view tests/test-addremove-similar @ 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

hg init rep; cd rep

touch empty-file
python -c 'for x in range(10000): print x' > large-file

hg addremove

hg commit -m A

rm large-file empty-file
python -c 'for x in range(10,10000): print x' > another-file

hg addremove -s50

hg commit -m B

echo % comparing two empty files caused ZeroDivisionError in the past
hg update -C 0
rm empty-file
touch another-empty-file
hg addremove -s50

cd ..

hg init rep2; cd rep2

python -c 'for x in range(10000): print x' > large-file
python -c 'for x in range(50): print x' > tiny-file

hg addremove

hg commit -m A

python -c 'for x in range(70): print x' > small-file
rm tiny-file
rm large-file

hg addremove -s50

hg commit -m B

echo % should all fail
hg addremove -s foo
hg addremove -s -1
hg addremove -s 1e6

cd ..

echo '% issue 1527'
hg init rep3; cd rep3
mkdir d
echo a > d/a
hg add d/a
hg commit -m 1

mv d/a d/b
hg addremove -s80
hg debugstate
mv d/b c
echo "% no copies found here (since the target isn't in d"
hg addremove -s80 d
echo "% copies here"
hg addremove -s80

true