private static void execSearchDoeCorpus(String[] args) {
String searchString = args[1];
boolean interactive = false;
// Load corpus first
execParseDoeCorpus(false /* doSave */);
// Check mode
if (args.length > 2) if (args[2].equals("i")) interactive = true;
// Search for string
HashMap<String, ArrayList<DOECorpusLine>> matches = corpus.getConcordances(searchString);
printSearchResults(searchString, matches);
if (interactive) {
do {
System.out.println("Enter the sear term here (or QUIT to exit):");
Scanner scanIn = new Scanner(System.in);
searchString = scanIn.nextLine();
scanIn.close();
if (!("QUIT".equals(searchString))) {
matches = corpus.getConcordances(searchString);
printSearchResults(searchString, matches);
}
} while (!("QUIT".equals(searchString)));
}
}
private static void execFindConcordancesDoeCorpus(String[] args) {
int limit = 1000000;
if (args.length > 2) limit = 100;
String searchString = args[1];
execParseDoeCorpus(false /* doSave */);
ArrayList<DOECorpusLine> allLines = new ArrayList<DOECorpusLine>();
HashMap<String, ArrayList<DOECorpusLine>> matches = corpus.getConcordances(searchString);
for (ArrayList<DOECorpusLine> list : matches.values()) allLines.addAll(list);
if (allLines.size() > limit) allLines = getRandomSelectionFromList(allLines, limit);
System.out.println("Concordances for search term " + searchString + " with limit " + limit);
for (DOECorpusLine line : allLines) {
System.out.println(
"Doc ID: "
+ line.getShortTitle()
+ "; Line ID: "
+ line.getLineID()
+ "; "
+ line.getLine());
}
}
private static void execConvertToMalletFormat(String[] args) {
if (args.length != 5)
throw new IllegalArgumentException(
"There should be 5 arguments, but I found only " + args.length);
// Load corpus first
execParseDoeCorpus(false /* doSave */);
String targetTerm = args[1];
String sourceFile = args[2];
String targetFile = args[3];
int termWindowSize = Integer.parseInt(args[4]);
System.out.println("Reading concordance file for target term '" + targetTerm + "'...");
System.out.println("File path: " + sourceFile);
BufferedReader in = null;
String malletFileString = "";
try {
in = new BufferedReader(new FileReader(sourceFile));
String str;
while ((str = in.readLine()) != null) {
String[] lineArray = str.split(";");
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];
String data =
corpus.getWindowTokensAsSpaceSeparatedString(targetTerm, docID, lineID, termWindowSize);
if (data != null) {
String malletInstanceLine = instanceID + " " + senseID + " " + data + "\n";
malletFileString += malletInstanceLine;
}
}
in.close();
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
System.out.println("Writing result to Mallet file...");
System.out.println("File path: " + targetFile);
PrintWriter out;
try {
out = new PrintWriter(targetFile);
out.println(malletFileString);
out.close();
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
System.out.println("Writing result to Mallet file...DONE");
}
private static void execFindOccurrencesDoeCorpus(String[] args) {
int minCount = Integer.parseInt(args[1]);
int maxCount = Integer.parseInt(args[2]);
int minLen = Integer.parseInt(args[3]);
// Load corpus first
execParseDoeCorpus(false /* doSave */);
corpus.findTypesWithMinMaxOccurrenceAndMinLength(minCount, maxCount, minLen);
}
private static void execParseDoeCorpus(boolean doSave) {
if (corpus != null) {
System.out.println("Using pre-loaded corpus.");
return;
}
DOECorpusReader corpusReader =
new DOECorpusReader(DOE_CORPUS_SOURCE_DIR, DOE_CORPUS_SAVE_DIR, doSave);
corpus = corpusReader.loadFromHTML();
if (doSave) corpus.saveToFile(DOE_CORPUS_SAVE_DIR + "doe.corpus");
}
private static void execPrintTypesDoeCorpus(String[] args) {
boolean ascending = true;
// Ascending or descending?
if (args.length > 1)
if ("asc".equalsIgnoreCase(args[1])) ascending = true;
else if ("desc".equalsIgnoreCase(args[1])) ascending = false;
else throw new IllegalArgumentException("Second parameter must be either 'asc' or 'desc'");
// Save to file?
String path = "";
List<String> lines = null;
boolean writeToFile = false;
if (args.length > 2) {
path = args[2];
lines = new ArrayList<>();
writeToFile = true;
}
// Load corpus first
execParseDoeCorpus(false /* doSave */);
HashMap<String, Integer> types = corpus.getVocabulary();
Map<String, Integer> sortedTypes = ListAndMapUtil.sortByComparator(types, ascending);
for (String key : sortedTypes.keySet()) {
String line = key + ";" + sortedTypes.get(key);
System.out.println(line);
if (writeToFile) lines.add(line);
}
// Save to file
if (writeToFile)
try {
FileUtils.writeLines(new File(path), lines);
} catch (IOException e) {
System.out.println("Error while trying to write to file " + path);
e.printStackTrace();
}
}
private static void execLoadDoeCorpus(ArrayList<String> params) {
DOECorpus corpus = DOECorpus.loadFromFile(DOE_CORPUS_SAVE_DIR + "doe.corpus");
}
/**
* @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;
}
