tests/test-encoding
author Alexis S. L. Carvalho <alexis@cecm.usp.br>
Fri, 17 Aug 2007 20:18:05 -0300
changeset 5195 33015dac5df5
parent 3862 46abbed02b2d
child 9483 29d2a7e3a88b
permissions -rwxr-xr-x
convert: fix mercurial_sink.putcommit Changeset 4ebc8693ce72 added some code to putcommit to avoid creating a revision that touches no files, but this can break regular conversions from some repositories: - conceptually, since we're converting a repo, we should try to make the new hg repo as similar as possible to the original repo - we should create a new changeset, even if the original revision didn't touch any files (maybe the commit message had some important bit); - even if a "regular" revision that doesn't touch any file may seem weird (and maybe even broken), it's completely legitimate for a merge revision to not touch any file, and, if we just skip it, the converted repo will end up with wrong history and possibly an extra head. As an example, say the crew and main hg repos are sync'ed. Somebody sends an important patch to the mailing list. Matt quickly applies and pushes it. But at the same time somebody also applies it to crew and pushes it. Suppose the commit message ended up being a bit different (say, there was a typo and somebody didn't fix it) or that the date ended up being different (because of different patch-applying scripts): the changeset hashes will be different, but the manifests will be the same. Since both changesets were pushed to public repos, it's hard to recall them. If both are merged, the manifest from the resulting merge revision will have the exact same contents as its parents - i.e. the merge revision really doesn't touch any file at all. To keep the file filtering stuff "working", the generic code was changed to skip empty revisions if we're filtering the repo, fixing a bug in the process (we want parents[0] instead of tip).

#!/bin/sh

hg init t
cd t

# we need a repo with some legacy latin-1 changesets
hg unbundle $TESTDIR/legacy-encoding.hg
hg co

python << EOF
f = file('latin-1', 'w'); f.write("latin-1 e' encoded: \xe9"); f.close()
f = file('utf-8', 'w'); f.write("utf-8 e' encoded: \xc3\xa9"); f.close()
f = file('latin-1-tag', 'w'); f.write("\xe9"); f.close()
EOF

echo % should fail with encoding error
echo "plain old ascii" > a
hg st
HGENCODING=ascii hg ci -l latin-1 -d "1000000 0"

echo % these should work
echo "latin-1" > a
HGENCODING=latin-1 hg ci -l latin-1 -d "1000000 0"
echo "utf-8" > a
HGENCODING=utf-8 hg ci -l utf-8 -d "1000000 0"

HGENCODING=latin-1 hg tag -d "1000000 0" `cat latin-1-tag`
HGENCODING=latin-1 hg branch `cat latin-1-tag`
HGENCODING=latin-1 hg ci -d "1000000 0" -m 'latin1 branch'
rm .hg/branch

echo % ascii
hg --encoding ascii log
echo % latin-1
hg --encoding latin-1 log
echo % utf-8
hg --encoding utf-8 log
echo % ascii
HGENCODING=ascii hg tags
echo % latin-1
HGENCODING=latin-1 hg tags
echo % utf-8
HGENCODING=utf-8 hg tags
echo % ascii
HGENCODING=ascii hg branches
echo % latin-1
HGENCODING=latin-1 hg branches
echo % utf-8
HGENCODING=utf-8 hg branches

echo '[ui]' >> .hg/hgrc
echo 'fallbackencoding = koi8-r' >> .hg/hgrc
echo % utf-8
HGENCODING=utf-8 hg log

HGENCODING=dolphin hg log

HGENCODING=ascii hg branch `cat latin-1-tag`
cp latin-1-tag .hg/branch
HGENCODING=latin-1 hg ci -d "1000000 0" -m 'should fail'
exit 0