Remove unnecessary function and lots of linting (#132)

* IOError is now OSError in CPython, do not need to inherit from object

* use PEP 585 annotations

* delay annotations to allow TfsCollection hints

* remove trailing whitespaces

* type checking block

* remove trailing whitespaces

* __new__ is classmethod, should have cls as first argument

* no implicit none

* error messages should be defined outside raise statement

* ignore unused args and kwargs in abstractmethod signature

* unnecessary else

* ignore for legitimate reasons, minor formatting

* use PEP 585 annotations

* no pass statement in exception definition

* get Sequence from collections.abc

* remove trailing whitespaces

* use PEP 585 annotations

* mutable class var should be type hinted ClassVar

* Exception must not use a string literal, assign to variable first

* Exception must not use a string literal, assign to variable first

* reraise from previous error

* also reraise from full stacktrace here

* PEP 604 unions and avoid implicit optional

* type checking block

* let ruff know we target python 3.9

* PEP 604 unions

* put annotation-only type in TYPE_CHECKING block

* Use key in dict instead of key in dict.keys()

* remove trailing whitespaces

* Exception must not use a string literal, assign to variable first

* use contextlib to suppress a specific error instead of try-except-pass

* use PEP 585 annotations

* PEP 604 unions and avoid implicit optional

* stop caring about boolean arg

* Exception must not use a string literal, assign to variable first

* reraise from previous error

* use PEP 585 annotations

* stop caring about boolean arg

* PEP 604 unions

* put annotation-only type in TYPE_CHECKING block

* stop caring about boolean arg

* Exception must not use a string literal, assign to variable first

* lets not overwrite the loop variable

* use PEP 585 annotations

* PEP 604 unions and avoid implicit optional

* stop caring about boolean arg

* remove trailing whitespaces

* unnecessary else after return

* no need to restate the raise error name

* remove _autoset_pandas_types as we prohibit pandas <2.1 and the need for this workaround was only for pandas up to 1.3 (excluded) in which they fixed the problem. See the NOTE in the deleted function and the github comment it links to

* Exception must not use a string literal, assign to variable first

* use startswith with a tuple instead of several checks

* use single if statement instead of nested ones

* unnecessary assignment before return

* elifs can be ifs since theyre after return statements

* minimal formatting

* Use key in dict instead of key in dict.keys()

* stop caring about boolean arg

* set match in pytest.raises as it was too broad

* Use key in dict instead of key in dict.keys()

* remove unused caplogs

* set match in pytest.raises as it was too broad

* should assign in access expressions

* asserts should only check one thing

* unused import and orders

* set match in pytest.raises as it was too broad

* Use key in dict instead of key in dict.keys()

* remove unused caplogs

* pandas as pd, numpy as np

* remove unused caplogs

* use dict literal

* oops

* help josch's eyes

* bit more formatting consistency

* no need for these skipifs as the condition no longer applies

* again an unused import

* add in progress to the changelog

* noqa on the correct line again

Author: fsoubelet

CHANGELOG.md

@@ -1,5 +1,10 @@
 # TFS-Pandas Changelog
 
+## IN PROGRESS - 3.9.0
+
+- Fixed:
+  - Removed a workaround function which is no longer necessary due to the higher minimum `pandas` version.
+
 ## Version 3.8.1
 
 - Changed:

doc/conf.py

@@ -1,4 +1,3 @@
-# -*- coding: utf-8 -*-
 #
 # TFS-Pandas documentation build configuration file, created by
 # sphinx-quickstart on Tue Feb  6 12:10:18 2018.
@@ -54,7 +53,7 @@ def about_package(init_posixpath: pathlib.Path) -> dict:
     "sphinx.ext.coverage",  # Collect doc coverage stats
     "sphinx.ext.doctest",  # Test snippets in the documentation
     "sphinx.ext.githubpages",  # Publish HTML docs in GitHub Pages
-    "sphinx.ext.intersphinx",  # Link to other projects’ documentation
+    "sphinx.ext.intersphinx",  # Link to other projects' documentation
     "sphinx.ext.mathjax",  # Render math via JavaScript
     "sphinx.ext.napoleon",  # Support for NumPy and Google style docstrings
     "sphinx.ext.todo",  # Support for todo items
@@ -244,4 +243,4 @@ def about_package(init_posixpath: pathlib.Path) -> dict:
     "matplotlib": ("https://matplotlib.org/stable/", None),
     "scipy": ("https://docs.scipy.org/doc/scipy/", None),
     "cpymad": ("https://hibtc.github.io/cpymad/", None),
-}
+}

pyproject.toml

@@ -86,3 +86,9 @@ homepage = "https://github.com/pylhc/tfs"
 repository = "https://github.com/pylhc/tfs"
 documentation = "https://pylhc.github.io/tfs/ "
 changelog = "https://github.com/pylhc/tfs/blob/master/CHANGELOG.md"
+
+
+[tool.ruff]
+
+# Assume Python 3.9+
+target-version = "py39"

tests/test_collection.py

@@ -1,5 +1,5 @@
-import os
 import pathlib
+
 import pytest
 from pandas.testing import assert_frame_equal
 
@@ -143,8 +143,8 @@ def test_buffer_flush_nowrite(self, _input_dir_str: str, _tfs_x: TfsDataFrame, _
         assert_frame_equal(tfs_y, read_tfs(c.get_path("nofile_y"), index=c.INDEX))
 
         c.allow_write = False
-        with pytest.raises(IOError):
-            c.flush()
+        with pytest.raises(OSError, match="Cannot flush TfsCollection"):
+            c.flush()  # because allow_write is set to False
 
         tfs_x_after_flush = read_tfs(c.get_path("file_x"), index=c.INDEX)
         tfs_y_after_flush = read_tfs(c.get_path("nofile_y"), index=c.INDEX)
@@ -156,7 +156,7 @@ class TestFilenames:
 
     def test_tfscollection_getfilename_not_implemented(self):
         with pytest.raises(NotImplementedError):
-            TfsCollection._get_filename("doesnt matter")
+            TfsCollection._get_filename("doesnt matter")  # noqa: SLF001
 
     def test_get_filename(self, _input_dir_pathlib: pathlib.Path):
         c = CollectionTest(_input_dir_pathlib, allow_write=False)
@@ -186,13 +186,13 @@ def test_filenames(self, _input_dir_pathlib: pathlib.Path):
         assert c.filenames()["file_x"] == "file_x.tfs"
         assert c.filenames()["nofile_y"] == "nofile_y.tfs"
 
-        assert all(f in c.filenames().keys() for f in exist_properties)
-        assert all(f in c.filenames().keys() for f in not_exist_properties)
+        assert all(f in c.filenames() for f in exist_properties)
+        assert all(f in c.filenames() for f in not_exist_properties)
         assert all(f in c.filenames().values() for f in exist_files)
         assert all(f in c.filenames().values() for f in not_exist_files)
 
-        assert all(f in c.filenames(exist=True).keys() for f in exist_properties)
-        assert all(f not in c.filenames(exist=True).keys() for f in not_exist_properties)
+        assert all(f in c.filenames(exist=True) for f in exist_properties)
+        assert all(f not in c.filenames(exist=True) for f in not_exist_properties)
         assert all(f in c.filenames(exist=True).values() for f in exist_files)
         assert all(f not in c.filenames(exist=True).values() for f in not_exist_files)
 
@@ -254,10 +254,10 @@ def _test_fun(df, a, b):
         assert res_file[1] == 13
 
     def test_buffer_clear(self, _dummy_collection):
-        _dummy_collection._buffer["some_key"] = 5
-        assert _dummy_collection._buffer["some_key"]
+        _dummy_collection._buffer["some_key"] = 5  # noqa: SLF001
+        assert _dummy_collection._buffer["some_key"]  # noqa: SLF001
         _dummy_collection.clear()
-        assert not _dummy_collection._buffer
+        assert not _dummy_collection._buffer  # noqa: SLF001
 
     def test_no_attribute(self, _dummy_collection):
         with pytest.raises(AttributeError):
@@ -269,26 +269,26 @@ def _read_tfs(path):
     return read_tfs(path).set_index("NAME", drop=False)
 
 
-@pytest.fixture()
+@pytest.fixture
 def _tfs_x() -> TfsDataFrame:
     return _read_tfs(INPUT_DIR / "file_x.tfs")
 
 
-@pytest.fixture()
+@pytest.fixture
 def _tfs_y() -> TfsDataFrame:
     return _read_tfs(INPUT_DIR / "file_y.tfs")
 
 
-@pytest.fixture()
+@pytest.fixture
 def _input_dir_pathlib() -> pathlib.Path:
     return INPUT_DIR
 
 
-@pytest.fixture()
+@pytest.fixture
 def _input_dir_str() -> str:
     return str(INPUT_DIR)
 
 
-@pytest.fixture()
+@pytest.fixture
 def _dummy_collection() -> TfsCollection:
     return TfsCollection("")

tests/test_compression.py

@@ -2,7 +2,6 @@
 Here we only test that reading and writing with compression keeps the data intact.
 """
 import pathlib
-import sys
 
 import pytest
 from pandas._testing import assert_dict_equal
@@ -14,11 +13,6 @@
 CURRENT_DIR = pathlib.Path(__file__).parent
 
 
-# TODO: remove the skipif once Python 3.7 is EoL and we drop support for it
-@pytest.mark.skipif(
-    sys.version_info < (3, 8),
-    reason="Not run on Python 3.7 for format protocol incompatibility reasons",
-)
 @pytest.mark.parametrize("extension", ["gz", "bz2", "zip", "xz", "zst", "tar", "tar.gz"])
 def test_read_compressed_is_same_data(_tfs_filex, _tfs_compressed_filex_no_suffix, extension):
     """Compare the data from a compressed file with the original one."""
@@ -33,11 +27,6 @@ def test_read_compressed_is_same_data(_tfs_filex, _tfs_compressed_filex_no_suffi
     assert_frame_equal(ref_df, test_df)
 
 
-# TODO: remove the skipif once Python 3.7 is EoL and we drop support for it
-@pytest.mark.skipif(
-    sys.version_info < (3, 8),
-    reason="Not run on Python 3.7 for format protocol incompatibility reasons",
-)
 @pytest.mark.parametrize("extension", ["gz", "bz2", "zip", "xz", "zst", "tar", "tar.gz"])
 def test_write_read_compressed(_tfs_filey, tmp_path, extension):
     """Ensure that writing in compressed format preserves data."""
@@ -57,11 +46,6 @@ def test_write_read_compressed(_tfs_filey, tmp_path, extension):
     assert_frame_equal(ref_df, test_df)
 
 
-# TODO: remove the skipif once Python 3.7 is EoL and we drop support for it
-@pytest.mark.skipif(
-    sys.version_info < (3, 8),
-    reason="Not run on Python 3.7 for format protocol incompatibility reasons",
-)
 @pytest.mark.parametrize("extension", ["gz", "bz2", "zip", "xz", "zst", "tar", "tar.gz"])
 def test_read_headers_compressed(_tfs_compressed_filex_no_suffix, extension):
     compressed_file = _path_with_added_extension(_tfs_compressed_filex_no_suffix, extension)
@@ -70,7 +54,7 @@ def test_read_headers_compressed(_tfs_compressed_filex_no_suffix, extension):
     assert len(headers) > 0
     assert len(str(headers)) > 0
     assert all(
-        key in headers.keys()
+        key in headers
         for key in ["TITLE", "DPP", "Q1", "Q1RMS", "NATQ1", "NATQ1RMS", "BPMCOUNT"]
     )
 
@@ -86,23 +70,23 @@ def _path_with_added_extension(path: pathlib.Path, extension: str) -> pathlib.Pa
 # ------ Fixtures ------ #
 
 
-@pytest.fixture()
+@pytest.fixture
 def _tfs_filex() -> pathlib.Path:
     return CURRENT_DIR / "inputs" / "file_x.tfs"
 
 
-@pytest.fixture()
+@pytest.fixture
 def _tfs_filey() -> pathlib.Path:
     return CURRENT_DIR / "inputs" / "file_y.tfs"
 
 
-@pytest.fixture()
+@pytest.fixture
 def _tfs_compressed_filex_no_suffix() -> pathlib.Path:
     """Add the wanted compression suffix to this."""
     return CURRENT_DIR / "inputs" / "compressed" / "file_x.tfs"
 
 
-@pytest.fixture()
+@pytest.fixture
 def _tfs_compressed_filey_no_suffix() -> pathlib.Path:
     """Add the wanted compression suffix to this."""
     return CURRENT_DIR / "inputs" / "compressed" / "file_y.tfs"

tests/test_frame.py

@@ -14,29 +14,29 @@
 
 
 class TestFailures:
-    def test_validate_raises_on_wrong_unique_behavior(self, caplog):
+    def test_validate_raises_on_wrong_unique_behavior(self):
         df = TfsDataFrame(index=["A", "B", "A"], columns=["A", "B", "A"])
         with pytest.raises(KeyError):
             validate(df, "", non_unique_behavior="invalid")
 
     @pytest.mark.parametrize("how", ["invalid", "not_left", "not_right"])
-    def test_merge_headers_raises_on_invalid_how_key(self, caplog, how):
+    def test_merge_headers_raises_on_invalid_how_key(self, how):
         headers_left = OrderedDict()
         headers_right = OrderedDict()
 
-        with pytest.raises(ValueError):
+        with pytest.raises(ValueError, match="Invalid 'how' argument"):
             merge_headers(headers_left, headers_right, how=how)
 
     def test_access_errors(self):
         df = TfsDataFrame(index=["A", "B", "A"], columns=["A", "B", "A"], headers={"HEADER": 10})
         with pytest.raises(AttributeError):
-            df.does_not_exist
+            _ = df.does_not_exist
 
         with pytest.raises(KeyError):
-            df["does also not exist"]
+            _ = df["does also not exist"]
 
         with pytest.raises(KeyError):  # raises KeyError in pandas, TypeError in dict
-            df[[1, 2, 3]]
+            _ = df[[1, 2, 3]]
 
 
 class TestTfsDataFrameMerging:
@@ -79,7 +79,8 @@ def test_headers_merging_left(self, _tfs_file_x_pathlib, _tfs_file_y_pathlib, ho
         result = merge_headers(headers_left, headers_right, how=how)
 
         assert isinstance(result, OrderedDict)
-        assert len(result) >= len(headers_left) and len(result) >= len(headers_right)  # no key disappeared
+        assert len(result) >= len(headers_left)  # no key disappeared
+        assert len(result) >= len(headers_right)  # no key disappeared
         for key in result:  # check that we prioritized headers_left's contents
             if key in headers_left and key in headers_right:
                 assert result[key] == headers_left[key]
@@ -91,7 +92,8 @@ def test_headers_merging_right(self, _tfs_file_x_pathlib, _tfs_file_y_pathlib, h
         result = merge_headers(headers_left, headers_right, how=how)
 
         assert isinstance(result, OrderedDict)
-        assert len(result) >= len(headers_left) and len(result) >= len(headers_right)  # no key disappeared
+        assert len(result) >= len(headers_left)  # no key disappeared
+        assert len(result) >= len(headers_right)  # no key disappeared
         for key in result:  # check that we prioritized headers_right's contents
             if key in headers_left and key in headers_right:
                 assert result[key] == headers_right[key]
@@ -132,7 +134,7 @@ def test_long_headers_print(self):
         assert "Headers" in print_out
 
         # Check that the ellipsis worked
-        assert not all(key in print_out for key in headers.keys())
+        assert not all(key in print_out for key in headers)
         assert not all(str(val) in print_out for val in headers.values())
         assert "..." in print_out
 
@@ -185,11 +187,11 @@ def test_concatenating_accepts_pandas_dataframes(
 # ------ Fixtures ------ #
 
 
-@pytest.fixture()
+@pytest.fixture
 def _tfs_file_x_pathlib() -> pathlib.Path:
     return CURRENT_DIR / "inputs" / "file_x.tfs"
 
 
-@pytest.fixture()
+@pytest.fixture
 def _tfs_file_y_pathlib() -> pathlib.Path:
     return CURRENT_DIR / "inputs" / "file_x.tfs"

tests/test_hdf.py

@@ -1,12 +1,12 @@
-import sys
 
-import numpy as np
-import pytest
 from pathlib import Path
 
-from tfs import TfsDataFrame, write_hdf, read_hdf
-from pandas.testing import assert_frame_equal
+import numpy as np
+import pytest
 from pandas._testing import assert_dict_equal
+from pandas.testing import assert_frame_equal
+
+from tfs import TfsDataFrame, read_hdf, write_hdf
 
 
 class TestHDF: