private void addSegs(List segs, Sequence output) {
int segtype = -1;
int startidx = -1;
for (int j = 0; j < output.size(); j++) {
// System.out.println("addSegs j="+j);
Object tag = output.get(j);
segtype = ArrayUtils.indexOf(segmentTags, tag.toString());
if (segtype > -1) {
// System.out.println("...found segment "+tag);
// A new segment is starting
startidx = j;
while (j < output.size() - 1) {
// System.out.println("...inner addSegs j="+j);
j++;
Object nextTag = output.get(j);
if (!nextTag.equals(tag)) {
j--;
segs.add(new Segment(segtype, startidx, j));
segtype = startidx = -1;
break;
}
}
}
}
// Handle end-of-sequence
if (startidx > -1) {
segs.add(new Segment(segtype, startidx, output.size() - 1));
}
}
@Override
@SuppressWarnings("unchecked")
public <E> E[] toArray(E[] a) {
final long cursor = buffer.getCursor();
long s = pollCursor.get() + 1L;
final E[] array;
final int n = (int) (cursor - s);
if (n == 0) {
return a;
}
if (a.length < n) {
array = (E[]) new Object[n];
} else {
array = a;
}
int i = 0;
while (s < cursor) {
array[i++] = (E) buffer.get(cursor).value;
s++;
}
return array;
}
@Override
public void publish(final long sequence, final Sequence upperCursor) {
final long expectedSequence = sequence - 1L;
while (expectedSequence != upperCursor.get()) {
// busy spin
}
upperCursor.set(sequence);
}
@Override
public void publishInterruptibly(final long sequence, final Sequence upperCursor)
throws InterruptedException {
final long expectedSequence = sequence - 1L;
while (expectedSequence != upperCursor.get()) {
if (Thread.interrupted()) throw new InterruptedException();
// busy spin
}
upperCursor.set(sequence);
}
@Override
public T peek() {
long current = buffer.getCursor();
long cachedSequence = pollCursor.get() + 1L;
if (cachedSequence <= current) {
return buffer.get(cachedSequence).value;
}
return null;
}
@Override
public T poll() {
long current = buffer.getCursor();
long cachedSequence = pollCursor.get() + 1L;
if (cachedSequence <= current) {
T v = buffer.get(cachedSequence).value;
if (v != null) {
pollCursor.set(cachedSequence);
}
return v;
}
return null;
}
public Instance pipe(Instance carrier) {
Sequence data = (Sequence) carrier.getData();
Sequence target = (Sequence) carrier.getTarget();
if (data.size() != target.size())
throw new IllegalArgumentException(
"Trying to print into SimpleTagger format, where data and target lengths do not match\n"
+ "data.length = "
+ data.size()
+ ", target.length = "
+ target.size());
int N = data.size();
if (data instanceof TokenSequence) {
throw new UnsupportedOperationException("Not yet implemented.");
} else if (data instanceof FeatureVectorSequence) {
FeatureVectorSequence fvs = (FeatureVectorSequence) data;
Alphabet dict = (fvs.size() > 0) ? fvs.getFeatureVector(0).getAlphabet() : null;
for (int i = 0; i < N; i++) {
Object label = target.get(i);
writer.print(label);
FeatureVector fv = fvs.getFeatureVector(i);
for (int loc = 0; loc < fv.numLocations(); loc++) {
writer.print(' ');
String fname = dict.lookupObject(fv.indexAtLocation(loc)).toString();
double value = fv.valueAtLocation(loc);
// if (!Maths.almostEquals(value, 1.0)) {
// throw new IllegalArgumentException ("Printing to SimpleTagger format: FeatureVector
// not binary at time slice "+i+" fv:"+fv);
// }
writer.print(fname + String.valueOf(value));
}
writer.println();
}
} else {
throw new IllegalArgumentException("Don't know how to print data of type " + data);
}
writer.println();
// writer.print(getDataAlphabet());
return carrier;
}
public EntityConfidence(double conf, boolean corr, Sequence input, int start, int end) {
this.confidence = conf;
this.correct = corr;
StringBuffer buff = new StringBuffer();
if (input != null) {
for (int j = start; j <= end; j++) {
FeatureVector fv = (FeatureVector) input.get(j);
for (int k = 0; k < fv.numLocations(); k++) {
String featureName = fv.getAlphabet().lookupObject(fv.indexAtLocation(k)).toString();
if (featureName.startsWith("W=") && featureName.indexOf("@") == -1) {
buff.append(featureName.substring(featureName.indexOf('=') + 1) + " ");
}
}
}
}
this.entity = buff.toString();
}
@Override
public boolean isEmpty() {
return buffer.getCursor() == pollCursor.get();
}
@Override
public int size() {
return (int) (buffer.getCursor() - pollCursor.get());
}