view tests/test-committer @ 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

unset HGUSER
EMAIL="My Name <[e-mail]>"
export EMAIL

hg init test
cd test
touch asdf
hg add asdf
hg commit -d '1000000 0' -m commit-1
hg tip

unset EMAIL
echo 1234 > asdf
hg commit -d '1000000 0' -u "[e-mail]" -m commit-1
hg tip
echo "[ui]" >> .hg/hgrc
echo "username = foobar <[e-mail]>" >> .hg/hgrc
echo 12 > asdf
hg commit -d '1000000 0' -m commit-1
hg tip
echo 1 > asdf
hg commit -d '1000000 0' -u "[e-mail]" -m commit-1
hg tip
echo 123 > asdf
echo "[ui]" > .hg/hgrc
echo "username = " >> .hg/hgrc
hg commit -d '1000000 0' -m commit-1
rm .hg/hgrc
hg commit -d '1000000 0' -m commit-1 2>&1 | sed -e "s/'[^']*'/user@host/"

echo space > asdf
hg commit -d '1000000 0' -u ' ' -m commit-1

true