private CText getTaxonomyList(final String inputText, final String title, boolean breakdown) {
/*
* Step 1: Create a document model
*/
CText document = new CText(title);
/*
* Step 2:Extract the N-Grams from the document
*/
CNGramsExtractor nGramsExtract = new CNGramsExtractor();
// INFO
System.out.println("Last execution");
if (nGramsExtract.extract(document, inputText)) {
document.setState(CText.E_STATES.NGRAMS);
System.out.println("NGram extracted");
/*
* Step 3: Extract Composite and semantics
*/
CTaxonomyExtractor taxonomyExtractor = new CTaxonomyExtractor(_taxonomyConnection, breakdown);
if (taxonomyExtractor.extract(document)) {
document.setState(CText.E_STATES.TAXONOMY);
}
}
return document;
}
private CNGramsStats extractFragment(final String content, String label)
throws SemanticAnalysisException {
int nGramRank = -1;
CText document = new CText(content);
CNGramsStats nGramsFrequencyStats = new CNGramsStats(label);
CNGramsGenerator nGramsExtractor = new CNGramsGenerator(nGramsFrequencyStats);
if (nGramsExtractor.extract(document, content)) {
nGramsFrequencyStats = nGramsExtractor.getNGramsFrequencyStats();
if (nGramsFrequencyStats != null) {
NTaxonomiesConn taxonomyConnection =
CTaxonomyConnectionsPool.getInstance().getLabelsAndCatsConnection();
CTaxonomyExtractor taxonomyExtractor = new CTaxonomyExtractor(taxonomyConnection);
if (taxonomyExtractor.extract(document)) {
/*
* Walk through the list of taxonomyInstance nouns from
* this document document to extract statistics for the label.
*/
int rank = 0;
/*
for( CTaxonomyInstance taxonomyInstance : document.getObjectsMap().values()) {
if( label.compareTo(taxonomyInstance.getLabel()) == 0) {
nGramRank = rank;
break;
}
rank++;
}
*/
}
}
}
return (nGramRank >= 0) ? nGramsFrequencyStats : null;
}