Author: jnioche
Date: Wed Jan 5 19:51:15 2011
New Revision: 1055608
URL: http://svn.apache.org/viewvc?rev=1055608&view=rev
Log:
NUTCH-950 DomainURLFilter throws NPE on bogus urls
Modified:
nutch/trunk/CHANGES.txt
nutch/trunk/src/plugin/urlfilter-domain/src/java/org/apache/nutch/urlfilter/domain/DomainURLFilter.java
Modified: nutch/trunk/CHANGES.txt
URL:
http://svn.apache.org/viewvc/nutch/trunk/CHANGES.txt?rev=1055608&r1=1055607&r2=1055608&view=diff
==============================================================================
--- nutch/trunk/CHANGES.txt (original)
+++ nutch/trunk/CHANGES.txt Wed Jan 5 19:51:15 2011
@@ -2,6 +2,8 @@ Nutch Change Log
Release 2.0 - Current Development
+* NUTCH-950 DomainURLFilter throws NPE on bogus urls (Alexis Detreglode via
jnioche)
+
* NUTCH-935 basicurlnormalizer removes unnecessary /./ in URLs
* NUTCH-912 MoreIndexingFilter does not parse docx and xlsx date formats
(Markus Jelsma, jnioche)
Modified:
nutch/trunk/src/plugin/urlfilter-domain/src/java/org/apache/nutch/urlfilter/domain/DomainURLFilter.java
URL:
http://svn.apache.org/viewvc/nutch/trunk/src/plugin/urlfilter-domain/src/java/org/apache/nutch/urlfilter/domain/DomainURLFilter.java?rev=1055608&r1=1055607&r2=1055608&view=diff
==============================================================================
---
nutch/trunk/src/plugin/urlfilter-domain/src/java/org/apache/nutch/urlfilter/domain/DomainURLFilter.java
(original)
+++
nutch/trunk/src/plugin/urlfilter-domain/src/java/org/apache/nutch/urlfilter/domain/DomainURLFilter.java
Wed Jan 5 19:51:15 2011
@@ -32,6 +32,7 @@ import org.apache.nutch.net.URLFilter;
import org.apache.nutch.plugin.Extension;
import org.apache.nutch.plugin.PluginRepository;
import org.apache.nutch.util.URLUtil;
+import org.apache.nutch.util.domain.DomainSuffix;
/**
* <p>Filters URLs based on a file containing domain suffixes, domain names,
and
@@ -174,9 +175,14 @@ public class DomainURLFilter
// match for suffix, domain, and host in that order. more general will
// override more specific
- String suffix = URLUtil.getDomainSuffix(url).getDomain();
String domain = URLUtil.getDomainName(url).toLowerCase().trim();
String host = URLUtil.getHost(url);
+ String suffix = null;
+ DomainSuffix domainSuffix = URLUtil.getDomainSuffix(url);
+ if (domainSuffix != null) {
+ suffix = domainSuffix.getDomain();
+ }
+
if (domainSet.contains(suffix) || domainSet.contains(domain)
|| domainSet.contains(host)) {
return url;