path: root/contrib/remote-helpers/git-remote-hg

#!/usr/bin/env python
#
# Copyright (c) 2012 Felipe Contreras
#

# Inspired by Rocco Rutte's hg-fast-export

# Just copy to your ~/bin, or anywhere in your $PATH.
# Then you can clone with:
# git clone hg::/path/to/mercurial/repo/

from mercurial import hg, ui, bookmarks

import re
import sys
import os
import json

NAME_RE = re.compile('^([^<>]+)')
AUTHOR_RE = re.compile('^([^<>]+?)? ?<([^<>]+)>$')

def die(msg, *args):
    sys.stderr.write('ERROR: %s\n' % (msg % args))
    sys.exit(1)

def warn(msg, *args):
    sys.stderr.write('WARNING: %s\n' % (msg % args))

def gitmode(flags):
    return 'l' in flags and '120000' or 'x' in flags and '100755' or '100644'

def gittz(tz):
    return '%+03d%02d' % (-tz / 3600, -tz % 3600 / 60)

class Marks:

    def __init__(self, path):
        self.path = path
        self.tips = {}
        self.marks = {}
        self.last_mark = 0

        self.load()

    def load(self):
        if not os.path.exists(self.path):
            return

        tmp = json.load(open(self.path))

        self.tips = tmp['tips']
        self.marks = tmp['marks']
        self.last_mark = tmp['last-mark']

    def dict(self):
        return { 'tips': self.tips, 'marks': self.marks, 'last-mark' : self.last_mark }

    def store(self):
        json.dump(self.dict(), open(self.path, 'w'))

    def __str__(self):
        return str(self.dict())

    def from_rev(self, rev):
        return self.marks[str(rev)]

    def get_mark(self, rev):
        self.last_mark += 1
        self.marks[str(rev)] = self.last_mark
        return self.last_mark

    def is_marked(self, rev):
        return self.marks.has_key(str(rev))

    def get_tip(self, branch):
        return self.tips.get(branch, 0)

    def set_tip(self, branch, tip):
        self.tips[branch] = tip

class Parser:

    def __init__(self, repo):
        self.repo = repo
        self.line = self.get_line()

    def get_line(self):
        return sys.stdin.readline().strip()

    def __getitem__(self, i):
        return self.line.split()[i]

    def check(self, word):
        return self.line.startswith(word)

    def each_block(self, separator):
        while self.line != separator:
            yield self.line
            self.line = self.get_line()

    def __iter__(self):
        return self.each_block('')

    def next(self):
        self.line = self.get_line()
        if self.line == 'done':
            self.line = None

def export_file(fc):
    d = fc.data()
    print "M %s inline %s" % (gitmode(fc.flags()), fc.path())
    print "data %d" % len(d)
    print d

def get_filechanges(repo, ctx, parent):
    modified = set()
    added = set()
    removed = set()

    cur = ctx.manifest()
    prev = repo[parent].manifest().copy()

    for fn in cur:
        if fn in prev:
            if (cur.flags(fn) != prev.flags(fn) or cur[fn] != prev[fn]):
                modified.add(fn)
            del prev[fn]
        else:
            added.add(fn)
    removed |= set(prev.keys())

    return added | modified, removed

def fixup_user(user):
    user = user.replace('"', '')
    name = mail = None
    m = AUTHOR_RE.match(user)
    if m:
        name = m.group(1)
        mail = m.group(2).strip()
    else:
        m = NAME_RE.match(user)
        if m:
            name = m.group(1).strip()

    if not name:
        name = 'Unknown'
    if not mail:
        mail = 'unknown'

    return '%s <%s>' % (name, mail)

def get_repo(url, alias):
    global dirname

    myui = ui.ui()
    myui.setconfig('ui', 'interactive', 'off')

    if hg.islocal(url):
        repo = hg.repository(myui, url)
    else:
        local_path = os.path.join(dirname, 'clone')
        if not os.path.exists(local_path):
            peer, dstpeer = hg.clone(myui, {}, url, local_path, update=False, pull=True)
            repo = dstpeer.local()
        else:
            repo = hg.repository(myui, local_path)
            peer = hg.peer(myui, {}, url)
            repo.pull(peer, heads=None, force=True)

    return repo

def rev_to_mark(rev):
    global marks
    return marks.from_rev(rev)

def export_ref(repo, name, kind, head):
    global prefix, marks

    ename = '%s/%s' % (kind, name)
    tip = marks.get_tip(ename)

    # mercurial takes too much time checking this
    if tip and tip == head.rev():
        # nothing to do
        return
    revs = repo.revs('%u:%u' % (tip, head))
    count = 0

    revs = [rev for rev in revs if not marks.is_marked(rev)]

    for rev in revs:

        c = repo[rev]
        (manifest, user, (time, tz), files, desc, extra) = repo.changelog.read(c.node())
        rev_branch = extra['branch']

        author = "%s %d %s" % (fixup_user(user), time, gittz(tz))
        if 'committer' in extra:
            user, time, tz = extra['committer'].rsplit(' ', 2)
            committer = "%s %s %s" % (user, time, gittz(int(tz)))
        else:
            committer = author

        parents = [p for p in repo.changelog.parentrevs(rev) if p >= 0]

        if len(parents) == 0:
            modified = c.manifest().keys()
            removed = []
        else:
            modified, removed = get_filechanges(repo, c, parents[0])

        if len(parents) == 0 and rev:
            print 'reset %s/%s' % (prefix, ename)

        print "commit %s/%s" % (prefix, ename)
        print "mark :%d" % (marks.get_mark(rev))
        print "author %s" % (author)
        print "committer %s" % (committer)
        print "data %d" % (len(desc))
        print desc

        if len(parents) > 0:
            print "from :%s" % (rev_to_mark(parents[0]))
            if len(parents) > 1:
                print "merge :%s" % (rev_to_mark(parents[1]))

        for f in modified:
            export_file(c.filectx(f))
        for f in removed:
            print "D %s" % (f)
        print

        count += 1
        if (count % 100 == 0):
            print "progress revision %d '%s' (%d/%d)" % (rev, name, count, len(revs))
            print "#############################################################"

    # make sure the ref is updated
    print "reset %s/%s" % (prefix, ename)
    print "from :%u" % rev_to_mark(rev)
    print

    marks.set_tip(ename, rev)

def export_tag(repo, tag):
    export_ref(repo, tag, 'tags', repo[tag])

def export_bookmark(repo, bmark):
    head = bmarks[bmark]
    export_ref(repo, bmark, 'bookmarks', head)

def export_branch(repo, branch):
    tip = get_branch_tip(repo, branch)
    head = repo[tip]
    export_ref(repo, branch, 'branches', head)

def export_head(repo):
    global g_head
    export_ref(repo, g_head[0], 'bookmarks', g_head[1])

def do_capabilities(parser):
    global prefix, dirname

    print "import"
    print "refspec refs/heads/branches/*:%s/branches/*" % prefix
    print "refspec refs/heads/*:%s/bookmarks/*" % prefix
    print "refspec refs/tags/*:%s/tags/*" % prefix
    print

def get_branch_tip(repo, branch):
    global branches

    heads = branches.get(branch, None)
    if not heads:
        return None

    # verify there's only one head
    if (len(heads) > 1):
        warn("Branch '%s' has more than one head, consider merging" % branch)
        # older versions of mercurial don't have this
        if hasattr(repo, "branchtip"):
            return repo.branchtip(branch)

    return heads[0]

def list_head(repo, cur):
    global g_head

    head = bookmarks.readcurrent(repo)
    if not head:
        return
    node = repo[head]
    print "@refs/heads/%s HEAD" % head
    g_head = (head, node)

def do_list(parser):
    global branches, bmarks

    repo = parser.repo
    for branch in repo.branchmap():
        heads = repo.branchheads(branch)
        if len(heads):
            branches[branch] = heads

    for bmark, node in bookmarks.listbookmarks(repo).iteritems():
        bmarks[bmark] = repo[node]

    cur = repo.dirstate.branch()

    list_head(repo, cur)
    for branch in branches:
        print "? refs/heads/branches/%s" % branch
    for bmark in bmarks:
        print "? refs/heads/%s" % bmark

    for tag, node in repo.tagslist():
        if tag == 'tip':
            continue
        print "? refs/tags/%s" % tag

    print

def do_import(parser):
    repo = parser.repo

    path = os.path.join(dirname, 'marks-git')

    print "feature done"
    if os.path.exists(path):
        print "feature import-marks=%s" % path
    print "feature export-marks=%s" % path
    sys.stdout.flush()

    # lets get all the import lines
    while parser.check('import'):
        ref = parser[1]

        if (ref == 'HEAD'):
            export_head(repo)
        elif ref.startswith('refs/heads/branches/'):
            branch = ref[len('refs/heads/branches/'):]
            export_branch(repo, branch)
        elif ref.startswith('refs/heads/'):
            bmark = ref[len('refs/heads/'):]
            export_bookmark(repo, bmark)
        elif ref.startswith('refs/tags/'):
            tag = ref[len('refs/tags/'):]
            export_tag(repo, tag)

        parser.next()

    print 'done'

def main(args):
    global prefix, dirname, marks, branches, bmarks

    alias = args[1]
    url = args[2]

    gitdir = os.environ['GIT_DIR']
    dirname = os.path.join(gitdir, 'hg', alias)
    branches = {}
    bmarks = {}

    repo = get_repo(url, alias)
    prefix = 'refs/hg/%s' % alias

    if not os.path.exists(dirname):
        os.makedirs(dirname)

    marks_path = os.path.join(dirname, 'marks-hg')
    marks = Marks(marks_path)

    parser = Parser(repo)
    for line in parser:
        if parser.check('capabilities'):
            do_capabilities(parser)
        elif parser.check('list'):
            do_list(parser)
        elif parser.check('import'):
            do_import(parser)
        elif parser.check('export'):
            do_export(parser)
        else:
            die('unhandled command: %s' % line)
        sys.stdout.flush()

    marks.store()

sys.exit(main(sys.argv))