view tests/test-convert-hg-startrev @ 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 'graphlog =' >> $HGRCPATH
echo 'convert =' >> $HGRCPATH

glog()
{
    hg -R "$1" glog --template '{rev} "{desc}" files: {files}\n'
}

hg init source
cd source

echo a > a
echo b > b
hg ci -d '0 0' -qAm '0: add a b'
echo c > c
hg ci -d '1 0' -qAm '1: add c'
hg copy a e
echo b >> b
hg ci -d '2 0' -qAm '2: copy e from a, change b'
hg up -C 0
echo a >> a
hg ci -d '3 0' -qAm '3: change a'
hg merge
hg copy b d
hg ci -d '4 0' -qAm '4: merge 2 and 3, copy d from b'
echo a >> a
hg ci -d '5 0' -qAm '5: change a'
cd ..

echo % convert from null revision
hg convert --config convert.hg.startrev=null source empty
glog empty

echo % convert from zero revision
hg convert --config convert.hg.startrev=0 source full
glog full

echo % convert from merge parent
hg convert --config convert.hg.startrev=1 source conv1
glog conv1
cd conv1
echo % check copy preservation
hg log --follow --copies e
echo % check copy removal on missing parent
hg log --follow --copies d
hg cat -r tip a b
hg -q verify
cd ..

echo % convert from merge
hg convert --config convert.hg.startrev=4 source conv4
glog conv4
cd conv4
hg up -C
hg cat -r tip a b
hg -q verify
cd ..