Package org.apache.ctakes.typesystem.type.textspan

Examples of org.apache.ctakes.typesystem.type.textspan.Segment

563
564
565
566
567
568
569
570
571
572
573
574
575
    List sortedSubSecInds = sortSubSectionInd(subSectionIndSet.toArray());

    for (int i = 0, endBodyOffset = 0; i < sortedSubSecInds.size(); i++, endBodyOffset = 0)
    {
      SubSectionIndicator ssi = (SubSectionIndicator) sortedSubSecInds.get(i);
      Segment segment = getSegmentContainingOffsets(jcas, ssi.getStartOffset(),
          ssi.getEndOffset());
      endBodyOffset = segment.getEnd(); // backup

      SubSectionAnnotation ssa = new SubSectionAnnotation(jcas);

      ssa.setBegin(ssi.getStartOffset());
      // header is marked by the indicator
View Full Code Here
627
628
629
630
631
632
633
634
635
636
637
638
639
    JFSIndexRepository indexes = jcas.getJFSIndexRepository();
    Iterator segmentItr = indexes.getAnnotationIndex(Segment.type).iterator();

    while (segmentItr.hasNext())
    {
      Segment seg = (Segment) segmentItr.next();

      if (seg.getBegin() <= start && seg.getEnd() >= end)
        return seg;
    }

    return null; // did not find a segment - cannot happen - we always have
    // segments
View Full Code Here
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
        //      String[] splitContent = content.split("\n");
        //      int endLine = startLine + splitContent.length;

        index = text.indexOf(content, index);

        Segment segment = new Segment(jCas);
        segment.setBegin(index);
        segment.setEnd(index+content.length());
        segment.setId(sct.getHeader());
        segment.addToIndexes();
        index = index + content.length();
        //      DocumentSection section =
        //          new DocumentSection(startLine, endLine, content);
        //      section.setSectionName(nodeName);
        //      sections.put(startLine, section);
        //
        //      startLine = endLine ;
      }
    } catch(FileNotFoundException e) {
      e.printStackTrace();
      Segment seg = new Segment(jCas);
      seg.setBegin(0);
      seg.setEnd(text.length());
      seg.setId(segmentId);
      seg.addToIndexes();
    }
  }
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
  /**
   * Entry point for processing.
   */
  public void process(JCas jCas) throws AnalysisEngineProcessException {
    Segment segment = new Segment(jCas);
    segment.setBegin(0);
    String text = jCas.getDocumentText();
    if (text == null) {
      String docId = DocumentIDAnnotationUtil.getDocumentID(jCas);
      throw new AnalysisEngineProcessException("text is null for docId="
          + docId, null);
    }
    segment.setEnd(jCas.getDocumentText().length());
    segment.setId(segmentId);
    segment.addToIndexes();
  }
View Full Code Here
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
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
    }
    if (segmentId.compareTo("parseSectionTag") != 0) {
      // If the default segment ID or a segment ID other than
      // "parseSectionTag",
      // create 1 segment using the given segment ID.
      Segment sa = new Segment(jcas);
      sa.setBegin(0);
      sa.setEnd(jcas.getDocumentText().length());
      sa.setId(segmentId);
      sa.addToIndexes();
    } else { // is "parseSectionTag", so search for the segment markers and
          // annotate
      BufferedReader fileReader = new BufferedReader(new StringReader(
          text));

      int charNum = 0;
      int charPos = 0;
      char[] sectIdArr = new char[5];
      int endStartSegment = 0;
      int beginEndSegment = 0;

      try {
        while ((charNum = fileReader.read()) != -1) {

          if (charNum == '[') {
            charPos++;
            if (((charNum = fileReader.read()) == 's')
                || (charNum == 'e')) {
              charPos++;
              if (((charNum = fileReader.read()) == 't')
                  || (charNum == 'n')) {
                charPos++;
                if (((charNum = fileReader.read()) == 'a')
                    || (charNum == 'd')) {
                  charPos++;

                  if ((charNum = fileReader.read()) == 'r') {
                    endStartSegment = charPos + 24;
                    fileReader.skip(14);

                    fileReader.read(sectIdArr, 0, 5);
                    charPos = charPos + 19;

                  } else if (charNum == ' ') {
                    beginEndSegment = charPos - 5;
                    Segment sa = new Segment(jcas);
                    sa.setBegin(endStartSegment);
                    sa.setEnd(beginEndSegment);
                    sa.setId(String.copyValueOf(sectIdArr));
                    for (int i = 0; i < sectIdArr.length; i++)
                      sectIdArr[i] = ' ';
                    sa.addToIndexes();
                  }
                  charPos++;
                }
              }
            }
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
    tokenCount = 0;

    JFSIndexRepository indexes = jcas.getJFSIndexRepository();
    FSIterator<Annotation> segmentItr = indexes.getAnnotationIndex(Segment.type).iterator();
    while (segmentItr.hasNext()) {
      Segment sa = (Segment) segmentItr.next();
      String segmentID = sa.getId();
      if (!skipSegmentsSet.contains(segmentID)) {
        try {
          annotateRange(jcas, sa.getBegin(), sa.getEnd());
        } catch (AnnotatorProcessException e) {
          throw new AnalysisEngineProcessException(e);
        }
      }
    }
View Full Code Here
129
130
131
132
133
134
135
136
137
138
139
140
    JFSIndexRepository indexes = jcas.getJFSIndexRepository();
    FSIterator<Annotation> segmentItr = indexes.getAnnotationIndex(
        Segment.type).iterator();
    while (segmentItr.hasNext()) {
      Segment sa = (Segment) segmentItr.next();
      String segmentID = sa.getId();
      if (!skipSegmentsSet.contains(segmentID)) {
        annotateRange(jcas, sa.getBegin(), sa.getEnd());
      }
    }
  }
View Full Code Here
128
129
130
131
132
133
134
135
136
137
138
139
    JFSIndexRepository indexes = jcas.getJFSIndexRepository();
    Iterator<?> sectionItr = indexes.getAnnotationIndex(Segment.type)
        .iterator();
    while (sectionItr.hasNext()) {
      Segment sa = (Segment) sectionItr.next();
      String sectionID = sa.getId();
      if (!skipSegmentsSet.contains(sectionID)) {
        sentenceCount = annotateRange(jcas, text, sa, sentenceCount);
      }
    }
  }
View Full Code Here
146
147
148
149
150
151
152
153
154
155
156
157
158
    JFSIndexRepository indexes = jcas.getJFSIndexRepository();
    Iterator iter= indexes.getAnnotationIndex(Segment.type).iterator();
    String segID=null;
   
    while(iter.hasNext()) {
      Segment seg = (Segment) iter.next();
      if(seg.getBegin()<=begin && seg.getEnd()>=end) {
        segID = seg.getId();
        break;
      }
    }
   
    return segID;
View Full Code Here
761
762
763
764
765
766
767
768
769
770
771
772
773
774
    //check if pse is in Medication subsection
    boolean inMedication = false;
    JFSIndexRepository indexes = jcas.getJFSIndexRepository();
        Iterator saIter= indexes.getAnnotationIndex(Segment.type).iterator();
        while(saIter.hasNext()) {
          Segment sa = (Segment) saIter.next();
          if(sa.getBegin()<pse.ne.getBegin() && sa.getEnd()>pse.ne.getEnd()) {
            Iterator ssIter = FSUtil.getAnnotationsInSpanIterator(
                jcas, SubSectionAnnotation.type, sa.getBegin(), sa.getEnd());
            while(ssIter.hasNext()) {
              SubSectionAnnotation ss = (SubSectionAnnotation) ssIter.next();
              //if(ss.getCoveredText().replaceAll(":","").trim().equalsIgnoreCase("medication"))
                if(ss.getCoveredText().toLowerCase().trim().startsWith("medication"))
                if(ss.getSubSectionHeaderBegin()<pse.ne.getBegin() &&
View Full Code Here
TOP

Related Classes of org.apache.ctakes.typesystem.type.textspan.Segment

  • org.apache.ctakes.clinicalpipeline.ae.ExtractionPrepAnnotator
  • org.apache.ctakes.core.ae.CDASegmentAnnotator
  • org.apache.ctakes.core.ae.SectionSegmentAnnotator
  • org.apache.ctakes.core.ae.SentenceDetector
  • org.apache.ctakes.core.ae.SimpleSegmentAnnotator
  • org.apache.ctakes.core.ae.SimpleSegmentAnnotatorTests
  • org.apache.ctakes.core.ae.SimpleSegmentWithTagsAnnotator
  • org.apache.ctakes.core.ae.TokenizerAnnotator
  • org.apache.ctakes.core.ae.TokenizerAnnotatorPTB
  • org.apache.ctakes.drugner.ae.DrugMentionAnnotator
    • 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.