From f96b02af060feaa044b85224bfbfeeb548e8b1da Mon Sep 17 00:00:00 2001
From: Doron Cohen <doronc@apache.org>
Date: Fri, 7 Dec 2012 11:31:53 +0000
Subject: [PATCH] LUCENE--4595: EnwikiContentSource thread safety NPE in
 'forever' mode

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1418281 13f79535-47bb-0310-9956-ffa450edef68
---
 lucene/CHANGES.txt                            |  3 ++
 .../byTask/feeds/EnwikiContentSource.java     | 32 ++++++++++---------
 2 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/lucene/CHANGES.txt b/lucene/CHANGES.txt
index cd0d78a0b74..d6a7d92d3e7 100644
--- a/lucene/CHANGES.txt
+++ b/lucene/CHANGES.txt
@@ -219,6 +219,9 @@ Bug Fixes
   In addition, it wasn't possible to index a shape representing the entire
   globe.
 
+* LUCENE--4595: EnwikiContentSource had a thread safety problem (NPE) in 
+  'forever' mode (Doron Cohen)
+
 Optimizations
 
 * LUCENE-2221: oal.util.BitUtil was modified to use Long.bitCount and
diff --git a/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSource.java b/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSource.java
index 4a0dde0920d..09745cbe88e 100644
--- a/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSource.java
+++ b/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/EnwikiContentSource.java
@@ -178,23 +178,25 @@ public class EnwikiContentSource extends ContentSource {
         reader.setErrorHandler(this);
         while(!stopped){
           final InputStream localFileIS = is;
-          try {
-            // To work around a bug in XERCES (XERCESJ-1257), we assume the XML is always UTF8, so we simply provide reader.
-            CharsetDecoder decoder = IOUtils.CHARSET_UTF_8.newDecoder()
-                .onMalformedInput(CodingErrorAction.REPORT)
-                .onUnmappableCharacter(CodingErrorAction.REPORT);
-            reader.parse(new InputSource(new BufferedReader(new InputStreamReader(localFileIS, decoder))));
-          } catch (IOException ioe) {
-            synchronized(EnwikiContentSource.this) {
-              if (localFileIS != is) {
-                // fileIS was closed on us, so, just fall through
-              } else
-                // Exception is real
-                throw ioe;
+          if (localFileIS != null) { // null means fileIS was closed on us 
+            try {
+              // To work around a bug in XERCES (XERCESJ-1257), we assume the XML is always UTF8, so we simply provide reader.
+              CharsetDecoder decoder = IOUtils.CHARSET_UTF_8.newDecoder()
+                  .onMalformedInput(CodingErrorAction.REPORT)
+                  .onUnmappableCharacter(CodingErrorAction.REPORT);
+              reader.parse(new InputSource(new BufferedReader(new InputStreamReader(localFileIS, decoder))));
+            } catch (IOException ioe) {
+              synchronized(EnwikiContentSource.this) {
+                if (localFileIS != is) {
+                  // fileIS was closed on us, so, just fall through
+                } else
+                  // Exception is real
+                  throw ioe;
+              }
             }
           }
           synchronized(this) {
-            if (!forever) {
+            if (stopped || !forever) {
               nmde = new NoMoreDataException();
               notify();
               return;
@@ -291,11 +293,11 @@ public class EnwikiContentSource extends ContentSource {
   @Override
   public void close() throws IOException {
     synchronized (EnwikiContentSource.this) {
+      parser.stop();
       if (is != null) {
         is.close();
         is = null;
       }
-      parser.stop();
     }
   }