convert: add bzr source

hgext/convert/bzr.py

@@ -0,0 +1,216 b''
+# bzr support for the convert extension
+# This module is for handling 'bzr', that was formerly known as Bazaar-NG;
+# it cannot access 'bar' repositories, but they were never used very much
+
+import os
+from mercurial import demandimport
+# these do not work with demandimport, blacklist
+demandimport.ignore.extend([
+        'bzrlib.transactions',
+        'bzrlib.urlutils',
+    ])
+
+from mercurial.i18n import _
+from mercurial import util
+from common import NoRepo, commit, converter_source
+
+try:
+    # bazaar imports
+    from bzrlib import branch, revision, errors
+    from bzrlib.revisionspec import RevisionSpec
+except ImportError:
+    pass
+
+class bzr_source(converter_source):
+    """Reads Bazaar repositories by using the Bazaar Python libraries"""
+
+    def __init__(self, ui, path, rev=None):
+        super(bzr_source, self).__init__(ui, path, rev=rev)
+
+        try:
+            # access bzrlib stuff
+            branch
+        except NameError:
+            raise NoRepo('Bazaar modules could not be loaded')
+
+        if not os.path.exists(os.path.join(path, '.bzr')):
+            raise NoRepo('%s does not look like a Bazaar repo' % path)
+
+        path = os.path.abspath(path)
+        self.branch = branch.Branch.open(path)
+        self.sourcerepo = self.branch.repository
+        self._parentids = {}
+
+    def before(self):
+        """Before the conversion begins, acquire a read lock
+        for all the operations that might need it. Fortunately
+        read locks don't block other reads or writes to the
+        repository, so this shouldn't have any impact on the usage of
+        the source repository.
+
+        The alternative would be locking on every operation that
+        needs locks (there are currently two: getting the file and
+        getting the parent map) and releasing immediately after,
+        but this approach can take even 40% longer."""
+        self.sourcerepo.lock_read()
+
+    def after(self):
+        self.sourcerepo.unlock()
+
+    def getheads(self):
+        if not self.rev:
+            return [self.branch.last_revision()]
+        try:
+            r = RevisionSpec.from_string(self.rev)
+            info = r.in_history(self.branch)
+        except errors.BzrError:
+            raise util.Abort(_('%s is not a valid revision in current branch')
+                             % self.rev)
+        return [info.rev_id]
+
+    def getfile(self, name, rev):
+        revtree = self.sourcerepo.revision_tree(rev)
+        fileid = revtree.path2id(name)
+        if fileid is None:
+            # the file is not available anymore - was deleted
+            raise IOError(_('%s is not available in %s anymore') %
+                    (name, rev))
+        sio = revtree.get_file(fileid)
+        return sio.read()
+
+    def getmode(self, name, rev):
+        return self._modecache[(name, rev)]
+
+    def getchanges(self, version):
+        # set up caches: modecache and revtree
+        self._modecache = {}
+        self._revtree = self.sourcerepo.revision_tree(version)
+        # get the parentids from the cache
+        parentids = self._parentids.pop(version)
+        # only diff against first parent id
+        prevtree = self.sourcerepo.revision_tree(parentids[0])
+        return self._gettreechanges(self._revtree, prevtree)
+
+    def getcommit(self, version):
+        rev = self.sourcerepo.get_revision(version)
+        # populate parent id cache
+        if not rev.parent_ids:
+            parents = []
+            self._parentids[version] = (revision.NULL_REVISION,)
+        else:
+            parents = self._filterghosts(rev.parent_ids)
+            self._parentids[version] = parents
+
+        return commit(parents=parents,
+                # bzr uses 1 second timezone precision
+                date='%d %d' % (rev.timestamp, rev.timezone / 3600),
+                author=self.recode(rev.committer),
+                # bzr returns bytestrings or unicode, depending on the content
+                desc=self.recode(rev.message),
+                rev=version)
+
+    def gettags(self):
+        if not self.branch.supports_tags():
+            return {}
+        tagdict = self.branch.tags.get_tag_dict()
+        bytetags = {}
+        for name, rev in tagdict.iteritems():
+            bytetags[self.recode(name)] = rev
+        return bytetags
+
+    def getchangedfiles(self, rev, i):
+        self._modecache = {}
+        curtree = self.sourcerepo.revision_tree(rev)
+        parentids = self._parentids.pop(rev)
+        if i is not None:
+            parentid = parentids[i]
+        else:
+            # no parent id, get the empty revision
+            parentid = revision.NULL_REVISION
+
+        prevtree = self.sourcerepo.revision_tree(parentid)
+        changes = [e[0] for e in self._gettreechanges(curtree, prevtree)[0]]
+        return changes
+
+    def _gettreechanges(self, current, origin):
+        revid = current._revision_id;
+        changes = []
+        renames = {}
+        for (fileid, paths, changed_content, versioned, parent, name,
+            kind, executable) in current.iter_changes(origin):
+
+            if paths[0] == u'' or paths[1] == u'':
+                # ignore changes to tree root
+                continue
+
+            # bazaar tracks directories, mercurial does not, so
+            # we have to rename the directory contents
+            if kind[1] == 'directory':
+                if None not in paths and paths[0] != paths[1]:
+                    # neither an add nor an delete - a move
+                    # rename all directory contents manually
+                    subdir = origin.inventory.path2id(paths[0])
+                    # get all child-entries of the directory
+                    for name, entry in origin.inventory.iter_entries(subdir):
+                        # hg does not track directory renames
+                        if entry.kind == 'directory':
+                            continue
+                        frompath = self.recode(paths[0] + '/' + name)
+                        topath = self.recode(paths[1] + '/' + name)
+                        # register the files as changed
+                        changes.append((frompath, revid))
+                        changes.append((topath, revid))
+                        # add to mode cache
+                        mode = ((entry.executable and 'x') or (entry.kind == 'symlink' and 's')
+                                or '')
+                        self._modecache[(topath, revid)] = mode
+                        # register the change as move
+                        renames[topath] = frompath
+
+                # no futher changes, go to the next change
+                continue
+
+            # we got unicode paths, need to convert them
+            path, topath = [self.recode(part) for part in paths]
+
+            if topath is None:
+                # file deleted
+                changes.append((path, revid))
+                continue
+
+            # renamed
+            if path and path != topath:
+                renames[topath] = path
+
+            # populate the mode cache
+            kind, executable = [e[1] for e in (kind, executable)]
+            mode = ((executable and 'x') or (kind == 'symlink' and 's')
+                    or '')
+            self._modecache[(topath, revid)] = mode
+            changes.append((topath, revid))
+
+        return changes, renames
+
+    def _filterghosts(self, ids):
+        """Filters out ghost revisions which hg does not support, see
+        <http://bazaar-vcs.org/GhostRevision>
+        """
+        parentmap = self.sourcerepo.get_parent_map(ids)
+        parents = tuple(parent for parent in ids if parent in parentmap)
+        return parents
+
+    def recode(self, s, encoding=None):
+        """This version of recode tries to encode unicode to bytecode,
+        and preferably using the UTF-8 codec.
+        Other types than Unicode are silently returned, this is by
+        intention, e.g. the None-type is not going to be encoded but instead
+        just passed through
+        """
+        if not encoding:
+            encoding = self.encoding or 'utf-8'
+
+        if isinstance(s, unicode):
+            return s.encode(encoding)
+        else:
+            # leave it alone
+            return s

tests/bzr-definitions

@@ -0,0 +1,18 b''
+# this file holds the definitions that are used in various bzr tests
+
+"$TESTDIR/hghave" bzr || exit 80
+
+echo '[extensions]' >> $HGRCPATH
+echo 'convert = ' >> $HGRCPATH
+echo 'hgext.graphlog = ' >> $HGRCPATH
+
+glog()
+{
+    hg glog --template '#rev# "#desc|firstline#" files: #files#\n' "$@"
+}
+
+manifest()
+{
+    echo "% manifest of $2"
+    hg -R $1 manifest -v -r $2
+}

tests/test-convert-bzr

@@ -0,0 +1,81 b''
+#!/bin/sh
+
+source "$TESTDIR/bzr-definitions"
+
+echo % create and rename on the same file in the same step
+mkdir test-createandrename
+cd test-createandrename
+bzr init -q source
+cd source
+echo a > a
+bzr add -q a
+bzr commit -q -m 'Initial add: a'
+bzr mv a b
+echo a2 >> a
+bzr add -q a
+bzr commit -q -m 'rename a into b, create a'
+cd ..
+hg convert source source-hg
+glog -R source-hg
+echo "% test --rev option"
+hg convert -r 1 source source-1-hg
+glog -R source-1-hg
+cd ..
+
+echo % merge
+mkdir test-merge
+cd test-merge
+
+cat > helper.py <<EOF
+import sys
+from bzrlib import workingtree
+wt = workingtree.WorkingTree.open('.')
+
+message, stamp = sys.argv[1:]
+wt.commit(message, timestamp=int(stamp))
+EOF
+
+bzr init -q source
+cd source
+echo content > a
+echo content2 > b
+bzr add -q a b
+bzr commit -q -m 'Initial add'
+cd ..
+bzr branch -q source source-improve
+cd source
+echo more >> a
+python ../helper.py 'Editing a' 100
+cd ../source-improve
+echo content3 >> b
+python ../helper.py 'Editing b' 200
+cd ../source
+bzr merge -q ../source-improve
+bzr commit -q -m 'Merged improve branch'
+cd ..
+hg convert --datesort source source-hg
+glog -R source-hg
+cd ..
+
+echo % symlinks and executable files
+mkdir test-symlinks
+cd test-symlinks
+bzr init -q source
+cd source
+touch program
+chmod +x program
+ln -s program altname
+bzr add -q altname program
+bzr commit -q -m 'Initial setup'
+touch newprog
+chmod +x newprog
+rm altname
+ln -s newprog altname
+chmod -x program
+bzr add -q newprog
+bzr commit -q -m 'Symlink changed, x bits changed'
+cd ..
+hg convert source source-hg
+manifest source-hg 0
+manifest source-hg tip
+cd ..

tests/test-convert-bzr-directories

@@ -0,0 +1,93 b''
+#!/bin/sh
+
+source "$TESTDIR/bzr-definitions"
+
+echo % empty directory
+mkdir test-empty
+cd test-empty
+bzr init -q source
+cd source
+echo content > a
+bzr add -q a
+bzr commit -q -m 'Initial add'
+mkdir empty
+bzr add -q empty
+bzr commit -q -m 'Empty directory added'
+echo content > empty/something
+bzr add -q empty/something
+bzr commit -q -m 'Added file into directory'
+cd ..
+hg convert source source-hg
+manifest source-hg 1
+manifest source-hg tip
+cd ..
+
+echo % directory renames
+mkdir test-dir-rename
+cd test-dir-rename
+bzr init -q source
+cd source
+mkdir tpyo
+echo content > tpyo/something
+bzr add -q tpyo
+bzr commit -q -m 'Added directory'
+bzr mv tpyo typo
+bzr commit -q -m 'Oops, typo'
+cd ..
+hg convert source source-hg
+manifest source-hg 0
+manifest source-hg tip
+cd ..
+
+echo % nested directory renames
+mkdir test-nested-dir-rename
+cd test-nested-dir-rename
+bzr init -q source
+cd source
+mkdir -p firstlevel/secondlevel/thirdlevel
+echo content > firstlevel/secondlevel/file
+echo this_needs_to_be_there_too > firstlevel/secondlevel/thirdlevel/stuff
+bzr add -q firstlevel
+bzr commit -q -m 'Added nested directories'
+bzr mv firstlevel/secondlevel secondlevel
+bzr commit -q -m 'Moved secondlevel one level up'
+cd ..
+hg convert source source-hg
+manifest source-hg tip
+cd ..
+
+echo % directory remove
+mkdir test-dir-remove
+cd test-dir-remove
+bzr init -q source
+cd source
+mkdir src
+echo content > src/sourcecode
+bzr add -q src
+bzr commit -q -m 'Added directory'
+bzr rm -q src
+bzr commit -q -m 'Removed directory'
+cd ..
+hg convert source source-hg
+manifest source-hg 0
+manifest source-hg tip
+cd ..
+
+echo % directory replace
+mkdir test-dir-replace
+cd test-dir-replace
+bzr init -q source
+cd source
+mkdir first second
+echo content > first/file
+echo morecontent > first/dummy
+echo othercontent > second/something
+bzr add -q first second
+bzr commit -q -m 'Initial layout'
+bzr mv first/file second/file
+bzr mv first third
+bzr commit -q -m 'Some conflicting moves'
+cd ..
+hg convert source source-hg
+manifest source-hg tip
+cd ..

tests/test-convert-bzr-directories.out

@@ -0,0 +1,59 b''
+% empty directory
+initializing destination source-hg repository
+scanning source...
+sorting...
+converting...
+2 Initial add
+1 Empty directory added
+0 Added file into directory
+% manifest of 1
+644   a
+% manifest of tip
+644   a
+644   empty/something
+% directory renames
+tpyo => typo
+initializing destination source-hg repository
+scanning source...
+sorting...
+converting...
+1 Added directory
+0 Oops, typo
+% manifest of 0
+644   tpyo/something
+% manifest of tip
+644   typo/something
+% nested directory renames
+firstlevel/secondlevel => secondlevel
+initializing destination source-hg repository
+scanning source...
+sorting...
+converting...
+1 Added nested directories
+0 Moved secondlevel one level up
+% manifest of tip
+644   secondlevel/file
+644   secondlevel/thirdlevel/stuff
+% directory remove
+initializing destination source-hg repository
+scanning source...
+sorting...
+converting...
+1 Added directory
+0 Removed directory
+% manifest of 0
+644   src/sourcecode
+% manifest of tip
+% directory replace
+first/file => second/file
+first => third
+initializing destination source-hg repository
+scanning source...
+sorting...
+converting...
+1 Initial layout
+0 Some conflicting moves
+% manifest of tip
+644   second/file
+644   second/something
+644   third/dummy

tests/test-convert-bzr-ghosts

@@ -0,0 +1,27 b''
+#!/bin/sh
+
+source "$TESTDIR/bzr-definitions"
+
+cat > ghostcreator.py <<EOF
+import sys
+from bzrlib import workingtree
+wt = workingtree.WorkingTree.open('.')
+
+message, ghostrev = sys.argv[1:]
+wt.set_parent_ids(wt.get_parent_ids() + [ghostrev])
+wt.commit(message)
+EOF
+
+echo % ghost revisions
+mkdir test-ghost-revisions
+cd test-ghost-revisions
+bzr init -q source
+cd source
+echo content > somefile
+bzr add -q somefile
+bzr commit -q -m 'Initial layout setup'
+echo morecontent >> somefile
+python ../../ghostcreator.py 'Commit with ghost revision' ghostrev
+cd ..
+hg convert source source-hg
+glog -R source-hg

tests/test-convert-bzr-ghosts.out

@@ -0,0 +1,11 b''
+% ghost revisions
+initializing destination source-hg repository
+scanning source...
+sorting...
+converting...
+1 Initial layout setup
+0 Commit with ghost revision
+o  1 "Commit with ghost revision" files: somefile
+|
+o  0 "Initial layout setup" files: somefile
+

tests/test-convert-bzr-merges

@@ -0,0 +1,37 b''
+#!/bin/sh
+
+source "$TESTDIR/bzr-definitions"
+
+echo % test multiple merges at once
+mkdir test-multimerge
+cd test-multimerge
+bzr init -q source
+cd source
+echo content > file
+bzr add -q file
+bzr commit -q -m 'Initial add'
+cd ..
+bzr branch -q source source-branch1
+cd source-branch1
+echo morecontent >> file
+echo evenmorecontent > file-branch1
+bzr add -q file-branch1
+bzr commit -q -m 'Added branch1 file'
+cd ../source
+echo content > file-parent
+bzr add -q file-parent
+bzr commit -q -m 'Added parent file'
+cd ..
+bzr branch -q source source-branch2
+cd source-branch2
+echo somecontent > file-branch2
+bzr add -q file-branch2
+bzr commit -q -m 'Added brach2 file'
+cd ../source
+bzr merge -q ../source-branch1
+bzr merge -q --force ../source-branch2
+bzr commit -q -m 'Merged branches'
+cd ..
+hg convert --datesort source source-hg
+glog -R source-hg
+manifest source-hg tip

tests/test-convert-bzr-merges.out

@@ -0,0 +1,27 b''
+% test multiple merges at once
+initializing destination source-hg repository
+scanning source...
+sorting...
+converting...
+4 Initial add
+3 Added branch1 file
+2 Added parent file
+1 Added brach2 file
+0 Merged branches
+o    5 "(octopus merge fixup)" files:
+|\
+| o    4 "Merged branches" files: file-branch2
+| |\
+o---+  3 "Added brach2 file" files: file-branch2
+ / /
+| o  2 "Added parent file" files: file-parent
+| |
+o |  1 "Added branch1 file" files: file file-branch1
+|/
+o  0 "Initial add" files: file
+
+% manifest of tip
+644   file
+644   file-branch1
+644   file-branch2
+644   file-parent

tests/test-convert-bzr-treeroot

@@ -0,0 +1,26 b''
+#!/bin/sh
+
+source "$TESTDIR/bzr-definitions"
+
+cat > treeset.py <<EOF
+import sys
+from bzrlib import workingtree
+wt = workingtree.WorkingTree.open('.')
+
+message, rootid = sys.argv[1:]
+wt.set_root_id('tree_root-%s' % rootid)
+wt.commit(message)
+EOF
+
+echo % change the id of the tree root
+mkdir test-change-treeroot-id
+cd test-change-treeroot-id
+bzr init -q source
+cd source
+echo content > file
+bzr add -q file
+bzr commit -q -m 'Initial add'
+python ../../treeset.py 'Changed root' new
+cd ..
+hg convert source source-hg
+manifest source-hg tip

tests/test-convert-bzr-treeroot.out

@@ -0,0 +1,9 b''
+% change the id of the tree root
+initializing destination source-hg repository
+scanning source...
+sorting...
+converting...
+1 Initial add
+0 Changed root
+% manifest of tip
+644   file

tests/test-convert-bzr.out

@@ -0,0 +1,51 b''
+% create and rename on the same file in the same step
+a => b
+initializing destination source-hg repository
+scanning source...
+sorting...
+converting...
+1 Initial add: a
+0 rename a into b, create a
+o  1 "rename a into b, create a" files: a b
+|
+o  0 "Initial add: a" files: a
+
+% test --rev option
+initializing destination source-1-hg repository
+scanning source...
+sorting...
+converting...
+0 Initial add: a
+o  0 "Initial add: a" files: a
+
+% merge
+initializing destination source-hg repository
+scanning source...
+sorting...
+converting...
+3 Initial add
+2 Editing a
+1 Editing b
+0 Merged improve branch
+o    3 "Merged improve branch" files:
+|\
+| o  2 "Editing b" files: b
+| |
+o |  1 "Editing a" files: a
+|/
+o  0 "Initial add" files: a b
+
+% symlinks and executable files
+initializing destination source-hg repository
+scanning source...
+sorting...
+converting...
+1 Initial setup
+0 Symlink changed, x bits changed
+% manifest of 0
+644   altname
+755 * program
+% manifest of tip
+644   altname
+755 * newprog
+644   program

hgext/convert/__init__.py

@@ -1,197 +1,198 b''
 # convert.py Foreign SCM converter
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 '''converting foreign VCS repositories to Mercurial'''
 
 import convcmd
 from mercurial import commands
 from mercurial.i18n import _
 
 # Commands definition was moved elsewhere to ease demandload job.
 
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     """Convert a foreign SCM repository to a Mercurial one.
 
     Accepted source formats [identifiers]:
     - Mercurial [hg]
     - CVS [cvs]
     - Darcs [darcs]
     - git [git]
     - Subversion [svn]
     - Monotone [mtn]
     - GNU Arch [gnuarch]
+    - Bazaar [bzr]
 
     Accepted destination formats [identifiers]:
     - Mercurial [hg]
     - Subversion [svn] (history on branches is not preserved)
 
     If no revision is given, all revisions will be converted. Otherwise,
     convert will only import up to the named revision (given in a format
     understood by the source).
 
     If no destination directory name is specified, it defaults to the
     basename of the source with '-hg' appended.  If the destination
     repository doesn't exist, it will be created.
 
     If <REVMAP> isn't given, it will be put in a default location
     (<dest>/.hg/shamap by default).  The <REVMAP> is a simple text
     file that maps each source commit ID to the destination ID for
     that revision, like so:
     <source ID> <destination ID>
 
     If the file doesn't exist, it's automatically created.  It's updated
     on each commit copied, so convert-repo can be interrupted and can
     be run repeatedly to copy new commits.
 
     The [username mapping] file is a simple text file that maps each source
     commit author to a destination commit author. It is handy for source SCMs
     that use unix logins to identify authors (eg: CVS). One line per author
     mapping and the line format is:
     srcauthor=whatever string you want
 
     The filemap is a file that allows filtering and remapping of files
     and directories.  Comment lines start with '#'.  Each line can
     contain one of the following directives:
 
       include path/to/file
 
       exclude path/to/file
 
       rename from/file to/file
 
     The 'include' directive causes a file, or all files under a
     directory, to be included in the destination repository, and the
     exclusion of all other files and dirs not explicitely included.
     The 'exclude' directive causes files or directories to be omitted.
     The 'rename' directive renames a file or directory.  To rename from a
     subdirectory into the root of the repository, use '.' as the path to
     rename to.
 
     The splicemap is a file that allows insertion of synthetic
     history, letting you specify the parents of a revision.  This is
     useful if you want to e.g. give a Subversion merge two parents, or
     graft two disconnected series of history together.  Each entry
     contains a key, followed by a space, followed by one or two
     values, separated by spaces.  The key is the revision ID in the
     source revision control system whose parents should be modified
     (same format as a key in .hg/shamap).  The values are the revision
     IDs (in either the source or destination revision control system)
     that should be used as the new parents for that node.
 
     Mercurial Source
     -----------------
 
     --config convert.hg.saverev=True          (boolean)
         allow target to preserve source revision ID
     --config convert.hg.startrev=0            (hg revision identifier)
         convert start revision and its descendants
 
     CVS Source
     ----------
 
     CVS source will use a sandbox (i.e. a checked-out copy) from CVS
     to indicate the starting point of what will be converted. Direct
     access to the repository files is not needed, unless of course
     the repository is :local:. The conversion uses the top level
     directory in the sandbox to find the CVS repository, and then uses
     CVS rlog commands to find files to convert. This means that unless
     a filemap is given, all files under the starting directory will be
     converted, and that any directory reorganisation in the CVS
     sandbox is ignored.
 
     Because CVS does not have changesets, it is necessary to collect
     individual commits to CVS and merge them into changesets. CVS source
     can use the external 'cvsps' program (this is a legacy option and may
     be removed in future) or use its internal changeset merging code.
     External cvsps is default, and options may be passed to it by setting
         --config convert.cvsps='cvsps -A -u --cvs-direct -q'
     The options shown are the defaults.
 
     Internal cvsps is selected by setting
         --config convert.cvsps=builtin
     and has a few more configurable options:
         --config convert.cvsps.fuzz=60   (integer)
             Specify the maximum time (in seconds) that is allowed between
             commits with identical user and log message in a single
             changeset. When very large files were checked in as part
             of a changeset then the default may not be long enough.
         --config convert.cvsps.mergeto='{{mergetobranch ([-\w]+)}}'
             Specify a regular expression to which commit log messages are
             matched. If a match occurs, then the conversion process will
             insert a dummy revision merging the branch on which this log
             message occurs to the branch indicated in the regex.
         --config convert.cvsps.mergefrom='{{mergefrombranch ([-\w]+)}}'
             Specify a regular expression to which commit log messages are
             matched. If a match occurs, then the conversion process will
             add the most recent revision on the branch indicated in the
             regex as the second parent of the changeset.
 
     The hgext/convert/cvsps wrapper script allows the builtin changeset
     merging code to be run without doing a conversion. Its parameters and
     output are similar to that of cvsps 2.1.
 
     Subversion Source
     -----------------
 
     Subversion source detects classical trunk/branches/tags layouts.
     By default, the supplied "svn://repo/path/" source URL is
     converted as a single branch. If "svn://repo/path/trunk" exists
     it replaces the default branch. If "svn://repo/path/branches"
     exists, its subdirectories are listed as possible branches. If
     "svn://repo/path/tags" exists, it is looked for tags referencing
     converted branches. Default "trunk", "branches" and "tags" values
     can be overriden with following options. Set them to paths
     relative to the source URL, or leave them blank to disable
     autodetection.
 
     --config convert.svn.branches=branches    (directory name)
         specify the directory containing branches
     --config convert.svn.tags=tags            (directory name)
         specify the directory containing tags
     --config convert.svn.trunk=trunk          (directory name)
         specify the name of the trunk branch
 
     Source history can be retrieved starting at a specific revision,
     instead of being integrally converted. Only single branch
     conversions are supported.
 
     --config convert.svn.startrev=0           (svn revision number)
         specify start Subversion revision.
 
     Mercurial Destination
     ---------------------
 
     --config convert.hg.clonebranches=False   (boolean)
         dispatch source branches in separate clones.
     --config convert.hg.tagsbranch=default    (branch name)
         tag revisions branch name
     --config convert.hg.usebranchnames=True   (boolean)
         preserve branch names
 
     """
     return convcmd.convert(ui, src, dest, revmapfile, **opts)
 
 def debugsvnlog(ui, **opts):
     return convcmd.debugsvnlog(ui, **opts)
 
 commands.norepo += " convert debugsvnlog"
 
 cmdtable = {
     "convert":
         (convert,
          [('A', 'authors', '', _('username mapping filename')),
           ('d', 'dest-type', '', _('destination repository type')),
           ('', 'filemap', '', _('remap file names using contents of file')),
           ('r', 'rev', '', _('import up to target revision REV')),
           ('s', 'source-type', '', _('source repository type')),
           ('', 'splicemap', '', _('splice synthesized history into place')),
           ('', 'datesort', None, _('try to sort changesets by date'))],
          _('hg convert [OPTION]... SOURCE [DEST [REVMAP]]')),
     "debugsvnlog":
         (debugsvnlog,
          [],
          'hg debugsvnlog'),
 }

hgext/convert/convcmd.py

@@ -1,337 +1,339 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, incorporated herein by reference.
 
 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 debugsvnlog, svn_source, svn_sink
 from monotone import monotone_source
 from gnuarch import gnuarch_source
+from bzr import bzr_source
 import filemap
 
 import os, shutil
 from mercurial import hg, util
 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')
 
 source_converters = [
     ('cvs', convert_cvs),
     ('git', convert_git),
     ('svn', svn_source),
     ('hg', mercurial_source),
     ('darcs', darcs_source),
     ('mtn', monotone_source),
     ('gnuarch', gnuarch_source),
+    ('bzr', bzr_source),
     ]
 
 sink_converters = [
     ('hg', mercurial_sink),
     ('svn', svn_sink),
     ]
 
 def convertsource(ui, path, type, rev):
     exceptions = []
     for name, source in source_converters:
         try:
             if not type or name == type:
                 return source(ui, path, rev)
         except (NoRepo, MissingTool), 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):
     for name, sink in sink_converters:
         try:
             if not type or name == type:
                 return sink(ui, path)
         except NoRepo, inst:
             ui.note(_("convert: %s\n") % inst)
     raise util.Abort(_('%s: unknown repository type') % path)
 
 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
 
         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('authors'):
             self.readauthormap(opts.get('authors'))
             self.authorfile = self.dest.authorfile()
 
         self.splicemap = mapfile(ui, opts.get('splicemap'))
 
     def walktree(self, heads):
         '''Return a mapping that identifies the uncommitted parents of every
         uncommitted changeset.'''
         visit = heads
         known = {}
         parents = {}
         while visit:
             n = visit.pop(0)
             if n in known or n in self.map: continue
             known[n] = 1
             commit = self.cachecommit(n)
             parents[n] = []
             for p in commit.parents:
                 parents[n].append(p)
                 visit.append(p)
 
         return parents
 
     def toposort(self, parents):
         '''Return an ordering such that every uncommitted changeset is
         preceeded by all its uncommitted ancestors.'''
         visit = parents.keys()
         seen = {}
         children = {}
         actives = []
 
         while visit:
             n = visit.pop(0)
             if n in seen: continue
             seen[n] = 1
             # Ensure that nodes without parents are present in the 'children'
             # mapping.
             children.setdefault(n, [])
             hasparent = False
             for p in parents[n]:
                 if not p in self.map:
                     visit.append(p)
                     hasparent = True
                 children.setdefault(p, []).append(n)
             if not hasparent:
                 actives.append(n)
 
         del seen
         del visit
 
         if self.opts.get('datesort'):
             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]
         else:
             prev = [None]
             def picknext(nodes):
                 # Return the first eligible child of the previously converted
                 # revision, or any of them.
                 next = nodes[0]
                 for n in nodes:
                     if prev[0] in parents[n]:
                         next = n
                         break
                 prev[0] = next
                 return next
 
         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:
             if line.strip() == '':
                 continue
             try:
                 srcauthor, dstauthor = line.split('=', 1)
                 srcauthor = srcauthor.strip()
                 dstauthor = dstauthor.strip()
                 if srcauthor in self.authors and dstauthor != self.authors[srcauthor]:
                     self.ui.status(
                         _('Overriding mapping for author %s, was %s, will be %s\n')
                         % (srcauthor, self.authors[srcauthor], dstauthor))
                 else:
                     self.ui.debug(_('Mapping author %s to %s\n')
                                   % (srcauthor, dstauthor))
                     self.authors[srcauthor] = dstauthor
             except IndexError:
                 self.ui.warn(
                     _('Ignoring bad line in author map file %s: %s\n')
                     % (authorfile, line.rstrip()))
         afile.close()
 
     def cachecommit(self, rev):
         commit = self.source.getcommit(rev)
         commit.author = self.authors.get(commit.author, commit.author)
         self.commitcache[rev] = commit
         return commit
 
     def copy(self, rev):
         commit = self.commitcache[rev]
 
         changes = self.source.getchanges(rev)
         if isinstance(changes, basestring):
             if changes == SKIPREV:
                 dest = SKIPREV
             else:
                 dest = self.map[changes]
             self.map[rev] = dest
             return
         files, copies = 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].replace(',', ' ').split()
             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]
         newnode = self.dest.putcommit(files, copies, parents, commit, self.source)
         self.source.converted(rev, newnode)
         self.map[rev] = newnode
 
     def convert(self):
 
         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.ui.status(_("sorting...\n"))
             t = self.toposort(parents)
             num = len(t)
             c = None
 
             self.ui.status(_("converting...\n"))
             for c in 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 util._encoding conver() use it as
                 # 'utf-8'
                 self.ui.status("%d %s\n" % (num, recode(desc)))
                 self.ui.note(_("source: %s\n") % recode(c))
                 self.copy(c)
 
             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 = self.dest.puttags(ctags)
                 # write another hash correspondence to override the previous
                 # one so we don't end up with extra tag heads
                 if nrev:
                     self.map[c] = nrev
 
             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 = util._encoding
     util._encoding = 'UTF-8'
 
     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 = convertsource(ui, src, opts.get('source_type'),
                              opts.get('rev'))
     except Exception:
         for path in destc.created:
             shutil.rmtree(path, True)
         raise
 
     fmap = opts.get('filemap')
     if fmap:
         srcc = filemap.filemap_source(ui, srcc, fmap)
         destc.setfilemapmode(True)
 
     if not revmapfile:
         try:
             revmapfile = destc.revmapfile()
         except:
             revmapfile = os.path.join(destc, "map")
 
     c = converter(ui, srcc, destc, revmapfile, opts)
     c.convert()
 

tests/hghave

@@ -1,214 +1,218 b''
 #!/usr/bin/env python
 """Test the running system for features availability. Exit with zero
 if all features are there, non-zero otherwise. If a feature name is
 prefixed with "no-", the absence of feature is tested.
 """
 import optparse
 import os
 import re
 import sys
 import tempfile
 
 tempprefix = 'hg-hghave-'
 
 def matchoutput(cmd, regexp, ignorestatus=False):
     """Return True if cmd executes successfully and its output
     is matched by the supplied regular expression.
     """
     r = re.compile(regexp)
     fh = os.popen(cmd)
     s = fh.read()
     ret = fh.close()
     return (ignorestatus or ret is None) and r.search(s)
 
 def has_baz():
     return matchoutput('baz --version 2>&1', r'baz Bazaar version')
 
+def has_bzr():
+    return matchoutput('bzr --version 2>&1', r'Bazaar \(bzr\)')
+
 def has_cvs():
     re = r'Concurrent Versions System.*?server'
     return matchoutput('cvs --version 2>&1', re)
 
 def has_cvsps():
     return matchoutput('cvsps -h -q 2>&1', r'cvsps version', True)
 
 def has_darcs():
     return matchoutput('darcs', r'darcs version', True)
 
 def has_mtn():
     return matchoutput('mtn --version', r'monotone', True) and not matchoutput(
         'mtn --version', r'monotone 0\.(\d|[12]\d|3[01])[^\d]', True)
 
 def has_eol_in_paths():
     try:
         fd, path = tempfile.mkstemp(prefix=tempprefix, suffix='\n\r')
         os.close(fd)
         os.remove(path)
         return True
     except:
         return False
 
 def has_executablebit():
     fd, path = tempfile.mkstemp(prefix=tempprefix)
     os.close(fd)
     try:
         s = os.lstat(path).st_mode
         os.chmod(path, s | 0100)
         return (os.lstat(path).st_mode & 0100 != 0)
     finally:
         os.remove(path)
 
 def has_icasefs():
     # Stolen from mercurial.util
     fd, path = tempfile.mkstemp(prefix=tempprefix)
     os.close(fd)
     try:
         s1 = os.stat(path)
         d, b = os.path.split(path)
         p2 = os.path.join(d, b.upper())
         if path == p2:
             p2 = os.path.join(d, b.lower())
         try:
             s2 = os.stat(p2)
             return s2 == s1
         except:
             return False
     finally:
         os.remove(path)
 
 def has_inotify():
     try:
         import hgext.inotify.linux.watcher
         return True
     except ImportError:
         return False
 
 def has_fifo():
     return hasattr(os, "mkfifo")
 
 def has_hotshot():
     try:
         # hotshot.stats tests hotshot and many problematic dependencies
         # like profile.
         import hotshot.stats
         return True
     except ImportError:
         return False
 
 def has_lsprof():
     try:
         import _lsprof
         return True
     except ImportError:
         return False
 
 def has_git():
     return matchoutput('git --version 2>&1', r'^git version')
 
 def has_svn():
     return matchoutput('svn --version 2>&1', r'^svn, version') and \
         matchoutput('svnadmin --version 2>&1', r'^svnadmin, version')
 
 def has_svn_bindings():
     try:
         import svn.core
         return True
     except ImportError:
         return False
 
 def has_symlink():
     return hasattr(os, "symlink")
 
 def has_tla():
     return matchoutput('tla --version 2>&1', r'The GNU Arch Revision')
 
 def has_unix_permissions():
     d = tempfile.mkdtemp(prefix=tempprefix, dir=".")
     try:
         fname = os.path.join(d, 'foo')
         for umask in (077, 007, 022):
             os.umask(umask)
             f = open(fname, 'w')
             f.close()
             mode = os.stat(fname).st_mode
             os.unlink(fname)
             if mode & 0777 != ~umask & 0666:
                 return False
         return True
     finally:
         os.rmdir(d)
 
 def has_pygments():
     try:
         import pygments
         return True
     except ImportError:
         return False
 
 checks = {
     "baz": (has_baz, "GNU Arch baz client"),
+    "bzr": (has_bzr, "Canonical's Bazaar client"),
     "cvs": (has_cvs, "cvs client/server"),
     "cvsps": (has_cvsps, "cvsps utility"),
     "darcs": (has_darcs, "darcs client"),
     "eol-in-paths": (has_eol_in_paths, "end-of-lines in paths"),
     "execbit": (has_executablebit, "executable bit"),
     "fifo": (has_fifo, "named pipes"),
     "git": (has_git, "git command line client"),
     "hotshot": (has_hotshot, "python hotshot module"),
     "icasefs": (has_icasefs, "case insensitive file system"),
     "inotify": (has_inotify, "inotify extension support"),
     "lsprof": (has_lsprof, "python lsprof module"),
     "mtn": (has_mtn, "monotone client (> 0.31)"),
     "pygments": (has_pygments, "Pygments source highlighting library"),
     "svn": (has_svn, "subversion client and admin tools"),
     "svn-bindings": (has_svn_bindings, "subversion python bindings"),
     "symlink": (has_symlink, "symbolic links"),
     "tla": (has_tla, "GNU Arch tla client"),
     "unix-permissions": (has_unix_permissions, "unix-style permissions"),
 }
 
 def list_features():
     for name, feature in checks.iteritems():
         desc = feature[1]
         print name + ':', desc
 
 parser = optparse.OptionParser("%prog [options] [features]")
 parser.add_option("--list-features", action="store_true",
                   help="list available features")
 parser.add_option("-q", "--quiet", action="store_true",
                   help="check features silently")
 
 if __name__ == '__main__':
     options, args = parser.parse_args()
     if options.list_features:
         list_features()
         sys.exit(0)
 
     quiet = options.quiet
 
     failures = 0
 
     def error(msg):
         global failures
         if not quiet:
             sys.stderr.write(msg + '\n')
         failures += 1
 
     for feature in args:
         negate = feature.startswith('no-')
         if negate:
             feature = feature[3:]
 
         if feature not in checks:
             error('skipped: unknown feature: ' + feature)
             continue
 
         check, desc = checks[feature]
         if not negate and not check():
             error('skipped: missing feature: ' + desc)
         elif negate and check():
             error('skipped: system supports %s' % desc)
 
     if failures != 0:
         sys.exit(1)
 
 

tests/test-convert.out

@@ -1,205 +1,206 b''
 hg convert [OPTION]... SOURCE [DEST [REVMAP]]
 
 Convert a foreign SCM repository to a Mercurial one.
 
     Accepted source formats [identifiers]:
     - Mercurial [hg]
     - CVS [cvs]
     - Darcs [darcs]
     - git [git]
     - Subversion [svn]
     - Monotone [mtn]
     - GNU Arch [gnuarch]
+    - Bazaar [bzr]
 
     Accepted destination formats [identifiers]:
     - Mercurial [hg]
     - Subversion [svn] (history on branches is not preserved)
 
     If no revision is given, all revisions will be converted. Otherwise,
     convert will only import up to the named revision (given in a format
     understood by the source).
 
     If no destination directory name is specified, it defaults to the
     basename of the source with '-hg' appended.  If the destination
     repository doesn't exist, it will be created.
 
     If <REVMAP> isn't given, it will be put in a default location
     (<dest>/.hg/shamap by default).  The <REVMAP> is a simple text
     file that maps each source commit ID to the destination ID for
     that revision, like so:
     <source ID> <destination ID>
 
     If the file doesn't exist, it's automatically created.  It's updated
     on each commit copied, so convert-repo can be interrupted and can
     be run repeatedly to copy new commits.
 
     The [username mapping] file is a simple text file that maps each source
     commit author to a destination commit author. It is handy for source SCMs
     that use unix logins to identify authors (eg: CVS). One line per author
     mapping and the line format is:
     srcauthor=whatever string you want
 
     The filemap is a file that allows filtering and remapping of files
     and directories.  Comment lines start with '#'.  Each line can
     contain one of the following directives:
 
       include path/to/file
 
       exclude path/to/file
 
       rename from/file to/file
 
     The 'include' directive causes a file, or all files under a
     directory, to be included in the destination repository, and the
     exclusion of all other files and dirs not explicitely included.
     The 'exclude' directive causes files or directories to be omitted.
     The 'rename' directive renames a file or directory.  To rename from a
     subdirectory into the root of the repository, use '.' as the path to
     rename to.
 
     The splicemap is a file that allows insertion of synthetic
     history, letting you specify the parents of a revision.  This is
     useful if you want to e.g. give a Subversion merge two parents, or
     graft two disconnected series of history together.  Each entry
     contains a key, followed by a space, followed by one or two
     values, separated by spaces.  The key is the revision ID in the
     source revision control system whose parents should be modified
     (same format as a key in .hg/shamap).  The values are the revision
     IDs (in either the source or destination revision control system)
     that should be used as the new parents for that node.
 
     Mercurial Source
     -----------------
 
     --config convert.hg.saverev=True          (boolean)
         allow target to preserve source revision ID
     --config convert.hg.startrev=0            (hg revision identifier)
         convert start revision and its descendants
 
     CVS Source
     ----------
 
     CVS source will use a sandbox (i.e. a checked-out copy) from CVS
     to indicate the starting point of what will be converted. Direct
     access to the repository files is not needed, unless of course
     the repository is :local:. The conversion uses the top level
     directory in the sandbox to find the CVS repository, and then uses
     CVS rlog commands to find files to convert. This means that unless
     a filemap is given, all files under the starting directory will be
     converted, and that any directory reorganisation in the CVS
     sandbox is ignored.
 
     Because CVS does not have changesets, it is necessary to collect
     individual commits to CVS and merge them into changesets. CVS source
     can use the external 'cvsps' program (this is a legacy option and may
     be removed in future) or use its internal changeset merging code.
     External cvsps is default, and options may be passed to it by setting
         --config convert.cvsps='cvsps -A -u --cvs-direct -q'
     The options shown are the defaults.
 
     Internal cvsps is selected by setting
         --config convert.cvsps=builtin
     and has a few more configurable options:
         --config convert.cvsps.fuzz=60   (integer)
             Specify the maximum time (in seconds) that is allowed between
             commits with identical user and log message in a single
             changeset. When very large files were checked in as part
             of a changeset then the default may not be long enough.
         --config convert.cvsps.mergeto='{{mergetobranch ([-\w]+)}}'
             Specify a regular expression to which commit log messages are
             matched. If a match occurs, then the conversion process will
             insert a dummy revision merging the branch on which this log
             message occurs to the branch indicated in the regex.
         --config convert.cvsps.mergefrom='{{mergefrombranch ([-\w]+)}}'
             Specify a regular expression to which commit log messages are
             matched. If a match occurs, then the conversion process will
             add the most recent revision on the branch indicated in the
             regex as the second parent of the changeset.
 
     The hgext/convert/cvsps wrapper script allows the builtin changeset
     merging code to be run without doing a conversion. Its parameters and
     output are similar to that of cvsps 2.1.
 
     Subversion Source
     -----------------
 
     Subversion source detects classical trunk/branches/tags layouts.
     By default, the supplied "svn://repo/path/" source URL is
     converted as a single branch. If "svn://repo/path/trunk" exists
     it replaces the default branch. If "svn://repo/path/branches"
     exists, its subdirectories are listed as possible branches. If
     "svn://repo/path/tags" exists, it is looked for tags referencing
     converted branches. Default "trunk", "branches" and "tags" values
     can be overriden with following options. Set them to paths
     relative to the source URL, or leave them blank to disable
     autodetection.
 
     --config convert.svn.branches=branches    (directory name)
         specify the directory containing branches
     --config convert.svn.tags=tags            (directory name)
         specify the directory containing tags
     --config convert.svn.trunk=trunk          (directory name)
         specify the name of the trunk branch
 
     Source history can be retrieved starting at a specific revision,
     instead of being integrally converted. Only single branch
     conversions are supported.
 
     --config convert.svn.startrev=0           (svn revision number)
         specify start Subversion revision.
 
     Mercurial Destination
     ---------------------
 
     --config convert.hg.clonebranches=False   (boolean)
         dispatch source branches in separate clones.
     --config convert.hg.tagsbranch=default    (branch name)
         tag revisions branch name
     --config convert.hg.usebranchnames=True   (boolean)
         preserve branch names
 
 options:
 
  -A --authors      username mapping filename
  -d --dest-type    destination repository type
     --filemap      remap file names using contents of file
  -r --rev          import up to target revision REV
  -s --source-type  source repository type
     --splicemap    splice synthesized history into place
     --datesort     try to sort changesets by date
 
 use "hg -v help convert" to show global options
 adding a
 assuming destination a-hg
 initializing destination a-hg repository
 scanning source...
 sorting...
 converting...
 4 a
 3 b
 2 c
 1 d
 0 e
 pulling from ../a
 searching for changes
 no changes found
 % should fail
 initializing destination bogusfile repository
 abort: cannot create new bundle repository
 % should fail
 abort: Permission denied: bogusdir
 % should succeed
 initializing destination bogusdir repository
 scanning source...
 sorting...
 converting...
 4 a
 3 b
 2 c
 1 d
 0 e
 % test pre and post conversion actions
 run hg source pre-conversion action
 run hg sink pre-conversion action
 run hg sink post-conversion action
 run hg source post-conversion action