From faca588e9353180eaa66cfe2a087333a7e8f9d4d Mon Sep 17 00:00:00 2001
From: Robert Muir <rmuir@apache.org>
Date: Thu, 15 Mar 2012 19:12:41 +0000
Subject: [PATCH] LUCENE-3874: don't let bogus positions corrumpt the index

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1301155 13f79535-47bb-0310-9956-ffa450edef68
---
 lucene/CHANGES.txt                            |  6 +++++
 .../lucene/index/DocInverterPerField.java     | 12 +++++++---
 .../index/TestIndexWriterExceptions.java      | 23 +++++++++++++++++++
 3 files changed, 38 insertions(+), 3 deletions(-)

diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
index 08fc4719a0a..c66ae9507bc 100644
--- a/lucene/CHANGES.txt
+++ b/lucene/CHANGES.txt
@@ -937,6 +937,12 @@ Bug fixes
 * LUCENE-3872: IndexWriter.close() now throws IllegalStateException if
   you call it after calling prepareCommit() without calling commit()
   first.  (Tim Bogaert via Mike McCandless)
+
+* LUCENE-3874: Throw IllegalArgumentException from IndexWriter (rather
+  than producing a corrupt index), if a positionIncrement would cause
+  integer overflow. This can happen, for example when using a buggy
+  TokenStream that forgets to call clearAttributes() in combination
+  with a StopFilter. (Robert Muir)
     
 Optimizations
 
diff --git a/lucene/core/src/java/org/apache/lucene/index/DocInverterPerField.java b/lucene/core/src/java/org/apache/lucene/index/DocInverterPerField.java
index 47e4dc88a71..d8a3acdf230 100644
--- a/lucene/core/src/java/org/apache/lucene/index/DocInverterPerField.java
+++ b/lucene/core/src/java/org/apache/lucene/index/DocInverterPerField.java
@@ -109,10 +109,16 @@ final class DocInverterPerField extends DocFieldConsumerPerField {
             if (!hasMoreTokens) break;
 
             final int posIncr = posIncrAttribute.getPositionIncrement();
-            fieldState.position += posIncr;
-            if (fieldState.position > 0) {
-              fieldState.position--;
+            int position = fieldState.position + posIncr;
+            if (position > 0) {
+              position--;
+            } else if (position < 0) {
+              throw new IllegalArgumentException("position overflow for field '" + field.name() + "'");
             }
+            
+            // position is legal, we can safely place it in fieldState now.
+            // not sure if anything will use fieldState after non-aborting exc...
+            fieldState.position = position;
 
             if (posIncr == 0)
               fieldState.numOverlap++;
diff --git a/lucene/core/src/test/org/apache/lucene/index/TestIndexWriterExceptions.java b/lucene/core/src/test/org/apache/lucene/index/TestIndexWriterExceptions.java
index 8554f02a626..a4503dcc353 100644
--- a/lucene/core/src/test/org/apache/lucene/index/TestIndexWriterExceptions.java
+++ b/lucene/core/src/test/org/apache/lucene/index/TestIndexWriterExceptions.java
@@ -1494,4 +1494,27 @@ public class TestIndexWriterExceptions extends LuceneTestCase {
     uoe.doFail = false;
     d.close();
   }
+  
+  public void testIllegalPositions() throws Exception {
+    Directory dir = newDirectory();
+    IndexWriter iw = new IndexWriter(dir, newIndexWriterConfig(TEST_VERSION_CURRENT, null));
+    Document doc = new Document();
+    Token t1 = new Token("foo", 0, 3);
+    t1.setPositionIncrement(Integer.MAX_VALUE);
+    Token t2 = new Token("bar", 4, 7);
+    t2.setPositionIncrement(200);
+    TokenStream overflowingTokenStream = new CannedTokenStream(
+        new Token[] { t1, t2 }
+    );
+    Field field = new TextField("foo", overflowingTokenStream);
+    doc.add(field);
+    try {
+      iw.addDocument(doc);
+      fail();
+    } catch (IllegalArgumentException expected) {
+      // expected exception
+    }
+    iw.close();
+    dir.close();
+  }
 }