Author: toad
Date: 2007-09-14 15:36:57 +0000 (Fri, 14 Sep 2007)
New Revision: 15167
Modified:
trunk/plugins/XMLSpider/XMLSpider.java
Log:
XMLSpider 13: Intern words for much smaller long-term storage cost
Modified: trunk/plugins/XMLSpider/XMLSpider.java
===================================================================
--- trunk/plugins/XMLSpider/XMLSpider.java 2007-09-14 15:18:46 UTC (rev
15166)
+++ trunk/plugins/XMLSpider/XMLSpider.java 2007-09-14 15:36:57 UTC (rev
15167)
@@ -138,7 +138,7 @@
*/
public Set allowedMIMETypes;
private static final int MAX_ENTRIES = 200;
- private static int version = 12;
+ private static int version = 13;
private static final String pluginName = "XML spider "+version;
/**
* Gives the allowed fraction of total time spent on generating indices
with
@@ -1118,6 +1118,7 @@
if ((word == null) || (word.length() == 0))
continue;
word = word.toLowerCase();
+ word = word.intern();
try{
if(type == null)
addWord(word,
lastPosition.intValue() + i, id);