From 5268ae2ce93c07cd222909fc0732060cc378184a Mon Sep 17 00:00:00 2001
From: zutto <zutto@localhost>
Date: Sat, 29 Jun 2024 10:11:58 +0300
Subject: [PATCH] check the document protocol & host values before proceeding
 to form final url.

---
 source/net/yacy/crawler/data/CrawlQueues.java | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/source/net/yacy/crawler/data/CrawlQueues.java b/source/net/yacy/crawler/data/CrawlQueues.java
index 30a5ea93a..38c8e8a2c 100644
--- a/source/net/yacy/crawler/data/CrawlQueues.java
+++ b/source/net/yacy/crawler/data/CrawlQueues.java
@@ -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);