test.ml
5.24 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
(*
* ENIAMmorphology, a morphological analyser and a guesser 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 library is free software: you can redistribute it and/or modify
* it under the terms of the GNU Lesser General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This library 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 Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*)
let test_strings = [
"Ale";
"ale";
"miał";
"kota";
"Kot";
"Szpak";
"sepulkujemy";
"najsepulkowniejszy";
]
let string_of_token (lemma,interp,quantity,attrs) =
Printf.sprintf "%s\t%s\t%d\t%s" lemma interp quantity (String.concat ", " attrs)
(*let _ =
ENIAMinflexion.initialize ();
print_endline "Testy wbudowane";
Xlist.iter test_strings (fun s ->
print_endline ("\nTEST: " ^ s);
let tokens = ENIAMinflexion.get_interpretations s in
(* print_endline (ENIAMtokenizer.xml_of tokens); *)
Xlist.iter tokens (fun token -> print_endline (string_of_token token)));
print_endline "Testy użytkownika.";
print_endline "Wpisz tekst i naciśnij ENTER, pusty tekst kończy.";
let s = ref (read_line ()) in
while !s <> "" do
let tokens = ENIAMinflexion.get_interpretations !s in
(* print_endline (ENIAMtokenizer.xml_of tokens); *)
Xlist.iter tokens (fun token -> print_endline (string_of_token token));
print_endline "Wpisz tekst i naciśnij ENTER, pusty tekst kończy.";
s := read_line ()
done;
()*)
open ENIAMmorphologyTypes
let test_strings2 = [
(* "być","praet:_:_:_",[],[];
"być","fin:_:_:_",[],[];
"być","ppas:_:_:_:_:_",[],[];
"być","pant:_",[],[];
"mieć","ger:_:_:_:_:_",[],[];
"mieć","pant:_",[],[];
"kot","subst:_:_:_",[],[];
"kość","subst:_:_:_",[],[];
"kość","subst:_:_:f",[],[];
"zielony","adj:_:_:_:_",[],[];
"zielony","adj:sg:gen:m1:_",[],[];
"wesoły","adj:_:_:_:_",[],[];
"mało","adv:_",[],[];
"ślisko","adv:_",[],[];
"cienko","adv:_",[],[];
"pracować","praet:_:_:_",[],[];
"pracować","fin:_:_:_",[],[];
"pracować","ppas:_:_:_:_:neg",[],[Dial];
"przepracować","ppas:_:_:_:_:_",[],[];
"Leśniowski","subst:_:_:m1",[],[Acro;Aux;Aux2;Ndm];*)
(* "Richelieu","subst:_:_:_",[],[];
"VAT","subst:_:_:_",[],[];*)
"NFZ","subst:_:_:_",[Acro],[]; (* FIXME: Zot *)
(* "paść","praet:_:_:_",[],[];
"paść:v1","praet:_:_:_",[],[];
"paść:v2","praet:_:_:_",[],[];
"Jacques","subst:_:_:m1",[],[];
"Tacques","subst:_:_:m1",[Aux;Aux2],[Dial;Ndm];*)
"Cauchy","subst:_:_:m1",[],[]; (* FIXME *)
(* "blablarować","fin:_:_:_",[],[Dial];
"blablarzyć","fin:_:_:_",[],[Dial];
"blablarzeć","fin:_:_:_",[],[Dial];
"blablarzuć","fin:_:_:_",[],[];
"blablarzać","fin:_:_:_",[],[Dial];
"blablarzić","fin:_:_:_",[],[Dial];
"blablarzoć","fin:_:_:_",[],[];*)
(* "elemelenikt","subst:_:_:m1",[],[Acro;Aux;Aux2;Ndm;Dial];
"elemelenikt","subst:_:_:m2",[],[Acro;Aux;Aux2;Ndm;Dial];
"elemelenikt","subst:_:_:m3",[],[Acro;Aux;Aux2;Ndm;Dial];
"elemelenikt","subst:_:_:f",[],[Acro;Aux;Aux2;Ndm;Dial];
"xligand","subst:sg:gen:_",[],[Acro;Aux;Aux2;Ndm;Dial];
"pupcia","subst:_:_:m1",[],[Acro;Aux;Aux2;Ndm;Dial];
"dupa","subst:_:_:m1",[],[Acro;Aux;Aux2;Ndm;Dial];*)
"pipipipi","adj:_:_:_:pos",[],[]; (* FIXME: pojawia się j *)
"ddddana","subst:_:_:f",[],[Acro;Aux;Aux2;Ndm;Dial]; (* FIXME: aen *)
"lamiwudyna","",[],[Acro;Aux;Aux2;Ndm;Dial];
"lamiwudyna","subst:_:_:_",[],[Acro;Aux;Aux2;Ndm;Dial];
"lamiwudyna","subst:_:_:f",[],[Acro;Aux;Aux2;Ndm;Dial];
]
let _ =
ENIAMinflexion.initialize ();
print_endline "Testy wbudowane";
Xlist.iter test_strings2 (fun (lemma,interp,feat,excl) ->
print_endline ("\nTEST: " ^ lemma ^ " " ^ interp ^
" [" ^ String.concat ";" (Xlist.map feat ENIAMmorphologyRules.string_of_star) ^ "] [" ^
String.concat ";" (Xlist.map excl ENIAMmorphologyRules.string_of_star) ^ "]");
let result = ENIAMinflexion.disambiguate feat excl (ENIAMinflexion.synthetize lemma interp) in
(* print_endline (ENIAMtokenizer.xml_of tokens); *)
print_endline (ENIAMinflexion.string_of_interpretations result ^ "\n\n"));
(* print_endline "Testy użytkownika.";
print_endline "Wpisz tekst i naciśnij ENTER, pusty tekst kończy.";
let s = ref (read_line ()) in
while !s <> "" do
let tokens = ENIAMinflexion.get_interpretations !s in
(* print_endline (ENIAMtokenizer.xml_of tokens); *)
Xlist.iter tokens (fun token -> print_endline (string_of_token token));
print_endline "Wpisz tekst i naciśnij ENTER, pusty tekst kończy.";
s := read_line ()
done;*)
()
(*
zieloni i zieleni - obie poprawne
wesoli i weseli - jedna poprawna
Jacques - poprawnie lematyzowany
Tacques - z treści lematu nie wynika, że słowo ma obcą ortografie (i którą obcą ortografię), trzeba dostarczyć dodatkowych informacji
*)