ENIAMsubsyntaxStringOf.ml
3.74 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
(*
* ENIAMsubsyntax: MWE, abbreviation and sentence detecion 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/>.
*)
open ENIAMsubsyntaxTypes
open Printf
let mode = function
Raw -> "Raw"
| Struct -> "Struct"
| CONLL -> "CONLL"
| ENIAM -> "ENIAM"
| Mate -> "Mate"
| Swigra -> "Swigra"
| POLFIE -> "POLFIE"
let token_extarray t =
String.concat "\n" (List.rev (Int.fold 0 (ExtArray.size t - 1) [] (fun l id ->
let t2 = ExtArray.get t id in
(Printf.sprintf "%3d %s" id (ENIAMtokens.string_of_token_env t2)) :: l)))
let token_list paths (*last*) =
String.concat "\n" (Xlist.map paths (fun t -> ENIAMtokens.string_of_token_env t))
(* ^ (if last < 0 then "" else Printf.sprintf "\nlast=%d" last) *)
let struct_sentence spaces t paths last =
spaces ^ " id lnode rnode orth token\n" ^
String.concat "\n" (Xlist.map (List.sort compare paths) (fun (id,lnode,rnode) ->
let t2 = ExtArray.get t id in
sprintf "%s%3d %5d %5d %s %s" spaces
id lnode rnode t2.ENIAMtokenizerTypes.orth (ENIAMtokens.string_of_token t2.ENIAMtokenizerTypes.token))) ^
sprintf "\n%s last=%d" spaces last
let dep_sentence spaces t paths =
spaces ^ " id conll_id super label orth token \n" ^
String.concat "\n" (List.rev (Int.fold 0 (Array.length paths - 1) [] (fun l conll_id ->
let id,super,label = paths.(conll_id) in
let t2 = ExtArray.get t id in
(sprintf "%s%3d %8d %5d %s %s %s" spaces
id conll_id super label t2.ENIAMtokenizerTypes.orth (ENIAMtokens.string_of_token t2.ENIAMtokenizerTypes.token)) :: l)))
let rec sentence spaces t = function
RawSentence s -> spaces ^ "RawSentence: " ^ s
| StructSentence(paths,last) -> spaces ^ "StructSentence:\n" ^ struct_sentence " " t paths last
| DepSentence paths -> spaces ^ "DepSentence:\n" ^ dep_sentence " " t paths
| QuotedSentences sentences ->
spaces ^ "QuotedSentences:\n" ^ String.concat "\n" (Xlist.map sentences (fun p ->
sprintf " id=%s beg=%d len=%d next=%d\n%s" p.id p.beg p.len p.next (sentence " " t p.sentence)))
| AltSentence l ->
String.concat "\n" (Xlist.map l (fun (m,s) ->
sprintf "%sAltSentence mode=%s %s" spaces (mode m) (sentence "" t s)))
let rec paragraph spaces t = function
RawParagraph s -> spaces ^ "RawParagraph: " ^ s
| StructParagraph sentences ->
spaces ^ "StructParagraph:\n" ^ String.concat "\n" (Xlist.map sentences (fun p ->
sprintf " id=%s beg=%d len=%d next=%d\n%s" p.id p.beg p.len p.next (sentence " " t p.sentence)))
| AltParagraph l ->
String.concat "\n" (Xlist.map l (fun (m,p) ->
sprintf "%sAltParagraph mode=%s %s" spaces (mode m) (paragraph "" t p)))
let rec text spaces t = function
RawText s -> spaces ^ "RawText: " ^ s
| StructText paragraphs ->
spaces ^ "StructText:\n" ^ String.concat "\n" (Xlist.map paragraphs (paragraph " " t))
| AltText l ->
String.concat "\n" (Xlist.map l (fun (m,te) ->
sprintf "%sAltText mode=%s %s" spaces (mode m) (text "" t te)))