walParser.ml
38.3 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
(*
* ENIAM: Categorial Syntactic-Semantic Parser for Polish
* Copyright (C) 2016 Wojciech Jaworski <wjaworski atSPAMfree mimuw dot edu dot pl>
* Copyright (C) 2016 Institute of Computer Science Polish Academy of Sciences
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*)
open WalTypes
open Xstd
let rec find_brackets = function
LParen :: l ->
let found,l = find_rbracket RParen [] l in
(Paren found) :: (find_brackets l)
| LBracet :: l ->
let found,l = find_rbracket RBracet [] l in
(Bracet found) :: (find_brackets l)
| LSqBra :: l ->
let found,l = find_rbracket RSqBra [] l in
(SqBra found) :: (find_brackets l)
| s :: l -> s :: (find_brackets l)
| [] -> []
and find_rbracket bracket rev = function
LParen :: l ->
let found,l = find_rbracket RParen [] l in
find_rbracket bracket (Paren found :: rev) l
| LBracet :: l ->
let found,l = find_rbracket RBracet [] l in
find_rbracket bracket (Bracet found :: rev) l
| LSqBra :: l ->
let found,l = find_rbracket RSqBra [] l in
find_rbracket bracket (SqBra found :: rev) l
| RParen :: l -> if bracket = RParen then List.rev rev, l else failwith "find_rbracket"
| RBracet :: l -> if bracket = RBracet then List.rev rev, l else failwith "find_rbracket"
| RSqBra :: l -> if bracket = RSqBra then List.rev rev, l else failwith "find_rbracket"
| s :: l -> find_rbracket bracket (s :: rev) l
| [] -> failwith "find_rbracket"
let rec split_symbol symb rev = function
[] -> [List.rev rev](*failwith "split_symbol"*)
| s :: l ->
if s = symb then
if l = [] then (*[List.rev rev]*)failwith "split_symbol"
else (List.rev rev) :: (split_symbol symb [] l)
else split_symbol symb (s :: rev) l
let parse_opinion = function
"pewny" -> Pewny
| "cer" -> Pewny
| "potoczny" -> Potoczny
| "col" -> Potoczny
| "wątpliwy" -> Watpliwy
| "unc" -> Watpliwy
| "archaiczny" -> Archaiczny
| "dat" -> Archaiczny
| "zły" -> Zly
| "bad" -> Zly
| "wulgarny" -> Wulgarny
| "vul" -> Wulgarny
| x -> failwith ("parse_opinion: " ^ x)
let parse_roles l =
let r,cr,ce = Xlist.fold l ([],[],[]) (fun (r,controller,controllee) -> function
"subj" -> SUBJ :: r, controller, controllee
| "obj" -> OBJ :: r, controller, controllee
| "controller" -> r, "1" :: controller, controllee
| "controllee" -> r, controller, "1" :: controllee
| "controller2" -> r, "2" :: controller, controllee
| "controllee2" -> r, controller, "2" :: controllee
| "" -> r, controller, controllee
| x -> failwith ("parse_roles: " ^ x)) in
(match r with
[] -> ARG
| [x] -> x
| _ -> failwith "parse_roles"),cr,ce
let parse_negation = function
[Text "_"] -> NegationUndef
| [Text "neg"] -> Negation
| [Text "aff"] -> Aff
| [Text ""] -> NegationNA
| l -> failwith ("parse_negation: " ^ WalStringOf.token_list l)
let parse_pred = function
[Text ""] -> PredNA
| [Text "pred"] -> Pred
| [Text "false"] -> PredNA
| [Text "true"] -> Pred
| l -> failwith ("parse_pred: " ^ WalStringOf.token_list l)
let parse_aspect = function
[Text "perf"] -> Aspect "perf"
| [Text "imperf"] -> Aspect "imperf"
| [Text "_"] -> AspectUndef
| [Text ""] -> AspectNA
| l -> failwith ("parse_aspect: " ^ WalStringOf.token_list l)
let parse_case = function
[Text "nom"] -> Case "nom"
| [Text "gen"] -> Case "gen"
| [Text "dat"] -> Case "dat"
| [Text "acc"] -> Case "acc"
| [Text "inst"] -> Case "inst"
| [Text "loc"] -> Case "loc"
| [Text "str"] -> Str
| [Text "pred"] -> Case "pred"
| [Text "part"] -> Part
| [Text "postp"] -> Case "postp"
| [Text "agr"] -> CaseAgr
| l -> failwith ("parse_case: " ^ WalStringOf.token_list l)
let parse_prep = function
| [Text "niż"] -> "niż"
| [Text "w czasie"] -> "w czasie"
| [Text "podczas"] -> "podczas"
| [Text "w roli"] -> "w roli"
| [Text "pomiędzy"] -> "pomiędzy"
| [Text "według"] -> "według"
| [Text "zza"] -> "zza"
| [Text "poza"] -> "poza"
| [Text "spośród"] -> "spośród"
| [Text "spod"] -> "spod"
| [Text "koło"] -> "koło"
| [Text "względem"] -> "względem"
| [Text "wśród"] -> "wśród"
| [Text "wskutek"] -> "wskutek"
| [Text "przez"] -> "przez"
| [Text "co do"] -> "co do"
| [Text "wokół"] -> "wokół"
| [Text "między"] -> "między"
| [Text "bez"] -> "bez"
| [Text "przy"] -> "przy"
| [Text "na rzecz"] -> "na rzecz"
| [Text "na temat"] -> "na temat"
| [Text "po"] -> "po"
| [Text "u"] -> "u"
| [Text "pod"] -> "pod"
| [Text "ponad"] -> "ponad"
| [Text "jako"] -> "jako"
| [Text "w kwestii"] -> "w kwestii"
| [Text "w sprawie"] -> "w sprawie"
| [Text "ku"] -> "ku"
| [Text "przeciw"] -> "przeciw"
| [Text "nad"] -> "nad"
| [Text "z powodu"] -> "z powodu"
| [Text "przed"] -> "przed"
| [Text "od"] -> "od"
| [Text "o"] -> "o"
| [Text "w"] -> "w"
| [Text "za"] -> "za"
| [Text "dla"] -> "dla"
| [Text "na"] -> "na"
| [Text "z"] -> "z"
| [Text "do"] -> "do"
| [Text "wobec"] -> "wobec"
| [Text "jak"] -> "jak"
| [Text "spomiędzy"] -> "spomiędzy"
| [Text "sponad"] -> "sponad"
| [Text "spopod"] -> "spopod"
| [Text "spoza"] -> "spoza"
| [Text "sprzed"] -> "sprzed"
| [Text "znad"] -> "znad"
| [Text "dokoła"] -> "dokoła"
| [Text "dookoła"] -> "dookoła"
| [Text "naokoło"] -> "naokoło"
| [Text "naprzeciw"] -> "naprzeciw"
| [Text "obok"] -> "obok"
| [Text "poniżej"] -> "poniżej"
| [Text "popod"] -> "popod"
| [Text "pośrodku"] -> "pośrodku"
| [Text "pośród"] -> "pośród"
| [Text "powyżej"] -> "powyżej"
| [Text "wewnątrz"] -> "wewnątrz"
| [Text "wkoło"] -> "wkoło"
| [Text "wzdłuż"] -> "wzdłuż"
| [Text "naokół"] -> "naokół"
| [Text "śród"] -> "śród"
| [Text "wpośród"] -> "wpośród"
| [Text "poprzez"] -> "poprzez"
| [Text "około"] -> "około"
| [Text "na punkcie"] -> "na punkcie"
| [Text "pod względem"] -> "pod względem"
| [Text "pod wpływem"] -> "pod wpływem"
| [Text "na skutek"] -> "na skutek"
| [Text "na polu"] -> "na polu"
| [Text "na poczet"] -> "na poczet"
| [Text "na widok"] -> "na widok"
| [Text "w dziedzinie"] -> "w dziedzinie"
| [Text "pod pozorem"] -> "pod pozorem"
| [Text "pod pretekstem"] -> "pod pretekstem"
| [Text "za pomocą"] -> "za pomocą"
| [Text "pod adresem"] -> "pod adresem"
| [Text "w kierunku"] -> "w kierunku"
| [Text "w stronę"] -> "w stronę"
| [Text "w obliczu"] -> "w obliczu"
| [Text "u podstaw"] -> "u podstaw"
| [Text "pod kątem"] -> "pod kątem"
| [Text "na okoliczność"] -> "na okoliczność"
| [Text "w temacie"] -> "w temacie"
| [Text "od strony"] -> "od strony"
| [Text "ze strony"] -> "ze strony"
| [Text "po stronie"] -> "po stronie"
| [Text "na myśl"] -> "na myśl"
| [Text "w charakterze"] -> "w charakterze"
| [Text "w zakresie"] -> "w zakresie"
| [Text "ze względu na"] -> "ze względu na"
| [Text "na podstawie"] -> "na podstawie"
| [Text "w stosunku do"] -> "w stosunku do"
| [Text "z tytułu"] -> "z tytułu"
| [Text "z okazji"] -> "z okazji"
| [Text "z zakresu"] -> "z zakresu"
| [Text "w wysokości"] -> "w wysokości"
| [Text "na gruncie"] -> "na gruncie"
| [Text "z dziedziny"] -> "z dziedziny"
| [Text "na tle"] -> "na tle"
| [Text "na niwie"] -> "na niwie"
| [Text "w ramach"] -> "w ramach"
| [Text "na korzyść"] -> "na korzyść"
| [Text "w intencji"] -> "w intencji"
| [Text "na kanwie"] -> "na kanwie"
| [Text "na niekorzyść"] -> "na niekorzyść"
| [Text "z ramienia"] -> "z ramienia"
| [Text "w wyniku"] -> "w wyniku"
| [Text "za sprawą"] -> "za sprawą"
| [Text "w imię"] -> "w imię"
| [Text "w celu"] -> "w celu"
| [Text "z pomocą"] -> "z pomocą"
| [Text "per"] -> "per"
| [Text "co"] -> "co"
| [Text s] -> s
| l -> failwith ("parse_prep: " ^ WalStringOf.token_list l)
let rec parse_comp = function
[Text "int"] -> Int,[]
| [Text "rel"] -> Rel,[]
| [Text "int";SqBra l] -> Int,List.flatten (Xlist.map (split_symbol Semic [] l) (fun c -> snd (parse_comp c)))
| [Text "rel";SqBra l] -> Rel,List.flatten (Xlist.map (split_symbol Semic [] l) (fun c -> snd (parse_comp c)))
| [Text "co"] -> CompTypeUndef,[Comp "co"] (* subst qub prep comp *)
| [Text "kto"] -> CompTypeUndef,[Comp "kto"] (* subst *)
| [Text "ile"] -> CompTypeUndef,[Comp "ile"] (* num adv *)
| [Text "jaki"] -> CompTypeUndef,[Comp "jaki"] (* adj *)
| [Text "który"] -> CompTypeUndef,[Comp "który"] (* adj *)
| [Text "czyj"] -> CompTypeUndef,[Comp "czyj"] (* adj *)
| [Text "jak"] -> CompTypeUndef,[Comp "jak"] (* prep conj adv *)
| [Text "kiedy"] -> CompTypeUndef,[Comp "kiedy"] (* comp adv *)
| [Text "gdzie"] -> CompTypeUndef,[Comp "gdzie"] (* qub adv *)
| [Text "odkąd"] -> CompTypeUndef,[Comp "odkąd"] (* adv *)
| [Text "skąd"] -> CompTypeUndef,[Comp "skąd"] (* adv *)
| [Text "dokąd"] -> CompTypeUndef,[Comp "dokąd"] (* adv *)
| [Text "którędy"] -> CompTypeUndef,[Comp "którędy"] (* adv *)
| [Text "dlaczego"] -> CompTypeUndef,[Comp "dlaczego"] (* adv *)
| [Text "czemu"] -> CompTypeUndef,[Comp "czemu"] (* adv *)
| [Text "czy"] -> CompTypeUndef,[Comp "czy"] (* qub conj *)
| [Text "jakby"] -> CompTypeUndef,[Comp "jakby"] (* qub comp *)
| [Text "jakoby"] -> CompTypeUndef,[Comp "jakoby"] (* qub comp *)
| [Text "gdy"] -> CompTypeUndef,[Gdy] (* adv; gdyby: qub comp *)
| [Text "dopóki"] -> CompTypeUndef,[Comp "dopóki"] (* comp *)
| [Text "zanim"] -> CompTypeUndef,[Comp "zanim"] (* comp *)
| [Text "jeśli"] -> CompTypeUndef,[Comp "jeśli"] (* comp *)
| [Text "żeby2"] -> CompTypeUndef,[Zeby]
| [Text "żeby"] -> CompTypeUndef,[Comp "żeby"] (* qub comp *)
| [Text "że"] -> CompTypeUndef,[Comp "że"] (* qub comp *)
| [Text "aż"] -> CompTypeUndef,[Comp "aż"] (* qub comp *)
| [Text "bo"] -> CompTypeUndef,[Comp "bo"] (* qub comp *)
| l -> failwith ("parse_comp: " ^ WalStringOf.token_list l)
let parse_number = function
[Text "sg"] -> Number "sg"
| [Text "pl"] -> Number "pl"
| [Text "agr"] -> NumberAgr
| [Text "_"] -> NumberUndef
| l -> failwith ("parse_number: " ^ WalStringOf.token_list l)
let parse_gender = function
[Text "m1"] -> Gender "m1"
| [Text "m3"] -> Gender "m3"
| [Text "n"] -> Genders["n1";"n2"]
| [Text "f"] -> Gender "f"
| [Text "m1.n"] -> Genders["m1";"n1";"n2"]
| [Text "_"] -> GenderUndef
| [Text "agr"] -> GenderAgr
| l -> failwith ("parse_gender: " ^ WalStringOf.token_list l)
let parse_grad = function
[Text "pos"] -> Grad "pos"
| [Text "com"] -> Grad "com"
| [Text "sup"] -> Grad "sup"
| [Text "_"] -> GradUndef
| l -> failwith ("parse_grad: " ^ WalStringOf.token_list l)
let parse_refl = function
[] -> ReflEmpty
| [Text "się"] -> ReflSie
| [Text ""] -> ReflEmpty
| [Text "false"] -> ReflEmpty
| [Text "true"] -> ReflSie
| l -> failwith ("parse_refl: " ^ WalStringOf.token_list l)
let rec parse_lex = function
[Quot; Text "E"; Paren[Text gender]; Quot] -> Elexeme(parse_gender [Text gender])
| [Quot; Text x; Quot] -> Lexeme x
| [Quot; Text x; Comma; Text y; Quot] -> Lexeme (x ^ "," ^ y)
| [Text "OR"; Paren l] ->
(match split_symbol Semic [] l with
[l] -> (match split_symbol Comma [] l with
[_] -> failwith "parse_lex OR"
| ll -> ORconcat(Xlist.map ll parse_lex))
| ll -> ORcoord(Xlist.map ll parse_lex))
| [Text "XOR"; Paren l] -> XOR(Xlist.map (List.flatten (Xlist.map (split_symbol Semic [] l) (split_symbol Comma []))) parse_lex)
| l -> failwith ("parse_lex: " ^ WalStringOf.token_list l)
let get_lexeme = function
Lexeme s -> s
| _ -> failwith "get_lexeme"
let new_schema r cr ce morfs =
{gf=r; role=""; role_attr="";sel_prefs=[]; cr=cr; ce=ce; dir=Both; morfs=morfs}
let rec parse_restr = function
[Text "natr"] -> Natr,[]
| [Text "atr"] -> Atr,[]
| [Text "ratr"] -> Ratr,[]
| [Text "atr1"] -> Atr1,[]
| [Text "ratr1"] -> Ratr1,[]
| [Text "ratr1"; Paren schema] -> Ratr1, parse_schema_simple schema
| [Text "ratr"; Paren schema] -> Ratr, parse_schema_simple schema
| [Text "atr1"; Paren schema] -> Atr1, parse_schema_simple schema
| [Text "atr"; Paren schema] -> Atr, parse_schema_simple schema
| l -> failwith ("parse_restr: " ^ WalStringOf.token_list l)
and parse_schema_simple schema =
Xlist.map (split_symbol Plus [] schema) (function
[Bracet b] -> let r,cr,ce = parse_roles [] in new_schema r cr ce (parse_morfs b)
| [Text s1;Bracet b] -> let r,cr,ce = parse_roles [s1] in new_schema r cr ce (parse_morfs b)
| _ -> failwith "parse_schema_simple")
and parse_mode = function
[Text "abl"] -> "abl",[]
| [Text "adl"] -> "adl",[]
| [Text "caus"] -> "caus",[]
| [Text "dest"] -> "dest",[]
| [Text "dur"] -> "dur",[]
| [Text "instr"] -> "instr",[]
| [Text "locat"] -> "locat",[]
| [Text "perl"] -> "perl",[]
| [Text "temp"] -> "temp",[]
| [Text "abl";SqBra l] -> "abl",parse_morfs l
| [Text "adl";SqBra l] -> "adl",parse_morfs l
| [Text "caus";SqBra l] -> "caus",parse_morfs l
| [Text "dest";SqBra l] -> "dest",parse_morfs l
| [Text "dur";SqBra l] -> "dur",parse_morfs l
| [Text "instr";SqBra l] -> "instr",parse_morfs l
| [Text "locat";SqBra l] -> "locat",parse_morfs l
| [Text "perl";SqBra l] -> "perl",parse_morfs l
| [Text "temp";SqBra l] -> "temp",parse_morfs l
| [Text "mod"] -> "mod",[]
| [Text "mod";SqBra l] -> "mod",parse_morfs l
| [Text "pron"] -> "pron",[]
| [Text "misc"] -> "misc",[]
| l -> failwith ("parse_mode: " ^ WalStringOf.token_list l)
and parse_morf = function
"np",[case] -> Phrase(NP(parse_case case))
| "prepnp",[prep; case] -> Phrase(PrepNP(Sem,parse_prep prep,parse_case case))
| "adjp",[case] -> Phrase(AdjP(parse_case case))
| "prepadjp",[prep; case] -> Phrase(PrepAdjP(Sem,parse_prep prep,parse_case case))
| "nump",[case] -> Phrase(NumP(parse_case case))
| "prepnump",[prep; case] -> Phrase(PrepNumP(Sem,parse_prep prep,parse_case case))
| "comprepnp",[prep] -> Phrase(ComprepNP(Sem,parse_prep prep))
| "compar",[prep] -> PhraseAbbr(ComparP(parse_prep prep),[])
| "cp",[comp] -> PhraseComp(Cp,parse_comp comp)
| "ncp",[case; comp] -> PhraseComp(Ncp(parse_case case),parse_comp comp)
| "prepncp",[prep; case; comp] -> PhraseComp(Prepncp(parse_prep prep,parse_case case),parse_comp comp)
| "infp",[aspect] -> Phrase(InfP(parse_aspect aspect(*,ReqUndef*)))
| "fixed",[morf;lex] -> Phrase(FixedP((*parse_morf_single morf,*) get_lexeme (parse_lex lex)))
| "fixed",[morf;lex;lex2] -> Phrase(FixedP((*parse_morf_single morf,*) get_lexeme (parse_lex (lex @ [Comma] @ lex2))))
| "or",[] -> Phrase Or
| "refl",[] -> Phrase (*Refl*)(Lex "się")
| "recip",[] -> Phrase (*Recip*)(Lex "się") (* FIXME *)
| "E",[] -> E Null
| "advp",[mode] -> let mode,morfs = parse_mode mode in PhraseAbbr(Advp mode,morfs)
| "xp",[mode] -> let mode,morfs = parse_mode mode in PhraseAbbr(Xp mode,morfs)
| "nonch",[] -> PhraseAbbr(Nonch,[])
| "distrp",[] -> PhraseAbbr(Distrp,[])
| "possp",[] -> PhraseAbbr(Possp,[])
| "null",[] -> Phrase Null
| "lex",[Text a; Paren p] :: ll -> parse_lex_morf (a, split_symbol Comma [] p, ll)
| "lex",[Text a] :: ll -> parse_lex_morf (a, [], ll)
| s,ll -> failwith ("parse_morf: " ^ s ^ "(" ^ String.concat "," (Xlist.map ll WalStringOf.token_list) ^ ")")
and parse_lex_morf = function
| "np",[case],[num;lex;restr] -> LexPhrase([SUBST(parse_number num,parse_case case),parse_lex lex], parse_restr restr)
| "prepnp",[prep; case],[num;lex;restr] -> LexPhrase([PREP(parse_case case),Lexeme(parse_prep prep);SUBST(parse_number num,parse_case case),parse_lex lex], parse_restr restr)
| "adjp",[case],[num;gender;grad;lex;restr] -> LexPhrase([ADJ(parse_number num,parse_case case,parse_gender gender,parse_grad grad),parse_lex lex], parse_restr restr)
| "prepadjp",[prep; case],[num;gender;grad;lex;restr] -> LexPhrase([PREP(parse_case case),Lexeme(parse_prep prep);ADJ(parse_number num,parse_case case,parse_gender gender,parse_grad grad),parse_lex lex], parse_restr restr)
| "ppasp",[case],[num;gender;negation;lex;restr] -> LexPhrase([PPAS(parse_number num,parse_case case,parse_gender gender,AspectUndef,parse_negation negation),parse_lex lex], parse_restr restr)
| "prepppasp",[prep;case],[num;gender;negation;lex;restr] -> LexPhrase([PREP(parse_case case),Lexeme(parse_prep prep);PPAS(parse_number num,parse_case case,parse_gender gender,AspectUndef,parse_negation negation),parse_lex lex], parse_restr restr)
| "pactp",[case],[num;gender;negation;lex;refl;restr] -> LexPhrase([PACT(parse_number num,parse_case case,parse_gender gender,AspectUndef,parse_negation negation,parse_refl refl),parse_lex lex], parse_restr restr)
| "preppactp",[prep;case],[num;gender;negation;lex;refl;restr] -> LexPhrase([PREP(parse_case case),Lexeme(parse_prep prep);PACT(parse_number num,parse_case case,parse_gender gender,AspectUndef,parse_negation negation,parse_refl refl),parse_lex lex], parse_restr restr)
| "gerp",[case],[num;negation;lex;refl;restr] -> LexPhrase([GER(parse_number num,parse_case case,GenderUndef,AspectUndef,parse_negation negation,parse_refl refl),parse_lex lex], parse_restr restr)
| "prepgerp",[prep;case],[num;negation;lex;refl;restr] -> LexPhrase([PREP(parse_case case),Lexeme(parse_prep prep);GER(parse_number num,parse_case case,GenderUndef,AspectUndef,parse_negation negation,parse_refl refl),parse_lex lex], parse_restr restr)
| "nump",[case],[lex1;lex2;restr] -> LexPhrase([NUM(parse_case case,GenderUndef,AcmUndef),parse_lex lex1;SUBST(NumberUndef,CaseUndef),parse_lex lex2], parse_restr restr)
| "prepnump",[prep;case],[lex1;lex2;restr] -> LexPhrase([PREP(parse_case case),Lexeme(parse_prep prep);NUM(parse_case case,GenderUndef,AcmUndef),parse_lex lex1;SUBST(NumberUndef,CaseUndef),parse_lex lex2], parse_restr restr)
| "compar",[prep],[morfs] -> LexPhrase([COMPAR,Lexeme(parse_prep prep)],(Ratrs,Xlist.map (split_symbol Plus [] morfs) (fun morf -> new_schema ARG [] [] [parse_morf_single morf])))
| "infp",[aspect],[negation;lex;refl;restr] -> LexPhrase([INF(parse_aspect aspect,parse_negation negation,parse_refl refl),parse_lex lex], parse_restr restr)
| "qub",[],[lex;restr] -> LexPhrase([QUB,parse_lex lex], parse_restr restr)
| "advp",[mode],[grad;lex;restr] ->
(match parse_mode mode with
mode, [] -> LexPhraseMode(mode,[ADV(parse_grad grad),parse_lex lex], parse_restr restr)
| _ -> failwith "parse_lex_morf")
| "xp",[[Text mode;SqBra [Text "prepgerp"; Paren [prep;Comma;case]]]],[num;negation;lex;refl;restr] ->
LexPhraseMode(mode,[PREP(parse_case [case]),Lexeme(parse_prep [prep]);GER(parse_number num,parse_case [case],GenderUndef,AspectUndef,parse_negation negation,parse_refl refl),parse_lex lex], parse_restr restr)
| "xp",[mode],ll ->
(match parse_mode mode,ll with
(mode,[Phrase(NP case)]),[num;lex;restr] -> LexPhraseMode(mode,[SUBST(parse_number num,case),parse_lex lex], parse_restr restr)
| (mode,[Phrase(PrepNP(_,prep,case))]),[num;lex;restr] -> LexPhraseMode(mode,[PREP case,Lexeme prep;SUBST(parse_number num,case),parse_lex lex], parse_restr restr)
| (mode,[Phrase(PrepAdjP(_,prep,case))]),[num;gender;grad;lex;restr] -> LexPhraseMode(mode,[PREP case,Lexeme prep;ADJ(parse_number num,case,parse_gender gender,parse_grad grad),parse_lex lex], parse_restr restr)
| (mode,[Phrase(NumP case)]),[lex1;lex2;restr] -> LexPhraseMode(mode,[NUM(case,GenderUndef,AcmUndef),parse_lex lex1;SUBST(NumberUndef,CaseUndef),parse_lex lex2], parse_restr restr)
| (mode,[Phrase(PrepNumP(_,prep,case))]),[lex1;lex2;restr] -> LexPhraseMode(mode,[PREP case,Lexeme prep;NUM(case,GenderUndef,AcmUndef),parse_lex lex1;SUBST(NumberUndef,CaseUndef),parse_lex lex2], parse_restr restr)
| (mode,[PhraseAbbr(Advp _,[])]),[grad;lex;restr] -> LexPhraseMode(mode,[ADV(parse_grad grad),parse_lex lex], parse_restr restr)
| (mode,[PhraseAbbr(ComparP prep,[])]),[morfs] -> LexPhraseMode(mode,[COMPAR,Lexeme prep],(Ratrs,Xlist.map (split_symbol Plus [] morfs) (fun morf -> new_schema ARG [] [] [parse_morf_single morf])))
| (mode,[PhraseComp(Cp,(ctype,[Comp comp]))]),[negation;lex;refl;restr] -> LexPhrase([COMP ctype,Lexeme comp;PERS(parse_negation negation,parse_refl refl),parse_lex lex], parse_restr restr)
| _ -> failwith ("parse_lex_morf: xp(" ^ WalStringOf.token_list mode ^ ")," ^ String.concat "," (Xlist.map ll WalStringOf.token_list) ^ ")"))
| "cp",[comp],[negation;lex;refl;restr] ->
(match parse_comp comp with
ctype,[Comp comp] -> LexPhrase([COMP ctype,Lexeme comp;PERS(parse_negation negation,parse_refl refl),parse_lex lex], parse_restr restr)
| ctype,[Comp comp1;Comp comp2] -> LexPhrase([COMP ctype,XOR[Lexeme comp1;Lexeme comp2];PERS(parse_negation negation,parse_refl refl),parse_lex lex], parse_restr restr)
| _,comp -> failwith ("parse_lex_morf comp: " (*^ WalStringOf.comp comp*)))
| "ncp",[case;comp],[negation;lex;refl;restr] ->
(match parse_comp comp with
ctype,[Comp comp] -> LexPhrase([SUBST(Number "sg",parse_case case),Lexeme "to";COMP ctype,Lexeme comp;PERS(parse_negation negation,parse_refl refl),parse_lex lex], parse_restr restr)
| _,comp -> failwith ("parse_lex_morf comp: " (*^ WalStringOf.comp comp*)))
| s,ll,ll2 -> failwith ("parse_lex_morf: " ^ s ^ "(" ^ String.concat "," (Xlist.map ll WalStringOf.token_list) ^ ")," ^ String.concat "," (Xlist.map ll2 WalStringOf.token_list) ^ ")")
and parse_morfs l =
let morfs = Xlist.map (split_symbol Semic [] l) (function
[Text a; Paren p] -> parse_morf (a, split_symbol Comma [] p)
| [Text a] -> parse_morf (a, [])
| l -> failwith ("parse_morfs: " ^ WalStringOf.token_list l)) in
(* expand_prep_morfs equivs (expand_comp_morfs equivs morfs) *)morfs
and parse_morf_single l = (* FIXME: problem z equivs *)
match parse_morfs l with
[x] -> x
| l -> failwith ("parse_morf_single: " ^ String.concat ";" (Xlist.map l WalStringOf.morf))
let split_schema schema =
find_brackets (Xlist.map (Str.full_split (Str.regexp "\\]\\|\\+\\|{\\|}\\|(\\|)\\|,\\|;\\|'\\|\\[") schema) (function
Str.Text s -> Text s
| Str.Delim "(" -> LParen
| Str.Delim ")" -> RParen
| Str.Delim "{" -> LBracet
| Str.Delim "}" -> RBracet
| Str.Delim "[" -> LSqBra
| Str.Delim "]" -> RSqBra
| Str.Delim ";" -> Semic
| Str.Delim "+" -> Plus
| Str.Delim "," -> Comma
| Str.Delim "'" -> Quot
| _ -> failwith "parse_schema"))
let parse_schema schema =
if schema = "" then [] else (
let l = split_schema schema in
(* print_endline schema; *)
Xlist.map (split_symbol Plus [] l) (function
[Bracet b] -> let r,cr,ce = parse_roles [] in new_schema r cr ce (parse_morfs b)
| [Text s1;Bracet b] -> let r,cr,ce = parse_roles [s1] in new_schema r cr ce (parse_morfs b)
| [Text s1;Comma;Text s2;Bracet b] -> let r,cr,ce = parse_roles [s1;s2] in new_schema r cr ce (parse_morfs b)
| [Text s1;Comma;Text s2;Comma;Text s3;Bracet b] -> let r,cr,ce = parse_roles [s1;s2;s3] in new_schema r cr ce (parse_morfs b)
| _ -> failwith ("parse_schema: " ^ schema)))
let parse_lexeme s =
match Str.split (Str.regexp " ") s with
[s] -> s,""
| [s;"się"] -> s,"się"
| _ -> failwith ("parse_lexeme: " ^ s)
let load_frames filename =
Xlist.fold (List.tl (Str.split (Str.regexp "\n") (File.load_file filename))) StringMap.empty (fun schemas line ->
if String.sub line 0 1 = "%" then schemas else
match Str.split_delim (Str.regexp ": ") line with
[lexeme;opinion;negation;pred;aspect;schema] ->
let lexeme,refl = parse_lexeme lexeme in
StringMap.add_inc schemas lexeme [refl,opinion,negation,pred,aspect,schema] (fun l -> (refl,opinion,negation,pred,aspect,schema) :: l)
| _ -> failwith ("load_frames: " ^ line))
let rec expand_schema_morf expands = function
PhraseAbbr(Advp "misc",[]) -> PhraseAbbr(Advp "misc",[])
| PhraseAbbr(Advp "mod",[]) -> PhraseAbbr(Advp "mod",[])
| PhraseAbbr(ComparP s,[]) -> PhraseAbbr(ComparP s,[Phrase(ComparNP(Sem,s,Str));Phrase(ComparPP(Sem,s))])
| PhraseAbbr(abbr,[]) -> (try PhraseAbbr(abbr,AbbrMap.find expands abbr) with Not_found -> failwith "expand_schema_morf")
| PhraseAbbr(abbr,morfs) -> PhraseAbbr(abbr,Xlist.map morfs (expand_schema_morf expands))
| LexPhrase(pos_lex,(restr,schema)) -> LexPhrase(pos_lex,(restr,expand_schema expands schema))
| LexPhraseMode(mode,pos_lex,(restr,schema)) -> LexPhraseMode(mode,pos_lex,(restr,expand_schema expands schema))
| morf -> morf
and expand_schema expands schema =
Xlist.map schema (fun s ->
{s with morfs=Xlist.map s.morfs (expand_schema_morf expands)})
let rec expand_subtypes_morf subtypes = function
PhraseComp(comp_morf,(ctype,comps)) ->
let comps = if comps = [] then (try CompMap.find subtypes ctype with Not_found -> failwith "expand_subtypes_schema") else comps in
Xlist.map comps (fun comp -> Phrase(match comp_morf with
Cp -> CP(ctype,comp)
| Ncp case -> NCP(case,ctype,comp)
| Prepncp(prep,case) -> PrepNCP(Sem,prep,case,ctype,comp)))
| LexPhrase(pos_lex,(restr,schema)) -> [LexPhrase(pos_lex,(restr,expand_subtypes subtypes schema))]
| LexPhraseMode(mode,pos_lex,(restr,schema)) -> [LexPhraseMode(mode,pos_lex,(restr,expand_subtypes subtypes schema))]
| PhraseAbbr(abbr,morfs) -> [PhraseAbbr(abbr,List.flatten (Xlist.map morfs (expand_subtypes_morf subtypes)))]
| E Null -> [E(NP(Str));E(NCP(Str,CompTypeUndef,CompUndef));E(CP(CompTypeUndef,CompUndef)); E(Or)]
| morf -> [morf]
and expand_subtypes subtypes schema =
Xlist.map schema (fun s ->
{s with morfs=List.flatten (Xlist.map s.morfs (expand_subtypes_morf subtypes))})
let expand_equivs_phrase equivs = function
| PrepNP(sem,prep,case) -> Xlist.map (try StringMap.find equivs prep with Not_found -> [prep]) (fun prep -> PrepNP(sem,prep,case))
| PrepAdjP(sem,prep,case) -> Xlist.map (try StringMap.find equivs prep with Not_found -> [prep]) (fun prep -> PrepAdjP(sem,prep,case))
| PrepNumP(sem,prep,case) -> Xlist.map (try StringMap.find equivs prep with Not_found -> [prep]) (fun prep -> PrepNumP(sem,prep,case))
| ComprepNP(sem,prep) -> Xlist.map (try StringMap.find equivs prep with Not_found -> [prep]) (fun prep -> ComprepNP(sem,prep))
| ComparNP(sem,prep,case) -> Xlist.map (try StringMap.find equivs prep with Not_found -> [prep]) (fun prep -> ComparNP(sem,prep,case))
| ComparPP(sem,prep) -> Xlist.map (try StringMap.find equivs prep with Not_found -> [prep]) (fun prep -> ComparPP(sem,prep))
| CP(ctype,Comp comp) -> Xlist.map (try StringMap.find equivs comp with Not_found -> [comp]) (fun comp -> CP(ctype,Comp comp))
| NCP(case,ctype,Comp comp) -> Xlist.map (try StringMap.find equivs comp with Not_found -> [comp]) (fun comp -> NCP(case,ctype,Comp comp))
| PrepNCP(sem,prep,case,ctype,Comp comp) -> List.flatten (
Xlist.map (try StringMap.find equivs comp with Not_found -> [comp]) (fun comp ->
Xlist.map (try StringMap.find equivs prep with Not_found -> [prep]) (fun prep ->
PrepNCP(sem,prep,case,ctype,Comp comp))))
| phrase -> [phrase]
let rec expand_equivs_lex equivs = function
Lexeme s -> (try XOR(Xlist.map (StringMap.find equivs s) (fun s -> Lexeme s)) with Not_found -> Lexeme s)
| ORconcat l -> ORconcat(Xlist.map l (expand_equivs_lex equivs))
| ORcoord l -> ORcoord(Xlist.map l (expand_equivs_lex equivs))
| XOR l -> XOR(Xlist.map l (expand_equivs_lex equivs))
| Elexeme gender -> Elexeme gender
let rec expand_equivs_morf equivs = function
Phrase phrase -> Xlist.map (expand_equivs_phrase equivs phrase) (fun phrase -> Phrase phrase)
| E phrase -> Xlist.map (expand_equivs_phrase equivs phrase) (fun phrase -> E phrase)
| LexPhrase(pos_lex,(restr,schema)) -> [LexPhrase(Xlist.map pos_lex (fun (pos,lex) -> pos, expand_equivs_lex equivs lex),(restr,expand_equivs_schema equivs schema))]
| LexPhraseMode(mode,pos_lex,(restr,schema)) -> [LexPhraseMode(mode,Xlist.map pos_lex (fun (pos,lex) -> pos, expand_equivs_lex equivs lex),(restr,expand_equivs_schema equivs schema))]
| PhraseAbbr(abbr,morfs) -> [PhraseAbbr(abbr,List.flatten (Xlist.map morfs (expand_equivs_morf equivs)))]
| morf -> failwith ("expand_equivs_morf: " ^ WalStringOf.morf morf)
and expand_equivs_schema equivs schema =
Xlist.map schema (fun s ->
{s with morfs=List.flatten (Xlist.map s.morfs (expand_equivs_morf equivs))})
let rec load_realizations_rec (expands,subtypes,equivs) found rev = function
[] -> if rev <> [] || found <> [] then failwith "load_realizations_rec" else expands,subtypes,equivs
| [Str.Text s; Str.Delim "-->"] :: l -> load_realizations_rec (expands,subtypes,equivs) ((s,rev) :: found) [] l
| [Str.Delim " "; Str.Text s; Str.Delim "\t"; Str.Text t] :: l ->
load_realizations_rec (expands,subtypes,equivs) found ((s,t) :: rev) l
| [Str.Delim " "; Str.Text s] :: l ->
load_realizations_rec (expands,subtypes,equivs) found ((s,"") :: rev) l
| [Str.Delim "% "; Str.Text "Phrase types expand:"] :: l -> load_realizations_rec (found,subtypes,equivs) [] rev l
| [Str.Delim "% "; Str.Text "Attributes subtypes:"] :: l -> load_realizations_rec (expands,found,equivs) [] rev l
| [Str.Delim "% "; Str.Text "Attributes equivalents:"] :: l -> load_realizations_rec (expands,subtypes,found) [] rev l
(* | [Str.Delim "% "; Str.Text s] :: l -> print_endline s; load_realizations_rec found rev l *)
| [] :: l -> load_realizations_rec (expands,subtypes,equivs) found rev l
| _ -> failwith "load_realizations_rec"
let rec get_lexemes = function
Lexeme s -> [s]
| ORconcat l -> List.flatten (Xlist.map l get_lexemes)
| ORcoord l -> List.flatten (Xlist.map l get_lexemes)
| XOR l -> List.flatten (Xlist.map l get_lexemes)
| Elexeme gender -> failwith "get_lexemes"
let find_comprep_reqs compreps =
Xlist.fold compreps StringMap.empty (fun comprep_reqs (s,l) ->
let l = Xlist.map l (function
LexPhrase(pos_lex,_) -> Xlist.fold pos_lex StringSet.empty (fun set -> function
_,Lexeme s -> StringSet.add set s
| _ -> set)
| LexPhraseMode(_,pos_lex,_) -> Xlist.fold pos_lex StringSet.empty (fun set -> function
_,Lexeme s -> StringSet.add set s
| _ -> set)
| morf -> failwith ("find_compreps_reqs: " ^ WalStringOf.morf morf)) in
if l = [] then failwith "find_compreps_reqs";
StringMap.add comprep_reqs s (StringSet.to_list (Xlist.fold (List.tl l) (List.hd l) StringSet.union)))
let create_comprep_dict compreps =
Xlist.fold compreps StringMap.empty (fun compreps (s,l) ->
Xlist.fold l compreps (fun compreps -> function
LexPhrase([PREP _,_;SUBST _,lex],_) as morf ->
let lexemes = get_lexemes lex in
Xlist.fold lexemes compreps (fun compreps lexeme ->
StringMap.add_inc compreps lexeme ["subst",(s,morf)] (fun l -> ("subst",(s,morf)) :: l))
| LexPhraseMode("misc",[ADV grad,lex],restr) ->
let morf = LexPhrase([ADV grad,lex],restr) in
let lexemes = get_lexemes lex in
Xlist.fold lexemes compreps (fun compreps lexeme ->
StringMap.add_inc compreps lexeme ["adv",(s,morf)] (fun l -> ("adv",(s,morf)) :: l))
| LexPhrase([PREP _,_;NUM _,_;SUBST _,lex],_) as morf ->
let lexemes = get_lexemes lex in
Xlist.fold lexemes compreps (fun compreps lexeme ->
StringMap.add_inc compreps lexeme ["subst",(s,morf)] (fun l -> ("subst",(s,morf)) :: l))
| morf -> failwith ("create_comprep_dict: " ^ WalStringOf.morf morf)))
let load_realizations () =
let lines = Str.split (Str.regexp "\n") (File.load_file (Paths.realizations_filename)) in
let lines = Xlist.rev_map lines (fun line -> Str.full_split (Str.regexp "% \\|-->\\| \\|\t") line) in
let expands,subtypes,equivs = load_realizations_rec ([],[],[]) [] [] lines in
let subtypes = Xlist.fold subtypes CompMap.empty (fun subtypes -> function
"int",l -> CompMap.add subtypes Int (List.flatten (Xlist.map l (fun (v,_) -> snd(parse_comp [Text v]))))
| "rel",l -> CompMap.add subtypes Rel (List.flatten (Xlist.map l (fun (v,_) -> snd(parse_comp [Text v]))))
| _ -> failwith "load_realizations 1") in
let equivs = Xlist.fold equivs StringMap.empty (fun equivs (k,l) -> StringMap.add equivs k (k :: (Xlist.map l (fun (v,_) -> v)))) in
let expands,compreps = Xlist.fold expands (AbbrMap.empty,[]) (fun (expands, compreps) (k,l) ->
match parse_morf_single (split_schema k) with
PhraseAbbr(Advp m,[]) -> AbbrMap.add expands (Advp m) (Xlist.map l (fun (v,_) ->
LexPhraseMode(m,[ADV GradUndef,Lexeme v],(Natr,[])))), compreps
| PhraseAbbr(Nonch,[]) -> AbbrMap.add expands Nonch (Xlist.map l (fun (v,_) ->
LexPhrase([SUBST(NumberUndef,Str),Lexeme v],(Natr,[])))), compreps
| PhraseAbbr(Xp m,[]) -> AbbrMap.add expands (Xp m) (List.flatten (Xlist.map l (fun (v,_) ->
match parse_morfs (split_schema v) with
[PhraseAbbr(Advp m,[])] -> (try AbbrMap.find expands (Advp m) with Not_found -> [PhraseAbbr(Advp m,[])]) (* FIXME: zakładam, że advp się nie rozmnoży *)
| morfs -> morfs))), compreps
| Phrase(ComprepNP(_,s)) -> expands, (s, Xlist.map l (fun (v,_) -> parse_morf_single (split_schema v))) :: compreps
| PhraseAbbr(Distrp,[]) -> AbbrMap.add expands Distrp (Xlist.map l (fun (v,_) -> parse_morf_single (split_schema v))), compreps
| PhraseAbbr(Possp,[]) -> AbbrMap.add expands Possp (Xlist.map l (fun (v,_) -> parse_morf_single (split_schema v))), compreps
| _ -> failwith "load_realizations 2") in
let compreps = Xlist.map compreps (fun (s,morfs) ->
s, List.flatten (List.flatten (Xlist.map morfs (fun morf -> Xlist.map (expand_subtypes_morf subtypes (expand_schema_morf expands morf)) (expand_equivs_morf equivs))))) in
let comprep_reqs = find_comprep_reqs compreps in
let compreps = create_comprep_dict compreps in
expands,compreps,comprep_reqs,subtypes,equivs
let rec extract_fixed_schema fixed schema =
Xlist.fold schema fixed (fun fixed s ->
Xlist.fold s.morfs fixed (fun fixed -> function
Phrase(FixedP s) -> StringSet.add fixed s
| LexPhrase(_,(_,schema)) -> extract_fixed_schema fixed schema
| LexPhraseMode(_,_,(_,schema)) -> extract_fixed_schema fixed schema
| _ -> fixed))
(*let extract_fixed fixed_filename = (* FIXME: nie wykrywa fixed w argumentach leksykalizacji *)
(* let expands,compreps,comprep_reqs,subtypes,equivs = load_realizations () in *)
let fixed = Xlist.fold Paths.walenty_filenames StringSet.empty (fun fixed filename ->
(* print_endline filename; *)
let frames = load_frames (Paths.walenty_path ^ filename) in
StringMap.fold frames fixed (fun fixed _ l ->
Xlist.fold l fixed (fun fixed (refl,opinion,negation,pred,aspect,schema) ->
extract_fixed_schema fixed (parse_schema schema)))) in
let entries = StringSet.fold fixed StringSet.empty (fun entries s ->
let tokens = List.rev (Xlist.fold (Str.full_split (Str.regexp " \\|,") s) [] (fun l -> function
Str.Text t -> t :: l
| Str.Delim " " -> l
| Str.Delim t -> t :: l)) in
let tokens_string = String.concat " " tokens in
Xlist.fold tokens entries (fun entries token ->
StringSet.add entries (Printf.sprintf "%s\t%s\t%s:fixed\tfixed" token s tokens_string))) in
File.file_out fixed_filename (fun file ->
StringSet.iter entries (fun entry ->
Printf.fprintf file "%s\n" entry))
(* generowanie fixed.tab *)
(* let _ = extract_fixed "data/fixed.tab" *)
let print_subjs () =
(* let expands,compreps,comprep_reqs,subtypes,equivs = load_realizations () in *)
let subjs = Xlist.fold Paths.walenty_filenames StringQMap.empty (fun subjs filename ->
(* print_endline filename; *)
let frames = load_frames (Paths.walenty_path ^ filename) in
StringMap.fold frames subjs (fun subjs _ l ->
Xlist.fold l subjs (fun subjs (refl,opinion,negation,pred,aspect,schema) ->
Xlist.fold (parse_schema schema) subjs (fun subjs s ->
if s.gf = SUBJ then StringQMap.add subjs (WalStringOf.schema [s]) else subjs)))) in
StringQMap.iter subjs (fun s v ->
Printf.printf "%5d %s\n" v s)
(* let _ = print_subjs () *)
let print_ctrls () =
(* let expands,compreps,comprep_reqs,subtypes,equivs = load_realizations () in *)
let ctrls = Xlist.fold Paths.walenty_filenames StringQMap.empty (fun ctrls filename ->
(* print_endline filename; *)
let frames = load_frames (Paths.walenty_path ^ filename) in
StringMap.fold frames ctrls (fun ctrls _ l ->
Xlist.fold l ctrls (fun ctrls (refl,opinion,negation,pred,aspect,schema) ->
let schema = List.rev (Xlist.fold (parse_schema schema) [] (fun l s ->
if s.cr = [] && s.ce = [] then l else s :: l)) in
StringQMap.add ctrls (WalStringOf.schema schema)))) in
StringQMap.iter ctrls (fun s v ->
Printf.printf "%5d %s\n" v s)
(* let _ = print_ctrls () *)
(* Test parsowania *)
(*let _ =
let expands,compreps,comprep_reqs,subtypes,equivs = load_realizations () in
Xlist.iter Paths.walenty_filenames (fun filename ->
print_endline filename;
let frames = load_frames (Paths.walenty_path ^ filename) in
StringMap.iter frames (fun _ l ->
Xlist.iter l (fun (refl,opinion,negation,pred,aspect,schema) ->
(* print_endline schema; *)
ignore (parse_opinion opinion);
ignore (parse_negation [Text negation]);
ignore (parse_pred [Text pred]);
ignore (parse_aspect [Text aspect]);
ignore (expand_equivs_schema equivs (expand_subtypes subtypes (expand_schema expands (parse_schema schema)))))))*)*)