deltacat 1.1.36__py3-none-any.whl → 2.0.0b2__py3-none-any.whl

deltacat/examples/basic_logging.py

@@ -0,0 +1,101 @@
+import os
+import ray
+import logging
+
+from deltacat import logs
+from deltacat.constants import DELTACAT_APP_LOG_DIR, DELTACAT_SYS_LOG_DIR
+from deltacat.examples.common.fixtures import (
+    store_cli_args_in_os_environ,
+)
+from deltacat.env import create_ray_runtime_environment
+
+# initialize the driver logger
+driver_logger = logs.configure_application_logger(logging.getLogger(__name__))
+
+
+@ray.remote
+def logging_worker(var1, var2):
+    # for AWS Glue, worker loggers must be initialized within the worker process
+    worker_logger = logs.configure_application_logger(logging.getLogger(__name__))
+
+    log_line_1 = f"Worker System Environment: {os.environ}"
+    print(
+        f"Writing DEBUG log line from Worker to {DELTACAT_APP_LOG_DIR}: '{log_line_1}'"
+    )
+    worker_logger.debug(log_line_1)
+
+    log_line_2 = f"Worker Variable 1: {var1}"
+    print(
+        f"Writing INFO log line from Worker to {DELTACAT_APP_LOG_DIR}: '{log_line_2}'"
+    )
+    worker_logger.info(log_line_2)
+
+    log_line_3 = f"Worker Variable 2: {var2}"
+    print(
+        f"Writing INFO log line from Worker to {DELTACAT_APP_LOG_DIR}: '{log_line_3}'"
+    )
+    worker_logger.info(log_line_3)
+
+
+def run(var1="default1", var2="default2", **kwargs):
+    log_line_1 = f"Driver Variable 1: {var1}"
+    print(
+        f"Writing INFO log line from Driver to {DELTACAT_APP_LOG_DIR}: '{log_line_1}'"
+    )
+    driver_logger.info(log_line_1)
+
+    log_line_2 = f"Driver Variable 2: {var2}"
+    print(
+        f"Writing INFO log line from Driver to {DELTACAT_APP_LOG_DIR}: '{log_line_2}'"
+    )
+    driver_logger.info(log_line_2)
+
+    print("Starting worker...")
+    ray.get(logging_worker.remote(var1, var2))
+    print(
+        f"The driver is shutting down. Additional DeltaCAT system logs have been written to {DELTACAT_SYS_LOG_DIR}"
+    )
+
+
+if __name__ == "__main__":
+    example_script_args = [
+        (
+            [
+                "--var1",
+            ],
+            {
+                "help": "First argument to log.",
+                "type": str,
+            },
+        ),
+        (
+            [
+                "--var2",
+            ],
+            {
+                "help": "Second argument to log.",
+                "type": str,
+            },
+        ),
+        (
+            [
+                "--STAGE",
+            ],
+            {
+                "help": "Example runtime environment stage (e.g. dev, alpha, beta, prod).",
+                "type": str,
+            },
+        ),
+    ]
+
+    # store any CLI args in the runtime environment
+    store_cli_args_in_os_environ(example_script_args)
+
+    # create any runtime environment required to run the example
+    runtime_env = create_ray_runtime_environment()
+
+    # initialize ray
+    ray.init(runtime_env=runtime_env)
+
+    # run the example using os.environ as kwargs
+    run(**os.environ)

deltacat/examples/common/fixtures.py

@@ -0,0 +1,15 @@
+import os
+import logging
+import argparse
+from deltacat import logs
+
+logger = logs.configure_deltacat_logger(logging.getLogger(__name__))
+
+
+def store_cli_args_in_os_environ(script_args_list=[]):
+    parser = argparse.ArgumentParser()
+    for args, kwargs in script_args_list:
+        parser.add_argument(*args, **kwargs)
+    args = parser.parse_args()
+    print(f"Command Line Arguments: {args}")
+    os.environ.update(vars(args))

deltacat/examples/hello_world.py

@@ -0,0 +1,27 @@
+import ray
+import deltacat
+import daft
+import pyiceberg
+
+
+def print_package_version_info():
+    print(f"DeltaCAT Version: {deltacat.__version__}")
+    print(f"PyIceberg Version: {pyiceberg.__version__}")
+    print(f"Ray Version: {ray.__version__}")
+    print(f"Daft Version: {daft.__version__}")
+
+
+@ray.remote
+def hello_worker():
+    print("Hello, Worker!")
+    print_package_version_info()
+
+
+def run():
+    print("Hello, Driver!")
+    print_package_version_info()
+    hello_worker.remote()
+
+
+if __name__ == "__main__":
+    run()

deltacat/examples/iceberg/iceberg_bucket_writer.py

@@ -0,0 +1,139 @@
+import os
+import logging
+
+import daft
+import deltacat as dc
+
+from deltacat import logs
+from deltacat import IcebergCatalog
+from deltacat.examples.common.fixtures import (
+    store_cli_args_in_os_environ,
+)
+
+from pyiceberg.schema import (
+    Schema,
+    NestedField,
+    DoubleType,
+    StringType,
+)
+from pyiceberg.partitioning import PartitionSpec, PartitionField
+from pyiceberg.transforms import BucketTransform
+
+from deltacat.storage.iceberg.model import (
+    SchemaMapper,
+    PartitionSchemeMapper,
+)
+from deltacat.env import create_ray_runtime_environment
+
+# initialize the driver logger
+driver_logger = logs.configure_application_logger(logging.getLogger(__name__))
+
+
+def run(warehouse="s3://my-bucket/my/key/prefix", **kwargs):
+    # create any runtime environment required to run the example
+    runtime_env = create_ray_runtime_environment()
+
+    # Start by initializing DeltaCAT and registering available Catalogs.
+    # Ray will be initialized automatically via `ray.init()`.
+    # Only the `iceberg` data catalog is provided so it will become the default.
+    # If initializing multiple catalogs, use the `default_catalog_name` param
+    # to specify which catalog should be the default.
+    dc.init(
+        catalogs={
+            # the name of the DeltaCAT catalog is "iceberg"
+            "iceberg": dc.Catalog(
+                # Apache Iceberg implementation of deltacat.catalog.interface
+                impl=IcebergCatalog,
+                # kwargs for pyiceberg.catalog.load_catalog start here...
+                # the name of the Iceberg catalog is "example-iceberg-catalog"
+                name="example-iceberg-catalog",
+                # for additional properties see:
+                # https://py.iceberg.apache.org/configuration/
+                properties={
+                    "type": "glue",
+                    "region_name": "us-east-1",
+                    "warehouse": warehouse,
+                },
+            )
+        },
+        # pass the runtime environment into ray.init()
+        ray_init_args={"runtime_env": runtime_env},
+    )
+
+    # define a native Iceberg table schema
+    schema = Schema(
+        NestedField(field_id=1, name="symbol", field_type=StringType(), required=True),
+        NestedField(field_id=2, name="bid", field_type=DoubleType(), required=False),
+        NestedField(field_id=3, name="ask", field_type=DoubleType(), required=False),
+    )
+
+    # define a native Iceberg partition spec
+    partition_spec = PartitionSpec(
+        PartitionField(
+            source_id=1,
+            field_id=1000,
+            transform=BucketTransform(2),
+            name="symbol_bucket",
+        )
+    )
+
+    # define a native Iceberg sort order
+    # sort_order = SortOrder(SortField(source_id=1, transform=IdentityTransform()))
+
+    # define the Daft dataframe to write
+    df = daft.from_pydict(
+        {
+            "symbol": ["amzn", "goog", "meta", "msft"],
+            "bid": [157.16, 150.55, 392.03, 403.25],
+            "ask": [157.17, 150.56, 392.09, 403.27],
+        }
+    )
+
+    # write to a table named `test_namespace.test_table_bucketed`
+    # we don't need to specify which catalog to create this table in since
+    # only the "iceberg" catalog is available
+    table_name = "test_table_bucketed"
+    namespace = "test_namespace"
+    print(f"Creating Glue Table: {namespace}.{table_name}")
+    dc.write_to_table(
+        data=df,
+        # path=warehouse + "/datafiles",
+        table=table_name,
+        namespace=namespace,
+        schema=SchemaMapper.map(schema),
+        partition_scheme=PartitionSchemeMapper.map(partition_spec, schema),
+        # sort_keys=SortSchemeMapper.map(sort_order, schema),
+    )
+
+    print(f"Getting Glue Table: {namespace}.{table_name}")
+    table_definition = dc.get_table(table_name, namespace)
+    print(f"Retrieved Glue Table: {table_definition}")
+
+
+if __name__ == "__main__":
+    example_script_args = [
+        (
+            [
+                "--warehouse",
+            ],
+            {
+                "help": "S3 path for Iceberg file storage.",
+                "type": str,
+            },
+        ),
+        (
+            [
+                "--STAGE",
+            ],
+            {
+                "help": "Example runtime environment stage (e.g. dev, alpha, beta, prod).",
+                "type": str,
+            },
+        ),
+    ]
+
+    # store any CLI args in the runtime environment
+    store_cli_args_in_os_environ(example_script_args)
+
+    # run the example using os.environ as kwargs
+    run(**os.environ)

deltacat/examples/iceberg/iceberg_reader.py

@@ -0,0 +1,149 @@
+import os
+import logging
+import deltacat as dc
+
+from deltacat import logs
+from deltacat import IcebergCatalog
+from deltacat.examples.common.fixtures import (
+    store_cli_args_in_os_environ,
+)
+
+from pyiceberg.schema import (
+    Schema,
+    NestedField,
+    DoubleType,
+    StringType,
+    TimestampType,
+    FloatType,
+    StructType,
+)
+from pyiceberg.partitioning import PartitionSpec, PartitionField
+from pyiceberg.transforms import DayTransform, IdentityTransform
+from pyiceberg.table.sorting import SortField, SortOrder
+
+from deltacat.exceptions import TableAlreadyExistsError
+from deltacat.storage.iceberg.model import (
+    SchemaMapper,
+    PartitionSchemeMapper,
+    SortSchemeMapper,
+)
+from deltacat.env import create_ray_runtime_environment
+
+# initialize the driver logger
+driver_logger = logs.configure_application_logger(logging.getLogger(__name__))
+
+
+def run(warehouse="s3://my-bucket/my/key/prefix", **kwargs):
+    # create any runtime environment required to run the example
+    runtime_env = create_ray_runtime_environment()
+
+    # Start by initializing DeltaCAT and registering available Catalogs.
+    # Ray will be initialized automatically via `ray.init()`.
+    # Only the `iceberg` data catalog is provided so it will become the default.
+    # If initializing multiple catalogs, use the `default_catalog_name` param
+    # to specify which catalog should be the default.
+    dc.init(
+        catalogs={
+            # the name of the DeltaCAT catalog is "iceberg"
+            "iceberg": dc.Catalog(
+                # Apache Iceberg implementation of deltacat.catalog.interface
+                impl=IcebergCatalog,
+                # kwargs for pyiceberg.catalog.load_catalog start here...
+                # the name of the Iceberg catalog is "example-iceberg-catalog"
+                name="example-iceberg-catalog",
+                # for additional properties see:
+                # https://py.iceberg.apache.org/configuration/
+                properties={
+                    "type": "glue",
+                    "region_name": "us-east-1",
+                    "warehouse": warehouse,
+                },
+            )
+        },
+        # pass the runtime environment into ray.init()
+        ray_init_args={"runtime_env": runtime_env},
+    )
+
+    # define a native Iceberg table schema
+    schema = Schema(
+        NestedField(
+            field_id=1, name="datetime", field_type=TimestampType(), required=True
+        ),
+        NestedField(field_id=2, name="symbol", field_type=StringType(), required=True),
+        NestedField(field_id=3, name="bid", field_type=FloatType(), required=False),
+        NestedField(field_id=4, name="ask", field_type=DoubleType(), required=False),
+        NestedField(
+            field_id=5,
+            name="details",
+            field_type=StructType(
+                NestedField(
+                    field_id=6,
+                    name="created_by",
+                    field_type=StringType(),
+                    required=False,
+                ),
+            ),
+            required=False,
+        ),
+    )
+
+    # define a native Iceberg partition spec
+    partition_spec = PartitionSpec(
+        PartitionField(
+            source_id=1, field_id=1000, transform=DayTransform(), name="datetime_day"
+        )
+    )
+
+    # define a native Iceberg sort order
+    sort_order = SortOrder(SortField(source_id=2, transform=IdentityTransform()))
+
+    # create a table named `test_namespace.test_table`
+    # we don't need to specify which catalog to create this table in since
+    # only the "iceberg" catalog is available
+    table_name = "test_table"
+    namespace = "test_namespace"
+    print(f"Creating Glue Table: {namespace}.{table_name}")
+    try:
+        table_definition = dc.create_table(
+            table=table_name,
+            namespace=namespace,
+            schema=SchemaMapper.map(schema),
+            partition_scheme=PartitionSchemeMapper.map(partition_spec, schema),
+            sort_keys=SortSchemeMapper.map(sort_order, schema),
+        )
+        print(f"Created Glue Table: {table_definition}")
+    except TableAlreadyExistsError:
+        print(f"Glue Table `{namespace}.{table_name}` already exists.")
+
+    print(f"Getting Glue Table: {namespace}.{table_name}")
+    table_definition = dc.get_table(table_name, namespace)
+    print(f"Retrieved Glue Table: {table_definition}")
+
+
+if __name__ == "__main__":
+    example_script_args = [
+        (
+            [
+                "--warehouse",
+            ],
+            {
+                "help": "S3 path for Iceberg file storage.",
+                "type": str,
+            },
+        ),
+        (
+            [
+                "--STAGE",
+            ],
+            {
+                "help": "Example runtime environment stage (e.g. dev, alpha, beta, prod).",
+                "type": str,
+            },
+        ),
+    ]
+
+    # store any CLI args in the runtime environment
+    store_cli_args_in_os_environ(example_script_args)
+
+    # run the example using os.environ as kwargs
+    run(**os.environ)

deltacat/exceptions.py

@@ -1,10 +1,16 @@
 from __future__ import annotations
 from enum import Enum
-import botocore
-import ray
+from typing import Callable
 import logging
+
 import tenacity
-from deltacat import logs
+
+from pyarrow.lib import ArrowException, ArrowInvalid, ArrowCapacityError
+
+import botocore
+from botocore.exceptions import BotoCoreError
+
+import ray
 from ray.exceptions import (
     RayError,
     RayTaskError,
@@ -13,14 +19,14 @@ from ray.exceptions import (
     NodeDiedError,
     OutOfMemoryError,
 )
-from deltacat.storage import interface as DeltaCatStorage
-from pyarrow.lib import ArrowException, ArrowInvalid, ArrowCapacityError
-from botocore.exceptions import BotoCoreError
-from typing import Callable
+
+from daft.exceptions import DaftTransientError, DaftCoreException
+
+import deltacat as dc
+from deltacat import logs
 from deltacat.utils.ray_utils.runtime import (
     get_current_ray_task_id,
 )
-from daft.exceptions import DaftTransientError, DaftCoreException
 
 logger = logs.configure_deltacat_logger(logging.getLogger(__name__))
 
@@ -64,6 +70,14 @@ class DeltaCatErrorNames(str, Enum):
     UNCLASSIFIED_DELTACAT_ERROR = "UnclassifiedDeltaCatError"
     UNRECOGNIZED_RAY_TASK_ERROR = "UnrecognizedRayTaskError"
 
+    NAMESPACE_NOT_FOUND_ERROR = "NamespaceNotFoundError"
+    TABLE_NOT_FOUND_ERROR = "TableNotFoundError"
+    TABLE_VERSION_NOT_FOUND_ERROR = "TableVersionNotFoundError"
+    STREAM_NOT_FOUND_ERROR = "StreamNotFoundError"
+    DELTA_NOT_FOUND_ERROR = "DeltaNotFoundError"
+    TABLE_ALREADY_EXISTS_ERROR = "TableAlreadyExistsError"
+    NAMESPACE_ALREADY_EXISTS_ERROR = "NamespaceAlreadyExistsError"
+
 
 class DeltaCatError(Exception):
     def __init__(self, *args, **kwargs):
@@ -206,6 +220,34 @@ class UnrecognizedRayTaskError(NonRetryableError):
     error_name = DeltaCatErrorNames.UNRECOGNIZED_RAY_TASK_ERROR.value
 
 
+class NamespaceNotFoundError(NonRetryableError):
+    error_name = DeltaCatErrorNames.NAMESPACE_NOT_FOUND_ERROR.value
+
+
+class TableNotFoundError(NonRetryableError):
+    error_name = DeltaCatErrorNames.TABLE_NOT_FOUND_ERROR.value
+
+
+class TableVersionNotFoundError(NonRetryableError):
+    error_name = DeltaCatErrorNames.TABLE_VERSION_NOT_FOUND_ERROR.value
+
+
+class StreamNotFoundError(NonRetryableError):
+    error_name = DeltaCatErrorNames.STREAM_NOT_FOUND_ERROR.value
+
+
+class DeltaNotFoundError(NonRetryableError):
+    error_name = DeltaCatErrorNames.DELTA_NOT_FOUND_ERROR.value
+
+
+class TableAlreadyExistsError(NonRetryableError):
+    error_name = DeltaCatErrorNames.TABLE_ALREADY_EXISTS_ERROR.value
+
+
+class NamespaceAlreadyExistsError(NonRetryableError):
+    error_name = DeltaCatErrorNames.TABLE_ALREADY_EXISTS_ERROR.value
+
+
 def categorize_errors(func: Callable):
     def wrapper(*args, **kwargs):
         try:
@@ -238,7 +280,7 @@ def categorize_errors(func: Callable):
 
 def categorize_deltacat_exception(
     e: BaseException,
-    deltacat_storage: DeltaCatStorage = None,
+    deltacat_storage: dc.storage.interface = None,
     deltacat_storage_kwargs: dict = None,
 ):
     if deltacat_storage_kwargs is None:

deltacat/logs.py

@@ -18,6 +18,7 @@ from deltacat.constants import (
     DELTACAT_APP_DEBUG_LOG_BASE_FILE_NAME,
     DELTACAT_SYS_DEBUG_LOG_BASE_FILE_NAME,
     DELTACAT_LOGGER_CONTEXT,
+    DELTACAT_LOGGER_USE_SINGLE_HANDLER,
 )
 
 DEFAULT_LOG_LEVEL = "INFO"
@@ -226,6 +227,7 @@ def _configure_logger(
     # This maintains log level of rotating file handlers
     primary_log_level = log_level
     logger.propagate = False
+    needs_handler = True
     if log_level <= logging.getLevelName("DEBUG"):
         if not _file_handler_exists(logger, log_dir, debug_log_base_file_name):
             handler = _create_rotating_file_handler(
@@ -235,8 +237,9 @@ def _configure_logger(
                 context_kwargs=context_kwargs,
             )
             _add_logger_handler(logger, handler)
+            needs_handler = not DELTACAT_LOGGER_USE_SINGLE_HANDLER
             primary_log_level = logging.getLevelName("INFO")
-    if not _file_handler_exists(logger, log_dir, log_base_file_name):
+    if not _file_handler_exists(logger, log_dir, log_base_file_name) and needs_handler:
         handler = _create_rotating_file_handler(
             log_dir,
             log_base_file_name,