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).

     1

#!/bin/sh

     2

     3

hg init t

     4

cd t

     5

     6

# we need a repo with some legacy latin-1 changesets

     7

hg unbundle $TESTDIR/legacy-encoding.hg

     8

hg co

     9

    10

python << EOF

    11

f = file('latin-1', 'w'); f.write("latin-1 e' encoded: \xe9"); f.close()

    12

f = file('utf-8', 'w'); f.write("utf-8 e' encoded: \xc3\xa9"); f.close()

    13

f = file('latin-1-tag', 'w'); f.write("\xe9"); f.close()

    14

EOF

    15

    16

echo % should fail with encoding error

    17

echo "plain old ascii" > a

    18

hg st

    19

HGENCODING=ascii hg ci -l latin-1 -d "1000000 0"

    20

    21

echo % these should work

    22

echo "latin-1" > a

    23

HGENCODING=latin-1 hg ci -l latin-1 -d "1000000 0"

    24

echo "utf-8" > a

    25

HGENCODING=utf-8 hg ci -l utf-8 -d "1000000 0"

    26

    27

HGENCODING=latin-1 hg tag -d "1000000 0" `cat latin-1-tag`

    28

HGENCODING=latin-1 hg branch `cat latin-1-tag`

    29

HGENCODING=latin-1 hg ci -d "1000000 0" -m 'latin1 branch'

    30

rm .hg/branch

    31

    32

echo % ascii

    33

hg --encoding ascii log

    34

echo % latin-1

    35

hg --encoding latin-1 log

    36

echo % utf-8

    37

hg --encoding utf-8 log

    38

echo % ascii

    39

HGENCODING=ascii hg tags

    40

echo % latin-1

    41

HGENCODING=latin-1 hg tags

    42

echo % utf-8

    43

HGENCODING=utf-8 hg tags

    44

echo % ascii

    45

HGENCODING=ascii hg branches

    46

echo % latin-1

    47

HGENCODING=latin-1 hg branches

    48

echo % utf-8

    49

HGENCODING=utf-8 hg branches

    50

    51

echo '[ui]' >> .hg/hgrc

    52

echo 'fallbackencoding = koi8-r' >> .hg/hgrc

    53

echo % utf-8

    54

HGENCODING=utf-8 hg log

    55

    56

HGENCODING=dolphin hg log

    57

    58

HGENCODING=ascii hg branch `cat latin-1-tag`

    59

cp latin-1-tag .hg/branch

    60

HGENCODING=latin-1 hg ci -d "1000000 0" -m 'should fail'

    61

exit 0