svn commit: r1795282 - in /jackrabbit/oak/trunk: oak-doc/src/site/markdown/query/lucene.md oak-lucene/src/test/java/org/apache/jackrabbit/oak/plugins/index/lucene/LucenePropertyIndexTest.java

[to...@apache.org]

Author: tommaso
Date: Tue May 16 09:25:02 2017
New Revision: 1795282

URL: http://svn.apache.org/viewvc?rev=1795282&view=rev
Log:
OAK-4804 - added unit test and some notes about synonyms

Modified:
    jackrabbit/oak/trunk/oak-doc/src/site/markdown/query/lucene.md
    jackrabbit/oak/trunk/oak-lucene/src/test/java/org/apache/jackrabbit/oak/plugins/index/lucene/LucenePropertyIndexTest.java

Modified: jackrabbit/oak/trunk/oak-doc/src/site/markdown/query/lucene.md
URL: http://svn.apache.org/viewvc/jackrabbit/oak/trunk/oak-doc/src/site/markdown/query/lucene.md?rev=1795282&r1=1795281&r2=1795282&view=diff
==============================================================================
--- jackrabbit/oak/trunk/oak-doc/src/site/markdown/query/lucene.md (original)
+++ jackrabbit/oak/trunk/oak-doc/src/site/markdown/query/lucene.md Tue May 16 09:25:02 2017
@@ -758,6 +758,11 @@ Points to note
     * https://cwiki.apache.org/confluence/display/solr/Understanding+Analyzers%2C+Tokenizers%2C+and+Filters
     * https://cwiki.apache.org/confluence/display/solr/CharFilterFactories
     * https://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters#Specifying_an_Analyzer_in_the_schema
+7. When defining synonyms:
+    * in the synonym file, lines like _plane, airplane, aircraft_ refer to tokens that are mutual synoyms whereas lines 
+    like _plane => airplane_ refer to _one way_ synonyms, so that plane will be expanded to airplane but not vice versa
+    * special characters have to be escaped
+    * multi word synonyms need particular attention (see https://lucidworks.com/2014/07/12/solution-for-multi-term-synonyms-in-lucenesolr-using-the-auto-phrasing-tokenfilter)
     
 Note that currently only one analyzer can be configured per index. Its not possible to specify separate
 analyzer for query and index time currently. 

Modified: jackrabbit/oak/trunk/oak-lucene/src/test/java/org/apache/jackrabbit/oak/plugins/index/lucene/LucenePropertyIndexTest.java
URL: http://svn.apache.org/viewvc/jackrabbit/oak/trunk/oak-lucene/src/test/java/org/apache/jackrabbit/oak/plugins/index/lucene/LucenePropertyIndexTest.java?rev=1795282&r1=1795281&r2=1795282&view=diff
==============================================================================
--- jackrabbit/oak/trunk/oak-lucene/src/test/java/org/apache/jackrabbit/oak/plugins/index/lucene/LucenePropertyIndexTest.java (original)
+++ jackrabbit/oak/trunk/oak-lucene/src/test/java/org/apache/jackrabbit/oak/plugins/index/lucene/LucenePropertyIndexTest.java Tue May 16 09:25:02 2017
@@ -282,6 +282,27 @@ public class LucenePropertyIndexTest ext
         executeQuery("SELECT * FROM [nt:base] where a='b'", SQL2, NO_BINDINGS);
     }
 
+    @Test
+    public void testSynonyms() throws Exception {
+        Tree idx = createFulltextIndex(root.getTree("/"), "synonymIndex");
+        TestUtil.useV2(idx);
+
+        Tree anl = idx.addChild(LuceneIndexConstants.ANALYZERS).addChild(LuceneIndexConstants.ANL_DEFAULT);
+        anl.addChild(LuceneIndexConstants.ANL_TOKENIZER).setProperty(LuceneIndexConstants.ANL_NAME, "Standard");
+        Tree synFilter = anl.addChild(LuceneIndexConstants.ANL_FILTERS).addChild("Synonym");
+        synFilter.setProperty("synonyms", "syn.txt");
+        synFilter.addChild("syn.txt").addChild(JCR_CONTENT).setProperty(JCR_DATA, "plane, airplane, aircraft\nflies=>scars");
+
+        Tree test = root.getTree("/").addChild("test").addChild("node");
+        test.setProperty("foo", "an aircraft flies");
+        root.commit();
+
+        assertQuery("select * from [nt:base] where ISDESCENDANTNODE('/test') and CONTAINS(*, 'plane')", asList("/test/node"));
+        assertQuery("select * from [nt:base] where ISDESCENDANTNODE('/test') and CONTAINS(*, 'airplane')", asList("/test/node"));
+        assertQuery("select * from [nt:base] where ISDESCENDANTNODE('/test') and CONTAINS(*, 'aircraft')", asList("/test/node"));
+        assertQuery("select * from [nt:base] where ISDESCENDANTNODE('/test') and CONTAINS(*, 'scars')", asList("/test/node"));
+    }
+
     private Tree createFulltextIndex(Tree index, String name) throws CommitFailedException {
         return TestUtil.createFulltextIndex(index, name);
     }