Remove support for py.path objects in IO readers (pandas-dev#57091)

mroeschke · pmhatre1 · commit 5af42bc32076 · 2024-05-06T23:12:55.000-07:00
* CLN: Remove testing for py.path objects

* Add whatsnew

* Missed annotation

* Add whatsnew
diff --git a/doc/source/conf.py b/doc/source/conf.py
@@ -460,7 +460,6 @@
         "dateutil": ("https://dateutil.readthedocs.io/en/latest/", None),
         "matplotlib": ("https://matplotlib.org/stable/", None),
         "numpy": ("https://numpy.org/doc/stable/", None),
-        "py": ("https://pylib.readthedocs.io/en/latest/", None),
         "python": ("https://docs.python.org/3/", None),
         "scipy": ("https://docs.scipy.org/doc/scipy/", None),
         "pyarrow": ("https://arrow.apache.org/docs/", None),
diff --git a/doc/source/user_guide/io.rst b/doc/source/user_guide/io.rst
@@ -61,8 +61,8 @@ Basic
 +++++
 
 filepath_or_buffer : various
-  Either a path to a file (a :class:`python:str`, :class:`python:pathlib.Path`,
-  or :class:`py:py._path.local.LocalPath`), URL (including http, ftp, and S3
+  Either a path to a file (a :class:`python:str`, :class:`python:pathlib.Path`)
+  URL (including http, ftp, and S3
   locations), or any object with a ``read()`` method (such as an open file or
   :class:`~python:io.StringIO`).
 sep : str, defaults to ``','`` for :func:`read_csv`, ``\t`` for :func:`read_table`
diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst
@@ -84,7 +84,7 @@ See :ref:`install.dependencies` and :ref:`install.optional_dependencies` for mor
 
 Other API changes
 ^^^^^^^^^^^^^^^^^
--
+- 3rd party ``py.path`` objects are no longer explicitly supported in IO methods. Use :py:class:`pathlib.Path` objects instead (:issue:`57091`)
 -
 
 .. ---------------------------------------------------------------------------
diff --git a/pandas/_testing/__init__.py b/pandas/_testing/__init__.py
@@ -34,7 +34,6 @@
     Series,
 )
 from pandas._testing._io import (
-    round_trip_localpath,
     round_trip_pathlib,
     round_trip_pickle,
     write_to_compressed,
@@ -609,7 +608,6 @@ def shares_memory(left, right) -> bool:
     "OBJECT_DTYPES",
     "raise_assert_detail",
     "raises_chained_assignment_error",
-    "round_trip_localpath",
     "round_trip_pathlib",
     "round_trip_pickle",
     "setitem",
diff --git a/pandas/_testing/_io.py b/pandas/_testing/_io.py
@@ -89,35 +89,6 @@ def round_trip_pathlib(writer, reader, path: str | None = None):
     return obj
 
 
-def round_trip_localpath(writer, reader, path: str | None = None):
-    """
-    Write an object to file specified by a py.path LocalPath and read it back.
-
-    Parameters
-    ----------
-    writer : callable bound to pandas object
-        IO writing function (e.g. DataFrame.to_csv )
-    reader : callable
-        IO reading function (e.g. pd.read_csv )
-    path : str, default None
-        The path where the object is written and then read.
-
-    Returns
-    -------
-    pandas object
-        The original object that was serialized and then re-read.
-    """
-    import pytest
-
-    LocalPath = pytest.importorskip("py.path").local
-    if path is None:
-        path = "___localpath___"
-    with ensure_clean(path) as path:
-        writer(LocalPath(path))
-        obj = reader(LocalPath(path))
-    return obj
-
-
 def write_to_compressed(compression, path, data, dest: str = "test") -> None:
     """
     Write data to a compressed file.
diff --git a/pandas/io/common.py b/pandas/io/common.py
@@ -318,7 +318,7 @@ def _get_filepath_or_buffer(
 
     Parameters
     ----------
-    filepath_or_buffer : a url, filepath (str, py.path.local or pathlib.Path),
+    filepath_or_buffer : a url, filepath (str or pathlib.Path),
                          or buffer
     {compression_options}
 
diff --git a/pandas/io/excel/_base.py b/pandas/io/excel/_base.py
@@ -1441,7 +1441,7 @@ class ExcelFile:
 
     Parameters
     ----------
-    path_or_buffer : str, bytes, path object (pathlib.Path or py._path.local.LocalPath),
+    path_or_buffer : str, bytes, pathlib.Path,
         A file-like object, xlrd workbook or openpyxl workbook.
         If a string or path object, expected to be a path to a
         .xls, .xlsx, .xlsb, .xlsm, .odf, .ods, or .odt file.
diff --git a/pandas/io/stata.py b/pandas/io/stata.py
@@ -216,7 +216,7 @@
 Parameters
 ----------
 path_or_buf : path (string), buffer or path object
-    string, path object (pathlib.Path or py._path.local.LocalPath) or object
+    string, pathlib.Path or object
     implementing a binary read() functions.
 {_statafile_processing_params1}
 {_statafile_processing_params2}
@@ -2258,7 +2258,7 @@ class StataWriter(StataParser):
     Parameters
     ----------
     fname : path (string), buffer or path object
-        string, path object (pathlib.Path or py._path.local.LocalPath) or
+        string, pathlib.Path or
         object implementing a binary write() functions. If using a buffer
         then the buffer will not be automatically closed after the file
         is written.
@@ -3208,7 +3208,7 @@ class StataWriter117(StataWriter):
     Parameters
     ----------
     fname : path (string), buffer or path object
-        string, path object (pathlib.Path or py._path.local.LocalPath) or
+        string, pathlib.Path or
         object implementing a binary write() functions. If using a buffer
         then the buffer will not be automatically closed after the file
         is written.
@@ -3594,7 +3594,7 @@ class StataWriterUTF8(StataWriter117):
     Parameters
     ----------
     fname : path (string), buffer or path object
-        string, path object (pathlib.Path or py._path.local.LocalPath) or
+        string, pathlib.Path or
         object implementing a binary write() functions. If using a buffer
         then the buffer will not be automatically closed after the file
         is written.
diff --git a/pandas/tests/io/excel/test_readers.py b/pandas/tests/io/excel/test_readers.py
@@ -966,19 +966,6 @@ def test_read_from_pathlib_path(self, read_ext):
 
         tm.assert_frame_equal(expected, actual)
 
-    @td.skip_if_no("py.path")
-    def test_read_from_py_localpath(self, read_ext):
-        # GH12655
-        from py.path import local as LocalPath
-
-        str_path = os.path.join("test1" + read_ext)
-        expected = pd.read_excel(str_path, sheet_name="Sheet1", index_col=0)
-
-        path_obj = LocalPath().join("test1" + read_ext)
-        actual = pd.read_excel(path_obj, sheet_name="Sheet1", index_col=0)
-
-        tm.assert_frame_equal(expected, actual)
-
     def test_close_from_py_localpath(self, read_ext):
         # GH31467
         str_path = os.path.join("test1" + read_ext)
diff --git a/pandas/tests/io/excel/test_writers.py b/pandas/tests/io/excel/test_writers.py
@@ -1319,18 +1319,6 @@ def test_path_path_lib(self, engine, ext):
         result = tm.round_trip_pathlib(writer, reader, path=f"foo{ext}")
         tm.assert_frame_equal(result, df)
 
-    def test_path_local_path(self, engine, ext):
-        df = DataFrame(
-            1.1 * np.arange(120).reshape((30, 4)),
-            columns=Index(list("ABCD")),
-            index=Index([f"i-{i}" for i in range(30)]),
-        )
-        writer = partial(df.to_excel, engine=engine)
-
-        reader = partial(pd.read_excel, index_col=0)
-        result = tm.round_trip_localpath(writer, reader, path=f"foo{ext}")
-        tm.assert_frame_equal(result, df)
-
     def test_merged_cell_custom_objects(self, path):
         # see GH-27006
         mi = MultiIndex.from_tuples(
diff --git a/pandas/tests/io/parser/common/test_file_buffer_url.py b/pandas/tests/io/parser/common/test_file_buffer_url.py
@@ -79,20 +79,6 @@ def test_path_path_lib(all_parsers):
     tm.assert_frame_equal(df, result)
 
 
-@xfail_pyarrow  # AssertionError: DataFrame.index are different
-def test_path_local_path(all_parsers):
-    parser = all_parsers
-    df = DataFrame(
-        1.1 * np.arange(120).reshape((30, 4)),
-        columns=Index(list("ABCD"), dtype=object),
-        index=Index([f"i-{i}" for i in range(30)], dtype=object),
-    )
-    result = tm.round_trip_localpath(
-        df.to_csv, lambda p: parser.read_csv(p, index_col=0)
-    )
-    tm.assert_frame_equal(df, result)
-
-
 def test_nonexistent_path(all_parsers):
     # gh-2428: pls no segfault
     # gh-14086: raise more helpful FileNotFoundError
diff --git a/pandas/tests/io/pytables/test_read.py b/pandas/tests/io/pytables/test_read.py
@@ -22,7 +22,6 @@
     _maybe_remove,
     ensure_clean_store,
 )
-from pandas.util import _test_decorators as td
 
 from pandas.io.pytables import TableIterator
 
@@ -337,25 +336,6 @@ def test_read_from_pathlib_path(tmp_path, setup_path):
     tm.assert_frame_equal(expected, actual)
 
 
-@td.skip_if_no("py.path")
-def test_read_from_py_localpath(tmp_path, setup_path):
-    # GH11773
-    from py.path import local as LocalPath
-
-    expected = DataFrame(
-        np.random.default_rng(2).random((4, 5)),
-        index=list("abcd"),
-        columns=list("ABCDE"),
-    )
-    filename = tmp_path / setup_path
-    path_obj = LocalPath(filename)
-
-    expected.to_hdf(path_obj, key="df", mode="a")
-    actual = read_hdf(path_obj, key="df")
-
-    tm.assert_frame_equal(expected, actual)
-
-
 @pytest.mark.parametrize("format", ["fixed", "table"])
 def test_read_hdf_series_mode_r(tmp_path, format, setup_path):
     # GH 16583
diff --git a/pandas/tests/io/pytables/test_store.py b/pandas/tests/io/pytables/test_store.py
@@ -958,25 +958,6 @@ def test_pickle_path_localpath():
     tm.assert_frame_equal(df, result)
 
 
-def test_path_localpath_hdfstore():
-    df = DataFrame(
-        1.1 * np.arange(120).reshape((30, 4)),
-        columns=Index(list("ABCD"), dtype=object),
-        index=Index([f"i-{i}" for i in range(30)], dtype=object),
-    )
-
-    def writer(path):
-        with HDFStore(path) as store:
-            df.to_hdf(store, key="df")
-
-    def reader(path):
-        with HDFStore(path) as store:
-            return read_hdf(store, "df")
-
-    result = tm.round_trip_localpath(writer, reader)
-    tm.assert_frame_equal(df, result)
-
-
 @pytest.mark.parametrize("propindexes", [True, False])
 def test_copy(propindexes):
     df = DataFrame(
diff --git a/pandas/tests/io/sas/test_sas7bdat.py b/pandas/tests/io/sas/test_sas7bdat.py
@@ -9,7 +9,6 @@
 
 from pandas.compat import IS64
 from pandas.errors import EmptyDataError
-import pandas.util._test_decorators as td
 
 import pandas as pd
 import pandas._testing as tm
@@ -82,17 +81,6 @@ def test_path_pathlib(self, dirpath, data_test_ix):
             df = pd.read_sas(fname, encoding="utf-8")
             tm.assert_frame_equal(df, expected)
 
-    @td.skip_if_no("py.path")
-    @pytest.mark.slow
-    def test_path_localpath(self, dirpath, data_test_ix):
-        from py.path import local as LocalPath
-
-        expected, test_ix = data_test_ix
-        for k in test_ix:
-            fname = LocalPath(os.path.join(dirpath, f"test{k}.sas7bdat"))
-            df = pd.read_sas(fname, encoding="utf-8")
-            tm.assert_frame_equal(df, expected)
-
     @pytest.mark.slow
     @pytest.mark.parametrize("chunksize", (3, 5, 10, 11))
     @pytest.mark.parametrize("k", range(1, 17))
diff --git a/pandas/tests/io/test_common.py b/pandas/tests/io/test_common.py
@@ -19,7 +19,6 @@
 import pytest
 
 from pandas.compat import is_platform_windows
-import pandas.util._test_decorators as td
 
 import pandas as pd
 import pandas._testing as tm
@@ -41,16 +40,6 @@ def __fspath__(self):
         return self.path
 
 
-# Functions that consume a string path and return a string or path-like object
-path_types = [str, CustomFSPath, Path]
-
-try:
-    from py.path import local as LocalPath
-
-    path_types.append(LocalPath)
-except ImportError:
-    pass
-
 HERE = os.path.abspath(os.path.dirname(__file__))
 
 
@@ -86,13 +75,6 @@ def test_stringify_path_pathlib(self):
         redundant_path = icom.stringify_path(Path("foo//bar"))
         assert redundant_path == os.path.join("foo", "bar")
 
-    @td.skip_if_no("py.path")
-    def test_stringify_path_localpath(self):
-        path = os.path.join("foo", "bar")
-        abs_path = os.path.abspath(path)
-        lpath = LocalPath(path)
-        assert icom.stringify_path(lpath) == abs_path
-
     def test_stringify_path_fspath(self):
         p = CustomFSPath("foo/bar.csv")
         result = icom.stringify_path(p)
@@ -105,7 +87,7 @@ def test_stringify_file_and_path_like(self):
             with fsspec.open(f"file://{path}", mode="wb") as fsspec_obj:
                 assert fsspec_obj == icom.stringify_path(fsspec_obj)
 
-    @pytest.mark.parametrize("path_type", path_types)
+    @pytest.mark.parametrize("path_type", [str, CustomFSPath, Path])
     def test_infer_compression_from_path(self, compression_format, path_type):
         extension, expected = compression_format
         path = path_type("foo/bar.csv" + extension)
@@ -114,7 +96,6 @@ def test_infer_compression_from_path(self, compression_format, path_type):
 
     @pytest.mark.parametrize("path_type", [str, CustomFSPath, Path])
     def test_get_handle_with_path(self, path_type):
-        # ignore LocalPath: it creates strange paths: /absolute/~/sometest
         with tempfile.TemporaryDirectory(dir=Path.home()) as tmp:
             filename = path_type("~/" + Path(tmp).name + "/sometest")
             with icom.get_handle(filename, "w") as handles:
diff --git a/pandas/tests/io/test_feather.py b/pandas/tests/io/test_feather.py
@@ -140,15 +140,6 @@ def test_path_pathlib(self):
         result = tm.round_trip_pathlib(df.to_feather, read_feather)
         tm.assert_frame_equal(df, result)
 
-    def test_path_localpath(self):
-        df = pd.DataFrame(
-            1.1 * np.arange(120).reshape((30, 4)),
-            columns=pd.Index(list("ABCD"), dtype=object),
-            index=pd.Index([f"i-{i}" for i in range(30)], dtype=object),
-        ).reset_index()
-        result = tm.round_trip_localpath(df.to_feather, read_feather)
-        tm.assert_frame_equal(df, result)
-
     def test_passthrough_keywords(self):
         df = pd.DataFrame(
             1.1 * np.arange(120).reshape((30, 4)),
diff --git a/pandas/tests/io/test_pickle.py b/pandas/tests/io/test_pickle.py
@@ -229,16 +229,6 @@ def test_pickle_path_pathlib():
     tm.assert_frame_equal(df, result)
 
 
-def test_pickle_path_localpath():
-    df = DataFrame(
-        1.1 * np.arange(120).reshape((30, 4)),
-        columns=Index(list("ABCD"), dtype=object),
-        index=Index([f"i-{i}" for i in range(30)], dtype=object),
-    )
-    result = tm.round_trip_localpath(df.to_pickle, pd.read_pickle)
-    tm.assert_frame_equal(df, result)
-
-
 # ---------------------
 # test pickle compression
 # ---------------------
diff --git a/pandas/tests/io/test_stata.py b/pandas/tests/io/test_stata.py
@@ -1546,17 +1546,6 @@ def test_path_pathlib(self):
         result = tm.round_trip_pathlib(df.to_stata, reader)
         tm.assert_frame_equal(df, result)
 
-    def test_pickle_path_localpath(self):
-        df = DataFrame(
-            1.1 * np.arange(120).reshape((30, 4)),
-            columns=pd.Index(list("ABCD"), dtype=object),
-            index=pd.Index([f"i-{i}" for i in range(30)], dtype=object),
-        )
-        df.index.name = "index"
-        reader = lambda x: read_stata(x).set_index("index")
-        result = tm.round_trip_localpath(df.to_stata, reader)
-        tm.assert_frame_equal(df, result)
-
     @pytest.mark.parametrize("write_index", [True, False])
     def test_value_labels_iterator(self, write_index):
         # GH 16923

Original file line number	Diff line number	Diff line change
@@ -84,7 +84,7 @@ See :ref:`install.dependencies` and :ref:`install.optional_dependencies` for mor
`84`	`84`
`85`	`85`	`Other API changes`
`86`	`86`	`^^^^^^^^^^^^^^^^^`
`87`		`--`
	`87`	+- 3rd party ``py.path`` objects are no longer explicitly supported in IO methods. Use :py:class:`pathlib.Path` objects instead (:issue:`57091`)
`88`	`88`	`-`
`89`	`89`
`90`	`90`	`.. ---------------------------------------------------------------------------`