convert: hg sink commits without working dir

hgext/convert/hg.py

@@ -1,305 +1,290
 # hg backend for convert extension
 
 # Notes for hg->hg conversion:
 #
 # * Old versions of Mercurial didn't trim the whitespace from the ends
 #   of commit messages, but new versions do.  Changesets created by
 #   those older versions, then converted, may thus have different
 #   hashes for changesets that are otherwise identical.
 #
 # * By default, the source revision is stored in the converted
 #   revision.  This will cause the converted revision to have a
 #   different identity than the source.  To avoid this, use the
 #   following option: "--config convert.hg.saverev=false"
 
 
 import os, time
 from mercurial.i18n import _
 from mercurial.repo import RepoError
 from mercurial.node import bin, hex, nullid
-from mercurial import hg, revlog, util
+from mercurial import hg, revlog, util, context
 
 from common import NoRepo, commit, converter_source, converter_sink
 
 class mercurial_sink(converter_sink):
     def __init__(self, ui, path):
         converter_sink.__init__(self, ui, path)
         self.branchnames = ui.configbool('convert', 'hg.usebranchnames', True)
         self.clonebranches = ui.configbool('convert', 'hg.clonebranches', False)
         self.tagsbranch = ui.config('convert', 'hg.tagsbranch', 'default')
         self.lastbranch = None
         if os.path.isdir(path) and len(os.listdir(path)) > 0:
             try:
                 self.repo = hg.repository(self.ui, path)
                 if not self.repo.local():
                     raise NoRepo(_('%s is not a local Mercurial repo') % path)
             except RepoError, err:
                 ui.print_exc()
                 raise NoRepo(err.args[0])
         else:
             try:
                 ui.status(_('initializing destination %s repository\n') % path)
                 self.repo = hg.repository(self.ui, path, create=True)
                 if not self.repo.local():
                     raise NoRepo(_('%s is not a local Mercurial repo') % path)
                 self.created.append(path)
             except RepoError, err:
                 ui.print_exc()
                 raise NoRepo("could not create hg repo %s as sink" % path)
         self.lock = None
         self.wlock = None
         self.filemapmode = False
 
     def before(self):
         self.ui.debug(_('run hg sink pre-conversion action\n'))
         self.wlock = self.repo.wlock()
         self.lock = self.repo.lock()
-        self.repo.dirstate.clear()
 
     def after(self):
         self.ui.debug(_('run hg sink post-conversion action\n'))
-        self.repo.dirstate.invalidate()
         self.lock = None
         self.wlock = None
 
     def revmapfile(self):
         return os.path.join(self.path, ".hg", "shamap")
 
     def authorfile(self):
         return os.path.join(self.path, ".hg", "authormap")
 
     def getheads(self):
         h = self.repo.changelog.heads()
         return [ hex(x) for x in h ]
 
     def setbranch(self, branch, pbranches):
         if not self.clonebranches:
             return
 
         setbranch = (branch != self.lastbranch)
         self.lastbranch = branch
         if not branch:
             branch = 'default'
         pbranches = [(b[0], b[1] and b[1] or 'default') for b in pbranches]
         pbranch = pbranches and pbranches[0][1] or 'default'
 
         branchpath = os.path.join(self.path, branch)
         if setbranch:
             self.after()
             try:
                 self.repo = hg.repository(self.ui, branchpath)
             except:
                 self.repo = hg.repository(self.ui, branchpath, create=True)
             self.before()
 
         # pbranches may bring revisions from other branches (merge parents)
         # Make sure we have them, or pull them.
         missings = {}
         for b in pbranches:
             try:
                 self.repo.lookup(b[0])
             except:
                 missings.setdefault(b[1], []).append(b[0])
 
         if missings:
             self.after()
             for pbranch, heads in missings.iteritems():
                 pbranchpath = os.path.join(self.path, pbranch)
                 prepo = hg.repository(self.ui, pbranchpath)
                 self.ui.note(_('pulling from %s into %s\n') % (pbranch, branch))
                 self.repo.pull(prepo, [prepo.lookup(h) for h in heads])
             self.before()
 
     def putcommit(self, files, copies, parents, commit, source):
-        # Apply changes to working copy
-        for f, v in files:
-            try:
-                data = source.getfile(f, v)
-            except IOError, inst:
-                try:
-                    util.unlink(self.repo.wjoin(f))
-                except OSError:
-                    pass
-            else:
-                e = source.getmode(f, v)
-                self.repo.wwrite(f, data, e)
-                if f not in self.repo.dirstate:
-                    self.repo.dirstate.normallookup(f)
-                if f in copies:
-                    self.repo.copy(copies[f], f)
-        files = [f[0] for f in files]
 
-        seen = {}
+        files = dict(files)
+        def getfilectx(repo, memctx, f):
+            v = files[f]
+            data = source.getfile(f, v)
+            e = source.getmode(f, v)
+            return context.memfilectx(f, data, 'l' in e, 'x' in e, copies.get(f))
+
         pl = []
         for p in parents:
-            if p not in seen:
+            if p not in pl:
                 pl.append(p)
-                seen[p] = 1
         parents = pl
         nparents = len(parents)
         if self.filemapmode and nparents == 1:
             m1node = self.repo.changelog.read(bin(parents[0]))[0]
             parent = parents[0]
 
         if len(parents) < 2: parents.append("0" * 40)
         if len(parents) < 2: parents.append("0" * 40)
         p2 = parents.pop(0)
 
         text = commit.desc
         extra = commit.extra.copy()
         if self.branchnames and commit.branch:
             extra['branch'] = commit.branch
         if commit.rev:
             extra['convert_revision'] = commit.rev
 
         while parents:
             p1 = p2
             p2 = parents.pop(0)
-            a = self.repo.rawcommit(files, text, commit.author, commit.date,
-                                    bin(p1), bin(p2), extra=extra)
-            self.repo.dirstate.clear()
+            ctx = context.memctx(self.repo, (p1, p2), text, files.keys(), getfilectx,
+                                 commit.author, commit.date, extra)
+            a = self.repo.commitctx(ctx)
             text = "(octopus merge fixup)\n"
             p2 = hex(self.repo.changelog.tip())
 
         if self.filemapmode and nparents == 1:
             man = self.repo.manifest
             mnode = self.repo.changelog.read(bin(p2))[0]
             if not man.cmp(m1node, man.revision(mnode)):
                 self.repo.rollback()
-                self.repo.dirstate.clear()
                 return parent
         return p2
 
     def puttags(self, tags):
-        try:
-            old = self.repo.wfile(".hgtags").read()
-            oldlines = old.splitlines(1)
-            oldlines.sort()
-        except:
-            oldlines = []
+         try:
+             parentctx = self.repo.changectx(self.tagsbranch)
+             tagparent = parentctx.node()
+         except RepoError, inst:
+             parentctx = None
+             tagparent = nullid
 
-        k = tags.keys()
-        k.sort()
-        newlines = []
-        for tag in k:
-            newlines.append("%s %s\n" % (tags[tag], tag))
-
-        newlines.sort()
+         try:
+             old = parentctx.filectx(".hgtags").data()
+             oldlines = old.splitlines(1)
+             oldlines.sort()
+         except:
+             oldlines = []
 
-        if newlines != oldlines:
-            self.ui.status("updating tags\n")
-            f = self.repo.wfile(".hgtags", "w")
-            f.write("".join(newlines))
-            f.close()
-            if not oldlines: self.repo.add([".hgtags"])
-            date = "%s 0" % int(time.mktime(time.gmtime()))
-            extra = {}
-            if self.tagsbranch != 'default':
-                extra['branch'] = self.tagsbranch
-            try:
-                tagparent = self.repo.changectx(self.tagsbranch).node()
-            except RepoError, inst:
-                tagparent = nullid
-            self.repo.rawcommit([".hgtags"], "update tags", "convert-repo",
-                                date, tagparent, nullid, extra=extra)
-            return hex(self.repo.changelog.tip())
+         newlines = [("%s %s\n" % (tags[tag], tag)) for tag in tags.keys()]
+         newlines.sort()
+
+         if newlines == oldlines:
+             return None
+         data = "".join(newlines)
+
+         def getfilectx(repo, memctx, f):
+            return context.memfilectx(f, data, False, False, None)
+
+         self.ui.status("updating tags\n")
+         date = "%s 0" % int(time.mktime(time.gmtime()))
+         extra = {'branch': self.tagsbranch}
+         ctx = context.memctx(self.repo, (tagparent, None), "update tags",
+                              [".hgtags"], getfilectx, "convert-repo", date,
+                              extra)
+         self.repo.commitctx(ctx)
+         return hex(self.repo.changelog.tip())
 
     def setfilemapmode(self, active):
         self.filemapmode = active
 
 class mercurial_source(converter_source):
     def __init__(self, ui, path, rev=None):
         converter_source.__init__(self, ui, path, rev)
         self.saverev = ui.configbool('convert', 'hg.saverev', True)
         try:
             self.repo = hg.repository(self.ui, path)
             # try to provoke an exception if this isn't really a hg
             # repo, but some other bogus compatible-looking url
             if not self.repo.local():
                 raise RepoError()
         except RepoError:
             ui.print_exc()
             raise NoRepo("%s is not a local Mercurial repo" % path)
         self.lastrev = None
         self.lastctx = None
         self._changescache = None
         self.convertfp = None
 
     def changectx(self, rev):
         if self.lastrev != rev:
             self.lastctx = self.repo.changectx(rev)
             self.lastrev = rev
         return self.lastctx
 
     def getheads(self):
         if self.rev:
             return [hex(self.repo.changectx(self.rev).node())]
         else:
             return [hex(node) for node in self.repo.heads()]
 
     def getfile(self, name, rev):
         try:
             return self.changectx(rev).filectx(name).data()
         except revlog.LookupError, err:
             raise IOError(err)
 
     def getmode(self, name, rev):
         m = self.changectx(rev).manifest()
         return (m.execf(name) and 'x' or '') + (m.linkf(name) and 'l' or '')
 
     def getchanges(self, rev):
         ctx = self.changectx(rev)
         if self._changescache and self._changescache[0] == rev:
             m, a, r = self._changescache[1]
         else:
             m, a, r = self.repo.status(ctx.parents()[0].node(), ctx.node())[:3]
         changes = [(name, rev) for name in m + a + r]
         changes.sort()
         return (changes, self.getcopies(ctx, m + a))
 
     def getcopies(self, ctx, files):
         copies = {}
         for name in files:
             try:
                 copies[name] = ctx.filectx(name).renamed()[0]
             except TypeError:
                 pass
         return copies
 
     def getcommit(self, rev):
         ctx = self.changectx(rev)
         parents = [hex(p.node()) for p in ctx.parents() if p.node() != nullid]
         if self.saverev:
             crev = rev
         else:
             crev = None
         return commit(author=ctx.user(), date=util.datestr(ctx.date()),
                       desc=ctx.description(), rev=crev, parents=parents,
                       branch=ctx.branch(), extra=ctx.extra())
 
     def gettags(self):
         tags = [t for t in self.repo.tagslist() if t[0] != 'tip']
         return dict([(name, hex(node)) for name, node in tags])
 
     def getchangedfiles(self, rev, i):
         ctx = self.changectx(rev)
         i = i or 0
         changes = self.repo.status(ctx.parents()[i].node(), ctx.node())[:3]
 
         if i == 0:
             self._changescache = (rev, changes)
 
         return changes[0] + changes[1] + changes[2]
 
     def converted(self, rev, destrev):
         if self.convertfp is None:
             self.convertfp = open(os.path.join(self.path, '.hg', 'shamap'),
                                   'a')
         self.convertfp.write('%s %s\n' % (destrev, rev))
         self.convertfp.flush()
 
     def before(self):
         self.ui.debug(_('run hg source pre-conversion action\n'))
 
     def after(self):
         self.ui.debug(_('run hg source post-conversion action\n'))

tests/test-convert-cvs

@@ -1,96 +1,101
 #!/bin/sh
 
 "$TESTDIR/hghave" cvs cvsps || exit 80
 
 cvscall()
 {
     cvs -f $@
 }
 
+hgcat()
+{
+    hg --cwd src-hg cat -r tip "$1"
+}
+
 echo "[extensions]" >> $HGRCPATH
 echo "convert = " >> $HGRCPATH
 
 echo % create cvs repository
 mkdir cvsrepo
 cd cvsrepo
 export CVSROOT=`pwd`
 export CVS_OPTIONS=-f
 cd ..
 
 cvscall -q -d "$CVSROOT" init
 
 echo % create source directory
 mkdir src-temp
 cd src-temp
 echo a > a
 mkdir b
 cd b
 echo c > c
 cd ..
 
 echo % import source directory
 cvscall -q import -m import src INITIAL start
 cd ..
 
 echo % checkout source directory
 cvscall -q checkout src
 
 echo % commit a new revision changing b/c
 cd src
 sleep 1
 echo c >> b/c
 cvscall -q commit -mci0 . | grep '<--' |\
     sed -e 's:.*src/\(.*\),v.*:checking in src/\1,v:g'
 cd ..
 
 echo % convert fresh repo
 hg convert src src-hg | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
-cat src-hg/a
-cat src-hg/b/c
+hgcat a
+hgcat b/c
 
 echo % convert fresh repo with --filemap
 echo include b/c > filemap
 hg convert --filemap filemap src src-filemap | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
-cat src-hg/b/c
+hgcat b/c
 hg -R src-filemap log --template '#rev# #desc# files: #files#\n'
 
 echo % commit new file revisions
 cd src
 echo a >> a
 echo c >> b/c
 cvscall -q commit -mci1 . | grep '<--' |\
     sed -e 's:.*src/\(.*\),v.*:checking in src/\1,v:g'
 cd ..
 
 echo % convert again
 hg convert src src-hg | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
-cat src-hg/a
-cat src-hg/b/c
+hgcat a
+hgcat b/c
 
 echo % convert again with --filemap
 hg convert --filemap filemap src src-filemap | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
-cat src-hg/b/c
+hgcat b/c
 hg -R src-filemap log --template '#rev# #desc# files: #files#\n'
 
 echo % commit branch
 cd src
 cvs -q update -r1.1 b/c
 cvs -q tag -b branch
 cvs -q update -r branch
 echo d >> b/c
 cvs -q commit -mci2 . | grep '<--' |\
     sed -e 's:.*src/\(.*\),v.*:checking in src/\1,v:g'
 cd ..
 
 echo % convert again
 hg convert src src-hg | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
-cat src-hg/a
-cat src-hg/b/c
+hgcat a
+hgcat b/c
 
 echo % convert again with --filemap
 hg convert --filemap filemap src src-filemap | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
-cat src-hg/b/c
+hgcat b/c
 hg -R src-filemap log --template '#rev# #desc# files: #files#\n'
 
 echo "graphlog = " >> $HGRCPATH
 hg -R src-hg glog --template '#rev# (#branches#) #desc# files: #files#\n'

tests/test-convert-cvs-builtincvsps

@@ -1,99 +1,104
 #!/bin/sh
 
 "$TESTDIR/hghave" cvs || exit 80
 
 cvscall()
 {
     cvs -f "$@"
 }
 
+hgcat()
+{
+    hg --cwd src-hg cat -r tip "$1"
+}
+
 echo "[extensions]" >> $HGRCPATH
 echo "convert = " >> $HGRCPATH
 echo "graphlog = " >> $HGRCPATH
 echo "[convert]" >> $HGRCPATH
 echo "cvsps=builtin" >> $HGRCPATH
 
 echo % create cvs repository
 mkdir cvsrepo
 cd cvsrepo
 export CVSROOT=`pwd`
 export CVS_OPTIONS=-f
 cd ..
 
 cvscall -q -d "$CVSROOT" init
 
 echo % create source directory
 mkdir src-temp
 cd src-temp
 echo a > a
 mkdir b
 cd b
 echo c > c
 cd ..
 
 echo % import source directory
 cvscall -q import -m import src INITIAL start
 cd ..
 
 echo % checkout source directory
 cvscall -q checkout src
 
 echo % commit a new revision changing b/c
 cd src
 sleep 1
 echo c >> b/c
 cvscall -q commit -mci0 . | grep '<--' |\
     sed -e 's:.*src/\(.*\),v.*:checking in src/\1,v:g'
 cd ..
 
 echo % convert fresh repo
 hg convert src src-hg | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
-cat src-hg/a
-cat src-hg/b/c
+hgcat a
+hgcat b/c
 
 echo % convert fresh repo with --filemap
 echo include b/c > filemap
 hg convert --filemap filemap src src-filemap | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
-cat src-hg/b/c
+hgcat b/c
 hg -R src-filemap log --template '#rev# #desc# files: #files#\n'
 
 echo % commit new file revisions
 cd src
 echo a >> a
 echo c >> b/c
 cvscall -q commit -mci1 . | grep '<--' |\
     sed -e 's:.*src/\(.*\),v.*:checking in src/\1,v:g'
 cd ..
 
 echo % convert again
 hg convert src src-hg | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
-cat src-hg/a
-cat src-hg/b/c
+hgcat a
+hgcat b/c
 
 echo % convert again with --filemap
 hg convert --filemap filemap src src-filemap | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
-cat src-hg/b/c
+hgcat b/c
 hg -R src-filemap log --template '#rev# #desc# files: #files#\n'
 
 echo % commit branch
 cd src
 cvs -q update -r1.1 b/c
 cvs -q tag -b branch
 cvs -q update -r branch
 echo d >> b/c
 cvs -q commit -mci2 . | grep '<--' |\
     sed -e 's:.*src/\(.*\),v.*:checking in src/\1,v:g'
 cd ..
 
 echo % convert again
 hg convert src src-hg | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
-cat src-hg/a
-cat src-hg/b/c
+hgcat a
+hgcat b/c
 
 echo % convert again with --filemap
 hg convert --filemap filemap src src-filemap | sed -e 's/connecting to.*cvsrepo/connecting to cvsrepo/g'
-cat src-hg/b/c
+hgcat b/c
 hg -R src-filemap log --template '#rev# #desc# files: #files#\n'
 
 echo "graphlog = " >> $HGRCPATH
 hg -R src-hg glog --template '#rev# (#branches#) #desc# files: #files#\n'

tests/test-convert-cvs-builtincvsps.out

@@ -1,139 +1,138
 % create cvs repository
 % create source directory
 % import source directory
 N src/a
 N src/b/c
 
 No conflicts created by this import
 
 % checkout source directory
 U src/a
 U src/b/c
 % commit a new revision changing b/c
 checking in src/b/c,v
 % convert fresh repo
 initializing destination src-hg repository
 using builtin cvsps
 collecting CVS rlog
 5 log entries
 creating changesets
 3 changeset entries
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 2 Initial revision
 1 import
 0 ci0
 updating tags
 a
 c
 c
 % convert fresh repo with --filemap
 initializing destination src-filemap repository
 using builtin cvsps
 collecting CVS rlog
 5 log entries
 creating changesets
 3 changeset entries
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 2 Initial revision
 1 import
 rolling back last transaction
 0 ci0
 updating tags
 c
 c
 2 update tags files: .hgtags
 1 ci0 files: b/c
 0 Initial revision files: b/c
 % commit new file revisions
 checking in src/a,v
 checking in src/b/c,v
 % convert again
 using builtin cvsps
 collecting CVS rlog
 7 log entries
 creating changesets
 4 changeset entries
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 0 ci1
 a
 a
 c
 c
 c
 % convert again with --filemap
 using builtin cvsps
 collecting CVS rlog
 7 log entries
 creating changesets
 4 changeset entries
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 0 ci1
 c
 c
 c
 3 ci1 files: b/c
 2 update tags files: .hgtags
 1 ci0 files: b/c
 0 Initial revision files: b/c
 % commit branch
 U b/c
 T a
 T b/c
 checking in src/b/c,v
 % convert again
 using builtin cvsps
 collecting CVS rlog
 8 log entries
 creating changesets
 5 changeset entries
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 0 ci2
 a
-a
 c
 d
 % convert again with --filemap
 using builtin cvsps
 collecting CVS rlog
 8 log entries
 creating changesets
 5 changeset entries
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 0 ci2
 c
 d
 4 ci2 files: b/c
 3 ci1 files: b/c
 2 update tags files: .hgtags
 1 ci0 files: b/c
 0 Initial revision files: b/c
 o  5 (branch) ci2 files: b/c
 |
 | o  4 () ci1 files: a b/c
 | |
 | o  3 () update tags files: .hgtags
 | |
 | o  2 () ci0 files: b/c
 |/
 | o  1 (INITIAL) import files:
 |/
 o  0 () Initial revision files: a b/c
 

tests/test-convert-cvs.out

@@ -1,109 +1,108
 % create cvs repository
 % create source directory
 % import source directory
 N src/a
 N src/b/c
 
 No conflicts created by this import
 
 % checkout source directory
 U src/a
 U src/b/c
 % commit a new revision changing b/c
 checking in src/b/c,v
 % convert fresh repo
 initializing destination src-hg repository
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 2 Initial revision
 1 import
 0 ci0
 updating tags
 a
 c
 c
 % convert fresh repo with --filemap
 initializing destination src-filemap repository
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 2 Initial revision
 1 import
 rolling back last transaction
 0 ci0
 updating tags
 c
 c
 2 update tags files: .hgtags
 1 ci0 files: b/c
 0 Initial revision files: b/c
 % commit new file revisions
 checking in src/a,v
 checking in src/b/c,v
 % convert again
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 0 ci1
 a
 a
 c
 c
 c
 % convert again with --filemap
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 0 ci1
 c
 c
 c
 3 ci1 files: b/c
 2 update tags files: .hgtags
 1 ci0 files: b/c
 0 Initial revision files: b/c
 % commit branch
 U b/c
 T a
 T b/c
 checking in src/b/c,v
 % convert again
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 0 ci2
 a
-a
 c
 d
 % convert again with --filemap
 connecting to cvsrepo
 scanning source...
 sorting...
 converting...
 0 ci2
 c
 d
 4 ci2 files: b/c
 3 ci1 files: b/c
 2 update tags files: .hgtags
 1 ci0 files: b/c
 0 Initial revision files: b/c
 o  5 (branch) ci2 files: b/c
 |
 | o  4 () ci1 files: a b/c
 | |
 | o  3 () update tags files: .hgtags
 | |
 | o  2 () ci0 files: b/c
 |/
 | o  1 (INITIAL) import files:
 |/
 o  0 () Initial revision files: a b/c