view tests/test-config-env.py @ 45020:697212a830fb stable

convert: bail out in Subversion source if encountering non-ASCII HTTP(S) URL

Before this patch, in the tested case, urllib raised `httplib.InvalidURL: URL
can't contain control characters. '/\xff/!svn/ver/0/.svn' (found at least
'\xff')`, which resulted in that the URL was never recognized as a Subversion
repository.

This patch adds a check that bails out if the URL contains non-ASCII characters.
The warning is not overly user-friendly, but giving the user something to type
into a search engine is definitively better than not explaining why the
repository was not recognized.

We could support non-ASCII chracters by quoting them before passing them to
urllib. However, we would want to be compatible with what the `svn` command
does, which converts the URL from the locale encoding to UTF-8, percent-encodes
it and sends it to the server. If the locale encoding is not UTF-8, the
behavior is IMHO not very intuitive, as the `svn` command may send different
(percent-encoded) octets than what was passed on the console. Instead of
copying this behavior, we better leave it forbidden.

# Test the config layer generated by environment variables

from __future__ import absolute_import, print_function

import os

from mercurial import (
    encoding,
    extensions,
    rcutil,
    ui as uimod,
    util,
)

from mercurial.utils import procutil

testtmp = encoding.environ[b'TESTTMP']

# prepare hgrc files
def join(name):
    return os.path.join(testtmp, name)


with open(join(b'sysrc'), 'wb') as f:
    f.write(b'[ui]\neditor=e0\n[pager]\npager=p0\n')

with open(join(b'userrc'), 'wb') as f:
    f.write(b'[ui]\neditor=e1')

# replace rcpath functions so they point to the files above
def systemrcpath():
    return [join(b'sysrc')]


def userrcpath():
    return [join(b'userrc')]


extensions.wrapfunction(rcutil, 'default_rc_resources', lambda orig: [])

rcutil.systemrcpath = systemrcpath
rcutil.userrcpath = userrcpath

# utility to print configs
def printconfigs(env):
    encoding.environ = env
    rcutil._rccomponents = None  # reset cache
    ui = uimod.ui.load()
    for section, name, value in ui.walkconfig():
        source = ui.configsource(section, name)
        procutil.stdout.write(
            b'%s.%s=%s # %s\n' % (section, name, value, util.pconvert(source))
        )
    procutil.stdout.write(b'\n')


# environment variable overrides
printconfigs({})
printconfigs({b'EDITOR': b'e2', b'PAGER': b'p2'})