Package opennlp.tools.util

Examples of opennlp.tools.util.StringList

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
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
    if (dict != null) {

      if (p_2 != null) {
        unigram[0] = p_2.getHead().toString();
        u_2 = dict.contains(new StringList(unigram));
      }

      if (p2 != null) {
        unigram[0] = p2.getHead().toString();
        u2 = dict.contains(new StringList(unigram));
      }

      unigram[0] = p0.getHead().toString();
      u0 = dict.contains(new StringList(unigram));

      if (p_2 != null && p_1 != null) {
        bigram[0] = p_2.getHead().toString();
        bigram[1] = p_1.getHead().toString();
        b_2_1 = dict.contains(new StringList(bigram));

        trigram[0] = p_2.getHead().toString();
        trigram[1] = p_1.getHead().toString();
        trigram[2] = p0.getHead().toString();
        t_2_10 = dict.contains(new StringList(trigram));
      }
      if (p_1 != null && p1 != null) {
        trigram[0] = p_1.getHead().toString();
        trigram[1] = p0.getHead().toString();
        trigram[2] = p1.getHead().toString();
        t_101 = dict.contains(new StringList(trigram));
      }
      if (p_1 != null) {
        unigram[0] = p_1.getHead().toString();
        u_1 = dict.contains(new StringList(unigram));

        //extra check for 2==null case
        b_2_1 = b_2_1 && u_1 & u_2;
        t_2_10 = t_2_10 && u_1 & u_2 & u0;
        t_101 = t_101 && u_1 & u0 && u1;

        bigram[0] = p_1.getHead().toString();
        bigram[1] = p0.getHead().toString();
        b_10 = dict.contains(new StringList(bigram)) && u_1 && u0;
      }
      if (p1 != null && p2 != null) {
        bigram[0] = p1.getHead().toString();
        bigram[1] = p2.getHead().toString();
        b12 = dict.contains(new StringList(bigram));

        trigram[0] = p0.getHead().toString();
        trigram[1] = p1.getHead().toString();
        trigram[2] = p2.getHead().toString();
        t012 = dict.contains(new StringList(trigram));
      }
      if (p1 != null) {
        unigram[0] = p1.getHead().toString();
        u1 = dict.contains(new StringList(unigram));

        //extra check for 2==null case
        b12 = b12 && u1 && u2;
        t012 = t012 && u1 && u2 && u0;
        t_101 = t_101 && u0 && u_1 && u1;

        bigram[0] = p0.getHead().toString();
        bigram[1] = p1.getHead().toString();
        b01 = dict.contains(new StringList(bigram));
        b01 = b01 && u0 && u1;
      }
    }

    String consp_2 = cons(p_2, -2);
View Full Code Here
315
316
317
318
319
320
321
322
323
324
325
326
327
              "", 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
287
288
289
290
291
292
293
294
295
296
297
      for (int wi=0;wi<words.length;wi++) {
        words[wi] =
            tt[wi].substring(0,tt[wi].lastIndexOf('_'));
      }

      ngramModel.add(new StringList(words), 1, 1);
    }

    System.out.println("Saving the dictionary");

    ngramModel.cutoff(cutoff, Integer.MAX_VALUE);
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
120
121
122
123
124
125
126
127
128
129
  private static Dictionary readNames(String nameFile) throws IOException {
    Dictionary names = new Dictionary();

    BufferedReader nameReader = new BufferedReader(new FileReader(nameFile));
    for (String line = nameReader.readLine(); line != null; line = nameReader.readLine()) {
      names.put(new StringList(line));
    }

    return names;
  }
View Full Code Here
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
580
581
582
583
584
585
      //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);
        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
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
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
    if (dict != null) {

      if (p_2 != null) {
        unigram[0] = p_2.getHead().getCoveredText();
        u_2 = dict.contains(new StringList(unigram));
      }

      if (p2 != null) {
        unigram[0] = p2.getHead().getCoveredText();
        u2 = dict.contains(new StringList(unigram));
      }

      unigram[0] = p0.getHead().getCoveredText();
      u0 = dict.contains(new StringList(unigram));

      if (p_2 != null && p_1 != null) {
        bigram[0] = p_2.getHead().getCoveredText();
        bigram[1] = p_1.getHead().getCoveredText();
        b_2_1 = dict.contains(new StringList(bigram));

        trigram[0] = p_2.getHead().getCoveredText();
        trigram[1] = p_1.getHead().getCoveredText();
        trigram[2] = p0.getHead().getCoveredText();
        t_2_10 = dict.contains(new StringList(trigram));
      }
      if (p_1 != null && p1 != null) {
        trigram[0] = p_1.getHead().getCoveredText();
        trigram[1] = p0.getHead().getCoveredText();
        trigram[2] = p1.getHead().getCoveredText();
        t_101 = dict.contains(new StringList(trigram));
      }
      if (p_1 != null) {
        unigram[0] = p_1.getHead().getCoveredText();
        u_1 = dict.contains(new StringList(unigram));

        //extra check for 2==null case
        b_2_1 = b_2_1 && u_1 & u_2;
        t_2_10 = t_2_10 && u_1 & u_2 & u0;
        t_101 = t_101 && u_1 & u0 && u1;

        bigram[0] = p_1.getHead().getCoveredText();
        bigram[1] = p0.getHead().getCoveredText();
        b_10 = dict.contains(new StringList(bigram)) && u_1 && u0;
      }
      if (p1 != null && p2 != null) {
        bigram[0] = p1.getHead().getCoveredText();
        bigram[1] = p2.getHead().getCoveredText();
        b12 = dict.contains(new StringList(bigram));

        trigram[0] = p0.getHead().getCoveredText();
        trigram[1] = p1.getHead().getCoveredText();
        trigram[2] = p2.getHead().getCoveredText();
        t012 = dict.contains(new StringList(trigram));
      }
      if (p1 != null) {
        unigram[0] = p1.getHead().getCoveredText();
        u1 = dict.contains(new StringList(unigram));

        //extra check for 2==null case
        b12 = b12 && u1 && u2;
        t012 = t012 && u1 && u2 && u0;
        t_101 = t_101 && u0 && u_1 && u1;

        bigram[0] = p0.getHead().getCoveredText();
        bigram[1] = p1.getHead().getCoveredText();
        b01 = dict.contains(new StringList(bigram));
        b01 = b01 && u0 && u1;
      }
    }

    String consp_2 = cons(p_2, -2);
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
51
   */
  public Index(Iterator<StringList> tokenLists) {

    while (tokenLists.hasNext()) {

      StringList tokens = tokenLists.next();

      for (int i = 0; i < tokens.size(); i++) {
        this.tokens.add(tokens.getToken(i));
      }
    }
  }
View Full Code Here
161
162
163
164
165
166
167
168
169
        for (int i = textIndex; i < textIndex + lengthIndex; i++) {
          grams[i - textIndex] = ngram.getToken(i);
        }

        add(new StringList(grams));
      }
    }
  }
View Full Code Here
183
184
185
186
187
188
189
190
191
          textIndex + lengthIndex - 1 < chars.length(); textIndex++) {

        String gram =
            chars.substring(textIndex, textIndex + lengthIndex).toLowerCase();

        add(new StringList(new String[]{gram}));
      }
    }
  }
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.