view mercurial/rcutil.py @ 42919:6ccf539aec71

hgweb: fix websub regex flag syntax on Python 3

The `websub` config section for hgweb is broken under Python 3
when using regex flags syntax (ie the optional `i` in the example
from `hg help config.websub`:

    patternname = s/SEARCH_REGEX/REPLACE_EXPRESSION/[i]

Flags are pulled out of the specified byte-string using a regular
expression, and uppercased. The flags are then iterated over and
passed to the `re` module using `re.__dict__[item]`, to get the
object attribute of the same name from the `re` module. So on Python
2 if the `il` flags are passed, this transition looks like:

    `'il'` -> `'IL'` -> `'I'` -> `re.__dict__['I']` -> `re.I`

However on Python 3, these are bytes objects. When we iterate over
a bytes object in Python 3, instead of getting the individual characters
in the string as string objects of length one, we get the integer \
value corresponding to that byte. So the same transition looks like:

    `b'il'` -> `b'IL'` -> `73` -> `re.__dict__[73]` -> `KeyError`

This commit fixes the type mismatch by converting the bytes to a
system string before iterating over each element to pass to `re`.
The transition will now look like:

    `b'il'` -> `u'IL'` -> `u'I'` -> `re.__dict__[u'I']` -> `re.I`

In addition we expand `test-websub.t` to cover the regex flag case
(for both the `websub` section and `interhg`).

Differential Revision: https://phab.mercurial-scm.org/D6788

# rcutil.py - utilities about config paths, special config sections etc.
#
#  Copyright Mercurial Contributors
#
# 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

import os

from . import (
    encoding,
    pycompat,
    util,
)

if pycompat.iswindows:
    from . import scmwindows as scmplatform
else:
    from . import scmposix as scmplatform

fallbackpager = scmplatform.fallbackpager
systemrcpath = scmplatform.systemrcpath
userrcpath = scmplatform.userrcpath

def _expandrcpath(path):
    '''path could be a file or a directory. return a list of file paths'''
    p = util.expandpath(path)
    if os.path.isdir(p):
        join = os.path.join
        return sorted(join(p, f) for f, k in util.listdir(p)
                      if f.endswith('.rc'))
    return [p]

def envrcitems(env=None):
    '''Return [(section, name, value, source)] config items.

    The config items are extracted from environment variables specified by env,
    used to override systemrc, but not userrc.

    If env is not provided, encoding.environ will be used.
    '''
    if env is None:
        env = encoding.environ
    checklist = [
        ('EDITOR', 'ui', 'editor'),
        ('VISUAL', 'ui', 'editor'),
        ('PAGER', 'pager', 'pager'),
    ]
    result = []
    for envname, section, configname in checklist:
        if envname not in env:
            continue
        result.append((section, configname, env[envname], '$%s' % envname))
    return result

def defaultrcpath():
    '''return rc paths in default.d'''
    path = []
    defaultpath = os.path.join(util.datapath, 'default.d')
    if os.path.isdir(defaultpath):
        path = _expandrcpath(defaultpath)
    return path

def rccomponents():
    '''return an ordered [(type, obj)] about where to load configs.

    respect $HGRCPATH. if $HGRCPATH is empty, only .hg/hgrc of current repo is
    used. if $HGRCPATH is not set, the platform default will be used.

    if a directory is provided, *.rc files under it will be used.

    type could be either 'path' or 'items', if type is 'path', obj is a string,
    and is the config file path. if type is 'items', obj is a list of (section,
    name, value, source) that should fill the config directly.
    '''
    envrc = ('items', envrcitems())

    if 'HGRCPATH' in encoding.environ:
        # assume HGRCPATH is all about user configs so environments can be
        # overridden.
        _rccomponents = [envrc]
        for p in encoding.environ['HGRCPATH'].split(pycompat.ospathsep):
            if not p:
                continue
            _rccomponents.extend(('path', p) for p in _expandrcpath(p))
    else:
        normpaths = lambda paths: [('path', os.path.normpath(p)) for p in paths]
        _rccomponents = normpaths(defaultrcpath() + systemrcpath())
        _rccomponents.append(envrc)
        _rccomponents.extend(normpaths(userrcpath()))
    return _rccomponents

def defaultpagerenv():
    '''return a dict of default environment variables and their values,
    intended to be set before starting a pager.
    '''
    return {'LESS': 'FRX', 'LV': '-c'}