Added unused blobs removal script
authorThierry Florac <tflorac@ulthar.net>
Tue, 05 Feb 2019 09:40:54 +0100
changeset 177 d160b2d18797
parent 176 4eb49f19314a
child 178 8361af8c753f
Added unused blobs removal script
src/pyams_file/script/__init__.py
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/src/pyams_file/script/__init__.py	Tue Feb 05 09:40:54 2019 +0100
@@ -0,0 +1,60 @@
+#
+# Copyright (c) 2008-2019 Thierry Florac <tflorac AT ulthar.net>
+# All Rights Reserved.
+#
+# This software is subject to the provisions of the Zope Public License,
+# Version 2.1 (ZPL).  A copy of the ZPL should accompany this distribution.
+# THIS SOFTWARE IS PROVIDED "AS IS" AND ANY AND ALL EXPRESS OR IMPLIED
+# WARRANTIES ARE DISCLAIMED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+# WARRANTIES OF TITLE, MERCHANTABILITY, AGAINST INFRINGEMENT, AND FITNESS
+# FOR A PARTICULAR PURPOSE.
+#
+
+__docformat__ = 'restructuredtext'
+
+
+from ZODB.utils import oid_repr, p64
+
+from pyams_file.interfaces import IBlobReferenceManager
+from pyams_utils.registry import get_utility, set_local_registry
+
+
+def remove_unused_blobs(root):
+    """Blobs removal scripts
+
+    This file is intended to be used from *pshell* after running an *mdtools.relstorage* command like this:
+
+    /var/local/env/pyams$ ./bin/zodbsearch --config etc/zodb-relstorage.conf \
+        --data pyams_file.file.File pyams_file.file.ImageFile pyams_file.file.SVGImageFile \
+        pyams_file.file.VideoFile pyams_file.file.AudioFile 2>&1 \
+        | grep found | awk '{print $7}' | sort -u | cut -d \" -f 2 > var/FILES.oids
+
+    P.S.: this command can be used with any database storage (ZEO, Relstorage or Newt)!!!
+
+    This command will generate a FILES.oids file in "var" directory, containing the OIDs of all
+    files stored in the ZODB.
+
+    The script will then read this file and get access to all stored files; if the file blob is not referenced
+    into blobs references manager, it can be removed. Removal is done by removing all references to it, so that
+    the blob file will be physically removed after next database pack.
+    """
+
+    set_local_registry(root.getSiteManager())
+    references = get_utility(IBlobReferenceManager)
+
+    db = getattr(root, '_p_jar')
+    files = open('var/FILES.oids', 'r')
+
+    for foid in files.readlines():
+        if not foid:
+            continue
+        file_oid = p64(int(foid, 16))
+        file = db.get(file_oid)
+        blob = getattr(file, '_blob', None)
+        if blob is not None:
+            blob_oid = oid_repr(getattr(blob, '_p_oid'))
+            if blob_oid not in references.refs:
+                delattr(file, '_blob')
+                file._blob = None
+                file.__parent__ = None
+                print("{!r}".format(file))