Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

Commit 7d7ee41

Browse files
authored
chore: use temp_file instead of ensure_clean in test (#62529)
1 parent 5cc3240 commit 7d7ee41

File tree

2 files changed

+60
-55
lines changed

2 files changed

+60
-55
lines changed

‎pandas/tests/io/parser/test_encoding.py‎

Lines changed: 32 additions & 38 deletions
Original file line numberDiff line numberDiff line change
@@ -9,7 +9,6 @@
99
)
1010
import os
1111
import tempfile
12-
import uuid
1312

1413
import numpy as np
1514
import pytest
@@ -51,28 +50,26 @@ def test_read_csv_unicode(all_parsers):
5150
@skip_pyarrow
5251
@pytest.mark.parametrize("sep", [",", "\t"])
5352
@pytest.mark.parametrize("encoding", ["utf-16", "utf-16le", "utf-16be"])
54-
def test_utf16_bom_skiprows(all_parsers, sep, encoding):
53+
def test_utf16_bom_skiprows(all_parsers, sep, encoding, temp_file):
5554
# see gh-2298
5655
parser = all_parsers
5756
data = """skip this
5857
skip this too
5958
A,B,C
6059
1,2,3
6160
4,5,6""".replace(",", sep)
62-
path = f"__{uuid.uuid4()}__.csv"
6361
kwargs = {"sep": sep, "skiprows": 2}
6462
utf8 = "utf-8"
6563

66-
with tm.ensure_clean(path) as path:
67-
bytes_data = data.encode(encoding)
64+
bytes_data = data.encode(encoding)
6865

69-
with open(path, "wb") as f:
70-
f.write(bytes_data)
66+
with open(temp_file, "wb") as f:
67+
f.write(bytes_data)
7168

72-
with TextIOWrapper(BytesIO(data.encode(utf8)), encoding=utf8) as bytes_buffer:
73-
result = parser.read_csv(path, encoding=encoding, **kwargs)
74-
expected = parser.read_csv(bytes_buffer, encoding=utf8, **kwargs)
75-
tm.assert_frame_equal(result, expected)
69+
with TextIOWrapper(BytesIO(data.encode(utf8)), encoding=utf8) as bytes_buffer:
70+
result = parser.read_csv(temp_file, encoding=encoding, **kwargs)
71+
expected = parser.read_csv(bytes_buffer, encoding=utf8, **kwargs)
72+
tm.assert_frame_equal(result, expected)
7673

7774

7875
def test_utf16_example(all_parsers, csv_dir_path):
@@ -240,7 +237,7 @@ def test_parse_encoded_special_characters(encoding):
240237

241238

242239
@pytest.mark.parametrize("encoding", ["utf-8", None, "utf-16", "cp1255", "latin-1"])
243-
def test_encoding_memory_map(all_parsers, encoding):
240+
def test_encoding_memory_map(all_parsers, encoding, temp_file):
244241
# GH40986
245242
parser = all_parsers
246243
expected = DataFrame(
@@ -250,20 +247,19 @@ def test_encoding_memory_map(all_parsers, encoding):
250247
"weapon": ["sai", "bo staff", "nunchunk", "katana"],
251248
}
252249
)
253-
with tm.ensure_clean() as file:
254-
expected.to_csv(file, index=False, encoding=encoding)
250+
expected.to_csv(temp_file, index=False, encoding=encoding)
255251

256-
if parser.engine == "pyarrow":
257-
msg = "The 'memory_map' option is not supported with the 'pyarrow' engine"
258-
with pytest.raises(ValueError, match=msg):
259-
parser.read_csv(file, encoding=encoding, memory_map=True)
260-
return
252+
if parser.engine == "pyarrow":
253+
msg = "The 'memory_map' option is not supported with the 'pyarrow' engine"
254+
with pytest.raises(ValueError, match=msg):
255+
parser.read_csv(temp_file, encoding=encoding, memory_map=True)
256+
return
261257

262-
df = parser.read_csv(file, encoding=encoding, memory_map=True)
258+
df = parser.read_csv(temp_file, encoding=encoding, memory_map=True)
263259
tm.assert_frame_equal(df, expected)
264260

265261

266-
def test_chunk_splits_multibyte_char(all_parsers):
262+
def test_chunk_splits_multibyte_char(all_parsers, temp_file):
267263
"""
268264
Chunk splits a multibyte character with memory_map=True
269265
@@ -276,20 +272,19 @@ def test_chunk_splits_multibyte_char(all_parsers):
276272
# Put two-bytes utf-8 encoded character "ą" at the end of chunk
277273
# utf-8 encoding of "ą" is b'\xc4\x85'
278274
df.iloc[2047] = "a" * 127 + "ą"
279-
with tm.ensure_clean("bug-gh43540.csv") as fname:
280-
df.to_csv(fname, index=False, header=False, encoding="utf-8")
275+
df.to_csv(temp_file, index=False, header=False, encoding="utf-8")
281276

282-
if parser.engine == "pyarrow":
283-
msg = "The 'memory_map' option is not supported with the 'pyarrow' engine"
284-
with pytest.raises(ValueError, match=msg):
285-
parser.read_csv(fname, header=None, memory_map=True)
286-
return
277+
if parser.engine == "pyarrow":
278+
msg = "The 'memory_map' option is not supported with the 'pyarrow' engine"
279+
with pytest.raises(ValueError, match=msg):
280+
parser.read_csv(temp_file, header=None, memory_map=True)
281+
return
287282

288-
dfr = parser.read_csv(fname, header=None, memory_map=True)
283+
dfr = parser.read_csv(temp_file, header=None, memory_map=True)
289284
tm.assert_frame_equal(dfr, df)
290285

291286

292-
def test_readcsv_memmap_utf8(all_parsers):
287+
def test_readcsv_memmap_utf8(all_parsers, temp_file):
293288
"""
294289
GH 43787
295290
@@ -310,16 +305,15 @@ def test_readcsv_memmap_utf8(all_parsers):
310305
lines.append(line)
311306
parser = all_parsers
312307
df = DataFrame(lines)
313-
with tm.ensure_clean("utf8test.csv") as fname:
314-
df.to_csv(fname, index=False, header=False, encoding="utf-8")
308+
df.to_csv(temp_file, index=False, header=False, encoding="utf-8")
315309

316-
if parser.engine == "pyarrow":
317-
msg = "The 'memory_map' option is not supported with the 'pyarrow' engine"
318-
with pytest.raises(ValueError, match=msg):
319-
parser.read_csv(fname, header=None, memory_map=True, encoding="utf-8")
320-
return
310+
if parser.engine == "pyarrow":
311+
msg = "The 'memory_map' option is not supported with the 'pyarrow' engine"
312+
with pytest.raises(ValueError, match=msg):
313+
parser.read_csv(temp_file, header=None, memory_map=True, encoding="utf-8")
314+
return
321315

322-
dfr = parser.read_csv(fname, header=None, memory_map=True, encoding="utf-8")
316+
dfr = parser.read_csv(temp_file, header=None, memory_map=True, encoding="utf-8")
323317
tm.assert_frame_equal(df, dfr)
324318

325319

‎pandas/tests/io/xml/test_xml_dtypes.py‎

Lines changed: 28 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -31,11 +31,10 @@ def iterparse(request):
3131
return request.param
3232

3333

34-
def read_xml_iterparse(data, **kwargs):
35-
with tm.ensure_clean() as path:
36-
with open(path, "w", encoding="utf-8") as f:
37-
f.write(data)
38-
return read_xml(path, **kwargs)
34+
def read_xml_iterparse(data, temp_file, **kwargs):
35+
with open(temp_file, "w", encoding="utf-8") as f:
36+
f.write(data)
37+
return read_xml(temp_file, **kwargs)
3938

4039

4140
xml_types = """\
@@ -84,13 +83,14 @@ def read_xml_iterparse(data, **kwargs):
8483
# DTYPE
8584

8685

87-
def test_dtype_single_str(parser):
86+
def test_dtype_single_str(parser, temp_file):
8887
df_result = read_xml(StringIO(xml_types), dtype={"degrees": "str"}, parser=parser)
8988
df_iter = read_xml_iterparse(
9089
xml_types,
9190
parser=parser,
9291
dtype={"degrees": "str"},
9392
iterparse={"row": ["shape", "degrees", "sides"]},
93+
temp_file=temp_file,
9494
)
9595

9696
df_expected = DataFrame(
@@ -105,13 +105,14 @@ def test_dtype_single_str(parser):
105105
tm.assert_frame_equal(df_iter, df_expected)
106106

107107

108-
def test_dtypes_all_str(parser):
108+
def test_dtypes_all_str(parser, temp_file):
109109
df_result = read_xml(StringIO(xml_dates), dtype="string", parser=parser)
110110
df_iter = read_xml_iterparse(
111111
xml_dates,
112112
parser=parser,
113113
dtype="string",
114114
iterparse={"row": ["shape", "degrees", "sides", "date"]},
115+
temp_file=temp_file,
115116
)
116117

117118
df_expected = DataFrame(
@@ -128,7 +129,7 @@ def test_dtypes_all_str(parser):
128129
tm.assert_frame_equal(df_iter, df_expected)
129130

130131

131-
def test_dtypes_with_names(parser):
132+
def test_dtypes_with_names(parser, temp_file):
132133
df_result = read_xml(
133134
StringIO(xml_dates),
134135
names=["Col1", "Col2", "Col3", "Col4"],
@@ -141,6 +142,7 @@ def test_dtypes_with_names(parser):
141142
names=["Col1", "Col2", "Col3", "Col4"],
142143
dtype={"Col2": "string", "Col3": "Int64", "Col4": "datetime64[ns]"},
143144
iterparse={"row": ["shape", "degrees", "sides", "date"]},
145+
temp_file=temp_file,
144146
)
145147

146148
df_expected = DataFrame(
@@ -158,13 +160,14 @@ def test_dtypes_with_names(parser):
158160
tm.assert_frame_equal(df_iter, df_expected)
159161

160162

161-
def test_dtype_nullable_int(parser):
163+
def test_dtype_nullable_int(parser, temp_file):
162164
df_result = read_xml(StringIO(xml_types), dtype={"sides": "Int64"}, parser=parser)
163165
df_iter = read_xml_iterparse(
164166
xml_types,
165167
parser=parser,
166168
dtype={"sides": "Int64"},
167169
iterparse={"row": ["shape", "degrees", "sides"]},
170+
temp_file=temp_file,
168171
)
169172

170173
df_expected = DataFrame(
@@ -179,13 +182,14 @@ def test_dtype_nullable_int(parser):
179182
tm.assert_frame_equal(df_iter, df_expected)
180183

181184

182-
def test_dtype_float(parser):
185+
def test_dtype_float(parser, temp_file):
183186
df_result = read_xml(StringIO(xml_types), dtype={"degrees": "float"}, parser=parser)
184187
df_iter = read_xml_iterparse(
185188
xml_types,
186189
parser=parser,
187190
dtype={"degrees": "float"},
188191
iterparse={"row": ["shape", "degrees", "sides"]},
192+
temp_file=temp_file,
189193
)
190194

191195
df_expected = DataFrame(
@@ -209,7 +213,7 @@ def test_wrong_dtype(xml_books, parser, iterparse):
209213
)
210214

211215

212-
def test_both_dtype_converters(parser):
216+
def test_both_dtype_converters(parser, temp_file):
213217
df_expected = DataFrame(
214218
{
215219
"shape": ["square", "circle", "triangle"],
@@ -231,6 +235,7 @@ def test_both_dtype_converters(parser):
231235
converters={"degrees": str},
232236
parser=parser,
233237
iterparse={"row": ["shape", "degrees", "sides"]},
238+
temp_file=temp_file,
234239
)
235240

236241
tm.assert_frame_equal(df_result, df_expected)
@@ -240,7 +245,7 @@ def test_both_dtype_converters(parser):
240245
# CONVERTERS
241246

242247

243-
def test_converters_str(parser):
248+
def test_converters_str(parser, temp_file):
244249
df_result = read_xml(
245250
StringIO(xml_types), converters={"degrees": str}, parser=parser
246251
)
@@ -249,6 +254,7 @@ def test_converters_str(parser):
249254
parser=parser,
250255
converters={"degrees": str},
251256
iterparse={"row": ["shape", "degrees", "sides"]},
257+
temp_file=temp_file,
252258
)
253259

254260
df_expected = DataFrame(
@@ -263,7 +269,7 @@ def test_converters_str(parser):
263269
tm.assert_frame_equal(df_iter, df_expected)
264270

265271

266-
def test_converters_date(parser):
272+
def test_converters_date(parser, temp_file):
267273
convert_to_datetime = lambda x: to_datetime(x)
268274
df_result = read_xml(
269275
StringIO(xml_dates), converters={"date": convert_to_datetime}, parser=parser
@@ -273,6 +279,7 @@ def test_converters_date(parser):
273279
parser=parser,
274280
converters={"date": convert_to_datetime},
275281
iterparse={"row": ["shape", "degrees", "sides", "date"]},
282+
temp_file=temp_file,
276283
)
277284

278285
df_expected = DataFrame(
@@ -312,13 +319,14 @@ def test_callable_str_converters(xml_books, parser, iterparse):
312319
# PARSE DATES
313320

314321

315-
def test_parse_dates_column_name(parser):
322+
def test_parse_dates_column_name(parser, temp_file):
316323
df_result = read_xml(StringIO(xml_dates), parse_dates=["date"], parser=parser)
317324
df_iter = read_xml_iterparse(
318325
xml_dates,
319326
parser=parser,
320327
parse_dates=["date"],
321328
iterparse={"row": ["shape", "degrees", "sides", "date"]},
329+
temp_file=temp_file,
322330
)
323331

324332
df_expected = DataFrame(
@@ -334,13 +342,14 @@ def test_parse_dates_column_name(parser):
334342
tm.assert_frame_equal(df_iter, df_expected)
335343

336344

337-
def test_parse_dates_column_index(parser):
345+
def test_parse_dates_column_index(parser, temp_file):
338346
df_result = read_xml(StringIO(xml_dates), parse_dates=[3], parser=parser)
339347
df_iter = read_xml_iterparse(
340348
xml_dates,
341349
parser=parser,
342350
parse_dates=[3],
343351
iterparse={"row": ["shape", "degrees", "sides", "date"]},
352+
temp_file=temp_file,
344353
)
345354

346355
df_expected = DataFrame(
@@ -356,14 +365,15 @@ def test_parse_dates_column_index(parser):
356365
tm.assert_frame_equal(df_iter, df_expected)
357366

358367

359-
def test_parse_dates_true(parser):
368+
def test_parse_dates_true(parser, temp_file):
360369
df_result = read_xml(StringIO(xml_dates), parse_dates=True, parser=parser)
361370

362371
df_iter = read_xml_iterparse(
363372
xml_dates,
364373
parser=parser,
365374
parse_dates=True,
366375
iterparse={"row": ["shape", "degrees", "sides", "date"]},
376+
temp_file=temp_file,
367377
)
368378

369379
df_expected = DataFrame(
@@ -379,7 +389,7 @@ def test_parse_dates_true(parser):
379389
tm.assert_frame_equal(df_iter, df_expected)
380390

381391

382-
def test_day_first_parse_dates(parser):
392+
def test_day_first_parse_dates(parser, temp_file):
383393
xml = """\
384394
<?xml version='1.0' encoding='utf-8'?>
385395
<data>
@@ -421,6 +431,7 @@ def test_day_first_parse_dates(parser):
421431
parse_dates=["date"],
422432
parser=parser,
423433
iterparse={"row": ["shape", "degrees", "sides", "date"]},
434+
temp_file=temp_file,
424435
)
425436

426437
tm.assert_frame_equal(df_result, df_expected)

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /