Andrew's git / gitweb.git / contrib/hg-to-git/hg-to-git.py
?
contrib / hg-to-git / hg-to-git.pyon commit Merge branch 'mm/merge-in-dirty-worktree-doc' into maint (4f9f1f5)
   1#!/usr/bin/env python
   2
   3""" hg-to-git.py - A Mercurial to GIT converter
   4
   5    Copyright (C)2007 Stelian Pop <stelian@popies.net>
   6
   7    This program is free software; you can redistribute it and/or modify
   8    it under the terms of the GNU General Public License as published by
   9    the Free Software Foundation; either version 2, or (at your option)
  10    any later version.
  11
  12    This program is distributed in the hope that it will be useful,
  13    but WITHOUT ANY WARRANTY; without even the implied warranty of
  14    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15    GNU General Public License for more details.
  16
  17    You should have received a copy of the GNU General Public License
  18    along with this program; if not, write to the Free Software
  19    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  20"""
  21
  22import os, os.path, sys
  23import tempfile, pickle, getopt
  24import re
  25
  26if sys.hexversion < 0x02030000:
  27   # The behavior of the pickle module changed significantly in 2.3
  28   sys.stderr.write("hg-to-git.py: requires Python 2.3 or later.\n")
  29   sys.exit(1)
  30
  31# Maps hg version -> git version
  32hgvers = {}
  33# List of children for each hg revision
  34hgchildren = {}
  35# List of parents for each hg revision
  36hgparents = {}
  37# Current branch for each hg revision
  38hgbranch = {}
  39# Number of new changesets converted from hg
  40hgnewcsets = 0
  41
  42#------------------------------------------------------------------------------
  43
  44def usage():
  45
  46        print """\
  47%s: [OPTIONS] <hgprj>
  48
  49options:
  50    -s, --gitstate=FILE: name of the state to be saved/read
  51                         for incrementals
  52    -n, --nrepack=INT:   number of changesets that will trigger
  53                         a repack (default=0, -1 to deactivate)
  54    -v, --verbose:       be verbose
  55
  56required:
  57    hgprj:  name of the HG project to import (directory)
  58""" % sys.argv[0]
  59
  60#------------------------------------------------------------------------------
  61
  62def getgitenv(user, date):
  63    env = ''
  64    elems = re.compile('(.*?)\s+<(.*)>').match(user)
  65    if elems:
  66        env += 'export GIT_AUTHOR_NAME="%s" ;' % elems.group(1)
  67        env += 'export GIT_COMMITTER_NAME="%s" ;' % elems.group(1)
  68        env += 'export GIT_AUTHOR_EMAIL="%s" ;' % elems.group(2)
  69        env += 'export GIT_COMMITTER_EMAIL="%s" ;' % elems.group(2)
  70    else:
  71        env += 'export GIT_AUTHOR_NAME="%s" ;' % user
  72        env += 'export GIT_COMMITTER_NAME="%s" ;' % user
  73        env += 'export GIT_AUTHOR_EMAIL= ;'
  74        env += 'export GIT_COMMITTER_EMAIL= ;'
  75
  76    env += 'export GIT_AUTHOR_DATE="%s" ;' % date
  77    env += 'export GIT_COMMITTER_DATE="%s" ;' % date
  78    return env
  79
  80#------------------------------------------------------------------------------
  81
  82state = ''
  83opt_nrepack = 0
  84verbose = False
  85
  86try:
  87    opts, args = getopt.getopt(sys.argv[1:], 's:t:n:v', ['gitstate=', 'tempdir=', 'nrepack=', 'verbose'])
  88    for o, a in opts:
  89        if o in ('-s', '--gitstate'):
  90            state = a
  91            state = os.path.abspath(state)
  92        if o in ('-n', '--nrepack'):
  93            opt_nrepack = int(a)
  94        if o in ('-v', '--verbose'):
  95            verbose = True
  96    if len(args) != 1:
  97        raise Exception('params')
  98except:
  99    usage()
 100    sys.exit(1)
 101
 102hgprj = args[0]
 103os.chdir(hgprj)
 104
 105if state:
 106    if os.path.exists(state):
 107        if verbose:
 108            print 'State does exist, reading'
 109        f = open(state, 'r')
 110        hgvers = pickle.load(f)
 111    else:
 112        print 'State does not exist, first run'
 113
 114sock = os.popen('hg tip --template "{rev}"')
 115tip = sock.read()
 116if sock.close():
 117    sys.exit(1)
 118if verbose:
 119    print 'tip is', tip
 120
 121# Calculate the branches
 122if verbose:
 123    print 'analysing the branches...'
 124hgchildren["0"] = ()
 125hgparents["0"] = (None, None)
 126hgbranch["0"] = "master"
 127for cset in range(1, int(tip) + 1):
 128    hgchildren[str(cset)] = ()
 129    prnts = os.popen('hg log -r %d --template "{parents}"' % cset).read().strip().split(' ')
 130    prnts = map(lambda x: x[:x.find(':')], prnts)
 131    if prnts[0] != '':
 132        parent = prnts[0].strip()
 133    else:
 134        parent = str(cset - 1)
 135    hgchildren[parent] += ( str(cset), )
 136    if len(prnts) > 1:
 137        mparent = prnts[1].strip()
 138        hgchildren[mparent] += ( str(cset), )
 139    else:
 140        mparent = None
 141
 142    hgparents[str(cset)] = (parent, mparent)
 143
 144    if mparent:
 145        # For merge changesets, take either one, preferably the 'master' branch
 146        if hgbranch[mparent] == 'master':
 147            hgbranch[str(cset)] = 'master'
 148        else:
 149            hgbranch[str(cset)] = hgbranch[parent]
 150    else:
 151        # Normal changesets
 152        # For first children, take the parent branch, for the others create a new branch
 153        if hgchildren[parent][0] == str(cset):
 154            hgbranch[str(cset)] = hgbranch[parent]
 155        else:
 156            hgbranch[str(cset)] = "branch-" + str(cset)
 157
 158if not hgvers.has_key("0"):
 159    print 'creating repository'
 160    os.system('git init')
 161
 162# loop through every hg changeset
 163for cset in range(int(tip) + 1):
 164
 165    # incremental, already seen
 166    if hgvers.has_key(str(cset)):
 167        continue
 168    hgnewcsets += 1
 169
 170    # get info
 171    log_data = os.popen('hg log -r %d --template "{tags}\n{date|date}\n{author}\n"' % cset).readlines()
 172    tag = log_data[0].strip()
 173    date = log_data[1].strip()
 174    user = log_data[2].strip()
 175    parent = hgparents[str(cset)][0]
 176    mparent = hgparents[str(cset)][1]
 177
 178    #get comment
 179    (fdcomment, filecomment) = tempfile.mkstemp()
 180    csetcomment = os.popen('hg log -r %d --template "{desc}"' % cset).read().strip()
 181    os.write(fdcomment, csetcomment)
 182    os.close(fdcomment)
 183
 184    print '-----------------------------------------'
 185    print 'cset:', cset
 186    print 'branch:', hgbranch[str(cset)]
 187    print 'user:', user
 188    print 'date:', date
 189    print 'comment:', csetcomment
 190    if parent:
 191        print 'parent:', parent
 192    if mparent:
 193        print 'mparent:', mparent
 194    if tag:
 195        print 'tag:', tag
 196    print '-----------------------------------------'
 197
 198    # checkout the parent if necessary
 199    if cset != 0:
 200        if hgbranch[str(cset)] == "branch-" + str(cset):
 201            print 'creating new branch', hgbranch[str(cset)]
 202            os.system('git checkout -b %s %s' % (hgbranch[str(cset)], hgvers[parent]))
 203        else:
 204            print 'checking out branch', hgbranch[str(cset)]
 205            os.system('git checkout %s' % hgbranch[str(cset)])
 206
 207    # merge
 208    if mparent:
 209        if hgbranch[parent] == hgbranch[str(cset)]:
 210            otherbranch = hgbranch[mparent]
 211        else:
 212            otherbranch = hgbranch[parent]
 213        print 'merging', otherbranch, 'into', hgbranch[str(cset)]
 214        os.system(getgitenv(user, date) + 'git merge --no-commit -s ours "" %s %s' % (hgbranch[str(cset)], otherbranch))
 215
 216    # remove everything except .git and .hg directories
 217    os.system('find . \( -path "./.hg" -o -path "./.git" \) -prune -o ! -name "." -print | xargs rm -rf')
 218
 219    # repopulate with checkouted files
 220    os.system('hg update -C %d' % cset)
 221
 222    # add new files
 223    os.system('git ls-files -x .hg --others | git update-index --add --stdin')
 224    # delete removed files
 225    os.system('git ls-files -x .hg --deleted | git update-index --remove --stdin')
 226
 227    # commit
 228    os.system(getgitenv(user, date) + 'git commit --allow-empty -a -F %s' % filecomment)
 229    os.unlink(filecomment)
 230
 231    # tag
 232    if tag and tag != 'tip':
 233        os.system(getgitenv(user, date) + 'git tag %s' % tag)
 234
 235    # delete branch if not used anymore...
 236    if mparent and len(hgchildren[str(cset)]):
 237        print "Deleting unused branch:", otherbranch
 238        os.system('git branch -d %s' % otherbranch)
 239
 240    # retrieve and record the version
 241    vvv = os.popen('git show --quiet --pretty=format:%H').read()
 242    print 'record', cset, '->', vvv
 243    hgvers[str(cset)] = vvv
 244
 245if hgnewcsets >= opt_nrepack and opt_nrepack != -1:
 246    os.system('git repack -a -d')
 247
 248# write the state for incrementals
 249if state:
 250    if verbose:
 251        print 'Writing state'
 252    f = open(state, 'w')
 253    pickle.dump(hgvers, f)
 254
 255# vim: et ts=8 sw=4 sts=4