run-mirror

#!/usr/bin/env python

from optparse import OptionParser
import os
from subprocess import check_call
import sys


DEBUG = False
HERE = os.path.abspath(os.path.dirname(__file__))


def run(*popenargs, **kwargs):
    cmd = popenargs[0]

    if DEBUG:
        if isinstance(cmd, list):
            print "Running: %s" % " ".join(cmd)
        else:
            print "Running: %s" % cmd

    return check_call(*popenargs, **kwargs)


def run_output(*popenargs, **kwargs):
    cmd = popenargs[0]

    if DEBUG:
        if isinstance(cmd, list):
            print "Running: %s" % " ".join(cmd)
        else:
            print "Running: %s" % cmd

    return check_output(*popenargs, **kwargs)


def check_output(*popenargs, **kwargs): # From python2.6
    r"""Run command with arguments and return its output as a byte string.

    If the exit code was non-zero it raises a CalledProcessError.  The
    CalledProcessError object will have the return code in the
    returncode
    attribute and output in the output attribute.

    The arguments are the same as for the Popen constructor.
    Example:

    >>> check_output(["ls", "-l", "/dev/null"])
    'crw-rw-rw- 1 root root 1, 3 Oct 18  2007 /dev/null\n'

    The stdout argument is not allowed as it
    is used internally.
    To capture standard error in the
    result, use stderr=STDOUT.

    >>> check_output(["/bin/sh", "-c",
    ...               "ls -l non_existent_file ; exit 0"],
    ...               stderr=STDOUT)
    'ls: non_existent_file: No such file or directory\n'
    """

    from subprocess import Popen, PIPE, CalledProcessError

    if 'stdout' in kwargs:
        raise ValueError('stdout argument not allowed, it will be overridden.')

    process = Popen(stdout=PIPE, *popenargs, **kwargs)
    output, unused_err = process.communicate()
    retcode = process.poll()
    if retcode:
        cmd = kwargs.get("args")
        if cmd is None:
            cmd = popenargs[0]
        raise CalledProcessError(retcode, cmd) #, output=output)
    return output


def convert_to_git(src, dst):

    print "Converting SVN repository %s to Git repository %s" % (
        src, dst)

    env = os.environ.copy()
    env['GIT_DIR'] = os.path.join(dst, '.git')

    git = lambda *args, **kwargs: run_output(
        ["git"] + args[0], *args[1:], env=env, **kwargs)

    if os.path.exists(dst):
        print "Fetching new revisions..."
        git(["svn", "fetch"])
    else:
        print "Cloning from %s" % src
        git(["svn", "clone", "--stdlayout", src, dst])

    tags = [line.strip()
            for line in check_output(["git", "tag"], env=env).split('\n')
            if line.strip() != '']
    branches = [line[2:].strip()
                for line in check_output(["git", "branch"], env=env).split('\n')
                if line.strip() != '']

    print "Found %d tags and %d branches" % (len(tags), len(branches))

    refs = [line[2:].strip()
            for line in git(["branch", "-a"]).split('\n')
            if line.strip() != '']

    # Add tags
    for tag_ref in (line for line in refs if line.startswith('remotes/tags')):

        tag = tag_ref.split('/', 2)[2]
        if tag not in tags:

            # First, find the author of the commit we want to tag
            # Take only the first line, since some lines seems to be broken
            # sometimes !?
            commiter = check_output(
                ["git", "show", "--pretty=format:%cN", tag_ref],
                env=env).strip().split('\n')[0]

            # Change the author of the next commit
            git(["config", "user.name", commiter])

            print "Tagging %r with %r" % (tag_ref, tag)
            # Now, create the tag
            git(["tag",
                 "-a", "-m", "Tag release: %s" % tag,
                 tag, tag_ref])

            # And unset the configuration we changed before
            git(["config", "--remove-section", "user"])

    # Add branches
    for branch_ref in (line for line in refs
                       if line.startswith('remotes/') and
                       # Don't create branch already pushed!
                       # 'origin' here is the repository where the mirror is
                       # mirrored to, not where it's mirrored *from*.
                       not line.startswith('remotes/origin/') and
                       not line.startswith('remotes/tags') and
                       not line.startswith('remotes/trunk')):
        branch = branch_ref.split('/', 1)[1]
        if branch not in branches:
            print "Creating branch %r from %r" % (branch, branch_ref)
            git(["branch", branch, branch_ref])

    # Compress the Git data
    print "Clean the repository"
    git(["repack", "-Adfq"])



def run(argv=None):
    global DEBUG # beuargh

    if argv is None:
        argv = sys.argv

    parser = OptionParser(usage="%prog SVN_URL [DEST]")
    parser.add_option('-d', '--debug', action='store_true', dest="debug",
                      help="Display commands run", default=False)
    (options, args) = parser.parse_args(argv)

    DEBUG = options.debug


    if len(args) == 3:
        (svn_url, dest) = args[1:]
    else:
        parser.error("Not enought argument")

    convert_to_git(svn_url, dest)


if __name__ == '__main__':
    run()