Author: ab
Date: Wed Mar 9 12:01:55 2011
New Revision: 1079765
URL: http://svn.apache.org/viewvc?rev=1079765&view=rev
Log:
NUTCH-962 max. redirects not handled correctly: fetcher stops at max-1
redirects.
Modified:
nutch/branches/branch-1.3/CHANGES.txt
nutch/branches/branch-1.3/src/java/org/apache/nutch/fetcher/Fetcher.java
Modified: nutch/branches/branch-1.3/CHANGES.txt
URL:
http://svn.apache.org/viewvc/nutch/branches/branch-1.3/CHANGES.txt?rev=1079765&r1=1079764&r2=1079765&view=diff
==============================================================================
--- nutch/branches/branch-1.3/CHANGES.txt (original)
+++ nutch/branches/branch-1.3/CHANGES.txt Wed Mar 9 12:01:55 2011
@@ -2,6 +2,8 @@ Nutch Change Log
Release 1.3 - Current Development
+* NUTCH-962 max. redirects not handled correctly: fetcher stops at max-1
redirects (Sebastian Nagel via ab)
+
* NUTCH-921 Reduce dependency of Nutch on config files (ab)
* NUTCH-876 Remove remaining robots/IP blocking code in lib-http (ab)
Modified:
nutch/branches/branch-1.3/src/java/org/apache/nutch/fetcher/Fetcher.java
URL:
http://svn.apache.org/viewvc/nutch/branches/branch-1.3/src/java/org/apache/nutch/fetcher/Fetcher.java?rev=1079765&r1=1079764&r2=1079765&view=diff
==============================================================================
--- nutch/branches/branch-1.3/src/java/org/apache/nutch/fetcher/Fetcher.java
(original)
+++ nutch/branches/branch-1.3/src/java/org/apache/nutch/fetcher/Fetcher.java
Wed Mar 9 12:01:55 2011
@@ -751,7 +751,7 @@ public class Fetcher extends Configured
output(fit.url, fit.datum, null, status,
CrawlDatum.STATUS_FETCH_RETRY);
}
- if (redirecting && redirectCount >= maxRedirect) {
+ if (redirecting && redirectCount > maxRedirect) {
fetchQueues.finishFetchItem(fit);
if (LOG.isInfoEnabled()) {
LOG.info(" - redirect count exceeded " + fit.url);
@@ -759,7 +759,7 @@ public class Fetcher extends Configured
output(fit.url, fit.datum, null,
ProtocolStatus.STATUS_REDIR_EXCEEDED, CrawlDatum.STATUS_FETCH_GONE);
}
- } while (redirecting && (redirectCount < maxRedirect));
+ } while (redirecting && (redirectCount <= maxRedirect));
} catch (Throwable t) { // unexpected exception
// unblock