Package edu.harvard.wcfia.yoshikoder.document.tokenizer

Examples of edu.harvard.wcfia.yoshikoder.document.tokenizer.Token

32
33
34
35
36
37
38
39
40
41
42
43
  }
 
    public String getLeftHandSideView(){
        StringBuffer sb = new StringBuffer();
        for (Iterator<Token> iter = lhs.iterator(); iter.hasNext();) {
            Token el = iter.next();
            sb.append(el.getText() + " ");
        }
        if (sb.length()>0)
            sb.deleteCharAt(sb.length()-1);
        return sb.toString();       
    }
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
54
    }

    public String getRightHandSideView(){
        StringBuffer sb = new StringBuffer();
        for (Iterator<Token> iter = rhs.iterator(); iter.hasNext();) {
            Token el = iter.next();
            sb.append(el.getText() + " ");
        }
        if (sb.length()>0)
            sb.deleteCharAt(sb.length()-1);
       
        return sb.toString();       
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
   
    public String toString() {
        StringBuffer sb = new StringBuffer();
        sb.append("[");
        for (Iterator<Token> iter = lhs.iterator(); iter.hasNext();) {
            Token word = iter.next();
            sb.append(word.getText() + " ");
        }
        sb.append("[" + target.getText() + "] ");
        for (Iterator<Token> iter = rhs.iterator(); iter.hasNext();) {
            Token word = iter.next();
            sb.append(word.getText() + " ");
        }
        if (sb.length()>0)
            sb.delete(sb.length()-1, sb.length());
        sb.append("]");
        return sb.toString();
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
              TokenList tlist = new TokenListImpl();
              Concordance conc = concmap.get(doc);
              for (Iterator iter = conc.iterator(); iter.hasNext();) {
                ConcordanceLine line = (ConcordanceLine) iter.next();
                for (Iterator iterator = line.getLeftHandSide().iterator(); iterator.hasNext();) {
                  Token token = (Token) iterator.next();
                  tlist.add(token);
                }
                for (Iterator iterator = line.getRightHandSide().iterator(); iterator.hasNext();) {
                  Token token = (Token) iterator.next();
                  tlist.add(token);
                }
              }
              efm = new EntryFrequencyMap(yoshikoder.getDictionary(), tlist);
              efmMap.put(doc, efm);
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
    public void addHighlights(Set<Token> tl, Color col){
        if (!colors.contains(col) && tl.size()>0)
            colors.add(col);
       
        for (Iterator iter = tl.iterator(); iter.hasNext();) {
            Token element = (Token) iter.next();
            Location loc =
                new LocationImpl(element.getStart(), element.getEnd());
            locationToColor.put(loc, col);
        }
    }
View Full Code Here
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
          counter++;
         
          TokenList lhs = line.getLeftHandSide();
          sb.append("<td class='right'>");
          for (Iterator<Token> iterator = lhs.iterator(); iterator.hasNext();) {
            Token word = iterator.next();
            sb.append(escapeXML(word.getText()) + " "); 
          }
          sb.append("</td><td><b>");
          sb.append(escapeXML(line.getTarget().getText()));
          TokenList rhs = line.getRightHandSide();
          sb.append("</b>");
          for (Iterator<Token> iterator = rhs.iterator(); iterator.hasNext();) {
            Token word = iterator.next();
            sb.append(" " + escapeXML(word.getText())); 
          }
          sb.append("</td></tr>\n");
        }
      }
      sb.append("</table>\n");
View Full Code Here
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
          for (Iterator<ConcordanceLine> iter = conc.iterator(); iter.hasNext();) {
            ConcordanceLine line = iter.next();
            sb.append("<line>");
            TokenList lhs = line.getLeftHandSide();
            for (Iterator<Token> iterator = lhs.iterator(); iterator.hasNext();) {
              Token word = iterator.next();
              sb.append("<w txt=\"" + escapeXML(word.getText()) + "\"/>"); 
            }
            sb.append( "<w txt=\"" + escapeXML(line.getTarget().getText()) + 
            "\" target=\"true\"/>");
            TokenList rhs = line.getRightHandSide();
            for (Iterator<Token> iterator = rhs.iterator(); iterator.hasNext();) {
              Token word = iterator.next();
              sb.append("<w txt=\"" + escapeXML(word.getText()) + "\"/>"); 
            }
            sb.append("</line>\n");
          }
          sb.append("</concgroup>\n");
        }
View Full Code Here
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
        for (Iterator<ConcordanceLine> iter = conc.iterator(); iter.hasNext();) {
            ConcordanceLine line = iter.next();
            sb.append("    <line>");
            TokenList lhs = line.getLeftHandSide();
            for (Iterator<Token> iterator = lhs.iterator(); iterator.hasNext();) {
                Token word = iterator.next();
                sb.append("<w txt=\"" + escapeXML(word.getText()) + "\"/>"); 
            }
            sb.append( "<w txt=\"" + escapeXML(line.getTarget().getText()) + 
            "\" target=\"true\"/>");
            TokenList rhs = line.getRightHandSide();
            for (Iterator<Token> iterator = rhs.iterator(); iterator.hasNext();) {
                Token word = iterator.next();
                sb.append("<w txt=\"" + escapeXML(word.getText()) + "\"/>"); 
            }
            sb.append("</line>\n");
        }
        sb.append("</concordance>\n");
       
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
    public void endElement(String uri, String localName, String qName){                                                 
        if (qName.equals("line")) { //$NON-NLS-1$
            TokenList tl = new TokenListImpl();
            for (Iterator iter = lhs.iterator(); iter.hasNext();) {
                String lhs = (String) iter.next();
                Token t = new TokenImpl(lhs, 0, 0);
                tl.add(t);
            }
            TokenList rl = new TokenListImpl();
            for (Iterator iter = rhs.iterator(); iter.hasNext();) {
                String rhs = (String) iter.next();
                Token t = new TokenImpl(rhs, 0, 0);
                rl.add(t);
            }
            Token targ = new TokenImpl(target, 0, 0);
            ConcordanceLine line = new ConcordanceLineImpl(tl, targ, rl);
            clist.add(line);
        }
    }
View Full Code Here
28
29
30
31
32
33
34
35
36
37
38
39
    public WordFrequencyMap(TokenList tl){
        map = new HashMap<String,Set<Integer>>();
        total = 0;
        int wordIndex = 0;
        for (Iterator<Token> iter = tl.iterator(); iter.hasNext();) {
            Token token = iter.next();
            String text = token.getText().toLowerCase(); // make sure we don't hang onto the token list here
            Set<Integer> indices = map.get(text);
            if (indices == null){
              Integer index = new Integer(wordIndex);
              Set<Integer> inds = new HashSet<Integer>();
              inds.add(index);
View Full Code Here
TOP

Related Classes of edu.harvard.wcfia.yoshikoder.document.tokenizer.Token

  • edu.harvard.wcfia.yoshikoder.concordance.ConcordanceLineImpl
  • edu.harvard.wcfia.yoshikoder.ConcordanceFrequencyReportAction
  • edu.harvard.wcfia.yoshikoder.reporting.WordFrequencyMap
  • edu.harvard.wcfia.yoshikoder.ui.DocumentState
  • edu.harvard.wcfia.yoshikoder.util.ConcordanceHandler
  • edu.harvard.wcfia.yoshikoder.util.ExportUtil
    • 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.