Merge pull request 'Add a list of packages no longer existing' (#22) from add_gone into main

Reviewed-on: https://gitea.opensuse.org/importers/git-importer/pulls/22

lib/importer.py

@@ -1,5 +1,6 @@
 import concurrent.futures
 import logging
+import pathlib
 import xml.etree.ElementTree as ET
 
 from lib.db import DB
@@ -31,6 +32,7 @@ class Importer:
         self.obs = OBS(api_url)
         assert project == "openSUSE:Factory"
         self.refreshed_packages = set()
+        self.gone_packages_set = None
 
     def import_request(self, number):
         self.obs.request(number).import_into_db(self.db)
@@ -208,6 +210,8 @@ class Importer:
         if key in self.refreshed_packages:
             # refreshing once is good enough
             return
+        if self.package_gone(key):
+            return
         logging.debug(f"Refresh {project}/{package}")
         self.refreshed_packages.add(key)
         self.update_db_package(project, package)
@@ -254,3 +258,11 @@ class Importer:
 
         self.fill_file_lists()
         self.db.conn.commit()
+
+    def package_gone(self, key):
+        if not self.gone_packages_set:
+            self.gone_packages_set = set()
+            with open(pathlib.Path(__file__).parent.parent / "gone-packages.txt") as f:
+                for line in f.readlines():
+                    self.gone_packages_set.add(line.strip())
+        return key in self.gone_packages_set