Author: markus Date: Mon Jun 11 09:28:14 2012 New Revision: 1348764 URL: http://svn.apache.org/viewvc?rev=1348764&view=rev Log: NUTCH-1385 More robust plug-in order properties in nutch-site.xml
Modified: nutch/trunk/CHANGES.txt nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFilters.java nutch/trunk/src/java/org/apache/nutch/net/URLFilters.java nutch/trunk/src/java/org/apache/nutch/net/URLNormalizers.java nutch/trunk/src/java/org/apache/nutch/parse/HtmlParseFilters.java nutch/trunk/src/java/org/apache/nutch/scoring/ScoringFilters.java Modified: nutch/trunk/CHANGES.txt URL: http://svn.apache.org/viewvc/nutch/trunk/CHANGES.txt?rev=1348764&r1=1348763&r2=1348764&view=diff ============================================================================== --- nutch/trunk/CHANGES.txt (original) +++ nutch/trunk/CHANGES.txt Mon Jun 11 09:28:14 2012 @@ -2,6 +2,8 @@ Nutch Change Log (trunk) Current Development: +* NUTCH-1385 More robust plug-in order properties in nutch-site.xml (Andy Xue via markus) + * NUTCH-1336 Optionally not index db_notmodified pages (markus) * NUTCH-1346 Follow outlinks to ignore external (markus) Modified: nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFilters.java URL: http://svn.apache.org/viewvc/nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFilters.java?rev=1348764&r1=1348763&r2=1348764&view=diff ============================================================================== --- nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFilters.java (original) +++ nutch/trunk/src/java/org/apache/nutch/indexer/IndexingFilters.java Mon Jun 11 09:28:14 2012 @@ -54,7 +54,7 @@ public class IndexingFilters { */ String[] orderedFilters = null; if (order != null && !order.trim().equals("")) { - orderedFilters = order.split("\\s+"); + orderedFilters = order.trim().split("\\s+"); } try { ExtensionPoint point = PluginRepository.get(conf).getExtensionPoint( Modified: nutch/trunk/src/java/org/apache/nutch/net/URLFilters.java URL: http://svn.apache.org/viewvc/nutch/trunk/src/java/org/apache/nutch/net/URLFilters.java?rev=1348764&r1=1348763&r2=1348764&view=diff ============================================================================== --- nutch/trunk/src/java/org/apache/nutch/net/URLFilters.java (original) +++ nutch/trunk/src/java/org/apache/nutch/net/URLFilters.java Mon Jun 11 09:28:14 2012 @@ -42,7 +42,7 @@ public class URLFilters { if (this.filters == null) { String[] orderedFilters = null; if (order != null && !order.trim().equals("")) { - orderedFilters = order.split("\\s+"); + orderedFilters = order.trim().split("\\s+"); } try { Modified: nutch/trunk/src/java/org/apache/nutch/net/URLNormalizers.java URL: http://svn.apache.org/viewvc/nutch/trunk/src/java/org/apache/nutch/net/URLNormalizers.java?rev=1348764&r1=1348763&r2=1348764&view=diff ============================================================================== --- nutch/trunk/src/java/org/apache/nutch/net/URLNormalizers.java (original) +++ nutch/trunk/src/java/org/apache/nutch/net/URLNormalizers.java Mon Jun 11 09:28:14 2012 @@ -234,7 +234,7 @@ public final class URLNormalizers { String orderlist = conf.get("urlnormalizer.order." + scope); if (orderlist == null) orderlist = conf.get("urlnormalizer.order"); if (orderlist != null && !orderlist.trim().equals("")) { - orders = orderlist.split("\\s+"); + orders = orderlist.trim().split("\\s+"); } String scopelist = conf.get("urlnormalizer.scope." + scope); Set<String> impls = null; Modified: nutch/trunk/src/java/org/apache/nutch/parse/HtmlParseFilters.java URL: http://svn.apache.org/viewvc/nutch/trunk/src/java/org/apache/nutch/parse/HtmlParseFilters.java?rev=1348764&r1=1348763&r2=1348764&view=diff ============================================================================== --- nutch/trunk/src/java/org/apache/nutch/parse/HtmlParseFilters.java (original) +++ nutch/trunk/src/java/org/apache/nutch/parse/HtmlParseFilters.java Mon Jun 11 09:28:14 2012 @@ -45,7 +45,7 @@ public class HtmlParseFilters { */ String[] orderedFilters = null; if (order != null && !order.trim().equals("")) { - orderedFilters = order.split("\\s+"); + orderedFilters = order.trim().split("\\s+"); } HashMap<String, HtmlParseFilter> filterMap = new HashMap<String, HtmlParseFilter>(); Modified: nutch/trunk/src/java/org/apache/nutch/scoring/ScoringFilters.java URL: http://svn.apache.org/viewvc/nutch/trunk/src/java/org/apache/nutch/scoring/ScoringFilters.java?rev=1348764&r1=1348763&r2=1348764&view=diff ============================================================================== --- nutch/trunk/src/java/org/apache/nutch/scoring/ScoringFilters.java (original) +++ nutch/trunk/src/java/org/apache/nutch/scoring/ScoringFilters.java Mon Jun 11 09:28:14 2012 @@ -56,7 +56,7 @@ public class ScoringFilters extends Conf if (this.filters == null) { String[] orderedFilters = null; if (order != null && !order.trim().equals("")) { - orderedFilters = order.split("\\s+"); + orderedFilters = order.trim().split("\\s+"); } try {