convert/gnuarch: fix switched copy source and destination

Reported by Edouard Gomez <[e-mail]>

hgext/convert/gnuarch.py

@@ -1,299 +1,298 b''
 # GNU Arch support for the convert extension
 
 from common import NoRepo, commandline, commit, converter_source
 from mercurial.i18n import _
 from mercurial import util
 import os, shutil, tempfile, stat
 
 class gnuarch_source(converter_source, commandline):
 
     class gnuarch_rev:
         def __init__(self, rev):
             self.rev = rev
             self.summary = ''
             self.date = None
             self.author = ''
             self.add_files = []
             self.mod_files = []
             self.del_files = []
             self.ren_files = {}
             self.ren_dirs = {}
 
     def __init__(self, ui, path, rev=None):
         super(gnuarch_source, self).__init__(ui, path, rev=rev)
 
         if not os.path.exists(os.path.join(path, '{arch}')):
             raise NoRepo(_("%s does not look like a GNU Arch repo") % path)
 
         # Could use checktool, but we want to check for baz or tla.
         self.execmd = None
         if util.find_exe('baz'):
             self.execmd = 'baz'
         else:
             if util.find_exe('tla'):
                 self.execmd = 'tla'
             else:
                 raise util.Abort(_('cannot find a GNU Arch tool'))
 
         commandline.__init__(self, ui, self.execmd)
 
         self.path = os.path.realpath(path)
         self.tmppath = None
 
         self.treeversion = None
         self.lastrev = None
         self.changes = {}
         self.parents = {}
         self.tags = {}
         self.modecache = {}
 
     def before(self):
         if self.execmd == 'tla':
             output = self.run0('tree-version', self.path)
         else:
             output = self.run0('tree-version', '-d', self.path)
         self.treeversion = output.strip()
 
         self.ui.status(_('analyzing tree version %s...\n') % self.treeversion)
 
         # Get name of temporary directory
         version = self.treeversion.split('/')
         self.tmppath = os.path.join(tempfile.gettempdir(),
                                     'hg-%s' % version[1])
 
         # Generate parents dictionary
         child = []
         output, status = self.runlines('revisions', self.treeversion)
         self.checkexit(status, 'archive registered?')
         for l in output:
             rev = l.strip()
             self.changes[rev] = self.gnuarch_rev(rev)
 
             # Read author, date and summary
             catlog = self.runlines0('cat-log', '-d', self.path, rev)
             self._parsecatlog(catlog, rev)
 
             self.parents[rev] = child
             child = [rev]
             if rev == self.rev:
                 break
         self.parents[None] = child
 
     def after(self):
         self.ui.debug(_('cleaning up %s\n') % self.tmppath)
         shutil.rmtree(self.tmppath, ignore_errors=True)
 
     def getheads(self):
         return self.parents[None]
 
     def getfile(self, name, rev):
         if rev != self.lastrev:
             raise util.Abort(_('internal calling inconsistency'))
 
         # Raise IOError if necessary (i.e. deleted files).
         if not os.path.exists(os.path.join(self.tmppath, name)):
             raise IOError
 
         data, mode = self._getfile(name, rev)
         self.modecache[(name, rev)] = mode
 
         return data
 
     def getmode(self, name, rev):
         return self.modecache[(name, rev)]
 
     def getchanges(self, rev):
         self.modecache = {}
         self._update(rev)
         changes = []
         copies = {}
 
         for f in self.changes[rev].add_files:
             changes.append((f, rev))
 
         for f in self.changes[rev].mod_files:
             changes.append((f, rev))
 
         for f in self.changes[rev].del_files:
             changes.append((f, rev))
 
         for src in self.changes[rev].ren_files:
             to = self.changes[rev].ren_files[src]
             changes.append((src, rev))
             changes.append((to, rev))
-            copies[src] = to
+            copies[to] = src
 
         for src in self.changes[rev].ren_dirs:
             to = self.changes[rev].ren_dirs[src]
             chgs, cps = self._rendirchanges(src, to);
             changes += [(f, rev) for f in chgs]
-            for c in cps:
-                copies[c] = cps[c]
+            copies.update(cps)
 
         self.lastrev = rev
-        return util.sort(changes), copies
+        return util.sort(util.unique(changes)), copies
 
     def getcommit(self, rev):
         changes = self.changes[rev]
         return commit(author = changes.author, date = changes.date,
                       desc = changes.summary, parents = self.parents[rev])
 
     def gettags(self):
         return self.tags
 
     def _execute(self, cmd, *args, **kwargs):
         cmdline = [self.execmd, cmd]
         cmdline += args
         cmdline = [util.shellquote(arg) for arg in cmdline]
         cmdline += ['>', util.nulldev, '2>', util.nulldev]
         cmdline = util.quotecommand(' '.join(cmdline))
         self.ui.debug(cmdline, '\n')
         return os.system(cmdline)
 
     def _update(self, rev):
         if rev == 'base-0':
             # Initialise 'base-0' revision
             self._obtainrevision(rev)
         else:
             self.ui.debug(_('applying revision %s...\n') % rev)
             revision = '%s--%s' % (self.treeversion, rev)
             changeset, status = self.runlines('replay', '-d', self.tmppath,
                                               revision)
             if status:
                 # Something went wrong while merging (baz or tla
                 # issue?), get latest revision and try from there
                 shutil.rmtree(self.tmppath, ignore_errors=True)
                 self._obtainrevision(rev)
             else:
                 old_rev = self.parents[rev][0]
                 self.ui.debug(_('computing changeset between %s and %s...\n')
                               % (old_rev, rev))
                 rev_a = '%s--%s' % (self.treeversion, old_rev)
                 rev_b = '%s--%s' % (self.treeversion, rev)
                 self._parsechangeset(changeset, rev)
 
     def _getfile(self, name, rev):
         mode = os.lstat(os.path.join(self.tmppath, name)).st_mode
         if stat.S_ISLNK(mode):
             data = os.readlink(os.path.join(self.tmppath, name))
             mode = mode and 'l' or ''
         else:
             data = open(os.path.join(self.tmppath, name), 'rb').read()
             mode = (mode & 0111) and 'x' or ''
         return data, mode
 
     def _exclude(self, name):
         exclude = [ '{arch}', '.arch-ids', '.arch-inventory' ]
         for exc in exclude:
             if name.find(exc) != -1:
                 return True
         return False
 
     def _readcontents(self, path):
         files = []
         contents = os.listdir(path)
         while len(contents) > 0:
             c = contents.pop()
             p = os.path.join(path, c)
             # os.walk could be used, but here we avoid internal GNU
             # Arch files and directories, thus saving a lot time.
             if not self._exclude(p):
                 if os.path.isdir(p):
                     contents += [os.path.join(c, f) for f in os.listdir(p)]
                 else:
                     files.append(c)
         return files
 
     def _rendirchanges(self, src, dest):
         changes = []
         copies = {}
         files = self._readcontents(os.path.join(self.tmppath, dest))
         for f in files:
             s = os.path.join(src, f)
             d = os.path.join(dest, f)
             changes.append(s)
             changes.append(d)
-            copies[s] = d
+            copies[d] = s
         return changes, copies
 
     def _obtainrevision(self, rev):
         self.ui.debug(_('obtaining revision %s...\n') % rev)
         revision = '%s--%s' % (self.treeversion, rev)
         output = self._execute('get', revision, self.tmppath)
         self.checkexit(output)
         self.ui.debug(_('analysing revision %s...\n') % rev)
         files = self._readcontents(self.tmppath)
         self.changes[rev].add_files += files
 
     def _stripbasepath(self, path):
         if path.startswith('./'):
             return path[2:]
         return path
 
     def _parsecatlog(self, data, rev):
         summary = []
         for l in data:
             l = l.strip()
             if summary:
                 summary.append(l)
             elif l.startswith('Summary:'):
                 summary.append(l[len('Summary: '):])
             elif l.startswith('Standard-date:'):
                 date = l[len('Standard-date: '):]
                 strdate = util.strdate(date, '%Y-%m-%d %H:%M:%S')
                 self.changes[rev].date = util.datestr(strdate)
             elif l.startswith('Creator:'):
                 self.changes[rev].author = l[len('Creator: '):]
         self.changes[rev].summary = '\n'.join(summary)
 
     def _parsechangeset(self, data, rev):
         for l in data:
             l = l.strip()
             # Added file (ignore added directory)
             if l.startswith('A') and not l.startswith('A/'):
                 file = self._stripbasepath(l[1:].strip())
                 if not self._exclude(file):
                     self.changes[rev].add_files.append(file)
             # Deleted file (ignore deleted directory)
             elif l.startswith('D') and not l.startswith('D/'):
                 file = self._stripbasepath(l[1:].strip())
                 if not self._exclude(file):
                     self.changes[rev].del_files.append(file)
             # Modified binary file
             elif l.startswith('Mb'):
                 file = self._stripbasepath(l[2:].strip())
                 if not self._exclude(file):
                     self.changes[rev].mod_files.append(file)
             # Modified link
             elif l.startswith('M->'):
                 file = self._stripbasepath(l[3:].strip())
                 if not self._exclude(file):
                     self.changes[rev].mod_files.append(file)
             # Modified file
             elif l.startswith('M'):
                 file = self._stripbasepath(l[1:].strip())
                 if not self._exclude(file):
                     self.changes[rev].mod_files.append(file)
             # Renamed file (or link)
             elif l.startswith('=>'):
                 files = l[2:].strip().split(' ')
                 if len(files) == 1:
                     files = l[2:].strip().split('\t')
                 src = self._stripbasepath(files[0])
                 dst = self._stripbasepath(files[1])
                 if not self._exclude(src) and not self._exclude(dst):
                     self.changes[rev].ren_files[src] = dst
             # Conversion from file to link or from link to file (modified)
             elif l.startswith('ch'):
                 file = self._stripbasepath(l[2:].strip())
                 if not self._exclude(file):
                     self.changes[rev].mod_files.append(file)
             # Renamed directory
             elif l.startswith('/>'):
                 dirs = l[2:].strip().split(' ')
                 if len(dirs) == 1:
                     dirs = l[2:].strip().split('\t')
                 src = self._stripbasepath(dirs[0])
                 dst = self._stripbasepath(dirs[1])
                 if not self._exclude(src) and not self._exclude(dst):
                     self.changes[rev].ren_dirs[src] = dst

tests/test-convert-baz

@@ -1,73 +1,82 b''
 #!/bin/sh
 
 "$TESTDIR/hghave" baz || exit 80
 
 mkdir do_not_use_HOME_baz
 cd do_not_use_HOME_baz
 HOME=`pwd`; export HOME
 cd ..
 baz my-id "mercurial <[e-mail]>"
 
 echo "[extensions]" >> $HGRCPATH
 echo "convert=" >> $HGRCPATH
 echo 'hgext.graphlog =' >> $HGRCPATH
 
 echo % create baz archive
 baz make-archive baz@mercurial--convert hg-test-convert-baz
 
 echo % initialize baz repo
 mkdir baz-repo
 cd baz-repo/
 baz init-tree baz@mercurial--convert/baz--test--0
 baz import
 
 echo % create initial files
 echo 'this is a file' > a
 baz add a
 mkdir src
 baz add src
 cd src
 dd count=1 if=/dev/zero of=b > /dev/null 2> /dev/null
 baz add b
 baz commit -s "added a file, src and src/b (binary)"
 
 echo % create link file and modify a
 ln -s ../a a-link
 baz add a-link
 echo 'this a modification to a' >> ../a
 baz commit -s "added link to a and modify a"
 
 echo % create second link and modify b
 ln -s ../a a-link-2
 baz add a-link-2
 dd count=1 seek=1 if=/dev/zero of=b > /dev/null 2> /dev/null
 baz commit -s "added second link and modify b"
 
 echo % b file to link and a-link-2 to regular file
 rm -f a-link-2
 echo 'this is now a regular file' > a-link-2
 ln -sf ../a b
 baz commit -s "file to link and link to file test"
 
 echo % move a-link-2 file and src directory
 cd ..
 baz mv src/a-link-2 c
 baz mv src test
 baz commit -s "move and rename a-link-2 file and src directory"
 
+echo % move and add the moved file again
+echo e > e
+baz add e
+baz commit -s "add e"
+baz mv e f
+echo ee > e
+baz add e
+baz commit -s "move e and recreate it again"
 cd ..
 
 echo % converting baz repo to Mercurial
 hg convert baz-repo baz-repo-hg
 
 baz register-archive -d baz@mercurial--convert
 
 glog()
 {
     hg glog --template '#rev# "#desc|firstline#" files: #files#\n' "$@"
 }
 
 echo % show graph log
 glog -R baz-repo-hg
 hg up -q -R baz-repo-hg
 hg -R baz-repo-hg manifest --debug
+hg -R baz-repo-hg log -r 5 -r 7 -C --debug | grep copies

tests/test-convert-baz.out

@@ -1,75 +1,96 b''
 % create baz archive
 % initialize baz repo
 * creating version baz@mercurial--convert/baz--test--0
 * imported baz@mercurial--convert/baz--test--0
 % create initial files
 * build pristine tree for baz@mercurial--convert/baz--test--0--base-0
 * Scanning for full-tree revision: .
 * from import revision: baz@mercurial--convert/baz--test--0--base-0
 A/ .arch-ids
 A/ src
 A/ src/.arch-ids
 A  .arch-ids/a.id
 A  a
 A  src/.arch-ids/=id
 A  src/.arch-ids/b.id
 A  src/b
 * update pristine tree (baz@mercurial--convert/baz--test--0--base-0 => baz--test--0--patch-1)
 * committed baz@mercurial--convert/baz--test--0--patch-1
 % create link file and modify a
 A  src/.arch-ids/a-link.id
 A  src/a-link
 M  a
 * update pristine tree (baz@mercurial--convert/baz--test--0--patch-1 => baz--test--0--patch-2)
 * committed baz@mercurial--convert/baz--test--0--patch-2
 % create second link and modify b
 A  src/.arch-ids/a-link-2.id
 A  src/a-link-2
 Mb src/b
 * update pristine tree (baz@mercurial--convert/baz--test--0--patch-2 => baz--test--0--patch-3)
 * committed baz@mercurial--convert/baz--test--0--patch-3
 % b file to link and a-link-2 to regular file
 fl src/b
 lf src/a-link-2
 * update pristine tree (baz@mercurial--convert/baz--test--0--patch-3 => baz--test--0--patch-4)
 * committed baz@mercurial--convert/baz--test--0--patch-4
 % move a-link-2 file and src directory
 D/ src/.arch-ids
 A/ test/.arch-ids
 /> src	test
 => src/.arch-ids/a-link-2.id	.arch-ids/c.id
 => src/a-link-2	c
 => src/.arch-ids/=id	test/.arch-ids/=id
 => src/.arch-ids/a-link.id	test/.arch-ids/a-link.id
 => src/.arch-ids/b.id	test/.arch-ids/b.id
 * update pristine tree (baz@mercurial--convert/baz--test--0--patch-4 => baz--test--0--patch-5)
 * committed baz@mercurial--convert/baz--test--0--patch-5
+% move and add the moved file again
+A  .arch-ids/e.id
+A  e
+* update pristine tree (baz@mercurial--convert/baz--test--0--patch-5 => baz--test--0--patch-6)
+* committed baz@mercurial--convert/baz--test--0--patch-6
+A  .arch-ids/e.id
+A  e
+=> .arch-ids/e.id	.arch-ids/f.id
+=> e	f
+* update pristine tree (baz@mercurial--convert/baz--test--0--patch-6 => baz--test--0--patch-7)
+* committed baz@mercurial--convert/baz--test--0--patch-7
 % converting baz repo to Mercurial
 initializing destination baz-repo-hg repository
 analyzing tree version baz@mercurial--convert/baz--test--0...
 scanning source...
 sorting...
 converting...
-5 initial import
-4 added a file, src and src/b (binary)
-3 added link to a and modify a
-2 added second link and modify b
-1 file to link and link to file test
-0 move and rename a-link-2 file and src directory
+7 initial import
+6 added a file, src and src/b (binary)
+5 added link to a and modify a
+4 added second link and modify b
+3 file to link and link to file test
+2 move and rename a-link-2 file and src directory
+1 add e
+0 move e and recreate it again
 % show graph log
+o  7 "move e and recreate it again" files: e f
+|
+o  6 "add e" files: e
+|
 o  5 "move and rename a-link-2 file and src directory" files: c src/a-link src/a-link-2 src/b test/a-link test/b
 |
 o  4 "file to link and link to file test" files: src/a-link-2 src/b
 |
 o  3 "added second link and modify b" files: src/a-link-2 src/b
 |
 o  2 "added link to a and modify a" files: a src/a-link
 |
 o  1 "added a file, src and src/b (binary)" files: a src/b
 |
 o  0 "initial import" files:
 
 c4072c4b72e1cabace081888efa148ee80ca3cbb 644   a
-e3207be798aaf87a444a62903621edab4ddc1fb6 644   c
-1f6b5bb93f1da278ef1fead1e4740a03d8802e9f 644 @ test/a-link
-1f6b5bb93f1da278ef1fead1e4740a03d8802e9f 644 @ test/b
[phone]de842342ac7b221ae9ccabc13b5d8c8 644   c
+1a4a864db0073705a11b1439f563bfa4b46d9246 644   e
+ab9089704d7c988687521e6adf018ebf767da7d6 644   f
+43b4308708a4b36340566684df2e2a074b12ceb0 644 @ test/a-link
+73773e3389ef7ec5a070519b74895d2eaa4ad5db 644 @ test/b
+copies:      c (src/a-link-2) test/a-link (src/a-link) test/b (src/b)
+copies:      f (e)

tests/test-convert-tla.out

@@ -1,72 +1,72 b''
 % create tla archive
 % initialize tla repo
 * creating version tla@mercurial--convert/tla--test--0
 * imported tla@mercurial--convert/tla--test--0
 % create initial files
 A/ .arch-ids
 A/ src
 A/ src/.arch-ids
 A  .arch-ids/a.id
 A  a
 A  src/.arch-ids/=id
 A  src/.arch-ids/b.id
 A  src/b
 * update pristine tree (tla@mercurial--convert/tla--test--0--base-0 => tla--test--0--patch-1)
 * committed tla@mercurial--convert/tla--test--0--patch-1
 % create link file and modify a
 A  src/.arch-ids/a-link.id
 A  src/a-link
 M  a
 * update pristine tree (tla@mercurial--convert/tla--test--0--patch-1 => tla--test--0--patch-2)
 * committed tla@mercurial--convert/tla--test--0--patch-2
 % create second link and modify b
 A  src/.arch-ids/a-link-2.id
 A  src/a-link-2
 Mb src/b
 * update pristine tree (tla@mercurial--convert/tla--test--0--patch-2 => tla--test--0--patch-3)
 * committed tla@mercurial--convert/tla--test--0--patch-3
 % b file to link and a-link-2 to regular file
 fl src/b
 lf src/a-link-2
 * update pristine tree (tla@mercurial--convert/tla--test--0--patch-3 => tla--test--0--patch-4)
 * committed tla@mercurial--convert/tla--test--0--patch-4
 % move a-link-2 file and src directory
 D/ src/.arch-ids
 A/ test/.arch-ids
 /> src	test
 => src/.arch-ids/a-link-2.id	.arch-ids/c.id
 => src/a-link-2	c
 => src/.arch-ids/=id	test/.arch-ids/=id
 => src/.arch-ids/a-link.id	test/.arch-ids/a-link.id
 => src/.arch-ids/b.id	test/.arch-ids/b.id
 * update pristine tree (tla@mercurial--convert/tla--test--0--patch-4 => tla--test--0--patch-5)
 * committed tla@mercurial--convert/tla--test--0--patch-5
 % converting tla repo to Mercurial
 initializing destination tla-repo-hg repository
 analyzing tree version tla@mercurial--convert/tla--test--0...
 scanning source...
 sorting...
 converting...
 5 initial import
 4 added a file, src and src/b (binary)
 3 added link to a and modify a
 2 added second link and modify b
 1 file to link and link to file test
 0 move and rename a-link-2 file and src directory
 % show graph log
 o  5 "move and rename a-link-2 file and src directory" files: c src/a-link src/a-link-2 src/b test/a-link test/b
 |
 o  4 "file to link and link to file test" files: src/a-link-2 src/b
 |
 o  3 "added second link and modify b" files: src/a-link-2 src/b
 |
 o  2 "added link to a and modify a" files: a src/a-link
 |
 o  1 "added a file, src and src/b (binary)" files: a src/b
 |
 o  0 "initial import" files:
 
 c4072c4b72e1cabace081888efa148ee80ca3cbb 644   a
-e3207be798aaf87a444a62903621edab4ddc1fb6 644   c
-1f6b5bb93f1da278ef1fead1e4740a03d8802e9f 644 @ test/a-link
-1f6b5bb93f1da278ef1fead1e4740a03d8802e9f 644 @ test/b
[phone]de842342ac7b221ae9ccabc13b5d8c8 644   c
+43b4308708a4b36340566684df2e2a074b12ceb0 644 @ test/a-link
+73773e3389ef7ec5a070519b74895d2eaa4ad5db 644 @ test/b