lee/heritrix3
1
0
Fork 0
mirror of https://github.com/internetarchive/heritrix3.git synced 2026-09-26 07:35:39 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix for null paths

Browse Source 
* TooManyPathSegmentsDecideRule
    Sometimes the path is null, throwing a NPE when the loop in evaluate(CrawlURI)
    is entered. In such a case, revert to previous behavior.
This commit is contained in:
Travis Wellman
2012-07-10 18:01:53 -07:00
parent 4ca6e9cc99
commit 9505edc9c3
1 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/src/main/java/org/archive/modules/deciderules/TooManyPathSegmentsDecideRule.java
+9
View File
@@ -18,6 +18,9 @@
*/
package org.archive.modules.deciderules;
import java.util.logging.Level;
import java.util.logging.Logger;
import org.archive.modules.CrawlURI;
/**
@@ -30,6 +33,7 @@ import org.archive.modules.CrawlURI;
public class TooManyPathSegmentsDecideRule extends PredicatedDecideRule {
private static final long serialVersionUID = 3L;
private static final Logger logger = Logger.getLogger(TooManyPathSegmentsDecideRule.class.getName());
/** default for this class is to REJECT */
{
@@ -64,6 +68,11 @@ public class TooManyPathSegmentsDecideRule extends PredicatedDecideRule {
@Override
protected boolean evaluate(CrawlURI curi) {
String uriPath = curi.getUURI().getEscapedPath();
if (uriPath == null) {
uriPath = curi.toString();
// TODO this is a quick fix. figure out why getUURI().getEscapedPath() returns null.
logger.log(Level.WARNING, "getUURI().getEscapedPath() returns null for the given CrawlURI: "+ uriPath);
}
int count = 0;
int threshold = getMaxPathDepth();
for (int i = 0; i < uriPath.length(); i++) {