Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Use HTMLStripCharFilter instead of deprecated HTMLStripReader 

git-svn-id: https://svn.apache.org/repos/asf/lucene/solr/trunk@819638 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Shalin Shekhar Mangar 2009-09-28 16:44:26 +00:00
parent 36a99b82fc
commit fae44c8c06
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
contrib/dataimporthandler/src/main/java/org/apache/solr/handler/dataimport/HTMLStripTransformer.java
View File

@ -16,10 +16,12 @@
*/
package org.apache.solr.handler.dataimport;
import org.apache.solr.analysis.HTMLStripReader;
import org.apache.solr.analysis.HTMLStripCharFilter;
import org.apache.lucene.analysis.CharReader;
import java.io.IOException;
import java.io.StringReader;
import java.io.BufferedReader;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
@ -29,7 +31,7 @@ import java.util.Map;
* in case you don't need this HTML anyway.
*
* @version $Id$
* @see org.apache.solr.analysis.HTMLStripReader
* @see org.apache.solr.analysis.HTMLStripCharFilter
* @since solr 1.4
*/
public class HTMLStripTransformer extends Transformer {
@ -73,7 +75,7 @@ public class HTMLStripTransformer extends Transformer {
StringBuilder out = new StringBuilder();
StringReader strReader = new StringReader(value);
try {
HTMLStripReader html = new HTMLStripReader(strReader);
HTMLStripCharFilter html = new HTMLStripCharFilter(CharReader.get(strReader.markSupported() ? strReader : new BufferedReader(strReader)));
char[] cbuf = new char[1024 * 10];
while (true) {
int count = html.read(cbuf);