"""Native asyncio cursor that returns Athena query results as Apache Arrow tables."""
from __future__ import annotations
import asyncio
import logging
from collections.abc import Callable
from typing import TYPE_CHECKING, Any, cast
from pyathena.aio.common import WithAsyncFetch
from pyathena.arrow.converter import (
DefaultArrowTypeConverter,
DefaultArrowUnloadTypeConverter,
)
from pyathena.arrow.result_set import AthenaArrowResultSet
from pyathena.common import CursorIterator
from pyathena.error import OperationalError, ProgrammingError
from pyathena.model import AthenaQueryExecution
from pyathena.options import ExecuteOptions
from pyathena.util import override
if TYPE_CHECKING:
import polars as pl
from pyarrow import Table
_logger = logging.getLogger(__name__)
[docs]
class AioArrowCursor(WithAsyncFetch):
"""Native asyncio cursor that returns results as Apache Arrow Tables.
Uses ``asyncio.to_thread()`` for both result set creation and fetch
operations, keeping the event loop free.
Example:
>>> async with await pyathena.aio_connect(...) as conn:
... cursor = conn.cursor(AioArrowCursor)
... await cursor.execute("SELECT * FROM my_table")
... table = cursor.as_arrow()
"""
[docs]
def __init__(
self,
s3_staging_dir: str | None = None,
schema_name: str | None = None,
catalog_name: str | None = None,
work_group: str | None = None,
poll_interval: float = 1,
encryption_option: str | None = None,
kms_key: str | None = None,
kill_on_interrupt: bool = True,
unload: bool = False,
result_reuse_enable: bool = False,
result_reuse_minutes: int = CursorIterator.DEFAULT_RESULT_REUSE_MINUTES,
connect_timeout: float | None = None,
request_timeout: float | None = None,
**kwargs,
) -> None:
"""Initialize an AioArrowCursor.
Args:
s3_staging_dir: S3 location for query results.
schema_name: Default schema name.
catalog_name: Default catalog name.
work_group: Athena workgroup name.
poll_interval: Query status polling interval in seconds.
encryption_option: S3 encryption option for query results.
kms_key: KMS key for encrypting query results.
kill_on_interrupt: Cancel the query when the task is cancelled while
``execute()`` starts or waits for the query.
unload: Whether to wrap queries in ``UNLOAD`` and read the Parquet output.
result_reuse_enable: Whether to enable Athena query result reuse.
result_reuse_minutes: Maximum age of a reused query result in minutes.
connect_timeout: Connection timeout in seconds of the pyarrow S3 filesystem
that reads the results. If None, the pyarrow default is used.
request_timeout: Request timeout in seconds of the pyarrow S3 filesystem
that reads the results. If None, the pyarrow default is used.
**kwargs: Other cursor arguments, such as ``connection`` and ``arraysize``,
passed to the parent ``__init__``.
"""
super().__init__(
s3_staging_dir=s3_staging_dir,
schema_name=schema_name,
catalog_name=catalog_name,
work_group=work_group,
poll_interval=poll_interval,
encryption_option=encryption_option,
kms_key=kms_key,
kill_on_interrupt=kill_on_interrupt,
result_reuse_enable=result_reuse_enable,
result_reuse_minutes=result_reuse_minutes,
**kwargs,
)
self._unload = unload
self._connect_timeout = connect_timeout
self._request_timeout = request_timeout
self._result_set: AthenaArrowResultSet | None = None
[docs]
@staticmethod
@override
def get_default_converter(
unload: bool = False,
) -> DefaultArrowTypeConverter | DefaultArrowUnloadTypeConverter | Any:
if unload:
return DefaultArrowUnloadTypeConverter()
return DefaultArrowTypeConverter()
[docs]
@override
async def execute(
self,
operation: str,
parameters: dict[str, Any] | list[str] | None = None,
work_group: str | None = None,
s3_staging_dir: str | None = None,
cache_size: int | None = None,
cache_expiration_time: int | None = None,
result_reuse_enable: bool | None = None,
result_reuse_minutes: int | None = None,
paramstyle: str | None = None,
on_start_query_execution: Callable[[str], None] | None = None,
result_set_type_hints: dict[str | int, str] | None = None,
*,
options: ExecuteOptions | None = None,
**kwargs,
) -> AioArrowCursor:
"""Execute a SQL query asynchronously and return results as Arrow Tables.
Args:
operation: SQL query string to execute.
parameters: Query parameters for parameterized queries.
work_group: Athena workgroup to use for this query.
s3_staging_dir: S3 location for query results.
cache_size: Number of queries to check for result caching.
cache_expiration_time: Cache expiration time in seconds.
result_reuse_enable: Enable Athena result reuse for this query.
result_reuse_minutes: Minutes to reuse cached results.
paramstyle: Parameter style ('qmark' or 'pyformat').
on_start_query_execution: Callback invoked with the query ID before ``execute()``
waits for the query: after the ``StartQueryExecution`` call, or after a
reusable query ID is found through ``cache_size``.
result_set_type_hints: Athena type signatures for complex-type columns,
keyed by column name (case-insensitive) or zero-based column index.
options: Shared execution options as an
:class:`~pyathena.options.ExecuteOptions` instance. Individual
keyword arguments take precedence over ``options`` fields.
**kwargs: Additional execution parameters.
Returns:
Self reference for method chaining.
"""
self._reset_state()
options = ExecuteOptions.resolve(
options,
work_group=work_group,
s3_staging_dir=s3_staging_dir,
cache_size=cache_size,
cache_expiration_time=cache_expiration_time,
result_reuse_enable=result_reuse_enable,
result_reuse_minutes=result_reuse_minutes,
paramstyle=paramstyle,
on_start_query_execution=on_start_query_execution,
result_set_type_hints=result_set_type_hints,
)
operation, unload_location = self._prepare_unload(operation, options.s3_staging_dir)
self.query_id = await self._execute(
operation,
parameters=parameters,
options=options,
)
# Call user callbacks immediately after start_query_execution
self._call_on_start_query_execution(self.query_id, options)
query_execution = await self._poll(self.query_id)
if query_execution.state == AthenaQueryExecution.STATE_SUCCEEDED:
self.result_set = await asyncio.to_thread(
AthenaArrowResultSet,
connection=self._connection,
converter=self._converter,
query_execution=query_execution,
arraysize=self.arraysize,
retry_config=self._retry_config,
unload=self._unload,
unload_location=unload_location,
connect_timeout=self._connect_timeout,
request_timeout=self._request_timeout,
result_set_type_hints=options.result_set_type_hints,
**kwargs,
)
else:
raise OperationalError(query_execution.state_change_reason)
return self
[docs]
def as_arrow(self) -> Table:
"""Return query results as an Apache Arrow Table.
Returns:
Apache Arrow Table containing all query results.
"""
if not self.has_result_set:
raise ProgrammingError("No result set.")
result_set = cast(AthenaArrowResultSet, self.result_set)
return result_set.as_arrow()
[docs]
def as_polars(self) -> pl.DataFrame:
"""Return query results as a Polars DataFrame.
Returns:
Polars DataFrame containing all query results.
"""
if not self.has_result_set:
raise ProgrammingError("No result set.")
result_set = cast(AthenaArrowResultSet, self.result_set)
return result_set.as_polars()