view tests/test-convert-clonebranches @ 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 "[convert]" >> $HGRCPATH
echo "hg.tagsbranch=0" >> $HGRCPATH

hg init source
cd source
echo a > a
hg ci -qAm adda
# Add a merge with one parent in the same branch
echo a >> a
hg ci -qAm changea
hg up -qC 0
hg branch branch0
echo b > b
hg ci -qAm addb
hg up -qC
hg merge default
hg ci -qm mergeab
hg tag -ql mergeab
cd ..

# Miss perl... sometimes
cat > filter.py <<EOF
import sys, re

r = re.compile(r'^(?:\d+|pulling from)')
sys.stdout.writelines([l for l in sys.stdin if r.search(l)])
EOF

echo % convert
hg convert -v --config convert.hg.clonebranches=1 source dest |
    python filter.py

# Add a merge with both parents and child in different branches
cd source
hg branch branch1
echo a > file1
hg ci -qAm c1
hg up -qC mergeab
hg branch branch2
echo a > file2
hg ci -qAm c2
hg merge branch1
hg branch branch3
hg ci -qAm c3
cd ..

echo % incremental conversion
hg convert -v --config convert.hg.clonebranches=1 source dest |
    python filter.py