diff options
Diffstat (limited to 'contrib/remote-helpers/git-remote-hg')
| -rwxr-xr-x | contrib/remote-helpers/git-remote-hg | 304 |
1 files changed, 241 insertions, 63 deletions
diff --git a/contrib/remote-helpers/git-remote-hg b/contrib/remote-helpers/git-remote-hg index 45f6c80d45..1dd3d7030e 100755 --- a/contrib/remote-helpers/git-remote-hg +++ b/contrib/remote-helpers/git-remote-hg @@ -8,8 +8,11 @@ # Just copy to your ~/bin, or anywhere in your $PATH. # Then you can clone with: # git clone hg::/path/to/mercurial/repo/ +# +# For remote repositories a local clone is stored in +# "$GIT_DIR/hg/origin/clone/.hg/". -from mercurial import hg, ui, bookmarks, context, util, encoding +from mercurial import hg, ui, bookmarks, context, encoding, node, error, extensions import re import sys @@ -18,8 +21,20 @@ import json import shutil import subprocess import urllib +import atexit +import urlparse, hashlib # +# 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 +# +# If you don't want to force pushes (and thus risk creating new remote heads): +# git config --global remote-hg.force-push false +# +# If you want the equivalent of hg's clone/pull--insecure option: +# git config --global remote-hg.insecure true +# # If you want to switch to hg-git compatibility mode: # git config --global remote-hg.hg-git-compat true # @@ -36,6 +51,7 @@ import urllib NAME_RE = re.compile('^([^<>]+)') AUTHOR_RE = re.compile('^([^<>]+?)? ?<([^<>]*)>$') +EMAIL_RE = re.compile('^([^<>]+[^ \\\t<>])?\\b(?:[ \\t<>]*?)\\b([^ \\t<>]+@[^ \\t<>]+)') AUTHOR_HG_RE = re.compile('^(.*?) ?<(.*?)(?:>(.+)?)?$') RAW_AUTHOR_RE = re.compile('^(\w+) (?:(.+)? )?<(.*)> (\d+) ([+-]\d+)') @@ -56,12 +72,30 @@ def hgmode(mode): m = { '100755': 'x', '120000': 'l' } return m.get(mode, '') +def hghex(node): + return hg.node.hex(node) + +def hgref(ref): + return ref.replace('___', ' ') + +def gitref(ref): + return ref.replace(' ', '___') + def get_config(config): cmd = ['git', 'config', '--get', config] process = subprocess.Popen(cmd, stdout=subprocess.PIPE) output, _ = process.communicate() return output +def get_config_bool(config, default=False): + value = get_config(config).rstrip('\n') + if value == "true": + return True + elif value == "false": + return False + else: + return default + class Marks: def __init__(self, path): @@ -101,6 +135,10 @@ class Marks: def to_rev(self, mark): return self.rev_marks[mark] + def next_mark(self): + self.last_mark += 1 + return self.last_mark + def get_mark(self, rev): self.last_mark += 1 self.marks[str(rev)] = self.last_mark @@ -112,7 +150,7 @@ class Marks: self.last_mark = mark def is_marked(self, rev): - return self.marks.has_key(str(rev)) + return str(rev) in self.marks def get_tip(self, branch): return self.tips.get(branch, 0) @@ -188,19 +226,43 @@ class Parser: 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 fix_file_path(path): + if not os.path.isabs(path): + return path + return os.path.relpath(path, '/') + +def export_files(files): + global marks, filenodes + + final = [] + for f in files: + fid = node.hex(f.filenode()) + + if fid in filenodes: + mark = filenodes[fid] + else: + mark = marks.next_mark() + filenodes[fid] = mark + d = f.data() + + print "blob" + print "mark :%u" % mark + print "data %d" % len(d) + print d + + path = fix_file_path(f.path()) + final.append((gitmode(f.flags()), mark, path)) + + return final def get_filechanges(repo, ctx, parent): modified = set() added = set() removed = set() - cur = ctx.manifest() + # load earliest manifest first for caching reasons prev = repo[parent].manifest().copy() + cur = ctx.manifest() for fn in cur: if fn in prev: @@ -221,9 +283,14 @@ def fixup_user_git(user): name = m.group(1) mail = m.group(2).strip() else: - m = NAME_RE.match(user) + m = EMAIL_RE.match(user) if m: - name = m.group(1).strip() + name = m.group(1) + mail = m.group(2) + else: + m = NAME_RE.match(user) + if m: + name = m.group(1).strip() return (name, mail) def fixup_user_hg(user): @@ -267,17 +334,33 @@ def get_repo(url, alias): myui = ui.ui() myui.setconfig('ui', 'interactive', 'off') + myui.fout = sys.stderr + + if get_config_bool('remote-hg.insecure'): + myui.setconfig('web', 'cacerts', '') + + try: + mod = extensions.load(myui, 'hgext.schemes', None) + mod.extsetup(myui) + except ImportError: + pass 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) + try: + peer, dstpeer = hg.clone(myui, {}, url, local_path, update=True, pull=True) + except: + die('Repository error') repo = dstpeer.local() else: repo = hg.repository(myui, local_path) - peer = hg.peer(myui, {}, url) + try: + peer = hg.peer(myui, {}, url) + except: + die('Repository error') repo.pull(peer, heads=None, force=True) return repo @@ -296,10 +379,6 @@ def export_ref(repo, name, kind, head): 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 @@ -357,6 +436,8 @@ def export_ref(repo, name, kind, head): if len(parents) == 0 and rev: print 'reset %s/%s' % (prefix, ename) + modified_final = export_files(c.filectx(f) for f in modified) + print "commit %s/%s" % (prefix, ename) print "mark :%d" % (marks.get_mark(rev)) print "author %s" % (author) @@ -369,16 +450,15 @@ def export_ref(repo, name, kind, head): if len(parents) > 1: print "merge :%s" % (rev_to_mark(parents[1])) - for f in modified: - export_file(c.filectx(f)) + for f in modified_final: + print "M %s :%u %s" % f for f in removed: - print "D %s" % (f) + print "D %s" % (fix_file_path(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) @@ -388,10 +468,10 @@ def export_ref(repo, name, kind, head): marks.set_tip(ename, rev) def export_tag(repo, tag): - export_ref(repo, tag, 'tags', repo[tag]) + export_ref(repo, tag, 'tags', repo[hgref(tag)]) def export_bookmark(repo, bmark): - head = bmarks[bmark] + head = bmarks[hgref(bmark)] export_ref(repo, bmark, 'bookmarks', head) def export_branch(repo, branch): @@ -420,19 +500,24 @@ def do_capabilities(parser): print +def branch_tip(repo, branch): + # older versions of mercurial don't have this + if hasattr(repo, 'branchtip'): + return repo.branchtip(branch) + else: + return repo.branchtags()[branch] + def get_branch_tip(repo, branch): global branches - heads = branches.get(branch, None) + heads = branches.get(hgref(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 branch_tip(repo, hgref(branch)) return heads[0] @@ -454,11 +539,12 @@ def list_head(repo, cur): head = 'master' bmarks[head] = node + head = gitref(head) print "@refs/heads/%s HEAD" % head g_head = (head, node) def do_list(parser): - global branches, bmarks, mode, track_branches + global branches, bmarks, track_branches repo = parser.repo for bmark, node in bookmarks.listbookmarks(repo).iteritems(): @@ -475,15 +561,15 @@ def do_list(parser): branches[branch] = heads for branch in branches: - print "? refs/heads/branches/%s" % branch + print "? refs/heads/branches/%s" % gitref(branch) for bmark in bmarks: - print "? refs/heads/%s" % bmark + print "? refs/heads/%s" % gitref(bmark) for tag, node in repo.tagslist(): if tag == 'tip': continue - print "? refs/tags/%s" % tag + print "? refs/tags/%s" % gitref(tag) print @@ -532,7 +618,6 @@ def parse_blob(parser): data = parser.get_data() blob_marks[mark] = data parser.next() - return def get_merge_files(repo, p1, p2, files): for e in repo[p1].files(): @@ -543,7 +628,7 @@ def get_merge_files(repo, p1, p2, files): files[e] = f def parse_commit(parser): - global marks, blob_marks, bmarks, parsed_refs + global marks, blob_marks, parsed_refs global mode from_mark = merge_mark = None @@ -568,6 +653,10 @@ def parse_commit(parser): if parser.check('merge'): die('octopus merges are not supported yet') + # fast-export adds an extra newline + if data[-1] == '\n': + data = data[:-1] + files = {} for line in parser: @@ -576,7 +665,7 @@ def parse_commit(parser): mark = int(mark_ref[1:]) f = { 'mode' : hgmode(m), 'data' : blob_marks[mark] } elif parser.check('D'): - t, path = line.split(' ') + t, path = line.split(' ', 1) f = { 'deleted' : True } else: die('Unknown file command: %s' % line) @@ -619,11 +708,16 @@ def parse_commit(parser): if merge_mark: get_merge_files(repo, p1, p2, files) + # Check if the ref is supposed to be a named branch + if ref.startswith('refs/heads/branches/'): + branch = ref[len('refs/heads/branches/'):] + extra['branch'] = hgref(branch) + 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(' : ') for e in tmp.split('\n')]: + 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 @@ -648,10 +742,11 @@ def parse_commit(parser): 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 @@ -676,11 +771,46 @@ def parse_tag(parser): data = parser.get_data() parser.next() - # nothing to do + parsed_tags[name] = (tagger, data) + +def write_tag(repo, tag, node, msg, author): + branch = repo[node].branch() + tip = branch_tip(repo, branch) + tip = repo[tip] + + def getfilectx(repo, memctx, f): + try: + fctx = tip.filectx(f) + data = fctx.data() + except error.ManifestLookupError: + data = "" + content = data + "%s %s\n" % (hghex(node), tag) + return context.memfilectx(f, content, False, False, None) + + p1 = tip.hex() + p2 = '\0' * 20 + if not author: + author = (None, 0, 0) + user, date, tz = author + + ctx = context.memctx(repo, (p1, p2), msg, + ['.hgtags'], getfilectx, + user, (date, tz), {'branch' : branch}) + + tmp = encoding.encoding + encoding.encoding = 'utf-8' + + tagnode = repo.commitctx(ctx) + + encoding.encoding = tmp + + return tagnode def do_export(parser): global parsed_refs, bmarks, peer + p_bmarks = [] + parser.next() for line in parser.each_block('done'): @@ -699,56 +829,93 @@ def do_export(parser): for ref, node in parsed_refs.iteritems(): if ref.startswith('refs/heads/branches'): - pass + branch = ref[len('refs/heads/branches/'):] + if branch in branches and node in branches[branch]: + # up to date + continue + print "ok %s" % ref elif ref.startswith('refs/heads/'): bmark = ref[len('refs/heads/'):] - if bmark in bmarks: - old = bmarks[bmark].hex() - else: - old = '' - if not bookmarks.pushbookmark(parser.repo, bmark, old, node): - continue + p_bmarks.append((bmark, node)) + continue elif ref.startswith('refs/tags/'): tag = ref[len('refs/tags/'):] - parser.repo.tag([tag], node, None, True, None, {}) + tag = hgref(tag) + author, msg = parsed_tags.get(tag, (None, None)) + if mode == 'git': + if not msg: + msg = 'Added tag %s for changeset %s' % (tag, hghex(node[:6])); + write_tag(parser.repo, tag, node, msg, author) + else: + fp = parser.repo.opener('localtags', 'a') + fp.write('%s %s\n' % (hghex(node), tag)) + fp.close() + print "ok %s" % ref else: # transport-helper/fast-export bugs continue + + if peer: + parser.repo.push(peer, force=force_push, newbranch=True) + + # 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 old == new: + continue + + if bmark == 'master' and 'master' not in parser.repo._bookmarks: + # fake bookmark + print "ok %s" % ref + continue + elif bookmarks.pushbookmark(parser.repo, bmark, old, new): + # updated locally + pass + else: + print "error %s" % ref + continue + + if peer: + rb = peer.listkeys('bookmarks') + old = rb.get(bmark, '') + if not peer.pushkey('bookmarks', bmark, old, new): + print "error %s" % ref + continue + print "ok %s" % ref print - if peer: - parser.repo.push(peer, force=False) - def fix_path(alias, repo, orig_url): - repo_url = util.url(repo.url()) - url = util.url(orig_url) - if str(url) == str(repo_url): + url = urlparse.urlparse(orig_url, 'file') + if url.scheme != 'file' or os.path.isabs(url.path): return - cmd = ['git', 'config', 'remote.%s.url' % alias, "hg::%s" % repo_url] + abs_url = urlparse.urljoin("%s/" % os.getcwd(), orig_url) + cmd = ['git', 'config', 'remote.%s.url' % alias, "hg::%s" % abs_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 + global track_branches, force_push, is_tmp + global parsed_tags + global filenodes 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 + hg_git_compat = get_config_bool('remote-hg.hg-git-compat') + track_branches = get_config_bool('remote-hg.track-branches', True) + force_push = get_config_bool('remote-hg.force-push') if hg_git_compat: mode = 'hg' @@ -761,7 +928,7 @@ def main(args): if alias[4:] == url: is_tmp = True - alias = util.sha1(alias).hexdigest() + alias = hashlib.sha1(alias).hexdigest() else: is_tmp = False @@ -771,6 +938,9 @@ def main(args): bmarks = {} blob_marks = {} parsed_refs = {} + marks = None + parsed_tags = {} + filenodes = {} repo = get_repo(url, alias) prefix = 'refs/hg/%s' % alias @@ -784,6 +954,10 @@ def main(args): marks_path = os.path.join(dirname, 'marks-hg') marks = Marks(marks_path) + if sys.platform == 'win32': + import msvcrt + msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY) + parser = Parser(repo) for line in parser: if parser.check('capabilities'): @@ -798,9 +972,13 @@ def main(args): die('unhandled command: %s' % line) sys.stdout.flush() +def bye(): + if not marks: + return if not is_tmp: marks.store() else: shutil.rmtree(dirname) +atexit.register(bye) sys.exit(main(sys.argv)) |