Skip to content

change(scripts): verify copied file checksums and skip plots #577

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
kpsherva merged 1 commit into from
Aug 21, 2026
Merged

change(scripts): verify copied file checksums and skip plots #577

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 25 additions & 3 deletions scripts/copy_collection_files.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
import argparse
import hashlib
import json
import os
import shutil
Expand All @@ -8,7 +9,15 @@
sys.setdefaultencoding("utf-8")


def copy_collection_file(dump_files, destination_prefix, working_dir):
def file_md5(path):
md5 = hashlib.md5()
with open(path, "rb") as handle:
for chunk in iter(lambda: handle.read(1024 * 1024), b""):
md5.update(chunk)
return md5.hexdigest()


def copy_collection_file(dump_files, destination_prefix, working_dir, skip_plots=False):
file_log = open(os.path.join(working_dir, "files.log"), "wb")

for i, dump_file in enumerate(dump_files):
Expand All @@ -23,8 +32,10 @@ def copy_collection_file(dump_files, destination_prefix, working_dir):
for record in data:
legacy_record_files = record["files"]
recid = record["recid"]
print("Processing {}".format(recid))
for legacy_record_file in legacy_record_files:
print("Processing {}".format(recid))
if skip_plots and legacy_record_file.get("type") == "Plot":
continue
full_path = legacy_record_file["full_path"]
# important: last slash
path_to_replace = "/opt/cdsweb/var/data/files/"
Expand All @@ -42,6 +53,16 @@ def copy_collection_file(dump_files, destination_prefix, working_dir):
destination_path = destination_path.encode("utf-8")
print(filename)
print(destination_path)

expected = legacy_record_file.get("checksum") or ""
dest_md5 = file_md5(destination_path)
checksum_mismatch = dest_md5 != expected
if checksum_mismatch:
raise ValueError(
"ERROR checksum mismatch: recid={} expected={} dest={}".format(
recid, expected, dest_md5
)
)
file_log.write(
"RECID: %s bibdocid: %s file: %s, destination: %s \n"
% (
Expand All @@ -64,6 +85,7 @@ def get_dump_files_paths(json_dump_dir):

collection = "lep/aleph_drafts"
environment = "dev"
skip_plots = False

destination_prefix = "/eos/media/cds/cds-rdm/{0}/migration/{1}/files".format(
environment, collection
Expand All @@ -74,4 +96,4 @@ def get_dump_files_paths(json_dump_dir):
)

dump_files = get_dump_files_paths(json_dump_dir)
copy_collection_file(dump_files, destination_prefix, working_dir)
copy_collection_file(dump_files, destination_prefix, working_dir, skip_plots=skip_plots)
Loading