feat: Add bucket management APIs and improve SDK filtering

This commit adds core bucket management functionality and enhances the SDK's internal file filtering to provide a cleaner abstraction layer.

**Bucket Management**:
- Add create_bucket(), delete_bucket(), list_buckets() to DeltaGliderClient
- Idempotent operations (creating existing bucket or deleting non-existent returns success)
- Complete boto3-compatible API for basic bucket operations
- Eliminates need for boto3 in most use cases

**Enhanced SDK Filtering**:
- SDK now filters .delta suffix and reference.bin from all list_objects() responses
- Simplified CLI to rely on SDK filtering (removed duplicate logic)
- Single source of truth for internal file hiding

**Delete Cleanup Logic**:
- Automatically removes orphaned reference.bin when last delta in DeltaSpace is deleted
- Prevents storage waste from abandoned reference files
- Works for both single delete() and recursive delete_recursive()

**Documentation & Testing**:
- Added BOTO3_COMPATIBILITY.md documenting actual 20% method coverage (21/100+ methods)
- Updated README to reflect accurate boto3 compatibility claims
- New comprehensive test suite for filtering and cleanup features (test_filtering_and_cleanup.py)
- New bucket management test suite (test_bucket_management.py)
- Example code for bucket lifecycle management (examples/bucket_management.py)
- Fixed mypy configuration to eliminate source file found twice errors
- All CI checks passing (lint, format, type check, 18 unit tests, 61 integration tests)

**Cleanup**:
- Removed PYPI_RELEASE.md (redundant with existing docs)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Simone Scarduzio
2025-10-03 19:07:08 +02:00
parent dd39595c67
commit 03106b76a8
12 changed files with 1249 additions and 135 deletions
+148 -1
View File
@@ -107,7 +107,16 @@ class BucketStats:
class DeltaGliderClient:
"""DeltaGlider client with boto3-compatible APIs and advanced features."""
"""DeltaGlider client with boto3-compatible APIs and advanced features.
Implements core boto3 S3 client methods (~21 methods covering 80% of use cases):
- Object operations: put_object, get_object, delete_object, list_objects, head_object
- Bucket operations: create_bucket, delete_bucket, list_buckets
- Presigned URLs: generate_presigned_url, generate_presigned_post
- Plus DeltaGlider extensions for compression stats and batch operations
See BOTO3_COMPATIBILITY.md for complete compatibility matrix.
"""
def __init__(self, service: DeltaService, endpoint_url: str | None = None):
"""Initialize client with service."""
@@ -1234,6 +1243,144 @@ class DeltaGliderClient:
},
}
# ============================================================================
# Bucket Management APIs (boto3-compatible)
# ============================================================================
def create_bucket(
self,
Bucket: str,
CreateBucketConfiguration: dict[str, str] | None = None,
**kwargs: Any,
) -> dict[str, Any]:
"""Create an S3 bucket (boto3-compatible).
Args:
Bucket: Bucket name to create
CreateBucketConfiguration: Optional bucket configuration (e.g., LocationConstraint)
**kwargs: Additional S3 parameters (for compatibility)
Returns:
Response dict with bucket location
Example:
>>> client = create_client()
>>> client.create_bucket(Bucket='my-bucket')
>>> # With region
>>> client.create_bucket(
... Bucket='my-bucket',
... CreateBucketConfiguration={'LocationConstraint': 'us-west-2'}
... )
"""
storage_adapter = self.service.storage
# Check if storage adapter has boto3 client
if hasattr(storage_adapter, "client"):
try:
params: dict[str, Any] = {"Bucket": Bucket}
if CreateBucketConfiguration:
params["CreateBucketConfiguration"] = CreateBucketConfiguration
response = storage_adapter.client.create_bucket(**params)
return {
"Location": response.get("Location", f"/{Bucket}"),
"ResponseMetadata": {
"HTTPStatusCode": 200,
},
}
except Exception as e:
error_msg = str(e)
if "BucketAlreadyExists" in error_msg or "BucketAlreadyOwnedByYou" in error_msg:
# Bucket already exists - return success
self.service.logger.debug(f"Bucket {Bucket} already exists")
return {
"Location": f"/{Bucket}",
"ResponseMetadata": {
"HTTPStatusCode": 200,
},
}
raise RuntimeError(f"Failed to create bucket: {e}") from e
else:
raise NotImplementedError("Storage adapter does not support bucket creation")
def delete_bucket(
self,
Bucket: str,
**kwargs: Any,
) -> dict[str, Any]:
"""Delete an S3 bucket (boto3-compatible).
Note: Bucket must be empty before deletion.
Args:
Bucket: Bucket name to delete
**kwargs: Additional S3 parameters (for compatibility)
Returns:
Response dict with deletion status
Example:
>>> client = create_client()
>>> client.delete_bucket(Bucket='my-bucket')
"""
storage_adapter = self.service.storage
# Check if storage adapter has boto3 client
if hasattr(storage_adapter, "client"):
try:
storage_adapter.client.delete_bucket(Bucket=Bucket)
return {
"ResponseMetadata": {
"HTTPStatusCode": 204,
},
}
except Exception as e:
error_msg = str(e)
if "NoSuchBucket" in error_msg:
# Bucket doesn't exist - return success
self.service.logger.debug(f"Bucket {Bucket} does not exist")
return {
"ResponseMetadata": {
"HTTPStatusCode": 204,
},
}
raise RuntimeError(f"Failed to delete bucket: {e}") from e
else:
raise NotImplementedError("Storage adapter does not support bucket deletion")
def list_buckets(self, **kwargs: Any) -> dict[str, Any]:
"""List all S3 buckets (boto3-compatible).
Args:
**kwargs: Additional S3 parameters (for compatibility)
Returns:
Response dict with bucket list
Example:
>>> client = create_client()
>>> response = client.list_buckets()
>>> for bucket in response['Buckets']:
... print(bucket['Name'])
"""
storage_adapter = self.service.storage
# Check if storage adapter has boto3 client
if hasattr(storage_adapter, "client"):
try:
response = storage_adapter.client.list_buckets()
return {
"Buckets": response.get("Buckets", []),
"Owner": response.get("Owner", {}),
"ResponseMetadata": {
"HTTPStatusCode": 200,
},
}
except Exception as e:
raise RuntimeError(f"Failed to list buckets: {e}") from e
else:
raise NotImplementedError("Storage adapter does not support bucket listing")
def _parse_tagging(self, tagging: str) -> dict[str, str]:
"""Parse URL-encoded tagging string to dict."""
tags = {}