org.apache.solr.search.TermsQParserPlugin Maven / Gradle / Ivy
Show all versions of solr-core Show documentation
/*
* 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.
*/
package org.apache.solr.search;
import java.util.Arrays;
import java.util.Locale;
import java.util.regex.Pattern;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.AutomatonQuery;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.ConstantScoreQuery;
import org.apache.lucene.search.DocValuesTermsQuery;
import org.apache.lucene.search.MatchNoDocsQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TermInSetQuery;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.util.ArrayUtil;
import org.apache.lucene.util.BytesRef;
import org.apache.lucene.util.BytesRefBuilder;
import org.apache.lucene.util.automaton.Automata;
import org.apache.lucene.util.automaton.Automaton;
import org.apache.solr.common.params.SolrParams;
import org.apache.solr.request.SolrQueryRequest;
import org.apache.solr.schema.FieldType;
import org.apache.solr.schema.PointField;
/**
* Finds documents whose specified field has any of the specified values. It's like
* {@link TermQParserPlugin} but multi-valued, and supports a variety of internal algorithms.
*
Parameters:
*
f
: The field name (mandatory)
*
separator
: the separator delimiting the values in the query string, defaulting to a comma.
* If it's a " " then it splits on any consecutive whitespace.
*
method
: Any of termsFilter (default), booleanQuery, automaton, docValuesTermsFilter.
*
* Note that if no values are specified then the query matches no documents.
*/
public class TermsQParserPlugin extends QParserPlugin {
public static final String NAME = "terms";
/** The separator to use in the underlying suggester */
public static final String SEPARATOR = "separator";
/** Choose the internal algorithm */
private static final String METHOD = "method";
private static enum Method {
termsFilter {
@Override
Query makeFilter(String fname, BytesRef[] bytesRefs) {
return new TermInSetQuery(fname, bytesRefs);// constant scores
}
},
booleanQuery {
@Override
Query makeFilter(String fname, BytesRef[] byteRefs) {
BooleanQuery.Builder bq = new BooleanQuery.Builder();
for (BytesRef byteRef : byteRefs) {
bq.add(new TermQuery(new Term(fname, byteRef)), BooleanClause.Occur.SHOULD);
}
return new ConstantScoreQuery(bq.build());
}
},
automaton {
@Override
Query makeFilter(String fname, BytesRef[] byteRefs) {
ArrayUtil.timSort(byteRefs); // same sort algo as TermInSetQuery's choice
Automaton union = Automata.makeStringUnion(Arrays.asList(byteRefs)); // input must be sorted
return new AutomatonQuery(new Term(fname), union);//constant scores
}
},
docValuesTermsFilter {//on 4x this is FieldCacheTermsFilter but we use the 5x name any way
@Override
Query makeFilter(String fname, BytesRef[] byteRefs) {
return new DocValuesTermsQuery(fname, byteRefs);//constant scores
}
};
abstract Query makeFilter(String fname, BytesRef[] byteRefs);
}
@Override
public QParser createParser(String qstr, SolrParams localParams, SolrParams params, SolrQueryRequest req) {
return new QParser(qstr, localParams, params, req) {
@Override
public Query parse() throws SyntaxError {
String fname = localParams.get(QueryParsing.F);
FieldType ft = req.getSchema().getFieldTypeNoEx(fname);
String separator = localParams.get(SEPARATOR, ",");
String qstr = localParams.get(QueryParsing.V);//never null
Method method = Method.valueOf(localParams.get(METHOD, Method.termsFilter.name()));
//TODO pick the default method based on various heuristics from benchmarks
//TODO pick the default using FieldType.getSetQuery
//if space then split on all whitespace & trim, otherwise strictly interpret
final boolean sepIsSpace = separator.equals(" ");
if (sepIsSpace)
qstr = qstr.trim();
if (qstr.length() == 0)
return new MatchNoDocsQuery();
final String[] splitVals = sepIsSpace ? qstr.split("\\s+") : qstr.split(Pattern.quote(separator), -1);
assert splitVals.length > 0;
if (ft.isPointField()) {
if (localParams.get(METHOD) != null) {
throw new IllegalArgumentException(
String.format(Locale.ROOT, "Method '%s' not supported in TermsQParser when using PointFields", localParams.get(METHOD)));
}
return ((PointField)ft).getSetQuery(this, req.getSchema().getField(fname), Arrays.asList(splitVals));
}
BytesRef[] bytesRefs = new BytesRef[splitVals.length];
BytesRefBuilder term = new BytesRefBuilder();
for (int i = 0; i < splitVals.length; i++) {
String stringVal = splitVals[i];
//logic same as TermQParserPlugin
if (ft != null) {
ft.readableToIndexed(stringVal, term);
} else {
term.copyChars(stringVal);
}
bytesRefs[i] = term.toBytesRef();
}
return method.makeFilter(fname, bytesRefs);
}
};
}
}