git-commit-vandalism/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, context, util, encoding, node

import re
import sys
import os
import json
import shutil
import subprocess
import urllib

#
# If you want to switch to hg-git compatibility mode:
# git config --global remote-hg.hg-git-compat true
#
# If you are not in hg-git-compat mode and want to disable the tracking of
# named branches:
# git config --global remote-hg.track-branches false
#
# git:
# Sensible defaults for git.
# hg bookmarks are exported as git branches, hg branches are prefixed
# with 'branches/', HEAD is a special case.
#
# hg:
# Emulate hg-git.
# Only hg bookmarks are exported as git branches.
# Commits are modified to preserve hg information and allow bidirectionality.
#

NAME_RE = re.compile('^([^<>]+)')
AUTHOR_RE = re.compile('^([^<>]+?)? ?<([^<>]*)>$')
AUTHOR_HG_RE = re.compile('^(.*?) ?<(.*?)(?:>(.+)?)?$')
RAW_AUTHOR_RE = re.compile('^(\w+) (?:(.+)? )?<(.*)> (\d+) ([+-]\d+)')

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)

def hgmode(mode):
    m = { '100755': 'x', '120000': 'l' }
    return m.get(mode, '')

def hghex(node):
    return hg.node.hex(node)

def get_config(config):
    cmd = ['git', 'config', '--get', config]
    process = subprocess.Popen(cmd, stdout=subprocess.PIPE)
    output, _ = process.communicate()
    return output

class Marks:

    def __init__(self, path):
        self.path = path
        self.tips = {}
        self.marks = {}
        self.rev_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']

        for rev, mark in self.marks.iteritems():
            self.rev_marks[mark] = int(rev)

    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 to_rev(self, mark):
        return self.rev_marks[mark]

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

    def new_mark(self, rev, mark):
        self.marks[str(rev)] = mark
        self.rev_marks[mark] = rev
        self.last_mark = 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 get_mark(self):
        i = self.line.index(':') + 1
        return int(self.line[i:])

    def get_data(self):
        if not self.check('data'):
            return None
        i = self.line.index(' ') + 1
        size = int(self.line[i:])
        return sys.stdin.read(size)

    def get_author(self):
        global bad_mail

        ex = None
        m = RAW_AUTHOR_RE.match(self.line)
        if not m:
            return None
        _, name, email, date, tz = m.groups()
        if name and 'ext:' in name:
            m = re.match('^(.+?) ext:\((.+)\)$', name)
            if m:
                name = m.group(1)
                ex = urllib.unquote(m.group(2))

        if email != bad_mail:
            if name:
                user = '%s <%s>' % (name, email)
            else:
                user = '<%s>' % (email)
        else:
            user = name

        if ex:
            user += ex

        tz = int(tz)
        tz = ((tz / 100) * 3600) + ((tz % 100) * 60)
        return (user, int(date), -tz)

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_git(user):
    name = mail = None
    user = user.replace('"', '')
    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()
    return (name, mail)

def fixup_user_hg(user):
    def sanitize(name):
        # stole this from hg-git
        return re.sub('[<>\n]', '?', name.lstrip('< ').rstrip('> '))

    m = AUTHOR_HG_RE.match(user)
    if m:
        name = sanitize(m.group(1))
        mail = sanitize(m.group(2))
        ex = m.group(3)
        if ex:
            name += ' ext:(' + urllib.quote(ex) + ')'
    else:
        name = sanitize(user)
        if '@' in user:
            mail = name
        else:
            mail = None

    return (name, mail)

def fixup_user(user):
    global mode, bad_mail

    if mode == 'git':
        name, mail = fixup_user_git(user)
    else:
        name, mail = fixup_user_hg(user)

    if not name:
        name = bad_name
    if not mail:
        mail = bad_mail

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

def get_repo(url, alias):
    global dirname, peer

    myui = ui.ui()
    myui.setconfig('ui', 'interactive', 'off')
    myui.fout = sys.stderr

    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 mark_to_rev(mark):
    global marks
    return marks.to_rev(mark)

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

    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 = xrange(tip, head.rev() + 1)
    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 mode == 'hg':
            extra_msg = ''

            if rev_branch != 'default':
                extra_msg += 'branch : %s\n' % rev_branch

            renames = []
            for f in c.files():
                if f not in c.manifest():
                    continue
                rename = c.filectx(f).renamed()
                if rename:
                    renames.append((rename[0], f))

            for e in renames:
                extra_msg += "rename : %s => %s\n" % e

            for key, value in extra.iteritems():
                if key in ('author', 'committer', 'encoding', 'message', 'branch', 'hg-git'):
                    continue
                else:
                    extra_msg += "extra : %s : %s\n" % (key, urllib.quote(value))

            desc += '\n'
            if extra_msg:
                desc += '\n--HG--\n' + extra_msg

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

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

    if os.path.exists(path):
        print "*import-marks %s" % path
    print "*export-marks %s" % path

    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, bmarks

    head = bookmarks.readcurrent(repo)
    if head:
        node = repo[head]
    else:
        # fake bookmark from current branch
        head = cur
        node = repo['.']
        if not node:
            node = repo['tip']
        if not node:
            return
        if head == 'default':
            head = 'master'
        bmarks[head] = node

    print "@refs/heads/%s HEAD" % head
    g_head = (head, node)

def do_list(parser):
    global branches, bmarks, mode, track_branches

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

    cur = repo.dirstate.branch()

    list_head(repo, cur)

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

        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()

    tmp = encoding.encoding
    encoding.encoding = 'utf-8'

    # 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()

    encoding.encoding = tmp

    print 'done'

def parse_blob(parser):
    global blob_marks

    parser.next()
    mark = parser.get_mark()
    parser.next()
    data = parser.get_data()
    blob_marks[mark] = data
    parser.next()

def get_merge_files(repo, p1, p2, files):
    for e in repo[p1].files():
        if e not in files:
            if e not in repo[p1].manifest():
                continue
            f = { 'ctx' : repo[p1][e] }
            files[e] = f

def parse_commit(parser):
    global marks, blob_marks, parsed_refs
    global mode

    from_mark = merge_mark = None

    ref = parser[1]
    parser.next()

    commit_mark = parser.get_mark()
    parser.next()
    author = parser.get_author()
    parser.next()
    committer = parser.get_author()
    parser.next()
    data = parser.get_data()
    parser.next()
    if parser.check('from'):
        from_mark = parser.get_mark()
        parser.next()
    if parser.check('merge'):
        merge_mark = parser.get_mark()
        parser.next()
        if parser.check('merge'):
            die('octopus merges are not supported yet')

    files = {}

    for line in parser:
        if parser.check('M'):
            t, m, mark_ref, path = line.split(' ', 3)
            mark = int(mark_ref[1:])
            f = { 'mode' : hgmode(m), 'data' : blob_marks[mark] }
        elif parser.check('D'):
            t, path = line.split(' ', 1)
            f = { 'deleted' : True }
        else:
            die('Unknown file command: %s' % line)
        files[path] = f

    def getfilectx(repo, memctx, f):
        of = files[f]
        if 'deleted' in of:
            raise IOError
        if 'ctx' in of:
            return of['ctx']
        is_exec = of['mode'] == 'x'
        is_link = of['mode'] == 'l'
        rename = of.get('rename', None)
        return context.memfilectx(f, of['data'],
                is_link, is_exec, rename)

    repo = parser.repo

    user, date, tz = author
    extra = {}

    if committer != author:
        extra['committer'] = "%s %u %u" % committer

    if from_mark:
        p1 = repo.changelog.node(mark_to_rev(from_mark))
    else:
        p1 = '\0' * 20

    if merge_mark:
        p2 = repo.changelog.node(mark_to_rev(merge_mark))
    else:
        p2 = '\0' * 20

    #
    # If files changed from any of the parents, hg wants to know, but in git if
    # nothing changed from the first parent, nothing changed.
    #
    if merge_mark:
        get_merge_files(repo, p1, p2, files)

    if mode == 'hg':
        i = data.find('\n--HG--\n')
        if i >= 0:
            tmp = data[i + len('\n--HG--\n'):].strip()
            for k, v in [e.split(' : ', 1) for e in tmp.split('\n')]:
                if k == 'rename':
                    old, new = v.split(' => ', 1)
                    files[new]['rename'] = old
                elif k == 'branch':
                    extra[k] = v
                elif k == 'extra':
                    ek, ev = v.split(' : ', 1)
                    extra[ek] = urllib.unquote(ev)
            data = data[:i]

    ctx = context.memctx(repo, (p1, p2), data,
            files.keys(), getfilectx,
            user, (date, tz), extra)

    tmp = encoding.encoding
    encoding.encoding = 'utf-8'

    node = repo.commitctx(ctx)

    encoding.encoding = tmp

    rev = repo[node].rev()

    parsed_refs[ref] = node
    marks.new_mark(rev, commit_mark)

def parse_reset(parser):
    global parsed_refs

    ref = parser[1]
    parser.next()
    # ugh
    if parser.check('commit'):
        parse_commit(parser)
        return
    if not parser.check('from'):
        return
    from_mark = parser.get_mark()
    parser.next()

    node = parser.repo.changelog.node(mark_to_rev(from_mark))
    parsed_refs[ref] = node

def parse_tag(parser):
    name = parser[1]
    parser.next()
    from_mark = parser.get_mark()
    parser.next()
    tagger = parser.get_author()
    parser.next()
    data = parser.get_data()
    parser.next()

    # nothing to do

def do_export(parser):
    global parsed_refs, bmarks, peer

    p_bmarks = []

    parser.next()

    for line in parser.each_block('done'):
        if parser.check('blob'):
            parse_blob(parser)
        elif parser.check('commit'):
            parse_commit(parser)
        elif parser.check('reset'):
            parse_reset(parser)
        elif parser.check('tag'):
            parse_tag(parser)
        elif parser.check('feature'):
            pass
        else:
            die('unhandled export command: %s' % line)

    for ref, node in parsed_refs.iteritems():
        if ref.startswith('refs/heads/branches'):
            print "ok %s" % ref
        elif ref.startswith('refs/heads/'):
            bmark = ref[len('refs/heads/'):]
            p_bmarks.append((bmark, node))
            continue
        elif ref.startswith('refs/tags/'):
            tag = ref[len('refs/tags/'):]
            if mode == 'git':
                msg = 'Added tag %s for changeset %s' % (tag, hghex(node[:6]));
                parser.repo.tag([tag], node, msg, False, None, {})
            else:
                parser.repo.tag([tag], node, None, True, None, {})
            print "ok %s" % ref
        else:
            # transport-helper/fast-export bugs
            continue

    if peer:
        parser.repo.push(peer, force=False)

    # handle bookmarks
    for bmark, node in p_bmarks:
        ref = 'refs/heads/' + bmark
        new = hghex(node)

        if bmark in bmarks:
            old = bmarks[bmark].hex()
        else:
            old = ''

        if bmark == 'master' and 'master' not in parser.repo._bookmarks:
            # fake bookmark
            pass
        elif bookmarks.pushbookmark(parser.repo, bmark, old, new):
            # updated locally
            pass
        else:
            print "error %s" % ref
            continue

        if peer:
            if not peer.pushkey('bookmarks', bmark, old, new):
                print "error %s" % ref
                continue

        print "ok %s" % ref

    print

def fix_path(alias, repo, orig_url):
    repo_url = util.url(repo.url())
    url = util.url(orig_url)
    if str(url) == str(repo_url):
        return
    cmd = ['git', 'config', 'remote.%s.url' % alias, "hg::%s" % repo_url]
    subprocess.call(cmd)

def main(args):
    global prefix, dirname, branches, bmarks
    global marks, blob_marks, parsed_refs
    global peer, mode, bad_mail, bad_name
    global track_branches

    alias = args[1]
    url = args[2]
    peer = None

    hg_git_compat = False
    track_branches = True
    try:
        if get_config('remote-hg.hg-git-compat') == 'true\n':
            hg_git_compat = True
            track_branches = False
        if get_config('remote-hg.track-branches') == 'false\n':
            track_branches = False
    except subprocess.CalledProcessError:
        pass

    if hg_git_compat:
        mode = 'hg'
        bad_mail = 'none@none'
        bad_name = ''
    else:
        mode = 'git'
        bad_mail = 'unknown'
        bad_name = 'Unknown'

    if alias[4:] == url:
        is_tmp = True
        alias = util.sha1(alias).hexdigest()
    else:
        is_tmp = False

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

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

    if not is_tmp:
        fix_path(alias, peer or repo, url)

    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()

    if not is_tmp:
        marks.store()
    else:
        shutil.rmtree(dirname)

sys.exit(main(sys.argv))