view tests/test-convert-splicemap @ 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

echo "[extensions]" >> $HGRCPATH
echo "convert=" >> $HGRCPATH
echo 'graphlog =' >> $HGRCPATH

glog()
{
    hg glog --template '{rev} "{desc|firstline}" files: {files}\n' "$@"
}

hg init repo1
cd repo1
echo a > a
hg ci -Am adda
echo b > b
echo a >> a
hg ci -Am addb
PARENTID1=`hg id --debug -i`
echo c > c
hg ci -Am addc
PARENTID2=`hg id --debug -i`
cd ..

hg init repo2
cd repo2
echo b > a
echo d > d
hg ci -Am addaandd
CHILDID1=`hg id --debug -i`
echo d >> d
hg ci -Am changed
CHILDID2=`hg id --debug -i`
echo e > e
hg ci -Am adde
cd ..

echo '% test invalid splicemap'
cat > splicemap <<EOF
$CHILDID2
EOF
hg convert --splicemap splicemap repo2 repo1

echo '% splice repo2 on repo1'
cat > splicemap <<EOF
$CHILDID1 $PARENTID1
$CHILDID2 $PARENTID2,$CHILDID1
EOF
hg clone repo1 target1
hg convert --splicemap splicemap repo2 target1
glog -R target1