Package edu.stanford.nlp.trees

Examples of edu.stanford.nlp.trees.TreeReader

346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
    TreeReaderFactory trf = new FrenchXMLTreeReaderFactory(false);
    int totalTrees = 0;
    Set<String> morphAnalyses = Generics.newHashSet();
    try {
      for(File file : fileList) {
        TreeReader tr = trf.newTreeReader(new BufferedReader(new InputStreamReader(new FileInputStream(file),"UTF-8")));

        Tree t;
        int numTrees;
        String canonicalFileName = file.getName().substring(0, file.getName().lastIndexOf('.'));

        for(numTrees = 0; (t = tr.readTree()) != null; numTrees++) {
          String ftbID = ((CoreLabel) t.label()).get(CoreAnnotations.SentenceIDAnnotation.class);
          System.out.printf("%s-%s\t%s%n",canonicalFileName, ftbID, t.toString());
          List<Label> leaves = t.yield();
          for(Label label : leaves) {
            if(label instanceof CoreLabel)
              morphAnalyses.add(((CoreLabel) label).originalText());
          }
        }

        tr.close();
        System.err.printf("%s: %d trees%n",file.getName(),numTrees);
        totalTrees += numTrees;
      }

//wsg2011: Print out the observed morphological analyses
View Full Code Here
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
      TregexPattern pBadTree = TregexPattern.compile("@SENT <: @PUNC");
      TregexPattern pBadTree2 = TregexPattern.compile("@SENT <1 @PUNC <2 @PUNC !<3 __");
     
      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(f), "UTF-8"));
      TreeReaderFactory trf = new FrenchTreeReaderFactory();
      TreeReader tr = trf.newTreeReader(br);
  
      int nTrees = 0;
      for(Tree t; (t = tr.readTree()) != null;nTrees++) {
        TregexMatcher m = pBadTree.matcher(t);
        TregexMatcher m2 = pBadTree2.matcher(t);
        if(m.find() || m2.find()) {
          System.err.println("Discarding tree: " + t.toString());
        } else {
          Tree fixedT = tt.transformTree(t);
          System.out.println(fixedT.toString());
        }
      }
     
      tr.close();
     
      System.err.printf("Wrote %d trees%n",nTrees);
     
    } catch (UnsupportedEncodingException e) {
      e.printStackTrace();
View Full Code Here
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
    MultiWordTreeExpander expander = new MultiWordTreeExpander();

    try {
      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
      TreeReaderFactory trf = new SpanishTreeReaderFactory();
      TreeReader tr = trf.newTreeReader(br);

      PrintWriter pw = new PrintWriter(new PrintStream(new FileOutputStream(new File(treeFile + ".fixed")),false,"UTF-8"));

      int nTrees = 0;
      for(Tree t; (t = tr.readTree()) != null;nTrees++) {
        traverseAndFix(t, null, unigramTagger, retainNER);

        // Now "decompress" further the expanded trees formed by
        // multiword token splitting
        t = expander.expandPhrases(t, tn, tf);

        if (tn != null)
          t = tn.normalizeWholeTree(t, tf);

        pw.println(t.toString());
      }

      pw.close();
      tr.close();

      System.out.println("Processed " +nTrees+ " trees");

    } catch (UnsupportedEncodingException e) {
      e.printStackTrace();
View Full Code Here
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
      new TwoDimensionalCounter<String,String>();

    try {
      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
      TreeReaderFactory trf = new SpanishTreeReaderFactory();
      TreeReader tr = trf.newTreeReader(br);

      for(Tree t; (t = tr.readTree()) != null;) {
        updateTagger(unigramTagger, t);
      }
      tr.close(); //Closes the underlying reader

      System.out.println("Resolving DUMMY tags");
      resolveDummyTags(treeFile, unigramTagger, retainNER,
                       normalize ? new SpanishTreeNormalizer(true, false, false) : null);
View Full Code Here
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
    String treeFile = args[0];
   
    TreeReaderFactory trf = new FrenchTreeReaderFactory();
    try {
      TreeReader tr = trf.newTreeReader(new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8")));
 
      for (Tree tree1; (tree1 = tr.readTree()) != null;) {
        List<Label> pretermYield = tree1.preTerminalYield();
        List<Label> yield = tree1.yield();
        int yieldLen = yield.size();
        for (int i = 0; i < yieldLen; ++i) {
          CoreLabel rawToken = (CoreLabel) yield.get(i);
          String word = rawToken.value();
          String morphStr = rawToken.originalText();
          Pair<String,String> lemmaMorph = MorphoFeatureSpecification.splitMorphString(word, morphStr);
          String lemma = lemmaMorph.first();
          String morph = lemmaMorph.second();
          if (morph == null || morph.equals("") || morph.equals("XXX")) {
            morph = ((CoreLabel) pretermYield.get(i)).value();
          }
          System.out.printf("%s %s %s%n", word, lemma, morph);
        }
        System.out.println();
      }
   
      tr.close();
     
    } catch (UnsupportedEncodingException e) {
      e.printStackTrace();
    } catch (FileNotFoundException e) {
      e.printStackTrace();
View Full Code Here
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
147
148
149
150
151
152
    String treeFile = args[0];
    String morfetteFile = args[1];
    TreeReaderFactory trf = new FrenchTreeReaderFactory();
    try {
      TreeReader tr = trf.newTreeReader(new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8")));
      Iterator<List<CoreLabel>> morfetteItr = new MorfetteFileIterator(morfetteFile);
      for (Tree tree; (tree = tr.readTree()) != null && morfetteItr.hasNext();) {
        List<CoreLabel> analysis = morfetteItr.next();
        List<Label> yield = tree.yield();
        assert analysis.size() == yield.size();

        int yieldLen = yield.size();
        for (int i = 0; i < yieldLen; ++i) {
          CoreLabel tokenAnalysis = analysis.get(i);
          Label token = yield.get(i);
          String lemma = getLemma(token.value(), tokenAnalysis.lemma());
          String newLeaf = String.format("%s%s%s%s%s", token.value(),
              MorphoFeatureSpecification.MORPHO_MARK,
              lemma,
              MorphoFeatureSpecification.LEMMA_MARK,
              tokenAnalysis.tag());
          ((CoreLabel) token).setValue(newLeaf);
        }
        System.out.println(tree.toString());
      }

      if (tr.readTree() != null || morfetteItr.hasNext()) {
        System.err.println("WARNING: Uneven input files!");
      }

      tr.close();

    } catch (UnsupportedEncodingException e) {
      e.printStackTrace();
    } catch (FileNotFoundException e) {
      e.printStackTrace();
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
      System.exit(-1);
    }
   
    TreeReaderFactory trf = new ArabicTreeReaderFactory();
    try {
      TreeReader tr = trf.newTreeReader(new BufferedReader(new InputStreamReader(new FileInputStream(args[0]), "UTF-8")));
      TreeVisitor visitor = new MWETreeVisitorExternal();
     
      int treeId = 0;
      for (Tree tree; (tree = tr.readTree()) != null; ++treeId) {
        if (tree.value().equals("ROOT")) {
          // Skip over the ROOT tag
          tree = tree.firstChild();
        }
        visitor.visitTree(tree);
        System.out.println(tree.toString());
      }
      tr.close();
     
      System.err.printf("Processed %d trees.%n", treeId);
   
    } catch (UnsupportedEncodingException e) {
      e.printStackTrace();
View Full Code Here
31
32
33
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
95
    String treeFile = args[0];

    try {
      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
      TreeReaderFactory trf = new SpanishTreeReaderFactory();
      TreeReader tr = trf.newTreeReader(br);

      StringBuilder sb = new StringBuilder();
      String nl = System.getProperty("line.separator");

      Pattern nePattern = Pattern.compile("^grup\\.nom\\.");
      Pattern npPattern = Pattern.compile("^np0000.$");

      for (Tree tree; (tree = tr.readTree()) != null;) {
        for(Tree t : tree) {
          if(!t.isPreTerminal())
            continue;

          char type = 'O';
          Tree grandma = t.ancestor(1, tree);
          String grandmaValue = ((CoreLabel) grandma.label()).value();

          // grup.nom.x
          if(nePattern.matcher(grandmaValue).find())
            type = grandmaValue.charAt(9);

          // else check the pos for np0000x or not
          else {
            String pos = ((CoreLabel) t.label()).value();
            if(npPattern.matcher(pos).find())
              type = pos.charAt(6);
          }

          Tree wordNode = t.firstChild();
          String word = ((CoreLabel) wordNode.label()).value();
          sb.append(word).append("\t");
          switch(type) {
          case 'p':
            sb.append("PERS");
            break;
          case 'l':
            sb.append("LUG");
            break;
          case 'o':
            sb.append("ORG");
            break;
          case '0':
            sb.append("OTROS");
            break;
          default:
            sb.append("O");
          }
          sb.append(nl);
        }
        sb.append(nl);
      }
      System.out.print(sb.toString());

      tr.close();
    } catch (UnsupportedEncodingException e) {
      e.printStackTrace();
    } catch (FileNotFoundException e) {
      e.printStackTrace();
    } catch (IOException e) {
View Full Code Here
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
    File f = new File(args[0]);
    try {

      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(f), "UTF-8"));
      TreeReaderFactory trf = new ArabicTreeReaderFactory.ArabicRawTreeReaderFactory();
      TreeReader tr = trf.newTreeReader(br);

      int nTrees = 0;
      for(Tree t; (t = tr.readTree()) != null;nTrees++) {
        Tree fixedT = tt.transformTree(t);
        System.out.println(fixedT.toString());
      }

      tr.close();

      System.err.printf("Wrote %d trees%n",nTrees);

    } catch (UnsupportedEncodingException e) {
      e.printStackTrace();
View Full Code Here
22
23
24
25
26
27
28
29
30
31
32
33
34
35
public class ThreadedParserSlowITest extends TestCase {
  public static List<Tree> readTrees(String filename, String encoding) {
    ArrayList<Tree> trees = new ArrayList<Tree>();
    try {
      TreeReaderFactory trf = new LabeledScoredTreeReaderFactory();
      TreeReader tr = trf.newTreeReader(new InputStreamReader(
                        new FileInputStream(filename), encoding));
      Tree next;
      while ((next = tr.readTree()) != null) {
        trees.add(next);
      }
      System.out.println("Read " + trees.size() + " trees from " + filename);
      return trees;
    } catch (IOException e) {
View Full Code Here
TOP

Related Classes of edu.stanford.nlp.trees.TreeReader

  • edu.jhu.agiga.StanfordAgigaSentence
  • edu.stanford.nlp.international.arabic.pipeline.ATBCorrector
  • edu.stanford.nlp.international.arabic.pipeline.MWETreeVisitorExternal
  • edu.stanford.nlp.international.french.pipeline.FTBCorrector
  • edu.stanford.nlp.international.french.pipeline.MWEPreprocessor
  • edu.stanford.nlp.international.french.scripts.MungeTreesWithMorfetteAnalyses
  • edu.stanford.nlp.international.french.scripts.MWEFrequencyDist
  • edu.stanford.nlp.international.french.scripts.TreeToMorfette
  • edu.stanford.nlp.international.spanish.pipeline.AnCoraPOSStats
  • edu.stanford.nlp.international.spanish.pipeline.MultiWordPreprocessor
    • 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.