contrib/check-py3-compat.py

match: making visitdir() deal with non-recursive entries

Primarily as an optimization to avoid recursing into directories that will
never have a match inside, this classifies each matcher pattern's root as
recursive or non-recursive (erring on the side of keeping it recursive,
which may lead to wasteful directory or manifest walks that yield no matches).

I measured the performance of "rootfilesin" in two repos:
- The Firefox repo with tree manifests, with
  "hg files -r . -I rootfilesin:browser".
  The browser directory contains about 3K files across 249 subdirectories.
- A specific Google-internal directory which contains 75K files across 19K
  subdirectories, with "hg files -r . -I rootfilesin:REDACTED".

I tested with both cold and warm disk caches. Cold cache was produced by
running "sync; echo 3 > /proc/sys/vm/drop_caches". Warm cache was produced
by re-running the same command a few times.

These were the results:

               Cold cache           Warm cache
             Before   After      Before   After
firefox      0m5.1s   0m2.18s   0m0.22s  0m0.14s
google3 dir  2m3.9s   0m1.57s   0m8.12s  0m0.16s

Certain extensions, notably narrowhg, can depend on this for correctness
(not trying to recurse into directories for which it has no information).

#!/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 os
import sys
import traceback

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."""
    import importlib  # not available on Python 2.6
    with open(f, 'rb') as fh:
        content = fh.read()

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

    # Try to import the module.
    # For now we only support mercurial.* and hgext.* modules because figuring
    # out module paths for things not in a package can be confusing.
    if f.startswith(('hgext/', 'mercurial/')) and not f.endswith('__init__.py'):
        assert f.endswith('.py')
        name = f.replace('/', '.')[:-3].replace('.pure.', '.')
        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:]:
        fn(f)

    sys.exit(0)