Package org.apache.uima.examples

Examples of org.apache.uima.examples.SourceDocumentInformation

93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
    // retreive the filename of the input file from the CAS
    FSIterator it = jcas.getAnnotationIndex(SourceDocumentInformation.type).iterator();
    File outFile = null;
    if (it.hasNext()) {
      SourceDocumentInformation fileLoc = (SourceDocumentInformation) it.next();
      File inFile;
      try {
        inFile = new File(new URL(fileLoc.getUri()).getPath());
        String outFileName = inFile.getName();
        if (fileLoc.getOffsetInSource() > 0) {
          outFileName += ("_" + fileLoc.getOffsetInSource());
        }
        outFileName += ".xmi";
        outFile = new File(mOutputDir, outFileName);
        modelFileName = mOutputDir.getAbsolutePath() + "/" + inFile.getName() + ".ecore";
      } catch (MalformedURLException e1) {
View Full Code Here
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
      // Also store location of source document in CAS. This information is critical
      // if CAS Consumers will need to know where the original document contents are located.
      // For example, the Semantic Search CAS Indexer writes this information into the
      // search index that it creates, which allows applications that use the search index to
      // locate the documents that satisfy their semantic queries.
      SourceDocumentInformation srcDocInfo = new SourceDocumentInformation(jcas);
      srcDocInfo.setUri(file.getAbsoluteFile().toURL().toString());
      srcDocInfo.setOffsetInSource(0);
      srcDocInfo.setDocumentSize((int) file.length());
      srcDocInfo.setLastSegment(mCurrentIndex == mFiles.size());
      srcDocInfo.addToIndexes();
    }
    // XCAS input files
    else {
      try {
        if (mXCAS.equalsIgnoreCase("xmi")) {
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
    mPos = 0;
    // retreive the filename of the input file from the CAS so that it can be added
    // to each segment
    FSIterator it = aJCas.getAnnotationIndex(SourceDocumentInformation.type).iterator();
    if (it.hasNext()) {
      SourceDocumentInformation fileLoc = (SourceDocumentInformation) it.next();
      mDocUri = fileLoc.getUri();
    } else {
      mDocUri = null;
    }
  }
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
    try {
      jcas.setDocumentText(mDoc.substring(mPos, breakAt));
      // if original CAS had SourceDocumentInformation, also add SourceDocumentInformatio
      // to each segment
      if (mDocUri != null) {
        SourceDocumentInformation sdi = new SourceDocumentInformation(jcas);
        sdi.setUri(mDocUri);
        sdi.setOffsetInSource(mPos);
        sdi.setDocumentSize(breakAt - mPos);
        sdi.addToIndexes();

        if (breakAt == mDoc.length()) {
          sdi.setLastSegment(true);
        }
      }

      mPos = breakAt;
      return jcas;
View Full Code Here
89
90
91
92
93
94
95
96
97
98
99
100
101
102
    // retreive the filename of the input file from the CAS
    FSIterator it = jcas.getAnnotationIndex(SourceDocumentInformation.type).iterator();
    File outFile = null;
    if (it.hasNext()) {
      SourceDocumentInformation fileLoc = (SourceDocumentInformation) it.next();
      File inFile;
      try {
        inFile = new File(new URL(fileLoc.getUri()).getPath());
        outFile = new File(mOutputDir, inFile.getName());
      } catch (MalformedURLException e1) {
        // invalid URL, use default processing below
      }
    }
View Full Code Here
110
111
112
113
114
115
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
      mBuf.append(mDoc.substring(mCurIndex));
      if (mJCases[mActiveJCas] == null) {
        mJCases[mActiveJCas] = getEmptyJCas();
      }
      // add SourceDocumentInformation to active JCas
      SourceDocumentInformation sdi = new SourceDocumentInformation(mJCases[mActiveJCas]);
      sdi.setBegin(begin);
      sdi.setEnd(mBuf.length());
      sdi.setUri(getCasSourceUri(mCurrentInputCas));
      sdi.addToIndexes();
      mHasNext = false; // we need to see another input CAS before we can create output
      mCurIndex = 0;
    } else // yes, newline
    {
      // append doc up to newline
      int begin = mBuf.length(); // record start offset of new text
      mBuf.append(mDoc.substring(mCurIndex, nlIndex));
      if (mJCases[mActiveJCas] == null) {
        mJCases[mActiveJCas] = getEmptyJCas();
      }
      // add SourceDocumentInformation to active JCas
      SourceDocumentInformation sdi = new SourceDocumentInformation(mJCases[mActiveJCas]);
      sdi.setBegin(begin);
      sdi.setEnd(mBuf.length());
      sdi.setUri(getCasSourceUri(mCurrentInputCas));
      sdi.addToIndexes();
      // set doc text
      mJCases[mActiveJCas].setDocumentText(mBuf.toString());
      mBuf.setLength(0);
      mCurIndex = nlIndex + 1;
      mHasNext = true; // ready to output!
View Full Code Here
143
144
145
146
147
148
149
150
151
152
153
  private String getCasSourceUri(JCas jcas) {
    Iterator<Annotation> iter = jcas.getJFSIndexRepository().getAnnotationIndex(SourceDocumentInformation.type)
            .iterator();
    if (iter.hasNext()) {
      SourceDocumentInformation sdi = (SourceDocumentInformation) iter.next();
      return sdi.getUri();
    } else {
      return "unknown";
    }
  }
View Full Code Here
131
132
133
134
135
136
137
138
139
140
141
142
    // Also store location of source document in CAS. This information is critical
    // if CAS Consumers will need to know where the original document contents are located.
    // For example, the Semantic Search CAS Indexer writes this information into the
    // search index that it creates, which allows applications that use the search index to
    // locate the documents that satisfy their semantic queries.
    SourceDocumentInformation srcDocInfo = new SourceDocumentInformation(jcas);
    srcDocInfo.setUri(file.getAbsoluteFile().toURL().toString());
    srcDocInfo.setOffsetInSource(0);
    srcDocInfo.setDocumentSize((int) file.length());
    srcDocInfo.setLastSegment(mCurrentIndex == mFiles.size());
    srcDocInfo.addToIndexes();
  }
View Full Code Here
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
    // retrieve the filename of the input file from the CAS
    FSIterator it = jcas.getAnnotationIndex(SourceDocumentInformation.type).iterator();
    File outFile = null;
    if (it.hasNext()) {
      SourceDocumentInformation fileLoc = (SourceDocumentInformation) it.next();
      File inFile;
      try {
        // handle blanks in path
        // https://issues.apache.org/jira/browse/UIMA-1748
        // use 3 arg form of URI Constructor to properly quote any otherwise illegal chars such as blank
        // https://issues.apache.org/jira/browse/UIMA-2097
        URI uri = UriUtils.quote(fileLoc.getUri());
        inFile = new File(uri);
        String outFileName = inFile.getName();
        if (fileLoc.getOffsetInSource() > 0) {
          outFileName += ("_" + fileLoc.getOffsetInSource());
        }
        outFileName += ".xmi";
        outFile = new File(mOutputDir, outFileName);
        modelFileName = mOutputDir.getAbsolutePath() + "/" + inFile.getName() + ".ecore";
      } catch (URISyntaxException e) {
View Full Code Here
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
      mBuf.append(mDoc.substring(mCurIndex));
      if (mJCases[mActiveJCas] == null) {
        mJCases[mActiveJCas] = getEmptyJCas();
      }
      // add SourceDocumentInformation to active JCas
      SourceDocumentInformation sdi = new SourceDocumentInformation(mJCases[mActiveJCas]);
      sdi.setBegin(begin);
      sdi.setEnd(mBuf.length());
      sdi.setUri(getCasSourceUri(mCurrentInputCas));
      sdi.addToIndexes();
      mHasNext = false; // we need to see another input CAS before we can create output
      mCurIndex = 0;
    } else // yes, newline
    {
      // append doc up to newline
      int begin = mBuf.length(); // record start offset of new text
      mBuf.append(mDoc.substring(mCurIndex, nlIndex));
      if (mJCases[mActiveJCas] == null) {
        mJCases[mActiveJCas] = getEmptyJCas();
      }
      // add SourceDocumentInformation to active JCas
      SourceDocumentInformation sdi = new SourceDocumentInformation(mJCases[mActiveJCas]);
      sdi.setBegin(begin);
      sdi.setEnd(mBuf.length());
      sdi.setUri(getCasSourceUri(mCurrentInputCas));
      sdi.addToIndexes();
      // set doc text
      mJCases[mActiveJCas].setDocumentText(mBuf.toString());
      mBuf.setLength(0);
      mCurIndex = nlIndex + 1;
      mHasNext = true; // ready to output!
View Full Code Here
TOP

Related Classes of org.apache.uima.examples.SourceDocumentInformation

  • org.apache.uima.ae.noop.SimpleAnnotator
  • org.apache.uima.analysis_engine.impl.NewlineResegmenter
  • org.apache.uima.examples.casMultiplier.SimpleTextMerger
  • org.apache.uima.examples.casMultiplier.SimpleTextSegmenter
  • org.apache.uima.examples.cpe.AnnotationPrinter
  • org.apache.uima.examples.cpe.FileSystemCollectionReader
  • org.apache.uima.examples.cpe.InlineXmlCasConsumer
  • org.apache.uima.examples.cpe.PersonTitleDBWriterCasConsumer
  • org.apache.uima.examples.cpe.XCasWriterCasConsumer
  • org.apache.uima.examples.xmi.XmiEcoreCasConsumer
    • 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.