Examples of CharTermAttribute

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

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
      }

      // common case fast-path of first token not matching anything
      AttributeSource firstTok = nextTok();
      if (firstTok == null) return false;
      CharTermAttribute termAtt = firstTok.addAttribute(CharTermAttribute.class);
      SlowSynonymMap result = map.submap!=null ? map.submap.get(termAtt.buffer(), 0, termAtt.length()) : null;
      if (result == null) {
        copy(this, firstTok);
        return true;
      }

      // fast-path failed, clone ourselves if needed
      if (firstTok == this)
        firstTok = cloneAttributes();
      // OK, we matched a token, so find the longest match.

      matched = new LinkedList<AttributeSource>();

      result = match(result);

      if (result==null) {
        // no match, simply return the first token read.
        copy(this, firstTok);
        return true;
      }

      // reuse, or create new one each time?
      ArrayList<AttributeSource> generated = new ArrayList<AttributeSource>(result.synonyms.length + matched.size() + 1);

      //
      // there was a match... let's generate the new tokens, merging
      // in the matched tokens (position increments need adjusting)
      //
      AttributeSource lastTok = matched.isEmpty() ? firstTok : matched.getLast();
      boolean includeOrig = result.includeOrig();

      AttributeSource origTok = includeOrig ? firstTok : null;
      PositionIncrementAttribute firstPosIncAtt = firstTok.addAttribute(PositionIncrementAttribute.class);
      int origPos = firstPosIncAtt.getPositionIncrement();  // position of origTok in the original stream
      int repPos=0; // curr position in replacement token stream
      int pos=0;  // current position in merged token stream

      for (int i=0; i<result.synonyms.length; i++) {
        Token repTok = result.synonyms[i];
        AttributeSource newTok = firstTok.cloneAttributes();
        CharTermAttribute newTermAtt = newTok.addAttribute(CharTermAttribute.class);
        OffsetAttribute newOffsetAtt = newTok.addAttribute(OffsetAttribute.class);
        PositionIncrementAttribute newPosIncAtt = newTok.addAttribute(PositionIncrementAttribute.class);

        OffsetAttribute lastOffsetAtt = lastTok.addAttribute(OffsetAttribute.class);

        newOffsetAtt.setOffset(newOffsetAtt.startOffset(), lastOffsetAtt.endOffset());
        newTermAtt.copyBuffer(repTok.buffer(), 0, repTok.length());
        repPos += repTok.getPositionIncrement();
        if (i==0) repPos=origPos;  // make position of first token equal to original

        // if necessary, insert original tokens and adjust position increment
        while (origTok != null && origPos <= repPos) {
View Full Code Here

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

220
221
222
223
224
225
226
227
228
229
230
231
      if (tok != null) {
        // clone ourselves.
        if (tok == this)
          tok = cloneAttributes();
        // check for positionIncrement!=1?  if>1, should not match, if==0, check multiple at this level?
        CharTermAttribute termAtt = tok.getAttribute(CharTermAttribute.class);
        SlowSynonymMap subMap = map.submap.get(termAtt.buffer(), 0, termAtt.length());

        if (subMap != null) {
          // recurse
          result = match(subMap);
        }
View Full Code Here

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

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
  @Test public void testNameFilter() throws IOException {
    Reader in = new StringReader(input);
    Tokenizer tok = new SentenceTokenizer(in, detector);
    NameFilter nf = new NameFilter(tok, modelName, finder);

    CharTermAttribute cta;
    PositionIncrementAttribute pta;
    OffsetAttribute oa;
   
    int pass = 0;
   
    while (pass < 2) { // test reuse.
      int pos = 0;
      int lastStart = 0;
      int lastEnd   = 0;
     
      while (nf.incrementToken()) {
        cta = (CharTermAttribute) nf.getAttribute(CharTermAttribute.class);
        pta = (PositionIncrementAttribute) nf.getAttribute(PositionIncrementAttribute.class);
        oa  = (OffsetAttribute) nf.getAttribute(OffsetAttribute.class);
       
        System.err.println("'" + cta.toString() + "'");
        System.err.println(pta.toString());
        System.err.println(oa.toString());
        System.err.println("--- pass: " + pass);
       
        TestCase.assertEquals(tokenStrings[pos], cta.toString());
        TestCase.assertEquals(positionIncrements[pos], pta.getPositionIncrement());
       
        if (pta.getPositionIncrement() == 0) {
          TestCase.assertEquals(lastStart, oa.startOffset());
          TestCase.assertEquals(lastEnd, oa.endOffset());
        }
       
        if (!cta.toString().startsWith("NE_")) {
          TestCase.assertEquals(input.substring(oa.startOffset(), oa.endOffset()), cta.toString());
        }
       
        lastStart = oa.startOffset();
        lastEnd   = oa.endOffset();
       
View Full Code Here

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

156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
   * @param analyzer The analyzer to use.
   */
  protected Set<String> getQueryTokenSet(String query, Analyzer analyzer) {
    final Set<String> tokens = new HashSet<String>();
    final TokenStream tokenStream = analyzer.tokenStream("", new StringReader(query));
    final CharTermAttribute termAtt = tokenStream.addAttribute(CharTermAttribute.class);
    try {
      tokenStream.reset();
      while (tokenStream.incrementToken()) {
        tokens.add(termAtt.toString());
      }
    } catch (IOException ioe) {
      throw new RuntimeException("Error occured while iterating over tokenstream", ioe);
    }
    return tokens;
View Full Code Here

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

104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
      String word = matcher.group(0);
      if (word.equals("AND") == false && word.equals("OR") == false) {
        try {
          stream = analyzer.reusableTokenStream("", new StringReader(word));
          // TODO: support custom attributes
          CharTermAttribute termAtt = stream.addAttribute(CharTermAttribute.class);
          FlagsAttribute flagsAtt = stream.addAttribute(FlagsAttribute.class);
          TypeAttribute typeAtt = stream.addAttribute(TypeAttribute.class);
          PayloadAttribute payloadAtt = stream.addAttribute(PayloadAttribute.class);
          PositionIncrementAttribute posIncAtt = stream.addAttribute(PositionIncrementAttribute.class);
          stream.reset();
          while (stream.incrementToken()) {
            Token token = new Token();
            token.copyBuffer(termAtt.buffer(), 0, termAtt.length());
            token.setStartOffset(matcher.start());
            token.setEndOffset(matcher.end());
            token.setFlags(flagsAtt.getFlags());
            token.setType(typeAtt.type());
            token.setPayload(payloadAtt.getPayload());
View Full Code Here

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

473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
  private Collection<Token> getTokens(String q, Analyzer analyzer) throws IOException {
    Collection<Token> result = new ArrayList<Token>();
    TokenStream ts = analyzer.reusableTokenStream("", new StringReader(q));
    ts.reset();
    // TODO: support custom attributes
    CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
    OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
    TypeAttribute typeAtt = ts.addAttribute(TypeAttribute.class);
    FlagsAttribute flagsAtt = ts.addAttribute(FlagsAttribute.class);
    PayloadAttribute payloadAtt = ts.addAttribute(PayloadAttribute.class);
    PositionIncrementAttribute posIncAtt = ts.addAttribute(PositionIncrementAttribute.class);
   
    while (ts.incrementToken()){
      Token token = new Token();
      token.copyBuffer(termAtt.buffer(), 0, termAtt.length());
      token.setOffset(offsetAtt.startOffset(), offsetAtt.endOffset());
      token.setType(typeAtt.type());
      token.setFlags(flagsAtt.getFlags());
      token.setPayload(payloadAtt.getPayload());
      token.setPositionIncrement(posIncAtt.getPositionIncrement());
View Full Code Here

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

348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
      HashMap<String,ArrayIntList> terms = new HashMap<String,ArrayIntList>();
      int numTokens = 0;
      int numOverlapTokens = 0;
      int pos = -1;
     
      CharTermAttribute termAtt = stream.addAttribute(CharTermAttribute.class);
      PositionIncrementAttribute posIncrAttribute = stream.addAttribute(PositionIncrementAttribute.class);
      OffsetAttribute offsetAtt = stream.addAttribute(OffsetAttribute.class);
      stream.reset();
      while (stream.incrementToken()) {
        String term = termAtt.toString();
        if (term.length() == 0) continue; // nothing to do
//        if (DEBUG) System.err.println("token='" + term + "'");
        numTokens++;
        final int posIncr = posIncrAttribute.getPositionIncrement();
        if (posIncr == 0)
View Full Code Here

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

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
    args.put("modelDirectory", modelsDir.getAbsolutePath());
    factory.init(args);
   
    SentenceTokenizer tok = factory.create(new StringReader(inputString));
   
    CharTermAttribute cta;
    PositionIncrementAttribute pta;
    OffsetAttribute oa;

    int pass = 0;
   
    while (pass < 2) { // test reuse
      int pos = 0;
      int offset = 0;
     
      while (tok.incrementToken()) {
        cta = (CharTermAttribute) tok.getAttribute(CharTermAttribute.class);
        pta = (PositionIncrementAttribute) tok.getAttribute(PositionIncrementAttribute.class);
        oa  = (OffsetAttribute) tok.getAttribute(OffsetAttribute.class);
       
        System.err.println("'" + cta.toString() + "'");
        System.err.println(pta.toString());
        System.err.println(oa.toString());
        System.err.println("--- pass: " + pass);
       
        String expected = expectedStrings[pos];
        TestCase.assertEquals("Strings don't match", expected, cta.toString());
        TestCase.assertEquals("Positing increment is incorrect", 1, pta.getPositionIncrement());
        TestCase.assertEquals("Start offset is incorrect", offset, oa.startOffset());
        TestCase.assertEquals("End offset is incorrect",  offset + expected.length(), oa.endOffset());
       
        offset += expected.length() + 1; // space after end of sentence
View Full Code Here

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

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
      }

      if (!buffer.hasAttribute(CharTermAttribute.class)) {
        return new NoTokenFoundQueryNode();
      }
      final CharTermAttribute termAtt = buffer.getAttribute(CharTermAttribute.class);

      if (numTokens == 0) {
        return new NoTokenFoundQueryNode();
      } else if (numTokens != 1) {
        // phrase query
        final TokenizedPhraseQueryNode pq = new TokenizedPhraseQueryNode();

        for (int i = 0; i < numTokens; i++) {
          String term = null;

          try {
            final boolean hasNext = buffer.incrementToken();
            assert hasNext == true;
            term = termAtt.toString();

          } catch (final IOException e) {
            // safe to ignore, because we know the number of tokens
          }
View Full Code Here

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

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
      }

      if (!buffer.hasAttribute(CharTermAttribute.class)) {
        return new NoTokenFoundQueryNode();
      }
      final CharTermAttribute termAtt = buffer.getAttribute(CharTermAttribute.class);

      if (numTokens == 0) {
        if (nbTwigs != 0) { // Twig special case
          return new WildcardNodeQueryNode();
        }
        return new NoTokenFoundQueryNode();
      }
      else if (numTokens == 1) {
        String term = null;
        try {
          boolean hasNext;
          hasNext = buffer.incrementToken();
          assert hasNext == true;
          term = termAtt.toString();
        } catch (final IOException e) {
          // safe to ignore, because we know the number of tokens
        }
        fieldNode.setText(term);
        return fieldNode;
      }
      else {
        // no phrase query:
        final LinkedList<QueryNode> children = new LinkedList<QueryNode>();

        int position = -1;

        for (int i = 0; i < numTokens; i++) {
          String term = null;
          final int positionIncrement = 1;

          try {
            final boolean hasNext = buffer.incrementToken();
            assert hasNext == true;
            term = termAtt.toString();

          } catch (final IOException e) {
            // safe to ignore, because we know the number of tokens
          }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.