Package org.apache.uima.examples

Examples of org.apache.uima.examples.SourceDocumentInformation

130
131
132
133
134
135
136
137
138
139
140
141
142
        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
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
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
      // 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
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
    // 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();
        }
        outFile = new File(mOutputDir, outFileName);
      } catch (URISyntaxException e) {
        // invalid URL, use default processing below
      }
View Full Code Here
157
158
159
160
161
162
163
164
165
166
167
168
    // 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
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
    // 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();
        }
        outFile = new File(mOutputDir, outFileName);
      } catch (MalformedURLException e1) {
        // invalid URL, use default processing below
      }
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
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
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
    // 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();
        }
        outFile = new File(mOutputDir, outFileName);
      } catch (MalformedURLException e1) {
        // invalid URL, use default processing below
      }
View Full Code Here
130
131
132
133
134
135
136
137
138
139
140
141
142
        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
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.