contrib/check-py3-compat.py

hgweb: parse WSGI request into a data structure

Currently, our WSGI applications (hgweb_mod and hgwebdir_mod) process
the raw WSGI request instance themselves. This means they have to
talk in terms of system strings. And they need to know details
about what's in the WSGI request. And in the case of hgweb_mod, it
is doing some very funky things with URL parsing to impact
dispatching. The code is difficult to read and maintain.

This commit introduces parsing of the WSGI request into a higher-level
and easier-to-reason-about data structure.

To prove it works, we hook it up to hgweb_mod and use it for populating
the relative URL on the request instance.

We hold off on using it in more places because the logic in hgweb_mod
is crazy and I don't want to involve those changes with review of
the parsing code.

The URL construction code has variations that use the HTTP: Host header
(the canonical WSGI way of reconstructing the URL) and with the use
of SERVER_NAME. We need to differentiate because hgweb is currently
using SERVER_NAME for URL construction.

Differential Revision: https://phab.mercurial-scm.org/D2734

#!/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

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)
    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:]:
        fn(f)

    sys.exit(0)