From 9155e5f4f9d9d1d6746e451136f4d1e1ceba1dcc Mon Sep 17 00:00:00 2001
From: gojomo <gojomo@daa5b2f2-a927-0410-8b2d-f5f262fa301a>
Date: Thu, 14 May 2009 21:19:24 +0000
Subject: [PATCH] copying noah's work to h3 Fix for [HER-1506]
 ByteReplayCharSequence ignores specified/non-default character encodings,
 reported by Jean-No?\195?\171l Rivasseau * RecordingOutputStream.java     use
 ByteReplayCharSequence only for iso8859-1 * ReplayCharSequenceTest.java    
 new tests for iso8859-1, windows-1252 and ascii

---
 .../org/archive/io/RecordingOutputStream.java | 11 ++--
 .../archive/io/ReplayCharSequenceTest.java    | 51 +++++++++++++++++++
 2 files changed, 58 insertions(+), 4 deletions(-)

diff --git a/commons/src/main/java/org/archive/io/RecordingOutputStream.java b/commons/src/main/java/org/archive/io/RecordingOutputStream.java
index b0358d9f..0537fe38 100644
--- a/commons/src/main/java/org/archive/io/RecordingOutputStream.java
+++ b/commons/src/main/java/org/archive/io/RecordingOutputStream.java
@@ -29,6 +29,7 @@ import it.unimi.dsi.fastutil.io.FastBufferedOutputStream;
 import java.io.FileOutputStream;
 import java.io.IOException;
 import java.io.OutputStream;
+import java.nio.charset.Charset;
 import java.security.MessageDigest;
 import java.security.NoSuchAlgorithmException;
 import java.util.logging.Level;
@@ -515,6 +516,8 @@ public class RecordingOutputStream extends OutputStream {
         return getReplayCharSequence(characterEncoding, this.contentBeginMark);
     }
     
+    private static final String canonicalLatin1 = Charset.forName("iso8859-1").name();
+    
     /**
      * @param characterEncoding Encoding of recorded stream.
      * @return A ReplayCharSequence  Will return null if an IOException.  Call
@@ -523,11 +526,11 @@ public class RecordingOutputStream extends OutputStream {
      */
     public ReplayCharSequence getReplayCharSequence(String characterEncoding, 
             long startOffset) throws IOException {
+        if (characterEncoding == null) {
+            characterEncoding = Charset.defaultCharset().name();
+        }
         // TODO: handled transfer-encoding: chunked content-bodies properly
-        float maxBytesPerChar = IoUtils.encodingMaxBytesPerChar(characterEncoding);
-        if(maxBytesPerChar<=1) {
-            // single
-            // TODO: take into account single-byte encoding may be non-default
+        if (canonicalLatin1.equals(Charset.forName(characterEncoding).name())) {
             return new Latin1ByteReplayCharSequence(
                     this.buffer, 
                     this.size, 
diff --git a/commons/src/test/java/org/archive/io/ReplayCharSequenceTest.java b/commons/src/test/java/org/archive/io/ReplayCharSequenceTest.java
index 614e05cb..32e20bb9 100644
--- a/commons/src/test/java/org/archive/io/ReplayCharSequenceTest.java
+++ b/commons/src/test/java/org/archive/io/ReplayCharSequenceTest.java
@@ -158,6 +158,57 @@ public class ReplayCharSequenceTest extends TmpDirTestCase
         assertEquals("Strings don't match",result,fileContent);
     }
     
+    private String toHexString(String str)
+    {
+        if (str != null) {
+            StringBuilder buf = new StringBuilder("{ ");
+            buf.append(Integer.toString(str.charAt(0), 16));
+            for (int i = 1; i < str.length(); i++) {
+                buf.append(", ");
+                buf.append(Integer.toString(str.charAt(i), 16));
+            }
+            buf.append(" }");
+            return buf.toString();
+        }
+        else 
+            return "null";
+    }
+     
+    public void testSingleByteEncodings() throws IOException {
+        byte[] bytes = {
+            (byte) 0x61, (byte) 0x62, (byte) 0x63, (byte) 0x64,
+            (byte) 0x7d, (byte) 0x7e, (byte) 0x7f, (byte) 0x80,
+            (byte) 0x81, (byte) 0x82, (byte) 0x83, (byte) 0x84,
+            (byte) 0xfc, (byte) 0xfd, (byte) 0xfe, (byte) 0xff };
+
+        String latin1String = new String(bytes, "latin1");
+        RecordingOutputStream ros = writeTestStream(
+                bytes, 1, "testSingleByteEncodings-latin1.txt", 0);
+        ReplayCharSequence rcs = ros.getReplayCharSequence("latin1");
+        String result = rcs.toString();
+        logger.info("latin1[0] " + toHexString(latin1String));
+        logger.info("latin1[1] " + toHexString(result));
+        assertEquals("latin1 strings don't match", result, latin1String);
+        
+        String w1252String = new String(bytes, "windows-1252");
+        ros = writeTestStream(
+                bytes, 1, "testSingleByteEncodings-windows-1252.txt", 0);
+        rcs = ros.getReplayCharSequence("windows-1252");
+        result = rcs.toString();
+        logger.info("windows-1252[0] " + toHexString(w1252String));
+        logger.info("windows-1252[1] " + toHexString(result));
+        assertEquals("windows-1252 strings don't match", result, w1252String);
+
+        String asciiString = new String(bytes, "ascii");
+        ros = writeTestStream(
+                bytes, 1, "testSingleByteEncodings-ascii.txt", 0);
+        rcs = ros.getReplayCharSequence("ascii");
+        result = rcs.toString();
+        logger.info("ascii[0] " + toHexString(asciiString));
+        logger.info("ascii[1] " + toHexString(result));
+        assertEquals("ascii strings don't match", result, asciiString);
+    }
+    
     public void testReplayCharSequenceByteToStringOverflow() throws IOException {
         String fileContent = "Some file content. ";
         byte [] buffer = fileContent.getBytes();