Package opennlp.tools.util

Examples of opennlp.tools.util.StringList

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
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
  @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
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
580
581
582
583
584
585
586
587
588
589
590
591
592
593
      //add all uni-grams
      for (int wi=0;wi<words.length;wi++) {
        words[wi] = pwords[wi].getCoveredText();
      }

      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().getCoveredText();
      }
      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().getCoveredText()+" chunks.length="+chunks.length + "  " + chunks[ci].getParent());

        if (chunks[ci].getParent() == null) {
          chunks[ci].show();
        }
        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().getCoveredText();
            if (ci-1 >= 0) window[wi++] = chunks[ci-1].getHead().getCoveredText();
            window[wi++] = chunks[ci].getHead().getCoveredText();
            if (ci+1 < chunks.length) window[wi++] = chunks[ci+1].getHead().getCoveredText();
            if (ci+2 < chunks.length) window[wi++] = chunks[ci+2].getHead().getCoveredText();
            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
223
224
225
226
227
228
229
230
231
232
233
        String word = iterator.next();

        Attributes tagAttribute = new Attributes();
        tagAttribute.setValue("tags", tagsToString(getTags(word)));

        return new Entry(new StringList(word), tagAttribute);
      }

      public void remove() {
        throw new UnsupportedOperationException();
      }
View Full Code Here
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
        String tagString = entry.getAttributes().getValue("tags");

        String[] tags = tagString.split(" ");

        StringList word = entry.getTokens();

        if (word.size() != 1)
          throw new InvalidFormatException("Each entry must have exactly one token! "+word);

        newPosDict.dictionary.put(word.getToken(0), tags);
      }});

    newPosDict.caseSensitive = isCaseSensitive;

    // TODO: The dictionary API needs to be improved to do this better!
View Full Code Here
237
238
239
240
241
242
243
244
245
246
247
          return dictionaryIterator.hasNext();
        }

        public Entry next() {

          StringList tokens = dictionaryIterator.next();

          return new Entry(tokens, new Attributes());
        }

        public void remove() {
View Full Code Here
309
310
311
312
313
314
315
316
317
318
319
        int tokenIndex = 0;
        while (whiteSpaceTokenizer.hasMoreTokens()) {
          tokens[tokenIndex++] = whiteSpaceTokenizer.nextToken();
        }

        dictionary.put(new StringList(tokens));
      }
    }

    return dictionary;
  }
View Full Code Here
360
361
362
363
364
365
366
367
368
369
370
        boolean result = false;

        if (obj instanceof String) {
          String str = (String) obj;

          result = entrySet.contains(new StringListWrapper(new StringList(str)));

        }

        return result;
      }
View Full Code Here
316
317
318
319
320
321
322
323
324
325
326
327
328
              "", entry.getAttributes().getValue(key));
    }

    hd.startElement("", "", ENTRY_ELEMENT, entryAttributes);

    StringList tokens = entry.getTokens();

    for (Iterator<String> it = tokens.iterator(); it.hasNext(); ) {

      hd.startElement("", "", TOKEN_ELEMENT, new AttributesImpl());

      String token = it.next();
View Full Code Here
132
133
134
135
136
137
138
139
140
141
142
       else if (ENTRY_ELEMENT.equals(localName)) {

         String[] tokens = mTokenList.toArray(
             new String[mTokenList.size()]);

         Entry entry = new Entry(new StringList(tokens), mAttributes);

         try {
           mInserter.insert(entry);
         } catch (InvalidFormatException e) {
           throw new SAXException("Invalid dictionary format!", e);
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.