mirror of
https://github.com/frej/fast-export.git
synced 2025-11-01 00:45:47 +01:00
b961f146df
Port hg-fast-import to Python 2/3 polyglot code.
Since mercurial accepts and returns bytestrings for all repository data,
the approach I've taken here is to use bytestrings throughout the
hg-fast-import code. All strings pertaining to repository data are
bytestrings. This means the code is using the same string datatype for
this data on Python 3 as it did (and still does) on Python 2.
Repository data coming from subprocess calls to git, or read from files,
is also left as the bytestrings either returned from
subprocess.check_output or as read from the file in 'rb' mode.
Regexes and string literals that are used with repository data have
all had a b'' prefix added.
When repository data is used in error/warning messages, it is decoded
with the UTF8 codec for printing.
With this patch, hg-fast-export.py writes binary output to
sys.stdout.buffer on Python 3 - on Python 2 this doesn't exist and it
still uses sys.stdout.
The only strings that are left as "native" strings and not coerced to
bytestrings are filepaths passed in on the command line, and dictionary
keys for internal data structures used by hg-fast-import.py, that do
not originate in repository data.
Mapping files are read in 'rb' mode, and thus bytestrings are read from
them. When an encoding is given, their contents are decoded with that
encoding, but then immediately encoded again with UTF8 and they are
returned as the resulting bytestrings
Other necessary changes were:
- indexing byestrings with a single index returns an integer on Python.
These indexing operations have been replaced with a one-element
slice: x[0] -> x[0:1] or x[-1] -> [-1:] so at to return a bytestring.
- raw_hash.encode('hex_codec') replaced with binascii.hexlify(raw_hash)
- str(integer) -> b'%d' % integer
- 'string_escape' codec replaced with 'unicode_escape' (which was
backported to python 2.7). Strings decoded with this codec were then
immediately re-encoded with UTF8.
- Calls to map() intended to execute their contents immediately were
unwrapped or converted to list comprehensions, since map() is an
iterator and does not execute until iterated over.
hg-fast-export.sh has been modified to not require Python 2. Instead, if
PYTHON has not been defined, it checks python2, python, then python3,
and uses the first one that exists and can import the mercurial module.
92 lines
2.4 KiB
Bash
Executable File
92 lines
2.4 KiB
Bash
Executable File
#!/bin/sh
|
|
|
|
# Copyright (c) 2007, 2008 Rocco Rutte <pdmef@gmx.net> and others.
|
|
# License: MIT <http://www.opensource.org/licenses/mit-license.php>
|
|
|
|
ROOT="`dirname $0`"
|
|
REPO=""
|
|
PFX="hg2git"
|
|
SFX_MARKS="marks"
|
|
SFX_MAPPING="mapping"
|
|
SFX_HEADS="heads"
|
|
SFX_STATE="state"
|
|
QUIET=""
|
|
|
|
if [ -z "${PYTHON}" ]; then
|
|
# $PYTHON is not set, so we try to find a working python with mercurial:
|
|
for python_cmd in python2 python python3; do
|
|
if command -v $python_cmd > /dev/null; then
|
|
$python_cmd -c 'import mercurial' 2> /dev/null
|
|
if [ $? -eq 0 ]; then
|
|
PYTHON=$python_cmd
|
|
break
|
|
fi
|
|
fi
|
|
done
|
|
fi
|
|
if [ -z "${PYTHON}" ]; then
|
|
echo "Could not find a python interpreter with the mercurial module available. " \
|
|
"Please use the 'PYTHON'environment variable to specify the interpreter to use."
|
|
exit 1
|
|
fi
|
|
|
|
USAGE="[-r <repo>] -R <rev>"
|
|
LONG_USAGE="Print SHA1s of latest changes per branch up to <rev> useful
|
|
to reset import and restart at <rev>.
|
|
If <repo> is omitted, use last hg repository as obtained from state file,
|
|
GIT_DIR/$PFX-$SFX_STATE by default.
|
|
|
|
Options:
|
|
-R Hg revision to reset to
|
|
-r Mercurial repository to use
|
|
"
|
|
|
|
IS_BARE=$(git rev-parse --is-bare-repository) \
|
|
|| (echo "Could not find git repo" ; exit 1)
|
|
if test "z$IS_BARE" != ztrue; then
|
|
# This is not a bare repo, cd to the toplevel
|
|
TOPLEVEL=$(git rev-parse --show-toplevel) \
|
|
|| (echo "Could not find git repo toplevel" ; exit 1)
|
|
cd $TOPLEVEL || exit 1
|
|
fi
|
|
GIT_DIR=$(git rev-parse --git-dir) || (echo "Could not find git repo" ; exit 1)
|
|
|
|
while case "$#" in 0) break ;; esac
|
|
do
|
|
case "$1" in
|
|
-r|--r|--re|--rep|--repo)
|
|
shift
|
|
REPO="$1"
|
|
;;
|
|
-*)
|
|
# pass any other options down to hg2git.py
|
|
break
|
|
;;
|
|
*)
|
|
break
|
|
;;
|
|
esac
|
|
shift
|
|
done
|
|
|
|
# for convenience: get default repo from state file
|
|
if [ x"$REPO" = x -a -f "$GIT_DIR/$PFX-$SFX_STATE" ] ; then
|
|
REPO="`grep '^:repo ' "$GIT_DIR/$PFX-$SFX_STATE" | cut -d ' ' -f 2`"
|
|
echo "Using last hg repository \"$REPO\""
|
|
fi
|
|
|
|
# make sure we have a marks cache
|
|
if [ ! -f "$GIT_DIR/$PFX-$SFX_MARKS" ] ; then
|
|
touch "$GIT_DIR/$PFX-$SFX_MARKS"
|
|
fi
|
|
|
|
GIT_DIR="$GIT_DIR" $PYTHON "$ROOT/hg-reset.py" \
|
|
--repo "$REPO" \
|
|
--marks "$GIT_DIR/$PFX-$SFX_MARKS" \
|
|
--mapping "$GIT_DIR/$PFX-$SFX_MAPPING" \
|
|
--heads "$GIT_DIR/$PFX-$SFX_HEADS" \
|
|
--status "$GIT_DIR/$PFX-$SFX_STATE" \
|
|
"$@"
|
|
|
|
exit $?
|