procutil: bulk-replace function calls to point to new module

contrib/dumprevlog

@@ -1,35 +1,37
 #!/usr/bin/env python
 # Dump revlogs as raw data stream
 # $ find .hg/store/ -name "*.i" | xargs dumprevlog > repo.dump
 
 from __future__ import absolute_import, print_function
 
 import sys
 from mercurial import (
     node,
     revlog,
-    util,
+)
+from mercurial.utils import (
+    procutil,
 )
 
 for fp in (sys.stdin, sys.stdout, sys.stderr):
-    util.setbinary(fp)
+    procutil.setbinary(fp)
 
 def binopen(path, mode='rb'):
     if 'b' not in mode:
         mode = mode + 'b'
     return open(path, mode)
 
 for f in sys.argv[1:]:
     r = revlog.revlog(binopen, f)
     print("file:", f)
     for i in r:
         n = r.node(i)
         p = r.parents(n)
         d = r.revision(n)
         print("node:", node.hex(n))
         print("linkrev:", r.linkrev(i))
         print("parents:", node.hex(p[0]), node.hex(p[1]))
         print("length:", len(d))
         print("-start-")
         print(d)
         print("-end-")

contrib/phabricator.py

@@ -1,924 +1,928
 # phabricator.py - simple Phabricator integration
 #
 # Copyright 2017 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 """simple Phabricator integration
 
 This extension provides a ``phabsend`` command which sends a stack of
 changesets to Phabricator, and a ``phabread`` command which prints a stack of
 revisions in a format suitable for :hg:`import`, and a ``phabupdate`` command
 to update statuses in batch.
 
 By default, Phabricator requires ``Test Plan`` which might prevent some
 changeset from being sent. The requirement could be disabled by changing
 ``differential.require-test-plan-field`` config server side.
 
 Config::
 
     [phabricator]
     # Phabricator URL
     url = https://phab.example.com/
 
     # API token. Get it from https://$HOST/conduit/login/
     # Deprecated: see [phabricator.auth] below
     #token = cli-xxxxxxxxxxxxxxxxxxxxxxxxxxxx
 
     # Repo callsign. If a repo has a URL https://$HOST/diffusion/FOO, then its
     # callsign is "FOO".
     callsign = FOO
 
     # curl command to use. If not set (default), use builtin HTTP library to
     # communicate. If set, use the specified curl command. This could be useful
     # if you need to specify advanced options that is not easily supported by
     # the internal library.
     curlcmd = curl --connect-timeout 2 --retry 3 --silent
 
     [phabricator.auth]
     example.url = https://phab.example.com/
     # API token. Get it from https://$HOST/conduit/login/
     example.token = cli-xxxxxxxxxxxxxxxxxxxxxxxxxxxx
 """
 
 from __future__ import absolute_import
 
 import itertools
 import json
 import operator
 import re
 
 from mercurial.node import bin, nullid
 from mercurial.i18n import _
 from mercurial import (
     cmdutil,
     context,
     encoding,
     error,
     mdiff,
     obsutil,
     parser,
     patch,
     registrar,
     scmutil,
     smartset,
     tags,
     url as urlmod,
     util,
 )
+from mercurial.utils import (
+    procutil,
+)
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 colortable = {
     'phabricator.action.created': 'green',
     'phabricator.action.skipped': 'magenta',
     'phabricator.action.updated': 'magenta',
     'phabricator.desc': '',
     'phabricator.drev': 'bold',
     'phabricator.node': '',
 }
 
 def urlencodenested(params):
     """like urlencode, but works with nested parameters.
 
     For example, if params is {'a': ['b', 'c'], 'd': {'e': 'f'}}, it will be
     flattened to {'a[0]': 'b', 'a[1]': 'c', 'd[e]': 'f'} and then passed to
     urlencode. Note: the encoding is consistent with PHP's http_build_query.
     """
     flatparams = util.sortdict()
     def process(prefix, obj):
         items = {list: enumerate, dict: lambda x: x.items()}.get(type(obj))
         if items is None:
             flatparams[prefix] = obj
         else:
             for k, v in items(obj):
                 if prefix:
                     process('%s[%s]' % (prefix, k), v)
                 else:
                     process(k, v)
     process('', params)
     return util.urlreq.urlencode(flatparams)
 
 printed_token_warning = False
 
 def readlegacytoken(repo):
     """Transitional support for old phabricator tokens.
 
     Remove before the 4.6 release.
     """
     global printed_token_warning
     token = repo.ui.config('phabricator', 'token')
     if token and not printed_token_warning:
         printed_token_warning = True
         repo.ui.warn(_('phabricator.token is deprecated - please '
                        'migrate to the phabricator.auth section.\n'))
     return token
 
 def readurltoken(repo):
     """return conduit url, token and make sure they exist
 
     Currently read from [phabricator] config section. In the future, it might
     make sense to read from .arcconfig and .arcrc as well.
     """
     url = repo.ui.config('phabricator', 'url')
     if not url:
         raise error.Abort(_('config %s.%s is required')
                           % ('phabricator', 'url'))
 
     groups = {}
     for key, val in repo.ui.configitems('phabricator.auth'):
         if '.' not in key:
             repo.ui.warn(_("ignoring invalid [phabricator.auth] key '%s'\n")
                          % key)
             continue
         group, setting = key.rsplit('.', 1)
         groups.setdefault(group, {})[setting] = val
 
     token = None
     for group, auth in groups.iteritems():
         if url != auth.get('url'):
             continue
         token = auth.get('token')
         if token:
             break
 
     if not token:
         token = readlegacytoken(repo)
         if not token:
             raise error.Abort(_('Can\'t find conduit token associated to %s')
                               % (url,))
 
     return url, token
 
 def callconduit(repo, name, params):
     """call Conduit API, params is a dict. return json.loads result, or None"""
     host, token = readurltoken(repo)
     url, authinfo = util.url('/'.join([host, 'api', name])).authinfo()
     repo.ui.debug('Conduit Call: %s %s\n' % (url, params))
     params = params.copy()
     params['api.token'] = token
     data = urlencodenested(params)
     curlcmd = repo.ui.config('phabricator', 'curlcmd')
     if curlcmd:
-        sin, sout = util.popen2('%s -d @- %s' % (curlcmd, util.shellquote(url)))
+        sin, sout = procutil.popen2('%s -d @- %s'
+                                    % (curlcmd, procutil.shellquote(url)))
         sin.write(data)
         sin.close()
         body = sout.read()
     else:
         urlopener = urlmod.opener(repo.ui, authinfo)
         request = util.urlreq.request(url, data=data)
         body = urlopener.open(request).read()
     repo.ui.debug('Conduit Response: %s\n' % body)
     parsed = json.loads(body)
     if parsed.get(r'error_code'):
         msg = (_('Conduit Error (%s): %s')
                % (parsed[r'error_code'], parsed[r'error_info']))
         raise error.Abort(msg)
     return parsed[r'result']
 
 @command('debugcallconduit', [], _('METHOD'))
 def debugcallconduit(ui, repo, name):
     """call Conduit API
 
     Call parameters are read from stdin as a JSON blob. Result will be written
     to stdout as a JSON blob.
     """
     params = json.loads(ui.fin.read())
     result = callconduit(repo, name, params)
     s = json.dumps(result, sort_keys=True, indent=2, separators=(',', ': '))
     ui.write('%s\n' % s)
 
 def getrepophid(repo):
     """given callsign, return repository PHID or None"""
     # developer config: phabricator.repophid
     repophid = repo.ui.config('phabricator', 'repophid')
     if repophid:
         return repophid
     callsign = repo.ui.config('phabricator', 'callsign')
     if not callsign:
         return None
     query = callconduit(repo, 'diffusion.repository.search',
                         {'constraints': {'callsigns': [callsign]}})
     if len(query[r'data']) == 0:
         return None
     repophid = encoding.strtolocal(query[r'data'][0][r'phid'])
     repo.ui.setconfig('phabricator', 'repophid', repophid)
     return repophid
 
 _differentialrevisiontagre = re.compile('\AD([1-9][0-9]*)\Z')
 _differentialrevisiondescre = re.compile(
     '^Differential Revision:\s*(?P<url>(?:.*)D(?P<id>[1-9][0-9]*))$', re.M)
 
 def getoldnodedrevmap(repo, nodelist):
     """find previous nodes that has been sent to Phabricator
 
     return {node: (oldnode, Differential diff, Differential Revision ID)}
     for node in nodelist with known previous sent versions, or associated
     Differential Revision IDs. ``oldnode`` and ``Differential diff`` could
     be ``None``.
 
     Examines commit messages like "Differential Revision:" to get the
     association information.
 
     If such commit message line is not found, examines all precursors and their
     tags. Tags with format like "D1234" are considered a match and the node
     with that tag, and the number after "D" (ex. 1234) will be returned.
 
     The ``old node``, if not None, is guaranteed to be the last diff of
     corresponding Differential Revision, and exist in the repo.
     """
     url, token = readurltoken(repo)
     unfi = repo.unfiltered()
     nodemap = unfi.changelog.nodemap
 
     result = {} # {node: (oldnode?, lastdiff?, drev)}
     toconfirm = {} # {node: (force, {precnode}, drev)}
     for node in nodelist:
         ctx = unfi[node]
         # For tags like "D123", put them into "toconfirm" to verify later
         precnodes = list(obsutil.allpredecessors(unfi.obsstore, [node]))
         for n in precnodes:
             if n in nodemap:
                 for tag in unfi.nodetags(n):
                     m = _differentialrevisiontagre.match(tag)
                     if m:
                         toconfirm[node] = (0, set(precnodes), int(m.group(1)))
                         continue
 
         # Check commit message
         m = _differentialrevisiondescre.search(ctx.description())
         if m:
             toconfirm[node] = (1, set(precnodes), int(m.group('id')))
 
     # Double check if tags are genuine by collecting all old nodes from
     # Phabricator, and expect precursors overlap with it.
     if toconfirm:
         drevs = [drev for force, precs, drev in toconfirm.values()]
         alldiffs = callconduit(unfi, 'differential.querydiffs',
                                {'revisionIDs': drevs})
         getnode = lambda d: bin(encoding.unitolocal(
             getdiffmeta(d).get(r'node', ''))) or None
         for newnode, (force, precset, drev) in toconfirm.items():
             diffs = [d for d in alldiffs.values()
                      if int(d[r'revisionID']) == drev]
 
             # "precursors" as known by Phabricator
             phprecset = set(getnode(d) for d in diffs)
 
             # Ignore if precursors (Phabricator and local repo) do not overlap,
             # and force is not set (when commit message says nothing)
             if not force and not bool(phprecset & precset):
                 tagname = 'D%d' % drev
                 tags.tag(repo, tagname, nullid, message=None, user=None,
                          date=None, local=True)
                 unfi.ui.warn(_('D%s: local tag removed - does not match '
                                'Differential history\n') % drev)
                 continue
 
             # Find the last node using Phabricator metadata, and make sure it
             # exists in the repo
             oldnode = lastdiff = None
             if diffs:
                 lastdiff = max(diffs, key=lambda d: int(d[r'id']))
                 oldnode = getnode(lastdiff)
                 if oldnode and oldnode not in nodemap:
                     oldnode = None
 
             result[newnode] = (oldnode, lastdiff, drev)
 
     return result
 
 def getdiff(ctx, diffopts):
     """plain-text diff without header (user, commit message, etc)"""
     output = util.stringio()
     for chunk, _label in patch.diffui(ctx.repo(), ctx.p1().node(), ctx.node(),
                                       None, opts=diffopts):
         output.write(chunk)
     return output.getvalue()
 
 def creatediff(ctx):
     """create a Differential Diff"""
     repo = ctx.repo()
     repophid = getrepophid(repo)
     # Create a "Differential Diff" via "differential.createrawdiff" API
     params = {'diff': getdiff(ctx, mdiff.diffopts(git=True, context=32767))}
     if repophid:
         params['repositoryPHID'] = repophid
     diff = callconduit(repo, 'differential.createrawdiff', params)
     if not diff:
         raise error.Abort(_('cannot create diff for %s') % ctx)
     return diff
 
 def writediffproperties(ctx, diff):
     """write metadata to diff so patches could be applied losslessly"""
     params = {
         'diff_id': diff[r'id'],
         'name': 'hg:meta',
         'data': json.dumps({
             'user': ctx.user(),
             'date': '%d %d' % ctx.date(),
             'node': ctx.hex(),
             'parent': ctx.p1().hex(),
         }),
     }
     callconduit(ctx.repo(), 'differential.setdiffproperty', params)
 
 def createdifferentialrevision(ctx, revid=None, parentrevid=None, oldnode=None,
                                olddiff=None, actions=None):
     """create or update a Differential Revision
 
     If revid is None, create a new Differential Revision, otherwise update
     revid. If parentrevid is not None, set it as a dependency.
 
     If oldnode is not None, check if the patch content (without commit message
     and metadata) has changed before creating another diff.
 
     If actions is not None, they will be appended to the transaction.
     """
     repo = ctx.repo()
     if oldnode:
         diffopts = mdiff.diffopts(git=True, context=32767)
         oldctx = repo.unfiltered()[oldnode]
         neednewdiff = (getdiff(ctx, diffopts) != getdiff(oldctx, diffopts))
     else:
         neednewdiff = True
 
     transactions = []
     if neednewdiff:
         diff = creatediff(ctx)
         transactions.append({'type': 'update', 'value': diff[r'phid']})
     else:
         # Even if we don't need to upload a new diff because the patch content
         # does not change. We might still need to update its metadata so
         # pushers could know the correct node metadata.
         assert olddiff
         diff = olddiff
     writediffproperties(ctx, diff)
 
     # Use a temporary summary to set dependency. There might be better ways but
     # I cannot find them for now. But do not do that if we are updating an
     # existing revision (revid is not None) since that introduces visible
     # churns (someone edited "Summary" twice) on the web page.
     if parentrevid and revid is None:
         summary = 'Depends on D%s' % parentrevid
         transactions += [{'type': 'summary', 'value': summary},
                          {'type': 'summary', 'value': ' '}]
 
     if actions:
         transactions += actions
 
     # Parse commit message and update related fields.
     desc = ctx.description()
     info = callconduit(repo, 'differential.parsecommitmessage',
                        {'corpus': desc})
     for k, v in info[r'fields'].items():
         if k in ['title', 'summary', 'testPlan']:
             transactions.append({'type': k, 'value': v})
 
     params = {'transactions': transactions}
     if revid is not None:
         # Update an existing Differential Revision
         params['objectIdentifier'] = revid
 
     revision = callconduit(repo, 'differential.revision.edit', params)
     if not revision:
         raise error.Abort(_('cannot create revision for %s') % ctx)
 
     return revision, diff
 
 def userphids(repo, names):
     """convert user names to PHIDs"""
     query = {'constraints': {'usernames': names}}
     result = callconduit(repo, 'user.search', query)
     # username not found is not an error of the API. So check if we have missed
     # some names here.
     data = result[r'data']
     resolved = set(entry[r'fields'][r'username'] for entry in data)
     unresolved = set(names) - resolved
     if unresolved:
         raise error.Abort(_('unknown username: %s')
                           % ' '.join(sorted(unresolved)))
     return [entry[r'phid'] for entry in data]
 
 @command('phabsend',
          [('r', 'rev', [], _('revisions to send'), _('REV')),
           ('', 'amend', True, _('update commit messages')),
           ('', 'reviewer', [], _('specify reviewers')),
           ('', 'confirm', None, _('ask for confirmation before sending'))],
          _('REV [OPTIONS]'))
 def phabsend(ui, repo, *revs, **opts):
     """upload changesets to Phabricator
 
     If there are multiple revisions specified, they will be send as a stack
     with a linear dependencies relationship using the order specified by the
     revset.
 
     For the first time uploading changesets, local tags will be created to
     maintain the association. After the first time, phabsend will check
     obsstore and tags information so it can figure out whether to update an
     existing Differential Revision, or create a new one.
 
     If --amend is set, update commit messages so they have the
     ``Differential Revision`` URL, remove related tags. This is similar to what
     arcanist will do, and is more desired in author-push workflows. Otherwise,
     use local tags to record the ``Differential Revision`` association.
 
     The --confirm option lets you confirm changesets before sending them. You
     can also add following to your configuration file to make it default
     behaviour::
 
         [phabsend]
         confirm = true
 
     phabsend will check obsstore and the above association to decide whether to
     update an existing Differential Revision, or create a new one.
     """
     revs = list(revs) + opts.get('rev', [])
     revs = scmutil.revrange(repo, revs)
 
     if not revs:
         raise error.Abort(_('phabsend requires at least one changeset'))
     if opts.get('amend'):
         cmdutil.checkunfinished(repo)
 
     # {newnode: (oldnode, olddiff, olddrev}
     oldmap = getoldnodedrevmap(repo, [repo[r].node() for r in revs])
 
     confirm = ui.configbool('phabsend', 'confirm')
     confirm |= bool(opts.get('confirm'))
     if confirm:
         confirmed = _confirmbeforesend(repo, revs, oldmap)
         if not confirmed:
             raise error.Abort(_('phabsend cancelled'))
 
     actions = []
     reviewers = opts.get('reviewer', [])
     if reviewers:
         phids = userphids(repo, reviewers)
         actions.append({'type': 'reviewers.add', 'value': phids})
 
     drevids = [] # [int]
     diffmap = {} # {newnode: diff}
 
     # Send patches one by one so we know their Differential Revision IDs and
     # can provide dependency relationship
     lastrevid = None
     for rev in revs:
         ui.debug('sending rev %d\n' % rev)
         ctx = repo[rev]
 
         # Get Differential Revision ID
         oldnode, olddiff, revid = oldmap.get(ctx.node(), (None, None, None))
         if oldnode != ctx.node() or opts.get('amend'):
             # Create or update Differential Revision
             revision, diff = createdifferentialrevision(
                 ctx, revid, lastrevid, oldnode, olddiff, actions)
             diffmap[ctx.node()] = diff
             newrevid = int(revision[r'object'][r'id'])
             if revid:
                 action = 'updated'
             else:
                 action = 'created'
 
             # Create a local tag to note the association, if commit message
             # does not have it already
             m = _differentialrevisiondescre.search(ctx.description())
             if not m or int(m.group('id')) != newrevid:
                 tagname = 'D%d' % newrevid
                 tags.tag(repo, tagname, ctx.node(), message=None, user=None,
                          date=None, local=True)
         else:
             # Nothing changed. But still set "newrevid" so the next revision
             # could depend on this one.
             newrevid = revid
             action = 'skipped'
 
         actiondesc = ui.label(
             {'created': _('created'),
              'skipped': _('skipped'),
              'updated': _('updated')}[action],
             'phabricator.action.%s' % action)
         drevdesc = ui.label('D%s' % newrevid, 'phabricator.drev')
         nodedesc = ui.label(bytes(ctx), 'phabricator.node')
         desc = ui.label(ctx.description().split('\n')[0], 'phabricator.desc')
         ui.write(_('%s - %s - %s: %s\n') % (drevdesc, actiondesc, nodedesc,
                                             desc))
         drevids.append(newrevid)
         lastrevid = newrevid
 
     # Update commit messages and remove tags
     if opts.get('amend'):
         unfi = repo.unfiltered()
         drevs = callconduit(repo, 'differential.query', {'ids': drevids})
         with repo.wlock(), repo.lock(), repo.transaction('phabsend'):
             wnode = unfi['.'].node()
             mapping = {} # {oldnode: [newnode]}
             for i, rev in enumerate(revs):
                 old = unfi[rev]
                 drevid = drevids[i]
                 drev = [d for d in drevs if int(d[r'id']) == drevid][0]
                 newdesc = getdescfromdrev(drev)
                 # Make sure commit message contain "Differential Revision"
                 if old.description() != newdesc:
                     parents = [
                         mapping.get(old.p1().node(), (old.p1(),))[0],
                         mapping.get(old.p2().node(), (old.p2(),))[0],
                     ]
                     new = context.metadataonlyctx(
                         repo, old, parents=parents, text=newdesc,
                         user=old.user(), date=old.date(), extra=old.extra())
                     newnode = new.commit()
                     mapping[old.node()] = [newnode]
                     # Update diff property
                     writediffproperties(unfi[newnode], diffmap[old.node()])
                 # Remove local tags since it's no longer necessary
                 tagname = 'D%d' % drevid
                 if tagname in repo.tags():
                     tags.tag(repo, tagname, nullid, message=None, user=None,
                              date=None, local=True)
             scmutil.cleanupnodes(repo, mapping, 'phabsend')
             if wnode in mapping:
                 unfi.setparents(mapping[wnode][0])
 
 # Map from "hg:meta" keys to header understood by "hg import". The order is
 # consistent with "hg export" output.
 _metanamemap = util.sortdict([(r'user', 'User'), (r'date', 'Date'),
                               (r'node', 'Node ID'), (r'parent', 'Parent ')])
 
 def _confirmbeforesend(repo, revs, oldmap):
     url, token = readurltoken(repo)
     ui = repo.ui
     for rev in revs:
         ctx = repo[rev]
         desc = ctx.description().splitlines()[0]
         oldnode, olddiff, drevid = oldmap.get(ctx.node(), (None, None, None))
         if drevid:
             drevdesc = ui.label('D%s' % drevid, 'phabricator.drev')
         else:
             drevdesc = ui.label(_('NEW'), 'phabricator.drev')
 
         ui.write(_('%s - %s: %s\n') % (drevdesc,
                                        ui.label(bytes(ctx), 'phabricator.node'),
                                        ui.label(desc, 'phabricator.desc')))
 
     if ui.promptchoice(_('Send the above changes to %s (yn)?'
                          '$$ &Yes $$ &No') % url):
         return False
 
     return True
 
 _knownstatusnames = {'accepted', 'needsreview', 'needsrevision', 'closed',
                      'abandoned'}
 
 def _getstatusname(drev):
     """get normalized status name from a Differential Revision"""
     return drev[r'statusName'].replace(' ', '').lower()
 
 # Small language to specify differential revisions. Support symbols: (), :X,
 # +, and -.
 
 _elements = {
     # token-type: binding-strength, primary, prefix, infix, suffix
     '(':      (12, None, ('group', 1, ')'), None, None),
     ':':      (8, None, ('ancestors', 8), None, None),
     '&':      (5,  None, None, ('and_', 5), None),
     '+':      (4,  None, None, ('add', 4), None),
     '-':      (4,  None, None, ('sub', 4), None),
     ')':      (0,  None, None, None, None),
     'symbol': (0, 'symbol', None, None, None),
     'end':    (0, None, None, None, None),
 }
 
 def _tokenize(text):
     view = memoryview(text) # zero-copy slice
     special = '():+-& '
     pos = 0
     length = len(text)
     while pos < length:
         symbol = ''.join(itertools.takewhile(lambda ch: ch not in special,
                                              view[pos:]))
         if symbol:
             yield ('symbol', symbol, pos)
             pos += len(symbol)
         else: # special char, ignore space
             if text[pos] != ' ':
                 yield (text[pos], None, pos)
             pos += 1
     yield ('end', None, pos)
 
 def _parse(text):
     tree, pos = parser.parser(_elements).parse(_tokenize(text))
     if pos != len(text):
         raise error.ParseError('invalid token', pos)
     return tree
 
 def _parsedrev(symbol):
     """str -> int or None, ex. 'D45' -> 45; '12' -> 12; 'x' -> None"""
     if symbol.startswith('D') and symbol[1:].isdigit():
         return int(symbol[1:])
     if symbol.isdigit():
         return int(symbol)
 
 def _prefetchdrevs(tree):
     """return ({single-drev-id}, {ancestor-drev-id}) to prefetch"""
     drevs = set()
     ancestordrevs = set()
     op = tree[0]
     if op == 'symbol':
         r = _parsedrev(tree[1])
         if r:
             drevs.add(r)
     elif op == 'ancestors':
         r, a = _prefetchdrevs(tree[1])
         drevs.update(r)
         ancestordrevs.update(r)
         ancestordrevs.update(a)
     else:
         for t in tree[1:]:
             r, a = _prefetchdrevs(t)
             drevs.update(r)
             ancestordrevs.update(a)
     return drevs, ancestordrevs
 
 def querydrev(repo, spec):
     """return a list of "Differential Revision" dicts
 
     spec is a string using a simple query language, see docstring in phabread
     for details.
 
     A "Differential Revision dict" looks like:
 
         {
             "id": "2",
             "phid": "PHID-DREV-672qvysjcczopag46qty",
             "title": "example",
             "uri": "https://phab.example.com/D2",
             "dateCreated": "1499181406",
             "dateModified": "1499182103",
             "authorPHID": "PHID-USER-tv3ohwc4v4jeu34otlye",
             "status": "0",
             "statusName": "Needs Review",
             "properties": [],
             "branch": null,
             "summary": "",
             "testPlan": "",
             "lineCount": "2",
             "activeDiffPHID": "PHID-DIFF-xoqnjkobbm6k4dk6hi72",
             "diffs": [
               "3",
               "4",
             ],
             "commits": [],
             "reviewers": [],
             "ccs": [],
             "hashes": [],
             "auxiliary": {
               "phabricator:projects": [],
               "phabricator:depends-on": [
                 "PHID-DREV-gbapp366kutjebt7agcd"
               ]
             },
             "repositoryPHID": "PHID-REPO-hub2hx62ieuqeheznasv",
             "sourcePath": null
         }
     """
     def fetch(params):
         """params -> single drev or None"""
         key = (params.get(r'ids') or params.get(r'phids') or [None])[0]
         if key in prefetched:
             return prefetched[key]
         drevs = callconduit(repo, 'differential.query', params)
         # Fill prefetched with the result
         for drev in drevs:
             prefetched[drev[r'phid']] = drev
             prefetched[int(drev[r'id'])] = drev
         if key not in prefetched:
             raise error.Abort(_('cannot get Differential Revision %r') % params)
         return prefetched[key]
 
     def getstack(topdrevids):
         """given a top, get a stack from the bottom, [id] -> [id]"""
         visited = set()
         result = []
         queue = [{r'ids': [i]} for i in topdrevids]
         while queue:
             params = queue.pop()
             drev = fetch(params)
             if drev[r'id'] in visited:
                 continue
             visited.add(drev[r'id'])
             result.append(int(drev[r'id']))
             auxiliary = drev.get(r'auxiliary', {})
             depends = auxiliary.get(r'phabricator:depends-on', [])
             for phid in depends:
                 queue.append({'phids': [phid]})
         result.reverse()
         return smartset.baseset(result)
 
     # Initialize prefetch cache
     prefetched = {} # {id or phid: drev}
 
     tree = _parse(spec)
     drevs, ancestordrevs = _prefetchdrevs(tree)
 
     # developer config: phabricator.batchsize
     batchsize = repo.ui.configint('phabricator', 'batchsize', 12)
 
     # Prefetch Differential Revisions in batch
     tofetch = set(drevs)
     for r in ancestordrevs:
         tofetch.update(range(max(1, r - batchsize), r + 1))
     if drevs:
         fetch({r'ids': list(tofetch)})
     validids = sorted(set(getstack(list(ancestordrevs))) | set(drevs))
 
     # Walk through the tree, return smartsets
     def walk(tree):
         op = tree[0]
         if op == 'symbol':
             drev = _parsedrev(tree[1])
             if drev:
                 return smartset.baseset([drev])
             elif tree[1] in _knownstatusnames:
                 drevs = [r for r in validids
                          if _getstatusname(prefetched[r]) == tree[1]]
                 return smartset.baseset(drevs)
             else:
                 raise error.Abort(_('unknown symbol: %s') % tree[1])
         elif op in {'and_', 'add', 'sub'}:
             assert len(tree) == 3
             return getattr(operator, op)(walk(tree[1]), walk(tree[2]))
         elif op == 'group':
             return walk(tree[1])
         elif op == 'ancestors':
             return getstack(walk(tree[1]))
         else:
             raise error.ProgrammingError('illegal tree: %r' % tree)
 
     return [prefetched[r] for r in walk(tree)]
 
 def getdescfromdrev(drev):
     """get description (commit message) from "Differential Revision"
 
     This is similar to differential.getcommitmessage API. But we only care
     about limited fields: title, summary, test plan, and URL.
     """
     title = drev[r'title']
     summary = drev[r'summary'].rstrip()
     testplan = drev[r'testPlan'].rstrip()
     if testplan:
         testplan = 'Test Plan:\n%s' % testplan
     uri = 'Differential Revision: %s' % drev[r'uri']
     return '\n\n'.join(filter(None, [title, summary, testplan, uri]))
 
 def getdiffmeta(diff):
     """get commit metadata (date, node, user, p1) from a diff object
 
     The metadata could be "hg:meta", sent by phabsend, like:
 
         "properties": {
           "hg:meta": {
             "date": "1499571514 25200",
             "node": "98c08acae292b2faf60a279b4189beb6cff1414d",
             "user": "Foo Bar <[e-mail]>",
             "parent": "6d0abad76b30e4724a37ab8721d630394070fe16"
           }
         }
 
     Or converted from "local:commits", sent by "arc", like:
 
         "properties": {
           "local:commits": {
             "98c08acae292b2faf60a279b4189beb6cff1414d": {
               "author": "Foo Bar",
               "time": 1499546314,
               "branch": "default",
               "tag": "",
               "commit": "98c08acae292b2faf60a279b4189beb6cff1414d",
               "rev": "98c08acae292b2faf60a279b4189beb6cff1414d",
               "local": "1000",
               "parents": ["6d0abad76b30e4724a37ab8721d630394070fe16"],
               "summary": "...",
               "message": "...",
               "authorEmail": "[e-mail]"
             }
           }
         }
 
     Note: metadata extracted from "local:commits" will lose time zone
     information.
     """
     props = diff.get(r'properties') or {}
     meta = props.get(r'hg:meta')
     if not meta and props.get(r'local:commits'):
         commit = sorted(props[r'local:commits'].values())[0]
         meta = {
             r'date': r'%d 0' % commit[r'time'],
             r'node': commit[r'rev'],
             r'user': r'%s <%s>' % (commit[r'author'], commit[r'authorEmail']),
         }
         if len(commit.get(r'parents', ())) >= 1:
             meta[r'parent'] = commit[r'parents'][0]
     return meta or {}
 
 def readpatch(repo, drevs, write):
     """generate plain-text patch readable by 'hg import'
 
     write is usually ui.write. drevs is what "querydrev" returns, results of
     "differential.query".
     """
     # Prefetch hg:meta property for all diffs
     diffids = sorted(set(max(int(v) for v in drev[r'diffs']) for drev in drevs))
     diffs = callconduit(repo, 'differential.querydiffs', {'ids': diffids})
 
     # Generate patch for each drev
     for drev in drevs:
         repo.ui.note(_('reading D%s\n') % drev[r'id'])
 
         diffid = max(int(v) for v in drev[r'diffs'])
         body = callconduit(repo, 'differential.getrawdiff', {'diffID': diffid})
         desc = getdescfromdrev(drev)
         header = '# HG changeset patch\n'
 
         # Try to preserve metadata from hg:meta property. Write hg patch
         # headers that can be read by the "import" command. See patchheadermap
         # and extract in mercurial/patch.py for supported headers.
         meta = getdiffmeta(diffs[str(diffid)])
         for k in _metanamemap.keys():
             if k in meta:
                 header += '# %s %s\n' % (_metanamemap[k], meta[k])
 
         content = '%s%s\n%s' % (header, desc, body)
         write(encoding.unitolocal(content))
 
 @command('phabread',
          [('', 'stack', False, _('read dependencies'))],
          _('DREVSPEC [OPTIONS]'))
 def phabread(ui, repo, spec, **opts):
     """print patches from Phabricator suitable for importing
 
     DREVSPEC could be a Differential Revision identity, like ``D123``, or just
     the number ``123``. It could also have common operators like ``+``, ``-``,
     ``&``, ``(``, ``)`` for complex queries. Prefix ``:`` could be used to
     select a stack.
 
     ``abandoned``, ``accepted``, ``closed``, ``needsreview``, ``needsrevision``
     could be used to filter patches by status. For performance reason, they
     only represent a subset of non-status selections and cannot be used alone.
 
     For example, ``:D6+8-(2+D4)`` selects a stack up to D6, plus D8 and exclude
     D2 and D4. ``:D9 & needsreview`` selects "Needs Review" revisions in a
     stack up to D9.
 
     If --stack is given, follow dependencies information and read all patches.
     It is equivalent to the ``:`` operator.
     """
     if opts.get('stack'):
         spec = ':(%s)' % spec
     drevs = querydrev(repo, spec)
     readpatch(repo, drevs, ui.write)
 
 @command('phabupdate',
          [('', 'accept', False, _('accept revisions')),
           ('', 'reject', False, _('reject revisions')),
           ('', 'abandon', False, _('abandon revisions')),
           ('', 'reclaim', False, _('reclaim revisions')),
           ('m', 'comment', '', _('comment on the last revision')),
          ], _('DREVSPEC [OPTIONS]'))
 def phabupdate(ui, repo, spec, **opts):
     """update Differential Revision in batch
 
     DREVSPEC selects revisions. See :hg:`help phabread` for its usage.
     """
     flags = [n for n in 'accept reject abandon reclaim'.split() if opts.get(n)]
     if len(flags) > 1:
         raise error.Abort(_('%s cannot be used together') % ', '.join(flags))
 
     actions = []
     for f in flags:
         actions.append({'type': f, 'value': 'true'})
 
     drevs = querydrev(repo, spec)
     for i, drev in enumerate(drevs):
         if i + 1 == len(drevs) and opts.get('comment'):
             actions.append({'type': 'comment', 'value': opts['comment']})
         if actions:
             params = {'objectIdentifier': drev[r'phid'],
                       'transactions': actions}
             callconduit(repo, 'differential.revision.edit', params)
 
 templatekeyword = registrar.templatekeyword()
 
 @templatekeyword('phabreview', requires={'ctx'})
 def template_review(context, mapping):
     """:phabreview: Object describing the review for this changeset.
     Has attributes `url` and `id`.
     """
     ctx = context.resource(mapping, 'ctx')
     m = _differentialrevisiondescre.search(ctx.description())
     if m:
         return {
             'url': m.group('url'),
             'id': "D{}".format(m.group('id')),
         }

contrib/simplemerge

@@ -1,81 +1,83
 #!/usr/bin/env python
 from __future__ import absolute_import
 
 import getopt
 import sys
 
 import hgdemandimport
 hgdemandimport.enable()
 
 from mercurial.i18n import _
 from mercurial import (
     context,
     error,
     fancyopts,
     simplemerge,
     ui as uimod,
-    util,
+)
+from mercurial.utils import (
+    procutil,
 )
 
 options = [('L', 'label', [], _('labels to use on conflict markers')),
            ('a', 'text', None, _('treat all files as text')),
            ('p', 'print', None,
             _('print results instead of overwriting LOCAL')),
            ('', 'no-minimal', None, _('no effect (DEPRECATED)')),
            ('h', 'help', None, _('display help and exit')),
            ('q', 'quiet', None, _('suppress output'))]
 
 usage = _('''simplemerge [OPTS] LOCAL BASE OTHER
 
     Simple three-way file merge utility with a minimal feature set.
 
     Apply to LOCAL the changes necessary to go from BASE to OTHER.
 
     By default, LOCAL is overwritten with the results of this operation.
 ''')
 
 class ParseError(Exception):
     """Exception raised on errors in parsing the command line."""
 
 def showhelp():
     sys.stdout.write(usage)
     sys.stdout.write('\noptions:\n')
 
     out_opts = []
     for shortopt, longopt, default, desc in options:
         out_opts.append(('%2s%s' % (shortopt and '-%s' % shortopt,
                                     longopt and ' --%s' % longopt),
                          '%s' % desc))
     opts_len = max([len(opt[0]) for opt in out_opts])
     for first, second in out_opts:
         sys.stdout.write(' %-*s  %s\n' % (opts_len, first, second))
 
 try:
     for fp in (sys.stdin, sys.stdout, sys.stderr):
-        util.setbinary(fp)
+        procutil.setbinary(fp)
 
     opts = {}
     try:
         args = fancyopts.fancyopts(sys.argv[1:], options, opts)
     except getopt.GetoptError as e:
         raise ParseError(e)
     if opts['help']:
         showhelp()
         sys.exit(0)
     if len(args) != 3:
             raise ParseError(_('wrong number of arguments'))
     local, base, other = args
     sys.exit(simplemerge.simplemerge(uimod.ui.load(),
                                      context.arbitraryfilectx(local),
                                      context.arbitraryfilectx(base),
                                      context.arbitraryfilectx(other),
                                      **opts))
 except ParseError as e:
     sys.stdout.write("%s: %s\n" % (sys.argv[0], e))
     showhelp()
     sys.exit(1)
 except error.Abort as e:
     sys.stderr.write("abort: %s\n" % e)
     sys.exit(255)
 except KeyboardInterrupt:
     sys.exit(255)

contrib/undumprevlog

@@ -1,46 +1,48
 #!/usr/bin/env python
 # Undump a dump from dumprevlog
 # $ hg init
 # $ undumprevlog < repo.dump
 
 from __future__ import absolute_import, print_function
 
 import sys
 from mercurial import (
     node,
     revlog,
     transaction,
-    util,
     vfs as vfsmod,
 )
+from mercurial.utils import (
+    procutil,
+)
 
 for fp in (sys.stdin, sys.stdout, sys.stderr):
-    util.setbinary(fp)
+    procutil.setbinary(fp)
 
 opener = vfsmod.vfs('.', False)
 tr = transaction.transaction(sys.stderr.write, opener, {'store': opener},
                              "undump.journal")
 while True:
     l = sys.stdin.readline()
     if not l:
         break
     if l.startswith("file:"):
         f = l[6:-1]
         r = revlog.revlog(opener, f)
         print(f)
     elif l.startswith("node:"):
         n = node.bin(l[6:-1])
     elif l.startswith("linkrev:"):
         lr = int(l[9:-1])
     elif l.startswith("parents:"):
         p = l[9:-1].split()
         p1 = node.bin(p[0])
         p2 = node.bin(p[1])
     elif l.startswith("length:"):
         length = int(l[8:-1])
         sys.stdin.readline() # start marker
         d = sys.stdin.read(length)
         sys.stdin.readline() # end marker
         r.addrevision(d, tr, lr, p1, p2)
 
 tr.close()

hgext/acl.py

@@ -1,377 +1,380
 # acl.py - changeset access control for mercurial
 #
 # Copyright 2006 Vadim Gelfer <[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.
 
 '''hooks for controlling repository access
 
 This hook makes it possible to allow or deny write access to given
 branches and paths of a repository when receiving incoming changesets
 via pretxnchangegroup and pretxncommit.
 
 The authorization is matched based on the local user name on the
 system where the hook runs, and not the committer of the original
 changeset (since the latter is merely informative).
 
 The acl hook is best used along with a restricted shell like hgsh,
 preventing authenticating users from doing anything other than pushing
 or pulling. The hook is not safe to use if users have interactive
 shell access, as they can then disable the hook. Nor is it safe if
 remote users share an account, because then there is no way to
 distinguish them.
 
 The order in which access checks are performed is:
 
 1) Deny  list for branches (section ``acl.deny.branches``)
 2) Allow list for branches (section ``acl.allow.branches``)
 3) Deny  list for paths    (section ``acl.deny``)
 4) Allow list for paths    (section ``acl.allow``)
 
 The allow and deny sections take key-value pairs.
 
 Branch-based Access Control
 ---------------------------
 
 Use the ``acl.deny.branches`` and ``acl.allow.branches`` sections to
 have branch-based access control. Keys in these sections can be
 either:
 
 - a branch name, or
 - an asterisk, to match any branch;
 
 The corresponding values can be either:
 
 - a comma-separated list containing users and groups, or
 - an asterisk, to match anyone;
 
 You can add the "!" prefix to a user or group name to invert the sense
 of the match.
 
 Path-based Access Control
 -------------------------
 
 Use the ``acl.deny`` and ``acl.allow`` sections to have path-based
 access control. Keys in these sections accept a subtree pattern (with
 a glob syntax by default). The corresponding values follow the same
 syntax as the other sections above.
 
 Groups
 ------
 
 Group names must be prefixed with an ``@`` symbol. Specifying a group
 name has the same effect as specifying all the users in that group.
 
 You can define group members in the ``acl.groups`` section.
 If a group name is not defined there, and Mercurial is running under
 a Unix-like system, the list of users will be taken from the OS.
 Otherwise, an exception will be raised.
 
 Example Configuration
 ---------------------
 
 ::
 
   [hooks]
 
   # Use this if you want to check access restrictions at commit time
   pretxncommit.acl = python:hgext.acl.hook
 
   # Use this if you want to check access restrictions for pull, push,
   # bundle and serve.
   pretxnchangegroup.acl = python:hgext.acl.hook
 
   [acl]
   # Allow or deny access for incoming changes only if their source is
   # listed here, let them pass otherwise. Source is "serve" for all
   # remote access (http or ssh), "push", "pull" or "bundle" when the
   # related commands are run locally.
   # Default: serve
   sources = serve
 
   [acl.deny.branches]
 
   # Everyone is denied to the frozen branch:
   frozen-branch = *
 
   # A bad user is denied on all branches:
   * = bad-user
 
   [acl.allow.branches]
 
   # A few users are allowed on branch-a:
   branch-a = user-1, user-2, user-3
 
   # Only one user is allowed on branch-b:
   branch-b = user-1
 
   # The super user is allowed on any branch:
   * = super-user
 
   # Everyone is allowed on branch-for-tests:
   branch-for-tests = *
 
   [acl.deny]
   # This list is checked first. If a match is found, acl.allow is not
   # checked. All users are granted access if acl.deny is not present.
   # Format for both lists: glob pattern = user, ..., @group, ...
 
   # To match everyone, use an asterisk for the user:
   # my/glob/pattern = *
 
   # user6 will not have write access to any file:
   ** = user6
 
   # Group "hg-denied" will not have write access to any file:
   ** = @hg-denied
 
   # Nobody will be able to change "DONT-TOUCH-THIS.txt", despite
   # everyone being able to change all other files. See below.
   src/main/resources/DONT-TOUCH-THIS.txt = *
 
   [acl.allow]
   # if acl.allow is not present, all users are allowed by default
   # empty acl.allow = no users allowed
 
   # User "doc_writer" has write access to any file under the "docs"
   # folder:
   docs/** = doc_writer
 
   # User "jack" and group "designers" have write access to any file
   # under the "images" folder:
   images/** = jack, @designers
 
   # Everyone (except for "user6" and "@hg-denied" - see acl.deny above)
   # will have write access to any file under the "resources" folder
   # (except for 1 file. See acl.deny):
   src/main/resources/** = *
 
   .hgtags = release_engineer
 
 Examples using the "!" prefix
 .............................
 
 Suppose there's a branch that only a given user (or group) should be able to
 push to, and you don't want to restrict access to any other branch that may
 be created.
 
 The "!" prefix allows you to prevent anyone except a given user or group to
 push changesets in a given branch or path.
 
 In the examples below, we will:
 1) Deny access to branch "ring" to anyone but user "gollum"
 2) Deny access to branch "lake" to anyone but members of the group "hobbit"
 3) Deny access to a file to anyone but user "gollum"
 
 ::
 
   [acl.allow.branches]
   # Empty
 
   [acl.deny.branches]
 
   # 1) only 'gollum' can commit to branch 'ring';
   # 'gollum' and anyone else can still commit to any other branch.
   ring = !gollum
 
   # 2) only members of the group 'hobbit' can commit to branch 'lake';
   # 'hobbit' members and anyone else can still commit to any other branch.
   lake = !@hobbit
 
   # You can also deny access based on file paths:
 
   [acl.allow]
   # Empty
 
   [acl.deny]
   # 3) only 'gollum' can change the file below;
   # 'gollum' and anyone else can still change any other file.
   /misty/mountains/cave/ring = !gollum
 
 '''
 
 from __future__ import absolute_import
 
 from mercurial.i18n import _
 from mercurial import (
     error,
     extensions,
     match,
     registrar,
     util,
 )
+from mercurial.utils import (
+    procutil,
+)
 
 urlreq = util.urlreq
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 # deprecated config: acl.config
 configitem('acl', 'config',
     default=None,
 )
 configitem('acl.groups', '.*',
     default=None,
     generic=True,
 )
 configitem('acl.deny.branches', '.*',
     default=None,
     generic=True,
 )
 configitem('acl.allow.branches', '.*',
     default=None,
     generic=True,
 )
 configitem('acl.deny', '.*',
     default=None,
     generic=True,
 )
 configitem('acl.allow', '.*',
     default=None,
     generic=True,
 )
 configitem('acl', 'sources',
     default=lambda: ['serve'],
 )
 
 def _getusers(ui, group):
 
     # First, try to use group definition from section [acl.groups]
     hgrcusers = ui.configlist('acl.groups', group)
     if hgrcusers:
         return hgrcusers
 
     ui.debug('acl: "%s" not defined in [acl.groups]\n' % group)
     # If no users found in group definition, get users from OS-level group
     try:
         return util.groupmembers(group)
     except KeyError:
         raise error.Abort(_("group '%s' is undefined") % group)
 
 def _usermatch(ui, user, usersorgroups):
 
     if usersorgroups == '*':
         return True
 
     for ug in usersorgroups.replace(',', ' ').split():
 
         if ug.startswith('!'):
             # Test for excluded user or group. Format:
             # if ug is a user  name: !username
             # if ug is a group name: !@groupname
             ug = ug[1:]
             if not ug.startswith('@') and user != ug \
                 or ug.startswith('@') and user not in _getusers(ui, ug[1:]):
                 return True
 
         # Test for user or group. Format:
         # if ug is a user  name: username
         # if ug is a group name: @groupname
         elif user == ug \
              or ug.startswith('@') and user in _getusers(ui, ug[1:]):
             return True
 
     return False
 
 def buildmatch(ui, repo, user, key):
     '''return tuple of (match function, list enabled).'''
     if not ui.has_section(key):
         ui.debug('acl: %s not enabled\n' % key)
         return None
 
     pats = [pat for pat, users in ui.configitems(key)
             if _usermatch(ui, user, users)]
     ui.debug('acl: %s enabled, %d entries for user %s\n' %
              (key, len(pats), user))
 
     # Branch-based ACL
     if not repo:
         if pats:
             # If there's an asterisk (meaning "any branch"), always return True;
             # Otherwise, test if b is in pats
             if '*' in pats:
                 return util.always
             return lambda b: b in pats
         return util.never
 
     # Path-based ACL
     if pats:
         return match.match(repo.root, '', pats)
     return util.never
 
 def ensureenabled(ui):
     """make sure the extension is enabled when used as hook
 
     When acl is used through hooks, the extension is never formally loaded and
     enabled. This has some side effect, for example the config declaration is
     never loaded. This function ensure the extension is enabled when running
     hooks.
     """
     if 'acl' in ui._knownconfig:
         return
     ui.setconfig('extensions', 'acl', '', source='internal')
     extensions.loadall(ui, ['acl'])
 
 def hook(ui, repo, hooktype, node=None, source=None, **kwargs):
 
     ensureenabled(ui)
 
     if hooktype not in ['pretxnchangegroup', 'pretxncommit']:
         raise error.Abort(_('config error - hook type "%s" cannot stop '
                            'incoming changesets nor commits') % hooktype)
     if (hooktype == 'pretxnchangegroup' and
         source not in ui.configlist('acl', 'sources')):
         ui.debug('acl: changes have source "%s" - skipping\n' % source)
         return
 
     user = None
     if source == 'serve' and r'url' in kwargs:
         url = kwargs[r'url'].split(':')
         if url[0] == 'remote' and url[1].startswith('http'):
             user = urlreq.unquote(url[3])
 
     if user is None:
-        user = util.getuser()
+        user = procutil.getuser()
 
     ui.debug('acl: checking access for user "%s"\n' % user)
 
     # deprecated config: acl.config
     cfg = ui.config('acl', 'config')
     if cfg:
         ui.readconfig(cfg, sections=['acl.groups', 'acl.allow.branches',
             'acl.deny.branches', 'acl.allow', 'acl.deny'])
 
     allowbranches = buildmatch(ui, None, user, 'acl.allow.branches')
     denybranches = buildmatch(ui, None, user, 'acl.deny.branches')
     allow = buildmatch(ui, repo, user, 'acl.allow')
     deny = buildmatch(ui, repo, user, 'acl.deny')
 
     for rev in xrange(repo[node].rev(), len(repo)):
         ctx = repo[rev]
         branch = ctx.branch()
         if denybranches and denybranches(branch):
             raise error.Abort(_('acl: user "%s" denied on branch "%s"'
                                ' (changeset "%s")')
                                % (user, branch, ctx))
         if allowbranches and not allowbranches(branch):
             raise error.Abort(_('acl: user "%s" not allowed on branch "%s"'
                                ' (changeset "%s")')
                                % (user, branch, ctx))
         ui.debug('acl: branch access granted: "%s" on branch "%s"\n'
         % (ctx, branch))
 
         for f in ctx.files():
             if deny and deny(f):
                 raise error.Abort(_('acl: user "%s" denied on "%s"'
                 ' (changeset "%s")') % (user, f, ctx))
             if allow and not allow(f):
                 raise error.Abort(_('acl: user "%s" not allowed on "%s"'
                 ' (changeset "%s")') % (user, f, ctx))
         ui.debug('acl: path access granted: "%s"\n' % ctx)

hgext/blackbox.py

@@ -1,251 +1,254
 # blackbox.py - log repository events to a file for post-mortem debugging
 #
 # Copyright 2010 Nicolas Dumazet
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """log repository events to a blackbox for debugging
 
 Logs event information to .hg/blackbox.log to help debug and diagnose problems.
 The events that get logged can be configured via the blackbox.track config key.
 
 Examples::
 
   [blackbox]
   track = *
   # dirty is *EXPENSIVE* (slow);
   # each log entry indicates `+` if the repository is dirty, like :hg:`id`.
   dirty = True
   # record the source of log messages
   logsource = True
 
   [blackbox]
   track = command, commandfinish, commandexception, exthook, pythonhook
 
   [blackbox]
   track = incoming
 
   [blackbox]
   # limit the size of a log file
   maxsize = 1.5 MB
   # rotate up to N log files when the current one gets too big
   maxfiles = 3
 
 """
 
 from __future__ import absolute_import
 
 import errno
 import re
 
 from mercurial.i18n import _
 from mercurial.node import hex
 
 from mercurial import (
     encoding,
     registrar,
     ui as uimod,
     util,
 )
-from mercurial.utils import dateutil
+from mercurial.utils import (
+    dateutil,
+    procutil,
+)
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('blackbox', 'dirty',
     default=False,
 )
 configitem('blackbox', 'maxsize',
     default='1 MB',
 )
 configitem('blackbox', 'logsource',
     default=False,
 )
 configitem('blackbox', 'maxfiles',
     default=7,
 )
 configitem('blackbox', 'track',
     default=lambda: ['*'],
 )
 
 lastui = None
 
 def _openlogfile(ui, vfs):
     def rotate(oldpath, newpath):
         try:
             vfs.unlink(newpath)
         except OSError as err:
             if err.errno != errno.ENOENT:
                 ui.debug("warning: cannot remove '%s': %s\n" %
                          (newpath, err.strerror))
         try:
             if newpath:
                 vfs.rename(oldpath, newpath)
         except OSError as err:
             if err.errno != errno.ENOENT:
                 ui.debug("warning: cannot rename '%s' to '%s': %s\n" %
                          (newpath, oldpath, err.strerror))
 
     maxsize = ui.configbytes('blackbox', 'maxsize')
     name = 'blackbox.log'
     if maxsize > 0:
         try:
             st = vfs.stat(name)
         except OSError:
             pass
         else:
             if st.st_size >= maxsize:
                 path = vfs.join(name)
                 maxfiles = ui.configint('blackbox', 'maxfiles')
                 for i in xrange(maxfiles - 1, 1, -1):
                     rotate(oldpath='%s.%d' % (path, i - 1),
                            newpath='%s.%d' % (path, i))
                 rotate(oldpath=path,
                        newpath=maxfiles > 0 and path + '.1')
     return vfs(name, 'a')
 
 def wrapui(ui):
     class blackboxui(ui.__class__):
         @property
         def _bbvfs(self):
             vfs = None
             repo = getattr(self, '_bbrepo', None)
             if repo:
                 vfs = repo.vfs
                 if not vfs.isdir('.'):
                     vfs = None
             return vfs
 
         @util.propertycache
         def track(self):
             return self.configlist('blackbox', 'track')
 
         def debug(self, *msg, **opts):
             super(blackboxui, self).debug(*msg, **opts)
             if self.debugflag:
                 self.log('debug', '%s', ''.join(msg))
 
         def log(self, event, *msg, **opts):
             global lastui
             super(blackboxui, self).log(event, *msg, **opts)
 
             if not '*' in self.track and not event in self.track:
                 return
 
             if self._bbvfs:
                 ui = self
             else:
                 # certain ui instances exist outside the context of
                 # a repo, so just default to the last blackbox that
                 # was seen.
                 ui = lastui
 
             if not ui:
                 return
             vfs = ui._bbvfs
             if not vfs:
                 return
 
             repo = getattr(ui, '_bbrepo', None)
             if not lastui or repo:
                 lastui = ui
             if getattr(ui, '_bbinlog', False):
                 # recursion and failure guard
                 return
             ui._bbinlog = True
             default = self.configdate('devel', 'default-date')
             date = dateutil.datestr(default, '%Y/%m/%d %H:%M:%S')
-            user = util.getuser()
-            pid = '%d' % util.getpid()
+            user = procutil.getuser()
+            pid = '%d' % procutil.getpid()
             formattedmsg = msg[0] % msg[1:]
             rev = '(unknown)'
             changed = ''
             if repo:
                 ctx = repo[None]
                 parents = ctx.parents()
                 rev = ('+'.join([hex(p.node()) for p in parents]))
                 if (ui.configbool('blackbox', 'dirty') and
                     ctx.dirty(missing=True, merge=False, branch=False)):
                     changed = '+'
             if ui.configbool('blackbox', 'logsource'):
                 src = ' [%s]' % event
             else:
                 src = ''
             try:
                 fmt = '%s %s @%s%s (%s)%s> %s'
                 args = (date, user, rev, changed, pid, src, formattedmsg)
                 with _openlogfile(ui, vfs) as fp:
                     fp.write(fmt % args)
             except (IOError, OSError) as err:
                 self.debug('warning: cannot write to blackbox.log: %s\n' %
                            encoding.strtolocal(err.strerror))
                 # do not restore _bbinlog intentionally to avoid failed
                 # logging again
             else:
                 ui._bbinlog = False
 
         def setrepo(self, repo):
             self._bbrepo = repo
 
     ui.__class__ = blackboxui
     uimod.ui = blackboxui
 
 def uisetup(ui):
     wrapui(ui)
 
 def reposetup(ui, repo):
     # During 'hg pull' a httppeer repo is created to represent the remote repo.
     # It doesn't have a .hg directory to put a blackbox in, so we don't do
     # the blackbox setup for it.
     if not repo.local():
         return
 
     if util.safehasattr(ui, 'setrepo'):
         ui.setrepo(repo)
 
         # Set lastui even if ui.log is not called. This gives blackbox a
         # fallback place to log.
         global lastui
         if lastui is None:
             lastui = ui
 
     repo._wlockfreeprefix.add('blackbox.log')
 
 @command('^blackbox',
     [('l', 'limit', 10, _('the number of events to show')),
     ],
     _('hg blackbox [OPTION]...'))
 def blackbox(ui, repo, *revs, **opts):
     '''view the recent repository events
     '''
 
     if not repo.vfs.exists('blackbox.log'):
         return
 
     limit = opts.get(r'limit')
     fp = repo.vfs('blackbox.log', 'r')
     lines = fp.read().split('\n')
 
     count = 0
     output = []
     for line in reversed(lines):
         if count >= limit:
             break
 
         # count the commands by matching lines like: 2013/01/23 19:13:36 root>
         if re.match('^\d{4}/\d{2}/\d{2} \d{2}:\d{2}:\d{2} .*> .*', line):
             count += 1
         output.append(line)
 
     ui.status('\n'.join(reversed(output)))

hgext/bugzilla.py

@@ -1,1128 +1,1129
 # bugzilla.py - bugzilla integration for mercurial
 #
 # Copyright 2006 Vadim Gelfer <[e-mail]>
 # Copyright 2011-4 Jim Hague <[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.
 
 '''hooks for integrating with the Bugzilla bug tracker
 
 This hook extension adds comments on bugs in Bugzilla when changesets
 that refer to bugs by Bugzilla ID are seen. The comment is formatted using
 the Mercurial template mechanism.
 
 The bug references can optionally include an update for Bugzilla of the
 hours spent working on the bug. Bugs can also be marked fixed.
 
 Four basic modes of access to Bugzilla are provided:
 
 1. Access via the Bugzilla REST-API. Requires bugzilla 5.0 or later.
 
 2. Access via the Bugzilla XMLRPC interface. Requires Bugzilla 3.4 or later.
 
 3. Check data via the Bugzilla XMLRPC interface and submit bug change
    via email to Bugzilla email interface. Requires Bugzilla 3.4 or later.
 
 4. Writing directly to the Bugzilla database. Only Bugzilla installations
    using MySQL are supported. Requires Python MySQLdb.
 
 Writing directly to the database is susceptible to schema changes, and
 relies on a Bugzilla contrib script to send out bug change
 notification emails. This script runs as the user running Mercurial,
 must be run on the host with the Bugzilla install, and requires
 permission to read Bugzilla configuration details and the necessary
 MySQL user and password to have full access rights to the Bugzilla
 database. For these reasons this access mode is now considered
 deprecated, and will not be updated for new Bugzilla versions going
 forward. Only adding comments is supported in this access mode.
 
 Access via XMLRPC needs a Bugzilla username and password to be specified
 in the configuration. Comments are added under that username. Since the
 configuration must be readable by all Mercurial users, it is recommended
 that the rights of that user are restricted in Bugzilla to the minimum
 necessary to add comments. Marking bugs fixed requires Bugzilla 4.0 and later.
 
 Access via XMLRPC/email uses XMLRPC to query Bugzilla, but sends
 email to the Bugzilla email interface to submit comments to bugs.
 The From: address in the email is set to the email address of the Mercurial
 user, so the comment appears to come from the Mercurial user. In the event
 that the Mercurial user email is not recognized by Bugzilla as a Bugzilla
 user, the email associated with the Bugzilla username used to log into
 Bugzilla is used instead as the source of the comment. Marking bugs fixed
 works on all supported Bugzilla versions.
 
 Access via the REST-API needs either a Bugzilla username and password
 or an apikey specified in the configuration. Comments are made under
 the given username or the user associated with the apikey in Bugzilla.
 
 Configuration items common to all access modes:
 
 bugzilla.version
   The access type to use. Values recognized are:
 
   :``restapi``:      Bugzilla REST-API, Bugzilla 5.0 and later.
   :``xmlrpc``:       Bugzilla XMLRPC interface.
   :``xmlrpc+email``: Bugzilla XMLRPC and email interfaces.
   :``3.0``:          MySQL access, Bugzilla 3.0 and later.
   :``2.18``:         MySQL access, Bugzilla 2.18 and up to but not
                      including 3.0.
   :``2.16``:         MySQL access, Bugzilla 2.16 and up to but not
                      including 2.18.
 
 bugzilla.regexp
   Regular expression to match bug IDs for update in changeset commit message.
   It must contain one "()" named group ``<ids>`` containing the bug
   IDs separated by non-digit characters. It may also contain
   a named group ``<hours>`` with a floating-point number giving the
   hours worked on the bug. If no named groups are present, the first
   "()" group is assumed to contain the bug IDs, and work time is not
   updated. The default expression matches ``Bug 1234``, ``Bug no. 1234``,
   ``Bug number 1234``, ``Bugs 1234,5678``, ``Bug 1234 and 5678`` and
   variations thereof, followed by an hours number prefixed by ``h`` or
   ``hours``, e.g. ``hours 1.5``. Matching is case insensitive.
 
 bugzilla.fixregexp
   Regular expression to match bug IDs for marking fixed in changeset
   commit message. This must contain a "()" named group ``<ids>` containing
   the bug IDs separated by non-digit characters. It may also contain
   a named group ``<hours>`` with a floating-point number giving the
   hours worked on the bug. If no named groups are present, the first
   "()" group is assumed to contain the bug IDs, and work time is not
   updated. The default expression matches ``Fixes 1234``, ``Fixes bug 1234``,
   ``Fixes bugs 1234,5678``, ``Fixes 1234 and 5678`` and
   variations thereof, followed by an hours number prefixed by ``h`` or
   ``hours``, e.g. ``hours 1.5``. Matching is case insensitive.
 
 bugzilla.fixstatus
   The status to set a bug to when marking fixed. Default ``RESOLVED``.
 
 bugzilla.fixresolution
   The resolution to set a bug to when marking fixed. Default ``FIXED``.
 
 bugzilla.style
   The style file to use when formatting comments.
 
 bugzilla.template
   Template to use when formatting comments. Overrides style if
   specified. In addition to the usual Mercurial keywords, the
   extension specifies:
 
   :``{bug}``:     The Bugzilla bug ID.
   :``{root}``:    The full pathname of the Mercurial repository.
   :``{webroot}``: Stripped pathname of the Mercurial repository.
   :``{hgweb}``:   Base URL for browsing Mercurial repositories.
 
   Default ``changeset {node|short} in repo {root} refers to bug
   {bug}.\\ndetails:\\n\\t{desc|tabindent}``
 
 bugzilla.strip
   The number of path separator characters to strip from the front of
   the Mercurial repository path (``{root}`` in templates) to produce
   ``{webroot}``. For example, a repository with ``{root}``
   ``/var/local/my-project`` with a strip of 2 gives a value for
   ``{webroot}`` of ``my-project``. Default 0.
 
 web.baseurl
   Base URL for browsing Mercurial repositories. Referenced from
   templates as ``{hgweb}``.
 
 Configuration items common to XMLRPC+email and MySQL access modes:
 
 bugzilla.usermap
   Path of file containing Mercurial committer email to Bugzilla user email
   mappings. If specified, the file should contain one mapping per
   line::
 
     committer = Bugzilla user
 
   See also the ``[usermap]`` section.
 
 The ``[usermap]`` section is used to specify mappings of Mercurial
 committer email to Bugzilla user email. See also ``bugzilla.usermap``.
 Contains entries of the form ``committer = Bugzilla user``.
 
 XMLRPC and REST-API access mode configuration:
 
 bugzilla.bzurl
   The base URL for the Bugzilla installation.
   Default ``http://localhost/bugzilla``.
 
 bugzilla.user
   The username to use to log into Bugzilla via XMLRPC. Default
   ``bugs``.
 
 bugzilla.password
   The password for Bugzilla login.
 
 REST-API access mode uses the options listed above as well as:
 
 bugzilla.apikey
   An apikey generated on the Bugzilla instance for api access.
   Using an apikey removes the need to store the user and password
   options.
 
 XMLRPC+email access mode uses the XMLRPC access mode configuration items,
 and also:
 
 bugzilla.bzemail
   The Bugzilla email address.
 
 In addition, the Mercurial email settings must be configured. See the
 documentation in hgrc(5), sections ``[email]`` and ``[smtp]``.
 
 MySQL access mode configuration:
 
 bugzilla.host
   Hostname of the MySQL server holding the Bugzilla database.
   Default ``localhost``.
 
 bugzilla.db
   Name of the Bugzilla database in MySQL. Default ``bugs``.
 
 bugzilla.user
   Username to use to access MySQL server. Default ``bugs``.
 
 bugzilla.password
   Password to use to access MySQL server.
 
 bugzilla.timeout
   Database connection timeout (seconds). Default 5.
 
 bugzilla.bzuser
   Fallback Bugzilla user name to record comments with, if changeset
   committer cannot be found as a Bugzilla user.
 
 bugzilla.bzdir
    Bugzilla install directory. Used by default notify. Default
    ``/var/www/html/bugzilla``.
 
 bugzilla.notify
   The command to run to get Bugzilla to send bug change notification
   emails. Substitutes from a map with 3 keys, ``bzdir``, ``id`` (bug
   id) and ``user`` (committer bugzilla email). Default depends on
   version; from 2.18 it is "cd %(bzdir)s && perl -T
   contrib/sendbugmail.pl %(id)s %(user)s".
 
 Activating the extension::
 
     [extensions]
     bugzilla =
 
     [hooks]
     # run bugzilla hook on every change pulled or pushed in here
     incoming.bugzilla = python:hgext.bugzilla.hook
 
 Example configurations:
 
 XMLRPC example configuration. This uses the Bugzilla at
 ``http://my-project.org/bugzilla``, logging in as user
 ``[e-mail]`` with password ``plugh``. It is used with a
 collection of Mercurial repositories in ``/var/local/hg/repos/``,
 with a web interface at ``http://my-project.org/hg``. ::
 
     [bugzilla]
     bzurl=http://my-project.org/bugzilla
     user=[e-mail]
     password=plugh
     version=xmlrpc
     template=Changeset {node|short} in {root|basename}.
              {hgweb}/{webroot}/rev/{node|short}\\n
              {desc}\\n
     strip=5
 
     [web]
     baseurl=http://my-project.org/hg
 
 XMLRPC+email example configuration. This uses the Bugzilla at
 ``http://my-project.org/bugzilla``, logging in as user
 ``[e-mail]`` with password ``plugh``. It is used with a
 collection of Mercurial repositories in ``/var/local/hg/repos/``,
 with a web interface at ``http://my-project.org/hg``. Bug comments
 are sent to the Bugzilla email address
 ``[e-mail]``. ::
 
     [bugzilla]
     bzurl=http://my-project.org/bugzilla
     user=[e-mail]
     password=plugh
     version=xmlrpc+email
     bzemail=[e-mail]
     template=Changeset {node|short} in {root|basename}.
              {hgweb}/{webroot}/rev/{node|short}\\n
              {desc}\\n
     strip=5
 
     [web]
     baseurl=http://my-project.org/hg
 
     [usermap]
     [e-mail]=[e-mail]
 
 MySQL example configuration. This has a local Bugzilla 3.2 installation
 in ``/opt/bugzilla-3.2``. The MySQL database is on ``localhost``,
 the Bugzilla database name is ``bugs`` and MySQL is
 accessed with MySQL username ``bugs`` password ``XYZZY``. It is used
 with a collection of Mercurial repositories in ``/var/local/hg/repos/``,
 with a web interface at ``http://my-project.org/hg``. ::
 
     [bugzilla]
     host=localhost
     password=XYZZY
     version=3.0
     bzuser=[e-mail]
     bzdir=/opt/bugzilla-3.2
     template=Changeset {node|short} in {root|basename}.
              {hgweb}/{webroot}/rev/{node|short}\\n
              {desc}\\n
     strip=5
 
     [web]
     baseurl=http://my-project.org/hg
 
     [usermap]
     [e-mail]=[e-mail]
 
 All the above add a comment to the Bugzilla bug record of the form::
 
     Changeset 3b16791d6642 in repository-name.
     http://my-project.org/hg/repository-name/rev/3b16791d6642
 
     Changeset commit comment. Bug 1234.
 '''
 
 from __future__ import absolute_import
 
 import json
 import re
 import time
 
 from mercurial.i18n import _
 from mercurial.node import short
 from mercurial import (
     error,
     logcmdutil,
     mail,
     registrar,
     url,
     util,
 )
 from mercurial.utils import (
+    procutil,
     stringutil,
 )
 
 xmlrpclib = util.xmlrpclib
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('bugzilla', 'apikey',
     default='',
 )
 configitem('bugzilla', 'bzdir',
     default='/var/www/html/bugzilla',
 )
 configitem('bugzilla', 'bzemail',
     default=None,
 )
 configitem('bugzilla', 'bzurl',
     default='http://localhost/bugzilla/',
 )
 configitem('bugzilla', 'bzuser',
     default=None,
 )
 configitem('bugzilla', 'db',
     default='bugs',
 )
 configitem('bugzilla', 'fixregexp',
     default=(r'fix(?:es)?\s*(?:bugs?\s*)?,?\s*'
              r'(?:nos?\.?|num(?:ber)?s?)?\s*'
              r'(?P<ids>(?:#?\d+\s*(?:,?\s*(?:and)?)?\s*)+)'
              r'\.?\s*(?:h(?:ours?)?\s*(?P<hours>\d*(?:\.\d+)?))?')
 )
 configitem('bugzilla', 'fixresolution',
     default='FIXED',
 )
 configitem('bugzilla', 'fixstatus',
     default='RESOLVED',
 )
 configitem('bugzilla', 'host',
     default='localhost',
 )
 configitem('bugzilla', 'notify',
     default=configitem.dynamicdefault,
 )
 configitem('bugzilla', 'password',
     default=None,
 )
 configitem('bugzilla', 'regexp',
     default=(r'bugs?\s*,?\s*(?:#|nos?\.?|num(?:ber)?s?)?\s*'
              r'(?P<ids>(?:\d+\s*(?:,?\s*(?:and)?)?\s*)+)'
              r'\.?\s*(?:h(?:ours?)?\s*(?P<hours>\d*(?:\.\d+)?))?')
 )
 configitem('bugzilla', 'strip',
     default=0,
 )
 configitem('bugzilla', 'style',
     default=None,
 )
 configitem('bugzilla', 'template',
     default=None,
 )
 configitem('bugzilla', 'timeout',
     default=5,
 )
 configitem('bugzilla', 'user',
     default='bugs',
 )
 configitem('bugzilla', 'usermap',
     default=None,
 )
 configitem('bugzilla', 'version',
     default=None,
 )
 
 class bzaccess(object):
     '''Base class for access to Bugzilla.'''
 
     def __init__(self, ui):
         self.ui = ui
         usermap = self.ui.config('bugzilla', 'usermap')
         if usermap:
             self.ui.readconfig(usermap, sections=['usermap'])
 
     def map_committer(self, user):
         '''map name of committer to Bugzilla user name.'''
         for committer, bzuser in self.ui.configitems('usermap'):
             if committer.lower() == user.lower():
                 return bzuser
         return user
 
     # Methods to be implemented by access classes.
     #
     # 'bugs' is a dict keyed on bug id, where values are a dict holding
     # updates to bug state. Recognized dict keys are:
     #
     # 'hours': Value, float containing work hours to be updated.
     # 'fix':   If key present, bug is to be marked fixed. Value ignored.
 
     def filter_real_bug_ids(self, bugs):
         '''remove bug IDs that do not exist in Bugzilla from bugs.'''
 
     def filter_cset_known_bug_ids(self, node, bugs):
         '''remove bug IDs where node occurs in comment text from bugs.'''
 
     def updatebug(self, bugid, newstate, text, committer):
         '''update the specified bug. Add comment text and set new states.
 
         If possible add the comment as being from the committer of
         the changeset. Otherwise use the default Bugzilla user.
         '''
 
     def notify(self, bugs, committer):
         '''Force sending of Bugzilla notification emails.
 
         Only required if the access method does not trigger notification
         emails automatically.
         '''
 
 # Bugzilla via direct access to MySQL database.
 class bzmysql(bzaccess):
     '''Support for direct MySQL access to Bugzilla.
 
     The earliest Bugzilla version this is tested with is version 2.16.
 
     If your Bugzilla is version 3.4 or above, you are strongly
     recommended to use the XMLRPC access method instead.
     '''
 
     @staticmethod
     def sql_buglist(ids):
         '''return SQL-friendly list of bug ids'''
         return '(' + ','.join(map(str, ids)) + ')'
 
     _MySQLdb = None
 
     def __init__(self, ui):
         try:
             import MySQLdb as mysql
             bzmysql._MySQLdb = mysql
         except ImportError as err:
             raise error.Abort(_('python mysql support not available: %s') % err)
 
         bzaccess.__init__(self, ui)
 
         host = self.ui.config('bugzilla', 'host')
         user = self.ui.config('bugzilla', 'user')
         passwd = self.ui.config('bugzilla', 'password')
         db = self.ui.config('bugzilla', 'db')
         timeout = int(self.ui.config('bugzilla', 'timeout'))
         self.ui.note(_('connecting to %s:%s as %s, password %s\n') %
                      (host, db, user, '*' * len(passwd)))
         self.conn = bzmysql._MySQLdb.connect(host=host,
                                                    user=user, passwd=passwd,
                                                    db=db,
                                                    connect_timeout=timeout)
         self.cursor = self.conn.cursor()
         self.longdesc_id = self.get_longdesc_id()
         self.user_ids = {}
         self.default_notify = "cd %(bzdir)s && ./processmail %(id)s %(user)s"
 
     def run(self, *args, **kwargs):
         '''run a query.'''
         self.ui.note(_('query: %s %s\n') % (args, kwargs))
         try:
             self.cursor.execute(*args, **kwargs)
         except bzmysql._MySQLdb.MySQLError:
             self.ui.note(_('failed query: %s %s\n') % (args, kwargs))
             raise
 
     def get_longdesc_id(self):
         '''get identity of longdesc field'''
         self.run('select fieldid from fielddefs where name = "longdesc"')
         ids = self.cursor.fetchall()
         if len(ids) != 1:
             raise error.Abort(_('unknown database schema'))
         return ids[0][0]
 
     def filter_real_bug_ids(self, bugs):
         '''filter not-existing bugs from set.'''
         self.run('select bug_id from bugs where bug_id in %s' %
                  bzmysql.sql_buglist(bugs.keys()))
         existing = [id for (id,) in self.cursor.fetchall()]
         for id in bugs.keys():
             if id not in existing:
                 self.ui.status(_('bug %d does not exist\n') % id)
                 del bugs[id]
 
     def filter_cset_known_bug_ids(self, node, bugs):
         '''filter bug ids that already refer to this changeset from set.'''
         self.run('''select bug_id from longdescs where
                     bug_id in %s and thetext like "%%%s%%"''' %
                  (bzmysql.sql_buglist(bugs.keys()), short(node)))
         for (id,) in self.cursor.fetchall():
             self.ui.status(_('bug %d already knows about changeset %s\n') %
                            (id, short(node)))
             del bugs[id]
 
     def notify(self, bugs, committer):
         '''tell bugzilla to send mail.'''
         self.ui.status(_('telling bugzilla to send mail:\n'))
         (user, userid) = self.get_bugzilla_user(committer)
         for id in bugs.keys():
             self.ui.status(_('  bug %s\n') % id)
             cmdfmt = self.ui.config('bugzilla', 'notify', self.default_notify)
             bzdir = self.ui.config('bugzilla', 'bzdir')
             try:
                 # Backwards-compatible with old notify string, which
                 # took one string. This will throw with a new format
                 # string.
                 cmd = cmdfmt % id
             except TypeError:
                 cmd = cmdfmt % {'bzdir': bzdir, 'id': id, 'user': user}
             self.ui.note(_('running notify command %s\n') % cmd)
-            fp = util.popen('(%s) 2>&1' % cmd)
+            fp = procutil.popen('(%s) 2>&1' % cmd)
             out = fp.read()
             ret = fp.close()
             if ret:
                 self.ui.warn(out)
                 raise error.Abort(_('bugzilla notify command %s') %
-                                 util.explainexit(ret)[0])
+                                  procutil.explainexit(ret)[0])
         self.ui.status(_('done\n'))
 
     def get_user_id(self, user):
         '''look up numeric bugzilla user id.'''
         try:
             return self.user_ids[user]
         except KeyError:
             try:
                 userid = int(user)
             except ValueError:
                 self.ui.note(_('looking up user %s\n') % user)
                 self.run('''select userid from profiles
                             where login_name like %s''', user)
                 all = self.cursor.fetchall()
                 if len(all) != 1:
                     raise KeyError(user)
                 userid = int(all[0][0])
             self.user_ids[user] = userid
             return userid
 
     def get_bugzilla_user(self, committer):
         '''See if committer is a registered bugzilla user. Return
         bugzilla username and userid if so. If not, return default
         bugzilla username and userid.'''
         user = self.map_committer(committer)
         try:
             userid = self.get_user_id(user)
         except KeyError:
             try:
                 defaultuser = self.ui.config('bugzilla', 'bzuser')
                 if not defaultuser:
                     raise error.Abort(_('cannot find bugzilla user id for %s') %
                                      user)
                 userid = self.get_user_id(defaultuser)
                 user = defaultuser
             except KeyError:
                 raise error.Abort(_('cannot find bugzilla user id for %s or %s')
                                  % (user, defaultuser))
         return (user, userid)
 
     def updatebug(self, bugid, newstate, text, committer):
         '''update bug state with comment text.
 
         Try adding comment as committer of changeset, otherwise as
         default bugzilla user.'''
         if len(newstate) > 0:
             self.ui.warn(_("Bugzilla/MySQL cannot update bug state\n"))
 
         (user, userid) = self.get_bugzilla_user(committer)
         now = time.strftime(r'%Y-%m-%d %H:%M:%S')
         self.run('''insert into longdescs
                     (bug_id, who, bug_when, thetext)
                     values (%s, %s, %s, %s)''',
                  (bugid, userid, now, text))
         self.run('''insert into bugs_activity (bug_id, who, bug_when, fieldid)
                     values (%s, %s, %s, %s)''',
                  (bugid, userid, now, self.longdesc_id))
         self.conn.commit()
 
 class bzmysql_2_18(bzmysql):
     '''support for bugzilla 2.18 series.'''
 
     def __init__(self, ui):
         bzmysql.__init__(self, ui)
         self.default_notify = \
             "cd %(bzdir)s && perl -T contrib/sendbugmail.pl %(id)s %(user)s"
 
 class bzmysql_3_0(bzmysql_2_18):
     '''support for bugzilla 3.0 series.'''
 
     def __init__(self, ui):
         bzmysql_2_18.__init__(self, ui)
 
     def get_longdesc_id(self):
         '''get identity of longdesc field'''
         self.run('select id from fielddefs where name = "longdesc"')
         ids = self.cursor.fetchall()
         if len(ids) != 1:
             raise error.Abort(_('unknown database schema'))
         return ids[0][0]
 
 # Bugzilla via XMLRPC interface.
 
 class cookietransportrequest(object):
     """A Transport request method that retains cookies over its lifetime.
 
     The regular xmlrpclib transports ignore cookies. Which causes
     a bit of a problem when you need a cookie-based login, as with
     the Bugzilla XMLRPC interface prior to 4.4.3.
 
     So this is a helper for defining a Transport which looks for
     cookies being set in responses and saves them to add to all future
     requests.
     """
 
     # Inspiration drawn from
     # http://blog.godson.in/2010/09/how-to-make-python-xmlrpclib-client.html
     # http://www.itkovian.net/base/transport-class-for-pythons-xml-rpc-lib/
 
     cookies = []
     def send_cookies(self, connection):
         if self.cookies:
             for cookie in self.cookies:
                 connection.putheader("Cookie", cookie)
 
     def request(self, host, handler, request_body, verbose=0):
         self.verbose = verbose
         self.accept_gzip_encoding = False
 
         # issue XML-RPC request
         h = self.make_connection(host)
         if verbose:
             h.set_debuglevel(1)
 
         self.send_request(h, handler, request_body)
         self.send_host(h, host)
         self.send_cookies(h)
         self.send_user_agent(h)
         self.send_content(h, request_body)
 
         # Deal with differences between Python 2.6 and 2.7.
         # In the former h is a HTTP(S). In the latter it's a
         # HTTP(S)Connection. Luckily, the 2.6 implementation of
         # HTTP(S) has an underlying HTTP(S)Connection, so extract
         # that and use it.
         try:
             response = h.getresponse()
         except AttributeError:
             response = h._conn.getresponse()
 
         # Add any cookie definitions to our list.
         for header in response.msg.getallmatchingheaders("Set-Cookie"):
             val = header.split(": ", 1)[1]
             cookie = val.split(";", 1)[0]
             self.cookies.append(cookie)
 
         if response.status != 200:
             raise xmlrpclib.ProtocolError(host + handler, response.status,
                                           response.reason, response.msg.headers)
 
         payload = response.read()
         parser, unmarshaller = self.getparser()
         parser.feed(payload)
         parser.close()
 
         return unmarshaller.close()
 
 # The explicit calls to the underlying xmlrpclib __init__() methods are
 # necessary. The xmlrpclib.Transport classes are old-style classes, and
 # it turns out their __init__() doesn't get called when doing multiple
 # inheritance with a new-style class.
 class cookietransport(cookietransportrequest, xmlrpclib.Transport):
     def __init__(self, use_datetime=0):
         if util.safehasattr(xmlrpclib.Transport, "__init__"):
             xmlrpclib.Transport.__init__(self, use_datetime)
 
 class cookiesafetransport(cookietransportrequest, xmlrpclib.SafeTransport):
     def __init__(self, use_datetime=0):
         if util.safehasattr(xmlrpclib.Transport, "__init__"):
             xmlrpclib.SafeTransport.__init__(self, use_datetime)
 
 class bzxmlrpc(bzaccess):
     """Support for access to Bugzilla via the Bugzilla XMLRPC API.
 
     Requires a minimum Bugzilla version 3.4.
     """
 
     def __init__(self, ui):
         bzaccess.__init__(self, ui)
 
         bzweb = self.ui.config('bugzilla', 'bzurl')
         bzweb = bzweb.rstrip("/") + "/xmlrpc.cgi"
 
         user = self.ui.config('bugzilla', 'user')
         passwd = self.ui.config('bugzilla', 'password')
 
         self.fixstatus = self.ui.config('bugzilla', 'fixstatus')
         self.fixresolution = self.ui.config('bugzilla', 'fixresolution')
 
         self.bzproxy = xmlrpclib.ServerProxy(bzweb, self.transport(bzweb))
         ver = self.bzproxy.Bugzilla.version()['version'].split('.')
         self.bzvermajor = int(ver[0])
         self.bzverminor = int(ver[1])
         login = self.bzproxy.User.login({'login': user, 'password': passwd,
                                          'restrict_login': True})
         self.bztoken = login.get('token', '')
 
     def transport(self, uri):
         if util.urlreq.urlparse(uri, "http")[0] == "https":
             return cookiesafetransport()
         else:
             return cookietransport()
 
     def get_bug_comments(self, id):
         """Return a string with all comment text for a bug."""
         c = self.bzproxy.Bug.comments({'ids': [id],
                                        'include_fields': ['text'],
                                        'token': self.bztoken})
         return ''.join([t['text'] for t in c['bugs'][str(id)]['comments']])
 
     def filter_real_bug_ids(self, bugs):
         probe = self.bzproxy.Bug.get({'ids': sorted(bugs.keys()),
                                       'include_fields': [],
                                       'permissive': True,
                                       'token': self.bztoken,
                                       })
         for badbug in probe['faults']:
             id = badbug['id']
             self.ui.status(_('bug %d does not exist\n') % id)
             del bugs[id]
 
     def filter_cset_known_bug_ids(self, node, bugs):
         for id in sorted(bugs.keys()):
             if self.get_bug_comments(id).find(short(node)) != -1:
                 self.ui.status(_('bug %d already knows about changeset %s\n') %
                                (id, short(node)))
                 del bugs[id]
 
     def updatebug(self, bugid, newstate, text, committer):
         args = {}
         if 'hours' in newstate:
             args['work_time'] = newstate['hours']
 
         if self.bzvermajor >= 4:
             args['ids'] = [bugid]
             args['comment'] = {'body' : text}
             if 'fix' in newstate:
                 args['status'] = self.fixstatus
                 args['resolution'] = self.fixresolution
             args['token'] = self.bztoken
             self.bzproxy.Bug.update(args)
         else:
             if 'fix' in newstate:
                 self.ui.warn(_("Bugzilla/XMLRPC needs Bugzilla 4.0 or later "
                                "to mark bugs fixed\n"))
             args['id'] = bugid
             args['comment'] = text
             self.bzproxy.Bug.add_comment(args)
 
 class bzxmlrpcemail(bzxmlrpc):
     """Read data from Bugzilla via XMLRPC, send updates via email.
 
     Advantages of sending updates via email:
       1. Comments can be added as any user, not just logged in user.
       2. Bug statuses or other fields not accessible via XMLRPC can
          potentially be updated.
 
     There is no XMLRPC function to change bug status before Bugzilla
     4.0, so bugs cannot be marked fixed via XMLRPC before Bugzilla 4.0.
     But bugs can be marked fixed via email from 3.4 onwards.
     """
 
     # The email interface changes subtly between 3.4 and 3.6. In 3.4,
     # in-email fields are specified as '@<fieldname> = <value>'. In
     # 3.6 this becomes '@<fieldname> <value>'. And fieldname @bug_id
     # in 3.4 becomes @id in 3.6. 3.6 and 4.0 both maintain backwards
     # compatibility, but rather than rely on this use the new format for
     # 4.0 onwards.
 
     def __init__(self, ui):
         bzxmlrpc.__init__(self, ui)
 
         self.bzemail = self.ui.config('bugzilla', 'bzemail')
         if not self.bzemail:
             raise error.Abort(_("configuration 'bzemail' missing"))
         mail.validateconfig(self.ui)
 
     def makecommandline(self, fieldname, value):
         if self.bzvermajor >= 4:
             return "@%s %s" % (fieldname, str(value))
         else:
             if fieldname == "id":
                 fieldname = "bug_id"
             return "@%s = %s" % (fieldname, str(value))
 
     def send_bug_modify_email(self, bugid, commands, comment, committer):
         '''send modification message to Bugzilla bug via email.
 
         The message format is documented in the Bugzilla email_in.pl
         specification. commands is a list of command lines, comment is the
         comment text.
 
         To stop users from crafting commit comments with
         Bugzilla commands, specify the bug ID via the message body, rather
         than the subject line, and leave a blank line after it.
         '''
         user = self.map_committer(committer)
         matches = self.bzproxy.User.get({'match': [user],
                                          'token': self.bztoken})
         if not matches['users']:
             user = self.ui.config('bugzilla', 'user')
             matches = self.bzproxy.User.get({'match': [user],
                                              'token': self.bztoken})
             if not matches['users']:
                 raise error.Abort(_("default bugzilla user %s email not found")
                                   % user)
         user = matches['users'][0]['email']
         commands.append(self.makecommandline("id", bugid))
 
         text = "\n".join(commands) + "\n\n" + comment
 
         _charsets = mail._charsets(self.ui)
         user = mail.addressencode(self.ui, user, _charsets)
         bzemail = mail.addressencode(self.ui, self.bzemail, _charsets)
         msg = mail.mimeencode(self.ui, text, _charsets)
         msg['From'] = user
         msg['To'] = bzemail
         msg['Subject'] = mail.headencode(self.ui, "Bug modification", _charsets)
         sendmail = mail.connect(self.ui)
         sendmail(user, bzemail, msg.as_string())
 
     def updatebug(self, bugid, newstate, text, committer):
         cmds = []
         if 'hours' in newstate:
             cmds.append(self.makecommandline("work_time", newstate['hours']))
         if 'fix' in newstate:
             cmds.append(self.makecommandline("bug_status", self.fixstatus))
             cmds.append(self.makecommandline("resolution", self.fixresolution))
         self.send_bug_modify_email(bugid, cmds, text, committer)
 
 class NotFound(LookupError):
     pass
 
 class bzrestapi(bzaccess):
     """Read and write bugzilla data using the REST API available since
     Bugzilla 5.0.
     """
     def __init__(self, ui):
         bzaccess.__init__(self, ui)
         bz = self.ui.config('bugzilla', 'bzurl')
         self.bzroot = '/'.join([bz, 'rest'])
         self.apikey = self.ui.config('bugzilla', 'apikey')
         self.user = self.ui.config('bugzilla', 'user')
         self.passwd = self.ui.config('bugzilla', 'password')
         self.fixstatus = self.ui.config('bugzilla', 'fixstatus')
         self.fixresolution = self.ui.config('bugzilla', 'fixresolution')
 
     def apiurl(self, targets, include_fields=None):
         url = '/'.join([self.bzroot] + [str(t) for t in targets])
         qv = {}
         if self.apikey:
             qv['api_key'] = self.apikey
         elif self.user and self.passwd:
             qv['login'] = self.user
             qv['password'] = self.passwd
         if include_fields:
             qv['include_fields'] = include_fields
         if qv:
             url = '%s?%s' % (url, util.urlreq.urlencode(qv))
         return url
 
     def _fetch(self, burl):
         try:
             resp = url.open(self.ui, burl)
             return json.loads(resp.read())
         except util.urlerr.httperror as inst:
             if inst.code == 401:
                 raise error.Abort(_('authorization failed'))
             if inst.code == 404:
                 raise NotFound()
             else:
                 raise
 
     def _submit(self, burl, data, method='POST'):
         data = json.dumps(data)
         if method == 'PUT':
             class putrequest(util.urlreq.request):
                 def get_method(self):
                     return 'PUT'
             request_type = putrequest
         else:
             request_type = util.urlreq.request
         req = request_type(burl, data,
                            {'Content-Type': 'application/json'})
         try:
             resp = url.opener(self.ui).open(req)
             return json.loads(resp.read())
         except util.urlerr.httperror as inst:
             if inst.code == 401:
                 raise error.Abort(_('authorization failed'))
             if inst.code == 404:
                 raise NotFound()
             else:
                 raise
 
     def filter_real_bug_ids(self, bugs):
         '''remove bug IDs that do not exist in Bugzilla from bugs.'''
         badbugs = set()
         for bugid in bugs:
             burl = self.apiurl(('bug', bugid), include_fields='status')
             try:
                 self._fetch(burl)
             except NotFound:
                 badbugs.add(bugid)
         for bugid in badbugs:
             del bugs[bugid]
 
     def filter_cset_known_bug_ids(self, node, bugs):
         '''remove bug IDs where node occurs in comment text from bugs.'''
         sn = short(node)
         for bugid in bugs.keys():
             burl = self.apiurl(('bug', bugid, 'comment'), include_fields='text')
             result = self._fetch(burl)
             comments = result['bugs'][str(bugid)]['comments']
             if any(sn in c['text'] for c in comments):
                 self.ui.status(_('bug %d already knows about changeset %s\n') %
                                (bugid, sn))
                 del bugs[bugid]
 
     def updatebug(self, bugid, newstate, text, committer):
         '''update the specified bug. Add comment text and set new states.
 
         If possible add the comment as being from the committer of
         the changeset. Otherwise use the default Bugzilla user.
         '''
         bugmod = {}
         if 'hours' in newstate:
             bugmod['work_time'] = newstate['hours']
         if 'fix' in newstate:
             bugmod['status'] = self.fixstatus
             bugmod['resolution'] = self.fixresolution
         if bugmod:
             # if we have to change the bugs state do it here
             bugmod['comment'] = {
                 'comment': text,
                 'is_private': False,
                 'is_markdown': False,
             }
             burl = self.apiurl(('bug', bugid))
             self._submit(burl, bugmod, method='PUT')
             self.ui.debug('updated bug %s\n' % bugid)
         else:
             burl = self.apiurl(('bug', bugid, 'comment'))
             self._submit(burl, {
                 'comment': text,
                 'is_private': False,
                 'is_markdown': False,
             })
             self.ui.debug('added comment to bug %s\n' % bugid)
 
     def notify(self, bugs, committer):
         '''Force sending of Bugzilla notification emails.
 
         Only required if the access method does not trigger notification
         emails automatically.
         '''
         pass
 
 class bugzilla(object):
     # supported versions of bugzilla. different versions have
     # different schemas.
     _versions = {
         '2.16': bzmysql,
         '2.18': bzmysql_2_18,
         '3.0':  bzmysql_3_0,
         'xmlrpc': bzxmlrpc,
         'xmlrpc+email': bzxmlrpcemail,
         'restapi': bzrestapi,
         }
 
     def __init__(self, ui, repo):
         self.ui = ui
         self.repo = repo
 
         bzversion = self.ui.config('bugzilla', 'version')
         try:
             bzclass = bugzilla._versions[bzversion]
         except KeyError:
             raise error.Abort(_('bugzilla version %s not supported') %
                              bzversion)
         self.bzdriver = bzclass(self.ui)
 
         self.bug_re = re.compile(
             self.ui.config('bugzilla', 'regexp'), re.IGNORECASE)
         self.fix_re = re.compile(
             self.ui.config('bugzilla', 'fixregexp'), re.IGNORECASE)
         self.split_re = re.compile(r'\D+')
 
     def find_bugs(self, ctx):
         '''return bugs dictionary created from commit comment.
 
         Extract bug info from changeset comments. Filter out any that are
         not known to Bugzilla, and any that already have a reference to
         the given changeset in their comments.
         '''
         start = 0
         hours = 0.0
         bugs = {}
         bugmatch = self.bug_re.search(ctx.description(), start)
         fixmatch = self.fix_re.search(ctx.description(), start)
         while True:
             bugattribs = {}
             if not bugmatch and not fixmatch:
                 break
             if not bugmatch:
                 m = fixmatch
             elif not fixmatch:
                 m = bugmatch
             else:
                 if bugmatch.start() < fixmatch.start():
                     m = bugmatch
                 else:
                     m = fixmatch
             start = m.end()
             if m is bugmatch:
                 bugmatch = self.bug_re.search(ctx.description(), start)
                 if 'fix' in bugattribs:
                     del bugattribs['fix']
             else:
                 fixmatch = self.fix_re.search(ctx.description(), start)
                 bugattribs['fix'] = None
 
             try:
                 ids = m.group('ids')
             except IndexError:
                 ids = m.group(1)
             try:
                 hours = float(m.group('hours'))
                 bugattribs['hours'] = hours
             except IndexError:
                 pass
             except TypeError:
                 pass
             except ValueError:
                 self.ui.status(_("%s: invalid hours\n") % m.group('hours'))
 
             for id in self.split_re.split(ids):
                 if not id:
                     continue
                 bugs[int(id)] = bugattribs
         if bugs:
             self.bzdriver.filter_real_bug_ids(bugs)
         if bugs:
             self.bzdriver.filter_cset_known_bug_ids(ctx.node(), bugs)
         return bugs
 
     def update(self, bugid, newstate, ctx):
         '''update bugzilla bug with reference to changeset.'''
 
         def webroot(root):
             '''strip leading prefix of repo root and turn into
             url-safe path.'''
             count = int(self.ui.config('bugzilla', 'strip'))
             root = util.pconvert(root)
             while count > 0:
                 c = root.find('/')
                 if c == -1:
                     break
                 root = root[c + 1:]
                 count -= 1
             return root
 
         mapfile = None
         tmpl = self.ui.config('bugzilla', 'template')
         if not tmpl:
             mapfile = self.ui.config('bugzilla', 'style')
         if not mapfile and not tmpl:
             tmpl = _('changeset {node|short} in repo {root} refers '
                      'to bug {bug}.\ndetails:\n\t{desc|tabindent}')
         spec = logcmdutil.templatespec(tmpl, mapfile)
         t = logcmdutil.changesettemplater(self.ui, self.repo, spec)
         self.ui.pushbuffer()
         t.show(ctx, changes=ctx.changeset(),
                bug=str(bugid),
                hgweb=self.ui.config('web', 'baseurl'),
                root=self.repo.root,
                webroot=webroot(self.repo.root))
         data = self.ui.popbuffer()
         self.bzdriver.updatebug(bugid, newstate, data,
                                 stringutil.email(ctx.user()))
 
     def notify(self, bugs, committer):
         '''ensure Bugzilla users are notified of bug change.'''
         self.bzdriver.notify(bugs, committer)
 
 def hook(ui, repo, hooktype, node=None, **kwargs):
     '''add comment to bugzilla for each changeset that refers to a
     bugzilla bug id. only add a comment once per bug, so same change
     seen multiple times does not fill bug with duplicate data.'''
     if node is None:
         raise error.Abort(_('hook type %s does not pass a changeset id') %
                          hooktype)
     try:
         bz = bugzilla(ui, repo)
         ctx = repo[node]
         bugs = bz.find_bugs(ctx)
         if bugs:
             for bug in bugs:
                 bz.update(bug, bugs[bug], ctx)
             bz.notify(bugs, stringutil.email(ctx.user()))
     except Exception as e:
         raise error.Abort(_('Bugzilla error: %s') % e)

hgext/convert/common.py

@@ -1,548 +1,551
 # common.py - common code for the convert extension
 #
 #  Copyright 2005-2009 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 or any later version.
 from __future__ import absolute_import
 
 import base64
 import datetime
 import errno
 import os
 import re
 import shlex
 import subprocess
 
 from mercurial.i18n import _
 from mercurial import (
     encoding,
     error,
     phases,
     pycompat,
     util,
 )
+from mercurial.utils import (
+    procutil,
+)
 
 pickle = util.pickle
 propertycache = util.propertycache
 
 def _encodeornone(d):
     if d is None:
         return
     return d.encode('latin1')
 
 class _shlexpy3proxy(object):
 
     def __init__(self, l):
         self._l = l
 
     def __iter__(self):
         return (_encodeornone(v) for v in self._l)
 
     def get_token(self):
         return _encodeornone(self._l.get_token())
 
     @property
     def infile(self):
         return self._l.infile or '<unknown>'
 
     @property
     def lineno(self):
         return self._l.lineno
 
 def shlexer(data=None, filepath=None, wordchars=None, whitespace=None):
     if data is None:
         if pycompat.ispy3:
             data = open(filepath, 'r', encoding=r'latin1')
         else:
             data = open(filepath, 'r')
     else:
         if filepath is not None:
             raise error.ProgrammingError(
                 'shlexer only accepts data or filepath, not both')
         if pycompat.ispy3:
             data = data.decode('latin1')
     l = shlex.shlex(data, infile=filepath, posix=True)
     if whitespace is not None:
         l.whitespace_split = True
         if pycompat.ispy3:
             l.whitespace += whitespace.decode('latin1')
         else:
             l.whitespace += whitespace
     if wordchars is not None:
         if pycompat.ispy3:
             l.wordchars += wordchars.decode('latin1')
         else:
             l.wordchars += wordchars
     if pycompat.ispy3:
         return _shlexpy3proxy(l)
     return l
 
 def encodeargs(args):
     def encodearg(s):
         lines = base64.encodestring(s)
         lines = [l.splitlines()[0] for l in lines]
         return ''.join(lines)
 
     s = pickle.dumps(args)
     return encodearg(s)
 
 def decodeargs(s):
     s = base64.decodestring(s)
     return pickle.loads(s)
 
 class MissingTool(Exception):
     pass
 
 def checktool(exe, name=None, abort=True):
     name = name or exe
-    if not util.findexe(exe):
+    if not procutil.findexe(exe):
         if abort:
             exc = error.Abort
         else:
             exc = MissingTool
         raise exc(_('cannot find required "%s" tool') % name)
 
 class NoRepo(Exception):
     pass
 
 SKIPREV = 'SKIP'
 
 class commit(object):
     def __init__(self, author, date, desc, parents, branch=None, rev=None,
                  extra=None, sortkey=None, saverev=True, phase=phases.draft,
                  optparents=None):
         self.author = author or 'unknown'
         self.date = date or '0 0'
         self.desc = desc
         self.parents = parents # will be converted and used as parents
         self.optparents = optparents or [] # will be used if already converted
         self.branch = branch
         self.rev = rev
         self.extra = extra or {}
         self.sortkey = sortkey
         self.saverev = saverev
         self.phase = phase
 
 class converter_source(object):
     """Conversion source interface"""
 
     def __init__(self, ui, repotype, path=None, revs=None):
         """Initialize conversion source (or raise NoRepo("message")
         exception if path is not a valid repository)"""
         self.ui = ui
         self.path = path
         self.revs = revs
         self.repotype = repotype
 
         self.encoding = 'utf-8'
 
     def checkhexformat(self, revstr, mapname='splicemap'):
         """ fails if revstr is not a 40 byte hex. mercurial and git both uses
             such format for their revision numbering
         """
         if not re.match(r'[0-9a-fA-F]{40,40}$', revstr):
             raise error.Abort(_('%s entry %s is not a valid revision'
                                ' identifier') % (mapname, revstr))
 
     def before(self):
         pass
 
     def after(self):
         pass
 
     def targetfilebelongstosource(self, targetfilename):
         """Returns true if the given targetfile belongs to the source repo. This
         is useful when only a subdirectory of the target belongs to the source
         repo."""
         # For normal full repo converts, this is always True.
         return True
 
     def setrevmap(self, revmap):
         """set the map of already-converted revisions"""
 
     def getheads(self):
         """Return a list of this repository's heads"""
         raise NotImplementedError
 
     def getfile(self, name, rev):
         """Return a pair (data, mode) where data is the file content
         as a string and mode one of '', 'x' or 'l'. rev is the
         identifier returned by a previous call to getchanges().
         Data is None if file is missing/deleted in rev.
         """
         raise NotImplementedError
 
     def getchanges(self, version, full):
         """Returns a tuple of (files, copies, cleanp2).
 
         files is a sorted list of (filename, id) tuples for all files
         changed between version and its first parent returned by
         getcommit(). If full, all files in that revision is returned.
         id is the source revision id of the file.
 
         copies is a dictionary of dest: source
 
         cleanp2 is the set of files filenames that are clean against p2.
         (Files that are clean against p1 are already not in files (unless
         full). This makes it possible to handle p2 clean files similarly.)
         """
         raise NotImplementedError
 
     def getcommit(self, version):
         """Return the commit object for version"""
         raise NotImplementedError
 
     def numcommits(self):
         """Return the number of commits in this source.
 
         If unknown, return None.
         """
         return None
 
     def gettags(self):
         """Return the tags as a dictionary of name: revision
 
         Tag names must be UTF-8 strings.
         """
         raise NotImplementedError
 
     def recode(self, s, encoding=None):
         if not encoding:
             encoding = self.encoding or 'utf-8'
 
         if isinstance(s, unicode):
             return s.encode("utf-8")
         try:
             return s.decode(encoding).encode("utf-8")
         except UnicodeError:
             try:
                 return s.decode("latin-1").encode("utf-8")
             except UnicodeError:
                 return s.decode(encoding, "replace").encode("utf-8")
 
     def getchangedfiles(self, rev, i):
         """Return the files changed by rev compared to parent[i].
 
         i is an index selecting one of the parents of rev.  The return
         value should be the list of files that are different in rev and
         this parent.
 
         If rev has no parents, i is None.
 
         This function is only needed to support --filemap
         """
         raise NotImplementedError
 
     def converted(self, rev, sinkrev):
         '''Notify the source that a revision has been converted.'''
 
     def hasnativeorder(self):
         """Return true if this source has a meaningful, native revision
         order. For instance, Mercurial revisions are store sequentially
         while there is no such global ordering with Darcs.
         """
         return False
 
     def hasnativeclose(self):
         """Return true if this source has ability to close branch.
         """
         return False
 
     def lookuprev(self, rev):
         """If rev is a meaningful revision reference in source, return
         the referenced identifier in the same format used by getcommit().
         return None otherwise.
         """
         return None
 
     def getbookmarks(self):
         """Return the bookmarks as a dictionary of name: revision
 
         Bookmark names are to be UTF-8 strings.
         """
         return {}
 
     def checkrevformat(self, revstr, mapname='splicemap'):
         """revstr is a string that describes a revision in the given
            source control system.  Return true if revstr has correct
            format.
         """
         return True
 
 class converter_sink(object):
     """Conversion sink (target) interface"""
 
     def __init__(self, ui, repotype, path):
         """Initialize conversion sink (or raise NoRepo("message")
         exception if path is not a valid repository)
 
         created is a list of paths to remove if a fatal error occurs
         later"""
         self.ui = ui
         self.path = path
         self.created = []
         self.repotype = repotype
 
     def revmapfile(self):
         """Path to a file that will contain lines
         source_rev_id sink_rev_id
         mapping equivalent revision identifiers for each system."""
         raise NotImplementedError
 
     def authorfile(self):
         """Path to a file that will contain lines
         srcauthor=dstauthor
         mapping equivalent authors identifiers for each system."""
         return None
 
     def putcommit(self, files, copies, parents, commit, source, revmap, full,
                   cleanp2):
         """Create a revision with all changed files listed in 'files'
         and having listed parents. 'commit' is a commit object
         containing at a minimum the author, date, and message for this
         changeset.  'files' is a list of (path, version) tuples,
         'copies' is a dictionary mapping destinations to sources,
         'source' is the source repository, and 'revmap' is a mapfile
         of source revisions to converted revisions. Only getfile() and
         lookuprev() should be called on 'source'. 'full' means that 'files'
         is complete and all other files should be removed.
         'cleanp2' is a set of the filenames that are unchanged from p2
         (only in the common merge case where there two parents).
 
         Note that the sink repository is not told to update itself to
         a particular revision (or even what that revision would be)
         before it receives the file data.
         """
         raise NotImplementedError
 
     def puttags(self, tags):
         """Put tags into sink.
 
         tags: {tagname: sink_rev_id, ...} where tagname is an UTF-8 string.
         Return a pair (tag_revision, tag_parent_revision), or (None, None)
         if nothing was changed.
         """
         raise NotImplementedError
 
     def setbranch(self, branch, pbranches):
         """Set the current branch name. Called before the first putcommit
         on the branch.
         branch: branch name for subsequent commits
         pbranches: (converted parent revision, parent branch) tuples"""
 
     def setfilemapmode(self, active):
         """Tell the destination that we're using a filemap
 
         Some converter_sources (svn in particular) can claim that a file
         was changed in a revision, even if there was no change.  This method
         tells the destination that we're using a filemap and that it should
         filter empty revisions.
         """
 
     def before(self):
         pass
 
     def after(self):
         pass
 
     def putbookmarks(self, bookmarks):
         """Put bookmarks into sink.
 
         bookmarks: {bookmarkname: sink_rev_id, ...}
         where bookmarkname is an UTF-8 string.
         """
 
     def hascommitfrommap(self, rev):
         """Return False if a rev mentioned in a filemap is known to not be
         present."""
         raise NotImplementedError
 
     def hascommitforsplicemap(self, rev):
         """This method is for the special needs for splicemap handling and not
         for general use. Returns True if the sink contains rev, aborts on some
         special cases."""
         raise NotImplementedError
 
 class commandline(object):
     def __init__(self, ui, command):
         self.ui = ui
         self.command = command
 
     def prerun(self):
         pass
 
     def postrun(self):
         pass
 
     def _cmdline(self, cmd, *args, **kwargs):
         kwargs = pycompat.byteskwargs(kwargs)
         cmdline = [self.command, cmd] + list(args)
         for k, v in kwargs.iteritems():
             if len(k) == 1:
                 cmdline.append('-' + k)
             else:
                 cmdline.append('--' + k.replace('_', '-'))
             try:
                 if len(k) == 1:
                     cmdline.append('' + v)
                 else:
                     cmdline[-1] += '=' + v
             except TypeError:
                 pass
-        cmdline = [util.shellquote(arg) for arg in cmdline]
+        cmdline = [procutil.shellquote(arg) for arg in cmdline]
         if not self.ui.debugflag:
             cmdline += ['2>', pycompat.bytestr(os.devnull)]
         cmdline = ' '.join(cmdline)
         return cmdline
 
     def _run(self, cmd, *args, **kwargs):
         def popen(cmdline):
             p = subprocess.Popen(cmdline, shell=True, bufsize=-1,
-                    close_fds=util.closefds,
-                    stdout=subprocess.PIPE)
+                                 close_fds=procutil.closefds,
+                                 stdout=subprocess.PIPE)
             return p
         return self._dorun(popen, cmd, *args, **kwargs)
 
     def _run2(self, cmd, *args, **kwargs):
-        return self._dorun(util.popen2, cmd, *args, **kwargs)
+        return self._dorun(procutil.popen2, cmd, *args, **kwargs)
 
     def _run3(self, cmd, *args, **kwargs):
-        return self._dorun(util.popen3, cmd, *args, **kwargs)
+        return self._dorun(procutil.popen3, cmd, *args, **kwargs)
 
     def _dorun(self, openfunc, cmd,  *args, **kwargs):
         cmdline = self._cmdline(cmd, *args, **kwargs)
         self.ui.debug('running: %s\n' % (cmdline,))
         self.prerun()
         try:
             return openfunc(cmdline)
         finally:
             self.postrun()
 
     def run(self, cmd, *args, **kwargs):
         p = self._run(cmd, *args, **kwargs)
         output = p.communicate()[0]
         self.ui.debug(output)
         return output, p.returncode
 
     def runlines(self, cmd, *args, **kwargs):
         p = self._run(cmd, *args, **kwargs)
         output = p.stdout.readlines()
         p.wait()
         self.ui.debug(''.join(output))
         return output, p.returncode
 
     def checkexit(self, status, output=''):
         if status:
             if output:
                 self.ui.warn(_('%s error:\n') % self.command)
                 self.ui.warn(output)
-            msg = util.explainexit(status)[0]
+            msg = procutil.explainexit(status)[0]
             raise error.Abort('%s %s' % (self.command, msg))
 
     def run0(self, cmd, *args, **kwargs):
         output, status = self.run(cmd, *args, **kwargs)
         self.checkexit(status, output)
         return output
 
     def runlines0(self, cmd, *args, **kwargs):
         output, status = self.runlines(cmd, *args, **kwargs)
         self.checkexit(status, ''.join(output))
         return output
 
     @propertycache
     def argmax(self):
         # POSIX requires at least 4096 bytes for ARG_MAX
         argmax = 4096
         try:
             argmax = os.sysconf("SC_ARG_MAX")
         except (AttributeError, ValueError):
             pass
 
         # Windows shells impose their own limits on command line length,
         # down to 2047 bytes for cmd.exe under Windows NT/2k and 2500 bytes
         # for older 4nt.exe. See http://support.microsoft.com/kb/830473 for
         # details about cmd.exe limitations.
 
         # Since ARG_MAX is for command line _and_ environment, lower our limit
         # (and make happy Windows shells while doing this).
         return argmax // 2 - 1
 
     def _limit_arglist(self, arglist, cmd, *args, **kwargs):
         cmdlen = len(self._cmdline(cmd, *args, **kwargs))
         limit = self.argmax - cmdlen
         numbytes = 0
         fl = []
         for fn in arglist:
             b = len(fn) + 3
             if numbytes + b < limit or len(fl) == 0:
                 fl.append(fn)
                 numbytes += b
             else:
                 yield fl
                 fl = [fn]
                 numbytes = b
         if fl:
             yield fl
 
     def xargs(self, arglist, cmd, *args, **kwargs):
         for l in self._limit_arglist(arglist, cmd, *args, **kwargs):
             self.run0(cmd, *(list(args) + l), **kwargs)
 
 class mapfile(dict):
     def __init__(self, ui, path):
         super(mapfile, self).__init__()
         self.ui = ui
         self.path = path
         self.fp = None
         self.order = []
         self._read()
 
     def _read(self):
         if not self.path:
             return
         try:
             fp = open(self.path, 'rb')
         except IOError as err:
             if err.errno != errno.ENOENT:
                 raise
             return
         for i, line in enumerate(util.iterfile(fp)):
             line = line.splitlines()[0].rstrip()
             if not line:
                 # Ignore blank lines
                 continue
             try:
                 key, value = line.rsplit(' ', 1)
             except ValueError:
                 raise error.Abort(
                     _('syntax error in %s(%d): key/value pair expected')
                     % (self.path, i + 1))
             if key not in self:
                 self.order.append(key)
             super(mapfile, self).__setitem__(key, value)
         fp.close()
 
     def __setitem__(self, key, value):
         if self.fp is None:
             try:
                 self.fp = open(self.path, 'ab')
             except IOError as err:
                 raise error.Abort(
                     _('could not open map file %r: %s') %
                     (self.path, encoding.strtolocal(err.strerror)))
         self.fp.write(util.tonativeeol('%s %s\n' % (key, value)))
         self.fp.flush()
         super(mapfile, self).__setitem__(key, value)
 
     def close(self):
         if self.fp:
             self.fp.close()
             self.fp = None
 
 def makedatetimestamp(t):
     """Like dateutil.makedate() but for time t instead of current time"""
     delta = (datetime.datetime.utcfromtimestamp(t) -
              datetime.datetime.fromtimestamp(t))
     tz = delta.days * 86400 + delta.seconds
     return t, tz

hgext/convert/cvs.py

@@ -1,298 +1,301
 # cvs.py: CVS conversion code inspired by hg-cvs-import and git-cvsimport
 #
 #  Copyright 2005-2009 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 or any later version.
 from __future__ import absolute_import
 
 import errno
 import os
 import re
 import socket
 
 from mercurial.i18n import _
 from mercurial import (
     encoding,
     error,
     pycompat,
     util,
 )
-from mercurial.utils import dateutil
+from mercurial.utils import (
+    dateutil,
+    procutil,
+)
 
 from . import (
     common,
     cvsps,
 )
 
 stringio = util.stringio
 checktool = common.checktool
 commit = common.commit
 converter_source = common.converter_source
 makedatetimestamp = common.makedatetimestamp
 NoRepo = common.NoRepo
 
 class convert_cvs(converter_source):
     def __init__(self, ui, repotype, path, revs=None):
         super(convert_cvs, self).__init__(ui, repotype, path, revs=revs)
 
         cvs = os.path.join(path, "CVS")
         if not os.path.exists(cvs):
             raise NoRepo(_("%s does not look like a CVS checkout") % path)
 
         checktool('cvs')
 
         self.changeset = None
         self.files = {}
         self.tags = {}
         self.lastbranch = {}
         self.socket = None
         self.cvsroot = open(os.path.join(cvs, "Root"), 'rb').read()[:-1]
         self.cvsrepo = open(os.path.join(cvs, "Repository"), 'rb').read()[:-1]
         self.encoding = encoding.encoding
 
         self._connect()
 
     def _parse(self):
         if self.changeset is not None:
             return
         self.changeset = {}
 
         maxrev = 0
         if self.revs:
             if len(self.revs) > 1:
                 raise error.Abort(_('cvs source does not support specifying '
                                    'multiple revs'))
             # TODO: handle tags
             try:
                 # patchset number?
                 maxrev = int(self.revs[0])
             except ValueError:
                 raise error.Abort(_('revision %s is not a patchset number')
                                  % self.revs[0])
 
         d = pycompat.getcwd()
         try:
             os.chdir(self.path)
             id = None
 
             cache = 'update'
             if not self.ui.configbool('convert', 'cvsps.cache'):
                 cache = None
             db = cvsps.createlog(self.ui, cache=cache)
             db = cvsps.createchangeset(self.ui, db,
                 fuzz=int(self.ui.config('convert', 'cvsps.fuzz')),
                 mergeto=self.ui.config('convert', 'cvsps.mergeto'),
                 mergefrom=self.ui.config('convert', 'cvsps.mergefrom'))
 
             for cs in db:
                 if maxrev and cs.id > maxrev:
                     break
                 id = str(cs.id)
                 cs.author = self.recode(cs.author)
                 self.lastbranch[cs.branch] = id
                 cs.comment = self.recode(cs.comment)
                 if self.ui.configbool('convert', 'localtimezone'):
                     cs.date = makedatetimestamp(cs.date[0])
                 date = dateutil.datestr(cs.date, '%Y-%m-%d %H:%M:%S %1%2')
                 self.tags.update(dict.fromkeys(cs.tags, id))
 
                 files = {}
                 for f in cs.entries:
                     files[f.file] = "%s%s" % ('.'.join([str(x)
                                                         for x in f.revision]),
                                               ['', '(DEAD)'][f.dead])
 
                 # add current commit to set
                 c = commit(author=cs.author, date=date,
                            parents=[str(p.id) for p in cs.parents],
                            desc=cs.comment, branch=cs.branch or '')
                 self.changeset[id] = c
                 self.files[id] = files
 
             self.heads = self.lastbranch.values()
         finally:
             os.chdir(d)
 
     def _connect(self):
         root = self.cvsroot
         conntype = None
         user, host = None, None
         cmd = ['cvs', 'server']
 
         self.ui.status(_("connecting to %s\n") % root)
 
         if root.startswith(":pserver:"):
             root = root[9:]
             m = re.match(r'(?:(.*?)(?::(.*?))?@)?([^:\/]*)(?::(\d*))?(.*)',
                          root)
             if m:
                 conntype = "pserver"
                 user, passw, serv, port, root = m.groups()
                 if not user:
                     user = "anonymous"
                 if not port:
                     port = 2401
                 else:
                     port = int(port)
                 format0 = ":pserver:%s@%s:%s" % (user, serv, root)
                 format1 = ":pserver:%s@%s:%d%s" % (user, serv, port, root)
 
                 if not passw:
                     passw = "A"
                     cvspass = os.path.expanduser("~/.cvspass")
                     try:
                         pf = open(cvspass, 'rb')
                         for line in pf.read().splitlines():
                             part1, part2 = line.split(' ', 1)
                             # /1 :pserver:[e-mail]:2401/cvsroot/foo
                             # Ah<Z
                             if part1 == '/1':
                                 part1, part2 = part2.split(' ', 1)
                                 format = format1
                             # :pserver:[e-mail]:/cvsroot/foo Ah<Z
                             else:
                                 format = format0
                             if part1 == format:
                                 passw = part2
                                 break
                         pf.close()
                     except IOError as inst:
                         if inst.errno != errno.ENOENT:
                             if not getattr(inst, 'filename', None):
                                 inst.filename = cvspass
                             raise
 
                 sck = socket.socket()
                 sck.connect((serv, port))
                 sck.send("\n".join(["BEGIN AUTH REQUEST", root, user, passw,
                                     "END AUTH REQUEST", ""]))
                 if sck.recv(128) != "I LOVE YOU\n":
                     raise error.Abort(_("CVS pserver authentication failed"))
 
                 self.writep = self.readp = sck.makefile('r+')
 
         if not conntype and root.startswith(":local:"):
             conntype = "local"
             root = root[7:]
 
         if not conntype:
             # :ext:user@host/home/user/path/to/cvsroot
             if root.startswith(":ext:"):
                 root = root[5:]
             m = re.match(br'(?:([^@:/]+)@)?([^:/]+):?(.*)', root)
             # Do not take Windows path "c:\foo\bar" for a connection strings
             if os.path.isdir(root) or not m:
                 conntype = "local"
             else:
                 conntype = "rsh"
                 user, host, root = m.group(1), m.group(2), m.group(3)
 
         if conntype != "pserver":
             if conntype == "rsh":
                 rsh = encoding.environ.get("CVS_RSH") or "ssh"
                 if user:
                     cmd = [rsh, '-l', user, host] + cmd
                 else:
                     cmd = [rsh, host] + cmd
 
             # popen2 does not support argument lists under Windows
-            cmd = [util.shellquote(arg) for arg in cmd]
-            cmd = util.quotecommand(' '.join(cmd))
-            self.writep, self.readp = util.popen2(cmd)
+            cmd = [procutil.shellquote(arg) for arg in cmd]
+            cmd = procutil.quotecommand(' '.join(cmd))
+            self.writep, self.readp = procutil.popen2(cmd)
 
         self.realroot = root
 
         self.writep.write("Root %s\n" % root)
         self.writep.write("Valid-responses ok error Valid-requests Mode"
                           " M Mbinary E Checked-in Created Updated"
                           " Merged Removed\n")
         self.writep.write("valid-requests\n")
         self.writep.flush()
         r = self.readp.readline()
         if not r.startswith("Valid-requests"):
             raise error.Abort(_('unexpected response from CVS server '
                                '(expected "Valid-requests", but got %r)')
                              % r)
         if "UseUnchanged" in r:
             self.writep.write("UseUnchanged\n")
             self.writep.flush()
             r = self.readp.readline()
 
     def getheads(self):
         self._parse()
         return self.heads
 
     def getfile(self, name, rev):
 
         def chunkedread(fp, count):
             # file-objects returned by socket.makefile() do not handle
             # large read() requests very well.
             chunksize = 65536
             output = stringio()
             while count > 0:
                 data = fp.read(min(count, chunksize))
                 if not data:
                     raise error.Abort(_("%d bytes missing from remote file")
                                      % count)
                 count -= len(data)
                 output.write(data)
             return output.getvalue()
 
         self._parse()
         if rev.endswith("(DEAD)"):
             return None, None
 
         args = ("-N -P -kk -r %s --" % rev).split()
         args.append(self.cvsrepo + '/' + name)
         for x in args:
             self.writep.write("Argument %s\n" % x)
         self.writep.write("Directory .\n%s\nco\n" % self.realroot)
         self.writep.flush()
 
         data = ""
         mode = None
         while True:
             line = self.readp.readline()
             if line.startswith("Created ") or line.startswith("Updated "):
                 self.readp.readline() # path
                 self.readp.readline() # entries
                 mode = self.readp.readline()[:-1]
                 count = int(self.readp.readline()[:-1])
                 data = chunkedread(self.readp, count)
             elif line.startswith(" "):
                 data += line[1:]
             elif line.startswith("M "):
                 pass
             elif line.startswith("Mbinary "):
                 count = int(self.readp.readline()[:-1])
                 data = chunkedread(self.readp, count)
             else:
                 if line == "ok\n":
                     if mode is None:
                         raise error.Abort(_('malformed response from CVS'))
                     return (data, "x" in mode and "x" or "")
                 elif line.startswith("E "):
                     self.ui.warn(_("cvs server: %s\n") % line[2:])
                 elif line.startswith("Remove"):
                     self.readp.readline()
                 else:
                     raise error.Abort(_("unknown CVS response: %s") % line)
 
     def getchanges(self, rev, full):
         if full:
             raise error.Abort(_("convert from cvs does not support --full"))
         self._parse()
         return sorted(self.files[rev].iteritems()), {}, set()
 
     def getcommit(self, rev):
         self._parse()
         return self.changeset[rev]
 
     def gettags(self):
         self._parse()
         return self.tags
 
     def getchangedfiles(self, rev, i):
         self._parse()
         return sorted(self.files[rev])

hgext/convert/cvsps.py

@@ -1,957 +1,958
 # Mercurial built-in replacement for cvsps.
 #
 # Copyright 2008, Frank Kingswood <[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 __future__ import absolute_import
 
 import os
 import re
 
 from mercurial.i18n import _
 from mercurial import (
     encoding,
     error,
     hook,
     pycompat,
     util,
 )
 from mercurial.utils import (
     dateutil,
+    procutil,
     stringutil,
 )
 
 pickle = util.pickle
 
 class logentry(object):
     '''Class logentry has the following attributes:
         .author    - author name as CVS knows it
         .branch    - name of branch this revision is on
         .branches  - revision tuple of branches starting at this revision
         .comment   - commit message
         .commitid  - CVS commitid or None
         .date      - the commit date as a (time, tz) tuple
         .dead      - true if file revision is dead
         .file      - Name of file
         .lines     - a tuple (+lines, -lines) or None
         .parent    - Previous revision of this entry
         .rcs       - name of file as returned from CVS
         .revision  - revision number as tuple
         .tags      - list of tags on the file
         .synthetic - is this a synthetic "file ... added on ..." revision?
         .mergepoint - the branch that has been merged from (if present in
                       rlog output) or None
         .branchpoints - the branches that start at the current entry or empty
     '''
     def __init__(self, **entries):
         self.synthetic = False
         self.__dict__.update(entries)
 
     def __repr__(self):
         items = ("%s=%r"%(k, self.__dict__[k]) for k in sorted(self.__dict__))
         return "%s(%s)"%(type(self).__name__, ", ".join(items))
 
 class logerror(Exception):
     pass
 
 def getrepopath(cvspath):
     """Return the repository path from a CVS path.
 
     >>> getrepopath(b'/foo/bar')
     '/foo/bar'
     >>> getrepopath(b'c:/foo/bar')
     '/foo/bar'
     >>> getrepopath(b':pserver:10/foo/bar')
     '/foo/bar'
     >>> getrepopath(b':pserver:10c:/foo/bar')
     '/foo/bar'
     >>> getrepopath(b':pserver:/foo/bar')
     '/foo/bar'
     >>> getrepopath(b':pserver:c:/foo/bar')
     '/foo/bar'
     >>> getrepopath(b':pserver:[e-mail]:/foo/bar')
     '/foo/bar'
     >>> getrepopath(b':pserver:[e-mail]:c:/foo/bar')
     '/foo/bar'
     >>> getrepopath(b'user@server/path/to/repository')
     '/path/to/repository'
     """
     # According to CVS manual, CVS paths are expressed like:
     # [:method:][[user][:password]@]hostname[:[port]]/path/to/repository
     #
     # CVSpath is splitted into parts and then position of the first occurrence
     # of the '/' char after the '@' is located. The solution is the rest of the
     # string after that '/' sign including it
 
     parts = cvspath.split(':')
     atposition = parts[-1].find('@')
     start = 0
 
     if atposition != -1:
         start = atposition
 
     repopath = parts[-1][parts[-1].find('/', start):]
     return repopath
 
 def createlog(ui, directory=None, root="", rlog=True, cache=None):
     '''Collect the CVS rlog'''
 
     # Because we store many duplicate commit log messages, reusing strings
     # saves a lot of memory and pickle storage space.
     _scache = {}
     def scache(s):
         "return a shared version of a string"
         return _scache.setdefault(s, s)
 
     ui.status(_('collecting CVS rlog\n'))
 
     log = []      # list of logentry objects containing the CVS state
 
     # patterns to match in CVS (r)log output, by state of use
     re_00 = re.compile('RCS file: (.+)$')
     re_01 = re.compile('cvs \\[r?log aborted\\]: (.+)$')
     re_02 = re.compile('cvs (r?log|server): (.+)\n$')
     re_03 = re.compile("(Cannot access.+CVSROOT)|"
                        "(can't create temporary directory.+)$")
     re_10 = re.compile('Working file: (.+)$')
     re_20 = re.compile('symbolic names:')
     re_30 = re.compile('\t(.+): ([\\d.]+)$')
     re_31 = re.compile('----------------------------$')
     re_32 = re.compile('======================================='
                        '======================================$')
     re_50 = re.compile('revision ([\\d.]+)(\s+locked by:\s+.+;)?$')
     re_60 = re.compile(r'date:\s+(.+);\s+author:\s+(.+);\s+state:\s+(.+?);'
                        r'(\s+lines:\s+(\+\d+)?\s+(-\d+)?;)?'
                        r'(\s+commitid:\s+([^;]+);)?'
                        r'(.*mergepoint:\s+([^;]+);)?')
     re_70 = re.compile('branches: (.+);$')
 
     file_added_re = re.compile(r'file [^/]+ was (initially )?added on branch')
 
     prefix = ''   # leading path to strip of what we get from CVS
 
     if directory is None:
         # Current working directory
 
         # Get the real directory in the repository
         try:
             prefix = open(os.path.join('CVS','Repository'), 'rb').read().strip()
             directory = prefix
             if prefix == ".":
                 prefix = ""
         except IOError:
             raise logerror(_('not a CVS sandbox'))
 
         if prefix and not prefix.endswith(pycompat.ossep):
             prefix += pycompat.ossep
 
         # Use the Root file in the sandbox, if it exists
         try:
             root = open(os.path.join('CVS','Root'), 'rb').read().strip()
         except IOError:
             pass
 
     if not root:
         root = encoding.environ.get('CVSROOT', '')
 
     # read log cache if one exists
     oldlog = []
     date = None
 
     if cache:
         cachedir = os.path.expanduser('~/.hg.cvsps')
         if not os.path.exists(cachedir):
             os.mkdir(cachedir)
 
         # The cvsps cache pickle needs a uniquified name, based on the
         # repository location. The address may have all sort of nasties
         # in it, slashes, colons and such. So here we take just the
         # alphanumeric characters, concatenated in a way that does not
         # mix up the various components, so that
         #    :pserver:user@server:/path
         # and
         #    /pserver/user/server/path
         # are mapped to different cache file names.
         cachefile = root.split(":") + [directory, "cache"]
         cachefile = ['-'.join(re.findall(br'\w+', s)) for s in cachefile if s]
         cachefile = os.path.join(cachedir,
                                  '.'.join([s for s in cachefile if s]))
 
     if cache == 'update':
         try:
             ui.note(_('reading cvs log cache %s\n') % cachefile)
             oldlog = pickle.load(open(cachefile, 'rb'))
             for e in oldlog:
                 if not (util.safehasattr(e, 'branchpoints') and
                         util.safehasattr(e, 'commitid') and
                         util.safehasattr(e, 'mergepoint')):
                     ui.status(_('ignoring old cache\n'))
                     oldlog = []
                     break
 
             ui.note(_('cache has %d log entries\n') % len(oldlog))
         except Exception as e:
             ui.note(_('error reading cache: %r\n') % e)
 
         if oldlog:
             date = oldlog[-1].date    # last commit date as a (time,tz) tuple
             date = dateutil.datestr(date, '%Y/%m/%d %H:%M:%S %1%2')
 
     # build the CVS commandline
     cmd = ['cvs', '-q']
     if root:
         cmd.append('-d%s' % root)
         p = util.normpath(getrepopath(root))
         if not p.endswith('/'):
             p += '/'
         if prefix:
             # looks like normpath replaces "" by "."
             prefix = p + util.normpath(prefix)
         else:
             prefix = p
     cmd.append(['log', 'rlog'][rlog])
     if date:
         # no space between option and date string
         cmd.append('-d>%s' % date)
     cmd.append(directory)
 
     # state machine begins here
     tags = {}     # dictionary of revisions on current file with their tags
     branchmap = {} # mapping between branch names and revision numbers
     rcsmap = {}
     state = 0
     store = False # set when a new record can be appended
 
-    cmd = [util.shellquote(arg) for arg in cmd]
+    cmd = [procutil.shellquote(arg) for arg in cmd]
     ui.note(_("running %s\n") % (' '.join(cmd)))
     ui.debug("prefix=%r directory=%r root=%r\n" % (prefix, directory, root))
 
-    pfp = util.popen(' '.join(cmd))
+    pfp = procutil.popen(' '.join(cmd))
     peek = pfp.readline()
     while True:
         line = peek
         if line == '':
             break
         peek = pfp.readline()
         if line.endswith('\n'):
             line = line[:-1]
         #ui.debug('state=%d line=%r\n' % (state, line))
 
         if state == 0:
             # initial state, consume input until we see 'RCS file'
             match = re_00.match(line)
             if match:
                 rcs = match.group(1)
                 tags = {}
                 if rlog:
                     filename = util.normpath(rcs[:-2])
                     if filename.startswith(prefix):
                         filename = filename[len(prefix):]
                     if filename.startswith('/'):
                         filename = filename[1:]
                     if filename.startswith('Attic/'):
                         filename = filename[6:]
                     else:
                         filename = filename.replace('/Attic/', '/')
                     state = 2
                     continue
                 state = 1
                 continue
             match = re_01.match(line)
             if match:
                 raise logerror(match.group(1))
             match = re_02.match(line)
             if match:
                 raise logerror(match.group(2))
             if re_03.match(line):
                 raise logerror(line)
 
         elif state == 1:
             # expect 'Working file' (only when using log instead of rlog)
             match = re_10.match(line)
             assert match, _('RCS file must be followed by working file')
             filename = util.normpath(match.group(1))
             state = 2
 
         elif state == 2:
             # expect 'symbolic names'
             if re_20.match(line):
                 branchmap = {}
                 state = 3
 
         elif state == 3:
             # read the symbolic names and store as tags
             match = re_30.match(line)
             if match:
                 rev = [int(x) for x in match.group(2).split('.')]
 
                 # Convert magic branch number to an odd-numbered one
                 revn = len(rev)
                 if revn > 3 and (revn % 2) == 0 and rev[-2] == 0:
                     rev = rev[:-2] + rev[-1:]
                 rev = tuple(rev)
 
                 if rev not in tags:
                     tags[rev] = []
                 tags[rev].append(match.group(1))
                 branchmap[match.group(1)] = match.group(2)
 
             elif re_31.match(line):
                 state = 5
             elif re_32.match(line):
                 state = 0
 
         elif state == 4:
             # expecting '------' separator before first revision
             if re_31.match(line):
                 state = 5
             else:
                 assert not re_32.match(line), _('must have at least '
                                                 'some revisions')
 
         elif state == 5:
             # expecting revision number and possibly (ignored) lock indication
             # we create the logentry here from values stored in states 0 to 4,
             # as this state is re-entered for subsequent revisions of a file.
             match = re_50.match(line)
             assert match, _('expected revision number')
             e = logentry(rcs=scache(rcs),
                          file=scache(filename),
                          revision=tuple([int(x) for x in
                                          match.group(1).split('.')]),
                          branches=[],
                          parent=None,
                          commitid=None,
                          mergepoint=None,
                          branchpoints=set())
 
             state = 6
 
         elif state == 6:
             # expecting date, author, state, lines changed
             match = re_60.match(line)
             assert match, _('revision must be followed by date line')
             d = match.group(1)
             if d[2] == '/':
                 # Y2K
                 d = '19' + d
 
             if len(d.split()) != 3:
                 # cvs log dates always in GMT
                 d = d + ' UTC'
             e.date = dateutil.parsedate(d, ['%y/%m/%d %H:%M:%S',
                                         '%Y/%m/%d %H:%M:%S',
                                         '%Y-%m-%d %H:%M:%S'])
             e.author = scache(match.group(2))
             e.dead = match.group(3).lower() == 'dead'
 
             if match.group(5):
                 if match.group(6):
                     e.lines = (int(match.group(5)), int(match.group(6)))
                 else:
                     e.lines = (int(match.group(5)), 0)
             elif match.group(6):
                 e.lines = (0, int(match.group(6)))
             else:
                 e.lines = None
 
             if match.group(7): # cvs 1.12 commitid
                 e.commitid = match.group(8)
 
             if match.group(9): # cvsnt mergepoint
                 myrev = match.group(10).split('.')
                 if len(myrev) == 2: # head
                     e.mergepoint = 'HEAD'
                 else:
                     myrev = '.'.join(myrev[:-2] + ['0', myrev[-2]])
                     branches = [b for b in branchmap if branchmap[b] == myrev]
                     assert len(branches) == 1, ('unknown branch: %s'
                                                 % e.mergepoint)
                     e.mergepoint = branches[0]
 
             e.comment = []
             state = 7
 
         elif state == 7:
             # read the revision numbers of branches that start at this revision
             # or store the commit log message otherwise
             m = re_70.match(line)
             if m:
                 e.branches = [tuple([int(y) for y in x.strip().split('.')])
                                 for x in m.group(1).split(';')]
                 state = 8
             elif re_31.match(line) and re_50.match(peek):
                 state = 5
                 store = True
             elif re_32.match(line):
                 state = 0
                 store = True
             else:
                 e.comment.append(line)
 
         elif state == 8:
             # store commit log message
             if re_31.match(line):
                 cpeek = peek
                 if cpeek.endswith('\n'):
                     cpeek = cpeek[:-1]
                 if re_50.match(cpeek):
                     state = 5
                     store = True
                 else:
                     e.comment.append(line)
             elif re_32.match(line):
                 state = 0
                 store = True
             else:
                 e.comment.append(line)
 
         # When a file is added on a branch B1, CVS creates a synthetic
         # dead trunk revision 1.1 so that the branch has a root.
         # Likewise, if you merge such a file to a later branch B2 (one
         # that already existed when the file was added on B1), CVS
         # creates a synthetic dead revision 1.1.x.1 on B2.  Don't drop
         # these revisions now, but mark them synthetic so
         # createchangeset() can take care of them.
         if (store and
               e.dead and
               e.revision[-1] == 1 and      # 1.1 or 1.1.x.1
               len(e.comment) == 1 and
               file_added_re.match(e.comment[0])):
             ui.debug('found synthetic revision in %s: %r\n'
                      % (e.rcs, e.comment[0]))
             e.synthetic = True
 
         if store:
             # clean up the results and save in the log.
             store = False
             e.tags = sorted([scache(x) for x in tags.get(e.revision, [])])
             e.comment = scache('\n'.join(e.comment))
 
             revn = len(e.revision)
             if revn > 3 and (revn % 2) == 0:
                 e.branch = tags.get(e.revision[:-1], [None])[0]
             else:
                 e.branch = None
 
             # find the branches starting from this revision
             branchpoints = set()
             for branch, revision in branchmap.iteritems():
                 revparts = tuple([int(i) for i in revision.split('.')])
                 if len(revparts) < 2: # bad tags
                     continue
                 if revparts[-2] == 0 and revparts[-1] % 2 == 0:
                     # normal branch
                     if revparts[:-2] == e.revision:
                         branchpoints.add(branch)
                 elif revparts == (1, 1, 1): # vendor branch
                     if revparts in e.branches:
                         branchpoints.add(branch)
             e.branchpoints = branchpoints
 
             log.append(e)
 
             rcsmap[e.rcs.replace('/Attic/', '/')] = e.rcs
 
             if len(log) % 100 == 0:
                 ui.status(stringutil.ellipsis('%d %s' % (len(log), e.file), 80)
                           + '\n')
 
     log.sort(key=lambda x: (x.rcs, x.revision))
 
     # find parent revisions of individual files
     versions = {}
     for e in sorted(oldlog, key=lambda x: (x.rcs, x.revision)):
         rcs = e.rcs.replace('/Attic/', '/')
         if rcs in rcsmap:
             e.rcs = rcsmap[rcs]
         branch = e.revision[:-1]
         versions[(e.rcs, branch)] = e.revision
 
     for e in log:
         branch = e.revision[:-1]
         p = versions.get((e.rcs, branch), None)
         if p is None:
             p = e.revision[:-2]
         e.parent = p
         versions[(e.rcs, branch)] = e.revision
 
     # update the log cache
     if cache:
         if log:
             # join up the old and new logs
             log.sort(key=lambda x: x.date)
 
             if oldlog and oldlog[-1].date >= log[0].date:
                 raise logerror(_('log cache overlaps with new log entries,'
                                  ' re-run without cache.'))
 
             log = oldlog + log
 
             # write the new cachefile
             ui.note(_('writing cvs log cache %s\n') % cachefile)
             pickle.dump(log, open(cachefile, 'wb'))
         else:
             log = oldlog
 
     ui.status(_('%d log entries\n') % len(log))
 
     encodings = ui.configlist('convert', 'cvsps.logencoding')
     if encodings:
         def revstr(r):
             # this is needed, because logentry.revision is a tuple of "int"
             # (e.g. (1, 2) for "1.2")
             return '.'.join(pycompat.maplist(pycompat.bytestr, r))
 
         for entry in log:
             comment = entry.comment
             for e in encodings:
                 try:
                     entry.comment = comment.decode(e).encode('utf-8')
                     if ui.debugflag:
                         ui.debug("transcoding by %s: %s of %s\n" %
                                  (e, revstr(entry.revision), entry.file))
                     break
                 except UnicodeDecodeError:
                     pass # try next encoding
                 except LookupError as inst: # unknown encoding, maybe
                     raise error.Abort(inst,
                                       hint=_('check convert.cvsps.logencoding'
                                              ' configuration'))
             else:
                 raise error.Abort(_("no encoding can transcode"
                                     " CVS log message for %s of %s")
                                   % (revstr(entry.revision), entry.file),
                                   hint=_('check convert.cvsps.logencoding'
                                          ' configuration'))
 
     hook.hook(ui, None, "cvslog", True, log=log)
 
     return log
 
 
 class changeset(object):
     '''Class changeset has the following attributes:
         .id        - integer identifying this changeset (list index)
         .author    - author name as CVS knows it
         .branch    - name of branch this changeset is on, or None
         .comment   - commit message
         .commitid  - CVS commitid or None
         .date      - the commit date as a (time,tz) tuple
         .entries   - list of logentry objects in this changeset
         .parents   - list of one or two parent changesets
         .tags      - list of tags on this changeset
         .synthetic - from synthetic revision "file ... added on branch ..."
         .mergepoint- the branch that has been merged from or None
         .branchpoints- the branches that start at the current entry or empty
     '''
     def __init__(self, **entries):
         self.id = None
         self.synthetic = False
         self.__dict__.update(entries)
 
     def __repr__(self):
         items = ("%s=%r"%(k, self.__dict__[k]) for k in sorted(self.__dict__))
         return "%s(%s)"%(type(self).__name__, ", ".join(items))
 
 def createchangeset(ui, log, fuzz=60, mergefrom=None, mergeto=None):
     '''Convert log into changesets.'''
 
     ui.status(_('creating changesets\n'))
 
     # try to order commitids by date
     mindate = {}
     for e in log:
         if e.commitid:
             mindate[e.commitid] = min(e.date, mindate.get(e.commitid))
 
     # Merge changesets
     log.sort(key=lambda x: (mindate.get(x.commitid), x.commitid, x.comment,
                             x.author, x.branch, x.date, x.branchpoints))
 
     changesets = []
     files = set()
     c = None
     for i, e in enumerate(log):
 
         # Check if log entry belongs to the current changeset or not.
 
         # Since CVS is file-centric, two different file revisions with
         # different branchpoints should be treated as belonging to two
         # different changesets (and the ordering is important and not
         # honoured by cvsps at this point).
         #
         # Consider the following case:
         # foo 1.1 branchpoints: [MYBRANCH]
         # bar 1.1 branchpoints: [MYBRANCH, MYBRANCH2]
         #
         # Here foo is part only of MYBRANCH, but not MYBRANCH2, e.g. a
         # later version of foo may be in MYBRANCH2, so foo should be the
         # first changeset and bar the next and MYBRANCH and MYBRANCH2
         # should both start off of the bar changeset. No provisions are
         # made to ensure that this is, in fact, what happens.
         if not (c and e.branchpoints == c.branchpoints and
                 (# cvs commitids
                  (e.commitid is not None and e.commitid == c.commitid) or
                  (# no commitids, use fuzzy commit detection
                   (e.commitid is None or c.commitid is None) and
                    e.comment == c.comment and
                    e.author == c.author and
                    e.branch == c.branch and
                    ((c.date[0] + c.date[1]) <=
                     (e.date[0] + e.date[1]) <=
                     (c.date[0] + c.date[1]) + fuzz) and
                    e.file not in files))):
             c = changeset(comment=e.comment, author=e.author,
                           branch=e.branch, date=e.date,
                           entries=[], mergepoint=e.mergepoint,
                           branchpoints=e.branchpoints, commitid=e.commitid)
             changesets.append(c)
 
             files = set()
             if len(changesets) % 100 == 0:
                 t = '%d %s' % (len(changesets), repr(e.comment)[1:-1])
                 ui.status(stringutil.ellipsis(t, 80) + '\n')
 
         c.entries.append(e)
         files.add(e.file)
         c.date = e.date       # changeset date is date of latest commit in it
 
     # Mark synthetic changesets
 
     for c in changesets:
         # Synthetic revisions always get their own changeset, because
         # the log message includes the filename.  E.g. if you add file3
         # and file4 on a branch, you get four log entries and three
         # changesets:
         #   "File file3 was added on branch ..." (synthetic, 1 entry)
         #   "File file4 was added on branch ..." (synthetic, 1 entry)
         #   "Add file3 and file4 to fix ..."     (real, 2 entries)
         # Hence the check for 1 entry here.
         c.synthetic = len(c.entries) == 1 and c.entries[0].synthetic
 
     # Sort files in each changeset
 
     def entitycompare(l, r):
         'Mimic cvsps sorting order'
         l = l.file.split('/')
         r = r.file.split('/')
         nl = len(l)
         nr = len(r)
         n = min(nl, nr)
         for i in range(n):
             if i + 1 == nl and nl < nr:
                 return -1
             elif i + 1 == nr and nl > nr:
                 return +1
             elif l[i] < r[i]:
                 return -1
             elif l[i] > r[i]:
                 return +1
         return 0
 
     for c in changesets:
         c.entries.sort(entitycompare)
 
     # Sort changesets by date
 
     odd = set()
     def cscmp(l, r):
         d = sum(l.date) - sum(r.date)
         if d:
             return d
 
         # detect vendor branches and initial commits on a branch
         le = {}
         for e in l.entries:
             le[e.rcs] = e.revision
         re = {}
         for e in r.entries:
             re[e.rcs] = e.revision
 
         d = 0
         for e in l.entries:
             if re.get(e.rcs, None) == e.parent:
                 assert not d
                 d = 1
                 break
 
         for e in r.entries:
             if le.get(e.rcs, None) == e.parent:
                 if d:
                     odd.add((l, r))
                 d = -1
                 break
         # By this point, the changesets are sufficiently compared that
         # we don't really care about ordering. However, this leaves
         # some race conditions in the tests, so we compare on the
         # number of files modified, the files contained in each
         # changeset, and the branchpoints in the change to ensure test
         # output remains stable.
 
         # recommended replacement for cmp from
         # https://docs.python.org/3.0/whatsnew/3.0.html
         c = lambda x, y: (x > y) - (x < y)
         # Sort bigger changes first.
         if not d:
             d = c(len(l.entries), len(r.entries))
         # Try sorting by filename in the change.
         if not d:
             d = c([e.file for e in l.entries], [e.file for e in r.entries])
         # Try and put changes without a branch point before ones with
         # a branch point.
         if not d:
             d = c(len(l.branchpoints), len(r.branchpoints))
         return d
 
     changesets.sort(cscmp)
 
     # Collect tags
 
     globaltags = {}
     for c in changesets:
         for e in c.entries:
             for tag in e.tags:
                 # remember which is the latest changeset to have this tag
                 globaltags[tag] = c
 
     for c in changesets:
         tags = set()
         for e in c.entries:
             tags.update(e.tags)
         # remember tags only if this is the latest changeset to have it
         c.tags = sorted(tag for tag in tags if globaltags[tag] is c)
 
     # Find parent changesets, handle {{mergetobranch BRANCHNAME}}
     # by inserting dummy changesets with two parents, and handle
     # {{mergefrombranch BRANCHNAME}} by setting two parents.
 
     if mergeto is None:
         mergeto = r'{{mergetobranch ([-\w]+)}}'
     if mergeto:
         mergeto = re.compile(mergeto)
 
     if mergefrom is None:
         mergefrom = r'{{mergefrombranch ([-\w]+)}}'
     if mergefrom:
         mergefrom = re.compile(mergefrom)
 
     versions = {}    # changeset index where we saw any particular file version
     branches = {}    # changeset index where we saw a branch
     n = len(changesets)
     i = 0
     while i < n:
         c = changesets[i]
 
         for f in c.entries:
             versions[(f.rcs, f.revision)] = i
 
         p = None
         if c.branch in branches:
             p = branches[c.branch]
         else:
             # first changeset on a new branch
             # the parent is a changeset with the branch in its
             # branchpoints such that it is the latest possible
             # commit without any intervening, unrelated commits.
 
             for candidate in xrange(i):
                 if c.branch not in changesets[candidate].branchpoints:
                     if p is not None:
                         break
                     continue
                 p = candidate
 
         c.parents = []
         if p is not None:
             p = changesets[p]
 
             # Ensure no changeset has a synthetic changeset as a parent.
             while p.synthetic:
                 assert len(p.parents) <= 1, \
                        _('synthetic changeset cannot have multiple parents')
                 if p.parents:
                     p = p.parents[0]
                 else:
                     p = None
                     break
 
             if p is not None:
                 c.parents.append(p)
 
         if c.mergepoint:
             if c.mergepoint == 'HEAD':
                 c.mergepoint = None
             c.parents.append(changesets[branches[c.mergepoint]])
 
         if mergefrom:
             m = mergefrom.search(c.comment)
             if m:
                 m = m.group(1)
                 if m == 'HEAD':
                     m = None
                 try:
                     candidate = changesets[branches[m]]
                 except KeyError:
                     ui.warn(_("warning: CVS commit message references "
                               "non-existent branch %r:\n%s\n")
                             % (m, c.comment))
                 if m in branches and c.branch != m and not candidate.synthetic:
                     c.parents.append(candidate)
 
         if mergeto:
             m = mergeto.search(c.comment)
             if m:
                 if m.groups():
                     m = m.group(1)
                     if m == 'HEAD':
                         m = None
                 else:
                     m = None   # if no group found then merge to HEAD
                 if m in branches and c.branch != m:
                     # insert empty changeset for merge
                     cc = changeset(
                         author=c.author, branch=m, date=c.date,
                         comment='convert-repo: CVS merge from branch %s'
                         % c.branch,
                         entries=[], tags=[],
                         parents=[changesets[branches[m]], c])
                     changesets.insert(i + 1, cc)
                     branches[m] = i + 1
 
                     # adjust our loop counters now we have inserted a new entry
                     n += 1
                     i += 2
                     continue
 
         branches[c.branch] = i
         i += 1
 
     # Drop synthetic changesets (safe now that we have ensured no other
     # changesets can have them as parents).
     i = 0
     while i < len(changesets):
         if changesets[i].synthetic:
             del changesets[i]
         else:
             i += 1
 
     # Number changesets
 
     for i, c in enumerate(changesets):
         c.id = i + 1
 
     if odd:
         for l, r in odd:
             if l.id is not None and r.id is not None:
                 ui.warn(_('changeset %d is both before and after %d\n')
                         % (l.id, r.id))
 
     ui.status(_('%d changeset entries\n') % len(changesets))
 
     hook.hook(ui, None, "cvschangesets", True, changesets=changesets)
 
     return changesets
 
 
 def debugcvsps(ui, *args, **opts):
     '''Read CVS rlog for current directory or named path in
     repository, and convert the log to changesets based on matching
     commit log entries and dates.
     '''
     opts = pycompat.byteskwargs(opts)
     if opts["new_cache"]:
         cache = "write"
     elif opts["update_cache"]:
         cache = "update"
     else:
         cache = None
 
     revisions = opts["revisions"]
 
     try:
         if args:
             log = []
             for d in args:
                 log += createlog(ui, d, root=opts["root"], cache=cache)
         else:
             log = createlog(ui, root=opts["root"], cache=cache)
     except logerror as e:
         ui.write("%r\n"%e)
         return
 
     changesets = createchangeset(ui, log, opts["fuzz"])
     del log
 
     # Print changesets (optionally filtered)
 
     off = len(revisions)
     branches = {}    # latest version number in each branch
     ancestors = {}   # parent branch
     for cs in changesets:
 
         if opts["ancestors"]:
             if cs.branch not in branches and cs.parents and cs.parents[0].id:
                 ancestors[cs.branch] = (changesets[cs.parents[0].id - 1].branch,
                                         cs.parents[0].id)
             branches[cs.branch] = cs.id
 
         # limit by branches
         if opts["branches"] and (cs.branch or 'HEAD') not in opts["branches"]:
             continue
 
         if not off:
             # Note: trailing spaces on several lines here are needed to have
             #       bug-for-bug compatibility with cvsps.
             ui.write('---------------------\n')
             ui.write(('PatchSet %d \n' % cs.id))
             ui.write(('Date: %s\n' % dateutil.datestr(cs.date,
                                                  '%Y/%m/%d %H:%M:%S %1%2')))
             ui.write(('Author: %s\n' % cs.author))
             ui.write(('Branch: %s\n' % (cs.branch or 'HEAD')))
             ui.write(('Tag%s: %s \n' % (['', 's'][len(cs.tags) > 1],
                                   ','.join(cs.tags) or '(none)')))
             if cs.branchpoints:
                 ui.write(('Branchpoints: %s \n') %
                          ', '.join(sorted(cs.branchpoints)))
             if opts["parents"] and cs.parents:
                 if len(cs.parents) > 1:
                     ui.write(('Parents: %s\n' %
                              (','.join([str(p.id) for p in cs.parents]))))
                 else:
                     ui.write(('Parent: %d\n' % cs.parents[0].id))
 
             if opts["ancestors"]:
                 b = cs.branch
                 r = []
                 while b:
                     b, c = ancestors[b]
                     r.append('%s:%d:%d' % (b or "HEAD", c, branches[b]))
                 if r:
                     ui.write(('Ancestors: %s\n' % (','.join(r))))
 
             ui.write(('Log:\n'))
             ui.write('%s\n\n' % cs.comment)
             ui.write(('Members: \n'))
             for f in cs.entries:
                 fn = f.file
                 if fn.startswith(opts["prefix"]):
                     fn = fn[len(opts["prefix"]):]
                 ui.write('\t%s:%s->%s%s \n' % (
                         fn, '.'.join([str(x) for x in f.parent]) or 'INITIAL',
                         '.'.join([str(x) for x in f.revision]),
                         ['', '(DEAD)'][f.dead]))
             ui.write('\n')
 
         # have we seen the start tag?
         if revisions and off:
             if revisions[0] == str(cs.id) or \
                 revisions[0] in cs.tags:
                 off = False
 
         # see if we reached the end tag
         if len(revisions) > 1 and not off:
             if revisions[1] == str(cs.id) or \
                 revisions[1] in cs.tags:
                 break

hgext/convert/gnuarch.py

@@ -1,353 +1,355
 # gnuarch.py - GNU Arch support for the convert extension
 #
 #  Copyright 2008, 2009 Aleix Conchillo Flaque <[e-mail]>
 #  and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 from __future__ import absolute_import
 
 import email.parser as emailparser
 import os
 import shutil
 import stat
 import tempfile
 
 from mercurial.i18n import _
 from mercurial import (
     encoding,
     error,
-    util,
 )
-from mercurial.utils import dateutil
+from mercurial.utils import (
+    dateutil,
+    procutil,
+)
 from . import common
 
 class gnuarch_source(common.converter_source, common.commandline):
 
     class gnuarch_rev(object):
         def __init__(self, rev):
             self.rev = rev
             self.summary = ''
             self.date = None
             self.author = ''
             self.continuationof = None
             self.add_files = []
             self.mod_files = []
             self.del_files = []
             self.ren_files = {}
             self.ren_dirs = {}
 
     def __init__(self, ui, repotype, path, revs=None):
         super(gnuarch_source, self).__init__(ui, repotype, path, revs=revs)
 
         if not os.path.exists(os.path.join(path, '{arch}')):
             raise common.NoRepo(_("%s does not look like a GNU Arch repository")
                          % path)
 
         # Could use checktool, but we want to check for baz or tla.
         self.execmd = None
-        if util.findexe('baz'):
+        if procutil.findexe('baz'):
             self.execmd = 'baz'
         else:
-            if util.findexe('tla'):
+            if procutil.findexe('tla'):
                 self.execmd = 'tla'
             else:
                 raise error.Abort(_('cannot find a GNU Arch tool'))
 
         common.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.catlogparser = emailparser.Parser()
         self.encoding = encoding.encoding
         self.archives = []
 
     def before(self):
         # Get registered archives
         self.archives = [i.rstrip('\n')
                          for i in self.runlines0('archives', '-n')]
 
         if self.execmd == 'tla':
             output = self.run0('tree-version', self.path)
         else:
             output = self.run0('tree-version', '-d', self.path)
         self.treeversion = output.strip()
 
         # Get name of temporary directory
         version = self.treeversion.split('/')
         self.tmppath = os.path.join(tempfile.gettempdir(),
                                     'hg-%s' % version[1])
 
         # Generate parents dictionary
         self.parents[None] = []
         treeversion = self.treeversion
         child = None
         while treeversion:
             self.ui.status(_('analyzing tree version %s...\n') % treeversion)
 
             archive = treeversion.split('/')[0]
             if archive not in self.archives:
                 self.ui.status(_('tree analysis stopped because it points to '
                                  'an unregistered archive %s...\n') % archive)
                 break
 
             # Get the complete list of revisions for that tree version
             output, status = self.runlines('revisions', '-r', '-f', treeversion)
             self.checkexit(status, 'failed retrieving revisions for %s'
                            % treeversion)
 
             # No new iteration unless a revision has a continuation-of header
             treeversion = None
 
             for l in output:
                 rev = l.strip()
                 self.changes[rev] = self.gnuarch_rev(rev)
                 self.parents[rev] = []
 
                 # Read author, date and summary
                 catlog, status = self.run('cat-log', '-d', self.path, rev)
                 if status:
                     catlog  = self.run0('cat-archive-log', rev)
                 self._parsecatlog(catlog, rev)
 
                 # Populate the parents map
                 self.parents[child].append(rev)
 
                 # Keep track of the current revision as the child of the next
                 # revision scanned
                 child = rev
 
                 # Check if we have to follow the usual incremental history
                 # or if we have to 'jump' to a different treeversion given
                 # by the continuation-of header.
                 if self.changes[rev].continuationof:
                     treeversion = '--'.join(
                         self.changes[rev].continuationof.split('--')[:-1])
                     break
 
                 # If we reached a base-0 revision w/o any continuation-of
                 # header, it means the tree history ends here.
                 if rev[-6:] == 'base-0':
                     break
 
     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 error.Abort(_('internal calling inconsistency'))
 
         if not os.path.lexists(os.path.join(self.tmppath, name)):
             return None, None
 
         return self._getfile(name, rev)
 
     def getchanges(self, rev, full):
         if full:
             raise error.Abort(_("convert from arch does not support --full"))
         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[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]
             copies.update(cps)
 
         self.lastrev = rev
         return sorted(set(changes)), copies, set()
 
     def getcommit(self, rev):
         changes = self.changes[rev]
         return common.commit(author=changes.author, date=changes.date,
                              desc=changes.summary, parents=self.parents[rev],
                              rev=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 = [procutil.shellquote(arg) for arg in cmdline]
         cmdline += ['>', os.devnull, '2>', os.devnull]
-        cmdline = util.quotecommand(' '.join(cmdline))
+        cmdline = procutil.quotecommand(' '.join(cmdline))
         self.ui.debug(cmdline, '\n')
         return os.system(cmdline)
 
     def _update(self, rev):
         self.ui.debug('applying revision %s...\n' % rev)
         changeset, status = self.runlines('replay', '-d', self.tmppath,
                                               rev)
         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))
             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))
             if mode:
                 mode = 'l'
             else:
                 mode = ''
         else:
             data = open(os.path.join(self.tmppath, name), 'rb').read()
             mode = (mode & 0o111) 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[d] = s
         return changes, copies
 
     def _obtainrevision(self, rev):
         self.ui.debug('obtaining revision %s...\n' % rev)
         output = self._execute('get', rev, self.tmppath)
         self.checkexit(output)
         self.ui.debug('analyzing 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):
         try:
             catlog = self.catlogparser.parsestr(data)
 
             # Commit date
             self.changes[rev].date = dateutil.datestr(
                 dateutil.strdate(catlog['Standard-date'],
                              '%Y-%m-%d %H:%M:%S'))
 
             # Commit author
             self.changes[rev].author = self.recode(catlog['Creator'])
 
             # Commit description
             self.changes[rev].summary = '\n\n'.join((catlog['Summary'],
                                                     catlog.get_payload()))
             self.changes[rev].summary = self.recode(self.changes[rev].summary)
 
             # Commit revision origin when dealing with a branch or tag
             if 'Continuation-of' in catlog:
                 self.changes[rev].continuationof = self.recode(
                     catlog['Continuation-of'])
         except Exception:
             raise error.Abort(_('could not parse cat-log of %s') % rev)
 
     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

hgext/convert/p4.py

@@ -1,377 +1,378
 # Perforce source for convert extension.
 #
 # Copyright 2009, Frank Kingswood <[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 __future__ import absolute_import
 
 import marshal
 import re
 
 from mercurial.i18n import _
 from mercurial import (
     error,
     util,
 )
 from mercurial.utils import (
     dateutil,
+    procutil,
     stringutil,
 )
 
 from . import common
 
 def loaditer(f):
     "Yield the dictionary objects generated by p4"
     try:
         while True:
             d = marshal.load(f)
             if not d:
                 break
             yield d
     except EOFError:
         pass
 
 def decodefilename(filename):
     """Perforce escapes special characters @, #, *, or %
     with %40, %23, %2A, or %25 respectively
 
     >>> decodefilename(b'portable-net45%252Bnetcore45%252Bwp8%252BMonoAndroid')
     'portable-net45%2Bnetcore45%2Bwp8%2BMonoAndroid'
     >>> decodefilename(b'//Depot/Directory/%2525/%2523/%23%40.%2A')
     '//Depot/Directory/%25/%23/#@.*'
     """
     replacements = [('%2A', '*'), ('%23', '#'), ('%40', '@'), ('%25', '%')]
     for k, v in replacements:
         filename = filename.replace(k, v)
     return filename
 
 class p4_source(common.converter_source):
     def __init__(self, ui, repotype, path, revs=None):
         # avoid import cycle
         from . import convcmd
 
         super(p4_source, self).__init__(ui, repotype, path, revs=revs)
 
         if "/" in path and not path.startswith('//'):
             raise common.NoRepo(_('%s does not look like a P4 repository') %
                                 path)
 
         common.checktool('p4', abort=False)
 
         self.revmap = {}
         self.encoding = self.ui.config('convert', 'p4.encoding',
                                        convcmd.orig_encoding)
         self.re_type = re.compile(
             "([a-z]+)?(text|binary|symlink|apple|resource|unicode|utf\d+)"
             "(\+\w+)?$")
         self.re_keywords = re.compile(
             r"\$(Id|Header|Date|DateTime|Change|File|Revision|Author)"
             r":[^$\n]*\$")
         self.re_keywords_old = re.compile("\$(Id|Header):[^$\n]*\$")
 
         if revs and len(revs) > 1:
             raise error.Abort(_("p4 source does not support specifying "
                                "multiple revisions"))
 
     def setrevmap(self, revmap):
         """Sets the parsed revmap dictionary.
 
         Revmap stores mappings from a source revision to a target revision.
         It is set in convertcmd.convert and provided by the user as a file
         on the commandline.
 
         Revisions in the map are considered beeing present in the
         repository and ignored during _parse(). This allows for incremental
         imports if a revmap is provided.
         """
         self.revmap = revmap
 
     def _parse_view(self, path):
         "Read changes affecting the path"
-        cmd = 'p4 -G changes -s submitted %s' % util.shellquote(path)
-        stdout = util.popen(cmd, mode='rb')
+        cmd = 'p4 -G changes -s submitted %s' % procutil.shellquote(path)
+        stdout = procutil.popen(cmd, mode='rb')
         p4changes = {}
         for d in loaditer(stdout):
             c = d.get("change", None)
             if c:
                 p4changes[c] = True
         return p4changes
 
     def _parse(self, ui, path):
         "Prepare list of P4 filenames and revisions to import"
         p4changes = {}
         changeset = {}
         files_map = {}
         copies_map = {}
         localname = {}
         depotname = {}
         heads = []
 
         ui.status(_('reading p4 views\n'))
 
         # read client spec or view
         if "/" in path:
             p4changes.update(self._parse_view(path))
             if path.startswith("//") and path.endswith("/..."):
                 views = {path[:-3]:""}
             else:
                 views = {"//": ""}
         else:
-            cmd = 'p4 -G client -o %s' % util.shellquote(path)
-            clientspec = marshal.load(util.popen(cmd, mode='rb'))
+            cmd = 'p4 -G client -o %s' % procutil.shellquote(path)
+            clientspec = marshal.load(procutil.popen(cmd, mode='rb'))
 
             views = {}
             for client in clientspec:
                 if client.startswith("View"):
                     sview, cview = clientspec[client].split()
                     p4changes.update(self._parse_view(sview))
                     if sview.endswith("...") and cview.endswith("..."):
                         sview = sview[:-3]
                         cview = cview[:-3]
                     cview = cview[2:]
                     cview = cview[cview.find("/") + 1:]
                     views[sview] = cview
 
         # list of changes that affect our source files
         p4changes = p4changes.keys()
         p4changes.sort(key=int)
 
         # list with depot pathnames, longest first
         vieworder = views.keys()
         vieworder.sort(key=len, reverse=True)
 
         # handle revision limiting
         startrev = self.ui.config('convert', 'p4.startrev')
 
         # now read the full changelists to get the list of file revisions
         ui.status(_('collecting p4 changelists\n'))
         lastid = None
         for change in p4changes:
             if startrev and int(change) < int(startrev):
                 continue
             if self.revs and int(change) > int(self.revs[0]):
                 continue
             if change in self.revmap:
                 # Ignore already present revisions, but set the parent pointer.
                 lastid = change
                 continue
 
             if lastid:
                 parents = [lastid]
             else:
                 parents = []
 
             d = self._fetch_revision(change)
             c = self._construct_commit(d, parents)
 
             descarr = c.desc.splitlines(True)
             if len(descarr) > 0:
                 shortdesc = descarr[0].rstrip('\r\n')
             else:
                 shortdesc = '**empty changelist description**'
 
             t = '%s %s' % (c.rev, repr(shortdesc)[1:-1])
             ui.status(stringutil.ellipsis(t, 80) + '\n')
 
             files = []
             copies = {}
             copiedfiles = []
             i = 0
             while ("depotFile%d" % i) in d and ("rev%d" % i) in d:
                 oldname = d["depotFile%d" % i]
                 filename = None
                 for v in vieworder:
                     if oldname.lower().startswith(v.lower()):
                         filename = decodefilename(views[v] + oldname[len(v):])
                         break
                 if filename:
                     files.append((filename, d["rev%d" % i]))
                     depotname[filename] = oldname
                     if (d.get("action%d" % i) == "move/add"):
                         copiedfiles.append(filename)
                     localname[oldname] = filename
                 i += 1
 
             # Collect information about copied files
             for filename in copiedfiles:
                 oldname = depotname[filename]
 
                 flcmd = 'p4 -G filelog %s' \
-                      % util.shellquote(oldname)
-                flstdout = util.popen(flcmd, mode='rb')
+                      % procutil.shellquote(oldname)
+                flstdout = procutil.popen(flcmd, mode='rb')
 
                 copiedfilename = None
                 for d in loaditer(flstdout):
                     copiedoldname = None
 
                     i = 0
                     while ("change%d" % i) in d:
                         if (d["change%d" % i] == change and
                             d["action%d" % i] == "move/add"):
                             j = 0
                             while ("file%d,%d" % (i, j)) in d:
                                 if d["how%d,%d" % (i, j)] == "moved from":
                                     copiedoldname = d["file%d,%d" % (i, j)]
                                     break
                                 j += 1
                         i += 1
 
                     if copiedoldname and copiedoldname in localname:
                         copiedfilename = localname[copiedoldname]
                         break
 
                 if copiedfilename:
                     copies[filename] = copiedfilename
                 else:
                     ui.warn(_("cannot find source for copied file: %s@%s\n")
                             % (filename, change))
 
             changeset[change] = c
             files_map[change] = files
             copies_map[change] = copies
             lastid = change
 
         if lastid and len(changeset) > 0:
             heads = [lastid]
 
         return {
             'changeset': changeset,
             'files': files_map,
             'copies': copies_map,
             'heads': heads,
             'depotname': depotname,
         }
 
     @util.propertycache
     def _parse_once(self):
         return self._parse(self.ui, self.path)
 
     @util.propertycache
     def copies(self):
         return self._parse_once['copies']
 
     @util.propertycache
     def files(self):
         return self._parse_once['files']
 
     @util.propertycache
     def changeset(self):
         return self._parse_once['changeset']
 
     @util.propertycache
     def heads(self):
         return self._parse_once['heads']
 
     @util.propertycache
     def depotname(self):
         return self._parse_once['depotname']
 
     def getheads(self):
         return self.heads
 
     def getfile(self, name, rev):
         cmd = 'p4 -G print %s' \
-            % util.shellquote("%s#%s" % (self.depotname[name], rev))
+            % procutil.shellquote("%s#%s" % (self.depotname[name], rev))
 
         lasterror = None
         while True:
-            stdout = util.popen(cmd, mode='rb')
+            stdout = procutil.popen(cmd, mode='rb')
 
             mode = None
             contents = []
             keywords = None
 
             for d in loaditer(stdout):
                 code = d["code"]
                 data = d.get("data")
 
                 if code == "error":
                     # if this is the first time error happened
                     # re-attempt getting the file
                     if not lasterror:
                         lasterror = IOError(d["generic"], data)
                         # this will exit inner-most for-loop
                         break
                     else:
                         raise lasterror
 
                 elif code == "stat":
                     action = d.get("action")
                     if action in ["purge", "delete", "move/delete"]:
                         return None, None
                     p4type = self.re_type.match(d["type"])
                     if p4type:
                         mode = ""
                         flags = ((p4type.group(1) or "")
                                + (p4type.group(3) or ""))
                         if "x" in flags:
                             mode = "x"
                         if p4type.group(2) == "symlink":
                             mode = "l"
                         if "ko" in flags:
                             keywords = self.re_keywords_old
                         elif "k" in flags:
                             keywords = self.re_keywords
 
                 elif code == "text" or code == "binary":
                     contents.append(data)
 
                 lasterror = None
 
             if not lasterror:
                 break
 
         if mode is None:
             return None, None
 
         contents = ''.join(contents)
 
         if keywords:
             contents = keywords.sub("$\\1$", contents)
         if mode == "l" and contents.endswith("\n"):
             contents = contents[:-1]
 
         return contents, mode
 
     def getchanges(self, rev, full):
         if full:
             raise error.Abort(_("convert from p4 does not support --full"))
         return self.files[rev], self.copies[rev], set()
 
     def _construct_commit(self, obj, parents=None):
         """
         Constructs a common.commit object from an unmarshalled
         `p4 describe` output
         """
         desc = self.recode(obj.get("desc", ""))
         date = (int(obj["time"]), 0)     # timezone not set
         if parents is None:
             parents = []
 
         return common.commit(author=self.recode(obj["user"]),
             date=dateutil.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'),
             parents=parents, desc=desc, branch=None, rev=obj['change'],
             extra={"p4": obj['change'], "convert_revision": obj['change']})
 
     def _fetch_revision(self, rev):
         """Return an output of `p4 describe` including author, commit date as
         a dictionary."""
         cmd = "p4 -G describe -s %s" % rev
-        stdout = util.popen(cmd, mode='rb')
+        stdout = procutil.popen(cmd, mode='rb')
         return marshal.load(stdout)
 
     def getcommit(self, rev):
         if rev in self.changeset:
             return self.changeset[rev]
         elif rev in self.revmap:
             d = self._fetch_revision(rev)
             return self._construct_commit(d, parents=None)
         raise error.Abort(
             _("cannot find %s in the revmap or parsed changesets") % rev)
 
     def gettags(self):
         return {}
 
     def getchangedfiles(self, rev, i):
         return sorted([x[0] for x in self.files[rev]])

hgext/convert/subversion.py

@@ -1,1360 +1,1361
 # Subversion 1.4/1.5 Python API backend
 #
 # Copyright(C) 2007 Daniel Holth et al
 from __future__ import absolute_import
 
 import os
 import re
 import tempfile
 import xml.dom.minidom
 
 from mercurial.i18n import _
 from mercurial import (
     encoding,
     error,
     pycompat,
     util,
     vfs as vfsmod,
 )
 from mercurial.utils import (
     dateutil,
+    procutil,
     stringutil,
 )
 
 from . import common
 
 pickle = util.pickle
 stringio = util.stringio
 propertycache = util.propertycache
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 commandline = common.commandline
 commit = common.commit
 converter_sink = common.converter_sink
 converter_source = common.converter_source
 decodeargs = common.decodeargs
 encodeargs = common.encodeargs
 makedatetimestamp = common.makedatetimestamp
 mapfile = common.mapfile
 MissingTool = common.MissingTool
 NoRepo = common.NoRepo
 
 # Subversion stuff. Works best with very recent Python SVN bindings
 # e.g. SVN 1.5 or backports. Thanks to the bzr folks for enhancing
 # these bindings.
 
 try:
     import svn
     import svn.client
     import svn.core
     import svn.ra
     import svn.delta
     from . import transport
     import warnings
     warnings.filterwarnings('ignore',
             module='svn.core',
             category=DeprecationWarning)
     svn.core.SubversionException # trigger import to catch error
 
 except ImportError:
     svn = None
 
 class SvnPathNotFound(Exception):
     pass
 
 def revsplit(rev):
     """Parse a revision string and return (uuid, path, revnum).
     >>> revsplit(b'svn:a2147622-4a9f-4db4-a8d3-13562ff547b2'
     ...          b'/proj%20B/mytrunk/mytrunk@1')
     ('a2147622-4a9f-4db4-a8d3-13562ff547b2', '/proj%20B/mytrunk/mytrunk', 1)
     >>> revsplit(b'svn:8af66a51-67f5-4354-b62c-98d67cc7be1d@1')
     ('', '', 1)
     >>> revsplit(b'@7')
     ('', '', 7)
     >>> revsplit(b'7')
     ('', '', 0)
     >>> revsplit(b'bad')
     ('', '', 0)
     """
     parts = rev.rsplit('@', 1)
     revnum = 0
     if len(parts) > 1:
         revnum = int(parts[1])
     parts = parts[0].split('/', 1)
     uuid = ''
     mod = ''
     if len(parts) > 1 and parts[0].startswith('svn:'):
         uuid = parts[0][4:]
         mod = '/' + parts[1]
     return uuid, mod, revnum
 
 def quote(s):
     # As of svn 1.7, many svn calls expect "canonical" paths. In
     # theory, we should call svn.core.*canonicalize() on all paths
     # before passing them to the API.  Instead, we assume the base url
     # is canonical and copy the behaviour of svn URL encoding function
     # so we can extend it safely with new components. The "safe"
     # characters were taken from the "svn_uri__char_validity" table in
     # libsvn_subr/path.c.
     return urlreq.quote(s, "!$&'()*+,-./:=@_~")
 
 def geturl(path):
     try:
         return svn.client.url_from_path(svn.core.svn_path_canonicalize(path))
     except svn.core.SubversionException:
         # svn.client.url_from_path() fails with local repositories
         pass
     if os.path.isdir(path):
         path = os.path.normpath(os.path.abspath(path))
         if pycompat.iswindows:
             path = '/' + util.normpath(path)
         # Module URL is later compared with the repository URL returned
         # by svn API, which is UTF-8.
         path = encoding.tolocal(path)
         path = 'file://%s' % quote(path)
     return svn.core.svn_path_canonicalize(path)
 
 def optrev(number):
     optrev = svn.core.svn_opt_revision_t()
     optrev.kind = svn.core.svn_opt_revision_number
     optrev.value.number = number
     return optrev
 
 class changedpath(object):
     def __init__(self, p):
         self.copyfrom_path = p.copyfrom_path
         self.copyfrom_rev = p.copyfrom_rev
         self.action = p.action
 
 def get_log_child(fp, url, paths, start, end, limit=0,
                   discover_changed_paths=True, strict_node_history=False):
     protocol = -1
     def receiver(orig_paths, revnum, author, date, message, pool):
         paths = {}
         if orig_paths is not None:
             for k, v in orig_paths.iteritems():
                 paths[k] = changedpath(v)
         pickle.dump((paths, revnum, author, date, message),
                     fp, protocol)
 
     try:
         # Use an ra of our own so that our parent can consume
         # our results without confusing the server.
         t = transport.SvnRaTransport(url=url)
         svn.ra.get_log(t.ra, paths, start, end, limit,
                        discover_changed_paths,
                        strict_node_history,
                        receiver)
     except IOError:
         # Caller may interrupt the iteration
         pickle.dump(None, fp, protocol)
     except Exception as inst:
         pickle.dump(stringutil.forcebytestr(inst), fp, protocol)
     else:
         pickle.dump(None, fp, protocol)
     fp.flush()
     # With large history, cleanup process goes crazy and suddenly
     # consumes *huge* amount of memory. The output file being closed,
     # there is no need for clean termination.
     os._exit(0)
 
 def debugsvnlog(ui, **opts):
     """Fetch SVN log in a subprocess and channel them back to parent to
     avoid memory collection issues.
     """
     if svn is None:
         raise error.Abort(_('debugsvnlog could not load Subversion python '
                            'bindings'))
 
     args = decodeargs(ui.fin.read())
     get_log_child(ui.fout, *args)
 
 class logstream(object):
     """Interruptible revision log iterator."""
     def __init__(self, stdout):
         self._stdout = stdout
 
     def __iter__(self):
         while True:
             try:
                 entry = pickle.load(self._stdout)
             except EOFError:
                 raise error.Abort(_('Mercurial failed to run itself, check'
                                    ' hg executable is in PATH'))
             try:
                 orig_paths, revnum, author, date, message = entry
             except (TypeError, ValueError):
                 if entry is None:
                     break
                 raise error.Abort(_("log stream exception '%s'") % entry)
             yield entry
 
     def close(self):
         if self._stdout:
             self._stdout.close()
             self._stdout = None
 
 class directlogstream(list):
     """Direct revision log iterator.
     This can be used for debugging and development but it will probably leak
     memory and is not suitable for real conversions."""
     def __init__(self, url, paths, start, end, limit=0,
                   discover_changed_paths=True, strict_node_history=False):
 
         def receiver(orig_paths, revnum, author, date, message, pool):
             paths = {}
             if orig_paths is not None:
                 for k, v in orig_paths.iteritems():
                     paths[k] = changedpath(v)
             self.append((paths, revnum, author, date, message))
 
         # Use an ra of our own so that our parent can consume
         # our results without confusing the server.
         t = transport.SvnRaTransport(url=url)
         svn.ra.get_log(t.ra, paths, start, end, limit,
                        discover_changed_paths,
                        strict_node_history,
                        receiver)
 
     def close(self):
         pass
 
 # Check to see if the given path is a local Subversion repo. Verify this by
 # looking for several svn-specific files and directories in the given
 # directory.
 def filecheck(ui, path, proto):
     for x in ('locks', 'hooks', 'format', 'db'):
         if not os.path.exists(os.path.join(path, x)):
             return False
     return True
 
 # Check to see if a given path is the root of an svn repo over http. We verify
 # this by requesting a version-controlled URL we know can't exist and looking
 # for the svn-specific "not found" XML.
 def httpcheck(ui, path, proto):
     try:
         opener = urlreq.buildopener()
         rsp = opener.open('%s://%s/!svn/ver/0/.svn' % (proto, path), 'rb')
         data = rsp.read()
     except urlerr.httperror as inst:
         if inst.code != 404:
             # Except for 404 we cannot know for sure this is not an svn repo
             ui.warn(_('svn: cannot probe remote repository, assume it could '
                       'be a subversion repository. Use --source-type if you '
                       'know better.\n'))
             return True
         data = inst.fp.read()
     except Exception:
         # Could be urlerr.urlerror if the URL is invalid or anything else.
         return False
     return '<m:human-readable errcode="160013">' in data
 
 protomap = {'http': httpcheck,
             'https': httpcheck,
             'file': filecheck,
             }
 def issvnurl(ui, url):
     try:
         proto, path = url.split('://', 1)
         if proto == 'file':
             if (pycompat.iswindows and path[:1] == '/'
                   and path[1:2].isalpha() and path[2:6].lower() == '%3a/'):
                 path = path[:2] + ':/' + path[6:]
             path = urlreq.url2pathname(path)
     except ValueError:
         proto = 'file'
         path = os.path.abspath(url)
     if proto == 'file':
         path = util.pconvert(path)
     check = protomap.get(proto, lambda *args: False)
     while '/' in path:
         if check(ui, path, proto):
             return True
         path = path.rsplit('/', 1)[0]
     return False
 
 # SVN conversion code stolen from bzr-svn and tailor
 #
 # Subversion looks like a versioned filesystem, branches structures
 # are defined by conventions and not enforced by the tool. First,
 # we define the potential branches (modules) as "trunk" and "branches"
 # children directories. Revisions are then identified by their
 # module and revision number (and a repository identifier).
 #
 # The revision graph is really a tree (or a forest). By default, a
 # revision parent is the previous revision in the same module. If the
 # module directory is copied/moved from another module then the
 # revision is the module root and its parent the source revision in
 # the parent module. A revision has at most one parent.
 #
 class svn_source(converter_source):
     def __init__(self, ui, repotype, url, revs=None):
         super(svn_source, self).__init__(ui, repotype, url, revs=revs)
 
         if not (url.startswith('svn://') or url.startswith('svn+ssh://') or
                 (os.path.exists(url) and
                  os.path.exists(os.path.join(url, '.svn'))) or
                 issvnurl(ui, url)):
             raise NoRepo(_("%s does not look like a Subversion repository")
                          % url)
         if svn is None:
             raise MissingTool(_('could not load Subversion python bindings'))
 
         try:
             version = svn.core.SVN_VER_MAJOR, svn.core.SVN_VER_MINOR
             if version < (1, 4):
                 raise MissingTool(_('Subversion python bindings %d.%d found, '
                                     '1.4 or later required') % version)
         except AttributeError:
             raise MissingTool(_('Subversion python bindings are too old, 1.4 '
                                 'or later required'))
 
         self.lastrevs = {}
 
         latest = None
         try:
             # Support file://path@rev syntax. Useful e.g. to convert
             # deleted branches.
             at = url.rfind('@')
             if at >= 0:
                 latest = int(url[at + 1:])
                 url = url[:at]
         except ValueError:
             pass
         self.url = geturl(url)
         self.encoding = 'UTF-8' # Subversion is always nominal UTF-8
         try:
             self.transport = transport.SvnRaTransport(url=self.url)
             self.ra = self.transport.ra
             self.ctx = self.transport.client
             self.baseurl = svn.ra.get_repos_root(self.ra)
             # Module is either empty or a repository path starting with
             # a slash and not ending with a slash.
             self.module = urlreq.unquote(self.url[len(self.baseurl):])
             self.prevmodule = None
             self.rootmodule = self.module
             self.commits = {}
             self.paths = {}
             self.uuid = svn.ra.get_uuid(self.ra)
         except svn.core.SubversionException:
             ui.traceback()
             svnversion = '%d.%d.%d' % (svn.core.SVN_VER_MAJOR,
                                        svn.core.SVN_VER_MINOR,
                                        svn.core.SVN_VER_MICRO)
             raise NoRepo(_("%s does not look like a Subversion repository "
                            "to libsvn version %s")
                          % (self.url, svnversion))
 
         if revs:
             if len(revs) > 1:
                 raise error.Abort(_('subversion source does not support '
                                    'specifying multiple revisions'))
             try:
                 latest = int(revs[0])
             except ValueError:
                 raise error.Abort(_('svn: revision %s is not an integer') %
                                  revs[0])
 
         trunkcfg = self.ui.config('convert', 'svn.trunk')
         if trunkcfg is None:
             trunkcfg = 'trunk'
         self.trunkname = trunkcfg.strip('/')
         self.startrev = self.ui.config('convert', 'svn.startrev')
         try:
             self.startrev = int(self.startrev)
             if self.startrev < 0:
                 self.startrev = 0
         except ValueError:
             raise error.Abort(_('svn: start revision %s is not an integer')
                              % self.startrev)
 
         try:
             self.head = self.latest(self.module, latest)
         except SvnPathNotFound:
             self.head = None
         if not self.head:
             raise error.Abort(_('no revision found in module %s')
                              % self.module)
         self.last_changed = self.revnum(self.head)
 
         self._changescache = (None, None)
 
         if os.path.exists(os.path.join(url, '.svn/entries')):
             self.wc = url
         else:
             self.wc = None
         self.convertfp = None
 
     def setrevmap(self, revmap):
         lastrevs = {}
         for revid in revmap:
             uuid, module, revnum = revsplit(revid)
             lastrevnum = lastrevs.setdefault(module, revnum)
             if revnum > lastrevnum:
                 lastrevs[module] = revnum
         self.lastrevs = lastrevs
 
     def exists(self, path, optrev):
         try:
             svn.client.ls(self.url.rstrip('/') + '/' + quote(path),
                                  optrev, False, self.ctx)
             return True
         except svn.core.SubversionException:
             return False
 
     def getheads(self):
 
         def isdir(path, revnum):
             kind = self._checkpath(path, revnum)
             return kind == svn.core.svn_node_dir
 
         def getcfgpath(name, rev):
             cfgpath = self.ui.config('convert', 'svn.' + name)
             if cfgpath is not None and cfgpath.strip() == '':
                 return None
             path = (cfgpath or name).strip('/')
             if not self.exists(path, rev):
                 if self.module.endswith(path) and name == 'trunk':
                     # we are converting from inside this directory
                     return None
                 if cfgpath:
                     raise error.Abort(_('expected %s to be at %r, but not found'
                                        ) % (name, path))
                 return None
             self.ui.note(_('found %s at %r\n') % (name, path))
             return path
 
         rev = optrev(self.last_changed)
         oldmodule = ''
         trunk = getcfgpath('trunk', rev)
         self.tags = getcfgpath('tags', rev)
         branches = getcfgpath('branches', rev)
 
         # If the project has a trunk or branches, we will extract heads
         # from them. We keep the project root otherwise.
         if trunk:
             oldmodule = self.module or ''
             self.module += '/' + trunk
             self.head = self.latest(self.module, self.last_changed)
             if not self.head:
                 raise error.Abort(_('no revision found in module %s')
                                  % self.module)
 
         # First head in the list is the module's head
         self.heads = [self.head]
         if self.tags is not None:
             self.tags = '%s/%s' % (oldmodule , (self.tags or 'tags'))
 
         # Check if branches bring a few more heads to the list
         if branches:
             rpath = self.url.strip('/')
             branchnames = svn.client.ls(rpath + '/' + quote(branches),
                                         rev, False, self.ctx)
             for branch in sorted(branchnames):
                 module = '%s/%s/%s' % (oldmodule, branches, branch)
                 if not isdir(module, self.last_changed):
                     continue
                 brevid = self.latest(module, self.last_changed)
                 if not brevid:
                     self.ui.note(_('ignoring empty branch %s\n') % branch)
                     continue
                 self.ui.note(_('found branch %s at %d\n') %
                              (branch, self.revnum(brevid)))
                 self.heads.append(brevid)
 
         if self.startrev and self.heads:
             if len(self.heads) > 1:
                 raise error.Abort(_('svn: start revision is not supported '
                                    'with more than one branch'))
             revnum = self.revnum(self.heads[0])
             if revnum < self.startrev:
                 raise error.Abort(
                     _('svn: no revision found after start revision %d')
                                  % self.startrev)
 
         return self.heads
 
     def _getchanges(self, rev, full):
         (paths, parents) = self.paths[rev]
         copies = {}
         if parents:
             files, self.removed, copies = self.expandpaths(rev, paths, parents)
         if full or not parents:
             # Perform a full checkout on roots
             uuid, module, revnum = revsplit(rev)
             entries = svn.client.ls(self.baseurl + quote(module),
                                     optrev(revnum), True, self.ctx)
             files = [n for n, e in entries.iteritems()
                      if e.kind == svn.core.svn_node_file]
             self.removed = set()
 
         files.sort()
         files = zip(files, [rev] * len(files))
         return (files, copies)
 
     def getchanges(self, rev, full):
         # reuse cache from getchangedfiles
         if self._changescache[0] == rev and not full:
             (files, copies) = self._changescache[1]
         else:
             (files, copies) = self._getchanges(rev, full)
             # caller caches the result, so free it here to release memory
             del self.paths[rev]
         return (files, copies, set())
 
     def getchangedfiles(self, rev, i):
         # called from filemap - cache computed values for reuse in getchanges
         (files, copies) = self._getchanges(rev, False)
         self._changescache = (rev, (files, copies))
         return [f[0] for f in files]
 
     def getcommit(self, rev):
         if rev not in self.commits:
             uuid, module, revnum = revsplit(rev)
             self.module = module
             self.reparent(module)
             # We assume that:
             # - requests for revisions after "stop" come from the
             # revision graph backward traversal. Cache all of them
             # down to stop, they will be used eventually.
             # - requests for revisions before "stop" come to get
             # isolated branches parents. Just fetch what is needed.
             stop = self.lastrevs.get(module, 0)
             if revnum < stop:
                 stop = revnum + 1
             self._fetch_revisions(revnum, stop)
             if rev not in self.commits:
                 raise error.Abort(_('svn: revision %s not found') % revnum)
         revcommit = self.commits[rev]
         # caller caches the result, so free it here to release memory
         del self.commits[rev]
         return revcommit
 
     def checkrevformat(self, revstr, mapname='splicemap'):
         """ fails if revision format does not match the correct format"""
         if not re.match(r'svn:[0-9a-f]{8,8}-[0-9a-f]{4,4}-'
                               r'[0-9a-f]{4,4}-[0-9a-f]{4,4}-[0-9a-f]'
                               r'{12,12}(.*)\@[0-9]+$',revstr):
             raise error.Abort(_('%s entry %s is not a valid revision'
                                ' identifier') % (mapname, revstr))
 
     def numcommits(self):
         return int(self.head.rsplit('@', 1)[1]) - self.startrev
 
     def gettags(self):
         tags = {}
         if self.tags is None:
             return tags
 
         # svn tags are just a convention, project branches left in a
         # 'tags' directory. There is no other relationship than
         # ancestry, which is expensive to discover and makes them hard
         # to update incrementally.  Worse, past revisions may be
         # referenced by tags far away in the future, requiring a deep
         # history traversal on every calculation.  Current code
         # performs a single backward traversal, tracking moves within
         # the tags directory (tag renaming) and recording a new tag
         # everytime a project is copied from outside the tags
         # directory. It also lists deleted tags, this behaviour may
         # change in the future.
         pendings = []
         tagspath = self.tags
         start = svn.ra.get_latest_revnum(self.ra)
         stream = self._getlog([self.tags], start, self.startrev)
         try:
             for entry in stream:
                 origpaths, revnum, author, date, message = entry
                 if not origpaths:
                     origpaths = []
                 copies = [(e.copyfrom_path, e.copyfrom_rev, p) for p, e
                           in origpaths.iteritems() if e.copyfrom_path]
                 # Apply moves/copies from more specific to general
                 copies.sort(reverse=True)
 
                 srctagspath = tagspath
                 if copies and copies[-1][2] == tagspath:
                     # Track tags directory moves
                     srctagspath = copies.pop()[0]
 
                 for source, sourcerev, dest in copies:
                     if not dest.startswith(tagspath + '/'):
                         continue
                     for tag in pendings:
                         if tag[0].startswith(dest):
                             tagpath = source + tag[0][len(dest):]
                             tag[:2] = [tagpath, sourcerev]
                             break
                     else:
                         pendings.append([source, sourcerev, dest])
 
                 # Filter out tags with children coming from different
                 # parts of the repository like:
                 # /tags/tag.1 (from /trunk:10)
                 # /tags/tag.1/foo (from /branches/foo:12)
                 # Here/tags/tag.1 discarded as well as its children.
                 # It happens with tools like cvs2svn. Such tags cannot
                 # be represented in mercurial.
                 addeds = dict((p, e.copyfrom_path) for p, e
                               in origpaths.iteritems()
                               if e.action == 'A' and e.copyfrom_path)
                 badroots = set()
                 for destroot in addeds:
                     for source, sourcerev, dest in pendings:
                         if (not dest.startswith(destroot + '/')
                             or source.startswith(addeds[destroot] + '/')):
                             continue
                         badroots.add(destroot)
                         break
 
                 for badroot in badroots:
                     pendings = [p for p in pendings if p[2] != badroot
                                 and not p[2].startswith(badroot + '/')]
 
                 # Tell tag renamings from tag creations
                 renamings = []
                 for source, sourcerev, dest in pendings:
                     tagname = dest.split('/')[-1]
                     if source.startswith(srctagspath):
                         renamings.append([source, sourcerev, tagname])
                         continue
                     if tagname in tags:
                         # Keep the latest tag value
                         continue
                     # From revision may be fake, get one with changes
                     try:
                         tagid = self.latest(source, sourcerev)
                         if tagid and tagname not in tags:
                             tags[tagname] = tagid
                     except SvnPathNotFound:
                         # It happens when we are following directories
                         # we assumed were copied with their parents
                         # but were really created in the tag
                         # directory.
                         pass
                 pendings = renamings
                 tagspath = srctagspath
         finally:
             stream.close()
         return tags
 
     def converted(self, rev, destrev):
         if not self.wc:
             return
         if self.convertfp is None:
             self.convertfp = open(os.path.join(self.wc, '.svn', 'hg-shamap'),
                                   'ab')
         self.convertfp.write(util.tonativeeol('%s %d\n'
                                               % (destrev, self.revnum(rev))))
         self.convertfp.flush()
 
     def revid(self, revnum, module=None):
         return 'svn:%s%s@%s' % (self.uuid, module or self.module, revnum)
 
     def revnum(self, rev):
         return int(rev.split('@')[-1])
 
     def latest(self, path, stop=None):
         """Find the latest revid affecting path, up to stop revision
         number. If stop is None, default to repository latest
         revision. It may return a revision in a different module,
         since a branch may be moved without a change being
         reported. Return None if computed module does not belong to
         rootmodule subtree.
         """
         def findchanges(path, start, stop=None):
             stream = self._getlog([path], start, stop or 1)
             try:
                 for entry in stream:
                     paths, revnum, author, date, message = entry
                     if stop is None and paths:
                         # We do not know the latest changed revision,
                         # keep the first one with changed paths.
                         break
                     if revnum <= stop:
                         break
 
                     for p in paths:
                         if (not path.startswith(p) or
                             not paths[p].copyfrom_path):
                             continue
                         newpath = paths[p].copyfrom_path + path[len(p):]
                         self.ui.debug("branch renamed from %s to %s at %d\n" %
                                       (path, newpath, revnum))
                         path = newpath
                         break
                 if not paths:
                     revnum = None
                 return revnum, path
             finally:
                 stream.close()
 
         if not path.startswith(self.rootmodule):
             # Requests on foreign branches may be forbidden at server level
             self.ui.debug('ignoring foreign branch %r\n' % path)
             return None
 
         if stop is None:
             stop = svn.ra.get_latest_revnum(self.ra)
         try:
             prevmodule = self.reparent('')
             dirent = svn.ra.stat(self.ra, path.strip('/'), stop)
             self.reparent(prevmodule)
         except svn.core.SubversionException:
             dirent = None
         if not dirent:
             raise SvnPathNotFound(_('%s not found up to revision %d')
                                   % (path, stop))
 
         # stat() gives us the previous revision on this line of
         # development, but it might be in *another module*. Fetch the
         # log and detect renames down to the latest revision.
         revnum, realpath = findchanges(path, stop, dirent.created_rev)
         if revnum is None:
             # Tools like svnsync can create empty revision, when
             # synchronizing only a subtree for instance. These empty
             # revisions created_rev still have their original values
             # despite all changes having disappeared and can be
             # returned by ra.stat(), at least when stating the root
             # module. In that case, do not trust created_rev and scan
             # the whole history.
             revnum, realpath = findchanges(path, stop)
             if revnum is None:
                 self.ui.debug('ignoring empty branch %r\n' % realpath)
                 return None
 
         if not realpath.startswith(self.rootmodule):
             self.ui.debug('ignoring foreign branch %r\n' % realpath)
             return None
         return self.revid(revnum, realpath)
 
     def reparent(self, module):
         """Reparent the svn transport and return the previous parent."""
         if self.prevmodule == module:
             return module
         svnurl = self.baseurl + quote(module)
         prevmodule = self.prevmodule
         if prevmodule is None:
             prevmodule = ''
         self.ui.debug("reparent to %s\n" % svnurl)
         svn.ra.reparent(self.ra, svnurl)
         self.prevmodule = module
         return prevmodule
 
     def expandpaths(self, rev, paths, parents):
         changed, removed = set(), set()
         copies = {}
 
         new_module, revnum = revsplit(rev)[1:]
         if new_module != self.module:
             self.module = new_module
             self.reparent(self.module)
 
         for i, (path, ent) in enumerate(paths):
             self.ui.progress(_('scanning paths'), i, item=path,
                              total=len(paths), unit=_('paths'))
             entrypath = self.getrelpath(path)
 
             kind = self._checkpath(entrypath, revnum)
             if kind == svn.core.svn_node_file:
                 changed.add(self.recode(entrypath))
                 if not ent.copyfrom_path or not parents:
                     continue
                 # Copy sources not in parent revisions cannot be
                 # represented, ignore their origin for now
                 pmodule, prevnum = revsplit(parents[0])[1:]
                 if ent.copyfrom_rev < prevnum:
                     continue
                 copyfrom_path = self.getrelpath(ent.copyfrom_path, pmodule)
                 if not copyfrom_path:
                     continue
                 self.ui.debug("copied to %s from %s@%s\n" %
                               (entrypath, copyfrom_path, ent.copyfrom_rev))
                 copies[self.recode(entrypath)] = self.recode(copyfrom_path)
             elif kind == 0: # gone, but had better be a deleted *file*
                 self.ui.debug("gone from %s\n" % ent.copyfrom_rev)
                 pmodule, prevnum = revsplit(parents[0])[1:]
                 parentpath = pmodule + "/" + entrypath
                 fromkind = self._checkpath(entrypath, prevnum, pmodule)
 
                 if fromkind == svn.core.svn_node_file:
                     removed.add(self.recode(entrypath))
                 elif fromkind == svn.core.svn_node_dir:
                     oroot = parentpath.strip('/')
                     nroot = path.strip('/')
                     children = self._iterfiles(oroot, prevnum)
                     for childpath in children:
                         childpath = childpath.replace(oroot, nroot)
                         childpath = self.getrelpath("/" + childpath, pmodule)
                         if childpath:
                             removed.add(self.recode(childpath))
                 else:
                     self.ui.debug('unknown path in revision %d: %s\n' % \
                                   (revnum, path))
             elif kind == svn.core.svn_node_dir:
                 if ent.action == 'M':
                     # If the directory just had a prop change,
                     # then we shouldn't need to look for its children.
                     continue
                 if ent.action == 'R' and parents:
                     # If a directory is replacing a file, mark the previous
                     # file as deleted
                     pmodule, prevnum = revsplit(parents[0])[1:]
                     pkind = self._checkpath(entrypath, prevnum, pmodule)
                     if pkind == svn.core.svn_node_file:
                         removed.add(self.recode(entrypath))
                     elif pkind == svn.core.svn_node_dir:
                         # We do not know what files were kept or removed,
                         # mark them all as changed.
                         for childpath in self._iterfiles(pmodule, prevnum):
                             childpath = self.getrelpath("/" + childpath)
                             if childpath:
                                 changed.add(self.recode(childpath))
 
                 for childpath in self._iterfiles(path, revnum):
                     childpath = self.getrelpath("/" + childpath)
                     if childpath:
                         changed.add(self.recode(childpath))
 
                 # Handle directory copies
                 if not ent.copyfrom_path or not parents:
                     continue
                 # Copy sources not in parent revisions cannot be
                 # represented, ignore their origin for now
                 pmodule, prevnum = revsplit(parents[0])[1:]
                 if ent.copyfrom_rev < prevnum:
                     continue
                 copyfrompath = self.getrelpath(ent.copyfrom_path, pmodule)
                 if not copyfrompath:
                     continue
                 self.ui.debug("mark %s came from %s:%d\n"
                               % (path, copyfrompath, ent.copyfrom_rev))
                 children = self._iterfiles(ent.copyfrom_path, ent.copyfrom_rev)
                 for childpath in children:
                     childpath = self.getrelpath("/" + childpath, pmodule)
                     if not childpath:
                         continue
                     copytopath = path + childpath[len(copyfrompath):]
                     copytopath = self.getrelpath(copytopath)
                     copies[self.recode(copytopath)] = self.recode(childpath)
 
         self.ui.progress(_('scanning paths'), None)
         changed.update(removed)
         return (list(changed), removed, copies)
 
     def _fetch_revisions(self, from_revnum, to_revnum):
         if from_revnum < to_revnum:
             from_revnum, to_revnum = to_revnum, from_revnum
 
         self.child_cset = None
 
         def parselogentry(orig_paths, revnum, author, date, message):
             """Return the parsed commit object or None, and True if
             the revision is a branch root.
             """
             self.ui.debug("parsing revision %d (%d changes)\n" %
                           (revnum, len(orig_paths)))
 
             branched = False
             rev = self.revid(revnum)
             # branch log might return entries for a parent we already have
 
             if rev in self.commits or revnum < to_revnum:
                 return None, branched
 
             parents = []
             # check whether this revision is the start of a branch or part
             # of a branch renaming
             orig_paths = sorted(orig_paths.iteritems())
             root_paths = [(p, e) for p, e in orig_paths
                           if self.module.startswith(p)]
             if root_paths:
                 path, ent = root_paths[-1]
                 if ent.copyfrom_path:
                     branched = True
                     newpath = ent.copyfrom_path + self.module[len(path):]
                     # ent.copyfrom_rev may not be the actual last revision
                     previd = self.latest(newpath, ent.copyfrom_rev)
                     if previd is not None:
                         prevmodule, prevnum = revsplit(previd)[1:]
                         if prevnum >= self.startrev:
                             parents = [previd]
                             self.ui.note(
                                 _('found parent of branch %s at %d: %s\n') %
                                 (self.module, prevnum, prevmodule))
                 else:
                     self.ui.debug("no copyfrom path, don't know what to do.\n")
 
             paths = []
             # filter out unrelated paths
             for path, ent in orig_paths:
                 if self.getrelpath(path) is None:
                     continue
                 paths.append((path, ent))
 
             # Example SVN datetime. Includes microseconds.
             # ISO-8601 conformant
             # '2007-01-04T17:35:00.902377Z'
             date = dateutil.parsedate(date[:19] + " UTC", ["%Y-%m-%dT%H:%M:%S"])
             if self.ui.configbool('convert', 'localtimezone'):
                 date = makedatetimestamp(date[0])
 
             if message:
                 log = self.recode(message)
             else:
                 log = ''
 
             if author:
                 author = self.recode(author)
             else:
                 author = ''
 
             try:
                 branch = self.module.split("/")[-1]
                 if branch == self.trunkname:
                     branch = None
             except IndexError:
                 branch = None
 
             cset = commit(author=author,
                           date=dateutil.datestr(date, '%Y-%m-%d %H:%M:%S %1%2'),
                           desc=log,
                           parents=parents,
                           branch=branch,
                           rev=rev)
 
             self.commits[rev] = cset
             # The parents list is *shared* among self.paths and the
             # commit object. Both will be updated below.
             self.paths[rev] = (paths, cset.parents)
             if self.child_cset and not self.child_cset.parents:
                 self.child_cset.parents[:] = [rev]
             self.child_cset = cset
             return cset, branched
 
         self.ui.note(_('fetching revision log for "%s" from %d to %d\n') %
                      (self.module, from_revnum, to_revnum))
 
         try:
             firstcset = None
             lastonbranch = False
             stream = self._getlog([self.module], from_revnum, to_revnum)
             try:
                 for entry in stream:
                     paths, revnum, author, date, message = entry
                     if revnum < self.startrev:
                         lastonbranch = True
                         break
                     if not paths:
                         self.ui.debug('revision %d has no entries\n' % revnum)
                         # If we ever leave the loop on an empty
                         # revision, do not try to get a parent branch
                         lastonbranch = lastonbranch or revnum == 0
                         continue
                     cset, lastonbranch = parselogentry(paths, revnum, author,
                                                        date, message)
                     if cset:
                         firstcset = cset
                     if lastonbranch:
                         break
             finally:
                 stream.close()
 
             if not lastonbranch and firstcset and not firstcset.parents:
                 # The first revision of the sequence (the last fetched one)
                 # has invalid parents if not a branch root. Find the parent
                 # revision now, if any.
                 try:
                     firstrevnum = self.revnum(firstcset.rev)
                     if firstrevnum > 1:
                         latest = self.latest(self.module, firstrevnum - 1)
                         if latest:
                             firstcset.parents.append(latest)
                 except SvnPathNotFound:
                     pass
         except svn.core.SubversionException as xxx_todo_changeme:
             (inst, num) = xxx_todo_changeme.args
             if num == svn.core.SVN_ERR_FS_NO_SUCH_REVISION:
                 raise error.Abort(_('svn: branch has no revision %s')
                                  % to_revnum)
             raise
 
     def getfile(self, file, rev):
         # TODO: ra.get_file transmits the whole file instead of diffs.
         if file in self.removed:
             return None, None
         mode = ''
         try:
             new_module, revnum = revsplit(rev)[1:]
             if self.module != new_module:
                 self.module = new_module
                 self.reparent(self.module)
             io = stringio()
             info = svn.ra.get_file(self.ra, file, revnum, io)
             data = io.getvalue()
             # ra.get_file() seems to keep a reference on the input buffer
             # preventing collection. Release it explicitly.
             io.close()
             if isinstance(info, list):
                 info = info[-1]
             mode = ("svn:executable" in info) and 'x' or ''
             mode = ("svn:special" in info) and 'l' or mode
         except svn.core.SubversionException as e:
             notfound = (svn.core.SVN_ERR_FS_NOT_FOUND,
                 svn.core.SVN_ERR_RA_DAV_PATH_NOT_FOUND)
             if e.apr_err in notfound: # File not found
                 return None, None
             raise
         if mode == 'l':
             link_prefix = "link "
             if data.startswith(link_prefix):
                 data = data[len(link_prefix):]
         return data, mode
 
     def _iterfiles(self, path, revnum):
         """Enumerate all files in path at revnum, recursively."""
         path = path.strip('/')
         pool = svn.core.Pool()
         rpath = '/'.join([self.baseurl, quote(path)]).strip('/')
         entries = svn.client.ls(rpath, optrev(revnum), True, self.ctx, pool)
         if path:
             path += '/'
         return ((path + p) for p, e in entries.iteritems()
                 if e.kind == svn.core.svn_node_file)
 
     def getrelpath(self, path, module=None):
         if module is None:
             module = self.module
         # Given the repository url of this wc, say
         #   "http://server/plone/CMFPlone/branches/Plone-2_0-branch"
         # extract the "entry" portion (a relative path) from what
         # svn log --xml says, i.e.
         #   "/CMFPlone/branches/Plone-2_0-branch/tests/PloneTestCase.py"
         # that is to say "tests/PloneTestCase.py"
         if path.startswith(module):
             relative = path.rstrip('/')[len(module):]
             if relative.startswith('/'):
                 return relative[1:]
             elif relative == '':
                 return relative
 
         # The path is outside our tracked tree...
         self.ui.debug('%r is not under %r, ignoring\n' % (path, module))
         return None
 
     def _checkpath(self, path, revnum, module=None):
         if module is not None:
             prevmodule = self.reparent('')
             path = module + '/' + path
         try:
             # ra.check_path does not like leading slashes very much, it leads
             # to PROPFIND subversion errors
             return svn.ra.check_path(self.ra, path.strip('/'), revnum)
         finally:
             if module is not None:
                 self.reparent(prevmodule)
 
     def _getlog(self, paths, start, end, limit=0, discover_changed_paths=True,
                 strict_node_history=False):
         # Normalize path names, svn >= 1.5 only wants paths relative to
         # supplied URL
         relpaths = []
         for p in paths:
             if not p.startswith('/'):
                 p = self.module + '/' + p
             relpaths.append(p.strip('/'))
         args = [self.baseurl, relpaths, start, end, limit,
                 discover_changed_paths, strict_node_history]
         # developer config: convert.svn.debugsvnlog
         if not self.ui.configbool('convert', 'svn.debugsvnlog'):
             return directlogstream(*args)
         arg = encodeargs(args)
-        hgexe = util.hgexecutable()
-        cmd = '%s debugsvnlog' % util.shellquote(hgexe)
-        stdin, stdout = util.popen2(util.quotecommand(cmd))
+        hgexe = procutil.hgexecutable()
+        cmd = '%s debugsvnlog' % procutil.shellquote(hgexe)
+        stdin, stdout = procutil.popen2(procutil.quotecommand(cmd))
         stdin.write(arg)
         try:
             stdin.close()
         except IOError:
             raise error.Abort(_('Mercurial failed to run itself, check'
                                ' hg executable is in PATH'))
         return logstream(stdout)
 
 pre_revprop_change = '''#!/bin/sh
 
 REPOS="$1"
 REV="$2"
 USER="$3"
 PROPNAME="$4"
 ACTION="$5"
 
 if [ "$ACTION" = "M" -a "$PROPNAME" = "svn:log" ]; then exit 0; fi
 if [ "$ACTION" = "A" -a "$PROPNAME" = "hg:convert-branch" ]; then exit 0; fi
 if [ "$ACTION" = "A" -a "$PROPNAME" = "hg:convert-rev" ]; then exit 0; fi
 
 echo "Changing prohibited revision property" >&2
 exit 1
 '''
 
 class svn_sink(converter_sink, commandline):
     commit_re = re.compile(r'Committed revision (\d+).', re.M)
     uuid_re = re.compile(r'Repository UUID:\s*(\S+)', re.M)
 
     def prerun(self):
         if self.wc:
             os.chdir(self.wc)
 
     def postrun(self):
         if self.wc:
             os.chdir(self.cwd)
 
     def join(self, name):
         return os.path.join(self.wc, '.svn', name)
 
     def revmapfile(self):
         return self.join('hg-shamap')
 
     def authorfile(self):
         return self.join('hg-authormap')
 
     def __init__(self, ui, repotype, path):
 
         converter_sink.__init__(self, ui, repotype, path)
         commandline.__init__(self, ui, 'svn')
         self.delete = []
         self.setexec = []
         self.delexec = []
         self.copies = []
         self.wc = None
         self.cwd = pycompat.getcwd()
 
         created = False
         if os.path.isfile(os.path.join(path, '.svn', 'entries')):
             self.wc = os.path.realpath(path)
             self.run0('update')
         else:
             if not re.search(br'^(file|http|https|svn|svn\+ssh)\://', path):
                 path = os.path.realpath(path)
                 if os.path.isdir(os.path.dirname(path)):
                     if not os.path.exists(os.path.join(path, 'db', 'fs-type')):
                         ui.status(_('initializing svn repository %r\n') %
                                   os.path.basename(path))
                         commandline(ui, 'svnadmin').run0('create', path)
                         created = path
                     path = util.normpath(path)
                     if not path.startswith('/'):
                         path = '/' + path
                     path = 'file://' + path
 
             wcpath = os.path.join(pycompat.getcwd(), os.path.basename(path) +
                                 '-wc')
             ui.status(_('initializing svn working copy %r\n')
                       % os.path.basename(wcpath))
             self.run0('checkout', path, wcpath)
 
             self.wc = wcpath
         self.opener = vfsmod.vfs(self.wc)
         self.wopener = vfsmod.vfs(self.wc)
         self.childmap = mapfile(ui, self.join('hg-childmap'))
         if util.checkexec(self.wc):
             self.is_exec = util.isexec
         else:
             self.is_exec = None
 
         if created:
             hook = os.path.join(created, 'hooks', 'pre-revprop-change')
             fp = open(hook, 'wb')
             fp.write(pre_revprop_change)
             fp.close()
             util.setflags(hook, False, True)
 
         output = self.run0('info')
         self.uuid = self.uuid_re.search(output).group(1).strip()
 
     def wjoin(self, *names):
         return os.path.join(self.wc, *names)
 
     @propertycache
     def manifest(self):
         # As of svn 1.7, the "add" command fails when receiving
         # already tracked entries, so we have to track and filter them
         # ourselves.
         m = set()
         output = self.run0('ls', recursive=True, xml=True)
         doc = xml.dom.minidom.parseString(output)
         for e in doc.getElementsByTagName('entry'):
             for n in e.childNodes:
                 if n.nodeType != n.ELEMENT_NODE or n.tagName != 'name':
                     continue
                 name = ''.join(c.data for c in n.childNodes
                                if c.nodeType == c.TEXT_NODE)
                 # Entries are compared with names coming from
                 # mercurial, so bytes with undefined encoding. Our
                 # best bet is to assume they are in local
                 # encoding. They will be passed to command line calls
                 # later anyway, so they better be.
                 m.add(encoding.unitolocal(name))
                 break
         return m
 
     def putfile(self, filename, flags, data):
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             try:
                 if os.path.islink(self.wjoin(filename)):
                     os.unlink(filename)
             except OSError:
                 pass
             self.wopener.write(filename, data)
 
             if self.is_exec:
                 if self.is_exec(self.wjoin(filename)):
                     if 'x' not in flags:
                         self.delexec.append(filename)
                 else:
                     if 'x' in flags:
                         self.setexec.append(filename)
                 util.setflags(self.wjoin(filename), False, 'x' in flags)
 
     def _copyfile(self, source, dest):
         # SVN's copy command pukes if the destination file exists, but
         # our copyfile method expects to record a copy that has
         # already occurred.  Cross the semantic gap.
         wdest = self.wjoin(dest)
         exists = os.path.lexists(wdest)
         if exists:
             fd, tempname = tempfile.mkstemp(
                 prefix='hg-copy-', dir=os.path.dirname(wdest))
             os.close(fd)
             os.unlink(tempname)
             os.rename(wdest, tempname)
         try:
             self.run0('copy', source, dest)
         finally:
             self.manifest.add(dest)
             if exists:
                 try:
                     os.unlink(wdest)
                 except OSError:
                     pass
                 os.rename(tempname, wdest)
 
     def dirs_of(self, files):
         dirs = set()
         for f in files:
             if os.path.isdir(self.wjoin(f)):
                 dirs.add(f)
             i = len(f)
             for i in iter(lambda: f.rfind('/', 0, i), -1):
                 dirs.add(f[:i])
         return dirs
 
     def add_dirs(self, files):
         add_dirs = [d for d in sorted(self.dirs_of(files))
                     if d not in self.manifest]
         if add_dirs:
             self.manifest.update(add_dirs)
             self.xargs(add_dirs, 'add', non_recursive=True, quiet=True)
         return add_dirs
 
     def add_files(self, files):
         files = [f for f in files if f not in self.manifest]
         if files:
             self.manifest.update(files)
             self.xargs(files, 'add', quiet=True)
         return files
 
     def addchild(self, parent, child):
         self.childmap[parent] = child
 
     def revid(self, rev):
         return u"svn:%s@%s" % (self.uuid, rev)
 
     def putcommit(self, files, copies, parents, commit, source, revmap, full,
                   cleanp2):
         for parent in parents:
             try:
                 return self.revid(self.childmap[parent])
             except KeyError:
                 pass
 
         # Apply changes to working copy
         for f, v in files:
             data, mode = source.getfile(f, v)
             if data is None:
                 self.delete.append(f)
             else:
                 self.putfile(f, mode, data)
                 if f in copies:
                     self.copies.append([copies[f], f])
         if full:
             self.delete.extend(sorted(self.manifest.difference(files)))
         files = [f[0] for f in files]
 
         entries = set(self.delete)
         files = frozenset(files)
         entries.update(self.add_dirs(files.difference(entries)))
         if self.copies:
             for s, d in self.copies:
                 self._copyfile(s, d)
             self.copies = []
         if self.delete:
             self.xargs(self.delete, 'delete')
             for f in self.delete:
                 self.manifest.remove(f)
             self.delete = []
         entries.update(self.add_files(files.difference(entries)))
         if self.delexec:
             self.xargs(self.delexec, 'propdel', 'svn:executable')
             self.delexec = []
         if self.setexec:
             self.xargs(self.setexec, 'propset', 'svn:executable', '*')
             self.setexec = []
 
         fd, messagefile = tempfile.mkstemp(prefix='hg-convert-')
         fp = os.fdopen(fd, r'wb')
         fp.write(util.tonativeeol(commit.desc))
         fp.close()
         try:
             output = self.run0('commit',
                                username=stringutil.shortuser(commit.author),
                                file=messagefile,
                                encoding='utf-8')
             try:
                 rev = self.commit_re.search(output).group(1)
             except AttributeError:
                 if parents and not files:
                     return parents[0]
                 self.ui.warn(_('unexpected svn output:\n'))
                 self.ui.warn(output)
                 raise error.Abort(_('unable to cope with svn output'))
             if commit.rev:
                 self.run('propset', 'hg:convert-rev', commit.rev,
                          revprop=True, revision=rev)
             if commit.branch and commit.branch != 'default':
                 self.run('propset', 'hg:convert-branch', commit.branch,
                          revprop=True, revision=rev)
             for parent in parents:
                 self.addchild(parent, rev)
             return self.revid(rev)
         finally:
             os.unlink(messagefile)
 
     def puttags(self, tags):
         self.ui.warn(_('writing Subversion tags is not yet implemented\n'))
         return None, None
 
     def hascommitfrommap(self, rev):
         # We trust that revisions referenced in a map still is present
         # TODO: implement something better if necessary and feasible
         return True
 
     def hascommitforsplicemap(self, rev):
         # This is not correct as one can convert to an existing subversion
         # repository and childmap would not list all revisions. Too bad.
         if rev in self.childmap:
             return True
         raise error.Abort(_('splice map revision %s not found in subversion '
                            'child map (revision lookups are not implemented)')
                          % rev)

hgext/extdiff.py

@@ -1,421 +1,422
 # extdiff.py - external diff program support for mercurial
 #
 # Copyright 2006 Vadim Gelfer <[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.
 
 '''command to allow external programs to compare revisions
 
 The extdiff Mercurial extension allows you to use external programs
 to compare revisions, or revision with working directory. The external
 diff programs are called with a configurable set of options and two
 non-option arguments: paths to directories containing snapshots of
 files to compare.
 
 The extdiff extension also allows you to configure new diff commands, so
 you do not need to type :hg:`extdiff -p kdiff3` always. ::
 
   [extdiff]
   # add new command that runs GNU diff(1) in 'context diff' mode
   cdiff = gdiff -Nprc5
   ## or the old way:
   #cmd.cdiff = gdiff
   #opts.cdiff = -Nprc5
 
   # add new command called meld, runs meld (no need to name twice).  If
   # the meld executable is not available, the meld tool in [merge-tools]
   # will be used, if available
   meld =
 
   # add new command called vimdiff, runs gvimdiff with DirDiff plugin
   # (see http://www.vim.org/scripts/script.php?script_id=102) Non
   # English user, be sure to put "let g:DirDiffDynamicDiffText = 1" in
   # your .vimrc
   vimdiff = gvim -f "+next" \\
             "+execute 'DirDiff' fnameescape(argv(0)) fnameescape(argv(1))"
 
 Tool arguments can include variables that are expanded at runtime::
 
   $parent1, $plabel1 - filename, descriptive label of first parent
   $child,   $clabel  - filename, descriptive label of child revision
   $parent2, $plabel2 - filename, descriptive label of second parent
   $root              - repository root
   $parent is an alias for $parent1.
 
 The extdiff extension will look in your [diff-tools] and [merge-tools]
 sections for diff tool arguments, when none are specified in [extdiff].
 
 ::
 
   [extdiff]
   kdiff3 =
 
   [diff-tools]
   kdiff3.diffargs=--L1 '$plabel1' --L2 '$clabel' $parent $child
 
 You can use -I/-X and list of file or directory names like normal
 :hg:`diff` command. The extdiff extension makes snapshots of only
 needed files, so running the external diff program will actually be
 pretty fast (at least faster than having to compare the entire tree).
 '''
 
 from __future__ import absolute_import
 
 import os
 import re
 import shutil
 import stat
 import tempfile
 from mercurial.i18n import _
 from mercurial.node import (
     nullid,
     short,
 )
 from mercurial import (
     archival,
     cmdutil,
     error,
     filemerge,
     pycompat,
     registrar,
     scmutil,
     util,
 )
 from mercurial.utils import (
+    procutil,
     stringutil,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('extdiff', br'opts\..*',
     default='',
     generic=True,
 )
 
 configitem('diff-tools', br'.*\.diffargs$',
     default=None,
     generic=True,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 def snapshot(ui, repo, files, node, tmproot, listsubrepos):
     '''snapshot files as of some revision
     if not using snapshot, -I/-X does not work and recursive diff
     in tools like kdiff3 and meld displays too many files.'''
     dirname = os.path.basename(repo.root)
     if dirname == "":
         dirname = "root"
     if node is not None:
         dirname = '%s.%s' % (dirname, short(node))
     base = os.path.join(tmproot, dirname)
     os.mkdir(base)
     fnsandstat = []
 
     if node is not None:
         ui.note(_('making snapshot of %d files from rev %s\n') %
                 (len(files), short(node)))
     else:
         ui.note(_('making snapshot of %d files from working directory\n') %
             (len(files)))
 
     if files:
         repo.ui.setconfig("ui", "archivemeta", False)
 
         archival.archive(repo, base, node, 'files',
                          matchfn=scmutil.matchfiles(repo, files),
                          subrepos=listsubrepos)
 
         for fn in sorted(files):
             wfn = util.pconvert(fn)
             ui.note('  %s\n' % wfn)
 
             if node is None:
                 dest = os.path.join(base, wfn)
 
                 fnsandstat.append((dest, repo.wjoin(fn), os.lstat(dest)))
     return dirname, fnsandstat
 
 def dodiff(ui, repo, cmdline, pats, opts):
     '''Do the actual diff:
 
     - copy to a temp structure if diffing 2 internal revisions
     - copy to a temp structure if diffing working revision with
       another one and more than 1 file is changed
     - just invoke the diff for a single file in the working dir
     '''
 
     revs = opts.get('rev')
     change = opts.get('change')
     do3way = '$parent2' in cmdline
 
     if revs and change:
         msg = _('cannot specify --rev and --change at the same time')
         raise error.Abort(msg)
     elif change:
         node2 = scmutil.revsingle(repo, change, None).node()
         node1a, node1b = repo.changelog.parents(node2)
     else:
         node1a, node2 = scmutil.revpair(repo, revs)
         if not revs:
             node1b = repo.dirstate.p2()
         else:
             node1b = nullid
 
     # Disable 3-way merge if there is only one parent
     if do3way:
         if node1b == nullid:
             do3way = False
 
     subrepos=opts.get('subrepos')
 
     matcher = scmutil.match(repo[node2], pats, opts)
 
     if opts.get('patch'):
         if subrepos:
             raise error.Abort(_('--patch cannot be used with --subrepos'))
         if node2 is None:
             raise error.Abort(_('--patch requires two revisions'))
     else:
         mod_a, add_a, rem_a = map(set, repo.status(node1a, node2, matcher,
                                                    listsubrepos=subrepos)[:3])
         if do3way:
             mod_b, add_b, rem_b = map(set,
                                       repo.status(node1b, node2, matcher,
                                                   listsubrepos=subrepos)[:3])
         else:
             mod_b, add_b, rem_b = set(), set(), set()
         modadd = mod_a | add_a | mod_b | add_b
         common = modadd | rem_a | rem_b
         if not common:
             return 0
 
     tmproot = tempfile.mkdtemp(prefix='extdiff.')
     try:
         if not opts.get('patch'):
             # Always make a copy of node1a (and node1b, if applicable)
             dir1a_files = mod_a | rem_a | ((mod_b | add_b) - add_a)
             dir1a = snapshot(ui, repo, dir1a_files, node1a, tmproot,
                              subrepos)[0]
             rev1a = '@%d' % repo[node1a].rev()
             if do3way:
                 dir1b_files = mod_b | rem_b | ((mod_a | add_a) - add_b)
                 dir1b = snapshot(ui, repo, dir1b_files, node1b, tmproot,
                                  subrepos)[0]
                 rev1b = '@%d' % repo[node1b].rev()
             else:
                 dir1b = None
                 rev1b = ''
 
             fnsandstat = []
 
             # If node2 in not the wc or there is >1 change, copy it
             dir2root = ''
             rev2 = ''
             if node2:
                 dir2 = snapshot(ui, repo, modadd, node2, tmproot, subrepos)[0]
                 rev2 = '@%d' % repo[node2].rev()
             elif len(common) > 1:
                 #we only actually need to get the files to copy back to
                 #the working dir in this case (because the other cases
                 #are: diffing 2 revisions or single file -- in which case
                 #the file is already directly passed to the diff tool).
                 dir2, fnsandstat = snapshot(ui, repo, modadd, None, tmproot,
                                             subrepos)
             else:
                 # This lets the diff tool open the changed file directly
                 dir2 = ''
                 dir2root = repo.root
 
             label1a = rev1a
             label1b = rev1b
             label2 = rev2
 
             # If only one change, diff the files instead of the directories
             # Handle bogus modifies correctly by checking if the files exist
             if len(common) == 1:
                 common_file = util.localpath(common.pop())
                 dir1a = os.path.join(tmproot, dir1a, common_file)
                 label1a = common_file + rev1a
                 if not os.path.isfile(dir1a):
                     dir1a = os.devnull
                 if do3way:
                     dir1b = os.path.join(tmproot, dir1b, common_file)
                     label1b = common_file + rev1b
                     if not os.path.isfile(dir1b):
                         dir1b = os.devnull
                 dir2 = os.path.join(dir2root, dir2, common_file)
                 label2 = common_file + rev2
         else:
             template = 'hg-%h.patch'
             cmdutil.export(repo, [repo[node1a].rev(), repo[node2].rev()],
                            fntemplate=repo.vfs.reljoin(tmproot, template),
                            match=matcher)
             label1a = cmdutil.makefilename(repo[node1a], template)
             label2 = cmdutil.makefilename(repo[node2], template)
             dir1a = repo.vfs.reljoin(tmproot, label1a)
             dir2 = repo.vfs.reljoin(tmproot, label2)
             dir1b = None
             label1b = None
             fnsandstat = []
 
         # Function to quote file/dir names in the argument string.
         # When not operating in 3-way mode, an empty string is
         # returned for parent2
         replace = {'parent': dir1a, 'parent1': dir1a, 'parent2': dir1b,
                    'plabel1': label1a, 'plabel2': label1b,
                    'clabel': label2, 'child': dir2,
                    'root': repo.root}
         def quote(match):
             pre = match.group(2)
             key = match.group(3)
             if not do3way and key == 'parent2':
                 return pre
-            return pre + util.shellquote(replace[key])
+            return pre + procutil.shellquote(replace[key])
 
         # Match parent2 first, so 'parent1?' will match both parent1 and parent
         regex = (br'''(['"]?)([^\s'"$]*)'''
                  br'\$(parent2|parent1?|child|plabel1|plabel2|clabel|root)\1')
         if not do3way and not re.search(regex, cmdline):
             cmdline += ' $parent1 $child'
         cmdline = re.sub(regex, quote, cmdline)
 
         ui.debug('running %r in %s\n' % (pycompat.bytestr(cmdline), tmproot))
         ui.system(cmdline, cwd=tmproot, blockedtag='extdiff')
 
         for copy_fn, working_fn, st in fnsandstat:
             cpstat = os.lstat(copy_fn)
             # Some tools copy the file and attributes, so mtime may not detect
             # all changes.  A size check will detect more cases, but not all.
             # The only certain way to detect every case is to diff all files,
             # which could be expensive.
             # copyfile() carries over the permission, so the mode check could
             # be in an 'elif' branch, but for the case where the file has
             # changed without affecting mtime or size.
             if (cpstat[stat.ST_MTIME] != st[stat.ST_MTIME]
                 or cpstat.st_size != st.st_size
                 or (cpstat.st_mode & 0o100) != (st.st_mode & 0o100)):
                 ui.debug('file changed while diffing. '
                          'Overwriting: %s (src: %s)\n' % (working_fn, copy_fn))
                 util.copyfile(copy_fn, working_fn)
 
         return 1
     finally:
         ui.note(_('cleaning up temp directory\n'))
         shutil.rmtree(tmproot)
 
 extdiffopts = [
     ('o', 'option', [],
      _('pass option to comparison program'), _('OPT')),
     ('r', 'rev', [], _('revision'), _('REV')),
     ('c', 'change', '', _('change made by revision'), _('REV')),
     ('', 'patch', None, _('compare patches for two revisions'))
     ] + cmdutil.walkopts + cmdutil.subrepoopts
 
 @command('extdiff',
     [('p', 'program', '', _('comparison program to run'), _('CMD')),
      ] + extdiffopts,
     _('hg extdiff [OPT]... [FILE]...'),
     inferrepo=True)
 def extdiff(ui, repo, *pats, **opts):
     '''use external program to diff repository (or selected files)
 
     Show differences between revisions for the specified files, using
     an external program. The default program used is diff, with
     default options "-Npru".
 
     To select a different program, use the -p/--program option. The
     program will be passed the names of two directories to compare. To
     pass additional options to the program, use -o/--option. These
     will be passed before the names of the directories to compare.
 
     When two revision arguments are given, then changes are shown
     between those revisions. If only one revision is specified then
     that revision is compared to the working directory, and, when no
     revisions are specified, the working directory files are compared
     to its parent.'''
     opts = pycompat.byteskwargs(opts)
     program = opts.get('program')
     option = opts.get('option')
     if not program:
         program = 'diff'
         option = option or ['-Npru']
-    cmdline = ' '.join(map(util.shellquote, [program] + option))
+    cmdline = ' '.join(map(procutil.shellquote, [program] + option))
     return dodiff(ui, repo, cmdline, pats, opts)
 
 class savedcmd(object):
     """use external program to diff repository (or selected files)
 
     Show differences between revisions for the specified files, using
     the following program::
 
         %(path)s
 
     When two revision arguments are given, then changes are shown
     between those revisions. If only one revision is specified then
     that revision is compared to the working directory, and, when no
     revisions are specified, the working directory files are compared
     to its parent.
     """
 
     def __init__(self, path, cmdline):
         # We can't pass non-ASCII through docstrings (and path is
         # in an unknown encoding anyway)
         docpath = stringutil.escapestr(path)
         self.__doc__ %= {r'path': pycompat.sysstr(stringutil.uirepr(docpath))}
         self._cmdline = cmdline
 
     def __call__(self, ui, repo, *pats, **opts):
         opts = pycompat.byteskwargs(opts)
-        options = ' '.join(map(util.shellquote, opts['option']))
+        options = ' '.join(map(procutil.shellquote, opts['option']))
         if options:
             options = ' ' + options
         return dodiff(ui, repo, self._cmdline + options, pats, opts)
 
 def uisetup(ui):
     for cmd, path in ui.configitems('extdiff'):
         path = util.expandpath(path)
         if cmd.startswith('cmd.'):
             cmd = cmd[4:]
             if not path:
-                path = util.findexe(cmd)
+                path = procutil.findexe(cmd)
                 if path is None:
                     path = filemerge.findexternaltool(ui, cmd) or cmd
             diffopts = ui.config('extdiff', 'opts.' + cmd)
-            cmdline = util.shellquote(path)
+            cmdline = procutil.shellquote(path)
             if diffopts:
                 cmdline += ' ' + diffopts
         elif cmd.startswith('opts.'):
             continue
         else:
             if path:
                 # case "cmd = path opts"
                 cmdline = path
                 diffopts = len(pycompat.shlexsplit(cmdline)) > 1
             else:
                 # case "cmd ="
-                path = util.findexe(cmd)
+                path = procutil.findexe(cmd)
                 if path is None:
                     path = filemerge.findexternaltool(ui, cmd) or cmd
-                cmdline = util.shellquote(path)
+                cmdline = procutil.shellquote(path)
                 diffopts = False
         # look for diff arguments in [diff-tools] then [merge-tools]
         if not diffopts:
             args = ui.config('diff-tools', cmd+'.diffargs') or \
                    ui.config('merge-tools', cmd+'.diffargs')
             if args:
                 cmdline += ' ' + args
         command(cmd, extdiffopts[:], _('hg %s [OPTION]... [FILE]...') % cmd,
                 inferrepo=True)(savedcmd(path, cmdline))
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = [savedcmd]

hgext/githelp.py

@@ -1,1076 +1,1078
 # githelp.py - Try to map Git commands to Mercurial equivalents.
 #
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 """try mapping git commands to Mercurial commands
 
 Tries to map a given git command to a Mercurial command:
 
   $ hg githelp -- git checkout master
   hg update master
 
 If an unknown command or parameter combination is detected, an error is
 produced.
 """
 
 from __future__ import absolute_import
 
 import getopt
 import re
 
 from mercurial.i18n import _
 from mercurial import (
     encoding,
     error,
     fancyopts,
     registrar,
-    util,
+)
+from mercurial.utils import (
+    procutil,
 )
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 def convert(s):
     if s.startswith("origin/"):
         return s[7:]
     if 'HEAD' in s:
         s = s.replace('HEAD', '.')
     # HEAD~ in git is .~1 in mercurial
     s = re.sub('~$', '~1', s)
     return s
 
 @command('^githelp|git', [
     ], _('hg githelp'))
 def githelp(ui, repo, *args, **kwargs):
     '''suggests the Mercurial equivalent of the given git command
 
     Usage: hg githelp -- <git command>
     '''
 
     if len(args) == 0 or (len(args) == 1 and args[0] =='git'):
         raise error.Abort(_('missing git command - '
                             'usage: hg githelp -- <git command>'))
 
     if args[0] == 'git':
         args = args[1:]
 
     cmd = args[0]
     if not cmd in gitcommands:
         raise error.Abort("error: unknown git command %s" % (cmd))
 
     ui.pager('githelp')
     args = args[1:]
     return gitcommands[cmd](ui, repo, *args, **kwargs)
 
 def parseoptions(ui, cmdoptions, args):
     cmdoptions = list(cmdoptions)
     opts = {}
     args = list(args)
     while True:
         try:
             args = fancyopts.fancyopts(list(args), cmdoptions, opts, True)
             break
         except getopt.GetoptError as ex:
             flag = None
             if "requires argument" in ex.msg:
                 raise
             if ('--' + ex.opt) in ex.msg:
                 flag = '--' + ex.opt
             elif ('-' + ex.opt) in ex.msg:
                 flag = '-' + ex.opt
             else:
                 raise error.Abort("unknown option %s" % ex.opt)
             try:
                 args.remove(flag)
             except Exception:
                 raise error.Abort(
                     "unknown option {0} packed with other options\n"
                     "Please try passing the option as it's own flag: -{0}" \
                     .format(ex.opt))
 
             ui.warn(_("ignoring unknown option %s\n") % flag)
 
     args = list([convert(x) for x in args])
     opts = dict([(k, convert(v)) if isinstance(v, str) else (k, v)
                                  for k, v in opts.iteritems()])
 
     return args, opts
 
 class Command(object):
     def __init__(self, name):
         self.name = name
         self.args = []
         self.opts = {}
 
     def __bytes__(self):
         cmd = "hg " + self.name
         if self.opts:
             for k, values in sorted(self.opts.iteritems()):
                 for v in values:
                     if v:
                         cmd += " %s %s" % (k, v)
                     else:
                         cmd += " %s" % (k,)
         if self.args:
             cmd += " "
             cmd += " ".join(self.args)
         return cmd
 
     __str__ = encoding.strmethod(__bytes__)
 
     def append(self, value):
         self.args.append(value)
 
     def extend(self, values):
         self.args.extend(values)
 
     def __setitem__(self, key, value):
         values = self.opts.setdefault(key, [])
         values.append(value)
 
     def __and__(self, other):
         return AndCommand(self, other)
 
 class AndCommand(object):
     def __init__(self, left, right):
         self.left = left
         self.right = right
 
     def __str__(self):
         return "%s && %s" % (self.left, self.right)
 
     def __and__(self, other):
         return AndCommand(self, other)
 
 def add(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('A', 'all', None, ''),
         ('p', 'patch', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     if (opts.get('patch')):
         ui.status(_("note: Mercurial will commit when complete, "
                     "as there is no staging area in Mercurial\n\n"))
         cmd = Command('commit --interactive')
     else:
         cmd = Command("add")
 
         if not opts.get('all'):
             cmd.extend(args)
         else:
             ui.status(_("note: use hg addremove to remove files that have "
                         "been deleted.\n\n"))
 
     ui.status((bytes(cmd)), "\n")
 
 def am(ui, repo, *args, **kwargs):
     cmdoptions=[
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
     cmd = Command('import')
     ui.status(bytes(cmd), "\n")
 
 def apply(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('p', 'p', int, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('import --no-commit')
     if (opts.get('p')):
         cmd['-p'] = opts.get('p')
     cmd.extend(args)
 
     ui.status((bytes(cmd)), "\n")
 
 def bisect(ui, repo, *args, **kwargs):
     ui.status(_("See 'hg help bisect' for how to use bisect.\n\n"))
 
 def blame(ui, repo, *args, **kwargs):
     cmdoptions = [
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
     cmd = Command('annotate -udl')
     cmd.extend([convert(v) for v in args])
     ui.status((bytes(cmd)), "\n")
 
 def branch(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('', 'set-upstream', None, ''),
         ('', 'set-upstream-to', '', ''),
         ('d', 'delete', None, ''),
         ('D', 'delete', None, ''),
         ('m', 'move', None, ''),
         ('M', 'move', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command("bookmark")
 
     if opts.get('set_upstream') or opts.get('set_upstream_to'):
         ui.status(_("Mercurial has no concept of upstream branches\n"))
         return
     elif opts.get('delete'):
         cmd = Command("strip")
         for branch in args:
             cmd['-B'] = branch
         else:
             cmd['-B'] = None
     elif opts.get('move'):
         if len(args) > 0:
             if len(args) > 1:
                 old = args.pop(0)
             else:
                 # shell command to output the active bookmark for the active
                 # revision
                 old = '`hg log -T"{activebookmark}" -r .`'
         new = args[0]
         cmd['-m'] = old
         cmd.append(new)
     else:
         if len(args) > 1:
             cmd['-r'] = args[1]
             cmd.append(args[0])
         elif len(args) == 1:
             cmd.append(args[0])
     ui.status((bytes(cmd)), "\n")
 
 def ispath(repo, string):
     """
     The first argument to git checkout can either be a revision or a path. Let's
     generally assume it's a revision, unless it's obviously a path. There are
     too many ways to spell revisions in git for us to reasonably catch all of
     them, so let's be conservative.
     """
     if string in repo:
         # if it's definitely a revision let's not even check if a file of the
         # same name exists.
         return False
 
     cwd = repo.getcwd()
     if cwd == '':
         repopath = string
     else:
         repopath = cwd + '/' + string
 
     exists = repo.wvfs.exists(repopath)
     if exists:
         return True
 
     manifest = repo['.'].manifest()
 
     didexist = (repopath in manifest) or manifest.hasdir(repopath)
 
     return didexist
 
 def checkout(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('b', 'branch', '', ''),
         ('B', 'branch', '', ''),
         ('f', 'force', None, ''),
         ('p', 'patch', None, ''),
     ]
     paths = []
     if '--' in args:
         sepindex = args.index('--')
         paths.extend(args[sepindex + 1:])
         args = args[:sepindex]
 
     args, opts = parseoptions(ui, cmdoptions, args)
 
     rev = None
     if args and ispath(repo, args[0]):
         paths = args + paths
     elif args:
         rev = args[0]
         paths = args[1:] + paths
 
     cmd = Command('update')
 
     if opts.get('force'):
         if paths or rev:
             cmd['-C'] = None
 
     if opts.get('patch'):
         cmd = Command('revert')
         cmd['-i'] = None
 
     if opts.get('branch'):
         if len(args) == 0:
             cmd = Command('bookmark')
             cmd.append(opts.get('branch'))
         else:
             cmd.append(args[0])
             bookcmd = Command('bookmark')
             bookcmd.append(opts.get('branch'))
             cmd = cmd & bookcmd
     # if there is any path argument supplied, use revert instead of update
     elif len(paths) > 0:
         ui.status(_("note: use --no-backup to avoid creating .orig files\n\n"))
         cmd = Command('revert')
         if opts.get('patch'):
             cmd['-i'] = None
         if rev:
             cmd['-r'] = rev
         cmd.extend(paths)
     elif rev:
         if opts.get('patch'):
             cmd['-r'] = rev
         else:
             cmd.append(rev)
     elif opts.get('force'):
         cmd = Command('revert')
         cmd['--all'] = None
     else:
         raise error.Abort("a commit must be specified")
 
     ui.status((bytes(cmd)), "\n")
 
 def cherrypick(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('', 'continue', None, ''),
         ('', 'abort', None, ''),
         ('e', 'edit', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('graft')
 
     if opts.get('edit'):
         cmd['--edit'] = None
     if opts.get('continue'):
         cmd['--continue'] = None
     elif opts.get('abort'):
         ui.status(_("note: hg graft does not have --abort.\n\n"))
         return
     else:
         cmd.extend(args)
 
     ui.status((bytes(cmd)), "\n")
 
 def clean(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('d', 'd', None, ''),
         ('f', 'force', None, ''),
         ('x', 'x', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('purge')
     if opts.get('x'):
         cmd['--all'] = None
     cmd.extend(args)
 
     ui.status((bytes(cmd)), "\n")
 
 def clone(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('', 'bare', None, ''),
         ('n', 'no-checkout', None, ''),
         ('b', 'branch', '', ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     if len(args) == 0:
         raise error.Abort("a repository to clone must be specified")
 
     cmd = Command('clone')
     cmd.append(args[0])
     if len(args) > 1:
         cmd.append(args[1])
 
     if opts.get('bare'):
         cmd['-U'] = None
         ui.status(_("note: Mercurial does not have bare clones. " +
             "-U will clone the repo without checking out a commit\n\n"))
     elif opts.get('no_checkout'):
         cmd['-U'] = None
 
     if opts.get('branch'):
         cocmd = Command("update")
         cocmd.append(opts.get('branch'))
         cmd = cmd & cocmd
 
     ui.status((bytes(cmd)), "\n")
 
 def commit(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('a', 'all', None, ''),
         ('m', 'message', '', ''),
         ('p', 'patch', None, ''),
         ('C', 'reuse-message', '', ''),
         ('F', 'file', '', ''),
         ('', 'author', '', ''),
         ('', 'date', '', ''),
         ('', 'amend', None, ''),
         ('', 'no-edit', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('commit')
     if opts.get('patch'):
         cmd = Command('commit --interactive')
 
     if opts.get('amend'):
         if opts.get('no_edit'):
             cmd = Command('amend')
         else:
             cmd['--amend'] = None
 
     if opts.get('reuse_message'):
         cmd['-M'] = opts.get('reuse_message')
 
     if opts.get('message'):
         cmd['-m'] = "'%s'" % (opts.get('message'),)
 
     if opts.get('all'):
         ui.status(_("note: Mercurial doesn't have a staging area, " +
             "so there is no --all. -A will add and remove files " +
             "for you though.\n\n"))
 
     if opts.get('file'):
         cmd['-l'] = opts.get('file')
 
     if opts.get('author'):
         cmd['-u'] = opts.get('author')
 
     if opts.get('date'):
         cmd['-d'] = opts.get('date')
 
     cmd.extend(args)
 
     ui.status((bytes(cmd)), "\n")
 
 def deprecated(ui, repo, *args, **kwargs):
     ui.warn(_('This command has been deprecated in the git project, ' +
         'thus isn\'t supported by this tool.\n\n'))
 
 def diff(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('a', 'all', None, ''),
         ('', 'cached', None, ''),
         ('R', 'reverse', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('diff')
 
     if opts.get('cached'):
         ui.status(_('note: Mercurial has no concept of a staging area, ' +
             'so --cached does nothing.\n\n'))
 
     if opts.get('reverse'):
         cmd['--reverse'] = None
 
     for a in list(args):
         args.remove(a)
         try:
             repo.revs(a)
             cmd['-r'] = a
         except Exception:
             cmd.append(a)
 
     ui.status((bytes(cmd)), "\n")
 
 def difftool(ui, repo, *args, **kwargs):
     ui.status(_('Mercurial does not enable external difftool by default. You '
         'need to enable the extdiff extension in your .hgrc file by adding\n'
         'extdiff =\n'
         'to the [extensions] section and then running\n\n'
         'hg extdiff -p <program>\n\n'
         'See \'hg help extdiff\' and \'hg help -e extdiff\' for more '
         'information.\n'))
 
 def fetch(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('', 'all', None, ''),
         ('f', 'force', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('pull')
 
     if len(args) > 0:
         cmd.append(args[0])
         if len(args) > 1:
             ui.status(_("note: Mercurial doesn't have refspecs. " +
                 "-r can be used to specify which commits you want to pull. " +
                 "-B can be used to specify which bookmark you want to pull." +
                 "\n\n"))
             for v in args[1:]:
                 if v in repo._bookmarks:
                     cmd['-B'] = v
                 else:
                     cmd['-r'] = v
 
     ui.status((bytes(cmd)), "\n")
 
 def grep(ui, repo, *args, **kwargs):
     cmdoptions = [
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('grep')
 
     # For basic usage, git grep and hg grep are the same. They both have the
     # pattern first, followed by paths.
     cmd.extend(args)
 
     ui.status((bytes(cmd)), "\n")
 
 def init(ui, repo, *args, **kwargs):
     cmdoptions = [
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('init')
 
     if len(args) > 0:
         cmd.append(args[0])
 
     ui.status((bytes(cmd)), "\n")
 
 def log(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('', 'follow', None, ''),
         ('', 'decorate', None, ''),
         ('n', 'number', '', ''),
         ('1', '1', None, ''),
         ('', 'pretty', '', ''),
         ('', 'format', '', ''),
         ('', 'oneline', None, ''),
         ('', 'stat', None, ''),
         ('', 'graph', None, ''),
         ('p', 'patch', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
     ui.status(_('note: -v prints the entire commit message like Git does. To ' +
               'print just the first line, drop the -v.\n\n'))
     ui.status(_("note: see hg help revset for information on how to filter " +
         "log output.\n\n"))
 
     cmd = Command('log')
     cmd['-v'] = None
 
     if opts.get('number'):
         cmd['-l'] = opts.get('number')
     if opts.get('1'):
         cmd['-l'] = '1'
     if opts.get('stat'):
         cmd['--stat'] = None
     if opts.get('graph'):
         cmd['-G'] = None
     if opts.get('patch'):
         cmd['-p'] = None
 
     if opts.get('pretty') or opts.get('format') or opts.get('oneline'):
         format = opts.get('format', '')
         if 'format:' in format:
             ui.status(_("note: --format format:??? equates to Mercurial's " +
                 "--template. See hg help templates for more info.\n\n"))
             cmd['--template'] = '???'
         else:
             ui.status(_("note: --pretty/format/oneline equate to Mercurial's " +
                 "--style or --template. See hg help templates for more info." +
                 "\n\n"))
             cmd['--style'] = '???'
 
     if len(args) > 0:
         if '..' in args[0]:
             since, until = args[0].split('..')
             cmd['-r'] = "'%s::%s'" % (since, until)
             del args[0]
         cmd.extend(args)
 
     ui.status((bytes(cmd)), "\n")
 
 def lsfiles(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('c', 'cached', None, ''),
         ('d', 'deleted', None, ''),
         ('m', 'modified', None, ''),
         ('o', 'others', None, ''),
         ('i', 'ignored', None, ''),
         ('s', 'stage', None, ''),
         ('z', '_zero', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     if (opts.get('modified') or opts.get('deleted')
         or opts.get('others') or opts.get('ignored')):
         cmd = Command('status')
         if opts.get('deleted'):
             cmd['-d'] = None
         if opts.get('modified'):
             cmd['-m'] = None
         if opts.get('others'):
             cmd['-o'] = None
         if opts.get('ignored'):
             cmd['-i'] = None
     else:
         cmd = Command('files')
     if opts.get('stage'):
         ui.status(_("note: Mercurial doesn't have a staging area, ignoring "
                   "--stage\n"))
     if opts.get('_zero'):
         cmd['-0'] = None
     cmd.append('.')
     for include in args:
-        cmd['-I'] = util.shellquote(include)
+        cmd['-I'] = procutil.shellquote(include)
 
     ui.status((bytes(cmd)), "\n")
 
 def merge(ui, repo, *args, **kwargs):
     cmdoptions = [
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('merge')
 
     if len(args) > 0:
         cmd.append(args[len(args) - 1])
 
     ui.status((bytes(cmd)), "\n")
 
 def mergebase(ui, repo, *args, **kwargs):
     cmdoptions = []
     args, opts = parseoptions(ui, cmdoptions, args)
 
     if len(args) != 2:
         args = ['A', 'B']
 
     cmd = Command("log -T '{node}\\n' -r 'ancestor(%s,%s)'"
                   % (args[0], args[1]))
 
     ui.status(_('NOTE: ancestors() is part of the revset language.\n'),
               _("Learn more about revsets with 'hg help revsets'\n\n"))
     ui.status((bytes(cmd)), "\n")
 
 def mergetool(ui, repo, *args, **kwargs):
     cmdoptions = []
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command("resolve")
 
     if len(args) == 0:
         cmd['--all'] = None
     cmd.extend(args)
     ui.status((bytes(cmd)), "\n")
 
 def mv(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('f', 'force', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('mv')
     cmd.extend(args)
 
     if opts.get('force'):
         cmd['-f'] = None
 
     ui.status((bytes(cmd)), "\n")
 
 def pull(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('', 'all', None, ''),
         ('f', 'force', None, ''),
         ('r', 'rebase', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('pull')
     cmd['--rebase'] = None
 
     if len(args) > 0:
         cmd.append(args[0])
         if len(args) > 1:
             ui.status(_("note: Mercurial doesn't have refspecs. " +
                 "-r can be used to specify which commits you want to pull. " +
                 "-B can be used to specify which bookmark you want to pull." +
                 "\n\n"))
             for v in args[1:]:
                 if v in repo._bookmarks:
                     cmd['-B'] = v
                 else:
                     cmd['-r'] = v
 
     ui.status((bytes(cmd)), "\n")
 
 def push(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('', 'all', None, ''),
         ('f', 'force', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('push')
 
     if len(args) > 0:
         cmd.append(args[0])
         if len(args) > 1:
             ui.status(_("note: Mercurial doesn't have refspecs. " +
                 "-r can be used to specify which commits you want to push. " +
                 "-B can be used to specify which bookmark you want to push." +
                 "\n\n"))
             for v in args[1:]:
                 if v in repo._bookmarks:
                     cmd['-B'] = v
                 else:
                     cmd['-r'] = v
 
     if opts.get('force'):
         cmd['-f'] = None
 
     ui.status((bytes(cmd)), "\n")
 
 def rebase(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('', 'all', None, ''),
         ('i', 'interactive', None, ''),
         ('', 'onto', '', ''),
         ('', 'abort', None, ''),
         ('', 'continue', None, ''),
         ('', 'skip', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     if opts.get('interactive'):
         ui.status(_("note: hg histedit does not perform a rebase. " +
             "It just edits history.\n\n"))
         cmd = Command('histedit')
         if len(args) > 0:
             ui.status(_("also note: 'hg histedit' will automatically detect"
                       " your stack, so no second argument is necessary.\n\n"))
         ui.status((bytes(cmd)), "\n")
         return
 
     if opts.get('skip'):
         cmd = Command('revert --all -r .')
         ui.status((bytes(cmd)), "\n")
 
     cmd = Command('rebase')
 
     if opts.get('continue') or opts.get('skip'):
         cmd['--continue'] = None
     if opts.get('abort'):
         cmd['--abort'] = None
 
     if opts.get('onto'):
         ui.status(_("note: if you're trying to lift a commit off one branch, " +
             "try hg rebase -d <destination commit> -s <commit to be lifted>" +
             "\n\n"))
         cmd['-d'] = convert(opts.get('onto'))
         if len(args) < 2:
             raise error.Abort("Expected format: git rebase --onto X Y Z")
         cmd['-s'] = "'::%s - ::%s'" % (convert(args[1]), convert(args[0]))
     else:
         if len(args) == 1:
             cmd['-d'] = convert(args[0])
         elif len(args) == 2:
             cmd['-d'] = convert(args[0])
             cmd['-b'] = convert(args[1])
 
     ui.status((bytes(cmd)), "\n")
 
 def reflog(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('', 'all', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('journal')
     if opts.get('all'):
         cmd['--all'] = None
     if len(args) > 0:
         cmd.append(args[0])
 
     ui.status(bytes(cmd), "\n\n")
     ui.status(_("note: in hg commits can be deleted from repo but we always"
               " have backups.\n"))
 
 def reset(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('', 'soft', None, ''),
         ('', 'hard', None, ''),
         ('', 'mixed', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     commit = convert(args[0] if len(args) > 0 else '.')
     hard = opts.get('hard')
 
     if opts.get('mixed'):
         ui.status(_('NOTE: --mixed has no meaning since Mercurial has no '
                     'staging area\n\n'))
     if opts.get('soft'):
         ui.status(_('NOTE: --soft has no meaning since Mercurial has no '
                     'staging area\n\n'))
 
     cmd = Command('update')
     if hard:
         cmd.append('--clean')
 
     cmd.append(commit)
 
     ui.status((bytes(cmd)), "\n")
 
 def revert(ui, repo, *args, **kwargs):
     cmdoptions = [
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     if len(args) > 1:
         ui.status(_("note: hg backout doesn't support multiple commits at " +
                     "once\n\n"))
 
     cmd = Command('backout')
     if args:
         cmd.append(args[0])
 
     ui.status((bytes(cmd)), "\n")
 
 def revparse(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('', 'show-cdup', None, ''),
         ('', 'show-toplevel', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     if opts.get('show_cdup') or opts.get('show_toplevel'):
         cmd = Command('root')
         if opts.get('show_cdup'):
             ui.status(_("note: hg root prints the root of the repository\n\n"))
         ui.status((bytes(cmd)), "\n")
     else:
         ui.status(_("note: see hg help revset for how to refer to commits\n"))
 
 def rm(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('f', 'force', None, ''),
         ('n', 'dry-run', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('rm')
     cmd.extend(args)
 
     if opts.get('force'):
         cmd['-f'] = None
     if opts.get('dry_run'):
         cmd['-n'] = None
 
     ui.status((bytes(cmd)), "\n")
 
 def show(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('', 'name-status', None, ''),
         ('', 'pretty', '', ''),
         ('U', 'unified', int, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     if opts.get('name_status'):
         if opts.get('pretty') == 'format:':
             cmd = Command('status')
             cmd['--change'] = '.'
         else:
             cmd = Command('log')
             cmd.append('--style status')
             cmd.append('-r .')
     elif len(args) > 0:
         if ispath(repo, args[0]):
             cmd = Command('cat')
         else:
             cmd = Command('export')
         cmd.extend(args)
         if opts.get('unified'):
             cmd.append('--config diff.unified=%d' % (opts['unified'],))
     elif opts.get('unified'):
         cmd = Command('export')
         cmd.append('--config diff.unified=%d' % (opts['unified'],))
     else:
         cmd = Command('export')
 
     ui.status((bytes(cmd)), "\n")
 
 def stash(ui, repo, *args, **kwargs):
     cmdoptions = [
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('shelve')
     action = args[0] if len(args) > 0 else None
 
     if action == 'list':
         cmd['-l'] = None
     elif action == 'drop':
         cmd['-d'] = None
         if len(args) > 1:
             cmd.append(args[1])
         else:
             cmd.append('<shelve name>')
     elif action == 'pop' or action == 'apply':
         cmd = Command('unshelve')
         if len(args) > 1:
             cmd.append(args[1])
         if action == 'apply':
             cmd['--keep'] = None
     elif (action == 'branch' or action == 'show' or action == 'clear'
         or action == 'create'):
         ui.status(_("note: Mercurial doesn't have equivalents to the " +
             "git stash branch, show, clear, or create actions.\n\n"))
         return
     else:
         if len(args) > 0:
             if args[0] != 'save':
                 cmd['--name'] = args[0]
             elif len(args) > 1:
                 cmd['--name'] = args[1]
 
     ui.status((bytes(cmd)), "\n")
 
 def status(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('', 'ignored', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('status')
     cmd.extend(args)
 
     if opts.get('ignored'):
         cmd['-i'] = None
 
     ui.status((bytes(cmd)), "\n")
 
 def svn(ui, repo, *args, **kwargs):
     svncmd = args[0]
     if not svncmd in gitsvncommands:
         ui.warn(_("error: unknown git svn command %s\n") % (svncmd))
 
     args = args[1:]
     return gitsvncommands[svncmd](ui, repo, *args, **kwargs)
 
 def svndcommit(ui, repo, *args, **kwargs):
     cmdoptions = [
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('push')
 
     ui.status((bytes(cmd)), "\n")
 
 def svnfetch(ui, repo, *args, **kwargs):
     cmdoptions = [
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('pull')
     cmd.append('default-push')
 
     ui.status((bytes(cmd)), "\n")
 
 def svnfindrev(ui, repo, *args, **kwargs):
     cmdoptions = [
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     cmd = Command('log')
     cmd['-r'] = args[0]
 
     ui.status((bytes(cmd)), "\n")
 
 def svnrebase(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('l', 'local', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     pullcmd = Command('pull')
     pullcmd.append('default-push')
     rebasecmd = Command('rebase')
     rebasecmd.append('tip')
 
     cmd = pullcmd & rebasecmd
 
     ui.status((bytes(cmd)), "\n")
 
 def tag(ui, repo, *args, **kwargs):
     cmdoptions = [
         ('f', 'force', None, ''),
         ('l', 'list', None, ''),
         ('d', 'delete', None, ''),
     ]
     args, opts = parseoptions(ui, cmdoptions, args)
 
     if opts.get('list'):
         cmd = Command('tags')
     else:
         cmd = Command('tag')
         cmd.append(args[0])
         if len(args) > 1:
             cmd['-r'] = args[1]
 
         if opts.get('delete'):
             cmd['--remove'] = None
 
         if opts.get('force'):
             cmd['-f'] = None
 
     ui.status((bytes(cmd)), "\n")
 
 gitcommands = {
     'add': add,
     'am': am,
     'apply': apply,
     'bisect': bisect,
     'blame': blame,
     'branch': branch,
     'checkout': checkout,
     'cherry-pick': cherrypick,
     'clean': clean,
     'clone': clone,
     'commit': commit,
     'diff': diff,
     'difftool': difftool,
     'fetch': fetch,
     'grep': grep,
     'init': init,
     'log': log,
     'ls-files': lsfiles,
     'merge': merge,
     'merge-base': mergebase,
     'mergetool': mergetool,
     'mv': mv,
     'pull': pull,
     'push': push,
     'rebase': rebase,
     'reflog': reflog,
     'reset': reset,
     'revert': revert,
     'rev-parse': revparse,
     'rm': rm,
     'show': show,
     'stash': stash,
     'status': status,
     'svn': svn,
     'tag': tag,
     'whatchanged': deprecated,
 }
 
 gitsvncommands = {
     'dcommit': svndcommit,
     'fetch': svnfetch,
     'find-rev': svnfindrev,
     'rebase': svnrebase,
 }

hgext/gpg.py

@@ -1,328 +1,330
 # Copyright 2005, 2006 Benoit Boissinot <[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.
 
 '''commands to sign and verify changesets'''
 
 from __future__ import absolute_import
 
 import binascii
 import os
 import tempfile
 
 from mercurial.i18n import _
 from mercurial import (
     cmdutil,
     error,
     match,
     node as hgnode,
     pycompat,
     registrar,
-    util,
 )
-from mercurial.utils import dateutil
+from mercurial.utils import (
+    dateutil,
+    procutil,
+)
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('gpg', 'cmd',
     default='gpg',
 )
 configitem('gpg', 'key',
     default=None,
 )
 configitem('gpg', '.*',
     default=None,
     generic=True,
 )
 
 class gpg(object):
     def __init__(self, path, key=None):
         self.path = path
         self.key = (key and " --local-user \"%s\"" % key) or ""
 
     def sign(self, data):
         gpgcmd = "%s --sign --detach-sign%s" % (self.path, self.key)
-        return util.filter(data, gpgcmd)
+        return procutil.filter(data, gpgcmd)
 
     def verify(self, data, sig):
         """ returns of the good and bad signatures"""
         sigfile = datafile = None
         try:
             # create temporary files
             fd, sigfile = tempfile.mkstemp(prefix="hg-gpg-", suffix=".sig")
             fp = os.fdopen(fd, r'wb')
             fp.write(sig)
             fp.close()
             fd, datafile = tempfile.mkstemp(prefix="hg-gpg-", suffix=".txt")
             fp = os.fdopen(fd, r'wb')
             fp.write(data)
             fp.close()
             gpgcmd = ("%s --logger-fd 1 --status-fd 1 --verify "
                       "\"%s\" \"%s\"" % (self.path, sigfile, datafile))
-            ret = util.filter("", gpgcmd)
+            ret = procutil.filter("", gpgcmd)
         finally:
             for f in (sigfile, datafile):
                 try:
                     if f:
                         os.unlink(f)
                 except OSError:
                     pass
         keys = []
         key, fingerprint = None, None
         for l in ret.splitlines():
             # see DETAILS in the gnupg documentation
             # filter the logger output
             if not l.startswith("[GNUPG:]"):
                 continue
             l = l[9:]
             if l.startswith("VALIDSIG"):
                 # fingerprint of the primary key
                 fingerprint = l.split()[10]
             elif l.startswith("ERRSIG"):
                 key = l.split(" ", 3)[:2]
                 key.append("")
                 fingerprint = None
             elif (l.startswith("GOODSIG") or
                   l.startswith("EXPSIG") or
                   l.startswith("EXPKEYSIG") or
                   l.startswith("BADSIG")):
                 if key is not None:
                     keys.append(key + [fingerprint])
                 key = l.split(" ", 2)
                 fingerprint = None
         if key is not None:
             keys.append(key + [fingerprint])
         return keys
 
 def newgpg(ui, **opts):
     """create a new gpg instance"""
     gpgpath = ui.config("gpg", "cmd")
     gpgkey = opts.get(r'key')
     if not gpgkey:
         gpgkey = ui.config("gpg", "key")
     return gpg(gpgpath, gpgkey)
 
 def sigwalk(repo):
     """
     walk over every sigs, yields a couple
     ((node, version, sig), (filename, linenumber))
     """
     def parsefile(fileiter, context):
         ln = 1
         for l in fileiter:
             if not l:
                 continue
             yield (l.split(" ", 2), (context, ln))
             ln += 1
 
     # read the heads
     fl = repo.file(".hgsigs")
     for r in reversed(fl.heads()):
         fn = ".hgsigs|%s" % hgnode.short(r)
         for item in parsefile(fl.read(r).splitlines(), fn):
             yield item
     try:
         # read local signatures
         fn = "localsigs"
         for item in parsefile(repo.vfs(fn), fn):
             yield item
     except IOError:
         pass
 
 def getkeys(ui, repo, mygpg, sigdata, context):
     """get the keys who signed a data"""
     fn, ln = context
     node, version, sig = sigdata
     prefix = "%s:%d" % (fn, ln)
     node = hgnode.bin(node)
 
     data = node2txt(repo, node, version)
     sig = binascii.a2b_base64(sig)
     keys = mygpg.verify(data, sig)
 
     validkeys = []
     # warn for expired key and/or sigs
     for key in keys:
         if key[0] == "ERRSIG":
             ui.write(_("%s Unknown key ID \"%s\"\n") % (prefix, key[1]))
             continue
         if key[0] == "BADSIG":
             ui.write(_("%s Bad signature from \"%s\"\n") % (prefix, key[2]))
             continue
         if key[0] == "EXPSIG":
             ui.write(_("%s Note: Signature has expired"
                        " (signed by: \"%s\")\n") % (prefix, key[2]))
         elif key[0] == "EXPKEYSIG":
             ui.write(_("%s Note: This key has expired"
                        " (signed by: \"%s\")\n") % (prefix, key[2]))
         validkeys.append((key[1], key[2], key[3]))
     return validkeys
 
 @command("sigs", [], _('hg sigs'))
 def sigs(ui, repo):
     """list signed changesets"""
     mygpg = newgpg(ui)
     revs = {}
 
     for data, context in sigwalk(repo):
         node, version, sig = data
         fn, ln = context
         try:
             n = repo.lookup(node)
         except KeyError:
             ui.warn(_("%s:%d node does not exist\n") % (fn, ln))
             continue
         r = repo.changelog.rev(n)
         keys = getkeys(ui, repo, mygpg, data, context)
         if not keys:
             continue
         revs.setdefault(r, [])
         revs[r].extend(keys)
     for rev in sorted(revs, reverse=True):
         for k in revs[rev]:
             r = "%5d:%s" % (rev, hgnode.hex(repo.changelog.node(rev)))
             ui.write("%-30s %s\n" % (keystr(ui, k), r))
 
 @command("sigcheck", [], _('hg sigcheck REV'))
 def sigcheck(ui, repo, rev):
     """verify all the signatures there may be for a particular revision"""
     mygpg = newgpg(ui)
     rev = repo.lookup(rev)
     hexrev = hgnode.hex(rev)
     keys = []
 
     for data, context in sigwalk(repo):
         node, version, sig = data
         if node == hexrev:
             k = getkeys(ui, repo, mygpg, data, context)
             if k:
                 keys.extend(k)
 
     if not keys:
         ui.write(_("no valid signature for %s\n") % hgnode.short(rev))
         return
 
     # print summary
     ui.write(_("%s is signed by:\n") % hgnode.short(rev))
     for key in keys:
         ui.write(" %s\n" % keystr(ui, key))
 
 def keystr(ui, key):
     """associate a string to a key (username, comment)"""
     keyid, user, fingerprint = key
     comment = ui.config("gpg", fingerprint)
     if comment:
         return "%s (%s)" % (user, comment)
     else:
         return user
 
 @command("sign",
          [('l', 'local', None, _('make the signature local')),
           ('f', 'force', None, _('sign even if the sigfile is modified')),
           ('', 'no-commit', None, _('do not commit the sigfile after signing')),
           ('k', 'key', '',
            _('the key id to sign with'), _('ID')),
           ('m', 'message', '',
            _('use text as commit message'), _('TEXT')),
           ('e', 'edit', False, _('invoke editor on commit messages')),
          ] + cmdutil.commitopts2,
          _('hg sign [OPTION]... [REV]...'))
 def sign(ui, repo, *revs, **opts):
     """add a signature for the current or given revision
 
     If no revision is given, the parent of the working directory is used,
     or tip if no revision is checked out.
 
     The ``gpg.cmd`` config setting can be used to specify the command
     to run. A default key can be specified with ``gpg.key``.
 
     See :hg:`help dates` for a list of formats valid for -d/--date.
     """
     with repo.wlock():
         return _dosign(ui, repo, *revs, **opts)
 
 def _dosign(ui, repo, *revs, **opts):
     mygpg = newgpg(ui, **opts)
     opts = pycompat.byteskwargs(opts)
     sigver = "0"
     sigmessage = ""
 
     date = opts.get('date')
     if date:
         opts['date'] = dateutil.parsedate(date)
 
     if revs:
         nodes = [repo.lookup(n) for n in revs]
     else:
         nodes = [node for node in repo.dirstate.parents()
                  if node != hgnode.nullid]
         if len(nodes) > 1:
             raise error.Abort(_('uncommitted merge - please provide a '
                                'specific revision'))
         if not nodes:
             nodes = [repo.changelog.tip()]
 
     for n in nodes:
         hexnode = hgnode.hex(n)
         ui.write(_("signing %d:%s\n") % (repo.changelog.rev(n),
                                          hgnode.short(n)))
         # build data
         data = node2txt(repo, n, sigver)
         sig = mygpg.sign(data)
         if not sig:
             raise error.Abort(_("error while signing"))
         sig = binascii.b2a_base64(sig)
         sig = sig.replace("\n", "")
         sigmessage += "%s %s %s\n" % (hexnode, sigver, sig)
 
     # write it
     if opts['local']:
         repo.vfs.append("localsigs", sigmessage)
         return
 
     if not opts["force"]:
         msigs = match.exact(repo.root, '', ['.hgsigs'])
         if any(repo.status(match=msigs, unknown=True, ignored=True)):
             raise error.Abort(_("working copy of .hgsigs is changed "),
                              hint=_("please commit .hgsigs manually"))
 
     sigsfile = repo.wvfs(".hgsigs", "ab")
     sigsfile.write(sigmessage)
     sigsfile.close()
 
     if '.hgsigs' not in repo.dirstate:
         repo[None].add([".hgsigs"])
 
     if opts["no_commit"]:
         return
 
     message = opts['message']
     if not message:
         # we don't translate commit messages
         message = "\n".join(["Added signature for changeset %s"
                              % hgnode.short(n)
                              for n in nodes])
     try:
         editor = cmdutil.getcommiteditor(editform='gpg.sign',
                                          **pycompat.strkwargs(opts))
         repo.commit(message, opts['user'], opts['date'], match=msigs,
                     editor=editor)
     except ValueError as inst:
         raise error.Abort(pycompat.bytestr(inst))
 
 def node2txt(repo, node, ver):
     """map a manifest into some text"""
     if ver == "0":
         return "%s\n" % hgnode.hex(node)
     else:
         raise error.Abort(_("unknown signature version"))

hgext/journal.py

@@ -1,523 +1,524
 # journal.py
 #
 # Copyright 2014-2016 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 """track previous positions of bookmarks (EXPERIMENTAL)
 
 This extension adds a new command: `hg journal`, which shows you where
 bookmarks were previously located.
 
 """
 
 from __future__ import absolute_import
 
 import collections
 import errno
 import os
 import weakref
 
 from mercurial.i18n import _
 
 from mercurial import (
     bookmarks,
     cmdutil,
     dispatch,
     encoding,
     error,
     extensions,
     hg,
     localrepo,
     lock,
     logcmdutil,
     node,
     pycompat,
     registrar,
     util,
 )
 from mercurial.utils import (
     dateutil,
+    procutil,
     stringutil,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 # storage format version; increment when the format changes
 storageversion = 0
 
 # namespaces
 bookmarktype = 'bookmark'
 wdirparenttype = 'wdirparent'
 # In a shared repository, what shared feature name is used
 # to indicate this namespace is shared with the source?
 sharednamespaces = {
     bookmarktype: hg.sharedbookmarks,
 }
 
 # Journal recording, register hooks and storage object
 def extsetup(ui):
     extensions.wrapfunction(dispatch, 'runcommand', runcommand)
     extensions.wrapfunction(bookmarks.bmstore, '_write', recordbookmarks)
     extensions.wrapfilecache(
         localrepo.localrepository, 'dirstate', wrapdirstate)
     extensions.wrapfunction(hg, 'postshare', wrappostshare)
     extensions.wrapfunction(hg, 'copystore', unsharejournal)
 
 def reposetup(ui, repo):
     if repo.local():
         repo.journal = journalstorage(repo)
         repo._wlockfreeprefix.add('namejournal')
 
         dirstate, cached = localrepo.isfilecached(repo, 'dirstate')
         if cached:
             # already instantiated dirstate isn't yet marked as
             # "journal"-ing, even though repo.dirstate() was already
             # wrapped by own wrapdirstate()
             _setupdirstate(repo, dirstate)
 
 def runcommand(orig, lui, repo, cmd, fullargs, *args):
     """Track the command line options for recording in the journal"""
     journalstorage.recordcommand(*fullargs)
     return orig(lui, repo, cmd, fullargs, *args)
 
 def _setupdirstate(repo, dirstate):
     dirstate.journalstorage = repo.journal
     dirstate.addparentchangecallback('journal', recorddirstateparents)
 
 # hooks to record dirstate changes
 def wrapdirstate(orig, repo):
     """Make journal storage available to the dirstate object"""
     dirstate = orig(repo)
     if util.safehasattr(repo, 'journal'):
         _setupdirstate(repo, dirstate)
     return dirstate
 
 def recorddirstateparents(dirstate, old, new):
     """Records all dirstate parent changes in the journal."""
     old = list(old)
     new = list(new)
     if util.safehasattr(dirstate, 'journalstorage'):
         # only record two hashes if there was a merge
         oldhashes = old[:1] if old[1] == node.nullid else old
         newhashes = new[:1] if new[1] == node.nullid else new
         dirstate.journalstorage.record(
             wdirparenttype, '.', oldhashes, newhashes)
 
 # hooks to record bookmark changes (both local and remote)
 def recordbookmarks(orig, store, fp):
     """Records all bookmark changes in the journal."""
     repo = store._repo
     if util.safehasattr(repo, 'journal'):
         oldmarks = bookmarks.bmstore(repo)
         for mark, value in store.iteritems():
             oldvalue = oldmarks.get(mark, node.nullid)
             if value != oldvalue:
                 repo.journal.record(bookmarktype, mark, oldvalue, value)
     return orig(store, fp)
 
 # shared repository support
 def _readsharedfeatures(repo):
     """A set of shared features for this repository"""
     try:
         return set(repo.vfs.read('shared').splitlines())
     except IOError as inst:
         if inst.errno != errno.ENOENT:
             raise
         return set()
 
 def _mergeentriesiter(*iterables, **kwargs):
     """Given a set of sorted iterables, yield the next entry in merged order
 
     Note that by default entries go from most recent to oldest.
     """
     order = kwargs.pop(r'order', max)
     iterables = [iter(it) for it in iterables]
     # this tracks still active iterables; iterables are deleted as they are
     # exhausted, which is why this is a dictionary and why each entry also
     # stores the key. Entries are mutable so we can store the next value each
     # time.
     iterable_map = {}
     for key, it in enumerate(iterables):
         try:
             iterable_map[key] = [next(it), key, it]
         except StopIteration:
             # empty entry, can be ignored
             pass
 
     while iterable_map:
         value, key, it = order(iterable_map.itervalues())
         yield value
         try:
             iterable_map[key][0] = next(it)
         except StopIteration:
             # this iterable is empty, remove it from consideration
             del iterable_map[key]
 
 def wrappostshare(orig, sourcerepo, destrepo, **kwargs):
     """Mark this shared working copy as sharing journal information"""
     with destrepo.wlock():
         orig(sourcerepo, destrepo, **kwargs)
         with destrepo.vfs('shared', 'a') as fp:
             fp.write('journal\n')
 
 def unsharejournal(orig, ui, repo, repopath):
     """Copy shared journal entries into this repo when unsharing"""
     if (repo.path == repopath and repo.shared() and
             util.safehasattr(repo, 'journal')):
         sharedrepo = hg.sharedreposource(repo)
         sharedfeatures = _readsharedfeatures(repo)
         if sharedrepo and sharedfeatures > {'journal'}:
             # there is a shared repository and there are shared journal entries
             # to copy. move shared date over from source to destination but
             # move the local file first
             if repo.vfs.exists('namejournal'):
                 journalpath = repo.vfs.join('namejournal')
                 util.rename(journalpath, journalpath + '.bak')
             storage = repo.journal
             local = storage._open(
                 repo.vfs, filename='namejournal.bak', _newestfirst=False)
             shared = (
                 e for e in storage._open(sharedrepo.vfs, _newestfirst=False)
                 if sharednamespaces.get(e.namespace) in sharedfeatures)
             for entry in _mergeentriesiter(local, shared, order=min):
                 storage._write(repo.vfs, entry)
 
     return orig(ui, repo, repopath)
 
 class journalentry(collections.namedtuple(
         u'journalentry',
         u'timestamp user command namespace name oldhashes newhashes')):
     """Individual journal entry
 
     * timestamp: a mercurial (time, timezone) tuple
     * user: the username that ran the command
     * namespace: the entry namespace, an opaque string
     * name: the name of the changed item, opaque string with meaning in the
       namespace
     * command: the hg command that triggered this record
     * oldhashes: a tuple of one or more binary hashes for the old location
     * newhashes: a tuple of one or more binary hashes for the new location
 
     Handles serialisation from and to the storage format. Fields are
     separated by newlines, hashes are written out in hex separated by commas,
     timestamp and timezone are separated by a space.
 
     """
     @classmethod
     def fromstorage(cls, line):
         (time, user, command, namespace, name,
          oldhashes, newhashes) = line.split('\n')
         timestamp, tz = time.split()
         timestamp, tz = float(timestamp), int(tz)
         oldhashes = tuple(node.bin(hash) for hash in oldhashes.split(','))
         newhashes = tuple(node.bin(hash) for hash in newhashes.split(','))
         return cls(
             (timestamp, tz), user, command, namespace, name,
             oldhashes, newhashes)
 
     def __bytes__(self):
         """bytes representation for storage"""
         time = ' '.join(map(str, self.timestamp))
         oldhashes = ','.join([node.hex(hash) for hash in self.oldhashes])
         newhashes = ','.join([node.hex(hash) for hash in self.newhashes])
         return '\n'.join((
             time, self.user, self.command, self.namespace, self.name,
             oldhashes, newhashes))
 
     __str__ = encoding.strmethod(__bytes__)
 
 class journalstorage(object):
     """Storage for journal entries
 
     Entries are divided over two files; one with entries that pertain to the
     local working copy *only*, and one with entries that are shared across
     multiple working copies when shared using the share extension.
 
     Entries are stored with NUL bytes as separators. See the journalentry
     class for the per-entry structure.
 
     The file format starts with an integer version, delimited by a NUL.
 
     This storage uses a dedicated lock; this makes it easier to avoid issues
     with adding entries that added when the regular wlock is unlocked (e.g.
     the dirstate).
 
     """
     _currentcommand = ()
     _lockref = None
 
     def __init__(self, repo):
-        self.user = util.getuser()
+        self.user = procutil.getuser()
         self.ui = repo.ui
         self.vfs = repo.vfs
 
         # is this working copy using a shared storage?
         self.sharedfeatures = self.sharedvfs = None
         if repo.shared():
             features = _readsharedfeatures(repo)
             sharedrepo = hg.sharedreposource(repo)
             if sharedrepo is not None and 'journal' in features:
                 self.sharedvfs = sharedrepo.vfs
                 self.sharedfeatures = features
 
     # track the current command for recording in journal entries
     @property
     def command(self):
         commandstr = ' '.join(
-            map(util.shellquote, journalstorage._currentcommand))
+            map(procutil.shellquote, journalstorage._currentcommand))
         if '\n' in commandstr:
             # truncate multi-line commands
             commandstr = commandstr.partition('\n')[0] + ' ...'
         return commandstr
 
     @classmethod
     def recordcommand(cls, *fullargs):
         """Set the current hg arguments, stored with recorded entries"""
         # Set the current command on the class because we may have started
         # with a non-local repo (cloning for example).
         cls._currentcommand = fullargs
 
     def _currentlock(self, lockref):
         """Returns the lock if it's held, or None if it's not.
 
         (This is copied from the localrepo class)
         """
         if lockref is None:
             return None
         l = lockref()
         if l is None or not l.held:
             return None
         return l
 
     def jlock(self, vfs):
         """Create a lock for the journal file"""
         if self._currentlock(self._lockref) is not None:
             raise error.Abort(_('journal lock does not support nesting'))
         desc = _('journal of %s') % vfs.base
         try:
             l = lock.lock(vfs, 'namejournal.lock', 0, desc=desc)
         except error.LockHeld as inst:
             self.ui.warn(
                 _("waiting for lock on %s held by %r\n") % (desc, inst.locker))
             # default to 600 seconds timeout
             l = lock.lock(
                 vfs, 'namejournal.lock',
                 self.ui.configint("ui", "timeout"), desc=desc)
             self.ui.warn(_("got lock after %s seconds\n") % l.delay)
         self._lockref = weakref.ref(l)
         return l
 
     def record(self, namespace, name, oldhashes, newhashes):
         """Record a new journal entry
 
         * namespace: an opaque string; this can be used to filter on the type
           of recorded entries.
         * name: the name defining this entry; for bookmarks, this is the
           bookmark name. Can be filtered on when retrieving entries.
         * oldhashes and newhashes: each a single binary hash, or a list of
           binary hashes. These represent the old and new position of the named
           item.
 
         """
         if not isinstance(oldhashes, list):
             oldhashes = [oldhashes]
         if not isinstance(newhashes, list):
             newhashes = [newhashes]
 
         entry = journalentry(
             dateutil.makedate(), self.user, self.command, namespace, name,
             oldhashes, newhashes)
 
         vfs = self.vfs
         if self.sharedvfs is not None:
             # write to the shared repository if this feature is being
             # shared between working copies.
             if sharednamespaces.get(namespace) in self.sharedfeatures:
                 vfs = self.sharedvfs
 
         self._write(vfs, entry)
 
     def _write(self, vfs, entry):
         with self.jlock(vfs):
             version = None
             # open file in amend mode to ensure it is created if missing
             with vfs('namejournal', mode='a+b') as f:
                 f.seek(0, os.SEEK_SET)
                 # Read just enough bytes to get a version number (up to 2
                 # digits plus separator)
                 version = f.read(3).partition('\0')[0]
                 if version and version != "%d" % storageversion:
                     # different version of the storage. Exit early (and not
                     # write anything) if this is not a version we can handle or
                     # the file is corrupt. In future, perhaps rotate the file
                     # instead?
                     self.ui.warn(
                         _("unsupported journal file version '%s'\n") % version)
                     return
                 if not version:
                     # empty file, write version first
                     f.write(("%d" % storageversion) + '\0')
                 f.seek(0, os.SEEK_END)
                 f.write(bytes(entry) + '\0')
 
     def filtered(self, namespace=None, name=None):
         """Yield all journal entries with the given namespace or name
 
         Both the namespace and the name are optional; if neither is given all
         entries in the journal are produced.
 
         Matching supports regular expressions by using the `re:` prefix
         (use `literal:` to match names or namespaces that start with `re:`)
 
         """
         if namespace is not None:
             namespace = stringutil.stringmatcher(namespace)[-1]
         if name is not None:
             name = stringutil.stringmatcher(name)[-1]
         for entry in self:
             if namespace is not None and not namespace(entry.namespace):
                 continue
             if name is not None and not name(entry.name):
                 continue
             yield entry
 
     def __iter__(self):
         """Iterate over the storage
 
         Yields journalentry instances for each contained journal record.
 
         """
         local = self._open(self.vfs)
 
         if self.sharedvfs is None:
             return local
 
         # iterate over both local and shared entries, but only those
         # shared entries that are among the currently shared features
         shared = (
             e for e in self._open(self.sharedvfs)
             if sharednamespaces.get(e.namespace) in self.sharedfeatures)
         return _mergeentriesiter(local, shared)
 
     def _open(self, vfs, filename='namejournal', _newestfirst=True):
         if not vfs.exists(filename):
             return
 
         with vfs(filename) as f:
             raw = f.read()
 
         lines = raw.split('\0')
         version = lines and lines[0]
         if version != "%d" % storageversion:
             version = version or _('not available')
             raise error.Abort(_("unknown journal file version '%s'") % version)
 
         # Skip the first line, it's a version number. Normally we iterate over
         # these in reverse order to list newest first; only when copying across
         # a shared storage do we forgo reversing.
         lines = lines[1:]
         if _newestfirst:
             lines = reversed(lines)
         for line in lines:
             if not line:
                 continue
             yield journalentry.fromstorage(line)
 
 # journal reading
 # log options that don't make sense for journal
 _ignoreopts = ('no-merges', 'graph')
 @command(
     'journal', [
         ('', 'all', None, 'show history for all names'),
         ('c', 'commits', None, 'show commit metadata'),
     ] + [opt for opt in cmdutil.logopts if opt[1] not in _ignoreopts],
     '[OPTION]... [BOOKMARKNAME]')
 def journal(ui, repo, *args, **opts):
     """show the previous position of bookmarks and the working copy
 
     The journal is used to see the previous commits that bookmarks and the
     working copy pointed to. By default the previous locations for the working
     copy.  Passing a bookmark name will show all the previous positions of
     that bookmark. Use the --all switch to show previous locations for all
     bookmarks and the working copy; each line will then include the bookmark
     name, or '.' for the working copy, as well.
 
     If `name` starts with `re:`, the remainder of the name is treated as
     a regular expression. To match a name that actually starts with `re:`,
     use the prefix `literal:`.
 
     By default hg journal only shows the commit hash and the command that was
     running at that time. -v/--verbose will show the prior hash, the user, and
     the time at which it happened.
 
     Use -c/--commits to output log information on each commit hash; at this
     point you can use the usual `--patch`, `--git`, `--stat` and `--template`
     switches to alter the log output for these.
 
     `hg journal -T json` can be used to produce machine readable output.
 
     """
     opts = pycompat.byteskwargs(opts)
     name = '.'
     if opts.get('all'):
         if args:
             raise error.Abort(
                 _("You can't combine --all and filtering on a name"))
         name = None
     if args:
         name = args[0]
 
     fm = ui.formatter('journal', opts)
 
     if opts.get("template") != "json":
         if name is None:
             displayname = _('the working copy and bookmarks')
         else:
             displayname = "'%s'" % name
         ui.status(_("previous locations of %s:\n") % displayname)
 
     limit = logcmdutil.getlimit(opts)
     entry = None
     ui.pager('journal')
     for count, entry in enumerate(repo.journal.filtered(name=name)):
         if count == limit:
             break
         newhashesstr = fm.formatlist(map(fm.hexfunc, entry.newhashes),
                                      name='node', sep=',')
         oldhashesstr = fm.formatlist(map(fm.hexfunc, entry.oldhashes),
                                      name='node', sep=',')
 
         fm.startitem()
         fm.condwrite(ui.verbose, 'oldhashes', '%s -> ', oldhashesstr)
         fm.write('newhashes', '%s', newhashesstr)
         fm.condwrite(ui.verbose, 'user', ' %-8s', entry.user)
         fm.condwrite(
             opts.get('all') or name.startswith('re:'),
             'name', '  %-8s', entry.name)
 
         timestring = fm.formatdate(entry.timestamp, '%Y-%m-%d %H:%M %1%2')
         fm.condwrite(ui.verbose, 'date', ' %s', timestring)
         fm.write('command', '  %s\n', entry.command)
 
         if opts.get("commits"):
             displayer = logcmdutil.changesetdisplayer(ui, repo, opts)
             for hash in entry.newhashes:
                 try:
                     ctx = repo[hash]
                     displayer.show(ctx)
                 except error.RepoLookupError as e:
                     fm.write('repolookuperror', "%s\n\n", pycompat.bytestr(e))
             displayer.close()
 
     fm.end()
 
     if entry is None:
         ui.status(_("no recorded locations\n"))

hgext/transplant.py

@@ -1,764 +1,766
 # Patch transplanting extension for Mercurial
 #
 # Copyright 2006, 2007 Brendan Cully <[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.
 
 '''command to transplant changesets from another branch
 
 This extension allows you to transplant changes to another parent revision,
 possibly in another repository. The transplant is done using 'diff' patches.
 
 Transplanted patches are recorded in .hg/transplant/transplants, as a
 map from a changeset hash to its hash in the source repository.
 '''
 from __future__ import absolute_import
 
 import os
 import tempfile
 from mercurial.i18n import _
 from mercurial import (
     bundlerepo,
     cmdutil,
     error,
     exchange,
     hg,
     logcmdutil,
     match,
     merge,
     node as nodemod,
     patch,
     pycompat,
     registrar,
     revlog,
     revset,
     scmutil,
     smartset,
     util,
     vfs as vfsmod,
 )
 from mercurial.utils import (
+    procutil,
     stringutil,
 )
 
 class TransplantError(error.Abort):
     pass
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = 'ships-with-hg-core'
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem('transplant', 'filter',
     default=None,
 )
 configitem('transplant', 'log',
     default=None,
 )
 
 class transplantentry(object):
     def __init__(self, lnode, rnode):
         self.lnode = lnode
         self.rnode = rnode
 
 class transplants(object):
     def __init__(self, path=None, transplantfile=None, opener=None):
         self.path = path
         self.transplantfile = transplantfile
         self.opener = opener
 
         if not opener:
             self.opener = vfsmod.vfs(self.path)
         self.transplants = {}
         self.dirty = False
         self.read()
 
     def read(self):
         abspath = os.path.join(self.path, self.transplantfile)
         if self.transplantfile and os.path.exists(abspath):
             for line in self.opener.read(self.transplantfile).splitlines():
                 lnode, rnode = map(revlog.bin, line.split(':'))
                 list = self.transplants.setdefault(rnode, [])
                 list.append(transplantentry(lnode, rnode))
 
     def write(self):
         if self.dirty and self.transplantfile:
             if not os.path.isdir(self.path):
                 os.mkdir(self.path)
             fp = self.opener(self.transplantfile, 'w')
             for list in self.transplants.itervalues():
                 for t in list:
                     l, r = map(nodemod.hex, (t.lnode, t.rnode))
                     fp.write(l + ':' + r + '\n')
             fp.close()
         self.dirty = False
 
     def get(self, rnode):
         return self.transplants.get(rnode) or []
 
     def set(self, lnode, rnode):
         list = self.transplants.setdefault(rnode, [])
         list.append(transplantentry(lnode, rnode))
         self.dirty = True
 
     def remove(self, transplant):
         list = self.transplants.get(transplant.rnode)
         if list:
             del list[list.index(transplant)]
             self.dirty = True
 
 class transplanter(object):
     def __init__(self, ui, repo, opts):
         self.ui = ui
         self.path = repo.vfs.join('transplant')
         self.opener = vfsmod.vfs(self.path)
         self.transplants = transplants(self.path, 'transplants',
                                        opener=self.opener)
         def getcommiteditor():
             editform = cmdutil.mergeeditform(repo[None], 'transplant')
             return cmdutil.getcommiteditor(editform=editform,
                                            **pycompat.strkwargs(opts))
         self.getcommiteditor = getcommiteditor
 
     def applied(self, repo, node, parent):
         '''returns True if a node is already an ancestor of parent
         or is parent or has already been transplanted'''
         if hasnode(repo, parent):
             parentrev = repo.changelog.rev(parent)
         if hasnode(repo, node):
             rev = repo.changelog.rev(node)
             reachable = repo.changelog.ancestors([parentrev], rev,
                                                  inclusive=True)
             if rev in reachable:
                 return True
         for t in self.transplants.get(node):
             # it might have been stripped
             if not hasnode(repo, t.lnode):
                 self.transplants.remove(t)
                 return False
             lnoderev = repo.changelog.rev(t.lnode)
             if lnoderev in repo.changelog.ancestors([parentrev], lnoderev,
                                                     inclusive=True):
                 return True
         return False
 
     def apply(self, repo, source, revmap, merges, opts=None):
         '''apply the revisions in revmap one by one in revision order'''
         if opts is None:
             opts = {}
         revs = sorted(revmap)
         p1, p2 = repo.dirstate.parents()
         pulls = []
         diffopts = patch.difffeatureopts(self.ui, opts)
         diffopts.git = True
 
         lock = tr = None
         try:
             lock = repo.lock()
             tr = repo.transaction('transplant')
             for rev in revs:
                 node = revmap[rev]
                 revstr = '%d:%s' % (rev, nodemod.short(node))
 
                 if self.applied(repo, node, p1):
                     self.ui.warn(_('skipping already applied revision %s\n') %
                                  revstr)
                     continue
 
                 parents = source.changelog.parents(node)
                 if not (opts.get('filter') or opts.get('log')):
                     # If the changeset parent is the same as the
                     # wdir's parent, just pull it.
                     if parents[0] == p1:
                         pulls.append(node)
                         p1 = node
                         continue
                     if pulls:
                         if source != repo:
                             exchange.pull(repo, source.peer(), heads=pulls)
                         merge.update(repo, pulls[-1], False, False)
                         p1, p2 = repo.dirstate.parents()
                         pulls = []
 
                 domerge = False
                 if node in merges:
                     # pulling all the merge revs at once would mean we
                     # couldn't transplant after the latest even if
                     # transplants before them fail.
                     domerge = True
                     if not hasnode(repo, node):
                         exchange.pull(repo, source.peer(), heads=[node])
 
                 skipmerge = False
                 if parents[1] != revlog.nullid:
                     if not opts.get('parent'):
                         self.ui.note(_('skipping merge changeset %d:%s\n')
                                      % (rev, nodemod.short(node)))
                         skipmerge = True
                     else:
                         parent = source.lookup(opts['parent'])
                         if parent not in parents:
                             raise error.Abort(_('%s is not a parent of %s') %
                                               (nodemod.short(parent),
                                                nodemod.short(node)))
                 else:
                     parent = parents[0]
 
                 if skipmerge:
                     patchfile = None
                 else:
                     fd, patchfile = tempfile.mkstemp(prefix='hg-transplant-')
                     fp = os.fdopen(fd, r'wb')
                     gen = patch.diff(source, parent, node, opts=diffopts)
                     for chunk in gen:
                         fp.write(chunk)
                     fp.close()
 
                 del revmap[rev]
                 if patchfile or domerge:
                     try:
                         try:
                             n = self.applyone(repo, node,
                                               source.changelog.read(node),
                                               patchfile, merge=domerge,
                                               log=opts.get('log'),
                                               filter=opts.get('filter'))
                         except TransplantError:
                             # Do not rollback, it is up to the user to
                             # fix the merge or cancel everything
                             tr.close()
                             raise
                         if n and domerge:
                             self.ui.status(_('%s merged at %s\n') % (revstr,
                                       nodemod.short(n)))
                         elif n:
                             self.ui.status(_('%s transplanted to %s\n')
                                            % (nodemod.short(node),
                                               nodemod.short(n)))
                     finally:
                         if patchfile:
                             os.unlink(patchfile)
             tr.close()
             if pulls:
                 exchange.pull(repo, source.peer(), heads=pulls)
                 merge.update(repo, pulls[-1], False, False)
         finally:
             self.saveseries(revmap, merges)
             self.transplants.write()
             if tr:
                 tr.release()
             if lock:
                 lock.release()
 
     def filter(self, filter, node, changelog, patchfile):
         '''arbitrarily rewrite changeset before applying it'''
 
         self.ui.status(_('filtering %s\n') % patchfile)
         user, date, msg = (changelog[1], changelog[2], changelog[4])
         fd, headerfile = tempfile.mkstemp(prefix='hg-transplant-')
         fp = os.fdopen(fd, r'wb')
         fp.write("# HG changeset patch\n")
         fp.write("# User %s\n" % user)
         fp.write("# Date %d %d\n" % date)
         fp.write(msg + '\n')
         fp.close()
 
         try:
-            self.ui.system('%s %s %s' % (filter, util.shellquote(headerfile),
-                                         util.shellquote(patchfile)),
+            self.ui.system('%s %s %s' % (filter,
+                                         procutil.shellquote(headerfile),
+                                         procutil.shellquote(patchfile)),
                            environ={'HGUSER': changelog[1],
                                     'HGREVISION': nodemod.hex(node),
                                     },
                            onerr=error.Abort, errprefix=_('filter failed'),
                            blockedtag='transplant_filter')
             user, date, msg = self.parselog(open(headerfile, 'rb'))[1:4]
         finally:
             os.unlink(headerfile)
 
         return (user, date, msg)
 
     def applyone(self, repo, node, cl, patchfile, merge=False, log=False,
                  filter=None):
         '''apply the patch in patchfile to the repository as a transplant'''
         (manifest, user, (time, timezone), files, message) = cl[:5]
         date = "%d %d" % (time, timezone)
         extra = {'transplant_source': node}
         if filter:
             (user, date, message) = self.filter(filter, node, cl, patchfile)
 
         if log:
             # we don't translate messages inserted into commits
             message += '\n(transplanted from %s)' % nodemod.hex(node)
 
         self.ui.status(_('applying %s\n') % nodemod.short(node))
         self.ui.note('%s %s\n%s\n' % (user, date, message))
 
         if not patchfile and not merge:
             raise error.Abort(_('can only omit patchfile if merging'))
         if patchfile:
             try:
                 files = set()
                 patch.patch(self.ui, repo, patchfile, files=files, eolmode=None)
                 files = list(files)
             except Exception as inst:
                 seriespath = os.path.join(self.path, 'series')
                 if os.path.exists(seriespath):
                     os.unlink(seriespath)
                 p1 = repo.dirstate.p1()
                 p2 = node
                 self.log(user, date, message, p1, p2, merge=merge)
                 self.ui.write(stringutil.forcebytestr(inst) + '\n')
                 raise TransplantError(_('fix up the working directory and run '
                                         'hg transplant --continue'))
         else:
             files = None
         if merge:
             p1, p2 = repo.dirstate.parents()
             repo.setparents(p1, node)
             m = match.always(repo.root, '')
         else:
             m = match.exact(repo.root, '', files)
 
         n = repo.commit(message, user, date, extra=extra, match=m,
                         editor=self.getcommiteditor())
         if not n:
             self.ui.warn(_('skipping emptied changeset %s\n') %
                            nodemod.short(node))
             return None
         if not merge:
             self.transplants.set(n, node)
 
         return n
 
     def canresume(self):
         return os.path.exists(os.path.join(self.path, 'journal'))
 
     def resume(self, repo, source, opts):
         '''recover last transaction and apply remaining changesets'''
         if os.path.exists(os.path.join(self.path, 'journal')):
             n, node = self.recover(repo, source, opts)
             if n:
                 self.ui.status(_('%s transplanted as %s\n') %
                                  (nodemod.short(node),
                                   nodemod.short(n)))
             else:
                 self.ui.status(_('%s skipped due to empty diff\n')
                                % (nodemod.short(node),))
         seriespath = os.path.join(self.path, 'series')
         if not os.path.exists(seriespath):
             self.transplants.write()
             return
         nodes, merges = self.readseries()
         revmap = {}
         for n in nodes:
             revmap[source.changelog.rev(n)] = n
         os.unlink(seriespath)
 
         self.apply(repo, source, revmap, merges, opts)
 
     def recover(self, repo, source, opts):
         '''commit working directory using journal metadata'''
         node, user, date, message, parents = self.readlog()
         merge = False
 
         if not user or not date or not message or not parents[0]:
             raise error.Abort(_('transplant log file is corrupt'))
 
         parent = parents[0]
         if len(parents) > 1:
             if opts.get('parent'):
                 parent = source.lookup(opts['parent'])
                 if parent not in parents:
                     raise error.Abort(_('%s is not a parent of %s') %
                                       (nodemod.short(parent),
                                        nodemod.short(node)))
             else:
                 merge = True
 
         extra = {'transplant_source': node}
         try:
             p1, p2 = repo.dirstate.parents()
             if p1 != parent:
                 raise error.Abort(_('working directory not at transplant '
                                    'parent %s') % nodemod.hex(parent))
             if merge:
                 repo.setparents(p1, parents[1])
             modified, added, removed, deleted = repo.status()[:4]
             if merge or modified or added or removed or deleted:
                 n = repo.commit(message, user, date, extra=extra,
                                 editor=self.getcommiteditor())
                 if not n:
                     raise error.Abort(_('commit failed'))
                 if not merge:
                     self.transplants.set(n, node)
             else:
                 n = None
             self.unlog()
 
             return n, node
         finally:
             # TODO: get rid of this meaningless try/finally enclosing.
             # this is kept only to reduce changes in a patch.
             pass
 
     def readseries(self):
         nodes = []
         merges = []
         cur = nodes
         for line in self.opener.read('series').splitlines():
             if line.startswith('# Merges'):
                 cur = merges
                 continue
             cur.append(revlog.bin(line))
 
         return (nodes, merges)
 
     def saveseries(self, revmap, merges):
         if not revmap:
             return
 
         if not os.path.isdir(self.path):
             os.mkdir(self.path)
         series = self.opener('series', 'w')
         for rev in sorted(revmap):
             series.write(nodemod.hex(revmap[rev]) + '\n')
         if merges:
             series.write('# Merges\n')
             for m in merges:
                 series.write(nodemod.hex(m) + '\n')
         series.close()
 
     def parselog(self, fp):
         parents = []
         message = []
         node = revlog.nullid
         inmsg = False
         user = None
         date = None
         for line in fp.read().splitlines():
             if inmsg:
                 message.append(line)
             elif line.startswith('# User '):
                 user = line[7:]
             elif line.startswith('# Date '):
                 date = line[7:]
             elif line.startswith('# Node ID '):
                 node = revlog.bin(line[10:])
             elif line.startswith('# Parent '):
                 parents.append(revlog.bin(line[9:]))
             elif not line.startswith('# '):
                 inmsg = True
                 message.append(line)
         if None in (user, date):
             raise error.Abort(_("filter corrupted changeset (no user or date)"))
         return (node, user, date, '\n'.join(message), parents)
 
     def log(self, user, date, message, p1, p2, merge=False):
         '''journal changelog metadata for later recover'''
 
         if not os.path.isdir(self.path):
             os.mkdir(self.path)
         fp = self.opener('journal', 'w')
         fp.write('# User %s\n' % user)
         fp.write('# Date %s\n' % date)
         fp.write('# Node ID %s\n' % nodemod.hex(p2))
         fp.write('# Parent ' + nodemod.hex(p1) + '\n')
         if merge:
             fp.write('# Parent ' + nodemod.hex(p2) + '\n')
         fp.write(message.rstrip() + '\n')
         fp.close()
 
     def readlog(self):
         return self.parselog(self.opener('journal'))
 
     def unlog(self):
         '''remove changelog journal'''
         absdst = os.path.join(self.path, 'journal')
         if os.path.exists(absdst):
             os.unlink(absdst)
 
     def transplantfilter(self, repo, source, root):
         def matchfn(node):
             if self.applied(repo, node, root):
                 return False
             if source.changelog.parents(node)[1] != revlog.nullid:
                 return False
             extra = source.changelog.read(node)[5]
             cnode = extra.get('transplant_source')
             if cnode and self.applied(repo, cnode, root):
                 return False
             return True
 
         return matchfn
 
 def hasnode(repo, node):
     try:
         return repo.changelog.rev(node) is not None
     except error.RevlogError:
         return False
 
 def browserevs(ui, repo, nodes, opts):
     '''interactively transplant changesets'''
     displayer = logcmdutil.changesetdisplayer(ui, repo, opts)
     transplants = []
     merges = []
     prompt = _('apply changeset? [ynmpcq?]:'
                '$$ &yes, transplant this changeset'
                '$$ &no, skip this changeset'
                '$$ &merge at this changeset'
                '$$ show &patch'
                '$$ &commit selected changesets'
                '$$ &quit and cancel transplant'
                '$$ &? (show this help)')
     for node in nodes:
         displayer.show(repo[node])
         action = None
         while not action:
             action = 'ynmpcq?'[ui.promptchoice(prompt)]
             if action == '?':
                 for c, t in ui.extractchoices(prompt)[1]:
                     ui.write('%s: %s\n' % (c, t))
                 action = None
             elif action == 'p':
                 parent = repo.changelog.parents(node)[0]
                 for chunk in patch.diff(repo, parent, node):
                     ui.write(chunk)
                 action = None
         if action == 'y':
             transplants.append(node)
         elif action == 'm':
             merges.append(node)
         elif action == 'c':
             break
         elif action == 'q':
             transplants = ()
             merges = ()
             break
     displayer.close()
     return (transplants, merges)
 
 @command('transplant',
     [('s', 'source', '', _('transplant changesets from REPO'), _('REPO')),
     ('b', 'branch', [], _('use this source changeset as head'), _('REV')),
     ('a', 'all', None, _('pull all changesets up to the --branch revisions')),
     ('p', 'prune', [], _('skip over REV'), _('REV')),
     ('m', 'merge', [], _('merge at REV'), _('REV')),
     ('', 'parent', '',
      _('parent to choose when transplanting merge'), _('REV')),
     ('e', 'edit', False, _('invoke editor on commit messages')),
     ('', 'log', None, _('append transplant info to log message')),
     ('c', 'continue', None, _('continue last transplant session '
                               'after fixing conflicts')),
     ('', 'filter', '',
      _('filter changesets through command'), _('CMD'))],
     _('hg transplant [-s REPO] [-b BRANCH [-a]] [-p REV] '
       '[-m REV] [REV]...'))
 def transplant(ui, repo, *revs, **opts):
     '''transplant changesets from another branch
 
     Selected changesets will be applied on top of the current working
     directory with the log of the original changeset. The changesets
     are copied and will thus appear twice in the history with different
     identities.
 
     Consider using the graft command if everything is inside the same
     repository - it will use merges and will usually give a better result.
     Use the rebase extension if the changesets are unpublished and you want
     to move them instead of copying them.
 
     If --log is specified, log messages will have a comment appended
     of the form::
 
       (transplanted from CHANGESETHASH)
 
     You can rewrite the changelog message with the --filter option.
     Its argument will be invoked with the current changelog message as
     $1 and the patch as $2.
 
     --source/-s specifies another repository to use for selecting changesets,
     just as if it temporarily had been pulled.
     If --branch/-b is specified, these revisions will be used as
     heads when deciding which changesets to transplant, just as if only
     these revisions had been pulled.
     If --all/-a is specified, all the revisions up to the heads specified
     with --branch will be transplanted.
 
     Example:
 
     - transplant all changes up to REV on top of your current revision::
 
         hg transplant --branch REV --all
 
     You can optionally mark selected transplanted changesets as merge
     changesets. You will not be prompted to transplant any ancestors
     of a merged transplant, and you can merge descendants of them
     normally instead of transplanting them.
 
     Merge changesets may be transplanted directly by specifying the
     proper parent changeset by calling :hg:`transplant --parent`.
 
     If no merges or revisions are provided, :hg:`transplant` will
     start an interactive changeset browser.
 
     If a changeset application fails, you can fix the merge by hand
     and then resume where you left off by calling :hg:`transplant
     --continue/-c`.
     '''
     with repo.wlock():
         return _dotransplant(ui, repo, *revs, **opts)
 
 def _dotransplant(ui, repo, *revs, **opts):
     def incwalk(repo, csets, match=util.always):
         for node in csets:
             if match(node):
                 yield node
 
     def transplantwalk(repo, dest, heads, match=util.always):
         '''Yield all nodes that are ancestors of a head but not ancestors
         of dest.
         If no heads are specified, the heads of repo will be used.'''
         if not heads:
             heads = repo.heads()
         ancestors = []
         ctx = repo[dest]
         for head in heads:
             ancestors.append(ctx.ancestor(repo[head]).node())
         for node in repo.changelog.nodesbetween(ancestors, heads)[0]:
             if match(node):
                 yield node
 
     def checkopts(opts, revs):
         if opts.get('continue'):
             if opts.get('branch') or opts.get('all') or opts.get('merge'):
                 raise error.Abort(_('--continue is incompatible with '
                                    '--branch, --all and --merge'))
             return
         if not (opts.get('source') or revs or
                 opts.get('merge') or opts.get('branch')):
             raise error.Abort(_('no source URL, branch revision, or revision '
                                'list provided'))
         if opts.get('all'):
             if not opts.get('branch'):
                 raise error.Abort(_('--all requires a branch revision'))
             if revs:
                 raise error.Abort(_('--all is incompatible with a '
                                    'revision list'))
 
     opts = pycompat.byteskwargs(opts)
     checkopts(opts, revs)
 
     if not opts.get('log'):
         # deprecated config: transplant.log
         opts['log'] = ui.config('transplant', 'log')
     if not opts.get('filter'):
         # deprecated config: transplant.filter
         opts['filter'] = ui.config('transplant', 'filter')
 
     tp = transplanter(ui, repo, opts)
 
     p1, p2 = repo.dirstate.parents()
     if len(repo) > 0 and p1 == revlog.nullid:
         raise error.Abort(_('no revision checked out'))
     if opts.get('continue'):
         if not tp.canresume():
             raise error.Abort(_('no transplant to continue'))
     else:
         cmdutil.checkunfinished(repo)
         if p2 != revlog.nullid:
             raise error.Abort(_('outstanding uncommitted merges'))
         m, a, r, d = repo.status()[:4]
         if m or a or r or d:
             raise error.Abort(_('outstanding local changes'))
 
     sourcerepo = opts.get('source')
     if sourcerepo:
         peer = hg.peer(repo, opts, ui.expandpath(sourcerepo))
         heads = map(peer.lookup, opts.get('branch', ()))
         target = set(heads)
         for r in revs:
             try:
                 target.add(peer.lookup(r))
             except error.RepoError:
                 pass
         source, csets, cleanupfn = bundlerepo.getremotechanges(ui, repo, peer,
                                     onlyheads=sorted(target), force=True)
     else:
         source = repo
         heads = map(source.lookup, opts.get('branch', ()))
         cleanupfn = None
 
     try:
         if opts.get('continue'):
             tp.resume(repo, source, opts)
             return
 
         tf = tp.transplantfilter(repo, source, p1)
         if opts.get('prune'):
             prune = set(source.lookup(r)
                         for r in scmutil.revrange(source, opts.get('prune')))
             matchfn = lambda x: tf(x) and x not in prune
         else:
             matchfn = tf
         merges = map(source.lookup, opts.get('merge', ()))
         revmap = {}
         if revs:
             for r in scmutil.revrange(source, revs):
                 revmap[int(r)] = source.lookup(r)
         elif opts.get('all') or not merges:
             if source != repo:
                 alltransplants = incwalk(source, csets, match=matchfn)
             else:
                 alltransplants = transplantwalk(source, p1, heads,
                                                 match=matchfn)
             if opts.get('all'):
                 revs = alltransplants
             else:
                 revs, newmerges = browserevs(ui, source, alltransplants, opts)
                 merges.extend(newmerges)
             for r in revs:
                 revmap[source.changelog.rev(r)] = r
         for r in merges:
             revmap[source.changelog.rev(r)] = r
 
         tp.apply(repo, source, revmap, merges, opts)
     finally:
         if cleanupfn:
             cleanupfn()
 
 revsetpredicate = registrar.revsetpredicate()
 
 @revsetpredicate('transplanted([set])')
 def revsettransplanted(repo, subset, x):
     """Transplanted changesets in set, or all transplanted changesets.
     """
     if x:
         s = revset.getset(repo, subset, x)
     else:
         s = subset
     return smartset.baseset([r for r in s if
         repo[r].extra().get('transplant_source')])
 
 templatekeyword = registrar.templatekeyword()
 
 @templatekeyword('transplanted', requires={'ctx'})
 def kwtransplanted(context, mapping):
     """String. The node identifier of the transplanted
     changeset if any."""
     ctx = context.resource(mapping, 'ctx')
     n = ctx.extra().get('transplant_source')
     return n and nodemod.hex(n) or ''
 
 def extsetup(ui):
     cmdutil.unfinishedstates.append(
         ['transplant/journal', True, False, _('transplant in progress'),
          _("use 'hg transplant --continue' or 'hg update' to abort")])
 
 # tell hggettext to extract docstrings from these functions:
 i18nfunctions = [revsettransplanted, kwtransplanted]

mercurial/chgserver.py

@@ -1,598 +1,598
 # chgserver.py - command server extension for cHg
 #
 # Copyright 2011 Yuya Nishihara <[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.
 
 """command server extension for cHg
 
 'S' channel (read/write)
     propagate ui.system() request to client
 
 'attachio' command
     attach client's stdio passed by sendmsg()
 
 'chdir' command
     change current directory
 
 'setenv' command
     replace os.environ completely
 
 'setumask' command
     set umask
 
 'validate' command
     reload the config and check if the server is up to date
 
 Config
 ------
 
 ::
 
   [chgserver]
   # how long (in seconds) should an idle chg server exit
   idletimeout = 3600
 
   # whether to skip config or env change checks
   skiphash = False
 """
 
 from __future__ import absolute_import
 
 import hashlib
 import inspect
 import os
 import re
 import socket
 import stat
 import struct
 import time
 
 from .i18n import _
 
 from . import (
     commandserver,
     encoding,
     error,
     extensions,
     node,
     pycompat,
     util,
 )
 
 from .utils import (
     procutil,
 )
 
 _log = commandserver.log
 
 def _hashlist(items):
     """return sha1 hexdigest for a list"""
     return node.hex(hashlib.sha1(str(items)).digest())
 
 # sensitive config sections affecting confighash
 _configsections = [
     'alias',  # affects global state commands.table
     'eol',    # uses setconfig('eol', ...)
     'extdiff',  # uisetup will register new commands
     'extensions',
 ]
 
 _configsectionitems = [
     ('commands', 'show.aliasprefix'), # show.py reads it in extsetup
 ]
 
 # sensitive environment variables affecting confighash
 _envre = re.compile(r'''\A(?:
                     CHGHG
                     |HG(?:DEMANDIMPORT|EMITWARNINGS|MODULEPOLICY|PROF|RCPATH)?
                     |HG(?:ENCODING|PLAIN).*
                     |LANG(?:UAGE)?
                     |LC_.*
                     |LD_.*
                     |PATH
                     |PYTHON.*
                     |TERM(?:INFO)?
                     |TZ
                     )\Z''', re.X)
 
 def _confighash(ui):
     """return a quick hash for detecting config/env changes
 
     confighash is the hash of sensitive config items and environment variables.
 
     for chgserver, it is designed that once confighash changes, the server is
     not qualified to serve its client and should redirect the client to a new
     server. different from mtimehash, confighash change will not mark the
     server outdated and exit since the user can have different configs at the
     same time.
     """
     sectionitems = []
     for section in _configsections:
         sectionitems.append(ui.configitems(section))
     for section, item in _configsectionitems:
         sectionitems.append(ui.config(section, item))
     sectionhash = _hashlist(sectionitems)
     # If $CHGHG is set, the change to $HG should not trigger a new chg server
     if 'CHGHG' in encoding.environ:
         ignored = {'HG'}
     else:
         ignored = set()
     envitems = [(k, v) for k, v in encoding.environ.iteritems()
                 if _envre.match(k) and k not in ignored]
     envhash = _hashlist(sorted(envitems))
     return sectionhash[:6] + envhash[:6]
 
 def _getmtimepaths(ui):
     """get a list of paths that should be checked to detect change
 
     The list will include:
     - extensions (will not cover all files for complex extensions)
     - mercurial/__version__.py
     - python binary
     """
     modules = [m for n, m in extensions.extensions(ui)]
     try:
         from . import __version__
         modules.append(__version__)
     except ImportError:
         pass
     files = [pycompat.sysexecutable]
     for m in modules:
         try:
             files.append(inspect.getabsfile(m))
         except TypeError:
             pass
     return sorted(set(files))
 
 def _mtimehash(paths):
     """return a quick hash for detecting file changes
 
     mtimehash calls stat on given paths and calculate a hash based on size and
     mtime of each file. mtimehash does not read file content because reading is
     expensive. therefore it's not 100% reliable for detecting content changes.
     it's possible to return different hashes for same file contents.
     it's also possible to return a same hash for different file contents for
     some carefully crafted situation.
 
     for chgserver, it is designed that once mtimehash changes, the server is
     considered outdated immediately and should no longer provide service.
 
     mtimehash is not included in confighash because we only know the paths of
     extensions after importing them (there is imp.find_module but that faces
     race conditions). We need to calculate confighash without importing.
     """
     def trystat(path):
         try:
             st = os.stat(path)
             return (st[stat.ST_MTIME], st.st_size)
         except OSError:
             # could be ENOENT, EPERM etc. not fatal in any case
             pass
     return _hashlist(map(trystat, paths))[:12]
 
 class hashstate(object):
     """a structure storing confighash, mtimehash, paths used for mtimehash"""
     def __init__(self, confighash, mtimehash, mtimepaths):
         self.confighash = confighash
         self.mtimehash = mtimehash
         self.mtimepaths = mtimepaths
 
     @staticmethod
     def fromui(ui, mtimepaths=None):
         if mtimepaths is None:
             mtimepaths = _getmtimepaths(ui)
         confighash = _confighash(ui)
         mtimehash = _mtimehash(mtimepaths)
         _log('confighash = %s mtimehash = %s\n' % (confighash, mtimehash))
         return hashstate(confighash, mtimehash, mtimepaths)
 
 def _newchgui(srcui, csystem, attachio):
     class chgui(srcui.__class__):
         def __init__(self, src=None):
             super(chgui, self).__init__(src)
             if src:
                 self._csystem = getattr(src, '_csystem', csystem)
             else:
                 self._csystem = csystem
 
         def _runsystem(self, cmd, environ, cwd, out):
             # fallback to the original system method if the output needs to be
             # captured (to self._buffers), or the output stream is not stdout
             # (e.g. stderr, cStringIO), because the chg client is not aware of
             # these situations and will behave differently (write to stdout).
             if (out is not self.fout
                 or not util.safehasattr(self.fout, 'fileno')
                 or self.fout.fileno() != procutil.stdout.fileno()):
-                return util.system(cmd, environ=environ, cwd=cwd, out=out)
+                return procutil.system(cmd, environ=environ, cwd=cwd, out=out)
             self.flush()
-            return self._csystem(cmd, util.shellenviron(environ), cwd)
+            return self._csystem(cmd, procutil.shellenviron(environ), cwd)
 
         def _runpager(self, cmd, env=None):
-            self._csystem(cmd, util.shellenviron(env), type='pager',
+            self._csystem(cmd, procutil.shellenviron(env), type='pager',
                           cmdtable={'attachio': attachio})
             return True
 
     return chgui(srcui)
 
 def _loadnewui(srcui, args):
     from . import dispatch  # avoid cycle
 
     newui = srcui.__class__.load()
     for a in ['fin', 'fout', 'ferr', 'environ']:
         setattr(newui, a, getattr(srcui, a))
     if util.safehasattr(srcui, '_csystem'):
         newui._csystem = srcui._csystem
 
     # command line args
     options = dispatch._earlyparseopts(newui, args)
     dispatch._parseconfig(newui, options['config'])
 
     # stolen from tortoisehg.util.copydynamicconfig()
     for section, name, value in srcui.walkconfig():
         source = srcui.configsource(section, name)
         if ':' in source or source == '--config' or source.startswith('$'):
             # path:line or command line, or environ
             continue
         newui.setconfig(section, name, value, source)
 
     # load wd and repo config, copied from dispatch.py
     cwd = options['cwd']
     cwd = cwd and os.path.realpath(cwd) or None
     rpath = options['repository']
     path, newlui = dispatch._getlocal(newui, rpath, wd=cwd)
 
     return (newui, newlui)
 
 class channeledsystem(object):
     """Propagate ui.system() request in the following format:
 
     payload length (unsigned int),
     type, '\0',
     cmd, '\0',
     cwd, '\0',
     envkey, '=', val, '\0',
     ...
     envkey, '=', val
 
     if type == 'system', waits for:
 
     exitcode length (unsigned int),
     exitcode (int)
 
     if type == 'pager', repetitively waits for a command name ending with '\n'
     and executes it defined by cmdtable, or exits the loop if the command name
     is empty.
     """
     def __init__(self, in_, out, channel):
         self.in_ = in_
         self.out = out
         self.channel = channel
 
     def __call__(self, cmd, environ, cwd=None, type='system', cmdtable=None):
-        args = [type, util.quotecommand(cmd), os.path.abspath(cwd or '.')]
+        args = [type, procutil.quotecommand(cmd), os.path.abspath(cwd or '.')]
         args.extend('%s=%s' % (k, v) for k, v in environ.iteritems())
         data = '\0'.join(args)
         self.out.write(struct.pack('>cI', self.channel, len(data)))
         self.out.write(data)
         self.out.flush()
 
         if type == 'system':
             length = self.in_.read(4)
             length, = struct.unpack('>I', length)
             if length != 4:
                 raise error.Abort(_('invalid response'))
             rc, = struct.unpack('>i', self.in_.read(4))
             return rc
         elif type == 'pager':
             while True:
                 cmd = self.in_.readline()[:-1]
                 if not cmd:
                     break
                 if cmdtable and cmd in cmdtable:
                     _log('pager subcommand: %s' % cmd)
                     cmdtable[cmd]()
                 else:
                     raise error.Abort(_('unexpected command: %s') % cmd)
         else:
             raise error.ProgrammingError('invalid S channel type: %s' % type)
 
 _iochannels = [
     # server.ch, ui.fp, mode
     ('cin', 'fin', r'rb'),
     ('cout', 'fout', r'wb'),
     ('cerr', 'ferr', r'wb'),
 ]
 
 class chgcmdserver(commandserver.server):
     def __init__(self, ui, repo, fin, fout, sock, hashstate, baseaddress):
         super(chgcmdserver, self).__init__(
             _newchgui(ui, channeledsystem(fin, fout, 'S'), self.attachio),
             repo, fin, fout)
         self.clientsock = sock
         self._oldios = []  # original (self.ch, ui.fp, fd) before "attachio"
         self.hashstate = hashstate
         self.baseaddress = baseaddress
         if hashstate is not None:
             self.capabilities = self.capabilities.copy()
             self.capabilities['validate'] = chgcmdserver.validate
 
     def cleanup(self):
         super(chgcmdserver, self).cleanup()
         # dispatch._runcatch() does not flush outputs if exception is not
         # handled by dispatch._dispatch()
         self.ui.flush()
         self._restoreio()
 
     def attachio(self):
         """Attach to client's stdio passed via unix domain socket; all
         channels except cresult will no longer be used
         """
         # tell client to sendmsg() with 1-byte payload, which makes it
         # distinctive from "attachio\n" command consumed by client.read()
         self.clientsock.sendall(struct.pack('>cI', 'I', 1))
         clientfds = util.recvfds(self.clientsock.fileno())
         _log('received fds: %r\n' % clientfds)
 
         ui = self.ui
         ui.flush()
         first = self._saveio()
         for fd, (cn, fn, mode) in zip(clientfds, _iochannels):
             assert fd > 0
             fp = getattr(ui, fn)
             os.dup2(fd, fp.fileno())
             os.close(fd)
             if not first:
                 continue
             # reset buffering mode when client is first attached. as we want
             # to see output immediately on pager, the mode stays unchanged
             # when client re-attached. ferr is unchanged because it should
             # be unbuffered no matter if it is a tty or not.
             if fn == 'ferr':
                 newfp = fp
             else:
                 # make it line buffered explicitly because the default is
                 # decided on first write(), where fout could be a pager.
                 if fp.isatty():
                     bufsize = 1  # line buffered
                 else:
                     bufsize = -1  # system default
                 newfp = os.fdopen(fp.fileno(), mode, bufsize)
                 setattr(ui, fn, newfp)
             setattr(self, cn, newfp)
 
         self.cresult.write(struct.pack('>i', len(clientfds)))
 
     def _saveio(self):
         if self._oldios:
             return False
         ui = self.ui
         for cn, fn, _mode in _iochannels:
             ch = getattr(self, cn)
             fp = getattr(ui, fn)
             fd = os.dup(fp.fileno())
             self._oldios.append((ch, fp, fd))
         return True
 
     def _restoreio(self):
         ui = self.ui
         for (ch, fp, fd), (cn, fn, _mode) in zip(self._oldios, _iochannels):
             newfp = getattr(ui, fn)
             # close newfp while it's associated with client; otherwise it
             # would be closed when newfp is deleted
             if newfp is not fp:
                 newfp.close()
             # restore original fd: fp is open again
             os.dup2(fd, fp.fileno())
             os.close(fd)
             setattr(self, cn, ch)
             setattr(ui, fn, fp)
         del self._oldios[:]
 
     def validate(self):
         """Reload the config and check if the server is up to date
 
         Read a list of '\0' separated arguments.
         Write a non-empty list of '\0' separated instruction strings or '\0'
         if the list is empty.
         An instruction string could be either:
             - "unlink $path", the client should unlink the path to stop the
               outdated server.
             - "redirect $path", the client should attempt to connect to $path
               first. If it does not work, start a new server. It implies
               "reconnect".
             - "exit $n", the client should exit directly with code n.
               This may happen if we cannot parse the config.
             - "reconnect", the client should close the connection and
               reconnect.
         If neither "reconnect" nor "redirect" is included in the instruction
         list, the client can continue with this server after completing all
         the instructions.
         """
         from . import dispatch  # avoid cycle
 
         args = self._readlist()
         try:
             self.ui, lui = _loadnewui(self.ui, args)
         except error.ParseError as inst:
             dispatch._formatparse(self.ui.warn, inst)
             self.ui.flush()
             self.cresult.write('exit 255')
             return
         newhash = hashstate.fromui(lui, self.hashstate.mtimepaths)
         insts = []
         if newhash.mtimehash != self.hashstate.mtimehash:
             addr = _hashaddress(self.baseaddress, self.hashstate.confighash)
             insts.append('unlink %s' % addr)
             # mtimehash is empty if one or more extensions fail to load.
             # to be compatible with hg, still serve the client this time.
             if self.hashstate.mtimehash:
                 insts.append('reconnect')
         if newhash.confighash != self.hashstate.confighash:
             addr = _hashaddress(self.baseaddress, newhash.confighash)
             insts.append('redirect %s' % addr)
         _log('validate: %s\n' % insts)
         self.cresult.write('\0'.join(insts) or '\0')
 
     def chdir(self):
         """Change current directory
 
         Note that the behavior of --cwd option is bit different from this.
         It does not affect --config parameter.
         """
         path = self._readstr()
         if not path:
             return
         _log('chdir to %r\n' % path)
         os.chdir(path)
 
     def setumask(self):
         """Change umask"""
         mask = struct.unpack('>I', self._read(4))[0]
         _log('setumask %r\n' % mask)
         os.umask(mask)
 
     def runcommand(self):
         return super(chgcmdserver, self).runcommand()
 
     def setenv(self):
         """Clear and update os.environ
 
         Note that not all variables can make an effect on the running process.
         """
         l = self._readlist()
         try:
             newenv = dict(s.split('=', 1) for s in l)
         except ValueError:
             raise ValueError('unexpected value in setenv request')
         _log('setenv: %r\n' % sorted(newenv.keys()))
         encoding.environ.clear()
         encoding.environ.update(newenv)
 
     capabilities = commandserver.server.capabilities.copy()
     capabilities.update({'attachio': attachio,
                          'chdir': chdir,
                          'runcommand': runcommand,
                          'setenv': setenv,
                          'setumask': setumask})
 
-    if util.safehasattr(util, 'setprocname'):
+    if util.safehasattr(procutil, 'setprocname'):
         def setprocname(self):
             """Change process title"""
             name = self._readstr()
             _log('setprocname: %r\n' % name)
-            util.setprocname(name)
+            procutil.setprocname(name)
         capabilities['setprocname'] = setprocname
 
 def _tempaddress(address):
     return '%s.%d.tmp' % (address, os.getpid())
 
 def _hashaddress(address, hashstr):
     # if the basename of address contains '.', use only the left part. this
     # makes it possible for the client to pass 'server.tmp$PID' and follow by
     # an atomic rename to avoid locking when spawning new servers.
     dirname, basename = os.path.split(address)
     basename = basename.split('.', 1)[0]
     return '%s-%s' % (os.path.join(dirname, basename), hashstr)
 
 class chgunixservicehandler(object):
     """Set of operations for chg services"""
 
     pollinterval = 1  # [sec]
 
     def __init__(self, ui):
         self.ui = ui
         self._idletimeout = ui.configint('chgserver', 'idletimeout')
         self._lastactive = time.time()
 
     def bindsocket(self, sock, address):
         self._inithashstate(address)
         self._checkextensions()
         self._bind(sock)
         self._createsymlink()
         # no "listening at" message should be printed to simulate hg behavior
 
     def _inithashstate(self, address):
         self._baseaddress = address
         if self.ui.configbool('chgserver', 'skiphash'):
             self._hashstate = None
             self._realaddress = address
             return
         self._hashstate = hashstate.fromui(self.ui)
         self._realaddress = _hashaddress(address, self._hashstate.confighash)
 
     def _checkextensions(self):
         if not self._hashstate:
             return
         if extensions.notloaded():
             # one or more extensions failed to load. mtimehash becomes
             # meaningless because we do not know the paths of those extensions.
             # set mtimehash to an illegal hash value to invalidate the server.
             self._hashstate.mtimehash = ''
 
     def _bind(self, sock):
         # use a unique temp address so we can stat the file and do ownership
         # check later
         tempaddress = _tempaddress(self._realaddress)
         util.bindunixsocket(sock, tempaddress)
         self._socketstat = os.stat(tempaddress)
         sock.listen(socket.SOMAXCONN)
         # rename will replace the old socket file if exists atomically. the
         # old server will detect ownership change and exit.
         util.rename(tempaddress, self._realaddress)
 
     def _createsymlink(self):
         if self._baseaddress == self._realaddress:
             return
         tempaddress = _tempaddress(self._baseaddress)
         os.symlink(os.path.basename(self._realaddress), tempaddress)
         util.rename(tempaddress, self._baseaddress)
 
     def _issocketowner(self):
         try:
             st = os.stat(self._realaddress)
             return (st.st_ino == self._socketstat.st_ino and
                     st[stat.ST_MTIME] == self._socketstat[stat.ST_MTIME])
         except OSError:
             return False
 
     def unlinksocket(self, address):
         if not self._issocketowner():
             return
         # it is possible to have a race condition here that we may
         # remove another server's socket file. but that's okay
         # since that server will detect and exit automatically and
         # the client will start a new server on demand.
         util.tryunlink(self._realaddress)
 
     def shouldexit(self):
         if not self._issocketowner():
             self.ui.debug('%s is not owned, exiting.\n' % self._realaddress)
             return True
         if time.time() - self._lastactive > self._idletimeout:
             self.ui.debug('being idle too long. exiting.\n')
             return True
         return False
 
     def newconnection(self):
         self._lastactive = time.time()
 
     def createcmdserver(self, repo, conn, fin, fout):
         return chgcmdserver(self.ui, repo, fin, fout, conn,
                             self._hashstate, self._baseaddress)
 
 def chgunixservice(ui, repo, opts):
     # CHGINTERNALMARK is set by chg client. It is an indication of things are
     # started by chg so other code can do things accordingly, like disabling
     # demandimport or detecting chg client started by chg client. When executed
     # here, CHGINTERNALMARK is no longer useful and hence dropped to make
     # environ cleaner.
     if 'CHGINTERNALMARK' in encoding.environ:
         del encoding.environ['CHGINTERNALMARK']
 
     if repo:
         # one chgserver can serve multiple repos. drop repo information
         ui.setconfig('bundle', 'mainreporoot', '', 'repo')
     h = chgunixservicehandler(ui)
     return commandserver.unixforkingservice(ui, repo=None, opts=opts, handler=h)