git/contrib/hg-to-git/hg-to-git.py

   1 #! /usr/bin/python
   2
   3 """ hg-to-svn.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
  22 import os, os.path, sys
  23 import tempfile, popen2, pickle, getopt
  24 import re
  25
  26 # Maps hg version -> git version
  27 hgvers = {}
  28 # List of children for each hg revision
  29 hgchildren = {}
  30 # Current branch for each hg revision
  31 hgbranch = {}
  32
  33 #------------------------------------------------------------------------------
  34
  35 def usage():
  36
  37         print """\
  38 %s: [OPTIONS] <hgprj>
  39
  40 options:
  41     -s, --gitstate=FILE: name of the state to be saved/read
  42                          for incrementals
  43
  44 required:
  45     hgprj:  name of the HG project to import (directory)
  46 """ % sys.argv[0]
  47
  48 #------------------------------------------------------------------------------
  49
  50 def getgitenv(user, date):
  51     env = ''
  52     elems = re.compile('(.*?)\s+<(.*)>').match(user)
  53     if elems:
  54         env += 'export GIT_AUTHOR_NAME="%s" ;' % elems.group(1)
  55         env += 'export GIT_COMMITER_NAME="%s" ;' % elems.group(1)
  56         env += 'export GIT_AUTHOR_EMAIL="%s" ;' % elems.group(2)
  57         env += 'export GIT_COMMITER_EMAIL="%s" ;' % elems.group(2)
  58     else:
  59         env += 'export GIT_AUTHOR_NAME="%s" ;' % user
  60         env += 'export GIT_COMMITER_NAME="%s" ;' % user
  61         env += 'export GIT_AUTHOR_EMAIL= ;'
  62         env += 'export GIT_COMMITER_EMAIL= ;'
  63
  64     env += 'export GIT_AUTHOR_DATE="%s" ;' % date
  65     env += 'export GIT_COMMITTER_DATE="%s" ;' % date
  66     return env
  67
  68 #------------------------------------------------------------------------------
  69
  70 state = ''
  71
  72 try:
  73     opts, args = getopt.getopt(sys.argv[1:], 's:t:', ['gitstate=', 'tempdir='])
  74     for o, a in opts:
  75         if o in ('-s', '--gitstate'):
  76             state = a
  77             state = os.path.abspath(state)
  78
  79     if len(args) != 1:
  80         raise('params')
  81 except:
  82     usage()
  83     sys.exit(1)
  84
  85 hgprj = args[0]
  86 os.chdir(hgprj)
  87
  88 if state:
  89     if os.path.exists(state):
  90         print 'State does exist, reading'
  91         f = open(state, 'r')
  92         hgvers = pickle.load(f)
  93     else:
  94         print 'State does not exist, first run'
  95
  96 tip = os.popen('hg tip | head -1 | cut -f 2 -d :').read().strip()
  97 print 'tip is', tip
  98
  99 # Calculate the branches
 100 print 'analysing the branches...'
 101 hgchildren["0"] = ()
 102 hgbranch["0"] = "master"
 103 for cset in range(1, int(tip) + 1):
 104     hgchildren[str(cset)] = ()
 105     prnts = os.popen('hg log -r %d | grep ^parent: | cut -f 2 -d :' % cset).readlines()
 106     if len(prnts) > 0:
 107         parent = prnts[0].strip()
 108     else:
 109         parent = str(cset - 1)
 110     hgchildren[parent] += ( str(cset), )
 111     if len(prnts) > 1:
 112         mparent = prnts[1].strip()
 113         hgchildren[mparent] += ( str(cset), )
 114     else:
 115         mparent = None
 116
 117     if mparent:
 118         # For merge changesets, take either one, preferably the 'master' branch
 119         if hgbranch[mparent] == 'master':
 120             hgbranch[str(cset)] = 'master'
 121         else:
 122             hgbranch[str(cset)] = hgbranch[parent]
 123     else:
 124         # Normal changesets
 125         # For first children, take the parent branch, for the others create a new branch
 126         if hgchildren[parent][0] == str(cset):
 127             hgbranch[str(cset)] = hgbranch[parent]
 128         else:
 129             hgbranch[str(cset)] = "branch-" + str(cset)
 130
 131 if not hgvers.has_key("0"):
 132     print 'creating repository'
 133     os.system('git-init-db')
 134
 135 # loop through every hg changeset
 136 for cset in range(int(tip) + 1):
 137
 138     # incremental, already seen
 139     if hgvers.has_key(str(cset)):
 140         continue
 141
 142     # get info
 143     prnts = os.popen('hg log -r %d | grep ^parent: | cut -f 2 -d :' % cset).readlines()
 144     if len(prnts) > 0:
 145         parent = prnts[0].strip()
 146     else:
 147         parent = str(cset - 1)
 148     if len(prnts) > 1:
 149         mparent = prnts[1].strip()
 150     else:
 151         mparent = None
 152
 153     (fdcomment, filecomment) = tempfile.mkstemp()
 154     csetcomment = os.popen('hg log -r %d -v | grep -v ^changeset: | grep -v ^parent: | grep -v ^user: | grep -v ^date | grep -v ^files: | grep -v ^description: | grep -v ^tag:' % cset).read().strip()
 155     os.write(fdcomment, csetcomment)
 156     os.close(fdcomment)
 157
 158     date = os.popen('hg log -r %d | grep ^date: | cut -f 2- -d :' % cset).read().strip()
 159
 160     tag = os.popen('hg log -r %d | grep ^tag: | cut -f 2- -d :' % cset).read().strip()
 161
 162     user = os.popen('hg log -r %d | grep ^user: | cut -f 2- -d :' % cset).read().strip()
 163
 164     print '-----------------------------------------'
 165     print 'cset:', cset
 166     print 'branch:', hgbranch[str(cset)]
 167     print 'user:', user
 168     print 'date:', date
 169     print 'comment:', csetcomment
 170     print 'parent:', parent
 171     if mparent:
 172         print 'mparent:', mparent
 173     if tag:
 174         print 'tag:', tag
 175     print '-----------------------------------------'
 176
 177     # checkout the parent if necessary
 178     if cset != 0:
 179         if hgbranch[str(cset)] == "branch-" + str(cset):
 180             print 'creating new branch', hgbranch[str(cset)]
 181             os.system('git-checkout -b %s %s' % (hgbranch[str(cset)], hgvers[parent]))
 182         else:
 183             print 'checking out branch', hgbranch[str(cset)]
 184             os.system('git-checkout %s' % hgbranch[str(cset)])
 185
 186     # merge
 187     if mparent:
 188         if hgbranch[parent] == hgbranch[str(cset)]:
 189             otherbranch = hgbranch[mparent]
 190         else:
 191             otherbranch = hgbranch[parent]
 192         print 'merging', otherbranch, 'into', hgbranch[str(cset)]
 193         os.system(getgitenv(user, date) + 'git-merge --no-commit -s ours "" %s %s' % (hgbranch[str(cset)], otherbranch))
 194
 195     # remove everything except .git and .hg directories
 196     os.system('find . \( -path "./.hg" -o -path "./.git" \) -prune -o ! -name "." -print | xargs rm -rf')
 197
 198     # repopulate with checkouted files
 199     os.system('hg update -C %d' % cset)
 200
 201     # add new files
 202     os.system('git-ls-files -x .hg --others | git-update-index --add --stdin')
 203     # delete removed files
 204     os.system('git-ls-files -x .hg --deleted | git-update-index --remove --stdin')
 205
 206     # commit
 207     os.system(getgitenv(user, date) + 'git-commit -a -F %s' % filecomment)
 208     os.unlink(filecomment)
 209
 210     # tag
 211     if tag and tag != 'tip':
 212         os.system(getgitenv(user, date) + 'git-tag %s' % tag)
 213
 214     # delete branch if not used anymore...
 215     if mparent and len(hgchildren[str(cset)]):
 216         print "Deleting unused branch:", otherbranch
 217         os.system('git-branch -d %s' % otherbranch)
 218
 219     # retrieve and record the version
 220     vvv = os.popen('git-show | head -1').read()
 221     vvv = vvv[vvv.index(' ') + 1 : ].strip()
 222     print 'record', cset, '->', vvv
 223     hgvers[str(cset)] = vvv
 224
 225 os.system('git-repack -a -d')
 226
 227 # write the state for incrementals
 228 if state:
 229     print 'Writing state'
 230     f = open(state, 'w')
 231     pickle.dump(hgvers, f)
 232
 233 # vim: et ts=8 sw=4 sts=4