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.)
#!/bin/sh
# Tests if hgweb can run without touching sys.stdin, as is required
# by the WSGI standard and strictly implemented by mod_wsgi.
mkdir repo
cd repo
hg init
echo foo > bar
hg add bar
hg commit -m "test"
hg tip
cat > request.py <<EOF
from mercurial import dispatch
from mercurial.hgweb.hgweb_mod import hgweb
from mercurial.ui import ui
from mercurial import hg
from StringIO import StringIO
import os, sys
class FileLike(object):
def __init__(self, real):
self.real = real
def fileno(self):
print >> sys.__stdout__, 'FILENO'
return self.real.fileno()
def read(self):
print >> sys.__stdout__, 'READ'
return self.real.read()
def readline(self):
print >> sys.__stdout__, 'READLINE'
return self.real.readline()
sys.stdin = FileLike(sys.stdin)
errors = StringIO()
input = StringIO()
output = StringIO()
def startrsp(headers, data):
print '---- HEADERS'
print headers
print '---- DATA'
print data
return output.write
env = {
'wsgi.version': (1, 0),
'wsgi.url_scheme': 'http',
'wsgi.errors': errors,
'wsgi.input': input,
'wsgi.multithread': False,
'wsgi.multiprocess': False,
'wsgi.run_once': False,
'REQUEST_METHOD': 'GET',
'SCRIPT_NAME': '',
'PATH_INFO': '',
'QUERY_STRING': '',
'SERVER_NAME': '127.0.0.1',
'SERVER_PORT': os.environ['HGPORT'],
'SERVER_PROTOCOL': 'HTTP/1.0'
}
i = hgweb('.')
i(env, startrsp)
print '---- ERRORS'
print errors.getvalue()
print '---- OS.ENVIRON wsgi variables'
print sorted([x for x in os.environ if x.startswith('wsgi')])
print '---- request.ENVIRON wsgi variables'
print sorted([x for x in i.repo.ui.environ if x.startswith('wsgi')])
EOF
python request.py