From: <dfl...@us...> - 2013-09-06 12:48:13
|
Revision: 4094 http://sourceforge.net/p/dl-learner/code/4094 Author: dfleischhacker Date: 2013-09-06 12:48:08 +0000 (Fri, 06 Sep 2013) Log Message: ----------- Normalize documents to all lowercase Modified Paths: -------------- trunk/components-core/src/main/java/org/dllearner/algorithms/isle/index/TextDocument.java Modified: trunk/components-core/src/main/java/org/dllearner/algorithms/isle/index/TextDocument.java =================================================================== --- trunk/components-core/src/main/java/org/dllearner/algorithms/isle/index/TextDocument.java 2013-09-06 11:36:33 UTC (rev 4093) +++ trunk/components-core/src/main/java/org/dllearner/algorithms/isle/index/TextDocument.java 2013-09-06 12:48:08 UTC (rev 4094) @@ -20,6 +20,7 @@ this.rawContent = content; this.content = content.replaceAll("[^A-Za-z ]", " "); this.content = this.content.replaceAll("\\s{2,}", " "); + this.content = content.toLowerCase(); } @Override This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site. |