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
|
/* LanguageTool, a natural language style checker
* Copyright (C) 2005 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;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import de.danielnaber.languagetool.tagging.de.AnalyzedGermanTokenReadings;
/**
* A sentence that has been tokenized and analyzed.
*
* @author Daniel Naber
*/
public class AnalyzedSentence {
@Override
public int hashCode() {
final int prime = 31;
int result = 1;
result = prime * result + Arrays.hashCode(nonBlankTokens);
result = prime * result + Arrays.hashCode(tokens);
result = prime * result + Arrays.hashCode(whPositions);
return result;
}
@Override
public boolean equals(Object obj) {
if (this == obj)
return true;
if (obj == null)
return false;
if (getClass() != obj.getClass())
return false;
final AnalyzedSentence other = (AnalyzedSentence) obj;
if (!Arrays.equals(nonBlankTokens, other.nonBlankTokens))
return false;
if (!Arrays.equals(tokens, other.tokens))
return false;
if (!Arrays.equals(whPositions, other.whPositions))
return false;
return true;
}
private AnalyzedTokenReadings[] tokens;
private AnalyzedTokenReadings[] nonBlankTokens;
/**
* Array mapping positions of tokens as returned with
* getTokensWithoutWhitespace() to the internal tokens array.
*/
private int[] whPositions;
/**
* Sets {@link AnalyzedTokenReadings}. Whitespace is also a token.
*/
public AnalyzedSentence(final AnalyzedTokenReadings[] tokens) {
this.tokens = tokens;
}
public AnalyzedSentence(final AnalyzedTokenReadings[] tokens, final
int[] whPositions) {
this.tokens = tokens;
this.setWhPositions(whPositions);
getTokensWithoutWhitespace();
}
/**
* Returns the {@link AnalyzedTokenReadings} of the analyzed text. Whitespace
* is also a token.
*/
public final AnalyzedTokenReadings[] getTokens() {
return tokens;
}
/**
* Returns the {@link AnalyzedTokenReadings} of the analyzed text, with
* whitespace tokens removed but with the artificial <code>SENT_START</code>
* token included.
*/
public final AnalyzedTokenReadings[] getTokensWithoutWhitespace() {
if (nonBlankTokens == null) {
int whCounter = 0;
int nonWhCounter = 0;
final int[] mapping = new int[tokens.length + 1];
final List<AnalyzedTokenReadings> l = new ArrayList<AnalyzedTokenReadings>();
for (final AnalyzedTokenReadings token : tokens) {
if (!token.isWhitespace() || token.isSentStart() || token.isSentEnd()
|| token.isParaEnd()) {
l.add(token);
mapping[nonWhCounter] = whCounter;
nonWhCounter++;
}
whCounter++;
}
setNonBlankTokens(l.toArray(new AnalyzedTokenReadings[l.size()]));
setWhPositions(mapping.clone());
}
return nonBlankTokens.clone();
}
/**
* Get a position of a non-whitespace token in the original sentence with
* whitespace.
*
* @param nonWhPosition
* Position of a non-whitespace token
* @return int position in the original sentence.
*/
public final int getOriginalPosition(final int nonWhPosition) {
if (nonBlankTokens == null) {
getTokensWithoutWhitespace();
}
return getWhPositions()[nonWhPosition];
}
@Override
public final String toString() {
final StringBuilder sb = new StringBuilder();
for (final AnalyzedTokenReadings element : tokens) {
if (!element.isWhitespace()) {
sb.append(element.getToken());
sb.append('[');
}
for (int j = 0; j < element.getReadingsLength(); j++) {
final String posTag = element.getAnalyzedToken(j).getPOSTag();
if (element.isSentStart()) {
sb.append("<S>");
} else if (JLanguageTool.SENTENCE_END_TAGNAME.equals(element
.getAnalyzedToken(j).getPOSTag())) {
sb.append("</S>");
} else if (JLanguageTool.PARAGRAPH_END_TAGNAME.equals(element
.getAnalyzedToken(j).getPOSTag())) {
sb.append("<P/>");
} else if (element.getAnalyzedToken(j) != null && posTag == null
&& !(element instanceof AnalyzedGermanTokenReadings)) {
// FIXME: don't depend on AnalyzedGermanTokenReadings here
sb.append(element.getAnalyzedToken(j).getToken());
} else {
if (!element.isWhitespace()) {
sb.append(element.getAnalyzedToken(j));
if (j < element.getReadingsLength() - 1) {
sb.append(',');
}
}
}
}
if (!element.isWhitespace()) {
sb.append(']');
} else {
sb.append(' ');
}
}
return sb.toString();
}
/**
* @param whPositions the whPositions to set
*/
public void setWhPositions(int[] whPositions) {
this.whPositions = whPositions;
}
/**
* @return the whPositions
*/
public int[] getWhPositions() {
return whPositions;
}
/**
* @param nonBlankTokens the nonBlankTokens to set
*/
public void setNonBlankTokens(AnalyzedTokenReadings[] nonBlankTokens) {
this.nonBlankTokens = nonBlankTokens;
}
}
|
