view tests/test-convert-hg-sink @ 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 and bar'

hg rm foo
hg ci -m 'remove foo'

mkdir foo
echo file > foo/file
hg ci -qAm 'add foo/file'

hg tag some-tag

hg log
cd ..

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

echo '% dirstate should be empty:'
hg debugstate
hg parents -q

hg up -C
hg copy bar baz
echo '% put something in the dirstate:'
hg debugstate > debugstate
grep baz debugstate

echo '% add a new revision in the original repo'
cd ../orig
echo baz > baz
hg ci -qAm 'add baz'

cd ..
hg convert orig new 2>&1 | grep -v 'subversion python bindings could not be loaded'
cd new
hg out ../orig
echo '% dirstate should be the same (no output below):'
hg debugstate > new-debugstate
diff debugstate new-debugstate

echo '% no copies'
hg up -C
hg debugrename baz
cd ..

echo '% test tag rewriting'
cat > filemap <<EOF
exclude foo
EOF
hg convert --filemap filemap orig new-filemap 2>&1 | grep -v 'subversion python bindings could not be loaded'
cd new-filemap
hg tags
cd ..