cmarschner 2002/06/17 07:16:13
Modified: contributions/webcrawler-LARM/src/de/lanlab/larm/util
WebDocument.java
Log:
added URLNormalizer
Revision Changes Path
1.4 +3 -2 jakarta-lucene-sandbox/contributions/webcrawler-LARM/src/de/lanlab/larm/util/WebDocument.java
Index: WebDocument.java
===================================================================
RCS file: /home/cvs/jakarta-lucene-sandbox/contributions/webcrawler-LARM/src/de/lanlab/larm/util/WebDocument.java,v
retrieving revision 1.3
retrieving revision 1.4
diff -u -r1.3 -r1.4
--- WebDocument.java 1 Jun 2002 18:55:16 -0000 1.3
+++ WebDocument.java 17 Jun 2002 14:16:12 -0000 1.4
@@ -57,6 +57,7 @@
import java.net.URL;
import de.lanlab.larm.fetcher.URLMessage;
+import de.lanlab.larm.net.HostManager;
/**
* a web document of whatever type. generated by a fetcher task
@@ -69,9 +70,9 @@
protected int size;
protected String title;
- public WebDocument(URL url, String mimeType, byte[] document, int resultCode, URL referer, int size, String title)
+ public WebDocument(URL url, String mimeType, byte[] document, int resultCode, URL referer, int size, String title, HostManager hm)
{
- super(url, referer, false, null);
+ super(url, referer, false, null, hm);
this.url = url;
this.mimeType = mimeType;
this.document = document;
--
To unsubscribe, e-mail: <mailto:lucene-dev-unsubscribe@jakarta.apache.org>
For additional commands, e-mail: <mailto:lucene-dev-help@jakarta.apache.org>
Modified: contributions/webcrawler-LARM/src/de/lanlab/larm/util
WebDocument.java
Log:
added URLNormalizer
Revision Changes Path
1.4 +3 -2 jakarta-lucene-sandbox/contributions/webcrawler-LARM/src/de/lanlab/larm/util/WebDocument.java
Index: WebDocument.java
===================================================================
RCS file: /home/cvs/jakarta-lucene-sandbox/contributions/webcrawler-LARM/src/de/lanlab/larm/util/WebDocument.java,v
retrieving revision 1.3
retrieving revision 1.4
diff -u -r1.3 -r1.4
--- WebDocument.java 1 Jun 2002 18:55:16 -0000 1.3
+++ WebDocument.java 17 Jun 2002 14:16:12 -0000 1.4
@@ -57,6 +57,7 @@
import java.net.URL;
import de.lanlab.larm.fetcher.URLMessage;
+import de.lanlab.larm.net.HostManager;
/**
* a web document of whatever type. generated by a fetcher task
@@ -69,9 +70,9 @@
protected int size;
protected String title;
- public WebDocument(URL url, String mimeType, byte[] document, int resultCode, URL referer, int size, String title)
+ public WebDocument(URL url, String mimeType, byte[] document, int resultCode, URL referer, int size, String title, HostManager hm)
{
- super(url, referer, false, null);
+ super(url, referer, false, null, hm);
this.url = url;
this.mimeType = mimeType;
this.document = document;
--
To unsubscribe, e-mail: <mailto:lucene-dev-unsubscribe@jakarta.apache.org>
For additional commands, e-mail: <mailto:lucene-dev-help@jakarta.apache.org>