honeymoose
/
OpenSearch
mirror of https://github.com/honeymoose/OpenSearch.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

query_string_query should take term length into consideration when fuzziness is auto 

Fixes #15972
This commit is contained in:
Masaru Hasegawa 2016-09-02 18:07:26 +09:00
parent 28d7ebe8f8
commit 3a13f54755
2 changed files with 31 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
core/src/main/java/org/apache/lucene/queryparser/classic/MapperQueryParser.java
View File

@ -102,7 +102,6 @@ public class MapperQueryParser extends QueryParser {
setLowercaseExpandedTerms(settings.lowercaseExpandedTerms());
setPhraseSlop(settings.phraseSlop());
setDefaultOperator(settings.defaultOperator());
setFuzzyMinSim(settings.fuzziness().asFloat());
setFuzzyPrefixLength(settings.fuzzyPrefixLength());
setLocale(settings.locale());
}
@ -114,7 +113,7 @@ public class MapperQueryParser extends QueryParser {
@Override
Query handleBareFuzzy(String qfield, Token fuzzySlop, String termImage) throws ParseException {
if (fuzzySlop.image.length() == 1) {
return getFuzzyQuery(qfield, termImage, Float.toString(fuzzyMinSim));
return getFuzzyQuery(qfield, termImage, Float.toString(settings.fuzziness().asDistance(termImage)));
}
return getFuzzyQuery(qfield, termImage, fuzzySlop.image.substring(1));
}

33
core/src/test/java/org/elasticsearch/index/query/QueryStringQueryBuilderTests.java
View File

@ -26,15 +26,16 @@ import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.BoostQuery;
import org.apache.lucene.search.DisjunctionMaxQuery;
import org.apache.lucene.search.FuzzyQuery;
import org.apache.lucene.search.MatchAllDocsQuery;
import org.apache.lucene.search.MatchNoDocsQuery;
import org.apache.lucene.search.MultiTermQuery;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.RegexpQuery;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.SynonymQuery;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.MultiTermQuery;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.util.automaton.TooComplexToDeterminizeException;
import org.elasticsearch.common.lucene.all.AllTermQuery;
import org.elasticsearch.common.unit.Fuzziness;
@ -390,6 +391,32 @@ public class QueryStringQueryBuilderTests extends AbstractQueryTestCase<QueryStr
assertThat(e.getMessage(), containsString("would result in more than 10000 states"));
}
public void testToQueryFuzzyQueryAutoFuziness() throws Exception {
assumeTrue("test runs only when at least a type is registered", getCurrentTypes().length > 0);
int length = randomIntBetween(1, 10);
StringBuilder queryString = new StringBuilder();
for (int i = 0; i < length; i++) {
queryString.append("a");
}
queryString.append("~");
int expectedEdits;
if (length <= 2) {
expectedEdits = 0;
} else if (3 <= length && length <= 5) {
expectedEdits = 1;
} else {
expectedEdits = 2;
}
Query query = queryStringQuery(queryString.toString()).defaultField(STRING_FIELD_NAME).fuzziness(Fuzziness.AUTO)
.toQuery(createShardContext());
assertThat(query, instanceOf(FuzzyQuery.class));
FuzzyQuery fuzzyQuery = (FuzzyQuery) query;
assertEquals(expectedEdits, fuzzyQuery.getMaxEdits());
}
public void testFuzzyNumeric() throws Exception {
assumeTrue("test runs only when at least a type is registered", getCurrentTypes().length > 0);
QueryStringQueryBuilder query = queryStringQuery("12~0.2").defaultField(INT_FIELD_NAME);