convert: use 'default' for specifying branch name in branchmap (issue4753)

A fix for issue2653 with 1d155582a8ea introduced a discrepancy how default
branch should be denoted when converting with branchmap from different SCM.
E.g. for Git and Mercurial you need to use 'default' whilst for Perforce and
SVN you had to use 'None'. This changeset unifies 'default' for such purposes
whilst falling back to 'None' when no 'default' mapping specified.

hgext/convert/convcmd.py

@@ -1,548 +1,576 b''
 # convcmd - convert extension commands definition
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from common import NoRepo, MissingTool, SKIPREV, mapfile
 from cvs import convert_cvs
 from darcs import darcs_source
 from git import convert_git
 from hg import mercurial_source, mercurial_sink
 from subversion import svn_source, svn_sink
 from monotone import monotone_source
 from gnuarch import gnuarch_source
 from bzr import bzr_source
 from p4 import p4_source
 import filemap
 
 import os, shutil, shlex
 from mercurial import hg, util, encoding
 from mercurial.i18n import _
 
 orig_encoding = 'ascii'
 
 def recode(s):
     if isinstance(s, unicode):
         return s.encode(orig_encoding, 'replace')
     else:
         return s.decode('utf-8').encode(orig_encoding, 'replace')
 
+def mapbranch(branch, branchmap):
+    '''
+    >>> bmap = {'default': 'branch1'}
+    >>> for i in ['', None]:
+    ...     mapbranch(i, bmap)
+    'branch1'
+    'branch1'
+    >>> bmap = {'None': 'branch2'}
+    >>> for i in ['', None]:
+    ...     mapbranch(i, bmap)
+    'branch2'
+    'branch2'
+    >>> bmap = {'None': 'branch3', 'default': 'branch4'}
+    >>> for i in ['None', '', None, 'default', 'branch5']:
+    ...     mapbranch(i, bmap)
+    'branch3'
+    'branch4'
+    'branch4'
+    'branch4'
+    'branch5'
+    '''
+    # If branch is None or empty, this commit is coming from the source
+    # repository's default branch and destined for the default branch in the
+    # destination repository. For such commits, using a literal "default"
+    # in branchmap below allows the user to map "default" to an alternate
+    # default branch in the destination repository.
+    branch = branchmap.get(branch or 'default', branch)
+    # At some point we used "None" literal to denote the default branch,
+    # attempt to use that for backward compatibility.
+    if (not branch):
+        branch = branchmap.get(str(None), branch)
+    return branch
+
 source_converters = [
     ('cvs', convert_cvs, 'branchsort'),
     ('git', convert_git, 'branchsort'),
     ('svn', svn_source, 'branchsort'),
     ('hg', mercurial_source, 'sourcesort'),
     ('darcs', darcs_source, 'branchsort'),
     ('mtn', monotone_source, 'branchsort'),
     ('gnuarch', gnuarch_source, 'branchsort'),
     ('bzr', bzr_source, 'branchsort'),
     ('p4', p4_source, 'branchsort'),
     ]
 
 sink_converters = [
     ('hg', mercurial_sink),
     ('svn', svn_sink),
     ]
 
 def convertsource(ui, path, type, revs):
     exceptions = []
     if type and type not in [s[0] for s in source_converters]:
         raise util.Abort(_('%s: invalid source repository type') % type)
     for name, source, sortmode in source_converters:
         try:
             if not type or name == type:
                 return source(ui, path, revs), sortmode
         except (NoRepo, MissingTool) as inst:
             exceptions.append(inst)
     if not ui.quiet:
         for inst in exceptions:
             ui.write("%s\n" % inst)
     raise util.Abort(_('%s: missing or unsupported repository') % path)
 
 def convertsink(ui, path, type):
     if type and type not in [s[0] for s in sink_converters]:
         raise util.Abort(_('%s: invalid destination repository type') % type)
     for name, sink in sink_converters:
         try:
             if not type or name == type:
                 return sink(ui, path)
         except NoRepo as inst:
             ui.note(_("convert: %s\n") % inst)
         except MissingTool as inst:
             raise util.Abort('%s\n' % inst)
     raise util.Abort(_('%s: unknown repository type') % path)
 
 class progresssource(object):
     def __init__(self, ui, source, filecount):
         self.ui = ui
         self.source = source
         self.filecount = filecount
         self.retrieved = 0
 
     def getfile(self, file, rev):
         self.retrieved += 1
         self.ui.progress(_('getting files'), self.retrieved,
                          item=file, total=self.filecount)
         return self.source.getfile(file, rev)
 
     def lookuprev(self, rev):
         return self.source.lookuprev(rev)
 
     def close(self):
         self.ui.progress(_('getting files'), None)
 
 class converter(object):
     def __init__(self, ui, source, dest, revmapfile, opts):
 
         self.source = source
         self.dest = dest
         self.ui = ui
         self.opts = opts
         self.commitcache = {}
         self.authors = {}
         self.authorfile = None
 
         # Record converted revisions persistently: maps source revision
         # ID to target revision ID (both strings).  (This is how
         # incremental conversions work.)
         self.map = mapfile(ui, revmapfile)
 
         # Read first the dst author map if any
         authorfile = self.dest.authorfile()
         if authorfile and os.path.exists(authorfile):
             self.readauthormap(authorfile)
         # Extend/Override with new author map if necessary
         if opts.get('authormap'):
             self.readauthormap(opts.get('authormap'))
             self.authorfile = self.dest.authorfile()
 
         self.splicemap = self.parsesplicemap(opts.get('splicemap'))
         self.branchmap = mapfile(ui, opts.get('branchmap'))
 
     def parsesplicemap(self, path):
         """ check and validate the splicemap format and
             return a child/parents dictionary.
             Format checking has two parts.
             1. generic format which is same across all source types
             2. specific format checking which may be different for
                different source type.  This logic is implemented in
                checkrevformat function in source files like
                hg.py, subversion.py etc.
         """
 
         if not path:
             return {}
         m = {}
         try:
             fp = open(path, 'r')
             for i, line in enumerate(fp):
                 line = line.splitlines()[0].rstrip()
                 if not line:
                     # Ignore blank lines
                     continue
                 # split line
                 lex = shlex.shlex(line, posix=True)
                 lex.whitespace_split = True
                 lex.whitespace += ','
                 line = list(lex)
                 # check number of parents
                 if not (2 <= len(line) <= 3):
                     raise util.Abort(_('syntax error in %s(%d): child parent1'
                                        '[,parent2] expected') % (path, i + 1))
                 for part in line:
                     self.source.checkrevformat(part)
                 child, p1, p2 = line[0], line[1:2], line[2:]
                 if p1 == p2:
                     m[child] = p1
                 else:
                     m[child] = p1 + p2
          # if file does not exist or error reading, exit
         except IOError:
             raise util.Abort(_('splicemap file not found or error reading %s:')
                                % path)
         return m
 
 
     def walktree(self, heads):
         '''Return a mapping that identifies the uncommitted parents of every
         uncommitted changeset.'''
         visit = heads
         known = set()
         parents = {}
         numcommits = self.source.numcommits()
         while visit:
             n = visit.pop(0)
             if n in known:
                 continue
             if n in self.map:
                 m = self.map[n]
                 if m == SKIPREV or self.dest.hascommitfrommap(m):
                     continue
             known.add(n)
             self.ui.progress(_('scanning'), len(known), unit=_('revisions'),
                              total=numcommits)
             commit = self.cachecommit(n)
             parents[n] = []
             for p in commit.parents:
                 parents[n].append(p)
                 visit.append(p)
         self.ui.progress(_('scanning'), None)
 
         return parents
 
     def mergesplicemap(self, parents, splicemap):
         """A splicemap redefines child/parent relationships. Check the
         map contains valid revision identifiers and merge the new
         links in the source graph.
         """
         for c in sorted(splicemap):
             if c not in parents:
                 if not self.dest.hascommitforsplicemap(self.map.get(c, c)):
                     # Could be in source but not converted during this run
                     self.ui.warn(_('splice map revision %s is not being '
                                    'converted, ignoring\n') % c)
                 continue
             pc = []
             for p in splicemap[c]:
                 # We do not have to wait for nodes already in dest.
                 if self.dest.hascommitforsplicemap(self.map.get(p, p)):
                     continue
                 # Parent is not in dest and not being converted, not good
                 if p not in parents:
                     raise util.Abort(_('unknown splice map parent: %s') % p)
                 pc.append(p)
             parents[c] = pc
 
     def toposort(self, parents, sortmode):
         '''Return an ordering such that every uncommitted changeset is
         preceded by all its uncommitted ancestors.'''
 
         def mapchildren(parents):
             """Return a (children, roots) tuple where 'children' maps parent
             revision identifiers to children ones, and 'roots' is the list of
             revisions without parents. 'parents' must be a mapping of revision
             identifier to its parents ones.
             """
             visit = sorted(parents)
             seen = set()
             children = {}
             roots = []
 
             while visit:
                 n = visit.pop(0)
                 if n in seen:
                     continue
                 seen.add(n)
                 # Ensure that nodes without parents are present in the
                 # 'children' mapping.
                 children.setdefault(n, [])
                 hasparent = False
                 for p in parents[n]:
                     if p not in self.map:
                         visit.append(p)
                         hasparent = True
                     children.setdefault(p, []).append(n)
                 if not hasparent:
                     roots.append(n)
 
             return children, roots
 
         # Sort functions are supposed to take a list of revisions which
         # can be converted immediately and pick one
 
         def makebranchsorter():
             """If the previously converted revision has a child in the
             eligible revisions list, pick it. Return the list head
             otherwise. Branch sort attempts to minimize branch
             switching, which is harmful for Mercurial backend
             compression.
             """
             prev = [None]
             def picknext(nodes):
                 next = nodes[0]
                 for n in nodes:
                     if prev[0] in parents[n]:
                         next = n
                         break
                 prev[0] = next
                 return next
             return picknext
 
         def makesourcesorter():
             """Source specific sort."""
             keyfn = lambda n: self.commitcache[n].sortkey
             def picknext(nodes):
                 return sorted(nodes, key=keyfn)[0]
             return picknext
 
         def makeclosesorter():
             """Close order sort."""
             keyfn = lambda n: ('close' not in self.commitcache[n].extra,
                                self.commitcache[n].sortkey)
             def picknext(nodes):
                 return sorted(nodes, key=keyfn)[0]
             return picknext
 
         def makedatesorter():
             """Sort revisions by date."""
             dates = {}
             def getdate(n):
                 if n not in dates:
                     dates[n] = util.parsedate(self.commitcache[n].date)
                 return dates[n]
 
             def picknext(nodes):
                 return min([(getdate(n), n) for n in nodes])[1]
 
             return picknext
 
         if sortmode == 'branchsort':
             picknext = makebranchsorter()
         elif sortmode == 'datesort':
             picknext = makedatesorter()
         elif sortmode == 'sourcesort':
             picknext = makesourcesorter()
         elif sortmode == 'closesort':
             picknext = makeclosesorter()
         else:
             raise util.Abort(_('unknown sort mode: %s') % sortmode)
 
         children, actives = mapchildren(parents)
 
         s = []
         pendings = {}
         while actives:
             n = picknext(actives)
             actives.remove(n)
             s.append(n)
 
             # Update dependents list
             for c in children.get(n, []):
                 if c not in pendings:
                     pendings[c] = [p for p in parents[c] if p not in self.map]
                 try:
                     pendings[c].remove(n)
                 except ValueError:
                     raise util.Abort(_('cycle detected between %s and %s')
                                        % (recode(c), recode(n)))
                 if not pendings[c]:
                     # Parents are converted, node is eligible
                     actives.insert(0, c)
                     pendings[c] = None
 
         if len(s) != len(parents):
             raise util.Abort(_("not all revisions were sorted"))
 
         return s
 
     def writeauthormap(self):
         authorfile = self.authorfile
         if authorfile:
             self.ui.status(_('writing author map file %s\n') % authorfile)
             ofile = open(authorfile, 'w+')
             for author in self.authors:
                 ofile.write("%s=%s\n" % (author, self.authors[author]))
             ofile.close()
 
     def readauthormap(self, authorfile):
         afile = open(authorfile, 'r')
         for line in afile:
 
             line = line.strip()
             if not line or line.startswith('#'):
                 continue
 
             try:
                 srcauthor, dstauthor = line.split('=', 1)
             except ValueError:
                 msg = _('ignoring bad line in author map file %s: %s\n')
                 self.ui.warn(msg % (authorfile, line.rstrip()))
                 continue
 
             srcauthor = srcauthor.strip()
             dstauthor = dstauthor.strip()
             if self.authors.get(srcauthor) in (None, dstauthor):
                 msg = _('mapping author %s to %s\n')
                 self.ui.debug(msg % (srcauthor, dstauthor))
                 self.authors[srcauthor] = dstauthor
                 continue
 
             m = _('overriding mapping for author %s, was %s, will be %s\n')
             self.ui.status(m % (srcauthor, self.authors[srcauthor], dstauthor))
 
         afile.close()
 
     def cachecommit(self, rev):
         commit = self.source.getcommit(rev)
         commit.author = self.authors.get(commit.author, commit.author)
-        # If commit.branch is None, this commit is coming from the source
-        # repository's default branch and destined for the default branch in the
-        # destination repository. For such commits, passing a literal "None"
-        # string to branchmap.get() below allows the user to map "None" to an
-        # alternate default branch in the destination repository.
-        commit.branch = self.branchmap.get(str(commit.branch), commit.branch)
+        commit.branch = mapbranch(commit.branch, self.branchmap)
         self.commitcache[rev] = commit
         return commit
 
     def copy(self, rev):
         commit = self.commitcache[rev]
         full = self.opts.get('full')
         changes = self.source.getchanges(rev, full)
         if isinstance(changes, basestring):
             if changes == SKIPREV:
                 dest = SKIPREV
             else:
                 dest = self.map[changes]
             self.map[rev] = dest
             return
         files, copies, cleanp2 = changes
         pbranches = []
         if commit.parents:
             for prev in commit.parents:
                 if prev not in self.commitcache:
                     self.cachecommit(prev)
                 pbranches.append((self.map[prev],
                                   self.commitcache[prev].branch))
         self.dest.setbranch(commit.branch, pbranches)
         try:
             parents = self.splicemap[rev]
             self.ui.status(_('spliced in %s as parents of %s\n') %
                            (parents, rev))
             parents = [self.map.get(p, p) for p in parents]
         except KeyError:
             parents = [b[0] for b in pbranches]
         if len(pbranches) != 2:
             cleanp2 = set()
         if len(parents) < 3:
             source = progresssource(self.ui, self.source, len(files))
         else:
             # For an octopus merge, we end up traversing the list of
             # changed files N-1 times. This tweak to the number of
             # files makes it so the progress bar doesn't overflow
             # itself.
             source = progresssource(self.ui, self.source,
                                     len(files) * (len(parents) - 1))
         newnode = self.dest.putcommit(files, copies, parents, commit,
                                       source, self.map, full, cleanp2)
         source.close()
         self.source.converted(rev, newnode)
         self.map[rev] = newnode
 
     def convert(self, sortmode):
         try:
             self.source.before()
             self.dest.before()
             self.source.setrevmap(self.map)
             self.ui.status(_("scanning source...\n"))
             heads = self.source.getheads()
             parents = self.walktree(heads)
             self.mergesplicemap(parents, self.splicemap)
             self.ui.status(_("sorting...\n"))
             t = self.toposort(parents, sortmode)
             num = len(t)
             c = None
 
             self.ui.status(_("converting...\n"))
             for i, c in enumerate(t):
                 num -= 1
                 desc = self.commitcache[c].desc
                 if "\n" in desc:
                     desc = desc.splitlines()[0]
                 # convert log message to local encoding without using
                 # tolocal() because the encoding.encoding convert()
                 # uses is 'utf-8'
                 self.ui.status("%d %s\n" % (num, recode(desc)))
                 self.ui.note(_("source: %s\n") % recode(c))
                 self.ui.progress(_('converting'), i, unit=_('revisions'),
                                  total=len(t))
                 self.copy(c)
             self.ui.progress(_('converting'), None)
 
             if not self.ui.configbool('convert', 'skiptags'):
                 tags = self.source.gettags()
                 ctags = {}
                 for k in tags:
                     v = tags[k]
                     if self.map.get(v, SKIPREV) != SKIPREV:
                         ctags[k] = self.map[v]
 
                 if c and ctags:
                     nrev, tagsparent = self.dest.puttags(ctags)
                     if nrev and tagsparent:
                         # write another hash correspondence to override the
                         # previous one so we don't end up with extra tag heads
                         tagsparents = [e for e in self.map.iteritems()
                                        if e[1] == tagsparent]
                         if tagsparents:
                             self.map[tagsparents[0][0]] = nrev
 
             bookmarks = self.source.getbookmarks()
             cbookmarks = {}
             for k in bookmarks:
                 v = bookmarks[k]
                 if self.map.get(v, SKIPREV) != SKIPREV:
                     cbookmarks[k] = self.map[v]
 
             if c and cbookmarks:
                 self.dest.putbookmarks(cbookmarks)
 
             self.writeauthormap()
         finally:
             self.cleanup()
 
     def cleanup(self):
         try:
             self.dest.after()
         finally:
             self.source.after()
         self.map.close()
 
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     global orig_encoding
     orig_encoding = encoding.encoding
     encoding.encoding = 'UTF-8'
 
     # support --authors as an alias for --authormap
     if not opts.get('authormap'):
         opts['authormap'] = opts.get('authors')
 
     if not dest:
         dest = hg.defaultdest(src) + "-hg"
         ui.status(_("assuming destination %s\n") % dest)
 
     destc = convertsink(ui, dest, opts.get('dest_type'))
 
     try:
         srcc, defaultsort = convertsource(ui, src, opts.get('source_type'),
                                           opts.get('rev'))
     except Exception:
         for path in destc.created:
             shutil.rmtree(path, True)
         raise
 
     sortmodes = ('branchsort', 'datesort', 'sourcesort', 'closesort')
     sortmode = [m for m in sortmodes if opts.get(m)]
     if len(sortmode) > 1:
         raise util.Abort(_('more than one sort mode specified'))
     if sortmode:
         sortmode = sortmode[0]
     else:
         sortmode = defaultsort
 
     if sortmode == 'sourcesort' and not srcc.hasnativeorder():
         raise util.Abort(_('--sourcesort is not supported by this data source'))
     if sortmode == 'closesort' and not srcc.hasnativeclose():
         raise util.Abort(_('--closesort is not supported by this data source'))
 
     fmap = opts.get('filemap')
     if fmap:
         srcc = filemap.filemap_source(ui, srcc, fmap)
         destc.setfilemapmode(True)
 
     if not revmapfile:
         revmapfile = destc.revmapfile()
 
     c = converter(ui, srcc, destc, revmapfile, opts)
     c.convert(sortmode)

hgext/convert/p4.py

@@ -1,284 +1,284 b''
 # Perforce source for convert extension.
 #
 # Copyright 2009, Frank Kingswood <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from mercurial import util
 from mercurial.i18n import _
 
 from common import commit, converter_source, checktool, NoRepo
 import marshal
 import re
 
 def loaditer(f):
     "Yield the dictionary objects generated by p4"
     try:
         while True:
             d = marshal.load(f)
             if not d:
                 break
             yield d
     except EOFError:
         pass
 
 def decodefilename(filename):
     """Perforce escapes special characters @, #, *, or %
     with %40, %23, %2A, or %25 respectively
 
     >>> decodefilename('portable-net45%252Bnetcore45%252Bwp8%252BMonoAndroid')
     'portable-net45%2Bnetcore45%2Bwp8%2BMonoAndroid'
     >>> decodefilename('//Depot/Directory/%2525/%2523/%23%40.%2A')
     '//Depot/Directory/%25/%23/#@.*'
     """
     replacements = [('%2A', '*'), ('%23', '#'), ('%40', '@'), ('%25', '%')]
     for k, v in replacements:
         filename = filename.replace(k, v)
     return filename
 
 class p4_source(converter_source):
     def __init__(self, ui, path, revs=None):
         super(p4_source, self).__init__(ui, path, revs=revs)
 
         if "/" in path and not path.startswith('//'):
             raise NoRepo(_('%s does not look like a P4 repository') % path)
 
         checktool('p4', abort=False)
 
         self.p4changes = {}
         self.heads = {}
         self.changeset = {}
         self.files = {}
         self.copies = {}
         self.tags = {}
         self.lastbranch = {}
         self.parent = {}
         self.encoding = "latin_1"
         self.depotname = {}           # mapping from local name to depot name
         self.localname = {} # mapping from depot name to local name
         self.re_type = re.compile(
             "([a-z]+)?(text|binary|symlink|apple|resource|unicode|utf\d+)"
             "(\+\w+)?$")
         self.re_keywords = re.compile(
             r"\$(Id|Header|Date|DateTime|Change|File|Revision|Author)"
             r":[^$\n]*\$")
         self.re_keywords_old = re.compile("\$(Id|Header):[^$\n]*\$")
 
         if revs and len(revs) > 1:
             raise util.Abort(_("p4 source does not support specifying "
                                "multiple revisions"))
         self._parse(ui, path)
 
     def _parse_view(self, path):
         "Read changes affecting the path"
         cmd = 'p4 -G changes -s submitted %s' % util.shellquote(path)
         stdout = util.popen(cmd, mode='rb')
         for d in loaditer(stdout):
             c = d.get("change", None)
             if c:
                 self.p4changes[c] = True
 
     def _parse(self, ui, path):
         "Prepare list of P4 filenames and revisions to import"
         ui.status(_('reading p4 views\n'))
 
         # read client spec or view
         if "/" in path:
             self._parse_view(path)
             if path.startswith("//") and path.endswith("/..."):
                 views = {path[:-3]:""}
             else:
                 views = {"//": ""}
         else:
             cmd = 'p4 -G client -o %s' % util.shellquote(path)
             clientspec = marshal.load(util.popen(cmd, mode='rb'))
 
             views = {}
             for client in clientspec:
                 if client.startswith("View"):
                     sview, cview = clientspec[client].split()
                     self._parse_view(sview)
                     if sview.endswith("...") and cview.endswith("..."):
                         sview = sview[:-3]
                         cview = cview[:-3]
                     cview = cview[2:]
                     cview = cview[cview.find("/") + 1:]
                     views[sview] = cview
 
         # list of changes that affect our source files
         self.p4changes = self.p4changes.keys()
         self.p4changes.sort(key=int)
 
         # list with depot pathnames, longest first
         vieworder = views.keys()
         vieworder.sort(key=len, reverse=True)
 
         # handle revision limiting
         startrev = self.ui.config('convert', 'p4.startrev', default=0)
         self.p4changes = [x for x in self.p4changes
                           if ((not startrev or int(x) >= int(startrev)) and
                               (not self.revs or int(x) <= int(self.revs[0])))]
 
         # now read the full changelists to get the list of file revisions
         ui.status(_('collecting p4 changelists\n'))
         lastid = None
         for change in self.p4changes:
             cmd = "p4 -G describe -s %s" % change
             stdout = util.popen(cmd, mode='rb')
             d = marshal.load(stdout)
             desc = self.recode(d.get("desc", ""))
             shortdesc = desc.split("\n", 1)[0]
             t = '%s %s' % (d["change"], repr(shortdesc)[1:-1])
             ui.status(util.ellipsis(t, 80) + '\n')
 
             if lastid:
                 parents = [lastid]
             else:
                 parents = []
 
             date = (int(d["time"]), 0)     # timezone not set
             c = commit(author=self.recode(d["user"]),
                        date=util.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'),
-                       parents=parents, desc=desc, branch='',
+                       parents=parents, desc=desc, branch=None,
                        extra={"p4": change})
 
             files = []
             copies = {}
             copiedfiles = []
             i = 0
             while ("depotFile%d" % i) in d and ("rev%d" % i) in d:
                 oldname = d["depotFile%d" % i]
                 filename = None
                 for v in vieworder:
                     if oldname.lower().startswith(v.lower()):
                         filename = decodefilename(views[v] + oldname[len(v):])
                         break
                 if filename:
                     files.append((filename, d["rev%d" % i]))
                     self.depotname[filename] = oldname
                     if (d.get("action%d" % i) == "move/add"):
                         copiedfiles.append(filename)
                     self.localname[oldname] = filename
                 i += 1
 
             # Collect information about copied files
             for filename in copiedfiles:
                 oldname = self.depotname[filename]
 
                 flcmd = 'p4 -G filelog %s' \
                       % util.shellquote(oldname)
                 flstdout = util.popen(flcmd, mode='rb')
 
                 copiedfilename = None
                 for d in loaditer(flstdout):
                     copiedoldname = None
 
                     i = 0
                     while ("change%d" % i) in d:
                         if (d["change%d" % i] == change and
                             d["action%d" % i] == "move/add"):
                             j = 0
                             while ("file%d,%d" % (i, j)) in d:
                                 if d["how%d,%d" % (i, j)] == "moved from":
                                     copiedoldname = d["file%d,%d" % (i, j)]
                                     break
                                 j += 1
                         i += 1
 
                     if copiedoldname and copiedoldname in self.localname:
                         copiedfilename = self.localname[copiedoldname]
                         break
 
                 if copiedfilename:
                     copies[filename] = copiedfilename
                 else:
                     ui.warn(_("cannot find source for copied file: %s@%s\n")
                             % (filename, change))
 
             self.changeset[change] = c
             self.files[change] = files
             self.copies[change] = copies
             lastid = change
 
         if lastid:
             self.heads = [lastid]
 
     def getheads(self):
         return self.heads
 
     def getfile(self, name, rev):
         cmd = 'p4 -G print %s' \
             % util.shellquote("%s#%s" % (self.depotname[name], rev))
 
         lasterror = None
         while True:
             stdout = util.popen(cmd, mode='rb')
 
             mode = None
             contents = ""
             keywords = None
 
             for d in loaditer(stdout):
                 code = d["code"]
                 data = d.get("data")
 
                 if code == "error":
                     # if this is the first time error happened
                     # re-attempt getting the file
                     if not lasterror:
                         lasterror = IOError(d["generic"], data)
                         # this will exit inner-most for-loop
                         break
                     else:
                         raise lasterror
 
                 elif code == "stat":
                     action = d.get("action")
                     if action in ["purge", "delete", "move/delete"]:
                         return None, None
                     p4type = self.re_type.match(d["type"])
                     if p4type:
                         mode = ""
                         flags = ((p4type.group(1) or "")
                                + (p4type.group(3) or ""))
                         if "x" in flags:
                             mode = "x"
                         if p4type.group(2) == "symlink":
                             mode = "l"
                         if "ko" in flags:
                             keywords = self.re_keywords_old
                         elif "k" in flags:
                             keywords = self.re_keywords
 
                 elif code == "text" or code == "binary":
                     contents += data
 
                 lasterror = None
 
             if not lasterror:
                 break
 
         if mode is None:
             return None, None
 
         if keywords:
             contents = keywords.sub("$\\1$", contents)
         if mode == "l" and contents.endswith("\n"):
             contents = contents[:-1]
 
         return contents, mode
 
     def getchanges(self, rev, full):
         if full:
             raise util.Abort(_("convert from p4 do not support --full"))
         return self.files[rev], self.copies[rev], set()
 
     def getcommit(self, rev):
         return self.changeset[rev]
 
     def gettags(self):
         return self.tags
 
     def getchangedfiles(self, rev, i):
         return sorted([x[0] for x in self.files[rev]])

tests/test-convert-svn-branches.t

@@ -1,129 +1,128 b''
 #require svn svn-bindings
 
   $ cat >> $HGRCPATH <<EOF
   > [extensions]
   > convert =
   > EOF
 
   $ svnadmin create svn-repo
   $ svnadmin load -q svn-repo < "$TESTDIR/svn/branches.svndump"
 
 Convert trunk and branches
 
   $ cat > branchmap <<EOF
   > old3 newbranch
   > 
   > 
   > EOF
   $ hg convert --branchmap=branchmap --datesort -r 10 svn-repo A-hg
   initializing destination A-hg repository
   scanning source...
   sorting...
   converting...
   10 init projA
   9 hello
   8 branch trunk, remove c and dir
   7 change a
   6 change b
   5 move and update c
   4 move and update c
   3 change b again
   2 move to old2
   1 move back to old
   0 last change to a
 
 Test template keywords
 
   $ hg -R A-hg log --template '{rev} {svnuuid}{svnpath}@{svnrev}\n'
   10 644ede6c-2b81-4367-9dc8-d786514f2cde/trunk@10
   9 644ede6c-2b81-4367-9dc8-d786514f2cde/branches/old@9
   8 644ede6c-2b81-4367-9dc8-d786514f2cde/branches/old2@8
   7 644ede6c-2b81-4367-9dc8-d786514f2cde/branches/old@7
   6 644ede6c-2b81-4367-9dc8-d786514f2cde/trunk@6
   5 644ede6c-2b81-4367-9dc8-d786514f2cde/branches/old@6
   4 644ede6c-2b81-4367-9dc8-d786514f2cde/branches/old@5
   3 644ede6c-2b81-4367-9dc8-d786514f2cde/trunk@4
   2 644ede6c-2b81-4367-9dc8-d786514f2cde/branches/old@3
   1 644ede6c-2b81-4367-9dc8-d786514f2cde/trunk@2
   0 644ede6c-2b81-4367-9dc8-d786514f2cde/trunk@1
 
 Convert again
 
   $ hg convert --branchmap=branchmap --datesort svn-repo A-hg
   scanning source...
   sorting...
   converting...
   0 branch trunk@1 into old3
 
   $ cd A-hg
   $ hg log -G --template 'branch={branches} {rev} {desc|firstline} files: {files}\n'
   o  branch=newbranch 11 branch trunk@1 into old3 files:
   |
   | o  branch= 10 last change to a files: a
   | |
   | | o  branch=old 9 move back to old files:
   | | |
   | | o  branch=old2 8 move to old2 files:
   | | |
   | | o  branch=old 7 change b again files: b
   | | |
   | o |  branch= 6 move and update c files: b
   | | |
   | | o  branch=old 5 move and update c files: c
   | | |
   | | o  branch=old 4 change b files: b
   | | |
   | o |  branch= 3 change a files: a
   | | |
   | | o  branch=old 2 branch trunk, remove c and dir files: c
   | |/
   | o  branch= 1 hello files: a b c dir/e
   |/
   o  branch= 0 init projA files:
   
 
   $ hg branches
   newbranch                     11:a6d7cc050ad1
   default                       10:6e2b33404495
   old                            9:93c4b0f99529
   old2                           8:b52884d7bead (inactive)
   $ hg tags -q
   tip
   $ cd ..
 
 Test hg failing to call itself
 
   $ HG=foobar hg convert svn-repo B-hg 2>&1 | grep abort
   abort: Mercurial failed to run itself, check hg executable is in PATH
 
 Convert 'trunk' to branch other than 'default'
 
   $ cat > branchmap <<EOF
-  > None hgtrunk
+  > default hgtrunk
   > 
   > 
   > EOF
   $ hg convert --branchmap=branchmap --datesort -r 10 svn-repo C-hg
   initializing destination C-hg repository
   scanning source...
   sorting...
   converting...
   10 init projA
   9 hello
   8 branch trunk, remove c and dir
   7 change a
   6 change b
   5 move and update c
   4 move and update c
   3 change b again
   2 move to old2
   1 move back to old
   0 last change to a
 
   $ cd C-hg
-  $ hg branches
-  hgtrunk                       10:745f063703b4
-  old                            9:aa50d7b8d922
-  old2                           8:c85a22267b6e (inactive)
+  $ hg branches --template '{branch}\n'
+  hgtrunk
+  old
+  old2
   $ cd ..
-

tests/test-doctest.py

@@ -1,38 +1,39 b''
 # this is hack to make sure no escape characters are inserted into the output
 import os, sys
 if 'TERM' in os.environ:
     del os.environ['TERM']
 import doctest
 
 def testmod(name, optionflags=0, testtarget=None):
     __import__(name)
     mod = sys.modules[name]
     if testtarget is not None:
         mod = getattr(mod, testtarget)
     doctest.testmod(mod, optionflags=optionflags)
 
 testmod('mercurial.changelog')
 testmod('mercurial.dagparser', optionflags=doctest.NORMALIZE_WHITESPACE)
 testmod('mercurial.dispatch')
 testmod('mercurial.encoding')
 testmod('mercurial.hg')
 testmod('mercurial.hgweb.hgwebdir_mod')
 testmod('mercurial.match')
 testmod('mercurial.minirst')
 testmod('mercurial.patch')
 testmod('mercurial.pathutil')
 testmod('mercurial.parser')
 testmod('mercurial.revset')
 testmod('mercurial.store')
 testmod('mercurial.subrepo')
 testmod('mercurial.templatefilters')
 testmod('mercurial.templater')
 testmod('mercurial.ui')
 testmod('mercurial.url')
 testmod('mercurial.util')
 testmod('mercurial.util', testtarget='platform')
+testmod('hgext.convert.convcmd')
 testmod('hgext.convert.cvsps')
 testmod('hgext.convert.filemap')
 testmod('hgext.convert.p4')
 testmod('hgext.convert.subversion')
 testmod('hgext.mq')