TST: Replace 'ensure_clean' with 'temp_file' in some tests (#62474)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: kianelbo

pandas/tests/io/parser/common/test_chunksize.py

@@ -295,29 +295,28 @@ def test_empty_with_nrows_chunksize(all_parsers, iterator):
     tm.assert_frame_equal(result, expected)
 
 
-def test_read_csv_memory_growth_chunksize(all_parsers):
+def test_read_csv_memory_growth_chunksize(temp_file, all_parsers):
     # see gh-24805
     #
     # Let's just make sure that we don't crash
     # as we iteratively process all chunks.
     parser = all_parsers
 
-    with tm.ensure_clean() as path:
-        with open(path, "w", encoding="utf-8") as f:
-            for i in range(1000):
-                f.write(str(i) + "\n")
-
-        if parser.engine == "pyarrow":
-            msg = "The 'chunksize' option is not supported with the 'pyarrow' engine"
-            with pytest.raises(ValueError, match=msg):
-                with parser.read_csv(path, chunksize=20) as result:
-                    for _ in result:
-                        pass
-            return
-
-        with parser.read_csv(path, chunksize=20) as result:
-            for _ in result:
-                pass
+    with open(temp_file, "w", encoding="utf-8") as f:
+        for i in range(1000):
+            f.write(str(i) + "\n")
+
+    if parser.engine == "pyarrow":
+        msg = "The 'chunksize' option is not supported with the 'pyarrow' engine"
+        with pytest.raises(ValueError, match=msg):
+            with parser.read_csv(temp_file, chunksize=20) as result:
+                for _ in result:
+                    pass
+        return
+
+    with parser.read_csv(temp_file, chunksize=20) as result:
+        for _ in result:
+            pass
 
 
 def test_chunksize_with_usecols_second_block_shorter(all_parsers):

pandas/tests/io/parser/common/test_iterator.py

@@ -142,19 +142,18 @@ def test_iterator_skipfooter_errors(all_parsers, kwargs):
             pass
 
 
-def test_iteration_open_handle(all_parsers):
+def test_iteration_open_handle(temp_file, all_parsers):
     parser = all_parsers
     kwargs = {"header": None}
 
-    with tm.ensure_clean() as path:
-        with open(path, "w", encoding="utf-8") as f:
-            f.write("AAA\nBBB\nCCC\nDDD\nEEE\nFFF\nGGG")
+    with open(temp_file, "w", encoding="utf-8") as f:
+        f.write("AAA\nBBB\nCCC\nDDD\nEEE\nFFF\nGGG")
 
-        with open(path, encoding="utf-8") as f:
-            for line in f:
-                if "CCC" in line:
-                    break
+    with open(temp_file, encoding="utf-8") as f:
+        for line in f:
+            if "CCC" in line:
+                break
 
-            result = parser.read_csv(f, **kwargs)
-            expected = DataFrame({0: ["DDD", "EEE", "FFF", "GGG"]})
-            tm.assert_frame_equal(result, expected)
+        result = parser.read_csv(f, **kwargs)
+        expected = DataFrame({0: ["DDD", "EEE", "FFF", "GGG"]})
+        tm.assert_frame_equal(result, expected)

pandas/tests/io/parser/test_index_col.py

@@ -200,7 +200,7 @@ def test_multi_index_naming_not_all_at_beginning(all_parsers):
 
 
 @xfail_pyarrow  # ValueError: Found non-unique column index
-def test_no_multi_index_level_names_empty(all_parsers):
+def test_no_multi_index_level_names_empty(temp_file, all_parsers):
     # GH 10984
     parser = all_parsers
     midx = MultiIndex.from_tuples([("A", 1, 2), ("A", 1, 2), ("B", 1, 2)])
@@ -209,9 +209,8 @@ def test_no_multi_index_level_names_empty(all_parsers):
         index=midx,
         columns=["x", "y", "z"],
     )
-    with tm.ensure_clean() as path:
-        expected.to_csv(path)
-        result = parser.read_csv(path, index_col=[0, 1, 2])
+    expected.to_csv(temp_file)
+    result = parser.read_csv(temp_file, index_col=[0, 1, 2])
     tm.assert_frame_equal(result, expected)
 
 
@@ -240,7 +239,7 @@ def test_header_with_index_col(all_parsers):
 
 
 @pytest.mark.slow
-def test_index_col_large_csv(all_parsers, monkeypatch):
+def test_index_col_large_csv(temp_file, all_parsers, monkeypatch):
     # https://github.com/pandas-dev/pandas/issues/37094
     parser = all_parsers
 
@@ -252,11 +251,10 @@ def test_index_col_large_csv(all_parsers, monkeypatch):
         }
     )
 
-    with tm.ensure_clean() as path:
-        df.to_csv(path, index=False)
-        with monkeypatch.context() as m:
-            m.setattr("pandas.core.algorithms._MINIMUM_COMP_ARR_LEN", ARR_LEN)
-            result = parser.read_csv(path, index_col=[0])
+    df.to_csv(temp_file, index=False)
+    with monkeypatch.context() as m:
+        m.setattr("pandas.core.algorithms._MINIMUM_COMP_ARR_LEN", ARR_LEN)
+        result = parser.read_csv(temp_file, index_col=[0])
 
     tm.assert_frame_equal(result, df.set_index("a"))
 

pandas/tests/io/parser/test_python_parser_only.py

@@ -158,7 +158,9 @@ def test_skipfooter(python_parser_only, kwargs):
 @pytest.mark.parametrize(
     "compression,klass", [("gzip", "GzipFile"), ("bz2", "BZ2File")]
 )
-def test_decompression_regex_sep(python_parser_only, csv1, compression, klass):
+def test_decompression_regex_sep(
+    temp_file, python_parser_only, csv1, compression, klass
+):
     # see gh-6607
     parser = python_parser_only
 
@@ -171,12 +173,11 @@ def test_decompression_regex_sep(python_parser_only, csv1, compression, klass):
     module = pytest.importorskip(compression)
     klass = getattr(module, klass)
 
-    with tm.ensure_clean() as path:
-        with klass(path, mode="wb") as tmp:
-            tmp.write(data)
+    with klass(temp_file, mode="wb") as tmp:
+        tmp.write(data)
 
-        result = parser.read_csv(path, sep="::", compression=compression)
-        tm.assert_frame_equal(result, expected)
+    result = parser.read_csv(temp_file, sep="::", compression=compression)
+    tm.assert_frame_equal(result, expected)
 
 
 def test_read_csv_buglet_4x_multi_index(python_parser_only):

pandas/tests/io/pytables/test_round_trip.py

@@ -27,33 +27,31 @@
 pytestmark = [pytest.mark.single_cpu]
 
 
-def test_conv_read_write():
-    with tm.ensure_clean() as path:
+def test_conv_read_write(temp_file):
+    def roundtrip(key, obj, **kwargs):
+        obj.to_hdf(temp_file, key=key, **kwargs)
+        return read_hdf(temp_file, key)
 
-        def roundtrip(key, obj, **kwargs):
-            obj.to_hdf(path, key=key, **kwargs)
-            return read_hdf(path, key)
-
-        o = Series(
-            np.arange(10, dtype=np.float64), index=date_range("2020-01-01", periods=10)
-        )
-        tm.assert_series_equal(o, roundtrip("series", o))
+    o = Series(
+        np.arange(10, dtype=np.float64), index=date_range("2020-01-01", periods=10)
+    )
+    tm.assert_series_equal(o, roundtrip("series", o))
 
-        o = Series(range(10), dtype="float64", index=[f"i_{i}" for i in range(10)])
-        tm.assert_series_equal(o, roundtrip("string_series", o))
+    o = Series(range(10), dtype="float64", index=[f"i_{i}" for i in range(10)])
+    tm.assert_series_equal(o, roundtrip("string_series", o))
 
-        o = DataFrame(
-            1.1 * np.arange(120).reshape((30, 4)),
-            columns=Index(list("ABCD")),
-            index=Index([f"i-{i}" for i in range(30)]),
-        )
-        tm.assert_frame_equal(o, roundtrip("frame", o))
+    o = DataFrame(
+        1.1 * np.arange(120).reshape((30, 4)),
+        columns=Index(list("ABCD")),
+        index=Index([f"i-{i}" for i in range(30)]),
+    )
+    tm.assert_frame_equal(o, roundtrip("frame", o))
 
-        # table
-        df = DataFrame({"A": range(5), "B": range(5)})
-        df.to_hdf(path, key="table", append=True)
-        result = read_hdf(path, "table", where=["index>2"])
-        tm.assert_frame_equal(df[df.index > 2], result)
+    # table
+    df = DataFrame({"A": range(5), "B": range(5)})
+    df.to_hdf(temp_file, key="table", append=True)
+    result = read_hdf(temp_file, "table", where=["index>2"])
+    tm.assert_frame_equal(df[df.index > 2], result)
 
 
 def test_long_strings(setup_path):

pandas/tests/io/test_sql.py

@@ -748,10 +748,9 @@ def postgresql_psycopg2_conn_types(postgresql_psycopg2_engine_types):
 
 
 @pytest.fixture
-def sqlite_str():
+def sqlite_str(temp_file):
     pytest.importorskip("sqlalchemy")
-    with tm.ensure_clean() as name:
-        yield f"sqlite:///{name}"
+    return f"sqlite:///{temp_file}"
 
 
 @pytest.fixture
@@ -817,20 +816,19 @@ def sqlite_conn_types(sqlite_engine_types):
 
 
 @pytest.fixture
-def sqlite_adbc_conn():
+def sqlite_adbc_conn(temp_file):
     pytest.importorskip("pyarrow")
     pytest.importorskip("adbc_driver_sqlite")
     from adbc_driver_sqlite import dbapi
 
-    with tm.ensure_clean() as name:
-        uri = f"file:{name}"
-        with dbapi.connect(uri) as conn:
-            yield conn
-            for view in get_all_views(conn):
-                drop_view(view, conn)
-            for tbl in get_all_tables(conn):
-                drop_table(tbl, conn)
-            conn.commit()
+    uri = f"file:{temp_file}"
+    with dbapi.connect(uri) as conn:
+        yield conn
+        for view in get_all_views(conn):
+            drop_view(view, conn)
+        for tbl in get_all_tables(conn):
+            drop_table(tbl, conn)
+        conn.commit()
 
 
 @pytest.fixture
@@ -2504,20 +2502,20 @@ def test_sqlalchemy_integer_overload_mapping(conn, request, integer):
             sql.SQLTable("test_type", db, frame=df)
 
 
-def test_database_uri_string(request, test_frame1):
+def test_database_uri_string(temp_file, request, test_frame1):
     pytest.importorskip("sqlalchemy")
     # Test read_sql and .to_sql method with a database URI (GH10654)
     # db_uri = 'sqlite:///:memory:' # raises
     # sqlalchemy.exc.OperationalError: (sqlite3.OperationalError) near
     # "iris": syntax error [SQL: 'iris']
-    with tm.ensure_clean() as name:
-        db_uri = "sqlite:///" + name
-        table = "iris"
-        test_frame1.to_sql(name=table, con=db_uri, if_exists="replace", index=False)
-        test_frame2 = sql.read_sql(table, db_uri)
-        test_frame3 = sql.read_sql_table(table, db_uri)
-        query = "SELECT * FROM iris"
-        test_frame4 = sql.read_sql_query(query, db_uri)
+    name = str(temp_file)
+    db_uri = "sqlite:///" + name
+    table = "iris"
+    test_frame1.to_sql(name=table, con=db_uri, if_exists="replace", index=False)
+    test_frame2 = sql.read_sql(table, db_uri)
+    test_frame3 = sql.read_sql_table(table, db_uri)
+    query = "SELECT * FROM iris"
+    test_frame4 = sql.read_sql_query(query, db_uri)
     tm.assert_frame_equal(test_frame1, test_frame2)
     tm.assert_frame_equal(test_frame1, test_frame3)
     tm.assert_frame_equal(test_frame1, test_frame4)
@@ -2581,16 +2579,15 @@ def test_column_with_percentage(conn, request):
     tm.assert_frame_equal(res, df)
 
 
-def test_sql_open_close(test_frame3):
+def test_sql_open_close(temp_file, test_frame3):
     # Test if the IO in the database still work if the connection closed
     # between the writing and reading (as in many real situations).
 
-    with tm.ensure_clean() as name:
-        with contextlib.closing(sqlite3.connect(name)) as conn:
-            assert sql.to_sql(test_frame3, "test_frame3_legacy", conn, index=False) == 4
+    with contextlib.closing(sqlite3.connect(temp_file)) as conn:
+        assert sql.to_sql(test_frame3, "test_frame3_legacy", conn, index=False) == 4
 
-        with contextlib.closing(sqlite3.connect(name)) as conn:
-            result = sql.read_sql_query("SELECT * FROM test_frame3_legacy;", conn)
+    with contextlib.closing(sqlite3.connect(temp_file)) as conn:
+        result = sql.read_sql_query("SELECT * FROM test_frame3_legacy;", conn)
 
     tm.assert_frame_equal(test_frame3, result)