Package opennlp.tools.util

Examples of opennlp.tools.util.PlainTextByLineStream

115
116
117
118
119
120
121
122
123
124
125
  public void setup() throws IOException {
    InputStream in = ADParagraphStreamTest.class
        .getResourceAsStream("/opennlp/tools/formats/ad.sample");

    ADNameSampleStream stream = new ADNameSampleStream(
        new PlainTextByLineStream(in, "UTF-8"), true);

    NameSample sample = stream.read();

    while (sample != null) {
      samples.add(sample);
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
        TokenNameFinderModel model = new TokenNameFinderModelLoader().load(new File(args[i]));
        nameFinders[i] = new NameFinderME(model);
      }

      ObjectStream<String> untokenizedLineStream =
          new PlainTextByLineStream(new InputStreamReader(System.in));

      PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
      perfMon.start();

      try {
        String line;
        while((line = untokenizedLineStream.read()) != null) {
          String whitespaceTokenizerLine[] = WhitespaceTokenizer.INSTANCE.tokenize(line);

          // A new line indicates a new document,
          // adaptive data must be cleared for a new document
View Full Code Here
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
      } catch (IOException e) {
        throw new TerminateToolException(-1, "Failed to load all coreferencer models!", e);
      }
     
      ObjectStream<String> lineStream =
          new PlainTextByLineStream(new InputStreamReader(System.in));
     
      PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "parses");
      perfMon.start();
     
      try {
       
        int sentenceNumber = 0;
        List<Mention> document = new ArrayList<Mention>();
        List<Parse> parses = new ArrayList<Parse>();
       
        String line;
        while ((line = lineStream.read()) != null) {

          if (line.equals("")) {
            DiscourseEntity[] entities = treebankLinker.getEntities(document.toArray(new Mention[document.size()]));
            //showEntities(entities);
            new CorefParse(parses,entities).show();
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
    FileInputStream sampleDataIn = new FileInputStream(new File(getClass()
        .getClassLoader()
        .getResource("opennlp/tools/namefind/AnnotatedSentences.txt").toURI()));

    ObjectStream<NameSample> sampleStream = new NameSampleDataStream(
        new PlainTextByLineStream(sampleDataIn.getChannel(), "ISO-8859-1"));

    TrainingParameters mlParams = ModelUtil.createTrainingParameters(70, 1);
    mlParams.put(TrainingParameters.ALGORITHM_PARAM,
        ModelType.MAXENT.toString());
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
    FileInputStream sampleDataIn = new FileInputStream(new File(getClass()
        .getClassLoader()
        .getResource("opennlp/tools/namefind/AnnotatedSentences.txt").toURI()));

    ObjectStream<NameSample> sampleStream = new NameSampleDataStream(
        new PlainTextByLineStream(sampleDataIn.getChannel(), "ISO-8859-1"));

    TrainingParameters mlParams = ModelUtil.createTrainingParameters(70, 1);
    mlParams.put(TrainingParameters.ALGORITHM_PARAM,
        ModelType.MAXENT.toString());
   
View Full Code Here
47
48
49
50
51
52
53
54
  private static ObjectStream<TokenSample> createSampleStream()
      throws IOException {
    InputStream in = TokenizerFactoryTest.class.getClassLoader()
        .getResourceAsStream("opennlp/tools/tokenize/token.train");

    return new TokenSampleStream(new PlainTextByLineStream(
        new InputStreamReader(in)));
  }
View Full Code Here
30
31
32
33
34
35
36
37
38
39
40
  @Test
  public void testSimple() throws IOException {
    // add one sentence with expandME = includeFeats = false
    ADPOSSampleStream stream = new ADPOSSampleStream(
        new PlainTextByLineStream(
            ADParagraphStreamTest.class
                .getResourceAsStream("/opennlp/tools/formats/ad.sample"),
            "UTF-8"), false, false);

    POSSample sample = stream.read();
View Full Code Here
78
79
80
81
82
83
84
85
86
87
88
        "opennlp/tools/namefind/AnnotatedSentences.txt");

    String encoding = "ISO-8859-1";

    NameSampleDataStream ds = new NameSampleDataStream(
        new PlainTextByLineStream(new InputStreamReader(in, encoding)));

    NameSample ns = ds.read();

    String[] expectedNames = { "Alan McKennedy", "Julie", "Marie Clara",
        "Stefanie Schmidt", "Mike", "Stefanie Schmidt", "George", "Luise",
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
 
  @Test
  public void testExpandME() throws IOException {
    // add one sentence with expandME = true
    ADPOSSampleStream stream = new ADPOSSampleStream(
        new PlainTextByLineStream(
            ADParagraphStreamTest.class
                .getResourceAsStream("/opennlp/tools/formats/ad.sample"),
            "UTF-8"), true, false);

    POSSample sample = stream.read();
View Full Code Here
175
176
177
178
179
180
181
182
183
184
185
  public void testWithNameTypes() throws Exception {
    InputStream in = getClass().getClassLoader().getResourceAsStream(
        "opennlp/tools/namefind/voa1.train");

    NameSampleDataStream ds = new NameSampleDataStream(
        new PlainTextByLineStream(new InputStreamReader(in)));

    Map<String, List<String>> names = new HashMap<String, List<String>>();
    Map<String, List<Span>> spans = new HashMap<String, List<Span>>();
   
    NameSample ns;
View Full Code Here
TOP

Related Classes of opennlp.tools.util.PlainTextByLineStream

  • com.tamingtext.opennlp.NameFinderTest
  • io.lumify.opennlpDictionary.OpenNLPDictionaryExtractorGraphPropertyWorker
  • io.lumify.opennlpme.OpenNLPMaximumEntropyExtractorGraphPropertyWorker
  • opennlp.tools.chunker.ChunkerDetailedFMeasureListenerTest
  • opennlp.tools.chunker.ChunkerEvaluatorTest
  • opennlp.tools.chunker.ChunkerFactoryTest
  • opennlp.tools.chunker.ChunkerME
  • opennlp.tools.chunker.ChunkerMETest
  • opennlp.tools.chunker.ChunkSampleStreamTest
  • opennlp.tools.chunker.ChunkSampleTest
    • 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.