/** * {@inheritDoc}. * This implementation only places content in the runs in memory, which will eventually be flushed to disk. */ @Override protected void indexDocument(Map<String,String> docProperties, DocumentPostingList termsInDocument) throws Exception { if (seenDocnos.contains(docProperties.get("docno"))) return; else seenDocnos.add(docProperties.get("docno")); if (termsInDocument.getDocumentLength() > 0) { numberOfDocsSinceCheck++; numberOfDocsSinceFlush++; checkFlush(); mp.addTerms(termsInDocument, currentId); DocumentIndexEntry die = termsInDocument.getDocumentStatistics(); docIndexBuilder.addEntryToBuffer((FieldScore.FIELDS_COUNT > 0) ? die : new SimpleDocumentIndexEntry(die)); metaBuilder.writeDocumentEntry(docProperties); currentId++; numberOfDocuments++; } }
/** Return a DocumentIndexEntry for this document */ public DocumentIndexEntry getDocumentStatistics() { DocumentIndexEntry die = new BasicDocumentIndexEntry(); die.setDocumentLength(this.getDocumentLength()); die.setNumberOfEntries(this.getNumberOfPointers()); return die; }
document.addDocument(docContents.getDocumentLength()); stats.update(1, docContents.getDocumentLength(), docContents.termSet().length); stats.updateUniqueTerms(lexicon.numberOfEntries());
/** * {@inheritDoc}. * This implementation only places content in the runs in memory, which will eventually be flushed to disk. */ @Override protected void indexDocument(Map<String,String> docProperties, DocumentPostingList termsInDocument) throws Exception { if (termsInDocument.getDocumentLength() > 0) { numberOfDocsSinceCheck++; numberOfDocsSinceFlush++; checkFlush(); mp.addTerms(termsInDocument, currentId); DocumentIndexEntry die = termsInDocument.getDocumentStatistics(); docIndexBuilder.addEntryToBuffer((FieldScore.FIELDS_COUNT > 0) ? die : new SimpleDocumentIndexEntry(die)); metaBuilder.writeDocumentEntry(docProperties); currentId++; numberOfDocuments++; } }
docContents.getDocumentLength() + document.getDocumentLength(docid)); stats.update(0, docContents.getDocumentLength(), pointers); stats.updateUniqueTerms(lexicon.numberOfEntries());
if (termsInDocument.getDocumentLength() == 0)
document.addDocument(docContents.getDocumentLength()); stats.update(1, docContents.getDocumentLength(), docContents.termSet().length); stats.updateUniqueTerms(lexicon.numberOfEntries());
if (termsInDocument.getDocumentLength() == 0)
if (termsInDocument.getDocumentLength() == 0) {
if (termsInDocument.getDocumentLength() == 0)
((MemoryDocumentIndexFields) document).addDocument(docContents.getDocumentLength(), ((FieldDocumentIndexEntry) docContents.getDocumentStatistics()).getFieldLengths()); stats.update(1, docContents.getDocumentLength(), docContents.termSet().length); stats.updateUniqueTerms(lexicon.numberOfEntries()); stats.updateFields(fieldcounts);