Commit 78e8cc501860a04eff409542a2d65e5f3f34bcea
1 parent
f7ed7092
Reorganizacja warstwy fonetycznej
Showing
16 changed files
with
1191 additions
and
1718 deletions
morphology/data/alternations.dic
morphology/data/fonetics.dic
0 → 100644
1 | +@symbols | |
2 | +ω a ą e ę o ó u | |
3 | +δ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y z ź ż - ε v x q | |
4 | +#γ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y ź ż - ε | |
5 | +#ξ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y - ε | |
6 | +#μ a ą b c ć d e ę f g k l ł m n ń o ó p r s ś t u w y ź ż - ε | |
7 | +λ b c ć d f g h k l ł m n ń p r s ś t w z ź ż - ε v x q | |
8 | +κ b c ć d f g h i j k l ł m n ń p r s ś t w z ź ż - ε v x q | |
9 | +#σ a ą b c ć d e ę f g j h k l ł m n ń o ó p r s ś t u w y z ź ż - ε | |
10 | +ρ aε achε amiε ąε eε ęε iε oε omε onε umε | |
11 | +α ε goε muε mε | |
12 | +ά ε goε muε | |
13 | +β ε chε miε mε | |
14 | +γ aε achε amiε ąε eε ęε iε oε omε onε umε ówε uε owiε omε emε yε owieε emuε egoε goε mε muε ε | |
15 | + | |
16 | +@rev_symbols | |
17 | +ω a ą e ę o ó u {eu} | |
18 | +δ a ą b c ć č d ʒ ǯ e ę f g h x i k l ł m n ń o ó p r ř s ś š t u v w y z ź ž - ε { | |
19 | +λ b c ć č d ʒ ǯ f g h x k l ł m n ń p r ř s ś š t v w z ź ž - ε { q | |
20 | +κ b c ć č d ʒ ǯ f g h x i j ʲ k l ł m n ń p r ř s ś š t v w z ź ž - ε { | |
21 | +ρ aε axε am′iε ąε eε ęε iε oε omε onε umε | |
22 | + | |
23 | +@rev_rules | |
24 | +core p′ pi ω | |
25 | +core p′ p i | |
26 | +core pj pi ρ | |
27 | +core b′ bi ω | |
28 | +core b′ b i | |
29 | +core bj bi ρ | |
30 | +core m′ mi ω | |
31 | +core m′ m i | |
32 | +core m′j mi ρ | |
33 | +core f′ fi ω | |
34 | +core f′ f i | |
35 | +core fj fi ρ | |
36 | +core v′ wi ω | |
37 | +core v′ w i | |
38 | +core v w δ | |
39 | +core vj wi ρ | |
40 | +#core v w j | |
41 | +core t′ ć λ | |
42 | +core t′ ci ω | |
43 | +core t′ c i | |
44 | +core d′ dź λ | |
45 | +core d′ dzi ω | |
46 | +core d′ dz i | |
47 | +core ʒ dz | |
48 | +core tʲ ti ω | |
49 | +core tʲ t i | |
50 | +core tj ti ρ | |
51 | +core dʲ di ω | |
52 | +core dʲ d i | |
53 | +core dj di ρ | |
54 | +core č cz δ | |
55 | +core čʲ czi ω | |
56 | +core čʲ cz i | |
57 | +core č cz j | |
58 | +core ǯ dż δ | |
59 | +core ǯʲ dżi ω | |
60 | +core ǯʲ dż i | |
61 | +core ǯj dżi ρ | |
62 | +core s′ ś λ | |
63 | +core s′ si ω | |
64 | +core s′ s i | |
65 | +core z′ ź λ | |
66 | +core z′ zi ω | |
67 | +core z′ z i | |
68 | +core š sz δ | |
69 | +core š sz j | |
70 | +core šʲ szi ω | |
71 | +core šʲ sz i | |
72 | +core ž ż δ | |
73 | +core žʲ żi ω | |
74 | +core žʲ ż i | |
75 | +core žj żi ρ | |
76 | +core lʲ li ω | |
77 | +core lj li ρ | |
78 | +core ř rz δ | |
79 | +core ř rz j | |
80 | +core rʲ ri ω | |
81 | +core rʲ r i | |
82 | +core rj ri ρ | |
83 | +core n′ ń λ | |
84 | +core n′ ni ω | |
85 | +core n′ n i | |
86 | +core n′j ni ρ | |
87 | +core k′ ki ω | |
88 | +core k′ k i | |
89 | +core k′j ki ρ | |
90 | +core g′ gi ω | |
91 | +core g′ g i | |
92 | +core g′j gi ρ | |
93 | +core x ch δ | |
94 | +core xʲ chi ω | |
95 | +core xʲ ch i | |
96 | +core xʲj chi ρ | |
97 | +core hʲ hi ω | |
98 | +core hʲ h i | |
99 | +core aʲ a i | |
100 | +core eʲ e i | |
101 | +core oʲ o i | |
102 | +core óʲ ó i | |
103 | +core uʲ u i | |
104 | +core iʲ i i | |
105 | +core yʲ y i | |
106 | + | |
107 | +aux {ch}š ch | |
108 | +aux {q}k q | |
109 | +aux {ng}n ng | |
110 | +aux {tch}č tch | |
111 | +aux {sh}š sh | |
112 | +aux {w}ł w | |
113 | +aux {leigh}l leigh | |
114 | +aux {au}ał au | |
115 | +aux {sch}š sch | |
116 | +aux {tsch}č tsch | |
117 | +aux {z}c z | |
118 | +core {lj}lj lj a | |
119 | +core {lj}lj lj e | |
120 | +core {pj}pj pj e | |
121 | +aux {zs}ž zs ε | |
122 | +aux {cs}č cs ε | |
123 | + | |
124 | +aux {ay}aj ay ε | |
125 | +aux {ey}ej ey ε | |
126 | +aux {oy}oj oy ε | |
127 | +aux {ay}aj ay ω | |
128 | +aux {ey}ej ey ω | |
129 | +aux {oy}oj oy ω | |
130 | +aux {ai}aj ai ε | |
131 | +aux {ai}aj ai ω | |
132 | + | |
133 | +aux {dh}dʲ dhi ω | |
134 | +aux {dh}dʲ dh iκ | |
135 | +aux {dh}d dh δ | |
136 | +aux {gh}g′ ghi ω | |
137 | +aux {gh}g′ gh iκ | |
138 | +aux {gh}g gh δ | |
139 | +aux {kh}k′ khi ω | |
140 | +aux {kh}k′ kh iκ | |
141 | +aux {kh}k kh δ | |
142 | +aux {nh}n′ nhi ω | |
143 | +aux {nh}n′ nh iκ | |
144 | +aux {nh}n nh δ | |
145 | +aux {th}tʲ thi ω | |
146 | +aux {th}tʲ th iκ | |
147 | +aux {th}t th δ | |
148 | +core {v}v′ vi ω | |
149 | +core {v}v′ v iκ | |
150 | +core {v}v v δ | |
151 | +core {v}vj vi ρ | |
152 | +core {x}ks′ xi ω | |
153 | +core {x}ks′ x iκ | |
154 | +core {x}ks x δ | |
155 | + | |
156 | +#lemma=e/y gender=m1 | |
157 | +aux {dieu}dʲe dieu ε | |
158 | +aux {dieu}dʲi dieu ε | |
159 | +aux {quieu}k′e quieu ε | |
160 | +aux {quieu}k′i quieu ε | |
161 | +aux {lieu}lʲe lieu ε | |
162 | +aux {lieu}lʲi lieu ε | |
163 | +aux {rie}rʲe rie ε | |
164 | +aux {rie}rʲi rie ε | |
165 | +aux {gie}ǯʲe gie ε | |
166 | +aux {gie}ǯʲi gie ε | |
167 | +aux {kie}k′e kie ε | |
168 | +aux {kie}k′i kie ε | |
169 | +aux {tie}tʲe tie ε | |
170 | +aux {tie}tʲi tie ε | |
171 | +aux {pie}p′e pie ε | |
172 | +aux {pie}p′i pie ε | |
173 | +aux {die}dʲe die ε | |
174 | +aux {die}dʲi die ε | |
175 | +aux {bee}b′e bee ε | |
176 | +aux {bee}b′i bee ε | |
177 | + | |
178 | +#lemma=e gender=m1 | |
179 | +aux {mée}me mée ε | |
180 | +aux {ge}g′e ge ε | |
181 | +aux {ke}k′e ke ε | |
182 | + | |
183 | +#lemma=y gender=m1 | |
184 | +aux {by}b′i by ε | |
185 | +aux {dy}dʲi dy ε | |
186 | +aux {dí}dʲi dí ε | |
187 | +aux {phy}f′i phy ε | |
188 | +aux {guy}g′i guy ε | |
189 | +aux {ky}k′i ky ε | |
190 | +aux {my}m′i my ε | |
191 | +aux {li}li li ε | |
192 | +aux {ly}li ly ε | |
193 | +aux {ry}rʲi ry ε | |
194 | +core {ři}rʲi ři ε | |
195 | +aux {sy}sʲi sy ε | |
196 | +aux {cy}sʲi cy ε | |
197 | +aux {şi}sʲi şi ε | |
198 | +aux {thy}tʲi thy ε | |
199 | + | |
200 | +#lemma=e/ndm gender=m1 | |
201 | +aux {chais}še chais ε | |
202 | +aux {lais}le lais ε | |
203 | +aux {nais}ne nais ε | |
204 | +aux {rès}re rès ε | |
205 | +aux {rés}re rés ε | |
206 | +aux {ré}re ré ε | |
207 | + | |
208 | +#lemma=ε | |
209 | +aux {de}d de ε | |
210 | +aux {fe}f fe ε | |
211 | +aux {phe}f phe ε | |
212 | +aux {ge}ǯ ge ε | |
213 | +aux {ges}ǯ ges ε | |
214 | +aux {gue}g gue ε | |
215 | +aux {gues}g gues ε | |
216 | +aux {ke}k ke ε | |
217 | +aux {que}k que ε | |
218 | +aux {ques}k ques ε | |
219 | +aux {le}l le ε | |
220 | +aux {les}l les ε | |
221 | +aux {me}m me ε | |
222 | +aux {ne}n ne ε | |
223 | +aux {gne}n′ gne ε | |
224 | +aux {re}r re ε | |
225 | +aux {rue}r rue ε | |
226 | +aux {se}s se ε | |
227 | +aux {ce}s ce ε | |
228 | +aux {che}š che ε | |
229 | +aux {te}t te ε | |
230 | +aux {the}t the ε | |
231 | +aux {ve}v ve ε | |
232 | +aux {we}ł we ε | |
233 | +aux {se}z se ε | |
234 | +aux {ge}ž ge ε | |
235 | +aux {oe}oł oe ε | |
236 | + | |
237 | + | |
238 | +aux g′el gel ε | |
239 | + | |
240 | +aux g′e ge ε | |
241 | +aux k′e ke ε | |
242 | +aux k′i ky ε | |
243 | +aux k′i kij ε | |
244 | +aux k′i koj ε | |
245 | +aux k′i kyj ε | |
246 | + s s k′i | |
247 | +aux sk′i szky ε | |
248 | + l l i | |
249 | +aux li ly ε | |
250 | + | |
251 | +aux ks x ε | |
252 | +aux ks kx ε | |
253 | + | |
254 | + r r a | |
255 | +aux r rh a | |
256 | + t t a | |
257 | +aux t th a | |
258 | + k k | |
259 | +aux k kh a | |
260 | +aux ks x a | |
261 | +aux k c a | |
262 | + n n a | |
263 | +aux n nh a | |
264 | + d d a | |
265 | +aux d dh a | |
266 | + g g a | |
267 | +aux g gh a | |
268 | + | |
269 | +aux k c o | |
270 | +aux kk cc o | |
271 | + | |
272 | + | |
273 | + b b ε | |
274 | +aux b bes ε | |
275 | + d d ε | |
276 | +aux d de ε | |
277 | +aux d dh ε | |
278 | + f f ε | |
279 | +aux f phe ε | |
280 | +aux f ph ε | |
281 | + g g ε | |
282 | +aux g gue ε | |
283 | +aux g gues ε | |
284 | + k k ε | |
285 | +aux k ke ε | |
286 | +aux k c ε | |
287 | +aux k que ε | |
288 | +aux k q ε | |
289 | +aux k cq ε | |
290 | +aux k ques ε | |
291 | +aux k cques ε | |
292 | +aux kt ct ε | |
293 | + m m ε | |
294 | +aux m me ε | |
295 | + n n ε | |
296 | +aux n ne ε | |
297 | +aux n nes ε | |
298 | +aux n ng ε | |
299 | +aux n nh ε | |
300 | + r r ε | |
301 | +aux r re ε | |
302 | +aux r res ε | |
303 | +aux r rs ε | |
304 | +aux r rh ε | |
305 | + s s ε | |
306 | +aux s se ε | |
307 | +aux s ce ε | |
308 | +aux s th ε | |
309 | + t t ε | |
310 | +aux t te ε | |
311 | +aux t tes ε | |
312 | +aux t thes ε | |
313 | +aux t th ε | |
314 | +aux t the ε | |
315 | +aux t tt ε | |
316 | + | |
317 | + e e j | |
318 | +aux ej ey ε | |
319 | + | |
320 | + a a ε | |
321 | +aux a ah ε | |
322 | + a a j | |
323 | +aux aja ayah ε | |
324 | + | |
325 | + o o j | |
326 | +aux oja oya ε | |
327 | + | |
328 | +acro {A}a A | |
329 | +acro {B}b B | |
330 | +acro {C}c C | |
331 | +acro {C}k C | |
332 | +acro {Ć}t′ Ć | |
333 | +acro {D}d D | |
334 | +acro {E}e E | |
335 | +acro {F}f F | |
336 | +acro {G}g G | |
337 | +acro {H}h H | |
338 | +acro {I}j I | |
339 | +acro {J}j J | |
340 | +acro {K}k K | |
341 | +acro {L}l L | |
342 | +acro {Ł}ł Ł | |
343 | +acro {M}m M | |
344 | +acro {N}n N | |
345 | +acro {O}o O | |
346 | +acro {P}p P | |
347 | +acro {R}r R | |
348 | +acro {S}s S | |
349 | +acro {Ś}s′ Ś | |
350 | +acro {T}t T | |
351 | +acro {U}u U | |
352 | +acro {V}v V | |
353 | +acro {W}v W | |
354 | +acro {X}ks X | |
355 | +acro {Y}y Y | |
356 | +acro {Z}z Z | |
357 | +acro {Ż}ž Ż | |
358 | +acro {J}jot J | |
359 | +acro {Z}zet Z | |
360 | +acro {Ż}žet Ż | |
361 | +acro {v}v V | |
362 | +acro {x}ks X | |
363 | +acro {j}jot J | |
364 | +acro {z}zet z | |
365 | +acro {ż}žet Ż | |
366 | + | |
367 | +acro a A ε | |
368 | + | |
369 | +@rules | |
370 | +core p′ pi ω | |
371 | +core p′ p iκ | |
372 | +#core p p δ | |
373 | +#core p p j | |
374 | +core pj pi ρ | |
375 | +core b′ bi ω | |
376 | +core b′ b iκ | |
377 | +#core b b δ | |
378 | +core bj bi ρ | |
379 | +#zbitka | |
380 | +#core b b j | |
381 | +core m′ mi ω | |
382 | +core m′ m iκ | |
383 | +#core m m δ | |
384 | +core m′j mi ρ | |
385 | +core f′ fi ω | |
386 | +core f′ f iκ | |
387 | +#core f f δ | |
388 | +core fj fi ρ | |
389 | +core v′ wi ω | |
390 | +core v′ w iκ | |
391 | +core v w δ | |
392 | +core vj wi ρ | |
393 | +#zbitka | |
394 | +#core v w j | |
395 | +core t′ ć λ | |
396 | +#zbitki | |
397 | +#core t′ ć u | |
398 | +#core t′ ć a | |
399 | +#core t′ ć i | |
400 | +core t′ ci ω | |
401 | +#core c c j | |
402 | +core t′ c iκ | |
403 | +#core c c μ | |
404 | +core d′ dź λ | |
405 | +core d′ dzi ω | |
406 | +core d′ dz iκ | |
407 | +core ʒ dz δ | |
408 | +#zbitka | |
409 | +#core ʒ dz j | |
410 | +#core t t δ | |
411 | +#core t t j | |
412 | +core tʲ ti ω | |
413 | +core tʲ t iκ | |
414 | +core tj ti ρ | |
415 | +#core d d ξ | |
416 | +core dʲ di ω | |
417 | +core dʲ d iκ | |
418 | +#core d d j | |
419 | +core dj di ρ | |
420 | +core č cz δ | |
421 | +core čʲ czi ω | |
422 | +core čʲ cz iκ | |
423 | +#core čʲ cz j | |
424 | +core ǯ dż δ | |
425 | +core ǯʲ dżi ω | |
426 | +core ǯʲ dż iκ | |
427 | +core ǯj dżi ρ | |
428 | +core s′ ś λ | |
429 | +core s′ si ω | |
430 | +#core s s j | |
431 | +core s′ s iκ | |
432 | +#core s s γ | |
433 | +core z′ ź λ | |
434 | +core z′ zi ω | |
435 | +#core z z j | |
436 | +core z′ z iκ | |
437 | +#core z z δ | |
438 | +core š sz δ | |
439 | +#core šʲ sz j | |
440 | +core šʲ szi ω | |
441 | +core šʲ sz iκ | |
442 | +core ž ż δ | |
443 | +core žʲ żi ω | |
444 | +core žʲ ż iκ | |
445 | +core žj żi ρ | |
446 | +#core l l δ | |
447 | +core lʲ li ω | |
448 | +core l l iκ | |
449 | +#core l l j | |
450 | +#core ł ł δ | |
451 | +#zbitka | |
452 | +#core ł ł i | |
453 | +#zbitka | |
454 | +#core ł ł j | |
455 | +core lj li ρ | |
456 | +core ř rz δ | |
457 | +#zbitka | |
458 | +#core ř rz j | |
459 | +core r r zi | |
460 | +#core r r γ | |
461 | +#core r r j | |
462 | +core rʲ ri ω | |
463 | +core rʲ r iκ | |
464 | +core rj ri ρ | |
465 | +core n′ ń λ | |
466 | +core n′ ni ω | |
467 | +core n′ n iκ | |
468 | +#core n n δ | |
469 | +#core n n j | |
470 | +core n′j ni ρ | |
471 | +core k′ ki ω | |
472 | +core k′ k iκ | |
473 | +#core k k δ | |
474 | +#core k k j | |
475 | +core k′j ki ρ | |
476 | +core g′ gi ω | |
477 | +core g′ g iκ | |
478 | +#core g g δ | |
479 | +core g′j gi ρ | |
480 | +core x ch δ | |
481 | +core xʲ chi ω | |
482 | +core xʲ ch iκ | |
483 | +core xʲj chi ρ | |
484 | +#core h h δ | |
485 | +core hʲ hi ω | |
486 | +core hʲ h iκ | |
487 | +core mar mar z | |
488 | +core m′er mier z | |
489 | +core n′e nie i | |
490 | +#core a a σ | |
491 | +core aʲ a i | |
492 | +#core a a i | |
493 | +#core e e σ | |
494 | +core eʲ e i | |
495 | +#core e e i | |
496 | +#core o o σ | |
497 | +core oʲ o i | |
498 | +#core o o i | |
499 | +#core ó ó σ | |
500 | +core óʲ ó i | |
501 | +#core ó ó i | |
502 | +#core u u σ | |
503 | +core uʲ u i | |
504 | +#core u u i | |
505 | +#core i i σ | |
506 | +core iʲ i i | |
507 | +#core i i i | |
508 | +#core y y σ | |
509 | +core yʲ y i | |
510 | +#core y y i | |
511 | +#core ą ą σ | |
512 | +#core ę ę σ | |
513 | +#core j j | |
514 | +#core A A | |
515 | +#core B B | |
516 | +#core C C | |
517 | +#core Ć Ć | |
518 | +#core D D | |
519 | +#core E E | |
520 | +#core F F | |
521 | +#core G G | |
522 | +#core H H | |
523 | +#core I I | |
524 | +#core J J | |
525 | +#core K K | |
526 | +#core L L | |
527 | +#core Ł Ł | |
528 | +#core M M | |
529 | +#core N N | |
530 | +#core O O | |
531 | +#core P P | |
532 | +#core R R | |
533 | +#core S S | |
534 | +#core Ś Ś | |
535 | +#core T T | |
536 | +#core U U | |
537 | +#core W W | |
538 | +#core Y Y | |
539 | +#core Z Z | |
540 | +#core Ż Ż | |
541 | +#core - - | |
542 | + | |
543 | +aux {ch}š ch γ | |
544 | +aux {q}k q γ | |
545 | +aux {ng}n ng γ | |
546 | +aux {tch}č tch γ | |
547 | +aux {sh}š sh γ | |
548 | +aux {w}ł w | |
549 | +aux {leigh}l leigh γ | |
550 | +aux {au}ał au γ | |
551 | +aux {sch}š sch γ | |
552 | +aux {tsch}č tsch γ | |
553 | +aux {z}c z γ | |
554 | +core {lj}lj lj γ | |
555 | +core {pj}pj pj γ | |
556 | +aux {zs}ž zs γ | |
557 | +aux {cs}č cs γ | |
558 | + | |
559 | +aux {ay}aj ay γ | |
560 | +aux {ey}ej ey γ | |
561 | +aux {oy}oj oy γ | |
562 | +aux {ai}aj ai γ | |
563 | + | |
564 | +aux {dh}dʲ dhi ω | |
565 | +aux {dh}dʲ dh iκ | |
566 | +aux {dh}d dh δ | |
567 | +aux {gh}g′ ghi ω | |
568 | +aux {gh}g′ gh iκ | |
569 | +aux {gh}g gh δ | |
570 | +aux {kh}k′ khi ω | |
571 | +aux {kh}k′ kh iκ | |
572 | +aux {kh}k kh δ | |
573 | +aux {nh}n′ nhi ω | |
574 | +aux {nh}n′ nh iκ | |
575 | +aux {nh}n nh δ | |
576 | +aux {th}tʲ thi ω | |
577 | +aux {th}tʲ th iκ | |
578 | +aux {th}t th δ | |
579 | +core {v}v′ vi ω | |
580 | +core {v}v′ v iκ | |
581 | +core {v}v v δ | |
582 | +core {v}vj vi ρ | |
583 | +core {x}ks′ xi ω | |
584 | +core {x}ks′ x iκ | |
585 | +core {x}ks x δ | |
586 | + | |
587 | +#lemma=e/y gender=m1 | |
588 | +aux {dieu}dʲe dieu α | |
589 | +aux {dieu}dʲi dieu β | |
590 | +aux {quieu}k′e quieu α | |
591 | +aux {quieu}k′i quieu β | |
592 | +aux {lieu}lʲe lieu α | |
593 | +aux {lieu}lʲi lieu β | |
594 | +aux {rie}rʲe rie α | |
595 | +aux {rie}rʲi rie β | |
596 | +aux {gie}ǯʲe gie α | |
597 | +aux {gie}ǯʲi gie β | |
598 | +aux {kie}k′e kie α | |
599 | +aux {kie}k′i kie β | |
600 | +aux {tie}tʲe tie α | |
601 | +aux {tie}tʲi tie β | |
602 | +aux {pie}p′e pie α | |
603 | +aux {pie}p′i pie β | |
604 | +aux {die}dʲe die α | |
605 | +aux {die}dʲi die β | |
606 | +aux {bee}b′e bee α | |
607 | +aux {bee}b′i bee β | |
608 | + | |
609 | +#lemma=e gender=m1 | |
610 | +aux {mée}me mée α | |
611 | +aux {ge}g′e ge α | |
612 | +aux {ke}k′e ke α | |
613 | + | |
614 | +#lemma=y gender=m1 | |
615 | +aux {by}b′ by ’eά | |
616 | +aux {by}b′i by β | |
617 | +aux {dy}dʲ dy ’eά | |
618 | +aux {dy}dʲ dy eά | |
619 | +aux {dy}dʲ dy owieε | |
620 | +aux {dy}dʲi dy β | |
621 | +aux {dí}dʲ dí eά | |
622 | +aux {dí}dʲ dí owieε | |
623 | +aux {dí}dʲi dí β | |
624 | +aux {phy}f′ phy ’eά | |
625 | +aux {phy}f′i phy β | |
626 | +aux {guy}g′ guy ’eά | |
627 | +aux {guy}g′i guy β | |
628 | +aux {ky}k′ ky ’eά | |
629 | +aux {ky}k′ ky eά | |
630 | +aux {ky}k ky owieε | |
631 | +aux {ky}k′i ky β | |
632 | +aux {my}m′ my ’eά | |
633 | +aux {my}m′i my β | |
634 | +aux {li}l li eά | |
635 | +aux {li}l l iβ | |
636 | +aux {ly}l ly ’eά | |
637 | +aux {ly}li ly β | |
638 | +aux {ry}rʲ ry ’eά | |
639 | +aux {ry}rʲi ry β | |
640 | +core {ři}rʲ ři eά | |
641 | +core {ři}rʲ ři owieε | |
642 | +core {ři}rʲi ři β | |
643 | +aux {sy}sʲ sy ’eά | |
644 | +aux {sy}sʲ sy eά | |
645 | +aux {sy}sʲ sy owieε | |
646 | +aux {sy}sʲi sy β | |
647 | +aux {şi}sʲ şi eά | |
648 | +aux {şi}sʲ şi owieε | |
649 | +aux {şi}sʲi şi β | |
650 | +aux {cy}sʲ cy ’eά | |
651 | +aux {cy}sʲi cy β | |
652 | +aux {thy}tʲ thy ’eά | |
653 | +aux {thy}tʲ thy eά | |
654 | +aux {thy}tʲ thy owieε | |
655 | +aux {thy}tʲi thy β | |
656 | + | |
657 | +#lemma=e/ndm gender=m1 | |
658 | +aux {chais}še chais ’ | |
659 | +aux {lais}le lais ’ | |
660 | +aux {nais}ne nais ’ | |
661 | +aux {rès}re rès ’ | |
662 | +aux {rés}re rés ’ | |
663 | +aux {ré}re ré ά | |
664 | + | |
665 | +#lemma=ε | |
666 | +aux {de}d de ’ | |
667 | +aux {de}d de ε | |
668 | +aux {fe}f fe ’ | |
669 | +aux {fe}f fe ε | |
670 | +aux {phe}f phe ’ | |
671 | +aux {phe}f phe ε | |
672 | +aux {ge}ǯ ge ’ | |
673 | +aux {ge}ǯ ge ε | |
674 | +aux {ges}ǯ ges ’ | |
675 | +aux {ges}ǯ ges ε | |
676 | +aux {gue}g gue ’ | |
677 | +aux {gue}g gue ε | |
678 | +aux {gues}g gues ’ | |
679 | +aux {gues}g gues ε | |
680 | +aux {ke}k ke ’ | |
681 | +aux {ke}k ke ε | |
682 | +aux {que}k que ’ | |
683 | +aux {que}k que ε | |
684 | +aux {ques}k ques ’ | |
685 | +aux {ques}k ques ε | |
686 | +aux {le}l le ’ | |
687 | +aux {le}l le ε | |
688 | +aux {les}l les ’ | |
689 | +aux {les}l les ε | |
690 | +aux {me}m me ’ | |
691 | +aux {me}m me ε | |
692 | +aux {ne}n ne ’ | |
693 | +aux {ne}n ne ε | |
694 | +aux {gne}n′ gne ’ | |
695 | +aux {gne}n′ gne ε | |
696 | +aux {re}r re ’ | |
697 | +aux {re}r re ε | |
698 | +aux {rue}r rue ’ | |
699 | +aux {rue}r rue ε | |
700 | +aux {se}s se ’ | |
701 | +aux {se}s se ε | |
702 | +aux {ce}s ce ’ | |
703 | +aux {ce}s ce ε | |
704 | +aux {che}š che ’ | |
705 | +aux {che}š che ε | |
706 | +aux {te}t te ’ | |
707 | +aux {te}t te ε | |
708 | +aux {the}t the ’ | |
709 | +aux {the}t the ε | |
710 | +aux {ve}v ve ’ | |
711 | +aux {ve}v ve ε | |
712 | +aux {we}ł we ’ | |
713 | +aux {we}ł we ε | |
714 | +aux {se}z se ’ | |
715 | +aux {se}z se ε | |
716 | +aux {ge}ž ge ’ | |
717 | +aux {ge}ž ge ε | |
718 | +#z wyjątkiem sg:loc.voc | |
719 | +aux {oe}oł oe ’ | |
720 | +aux {oe}oł oe ε | |
721 | + | |
722 | +aux ’ γ | |
723 | +# ’ ’ owi | |
724 | + | |
725 | + n n g | |
726 | + z z γ | |
727 | + b b e | |
728 | + b b y | |
729 | + d d y | |
730 | + m m y | |
731 | + s s y | |
732 | + c c y | |
733 | + r r y | |
734 | + k k y | |
735 | + l l y | |
736 | + l l a | |
737 | + n n a | |
738 | + r r è | |
739 | + d d e | |
740 | + f f e | |
741 | + p p h | |
742 | + g g e | |
743 | + g g u | |
744 | + k k e | |
745 | + q q u | |
746 | + l l e | |
747 | + m m e | |
748 | + n n e | |
749 | + g g n | |
750 | + r r e | |
751 | + s s e | |
752 | + c c e | |
753 | +# c c h | |
754 | + t t e | |
755 | + t t h | |
756 | + v v e | |
757 | + w w e | |
758 | + s s e | |
759 | + o o e | |
760 | + m m é | |
761 | + a a y | |
762 | + e e y | |
763 | + o o y | |
764 | + | |
765 | +acro a A ε | |
766 | + | |
767 | +acro {A}a A | |
768 | +acro {B}b B | |
769 | +acro {C}c C | |
770 | +acro {C}k C | |
771 | +acro {Ć}t′ Ć | |
772 | +acro {D}d D | |
773 | +acro {E}e E | |
774 | +acro {F}f F | |
775 | +acro {G}g G | |
776 | +acro {H}h H | |
777 | +acro {I}j I | |
778 | +acro {J}j J | |
779 | +acro {K}k K | |
780 | +acro {L}l L | |
781 | +acro {Ł}ł Ł | |
782 | +acro {M}m M | |
783 | +acro {N}n N | |
784 | +acro {O}o O | |
785 | +acro {P}p P | |
786 | +acro {R}r R | |
787 | +acro {S}s S | |
788 | +acro {Ś}s′ Ś | |
789 | +acro {T}t T | |
790 | +acro {U}u U | |
791 | +acro {V}v V | |
792 | +acro {W}v W | |
793 | +acro {X}ks X | |
794 | +acro {Y}y Y | |
795 | +acro {Z}z Z | |
796 | +acro {Ż}ž Ż | |
797 | +acro {J}jot J-ot δ | |
798 | +acro {Z}zet Z-et δ | |
799 | +acro {Ż}žet Ż-et δ | |
800 | +acro {z}zet z-et δ | |
801 | + | |
802 | +acro {B}b′e B-ie ε | |
803 | +acro {D}d′e D-zie ε | |
804 | +acro {F}f′e F-ie ε | |
805 | +acro {M}m′e M-ie ε | |
806 | +acro {N}n′e N-ie ε | |
807 | +acro {P}p′e P-ie ε | |
808 | +acro {R}ře R-ze ε | |
809 | +acro {S}s′e S-ie ε | |
810 | +acro {T}t′e -cie ε | |
811 | +acro {V}v′e V-ie ε | |
812 | +acro {W}v′e W-ie ε | |
813 | +acro {X}ks′e X-ie ε | |
814 | +acro {Z}z′e Z-ie ε | |
815 | +acro {J}jot′e J-ocie ε | |
816 | +acro {Z}zet′e Z-ecie ε | |
817 | +acro {Ż}žet′e Ż-ecie ε | |
818 | + | |
819 | +acro {B}b′e Bie ε | |
820 | +acro {D}d′e Dzie ε | |
821 | +acro {F}f′e Fie ε | |
822 | +acro {M}m′e Mie ε | |
823 | +acro {N}n′e Nie ε | |
824 | +acro {P}p′e Pie ε | |
825 | +acro {R}ře Rze ε | |
826 | +acro {S}s′e Sie ε | |
827 | +acro {T}t′e cie ε | |
828 | +acro {V}v′e Vie ε | |
829 | +acro {W}v′e Wie ε | |
830 | +acro {X}ks′e Xie ε | |
831 | +acro {Z}z′e Zie ε | |
832 | +acro {J}jot′e Jocie ε | |
833 | +acro {Z}zet′e Zecie ε | |
834 | +acro {Ż}žet′e Żecie ε | |
835 | + | |
836 | +acro b′e b-ie ε | |
837 | +acro d′e d-zie ε | |
838 | +acro f′e f-ie ε | |
839 | +acro m′e m-ie ε | |
840 | +acro n′e n-ie ε | |
841 | +acro p′e p-ie ε | |
842 | +acro ře r-ze ε | |
843 | +acro s′e s-ie ε | |
844 | +acro t′e -cie ε | |
845 | +core {v}v′e v-ie ε | |
846 | +acro v′e w-ie ε | |
847 | +core {x}ks′e x-ie ε | |
848 | +acro z′e z-ie ε | |
849 | +acro {j}jot′e j-ocie ε | |
850 | +acro {z}zet′e z-ecie ε | |
851 | +acro {ż}žet′e ż-ecie ε | |
852 | + | |
853 | +acro {T}t′e CIE ε | |
854 | + a a cieε | |
855 | + e e cieε | |
856 | + i i cieε | |
857 | + o o cieε | |
858 | + u u cieε | |
859 | +acro {A}a{T}t′e acie ε | |
860 | +acro {E}e{T}t′e ecie ε | |
861 | +acro {I}j{T}t′e icie ε | |
862 | +acro {O}o{T}t′e ocie ε | |
863 | +acro {U}u{T}t′e ucie ε | |
864 | + | |
865 | +acro {C}k′i C-i ε | |
866 | +acro {C}k′em C-iem ε | |
867 | +acro {E}eʲi E-i ε | |
868 | +acro {G}g′i G-i ε | |
869 | +acro {G}g′em G-iem ε | |
870 | +acro {J}ji J-i ε | |
871 | +acro {K}k′i K-i ε | |
872 | +acro {K}k′em K-iem ε | |
873 | +acro {L}li L-i ε | |
874 | +acro - γ | |
875 | + | |
876 | + | |
... | ... |
morphology/data/fonetics_acro.dic deleted
1 | -@symbols | |
2 | -δ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y z ź ż - ε v x q | |
3 | -γ aε achε amiε ąε eε ęε iε oε omε onε umε ówε uε owiε omε emε yε owieε emuε egoε goε mε muε ε | |
4 | - | |
5 | - | |
6 | -@rev_symbols | |
7 | - | |
8 | - | |
9 | -@rev_rules | |
10 | -acro {A}a A | |
11 | -acro {B}b B | |
12 | -acro {C}c C | |
13 | -acro {C}k C | |
14 | -acro {Ć}t′ Ć | |
15 | -acro {D}d D | |
16 | -acro {E}e E | |
17 | -acro {F}f F | |
18 | -acro {G}g G | |
19 | -acro {H}h H | |
20 | -acro {I}j I | |
21 | -acro {J}j J | |
22 | -acro {K}k K | |
23 | -acro {L}l L | |
24 | -acro {Ł}ł Ł | |
25 | -acro {M}m M | |
26 | -acro {N}n N | |
27 | -acro {O}o O | |
28 | -acro {P}p P | |
29 | -acro {R}r R | |
30 | -acro {S}s S | |
31 | -acro {Ś}s′ Ś | |
32 | -acro {T}t T | |
33 | -acro {U}u U | |
34 | -acro {V}v V | |
35 | -acro {W}v W | |
36 | -acro {X}ks X | |
37 | -acro {Y}y Y | |
38 | -acro {Z}z Z | |
39 | -acro {Ż}ž Ż | |
40 | -acro {J}jot J | |
41 | -acro {Z}zet Z | |
42 | -acro {Ż}žet Ż | |
43 | -acro {v}v V | |
44 | -acro {x}ks X | |
45 | -acro {j}jot J | |
46 | -acro {z}zet z | |
47 | -acro {ż}žet Ż | |
48 | - | |
49 | -acro a A ε | |
50 | - | |
51 | - | |
52 | -@rules | |
53 | -acro {A}a A δ | |
54 | -acro {B}b B δ | |
55 | -acro {C}c C δ | |
56 | -acro {C}k C δ | |
57 | -acro {Ć}t′ Ć δ | |
58 | -acro {D}d D δ | |
59 | -acro {E}e E δ | |
60 | -acro {F}f F δ | |
61 | -acro {G}g G δ | |
62 | -acro {H}h H δ | |
63 | -acro {I}j I δ | |
64 | -acro {J}j J δ | |
65 | -acro {K}k K δ | |
66 | -acro {L}l L δ | |
67 | -acro {Ł}ł Ł δ | |
68 | -acro {M}m M δ | |
69 | -acro {N}n N δ | |
70 | -acro {O}o O δ | |
71 | -acro {P}p P δ | |
72 | -acro {R}r R δ | |
73 | -acro {S}s S δ | |
74 | -acro {Ś}s′ Ś δ | |
75 | -acro {T}t T δ | |
76 | -acro {U}u U δ | |
77 | -acro {V}v V δ | |
78 | -acro {W}v W δ | |
79 | -acro {X}ks X δ | |
80 | -acro {Y}y Y δ | |
81 | -acro {Z}z Z δ | |
82 | -acro {Ż}ž Ż δ | |
83 | -acro {J}jot J-ot δ | |
84 | -acro {Z}zet Z-et δ | |
85 | -acro {Ż}žet Ż-et δ | |
86 | -acro {z}zet z-et δ | |
87 | - | |
88 | -acro {B}b′e B-ie ε | |
89 | -acro {D}d′e D-zie ε | |
90 | -acro {F}f′e F-ie ε | |
91 | -acro {M}m′e M-ie ε | |
92 | -acro {N}n′e N-ie ε | |
93 | -acro {P}p′e P-ie ε | |
94 | -acro {R}ře R-ze ε | |
95 | -acro {S}s′e S-ie ε | |
96 | -acro {T}t′e -cie ε | |
97 | -acro {V}v′e V-ie ε | |
98 | -acro {W}v W-ie ε | |
99 | -acro {X}ks′e X-ie ε | |
100 | -acro {Z}z Z-ie ε | |
101 | -acro {J}jot′e J-ocie ε | |
102 | -acro {Z}zet′e Z-ecie ε | |
103 | -acro {Ż}žet′e Ż-ecie ε | |
104 | - | |
105 | -acro {B}b′e Bie ε | |
106 | -acro {D}d′e Dzie ε | |
107 | -acro {F}f′e Fie ε | |
108 | -acro {M}m′e Mie ε | |
109 | -acro {N}n′e Nie ε | |
110 | -acro {P}p′e Pie ε | |
111 | -acro {R}ře Rze ε | |
112 | -acro {S}s′e Sie ε | |
113 | -acro {T}t′e cie ε | |
114 | -acro {V}v′e Vie ε | |
115 | -acro {W}v Wie ε | |
116 | -acro {X}ks′e Xie ε | |
117 | -acro {Z}z Zie ε | |
118 | -acro {J}jot′e Jocie ε | |
119 | -acro {Z}zet′e Zecie ε | |
120 | -acro {Ż}žet′e Żecie ε | |
121 | - | |
122 | -acro b′e b-ie ε | |
123 | -acro d′e d-zie ε | |
124 | -acro f′e f-ie ε | |
125 | -acro m′e m-ie ε | |
126 | -acro n′e n-ie ε | |
127 | -acro p′e p-ie ε | |
128 | -acro ře r-ze ε | |
129 | -acro s′e s-ie ε | |
130 | -acro t′e -cie ε | |
131 | -acro {v}v′e v-ie ε | |
132 | -acro v w-ie ε | |
133 | -acro {x}ks′e x-ie ε | |
134 | -acro z z-ie ε | |
135 | -acro {j}jot′e j-ocie ε | |
136 | -acro {z}zet′e z-ecie ε | |
137 | -acro {ż}žet′e ż-ecie ε | |
138 | - | |
139 | -acro {T}t′e CIE ε | |
140 | -acro {A}a{T}t′e acie ε | |
141 | -acro {E}e{T}t′e ecie ε | |
142 | -acro {I}j{T}t′e icie ε | |
143 | -acro {O}o{T}t′e ocie ε | |
144 | -acro {U}u{T}t′e ucie ε | |
145 | - | |
146 | -acro {C}k′i C-i ε | |
147 | -acro {C}k′em C-iem ε | |
148 | -acro {G}g′i G-i ε | |
149 | -acro {G}g′em G-iem ε | |
150 | -acro {J}ji J-i ε | |
151 | -acro {K}k′i K-i ε | |
152 | -acro {K}k′em K-iem ε | |
153 | -acro {L}li L-i ε | |
154 | -acro - γ | |
155 | - a a ε | |
156 | - ax ach ε | |
157 | - am′i ami ε | |
158 | - ą ą ε | |
159 | - e e ε | |
160 | - ę ę ε | |
161 | - em em ε | |
162 | - o o ε | |
163 | - om om ε | |
164 | - ov′i owi ε | |
165 | - ov′e owie ε | |
166 | - u u ε | |
167 | - óv ów ε | |
168 | - y y ε | |
169 | - | |
170 | - |
morphology/data/fonetics_acro_old.dic deleted
1 | -@symbols | |
2 | - | |
3 | - | |
4 | -@rev_symbols | |
5 | - | |
6 | - | |
7 | -@rev_rules | |
8 | -!a A | |
9 | -!b B | |
10 | -!c C | |
11 | -!t′ Ć | |
12 | -!d D | |
13 | -!e E | |
14 | -!f F | |
15 | -!g G | |
16 | -!h H | |
17 | -!i I | |
18 | -#!j J | |
19 | -!k K | |
20 | -!l L | |
21 | -!ł Ł | |
22 | -!m M | |
23 | -!n N | |
24 | -!o O | |
25 | -!p P | |
26 | -!r R | |
27 | -!s S | |
28 | -!s′ Ś | |
29 | -!t T | |
30 | -!u U | |
31 | -!v W | |
32 | -!y Y | |
33 | -!z Z | |
34 | -!ż Ż | |
35 | -#x ch ε | |
36 | -ax -ach ε | |
37 | -ę -ę ε | |
38 | -ʲi -i ε | |
39 | -a A ε | |
40 | -!jot′e J-ocie ε | |
41 | -!jotax J-otach ε | |
42 | -!jot J ε | |
43 | -t′e -cie ε | |
44 | - | |
45 | - | |
46 | -@rules | |
47 | -!a A | |
48 | -!b B | |
49 | -!c C | |
50 | -!t′ Ć | |
51 | -!d D | |
52 | -!e E | |
53 | -!f F | |
54 | -!g G | |
55 | -!h H | |
56 | -!i I | |
57 | -#!jot J | |
58 | -!k K | |
59 | -!l L | |
60 | -!ł Ł | |
61 | -!m M | |
62 | -!n N | |
63 | -!o O | |
64 | -!p P | |
65 | -!r R | |
66 | -!s S | |
67 | -!s′ Ś | |
68 | -!t T | |
69 | -!u U | |
70 | -!v W | |
71 | -!y Y | |
72 | -!z Z | |
73 | -!ž Ż | |
74 | -ax -ach ε | |
75 | -ę -ę ε | |
76 | -ʲi -i ε | |
77 | -!jot′e J-ocie ε | |
78 | -!jotax J-otach ε | |
79 | -t′e -cie ε | |
80 | - | |
81 | - |
morphology/data/fonetics_de.dic deleted
1 | -@symbols | |
2 | -ω a ą e ę o ó u | |
3 | -δ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y z ź ż - ε | |
4 | -γ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y ź ż - ε | |
5 | -ξ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y - ε | |
6 | -μ a ą b c ć d e ę f g k l ł m n ń o ó p r s ś t u w y ź ż - ε | |
7 | -λ b c ć d f g h k l ł m n ń p r s ś t w z ź ż - ε | |
8 | -κ b c ć d f g h i j k l ł m n ń p r s ś t w z ź ż - ε | |
9 | -σ a ą b c ć d e ę f g j h k l ł m n ń o ó p r s ś t u w y z ź ż - ε | |
10 | -ρ aε achε amiε ąε eε ęε iε oε omε onε umε ówε uε owiε omε emε yε owieε emuε egoε goε mε muε ε | |
11 | - | |
12 | -@rev_symbols | |
13 | -ω a ą e ę o ó u | |
14 | -δ a ą b c ć č d ʒ ǯ e ę f g h x i k l ł m n ń o ó p r ř s ś š t u v w y z ź ž - ε | |
15 | -λ b c ć č d ʒ ǯ f g h x k l ł m n ń p r ř s ś š t v w z ź ž - ε | |
16 | -κ b c ć č d ʒ ǯ f g h x i j ʲ k l ł m n ń p r ř s ś š t v w z ź ž - ε | |
17 | -ρ aε axε am′iε ąε eε ęε iε oε omε onε umε óvε uε ov′iε omε emε ε | |
18 | - | |
19 | -@rev_rules | |
20 | -de r rh | |
21 | -de r r | |
22 | -de ta tha | |
23 | -de ks x | |
24 | - | |
25 | -de g′e ge ε | |
26 | -de k′e ke ε | |
27 | - | |
28 | -de k′i ky ε | |
29 | - | |
30 | - | |
31 | -@rules | |
32 | -de š sch | |
33 | -de r rh | |
34 | -de c z | |
35 | -de ał au | |
36 | - | |
37 | -de ře rze ε | |
38 | -de ks′e ksie ε | |
39 | -de t′e cie ε | |
40 | -de v′e vie ε | |
41 | - | |
42 | -de óv ów ε | |
43 | -de ov′i owi ε | |
44 | -de ov′e owie ε | |
45 | -de am′i ami ε | |
46 | -de ax ach ε | |
47 | - | |
48 | -de g′e ge ch | |
49 | -de g′e ge go | |
50 | -de g′e ge m | |
51 | -de g′e ge mi | |
52 | -de g′e ge mu | |
53 | -de k′e ke ch | |
54 | -de k′e ke go | |
55 | -de k′e ke m | |
56 | -de k′e ke mi | |
57 | -de k′e ke mu | |
58 | -de k′i ky ch | |
59 | -de k′i ky mi | |
60 | -de k′i ky m | |
61 | -de x ch ε | |
62 | -de m′i mi ε | |
63 | - | |
64 | -de kj ky ’ | |
65 | -de ’ ρ | |
66 | - | |
67 | -de góv gów ε | |
68 | -de gov′i gowi ε | |
69 | -de gov′e gowie ε | |
70 | -de gam′i gami ε | |
71 | -de gax gach ε | |
72 | -de gom gom ε | |
73 | -de kóv ków ε | |
74 | -de kov′i kowi ε | |
75 | -de kov′e kowie ε | |
76 | -de kam′i kami ε | |
77 | -de kax kach ε | |
78 | -de kom kom ε | |
79 | - | |
80 | -de k′ix kich ε | |
81 | -de k′e kie ε | |
82 | -de k′im kim ε | |
83 | -de k′im′i kimi ε | |
84 | -de k′ego kiego ε | |
85 | -de k′emu kiemu ε | |
86 | - | |
87 | - | |
88 | - |
morphology/data/fonetics_en.dic deleted
1 | -@symbols | |
2 | -ω a ą e ę o ó u | |
3 | -δ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y z ź ż - ε | |
4 | -γ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y ź ż - ε | |
5 | -ξ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y - ε | |
6 | -μ a ą b c ć d e ę f g k l ł m n ń o ó p r s ś t u w y ź ż - ε | |
7 | -λ b c ć d f g h k l ł m n ń p r s ś t w z ź ż - ε | |
8 | -κ b c ć d f g h i j k l ł m n ń p r s ś t w z ź ż - ε | |
9 | -σ a ą b c ć d e ę f g j h k l ł m n ń o ó p r s ś t u w y z ź ż - ε | |
10 | -ρ aε achε amiε ąε eε ęε iε oε omε onε umε ówε uε owiε omε emε yε owieε emuε egoε ε | |
11 | - | |
12 | -@rev_symbols | |
13 | -ω a ą e ę o ó u | |
14 | -δ a ą b c ć č d ʒ ǯ e ę f g h x i k l ł m n ń o ó p r ř s ś š t u v w y z ź ž - ε | |
15 | -λ b c ć č d ʒ ǯ f g h x k l ł m n ń p r ř s ś š t v w z ź ž - ε | |
16 | -κ b c ć č d ʒ ǯ f g h x i j ʲ k l ł m n ń p r ř s ś š t v w z ź ž - ε | |
17 | -ρ aε axε am′iε ąε eε ęε iε oε omε onε umε óvε uε ov′iε omε emε ε | |
18 | - | |
19 | -@rev_rules | |
20 | -en ks x | |
21 | -en č tch | |
22 | -en ł w | |
23 | -en aj ay ρ | |
24 | -en ej ey ρ | |
25 | -en oj oy ρ | |
26 | - | |
27 | -en d de ε | |
28 | -en d d ε | |
29 | -en f ph ε | |
30 | -en k ke ε | |
31 | -en k k ε | |
32 | -en k kes ε | |
33 | -en k c | |
34 | -en k ky ε | |
35 | -en t te ε | |
36 | -en t t ε | |
37 | -en t th | |
38 | -en t the ε | |
39 | -en r re ε | |
40 | -en r r ε | |
41 | -en r rh ε | |
42 | -en m me ε | |
43 | -en m m ε | |
44 | -en n ne ε | |
45 | -en n n ε | |
46 | -en s se ε | |
47 | -en s s ε | |
48 | -en s ce ε | |
49 | -en s th ε | |
50 | -en s the ε | |
51 | - | |
52 | -en a a ε | |
53 | -en a ah ε | |
54 | -en ka kha ε | |
55 | -en vja via ε | |
56 | - | |
57 | -en ʲi ie ε | |
58 | -en ʲi i ε | |
59 | -en ʲi y ε | |
60 | - | |
61 | -@rules | |
62 | -en ks x | |
63 | -en č tch | |
64 | -en ł w | |
65 | -en d dh | |
66 | -en g gh | |
67 | -en k kh | |
68 | -en l leigh | |
69 | -en aj ay ρ | |
70 | -en ej ey ρ | |
71 | -en oj oy ρ | |
72 | -en aʲi ai ε | |
73 | -en oʲi oi ε | |
74 | -en eʲi ei ε | |
75 | -en uʲi ui ε | |
76 | - | |
77 | -en vj vi ρ | |
78 | -en v′ij vij ε | |
79 | - | |
80 | -en ce ce ε | |
81 | -en f′e fie ε | |
82 | -en ře rze ε | |
83 | -en t′e cie ε | |
84 | -en kt′e kcie ε | |
85 | -en s′t′e ście ε | |
86 | -en m′e mie ε | |
87 | -en n′e nie ε | |
88 | -en d′e dzie ε | |
89 | -en p′e pie ε | |
90 | -en s′e sie ε | |
91 | -en ks′e ksie ε | |
92 | -en v′e vie ε | |
93 | -en z′e zie ε | |
94 | - | |
95 | -en k′i ki ε | |
96 | -en k′em kiem ε | |
97 | -en k k iem | |
98 | -en řy rzy ε | |
99 | - | |
100 | - | |
101 | -en ʲi ie ch | |
102 | -en ʲi ie mi | |
103 | -en ʲi ie m | |
104 | -en ʲi ee ch | |
105 | -en ʲi ee mi | |
106 | -en li ly ch | |
107 | -en li ly mi | |
108 | -en li ly m | |
109 | -en ʲego iego ε | |
110 | -en ʲemu iemu ε | |
111 | -en ʲem iem ε | |
112 | -en ʲim im ε | |
113 | -en ʲix ich ε | |
114 | -en ʲe ie ε | |
115 | -en ʲim′i imi ε | |
116 | -en ʲov′e iowie ε | |
117 | -en ′e ie m | |
118 | -en ′i i ε | |
119 | -en i i ε | |
120 | -en x ch ε | |
121 | -en m′i mi ε | |
122 | -en óv ów ε | |
123 | -en ov′i owi ε | |
124 | -en ov′e owie ε | |
125 | -en am′i ami ε | |
126 | -en ax ach ε | |
127 | - | |
128 | -en oł oe ’ | |
129 | -en b by ’ | |
130 | -en k′ ky ’ | |
131 | -en r ry ’ | |
132 | -en t thy ’ | |
133 | -en d dy ’ | |
134 | -en m my ’ | |
135 | -en s cy ’ | |
136 | -en l ly ’ | |
137 | -en d dy ’ | |
138 | -en s ce ’ | |
139 | -en d de ’ | |
140 | -en f fe ’ | |
141 | -en ǯ ge ’ | |
142 | -en k ke ’ | |
143 | -en l le ’ | |
144 | -en m me ’ | |
145 | -en n ne ’ | |
146 | -en r re ’ | |
147 | -en s se ’ | |
148 | -en t te ’ | |
149 | -en t the ’ | |
150 | -en v ve ’ | |
151 | -en ł we ’ | |
152 | -en ’ ρ | |
153 | - | |
154 | -en s ce ε | |
155 | -en d de ε | |
156 | -en f fe ε | |
157 | -en ǯ ge ε | |
158 | -en k ke ε | |
159 | -en l le ε | |
160 | -en le le ε | |
161 | -en m me ε | |
162 | -en me me ε | |
163 | -en n ne ε | |
164 | -en r re ε | |
165 | -en re re ε | |
166 | -en s se ε | |
167 | -en t te ε | |
168 | -en v ve ε | |
169 | -en ł we ε | |
170 | - | |
171 | - | |
172 | -#en os′t′ ość ε | |
173 | -#en os′t′ą ością ε | |
174 | -#en os′t′om ościom ε | |
175 | -#en os′t′am′i ościami ε | |
176 | -#en os′t′ax ościach ε | |
177 | -#en os′t′i ości ε | |
178 | -#en ovą ową ε | |
179 | -#en ovym′i owymi ε | |
180 | -#en ovym owym ε | |
181 | -#en ovyx owych ε | |
182 | -#en ovy owy ε | |
183 | -#en ovo owo ε | |
184 | -#en ov′i owi ε | |
185 | -#en ovemu owemu ε | |
186 | -#en ovej owej ε | |
187 | -#en ovego owego ε | |
188 | -#en ove owe ε | |
189 | -#en ova owa ε | |
190 | -#en oły owy ε | |
191 | -#en oła owa ε | |
192 | -#en k′ix kich ε | |
193 | -#en k′e kie ε | |
194 | -#en k′ej kiej ε | |
195 | -#en k′im kim ε | |
196 | -#en k′im′i kimi ε | |
197 | -#en ka ka ε | |
198 | -#en ką ką ε | |
199 | -#en ko ko ε | |
200 | -#en ku ku ε | |
201 | -#en če cze ε | |
202 | -#en n′ja nia ε | |
203 | -#en n′ją nią ε | |
204 | -#en n′je nie ε | |
205 | -#en n′ję nię ε | |
206 | -#en n′ji nii ε | |
207 | -#en n′ij nij ε | |
208 | -#en n′jom niom ε | |
209 | -#en n′jo nio ε | |
210 | -#en n′jax niach ε | |
211 | -#en n′jam′i niami ε | |
212 | - |
morphology/data/fonetics_fr.dic deleted
1 | -@symbols | |
2 | -ω a ą e ę o ó u | |
3 | -δ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y z ź ż - ε | |
4 | -γ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y ź ż - ε | |
5 | -ξ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y - ε | |
6 | -μ a ą b c ć d e ę f g k l ł m n ń o ó p r s ś t u w y ź ż - ε | |
7 | -λ b c ć d f g h k l ł m n ń p r s ś t w z ź ż - ε | |
8 | -κ b c ć d f g h i j k l ł m n ń p r s ś t w z ź ż - ε | |
9 | -σ a ą b c ć d e ę f g j h k l ł m n ń o ó p r s ś t u w y z ź ż - ε | |
10 | -ρ aε achε amiε ąε eε ęε iε oε omε onε umε ówε uε owiε omε emε yε owieε emuε egoε goε mε muε ε | |
11 | - | |
12 | -@rev_symbols | |
13 | -ω a ą e ę o ó u | |
14 | -δ a ą b c ć č d ʒ ǯ e ę f g h x i k l ł m n ń o ó p r ř s ś š t u v w y z ź ž - ε | |
15 | -λ b c ć č d ʒ ǯ f g h x k l ł m n ń p r ř s ś š t v w z ź ž - ε | |
16 | -κ b c ć č d ʒ ǯ f g h x i j ʲ k l ł m n ń p r ř s ś š t v w z ź ž - ε | |
17 | -ρ aε axε am′iε ąε eε ęε iε oε omε onε umε óvε uε ov′iε omε emε ε | |
18 | - | |
19 | -@rev_rules | |
20 | -fr ks x | |
21 | -fr b bes ε | |
22 | -fr d d ε | |
23 | -fr d de ε | |
24 | -fr f phe ε | |
25 | -fr g gue ε | |
26 | -fr g gues ε | |
27 | -fr k c ε | |
28 | -fr k que ε | |
29 | -fr k q ε | |
30 | -fr k cq ε | |
31 | -fr k ques ε | |
32 | -fr k cques ε | |
33 | -fr m me ε | |
34 | -fr n n ε | |
35 | -fr n ne ε | |
36 | -fr n nes ε | |
37 | -fr n′ ng ε | |
38 | -fr r r ε | |
39 | -fr r re ε | |
40 | -fr r res ε | |
41 | -fr r rs ε | |
42 | -fr s s ε | |
43 | -fr s se ε | |
44 | -fr s ce ε | |
45 | -fr t t ε | |
46 | -fr t tes ε | |
47 | -fr t thes ε | |
48 | -fr z se ε | |
49 | - | |
50 | -@rules | |
51 | -fr k q | |
52 | -fr n ng | |
53 | - | |
54 | -fr b′e bie ε | |
55 | -fr d′e dzie ε | |
56 | -fr f′e fie ε | |
57 | -fr m′e mie ε | |
58 | -fr n′e nie ε | |
59 | -fr s′n′e śnie ε | |
60 | -fr ře rze ε | |
61 | -fr s′e sie ε | |
62 | -fr ks′e ksie ε | |
63 | -fr t′e cie ε | |
64 | -fr s′t′e ście ε | |
65 | -fr v′e vie ε | |
66 | -fr z′e zie ε | |
67 | - | |
68 | -fr řy rzy ε | |
69 | -fr t′i ci ε | |
70 | -fr v′i vi ε | |
71 | - | |
72 | -fr g′em giem ε | |
73 | -fr g′i gi ε | |
74 | -fr k′em kiem ε | |
75 | -fr k′i ki ε | |
76 | - | |
77 | -fr ʲi ieu ch | |
78 | -fr ʲe ieu go | |
79 | -fr ʲi ieu m | |
80 | -fr ʲi ieu mi | |
81 | -fr ʲe ieu mu | |
82 | -fr llj lli ego | |
83 | -fr llj lli emu | |
84 | -fr llj lli e | |
85 | -fr e ée go | |
86 | -fr e ée m | |
87 | -fr e ée mu | |
88 | -fr x ch ε | |
89 | -fr m′i mi ε | |
90 | - | |
91 | -fr óv ów ε | |
92 | -fr ov′i owi ε | |
93 | -fr ov′e owie ε | |
94 | -fr am′i ami ε | |
95 | -fr ax ach ε | |
96 | - | |
97 | -fr e ès ’ | |
98 | -fr e ais ’ | |
99 | -fr k que ’ | |
100 | -fr f phe ’ | |
101 | -fr sj sy ’ | |
102 | -fr fj phy ’ | |
103 | -fr rj ry ’ | |
104 | -fr š che ’ | |
105 | -fr d de ’ | |
106 | -fr r re ’ | |
107 | -fr z se ’ | |
108 | -fr ž ge ’ | |
109 | -fr # ine ’ | |
110 | -fr t te ’ | |
111 | -fr l le ’ | |
112 | -fr m me ’ | |
113 | -fr n′ gne ’ | |
114 | -fr n ne ’ | |
115 | -fr v ve ’ | |
116 | -fr g gue ’ | |
117 | -fr s ce ’ | |
118 | -fr gj guy ’ | |
119 | -fr ’ ρ | |
120 | - | |
121 | - |
morphology/data/fonetics_pl.dic deleted
1 | -@symbols | |
2 | -ω a ą e ę o ó u | |
3 | -δ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y z ź ż - ε v x q | |
4 | -#γ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y ź ż - ε | |
5 | -#ξ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y - ε | |
6 | -#μ a ą b c ć d e ę f g k l ł m n ń o ó p r s ś t u w y ź ż - ε | |
7 | -λ b c ć d f g h k l ł m n ń p r s ś t w z ź ż - ε v x q | |
8 | -κ b c ć d f g h i j k l ł m n ń p r s ś t w z ź ż - ε v x q | |
9 | -#σ a ą b c ć d e ę f g j h k l ł m n ń o ó p r s ś t u w y z ź ż - ε | |
10 | -ρ aε achε amiε ąε eε ęε iε oε omε onε umε | |
11 | -α ε goε muε mε | |
12 | -ά ε goε muε | |
13 | -β ε chε miε mε | |
14 | -γ aε achε amiε ąε eε ęε iε oε omε onε umε ówε uε owiε omε emε yε owieε emuε egoε goε mε muε ε | |
15 | - | |
16 | -@rev_symbols | |
17 | -ω a ą e ę o ó u {eu} | |
18 | -δ a ą b c ć č d ʒ ǯ e ę f g h x i k l ł m n ń o ó p r ř s ś š t u v w y z ź ž - ε { | |
19 | -λ b c ć č d ʒ ǯ f g h x k l ł m n ń p r ř s ś š t v w z ź ž - ε { q | |
20 | -κ b c ć č d ʒ ǯ f g h x i j ʲ k l ł m n ń p r ř s ś š t v w z ź ž - ε { | |
21 | -ρ aε axε am′iε ąε eε ęε iε oε omε onε umε | |
22 | - | |
23 | -@rev_rules | |
24 | -pl p′ pi ω | |
25 | -pl p′ p i | |
26 | -pl pj pi ρ | |
27 | -pl b′ bi ω | |
28 | -pl b′ b i | |
29 | -pl bj bi ρ | |
30 | -pl m′ mi ω | |
31 | -pl m′ m i | |
32 | -pl m′j mi ρ | |
33 | -pl f′ fi ω | |
34 | -pl f′ f i | |
35 | -pl fj fi ρ | |
36 | -pl v′ wi ω | |
37 | -pl v′ w i | |
38 | -pl v w δ | |
39 | -pl vj wi ρ | |
40 | -#pl v w j | |
41 | -pl t′ ć λ | |
42 | -pl t′ ci ω | |
43 | -pl t′ c i | |
44 | -pl d′ dź λ | |
45 | -pl d′ dzi ω | |
46 | -pl d′ dz i | |
47 | -pl ʒ dz | |
48 | -pl tʲ ti ω | |
49 | -pl tʲ t i | |
50 | -pl tj ti ρ | |
51 | -pl dʲ di ω | |
52 | -pl dʲ d i | |
53 | -pl dj di ρ | |
54 | -pl č cz δ | |
55 | -pl čʲ czi ω | |
56 | -pl čʲ cz i | |
57 | -pl č cz j | |
58 | -pl ǯ dż δ | |
59 | -pl ǯʲ dżi ω | |
60 | -pl ǯʲ dż i | |
61 | -pl ǯj dżi ρ | |
62 | -pl s′ ś λ | |
63 | -pl s′ si ω | |
64 | -pl s′ s i | |
65 | -pl z′ ź λ | |
66 | -pl z′ zi ω | |
67 | -pl z′ z i | |
68 | -pl š sz δ | |
69 | -pl š sz j | |
70 | -pl šʲ szi ω | |
71 | -pl šʲ sz i | |
72 | -pl ž ż δ | |
73 | -pl žʲ żi ω | |
74 | -pl žʲ ż i | |
75 | -pl žj żi ρ | |
76 | -pl lʲ li ω | |
77 | -pl lj li ρ | |
78 | -pl ř rz δ | |
79 | -pl ř rz j | |
80 | -pl rʲ ri ω | |
81 | -pl rʲ r i | |
82 | -pl rj ri ρ | |
83 | -pl n′ ń λ | |
84 | -pl n′ ni ω | |
85 | -pl n′ n i | |
86 | -pl n′j ni ρ | |
87 | -pl k′ ki ω | |
88 | -pl k′ k i | |
89 | -pl k′j ki ρ | |
90 | -pl g′ gi ω | |
91 | -pl g′ g i | |
92 | -pl g′j gi ρ | |
93 | -pl x ch δ | |
94 | -pl xʲ chi ω | |
95 | -pl xʲ ch i | |
96 | -pl xʲj chi ρ | |
97 | -pl hʲ hi ω | |
98 | -pl hʲ h i | |
99 | -pl aʲ a i | |
100 | -pl eʲ e i | |
101 | -pl oʲ o i | |
102 | -pl óʲ ó i | |
103 | -pl uʲ u i | |
104 | -pl iʲ i i | |
105 | -pl yʲ y i | |
106 | - | |
107 | -fr {ch}š ch | |
108 | -fr {q}k q | |
109 | -fr {ng}n ng | |
110 | -en {tch}č tch | |
111 | -en {w}ł w | |
112 | -en {leigh}l leigh | |
113 | -de {au}ał au | |
114 | -de {sch}š sch | |
115 | -de {tsch}č tsch | |
116 | -de {z}c z | |
117 | - | |
118 | -en {ay}aj ay ε | |
119 | -en {ey}ej ey ε | |
120 | -en {oy}oj oy ε | |
121 | -en {ay}aj ay ω | |
122 | -en {ey}ej ey ω | |
123 | -en {oy}oj oy ω | |
124 | - | |
125 | -en {dh}dʲ dhi ω | |
126 | -en {dh}dʲ dh iκ | |
127 | -en {dh}d dh δ | |
128 | -en {gh}g′ ghi ω | |
129 | -en {gh}g′ gh iκ | |
130 | -en {gh}g gh δ | |
131 | -en {kh}k′ khi ω | |
132 | -en {kh}k′ kh iκ | |
133 | -en {kh}k kh δ | |
134 | -en {th}tʲ thi ω | |
135 | -en {th}tʲ th iκ | |
136 | -en {th}t th δ | |
137 | -en {v}v′ vi ω | |
138 | -en {v}v′ v iκ | |
139 | -en {v}v v δ | |
140 | -en {v}vj vi ρ | |
141 | -de-en-fr {x}ks′ xi ω | |
142 | -de-en-fr {x}ks′ x iκ | |
143 | -de-en-fr {x}ks x δ | |
144 | - | |
145 | -#lemma=e/y gender=m1 | |
146 | -fr {dieu}dʲe dieu ε | |
147 | -fr {dieu}dʲi dieu ε | |
148 | -fr {quieu}k′e quieu ε | |
149 | -fr {quieu}k′i quieu ε | |
150 | -fr {lieu}lʲe lieu ε | |
151 | -fr {lieu}lʲi lieu ε | |
152 | -en {rie}rʲe rie ε | |
153 | -en {rie}rʲi rie ε | |
154 | -en {gie}ǯʲe gie ε | |
155 | -en {gie}ǯʲi gie ε | |
156 | -en {kie}k′e kie ε | |
157 | -en {kie}k′i kie ε | |
158 | -en {tie}tʲe tie ε | |
159 | -en {tie}tʲi tie ε | |
160 | -en {pie}p′e pie ε | |
161 | -en {pie}p′i pie ε | |
162 | -en {die}dʲe die ε | |
163 | -en {die}dʲi die ε | |
164 | -en {bee}b′e bee ε | |
165 | -en {bee}b′i bee ε | |
166 | - | |
167 | -#lemma=e gender=m1 | |
168 | -fr {mée}me mée ε | |
169 | -de {ge}g′e ge ε | |
170 | -de {ke}k′e ke ε | |
171 | - | |
172 | -#lemma=y gender=m1 | |
173 | -en {by}b′i by ε | |
174 | -en {dy}dʲi dy ε | |
175 | -es {dí}dʲi dí ε | |
176 | -fr {phy}f′i phy ε | |
177 | -fr {guy}g′i guy ε | |
178 | -de-en {ky}k′i ky ε | |
179 | -en {my}m′i my ε | |
180 | -fr {li}li li ε | |
181 | -en {ly}li ly ε | |
182 | -en-fr {ry}rʲi ry ε | |
183 | -fr {sy}sʲi sy ε | |
184 | -en {cy}sʲi cy ε | |
185 | -en {thy}tʲi thy ε | |
186 | - | |
187 | -#lemma=e/ndm gender=m1 | |
188 | -fr {chais}še chais ε | |
189 | -fr {lais}le lais ε | |
190 | -fr {nais}ne nais ε | |
191 | -fr {rès}re rès ε | |
192 | - | |
193 | -#lemma=ε | |
194 | -en-fr {de}d de ε | |
195 | -en {fe}f fe ε | |
196 | -fr {phe}f phe ε | |
197 | -en {ge}ǯ ge ε | |
198 | -fr {gue}g gue ε | |
199 | -en {ke}k ke ε | |
200 | -fr {que}k que ε | |
201 | -en-fr {le}l le ε | |
202 | -en-fr {me}m me ε | |
203 | -en-fr {ne}n ne ε | |
204 | -fr {gne}n′ gne ε | |
205 | -en-fr {re}r re ε | |
206 | -en {se}s se ε | |
207 | -en-fr {ce}s ce ε | |
208 | -fr {che}š che ε | |
209 | -en-fr {te}t te ε | |
210 | -en {the}t the ε | |
211 | -en-fr {ve}v ve ε | |
212 | -en {we}ł we ε | |
213 | -fr {se}z se ε | |
214 | -fr {ge}ž ge ε | |
215 | -en {oe}oł oe ε | |
216 | - | |
217 | - | |
218 | -de g′el gel ε | |
219 | - | |
220 | -de g′e ge ε | |
221 | -de k′e ke ε | |
222 | -de k′i ky ε | |
223 | -de-en-fr ks x ε | |
224 | - | |
225 | - r r a | |
226 | -de r rh a | |
227 | - t t a | |
228 | -de t th a | |
229 | - k k | |
230 | -en k kh a | |
231 | -de-en-fr ks x a | |
232 | -en k c a | |
233 | - | |
234 | -en k c o | |
235 | - | |
236 | - b b ε | |
237 | -fr b bes ε | |
238 | - d d ε | |
239 | -en-fr d de ε | |
240 | - f f ε | |
241 | -fr f phe ε | |
242 | -en f ph ε | |
243 | - g g ε | |
244 | -fr g gue ε | |
245 | -fr g gues ε | |
246 | - k k ε | |
247 | -fr k c ε | |
248 | -fr k que ε | |
249 | -fr k q ε | |
250 | -fr k cq ε | |
251 | -fr k ques ε | |
252 | -fr k cques ε | |
253 | -en kt ct ε | |
254 | - m m ε | |
255 | -en-fr m me ε | |
256 | - n n ε | |
257 | -en-fr n ne ε | |
258 | -fr n nes ε | |
259 | -fr n ng ε | |
260 | - r r ε | |
261 | -en-fr r re ε | |
262 | -fr r res ε | |
263 | -fr r rs ε | |
264 | -en r rh ε | |
265 | - s s ε | |
266 | -en-fr s se ε | |
267 | -en-fr s ce ε | |
268 | -en s th ε | |
269 | - t t ε | |
270 | -fr t te ε | |
271 | -fr t tes ε | |
272 | -fr t thes ε | |
273 | -en t th ε | |
274 | -en t the ε | |
275 | - | |
276 | - e e j | |
277 | -en ej ey ε | |
278 | - | |
279 | - a a ε | |
280 | -en a ah ε | |
281 | -en aja ayah ε | |
282 | - | |
283 | -acro {A}a A | |
284 | -acro {B}b B | |
285 | -acro {C}c C | |
286 | -acro {C}k C | |
287 | -acro {Ć}t′ Ć | |
288 | -acro {D}d D | |
289 | -acro {E}e E | |
290 | -acro {F}f F | |
291 | -acro {G}g G | |
292 | -acro {H}h H | |
293 | -acro {I}j I | |
294 | -acro {J}j J | |
295 | -acro {K}k K | |
296 | -acro {L}l L | |
297 | -acro {Ł}ł Ł | |
298 | -acro {M}m M | |
299 | -acro {N}n N | |
300 | -acro {O}o O | |
301 | -acro {P}p P | |
302 | -acro {R}r R | |
303 | -acro {S}s S | |
304 | -acro {Ś}s′ Ś | |
305 | -acro {T}t T | |
306 | -acro {U}u U | |
307 | -acro {V}v V | |
308 | -acro {W}v W | |
309 | -acro {X}ks X | |
310 | -acro {Y}y Y | |
311 | -acro {Z}z Z | |
312 | -acro {Ż}ž Ż | |
313 | -acro {J}jot J | |
314 | -acro {Z}zet Z | |
315 | -acro {Ż}žet Ż | |
316 | -acro {v}v V | |
317 | -acro {x}ks X | |
318 | -acro {j}jot J | |
319 | -acro {z}zet z | |
320 | -acro {ż}žet Ż | |
321 | - | |
322 | -acro a A ε | |
323 | - | |
324 | -@rules | |
325 | -pl p′ pi ω | |
326 | -pl p′ p iκ | |
327 | -#pl p p δ | |
328 | -#pl p p j | |
329 | -pl pj pi ρ | |
330 | -pl b′ bi ω | |
331 | -pl b′ b iκ | |
332 | -#pl b b δ | |
333 | -pl bj bi ρ | |
334 | -#zbitka | |
335 | -#pl b b j | |
336 | -pl m′ mi ω | |
337 | -pl m′ m iκ | |
338 | -#pl m m δ | |
339 | -pl m′j mi ρ | |
340 | -pl f′ fi ω | |
341 | -pl f′ f iκ | |
342 | -#pl f f δ | |
343 | -pl fj fi ρ | |
344 | -pl v′ wi ω | |
345 | -pl v′ w iκ | |
346 | -pl v w δ | |
347 | -pl vj wi ρ | |
348 | -#zbitka | |
349 | -#pl v w j | |
350 | -pl t′ ć λ | |
351 | -#zbitki | |
352 | -#pl t′ ć u | |
353 | -#pl t′ ć a | |
354 | -#pl t′ ć i | |
355 | -pl t′ ci ω | |
356 | -#pl c c j | |
357 | -pl t′ c iκ | |
358 | -#pl c c μ | |
359 | -pl d′ dź λ | |
360 | -pl d′ dzi ω | |
361 | -pl d′ dz iκ | |
362 | -pl ʒ dz δ | |
363 | -#zbitka | |
364 | -#pl ʒ dz j | |
365 | -#pl t t δ | |
366 | -#pl t t j | |
367 | -pl tʲ ti ω | |
368 | -pl tʲ t iκ | |
369 | -pl tj ti ρ | |
370 | -#pl d d ξ | |
371 | -pl dʲ di ω | |
372 | -pl dʲ d iκ | |
373 | -#pl d d j | |
374 | -pl dj di ρ | |
375 | -pl č cz δ | |
376 | -pl čʲ czi ω | |
377 | -pl čʲ cz iκ | |
378 | -#pl čʲ cz j | |
379 | -pl ǯ dż δ | |
380 | -pl ǯʲ dżi ω | |
381 | -pl ǯʲ dż iκ | |
382 | -pl ǯj dżi ρ | |
383 | -pl s′ ś λ | |
384 | -pl s′ si ω | |
385 | -#pl s s j | |
386 | -pl s′ s iκ | |
387 | -#pl s s γ | |
388 | -pl z′ ź λ | |
389 | -pl z′ zi ω | |
390 | -#pl z z j | |
391 | -pl z′ z iκ | |
392 | -#pl z z δ | |
393 | -pl š sz δ | |
394 | -#pl šʲ sz j | |
395 | -pl šʲ szi ω | |
396 | -pl šʲ sz iκ | |
397 | -pl ž ż δ | |
398 | -pl žʲ żi ω | |
399 | -pl žʲ ż iκ | |
400 | -pl žj żi ρ | |
401 | -#pl l l δ | |
402 | -pl lʲ li ω | |
403 | -pl l l iκ | |
404 | -#pl l l j | |
405 | -#pl ł ł δ | |
406 | -#zbitka | |
407 | -#pl ł ł i | |
408 | -#zbitka | |
409 | -#pl ł ł j | |
410 | -pl lj li ρ | |
411 | -pl ř rz δ | |
412 | -#zbitka | |
413 | -#pl ř rz j | |
414 | -pl r r zi | |
415 | -#pl r r γ | |
416 | -#pl r r j | |
417 | -pl rʲ ri ω | |
418 | -pl rʲ r iκ | |
419 | -pl rj ri ρ | |
420 | -pl n′ ń λ | |
421 | -pl n′ ni ω | |
422 | -pl n′ n iκ | |
423 | -#pl n n δ | |
424 | -#pl n n j | |
425 | -pl n′j ni ρ | |
426 | -pl k′ ki ω | |
427 | -pl k′ k iκ | |
428 | -#pl k k δ | |
429 | -#pl k k j | |
430 | -pl k′j ki ρ | |
431 | -pl g′ gi ω | |
432 | -pl g′ g iκ | |
433 | -#pl g g δ | |
434 | -pl g′j gi ρ | |
435 | -pl x ch δ | |
436 | -pl xʲ chi ω | |
437 | -pl xʲ ch iκ | |
438 | -pl xʲj chi ρ | |
439 | -#pl h h δ | |
440 | -pl hʲ hi ω | |
441 | -pl hʲ h iκ | |
442 | -pl mar mar z | |
443 | -pl m′er mier z | |
444 | -pl n′e nie i | |
445 | -#pl a a σ | |
446 | -pl aʲ a i | |
447 | -#pl a a i | |
448 | -#pl e e σ | |
449 | -pl eʲ e i | |
450 | -#pl e e i | |
451 | -#pl o o σ | |
452 | -pl oʲ o i | |
453 | -#pl o o i | |
454 | -#pl ó ó σ | |
455 | -pl óʲ ó i | |
456 | -#pl ó ó i | |
457 | -#pl u u σ | |
458 | -pl uʲ u i | |
459 | -#pl u u i | |
460 | -#pl i i σ | |
461 | -pl iʲ i i | |
462 | -#pl i i i | |
463 | -#pl y y σ | |
464 | -pl yʲ y i | |
465 | -#pl y y i | |
466 | -#pl ą ą σ | |
467 | -#pl ę ę σ | |
468 | -#pl j j | |
469 | -#pl A A | |
470 | -#pl B B | |
471 | -#pl C C | |
472 | -#pl Ć Ć | |
473 | -#pl D D | |
474 | -#pl E E | |
475 | -#pl F F | |
476 | -#pl G G | |
477 | -#pl H H | |
478 | -#pl I I | |
479 | -#pl J J | |
480 | -#pl K K | |
481 | -#pl L L | |
482 | -#pl Ł Ł | |
483 | -#pl M M | |
484 | -#pl N N | |
485 | -#pl O O | |
486 | -#pl P P | |
487 | -#pl R R | |
488 | -#pl S S | |
489 | -#pl Ś Ś | |
490 | -#pl T T | |
491 | -#pl U U | |
492 | -#pl W W | |
493 | -#pl Y Y | |
494 | -#pl Z Z | |
495 | -#pl Ż Ż | |
496 | -#pl - - | |
497 | -#pl χ́ chi | |
498 | -#pl h́ hi | |
499 | - | |
500 | -fr {ch}š ch γ | |
501 | -fr {q}k q γ | |
502 | -fr {ng}n ng γ | |
503 | -en {tch}č tch γ | |
504 | -en {w}ł w | |
505 | -en {leigh}l leigh γ | |
506 | -de {au}ał au γ | |
507 | -de {sch}š sch γ | |
508 | -de {tsch}č tsch γ | |
509 | -de {z}c z γ | |
510 | - | |
511 | -en {ay}aj ay γ | |
512 | -en {ey}ej ey γ | |
513 | -en {oy}oj oy γ | |
514 | - | |
515 | -en {dh}dʲ dhi ω | |
516 | -en {dh}dʲ dh iκ | |
517 | -en {dh}d dh δ | |
518 | -en {gh}g′ ghi ω | |
519 | -en {gh}g′ gh iκ | |
520 | -en {gh}g gh δ | |
521 | -en {kh}k′ khi ω | |
522 | -en {kh}k′ kh iκ | |
523 | -en {kh}k kh δ | |
524 | -en {th}tʲ thi ω | |
525 | -en {th}tʲ th iκ | |
526 | -en {th}t th δ | |
527 | -en {v}v′ vi ω | |
528 | -en {v}v′ v iκ | |
529 | -en {v}v v δ | |
530 | -en {v}vj vi ρ | |
531 | -de-en-fr {x}ks′ xi ω | |
532 | -de-en-fr {x}ks′ x iκ | |
533 | -de-en-fr {x}ks x δ | |
534 | - | |
535 | -#lemma=e/y gender=m1 | |
536 | -fr {dieu}dʲe dieu α | |
537 | -fr {dieu}dʲi dieu β | |
538 | -fr {quieu}k′e quieu α | |
539 | -fr {quieu}k′i quieu β | |
540 | -fr {lieu}lʲe lieu α | |
541 | -fr {lieu}lʲi lieu β | |
542 | -en {rie}rʲe rie α | |
543 | -en {rie}rʲi rie β | |
544 | -en {gie}ǯʲe gie α | |
545 | -en {gie}ǯʲi gie β | |
546 | -en {kie}k′e kie α | |
547 | -en {kie}k′i kie β | |
548 | -en {tie}tʲe tie α | |
549 | -en {tie}tʲi tie β | |
550 | -en {pie}p′e pie α | |
551 | -en {pie}p′i pie β | |
552 | -en {die}dʲe die α | |
553 | -en {die}dʲi die β | |
554 | -en {bee}b′e bee α | |
555 | -en {bee}b′i bee β | |
556 | - | |
557 | -#lemma=e gender=m1 | |
558 | -fr {mée}me mée α | |
559 | -de {ge}g′e ge α | |
560 | -de {ke}k′e ke α | |
561 | - | |
562 | -#lemma=y gender=m1 | |
563 | -en {by}b′ by ’eά | |
564 | -en {by}b′i by β | |
565 | -en {dy}dʲ dy ’eά | |
566 | -en {dy}dʲi dy β | |
567 | -es {dí}dʲ dí eά | |
568 | -es {dí}dʲi dí β | |
569 | -fr {phy}f′ phy ’eά | |
570 | -fr {phy}f′i phy β | |
571 | -fr {guy}g′ guy ’eά | |
572 | -fr {guy}g′i guy β | |
573 | -de-en {ky}k′ ky ’eά | |
574 | -de-en {ky}k′i ky β | |
575 | -en {my}m′ my ’eά | |
576 | -en {my}m′i my β | |
577 | -fr {li}l li eά | |
578 | -fr {li}l l iβ | |
579 | -en {ly}l ly ’eά | |
580 | -en {ly}li ly β | |
581 | -en-fr {ry}rʲ ry ’eά | |
582 | -en-fr {ry}rʲi ry β | |
583 | -fr {sy}sʲ sy ’eά | |
584 | -fr {sy}sʲi sy β | |
585 | -en {cy}sʲ cy ’eά | |
586 | -en {cy}sʲi cy β | |
587 | -en {thy}tʲ thy ’eά | |
588 | -en {thy}tʲi thy β | |
589 | - | |
590 | -#lemma=e/ndm gender=m1 | |
591 | -fr {chais}še chais ’ | |
592 | -fr {lais}le lais ’ | |
593 | -fr {nais}ne nais ’ | |
594 | -fr {rès}re rès ’ | |
595 | - | |
596 | -#lemma=ε | |
597 | -en-fr {de}d de ’ | |
598 | -en-fr {de}d de ε | |
599 | -en {fe}f fe ’ | |
600 | -en {fe}f fe ε | |
601 | -fr {phe}f phe ’ | |
602 | -fr {phe}f phe ε | |
603 | -en {ge}ǯ ge ’ | |
604 | -en {ge}ǯ ge ε | |
605 | -fr {gue}g gue ’ | |
606 | -fr {gue}g gue ε | |
607 | -en {ke}k ke ’ | |
608 | -en {ke}k ke ε | |
609 | -fr {que}k que ’ | |
610 | -fr {que}k que ε | |
611 | -en-fr {le}l le ’ | |
612 | -en-fr {le}l le ε | |
613 | -en-fr {me}m me ’ | |
614 | -en-fr {me}m me ε | |
615 | -en-fr {ne}n ne ’ | |
616 | -en-fr {ne}n ne ε | |
617 | -fr {gne}n′ gne ’ | |
618 | -fr {gne}n′ gne ε | |
619 | -en-fr {re}r re ’ | |
620 | -en-fr {re}r re ε | |
621 | -en {se}s se ’ | |
622 | -en {se}s se ε | |
623 | -en-fr {ce}s ce ’ | |
624 | -en-fr {ce}s ce ε | |
625 | -fr {che}š che ’ | |
626 | -fr {che}š che ε | |
627 | -en-fr {te}t te ’ | |
628 | -en-fr {te}t te ε | |
629 | -en {the}t the ’ | |
630 | -en {the}t the ε | |
631 | -en-fr {ve}v ve ’ | |
632 | -en-fr {ve}v ve ε | |
633 | -en {we}ł we ’ | |
634 | -en {we}ł we ε | |
635 | -fr {se}z se ’ | |
636 | -fr {se}z se ε | |
637 | -fr {ge}ž ge ’ | |
638 | -fr {ge}ž ge ε | |
639 | -#z wyjątkiem sg:loc.voc | |
640 | -en {oe}oł oe ’ | |
641 | -en {oe}oł oe ε | |
642 | - | |
643 | -de-en-fr ’ γ | |
644 | - | |
645 | - n n g | |
646 | - z z γ | |
647 | - b b e | |
648 | - b b y | |
649 | - d d y | |
650 | - m m y | |
651 | - s s y | |
652 | - c c y | |
653 | - r r y | |
654 | - k k y | |
655 | - l l y | |
656 | - l l a | |
657 | - n n a | |
658 | - r r è | |
659 | - d d e | |
660 | - f f e | |
661 | - p p h | |
662 | - g g e | |
663 | - g g u | |
664 | - k k e | |
665 | - q q u | |
666 | - l l e | |
667 | - m m e | |
668 | - n n e | |
669 | - g g n | |
670 | - r r e | |
671 | - s s e | |
672 | - c c e | |
673 | - c c h | |
674 | - t t e | |
675 | - t t h | |
676 | - v v e | |
677 | - w w e | |
678 | - s s e | |
679 | - o o e | |
680 | - m m é | |
681 | - a a y | |
682 | - e e y | |
683 | - o o y | |
684 | - | |
685 | -acro a A ε | |
686 | - | |
687 | -acro {A}a A | |
688 | -acro {B}b B | |
689 | -acro {C}c C | |
690 | -acro {C}k C | |
691 | -acro {Ć}t′ Ć | |
692 | -acro {D}d D | |
693 | -acro {E}e E | |
694 | -acro {F}f F | |
695 | -acro {G}g G | |
696 | -acro {H}h H | |
697 | -acro {I}j I | |
698 | -acro {J}j J | |
699 | -acro {K}k K | |
700 | -acro {L}l L | |
701 | -acro {Ł}ł Ł | |
702 | -acro {M}m M | |
703 | -acro {N}n N | |
704 | -acro {O}o O | |
705 | -acro {P}p P | |
706 | -acro {R}r R | |
707 | -acro {S}s S | |
708 | -acro {Ś}s′ Ś | |
709 | -acro {T}t T | |
710 | -acro {U}u U | |
711 | -acro {V}v V | |
712 | -acro {W}v W | |
713 | -acro {X}ks X | |
714 | -acro {Y}y Y | |
715 | -acro {Z}z Z | |
716 | -acro {Ż}ž Ż | |
717 | -acro {J}jot J-ot δ | |
718 | -acro {Z}zet Z-et δ | |
719 | -acro {Ż}žet Ż-et δ | |
720 | -acro {z}zet z-et δ | |
721 | - | |
722 | -acro {B}b′e B-ie ε | |
723 | -acro {D}d′e D-zie ε | |
724 | -acro {F}f′e F-ie ε | |
725 | -acro {M}m′e M-ie ε | |
726 | -acro {N}n′e N-ie ε | |
727 | -acro {P}p′e P-ie ε | |
728 | -acro {R}ře R-ze ε | |
729 | -acro {S}s′e S-ie ε | |
730 | -acro {T}t′e -cie ε | |
731 | -acro {V}v′e V-ie ε | |
732 | -acro {W}v W-ie ε | |
733 | -acro {X}ks′e X-ie ε | |
734 | -acro {Z}z Z-ie ε | |
735 | -acro {J}jot′e J-ocie ε | |
736 | -acro {Z}zet′e Z-ecie ε | |
737 | -acro {Ż}žet′e Ż-ecie ε | |
738 | - | |
739 | -acro {B}b′e Bie ε | |
740 | -acro {D}d′e Dzie ε | |
741 | -acro {F}f′e Fie ε | |
742 | -acro {M}m′e Mie ε | |
743 | -acro {N}n′e Nie ε | |
744 | -acro {P}p′e Pie ε | |
745 | -acro {R}ře Rze ε | |
746 | -acro {S}s′e Sie ε | |
747 | -acro {T}t′e cie ε | |
748 | -acro {V}v′e Vie ε | |
749 | -acro {W}v Wie ε | |
750 | -acro {X}ks′e Xie ε | |
751 | -acro {Z}z Zie ε | |
752 | -acro {J}jot′e Jocie ε | |
753 | -acro {Z}zet′e Zecie ε | |
754 | -acro {Ż}žet′e Żecie ε | |
755 | - | |
756 | -acro b′e b-ie ε | |
757 | -acro d′e d-zie ε | |
758 | -acro f′e f-ie ε | |
759 | -acro m′e m-ie ε | |
760 | -acro n′e n-ie ε | |
761 | -acro p′e p-ie ε | |
762 | -acro ře r-ze ε | |
763 | -acro s′e s-ie ε | |
764 | -acro t′e -cie ε | |
765 | -acro {v}v′e v-ie ε | |
766 | -acro v w-ie ε | |
767 | -acro {x}ks′e x-ie ε | |
768 | -acro z z-ie ε | |
769 | -acro {j}jot′e j-ocie ε | |
770 | -acro {z}zet′e z-ecie ε | |
771 | -acro {ż}žet′e ż-ecie ε | |
772 | - | |
773 | -acro {T}t′e CIE ε | |
774 | -acro {A}a{T}t′e acie ε | |
775 | -acro {E}e{T}t′e ecie ε | |
776 | -acro {I}j{T}t′e icie ε | |
777 | -acro {O}o{T}t′e ocie ε | |
778 | -acro {U}u{T}t′e ucie ε | |
779 | - | |
780 | -acro {C}k′i C-i ε | |
781 | -acro {C}k′em C-iem ε | |
782 | -acro {G}g′i G-i ε | |
783 | -acro {G}g′em G-iem ε | |
784 | -acro {J}ji J-i ε | |
785 | -acro {K}k′i K-i ε | |
786 | -acro {K}k′em K-iem ε | |
787 | -acro {L}li L-i ε | |
788 | -acro - γ | |
789 | - | |
790 | - |
morphology/data/fonetics_pl_old.dic deleted
1 | -@symbols | |
2 | -ω a ą e ę o ó u | |
3 | -δ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y z ź ż - ε | |
4 | -γ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y ź ż - ε | |
5 | -ξ a ą b c ć d e ę f g h k l ł m n ń o ó p r s ś t u w y - ε | |
6 | -μ a ą b c ć d e ę f g k l ł m n ń o ó p r s ś t u w y ź ż - ε | |
7 | -λ b c ć d f g h k l ł m n ń p r s ś t w z ź ż - ε | |
8 | -κ b c ć d f g h j k l ł m n ń p r s ś t w z ź ż - ε | |
9 | -σ a ą b c ć d e ę f g i h k l ł m n ń o ó p r s ś t u w y z ź ż - ε | |
10 | - | |
11 | -@rules | |
12 | -ṕ pi ω | |
13 | -ṕ p iκ | |
14 | -p p δ | |
15 | -b́ bi ω | |
16 | -b′ bj ω | |
17 | -b́ b iκ | |
18 | -b b δ | |
19 | -f́ fi ω | |
20 | -f́ f iκ | |
21 | -f f δ | |
22 | -v́ wi ω | |
23 | -v́ w iκ | |
24 | -v w δ | |
25 | -ć ć λ | |
26 | -ć ci ω | |
27 | -c′ cj ω | |
28 | -ć c iκ | |
29 | -c c μ | |
30 | -ʒ́ dź λ | |
31 | -ʒ́ dzi ω | |
32 | -ʒ́ dz iκ | |
33 | -ʒ dz δ | |
34 | -t t δ | |
35 | -t′ ti ω | |
36 | -t′ t iκ | |
37 | -d d ξ | |
38 | -d′ di ω | |
39 | -d′ d iκ | |
40 | -č cz δ | |
41 | -ǯ dż δ | |
42 | -ś ś λ | |
43 | -ś si ω | |
44 | -s′ sj ω | |
45 | -ś s iκ | |
46 | -s s γ | |
47 | -ź ź λ | |
48 | -ź zi ω | |
49 | -z′ zj ω | |
50 | -ź z iκ | |
51 | -z z δ | |
52 | -š sz δ | |
53 | -ž ż δ | |
54 | -l l δ | |
55 | -l′ li ω | |
56 | -l′ l iκ | |
57 | -ł ł δ | |
58 | -ř rz δ | |
59 | -r r γ | |
60 | -r′ ri ω | |
61 | -r′ r iκ | |
62 | -ḿ mi ω | |
63 | -ḿ m iκ | |
64 | -m m δ | |
65 | -ń ń λ | |
66 | -ń ni ω | |
67 | -ń n iκ | |
68 | -n n δ | |
69 | -ḱ ki ω | |
70 | -ḱ k iκ | |
71 | -k k δ | |
72 | -ǵ gi ω | |
73 | -ǵ g iκ | |
74 | -g g δ | |
75 | -χ ch δ | |
76 | -x′ chi ω | |
77 | -x′ ch iκ | |
78 | -h h δ | |
79 | -h′ hi ω | |
80 | -h′ h iκ | |
81 | -a a σ | |
82 | -a′ aj | |
83 | -e e σ | |
84 | -e′ ej | |
85 | -o o σ | |
86 | -o′ oj | |
87 | -ó ó σ | |
88 | -ó′ ój | |
89 | -u u σ | |
90 | -u′ uj | |
91 | -i i σ | |
92 | -i′ ij | |
93 | -y y σ | |
94 | -y′ yj | |
95 | -ą ą σ | |
96 | -ę ę σ | |
97 | -j j | |
98 | -A A | |
99 | -B B | |
100 | -C C | |
101 | -D D | |
102 | -E E | |
103 | -F F | |
104 | -G G | |
105 | -H H | |
106 | -I I | |
107 | -J J | |
108 | -K K | |
109 | -L L | |
110 | -Ł Ł | |
111 | -M M | |
112 | -N N | |
113 | -O O | |
114 | -P P | |
115 | -R R | |
116 | -S S | |
117 | -Ś Ś | |
118 | -T T | |
119 | -U U | |
120 | -W W | |
121 | -Y Y | |
122 | -Z Z | |
123 | -Ż Ż | |
124 | -- - | |
125 | -#χ́ chi | |
126 | -#h́ hi | |
127 | - |
morphology/data/interp_rules.dic
... | ... | @@ -334,8 +334,10 @@ |
334 | 334 | * cat=ndm subst:sg.pl:nom.gen.dat.acc.inst.loc.voc:n:ncol # 836 Aachen Age Aires:s Angeles Argos:s1 Arkansas:s1 Arkansas:s3 Arnhem Auschwitz Austerlitz Baku Betlejem Birkenau Bizancjum Bonn Borneo Borodino Buffalo:s1 Burgas CB-radio |
335 | 335 | * cat=ndm subst:sg.pl:nom.gen.dat.acc.inst.loc.voc:m3 # 147 Aachen Arkansas:s1 Arkansas:s2 Bator Kansas:s2 Kara-Kum Kent Kyzył-Kum Michigan Missisipi:s1 Mississippi:s2 Missouri:s1 Montgomery:s3 Szoa Tet Ułan Westminster Windows Wisconsin Woodstock |
336 | 336 | * cat=ndm subst:sg.pl:nom.gen.dat.acc.inst.loc.voc:m2 # 36 aguti aksis argali bankiwa boa:s1 czau-czau dingo dodo emu ferrari galago grizli kagu karibu kiwi:s2 koati koendu kuandu maki mehari |
337 | -#* cat=ndm subst:sg.pl:nom.gen.dat.acc.inst.loc.voc:m1 # 90 Allende Ante Bambo Bantu Bartoszcze Belmondo Brando Buffalo:s2 Capone Caruso Castro Crusoe Curie Defoe Diego Domingo Fo Gard Giuseppe Hugo:s2 | |
337 | +* cat=ndm subst:sg.pl:nom.gen.dat.acc.inst.loc.voc:m1 # 90 Allende Ante Bambo Bantu Bartoszcze Belmondo Brando Buffalo:s2 Capone Caruso Castro Crusoe Curie Defoe Diego Domingo Fo Gard Giuseppe Hugo:s2 | |
338 | +* cat=ndm subst:sg.pl:nom.gen.dat.acc.inst.loc.voc:m1|depr:pl:nom.acc.voc:m2 # | |
338 | 339 | * cat=ndm subst:sg.pl:nom.gen.dat.acc.inst.loc.voc:f # 150 Abisag Abiszag Akropolis Ananke Arachne Arkansas:s2 Ata:s Babel Beatrycze Berenike Carmen Colorado:s2 Dafne Demeter Dolores Doris Dudziak:s2 Edith Ferdydurke Gabi |
340 | +* cat=ndm subst:pl:nom.gen.dat.acc.inst.loc.voc:n:pt # | |
339 | 341 | |
340 | 342 | * cat=noun flex=ego lemma=a subst:sg:gen.acc:m1 # 9 burgrabia gograbia grabia hrabia margrabia murgrabia sędzia:s1 wicehrabia współsędzia |
341 | 343 | * cat=noun flex=ego lemma=a subst:sg:gen:m1 # 9 burgrabia gograbia grabia hrabia margrabia murgrabia sędzia:s1 wicehrabia współsędzia |
... | ... | @@ -424,8 +426,6 @@ |
424 | 426 | * cat=adj flex=i lemma=ε adj:pl:nom:m1:pos # 4 kontent:a niekontent:a nierad:a rad:a |
425 | 427 | * cat=adj flex=ych lemma=ε adj:pl:gen.loc:m1.m2.m3.f.n:pos|adj:pl:acc:m1:pos # 22 czyj jeden:a mój:a nasz niczyj niejeden:a1 niejeden:a2 niesamoswój nieswój niewart oboj obój:a pewien sam:a samojeden samoswój swój twój:a wart:a wasz |
426 | 428 | * cat=adj flex=ymi lemma=ε adj:pl:inst:m1.m2.m3.f.n:pos # 23 czyj jeden:a mój:a nasz niczyj niejeden:a1 niejeden:a2 niesamoswój nieswój niewart oboj obój:a pewien sam:a samojeden samoswój swój twój:a wart:a wasz |
427 | -* cat=adj flex=ε lemma=ε adj:sg.pl:nom.gen.dat.acc.inst.loc.voc:m1.m2.m3.f.n:pos|adja # 1 pop:a | |
428 | -* cat=adj flex=ε lemma=ε adj:sg.pl:nom.gen.dat.acc.inst.loc.voc:m1.m2.m3.f.n:pos # 26 a-z a-ż beż:a blond:a ciemnoblond:a ck cool:a dum-dum fest:a frysz ful:a git:a instant jasnoblond lilaróż:a maksi nonajron:a okej:a open perfekt:a | |
429 | 429 | |
430 | 430 | cat=adj:grad pref=ε flex=ą lemma=y adj:sg:acc.inst:f:com # 1076 absurdalny adekwatny agresywny aktualny aktywny akuratny ambitny apetyczny arystokratyczny atrakcyjny autentyczny baczny bajeczny banalny barwny bezbożny:a bezbronny bezczelny bezecny bezpieczny |
431 | 431 | cat=adj:grad pref=ε flex=ymi lemma=y adj:pl:inst:m1.m2.m3.f.n:com # 1076 absurdalny adekwatny agresywny aktualny aktywny akuratny ambitny apetyczny arystokratyczny atrakcyjny autentyczny baczny bajeczny banalny barwny bezbożny:a bezbronny bezczelny bezecny bezpieczny |
... | ... |
morphology/dict.ml
... | ... | @@ -172,6 +172,7 @@ let split_language lang_filename in_path filename out_path = |
172 | 172 | let dict_map = Xlist.fold dict StringMap.empty (fun dict_map e -> |
173 | 173 | try |
174 | 174 | let lang = StringMap.find map e.lemma in |
175 | + (* let lang = "all" in *) | |
175 | 176 | StringMap.add_inc dict_map lang [e] (fun l -> e :: l) |
176 | 177 | with Not_found -> dict_map) in |
177 | 178 | StringMap.iter dict_map (fun lang dict -> |
... | ... | @@ -214,10 +215,43 @@ let rec get_aspect lemma = function |
214 | 215 | | _ -> get_aspect lemma l) |
215 | 216 | | [] -> failwith ("get_aspect: " ^ lemma) |
216 | 217 | |
218 | +let epsilon_lemmata = StringSet.of_list [ | |
219 | + "Berkeley"; "Blake"; "Bourdelle"; "Boyle"; "Boy"; "Braille"; "Braque"; "Brooke"; "Halley"; | |
220 | + "Constable"; "Corneille"; "Delavigne"; "Doyle"; "Drake"; "Dunaway"; "Faraday"; "Gable"; "Gay"; | |
221 | + "George"; "Heaney"; "Google"; "Desargues"; "Disney"; "Doumergue"; "Gaulle"; "Hemingway"; "Hubble"; | |
222 | + "Huxley"; "Jokai"; "Joule"; "Jókai"; "Lisle"; "Locke"; "Losey"; "Macaulay"; "May"; | |
223 | + "McCartney"; "Remarque"; "Searle"; "Shelley"; "Sisley"; "Stanley"; "Thackeray"; "Updike"; "Winfrey"; | |
224 | + "assemblage"; "boutique"; "branle"; "cartridge"; "chippendale"; "collage"; "collége"; "decoupage"; "dodge"; | |
225 | + "entourage"; "freestyle"; "grisaille"; "grunge"; "joule"; "quiche"; "remake"; "rocaille"; "scrabble"; | |
226 | + "siècle"; "playboy"; "oldboy"; "jockey"; "image"; "college"; "cockney"; "Montaigne"; ""; | |
227 | + "allemande"; "anglaise"; "beguine"; "breakdance"; "courante"; "ensemble"; "high-life"; "iPhone"; "iphone"; | |
228 | + "rolls-royce"; "Redgrave"; "cowboy"; "drive"; "Nightingale"; "Presley"; ""; ""; ""; | |
229 | + ""; ""; ""; ""; ""; ""; ""; ""; ""; | |
230 | + ""; ""; ""; ""; ""; ""; ""; ""; ""; | |
231 | + ""; ""; ""; ""; ""; ""; ""; ""; ""; | |
232 | + ] | |
233 | + | |
234 | +let e_lemmata = StringSet.of_list [ | |
235 | + "Barrès"; "Beaumarchais"; "Marchais"; "Montesquieu"; "Rabelais"; "Resnais"; "Richelieu"; ""; ""; | |
236 | + ""; ""; ""; ""; ""; ""; ""; ""; ""; | |
237 | + ""; ""; ""; ""; ""; ""; ""; ""; ""; | |
238 | + ] | |
239 | + | |
240 | +let y_lemmata = StringSet.of_list [ | |
241 | + "Bogorodckij"; "Gaudí"; "Szeptyćkyj"; "Toynbee"; "Trubieckoj"; "Wołżskij"; ""; ""; ""; | |
242 | + ""; ""; ""; ""; ""; ""; ""; ""; ""; | |
243 | + ""; ""; ""; ""; ""; ""; ""; ""; ""; | |
244 | + ""; ""; ""; ""; ""; ""; ""; ""; ""; | |
245 | + ] | |
246 | + | |
217 | 247 | let get_lemma_suf lemma = |
248 | + let lemma = Stem.simplify_lemma lemma in | |
249 | + if StringSet.mem epsilon_lemmata lemma then "ε" else | |
250 | + if StringSet.mem e_lemmata lemma then "e" else | |
251 | + if StringSet.mem y_lemmata lemma then "y" else | |
218 | 252 | let lemma_suf = |
219 | 253 | if lemma = "" then "" else |
220 | - List.hd (List.rev (Xunicode.utf8_chars_of_utf8_string (Stem.simplify_lemma lemma))) in | |
254 | + List.hd (List.rev (Xunicode.utf8_chars_of_utf8_string lemma)) in | |
221 | 255 | match lemma_suf with |
222 | 256 | "a" -> "a" |
223 | 257 | | "e" -> "e" |
... | ... | @@ -366,7 +400,7 @@ let merge_interps lemma forms = |
366 | 400 | | _,["depr:pl:nom.acc.voc:m2";"subst:sg.pl:nom.gen.dat.acc.inst.loc.voc:m1"] -> {empty_form with orth=orth; interp="subst:sg.pl:nom.gen.dat.acc.inst.loc.voc:m1|depr:pl:nom.acc.voc:m2"} :: forms |
367 | 401 | | _,[interp] -> {empty_form with orth=orth; interp=interp} :: forms |
368 | 402 | | _,interps -> |
369 | - (* print_endline ("merge_interps: " (*^ lemma_suf*) ^ " [\"" ^ String.concat "\";\"" interps ^ "\"]"); *) | |
403 | + (* print_endline ("merge_interps: " ^ lemma_suf ^ " " ^ orth ^ " [\"" ^ String.concat "\";\"" interps ^ "\"]"); *) | |
370 | 404 | Xlist.fold interps forms (fun forms interp -> |
371 | 405 | {empty_form with orth=orth; interp=interp} :: forms)) |
372 | 406 | |
... | ... | @@ -460,7 +494,7 @@ let find_kolwiek_suffixes dict = |
460 | 494 | |
461 | 495 | let exceptional_lemmata = StringSet.of_list ([ |
462 | 496 | (* wiele stemów *) |
463 | - "Apollo"; "Aujeszky"; "Białystok"; "Gózd"; "Krasnystaw"; "Różanystok"; "Wielkanoc"; "białagłowa"; | |
497 | +(* "Apollo"; "Aujeszky"; "Białystok"; "Gózd"; "Krasnystaw"; "Różanystok"; "Wielkanoc"; "białagłowa"; | |
464 | 498 | "deszcz"; "imćpan"; "iściec"; "otrząs"; "rzeczpospolita"; "wilczełyko"; "woleoczko"; |
465 | 499 | |
466 | 500 | "prapraojciec"; "praojciec"; "ojciec"; "współbrat"; "spółbrat"; "półbrat"; "brat"; |
... | ... | @@ -569,9 +603,12 @@ let exceptional_lemmata = StringSet.of_list ([ |
569 | 603 | "nieunixowość"; "niesurvivalowy"; "niesurvivalowość"; "niesoftware’owy"; "niesoftware’owość"; "nierock’n’rollowy"; "nierock’n’rollowość"; "nierock’n’rollowo"; "niequmrańskość"; |
570 | 604 | "niequmrański"; "niequizowy"; "niequizowość"; "niequeerowość"; "niequeerowo"; "niequadowy"; "nieoxfordzkość"; "nieoxfordzki"; "nienovellowskość"; "nienovellowski"; "nienewage'owy"; "nieliverpoolskość"; |
571 | 605 | "nieliverpoolski"; "niekickboxingowy"; "niekickboxingowość"; "nieheavymetalowy"; "nieheavymetalowość"; "nieheavymetalowo"; "nieharvardzkość"; "nieharvardzki"; "niedeveloperskość"; |
572 | - "niedeveloperski"; "niedaviscupowy"; "niedaviscupowość"; "niebrexitowość"; "nieampexowy"; "nieampexowość"; "newage'owy"; "newage'owość"; "newage'owo"; "liverpoolskość"; "liverpoolski"; | |
606 | + "niedeveloperski"; "niedaviscupowy"; "niedaviscupowość"; "niebrexitowość"; "nieampexowy"; "nieampexowość"; "newage'owy"; "newage'owość"; "newage'owo"; "liverpoolskość"; "liverpoolski";*) | |
607 | + "Akademgorodok"; "berceuse"; "colloquium"; "cornflakes"; "dacia"; "Dziubanii"; "epeisodion"; "facsimile"; "felicia"; "Garcia"; "Giedroyc"; "glediczia"; | |
608 | + "głasnost"; "hippie"; "Kodaly"; "KRRiT"; "lancia"; "Murii"; "Nagy"; "PAGART"; "paparazzo"; "Praha"; "pudźa"; "Selye"; | |
609 | + "welwiczia"; "yuppi"; "yuppie"; "Zápolya"; "Zrínyi"; ""; ""; ""; ""; ""; ""; ""; | |
573 | 610 | ] (*@ File.load_lines "../morphology/data/obce.tab" @ File.load_lines "../morphology/data/akronimy.tab" @*) |
574 | - @ File.fold_tab "../morphology/data/obce_langs.tab" [] (fun l x -> List.hd x :: l) @ | |
611 | + (*@ File.fold_tab "../morphology/data/obce_langs.tab" [] (fun l x -> List.hd x :: l)*) @ | |
575 | 612 | (*File.load_lines "../morphology/data/nieregularne.tab" @ File.load_lines "results/interp_validated_verb.tab" @ *) |
576 | 613 | (*File.load_lines "results/interp_validated_noun.tab" @ File.load_lines "results/interp_validated_adj.tab" @ |
577 | 614 | File.load_lines "../morphology/data/validated_adj.tab" @ File.load_lines "../morphology/data/validated_noun.tab" @ |
... | ... | @@ -619,21 +656,57 @@ let lowercase_lu dict = |
619 | 656 | lemma2=Xunicode.lowercase_utf8_string entry.lemma2}) |
620 | 657 | |
621 | 658 | |
622 | -let fonetic_translation dict = | |
623 | - Xlist.fold dict [] (fun dict e -> | |
624 | - try | |
659 | +let fonetic_translation_entry e = | |
625 | 660 | (* let lemma = Stem.simplify_lemma e.lemma in *) |
626 | 661 | (* let phon_lemma = Fonetics.translate_and_check true Fonetics.rules Fonetics.rev_rules lemma in *) |
627 | - let phon_stem = Fonetics.translate(*_and_check*) true Fonetics.rules (*Fonetics.rev_rules*) e.stem in | |
662 | + let rules = match e.cat with | |
663 | + "noun" -> Fonetics.rules | |
664 | + | "" -> failwith "fonetic_translation" | |
665 | + | _ -> Fonetics.core_rules in | |
666 | + let phon_stem = Fonetics.translate true rules e.stem in | |
628 | 667 | {e with (*phon_lemma = phon_lemma;*) phon_stem=Xlist.map phon_stem (fun s -> s.phon); |
629 | 668 | forms = Xlist.map e.forms (fun f -> |
630 | - let phon_orth = Fonetics.translate(*_and_check*) true Fonetics.rules (*Fonetics.rev_rules*) f.orth in | |
631 | - {f with phon_orth = phon_orth})} :: dict | |
669 | + let phon_orth = Fonetics.translate true rules f.orth in | |
670 | + {f with phon_orth = phon_orth})} | |
671 | + | |
672 | +(* let fonetic_translation dict = | |
673 | + Xlist.fold dict [] (fun dict e -> | |
674 | + try (fonetic_translation_entry e) :: dict | |
632 | 675 | with |
633 | 676 | Fonetics.NotFound(x,s) -> printf "NF %s %s %s\n%!" e.lemma x s; dict |
634 | 677 | | Fonetics.NotEqual(x,s,t) -> printf "NE %s %s %s %s\n%!" e.lemma x s t; dict |
635 | 678 | | Fonetics.MulipleSolutions(x,s,l) -> printf "MS %s %s %s: %s\n%!" e.lemma x s (String.concat " " l); dict |
636 | - | _ -> dict) | |
679 | + | _ -> dict) *) | |
680 | + | |
681 | +let select_rev_rules e = | |
682 | + match e.cat with | |
683 | + "noun" -> Fonetics.rev_rules | |
684 | + | "" -> failwith "select_rev_rules" | |
685 | + | _ -> Fonetics.core_rev_rules | |
686 | + | |
687 | +let create_candidates interp_flag rules e = | |
688 | + let e = try fonetic_translation_entry e with _ -> print_endline ("fonetic_translation_entry: " ^ e.lemma); {e with forms=[]} in | |
689 | + let simple_lemma = Stem.simplify_lemma e.lemma in | |
690 | + let phon_rev_rules = select_rev_rules e in | |
691 | + let forms = Xlist.rev_map e.forms (fun f -> | |
692 | + (* if f.orth = "poljom" then printf "phon_orths: \n %s\n%!" (String.concat "\n " (Xlist.map f.phon_orth Fonetics.string_of_phon)); *) | |
693 | + let candidates = Xlist.fold f.phon_orth [] (fun candidates s -> | |
694 | + Xlist.fold (Rules.CharTrees.find rules s.phon) candidates (fun candidates (stem,rule) -> | |
695 | + let candidate_lemmas = Fonetics.translate_simple true phon_rev_rules (stem ^ rule.set) in | |
696 | + let b = Xlist.fold candidate_lemmas false (fun b candidate_lemma -> | |
697 | + (* if f.orth = "poljom" then (if candidate_lemma = simple_lemma then printf "E" else printf " "); | |
698 | + if f.orth = "poljom" then printf " %s %s %s %s\n%!" s.phon stem (string_of_rule rule) candidate_lemma; *) | |
699 | + candidate_lemma = simple_lemma || b) in | |
700 | + if b && ((not interp_flag) || f.interp = rule.interp) then (stem,rule,s) :: candidates else candidates)) in | |
701 | + {f with candidates=candidates}) in | |
702 | + {e with forms=forms} | |
703 | + | |
704 | +let phon_validate rules dict = | |
705 | + Xlist.rev_map dict (fun entry -> | |
706 | + let entry = create_candidates false rules entry in | |
707 | + let forms = Xlist.rev_map entry.forms (fun form -> | |
708 | + if form.candidates = [] then {form with validated=false} else {form with validated=true}) in | |
709 | + {entry with forms=forms}) | |
637 | 710 | |
638 | 711 | (*let validate rules dict = |
639 | 712 | Xlist.rev_map dict (fun entry -> |
... | ... | @@ -645,18 +718,6 @@ let fonetic_translation dict = |
645 | 718 | if candidates = [] then {form with validated=false} else {form with validated=true}) in |
646 | 719 | {entry with forms=forms})*) |
647 | 720 | |
648 | -let phon_validate rules dict = | |
649 | - Xlist.rev_map dict (fun entry -> | |
650 | - let simple_lemma = Stem.simplify_lemma entry.lemma in | |
651 | - let forms = Xlist.rev_map entry.forms (fun form -> | |
652 | - let candidates = Xlist.fold form.phon_orth [] (fun candidates s -> | |
653 | - Xlist.fold (Rules.CharTrees.find rules s.phon) candidates (fun candidates (stem,rule) -> | |
654 | - let candidate_lemmas = Fonetics.rev_translate2 true Fonetics.rev_rules (stem ^ rule.set) s.mapping in | |
655 | - let b = Xlist.fold candidate_lemmas false (fun b candidate_lemma -> candidate_lemma = simple_lemma || b) in | |
656 | - if b then (stem,rule) :: candidates else candidates)) in | |
657 | - if candidates = [] then {form with validated=false} else {form with validated=true}) in | |
658 | - {entry with forms=forms}) | |
659 | - | |
660 | 721 | let validate_lu rules dict = |
661 | 722 | Xlist.rev_map dict (fun entry -> |
662 | 723 | let candidates1 = Rules.CharTrees.find rules entry.lemma1 in |
... | ... | @@ -674,20 +735,19 @@ let validate_interp rules dict = |
674 | 735 | Xlist.rev_map dict (fun entry -> |
675 | 736 | let simple_lemma = Stem.simplify_lemma entry.lemma in |
676 | 737 | let forms = Xlist.rev_map entry.forms (fun form -> |
677 | - let candidates = Xlist.fold form.phon_orth [] (fun candidates s -> | |
678 | - Xlist.fold (Rules.CharTrees.find rules s.phon) candidates (fun candidates (stem,rule) -> | |
679 | - (* if rule.star = Ndm && not entry.ndm then candidates else | |
680 | - if rule.star <> Ndm && entry.ndm then candidates else *) | |
681 | - (* let candidate_lemma = Fonetics.rev_translate true Fonetics.rev_rules (stem ^ rule.set) s.mapping in | |
682 | - if candidate_lemma = simple_lemma && form.interp = rule.interp then | |
683 | - (stem,rule) :: candidates else candidates)) in *) | |
684 | - let candidate_lemmas = Fonetics.rev_translate2 true Fonetics.rev_rules (stem ^ rule.set) s.mapping in | |
685 | - let b = Xlist.fold candidate_lemmas false (fun b candidate_lemma -> candidate_lemma = simple_lemma || b) in | |
686 | - if b && form.interp = rule.interp then | |
687 | - (stem,rule) :: candidates else candidates)) in | |
738 | + let candidates = Xlist.fold (Rules.CharTrees.find rules form.orth) [] (fun candidates (stem,rule) -> | |
739 | + if stem ^ rule.set = simple_lemma && form.interp = rule.interp then | |
740 | + (stem,rule) :: candidates else candidates) in | |
688 | 741 | if candidates = [] then ((*printf "validate_interp: %s\t%s\t%s\n" form.orth entry.lemma form.interp;*) {form with validated=false}) else {form with validated=true}) in |
689 | 742 | {entry with forms=forms}) |
690 | 743 | |
744 | +let phon_validate_interp rules dict = | |
745 | + Xlist.rev_map dict (fun entry -> | |
746 | + let entry = create_candidates true rules entry in | |
747 | + let forms = Xlist.rev_map entry.forms (fun form -> | |
748 | + if form.candidates = [] then {form with validated=false} else {form with validated=true}) in | |
749 | + {entry with forms=forms}) | |
750 | + | |
691 | 751 | let remove_validated_forms dict = |
692 | 752 | Xlist.fold dict [] (fun dict entry -> |
693 | 753 | let forms = Xlist.fold entry.forms [] (fun forms form -> |
... | ... | @@ -791,11 +851,11 @@ let generate_rules rules path filename rules_filename = |
791 | 851 | let dict = remove_exceptional_lemmata dict in |
792 | 852 | let dict = find_kolwiek_suffixes dict in (* FIXME: lematy z kolwiek_suffixes nie są walidowane *) |
793 | 853 | let dict = generate_stem dict in |
794 | - let dict = fonetic_translation dict in | |
795 | 854 | let dict = phon_validate rules dict in |
796 | 855 | let dict = remove_validated_forms dict in |
797 | 856 | let dict = remove_sup_neg_forms dict in (* FIXME *) |
798 | 857 | let rules = Xlist.fold dict StringMap.empty (fun rules entry -> |
858 | + let entry = fonetic_translation_entry entry in | |
799 | 859 | Xlist.fold (RuleGenerator.phon_generate_rules_entry entry) rules (fun rules (key,rule) -> |
800 | 860 | let rules2 = try StringMap.find rules key with Not_found -> StringMap.empty in |
801 | 861 | let rules2 = StringMap.add_inc rules2 rule (1,[entry.lemma]) (fun (q,l) -> q+1, if q < 20 then entry.lemma :: l else l) in |
... | ... | @@ -837,13 +897,13 @@ let generate_interp_rules rules interp_rules selected_tags path filename rules_f |
837 | 897 | let dict = remove_exceptional_lemmata dict in |
838 | 898 | (* let dict = find_kolwiek_suffixes dict in *) |
839 | 899 | (* let dict = generate_stem dict in *) |
840 | - let dict = fonetic_translation dict in | |
841 | - let dict = validate_interp interp_rules dict in | |
900 | + let dict = phon_validate_interp interp_rules dict in | |
842 | 901 | let dict = remove_validated_forms dict in |
843 | 902 | let interp_rules = Xlist.fold dict StringMap.empty (fun interp_rules entry -> |
844 | - let simple_lemma = Stem.simplify_lemma entry.lemma in | |
903 | + (* let simple_lemma = Stem.simplify_lemma entry.lemma in *) | |
904 | + let entry = create_candidates false rules entry in | |
845 | 905 | Xlist.fold entry.forms interp_rules (fun interp_rules form -> |
846 | - let candidates = RuleGenerator.phon_generate_interp_rules rules selected_tags simple_lemma form in | |
906 | + let candidates = RuleGenerator.phon_generate_interp_rules (*rules*) selected_tags (*simple_lemma*) form in | |
847 | 907 | Xlist.fold candidates interp_rules (fun interp_rules (v,cand) -> |
848 | 908 | (* StringMap.add_inc interp_rules cand (1,[entry.lemma]) (fun (q,l) -> q+1, if q < 20 then entry.lemma :: l else l)))) in *) |
849 | 909 | StringMap.add_inc interp_rules cand (v,StringSet.singleton entry.lemma) (fun (v,set) -> v,StringSet.add set entry.lemma)))) in |
... | ... | @@ -862,6 +922,12 @@ let generate_interp_rules rules interp_rules selected_tags path filename rules_f |
862 | 922 | fst (Rules.RuleQMap.fold freq_rules (Rules.RuleQMap.empty,1) (fun (freq_rules,i) rule freq -> |
863 | 923 | Rules.RuleQMap.add_val freq_rules {rule with id = "N" ^ string_of_int i} freq, i+1)) *) |
864 | 924 | |
925 | +let manage_x_lemma stem suffix lemma = | |
926 | + match suffix with | |
927 | + "s" -> if Xstring.check_sufix "x" lemma && Xstring.check_sufix "k" stem then Xstring.cut_sufix "k" stem else stem | |
928 | + | "sa" -> if Xstring.check_sufix "xa" lemma && Xstring.check_sufix "k" stem then Xstring.cut_sufix "k" stem else stem | |
929 | + | _ -> stem | |
930 | + | |
865 | 931 | let generate_rule_frequencies rules path filename rules_filename = |
866 | 932 | let dict = load_tab (path ^ filename) in |
867 | 933 | let dict = merge_entries dict in |
... | ... | @@ -871,16 +937,81 @@ let generate_rule_frequencies rules path filename rules_filename = |
871 | 937 | let freq_rules = generate_ndm_rules (remove_not_ndm dict) in |
872 | 938 | let dict = remove_ndm dict in *) |
873 | 939 | let dict = remove_exceptional_lemmata dict in |
874 | - let dict = generate_stem dict in | |
875 | - let dict = fonetic_translation dict in | |
940 | + (* let dict = generate_stem dict in *) | |
876 | 941 | let freq_rules = Xlist.fold dict Rules.RuleQMap.empty(*freq_rules*) (fun freq_rules entry -> |
942 | + let entry = create_candidates true rules entry in | |
877 | 943 | let simple_lemma = Stem.simplify_lemma entry.lemma in |
944 | + (* print_endline simple_lemma; *) | |
878 | 945 | Xlist.fold entry.forms freq_rules (fun freq_rules form -> |
879 | - let candidates = Rules.CharTrees.find rules form.orth in | |
946 | + let candidates = Xlist.fold form.candidates [] (fun candidates (stem,rule,s) -> | |
947 | + let x_stem = manage_x_lemma stem rule.set simple_lemma in | |
948 | + let rule,pref_stem,short_stem = match rule.pref with | |
949 | + "naj" -> | |
950 | + let pref_stem = Fonetics.get_short_stem "" ("naj" ^ x_stem) s.mapping in | |
951 | + rule, pref_stem, Xstring.cut_prefix "naj" pref_stem | |
952 | + | "n′e" -> | |
953 | + let pref_stem = Fonetics.get_short_stem "" ("nie" ^ x_stem) s.mapping in | |
954 | + {rule with pref="nie"}, pref_stem, Xstring.cut_prefix "nie" pref_stem | |
955 | + | "" -> | |
956 | + let pref_stem = Fonetics.get_short_stem "" x_stem s.mapping in | |
957 | + rule, pref_stem, pref_stem | |
958 | + | _ -> failwith "generate_rule_frequencies" in | |
959 | + (* printf "%s %s %s\n%!" simple_lemma stem pref_stem; *) | |
960 | + let rule = {rule with | |
961 | + find = Xstring.cut_prefix pref_stem form.orth; | |
962 | + set = Xstring.cut_prefix short_stem simple_lemma} in | |
963 | + (stem,rule) :: candidates) in | |
964 | + (* printf "%s %s %d\n%!" simple_lemma form.orth (Xlist.size candidates); *) | |
965 | + (* let candidates = Rules.CharTrees.find rules form.orth in | |
880 | 966 | let candidates = Xlist.fold candidates [] (fun candidates (stem,rule) -> |
881 | 967 | if stem ^ rule.set = simple_lemma && form.interp = rule.interp then |
882 | - (stem,rule) :: candidates else candidates) in | |
883 | - if candidates = [] then freq_rules else Rules.RuleQMap.add freq_rules (snd (List.hd candidates)))) in | |
968 | + (stem,rule) :: candidates else candidates) in *) | |
969 | + let candidates2 = | |
970 | + Xlist.fold candidates [] (fun candidates2 (stem,rule) -> | |
971 | + if rule.star = Star then candidates2 else (stem,rule) :: candidates2) in | |
972 | + let candidates = if candidates2 = [] then candidates else candidates2 in | |
973 | + let _,candidates = Xlist.fold candidates (max_int,[]) (fun (min_n,min_l) (stem,rule) -> | |
974 | + let n = Xstring.size rule.find in | |
975 | + if n < min_n then n,[stem,rule] else | |
976 | + if n > min_n then min_n,min_l else | |
977 | + min_n, (stem,rule) :: min_l) in | |
978 | + let map = Xlist.fold candidates StringMap.empty (fun map (_,r) -> StringMap.add map (string_of_rule r) r) in | |
979 | + match StringMap.fold map [] (fun l s r -> (s,Rules.get_tag r.tags "con",Rules.get_tag r.tags "group",Rules.get_tag r.tags "lemma",r) :: l) with | |
980 | + (* match Rules.RuleSet.to_list (Xlist.fold candidates Rules.RuleSet.empty (fun set (_,r) -> Rules.RuleSet.add set r)) with *) | |
981 | + [] -> freq_rules | |
982 | + | [_,_,_,_,r] -> Rules.RuleQMap.add freq_rules r | |
983 | + | [_,"ʲ",_,_,_;_,"j",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
984 | + | [_,"ʲ",_,_,_;_,"r",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
985 | + | [_,"ʲ",_,_,_;_,"c",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
986 | + | [_,"ʲ",_,_,_;_,"d",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
987 | + | [_,"ʲ",_,_,_;_,"s",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
988 | + | [_,"ʲ",_,_,_;_,"a",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
989 | + | [_,"m′",_,_,_;_,"m",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
990 | + | [_,"b′",_,_,_;_,"b",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
991 | + | [_,"f′",_,_,_;_,"f",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
992 | + | [_,"v′",_,_,_;_,"j",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
993 | + | [_,"z",_,_,_;_,"s",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
994 | + | [_,"c",_,_,_;_,"z",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
995 | + | [_,"p′",_,_,_;_,"p",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
996 | + | [_,"ǯ",_,_,_;_,"ž",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
997 | + | [_,"v′",_,_,_;_,"v",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
998 | + | [_,"g′",_,_,_;_,"g",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
999 | + | [_,"š",_,_,_;_,"x",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
1000 | + | [_,"j",_,_,r;_,"b′",_,_,_] -> Rules.RuleQMap.add freq_rules r | |
1001 | + | [_,"j",_,_,r;_,"g′",_,_,_] -> Rules.RuleQMap.add freq_rules r | |
1002 | + | [_,"j",_,_,r;_,"k",_,_,_] -> Rules.RuleQMap.add freq_rules r | |
1003 | + | [_,"n′",_,_,_;_,"j",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
1004 | + | [_,"ł",_,_,_;_,"v",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
1005 | + | [_,"k′",_,_,_;_,"k",_,_,r] -> Rules.RuleQMap.add freq_rules r | |
1006 | + | [_,"c",_,_,r;_,"k",_,_,_] -> Rules.RuleQMap.add freq_rules r | |
1007 | + | [_,_,_,"ε",_;_,_,_,"e",r] -> Rules.RuleQMap.add freq_rules r | |
1008 | + | [_,_,_,"y",_;_,_,_,"e",r] -> Rules.RuleQMap.add freq_rules r | |
1009 | + (* | [_;"\t\t\tcat=ndm",r] -> Rules.RuleQMap.add freq_rules r | |
1010 | + | [_;_;"\t\t\tcat=ndm",r] -> Rules.RuleQMap.add freq_rules r *) | |
1011 | + | l -> | |
1012 | + printf "%s %s\n %s\n" form.orth entry.lemma (String.concat "\n " (Xlist.map l (fun (s,_,_,_,_) -> s))); | |
1013 | + let _,_,_,_,r = List.hd l in | |
1014 | + Rules.RuleQMap.add freq_rules r)) in | |
884 | 1015 | File.file_out rules_filename (fun file -> |
885 | 1016 | Rules.RuleQMap.iter freq_rules (fun rule freq -> |
886 | 1017 | fprintf file "%s\n" (Rules.string_of_freq_rule {rule with freq=freq}))) |
... | ... | @@ -892,9 +1023,9 @@ let generate_stem_dict rules_filename path filename out_filename = |
892 | 1023 | let dict = merge_entries dict in |
893 | 1024 | let dict = process_interps dict in |
894 | 1025 | let dict = remove_cat "cond" dict in |
895 | - let dict = fonetic_translation dict in | |
896 | 1026 | (* let dict = mark_ndm dict in *) |
897 | 1027 | let stems = Xlist.fold dict StringMap.empty (fun stems entry -> |
1028 | + let entry = fonetic_translation_entry entry in | |
898 | 1029 | let simple_lemma,lemma_suf = Stem.simplify_lemma_full entry.lemma in |
899 | 1030 | Xlist.fold entry.forms stems (fun stems form -> |
900 | 1031 | let candidates = Rules.CharTrees.find rules form.orth in |
... | ... |
morphology/fonetics.ml
... | ... | @@ -4,6 +4,9 @@ open Printf |
4 | 4 | type status = Idle | Symbols | Rules | RevSymbols | RevRules |
5 | 5 | type rule = {set: string; find: string; suf: string; lang: string} |
6 | 6 | |
7 | +let string_of_phon p = | |
8 | + Printf.sprintf "%s %s" p.Types.phon (String.concat " " (Xlist.map p.Types.mapping (fun (a,b) -> a ^ "->" ^ b))) | |
9 | + | |
7 | 10 | module CharTree = struct |
8 | 11 | |
9 | 12 | type t = M of t CharMap.t * rule list |
... | ... | @@ -64,14 +67,18 @@ let prepare_rules symbol_defs rules = |
64 | 67 | {r with suf=String.concat "" l}))) in |
65 | 68 | CharTree.create rules |
66 | 69 | |
67 | -let rules, rev_rules = | |
68 | - (* let symbol_defs,rev_symbol_defs,rules,rev_rules = load_rules "data/fonetics_acro.dic" in *) | |
69 | - let symbol_defs,rev_symbol_defs,rules,rev_rules = load_rules "data/fonetics_pl.dic" in | |
70 | - (* let symbol_defs,rev_symbol_defs,rules,rev_rules = load_rules "data/fonetics_en.dic" in *) | |
71 | - (* let symbol_defs,rev_symbol_defs,rules,rev_rules = load_rules "data/fonetics_fr.dic" in *) | |
72 | - (* let symbol_defs,rev_symbol_defs,rules,rev_rules = load_rules "data/fonetics_de.dic" in *) | |
70 | +let select_rules lang rules = | |
71 | + Xlist.fold rules [] (fun rules r -> | |
72 | + if r.lang = lang then r :: rules else rules) | |
73 | + | |
74 | +let rules, rev_rules, core_rules, core_rev_rules = | |
75 | + let symbol_defs,rev_symbol_defs,rules,rev_rules = load_rules "data/fonetics.dic" in | |
76 | + let core_rules = select_rules "core" rules in | |
77 | + let core_rev_rules = select_rules "core" rev_rules in | |
73 | 78 | prepare_rules symbol_defs rules, |
74 | - prepare_rules rev_symbol_defs rev_rules | |
79 | + prepare_rules rev_symbol_defs rev_rules, | |
80 | + prepare_rules symbol_defs core_rules, | |
81 | + prepare_rules rev_symbol_defs core_rev_rules | |
75 | 82 | |
76 | 83 | let sufs = ["ω"; "iκ"; "ρ"; "δ"; "λ"; "i"(*; "zi"*)] |
77 | 84 | |
... | ... | @@ -132,22 +139,22 @@ let rec translate_rec closure found found_maping rules s = |
132 | 139 | let l = if l = [] && closure then |
133 | 140 | let c,s = Xunicode.first_utf8_char_of_utf8_string s in |
134 | 141 | [s,{find=c; set=c; suf=""; lang=""}] else l in |
135 | - (* let n = String.length s in | |
136 | - let c = String.sub s 0 1 in | |
137 | - [String.sub s 1 (n-1),{find=c; set=c; suf=""}] else l in *) | |
138 | 142 | List.flatten (Xlist.rev_map l (fun (t,r) -> |
139 | 143 | translate_rec closure (r.set :: found) ((r.find,r.set) :: found_maping) rules (r.suf ^ t))) |
140 | 144 | |
141 | 145 | let translate closure rules s = |
142 | 146 | (* printf "translate 1: %s\n%!" s; *) |
143 | 147 | let ll = translate_rec closure [] [] rules (s ^ "ε") in |
144 | - Xlist.rev_map ll (fun (phon,mapping) -> {Types.phon=String.concat "" phon; Types.mapping=[](*mapping*)}) | |
145 | -(* let s = String.concat "" l in | |
146 | - (* printf "translate 2: %s\n%!" s; *) | |
147 | - s*) | |
148 | + Xlist.rev_map ll (fun (phon,mapping) -> {Types.phon=String.concat "" phon; Types.mapping=mapping}) | |
148 | 149 | |
149 | -let string_of_phon p = | |
150 | - Printf.sprintf "%s %s" p.Types.phon (String.concat " " (Xlist.map p.Types.mapping (fun (a,b) -> a ^ "->" ^ b))) | |
150 | +exception NotFound of string * string | |
151 | +exception NotEqual of string * string * string | |
152 | +exception MulipleSolutions of string * string * string list | |
153 | + | |
154 | +let translate_simple closure rules s = | |
155 | + let ll = translate_rec closure [] [] rules (s ^ "ε") in | |
156 | + if ll = [] then raise (NotFound(s,"")) else | |
157 | + Xlist.rev_map ll (fun (phon,mapping) -> String.concat "" phon) | |
151 | 158 | |
152 | 159 | let print_phon p = print_endline (string_of_phon p) |
153 | 160 | |
... | ... | @@ -161,22 +168,18 @@ let _ = Xlist.iter (translate true rules "łódź") print_phon |
161 | 168 | let _ = Xlist.iter (translate true rules "Łódź") print_phon *) |
162 | 169 | (* let _ = translate true rules "izolował" *) |
163 | 170 | |
164 | -exception NotFound of string * string | |
165 | -exception NotEqual of string * string * string | |
166 | -exception MulipleSolutions of string * string * string list | |
167 | - | |
168 | -let translate_and_check closure rules rev_rules x = | |
169 | - let l = translate closure rules x in | |
171 | +let translate_and_check closure rules rev_rules orth = | |
172 | + let l = translate closure rules orth in | |
170 | 173 | Xlist.iter l (fun s -> |
171 | 174 | let y = translate closure rev_rules s.Types.phon in |
172 | 175 | let y = Xlist.map y (fun s -> s.Types.phon) in |
173 | 176 | match StringSet.to_list (StringSet.of_list y) with |
174 | - [] -> raise (NotFound(x,s.Types.phon)) | |
175 | - | [t] -> if t <> x then raise (NotEqual(x,s.Types.phon,t)) | |
176 | - | l -> raise (MulipleSolutions(x,s.Types.phon,l))); | |
177 | - l | |
177 | + [] -> raise (NotFound(orth,s.Types.phon)) | |
178 | + | [t] -> if t <> orth then raise (NotEqual(orth,s.Types.phon,t)) | |
179 | + | l -> raise (MulipleSolutions(orth,s.Types.phon,l))) | |
180 | + | |
178 | 181 | |
179 | -let translate_single closure rules x = | |
182 | +(*let translate_single closure rules x = | |
180 | 183 | let y = translate closure rev_rules x in |
181 | 184 | let y = Xlist.map y (fun s -> s.Types.phon) in |
182 | 185 | match StringSet.to_list (StringSet.of_list y) with |
... | ... | @@ -196,11 +199,17 @@ let rec rev_translate_rec x s = function |
196 | 199 | let rev_translate closure rev_rules s m = |
197 | 200 | let x,s,_ = rev_translate_rec "" s m in |
198 | 201 | if s = "" then x else |
199 | - x ^ (translate_single closure rev_rules s) | |
202 | + x ^ (translate_single closure rev_rules s)*) | |
200 | 203 | |
201 | -let rev_translate2 closure rev_rules s m = | |
204 | +(*let rev_translate2 closure rev_rules s m = | |
202 | 205 | let x,s,_ = rev_translate_rec "" s m in |
203 | 206 | if s = "" then [x] else |
204 | 207 | let l = translate closure rev_rules s in |
205 | 208 | if l = [] then raise (NotFound(s,"")) else |
206 | - Xlist.rev_map l (fun y -> x ^ y.Types.phon) | |
209 | + Xlist.rev_map l (fun y -> x ^ y.Types.phon)*) | |
210 | + | |
211 | +let rec get_short_stem x s = function | |
212 | + [] -> if s = "" then x else failwith "get_short_stem" | |
213 | + | (a,b) :: m -> | |
214 | + if Xstring.check_prefix b s then get_short_stem (x^a) (Xstring.cut_prefix b s) m | |
215 | + else x | |
... | ... |
morphology/generate.ml
... | ... | @@ -156,6 +156,7 @@ let _ = |
156 | 156 | (* test_process_interps results_path adj_sgjp_filename; *) |
157 | 157 | (* test_process_interps results_path verb_sgjp_filename; *) |
158 | 158 | (* test_process_interps results_path noun_sgjp_filename; *) |
159 | + (* test_process_interps results_path "interp_not_validated_lang_all.tab"; *) | |
159 | 160 | () |
160 | 161 | |
161 | 162 | |
... | ... | @@ -180,9 +181,15 @@ let _ = |
180 | 181 | |
181 | 182 | let test_fonetics path filename = |
182 | 183 | let dict = Dict.load_tab_full (path ^ filename) in |
183 | - let dict = Dict.remove_exceptional_lemmata_gen obce dict in | |
184 | - let _ = Dict.fonetic_translation dict in | |
185 | - () | |
184 | + (* let dict = Dict.remove_exceptional_lemmata_gen obce dict in *) | |
185 | + Xlist.iter dict (fun e -> | |
186 | + Xlist.iter e.forms (fun f -> | |
187 | + try | |
188 | + Fonetics.translate_and_check true Fonetics.core_rules Fonetics.core_rev_rules f.orth | |
189 | + with | |
190 | + Fonetics.NotFound(orth,phon) -> printf "NF lemma=%s orth=%s phon=%s\n%!" e.lemma orth phon | |
191 | + | Fonetics.NotEqual(orth,phon,t) -> printf "NE lemma=%s orth=%s phon=%s: %s\n%!" e.lemma orth phon t | |
192 | + | Fonetics.MulipleSolutions(orth,phon,l) -> printf "MS lemma=%s orth=%s phon=%s: %s\n%!" e.lemma orth phon (String.concat " " l))) | |
186 | 193 | |
187 | 194 | (* Test translacji fonetycznej *) |
188 | 195 | let _ = |
... | ... | @@ -215,7 +222,6 @@ let check_stem_generation path filename = |
215 | 222 | (* let dict = Dict.mark_ndm dict in *) |
216 | 223 | let dict = Dict.remove_exceptional_lemmata dict in |
217 | 224 | let dict = Dict.find_kolwiek_suffixes dict in |
218 | - (* let dict = Dict.fonetic_translation dict in *) | |
219 | 225 | let _ = Dict.generate_stem dict in |
220 | 226 | () |
221 | 227 | |
... | ... | @@ -239,7 +245,7 @@ let interp_compound_rule_trees = Rules.make_interp_compound_rule_trees compound_ |
239 | 245 | |
240 | 246 | let find_not_validated_forms rules path filename out_filename = |
241 | 247 | let dict = Dict.load_tab (path ^ filename) in |
242 | - let dict = Dict.fonetic_translation dict in | |
248 | + let dict = Dict.assign_entry_cat dict in | |
243 | 249 | let dict = Dict.phon_validate rules dict in |
244 | 250 | let dict = Dict.remove_validated_forms dict in |
245 | 251 | Dict.print out_filename dict |
... | ... | @@ -250,8 +256,7 @@ let find_not_validated_entries rules path filename out_filename = |
250 | 256 | let dict = Dict.process_interps dict in |
251 | 257 | (* let dict = Dict.mark_ndm dict in |
252 | 258 | let dict = Dict.remove_ndm dict in *) |
253 | - let dict = Dict.remove_exceptional_lemmata dict in | |
254 | - let dict = Dict.fonetic_translation dict in | |
259 | + (* let dict = Dict.remove_exceptional_lemmata dict in *) | |
255 | 260 | let dict = Dict.phon_validate rules dict in |
256 | 261 | let dict = Dict.remove_validated_entries dict in |
257 | 262 | Dict.print out_filename dict |
... | ... | @@ -281,6 +286,10 @@ let _ = |
281 | 286 | (* find_not_validated_forms compound_rule_trees results_path "lang_acro_sgjp-20170730.tab" "results/lang_acro.tab"; *) |
282 | 287 | (* find_not_validated_forms compound_rule_trees results_path "lang_la_sgjp-20170730.tab" "results/lang_la.tab"; *) |
283 | 288 | (* find_not_validated_forms compound_rule_trees results_path "lang_es_sgjp-20170730.tab" "results/lang_es.tab"; *) |
289 | + (* find_not_validated_forms compound_rule_trees results_path "lang_all_sgjp-20170730.tab" "results/lang_all.tab"; *) | |
290 | + (* find_not_validated_entries compound_rule_trees results_path "lang_all_sgjp-20170730.tab" "results/lang_all.tab"; *) | |
291 | + (* find_not_validated_entries compound_rule_trees results_path noun_polimorf_filename "results/not_validated_p_noun.tab"; *) | |
292 | + (* find_not_validated_forms compound_rule_trees results_path "not_validated_p_noun.tab" "results/not_validated_p_noun2.tab"; *) | |
284 | 293 | () |
285 | 294 | |
286 | 295 | let find_not_validated_lemmata rules path filename out_filename = |
... | ... | @@ -288,7 +297,6 @@ let find_not_validated_lemmata rules path filename out_filename = |
288 | 297 | let dict = Dict.merge_entries dict in |
289 | 298 | let dict = Dict.process_interps dict in |
290 | 299 | let dict = Dict.remove_exceptional_lemmata dict in |
291 | - let dict = Dict.fonetic_translation dict in | |
292 | 300 | let dict = Dict.phon_validate rules dict in |
293 | 301 | let dict = Dict.remove_validated_entries dict in |
294 | 302 | Dict.print_lemmata out_filename dict |
... | ... | @@ -304,7 +312,6 @@ let find_validated_lemmata rules path filename out_filename = |
304 | 312 | let dict = Dict.load_tab (path ^ filename) in |
305 | 313 | let dict = Dict.merge_entries dict in |
306 | 314 | let dict = Dict.process_interps dict in |
307 | - let dict = Dict.fonetic_translation dict in | |
308 | 315 | let dict = Dict.phon_validate rules dict in |
309 | 316 | let dict = Dict.remove_not_validated_entries dict in |
310 | 317 | Dict.print_lemmata out_filename dict |
... | ... | @@ -319,11 +326,11 @@ let _ = |
319 | 326 | let test_lemmatize lemma orth = |
320 | 327 | printf "test_lemmatize: %s %s\n%!" lemma orth; |
321 | 328 | let simple_lemma = Stem.simplify_lemma lemma in |
322 | - let phon_orths = Fonetics.translate(*_and_check*) true Fonetics.rules (*Fonetics.rev_rules*) orth in | |
329 | + let phon_orths = Fonetics.translate true Fonetics.core_rules orth in | |
323 | 330 | printf "phon_orths: \n %s\n%!" (String.concat "\n " (Xlist.map phon_orths Fonetics.string_of_phon)); |
324 | 331 | Xlist.iter phon_orths (fun phon_orth -> |
325 | 332 | Xlist.iter (Rules.CharTrees.find compound_rule_trees phon_orth.phon) (fun (stem,rule) -> |
326 | - let candidate_lemmas = Fonetics.rev_translate2 true Fonetics.rev_rules (stem ^ rule.set) (phon_orth.mapping) in | |
333 | + let candidate_lemmas = Fonetics.translate_simple true Fonetics.core_rev_rules (stem ^ rule.set) in | |
327 | 334 | Xlist.iter candidate_lemmas (fun candidate_lemma -> |
328 | 335 | if candidate_lemma = simple_lemma then printf "E" else printf " "; |
329 | 336 | printf " %s %s %s %s\n%!" phon_orth.phon stem (string_of_rule rule) candidate_lemma))) |
... | ... | @@ -430,6 +437,20 @@ let _ = |
430 | 437 | (* test_lemmatize "Lefebvre" "Lefebvre’a"; *) |
431 | 438 | (* test_lemmatize "Kayah" "Kayom"; *) |
432 | 439 | (* test_lemmatize "Dixa" "Diksie"; *) |
440 | + (* test_lemmatize "White" "Whicie"; | |
441 | + test_lemmatize "Voit" "Voicie"; | |
442 | + test_lemmatize "Violeta" "Violecie"; | |
443 | + test_lemmatize "veto" "vecie"; *) | |
444 | + (* test_lemmatize "Andrássy" "Andrássyowie"; *) | |
445 | + (* test_lemmatize "Cezanne" "Cezanne’ami"; | |
446 | + test_lemmatize "Connery" "Connery’ego"; *) | |
447 | + (* test_lemmatize "Barrés" "Barrés’go"; *) | |
448 | + (* test_lemmatize "IKEA" "IKE-i"; *) | |
449 | + (* test_lemmatize "mix" "miksowi"; | |
450 | + test_lemmatize "Laxa" "Laksie"; *) | |
451 | + (* test_lemmatize "münsterski" "münstersku"; *) | |
452 | + (* test_lemmatize "würzburski" "würzburskiemu"; *) | |
453 | + (* test_lemmatize "polje" "poljom"; *) | |
433 | 454 | (* test_lemmatize "" ""; |
434 | 455 | test_lemmatize "" ""; |
435 | 456 | test_lemmatize "" ""; *) |
... | ... | @@ -461,8 +482,7 @@ let find_interp_validated_lemmata interp_rules path filename out_filename = |
461 | 482 | (* let dict = Dict.remove_exceptional_lemmata dict in *) |
462 | 483 | (* let dict = find_kolwiek_suffixes dict in *) |
463 | 484 | (* let dict = generate_stem dict in *) |
464 | - let dict = Dict.fonetic_translation dict in | |
465 | - let dict = Dict.validate_interp interp_rules dict in | |
485 | + let dict = Dict.phon_validate_interp interp_rules dict in | |
466 | 486 | let dict = Dict.remove_not_validated_entries dict in |
467 | 487 | Dict.print_lemmata out_filename dict |
468 | 488 | |
... | ... | @@ -474,8 +494,7 @@ let find_not_interp_validated_lemmata interp_rules path filename out_filename = |
474 | 494 | (* let dict = Dict.remove_exceptional_lemmata dict in *) |
475 | 495 | (* let dict = find_kolwiek_suffixes dict in *) |
476 | 496 | (* let dict = generate_stem dict in *) |
477 | - let dict = Dict.fonetic_translation dict in | |
478 | - let dict = Dict.validate_interp interp_rules dict in | |
497 | + let dict = Dict.phon_validate_interp interp_rules dict in | |
479 | 498 | let dict = Dict.remove_validated_entries dict in |
480 | 499 | Dict.print_lemmata out_filename dict |
481 | 500 | |
... | ... | @@ -485,8 +504,7 @@ let find_not_interp_validated_entries interp_rules path filename out_filename = |
485 | 504 | let dict = Dict.process_interps dict in |
486 | 505 | (* let dict = Dict.mark_ndm dict in |
487 | 506 | let dict = Dict.remove_ndm dict in *) |
488 | - let dict = Dict.fonetic_translation dict in | |
489 | - let dict = Dict.validate_interp interp_rules dict in | |
507 | + let dict = Dict.phon_validate_interp interp_rules dict in | |
490 | 508 | let dict = Dict.remove_validated_entries dict in |
491 | 509 | Dict.print out_filename dict |
492 | 510 | |
... | ... | @@ -494,8 +512,8 @@ let find_not_interp_validated_forms interp_rules path filename out_filename = |
494 | 512 | let dict = Dict.load_tab (path ^ filename) in |
495 | 513 | let dict = Dict.merge_entries dict in |
496 | 514 | let dict = Dict.process_interps dict in |
497 | - let dict = Dict.fonetic_translation dict in | |
498 | - let dict = Dict.validate_interp interp_rules dict in | |
515 | + let dict = Dict.remove_exceptional_lemmata dict in | |
516 | + let dict = Dict.phon_validate_interp interp_rules dict in | |
499 | 517 | let dict = Dict.remove_validated_forms dict in |
500 | 518 | Dict.print out_filename dict |
501 | 519 | |
... | ... | @@ -506,8 +524,8 @@ let _ = |
506 | 524 | find_interp_validated_lemmata interp_compound_rule_trees results_path adj_sgjp_filename "results/interp_validated_adj.tab"; |
507 | 525 | find_not_interp_validated_lemmata interp_compound_rule_trees results_path adj_sgjp_filename "results/interp_not_validated_adj.tab"; |
508 | 526 | find_interp_validated_lemmata interp_compound_rule_trees results_path adv_sgjp_filename "results/interp_validated_adv.tab"; |
509 | - find_not_interp_validated_lemmata interp_compound_rule_trees results_path adv_sgjp_filename "results/interp_not_validated_adv.tab"; *) | |
510 | - (* find_interp_validated_lemmata interp_compound_rule_trees results_path verb_sgjp_filename "results/interp_validated_verb.tab"; | |
527 | + find_not_interp_validated_lemmata interp_compound_rule_trees results_path adv_sgjp_filename "results/interp_not_validated_adv.tab"; | |
528 | + find_interp_validated_lemmata interp_compound_rule_trees results_path verb_sgjp_filename "results/interp_validated_verb.tab"; | |
511 | 529 | find_not_interp_validated_lemmata interp_compound_rule_trees results_path verb_sgjp_filename "results/interp_not_validated_verb.tab"; |
512 | 530 | find_interp_validated_lemmata interp_compound_rule_trees results_path "verb_sgjp_no_pref.tab" "results/interp_validated_no_pref_verb.tab"; |
513 | 531 | find_not_interp_validated_lemmata interp_compound_rule_trees results_path "verb_sgjp_no_pref.tab" "results/interp_not_validated_no_pref_verb.tab"; *) |
... | ... | @@ -519,19 +537,18 @@ let _ = |
519 | 537 | (* find_not_interp_validated_forms interp_compound_rule_trees results_path "lang_fr_sgjp-20170730.tab" "results/lang_fr.tab"; *) |
520 | 538 | (* find_not_interp_validated_forms interp_compound_rule_trees results_path "lang_de_sgjp-20170730.tab" "results/lang_de.tab"; *) |
521 | 539 | (* find_not_interp_validated_forms interp_compound_rule_trees results_path "lang_acro_sgjp-20170730.tab" "results/lang_acro.tab"; *) |
540 | + (* find_not_interp_validated_forms interp_compound_rule_trees results_path "lang_all_sgjp-20170730.tab" "results/lang_all.tab"; *) | |
541 | + (* find_not_interp_validated_entries interp_compound_rule_trees results_path "lang_all_sgjp-20170730.tab" "results/interp_not_validated_lang_all.tab"; *) | |
522 | 542 | () |
523 | 543 | |
524 | 544 | let test_interp_lemmatize lemma orth = |
525 | 545 | printf "test_interp_lemmatize: %s %s\n%!" lemma orth; |
526 | - let simple_lemma = Stem.simplify_lemma lemma in | |
527 | - let phon_orths = Fonetics.translate(*_and_check*) true Fonetics.rules (*Fonetics.rev_rules*) orth in | |
528 | - printf "phon_orths: \n %s\n%!" (String.concat "\n " (Xlist.map phon_orths Fonetics.string_of_phon)); | |
529 | - Xlist.iter phon_orths (fun phon_orth -> | |
530 | - Xlist.iter (Rules.CharTrees.find interp_compound_rule_trees phon_orth.phon) (fun (stem,rule) -> | |
531 | - let candidate_lemmas = Fonetics.rev_translate2 true Fonetics.rev_rules (stem ^ rule.set) (phon_orth.mapping) in | |
532 | - Xlist.iter candidate_lemmas (fun candidate_lemma -> | |
533 | - if candidate_lemma = simple_lemma then (*printf "E" else printf " ";*) | |
534 | - printf " %s %s %s %s %s\n%!" phon_orth.phon stem (string_of_rule rule) candidate_lemma rule.interp))) | |
546 | + let entry = {empty_entry with lemma=lemma; cat="noun"; forms=[{empty_form with orth=orth}]} in | |
547 | + let entry = Dict.create_candidates false interp_compound_rule_trees entry in | |
548 | + Xlist.iter entry.forms (fun f -> | |
549 | + printf "phon_orths: \n %s\n%!" (String.concat "\n " (Xlist.map f.phon_orth Fonetics.string_of_phon)); | |
550 | + Xlist.iter f.candidates (fun (stem,rule,s) -> | |
551 | + printf "%s %s %s %s\n%!" s.phon stem (string_of_rule rule) rule.interp)) | |
535 | 552 | |
536 | 553 | let _ = |
537 | 554 | (* test_interp_lemmatize "Benveniste" "Benveniście"; *) |
... | ... | @@ -539,6 +556,19 @@ let _ = |
539 | 556 | (* test_interp_lemmatize "Depardieu" "Depardieuch"; *) |
540 | 557 | (* test_interp_lemmatize "Braille" "Braille’u"; *) |
541 | 558 | (* test_interp_lemmatize "FAMA" "FAMA"; *) |
559 | + (* test_interp_lemmatize "lichy" "lichego"; *) | |
560 | + (* test_interp_lemmatize "niekaraluszy" "niekaraluszych"; *) | |
561 | + (* test_interp_lemmatize "ninja" "ninjami"; *) | |
562 | + (* test_interp_lemmatize "ninja" "ninji"; *) | |
563 | + (* test_interp_lemmatize "mix" "miksowi"; *) | |
564 | + (* test_interp_lemmatize "münsterski" "münstersku"; *) | |
565 | + (* test_interp_lemmatize "Trubieckoj" "Trubieckich"; *) | |
566 | + (* test_interp_lemmatize "Balazs" "Balazsu"; *) | |
567 | + (* test_interp_lemmatize "Blake" "Blakiem"; | |
568 | + test_interp_lemmatize "Bogorodckij" "Bogorodckiego"; | |
569 | + test_interp_lemmatize "BUW" "BUW-ie"; | |
570 | + test_interp_lemmatize "Bush" "Bushe"; *) | |
571 | + (* test_interp_lemmatize "ensemble" "ensemblowi"; *) | |
542 | 572 | (*test_interp_lemmatize "" ""; |
543 | 573 | test_interp_lemmatize "" ""; |
544 | 574 | test_interp_lemmatize "" "";*) |
... | ... | @@ -569,7 +599,11 @@ let _ = |
569 | 599 | (* Generowanie złożonych reguł zaopatrzonych we frekwencje *) |
570 | 600 | let _ = |
571 | 601 | (* Dict.generate_rule_frequencies interp_compound_rule_trees results_path adj_sgjp_filename "results/freq_rules-adj.tab"; *) |
602 | + (* Dict.generate_rule_frequencies interp_compound_rule_trees results_path "verb_sgjp_no_pref.tab" "results/freq_rules-verb.tab"; *) | |
603 | + (* Dict.generate_rule_frequencies interp_compound_rule_trees results_path verb_sgjp_filename "results/freq_rules-verb.tab"; *) | |
604 | + (* Dict.generate_rule_frequencies interp_compound_rule_trees results_path "lang_all_sgjp-20170730.tab" "results/freq_rules-lang.tab"; *) | |
572 | 605 | (* Dict.generate_rule_frequencies interp_compound_rule_trees sgjp_path sgjp_filename "results/freq_rules.tab"; *) |
606 | + (* ignore (Sys.command "totem ~/Dokumenty/Inne/gong/gong_05m_00s.ogg"); *) | |
573 | 607 | () |
574 | 608 | |
575 | 609 | let generate_alt rules_filename path filename out_filename = |
... | ... | @@ -588,6 +622,7 @@ let generate_alt rules_filename path filename out_filename = |
588 | 622 | let _ = |
589 | 623 | (* generate_alt "results/freq_rules-adj.tab" results_path adj_sgjp_filename "results/alt-adj.tab"; *) |
590 | 624 | (* generate_alt "results/freq_rules.tab" sgjp_path sgjp_filename "results/alt.tab"; *) |
625 | + (* generate_alt "results/freq_rules-lang.tab" results_path "lang_all_sgjp-20170730.tab" "results/alt-lang.tab"; *) | |
591 | 626 | () |
592 | 627 | |
593 | 628 | (* Generowanie stemów z regułami *) |
... | ... |
morphology/ruleGenerator.ml
... | ... | @@ -306,9 +306,9 @@ let calculate_person_value = function |
306 | 306 | |
307 | 307 | let calculate_rule_value tags interp = |
308 | 308 | if interp = "" then failwith "calculate_rule_value: empty interp" else |
309 | - let cat = try Xlist.assoc tags "cat" with Not_found -> "" in | |
310 | - let lemma = try Xlist.assoc tags "lemma" with Not_found -> "" in | |
311 | - let group = try Xlist.assoc tags "group" with Not_found -> "" in | |
309 | + let cat = Rules.get_tag tags "cat" in | |
310 | + let lemma = Rules.get_tag tags "lemma" in | |
311 | + let group = Rules.get_tag tags "group" in | |
312 | 312 | if cat = "noun" || cat = "adj" then |
313 | 313 | let lemma_val = match lemma with |
314 | 314 | "a" -> 20 |
... | ... | @@ -405,7 +405,15 @@ let calculate_rule_value tags interp = |
405 | 405 | 10000000 * lemma_val + 10000 * group_val + interp_val |
406 | 406 | else 0 |
407 | 407 | |
408 | -let phon_generate_interp_rules rules selected_tags simple_lemma form = | |
408 | +let phon_generate_interp_rules selected_tags form = | |
409 | + Xlist.rev_map form.candidates (fun (_,rule,_) -> | |
410 | + let tags = Xlist.fold rule.tags [] (fun tags (k,v) -> | |
411 | + if StringSet.mem selected_tags k then (k,v) :: tags else tags) in | |
412 | + let tags = Xlist.sort tags Rules.compare_tag in | |
413 | + calculate_rule_value rule.tags form.interp, | |
414 | + String.concat " " (Xlist.map tags (fun (k,v) -> k ^ "=" ^ v)) ^ "\t" ^ form.interp) | |
415 | + | |
416 | +(* let phon_generate_interp_rules rules selected_tags simple_lemma form = | |
409 | 417 | Xlist.fold form.phon_orth [] (fun found orth -> |
410 | 418 | let candidates = Rules.CharTrees.find rules orth.phon in |
411 | 419 | (* printf "S %d\n" (Xlist.size forms); *) |
... | ... | @@ -418,4 +426,4 @@ let phon_generate_interp_rules rules selected_tags simple_lemma form = |
418 | 426 | if StringSet.mem selected_tags k then (k,v) :: tags else tags) in |
419 | 427 | let tags = Xlist.sort tags Rules.compare_tag in |
420 | 428 | calculate_rule_value rule.tags form.interp, |
421 | - String.concat " " (Xlist.map tags (fun (k,v) -> k ^ "=" ^ v)) ^ "\t" ^ form.interp) @ found) | |
429 | + String.concat " " (Xlist.map tags (fun (k,v) -> k ^ "=" ^ v)) ^ "\t" ^ form.interp) @ found) *) | |
... | ... |
morphology/rules.ml
... | ... | @@ -139,6 +139,9 @@ let rec extract_tag s rev = function |
139 | 139 | [] -> "", List.rev rev |
140 | 140 | | (k,v) :: l -> if s = k then v, List.rev rev @ l else extract_tag s ((k,v) :: rev) l |
141 | 141 | |
142 | +let get_tag l tag = | |
143 | + try Xlist.assoc l tag with Not_found -> "" | |
144 | + | |
142 | 145 | let create_compound_rules schemata rule_map = |
143 | 146 | let found = Xlist.fold schemata [] (fun found schema -> |
144 | 147 | let compounds = Xlist.fold schema [{star=Productive;pref="";find="";set="";tags=[];interp=""; id=""; freq=0}] (fun compounds rule_set_name -> |
... | ... | @@ -667,9 +670,9 @@ let latex_of_schemata () = |
667 | 670 | print_endline "\\]\\end{scriptsize}\n") |
668 | 671 | |
669 | 672 | let make_rule_key r = |
670 | - let cat = try Xlist.assoc r.tags "cat" with Not_found -> "" in | |
671 | - let lemma = try Xlist.assoc r.tags "lemma" with Not_found -> "" in | |
672 | - let group = try Xlist.assoc r.tags "group" with Not_found -> "" in | |
673 | + let cat = get_tag r.tags "cat" in | |
674 | + let lemma = get_tag r.tags "lemma" in | |
675 | + let group = get_tag r.tags "group" in | |
673 | 676 | let gender = |
674 | 677 | match Xstring.split ":" (List.hd (Xstring.split "|" r.interp)) with |
675 | 678 | "subst" :: n :: c :: g -> (String.concat ":" g) |
... | ... | @@ -708,8 +711,8 @@ let rec get_gender = function |
708 | 711 | | [] -> failwith "get_gender" |
709 | 712 | |
710 | 713 | let latex_of_noun_interp_rules l = |
711 | - let cat = Xlist.assoc (List.hd l).tags "cat" in | |
712 | - let lemma = Xlist.assoc (List.hd l).tags "lemma" in | |
714 | + let cat = get_tag (List.hd l).tags "cat" in | |
715 | + let lemma = get_tag (List.hd l).tags "lemma" in | |
713 | 716 | let gender = get_gender (Xlist.map l (fun r -> r.interp)) in |
714 | 717 | let l = Xlist.map l (fun r -> {r with tags = snd (extract_tag "cat" [] r.tags)}) in |
715 | 718 | let l = Xlist.map l (fun r -> {r with tags = snd (extract_tag "lemma" [] r.tags)}) in |
... | ... | @@ -750,12 +753,12 @@ let latex_of_noun_interp_rules l = |
750 | 753 | let latex_of_interp_rules_table l tags = |
751 | 754 | print_endline ("\\begin{longtable}{p{7cm}|" ^ String.concat "|" (Xlist.map tags (fun _ -> "l")) ^ "}"); |
752 | 755 | print_endline ("interpretation & " ^ String.concat " & " tags ^ "\\\\\n\\hline"); |
753 | - Xlist.iter (List.rev l) (fun r -> | |
756 | + Xlist.iter (List.rev l) (fun (r: rule) -> | |
754 | 757 | let interp = String.concat "" (Xstring.split ":imperf\\.perf" r.interp) in |
755 | 758 | let interp = String.concat " " (Xstring.split "|" interp) in |
756 | 759 | print_endline ((if r.star = Star then "$\\star$" else "") ^ interp ^ " & " ^ |
757 | 760 | String.concat " & " (Xlist.map tags (fun tag -> |
758 | - latex_escape_string (Xlist.assoc r.tags tag))) ^ "\\\\")); | |
761 | + latex_escape_string (get_tag r.tags tag))) ^ "\\\\")); | |
759 | 762 | print_endline "\\end{longtable}" |
760 | 763 | |
761 | 764 | |
... | ... |
morphology/types.ml
1 | +type star = Productive | Star | Ndm | Dial | |
2 | + | |
3 | +type rule = {star: star; pref: string; find: string; set: string; tags: (string * string) list; | |
4 | + interp: string; id: string; freq: int} | |
5 | + | |
1 | 6 | type phon_orth = {phon: string; mapping: (string * string) list} |
2 | -type form = {orth: string; phon_orth: phon_orth list; interp: string; freq: int; genre: string; validated: bool} | |
7 | +type form = {orth: string; phon_orth: phon_orth list; interp: string; freq: int; genre: string; validated: bool; candidates: (string * rule * phon_orth) list} | |
3 | 8 | type entry = {lemma: string; (*phon_lemma: string list;*) cat: string; forms: form list; |
4 | 9 | proper_type: string; (*ndm: bool;*) stem: string; phon_stem: string list; aspect: string} |
5 | 10 | |
6 | -let empty_form = {orth=""; phon_orth=[]; interp=""; freq=1; genre=""; validated=false} | |
11 | +let empty_form = {orth=""; phon_orth=[]; interp=""; freq=1; genre=""; validated=false; candidates=[]} | |
7 | 12 | let empty_entry = {lemma=""; (*phon_lemma=[];*) cat=""; forms=[]; proper_type=""; (*ndm=false;*) |
8 | 13 | stem=""; phon_stem=[]; aspect=""} |
9 | 14 | |
10 | -type star = Productive | Star | Ndm | Dial | |
11 | - | |
12 | -type rule = {star: star; pref: string; find: string; set: string; tags: (string * string) list; | |
13 | - interp: string; id: string; freq: int} | |
14 | - | |
15 | 15 | let empty_rule = {star=Productive; pref=""; find=""; set=""; tags=[]; interp=""; id=""; freq=0} |
16 | 16 | |
17 | 17 | let string_of_rule r = |
... | ... |