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 5bb53c7ffc GH-36973: [CI][Python] Archery linter integrated with
flake8==6.1.0 (#36976)
5bb53c7ffc is described below
commit 5bb53c7ffc9c7ca21d5d415bf8fde4d6b0034b47
Author: Dane Pitkin <[email protected]>
AuthorDate: Tue Aug 1 11:36:15 2023 -0400
GH-36973: [CI][Python] Archery linter integrated with flake8==6.1.0 (#36976)
### Rationale for this change
Fix archery lint issues with new version of flake8 dependency.
### What changes are included in this PR?
* Lint errors.
### Are these changes tested?
Yes.
```
$ flake8 --version
6.1.0 (mccabe: 0.7.0, pycodestyle: 2.11.0, pyflakes: 3.1.0) CPython 3.11.4
on Darwin
$ archery lint --python
INFO:archery:Running Python formatter (autopep8)
INFO:archery:Running Python linter (flake8)
INFO:archery:Running Cython linter (cython-lint)
$
```
### Are there any user-facing changes?
No
* Closes: #36973
Authored-by: Dane Pitkin <[email protected]>
Signed-off-by: Raúl Cumplido <[email protected]>
---
.pre-commit-config.yaml | 2 +-
dev/archery/setup.py | 5 ++---
python/pyarrow/tests/test_array.py | 2 +-
python/pyarrow/tests/test_csv.py | 2 +-
python/pyarrow/tests/test_dataset.py | 8 ++++----
python/pyarrow/tests/test_extension_type.py | 16 ++++++++--------
python/pyarrow/tests/test_flight.py | 2 +-
python/pyarrow/tests/test_table.py | 4 ++--
8 files changed, 20 insertions(+), 21 deletions(-)
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index e95778ce1c..d3c7624f63 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -37,7 +37,7 @@ repos:
entry: --entrypoint /bin/hadolint hadolint/hadolint:latest -
exclude: ^dev/.*$
- repo: https://github.com/pycqa/flake8
- rev: 5.0.3
+ rev: 6.1.0
hooks:
- id: flake8
name: Python Format
diff --git a/dev/archery/setup.py b/dev/archery/setup.py
index 7dbfe47d6e..627e576fb6 100755
--- a/dev/archery/setup.py
+++ b/dev/archery/setup.py
@@ -28,9 +28,8 @@ if sys.version_info < (3, 8):
jinja_req = 'jinja2>=2.11'
extras = {
- 'lint': [
- 'numpydoc==1.1.0', 'autopep8', 'flake8', 'cython-lint',
'cmake_format==0.6.13'
- ],
+ 'lint': ['numpydoc==1.1.0', 'autopep8', 'flake8==6.1.0', 'cython-lint',
+ 'cmake_format==0.6.13'],
'benchmark': ['pandas'],
'docker': ['ruamel.yaml', 'python-dotenv'],
'release': ['pygithub', jinja_req, 'jira', 'semver', 'gitpython'],
diff --git a/python/pyarrow/tests/test_array.py
b/python/pyarrow/tests/test_array.py
index 77eaca3dd1..0546830a66 100644
--- a/python/pyarrow/tests/test_array.py
+++ b/python/pyarrow/tests/test_array.py
@@ -301,7 +301,7 @@ def test_asarray():
np_arr = np.asarray([_ for _ in arr])
assert np_arr.tolist() == [0, 1, 2, 3]
assert np_arr.dtype == np.dtype('O')
- assert type(np_arr[0]) == pa.lib.Int64Value
+ assert isinstance(np_arr[0], pa.lib.Int64Value)
# Calling with the arrow array gives back an array with 'int64' dtype
np_arr = np.asarray(arr)
diff --git a/python/pyarrow/tests/test_csv.py b/python/pyarrow/tests/test_csv.py
index e92afce035..81c31d98ac 100644
--- a/python/pyarrow/tests/test_csv.py
+++ b/python/pyarrow/tests/test_csv.py
@@ -1936,7 +1936,7 @@ def test_write_quoting_style():
except Exception as e:
# This will trigger when we try to write a comma (,)
# without quotes, which is invalid
- assert type(e) == res
+ assert isinstance(e, res)
break
assert buf.getvalue() == res
buf.seek(0)
diff --git a/python/pyarrow/tests/test_dataset.py
b/python/pyarrow/tests/test_dataset.py
index a70cf2fbc7..f92317c0f2 100644
--- a/python/pyarrow/tests/test_dataset.py
+++ b/python/pyarrow/tests/test_dataset.py
@@ -5021,8 +5021,8 @@ def test_dataset_filter(tempdir, dstype):
# Ensure chained filtering works.
result = ds1.filter(pc.field("colA") < 3).filter(pc.field("col2") == "a")
- assert type(result) == (ds.FileSystemDataset if dstype ==
- "fs" else ds.InMemoryDataset)
+ expected = ds.FileSystemDataset if dstype == "fs" else ds.InMemoryDataset
+ assert isinstance(result, expected)
assert result.to_table() == pa.table({
"colA": [1],
@@ -5181,9 +5181,9 @@ def test_read_table_nested_columns(tempdir, format):
"a.dotted.field": [1, 2],
"interaction": [
{"type": None, "element": "button",
- "values": [1, 2], "structs":[{"foo": "bar"}, None]},
+ "values": [1, 2], "structs": [{"foo": "bar"}, None]},
{"type": "scroll", "element": "window",
- "values": [None, 3, 4], "structs":[{"fizz": "buzz"}]}
+ "values": [None, 3, 4], "structs": [{"fizz": "buzz"}]}
]})
ds.write_dataset(table, tempdir / "table", format=format)
ds1 = ds.dataset(tempdir / "table", format=format)
diff --git a/python/pyarrow/tests/test_extension_type.py
b/python/pyarrow/tests/test_extension_type.py
index 009896fd67..973aa29c75 100644
--- a/python/pyarrow/tests/test_extension_type.py
+++ b/python/pyarrow/tests/test_extension_type.py
@@ -340,8 +340,8 @@ def test_ext_scalar_from_array():
assert len(scalars_a) == 4
assert ty1.__arrow_ext_scalar_class__() == UuidScalarType
- assert type(a[0]) == UuidScalarType
- assert type(scalars_a[0]) == UuidScalarType
+ assert isinstance(a[0], UuidScalarType)
+ assert isinstance(scalars_a[0], UuidScalarType)
for s, val in zip(scalars_a, data):
assert isinstance(s, pa.ExtensionScalar)
@@ -737,7 +737,7 @@ class PeriodType(pa.ExtensionType):
def __eq__(self, other):
if isinstance(other, pa.BaseExtensionType):
- return (type(self) == type(other) and
+ return (isinstance(self, type(other)) and
self.freq == other.freq)
else:
return NotImplemented
@@ -799,7 +799,7 @@ def test_generic_ext_type_ipc(registered_period_type):
arr = pa.ExtensionArray.from_storage(period_type, storage)
batch = pa.RecordBatch.from_arrays([arr], ["ext"])
# check the built array has exactly the expected clss
- assert type(arr) == period_class
+ assert isinstance(arr, period_class)
buf = ipc_write_batch(batch)
del batch
@@ -807,7 +807,7 @@ def test_generic_ext_type_ipc(registered_period_type):
result = batch.column(0)
# check the deserialized array class is the expected one
- assert type(result) == period_class
+ assert isinstance(result, period_class)
assert result.type.extension_name == "test.period"
assert arr.storage.to_pylist() == [1, 2, 3, 4]
@@ -830,7 +830,7 @@ def test_generic_ext_type_ipc(registered_period_type):
result = batch.column(0)
assert isinstance(result.type, PeriodType)
assert result.type.freq == 'H'
- assert type(result) == period_class
+ assert isinstance(result, period_class)
def test_generic_ext_type_ipc_unknown(registered_period_type):
@@ -1261,7 +1261,7 @@ def test_tensor_type_ipc(tensor_type):
# check the built array has exactly the expected clss
tensor_class = tensor_type.__arrow_ext_class__()
- assert type(arr) == tensor_class
+ assert isinstance(arr, tensor_class)
buf = ipc_write_batch(batch)
del batch
@@ -1269,7 +1269,7 @@ def test_tensor_type_ipc(tensor_type):
result = batch.column(0)
# check the deserialized array class is the expected one
- assert type(result) == tensor_class
+ assert isinstance(result, tensor_class)
assert result.type.extension_name == "arrow.fixed_shape_tensor"
assert arr.storage.to_pylist() == [[1, 2, 3, 4, 5, 6, 1, 2, 3, 4, 5, 6]]
diff --git a/python/pyarrow/tests/test_flight.py
b/python/pyarrow/tests/test_flight.py
index 6c1c582dce..bf15ad0bc4 100644
--- a/python/pyarrow/tests/test_flight.py
+++ b/python/pyarrow/tests/test_flight.py
@@ -1495,7 +1495,7 @@ def test_tls_override_hostname():
"""Check that incorrectly overriding the hostname fails."""
certs = example_tls_certs()
- with ConstantFlightServer(tls_certificates=certs["certificates"]) as s,\
+ with ConstantFlightServer(tls_certificates=certs["certificates"]) as s, \
flight.connect(('localhost', s.port),
tls_root_certs=certs["root_cert"],
override_hostname="fakehostname") as client:
diff --git a/python/pyarrow/tests/test_table.py
b/python/pyarrow/tests/test_table.py
index 61cfb1af58..e28256e91f 100644
--- a/python/pyarrow/tests/test_table.py
+++ b/python/pyarrow/tests/test_table.py
@@ -511,7 +511,7 @@ def test_recordbatch_basics():
('c0', [0, 1, 2, 3, 4]),
('c1', [-10, -5, 0, None, 10])
])
- assert type(pydict) == dict
+ assert isinstance(pydict, dict)
with pytest.raises(IndexError):
# bounds checking
@@ -949,7 +949,7 @@ def test_table_basics():
('a', [0, 1, 2, 3, 4]),
('b', [-10, -5, 0, 5, 10])
])
- assert type(pydict) == dict
+ assert isinstance(pydict, dict)
columns = []
for col in table.itercolumns():
