* full integration with iceberg-go * Table Commit Operations (handleUpdateTable) * s3tables: fix Iceberg v2 compliance and namespace properties This commit ensures SeaweedFS Iceberg REST Catalog is compliant with Iceberg Format Version 2 by: - Using iceberg-go's table.NewMetadataWithUUID for strict v2 compliance. - Explicitly initializing namespace properties to empty maps. - Removing omitempty from required Iceberg response fields. - Fixing CommitTableRequest unmarshaling using table.Requirements and table.Updates. * s3tables: automate Iceberg integration tests - Added Makefile for local test execution and cluster management. - Added docker-compose for PyIceberg compatibility kit. - Added Go integration test harness for PyIceberg. - Updated GitHub CI to run Iceberg catalog tests automatically. * s3tables: update PyIceberg test suite for compatibility - Updated test_rest_catalog.py to use latest PyIceberg transaction APIs. - Updated Dockerfile to include pyarrow and pandas dependencies. - Improved namespace and table handling in integration tests. * s3tables: address review feedback on Iceberg Catalog - Implemented robust metadata version parsing and incrementing. - Ensured table metadata changes are persisted during commit (handleUpdateTable). - Standardized namespace property initialization for consistency. - Fixed unused variable and incorrect struct field build errors. * s3tables: finalize Iceberg REST Catalog and optimize tests - Implemented robust metadata versioning and persistence. - Standardized namespace property initialization. - Optimized integration tests using pre-built Docker image. - Added strict property persistence validation to test suite. - Fixed build errors from previous partial updates. * Address PR review: fix Table UUID stability, implement S3Tables UpdateTable, and support full metadata persistence individually * fix: Iceberg catalog stable UUIDs, metadata persistence, and file writing - Ensure table UUIDs are stable (do not regenerate on load). - Persist full table metadata (Iceberg JSON) in s3tables extended attributes. - Add `MetadataVersion` to explicitly track version numbers, replacing regex parsing. - Implement `saveMetadataFile` to persist metadata JSON files to the Filer on commit. - Update `CreateTable` and `UpdateTable` handlers to use the new logic. * test: bind weed mini to 0.0.0.0 in integration tests to fix Docker connectivity * Iceberg: fix metadata handling in REST catalog - Add nil guard in createTable - Fix updateTable to correctly load existing metadata from storage - Ensure full metadata persistence on updates - Populate loadTable result with parsed metadata * S3Tables: add auth checks and fix response fields in UpdateTable - Add CheckPermissionWithContext to UpdateTable handler - Include TableARN and MetadataLocation in UpdateTable response - Use ErrCodeConflict (409) for version token mismatches * Tests: improve Iceberg catalog test infrastructure and cleanup - Makefile: use PID file for precise process killing - test_rest_catalog.py: remove unused variables and fix f-strings * Iceberg: fix variable shadowing in UpdateTable - Rename inner loop variable `req` to `requirement` to avoid shadowing outer request variable * S3Tables: simplify MetadataVersion initialization - Use `max(req.MetadataVersion, 1)` instead of anonymous function * Tests: remove unicode characters from S3 tables integration test logs - Remove unicode checkmarks from test output for cleaner logs * Iceberg: improve metadata persistence robustness - Fix MetadataLocation in LoadTableResult to fallback to generated location - Improve saveMetadataFile to ensure directory hierarchy existence and robust error handling
237 lines
7.1 KiB
Python
237 lines
7.1 KiB
Python
#!/usr/bin/env python3
|
|
"""
|
|
Iceberg REST Catalog Compatibility Test for SeaweedFS
|
|
|
|
This script tests the Iceberg REST Catalog API compatibility of the
|
|
SeaweedFS Iceberg REST Catalog implementation.
|
|
|
|
Usage:
|
|
python3 test_rest_catalog.py --catalog-url http://localhost:8182
|
|
|
|
Requirements:
|
|
pip install pyiceberg[s3fs]
|
|
"""
|
|
|
|
import argparse
|
|
import sys
|
|
from pyiceberg.catalog import load_catalog
|
|
from pyiceberg.schema import Schema
|
|
from pyiceberg.types import (
|
|
IntegerType,
|
|
LongType,
|
|
StringType,
|
|
NestedField,
|
|
)
|
|
from pyiceberg.exceptions import (
|
|
NamespaceAlreadyExistsError,
|
|
NoSuchNamespaceError,
|
|
TableAlreadyExistsError,
|
|
NoSuchTableError,
|
|
)
|
|
|
|
|
|
def test_config_endpoint(catalog):
|
|
"""Test that the catalog config endpoint returns valid configuration."""
|
|
print("Testing /v1/config endpoint...")
|
|
# The catalog is already loaded which means config endpoint worked
|
|
print(" /v1/config endpoint working")
|
|
return True
|
|
|
|
|
|
def test_namespace_operations(catalog, prefix):
|
|
"""Test namespace CRUD operations."""
|
|
print("Testing namespace operations...")
|
|
namespace = (f"{prefix.replace('-', '_')}_test_ns",)
|
|
|
|
# List initial namespaces
|
|
namespaces = catalog.list_namespaces()
|
|
print(f" Initial namespaces: {namespaces}")
|
|
|
|
# Create namespace
|
|
try:
|
|
catalog.create_namespace(namespace)
|
|
print(f" Created namespace: {namespace}")
|
|
except NamespaceAlreadyExistsError:
|
|
print(f" ! Namespace already exists: {namespace}")
|
|
|
|
# List namespaces (should include our new one)
|
|
namespaces = catalog.list_namespaces()
|
|
if namespace in namespaces:
|
|
print(" Namespace appears in list")
|
|
else:
|
|
print(f" Namespace not found in list: {namespaces}")
|
|
return False
|
|
|
|
# Get namespace properties
|
|
try:
|
|
props = catalog.load_namespace_properties(namespace)
|
|
print(f" Loaded namespace properties: {props}")
|
|
except NoSuchNamespaceError:
|
|
print(f" Failed to load namespace properties")
|
|
return False
|
|
|
|
return True
|
|
|
|
|
|
def test_table_operations(catalog, prefix):
|
|
"""Test table CRUD operations."""
|
|
print("Testing table operations...")
|
|
namespace = (f"{prefix.replace('-', '_')}_test_ns",)
|
|
table_name = "test_table"
|
|
table_id = namespace + (table_name,)
|
|
|
|
# Define a simple schema
|
|
schema = Schema(
|
|
NestedField(field_id=1, name="id", field_type=LongType(), required=True),
|
|
NestedField(field_id=2, name="name", field_type=StringType(), required=False),
|
|
NestedField(field_id=3, name="age", field_type=IntegerType(), required=False),
|
|
)
|
|
|
|
# Create table
|
|
try:
|
|
table = catalog.create_table(
|
|
identifier=table_id,
|
|
schema=schema,
|
|
)
|
|
print(f" Created table: {table_id}")
|
|
except TableAlreadyExistsError:
|
|
print(f" ! Table already exists: {table_id}")
|
|
_ = catalog.load_table(table_id)
|
|
|
|
# List tables
|
|
tables = catalog.list_tables(namespace)
|
|
if table_name in [t[1] for t in tables]:
|
|
print(" Table appears in list")
|
|
else:
|
|
print(f" Table not found in list: {tables}")
|
|
return False
|
|
|
|
# Load table
|
|
try:
|
|
loaded_table = catalog.load_table(table_id)
|
|
print(f" Loaded table: {loaded_table.name()}")
|
|
print(f" Schema: {loaded_table.schema()}")
|
|
print(f" Location: {loaded_table.location()}")
|
|
except NoSuchTableError:
|
|
print(f" Failed to load table")
|
|
return False
|
|
|
|
return True
|
|
|
|
|
|
def test_table_update(catalog, prefix):
|
|
"""Test table update/commit operations."""
|
|
print("Testing table update operations...")
|
|
namespace = (f"{prefix.replace('-', '_')}_test_ns",)
|
|
table_name = "test_table"
|
|
table_id = namespace + (table_name,)
|
|
|
|
try:
|
|
table = catalog.load_table(table_id)
|
|
|
|
# Update table properties
|
|
with table.transaction() as transaction:
|
|
transaction.set_properties({"test.property": "test.value"})
|
|
|
|
print(" Updated table properties")
|
|
|
|
# Reload and verify
|
|
table = catalog.load_table(table_id)
|
|
if table.properties.get("test.property") == "test.value":
|
|
print(" Property update verified")
|
|
else:
|
|
print(" ! Property update failed or not persisted")
|
|
return False
|
|
|
|
except Exception as e:
|
|
print(f" Table update failed: {e}")
|
|
return False
|
|
|
|
return True
|
|
|
|
|
|
def test_cleanup(catalog, prefix):
|
|
"""Test table and namespace deletion."""
|
|
print("Testing cleanup operations...")
|
|
namespace = (f"{prefix.replace('-', '_')}_test_ns",)
|
|
table_id = namespace + ("test_table",)
|
|
|
|
# Drop table
|
|
try:
|
|
catalog.drop_table(table_id)
|
|
print(f" Dropped table: {table_id}")
|
|
except NoSuchTableError:
|
|
print(f" ! Table already deleted: {table_id}")
|
|
|
|
# Drop namespace
|
|
try:
|
|
catalog.drop_namespace(namespace)
|
|
print(f" Dropped namespace: {namespace}")
|
|
except NoSuchNamespaceError:
|
|
print(f" ! Namespace already deleted: {namespace}")
|
|
except Exception as e:
|
|
print(f" ? Namespace drop error (may be expected): {e}")
|
|
|
|
return True
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(description="Test Iceberg REST Catalog compatibility")
|
|
parser.add_argument("--catalog-url", required=True, help="Iceberg REST Catalog URL (e.g., http://localhost:8182)")
|
|
parser.add_argument("--warehouse", default="s3://iceberg-test/", help="Warehouse location")
|
|
parser.add_argument("--prefix", required=True, help="Table bucket prefix")
|
|
parser.add_argument("--skip-cleanup", action="store_true", help="Skip cleanup at the end")
|
|
args = parser.parse_args()
|
|
|
|
print(f"Connecting to Iceberg REST Catalog at: {args.catalog_url}")
|
|
print(f"Warehouse: {args.warehouse}")
|
|
print(f"Prefix: {args.prefix}")
|
|
print()
|
|
|
|
# Load the REST catalog
|
|
catalog = load_catalog(
|
|
"rest",
|
|
**{
|
|
"type": "rest",
|
|
"uri": args.catalog_url,
|
|
"warehouse": args.warehouse,
|
|
"prefix": args.prefix,
|
|
}
|
|
)
|
|
|
|
# Run tests
|
|
tests = [
|
|
("Config Endpoint", lambda: test_config_endpoint(catalog)),
|
|
("Namespace Operations", lambda: test_namespace_operations(catalog, args.prefix)),
|
|
("Table Operations", lambda: test_table_operations(catalog, args.prefix)),
|
|
("Table Update", lambda: test_table_update(catalog, args.prefix)),
|
|
]
|
|
|
|
if not args.skip_cleanup:
|
|
tests.append(("Cleanup", lambda: test_cleanup(catalog, args.prefix)))
|
|
|
|
passed = 0
|
|
failed = 0
|
|
|
|
for name, test_fn in tests:
|
|
print(f"\n{'='*50}")
|
|
try:
|
|
if test_fn():
|
|
passed += 1
|
|
print(f"PASSED: {name}")
|
|
else:
|
|
failed += 1
|
|
print(f"FAILED: {name}")
|
|
except Exception as e:
|
|
failed += 1
|
|
print(f"ERROR in {name}: {e}")
|
|
|
|
print(f"\n{'='*50}")
|
|
print(f"Results: {passed} passed, {failed} failed")
|
|
|
|
return 0 if failed == 0 else 1
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|