abydos.phonetic.phonet.phonet() - Code Metrics - Inspection of "Merge pull request #120 from chrislit/modularize" - chrislit/abydos - Measure and Improve Code Quality continuously with Scrutinizer

Test Failed

Push — master ( 64abe2...a464fa )

by Chris

created 2018-10-19 22:32 UTC

abydos.phonetic.phonet.phonet() F

↳ Parent: abydos.phonetic.phonet

Complexity

Conditions

142

Size

Total Lines	1512
Code Lines	1315

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	142
eloc	1315
nop	3
dl	0
loc	1512
rs	0
c	0
b	0
f	0

How to fix Long Method Complexity

1			# -- coding: utf-8 --
2
3			# Copyright 2014-2018 by Christopher C. Little.
4			# This file is part of Abydos.
5			#
6			# Abydos is free software: you can redistribute it and/or modify
7			# it under the terms of the GNU General Public License as published by
8			# the Free Software Foundation, either version 3 of the License, or
9			# (at your option) any later version.
10			#
11			# Abydos is distributed in the hope that it will be useful,
12			# but WITHOUT ANY WARRANTY; without even the implied warranty of
13			# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14			# GNU General Public License for more details.
15			#
16			# You should have received a copy of the GNU General Public License
17			# along with Abydos. If not, see <http://www.gnu.org/licenses/>.
18
19			"""abydos.phonetic.phonet.
20
21			The phonetic.phonet module implements phonet algorithm (a.k.a. Hannoveraner
22			Phonetik), intended chiefly for German.
23			"""
24
25			from __future__ import unicode_literals
26
27			from collections import Counter
28			from unicodedata import normalize as unicode_normalize
29
30			from six import text_type
31			from six.moves import range
32
33			__all__ = ['phonet']
34
35
36			def phonet(word, mode=1, lang='de'):
37			"""Return the phonet code for a word.
38
39			phonet ("Hannoveraner Phonetik") was developed by Jörg Michael and
40			documented in :cite:`Michael:1999`.
41
42			This is a port of Jesper Zedlitz's code, which is licensed LGPL
43			:cite:`Zedlitz:2015`.
44
45			That is, in turn, based on Michael's C code, which is also licensed LGPL
46			:cite:`Michael:2007`.
47
48			:param str word: the word to transform
49			:param int mode: the ponet variant to employ (1 or 2)
50			:param str lang: 'de' (default) for German
51			'none' for no language
52			:returns: the phonet value
53			:rtype: str
54
55			>>> phonet('Christopher')
56			'KRISTOFA'
57			>>> phonet('Niall')
58			'NIAL'
59			>>> phonet('Smith')
60			'SMIT'
61			>>> phonet('Schmidt')
62			'SHMIT'
63
64			>>> phonet('Christopher', mode=2)
65			'KRIZTUFA'
66			>>> phonet('Niall', mode=2)
67			'NIAL'
68			>>> phonet('Smith', mode=2)
69			'ZNIT'
70			>>> phonet('Schmidt', mode=2)
71			'ZNIT'
72
73			>>> phonet('Christopher', lang='none')
74			'CHRISTOPHER'
75			>>> phonet('Niall', lang='none')
76			'NIAL'
77			>>> phonet('Smith', lang='none')
78			'SMITH'
79			>>> phonet('Schmidt', lang='none')
80			'SCHMIDT'
81			"""
82			_phonet_rules_no_lang = ( # separator chars
83			'´', ' ', ' ',
84			'"', ' ', ' ',
85			'`$', '', '',
86			'\'', ' ', ' ',
87			',', ',', ',',
88			';', ',', ',',
89			'-', ' ', ' ',
90			' ', ' ', ' ',
91			'.', '.', '.',
92			':', '.', '.',
93			# German umlauts
94			'Ä', 'AE', 'AE',
95			'Ö', 'OE', 'OE',
96			'Ü', 'UE', 'UE',
97			'ß', 'S', 'S',
98			# international umlauts
99			'À', 'A', 'A',
100			'Á', 'A', 'A',
101			'Â', 'A', 'A',
102			'Ã', 'A', 'A',
103			'Å', 'A', 'A',
104			'Æ', 'AE', 'AE',
105			'Ç', 'C', 'C',
106			'Ð', 'DJ', 'DJ',
107			'È', 'E', 'E',
108			'É', 'E', 'E',
109			'Ê', 'E', 'E',
110			'Ë', 'E', 'E',
111			'Ì', 'I', 'I',
112			'Í', 'I', 'I',
113			'Î', 'I', 'I',
114			'Ï', 'I', 'I',
115			'Ñ', 'NH', 'NH',
116			'Ò', 'O', 'O',
117			'Ó', 'O', 'O',
118			'Ô', 'O', 'O',
119			'Õ', 'O', 'O',
120			'Œ', 'OE', 'OE',
121			'Ø', 'OE', 'OE',
122			'Š', 'SH', 'SH',
123			'Þ', 'TH', 'TH',
124			'Ù', 'U', 'U',
125			'Ú', 'U', 'U',
126			'Û', 'U', 'U',
127			'Ý', 'Y', 'Y',
128			'Ÿ', 'Y', 'Y',
129			# 'normal' letters (A-Z)
130			'MC^', 'MAC', 'MAC',
131			'MC^', 'MAC', 'MAC',
132			'M´^', 'MAC', 'MAC',
133			'M\'^', 'MAC', 'MAC',
134			'O´^', 'O', 'O',
135			'O\'^', 'O', 'O',
136			'VAN DEN ^', 'VANDEN', 'VANDEN',
137			None, None, None)
138
139			_phonet_rules_german = ( # separator chars
140			'´', ' ', ' ',
141			'"', ' ', ' ',
142			'`$', '', '',
143			'\'', ' ', ' ',
144			',', ' ', ' ',
145			';', ' ', ' ',
146			'-', ' ', ' ',
147			' ', ' ', ' ',
148			'.', '.', '.',
149			':', '.', '.',
150			# German umlauts
151			'ÄE', 'E', 'E',
152			'ÄU<', 'EU', 'EU',
153			'ÄV(AEOU)-<', 'EW', None,
154			'Ä$', 'Ä', None,
155			'Ä<', None, 'E',
156			'Ä', 'E', None,
157			'ÖE', 'Ö', 'Ö',
158			'ÖU', 'Ö', 'Ö',
159			'ÖVER--<', 'ÖW', None,
160			'ÖV(AOU)-', 'ÖW', None,
161			'ÜBEL(GNRW)-^^', 'ÜBL ', 'IBL ',
162			'ÜBER^^', 'ÜBA', 'IBA',
163			'ÜE', 'Ü', 'I',
164			'ÜVER--<', 'ÜW', None,
165			'ÜV(AOU)-', 'ÜW', None,
166			'Ü', None, 'I',
167			'ßCH<', None, 'Z',
168			'ß<', 'S', 'Z',
169			# international umlauts
170			'À<', 'A', 'A',
171			'Á<', 'A', 'A',
172			'Â<', 'A', 'A',
173			'Ã<', 'A', 'A',
174			'Å<', 'A', 'A',
175			'ÆER-', 'E', 'E',
176			'ÆU<', 'EU', 'EU',
177			'ÆV(AEOU)-<', 'EW', None,
178			'Æ$', 'Ä', None,
179			'Æ<', None, 'E',
180			'Æ', 'E', None,
181			'Ç', 'Z', 'Z',
182			'ÐÐ-', '', '',
183			'Ð', 'DI', 'TI',
184			'È<', 'E', 'E',
185			'É<', 'E', 'E',
186			'Ê<', 'E', 'E',
187			'Ë', 'E', 'E',
188			'Ì<', 'I', 'I',
189			'Í<', 'I', 'I',
190			'Î<', 'I', 'I',
191			'Ï', 'I', 'I',
192			'ÑÑ-', '', '',
193			'Ñ', 'NI', 'NI',
194			'Ò<', 'O', 'U',
195			'Ó<', 'O', 'U',
196			'Ô<', 'O', 'U',
197			'Õ<', 'O', 'U',
198			'Œ<', 'Ö', 'Ö',
199			'Ø(IJY)-<', 'E', 'E',
200			'Ø<', 'Ö', 'Ö',
201			'Š', 'SH', 'Z',
202			'Þ', 'T', 'T',
203			'Ù<', 'U', 'U',
204			'Ú<', 'U', 'U',
205			'Û<', 'U', 'U',
206			'Ý<', 'I', 'I',
207			'Ÿ<', 'I', 'I',
208			# 'normal' letters (A-Z)
209			'ABELLE$', 'ABL', 'ABL',
210			'ABELL$', 'ABL', 'ABL',
211			'ABIENNE$', 'ABIN', 'ABIN',
212			'ACHME---^', 'ACH', 'AK',
213			'ACEY$', 'AZI', 'AZI',
214			'ADV', 'ATW', None,
215			'AEGL-', 'EK', None,
216			'AEU<', 'EU', 'EU',
217			'AE2', 'E', 'E',
218			'AFTRAUBEN------', 'AFT ', 'AFT ',
219			'AGL-1', 'AK', None,
220			'AGNI-^', 'AKN', 'AKN',
221			'AGNIE-', 'ANI', 'ANI',
222			'AGN(AEOU)-$', 'ANI', 'ANI',
223			'AH(AIOÖUÜY)-', 'AH', None,
224			'AIA2', 'AIA', 'AIA',
225			'AIE$', 'E', 'E',
226			'AILL(EOU)-', 'ALI', 'ALI',
227			'AINE$', 'EN', 'EN',
228			'AIRE$', 'ER', 'ER',
229			'AIR-', 'E', 'E',
230			'AISE$', 'ES', 'EZ',
231			'AISSANCE$', 'ESANS', 'EZANZ',
232			'AISSE$', 'ES', 'EZ',
233			'AIX$', 'EX', 'EX',
234			'AJ(AÄEÈÉÊIOÖUÜ)--', 'A', 'A',
235			'AKTIE', 'AXIE', 'AXIE',
236			'AKTUEL', 'AKTUEL', None,
237			'ALOI^', 'ALOI', 'ALUI', # Don't merge these rules
238			'ALOY^', 'ALOI', 'ALUI', # needed by 'check_rules'
239			'AMATEU(RS)-', 'AMATÖ', 'ANATÖ',
240			'ANCH(OEI)-', 'ANSH', 'ANZ',
241			'ANDERGEGANG----', 'ANDA GE', 'ANTA KE',
242			'ANDERGEHE----', 'ANDA ', 'ANTA ',
243			'ANDERGESETZ----', 'ANDA GE', 'ANTA KE',
244			'ANDERGING----', 'ANDA ', 'ANTA ',
245			'ANDERSETZ(ET)-----', 'ANDA ', 'ANTA ',
246			'ANDERZUGEHE----', 'ANDA ZU ', 'ANTA ZU ',
247			'ANDERZUSETZE-----', 'ANDA ZU ', 'ANTA ZU ',
248			'ANER(BKO)---^^', 'AN', None,
249			'ANHAND---^$', 'AN H', 'AN ',
250			'ANH(AÄEIOÖUÜY)--^^', 'AN', None,
251			'ANIELLE$', 'ANIEL', 'ANIL',
252			'ANIEL', 'ANIEL', None,
253			'ANSTELLE----^$', 'AN ST', 'AN ZT',
254			'ANTI^^', 'ANTI', 'ANTI',
255			'ANVER^^', 'ANFA', 'ANFA',
256			'ATIA$', 'ATIA', 'ATIA',
257			'ATIA(NS)--', 'ATI', 'ATI',
258			'ATI(AÄOÖUÜ)-', 'AZI', 'AZI',
259			'AUAU--', '', '',
260			'AUERE$', 'AUERE', None,
261			'AUERE(NS)-$', 'AUERE', None,
262			'AUERE(AIOUY)--', 'AUER', None,
263			'AUER(AÄIOÖUÜY)-', 'AUER', None,
264			'AUER<', 'AUA', 'AUA',
265			'AUF^^', 'AUF', 'AUF',
266			'AULT$', 'O', 'U',
267			'AUR(BCDFGKLMNQSTVWZ)-', 'AUA', 'AUA',
268			'AUR$', 'AUA', 'AUA',
269			'AUSSE$', 'OS', 'UZ',
270			'AUS(ST)-^', 'AUS', 'AUS',
271			'AUS^^', 'AUS', 'AUS',
272			'AUTOFAHR----', 'AUTO ', 'AUTU ',
273			'AUTO^^', 'AUTO', 'AUTU',
274			'AUX(IY)-', 'AUX', 'AUX',
275			'AUX', 'O', 'U',
276			'AU', 'AU', 'AU',
277			'AVER--<', 'AW', None,
278			'AVIER$', 'AWIE', 'AFIE',
279			'AV(EÈÉÊI)-^', 'AW', None,
280			'AV(AOU)-', 'AW', None,
281			'AYRE$', 'EIRE', 'EIRE',
282			'AYRE(NS)-$', 'EIRE', 'EIRE',
283			'AYRE(AIOUY)--', 'EIR', 'EIR',
284			'AYR(AÄIOÖUÜY)-', 'EIR', 'EIR',
285			'AYR<', 'EIA', 'EIA',
286			'AYER--<', 'EI', 'EI',
287			'AY(AÄEIOÖUÜY)--', 'A', 'A',
288			'AË', 'E', 'E',
289			'A(IJY)<', 'EI', 'EI',
290			'BABY^$', 'BEBI', 'BEBI',
291			'BAB(IY)^', 'BEBI', 'BEBI',
292			'BEAU^$', 'BO', None,
293			'BEA(BCMNRU)-^', 'BEA', 'BEA',
294			'BEAT(AEIMORU)-^', 'BEAT', 'BEAT',
295			'BEE$', 'BI', 'BI',
296			'BEIGE^$', 'BESH', 'BEZ',
297			'BENOIT--', 'BENO', 'BENU',
298			'BER(DT)-', 'BER', None,
299			'BERN(DT)-', 'BERN', None,
300			'BE(LMNRST)-^', 'BE', 'BE',
301			'BETTE$', 'BET', 'BET',
302			'BEVOR^$', 'BEFOR', None,
303			'BIC$', 'BIZ', 'BIZ',
304			'BOWL(EI)-', 'BOL', 'BUL',
305			'BP(AÄEÈÉÊIÌÍÎOÖRUÜY)-', 'B', 'B',
306			'BRINGEND-----^', 'BRI', 'BRI',
307			'BRINGEND-----', ' BRI', ' BRI',
308			'BROW(NS)-', 'BRAU', 'BRAU',
309			'BUDGET7', 'BÜGE', 'BIKE',
310			'BUFFET7', 'BÜFE', 'BIFE',
311			'BYLLE$', 'BILE', 'BILE',
312			'BYLL$', 'BIL', 'BIL',
313			'BYPA--^', 'BEI', 'BEI',
314			'BYTE<', 'BEIT', 'BEIT',
315			'BY9^', 'BÜ', None,
316			'B(SßZ)$', 'BS', None,
317			'CACH(EI)-^', 'KESH', 'KEZ',
318			'CAE--', 'Z', 'Z',
319			'CA(IY)$', 'ZEI', 'ZEI',
320			'CE(EIJUY)--', 'Z', 'Z',
321			'CENT<', 'ZENT', 'ZENT',
322			'CERST(EI)----^', 'KE', 'KE',
323			'CER$', 'ZA', 'ZA',
324			'CE3', 'ZE', 'ZE',
325			'CH\'S$', 'X', 'X',
326			'CH´S$', 'X', 'X',
327			'CHAO(ST)-', 'KAO', 'KAU',
328			'CHAMPIO-^', 'SHEMPI', 'ZENBI',
329			'CHAR(AI)-^', 'KAR', 'KAR',
330			'CHAU(CDFSVWXZ)-', 'SHO', 'ZU',
331			'CHÄ(CF)-', 'SHE', 'ZE',
332			'CHE(CF)-', 'SHE', 'ZE',
333			'CHEM-^', 'KE', 'KE', # or: 'CHE', 'KE'
334			'CHEQUE<', 'SHEK', 'ZEK',
335			'CHI(CFGPVW)-', 'SHI', 'ZI',
336			'CH(AEUY)-<^', 'SH', 'Z',
337			'CHK-', '', '',
338			'CHO(CKPS)-^', 'SHO', 'ZU',
339			'CHRIS-', 'KRI', None,
340			'CHRO-', 'KR', None,
341			'CH(LOR)-<^', 'K', 'K',
342			'CHST-', 'X', 'X',
343			'CH(SßXZ)3', 'X', 'X',
344			'CHTNI-3', 'CHN', 'KN',
345			'CH^', 'K', 'K', # or: 'CH', 'K'
346			'CH', 'CH', 'K',
347			'CIC$', 'ZIZ', 'ZIZ',
348			'CIENCEFICT----', 'EIENS ', 'EIENZ ',
349			'CIENCE$', 'EIENS', 'EIENZ',
350			'CIER$', 'ZIE', 'ZIE',
351			'CYB-^', 'ZEI', 'ZEI',
352			'CY9^', 'ZÜ', 'ZI',
353			'C(IJY)-<3', 'Z', 'Z',
354			'CLOWN-', 'KLAU', 'KLAU',
355			'CCH', 'Z', 'Z',
356			'CCE-', 'X', 'X',
357			'C(CK)-', '', '',
358			'CLAUDET---', 'KLO', 'KLU',
359			'CLAUDINE^$', 'KLODIN', 'KLUTIN',
360			'COACH', 'KOSH', 'KUZ',
361			'COLE$', 'KOL', 'KUL',
362			'COUCH', 'KAUSH', 'KAUZ',
363			'COW', 'KAU', 'KAU',
364			'CQUES$', 'K', 'K',
365			'CQUE', 'K', 'K',
366			'CRASH--9', 'KRE', 'KRE',
367			'CREAT-^', 'KREA', 'KREA',
368			'CST', 'XT', 'XT',
369			'CS<^', 'Z', 'Z',
370			'C(SßX)', 'X', 'X',
371			'CT\'S$', 'X', 'X',
372			'CT(SßXZ)', 'X', 'X',
373			'CZ<', 'Z', 'Z',
374			'C(ÈÉÊÌÍÎÝ)3', 'Z', 'Z',
375			'C.^', 'C.', 'C.',
376			'CÄ-', 'Z', 'Z',
377			'CÜ$', 'ZÜ', 'ZI',
378			'C\'S$', 'X', 'X',
379			'C<', 'K', 'K',
380			'DAHER^$', 'DAHER', None,
381			'DARAUFFOLGE-----', 'DARAUF ', 'TARAUF ',
382			'DAVO(NR)-^$', 'DAFO', 'TAFU',
383			'DD(SZ)--<', '', '',
384			'DD9', 'D', None,
385			'DEPOT7', 'DEPO', 'TEBU',
386			'DESIGN', 'DISEIN', 'TIZEIN',
387			'DE(LMNRST)-3^', 'DE', 'TE',
388			'DETTE$', 'DET', 'TET',
389			'DH$', 'T', None,
390			'DIC$', 'DIZ', 'TIZ',
391			'DIDR-^', 'DIT', None,
392			'DIEDR-^', 'DIT', None,
393			'DJ(AEIOU)-^', 'I', 'I',
394			'DMITR-^', 'DIMIT', 'TINIT',
395			'DRY9^', 'DRÜ', None,
396			'DT-', '', '',
397			'DUIS-^', 'DÜ', 'TI',
398			'DURCH^^', 'DURCH', 'TURK',
399			'DVA$', 'TWA', None,
400			'DY9^', 'DÜ', None,
401			'DYS$', 'DIS', None,
402			'DS(CH)--<', 'T', 'T',
403			'DST', 'ZT', 'ZT',
404			'DZS(CH)--', 'T', 'T',
405			'D(SßZ)', 'Z', 'Z',
406			'D(AÄEIOÖRUÜY)-', 'D', None,
407			'D(ÀÁÂÃÅÈÉÊÌÍÎÙÚÛ)-', 'D', None,
408			'D\'H^', 'D', 'T',
409			'D´H^', 'D', 'T',
410			'D`H^', 'D', 'T',
411			'D\'S3$', 'Z', 'Z',
412			'D´S3$', 'Z', 'Z',
413			'D^', 'D', None,
414			'D', 'T', 'T',
415			'EAULT$', 'O', 'U',
416			'EAUX$', 'O', 'U',
417			'EAU', 'O', 'U',
418			'EAV', 'IW', 'IF',
419			'EAS3$', 'EAS', None,
420			'EA(AÄEIOÖÜY)-3', 'EA', 'EA',
421			'EA3$', 'EA', 'EA',
422			'EA3', 'I', 'I',
423			'EBENSO^$', 'EBNSO', 'EBNZU',
424			'EBENSO^^', 'EBNSO ', 'EBNZU ',
425			'EBEN^^', 'EBN', 'EBN',
426			'EE9', 'E', 'E',
427			'EGL-1', 'EK', None,
428			'EHE(IUY)--1', 'EH', None,
429			'EHUNG---1', 'E', None,
430			'EH(AÄIOÖUÜY)-1', 'EH', None,
431			'EIEI--', '', '',
432			'EIERE^$', 'EIERE', None,
433			'EIERE$', 'EIERE', None,
434			'EIERE(NS)-$', 'EIERE', None,
435			'EIERE(AIOUY)--', 'EIER', None,
436			'EIER(AÄIOÖUÜY)-', 'EIER', None,
437			'EIER<', 'EIA', None,
438			'EIGL-1', 'EIK', None,
439			'EIGH$', 'EI', 'EI',
440			'EIH--', 'E', 'E',
441			'EILLE$', 'EI', 'EI',
442			'EIR(BCDFGKLMNQSTVWZ)-', 'EIA', 'EIA',
443			'EIR$', 'EIA', 'EIA',
444			'EITRAUBEN------', 'EIT ', 'EIT ',
445			'EI', 'EI', 'EI',
446			'EJ$', 'EI', 'EI',
447			'ELIZ^', 'ELIS', None,
448			'ELZ^', 'ELS', None,
449			'EL-^', 'E', 'E',
450			'ELANG----1', 'E', 'E',
451			'EL(DKL)--1', 'E', 'E',
452			'EL(MNT)--1$', 'E', 'E',
453			'ELYNE$', 'ELINE', 'ELINE',
454			'ELYN$', 'ELIN', 'ELIN',
455			'EL(AÄEÈÉÊIÌÍÎOÖUÜY)-1', 'EL', 'EL',
456			'EL-1', 'L', 'L',
457			'EM-^', None, 'E',
458			'EM(DFKMPQT)--1', None, 'E',
459			'EM(AÄEÈÉÊIÌÍÎOÖUÜY)--1', None, 'E',
460			'EM-1', None, 'N',
461			'ENGAG-^', 'ANGA', 'ANKA',
462			'EN-^', 'E', 'E',
463			'ENTUEL', 'ENTUEL', None,
464			'EN(CDGKQSTZ)--1', 'E', 'E',
465			'EN(AÄEÈÉÊIÌÍÎNOÖUÜY)-1', 'EN', 'EN',
466			'EN-1', '', '',
467			'ERH(AÄEIOÖUÜ)-^', 'ERH', 'ER',
468			'ER-^', 'E', 'E',
469			'ERREGEND-----', ' ER', ' ER',
470			'ERT1$', 'AT', None,
471			'ER(DGLKMNRQTZß)-1', 'ER', None,
472			'ER(AÄEÈÉÊIÌÍÎOÖUÜY)-1', 'ER', 'A',
473			'ER1$', 'A', 'A',
474			'ER<1', 'A', 'A',
475			'ETAT7', 'ETA', 'ETA',
476			'ETI(AÄOÖÜU)-', 'EZI', 'EZI',
477			'EUERE$', 'EUERE', None,
478			'EUERE(NS)-$', 'EUERE', None,
479			'EUERE(AIOUY)--', 'EUER', None,
480			'EUER(AÄIOÖUÜY)-', 'EUER', None,
481			'EUER<', 'EUA', None,
482			'EUEU--', '', '',
483			'EUILLE$', 'Ö', 'Ö',
484			'EUR$', 'ÖR', 'ÖR',
485			'EUX', 'Ö', 'Ö',
486			'EUSZ$', 'EUS', None,
487			'EUTZ$', 'EUS', None,
488			'EUYS$', 'EUS', 'EUZ',
489			'EUZ$', 'EUS', None,
490			'EU', 'EU', 'EU',
491			'EVER--<1', 'EW', None,
492			'EV(ÄOÖUÜ)-1', 'EW', None,
493			'EYER<', 'EIA', 'EIA',
494			'EY<', 'EI', 'EI',
495			'FACETTE', 'FASET', 'FAZET',
496			'FANS--^$', 'FE', 'FE',
497			'FAN-^$', 'FE', 'FE',
498			'FAULT-', 'FOL', 'FUL',
499			'FEE(DL)-', 'FI', 'FI',
500			'FEHLER', 'FELA', 'FELA',
501			'FE(LMNRST)-3^', 'FE', 'FE',
502			'FOERDERN---^', 'FÖRD', 'FÖRT',
503			'FOERDERN---', ' FÖRD', ' FÖRT',
504			'FOND7', 'FON', 'FUN',
505			'FRAIN$', 'FRA', 'FRA',
506			'FRISEU(RS)-', 'FRISÖ', 'FRIZÖ',
507			'FY9^', 'FÜ', None,
508			'FÖRDERN---^', 'FÖRD', 'FÖRT',
509			'FÖRDERN---', ' FÖRD', ' FÖRT',
510			'GAGS^$', 'GEX', 'KEX',
511			'GAG^$', 'GEK', 'KEK',
512			'GD', 'KT', 'KT',
513			'GEGEN^^', 'GEGN', 'KEKN',
514			'GEGENGEKOM-----', 'GEGN ', 'KEKN ',
515			'GEGENGESET-----', 'GEGN ', 'KEKN ',
516			'GEGENKOMME-----', 'GEGN ', 'KEKN ',
517			'GEGENZUKOM---', 'GEGN ZU ', 'KEKN ZU ',
518			'GENDETWAS-----$', 'GENT ', 'KENT ',
519			'GENRE', 'IORE', 'IURE',
520			'GE(LMNRST)-3^', 'GE', 'KE',
521			'GER(DKT)-', 'GER', None,
522			'GETTE$', 'GET', 'KET',
523			'GGF.', 'GF.', None,
524			'GG-', '', '',
525			'GH', 'G', None,
526			'GI(AOU)-^', 'I', 'I',
527			'GION-3', 'KIO', 'KIU',
528			'G(CK)-', '', '',
529			'GJ(AEIOU)-^', 'I', 'I',
530			'GMBH^$', 'GMBH', 'GMBH',
531			'GNAC$', 'NIAK', 'NIAK',
532			'GNON$', 'NION', 'NIUN',
533			'GN$', 'N', 'N',
534			'GONCAL-^', 'GONZA', 'KUNZA',
535			'GRY9^', 'GRÜ', None,
536			'G(SßXZ)-<', 'K', 'K',
537			'GUCK-', 'KU', 'KU',
538			'GUISEP-^', 'IUSE', 'IUZE',
539			'GUI-^', 'G', 'K',
540			'GUTAUSSEH------^', 'GUT ', 'KUT ',
541			'GUTGEHEND------^', 'GUT ', 'KUT ',
542			'GY9^', 'GÜ', None,
543			'G(AÄEILOÖRUÜY)-', 'G', None,
544			'G(ÀÁÂÃÅÈÉÊÌÍÎÙÚÛ)-', 'G', None,
545			'G\'S$', 'X', 'X',
546			'G´S$', 'X', 'X',
547			'G^', 'G', None,
548			'G', 'K', 'K',
549			'HA(HIUY)--1', 'H', None,
550			'HANDVOL---^', 'HANT ', 'ANT ',
551			'HANNOVE-^', 'HANOF', None,
552			'HAVEN7$', 'HAFN', None,
553			'HEAD-', 'HE', 'E',
554			'HELIEGEN------', 'E ', 'E ',
555			'HESTEHEN------', 'E ', 'E ',
556			'HE(LMNRST)-3^', 'HE', 'E',
557			'HE(LMN)-1', 'E', 'E',
558			'HEUR1$', 'ÖR', 'ÖR',
559			'HE(HIUY)--1', 'H', None,
560			'HIH(AÄEIOÖUÜY)-1', 'IH', None,
561			'HLH(AÄEIOÖUÜY)-1', 'LH', None,
562			'HMH(AÄEIOÖUÜY)-1', 'MH', None,
563			'HNH(AÄEIOÖUÜY)-1', 'NH', None,
564			'HOBBY9^', 'HOBI', None,
565			'HOCHBEGAB-----^', 'HOCH ', 'UK ',
566			'HOCHTALEN-----^', 'HOCH ', 'UK ',
567			'HOCHZUFRI-----^', 'HOCH ', 'UK ',
568			'HO(HIY)--1', 'H', None,
569			'HRH(AÄEIOÖUÜY)-1', 'RH', None,
570			'HUH(AÄEIOÖUÜY)-1', 'UH', None,
571			'HUIS^^', 'HÜS', 'IZ',
572			'HUIS$', 'ÜS', 'IZ',
573			'HUI--1', 'H', None,
574			'HYGIEN^', 'HÜKIEN', None,
575			'HY9^', 'HÜ', None,
576			'HY(BDGMNPST)-', 'Ü', None,
577			'H.^', None, 'H.',
578			'HÄU--1', 'H', None,
579			'H^', 'H', '',
580			'H', '', '',
581			'ICHELL---', 'ISH', 'IZ',
582			'ICHI$', 'ISHI', 'IZI',
583			'IEC$', 'IZ', 'IZ',
584			'IEDENSTELLE------', 'IDN ', 'ITN ',
585			'IEI-3', '', '',
586			'IELL3', 'IEL', 'IEL',
587			'IENNE$', 'IN', 'IN',
588			'IERRE$', 'IER', 'IER',
589			'IERZULAN---', 'IR ZU ', 'IR ZU ',
590			'IETTE$', 'IT', 'IT',
591			'IEU', 'IÖ', 'IÖ',
592			'IE<4', 'I', 'I',
593			'IGL-1', 'IK', None,
594			'IGHT3$', 'EIT', 'EIT',
595			'IGNI(EO)-', 'INI', 'INI',
596			'IGN(AEOU)-$', 'INI', 'INI',
597			'IHER(DGLKRT)--1', 'IHE', None,
598			'IHE(IUY)--', 'IH', None,
599			'IH(AIOÖUÜY)-', 'IH', None,
600			'IJ(AOU)-', 'I', 'I',
601			'IJ$', 'I', 'I',
602			'IJ<', 'EI', 'EI',
603			'IKOLE$', 'IKOL', 'IKUL',
604			'ILLAN(STZ)--4', 'ILIA', 'ILIA',
605			'ILLAR(DT)--4', 'ILIA', 'ILIA',
606			'IMSTAN----^', 'IM ', 'IN ',
607			'INDELERREGE------', 'INDL ', 'INTL ',
608			'INFRAGE-----^$', 'IN ', 'IN ',
609			'INTERN(AOU)-^', 'INTAN', 'INTAN',
610			'INVER-', 'INWE', 'INFE',
611			'ITI(AÄIOÖUÜ)-', 'IZI', 'IZI',
612			'IUSZ$', 'IUS', None,
613			'IUTZ$', 'IUS', None,
614			'IUZ$', 'IUS', None,
615			'IVER--<', 'IW', None,
616			'IVIER$', 'IWIE', 'IFIE',
617			'IV(ÄOÖUÜ)-', 'IW', None,
618			'IV<3', 'IW', None,
619			'IY2', 'I', None,
620			'I(ÈÉÊ)<4', 'I', 'I',
621			'JAVIE---<^', 'ZA', 'ZA',
622			'JEANS^$', 'JINS', 'INZ',
623			'JEANNE^$', 'IAN', 'IAN',
624			'JEAN-^', 'IA', 'IA',
625			'JER-^', 'IE', 'IE',
626			'JE(LMNST)-', 'IE', 'IE',
627			'JI^', 'JI', None,
628			'JOR(GK)^$', 'IÖRK', 'IÖRK',
629			'J', 'I', 'I',
630			'KC(ÄEIJ)-', 'X', 'X',
631			'KD', 'KT', None,
632			'KE(LMNRST)-3^', 'KE', 'KE',
633			'KG(AÄEILOÖRUÜY)-', 'K', None,
634			'KH<^', 'K', 'K',
635			'KIC$', 'KIZ', 'KIZ',
636			'KLE(LMNRST)-3^', 'KLE', 'KLE',
637			'KOTELE-^', 'KOTL', 'KUTL',
638			'KREAT-^', 'KREA', 'KREA',
639			'KRÜS(TZ)--^', 'KRI', None,
640			'KRYS(TZ)--^', 'KRI', None,
641			'KRY9^', 'KRÜ', None,
642			'KSCH---', 'K', 'K',
643			'KSH--', 'K', 'K',
644			'K(SßXZ)7', 'X', 'X', # implies 'KST' -> 'XT'
645			'KT\'S$', 'X', 'X',
646			'KTI(AIOU)-3', 'XI', 'XI',
647			'KT(SßXZ)', 'X', 'X',
648			'KY9^', 'KÜ', None,
649			'K\'S$', 'X', 'X',
650			'K´S$', 'X', 'X',
651			'LANGES$', ' LANGES', ' LANKEZ',
652			'LANGE$', ' LANGE', ' LANKE',
653			'LANG$', ' LANK', ' LANK',
654			'LARVE-', 'LARF', 'LARF',
655			'LD(SßZ)$', 'LS', 'LZ',
656			'LD\'S$', 'LS', 'LZ',
657			'LD´S$', 'LS', 'LZ',
658			'LEAND-^', 'LEAN', 'LEAN',
659			'LEERSTEHE-----^', 'LER ', 'LER ',
660			'LEICHBLEIB-----', 'LEICH ', 'LEIK ',
661			'LEICHLAUTE-----', 'LEICH ', 'LEIK ',
662			'LEIDERREGE------', 'LEIT ', 'LEIT ',
663			'LEIDGEPR----^', 'LEIT ', 'LEIT ',
664			'LEINSTEHE-----', 'LEIN ', 'LEIN ',
665			'LEL-', 'LE', 'LE',
666			'LE(MNRST)-3^', 'LE', 'LE',
667			'LETTE$', 'LET', 'LET',
668			'LFGNAG-', 'LFGAN', 'LFKAN',
669			'LICHERWEIS----', 'LICHA ', 'LIKA ',
670			'LIC$', 'LIZ', 'LIZ',
671			'LIVE^$', 'LEIF', 'LEIF',
672			'LT(SßZ)$', 'LS', 'LZ',
673			'LT\'S$', 'LS', 'LZ',
674			'LT´S$', 'LS', 'LZ',
675			'LUI(GS)--', 'LU', 'LU',
676			'LV(AIO)-', 'LW', None,
677			'LY9^', 'LÜ', None,
678			'LSTS$', 'LS', 'LZ',
679			'LZ(BDFGKLMNPQRSTVWX)-', 'LS', None,
680			'L(SßZ)$', 'LS', None,
681			'MAIR-<', 'MEI', 'NEI',
682			'MANAG-', 'MENE', 'NENE',
683			'MANUEL', 'MANUEL', None,
684			'MASSEU(RS)-', 'MASÖ', 'NAZÖ',
685			'MATCH', 'MESH', 'NEZ',
686			'MAURICE', 'MORIS', 'NURIZ',
687			'MBH^$', 'MBH', 'MBH',
688			'MB(ßZ)$', 'MS', None,
689			'MB(SßTZ)-', 'M', 'N',
690			'MCG9^', 'MAK', 'NAK',
691			'MC9^', 'MAK', 'NAK',
692			'MEMOIR-^', 'MEMOA', 'NENUA',
693			'MERHAVEN$', 'MAHAFN', None,
694			'ME(LMNRST)-3^', 'ME', 'NE',
695			'MEN(STZ)--3', 'ME', None,
696			'MEN$', 'MEN', None,
697			'MIGUEL-', 'MIGE', 'NIKE',
698			'MIKE^$', 'MEIK', 'NEIK',
699			'MITHILFE----^$', 'MIT H', 'NIT ',
700			'MN$', 'M', None,
701			'MN', 'N', 'N',
702			'MPJUTE-', 'MPUT', 'NBUT',
703			'MP(ßZ)$', 'MS', None,
704			'MP(SßTZ)-', 'M', 'N',
705			'MP(BDJLMNPQVW)-', 'MB', 'NB',
706			'MY9^', 'MÜ', None,
707			'M(ßZ)$', 'MS', None,
708			'M´G7^', 'MAK', 'NAK',
709			'M\'G7^', 'MAK', 'NAK',
710			'M´^', 'MAK', 'NAK',
711			'M\'^', 'MAK', 'NAK',
712			'M', None, 'N',
713			'NACH^^', 'NACH', 'NAK',
714			'NADINE', 'NADIN', 'NATIN',
715			'NAIV--', 'NA', 'NA',
716			'NAISE$', 'NESE', 'NEZE',
717			'NAUGENOMM------', 'NAU ', 'NAU ',
718			'NAUSOGUT$', 'NAUSO GUT', 'NAUZU KUT',
719			'NCH$', 'NSH', 'NZ',
720			'NCOISE$', 'SOA', 'ZUA',
721			'NCOIS$', 'SOA', 'ZUA',
722			'NDAR$', 'NDA', 'NTA',
723			'NDERINGEN------', 'NDE ', 'NTE ',
724			'NDRO(CDKTZ)-', 'NTRO', None,
725			'ND(BFGJLMNPQVW)-', 'NT', None,
726			'ND(SßZ)$', 'NS', 'NZ',
727			'ND\'S$', 'NS', 'NZ',
728			'ND´S$', 'NS', 'NZ',
729			'NEBEN^^', 'NEBN', 'NEBN',
730			'NENGELERN------', 'NEN ', 'NEN ',
731			'NENLERN(ET)---', 'NEN LE', 'NEN LE',
732			'NENZULERNE---', 'NEN ZU LE', 'NEN ZU LE',
733			'NE(LMNRST)-3^', 'NE', 'NE',
734			'NEN-3', 'NE', 'NE',
735			'NETTE$', 'NET', 'NET',
736			'NGU^^', 'NU', 'NU',
737			'NG(BDFJLMNPQRTVW)-', 'NK', 'NK',
738			'NH(AUO)-$', 'NI', 'NI',
739			'NICHTSAHNEN-----', 'NIX ', 'NIX ',
740			'NICHTSSAGE----', 'NIX ', 'NIX ',
741			'NICHTS^^', 'NIX', 'NIX',
742			'NICHT^^', 'NICHT', 'NIKT',
743			'NINE$', 'NIN', 'NIN',
744			'NON^^', 'NON', 'NUN',
745			'NOTLEIDE-----^', 'NOT ', 'NUT ',
746			'NOT^^', 'NOT', 'NUT',
747			'NTI(AIOU)-3', 'NZI', 'NZI',
748			'NTIEL--3', 'NZI', 'NZI',
749			'NT(SßZ)$', 'NS', 'NZ',
750			'NT\'S$', 'NS', 'NZ',
751			'NT´S$', 'NS', 'NZ',
752			'NYLON', 'NEILON', 'NEILUN',
753			'NY9^', 'NÜ', None,
754			'NSTZUNEH---', 'NST ZU ', 'NZT ZU ',
755			'NSZ-', 'NS', None,
756			'NSTS$', 'NS', 'NZ',
757			'NZ(BDFGKLMNPQRSTVWX)-', 'NS', None,
758			'N(SßZ)$', 'NS', None,
759			'OBERE-', 'OBER', None,
760			'OBER^^', 'OBA', 'UBA',
761			'OEU2', 'Ö', 'Ö',
762			'OE<2', 'Ö', 'Ö',
763			'OGL-', 'OK', None,
764			'OGNIE-', 'ONI', 'UNI',
765			'OGN(AEOU)-$', 'ONI', 'UNI',
766			'OH(AIOÖUÜY)-', 'OH', None,
767			'OIE$', 'Ö', 'Ö',
768			'OIRE$', 'OA', 'UA',
769			'OIR$', 'OA', 'UA',
770			'OIX', 'OA', 'UA',
771			'OI<3', 'EU', 'EU',
772			'OKAY^$', 'OKE', 'UKE',
773			'OLYN$', 'OLIN', 'ULIN',
774			'OO(DLMZ)-', 'U', None,
775			'OO$', 'U', None,
776			'OO-', '', '',
777			'ORGINAL-----', 'ORI', 'URI',
778			'OTI(AÄOÖUÜ)-', 'OZI', 'UZI',
779			'OUI^', 'WI', 'FI',
780			'OUILLE$', 'ULIE', 'ULIE',
781			'OU(DT)-^', 'AU', 'AU',
782			'OUSE$', 'AUS', 'AUZ',
783			'OUT-', 'AU', 'AU',
784			'OU', 'U', 'U',
785			'O(FV)$', 'AU', 'AU', # due to 'OW$' -> 'AU'
786			'OVER--<', 'OW', None,
787			'OV(AOU)-', 'OW', None,
788			'OW$', 'AU', 'AU',
789			'OWS$', 'OS', 'UZ',
790			'OJ(AÄEIOÖUÜ)--', 'O', 'U',
791			'OYER', 'OIA', None,
792			'OY(AÄEIOÖUÜ)--', 'O', 'U',
793			'O(JY)<', 'EU', 'EU',
794			'OZ$', 'OS', None,
795			'O´^', 'O', 'U',
796			'O\'^', 'O', 'U',
797			'O', None, 'U',
798			'PATIEN--^', 'PAZI', 'PAZI',
799			'PENSIO-^', 'PANSI', 'PANZI',
800			'PE(LMNRST)-3^', 'PE', 'PE',
801			'PFER-^', 'FE', 'FE',
802			'P(FH)<', 'F', 'F',
803			'PIC^$', 'PIK', 'PIK',
804			'PIC$', 'PIZ', 'PIZ',
805			'PIPELINE', 'PEIBLEIN', 'PEIBLEIN',
806			'POLYP-', 'POLÜ', None,
807			'POLY^^', 'POLI', 'PULI',
808			'PORTRAIT7', 'PORTRE', 'PURTRE',
809			'POWER7', 'PAUA', 'PAUA',
810			'PP(FH)--<', 'B', 'B',
811			'PP-', '', '',
812			'PRODUZ-^', 'PRODU', 'BRUTU',
813			'PRODUZI--', ' PRODU', ' BRUTU',
814			'PRIX^$', 'PRI', 'PRI',
815			'PS-^^', 'P', None,
816			'P(SßZ)^', None, 'Z',
817			'P(SßZ)$', 'BS', None,
818			'PT-^', '', '',
819			'PTI(AÄOÖUÜ)-3', 'BZI', 'BZI',
820			'PY9^', 'PÜ', None,
821			'P(AÄEIOÖRUÜY)-', 'P', 'P',
822			'P(ÀÁÂÃÅÈÉÊÌÍÎÙÚÛ)-', 'P', None,
823			'P.^', None, 'P.',
824			'P^', 'P', None,
825			'P', 'B', 'B',
826			'QI-', 'Z', 'Z',
827			'QUARANT--', 'KARA', 'KARA',
828			'QUE(LMNRST)-3', 'KWE', 'KFE',
829			'QUE$', 'K', 'K',
830			'QUI(NS)$', 'KI', 'KI',
831			'QUIZ7', 'KWIS', None,
832			'Q(UV)7', 'KW', 'KF',
833			'Q<', 'K', 'K',
834			'RADFAHR----', 'RAT ', 'RAT ',
835			'RAEFTEZEHRE-----', 'REFTE ', 'REFTE ',
836			'RCH', 'RCH', 'RK',
837			'REA(DU)---3^', 'R', None,
838			'REBSERZEUG------', 'REBS ', 'REBZ ',
839			'RECHERCH^', 'RESHASH', 'REZAZ',
840			'RECYCL--', 'RIZEI', 'RIZEI',
841			'RE(ALST)-3^', 'RE', None,
842			'REE$', 'RI', 'RI',
843			'RER$', 'RA', 'RA',
844			'RE(MNR)-4', 'RE', 'RE',
845			'RETTE$', 'RET', 'RET',
846			'REUZ$', 'REUZ', None,
847			'REW$', 'RU', 'RU',
848			'RH<^', 'R', 'R',
849			'RJA(MN)--', 'RI', 'RI',
850			'ROWD-^', 'RAU', 'RAU',
851			'RTEMONNAIE-', 'RTMON', 'RTNUN',
852			'RTI(AÄOÖUÜ)-3', 'RZI', 'RZI',
853			'RTIEL--3', 'RZI', 'RZI',
854			'RV(AEOU)-3', 'RW', None,
855			'RY(KN)-$', 'RI', 'RI',
856			'RY9^', 'RÜ', None,
857			'RÄFTEZEHRE-----', 'REFTE ', 'REFTE ',
858			'SAISO-^', 'SES', 'ZEZ',
859			'SAFE^$', 'SEIF', 'ZEIF',
860			'SAUCE-^', 'SOS', 'ZUZ',
861			'SCHLAGGEBEN-----<', 'SHLAK ', 'ZLAK ',
862			'SCHSCH---7', '', '',
863			'SCHTSCH', 'SH', 'Z',
864			'SC(HZ)<', 'SH', 'Z',
865			'SC', 'SK', 'ZK',
866			'SELBSTST--7^^', 'SELB', 'ZELB',
867			'SELBST7^^', 'SELBST', 'ZELBZT',
868			'SERVICE7^', 'SÖRWIS', 'ZÖRFIZ',
869			'SERVI-^', 'SERW', None,
870			'SE(LMNRST)-3^', 'SE', 'ZE',
871			'SETTE$', 'SET', 'ZET',
872			'SHP-^', 'S', 'Z',
873			'SHST', 'SHT', 'ZT',
874			'SHTSH', 'SH', 'Z',
875			'SHT', 'ST', 'Z',
876			'SHY9^', 'SHÜ', None,
877			'SH^^', 'SH', None,
878			'SH3', 'SH', 'Z',
879			'SICHERGEGAN-----^', 'SICHA ', 'ZIKA ',
880			'SICHERGEHE----^', 'SICHA ', 'ZIKA ',
881			'SICHERGESTEL------^', 'SICHA ', 'ZIKA ',
882			'SICHERSTELL-----^', 'SICHA ', 'ZIKA ',
883			'SICHERZU(GS)--^', 'SICHA ZU ', 'ZIKA ZU ',
884			'SIEGLI-^', 'SIKL', 'ZIKL',
885			'SIGLI-^', 'SIKL', 'ZIKL',
886			'SIGHT', 'SEIT', 'ZEIT',
887			'SIGN', 'SEIN', 'ZEIN',
888			'SKI(NPZ)-', 'SKI', 'ZKI',
889			'SKI<^', 'SHI', 'ZI',
890			'SODASS^$', 'SO DAS', 'ZU TAZ',
891			'SODAß^$', 'SO DAS', 'ZU TAZ',
892			'SOGENAN--^', 'SO GEN', 'ZU KEN',
893			'SOUND-', 'SAUN', 'ZAUN',
894			'STAATS^^', 'STAZ', 'ZTAZ',
895			'STADT^^', 'STAT', 'ZTAT',
896			'STANDE$', ' STANDE', ' ZTANTE',
897			'START^^', 'START', 'ZTART',
898			'STAURANT7', 'STORAN', 'ZTURAN',
899			'STEAK-', 'STE', 'ZTE',
900			'STEPHEN-^$', 'STEW', None,
901			'STERN', 'STERN', None,
902			'STRAF^^', 'STRAF', 'ZTRAF',
903			'ST\'S$', 'Z', 'Z',
904			'ST´S$', 'Z', 'Z',
905			'STST--', '', '',
906			'STS(ACEÈÉÊHIÌÍÎOUÄÜÖ)--', 'ST', 'ZT',
907			'ST(SZ)', 'Z', 'Z',
908			'SPAREN---^', 'SPA', 'ZPA',
909			'SPAREND----', ' SPA', ' ZPA',
910			'S(PTW)-^^', 'S', None,
911			'SP', 'SP', None,
912			'STYN(AE)-$', 'STIN', 'ZTIN',
913			'ST', 'ST', 'ZT',
914			'SUITE<', 'SIUT', 'ZIUT',
915			'SUKE--$', 'S', 'Z',
916			'SURF(EI)-', 'SÖRF', 'ZÖRF',
917			'SV(AEÈÉÊIÌÍÎOU)-<^', 'SW', None,
918			'SYB(IY)--^', 'SIB', None,
919			'SYL(KVW)--^', 'SI', None,
920			'SY9^', 'SÜ', None,
921			'SZE(NPT)-^', 'ZE', 'ZE',
922			'SZI(ELN)-^', 'ZI', 'ZI',
923			'SZCZ<', 'SH', 'Z',
924			'SZT<', 'ST', 'ZT',
925			'SZ<3', 'SH', 'Z',
926			'SÜL(KVW)--^', 'SI', None,
927			'S', None, 'Z',
928			'TCH', 'SH', 'Z',
929			'TD(AÄEIOÖRUÜY)-', 'T', None,
930			'TD(ÀÁÂÃÅÈÉÊËÌÍÎÏÒÓÔÕØÙÚÛÝŸ)-', 'T', None,
931			'TEAT-^', 'TEA', 'TEA',
932			'TERRAI7^', 'TERA', 'TERA',
933			'TE(LMNRST)-3^', 'TE', 'TE',
934			'TH<', 'T', 'T',
935			'TICHT-', 'TIK', 'TIK',
936			'TICH$', 'TIK', 'TIK',
937			'TIC$', 'TIZ', 'TIZ',
938			'TIGGESTELL-------', 'TIK ', 'TIK ',
939			'TIGSTELL-----', 'TIK ', 'TIK ',
940			'TOAS-^', 'TO', 'TU',
941			'TOILET-', 'TOLE', 'TULE',
942			'TOIN-', 'TOA', 'TUA',
943			'TRAECHTI-^', 'TRECHT', 'TREKT',
944			'TRAECHTIG--', ' TRECHT', ' TREKT',
945			'TRAINI-', 'TREN', 'TREN',
946			'TRÄCHTI-^', 'TRECHT', 'TREKT',
947			'TRÄCHTIG--', ' TRECHT', ' TREKT',
948			'TSCH', 'SH', 'Z',
949			'TSH', 'SH', 'Z',
950			'TST', 'ZT', 'ZT',
951			'T(Sß)', 'Z', 'Z',
952			'TT(SZ)--<', '', '',
953			'TT9', 'T', 'T',
954			'TV^$', 'TV', 'TV',
955			'TX(AEIOU)-3', 'SH', 'Z',
956			'TY9^', 'TÜ', None,
957			'TZ-', '', '',
958			'T\'S3$', 'Z', 'Z',
959			'T´S3$', 'Z', 'Z',
960			'UEBEL(GNRW)-^^', 'ÜBL ', 'IBL ',
961			'UEBER^^', 'ÜBA', 'IBA',
962			'UE2', 'Ü', 'I',
963			'UGL-', 'UK', None,
964			'UH(AOÖUÜY)-', 'UH', None,
965			'UIE$', 'Ü', 'I',
966			'UM^^', 'UM', 'UN',
967			'UNTERE--3', 'UNTE', 'UNTE',
968			'UNTER^^', 'UNTA', 'UNTA',
969			'UNVER^^', 'UNFA', 'UNFA',
970			'UN^^', 'UN', 'UN',
971			'UTI(AÄOÖUÜ)-', 'UZI', 'UZI',
972			'UVE-4', 'UW', None,
973			'UY2', 'UI', None,
974			'UZZ', 'AS', 'AZ',
975			'VACL-^', 'WAZ', 'FAZ',
976			'VAC$', 'WAZ', 'FAZ',
977			'VAN DEN ^', 'FANDN', 'FANTN',
978			'VANES-^', 'WANE', None,
979			'VATRO-', 'WATR', None,
980			'VA(DHJNT)--^', 'F', None,
981			'VEDD-^', 'FE', 'FE',
982			'VE(BEHIU)--^', 'F', None,
983			'VEL(BDLMNT)-^', 'FEL', None,
984			'VENTZ-^', 'FEN', None,
985			'VEN(NRSZ)-^', 'FEN', None,
986			'VER(AB)-^$', 'WER', None,
987			'VERBAL^$', 'WERBAL', None,
988			'VERBAL(EINS)-^', 'WERBAL', None,
989			'VERTEBR--', 'WERTE', None,
990			'VEREIN-----', 'F', None,
991			'VEREN(AEIOU)-^', 'WEREN', None,
992			'VERIFI', 'WERIFI', None,
993			'VERON(AEIOU)-^', 'WERON', None,
994			'VERSEN^', 'FERSN', 'FAZN',
995			'VERSIERT--^', 'WERSI', None,
996			'VERSIO--^', 'WERS', None,
997			'VERSUS', 'WERSUS', None,
998			'VERTI(GK)-', 'WERTI', None,
999			'VER^^', 'FER', 'FA',
1000			'VERSPRECHE-------', ' FER', ' FA',
1001			'VER$', 'WA', None,
1002			'VER', 'FA', 'FA',
1003			'VET(HT)-^', 'FET', 'FET',
1004			'VETTE$', 'WET', 'FET',
1005			'VE^', 'WE', None,
1006			'VIC$', 'WIZ', 'FIZ',
1007			'VIELSAGE----', 'FIL ', 'FIL ',
1008			'VIEL', 'FIL', 'FIL',
1009			'VIEW', 'WIU', 'FIU',
1010			'VILL(AE)-', 'WIL', None,
1011			'VIS(ACEIKUVWZ)-<^', 'WIS', None,
1012			'VI(ELS)--^', 'F', None,
1013			'VILLON--', 'WILI', 'FILI',
1014			'VIZE^^', 'FIZE', 'FIZE',
1015			'VLIE--^', 'FL', None,
1016			'VL(AEIOU)--', 'W', None,
1017			'VOKA-^', 'WOK', None,
1018			'VOL(ATUVW)--^', 'WO', None,
1019			'VOR^^', 'FOR', 'FUR',
1020			'VR(AEIOU)--', 'W', None,
1021			'VV9', 'W', None,
1022			'VY9^', 'WÜ', 'FI',
1023			'V(ÜY)-', 'W', None,
1024			'V(ÀÁÂÃÅÈÉÊÌÍÎÙÚÛ)-', 'W', None,
1025			'V(AEIJLRU)-<', 'W', None,
1026			'V.^', 'V.', None,
1027			'V<', 'F', 'F',
1028			'WEITERENTWI-----^', 'WEITA ', 'FEITA ',
1029			'WEITREICH-----^', 'WEIT ', 'FEIT ',
1030			'WEITVER^', 'WEIT FER', 'FEIT FA',
1031			'WE(LMNRST)-3^', 'WE', 'FE',
1032			'WER(DST)-', 'WER', None,
1033			'WIC$', 'WIZ', 'FIZ',
1034			'WIEDERU--', 'WIDE', 'FITE',
1035			'WIEDER^$', 'WIDA', 'FITA',
1036			'WIEDER^^', 'WIDA ', 'FITA ',
1037			'WIEVIEL', 'WI FIL', 'FI FIL',
1038			'WISUEL', 'WISUEL', None,
1039			'WR-^', 'W', None,
1040			'WY9^', 'WÜ', 'FI',
1041			'W(BDFGJKLMNPQRSTZ)-', 'F', None,
1042			'W$', 'F', None,
1043			'W', None, 'F',
1044			'X<^', 'Z', 'Z',
1045			'XHAVEN$', 'XAFN', None,
1046			'X(CSZ)', 'X', 'X',
1047			'XTS(CH)--', 'XT', 'XT',
1048			'XT(SZ)', 'Z', 'Z',
1049			'YE(LMNRST)-3^', 'IE', 'IE',
1050			'YE-3', 'I', 'I',
1051			'YOR(GK)^$', 'IÖRK', 'IÖRK',
1052			'Y(AOU)-<7', 'I', 'I',
1053			'Y(BKLMNPRSTX)-1', 'Ü', None,
1054			'YVES^$', 'IF', 'IF',
1055			'YVONNE^$', 'IWON', 'IFUN',
1056			'Y.^', 'Y.', None,
1057			'Y', 'I', 'I',
1058			'ZC(AOU)-', 'SK', 'ZK',
1059			'ZE(LMNRST)-3^', 'ZE', 'ZE',
1060			'ZIEJ$', 'ZI', 'ZI',
1061			'ZIGERJA(HR)-3', 'ZIGA IA', 'ZIKA IA',
1062			'ZL(AEIOU)-', 'SL', None,
1063			'ZS(CHT)--', '', '',
1064			'ZS', 'SH', 'Z',
1065			'ZUERST', 'ZUERST', 'ZUERST',
1066			'ZUGRUNDE^$', 'ZU GRUNDE', 'ZU KRUNTE',
1067			'ZUGRUNDE', 'ZU GRUNDE ', 'ZU KRUNTE ',
1068			'ZUGUNSTEN', 'ZU GUNSTN', 'ZU KUNZTN',
1069			'ZUHAUSE-', 'ZU HAUS', 'ZU AUZ',
1070			'ZULASTEN^$', 'ZU LASTN', 'ZU LAZTN',
1071			'ZURUECK^^', 'ZURÜK', 'ZURIK',
1072			'ZURZEIT', 'ZUR ZEIT', 'ZUR ZEIT',
1073			'ZURÜCK^^', 'ZURÜK', 'ZURIK',
1074			'ZUSTANDE', 'ZU STANDE', 'ZU ZTANTE',
1075			'ZUTAGE', 'ZU TAGE', 'ZU TAKE',
1076			'ZUVER^^', 'ZUFA', 'ZUFA',
1077			'ZUVIEL', 'ZU FIL', 'ZU FIL',
1078			'ZUWENIG', 'ZU WENIK', 'ZU FENIK',
1079			'ZY9^', 'ZÜ', None,
1080			'ZYK3$', 'ZIK', None,
1081			'Z(VW)7^', 'SW', None,
1082			None, None, None)
1083
1084			phonet_hash = Counter()
1085			alpha_pos = Counter()
1086
1087			phonet_hash_1 = Counter()
1088			phonet_hash_2 = Counter()
1089
1090			_phonet_upper_translation = dict(zip((ord(_) for _ in
			0 ignored issues – show Comprehensibility Best Practice introduced 2018-08-02 19:04 UTC by Report Bug Copy Issue Report The variable `_` does not seem to be defined. Loading history...
1091			'abcdefghijklmnopqrstuvwxyzàáâãåäæ' +
1092			'çðèéêëìíîïñòóôõöøœšßþùúûüýÿ'),
1093			'ABCDEFGHIJKLMNOPQRSTUVWXYZÀÁÂÃÅÄÆ' +
1094			'ÇÐÈÉÊËÌÍÎÏÑÒÓÔÕÖØŒŠßÞÙÚÛÜÝŸ'))
1095
1096			def _initialize_phonet(lang):
1097			"""Initialize phonet variables."""
1098			if lang == 'none':
1099			_phonet_rules = _phonet_rules_no_lang
1100			else:
1101			_phonet_rules = _phonet_rules_german
1102
1103			phonet_hash[''] = -1
1104
1105			# German and international umlauts
1106			for j in {'À', 'Á', 'Â', 'Ã', 'Ä', 'Å', 'Æ', 'Ç', 'È', 'É', 'Ê', 'Ë',
1107			'Ì', 'Í', 'Î', 'Ï', 'Ð', 'Ñ', 'Ò', 'Ó', 'Ô', 'Õ', 'Ö', 'Ø',
1108			'Ù', 'Ú', 'Û', 'Ü', 'Ý', 'Þ', 'ß', 'Œ', 'Š', 'Ÿ'}:
1109			alpha_pos[j] = 1
1110			phonet_hash[j] = -1
1111
1112			# "normal" letters ('A'-'Z')
1113			for i, j in enumerate('ABCDEFGHIJKLMNOPQRSTUVWXYZ'):
1114			alpha_pos[j] = i + 2
1115			phonet_hash[j] = -1
1116
1117			for i in range(26):
1118			for j in range(28):
1119			phonet_hash_1[i, j] = -1
1120			phonet_hash_2[i, j] = -1
1121
1122			# for each phonetc rule
1123			for i in range(len(_phonet_rules)):
1124			rule = _phonet_rules[i]
1125
1126			if rule and i % 3 == 0:
1127			# calculate first hash value
1128			k = _phonet_rules[i][0]
1129
1130			if phonet_hash[k] < 0 and (_phonet_rules[i+1] or
			0 ignored issues – show Comprehensibility Best Practice introduced 2018-08-02 19:04 UTC by Report Bug Copy Issue Report The variable `phonet_hash` does not seem to be defined. Loading history...
1131			_phonet_rules[i+2]):
1132			phonet_hash[k] = i
1133
1134			# calculate second hash values
1135			if k and alpha_pos[k] >= 2:
			0 ignored issues – show Comprehensibility Best Practice introduced 2018-08-02 19:04 UTC by Report Bug Copy Issue Report The variable `alpha_pos` does not seem to be defined. Loading history...
1136			k = alpha_pos[k]
1137
1138			j = k-2
1139			rule = rule[1:]
1140
1141			if not rule:
1142			rule = ' '
1143			elif rule[0] == '(':
1144			rule = rule[1:]
1145			else:
1146			rule = rule[0]
1147
1148			while rule and (rule[0] != ')'):
1149			k = alpha_pos[rule[0]]
1150
1151			if k > 0:
1152			# add hash value for this letter
1153			if phonet_hash_1[j, k] < 0:
			0 ignored issues – show Comprehensibility Best Practice introduced 2018-08-02 19:04 UTC by Report Bug Copy Issue Report The variable `phonet_hash_1` does not seem to be defined. Loading history...
1154			phonet_hash_1[j, k] = i
1155			phonet_hash_2[j, k] = i
1156
1157			if phonet_hash_2[j, k] >= (i-30):
			0 ignored issues – show Comprehensibility Best Practice introduced 2018-08-02 19:04 UTC by Report Bug Copy Issue Report The variable `phonet_hash_2` does not seem to be defined. Loading history...
1158			phonet_hash_2[j, k] = i
1159			else:
1160			k = -1
1161
1162			if k <= 0:
1163			# add hash value for all letters
1164			if phonet_hash_1[j, 0] < 0:
1165			phonet_hash_1[j, 0] = i
1166
1167			phonet_hash_2[j, 0] = i
1168
1169			rule = rule[1:]
1170
1171			def _phonet(term, mode, lang):
1172			"""Return the phonet coded form of a term."""
1173			if lang == 'none':
1174			_phonet_rules = _phonet_rules_no_lang
1175			else:
1176			_phonet_rules = _phonet_rules_german
1177
1178			char0 = ''
1179			dest = term
1180
1181			if not term:
1182			return ''
1183
1184			term_length = len(term)
1185
1186			# convert input string to upper-case
1187			src = term.translate(_phonet_upper_translation)
1188
1189			# check "src"
1190			i = 0
1191			j = 0
1192			zeta = 0
1193
1194			while i < len(src):
1195			char = src[i]
1196
1197			pos = alpha_pos[char]
1198
1199			if pos >= 2:
1200			xpos = pos-2
1201
1202			if i+1 == len(src):
1203			pos = alpha_pos['']
1204			else:
1205			pos = alpha_pos[src[i+1]]
1206
1207			start1 = phonet_hash_1[xpos, pos]
1208			start2 = phonet_hash_1[xpos, 0]
1209			end1 = phonet_hash_2[xpos, pos]
1210			end2 = phonet_hash_2[xpos, 0]
1211
1212			# preserve rule priorities
1213			if (start2 >= 0) and ((start1 < 0) or (start2 < start1)):
1214			pos = start1
1215			start1 = start2
1216			start2 = pos
1217			pos = end1
1218			end1 = end2
1219			end2 = pos
1220
1221			if (end1 >= start2) and (start2 >= 0):
1222			if end2 > end1:
1223			end1 = end2
1224
1225			start2 = -1
1226			end2 = -1
1227			else:
1228			pos = phonet_hash[char]
1229			start1 = pos
1230			end1 = 10000
1231			start2 = -1
1232			end2 = -1
1233
1234			pos = start1
1235			zeta0 = 0
1236
1237			if pos >= 0:
1238			# check rules for this char
1239			while ((_phonet_rules[pos] is None) or
1240			(_phonet_rules[pos][0] == char)):
1241			if pos > end1:
1242			if start2 > 0:
1243			pos = start2
1244			start1 = start2
1245			start2 = -1
1246			end1 = end2
1247			end2 = -1
1248			continue
1249
1250			break
1251
1252			if (((_phonet_rules[pos] is None) or
1253			(_phonet_rules[pos + mode] is None))):
1254			# no conversion rule available
1255			pos += 3
1256			continue
1257
1258			# check whole string
1259			matches = 1 # number of matching letters
1260			priority = 5 # default priority
1261			rule = _phonet_rules[pos]
1262			rule = rule[1:]
1263
1264			while (rule and
1265			(len(src) > (i + matches)) and
1266			(src[i + matches] == rule[0]) and
1267			not rule[0].isdigit() and
1268			(rule not in '(-<^$')):
1269			matches += 1
1270			rule = rule[1:]
1271
1272			if rule and (rule[0] == '('):
1273			# check an array of letters
1274			if (((len(src) > (i + matches)) and
1275			src[i + matches].isalpha() and
1276			(src[i + matches] in rule[1:]))):
1277			matches += 1
1278
1279			while rule and rule[0] != ')':
1280			rule = rule[1:]
1281
1282			# if rule[0] == ')':
1283			rule = rule[1:]
1284
1285			if rule:
1286			priority0 = ord(rule[0])
1287			else:
1288			priority0 = 0
1289
1290			matches0 = matches
1291
1292			while rule and rule[0] == '-' and matches > 1:
1293			matches -= 1
1294			rule = rule[1:]
1295
1296			if rule and rule[0] == '<':
1297			rule = rule[1:]
1298
1299			if rule and rule[0].isdigit():
1300			# read priority
1301			priority = int(rule[0])
1302			rule = rule[1:]
1303
1304			if rule and rule[0:2] == '^^':
1305			rule = rule[1:]
1306
1307			if (not rule or
1308			((rule[0] == '^') and
1309			((i == 0) or not src[i-1].isalpha()) and
1310			((rule[1:2] != '$') or
1311			(not (src[i+matches0:i+matches0+1].isalpha()) and
1312			(src[i+matches0:i+matches0+1] != '.')))) or
1313			((rule[0] == '$') and (i > 0) and
1314			src[i-1].isalpha() and
1315			((not src[i+matches0:i+matches0+1].isalpha()) and
1316			(src[i+matches0:i+matches0+1] != '.')))):
1317			# look for continuation, if:
1318			# matches > 1 und NO '-' in first string */
1319			pos0 = -1
1320
1321			start3 = 0
1322			start4 = 0
1323			end3 = 0
1324			end4 = 0
1325
1326			if (((matches > 1) and
1327			src[i+matches:i+matches+1] and
1328			(priority0 != ord('-')))):
1329			char0 = src[i+matches-1]
1330			pos0 = alpha_pos[char0]
1331
1332			if pos0 >= 2 and src[i+matches]:
1333			xpos = pos0 - 2
1334			pos0 = alpha_pos[src[i+matches]]
1335			start3 = phonet_hash_1[xpos, pos0]
1336			start4 = phonet_hash_1[xpos, 0]
1337			end3 = phonet_hash_2[xpos, pos0]
1338			end4 = phonet_hash_2[xpos, 0]
1339
1340			# preserve rule priorities
1341			if (((start4 >= 0) and
1342			((start3 < 0) or (start4 < start3)))):
1343			pos0 = start3
1344			start3 = start4
1345			start4 = pos0
1346			pos0 = end3
1347			end3 = end4
1348			end4 = pos0
1349
1350			if (end3 >= start4) and (start4 >= 0):
1351			if end4 > end3:
1352			end3 = end4
1353
1354			start4 = -1
1355			end4 = -1
1356			else:
1357			pos0 = phonet_hash[char0]
1358			start3 = pos0
1359			end3 = 10000
1360			start4 = -1
1361			end4 = -1
1362
1363			pos0 = start3
1364
1365			# check continuation rules for src[i+matches]
1366			if pos0 >= 0:
1367			while ((_phonet_rules[pos0] is None) or
1368			(_phonet_rules[pos0][0] == char0)):
1369			if pos0 > end3:
1370			if start4 > 0:
1371			pos0 = start4
1372			start3 = start4
1373			start4 = -1
1374			end3 = end4
1375			end4 = -1
1376			continue
1377
1378			priority0 = -1
1379
1380			# important
1381			break
1382
1383			if (((_phonet_rules[pos0] is None) or
1384			(_phonet_rules[pos0 + mode]
1385			is None))):
1386			# no conversion rule available
1387			pos0 += 3
1388			continue
1389
1390			# check whole string
1391			matches0 = matches
1392			priority0 = 5
1393			rule = _phonet_rules[pos0]
1394			rule = rule[1:]
1395
1396			while (rule and
1397			(src[i+matches0:i+matches0+1] ==
1398			rule[0]) and
1399			(not rule[0].isdigit() or
1400			(rule in '(-<^$'))):
1401			matches0 += 1
1402			rule = rule[1:]
1403
1404			if rule and rule[0] == '(':
1405			# check an array of letters
1406			if ((src[i+matches0:i+matches0+1]
1407			.isalpha() and
1408			(src[i+matches0] in rule[1:]))):
1409			matches0 += 1
1410
1411			while rule and rule[0] != ')':
1412			rule = rule[1:]
1413
1414			# if rule[0] == ')':
1415			rule = rule[1:]
1416
1417			while rule and rule[0] == '-':
1418			# "matches0" is NOT decremented
1419			# because of "if (matches0 == matches)"
1420			rule = rule[1:]
1421
1422			if rule and rule[0] == '<':
1423			rule = rule[1:]
1424
1425			if rule and rule[0].isdigit():
1426			priority0 = int(rule[0])
1427			rule = rule[1:]
1428
1429			if (not rule or
1430			# rule == '^' is not possible here
1431			((rule[0] == '$') and not
1432			src[i+matches0:i+matches0+1]
1433			.isalpha() and
1434			(src[i+matches0:i+matches0+1]
1435			!= '.'))):
1436			if matches0 == matches:
1437			# this is only a partial string
1438			pos0 += 3
1439			continue
1440
1441			if priority0 < priority:
1442			# priority is too low
1443			pos0 += 3
1444			continue
1445
1446			# continuation rule found
1447			break
1448
1449			pos0 += 3
1450
1451			# end of "while"
1452			if ((priority0 >= priority) and
1453			((_phonet_rules[pos0] is not None) and
1454			(_phonet_rules[pos0][0] == char0))):
1455
1456			pos += 3
1457			continue
1458
1459			# replace string
1460			if ((_phonet_rules[pos] and
1461			('<' in _phonet_rules[pos][1:]))):
1462			priority0 = 1
1463			else:
1464			priority0 = 0
1465
1466			rule = _phonet_rules[pos + mode]
1467
1468			if (priority0 == 1) and (zeta == 0):
1469			# rule with '<' is applied
1470			if ((j > 0) and rule and
1471			((dest[j-1] == char) or
1472			(dest[j-1] == rule[0]))):
1473			j -= 1
1474
1475			zeta0 = 1
1476			zeta += 1
1477			matches0 = 0
1478
1479			while rule and src[i+matches0]:
1480			src = (src[0:i+matches0] + rule[0] +
1481			src[i+matches0+1:])
1482			matches0 += 1
1483			rule = rule[1:]
1484
1485			if matches0 < matches:
1486			src = (src[0:i+matches0] +
1487			src[i+matches:])
1488
1489			char = src[i]
1490			else:
1491			i = i + matches - 1
1492			zeta = 0
1493
1494			while len(rule) > 1:
1495			if (j == 0) or (dest[j - 1] != rule[0]):
1496			dest = (dest[0:j] + rule[0] +
1497			dest[min(len(dest), j+1):])
1498			j += 1
1499
1500			rule = rule[1:]
1501
1502			# new "current char"
1503			if not rule:
1504			rule = ''
1505			char = ''
1506			else:
1507			char = rule[0]
1508
1509			if ((_phonet_rules[pos] and
1510			'^^' in _phonet_rules[pos][1:])):
1511			if char:
1512			dest = (dest[0:j] + char +
1513			dest[min(len(dest), j + 1):])
1514			j += 1
1515
1516			src = src[i + 1:]
1517			i = 0
1518			zeta0 = 1
1519
1520			break
1521
1522			pos += 3
1523
1524			if pos > end1 and start2 > 0:
1525			pos = start2
1526			start1 = start2
1527			end1 = end2
1528			start2 = -1
1529			end2 = -1
1530
1531			if zeta0 == 0:
1532			if char and ((j == 0) or (dest[j-1] != char)):
1533			# delete multiple letters only
1534			dest = dest[0:j] + char + dest[min(j+1, term_length):]
1535			j += 1
1536
1537			i += 1
1538			zeta = 0
1539
1540			dest = dest[0:j]
1541
1542			return dest
1543
1544			_initialize_phonet(lang)
1545
1546			word = unicode_normalize('NFKC', text_type(word))
1547			return _phonet(word, mode, lang)
1548
1549
1550			if __name__ == '__main__':
1551			import doctest
1552			doctest.testmod()
1553

chrislit / abydos

Push — master ( 64abe2...a464fa )

abydos.phonetic.phonet.phonet() F

Complexity

Size

Duplication

Importance

How to fix Long Method Complexity

Long Method

Complexity

Duplication Side-by-Side

Filter issues like