return MultiFields.getFields(index.createSearcher().getIndexReader());
public LuceneTokenCounter(Analyzer generalAnalyzer) throws IOException { memoryIndex = new MemoryIndex(); IndexSearcher searcher = memoryIndex.createSearcher(); leafReader = (LeafReader)searcher.getIndexReader(); this.generalAnalyzer = generalAnalyzer; }
public DocEngineSearcher(MemoryIndex memoryIndex) { super("percolate", memoryIndex.createSearcher()); this.memoryIndex = memoryIndex; }
throw new IllegalArgumentException("query must not be null"); IndexSearcher searcher = createSearcher(); try { final float[] scores = new float[1]; // inits to 0.0f (no match)
throw new IllegalArgumentException("query must not be null"); IndexSearcher searcher = createSearcher(); try { final float[] scores = new float[1]; // inits to 0.0f (no match)
return MultiFields.getFields(index.createSearcher().getIndexReader());
return MultiFields.getFields(index.createSearcher().getIndexReader());
return MultiFields.getFields(index.createSearcher().getIndexReader());
private SingletonDocumentBatch(Collection<InputDocument> documents, Similarity similarity) { super(documents, similarity); assert documents.size() == 1; memoryindex.setSimilarity(similarity); for (InputDocument doc : documents) { for (IndexableField field : doc.getDocument()) { memoryindex.addField(field, doc.getAnalyzers()); } } memoryindex.freeze(); reader = (LeafReader) memoryindex.createSearcher().getIndexReader(); }
public void buildTermVector(int docid) throws IOException { /* */ Set<String> fieldList = new HashSet<>(); fieldList.add("content"); Document doc = reader.document(docid, fieldList); MemoryIndex mi = MemoryIndex.fromDocument(doc, new StandardAnalyzer()); IndexReader mr = mi.createSearcher().getIndexReader(); Terms t = mr.leaves().get(0).reader().terms("content"); if ((t != null) && (t.size()>0)) { TermsEnum te = t.iterator(); BytesRef term = null; System.out.println(t.size()); while ((term = te.next()) != null) { System.out.println("BytesRef: " + term.utf8ToString()); System.out.println("docFreq: " + te.docFreq()); System.out.println("totalTermFreq: " + te.totalTermFreq()); } } }
private static HashSet<String> performSearch(Analyzer a) throws IOException { HashSet<String> results = new HashSet<>(); for (File file : getTestFiles()) { MemoryIndex memoryIndex = new MemoryIndex(true); final List<String> lines = Files.readAllLines(file.toPath(), Charset.forName("UTF-8")); memoryIndex.addField("title", lines.get(0), a); StringBuilder sb = new StringBuilder(); for (String line : lines) { sb.append(line); } memoryIndex.addField("content", sb.toString(), a); IndexSearcher searcher = memoryIndex.createSearcher(); ExistsCollector collector = new ExistsCollector(); searcher.search(new TermQuery(new Term("content", "אני")), collector); if (collector.exists()) { results.add(file.getName()); } } return results; }
private Fields generateTermVectors(Collection<GetField> getFields, boolean withOffsets, @Nullable Map<String, String> perFieldAnalyzer, Set<String> fields) throws IOException { /* store document in memory index */ MemoryIndex index = new MemoryIndex(withOffsets); for (GetField getField : getFields) { String field = getField.getName(); if (fields.contains(field) == false) { // some fields are returned even when not asked for, eg. _timestamp continue; } Analyzer analyzer = getAnalyzerAtField(field, perFieldAnalyzer); for (Object text : getField.getValues()) { index.addField(field, text.toString(), analyzer); } } /* and read vectors from it */ return MultiFields.getFields(index.createSearcher().getIndexReader()); }
IndexReader mr = mi.createSearcher().getIndexReader();
} else { MemoryIndex memoryIndex = MemoryIndex.fromDocument(docs.get(0).rootDoc(), analyzer, true, false); docSearcher = memoryIndex.createSearcher(); docSearcher.setQueryCache(null);
} else { MemoryIndex memoryIndex = MemoryIndex.fromDocument(docs.get(0).rootDoc(), analyzer, true, false); docSearcher = memoryIndex.createSearcher(); docSearcher.setQueryCache(null);
memoryIndices[i] = indexDoc(d, analyzer, memoryIndex).createSearcher().getIndexReader();
new OffsetLimitTokenFilter(tokenStream, maxDocCharsToAnalyze)); final IndexSearcher searcher = indexer.createSearcher();