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

Examples of uk.ac.cam.ch.wwmm.oscar3.recogniser.document.ProcessingDocument

61
62
63
64
65
66
67
68
69
70
71
72
73
   
   
   
    for(File file : files) {
      System.out.println(file);
      ProcessingDocument procDoc = ProcessingDocumentFactory.getInstance().makeTokenisedDocument(new Builder().build(file), false, false, false);
      Bag<String> b = new Bag<String>();
      for(TokenSequence ts : procDoc.getTokenSequences()) {
        for(Token t : ts.getTokens()) {
          String s = t.getValue().intern();
          if(!TermSets.getClosedClass().contains(s.toLowerCase())) b.add(s);
        }
      }
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
    for(int i=0;i<nodes.size();i++) {
      XOMTools.removeElementPreservingText((Element)nodes.get(i));
    }
    Document safDoc = InlineToSAF.extractSAFs(doc, sourceDoc, "foo");

    ProcessingDocument procDoc = ProcessingDocumentFactory.getInstance().makeTokenisedDocument(sourceDoc, false, false, false);

    //NameRecogniser nr = new NameRecogniser();
    //nr.halfProcess(sourceDoc);
    //nr.makeTokenisers(false);

    Nodes n = safDoc.query("/saf/annot[slot[@name='type']['PRW']]");

    Map<TokenSequence,Boolean> tokSeqs = new HashMap<TokenSequence,Boolean>();
    Map<TokenSequence,Bag<String>> tokSeqPRWs = new HashMap<TokenSequence,Bag<String>>();
   
    for(int i=0;i<n.size();i++) {
      Element e = (Element)n.get(i);
      Token token = procDoc.getTokenByStart(e.getAttributeValue("from"));
      if(token == null) token = procDoc.getTokenByEnd(e.getAttributeValue("to"));
      if(token == null) {
        System.out.println("Eeep!");
      } else {
        TokenSequence tokSeq = token.getTokenSequence();
        boolean isReact = "REACT".equals(SafTools.getSlotValue(e, "subtype"));
View Full Code Here
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
      for(int i=0;i<nodes.size();i++) {
        XOMTools.removeElementPreservingText((Element)nodes.get(i));
      }
      Document safDoc = InlineToSAF.extractSAFs(doc, sourceDoc, "foo");

      ProcessingDocument procDoc = ProcessingDocumentFactory.getInstance().makeTokenisedDocument(sourceDoc, false, false, false);
      //NameRecogniser nr = new NameRecogniser();
      //nr.halfProcess(sourceDoc);
      //nr.makeTokenisers(false);
      Set<String> tokenSet = new HashSet<String>();
      Bag<String> tokenBag = new Bag<String>();
      for(TokenSequence t : procDoc.getTokenSequences()) {
        //System.out.println(t.getSourceString());
        for(Token token : t.getTokens()) {
          //tokenSet.add("stem=" + stemmer.getStem(token.getValue().toLowerCase()));
          //tokenSet.add(token.getValue().toLowerCase());
          tokenBag.add(token.getValue().toLowerCase());
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
   
    File inlineFile = new File(paperDir, "source.xml");
    File safFile = new File(paperDir, "saf.xml");
    Document doc = new Builder().build(inlineFile);
    Document safDoc = new Builder().build(safFile);
    ProcessingDocument procDoc = ProcessingDocumentFactory.getInstance().makeTokenisedDocument(doc, false, false, false);
    //NameRecogniser nr = new NameRecogniser();
    //nr.halfProcess(doc);
    //Nodes n = doc.query(XMLStrings.CHEMICAL_PLACES_XPATH);
    DFARelationFinder relf = DFARelationFinder.getInstance();
    List<Lattice> lattices = Lattice.buildLattices(procDoc, safDoc.getRootElement());
View Full Code Here
22
23
24
25
26
27
28
29
30
31
32
    //Document doc = new Document((Element)(sourceDoc.getRootElement().copy()));
    safDoc = new Document((Element)(safDoc.getRootElement().copy()));
   
    //NameRecogniser nr = new NameRecogniser();
    //nr.halfProcess(doc);
    ProcessingDocument procDoc = ProcessingDocumentFactory.getInstance().makeTokenisedDocument(doc, false, false, false);
   
    DFARelationFinder relf = DFARelationFinder.getInstance();
    List<Lattice> lattices = Lattice.buildLattices(procDoc, safDoc.getRootElement());
   
    for(Lattice lattice : lattices) {
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
        XOMTools.removeElementPreservingText((Element)nodes.get(i));
      }
      Document safDoc = InlineToSAF.extractSAFs(doc, sourceDoc, "foo");

     
      ProcessingDocument procDoc = ProcessingDocumentFactory.getInstance().makeTokenisedDocument(sourceDoc, false, false, false);
     
      //NameRecogniser nr = new NameRecogniser();
      //nr.halfProcess(sourceDoc);
      //nr.makeTokenisers(false);
      Set<String> tokenSet = new HashSet<String>();
      Bag<String> tokenBag = new Bag<String>();
      for(TokenSequence t : procDoc.getTokenSequences()) {
        //System.out.println(t.getSourceString());
        for(Token token : t.getTokens()) {
          tokenSet.add(token.getValue().toLowerCase());
          tokenBag.add(token.getValue().toLowerCase());
        }
View Full Code Here
41
42
43
44
45
46
47
48
49
50
51
52
    tokenList = new ArrayList<String>();
    tokenIndex = new HashMap<String,Integer>();
   
    numdocs = 0;
    for(File f : files) {
      ProcessingDocument procDoc = ProcessingDocumentFactory.getInstance().makeTokenisedDocument(new Builder().build(f), false, false, false);
      for(TokenSequence ts : procDoc.getTokenSequences()) {
        if(ts.size() == 0) continue;
        for(Token t : ts.getTokens()) {
          String s = t.getValue().toLowerCase().intern();
          int tn = -1;
          if(tokenIndex.containsKey(s)) {
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
88
89
  public void randomCorpus(List<File> files, int num, int seed) throws Exception {
    List<Integer> sizes = new ArrayList<Integer>();
    List<Integer> corpus = new ArrayList<Integer>();
    long time = System.currentTimeMillis();
    for(File f : files) {
      ProcessingDocument procDoc = ProcessingDocumentFactory.getInstance().makeTokenisedDocument(new Builder().build(f), false, false, false);
      int size = 0;
      for(TokenSequence ts : procDoc.getTokenSequences()) {
        if(ts.size() == 0) continue;
        for(Token t : ts.getTokens()) {
          size++;
          String s = t.getValue().toLowerCase().intern();
          int tn = -1;
View Full Code Here
124
125
126
127
128
129
130
131
132
133
134
135
136
   
    Stemmer st = new Stemmer(new PorterStemmer());
   
    long time = System.currentTimeMillis();
    for(File f : files) {
      ProcessingDocument procDoc = ProcessingDocumentFactory.getInstance().makeTokenisedDocument(new Builder().build(f), false, false, false);
      Set<Integer> tokSet = new HashSet<Integer>();
      for(TokenSequence ts : procDoc.getTokenSequences()) {
        if(ts.size() == 0) continue;
        for(Token t : ts.getTokens()) {
          String s = t.getValue().toLowerCase().intern();
          if(s.matches(".*[a-z].*")) s = st.getStem(s);
          if(s == null || s.length() == 0) continue;
View Full Code Here
34
35
36
37
38
39
40
41
42
43
44
45
46
47
      //NameRecogniser nr = new NameRecogniser();
     
      //nr.halfProcess(new Builder().build(new File(f.getParentFile(), "source.xml")));
      //List<Tokeniser> tokSeqs = nr.buildTokenTables(new Builder().build(new File(f.getParentFile(), "saf.xml")).getRootElement(), false, true);
     
      ProcessingDocument procDoc = ProcessingDocumentFactory.getInstance().makeTokenisedDocument(new Builder().build(new File(f.getParentFile(), "source.xml")), true, true, false,
          new Builder().build(new File(f.getParentFile(), "saf.xml")));
     
      for(TokenSequence tokSeq : procDoc.getTokenSequences()) {
        for(Token t : tokSeq.getTokens()) {
          String tokVal = t.getValue();
          tokVal = StringTools.normaliseName(tokVal);
          tokVal.replaceAll("\\s+", "_");
         
View Full Code Here
TOP

Related Classes of uk.ac.cam.ch.wwmm.oscar3.recogniser.document.ProcessingDocument

  • dk.brics.automaton.Automaton
  • dk.brics.automaton.RunAutomaton
  • jregex.Pattern
  • nu.xom.Attribute
  • nu.xom.Builder
  • nu.xom.Document
  • nu.xom.Element
  • nu.xom.Elements
  • nu.xom.Node
  • nu.xom.Nodes
    • 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.