From 8a0e3198ca553688cdfab25823c60a67c4d2f0db Mon Sep 17 00:00:00 2001
From: Dawid Weiss <dweiss@apache.org>
Date: Thu, 5 Jul 2012 14:41:03 +0000
Subject: [PATCH] LUCENE-4194: more encoding fixes.

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1357636 13f79535-47bb-0310-9956-ffa450edef68
---
 .../apache/lucene/benchmark/byTask/TestPerfTasksParse.java   | 5 ++++-
 .../org/apache/lucene/search/highlight/HighlighterTest.java  | 2 +-
 .../test/org/apache/lucene/queryparser/xml/TestParser.java   | 3 ++-
 3 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/TestPerfTasksParse.java b/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/TestPerfTasksParse.java
index a06efa59064..36734bd5c85 100755
--- a/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/TestPerfTasksParse.java
+++ b/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/TestPerfTasksParse.java
@@ -19,9 +19,12 @@ package org.apache.lucene.benchmark.byTask;
 
 import java.io.File;
 import java.io.FileFilter;
+import java.io.FileInputStream;
 import java.io.FileReader;
 import java.io.IOException;
+import java.io.InputStreamReader;
 import java.io.StringReader;
+import java.nio.charset.Charset;
 import java.util.ArrayList;
 
 import org.apache.lucene.benchmark.byTask.feeds.AbstractQueryMaker;
@@ -113,7 +116,7 @@ public class TestPerfTasksParse extends LuceneTestCase {
       public boolean accept(File pathname) { return pathname.isFile() && pathname.getName().endsWith(".alg"); }
     })) {
       try {
-        Config config = new Config(new FileReader(algFile));
+        Config config = new Config(new InputStreamReader(new FileInputStream(algFile), "UTF-8"));
         String contentSource = config.get("content.source", null);
         if (contentSource != null) { Class.forName(contentSource); }
         config.set("work.dir", new File(TEMP_DIR,"work").getAbsolutePath());
diff --git a/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java b/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
index 4f0fddbafa8..67ea75f940c 100644
--- a/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
+++ b/lucene/highlighter/src/test/org/apache/lucene/search/highlight/HighlighterTest.java
@@ -1371,7 +1371,7 @@ public class HighlighterTest extends BaseTokenStreamTestCase implements Formatte
     // now an ugly built of XML parsing to test the snippet is encoded OK
     DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
     DocumentBuilder db = dbf.newDocumentBuilder();
-    org.w3c.dom.Document doc = db.parse(new ByteArrayInputStream(xhtml.getBytes()));
+    org.w3c.dom.Document doc = db.parse(new ByteArrayInputStream(xhtml.getBytes("UTF-8")));
     Element root = doc.getDocumentElement();
     NodeList nodes = root.getElementsByTagName("body");
     Element body = (Element) nodes.item(0);
diff --git a/lucene/queryparser/src/test/org/apache/lucene/queryparser/xml/TestParser.java b/lucene/queryparser/src/test/org/apache/lucene/queryparser/xml/TestParser.java
index 4f7e4380633..e087f644a54 100644
--- a/lucene/queryparser/src/test/org/apache/lucene/queryparser/xml/TestParser.java
+++ b/lucene/queryparser/src/test/org/apache/lucene/queryparser/xml/TestParser.java
@@ -61,7 +61,8 @@ public class TestParser extends LuceneTestCase {
     //initialize the parser
     builder = new CorePlusExtensionsParser("contents", analyzer);
 
-    BufferedReader d = new BufferedReader(new InputStreamReader(TestParser.class.getResourceAsStream("reuters21578.txt")));
+    BufferedReader d = new BufferedReader(new InputStreamReader(
+        TestParser.class.getResourceAsStream("reuters21578.txt"), "US-ASCII"));
     dir = newDirectory();
     IndexWriter writer = new IndexWriter(dir, newIndexWriterConfig(Version.LUCENE_40, analyzer));
     String line = d.readLine();