You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by ma...@apache.org on 2010/11/22 15:28:30 UTC
svn commit: r1037732 -
/nutch/branches/branch-1.3/src/plugin/languageidentifier/src/java/org/apache/nutch/analysis/lang/LanguageIndexingFilter.java
Author: markus
Date: Mon Nov 22 14:28:29 2010
New Revision: 1037732
URL: http://svn.apache.org/viewvc?rev=1037732&view=rev
Log:
NUTCH-936 - LanguageIdentifier should not set empty lang field on NutchDocument
Modified:
nutch/branches/branch-1.3/src/plugin/languageidentifier/src/java/org/apache/nutch/analysis/lang/LanguageIndexingFilter.java
Modified: nutch/branches/branch-1.3/src/plugin/languageidentifier/src/java/org/apache/nutch/analysis/lang/LanguageIndexingFilter.java
URL: http://svn.apache.org/viewvc/nutch/branches/branch-1.3/src/plugin/languageidentifier/src/java/org/apache/nutch/analysis/lang/LanguageIndexingFilter.java?rev=1037732&r1=1037731&r2=1037732&view=diff
==============================================================================
--- nutch/branches/branch-1.3/src/plugin/languageidentifier/src/java/org/apache/nutch/analysis/lang/LanguageIndexingFilter.java (original)
+++ nutch/branches/branch-1.3/src/plugin/languageidentifier/src/java/org/apache/nutch/analysis/lang/LanguageIndexingFilter.java Mon Nov 22 14:28:29 2010
@@ -85,7 +85,7 @@ public class LanguageIndexingFilter impl
lang = this.languageIdentifier.identify(text);
}
- if (lang == null) {
+ if (lang == null || lang.length() == 0) {
lang = "unknown";
}