Author: jukka
Date: Fri Nov 13 03:49:27 2009
New Revision: 835726
URL: http://svn.apache.org/viewvc?rev=835726&view=rev
Log:
TIKA-319: HtmlParser - use encoding hint only if charset is supported
Fixed as suggested by Piotr B.
Modified:
lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java
Modified:
lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java
URL:
http://svn.apache.org/viewvc/lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java?rev=835726&r1=835725&r2=835726&view=diff
==============================================================================
---
lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java
(original)
+++
lucene/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/html/HtmlParser.java
Fri Nov 13 03:49:27 2009
@@ -18,6 +18,7 @@
import java.io.IOException;
import java.io.InputStream;
+import java.nio.charset.Charset;
import java.util.Collections;
import java.util.Map;
@@ -46,7 +47,7 @@
// Prepare the input source using the encoding hint if available
InputSource source = new InputSource(stream);
String encoding = metadata.get(Metadata.CONTENT_ENCODING);
- if (encoding != null) {
+ if (encoding != null && Charset.isSupported(encoding)) {
source.setEncoding(encoding);
}