view tests/test-dumprevlog @ 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

CONTRIBDIR=$TESTDIR/../contrib

echo % prepare repo-a
mkdir repo-a
cd repo-a
hg init

echo this is file a > a
hg add a
hg commit -m first

echo adding to file a >> a
hg commit -m second

echo adding more to file a >> a
hg commit -m third

hg verify

echo
echo % dumping revlog of file a to stdout
python $CONTRIBDIR/dumprevlog .hg/store/data/a.i
echo % dumprevlog done

echo
echo % dump all revlogs to file repo.dump
find .hg/store -name "*.i" | sort | xargs python $CONTRIBDIR/dumprevlog > ../repo.dump

cd ..

mkdir repo-b
cd repo-b
hg init

echo
echo % undumping into repo-b
python $CONTRIBDIR/undumprevlog < ../repo.dump
echo % undumping done

cd ..

echo
echo % clone --pull repo-b repo-c  to rebuild fncache
hg clone --pull -U repo-b repo-c

cd repo-c

echo
echo % verify repo-c
hg verify

cd ..

echo
echo % comparing repos
hg -R repo-c incoming repo-a
hg -R repo-a incoming repo-c

exit 0