/** @see org.apache.uima.collection.CollectionReader#getNext(org.apache.uima.cas.CAS) */
public void getNext(CAS aCAS) throws IOException, CollectionException {
JCas jcas;
try {
jcas = aCAS.getJCas();
} catch (CASException e) {
throw new CollectionException(e);
}
// open input stream to file
File file = (File) mFiles.get(mCurrentIndex++);
String text = FileUtils.file2String(file, mEncoding);
// put document in CAS
jcas.setDocumentText(text);
// set language if it was explicitly specified as a configuration parameter
if (mLanguage != null) {
jcas.setDocumentLanguage(mLanguage);
}
// 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();
}
/**
* @param input the text to vectorize
* @param label the label of the text
* @return a dataset with a applyTransformToDestination of weights(relative to impl; could be word
* counts or tfidf scores)
*/
@Override
public DataSet vectorize(File input, String label) {
try {
String text = FileUtils.file2String(input);
return vectorize(text, label);
} catch (Exception e) {
throw new RuntimeException(e);
}
}
/**
* CasConsumer would use tags and features to write output file, evaluate and print precision,
* recall and F-1 measure.
*
* @param arg0
* @throws ResourceProcessException
*/
@Override
public void processCas(CAS arg0) throws ResourceProcessException {
/** convert type of arg0 */
JCas jcas = null;
try {
jcas = arg0.getJCas();
} catch (CASException e1) {
// TODO Auto-generated catch block
e1.printStackTrace();
}
// TODO Auto-generated method stub
FSIterator<Annotation> ite = jcas.getAnnotationIndex(WordTag.type).iterator();
while (ite.hasNext()) {
/** collect features */
String id = ((WordTag) ite.get()).getId();
int begin = ((WordTag) ite.get()).getBegin0();
int end = ((WordTag) ite.get()).getEnd0();
String name = ((WordTag) ite.get()).getName();
/** organize string for output */
report.append(id);
report.append("|");
report.append(begin);
report.append(" ");
report.append(end);
report.append("|");
report.append(name);
report.append("\n");
/** count the length of output string */
count++;
ite.next();
}
result = report.toString();
File sampleOut = new File("src/main/resources/data/sample.out");
try {
testRecall = FileUtils.file2String(sampleOut);
} catch (IOException e1) {
// TODO Auto-generated catch block
e1.printStackTrace();
}
/** split strings from file into sentences */
String[] resultSplit = result.split("\n");
String[] recallSplit = testRecall.split("\n");
PrecisionRecallCalculator(recallSplit, resultSplit);
/** write the output file to the project root */
String path = "hw1-longh.out";
File dirFile = new File(path);
/** make sure no conflict */
if (dirFile.exists()) {
dirFile.delete();
}
try {
/** write file */
BufferedWriter bw1 = new BufferedWriter(new FileWriter(path, true));
bw1.write(report.toString());
bw1.flush();
bw1.close();
} catch (IOException e) {
e.printStackTrace();
}
}