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
|
/* 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.io.IOException;
import java.lang.reflect.InvocationTargetException;
import java.lang.reflect.Method;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Iterator;
import java.util.List;
import java.util.Locale;
import java.util.ResourceBundle;
import junit.framework.Assert;
import de.danielnaber.languagetool.tagging.Tagger;
import de.danielnaber.languagetool.tagging.disambiguation.Disambiguator;
import de.danielnaber.languagetool.tokenizers.SentenceTokenizer;
import de.danielnaber.languagetool.tokenizers.Tokenizer;
import de.danielnaber.languagetool.tools.StringTools;
/**
* @author Daniel Naber
*/
public final class TestTools {
private TestTools() {
}
public static ResourceBundle getEnglishMessages() {
return getMessages("en");
}
/**
* Gets the resource bundle for the specified language.
* @param language lowercase two-letter ISO-639 code.
* @return the resource bundle for the specified language.
*/
public static ResourceBundle getMessages(String language) {
final ResourceBundle messages = ResourceBundle.getBundle(
"de.danielnaber.languagetool.MessagesBundle", new Locale(language));
return messages;
}
public static void testSplit(final String[] sentences,
final SentenceTokenizer stokenizer) {
final StringBuilder inputString = new StringBuilder();
final List<String> input = new ArrayList<String>();
for (final String sentence : sentences) {
input.add(sentence);
}
for (final String string : input) {
inputString.append(string);
}
Assert.assertEquals(input, stokenizer.tokenize(inputString.toString()));
}
public static void myAssert(final String input, final String expected,
final Tokenizer tokenizer, final Tagger tagger) throws IOException {
final List<String> tokens = tokenizer.tokenize(input);
final List<String> noWhitespaceTokens = new ArrayList<String>();
// whitespace confuses tagger, so give it the tokens but no whitespace
// tokens:
for (final String token : tokens) {
if (isWord(token)) {
noWhitespaceTokens.add(token);
}
}
final List<AnalyzedTokenReadings> output = tagger.tag(noWhitespaceTokens);
final StringBuffer outputStr = new StringBuffer();
for (final Iterator<AnalyzedTokenReadings> iter = output.iterator(); iter
.hasNext();) {
final AnalyzedTokenReadings token = iter.next();
final int readingsNumber = token.getReadingsLength();
final List<String> readings = new ArrayList<String>();
for (int j = 0; j < readingsNumber; j++) {
final StringBuffer readingStr = new StringBuffer();
readingStr.append(token.getAnalyzedToken(j).getToken());
readingStr.append("/[");
readingStr.append(token.getAnalyzedToken(j).getLemma());
readingStr.append(']');
readingStr.append(token.getAnalyzedToken(j).getPOSTag());
readings.add(readingStr.toString());
}
// force some order on the result just for the test case - order may vary
// from one version of the lexicon to the next:
Collections.sort(readings);
outputStr.append(StringTools.listToString(readings, "|"));
if (iter.hasNext()) {
outputStr.append(" -- ");
}
}
Assert.assertEquals(expected, outputStr.toString());
}
public static void myAssert(final String input, final String expected,
final Tokenizer tokenizer, final SentenceTokenizer sentenceTokenizer,
final Tagger tagger, final Disambiguator disambiguator)
throws IOException {
final StringBuffer outputStr = new StringBuffer();
final List<String> sentences = sentenceTokenizer.tokenize(input);
for (final String sentence : sentences) {
final List<String> tokens = tokenizer.tokenize(sentence);
final List<String> noWhitespaceTokens = new ArrayList<String>();
// whitespace confuses tagger, so give it the tokens but no whitespace
// tokens:
for (final String token : tokens) {
if (isWord(token)) {
noWhitespaceTokens.add(token);
}
}
final List<AnalyzedTokenReadings> aTokens = tagger
.tag(noWhitespaceTokens);
final AnalyzedTokenReadings[] tokenArray = new AnalyzedTokenReadings[tokens
.size() + 1];
final AnalyzedToken[] startTokenArray = new AnalyzedToken[1];
int toArrayCount = 0;
final AnalyzedToken sentenceStartToken = new AnalyzedToken("",
"SENT_START", null);
startTokenArray[0] = sentenceStartToken;
tokenArray[toArrayCount++] = new AnalyzedTokenReadings(startTokenArray, 0);
int startPos = 0;
int noWhitespaceCount = 0;
for (final String tokenStr : tokens) {
AnalyzedTokenReadings posTag = null;
if (isWord(tokenStr)) {
posTag = aTokens.get(noWhitespaceCount);
posTag.setStartPos(startPos);
noWhitespaceCount++;
} else {
posTag = tagger.createNullToken(tokenStr, startPos);
}
tokenArray[toArrayCount++] = posTag;
startPos += tokenStr.length();
}
AnalyzedSentence finalSentence = new AnalyzedSentence(tokenArray);
// disambiguate assigned tags
finalSentence = disambiguator.disambiguate(finalSentence);
final AnalyzedTokenReadings[] output = finalSentence.getTokens();
for (int i = 0; i < output.length; i++) {
final AnalyzedTokenReadings token = output[i];
final int readingsNumber = token.getReadingsLength();
final List<String> readings = new ArrayList<String>();
for (int j = 0; j < readingsNumber; j++) {
final StringBuffer readingStr = new StringBuffer();
readingStr.append(token.getAnalyzedToken(j).getToken());
readingStr.append("/[");
readingStr.append(token.getAnalyzedToken(j).getLemma());
readingStr.append(']');
readingStr.append(token.getAnalyzedToken(j).getPOSTag());
readings.add(readingStr.toString());
}
// force some order on the result just for the test case - order may vary
// from one version of the lexicon to the next:
Collections.sort(readings);
outputStr.append(StringTools.listToString(readings, "|"));
if (i < output.length - 1) {
outputStr.append(' ');
}
}
}
Assert.assertEquals(expected, outputStr.toString());
}
public static boolean isWord(final String token) {
for (int i = 0; i < token.length(); i++) {
final char c = token.charAt(i);
if (Character.isLetter(c) || Character.isDigit(c)) {
return true;
}
}
return false;
}
/**
* Used to call private methods for testing
*
* @param targetClass
* Class under test
* @param methodName
* Name of the method under test
* @param argClasses
* Types of arguments
* @param argObjects
* Values of arguments
* @throws InvocationTargetException
* @throws IllegalAccessException
* @throws IllegalArgumentException
* @throws NoSuchMethodException
* @throws SecurityException
*/
public static void callStaticMethod(final Class targetClass,
final String methodName, final Class[] argClasses,
final Object[] argObjects) throws InvocationTargetException,
IllegalArgumentException, IllegalAccessException, SecurityException,
NoSuchMethodException {
final Method method = targetClass.getDeclaredMethod(methodName, argClasses);
method.setAccessible(true);
method.invoke(null, argObjects);
}
public static String callStringStaticMethod(final Class targetClass,
final String methodName, final Class[] argClasses,
final Object[] argObjects) throws InvocationTargetException,
IllegalArgumentException, IllegalAccessException, SecurityException,
NoSuchMethodException {
final Method method = targetClass.getDeclaredMethod(methodName, argClasses);
method.setAccessible(true);
return (String) method.invoke(null, argObjects);
}
}
|
