view tests/test-walkrepo.py @ 12252:4481f8a93c7a stable

convert/darcs: handle non-ASCII metadata in darcs changelog (issue2354)

Given a commit author or message with non-ASCII characters in a darcs
repo, convert would raise a UnicodeEncodeError when adding changesets
to the hg changelog.

This happened because etree returns back unicode objects for any text
it can't encode into ASCII. convert was passing these objects to
changelog.add(), which would then attempt encoding.fromlocal() on
them.

This patch ensures converter_source.recode() is called on each piece
of commit data returned by etree.

(Also note that darcs is currently encoding agnostic and will print
out whatever is in a patch's metadata byte-for-byte, even in the XML
changelog.)

import os
from mercurial import hg, ui
from mercurial.util import walkrepos
from os import mkdir, chdir
from os.path import join as pjoin

u = ui.ui()
sym = hasattr(os, 'symlink') and hasattr(os.path, 'samestat')

hg.repository(u, 'top1', create=1)
mkdir('subdir')
chdir('subdir')
hg.repository(u, 'sub1', create=1)
mkdir('subsubdir')
chdir('subsubdir')
hg.repository(u, 'subsub1', create=1)
chdir(os.path.pardir)
if sym:
    os.symlink(os.path.pardir, 'circle')
    os.symlink(pjoin('subsubdir', 'subsub1'), 'subsub1')

def runtest():
    reposet = frozenset(walkrepos('.', followsym=True))
    if sym and (len(reposet) != 3):
        print "reposet = %r" % (reposet,)
        print "Found %d repositories when I should have found 3" % (len(reposet),)
    if (not sym) and (len(reposet) != 2):
        print "reposet = %r" % (reposet,)
        print "Found %d repositories when I should have found 2" % (len(reposet),)
    sub1set = frozenset((pjoin('.', 'sub1'),
                         pjoin('.', 'circle', 'subdir', 'sub1')))
    if len(sub1set & reposet) != 1:
        print "sub1set = %r" % (sub1set,)
        print "reposet = %r" % (reposet,)
        print "sub1set and reposet should have exactly one path in common."
    sub2set = frozenset((pjoin('.', 'subsub1'),
                         pjoin('.', 'subsubdir', 'subsub1')))
    if len(sub2set & reposet) != 1:
        print "sub2set = %r" % (sub2set,)
        print "reposet = %r" % (reposet,)
        print "sub1set and reposet should have exactly one path in common."
    sub3 = pjoin('.', 'circle', 'top1')
    if sym and not (sub3 in reposet):
        print "reposet = %r" % (reposet,)
        print "Symbolic links are supported and %s is not in reposet" % (sub3,)

runtest()
if sym:
    # Simulate not having symlinks.
    del os.path.samestat
    sym = False
    runtest()