Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.CharFilter

153
154
155
156
157
158
159
160
161
162
163
    assertCharFilterEquals(filter, "時々、おおのさんと一緒にお寿司が食べたいです。abcところどころ。");
  }

  public void testNone() throws IOException {
    // Test no repetition marks
    CharFilter filter = new JapaneseIterationMarkCharFilter(
        new StringReader("時々、おゝのさんと一緒にお寿司が食べたいです。abcところゞゝゝ。"),
        false, // no kanji
        false  // no kana
    );
    assertCharFilterEquals(filter, "時々、おゝのさんと一緒にお寿司が食べたいです。abcところゞゝゝ。");
View Full Code Here
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
      throw new UnsupportedOperationException("read(char[], int, int)");
    }
  };
 
  public void testWrapping() throws Exception {
    CharFilter cs = new TestRandomChains.CheckThatYouDidntReadAnythingReaderWrapper(wrappedStream);
    try {
      cs.mark(1);
      fail();
    } catch (Exception e) {
      assertEquals("mark(int)", e.getMessage());
    }
   
    try {
      cs.markSupported();
      fail();
    } catch (Exception e) {
      assertEquals("markSupported()", e.getMessage());
    }
   
    try {
      cs.read();
      fail();
    } catch (Exception e) {
      assertEquals("read()", e.getMessage());
    }
   
    try {
      cs.read(new char[0]);
      fail();
    } catch (Exception e) {
      assertEquals("read(char[])", e.getMessage());
    }
   
    try {
      cs.read(CharBuffer.wrap(new char[0]));
      fail();
    } catch (Exception e) {
      assertEquals("read(CharBuffer)", e.getMessage());
    }
   
    try {
      cs.reset();
      fail();
    } catch (Exception e) {
      assertEquals("reset()", e.getMessage());
    }
   
    try {
      cs.skip(1);
      fail();
    } catch (Exception e) {
      assertEquals("skip(long)", e.getMessage());
    }
   
    try {
      cs.correctOffset(1);
      fail();
    } catch (Exception e) {
      assertEquals("correct(int)", e.getMessage());
    }
   
    try {
      cs.close();
      fail();
    } catch (Exception e) {
      assertEquals("close()", e.getMessage());
    }
   
    try {
      cs.read(new char[0], 0, 0);
      fail();
    } catch (Exception e) {
      assertEquals("read(char[], int, int)", e.getMessage());
    }
  }
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
    List<String> mappingRules = new ArrayList<String>();
    mappingRules.add( "\"&uuml;\" => \"ü\"" );
    NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
    builder.add("&uuml;", "ü");
    NormalizeCharMap normMap = builder.build();
    CharFilter charStream = new MappingCharFilter( normMap, new StringReader( INPUT ) );

    // create PatternTokenizer
    TokenStream stream = new PatternTokenizer(charStream, Pattern.compile("[,;/\\s]+"), -1);
    assertTokenStreamContents(stream,
        new String[] { "Günther", "Günther", "is", "here" },
View Full Code Here
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
      throw new UnsupportedOperationException("read(char[], int, int)");
    }
  };
 
  public void testWrapping() throws Exception {
    CharFilter cs = new TestRandomChains.CheckThatYouDidntReadAnythingReaderWrapper(wrappedStream);
    try {
      cs.mark(1);
      fail();
    } catch (Exception e) {
      assertEquals("mark(int)", e.getMessage());
    }
   
    try {
      cs.markSupported();
      fail();
    } catch (Exception e) {
      assertEquals("markSupported()", e.getMessage());
    }
   
    try {
      cs.read();
      fail();
    } catch (Exception e) {
      assertEquals("read()", e.getMessage());
    }
   
    try {
      cs.read(new char[0]);
      fail();
    } catch (Exception e) {
      assertEquals("read(char[])", e.getMessage());
    }
   
    try {
      cs.read(CharBuffer.wrap(new char[0]));
      fail();
    } catch (Exception e) {
      assertEquals("read(CharBuffer)", e.getMessage());
    }
   
    try {
      cs.reset();
      fail();
    } catch (Exception e) {
      assertEquals("reset()", e.getMessage());
    }
   
    try {
      cs.skip(1);
      fail();
    } catch (Exception e) {
      assertEquals("skip(long)", e.getMessage());
    }
   
    try {
      cs.correctOffset(1);
      fail();
    } catch (Exception e) {
      assertEquals("correct(int)", e.getMessage());
    }
   
    try {
      cs.close();
      fail();
    } catch (Exception e) {
      assertEquals("close()", e.getMessage());
    }
   
    try {
      cs.read(new char[0], 0, 0);
      fail();
    } catch (Exception e) {
      assertEquals("read(char[], int, int)", e.getMessage());
    }
  }
View Full Code Here
34
35
36
37
38
39
40
41
42
public class TestJapaneseIterationMarkCharFilterFactory extends BaseTokenStreamTestCase {

  public void testIterationMarksWithKeywordTokenizer() throws IOException {
    final String text = "時々馬鹿々々しいところゞゝゝミスヾ";
    JapaneseIterationMarkCharFilterFactory filterFactory = new JapaneseIterationMarkCharFilterFactory();
    CharFilter filter = filterFactory.create(new StringReader(text));
    TokenStream tokenStream = new MockTokenizer(filter, MockTokenizer.KEYWORD, false);
    assertTokenStreamContents(tokenStream, new String[]{"時時馬鹿馬鹿しいところどころミスズ"});
  }
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
    JapaneseIterationMarkCharFilterFactory filterFactory = new JapaneseIterationMarkCharFilterFactory();
    Map<String, String> filterArgs = Collections.emptyMap();
    filterFactory.init(filterArgs);

    CharFilter filter = filterFactory.create(
        new StringReader("時々馬鹿々々しいところゞゝゝミスヾ")
    );
    TokenStream tokenStream = tokenizerFactory.create(filter);
    assertTokenStreamContents(tokenStream, new String[]{"時時", "馬鹿馬鹿しい", "ところどころ", "ミ", "スズ"});
  }
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
    Map<String, String> filterArgs = new HashMap<String, String>();
    filterArgs.put("normalizeKanji", "true");
    filterArgs.put("normalizeKana", "false");
    filterFactory.init(filterArgs);
   
    CharFilter filter = filterFactory.create(
        new StringReader("時々馬鹿々々しいところゞゝゝミスヾ")
    );
    TokenStream tokenStream = tokenizerFactory.create(filter);
    assertTokenStreamContents(tokenStream, new String[]{"時時", "馬鹿馬鹿しい", "ところ", "ゞ", "ゝ", "ゝ", "ミス", "ヾ"});
  }
View Full Code Here
87
88
89
90
91
92
93
94
95
96
97
    Map<String, String> filterArgs = new HashMap<String, String>();
    filterArgs.put("normalizeKanji", "false");
    filterArgs.put("normalizeKana", "true");
    filterFactory.init(filterArgs);

    CharFilter filter = filterFactory.create(
        new StringReader("時々馬鹿々々しいところゞゝゝミスヾ")
    );
    TokenStream tokenStream = tokenizerFactory.create(filter);
    assertTokenStreamContents(tokenStream, new String[]{"時々", "馬鹿", "々", "々", "しい", "ところどころ", "ミ", "スズ"});
  }
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
    List<String> mappingRules = new ArrayList<String>();
    mappingRules.add( "\"&uuml;\" => \"ü\"" );
    NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
    builder.add("&uuml;", "ü");
    NormalizeCharMap normMap = builder.build();
    CharFilter charStream = new MappingCharFilter( normMap, new StringReader( INPUT ) );

    // create PatternTokenizer
    TokenStream stream = new PatternTokenizer(charStream, Pattern.compile("[,;/\\s]+"), -1);
    assertTokenStreamContents(stream,
        new String[] { "Günther", "Günther", "is", "here" },
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
  public void testNormalization() throws IOException {
    String input = "ʰ㌰゙5℃№㈱㌘，バッファーの正規化のテスト．㋐㋑㋒㋓㋔ｶｷｸｹｺｻﾞｼﾞｽﾞｾﾞｿﾞg̈각/각நிเกषिchkʷक्षि";
    Normalizer2 normalizer = Normalizer2.getInstance(null, "nfkc_cf", Normalizer2.Mode.COMPOSE);
    String expectedOutput = normalizer.normalize(input);

    CharFilter reader = new ICUNormalizer2CharFilter(new StringReader(input), normalizer);
    char[] tempBuff = new char[10];
    StringBuilder output = new StringBuilder();
    while (true) {
      int length = reader.read(tempBuff);
      if (length == -1) {
        break;
      }
      output.append(tempBuff, 0, length);
      assertEquals(output.toString(), normalizer.normalize(input.substring(0, reader.correctOffset(output.length()))));
    }

    assertEquals(expectedOutput, output.toString());
  }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.CharFilter

  • org.apache.lucene.analysis.charfilter.TestMappingCharFilter
  • org.apache.lucene.analysis.core.TestBugInSomething
  • org.apache.lucene.analysis.icu.TestICUNormalizer2CharFilter
  • org.apache.lucene.analysis.ja.TestJapaneseIterationMarkCharFilter
  • org.apache.lucene.analysis.ja.TestJapaneseIterationMarkCharFilterFactory
  • org.apache.lucene.analysis.pattern.TestPatternReplaceCharFilter
  • org.apache.lucene.analysis.pattern.TestPatternTokenizer
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.