Package org.apache.lucene.analysis.tokenattributes

Examples of org.apache.lucene.analysis.tokenattributes.CharTermAttribute

128
129
130
131
132
133
134
135
136
137
138
139
      //make sure we produce the same tokens
      TeeSinkTokenFilter teeStream = new TeeSinkTokenFilter(new StandardFilter(new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.toString()))));
      TokenStream sink = teeStream.newSinkTokenStream(new ModuloSinkFilter(100));
      teeStream.consumeAllTokens();
      TokenStream stream = new ModuloTokenFilter(new StandardFilter(new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(buffer.toString()))), 100);
      CharTermAttribute tfTok = stream.addAttribute(CharTermAttribute.class);
      CharTermAttribute sinkTok = sink.addAttribute(CharTermAttribute.class);
      for (int i=0; stream.incrementToken(); i++) {
        assertTrue(sink.incrementToken());
        assertTrue(tfTok + " is not equal to " + sinkTok + " at token: " + i, tfTok.equals(sinkTok) == true);
      }
     
View Full Code Here
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
    // and ensure they are the same as the ones we produced in serial fashion.

    for (int i = 0; i < numTestPoints; i++) {
      String term = _TestUtil.randomSimpleString(random);
      TokenStream ts = analyzer.reusableTokenStream("fake", new StringReader(term));
      CharTermAttribute encodedBytes = ts.addAttribute(CharTermAttribute.class);
      ts.reset();
      assertTrue(ts.incrementToken());
      // ensure we make a copy of the actual bytes too
      map.put(term, encodedBytes.toString());
    }
   
    Thread threads[] = new Thread[numThreads];
    for (int i = 0; i < numThreads; i++) {
      threads[i] = new Thread() {
        @Override
        public void run() {
          try {
            for (Map.Entry<String,String> mapping : map.entrySet()) {
              String term = mapping.getKey();
              String expected = mapping.getValue();
              TokenStream ts = analyzer.reusableTokenStream("fake", new StringReader(term));
              CharTermAttribute encodedBytes = ts.addAttribute(CharTermAttribute.class);
              ts.reset();
              assertTrue(ts.incrementToken());
              assertEquals(expected, encodedBytes.toString());
            }
          } catch (IOException e) {
            throw new RuntimeException(e);
          }
        }
View Full Code Here
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
234
235
236
237
238
    throws IOException, InvalidTokenOffsetsException
  {
    ArrayList<TextFragment> docFrags = new ArrayList<TextFragment>();
    StringBuilder newText=new StringBuilder();
   
      CharTermAttribute termAtt = tokenStream.addAttribute(CharTermAttribute.class);
      OffsetAttribute offsetAtt = tokenStream.addAttribute(OffsetAttribute.class);
      tokenStream.addAttribute(PositionIncrementAttribute.class);
      tokenStream.reset();
     
    TextFragment currentFrag =  new TextFragment(newText,newText.length(), docFrags.size());
   
    if (fragmentScorer instanceof QueryScorer) {
      ((QueryScorer) fragmentScorer).setMaxDocCharsToAnalyze(maxDocCharsToAnalyze);
    }
   
    TokenStream newStream = fragmentScorer.init(tokenStream);
    if(newStream != null) {
      tokenStream = newStream;
    }
    fragmentScorer.startFragment(currentFrag);
    docFrags.add(currentFrag);

    FragmentQueue fragQueue = new FragmentQueue(maxNumFragments);

    try
    {

      String tokenText;
      int startOffset;
      int endOffset;
      int lastEndOffset = 0;
      textFragmenter.start(text, tokenStream);

      TokenGroup tokenGroup=new TokenGroup(tokenStream);

      for (boolean next = tokenStream.incrementToken(); next && (offsetAtt.startOffset()< maxDocCharsToAnalyze);
            next = tokenStream.incrementToken())
      {
        if(  (offsetAtt.endOffset()>text.length())
          ||
          (offsetAtt.startOffset()>text.length())
          )           
        {
          throw new InvalidTokenOffsetsException("Token "+ termAtt.toString()
              +" exceeds length of provided text sized "+text.length());
        }
        if((tokenGroup.numTokens>0)&&(tokenGroup.isDistinct()))
        {
          //the current token is distinct from previous tokens -
View Full Code Here
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
        List<String> tokens = new ArrayList<String>();
        TokenStream stream = null;
        try {
            stream = analyzer.tokenStream(FieldNames.FULLTEXT,
                    new StringReader(text));
            CharTermAttribute termAtt = stream
                    .addAttribute(CharTermAttribute.class);
            OffsetAttribute offsetAtt = stream
                    .addAttribute(OffsetAttribute.class);
            // TypeAttribute type = stream.addAttribute(TypeAttribute.class);

            stream.reset();

            int poz = 0;
            boolean hasFulltextToken = false;
            StringBuilder token = new StringBuilder();
            while (stream.incrementToken()) {
                String term = termAtt.toString();
                int start = offsetAtt.startOffset();
                int end = offsetAtt.endOffset();
                if (start > poz) {
                    for (int i = poz; i < start; i++) {
                        for (char c : fulltextTokens) {
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
        displayTokens(analyzer.tokenStream("contents", new StringReader(text)));
    }

    public static void displayTokens(TokenStream stream) throws IOException {

        CharTermAttribute term = stream.addAttribute(CharTermAttribute.class);
        while (stream.incrementToken()) {
            System.out.println("[" + term.toString() + "] ");
        }

    }
View Full Code Here
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
            throws IOException {

        TokenStream stream = analyzer.tokenStream("contents",
                new StringReader(text));

        CharTermAttribute term = stream.addAttribute(CharTermAttribute.class);
        PositionIncrementAttribute posIncr = stream
                .addAttribute(PositionIncrementAttribute.class);

        int position = 0;
        while (stream.incrementToken()) {

            int increment = posIncr.getPositionIncrement();
            if (increment > 0) {
                position = position + increment;
                System.out.println();
                System.out.print(position + ":");
            }

            System.out.print("[" + term.toString() + "] ");

        }
        System.out.println();

    }
View Full Code Here
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
            throws IOException {

        TokenStream stream = analyzer.tokenStream("contents",
                new StringReader(text));

        CharTermAttribute term = stream.addAttribute(CharTermAttribute.class);
        PositionIncrementAttribute posIncr = stream
                .addAttribute(PositionIncrementAttribute.class);
        OffsetAttribute offset = stream.addAttribute(OffsetAttribute.class);
        TypeAttribute type = stream.addAttribute(TypeAttribute.class);
        PayloadAttribute payload = stream.addAttribute(PayloadAttribute.class);

        int position = 0;
        while (stream.incrementToken()) {

            int increment = posIncr.getPositionIncrement();
            if (increment > 0) {
                position = position + increment;
                System.out.println();
                System.out.print(position + ":");
            }

            BytesRef pl = payload.getPayload();

            if (pl != null) {
                System.out.print("[" + term.toString() + ":" + offset.startOffset()
                        + "->" + offset.endOffset() + ":" + type.type() + ":"
                        + new String(pl.bytes) + "] ");

            } else {
                System.out.print("[" + term.toString() + ":" + offset.startOffset()
                        + "->" + offset.endOffset() + ":" + type.type() + "] ");

            }
        }
        System.out.println();
View Full Code Here
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
    config.set("pattern", "\\s+");
    config.set("lowercase", "false");
    CustomPatternAnalyzer a = new CustomPatternAnalyzer(config);
   
    TokenStream tokenStream = a.tokenStream("test", "this is a Text with Whitespaces");
    CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);

    tokenStream.incrementToken();
    String t2 = charTermAttribute.toString();
    tokenStream.incrementToken();
    String t3 = charTermAttribute.toString();
   
    assertEquals("Second Token did not match!", "Text", t2);
    assertEquals("Third Token did not match!", "Whitespaces", t3);
   
  }
View Full Code Here
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
    config.set("pattern", "\\s+");
    config.set("lowercase", "true");
    CustomPatternAnalyzer a = new CustomPatternAnalyzer(config);
   
    TokenStream tokenStream = a.tokenStream("test", "this is a Text with Whitespaces");
    CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);

    tokenStream.incrementToken();
    String t2 = charTermAttribute.toString();
    tokenStream.incrementToken();
    String t3 = charTermAttribute.toString();
   
    assertEquals("Second Token did not match!", "text", t2);
    assertEquals("Third Token did not match!", "whitespaces", t3);
   
  }
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
    GenericConfiguration config = new GenericConfiguration();
    config.set("pattern", "\\s+");
    CustomPatternAnalyzer a = new CustomPatternAnalyzer(config);
   
    TokenStream tokenStream = a.tokenStream("test", "this is a Text with Whitespaces");
    CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);

    tokenStream.incrementToken();
    String t2 = charTermAttribute.toString();
    tokenStream.incrementToken();
    String t3 = charTermAttribute.toString();
   
    assertEquals("Second Token did not match!", "text", t2);
    assertEquals("Third Token did not match!", "whitespaces", t3);
   
  }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.tokenattributes.CharTermAttribute

  • com.chenlb.mmseg4j.analysis.TokenUtils
  • com.code972.elasticsearch.rest.action.RestHebrewAnalyzerCheckWordAction
  • com.digitalpebble.behemoth.mahout.LuceneTokenizerMapper
  • com.gentics.cr.lucene.analysis.CustomPatternAnalyzerTest
  • com.ikanow.infinit.e.api.knowledge.SearchHandler
  • com.livingsocial.hive.udf.Tokenize
  • com.mozilla.grouperfish.lucene.analysis.en.NGramEnglishAnalyzer
  • com.mozilla.grouperfish.pig.eval.text.NGramTokenize
  • com.mozilla.grouperfish.pig.eval.text.Tokenize
  • ivory.core.tokenize.LuceneArabicAnalyzer
    • 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.