You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@uima.apache.org by pk...@apache.org on 2014/09/29 11:07:49 UTC

svn commit: r1628140 - /uima/ruta/trunk/ruta-core/src/main/java/org/apache/uima/ruta/engine/HtmlConverter.java

Author: pkluegl
Date: Mon Sep 29 09:07:48 2014
New Revision: 1628140

URL: http://svn.apache.org/r1628140
Log:
UIMA-4025
- applied patch

Modified:
    uima/ruta/trunk/ruta-core/src/main/java/org/apache/uima/ruta/engine/HtmlConverter.java

Modified: uima/ruta/trunk/ruta-core/src/main/java/org/apache/uima/ruta/engine/HtmlConverter.java
URL: http://svn.apache.org/viewvc/uima/ruta/trunk/ruta-core/src/main/java/org/apache/uima/ruta/engine/HtmlConverter.java?rev=1628140&r1=1628139&r2=1628140&view=diff
==============================================================================
--- uima/ruta/trunk/ruta-core/src/main/java/org/apache/uima/ruta/engine/HtmlConverter.java (original)
+++ uima/ruta/trunk/ruta-core/src/main/java/org/apache/uima/ruta/engine/HtmlConverter.java Mon Sep 29 09:07:48 2014
@@ -344,8 +344,8 @@ public class HtmlConverter extends JCasA
   private SortedSet<HtmlConverterPSpan> htmlDecoding(SortedSet<HtmlConverterPSpan> visibleSpansSoFar) {
     TreeSet<HtmlConverterPSpan> copy = new TreeSet<HtmlConverterPSpan>(visibleSpansSoFar);
 
-    Pattern patt = Pattern.compile("(&[a-zA-Z]{2,5};)|(&#\\d{2,5};)");
-
+    Pattern patt = Pattern.compile("(&[a-zA-Z0-9]{2,6};)|(&#\\d{2,5};)");
+    
     for (HtmlConverterPSpan pSpan : visibleSpansSoFar) {
       String spanTxt = pSpan.getTxt();
       Matcher matcher = patt.matcher(spanTxt);