You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@nutch.apache.org by pk...@apache.org on 2006/03/09 22:13:44 UTC
svn commit: r384617 - in /lucene/nutch/branches/branch-0.7: CHANGES.txt
src/plugin/parse-html/src/java/org/apache/nutch/parse/html/HtmlParser.java
Author: pkosiorowski
Date: Thu Mar 9 13:13:42 2006
New Revision: 384617
URL: http://svn.apache.org/viewcvs?rev=384617&view=rev
Log:
NUTCH-91 - empty encoding causes exception. (Michael Nebel)
Modified:
lucene/nutch/branches/branch-0.7/CHANGES.txt
lucene/nutch/branches/branch-0.7/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/HtmlParser.java
Modified: lucene/nutch/branches/branch-0.7/CHANGES.txt
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/branch-0.7/CHANGES.txt?rev=384617&r1=384616&r2=384617&view=diff
==============================================================================
--- lucene/nutch/branches/branch-0.7/CHANGES.txt (original)
+++ lucene/nutch/branches/branch-0.7/CHANGES.txt Thu Mar 9 13:13:42 2006
@@ -16,6 +16,8 @@
6. Fixed TestFetcher JUnit test failing due to changes in www.nutch.org
website.
+ 7. NUTCH-91 - empty encoding causes exception. (Michael Nebel).
+
Release 0.7.1 - 2005-10-01
Modified: lucene/nutch/branches/branch-0.7/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/HtmlParser.java
URL: http://svn.apache.org/viewcvs/lucene/nutch/branches/branch-0.7/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/HtmlParser.java?rev=384617&r1=384616&r2=384617&view=diff
==============================================================================
--- lucene/nutch/branches/branch-0.7/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/HtmlParser.java (original)
+++ lucene/nutch/branches/branch-0.7/src/plugin/parse-html/src/java/org/apache/nutch/parse/html/HtmlParser.java Thu Mar 9 13:13:42 2006
@@ -120,7 +120,7 @@
byte[] contentInOctets = content.getContent();
InputSource input = new InputSource(new ByteArrayInputStream(contentInOctets));
String encoding = StringUtil.parseCharacterEncoding(contentType);
- if (encoding!=null) {
+ if ((encoding != null) && !("".equals(encoding))) {
metadata.put("OriginalCharEncoding", encoding);
if ((encoding = StringUtil.resolveEncodingAlias(encoding)) != null) {
metadata.put("CharEncodingForConversion", encoding);
@@ -129,7 +129,7 @@
}
// sniff out 'charset' value from the beginning of a document
- if (encoding == null) {
+ if ((encoding == null) || ("".equals(encoding))) {
encoding = sniffCharacterEncoding(contentInOctets);
if (encoding!=null) {
metadata.put("OriginalCharEncoding", encoding);