Package org.apache.uima.examples

Examples of org.apache.uima.examples.SourceDocumentInformation

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
141
142
143
144
145
146
147
148
149
150
151
  private String getCasSourceUri(JCas jcas) {
    Iterator 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
133
134
135
136
137
138
139
140
141
142
143
144
    // 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
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
    // 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
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
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
      // 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
131
132
133
134
135
136
137
138
139
140
141
142
143
        if (it.hasNext()) {
          // get the output file name from the annotation in the CAS ...
          // ... note this is a little flakey if processing an XCAS file,
          // which could have such an annotation with a different name than the input XCAS file!
          // So we don't do this if XCAS output is specified.
          SourceDocumentInformation fileLoc = (SourceDocumentInformation) it.next();
          File inFile;
          inFile = new File(new URL(fileLoc.getUri()).getPath());
          outFile = new File(mOutputDir, inFile.getName());
        }
      } catch (CASRuntimeException e) {
        // default Sofa name does not exist, use default processing below
      } catch (CASException e) {
View Full Code Here
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
      // 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 {
        XCASDeserializer.deserialize(fis, aCAS);
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
    // 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
64
65
66
67
68
69
70
71
72
73
74
75
    {
      logger.info("AnnotationIndex's iterator returned empty iterator. continuing...");
      return;
    }
   
    SourceDocumentInformation sdi = (SourceDocumentInformation)iterator.next();
    String fullUriString = sdi.getUri();
    URI fullUri;
    URL fullUrl;
    try
    {
      fullUri = new URI(fullUriString);
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.