convert: better error on invalid repository type

hgext/convert/convcmd.py

@@ -1,399 +1,403 b''
 # 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, incorporated herein by reference.
 
 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)
             commit = self.cachecommit(n)
             parents[n] = []
             for p in commit.parents:
                 parents[n].append(p)
                 visit.append(p)
 
         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:
                 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.copy(c)
 
             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

@@ -1,52 +1,59 b''
 #!/bin/sh
 
 cat >> $HGRCPATH <<EOF
 [extensions]
 convert=
 [convert]
 hg.saverev=False
 EOF
 
 hg help convert
 
 hg init a
 cd a
 echo a > a
 hg ci -d'0 0' -Ama
 hg cp a b
 hg ci -d'1 0' -mb
 hg rm a
 hg ci -d'2 0' -mc
 hg mv b a
 hg ci -d'3 0' -md
 echo a >> a
 hg ci -d'4 0' -me
 
 cd ..
 hg convert a 2>&1 | grep -v 'subversion python bindings could not be loaded'
 hg --cwd a-hg pull ../a
 
 touch bogusfile
 echo % should fail
 hg convert a bogusfile
 
 mkdir bogusdir
 chmod 000 bogusdir
 
 echo % should fail
 hg convert a bogusdir
 
 echo % should succeed
 chmod 700 bogusdir
 hg convert a bogusdir
 
 echo % test pre and post conversion actions
 echo 'include b' > filemap
 hg convert --debug --filemap filemap a partialb | \
     grep 'run hg'
 
 echo % converting empty dir should fail "nicely"
 mkdir emptydir
 # override $PATH to ensure p4 not visible; use $PYTHON in case we're
 # running from a devel copy, not a temp installation
 PATH=$BINDIR $PYTHON $BINDIR/hg convert emptydir 2>&1 | sed 's,file://.*/emptydir,.../emptydir,g'
+
+echo % convert with imaginary source type
+hg convert --source-type foo a a-foo
+echo % convert with imaginary sink type
+hg convert --dest-type foo a a-foo
+
+true

tests/test-convert.out

@@ -1,261 +1,266 b''
 hg convert [OPTION]... SOURCE [DEST [REVMAP]]
 
 convert a foreign SCM repository to a Mercurial one.
 
     Accepted source formats [identifiers]:
 
     - Mercurial [hg]
     - CVS [cvs]
     - Darcs [darcs]
     - git [git]
     - Subversion [svn]
     - Monotone [mtn]
     - GNU Arch [gnuarch]
     - Bazaar [bzr]
     - Perforce [p4]
 
     Accepted destination formats [identifiers]:
 
     - Mercurial [hg]
     - Subversion [svn] (history on branches is not preserved)
 
     If no revision is given, all revisions will be converted. Otherwise,
     convert will only import up to the named revision (given in a format
     understood by the source).
 
     If no destination directory name is specified, it defaults to the basename
     of the source with '-hg' appended. If the destination repository doesn't
     exist, it will be created.
 
     By default, all sources except Mercurial will use --branchsort. Mercurial
     uses --sourcesort to preserve original revision numbers order. Sort modes
     have the following effects:
 
     --branchsort  convert from parent to child revision when possible, which
                   means branches are usually converted one after the other. It
                   generates more compact repositories.
     --datesort    sort revisions by date. Converted repositories have good-
                   looking changelogs but are often an order of magnitude
                   larger than the same ones generated by --branchsort.
     --sourcesort  try to preserve source revisions order, only supported by
                   Mercurial sources.
 
     If <REVMAP> isn't given, it will be put in a default location
     (<dest>/.hg/shamap by default). The <REVMAP> is a simple text file that
     maps each source commit ID to the destination ID for that revision, like
     so:
 
       <source ID> <destination ID>
 
     If the file doesn't exist, it's automatically created. It's updated on
     each commit copied, so convert-repo can be interrupted and can be run
     repeatedly to copy new commits.
 
     The [username mapping] file is a simple text file that maps each source
     commit author to a destination commit author. It is handy for source SCMs
     that use unix logins to identify authors (eg: CVS). One line per author
     mapping and the line format is: srcauthor=whatever string you want
 
     The filemap is a file that allows filtering and remapping of files and
     directories. Comment lines start with '#'. Each line can contain one of
     the following directives:
 
       include path/to/file
 
       exclude path/to/file
 
       rename from/file to/file
 
     The 'include' directive causes a file, or all files under a directory, to
     be included in the destination repository, and the exclusion of all other
     files and directories not explicitly included. The 'exclude' directive
     causes files or directories to be omitted. The 'rename' directive renames
     a file or directory. To rename from a subdirectory into the root of the
     repository, use '.' as the path to rename to.
 
     The splicemap is a file that allows insertion of synthetic history,
     letting you specify the parents of a revision. This is useful if you want
     to e.g. give a Subversion merge two parents, or graft two disconnected
     series of history together. Each entry contains a key, followed by a
     space, followed by one or two comma-separated values. The key is the
     revision ID in the source revision control system whose parents should be
     modified (same format as a key in .hg/shamap). The values are the revision
     IDs (in either the source or destination revision control system) that
     should be used as the new parents for that node. For example, if you have
     merged "release-1.0" into "trunk", then you should specify the revision on
     "trunk" as the first parent and the one on the "release-1.0" branch as the
     second.
 
     The branchmap is a file that allows you to rename a branch when it is
     being brought in from whatever external repository. When used in
     conjunction with a splicemap, it allows for a powerful combination to help
     fix even the most badly mismanaged repositories and turn them into nicely
     structured Mercurial repositories. The branchmap contains lines of the
     form "original_branch_name new_branch_name". "original_branch_name" is the
     name of the branch in the source repository, and "new_branch_name" is the
     name of the branch is the destination repository. This can be used to (for
     instance) move code in one repository from "default" to a named branch.
 
     Mercurial Source
     ----------------
 
     --config convert.hg.ignoreerrors=False    (boolean)
         ignore integrity errors when reading. Use it to fix Mercurial
         repositories with missing revlogs, by converting from and to
         Mercurial.
     --config convert.hg.saverev=False         (boolean)
         store original revision ID in changeset (forces target IDs to change)
     --config convert.hg.startrev=0            (hg revision identifier)
         convert start revision and its descendants
 
     CVS Source
     ----------
 
     CVS source will use a sandbox (i.e. a checked-out copy) from CVS to
     indicate the starting point of what will be converted. Direct access to
     the repository files is not needed, unless of course the repository is
     :local:. The conversion uses the top level directory in the sandbox to
     find the CVS repository, and then uses CVS rlog commands to find files to
     convert. This means that unless a filemap is given, all files under the
     starting directory will be converted, and that any directory
     reorganization in the CVS sandbox is ignored.
 
     The options shown are the defaults.
 
     --config convert.cvsps.cache=True         (boolean)
         Set to False to disable remote log caching, for testing and debugging
         purposes.
     --config convert.cvsps.fuzz=60            (integer)
         Specify the maximum time (in seconds) that is allowed between commits
         with identical user and log message in a single changeset. When very
         large files were checked in as part of a changeset then the default
         may not be long enough.
     --config convert.cvsps.mergeto='{{mergetobranch ([-\w]+)}}'
         Specify a regular expression to which commit log messages are matched.
         If a match occurs, then the conversion process will insert a dummy
         revision merging the branch on which this log message occurs to the
         branch indicated in the regex.
     --config convert.cvsps.mergefrom='{{mergefrombranch ([-\w]+)}}'
         Specify a regular expression to which commit log messages are matched.
         If a match occurs, then the conversion process will add the most
         recent revision on the branch indicated in the regex as the second
         parent of the changeset.
 
     An additional "debugcvsps" Mercurial command allows the builtin changeset
     merging code to be run without doing a conversion. Its parameters and
     output are similar to that of cvsps 2.1. Please see the command help for
     more details.
 
     Subversion Source
     -----------------
 
     Subversion source detects classical trunk/branches/tags layouts. By
     default, the supplied "svn://repo/path/" source URL is converted as a
     single branch. If "svn://repo/path/trunk" exists it replaces the default
     branch. If "svn://repo/path/branches" exists, its subdirectories are
     listed as possible branches. If "svn://repo/path/tags" exists, it is
     looked for tags referencing converted branches. Default "trunk",
     "branches" and "tags" values can be overridden with following options. Set
     them to paths relative to the source URL, or leave them blank to disable
     auto detection.
 
     --config convert.svn.branches=branches    (directory name)
         specify the directory containing branches
     --config convert.svn.tags=tags            (directory name)
         specify the directory containing tags
     --config convert.svn.trunk=trunk          (directory name)
         specify the name of the trunk branch
 
     Source history can be retrieved starting at a specific revision, instead
     of being integrally converted. Only single branch conversions are
     supported.
 
     --config convert.svn.startrev=0           (svn revision number)
         specify start Subversion revision.
 
     Perforce Source
     ---------------
 
     The Perforce (P4) importer can be given a p4 depot path or a client
     specification as source. It will convert all files in the source to a flat
     Mercurial repository, ignoring labels, branches and integrations. Note
     that when a depot path is given you then usually should specify a target
     directory, because otherwise the target may be named ...-hg.
 
     It is possible to limit the amount of source history to be converted by
     specifying an initial Perforce revision.
 
     --config convert.p4.startrev=0            (perforce changelist number)
         specify initial Perforce revision.
 
     Mercurial Destination
     ---------------------
 
     --config convert.hg.clonebranches=False   (boolean)
         dispatch source branches in separate clones.
     --config convert.hg.tagsbranch=default    (branch name)
         tag revisions branch name
     --config convert.hg.usebranchnames=True   (boolean)
         preserve branch names
 
 options:
 
  -A --authors      username mapping filename
  -d --dest-type    destination repository type
     --filemap      remap file names using contents of file
  -r --rev          import up to target revision REV
  -s --source-type  source repository type
     --splicemap    splice synthesized history into place
     --branchmap    change branch names while converting
     --branchsort   try to sort changesets by branches
     --datesort     try to sort changesets by date
     --sourcesort   preserve source changesets order
 
 use "hg -v help convert" to show global options
 adding a
 assuming destination a-hg
 initializing destination a-hg repository
 scanning source...
 sorting...
 converting...
 4 a
 3 b
 2 c
 1 d
 0 e
 pulling from ../a
 searching for changes
 no changes found
 % should fail
 initializing destination bogusfile repository
 abort: cannot create new bundle repository
 % should fail
 abort: Permission denied: bogusdir
 % should succeed
 initializing destination bogusdir repository
 scanning source...
 sorting...
 converting...
 4 a
 3 b
 2 c
 1 d
 0 e
 % test pre and post conversion actions
 run hg source pre-conversion action
 run hg sink pre-conversion action
 run hg sink post-conversion action
 run hg source post-conversion action
 % converting empty dir should fail nicely
 assuming destination emptydir-hg
 initializing destination emptydir-hg repository
 emptydir does not look like a CVS checkout
 emptydir does not look like a Git repo
 emptydir does not look like a Subversion repo
 emptydir is not a local Mercurial repo
 emptydir does not look like a darcs repo
 emptydir does not look like a monotone repo
 emptydir does not look like a GNU Arch repo
 emptydir does not look like a Bazaar repo
 cannot find required "p4" tool
 abort: emptydir: missing or unsupported repository
+% convert with imaginary source type
+initializing destination a-foo repository
+abort: foo: invalid source repository type
+% convert with imaginary sink type
+abort: foo: invalid destination repository type