/**
* @param targetTerm
* @param sourceFile
* @param termWindowSize
* @param pipe
*/
private static InstanceList readConcordanceFileToInstanceList(
String targetTerm,
String sourceFile,
int termWindowSize,
Pipe pipe,
boolean useCollocationalVector) {
InstanceList instanceList = new InstanceList(pipe);
BufferedReader in = null;
try {
in = new BufferedReader(new FileReader(sourceFile));
int incomplete = 0;
String str;
while ((str = in.readLine()) != null) {
String[] lineArray = str.split(";");
if (lineArray.length != 4) {
System.out.println(
"WARNING: Skipping possibly invalid CSV line " + str + " in file " + sourceFile);
continue;
}
String docID = lineArray[0].replace("Doc ID: ", "").trim();
String lineID = lineArray[1].replace("Line ID: ", "").trim();
String instanceID = (docID + "_" + lineID).replaceAll(" ", "_");
String senseID = lineArray[2].replace("DOE sense ID: ", "").trim();
String text = lineArray[3];
if (targetTerm.equals("faeder")) targetTerm = "fæder";
ArrayList<String> data = corpus.getWindowTokens(targetTerm, docID, lineID, termWindowSize);
if (data.size() != 2 * termWindowSize) {
incomplete++;
System.out.println("WARNING: Incomplete token list " + incomplete + " found " + data);
}
if (useCollocationalVector) {
System.out.println("Converting data to collocational vector: \n\t" + data);
int i = termWindowSize * (-1);
int index = i + termWindowSize;
while (i <= termWindowSize && index < data.size()) {
if (i != 0) {
data.set(index, data.get(index) + "_" + i); // skip position of target term
index++;
}
i++;
}
System.out.println("Converting data to collocational vector...DONE\n\t" + data);
}
String dataStr =
data.toString().replace(", ", " ").replace("[", "").replace("]", "").replace(".", "");
Instance trainingInstance = new Instance(dataStr, senseID, instanceID, text);
instanceList.addThruPipe(trainingInstance);
}
in.close();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} finally {
if (in != null)
try {
in.close();
} catch (IOException e1) {
}
}
return instanceList;
}
