You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by ko...@apache.org on 2012/10/09 04:47:23 UTC

svn commit: r1395848 - in /lucene/dev/branches/branch_4x: ./ dev-tools/ lucene/ lucene/analysis/ lucene/analysis/icu/src/java/org/apache/lucene/collation/ lucene/backwards/ lucene/benchmark/ lucene/codecs/ lucene/core/ lucene/core/src/test/org/apache/l...

Author: koji
Date: Tue Oct  9 02:47:21 2012
New Revision: 1395848

URL: http://svn.apache.org/viewvc?rev=1395848&view=rev
Log:
LUCENE-1822: BaseFragListBuilder hard-coded 6 char margin is too naive.

Modified:
    lucene/dev/branches/branch_4x/   (props changed)
    lucene/dev/branches/branch_4x/dev-tools/   (props changed)
    lucene/dev/branches/branch_4x/lucene/   (props changed)
    lucene/dev/branches/branch_4x/lucene/BUILD.txt   (props changed)
    lucene/dev/branches/branch_4x/lucene/CHANGES.txt   (contents, props changed)
    lucene/dev/branches/branch_4x/lucene/JRE_VERSION_MIGRATION.txt   (props changed)
    lucene/dev/branches/branch_4x/lucene/LICENSE.txt   (props changed)
    lucene/dev/branches/branch_4x/lucene/MIGRATE.txt   (props changed)
    lucene/dev/branches/branch_4x/lucene/NOTICE.txt   (props changed)
    lucene/dev/branches/branch_4x/lucene/README.txt   (props changed)
    lucene/dev/branches/branch_4x/lucene/analysis/   (props changed)
    lucene/dev/branches/branch_4x/lucene/analysis/icu/src/java/org/apache/lucene/collation/ICUCollationKeyFilterFactory.java   (props changed)
    lucene/dev/branches/branch_4x/lucene/backwards/   (props changed)
    lucene/dev/branches/branch_4x/lucene/benchmark/   (props changed)
    lucene/dev/branches/branch_4x/lucene/build.xml   (props changed)
    lucene/dev/branches/branch_4x/lucene/codecs/   (props changed)
    lucene/dev/branches/branch_4x/lucene/common-build.xml   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/index/TestBackwardsCompatibility.java   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/index/index.40.cfs.zip   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/index/index.40.nocfs.zip   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/index/index.40.optimized.cfs.zip   (props changed)
    lucene/dev/branches/branch_4x/lucene/core/src/test/org/apache/lucene/index/index.40.optimized.nocfs.zip   (props changed)
    lucene/dev/branches/branch_4x/lucene/demo/   (props changed)
    lucene/dev/branches/branch_4x/lucene/facet/   (props changed)
    lucene/dev/branches/branch_4x/lucene/grouping/   (props changed)
    lucene/dev/branches/branch_4x/lucene/highlighter/   (props changed)
    lucene/dev/branches/branch_4x/lucene/highlighter/src/java/org/apache/lucene/search/vectorhighlight/BaseFragListBuilder.java
    lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragListBuilderTest.java
    lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragmentsBuilderTest.java
    lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/WeightedFragListBuilderTest.java
    lucene/dev/branches/branch_4x/lucene/ivy-settings.xml   (props changed)
    lucene/dev/branches/branch_4x/lucene/join/   (props changed)
    lucene/dev/branches/branch_4x/lucene/licenses/   (props changed)
    lucene/dev/branches/branch_4x/lucene/memory/   (props changed)
    lucene/dev/branches/branch_4x/lucene/misc/   (props changed)
    lucene/dev/branches/branch_4x/lucene/module-build.xml   (props changed)
    lucene/dev/branches/branch_4x/lucene/queries/   (props changed)
    lucene/dev/branches/branch_4x/lucene/queryparser/   (props changed)
    lucene/dev/branches/branch_4x/lucene/sandbox/   (props changed)
    lucene/dev/branches/branch_4x/lucene/site/   (props changed)
    lucene/dev/branches/branch_4x/lucene/spatial/   (props changed)
    lucene/dev/branches/branch_4x/lucene/suggest/   (props changed)
    lucene/dev/branches/branch_4x/lucene/test-framework/   (props changed)
    lucene/dev/branches/branch_4x/lucene/tools/   (props changed)
    lucene/dev/branches/branch_4x/solr/   (props changed)
    lucene/dev/branches/branch_4x/solr/CHANGES.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/LICENSE.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/NOTICE.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/README.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/build.xml   (props changed)
    lucene/dev/branches/branch_4x/solr/cloud-dev/   (props changed)
    lucene/dev/branches/branch_4x/solr/common-build.xml   (props changed)
    lucene/dev/branches/branch_4x/solr/contrib/   (props changed)
    lucene/dev/branches/branch_4x/solr/core/   (props changed)
    lucene/dev/branches/branch_4x/solr/example/   (props changed)
    lucene/dev/branches/branch_4x/solr/licenses/   (props changed)
    lucene/dev/branches/branch_4x/solr/licenses/httpclient-LICENSE-ASL.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/licenses/httpclient-NOTICE.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/licenses/httpcore-LICENSE-ASL.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/licenses/httpcore-NOTICE.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/licenses/httpmime-LICENSE-ASL.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/licenses/httpmime-NOTICE.txt   (props changed)
    lucene/dev/branches/branch_4x/solr/scripts/   (props changed)
    lucene/dev/branches/branch_4x/solr/site/   (props changed)
    lucene/dev/branches/branch_4x/solr/solrj/   (props changed)
    lucene/dev/branches/branch_4x/solr/test-framework/   (props changed)
    lucene/dev/branches/branch_4x/solr/testlogging.properties   (props changed)
    lucene/dev/branches/branch_4x/solr/webapp/   (props changed)

Modified: lucene/dev/branches/branch_4x/lucene/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/CHANGES.txt?rev=1395848&r1=1395847&r2=1395848&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/CHANGES.txt (original)
+++ lucene/dev/branches/branch_4x/lucene/CHANGES.txt Tue Oct  9 02:47:21 2012
@@ -34,6 +34,11 @@ New Features
   the suggester to ignore such variations. (Robert Muir, Sudarshan
   Gaikaiwari, Mike McCandless)
 
+Bug Fixes
+
+* LUCENE-1822: BaseFragListBuilder hard-coded 6 char margin is too naive.
+  (Alex Vigdor, Arcadius Ahouansou, Koji Sekiguchi)
+
 Optimizations
 
 * LUCENE-4443: BlockPostingsFormat no longer writes unnecessary offsets 

Modified: lucene/dev/branches/branch_4x/lucene/highlighter/src/java/org/apache/lucene/search/vectorhighlight/BaseFragListBuilder.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/highlighter/src/java/org/apache/lucene/search/vectorhighlight/BaseFragListBuilder.java?rev=1395848&r1=1395847&r2=1395848&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/highlighter/src/java/org/apache/lucene/search/vectorhighlight/BaseFragListBuilder.java (original)
+++ lucene/dev/branches/branch_4x/lucene/highlighter/src/java/org/apache/lucene/search/vectorhighlight/BaseFragListBuilder.java Tue Oct  9 02:47:21 2012
@@ -69,13 +69,14 @@ public abstract class BaseFragListBuilde
 
       wpil.clear();
       wpil.add( phraseInfo );
+      int firstOffset = phraseInfo.getStartOffset();
       int st = phraseInfo.getStartOffset() - margin < startOffset ?
           startOffset : phraseInfo.getStartOffset() - margin;
       int en = st + fragCharSize;
       if( phraseInfo.getEndOffset() > en )
         en = phraseInfo.getEndOffset();
-      startOffset = en;
 
+      int lastEndOffset = phraseInfo.getEndOffset();
       while( true ){
         if( ite.hasNext() ){
           phraseInfo = ite.next();
@@ -84,11 +85,22 @@ public abstract class BaseFragListBuilde
         }
         else
           break;
-        if( phraseInfo.getEndOffset() <= en )
+        if( phraseInfo.getEndOffset() <= en ){
           wpil.add( phraseInfo );
+          lastEndOffset = phraseInfo.getEndOffset();
+        }
         else
           break;
       }
+      int matchLen = lastEndOffset - firstOffset;
+      //now recalculate the start and end position to "center" the result
+      int newMargin = (fragCharSize-matchLen)/2;
+      st = firstOffset - newMargin;
+      if(st<startOffset){
+        st = startOffset;
+      }
+      en = st+fragCharSize;
+      startOffset = en;
       fieldFragList.add( st, en, wpil );
     }
     return fieldFragList;

Modified: lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragListBuilderTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragListBuilderTest.java?rev=1395848&r1=1395847&r2=1395848&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragListBuilderTest.java (original)
+++ lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragListBuilderTest.java Tue Oct  9 02:47:21 2012
@@ -42,7 +42,7 @@ public class SimpleFragListBuilderTest e
     SimpleFragListBuilder sflb = new SimpleFragListBuilder();
     FieldFragList ffl = sflb.createFieldFragList( fpl(new TermQuery(new Term(F, "abcdefghijklmnopqrs")), "abcdefghijklmnopqrs" ), sflb.minFragCharSize );
     assertEquals( 1, ffl.getFragInfos().size() );
-    assertEquals( "subInfos=(abcdefghijklmnopqrs((0,19)))/1.0(0,19)", ffl.getFragInfos().get( 0 ).toString() );
+    assertEquals( "subInfos=(abcdefghijklmnopqrs((0,19)))/1.0(0,18)", ffl.getFragInfos().get( 0 ).toString() );
   }
   
   public void testSmallerFragSizeThanPhraseQuery() throws Exception {
@@ -55,7 +55,7 @@ public class SimpleFragListBuilderTest e
     FieldFragList ffl = sflb.createFieldFragList( fpl(phraseQuery, "abcdefgh   jklmnopqrs" ), sflb.minFragCharSize );
     assertEquals( 1, ffl.getFragInfos().size() );
     if (VERBOSE) System.out.println( ffl.getFragInfos().get( 0 ).toString() );
-    assertEquals( "subInfos=(abcdefghjklmnopqrs((0,21)))/1.0(0,21)", ffl.getFragInfos().get( 0 ).toString() );
+    assertEquals( "subInfos=(abcdefghjklmnopqrs((0,21)))/1.0(1,19)", ffl.getFragInfos().get( 0 ).toString() );
   }
   
   public void test1TermIndex() throws Exception {
@@ -77,7 +77,7 @@ public class SimpleFragListBuilderTest e
 
     ffl = sflb.createFieldFragList( fpl(new TermQuery(new Term(F, "a")), "b b b b a b b b b a" ), 20 );
     assertEquals( 1, ffl.getFragInfos().size() );
-    assertEquals( "subInfos=(a((8,9))a((18,19)))/2.0(2,22)", ffl.getFragInfos().get( 0 ).toString() );
+    assertEquals( "subInfos=(a((8,9))a((18,19)))/2.0(4,24)", ffl.getFragInfos().get( 0 ).toString() );
   }
   
   public void test2TermsIndex2Frags() throws Exception {
@@ -85,7 +85,7 @@ public class SimpleFragListBuilderTest e
     FieldFragList ffl = sflb.createFieldFragList( fpl(new TermQuery(new Term(F, "a")), "a b b b b b b b b b b b b b a" ), 20 );
     assertEquals( 2, ffl.getFragInfos().size() );
     assertEquals( "subInfos=(a((0,1)))/1.0(0,20)", ffl.getFragInfos().get( 0 ).toString() );
-    assertEquals( "subInfos=(a((28,29)))/1.0(22,42)", ffl.getFragInfos().get( 1 ).toString() );
+    assertEquals( "subInfos=(a((28,29)))/1.0(20,40)", ffl.getFragInfos().get( 1 ).toString() );
 
     ffl = sflb.createFieldFragList( fpl(new TermQuery(new Term(F, "a")), "a b b b b b b b b b b b b a" ), 20 );
     assertEquals( 2, ffl.getFragInfos().size() );
@@ -164,7 +164,7 @@ public class SimpleFragListBuilderTest e
     SimpleFragListBuilder sflb = new SimpleFragListBuilder();
     FieldFragList ffl = sflb.createFieldFragList( fpl, 100 );
     assertEquals( 1, ffl.getFragInfos().size() );
-    assertEquals( "subInfos=(d((9,10)))/1.0(3,103)", ffl.getFragInfos().get( 0 ).toString() );
+    assertEquals( "subInfos=(d((9,10)))/1.0(0,100)", ffl.getFragInfos().get( 0 ).toString() );
   }
   
   public void test1PhraseLongMV() throws Exception {
@@ -176,7 +176,7 @@ public class SimpleFragListBuilderTest e
     SimpleFragListBuilder sflb = new SimpleFragListBuilder();
     FieldFragList ffl = sflb.createFieldFragList( fpl, 100 );
     assertEquals( 1, ffl.getFragInfos().size() );
-    assertEquals( "subInfos=(searchengines((102,116))searchengines((157,171)))/2.0(96,196)", ffl.getFragInfos().get( 0 ).toString() );
+    assertEquals( "subInfos=(searchengines((102,116))searchengines((157,171)))/2.0(87,187)", ffl.getFragInfos().get( 0 ).toString() );
   }
 
   public void test1PhraseLongMVB() throws Exception {
@@ -188,6 +188,6 @@ public class SimpleFragListBuilderTest e
     SimpleFragListBuilder sflb = new SimpleFragListBuilder();
     FieldFragList ffl = sflb.createFieldFragList( fpl, 100 );
     assertEquals( 1, ffl.getFragInfos().size() );
-    assertEquals( "subInfos=(sppeeeed((88,93)))/1.0(82,182)", ffl.getFragInfos().get( 0 ).toString() );
+    assertEquals( "subInfos=(sppeeeed((88,93)))/1.0(41,141)", ffl.getFragInfos().get( 0 ).toString() );
   }
 }

Modified: lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragmentsBuilderTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragmentsBuilderTest.java?rev=1395848&r1=1395847&r2=1395848&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragmentsBuilderTest.java (original)
+++ lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragmentsBuilderTest.java Tue Oct  9 02:47:21 2012
@@ -106,7 +106,8 @@ public class SimpleFragmentsBuilderTest 
     SimpleFragListBuilder sflb = new SimpleFragListBuilder();
     FieldFragList ffl = sflb.createFieldFragList( fpl, 100 );
     SimpleFragmentsBuilder sfb = new SimpleFragmentsBuilder();
-    assertEquals( "a b c  <b>d</b> e", sfb.createFragment( reader, 0, F, ffl ) );
+    // Should we probably be trimming?
+    assertEquals( "  a b c  <b>d</b> e", sfb.createFragment( reader, 0, F, ffl ) );
   }
   
   public void test1PhraseLongMV() throws Exception {
@@ -118,7 +119,7 @@ public class SimpleFragmentsBuilderTest 
     SimpleFragListBuilder sflb = new SimpleFragListBuilder();
     FieldFragList ffl = sflb.createFieldFragList( fpl, 100 );
     SimpleFragmentsBuilder sfb = new SimpleFragmentsBuilder();
-    assertEquals( "The most <b>search engines</b> use only one of these methods. Even the <b>search engines</b> that says they can use the",
+    assertEquals( "customization: The most <b>search engines</b> use only one of these methods. Even the <b>search engines</b> that says they can",
         sfb.createFragment( reader, 0, F, ffl ) );
   }
 
@@ -131,7 +132,7 @@ public class SimpleFragmentsBuilderTest 
     SimpleFragListBuilder sflb = new SimpleFragListBuilder();
     FieldFragList ffl = sflb.createFieldFragList( fpl, 100 );
     SimpleFragmentsBuilder sfb = new SimpleFragmentsBuilder();
-    assertEquals( "processing <b>speed</b>, the", sfb.createFragment( reader, 0, F, ffl ) );
+    assertEquals( "additional hardware. \nWhen you talk about processing <b>speed</b>, the", sfb.createFragment( reader, 0, F, ffl ) );
   }
   
   public void testUnstoredField() throws Exception {
@@ -209,7 +210,7 @@ public class SimpleFragmentsBuilderTest 
     String[] result = sfb.createFragments(reader, 0, F, ffl, 3);
     assertEquals(2, result.length);
     assertEquals("some <b>text</b> to highlight", result[0]);
-    assertEquals("other <b>text</b>", result[1]);
+    assertEquals("highlight other <b>text</b>", result[1]);
 
     fq = new FieldQuery( tq( "highlight" ), true, true );
     stack = new FieldTermStack( reader, 0, F, fq );

Modified: lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/WeightedFragListBuilderTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/WeightedFragListBuilderTest.java?rev=1395848&r1=1395847&r2=1395848&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/WeightedFragListBuilderTest.java (original)
+++ lucene/dev/branches/branch_4x/lucene/highlighter/src/test/org/apache/lucene/search/vectorhighlight/WeightedFragListBuilderTest.java Tue Oct  9 02:47:21 2012
@@ -29,7 +29,7 @@ public class WeightedFragListBuilderTest
     WeightedFragListBuilder wflb = new WeightedFragListBuilder();
     FieldFragList ffl = wflb.createFieldFragList( fpl, 100 );
     assertEquals( 1, ffl.getFragInfos().size() );
-    assertEquals( "subInfos=(theboth((195,203)))/0.86791086(189,289)", ffl.getFragInfos().get( 0 ).toString() );
+    assertEquals( "subInfos=(theboth((195,203)))/0.86791086(149,249)", ffl.getFragInfos().get( 0 ).toString() );
   }
 
 }