Author: kwright
Date: Thu Jan 10 08:43:42 2013
New Revision: 1431209
URL: http://svn.apache.org/viewvc?rev=1431209&view=rev
Log:
Exclude negative bytes from isStrange test
Modified:
manifoldcf/trunk/connectors/webcrawler/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/webcrawler/WebcrawlerConnector.java
Modified:
manifoldcf/trunk/connectors/webcrawler/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/webcrawler/WebcrawlerConnector.java
URL:
http://svn.apache.org/viewvc/manifoldcf/trunk/connectors/webcrawler/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/webcrawler/WebcrawlerConnector.java?rev=1431209&r1=1431208&r2=1431209&view=diff
==============================================================================
---
manifoldcf/trunk/connectors/webcrawler/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/webcrawler/WebcrawlerConnector.java
(original)
+++
manifoldcf/trunk/connectors/webcrawler/connector/src/main/java/org/apache/manifoldcf/crawler/connectors/webcrawler/WebcrawlerConnector.java
Thu Jan 10 08:43:42 2013
@@ -6903,7 +6903,7 @@ public class WebcrawlerConnector extends
/** Check if character is not typical ASCII or utf-8. */
protected static boolean isStrange(byte x)
{
- return (x < 32) && (!isWhiteSpace(x));
+ return (x >= 0 && x < 32) && (!isWhiteSpace(x));
}
/** Check if a byte is a whitespace character. */