fix: robust bug fixes and storage verification tools #110
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,91 @@ | ||
|
|
||
| import frappe | ||
| import os | ||
| from cloud_storage.cloud_storage.overrides.file import get_cloud_storage_client, get_cloud_storage_config | ||
| from botocore.exceptions import ClientError | ||
|
|
||
| def execute(): | ||
| print(f"\n{'='*50}") | ||
| print(f"Storage Verification for Site: {frappe.local.site}") | ||
| print(f"{'='*50}") | ||
|
|
||
| # 1. Get All Files from DB | ||
| files = frappe.get_all( | ||
| "File", | ||
| fields=["name", "file_name", "file_url", "is_private", "s3_key", "is_folder"], | ||
| filters={"is_folder": 0} | ||
| ) | ||
| total_db_files = len(files) | ||
| print(f"Total Files in DB: {total_db_files}") | ||
|
|
||
| config = get_cloud_storage_config() | ||
| if not config: | ||
| print("Cloud Storage not configured for this site.") | ||
| return | ||
|
|
||
| try: | ||
| client = get_cloud_storage_client() | ||
| bucket = client.bucket | ||
| except Exception as e: | ||
| print(f"Failed to initialize MinIO client: {e}") | ||
| return | ||
|
|
||
| local_count = 0 | ||
| minio_count = 0 | ||
| synced_count = 0 | ||
|
Collaborator
There was a problem hiding this comment.
|
||
| missing_local = [] | ||
| missing_minio = [] | ||
|
|
||
| print("\nScanning files...") | ||
|
|
||
| for f in files: | ||
| # Check Local | ||
| if f.is_private: | ||
| local_path = frappe.get_site_path("private", "files", f.file_name) | ||
| else: | ||
| local_path = frappe.get_site_path("public", "files", f.file_name) | ||
|
Collaborator
There was a problem hiding this comment. This assumes all public files are in Should we use something like: local_path = frappe.get_site_path("public", f.file_url.lstrip("/")) |
||
|
|
||
| if os.path.exists(local_path): | ||
| local_count += 1 | ||
| else: | ||
| missing_local.append(f.file_name) | ||
|
|
||
| # Check MinIO | ||
| in_minio = False | ||
| if f.s3_key: | ||
| try: | ||
| client.head_object(Bucket=bucket, Key=f.s3_key) | ||
| in_minio = True | ||
| minio_count += 1 | ||
| synced_count += 1 | ||
| except ClientError: | ||
| missing_minio.append(f.file_name) | ||
| else: | ||
| # Not marked as migrated (s3_key is empty/null) | ||
| pass | ||
|
|
||
| print(f"\n{'='*50}") | ||
| print(f"Verification Summary for {frappe.local.site}") | ||
| print(f"{'='*50}") | ||
| print(f"Total Records in DB: {total_db_files}") | ||
| print(f"Found Locally: {local_count}") | ||
| print(f"Found in MinIO (Verified): {minio_count}") | ||
| print(f"Marked as Migrated (DB): {len([f for f in files if f.s3_key])}") | ||
| print(f"{'='*50}") | ||
|
|
||
| if missing_local: | ||
| print(f"\n[WARNING] Missing Local Files ({len(missing_local)}):") | ||
| print(", ".join(missing_local[:10]) + ("..." if len(missing_local) > 10 else "")) | ||
|
|
||
| if missing_minio: | ||
| print(f"\n[ERROR] Missing in MinIO (DB claims migrated) ({len(missing_minio)}):") | ||
| print(", ".join(missing_minio[:10]) + ("..." if len(missing_minio) > 10 else "")) | ||
|
|
||
| # Verification of count | ||
|
Collaborator
There was a problem hiding this comment. Comparing
A better logic would be: marked_as_migrated = len([f for f in files if f.s3_key])
if marked_as_migrated != minio_count:
print(f"[ERROR] Sync Issue: DB claims {marked_as_migrated} files migrated, but only {minio_count} found in cloud!")This catches the critical case where DB thinks files are migrated but they're missing from cloud storage. |
||
| if local_count != minio_count: | ||
| print(f"\n[INFO] Count Mismatch: Local ({local_count}) vs MinIO ({minio_count})") | ||
| print("Note: This is expected if partial migration or if 'remove_local' was used.") | ||
| else: | ||
| print("\n[SUCCESS] Local and MinIO counts match (for migrated files).") | ||
|
|
||
| print(f"{'='*50}\n") | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This project supports S3, DigitalOcean Spaces, Backblaze, etc. Consider using generic messaging like: