You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by le...@apache.org on 2014/04/17 00:16:20 UTC

svn commit: r1588088 - in /nutch/branches/2.x: CHANGES.txt src/plugin/parse-zip/src/java/org/apache/nutch/parse/zip/ZipParser.java

Author: lewismc
Date: Wed Apr 16 22:16:20 2014
New Revision: 1588088

URL: http://svn.apache.org/r1588088
Log:
NUTCH-1603 ZIP parser complains about truncated PDF file

Modified:
    nutch/branches/2.x/CHANGES.txt
    nutch/branches/2.x/src/plugin/parse-zip/src/java/org/apache/nutch/parse/zip/ZipParser.java

Modified: nutch/branches/2.x/CHANGES.txt
URL: http://svn.apache.org/viewvc/nutch/branches/2.x/CHANGES.txt?rev=1588088&r1=1588087&r2=1588088&view=diff
==============================================================================
--- nutch/branches/2.x/CHANGES.txt (original)
+++ nutch/branches/2.x/CHANGES.txt Wed Apr 16 22:16:20 2014
@@ -2,6 +2,8 @@ Nutch Change Log
 
 Current Development
 
+* NUTCH-1603 ZIP parser complains about truncated PDF file (snagel via lewismc)
+
 * NUTCH-1743 parsechecker to show outlinks (snagel)
 
 * NUTCH-1732 Better cmd line parsing for NutchServer (Fjodor Vershinin via lewismc)

Modified: nutch/branches/2.x/src/plugin/parse-zip/src/java/org/apache/nutch/parse/zip/ZipParser.java
URL: http://svn.apache.org/viewvc/nutch/branches/2.x/src/plugin/parse-zip/src/java/org/apache/nutch/parse/zip/ZipParser.java?rev=1588088&r1=1588087&r2=1588088&view=diff
==============================================================================
--- nutch/branches/2.x/src/plugin/parse-zip/src/java/org/apache/nutch/parse/zip/ZipParser.java (original)
+++ nutch/branches/2.x/src/plugin/parse-zip/src/java/org/apache/nutch/parse/zip/ZipParser.java Wed Apr 16 22:16:20 2014
@@ -69,7 +69,7 @@ public class ZipParser implements Parser
         return new ParseStatus(ParseStatus.FAILED,
             ParseStatus.FAILED_TRUNCATED, "Content truncated at "
                 + contentInBytes.length
-                + " bytes. Parser can't handle incomplete pdf file.")
+                + " bytes. Parser can't handle incomplete zip file.")
             .getEmptyParseResult(content.getUrl(), getConf());
       }