-
Notifications
You must be signed in to change notification settings - Fork 24.3k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Added support for multi match query.
- Loading branch information
Showing
7 changed files
with
526 additions
and
14 deletions.
There are no files selected for viewing
211 changes: 211 additions & 0 deletions
211
src/main/java/org/elasticsearch/index/query/MultiMatchQueryBuilder.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,211 @@ | ||
/* | ||
* Licensed to ElasticSearch and Shay Banon under one | ||
* or more contributor license agreements. See the NOTICE file | ||
* distributed with this work for additional information | ||
* regarding copyright ownership. ElasticSearch 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.elasticsearch.index.query; | ||
|
||
import org.elasticsearch.common.xcontent.XContentBuilder; | ||
|
||
import java.io.IOException; | ||
import java.util.Arrays; | ||
import java.util.List; | ||
import java.util.Locale; | ||
|
||
/** | ||
* Same as {@link MatchQueryBuilder} but supports multiple fields. | ||
*/ | ||
public class MultiMatchQueryBuilder extends BaseQueryBuilder implements BoostableQueryBuilder<MultiMatchQueryBuilder> { | ||
|
||
private final Object text; | ||
|
||
private final List<String> fields; | ||
|
||
private MatchQueryBuilder.Type type; | ||
|
||
private MatchQueryBuilder.Operator operator; | ||
|
||
private String analyzer; | ||
|
||
private Float boost; | ||
|
||
private Integer slop; | ||
|
||
private String fuzziness; | ||
|
||
private Integer prefixLength; | ||
|
||
private Integer maxExpansions; | ||
|
||
private String minimumShouldMatch; | ||
|
||
private String rewrite = null; | ||
|
||
private String fuzzyRewrite = null; | ||
|
||
private Boolean useDisMax; | ||
|
||
private Integer tieBreaker; | ||
|
||
/** | ||
* Constructs a new text query. | ||
*/ | ||
public MultiMatchQueryBuilder(Object text, String... fields) { | ||
this.fields = Arrays.asList(fields); | ||
this.text = text; | ||
} | ||
|
||
/** | ||
* Sets the type of the text query. | ||
*/ | ||
public MultiMatchQueryBuilder type(MatchQueryBuilder.Type type) { | ||
this.type = type; | ||
return this; | ||
} | ||
|
||
/** | ||
* Sets the operator to use when using a boolean query. Defaults to <tt>OR</tt>. | ||
*/ | ||
public MultiMatchQueryBuilder operator(MatchQueryBuilder.Operator operator) { | ||
this.operator = operator; | ||
return this; | ||
} | ||
|
||
/** | ||
* Explicitly set the analyzer to use. Defaults to use explicit mapping config for the field, or, if not | ||
* set, the default search analyzer. | ||
*/ | ||
public MultiMatchQueryBuilder analyzer(String analyzer) { | ||
this.analyzer = analyzer; | ||
return this; | ||
} | ||
|
||
/** | ||
* Set the boost to apply to the query. | ||
*/ | ||
public MultiMatchQueryBuilder boost(float boost) { | ||
this.boost = boost; | ||
return this; | ||
} | ||
|
||
/** | ||
* Set the phrase slop if evaluated to a phrase query type. | ||
*/ | ||
public MultiMatchQueryBuilder slop(int slop) { | ||
this.slop = slop; | ||
return this; | ||
} | ||
|
||
/** | ||
* Sets the minimum similarity used when evaluated to a fuzzy query type. Defaults to "0.5". | ||
*/ | ||
public MultiMatchQueryBuilder fuzziness(Object fuzziness) { | ||
this.fuzziness = fuzziness.toString(); | ||
return this; | ||
} | ||
|
||
public MultiMatchQueryBuilder prefixLength(int prefixLength) { | ||
this.prefixLength = prefixLength; | ||
return this; | ||
} | ||
|
||
/** | ||
* When using fuzzy or prefix type query, the number of term expansions to use. Defaults to unbounded | ||
* so its recommended to set it to a reasonable value for faster execution. | ||
*/ | ||
public MultiMatchQueryBuilder maxExpansions(int maxExpansions) { | ||
this.maxExpansions = maxExpansions; | ||
return this; | ||
} | ||
|
||
public MultiMatchQueryBuilder minimumShouldMatch(String minimumShouldMatch) { | ||
this.minimumShouldMatch = minimumShouldMatch; | ||
return this; | ||
} | ||
|
||
public MultiMatchQueryBuilder rewrite(String rewrite) { | ||
this.rewrite = rewrite; | ||
return this; | ||
} | ||
|
||
public MultiMatchQueryBuilder fuzzyRewrite(String fuzzyRewrite) { | ||
this.fuzzyRewrite = fuzzyRewrite; | ||
return this; | ||
} | ||
|
||
public MultiMatchQueryBuilder useDisMax(Boolean useDisMax) { | ||
this.useDisMax = useDisMax; | ||
return this; | ||
} | ||
|
||
public MultiMatchQueryBuilder setTieBreaker(Integer tieBreaker) { | ||
this.tieBreaker = tieBreaker; | ||
return this; | ||
} | ||
|
||
@Override | ||
public void doXContent(XContentBuilder builder, Params params) throws IOException { | ||
builder.startObject(MultiMatchQueryParser.NAME); | ||
|
||
builder.field("query", text); | ||
builder.field("fields", fields); | ||
|
||
if (type != null) { | ||
builder.field("type", type.toString().toLowerCase(Locale.ENGLISH)); | ||
} | ||
if (operator != null) { | ||
builder.field("operator", operator.toString()); | ||
} | ||
if (analyzer != null) { | ||
builder.field("analyzer", analyzer); | ||
} | ||
if (boost != null) { | ||
builder.field("boost", boost); | ||
} | ||
if (slop != null) { | ||
builder.field("slop", slop); | ||
} | ||
if (fuzziness != null) { | ||
builder.field("fuzziness", fuzziness); | ||
} | ||
if (prefixLength != null) { | ||
builder.field("prefix_length", prefixLength); | ||
} | ||
if (maxExpansions != null) { | ||
builder.field("max_expansions", maxExpansions); | ||
} | ||
if (minimumShouldMatch != null) { | ||
builder.field("minimum_should_match", minimumShouldMatch); | ||
} | ||
if (rewrite != null) { | ||
builder.field("rewrite", rewrite); | ||
} | ||
if (fuzzyRewrite != null) { | ||
builder.field("fuzzy_rewrite", fuzzyRewrite); | ||
} | ||
|
||
if (useDisMax != null) { | ||
builder.field("use_dis_max", useDisMax); | ||
} | ||
|
||
if (tieBreaker != null) { | ||
builder.field("tie_breaker", tieBreaker); | ||
} | ||
|
||
builder.endObject(); | ||
} | ||
} |
180 changes: 180 additions & 0 deletions
180
src/main/java/org/elasticsearch/index/query/MultiMatchQueryParser.java
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,180 @@ | ||
/* | ||
* Licensed to ElasticSearch and Shay Banon under one | ||
* or more contributor license agreements. See the NOTICE file | ||
* distributed with this work for additional information | ||
* regarding copyright ownership. ElasticSearch 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.elasticsearch.index.query; | ||
|
||
import com.google.common.collect.Lists; | ||
import com.google.common.collect.Maps; | ||
import org.apache.lucene.search.BooleanClause; | ||
import org.apache.lucene.search.BooleanQuery; | ||
import org.apache.lucene.search.Query; | ||
import org.elasticsearch.common.inject.Inject; | ||
import org.elasticsearch.common.lucene.search.Queries; | ||
import org.elasticsearch.common.regex.Regex; | ||
import org.elasticsearch.common.xcontent.XContentParser; | ||
import org.elasticsearch.index.query.support.QueryParsers; | ||
import org.elasticsearch.index.search.MatchQuery; | ||
import org.elasticsearch.index.search.MultiMatchQuery; | ||
|
||
import java.io.IOException; | ||
import java.util.List; | ||
import java.util.Map; | ||
|
||
/** | ||
* Same ad {@link MatchQueryParser} but has support for multiple fields. | ||
*/ | ||
public class MultiMatchQueryParser implements QueryParser { | ||
|
||
public static final String NAME = "multi_match"; | ||
|
||
@Inject | ||
public MultiMatchQueryParser() { | ||
} | ||
|
||
@Override | ||
public String[] names() { | ||
return new String[]{ | ||
NAME, "multiMatch" | ||
}; | ||
} | ||
|
||
@Override | ||
public Query parse(QueryParseContext parseContext) throws IOException, QueryParsingException { | ||
XContentParser parser = parseContext.parser(); | ||
|
||
String text = null; | ||
float boost = 1.0f; | ||
MatchQuery.Type type = MatchQuery.Type.BOOLEAN; | ||
MultiMatchQuery multiMatchQuery = new MultiMatchQuery(parseContext); | ||
String minimumShouldMatch = null; | ||
List<String> fieldNames = Lists.newArrayList(); | ||
Map<String, Float> fieldNameToBoost = Maps.newHashMap(); | ||
|
||
XContentParser.Token token; | ||
String currentFieldName = null; | ||
while ((token = parser.nextToken()) != XContentParser.Token.END_OBJECT) { | ||
if (token == XContentParser.Token.FIELD_NAME) { | ||
currentFieldName = parser.currentName(); | ||
} else if (token == XContentParser.Token.START_ARRAY) { | ||
if ("fields".equals(currentFieldName)) { | ||
while ((token = parser.nextToken()) != XContentParser.Token.END_ARRAY) { | ||
String fField = null; | ||
float fBoost = -1; | ||
char[] fieldText = parser.textCharacters(); | ||
int end = parser.textOffset() + parser.textLength(); | ||
for (int i = parser.textOffset(); i < end; i++) { | ||
if (fieldText[i] == '^') { | ||
int relativeLocation = i - parser.textOffset(); | ||
fField = new String(fieldText, parser.textOffset(), relativeLocation); | ||
fBoost = Float.parseFloat(new String(fieldText, i + 1, parser.textLength() - relativeLocation - 1)); | ||
break; | ||
} | ||
} | ||
if (fField == null) { | ||
fField = parser.text(); | ||
} | ||
|
||
if (Regex.isSimpleMatchPattern(fField)) { | ||
for (String field : parseContext.mapperService().simpleMatchToIndexNames(fField)) { | ||
fieldNames.add(field); | ||
if (fBoost != -1) { | ||
fieldNameToBoost.put(field, fBoost); | ||
} | ||
} | ||
} else { | ||
fieldNames.add(fField); | ||
if (fBoost != -1) { | ||
fieldNameToBoost.put(fField, fBoost); | ||
} | ||
} | ||
} | ||
} else { | ||
throw new QueryParsingException(parseContext.index(), "[query_string] query does not support [" + currentFieldName + "]"); | ||
} | ||
} else if (token.isValue()) { | ||
if ("query".equals(currentFieldName)) { | ||
text = parser.text(); | ||
} else if ("type".equals(currentFieldName)) { | ||
String tStr = parser.text(); | ||
if ("boolean".equals(tStr)) { | ||
type = MatchQuery.Type.BOOLEAN; | ||
} else if ("phrase".equals(tStr)) { | ||
type = MatchQuery.Type.PHRASE; | ||
} else if ("phrase_prefix".equals(tStr) || "phrasePrefix".equals(currentFieldName)) { | ||
type = MatchQuery.Type.PHRASE_PREFIX; | ||
} | ||
} else if ("analyzer".equals(currentFieldName)) { | ||
String analyzer = parser.text(); | ||
if (parseContext.analysisService().analyzer(analyzer) == null) { | ||
throw new QueryParsingException(parseContext.index(), "[match] analyzer [" + parser.text() + "] not found"); | ||
} | ||
multiMatchQuery.setAnalyzer(analyzer); | ||
} else if ("boost".equals(currentFieldName)) { | ||
boost = parser.floatValue(); | ||
} else if ("slop".equals(currentFieldName) || "phrase_slop".equals(currentFieldName) || "phraseSlop".equals(currentFieldName)) { | ||
multiMatchQuery.setPhraseSlop(parser.intValue()); | ||
} else if ("fuzziness".equals(currentFieldName)) { | ||
multiMatchQuery.setFuzziness(parser.textOrNull()); | ||
} else if ("prefix_length".equals(currentFieldName) || "prefixLength".equals(currentFieldName)) { | ||
multiMatchQuery.setFuzzyPrefixLength(parser.intValue()); | ||
} else if ("max_expansions".equals(currentFieldName) || "maxExpansions".equals(currentFieldName)) { | ||
multiMatchQuery.setMaxExpansions(parser.intValue()); | ||
} else if ("operator".equals(currentFieldName)) { | ||
String op = parser.text(); | ||
if ("or".equalsIgnoreCase(op)) { | ||
multiMatchQuery.setOccur(BooleanClause.Occur.SHOULD); | ||
} else if ("and".equalsIgnoreCase(op)) { | ||
multiMatchQuery.setOccur(BooleanClause.Occur.MUST); | ||
} else { | ||
throw new QueryParsingException(parseContext.index(), "text query requires operator to be either 'and' or 'or', not [" + op + "]"); | ||
} | ||
} else if ("minimum_should_match".equals(currentFieldName) || "minimumShouldMatch".equals(currentFieldName)) { | ||
minimumShouldMatch = parser.textOrNull(); | ||
} else if ("rewrite".equals(currentFieldName)) { | ||
multiMatchQuery.setRewriteMethod(QueryParsers.parseRewriteMethod(parser.textOrNull(), null)); | ||
} else if ("fuzzy_rewrite".equals(currentFieldName) || "fuzzyRewrite".equals(currentFieldName)) { | ||
multiMatchQuery.setFuzzyRewriteMethod(QueryParsers.parseRewriteMethod(parser.textOrNull(), null)); | ||
} else if ("use_dis_max".equals(currentFieldName) || "useDisMax".equals(currentFieldName)) { | ||
multiMatchQuery.setUseDisMax(parser.booleanValue()); | ||
} else if ("tie_breaker".equals(currentFieldName) || "tieBreaker".equals(currentFieldName)) { | ||
multiMatchQuery.setTieBreaker(parser.intValue()); | ||
} else { | ||
throw new QueryParsingException(parseContext.index(), "[match] query does not support [" + currentFieldName + "]"); | ||
} | ||
} | ||
} | ||
|
||
if (text == null) { | ||
throw new QueryParsingException(parseContext.index(), "No text specified for match_all query"); | ||
} | ||
|
||
if (fieldNames.isEmpty()) { | ||
throw new QueryParsingException(parseContext.index(), "No fields specified for match_all query"); | ||
} | ||
|
||
Query query = multiMatchQuery.parse(type, fieldNames, text); | ||
|
||
if (query instanceof BooleanQuery) { | ||
Queries.applyMinimumShouldMatch((BooleanQuery) query, minimumShouldMatch); | ||
} | ||
|
||
query.setBoost(boost); | ||
return query; | ||
} | ||
} |
Oops, something went wrong.