TST/CLN: Remove ensure_clean_path for tmp_dir fixture (#48925)

Author: mroeschke

pandas/tests/io/pytables/common.py

@@ -1,5 +1,5 @@
 from contextlib import contextmanager
-import os
+import pathlib
 import tempfile
 from typing import Generator
 
@@ -14,14 +14,6 @@
 tables.parameters.MAX_THREADS = 1
 
 
-def safe_remove(path):
-    if path is not None:
-        try:
-            os.remove(path)  # noqa: PDF008
-        except OSError:
-            pass
-
-
 def safe_close(store):
     try:
         if store is not None:
@@ -30,50 +22,22 @@ def safe_close(store):
         pass
 
 
-def create_tempfile(path):
-    """create an unopened named temporary file"""
-    return os.path.join(tempfile.gettempdir(), path)
-
-
 # contextmanager to ensure the file cleanup
 @contextmanager
 def ensure_clean_store(
     path, mode="a", complevel=None, complib=None, fletcher32=False
 ) -> Generator[HDFStore, None, None]:
 
-    try:
-
-        # put in the temporary path if we don't have one already
-        if not len(os.path.dirname(path)):
-            path = create_tempfile(path)
-
-        store = HDFStore(
-            path, mode=mode, complevel=complevel, complib=complib, fletcher32=False
-        )
-        yield store
-    finally:
-        safe_close(store)
-        if mode == "w" or mode == "a":
-            safe_remove(path)
-
-
-@contextmanager
-def ensure_clean_path(path):
-    """
-    return essentially a named temporary file that is not opened
-    and deleted on exiting; if path is a list, then create and
-    return list of filenames
-    """
-    try:
-        if isinstance(path, list):
-            filenames = [create_tempfile(p) for p in path]
-            yield filenames
-        else:
-            filenames = [create_tempfile(path)]
-            yield filenames[0]
-    finally:
-        for f in filenames:
-            safe_remove(f)
+    with tempfile.TemporaryDirectory() as tmpdirname:
+        tmp_path = pathlib.Path(tmpdirname, path)
+        with HDFStore(
+            tmp_path,
+            mode=mode,
+            complevel=complevel,
+            complib=complib,
+            fletcher32=fletcher32,
+        ) as store:
+            yield store
 
 
 def _maybe_remove(store, key):

pandas/tests/io/pytables/test_append.py

@@ -20,7 +20,6 @@
 )
 from pandas.tests.io.pytables.common import (
     _maybe_remove,
-    ensure_clean_path,
     ensure_clean_store,
 )
 
@@ -634,7 +633,7 @@ def check_col(key, name, size):
         tm.assert_frame_equal(result, expected)
 
 
-def test_append_hierarchical(setup_path, multiindex_dataframe_random_data):
+def test_append_hierarchical(tmp_path, setup_path, multiindex_dataframe_random_data):
     df = multiindex_dataframe_random_data
     df.columns.name = None
 
@@ -648,11 +647,11 @@ def test_append_hierarchical(setup_path, multiindex_dataframe_random_data):
         expected = df.reindex(columns=["A", "B"])
         tm.assert_frame_equal(result, expected)
 
-    with ensure_clean_path("test.hdf") as path:
-        df.to_hdf(path, "df", format="table")
-        result = read_hdf(path, "df", columns=["A", "B"])
-        expected = df.reindex(columns=["A", "B"])
-        tm.assert_frame_equal(result, expected)
+    path = tmp_path / "test.hdf"
+    df.to_hdf(path, "df", format="table")
+    result = read_hdf(path, "df", columns=["A", "B"])
+    expected = df.reindex(columns=["A", "B"])
+    tm.assert_frame_equal(result, expected)
 
 
 def test_append_misc(setup_path):

pandas/tests/io/pytables/test_categorical.py

@@ -11,7 +11,6 @@
 )
 from pandas.tests.io.pytables.common import (
     _maybe_remove,
-    ensure_clean_path,
     ensure_clean_store,
 )
 
@@ -147,7 +146,7 @@ def test_categorical(setup_path):
             store.select("df3/meta/s/meta")
 
 
-def test_categorical_conversion(setup_path):
+def test_categorical_conversion(tmp_path, setup_path):
 
     # GH13322
     # Check that read_hdf with categorical columns doesn't return rows if
@@ -161,24 +160,24 @@ def test_categorical_conversion(setup_path):
 
     # We are expecting an empty DataFrame matching types of df
     expected = df.iloc[[], :]
-    with ensure_clean_path(setup_path) as path:
-        df.to_hdf(path, "df", format="table", data_columns=True)
-        result = read_hdf(path, "df", where="obsids=B")
-        tm.assert_frame_equal(result, expected)
+    path = tmp_path / setup_path
+    df.to_hdf(path, "df", format="table", data_columns=True)
+    result = read_hdf(path, "df", where="obsids=B")
+    tm.assert_frame_equal(result, expected)
 
     # Test with categories
     df.obsids = df.obsids.astype("category")
     df.imgids = df.imgids.astype("category")
 
     # We are expecting an empty DataFrame matching types of df
     expected = df.iloc[[], :]
-    with ensure_clean_path(setup_path) as path:
-        df.to_hdf(path, "df", format="table", data_columns=True)
-        result = read_hdf(path, "df", where="obsids=B")
-        tm.assert_frame_equal(result, expected)
+    path = tmp_path / setup_path
+    df.to_hdf(path, "df", format="table", data_columns=True)
+    result = read_hdf(path, "df", where="obsids=B")
+    tm.assert_frame_equal(result, expected)
 
 
-def test_categorical_nan_only_columns(setup_path):
+def test_categorical_nan_only_columns(tmp_path, setup_path):
     # GH18413
     # Check that read_hdf with categorical columns with NaN-only values can
     # be read back.
@@ -194,10 +193,10 @@ def test_categorical_nan_only_columns(setup_path):
     df["b"] = df.b.astype("category")
     df["d"] = df.b.astype("category")
     expected = df
-    with ensure_clean_path(setup_path) as path:
-        df.to_hdf(path, "df", format="table", data_columns=True)
-        result = read_hdf(path, "df")
-        tm.assert_frame_equal(result, expected)
+    path = tmp_path / setup_path
+    df.to_hdf(path, "df", format="table", data_columns=True)
+    result = read_hdf(path, "df")
+    tm.assert_frame_equal(result, expected)
 
 
 @pytest.mark.parametrize(
@@ -207,7 +206,9 @@ def test_categorical_nan_only_columns(setup_path):
         ('col=="a"', DataFrame({"col": ["a", "b", "s"]}), DataFrame({"col": ["a"]})),
     ],
 )
-def test_convert_value(setup_path, where: str, df: DataFrame, expected: DataFrame):
+def test_convert_value(
+    tmp_path, setup_path, where: str, df: DataFrame, expected: DataFrame
+):
     # GH39420
     # Check that read_hdf with categorical columns can filter by where condition.
     df.col = df.col.astype("category")
@@ -216,7 +217,7 @@ def test_convert_value(setup_path, where: str, df: DataFrame, expected: DataFram
     expected.col = expected.col.astype("category")
     expected.col = expected.col.cat.set_categories(categorical_values)
 
-    with ensure_clean_path(setup_path) as path:
-        df.to_hdf(path, "df", format="table", min_itemsize=max_widths)
-        result = read_hdf(path, where=where)
-        tm.assert_frame_equal(result, expected)
+    path = tmp_path / setup_path
+    df.to_hdf(path, "df", format="table", min_itemsize=max_widths)
+    result = read_hdf(path, where=where)
+    tm.assert_frame_equal(result, expected)

pandas/tests/io/pytables/test_compat.py

@@ -2,13 +2,12 @@
 
 import pandas as pd
 import pandas._testing as tm
-from pandas.tests.io.pytables.common import ensure_clean_path
 
 tables = pytest.importorskip("tables")
 
 
 @pytest.fixture
-def pytables_hdf5_file():
+def pytables_hdf5_file(tmp_path):
     """
     Use PyTables to create a simple HDF5 file.
     """
@@ -29,16 +28,15 @@ def pytables_hdf5_file():
 
     objname = "pandas_test_timeseries"
 
-    with ensure_clean_path("written_with_pytables.h5") as path:
-        # The `ensure_clean_path` context mgr removes the temp file upon exit.
-        with tables.open_file(path, mode="w") as f:
-            t = f.create_table("/", name=objname, description=table_schema)
-            for sample in testsamples:
-                for key, value in sample.items():
-                    t.row[key] = value
-                t.row.append()
+    path = tmp_path / "written_with_pytables.h5"
+    with tables.open_file(path, mode="w") as f:
+        t = f.create_table("/", name=objname, description=table_schema)
+        for sample in testsamples:
+            for key, value in sample.items():
+                t.row[key] = value
+            t.row.append()
 
-        yield path, objname, pd.DataFrame(testsamples)
+    yield path, objname, pd.DataFrame(testsamples)
 
 
 class TestReadPyTablesHDF5: