implement file caching

to prevent having to download files multiple times

lib/obs.py

@@ -1,9 +1,11 @@
 import errno
 import logging
+import shutil
 import time
 import urllib.parse
 import xml.etree.ElementTree as ET
 from urllib.error import HTTPError
+from pathlib import Path
 
 import osc.core
 
@@ -160,8 +162,13 @@ class OBS:
         dirpath: str,
         file_md5: str,
     ) -> None:
-        with (dirpath / name).open("wb") as f:
-            f.write(self._download(project, package, name, revision).read())
+        cached_file = self._path_from_md5(name, dirpath, file_md5)
+        if not self.in_cache(name, dirpath, file_md5):
+            with (dirpath / name).open("wb") as f:
+                f.write(self._download(project, package, name, revision).read())
+            shutil.copy(dirpath / name, cached_file)
+        else:
+            shutil.copy(cached_file, dirpath / name)
 
     def list(self, project, package, srcmd5, linkrev):
         params = {"rev": srcmd5, "expand": "1"}
@@ -179,3 +186,16 @@ class OBS:
             raise e
 
         return root
+
+    def _path_from_md5(self, name, dirpath, md5):
+        cache = dirpath.joinpath(".cache/")
+        if not Path(cache).exists():
+            cache.mkdir()
+        filepath = cache.joinpath(f"{md5[0:3]}/{md5[3:6]}/{md5[6:9]}/")
+        filepath.mkdir(parents=True, exist_ok=True)
+        return filepath.joinpath(f"{md5[9:]}-{name}")
+
+    def in_cache(self, name, dirpath, md5):
+        if self._path_from_md5(name, dirpath, md5).is_file():
+            return True
+        return False