torproject/metrics-lib
1
0
Fork 0
mirror of https://github.com/torproject/metrics-lib.git synced 2025-02-14 14:28:52 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Fix encoding problem when parsing multi-descriptor files.

Browse Source 
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.
This commit is contained in:
Karsten Loesing 2014-05-25 12:32:36 +02:00
parent 38c48ddd0c
commit b298cbcbd1
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/org/torproject/descriptor/impl/DescriptorImpl.java
View File

@ -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("@") ||