mirror of https://github.com/apache/lucene.git
SOLR-3674: better docs, example, test for PathHierarchyTokenizerFactory
git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1367178 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Chris M. Hostetter
parent
5ab5df93ce
commit
8f20844ee9
|
|
@ -27,13 +27,47 @@ import org.apache.lucene.analysis.util.TokenizerFactory;
|
|||
|
||||
/**
|
||||
* Factory for {@link PathHierarchyTokenizer}.
|
||||
* <pre class="prettyprint" >
|
||||
* <fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
|
||||
* <analyzer>
|
||||
* <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="\" replace="/"/>
|
||||
* </analyzer>
|
||||
* </fieldType></pre>
|
||||
* <p>
|
||||
* This factory is typically configured for use only in the <code>index</code>
|
||||
* Analyzer (or only in the <code>query</code> Analyzer, but never both).
|
||||
* </p>
|
||||
* <p>
|
||||
* For example, in the configuration below a query for
|
||||
* <code>Books/NonFic</code> will match documents indexed with values like
|
||||
* <code>Books/NonFic</code>, <code>Books/NonFic/Law</code>,
|
||||
* <code>Books/NonFic/Science/Physics</code>, etc. But it will not match
|
||||
* documents indexed with values like <code>Books</code>, or
|
||||
* <code>Books/Fic</code>...
|
||||
* </p>
|
||||
*
|
||||
* <pre class="prettyprint" >
|
||||
* <fieldType name="descendent_path" class="solr.TextField">
|
||||
* <analyzer type="index">
|
||||
* <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
|
||||
* </analyzer>
|
||||
* <analyzer type="query">
|
||||
* <tokenizer class="solr.KeywordTokenizerFactory" />
|
||||
* </analyzer>
|
||||
* </fieldType>
|
||||
* </pre>
|
||||
* <p>
|
||||
* In this example however we see the oposite configuration, so that a query
|
||||
* for <code>Books/NonFic/Science/Physics</code> would match documents
|
||||
* containing <code>Books/NonFic</code>, <code>Books/NonFic/Science</code>,
|
||||
* or <code>Books/NonFic/Science/Physics</code>, but not
|
||||
* <code>Books/NonFic/Science/Physics/Theory</code> or
|
||||
* <code>Books/NonFic/Law</code>.
|
||||
* </p>
|
||||
* <pre class="prettyprint" >
|
||||
* <fieldType name="descendent_path" class="solr.TextField">
|
||||
* <analyzer type="index">
|
||||
* <tokenizer class="solr.KeywordTokenizerFactory" />
|
||||
* </analyzer>
|
||||
* <analyzer type="query">
|
||||
* <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
|
||||
* </analyzer>
|
||||
* </fieldType>
|
||||
* </pre>
|
||||
*/
|
||||
public class PathHierarchyTokenizerFactory extends TokenizerFactory {
|
||||
|
||||
|
|
|
|||
|
|
@ -414,7 +414,32 @@
|
|||
|
||||
<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
|
||||
|
||||
</types>
|
||||
<!--
|
||||
Example of using PathHierarchyTokenizerFactory at index time, so
|
||||
queries for paths match documents at that path, or in descendent paths
|
||||
-->
|
||||
<fieldType name="path" class="solr.TextField">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.KeywordTokenizerFactory" />
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<!--
|
||||
Example of using PathHierarchyTokenizerFactory at query time, so
|
||||
queries for paths match documents at that path, or in ancestor paths
|
||||
-->
|
||||
<fieldType name="ancestor_path" class="solr.TextField">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.KeywordTokenizerFactory" />
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
|
||||
</types>
|
||||
|
||||
|
||||
<fields>
|
||||
|
|
@ -640,6 +665,10 @@
|
|||
|
||||
<!-- Type used to index the lat and lon components for the "location" FieldType -->
|
||||
<dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" omitNorms="true" />
|
||||
|
||||
<dynamicField name="*_path" type="path" indexed="true" stored="true" omitNorms="true" multiValued="true" />
|
||||
<dynamicField name="*_ancestor" type="ancestor_path" indexed="true" stored="true" omitNorms="true" multiValued="true" />
|
||||
|
||||
</fields>
|
||||
|
||||
<defaultSearchField>text</defaultSearchField>
|
||||
|
|
@ -673,6 +702,7 @@
|
|||
|
||||
<!-- dynamic destination -->
|
||||
<copyField source="*_dynamic" dest="dynamic_*"/>
|
||||
<copyField source="*_path" dest="*_ancestor"/>
|
||||
|
||||
<!-- example of a custom similarity -->
|
||||
<similarity class="solr.CustomSimilarityFactory">
|
||||
|
|
|
|||
|
|
@ -0,0 +1,100 @@
|
|||
/*
|
||||
* 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.analysis;
|
||||
|
||||
import java.util.HashMap;
|
||||
import java.util.Map;
|
||||
|
||||
import org.apache.solr.SolrTestCaseJ4;
|
||||
|
||||
import org.junit.BeforeClass;
|
||||
|
||||
public class PathHierarchyTokenizerFactoryTest extends SolrTestCaseJ4 {
|
||||
|
||||
@BeforeClass
|
||||
public static void beforeTests() throws Exception {
|
||||
initCore("solrconfig.xml","schema.xml");
|
||||
|
||||
assertU(adoc("id", "11",
|
||||
"cat_path", "Movies/Fic/War"));
|
||||
|
||||
assertU(adoc("id", "31",
|
||||
"cat_path", "Books/Fic"));
|
||||
assertU(adoc("id", "31",
|
||||
"cat_path", "Books/Fic/Law"));
|
||||
assertU(adoc("id", "32",
|
||||
"cat_path", "Books/Fic/Science"));
|
||||
|
||||
assertU(adoc("id", "40",
|
||||
"cat_path", "Books/NonFic"));
|
||||
assertU(adoc("id", "41",
|
||||
"cat_path", "Books/NonFic/Law"));
|
||||
assertU(adoc("id", "42",
|
||||
"cat_path", "Books/NonFic/Law",
|
||||
"cat_path", "Books/NonFic/Science"));
|
||||
assertU(adoc("id", "43",
|
||||
"cat_path", "Books/NonFic/Science/Physics",
|
||||
"cat_path", "Books/NonFic/History"));
|
||||
|
||||
assertU(commit());
|
||||
}
|
||||
|
||||
public void testDescendents() throws Exception {
|
||||
|
||||
assertQ(req("{!field f=cat_path}Books/NonFic")
|
||||
,"//*[@numFound='4']"
|
||||
,"//int[@name='id' and .='40']"
|
||||
,"//int[@name='id' and .='41']"
|
||||
,"//int[@name='id' and .='42']"
|
||||
,"//int[@name='id' and .='43']"
|
||||
);
|
||||
assertQ(req("{!field f=cat_path}Books/NonFic/Law")
|
||||
,"//*[@numFound='2']"
|
||||
,"//int[@name='id' and .='41']"
|
||||
,"//int[@name='id' and .='42']"
|
||||
);
|
||||
|
||||
assertQ(req("{!field f=cat_path}Books/NonFic/Science")
|
||||
,"//*[@numFound='2']"
|
||||
,"//int[@name='id' and .='42']"
|
||||
,"//int[@name='id' and .='43']"
|
||||
);
|
||||
}
|
||||
|
||||
public void testAncestors() throws Exception {
|
||||
|
||||
assertQ(req("{!field f=cat_ancestor}Books/NonFic/Science")
|
||||
,"//*[@numFound='2']"
|
||||
,"//int[@name='id' and .='40']"
|
||||
,"//int[@name='id' and .='42']"
|
||||
);
|
||||
assertQ(req("{!field f=cat_ancestor}Books/NonFic/Law")
|
||||
,"//*[@numFound='3']"
|
||||
,"//int[@name='id' and .='40']"
|
||||
,"//int[@name='id' and .='41']"
|
||||
,"//int[@name='id' and .='42']"
|
||||
);
|
||||
|
||||
assertQ(req("{!field f=cat_ancestor}Books/NonFic/Science/Physics")
|
||||
,"//*[@numFound='3']"
|
||||
,"//int[@name='id' and .='40']"
|
||||
,"//int[@name='id' and .='42']"
|
||||
,"//int[@name='id' and .='43']"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
|
@ -137,7 +137,6 @@
|
|||
|
||||
<field name="payloads" type="payloads" indexed="true" stored="true"/>
|
||||
|
||||
|
||||
<field name="_version_" type="long" indexed="true" stored="true"/>
|
||||
|
||||
<!-- Uncommenting the following will create a "timestamp" field using
|
||||
|
|
@ -607,12 +606,30 @@
|
|||
</analyzer>
|
||||
</fieldType>
|
||||
|
||||
<fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
|
||||
<analyzer>
|
||||
<tokenizer class="solr.PathHierarchyTokenizerFactory"/>
|
||||
<!--
|
||||
Example of using PathHierarchyTokenizerFactory at index time, so
|
||||
queries for paths match documents at that path, or in descendent paths
|
||||
-->
|
||||
<fieldType name="descendent_path" class="solr.TextField">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.KeywordTokenizerFactory" />
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
<!--
|
||||
Example of using PathHierarchyTokenizerFactory at query time, so
|
||||
queries for paths match documents at that path, or in ancestor paths
|
||||
-->
|
||||
<fieldType name="ancestor_path" class="solr.TextField">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solr.KeywordTokenizerFactory" />
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
|
||||
|
||||
<!-- since fields of this type are by default not stored or indexed,
|
||||
any data added to them will be ignored outright. -->
|
||||
|
|
@ -1041,6 +1058,7 @@
|
|||
<filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
|
||||
</analyzer>
|
||||
</fieldType>
|
||||
|
||||
</types>
|
||||
|
||||
<!-- Similarity is the scoring routine for each document vs. a query.
|
||||
|
|
|
|||
Loading…
Reference in New Issue