Author: ab
Date: Thu Jul 1 12:22:39 2010
New Revision: 959631
URL: http://svn.apache.org/viewvc?rev=959631&view=rev
Log:
Merge from trunk rev. 959629.
Modified:
nutch/branches/branch-1.2/CHANGES.txt
nutch/branches/branch-1.2/src/java/org/apache/nutch/crawl/MD5Signature.java
Modified: nutch/branches/branch-1.2/CHANGES.txt
URL:
http://svn.apache.org/viewvc/nutch/branches/branch-1.2/CHANGES.txt?rev=959631&r1=959630&r2=959631&view=diff
==============================================================================
--- nutch/branches/branch-1.2/CHANGES.txt (original)
+++ nutch/branches/branch-1.2/CHANGES.txt Thu Jul 1 12:22:39 2010
@@ -2,6 +2,8 @@ Nutch Change Log
Release 1.2 - Current Development
+* NUTCH-835 Document deduplication failed using MD5Signature (Sebastian Nagel
via ab)
+
* NUTCH-831 Allow configuration of how fields crawled by Nutch are stored /
indexed /
tokenized (Jeroen van Vianen via mattmann)
Modified:
nutch/branches/branch-1.2/src/java/org/apache/nutch/crawl/MD5Signature.java
URL:
http://svn.apache.org/viewvc/nutch/branches/branch-1.2/src/java/org/apache/nutch/crawl/MD5Signature.java?rev=959631&r1=959630&r2=959631&view=diff
==============================================================================
--- nutch/branches/branch-1.2/src/java/org/apache/nutch/crawl/MD5Signature.java
(original)
+++ nutch/branches/branch-1.2/src/java/org/apache/nutch/crawl/MD5Signature.java
Thu Jul 1 12:22:39 2010
@@ -33,7 +33,6 @@ public class MD5Signature extends Signat
public byte[] calculate(Content content, Parse parse) {
byte[] data = content.getContent();
if (data == null) data = content.getUrl().getBytes();
- StringBuilder buf = new
StringBuilder().append(data).append(parse.getText());
- return MD5Hash.digest(buf.toString().getBytes()).getDigest();
+ return MD5Hash.digest(data).getDigest();
}
}