convert: add support for Subversion as a sink

tests/test-convert-svn-sink

@@ -0,0 +1,91 b''
+#!/bin/sh
+
+"$TESTDIR/hghave" svn svn-bindings || exit 80
+
+echo "[extensions]" >> $HGRCPATH
+echo "convert = " >> $HGRCPATH
+
+hg init a
+
+echo a > a/a
+echo % add
+hg --cwd a ci -d '0 0' -A -m 'add a file'
+
+echo a >> a/a
+echo % modify
+hg --cwd a ci -d '1 0' -m 'modify a file'
+hg --cwd a tip -q
+
+hg convert -d svn a
+(cd a-hg-wc; svn up; svn st -v; svn log --xml -v --limit=2 | sed 's,<date>.*,<date/>,')
+ls a a-hg-wc
+cmp a/a a-hg-wc/a && echo same || echo different
+
+hg --cwd a mv a b
+echo % rename
+hg --cwd a ci -d '2 0' -m 'rename a file'
+hg --cwd a tip -q
+
+hg convert -d svn a
+(cd a-hg-wc; svn up; svn st -v; svn log --xml -v --limit=1 | sed 's,<date>.*,<date/>,')
+ls a a-hg-wc
+
+hg --cwd a cp b c
+echo % copy
+hg --cwd a ci -d '3 0' -m 'copy a file'
+hg --cwd a tip -q
+
+hg convert -d svn a
+(cd a-hg-wc; svn up; svn st -v; svn log --xml -v --limit=1 | sed 's,<date>.*,<date/>,')
+ls a a-hg-wc
+
+hg --cwd a rm b
+echo % remove
+hg --cwd a ci -d '4 0' -m 'remove a file'
+hg --cwd a tip -q
+
+hg convert -d svn a
+(cd a-hg-wc; svn up; svn st -v; svn log --xml -v --limit=1 | sed 's,<date>.*,<date/>,')
+ls a a-hg-wc
+
+chmod +x a/c
+echo % executable
+hg --cwd a ci -d '5 0' -m 'make a file executable'
+hg --cwd a tip -q
+
+hg convert -d svn a
+(cd a-hg-wc; svn up; svn st -v; svn log --xml -v --limit=1 | sed 's,<date>.*,<date/>,')
+test -x a-hg-wc/c && echo executable || echo not executable
+
+echo % branchy history
+
+hg init b
+echo base > b/b
+hg --cwd b ci -d '0 0' -Ambase
+
+echo left-1 >> b/b
+echo left-1 > b/left-1
+hg --cwd b ci -d '1 0' -Amleft-1
+
+echo left-2 >> b/b
+echo left-2 > b/left-2
+hg --cwd b ci -d '2 0' -Amleft-2
+
+hg --cwd b up 0
+
+echo right-1 >> b/b
+echo right-1 > b/right-1
+hg --cwd b ci -d '3 0' -Amright-1
+
+echo right-2 >> b/b
+echo right-2 > b/right-2
+hg --cwd b ci -d '4 0' -Amright-2
+
+hg --cwd b up -C 2
+hg --cwd b merge
+hg --cwd b revert -r 2 b
+hg --cwd b ci -d '5 0' -m 'merge'
+
+hg convert -d svn b
+echo % expect 4 changes
+(cd b-hg-wc; svn up; svn st -v; svn log --xml -v | sed 's,<date>.*,<date/>,')

tests/test-convert-svn-sink.out

@@ -0,0 +1,251 b''
+% add
+adding a
+% modify
+1:10307c220ed9
+assuming destination a-hg
+initializing svn repo 'a-hg'
+initializing svn wc 'a-hg-wc'
+scanning source...
+sorting...
+converting...
+1 add a file
+0 modify a file
+At revision 2.
+                2        2 test         .
+                2        2 test         a
+<?xml version="1.0"?>
+<log>
+<logentry
+   revision="2">
+<author>test</author>
+<date/>
+<paths>
+<path
+   action="M">/a</path>
+</paths>
+<msg>modify a file</msg>
+</logentry>
+<logentry
+   revision="1">
+<author>test</author>
+<date/>
+<paths>
+<path
+   action="A">/a</path>
+</paths>
+<msg>add a file</msg>
+</logentry>
+</log>
+a:
+a
+
+a-hg-wc:
+a
+same
+% rename
+2:6e45a219686e
+assuming destination a-hg
+initializing svn wc 'a-hg-wc'
+scanning source...
+sorting...
+converting...
+0 rename a file
+At revision 3.
+                3        3 test         .
+                3        3 test         b
+<?xml version="1.0"?>
+<log>
+<logentry
+   revision="3">
+<author>test</author>
+<date/>
+<paths>
+<path
+   action="D">/a</path>
+<path
+   copyfrom-path="/a"
+   copyfrom-rev="2"
+   action="A">/b</path>
+</paths>
+<msg>rename a file</msg>
+</logentry>
+</log>
+a:
+b
+
+a-hg-wc:
+b
+% copy
+3:d811dc81efbb
+assuming destination a-hg
+initializing svn wc 'a-hg-wc'
+scanning source...
+sorting...
+converting...
+0 copy a file
+At revision 4.
+                4        4 test         .
+                4        3 test         b
+                4        4 test         c
+<?xml version="1.0"?>
+<log>
+<logentry
+   revision="4">
+<author>test</author>
+<date/>
+<paths>
+<path
+   copyfrom-path="/b"
+   copyfrom-rev="3"
+   action="A">/c</path>
+</paths>
+<msg>copy a file</msg>
+</logentry>
+</log>
+a:
+b
+c
+
+a-hg-wc:
+b
+c
+% remove
+4:045e93063aca
+assuming destination a-hg
+initializing svn wc 'a-hg-wc'
+scanning source...
+sorting...
+converting...
+0 remove a file
+At revision 5.
+                5        5 test         .
+                5        4 test         c
+<?xml version="1.0"?>
+<log>
+<logentry
+   revision="5">
+<author>test</author>
+<date/>
+<paths>
+<path
+   action="D">/b</path>
+</paths>
+<msg>remove a file</msg>
+</logentry>
+</log>
+a:
+c
+
+a-hg-wc:
+c
+% executable
+5:7eda3f4b5331
+svn: Path 'b' does not exist
+assuming destination a-hg
+initializing svn wc 'a-hg-wc'
+scanning source...
+sorting...
+converting...
+0 make a file executable
+abort: svn exited with status 1
+At revision 5.
+                5        5 test         .
+ M              5        4 test         c
+<?xml version="1.0"?>
+<log>
+<logentry
+   revision="5">
+<author>test</author>
+<date/>
+<paths>
+<path
+   action="D">/b</path>
+</paths>
+<msg>remove a file</msg>
+</logentry>
+</log>
+executable
+% branchy history
+adding b
+adding left-1
+adding left-2
+1 files updated, 0 files merged, 2 files removed, 0 files unresolved
+adding right-1
+adding right-2
+3 files updated, 0 files merged, 2 files removed, 0 files unresolved
+warning: conflicts during merge.
+merging b
+merging b failed!
+2 files updated, 0 files merged, 0 files removed, 1 files unresolved
+There are unresolved merges, you can redo the full merge using:
+  hg update -C 2
+  hg merge 4
+assuming destination b-hg
+initializing svn repo 'b-hg'
+initializing svn wc 'b-hg-wc'
+scanning source...
+sorting...
+converting...
+5 base
+4 left-1
+3 left-2
+2 right-1
+1 right-2
+0 merge
+% expect 4 changes
+At revision 4.
+                4        4 test         .
+                4        3 test         b
+                4        2 test         left-1
+                4        3 test         left-2
+                4        4 test         right-1
+                4        4 test         right-2
+<?xml version="1.0"?>
+<log>
+<logentry
+   revision="4">
+<author>test</author>
+<date/>
+<paths>
+<path
+   action="A">/right-1</path>
+<path
+   action="A">/right-2</path>
+</paths>
+<msg>merge</msg>
+</logentry>
+<logentry
+   revision="3">
+<author>test</author>
+<date/>
+<paths>
+<path
+   action="M">/b</path>
+<path
+   action="A">/left-2</path>
+</paths>
+<msg>left-2</msg>
+</logentry>
+<logentry
+   revision="2">
+<author>test</author>
+<date/>
+<paths>
+<path
+   action="M">/b</path>
+<path
+   action="A">/left-1</path>
+</paths>
+<msg>left-1</msg>
+</logentry>
+<logentry
+   revision="1">
+<author>test</author>
+<date/>
+<paths>
+<path
+   action="A">/b</path>
+</paths>
+<msg>base</msg>
+</logentry>
+</log>

hgext/convert/__init__.py

@@ -1,376 +1,378 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.
 
 from common import NoRepo, SKIPREV, converter_source, converter_sink, 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, debugsvnlog
+from subversion import debugsvnlog, svn_source, svn_sink
 import filemap
 
 import os, shutil
 from mercurial import hg, ui, util, commands
 from mercurial.i18n import _
 
 commands.norepo += " convert debugsvnlog"
 
 source_converters = [
     ('cvs', convert_cvs),
     ('git', convert_git),
     ('svn', svn_source),
     ('hg', mercurial_source),
     ('darcs', darcs_source),
     ]
 
 sink_converters = [
     ('hg', mercurial_sink),
+    ('svn', svn_sink),
     ]
 
 def convertsource(ui, path, type, rev):
     for name, source in source_converters:
         try:
             if not type or name == type:
                 return source(ui, path, rev)
         except NoRepo, inst:
             ui.note(_("convert: %s\n") % inst)
     raise util.Abort('%s: unknown repository type' % 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()
 
     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 = {}
 
         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, [])
             for p in parents[n]:
                 if not p in self.map:
                     visit.append(p)
                 children.setdefault(p, []).append(n)
 
         s = []
         removed = {}
         visit = children.keys()
         while visit:
             n = visit.pop(0)
             if n in removed: continue
             dep = 0
             if n in parents:
                 for p in parents[n]:
                     if p in self.map: continue
                     if p not in removed:
                         # we're still dependent
                         visit.append(n)
                         dep = 1
                         break
 
             if not dep:
                 # all n's parents are in the list
                 removed[n] = 1
                 if n not in self.map:
                     s.append(n)
                 if n in children:
                     for c in children[n]:
                         visit.insert(0, c)
 
         if self.opts.get('datesort'):
             depth = {}
             for n in s:
                 depth[n] = 0
                 pl = [p for p in self.commitcache[n].parents
                       if p not in self.map]
                 if pl:
                     depth[n] = max([depth[p] for p in pl]) + 1
 
             s = [(depth[n], self.commitcache[n].date, n) for n in s]
             s.sort()
             s = [e[2] for e in s]
 
         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:
             try:
                 srcauthor = line.split('=')[0].strip()
                 dstauthor = line.split('=')[1].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 file map %s: %s\n'
                     % (authorfile, line))
         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]
         do_copies = hasattr(self.dest, 'copyfile')
         filenames = []
 
         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
         parents = [self.map[r] for r in commit.parents]
         if commit.parents:
             prev = commit.parents[0]
             if prev not in self.commitcache:
                 self.cachecommit(prev)
             pbranch = self.commitcache[prev].branch
         else:
             pbranch = None
         self.dest.setbranch(commit.branch, pbranch, parents)
         for f, v in files:
             filenames.append(f)
             try:
                 data = self.source.getfile(f, v)
             except IOError, inst:
                 self.dest.delfile(f)
             else:
                 e = self.source.getmode(f, v)
                 self.dest.putfile(f, e, data)
                 if do_copies:
                     if f in copies:
                         copyf = copies[f]
                         # Merely marks that a copy happened.
                         self.dest.copyfile(copyf, f)
 
         newnode = self.dest.putcommit(filenames, parents, commit)
         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]
                 self.ui.status("%d %s\n" % (num, desc))
                 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):
     """Convert a foreign SCM repository to a Mercurial one.
 
     Accepted source formats:
     - Mercurial
     - CVS
     - Darcs
     - git
     - Subversion
 
     Accepted destination formats:
     - Mercurial
+    - Subversion (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 <MAPFILE> isn't given, it will be put in a default location
     (<dest>/.hg/shamap by default).  The <MAPFILE> 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.
     """
 
     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()
 
 
 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'),
           ('', 'datesort', None, 'try to sort changesets by date')],
          'hg convert [OPTION]... SOURCE [DEST [MAPFILE]]'),
     "debugsvnlog":
         (debugsvnlog,
          [],
          'hg debugsvnlog'),
 }
 

hgext/convert/common.py

@@ -1,291 +1,292 b''
 # common code for the convert extension
 import base64, errno
 import cPickle as pickle
 from mercurial import util
+from mercurial.i18n import _
 
 def encodeargs(args):
     def encodearg(s):
         lines = base64.encodestring(s)
         lines = [l.splitlines()[0] for l in lines]
         return ''.join(lines)
 
     s = pickle.dumps(args)
     return encodearg(s)
 
 def decodeargs(s):
     s = base64.decodestring(s)
     return pickle.loads(s)
 
 def checktool(exe, name=None):
     name = name or exe
     if not util.find_exe(exe):
         raise util.Abort('cannot find required "%s" tool' % name)
 
 class NoRepo(Exception): pass
 
 SKIPREV = 'SKIP'
 
 class commit(object):
     def __init__(self, author, date, desc, parents, branch=None, rev=None,
                  extra={}):
         self.author = author
         self.date = date
         self.desc = desc
         self.parents = parents
         self.branch = branch
         self.rev = rev
         self.extra = extra
 
 class converter_source(object):
     """Conversion source interface"""
 
     def __init__(self, ui, path, rev=None):
         """Initialize conversion source (or raise NoRepo("message")
         exception if path is not a valid repository)"""
         self.ui = ui
         self.path = path
         self.rev = rev
 
         self.encoding = 'utf-8'
 
     def before(self):
         pass
 
     def after(self):
         pass
 
     def setrevmap(self, revmap):
         """set the map of already-converted revisions"""
         pass
 
     def getheads(self):
         """Return a list of this repository's heads"""
         raise NotImplementedError()
 
     def getfile(self, name, rev):
         """Return file contents as a string"""
         raise NotImplementedError()
 
     def getmode(self, name, rev):
         """Return file mode, eg. '', 'x', or 'l'"""
         raise NotImplementedError()
 
     def getchanges(self, version):
         """Returns a tuple of (files, copies)
         Files is a sorted list of (filename, id) tuples for all files changed
         in version, where id is the source revision id of the file.
 
         copies is a dictionary of dest: source
         """
         raise NotImplementedError()
 
     def getcommit(self, version):
         """Return the commit object for version"""
         raise NotImplementedError()
 
     def gettags(self):
         """Return the tags as a dictionary of name: revision"""
         raise NotImplementedError()
 
     def recode(self, s, encoding=None):
         if not encoding:
             encoding = self.encoding or 'utf-8'
 
         if isinstance(s, unicode):
             return s.encode("utf-8")
         try:
             return s.decode(encoding).encode("utf-8")
         except:
             try:
                 return s.decode("latin-1").encode("utf-8")
             except:
                 return s.decode(encoding, "replace").encode("utf-8")
 
     def getchangedfiles(self, rev, i):
         """Return the files changed by rev compared to parent[i].
     
         i is an index selecting one of the parents of rev.  The return
         value should be the list of files that are different in rev and
         this parent.
 
         If rev has no parents, i is None.
     
         This function is only needed to support --filemap
         """
         raise NotImplementedError()
 
 class converter_sink(object):
     """Conversion sink (target) interface"""
 
     def __init__(self, ui, path):
         """Initialize conversion sink (or raise NoRepo("message")
         exception if path is not a valid repository)
 
         created is a list of paths to remove if a fatal error occurs
         later"""
         self.ui = ui
         self.path = path
         self.created = []
 
     def getheads(self):
         """Return a list of this repository's heads"""
         raise NotImplementedError()
 
     def revmapfile(self):
         """Path to a file that will contain lines
         source_rev_id sink_rev_id
         mapping equivalent revision identifiers for each system."""
         raise NotImplementedError()
 
     def authorfile(self):
         """Path to a file that will contain lines
         srcauthor=dstauthor
         mapping equivalent authors identifiers for each system."""
         return None
 
     def putfile(self, f, e, data):
         """Put file for next putcommit().
         f: path to file
         e: '', 'x', or 'l' (regular file, executable, or symlink)
         data: file contents"""
         raise NotImplementedError()
 
     def delfile(self, f):
         """Delete file for next putcommit().
         f: path to file"""
         raise NotImplementedError()
 
     def putcommit(self, files, parents, commit):
         """Create a revision with all changed files listed in 'files'
         and having listed parents. 'commit' is a commit object containing
         at a minimum the author, date, and message for this changeset.
         Called after putfile() and delfile() calls. Note that the sink
         repository is not told to update itself to a particular revision
         (or even what that revision would be) before it receives the
         file data."""
         raise NotImplementedError()
 
     def puttags(self, tags):
         """Put tags into sink.
         tags: {tagname: sink_rev_id, ...}"""
         raise NotImplementedError()
 
     def setbranch(self, branch, pbranch, parents):
         """Set the current branch name. Called before the first putfile
         on the branch.
         branch: branch name for subsequent commits
         pbranch: branch name of parent commit
         parents: destination revisions of parent"""
         pass
 
     def setfilemapmode(self, active):
         """Tell the destination that we're using a filemap
 
         Some converter_sources (svn in particular) can claim that a file
         was changed in a revision, even if there was no change.  This method
         tells the destination that we're using a filemap and that it should
         filter empty revisions.
         """
         pass
 
     def before(self):
         pass
 
     def after(self):
         pass
 
 
 class commandline(object):
     def __init__(self, ui, command):
         self.ui = ui
         self.command = command
 
     def prerun(self):
         pass
 
     def postrun(self):
         pass
 
     def _run(self, cmd, *args, **kwargs):
         cmdline = [self.command, cmd] + list(args)
         for k, v in kwargs.iteritems():
             if len(k) == 1:
                 cmdline.append('-' + k)
             else:
                 cmdline.append('--' + k.replace('_', '-'))
             try:
                 if len(k) == 1:
                     cmdline.append('' + v)
                 else:
                     cmdline[-1] += '=' + v
             except TypeError:
                 pass
         cmdline = [util.shellquote(arg) for arg in cmdline]
         cmdline += ['<', util.nulldev]
         cmdline = util.quotecommand(' '.join(cmdline))
         self.ui.debug(cmdline, '\n')
 
         self.prerun()
         try:
             return util.popen(cmdline)
         finally:
             self.postrun()
 
     def run(self, cmd, *args, **kwargs):
         fp = self._run(cmd, *args, **kwargs)
         output = fp.read()
         self.ui.debug(output)
         return output, fp.close()
 
     def checkexit(self, status, output=''):
         if status:
             if output:
                 self.ui.warn(_('%s error:\n') % self.command)
                 self.ui.warn(output)
             msg = util.explain_exit(status)[0]
             raise util.Abort(_('%s %s') % (self.command, msg))
 
     def run0(self, cmd, *args, **kwargs):
         output, status = self.run(cmd, *args, **kwargs)
         self.checkexit(status, output)
         return output
 
 
 class mapfile(dict):
     def __init__(self, ui, path):
         super(mapfile, self).__init__()
         self.ui = ui
         self.path = path
         self.fp = None
         self.order = []
         self._read()
 
     def _read(self):
         try:
             fp = open(self.path, 'r')
         except IOError, err:
             if err.errno != errno.ENOENT:
                 raise
             return
         for line in fp:
             key, value = line[:-1].split(' ', 1)
             if key not in self:
                 self.order.append(key)
             super(mapfile, self).__setitem__(key, value)
         fp.close()
             
     def __setitem__(self, key, value):
         if self.fp is None:
             try:
                 self.fp = open(self.path, 'a')
             except IOError, err:
                 raise util.Abort(_('could not open map file %r: %s') %
                                  (self.path, err.strerror))
         self.fp.write('%s %s\n' % (key, value))
         self.fp.flush()
         super(mapfile, self).__setitem__(key, value)
 
     def close(self):
         if self.fp:
             self.fp.close()
             self.fp = None

hgext/convert/subversion.py

@@ -1,666 +1,866 b''
 # Subversion 1.4/1.5 Python API backend
 #
 # Copyright(C) 2007 Daniel Holth et al
 #
 # Configuration options:
 #
 # convert.svn.trunk
 #   Relative path to the trunk (default: "trunk")
 # convert.svn.branches
 #   Relative path to tree of branches (default: "branches")
 # convert.svn.tags
 #   Relative path to tree of tags (default: "tags")
 #
 # Set these in a hgrc, or on the command line as follows:
 #
 #   hg convert --config convert.svn.trunk=wackoname [...]
 
 import locale
 import os
+import re
 import sys
 import cPickle as pickle
-from mercurial import util
+import tempfile
+
+from mercurial import strutil, util
+from mercurial.i18n import _
 
 # Subversion stuff. Works best with very recent Python SVN bindings
 # e.g. SVN 1.5 or backports. Thanks to the bzr folks for enhancing
 # these bindings.
 
 from cStringIO import StringIO
 
 from common import NoRepo, commit, converter_source, encodeargs, decodeargs
+from common import commandline, converter_sink, mapfile
 
 try:
     from svn.core import SubversionException, Pool
     import svn
     import svn.client
     import svn.core
     import svn.ra
     import svn.delta
     import transport
 except ImportError:
     pass
 
 def geturl(path):
     try:
         return svn.client.url_from_path(svn.core.svn_path_canonicalize(path))
     except SubversionException:
         pass
     if os.path.isdir(path):
         return 'file://%s' % os.path.normpath(os.path.abspath(path))
     return path
 
 def optrev(number):
     optrev = svn.core.svn_opt_revision_t()
     optrev.kind = svn.core.svn_opt_revision_number
     optrev.value.number = number
     return optrev
 
 class changedpath(object):
     def __init__(self, p):
         self.copyfrom_path = p.copyfrom_path
         self.copyfrom_rev = p.copyfrom_rev
         self.action = p.action
 
 def get_log_child(fp, url, paths, start, end, limit=0, discover_changed_paths=True,
                     strict_node_history=False):
     protocol = -1
     def receiver(orig_paths, revnum, author, date, message, pool):
         if orig_paths is not None:
             for k, v in orig_paths.iteritems():
                 orig_paths[k] = changedpath(v)
         pickle.dump((orig_paths, revnum, author, date, message),
                     fp, protocol)
 
     try:
         # Use an ra of our own so that our parent can consume
         # our results without confusing the server.
         t = transport.SvnRaTransport(url=url)
         svn.ra.get_log(t.ra, paths, start, end, limit,
                        discover_changed_paths,
                        strict_node_history,
                        receiver)
     except SubversionException, (inst, num):
         pickle.dump(num, fp, protocol)
     else:
         pickle.dump(None, fp, protocol)
     fp.close()
 
 def debugsvnlog(ui, **opts):
     """Fetch SVN log in a subprocess and channel them back to parent to
     avoid memory collection issues.
     """
     util.set_binary(sys.stdin)
     util.set_binary(sys.stdout)
     args = decodeargs(sys.stdin.read())
     get_log_child(sys.stdout, *args)
 
 # SVN conversion code stolen from bzr-svn and tailor
 class svn_source(converter_source):
     def __init__(self, ui, url, rev=None):
         super(svn_source, self).__init__(ui, url, rev=rev)
 
         try:
             SubversionException
         except NameError:
             raise NoRepo('subversion python bindings could not be loaded')
 
         self.encoding = locale.getpreferredencoding()
         self.lastrevs = {}
 
         latest = None
         try:
             # Support file://path@rev syntax. Useful e.g. to convert
             # deleted branches.
             at = url.rfind('@')
             if at >= 0:
                 latest = int(url[at+1:])
                 url = url[:at]
         except ValueError, e:
             pass
         self.url = geturl(url)
         self.encoding = 'UTF-8' # Subversion is always nominal UTF-8
         try:
             self.transport = transport.SvnRaTransport(url=self.url)
             self.ra = self.transport.ra
             self.ctx = self.transport.client
             self.base = svn.ra.get_repos_root(self.ra)
             self.module = self.url[len(self.base):]
             self.modulemap = {} # revision, module
             self.commits = {}
             self.paths = {}
             self.uuid = svn.ra.get_uuid(self.ra).decode(self.encoding)
         except SubversionException, e:
             ui.print_exc()
             raise NoRepo("couldn't open SVN repo %s" % self.url)
 
         if rev:
             try:
                 latest = int(rev)
             except ValueError:
                 raise util.Abort('svn: revision %s is not an integer' % rev)
 
         try:
             self.get_blacklist()
         except IOError, e:
             pass
 
         self.last_changed = self.latest(self.module, latest)
 
         self.head = self.revid(self.last_changed)
         self._changescache = None
 
     def setrevmap(self, revmap):
         lastrevs = {}
         for revid in revmap.iterkeys():
             uuid, module, revnum = self.revsplit(revid)
             lastrevnum = lastrevs.setdefault(module, revnum)
             if revnum > lastrevnum:
                 lastrevs[module] = revnum
         self.lastrevs = lastrevs
 
     def exists(self, path, optrev):
         try:
             svn.client.ls(self.url.rstrip('/') + '/' + path,
                                  optrev, False, self.ctx)
             return True
         except SubversionException, err:
             return False
 
     def getheads(self):
         # detect standard /branches, /tags, /trunk layout
         rev = optrev(self.last_changed)
         rpath = self.url.strip('/')
         cfgtrunk = self.ui.config('convert', 'svn.trunk')
         cfgbranches = self.ui.config('convert', 'svn.branches')
         cfgtags = self.ui.config('convert', 'svn.tags')
         trunk = (cfgtrunk or 'trunk').strip('/')
         branches = (cfgbranches or 'branches').strip('/')
         tags = (cfgtags or 'tags').strip('/')
         if self.exists(trunk, rev) and self.exists(branches, rev) and self.exists(tags, rev):
             self.ui.note('found trunk at %r, branches at %r and tags at %r\n' %
                          (trunk, branches, tags))
             oldmodule = self.module
             self.module += '/' + trunk
             lt = self.latest(self.module, self.last_changed)
             self.head = self.revid(lt)
             self.heads = [self.head]
             branchnames = svn.client.ls(rpath + '/' + branches, rev, False,
                                         self.ctx)
             for branch in branchnames.keys():
                 if oldmodule:
                     module = oldmodule + '/' + branches + '/' + branch
                 else:
                     module = '/' + branches + '/' + branch
                 brevnum = self.latest(module, self.last_changed)
                 brev = self.revid(brevnum, module)
                 self.ui.note('found branch %s at %d\n' % (branch, brevnum))
                 self.heads.append(brev)
 
             if oldmodule:
                 self.tags = '%s/%s' % (oldmodule, tags) 
             else:
                 self.tags = '/%s' % tags
 
         elif cfgtrunk or cfgbranches or cfgtags:
             raise util.Abort('trunk/branch/tags layout expected, but not found')
         else:
             self.ui.note('working with one branch\n')
             self.heads = [self.head]
             self.tags  = tags
         return self.heads
 
     def getfile(self, file, rev):
         data, mode = self._getfile(file, rev)
         self.modecache[(file, rev)] = mode
         return data
 
     def getmode(self, file, rev):
         return self.modecache[(file, rev)]
 
     def getchanges(self, rev):
         if self._changescache and self._changescache[0] == rev:
             return self._changescache[1]
         self._changescache = None
         self.modecache = {}
         (paths, parents) = self.paths[rev]
         files, copies = self.expandpaths(rev, paths, parents)
         files.sort()
         files = zip(files, [rev] * len(files))
 
         # caller caches the result, so free it here to release memory
         del self.paths[rev]
         return (files, copies)
 
     def getchangedfiles(self, rev, i):
         changes = self.getchanges(rev)
         self._changescache = (rev, changes)
         return [f[0] for f in changes[0]]
 
     def getcommit(self, rev):
         if rev not in self.commits:
             uuid, module, revnum = self.revsplit(rev)
             self.module = module
             self.reparent(module)
             stop = self.lastrevs.get(module, 0)
             self._fetch_revisions(from_revnum=revnum, to_revnum=stop)
         commit = self.commits[rev]
         # caller caches the result, so free it here to release memory
         del self.commits[rev]
         return commit
 
     def get_log(self, paths, start, end, limit=0, discover_changed_paths=True,
                 strict_node_history=False):
 
         def parent(fp):
             while True:
                 entry = pickle.load(fp)
                 try:
                     orig_paths, revnum, author, date, message = entry
                 except:
                     if entry is None:
                         break
                     raise SubversionException("child raised exception", entry)
                 yield entry
 
         args = [self.url, paths, start, end, limit, discover_changed_paths,
                 strict_node_history]
         arg = encodeargs(args)
         hgexe = util.hgexecutable()
         cmd = '%s debugsvnlog' % util.shellquote(hgexe)
         stdin, stdout = os.popen2(cmd, 'b')
 
         stdin.write(arg)
         stdin.close()
 
         for p in parent(stdout):
             yield p
 
     def gettags(self):
         tags = {}
         start = self.revnum(self.head)
         try:
             for entry in self.get_log([self.tags], 0, start):
                 orig_paths, revnum, author, date, message = entry
                 for path in orig_paths:
                     if not path.startswith(self.tags+'/'):
                         continue
                     ent = orig_paths[path]
                     source = ent.copyfrom_path
                     rev = ent.copyfrom_rev
                     tag = path.split('/')[-1]
                     tags[tag] = self.revid(rev, module=source)
         except SubversionException, (inst, num):
             self.ui.note('no tags found at revision %d\n' % start)
         return tags
 
     # -- helper functions --
 
     def revid(self, revnum, module=None):
         if not module:
             module = self.module
         return u"svn:%s%s@%s" % (self.uuid, module.decode(self.encoding),
                                  revnum)
 
     def revnum(self, rev):
         return int(rev.split('@')[-1])
 
     def revsplit(self, rev):
         url, revnum = rev.encode(self.encoding).split('@', 1)
         revnum = int(revnum)
         parts = url.split('/', 1)
         uuid = parts.pop(0)[4:]
         mod = ''
         if parts:
             mod = '/' + parts[0]
         return uuid, mod, revnum
 
     def latest(self, path, stop=0):
         'find the latest revision affecting path, up to stop'
         if not stop:
             stop = svn.ra.get_latest_revnum(self.ra)
         try:
             self.reparent('')
             dirent = svn.ra.stat(self.ra, path.strip('/'), stop)
             self.reparent(self.module)
         except SubversionException:
             dirent = None
         if not dirent:
             raise util.Abort('%s not found up to revision %d' % (path, stop))
 
         return dirent.created_rev
 
     def get_blacklist(self):
         """Avoid certain revision numbers.
         It is not uncommon for two nearby revisions to cancel each other
         out, e.g. 'I copied trunk into a subdirectory of itself instead
         of making a branch'. The converted repository is significantly
         smaller if we ignore such revisions."""
         self.blacklist = util.set()
         blacklist = self.blacklist
         for line in file("blacklist.txt", "r"):
             if not line.startswith("#"):
                 try:
                     svn_rev = int(line.strip())
                     blacklist.add(svn_rev)
                 except ValueError, e:
                     pass # not an integer or a comment
 
     def is_blacklisted(self, svn_rev):
         return svn_rev in self.blacklist
 
     def reparent(self, module):
         svn_url = self.base + module
         self.ui.debug("reparent to %s\n" % svn_url.encode(self.encoding))
         svn.ra.reparent(self.ra, svn_url.encode(self.encoding))
 
     def expandpaths(self, rev, paths, parents):
         def get_entry_from_path(path, module=self.module):
             # Given the repository url of this wc, say
             #   "http://server/plone/CMFPlone/branches/Plone-2_0-branch"
             # extract the "entry" portion (a relative path) from what
             # svn log --xml says, ie
             #   "/CMFPlone/branches/Plone-2_0-branch/tests/PloneTestCase.py"
             # that is to say "tests/PloneTestCase.py"
             if path.startswith(module):
                 relative = path[len(module):]
                 if relative.startswith('/'):
                     return relative[1:]
                 else:
                     return relative
 
             # The path is outside our tracked tree...
             self.ui.debug('%r is not under %r, ignoring\n' % (path, module))
             return None
 
         entries = []
         copyfrom = {} # Map of entrypath, revision for finding source of deleted revisions.
         copies = {}
         revnum = self.revnum(rev)
 
         if revnum in self.modulemap:
             new_module = self.modulemap[revnum]
             if new_module != self.module:
                 self.module = new_module
                 self.reparent(self.module)
 
         for path, ent in paths:
             entrypath = get_entry_from_path(path, module=self.module)
             entry = entrypath.decode(self.encoding)
 
             kind = svn.ra.check_path(self.ra, entrypath, revnum)
             if kind == svn.core.svn_node_file:
                 if ent.copyfrom_path:
                     copyfrom_path = get_entry_from_path(ent.copyfrom_path)
                     if copyfrom_path:
                         self.ui.debug("Copied to %s from %s@%s\n" % (entry, copyfrom_path, ent.copyfrom_rev))
                         # It's probably important for hg that the source
                         # exists in the revision's parent, not just the
                         # ent.copyfrom_rev
                         fromkind = svn.ra.check_path(self.ra, copyfrom_path, ent.copyfrom_rev)
                         if fromkind != 0:
                             copies[self.recode(entry)] = self.recode(copyfrom_path)
                 entries.append(self.recode(entry))
             elif kind == 0: # gone, but had better be a deleted *file*
                 self.ui.debug("gone from %s\n" % ent.copyfrom_rev)
 
                 # if a branch is created but entries are removed in the same
                 # changeset, get the right fromrev
                 if parents:
                     uuid, old_module, fromrev = self.revsplit(parents[0])
                 else:
                     fromrev = revnum - 1
                     # might always need to be revnum - 1 in these 3 lines?
                     old_module = self.modulemap.get(fromrev, self.module)
 
                 basepath = old_module + "/" + get_entry_from_path(path, module=self.module)
                 entrypath = old_module + "/" + get_entry_from_path(path, module=self.module)
 
                 def lookup_parts(p):
                     rc = None
                     parts = p.split("/")
                     for i in range(len(parts)):
                         part = "/".join(parts[:i])
                         info = part, copyfrom.get(part, None)
                         if info[1] is not None:
                             self.ui.debug("Found parent directory %s\n" % info[1])
                             rc = info
                     return rc
 
                 self.ui.debug("base, entry %s %s\n" % (basepath, entrypath))
 
                 frompath, froment = lookup_parts(entrypath) or (None, revnum - 1)
 
                 # need to remove fragment from lookup_parts and replace with copyfrom_path
                 if frompath is not None:
                     self.ui.debug("munge-o-matic\n")
                     self.ui.debug(entrypath + '\n')
                     self.ui.debug(entrypath[len(frompath):] + '\n')
                     entrypath = froment.copyfrom_path + entrypath[len(frompath):]
                     fromrev = froment.copyfrom_rev
                     self.ui.debug("Info: %s %s %s %s\n" % (frompath, froment, ent, entrypath))
 
                 fromkind = svn.ra.check_path(self.ra, entrypath, fromrev)
                 if fromkind == svn.core.svn_node_file:   # a deleted file
                     entries.append(self.recode(entry))
                 elif fromkind == svn.core.svn_node_dir:
                     # print "Deleted/moved non-file:", revnum, path, ent
                     # children = self._find_children(path, revnum - 1)
                     # print "find children %s@%d from %d action %s" % (path, revnum, ent.copyfrom_rev, ent.action)
                     # Sometimes this is tricky. For example: in
                     # The Subversion Repository revision 6940 a dir
                     # was copied and one of its files was deleted
                     # from the new location in the same commit. This
                     # code can't deal with that yet.
                     if ent.action == 'C':
                         children = self._find_children(path, fromrev)
                     else:
                         oroot = entrypath.strip('/')
                         nroot = path.strip('/')
                         children = self._find_children(oroot, fromrev)
                         children = [s.replace(oroot,nroot) for s in children]
                     # Mark all [files, not directories] as deleted.
                     for child in children:
                         # Can we move a child directory and its
                         # parent in the same commit? (probably can). Could
                         # cause problems if instead of revnum -1,
                         # we have to look in (copyfrom_path, revnum - 1)
                         entrypath = get_entry_from_path("/" + child, module=old_module)
                         if entrypath:
                             entry = self.recode(entrypath.decode(self.encoding))
                             if entry in copies:
                                 # deleted file within a copy
                                 del copies[entry]
                             else:
                                 entries.append(entry)
                 else:
                     self.ui.debug('unknown path in revision %d: %s\n' % \
                                   (revnum, path))
             elif kind == svn.core.svn_node_dir:
                 # Should probably synthesize normal file entries
                 # and handle as above to clean up copy/rename handling.
 
                 # If the directory just had a prop change,
                 # then we shouldn't need to look for its children.
                 # Also this could create duplicate entries. Not sure
                 # whether this will matter. Maybe should make entries a set.
                 # print "Changed directory", revnum, path, ent.action, ent.copyfrom_path, ent.copyfrom_rev
                 # This will fail if a directory was copied
                 # from another branch and then some of its files
                 # were deleted in the same transaction.
                 children = self._find_children(path, revnum)
                 children.sort()
                 for child in children:
                     # Can we move a child directory and its
                     # parent in the same commit? (probably can). Could
                     # cause problems if instead of revnum -1,
                     # we have to look in (copyfrom_path, revnum - 1)
                     entrypath = get_entry_from_path("/" + child, module=self.module)
                     # print child, self.module, entrypath
                     if entrypath:
                         # Need to filter out directories here...
                         kind = svn.ra.check_path(self.ra, entrypath, revnum)
                         if kind != svn.core.svn_node_dir:
                             entries.append(self.recode(entrypath))
 
                 # Copies here (must copy all from source)
                 # Probably not a real problem for us if
                 # source does not exist
 
                 # Can do this with the copy command "hg copy"
                 # if ent.copyfrom_path:
                 #     copyfrom_entry = get_entry_from_path(ent.copyfrom_path.decode(self.encoding),
                 #             module=self.module)
                 #     copyto_entry = entrypath
                 #
                 #     print "copy directory", copyfrom_entry, 'to', copyto_entry
                 #
                 #     copies.append((copyfrom_entry, copyto_entry))
 
                 if ent.copyfrom_path:
                     copyfrom_path = ent.copyfrom_path.decode(self.encoding)
                     copyfrom_entry = get_entry_from_path(copyfrom_path, module=self.module)
                     if copyfrom_entry:
                         copyfrom[path] = ent
                         self.ui.debug("mark %s came from %s\n" % (path, copyfrom[path]))
 
                         # Good, /probably/ a regular copy. Really should check
                         # to see whether the parent revision actually contains
                         # the directory in question.
                         children = self._find_children(self.recode(copyfrom_path), ent.copyfrom_rev)
                         children.sort()
                         for child in children:
                             entrypath = get_entry_from_path("/" + child, module=self.module)
                             if entrypath:
                                 entry = entrypath.decode(self.encoding)
                                 # print "COPY COPY From", copyfrom_entry, entry
                                 copyto_path = path + entry[len(copyfrom_entry):]
                                 copyto_entry =  get_entry_from_path(copyto_path, module=self.module)
                                 # print "COPY", entry, "COPY To", copyto_entry
                                 copies[self.recode(copyto_entry)] = self.recode(entry)
                                 # copy from quux splort/quuxfile
 
         return (entries, copies)
 
     def _fetch_revisions(self, from_revnum = 0, to_revnum = 347):
         self.child_cset = None
         def parselogentry(orig_paths, revnum, author, date, message):
             self.ui.debug("parsing revision %d (%d changes)\n" %
                           (revnum, len(orig_paths)))
 
             if revnum in self.modulemap:
                 new_module = self.modulemap[revnum]
                 if new_module != self.module:
                     self.module = new_module
                     self.reparent(self.module)
 
             rev = self.revid(revnum)
             # branch log might return entries for a parent we already have
             if (rev in self.commits or
                 (revnum < self.lastrevs.get(self.module, 0))):
                 return
 
             parents = []
             # check whether this revision is the start of a branch
             if self.module in orig_paths:
                 ent = orig_paths[self.module]
                 if ent.copyfrom_path:
                     # ent.copyfrom_rev may not be the actual last revision
                     prev = self.latest(ent.copyfrom_path, ent.copyfrom_rev)
                     self.modulemap[prev] = ent.copyfrom_path
                     parents = [self.revid(prev, ent.copyfrom_path)]
                     self.ui.note('found parent of branch %s at %d: %s\n' % \
                                      (self.module, prev, ent.copyfrom_path))
                 else:
                     self.ui.debug("No copyfrom path, don't know what to do.\n")
 
             self.modulemap[revnum] = self.module # track backwards in time
 
             orig_paths = orig_paths.items()
             orig_paths.sort()
             paths = []
             # filter out unrelated paths
             for path, ent in orig_paths:
                 if not path.startswith(self.module):
                     self.ui.debug("boring@%s: %s\n" % (revnum, path))
                     continue
                 paths.append((path, ent))
 
             self.paths[rev] = (paths, parents)
 
             # Example SVN datetime. Includes microseconds.
             # ISO-8601 conformant
             # '2007-01-04T17:35:00.902377Z'
             date = util.parsedate(date[:18] + " UTC", ["%Y-%m-%dT%H:%M:%S"])
 
             log = message and self.recode(message)
             author = author and self.recode(author) or ''
             try:
                 branch = self.module.split("/")[-1]
                 if branch == 'trunk':
                     branch = ''
             except IndexError:
                 branch = None
 
             cset = commit(author=author,
                           date=util.datestr(date),
                           desc=log,
                           parents=parents,
                           branch=branch,
                           rev=rev.encode('utf-8'))
 
             self.commits[rev] = cset
             if self.child_cset and not self.child_cset.parents:
                 self.child_cset.parents = [rev]
             self.child_cset = cset
 
         self.ui.note('fetching revision log for "%s" from %d to %d\n' %
                      (self.module, from_revnum, to_revnum))
 
         try:
             for entry in self.get_log([self.module], from_revnum, to_revnum):
                 orig_paths, revnum, author, date, message = entry
                 if self.is_blacklisted(revnum):
                     self.ui.note('skipping blacklisted revision %d\n' % revnum)
                     continue
                 if orig_paths is None:
                     self.ui.debug('revision %d has no entries\n' % revnum)
                     continue
                 parselogentry(orig_paths, revnum, author, date, message)
         except SubversionException, (inst, num):
             if num == svn.core.SVN_ERR_FS_NO_SUCH_REVISION:
                 raise NoSuchRevision(branch=self,
                     revision="Revision number %d" % to_revnum)
             raise
 
     def _getfile(self, file, rev):
         io = StringIO()
         # TODO: ra.get_file transmits the whole file instead of diffs.
         mode = ''
         try:
             revnum = self.revnum(rev)
             if self.module != self.modulemap[revnum]:
                 self.module = self.modulemap[revnum]
                 self.reparent(self.module)
             info = svn.ra.get_file(self.ra, file, revnum, io)
             if isinstance(info, list):
                 info = info[-1]
             mode = ("svn:executable" in info) and 'x' or ''
             mode = ("svn:special" in info) and 'l' or mode
         except SubversionException, e:
             notfound = (svn.core.SVN_ERR_FS_NOT_FOUND,
                 svn.core.SVN_ERR_RA_DAV_PATH_NOT_FOUND)
             if e.apr_err in notfound: # File not found
                 raise IOError()
             raise
         data = io.getvalue()
         if mode == 'l':
             link_prefix = "link "
             if data.startswith(link_prefix):
                 data = data[len(link_prefix):]
         return data, mode
 
     def _find_children(self, path, revnum):
         path = path.strip('/')
         pool = Pool()
         rpath = '/'.join([self.base, path]).strip('/')
         return ['%s/%s' % (path, x) for x in svn.client.ls(rpath, optrev(revnum), True, self.ctx, pool).keys()]
+
+pre_revprop_change = '''#!/bin/sh
+
+REPOS="$1"
+REV="$2"
+USER="$3"
+PROPNAME="$4"
+ACTION="$5"
+
+if [ "$ACTION" = "M" -a "$PROPNAME" = "svn:log" ]; then exit 0; fi
+if [ "$ACTION" = "A" -a "$PROPNAME" = "hg:convert-branch" ]; then exit 0; fi
+if [ "$ACTION" = "A" -a "$PROPNAME" = "hg:convert-rev" ]; then exit 0; fi
+
+echo "Changing prohibited revision property" >&2
+exit 1
+'''
+
+class svn_sink(converter_sink, commandline):
+    commit_re = re.compile(r'Committed revision (\d+).', re.M)
+
+    def prerun(self):
+        if self.wc:
+            os.chdir(self.wc)
+
+    def postrun(self):
+        if self.wc:
+            os.chdir(self.cwd)
+
+    def join(self, name):
+        return os.path.join(self.wc, '.svn', name)
+        
+    def revmapfile(self):
+        return self.join('hg-shamap')
+
+    def authorfile(self):
+        return self.join('hg-authormap')
+
+    def __init__(self, ui, path):
+        converter_sink.__init__(self, ui, path)
+        commandline.__init__(self, ui, 'svn')
+        self.delete = []
+        self.wc = None
+        self.cwd = os.getcwd()
+
+        path = os.path.realpath(path)
+
+        created = False
+        if os.path.isfile(os.path.join(path, '.svn', 'entries')):
+            self.wc = path
+            self.run0('update')
+        else:
+            if os.path.isdir(os.path.dirname(path)):
+                if not os.path.exists(os.path.join(path, 'db', 'fs-type')):
+                    ui.status(_('initializing svn repo %r\n') %
+                              os.path.basename(path))
+                    commandline(ui, 'svnadmin').run0('create', path)
+                    created = path
+                path = 'file://' + path
+            wcpath = os.path.join(os.getcwd(), os.path.basename(path) + '-wc')
+            ui.status(_('initializing svn wc %r\n') % os.path.basename(wcpath))
+            self.run0('checkout', path, wcpath)
+
+            self.wc = wcpath
+        self.opener = util.opener(self.wc)
+        self.wopener = util.opener(self.wc)
+        self.childmap = mapfile(ui, self.join('hg-childmap'))
+
+        if created:
+            hook = os.path.join(created, 'hooks', 'pre-revprop-change')
+            fp = open(hook, 'w')
+            fp.write(pre_revprop_change)
+            fp.close()
+            util.set_exec(hook, True)
+
+    def wjoin(self, *names):
+        return os.path.join(self.wc, *names)
+
+    def putfile(self, filename, flags, data):
+        if 'l' in flags:
+            self.wopener.symlink(data, filename)
+        else:
+            try:
+                if os.path.islink(self.wjoin(filename)):
+                    os.unlink(filename)
+            except OSError:
+                pass
+            self.wopener(filename, 'w').write(data)
+            was_exec = util.is_exec(self.wjoin(filename))
+            util.set_exec(self.wjoin(filename), 'x' in flags)
+            if was_exec:
+                if 'x' not in flags:
+                    self.run0('propdel', 'svn:executable', filename)
+            else:
+                if 'x' in flags:
+                    self.run0('propset', 'svn:executable', '*', filename)
+            
+    def delfile(self, name):
+        self.delete.append(name)
+
+    def copyfile(self, source, dest):
+        # SVN's copy command pukes if the destination file exists, but
+        # our copyfile method expects to record a copy that has
+        # already occurred.  Cross the semantic gap.
+        wdest = self.wjoin(dest)
+        exists = os.path.exists(wdest)
+        if exists:
+            fd, tempname = tempfile.mkstemp(
+                prefix='hg-copy-', dir=os.path.dirname(wdest))
+            os.close(fd)
+            os.unlink(tempname)
+            os.rename(wdest, tempname)
+        try:
+            self.run0('copy', source, dest)
+        finally:
+            if exists:
+                try:
+                    os.unlink(wdest)
+                except OSError:
+                    pass
+                os.rename(tempname, wdest)
+
+    def dirs_of(self, files):
+        dirs = set()
+        for f in files:
+            if os.path.isdir(self.wjoin(f)):
+                dirs.add(f)
+            for i in strutil.rfindall(f, '/'):
+                dirs.add(f[:i])
+        return dirs
+
+    def add_files(self, files):
+        add_dirs = [d for d in self.dirs_of(files)
+                    if not os.path.exists(self.wjoin(d, '.svn', 'entries'))]
+        if add_dirs:
+            self.run('add', non_recursive=True, quiet=True, *add)
+        if files:
+            self.run('add', quiet=True, *files)
+        return files.union(add_dirs)
+        
+    def tidy_dirs(self, names):
+        dirs = list(self.dirs_of(names))
+        dirs.sort(reverse=True)
+        deleted = []
+        for d in dirs:
+            wd = self.wjoin(d)
+            if os.listdir(wd) == '.svn':
+                self.run0('delete', d)
+                deleted.append(d)
+        return deleted
+
+    def addchild(self, parent, child):
+        self.childmap[parent] = child
+
+    def putcommit(self, files, parents, commit):
+        for parent in parents:
+            try:
+                return self.childmap[parent]
+            except KeyError:
+                pass
+        entries = set(self.delete)
+        if self.delete:
+            self.run0('delete', *self.delete)
+            self.delete = []
+        files = util.frozenset(files)
+        entries.update(self.add_files(files.difference(entries)))
+        entries.update(self.tidy_dirs(entries))
+        fd, messagefile = tempfile.mkstemp(prefix='hg-convert-')
+        fp = os.fdopen(fd, 'w')
+        fp.write(commit.desc)
+        fp.close()
+        try:
+            output = self.run0('commit',
+                               username=util.shortuser(commit.author),
+                               file=messagefile,
+                               *list(entries))
+            try:
+                rev = self.commit_re.search(output).group(1)
+            except AttributeError:
+                self.ui.warn(_('unexpected svn output:\n'))
+                self.ui.warn(output)
+                raise util.Abort(_('unable to cope with svn output'))
+            if commit.rev:
+                self.run('propset', 'hg:convert-rev', commit.rev,
+                         revprop=True, revision=rev)
+            if commit.branch and commit.branch != 'default':
+                self.run('propset', 'hg:convert-branch', commit.branch,
+                         revprop=True, revision=rev)
+            for parent in parents:
+                self.addchild(parent, rev)
+            return rev
+        finally:
+            os.unlink(messagefile)
+
+    def puttags(self, tags):
+        self.ui.warn(_('XXX TAGS NOT IMPLEMENTED YET\n'))

tests/test-convert.out

@@ -1,95 +1,96 b''
 hg convert [OPTION]... SOURCE [DEST [MAPFILE]]
 
 Convert a foreign SCM repository to a Mercurial one.
 
     Accepted source formats:
     - Mercurial
     - CVS
     - Darcs
     - git
     - Subversion
 
     Accepted destination formats:
     - Mercurial
+    - Subversion (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 <MAPFILE> isn't given, it will be put in a default location
     (<dest>/.hg/shamap by default).  The <MAPFILE> 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.
 
 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
     --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