[tor-commits] [metrics-lib/master] Fix encoding problem when parsing multi-descriptor files.

[karsten at torproject.org]

commit b298cbcbd167c14a12d05c49e93b2795d98e209a
Author: Karsten Loesing <karsten.loesing at gmx.net>
Date:   Sun May 25 12:32:36 2014 +0200

    Fix encoding problem when parsing multi-descriptor files.
    
    When we're parsing a descriptor file with potentially more than one
    descriptor in it, we're converting file contents to String to be able to
    search for descriptor beginnings using String methods.  But we're not
    passing a character encoding, leaving it up to Java to guess.  What we
    should do is tell it to use "US-ASCII" as encoding, which is sufficient to
    find keywords marking the beginning of a new descriptor.
    
    Fixes #11821.
---
 src/org/torproject/descriptor/impl/DescriptorImpl.java |    8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/src/org/torproject/descriptor/impl/DescriptorImpl.java b/src/org/torproject/descriptor/impl/DescriptorImpl.java
index 770ee4f..ee50ec6 100644
--- a/src/org/torproject/descriptor/impl/DescriptorImpl.java
+++ b/src/org/torproject/descriptor/impl/DescriptorImpl.java
@@ -2,6 +2,7 @@
  * See LICENSE for licensing information */
 package org.torproject.descriptor.impl;
 
+import java.io.UnsupportedEncodingException;
 import java.util.ArrayList;
 import java.util.HashMap;
 import java.util.List;
@@ -107,7 +108,12 @@ public abstract class DescriptorImpl implements Descriptor {
       byte[] rawDescriptorBytes, String startToken) {
     List<byte[]> rawDescriptors = new ArrayList<byte[]>();
     String splitToken = "\n" + startToken;
-    String ascii = new String(rawDescriptorBytes);
+    String ascii;
+    try {
+      ascii = new String(rawDescriptorBytes, "US-ASCII");
+    } catch (UnsupportedEncodingException e) {
+      return rawDescriptors;
+    }
     int endAllDescriptors = rawDescriptorBytes.length,
         startAnnotations = 0;
     boolean containsAnnotations = ascii.startsWith("@") ||