Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

SOLR-4076: fuzzy support for MultiTermAwareComponent in SolrQueryParser 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1409517 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Yonik Seeley 2012-11-14 22:58:12 +00:00
parent 899f74978f
commit 102b0b8f61
3 changed files with 31 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
solr/CHANGES.txt
View File

@ -194,6 +194,12 @@ Bug Fixes
that start with /zookeeper, as this can fail and stop the removal of
further nodes. (Mark Miller)
* SOLR-4076: SolrQueryParser should run fuzzy terms through
MultiTermAwareComponents to ensure that (for example) a fuzzy query of
foobar~2 is equivalent to FooBar~2 on a field that includes lowercasing.
(yonik)
Other Changes
----------------------

8
solr/core/src/java/org/apache/solr/search/SolrQueryParser.java
View File

@ -246,4 +246,12 @@ public class SolrQueryParser extends QueryParser {
termStr = analyzeIfMultitermTermText(field, termStr, schema.getFieldType(field));
return newRegexpQuery(new Term(field, termStr));
}
@Override
protected Query getFuzzyQuery(String field, String termStr, float minSimilarity) throws ParseException {
termStr = analyzeIfMultitermTermText(field, termStr, schema.getFieldType(field));
Term t = new Term(field, termStr);
return newFuzzyQuery(t, minSimilarity, getFuzzyPrefixLength());
}
}

23
solr/core/src/test/org/apache/solr/search/TestFoldingMultitermQuery.java
View File

@ -185,26 +185,37 @@ public class TestFoldingMultitermQuery extends SolrTestCaseJ4 {
assertQ(req("q", "content_lower_token:hȉ*l?*"), "//result[@numFound='1']");
}
@Test
public void testFuzzy() throws Exception {
assertQ(req("q", "content:ZiLLx~1"),
"//result[@numFound='1']");
assertQ(req("q", "content_straight:ZiLLx~1"), // case preserving field shouldn't match
"//result[@numFound='0']");
assertQ(req("q", "content_folding:ZiLLx~1"), // case preserving field shouldn't match
"//result[@numFound='0']");
}
@Test
public void testRegex() throws Exception {
assertQ(req("q", "content:/Zill[a-z]/"),
"//result[@numFound='1']");
"//result[@numFound='1']");
assertQ(req("q", "content:/Zill[A-Z]/"), // everything in the regex gets lowercased?
"//result[@numFound='1']");
"//result[@numFound='1']");
assertQ(req("q", "content_keyword:/.*Zill[A-Z]/"),
"//result[@numFound='1']");
"//result[@numFound='1']");
assertQ(req("q", "content_straight:/Zill[a-z]/"), // case preserving field shouldn't match
"//result[@numFound='0']");
"//result[@numFound='0']");
assertQ(req("q", "content_folding:/Zill[a-z]/"), // case preserving field shouldn't match
"//result[@numFound='0']");
"//result[@numFound='0']");
assertQ(req("q", "content_keyword:/Abcdefg1 Finger/"), // test spaces
"//result[@numFound='1']");
"//result[@numFound='1']");
}
@Test
public void testGeneral() throws Exception {
assertQ(req("q", "content_stemming:fings*"), "//result[@numFound='0']"); // should not match (but would if fings* was stemmed to fing*