Conditions | 219 |
Total Lines | 918 |
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._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 64, 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 | else: |
||
76 | 1 | max_length = 64 |
|
77 | |||
78 | 1 | primary = '' |
|
79 | 1 | secondary = '' |
|
80 | |||
81 | 1 | def _slavo_germanic(): |
|
82 | """Return True if the word appears to be Slavic or Germanic. |
||
83 | |||
84 | Returns |
||
85 | ------- |
||
86 | bool |
||
87 | True if the word appears to be Slavic or Germanic |
||
88 | |||
89 | """ |
||
90 | 1 | if 'W' in word or 'K' in word or 'CZ' in word: |
|
91 | 1 | return True |
|
92 | 1 | return False |
|
93 | |||
94 | 1 | def _metaph_add(pri, sec=''): |
|
95 | """Return a new metaphone tuple with the supplied elements. |
||
96 | |||
97 | Parameters |
||
98 | ---------- |
||
99 | pri : str |
||
100 | The primary element |
||
101 | sec : str |
||
102 | The secondary element |
||
103 | |||
104 | Returns |
||
105 | ------- |
||
106 | tuple |
||
107 | A new metaphone tuple with the supplied elements |
||
108 | |||
109 | """ |
||
110 | 1 | newpri = primary |
|
111 | 1 | newsec = secondary |
|
112 | 1 | if pri: |
|
113 | 1 | newpri += pri |
|
114 | 1 | if sec: |
|
115 | 1 | if sec != ' ': |
|
116 | 1 | newsec += sec |
|
117 | else: |
||
118 | 1 | newsec += pri |
|
119 | 1 | return newpri, newsec |
|
120 | |||
121 | 1 | def _is_vowel(pos): |
|
122 | """Return True if the character at word[pos] is a vowel. |
||
123 | |||
124 | Parameters |
||
125 | ---------- |
||
126 | pos : int |
||
127 | Position in the word |
||
128 | |||
129 | Returns |
||
130 | ------- |
||
131 | bool |
||
132 | True if the character is a vowel |
||
133 | |||
134 | """ |
||
135 | 1 | if pos >= 0 and word[pos] in {'A', 'E', 'I', 'O', 'U', 'Y'}: |
|
136 | 1 | return True |
|
137 | 1 | return False |
|
138 | |||
139 | 1 | def _get_at(pos): |
|
140 | """Return the character at word[pos]. |
||
141 | |||
142 | Parameters |
||
143 | ---------- |
||
144 | pos : int |
||
145 | Position in the word |
||
146 | |||
147 | Returns |
||
148 | ------- |
||
149 | str |
||
150 | Character at word[pos] |
||
151 | |||
152 | """ |
||
153 | 1 | return word[pos] |
|
154 | |||
155 | 1 | def _string_at(pos, slen, substrings): |
|
156 | """Return True if word[pos:pos+slen] is in substrings. |
||
157 | |||
158 | Parameters |
||
159 | ---------- |
||
160 | pos : int |
||
161 | Position in the word |
||
162 | slen : int |
||
163 | Substring length |
||
164 | substrings : set |
||
165 | Substrings to search |
||
166 | |||
167 | Returns |
||
168 | ------- |
||
169 | bool |
||
170 | True if word[pos:pos+slen] is in substrings |
||
171 | |||
172 | """ |
||
173 | 1 | if pos < 0: |
|
174 | 1 | return False |
|
175 | 1 | return word[pos : pos + slen] in substrings |
|
176 | |||
177 | 1 | current = 0 |
|
178 | 1 | length = len(word) |
|
179 | 1 | if length < 1: |
|
180 | 1 | return '', '' |
|
181 | 1 | last = length - 1 |
|
182 | |||
183 | 1 | word = word.upper() |
|
184 | 1 | word = word.replace('ß', 'SS') |
|
185 | |||
186 | # Pad the original string so that we can index beyond the edge of the |
||
187 | # world |
||
188 | 1 | word += ' ' |
|
189 | |||
190 | # Skip these when at start of word |
||
191 | 1 | if word[0:2] in {'GN', 'KN', 'PN', 'WR', 'PS'}: |
|
192 | 1 | current += 1 |
|
193 | |||
194 | # Initial 'X' is pronounced 'Z' e.g. 'Xavier' |
||
195 | 1 | if _get_at(0) == 'X': |
|
196 | 1 | primary, secondary = _metaph_add('S') # 'Z' maps to 'S' |
|
197 | 1 | current += 1 |
|
198 | |||
199 | # Main loop |
||
200 | 1 | while True: |
|
201 | 1 | if current >= length: |
|
202 | 1 | break |
|
203 | |||
204 | 1 | if _get_at(current) in {'A', 'E', 'I', 'O', 'U', 'Y'}: |
|
205 | 1 | if current == 0: |
|
206 | # All init vowels now map to 'A' |
||
207 | 1 | primary, secondary = _metaph_add('A') |
|
208 | 1 | current += 1 |
|
209 | 1 | continue |
|
210 | |||
211 | 1 | elif _get_at(current) == 'B': |
|
212 | # "-mb", e.g", "dumb", already skipped over... |
||
213 | 1 | primary, secondary = _metaph_add('P') |
|
214 | 1 | if _get_at(current + 1) == 'B': |
|
215 | 1 | current += 2 |
|
216 | else: |
||
217 | 1 | current += 1 |
|
218 | 1 | continue |
|
219 | |||
220 | 1 | elif _get_at(current) == 'Ç': |
|
221 | 1 | primary, secondary = _metaph_add('S') |
|
222 | 1 | current += 1 |
|
223 | 1 | continue |
|
224 | |||
225 | 1 | elif _get_at(current) == 'C': |
|
226 | # Various Germanic |
||
227 | 1 | if ( |
|
228 | current > 1 |
||
229 | and not _is_vowel(current - 2) |
||
230 | and _string_at((current - 1), 3, {'ACH'}) |
||
231 | and ( |
||
232 | (_get_at(current + 2) != 'I') |
||
233 | and ( |
||
234 | (_get_at(current + 2) != 'E') |
||
235 | or _string_at( |
||
236 | (current - 2), 6, {'BACHER', 'MACHER'} |
||
237 | ) |
||
238 | ) |
||
239 | ) |
||
240 | ): |
||
241 | 1 | primary, secondary = _metaph_add('K') |
|
242 | 1 | current += 2 |
|
243 | 1 | continue |
|
244 | |||
245 | # Special case 'caesar' |
||
246 | 1 | elif current == 0 and _string_at(current, 6, {'CAESAR'}): |
|
247 | 1 | primary, secondary = _metaph_add('S') |
|
248 | 1 | current += 2 |
|
249 | 1 | continue |
|
250 | |||
251 | # Italian 'chianti' |
||
252 | 1 | elif _string_at(current, 4, {'CHIA'}): |
|
253 | 1 | primary, secondary = _metaph_add('K') |
|
254 | 1 | current += 2 |
|
255 | 1 | continue |
|
256 | |||
257 | 1 | elif _string_at(current, 2, {'CH'}): |
|
258 | # Find 'Michael' |
||
259 | 1 | if current > 0 and _string_at(current, 4, {'CHAE'}): |
|
260 | 1 | primary, secondary = _metaph_add('K', 'X') |
|
261 | 1 | current += 2 |
|
262 | 1 | continue |
|
263 | |||
264 | # Greek roots e.g. 'chemistry', 'chorus' |
||
265 | 1 | elif ( |
|
266 | current == 0 |
||
267 | and ( |
||
268 | _string_at((current + 1), 5, {'HARAC', 'HARIS'}) |
||
269 | or _string_at( |
||
270 | (current + 1), 3, {'HOR', 'HYM', 'HIA', 'HEM'} |
||
271 | ) |
||
272 | ) |
||
273 | and not _string_at(0, 5, {'CHORE'}) |
||
274 | ): |
||
275 | 1 | primary, secondary = _metaph_add('K') |
|
276 | 1 | current += 2 |
|
277 | 1 | continue |
|
278 | |||
279 | # Germanic, Greek, or otherwise 'ch' for 'kh' sound |
||
280 | 1 | elif ( |
|
281 | ( |
||
282 | _string_at(0, 4, {'VAN ', 'VON '}) |
||
283 | or _string_at(0, 3, {'SCH'}) |
||
284 | ) |
||
285 | or |
||
286 | # 'architect but not 'arch', 'orchestra', 'orchid' |
||
287 | _string_at( |
||
288 | (current - 2), 6, {'ORCHES', 'ARCHIT', 'ORCHID'} |
||
289 | ) |
||
290 | or _string_at((current + 2), 1, {'T', 'S'}) |
||
291 | or ( |
||
292 | ( |
||
293 | _string_at( |
||
294 | (current - 1), 1, {'A', 'O', 'U', 'E'} |
||
295 | ) |
||
296 | or (current == 0) |
||
297 | ) |
||
298 | and |
||
299 | # e.g., 'wachtler', 'wechsler', but not 'tichner' |
||
300 | _string_at( |
||
301 | (current + 2), |
||
302 | 1, |
||
303 | { |
||
304 | 'L', |
||
305 | 'R', |
||
306 | 'N', |
||
307 | 'M', |
||
308 | 'B', |
||
309 | 'H', |
||
310 | 'F', |
||
311 | 'V', |
||
312 | 'W', |
||
313 | ' ', |
||
314 | }, |
||
315 | ) |
||
316 | ) |
||
317 | ): |
||
318 | 1 | primary, secondary = _metaph_add('K') |
|
319 | |||
320 | else: |
||
321 | 1 | if current > 0: |
|
322 | 1 | if _string_at(0, 2, {'MC'}): |
|
323 | # e.g., "McHugh" |
||
324 | 1 | primary, secondary = _metaph_add('K') |
|
325 | else: |
||
326 | 1 | primary, secondary = _metaph_add('X', 'K') |
|
327 | else: |
||
328 | 1 | primary, secondary = _metaph_add('X') |
|
329 | |||
330 | 1 | current += 2 |
|
331 | 1 | continue |
|
332 | |||
333 | # e.g, 'czerny' |
||
334 | 1 | elif _string_at(current, 2, {'CZ'}) and not _string_at( |
|
335 | (current - 2), 4, {'WICZ'} |
||
336 | ): |
||
337 | 1 | primary, secondary = _metaph_add('S', 'X') |
|
338 | 1 | current += 2 |
|
339 | 1 | continue |
|
340 | |||
341 | # e.g., 'focaccia' |
||
342 | 1 | elif _string_at((current + 1), 3, {'CIA'}): |
|
343 | 1 | primary, secondary = _metaph_add('X') |
|
344 | 1 | current += 3 |
|
345 | |||
346 | # double 'C', but not if e.g. 'McClellan' |
||
347 | 1 | elif _string_at(current, 2, {'CC'}) and not ( |
|
348 | (current == 1) and (_get_at(0) == 'M') |
||
349 | ): |
||
350 | # 'bellocchio' but not 'bacchus' |
||
351 | 1 | if _string_at( |
|
352 | (current + 2), 1, {'I', 'E', 'H'} |
||
353 | ) and not _string_at((current + 2), 2, {'HU'}): |
||
354 | # 'accident', 'accede' 'succeed' |
||
355 | 1 | if ( |
|
356 | (current == 1) and _get_at(current - 1) == 'A' |
||
357 | ) or _string_at((current - 1), 5, {'UCCEE', 'UCCES'}): |
||
358 | 1 | primary, secondary = _metaph_add('KS') |
|
359 | # 'bacci', 'bertucci', other italian |
||
360 | else: |
||
361 | 1 | primary, secondary = _metaph_add('X') |
|
362 | 1 | current += 3 |
|
363 | 1 | continue |
|
364 | else: # Pierce's rule |
||
365 | 1 | primary, secondary = _metaph_add('K') |
|
366 | 1 | current += 2 |
|
367 | 1 | continue |
|
368 | |||
369 | 1 | elif _string_at(current, 2, {'CK', 'CG', 'CQ'}): |
|
370 | 1 | primary, secondary = _metaph_add('K') |
|
371 | 1 | current += 2 |
|
372 | 1 | continue |
|
373 | |||
374 | 1 | elif _string_at(current, 2, {'CI', 'CE', 'CY'}): |
|
375 | # Italian vs. English |
||
376 | 1 | if _string_at(current, 3, {'CIO', 'CIE', 'CIA'}): |
|
377 | 1 | primary, secondary = _metaph_add('S', 'X') |
|
378 | else: |
||
379 | 1 | primary, secondary = _metaph_add('S') |
|
380 | 1 | current += 2 |
|
381 | 1 | continue |
|
382 | |||
383 | # else |
||
384 | else: |
||
385 | 1 | primary, secondary = _metaph_add('K') |
|
386 | |||
387 | # name sent in 'mac caffrey', 'mac gregor |
||
388 | 1 | if _string_at((current + 1), 2, {' C', ' Q', ' G'}): |
|
389 | 1 | current += 3 |
|
390 | 1 | elif _string_at( |
|
391 | (current + 1), 1, {'C', 'K', 'Q'} |
||
392 | ) and not _string_at((current + 1), 2, {'CE', 'CI'}): |
||
393 | 1 | current += 2 |
|
394 | else: |
||
395 | 1 | current += 1 |
|
396 | 1 | continue |
|
397 | |||
398 | 1 | elif _get_at(current) == 'D': |
|
399 | 1 | if _string_at(current, 2, {'DG'}): |
|
400 | 1 | if _string_at((current + 2), 1, {'I', 'E', 'Y'}): |
|
401 | # e.g. 'edge' |
||
402 | 1 | primary, secondary = _metaph_add('J') |
|
403 | 1 | current += 3 |
|
404 | 1 | continue |
|
405 | else: |
||
406 | # e.g. 'edgar' |
||
407 | 1 | primary, secondary = _metaph_add('TK') |
|
408 | 1 | current += 2 |
|
409 | 1 | continue |
|
410 | |||
411 | 1 | elif _string_at(current, 2, {'DT', 'DD'}): |
|
412 | 1 | primary, secondary = _metaph_add('T') |
|
413 | 1 | current += 2 |
|
414 | 1 | continue |
|
415 | |||
416 | # else |
||
417 | else: |
||
418 | 1 | primary, secondary = _metaph_add('T') |
|
419 | 1 | current += 1 |
|
420 | 1 | continue |
|
421 | |||
422 | 1 | elif _get_at(current) == 'F': |
|
423 | 1 | if _get_at(current + 1) == 'F': |
|
424 | 1 | current += 2 |
|
425 | else: |
||
426 | 1 | current += 1 |
|
427 | 1 | primary, secondary = _metaph_add('F') |
|
428 | 1 | continue |
|
429 | |||
430 | 1 | elif _get_at(current) == 'G': |
|
431 | 1 | if _get_at(current + 1) == 'H': |
|
432 | 1 | if (current > 0) and not _is_vowel(current - 1): |
|
433 | 1 | primary, secondary = _metaph_add('K') |
|
434 | 1 | current += 2 |
|
435 | 1 | continue |
|
436 | |||
437 | # 'ghislane', ghiradelli |
||
438 | 1 | elif current == 0: |
|
439 | 1 | if _get_at(current + 2) == 'I': |
|
440 | 1 | primary, secondary = _metaph_add('J') |
|
441 | else: |
||
442 | 1 | primary, secondary = _metaph_add('K') |
|
443 | 1 | current += 2 |
|
444 | 1 | continue |
|
445 | |||
446 | # Parker's rule (with some further refinements) - |
||
447 | # e.g., 'hugh' |
||
448 | 1 | elif ( |
|
449 | ( |
||
450 | (current > 1) |
||
451 | and _string_at((current - 2), 1, {'B', 'H', 'D'}) |
||
452 | ) |
||
453 | or |
||
454 | # e.g., 'bough' |
||
455 | ( |
||
456 | (current > 2) |
||
457 | and _string_at((current - 3), 1, {'B', 'H', 'D'}) |
||
458 | ) |
||
459 | or |
||
460 | # e.g., 'broughton' |
||
461 | ( |
||
462 | (current > 3) |
||
463 | and _string_at((current - 4), 1, {'B', 'H'}) |
||
464 | ) |
||
465 | ): |
||
466 | 1 | current += 2 |
|
467 | 1 | continue |
|
468 | else: |
||
469 | # e.g. 'laugh', 'McLaughlin', 'cough', |
||
470 | # 'gough', 'rough', 'tough' |
||
471 | 1 | if ( |
|
472 | (current > 2) |
||
473 | and (_get_at(current - 1) == 'U') |
||
474 | and ( |
||
475 | _string_at( |
||
476 | (current - 3), 1, {'C', 'G', 'L', 'R', 'T'} |
||
477 | ) |
||
478 | ) |
||
479 | ): |
||
480 | 1 | primary, secondary = _metaph_add('F') |
|
481 | 1 | elif (current > 0) and _get_at(current - 1) != 'I': |
|
482 | 1 | primary, secondary = _metaph_add('K') |
|
483 | 1 | current += 2 |
|
484 | 1 | continue |
|
485 | |||
486 | 1 | elif _get_at(current + 1) == 'N': |
|
487 | 1 | if ( |
|
488 | (current == 1) |
||
489 | and _is_vowel(0) |
||
490 | and not _slavo_germanic() |
||
491 | ): |
||
492 | 1 | primary, secondary = _metaph_add('KN', 'N') |
|
493 | # not e.g. 'cagney' |
||
494 | 1 | elif ( |
|
495 | not _string_at((current + 2), 2, {'EY'}) |
||
496 | and (_get_at(current + 1) != 'Y') |
||
497 | and not _slavo_germanic() |
||
498 | ): |
||
499 | 1 | primary, secondary = _metaph_add('N', 'KN') |
|
500 | else: |
||
501 | 1 | primary, secondary = _metaph_add('KN') |
|
502 | 1 | current += 2 |
|
503 | 1 | continue |
|
504 | |||
505 | # 'tagliaro' |
||
506 | 1 | elif ( |
|
507 | _string_at((current + 1), 2, {'LI'}) |
||
508 | and not _slavo_germanic() |
||
509 | ): |
||
510 | 1 | primary, secondary = _metaph_add('KL', 'L') |
|
511 | 1 | current += 2 |
|
512 | 1 | continue |
|
513 | |||
514 | # -ges-, -gep-, -gel-, -gie- at beginning |
||
515 | 1 | elif (current == 0) and ( |
|
516 | (_get_at(current + 1) == 'Y') |
||
517 | or _string_at( |
||
518 | (current + 1), |
||
519 | 2, |
||
520 | { |
||
521 | 'ES', |
||
522 | 'EP', |
||
523 | 'EB', |
||
524 | 'EL', |
||
525 | 'EY', |
||
526 | 'IB', |
||
527 | 'IL', |
||
528 | 'IN', |
||
529 | 'IE', |
||
530 | 'EI', |
||
531 | 'ER', |
||
532 | }, |
||
533 | ) |
||
534 | ): |
||
535 | 1 | primary, secondary = _metaph_add('K', 'J') |
|
536 | 1 | current += 2 |
|
537 | 1 | continue |
|
538 | |||
539 | # -ger-, -gy- |
||
540 | 1 | elif ( |
|
541 | ( |
||
542 | _string_at((current + 1), 2, {'ER'}) |
||
543 | or (_get_at(current + 1) == 'Y') |
||
544 | ) |
||
545 | and not _string_at(0, 6, {'DANGER', 'RANGER', 'MANGER'}) |
||
546 | and not _string_at((current - 1), 1, {'E', 'I'}) |
||
547 | and not _string_at((current - 1), 3, {'RGY', 'OGY'}) |
||
548 | ): |
||
549 | 1 | primary, secondary = _metaph_add('K', 'J') |
|
550 | 1 | current += 2 |
|
551 | 1 | continue |
|
552 | |||
553 | # italian e.g, 'biaggi' |
||
554 | 1 | elif _string_at( |
|
555 | (current + 1), 1, {'E', 'I', 'Y'} |
||
556 | ) or _string_at((current - 1), 4, {'AGGI', 'OGGI'}): |
||
557 | # obvious germanic |
||
558 | 1 | if ( |
|
559 | _string_at(0, 4, {'VAN ', 'VON '}) |
||
560 | or _string_at(0, 3, {'SCH'}) |
||
561 | ) or _string_at((current + 1), 2, {'ET'}): |
||
562 | 1 | primary, secondary = _metaph_add('K') |
|
563 | 1 | elif _string_at((current + 1), 4, {'IER '}): |
|
564 | 1 | primary, secondary = _metaph_add('J') |
|
565 | else: |
||
566 | 1 | primary, secondary = _metaph_add('J', 'K') |
|
567 | 1 | current += 2 |
|
568 | 1 | continue |
|
569 | |||
570 | else: |
||
571 | 1 | if _get_at(current + 1) == 'G': |
|
572 | 1 | current += 2 |
|
573 | else: |
||
574 | 1 | current += 1 |
|
575 | 1 | primary, secondary = _metaph_add('K') |
|
576 | 1 | continue |
|
577 | |||
578 | 1 | elif _get_at(current) == 'H': |
|
579 | # only keep if first & before vowel or btw. 2 vowels |
||
580 | 1 | if ((current == 0) or _is_vowel(current - 1)) and _is_vowel( |
|
581 | current + 1 |
||
582 | ): |
||
583 | 1 | primary, secondary = _metaph_add('H') |
|
584 | 1 | current += 2 |
|
585 | else: # also takes care of 'HH' |
||
586 | 1 | current += 1 |
|
587 | 1 | continue |
|
588 | |||
589 | 1 | elif _get_at(current) == 'J': |
|
590 | # obvious spanish, 'jose', 'san jacinto' |
||
591 | 1 | if _string_at(current, 4, {'JOSE'}) or _string_at( |
|
592 | 0, 4, {'SAN '} |
||
593 | ): |
||
594 | 1 | if ( |
|
595 | (current == 0) and (_get_at(current + 4) == ' ') |
||
596 | ) or _string_at(0, 4, {'SAN '}): |
||
597 | 1 | primary, secondary = _metaph_add('H') |
|
598 | else: |
||
599 | 1 | primary, secondary = _metaph_add('J', 'H') |
|
600 | 1 | current += 1 |
|
601 | 1 | continue |
|
602 | |||
603 | 1 | elif (current == 0) and not _string_at(current, 4, {'JOSE'}): |
|
604 | # Yankelovich/Jankelowicz |
||
605 | 1 | primary, secondary = _metaph_add('J', 'A') |
|
606 | # Spanish pron. of e.g. 'bajador' |
||
607 | 1 | elif ( |
|
608 | _is_vowel(current - 1) |
||
609 | and not _slavo_germanic() |
||
610 | and ( |
||
611 | (_get_at(current + 1) == 'A') |
||
612 | or (_get_at(current + 1) == 'O') |
||
613 | ) |
||
614 | ): |
||
615 | 1 | primary, secondary = _metaph_add('J', 'H') |
|
616 | 1 | elif current == last: |
|
617 | 1 | primary, secondary = _metaph_add('J', ' ') |
|
618 | 1 | elif not _string_at( |
|
619 | (current + 1), 1, {'L', 'T', 'K', 'S', 'N', 'M', 'B', 'Z'} |
||
620 | ) and not _string_at((current - 1), 1, {'S', 'K', 'L'}): |
||
621 | 1 | primary, secondary = _metaph_add('J') |
|
622 | |||
623 | 1 | if _get_at(current + 1) == 'J': # it could happen! |
|
624 | 1 | current += 2 |
|
625 | else: |
||
626 | 1 | current += 1 |
|
627 | 1 | continue |
|
628 | |||
629 | 1 | elif _get_at(current) == 'K': |
|
630 | 1 | if _get_at(current + 1) == 'K': |
|
631 | 1 | current += 2 |
|
632 | else: |
||
633 | 1 | current += 1 |
|
634 | 1 | primary, secondary = _metaph_add('K') |
|
635 | 1 | continue |
|
636 | |||
637 | 1 | elif _get_at(current) == 'L': |
|
638 | 1 | if _get_at(current + 1) == 'L': |
|
639 | # Spanish e.g. 'cabrillo', 'gallegos' |
||
640 | 1 | if ( |
|
641 | (current == (length - 3)) |
||
642 | and _string_at( |
||
643 | (current - 1), 4, {'ILLO', 'ILLA', 'ALLE'} |
||
644 | ) |
||
645 | ) or ( |
||
646 | ( |
||
647 | _string_at((last - 1), 2, {'AS', 'OS'}) |
||
648 | or _string_at(last, 1, {'A', 'O'}) |
||
649 | ) |
||
650 | and _string_at((current - 1), 4, {'ALLE'}) |
||
651 | ): |
||
652 | 1 | primary, secondary = _metaph_add('L', ' ') |
|
653 | 1 | current += 2 |
|
654 | 1 | continue |
|
655 | 1 | current += 2 |
|
656 | else: |
||
657 | 1 | current += 1 |
|
658 | 1 | primary, secondary = _metaph_add('L') |
|
659 | 1 | continue |
|
660 | |||
661 | 1 | elif _get_at(current) == 'M': |
|
662 | 1 | if ( |
|
663 | ( |
||
664 | _string_at((current - 1), 3, {'UMB'}) |
||
665 | and ( |
||
666 | ((current + 1) == last) |
||
667 | or _string_at((current + 2), 2, {'ER'}) |
||
668 | ) |
||
669 | ) |
||
670 | or |
||
671 | # 'dumb', 'thumb' |
||
672 | (_get_at(current + 1) == 'M') |
||
673 | ): |
||
674 | 1 | current += 2 |
|
675 | else: |
||
676 | 1 | current += 1 |
|
677 | 1 | primary, secondary = _metaph_add('M') |
|
678 | 1 | continue |
|
679 | |||
680 | 1 | elif _get_at(current) == 'N': |
|
681 | 1 | if _get_at(current + 1) == 'N': |
|
682 | 1 | current += 2 |
|
683 | else: |
||
684 | 1 | current += 1 |
|
685 | 1 | primary, secondary = _metaph_add('N') |
|
686 | 1 | continue |
|
687 | |||
688 | 1 | elif _get_at(current) == 'Ñ': |
|
689 | 1 | current += 1 |
|
690 | 1 | primary, secondary = _metaph_add('N') |
|
691 | 1 | continue |
|
692 | |||
693 | 1 | elif _get_at(current) == 'P': |
|
694 | 1 | if _get_at(current + 1) == 'H': |
|
695 | 1 | primary, secondary = _metaph_add('F') |
|
696 | 1 | current += 2 |
|
697 | 1 | continue |
|
698 | |||
699 | # also account for "campbell", "raspberry" |
||
700 | 1 | elif _string_at((current + 1), 1, {'P', 'B'}): |
|
701 | 1 | current += 2 |
|
702 | else: |
||
703 | 1 | current += 1 |
|
704 | 1 | primary, secondary = _metaph_add('P') |
|
705 | 1 | continue |
|
706 | |||
707 | 1 | elif _get_at(current) == 'Q': |
|
708 | 1 | if _get_at(current + 1) == 'Q': |
|
709 | 1 | current += 2 |
|
710 | else: |
||
711 | 1 | current += 1 |
|
712 | 1 | primary, secondary = _metaph_add('K') |
|
713 | 1 | continue |
|
714 | |||
715 | 1 | elif _get_at(current) == 'R': |
|
716 | # french e.g. 'rogier', but exclude 'hochmeier' |
||
717 | 1 | if ( |
|
718 | (current == last) |
||
719 | and not _slavo_germanic() |
||
720 | and _string_at((current - 2), 2, {'IE'}) |
||
721 | and not _string_at((current - 4), 2, {'ME', 'MA'}) |
||
722 | ): |
||
723 | 1 | primary, secondary = _metaph_add('', 'R') |
|
724 | else: |
||
725 | 1 | primary, secondary = _metaph_add('R') |
|
726 | |||
727 | 1 | if _get_at(current + 1) == 'R': |
|
728 | 1 | current += 2 |
|
729 | else: |
||
730 | 1 | current += 1 |
|
731 | 1 | continue |
|
732 | |||
733 | 1 | elif _get_at(current) == 'S': |
|
734 | # special cases 'island', 'isle', 'carlisle', 'carlysle' |
||
735 | 1 | if _string_at((current - 1), 3, {'ISL', 'YSL'}): |
|
736 | 1 | current += 1 |
|
737 | 1 | continue |
|
738 | |||
739 | # special case 'sugar-' |
||
740 | 1 | elif (current == 0) and _string_at(current, 5, {'SUGAR'}): |
|
741 | 1 | primary, secondary = _metaph_add('X', 'S') |
|
742 | 1 | current += 1 |
|
743 | 1 | continue |
|
744 | |||
745 | 1 | elif _string_at(current, 2, {'SH'}): |
|
746 | # Germanic |
||
747 | 1 | if _string_at( |
|
748 | (current + 1), 4, {'HEIM', 'HOEK', 'HOLM', 'HOLZ'} |
||
749 | ): |
||
750 | 1 | primary, secondary = _metaph_add('S') |
|
751 | else: |
||
752 | 1 | primary, secondary = _metaph_add('X') |
|
753 | 1 | current += 2 |
|
754 | 1 | continue |
|
755 | |||
756 | # Italian & Armenian |
||
757 | 1 | elif _string_at(current, 3, {'SIO', 'SIA'}) or _string_at( |
|
758 | current, 4, {'SIAN'} |
||
759 | ): |
||
760 | 1 | if not _slavo_germanic(): |
|
761 | 1 | primary, secondary = _metaph_add('S', 'X') |
|
762 | else: |
||
763 | 1 | primary, secondary = _metaph_add('S') |
|
764 | 1 | current += 3 |
|
765 | 1 | continue |
|
766 | |||
767 | # German & anglicisations, e.g. 'smith' match 'schmidt', |
||
768 | # 'snider' match 'schneider' |
||
769 | # also, -sz- in Slavic language although in Hungarian it is |
||
770 | # pronounced 's' |
||
771 | 1 | elif ( |
|
772 | (current == 0) |
||
773 | and _string_at((current + 1), 1, {'M', 'N', 'L', 'W'}) |
||
774 | ) or _string_at((current + 1), 1, {'Z'}): |
||
775 | 1 | primary, secondary = _metaph_add('S', 'X') |
|
776 | 1 | if _string_at((current + 1), 1, {'Z'}): |
|
777 | 1 | current += 2 |
|
778 | else: |
||
779 | 1 | current += 1 |
|
780 | 1 | continue |
|
781 | |||
782 | 1 | elif _string_at(current, 2, {'SC'}): |
|
783 | # Schlesinger's rule |
||
784 | 1 | if _get_at(current + 2) == 'H': |
|
785 | # dutch origin, e.g. 'school', 'schooner' |
||
786 | 1 | if _string_at( |
|
787 | (current + 3), |
||
788 | 2, |
||
789 | {'OO', 'ER', 'EN', 'UY', 'ED', 'EM'}, |
||
790 | ): |
||
791 | # 'schermerhorn', 'schenker' |
||
792 | 1 | if _string_at((current + 3), 2, {'ER', 'EN'}): |
|
793 | 1 | primary, secondary = _metaph_add('X', 'SK') |
|
794 | else: |
||
795 | 1 | primary, secondary = _metaph_add('SK') |
|
796 | 1 | current += 3 |
|
797 | 1 | continue |
|
798 | else: |
||
799 | 1 | if ( |
|
800 | (current == 0) |
||
801 | and not _is_vowel(3) |
||
802 | and (_get_at(3) != 'W') |
||
803 | ): |
||
804 | 1 | primary, secondary = _metaph_add('X', 'S') |
|
805 | else: |
||
806 | 1 | primary, secondary = _metaph_add('X') |
|
807 | 1 | current += 3 |
|
808 | 1 | continue |
|
809 | |||
810 | 1 | elif _string_at((current + 2), 1, {'I', 'E', 'Y'}): |
|
811 | 1 | primary, secondary = _metaph_add('S') |
|
812 | 1 | current += 3 |
|
813 | 1 | continue |
|
814 | |||
815 | # else |
||
816 | else: |
||
817 | 1 | primary, secondary = _metaph_add('SK') |
|
818 | 1 | current += 3 |
|
819 | 1 | continue |
|
820 | |||
821 | else: |
||
822 | # french e.g. 'resnais', 'artois' |
||
823 | 1 | if (current == last) and _string_at( |
|
824 | (current - 2), 2, {'AI', 'OI'} |
||
825 | ): |
||
826 | 1 | primary, secondary = _metaph_add('', 'S') |
|
827 | else: |
||
828 | 1 | primary, secondary = _metaph_add('S') |
|
829 | |||
830 | 1 | if _string_at((current + 1), 1, {'S', 'Z'}): |
|
831 | 1 | current += 2 |
|
832 | else: |
||
833 | 1 | current += 1 |
|
834 | 1 | continue |
|
835 | |||
836 | 1 | elif _get_at(current) == 'T': |
|
837 | 1 | if _string_at(current, 4, {'TION'}): |
|
838 | 1 | primary, secondary = _metaph_add('X') |
|
839 | 1 | current += 3 |
|
840 | 1 | continue |
|
841 | |||
842 | 1 | elif _string_at(current, 3, {'TIA', 'TCH'}): |
|
843 | 1 | primary, secondary = _metaph_add('X') |
|
844 | 1 | current += 3 |
|
845 | 1 | continue |
|
846 | |||
847 | 1 | elif _string_at(current, 2, {'TH'}) or _string_at( |
|
848 | current, 3, {'TTH'} |
||
849 | ): |
||
850 | # special case 'thomas', 'thames' or germanic |
||
851 | 1 | if ( |
|
852 | _string_at((current + 2), 2, {'OM', 'AM'}) |
||
853 | or _string_at(0, 4, {'VAN ', 'VON '}) |
||
854 | or _string_at(0, 3, {'SCH'}) |
||
855 | ): |
||
856 | 1 | primary, secondary = _metaph_add('T') |
|
857 | else: |
||
858 | 1 | primary, secondary = _metaph_add('0', 'T') |
|
859 | 1 | current += 2 |
|
860 | 1 | continue |
|
861 | |||
862 | 1 | elif _string_at((current + 1), 1, {'T', 'D'}): |
|
863 | 1 | current += 2 |
|
864 | else: |
||
865 | 1 | current += 1 |
|
866 | 1 | primary, secondary = _metaph_add('T') |
|
867 | 1 | continue |
|
868 | |||
869 | 1 | elif _get_at(current) == 'V': |
|
870 | 1 | if _get_at(current + 1) == 'V': |
|
871 | 1 | current += 2 |
|
872 | else: |
||
873 | 1 | current += 1 |
|
874 | 1 | primary, secondary = _metaph_add('F') |
|
875 | 1 | continue |
|
876 | |||
877 | 1 | elif _get_at(current) == 'W': |
|
878 | # can also be in middle of word |
||
879 | 1 | if _string_at(current, 2, {'WR'}): |
|
880 | 1 | primary, secondary = _metaph_add('R') |
|
881 | 1 | current += 2 |
|
882 | 1 | continue |
|
883 | 1 | elif (current == 0) and ( |
|
884 | _is_vowel(current + 1) or _string_at(current, 2, {'WH'}) |
||
885 | ): |
||
886 | # Wasserman should match Vasserman |
||
887 | 1 | if _is_vowel(current + 1): |
|
888 | 1 | primary, secondary = _metaph_add('A', 'F') |
|
889 | else: |
||
890 | # need Uomo to match Womo |
||
891 | 1 | primary, secondary = _metaph_add('A') |
|
892 | |||
893 | # Arnow should match Arnoff |
||
894 | 1 | if ( |
|
895 | ((current == last) and _is_vowel(current - 1)) |
||
896 | or _string_at( |
||
897 | (current - 1), 5, {'EWSKI', 'EWSKY', 'OWSKI', 'OWSKY'} |
||
898 | ) |
||
899 | or _string_at(0, 3, {'SCH'}) |
||
900 | ): |
||
901 | 1 | primary, secondary = _metaph_add('', 'F') |
|
902 | 1 | current += 1 |
|
903 | 1 | continue |
|
904 | # Polish e.g. 'filipowicz' |
||
905 | 1 | elif _string_at(current, 4, {'WICZ', 'WITZ'}): |
|
906 | 1 | primary, secondary = _metaph_add('TS', 'FX') |
|
907 | 1 | current += 4 |
|
908 | 1 | continue |
|
909 | # else skip it |
||
910 | else: |
||
911 | 1 | current += 1 |
|
912 | 1 | continue |
|
913 | |||
914 | 1 | elif _get_at(current) == 'X': |
|
915 | # French e.g. breaux |
||
916 | 1 | if not ( |
|
917 | (current == last) |
||
918 | and ( |
||
919 | _string_at((current - 3), 3, {'IAU', 'EAU'}) |
||
920 | or _string_at((current - 2), 2, {'AU', 'OU'}) |
||
921 | ) |
||
922 | ): |
||
923 | 1 | primary, secondary = _metaph_add('KS') |
|
924 | |||
925 | 1 | if _string_at((current + 1), 1, {'C', 'X'}): |
|
926 | 1 | current += 2 |
|
927 | else: |
||
928 | 1 | current += 1 |
|
929 | 1 | continue |
|
930 | |||
931 | 1 | elif _get_at(current) == 'Z': |
|
932 | # Chinese Pinyin e.g. 'zhao' |
||
933 | 1 | if _get_at(current + 1) == 'H': |
|
934 | 1 | primary, secondary = _metaph_add('J') |
|
935 | 1 | current += 2 |
|
936 | 1 | continue |
|
937 | 1 | elif _string_at((current + 1), 2, {'ZO', 'ZI', 'ZA'}) or ( |
|
938 | _slavo_germanic() |
||
939 | and ((current > 0) and _get_at(current - 1) != 'T') |
||
940 | ): |
||
941 | 1 | primary, secondary = _metaph_add('S', 'TS') |
|
942 | else: |
||
943 | 1 | primary, secondary = _metaph_add('S') |
|
944 | |||
945 | 1 | if _get_at(current + 1) == 'Z': |
|
946 | 1 | current += 2 |
|
947 | else: |
||
948 | 1 | current += 1 |
|
949 | 1 | continue |
|
950 | |||
951 | else: |
||
952 | 1 | current += 1 |
|
953 | |||
954 | 1 | if max_length > 0: |
|
955 | 1 | primary = primary[:max_length] |
|
956 | 1 | secondary = secondary[:max_length] |
|
957 | 1 | if primary == secondary: |
|
958 | 1 | secondary = '' |
|
959 | |||
960 | 1 | return primary, secondary |
|
961 | |||
1000 |