contrib/check-py3-compat.py

sidedatacopies: fast path data fetching if revision has no sidedata

When using the side data mode, we know their won't be any copy information
sidedata. Skipping revision restoration give an important speed boost.

In the future, there will be other user of sidedata, reducing the efficiency of
this. We should consider adding a dedicated flag in revlog V2 to preserve this
optimisation. The current situation is good enough for now.

revision: large amount; added files: large amount; rename small amount; c3b14617fbd7 9ba6ab77fd29
before:  ! wall 2.401569 comb 2.400000 user 2.390000 sys 0.010000 (median of 10)
after:   ! wall 1.429294 comb 1.430000 user 1.410000 sys 0.020000 (median of 10)
revision: large amount; added files: small amount; rename small amount; c3b14617fbd7 f650a9b140d2
before:  ! wall 3.519140 comb 3.520000 user 3.470000 sys 0.050000 (median of 10)
after:   ! wall 1.963332 comb 1.960000 user 1.960000 sys 0.000000 (median of 10)
revision: large amount; added files: large amount; rename large amount; 08ea3258278e d9fa043f30c0
before:  ! wall 0.593880 comb 0.600000 user 0.590000 sys 0.010000 (median of 15)
after:   ! wall 0.251679 comb 0.250000 user 0.250000 sys 0.000000 (median of 38)
revision: small amount; added files: large amount; rename large amount; df6f7a526b60 a83dc6a2d56f
before:  ! wall 0.013414 comb 0.020000 user 0.020000 sys 0.000000 (median of 220)
after:   ! wall 0.013222 comb 0.020000 user 0.020000 sys 0.000000 (median of 223)
revision: small amount; added files: large amount; rename small amount; 4aa4e1f8e19a 169138063d63
before:  ! wall 0.002711 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000)
after:   ! wall 0.001631 comb 0.000000 user 0.000000 sys 0.000000 (median of 1000)
revision: small amount; added files: small amount; rename small amount; 4bc173b045a6 964879152e2e
before:  ! wall 0.000077 comb 0.000000 user 0.000000 sys 0.000000 (median of 12208)
after:   ! wall 0.000078 comb 0.000000 user 0.000000 sys 0.000000 (median of 12012)
revision: medium amount; added files: large amount; rename medium amount; c95f1ced15f2 2c68e87c3efe
before:  ! wall 0.410067 comb 0.410000 user 0.410000 sys 0.000000 (median of 23)
after:   ! wall 0.207786 comb 0.200000 user 0.200000 sys 0.000000 (median of 46)
revision: medium amount; added files: medium amount; rename small amount; d343da0c55a8 d7746d32bf9d
before:  ! wall 0.097004 comb 0.090000 user 0.090000 sys 0.000000 (median of 100)
after:   ! wall 0.038495 comb 0.030000 user 0.030000 sys 0.000000 (median of 100)

Differential Revision: https://phab.mercurial-scm.org/D7074

#!/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 |= set(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)