deltacat 1.1.38__py3-none-any.whl → 2.0.0__py3-none-any.whl

deltacat/examples/indexer/indexer.py

@@ -0,0 +1,163 @@
+import argparse
+
+from datetime import datetime
+
+import ray
+
+import deltacat
+import daft
+import pyarrow as pa
+import pandas as pd
+import polars as pl
+import numpy as np
+
+from deltacat import DeltaCatUrl
+
+
+def print_package_version_info() -> None:
+    print(f"DeltaCAT Version: {deltacat.__version__}")
+    print(f"Ray Version: {ray.__version__}")
+    print(f"Daft Version: {daft.__version__}")
+    print(f"NumPy Version: {np.__version__}")
+    print(f"PyArrow Version: {pa.__version__}")
+    print(f"Polars Version: {pl.__version__}")
+    print(f"Pandas Version: {pd.__version__}")
+
+
+def json_path_to_regex(path: str):
+    if not path:
+        raise ValueError("Path cannot be empty")
+    parts = path.split("/")
+    leaf_key = parts.pop()
+    regex = r""
+    for part in parts:
+        if part.strip():  # discard leading and/or redundant separators
+            regex += rf'"{part}"\s*:\s*[{{\[].*?'
+    regex += rf'"{leaf_key}"\s*:\s*"(?<{leaf_key}>.*?)"'
+    return regex
+
+
+def run(
+    source: str,
+    dest: str,
+) -> None:
+    # print package version info
+    print_package_version_info()
+
+    # run a synchronous copy from the source to the destination
+    deltacat.copy(
+        DeltaCatUrl(source),
+        DeltaCatUrl(dest),
+        # reader arguments to pass to the default reader (polars)
+        # for the given text-based datasource, it accepts the same
+        # arguments as polars.read_csv except for `source`, `n_threads`
+        # `new_columns`, `separator`, `has_header`, `quote_char`, and
+        # `infer_schema`.
+        reader_args={
+            "low_memory": True,  # try to use less memory (++stability, --perf)
+            "batch_size": 1024,  # text line count read into a buffer at once
+            "use_pyarrow": True,  # use the native pyarrow reader
+        },
+        # writer arguments to pass to the default writer (polars)
+        # for the given parquet-based datasink, it generally accepts the same
+        # arguments as polars.DataFrame.write_{dest-type} except for `file`
+        writer_args={
+            "compression": "lz4",  # faster compression & decompression
+            # "compression": "zstd",  # better compression ratio
+            # "compression": "snappy",  # compatible w/ older Parquet readers
+        },
+        # Transforms to run against the default polars dataframe read.
+        # By default, each transform takes a polars dataframe `df` as input
+        # and produces a polars dataframe as output. All transforms listed
+        # are run in order (i.e., the dataframe output from transform[0]
+        # is the dataframe input to transform[1]).
+        #
+        # See:
+        # https://docs.pola.rs/api/python/stable/reference/dataframe/index.html
+        # https://docs.pola.rs/api/python/stable/reference/expressions/index.html
+        transforms=[
+            lambda df, src: df.rename(
+                {"text": "utf8_body"},
+            ),
+            lambda df, src: df.with_columns(
+                pl.col("utf8_body").hash().alias("utf8_body_hash"),
+                pl.lit(datetime.utcnow()).dt.datetime().alias("processing_time"),
+                pl.lit(src.url_path).alias("source_file_path"),
+            ),
+        ],
+    )
+
+
+if __name__ == "__main__":
+    """
+    Example 1: Run this script locally using Ray:
+    $ python indexer.py \
+    $   --source 'text+s3://openalex-mag-format/data_dump_v1/2022-07-08/nlp/PaperAbstractsInvertedIndex.txt_part31' \
+    $   --dest 'parquet+s3://deltacat-example-output/openalex/PaperAbstractsInvertedIndex.part31.parquet'
+
+    Example 2: Submit this script as a local Ray job using a local job client:
+    >>> from deltacat import local_job_client
+    >>> client = local_job_client()
+    >>> # read the source file as line-delimited text
+    >>> src = "text+s3://openalex-mag-format/data_dump_v1/2022-07-08/nlp/PaperAbstractsInvertedIndex.txt_part31"
+    >>> # write to the destination file using the default DeltaCAT Parquet writer (i.e., polars.DataFrame.write_parquet)
+    >>> dst = "parquet+s3://deltacat-example-output/openalex/PaperAbstractsInvertedIndex.part31.parquet"
+    >>> try:
+    >>>   job_run_result = client.run_job(
+    >>>       # Entrypoint shell command to run the indexer job
+    >>>       entrypoint=f"python indexer.py --source '{src}' --dest '{dst}'",
+    >>>       # Path to the local directory that contains the indexer.py file
+    >>>       runtime_env={"working_dir": "./deltacat/examples/indexer.py"},
+    >>>   )
+    >>>   print(f"Job ID {job_run_result.job_id} terminal state: {job_run_result.job_status}")
+    >>>   print(f"Job ID {job_run_result.job_id} logs: ")
+    >>>   print(job_run_result.job_logs)
+    >>> except RuntimeError as e:
+    >>>     print(f"Job Run Failed: {e}")
+    >>> except TimeoutError as e:
+    >>>     print(f"Job Run Timed Out: {e}")
+
+    Example 3: Submit this script as a remote Ray job using a remote job client:
+    >>> from deltacat import job_client
+    >>> # use `deltacat.yaml` from the current working directory as the ray cluster launcher config file
+    >>> # automatically launches the cluster if it doesn't exist or has died
+    >>> # automatically forwards the ray cluster's dashboard for viewing in a web browser @ http://localhost:8265
+    >>> client = job_client()
+    >>> # ... follow the same steps as above to submit a synchronous indexer job ...
+    >>>
+    >>> # OR use an explicit cluster launcher config file path
+    >>> client = job_client("/Users/pdames/workspace/deltacat.yaml")
+    >>> # ... follow the same steps as above to submit a synchronous indexer job ...
+    """
+    script_args = [
+        (
+            [
+                "--source",
+            ],
+            {
+                "help": "Source DeltaCAT URL to index.",
+                "type": str,
+            },
+        ),
+        (
+            [
+                "--dest",
+            ],
+            {
+                "help": "Destination DeltaCAT URL to index.",
+                "type": str,
+            },
+        ),
+    ]
+    # parse CLI input arguments
+    parser = argparse.ArgumentParser()
+    for args, kwargs in script_args:
+        parser.add_argument(*args, **kwargs)
+    args = parser.parse_args()
+    print(f"Command Line Arguments: {args}")
+
+    # initialize deltacat
+    deltacat.init()
+
+    # run the example using the parsed arguments
+    run(**vars(args))

deltacat/examples/indexer/job_runner.py

@@ -0,0 +1,198 @@
+import argparse
+import pathlib
+
+from deltacat.compute import (
+    job_client,
+    JobStatus,
+)
+
+
+def run_async(
+    source: str,
+    dest: str,
+    jobs_to_submit: int,
+    job_timeout: int,
+    cloud: str,
+    restart_ray: bool,
+):
+    # print package version info
+    working_dir = pathlib.Path(__file__).parent
+    cluster_cfg_file_path = working_dir.joinpath(cloud).joinpath("deltacat.yaml")
+    job_number = 0
+    client = job_client(cluster_cfg_file_path, restart_ray=restart_ray)
+    job_ids = []
+    while jobs_to_submit > 0:
+        jobs_to_submit -= 1
+        job_dest = dest + f".{job_number}"
+        job_id = client.submit_job(
+            # Entrypoint shell command to execute
+            entrypoint=f"python3 indexer.py --source '{source}' --dest '{job_dest}'",
+            # Path to the local directory that contains the indexer.py file
+            # This entire directory will be zipped into a job package, so keep
+            # it small.
+            runtime_env={"working_dir": working_dir},
+        )
+        job_ids.append(job_id)
+        job_number += 1
+
+    print("Waiting for all jobs to complete...")
+    job_number = 0
+    all_job_logs = ""
+    for job_id in job_ids:
+        job_status = client.await_job(job_id, timeout_seconds=job_timeout)
+        if job_status != JobStatus.SUCCEEDED:
+            print(f"Job `{job_id}` logs: ")
+            print(client.get_job_logs(job_id))
+            raise RuntimeError(f"Job `{job_id}` terminated with status: {job_status}")
+        all_job_logs += f"\nJob #{job_number} logs: \n"
+        all_job_logs += client.get_job_logs(job_id)
+        job_number += 1
+    print("All jobs completed!")
+    print("Job Logs: ")
+    print(all_job_logs)
+
+
+def run_sync(
+    source: str,
+    dest: str,
+    jobs_to_submit: int,
+    job_timeout: int,
+    cloud: str,
+    restart_ray: bool,
+):
+    working_dir = pathlib.Path(__file__).parent
+    cluster_cfg_file_path = working_dir.joinpath(cloud).joinpath("deltacat.yaml")
+    client = job_client(cluster_cfg_file_path, restart_ray=restart_ray)
+    job_number = 0
+    while job_number < jobs_to_submit:
+        job_dest = dest + f".{job_number}"
+        job_run_result = client.run_job(
+            # Entrypoint shell command to execute
+            entrypoint=f"python3 indexer.py --source '{source}' --dest '{job_dest}'",
+            # Path to the local directory that contains the indexer.py file
+            # This entire directory will be zipped into a job package, so keep
+            # it small.
+            runtime_env={"working_dir": working_dir},
+            timeout_seconds=job_timeout,
+        )
+        print(
+            f"Job ID {job_run_result.job_id} terminal state: {job_run_result.job_status}"
+        )
+        print(f"Job ID {job_run_result.job_id} logs: ")
+        print(job_run_result.job_logs)
+        job_number += 1
+
+
+def run(
+    source: str,
+    dest: str,
+    restart_ray: bool,
+    jobs_to_submit: int,
+    job_timeout: int,
+    asynchronous: bool,
+    cloud_provider: str,
+):
+    run_func = run_async if asynchronous else run_sync
+    run_func(
+        source=source,
+        dest=dest,
+        jobs_to_submit=jobs_to_submit,
+        job_timeout=job_timeout,
+        cloud=cloud_provider,
+        restart_ray=restart_ray,
+    )
+
+
+if __name__ == "__main__":
+    """
+    # Run this example through a command of the form:
+    $ python ./deltacat/examples/job_runner.py -- \
+    $ --source text+s3://openalex-mag-format/data_dump_v1/2022-07-08/nlp/PaperAbstractsInvertedIndex.txt_part31 \
+    $ --dest parquet+s3://deltacat-example-output/openalex/PaperAbstractsInvertedIndex.part31.parquet \
+    $ --asynchronous \
+    $ --jobs-to-submit 100 \
+    $ --job-timeout 90 \
+    $ --cloud-provider aws
+    """
+    script_args = [
+        (
+            [
+                "--source",
+            ],
+            {
+                "help": "Source DeltaCAT URL to index.",
+                "type": str,
+                "default": "text+s3://openalex-mag-format/data_dump_v1/2022-07-08/nlp/PaperAbstractsInvertedIndex.txt_part31",
+            },
+        ),
+        (
+            [
+                "--dest",
+            ],
+            {
+                "help": "Destination DeltaCAT URL to store the indexed file.",
+                "type": str,
+                "default": "parquet+s3://deltacat-example-output/openalex/PaperAbstractsInvertedIndex.part31.parquet",
+            },
+        ),
+        (
+            [
+                "--restart-ray",
+            ],
+            {
+                "help": "Restart Ray on an existing cluster.",
+                "action": "store_true",
+                "default": False,
+            },
+        ),
+        (
+            [
+                "--asynchronous",
+            ],
+            {
+                "help": "Run jobs asynchronously.",
+                "action": "store_true",
+                "default": False,
+            },
+        ),
+        (
+            [
+                "--jobs-to-submit",
+            ],
+            {
+                "help": "Number of indexer jobs to submit for execution.",
+                "type": int,
+                "default": 1,
+            },
+        ),
+        (
+            [
+                "--job-timeout",
+            ],
+            {
+                "help": "Job timeout in seconds.",
+                "type": int,
+                "default": 300,
+            },
+        ),
+        (
+            [
+                "--cloud-provider",
+            ],
+            {
+                "help": "Ray Cluster Cloud Provider ('aws' or 'gcp')",
+                "type": str,
+                "default": "aws",
+            },
+        ),
+    ]
+
+    # parse CLI input arguments
+    parser = argparse.ArgumentParser()
+    for args, kwargs in script_args:
+        parser.add_argument(*args, **kwargs)
+    args = parser.parse_args()
+    print(f"Command Line Arguments: {args}")
+
+    # run the example using os.environ as kwargs
+    run(**vars(args))

deltacat/exceptions.py

@@ -1,10 +1,16 @@
 from __future__ import annotations
 from enum import Enum
-import botocore
-import ray
+from typing import Callable, Optional, TYPE_CHECKING
 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 +19,17 @@ 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
+
+if TYPE_CHECKING:
+    from deltacat.storage.model.schema import FieldLocator
 
 logger = logs.configure_deltacat_logger(logging.getLogger(__name__))
 
@@ -64,6 +73,23 @@ 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"
+    PARTITION_NOT_FOUND_ERROR = "PartitionNotFoundError"
+    DELTA_NOT_FOUND_ERROR = "DeltaNotFoundError"
+    TABLE_ALREADY_EXISTS_ERROR = "TableAlreadyExistsError"
+    TABLE_VERSION_ALREADY_EXISTS_ERROR = "TableVersionAlreadyExistsError"
+    NAMESPACE_ALREADY_EXISTS_ERROR = "NamespaceAlreadyExistsError"
+    SCHEMA_COMPATIBILITY_ERROR = "SchemaCompatibilityError"
+    SCHEMA_VALIDATION_ERROR = "SchemaValidationError"
+    TABLE_VALIDATION_ERROR = "TableValidationError"
+    CONCURRENT_MODIFICATION_ERROR = "ConcurrentModificationError"
+    OBJECT_NOT_FOUND_ERROR = "ObjectNotFoundError"
+    OBJECT_DELETED_ERROR = "ObjectDeletedError"
+    OBJECT_ALREADY_EXISTS_ERROR = "ObjectAlreadyExistsError"
+
 
 class DeltaCatError(Exception):
     def __init__(self, *args, **kwargs):
@@ -73,9 +99,12 @@ class DeltaCatError(Exception):
         super().__init__(*args, **kwargs)
 
     def _get_ray_task_id_and_node_ip(self):
-        task_id = get_current_ray_task_id()
-        node_ip = ray.util.get_node_ip_address()
-        return task_id, node_ip
+        if ray.is_initialized():
+            task_id = get_current_ray_task_id()
+            node_ip = ray.util.get_node_ip_address()
+            return task_id, node_ip
+        else:
+            return None, None
 
 
 class NonRetryableError(DeltaCatError):
@@ -206,6 +235,81 @@ 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 PartitionNotFoundError(NonRetryableError):
+    error_name = DeltaCatErrorNames.PARTITION_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 TableVersionAlreadyExistsError(NonRetryableError):
+    error_name = DeltaCatErrorNames.TABLE_VERSION_ALREADY_EXISTS_ERROR.value
+
+
+class NamespaceAlreadyExistsError(NonRetryableError):
+    error_name = DeltaCatErrorNames.TABLE_ALREADY_EXISTS_ERROR.value
+
+
+class ObjectNotFoundError(NonRetryableError):
+    error_name = DeltaCatErrorNames.OBJECT_NOT_FOUND_ERROR.value
+
+
+class ObjectDeletedError(NonRetryableError):
+    error_name = DeltaCatErrorNames.OBJECT_DELETED_ERROR.value
+
+
+class ObjectAlreadyExistsError(NonRetryableError):
+    error_name = DeltaCatErrorNames.OBJECT_ALREADY_EXISTS_ERROR.value
+
+
+class ConcurrentModificationError(NonRetryableError):
+    error_name = DeltaCatErrorNames.CONCURRENT_MODIFICATION_ERROR.value
+
+
+class SchemaValidationError(NonRetryableError):
+    error_name = DeltaCatErrorNames.SCHEMA_VALIDATION_ERROR.value
+
+
+class TableValidationError(NonRetryableError):
+    error_name = DeltaCatErrorNames.TABLE_VALIDATION_ERROR.value
+
+
+class SchemaCompatibilityError(NonRetryableError):
+    error_name = DeltaCatErrorNames.SCHEMA_COMPATIBILITY_ERROR.value
+    """Raised when a schema update would break backward compatibility."""
+
+    def __init__(
+        self,
+        message: str,
+        field_locator: Optional[FieldLocator] = None,
+        *args,
+        **kwargs,
+    ):
+        super().__init__(message, *args, **kwargs)
+        self.field_locator = field_locator
+
+
 def categorize_errors(func: Callable):
     def wrapper(*args, **kwargs):
         try:
@@ -238,7 +342,7 @@ 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/experimental/catalog/iceberg/__init__.py

@@ -0,0 +1,6 @@
+from deltacat.experimental.catalog.iceberg.iceberg_catalog_config import (
+    IcebergCatalogConfig,
+)
+import deltacat.experimental.catalog.iceberg.impl as IcebergCatalog
+
+__all__ = ["IcebergCatalogConfig", "IcebergCatalog"]

deltacat/experimental/catalog/iceberg/iceberg_catalog_config.py

@@ -0,0 +1,26 @@
+from __future__ import annotations
+from typing import Any, Dict
+
+from attr import dataclass
+from pyiceberg.catalog import CatalogType
+
+
+@dataclass
+class IcebergCatalogConfig:
+    """
+    Configuration properties for Iceberg catalog implementation.
+
+    This class holds the PyIceberg Catalog instance needed for interaction with
+    Iceberg tables and metadata.
+
+    This configuration is passed through to PyIceberg by invoking load_catalog.
+    The Properties provided must match properties accepted by PyIceberg for each catalog type
+    See: :func:`deltacat.experimental.catalog.iceberg.initialize`
+
+    Attributes:
+        type: The PyIceberg Catalog instance
+        properties: Dict of properties passed to pyiceberg load_catalog
+    """
+
+    type: CatalogType
+    properties: Dict[str, Any]