Package opennlp.tools.util

Examples of opennlp.tools.util.StringList

229
230
231
232
233
234
235
236
237
238
239
240
   * Tests the lookup of tokens of different case.
   */
  @Test
  public void testDifferentCaseLookupCaseSensitive() {

    StringList entry1 = new StringList(new String[]{"1a", "1b"});
    StringList entry2 = new StringList(new String[]{"1A", "1B"});

    Dictionary dict = getCaseSensitive();

    dict.put(entry1);

View Full Code Here
37
38
39
40
41
42
43
  private Dictionary getDict() {
    return new Dictionary(true);
  }
 
  private StringList asSL(String str) {
    return new StringList(str);
  }
View Full Code Here
37
38
39
40
41
42
43
  private Dictionary getDict() {
    return new Dictionary(false);
  }
 
  private StringList asSL(String str) {
    return new StringList(str);
  }
View Full Code Here
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
  @Test
  public void testParsingEnglishSample() throws IOException {

    ObjectStream<StringList> sampleStream = openData("census90.sample");

    StringList personName = sampleStream.read();

    // verify the first 5 taken from the Surname data
    assertNotNull(personName);
    assertEquals("Smith", personName.getToken(0));
    personName = sampleStream.read();
    assertNotNull(personName);
    assertEquals("Johnson", personName.getToken(0));
    personName = sampleStream.read();
    assertNotNull(personName);
    assertEquals("Williams", personName.getToken(0));
    personName = sampleStream.read();
    assertNotNull(personName);
    assertEquals("Jones", personName.getToken(0));
    personName = sampleStream.read();
    assertNotNull(personName);
    assertEquals("Brown", personName.getToken(0));

    // verify the next 5 taken from the female names
    personName = sampleStream.read();
    assertNotNull(personName);
    assertEquals("Mary", personName.getToken(0));
    personName = sampleStream.read();
    assertNotNull(personName);
    assertEquals("Patricia", personName.getToken(0));
    personName = sampleStream.read();
    assertNotNull(personName);
    assertEquals("Linda", personName.getToken(0));
    personName = sampleStream.read();
    assertNotNull(personName);
    assertEquals("Barbara", personName.getToken(0));
    personName = sampleStream.read();
    assertNotNull(personName);
    assertEquals("Elizabeth", personName.getToken(0));

    // verify the last 5 taken from the male names
    personName = sampleStream.read();
    assertNotNull(personName);
    assertEquals("James", personName.getToken(0));
    personName = sampleStream.read();
    assertNotNull(personName);
    assertEquals("John", personName.getToken(0));
    personName = sampleStream.read();
    assertNotNull(personName);
    assertEquals("Robert", personName.getToken(0));
    personName = sampleStream.read();
    assertNotNull(personName);
    assertEquals("Michael", personName.getToken(0));
    personName = sampleStream.read();
    assertNotNull(personName);
    assertEquals("William", personName.getToken(0));

    // verify the end of the file.
    personName = sampleStream.read();
    assertNull(personName);
  }
View Full Code Here
194
195
196
197
198
199
200
201
202
203
204
      String text = nameAnnotation.getCoveredText();

      // if possible replace text with normalization from dictionary
      if (mLookupDictionary != null) {

        StringList tokens = new StringList(text);

        String normalizedText = mLookupDictionary.get(tokens);

        if (normalizedText != null) {
          text = normalizedText;
View Full Code Here
106
107
108
109
110
111
112
113
114
115
116
   * @throws IOException
   */
  public static Dictionary createDictionary(ObjectStream<StringList> sampleStream) throws IOException {

    Dictionary mNameDictionary = new Dictionary(true);
    StringList entry;

    entry = sampleStream.read();
    while (entry != null) {
      if (!mNameDictionary.contains(entry)) {
        mNameDictionary.put(entry);
View Full Code Here
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
      //add all uni-grams
      for (int wi=0;wi<words.length;wi++) {
        words[wi] = pwords[wi].toString();
      }

      mdict.add(new StringList(words), 1, 1);
      //add tri-grams and bi-grams for inital sequence
      Parse[] chunks = collapsePunctuation(ParserEventStream.getInitialChunks(p),rules.getPunctuationTags());
      String[] cwords = new String[chunks.length];
      for (int wi=0;wi<cwords.length;wi++) {
        cwords[wi] = chunks[wi].getHead().toString();
      }
      mdict.add(new StringList(cwords), 2, 3);

      //emulate reductions to produce additional n-grams
      int ci = 0;
      while (ci < chunks.length) {
        //System.err.println("chunks["+ci+"]="+chunks[ci].getHead().toString()+" chunks.length="+chunks.length);
        if (lastChild(chunks[ci], chunks[ci].getParent(),rules.getPunctuationTags())) {
          //perform reduce
          int reduceStart = ci;
          while (reduceStart >=0 && chunks[reduceStart].getParent() == chunks[ci].getParent()) {
            reduceStart--;
          }
          reduceStart++;
          chunks = ParserEventStream.reduceChunks(chunks,ci,chunks[ci].getParent());
          ci = reduceStart;
          if (chunks.length != 0) {
            String[] window = new String[5];
            int wi = 0;
            if (ci-2 >= 0) window[wi++] = chunks[ci-2].getHead().toString();
            if (ci-1 >= 0) window[wi++] = chunks[ci-1].getHead().toString();
            window[wi++] = chunks[ci].getHead().toString();
            if (ci+1 < chunks.length) window[wi++] = chunks[ci+1].getHead().toString();
            if (ci+2 < chunks.length) window[wi++] = chunks[ci+2].getHead().toString();
            if (wi < 5) {
              String[] subWindow = new String[wi];
              for (int swi=0;swi<wi;swi++) {
                subWindow[swi]=window[swi];
              }
              window = subWindow;
            }
            if (window.length >=3) {
              mdict.add(new StringList(window), 2, 3);
            }
            else if (window.length == 2) {
              mdict.add(new StringList(window), 2, 2);
            }
          }
          ci=reduceStart-1; //ci will be incremented at end of loop
        }
        ci++;
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
        return mDictionaryIterator.hasNext();
      }

      public Entry next() {

        StringList tokens = mDictionaryIterator.next();

        Attributes attributes = new Attributes();

        attributes.setValue("value", get(tokens));
View Full Code Here
370
371
372
373
374
375
376
377
378
379
380
    POSSample sample;
    while((sample = samples.read()) != null) {
      String[] words = sample.getSentence();
     
      if (words.length > 0)
        ngramModel.add(new StringList(words), 1, 1);
    }
   
    ngramModel.cutoff(cutoff, Integer.MAX_VALUE);
   
    return ngramModel.toDictionary(true);
View Full Code Here
144
145
146
147
148
149
150
151
152
153
154
    List<String> e = new ArrayList<String>();
    e.add("default");
    // add the word itself
    e.add("w=" + lex);
    dictGram[0] = lex;
    if (dict == null || !dict.contains(new StringList(dictGram))) {
      // do some basic suffix analysis
      String[] suffs = getSuffixes(lex);
      for (int i = 0; i < suffs.length; i++) {
        e.add("suf=" + suffs[i]);
      }
View Full Code Here
TOP

Related Classes of opennlp.tools.util.StringList

  • io.lumify.opennlpDictionary.OpenNLPDictionaryExtractorGraphPropertyWorker
  • io.lumify.opennlpDictionary.OpenNLPDictionaryExtractorGraphPropertyWorkerTest
  • opennlp.tools.cmdline.namefind.CensusDictionaryCreatorTool
  • opennlp.tools.coref.CorefModel
  • opennlp.tools.dictionary.Dictionary
  • opennlp.tools.dictionary.DictionaryAsSetCaseInsensitiveTest
  • opennlp.tools.dictionary.DictionaryAsSetCaseSensitiveTest
  • opennlp.tools.dictionary.DictionaryTest
  • opennlp.tools.dictionary.Index
  • opennlp.tools.dictionary.serializer.DictionarySerializer
    • 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.