view contrib/check-py3-compat.py @ 44593:496868f1030c

rust-matchers: use the `regex` crate

Instead of falling back to Python when a code path with "ignore" functionality
is reached and `Re2` is not installed, the default compilation (i.e. without
the `with-re2` feature) will use the `regex` crate for all regular expressions
business.

As with the introduction of `Re2` in a previous series, this yields a big
performance boost compared to the Python + C code in `status`, `diff`, `commit`,
`update`, and maybe others.

For now `Re2` looks to be faster at compiling the DFA (1.5ms vs 5ms for
Netbeans' `.hgignore`) and a bit faster in actual use: (123ms vs 137ms for
the parallel traversal of Netbeans' clean repo). I am in talks with the author
of `regex` to see whether that performance difference is a bug, a "won't fix",
or a tuning issue.

The `regex` crate is already one of our dependencies and using this code does
not require any additional work from the end-user than to use the Rust
extensions.

Differential Revision: https://phab.mercurial-scm.org/D8323

#!/usr/bin/env python
#
# check-py3-compat - check Python 3 compatibility of Mercurial files
#
# Copyright 2015 Gregory Szorc <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from __future__ import absolute_import, print_function

import ast
import importlib
import os
import sys
import traceback
import warnings


def check_compat_py2(f):
    """Check Python 3 compatibility for a file with Python 2"""
    with open(f, 'rb') as fh:
        content = fh.read()
    root = ast.parse(content)

    # Ignore empty files.
    if not root.body:
        return

    futures = set()
    haveprint = False
    for node in ast.walk(root):
        if isinstance(node, ast.ImportFrom):
            if node.module == '__future__':
                futures |= {n.name for n in node.names}
        elif isinstance(node, ast.Print):
            haveprint = True

    if 'absolute_import' not in futures:
        print('%s not using absolute_import' % f)
    if haveprint and 'print_function' not in futures:
        print('%s requires print_function' % f)


def check_compat_py3(f):
    """Check Python 3 compatibility of a file with Python 3."""
    with open(f, 'rb') as fh:
        content = fh.read()

    try:
        ast.parse(content, filename=f)
    except SyntaxError as e:
        print('%s: invalid syntax: %s' % (f, e))
        return

    # Try to import the module.
    # For now we only support modules in packages because figuring out module
    # paths for things not in a package can be confusing.
    if f.startswith(
        ('hgdemandimport/', 'hgext/', 'mercurial/')
    ) and not f.endswith('__init__.py'):
        assert f.endswith('.py')
        name = f.replace('/', '.')[:-3]
        try:
            importlib.import_module(name)
        except Exception as e:
            exc_type, exc_value, tb = sys.exc_info()
            # We walk the stack and ignore frames from our custom importer,
            # import mechanisms, and stdlib modules. This kinda/sorta
            # emulates CPython behavior in import.c while also attempting
            # to pin blame on a Mercurial file.
            for frame in reversed(traceback.extract_tb(tb)):
                if frame.name == '_call_with_frames_removed':
                    continue
                if 'importlib' in frame.filename:
                    continue
                if 'mercurial/__init__.py' in frame.filename:
                    continue
                if frame.filename.startswith(sys.prefix):
                    continue
                break

            if frame.filename:
                filename = os.path.basename(frame.filename)
                print(
                    '%s: error importing: <%s> %s (error at %s:%d)'
                    % (f, type(e).__name__, e, filename, frame.lineno)
                )
            else:
                print(
                    '%s: error importing module: <%s> %s (line %d)'
                    % (f, type(e).__name__, e, frame.lineno)
                )


if __name__ == '__main__':
    if sys.version_info[0] == 2:
        fn = check_compat_py2
    else:
        fn = check_compat_py3

    for f in sys.argv[1:]:
        with warnings.catch_warnings(record=True) as warns:
            fn(f)

        for w in warns:
            print(
                warnings.formatwarning(
                    w.message, w.category, w.filename, w.lineno
                ).rstrip()
            )

    sys.exit(0)