@Test
public void testEvaluator() throws IOException, URISyntaxException {
DictionaryNameFinder nameFinder = new DictionaryNameFinder(createDictionary());
TokenNameFinderEvaluator evaluator =
new TokenNameFinderEvaluator(nameFinder, new NameEvaluationErrorListener());
ObjectStream<NameSample> sample = createSample();
evaluator.evaluate(sample);
sample.close();
FMeasure fmeasure = evaluator.getFMeasure();
assertTrue(fmeasure.getFMeasure() == 1);
assertTrue(fmeasure.getRecallScore() == 1);
}
public void run(String[] args) {
Parameters params = validateAndParseParams(args, Parameters.class);
File testData = new File(params.getCensusData());
File dictOutFile = new File(params.getDict());
CmdLineUtil.checkInputFile("Name data", testData);
CmdLineUtil.checkOutputFile("Dictionary file", dictOutFile);
FileInputStream sampleDataIn = CmdLineUtil.openInFile(testData);
ObjectStream<StringList> sampleStream =
new NameFinderCensus90NameStream(sampleDataIn, Charset.forName(params.getEncoding()));
Dictionary mDictionary;
try {
System.out.println("Creating Dictionary...");
mDictionary = createDictionary(sampleStream);
} catch (IOException e) {
throw new TerminateToolException(
-1, "IO error while reading training data or indexing data: " + e.getMessage(), e);
} finally {
try {
sampleStream.close();
} catch (IOException e) {
// sorry this can fail..
}
}
System.out.println("Saving Dictionary...");
OutputStream out = null;
try {
out = new FileOutputStream(dictOutFile);
mDictionary.serialize(out);
} catch (IOException e) {
throw new TerminateToolException(
-1, "IO error while writing dictionary file: " + e.getMessage(), e);
} finally {
if (out != null)
try {
out.close();
} catch (IOException e) {
// file might be damaged
throw new TerminateToolException(
-1, "Attention: Failed to correctly write dictionary:" + e.getMessage(), e);
}
}
}
/**
* Creates a dictionary with all names from the sample data.
*
* @return a dictionary
* @throws IOException
* @throws URISyntaxException
*/
private static Dictionary createDictionary() throws IOException, URISyntaxException {
ObjectStream<NameSample> sampleStream = createSample();
NameSample sample = sampleStream.read();
List<String[]> entries = new ArrayList<String[]>();
while (sample != null) {
Span[] names = sample.getNames();
if (names != null && names.length > 0) {
String[] toks = sample.getSentence();
for (Span name : names) {
String[] nameToks = new String[name.length()];
System.arraycopy(toks, name.getStart(), nameToks, 0, name.length());
entries.add(nameToks);
}
}
sample = sampleStream.read();
}
sampleStream.close();
Dictionary dictionary = new Dictionary(true);
for (String[] entry : entries) {
StringList dicEntry = new StringList(entry);
dictionary.put(dicEntry);
}
return dictionary;
}
public void close() throws IOException {
adSentenceStream.close();
}
