view contrib/benchmarks/revset.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.

# revset.py - asv revset benchmarks
#
# Copyright 2016 Logilab SA <[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.

'''ASV revset benchmarks generated from contrib/base-revsets.txt

Each revset benchmark is parameterized with variants (first, last, sort, ...)
'''

from __future__ import absolute_import

import os
import string
import sys

from . import basedir, perfbench


def createrevsetbenchmark(baseset, variants=None):
    if variants is None:
        # Default variants
        variants = ["plain", "first", "last", "sort", "sort+first", "sort+last"]
    fname = "track_" + "_".join(
        "".join(
            [c if c in string.digits + string.letters else " " for c in baseset]
        ).split()
    )

    def wrap(fname, baseset):
        @perfbench(name=baseset, params=[("variant", variants)])
        def f(perf, variant):
            revset = baseset
            if variant != "plain":
                for var in variant.split("+"):
                    revset = "%s(%s)" % (var, revset)
            return perf("perfrevset", revset)

        f.__name__ = fname
        return f

    return wrap(fname, baseset)


def initializerevsetbenchmarks():
    mod = sys.modules[__name__]
    with open(os.path.join(basedir, 'contrib', 'base-revsets.txt'), 'rb') as fh:
        for line in fh:
            baseset = line.strip()
            if baseset and not baseset.startswith('#'):
                func = createrevsetbenchmark(baseset)
                setattr(mod, func.__name__, func)


initializerevsetbenchmarks()