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
|
/* LanguageTool, a natural language style checker
* Copyright (C) 2008 Daniel Naber (http://www.danielnaber.de)
*
* 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 2.1 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 library; if not, write to the Free Software
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301
* USA
*/
package de.danielnaber.languagetool.rules.patterns;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import de.danielnaber.languagetool.AnalyzedSentence;
import de.danielnaber.languagetool.AnalyzedToken;
import de.danielnaber.languagetool.AnalyzedTokenReadings;
import de.danielnaber.languagetool.Language;
import de.danielnaber.languagetool.rules.Rule;
import de.danielnaber.languagetool.rules.RuleMatch;
/**
* An Abstract Pattern Rule that describes a pattern of words or part-of-speech tags
* used for PatternRule and DisambiguationPatternRule.
*
* Introduced to minimize code duplication between those classes.
*
* @author Marcin Miłkowski
*/
public abstract class AbstractPatternRule extends Rule {
private final String id;
private final String description;
protected final List<Element> patternElements;
protected Unifier unifier;
protected final Language language;
protected int startPositionCorrection;
protected int endPositionCorrection;
protected boolean prevMatched;
protected final boolean testUnification;
private final boolean getUnified;
private boolean groupsOrUnification;
protected AnalyzedTokenReadings[] unifiedTokens;
protected final boolean sentStart;
public AbstractPatternRule(final String id,
final String description,
final Language language,
final List<Element> elements,
boolean getUnified) {
this.id = id;
this.description = description;
this.patternElements = new ArrayList<Element>(elements); // copy elements
this.language = language;
this.getUnified = getUnified;
unifier = language.getUnifier();
testUnification = initUnifier();
sentStart = patternElements.get(0).isSentStart();
if (!testUnification) {
for (Element elem : patternElements) {
if (elem.hasAndGroup()) {
groupsOrUnification = true;
break;
}
}
} else {
groupsOrUnification = true;
}
}
private boolean initUnifier() {
for (final Element elem : patternElements) {
if (elem.isUnified()) {
return true;
}
}
return false;
}
@Override
public final String toString() {
return id + ":" + patternElements + ":" + description;
}
@Override
public String getDescription() {
return description;
}
@Override
public String getId() {
return id;
}
@Override
public RuleMatch[] match(AnalyzedSentence text) throws IOException {
// TODO Auto-generated method stub
return null;
}
@Override
public void reset() {
// TODO Auto-generated method stub
}
public final void setStartPositionCorrection(final int startPositionCorrection) {
this.startPositionCorrection = startPositionCorrection;
}
public final void setEndPositionCorrection(final int endPositionCorrection) {
this.endPositionCorrection = endPositionCorrection;
}
protected void setupAndGroup(final int firstMatchToken,
final Element elem, final AnalyzedTokenReadings[] tokens)
throws IOException {
if (elem.hasAndGroup()) {
for (final Element andElement : elem.getAndGroup()) {
if (andElement.isReferenceElement()) {
setupRef(firstMatchToken, andElement, tokens);
}
}
elem.setupAndGroup();
}
}
//TODO: add .compile for all exceptions of the element?
protected void setupRef(final int firstMatchToken, final Element elem,
final AnalyzedTokenReadings[] tokens) throws IOException {
if (elem.isReferenceElement()) {
final int refPos = firstMatchToken + elem.getMatch().getTokenRef();
if (refPos < tokens.length) {
elem.compile(tokens[refPos], language.getSynthesizer());
}
}
}
protected boolean testAllReadings(final AnalyzedTokenReadings[] tokens,
final Element elem, final Element prevElement, final int tokenNo,
final int firstMatchToken, final int prevSkipNext) throws IOException {
boolean thisMatched = false;
final int numberOfReadings = tokens[tokenNo].getReadingsLength();
setupAndGroup(firstMatchToken, elem, tokens);
for (int l = 0; l < numberOfReadings; l++) {
final AnalyzedToken matchToken = tokens[tokenNo].getAnalyzedToken(l);
prevMatched = prevMatched || prevSkipNext > 0 && prevElement != null
&& prevElement.isMatchedByScopeNextException(matchToken);
if (prevMatched) {
return false;
}
thisMatched = thisMatched || elem.isMatched(matchToken);
if (!thisMatched && !elem.isInflected() && elem.getPOStag() == null
&& (prevElement != null && prevElement.getExceptionList() == null)) {
return false; // the token is the same, we will not get a match
}
if (groupsOrUnification) {
thisMatched &= testUnificationAndGroups(thisMatched,
l + 1 == numberOfReadings, matchToken, elem);
}
}
if (thisMatched) {
for (int l = 0; l < numberOfReadings; l++) {
if (elem.isExceptionMatchedCompletely(tokens[tokenNo].getAnalyzedToken(l)))
return false;
}
if (tokenNo > 0 && elem.hasPreviousException()) {
if (elem.isMatchedByPreviousException(tokens[tokenNo - 1]))
return false;
}
}
return thisMatched;
}
protected boolean testUnificationAndGroups(final boolean matched,
final boolean lastReading, final AnalyzedToken matchToken,
final Element elem) {
boolean thisMatched = matched;
if (testUnification) {
if (matched && elem.isUnified()) {
thisMatched = thisMatched && unifier.isUnified(matchToken, elem.getUniFeatures(),
elem.isUniNegated(), lastReading);
}
if (thisMatched && getUnified) {
unifiedTokens = unifier.getFinalUnified();
}
if (!elem.isUnified()) {
unifier.reset();
}
}
elem.addMemberAndGroup(matchToken);
if (lastReading) {
thisMatched &= elem.checkAndGroup(thisMatched);
}
return thisMatched;
}
}
|
