convert/mtn: handle new files in moved directories (issue1619)

Reported and investigated by Paul Aurich <[e-mail]>

hgext/convert/monotone.py

@@ -1,200 +1,207 b''
 # 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
         return certs
 
-    def mtnrenamefiles(self, files, fromdir, todir):
-        renamed = {}
-        for tofile in files:
-            if tofile.startswith(todir + '/'):
-                renamed[tofile] = fromdir + tofile[len(todir):]
-        return renamed
-
     # 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 = {}
+        addedfiles = {}
+        renameddirs = []
         copies = {}
         for e in revision:
             m = self.add_file_re.match(e)
             if m:
                 files[m.group(1)] = rev
+                addedfiles[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):
                     copies[toname] = fromname
                     files[toname] = rev
                     files[fromname] = rev
-                if self.mtnisdir(toname, rev):
-                    renamed = self.mtnrenamefiles(self.files, fromname, toname)
-                    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
+                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 addedfiles:
+                    continue
+                if tofile.startswith(todir + '/'):
+                    renamed[tofile] = fromdir + tofile[len(todir):]
+            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

@@ -1,106 +1,112 b''
 #!/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 c bin
+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
 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
 exit 0
 

tests/test-convert-mtn.out

@@ -1,98 +1,110 b''
 % 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 803ef0bf815e35b951dbd4310acd1e45e675016e
+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 4daf60753d6fe21a06ce5f716303fe55fd6d3a56
+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 6c6977a6ef609ec80e40779f89dbd2772c96de62
+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 e066b1feb2b7a7110450c2c18b5b4462011427d1
+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 2ad2409d25bb8d2583b57a3d4c0fa1df62aa1f79
+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 a85290b81fc4a8fbce4dc4d956404109842b406e
+mtn: committed revision fdb5a02dae8bfce3a79b3393680af471016e1b4c
 mtn: beginning commit on branch 'com.selenic.test'
-mtn: committed revision 7e3c8746060117104f16ff2d9212cf0f810cbff0
+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 a97e0433d041a6d253c5dc27e080d544e55d9c19
+mtn: committed revision 2323d4bc324e6c82628dc04d47a9fd32ad24e322
 % convert incrementally
 assuming destination repo.mtn-hg
 scanning source...
 sorting...
 converting...
 5 update2 "with" quotes
 4 createdir1
 3 movedir1
 2 movedir
 1 emptydir
 0 dropdirectory
-5 files updated, 0 files merged, 0 files removed, 0 files unresolved
+6 files updated, 0 files merged, 0 files removed, 0 files unresolved
 @  7 "dropdirectory" files: dir2/dir/subdir/f
 |
 o  6 "emptydir" files: dir2/dir/subdir/f
 |
-o  5 "movedir" files: dir/a dir2/a
+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
+o  0 "initialize" files: a bin c dir/b dir/d
 
 % manifest
 bin2
 dir1/subdir2/file1
 dir1/subdir2_other/file1
 dir2/a
+dir2/newfile
 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