convert: add progress support

hgext/convert/convcmd.py

@@ -1,404 +1,409
 # convcmd - convert extension commands definition
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from common import NoRepo, MissingTool, SKIPREV, mapfile
 from cvs import convert_cvs
 from darcs import darcs_source
 from git import convert_git
 from hg import mercurial_source, mercurial_sink
 from subversion import svn_source, svn_sink
 from monotone import monotone_source
 from gnuarch import gnuarch_source
 from bzr import bzr_source
 from p4 import p4_source
 import filemap
 
 import os, shutil
 from mercurial import hg, util, encoding
 from mercurial.i18n import _
 
 orig_encoding = 'ascii'
 
 def recode(s):
     if isinstance(s, unicode):
         return s.encode(orig_encoding, 'replace')
     else:
         return s.decode('utf-8').encode(orig_encoding, 'replace')
 
 source_converters = [
     ('cvs', convert_cvs, 'branchsort'),
     ('git', convert_git, 'branchsort'),
     ('svn', svn_source, 'branchsort'),
     ('hg', mercurial_source, 'sourcesort'),
     ('darcs', darcs_source, 'branchsort'),
     ('mtn', monotone_source, 'branchsort'),
     ('gnuarch', gnuarch_source, 'branchsort'),
     ('bzr', bzr_source, 'branchsort'),
     ('p4', p4_source, 'branchsort'),
     ]
 
 sink_converters = [
     ('hg', mercurial_sink),
     ('svn', svn_sink),
     ]
 
 def convertsource(ui, path, type, rev):
     exceptions = []
     if type and type not in [s[0] for s in source_converters]:
         raise util.Abort(_('%s: invalid source repository type') % type)
     for name, source, sortmode in source_converters:
         try:
             if not type or name == type:
                 return source(ui, path, rev), sortmode
         except (NoRepo, MissingTool), inst:
             exceptions.append(inst)
     if not ui.quiet:
         for inst in exceptions:
             ui.write("%s\n" % inst)
     raise util.Abort(_('%s: missing or unsupported repository') % path)
 
 def convertsink(ui, path, type):
     if type and type not in [s[0] for s in sink_converters]:
         raise util.Abort(_('%s: invalid destination repository type') % type)
     for name, sink in sink_converters:
         try:
             if not type or name == type:
                 return sink(ui, path)
         except NoRepo, inst:
             ui.note(_("convert: %s\n") % inst)
     raise util.Abort(_('%s: unknown repository type') % path)
 
 class converter(object):
     def __init__(self, ui, source, dest, revmapfile, opts):
 
         self.source = source
         self.dest = dest
         self.ui = ui
         self.opts = opts
         self.commitcache = {}
         self.authors = {}
         self.authorfile = None
 
         # Record converted revisions persistently: maps source revision
         # ID to target revision ID (both strings).  (This is how
         # incremental conversions work.)
         self.map = mapfile(ui, revmapfile)
 
         # Read first the dst author map if any
         authorfile = self.dest.authorfile()
         if authorfile and os.path.exists(authorfile):
             self.readauthormap(authorfile)
         # Extend/Override with new author map if necessary
         if opts.get('authors'):
             self.readauthormap(opts.get('authors'))
             self.authorfile = self.dest.authorfile()
 
         self.splicemap = mapfile(ui, opts.get('splicemap'))
         self.branchmap = mapfile(ui, opts.get('branchmap'))
 
     def walktree(self, heads):
         '''Return a mapping that identifies the uncommitted parents of every
         uncommitted changeset.'''
         visit = heads
         known = set()
         parents = {}
         while visit:
             n = visit.pop(0)
             if n in known or n in self.map:
                 continue
             known.add(n)
+            self.ui.progress(_('scanning'), len(known), unit=_('revisions'))
             commit = self.cachecommit(n)
             parents[n] = []
             for p in commit.parents:
                 parents[n].append(p)
                 visit.append(p)
+        self.ui.progress(_('scanning'), None)
 
         return parents
 
     def toposort(self, parents, sortmode):
         '''Return an ordering such that every uncommitted changeset is
         preceeded by all its uncommitted ancestors.'''
 
         def mapchildren(parents):
             """Return a (children, roots) tuple where 'children' maps parent
             revision identifiers to children ones, and 'roots' is the list of
             revisions without parents. 'parents' must be a mapping of revision
             identifier to its parents ones.
             """
             visit = parents.keys()
             seen = set()
             children = {}
             roots = []
 
             while visit:
                 n = visit.pop(0)
                 if n in seen:
                     continue
                 seen.add(n)
                 # Ensure that nodes without parents are present in the
                 # 'children' mapping.
                 children.setdefault(n, [])
                 hasparent = False
                 for p in parents[n]:
                     if not p in self.map:
                         visit.append(p)
                         hasparent = True
                     children.setdefault(p, []).append(n)
                 if not hasparent:
                     roots.append(n)
 
             return children, roots
 
         # Sort functions are supposed to take a list of revisions which
         # can be converted immediately and pick one
 
         def makebranchsorter():
             """If the previously converted revision has a child in the
             eligible revisions list, pick it. Return the list head
             otherwise. Branch sort attempts to minimize branch
             switching, which is harmful for Mercurial backend
             compression.
             """
             prev = [None]
             def picknext(nodes):
                 next = nodes[0]
                 for n in nodes:
                     if prev[0] in parents[n]:
                         next = n
                         break
                 prev[0] = next
                 return next
             return picknext
 
         def makesourcesorter():
             """Source specific sort."""
             keyfn = lambda n: self.commitcache[n].sortkey
             def picknext(nodes):
                 return sorted(nodes, key=keyfn)[0]
             return picknext
 
         def makedatesorter():
             """Sort revisions by date."""
             dates = {}
             def getdate(n):
                 if n not in dates:
                     dates[n] = util.parsedate(self.commitcache[n].date)
                 return dates[n]
 
             def picknext(nodes):
                 return min([(getdate(n), n) for n in nodes])[1]
 
             return picknext
 
         if sortmode == 'branchsort':
             picknext = makebranchsorter()
         elif sortmode == 'datesort':
             picknext = makedatesorter()
         elif sortmode == 'sourcesort':
             picknext = makesourcesorter()
         else:
             raise util.Abort(_('unknown sort mode: %s') % sortmode)
 
         children, actives = mapchildren(parents)
 
         s = []
         pendings = {}
         while actives:
             n = picknext(actives)
             actives.remove(n)
             s.append(n)
 
             # Update dependents list
             for c in children.get(n, []):
                 if c not in pendings:
                     pendings[c] = [p for p in parents[c] if p not in self.map]
                 try:
                     pendings[c].remove(n)
                 except ValueError:
                     raise util.Abort(_('cycle detected between %s and %s')
                                        % (recode(c), recode(n)))
                 if not pendings[c]:
                     # Parents are converted, node is eligible
                     actives.insert(0, c)
                     pendings[c] = None
 
         if len(s) != len(parents):
             raise util.Abort(_("not all revisions were sorted"))
 
         return s
 
     def writeauthormap(self):
         authorfile = self.authorfile
         if authorfile:
             self.ui.status(_('Writing author map file %s\n') % authorfile)
             ofile = open(authorfile, 'w+')
             for author in self.authors:
                 ofile.write("%s=%s\n" % (author, self.authors[author]))
             ofile.close()
 
     def readauthormap(self, authorfile):
         afile = open(authorfile, 'r')
         for line in afile:
 
             line = line.strip()
             if not line or line.startswith('#'):
                 continue
 
             try:
                 srcauthor, dstauthor = line.split('=', 1)
             except ValueError:
                 msg = _('Ignoring bad line in author map file %s: %s\n')
                 self.ui.warn(msg % (authorfile, line.rstrip()))
                 continue
 
             srcauthor = srcauthor.strip()
             dstauthor = dstauthor.strip()
             if self.authors.get(srcauthor) in (None, dstauthor):
                 msg = _('mapping author %s to %s\n')
                 self.ui.debug(msg % (srcauthor, dstauthor))
                 self.authors[srcauthor] = dstauthor
                 continue
 
             m = _('overriding mapping for author %s, was %s, will be %s\n')
             self.ui.status(m % (srcauthor, self.authors[srcauthor], dstauthor))
 
         afile.close()
 
     def cachecommit(self, rev):
         commit = self.source.getcommit(rev)
         commit.author = self.authors.get(commit.author, commit.author)
         commit.branch = self.branchmap.get(commit.branch, commit.branch)
         self.commitcache[rev] = commit
         return commit
 
     def copy(self, rev):
         commit = self.commitcache[rev]
 
         changes = self.source.getchanges(rev)
         if isinstance(changes, basestring):
             if changes == SKIPREV:
                 dest = SKIPREV
             else:
                 dest = self.map[changes]
             self.map[rev] = dest
             return
         files, copies = changes
         pbranches = []
         if commit.parents:
             for prev in commit.parents:
                 if prev not in self.commitcache:
                     self.cachecommit(prev)
                 pbranches.append((self.map[prev],
                                   self.commitcache[prev].branch))
         self.dest.setbranch(commit.branch, pbranches)
         try:
             parents = self.splicemap[rev].replace(',', ' ').split()
             self.ui.status(_('spliced in %s as parents of %s\n') %
                            (parents, rev))
             parents = [self.map.get(p, p) for p in parents]
         except KeyError:
             parents = [b[0] for b in pbranches]
         newnode = self.dest.putcommit(files, copies, parents, commit,
                                       self.source, self.map)
         self.source.converted(rev, newnode)
         self.map[rev] = newnode
 
     def convert(self, sortmode):
         try:
             self.source.before()
             self.dest.before()
             self.source.setrevmap(self.map)
             self.ui.status(_("scanning source...\n"))
             heads = self.source.getheads()
             parents = self.walktree(heads)
             self.ui.status(_("sorting...\n"))
             t = self.toposort(parents, sortmode)
             num = len(t)
             c = None
 
             self.ui.status(_("converting...\n"))
-            for c in t:
+            for i, c in enumerate(t):                
                 num -= 1
                 desc = self.commitcache[c].desc
                 if "\n" in desc:
                     desc = desc.splitlines()[0]
                 # convert log message to local encoding without using
                 # tolocal() because encoding.encoding conver() use it as
                 # 'utf-8'
                 self.ui.status("%d %s\n" % (num, recode(desc)))
                 self.ui.note(_("source: %s\n") % recode(c))
+                self.ui.progress(_('converting'), i, unit=_('revisions'),
+                                 total=len(t))
                 self.copy(c)
+            self.ui.progress(_('converting'), None)
 
             tags = self.source.gettags()
             ctags = {}
             for k in tags:
                 v = tags[k]
                 if self.map.get(v, SKIPREV) != SKIPREV:
                     ctags[k] = self.map[v]
 
             if c and ctags:
                 nrev, tagsparent = self.dest.puttags(ctags)
                 if nrev and tagsparent:
                     # write another hash correspondence to override the previous
                     # one so we don't end up with extra tag heads
                     tagsparents = [e for e in self.map.iteritems()
                                    if e[1] == tagsparent]
                     if tagsparents:
                         self.map[tagsparents[0][0]] = nrev
 
             self.writeauthormap()
         finally:
             self.cleanup()
 
     def cleanup(self):
         try:
             self.dest.after()
         finally:
             self.source.after()
         self.map.close()
 
 def convert(ui, src, dest=None, revmapfile=None, **opts):
     global orig_encoding
     orig_encoding = encoding.encoding
     encoding.encoding = 'UTF-8'
 
     if not dest:
         dest = hg.defaultdest(src) + "-hg"
         ui.status(_("assuming destination %s\n") % dest)
 
     destc = convertsink(ui, dest, opts.get('dest_type'))
 
     try:
         srcc, defaultsort = convertsource(ui, src, opts.get('source_type'),
                                           opts.get('rev'))
     except Exception:
         for path in destc.created:
             shutil.rmtree(path, True)
         raise
 
     sortmodes = ('branchsort', 'datesort', 'sourcesort')
     sortmode = [m for m in sortmodes if opts.get(m)]
     if len(sortmode) > 1:
         raise util.Abort(_('more than one sort mode specified'))
     sortmode = sortmode and sortmode[0] or defaultsort
     if sortmode == 'sourcesort' and not srcc.hasnativeorder():
         raise util.Abort(_('--sourcesort is not supported by this data source'))
 
     fmap = opts.get('filemap')
     if fmap:
         srcc = filemap.filemap_source(ui, srcc, fmap)
         destc.setfilemapmode(True)
 
     if not revmapfile:
         try:
             revmapfile = destc.revmapfile()
         except:
             revmapfile = os.path.join(destc, "map")
 
     c = converter(ui, srcc, destc, revmapfile, opts)
     c.convert(sortmode)
 

tests/test-convert-svn-move

@@ -1,53 +1,70
 #!/bin/sh
 
 "$TESTDIR/hghave" svn svn-bindings || exit 80
 
 fix_path()
 {
     tr '\\' /
 }
 
 echo "[extensions]" >> $HGRCPATH
 echo "convert = " >> $HGRCPATH
 echo "hgext.graphlog =" >> $HGRCPATH
 
 svnadmin create svn-repo
 cat "$TESTDIR/svn/move.svndump" | svnadmin load svn-repo > /dev/null
 
 svnpath=`pwd | fix_path`
 # SVN wants all paths to start with a slash. Unfortunately,
 # Windows ones don't. Handle that.
 expr "$svnpath" : "\/" > /dev/null
 if [ $? -ne 0 ]; then
     svnpath="/$svnpath"
 fi
 svnurl="file://$svnpath/svn-repo"
 
 echo % convert trunk and branches
 hg convert --datesort "$svnurl"/subproject A-hg
 
 cd A-hg
 hg glog --template '{rev} {desc|firstline} files: {files}\n'
 echo '% check move copy records'
 hg st --rev 12:13 --copies
 echo '% check branches'
 hg branches | sed 's/:.*/:/'
 cd ..
 
 mkdir test-replace
 cd test-replace
 svnadmin create svn-repo
 cat "$TESTDIR/svn/replace.svndump" | svnadmin load svn-repo > /dev/null
 
 echo '% convert files being replaced by directories'
 hg convert svn-repo hg-repo
 cd hg-repo
 echo '% manifest before'
 hg -v manifest -r 1
 echo '% manifest after clobber1'
 hg -v manifest -r 2
 echo '% manifest after clobber2'
 hg -v manifest -r 3
 echo '% try updating'
 hg up -qC default
 cd ..
+
+echo '% test convert progress bar'
+
+echo "progress=" >> $HGRCPATH
+echo "[progress]" >> $HGRCPATH
+echo "assume-tty=1" >> $HGRCPATH
+echo "delay=0" >> $HGRCPATH
+echo "refresh=0" >> $HGRCPATH
+
+cat > filtercr.py <<EOF
+import sys, re
+for line in sys.stdin:
+    line = re.sub(r'\r+[^\n]', lambda m: '\n' + m.group()[-1:], line)
+    sys.stdout.write(line)
+EOF
+
+hg convert svn-repo hg-progress 2>&1 | python filtercr.py

tests/test-convert-svn-move.out

@@ -1,82 +1,105
 % convert trunk and branches
 initializing destination A-hg repository
 scanning source...
 sorting...
 converting...
 13 createtrunk
 12 moved1
 11 moved1
 10 moved2
 9 changeb and rm d2
 8 changeb and rm d2
 7 moved1again
 6 moved1again
 5 copyfilefrompast
 4 copydirfrompast
 3 add d3
 2 copy dir and remove subdir
 1 add d4old
 0 rename d4old into d4new
 o  13 rename d4old into d4new files: d4new/g d4old/g
 |
 o  12 add d4old files: d4old/g
 |
 o  11 copy dir and remove subdir files: d3/d31/e d4/d31/e d4/f
 |
 o  10 add d3 files: d3/d31/e d3/f
 |
 o  9 copydirfrompast files: d2/d
 |
 o  8 copyfilefrompast files: d
 |
 o  7 moved1again files: d1/b d1/c
 |
 | o  6 moved1again files:
 | |
 o |  5 changeb and rm d2 files: d1/b d2/d
 | |
 | o  4 changeb and rm d2 files: b
 | |
 o |  3 moved2 files: d2/d
 | |
 o |  2 moved1 files: d1/b d1/c
 | |
 | o  1 moved1 files: b c
 |
 o  0 createtrunk files:
 
 % check move copy records
 A d4new/g
   d4old/g
 R d4old/g
 % check branches
 default                       13:
 d1                             6:
 % convert files being replaced by directories
 initializing destination hg-repo repository
 scanning source...
 sorting...
 converting...
 3 initial
 2 clobber symlink
 1 clobber1
 0 clobber2
 % manifest before
 644   a
 644   d/b
 644 @ dlink
 644 @ dlink2
 644   dlink3
 % manifest after clobber1
 644   a/b
 644   d/b
 644   dlink/b
 644 @ dlink2
 644   dlink3
 % manifest after clobber2
 644   a/b
 644   d/b
 644   dlink/b
 644 @ dlink2
 644 @ dlink3
 % try updating
+% test convert progress bar
+
+scanning [ <=>                                                              ] 1
+scanning [  <=>                                                             ] 2
+scanning [   <=>                                                            ] 3
+scanning [    <=>                                                           ] 4
+                                                                                
+converting [                                                              ] 0/4
+                                                                                
+converting [==============>                                               ] 1/4
+                                                                                
+converting [==============================>                               ] 2/4
+                                                                                
+converting [=============================================>                ] 3/4
+                                                                                
+initializing destination hg-progress repository
+scanning source...
+sorting...
+converting...
+3 initial
+2 clobber symlink
+1 clobber1
+0 clobber2