convert/mtn: handle directory move into moved directory (issue1619/3)

hgext/convert/monotone.py

@@ -1,210 +1,214
 # monotone support for the convert extension
 
 import os, re, time
 from mercurial import util
 from common import NoRepo, MissingTool, commit, converter_source, checktool
 from common import commandline
 from mercurial.i18n import _
 
 class monotone_source(converter_source, commandline):
     def __init__(self, ui, path=None, rev=None):
         converter_source.__init__(self, ui, path, rev)
         commandline.__init__(self, ui, 'mtn')
 
         self.ui = ui
         self.path = path
 
         # regular expressions for parsing monotone output
         space    = r'\s*'
         name     = r'\s+"((?:\\"|[^"])*)"\s*'
         value    = name
         revision = r'\s+\[(\w+)\]\s*'
         lines    = r'(?:.|\n)+'
 
         self.dir_re      = re.compile(space + "dir" + name)
         self.file_re     = re.compile(space + "file" + name + "content" + revision)
         self.add_file_re = re.compile(space + "add_file" + name + "content" + revision)
         self.patch_re    = re.compile(space + "patch" + name + "from" + revision + "to" + revision)
         self.rename_re   = re.compile(space + "rename" + name + "to" + name)
         self.delete_re   = re.compile(space + "delete" + name)
         self.tag_re      = re.compile(space + "tag" + name + "revision" + revision)
         self.cert_re     = re.compile(lines + space + "name" + name + "value" + value)
 
         attr = space + "file" + lines + space + "attr" + space
         self.attr_execute_re = re.compile(attr  + '"mtn:execute"' + space + '"true"')
 
         # cached data
         self.manifest_rev = None
         self.manifest = None
         self.files = None
         self.dirs  = None
 
         norepo = NoRepo (_("%s does not look like a monotone repo") % path)
         if not os.path.exists(path):
             raise norepo
 
         checktool('mtn', abort=False)
 
         # test if there are any revisions
         self.rev = None
         try:
             self.getheads()
         except:
             raise norepo
         self.rev = rev
 
     def mtnrun(self, *args, **kwargs):
         kwargs['d'] = self.path
         return self.run0('automate', *args, **kwargs)
 
     def mtnloadmanifest(self, rev):
         if self.manifest_rev == rev:
             return
         self.manifest = self.mtnrun("get_manifest_of", rev).split("\n\n")
         self.manifest_rev = rev
         self.files = {}
         self.dirs = {}
 
         for e in self.manifest:
             m = self.file_re.match(e)
             if m:
                 attr = ""
                 name = m.group(1)
                 node = m.group(2)
                 if self.attr_execute_re.match(e):
                     attr += "x"
                 self.files[name] = (node, attr)
             m = self.dir_re.match(e)
             if m:
                 self.dirs[m.group(1)] = True
 
     def mtnisfile(self, name, rev):
         # a non-file could be a directory or a deleted or renamed file
         self.mtnloadmanifest(rev)
         try:
             self.files[name]
             return True
         except KeyError:
             return False
 
     def mtnisdir(self, name, rev):
         self.mtnloadmanifest(rev)
         try:
             self.dirs[name]
             return True
         except KeyError:
             return False
 
     def mtngetcerts(self, rev):
         certs = {"author":"<missing>", "date":"<missing>",
             "changelog":"<missing>", "branch":"<missing>"}
         cert_list = self.mtnrun("certs", rev).split('\n\n      key "')
         for e in cert_list:
             m = self.cert_re.match(e)
             if m:
                 name, value = m.groups()
                 value = value.replace(r'\"', '"')
                 value = value.replace(r'\\', '\\')
                 certs[name] = value
         # Monotone may have subsecond dates: 2005-02-05T09:39:12.364306
         certs["date"] = certs["date"].split('.')[0]
         return certs
 
     # implement the converter_source interface:
 
     def getheads(self):
         if not self.rev:
             return self.mtnrun("leaves").splitlines()
         else:
             return [self.rev]
 
     def getchanges(self, rev):
         #revision = self.mtncmd("get_revision %s" % rev).split("\n\n")
         revision = self.mtnrun("get_revision", rev).split("\n\n")
         files = {}
         ignoremove = {}
         renameddirs = []
         copies = {}
         for e in revision:
             m = self.add_file_re.match(e)
             if m:
                 files[m.group(1)] = rev
                 ignoremove[m.group(1)] = rev
             m = self.patch_re.match(e)
             if m:
                 files[m.group(1)] = rev
             # Delete/rename is handled later when the convert engine
             # discovers an IOError exception from getfile,
             # but only if we add the "from" file to the list of changes.
             m = self.delete_re.match(e)
             if m:
                 files[m.group(1)] = rev
             m = self.rename_re.match(e)
             if m:
                 toname = m.group(2)
                 fromname = m.group(1)
                 if self.mtnisfile(toname, rev):
                     ignoremove[toname] = 1
                     copies[toname] = fromname
                     files[toname] = rev
                     files[fromname] = rev
                 elif self.mtnisdir(toname, rev):
                     renameddirs.append((fromname, toname))
 
         # Directory renames can be handled only once we have recorded
         # all new files
         for fromdir, todir in renameddirs:
             renamed = {}
             for tofile in self.files:
                 if tofile in ignoremove:
                     continue
                 if tofile.startswith(todir + '/'):
                     renamed[tofile] = fromdir + tofile[len(todir):]
+                    # Avoid chained moves like:
+                    # d1(/a) => d3/d1(/a)
+                    # d2 => d3
+                    ignoremove[tofile] = 1
             for tofile, fromfile in renamed.items():
                 self.ui.debug (_("copying file in renamed dir from '%s' to '%s'") 
                                % (fromfile, tofile), '\n')
                 files[tofile] = rev
                 copies[tofile] = fromfile
             for fromfile in renamed.values():
                 files[fromfile] = rev
 
         return (files.items(), copies)
 
     def getmode(self, name, rev):
         self.mtnloadmanifest(rev)
         try:
             node, attr = self.files[name]
             return attr
         except KeyError:
             return ""
 
     def getfile(self, name, rev):
         if not self.mtnisfile(name, rev):
             raise IOError() # file was deleted or renamed
         try:
             return self.mtnrun("get_file_of", name, r=rev)
         except:
             raise IOError() # file was deleted or renamed
 
     def getcommit(self, rev):
         certs   = self.mtngetcerts(rev)
         return commit(
             author=certs["author"],
             date=util.datestr(util.strdate(certs["date"], "%Y-%m-%dT%H:%M:%S")),
             desc=certs["changelog"],
             rev=rev,
             parents=self.mtnrun("parents", rev).splitlines(),
             branch=certs["branch"])
 
     def gettags(self):
         tags = {}
         for e in self.mtnrun("tags").split("\n\n"):
             m = self.tag_re.match(e)
             if m:
                 tags[m.group(1)] = m.group(2)
         return tags
 
     def getchangedfiles(self, rev, i):
         # This function is only needed to support --filemap
         # ... and we don't support that
         raise NotImplementedError()

tests/test-convert-mtn

@@ -1,122 +1,146
 #!/bin/sh
 
 "$TESTDIR/hghave" mtn || exit 80
 
 # Monotone directory is called .monotone on *nix and monotone
 # on Windows. Having a variable here ease test patching.
 mtndir=.monotone
 echo "[extensions]" >> $HGRCPATH
 echo "convert=" >> $HGRCPATH
 echo 'hgext.graphlog =' >> $HGRCPATH
 
 HOME=`pwd`/do_not_use_HOME_mtn; export HOME
 # Windows version of monotone home
 APPDATA=$HOME; export APPDATA
 
 echo % tedious monotone keys configuration
 # The /dev/null redirection is necessary under Windows, or
 # it complains about home directory permissions
 mtn --quiet genkey [e-mail] 1>/dev/null 2>&1 <<EOF
 passphrase
 passphrase
 EOF
 cat >> $HOME/$mtndir/monotonerc <<EOF
 function get_passphrase(keypair_id)
     return "passphrase"
 end
 EOF
 
 echo % create monotone repository
 mtn db init --db=repo.mtn
 mtn --db=repo.mtn --branch=com.selenic.test setup workingdir
 cd workingdir
 echo a > a
 mkdir dir
 echo b > dir/b
 echo d > dir/d
 python -c 'file("bin", "wb").write("a\\x00b")'
 echo c > c
 mtn add a dir/b dir/d c bin
 mtn ci -m initialize
 echo % update monotone working directory
 mtn mv a dir/a
 echo a >> dir/a
 echo b >> dir/b
 mtn drop c
 python -c 'file("bin", "wb").write("b\\x00c")'
 mtn ci -m update1
 cd ..
 
 echo % convert once
 hg convert -s mtn repo.mtn
 
 cd workingdir
 echo e > e
 mtn add e
 mtn drop dir/b
 mtn mv bin bin2
 mtn ci -m 'update2 "with" quotes'
 echo '% test directory move'
 mkdir -p dir1/subdir1
 mkdir -p dir1/subdir2_other
 echo file1 > dir1/subdir1/file1
 echo file2 > dir1/subdir2_other/file1
 mtn add dir1/subdir1/file1 dir1/subdir2_other/file1
 mtn ci -m createdir1
 mtn rename dir1/subdir1 dir1/subdir2
 mtn ci -m movedir1
 echo '% test subdirectory move'
 mtn mv dir dir2
 echo newfile > dir2/newfile
 mtn drop dir2/d
 mtn add dir2/newfile
 mtn ci -m movedir
 # Test directory removal with empty directory
 mkdir dir2/dir
 mkdir dir2/dir/subdir
 echo f > dir2/dir/subdir/f
 mkdir dir2/dir/emptydir
 mtn add --quiet -R dir2/dir
 mtn ci -m emptydir
 mtn drop -R dir2/dir
 mtn ci -m dropdirectory
 echo '% test directory and file move'
 mkdir -p dir3/d1
 echo a > dir3/a
 mtn add dir3/a dir3/d1
 mtn ci -m dirfilemove
 mtn mv dir3/a dir3/d1/a
 mtn mv dir3/d1 dir3/d2
 mtn ci -m dirfilemove2
+echo '% test directory move into another directory move'
+mkdir dir4
+mkdir dir5
+echo a > dir4/a
+mtn add dir4/a dir5
+mtn ci -m dirdirmove
+mtn mv dir5 dir6
+mtn mv dir4 dir6/dir4
+mtn ci -m dirdirmove2
+echo '% test diverging directory moves'
+mkdir -p dir7/dir9/dir8
+echo a > dir7/dir9/dir8/a
+echo b > dir7/dir9/b
+echo c > dir7/c
+mtn add -R dir7
+mtn ci -m divergentdirmove
+mtn mv dir7 dir7-2
+mtn mv dir7-2/dir9 dir9-2
+mtn mv dir9-2/dir8 dir8-2
+mtn ci -m divergentdirmove2
 cd ..
 
 echo % convert incrementally
 hg convert -s mtn repo.mtn
 
 glog()
 {
     hg glog --template '#rev# "#desc|firstline#" files: #files#\n' "$@"
 }
 
 cd repo.mtn-hg
 hg up -C
 glog
 echo % manifest
 hg manifest
 echo % contents
 cat dir2/a
 test -d dir2/dir && echo 'removed dir2/dir is still there!'
 
 echo % file move
 hg log -v -C -r 1 | grep copies
 echo % check directory move
 hg manifest -r 4
 test -d dir1/subdir2 || echo 'new dir1/subdir2 does not exist!'
 test -d dir1/subdir1 && echo 'renamed dir1/subdir1 is still there!'
 hg log -v -C -r 4 | grep copies
 echo % check file remove with directory move
 hg manifest -r 5
 echo % check file move with directory move
 hg manifest -r 9
+echo % check file directory directory move
+hg manifest -r 11
+echo % check divergent directory moves
+hg manifest -r 13
 exit 0
 

tests/test-convert-mtn.out

@@ -1,137 +1,199
 % tedious monotone keys configuration
 % create monotone repository
 mtn: adding a to workspace manifest
 mtn: adding bin to workspace manifest
 mtn: adding c to workspace manifest
 mtn: adding dir to workspace manifest
 mtn: adding dir/b to workspace manifest
 mtn: adding dir/d to workspace manifest
 mtn: beginning commit on branch 'com.selenic.test'
 mtn: committed revision 0f6e5e4f2e7d2a8ef312408f57618abf026afd90
 % update monotone working directory
 mtn: skipping dir, already accounted for in workspace
 mtn: renaming a to dir/a in workspace manifest
 mtn: dropping c from workspace manifest
 mtn: beginning commit on branch 'com.selenic.test'
 mtn: committed revision 51d0a982464573a2a2cf5ee2c9219c652aaebeff
 % convert once
 assuming destination repo.mtn-hg
 initializing destination repo.mtn-hg repository
 scanning source...
 sorting...
 converting...
 1 initialize
 0 update1
 mtn: adding e to workspace manifest
 mtn: dropping dir/b from workspace manifest
 mtn: renaming bin to bin2 in workspace manifest
 mtn: beginning commit on branch 'com.selenic.test'
 mtn: committed revision ebe58335d85d8cb176b6d0a12be04f5314b998da
 % test directory move
 mtn: adding dir1 to workspace manifest
 mtn: adding dir1/subdir1 to workspace manifest
 mtn: adding dir1/subdir1/file1 to workspace manifest
 mtn: adding dir1/subdir2_other to workspace manifest
 mtn: adding dir1/subdir2_other/file1 to workspace manifest
 mtn: beginning commit on branch 'com.selenic.test'
 mtn: committed revision a8d62bc04fee4d2936d28e98bbcc81686dd74306
 mtn: skipping dir1, already accounted for in workspace
 mtn: renaming dir1/subdir1 to dir1/subdir2 in workspace manifest
 mtn: beginning commit on branch 'com.selenic.test'
 mtn: committed revision 2c3d241bbbfe538b1b51d910f5676407e3f4d3a6
 % test subdirectory move
 mtn: renaming dir to dir2 in workspace manifest
 mtn: dropping dir2/d from workspace manifest
 mtn: adding dir2/newfile to workspace manifest
 mtn: beginning commit on branch 'com.selenic.test'
 mtn: committed revision fdb5a02dae8bfce3a79b3393680af471016e1b4c
 mtn: beginning commit on branch 'com.selenic.test'
 mtn: committed revision 8bbf76d717001d24964e4604739fdcd0f539fc88
 mtn: dropping dir2/dir/subdir/f from workspace manifest
 mtn: dropping dir2/dir/subdir from workspace manifest
 mtn: dropping dir2/dir/emptydir from workspace manifest
 mtn: dropping dir2/dir from workspace manifest
 mtn: beginning commit on branch 'com.selenic.test'
 mtn: committed revision 2323d4bc324e6c82628dc04d47a9fd32ad24e322
 % test directory and file move
 mtn: adding dir3 to workspace manifest
 mtn: adding dir3/a to workspace manifest
 mtn: adding dir3/d1 to workspace manifest
 mtn: beginning commit on branch 'com.selenic.test'
 mtn: committed revision 47b192f720faa622f48c68d1eb075b26d405aa8b
 mtn: skipping dir3/d1, already accounted for in workspace
 mtn: renaming dir3/a to dir3/d1/a in workspace manifest
 mtn: skipping dir3, already accounted for in workspace
 mtn: renaming dir3/d1 to dir3/d2 in workspace manifest
 mtn: beginning commit on branch 'com.selenic.test'
 mtn: committed revision 8b543a400d3ee7f6d4bb1835b9b9e3747c8cb632
+% test directory move into another directory move
+mtn: adding dir4 to workspace manifest
+mtn: adding dir4/a to workspace manifest
+mtn: adding dir5 to workspace manifest
+mtn: beginning commit on branch 'com.selenic.test'
+mtn: committed revision 466e0b2afc7a55aa2b4ab2f57cb240bb6cd66fc7
+mtn: renaming dir5 to dir6 in workspace manifest
+mtn: skipping dir6, already accounted for in workspace
+mtn: renaming dir4 to dir6/dir4 in workspace manifest
+mtn: beginning commit on branch 'com.selenic.test'
+mtn: committed revision 3d1f77ebad0c23a5d14911be3b670f990991b749
+% test diverging directory moves
+mtn: adding dir7 to workspace manifest
+mtn: adding dir7/c to workspace manifest
+mtn: adding dir7/dir9 to workspace manifest
+mtn: adding dir7/dir9/b to workspace manifest
+mtn: adding dir7/dir9/dir8 to workspace manifest
+mtn: adding dir7/dir9/dir8/a to workspace manifest
+mtn: beginning commit on branch 'com.selenic.test'
+mtn: committed revision 08a08511f18b428d840199b062de90d0396bc2ed
+mtn: renaming dir7 to dir7-2 in workspace manifest
+mtn: renaming dir7-2/dir9 to dir9-2 in workspace manifest
+mtn: renaming dir9-2/dir8 to dir8-2 in workspace manifest
+mtn: beginning commit on branch 'com.selenic.test'
+mtn: committed revision 4a736634505795f17786fffdf2c9cbf5b11df6f6
 % convert incrementally
 assuming destination repo.mtn-hg
 scanning source...
 sorting...
 converting...
-7 update2 "with" quotes
-6 createdir1
-5 movedir1
-4 movedir
-3 emptydir
-2 dropdirectory
-1 dirfilemove
-0 dirfilemove2
-7 files updated, 0 files merged, 0 files removed, 0 files unresolved
-@  9 "dirfilemove2" files: dir3/a dir3/d2/a
+11 update2 "with" quotes
+10 createdir1
+9 movedir1
+8 movedir
+7 emptydir
+6 dropdirectory
+5 dirfilemove
+4 dirfilemove2
+3 dirdirmove
+2 dirdirmove2
+1 divergentdirmove
+0 divergentdirmove2
+11 files updated, 0 files merged, 0 files removed, 0 files unresolved
+@  13 "divergentdirmove2" files: dir7-2/c dir7/c dir7/dir9/b dir7/dir9/dir8/a dir8-2/a dir9-2/b
+|
+o  12 "divergentdirmove" files: dir7/c dir7/dir9/b dir7/dir9/dir8/a
+|
+o  11 "dirdirmove2" files: dir4/a dir6/dir4/a
+|
+o  10 "dirdirmove" files: dir4/a
+|
+o  9 "dirfilemove2" files: dir3/a dir3/d2/a
 |
 o  8 "dirfilemove" files: dir3/a
 |
 o  7 "dropdirectory" files: dir2/dir/subdir/f
 |
 o  6 "emptydir" files: dir2/dir/subdir/f
 |
 o  5 "movedir" files: dir/a dir/d dir2/a dir2/newfile
 |
 o  4 "movedir1" files: dir1/subdir1/file1 dir1/subdir2/file1
 |
 o  3 "createdir1" files: dir1/subdir1/file1 dir1/subdir2_other/file1
 |
 o  2 "update2 "with" quotes" files: bin bin2 dir/b e
 |
 o  1 "update1" files: a bin c dir/a dir/b
 |
 o  0 "initialize" files: a bin c dir/b dir/d
 
 % manifest
 bin2
 dir1/subdir2/file1
 dir1/subdir2_other/file1
 dir2/a
 dir2/newfile
 dir3/d2/a
+dir6/dir4/a
+dir7-2/c
+dir8-2/a
+dir9-2/b
 e
 % contents
 a
 a
 % file move
 copies:      dir/a (a)
 % check directory move
 bin2
 dir/a
 dir/d
 dir1/subdir2/file1
 dir1/subdir2_other/file1
 e
 copies:      dir1/subdir2/file1 (dir1/subdir1/file1)
 % check file remove with directory move
 bin2
 dir1/subdir2/file1
 dir1/subdir2_other/file1
 dir2/a
 dir2/newfile
 e
 % check file move with directory move
 bin2
 dir1/subdir2/file1
 dir1/subdir2_other/file1
 dir2/a
 dir2/newfile
 dir3/d2/a
 e
+% check file directory directory move
+bin2
+dir1/subdir2/file1
+dir1/subdir2_other/file1
+dir2/a
+dir2/newfile
+dir3/d2/a
+dir6/dir4/a
+e
+% check divergent directory moves
+bin2
+dir1/subdir2/file1
+dir1/subdir2_other/file1
+dir2/a
+dir2/newfile
+dir3/d2/a
+dir6/dir4/a
+dir7-2/c
+dir8-2/a
+dir9-2/b
+e