Package uk.ac.cam.ch.wwmm.oscar3.recogniser.document

Examples of uk.ac.cam.ch.wwmm.oscar3.recogniser.document.TokenSequenceSource.reset()

55
56
57
58
59
60
61
62
63
64
65
      //files = FileTools.getFilesFromDirectoryByName(new File("/scratch/pubmed/2005"), "source.xml");
      StringSource ss = new StringSource(files, false);
     
      Bag<String> wordCounts = new Bag<String>();
     
      ss.reset();
      for(String s : ss) {
        TokenSequence t = Tokeniser.getInstance().tokenise(s);
        for(String word : t.getTokenStringList()) {
          if(!word.matches(".*[a-z][a-z].*")) continue;
          word = StringTools.normaliseName(word);
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
    StringSource ss = new StringSource(files, false);
   
    Bag<String> wordCounts = new Bag<String>();
   
    ss.reset();
    for(String s : ss) {
      TokenSequence t = Tokeniser.getInstance().tokenise(s);
      for(String word : t.getTokenStringList()) {
        if(!word.matches(".*[a-z][a-z].*")) continue;
        word = StringTools.normaliseName(word);
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
   
    Bag<String> wordCounts = new Bag<String>();
    Bag<String> collCounts = new Bag<String>();
   
   
    ss.reset();
    int col = 0;
    for(String s : ss) {
      /*System.out.print(".");
      col++;
      if(col >= 80) {
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
        terms.add(StringTools.normaliseName(word));
      }
    }*/
   
    TokenSequenceSource tokSeqSource = new TokenSequenceSource(files);
    tokSeqSource.reset();
    for(TokenSequence t : tokSeqSource) {
      for(String word : t.getTokenStringList()) {
        word = StringTools.normaliseName(word);
        word = word.replaceAll("\\s+", "_");
        terms.add(word.intern());
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.