
|
343 | 1 | newsec += sec |
|
344 | else: |
||
345 | 1 | newsec += pri |
|
346 | 1 | return newpri, newsec |
|
347 | |||
348 | 1 | def _is_vowel(pos): |
|
349 | """Return True if the character at word[pos] is a vowel. |
||
350 | |||
351 | Args: |
||
352 | pos (int): Position in the word |
||
353 | |||
354 | Returns: |
||
355 | bool: True if the character is a vowel |
||
356 | |||
357 | """ |
||
358 | 1 | if pos >= 0 and word[pos] in {'A', 'E', 'I', 'O', 'U', 'Y'}: |
|
359 | 1 | return True |
|
360 | 1 | return False |
|
361 | |||
362 | 1 | def _get_at(pos): |
|
363 | """Return the character at word[pos]. |
||
364 | |||
365 | Args: |
||
366 | pos (int): Position in the word |
||
367 | |||
368 | Returns: |
||
369 | str: Character at word[pos] |
||
370 | |||
371 | """ |
||
372 | 1 | return word[pos] |
|
373 | |||
374 | 1 | def _string_at(pos, slen, substrings): |
|
375 | """Return True if word[pos:pos+slen] is in substrings. |
||
376 | |||
377 | Args: |
||
378 | pos (int): Position in the word |
||
379 | slen (int): Substring length |
||
380 | substrings (set): Substrings to search |
||
381 | |||
382 | Returns: |
||
383 | bool: True if word[pos:pos+slen] is in substrings |
||
384 | |||
385 | """ |
||
386 | 1 | if pos < 0: |
|
387 | 1 | return False |
|
388 | 1 | return word[pos : pos + slen] in substrings |
|
389 | |||
390 | 1 | current = 0 |
|
391 | 1 | length = len(word) |
|
392 | 1 | if length < 1: |
|
393 | 1 | return '', '' |
|
394 | 1 | last = length - 1 |
|
395 | |||
396 | 1 | word = word.upper() |
|
397 | 1 | word = word.replace('ß', 'SS') |
|
398 | |||
399 | # Pad the original string so that we can index beyond the edge of the |
||
400 | # world |
||
401 | 1 | word += ' ' |
|
402 | |||
403 | # Skip these when at start of word |
||
404 | 1 | if word[0:2] in {'GN', 'KN', 'PN', 'WR', 'PS'}: |
|
405 | 1 | current += 1 |
|
406 | |||
407 | # Initial 'X' is pronounced 'Z' e.g. 'Xavier' |
||
408 | 1 | if _get_at(0) == 'X': |
|
409 | 1 | primary, secondary = _metaph_add('S') # 'Z' maps to 'S' |
|
410 | 1 | current += 1 |
|
411 | |||
412 | # Main loop |
||
413 | 1 | while True: |
|
414 | 1 | if current >= length: |
|
415 | 1 | break |
|
416 | |||
417 | 1 | if _get_at(current) in {'A', 'E', 'I', 'O', 'U', 'Y'}: |
|
418 | 1 | if current == 0: |
|
419 | # All init vowels now map to 'A' |
||
420 | 1 | primary, secondary = _metaph_add('A') |
|
421 | 1 | current += 1 |
|
422 | 1 | continue |
|
423 | |||
424 | 1 | elif _get_at(current) == 'B': |
|
425 | # "-mb", e.g", "dumb", already skipped over... |
||
426 | 1 | primary, secondary = _metaph_add('P') |
|
427 | 1 | if _get_at(current + 1) == 'B': |
|
428 | 1 | current += 2 |
|
429 | else: |
||
430 | 1 | current += 1 |
|
431 | 1 | continue |
|
432 | |||
433 | 1 | elif _get_at(current) == 'Ç': |
|
434 | 1 | primary, secondary = _metaph_add('S') |
|
435 | 1 | current += 1 |
|
436 | 1 | continue |
|
437 | |||
438 | 1 | elif _get_at(current) == 'C': |
|
439 | # Various Germanic |
||
440 | 1 | if ( |
|
441 | current > 1 |
||
442 | and not _is_vowel(current - 2) |
||
443 | and _string_at((current - 1), 3, {'ACH'}) |
||
444 | and ( |
||
445 | (_get_at(current + 2) != 'I') |
||
446 | and ( |
||
447 | (_get_at(current + 2) != 'E') |
||
448 | or _string_at( |
||
449 | (current - 2), 6, {'BACHER', 'MACHER'} |
||
450 | ) |
||
451 | ) |
||
452 | ) |
||
453 | ): |
||
454 | 1 | primary, secondary = _metaph_add('K') |
|
455 | 1 | current += 2 |
|
456 | 1 | continue |
|
457 | |||
458 | # Special case 'caesar' |
||
459 | 1 | elif current == 0 and _string_at(current, 6, {'CAESAR'}): |
|
460 | 1 | primary, secondary = _metaph_add('S') |
|
461 | 1 | current += 2 |
|
462 | 1 | continue |
|
463 | |||
464 | # Italian 'chianti' |
||
465 | 1 | elif _string_at(current, 4, {'CHIA'}): |
|
466 | 1 | primary, secondary = _metaph_add('K') |
|
467 | 1 | current += 2 |
|
468 | 1 | continue |
|
469 | |||
470 | 1 | elif _string_at(current, 2, {'CH'}): |
|
471 | # Find 'Michael' |
||
472 | 1 | if current > 0 and _string_at(current, 4, {'CHAE'}): |
|
473 | 1 | primary, secondary = _metaph_add('K', 'X') |
|
474 | 1 | current += 2 |
|
475 | 1 | continue |
|
476 | |||
477 | # Greek roots e.g. 'chemistry', 'chorus' |
||
478 | 1 | elif ( |
|
479 | current == 0 |
||
480 | and ( |
||
481 | _string_at((current + 1), 5, {'HARAC', 'HARIS'}) |
||
482 | or _string_at( |
||
483 | (current + 1), 3, {'HOR', 'HYM', 'HIA', 'HEM'} |
||
484 | ) |
||
485 | ) |
||
486 | and not _string_at(0, 5, {'CHORE'}) |
||
487 | ): |
||
488 | 1 | primary, secondary = _metaph_add('K') |
|
489 | 1 | current += 2 |
|
490 | 1 | continue |
|
491 | |||
492 | # Germanic, Greek, or otherwise 'ch' for 'kh' sound |
||
493 | 1 | elif ( |
|
494 | ( |
||
495 | _string_at(0, 4, {'VAN ', 'VON '}) |
||
496 | or _string_at(0, 3, {'SCH'}) |
||
497 | ) |
||
498 | or |
||
499 | # 'architect but not 'arch', 'orchestra', 'orchid' |
||
500 | _string_at( |
||
501 | (current - 2), 6, {'ORCHES', 'ARCHIT', 'ORCHID'} |
||
502 | ) |
||
503 | or _string_at((current + 2), 1, {'T', 'S'}) |
||
504 | or ( |
||
505 | ( |
||
506 | _string_at( |
||
507 | (current - 1), 1, {'A', 'O', 'U', 'E'} |
||
508 | ) |
||
509 | or (current == 0) |
||
510 | ) |
||
511 | and |
||
512 | # e.g., 'wachtler', 'wechsler', but not 'tichner' |
||
513 | _string_at( |
||
514 | (current + 2), |
||
515 | 1, |
||
516 | { |
||
517 | 'L', |
||
518 | 'R', |
||
519 | 'N', |
||
520 | 'M', |
||
521 | 'B', |
||
522 | 'H', |
||
523 | 'F', |
||
524 | 'V', |
||
525 | 'W', |
||
526 | ' ', |
||
527 | }, |
||
528 | ) |
||
529 | ) |
||
530 | ): |
||
531 | 1 | primary, secondary = _metaph_add('K') |
|
532 | |||
533 | else: |
||
534 | 1 | if current > 0: |
|
535 | 1 | if _string_at(0, 2, {'MC'}): |
|
536 | # e.g., "McHugh" |
||
537 | 1 | primary, secondary = _metaph_add('K') |
|
538 | else: |
||
539 | 1 | primary, secondary = _metaph_add('X', 'K') |
|
540 | else: |
||
541 | 1 | primary, secondary = _metaph_add('X') |
|
542 | |||
543 | 1 | current += 2 |
|
544 | 1 | continue |
|
545 | |||
546 | # e.g, 'czerny' |
||
547 | 1 | elif _string_at(current, 2, {'CZ'}) and not _string_at( |
|
548 | (current - 2), 4, {'WICZ'} |
||
549 | ): |
||
550 | 1 | primary, secondary = _metaph_add('S', 'X') |
|
551 | 1 | current += 2 |
|
552 | 1 | continue |
|
553 | |||
554 | # e.g., 'focaccia' |
||
555 | 1 | elif _string_at((current + 1), 3, {'CIA'}): |
|
556 | 1 | primary, secondary = _metaph_add('X') |
|
557 | 1 | current += 3 |
|
558 | |||
559 | # double 'C', but not if e.g. 'McClellan' |
||
560 | 1 | elif _string_at(current, 2, {'CC'}) and not ( |
|
561 | (current == 1) and (_get_at(0) == 'M') |
||
562 | ): |
||
563 | # 'bellocchio' but not 'bacchus' |
||
564 | 1 | if _string_at( |
|
565 | (current + 2), 1, {'I', 'E', 'H'} |
||
566 | ) and not _string_at((current + 2), 2, ['HU']): |
||
567 | # 'accident', 'accede' 'succeed' |
||
568 | 1 | if ( |
|
569 | (current == 1) and _get_at(current - 1) == 'A' |
||
570 | ) or _string_at((current - 1), 5, {'UCCEE', 'UCCES'}): |
||
571 | 1 | primary, secondary = _metaph_add('KS') |
|
572 | # 'bacci', 'bertucci', other italian |
||
573 | else: |
||
574 | 1 | primary, secondary = _metaph_add('X') |
|
575 | 1 | current += 3 |
|
576 | 1 | continue |
|
577 | else: # Pierce's rule |
||
578 | 1 | primary, secondary = _metaph_add('K') |
|
579 | 1 | current += 2 |
|
580 | 1 | continue |
|
581 | |||
582 | 1 | elif _string_at(current, 2, {'CK', 'CG', 'CQ'}): |
|
583 | 1 | primary, secondary = _metaph_add('K') |
|
584 | 1 | current += 2 |
|
585 | 1 | continue |
|
586 | |||
587 | 1 | elif _string_at(current, 2, {'CI', 'CE', 'CY'}): |
|
588 | # Italian vs. English |
||
589 | 1 | if _string_at(current, 3, {'CIO', 'CIE', 'CIA'}): |
|
590 | 1 | primary, secondary = _metaph_add('S', 'X') |
|
591 | else: |
||
592 | 1 | primary, secondary = _metaph_add('S') |
|
593 | 1 | current += 2 |
|
594 | 1 | continue |
|
595 | |||
596 | # else |
||
597 | else: |
||
598 | 1 | primary, secondary = _metaph_add('K') |
|
599 | |||
600 | # name sent in 'mac caffrey', 'mac gregor |
||
601 | 1 | if _string_at((current + 1), 2, {' C', ' Q', ' G'}): |
|
602 | 1 | current += 3 |
|
603 | 1 | elif _string_at( |
|
604 | (current + 1), 1, {'C', 'K', 'Q'} |
||
605 | ) and not _string_at((current + 1), 2, {'CE', 'CI'}): |
||
606 | 1 | current += 2 |
|
607 | else: |
||
608 | 1 | current += 1 |
|
609 | 1 | continue |
|
610 | |||
611 | 1 | elif _get_at(current) == 'D': |
|
612 | 1 | if _string_at(current, 2, {'DG'}): |
|
613 | 1 | if _string_at((current + 2), 1, {'I', 'E', 'Y'}): |
|
614 | # e.g. 'edge' |
||
615 | 1 | primary, secondary = _metaph_add('J') |
|
616 | 1 | current += 3 |
|
617 | 1 | continue |
|
618 | else: |
||
619 | # e.g. 'edgar' |
||
620 | 1 | primary, secondary = _metaph_add('TK') |
|
621 | 1 | current += 2 |
|
622 | 1 | continue |
|
623 | |||
624 | 1 | elif _string_at(current, 2, {'DT', 'DD'}): |
|
625 | 1 | primary, secondary = _metaph_add('T') |
|
626 | 1 | current += 2 |
|
627 | 1 | continue |
|
628 | |||
629 | # else |
||
630 | else: |
||
631 | 1 | primary, secondary = _metaph_add('T') |
|
632 | 1 | current += 1 |
|
633 | 1 | continue |
|
634 | |||
635 | 1 | elif _get_at(current) == 'F': |
|
636 | 1 | if _get_at(current + 1) == 'F': |
|
637 | 1 | current += 2 |
|
638 | else: |
||
639 | 1 | current += 1 |
|
640 | 1 | primary, secondary = _metaph_add('F') |
|
641 | 1 | continue |
|
642 | |||
643 | 1 | elif _get_at(current) == 'G': |
|
644 | 1 | if _get_at(current + 1) == 'H': |
|
645 | 1 | if (current > 0) and not _is_vowel(current - 1): |
|
646 | 1 | primary, secondary = _metaph_add('K') |
|
647 | 1 | current += 2 |
|
648 | 1 | continue |
|
649 | |||
650 | # 'ghislane', ghiradelli |
||
651 | 1 | elif current == 0: |
|
652 | 1 | if _get_at(current + 2) == 'I': |
|
653 | 1 | primary, secondary = _metaph_add('J') |
|
654 | else: |
||
655 | 1 | primary, secondary = _metaph_add('K') |
|
656 | 1 | current += 2 |
|
657 | 1 | continue |
|
658 | |||
659 | # Parker's rule (with some further refinements) - |
||
660 | # e.g., 'hugh' |
||
661 | 1 | elif ( |
|
662 | ( |
||
663 | (current > 1) |
||
664 | and _string_at((current - 2), 1, {'B', 'H', 'D'}) |
||
665 | ) |
||
666 | or |
||
667 | # e.g., 'bough' |
||
668 | ( |
||
669 | (current > 2) |
||
670 | and _string_at((current - 3), 1, {'B', 'H', 'D'}) |
||
671 | ) |
||
672 | or |
||
673 | # e.g., 'broughton' |
||
674 | ( |
||
675 | (current > 3) |
||
676 | and _string_at((current - 4), 1, {'B', 'H'}) |
||
677 | ) |
||
678 | ): |
||
679 | 1 | current += 2 |
|
680 | 1 | continue |
|
681 | else: |
||
682 | # e.g. 'laugh', 'McLaughlin', 'cough', |
||
683 | # 'gough', 'rough', 'tough' |
||
684 | 1 | if ( |
|
685 | (current > 2) |
||
686 | and (_get_at(current - 1) == 'U') |
||
687 | and ( |
||
688 | _string_at( |
||
689 | (current - 3), 1, {'C', 'G', 'L', 'R', 'T'} |
||
690 | ) |
||
691 | ) |
||
692 | ): |
||
693 | 1 | primary, secondary = _metaph_add('F') |
|
694 | 1 | elif (current > 0) and _get_at(current - 1) != 'I': |
|
695 | 1 | primary, secondary = _metaph_add('K') |
|
696 | 1 | current += 2 |
|
697 | 1 | continue |
|
698 | |||
699 | 1 | elif _get_at(current + 1) == 'N': |
|
700 | 1 | if ( |
|
701 | (current == 1) |
||
702 | and _is_vowel(0) |
||
703 | and not _slavo_germanic() |
||
704 | ): |
||
705 | 1 | primary, secondary = _metaph_add('KN', 'N') |
|
706 | # not e.g. 'cagney' |
||
707 | 1 | elif ( |
|
708 | not _string_at((current + 2), 2, {'EY'}) |
||
709 | and (_get_at(current + 1) != 'Y') |
||
710 | and not _slavo_germanic() |
||
711 | ): |
||
712 | 1 | primary, secondary = _metaph_add('N', 'KN') |
|
713 | else: |
||
714 | 1 | primary, secondary = _metaph_add('KN') |
|
715 | 1 | current += 2 |
|
716 | 1 | continue |
|
717 | |||
718 | # 'tagliaro' |
||
719 | 1 | elif ( |
|
720 | _string_at((current + 1), 2, {'LI'}) |
||
721 | and not _slavo_germanic() |
||
722 | ): |
||
723 | 1 | primary, secondary = _metaph_add('KL', 'L') |
|
724 | 1 | current += 2 |
|
725 | 1 | continue |
|
726 | |||
727 | # -ges-, -gep-, -gel-, -gie- at beginning |
||
728 | 1 | elif (current == 0) and ( |
|
729 | (_get_at(current + 1) == 'Y') |
||
730 | or _string_at( |
||
731 | (current + 1), |
||
732 | 2, |
||
733 | { |
||
734 | 'ES', |
||
735 | 'EP', |
||
736 | 'EB', |
||
737 | 'EL', |
||
738 | 'EY', |
||
739 | 'IB', |
||
740 | 'IL', |
||
741 | 'IN', |
||
742 | 'IE', |
||
743 | 'EI', |
||
744 | 'ER', |
||
745 | }, |
||
746 | ) |
||
747 | ): |
||
748 | 1 | primary, secondary = _metaph_add('K', 'J') |
|
749 | 1 | current += 2 |
|
750 | 1 | continue |
|
751 | |||
752 | # -ger-, -gy- |
||
753 | 1 | elif ( |
|
754 | ( |
||
755 | _string_at((current + 1), 2, {'ER'}) |
||
756 | or (_get_at(current + 1) == 'Y') |
||
757 | ) |
||
758 | and not _string_at(0, 6, {'DANGER', 'RANGER', 'MANGER'}) |
||
759 | and not _string_at((current - 1), 1, {'E', 'I'}) |
||
760 | and not _string_at((current - 1), 3, {'RGY', 'OGY'}) |
||
761 | ): |
||
762 | 1 | primary, secondary = _metaph_add('K', 'J') |
|
763 | 1 | current += 2 |
|
764 | 1 | continue |
|
765 | |||
766 | # italian e.g, 'biaggi' |
||
767 | 1 | elif _string_at( |
|
768 | (current + 1), 1, {'E', 'I', 'Y'} |
||
769 | ) or _string_at((current - 1), 4, {'AGGI', 'OGGI'}): |
||
770 | # obvious germanic |
||
771 | 1 | if ( |
|
772 | _string_at(0, 4, {'VAN ', 'VON '}) |
||
773 | or _string_at(0, 3, {'SCH'}) |
||
774 | ) or _string_at((current + 1), 2, {'ET'}): |
||
775 | 1 | primary, secondary = _metaph_add('K') |
|
776 | 1 | elif _string_at((current + 1), 4, {'IER '}): |
|
777 | 1 | primary, secondary = _metaph_add('J') |
|
778 | else: |
||
779 | 1 | primary, secondary = _metaph_add('J', 'K') |
|
780 | 1 | current += 2 |
|
781 | 1 | continue |
|
782 | |||
783 | else: |
||
784 | 1 | if _get_at(current + 1) == 'G': |
|
785 | 1 | current += 2 |
|
786 | else: |
||
787 | 1 | current += 1 |
|
788 | 1 | primary, secondary = _metaph_add('K') |
|
789 | 1 | continue |
|
790 | |||
791 | 1 | elif _get_at(current) == 'H': |
|
792 | # only keep if first & before vowel or btw. 2 vowels |
||
793 | 1 | if ((current == 0) or _is_vowel(current - 1)) and _is_vowel( |
|
794 | current + 1 |
||
795 | ): |
||
796 | 1 | primary, secondary = _metaph_add('H') |
|
797 | 1 | current += 2 |
|
798 | else: # also takes care of 'HH' |
||
799 | 1 | current += 1 |
|
800 | 1 | continue |
|
801 | |||
802 | 1 | elif _get_at(current) == 'J': |
|
803 | # obvious spanish, 'jose', 'san jacinto' |
||
804 | 1 | if _string_at(current, 4, ['JOSE']) or _string_at( |
|
805 | 0, 4, {'SAN '} |
||
806 | ): |
||
807 | 1 | if ( |
|
808 | (current == 0) and (_get_at(current + 4) == ' ') |
||
809 | ) or _string_at(0, 4, ['SAN ']): |
||
810 | 1 | primary, secondary = _metaph_add('H') |
|
811 | else: |
||
812 | 1 | primary, secondary = _metaph_add('J', 'H') |
|
813 | 1 | current += 1 |
|
814 | 1 | continue |
|
815 | |||
816 | 1 | elif (current == 0) and not _string_at(current, 4, {'JOSE'}): |
|
817 | # Yankelovich/Jankelowicz |
||
818 | 1 | primary, secondary = _metaph_add('J', 'A') |
|
819 | # Spanish pron. of e.g. 'bajador' |
||
820 | 1 | elif ( |
|
821 | _is_vowel(current - 1) |
||
822 | and not _slavo_germanic() |
||
823 | and ( |
||
824 | (_get_at(current + 1) == 'A') |
||
825 | or (_get_at(current + 1) == 'O') |
||
826 | ) |
||
827 | ): |
||
828 | 1 | primary, secondary = _metaph_add('J', 'H') |
|
829 | 1 | elif current == last: |
|
830 | 1 | primary, secondary = _metaph_add('J', ' ') |
|
831 | 1 | elif not _string_at( |
|
832 | (current + 1), 1, {'L', 'T', 'K', 'S', 'N', 'M', 'B', 'Z'} |
||
833 | ) and not _string_at((current - 1), 1, {'S', 'K', 'L'}): |
||
834 | 1 | primary, secondary = _metaph_add('J') |
|
835 | |||
836 | 1 | if _get_at(current + 1) == 'J': # it could happen! |
|
837 | 1 | current += 2 |
|
838 | else: |
||
839 | 1 | current += 1 |
|
840 | 1 | continue |
|
841 | |||
842 | 1 | elif _get_at(current) == 'K': |
|
843 | 1 | if _get_at(current + 1) == 'K': |
|
844 | 1 | current += 2 |
|
845 | else: |
||
846 | 1 | current += 1 |
|
847 | 1 | primary, secondary = _metaph_add('K') |
|
848 | 1 | continue |
|
849 | |||
850 | 1 | elif _get_at(current) == 'L': |
|
851 | 1 | if _get_at(current + 1) == 'L': |
|
852 | # Spanish e.g. 'cabrillo', 'gallegos' |
||
853 | 1 | if ( |
|
854 | (current == (length - 3)) |
||
855 | and _string_at( |
||
856 | (current - 1), 4, {'ILLO', 'ILLA', 'ALLE'} |
||
857 | ) |
||
858 | ) or ( |
||
859 | ( |
||
860 | _string_at((last - 1), 2, {'AS', 'OS'}) |
||
861 | or _string_at(last, 1, {'A', 'O'}) |
||
862 | ) |
||
863 | and _string_at((current - 1), 4, {'ALLE'}) |
||
864 | ): |
||
865 | 1 | primary, secondary = _metaph_add('L', ' ') |
|
866 | 1 | current += 2 |
|
867 | 1 | continue |
|
868 | 1 | current += 2 |
|
869 | else: |
||
870 | 1 | current += 1 |
|
871 | 1 | primary, secondary = _metaph_add('L') |
|
872 | 1 | continue |
|
873 | |||
874 | 1 | elif _get_at(current) == 'M': |
|
875 | 1 | if ( |
|
876 | ( |
||
877 | _string_at((current - 1), 3, {'UMB'}) |
||
878 | and ( |
||
879 | ((current + 1) == last) |
||
880 | or _string_at((current + 2), 2, {'ER'}) |
||
881 | ) |
||
882 | ) |
||
883 | or |
||
884 | # 'dumb', 'thumb' |
||
885 | (_get_at(current + 1) == 'M') |
||
886 | ): |
||
887 | 1 | current += 2 |
|
888 | else: |
||
889 | 1 | current += 1 |
|
890 | 1 | primary, secondary = _metaph_add('M') |
|
891 | 1 | continue |
|
892 | |||
893 | 1 | elif _get_at(current) == 'N': |
|
894 | 1 | if _get_at(current + 1) == 'N': |
|
895 | 1 | current += 2 |
|
896 | else: |
||
897 | 1 | current += 1 |
|
898 | 1 | primary, secondary = _metaph_add('N') |
|
899 | 1 | continue |
|
900 | |||
901 | 1 | elif _get_at(current) == 'Ñ': |
|
902 | 1 | current += 1 |
|
903 | 1 | primary, secondary = _metaph_add('N') |
|
904 | 1 | continue |
|
905 | |||
906 | 1 | elif _get_at(current) == 'P': |
|
907 | 1 | if _get_at(current + 1) == 'H': |
|
908 | 1 | primary, secondary = _metaph_add('F') |
|
909 | 1 | current += 2 |
|
910 | 1 | continue |
|
911 | |||
912 | # also account for "campbell", "raspberry" |
||
913 | 1 | elif _string_at((current + 1), 1, {'P', 'B'}): |
|
914 | 1 | current += 2 |
|
915 | else: |
||
916 | 1 | current += 1 |
|
917 | 1 | primary, secondary = _metaph_add('P') |
|
918 | 1 | continue |
|
919 | |||
920 | 1 | elif _get_at(current) == 'Q': |
|
921 | 1 | if _get_at(current + 1) == 'Q': |
|
922 | 1 | current += 2 |
|
923 | else: |
||
924 | 1 | current += 1 |
|
925 | 1 | primary, secondary = _metaph_add('K') |
|
926 | 1 | continue |
|
927 | |||
928 | 1 | elif _get_at(current) == 'R': |
|
929 | # french e.g. 'rogier', but exclude 'hochmeier' |
||
930 | 1 | if ( |
|
931 | (current == last) |
||
932 | and not _slavo_germanic() |
||
933 | and _string_at((current - 2), 2, {'IE'}) |
||
934 | and not _string_at((current - 4), 2, {'ME', 'MA'}) |
||
935 | ): |
||
936 | 1 | primary, secondary = _metaph_add('', 'R') |
|
937 | else: |
||
938 | 1 | primary, secondary = _metaph_add('R') |
|
939 | |||
940 | 1 | if _get_at(current + 1) == 'R': |
|
941 | 1 | current += 2 |
|
942 | else: |
||
943 | 1 | current += 1 |
|
944 | 1 | continue |
|
945 | |||
946 | 1 | elif _get_at(current) == 'S': |
|
947 | # special cases 'island', 'isle', 'carlisle', 'carlysle' |
||
948 | 1 | if _string_at((current - 1), 3, {'ISL', 'YSL'}): |
|
949 | 1 | current += 1 |
|
950 | 1 | continue |
|
951 | |||
952 | # special case 'sugar-' |
||
953 | 1 | elif (current == 0) and _string_at(current, 5, {'SUGAR'}): |
|
954 | 1 | primary, secondary = _metaph_add('X', 'S') |
|
955 | 1 | current += 1 |
|
956 | 1 | continue |
|
957 | |||
958 | 1 | elif _string_at(current, 2, {'SH'}): |
|
959 | # Germanic |
||
960 | 1 | if _string_at( |
|
961 | (current + 1), 4, {'HEIM', 'HOEK', 'HOLM', 'HOLZ'} |
||
962 | ): |
||
963 | 1 | primary, secondary = _metaph_add('S') |
|
964 | else: |
||
965 | 1 | primary, secondary = _metaph_add('X') |
|
966 | 1 | current += 2 |
|
967 | 1 | continue |
|
968 | |||
969 | # Italian & Armenian |
||
970 | 1 | elif _string_at(current, 3, {'SIO', 'SIA'}) or _string_at( |
|
971 | current, 4, {'SIAN'} |
||
972 | ): |
||
973 | 1 | if not _slavo_germanic(): |
|
974 | 1 | primary, secondary = _metaph_add('S', 'X') |
|
975 | else: |
||
976 | 1 | primary, secondary = _metaph_add('S') |
|
977 | 1 | current += 3 |
|
978 | 1 | continue |
|
979 | |||
980 | # German & anglicisations, e.g. 'smith' match 'schmidt', |
||
981 | # 'snider' match 'schneider' |
||
982 | # also, -sz- in Slavic language although in Hungarian it is |
||
983 | # pronounced 's' |
||
984 | 1 | elif ( |
|
985 | (current == 0) |
||
986 | and _string_at((current + 1), 1, {'M', 'N', 'L', 'W'}) |
||
987 | ) or _string_at((current + 1), 1, {'Z'}): |
||
988 | 1 | primary, secondary = _metaph_add('S', 'X') |
|
989 | 1 | if _string_at((current + 1), 1, {'Z'}): |
|
990 | 1 | current += 2 |
|
991 | else: |
||
992 | 1 | current += 1 |
|
993 | 1 | continue |
|
994 | |||
995 | 1 | elif _string_at(current, 2, {'SC'}): |
|
996 | # Schlesinger's rule |
||
997 | 1 | if _get_at(current + 2) == 'H': |
|
998 | # dutch origin, e.g. 'school', 'schooner' |
||
999 | 1 | if _string_at( |
|
1000 | (current + 3), |
||
1001 | 2, |
||
1002 | {'OO', 'ER', 'EN', 'UY', 'ED', 'EM'}, |
||
1003 | ): |
||
1004 | # 'schermerhorn', 'schenker' |
||
1005 | 1 | if _string_at((current + 3), 2, {'ER', 'EN'}): |
|
1006 | 1 | primary, secondary = _metaph_add('X', 'SK') |
|
1007 | else: |
||
1008 | 1 | primary, secondary = _metaph_add('SK') |
|
1009 | 1 | current += 3 |
|
1010 | 1 | continue |
|
1011 | else: |
||
1012 | 1 | if ( |
|
1013 | (current == 0) |
||
1014 | and not _is_vowel(3) |
||
1015 | and (_get_at(3) != 'W') |
||
1016 | ): |
||
1017 | 1 | primary, secondary = _metaph_add('X', 'S') |
|
1018 | else: |
||
1019 | 1 | primary, secondary = _metaph_add('X') |
|
1020 | 1 | current += 3 |
|
1021 | 1 | continue |
|
1022 | |||
1023 | 1 | elif _string_at((current + 2), 1, {'I', 'E', 'Y'}): |
|
1024 | 1 | primary, secondary = _metaph_add('S') |
|
1025 | 1 | current += 3 |
|
1026 | 1 | continue |
|
1027 | |||
1028 | # else |
||
1029 | else: |
||
1030 | 1 | primary, secondary = _metaph_add('SK') |
|
1031 | 1 | current += 3 |
|
1032 | 1 | continue |
|
1033 | |||
1034 | else: |
||
1035 | # french e.g. 'resnais', 'artois' |
||
1036 | 1 | if (current == last) and _string_at( |
|
1037 | (current - 2), 2, {'AI', 'OI'} |
||
1038 | ): |
||
1039 | 1 | primary, secondary = _metaph_add('', 'S') |
|
1040 | else: |
||
1041 | 1 | primary, secondary = _metaph_add('S') |
|
1042 | |||
1043 | 1 | if _string_at((current + 1), 1, {'S', 'Z'}): |
|
1044 | 1 | current += 2 |
|
1045 | else: |
||
1046 | 1 | current += 1 |
|
1047 | 1 | continue |
|
1048 | |||
1049 | 1 | elif _get_at(current) == 'T': |
|
1050 | 1 | if _string_at(current, 4, {'TION'}): |
|
1051 | 1 | primary, secondary = _metaph_add('X') |
|
1052 | 1 | current += 3 |
|
1053 | 1 | continue |
|
1054 | |||
1055 | 1 | elif _string_at(current, 3, {'TIA', 'TCH'}): |
|
1056 | 1 | primary, secondary = _metaph_add('X') |
|
1057 | 1 | current += 3 |
|
1058 | 1 | continue |
|
1059 | |||
1060 | 1 | elif _string_at(current, 2, {'TH'}) or _string_at( |
|
1061 | current, 3, {'TTH'} |
||
1062 | ): |
||
1063 | # special case 'thomas', 'thames' or germanic |
||
1064 | 1 | if ( |
|
1065 | _string_at((current + 2), 2, {'OM', 'AM'}) |
||
1066 | or _string_at(0, 4, {'VAN ', 'VON '}) |
||
1067 | or _string_at(0, 3, {'SCH'}) |
||
1068 | ): |
||
1069 | 1 | primary, secondary = _metaph_add('T') |
|
1070 | else: |
||
1071 | 1 | primary, secondary = _metaph_add('0', 'T') |
|
1072 | 1 | current += 2 |
|
1073 | 1 | continue |
|
1074 | |||
1075 | 1 | elif _string_at((current + 1), 1, {'T', 'D'}): |
|
1076 | 1 | current += 2 |
|
1077 | else: |
||
1078 | 1 | current += 1 |
|
1079 | 1 | primary, secondary = _metaph_add('T') |
|
1080 | 1 | continue |
|
1081 | |||
1082 | 1 | elif _get_at(current) == 'V': |
|
1083 | 1 | if _get_at(current + 1) == 'V': |
|
1084 | 1 | current += 2 |
|
1085 | else: |
||
1086 | 1 | current += 1 |
|
1087 | 1 | primary, secondary = _metaph_add('F') |
|
1088 | 1 | continue |
|
1089 | |||
1090 | 1 | elif _get_at(current) == 'W': |
|
1091 | # can also be in middle of word |
||
1092 | 1 | if _string_at(current, 2, {'WR'}): |
|
1093 | 1 | primary, secondary = _metaph_add('R') |
|
1094 | 1 | current += 2 |
|
1095 | 1 | continue |
|
1096 | 1 | elif (current == 0) and ( |
|
1097 | _is_vowel(current + 1) or _string_at(current, 2, {'WH'}) |
||
1098 | ): |
||
1099 | # Wasserman should match Vasserman |
||
1100 | 1 | if _is_vowel(current + 1): |
|
1101 | 1 | primary, secondary = _metaph_add('A', 'F') |
|
1102 | else: |
||
1103 | # need Uomo to match Womo |
||
1104 | 1 | primary, secondary = _metaph_add('A') |
|
1105 | |||
1106 | # Arnow should match Arnoff |
||
1107 | 1 | if ( |
|
1108 | ((current == last) and _is_vowel(current - 1)) |
||
1109 | or _string_at( |
||
1110 | (current - 1), 5, {'EWSKI', 'EWSKY', 'OWSKI', 'OWSKY'} |
||
1111 | ) |
||
1112 | or _string_at(0, 3, ['SCH']) |
||
1113 | ): |
||
1114 | 1 | primary, secondary = _metaph_add('', 'F') |
|
1115 | 1 | current += 1 |
|
1116 | 1 | continue |
|
1117 | # Polish e.g. 'filipowicz' |
||
1118 | 1 | elif _string_at(current, 4, {'WICZ', 'WITZ'}): |
|
1119 | 1 | primary, secondary = _metaph_add('TS', 'FX') |
|
1120 | 1 | current += 4 |
|
1121 | 1 | continue |
|
1122 | # else skip it |
||
1123 | else: |
||
1124 | 1 | current += 1 |
|
1125 | 1 | continue |
|
1126 | |||
1127 | 1 | elif _get_at(current) == 'X': |
|
1128 | # French e.g. breaux |
||
1129 | 1 | if not ( |
|
1130 | (current == last) |
||
1131 | and ( |
||
1132 | _string_at((current - 3), 3, {'IAU', 'EAU'}) |
||
1133 | or _string_at((current - 2), 2, {'AU', 'OU'}) |
||
1134 | ) |
||
1135 | ): |
||
1136 | 1 | primary, secondary = _metaph_add('KS') |
|
1137 | |||
1138 | 1 | if _string_at((current + 1), 1, {'C', 'X'}): |
|
1139 | 1 | current += 2 |
|
1140 | else: |
||
1141 | 1 | current += 1 |
|
1142 | 1 | continue |
|
1143 | |||
1144 | 1 | elif _get_at(current) == 'Z': |
|
1145 | # Chinese Pinyin e.g. 'zhao' |
||
1146 | 1 | if _get_at(current + 1) == 'H': |
|
1147 | 1 | primary, secondary = _metaph_add('J') |
|
1148 | 1 | current += 2 |
|
1149 | 1 | continue |
|
1150 | 1 | elif _string_at((current + 1), 2, {'ZO', 'ZI', 'ZA'}) or ( |
|
1151 | _slavo_germanic() |
||
1152 | and ((current > 0) and _get_at(current - 1) != 'T') |
||
1153 | ): |
||
1154 | 1 | primary, secondary = _metaph_add('S', 'TS') |
|
1155 | else: |
||
1156 | 1 | primary, secondary = _metaph_add('S') |
|
1157 | |||
1158 | 1 | if _get_at(current + 1) == 'Z': |
|
1159 | 1 | current += 2 |
|
1160 | else: |
||
1161 | 1 | current += 1 |
|
1162 | 1 | continue |
|
1163 | |||
1164 | else: |
||
1165 | 1 | current += 1 |
|
1166 | |||
1167 | 1 | if max_length > 0: |
|
1168 | 1 | primary = primary[:max_length] |
|
1169 | 1 | secondary = secondary[:max_length] |
|
1170 | 1 | if primary == secondary: |
|
1171 | 1 | secondary = '' |
|
1172 | |||
1173 | 1 | return primary, secondary |
|
1174 | |||
1209 |