DOC: Move code_style.rst docs to other sections & a check (#46724)

Author: mroeschke

.pre-commit-config.yaml

@@ -176,6 +176,13 @@ repos:
         files: ^pandas/core/
         exclude: ^pandas/core/api\.py$
         types: [python]
+    -   id: use-io-common-urlopen
+        name: Use pandas.io.common.urlopen instead of urllib.request.urlopen
+        language: python
+        entry: python scripts/use_io_common_urlopen.py
+        files: ^pandas/
+        exclude: ^pandas/tests/
+        types: [python]
     -   id: no-bool-in-core-generic
         name: Use bool_t instead of bool in pandas/core/generic.py
         entry: python scripts/no_bool_in_generic.py

doc/source/development/code_style.rst

@@ -37,15 +37,14 @@ In addition to ``./ci/code_checks.sh``, some extra checks are run by
 ``pre-commit`` - see :ref:`here <contributing.pre-commit>` for how to
 run them.
 
-Additional standards are outlined on the :ref:`pandas code style guide <code_style>`.
-
 .. _contributing.pre-commit:
 
 Pre-commit
 ----------
 
 Additionally, :ref:`Continuous Integration <contributing.ci>` will run code formatting checks
-like ``black``, ``flake8``, ``isort``, and ``cpplint`` and more using `pre-commit hooks <https://pre-commit.com/>`_
+like ``black``, ``flake8`` (including a `pandas-dev-flaker <https://github.com/pandas-dev/pandas-dev-flaker>`_ plugin),
+``isort``, and ``cpplint`` and more using `pre-commit hooks <https://pre-commit.com/>`_
 Any warnings from these checks will cause the :ref:`Continuous Integration <contributing.ci>` to fail; therefore,
 it is helpful to run the check yourself before submitting code. This
 can be done by installing ``pre-commit``::

doc/source/development/contributing_codebase.rst

@@ -16,7 +16,6 @@ Development
     contributing_environment
     contributing_documentation
     contributing_codebase
-    code_style
     maintaining
     internals
     test_writing

doc/source/development/index.rst

@@ -0,0 +1,23 @@
+import pytest
+
+from scripts.use_io_common_urlopen import use_io_common_urlopen
+
+PATH = "t.py"
+
+
+def test_inconsistent_usage(capsys):
+    content = "from urllib.request import urlopen"
+    result_msg = (
+        "t.py:1:0: Don't use urllib.request.urlopen, "
+        "use pandas.io.common.urlopen instead\n"
+    )
+    with pytest.raises(SystemExit, match=None):
+        use_io_common_urlopen(content, PATH)
+    expected_msg, _ = capsys.readouterr()
+    assert result_msg == expected_msg
+
+
+def test_consistent_usage():
+    # should not raise
+    content = "from pandas.io.common import urlopen"
+    use_io_common_urlopen(content, PATH)

scripts/tests/test_use_io_common_urlopen.py

@@ -0,0 +1,63 @@
+"""
+Check that pandas/core imports pandas.array as pd_array.
+
+This makes it easier to grep for usage of pandas array.
+
+This is meant to be run as a pre-commit hook - to run it manually, you can do:
+
+    pre-commit run use-io-common-urlopen --all-files
+
+"""
+
+from __future__ import annotations
+
+import argparse
+import ast
+import sys
+from typing import Sequence
+
+ERROR_MESSAGE = (
+    "{path}:{lineno}:{col_offset}: "
+    "Don't use urllib.request.urlopen, use pandas.io.common.urlopen instead\n"
+)
+
+
+class Visitor(ast.NodeVisitor):
+    def __init__(self, path: str) -> None:
+        self.path = path
+
+    def visit_ImportFrom(self, node: ast.ImportFrom) -> None:
+        # Check that pandas.io.common.urlopen is used instead of
+        # urllib.request.urlopen
+        if (
+            node.module is not None
+            and node.module.startswith("urllib.request")
+            and any(i.name == "urlopen" for i in node.names)
+        ):
+            msg = ERROR_MESSAGE.format(
+                path=self.path, lineno=node.lineno, col_offset=node.col_offset
+            )
+            sys.stdout.write(msg)
+            sys.exit(1)
+        super().generic_visit(node)
+
+
+def use_io_common_urlopen(content: str, path: str) -> None:
+    tree = ast.parse(content)
+    visitor = Visitor(path)
+    visitor.visit(tree)
+
+
+def main(argv: Sequence[str] | None = None) -> None:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("paths", nargs="*")
+    args = parser.parse_args(argv)
+
+    for path in args.paths:
+        with open(path, encoding="utf-8") as fd:
+            content = fd.read()
+        use_io_common_urlopen(content, path)
+
+
+if __name__ == "__main__":
+    main()