Marown/yacy_search_server
1
0
Fork 0
mirror of https://github.com/yacy/yacy_search_server.git synced 2024-09-19 00:01:41 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity

check the document protocol & host values before proceeding to form final url.

Browse Source
This commit is contained in:
zutto 2024-06-29 10:11:58 +03:00
parent 962aaec0c0
commit 5268ae2ce9
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
source/net/yacy/crawler/data/CrawlQueues.java
View File

@ -617,6 +617,10 @@ public class CrawlQueues {
deep = true;
}
DigestURL url;
if (doc.getFieldValue("url_protocol_s") == null || doc.getFieldValue("host_s") == null) {
//Skip this document if either of these values is null.
continue;
}
final String u = doc.getFieldValue("url_protocol_s").toString() + "://" + doc.getFieldValue("host_s").toString();
try {
url = new DigestURL(u);