package org.apache.lucene.search.spans; /* * Licensed to the Apache Software Foundation (ASF) under one or more * contributor license agreements. See the NOTICE file distributed with * this work for additional information regarding copyright ownership. * The ASF licenses this file to You under the Apache License, Version 2.0 * (the "License"); you may not use this file except in compliance with * the License. You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */ import org.apache.lucene.index.AtomicReaderContext; import org.apache.lucene.index.Fields; import org.apache.lucene.index.Term; import org.apache.lucene.index.DocsAndPositionsEnum; import org.apache.lucene.index.TermContext; import org.apache.lucene.index.TermState; import org.apache.lucene.index.Terms; import org.apache.lucene.index.TermsEnum; import org.apache.lucene.util.Bits; import org.apache.lucene.util.ToStringUtils; import java.io.IOException; import java.util.Map; import java.util.Set; /** Matches spans containing a term. */ public class SpanTermQuery extends SpanQuery { protected Term term; /** Construct a SpanTermQuery matching the named term's spans. */ public SpanTermQuery(Term term) { this.term = term; } /** Return the term whose spans are matched. */ public Term getTerm() { return term; } @Override public String getField() { return term.field(); } @Override public void extractTerms(Set<Term> terms) { terms.add(term); } @Override public String toString(String field) { StringBuilder buffer = new StringBuilder(); if (term.field().equals(field)) buffer.append(term.text()); else buffer.append(term.toString()); buffer.append(ToStringUtils.boost(getBoost())); return buffer.toString(); } @Override public int hashCode() { final int prime = 31; int result = super.hashCode(); result = prime * result + ((term == null) ? 0 : term.hashCode()); return result; } @Override public boolean equals(Object obj) { if (this == obj) return true; if (!super.equals(obj)) return false; if (getClass() != obj.getClass()) return false; SpanTermQuery other = (SpanTermQuery) obj; if (term == null) { if (other.term != null) return false; } else if (!term.equals(other.term)) return false; return true; } @Override public Spans getSpans(final AtomicReaderContext context, Bits acceptDocs, Map<Term,TermContext> termContexts) throws IOException { TermContext termContext = termContexts.get(term); final TermState state; if (termContext == null) { // this happens with span-not query, as it doesn't include the NOT side in extractTerms() // so we seek to the term now in this segment..., this sucks because its ugly mostly! final Fields fields = context.reader().fields(); if (fields != null) { final Terms terms = fields.terms(term.field()); if (terms != null) { final TermsEnum termsEnum = terms.iterator(null); if (termsEnum.seekExact(term.bytes())) { state = termsEnum.termState(); } else { state = null; } } else { state = null; } } else { state = null; } } else { state = termContext.get(context.ord); } if (state == null) { // term is not present in that reader return TermSpans.EMPTY_TERM_SPANS; } final TermsEnum termsEnum = context.reader().terms(term.field()).iterator(null); termsEnum.seekExact(term.bytes(), state); final DocsAndPositionsEnum postings = termsEnum.docsAndPositions(acceptDocs, null, DocsAndPositionsEnum.FLAG_PAYLOADS); if (postings != null) { return new TermSpans(postings, term); } else { // term does exist, but has no positions throw new IllegalStateException("field \"" + term.field() + "\" was indexed without position data; cannot run SpanTermQuery (term=" + term.text() + ")"); } } }