walStringOf.ml
11.5 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
(*
* 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
let rec token = function
Text s -> s
| Paren l -> "(" ^ String.concat "" (Xlist.map l token) ^ ")"
| Bracet l -> "{" ^ String.concat "" (Xlist.map l token) ^ "}"
| SqBra l -> "[" ^ String.concat "" (Xlist.map l token) ^ "]"
| LParen -> "("
| RParen -> ")"
| LBracet -> "{"
| RBracet -> "}"
| LSqBra -> "["
| RSqBra -> "]"
| Semic -> ";"
| Plus -> "+"
| Comma -> ","
| Quot -> "'"
let token_list l =
String.concat "" (Xlist.map l token)
let opinion = function
Pewny -> "pewny"
| Potoczny -> "potoczny"
| Watpliwy -> "wątpliwy"
| Archaiczny -> "archaiczny"
| Zly -> "zły"
| Wulgarny -> "wulgarny"
| Domyslny -> "domyślny"
let negation = function
Negation -> "neg"
| Aff -> "aff"
| NegationUndef -> "_"
| NegationNA -> ""
let pred = function
PredNA -> ""
| Pred -> "pred"
let aspect = function
Aspect s -> s
| AspectUndef -> "_"
| AspectNA -> ""
let case = function
Case s -> s
| Str -> "str"
| Part -> "part"
| CaseAgr -> "agr"
| CaseUAgr -> "uagr"
| NomAgr -> "nomagr"
| GenAgr -> "genagr"
| AllAgr -> "allagr"
| AllUAgr -> "alluagr"
| CaseUndef -> "_"
let rec comp = function
Comp s -> s
| Zeby -> "żeby2"
| Gdy -> "gdy"
| CompUndef -> "_"
let rec comp_type = function
Int -> "int"
| Rel -> "rel"
| Sub -> "sub"
| Coord -> "coord"
| CompTypeUndef -> "_"
| CompTypeAgr -> "agr"
let number = function
Number s -> s
| NumberAgr -> "agr"
| NumberUndef -> "_"
let gender = function
Gender s -> s
| GenderUndef -> "_"
| GenderAgr -> "agr"
| Genders l -> String.concat "." l
let grad = function
Grad s -> s
| GradUndef -> "_"
let refl = function
ReflEmpty -> ""
| ReflSie -> "się"
let acm = function
Acm s -> s
| AcmUndef -> "_"
let sem = function
Sem -> "sem"
| NoSem -> "nosem"
(*let req = function
Req -> ",req"
| NReq -> ",nreq"
| ReqUndef -> ""*)
let gf = function
SUBJ -> "subj"
| OBJ -> "obj"
| ARG -> "arg"(*""*)
| CORE -> "core"
| NOSEM -> "nosem"
| NOGF -> "nogf"
| ADJUNCT -> "adjunct"
| RAISED -> "raised"
| CLAUSE -> "clause"
| SENTENCE -> "sentence"
let pos = function
SUBST(n,c) -> "SUBST(" ^ number n ^ "," ^ case c ^ ")"
| PREP(c) -> "PREP(" ^ case c ^ ")"
| NUM(c,g,a) -> "NUM(" ^ case c ^ "," ^ gender g ^ "," ^ acm a ^ ")"
| ADJ(n,c,g,gr) -> "ADJ(" ^ number n ^ "," ^ case c ^ "," ^ gender g ^ "," ^ grad gr ^ ")"
| ADV(gr) -> "ADV(" ^ grad gr ^ ")"
| GER(n,c,g,a,neg,r) -> "GER(" ^ number n ^ "," ^ case c ^ "," ^ gender g ^ "," ^ aspect a ^ "," ^ negation neg ^ "," ^ refl r ^ ")"
| PACT(n,c,g,a,neg,r) -> "PACT(" ^ number n ^ "," ^ case c ^ "," ^ gender g ^ "," ^ aspect a ^ "," ^ negation neg ^ "," ^ refl r ^ ")"
| PPAS(n,c,g,a,neg) -> "PPAS(" ^ number n ^ "," ^ case c ^ "," ^ gender g ^ "," ^ aspect a ^ "," ^ negation neg ^ ")"
| INF(a,n,r) -> "INF(" ^ aspect a ^ "," ^ negation n ^ "," ^ refl r ^ ")"
| QUB -> "QUB"
| COMPAR -> "COMPAR"
| COMP(c) -> "COMP(" ^ comp_type c ^ ")"
| PERS(n,r) -> "PERS(" ^ negation n ^ "," ^ refl r ^ ")"
let phrase = function
NP c -> "np(" ^ case c ^ ")"
| PrepNP(s,prep,c) -> "prepnp(" ^ sem s ^ "," ^ prep ^ "," ^ case c ^ ")"
| AdjP c -> "adjp(" ^ case c ^ ")"
| PrepAdjP(s,prep,c) -> "prepadjp(" ^ sem s ^ "," ^ prep ^ "," ^ case c ^ ")"
| NumP(c) -> "nump(" ^ case c ^ ")"
| PrepNumP(s,prep,c) -> "prepnump(" ^ sem s ^ "," ^ prep ^ "," ^ case c ^ ")"
| ComprepNP(s,prep) -> "comprepnp(" ^ sem s ^ "," ^ prep ^ ")"
| ComparNP(s,prep,c) -> "comparnp(" ^ sem s ^ "," ^ prep ^ "," ^ case c ^ ")"
| ComparPP(s,prep) -> "comparpp(" ^ sem s ^ "," ^ prep ^ ")"
| IP -> "ip"
| CP(ct,co) -> "cp(" ^ comp_type ct ^ "," ^ comp co ^ ")"
| NCP(c,ct,co) -> "ncp(" ^ case c ^ "," ^ comp_type ct ^ "," ^ comp co ^ ")"
| PrepNCP(s,prep,c,ct,co) -> "prepncp(" ^ sem s ^ "," ^ prep ^ "," ^ case c ^ "," ^ comp_type ct ^ "," ^ comp co ^ ")"
| InfP(a(*,r*)) -> "infp(" ^ aspect a (*^ req r*) ^ ")"
| PadvP -> "padvp"
| AdvP -> "advp"
| FixedP s -> "fixed(" ^ s ^ ")"
| PrepP -> "prepp"
| Prep(prep,c) -> "prep(" ^ prep ^ "," ^ case c ^ ")"
| Num(c,a) -> "num(" ^ case c ^ "," ^ acm a ^ ")"
| Measure(c) -> "measure(" ^ case c ^ ")"
| Or -> "or"
(* | Refl -> "refl" *)
(* | Recip -> "recip" *)
| Qub -> "qub"
| Inclusion -> "inclusion"
| Adja -> "adja"
| AuxPast -> "aux-past"
| AuxFut -> "aux-fut"
| AuxImp -> "aux-imp"
| Aglt -> "aglt"
| Pro -> "pro"
| ProNG -> "prong"
| Null -> "null"
| X -> "x"
| Lex s -> "lex(" ^ s ^ ")"
let phrase_abbr = function
Xp(m) -> "xp(" ^ m ^ ")"
| Advp(m) -> "advp(" ^ m ^ ")"
| ComparP prep -> "compar(" ^ prep ^ ")"
| Nonch -> "nonch"
| Distrp -> "distrp"
| Possp -> "possp"
let phrase_comp = function
Cp -> "cp"
| Ncp(c) -> "ncp(" ^ case c ^ ")"
| Prepncp(prep,c) -> "prepncp(" ^ prep ^ "," ^ case c ^ ")"
let rec lex = function
Lexeme s -> "'" ^ s ^ "'"
| ORconcat l -> "OR(" ^ String.concat "," (Xlist.map l lex) ^ ")"
| ORcoord l -> "OR(" ^ String.concat ";" (Xlist.map l lex) ^ ")"
| XOR l -> "XOR(" ^ String.concat "," (Xlist.map l lex) ^ ")"
| Elexeme g -> "'E(" ^ gender g ^ ")"
let restr = function
Natr -> "natr"
| Atr -> "atr"
| Ratr -> "ratr"
| Ratrs -> "ratrs"
| Atr1 -> "atr1"
| Ratr1 -> "ratr1"
(* | Ratr1,s -> "ratr1(" ^ schema s ^ ")"
| Atr1,s -> "atr1(" ^ schema s ^ ")"
| Ratr,s -> "ratr(" ^ schema s ^ ")"
| Atr,s -> "atr(" ^ schema s ^ ")"
| Ratrs,s -> "ratrs(" ^ schema s ^ ")"
*) | NoRestr -> ""
(* | NoRestr,s -> schema s *)
let controllers l =
Xlist.map l (function
"1" -> "controller"
| n -> "controller" ^ n)
let controllees l =
Xlist.map l (function
"1" -> "controllee"
| n -> "controllee" ^ n)
(*let lex_specs = function
NSpecs num -> number num
| AdvSpecs gr -> grad gr
| AdjSpecs(num,g,gr) -> number num ^ "," ^ gender g ^ "," ^ grad gr
| PpasSpecs(num,g,neg) -> number num ^ "," ^ gender g ^ "," ^ negation neg
| PactSpecs(num,g,neg,r) -> number num ^ "," ^ gender g ^ "," ^ negation neg ^ "," ^ refl r
| GerSpecs(num,neg,r) -> number num ^ "," ^ negation neg ^ "," ^ refl r
| CSpecs(neg,r) -> negation neg ^ "," ^ refl r
| NumSpecs g -> gender g
| EmptySpecs -> ""*)
let mood = function
(*Mood*) s -> s
(*| MoodUndef -> "_"*)
let tense t = t
let aux = function
NoAux -> "-"
| PastAux -> "aux-past"
| FutAux -> "aux-fut"
| ImpAux -> "aux-imp"
let nsem = function
Common s -> s
| Time -> "time"
let direction = function
Forward -> "/"
| Backward -> "\\"
| Both -> "|"
let rec schema schema =
String.concat "+" (Xlist.map schema (fun s ->
String.concat "," (
(if s.gf = ARG then [] else [gf s.gf])@
(if s.role = "" then [] else [s.role])@
(if s.role_attr = "" then [] else [s.role_attr])@
s.sel_prefs@(controllers s.cr)@(controllees s.ce)) ^ direction s.dir ^ "{" ^ String.concat ";" (Xlist.map s.morfs morf) ^ "}"))
(*and schema_role schema =
String.concat "+" (Xlist.map schema (fun (r,role,cr,ce,morfs) ->
String.concat "," ((if r = "" then [] else [r])@(if role = "" then [] else [role])@(controllers cr)@(controllees ce)) ^ "{" ^ String.concat ";" (Xlist.map morfs morf) ^ "}")) *)
and morf = function
Phrase p -> phrase p
| E p -> "E(" ^ phrase p ^ ")"
| LexPhrase(pos_lex,(r,s)) -> "lex([" ^ String.concat ";" (Xlist.map pos_lex (fun (p,le) -> pos p ^ "," ^ lex le)) ^ "]," ^ restr r ^ "[" ^ schema s ^ "])"
| LexPhraseMode(m,pos_lex,(r,s)) -> "lex([" ^ m ^ "," ^ String.concat ";" (Xlist.map pos_lex (fun (p,le) -> pos p ^ "," ^ lex le)) ^ "]," ^ restr r ^ "[" ^ schema s ^ "])"
| PhraseAbbr(p,ml) -> phrase_abbr p ^ "[" ^ String.concat ";" (Xlist.map ml morf) ^ "]"
| PhraseComp(p,(ct,l)) -> phrase_comp p ^ "," ^ comp_type ct ^ "[" ^ String.concat ";" (Xlist.map l comp) ^ "]"
| LexPhraseId(id,p,le) -> "lex(" ^ id ^ "," ^ pos p ^ "," ^ lex le ^ ")"
| LexArg(id,p,le) -> "lex(" ^ id ^ "," ^ pos p ^ "," ^ le ^ ")"
(* | LexRealization(mrf,le) -> "lex(" ^ morf mrf ^ "," ^ le ^ ")"*)
| Raised(mrf1,dir,mrf2) -> "raised([" ^ String.concat ";" mrf1 ^ "]," ^ direction dir ^ "[" ^ String.concat ";" mrf2 ^ "])"
| Multi l -> "multi(" ^ String.concat ";" (Xlist.map l phrase) ^ ")"
(*and mode = function
Mode(s,[]) -> s
| Mode(s,l) -> s ^ "[" ^ "..."(*String.concat ";" (Xlist.map l morf)*) ^ "]"
(* | Mod l -> "mod[...]" *)
| Pron [] -> "pron"
| Pron l -> "pron" ^ "[" ^ "..."(*String.concat ";" (Xlist.map l morf)*) ^ "]"
| Misc -> "misc"*)
let frame_atrs = function
DefaultAtrs(m,r,o,neg,p,a) -> Printf.sprintf "%s: %s: %s: %s: %s: %s" (String.concat "; " m) (refl r) (opinion o) (negation neg) (pred p) (aspect a)
| EmptyAtrs m -> Printf.sprintf "%s" (String.concat "; " m)
| NounAtrs(m,nsyn,s(*,typ*)) -> Printf.sprintf "%s: %s: %s" (String.concat "; " m) nsyn (nsem s) (*(String.concat ";" typ)*)
| AdjAtrs(m,c,adjsyn(*,adjsem,typ*)) -> Printf.sprintf "%s: %s: %s" (String.concat "; " m) (case c) adjsyn (*adjsem (String.concat ";" typ)*)
| PersAtrs(m,le,neg,mo,t,au,a) -> Printf.sprintf "%s: %s: %s: %s: %s: %s: %s" (String.concat "; " m) le (negation neg) (mood mo) (tense t) (aux au) (aspect a)
| GerAtrs(m,le,neg,a) -> Printf.sprintf "%s: %s: %s: %s" (String.concat "; " m) le (negation neg) (aspect a)
| NonPersAtrs(m,le,role,role_attr,neg,a) -> Printf.sprintf "%s: %s: %s,%s: %s: %s" (String.concat "; " m) le role role_attr (negation neg) (aspect a)
| _ -> failwith "WalStringOf.frame_atrs"
let frame lexeme = function
Frame(atrs,s) ->
Printf.sprintf "%s: %s: %s" lexeme (frame_atrs atrs) (schema s)
| LexFrame(id,p,r,s) ->
Printf.sprintf "%s: %s: %s: %s: %s" lexeme id (pos p) (restr r) (schema s)
| ComprepFrame(le,p,r,s) ->
Printf.sprintf "%s: %s: %s: %s: %s" lexeme le (pos p) (restr r) (schema s)
(* | FrameR(atrs,s) ->
Printf.sprintf "%s: %s: %s" lexeme (frame_atrs atrs) (schema_role s)
| LexFrameR(id,p,r,s) ->
Printf.sprintf "%s: %s: %s: %s: %s" lexeme id (pos p) (restr r) (schema_role s)
| ComprepFrameR(le,p,r,s) ->
Printf.sprintf "%s: %s: %s: %s: %s" lexeme le (pos p) (restr r) (schema_role s)*)
(* | _ -> failwith "WalStringOf.frame" *)
let fnum_frame lexeme = function
fnum,Frame(atrs,s) ->
Printf.sprintf "%d: %s: %s: %s" fnum lexeme (frame_atrs atrs) (schema s)
| fnum,LexFrame(id,p,r,s) ->
Printf.sprintf "%d: %s: %s: %s: %s: %s" fnum lexeme id (pos p) (restr r) (schema s)
| fnum,ComprepFrame(le,p,r,s) ->
Printf.sprintf "%d: %s: %s: %s: %s: %s" fnum lexeme le (pos p) (restr r) (schema s)
let unparsed_frame lexeme (r,o,neg,p,a,s) = lexeme ^ " " ^ String.concat ": " [r;o;neg;p;a;s]