This is an automated email from the ASF dual-hosted git repository.
raulcd pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow.git
The following commit(s) were added to refs/heads/main by this push:
new eb19b7fce7d GH-49046: [Dev][Python] Remove unused scripts under
python/scripts (#50640)
eb19b7fce7d is described below
commit eb19b7fce7dd33af4e224acb8873797ec2675cc1
Author: Guja <[email protected]>
AuthorDate: Mon Jul 27 11:28:57 2026 +0200
GH-49046: [Dev][Python] Remove unused scripts under python/scripts (#50640)
### Rationale for this change
Resolves #49046
`python/scripts/test_imports.py` and `python/scripts/test_leak.py` are
leftovers from an older
test layout. They are not referenced by CI, packaging or the pytest suite,
and are not
documented anywhere. Their `test_`-prefixed names have also caused
accidental pytest collection
in the past (ARROW-1033). This follows the suggestion on the issue to
remove them.
Deletes `python/scripts/test_imports.py` and `python/scripts/test_leak.py`.
The other two scripts in that directory are untouched and still in use:
`run_emscripten_tests.py` (invoked from
`ci/scripts/python_test_emscripten.sh`) and
`update_stub_docstrings.py`.
The issue description raised the option of keeping `test_leak.py` as a
documented snippet for
checking leaks. This PR removes it, following the later comment. Happy to
restore and document
it under the developer docs instead if reviewers prefer.
### Are these changes tested?
No new tests, this only removes files that nothing references. I grepped
`ci/`, `dev/`,
`python/setup.py`, `python/pyproject.toml` and `python/MANIFEST.in` for
references and found
none. The only remaining mention in the repository is a historical
`CHANGELOG.md` entry for
ARROW-1033, left as is.
### Are there any user-facing changes?
No.
### AI usage disclosure
I used Claude Code to grep the repository for remaining references to the
two scripts and to
help draft this description. The change itself is a two file deletion, and
I reviewed both the
search results and the diff.
* GitHub Issue: #49046
Authored-by: Guja <[email protected]>
Signed-off-by: Raúl Cumplido <[email protected]>
---
python/scripts/test_imports.py | 21 --------
python/scripts/test_leak.py | 108 -----------------------------------------
2 files changed, 129 deletions(-)
diff --git a/python/scripts/test_imports.py b/python/scripts/test_imports.py
deleted file mode 100644
index c0beb4473ae..00000000000
--- a/python/scripts/test_imports.py
+++ /dev/null
@@ -1,21 +0,0 @@
-# Licensed to the Apache Software Foundation (ASF) under one
-# or more contributor license agreements. See the NOTICE file
-# distributed with this work for additional information
-# regarding copyright ownership. The ASF licenses this file
-# to you under the Apache License, Version 2.0 (the
-# "License"); you may not use this file except in compliance
-# with the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing,
-# software distributed under the License is distributed on an
-# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-# KIND, either express or implied. See the License for the
-# specific language governing permissions and limitations
-# under the License.
-
-import pyarrow as pa # noqa
-import sys
-
-assert 'pandas' not in sys.modules
diff --git a/python/scripts/test_leak.py b/python/scripts/test_leak.py
deleted file mode 100644
index e99c4751680..00000000000
--- a/python/scripts/test_leak.py
+++ /dev/null
@@ -1,108 +0,0 @@
-#!/usr/bin/env python
-
-# Licensed to the Apache Software Foundation (ASF) under one
-# or more contributor license agreements. See the NOTICE file
-# distributed with this work for additional information
-# regarding copyright ownership. The ASF licenses this file
-# to you under the Apache License, Version 2.0 (the
-# "License"); you may not use this file except in compliance
-# with the License. You may obtain a copy of the License at
-#
-# http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing,
-# software distributed under the License is distributed on an
-# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
-# KIND, either express or implied. See the License for the
-# specific language governing permissions and limitations
-# under the License.
-
-import pyarrow as pa
-import numpy as np
-import pandas as pd
-from pyarrow.tests.util import rands
-import memory_profiler
-import gc
-import io
-
-MEGABYTE = 1 << 20
-
-
-def assert_does_not_leak(f, iterations=10, check_interval=1, tolerance=5):
- gc.collect()
- baseline = memory_profiler.memory_usage()[0]
- for i in range(iterations):
- f()
- if i % check_interval == 0:
- gc.collect()
- usage = memory_profiler.memory_usage()[0]
- diff = usage - baseline
- print(f"{i}: {diff}\r", end="")
- if diff > tolerance:
- raise Exception(f"Memory increased by {diff} megabytes after
{i + 1} "
- "iterations")
- gc.collect()
- usage = memory_profiler.memory_usage()[0]
- diff = usage - baseline
- print(f"\nMemory increased by {diff} megabytes after {iterations}
iterations")
-
-
-def test_leak1():
- data = [pa.array(np.concatenate([np.random.randn(100000)] * 1000))]
- table = pa.Table.from_arrays(data, ['foo'])
-
- def func():
- table.to_pandas()
- assert_does_not_leak(func)
-
-
-def test_leak2():
- data = [pa.array(np.concatenate([np.random.randn(100000)] * 10))]
- table = pa.Table.from_arrays(data, ['foo'])
-
- def func():
- df = table.to_pandas()
-
- batch = pa.RecordBatch.from_pandas(df)
-
- sink = io.BytesIO()
- writer = pa.RecordBatchFileWriter(sink, batch.schema)
- writer.write_batch(batch)
- writer.close()
-
- buf_reader = pa.BufferReader(sink.getvalue())
- reader = pa.open_file(buf_reader)
- reader.read_all()
-
- assert_does_not_leak(func, iterations=50, tolerance=50)
-
-
-def test_leak3():
- import pyarrow.parquet as pq
-
- df = pd.DataFrame({f'a{i}': [1, 2, 3, 4] for i in range(50)})
- table = pa.Table.from_pandas(df, preserve_index=False)
-
- writer = pq.ParquetWriter('leak_test_' + rands(5) + '.parquet',
- table.schema)
-
- def func():
- writer.write_table(table, row_group_size=len(table))
-
- # This does not "leak" per se but we do want to have this use as little
- # memory as possible
- assert_does_not_leak(func, iterations=500,
- check_interval=50, tolerance=20)
-
-
-def test_ARROW_8801():
- x = pd.to_datetime(np.random.randint(0, 2**32, size=2**20, dtype=np.int64),
- unit='ms', utc=True)
- table = pa.table(pd.DataFrame({'x': x}))
-
- assert_does_not_leak(lambda: table.to_pandas(split_blocks=False),
- iterations=1000, check_interval=50, tolerance=1000)
-
-
-if __name__ == '__main__':
- test_ARROW_8801()
