Skip to content

GH-30774: [Python] Remove deprecated use_async #34034

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
jorisvandenbossche merged 2 commits into from
Feb 7, 2023
Merged

GH-30774: [Python] Remove deprecated use_async #34034

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
291ee19
GH-34033: [Python] Remove deprecated `use_async`
Fokko Feb 3, 2023
b2a0f0b
Merge branch 'master' of https://github.com/apache/arrow into fd-remo…
Fokko Feb 7, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
44 changes: 3 additions & 41 deletions python/pyarrow/_dataset.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2437,9 +2437,6 @@ cdef class Scanner(_Weakrefable):
use_threads : bool, default True
If enabled, then maximum parallelism will be used determined by
the number of available CPU cores.
use_async : bool, default True
This flag is deprecated and is being kept for this release for
backwards compatibility. It will be removed in the next release.
memory_pool : MemoryPool, default None
For memory allocations, if required. If not specified, uses the
default pool.
Expand Down Expand Up @@ -2493,8 +2490,7 @@ cdef class Scanner(_Weakrefable):
int batch_readahead=_DEFAULT_BATCH_READAHEAD,
int fragment_readahead=_DEFAULT_FRAGMENT_READAHEAD,
FragmentScanOptions fragment_scan_options=None,
bint use_threads=True, object use_async=None,
MemoryPool memory_pool=None):
bint use_threads=True, MemoryPool memory_pool=None):
"""
Create Scanner from Dataset,

Expand Down Expand Up @@ -2544,10 +2540,6 @@ cdef class Scanner(_Weakrefable):
use_threads : bool, default True
If enabled, then maximum parallelism will be used determined by
the number of available CPU cores.
use_async : bool, default True
This flag is deprecated and is being kept for this release for
backwards compatibility. It will be removed in the next
release.
memory_pool : MemoryPool, default None
For memory allocations, if required. If not specified, uses the
default pool.
Expand All @@ -2557,11 +2549,6 @@ cdef class Scanner(_Weakrefable):
shared_ptr[CScannerBuilder] builder
shared_ptr[CScanner] scanner

if use_async is not None:
warnings.warn('The use_async flag is deprecated and has no '
'effect. It will be removed in the next release.',
FutureWarning)

options = Scanner._make_scan_options(
dataset,
dict(columns=columns, filter=filter, batch_size=batch_size,
Expand All @@ -2579,8 +2566,7 @@ cdef class Scanner(_Weakrefable):
int batch_size=_DEFAULT_BATCH_SIZE,
int batch_readahead=_DEFAULT_BATCH_READAHEAD,
FragmentScanOptions fragment_scan_options=None,
bint use_threads=True, object use_async=None,
MemoryPool memory_pool=None,):
bint use_threads=True, MemoryPool memory_pool=None,):
"""
Create Scanner from Fragment,

Expand Down Expand Up @@ -2629,20 +2615,12 @@ cdef class Scanner(_Weakrefable):
use_threads : bool, default True
If enabled, then maximum parallelism will be used determined by
the number of available CPU cores.
use_async : bool, default True
This flag is deprecated and is being kept for this release for
backwards compatibility. It will be removed in the next
release.
memory_pool : MemoryPool, default None
For memory allocations, if required. If not specified, uses the
default pool.
use_threads : bool, default True
If enabled, then maximum parallelism will be used determined by
the number of available CPU cores.
use_async : bool, default True
This flag is deprecated and is being kept for this release for
backwards compatibility. It will be removed in the next
release.
memory_pool : MemoryPool, default None
For memory allocations, if required. If not specified, uses the
default pool.
Expand All @@ -2654,11 +2632,6 @@ cdef class Scanner(_Weakrefable):

schema = schema or fragment.physical_schema

if use_async is not None:
warnings.warn('The use_async flag is deprecated and has no '
'effect. It will be removed in the next release.',
FutureWarning)

builder = make_shared[CScannerBuilder](pyarrow_unwrap_schema(schema),
fragment.unwrap(), options)
_populate_builder(builder, columns=columns, filter=filter,
Expand All @@ -2675,8 +2648,7 @@ cdef class Scanner(_Weakrefable):
def from_batches(source, *, Schema schema=None, object columns=None,
Expression filter=None, int batch_size=_DEFAULT_BATCH_SIZE,
FragmentScanOptions fragment_scan_options=None,
bint use_threads=True, object use_async=None,
MemoryPool memory_pool=None):
bint use_threads=True, MemoryPool memory_pool=None):
"""
Create a Scanner from an iterator of batches.

Expand All @@ -2702,10 +2674,6 @@ cdef class Scanner(_Weakrefable):
use_threads : bool, default True
If enabled, then maximum parallelism will be used determined by
the number of available CPU cores.
use_async : bool, default True
This flag is deprecated and is being kept for this release for
backwards compatibility. It will be removed in the next
release.
memory_pool : MemoryPool, default None
For memory allocations, if required. If not specified, uses the
default pool.
Expand All @@ -2730,12 +2698,6 @@ cdef class Scanner(_Weakrefable):
'batches instead of the given type: ' +
type(source).__name__)
builder = CScannerBuilder.FromRecordBatchReader(reader.reader)

if use_async is not None:
warnings.warn('The use_async flag is deprecated and has no '
'effect. It will be removed in the next release.',
FutureWarning)

_populate_builder(builder, columns=columns, filter=filter,
batch_size=batch_size, batch_readahead=_DEFAULT_BATCH_READAHEAD,
fragment_readahead=_DEFAULT_FRAGMENT_READAHEAD, use_threads=use_threads,
Expand Down
26 changes: 0 additions & 26 deletions python/pyarrow/tests/test_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -512,32 +512,6 @@ def test_scanner_memory_pool(dataset):
pa.set_memory_pool(old_pool)


@pytest.mark.parquet
def test_scanner_async_deprecated(dataset):
with pytest.warns(FutureWarning):
dataset.scanner(use_async=False)
with pytest.warns(FutureWarning):
dataset.scanner(use_async=True)
with pytest.warns(FutureWarning):
dataset.to_table(use_async=False)
with pytest.warns(FutureWarning):
dataset.to_table(use_async=True)
with pytest.warns(FutureWarning):
dataset.head(1, use_async=False)
with pytest.warns(FutureWarning):
dataset.head(1, use_async=True)
with pytest.warns(FutureWarning):
ds.Scanner.from_dataset(dataset, use_async=False)
with pytest.warns(FutureWarning):
ds.Scanner.from_dataset(dataset, use_async=True)
with pytest.warns(FutureWarning):
ds.Scanner.from_fragment(
next(dataset.get_fragments()), use_async=False)
with pytest.warns(FutureWarning):
ds.Scanner.from_fragment(
next(dataset.get_fragments()), use_async=True)


@pytest.mark.parquet
def test_head(dataset, dataset_reader):
result = dataset_reader.head(dataset, 0)
Expand Down