From 13b08aca349002bcf967bf171546225c2b497462 Mon Sep 17 00:00:00 2001
From: Chris Malloy <cjmalloy@gmail.com>
Date: Tue, 18 Jul 2023 16:37:31 -0300
Subject: [PATCH] Periodically clear failed cache items

---
 src/main/java/jasper/component/WebScraper.java     | 6 ++++++
 src/main/java/jasper/repository/WebRepository.java | 3 +++
 2 files changed, 9 insertions(+)

diff --git a/src/main/java/jasper/component/WebScraper.java b/src/main/java/jasper/component/WebScraper.java
index ac6b342c..01de281e 100644
--- a/src/main/java/jasper/component/WebScraper.java
+++ b/src/main/java/jasper/component/WebScraper.java
@@ -34,6 +34,7 @@
 import java.util.Set;
 import java.util.concurrent.BlockingQueue;
 import java.util.concurrent.LinkedBlockingQueue;
+import java.util.concurrent.TimeUnit;
 
 import static com.fasterxml.jackson.databind.node.TextNode.valueOf;
 import static jasper.domain.proj.Tag.hasMedia;
@@ -681,6 +682,11 @@ public void drainAsyncScrape() {
 		scraping.clear();
 	}
 
+	@Scheduled(fixedDelay = 5, timeUnit = TimeUnit.MINUTES)
+	public void clearFailed() {
+		webRepository.deleteAllByDataIsNullAndMimeIsNull();
+	}
+
 	@Timed(value = "jasper.webscrape")
 	public Web fetch(String url) {
 		url = fixUrl(url);
diff --git a/src/main/java/jasper/repository/WebRepository.java b/src/main/java/jasper/repository/WebRepository.java
index d299580a..5ce81dda 100644
--- a/src/main/java/jasper/repository/WebRepository.java
+++ b/src/main/java/jasper/repository/WebRepository.java
@@ -3,7 +3,10 @@
 import jasper.domain.Web;
 import org.springframework.data.jpa.repository.JpaRepository;
 import org.springframework.stereotype.Repository;
+import org.springframework.transaction.annotation.Transactional;
 
 @Repository
+@Transactional
 public interface WebRepository extends JpaRepository<Web, String> {
+	void deleteAllByDataIsNullAndMimeIsNull();
 }