Author: markus Date: Tue Jan 19 14:53:05 2016 New Revision: 1725538 URL: http://svn.apache.org/viewvc?rev=1725538&view=rev Log: NUTCH-2203 Suffix URL filter can't handle trailing/leading whitespaces
Modified: nutch/trunk/CHANGES.txt nutch/trunk/src/plugin/urlfilter-suffix/src/java/org/apache/nutch/urlfilter/suffix/SuffixURLFilter.java Modified: nutch/trunk/CHANGES.txt URL: http://svn.apache.org/viewvc/nutch/trunk/CHANGES.txt?rev=1725538&r1=1725537&r2=1725538&view=diff ============================================================================== --- nutch/trunk/CHANGES.txt (original) +++ nutch/trunk/CHANGES.txt Tue Jan 19 14:53:05 2016 @@ -1,5 +1,7 @@ Nutch Change Log +* NUTCH-2203 Suffix URL filter can't handle trailing/leading whitespaces (Jurian Broertjes via markus) + * NUTCH-2194 Run IndexingFilterChecker as simple Telnet server (markus) * NUTCH-2196 IndexingFilterChecker to optionally normalize (markus) Modified: nutch/trunk/src/plugin/urlfilter-suffix/src/java/org/apache/nutch/urlfilter/suffix/SuffixURLFilter.java URL: http://svn.apache.org/viewvc/nutch/trunk/src/plugin/urlfilter-suffix/src/java/org/apache/nutch/urlfilter/suffix/SuffixURLFilter.java?rev=1725538&r1=1725537&r2=1725538&view=diff ============================================================================== --- nutch/trunk/src/plugin/urlfilter-suffix/src/java/org/apache/nutch/urlfilter/suffix/SuffixURLFilter.java (original) +++ nutch/trunk/src/plugin/urlfilter-suffix/src/java/org/apache/nutch/urlfilter/suffix/SuffixURLFilter.java Tue Jan 19 14:53:05 2016 @@ -196,6 +196,7 @@ public class SuffixURLFilter implements String line; while ((line = in.readLine()) != null) { + line = line.trim(); if (line.length() == 0) continue;