You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@jackrabbit.apache.org by mr...@apache.org on 2009/10/28 10:25:24 UTC

svn commit: r830478 - /jackrabbit/branches/1.6/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/HTMLParser.java

Author: mreutegg
Date: Wed Oct 28 09:25:24 2009
New Revision: 830478

URL: http://svn.apache.org/viewvc?rev=830478&view=rev
Log:
JCR-2365: HTML Text Extractor does not extract or index numerics

Modified:
    jackrabbit/branches/1.6/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/HTMLParser.java

Modified: jackrabbit/branches/1.6/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/HTMLParser.java
URL: http://svn.apache.org/viewvc/jackrabbit/branches/1.6/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/HTMLParser.java?rev=830478&r1=830477&r2=830478&view=diff
==============================================================================
--- jackrabbit/branches/1.6/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/HTMLParser.java (original)
+++ jackrabbit/branches/1.6/jackrabbit-text-extractors/src/main/java/org/apache/jackrabbit/extractor/HTMLParser.java Wed Oct 28 09:25:24 2009
@@ -70,7 +70,7 @@
                     continue;
                 }
             } else {
-                if (!Character.isLetter(c)) {
+                if (!Character.isLetterOrDigit(c)) {
                     if (!space) {
                         space = true;
                         buffer.append(' ');