/** Returns space-separated words that constitute this phrase. */
public CharSequence getPhrase(int index) {
StringBuilder sb = new StringBuilder();
for (int i = 0; i < wordIndices[index].length; i++) {
if (i > 0) sb.append(" ");
sb.append(new String(allWords.image[wordIndices[index][i]]));
}
return sb;
}
/** For debugging purposes. */
@Override
public String toString() {
StringWriter sw = new StringWriter();
TabularOutput t = new TabularOutput(sw);
t.flushEvery(Integer.MAX_VALUE);
t.addColumn("#");
t.addColumn("token").alignLeft();
t.addColumn("type");
t.addColumn("fieldIndex");
t.addColumn("=>field").alignLeft();
t.addColumn("docIdx");
t.addColumn("wordIdx");
t.addColumn("=>word").alignLeft();
for (int i = 0; i < image.length; i++, t.nextRow()) {
t.rowData(
i,
image[i] == null ? "<null>" : new String(image[i]),
type[i],
fieldIndex[i],
fieldIndex[i] >= 0 ? allFields.name[fieldIndex[i]] : null,
documentIndex[i],
wordIndex[i],
wordIndex[i] >= 0 ? new String(allWords.image[wordIndex[i]]) : null);
}
if (suffixOrder != null) {
t = new TabularOutput(sw);
t.addColumn("#");
t.addColumn("sa");
t.addColumn("lcp");
t.addColumn("=>words").alignLeft();
sw.append("\n");
final StringBuilder suffixImage = new StringBuilder();
for (int i = 0; i < suffixOrder.length; i++, t.nextRow()) {
t.rowData(i, suffixOrder[i], lcp[i]);
int windowLength = 5;
for (int j = suffixOrder[i],
max = Math.min(suffixOrder[i] + windowLength, wordIndex.length);
j < max; ) {
suffixImage
.append(wordIndex[j] >= 0 ? new String(allWords.image[wordIndex[j]]) : "|")
.append(" ");
if (++j == max && j != wordIndex.length) suffixImage.append(" [...]");
}
t.rowData(suffixImage.toString());
suffixImage.setLength(0);
}
sw.append("\n");
}
t.flush();
sw.append("\n");
return sw.toString();
}
/**
* Build a cluster's label from suffix tree edge indices, including some debugging and diagnostic
* information.
*/
@SuppressWarnings("unused")
private String buildDebugLabel(int[] phraseIndices) {
final StringBuilder b = new StringBuilder();
String sep = "";
int k = 0;
final short[] tokenTypes = context.allWords.type;
for (int i = 0; i < phraseIndices.length; i += 2) {
for (int j = phraseIndices[i]; j <= phraseIndices[i + 1]; j++, k++) {
b.append(sep);
final int termIndex = sb.input.get(j);
b.append(context.allWords.image[termIndex]);
if (TokenTypeUtils.isCommon(tokenTypes[termIndex])) b.append("[S]");
sep = " ";
}
sep = "_";
}
return b.toString();
}