From 90fc7e18c7bf7d90bb87fc94d2fff98d7e3eb803 Mon Sep 17 00:00:00 2001
From: Koji Sekiguchi <koji@apache.org>
Date: Thu, 8 Oct 2009 13:34:43 +0000
Subject: [PATCH] LUCENE-1953: FastVectorHighlighter: small fragCharSize can
 cause StringIndexOutOfBoundsException

git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@823170 13f79535-47bb-0310-9956-ffa450edef68
---
 contrib/CHANGES.txt                               |  3 +++
 .../vectorhighlight/SimpleFragListBuilder.java    |  2 ++
 .../SimpleFragListBuilderTest.java                | 15 +++++++++++++++
 3 files changed, 20 insertions(+)

diff --git a/contrib/CHANGES.txt b/contrib/CHANGES.txt
index 6f6d4dcc415..ff8693e4eff 100644
--- a/contrib/CHANGES.txt
+++ b/contrib/CHANGES.txt
@@ -26,6 +26,9 @@ Bug fixes
    Iterator#hasNext method on exhausted streams.
    (Patrick Jungermann via Karl Wettin)
 
+ * LUCENE-1953: FastVectorHighlighter: small fragCharSize can cause
+   StringIndexOutOfBoundsException. (Koji Sekiguchi)
+
 New features
 
  * LUCENE-1924: Added BalancedSegmentMergePolicy to contrib/misc,
diff --git a/contrib/fast-vector-highlighter/src/java/org/apache/lucene/search/vectorhighlight/SimpleFragListBuilder.java b/contrib/fast-vector-highlighter/src/java/org/apache/lucene/search/vectorhighlight/SimpleFragListBuilder.java
index d45ddb10857..089b42e739d 100644
--- a/contrib/fast-vector-highlighter/src/java/org/apache/lucene/search/vectorhighlight/SimpleFragListBuilder.java
+++ b/contrib/fast-vector-highlighter/src/java/org/apache/lucene/search/vectorhighlight/SimpleFragListBuilder.java
@@ -59,6 +59,8 @@ public class SimpleFragListBuilder implements FragListBuilder {
       int st = phraseInfo.getStartOffset() - MARGIN < startOffset ?
           startOffset : phraseInfo.getStartOffset() - MARGIN;
       int en = st + fragCharSize;
+      if( phraseInfo.getEndOffset() > en )
+        en = phraseInfo.getEndOffset();
       startOffset = en;
 
       while( true ){
diff --git a/contrib/fast-vector-highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragListBuilderTest.java b/contrib/fast-vector-highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragListBuilderTest.java
index d5951467506..996dfed2e01 100644
--- a/contrib/fast-vector-highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragListBuilderTest.java
+++ b/contrib/fast-vector-highlighter/src/test/org/apache/lucene/search/vectorhighlight/SimpleFragListBuilderTest.java
@@ -37,6 +37,21 @@ public class SimpleFragListBuilderTest extends AbstractTestCase {
     }
   }
   
+  public void testSmallerFragSizeThanTermQuery() throws Exception {
+    SimpleFragListBuilder sflb = new SimpleFragListBuilder();
+    FieldFragList ffl = sflb.createFieldFragList( fpl( "abcdefghijklmnopqrs", "abcdefghijklmnopqrs" ), SimpleFragListBuilder.MIN_FRAG_CHAR_SIZE );
+    assertEquals( 1, ffl.fragInfos.size() );
+    assertEquals( "subInfos=(abcdefghijklmnopqrs((0,19)))/1.0(0,19)", ffl.fragInfos.get( 0 ).toString() );
+  }
+  
+  public void testSmallerFragSizeThanPhraseQuery() throws Exception {
+    SimpleFragListBuilder sflb = new SimpleFragListBuilder();
+    FieldFragList ffl = sflb.createFieldFragList( fpl( "\"abcdefgh jklmnopqrs\"", "abcdefgh   jklmnopqrs" ), SimpleFragListBuilder.MIN_FRAG_CHAR_SIZE );
+    assertEquals( 1, ffl.fragInfos.size() );
+    System.out.println( ffl.fragInfos.get( 0 ).toString() );
+    assertEquals( "subInfos=(abcdefghjklmnopqrs((0,21)))/1.0(0,21)", ffl.fragInfos.get( 0 ).toString() );
+  }
+  
   public void test1TermIndex() throws Exception {
     SimpleFragListBuilder sflb = new SimpleFragListBuilder();
     FieldFragList ffl = sflb.createFieldFragList( fpl( "a", "a" ), 100 );