You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2012/04/11 14:16:31 UTC

svn commit: r1324727 - /lucene/dev/branches/lucene3969/modules/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java

Author: rmuir
Date: Wed Apr 11 12:16:31 2012
New Revision: 1324727

URL: http://svn.apache.org/viewvc?rev=1324727&view=rev
Log:
LUCENE-3969: when outputting a bigram token, mark posLen=2 to note that it spans two tokens

Modified:
    lucene/dev/branches/lucene3969/modules/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java

Modified: lucene/dev/branches/lucene3969/modules/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/lucene3969/modules/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java?rev=1324727&r1=1324726&r2=1324727&view=diff
==============================================================================
--- lucene/dev/branches/lucene3969/modules/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java (original)
+++ lucene/dev/branches/lucene3969/modules/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java Wed Apr 11 12:16:31 2012
@@ -16,6 +16,7 @@ import org.apache.lucene.analysis.TokenS
 import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
 import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+import org.apache.lucene.analysis.tokenattributes.PositionLengthAttribute;
 import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
 import org.apache.lucene.analysis.util.CharArraySet;
 import org.apache.lucene.util.Version;
@@ -54,6 +55,7 @@ public final class CommonGramsFilter ext
   private final OffsetAttribute offsetAttribute = addAttribute(OffsetAttribute.class);
   private final TypeAttribute typeAttribute = addAttribute(TypeAttribute.class);
   private final PositionIncrementAttribute posIncAttribute = addAttribute(PositionIncrementAttribute.class);
+  private final PositionLengthAttribute posLenAttribute = addAttribute(PositionLengthAttribute.class);
 
   private int lastStartOffset;
   private boolean lastWasCommon;
@@ -166,6 +168,7 @@ public final class CommonGramsFilter ext
     buffer.getChars(0, length, termText, 0);
     termAttribute.setLength(length);
     posIncAttribute.setPositionIncrement(0);
+    posLenAttribute.setPositionLength(2); // bigram
     offsetAttribute.setOffset(lastStartOffset, endOffset);
     typeAttribute.setType(GRAM_TYPE);
     buffer.setLength(0);