Add hg2git.py with library routines

Unfortunately, I can't do 'import hg-fast-export' from python itself, so
we need to move some common methods into 'hg2git.py' which is to be used
as a library for common hg->git routines.

Signed-off-by: Rocco Rutte <pdmef@gmx.net>

hg-fast-export.py

@@ -4,6 +4,7 @@
 # License: MIT <http://www.opensource.org/licenses/mit-license.php>
 
 from mercurial import repo,hg,cmdutil,util,ui,revlog,node
+from hg2git import setup_repo,fixup_user,get_branch,get_changeset,load_cache,save_cache
 from tempfile import mkstemp
 from optparse import OptionParser
 import re
@@ -12,58 +13,11 @@ import os
 
 # silly regex to catch Signed-off-by lines in log message
 sob_re=re.compile('^Signed-[Oo]ff-[Bb]y: (.+)$')
-# silly regex to see if user field has email address
-user_re=re.compile('([^<]+) (<[^>]+>)$')
-# silly regex to clean out user names
-user_clean_re=re.compile('^["]([^"]+)["]$')
-# git branch for hg's default 'HEAD' branch
-cfg_master='master'
 # insert 'checkpoint' command after this many commits or none at all if 0
 cfg_checkpoint_count=0
 # write some progress message every this many file contents written
 cfg_export_boundary=1000
 
-def setup_repo(url):
-  myui=ui.ui()
-  return myui,hg.repository(myui,url)
-
-def fixup_user(user,authors):
-  if authors!=None:
-    # if we have an authors table, try to get mapping
-    # by defaulting to the current value of 'user'
-    user=authors.get(user,user)
-  name,mail,m='','',user_re.match(user)
-  if m==None:
-    # if we don't have 'Name <mail>' syntax, use 'user
-    # <devnull@localhost>' if use contains no at and
-    # 'user <user>' otherwise
-    name=user
-    if '@' not in user:
-      mail='<devnull@localhost>'
-    else:
-      mail='<%s>' % user
-  else:
-    # if we have 'Name <mail>' syntax, everything is fine :)
-    name,mail=m.group(1),m.group(2)
-
-  # remove any silly quoting from username
-  m2=user_clean_re.match(name)
-  if m2!=None:
-    name=m2.group(1)
-  return '%s %s' % (name,mail)
-
-def get_branch(name):
-  if name=='HEAD':
-    name=cfg_master
-  return name
-
-def get_changeset(ui,repo,revision,authors={}):
-  node=repo.lookup(revision)
-  (manifest,user,(time,timezone),files,desc,extra)=repo.changelog.read(node)
-  tz="%+03d%02d" % (-timezone / 3600, ((-timezone % 3600) / 60))
-  branch=get_branch(extra.get('branch','master'))
-  return (node,manifest,fixup_user(user,authors),(time,tz),files,desc,branch,extra)
-
 def gitmode(x):
   return x and '100755' or '100644'
 
@@ -305,28 +259,6 @@ def load_authors(filename):
   sys.stderr.write('Loaded %d authors\n' % l)
   return cache
 
-def load_cache(filename):
-  cache={}
-  if not os.path.exists(filename):
-    return cache
-  f=open(filename,'r')
-  l=0
-  for line in f.readlines():
-    l+=1
-    fields=line.split(' ')
-    if fields==None or not len(fields)==2 or fields[0][0]!=':':
-      sys.stderr.write('Invalid file format in [%s], line %d\n' % (filename,l))
-      continue
-    # put key:value in cache, key without ^:
-    cache[fields[0][1:]]=fields[1].split('\n')[0]
-  f.close()
-  return cache
-
-def save_cache(filename,cache):
-  f=open(filename,'w+')
-  map(lambda x: f.write(':%s %s\n' % (str(x),str(cache.get(x)))),cache.keys())
-  f.close()
-
 def verify_heads(ui,repo,cache,force):
   def getsha1(branch):
     try:

hg2git.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python
+
+# Copyright (c) 2007 Rocco Rutte <pdmef@gmx.net>
+# License: MIT <http://www.opensource.org/licenses/mit-license.php>
+
+from mercurial import repo,hg,cmdutil,util,ui,revlog,node
+import re
+import os
+
+# git branch for hg's default 'HEAD' branch
+cfg_master='master'
+# silly regex to see if user field has email address
+user_re=re.compile('([^<]+) (<[^>]+>)$')
+# silly regex to clean out user names
+user_clean_re=re.compile('^["]([^"]+)["]$')
+
+def setup_repo(url):
+  myui=ui.ui(interactive=False)
+  return myui,hg.repository(myui,url)
+
+def fixup_user(user,authors):
+  if authors!=None:
+    # if we have an authors table, try to get mapping
+    # by defaulting to the current value of 'user'
+    user=authors.get(user,user)
+  name,mail,m='','',user_re.match(user)
+  if m==None:
+    # if we don't have 'Name <mail>' syntax, use 'user
+    # <devnull@localhost>' if use contains no at and
+    # 'user <user>' otherwise
+    name=user
+    if '@' not in user:
+      mail='<devnull@localhost>'
+    else:
+      mail='<%s>' % user
+  else:
+    # if we have 'Name <mail>' syntax, everything is fine :)
+    name,mail=m.group(1),m.group(2)
+
+  # remove any silly quoting from username
+  m2=user_clean_re.match(name)
+  if m2!=None:
+    name=m2.group(1)
+  return '%s %s' % (name,mail)
+
+def get_branch(name):
+  if name=='HEAD':
+    name=cfg_master
+  return name
+
+def get_changeset(ui,repo,revision,authors={}):
+  node=repo.lookup(revision)
+  (manifest,user,(time,timezone),files,desc,extra)=repo.changelog.read(node)
+  tz="%+03d%02d" % (-timezone / 3600, ((-timezone % 3600) / 60))
+  branch=get_branch(extra.get('branch','master'))
+  return (node,manifest,fixup_user(user,authors),(time,tz),files,desc,branch,extra)
+
+def load_cache(filename):
+  cache={}
+  if not os.path.exists(filename):
+    return cache
+  f=open(filename,'r')
+  l=0
+  for line in f.readlines():
+    l+=1
+    fields=line.split(' ')
+    if fields==None or not len(fields)==2 or fields[0][0]!=':':
+      sys.stderr.write('Invalid file format in [%s], line %d\n' % (filename,l))
+      continue
+    # put key:value in cache, key without ^:
+    cache[fields[0][1:]]=fields[1].split('\n')[0]
+  f.close()
+  return cache
+
+def save_cache(filename,cache):
+  f=open(filename,'w+')
+  map(lambda x: f.write(':%s %s\n' % (str(x),str(cache.get(x)))),cache.keys())
+  f.close()