public List<String> annotatePOSpeech(List<String> tokenized)
throws IOException, TreeTaggerException {
// Point TT4J to the TreeTagger installation directory. The executable
// is expected
// in the "bin" subdirectory - in this example at
// "/opt/treetagger/bin/tree-tagger"
System.setProperty("treetagger.home", treeTaggerFolder);
TreeTaggerWrapper<String> tt = new TreeTaggerWrapper<String>();
final List<String> outputTreeTagger = new ArrayList<String>();
try {
tt.setModel(treeTaggerFolder + "lib/english.par:utf8");
tt.setHandler(
new TokenHandler<String>() {
public void token(String token, String pos, String lemma) {
outputTreeTagger.add(token + "\t" + pos + "\t" + lemma);
}
});
tt.process(tokenized);
} finally {
tt.destroy();
}
return outputTreeTagger;
}
public LemmatiseurHandler(String ch) {
termes = new ArrayList();
termesLem = new ArrayList();
termesPos = new ArrayList();
tt = new TreeTaggerWrapper<String>();
// Lemmatiseur
System.setProperty("treetagger.home", ch);
try {
tt.setModel("french.par:UTF8");
tt.setHandler(
new TokenHandler<String>() {
@Override
public void token(String token, String pos, String lemma) {
// System.out.println(token + "\t" + pos + "\t" + lemma);
termesLem.add(lemma);
termesPos.add(pos);
}
});
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
public void destroy() throws IOException, TreeTaggerException {
// Lemmatisation
tt.destroy();
}
public void process() throws IOException, TreeTaggerException {
// Lemmatisation
tt.process(termes);
}
@Override
public void process(final JCas aJCas) throws AnalysisEngineProcessException {
final CAS cas = aJCas.getCas();
modelProvider.configure(cas);
posMappingProvider.configure(cas);
TreeTaggerWrapper<Token> treetagger = modelProvider.getResource();
try {
List<Token> tokens = new ArrayList<Token>(select(aJCas, Token.class));
final POS pos[] = new POS[tokens.size()];
final Lemma lemma[] = new Lemma[tokens.size()];
// Set the handler creating new UIMA annotations from the analyzed
// tokens
final AtomicInteger count = new AtomicInteger(0);
treetagger.setHandler(
new TokenHandler<Token>() {
@Override
public void token(Token aToken, String aPos, String aLemma) {
synchronized (cas) {
// Add the Part of Speech
if (writePos && aPos != null) {
Type posTag = posMappingProvider.getTagType(aPos);
POS posAnno =
(POS) cas.createAnnotation(posTag, aToken.getBegin(), aToken.getEnd());
posAnno.setPosValue(internTags ? aPos.intern() : aPos);
aToken.setPos(posAnno);
pos[count.get()] = posAnno;
}
// Add the lemma
if (writeLemma && aLemma != null) {
Lemma lemmaAnno = new Lemma(aJCas, aToken.getBegin(), aToken.getEnd());
lemmaAnno.setValue(internTags ? aLemma.intern() : aLemma);
aToken.setLemma(lemmaAnno);
lemma[count.get()] = lemmaAnno;
}
count.getAndIncrement();
}
}
});
treetagger.process(tokens);
// Add the annotations to the indexes
for (int i = 0; i < count.get(); i++) {
if (pos[i] != null) {
pos[i].addToIndexes();
}
if (lemma[i] != null) {
lemma[i].addToIndexes();
}
}
} catch (TreeTaggerException e) {
throw new AnalysisEngineProcessException(e);
} catch (IOException e) {
throw new AnalysisEngineProcessException(e);
}
}
