typing: consolidate "if not globals():" trick

Removes redundant inline comments. I think pycompat is good place to host
this kind of constants.

mercurial/branchmap.py

@@ -1,756 +1,756
 # branchmap.py - logic to computes, maintain and stores branchmap for local repo
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import struct
 
 from .node import (
     bin,
     hex,
     nullid,
     nullrev,
 )
 from . import (
     encoding,
     error,
     pycompat,
     scmutil,
     util,
 )
 from .utils import (
     repoviewutil,
     stringutil,
 )
 
-if not globals():
+if pycompat.TYPE_CHECKING:
     from typing import (
         Any,
         Callable,
         Dict,
         Iterable,
         List,
         Optional,
         Set,
         Tuple,
         Union,
     )
 
     assert any(
         (Any, Callable, Dict, Iterable, List, Optional, Set, Tuple, Union,)
     )
 
 subsettable = repoviewutil.subsettable
 
 calcsize = struct.calcsize
 pack_into = struct.pack_into
 unpack_from = struct.unpack_from
 
 
 class BranchMapCache(object):
     """mapping of filtered views of repo with their branchcache"""
 
     def __init__(self):
         self._per_filter = {}
 
     def __getitem__(self, repo):
         self.updatecache(repo)
         return self._per_filter[repo.filtername]
 
     def updatecache(self, repo):
         """Update the cache for the given filtered view on a repository"""
         # This can trigger updates for the caches for subsets of the filtered
         # view, e.g. when there is no cache for this filtered view or the cache
         # is stale.
 
         cl = repo.changelog
         filtername = repo.filtername
         bcache = self._per_filter.get(filtername)
         if bcache is None or not bcache.validfor(repo):
             # cache object missing or cache object stale? Read from disk
             bcache = branchcache.fromfile(repo)
 
         revs = []
         if bcache is None:
             # no (fresh) cache available anymore, perhaps we can re-use
             # the cache for a subset, then extend that to add info on missing
             # revisions.
             subsetname = subsettable.get(filtername)
             if subsetname is not None:
                 subset = repo.filtered(subsetname)
                 bcache = self[subset].copy()
                 extrarevs = subset.changelog.filteredrevs - cl.filteredrevs
                 revs.extend(r for r in extrarevs if r <= bcache.tiprev)
             else:
                 # nothing to fall back on, start empty.
                 bcache = branchcache()
 
         revs.extend(cl.revs(start=bcache.tiprev + 1))
         if revs:
             bcache.update(repo, revs)
 
         assert bcache.validfor(repo), filtername
         self._per_filter[repo.filtername] = bcache
 
     def replace(self, repo, remotebranchmap):
         """Replace the branchmap cache for a repo with a branch mapping.
 
         This is likely only called during clone with a branch map from a
         remote.
 
         """
         cl = repo.changelog
         clrev = cl.rev
         clbranchinfo = cl.branchinfo
         rbheads = []
         closed = set()
         for bheads in pycompat.itervalues(remotebranchmap):
             rbheads += bheads
             for h in bheads:
                 r = clrev(h)
                 b, c = clbranchinfo(r)
                 if c:
                     closed.add(h)
 
         if rbheads:
             rtiprev = max((int(clrev(node)) for node in rbheads))
             cache = branchcache(
                 remotebranchmap,
                 repo[rtiprev].node(),
                 rtiprev,
                 closednodes=closed,
             )
 
             # Try to stick it as low as possible
             # filter above served are unlikely to be fetch from a clone
             for candidate in (b'base', b'immutable', b'served'):
                 rview = repo.filtered(candidate)
                 if cache.validfor(rview):
                     self._per_filter[candidate] = cache
                     cache.write(rview)
                     return
 
     def clear(self):
         self._per_filter.clear()
 
 
 def _unknownnode(node):
     """ raises ValueError when branchcache found a node which does not exists
     """
     raise ValueError('node %s does not exist' % pycompat.sysstr(hex(node)))
 
 
 def _branchcachedesc(repo):
     if repo.filtername is not None:
         return b'branch cache (%s)' % repo.filtername
     else:
         return b'branch cache'
 
 
 class branchcache(object):
     """A dict like object that hold branches heads cache.
 
     This cache is used to avoid costly computations to determine all the
     branch heads of a repo.
 
     The cache is serialized on disk in the following format:
 
     <tip hex node> <tip rev number> [optional filtered repo hex hash]
     <branch head hex node> <open/closed state> <branch name>
     <branch head hex node> <open/closed state> <branch name>
     ...
 
     The first line is used to check if the cache is still valid. If the
     branch cache is for a filtered repo view, an optional third hash is
     included that hashes the hashes of all filtered revisions.
 
     The open/closed state is represented by a single letter 'o' or 'c'.
     This field can be used to avoid changelog reads when determining if a
     branch head closes a branch or not.
     """
 
     def __init__(
         self,
         entries=(),
         tipnode=nullid,
         tiprev=nullrev,
         filteredhash=None,
         closednodes=None,
         hasnode=None,
     ):
         # type: (Union[Dict[bytes, List[bytes]], Iterable[Tuple[bytes, List[bytes]]]], bytes,  int, Optional[bytes], Optional[Set[bytes]], Optional[Callable[[bytes], bool]]) -> None
         """ hasnode is a function which can be used to verify whether changelog
         has a given node or not. If it's not provided, we assume that every node
         we have exists in changelog """
         self.tipnode = tipnode
         self.tiprev = tiprev
         self.filteredhash = filteredhash
         # closednodes is a set of nodes that close their branch. If the branch
         # cache has been updated, it may contain nodes that are no longer
         # heads.
         if closednodes is None:
             self._closednodes = set()
         else:
             self._closednodes = closednodes
         self._entries = dict(entries)
         # whether closed nodes are verified or not
         self._closedverified = False
         # branches for which nodes are verified
         self._verifiedbranches = set()
         self._hasnode = hasnode
         if self._hasnode is None:
             self._hasnode = lambda x: True
 
     def _verifyclosed(self):
         """ verify the closed nodes we have """
         if self._closedverified:
             return
         for node in self._closednodes:
             if not self._hasnode(node):
                 _unknownnode(node)
 
         self._closedverified = True
 
     def _verifybranch(self, branch):
         """ verify head nodes for the given branch. """
         if branch not in self._entries or branch in self._verifiedbranches:
             return
         for n in self._entries[branch]:
             if not self._hasnode(n):
                 _unknownnode(n)
 
         self._verifiedbranches.add(branch)
 
     def _verifyall(self):
         """ verifies nodes of all the branches """
         needverification = set(self._entries.keys()) - self._verifiedbranches
         for b in needverification:
             self._verifybranch(b)
 
     def __iter__(self):
         return iter(self._entries)
 
     def __setitem__(self, key, value):
         self._entries[key] = value
 
     def __getitem__(self, key):
         self._verifybranch(key)
         return self._entries[key]
 
     def __contains__(self, key):
         self._verifybranch(key)
         return key in self._entries
 
     def iteritems(self):
         for k, v in pycompat.iteritems(self._entries):
             self._verifybranch(k)
             yield k, v
 
     items = iteritems
 
     def hasbranch(self, label):
         """ checks whether a branch of this name exists or not """
         self._verifybranch(label)
         return label in self._entries
 
     @classmethod
     def fromfile(cls, repo):
         f = None
         try:
             f = repo.cachevfs(cls._filename(repo))
             lineiter = iter(f)
             cachekey = next(lineiter).rstrip(b'\n').split(b" ", 2)
             last, lrev = cachekey[:2]
             last, lrev = bin(last), int(lrev)
             filteredhash = None
             hasnode = repo.changelog.hasnode
             if len(cachekey) > 2:
                 filteredhash = bin(cachekey[2])
             bcache = cls(
                 tipnode=last,
                 tiprev=lrev,
                 filteredhash=filteredhash,
                 hasnode=hasnode,
             )
             if not bcache.validfor(repo):
                 # invalidate the cache
                 raise ValueError('tip differs')
             bcache.load(repo, lineiter)
         except (IOError, OSError):
             return None
 
         except Exception as inst:
             if repo.ui.debugflag:
                 msg = b'invalid %s: %s\n'
                 repo.ui.debug(
                     msg
                     % (
                         _branchcachedesc(repo),
                         pycompat.bytestr(
                             inst  # pytype: disable=wrong-arg-types
                         ),
                     )
                 )
             bcache = None
 
         finally:
             if f:
                 f.close()
 
         return bcache
 
     def load(self, repo, lineiter):
         """ fully loads the branchcache by reading from the file using the line
         iterator passed"""
         for line in lineiter:
             line = line.rstrip(b'\n')
             if not line:
                 continue
             node, state, label = line.split(b" ", 2)
             if state not in b'oc':
                 raise ValueError('invalid branch state')
             label = encoding.tolocal(label.strip())
             node = bin(node)
             self._entries.setdefault(label, []).append(node)
             if state == b'c':
                 self._closednodes.add(node)
 
     @staticmethod
     def _filename(repo):
         """name of a branchcache file for a given repo or repoview"""
         filename = b"branch2"
         if repo.filtername:
             filename = b'%s-%s' % (filename, repo.filtername)
         return filename
 
     def validfor(self, repo):
         """Is the cache content valid regarding a repo
 
         - False when cached tipnode is unknown or if we detect a strip.
         - True when cache is up to date or a subset of current repo."""
         try:
             return (self.tipnode == repo.changelog.node(self.tiprev)) and (
                 self.filteredhash == scmutil.filteredhash(repo, self.tiprev)
             )
         except IndexError:
             return False
 
     def _branchtip(self, heads):
         '''Return tuple with last open head in heads and false,
         otherwise return last closed head and true.'''
         tip = heads[-1]
         closed = True
         for h in reversed(heads):
             if h not in self._closednodes:
                 tip = h
                 closed = False
                 break
         return tip, closed
 
     def branchtip(self, branch):
         '''Return the tipmost open head on branch head, otherwise return the
         tipmost closed head on branch.
         Raise KeyError for unknown branch.'''
         return self._branchtip(self[branch])[0]
 
     def iteropen(self, nodes):
         return (n for n in nodes if n not in self._closednodes)
 
     def branchheads(self, branch, closed=False):
         self._verifybranch(branch)
         heads = self._entries[branch]
         if not closed:
             heads = list(self.iteropen(heads))
         return heads
 
     def iterbranches(self):
         for bn, heads in pycompat.iteritems(self):
             yield (bn, heads) + self._branchtip(heads)
 
     def iterheads(self):
         """ returns all the heads """
         self._verifyall()
         return pycompat.itervalues(self._entries)
 
     def copy(self):
         """return an deep copy of the branchcache object"""
         return type(self)(
             self._entries,
             self.tipnode,
             self.tiprev,
             self.filteredhash,
             self._closednodes,
         )
 
     def write(self, repo):
         try:
             f = repo.cachevfs(self._filename(repo), b"w", atomictemp=True)
             cachekey = [hex(self.tipnode), b'%d' % self.tiprev]
             if self.filteredhash is not None:
                 cachekey.append(hex(self.filteredhash))
             f.write(b" ".join(cachekey) + b'\n')
             nodecount = 0
             for label, nodes in sorted(pycompat.iteritems(self._entries)):
                 label = encoding.fromlocal(label)
                 for node in nodes:
                     nodecount += 1
                     if node in self._closednodes:
                         state = b'c'
                     else:
                         state = b'o'
                     f.write(b"%s %s %s\n" % (hex(node), state, label))
             f.close()
             repo.ui.log(
                 b'branchcache',
                 b'wrote %s with %d labels and %d nodes\n',
                 _branchcachedesc(repo),
                 len(self._entries),
                 nodecount,
             )
         except (IOError, OSError, error.Abort) as inst:
             # Abort may be raised by read only opener, so log and continue
             repo.ui.debug(
                 b"couldn't write branch cache: %s\n"
                 % stringutil.forcebytestr(inst)
             )
 
     def update(self, repo, revgen):
         """Given a branchhead cache, self, that may have extra nodes or be
         missing heads, and a generator of nodes that are strictly a superset of
         heads missing, this function updates self to be correct.
         """
         starttime = util.timer()
         cl = repo.changelog
         # collect new branch entries
         newbranches = {}
         getbranchinfo = repo.revbranchcache().branchinfo
         for r in revgen:
             branch, closesbranch = getbranchinfo(r)
             newbranches.setdefault(branch, []).append(r)
             if closesbranch:
                 self._closednodes.add(cl.node(r))
 
         # fetch current topological heads to speed up filtering
         topoheads = set(cl.headrevs())
 
         # new tip revision which we found after iterating items from new
         # branches
         ntiprev = self.tiprev
 
         # if older branchheads are reachable from new ones, they aren't
         # really branchheads. Note checking parents is insufficient:
         # 1 (branch a) -> 2 (branch b) -> 3 (branch a)
         for branch, newheadrevs in pycompat.iteritems(newbranches):
             bheads = self._entries.setdefault(branch, [])
             bheadset = set(cl.rev(node) for node in bheads)
 
             # This have been tested True on all internal usage of this function.
             # run it again in case of doubt
             # assert not (set(bheadrevs) & set(newheadrevs))
             bheadset.update(newheadrevs)
 
             # This prunes out two kinds of heads - heads that are superseded by
             # a head in newheadrevs, and newheadrevs that are not heads because
             # an existing head is their descendant.
             uncertain = bheadset - topoheads
             if uncertain:
                 floorrev = min(uncertain)
                 ancestors = set(cl.ancestors(newheadrevs, floorrev))
                 bheadset -= ancestors
             bheadrevs = sorted(bheadset)
             self[branch] = [cl.node(rev) for rev in bheadrevs]
             tiprev = bheadrevs[-1]
             if tiprev > ntiprev:
                 ntiprev = tiprev
 
         if ntiprev > self.tiprev:
             self.tiprev = ntiprev
             self.tipnode = cl.node(ntiprev)
 
         if not self.validfor(repo):
             # cache key are not valid anymore
             self.tipnode = nullid
             self.tiprev = nullrev
             for heads in self.iterheads():
                 tiprev = max(cl.rev(node) for node in heads)
                 if tiprev > self.tiprev:
                     self.tipnode = cl.node(tiprev)
                     self.tiprev = tiprev
         self.filteredhash = scmutil.filteredhash(repo, self.tiprev)
 
         duration = util.timer() - starttime
         repo.ui.log(
             b'branchcache',
             b'updated %s in %.4f seconds\n',
             _branchcachedesc(repo),
             duration,
         )
 
         self.write(repo)
 
 
 class remotebranchcache(branchcache):
     """Branchmap info for a remote connection, should not write locally"""
 
     def write(self, repo):
         pass
 
 
 # Revision branch info cache
 
 _rbcversion = b'-v1'
 _rbcnames = b'rbc-names' + _rbcversion
 _rbcrevs = b'rbc-revs' + _rbcversion
 # [4 byte hash prefix][4 byte branch name number with sign bit indicating open]
 _rbcrecfmt = b'>4sI'
 _rbcrecsize = calcsize(_rbcrecfmt)
 _rbcnodelen = 4
 _rbcbranchidxmask = 0x7FFFFFFF
 _rbccloseflag = 0x80000000
 
 
 class revbranchcache(object):
     """Persistent cache, mapping from revision number to branch name and close.
     This is a low level cache, independent of filtering.
 
     Branch names are stored in rbc-names in internal encoding separated by 0.
     rbc-names is append-only, and each branch name is only stored once and will
     thus have a unique index.
 
     The branch info for each revision is stored in rbc-revs as constant size
     records. The whole file is read into memory, but it is only 'parsed' on
     demand. The file is usually append-only but will be truncated if repo
     modification is detected.
     The record for each revision contains the first 4 bytes of the
     corresponding node hash, and the record is only used if it still matches.
     Even a completely trashed rbc-revs fill thus still give the right result
     while converging towards full recovery ... assuming no incorrectly matching
     node hashes.
     The record also contains 4 bytes where 31 bits contains the index of the
     branch and the last bit indicate that it is a branch close commit.
     The usage pattern for rbc-revs is thus somewhat similar to 00changelog.i
     and will grow with it but be 1/8th of its size.
     """
 
     def __init__(self, repo, readonly=True):
         assert repo.filtername is None
         self._repo = repo
         self._names = []  # branch names in local encoding with static index
         self._rbcrevs = bytearray()
         self._rbcsnameslen = 0  # length of names read at _rbcsnameslen
         try:
             bndata = repo.cachevfs.read(_rbcnames)
             self._rbcsnameslen = len(bndata)  # for verification before writing
             if bndata:
                 self._names = [
                     encoding.tolocal(bn) for bn in bndata.split(b'\0')
                 ]
         except (IOError, OSError):
             if readonly:
                 # don't try to use cache - fall back to the slow path
                 self.branchinfo = self._branchinfo
 
         if self._names:
             try:
                 data = repo.cachevfs.read(_rbcrevs)
                 self._rbcrevs[:] = data
             except (IOError, OSError) as inst:
                 repo.ui.debug(
                     b"couldn't read revision branch cache: %s\n"
                     % stringutil.forcebytestr(inst)
                 )
         # remember number of good records on disk
         self._rbcrevslen = min(
             len(self._rbcrevs) // _rbcrecsize, len(repo.changelog)
         )
         if self._rbcrevslen == 0:
             self._names = []
         self._rbcnamescount = len(self._names)  # number of names read at
         # _rbcsnameslen
 
     def _clear(self):
         self._rbcsnameslen = 0
         del self._names[:]
         self._rbcnamescount = 0
         self._rbcrevslen = len(self._repo.changelog)
         self._rbcrevs = bytearray(self._rbcrevslen * _rbcrecsize)
         util.clearcachedproperty(self, b'_namesreverse')
 
     @util.propertycache
     def _namesreverse(self):
         return dict((b, r) for r, b in enumerate(self._names))
 
     def branchinfo(self, rev):
         """Return branch name and close flag for rev, using and updating
         persistent cache."""
         changelog = self._repo.changelog
         rbcrevidx = rev * _rbcrecsize
 
         # avoid negative index, changelog.read(nullrev) is fast without cache
         if rev == nullrev:
             return changelog.branchinfo(rev)
 
         # if requested rev isn't allocated, grow and cache the rev info
         if len(self._rbcrevs) < rbcrevidx + _rbcrecsize:
             return self._branchinfo(rev)
 
         # fast path: extract data from cache, use it if node is matching
         reponode = changelog.node(rev)[:_rbcnodelen]
         cachenode, branchidx = unpack_from(
             _rbcrecfmt, util.buffer(self._rbcrevs), rbcrevidx
         )
         close = bool(branchidx & _rbccloseflag)
         if close:
             branchidx &= _rbcbranchidxmask
         if cachenode == b'\0\0\0\0':
             pass
         elif cachenode == reponode:
             try:
                 return self._names[branchidx], close
             except IndexError:
                 # recover from invalid reference to unknown branch
                 self._repo.ui.debug(
                     b"referenced branch names not found"
                     b" - rebuilding revision branch cache from scratch\n"
                 )
                 self._clear()
         else:
             # rev/node map has changed, invalidate the cache from here up
             self._repo.ui.debug(
                 b"history modification detected - truncating "
                 b"revision branch cache to revision %d\n" % rev
             )
             truncate = rbcrevidx + _rbcrecsize
             del self._rbcrevs[truncate:]
             self._rbcrevslen = min(self._rbcrevslen, truncate)
 
         # fall back to slow path and make sure it will be written to disk
         return self._branchinfo(rev)
 
     def _branchinfo(self, rev):
         """Retrieve branch info from changelog and update _rbcrevs"""
         changelog = self._repo.changelog
         b, close = changelog.branchinfo(rev)
         if b in self._namesreverse:
             branchidx = self._namesreverse[b]
         else:
             branchidx = len(self._names)
             self._names.append(b)
             self._namesreverse[b] = branchidx
         reponode = changelog.node(rev)
         if close:
             branchidx |= _rbccloseflag
         self._setcachedata(rev, reponode, branchidx)
         return b, close
 
     def setdata(self, branch, rev, node, close):
         """add new data information to the cache"""
         if branch in self._namesreverse:
             branchidx = self._namesreverse[branch]
         else:
             branchidx = len(self._names)
             self._names.append(branch)
             self._namesreverse[branch] = branchidx
         if close:
             branchidx |= _rbccloseflag
         self._setcachedata(rev, node, branchidx)
         # If no cache data were readable (non exists, bad permission, etc)
         # the cache was bypassing itself by setting:
         #
         #   self.branchinfo = self._branchinfo
         #
         # Since we now have data in the cache, we need to drop this bypassing.
         if 'branchinfo' in vars(self):
             del self.branchinfo
 
     def _setcachedata(self, rev, node, branchidx):
         """Writes the node's branch data to the in-memory cache data."""
         if rev == nullrev:
             return
         rbcrevidx = rev * _rbcrecsize
         if len(self._rbcrevs) < rbcrevidx + _rbcrecsize:
             self._rbcrevs.extend(
                 b'\0'
                 * (len(self._repo.changelog) * _rbcrecsize - len(self._rbcrevs))
             )
         pack_into(_rbcrecfmt, self._rbcrevs, rbcrevidx, node, branchidx)
         self._rbcrevslen = min(self._rbcrevslen, rev)
 
         tr = self._repo.currenttransaction()
         if tr:
             tr.addfinalize(b'write-revbranchcache', self.write)
 
     def write(self, tr=None):
         """Save branch cache if it is dirty."""
         repo = self._repo
         wlock = None
         step = b''
         try:
             # write the new names
             if self._rbcnamescount < len(self._names):
                 wlock = repo.wlock(wait=False)
                 step = b' names'
                 self._writenames(repo)
 
             # write the new revs
             start = self._rbcrevslen * _rbcrecsize
             if start != len(self._rbcrevs):
                 step = b''
                 if wlock is None:
                     wlock = repo.wlock(wait=False)
                 self._writerevs(repo, start)
 
         except (IOError, OSError, error.Abort, error.LockError) as inst:
             repo.ui.debug(
                 b"couldn't write revision branch cache%s: %s\n"
                 % (step, stringutil.forcebytestr(inst))
             )
         finally:
             if wlock is not None:
                 wlock.release()
 
     def _writenames(self, repo):
         """ write the new branch names to revbranchcache """
         if self._rbcnamescount != 0:
             f = repo.cachevfs.open(_rbcnames, b'ab')
             if f.tell() == self._rbcsnameslen:
                 f.write(b'\0')
             else:
                 f.close()
                 repo.ui.debug(b"%s changed - rewriting it\n" % _rbcnames)
                 self._rbcnamescount = 0
                 self._rbcrevslen = 0
         if self._rbcnamescount == 0:
             # before rewriting names, make sure references are removed
             repo.cachevfs.unlinkpath(_rbcrevs, ignoremissing=True)
             f = repo.cachevfs.open(_rbcnames, b'wb')
         f.write(
             b'\0'.join(
                 encoding.fromlocal(b)
                 for b in self._names[self._rbcnamescount :]
             )
         )
         self._rbcsnameslen = f.tell()
         f.close()
         self._rbcnamescount = len(self._names)
 
     def _writerevs(self, repo, start):
         """ write the new revs to revbranchcache """
         revs = min(len(repo.changelog), len(self._rbcrevs) // _rbcrecsize)
         with repo.cachevfs.open(_rbcrevs, b'ab') as f:
             if f.tell() != start:
                 repo.ui.debug(
                     b"truncating cache/%s to %d\n" % (_rbcrevs, start)
                 )
                 f.seek(start)
                 if f.tell() != start:
                     start = 0
                     f.seek(start)
                 f.truncate()
             end = revs * _rbcrecsize
             f.write(self._rbcrevs[start:end])
         self._rbcrevslen = revs

mercurial/cmdutil.py

@@ -1,3984 +1,3984
 # cmdutil.py - help for command processing in mercurial
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import copy as copymod
 import errno
 import os
 import re
 
 from .i18n import _
 from .node import (
     hex,
     nullid,
     nullrev,
     short,
 )
 from .pycompat import (
     getattr,
     open,
     setattr,
 )
 
 from . import (
     bookmarks,
     changelog,
     copies,
     crecord as crecordmod,
     dirstateguard,
     encoding,
     error,
     formatter,
     logcmdutil,
     match as matchmod,
     merge as mergemod,
     mergeutil,
     obsolete,
     patch,
     pathutil,
     phases,
     pycompat,
     repair,
     revlog,
     rewriteutil,
     scmutil,
     smartset,
     state as statemod,
     subrepoutil,
     templatekw,
     templater,
     util,
     vfs as vfsmod,
 )
 
 from .utils import (
     dateutil,
     stringutil,
 )
 
-if not globals():
+if pycompat.TYPE_CHECKING:
     from typing import (
         Any,
         Dict,
     )
 
     for t in (Any, Dict):
         assert t
 
 stringio = util.stringio
 
 # templates of common command options
 
 dryrunopts = [
     (b'n', b'dry-run', None, _(b'do not perform actions, just print output')),
 ]
 
 confirmopts = [
     (b'', b'confirm', None, _(b'ask before applying actions')),
 ]
 
 remoteopts = [
     (b'e', b'ssh', b'', _(b'specify ssh command to use'), _(b'CMD')),
     (
         b'',
         b'remotecmd',
         b'',
         _(b'specify hg command to run on the remote side'),
         _(b'CMD'),
     ),
     (
         b'',
         b'insecure',
         None,
         _(b'do not verify server certificate (ignoring web.cacerts config)'),
     ),
 ]
 
 walkopts = [
     (
         b'I',
         b'include',
         [],
         _(b'include names matching the given patterns'),
         _(b'PATTERN'),
     ),
     (
         b'X',
         b'exclude',
         [],
         _(b'exclude names matching the given patterns'),
         _(b'PATTERN'),
     ),
 ]
 
 commitopts = [
     (b'm', b'message', b'', _(b'use text as commit message'), _(b'TEXT')),
     (b'l', b'logfile', b'', _(b'read commit message from file'), _(b'FILE')),
 ]
 
 commitopts2 = [
     (
         b'd',
         b'date',
         b'',
         _(b'record the specified date as commit date'),
         _(b'DATE'),
     ),
     (
         b'u',
         b'user',
         b'',
         _(b'record the specified user as committer'),
         _(b'USER'),
     ),
 ]
 
 commitopts3 = [
     (b'D', b'currentdate', None, _(b'record the current date as commit date')),
     (b'U', b'currentuser', None, _(b'record the current user as committer')),
 ]
 
 formatteropts = [
     (b'T', b'template', b'', _(b'display with template'), _(b'TEMPLATE')),
 ]
 
 templateopts = [
     (
         b'',
         b'style',
         b'',
         _(b'display using template map file (DEPRECATED)'),
         _(b'STYLE'),
     ),
     (b'T', b'template', b'', _(b'display with template'), _(b'TEMPLATE')),
 ]
 
 logopts = [
     (b'p', b'patch', None, _(b'show patch')),
     (b'g', b'git', None, _(b'use git extended diff format')),
     (b'l', b'limit', b'', _(b'limit number of changes displayed'), _(b'NUM')),
     (b'M', b'no-merges', None, _(b'do not show merges')),
     (b'', b'stat', None, _(b'output diffstat-style summary of changes')),
     (b'G', b'graph', None, _(b"show the revision DAG")),
 ] + templateopts
 
 diffopts = [
     (b'a', b'text', None, _(b'treat all files as text')),
     (b'g', b'git', None, _(b'use git extended diff format')),
     (b'', b'binary', None, _(b'generate binary diffs in git mode (default)')),
     (b'', b'nodates', None, _(b'omit dates from diff headers')),
 ]
 
 diffwsopts = [
     (
         b'w',
         b'ignore-all-space',
         None,
         _(b'ignore white space when comparing lines'),
     ),
     (
         b'b',
         b'ignore-space-change',
         None,
         _(b'ignore changes in the amount of white space'),
     ),
     (
         b'B',
         b'ignore-blank-lines',
         None,
         _(b'ignore changes whose lines are all blank'),
     ),
     (
         b'Z',
         b'ignore-space-at-eol',
         None,
         _(b'ignore changes in whitespace at EOL'),
     ),
 ]
 
 diffopts2 = (
     [
         (b'', b'noprefix', None, _(b'omit a/ and b/ prefixes from filenames')),
         (
             b'p',
             b'show-function',
             None,
             _(b'show which function each change is in'),
         ),
         (b'', b'reverse', None, _(b'produce a diff that undoes the changes')),
     ]
     + diffwsopts
     + [
         (
             b'U',
             b'unified',
             b'',
             _(b'number of lines of context to show'),
             _(b'NUM'),
         ),
         (b'', b'stat', None, _(b'output diffstat-style summary of changes')),
         (
             b'',
             b'root',
             b'',
             _(b'produce diffs relative to subdirectory'),
             _(b'DIR'),
         ),
     ]
 )
 
 mergetoolopts = [
     (b't', b'tool', b'', _(b'specify merge tool'), _(b'TOOL')),
 ]
 
 similarityopts = [
     (
         b's',
         b'similarity',
         b'',
         _(b'guess renamed files by similarity (0<=s<=100)'),
         _(b'SIMILARITY'),
     )
 ]
 
 subrepoopts = [(b'S', b'subrepos', None, _(b'recurse into subrepositories'))]
 
 debugrevlogopts = [
     (b'c', b'changelog', False, _(b'open changelog')),
     (b'm', b'manifest', False, _(b'open manifest')),
     (b'', b'dir', b'', _(b'open directory manifest')),
 ]
 
 # special string such that everything below this line will be ingored in the
 # editor text
 _linebelow = b"^HG: ------------------------ >8 ------------------------$"
 
 
 def resolvecommitoptions(ui, opts):
     """modify commit options dict to handle related options
 
     The return value indicates that ``rewrite.update-timestamp`` is the reason
     the ``date`` option is set.
     """
     if opts.get(b'date') and opts.get(b'currentdate'):
         raise error.Abort(_(b'--date and --currentdate are mutually exclusive'))
     if opts.get(b'user') and opts.get(b'currentuser'):
         raise error.Abort(_(b'--user and --currentuser are mutually exclusive'))
 
     datemaydiffer = False  # date-only change should be ignored?
 
     if opts.get(b'currentdate'):
         opts[b'date'] = b'%d %d' % dateutil.makedate()
     elif (
         not opts.get(b'date')
         and ui.configbool(b'rewrite', b'update-timestamp')
         and opts.get(b'currentdate') is None
     ):
         opts[b'date'] = b'%d %d' % dateutil.makedate()
         datemaydiffer = True
 
     if opts.get(b'currentuser'):
         opts[b'user'] = ui.username()
 
     return datemaydiffer
 
 
 def checknotesize(ui, opts):
     """ make sure note is of valid format """
 
     note = opts.get(b'note')
     if not note:
         return
 
     if len(note) > 255:
         raise error.Abort(_(b"cannot store a note of more than 255 bytes"))
     if b'\n' in note:
         raise error.Abort(_(b"note cannot contain a newline"))
 
 
 def ishunk(x):
     hunkclasses = (crecordmod.uihunk, patch.recordhunk)
     return isinstance(x, hunkclasses)
 
 
 def newandmodified(chunks, originalchunks):
     newlyaddedandmodifiedfiles = set()
     alsorestore = set()
     for chunk in chunks:
         if (
             ishunk(chunk)
             and chunk.header.isnewfile()
             and chunk not in originalchunks
         ):
             newlyaddedandmodifiedfiles.add(chunk.header.filename())
             alsorestore.update(
                 set(chunk.header.files()) - {chunk.header.filename()}
             )
     return newlyaddedandmodifiedfiles, alsorestore
 
 
 def parsealiases(cmd):
     return cmd.split(b"|")
 
 
 def setupwrapcolorwrite(ui):
     # wrap ui.write so diff output can be labeled/colorized
     def wrapwrite(orig, *args, **kw):
         label = kw.pop('label', b'')
         for chunk, l in patch.difflabel(lambda: args):
             orig(chunk, label=label + l)
 
     oldwrite = ui.write
 
     def wrap(*args, **kwargs):
         return wrapwrite(oldwrite, *args, **kwargs)
 
     setattr(ui, 'write', wrap)
     return oldwrite
 
 
 def filterchunks(ui, originalhunks, usecurses, testfile, match, operation=None):
     try:
         if usecurses:
             if testfile:
                 recordfn = crecordmod.testdecorator(
                     testfile, crecordmod.testchunkselector
                 )
             else:
                 recordfn = crecordmod.chunkselector
 
             return crecordmod.filterpatch(
                 ui, originalhunks, recordfn, operation
             )
     except crecordmod.fallbackerror as e:
         ui.warn(b'%s\n' % e.message)  # pytype: disable=attribute-error
         ui.warn(_(b'falling back to text mode\n'))
 
     return patch.filterpatch(ui, originalhunks, match, operation)
 
 
 def recordfilter(ui, originalhunks, match, operation=None):
     """ Prompts the user to filter the originalhunks and return a list of
     selected hunks.
     *operation* is used for to build ui messages to indicate the user what
     kind of filtering they are doing: reverting, committing, shelving, etc.
     (see patch.filterpatch).
     """
     usecurses = crecordmod.checkcurses(ui)
     testfile = ui.config(b'experimental', b'crecordtest')
     oldwrite = setupwrapcolorwrite(ui)
     try:
         newchunks, newopts = filterchunks(
             ui, originalhunks, usecurses, testfile, match, operation
         )
     finally:
         ui.write = oldwrite
     return newchunks, newopts
 
 
 def dorecord(
     ui, repo, commitfunc, cmdsuggest, backupall, filterfn, *pats, **opts
 ):
     opts = pycompat.byteskwargs(opts)
     if not ui.interactive():
         if cmdsuggest:
             msg = _(b'running non-interactively, use %s instead') % cmdsuggest
         else:
             msg = _(b'running non-interactively')
         raise error.Abort(msg)
 
     # make sure username is set before going interactive
     if not opts.get(b'user'):
         ui.username()  # raise exception, username not provided
 
     def recordfunc(ui, repo, message, match, opts):
         """This is generic record driver.
 
         Its job is to interactively filter local changes, and
         accordingly prepare working directory into a state in which the
         job can be delegated to a non-interactive commit command such as
         'commit' or 'qrefresh'.
 
         After the actual job is done by non-interactive command, the
         working directory is restored to its original state.
 
         In the end we'll record interesting changes, and everything else
         will be left in place, so the user can continue working.
         """
         if not opts.get(b'interactive-unshelve'):
             checkunfinished(repo, commit=True)
         wctx = repo[None]
         merge = len(wctx.parents()) > 1
         if merge:
             raise error.Abort(
                 _(
                     b'cannot partially commit a merge '
                     b'(use "hg commit" instead)'
                 )
             )
 
         def fail(f, msg):
             raise error.Abort(b'%s: %s' % (f, msg))
 
         force = opts.get(b'force')
         if not force:
             match = matchmod.badmatch(match, fail)
 
         status = repo.status(match=match)
 
         overrides = {(b'ui', b'commitsubrepos'): True}
 
         with repo.ui.configoverride(overrides, b'record'):
             # subrepoutil.precommit() modifies the status
             tmpstatus = scmutil.status(
                 copymod.copy(status.modified),
                 copymod.copy(status.added),
                 copymod.copy(status.removed),
                 copymod.copy(status.deleted),
                 copymod.copy(status.unknown),
                 copymod.copy(status.ignored),
                 copymod.copy(status.clean),  # pytype: disable=wrong-arg-count
             )
 
             # Force allows -X subrepo to skip the subrepo.
             subs, commitsubs, newstate = subrepoutil.precommit(
                 repo.ui, wctx, tmpstatus, match, force=True
             )
             for s in subs:
                 if s in commitsubs:
                     dirtyreason = wctx.sub(s).dirtyreason(True)
                     raise error.Abort(dirtyreason)
 
         if not force:
             repo.checkcommitpatterns(wctx, match, status, fail)
         diffopts = patch.difffeatureopts(
             ui,
             opts=opts,
             whitespace=True,
             section=b'commands',
             configprefix=b'commit.interactive.',
         )
         diffopts.nodates = True
         diffopts.git = True
         diffopts.showfunc = True
         originaldiff = patch.diff(repo, changes=status, opts=diffopts)
         originalchunks = patch.parsepatch(originaldiff)
         match = scmutil.match(repo[None], pats)
 
         # 1. filter patch, since we are intending to apply subset of it
         try:
             chunks, newopts = filterfn(ui, originalchunks, match)
         except error.PatchError as err:
             raise error.Abort(_(b'error parsing patch: %s') % err)
         opts.update(newopts)
 
         # We need to keep a backup of files that have been newly added and
         # modified during the recording process because there is a previous
         # version without the edit in the workdir. We also will need to restore
         # files that were the sources of renames so that the patch application
         # works.
         newlyaddedandmodifiedfiles, alsorestore = newandmodified(
             chunks, originalchunks
         )
         contenders = set()
         for h in chunks:
             try:
                 contenders.update(set(h.files()))
             except AttributeError:
                 pass
 
         changed = status.modified + status.added + status.removed
         newfiles = [f for f in changed if f in contenders]
         if not newfiles:
             ui.status(_(b'no changes to record\n'))
             return 0
 
         modified = set(status.modified)
 
         # 2. backup changed files, so we can restore them in the end
 
         if backupall:
             tobackup = changed
         else:
             tobackup = [
                 f
                 for f in newfiles
                 if f in modified or f in newlyaddedandmodifiedfiles
             ]
         backups = {}
         if tobackup:
             backupdir = repo.vfs.join(b'record-backups')
             try:
                 os.mkdir(backupdir)
             except OSError as err:
                 if err.errno != errno.EEXIST:
                     raise
         try:
             # backup continues
             for f in tobackup:
                 fd, tmpname = pycompat.mkstemp(
                     prefix=f.replace(b'/', b'_') + b'.', dir=backupdir
                 )
                 os.close(fd)
                 ui.debug(b'backup %r as %r\n' % (f, tmpname))
                 util.copyfile(repo.wjoin(f), tmpname, copystat=True)
                 backups[f] = tmpname
 
             fp = stringio()
             for c in chunks:
                 fname = c.filename()
                 if fname in backups:
                     c.write(fp)
             dopatch = fp.tell()
             fp.seek(0)
 
             # 2.5 optionally review / modify patch in text editor
             if opts.get(b'review', False):
                 patchtext = (
                     crecordmod.diffhelptext
                     + crecordmod.patchhelptext
                     + fp.read()
                 )
                 reviewedpatch = ui.edit(
                     patchtext, b"", action=b"diff", repopath=repo.path
                 )
                 fp.truncate(0)
                 fp.write(reviewedpatch)
                 fp.seek(0)
 
             [os.unlink(repo.wjoin(c)) for c in newlyaddedandmodifiedfiles]
             # 3a. apply filtered patch to clean repo  (clean)
             if backups:
                 # Equivalent to hg.revert
                 m = scmutil.matchfiles(repo, set(backups.keys()) | alsorestore)
                 mergemod.update(
                     repo,
                     repo.dirstate.p1(),
                     branchmerge=False,
                     force=True,
                     matcher=m,
                 )
 
             # 3b. (apply)
             if dopatch:
                 try:
                     ui.debug(b'applying patch\n')
                     ui.debug(fp.getvalue())
                     patch.internalpatch(ui, repo, fp, 1, eolmode=None)
                 except error.PatchError as err:
                     raise error.Abort(pycompat.bytestr(err))
             del fp
 
             # 4. We prepared working directory according to filtered
             #    patch. Now is the time to delegate the job to
             #    commit/qrefresh or the like!
 
             # Make all of the pathnames absolute.
             newfiles = [repo.wjoin(nf) for nf in newfiles]
             return commitfunc(ui, repo, *newfiles, **pycompat.strkwargs(opts))
         finally:
             # 5. finally restore backed-up files
             try:
                 dirstate = repo.dirstate
                 for realname, tmpname in pycompat.iteritems(backups):
                     ui.debug(b'restoring %r to %r\n' % (tmpname, realname))
 
                     if dirstate[realname] == b'n':
                         # without normallookup, restoring timestamp
                         # may cause partially committed files
                         # to be treated as unmodified
                         dirstate.normallookup(realname)
 
                     # copystat=True here and above are a hack to trick any
                     # editors that have f open that we haven't modified them.
                     #
                     # Also note that this racy as an editor could notice the
                     # file's mtime before we've finished writing it.
                     util.copyfile(tmpname, repo.wjoin(realname), copystat=True)
                     os.unlink(tmpname)
                 if tobackup:
                     os.rmdir(backupdir)
             except OSError:
                 pass
 
     def recordinwlock(ui, repo, message, match, opts):
         with repo.wlock():
             return recordfunc(ui, repo, message, match, opts)
 
     return commit(ui, repo, recordinwlock, pats, opts)
 
 
 class dirnode(object):
     """
     Represent a directory in user working copy with information required for
     the purpose of tersing its status.
 
     path is the path to the directory, without a trailing '/'
 
     statuses is a set of statuses of all files in this directory (this includes
     all the files in all the subdirectories too)
 
     files is a list of files which are direct child of this directory
 
     subdirs is a dictionary of sub-directory name as the key and it's own
     dirnode object as the value
     """
 
     def __init__(self, dirpath):
         self.path = dirpath
         self.statuses = set()
         self.files = []
         self.subdirs = {}
 
     def _addfileindir(self, filename, status):
         """Add a file in this directory as a direct child."""
         self.files.append((filename, status))
 
     def addfile(self, filename, status):
         """
         Add a file to this directory or to its direct parent directory.
 
         If the file is not direct child of this directory, we traverse to the
         directory of which this file is a direct child of and add the file
         there.
         """
 
         # the filename contains a path separator, it means it's not the direct
         # child of this directory
         if b'/' in filename:
             subdir, filep = filename.split(b'/', 1)
 
             # does the dirnode object for subdir exists
             if subdir not in self.subdirs:
                 subdirpath = pathutil.join(self.path, subdir)
                 self.subdirs[subdir] = dirnode(subdirpath)
 
             # try adding the file in subdir
             self.subdirs[subdir].addfile(filep, status)
 
         else:
             self._addfileindir(filename, status)
 
         if status not in self.statuses:
             self.statuses.add(status)
 
     def iterfilepaths(self):
         """Yield (status, path) for files directly under this directory."""
         for f, st in self.files:
             yield st, pathutil.join(self.path, f)
 
     def tersewalk(self, terseargs):
         """
         Yield (status, path) obtained by processing the status of this
         dirnode.
 
         terseargs is the string of arguments passed by the user with `--terse`
         flag.
 
         Following are the cases which can happen:
 
         1) All the files in the directory (including all the files in its
         subdirectories) share the same status and the user has asked us to terse
         that status. -> yield (status, dirpath).  dirpath will end in '/'.
 
         2) Otherwise, we do following:
 
                 a) Yield (status, filepath)  for all the files which are in this
                     directory (only the ones in this directory, not the subdirs)
 
                 b) Recurse the function on all the subdirectories of this
                    directory
         """
 
         if len(self.statuses) == 1:
             onlyst = self.statuses.pop()
 
             # Making sure we terse only when the status abbreviation is
             # passed as terse argument
             if onlyst in terseargs:
                 yield onlyst, self.path + b'/'
                 return
 
         # add the files to status list
         for st, fpath in self.iterfilepaths():
             yield st, fpath
 
         # recurse on the subdirs
         for dirobj in self.subdirs.values():
             for st, fpath in dirobj.tersewalk(terseargs):
                 yield st, fpath
 
 
 def tersedir(statuslist, terseargs):
     """
     Terse the status if all the files in a directory shares the same status.
 
     statuslist is scmutil.status() object which contains a list of files for
     each status.
     terseargs is string which is passed by the user as the argument to `--terse`
     flag.
 
     The function makes a tree of objects of dirnode class, and at each node it
     stores the information required to know whether we can terse a certain
     directory or not.
     """
     # the order matters here as that is used to produce final list
     allst = (b'm', b'a', b'r', b'd', b'u', b'i', b'c')
 
     # checking the argument validity
     for s in pycompat.bytestr(terseargs):
         if s not in allst:
             raise error.Abort(_(b"'%s' not recognized") % s)
 
     # creating a dirnode object for the root of the repo
     rootobj = dirnode(b'')
     pstatus = (
         b'modified',
         b'added',
         b'deleted',
         b'clean',
         b'unknown',
         b'ignored',
         b'removed',
     )
 
     tersedict = {}
     for attrname in pstatus:
         statuschar = attrname[0:1]
         for f in getattr(statuslist, attrname):
             rootobj.addfile(f, statuschar)
         tersedict[statuschar] = []
 
     # we won't be tersing the root dir, so add files in it
     for st, fpath in rootobj.iterfilepaths():
         tersedict[st].append(fpath)
 
     # process each sub-directory and build tersedict
     for subdir in rootobj.subdirs.values():
         for st, f in subdir.tersewalk(terseargs):
             tersedict[st].append(f)
 
     tersedlist = []
     for st in allst:
         tersedict[st].sort()
         tersedlist.append(tersedict[st])
 
     return scmutil.status(*tersedlist)
 
 
 def _commentlines(raw):
     '''Surround lineswith a comment char and a new line'''
     lines = raw.splitlines()
     commentedlines = [b'# %s' % line for line in lines]
     return b'\n'.join(commentedlines) + b'\n'
 
 
 def _conflictsmsg(repo):
     mergestate = mergemod.mergestate.read(repo)
     if not mergestate.active():
         return
 
     m = scmutil.match(repo[None])
     unresolvedlist = [f for f in mergestate.unresolved() if m(f)]
     if unresolvedlist:
         mergeliststr = b'\n'.join(
             [
                 b'    %s' % util.pathto(repo.root, encoding.getcwd(), path)
                 for path in sorted(unresolvedlist)
             ]
         )
         msg = (
             _(
                 '''Unresolved merge conflicts:
 
 %s
 
 To mark files as resolved:  hg resolve --mark FILE'''
             )
             % mergeliststr
         )
     else:
         msg = _(b'No unresolved merge conflicts.')
 
     return _commentlines(msg)
 
 
 def morestatus(repo, fm):
     statetuple = statemod.getrepostate(repo)
     label = b'status.morestatus'
     if statetuple:
         state, helpfulmsg = statetuple
         statemsg = _(b'The repository is in an unfinished *%s* state.') % state
         fm.plain(b'%s\n' % _commentlines(statemsg), label=label)
         conmsg = _conflictsmsg(repo)
         if conmsg:
             fm.plain(b'%s\n' % conmsg, label=label)
         if helpfulmsg:
             fm.plain(b'%s\n' % _commentlines(helpfulmsg), label=label)
 
 
 def findpossible(cmd, table, strict=False):
     """
     Return cmd -> (aliases, command table entry)
     for each matching command.
     Return debug commands (or their aliases) only if no normal command matches.
     """
     choice = {}
     debugchoice = {}
 
     if cmd in table:
         # short-circuit exact matches, "log" alias beats "log|history"
         keys = [cmd]
     else:
         keys = table.keys()
 
     allcmds = []
     for e in keys:
         aliases = parsealiases(e)
         allcmds.extend(aliases)
         found = None
         if cmd in aliases:
             found = cmd
         elif not strict:
             for a in aliases:
                 if a.startswith(cmd):
                     found = a
                     break
         if found is not None:
             if aliases[0].startswith(b"debug") or found.startswith(b"debug"):
                 debugchoice[found] = (aliases, table[e])
             else:
                 choice[found] = (aliases, table[e])
 
     if not choice and debugchoice:
         choice = debugchoice
 
     return choice, allcmds
 
 
 def findcmd(cmd, table, strict=True):
     """Return (aliases, command table entry) for command string."""
     choice, allcmds = findpossible(cmd, table, strict)
 
     if cmd in choice:
         return choice[cmd]
 
     if len(choice) > 1:
         clist = sorted(choice)
         raise error.AmbiguousCommand(cmd, clist)
 
     if choice:
         return list(choice.values())[0]
 
     raise error.UnknownCommand(cmd, allcmds)
 
 
 def changebranch(ui, repo, revs, label):
     """ Change the branch name of given revs to label """
 
     with repo.wlock(), repo.lock(), repo.transaction(b'branches'):
         # abort in case of uncommitted merge or dirty wdir
         bailifchanged(repo)
         revs = scmutil.revrange(repo, revs)
         if not revs:
             raise error.Abort(b"empty revision set")
         roots = repo.revs(b'roots(%ld)', revs)
         if len(roots) > 1:
             raise error.Abort(
                 _(b"cannot change branch of non-linear revisions")
             )
         rewriteutil.precheck(repo, revs, b'change branch of')
 
         root = repo[roots.first()]
         rpb = {parent.branch() for parent in root.parents()}
         if label not in rpb and label in repo.branchmap():
             raise error.Abort(_(b"a branch of the same name already exists"))
 
         if repo.revs(b'obsolete() and %ld', revs):
             raise error.Abort(
                 _(b"cannot change branch of a obsolete changeset")
             )
 
         # make sure only topological heads
         if repo.revs(b'heads(%ld) - head()', revs):
             raise error.Abort(_(b"cannot change branch in middle of a stack"))
 
         replacements = {}
         # avoid import cycle mercurial.cmdutil -> mercurial.context ->
         # mercurial.subrepo -> mercurial.cmdutil
         from . import context
 
         for rev in revs:
             ctx = repo[rev]
             oldbranch = ctx.branch()
             # check if ctx has same branch
             if oldbranch == label:
                 continue
 
             def filectxfn(repo, newctx, path):
                 try:
                     return ctx[path]
                 except error.ManifestLookupError:
                     return None
 
             ui.debug(
                 b"changing branch of '%s' from '%s' to '%s'\n"
                 % (hex(ctx.node()), oldbranch, label)
             )
             extra = ctx.extra()
             extra[b'branch_change'] = hex(ctx.node())
             # While changing branch of set of linear commits, make sure that
             # we base our commits on new parent rather than old parent which
             # was obsoleted while changing the branch
             p1 = ctx.p1().node()
             p2 = ctx.p2().node()
             if p1 in replacements:
                 p1 = replacements[p1][0]
             if p2 in replacements:
                 p2 = replacements[p2][0]
 
             mc = context.memctx(
                 repo,
                 (p1, p2),
                 ctx.description(),
                 ctx.files(),
                 filectxfn,
                 user=ctx.user(),
                 date=ctx.date(),
                 extra=extra,
                 branch=label,
             )
 
             newnode = repo.commitctx(mc)
             replacements[ctx.node()] = (newnode,)
             ui.debug(b'new node id is %s\n' % hex(newnode))
 
         # create obsmarkers and move bookmarks
         scmutil.cleanupnodes(
             repo, replacements, b'branch-change', fixphase=True
         )
 
         # move the working copy too
         wctx = repo[None]
         # in-progress merge is a bit too complex for now.
         if len(wctx.parents()) == 1:
             newid = replacements.get(wctx.p1().node())
             if newid is not None:
                 # avoid import cycle mercurial.cmdutil -> mercurial.hg ->
                 # mercurial.cmdutil
                 from . import hg
 
                 hg.update(repo, newid[0], quietempty=True)
 
         ui.status(_(b"changed branch on %d changesets\n") % len(replacements))
 
 
 def findrepo(p):
     while not os.path.isdir(os.path.join(p, b".hg")):
         oldp, p = p, os.path.dirname(p)
         if p == oldp:
             return None
 
     return p
 
 
 def bailifchanged(repo, merge=True, hint=None):
     """ enforce the precondition that working directory must be clean.
 
     'merge' can be set to false if a pending uncommitted merge should be
     ignored (such as when 'update --check' runs).
 
     'hint' is the usual hint given to Abort exception.
     """
 
     if merge and repo.dirstate.p2() != nullid:
         raise error.Abort(_(b'outstanding uncommitted merge'), hint=hint)
     st = repo.status()
     if st.modified or st.added or st.removed or st.deleted:
         raise error.Abort(_(b'uncommitted changes'), hint=hint)
     ctx = repo[None]
     for s in sorted(ctx.substate):
         ctx.sub(s).bailifchanged(hint=hint)
 
 
 def logmessage(ui, opts):
     """ get the log message according to -m and -l option """
     message = opts.get(b'message')
     logfile = opts.get(b'logfile')
 
     if message and logfile:
         raise error.Abort(
             _(b'options --message and --logfile are mutually exclusive')
         )
     if not message and logfile:
         try:
             if isstdiofilename(logfile):
                 message = ui.fin.read()
             else:
                 message = b'\n'.join(util.readfile(logfile).splitlines())
         except IOError as inst:
             raise error.Abort(
                 _(b"can't read commit message '%s': %s")
                 % (logfile, encoding.strtolocal(inst.strerror))
             )
     return message
 
 
 def mergeeditform(ctxorbool, baseformname):
     """return appropriate editform name (referencing a committemplate)
 
     'ctxorbool' is either a ctx to be committed, or a bool indicating whether
     merging is committed.
 
     This returns baseformname with '.merge' appended if it is a merge,
     otherwise '.normal' is appended.
     """
     if isinstance(ctxorbool, bool):
         if ctxorbool:
             return baseformname + b".merge"
     elif len(ctxorbool.parents()) > 1:
         return baseformname + b".merge"
 
     return baseformname + b".normal"
 
 
 def getcommiteditor(
     edit=False, finishdesc=None, extramsg=None, editform=b'', **opts
 ):
     """get appropriate commit message editor according to '--edit' option
 
     'finishdesc' is a function to be called with edited commit message
     (= 'description' of the new changeset) just after editing, but
     before checking empty-ness. It should return actual text to be
     stored into history. This allows to change description before
     storing.
 
     'extramsg' is a extra message to be shown in the editor instead of
     'Leave message empty to abort commit' line. 'HG: ' prefix and EOL
     is automatically added.
 
     'editform' is a dot-separated list of names, to distinguish
     the purpose of commit text editing.
 
     'getcommiteditor' returns 'commitforceeditor' regardless of
     'edit', if one of 'finishdesc' or 'extramsg' is specified, because
     they are specific for usage in MQ.
     """
     if edit or finishdesc or extramsg:
         return lambda r, c, s: commitforceeditor(
             r, c, s, finishdesc=finishdesc, extramsg=extramsg, editform=editform
         )
     elif editform:
         return lambda r, c, s: commiteditor(r, c, s, editform=editform)
     else:
         return commiteditor
 
 
 def _escapecommandtemplate(tmpl):
     parts = []
     for typ, start, end in templater.scantemplate(tmpl, raw=True):
         if typ == b'string':
             parts.append(stringutil.escapestr(tmpl[start:end]))
         else:
             parts.append(tmpl[start:end])
     return b''.join(parts)
 
 
 def rendercommandtemplate(ui, tmpl, props):
     r"""Expand a literal template 'tmpl' in a way suitable for command line
 
     '\' in outermost string is not taken as an escape character because it
     is a directory separator on Windows.
 
     >>> from . import ui as uimod
     >>> ui = uimod.ui()
     >>> rendercommandtemplate(ui, b'c:\\{path}', {b'path': b'foo'})
     'c:\\foo'
     >>> rendercommandtemplate(ui, b'{"c:\\{path}"}', {'path': b'foo'})
     'c:{path}'
     """
     if not tmpl:
         return tmpl
     t = formatter.maketemplater(ui, _escapecommandtemplate(tmpl))
     return t.renderdefault(props)
 
 
 def rendertemplate(ctx, tmpl, props=None):
     """Expand a literal template 'tmpl' byte-string against one changeset
 
     Each props item must be a stringify-able value or a callable returning
     such value, i.e. no bare list nor dict should be passed.
     """
     repo = ctx.repo()
     tres = formatter.templateresources(repo.ui, repo)
     t = formatter.maketemplater(
         repo.ui, tmpl, defaults=templatekw.keywords, resources=tres
     )
     mapping = {b'ctx': ctx}
     if props:
         mapping.update(props)
     return t.renderdefault(mapping)
 
 
 def _buildfntemplate(pat, total=None, seqno=None, revwidth=None, pathname=None):
     r"""Convert old-style filename format string to template string
 
     >>> _buildfntemplate(b'foo-%b-%n.patch', seqno=0)
     'foo-{reporoot|basename}-{seqno}.patch'
     >>> _buildfntemplate(b'%R{tags % "{tag}"}%H')
     '{rev}{tags % "{tag}"}{node}'
 
     '\' in outermost strings has to be escaped because it is a directory
     separator on Windows:
 
     >>> _buildfntemplate(b'c:\\tmp\\%R\\%n.patch', seqno=0)
     'c:\\\\tmp\\\\{rev}\\\\{seqno}.patch'
     >>> _buildfntemplate(b'\\\\foo\\bar.patch')
     '\\\\\\\\foo\\\\bar.patch'
     >>> _buildfntemplate(b'\\{tags % "{tag}"}')
     '\\\\{tags % "{tag}"}'
 
     but inner strings follow the template rules (i.e. '\' is taken as an
     escape character):
 
     >>> _buildfntemplate(br'{"c:\tmp"}', seqno=0)
     '{"c:\\tmp"}'
     """
     expander = {
         b'H': b'{node}',
         b'R': b'{rev}',
         b'h': b'{node|short}',
         b'm': br'{sub(r"[^\w]", "_", desc|firstline)}',
         b'r': b'{if(revwidth, pad(rev, revwidth, "0", left=True), rev)}',
         b'%': b'%',
         b'b': b'{reporoot|basename}',
     }
     if total is not None:
         expander[b'N'] = b'{total}'
     if seqno is not None:
         expander[b'n'] = b'{seqno}'
     if total is not None and seqno is not None:
         expander[b'n'] = b'{pad(seqno, total|stringify|count, "0", left=True)}'
     if pathname is not None:
         expander[b's'] = b'{pathname|basename}'
         expander[b'd'] = b'{if(pathname|dirname, pathname|dirname, ".")}'
         expander[b'p'] = b'{pathname}'
 
     newname = []
     for typ, start, end in templater.scantemplate(pat, raw=True):
         if typ != b'string':
             newname.append(pat[start:end])
             continue
         i = start
         while i < end:
             n = pat.find(b'%', i, end)
             if n < 0:
                 newname.append(stringutil.escapestr(pat[i:end]))
                 break
             newname.append(stringutil.escapestr(pat[i:n]))
             if n + 2 > end:
                 raise error.Abort(
                     _(b"incomplete format spec in output filename")
                 )
             c = pat[n + 1 : n + 2]
             i = n + 2
             try:
                 newname.append(expander[c])
             except KeyError:
                 raise error.Abort(
                     _(b"invalid format spec '%%%s' in output filename") % c
                 )
     return b''.join(newname)
 
 
 def makefilename(ctx, pat, **props):
     if not pat:
         return pat
     tmpl = _buildfntemplate(pat, **props)
     # BUG: alias expansion shouldn't be made against template fragments
     # rewritten from %-format strings, but we have no easy way to partially
     # disable the expansion.
     return rendertemplate(ctx, tmpl, pycompat.byteskwargs(props))
 
 
 def isstdiofilename(pat):
     """True if the given pat looks like a filename denoting stdin/stdout"""
     return not pat or pat == b'-'
 
 
 class _unclosablefile(object):
     def __init__(self, fp):
         self._fp = fp
 
     def close(self):
         pass
 
     def __iter__(self):
         return iter(self._fp)
 
     def __getattr__(self, attr):
         return getattr(self._fp, attr)
 
     def __enter__(self):
         return self
 
     def __exit__(self, exc_type, exc_value, exc_tb):
         pass
 
 
 def makefileobj(ctx, pat, mode=b'wb', **props):
     writable = mode not in (b'r', b'rb')
 
     if isstdiofilename(pat):
         repo = ctx.repo()
         if writable:
             fp = repo.ui.fout
         else:
             fp = repo.ui.fin
         return _unclosablefile(fp)
     fn = makefilename(ctx, pat, **props)
     return open(fn, mode)
 
 
 def openstorage(repo, cmd, file_, opts, returnrevlog=False):
     """opens the changelog, manifest, a filelog or a given revlog"""
     cl = opts[b'changelog']
     mf = opts[b'manifest']
     dir = opts[b'dir']
     msg = None
     if cl and mf:
         msg = _(b'cannot specify --changelog and --manifest at the same time')
     elif cl and dir:
         msg = _(b'cannot specify --changelog and --dir at the same time')
     elif cl or mf or dir:
         if file_:
             msg = _(b'cannot specify filename with --changelog or --manifest')
         elif not repo:
             msg = _(
                 b'cannot specify --changelog or --manifest or --dir '
                 b'without a repository'
             )
     if msg:
         raise error.Abort(msg)
 
     r = None
     if repo:
         if cl:
             r = repo.unfiltered().changelog
         elif dir:
             if b'treemanifest' not in repo.requirements:
                 raise error.Abort(
                     _(
                         b"--dir can only be used on repos with "
                         b"treemanifest enabled"
                     )
                 )
             if not dir.endswith(b'/'):
                 dir = dir + b'/'
             dirlog = repo.manifestlog.getstorage(dir)
             if len(dirlog):
                 r = dirlog
         elif mf:
             r = repo.manifestlog.getstorage(b'')
         elif file_:
             filelog = repo.file(file_)
             if len(filelog):
                 r = filelog
 
         # Not all storage may be revlogs. If requested, try to return an actual
         # revlog instance.
         if returnrevlog:
             if isinstance(r, revlog.revlog):
                 pass
             elif util.safehasattr(r, b'_revlog'):
                 r = r._revlog  # pytype: disable=attribute-error
             elif r is not None:
                 raise error.Abort(_(b'%r does not appear to be a revlog') % r)
 
     if not r:
         if not returnrevlog:
             raise error.Abort(_(b'cannot give path to non-revlog'))
 
         if not file_:
             raise error.CommandError(cmd, _(b'invalid arguments'))
         if not os.path.isfile(file_):
             raise error.Abort(_(b"revlog '%s' not found") % file_)
         r = revlog.revlog(
             vfsmod.vfs(encoding.getcwd(), audit=False), file_[:-2] + b".i"
         )
     return r
 
 
 def openrevlog(repo, cmd, file_, opts):
     """Obtain a revlog backing storage of an item.
 
     This is similar to ``openstorage()`` except it always returns a revlog.
 
     In most cases, a caller cares about the main storage object - not the
     revlog backing it. Therefore, this function should only be used by code
     that needs to examine low-level revlog implementation details. e.g. debug
     commands.
     """
     return openstorage(repo, cmd, file_, opts, returnrevlog=True)
 
 
 def copy(ui, repo, pats, opts, rename=False):
     # called with the repo lock held
     #
     # hgsep => pathname that uses "/" to separate directories
     # ossep => pathname that uses os.sep to separate directories
     cwd = repo.getcwd()
     targets = {}
     after = opts.get(b"after")
     dryrun = opts.get(b"dry_run")
     wctx = repo[None]
 
     uipathfn = scmutil.getuipathfn(repo, legacyrelativevalue=True)
 
     def walkpat(pat):
         srcs = []
         if after:
             badstates = b'?'
         else:
             badstates = b'?r'
         m = scmutil.match(wctx, [pat], opts, globbed=True)
         for abs in wctx.walk(m):
             state = repo.dirstate[abs]
             rel = uipathfn(abs)
             exact = m.exact(abs)
             if state in badstates:
                 if exact and state == b'?':
                     ui.warn(_(b'%s: not copying - file is not managed\n') % rel)
                 if exact and state == b'r':
                     ui.warn(
                         _(
                             b'%s: not copying - file has been marked for'
                             b' remove\n'
                         )
                         % rel
                     )
                 continue
             # abs: hgsep
             # rel: ossep
             srcs.append((abs, rel, exact))
         return srcs
 
     # abssrc: hgsep
     # relsrc: ossep
     # otarget: ossep
     def copyfile(abssrc, relsrc, otarget, exact):
         abstarget = pathutil.canonpath(repo.root, cwd, otarget)
         if b'/' in abstarget:
             # We cannot normalize abstarget itself, this would prevent
             # case only renames, like a => A.
             abspath, absname = abstarget.rsplit(b'/', 1)
             abstarget = repo.dirstate.normalize(abspath) + b'/' + absname
         reltarget = repo.pathto(abstarget, cwd)
         target = repo.wjoin(abstarget)
         src = repo.wjoin(abssrc)
         state = repo.dirstate[abstarget]
 
         scmutil.checkportable(ui, abstarget)
 
         # check for collisions
         prevsrc = targets.get(abstarget)
         if prevsrc is not None:
             ui.warn(
                 _(b'%s: not overwriting - %s collides with %s\n')
                 % (
                     reltarget,
                     repo.pathto(abssrc, cwd),
                     repo.pathto(prevsrc, cwd),
                 )
             )
             return True  # report a failure
 
         # check for overwrites
         exists = os.path.lexists(target)
         samefile = False
         if exists and abssrc != abstarget:
             if repo.dirstate.normalize(abssrc) == repo.dirstate.normalize(
                 abstarget
             ):
                 if not rename:
                     ui.warn(_(b"%s: can't copy - same file\n") % reltarget)
                     return True  # report a failure
                 exists = False
                 samefile = True
 
         if not after and exists or after and state in b'mn':
             if not opts[b'force']:
                 if state in b'mn':
                     msg = _(b'%s: not overwriting - file already committed\n')
                     if after:
                         flags = b'--after --force'
                     else:
                         flags = b'--force'
                     if rename:
                         hint = (
                             _(
                                 b"('hg rename %s' to replace the file by "
                                 b'recording a rename)\n'
                             )
                             % flags
                         )
                     else:
                         hint = (
                             _(
                                 b"('hg copy %s' to replace the file by "
                                 b'recording a copy)\n'
                             )
                             % flags
                         )
                 else:
                     msg = _(b'%s: not overwriting - file exists\n')
                     if rename:
                         hint = _(
                             b"('hg rename --after' to record the rename)\n"
                         )
                     else:
                         hint = _(b"('hg copy --after' to record the copy)\n")
                 ui.warn(msg % reltarget)
                 ui.warn(hint)
                 return True  # report a failure
 
         if after:
             if not exists:
                 if rename:
                     ui.warn(
                         _(b'%s: not recording move - %s does not exist\n')
                         % (relsrc, reltarget)
                     )
                 else:
                     ui.warn(
                         _(b'%s: not recording copy - %s does not exist\n')
                         % (relsrc, reltarget)
                     )
                 return True  # report a failure
         elif not dryrun:
             try:
                 if exists:
                     os.unlink(target)
                 targetdir = os.path.dirname(target) or b'.'
                 if not os.path.isdir(targetdir):
                     os.makedirs(targetdir)
                 if samefile:
                     tmp = target + b"~hgrename"
                     os.rename(src, tmp)
                     os.rename(tmp, target)
                 else:
                     # Preserve stat info on renames, not on copies; this matches
                     # Linux CLI behavior.
                     util.copyfile(src, target, copystat=rename)
                 srcexists = True
             except IOError as inst:
                 if inst.errno == errno.ENOENT:
                     ui.warn(_(b'%s: deleted in working directory\n') % relsrc)
                     srcexists = False
                 else:
                     ui.warn(
                         _(b'%s: cannot copy - %s\n')
                         % (relsrc, encoding.strtolocal(inst.strerror))
                     )
                     return True  # report a failure
 
         if ui.verbose or not exact:
             if rename:
                 ui.status(_(b'moving %s to %s\n') % (relsrc, reltarget))
             else:
                 ui.status(_(b'copying %s to %s\n') % (relsrc, reltarget))
 
         targets[abstarget] = abssrc
 
         # fix up dirstate
         scmutil.dirstatecopy(
             ui, repo, wctx, abssrc, abstarget, dryrun=dryrun, cwd=cwd
         )
         if rename and not dryrun:
             if not after and srcexists and not samefile:
                 rmdir = repo.ui.configbool(b'experimental', b'removeemptydirs')
                 repo.wvfs.unlinkpath(abssrc, rmdir=rmdir)
             wctx.forget([abssrc])
 
     # pat: ossep
     # dest ossep
     # srcs: list of (hgsep, hgsep, ossep, bool)
     # return: function that takes hgsep and returns ossep
     def targetpathfn(pat, dest, srcs):
         if os.path.isdir(pat):
             abspfx = pathutil.canonpath(repo.root, cwd, pat)
             abspfx = util.localpath(abspfx)
             if destdirexists:
                 striplen = len(os.path.split(abspfx)[0])
             else:
                 striplen = len(abspfx)
             if striplen:
                 striplen += len(pycompat.ossep)
             res = lambda p: os.path.join(dest, util.localpath(p)[striplen:])
         elif destdirexists:
             res = lambda p: os.path.join(
                 dest, os.path.basename(util.localpath(p))
             )
         else:
             res = lambda p: dest
         return res
 
     # pat: ossep
     # dest ossep
     # srcs: list of (hgsep, hgsep, ossep, bool)
     # return: function that takes hgsep and returns ossep
     def targetpathafterfn(pat, dest, srcs):
         if matchmod.patkind(pat):
             # a mercurial pattern
             res = lambda p: os.path.join(
                 dest, os.path.basename(util.localpath(p))
             )
         else:
             abspfx = pathutil.canonpath(repo.root, cwd, pat)
             if len(abspfx) < len(srcs[0][0]):
                 # A directory. Either the target path contains the last
                 # component of the source path or it does not.
                 def evalpath(striplen):
                     score = 0
                     for s in srcs:
                         t = os.path.join(dest, util.localpath(s[0])[striplen:])
                         if os.path.lexists(t):
                             score += 1
                     return score
 
                 abspfx = util.localpath(abspfx)
                 striplen = len(abspfx)
                 if striplen:
                     striplen += len(pycompat.ossep)
                 if os.path.isdir(os.path.join(dest, os.path.split(abspfx)[1])):
                     score = evalpath(striplen)
                     striplen1 = len(os.path.split(abspfx)[0])
                     if striplen1:
                         striplen1 += len(pycompat.ossep)
                     if evalpath(striplen1) > score:
                         striplen = striplen1
                 res = lambda p: os.path.join(dest, util.localpath(p)[striplen:])
             else:
                 # a file
                 if destdirexists:
                     res = lambda p: os.path.join(
                         dest, os.path.basename(util.localpath(p))
                     )
                 else:
                     res = lambda p: dest
         return res
 
     pats = scmutil.expandpats(pats)
     if not pats:
         raise error.Abort(_(b'no source or destination specified'))
     if len(pats) == 1:
         raise error.Abort(_(b'no destination specified'))
     dest = pats.pop()
     destdirexists = os.path.isdir(dest) and not os.path.islink(dest)
     if not destdirexists:
         if len(pats) > 1 or matchmod.patkind(pats[0]):
             raise error.Abort(
                 _(
                     b'with multiple sources, destination must be an '
                     b'existing directory'
                 )
             )
         if util.endswithsep(dest):
             raise error.Abort(_(b'destination %s is not a directory') % dest)
 
     tfn = targetpathfn
     if after:
         tfn = targetpathafterfn
     copylist = []
     for pat in pats:
         srcs = walkpat(pat)
         if not srcs:
             continue
         copylist.append((tfn(pat, dest, srcs), srcs))
     if not copylist:
         raise error.Abort(_(b'no files to copy'))
 
     errors = 0
     for targetpath, srcs in copylist:
         for abssrc, relsrc, exact in srcs:
             if copyfile(abssrc, relsrc, targetpath(abssrc), exact):
                 errors += 1
 
     return errors != 0
 
 
 ## facility to let extension process additional data into an import patch
 # list of identifier to be executed in order
 extrapreimport = []  # run before commit
 extrapostimport = []  # run after commit
 # mapping from identifier to actual import function
 #
 # 'preimport' are run before the commit is made and are provided the following
 # arguments:
 # - repo: the localrepository instance,
 # - patchdata: data extracted from patch header (cf m.patch.patchheadermap),
 # - extra: the future extra dictionary of the changeset, please mutate it,
 # - opts: the import options.
 # XXX ideally, we would just pass an ctx ready to be computed, that would allow
 # mutation of in memory commit and more. Feel free to rework the code to get
 # there.
 extrapreimportmap = {}
 # 'postimport' are run after the commit is made and are provided the following
 # argument:
 # - ctx: the changectx created by import.
 extrapostimportmap = {}
 
 
 def tryimportone(ui, repo, patchdata, parents, opts, msgs, updatefunc):
     """Utility function used by commands.import to import a single patch
 
     This function is explicitly defined here to help the evolve extension to
     wrap this part of the import logic.
 
     The API is currently a bit ugly because it a simple code translation from
     the import command. Feel free to make it better.
 
     :patchdata: a dictionary containing parsed patch data (such as from
                 ``patch.extract()``)
     :parents: nodes that will be parent of the created commit
     :opts: the full dict of option passed to the import command
     :msgs: list to save commit message to.
            (used in case we need to save it when failing)
     :updatefunc: a function that update a repo to a given node
                  updatefunc(<repo>, <node>)
     """
     # avoid cycle context -> subrepo -> cmdutil
     from . import context
 
     tmpname = patchdata.get(b'filename')
     message = patchdata.get(b'message')
     user = opts.get(b'user') or patchdata.get(b'user')
     date = opts.get(b'date') or patchdata.get(b'date')
     branch = patchdata.get(b'branch')
     nodeid = patchdata.get(b'nodeid')
     p1 = patchdata.get(b'p1')
     p2 = patchdata.get(b'p2')
 
     nocommit = opts.get(b'no_commit')
     importbranch = opts.get(b'import_branch')
     update = not opts.get(b'bypass')
     strip = opts[b"strip"]
     prefix = opts[b"prefix"]
     sim = float(opts.get(b'similarity') or 0)
 
     if not tmpname:
         return None, None, False
 
     rejects = False
 
     cmdline_message = logmessage(ui, opts)
     if cmdline_message:
         # pickup the cmdline msg
         message = cmdline_message
     elif message:
         # pickup the patch msg
         message = message.strip()
     else:
         # launch the editor
         message = None
     ui.debug(b'message:\n%s\n' % (message or b''))
 
     if len(parents) == 1:
         parents.append(repo[nullid])
     if opts.get(b'exact'):
         if not nodeid or not p1:
             raise error.Abort(_(b'not a Mercurial patch'))
         p1 = repo[p1]
         p2 = repo[p2 or nullid]
     elif p2:
         try:
             p1 = repo[p1]
             p2 = repo[p2]
             # Without any options, consider p2 only if the
             # patch is being applied on top of the recorded
             # first parent.
             if p1 != parents[0]:
                 p1 = parents[0]
                 p2 = repo[nullid]
         except error.RepoError:
             p1, p2 = parents
         if p2.node() == nullid:
             ui.warn(
                 _(
                     b"warning: import the patch as a normal revision\n"
                     b"(use --exact to import the patch as a merge)\n"
                 )
             )
     else:
         p1, p2 = parents
 
     n = None
     if update:
         if p1 != parents[0]:
             updatefunc(repo, p1.node())
         if p2 != parents[1]:
             repo.setparents(p1.node(), p2.node())
 
         if opts.get(b'exact') or importbranch:
             repo.dirstate.setbranch(branch or b'default')
 
         partial = opts.get(b'partial', False)
         files = set()
         try:
             patch.patch(
                 ui,
                 repo,
                 tmpname,
                 strip=strip,
                 prefix=prefix,
                 files=files,
                 eolmode=None,
                 similarity=sim / 100.0,
             )
         except error.PatchError as e:
             if not partial:
                 raise error.Abort(pycompat.bytestr(e))
             if partial:
                 rejects = True
 
         files = list(files)
         if nocommit:
             if message:
                 msgs.append(message)
         else:
             if opts.get(b'exact') or p2:
                 # If you got here, you either use --force and know what
                 # you are doing or used --exact or a merge patch while
                 # being updated to its first parent.
                 m = None
             else:
                 m = scmutil.matchfiles(repo, files or [])
             editform = mergeeditform(repo[None], b'import.normal')
             if opts.get(b'exact'):
                 editor = None
             else:
                 editor = getcommiteditor(
                     editform=editform, **pycompat.strkwargs(opts)
                 )
             extra = {}
             for idfunc in extrapreimport:
                 extrapreimportmap[idfunc](repo, patchdata, extra, opts)
             overrides = {}
             if partial:
                 overrides[(b'ui', b'allowemptycommit')] = True
             if opts.get(b'secret'):
                 overrides[(b'phases', b'new-commit')] = b'secret'
             with repo.ui.configoverride(overrides, b'import'):
                 n = repo.commit(
                     message, user, date, match=m, editor=editor, extra=extra
                 )
                 for idfunc in extrapostimport:
                     extrapostimportmap[idfunc](repo[n])
     else:
         if opts.get(b'exact') or importbranch:
             branch = branch or b'default'
         else:
             branch = p1.branch()
         store = patch.filestore()
         try:
             files = set()
             try:
                 patch.patchrepo(
                     ui,
                     repo,
                     p1,
                     store,
                     tmpname,
                     strip,
                     prefix,
                     files,
                     eolmode=None,
                 )
             except error.PatchError as e:
                 raise error.Abort(stringutil.forcebytestr(e))
             if opts.get(b'exact'):
                 editor = None
             else:
                 editor = getcommiteditor(editform=b'import.bypass')
             memctx = context.memctx(
                 repo,
                 (p1.node(), p2.node()),
                 message,
                 files=files,
                 filectxfn=store,
                 user=user,
                 date=date,
                 branch=branch,
                 editor=editor,
             )
             n = memctx.commit()
         finally:
             store.close()
     if opts.get(b'exact') and nocommit:
         # --exact with --no-commit is still useful in that it does merge
         # and branch bits
         ui.warn(_(b"warning: can't check exact import with --no-commit\n"))
     elif opts.get(b'exact') and (not n or hex(n) != nodeid):
         raise error.Abort(_(b'patch is damaged or loses information'))
     msg = _(b'applied to working directory')
     if n:
         # i18n: refers to a short changeset id
         msg = _(b'created %s') % short(n)
     return msg, n, rejects
 
 
 # facility to let extensions include additional data in an exported patch
 # list of identifiers to be executed in order
 extraexport = []
 # mapping from identifier to actual export function
 # function as to return a string to be added to the header or None
 # it is given two arguments (sequencenumber, changectx)
 extraexportmap = {}
 
 
 def _exportsingle(repo, ctx, fm, match, switch_parent, seqno, diffopts):
     node = scmutil.binnode(ctx)
     parents = [p.node() for p in ctx.parents() if p]
     branch = ctx.branch()
     if switch_parent:
         parents.reverse()
 
     if parents:
         prev = parents[0]
     else:
         prev = nullid
 
     fm.context(ctx=ctx)
     fm.plain(b'# HG changeset patch\n')
     fm.write(b'user', b'# User %s\n', ctx.user())
     fm.plain(b'# Date %d %d\n' % ctx.date())
     fm.write(b'date', b'#      %s\n', fm.formatdate(ctx.date()))
     fm.condwrite(
         branch and branch != b'default', b'branch', b'# Branch %s\n', branch
     )
     fm.write(b'node', b'# Node ID %s\n', hex(node))
     fm.plain(b'# Parent  %s\n' % hex(prev))
     if len(parents) > 1:
         fm.plain(b'# Parent  %s\n' % hex(parents[1]))
     fm.data(parents=fm.formatlist(pycompat.maplist(hex, parents), name=b'node'))
 
     # TODO: redesign extraexportmap function to support formatter
     for headerid in extraexport:
         header = extraexportmap[headerid](seqno, ctx)
         if header is not None:
             fm.plain(b'# %s\n' % header)
 
     fm.write(b'desc', b'%s\n', ctx.description().rstrip())
     fm.plain(b'\n')
 
     if fm.isplain():
         chunkiter = patch.diffui(repo, prev, node, match, opts=diffopts)
         for chunk, label in chunkiter:
             fm.plain(chunk, label=label)
     else:
         chunkiter = patch.diff(repo, prev, node, match, opts=diffopts)
         # TODO: make it structured?
         fm.data(diff=b''.join(chunkiter))
 
 
 def _exportfile(repo, revs, fm, dest, switch_parent, diffopts, match):
     """Export changesets to stdout or a single file"""
     for seqno, rev in enumerate(revs, 1):
         ctx = repo[rev]
         if not dest.startswith(b'<'):
             repo.ui.note(b"%s\n" % dest)
         fm.startitem()
         _exportsingle(repo, ctx, fm, match, switch_parent, seqno, diffopts)
 
 
 def _exportfntemplate(
     repo, revs, basefm, fntemplate, switch_parent, diffopts, match
 ):
     """Export changesets to possibly multiple files"""
     total = len(revs)
     revwidth = max(len(str(rev)) for rev in revs)
     filemap = util.sortdict()  # filename: [(seqno, rev), ...]
 
     for seqno, rev in enumerate(revs, 1):
         ctx = repo[rev]
         dest = makefilename(
             ctx, fntemplate, total=total, seqno=seqno, revwidth=revwidth
         )
         filemap.setdefault(dest, []).append((seqno, rev))
 
     for dest in filemap:
         with formatter.maybereopen(basefm, dest) as fm:
             repo.ui.note(b"%s\n" % dest)
             for seqno, rev in filemap[dest]:
                 fm.startitem()
                 ctx = repo[rev]
                 _exportsingle(
                     repo, ctx, fm, match, switch_parent, seqno, diffopts
                 )
 
 
 def _prefetchchangedfiles(repo, revs, match):
     allfiles = set()
     for rev in revs:
         for file in repo[rev].files():
             if not match or match(file):
                 allfiles.add(file)
     scmutil.prefetchfiles(repo, revs, scmutil.matchfiles(repo, allfiles))
 
 
 def export(
     repo,
     revs,
     basefm,
     fntemplate=b'hg-%h.patch',
     switch_parent=False,
     opts=None,
     match=None,
 ):
     '''export changesets as hg patches
 
     Args:
       repo: The repository from which we're exporting revisions.
       revs: A list of revisions to export as revision numbers.
       basefm: A formatter to which patches should be written.
       fntemplate: An optional string to use for generating patch file names.
       switch_parent: If True, show diffs against second parent when not nullid.
                      Default is false, which always shows diff against p1.
       opts: diff options to use for generating the patch.
       match: If specified, only export changes to files matching this matcher.
 
     Returns:
       Nothing.
 
     Side Effect:
       "HG Changeset Patch" data is emitted to one of the following
       destinations:
         fntemplate specified: Each rev is written to a unique file named using
                             the given template.
         Otherwise: All revs will be written to basefm.
     '''
     _prefetchchangedfiles(repo, revs, match)
 
     if not fntemplate:
         _exportfile(
             repo, revs, basefm, b'<unnamed>', switch_parent, opts, match
         )
     else:
         _exportfntemplate(
             repo, revs, basefm, fntemplate, switch_parent, opts, match
         )
 
 
 def exportfile(repo, revs, fp, switch_parent=False, opts=None, match=None):
     """Export changesets to the given file stream"""
     _prefetchchangedfiles(repo, revs, match)
 
     dest = getattr(fp, 'name', b'<unnamed>')
     with formatter.formatter(repo.ui, fp, b'export', {}) as fm:
         _exportfile(repo, revs, fm, dest, switch_parent, opts, match)
 
 
 def showmarker(fm, marker, index=None):
     """utility function to display obsolescence marker in a readable way
 
     To be used by debug function."""
     if index is not None:
         fm.write(b'index', b'%i ', index)
     fm.write(b'prednode', b'%s ', hex(marker.prednode()))
     succs = marker.succnodes()
     fm.condwrite(
         succs,
         b'succnodes',
         b'%s ',
         fm.formatlist(map(hex, succs), name=b'node'),
     )
     fm.write(b'flag', b'%X ', marker.flags())
     parents = marker.parentnodes()
     if parents is not None:
         fm.write(
             b'parentnodes',
             b'{%s} ',
             fm.formatlist(map(hex, parents), name=b'node', sep=b', '),
         )
     fm.write(b'date', b'(%s) ', fm.formatdate(marker.date()))
     meta = marker.metadata().copy()
     meta.pop(b'date', None)
     smeta = pycompat.rapply(pycompat.maybebytestr, meta)
     fm.write(
         b'metadata', b'{%s}', fm.formatdict(smeta, fmt=b'%r: %r', sep=b', ')
     )
     fm.plain(b'\n')
 
 
 def finddate(ui, repo, date):
     """Find the tipmost changeset that matches the given date spec"""
 
     df = dateutil.matchdate(date)
     m = scmutil.matchall(repo)
     results = {}
 
     def prep(ctx, fns):
         d = ctx.date()
         if df(d[0]):
             results[ctx.rev()] = d
 
     for ctx in walkchangerevs(repo, m, {b'rev': None}, prep):
         rev = ctx.rev()
         if rev in results:
             ui.status(
                 _(b"found revision %d from %s\n")
                 % (rev, dateutil.datestr(results[rev]))
             )
             return b'%d' % rev
 
     raise error.Abort(_(b"revision matching date not found"))
 
 
 def increasingwindows(windowsize=8, sizelimit=512):
     while True:
         yield windowsize
         if windowsize < sizelimit:
             windowsize *= 2
 
 
 def _walkrevs(repo, opts):
     # Default --rev value depends on --follow but --follow behavior
     # depends on revisions resolved from --rev...
     follow = opts.get(b'follow') or opts.get(b'follow_first')
     if opts.get(b'rev'):
         revs = scmutil.revrange(repo, opts[b'rev'])
     elif follow and repo.dirstate.p1() == nullid:
         revs = smartset.baseset()
     elif follow:
         revs = repo.revs(b'reverse(:.)')
     else:
         revs = smartset.spanset(repo)
         revs.reverse()
     return revs
 
 
 class FileWalkError(Exception):
     pass
 
 
 def walkfilerevs(repo, match, follow, revs, fncache):
     '''Walks the file history for the matched files.
 
     Returns the changeset revs that are involved in the file history.
 
     Throws FileWalkError if the file history can't be walked using
     filelogs alone.
     '''
     wanted = set()
     copies = []
     minrev, maxrev = min(revs), max(revs)
 
     def filerevs(filelog, last):
         """
         Only files, no patterns.  Check the history of each file.
 
         Examines filelog entries within minrev, maxrev linkrev range
         Returns an iterator yielding (linkrev, parentlinkrevs, copied)
         tuples in backwards order
         """
         cl_count = len(repo)
         revs = []
         for j in pycompat.xrange(0, last + 1):
             linkrev = filelog.linkrev(j)
             if linkrev < minrev:
                 continue
             # only yield rev for which we have the changelog, it can
             # happen while doing "hg log" during a pull or commit
             if linkrev >= cl_count:
                 break
 
             parentlinkrevs = []
             for p in filelog.parentrevs(j):
                 if p != nullrev:
                     parentlinkrevs.append(filelog.linkrev(p))
             n = filelog.node(j)
             revs.append(
                 (linkrev, parentlinkrevs, follow and filelog.renamed(n))
             )
 
         return reversed(revs)
 
     def iterfiles():
         pctx = repo[b'.']
         for filename in match.files():
             if follow:
                 if filename not in pctx:
                     raise error.Abort(
                         _(
                             b'cannot follow file not in parent '
                             b'revision: "%s"'
                         )
                         % filename
                     )
                 yield filename, pctx[filename].filenode()
             else:
                 yield filename, None
         for filename_node in copies:
             yield filename_node
 
     for file_, node in iterfiles():
         filelog = repo.file(file_)
         if not len(filelog):
             if node is None:
                 # A zero count may be a directory or deleted file, so
                 # try to find matching entries on the slow path.
                 if follow:
                     raise error.Abort(
                         _(b'cannot follow nonexistent file: "%s"') % file_
                     )
                 raise FileWalkError(b"Cannot walk via filelog")
             else:
                 continue
 
         if node is None:
             last = len(filelog) - 1
         else:
             last = filelog.rev(node)
 
         # keep track of all ancestors of the file
         ancestors = {filelog.linkrev(last)}
 
         # iterate from latest to oldest revision
         for rev, flparentlinkrevs, copied in filerevs(filelog, last):
             if not follow:
                 if rev > maxrev:
                     continue
             else:
                 # Note that last might not be the first interesting
                 # rev to us:
                 # if the file has been changed after maxrev, we'll
                 # have linkrev(last) > maxrev, and we still need
                 # to explore the file graph
                 if rev not in ancestors:
                     continue
                 # XXX insert 1327 fix here
                 if flparentlinkrevs:
                     ancestors.update(flparentlinkrevs)
 
             fncache.setdefault(rev, []).append(file_)
             wanted.add(rev)
             if copied:
                 copies.append(copied)
 
     return wanted
 
 
 class _followfilter(object):
     def __init__(self, repo, onlyfirst=False):
         self.repo = repo
         self.startrev = nullrev
         self.roots = set()
         self.onlyfirst = onlyfirst
 
     def match(self, rev):
         def realparents(rev):
             if self.onlyfirst:
                 return self.repo.changelog.parentrevs(rev)[0:1]
             else:
                 return filter(
                     lambda x: x != nullrev, self.repo.changelog.parentrevs(rev)
                 )
 
         if self.startrev == nullrev:
             self.startrev = rev
             return True
 
         if rev > self.startrev:
             # forward: all descendants
             if not self.roots:
                 self.roots.add(self.startrev)
             for parent in realparents(rev):
                 if parent in self.roots:
                     self.roots.add(rev)
                     return True
         else:
             # backwards: all parents
             if not self.roots:
                 self.roots.update(realparents(self.startrev))
             if rev in self.roots:
                 self.roots.remove(rev)
                 self.roots.update(realparents(rev))
                 return True
 
         return False
 
 
 def walkchangerevs(repo, match, opts, prepare):
     '''Iterate over files and the revs in which they changed.
 
     Callers most commonly need to iterate backwards over the history
     in which they are interested. Doing so has awful (quadratic-looking)
     performance, so we use iterators in a "windowed" way.
 
     We walk a window of revisions in the desired order.  Within the
     window, we first walk forwards to gather data, then in the desired
     order (usually backwards) to display it.
 
     This function returns an iterator yielding contexts. Before
     yielding each context, the iterator will first call the prepare
     function on each context in the window in forward order.'''
 
     allfiles = opts.get(b'all_files')
     follow = opts.get(b'follow') or opts.get(b'follow_first')
     revs = _walkrevs(repo, opts)
     if not revs:
         return []
     wanted = set()
     slowpath = match.anypats() or (not match.always() and opts.get(b'removed'))
     fncache = {}
     change = repo.__getitem__
 
     # First step is to fill wanted, the set of revisions that we want to yield.
     # When it does not induce extra cost, we also fill fncache for revisions in
     # wanted: a cache of filenames that were changed (ctx.files()) and that
     # match the file filtering conditions.
 
     if match.always() or allfiles:
         # No files, no patterns.  Display all revs.
         wanted = revs
     elif not slowpath:
         # We only have to read through the filelog to find wanted revisions
 
         try:
             wanted = walkfilerevs(repo, match, follow, revs, fncache)
         except FileWalkError:
             slowpath = True
 
             # We decided to fall back to the slowpath because at least one
             # of the paths was not a file. Check to see if at least one of them
             # existed in history, otherwise simply return
             for path in match.files():
                 if path == b'.' or path in repo.store:
                     break
             else:
                 return []
 
     if slowpath:
         # We have to read the changelog to match filenames against
         # changed files
 
         if follow:
             raise error.Abort(
                 _(b'can only follow copies/renames for explicit filenames')
             )
 
         # The slow path checks files modified in every changeset.
         # This is really slow on large repos, so compute the set lazily.
         class lazywantedset(object):
             def __init__(self):
                 self.set = set()
                 self.revs = set(revs)
 
             # No need to worry about locality here because it will be accessed
             # in the same order as the increasing window below.
             def __contains__(self, value):
                 if value in self.set:
                     return True
                 elif not value in self.revs:
                     return False
                 else:
                     self.revs.discard(value)
                     ctx = change(value)
                     if allfiles:
                         matches = list(ctx.manifest().walk(match))
                     else:
                         matches = [f for f in ctx.files() if match(f)]
                     if matches:
                         fncache[value] = matches
                         self.set.add(value)
                         return True
                     return False
 
             def discard(self, value):
                 self.revs.discard(value)
                 self.set.discard(value)
 
         wanted = lazywantedset()
 
     # it might be worthwhile to do this in the iterator if the rev range
     # is descending and the prune args are all within that range
     for rev in opts.get(b'prune', ()):
         rev = repo[rev].rev()
         ff = _followfilter(repo)
         stop = min(revs[0], revs[-1])
         for x in pycompat.xrange(rev, stop - 1, -1):
             if ff.match(x):
                 wanted = wanted - [x]
 
     # Now that wanted is correctly initialized, we can iterate over the
     # revision range, yielding only revisions in wanted.
     def iterate():
         if follow and match.always():
             ff = _followfilter(repo, onlyfirst=opts.get(b'follow_first'))
 
             def want(rev):
                 return ff.match(rev) and rev in wanted
 
         else:
 
             def want(rev):
                 return rev in wanted
 
         it = iter(revs)
         stopiteration = False
         for windowsize in increasingwindows():
             nrevs = []
             for i in pycompat.xrange(windowsize):
                 rev = next(it, None)
                 if rev is None:
                     stopiteration = True
                     break
                 elif want(rev):
                     nrevs.append(rev)
             for rev in sorted(nrevs):
                 fns = fncache.get(rev)
                 ctx = change(rev)
                 if not fns:
 
                     def fns_generator():
                         if allfiles:
                             fiter = iter(ctx)
                         else:
                             fiter = ctx.files()
                         for f in fiter:
                             if match(f):
                                 yield f
 
                     fns = fns_generator()
                 prepare(ctx, fns)
             for rev in nrevs:
                 yield change(rev)
 
             if stopiteration:
                 break
 
     return iterate()
 
 
 def add(ui, repo, match, prefix, uipathfn, explicitonly, **opts):
     bad = []
 
     badfn = lambda x, y: bad.append(x) or match.bad(x, y)
     names = []
     wctx = repo[None]
     cca = None
     abort, warn = scmutil.checkportabilityalert(ui)
     if abort or warn:
         cca = scmutil.casecollisionauditor(ui, abort, repo.dirstate)
 
     match = repo.narrowmatch(match, includeexact=True)
     badmatch = matchmod.badmatch(match, badfn)
     dirstate = repo.dirstate
     # We don't want to just call wctx.walk here, since it would return a lot of
     # clean files, which we aren't interested in and takes time.
     for f in sorted(
         dirstate.walk(
             badmatch,
             subrepos=sorted(wctx.substate),
             unknown=True,
             ignored=False,
             full=False,
         )
     ):
         exact = match.exact(f)
         if exact or not explicitonly and f not in wctx and repo.wvfs.lexists(f):
             if cca:
                 cca(f)
             names.append(f)
             if ui.verbose or not exact:
                 ui.status(
                     _(b'adding %s\n') % uipathfn(f), label=b'ui.addremove.added'
                 )
 
     for subpath in sorted(wctx.substate):
         sub = wctx.sub(subpath)
         try:
             submatch = matchmod.subdirmatcher(subpath, match)
             subprefix = repo.wvfs.reljoin(prefix, subpath)
             subuipathfn = scmutil.subdiruipathfn(subpath, uipathfn)
             if opts.get('subrepos'):
                 bad.extend(
                     sub.add(ui, submatch, subprefix, subuipathfn, False, **opts)
                 )
             else:
                 bad.extend(
                     sub.add(ui, submatch, subprefix, subuipathfn, True, **opts)
                 )
         except error.LookupError:
             ui.status(
                 _(b"skipping missing subrepository: %s\n") % uipathfn(subpath)
             )
 
     if not opts.get('dry_run'):
         rejected = wctx.add(names, prefix)
         bad.extend(f for f in rejected if f in match.files())
     return bad
 
 
 def addwebdirpath(repo, serverpath, webconf):
     webconf[serverpath] = repo.root
     repo.ui.debug(b'adding %s = %s\n' % (serverpath, repo.root))
 
     for r in repo.revs(b'filelog("path:.hgsub")'):
         ctx = repo[r]
         for subpath in ctx.substate:
             ctx.sub(subpath).addwebdirpath(serverpath, webconf)
 
 
 def forget(
     ui, repo, match, prefix, uipathfn, explicitonly, dryrun, interactive
 ):
     if dryrun and interactive:
         raise error.Abort(_(b"cannot specify both --dry-run and --interactive"))
     bad = []
     badfn = lambda x, y: bad.append(x) or match.bad(x, y)
     wctx = repo[None]
     forgot = []
 
     s = repo.status(match=matchmod.badmatch(match, badfn), clean=True)
     forget = sorted(s.modified + s.added + s.deleted + s.clean)
     if explicitonly:
         forget = [f for f in forget if match.exact(f)]
 
     for subpath in sorted(wctx.substate):
         sub = wctx.sub(subpath)
         submatch = matchmod.subdirmatcher(subpath, match)
         subprefix = repo.wvfs.reljoin(prefix, subpath)
         subuipathfn = scmutil.subdiruipathfn(subpath, uipathfn)
         try:
             subbad, subforgot = sub.forget(
                 submatch,
                 subprefix,
                 subuipathfn,
                 dryrun=dryrun,
                 interactive=interactive,
             )
             bad.extend([subpath + b'/' + f for f in subbad])
             forgot.extend([subpath + b'/' + f for f in subforgot])
         except error.LookupError:
             ui.status(
                 _(b"skipping missing subrepository: %s\n") % uipathfn(subpath)
             )
 
     if not explicitonly:
         for f in match.files():
             if f not in repo.dirstate and not repo.wvfs.isdir(f):
                 if f not in forgot:
                     if repo.wvfs.exists(f):
                         # Don't complain if the exact case match wasn't given.
                         # But don't do this until after checking 'forgot', so
                         # that subrepo files aren't normalized, and this op is
                         # purely from data cached by the status walk above.
                         if repo.dirstate.normalize(f) in repo.dirstate:
                             continue
                         ui.warn(
                             _(
                                 b'not removing %s: '
                                 b'file is already untracked\n'
                             )
                             % uipathfn(f)
                         )
                     bad.append(f)
 
     if interactive:
         responses = _(
             b'[Ynsa?]'
             b'$$ &Yes, forget this file'
             b'$$ &No, skip this file'
             b'$$ &Skip remaining files'
             b'$$ Include &all remaining files'
             b'$$ &? (display help)'
         )
         for filename in forget[:]:
             r = ui.promptchoice(
                 _(b'forget %s %s') % (uipathfn(filename), responses)
             )
             if r == 4:  # ?
                 while r == 4:
                     for c, t in ui.extractchoices(responses)[1]:
                         ui.write(b'%s - %s\n' % (c, encoding.lower(t)))
                     r = ui.promptchoice(
                         _(b'forget %s %s') % (uipathfn(filename), responses)
                     )
             if r == 0:  # yes
                 continue
             elif r == 1:  # no
                 forget.remove(filename)
             elif r == 2:  # Skip
                 fnindex = forget.index(filename)
                 del forget[fnindex:]
                 break
             elif r == 3:  # All
                 break
 
     for f in forget:
         if ui.verbose or not match.exact(f) or interactive:
             ui.status(
                 _(b'removing %s\n') % uipathfn(f), label=b'ui.addremove.removed'
             )
 
     if not dryrun:
         rejected = wctx.forget(forget, prefix)
         bad.extend(f for f in rejected if f in match.files())
         forgot.extend(f for f in forget if f not in rejected)
     return bad, forgot
 
 
 def files(ui, ctx, m, uipathfn, fm, fmt, subrepos):
     ret = 1
 
     needsfctx = ui.verbose or {b'size', b'flags'} & fm.datahint()
     for f in ctx.matches(m):
         fm.startitem()
         fm.context(ctx=ctx)
         if needsfctx:
             fc = ctx[f]
             fm.write(b'size flags', b'% 10d % 1s ', fc.size(), fc.flags())
         fm.data(path=f)
         fm.plain(fmt % uipathfn(f))
         ret = 0
 
     for subpath in sorted(ctx.substate):
         submatch = matchmod.subdirmatcher(subpath, m)
         subuipathfn = scmutil.subdiruipathfn(subpath, uipathfn)
         if subrepos or m.exact(subpath) or any(submatch.files()):
             sub = ctx.sub(subpath)
             try:
                 recurse = m.exact(subpath) or subrepos
                 if (
                     sub.printfiles(ui, submatch, subuipathfn, fm, fmt, recurse)
                     == 0
                 ):
                     ret = 0
             except error.LookupError:
                 ui.status(
                     _(b"skipping missing subrepository: %s\n")
                     % uipathfn(subpath)
                 )
 
     return ret
 
 
 def remove(
     ui, repo, m, prefix, uipathfn, after, force, subrepos, dryrun, warnings=None
 ):
     ret = 0
     s = repo.status(match=m, clean=True)
     modified, added, deleted, clean = s.modified, s.added, s.deleted, s.clean
 
     wctx = repo[None]
 
     if warnings is None:
         warnings = []
         warn = True
     else:
         warn = False
 
     subs = sorted(wctx.substate)
     progress = ui.makeprogress(
         _(b'searching'), total=len(subs), unit=_(b'subrepos')
     )
     for subpath in subs:
         submatch = matchmod.subdirmatcher(subpath, m)
         subprefix = repo.wvfs.reljoin(prefix, subpath)
         subuipathfn = scmutil.subdiruipathfn(subpath, uipathfn)
         if subrepos or m.exact(subpath) or any(submatch.files()):
             progress.increment()
             sub = wctx.sub(subpath)
             try:
                 if sub.removefiles(
                     submatch,
                     subprefix,
                     subuipathfn,
                     after,
                     force,
                     subrepos,
                     dryrun,
                     warnings,
                 ):
                     ret = 1
             except error.LookupError:
                 warnings.append(
                     _(b"skipping missing subrepository: %s\n")
                     % uipathfn(subpath)
                 )
     progress.complete()
 
     # warn about failure to delete explicit files/dirs
     deleteddirs = pathutil.dirs(deleted)
     files = m.files()
     progress = ui.makeprogress(
         _(b'deleting'), total=len(files), unit=_(b'files')
     )
     for f in files:
 
         def insubrepo():
             for subpath in wctx.substate:
                 if f.startswith(subpath + b'/'):
                     return True
             return False
 
         progress.increment()
         isdir = f in deleteddirs or wctx.hasdir(f)
         if f in repo.dirstate or isdir or f == b'.' or insubrepo() or f in subs:
             continue
 
         if repo.wvfs.exists(f):
             if repo.wvfs.isdir(f):
                 warnings.append(
                     _(b'not removing %s: no tracked files\n') % uipathfn(f)
                 )
             else:
                 warnings.append(
                     _(b'not removing %s: file is untracked\n') % uipathfn(f)
                 )
         # missing files will generate a warning elsewhere
         ret = 1
     progress.complete()
 
     if force:
         list = modified + deleted + clean + added
     elif after:
         list = deleted
         remaining = modified + added + clean
         progress = ui.makeprogress(
             _(b'skipping'), total=len(remaining), unit=_(b'files')
         )
         for f in remaining:
             progress.increment()
             if ui.verbose or (f in files):
                 warnings.append(
                     _(b'not removing %s: file still exists\n') % uipathfn(f)
                 )
             ret = 1
         progress.complete()
     else:
         list = deleted + clean
         progress = ui.makeprogress(
             _(b'skipping'), total=(len(modified) + len(added)), unit=_(b'files')
         )
         for f in modified:
             progress.increment()
             warnings.append(
                 _(
                     b'not removing %s: file is modified (use -f'
                     b' to force removal)\n'
                 )
                 % uipathfn(f)
             )
             ret = 1
         for f in added:
             progress.increment()
             warnings.append(
                 _(
                     b"not removing %s: file has been marked for add"
                     b" (use 'hg forget' to undo add)\n"
                 )
                 % uipathfn(f)
             )
             ret = 1
         progress.complete()
 
     list = sorted(list)
     progress = ui.makeprogress(
         _(b'deleting'), total=len(list), unit=_(b'files')
     )
     for f in list:
         if ui.verbose or not m.exact(f):
             progress.increment()
             ui.status(
                 _(b'removing %s\n') % uipathfn(f), label=b'ui.addremove.removed'
             )
     progress.complete()
 
     if not dryrun:
         with repo.wlock():
             if not after:
                 for f in list:
                     if f in added:
                         continue  # we never unlink added files on remove
                     rmdir = repo.ui.configbool(
                         b'experimental', b'removeemptydirs'
                     )
                     repo.wvfs.unlinkpath(f, ignoremissing=True, rmdir=rmdir)
             repo[None].forget(list)
 
     if warn:
         for warning in warnings:
             ui.warn(warning)
 
     return ret
 
 
 def _catfmtneedsdata(fm):
     return not fm.datahint() or b'data' in fm.datahint()
 
 
 def _updatecatformatter(fm, ctx, matcher, path, decode):
     """Hook for adding data to the formatter used by ``hg cat``.
 
     Extensions (e.g., lfs) can wrap this to inject keywords/data, but must call
     this method first."""
 
     # data() can be expensive to fetch (e.g. lfs), so don't fetch it if it
     # wasn't requested.
     data = b''
     if _catfmtneedsdata(fm):
         data = ctx[path].data()
         if decode:
             data = ctx.repo().wwritedata(path, data)
     fm.startitem()
     fm.context(ctx=ctx)
     fm.write(b'data', b'%s', data)
     fm.data(path=path)
 
 
 def cat(ui, repo, ctx, matcher, basefm, fntemplate, prefix, **opts):
     err = 1
     opts = pycompat.byteskwargs(opts)
 
     def write(path):
         filename = None
         if fntemplate:
             filename = makefilename(
                 ctx, fntemplate, pathname=os.path.join(prefix, path)
             )
             # attempt to create the directory if it does not already exist
             try:
                 os.makedirs(os.path.dirname(filename))
             except OSError:
                 pass
         with formatter.maybereopen(basefm, filename) as fm:
             _updatecatformatter(fm, ctx, matcher, path, opts.get(b'decode'))
 
     # Automation often uses hg cat on single files, so special case it
     # for performance to avoid the cost of parsing the manifest.
     if len(matcher.files()) == 1 and not matcher.anypats():
         file = matcher.files()[0]
         mfl = repo.manifestlog
         mfnode = ctx.manifestnode()
         try:
             if mfnode and mfl[mfnode].find(file)[0]:
                 if _catfmtneedsdata(basefm):
                     scmutil.prefetchfiles(repo, [ctx.rev()], matcher)
                 write(file)
                 return 0
         except KeyError:
             pass
 
     if _catfmtneedsdata(basefm):
         scmutil.prefetchfiles(repo, [ctx.rev()], matcher)
 
     for abs in ctx.walk(matcher):
         write(abs)
         err = 0
 
     uipathfn = scmutil.getuipathfn(repo, legacyrelativevalue=True)
     for subpath in sorted(ctx.substate):
         sub = ctx.sub(subpath)
         try:
             submatch = matchmod.subdirmatcher(subpath, matcher)
             subprefix = os.path.join(prefix, subpath)
             if not sub.cat(
                 submatch,
                 basefm,
                 fntemplate,
                 subprefix,
                 **pycompat.strkwargs(opts)
             ):
                 err = 0
         except error.RepoLookupError:
             ui.status(
                 _(b"skipping missing subrepository: %s\n") % uipathfn(subpath)
             )
 
     return err
 
 
 def commit(ui, repo, commitfunc, pats, opts):
     '''commit the specified files or all outstanding changes'''
     date = opts.get(b'date')
     if date:
         opts[b'date'] = dateutil.parsedate(date)
     message = logmessage(ui, opts)
     matcher = scmutil.match(repo[None], pats, opts)
 
     dsguard = None
     # extract addremove carefully -- this function can be called from a command
     # that doesn't support addremove
     if opts.get(b'addremove'):
         dsguard = dirstateguard.dirstateguard(repo, b'commit')
     with dsguard or util.nullcontextmanager():
         if dsguard:
             relative = scmutil.anypats(pats, opts)
             uipathfn = scmutil.getuipathfn(repo, legacyrelativevalue=relative)
             if scmutil.addremove(repo, matcher, b"", uipathfn, opts) != 0:
                 raise error.Abort(
                     _(b"failed to mark all new/missing files as added/removed")
                 )
 
         return commitfunc(ui, repo, message, matcher, opts)
 
 
 def samefile(f, ctx1, ctx2):
     if f in ctx1.manifest():
         a = ctx1.filectx(f)
         if f in ctx2.manifest():
             b = ctx2.filectx(f)
             return not a.cmp(b) and a.flags() == b.flags()
         else:
             return False
     else:
         return f not in ctx2.manifest()
 
 
 def amend(ui, repo, old, extra, pats, opts):
     # avoid cycle context -> subrepo -> cmdutil
     from . import context
 
     # amend will reuse the existing user if not specified, but the obsolete
     # marker creation requires that the current user's name is specified.
     if obsolete.isenabled(repo, obsolete.createmarkersopt):
         ui.username()  # raise exception if username not set
 
     ui.note(_(b'amending changeset %s\n') % old)
     base = old.p1()
 
     with repo.wlock(), repo.lock(), repo.transaction(b'amend'):
         # Participating changesets:
         #
         # wctx     o - workingctx that contains changes from working copy
         #          |   to go into amending commit
         #          |
         # old      o - changeset to amend
         #          |
         # base     o - first parent of the changeset to amend
         wctx = repo[None]
 
         # Copy to avoid mutating input
         extra = extra.copy()
         # Update extra dict from amended commit (e.g. to preserve graft
         # source)
         extra.update(old.extra())
 
         # Also update it from the from the wctx
         extra.update(wctx.extra())
 
         # date-only change should be ignored?
         datemaydiffer = resolvecommitoptions(ui, opts)
 
         date = old.date()
         if opts.get(b'date'):
             date = dateutil.parsedate(opts.get(b'date'))
         user = opts.get(b'user') or old.user()
 
         if len(old.parents()) > 1:
             # ctx.files() isn't reliable for merges, so fall back to the
             # slower repo.status() method
             st = base.status(old)
             files = set(st.modified) | set(st.added) | set(st.removed)
         else:
             files = set(old.files())
 
         # add/remove the files to the working copy if the "addremove" option
         # was specified.
         matcher = scmutil.match(wctx, pats, opts)
         relative = scmutil.anypats(pats, opts)
         uipathfn = scmutil.getuipathfn(repo, legacyrelativevalue=relative)
         if opts.get(b'addremove') and scmutil.addremove(
             repo, matcher, b"", uipathfn, opts
         ):
             raise error.Abort(
                 _(b"failed to mark all new/missing files as added/removed")
             )
 
         # Check subrepos. This depends on in-place wctx._status update in
         # subrepo.precommit(). To minimize the risk of this hack, we do
         # nothing if .hgsub does not exist.
         if b'.hgsub' in wctx or b'.hgsub' in old:
             subs, commitsubs, newsubstate = subrepoutil.precommit(
                 ui, wctx, wctx._status, matcher
             )
             # amend should abort if commitsubrepos is enabled
             assert not commitsubs
             if subs:
                 subrepoutil.writestate(repo, newsubstate)
 
         ms = mergemod.mergestate.read(repo)
         mergeutil.checkunresolved(ms)
 
         filestoamend = set(f for f in wctx.files() if matcher(f))
 
         changes = len(filestoamend) > 0
         if changes:
             # Recompute copies (avoid recording a -> b -> a)
             copied = copies.pathcopies(base, wctx, matcher)
             if old.p2:
                 copied.update(copies.pathcopies(old.p2(), wctx, matcher))
 
             # Prune files which were reverted by the updates: if old
             # introduced file X and the file was renamed in the working
             # copy, then those two files are the same and
             # we can discard X from our list of files. Likewise if X
             # was removed, it's no longer relevant. If X is missing (aka
             # deleted), old X must be preserved.
             files.update(filestoamend)
             files = [
                 f
                 for f in files
                 if (f not in filestoamend or not samefile(f, wctx, base))
             ]
 
             def filectxfn(repo, ctx_, path):
                 try:
                     # If the file being considered is not amongst the files
                     # to be amended, we should return the file context from the
                     # old changeset. This avoids issues when only some files in
                     # the working copy are being amended but there are also
                     # changes to other files from the old changeset.
                     if path not in filestoamend:
                         return old.filectx(path)
 
                     # Return None for removed files.
                     if path in wctx.removed():
                         return None
 
                     fctx = wctx[path]
                     flags = fctx.flags()
                     mctx = context.memfilectx(
                         repo,
                         ctx_,
                         fctx.path(),
                         fctx.data(),
                         islink=b'l' in flags,
                         isexec=b'x' in flags,
                         copysource=copied.get(path),
                     )
                     return mctx
                 except KeyError:
                     return None
 
         else:
             ui.note(_(b'copying changeset %s to %s\n') % (old, base))
 
             # Use version of files as in the old cset
             def filectxfn(repo, ctx_, path):
                 try:
                     return old.filectx(path)
                 except KeyError:
                     return None
 
         # See if we got a message from -m or -l, if not, open the editor with
         # the message of the changeset to amend.
         message = logmessage(ui, opts)
 
         editform = mergeeditform(old, b'commit.amend')
 
         if not message:
             message = old.description()
             # Default if message isn't provided and --edit is not passed is to
             # invoke editor, but allow --no-edit. If somehow we don't have any
             # description, let's always start the editor.
             doedit = not message or opts.get(b'edit') in [True, None]
         else:
             # Default if message is provided is to not invoke editor, but allow
             # --edit.
             doedit = opts.get(b'edit') is True
         editor = getcommiteditor(edit=doedit, editform=editform)
 
         pureextra = extra.copy()
         extra[b'amend_source'] = old.hex()
 
         new = context.memctx(
             repo,
             parents=[base.node(), old.p2().node()],
             text=message,
             files=files,
             filectxfn=filectxfn,
             user=user,
             date=date,
             extra=extra,
             editor=editor,
         )
 
         newdesc = changelog.stripdesc(new.description())
         if (
             (not changes)
             and newdesc == old.description()
             and user == old.user()
             and (date == old.date() or datemaydiffer)
             and pureextra == old.extra()
         ):
             # nothing changed. continuing here would create a new node
             # anyway because of the amend_source noise.
             #
             # This not what we expect from amend.
             return old.node()
 
         commitphase = None
         if opts.get(b'secret'):
             commitphase = phases.secret
         newid = repo.commitctx(new)
 
         # Reroute the working copy parent to the new changeset
         repo.setparents(newid, nullid)
         mapping = {old.node(): (newid,)}
         obsmetadata = None
         if opts.get(b'note'):
             obsmetadata = {b'note': encoding.fromlocal(opts[b'note'])}
         backup = ui.configbool(b'rewrite', b'backup-bundle')
         scmutil.cleanupnodes(
             repo,
             mapping,
             b'amend',
             metadata=obsmetadata,
             fixphase=True,
             targetphase=commitphase,
             backup=backup,
         )
 
         # Fixing the dirstate because localrepo.commitctx does not update
         # it. This is rather convenient because we did not need to update
         # the dirstate for all the files in the new commit which commitctx
         # could have done if it updated the dirstate. Now, we can
         # selectively update the dirstate only for the amended files.
         dirstate = repo.dirstate
 
         # Update the state of the files which were added and
         # and modified in the amend to "normal" in the dirstate.
         normalfiles = set(wctx.modified() + wctx.added()) & filestoamend
         for f in normalfiles:
             dirstate.normal(f)
 
         # Update the state of files which were removed in the amend
         # to "removed" in the dirstate.
         removedfiles = set(wctx.removed()) & filestoamend
         for f in removedfiles:
             dirstate.drop(f)
 
     return newid
 
 
 def commiteditor(repo, ctx, subs, editform=b''):
     if ctx.description():
         return ctx.description()
     return commitforceeditor(
         repo, ctx, subs, editform=editform, unchangedmessagedetection=True
     )
 
 
 def commitforceeditor(
     repo,
     ctx,
     subs,
     finishdesc=None,
     extramsg=None,
     editform=b'',
     unchangedmessagedetection=False,
 ):
     if not extramsg:
         extramsg = _(b"Leave message empty to abort commit.")
 
     forms = [e for e in editform.split(b'.') if e]
     forms.insert(0, b'changeset')
     templatetext = None
     while forms:
         ref = b'.'.join(forms)
         if repo.ui.config(b'committemplate', ref):
             templatetext = committext = buildcommittemplate(
                 repo, ctx, subs, extramsg, ref
             )
             break
         forms.pop()
     else:
         committext = buildcommittext(repo, ctx, subs, extramsg)
 
     # run editor in the repository root
     olddir = encoding.getcwd()
     os.chdir(repo.root)
 
     # make in-memory changes visible to external process
     tr = repo.currenttransaction()
     repo.dirstate.write(tr)
     pending = tr and tr.writepending() and repo.root
 
     editortext = repo.ui.edit(
         committext,
         ctx.user(),
         ctx.extra(),
         editform=editform,
         pending=pending,
         repopath=repo.path,
         action=b'commit',
     )
     text = editortext
 
     # strip away anything below this special string (used for editors that want
     # to display the diff)
     stripbelow = re.search(_linebelow, text, flags=re.MULTILINE)
     if stripbelow:
         text = text[: stripbelow.start()]
 
     text = re.sub(b"(?m)^HG:.*(\n|$)", b"", text)
     os.chdir(olddir)
 
     if finishdesc:
         text = finishdesc(text)
     if not text.strip():
         raise error.Abort(_(b"empty commit message"))
     if unchangedmessagedetection and editortext == templatetext:
         raise error.Abort(_(b"commit message unchanged"))
 
     return text
 
 
 def buildcommittemplate(repo, ctx, subs, extramsg, ref):
     ui = repo.ui
     spec = formatter.templatespec(ref, None, None)
     t = logcmdutil.changesettemplater(ui, repo, spec)
     t.t.cache.update(
         (k, templater.unquotestring(v))
         for k, v in repo.ui.configitems(b'committemplate')
     )
 
     if not extramsg:
         extramsg = b''  # ensure that extramsg is string
 
     ui.pushbuffer()
     t.show(ctx, extramsg=extramsg)
     return ui.popbuffer()
 
 
 def hgprefix(msg):
     return b"\n".join([b"HG: %s" % a for a in msg.split(b"\n") if a])
 
 
 def buildcommittext(repo, ctx, subs, extramsg):
     edittext = []
     modified, added, removed = ctx.modified(), ctx.added(), ctx.removed()
     if ctx.description():
         edittext.append(ctx.description())
     edittext.append(b"")
     edittext.append(b"")  # Empty line between message and comments.
     edittext.append(
         hgprefix(
             _(
                 b"Enter commit message."
                 b"  Lines beginning with 'HG:' are removed."
             )
         )
     )
     edittext.append(hgprefix(extramsg))
     edittext.append(b"HG: --")
     edittext.append(hgprefix(_(b"user: %s") % ctx.user()))
     if ctx.p2():
         edittext.append(hgprefix(_(b"branch merge")))
     if ctx.branch():
         edittext.append(hgprefix(_(b"branch '%s'") % ctx.branch()))
     if bookmarks.isactivewdirparent(repo):
         edittext.append(hgprefix(_(b"bookmark '%s'") % repo._activebookmark))
     edittext.extend([hgprefix(_(b"subrepo %s") % s) for s in subs])
     edittext.extend([hgprefix(_(b"added %s") % f) for f in added])
     edittext.extend([hgprefix(_(b"changed %s") % f) for f in modified])
     edittext.extend([hgprefix(_(b"removed %s") % f) for f in removed])
     if not added and not modified and not removed:
         edittext.append(hgprefix(_(b"no files changed")))
     edittext.append(b"")
 
     return b"\n".join(edittext)
 
 
 def commitstatus(repo, node, branch, bheads=None, opts=None):
     if opts is None:
         opts = {}
     ctx = repo[node]
     parents = ctx.parents()
 
     if (
         not opts.get(b'amend')
         and bheads
         and node not in bheads
         and not [
             x for x in parents if x.node() in bheads and x.branch() == branch
         ]
     ):
         repo.ui.status(_(b'created new head\n'))
         # The message is not printed for initial roots. For the other
         # changesets, it is printed in the following situations:
         #
         # Par column: for the 2 parents with ...
         #   N: null or no parent
         #   B: parent is on another named branch
         #   C: parent is a regular non head changeset
         #   H: parent was a branch head of the current branch
         # Msg column: whether we print "created new head" message
         # In the following, it is assumed that there already exists some
         # initial branch heads of the current branch, otherwise nothing is
         # printed anyway.
         #
         # Par Msg Comment
         # N N  y  additional topo root
         #
         # B N  y  additional branch root
         # C N  y  additional topo head
         # H N  n  usual case
         #
         # B B  y  weird additional branch root
         # C B  y  branch merge
         # H B  n  merge with named branch
         #
         # C C  y  additional head from merge
         # C H  n  merge with a head
         #
         # H H  n  head merge: head count decreases
 
     if not opts.get(b'close_branch'):
         for r in parents:
             if r.closesbranch() and r.branch() == branch:
                 repo.ui.status(
                     _(b'reopening closed branch head %d\n') % r.rev()
                 )
 
     if repo.ui.debugflag:
         repo.ui.write(
             _(b'committed changeset %d:%s\n') % (ctx.rev(), ctx.hex())
         )
     elif repo.ui.verbose:
         repo.ui.write(_(b'committed changeset %d:%s\n') % (ctx.rev(), ctx))
 
 
 def postcommitstatus(repo, pats, opts):
     return repo.status(match=scmutil.match(repo[None], pats, opts))
 
 
 def revert(ui, repo, ctx, parents, *pats, **opts):
     opts = pycompat.byteskwargs(opts)
     parent, p2 = parents
     node = ctx.node()
 
     mf = ctx.manifest()
     if node == p2:
         parent = p2
 
     # need all matching names in dirstate and manifest of target rev,
     # so have to walk both. do not print errors if files exist in one
     # but not other. in both cases, filesets should be evaluated against
     # workingctx to get consistent result (issue4497). this means 'set:**'
     # cannot be used to select missing files from target rev.
 
     # `names` is a mapping for all elements in working copy and target revision
     # The mapping is in the form:
     #   <abs path in repo> -> (<path from CWD>, <exactly specified by matcher?>)
     names = {}
     uipathfn = scmutil.getuipathfn(repo, legacyrelativevalue=True)
 
     with repo.wlock():
         ## filling of the `names` mapping
         # walk dirstate to fill `names`
 
         interactive = opts.get(b'interactive', False)
         wctx = repo[None]
         m = scmutil.match(wctx, pats, opts)
 
         # we'll need this later
         targetsubs = sorted(s for s in wctx.substate if m(s))
 
         if not m.always():
             matcher = matchmod.badmatch(m, lambda x, y: False)
             for abs in wctx.walk(matcher):
                 names[abs] = m.exact(abs)
 
             # walk target manifest to fill `names`
 
             def badfn(path, msg):
                 if path in names:
                     return
                 if path in ctx.substate:
                     return
                 path_ = path + b'/'
                 for f in names:
                     if f.startswith(path_):
                         return
                 ui.warn(b"%s: %s\n" % (uipathfn(path), msg))
 
             for abs in ctx.walk(matchmod.badmatch(m, badfn)):
                 if abs not in names:
                     names[abs] = m.exact(abs)
 
             # Find status of all file in `names`.
             m = scmutil.matchfiles(repo, names)
 
             changes = repo.status(
                 node1=node, match=m, unknown=True, ignored=True, clean=True
             )
         else:
             changes = repo.status(node1=node, match=m)
             for kind in changes:
                 for abs in kind:
                     names[abs] = m.exact(abs)
 
             m = scmutil.matchfiles(repo, names)
 
         modified = set(changes.modified)
         added = set(changes.added)
         removed = set(changes.removed)
         _deleted = set(changes.deleted)
         unknown = set(changes.unknown)
         unknown.update(changes.ignored)
         clean = set(changes.clean)
         modadded = set()
 
         # We need to account for the state of the file in the dirstate,
         # even when we revert against something else than parent. This will
         # slightly alter the behavior of revert (doing back up or not, delete
         # or just forget etc).
         if parent == node:
             dsmodified = modified
             dsadded = added
             dsremoved = removed
             # store all local modifications, useful later for rename detection
             localchanges = dsmodified | dsadded
             modified, added, removed = set(), set(), set()
         else:
             changes = repo.status(node1=parent, match=m)
             dsmodified = set(changes.modified)
             dsadded = set(changes.added)
             dsremoved = set(changes.removed)
             # store all local modifications, useful later for rename detection
             localchanges = dsmodified | dsadded
 
             # only take into account for removes between wc and target
             clean |= dsremoved - removed
             dsremoved &= removed
             # distinct between dirstate remove and other
             removed -= dsremoved
 
             modadded = added & dsmodified
             added -= modadded
 
             # tell newly modified apart.
             dsmodified &= modified
             dsmodified |= modified & dsadded  # dirstate added may need backup
             modified -= dsmodified
 
             # We need to wait for some post-processing to update this set
             # before making the distinction. The dirstate will be used for
             # that purpose.
             dsadded = added
 
         # in case of merge, files that are actually added can be reported as
         # modified, we need to post process the result
         if p2 != nullid:
             mergeadd = set(dsmodified)
             for path in dsmodified:
                 if path in mf:
                     mergeadd.remove(path)
             dsadded |= mergeadd
             dsmodified -= mergeadd
 
         # if f is a rename, update `names` to also revert the source
         for f in localchanges:
             src = repo.dirstate.copied(f)
             # XXX should we check for rename down to target node?
             if src and src not in names and repo.dirstate[src] == b'r':
                 dsremoved.add(src)
                 names[src] = True
 
         # determine the exact nature of the deleted changesets
         deladded = set(_deleted)
         for path in _deleted:
             if path in mf:
                 deladded.remove(path)
         deleted = _deleted - deladded
 
         # distinguish between file to forget and the other
         added = set()
         for abs in dsadded:
             if repo.dirstate[abs] != b'a':
                 added.add(abs)
         dsadded -= added
 
         for abs in deladded:
             if repo.dirstate[abs] == b'a':
                 dsadded.add(abs)
         deladded -= dsadded
 
         # For files marked as removed, we check if an unknown file is present at
         # the same path. If a such file exists it may need to be backed up.
         # Making the distinction at this stage helps have simpler backup
         # logic.
         removunk = set()
         for abs in removed:
             target = repo.wjoin(abs)
             if os.path.lexists(target):
                 removunk.add(abs)
         removed -= removunk
 
         dsremovunk = set()
         for abs in dsremoved:
             target = repo.wjoin(abs)
             if os.path.lexists(target):
                 dsremovunk.add(abs)
         dsremoved -= dsremovunk
 
         # action to be actually performed by revert
         # (<list of file>, message>) tuple
         actions = {
             b'revert': ([], _(b'reverting %s\n')),
             b'add': ([], _(b'adding %s\n')),
             b'remove': ([], _(b'removing %s\n')),
             b'drop': ([], _(b'removing %s\n')),
             b'forget': ([], _(b'forgetting %s\n')),
             b'undelete': ([], _(b'undeleting %s\n')),
             b'noop': (None, _(b'no changes needed to %s\n')),
             b'unknown': (None, _(b'file not managed: %s\n')),
         }
 
         # "constant" that convey the backup strategy.
         # All set to `discard` if `no-backup` is set do avoid checking
         # no_backup lower in the code.
         # These values are ordered for comparison purposes
         backupinteractive = 3  # do backup if interactively modified
         backup = 2  # unconditionally do backup
         check = 1  # check if the existing file differs from target
         discard = 0  # never do backup
         if opts.get(b'no_backup'):
             backupinteractive = backup = check = discard
         if interactive:
             dsmodifiedbackup = backupinteractive
         else:
             dsmodifiedbackup = backup
         tobackup = set()
 
         backupanddel = actions[b'remove']
         if not opts.get(b'no_backup'):
             backupanddel = actions[b'drop']
 
         disptable = (
             # dispatch table:
             #   file state
             #   action
             #   make backup
             ## Sets that results that will change file on disk
             # Modified compared to target, no local change
             (modified, actions[b'revert'], discard),
             # Modified compared to target, but local file is deleted
             (deleted, actions[b'revert'], discard),
             # Modified compared to target, local change
             (dsmodified, actions[b'revert'], dsmodifiedbackup),
             # Added since target
             (added, actions[b'remove'], discard),
             # Added in working directory
             (dsadded, actions[b'forget'], discard),
             # Added since target, have local modification
             (modadded, backupanddel, backup),
             # Added since target but file is missing in working directory
             (deladded, actions[b'drop'], discard),
             # Removed since  target, before working copy parent
             (removed, actions[b'add'], discard),
             # Same as `removed` but an unknown file exists at the same path
             (removunk, actions[b'add'], check),
             # Removed since targe, marked as such in working copy parent
             (dsremoved, actions[b'undelete'], discard),
             # Same as `dsremoved` but an unknown file exists at the same path
             (dsremovunk, actions[b'undelete'], check),
             ## the following sets does not result in any file changes
             # File with no modification
             (clean, actions[b'noop'], discard),
             # Existing file, not tracked anywhere
             (unknown, actions[b'unknown'], discard),
         )
 
         for abs, exact in sorted(names.items()):
             # target file to be touch on disk (relative to cwd)
             target = repo.wjoin(abs)
             # search the entry in the dispatch table.
             # if the file is in any of these sets, it was touched in the working
             # directory parent and we are sure it needs to be reverted.
             for table, (xlist, msg), dobackup in disptable:
                 if abs not in table:
                     continue
                 if xlist is not None:
                     xlist.append(abs)
                     if dobackup:
                         # If in interactive mode, don't automatically create
                         # .orig files (issue4793)
                         if dobackup == backupinteractive:
                             tobackup.add(abs)
                         elif backup <= dobackup or wctx[abs].cmp(ctx[abs]):
                             absbakname = scmutil.backuppath(ui, repo, abs)
                             bakname = os.path.relpath(
                                 absbakname, start=repo.root
                             )
                             ui.note(
                                 _(b'saving current version of %s as %s\n')
                                 % (uipathfn(abs), uipathfn(bakname))
                             )
                             if not opts.get(b'dry_run'):
                                 if interactive:
                                     util.copyfile(target, absbakname)
                                 else:
                                     util.rename(target, absbakname)
                     if opts.get(b'dry_run'):
                         if ui.verbose or not exact:
                             ui.status(msg % uipathfn(abs))
                 elif exact:
                     ui.warn(msg % uipathfn(abs))
                 break
 
         if not opts.get(b'dry_run'):
             needdata = (b'revert', b'add', b'undelete')
             oplist = [actions[name][0] for name in needdata]
             prefetch = scmutil.prefetchfiles
             matchfiles = scmutil.matchfiles
             prefetch(
                 repo,
                 [ctx.rev()],
                 matchfiles(repo, [f for sublist in oplist for f in sublist]),
             )
             match = scmutil.match(repo[None], pats)
             _performrevert(
                 repo,
                 parents,
                 ctx,
                 names,
                 uipathfn,
                 actions,
                 match,
                 interactive,
                 tobackup,
             )
 
         if targetsubs:
             # Revert the subrepos on the revert list
             for sub in targetsubs:
                 try:
                     wctx.sub(sub).revert(
                         ctx.substate[sub], *pats, **pycompat.strkwargs(opts)
                     )
                 except KeyError:
                     raise error.Abort(
                         b"subrepository '%s' does not exist in %s!"
                         % (sub, short(ctx.node()))
                     )
 
 
 def _performrevert(
     repo,
     parents,
     ctx,
     names,
     uipathfn,
     actions,
     match,
     interactive=False,
     tobackup=None,
 ):
     """function that actually perform all the actions computed for revert
 
     This is an independent function to let extension to plug in and react to
     the imminent revert.
 
     Make sure you have the working directory locked when calling this function.
     """
     parent, p2 = parents
     node = ctx.node()
     excluded_files = []
 
     def checkout(f):
         fc = ctx[f]
         repo.wwrite(f, fc.data(), fc.flags())
 
     def doremove(f):
         try:
             rmdir = repo.ui.configbool(b'experimental', b'removeemptydirs')
             repo.wvfs.unlinkpath(f, rmdir=rmdir)
         except OSError:
             pass
         repo.dirstate.remove(f)
 
     def prntstatusmsg(action, f):
         exact = names[f]
         if repo.ui.verbose or not exact:
             repo.ui.status(actions[action][1] % uipathfn(f))
 
     audit_path = pathutil.pathauditor(repo.root, cached=True)
     for f in actions[b'forget'][0]:
         if interactive:
             choice = repo.ui.promptchoice(
                 _(b"forget added file %s (Yn)?$$ &Yes $$ &No") % uipathfn(f)
             )
             if choice == 0:
                 prntstatusmsg(b'forget', f)
                 repo.dirstate.drop(f)
             else:
                 excluded_files.append(f)
         else:
             prntstatusmsg(b'forget', f)
             repo.dirstate.drop(f)
     for f in actions[b'remove'][0]:
         audit_path(f)
         if interactive:
             choice = repo.ui.promptchoice(
                 _(b"remove added file %s (Yn)?$$ &Yes $$ &No") % uipathfn(f)
             )
             if choice == 0:
                 prntstatusmsg(b'remove', f)
                 doremove(f)
             else:
                 excluded_files.append(f)
         else:
             prntstatusmsg(b'remove', f)
             doremove(f)
     for f in actions[b'drop'][0]:
         audit_path(f)
         prntstatusmsg(b'drop', f)
         repo.dirstate.remove(f)
 
     normal = None
     if node == parent:
         # We're reverting to our parent. If possible, we'd like status
         # to report the file as clean. We have to use normallookup for
         # merges to avoid losing information about merged/dirty files.
         if p2 != nullid:
             normal = repo.dirstate.normallookup
         else:
             normal = repo.dirstate.normal
 
     newlyaddedandmodifiedfiles = set()
     if interactive:
         # Prompt the user for changes to revert
         torevert = [f for f in actions[b'revert'][0] if f not in excluded_files]
         m = scmutil.matchfiles(repo, torevert)
         diffopts = patch.difffeatureopts(
             repo.ui,
             whitespace=True,
             section=b'commands',
             configprefix=b'revert.interactive.',
         )
         diffopts.nodates = True
         diffopts.git = True
         operation = b'apply'
         if node == parent:
             if repo.ui.configbool(
                 b'experimental', b'revert.interactive.select-to-keep'
             ):
                 operation = b'keep'
             else:
                 operation = b'discard'
 
         if operation == b'apply':
             diff = patch.diff(repo, None, ctx.node(), m, opts=diffopts)
         else:
             diff = patch.diff(repo, ctx.node(), None, m, opts=diffopts)
         originalchunks = patch.parsepatch(diff)
 
         try:
 
             chunks, opts = recordfilter(
                 repo.ui, originalchunks, match, operation=operation
             )
             if operation == b'discard':
                 chunks = patch.reversehunks(chunks)
 
         except error.PatchError as err:
             raise error.Abort(_(b'error parsing patch: %s') % err)
 
         # FIXME: when doing an interactive revert of a copy, there's no way of
         # performing a partial revert of the added file, the only option is
         # "remove added file <name> (Yn)?", so we don't need to worry about the
         # alsorestore value. Ideally we'd be able to partially revert
         # copied/renamed files.
         newlyaddedandmodifiedfiles, unusedalsorestore = newandmodified(
             chunks, originalchunks
         )
         if tobackup is None:
             tobackup = set()
         # Apply changes
         fp = stringio()
         # chunks are serialized per file, but files aren't sorted
         for f in sorted(set(c.header.filename() for c in chunks if ishunk(c))):
             prntstatusmsg(b'revert', f)
         files = set()
         for c in chunks:
             if ishunk(c):
                 abs = c.header.filename()
                 # Create a backup file only if this hunk should be backed up
                 if c.header.filename() in tobackup:
                     target = repo.wjoin(abs)
                     bakname = scmutil.backuppath(repo.ui, repo, abs)
                     util.copyfile(target, bakname)
                     tobackup.remove(abs)
                 if abs not in files:
                     files.add(abs)
                     if operation == b'keep':
                         checkout(abs)
             c.write(fp)
         dopatch = fp.tell()
         fp.seek(0)
         if dopatch:
             try:
                 patch.internalpatch(repo.ui, repo, fp, 1, eolmode=None)
             except error.PatchError as err:
                 raise error.Abort(pycompat.bytestr(err))
         del fp
     else:
         for f in actions[b'revert'][0]:
             prntstatusmsg(b'revert', f)
             checkout(f)
             if normal:
                 normal(f)
 
     for f in actions[b'add'][0]:
         # Don't checkout modified files, they are already created by the diff
         if f not in newlyaddedandmodifiedfiles:
             prntstatusmsg(b'add', f)
             checkout(f)
             repo.dirstate.add(f)
 
     normal = repo.dirstate.normallookup
     if node == parent and p2 == nullid:
         normal = repo.dirstate.normal
     for f in actions[b'undelete'][0]:
         if interactive:
             choice = repo.ui.promptchoice(
                 _(b"add back removed file %s (Yn)?$$ &Yes $$ &No") % f
             )
             if choice == 0:
                 prntstatusmsg(b'undelete', f)
                 checkout(f)
                 normal(f)
             else:
                 excluded_files.append(f)
         else:
             prntstatusmsg(b'undelete', f)
             checkout(f)
             normal(f)
 
     copied = copies.pathcopies(repo[parent], ctx)
 
     for f in (
         actions[b'add'][0] + actions[b'undelete'][0] + actions[b'revert'][0]
     ):
         if f in copied:
             repo.dirstate.copy(copied[f], f)
 
 
 # a list of (ui, repo, otherpeer, opts, missing) functions called by
 # commands.outgoing.  "missing" is "missing" of the result of
 # "findcommonoutgoing()"
 outgoinghooks = util.hooks()
 
 # a list of (ui, repo) functions called by commands.summary
 summaryhooks = util.hooks()
 
 # a list of (ui, repo, opts, changes) functions called by commands.summary.
 #
 # functions should return tuple of booleans below, if 'changes' is None:
 #  (whether-incomings-are-needed, whether-outgoings-are-needed)
 #
 # otherwise, 'changes' is a tuple of tuples below:
 #  - (sourceurl, sourcebranch, sourcepeer, incoming)
 #  - (desturl,   destbranch,   destpeer,   outgoing)
 summaryremotehooks = util.hooks()
 
 
 def checkunfinished(repo, commit=False, skipmerge=False):
     '''Look for an unfinished multistep operation, like graft, and abort
     if found. It's probably good to check this right before
     bailifchanged().
     '''
     # Check for non-clearable states first, so things like rebase will take
     # precedence over update.
     for state in statemod._unfinishedstates:
         if (
             state._clearable
             or (commit and state._allowcommit)
             or state._reportonly
         ):
             continue
         if state.isunfinished(repo):
             raise error.Abort(state.msg(), hint=state.hint())
 
     for s in statemod._unfinishedstates:
         if (
             not s._clearable
             or (commit and s._allowcommit)
             or (s._opname == b'merge' and skipmerge)
             or s._reportonly
         ):
             continue
         if s.isunfinished(repo):
             raise error.Abort(s.msg(), hint=s.hint())
 
 
 def clearunfinished(repo):
     '''Check for unfinished operations (as above), and clear the ones
     that are clearable.
     '''
     for state in statemod._unfinishedstates:
         if state._reportonly:
             continue
         if not state._clearable and state.isunfinished(repo):
             raise error.Abort(state.msg(), hint=state.hint())
 
     for s in statemod._unfinishedstates:
         if s._opname == b'merge' or state._reportonly:
             continue
         if s._clearable and s.isunfinished(repo):
             util.unlink(repo.vfs.join(s._fname))
 
 
 def getunfinishedstate(repo):
     ''' Checks for unfinished operations and returns statecheck object
         for it'''
     for state in statemod._unfinishedstates:
         if state.isunfinished(repo):
             return state
     return None
 
 
 def howtocontinue(repo):
     '''Check for an unfinished operation and return the command to finish
     it.
 
     statemod._unfinishedstates list is checked for an unfinished operation
     and the corresponding message to finish it is generated if a method to
     continue is supported by the operation.
 
     Returns a (msg, warning) tuple. 'msg' is a string and 'warning' is
     a boolean.
     '''
     contmsg = _(b"continue: %s")
     for state in statemod._unfinishedstates:
         if not state._continueflag:
             continue
         if state.isunfinished(repo):
             return contmsg % state.continuemsg(), True
     if repo[None].dirty(missing=True, merge=False, branch=False):
         return contmsg % _(b"hg commit"), False
     return None, None
 
 
 def checkafterresolved(repo):
     '''Inform the user about the next action after completing hg resolve
 
     If there's a an unfinished operation that supports continue flag,
     howtocontinue will yield repo.ui.warn as the reporter.
 
     Otherwise, it will yield repo.ui.note.
     '''
     msg, warning = howtocontinue(repo)
     if msg is not None:
         if warning:
             repo.ui.warn(b"%s\n" % msg)
         else:
             repo.ui.note(b"%s\n" % msg)
 
 
 def wrongtooltocontinue(repo, task):
     '''Raise an abort suggesting how to properly continue if there is an
     active task.
 
     Uses howtocontinue() to find the active task.
 
     If there's no task (repo.ui.note for 'hg commit'), it does not offer
     a hint.
     '''
     after = howtocontinue(repo)
     hint = None
     if after[1]:
         hint = after[0]
     raise error.Abort(_(b'no %s in progress') % task, hint=hint)
 
 
 def abortgraft(ui, repo, graftstate):
     """abort the interrupted graft and rollbacks to the state before interrupted
     graft"""
     if not graftstate.exists():
         raise error.Abort(_(b"no interrupted graft to abort"))
     statedata = readgraftstate(repo, graftstate)
     newnodes = statedata.get(b'newnodes')
     if newnodes is None:
         # and old graft state which does not have all the data required to abort
         # the graft
         raise error.Abort(_(b"cannot abort using an old graftstate"))
 
     # changeset from which graft operation was started
     if len(newnodes) > 0:
         startctx = repo[newnodes[0]].p1()
     else:
         startctx = repo[b'.']
     # whether to strip or not
     cleanup = False
     from . import hg
 
     if newnodes:
         newnodes = [repo[r].rev() for r in newnodes]
         cleanup = True
         # checking that none of the newnodes turned public or is public
         immutable = [c for c in newnodes if not repo[c].mutable()]
         if immutable:
             repo.ui.warn(
                 _(b"cannot clean up public changesets %s\n")
                 % b', '.join(bytes(repo[r]) for r in immutable),
                 hint=_(b"see 'hg help phases' for details"),
             )
             cleanup = False
 
         # checking that no new nodes are created on top of grafted revs
         desc = set(repo.changelog.descendants(newnodes))
         if desc - set(newnodes):
             repo.ui.warn(
                 _(
                     b"new changesets detected on destination "
                     b"branch, can't strip\n"
                 )
             )
             cleanup = False
 
         if cleanup:
             with repo.wlock(), repo.lock():
                 hg.updaterepo(repo, startctx.node(), overwrite=True)
                 # stripping the new nodes created
                 strippoints = [
                     c.node() for c in repo.set(b"roots(%ld)", newnodes)
                 ]
                 repair.strip(repo.ui, repo, strippoints, backup=False)
 
     if not cleanup:
         # we don't update to the startnode if we can't strip
         startctx = repo[b'.']
         hg.updaterepo(repo, startctx.node(), overwrite=True)
 
     ui.status(_(b"graft aborted\n"))
     ui.status(_(b"working directory is now at %s\n") % startctx.hex()[:12])
     graftstate.delete()
     return 0
 
 
 def readgraftstate(repo, graftstate):
     # type: (Any, statemod.cmdstate) -> Dict[bytes, Any]
     """read the graft state file and return a dict of the data stored in it"""
     try:
         return graftstate.read()
     except error.CorruptedState:
         nodes = repo.vfs.read(b'graftstate').splitlines()
         return {b'nodes': nodes}
 
 
 def hgabortgraft(ui, repo):
     """ abort logic for aborting graft using 'hg abort'"""
     with repo.wlock():
         graftstate = statemod.cmdstate(repo, b'graftstate')
         return abortgraft(ui, repo, graftstate)

mercurial/encoding.py

@@ -1,705 +1,702
 # encoding.py - character transcoding support for Mercurial
 #
 #  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, print_function
 
 import locale
 import os
 import unicodedata
 
 from .pycompat import getattr
 from . import (
     error,
     policy,
     pycompat,
 )
 
 from .pure import charencode as charencodepure
 
-_TYPE_CHECKING = False
-
-if not globals():  # hide this from non-pytype users
+if pycompat.TYPE_CHECKING:
     from typing import (
         Any,
         Callable,
         List,
-        TYPE_CHECKING as _TYPE_CHECKING,
         Text,
         Type,
         TypeVar,
         Union,
     )
 
     # keep pyflakes happy
     for t in (Any, Callable, List, Text, Type, Union):
         assert t
 
     _Tlocalstr = TypeVar('_Tlocalstr', bound='localstr')
 
 charencode = policy.importmod('charencode')
 
 isasciistr = charencode.isasciistr
 asciilower = charencode.asciilower
 asciiupper = charencode.asciiupper
 _jsonescapeu8fast = charencode.jsonescapeu8fast
 
 _sysstr = pycompat.sysstr
 
 if pycompat.ispy3:
     unichr = chr
 
 # These unicode characters are ignored by HFS+ (Apple Technote 1150,
 # "Unicode Subtleties"), so we need to ignore them in some places for
 # sanity.
 _ignore = [
     unichr(int(x, 16)).encode("utf-8")
     for x in b"200c 200d 200e 200f 202a 202b 202c 202d 202e "
     b"206a 206b 206c 206d 206e 206f feff".split()
 ]
 # verify the next function will work
 assert all(i.startswith((b"\xe2", b"\xef")) for i in _ignore)
 
 
 def hfsignoreclean(s):
     # type: (bytes) -> bytes
     """Remove codepoints ignored by HFS+ from s.
 
     >>> hfsignoreclean(u'.h\u200cg'.encode('utf-8'))
     '.hg'
     >>> hfsignoreclean(u'.h\ufeffg'.encode('utf-8'))
     '.hg'
     """
     if b"\xe2" in s or b"\xef" in s:
         for c in _ignore:
             s = s.replace(c, b'')
     return s
 
 
 # encoding.environ is provided read-only, which may not be used to modify
 # the process environment
 _nativeenviron = not pycompat.ispy3 or os.supports_bytes_environ
 if not pycompat.ispy3:
     environ = os.environ  # re-exports
 elif _nativeenviron:
     environ = os.environb  # re-exports
 else:
     # preferred encoding isn't known yet; use utf-8 to avoid unicode error
     # and recreate it once encoding is settled
     environ = dict(
         (k.encode('utf-8'), v.encode('utf-8'))
         for k, v in os.environ.items()  # re-exports
     )
 
 _encodingrewrites = {
     b'646': b'ascii',
     b'ANSI_X3.4-1968': b'ascii',
 }
 # cp65001 is a Windows variant of utf-8, which isn't supported on Python 2.
 # No idea if it should be rewritten to the canonical name 'utf-8' on Python 3.
 # https://bugs.python.org/issue13216
 if pycompat.iswindows and not pycompat.ispy3:
     _encodingrewrites[b'cp65001'] = b'utf-8'
 
 try:
     encoding = environ.get(b"HGENCODING")
     if not encoding:
         encoding = locale.getpreferredencoding().encode('ascii') or b'ascii'
         encoding = _encodingrewrites.get(encoding, encoding)
 except locale.Error:
     encoding = b'ascii'
 encodingmode = environ.get(b"HGENCODINGMODE", b"strict")
 fallbackencoding = b'ISO-8859-1'
 
 
 class localstr(bytes):
     '''This class allows strings that are unmodified to be
     round-tripped to the local encoding and back'''
 
     def __new__(cls, u, l):
         s = bytes.__new__(cls, l)
         s._utf8 = u
         return s
 
-    if _TYPE_CHECKING:
+    if pycompat.TYPE_CHECKING:
         # pseudo implementation to help pytype see localstr() constructor
         def __init__(self, u, l):
             # type: (bytes, bytes) -> None
             super(localstr, self).__init__(l)
             self._utf8 = u
 
     def __hash__(self):
         return hash(self._utf8)  # avoid collisions in local string space
 
 
 class safelocalstr(bytes):
     """Tagged string denoting it was previously an internal UTF-8 string,
     and can be converted back to UTF-8 losslessly
 
     >>> assert safelocalstr(b'\\xc3') == b'\\xc3'
     >>> assert b'\\xc3' == safelocalstr(b'\\xc3')
     >>> assert b'\\xc3' in {safelocalstr(b'\\xc3'): 0}
     >>> assert safelocalstr(b'\\xc3') in {b'\\xc3': 0}
     """
 
 
 def tolocal(s):
     # type: (bytes) -> bytes
     """
     Convert a string from internal UTF-8 to local encoding
 
     All internal strings should be UTF-8 but some repos before the
     implementation of locale support may contain latin1 or possibly
     other character sets. We attempt to decode everything strictly
     using UTF-8, then Latin-1, and failing that, we use UTF-8 and
     replace unknown characters.
 
     The localstr class is used to cache the known UTF-8 encoding of
     strings next to their local representation to allow lossless
     round-trip conversion back to UTF-8.
 
     >>> u = b'foo: \\xc3\\xa4' # utf-8
     >>> l = tolocal(u)
     >>> l
     'foo: ?'
     >>> fromlocal(l)
     'foo: \\xc3\\xa4'
     >>> u2 = b'foo: \\xc3\\xa1'
     >>> d = { l: 1, tolocal(u2): 2 }
     >>> len(d) # no collision
     2
     >>> b'foo: ?' in d
     False
     >>> l1 = b'foo: \\xe4' # historical latin1 fallback
     >>> l = tolocal(l1)
     >>> l
     'foo: ?'
     >>> fromlocal(l) # magically in utf-8
     'foo: \\xc3\\xa4'
     """
 
     if isasciistr(s):
         return s
 
     try:
         try:
             # make sure string is actually stored in UTF-8
             u = s.decode('UTF-8')
             if encoding == b'UTF-8':
                 # fast path
                 return s
             r = u.encode(_sysstr(encoding), "replace")
             if u == r.decode(_sysstr(encoding)):
                 # r is a safe, non-lossy encoding of s
                 return safelocalstr(r)
             return localstr(s, r)
         except UnicodeDecodeError:
             # we should only get here if we're looking at an ancient changeset
             try:
                 u = s.decode(_sysstr(fallbackencoding))
                 r = u.encode(_sysstr(encoding), "replace")
                 if u == r.decode(_sysstr(encoding)):
                     # r is a safe, non-lossy encoding of s
                     return safelocalstr(r)
                 return localstr(u.encode('UTF-8'), r)
             except UnicodeDecodeError:
                 u = s.decode("utf-8", "replace")  # last ditch
                 # can't round-trip
                 return u.encode(_sysstr(encoding), "replace")
     except LookupError as k:
         raise error.Abort(k, hint=b"please check your locale settings")
 
 
 def fromlocal(s):
     # type: (bytes) -> bytes
     """
     Convert a string from the local character encoding to UTF-8
 
     We attempt to decode strings using the encoding mode set by
     HGENCODINGMODE, which defaults to 'strict'. In this mode, unknown
     characters will cause an error message. Other modes include
     'replace', which replaces unknown characters with a special
     Unicode character, and 'ignore', which drops the character.
     """
 
     # can we do a lossless round-trip?
     if isinstance(s, localstr):
         return s._utf8
     if isasciistr(s):
         return s
 
     try:
         u = s.decode(_sysstr(encoding), _sysstr(encodingmode))
         return u.encode("utf-8")
     except UnicodeDecodeError as inst:
         sub = s[max(0, inst.start - 10) : inst.start + 10]
         raise error.Abort(
             b"decoding near '%s': %s!" % (sub, pycompat.bytestr(inst))
         )
     except LookupError as k:
         raise error.Abort(k, hint=b"please check your locale settings")
 
 
 def unitolocal(u):
     # type: (Text) -> bytes
     """Convert a unicode string to a byte string of local encoding"""
     return tolocal(u.encode('utf-8'))
 
 
 def unifromlocal(s):
     # type: (bytes) -> Text
     """Convert a byte string of local encoding to a unicode string"""
     return fromlocal(s).decode('utf-8')
 
 
 def unimethod(bytesfunc):
     # type: (Callable[[Any], bytes]) -> Callable[[Any], Text]
     """Create a proxy method that forwards __unicode__() and __str__() of
     Python 3 to __bytes__()"""
 
     def unifunc(obj):
         return unifromlocal(bytesfunc(obj))
 
     return unifunc
 
 
 # converter functions between native str and byte string. use these if the
 # character encoding is not aware (e.g. exception message) or is known to
 # be locale dependent (e.g. date formatting.)
 if pycompat.ispy3:
     strtolocal = unitolocal
     strfromlocal = unifromlocal
     strmethod = unimethod
 else:
 
     def strtolocal(s):
         # type: (str) -> bytes
         return s  # pytype: disable=bad-return-type
 
     def strfromlocal(s):
         # type: (bytes) -> str
         return s  # pytype: disable=bad-return-type
 
     strmethod = pycompat.identity
 
 if not _nativeenviron:
     # now encoding and helper functions are available, recreate the environ
     # dict to be exported to other modules
     environ = dict(
         (tolocal(k.encode('utf-8')), tolocal(v.encode('utf-8')))
         for k, v in os.environ.items()  # re-exports
     )
 
 if pycompat.ispy3:
     # os.getcwd() on Python 3 returns string, but it has os.getcwdb() which
     # returns bytes.
     if pycompat.iswindows:
         # Python 3 on Windows issues a DeprecationWarning about using the bytes
         # API when os.getcwdb() is called.
         getcwd = lambda: strtolocal(os.getcwd())  # re-exports
     else:
         getcwd = os.getcwdb  # re-exports
 else:
     getcwd = os.getcwd  # re-exports
 
 # How to treat ambiguous-width characters. Set to 'wide' to treat as wide.
 _wide = _sysstr(
     environ.get(b"HGENCODINGAMBIGUOUS", b"narrow") == b"wide"
     and b"WFA"
     or b"WF"
 )
 
 
 def colwidth(s):
     # type: (bytes) -> int
     b"Find the column width of a string for display in the local encoding"
     return ucolwidth(s.decode(_sysstr(encoding), 'replace'))
 
 
 def ucolwidth(d):
     # type: (Text) -> int
     b"Find the column width of a Unicode string for display"
     eaw = getattr(unicodedata, 'east_asian_width', None)
     if eaw is not None:
         return sum([eaw(c) in _wide and 2 or 1 for c in d])
     return len(d)
 
 
 def getcols(s, start, c):
     # type: (bytes, int, int) -> bytes
     '''Use colwidth to find a c-column substring of s starting at byte
     index start'''
     for x in pycompat.xrange(start + c, len(s)):
         t = s[start:x]
         if colwidth(t) == c:
             return t
     raise ValueError('substring not found')
 
 
 def trim(s, width, ellipsis=b'', leftside=False):
     # type: (bytes, int, bytes, bool) -> bytes
     """Trim string 's' to at most 'width' columns (including 'ellipsis').
 
     If 'leftside' is True, left side of string 's' is trimmed.
     'ellipsis' is always placed at trimmed side.
 
     >>> from .node import bin
     >>> def bprint(s):
     ...     print(pycompat.sysstr(s))
     >>> ellipsis = b'+++'
     >>> from . import encoding
     >>> encoding.encoding = b'utf-8'
     >>> t = b'1234567890'
     >>> bprint(trim(t, 12, ellipsis=ellipsis))
     1234567890
     >>> bprint(trim(t, 10, ellipsis=ellipsis))
     1234567890
     >>> bprint(trim(t, 8, ellipsis=ellipsis))
     12345+++
     >>> bprint(trim(t, 8, ellipsis=ellipsis, leftside=True))
     +++67890
     >>> bprint(trim(t, 8))
     12345678
     >>> bprint(trim(t, 8, leftside=True))
     34567890
     >>> bprint(trim(t, 3, ellipsis=ellipsis))
     +++
     >>> bprint(trim(t, 1, ellipsis=ellipsis))
     +
     >>> u = u'\u3042\u3044\u3046\u3048\u304a' # 2 x 5 = 10 columns
     >>> t = u.encode(pycompat.sysstr(encoding.encoding))
     >>> bprint(trim(t, 12, ellipsis=ellipsis))
     \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\xe3\x81\x88\xe3\x81\x8a
     >>> bprint(trim(t, 10, ellipsis=ellipsis))
     \xe3\x81\x82\xe3\x81\x84\xe3\x81\x86\xe3\x81\x88\xe3\x81\x8a
     >>> bprint(trim(t, 8, ellipsis=ellipsis))
     \xe3\x81\x82\xe3\x81\x84+++
     >>> bprint(trim(t, 8, ellipsis=ellipsis, leftside=True))
     +++\xe3\x81\x88\xe3\x81\x8a
     >>> bprint(trim(t, 5))
     \xe3\x81\x82\xe3\x81\x84
     >>> bprint(trim(t, 5, leftside=True))
     \xe3\x81\x88\xe3\x81\x8a
     >>> bprint(trim(t, 4, ellipsis=ellipsis))
     +++
     >>> bprint(trim(t, 4, ellipsis=ellipsis, leftside=True))
     +++
     >>> t = bin(b'112233445566778899aa') # invalid byte sequence
     >>> bprint(trim(t, 12, ellipsis=ellipsis))
     \x11\x22\x33\x44\x55\x66\x77\x88\x99\xaa
     >>> bprint(trim(t, 10, ellipsis=ellipsis))
     \x11\x22\x33\x44\x55\x66\x77\x88\x99\xaa
     >>> bprint(trim(t, 8, ellipsis=ellipsis))
     \x11\x22\x33\x44\x55+++
     >>> bprint(trim(t, 8, ellipsis=ellipsis, leftside=True))
     +++\x66\x77\x88\x99\xaa
     >>> bprint(trim(t, 8))
     \x11\x22\x33\x44\x55\x66\x77\x88
     >>> bprint(trim(t, 8, leftside=True))
     \x33\x44\x55\x66\x77\x88\x99\xaa
     >>> bprint(trim(t, 3, ellipsis=ellipsis))
     +++
     >>> bprint(trim(t, 1, ellipsis=ellipsis))
     +
     """
     try:
         u = s.decode(_sysstr(encoding))
     except UnicodeDecodeError:
         if len(s) <= width:  # trimming is not needed
             return s
         width -= len(ellipsis)
         if width <= 0:  # no enough room even for ellipsis
             return ellipsis[: width + len(ellipsis)]
         if leftside:
             return ellipsis + s[-width:]
         return s[:width] + ellipsis
 
     if ucolwidth(u) <= width:  # trimming is not needed
         return s
 
     width -= len(ellipsis)
     if width <= 0:  # no enough room even for ellipsis
         return ellipsis[: width + len(ellipsis)]
 
     if leftside:
         uslice = lambda i: u[i:]
         concat = lambda s: ellipsis + s
     else:
         uslice = lambda i: u[:-i]
         concat = lambda s: s + ellipsis
     for i in pycompat.xrange(1, len(u)):
         usub = uslice(i)
         if ucolwidth(usub) <= width:
             return concat(usub.encode(_sysstr(encoding)))
     return ellipsis  # no enough room for multi-column characters
 
 
 def lower(s):
     # type: (bytes) -> bytes
     b"best-effort encoding-aware case-folding of local string s"
     try:
         return asciilower(s)
     except UnicodeDecodeError:
         pass
     try:
         if isinstance(s, localstr):
             u = s._utf8.decode("utf-8")
         else:
             u = s.decode(_sysstr(encoding), _sysstr(encodingmode))
 
         lu = u.lower()
         if u == lu:
             return s  # preserve localstring
         return lu.encode(_sysstr(encoding))
     except UnicodeError:
         return s.lower()  # we don't know how to fold this except in ASCII
     except LookupError as k:
         raise error.Abort(k, hint=b"please check your locale settings")
 
 
 def upper(s):
     # type: (bytes) -> bytes
     b"best-effort encoding-aware case-folding of local string s"
     try:
         return asciiupper(s)
     except UnicodeDecodeError:
         return upperfallback(s)
 
 
 def upperfallback(s):
     # type: (Any) -> Any
     try:
         if isinstance(s, localstr):
             u = s._utf8.decode("utf-8")
         else:
             u = s.decode(_sysstr(encoding), _sysstr(encodingmode))
 
         uu = u.upper()
         if u == uu:
             return s  # preserve localstring
         return uu.encode(_sysstr(encoding))
     except UnicodeError:
         return s.upper()  # we don't know how to fold this except in ASCII
     except LookupError as k:
         raise error.Abort(k, hint=b"please check your locale settings")
 
 
 class normcasespecs(object):
     '''what a platform's normcase does to ASCII strings
 
     This is specified per platform, and should be consistent with what normcase
     on that platform actually does.
 
     lower: normcase lowercases ASCII strings
     upper: normcase uppercases ASCII strings
     other: the fallback function should always be called
 
     This should be kept in sync with normcase_spec in util.h.'''
 
     lower = -1
     upper = 1
     other = 0
 
 
 def jsonescape(s, paranoid=False):
     # type: (Any, Any) -> Any
     '''returns a string suitable for JSON
 
     JSON is problematic for us because it doesn't support non-Unicode
     bytes. To deal with this, we take the following approach:
 
     - localstr/safelocalstr objects are converted back to UTF-8
     - valid UTF-8/ASCII strings are passed as-is
     - other strings are converted to UTF-8b surrogate encoding
     - apply JSON-specified string escaping
 
     (escapes are doubled in these tests)
 
     >>> jsonescape(b'this is a test')
     'this is a test'
     >>> jsonescape(b'escape characters: \\0 \\x0b \\x7f')
     'escape characters: \\\\u0000 \\\\u000b \\\\u007f'
     >>> jsonescape(b'escape characters: \\b \\t \\n \\f \\r \\" \\\\')
     'escape characters: \\\\b \\\\t \\\\n \\\\f \\\\r \\\\" \\\\\\\\'
     >>> jsonescape(b'a weird byte: \\xdd')
     'a weird byte: \\xed\\xb3\\x9d'
     >>> jsonescape(b'utf-8: caf\\xc3\\xa9')
     'utf-8: caf\\xc3\\xa9'
     >>> jsonescape(b'')
     ''
 
     If paranoid, non-ascii and common troublesome characters are also escaped.
     This is suitable for web output.
 
     >>> s = b'escape characters: \\0 \\x0b \\x7f'
     >>> assert jsonescape(s) == jsonescape(s, paranoid=True)
     >>> s = b'escape characters: \\b \\t \\n \\f \\r \\" \\\\'
     >>> assert jsonescape(s) == jsonescape(s, paranoid=True)
     >>> jsonescape(b'escape boundary: \\x7e \\x7f \\xc2\\x80', paranoid=True)
     'escape boundary: ~ \\\\u007f \\\\u0080'
     >>> jsonescape(b'a weird byte: \\xdd', paranoid=True)
     'a weird byte: \\\\udcdd'
     >>> jsonescape(b'utf-8: caf\\xc3\\xa9', paranoid=True)
     'utf-8: caf\\\\u00e9'
     >>> jsonescape(b'non-BMP: \\xf0\\x9d\\x84\\x9e', paranoid=True)
     'non-BMP: \\\\ud834\\\\udd1e'
     >>> jsonescape(b'<[e-mail]>', paranoid=True)
     '\\\\[e-mail]\\\\u003e'
     '''
 
     u8chars = toutf8b(s)
     try:
         return _jsonescapeu8fast(u8chars, paranoid)
     except ValueError:
         pass
     return charencodepure.jsonescapeu8fallback(u8chars, paranoid)
 
 
 # We need to decode/encode U+DCxx codes transparently since invalid UTF-8
 # bytes are mapped to that range.
 if pycompat.ispy3:
     _utf8strict = r'surrogatepass'
 else:
     _utf8strict = r'strict'
 
 _utf8len = [0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 3, 4]
 
 
 def getutf8char(s, pos):
     # type: (bytes, int) -> bytes
     '''get the next full utf-8 character in the given string, starting at pos
 
     Raises a UnicodeError if the given location does not start a valid
     utf-8 character.
     '''
 
     # find how many bytes to attempt decoding from first nibble
     l = _utf8len[ord(s[pos : pos + 1]) >> 4]
     if not l:  # ascii
         return s[pos : pos + 1]
 
     c = s[pos : pos + l]
     # validate with attempted decode
     c.decode("utf-8", _utf8strict)
     return c
 
 
 def toutf8b(s):
     # type: (bytes) -> bytes
     '''convert a local, possibly-binary string into UTF-8b
 
     This is intended as a generic method to preserve data when working
     with schemes like JSON and XML that have no provision for
     arbitrary byte strings. As Mercurial often doesn't know
     what encoding data is in, we use so-called UTF-8b.
 
     If a string is already valid UTF-8 (or ASCII), it passes unmodified.
     Otherwise, unsupported bytes are mapped to UTF-16 surrogate range,
     uDC00-uDCFF.
 
     Principles of operation:
 
     - ASCII and UTF-8 data successfully round-trips and is understood
       by Unicode-oriented clients
     - filenames and file contents in arbitrary other encodings can have
       be round-tripped or recovered by clueful clients
     - local strings that have a cached known UTF-8 encoding (aka
       localstr) get sent as UTF-8 so Unicode-oriented clients get the
       Unicode data they want
     - non-lossy local strings (aka safelocalstr) get sent as UTF-8 as well
     - because we must preserve UTF-8 bytestring in places such as
       filenames, metadata can't be roundtripped without help
 
     (Note: "UTF-8b" often refers to decoding a mix of valid UTF-8 and
     arbitrary bytes into an internal Unicode format that can be
     re-encoded back into the original. Here we are exposing the
     internal surrogate encoding as a UTF-8 string.)
     '''
 
     if isinstance(s, localstr):
         # assume that the original UTF-8 sequence would never contain
         # invalid characters in U+DCxx range
         return s._utf8
     elif isinstance(s, safelocalstr):
         # already verified that s is non-lossy in legacy encoding, which
         # shouldn't contain characters in U+DCxx range
         return fromlocal(s)
     elif isasciistr(s):
         return s
     if b"\xed" not in s:
         try:
             s.decode('utf-8', _utf8strict)
             return s
         except UnicodeDecodeError:
             pass
 
     s = pycompat.bytestr(s)
     r = b""
     pos = 0
     l = len(s)
     while pos < l:
         try:
             c = getutf8char(s, pos)
             if b"\xed\xb0\x80" <= c <= b"\xed\xb3\xbf":
                 # have to re-escape existing U+DCxx characters
                 c = unichr(0xDC00 + ord(s[pos])).encode('utf-8', _utf8strict)
                 pos += 1
             else:
                 pos += len(c)
         except UnicodeDecodeError:
             c = unichr(0xDC00 + ord(s[pos])).encode('utf-8', _utf8strict)
             pos += 1
         r += c
     return r
 
 
 def fromutf8b(s):
     # type: (bytes) -> bytes
     '''Given a UTF-8b string, return a local, possibly-binary string.
 
     return the original binary string. This
     is a round-trip process for strings like filenames, but metadata
     that's was passed through tolocal will remain in UTF-8.
 
     >>> roundtrip = lambda x: fromutf8b(toutf8b(x)) == x
     >>> m = b"\\xc3\\xa9\\x99abcd"
     >>> toutf8b(m)
     '\\xc3\\xa9\\xed\\xb2\\x99abcd'
     >>> roundtrip(m)
     True
     >>> roundtrip(b"\\xc2\\xc2\\x80")
     True
     >>> roundtrip(b"\\xef\\xbf\\xbd")
     True
     >>> roundtrip(b"\\xef\\xef\\xbf\\xbd")
     True
     >>> roundtrip(b"\\xf1\\x80\\x80\\x80\\x80")
     True
     '''
 
     if isasciistr(s):
         return s
     # fast path - look for uDxxx prefixes in s
     if b"\xed" not in s:
         return s
 
     # We could do this with the unicode type but some Python builds
     # use UTF-16 internally (issue5031) which causes non-BMP code
     # points to be escaped. Instead, we use our handy getutf8char
     # helper again to walk the string without "decoding" it.
 
     s = pycompat.bytestr(s)
     r = b""
     pos = 0
     l = len(s)
     while pos < l:
         c = getutf8char(s, pos)
         pos += len(c)
         # unescape U+DCxx characters
         if b"\xed\xb0\x80" <= c <= b"\xed\xb3\xbf":
             c = pycompat.bytechr(ord(c.decode("utf-8", _utf8strict)) & 0xFF)
         r += c
     return r

mercurial/logcmdutil.py

@@ -1,1084 +1,1084
 # logcmdutil.py - utility for log-like commands
 #
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import itertools
 import os
 import posixpath
 
 from .i18n import _
 from .node import (
     nullid,
     wdirid,
     wdirrev,
 )
 
 from . import (
     dagop,
     error,
     formatter,
     graphmod,
     match as matchmod,
     mdiff,
     patch,
     pathutil,
     pycompat,
     revset,
     revsetlang,
     scmutil,
     smartset,
     templatekw,
     templater,
     util,
 )
 from .utils import (
     dateutil,
     stringutil,
 )
 
 
-if not globals():
+if pycompat.TYPE_CHECKING:
     from typing import (
         Any,
         Tuple,
     )
 
     for t in (Any, Tuple):
         assert t
 
 
 def getlimit(opts):
     """get the log limit according to option -l/--limit"""
     limit = opts.get(b'limit')
     if limit:
         try:
             limit = int(limit)
         except ValueError:
             raise error.Abort(_(b'limit must be a positive integer'))
         if limit <= 0:
             raise error.Abort(_(b'limit must be positive'))
     else:
         limit = None
     return limit
 
 
 def diffordiffstat(
     ui,
     repo,
     diffopts,
     node1,
     node2,
     match,
     changes=None,
     stat=False,
     fp=None,
     graphwidth=0,
     prefix=b'',
     root=b'',
     listsubrepos=False,
     hunksfilterfn=None,
 ):
     '''show diff or diffstat.'''
     ctx1 = repo[node1]
     ctx2 = repo[node2]
     if root:
         relroot = pathutil.canonpath(repo.root, repo.getcwd(), root)
     else:
         relroot = b''
     copysourcematch = None
 
     def compose(f, g):
         return lambda x: f(g(x))
 
     def pathfn(f):
         return posixpath.join(prefix, f)
 
     if relroot != b'':
         # XXX relative roots currently don't work if the root is within a
         # subrepo
         uipathfn = scmutil.getuipathfn(repo, legacyrelativevalue=True)
         uirelroot = uipathfn(pathfn(relroot))
         relroot += b'/'
         for matchroot in match.files():
             if not matchroot.startswith(relroot):
                 ui.warn(
                     _(b'warning: %s not inside relative root %s\n')
                     % (uipathfn(pathfn(matchroot)), uirelroot)
                 )
 
         relrootmatch = scmutil.match(ctx2, pats=[relroot], default=b'path')
         match = matchmod.intersectmatchers(match, relrootmatch)
         copysourcematch = relrootmatch
 
         checkroot = repo.ui.configbool(
             b'devel', b'all-warnings'
         ) or repo.ui.configbool(b'devel', b'check-relroot')
 
         def relrootpathfn(f):
             if checkroot and not f.startswith(relroot):
                 raise AssertionError(
                     b"file %s doesn't start with relroot %s" % (f, relroot)
                 )
             return f[len(relroot) :]
 
         pathfn = compose(relrootpathfn, pathfn)
 
     if stat:
         diffopts = diffopts.copy(context=0, noprefix=False)
         width = 80
         if not ui.plain():
             width = ui.termwidth() - graphwidth
         # If an explicit --root was given, don't respect ui.relative-paths
         if not relroot:
             pathfn = compose(scmutil.getuipathfn(repo), pathfn)
 
     chunks = ctx2.diff(
         ctx1,
         match,
         changes,
         opts=diffopts,
         pathfn=pathfn,
         copysourcematch=copysourcematch,
         hunksfilterfn=hunksfilterfn,
     )
 
     if fp is not None or ui.canwritewithoutlabels():
         out = fp or ui
         if stat:
             chunks = [patch.diffstat(util.iterlines(chunks), width=width)]
         for chunk in util.filechunkiter(util.chunkbuffer(chunks)):
             out.write(chunk)
     else:
         if stat:
             chunks = patch.diffstatui(util.iterlines(chunks), width=width)
         else:
             chunks = patch.difflabel(
                 lambda chunks, **kwargs: chunks, chunks, opts=diffopts
             )
         if ui.canbatchlabeledwrites():
 
             def gen():
                 for chunk, label in chunks:
                     yield ui.label(chunk, label=label)
 
             for chunk in util.filechunkiter(util.chunkbuffer(gen())):
                 ui.write(chunk)
         else:
             for chunk, label in chunks:
                 ui.write(chunk, label=label)
 
     for subpath, sub in scmutil.itersubrepos(ctx1, ctx2):
         tempnode2 = node2
         try:
             if node2 is not None:
                 tempnode2 = ctx2.substate[subpath][1]
         except KeyError:
             # A subrepo that existed in node1 was deleted between node1 and
             # node2 (inclusive). Thus, ctx2's substate won't contain that
             # subpath. The best we can do is to ignore it.
             tempnode2 = None
         submatch = matchmod.subdirmatcher(subpath, match)
         subprefix = repo.wvfs.reljoin(prefix, subpath)
         if listsubrepos or match.exact(subpath) or any(submatch.files()):
             sub.diff(
                 ui,
                 diffopts,
                 tempnode2,
                 submatch,
                 changes=changes,
                 stat=stat,
                 fp=fp,
                 prefix=subprefix,
             )
 
 
 class changesetdiffer(object):
     """Generate diff of changeset with pre-configured filtering functions"""
 
     def _makefilematcher(self, ctx):
         return scmutil.matchall(ctx.repo())
 
     def _makehunksfilter(self, ctx):
         return None
 
     def showdiff(self, ui, ctx, diffopts, graphwidth=0, stat=False):
         repo = ctx.repo()
         node = ctx.node()
         prev = ctx.p1().node()
         diffordiffstat(
             ui,
             repo,
             diffopts,
             prev,
             node,
             match=self._makefilematcher(ctx),
             stat=stat,
             graphwidth=graphwidth,
             hunksfilterfn=self._makehunksfilter(ctx),
         )
 
 
 def changesetlabels(ctx):
     labels = [b'log.changeset', b'changeset.%s' % ctx.phasestr()]
     if ctx.obsolete():
         labels.append(b'changeset.obsolete')
     if ctx.isunstable():
         labels.append(b'changeset.unstable')
         for instability in ctx.instabilities():
             labels.append(b'instability.%s' % instability)
     return b' '.join(labels)
 
 
 class changesetprinter(object):
     '''show changeset information when templating not requested.'''
 
     def __init__(self, ui, repo, differ=None, diffopts=None, buffered=False):
         self.ui = ui
         self.repo = repo
         self.buffered = buffered
         self._differ = differ or changesetdiffer()
         self._diffopts = patch.diffallopts(ui, diffopts)
         self._includestat = diffopts and diffopts.get(b'stat')
         self._includediff = diffopts and diffopts.get(b'patch')
         self.header = {}
         self.hunk = {}
         self.lastheader = None
         self.footer = None
         self._columns = templatekw.getlogcolumns()
 
     def flush(self, ctx):
         rev = ctx.rev()
         if rev in self.header:
             h = self.header[rev]
             if h != self.lastheader:
                 self.lastheader = h
                 self.ui.write(h)
             del self.header[rev]
         if rev in self.hunk:
             self.ui.write(self.hunk[rev])
             del self.hunk[rev]
 
     def close(self):
         if self.footer:
             self.ui.write(self.footer)
 
     def show(self, ctx, copies=None, **props):
         props = pycompat.byteskwargs(props)
         if self.buffered:
             self.ui.pushbuffer(labeled=True)
             self._show(ctx, copies, props)
             self.hunk[ctx.rev()] = self.ui.popbuffer()
         else:
             self._show(ctx, copies, props)
 
     def _show(self, ctx, copies, props):
         '''show a single changeset or file revision'''
         changenode = ctx.node()
         graphwidth = props.get(b'graphwidth', 0)
 
         if self.ui.quiet:
             self.ui.write(
                 b"%s\n" % scmutil.formatchangeid(ctx), label=b'log.node'
             )
             return
 
         columns = self._columns
         self.ui.write(
             columns[b'changeset'] % scmutil.formatchangeid(ctx),
             label=changesetlabels(ctx),
         )
 
         # branches are shown first before any other names due to backwards
         # compatibility
         branch = ctx.branch()
         # don't show the default branch name
         if branch != b'default':
             self.ui.write(columns[b'branch'] % branch, label=b'log.branch')
 
         for nsname, ns in pycompat.iteritems(self.repo.names):
             # branches has special logic already handled above, so here we just
             # skip it
             if nsname == b'branches':
                 continue
             # we will use the templatename as the color name since those two
             # should be the same
             for name in ns.names(self.repo, changenode):
                 self.ui.write(ns.logfmt % name, label=b'log.%s' % ns.colorname)
         if self.ui.debugflag:
             self.ui.write(
                 columns[b'phase'] % ctx.phasestr(), label=b'log.phase'
             )
         for pctx in scmutil.meaningfulparents(self.repo, ctx):
             label = b'log.parent changeset.%s' % pctx.phasestr()
             self.ui.write(
                 columns[b'parent'] % scmutil.formatchangeid(pctx), label=label
             )
 
         if self.ui.debugflag:
             mnode = ctx.manifestnode()
             if mnode is None:
                 mnode = wdirid
                 mrev = wdirrev
             else:
                 mrev = self.repo.manifestlog.rev(mnode)
             self.ui.write(
                 columns[b'manifest']
                 % scmutil.formatrevnode(self.ui, mrev, mnode),
                 label=b'ui.debug log.manifest',
             )
         self.ui.write(columns[b'user'] % ctx.user(), label=b'log.user')
         self.ui.write(
             columns[b'date'] % dateutil.datestr(ctx.date()), label=b'log.date'
         )
 
         if ctx.isunstable():
             instabilities = ctx.instabilities()
             self.ui.write(
                 columns[b'instability'] % b', '.join(instabilities),
                 label=b'log.instability',
             )
 
         elif ctx.obsolete():
             self._showobsfate(ctx)
 
         self._exthook(ctx)
 
         if self.ui.debugflag:
             files = ctx.p1().status(ctx)
             for key, value in zip(
                 [b'files', b'files+', b'files-'],
                 [files.modified, files.added, files.removed],
             ):
                 if value:
                     self.ui.write(
                         columns[key] % b" ".join(value),
                         label=b'ui.debug log.files',
                     )
         elif ctx.files() and self.ui.verbose:
             self.ui.write(
                 columns[b'files'] % b" ".join(ctx.files()),
                 label=b'ui.note log.files',
             )
         if copies and self.ui.verbose:
             copies = [b'%s (%s)' % c for c in copies]
             self.ui.write(
                 columns[b'copies'] % b' '.join(copies),
                 label=b'ui.note log.copies',
             )
 
         extra = ctx.extra()
         if extra and self.ui.debugflag:
             for key, value in sorted(extra.items()):
                 self.ui.write(
                     columns[b'extra'] % (key, stringutil.escapestr(value)),
                     label=b'ui.debug log.extra',
                 )
 
         description = ctx.description().strip()
         if description:
             if self.ui.verbose:
                 self.ui.write(
                     _(b"description:\n"), label=b'ui.note log.description'
                 )
                 self.ui.write(description, label=b'ui.note log.description')
                 self.ui.write(b"\n\n")
             else:
                 self.ui.write(
                     columns[b'summary'] % description.splitlines()[0],
                     label=b'log.summary',
                 )
         self.ui.write(b"\n")
 
         self._showpatch(ctx, graphwidth)
 
     def _showobsfate(self, ctx):
         # TODO: do not depend on templater
         tres = formatter.templateresources(self.repo.ui, self.repo)
         t = formatter.maketemplater(
             self.repo.ui,
             b'{join(obsfate, "\n")}',
             defaults=templatekw.keywords,
             resources=tres,
         )
         obsfate = t.renderdefault({b'ctx': ctx}).splitlines()
 
         if obsfate:
             for obsfateline in obsfate:
                 self.ui.write(
                     self._columns[b'obsolete'] % obsfateline,
                     label=b'log.obsfate',
                 )
 
     def _exthook(self, ctx):
         '''empty method used by extension as a hook point
         '''
 
     def _showpatch(self, ctx, graphwidth=0):
         if self._includestat:
             self._differ.showdiff(
                 self.ui, ctx, self._diffopts, graphwidth, stat=True
             )
         if self._includestat and self._includediff:
             self.ui.write(b"\n")
         if self._includediff:
             self._differ.showdiff(
                 self.ui, ctx, self._diffopts, graphwidth, stat=False
             )
         if self._includestat or self._includediff:
             self.ui.write(b"\n")
 
 
 class changesetformatter(changesetprinter):
     """Format changeset information by generic formatter"""
 
     def __init__(
         self, ui, repo, fm, differ=None, diffopts=None, buffered=False
     ):
         changesetprinter.__init__(self, ui, repo, differ, diffopts, buffered)
         self._diffopts = patch.difffeatureopts(ui, diffopts, git=True)
         self._fm = fm
 
     def close(self):
         self._fm.end()
 
     def _show(self, ctx, copies, props):
         '''show a single changeset or file revision'''
         fm = self._fm
         fm.startitem()
         fm.context(ctx=ctx)
         fm.data(rev=scmutil.intrev(ctx), node=fm.hexfunc(scmutil.binnode(ctx)))
 
         datahint = fm.datahint()
         if self.ui.quiet and not datahint:
             return
 
         fm.data(
             branch=ctx.branch(),
             phase=ctx.phasestr(),
             user=ctx.user(),
             date=fm.formatdate(ctx.date()),
             desc=ctx.description(),
             bookmarks=fm.formatlist(ctx.bookmarks(), name=b'bookmark'),
             tags=fm.formatlist(ctx.tags(), name=b'tag'),
             parents=fm.formatlist(
                 [fm.hexfunc(c.node()) for c in ctx.parents()], name=b'node'
             ),
         )
 
         if self.ui.debugflag or b'manifest' in datahint:
             fm.data(manifest=fm.hexfunc(ctx.manifestnode() or wdirid))
         if self.ui.debugflag or b'extra' in datahint:
             fm.data(extra=fm.formatdict(ctx.extra()))
 
         if (
             self.ui.debugflag
             or b'modified' in datahint
             or b'added' in datahint
             or b'removed' in datahint
         ):
             files = ctx.p1().status(ctx)
             fm.data(
                 modified=fm.formatlist(files.modified, name=b'file'),
                 added=fm.formatlist(files.added, name=b'file'),
                 removed=fm.formatlist(files.removed, name=b'file'),
             )
 
         verbose = not self.ui.debugflag and self.ui.verbose
         if verbose or b'files' in datahint:
             fm.data(files=fm.formatlist(ctx.files(), name=b'file'))
         if verbose and copies or b'copies' in datahint:
             fm.data(
                 copies=fm.formatdict(copies or {}, key=b'name', value=b'source')
             )
 
         if self._includestat or b'diffstat' in datahint:
             self.ui.pushbuffer()
             self._differ.showdiff(self.ui, ctx, self._diffopts, stat=True)
             fm.data(diffstat=self.ui.popbuffer())
         if self._includediff or b'diff' in datahint:
             self.ui.pushbuffer()
             self._differ.showdiff(self.ui, ctx, self._diffopts, stat=False)
             fm.data(diff=self.ui.popbuffer())
 
 
 class changesettemplater(changesetprinter):
     '''format changeset information.
 
     Note: there are a variety of convenience functions to build a
     changesettemplater for common cases. See functions such as:
     maketemplater, changesetdisplayer, buildcommittemplate, or other
     functions that use changesest_templater.
     '''
 
     # Arguments before "buffered" used to be positional. Consider not
     # adding/removing arguments before "buffered" to not break callers.
     def __init__(
         self, ui, repo, tmplspec, differ=None, diffopts=None, buffered=False
     ):
         changesetprinter.__init__(self, ui, repo, differ, diffopts, buffered)
         # tres is shared with _graphnodeformatter()
         self._tresources = tres = formatter.templateresources(ui, repo)
         self.t = formatter.loadtemplater(
             ui,
             tmplspec,
             defaults=templatekw.keywords,
             resources=tres,
             cache=templatekw.defaulttempl,
         )
         self._counter = itertools.count()
 
         self._tref = tmplspec.ref
         self._parts = {
             b'header': b'',
             b'footer': b'',
             tmplspec.ref: tmplspec.ref,
             b'docheader': b'',
             b'docfooter': b'',
             b'separator': b'',
         }
         if tmplspec.mapfile:
             # find correct templates for current mode, for backward
             # compatibility with 'log -v/-q/--debug' using a mapfile
             tmplmodes = [
                 (True, b''),
                 (self.ui.verbose, b'_verbose'),
                 (self.ui.quiet, b'_quiet'),
                 (self.ui.debugflag, b'_debug'),
             ]
             for mode, postfix in tmplmodes:
                 for t in self._parts:
                     cur = t + postfix
                     if mode and cur in self.t:
                         self._parts[t] = cur
         else:
             partnames = [p for p in self._parts.keys() if p != tmplspec.ref]
             m = formatter.templatepartsmap(tmplspec, self.t, partnames)
             self._parts.update(m)
 
         if self._parts[b'docheader']:
             self.ui.write(self.t.render(self._parts[b'docheader'], {}))
 
     def close(self):
         if self._parts[b'docfooter']:
             if not self.footer:
                 self.footer = b""
             self.footer += self.t.render(self._parts[b'docfooter'], {})
         return super(changesettemplater, self).close()
 
     def _show(self, ctx, copies, props):
         '''show a single changeset or file revision'''
         props = props.copy()
         props[b'ctx'] = ctx
         props[b'index'] = index = next(self._counter)
         props[b'revcache'] = {b'copies': copies}
         graphwidth = props.get(b'graphwidth', 0)
 
         # write separator, which wouldn't work well with the header part below
         # since there's inherently a conflict between header (across items) and
         # separator (per item)
         if self._parts[b'separator'] and index > 0:
             self.ui.write(self.t.render(self._parts[b'separator'], {}))
 
         # write header
         if self._parts[b'header']:
             h = self.t.render(self._parts[b'header'], props)
             if self.buffered:
                 self.header[ctx.rev()] = h
             else:
                 if self.lastheader != h:
                     self.lastheader = h
                     self.ui.write(h)
 
         # write changeset metadata, then patch if requested
         key = self._parts[self._tref]
         self.ui.write(self.t.render(key, props))
         self._showpatch(ctx, graphwidth)
 
         if self._parts[b'footer']:
             if not self.footer:
                 self.footer = self.t.render(self._parts[b'footer'], props)
 
 
 def templatespec(tmpl, mapfile):
     if pycompat.ispy3:
         assert not isinstance(tmpl, str), b'tmpl must not be a str'
     if mapfile:
         return formatter.templatespec(b'changeset', tmpl, mapfile)
     else:
         return formatter.templatespec(b'', tmpl, None)
 
 
 def _lookuptemplate(ui, tmpl, style):
     """Find the template matching the given template spec or style
 
     See formatter.lookuptemplate() for details.
     """
 
     # ui settings
     if not tmpl and not style:  # template are stronger than style
         tmpl = ui.config(b'ui', b'logtemplate')
         if tmpl:
             return templatespec(templater.unquotestring(tmpl), None)
         else:
             style = util.expandpath(ui.config(b'ui', b'style'))
 
     if not tmpl and style:
         mapfile = style
         if not os.path.split(mapfile)[0]:
             mapname = templater.templatepath(
                 b'map-cmdline.' + mapfile
             ) or templater.templatepath(mapfile)
             if mapname:
                 mapfile = mapname
         return templatespec(None, mapfile)
 
     return formatter.lookuptemplate(ui, b'changeset', tmpl)
 
 
 def maketemplater(ui, repo, tmpl, buffered=False):
     """Create a changesettemplater from a literal template 'tmpl'
     byte-string."""
     spec = templatespec(tmpl, None)
     return changesettemplater(ui, repo, spec, buffered=buffered)
 
 
 def changesetdisplayer(ui, repo, opts, differ=None, buffered=False):
     """show one changeset using template or regular display.
 
     Display format will be the first non-empty hit of:
     1. option 'template'
     2. option 'style'
     3. [ui] setting 'logtemplate'
     4. [ui] setting 'style'
     If all of these values are either the unset or the empty string,
     regular display via changesetprinter() is done.
     """
     postargs = (differ, opts, buffered)
     spec = _lookuptemplate(ui, opts.get(b'template'), opts.get(b'style'))
 
     # machine-readable formats have slightly different keyword set than
     # plain templates, which are handled by changesetformatter.
     # note that {b'pickle', b'debug'} can also be added to the list if needed.
     if spec.ref in {b'cbor', b'json'}:
         fm = ui.formatter(b'log', opts)
         return changesetformatter(ui, repo, fm, *postargs)
 
     if not spec.ref and not spec.tmpl and not spec.mapfile:
         return changesetprinter(ui, repo, *postargs)
 
     return changesettemplater(ui, repo, spec, *postargs)
 
 
 def _makematcher(repo, revs, pats, opts):
     """Build matcher and expanded patterns from log options
 
     If --follow, revs are the revisions to follow from.
 
     Returns (match, pats, slowpath) where
     - match: a matcher built from the given pats and -I/-X opts
     - pats: patterns used (globs are expanded on Windows)
     - slowpath: True if patterns aren't as simple as scanning filelogs
     """
     # pats/include/exclude are passed to match.match() directly in
     # _matchfiles() revset but walkchangerevs() builds its matcher with
     # scmutil.match(). The difference is input pats are globbed on
     # platforms without shell expansion (windows).
     wctx = repo[None]
     match, pats = scmutil.matchandpats(wctx, pats, opts)
     slowpath = match.anypats() or (not match.always() and opts.get(b'removed'))
     if not slowpath:
         follow = opts.get(b'follow') or opts.get(b'follow_first')
         startctxs = []
         if follow and opts.get(b'rev'):
             startctxs = [repo[r] for r in revs]
         for f in match.files():
             if follow and startctxs:
                 # No idea if the path was a directory at that revision, so
                 # take the slow path.
                 if any(f not in c for c in startctxs):
                     slowpath = True
                     continue
             elif follow and f not in wctx:
                 # If the file exists, it may be a directory, so let it
                 # take the slow path.
                 if os.path.exists(repo.wjoin(f)):
                     slowpath = True
                     continue
                 else:
                     raise error.Abort(
                         _(
                             b'cannot follow file not in parent '
                             b'revision: "%s"'
                         )
                         % f
                     )
             filelog = repo.file(f)
             if not filelog:
                 # A zero count may be a directory or deleted file, so
                 # try to find matching entries on the slow path.
                 if follow:
                     raise error.Abort(
                         _(b'cannot follow nonexistent file: "%s"') % f
                     )
                 slowpath = True
 
         # We decided to fall back to the slowpath because at least one
         # of the paths was not a file. Check to see if at least one of them
         # existed in history - in that case, we'll continue down the
         # slowpath; otherwise, we can turn off the slowpath
         if slowpath:
             for path in match.files():
                 if path == b'.' or path in repo.store:
                     break
             else:
                 slowpath = False
 
     return match, pats, slowpath
 
 
 def _fileancestors(repo, revs, match, followfirst):
     fctxs = []
     for r in revs:
         ctx = repo[r]
         fctxs.extend(ctx[f].introfilectx() for f in ctx.walk(match))
 
     # When displaying a revision with --patch --follow FILE, we have
     # to know which file of the revision must be diffed. With
     # --follow, we want the names of the ancestors of FILE in the
     # revision, stored in "fcache". "fcache" is populated as a side effect
     # of the graph traversal.
     fcache = {}
 
     def filematcher(ctx):
         return scmutil.matchfiles(repo, fcache.get(ctx.rev(), []))
 
     def revgen():
         for rev, cs in dagop.filectxancestors(fctxs, followfirst=followfirst):
             fcache[rev] = [c.path() for c in cs]
             yield rev
 
     return smartset.generatorset(revgen(), iterasc=False), filematcher
 
 
 def _makenofollowfilematcher(repo, pats, opts):
     '''hook for extensions to override the filematcher for non-follow cases'''
     return None
 
 
 _opt2logrevset = {
     b'no_merges': (b'not merge()', None),
     b'only_merges': (b'merge()', None),
     b'_matchfiles': (None, b'_matchfiles(%ps)'),
     b'date': (b'date(%s)', None),
     b'branch': (b'branch(%s)', b'%lr'),
     b'_patslog': (b'filelog(%s)', b'%lr'),
     b'keyword': (b'keyword(%s)', b'%lr'),
     b'prune': (b'ancestors(%s)', b'not %lr'),
     b'user': (b'user(%s)', b'%lr'),
 }
 
 
 def _makerevset(repo, match, pats, slowpath, opts):
     """Return a revset string built from log options and file patterns"""
     opts = dict(opts)
     # follow or not follow?
     follow = opts.get(b'follow') or opts.get(b'follow_first')
 
     # branch and only_branch are really aliases and must be handled at
     # the same time
     opts[b'branch'] = opts.get(b'branch', []) + opts.get(b'only_branch', [])
     opts[b'branch'] = [repo.lookupbranch(b) for b in opts[b'branch']]
 
     if slowpath:
         # See walkchangerevs() slow path.
         #
         # pats/include/exclude cannot be represented as separate
         # revset expressions as their filtering logic applies at file
         # level. For instance "-I a -X b" matches a revision touching
         # "a" and "b" while "file(a) and not file(b)" does
         # not. Besides, filesets are evaluated against the working
         # directory.
         matchargs = [b'r:', b'd:relpath']
         for p in pats:
             matchargs.append(b'p:' + p)
         for p in opts.get(b'include', []):
             matchargs.append(b'i:' + p)
         for p in opts.get(b'exclude', []):
             matchargs.append(b'x:' + p)
         opts[b'_matchfiles'] = matchargs
     elif not follow:
         opts[b'_patslog'] = list(pats)
 
     expr = []
     for op, val in sorted(pycompat.iteritems(opts)):
         if not val:
             continue
         if op not in _opt2logrevset:
             continue
         revop, listop = _opt2logrevset[op]
         if revop and b'%' not in revop:
             expr.append(revop)
         elif not listop:
             expr.append(revsetlang.formatspec(revop, val))
         else:
             if revop:
                 val = [revsetlang.formatspec(revop, v) for v in val]
             expr.append(revsetlang.formatspec(listop, val))
 
     if expr:
         expr = b'(' + b' and '.join(expr) + b')'
     else:
         expr = None
     return expr
 
 
 def _initialrevs(repo, opts):
     """Return the initial set of revisions to be filtered or followed"""
     follow = opts.get(b'follow') or opts.get(b'follow_first')
     if opts.get(b'rev'):
         revs = scmutil.revrange(repo, opts[b'rev'])
     elif follow and repo.dirstate.p1() == nullid:
         revs = smartset.baseset()
     elif follow:
         revs = repo.revs(b'.')
     else:
         revs = smartset.spanset(repo)
         revs.reverse()
     return revs
 
 
 def getrevs(repo, pats, opts):
     # type: (Any, Any, Any) -> Tuple[smartset.BaseSet, changesetdiffer]
     """Return (revs, differ) where revs is a smartset
 
     differ is a changesetdiffer with pre-configured file matcher.
     """
     follow = opts.get(b'follow') or opts.get(b'follow_first')
     followfirst = opts.get(b'follow_first')
     limit = getlimit(opts)
     revs = _initialrevs(repo, opts)
     if not revs:
         return smartset.baseset(), None
     match, pats, slowpath = _makematcher(repo, revs, pats, opts)
     filematcher = None
     if follow:
         if slowpath or match.always():
             revs = dagop.revancestors(repo, revs, followfirst=followfirst)
         else:
             revs, filematcher = _fileancestors(repo, revs, match, followfirst)
         revs.reverse()
     if filematcher is None:
         filematcher = _makenofollowfilematcher(repo, pats, opts)
     if filematcher is None:
 
         def filematcher(ctx):
             return match
 
     expr = _makerevset(repo, match, pats, slowpath, opts)
     if opts.get(b'graph'):
         # User-specified revs might be unsorted, but don't sort before
         # _makerevset because it might depend on the order of revs
         if repo.ui.configbool(b'experimental', b'log.topo'):
             if not revs.istopo():
                 revs = dagop.toposort(revs, repo.changelog.parentrevs)
                 # TODO: try to iterate the set lazily
                 revs = revset.baseset(list(revs), istopo=True)
         elif not (revs.isdescending() or revs.istopo()):
             revs.sort(reverse=True)
     if expr:
         matcher = revset.match(None, expr)
         revs = matcher(repo, revs)
     if limit is not None:
         revs = revs.slice(0, limit)
 
     differ = changesetdiffer()
     differ._makefilematcher = filematcher
     return revs, differ
 
 
 def _parselinerangeopt(repo, opts):
     """Parse --line-range log option and return a list of tuples (filename,
     (fromline, toline)).
     """
     linerangebyfname = []
     for pat in opts.get(b'line_range', []):
         try:
             pat, linerange = pat.rsplit(b',', 1)
         except ValueError:
             raise error.Abort(_(b'malformatted line-range pattern %s') % pat)
         try:
             fromline, toline = map(int, linerange.split(b':'))
         except ValueError:
             raise error.Abort(_(b"invalid line range for %s") % pat)
         msg = _(b"line range pattern '%s' must match exactly one file") % pat
         fname = scmutil.parsefollowlinespattern(repo, None, pat, msg)
         linerangebyfname.append(
             (fname, util.processlinerange(fromline, toline))
         )
     return linerangebyfname
 
 
 def getlinerangerevs(repo, userrevs, opts):
     """Return (revs, differ).
 
     "revs" are revisions obtained by processing "line-range" log options and
     walking block ancestors of each specified file/line-range.
 
     "differ" is a changesetdiffer with pre-configured file matcher and hunks
     filter.
     """
     wctx = repo[None]
 
     # Two-levels map of "rev -> file ctx -> [line range]".
     linerangesbyrev = {}
     for fname, (fromline, toline) in _parselinerangeopt(repo, opts):
         if fname not in wctx:
             raise error.Abort(
                 _(b'cannot follow file not in parent revision: "%s"') % fname
             )
         fctx = wctx.filectx(fname)
         for fctx, linerange in dagop.blockancestors(fctx, fromline, toline):
             rev = fctx.introrev()
             if rev not in userrevs:
                 continue
             linerangesbyrev.setdefault(rev, {}).setdefault(
                 fctx.path(), []
             ).append(linerange)
 
     def nofilterhunksfn(fctx, hunks):
         return hunks
 
     def hunksfilter(ctx):
         fctxlineranges = linerangesbyrev.get(ctx.rev())
         if fctxlineranges is None:
             return nofilterhunksfn
 
         def filterfn(fctx, hunks):
             lineranges = fctxlineranges.get(fctx.path())
             if lineranges is not None:
                 for hr, lines in hunks:
                     if hr is None:  # binary
                         yield hr, lines
                         continue
                     if any(mdiff.hunkinrange(hr[2:], lr) for lr in lineranges):
                         yield hr, lines
             else:
                 for hunk in hunks:
                     yield hunk
 
         return filterfn
 
     def filematcher(ctx):
         files = list(linerangesbyrev.get(ctx.rev(), []))
         return scmutil.matchfiles(repo, files)
 
     revs = sorted(linerangesbyrev, reverse=True)
 
     differ = changesetdiffer()
     differ._makefilematcher = filematcher
     differ._makehunksfilter = hunksfilter
     return smartset.baseset(revs), differ
 
 
 def _graphnodeformatter(ui, displayer):
     spec = ui.config(b'ui', b'graphnodetemplate')
     if not spec:
         return templatekw.getgraphnode  # fast path for "{graphnode}"
 
     spec = templater.unquotestring(spec)
     if isinstance(displayer, changesettemplater):
         # reuse cache of slow templates
         tres = displayer._tresources
     else:
         tres = formatter.templateresources(ui)
     templ = formatter.maketemplater(
         ui, spec, defaults=templatekw.keywords, resources=tres
     )
 
     def formatnode(repo, ctx):
         props = {b'ctx': ctx, b'repo': repo}
         return templ.renderdefault(props)
 
     return formatnode
 
 
 def displaygraph(ui, repo, dag, displayer, edgefn, getcopies=None, props=None):
     props = props or {}
     formatnode = _graphnodeformatter(ui, displayer)
     state = graphmod.asciistate()
     styles = state[b'styles']
 
     # only set graph styling if HGPLAIN is not set.
     if ui.plain(b'graph'):
         # set all edge styles to |, the default pre-3.8 behaviour
         styles.update(dict.fromkeys(styles, b'|'))
     else:
         edgetypes = {
             b'parent': graphmod.PARENT,
             b'grandparent': graphmod.GRANDPARENT,
             b'missing': graphmod.MISSINGPARENT,
         }
         for name, key in edgetypes.items():
             # experimental config: experimental.graphstyle.*
             styles[key] = ui.config(
                 b'experimental', b'graphstyle.%s' % name, styles[key]
             )
             if not styles[key]:
                 styles[key] = None
 
         # experimental config: experimental.graphshorten
         state[b'graphshorten'] = ui.configbool(b'experimental', b'graphshorten')
 
     for rev, type, ctx, parents in dag:
         char = formatnode(repo, ctx)
         copies = getcopies(ctx) if getcopies else None
         edges = edgefn(type, char, state, rev, parents)
         firstedge = next(edges)
         width = firstedge[2]
         displayer.show(
             ctx, copies=copies, graphwidth=width, **pycompat.strkwargs(props)
         )
         lines = displayer.hunk.pop(rev).split(b'\n')
         if not lines[-1]:
             del lines[-1]
         displayer.flush(ctx)
         for type, char, width, coldata in itertools.chain([firstedge], edges):
             graphmod.ascii(ui, state, type, char, lines, coldata)
             lines = []
     displayer.close()
 
 
 def displaygraphrevs(ui, repo, revs, displayer, getrenamed):
     revdag = graphmod.dagwalker(repo, revs)
     displaygraph(ui, repo, revdag, displayer, graphmod.asciiedges, getrenamed)
 
 
 def displayrevs(ui, repo, revs, displayer, getcopies):
     for rev in revs:
         ctx = repo[rev]
         copies = getcopies(ctx) if getcopies else None
         displayer.show(ctx, copies=copies)
         displayer.flush(ctx)
     displayer.close()
 
 
 def checkunsupportedgraphflags(pats, opts):
     for op in [b"newest_first"]:
         if op in opts and opts[op]:
             raise error.Abort(
                 _(b"-G/--graph option is incompatible with --%s")
                 % op.replace(b"_", b"-")
             )
 
 
 def graphrevs(repo, nodes, opts):
     limit = getlimit(opts)
     nodes.reverse()
     if limit is not None:
         nodes = nodes[:limit]
     return graphmod.nodes(repo, nodes)

mercurial/mail.py

@@ -1,517 +1,517
 # mail.py - mail sending bits for mercurial
 #
 # Copyright 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import email
 import email.charset
 import email.generator
 import email.header
 import email.message
 import email.parser
 import io
 import os
 import smtplib
 import socket
 import time
 
 from .i18n import _
 from .pycompat import (
     getattr,
     open,
 )
 from . import (
     encoding,
     error,
     pycompat,
     sslutil,
     util,
 )
 from .utils import (
     procutil,
     stringutil,
 )
 
-if not globals():  # hide this from non-pytype users
+if pycompat.TYPE_CHECKING:
     from typing import Any, List, Tuple, Union
 
     # keep pyflakes happy
     assert all((Any, List, Tuple, Union))
 
 
 class STARTTLS(smtplib.SMTP):
     '''Derived class to verify the peer certificate for STARTTLS.
 
     This class allows to pass any keyword arguments to SSL socket creation.
     '''
 
     def __init__(self, ui, host=None, **kwargs):
         smtplib.SMTP.__init__(self, **kwargs)
         self._ui = ui
         self._host = host
 
     def starttls(self, keyfile=None, certfile=None):
         if not self.has_extn("starttls"):
             msg = b"STARTTLS extension not supported by server"
             raise smtplib.SMTPException(msg)
         (resp, reply) = self.docmd("STARTTLS")
         if resp == 220:
             self.sock = sslutil.wrapsocket(
                 self.sock,
                 keyfile,
                 certfile,
                 ui=self._ui,
                 serverhostname=self._host,
             )
             self.file = self.sock.makefile("rb")
             self.helo_resp = None
             self.ehlo_resp = None
             self.esmtp_features = {}
             self.does_esmtp = 0
         return (resp, reply)
 
 
 class SMTPS(smtplib.SMTP):
     '''Derived class to verify the peer certificate for SMTPS.
 
     This class allows to pass any keyword arguments to SSL socket creation.
     '''
 
     def __init__(self, ui, keyfile=None, certfile=None, host=None, **kwargs):
         self.keyfile = keyfile
         self.certfile = certfile
         smtplib.SMTP.__init__(self, **kwargs)
         self._host = host
         self.default_port = smtplib.SMTP_SSL_PORT
         self._ui = ui
 
     def _get_socket(self, host, port, timeout):
         if self.debuglevel > 0:
             self._ui.debug(b'connect: %r\n' % ((host, port),))
         new_socket = socket.create_connection((host, port), timeout)
         new_socket = sslutil.wrapsocket(
             new_socket,
             self.keyfile,
             self.certfile,
             ui=self._ui,
             serverhostname=self._host,
         )
         self.file = new_socket.makefile('rb')
         return new_socket
 
 
 def _pyhastls():
     # type: () -> bool
     """Returns true iff Python has TLS support, false otherwise."""
     try:
         import ssl
 
         getattr(ssl, 'HAS_TLS', False)
         return True
     except ImportError:
         return False
 
 
 def _smtp(ui):
     '''build an smtp connection and return a function to send mail'''
     local_hostname = ui.config(b'smtp', b'local_hostname')
     tls = ui.config(b'smtp', b'tls')
     # backward compatible: when tls = true, we use starttls.
     starttls = tls == b'starttls' or stringutil.parsebool(tls)
     smtps = tls == b'smtps'
     if (starttls or smtps) and not _pyhastls():
         raise error.Abort(_(b"can't use TLS: Python SSL support not installed"))
     mailhost = ui.config(b'smtp', b'host')
     if not mailhost:
         raise error.Abort(_(b'smtp.host not configured - cannot send mail'))
     if smtps:
         ui.note(_(b'(using smtps)\n'))
         s = SMTPS(ui, local_hostname=local_hostname, host=mailhost)
     elif starttls:
         s = STARTTLS(ui, local_hostname=local_hostname, host=mailhost)
     else:
         s = smtplib.SMTP(local_hostname=local_hostname)
     if smtps:
         defaultport = 465
     else:
         defaultport = 25
     mailport = util.getport(ui.config(b'smtp', b'port', defaultport))
     ui.note(_(b'sending mail: smtp host %s, port %d\n') % (mailhost, mailport))
     s.connect(host=mailhost, port=mailport)
     if starttls:
         ui.note(_(b'(using starttls)\n'))
         s.ehlo()
         s.starttls()
         s.ehlo()
     if starttls or smtps:
         ui.note(_(b'(verifying remote certificate)\n'))
         sslutil.validatesocket(s.sock)
     username = ui.config(b'smtp', b'username')
     password = ui.config(b'smtp', b'password')
     if username:
         if password:
             password = encoding.strfromlocal(password)
         else:
             password = ui.getpass()
     if username and password:
         ui.note(_(b'(authenticating to mail server as %s)\n') % username)
         username = encoding.strfromlocal(username)
         try:
             s.login(username, password)
         except smtplib.SMTPException as inst:
             raise error.Abort(inst)
 
     def send(sender, recipients, msg):
         try:
             return s.sendmail(sender, recipients, msg)
         except smtplib.SMTPRecipientsRefused as inst:
             recipients = [r[1] for r in inst.recipients.values()]
             raise error.Abort(b'\n' + b'\n'.join(recipients))
         except smtplib.SMTPException as inst:
             raise error.Abort(inst)
 
     return send
 
 
 def _sendmail(ui, sender, recipients, msg):
     '''send mail using sendmail.'''
     program = ui.config(b'email', b'method')
 
     def stremail(x):
         return procutil.shellquote(stringutil.email(encoding.strtolocal(x)))
 
     cmdline = b'%s -f %s %s' % (
         program,
         stremail(sender),
         b' '.join(map(stremail, recipients)),
     )
     ui.note(_(b'sending mail: %s\n') % cmdline)
     fp = procutil.popen(cmdline, b'wb')
     fp.write(util.tonativeeol(msg))
     ret = fp.close()
     if ret:
         raise error.Abort(
             b'%s %s'
             % (
                 os.path.basename(program.split(None, 1)[0]),
                 procutil.explainexit(ret),
             )
         )
 
 
 def _mbox(mbox, sender, recipients, msg):
     '''write mails to mbox'''
     fp = open(mbox, b'ab+')
     # Should be time.asctime(), but Windows prints 2-characters day
     # of month instead of one. Make them print the same thing.
     date = time.strftime('%a %b %d %H:%M:%S %Y', time.localtime())
     fp.write(
         b'From %s %s\n'
         % (encoding.strtolocal(sender), encoding.strtolocal(date))
     )
     fp.write(msg)
     fp.write(b'\n\n')
     fp.close()
 
 
 def connect(ui, mbox=None):
     '''make a mail connection. return a function to send mail.
     call as sendmail(sender, list-of-recipients, msg).'''
     if mbox:
         open(mbox, b'wb').close()
         return lambda s, r, m: _mbox(mbox, s, r, m)
     if ui.config(b'email', b'method') == b'smtp':
         return _smtp(ui)
     return lambda s, r, m: _sendmail(ui, s, r, m)
 
 
 def sendmail(ui, sender, recipients, msg, mbox=None):
     send = connect(ui, mbox=mbox)
     return send(sender, recipients, msg)
 
 
 def validateconfig(ui):
     '''determine if we have enough config data to try sending email.'''
     method = ui.config(b'email', b'method')
     if method == b'smtp':
         if not ui.config(b'smtp', b'host'):
             raise error.Abort(
                 _(
                     b'smtp specified as email transport, '
                     b'but no smtp host configured'
                 )
             )
     else:
         if not procutil.findexe(method):
             raise error.Abort(
                 _(b'%r specified as email transport, but not in PATH') % method
             )
 
 
 def codec2iana(cs):
     # type: (str) -> str
     ''''''
     cs = email.charset.Charset(cs).input_charset.lower()
 
     # "latin1" normalizes to "iso8859-1", standard calls for "iso-8859-1"
     if cs.startswith("iso") and not cs.startswith("iso-"):
         return "iso-" + cs[3:]
     return cs
 
 
 def mimetextpatch(s, subtype='plain', display=False):
     # type: (bytes, str, bool) -> email.message.Message
     '''Return MIME message suitable for a patch.
     Charset will be detected by first trying to decode as us-ascii, then utf-8,
     and finally the global encodings. If all those fail, fall back to
     ISO-8859-1, an encoding with that allows all byte sequences.
     Transfer encodings will be used if necessary.'''
 
     cs = [
         'us-ascii',
         'utf-8',
         pycompat.sysstr(encoding.encoding),
         pycompat.sysstr(encoding.fallbackencoding),
     ]
     if display:
         cs = ['us-ascii']
     for charset in cs:
         try:
             s.decode(charset)
             return mimetextqp(s, subtype, codec2iana(charset))
         except UnicodeDecodeError:
             pass
 
     return mimetextqp(s, subtype, "iso-8859-1")
 
 
 def mimetextqp(body, subtype, charset):
     # type: (bytes, str, str) -> email.message.Message
     '''Return MIME message.
     Quoted-printable transfer encoding will be used if necessary.
     '''
     cs = email.charset.Charset(charset)
     msg = email.message.Message()
     msg.set_type('text/' + subtype)
 
     for line in body.splitlines():
         if len(line) > 950:
             cs.body_encoding = email.charset.QP
             break
 
     # On Python 2, this simply assigns a value. Python 3 inspects
     # body and does different things depending on whether it has
     # encode() or decode() attributes. We can get the old behavior
     # if we pass a str and charset is None and we call set_charset().
     # But we may get into  trouble later due to Python attempting to
     # encode/decode using the registered charset (or attempting to
     # use ascii in the absence of a charset).
     msg.set_payload(body, cs)
 
     return msg
 
 
 def _charsets(ui):
     # type: (Any) -> List[str]
     '''Obtains charsets to send mail parts not containing patches.'''
     charsets = [
         pycompat.sysstr(cs.lower())
         for cs in ui.configlist(b'email', b'charsets')
     ]
     fallbacks = [
         pycompat.sysstr(encoding.fallbackencoding.lower()),
         pycompat.sysstr(encoding.encoding.lower()),
         'utf-8',
     ]
     for cs in fallbacks:  # find unique charsets while keeping order
         if cs not in charsets:
             charsets.append(cs)
     return [cs for cs in charsets if not cs.endswith('ascii')]
 
 
 def _encode(ui, s, charsets):
     # type: (Any, bytes, List[str]) -> Tuple[bytes, str]
     '''Returns (converted) string, charset tuple.
     Finds out best charset by cycling through sendcharsets in descending
     order. Tries both encoding and fallbackencoding for input. Only as
     last resort send as is in fake ascii.
     Caveat: Do not use for mail parts containing patches!'''
     sendcharsets = charsets or _charsets(ui)
     if not isinstance(s, bytes):
         # We have unicode data, which we need to try and encode to
         # some reasonable-ish encoding. Try the encodings the user
         # wants, and fall back to garbage-in-ascii.
         for ocs in sendcharsets:
             try:
                 return s.encode(ocs), ocs
             except UnicodeEncodeError:
                 pass
             except LookupError:
                 ui.warn(
                     _(b'ignoring invalid sendcharset: %s\n')
                     % pycompat.sysbytes(ocs)
                 )
         else:
             # Everything failed, ascii-armor what we've got and send it.
             return s.encode('ascii', 'backslashreplace'), 'us-ascii'
     # We have a bytes of unknown encoding. We'll try and guess a valid
     # encoding, falling back to pretending we had ascii even though we
     # know that's wrong.
     try:
         s.decode('ascii')
     except UnicodeDecodeError:
         for ics in (encoding.encoding, encoding.fallbackencoding):
             ics = pycompat.sysstr(ics)
             try:
                 u = s.decode(ics)
             except UnicodeDecodeError:
                 continue
             for ocs in sendcharsets:
                 try:
                     return u.encode(ocs), ocs
                 except UnicodeEncodeError:
                     pass
                 except LookupError:
                     ui.warn(
                         _(b'ignoring invalid sendcharset: %s\n')
                         % pycompat.sysbytes(ocs)
                     )
     # if ascii, or all conversion attempts fail, send (broken) ascii
     return s, 'us-ascii'
 
 
 def headencode(ui, s, charsets=None, display=False):
     # type: (Any, Union[bytes, str], List[str], bool) -> str
     '''Returns RFC-2047 compliant header from given string.'''
     if not display:
         # split into words?
         s, cs = _encode(ui, s, charsets)
         return email.header.Header(s, cs).encode()
     return encoding.strfromlocal(s)
 
 
 def _addressencode(ui, name, addr, charsets=None):
     # type: (Any, str, str, List[str]) -> str
     addr = encoding.strtolocal(addr)
     name = headencode(ui, name, charsets)
     try:
         acc, dom = addr.split(b'@')
         acc.decode('ascii')
         dom = dom.decode(pycompat.sysstr(encoding.encoding)).encode('idna')
         addr = b'%s@%s' % (acc, dom)
     except UnicodeDecodeError:
         raise error.Abort(_(b'invalid email address: %s') % addr)
     except ValueError:
         try:
             # too strict?
             addr.decode('ascii')
         except UnicodeDecodeError:
             raise error.Abort(_(b'invalid local address: %s') % addr)
     return email.utils.formataddr((name, encoding.strfromlocal(addr)))
 
 
 def addressencode(ui, address, charsets=None, display=False):
     # type: (Any, bytes, List[str], bool) -> str
     '''Turns address into RFC-2047 compliant header.'''
     if display or not address:
         return encoding.strfromlocal(address or b'')
     name, addr = email.utils.parseaddr(encoding.strfromlocal(address))
     return _addressencode(ui, name, addr, charsets)
 
 
 def addrlistencode(ui, addrs, charsets=None, display=False):
     # type: (Any, List[bytes], List[str], bool) -> List[str]
     '''Turns a list of addresses into a list of RFC-2047 compliant headers.
     A single element of input list may contain multiple addresses, but output
     always has one address per item'''
     straddrs = []
     for a in addrs:
         assert isinstance(a, bytes), '%r unexpectedly not a bytestr' % a
         straddrs.append(encoding.strfromlocal(a))
     if display:
         return [a.strip() for a in straddrs if a.strip()]
 
     result = []
     for name, addr in email.utils.getaddresses(straddrs):
         if name or addr:
             r = _addressencode(ui, name, addr, charsets)
             result.append(r)
     return result
 
 
 def mimeencode(ui, s, charsets=None, display=False):
     # type: (Any, bytes, List[str], bool) -> email.message.Message
     '''creates mime text object, encodes it if needed, and sets
     charset and transfer-encoding accordingly.'''
     cs = 'us-ascii'
     if not display:
         s, cs = _encode(ui, s, charsets)
     return mimetextqp(s, 'plain', cs)
 
 
 if pycompat.ispy3:
 
     Generator = email.generator.BytesGenerator
 
     def parse(fp):
         # type: (Any) -> email.message.Message
         ep = email.parser.Parser()
         # disable the "universal newlines" mode, which isn't binary safe.
         # I have no idea if ascii/surrogateescape is correct, but that's
         # what the standard Python email parser does.
         fp = io.TextIOWrapper(
             fp, encoding='ascii', errors='surrogateescape', newline=chr(10)
         )
         try:
             return ep.parse(fp)
         finally:
             fp.detach()
 
     def parsebytes(data):
         # type: (bytes) -> email.message.Message
         ep = email.parser.BytesParser()
         return ep.parsebytes(data)
 
 
 else:
 
     Generator = email.generator.Generator
 
     def parse(fp):
         # type: (Any) -> email.message.Message
         ep = email.parser.Parser()
         return ep.parse(fp)
 
     def parsebytes(data):
         # type: (str) -> email.message.Message
         ep = email.parser.Parser()
         return ep.parsestr(data)
 
 
 def headdecode(s):
     # type: (Union[email.header.Header, bytes]) -> bytes
     '''Decodes RFC-2047 header'''
     uparts = []
     for part, charset in email.header.decode_header(s):
         if charset is not None:
             try:
                 uparts.append(part.decode(charset))
                 continue
             except (UnicodeDecodeError, LookupError):
                 pass
         # On Python 3, decode_header() may return either bytes or unicode
         # depending on whether the header has =?<charset>? or not
         if isinstance(part, type(u'')):
             uparts.append(part)
             continue
         try:
             uparts.append(part.decode('UTF-8'))
             continue
         except UnicodeDecodeError:
             pass
         uparts.append(part.decode('ISO-8859-1'))
     return encoding.unitolocal(u' '.join(uparts))

mercurial/pycompat.py

@@ -1,506 +1,512
 # pycompat.py - portability shim for python 3
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """Mercurial portability shim for python 3.
 
 This contains aliases to hide python version-specific details from the core.
 """
 
 from __future__ import absolute_import
 
 import getopt
 import inspect
 import json
 import os
 import shlex
 import sys
 import tempfile
 
 ispy3 = sys.version_info[0] >= 3
 ispypy = '__pypy__' in sys.builtin_module_names
+TYPE_CHECKING = False
+
+if not globals():  # hide this from non-pytype users
+    import typing
+
+    TYPE_CHECKING = typing.TYPE_CHECKING
 
 if not ispy3:
     import cookielib
     import cPickle as pickle
     import httplib
     import Queue as queue
     import SocketServer as socketserver
     import xmlrpclib
 
     from .thirdparty.concurrent import futures
 
     def future_set_exception_info(f, exc_info):
         f.set_exception_info(*exc_info)
 
 
 else:
     import concurrent.futures as futures
     import http.cookiejar as cookielib
     import http.client as httplib
     import pickle
     import queue as queue
     import socketserver
     import xmlrpc.client as xmlrpclib
 
     def future_set_exception_info(f, exc_info):
         f.set_exception(exc_info[0])
 
 
 def identity(a):
     return a
 
 
 def _rapply(f, xs):
     if xs is None:
         # assume None means non-value of optional data
         return xs
     if isinstance(xs, (list, set, tuple)):
         return type(xs)(_rapply(f, x) for x in xs)
     if isinstance(xs, dict):
         return type(xs)((_rapply(f, k), _rapply(f, v)) for k, v in xs.items())
     return f(xs)
 
 
 def rapply(f, xs):
     """Apply function recursively to every item preserving the data structure
 
     >>> def f(x):
     ...     return 'f(%s)' % x
     >>> rapply(f, None) is None
     True
     >>> rapply(f, 'a')
     'f(a)'
     >>> rapply(f, {'a'}) == {'f(a)'}
     True
     >>> rapply(f, ['a', 'b', None, {'c': 'd'}, []])
     ['f(a)', 'f(b)', None, {'f(c)': 'f(d)'}, []]
 
     >>> xs = [object()]
     >>> rapply(identity, xs) is xs
     True
     """
     if f is identity:
         # fast path mainly for py2
         return xs
     return _rapply(f, xs)
 
 
 if ispy3:
     import builtins
     import codecs
     import functools
     import io
     import struct
 
     if os.name == r'nt' and sys.version_info >= (3, 6):
         # MBCS (or ANSI) filesystem encoding must be used as before.
         # Otherwise non-ASCII filenames in existing repositories would be
         # corrupted.
         # This must be set once prior to any fsencode/fsdecode calls.
         sys._enablelegacywindowsfsencoding()  # pytype: disable=module-attr
 
     fsencode = os.fsencode
     fsdecode = os.fsdecode
     oscurdir = os.curdir.encode('ascii')
     oslinesep = os.linesep.encode('ascii')
     osname = os.name.encode('ascii')
     ospathsep = os.pathsep.encode('ascii')
     ospardir = os.pardir.encode('ascii')
     ossep = os.sep.encode('ascii')
     osaltsep = os.altsep
     if osaltsep:
         osaltsep = osaltsep.encode('ascii')
 
     sysplatform = sys.platform.encode('ascii')
     sysexecutable = sys.executable
     if sysexecutable:
         sysexecutable = os.fsencode(sysexecutable)
     bytesio = io.BytesIO
     # TODO deprecate stringio name, as it is a lie on Python 3.
     stringio = bytesio
 
     def maplist(*args):
         return list(map(*args))
 
     def rangelist(*args):
         return list(range(*args))
 
     def ziplist(*args):
         return list(zip(*args))
 
     rawinput = input
     getargspec = inspect.getfullargspec
 
     long = int
 
     # TODO: .buffer might not exist if std streams were replaced; we'll need
     # a silly wrapper to make a bytes stream backed by a unicode one.
     stdin = sys.stdin.buffer
     stdout = sys.stdout.buffer
     stderr = sys.stderr.buffer
 
     # Since Python 3 converts argv to wchar_t type by Py_DecodeLocale() on Unix,
     # we can use os.fsencode() to get back bytes argv.
     #
     # https://hg.python.org/cpython/file/v3.5.1/Programs/python.c#l55
     #
     # On Windows, the native argv is unicode and is converted to MBCS bytes
     # since we do enable the legacy filesystem encoding.
     if getattr(sys, 'argv', None) is not None:
         sysargv = list(map(os.fsencode, sys.argv))
 
     bytechr = struct.Struct('>B').pack
     byterepr = b'%r'.__mod__
 
     class bytestr(bytes):
         """A bytes which mostly acts as a Python 2 str
 
         >>> bytestr(), bytestr(bytearray(b'foo')), bytestr(u'ascii'), bytestr(1)
         ('', 'foo', 'ascii', '1')
         >>> s = bytestr(b'foo')
         >>> assert s is bytestr(s)
 
         __bytes__() should be called if provided:
 
         >>> class bytesable(object):
         ...     def __bytes__(self):
         ...         return b'bytes'
         >>> bytestr(bytesable())
         'bytes'
 
         There's no implicit conversion from non-ascii str as its encoding is
         unknown:
 
         >>> bytestr(chr(0x80)) # doctest: +ELLIPSIS
         Traceback (most recent call last):
           ...
         UnicodeEncodeError: ...
 
         Comparison between bytestr and bytes should work:
 
         >>> assert bytestr(b'foo') == b'foo'
         >>> assert b'foo' == bytestr(b'foo')
         >>> assert b'f' in bytestr(b'foo')
         >>> assert bytestr(b'f') in b'foo'
 
         Sliced elements should be bytes, not integer:
 
         >>> s[1], s[:2]
         (b'o', b'fo')
         >>> list(s), list(reversed(s))
         ([b'f', b'o', b'o'], [b'o', b'o', b'f'])
 
         As bytestr type isn't propagated across operations, you need to cast
         bytes to bytestr explicitly:
 
         >>> s = bytestr(b'foo').upper()
         >>> t = bytestr(s)
         >>> s[0], t[0]
         (70, b'F')
 
         Be careful to not pass a bytestr object to a function which expects
         bytearray-like behavior.
 
         >>> t = bytes(t)  # cast to bytes
         >>> assert type(t) is bytes
         """
 
         def __new__(cls, s=b''):
             if isinstance(s, bytestr):
                 return s
             if not isinstance(
                 s, (bytes, bytearray)
             ) and not hasattr(  # hasattr-py3-only
                 s, u'__bytes__'
             ):
                 s = str(s).encode('ascii')
             return bytes.__new__(cls, s)
 
         def __getitem__(self, key):
             s = bytes.__getitem__(self, key)
             if not isinstance(s, bytes):
                 s = bytechr(s)
             return s
 
         def __iter__(self):
             return iterbytestr(bytes.__iter__(self))
 
         def __repr__(self):
             return bytes.__repr__(self)[1:]  # drop b''
 
     def iterbytestr(s):
         """Iterate bytes as if it were a str object of Python 2"""
         return map(bytechr, s)
 
     def maybebytestr(s):
         """Promote bytes to bytestr"""
         if isinstance(s, bytes):
             return bytestr(s)
         return s
 
     def sysbytes(s):
         """Convert an internal str (e.g. keyword, __doc__) back to bytes
 
         This never raises UnicodeEncodeError, but only ASCII characters
         can be round-trip by sysstr(sysbytes(s)).
         """
         return s.encode('utf-8')
 
     def sysstr(s):
         """Return a keyword str to be passed to Python functions such as
         getattr() and str.encode()
 
         This never raises UnicodeDecodeError. Non-ascii characters are
         considered invalid and mapped to arbitrary but unique code points
         such that 'sysstr(a) != sysstr(b)' for all 'a != b'.
         """
         if isinstance(s, builtins.str):
             return s
         return s.decode('latin-1')
 
     def strurl(url):
         """Converts a bytes url back to str"""
         if isinstance(url, bytes):
             return url.decode('ascii')
         return url
 
     def bytesurl(url):
         """Converts a str url to bytes by encoding in ascii"""
         if isinstance(url, str):
             return url.encode('ascii')
         return url
 
     def raisewithtb(exc, tb):
         """Raise exception with the given traceback"""
         raise exc.with_traceback(tb)
 
     def getdoc(obj):
         """Get docstring as bytes; may be None so gettext() won't confuse it
         with _('')"""
         doc = getattr(obj, '__doc__', None)
         if doc is None:
             return doc
         return sysbytes(doc)
 
     def _wrapattrfunc(f):
         @functools.wraps(f)
         def w(object, name, *args):
             return f(object, sysstr(name), *args)
 
         return w
 
     # these wrappers are automagically imported by hgloader
     delattr = _wrapattrfunc(builtins.delattr)
     getattr = _wrapattrfunc(builtins.getattr)
     hasattr = _wrapattrfunc(builtins.hasattr)
     setattr = _wrapattrfunc(builtins.setattr)
     xrange = builtins.range
     unicode = str
 
     def open(name, mode=b'r', buffering=-1, encoding=None):
         return builtins.open(name, sysstr(mode), buffering, encoding)
 
     safehasattr = _wrapattrfunc(builtins.hasattr)
 
     def _getoptbwrapper(orig, args, shortlist, namelist):
         """
         Takes bytes arguments, converts them to unicode, pass them to
         getopt.getopt(), convert the returned values back to bytes and then
         return them for Python 3 compatibility as getopt.getopt() don't accepts
         bytes on Python 3.
         """
         args = [a.decode('latin-1') for a in args]
         shortlist = shortlist.decode('latin-1')
         namelist = [a.decode('latin-1') for a in namelist]
         opts, args = orig(args, shortlist, namelist)
         opts = [(a[0].encode('latin-1'), a[1].encode('latin-1')) for a in opts]
         args = [a.encode('latin-1') for a in args]
         return opts, args
 
     def strkwargs(dic):
         """
         Converts the keys of a python dictonary to str i.e. unicodes so that
         they can be passed as keyword arguments as dictonaries with bytes keys
         can't be passed as keyword arguments to functions on Python 3.
         """
         dic = dict((k.decode('latin-1'), v) for k, v in dic.items())
         return dic
 
     def byteskwargs(dic):
         """
         Converts keys of python dictonaries to bytes as they were converted to
         str to pass that dictonary as a keyword argument on Python 3.
         """
         dic = dict((k.encode('latin-1'), v) for k, v in dic.items())
         return dic
 
     # TODO: handle shlex.shlex().
     def shlexsplit(s, comments=False, posix=True):
         """
         Takes bytes argument, convert it to str i.e. unicodes, pass that into
         shlex.split(), convert the returned value to bytes and return that for
         Python 3 compatibility as shelx.split() don't accept bytes on Python 3.
         """
         ret = shlex.split(s.decode('latin-1'), comments, posix)
         return [a.encode('latin-1') for a in ret]
 
     iteritems = lambda x: x.items()
     itervalues = lambda x: x.values()
 
     # Python 3.5's json.load and json.loads require str. We polyfill its
     # code for detecting encoding from bytes.
     if sys.version_info[0:2] < (3, 6):
 
         def _detect_encoding(b):
             bstartswith = b.startswith
             if bstartswith((codecs.BOM_UTF32_BE, codecs.BOM_UTF32_LE)):
                 return 'utf-32'
             if bstartswith((codecs.BOM_UTF16_BE, codecs.BOM_UTF16_LE)):
                 return 'utf-16'
             if bstartswith(codecs.BOM_UTF8):
                 return 'utf-8-sig'
 
             if len(b) >= 4:
                 if not b[0]:
                     # 00 00 -- -- - utf-32-be
                     # 00 XX -- -- - utf-16-be
                     return 'utf-16-be' if b[1] else 'utf-32-be'
                 if not b[1]:
                     # XX 00 00 00 - utf-32-le
                     # XX 00 00 XX - utf-16-le
                     # XX 00 XX -- - utf-16-le
                     return 'utf-16-le' if b[2] or b[3] else 'utf-32-le'
             elif len(b) == 2:
                 if not b[0]:
                     # 00 XX - utf-16-be
                     return 'utf-16-be'
                 if not b[1]:
                     # XX 00 - utf-16-le
                     return 'utf-16-le'
             # default
             return 'utf-8'
 
         def json_loads(s, *args, **kwargs):
             if isinstance(s, (bytes, bytearray)):
                 s = s.decode(_detect_encoding(s), 'surrogatepass')
 
             return json.loads(s, *args, **kwargs)
 
     else:
         json_loads = json.loads
 
 else:
     import cStringIO
 
     xrange = xrange
     unicode = unicode
     bytechr = chr
     byterepr = repr
     bytestr = str
     iterbytestr = iter
     maybebytestr = identity
     sysbytes = identity
     sysstr = identity
     strurl = identity
     bytesurl = identity
     open = open
     delattr = delattr
     getattr = getattr
     hasattr = hasattr
     setattr = setattr
 
     # this can't be parsed on Python 3
     exec(b'def raisewithtb(exc, tb):\n    raise exc, None, tb\n')
 
     def fsencode(filename):
         """
         Partial backport from os.py in Python 3, which only accepts bytes.
         In Python 2, our paths should only ever be bytes, a unicode path
         indicates a bug.
         """
         if isinstance(filename, str):
             return filename
         else:
             raise TypeError("expect str, not %s" % type(filename).__name__)
 
     # In Python 2, fsdecode() has a very chance to receive bytes. So it's
     # better not to touch Python 2 part as it's already working fine.
     fsdecode = identity
 
     def getdoc(obj):
         return getattr(obj, '__doc__', None)
 
     _notset = object()
 
     def safehasattr(thing, attr):
         return getattr(thing, attr, _notset) is not _notset
 
     def _getoptbwrapper(orig, args, shortlist, namelist):
         return orig(args, shortlist, namelist)
 
     strkwargs = identity
     byteskwargs = identity
 
     oscurdir = os.curdir
     oslinesep = os.linesep
     osname = os.name
     ospathsep = os.pathsep
     ospardir = os.pardir
     ossep = os.sep
     osaltsep = os.altsep
     long = long
     stdin = sys.stdin
     stdout = sys.stdout
     stderr = sys.stderr
     if getattr(sys, 'argv', None) is not None:
         sysargv = sys.argv
     sysplatform = sys.platform
     sysexecutable = sys.executable
     shlexsplit = shlex.split
     bytesio = cStringIO.StringIO
     stringio = bytesio
     maplist = map
     rangelist = range
     ziplist = zip
     rawinput = raw_input
     getargspec = inspect.getargspec
     iteritems = lambda x: x.iteritems()
     itervalues = lambda x: x.itervalues()
     json_loads = json.loads
 
 isjython = sysplatform.startswith(b'java')
 
 isdarwin = sysplatform.startswith(b'darwin')
 islinux = sysplatform.startswith(b'linux')
 isposix = osname == b'posix'
 iswindows = osname == b'nt'
 
 
 def getoptb(args, shortlist, namelist):
     return _getoptbwrapper(getopt.getopt, args, shortlist, namelist)
 
 
 def gnugetoptb(args, shortlist, namelist):
     return _getoptbwrapper(getopt.gnu_getopt, args, shortlist, namelist)
 
 
 def mkdtemp(suffix=b'', prefix=b'tmp', dir=None):
     return tempfile.mkdtemp(suffix, prefix, dir)
 
 
 # text=True is not supported; use util.from/tonativeeol() instead
 def mkstemp(suffix=b'', prefix=b'tmp', dir=None):
     return tempfile.mkstemp(suffix, prefix, dir)
 
 
 # mode must include 'b'ytes as encoding= is not supported
 def namedtempfile(
     mode=b'w+b', bufsize=-1, suffix=b'', prefix=b'tmp', dir=None, delete=True
 ):
     mode = sysstr(mode)
     assert 'b' in mode
     return tempfile.NamedTemporaryFile(
         mode, bufsize, suffix=suffix, prefix=prefix, dir=dir, delete=delete
     )

mercurial/state.py

@@ -1,280 +1,281
 # state.py - writing and reading state files in Mercurial
 #
 # Copyright 2018 Pulkit Goyal <[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.
 
 """
 This file contains class to wrap the state for commands and other
 related logic.
 
 All the data related to the command state is stored as dictionary in the object.
 The class has methods using which the data can be stored to disk in a file under
 .hg/ directory.
 
 We store the data on disk in cbor, for which we use the CBOR format to encode
 the data.
 """
 
 from __future__ import absolute_import
 
 from .i18n import _
 
 from . import (
     error,
+    pycompat,
     util,
 )
 from .utils import cborutil
 
-if not globals():
+if pycompat.TYPE_CHECKING:
     from typing import (
         Any,
         Dict,
     )
 
     for t in (Any, Dict):
         assert t
 
 
 class cmdstate(object):
     """a wrapper class to store the state of commands like `rebase`, `graft`,
     `histedit`, `shelve` etc. Extensions can also use this to write state files.
 
     All the data for the state is stored in the form of key-value pairs in a
     dictionary.
 
     The class object can write all the data to a file in .hg/ directory and
     can populate the object data reading that file.
 
     Uses cbor to serialize and deserialize data while writing and reading from
     disk.
     """
 
     def __init__(self, repo, fname):
         """ repo is the repo object
         fname is the file name in which data should be stored in .hg directory
         """
         self._repo = repo
         self.fname = fname
 
     def read(self):
         # type: () -> Dict[bytes, Any]
         """read the existing state file and return a dict of data stored"""
         return self._read()
 
     def save(self, version, data):
         """write all the state data stored to .hg/<filename> file
 
         we use third-party library cbor to serialize data to write in the file.
         """
         if not isinstance(version, int):
             raise error.ProgrammingError(
                 b"version of state file should be an integer"
             )
 
         with self._repo.vfs(self.fname, b'wb', atomictemp=True) as fp:
             fp.write(b'%d\n' % version)
             for chunk in cborutil.streamencode(data):
                 fp.write(chunk)
 
     def _read(self):
         """reads the state file and returns a dictionary which contain
         data in the same format as it was before storing"""
         with self._repo.vfs(self.fname, b'rb') as fp:
             try:
                 int(fp.readline())
             except ValueError:
                 raise error.CorruptedState(
                     b"unknown version of state file found"
                 )
 
             return cborutil.decodeall(fp.read())[0]
 
     def delete(self):
         """drop the state file if exists"""
         util.unlinkpath(self._repo.vfs.join(self.fname), ignoremissing=True)
 
     def exists(self):
         """check whether the state file exists or not"""
         return self._repo.vfs.exists(self.fname)
 
 
 class _statecheck(object):
     """a utility class that deals with multistep operations like graft,
        histedit, bisect, update etc and check whether such commands
        are in an unfinished conditition or not and return appropriate message
        and hint.
        It also has the ability to register and determine the states of any new
        multistep operation or multistep command extension.
     """
 
     def __init__(
         self,
         opname,
         fname,
         clearable,
         allowcommit,
         reportonly,
         continueflag,
         stopflag,
         cmdmsg,
         cmdhint,
         statushint,
         abortfunc,
         continuefunc,
     ):
         self._opname = opname
         self._fname = fname
         self._clearable = clearable
         self._allowcommit = allowcommit
         self._reportonly = reportonly
         self._continueflag = continueflag
         self._stopflag = stopflag
         self._cmdmsg = cmdmsg
         self._cmdhint = cmdhint
         self._statushint = statushint
         self.abortfunc = abortfunc
         self.continuefunc = continuefunc
 
     def statusmsg(self):
         """returns the hint message corresponding to the command for
         hg status --verbose
         """
         if not self._statushint:
             hint = _(
                 b'To continue:    hg %s --continue\n'
                 b'To abort:       hg %s --abort'
             ) % (self._opname, self._opname)
             if self._stopflag:
                 hint = hint + (
                     _(b'\nTo stop:        hg %s --stop') % (self._opname)
                 )
             return hint
         return self._statushint
 
     def hint(self):
         """returns the hint message corresponding to an interrupted
         operation
         """
         if not self._cmdhint:
             return _(b"use 'hg %s --continue' or 'hg %s --abort'") % (
                 self._opname,
                 self._opname,
             )
         return self._cmdhint
 
     def msg(self):
         """returns the status message corresponding to the command"""
         if not self._cmdmsg:
             return _(b'%s in progress') % (self._opname)
         return self._cmdmsg
 
     def continuemsg(self):
         """ returns appropriate continue message corresponding to command"""
         return _(b'hg %s --continue') % (self._opname)
 
     def isunfinished(self, repo):
         """determines whether a multi-step operation is in progress
         or not
         """
         if self._opname == b'merge':
             return len(repo[None].parents()) > 1
         else:
             return repo.vfs.exists(self._fname)
 
 
 # A list of statecheck objects for multistep operations like graft.
 _unfinishedstates = []
 
 
 def addunfinished(
     opname,
     fname,
     clearable=False,
     allowcommit=False,
     reportonly=False,
     continueflag=False,
     stopflag=False,
     cmdmsg=b"",
     cmdhint=b"",
     statushint=b"",
     abortfunc=None,
     continuefunc=None,
 ):
     """this registers a new command or operation to unfinishedstates
     opname is the name the command or operation
     fname is the file name in which data should be stored in .hg directory.
     It is None for merge command.
     clearable boolean determines whether or not interrupted states can be
     cleared by running `hg update -C .` which in turn deletes the
     state file.
     allowcommit boolean decides whether commit is allowed during interrupted
     state or not.
     reportonly flag is used for operations like bisect where we just
     need to detect the operation using 'hg status --verbose'
     continueflag is a boolean determines whether or not a command supports
     `--continue` option or not.
     stopflag is a boolean that determines whether or not a command supports
     --stop flag
     cmdmsg is used to pass a different status message in case standard
     message of the format "abort: cmdname in progress" is not desired.
     cmdhint is used to pass a different hint message in case standard
     message of the format "To continue: hg cmdname --continue
     To abort: hg cmdname --abort" is not desired.
     statushint is used to pass a different status message in case standard
     message of the format ('To continue:    hg cmdname --continue'
     'To abort:       hg cmdname --abort') is not desired
     abortfunc stores the function required to abort an unfinished state.
     continuefunc stores the function required to finish an interrupted
     operation.
     """
     statecheckobj = _statecheck(
         opname,
         fname,
         clearable,
         allowcommit,
         reportonly,
         continueflag,
         stopflag,
         cmdmsg,
         cmdhint,
         statushint,
         abortfunc,
         continuefunc,
     )
     if opname == b'merge':
         _unfinishedstates.append(statecheckobj)
     else:
         _unfinishedstates.insert(0, statecheckobj)
 
 
 addunfinished(
     b'update',
     fname=b'updatestate',
     clearable=True,
     cmdmsg=_(b'last update was interrupted'),
     cmdhint=_(b"use 'hg update' to get a consistent checkout"),
     statushint=_(b"To continue:    hg update ."),
 )
 addunfinished(
     b'bisect',
     fname=b'bisect.state',
     allowcommit=True,
     reportonly=True,
     statushint=_(
         b'To mark the changeset good:    hg bisect --good\n'
         b'To mark the changeset bad:     hg bisect --bad\n'
         b'To abort:                      hg bisect --reset\n'
     ),
 )
 
 
 def getrepostate(repo):
     # experimental config: commands.status.skipstates
     skip = set(repo.ui.configlist(b'commands', b'status.skipstates'))
     for state in _unfinishedstates:
         if state._opname in skip:
             continue
         if state.isunfinished(repo):
             return (state._opname, state.statusmsg())