Author: ab Date: Wed Apr 5 10:01:02 2006 New Revision: 391676 URL: http://svn.apache.org/viewcvs?rev=391676&view=rev Log: Fix protocol-level redirect code. Patch by Dennis Kubes.
Make it clear that this is a protocol-level redirect, as opposed to a content-level redirect. Modified: lucene/nutch/trunk/src/java/org/apache/nutch/fetcher/Fetcher.java Modified: lucene/nutch/trunk/src/java/org/apache/nutch/fetcher/Fetcher.java URL: http://svn.apache.org/viewcvs/lucene/nutch/trunk/src/java/org/apache/nutch/fetcher/Fetcher.java?rev=391676&r1=391675&r2=391676&view=diff ============================================================================== --- lucene/nutch/trunk/src/java/org/apache/nutch/fetcher/Fetcher.java (original) +++ lucene/nutch/trunk/src/java/org/apache/nutch/fetcher/Fetcher.java Wed Apr 5 10:01:02 2006 @@ -116,6 +116,7 @@ lastRequestStart = System.currentTimeMillis(); } + // url may be changed through redirects. String url = key.toString(); try { LOG.info("fetching " + url); // fetch the page @@ -126,7 +127,7 @@ redirecting = false; LOG.fine("redirectCount=" + redirectCount); Protocol protocol = this.protocolFactory.getProtocol(url); - ProtocolOutput output = protocol.getProtocolOutput(key, datum); + ProtocolOutput output = protocol.getProtocolOutput(new UTF8(url), datum); ProtocolStatus status = output.getStatus(); Content content = output.getContent(); @@ -145,9 +146,9 @@ url = newUrl; redirecting = true; redirectCount++; - LOG.fine(" - redirect to " + url); + LOG.fine(" - protocol redirect to " + url); } else { - LOG.fine(" - redirect skipped: " + + LOG.fine(" - protocol redirect skipped: " + (url.equals(newUrl) ? "to same url" : "filtered")); } break;