SOLR-8271: Change implicit default Similarity to use SchemaSimilarityFactory when luceneMatchVersion >= 6

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1715393 13f79535-47bb-0310-9956-ffa450edef68

solr/CHANGES.txt

@@ -58,9 +58,9 @@ Upgrading from Solr 5.x
     refrenced in your schema.xml, edit your config to use the functionally identical ClassicSimilarityFactory.
     See SOLR-8239 for more details.
   * The implicit default Similarity used when no <similarity/> is configured in schema.xml has
-    been changed to BM25SimilarityFactory.  Users who wish to preserve backcompatible behavior should
+    been changed to SchemaSimilarityFactory.  Users who wish to preserve backcompatible behavior should
     either explicitly configure ClassicSimilarityFactory, or ensure that the luceneMatchVersion
-    for the collection is less then 6.0.  See SOLR-8270 for details.
+    for the collection is less then 6.0.  See SOLR-8270 + SOLR-8271 for details.
   * SchemaSimilarityFactory has been modified to use BM25Similarity as the default for fieldTypes that
     do not explicitly declare a Similarity.  The legacy behavior of using ClassicSimilarity as the
     default will occur if the luceneMatchVersion for the collection is less then 6.0.  See SOLR-8261 for
@@ -153,6 +153,8 @@ Other Changes
 
 * SOLR-8270: Change implicit default Similarity to use BM25 when luceneMatchVersion >= 6 (hossman)
 
+* SOLR-8271: Change implicit default Similarity to use SchemaSimilarityFactory when luceneMatchVersion >= 6 (hossman)
+
 ==================  5.4.0 ==================
 
 Consult the LUCENE_CHANGES.txt file for additional, low level, changes in this release

solr/core/src/java/org/apache/solr/schema/IndexSchema.java

@@ -41,6 +41,7 @@ import org.apache.lucene.util.Version;
 import org.apache.solr.common.SolrException;
 import org.apache.solr.common.SolrException.ErrorCode;
 import org.apache.solr.common.params.SolrParams;
+import org.apache.solr.common.params.ModifiableSolrParams;
 import org.apache.solr.common.util.NamedList;
 import org.apache.solr.common.util.SimpleOrderedMap;
 import org.apache.solr.core.Config;
@@ -49,8 +50,8 @@ import org.apache.solr.core.SolrResourceLoader;
 import org.apache.solr.request.LocalSolrQueryRequest;
 import org.apache.solr.response.SchemaXmlWriter;
 import org.apache.solr.response.SolrQueryResponse;
-import org.apache.solr.search.similarities.BM25SimilarityFactory;
 import org.apache.solr.search.similarities.ClassicSimilarityFactory;
+import org.apache.solr.search.similarities.SchemaSimilarityFactory;
 import org.apache.solr.util.DOMUtil;
 import org.apache.solr.util.plugin.SolrCoreAware;
 import org.slf4j.Logger;
@@ -479,14 +480,11 @@ public class IndexSchema {
       Node node = (Node) xpath.evaluate(expression, document, XPathConstants.NODE);
       similarityFactory = readSimilarity(loader, node);
       if (similarityFactory == null) {
-        Version luceneVersion = getDefaultLuceneMatchVersion();
+        final boolean modernSim = getDefaultLuceneMatchVersion().onOrAfter(Version.LUCENE_6_0_0);
-        if (getDefaultLuceneMatchVersion().onOrAfter(Version.LUCENE_6_0_0)) {
+        final Class simClass = modernSim ? SchemaSimilarityFactory.class : ClassicSimilarityFactory.class;
-          similarityFactory = new BM25SimilarityFactory();
+        // use the loader to ensure proper SolrCoreAware handling
-        } else {
+        similarityFactory = loader.newInstance(simClass.getName(), SimilarityFactory.class);
-          similarityFactory = new ClassicSimilarityFactory();
+        similarityFactory.init(new ModifiableSolrParams());
-        }
-        final NamedList similarityParams = new NamedList();
-        similarityFactory.init(SolrParams.toSolrParams(similarityParams));
       } else {
         isExplicitSimilarity = true;
       }

solr/core/src/test-files/solr/collection1/conf/bad-schema-sim-global-vs-ft-mismatch.xml

@@ -17,12 +17,15 @@
 -->
 
 <schema name="bad-schema-sim-global-vs-ft-mismatch" version="1.0">
+
+  <similarity class="solr.BM25SimilarityFactory" /> <!-- global sim -->
+  
   <types>
     <fieldType name="sim1" class="solr.TextField">
       <analyzer>
         <tokenizer class="solr.MockTokenizerFactory"/>
       </analyzer>
-      <!-- BAD: similarity here but no global sim that allows it -->
+      <!-- BAD: similarity here but global sim does not allow it -->
       <similarity class="org.apache.lucene.misc.SweetSpotSimilarity"/>
     </fieldType>
  </types>

solr/core/src/test-files/solr/collection1/conf/schema-add-schema-fields-update-processor.xml

@@ -48,8 +48,4 @@
 
   <uniqueKey>id</uniqueKey>
 
-  <!-- testing with a similarity that is SolrCoreAware -->
-  <similarity class="solr.SchemaSimilarityFactory"/>    
-        
-
 </schema>

solr/core/src/test-files/solr/collection1/conf/schema-bm25.xml

@@ -48,5 +48,4 @@
   <defaultSearchField>text</defaultSearchField>
   <uniqueKey>id</uniqueKey>
   
-  <similarity class="solr.SchemaSimilarityFactory"/>
 </schema>

solr/core/src/test-files/solr/collection1/conf/schema-class-name-shortening-on-serialization.xml

@@ -39,5 +39,10 @@
     <field name="id" type="string" indexed="true" stored="true" multiValued="false" required="true"/>
     <field name="signatureField" type="string" indexed="true" stored="false"/>
   </fields>
+
+  <!--
+      Even though SchemaSimilarityFactory is the current implicit default in IndexSchema, we
+      are explicit about it here in this schema file to verify the short class name is preserved
+  -->
   <similarity class="solr.SchemaSimilarityFactory"/>
 </schema>

solr/core/src/test-files/solr/collection1/conf/schema-dfr.xml

@@ -66,5 +66,4 @@
   <defaultSearchField>text</defaultSearchField>
   <uniqueKey>id</uniqueKey>
   
-  <similarity class="solr.SchemaSimilarityFactory"/>
 </schema>

solr/core/src/test-files/solr/collection1/conf/schema-ib.xml

@@ -54,5 +54,4 @@
   <defaultSearchField>text</defaultSearchField>
   <uniqueKey>id</uniqueKey>
 
-  <similarity class="solr.SchemaSimilarityFactory"/>
 </schema>

solr/core/src/test-files/solr/collection1/conf/schema-lmdirichlet.xml

@@ -47,5 +47,4 @@
   <defaultSearchField>text</defaultSearchField>
   <uniqueKey>id</uniqueKey>
 
-  <similarity class="solr.SchemaSimilarityFactory"/>
 </schema>

solr/core/src/test-files/solr/collection1/conf/schema-lmjelinekmercer.xml

@@ -47,5 +47,4 @@
   <defaultSearchField>text</defaultSearchField>
   <uniqueKey>id</uniqueKey>
 
-  <similarity class="solr.SchemaSimilarityFactory"/>
 </schema>

solr/core/src/test-files/solr/collection1/conf/schema-rest.xml

@@ -634,5 +634,4 @@
 
   <solrQueryParser defaultOperator="OR"/>
 
-  <similarity class="solr.SchemaSimilarityFactory" />
 </schema>

solr/core/src/test-files/solr/collection1/conf/schema-sim.xml

@@ -63,6 +63,12 @@
  <defaultSearchField>sim1text</defaultSearchField>
  <uniqueKey>id</uniqueKey>
 
- <!-- default similarity, defers to the fieldType -->
+ <!-- Global similarity, defers to the fieldType.
+      
+      Even though SchemaSimilarityFactory is the current implicit default in IndexSchema, we
+      are explicit about it here in this schema file because TestPerFieldSimilarityClassic overrides
+      the luceneMatchVersion which results in a diff implicit global default - but we still
+      need per-fieldtype sims for that test.
+ -->
  <similarity class="solr.SchemaSimilarityFactory"/>
 </schema>

solr/core/src/test-files/solr/collection1/conf/schema-sweetspot.xml

@@ -72,5 +72,4 @@
   <defaultSearchField>text</defaultSearchField>
   <uniqueKey>id</uniqueKey>
   
-  <similarity class="solr.SchemaSimilarityFactory"/>
 </schema>

solr/core/src/test-files/solr/collection1/conf/schema-tfidf.xml

@@ -42,5 +42,4 @@
   <fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
   <defaultSearchField>text</defaultSearchField>
   <uniqueKey>id</uniqueKey>
-  <similarity class="solr.SchemaSimilarityFactory"/>
 </schema>

solr/core/src/test-files/solr/collection1/conf/schema11.xml

@@ -431,6 +431,4 @@ valued. -->
  <!-- field for the QueryParser to use when an explicit fieldname is absent -->
  <defaultSearchField>text</defaultSearchField>
  
- <similarity class="solr.SchemaSimilarityFactory"/>
- 
 </schema>

solr/core/src/test/org/apache/solr/rest/schema/TestClassNameShortening.java

@@ -50,6 +50,10 @@ public class TestClassNameShortening extends RestTestBase {
             "/response/lst[@name='fieldType']/lst[@name='similarity']/str[@name='class'] = 'org.apache.lucene.misc.SweetSpotSimilarity'");
   }
 
+  /** 
+   * See {@link TestSchemaSimilarityResource#testGetSchemaSimilarity} for where the long class name
+   * is verified when the config doesn't specify a sim at all
+   */
   @Test
   public void testShortenedGlobalSimilarityStaysShortened() throws Exception {
     assertQ("/schema/similarity?indent=on&wt=xml",

solr/core/src/test/org/apache/solr/rest/schema/TestSchemaSimilarityResource.java

@@ -20,11 +20,18 @@ import org.apache.solr.rest.SolrRestletTestBase;
 import org.junit.Test;
 
 public class TestSchemaSimilarityResource extends SolrRestletTestBase {
+
+  /**
+   * NOTE: schema used by parent class doesn't define a global sim, so we get the implicit default
+   * which causes the FQN of the class to be returned
+   * 
+   * @see TestClassNameShortening#testShortenedGlobalSimilarityStaysShortened
+   */
   @Test
   public void testGetSchemaSimilarity() throws Exception {
     assertQ("/schema/similarity?indent=on&wt=xml",
             "count(/response/lst[@name='similarity']) = 1",
-            "/response/lst[@name='similarity']/str[@name='class'][.='solr.SchemaSimilarityFactory']");
+            "/response/lst[@name='similarity']/str[@name='class'][.='org.apache.solr.search.similarities.SchemaSimilarityFactory']");
   }
 }
 

solr/solrj/src/test/org/apache/solr/client/solrj/request/SchemaTest.java

@@ -240,7 +240,7 @@ public class SchemaTest extends RestTestBase {
         new SchemaRequest.GlobalSimilarity();
     SchemaResponse.GlobalSimilarityResponse globalSimilarityResponse = globalSimilarityRequest.process(getSolrClient());
     assertValidSchemaResponse(globalSimilarityResponse);
-    assertEquals("org.apache.solr.search.similarities.BM25SimilarityFactory",
+    assertEquals("org.apache.solr.search.similarities.SchemaSimilarityFactory",
         globalSimilarityResponse.getSimilarity().get("class"));
   }