convert/darcs: handle directory renaming

hgext/convert/darcs.py

@@ -1,136 +1,163 b''
 # darcs.py - darcs support for the convert extension
 #
 #  Copyright 2007-2009 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2, incorporated herein by reference.
 
 from common import NoRepo, checktool, commandline, commit, converter_source
 from mercurial.i18n import _
 from mercurial import util
 import os, shutil, tempfile
 
 # The naming drift of ElementTree is fun!
 
 try: from xml.etree.cElementTree import ElementTree
 except ImportError:
     try: from xml.etree.ElementTree import ElementTree
     except ImportError:
         try: from elementtree.cElementTree import ElementTree
         except ImportError:
             try: from elementtree.ElementTree import ElementTree
             except ImportError: ElementTree = None
 
 
 class darcs_source(converter_source, commandline):
     def __init__(self, ui, path, rev=None):
         converter_source.__init__(self, ui, path, rev=rev)
         commandline.__init__(self, ui, 'darcs')
 
         # check for _darcs, ElementTree, _darcs/inventory so that we can
         # easily skip test-convert-darcs if ElementTree is not around
         if not os.path.exists(os.path.join(path, '_darcs', 'inventories')):
             raise NoRepo("%s does not look like a darcs repo" % path)
 
         if not os.path.exists(os.path.join(path, '_darcs')):
             raise NoRepo("%s does not look like a darcs repo" % path)
 
         checktool('darcs')
         version = self.run0('--version').splitlines()[0].strip()
         if version < '2.1':
             raise util.Abort(_('darcs version 2.1 or newer needed (found %r)') %
                              version)
 
         if ElementTree is None:
             raise util.Abort(_("Python ElementTree module is not available"))
 
         self.path = os.path.realpath(path)
 
         self.lastrev = None
         self.changes = {}
         self.parents = {}
         self.tags = {}
 
     def before(self):
         self.tmppath = tempfile.mkdtemp(
             prefix='convert-' + os.path.basename(self.path) + '-')
         output, status = self.run('init', repodir=self.tmppath)
         self.checkexit(status)
 
         tree = self.xml('changes', xml_output=True, summary=True,
                         repodir=self.path)
         tagname = None
         child = None
         for elt in tree.findall('patch'):
             node = elt.get('hash')
             name = elt.findtext('name', '')
             if name.startswith('TAG '):
                 tagname = name[4:].strip()
             elif tagname is not None:
                 self.tags[tagname] = node
                 tagname = None
             self.changes[node] = elt
             self.parents[child] = [node]
             child = node
         self.parents[child] = []
 
     def after(self):
         self.ui.debug(_('cleaning up %s\n') % self.tmppath)
         shutil.rmtree(self.tmppath, ignore_errors=True)
 
     def xml(self, cmd, **kwargs):
         etree = ElementTree()
         fp = self._run(cmd, **kwargs)
         etree.parse(fp)
         self.checkexit(fp.close())
         return etree.getroot()
 
+    def manifest(self):
+        man = []
+        output, status = self.run('show', 'files', no_directories=True,
+                                  repodir=self.tmppath)
+        self.checkexit(status)
+        for line in output.split('\n'):
+            path = line[2:]
+            if path:
+                man.append(path)
+        return man
+
     def getheads(self):
         return self.parents[None]
 
     def getcommit(self, rev):
         elt = self.changes[rev]
         date = util.strdate(elt.get('local_date'), '%a %b %d %H:%M:%S %Z %Y')
         desc = elt.findtext('name') + '\n' + elt.findtext('comment', '')
         return commit(author=elt.get('author'), date=util.datestr(date),
                       desc=desc.strip(), parents=self.parents[rev])
 
     def pull(self, rev):
         output, status = self.run('pull', self.path, all=True,
                                   match='hash %s' % rev,
                                   no_test=True, no_posthook=True,
                                   external_merge='/bin/false',
                                   repodir=self.tmppath)
         if status:
             if output.find('We have conflicts in') == -1:
                 self.checkexit(status, output)
             output, status = self.run('revert', all=True, repodir=self.tmppath)
             self.checkexit(status, output)
 
-    def getchanges(self, rev):
-        self.pull(rev)
+    def getchanges(self, rev):        
         copies = {}
         changes = []
+        man = None
         for elt in self.changes[rev].find('summary').getchildren():
             if elt.tag in ('add_directory', 'remove_directory'):
                 continue
             if elt.tag == 'move':
-                changes.append((elt.get('from'), rev))
-                changes.append((elt.get('to'), rev))
-                copies[elt.get('to')] = elt.get('from')
+                if man is None:
+                    man = self.manifest()
+                source, dest = elt.get('from'), elt.get('to')
+                if source in man:
+                    # File move
+                    changes.append((source, rev))
+                    changes.append((dest, rev))
+                    copies[dest] = source
+                else:
+                    # Directory move, deduce file moves from manifest
+                    source = source + '/'
+                    for f in man:
+                        if not f.startswith(source):
+                            continue
+                        fdest = dest + '/' + f[len(source):]
+                        changes.append((f, rev))
+                        changes.append((fdest, rev))
+                        copies[fdest] = f
             else:
                 changes.append((elt.text.strip(), rev))
+        self.pull(rev)
         self.lastrev = rev
         return sorted(changes), copies
 
     def getfile(self, name, rev):
         if rev != self.lastrev:
             raise util.Abort(_('internal calling inconsistency'))
         return open(os.path.join(self.tmppath, name), 'rb').read()
 
     def getmode(self, name, rev):
         mode = os.lstat(os.path.join(self.tmppath, name)).st_mode
         return (mode & 0111) and 'x' or ''
 
     def gettags(self):
         return self.tags

tests/test-convert-darcs

@@ -1,68 +1,75 b''
 #!/bin/sh
 
 "$TESTDIR/hghave" darcs || exit 80
 
 echo "[extensions]" >> $HGRCPATH
 echo "convert=" >> $HGRCPATH
 echo 'hgext.graphlog =' >> $HGRCPATH
 
 DARCS_EMAIL='[e-mail]'; export DARCS_EMAIL
 HOME=`pwd`/do_not_use_HOME_darcs; export HOME
 
 # skip if we can't import elementtree
 mkdir dummy
 mkdir dummy/_darcs
 if hg convert dummy 2>&1 | grep ElementTree > /dev/null; then
     echo 'skipped: missing feature: elementtree module'
     exit 80
 fi
 
 echo % initialize darcs repo
 mkdir darcs-repo
 cd darcs-repo
 darcs init
 echo a > a
 darcs record -a -l -m p0
 cd ..
 
 echo % branch and update
 darcs get darcs-repo darcs-clone >/dev/null
 cd darcs-clone
 echo c >> a
 echo c > c
 darcs record -a -l -m p1.1
 cd ..
 
 echo % update source
 cd darcs-repo
 echo b >> a
 echo b > b
 darcs record -a -l -m p1.2
 
 echo % merge branch
 darcs pull -a ../darcs-clone
 sleep 1
 echo e > a
 echo f > f
+mkdir dir
+echo d > dir/d
+echo d > dir/d2
 darcs record -a -l -m p2
 
 echo % test file and directory move
 darcs mv f ff
+# Test remove + move
+darcs remove dir/d2
+rm dir/d2
+darcs mv dir dir2
 darcs record -a -l -m p3
 cd ..
 
 glog()
 {
     hg glog --template '{rev} "{desc|firstline}" files: {files}\n' "$@"
 }
 
 hg convert darcs-repo darcs-repo-hg
 # The converter does not currently handle patch conflicts very well.
 # When they occur, it reverts *all* changes and moves forward,
 # letting the conflict resolving patch fix collisions.
 # Unfortunately, non-conflicting changes, like the addition of the
 # "c" file in p1.1 patch are reverted too.
 # Just to say that manifest not listing "c" here is a bug.
 glog -R darcs-repo-hg
 hg up -q -R darcs-repo-hg
 hg -R darcs-repo-hg manifest --debug

tests/test-convert-darcs.out

@@ -1,36 +1,37 b''
 % initialize darcs repo
 Finished recording patch 'p0'
 % branch and update
 Finished recording patch 'p1.1'
 % update source
 Finished recording patch 'p1.2'
 % merge branch
 Backing up ./a(-darcs-backup0)
 We have conflicts in the following files:
 ./a
 Finished pulling and applying.
 Finished recording patch 'p2'
 % test file and directory move
 Finished recording patch 'p3'
 initializing destination darcs-repo-hg repository
 scanning source...
 sorting...
 converting...
 4 p0
 3 p1.2
 2 p1.1
 1 p2
 0 p3
-o  4 "p3" files: f ff
+o  4 "p3" files: dir/d dir/d2 dir2/d f ff
 |
-o  3 "p2" files: a f
+o  3 "p2" files: a dir/d dir/d2 f
 |
 o  2 "p1.1" files:
 |
 o  1 "p1.2" files: a b
 |
 o  0 "p0" files: a
 
 7225b30cdf38257d5cc7780772c051b6f33e6d6b 644   a
 1e88685f5ddec574a34c70af492f95b6debc8741 644   b
+d278f41640da5fc303a4cf9894af31c2983fc11d 644   dir2/d
 ef5c76581d78340f568d5f48d679bf307452cbc9 644   ff