Package edu.stanford.nlp.trees

Examples of edu.stanford.nlp.trees.TreeReaderFactory


    Format format = Format.TEXT;
    String encoding = getEncoding(config);
    String tagSeparator = getTagSeparator(config);
    TreeTransformer treeTransformer = null;
    TreeNormalizer treeNormalizer = null;
    TreeReaderFactory trf = null;
    NumberRangesFileFilter treeRange = null;
    Predicate<Tree> treeFilter = null;
    Integer wordColumn = null, tagColumn = null;

    for (String arg : args) {
View Full Code Here


    TwoDimensionalCounter<String,String> mweLabelToString = new TwoDimensionalCounter<String,String>();
    Set<String> uniquePOSSequences = Generics.newHashSet();
   
    try {
      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
      TreeReaderFactory trf = new FrenchTreeReaderFactory();
      TreeReader tr = trf.newTreeReader(br);

      final TregexPattern pMWE = TregexPattern.compile("/^MW/");
      for(Tree t; (t = tr.readTree()) != null;) {
        //Count MWE statistics
        TregexMatcher m = pMWE.matcher(t);
View Full Code Here

    TreebankLanguagePack tlp = new HebrewTreebankLanguagePack();
    String inputFile = args[0];
    File treeFile = new File(inputFile);
    try {
      TreeReaderFactory trf = new HebrewTreeReaderFactory();
      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), tlp.getEncoding()));
      TreeReader tr = trf.newTreeReader(br);

      PrintWriter pwDev = new PrintWriter(new PrintStream(new FileOutputStream(inputFile + ".clean.dev"),false,tlp.getEncoding()));
      PrintWriter pwTrain = new PrintWriter(new PrintStream(new FileOutputStream(inputFile + ".clean.train"),false,tlp.getEncoding()));
      PrintWriter pwTest = new PrintWriter(new PrintStream(new FileOutputStream(inputFile + ".clean.test"),false,tlp.getEncoding()));
View Full Code Here

    }

    TreebankLanguagePack tlp = new HebrewTreebankLanguagePack();
    File treeFile = new File(args[0]);
    try {
      TreeReaderFactory trf = new HebrewTreeReaderFactory();
      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), tlp.getEncoding()));
      TreeReader tr = trf.newTreeReader(br);

      int numTrees = 0;
      for(Tree t; ((t = tr.readTree()) != null); numTrees++)
        System.out.println(t.toString());
View Full Code Here

   
    final Pattern pParenStripper = Pattern.compile("[\\(\\)]");
       
    try {
      BufferedReader brIn = new BufferedReader(new InputStreamReader(System.in, encoding));
      TreeReaderFactory trf = new ArabicTreeReaderFactory.ArabicRawTreeReaderFactory(true);

      int nTrees = 0;
      for(String line; (line = brIn.readLine()) != null; ++nTrees) {
        Tree tree = trf.newTreeReader(new StringReader(line)).readTree();
        List<Tree> leaves = tree.getLeaves();
        if(!morphIter.hasNext()) {
          throw new RuntimeException("Mismatch between number of morpho analyses and number of input lines.");
        }
        List<String> morphTags = morphIter.next();
View Full Code Here

    TreeReader treeReader = null;
   
    public YieldIterator(String fileName, boolean isTree) {
      try {
        if (isTree) {
          TreeReaderFactory trf = new ArabicTreeReaderFactory.ArabicRawTreeReaderFactory(true);
          treeReader = trf.newTreeReader(new InputStreamReader(new FileInputStream(fileName), "UTF-8"));
        } else {
          fileReader = new BufferedReader(new InputStreamReader(new FileInputStream(fileName), "UTF-8"));
        }
      } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
View Full Code Here

    TwoDimensionalCounter<String,String> unigramTagger =
      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
View Full Code Here

      TwoDimensionalCounter<String, String> pretermLabel,
      TwoDimensionalCounter<String, String> unigramTagger) {

    try {
      BufferedReader br = new BufferedReader(new InputStreamReader(new FileInputStream(treeFile), "UTF-8"));
      TreeReaderFactory trf = new FrenchTreeReaderFactory();
      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++) {
View Full Code Here

    TwoDimensionalCounter<String,String> unigramTagger =
      new TwoDimensionalCounter<String,String>();

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

      for(Tree t; (t = tr.readTree()) != null;) {
        countMWEStatistics(t, unigramTagger,
                           labelPreterm, pretermLabel, labelTerm, termLabel);
      }
View Full Code Here

      System.out.printf("Usage: java %s tree_file%n", NegraPennTreeReaderFactory.class.getName());
      return;
    }

    TreebankLanguagePack tlp = new NegraPennLanguagePack();
    TreeReaderFactory trf = new NegraPennTreeReaderFactory(2,false,false,tlp);

    try {
      TreeReader tr = trf.newTreeReader(IOUtils.readerFromString(args[0], tlp.getEncoding()));

      for (Tree t; (t = tr.readTree()) != null; ) {
        t.pennPrint();
      }
View Full Code Here

TOP

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

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.