view tests/test-convert-hg-source @ 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.)

#!/bin/sh

cat >> $HGRCPATH <<EOF
[extensions]
convert=
[convert]
hg.saverev=False
EOF

hg init orig
cd orig

echo foo > foo
echo bar > bar
hg ci -qAm 'add foo bar' -d '0 0'

echo >> foo
hg ci -m 'change foo' -d '1 0'

hg up -qC 0
hg copy --after --force foo bar
hg copy foo baz
hg ci -m 'make bar and baz copies of foo' -d '2 0'

hg merge
hg ci -m 'merge local copy' -d '3 0'

hg up -C 1
hg merge 2
hg ci -m 'merge remote copy' -d '4 0'

chmod +x baz
hg ci -m 'mark baz executable' -d '5 0'

cd ..
hg convert --datesort orig new 2>&1 | grep -v 'subversion python bindings could not be loaded'
cd new
hg out ../orig
cd ..

echo '% check shamap LF and CRLF handling'
cat > rewrite.py <<EOF
import sys
# Interlace LF and CRLF
lines = [(l.rstrip() + ((i % 2) and '\n' or '\r\n'))
         for i, l in enumerate(file(sys.argv[1]))]
file(sys.argv[1], 'wb').write(''.join(lines))
EOF
python rewrite.py new/.hg/shamap
cd orig
hg up -qC 1
echo foo >> foo
hg ci -qm 'change foo again'
hg up -qC 2
echo foo >> foo
hg ci -qm 'change foo again again'
cd ..
hg convert --datesort orig new 2>&1 | grep -v 'subversion python bindings could not be loaded'

echo % init broken repository
hg init broken
cd broken
echo a >> a
echo b >> b
hg ci -qAm init
echo a >> a
echo b >> b
hg copy b c
hg ci -qAm changeall
hg up -qC 0
echo bc >> b
hg ci -m changebagain
HGMERGE=internal:local hg -q merge
hg ci -m merge
hg mv b d
hg ci -m moveb
echo % break it
rm .hg/store/data/b.*
cd ..

hg --config convert.hg.ignoreerrors=True convert broken fixed
hg -R fixed verify
echo '% manifest -r 0'
hg -R fixed manifest -r 0
echo '% manifest -r tip'
hg -R fixed manifest -r tip

true