py3: delete b'' prefix from safehasattr arguments

Differential Revision: https://phab.mercurial-scm.org/D7029

hgext/absorb.py

@@ -1,1131 +1,1131 b''
 # absorb.py
 #
 # Copyright 2016 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """apply working directory changes to changesets (EXPERIMENTAL)
 
 The absorb extension provides a command to use annotate information to
 amend modified chunks into the corresponding non-public changesets.
 
 ::
 
     [absorb]
     # only check 50 recent non-public changesets at most
     max-stack-size = 50
     # whether to add noise to new commits to avoid obsolescence cycle
     add-noise = 1
     # make `amend --correlated` a shortcut to the main command
     amend-flag = correlated
 
     [color]
     absorb.description = yellow
     absorb.node = blue bold
     absorb.path = bold
 """
 
 # TODO:
 #  * Rename config items to [commands] namespace
 #  * Converge getdraftstack() with other code in core
 #  * move many attributes on fixupstate to be private
 
 from __future__ import absolute_import
 
 import collections
 
 from mercurial.i18n import _
 from mercurial import (
     cmdutil,
     commands,
     context,
     crecord,
     error,
     linelog,
     mdiff,
     node,
     obsolete,
     patch,
     phases,
     pycompat,
     registrar,
     scmutil,
     util,
 )
 from mercurial.utils import stringutil
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = b'ships-with-hg-core'
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem(b'absorb', b'add-noise', default=True)
 configitem(b'absorb', b'amend-flag', default=None)
 configitem(b'absorb', b'max-stack-size', default=50)
 
 colortable = {
     b'absorb.description': b'yellow',
     b'absorb.node': b'blue bold',
     b'absorb.path': b'bold',
 }
 
 defaultdict = collections.defaultdict
 
 
 class nullui(object):
     """blank ui object doing nothing"""
 
     debugflag = False
     verbose = False
     quiet = True
 
     def __getitem__(name):
         def nullfunc(*args, **kwds):
             return
 
         return nullfunc
 
 
 class emptyfilecontext(object):
     """minimal filecontext representing an empty file"""
 
     def data(self):
         return b''
 
     def node(self):
         return node.nullid
 
 
 def uniq(lst):
     """list -> list. remove duplicated items without changing the order"""
     seen = set()
     result = []
     for x in lst:
         if x not in seen:
             seen.add(x)
             result.append(x)
     return result
 
 
 def getdraftstack(headctx, limit=None):
     """(ctx, int?) -> [ctx]. get a linear stack of non-public changesets.
 
     changesets are sorted in topo order, oldest first.
     return at most limit items, if limit is a positive number.
 
     merges are considered as non-draft as well. i.e. every commit
     returned has and only has 1 parent.
     """
     ctx = headctx
     result = []
     while ctx.phase() != phases.public:
         if limit and len(result) >= limit:
             break
         parents = ctx.parents()
         if len(parents) != 1:
             break
         result.append(ctx)
         ctx = parents[0]
     result.reverse()
     return result
 
 
 def getfilestack(stack, path, seenfctxs=None):
     """([ctx], str, set) -> [fctx], {ctx: fctx}
 
     stack is a list of contexts, from old to new. usually they are what
     "getdraftstack" returns.
 
     follows renames, but not copies.
 
     seenfctxs is a set of filecontexts that will be considered "immutable".
     they are usually what this function returned in earlier calls, useful
     to avoid issues that a file was "moved" to multiple places and was then
     modified differently, like: "a" was copied to "b", "a" was also copied to
     "c" and then "a" was deleted, then both "b" and "c" were "moved" from "a"
     and we enforce only one of them to be able to affect "a"'s content.
 
     return an empty list and an empty dict, if the specified path does not
     exist in stack[-1] (the top of the stack).
 
     otherwise, return a list of de-duplicated filecontexts, and the map to
     convert ctx in the stack to fctx, for possible mutable fctxs. the first item
     of the list would be outside the stack and should be considered immutable.
     the remaining items are within the stack.
 
     for example, given the following changelog and corresponding filelog
     revisions:
 
       changelog: 3----4----5----6----7
       filelog:   x    0----1----1----2 (x: no such file yet)
 
     - if stack = [5, 6, 7], returns ([0, 1, 2], {5: 1, 6: 1, 7: 2})
     - if stack = [3, 4, 5], returns ([e, 0, 1], {4: 0, 5: 1}), where "e" is a
       dummy empty filecontext.
     - if stack = [2], returns ([], {})
     - if stack = [7], returns ([1, 2], {7: 2})
     - if stack = [6, 7], returns ([1, 2], {6: 1, 7: 2}), although {6: 1} can be
       removed, since 1 is immutable.
     """
     if seenfctxs is None:
         seenfctxs = set()
     assert stack
 
     if path not in stack[-1]:
         return [], {}
 
     fctxs = []
     fctxmap = {}
 
     pctx = stack[0].p1()  # the public (immutable) ctx we stop at
     for ctx in reversed(stack):
         if path not in ctx:  # the file is added in the next commit
             pctx = ctx
             break
         fctx = ctx[path]
         fctxs.append(fctx)
         if fctx in seenfctxs:  # treat fctx as the immutable one
             pctx = None  # do not add another immutable fctx
             break
         fctxmap[ctx] = fctx  # only for mutable fctxs
         copy = fctx.copysource()
         if copy:
             path = copy  # follow rename
             if path in ctx:  # but do not follow copy
                 pctx = ctx.p1()
                 break
 
     if pctx is not None:  # need an extra immutable fctx
         if path in pctx:
             fctxs.append(pctx[path])
         else:
             fctxs.append(emptyfilecontext())
 
     fctxs.reverse()
     # note: we rely on a property of hg: filerev is not reused for linear
     # history. i.e. it's impossible to have:
     #   changelog:  4----5----6 (linear, no merges)
     #   filelog:    1----2----1
     #                         ^ reuse filerev (impossible)
     # because parents are part of the hash. if that's not true, we need to
     # remove uniq and find a different way to identify fctxs.
     return uniq(fctxs), fctxmap
 
 
 class overlaystore(patch.filestore):
     """read-only, hybrid store based on a dict and ctx.
     memworkingcopy: {path: content}, overrides file contents.
     """
 
     def __init__(self, basectx, memworkingcopy):
         self.basectx = basectx
         self.memworkingcopy = memworkingcopy
 
     def getfile(self, path):
         """comply with mercurial.patch.filestore.getfile"""
         if path not in self.basectx:
             return None, None, None
         fctx = self.basectx[path]
         if path in self.memworkingcopy:
             content = self.memworkingcopy[path]
         else:
             content = fctx.data()
         mode = (fctx.islink(), fctx.isexec())
         copy = fctx.copysource()
         return content, mode, copy
 
 
 def overlaycontext(memworkingcopy, ctx, parents=None, extra=None):
     """({path: content}, ctx, (p1node, p2node)?, {}?) -> memctx
     memworkingcopy overrides file contents.
     """
     # parents must contain 2 items: (node1, node2)
     if parents is None:
         parents = ctx.repo().changelog.parents(ctx.node())
     if extra is None:
         extra = ctx.extra()
     date = ctx.date()
     desc = ctx.description()
     user = ctx.user()
     files = set(ctx.files()).union(memworkingcopy)
     store = overlaystore(ctx, memworkingcopy)
     return context.memctx(
         repo=ctx.repo(),
         parents=parents,
         text=desc,
         files=files,
         filectxfn=store,
         user=user,
         date=date,
         branch=None,
         extra=extra,
     )
 
 
 class filefixupstate(object):
     """state needed to apply fixups to a single file
 
     internally, it keeps file contents of several revisions and a linelog.
 
     the linelog uses odd revision numbers for original contents (fctxs passed
     to __init__), and even revision numbers for fixups, like:
 
         linelog rev 1: self.fctxs[0] (from an immutable "public" changeset)
         linelog rev 2: fixups made to self.fctxs[0]
         linelog rev 3: self.fctxs[1] (a child of fctxs[0])
         linelog rev 4: fixups made to self.fctxs[1]
         ...
 
     a typical use is like:
 
         1. call diffwith, to calculate self.fixups
         2. (optionally), present self.fixups to the user, or change it
         3. call apply, to apply changes
         4. read results from "finalcontents", or call getfinalcontent
     """
 
     def __init__(self, fctxs, path, ui=None, opts=None):
         """([fctx], ui or None) -> None
 
         fctxs should be linear, and sorted by topo order - oldest first.
         fctxs[0] will be considered as "immutable" and will not be changed.
         """
         self.fctxs = fctxs
         self.path = path
         self.ui = ui or nullui()
         self.opts = opts or {}
 
         # following fields are built from fctxs. they exist for perf reason
         self.contents = [f.data() for f in fctxs]
         self.contentlines = pycompat.maplist(mdiff.splitnewlines, self.contents)
         self.linelog = self._buildlinelog()
         if self.ui.debugflag:
             assert self._checkoutlinelog() == self.contents
 
         # following fields will be filled later
         self.chunkstats = [0, 0]  # [adopted, total : int]
         self.targetlines = []  # [str]
         self.fixups = []  # [(linelog rev, a1, a2, b1, b2)]
         self.finalcontents = []  # [str]
         self.ctxaffected = set()
 
     def diffwith(self, targetfctx, fm=None):
         """calculate fixups needed by examining the differences between
         self.fctxs[-1] and targetfctx, chunk by chunk.
 
         targetfctx is the target state we move towards. we may or may not be
         able to get there because not all modified chunks can be amended into
         a non-public fctx unambiguously.
 
         call this only once, before apply().
 
         update self.fixups, self.chunkstats, and self.targetlines.
         """
         a = self.contents[-1]
         alines = self.contentlines[-1]
         b = targetfctx.data()
         blines = mdiff.splitnewlines(b)
         self.targetlines = blines
 
         self.linelog.annotate(self.linelog.maxrev)
         annotated = self.linelog.annotateresult  # [(linelog rev, linenum)]
         assert len(annotated) == len(alines)
         # add a dummy end line to make insertion at the end easier
         if annotated:
             dummyendline = (annotated[-1][0], annotated[-1][1] + 1)
             annotated.append(dummyendline)
 
         # analyse diff blocks
         for chunk in self._alldiffchunks(a, b, alines, blines):
             newfixups = self._analysediffchunk(chunk, annotated)
             self.chunkstats[0] += bool(newfixups)  # 1 or 0
             self.chunkstats[1] += 1
             self.fixups += newfixups
             if fm is not None:
                 self._showchanges(fm, alines, blines, chunk, newfixups)
 
     def apply(self):
         """apply self.fixups. update self.linelog, self.finalcontents.
 
         call this only once, before getfinalcontent(), after diffwith().
         """
         # the following is unnecessary, as it's done by "diffwith":
         #   self.linelog.annotate(self.linelog.maxrev)
         for rev, a1, a2, b1, b2 in reversed(self.fixups):
             blines = self.targetlines[b1:b2]
             if self.ui.debugflag:
                 idx = (max(rev - 1, 0)) // 2
                 self.ui.write(
                     _(b'%s: chunk %d:%d -> %d lines\n')
                     % (node.short(self.fctxs[idx].node()), a1, a2, len(blines))
                 )
             self.linelog.replacelines(rev, a1, a2, b1, b2)
         if self.opts.get(b'edit_lines', False):
             self.finalcontents = self._checkoutlinelogwithedits()
         else:
             self.finalcontents = self._checkoutlinelog()
 
     def getfinalcontent(self, fctx):
         """(fctx) -> str. get modified file content for a given filecontext"""
         idx = self.fctxs.index(fctx)
         return self.finalcontents[idx]
 
     def _analysediffchunk(self, chunk, annotated):
         """analyse a different chunk and return new fixups found
 
         return [] if no lines from the chunk can be safely applied.
 
         the chunk (or lines) cannot be safely applied, if, for example:
           - the modified (deleted) lines belong to a public changeset
             (self.fctxs[0])
           - the chunk is a pure insertion and the adjacent lines (at most 2
             lines) belong to different non-public changesets, or do not belong
             to any non-public changesets.
           - the chunk is modifying lines from different changesets.
             in this case, if the number of lines deleted equals to the number
             of lines added, assume it's a simple 1:1 map (could be wrong).
             otherwise, give up.
           - the chunk is modifying lines from a single non-public changeset,
             but other revisions touch the area as well. i.e. the lines are
             not continuous as seen from the linelog.
         """
         a1, a2, b1, b2 = chunk
         # find involved indexes from annotate result
         involved = annotated[a1:a2]
         if not involved and annotated:  # a1 == a2 and a is not empty
             # pure insertion, check nearby lines. ignore lines belong
             # to the public (first) changeset (i.e. annotated[i][0] == 1)
             nearbylinenums = {a2, max(0, a1 - 1)}
             involved = [
                 annotated[i] for i in nearbylinenums if annotated[i][0] != 1
             ]
         involvedrevs = list(set(r for r, l in involved))
         newfixups = []
         if len(involvedrevs) == 1 and self._iscontinuous(a1, a2 - 1, True):
             # chunk belongs to a single revision
             rev = involvedrevs[0]
             if rev > 1:
                 fixuprev = rev + 1
                 newfixups.append((fixuprev, a1, a2, b1, b2))
         elif a2 - a1 == b2 - b1 or b1 == b2:
             # 1:1 line mapping, or chunk was deleted
             for i in pycompat.xrange(a1, a2):
                 rev, linenum = annotated[i]
                 if rev > 1:
                     if b1 == b2:  # deletion, simply remove that single line
                         nb1 = nb2 = 0
                     else:  # 1:1 line mapping, change the corresponding rev
                         nb1 = b1 + i - a1
                         nb2 = nb1 + 1
                     fixuprev = rev + 1
                     newfixups.append((fixuprev, i, i + 1, nb1, nb2))
         return self._optimizefixups(newfixups)
 
     @staticmethod
     def _alldiffchunks(a, b, alines, blines):
         """like mdiff.allblocks, but only care about differences"""
         blocks = mdiff.allblocks(a, b, lines1=alines, lines2=blines)
         for chunk, btype in blocks:
             if btype != b'!':
                 continue
             yield chunk
 
     def _buildlinelog(self):
         """calculate the initial linelog based on self.content{,line}s.
         this is similar to running a partial "annotate".
         """
         llog = linelog.linelog()
         a, alines = b'', []
         for i in pycompat.xrange(len(self.contents)):
             b, blines = self.contents[i], self.contentlines[i]
             llrev = i * 2 + 1
             chunks = self._alldiffchunks(a, b, alines, blines)
             for a1, a2, b1, b2 in reversed(list(chunks)):
                 llog.replacelines(llrev, a1, a2, b1, b2)
             a, alines = b, blines
         return llog
 
     def _checkoutlinelog(self):
         """() -> [str]. check out file contents from linelog"""
         contents = []
         for i in pycompat.xrange(len(self.contents)):
             rev = (i + 1) * 2
             self.linelog.annotate(rev)
             content = b''.join(map(self._getline, self.linelog.annotateresult))
             contents.append(content)
         return contents
 
     def _checkoutlinelogwithedits(self):
         """() -> [str]. prompt all lines for edit"""
         alllines = self.linelog.getalllines()
         # header
         editortext = (
             _(
                 b'HG: editing %s\nHG: "y" means the line to the right '
                 b'exists in the changeset to the top\nHG:\n'
             )
             % self.fctxs[-1].path()
         )
         # [(idx, fctx)]. hide the dummy emptyfilecontext
         visiblefctxs = [
             (i, f)
             for i, f in enumerate(self.fctxs)
             if not isinstance(f, emptyfilecontext)
         ]
         for i, (j, f) in enumerate(visiblefctxs):
             editortext += _(b'HG: %s/%s %s %s\n') % (
                 b'|' * i,
                 b'-' * (len(visiblefctxs) - i + 1),
                 node.short(f.node()),
                 f.description().split(b'\n', 1)[0],
             )
         editortext += _(b'HG: %s\n') % (b'|' * len(visiblefctxs))
         # figure out the lifetime of a line, this is relatively inefficient,
         # but probably fine
         lineset = defaultdict(lambda: set())  # {(llrev, linenum): {llrev}}
         for i, f in visiblefctxs:
             self.linelog.annotate((i + 1) * 2)
             for l in self.linelog.annotateresult:
                 lineset[l].add(i)
         # append lines
         for l in alllines:
             editortext += b'    %s : %s' % (
                 b''.join(
                     [
                         (b'y' if i in lineset[l] else b' ')
                         for i, _f in visiblefctxs
                     ]
                 ),
                 self._getline(l),
             )
         # run editor
         editedtext = self.ui.edit(editortext, b'', action=b'absorb')
         if not editedtext:
             raise error.Abort(_(b'empty editor text'))
         # parse edited result
         contents = [b'' for i in self.fctxs]
         leftpadpos = 4
         colonpos = leftpadpos + len(visiblefctxs) + 1
         for l in mdiff.splitnewlines(editedtext):
             if l.startswith(b'HG:'):
                 continue
             if l[colonpos - 1 : colonpos + 2] != b' : ':
                 raise error.Abort(_(b'malformed line: %s') % l)
             linecontent = l[colonpos + 2 :]
             for i, ch in enumerate(
                 pycompat.bytestr(l[leftpadpos : colonpos - 1])
             ):
                 if ch == b'y':
                     contents[visiblefctxs[i][0]] += linecontent
         # chunkstats is hard to calculate if anything changes, therefore
         # set them to just a simple value (1, 1).
         if editedtext != editortext:
             self.chunkstats = [1, 1]
         return contents
 
     def _getline(self, lineinfo):
         """((rev, linenum)) -> str. convert rev+line number to line content"""
         rev, linenum = lineinfo
         if rev & 1:  # odd: original line taken from fctxs
             return self.contentlines[rev // 2][linenum]
         else:  # even: fixup line from targetfctx
             return self.targetlines[linenum]
 
     def _iscontinuous(self, a1, a2, closedinterval=False):
         """(a1, a2 : int) -> bool
 
         check if these lines are continuous. i.e. no other insertions or
         deletions (from other revisions) among these lines.
 
         closedinterval decides whether a2 should be included or not. i.e. is
         it [a1, a2), or [a1, a2] ?
         """
         if a1 >= a2:
             return True
         llog = self.linelog
         offset1 = llog.getoffset(a1)
         offset2 = llog.getoffset(a2) + int(closedinterval)
         linesinbetween = llog.getalllines(offset1, offset2)
         return len(linesinbetween) == a2 - a1 + int(closedinterval)
 
     def _optimizefixups(self, fixups):
         """[(rev, a1, a2, b1, b2)] -> [(rev, a1, a2, b1, b2)].
         merge adjacent fixups to make them less fragmented.
         """
         result = []
         pcurrentchunk = [[-1, -1, -1, -1, -1]]
 
         def pushchunk():
             if pcurrentchunk[0][0] != -1:
                 result.append(tuple(pcurrentchunk[0]))
 
         for i, chunk in enumerate(fixups):
             rev, a1, a2, b1, b2 = chunk
             lastrev = pcurrentchunk[0][0]
             lasta2 = pcurrentchunk[0][2]
             lastb2 = pcurrentchunk[0][4]
             if (
                 a1 == lasta2
                 and b1 == lastb2
                 and rev == lastrev
                 and self._iscontinuous(max(a1 - 1, 0), a1)
             ):
                 # merge into currentchunk
                 pcurrentchunk[0][2] = a2
                 pcurrentchunk[0][4] = b2
             else:
                 pushchunk()
                 pcurrentchunk[0] = list(chunk)
         pushchunk()
         return result
 
     def _showchanges(self, fm, alines, blines, chunk, fixups):
         def trim(line):
             if line.endswith(b'\n'):
                 line = line[:-1]
             return line
 
         # this is not optimized for perf but _showchanges only gets executed
         # with an extra command-line flag.
         a1, a2, b1, b2 = chunk
         aidxs, bidxs = [0] * (a2 - a1), [0] * (b2 - b1)
         for idx, fa1, fa2, fb1, fb2 in fixups:
             for i in pycompat.xrange(fa1, fa2):
                 aidxs[i - a1] = (max(idx, 1) - 1) // 2
             for i in pycompat.xrange(fb1, fb2):
                 bidxs[i - b1] = (max(idx, 1) - 1) // 2
 
         fm.startitem()
         fm.write(
             b'hunk',
             b'        %s\n',
             b'@@ -%d,%d +%d,%d @@' % (a1, a2 - a1, b1, b2 - b1),
             label=b'diff.hunk',
         )
         fm.data(path=self.path, linetype=b'hunk')
 
         def writeline(idx, diffchar, line, linetype, linelabel):
             fm.startitem()
             node = b''
             if idx:
                 ctx = self.fctxs[idx]
                 fm.context(fctx=ctx)
                 node = ctx.hex()
                 self.ctxaffected.add(ctx.changectx())
             fm.write(b'node', b'%-7.7s ', node, label=b'absorb.node')
             fm.write(
                 b'diffchar ' + linetype,
                 b'%s%s\n',
                 diffchar,
                 line,
                 label=linelabel,
             )
             fm.data(path=self.path, linetype=linetype)
 
         for i in pycompat.xrange(a1, a2):
             writeline(
                 aidxs[i - a1],
                 b'-',
                 trim(alines[i]),
                 b'deleted',
                 b'diff.deleted',
             )
         for i in pycompat.xrange(b1, b2):
             writeline(
                 bidxs[i - b1],
                 b'+',
                 trim(blines[i]),
                 b'inserted',
                 b'diff.inserted',
             )
 
 
 class fixupstate(object):
     """state needed to run absorb
 
     internally, it keeps paths and filefixupstates.
 
     a typical use is like filefixupstates:
 
         1. call diffwith, to calculate fixups
         2. (optionally), present fixups to the user, or edit fixups
         3. call apply, to apply changes to memory
         4. call commit, to commit changes to hg database
     """
 
     def __init__(self, stack, ui=None, opts=None):
         """([ctx], ui or None) -> None
 
         stack: should be linear, and sorted by topo order - oldest first.
         all commits in stack are considered mutable.
         """
         assert stack
         self.ui = ui or nullui()
         self.opts = opts or {}
         self.stack = stack
         self.repo = stack[-1].repo().unfiltered()
 
         # following fields will be filled later
         self.paths = []  # [str]
         self.status = None  # ctx.status output
         self.fctxmap = {}  # {path: {ctx: fctx}}
         self.fixupmap = {}  # {path: filefixupstate}
         self.replacemap = {}  # {oldnode: newnode or None}
         self.finalnode = None  # head after all fixups
         self.ctxaffected = set()  # ctx that will be absorbed into
 
     def diffwith(self, targetctx, match=None, fm=None):
         """diff and prepare fixups. update self.fixupmap, self.paths"""
         # only care about modified files
         self.status = self.stack[-1].status(targetctx, match)
         self.paths = []
         # but if --edit-lines is used, the user may want to edit files
         # even if they are not modified
         editopt = self.opts.get(b'edit_lines')
         if not self.status.modified and editopt and match:
             interestingpaths = match.files()
         else:
             interestingpaths = self.status.modified
         # prepare the filefixupstate
         seenfctxs = set()
         # sorting is necessary to eliminate ambiguity for the "double move"
         # case: "hg cp A B; hg cp A C; hg rm A", then only "B" can affect "A".
         for path in sorted(interestingpaths):
             self.ui.debug(b'calculating fixups for %s\n' % path)
             targetfctx = targetctx[path]
             fctxs, ctx2fctx = getfilestack(self.stack, path, seenfctxs)
             # ignore symbolic links or binary, or unchanged files
             if any(
                 f.islink() or stringutil.binary(f.data())
                 for f in [targetfctx] + fctxs
                 if not isinstance(f, emptyfilecontext)
             ):
                 continue
             if targetfctx.data() == fctxs[-1].data() and not editopt:
                 continue
             seenfctxs.update(fctxs[1:])
             self.fctxmap[path] = ctx2fctx
             fstate = filefixupstate(fctxs, path, ui=self.ui, opts=self.opts)
             if fm is not None:
                 fm.startitem()
                 fm.plain(b'showing changes for ')
                 fm.write(b'path', b'%s\n', path, label=b'absorb.path')
                 fm.data(linetype=b'path')
             fstate.diffwith(targetfctx, fm)
             self.fixupmap[path] = fstate
             self.paths.append(path)
             self.ctxaffected.update(fstate.ctxaffected)
 
     def apply(self):
         """apply fixups to individual filefixupstates"""
         for path, state in pycompat.iteritems(self.fixupmap):
             if self.ui.debugflag:
                 self.ui.write(_(b'applying fixups to %s\n') % path)
             state.apply()
 
     @property
     def chunkstats(self):
         """-> {path: chunkstats}. collect chunkstats from filefixupstates"""
         return dict(
             (path, state.chunkstats)
             for path, state in pycompat.iteritems(self.fixupmap)
         )
 
     def commit(self):
         """commit changes. update self.finalnode, self.replacemap"""
         with self.repo.transaction(b'absorb') as tr:
             self._commitstack()
             self._movebookmarks(tr)
             if self.repo[b'.'].node() in self.replacemap:
                 self._moveworkingdirectoryparent()
             self._cleanupoldcommits()
         return self.finalnode
 
     def printchunkstats(self):
         """print things like '1 of 2 chunk(s) applied'"""
         ui = self.ui
         chunkstats = self.chunkstats
         if ui.verbose:
             # chunkstats for each file
             for path, stat in pycompat.iteritems(chunkstats):
                 if stat[0]:
                     ui.write(
                         _(b'%s: %d of %d chunk(s) applied\n')
                         % (path, stat[0], stat[1])
                     )
         elif not ui.quiet:
             # a summary for all files
             stats = chunkstats.values()
             applied, total = (sum(s[i] for s in stats) for i in (0, 1))
             ui.write(_(b'%d of %d chunk(s) applied\n') % (applied, total))
 
     def _commitstack(self):
         """make new commits. update self.finalnode, self.replacemap.
         it is splitted from "commit" to avoid too much indentation.
         """
         # last node (20-char) committed by us
         lastcommitted = None
         # p1 which overrides the parent of the next commit, "None" means use
         # the original parent unchanged
         nextp1 = None
         for ctx in self.stack:
             memworkingcopy = self._getnewfilecontents(ctx)
             if not memworkingcopy and not lastcommitted:
                 # nothing changed, nothing commited
                 nextp1 = ctx
                 continue
             if self._willbecomenoop(memworkingcopy, ctx, nextp1):
                 # changeset is no longer necessary
                 self.replacemap[ctx.node()] = None
                 msg = _(b'became empty and was dropped')
             else:
                 # changeset needs re-commit
                 nodestr = self._commitsingle(memworkingcopy, ctx, p1=nextp1)
                 lastcommitted = self.repo[nodestr]
                 nextp1 = lastcommitted
                 self.replacemap[ctx.node()] = lastcommitted.node()
                 if memworkingcopy:
                     msg = _(b'%d file(s) changed, became %s') % (
                         len(memworkingcopy),
                         self._ctx2str(lastcommitted),
                     )
                 else:
                     msg = _(b'became %s') % self._ctx2str(lastcommitted)
             if self.ui.verbose and msg:
                 self.ui.write(_(b'%s: %s\n') % (self._ctx2str(ctx), msg))
         self.finalnode = lastcommitted and lastcommitted.node()
 
     def _ctx2str(self, ctx):
         if self.ui.debugflag:
             return b'%d:%s' % (ctx.rev(), ctx.hex())
         else:
             return b'%d:%s' % (ctx.rev(), node.short(ctx.node()))
 
     def _getnewfilecontents(self, ctx):
         """(ctx) -> {path: str}
 
         fetch file contents from filefixupstates.
         return the working copy overrides - files different from ctx.
         """
         result = {}
         for path in self.paths:
             ctx2fctx = self.fctxmap[path]  # {ctx: fctx}
             if ctx not in ctx2fctx:
                 continue
             fctx = ctx2fctx[ctx]
             content = fctx.data()
             newcontent = self.fixupmap[path].getfinalcontent(fctx)
             if content != newcontent:
                 result[fctx.path()] = newcontent
         return result
 
     def _movebookmarks(self, tr):
         repo = self.repo
         needupdate = [
             (name, self.replacemap[hsh])
             for name, hsh in pycompat.iteritems(repo._bookmarks)
             if hsh in self.replacemap
         ]
         changes = []
         for name, hsh in needupdate:
             if hsh:
                 changes.append((name, hsh))
                 if self.ui.verbose:
                     self.ui.write(
                         _(b'moving bookmark %s to %s\n') % (name, node.hex(hsh))
                     )
             else:
                 changes.append((name, None))
                 if self.ui.verbose:
                     self.ui.write(_(b'deleting bookmark %s\n') % name)
         repo._bookmarks.applychanges(repo, tr, changes)
 
     def _moveworkingdirectoryparent(self):
         if not self.finalnode:
             # Find the latest not-{obsoleted,stripped} parent.
             revs = self.repo.revs(b'max(::. - %ln)', self.replacemap.keys())
             ctx = self.repo[revs.first()]
             self.finalnode = ctx.node()
         else:
             ctx = self.repo[self.finalnode]
 
         dirstate = self.repo.dirstate
         # dirstate.rebuild invalidates fsmonitorstate, causing "hg status" to
         # be slow. in absorb's case, no need to invalidate fsmonitorstate.
         noop = lambda: 0
         restore = noop
-        if util.safehasattr(dirstate, b'_fsmonitorstate'):
+        if util.safehasattr(dirstate, '_fsmonitorstate'):
             bak = dirstate._fsmonitorstate.invalidate
 
             def restore():
                 dirstate._fsmonitorstate.invalidate = bak
 
             dirstate._fsmonitorstate.invalidate = noop
         try:
             with dirstate.parentchange():
                 dirstate.rebuild(ctx.node(), ctx.manifest(), self.paths)
         finally:
             restore()
 
     @staticmethod
     def _willbecomenoop(memworkingcopy, ctx, pctx=None):
         """({path: content}, ctx, ctx) -> bool. test if a commit will be noop
 
         if it will become an empty commit (does not change anything, after the
         memworkingcopy overrides), return True. otherwise return False.
         """
         if not pctx:
             parents = ctx.parents()
             if len(parents) != 1:
                 return False
             pctx = parents[0]
         # ctx changes more files (not a subset of memworkingcopy)
         if not set(ctx.files()).issubset(set(memworkingcopy)):
             return False
         for path, content in pycompat.iteritems(memworkingcopy):
             if path not in pctx or path not in ctx:
                 return False
             fctx = ctx[path]
             pfctx = pctx[path]
             if pfctx.flags() != fctx.flags():
                 return False
             if pfctx.data() != content:
                 return False
         return True
 
     def _commitsingle(self, memworkingcopy, ctx, p1=None):
         """(ctx, {path: content}, node) -> node. make a single commit
 
         the commit is a clone from ctx, with a (optionally) different p1, and
         different file contents replaced by memworkingcopy.
         """
         parents = p1 and (p1, node.nullid)
         extra = ctx.extra()
         if self._useobsolete and self.ui.configbool(b'absorb', b'add-noise'):
             extra[b'absorb_source'] = ctx.hex()
         mctx = overlaycontext(memworkingcopy, ctx, parents, extra=extra)
         return mctx.commit()
 
     @util.propertycache
     def _useobsolete(self):
         """() -> bool"""
         return obsolete.isenabled(self.repo, obsolete.createmarkersopt)
 
     def _cleanupoldcommits(self):
         replacements = {
             k: ([v] if v is not None else [])
             for k, v in pycompat.iteritems(self.replacemap)
         }
         if replacements:
             scmutil.cleanupnodes(
                 self.repo, replacements, operation=b'absorb', fixphase=True
             )
 
 
 def _parsechunk(hunk):
     """(crecord.uihunk or patch.recordhunk) -> (path, (a1, a2, [bline]))"""
     if type(hunk) not in (crecord.uihunk, patch.recordhunk):
         return None, None
     path = hunk.header.filename()
     a1 = hunk.fromline + len(hunk.before) - 1
     # remove before and after context
     hunk.before = hunk.after = []
     buf = util.stringio()
     hunk.write(buf)
     patchlines = mdiff.splitnewlines(buf.getvalue())
     # hunk.prettystr() will update hunk.removed
     a2 = a1 + hunk.removed
     blines = [l[1:] for l in patchlines[1:] if not l.startswith(b'-')]
     return path, (a1, a2, blines)
 
 
 def overlaydiffcontext(ctx, chunks):
     """(ctx, [crecord.uihunk]) -> memctx
 
     return a memctx with some [1] patches (chunks) applied to ctx.
     [1]: modifications are handled. renames, mode changes, etc. are ignored.
     """
     # sadly the applying-patch logic is hardly reusable, and messy:
     # 1. the core logic "_applydiff" is too heavy - it writes .rej files, it
     #    needs a file stream of a patch and will re-parse it, while we have
     #    structured hunk objects at hand.
     # 2. a lot of different implementations about "chunk" (patch.hunk,
     #    patch.recordhunk, crecord.uihunk)
     # as we only care about applying changes to modified files, no mode
     # change, no binary diff, and no renames, it's probably okay to
     # re-invent the logic using much simpler code here.
     memworkingcopy = {}  # {path: content}
     patchmap = defaultdict(lambda: [])  # {path: [(a1, a2, [bline])]}
     for path, info in map(_parsechunk, chunks):
         if not path or not info:
             continue
         patchmap[path].append(info)
     for path, patches in pycompat.iteritems(patchmap):
         if path not in ctx or not patches:
             continue
         patches.sort(reverse=True)
         lines = mdiff.splitnewlines(ctx[path].data())
         for a1, a2, blines in patches:
             lines[a1:a2] = blines
         memworkingcopy[path] = b''.join(lines)
     return overlaycontext(memworkingcopy, ctx)
 
 
 def absorb(ui, repo, stack=None, targetctx=None, pats=None, opts=None):
     """pick fixup chunks from targetctx, apply them to stack.
 
     if targetctx is None, the working copy context will be used.
     if stack is None, the current draft stack will be used.
     return fixupstate.
     """
     if stack is None:
         limit = ui.configint(b'absorb', b'max-stack-size')
         headctx = repo[b'.']
         if len(headctx.parents()) > 1:
             raise error.Abort(_(b'cannot absorb into a merge'))
         stack = getdraftstack(headctx, limit)
         if limit and len(stack) >= limit:
             ui.warn(
                 _(
                     b'absorb: only the recent %d changesets will '
                     b'be analysed\n'
                 )
                 % limit
             )
     if not stack:
         raise error.Abort(_(b'no mutable changeset to change'))
     if targetctx is None:  # default to working copy
         targetctx = repo[None]
     if pats is None:
         pats = ()
     if opts is None:
         opts = {}
     state = fixupstate(stack, ui=ui, opts=opts)
     matcher = scmutil.match(targetctx, pats, opts)
     if opts.get(b'interactive'):
         diff = patch.diff(repo, stack[-1].node(), targetctx.node(), matcher)
         origchunks = patch.parsepatch(diff)
         chunks = cmdutil.recordfilter(ui, origchunks, matcher)[0]
         targetctx = overlaydiffcontext(stack[-1], chunks)
     fm = None
     if opts.get(b'print_changes') or not opts.get(b'apply_changes'):
         fm = ui.formatter(b'absorb', opts)
     state.diffwith(targetctx, matcher, fm)
     if fm is not None:
         fm.startitem()
         fm.write(
             b"count", b"\n%d changesets affected\n", len(state.ctxaffected)
         )
         fm.data(linetype=b'summary')
         for ctx in reversed(stack):
             if ctx not in state.ctxaffected:
                 continue
             fm.startitem()
             fm.context(ctx=ctx)
             fm.data(linetype=b'changeset')
             fm.write(b'node', b'%-7.7s ', ctx.hex(), label=b'absorb.node')
             descfirstline = ctx.description().splitlines()[0]
             fm.write(
                 b'descfirstline',
                 b'%s\n',
                 descfirstline,
                 label=b'absorb.description',
             )
         fm.end()
     if not opts.get(b'dry_run'):
         if (
             not opts.get(b'apply_changes')
             and state.ctxaffected
             and ui.promptchoice(
                 b"apply changes (yn)? $$ &Yes $$ &No", default=1
             )
         ):
             raise error.Abort(_(b'absorb cancelled\n'))
 
         state.apply()
         if state.commit():
             state.printchunkstats()
         elif not ui.quiet:
             ui.write(_(b'nothing applied\n'))
     return state
 
 
 @command(
     b'absorb',
     [
         (
             b'a',
             b'apply-changes',
             None,
             _(b'apply changes without prompting for confirmation'),
         ),
         (
             b'p',
             b'print-changes',
             None,
             _(b'always print which changesets are modified by which changes'),
         ),
         (
             b'i',
             b'interactive',
             None,
             _(b'interactively select which chunks to apply (EXPERIMENTAL)'),
         ),
         (
             b'e',
             b'edit-lines',
             None,
             _(
                 b'edit what lines belong to which changesets before commit '
                 b'(EXPERIMENTAL)'
             ),
         ),
     ]
     + commands.dryrunopts
     + commands.templateopts
     + commands.walkopts,
     _(b'hg absorb [OPTION] [FILE]...'),
     helpcategory=command.CATEGORY_COMMITTING,
     helpbasic=True,
 )
 def absorbcmd(ui, repo, *pats, **opts):
     """incorporate corrections into the stack of draft changesets
 
     absorb analyzes each change in your working directory and attempts to
     amend the changed lines into the changesets in your stack that first
     introduced those lines.
 
     If absorb cannot find an unambiguous changeset to amend for a change,
     that change will be left in the working directory, untouched. They can be
     observed by :hg:`status` or :hg:`diff` afterwards. In other words,
     absorb does not write to the working directory.
 
     Changesets outside the revset `::. and not public() and not merge()` will
     not be changed.
 
     Changesets that become empty after applying the changes will be deleted.
 
     By default, absorb will show what it plans to do and prompt for
     confirmation.  If you are confident that the changes will be absorbed
     to the correct place, run :hg:`absorb -a` to apply the changes
     immediately.
 
     Returns 0 on success, 1 if all chunks were ignored and nothing amended.
     """
     opts = pycompat.byteskwargs(opts)
 
     with repo.wlock(), repo.lock():
         if not opts[b'dry_run']:
             cmdutil.checkunfinished(repo)
 
         state = absorb(ui, repo, pats=pats, opts=opts)
         if sum(s[0] for s in state.chunkstats.values()) == 0:
             return 1

hgext/bugzilla.py

@@ -1,1215 +1,1215 b''
 # bugzilla.py - bugzilla integration for mercurial
 #
 # Copyright 2006 Vadim Gelfer <[e-mail]>
 # Copyright 2011-4 Jim Hague <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''hooks for integrating with the Bugzilla bug tracker
 
 This hook extension adds comments on bugs in Bugzilla when changesets
 that refer to bugs by Bugzilla ID are seen. The comment is formatted using
 the Mercurial template mechanism.
 
 The bug references can optionally include an update for Bugzilla of the
 hours spent working on the bug. Bugs can also be marked fixed.
 
 Four basic modes of access to Bugzilla are provided:
 
 1. Access via the Bugzilla REST-API. Requires bugzilla 5.0 or later.
 
 2. Access via the Bugzilla XMLRPC interface. Requires Bugzilla 3.4 or later.
 
 3. Check data via the Bugzilla XMLRPC interface and submit bug change
    via email to Bugzilla email interface. Requires Bugzilla 3.4 or later.
 
 4. Writing directly to the Bugzilla database. Only Bugzilla installations
    using MySQL are supported. Requires Python MySQLdb.
 
 Writing directly to the database is susceptible to schema changes, and
 relies on a Bugzilla contrib script to send out bug change
 notification emails. This script runs as the user running Mercurial,
 must be run on the host with the Bugzilla install, and requires
 permission to read Bugzilla configuration details and the necessary
 MySQL user and password to have full access rights to the Bugzilla
 database. For these reasons this access mode is now considered
 deprecated, and will not be updated for new Bugzilla versions going
 forward. Only adding comments is supported in this access mode.
 
 Access via XMLRPC needs a Bugzilla username and password to be specified
 in the configuration. Comments are added under that username. Since the
 configuration must be readable by all Mercurial users, it is recommended
 that the rights of that user are restricted in Bugzilla to the minimum
 necessary to add comments. Marking bugs fixed requires Bugzilla 4.0 and later.
 
 Access via XMLRPC/email uses XMLRPC to query Bugzilla, but sends
 email to the Bugzilla email interface to submit comments to bugs.
 The From: address in the email is set to the email address of the Mercurial
 user, so the comment appears to come from the Mercurial user. In the event
 that the Mercurial user email is not recognized by Bugzilla as a Bugzilla
 user, the email associated with the Bugzilla username used to log into
 Bugzilla is used instead as the source of the comment. Marking bugs fixed
 works on all supported Bugzilla versions.
 
 Access via the REST-API needs either a Bugzilla username and password
 or an apikey specified in the configuration. Comments are made under
 the given username or the user associated with the apikey in Bugzilla.
 
 Configuration items common to all access modes:
 
 bugzilla.version
   The access type to use. Values recognized are:
 
   :``restapi``:      Bugzilla REST-API, Bugzilla 5.0 and later.
   :``xmlrpc``:       Bugzilla XMLRPC interface.
   :``xmlrpc+email``: Bugzilla XMLRPC and email interfaces.
   :``3.0``:          MySQL access, Bugzilla 3.0 and later.
   :``2.18``:         MySQL access, Bugzilla 2.18 and up to but not
                      including 3.0.
   :``2.16``:         MySQL access, Bugzilla 2.16 and up to but not
                      including 2.18.
 
 bugzilla.regexp
   Regular expression to match bug IDs for update in changeset commit message.
   It must contain one "()" named group ``<ids>`` containing the bug
   IDs separated by non-digit characters. It may also contain
   a named group ``<hours>`` with a floating-point number giving the
   hours worked on the bug. If no named groups are present, the first
   "()" group is assumed to contain the bug IDs, and work time is not
   updated. The default expression matches ``Bug 1234``, ``Bug no. 1234``,
   ``Bug number 1234``, ``Bugs 1234,5678``, ``Bug 1234 and 5678`` and
   variations thereof, followed by an hours number prefixed by ``h`` or
   ``hours``, e.g. ``hours 1.5``. Matching is case insensitive.
 
 bugzilla.fixregexp
   Regular expression to match bug IDs for marking fixed in changeset
   commit message. This must contain a "()" named group ``<ids>` containing
   the bug IDs separated by non-digit characters. It may also contain
   a named group ``<hours>`` with a floating-point number giving the
   hours worked on the bug. If no named groups are present, the first
   "()" group is assumed to contain the bug IDs, and work time is not
   updated. The default expression matches ``Fixes 1234``, ``Fixes bug 1234``,
   ``Fixes bugs 1234,5678``, ``Fixes 1234 and 5678`` and
   variations thereof, followed by an hours number prefixed by ``h`` or
   ``hours``, e.g. ``hours 1.5``. Matching is case insensitive.
 
 bugzilla.fixstatus
   The status to set a bug to when marking fixed. Default ``RESOLVED``.
 
 bugzilla.fixresolution
   The resolution to set a bug to when marking fixed. Default ``FIXED``.
 
 bugzilla.style
   The style file to use when formatting comments.
 
 bugzilla.template
   Template to use when formatting comments. Overrides style if
   specified. In addition to the usual Mercurial keywords, the
   extension specifies:
 
   :``{bug}``:     The Bugzilla bug ID.
   :``{root}``:    The full pathname of the Mercurial repository.
   :``{webroot}``: Stripped pathname of the Mercurial repository.
   :``{hgweb}``:   Base URL for browsing Mercurial repositories.
 
   Default ``changeset {node|short} in repo {root} refers to bug
   {bug}.\\ndetails:\\n\\t{desc|tabindent}``
 
 bugzilla.strip
   The number of path separator characters to strip from the front of
   the Mercurial repository path (``{root}`` in templates) to produce
   ``{webroot}``. For example, a repository with ``{root}``
   ``/var/local/my-project`` with a strip of 2 gives a value for
   ``{webroot}`` of ``my-project``. Default 0.
 
 web.baseurl
   Base URL for browsing Mercurial repositories. Referenced from
   templates as ``{hgweb}``.
 
 Configuration items common to XMLRPC+email and MySQL access modes:
 
 bugzilla.usermap
   Path of file containing Mercurial committer email to Bugzilla user email
   mappings. If specified, the file should contain one mapping per
   line::
 
     committer = Bugzilla user
 
   See also the ``[usermap]`` section.
 
 The ``[usermap]`` section is used to specify mappings of Mercurial
 committer email to Bugzilla user email. See also ``bugzilla.usermap``.
 Contains entries of the form ``committer = Bugzilla user``.
 
 XMLRPC and REST-API access mode configuration:
 
 bugzilla.bzurl
   The base URL for the Bugzilla installation.
   Default ``http://localhost/bugzilla``.
 
 bugzilla.user
   The username to use to log into Bugzilla via XMLRPC. Default
   ``bugs``.
 
 bugzilla.password
   The password for Bugzilla login.
 
 REST-API access mode uses the options listed above as well as:
 
 bugzilla.apikey
   An apikey generated on the Bugzilla instance for api access.
   Using an apikey removes the need to store the user and password
   options.
 
 XMLRPC+email access mode uses the XMLRPC access mode configuration items,
 and also:
 
 bugzilla.bzemail
   The Bugzilla email address.
 
 In addition, the Mercurial email settings must be configured. See the
 documentation in hgrc(5), sections ``[email]`` and ``[smtp]``.
 
 MySQL access mode configuration:
 
 bugzilla.host
   Hostname of the MySQL server holding the Bugzilla database.
   Default ``localhost``.
 
 bugzilla.db
   Name of the Bugzilla database in MySQL. Default ``bugs``.
 
 bugzilla.user
   Username to use to access MySQL server. Default ``bugs``.
 
 bugzilla.password
   Password to use to access MySQL server.
 
 bugzilla.timeout
   Database connection timeout (seconds). Default 5.
 
 bugzilla.bzuser
   Fallback Bugzilla user name to record comments with, if changeset
   committer cannot be found as a Bugzilla user.
 
 bugzilla.bzdir
    Bugzilla install directory. Used by default notify. Default
    ``/var/www/html/bugzilla``.
 
 bugzilla.notify
   The command to run to get Bugzilla to send bug change notification
   emails. Substitutes from a map with 3 keys, ``bzdir``, ``id`` (bug
   id) and ``user`` (committer bugzilla email). Default depends on
   version; from 2.18 it is "cd %(bzdir)s && perl -T
   contrib/sendbugmail.pl %(id)s %(user)s".
 
 Activating the extension::
 
     [extensions]
     bugzilla =
 
     [hooks]
     # run bugzilla hook on every change pulled or pushed in here
     incoming.bugzilla = python:hgext.bugzilla.hook
 
 Example configurations:
 
 XMLRPC example configuration. This uses the Bugzilla at
 ``http://my-project.org/bugzilla``, logging in as user
 ``[e-mail]`` with password ``plugh``. It is used with a
 collection of Mercurial repositories in ``/var/local/hg/repos/``,
 with a web interface at ``http://my-project.org/hg``. ::
 
     [bugzilla]
     bzurl=http://my-project.org/bugzilla
     user=[e-mail]
     password=plugh
     version=xmlrpc
     template=Changeset {node|short} in {root|basename}.
              {hgweb}/{webroot}/rev/{node|short}\\n
              {desc}\\n
     strip=5
 
     [web]
     baseurl=http://my-project.org/hg
 
 XMLRPC+email example configuration. This uses the Bugzilla at
 ``http://my-project.org/bugzilla``, logging in as user
 ``[e-mail]`` with password ``plugh``. It is used with a
 collection of Mercurial repositories in ``/var/local/hg/repos/``,
 with a web interface at ``http://my-project.org/hg``. Bug comments
 are sent to the Bugzilla email address
 ``[e-mail]``. ::
 
     [bugzilla]
     bzurl=http://my-project.org/bugzilla
     user=[e-mail]
     password=plugh
     version=xmlrpc+email
     bzemail=[e-mail]
     template=Changeset {node|short} in {root|basename}.
              {hgweb}/{webroot}/rev/{node|short}\\n
              {desc}\\n
     strip=5
 
     [web]
     baseurl=http://my-project.org/hg
 
     [usermap]
     [e-mail]=[e-mail]
 
 MySQL example configuration. This has a local Bugzilla 3.2 installation
 in ``/opt/bugzilla-3.2``. The MySQL database is on ``localhost``,
 the Bugzilla database name is ``bugs`` and MySQL is
 accessed with MySQL username ``bugs`` password ``XYZZY``. It is used
 with a collection of Mercurial repositories in ``/var/local/hg/repos/``,
 with a web interface at ``http://my-project.org/hg``. ::
 
     [bugzilla]
     host=localhost
     password=XYZZY
     version=3.0
     bzuser=[e-mail]
     bzdir=/opt/bugzilla-3.2
     template=Changeset {node|short} in {root|basename}.
              {hgweb}/{webroot}/rev/{node|short}\\n
              {desc}\\n
     strip=5
 
     [web]
     baseurl=http://my-project.org/hg
 
     [usermap]
     [e-mail]=[e-mail]
 
 All the above add a comment to the Bugzilla bug record of the form::
 
     Changeset 3b16791d6642 in repository-name.
     http://my-project.org/hg/repository-name/rev/3b16791d6642
 
     Changeset commit comment. Bug 1234.
 '''
 
 from __future__ import absolute_import
 
 import json
 import re
 import time
 
 from mercurial.i18n import _
 from mercurial.node import short
 from mercurial import (
     error,
     logcmdutil,
     mail,
     pycompat,
     registrar,
     url,
     util,
 )
 from mercurial.utils import (
     procutil,
     stringutil,
 )
 
 xmlrpclib = util.xmlrpclib
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = b'ships-with-hg-core'
 
 configtable = {}
 configitem = registrar.configitem(configtable)
 
 configitem(
     b'bugzilla', b'apikey', default=b'',
 )
 configitem(
     b'bugzilla', b'bzdir', default=b'/var/www/html/bugzilla',
 )
 configitem(
     b'bugzilla', b'bzemail', default=None,
 )
 configitem(
     b'bugzilla', b'bzurl', default=b'http://localhost/bugzilla/',
 )
 configitem(
     b'bugzilla', b'bzuser', default=None,
 )
 configitem(
     b'bugzilla', b'db', default=b'bugs',
 )
 configitem(
     b'bugzilla',
     b'fixregexp',
     default=(
         br'fix(?:es)?\s*(?:bugs?\s*)?,?\s*'
         br'(?:nos?\.?|num(?:ber)?s?)?\s*'
         br'(?P<ids>(?:#?\d+\s*(?:,?\s*(?:and)?)?\s*)+)'
         br'\.?\s*(?:h(?:ours?)?\s*(?P<hours>\d*(?:\.\d+)?))?'
     ),
 )
 configitem(
     b'bugzilla', b'fixresolution', default=b'FIXED',
 )
 configitem(
     b'bugzilla', b'fixstatus', default=b'RESOLVED',
 )
 configitem(
     b'bugzilla', b'host', default=b'localhost',
 )
 configitem(
     b'bugzilla', b'notify', default=configitem.dynamicdefault,
 )
 configitem(
     b'bugzilla', b'password', default=None,
 )
 configitem(
     b'bugzilla',
     b'regexp',
     default=(
         br'bugs?\s*,?\s*(?:#|nos?\.?|num(?:ber)?s?)?\s*'
         br'(?P<ids>(?:\d+\s*(?:,?\s*(?:and)?)?\s*)+)'
         br'\.?\s*(?:h(?:ours?)?\s*(?P<hours>\d*(?:\.\d+)?))?'
     ),
 )
 configitem(
     b'bugzilla', b'strip', default=0,
 )
 configitem(
     b'bugzilla', b'style', default=None,
 )
 configitem(
     b'bugzilla', b'template', default=None,
 )
 configitem(
     b'bugzilla', b'timeout', default=5,
 )
 configitem(
     b'bugzilla', b'user', default=b'bugs',
 )
 configitem(
     b'bugzilla', b'usermap', default=None,
 )
 configitem(
     b'bugzilla', b'version', default=None,
 )
 
 
 class bzaccess(object):
     '''Base class for access to Bugzilla.'''
 
     def __init__(self, ui):
         self.ui = ui
         usermap = self.ui.config(b'bugzilla', b'usermap')
         if usermap:
             self.ui.readconfig(usermap, sections=[b'usermap'])
 
     def map_committer(self, user):
         '''map name of committer to Bugzilla user name.'''
         for committer, bzuser in self.ui.configitems(b'usermap'):
             if committer.lower() == user.lower():
                 return bzuser
         return user
 
     # Methods to be implemented by access classes.
     #
     # 'bugs' is a dict keyed on bug id, where values are a dict holding
     # updates to bug state. Recognized dict keys are:
     #
     # 'hours': Value, float containing work hours to be updated.
     # 'fix':   If key present, bug is to be marked fixed. Value ignored.
 
     def filter_real_bug_ids(self, bugs):
         '''remove bug IDs that do not exist in Bugzilla from bugs.'''
 
     def filter_cset_known_bug_ids(self, node, bugs):
         '''remove bug IDs where node occurs in comment text from bugs.'''
 
     def updatebug(self, bugid, newstate, text, committer):
         '''update the specified bug. Add comment text and set new states.
 
         If possible add the comment as being from the committer of
         the changeset. Otherwise use the default Bugzilla user.
         '''
 
     def notify(self, bugs, committer):
         '''Force sending of Bugzilla notification emails.
 
         Only required if the access method does not trigger notification
         emails automatically.
         '''
 
 
 # Bugzilla via direct access to MySQL database.
 class bzmysql(bzaccess):
     '''Support for direct MySQL access to Bugzilla.
 
     The earliest Bugzilla version this is tested with is version 2.16.
 
     If your Bugzilla is version 3.4 or above, you are strongly
     recommended to use the XMLRPC access method instead.
     '''
 
     @staticmethod
     def sql_buglist(ids):
         '''return SQL-friendly list of bug ids'''
         return b'(' + b','.join(map(str, ids)) + b')'
 
     _MySQLdb = None
 
     def __init__(self, ui):
         try:
             import MySQLdb as mysql
 
             bzmysql._MySQLdb = mysql
         except ImportError as err:
             raise error.Abort(
                 _(b'python mysql support not available: %s') % err
             )
 
         bzaccess.__init__(self, ui)
 
         host = self.ui.config(b'bugzilla', b'host')
         user = self.ui.config(b'bugzilla', b'user')
         passwd = self.ui.config(b'bugzilla', b'password')
         db = self.ui.config(b'bugzilla', b'db')
         timeout = int(self.ui.config(b'bugzilla', b'timeout'))
         self.ui.note(
             _(b'connecting to %s:%s as %s, password %s\n')
             % (host, db, user, b'*' * len(passwd))
         )
         self.conn = bzmysql._MySQLdb.connect(
             host=host, user=user, passwd=passwd, db=db, connect_timeout=timeout
         )
         self.cursor = self.conn.cursor()
         self.longdesc_id = self.get_longdesc_id()
         self.user_ids = {}
         self.default_notify = b"cd %(bzdir)s && ./processmail %(id)s %(user)s"
 
     def run(self, *args, **kwargs):
         '''run a query.'''
         self.ui.note(_(b'query: %s %s\n') % (args, kwargs))
         try:
             self.cursor.execute(*args, **kwargs)
         except bzmysql._MySQLdb.MySQLError:
             self.ui.note(_(b'failed query: %s %s\n') % (args, kwargs))
             raise
 
     def get_longdesc_id(self):
         '''get identity of longdesc field'''
         self.run(b'select fieldid from fielddefs where name = "longdesc"')
         ids = self.cursor.fetchall()
         if len(ids) != 1:
             raise error.Abort(_(b'unknown database schema'))
         return ids[0][0]
 
     def filter_real_bug_ids(self, bugs):
         '''filter not-existing bugs from set.'''
         self.run(
             b'select bug_id from bugs where bug_id in %s'
             % bzmysql.sql_buglist(bugs.keys())
         )
         existing = [id for (id,) in self.cursor.fetchall()]
         for id in bugs.keys():
             if id not in existing:
                 self.ui.status(_(b'bug %d does not exist\n') % id)
                 del bugs[id]
 
     def filter_cset_known_bug_ids(self, node, bugs):
         '''filter bug ids that already refer to this changeset from set.'''
         self.run(
             '''select bug_id from longdescs where
                     bug_id in %s and thetext like "%%%s%%"'''
             % (bzmysql.sql_buglist(bugs.keys()), short(node))
         )
         for (id,) in self.cursor.fetchall():
             self.ui.status(
                 _(b'bug %d already knows about changeset %s\n')
                 % (id, short(node))
             )
             del bugs[id]
 
     def notify(self, bugs, committer):
         '''tell bugzilla to send mail.'''
         self.ui.status(_(b'telling bugzilla to send mail:\n'))
         (user, userid) = self.get_bugzilla_user(committer)
         for id in bugs.keys():
             self.ui.status(_(b'  bug %s\n') % id)
             cmdfmt = self.ui.config(b'bugzilla', b'notify', self.default_notify)
             bzdir = self.ui.config(b'bugzilla', b'bzdir')
             try:
                 # Backwards-compatible with old notify string, which
                 # took one string. This will throw with a new format
                 # string.
                 cmd = cmdfmt % id
             except TypeError:
                 cmd = cmdfmt % {b'bzdir': bzdir, b'id': id, b'user': user}
             self.ui.note(_(b'running notify command %s\n') % cmd)
             fp = procutil.popen(b'(%s) 2>&1' % cmd, b'rb')
             out = util.fromnativeeol(fp.read())
             ret = fp.close()
             if ret:
                 self.ui.warn(out)
                 raise error.Abort(
                     _(b'bugzilla notify command %s') % procutil.explainexit(ret)
                 )
         self.ui.status(_(b'done\n'))
 
     def get_user_id(self, user):
         '''look up numeric bugzilla user id.'''
         try:
             return self.user_ids[user]
         except KeyError:
             try:
                 userid = int(user)
             except ValueError:
                 self.ui.note(_(b'looking up user %s\n') % user)
                 self.run(
                     '''select userid from profiles
                             where login_name like %s''',
                     user,
                 )
                 all = self.cursor.fetchall()
                 if len(all) != 1:
                     raise KeyError(user)
                 userid = int(all[0][0])
             self.user_ids[user] = userid
             return userid
 
     def get_bugzilla_user(self, committer):
         '''See if committer is a registered bugzilla user. Return
         bugzilla username and userid if so. If not, return default
         bugzilla username and userid.'''
         user = self.map_committer(committer)
         try:
             userid = self.get_user_id(user)
         except KeyError:
             try:
                 defaultuser = self.ui.config(b'bugzilla', b'bzuser')
                 if not defaultuser:
                     raise error.Abort(
                         _(b'cannot find bugzilla user id for %s') % user
                     )
                 userid = self.get_user_id(defaultuser)
                 user = defaultuser
             except KeyError:
                 raise error.Abort(
                     _(b'cannot find bugzilla user id for %s or %s')
                     % (user, defaultuser)
                 )
         return (user, userid)
 
     def updatebug(self, bugid, newstate, text, committer):
         '''update bug state with comment text.
 
         Try adding comment as committer of changeset, otherwise as
         default bugzilla user.'''
         if len(newstate) > 0:
             self.ui.warn(_(b"Bugzilla/MySQL cannot update bug state\n"))
 
         (user, userid) = self.get_bugzilla_user(committer)
         now = time.strftime(r'%Y-%m-%d %H:%M:%S')
         self.run(
             '''insert into longdescs
                     (bug_id, who, bug_when, thetext)
                     values (%s, %s, %s, %s)''',
             (bugid, userid, now, text),
         )
         self.run(
             '''insert into bugs_activity (bug_id, who, bug_when, fieldid)
                     values (%s, %s, %s, %s)''',
             (bugid, userid, now, self.longdesc_id),
         )
         self.conn.commit()
 
 
 class bzmysql_2_18(bzmysql):
     '''support for bugzilla 2.18 series.'''
 
     def __init__(self, ui):
         bzmysql.__init__(self, ui)
         self.default_notify = (
             b"cd %(bzdir)s && perl -T contrib/sendbugmail.pl %(id)s %(user)s"
         )
 
 
 class bzmysql_3_0(bzmysql_2_18):
     '''support for bugzilla 3.0 series.'''
 
     def __init__(self, ui):
         bzmysql_2_18.__init__(self, ui)
 
     def get_longdesc_id(self):
         '''get identity of longdesc field'''
         self.run(b'select id from fielddefs where name = "longdesc"')
         ids = self.cursor.fetchall()
         if len(ids) != 1:
             raise error.Abort(_(b'unknown database schema'))
         return ids[0][0]
 
 
 # Bugzilla via XMLRPC interface.
 
 
 class cookietransportrequest(object):
     """A Transport request method that retains cookies over its lifetime.
 
     The regular xmlrpclib transports ignore cookies. Which causes
     a bit of a problem when you need a cookie-based login, as with
     the Bugzilla XMLRPC interface prior to 4.4.3.
 
     So this is a helper for defining a Transport which looks for
     cookies being set in responses and saves them to add to all future
     requests.
     """
 
     # Inspiration drawn from
     # http://blog.godson.in/2010/09/how-to-make-python-xmlrpclib-client.html
     # http://www.itkovian.net/base/transport-class-for-pythons-xml-rpc-lib/
 
     cookies = []
 
     def send_cookies(self, connection):
         if self.cookies:
             for cookie in self.cookies:
                 connection.putheader(b"Cookie", cookie)
 
     def request(self, host, handler, request_body, verbose=0):
         self.verbose = verbose
         self.accept_gzip_encoding = False
 
         # issue XML-RPC request
         h = self.make_connection(host)
         if verbose:
             h.set_debuglevel(1)
 
         self.send_request(h, handler, request_body)
         self.send_host(h, host)
         self.send_cookies(h)
         self.send_user_agent(h)
         self.send_content(h, request_body)
 
         # Deal with differences between Python 2.6 and 2.7.
         # In the former h is a HTTP(S). In the latter it's a
         # HTTP(S)Connection. Luckily, the 2.6 implementation of
         # HTTP(S) has an underlying HTTP(S)Connection, so extract
         # that and use it.
         try:
             response = h.getresponse()
         except AttributeError:
             response = h._conn.getresponse()
 
         # Add any cookie definitions to our list.
         for header in response.msg.getallmatchingheaders(b"Set-Cookie"):
             val = header.split(b": ", 1)[1]
             cookie = val.split(b";", 1)[0]
             self.cookies.append(cookie)
 
         if response.status != 200:
             raise xmlrpclib.ProtocolError(
                 host + handler,
                 response.status,
                 response.reason,
                 response.msg.headers,
             )
 
         payload = response.read()
         parser, unmarshaller = self.getparser()
         parser.feed(payload)
         parser.close()
 
         return unmarshaller.close()
 
 
 # The explicit calls to the underlying xmlrpclib __init__() methods are
 # necessary. The xmlrpclib.Transport classes are old-style classes, and
 # it turns out their __init__() doesn't get called when doing multiple
 # inheritance with a new-style class.
 class cookietransport(cookietransportrequest, xmlrpclib.Transport):
     def __init__(self, use_datetime=0):
-        if util.safehasattr(xmlrpclib.Transport, b"__init__"):
+        if util.safehasattr(xmlrpclib.Transport, "__init__"):
             xmlrpclib.Transport.__init__(self, use_datetime)
 
 
 class cookiesafetransport(cookietransportrequest, xmlrpclib.SafeTransport):
     def __init__(self, use_datetime=0):
-        if util.safehasattr(xmlrpclib.Transport, b"__init__"):
+        if util.safehasattr(xmlrpclib.Transport, "__init__"):
             xmlrpclib.SafeTransport.__init__(self, use_datetime)
 
 
 class bzxmlrpc(bzaccess):
     """Support for access to Bugzilla via the Bugzilla XMLRPC API.
 
     Requires a minimum Bugzilla version 3.4.
     """
 
     def __init__(self, ui):
         bzaccess.__init__(self, ui)
 
         bzweb = self.ui.config(b'bugzilla', b'bzurl')
         bzweb = bzweb.rstrip(b"/") + b"/xmlrpc.cgi"
 
         user = self.ui.config(b'bugzilla', b'user')
         passwd = self.ui.config(b'bugzilla', b'password')
 
         self.fixstatus = self.ui.config(b'bugzilla', b'fixstatus')
         self.fixresolution = self.ui.config(b'bugzilla', b'fixresolution')
 
         self.bzproxy = xmlrpclib.ServerProxy(bzweb, self.transport(bzweb))
         ver = self.bzproxy.Bugzilla.version()[b'version'].split(b'.')
         self.bzvermajor = int(ver[0])
         self.bzverminor = int(ver[1])
         login = self.bzproxy.User.login(
             {b'login': user, b'password': passwd, b'restrict_login': True}
         )
         self.bztoken = login.get(b'token', b'')
 
     def transport(self, uri):
         if util.urlreq.urlparse(uri, b"http")[0] == b"https":
             return cookiesafetransport()
         else:
             return cookietransport()
 
     def get_bug_comments(self, id):
         """Return a string with all comment text for a bug."""
         c = self.bzproxy.Bug.comments(
             {b'ids': [id], b'include_fields': [b'text'], b'token': self.bztoken}
         )
         return b''.join(
             [t[b'text'] for t in c[b'bugs'][b'%d' % id][b'comments']]
         )
 
     def filter_real_bug_ids(self, bugs):
         probe = self.bzproxy.Bug.get(
             {
                 b'ids': sorted(bugs.keys()),
                 b'include_fields': [],
                 b'permissive': True,
                 b'token': self.bztoken,
             }
         )
         for badbug in probe[b'faults']:
             id = badbug[b'id']
             self.ui.status(_(b'bug %d does not exist\n') % id)
             del bugs[id]
 
     def filter_cset_known_bug_ids(self, node, bugs):
         for id in sorted(bugs.keys()):
             if self.get_bug_comments(id).find(short(node)) != -1:
                 self.ui.status(
                     _(b'bug %d already knows about changeset %s\n')
                     % (id, short(node))
                 )
                 del bugs[id]
 
     def updatebug(self, bugid, newstate, text, committer):
         args = {}
         if b'hours' in newstate:
             args[b'work_time'] = newstate[b'hours']
 
         if self.bzvermajor >= 4:
             args[b'ids'] = [bugid]
             args[b'comment'] = {b'body': text}
             if b'fix' in newstate:
                 args[b'status'] = self.fixstatus
                 args[b'resolution'] = self.fixresolution
             args[b'token'] = self.bztoken
             self.bzproxy.Bug.update(args)
         else:
             if b'fix' in newstate:
                 self.ui.warn(
                     _(
                         b"Bugzilla/XMLRPC needs Bugzilla 4.0 or later "
                         b"to mark bugs fixed\n"
                     )
                 )
             args[b'id'] = bugid
             args[b'comment'] = text
             self.bzproxy.Bug.add_comment(args)
 
 
 class bzxmlrpcemail(bzxmlrpc):
     """Read data from Bugzilla via XMLRPC, send updates via email.
 
     Advantages of sending updates via email:
       1. Comments can be added as any user, not just logged in user.
       2. Bug statuses or other fields not accessible via XMLRPC can
          potentially be updated.
 
     There is no XMLRPC function to change bug status before Bugzilla
     4.0, so bugs cannot be marked fixed via XMLRPC before Bugzilla 4.0.
     But bugs can be marked fixed via email from 3.4 onwards.
     """
 
     # The email interface changes subtly between 3.4 and 3.6. In 3.4,
     # in-email fields are specified as '@<fieldname> = <value>'. In
     # 3.6 this becomes '@<fieldname> <value>'. And fieldname @bug_id
     # in 3.4 becomes @id in 3.6. 3.6 and 4.0 both maintain backwards
     # compatibility, but rather than rely on this use the new format for
     # 4.0 onwards.
 
     def __init__(self, ui):
         bzxmlrpc.__init__(self, ui)
 
         self.bzemail = self.ui.config(b'bugzilla', b'bzemail')
         if not self.bzemail:
             raise error.Abort(_(b"configuration 'bzemail' missing"))
         mail.validateconfig(self.ui)
 
     def makecommandline(self, fieldname, value):
         if self.bzvermajor >= 4:
             return b"@%s %s" % (fieldname, pycompat.bytestr(value))
         else:
             if fieldname == b"id":
                 fieldname = b"bug_id"
             return b"@%s = %s" % (fieldname, pycompat.bytestr(value))
 
     def send_bug_modify_email(self, bugid, commands, comment, committer):
         '''send modification message to Bugzilla bug via email.
 
         The message format is documented in the Bugzilla email_in.pl
         specification. commands is a list of command lines, comment is the
         comment text.
 
         To stop users from crafting commit comments with
         Bugzilla commands, specify the bug ID via the message body, rather
         than the subject line, and leave a blank line after it.
         '''
         user = self.map_committer(committer)
         matches = self.bzproxy.User.get(
             {b'match': [user], b'token': self.bztoken}
         )
         if not matches[b'users']:
             user = self.ui.config(b'bugzilla', b'user')
             matches = self.bzproxy.User.get(
                 {b'match': [user], b'token': self.bztoken}
             )
             if not matches[b'users']:
                 raise error.Abort(
                     _(b"default bugzilla user %s email not found") % user
                 )
         user = matches[b'users'][0][b'email']
         commands.append(self.makecommandline(b"id", bugid))
 
         text = b"\n".join(commands) + b"\n\n" + comment
 
         _charsets = mail._charsets(self.ui)
         user = mail.addressencode(self.ui, user, _charsets)
         bzemail = mail.addressencode(self.ui, self.bzemail, _charsets)
         msg = mail.mimeencode(self.ui, text, _charsets)
         msg[b'From'] = user
         msg[b'To'] = bzemail
         msg[b'Subject'] = mail.headencode(
             self.ui, b"Bug modification", _charsets
         )
         sendmail = mail.connect(self.ui)
         sendmail(user, bzemail, msg.as_string())
 
     def updatebug(self, bugid, newstate, text, committer):
         cmds = []
         if b'hours' in newstate:
             cmds.append(self.makecommandline(b"work_time", newstate[b'hours']))
         if b'fix' in newstate:
             cmds.append(self.makecommandline(b"bug_status", self.fixstatus))
             cmds.append(self.makecommandline(b"resolution", self.fixresolution))
         self.send_bug_modify_email(bugid, cmds, text, committer)
 
 
 class NotFound(LookupError):
     pass
 
 
 class bzrestapi(bzaccess):
     """Read and write bugzilla data using the REST API available since
     Bugzilla 5.0.
     """
 
     def __init__(self, ui):
         bzaccess.__init__(self, ui)
         bz = self.ui.config(b'bugzilla', b'bzurl')
         self.bzroot = b'/'.join([bz, b'rest'])
         self.apikey = self.ui.config(b'bugzilla', b'apikey')
         self.user = self.ui.config(b'bugzilla', b'user')
         self.passwd = self.ui.config(b'bugzilla', b'password')
         self.fixstatus = self.ui.config(b'bugzilla', b'fixstatus')
         self.fixresolution = self.ui.config(b'bugzilla', b'fixresolution')
 
     def apiurl(self, targets, include_fields=None):
         url = b'/'.join([self.bzroot] + [pycompat.bytestr(t) for t in targets])
         qv = {}
         if self.apikey:
             qv[b'api_key'] = self.apikey
         elif self.user and self.passwd:
             qv[b'login'] = self.user
             qv[b'password'] = self.passwd
         if include_fields:
             qv[b'include_fields'] = include_fields
         if qv:
             url = b'%s?%s' % (url, util.urlreq.urlencode(qv))
         return url
 
     def _fetch(self, burl):
         try:
             resp = url.open(self.ui, burl)
             return json.loads(resp.read())
         except util.urlerr.httperror as inst:
             if inst.code == 401:
                 raise error.Abort(_(b'authorization failed'))
             if inst.code == 404:
                 raise NotFound()
             else:
                 raise
 
     def _submit(self, burl, data, method=b'POST'):
         data = json.dumps(data)
         if method == b'PUT':
 
             class putrequest(util.urlreq.request):
                 def get_method(self):
                     return b'PUT'
 
             request_type = putrequest
         else:
             request_type = util.urlreq.request
         req = request_type(burl, data, {b'Content-Type': b'application/json'})
         try:
             resp = url.opener(self.ui).open(req)
             return json.loads(resp.read())
         except util.urlerr.httperror as inst:
             if inst.code == 401:
                 raise error.Abort(_(b'authorization failed'))
             if inst.code == 404:
                 raise NotFound()
             else:
                 raise
 
     def filter_real_bug_ids(self, bugs):
         '''remove bug IDs that do not exist in Bugzilla from bugs.'''
         badbugs = set()
         for bugid in bugs:
             burl = self.apiurl((b'bug', bugid), include_fields=b'status')
             try:
                 self._fetch(burl)
             except NotFound:
                 badbugs.add(bugid)
         for bugid in badbugs:
             del bugs[bugid]
 
     def filter_cset_known_bug_ids(self, node, bugs):
         '''remove bug IDs where node occurs in comment text from bugs.'''
         sn = short(node)
         for bugid in bugs.keys():
             burl = self.apiurl(
                 (b'bug', bugid, b'comment'), include_fields=b'text'
             )
             result = self._fetch(burl)
             comments = result[b'bugs'][pycompat.bytestr(bugid)][b'comments']
             if any(sn in c[b'text'] for c in comments):
                 self.ui.status(
                     _(b'bug %d already knows about changeset %s\n')
                     % (bugid, sn)
                 )
                 del bugs[bugid]
 
     def updatebug(self, bugid, newstate, text, committer):
         '''update the specified bug. Add comment text and set new states.
 
         If possible add the comment as being from the committer of
         the changeset. Otherwise use the default Bugzilla user.
         '''
         bugmod = {}
         if b'hours' in newstate:
             bugmod[b'work_time'] = newstate[b'hours']
         if b'fix' in newstate:
             bugmod[b'status'] = self.fixstatus
             bugmod[b'resolution'] = self.fixresolution
         if bugmod:
             # if we have to change the bugs state do it here
             bugmod[b'comment'] = {
                 b'comment': text,
                 b'is_private': False,
                 b'is_markdown': False,
             }
             burl = self.apiurl((b'bug', bugid))
             self._submit(burl, bugmod, method=b'PUT')
             self.ui.debug(b'updated bug %s\n' % bugid)
         else:
             burl = self.apiurl((b'bug', bugid, b'comment'))
             self._submit(
                 burl,
                 {
                     b'comment': text,
                     b'is_private': False,
                     b'is_markdown': False,
                 },
             )
             self.ui.debug(b'added comment to bug %s\n' % bugid)
 
     def notify(self, bugs, committer):
         '''Force sending of Bugzilla notification emails.
 
         Only required if the access method does not trigger notification
         emails automatically.
         '''
         pass
 
 
 class bugzilla(object):
     # supported versions of bugzilla. different versions have
     # different schemas.
     _versions = {
         b'2.16': bzmysql,
         b'2.18': bzmysql_2_18,
         b'3.0': bzmysql_3_0,
         b'xmlrpc': bzxmlrpc,
         b'xmlrpc+email': bzxmlrpcemail,
         b'restapi': bzrestapi,
     }
 
     def __init__(self, ui, repo):
         self.ui = ui
         self.repo = repo
 
         bzversion = self.ui.config(b'bugzilla', b'version')
         try:
             bzclass = bugzilla._versions[bzversion]
         except KeyError:
             raise error.Abort(
                 _(b'bugzilla version %s not supported') % bzversion
             )
         self.bzdriver = bzclass(self.ui)
 
         self.bug_re = re.compile(
             self.ui.config(b'bugzilla', b'regexp'), re.IGNORECASE
         )
         self.fix_re = re.compile(
             self.ui.config(b'bugzilla', b'fixregexp'), re.IGNORECASE
         )
         self.split_re = re.compile(br'\D+')
 
     def find_bugs(self, ctx):
         '''return bugs dictionary created from commit comment.
 
         Extract bug info from changeset comments. Filter out any that are
         not known to Bugzilla, and any that already have a reference to
         the given changeset in their comments.
         '''
         start = 0
         hours = 0.0
         bugs = {}
         bugmatch = self.bug_re.search(ctx.description(), start)
         fixmatch = self.fix_re.search(ctx.description(), start)
         while True:
             bugattribs = {}
             if not bugmatch and not fixmatch:
                 break
             if not bugmatch:
                 m = fixmatch
             elif not fixmatch:
                 m = bugmatch
             else:
                 if bugmatch.start() < fixmatch.start():
                     m = bugmatch
                 else:
                     m = fixmatch
             start = m.end()
             if m is bugmatch:
                 bugmatch = self.bug_re.search(ctx.description(), start)
                 if b'fix' in bugattribs:
                     del bugattribs[b'fix']
             else:
                 fixmatch = self.fix_re.search(ctx.description(), start)
                 bugattribs[b'fix'] = None
 
             try:
                 ids = m.group(b'ids')
             except IndexError:
                 ids = m.group(1)
             try:
                 hours = float(m.group(b'hours'))
                 bugattribs[b'hours'] = hours
             except IndexError:
                 pass
             except TypeError:
                 pass
             except ValueError:
                 self.ui.status(_(b"%s: invalid hours\n") % m.group(b'hours'))
 
             for id in self.split_re.split(ids):
                 if not id:
                     continue
                 bugs[int(id)] = bugattribs
         if bugs:
             self.bzdriver.filter_real_bug_ids(bugs)
         if bugs:
             self.bzdriver.filter_cset_known_bug_ids(ctx.node(), bugs)
         return bugs
 
     def update(self, bugid, newstate, ctx):
         '''update bugzilla bug with reference to changeset.'''
 
         def webroot(root):
             '''strip leading prefix of repo root and turn into
             url-safe path.'''
             count = int(self.ui.config(b'bugzilla', b'strip'))
             root = util.pconvert(root)
             while count > 0:
                 c = root.find(b'/')
                 if c == -1:
                     break
                 root = root[c + 1 :]
                 count -= 1
             return root
 
         mapfile = None
         tmpl = self.ui.config(b'bugzilla', b'template')
         if not tmpl:
             mapfile = self.ui.config(b'bugzilla', b'style')
         if not mapfile and not tmpl:
             tmpl = _(
                 b'changeset {node|short} in repo {root} refers '
                 b'to bug {bug}.\ndetails:\n\t{desc|tabindent}'
             )
         spec = logcmdutil.templatespec(tmpl, mapfile)
         t = logcmdutil.changesettemplater(self.ui, self.repo, spec)
         self.ui.pushbuffer()
         t.show(
             ctx,
             changes=ctx.changeset(),
             bug=pycompat.bytestr(bugid),
             hgweb=self.ui.config(b'web', b'baseurl'),
             root=self.repo.root,
             webroot=webroot(self.repo.root),
         )
         data = self.ui.popbuffer()
         self.bzdriver.updatebug(
             bugid, newstate, data, stringutil.email(ctx.user())
         )
 
     def notify(self, bugs, committer):
         '''ensure Bugzilla users are notified of bug change.'''
         self.bzdriver.notify(bugs, committer)
 
 
 def hook(ui, repo, hooktype, node=None, **kwargs):
     '''add comment to bugzilla for each changeset that refers to a
     bugzilla bug id. only add a comment once per bug, so same change
     seen multiple times does not fill bug with duplicate data.'''
     if node is None:
         raise error.Abort(
             _(b'hook type %s does not pass a changeset id') % hooktype
         )
     try:
         bz = bugzilla(ui, repo)
         ctx = repo[node]
         bugs = bz.find_bugs(ctx)
         if bugs:
             for bug in bugs:
                 bz.update(bug, bugs[bug], ctx)
             bz.notify(bugs, stringutil.email(ctx.user()))
     except Exception as e:
         raise error.Abort(_(b'Bugzilla error: %s') % e)

hgext/commitextras.py

@@ -1,89 +1,89 b''
 # commitextras.py
 #
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 '''adds a new flag extras to commit (ADVANCED)'''
 
 from __future__ import absolute_import
 
 import re
 
 from mercurial.i18n import _
 from mercurial import (
     commands,
     error,
     extensions,
     registrar,
     util,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 testedwith = b'ships-with-hg-core'
 
 usedinternally = {
     b'amend_source',
     b'branch',
     b'close',
     b'histedit_source',
     b'topic',
     b'rebase_source',
     b'intermediate-source',
     b'__touch-noise__',
     b'source',
     b'transplant_source',
 }
 
 
 def extsetup(ui):
     entry = extensions.wrapcommand(commands.table, b'commit', _commit)
     options = entry[1]
     options.append(
         (
             b'',
             b'extra',
             [],
             _(b'set a changeset\'s extra values'),
             _(b"KEY=VALUE"),
         )
     )
 
 
 def _commit(orig, ui, repo, *pats, **opts):
-    if util.safehasattr(repo, b'unfiltered'):
+    if util.safehasattr(repo, 'unfiltered'):
         repo = repo.unfiltered()
 
     class repoextra(repo.__class__):
         def commit(self, *innerpats, **inneropts):
             extras = opts.get(r'extra')
             for raw in extras:
                 if b'=' not in raw:
                     msg = _(
                         b"unable to parse '%s', should follow "
                         b"KEY=VALUE format"
                     )
                     raise error.Abort(msg % raw)
                 k, v = raw.split(b'=', 1)
                 if not k:
                     msg = _(b"unable to parse '%s', keys can't be empty")
                     raise error.Abort(msg % raw)
                 if re.search(br'[^\w-]', k):
                     msg = _(
                         b"keys can only contain ascii letters, digits,"
                         b" '_' and '-'"
                     )
                     raise error.Abort(msg)
                 if k in usedinternally:
                     msg = _(
                         b"key '%s' is used internally, can't be set "
                         b"manually"
                     )
                     raise error.Abort(msg % k)
                 inneropts[r'extra'][k] = v
             return super(repoextra, self).commit(*innerpats, **inneropts)
 
     repo.__class__ = repoextra
     return orig(ui, repo, *pats, **opts)

hgext/fastannotate/commands.py

@@ -1,357 +1,357 b''
 # Copyright 2016-present Facebook. All Rights Reserved.
 #
 # commands: fastannotate commands
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import os
 
 from mercurial.i18n import _
 from mercurial import (
     commands,
     encoding,
     error,
     extensions,
     patch,
     pycompat,
     registrar,
     scmutil,
     util,
 )
 
 from . import (
     context as facontext,
     error as faerror,
     formatter as faformatter,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 
 def _matchpaths(repo, rev, pats, opts, aopts=facontext.defaultopts):
     """generate paths matching given patterns"""
     perfhack = repo.ui.configbool(b'fastannotate', b'perfhack')
 
     # disable perfhack if:
     # a) any walkopt is used
     # b) if we treat pats as plain file names, some of them do not have
     #    corresponding linelog files
     if perfhack:
         # cwd related to reporoot
         reporoot = os.path.dirname(repo.path)
         reldir = os.path.relpath(encoding.getcwd(), reporoot)
         if reldir == b'.':
             reldir = b''
         if any(opts.get(o[1]) for o in commands.walkopts):  # a)
             perfhack = False
         else:  # b)
             relpats = [
                 os.path.relpath(p, reporoot) if os.path.isabs(p) else p
                 for p in pats
             ]
             # disable perfhack on '..' since it allows escaping from the repo
             if any(
                 (
                     b'..' in f
                     or not os.path.isfile(
                         facontext.pathhelper(repo, f, aopts).linelogpath
                     )
                 )
                 for f in relpats
             ):
                 perfhack = False
 
     # perfhack: emit paths directory without checking with manifest
     # this can be incorrect if the rev dos not have file.
     if perfhack:
         for p in relpats:
             yield os.path.join(reldir, p)
     else:
 
         def bad(x, y):
             raise error.Abort(b"%s: %s" % (x, y))
 
         ctx = scmutil.revsingle(repo, rev)
         m = scmutil.match(ctx, pats, opts, badfn=bad)
         for p in ctx.walk(m):
             yield p
 
 
 fastannotatecommandargs = {
     r'options': [
         (b'r', b'rev', b'.', _(b'annotate the specified revision'), _(b'REV')),
         (b'u', b'user', None, _(b'list the author (long with -v)')),
         (b'f', b'file', None, _(b'list the filename')),
         (b'd', b'date', None, _(b'list the date (short with -q)')),
         (b'n', b'number', None, _(b'list the revision number (default)')),
         (b'c', b'changeset', None, _(b'list the changeset')),
         (
             b'l',
             b'line-number',
             None,
             _(b'show line number at the first ' b'appearance'),
         ),
         (
             b'e',
             b'deleted',
             None,
             _(b'show deleted lines (slow) (EXPERIMENTAL)'),
         ),
         (
             b'',
             b'no-content',
             None,
             _(b'do not show file content (EXPERIMENTAL)'),
         ),
         (b'', b'no-follow', None, _(b"don't follow copies and renames")),
         (
             b'',
             b'linear',
             None,
             _(
                 b'enforce linear history, ignore second parent '
                 b'of merges (EXPERIMENTAL)'
             ),
         ),
         (
             b'',
             b'long-hash',
             None,
             _(b'show long changeset hash (EXPERIMENTAL)'),
         ),
         (
             b'',
             b'rebuild',
             None,
             _(b'rebuild cache even if it exists ' b'(EXPERIMENTAL)'),
         ),
     ]
     + commands.diffwsopts
     + commands.walkopts
     + commands.formatteropts,
     r'synopsis': _(b'[-r REV] [-f] [-a] [-u] [-d] [-n] [-c] [-l] FILE...'),
     r'inferrepo': True,
 }
 
 
 def fastannotate(ui, repo, *pats, **opts):
     """show changeset information by line for each file
 
     List changes in files, showing the revision id responsible for each line.
 
     This command is useful for discovering when a change was made and by whom.
 
     By default this command prints revision numbers. If you include --file,
     --user, or --date, the revision number is suppressed unless you also
     include --number. The default format can also be customized by setting
     fastannotate.defaultformat.
 
     Returns 0 on success.
 
     .. container:: verbose
 
         This command uses an implementation different from the vanilla annotate
         command, which may produce slightly different (while still reasonable)
         outputs for some cases.
 
         Unlike the vanilla anootate, fastannotate follows rename regardless of
         the existence of --file.
 
         For the best performance when running on a full repo, use -c, -l,
         avoid -u, -d, -n. Use --linear and --no-content to make it even faster.
 
         For the best performance when running on a shallow (remotefilelog)
         repo, avoid --linear, --no-follow, or any diff options. As the server
         won't be able to populate annotate cache when non-default options
         affecting results are used.
     """
     if not pats:
         raise error.Abort(_(b'at least one filename or pattern is required'))
 
     # performance hack: filtered repo can be slow. unfilter by default.
     if ui.configbool(b'fastannotate', b'unfilteredrepo'):
         repo = repo.unfiltered()
 
     opts = pycompat.byteskwargs(opts)
 
     rev = opts.get(b'rev', b'.')
     rebuild = opts.get(b'rebuild', False)
 
     diffopts = patch.difffeatureopts(
         ui, opts, section=b'annotate', whitespace=True
     )
     aopts = facontext.annotateopts(
         diffopts=diffopts,
         followmerge=not opts.get(b'linear', False),
         followrename=not opts.get(b'no_follow', False),
     )
 
     if not any(
         opts.get(s)
         for s in [b'user', b'date', b'file', b'number', b'changeset']
     ):
         # default 'number' for compatibility. but fastannotate is more
         # efficient with "changeset", "line-number" and "no-content".
         for name in ui.configlist(
             b'fastannotate', b'defaultformat', [b'number']
         ):
             opts[name] = True
 
     ui.pager(b'fastannotate')
     template = opts.get(b'template')
     if template == b'json':
         formatter = faformatter.jsonformatter(ui, repo, opts)
     else:
         formatter = faformatter.defaultformatter(ui, repo, opts)
     showdeleted = opts.get(b'deleted', False)
     showlines = not bool(opts.get(b'no_content'))
     showpath = opts.get(b'file', False)
 
     # find the head of the main (master) branch
     master = ui.config(b'fastannotate', b'mainbranch') or rev
 
     # paths will be used for prefetching and the real annotating
     paths = list(_matchpaths(repo, rev, pats, opts, aopts))
 
     # for client, prefetch from the server
-    if util.safehasattr(repo, b'prefetchfastannotate'):
+    if util.safehasattr(repo, 'prefetchfastannotate'):
         repo.prefetchfastannotate(paths)
 
     for path in paths:
         result = lines = existinglines = None
         while True:
             try:
                 with facontext.annotatecontext(repo, path, aopts, rebuild) as a:
                     result = a.annotate(
                         rev,
                         master=master,
                         showpath=showpath,
                         showlines=(showlines and not showdeleted),
                     )
                     if showdeleted:
                         existinglines = set((l[0], l[1]) for l in result)
                         result = a.annotatealllines(
                             rev, showpath=showpath, showlines=showlines
                         )
                 break
             except (faerror.CannotReuseError, faerror.CorruptedFileError):
                 # happens if master moves backwards, or the file was deleted
                 # and readded, or renamed to an existing name, or corrupted.
                 if rebuild:  # give up since we have tried rebuild already
                     raise
                 else:  # try a second time rebuilding the cache (slow)
                     rebuild = True
                     continue
 
         if showlines:
             result, lines = result
 
         formatter.write(result, lines, existinglines=existinglines)
     formatter.end()
 
 
 _newopts = set()
 _knownopts = {
     opt[1].replace(b'-', b'_')
     for opt in (fastannotatecommandargs[r'options'] + commands.globalopts)
 }
 
 
 def _annotatewrapper(orig, ui, repo, *pats, **opts):
     """used by wrapdefault"""
     # we need this hack until the obsstore has 0.0 seconds perf impact
     if ui.configbool(b'fastannotate', b'unfilteredrepo'):
         repo = repo.unfiltered()
 
     # treat the file as text (skip the isbinary check)
     if ui.configbool(b'fastannotate', b'forcetext'):
         opts[r'text'] = True
 
     # check if we need to do prefetch (client-side)
     rev = opts.get(r'rev')
-    if util.safehasattr(repo, b'prefetchfastannotate') and rev is not None:
+    if util.safehasattr(repo, 'prefetchfastannotate') and rev is not None:
         paths = list(_matchpaths(repo, rev, pats, pycompat.byteskwargs(opts)))
         repo.prefetchfastannotate(paths)
 
     return orig(ui, repo, *pats, **opts)
 
 
 def registercommand():
     """register the fastannotate command"""
     name = b'fastannotate|fastblame|fa'
     command(name, helpbasic=True, **fastannotatecommandargs)(fastannotate)
 
 
 def wrapdefault():
     """wrap the default annotate command, to be aware of the protocol"""
     extensions.wrapcommand(commands.table, b'annotate', _annotatewrapper)
 
 
 @command(
     b'debugbuildannotatecache',
     [(b'r', b'rev', b'', _(b'build up to the specific revision'), _(b'REV'))]
     + commands.walkopts,
     _(b'[-r REV] FILE...'),
 )
 def debugbuildannotatecache(ui, repo, *pats, **opts):
     """incrementally build fastannotate cache up to REV for specified files
 
     If REV is not specified, use the config 'fastannotate.mainbranch'.
 
     If fastannotate.client is True, download the annotate cache from the
     server. Otherwise, build the annotate cache locally.
 
     The annotate cache will be built using the default diff and follow
     options and lives in '.hg/fastannotate/default'.
     """
     opts = pycompat.byteskwargs(opts)
     rev = opts.get(b'REV') or ui.config(b'fastannotate', b'mainbranch')
     if not rev:
         raise error.Abort(
             _(b'you need to provide a revision'),
             hint=_(b'set fastannotate.mainbranch or use --rev'),
         )
     if ui.configbool(b'fastannotate', b'unfilteredrepo'):
         repo = repo.unfiltered()
     ctx = scmutil.revsingle(repo, rev)
     m = scmutil.match(ctx, pats, opts)
     paths = list(ctx.walk(m))
-    if util.safehasattr(repo, b'prefetchfastannotate'):
+    if util.safehasattr(repo, 'prefetchfastannotate'):
         # client
         if opts.get(b'REV'):
             raise error.Abort(_(b'--rev cannot be used for client'))
         repo.prefetchfastannotate(paths)
     else:
         # server, or full repo
         progress = ui.makeprogress(_(b'building'), total=len(paths))
         for i, path in enumerate(paths):
             progress.update(i)
             with facontext.annotatecontext(repo, path) as actx:
                 try:
                     if actx.isuptodate(rev):
                         continue
                     actx.annotate(rev, rev)
                 except (faerror.CannotReuseError, faerror.CorruptedFileError):
                     # the cache is broken (could happen with renaming so the
                     # file history gets invalidated). rebuild and try again.
                     ui.debug(
                         b'fastannotate: %s: rebuilding broken cache\n' % path
                     )
                     actx.rebuild()
                     try:
                         actx.annotate(rev, rev)
                     except Exception as ex:
                         # possibly a bug, but should not stop us from building
                         # cache for other files.
                         ui.warn(
                             _(
                                 b'fastannotate: %s: failed to '
                                 b'build cache: %r\n'
                             )
                             % (path, ex)
                         )
         progress.complete()

hgext/fsmonitor/watchmanclient.py

@@ -1,118 +1,118 b''
 # watchmanclient.py - Watchman client for the fsmonitor extension
 #
 # Copyright 2013-2016 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import getpass
 
 from mercurial import util
 
 from . import pywatchman
 
 
 class Unavailable(Exception):
     def __init__(self, msg, warn=True, invalidate=False):
         self.msg = msg
         self.warn = warn
         if self.msg == b'timed out waiting for response':
             self.warn = False
         self.invalidate = invalidate
 
     def __str__(self):
         if self.warn:
             return b'warning: Watchman unavailable: %s' % self.msg
         else:
             return b'Watchman unavailable: %s' % self.msg
 
 
 class WatchmanNoRoot(Unavailable):
     def __init__(self, root, msg):
         self.root = root
         super(WatchmanNoRoot, self).__init__(msg)
 
 
 class client(object):
     def __init__(self, ui, root, timeout=1.0):
         err = None
         if not self._user:
             err = b"couldn't get user"
             warn = True
         if self._user in ui.configlist(b'fsmonitor', b'blacklistusers'):
             err = b'user %s in blacklist' % self._user
             warn = False
 
         if err:
             raise Unavailable(err, warn)
 
         self._timeout = timeout
         self._watchmanclient = None
         self._root = root
         self._ui = ui
         self._firsttime = True
 
     def settimeout(self, timeout):
         self._timeout = timeout
         if self._watchmanclient is not None:
             self._watchmanclient.setTimeout(timeout)
 
     def getcurrentclock(self):
         result = self.command(b'clock')
-        if not util.safehasattr(result, b'clock'):
+        if not util.safehasattr(result, 'clock'):
             raise Unavailable(
                 b'clock result is missing clock value', invalidate=True
             )
         return result.clock
 
     def clearconnection(self):
         self._watchmanclient = None
 
     def available(self):
         return self._watchmanclient is not None or self._firsttime
 
     @util.propertycache
     def _user(self):
         try:
             return getpass.getuser()
         except KeyError:
             # couldn't figure out our user
             return None
 
     def _command(self, *args):
         watchmanargs = (args[0], self._root) + args[1:]
         try:
             if self._watchmanclient is None:
                 self._firsttime = False
                 watchman_exe = self._ui.configpath(
                     b'fsmonitor', b'watchman_exe'
                 )
                 self._watchmanclient = pywatchman.client(
                     timeout=self._timeout,
                     useImmutableBser=True,
                     watchman_exe=watchman_exe,
                 )
             return self._watchmanclient.query(*watchmanargs)
         except pywatchman.CommandError as ex:
             if b'unable to resolve root' in ex.msg:
                 raise WatchmanNoRoot(self._root, ex.msg)
             raise Unavailable(ex.msg)
         except pywatchman.WatchmanError as ex:
             raise Unavailable(str(ex))
 
     def command(self, *args):
         try:
             try:
                 return self._command(*args)
             except WatchmanNoRoot:
                 # this 'watch' command can also raise a WatchmanNoRoot if
                 # watchman refuses to accept this root
                 self._command(b'watch')
                 return self._command(*args)
         except Unavailable:
             # this is in an outer scope to catch Unavailable form any of the
             # above _command calls
             self._watchmanclient = None
             raise

hgext/journal.py

@@ -1,604 +1,604 b''
 # journal.py
 #
 # Copyright 2014-2016 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 """track previous positions of bookmarks (EXPERIMENTAL)
 
 This extension adds a new command: `hg journal`, which shows you where
 bookmarks were previously located.
 
 """
 
 from __future__ import absolute_import
 
 import collections
 import errno
 import os
 import weakref
 
 from mercurial.i18n import _
 
 from mercurial import (
     bookmarks,
     cmdutil,
     dispatch,
     encoding,
     error,
     extensions,
     hg,
     localrepo,
     lock,
     logcmdutil,
     node,
     pycompat,
     registrar,
     util,
 )
 from mercurial.utils import (
     dateutil,
     procutil,
     stringutil,
 )
 
 cmdtable = {}
 command = registrar.command(cmdtable)
 
 # Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for
 # extensions which SHIP WITH MERCURIAL. Non-mainline extensions should
 # be specifying the version(s) of Mercurial they are tested with, or
 # leave the attribute unspecified.
 testedwith = b'ships-with-hg-core'
 
 # storage format version; increment when the format changes
 storageversion = 0
 
 # namespaces
 bookmarktype = b'bookmark'
 wdirparenttype = b'wdirparent'
 # In a shared repository, what shared feature name is used
 # to indicate this namespace is shared with the source?
 sharednamespaces = {
     bookmarktype: hg.sharedbookmarks,
 }
 
 # Journal recording, register hooks and storage object
 def extsetup(ui):
     extensions.wrapfunction(dispatch, b'runcommand', runcommand)
     extensions.wrapfunction(bookmarks.bmstore, b'_write', recordbookmarks)
     extensions.wrapfilecache(
         localrepo.localrepository, b'dirstate', wrapdirstate
     )
     extensions.wrapfunction(hg, b'postshare', wrappostshare)
     extensions.wrapfunction(hg, b'copystore', unsharejournal)
 
 
 def reposetup(ui, repo):
     if repo.local():
         repo.journal = journalstorage(repo)
         repo._wlockfreeprefix.add(b'namejournal')
 
         dirstate, cached = localrepo.isfilecached(repo, b'dirstate')
         if cached:
             # already instantiated dirstate isn't yet marked as
             # "journal"-ing, even though repo.dirstate() was already
             # wrapped by own wrapdirstate()
             _setupdirstate(repo, dirstate)
 
 
 def runcommand(orig, lui, repo, cmd, fullargs, *args):
     """Track the command line options for recording in the journal"""
     journalstorage.recordcommand(*fullargs)
     return orig(lui, repo, cmd, fullargs, *args)
 
 
 def _setupdirstate(repo, dirstate):
     dirstate.journalstorage = repo.journal
     dirstate.addparentchangecallback(b'journal', recorddirstateparents)
 
 
 # hooks to record dirstate changes
 def wrapdirstate(orig, repo):
     """Make journal storage available to the dirstate object"""
     dirstate = orig(repo)
-    if util.safehasattr(repo, b'journal'):
+    if util.safehasattr(repo, 'journal'):
         _setupdirstate(repo, dirstate)
     return dirstate
 
 
 def recorddirstateparents(dirstate, old, new):
     """Records all dirstate parent changes in the journal."""
     old = list(old)
     new = list(new)
-    if util.safehasattr(dirstate, b'journalstorage'):
+    if util.safehasattr(dirstate, 'journalstorage'):
         # only record two hashes if there was a merge
         oldhashes = old[:1] if old[1] == node.nullid else old
         newhashes = new[:1] if new[1] == node.nullid else new
         dirstate.journalstorage.record(
             wdirparenttype, b'.', oldhashes, newhashes
         )
 
 
 # hooks to record bookmark changes (both local and remote)
 def recordbookmarks(orig, store, fp):
     """Records all bookmark changes in the journal."""
     repo = store._repo
-    if util.safehasattr(repo, b'journal'):
+    if util.safehasattr(repo, 'journal'):
         oldmarks = bookmarks.bmstore(repo)
         for mark, value in pycompat.iteritems(store):
             oldvalue = oldmarks.get(mark, node.nullid)
             if value != oldvalue:
                 repo.journal.record(bookmarktype, mark, oldvalue, value)
     return orig(store, fp)
 
 
 # shared repository support
 def _readsharedfeatures(repo):
     """A set of shared features for this repository"""
     try:
         return set(repo.vfs.read(b'shared').splitlines())
     except IOError as inst:
         if inst.errno != errno.ENOENT:
             raise
         return set()
 
 
 def _mergeentriesiter(*iterables, **kwargs):
     """Given a set of sorted iterables, yield the next entry in merged order
 
     Note that by default entries go from most recent to oldest.
     """
     order = kwargs.pop(r'order', max)
     iterables = [iter(it) for it in iterables]
     # this tracks still active iterables; iterables are deleted as they are
     # exhausted, which is why this is a dictionary and why each entry also
     # stores the key. Entries are mutable so we can store the next value each
     # time.
     iterable_map = {}
     for key, it in enumerate(iterables):
         try:
             iterable_map[key] = [next(it), key, it]
         except StopIteration:
             # empty entry, can be ignored
             pass
 
     while iterable_map:
         value, key, it = order(pycompat.itervalues(iterable_map))
         yield value
         try:
             iterable_map[key][0] = next(it)
         except StopIteration:
             # this iterable is empty, remove it from consideration
             del iterable_map[key]
 
 
 def wrappostshare(orig, sourcerepo, destrepo, **kwargs):
     """Mark this shared working copy as sharing journal information"""
     with destrepo.wlock():
         orig(sourcerepo, destrepo, **kwargs)
         with destrepo.vfs(b'shared', b'a') as fp:
             fp.write(b'journal\n')
 
 
 def unsharejournal(orig, ui, repo, repopath):
     """Copy shared journal entries into this repo when unsharing"""
     if (
         repo.path == repopath
         and repo.shared()
-        and util.safehasattr(repo, b'journal')
+        and util.safehasattr(repo, 'journal')
     ):
         sharedrepo = hg.sharedreposource(repo)
         sharedfeatures = _readsharedfeatures(repo)
         if sharedrepo and sharedfeatures > {b'journal'}:
             # there is a shared repository and there are shared journal entries
             # to copy. move shared date over from source to destination but
             # move the local file first
             if repo.vfs.exists(b'namejournal'):
                 journalpath = repo.vfs.join(b'namejournal')
                 util.rename(journalpath, journalpath + b'.bak')
             storage = repo.journal
             local = storage._open(
                 repo.vfs, filename=b'namejournal.bak', _newestfirst=False
             )
             shared = (
                 e
                 for e in storage._open(sharedrepo.vfs, _newestfirst=False)
                 if sharednamespaces.get(e.namespace) in sharedfeatures
             )
             for entry in _mergeentriesiter(local, shared, order=min):
                 storage._write(repo.vfs, entry)
 
     return orig(ui, repo, repopath)
 
 
 class journalentry(
     collections.namedtuple(
         r'journalentry',
         r'timestamp user command namespace name oldhashes newhashes',
     )
 ):
     """Individual journal entry
 
     * timestamp: a mercurial (time, timezone) tuple
     * user: the username that ran the command
     * namespace: the entry namespace, an opaque string
     * name: the name of the changed item, opaque string with meaning in the
       namespace
     * command: the hg command that triggered this record
     * oldhashes: a tuple of one or more binary hashes for the old location
     * newhashes: a tuple of one or more binary hashes for the new location
 
     Handles serialisation from and to the storage format. Fields are
     separated by newlines, hashes are written out in hex separated by commas,
     timestamp and timezone are separated by a space.
 
     """
 
     @classmethod
     def fromstorage(cls, line):
         (
             time,
             user,
             command,
             namespace,
             name,
             oldhashes,
             newhashes,
         ) = line.split(b'\n')
         timestamp, tz = time.split()
         timestamp, tz = float(timestamp), int(tz)
         oldhashes = tuple(node.bin(hash) for hash in oldhashes.split(b','))
         newhashes = tuple(node.bin(hash) for hash in newhashes.split(b','))
         return cls(
             (timestamp, tz),
             user,
             command,
             namespace,
             name,
             oldhashes,
             newhashes,
         )
 
     def __bytes__(self):
         """bytes representation for storage"""
         time = b' '.join(map(pycompat.bytestr, self.timestamp))
         oldhashes = b','.join([node.hex(hash) for hash in self.oldhashes])
         newhashes = b','.join([node.hex(hash) for hash in self.newhashes])
         return b'\n'.join(
             (
                 time,
                 self.user,
                 self.command,
                 self.namespace,
                 self.name,
                 oldhashes,
                 newhashes,
             )
         )
 
     __str__ = encoding.strmethod(__bytes__)
 
 
 class journalstorage(object):
     """Storage for journal entries
 
     Entries are divided over two files; one with entries that pertain to the
     local working copy *only*, and one with entries that are shared across
     multiple working copies when shared using the share extension.
 
     Entries are stored with NUL bytes as separators. See the journalentry
     class for the per-entry structure.
 
     The file format starts with an integer version, delimited by a NUL.
 
     This storage uses a dedicated lock; this makes it easier to avoid issues
     with adding entries that added when the regular wlock is unlocked (e.g.
     the dirstate).
 
     """
 
     _currentcommand = ()
     _lockref = None
 
     def __init__(self, repo):
         self.user = procutil.getuser()
         self.ui = repo.ui
         self.vfs = repo.vfs
 
         # is this working copy using a shared storage?
         self.sharedfeatures = self.sharedvfs = None
         if repo.shared():
             features = _readsharedfeatures(repo)
             sharedrepo = hg.sharedreposource(repo)
             if sharedrepo is not None and b'journal' in features:
                 self.sharedvfs = sharedrepo.vfs
                 self.sharedfeatures = features
 
     # track the current command for recording in journal entries
     @property
     def command(self):
         commandstr = b' '.join(
             map(procutil.shellquote, journalstorage._currentcommand)
         )
         if b'\n' in commandstr:
             # truncate multi-line commands
             commandstr = commandstr.partition(b'\n')[0] + b' ...'
         return commandstr
 
     @classmethod
     def recordcommand(cls, *fullargs):
         """Set the current hg arguments, stored with recorded entries"""
         # Set the current command on the class because we may have started
         # with a non-local repo (cloning for example).
         cls._currentcommand = fullargs
 
     def _currentlock(self, lockref):
         """Returns the lock if it's held, or None if it's not.
 
         (This is copied from the localrepo class)
         """
         if lockref is None:
             return None
         l = lockref()
         if l is None or not l.held:
             return None
         return l
 
     def jlock(self, vfs):
         """Create a lock for the journal file"""
         if self._currentlock(self._lockref) is not None:
             raise error.Abort(_(b'journal lock does not support nesting'))
         desc = _(b'journal of %s') % vfs.base
         try:
             l = lock.lock(vfs, b'namejournal.lock', 0, desc=desc)
         except error.LockHeld as inst:
             self.ui.warn(
                 _(b"waiting for lock on %s held by %r\n") % (desc, inst.locker)
             )
             # default to 600 seconds timeout
             l = lock.lock(
                 vfs,
                 b'namejournal.lock',
                 self.ui.configint(b"ui", b"timeout"),
                 desc=desc,
             )
             self.ui.warn(_(b"got lock after %s seconds\n") % l.delay)
         self._lockref = weakref.ref(l)
         return l
 
     def record(self, namespace, name, oldhashes, newhashes):
         """Record a new journal entry
 
         * namespace: an opaque string; this can be used to filter on the type
           of recorded entries.
         * name: the name defining this entry; for bookmarks, this is the
           bookmark name. Can be filtered on when retrieving entries.
         * oldhashes and newhashes: each a single binary hash, or a list of
           binary hashes. These represent the old and new position of the named
           item.
 
         """
         if not isinstance(oldhashes, list):
             oldhashes = [oldhashes]
         if not isinstance(newhashes, list):
             newhashes = [newhashes]
 
         entry = journalentry(
             dateutil.makedate(),
             self.user,
             self.command,
             namespace,
             name,
             oldhashes,
             newhashes,
         )
 
         vfs = self.vfs
         if self.sharedvfs is not None:
             # write to the shared repository if this feature is being
             # shared between working copies.
             if sharednamespaces.get(namespace) in self.sharedfeatures:
                 vfs = self.sharedvfs
 
         self._write(vfs, entry)
 
     def _write(self, vfs, entry):
         with self.jlock(vfs):
             # open file in amend mode to ensure it is created if missing
             with vfs(b'namejournal', mode=b'a+b') as f:
                 f.seek(0, os.SEEK_SET)
                 # Read just enough bytes to get a version number (up to 2
                 # digits plus separator)
                 version = f.read(3).partition(b'\0')[0]
                 if version and version != b"%d" % storageversion:
                     # different version of the storage. Exit early (and not
                     # write anything) if this is not a version we can handle or
                     # the file is corrupt. In future, perhaps rotate the file
                     # instead?
                     self.ui.warn(
                         _(b"unsupported journal file version '%s'\n") % version
                     )
                     return
                 if not version:
                     # empty file, write version first
                     f.write((b"%d" % storageversion) + b'\0')
                 f.seek(0, os.SEEK_END)
                 f.write(bytes(entry) + b'\0')
 
     def filtered(self, namespace=None, name=None):
         """Yield all journal entries with the given namespace or name
 
         Both the namespace and the name are optional; if neither is given all
         entries in the journal are produced.
 
         Matching supports regular expressions by using the `re:` prefix
         (use `literal:` to match names or namespaces that start with `re:`)
 
         """
         if namespace is not None:
             namespace = stringutil.stringmatcher(namespace)[-1]
         if name is not None:
             name = stringutil.stringmatcher(name)[-1]
         for entry in self:
             if namespace is not None and not namespace(entry.namespace):
                 continue
             if name is not None and not name(entry.name):
                 continue
             yield entry
 
     def __iter__(self):
         """Iterate over the storage
 
         Yields journalentry instances for each contained journal record.
 
         """
         local = self._open(self.vfs)
 
         if self.sharedvfs is None:
             return local
 
         # iterate over both local and shared entries, but only those
         # shared entries that are among the currently shared features
         shared = (
             e
             for e in self._open(self.sharedvfs)
             if sharednamespaces.get(e.namespace) in self.sharedfeatures
         )
         return _mergeentriesiter(local, shared)
 
     def _open(self, vfs, filename=b'namejournal', _newestfirst=True):
         if not vfs.exists(filename):
             return
 
         with vfs(filename) as f:
             raw = f.read()
 
         lines = raw.split(b'\0')
         version = lines and lines[0]
         if version != b"%d" % storageversion:
             version = version or _(b'not available')
             raise error.Abort(_(b"unknown journal file version '%s'") % version)
 
         # Skip the first line, it's a version number. Normally we iterate over
         # these in reverse order to list newest first; only when copying across
         # a shared storage do we forgo reversing.
         lines = lines[1:]
         if _newestfirst:
             lines = reversed(lines)
         for line in lines:
             if not line:
                 continue
             yield journalentry.fromstorage(line)
 
 
 # journal reading
 # log options that don't make sense for journal
 _ignoreopts = (b'no-merges', b'graph')
 
 
 @command(
     b'journal',
     [
         (b'', b'all', None, b'show history for all names'),
         (b'c', b'commits', None, b'show commit metadata'),
     ]
     + [opt for opt in cmdutil.logopts if opt[1] not in _ignoreopts],
     b'[OPTION]... [BOOKMARKNAME]',
     helpcategory=command.CATEGORY_CHANGE_ORGANIZATION,
 )
 def journal(ui, repo, *args, **opts):
     """show the previous position of bookmarks and the working copy
 
     The journal is used to see the previous commits that bookmarks and the
     working copy pointed to. By default the previous locations for the working
     copy.  Passing a bookmark name will show all the previous positions of
     that bookmark. Use the --all switch to show previous locations for all
     bookmarks and the working copy; each line will then include the bookmark
     name, or '.' for the working copy, as well.
 
     If `name` starts with `re:`, the remainder of the name is treated as
     a regular expression. To match a name that actually starts with `re:`,
     use the prefix `literal:`.
 
     By default hg journal only shows the commit hash and the command that was
     running at that time. -v/--verbose will show the prior hash, the user, and
     the time at which it happened.
 
     Use -c/--commits to output log information on each commit hash; at this
     point you can use the usual `--patch`, `--git`, `--stat` and `--template`
     switches to alter the log output for these.
 
     `hg journal -T json` can be used to produce machine readable output.
 
     """
     opts = pycompat.byteskwargs(opts)
     name = b'.'
     if opts.get(b'all'):
         if args:
             raise error.Abort(
                 _(b"You can't combine --all and filtering on a name")
             )
         name = None
     if args:
         name = args[0]
 
     fm = ui.formatter(b'journal', opts)
 
     def formatnodes(nodes):
         return fm.formatlist(map(fm.hexfunc, nodes), name=b'node', sep=b',')
 
     if opts.get(b"template") != b"json":
         if name is None:
             displayname = _(b'the working copy and bookmarks')
         else:
             displayname = b"'%s'" % name
         ui.status(_(b"previous locations of %s:\n") % displayname)
 
     limit = logcmdutil.getlimit(opts)
     entry = None
     ui.pager(b'journal')
     for count, entry in enumerate(repo.journal.filtered(name=name)):
         if count == limit:
             break
 
         fm.startitem()
         fm.condwrite(
             ui.verbose, b'oldnodes', b'%s -> ', formatnodes(entry.oldhashes)
         )
         fm.write(b'newnodes', b'%s', formatnodes(entry.newhashes))
         fm.condwrite(ui.verbose, b'user', b' %-8s', entry.user)
         fm.condwrite(
             opts.get(b'all') or name.startswith(b're:'),
             b'name',
             b'  %-8s',
             entry.name,
         )
 
         fm.condwrite(
             ui.verbose,
             b'date',
             b' %s',
             fm.formatdate(entry.timestamp, b'%Y-%m-%d %H:%M %1%2'),
         )
         fm.write(b'command', b'  %s\n', entry.command)
 
         if opts.get(b"commits"):
             if fm.isplain():
                 displayer = logcmdutil.changesetdisplayer(ui, repo, opts)
             else:
                 displayer = logcmdutil.changesetformatter(
                     ui, repo, fm.nested(b'changesets'), diffopts=opts
                 )
             for hash in entry.newhashes:
                 try:
                     ctx = repo[hash]
                     displayer.show(ctx)
                 except error.RepoLookupError as e:
                     fm.plain(b"%s\n\n" % pycompat.bytestr(e))
             displayer.close()
 
     fm.end()
 
     if entry is None:
         ui.status(_(b"no recorded locations\n"))

hgext/lfs/wireprotolfsserver.py

@@ -1,370 +1,370 b''
 # wireprotolfsserver.py - lfs protocol server side implementation
 #
 # Copyright 2018 Matt Harbison <[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 datetime
 import errno
 import json
 import traceback
 
 from mercurial.hgweb import common as hgwebcommon
 
 from mercurial import (
     exthelper,
     pycompat,
     util,
     wireprotoserver,
 )
 
 from . import blobstore
 
 HTTP_OK = hgwebcommon.HTTP_OK
 HTTP_CREATED = hgwebcommon.HTTP_CREATED
 HTTP_BAD_REQUEST = hgwebcommon.HTTP_BAD_REQUEST
 HTTP_NOT_FOUND = hgwebcommon.HTTP_NOT_FOUND
 HTTP_METHOD_NOT_ALLOWED = hgwebcommon.HTTP_METHOD_NOT_ALLOWED
 HTTP_NOT_ACCEPTABLE = hgwebcommon.HTTP_NOT_ACCEPTABLE
 HTTP_UNSUPPORTED_MEDIA_TYPE = hgwebcommon.HTTP_UNSUPPORTED_MEDIA_TYPE
 
 eh = exthelper.exthelper()
 
 
 @eh.wrapfunction(wireprotoserver, b'handlewsgirequest')
 def handlewsgirequest(orig, rctx, req, res, checkperm):
     """Wrap wireprotoserver.handlewsgirequest() to possibly process an LFS
     request if it is left unprocessed by the wrapped method.
     """
     if orig(rctx, req, res, checkperm):
         return True
 
     if not rctx.repo.ui.configbool(b'experimental', b'lfs.serve'):
         return False
 
-    if not util.safehasattr(rctx.repo.svfs, b'lfslocalblobstore'):
+    if not util.safehasattr(rctx.repo.svfs, 'lfslocalblobstore'):
         return False
 
     if not req.dispatchpath:
         return False
 
     try:
         if req.dispatchpath == b'.git/info/lfs/objects/batch':
             checkperm(rctx, req, b'pull')
             return _processbatchrequest(rctx.repo, req, res)
         # TODO: reserve and use a path in the proposed http wireprotocol /api/
         #       namespace?
         elif req.dispatchpath.startswith(b'.hg/lfs/objects'):
             return _processbasictransfer(
                 rctx.repo, req, res, lambda perm: checkperm(rctx, req, perm)
             )
         return False
     except hgwebcommon.ErrorResponse as e:
         # XXX: copied from the handler surrounding wireprotoserver._callhttp()
         #      in the wrapped function.  Should this be moved back to hgweb to
         #      be a common handler?
         for k, v in e.headers:
             res.headers[k] = v
         res.status = hgwebcommon.statusmessage(e.code, pycompat.bytestr(e))
         res.setbodybytes(b'0\n%s\n' % pycompat.bytestr(e))
         return True
 
 
 def _sethttperror(res, code, message=None):
     res.status = hgwebcommon.statusmessage(code, message=message)
     res.headers[b'Content-Type'] = b'text/plain; charset=utf-8'
     res.setbodybytes(b'')
 
 
 def _logexception(req):
     """Write information about the current exception to wsgi.errors."""
     tb = pycompat.sysbytes(traceback.format_exc())
     errorlog = req.rawenv[b'wsgi.errors']
 
     uri = b''
     if req.apppath:
         uri += req.apppath
     uri += b'/' + req.dispatchpath
 
     errorlog.write(
         b"Exception happened while processing request '%s':\n%s" % (uri, tb)
     )
 
 
 def _processbatchrequest(repo, req, res):
     """Handle a request for the Batch API, which is the gateway to granting file
     access.
 
     https://github.com/git-lfs/git-lfs/blob/master/docs/api/batch.md
     """
 
     # Mercurial client request:
     #
     #   HOST: localhost:$HGPORT
     #   ACCEPT: application/vnd.git-lfs+json
     #   ACCEPT-ENCODING: identity
     #   USER-AGENT: git-lfs/2.3.4 (Mercurial 4.5.2+1114-f48b9754f04c+20180316)
     #   Content-Length: 125
     #   Content-Type: application/vnd.git-lfs+json
     #
     #   {
     #     "objects": [
     #       {
     #         "oid": "31cf...8e5b"
     #         "size": 12
     #       }
     #     ]
     #     "operation": "upload"
     #  }
 
     if req.method != b'POST':
         _sethttperror(res, HTTP_METHOD_NOT_ALLOWED)
         return True
 
     if req.headers[b'Content-Type'] != b'application/vnd.git-lfs+json':
         _sethttperror(res, HTTP_UNSUPPORTED_MEDIA_TYPE)
         return True
 
     if req.headers[b'Accept'] != b'application/vnd.git-lfs+json':
         _sethttperror(res, HTTP_NOT_ACCEPTABLE)
         return True
 
     # XXX: specify an encoding?
     lfsreq = json.loads(req.bodyfh.read())
 
     # If no transfer handlers are explicitly requested, 'basic' is assumed.
     if r'basic' not in lfsreq.get(r'transfers', [r'basic']):
         _sethttperror(
             res,
             HTTP_BAD_REQUEST,
             b'Only the basic LFS transfer handler is supported',
         )
         return True
 
     operation = lfsreq.get(r'operation')
     operation = pycompat.bytestr(operation)
 
     if operation not in (b'upload', b'download'):
         _sethttperror(
             res,
             HTTP_BAD_REQUEST,
             b'Unsupported LFS transfer operation: %s' % operation,
         )
         return True
 
     localstore = repo.svfs.lfslocalblobstore
 
     objects = [
         p
         for p in _batchresponseobjects(
             req, lfsreq.get(r'objects', []), operation, localstore
         )
     ]
 
     rsp = {
         r'transfer': r'basic',
         r'objects': objects,
     }
 
     res.status = hgwebcommon.statusmessage(HTTP_OK)
     res.headers[b'Content-Type'] = b'application/vnd.git-lfs+json'
     res.setbodybytes(pycompat.bytestr(json.dumps(rsp)))
 
     return True
 
 
 def _batchresponseobjects(req, objects, action, store):
     """Yield one dictionary of attributes for the Batch API response for each
     object in the list.
 
     req: The parsedrequest for the Batch API request
     objects: The list of objects in the Batch API object request list
     action: 'upload' or 'download'
     store: The local blob store for servicing requests"""
 
     # Successful lfs-test-server response to solict an upload:
     # {
     #    u'objects': [{
     #       u'size': 12,
     #       u'oid': u'31cf...8e5b',
     #       u'actions': {
     #           u'upload': {
     #               u'href': u'http://localhost:$HGPORT/objects/31cf...8e5b',
     #               u'expires_at': u'0001-01-01T00:00:00Z',
     #               u'header': {
     #                   u'Accept': u'application/vnd.git-lfs'
     #               }
     #           }
     #       }
     #    }]
     # }
 
     # TODO: Sort out the expires_at/expires_in/authenticated keys.
 
     for obj in objects:
         # Convert unicode to ASCII to create a filesystem path
         soid = obj.get(r'oid')
         oid = soid.encode(r'ascii')
         rsp = {
             r'oid': soid,
             r'size': obj.get(r'size'),  # XXX: should this check the local size?
             # r'authenticated': True,
         }
 
         exists = True
         verifies = False
 
         # Verify an existing file on the upload request, so that the client is
         # solicited to re-upload if it corrupt locally.  Download requests are
         # also verified, so the error can be flagged in the Batch API response.
         # (Maybe we can use this to short circuit the download for `hg verify`,
         # IFF the client can assert that the remote end is an hg server.)
         # Otherwise, it's potentially overkill on download, since it is also
         # verified as the file is streamed to the caller.
         try:
             verifies = store.verify(oid)
             if verifies and action == b'upload':
                 # The client will skip this upload, but make sure it remains
                 # available locally.
                 store.linkfromusercache(oid)
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 _logexception(req)
 
                 rsp[r'error'] = {
                     r'code': 500,
                     r'message': inst.strerror or r'Internal Server Server',
                 }
                 yield rsp
                 continue
 
             exists = False
 
         # Items are always listed for downloads.  They are dropped for uploads
         # IFF they already exist locally.
         if action == b'download':
             if not exists:
                 rsp[r'error'] = {
                     r'code': 404,
                     r'message': r"The object does not exist",
                 }
                 yield rsp
                 continue
 
             elif not verifies:
                 rsp[r'error'] = {
                     r'code': 422,  # XXX: is this the right code?
                     r'message': r"The object is corrupt",
                 }
                 yield rsp
                 continue
 
         elif verifies:
             yield rsp  # Skip 'actions': already uploaded
             continue
 
         expiresat = datetime.datetime.now() + datetime.timedelta(minutes=10)
 
         def _buildheader():
             # The spec doesn't mention the Accept header here, but avoid
             # a gratuitous deviation from lfs-test-server in the test
             # output.
             hdr = {r'Accept': r'application/vnd.git-lfs'}
 
             auth = req.headers.get(b'Authorization', b'')
             if auth.startswith(b'Basic '):
                 hdr[r'Authorization'] = pycompat.strurl(auth)
 
             return hdr
 
         rsp[r'actions'] = {
             r'%s'
             % pycompat.strurl(action): {
                 r'href': pycompat.strurl(
                     b'%s%s/.hg/lfs/objects/%s' % (req.baseurl, req.apppath, oid)
                 ),
                 # datetime.isoformat() doesn't include the 'Z' suffix
                 r"expires_at": expiresat.strftime(r'%Y-%m-%dT%H:%M:%SZ'),
                 r'header': _buildheader(),
             }
         }
 
         yield rsp
 
 
 def _processbasictransfer(repo, req, res, checkperm):
     """Handle a single file upload (PUT) or download (GET) action for the Basic
     Transfer Adapter.
 
     After determining if the request is for an upload or download, the access
     must be checked by calling ``checkperm()`` with either 'pull' or 'upload'
     before accessing the files.
 
     https://github.com/git-lfs/git-lfs/blob/master/docs/api/basic-transfers.md
     """
 
     method = req.method
     oid = req.dispatchparts[-1]
     localstore = repo.svfs.lfslocalblobstore
 
     if len(req.dispatchparts) != 4:
         _sethttperror(res, HTTP_NOT_FOUND)
         return True
 
     if method == b'PUT':
         checkperm(b'upload')
 
         # TODO: verify Content-Type?
 
         existed = localstore.has(oid)
 
         # TODO: how to handle timeouts?  The body proxy handles limiting to
         #       Content-Length, but what happens if a client sends less than it
         #       says it will?
 
         statusmessage = hgwebcommon.statusmessage
         try:
             localstore.download(oid, req.bodyfh)
             res.status = statusmessage(HTTP_OK if existed else HTTP_CREATED)
         except blobstore.LfsCorruptionError:
             _logexception(req)
 
             # XXX: Is this the right code?
             res.status = statusmessage(422, b'corrupt blob')
 
         # There's no payload here, but this is the header that lfs-test-server
         # sends back.  This eliminates some gratuitous test output conditionals.
         res.headers[b'Content-Type'] = b'text/plain; charset=utf-8'
         res.setbodybytes(b'')
 
         return True
     elif method == b'GET':
         checkperm(b'pull')
 
         res.status = hgwebcommon.statusmessage(HTTP_OK)
         res.headers[b'Content-Type'] = b'application/octet-stream'
 
         try:
             # TODO: figure out how to send back the file in chunks, instead of
             #       reading the whole thing.  (Also figure out how to send back
             #       an error status if an IOError occurs after a partial write
             #       in that case.  Here, everything is read before starting.)
             res.setbodybytes(localstore.read(oid))
         except blobstore.LfsCorruptionError:
             _logexception(req)
 
             # XXX: Is this the right code?
             res.status = hgwebcommon.statusmessage(422, b'corrupt blob')
             res.setbodybytes(b'')
 
         return True
     else:
         _sethttperror(
             res,
             HTTP_METHOD_NOT_ALLOWED,
             message=b'Unsupported LFS transfer method: %s' % method,
         )
         return True

hgext/narrow/narrowbundle2.py

@@ -1,360 +1,360 b''
 # narrowbundle2.py - bundle2 extensions for narrow repository support
 #
 # Copyright 2017 Google, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import struct
 
 from mercurial.i18n import _
 from mercurial.node import (
     bin,
     nullid,
 )
 from mercurial import (
     bundle2,
     changegroup,
     error,
     exchange,
     localrepo,
     narrowspec,
     repair,
     util,
     wireprototypes,
 )
 from mercurial.interfaces import repository
 from mercurial.utils import stringutil
 
 _NARROWACL_SECTION = b'narrowacl'
 _CHANGESPECPART = b'narrow:changespec'
 _RESSPECS = b'narrow:responsespec'
 _SPECPART = b'narrow:spec'
 _SPECPART_INCLUDE = b'include'
 _SPECPART_EXCLUDE = b'exclude'
 _KILLNODESIGNAL = b'KILL'
 _DONESIGNAL = b'DONE'
 _ELIDEDCSHEADER = b'>20s20s20sl'  # cset id, p1, p2, len(text)
 _ELIDEDMFHEADER = b'>20s20s20s20sl'  # manifest id, p1, p2, link id, len(text)
 _CSHEADERSIZE = struct.calcsize(_ELIDEDCSHEADER)
 _MFHEADERSIZE = struct.calcsize(_ELIDEDMFHEADER)
 
 # Serve a changegroup for a client with a narrow clone.
 def getbundlechangegrouppart_narrow(
     bundler,
     repo,
     source,
     bundlecaps=None,
     b2caps=None,
     heads=None,
     common=None,
     **kwargs
 ):
     assert repo.ui.configbool(b'experimental', b'narrowservebrokenellipses')
 
     cgversions = b2caps.get(b'changegroup')
     cgversions = [
         v
         for v in cgversions
         if v in changegroup.supportedoutgoingversions(repo)
     ]
     if not cgversions:
         raise ValueError(_(b'no common changegroup version'))
     version = max(cgversions)
 
     oldinclude = sorted(filter(bool, kwargs.get(r'oldincludepats', [])))
     oldexclude = sorted(filter(bool, kwargs.get(r'oldexcludepats', [])))
     newinclude = sorted(filter(bool, kwargs.get(r'includepats', [])))
     newexclude = sorted(filter(bool, kwargs.get(r'excludepats', [])))
     known = {bin(n) for n in kwargs.get(r'known', [])}
     generateellipsesbundle2(
         bundler,
         repo,
         oldinclude,
         oldexclude,
         newinclude,
         newexclude,
         version,
         common,
         heads,
         known,
         kwargs.get(r'depth', None),
     )
 
 
 def generateellipsesbundle2(
     bundler,
     repo,
     oldinclude,
     oldexclude,
     newinclude,
     newexclude,
     version,
     common,
     heads,
     known,
     depth,
 ):
     newmatch = narrowspec.match(
         repo.root, include=newinclude, exclude=newexclude
     )
     if depth is not None:
         depth = int(depth)
         if depth < 1:
             raise error.Abort(_(b'depth must be positive, got %d') % depth)
 
     heads = set(heads or repo.heads())
     common = set(common or [nullid])
     if known and (oldinclude != newinclude or oldexclude != newexclude):
         # Steps:
         # 1. Send kill for "$known & ::common"
         #
         # 2. Send changegroup for ::common
         #
         # 3. Proceed.
         #
         # In the future, we can send kills for only the specific
         # nodes we know should go away or change shape, and then
         # send a data stream that tells the client something like this:
         #
         # a) apply this changegroup
         # b) apply nodes XXX, YYY, ZZZ that you already have
         # c) goto a
         #
         # until they've built up the full new state.
         # Convert to revnums and intersect with "common". The client should
         # have made it a subset of "common" already, but let's be safe.
         known = set(repo.revs(b"%ln & ::%ln", known, common))
         # TODO: we could send only roots() of this set, and the
         # list of nodes in common, and the client could work out
         # what to strip, instead of us explicitly sending every
         # single node.
         deadrevs = known
 
         def genkills():
             for r in deadrevs:
                 yield _KILLNODESIGNAL
                 yield repo.changelog.node(r)
             yield _DONESIGNAL
 
         bundler.newpart(_CHANGESPECPART, data=genkills())
         newvisit, newfull, newellipsis = exchange._computeellipsis(
             repo, set(), common, known, newmatch
         )
         if newvisit:
             packer = changegroup.getbundler(
                 version,
                 repo,
                 matcher=newmatch,
                 ellipses=True,
                 shallow=depth is not None,
                 ellipsisroots=newellipsis,
                 fullnodes=newfull,
             )
             cgdata = packer.generate(common, newvisit, False, b'narrow_widen')
 
             part = bundler.newpart(b'changegroup', data=cgdata)
             part.addparam(b'version', version)
             if b'treemanifest' in repo.requirements:
                 part.addparam(b'treemanifest', b'1')
 
     visitnodes, relevant_nodes, ellipsisroots = exchange._computeellipsis(
         repo, common, heads, set(), newmatch, depth=depth
     )
 
     repo.ui.debug(b'Found %d relevant revs\n' % len(relevant_nodes))
     if visitnodes:
         packer = changegroup.getbundler(
             version,
             repo,
             matcher=newmatch,
             ellipses=True,
             shallow=depth is not None,
             ellipsisroots=ellipsisroots,
             fullnodes=relevant_nodes,
         )
         cgdata = packer.generate(common, visitnodes, False, b'narrow_widen')
 
         part = bundler.newpart(b'changegroup', data=cgdata)
         part.addparam(b'version', version)
         if b'treemanifest' in repo.requirements:
             part.addparam(b'treemanifest', b'1')
 
 
 @bundle2.parthandler(_SPECPART, (_SPECPART_INCLUDE, _SPECPART_EXCLUDE))
 def _handlechangespec_2(op, inpart):
     # XXX: This bundle2 handling is buggy and should be removed after hg5.2 is
     # released. New servers will send a mandatory bundle2 part named
     # 'Narrowspec' and will send specs as data instead of params.
     # Refer to issue5952 and 6019
     includepats = set(inpart.params.get(_SPECPART_INCLUDE, b'').splitlines())
     excludepats = set(inpart.params.get(_SPECPART_EXCLUDE, b'').splitlines())
     narrowspec.validatepatterns(includepats)
     narrowspec.validatepatterns(excludepats)
 
     if not repository.NARROW_REQUIREMENT in op.repo.requirements:
         op.repo.requirements.add(repository.NARROW_REQUIREMENT)
         op.repo._writerequirements()
     op.repo.setnarrowpats(includepats, excludepats)
     narrowspec.copytoworkingcopy(op.repo)
 
 
 @bundle2.parthandler(_RESSPECS)
 def _handlenarrowspecs(op, inpart):
     data = inpart.read()
     inc, exc = data.split(b'\0')
     includepats = set(inc.splitlines())
     excludepats = set(exc.splitlines())
     narrowspec.validatepatterns(includepats)
     narrowspec.validatepatterns(excludepats)
 
     if repository.NARROW_REQUIREMENT not in op.repo.requirements:
         op.repo.requirements.add(repository.NARROW_REQUIREMENT)
         op.repo._writerequirements()
     op.repo.setnarrowpats(includepats, excludepats)
     narrowspec.copytoworkingcopy(op.repo)
 
 
 @bundle2.parthandler(_CHANGESPECPART)
 def _handlechangespec(op, inpart):
     repo = op.repo
     cl = repo.changelog
 
     # changesets which need to be stripped entirely. either they're no longer
     # needed in the new narrow spec, or the server is sending a replacement
     # in the changegroup part.
     clkills = set()
 
     # A changespec part contains all the updates to ellipsis nodes
     # that will happen as a result of widening or narrowing a
     # repo. All the changes that this block encounters are ellipsis
     # nodes or flags to kill an existing ellipsis.
     chunksignal = changegroup.readexactly(inpart, 4)
     while chunksignal != _DONESIGNAL:
         if chunksignal == _KILLNODESIGNAL:
             # a node used to be an ellipsis but isn't anymore
             ck = changegroup.readexactly(inpart, 20)
             if cl.hasnode(ck):
                 clkills.add(ck)
         else:
             raise error.Abort(
                 _(b'unexpected changespec node chunk type: %s') % chunksignal
             )
         chunksignal = changegroup.readexactly(inpart, 4)
 
     if clkills:
         # preserve bookmarks that repair.strip() would otherwise strip
         op._bookmarksbackup = repo._bookmarks
 
         class dummybmstore(dict):
             def applychanges(self, repo, tr, changes):
                 pass
 
         localrepo.localrepository._bookmarks.set(repo, dummybmstore())
         chgrpfile = repair.strip(
             op.ui, repo, list(clkills), backup=True, topic=b'widen'
         )
         if chgrpfile:
             op._widen_uninterr = repo.ui.uninterruptible()
             op._widen_uninterr.__enter__()
             # presence of _widen_bundle attribute activates widen handler later
             op._widen_bundle = chgrpfile
     # Set the new narrowspec if we're widening. The setnewnarrowpats() method
     # will currently always be there when using the core+narrowhg server, but
     # other servers may include a changespec part even when not widening (e.g.
     # because we're deepening a shallow repo).
-    if util.safehasattr(repo, b'setnewnarrowpats'):
+    if util.safehasattr(repo, 'setnewnarrowpats'):
         repo.setnewnarrowpats()
 
 
 def handlechangegroup_widen(op, inpart):
     """Changegroup exchange handler which restores temporarily-stripped nodes"""
     # We saved a bundle with stripped node data we must now restore.
     # This approach is based on mercurial/repair.py@6ee26a53c111.
     repo = op.repo
     ui = op.ui
 
     chgrpfile = op._widen_bundle
     del op._widen_bundle
     vfs = repo.vfs
 
     ui.note(_(b"adding branch\n"))
     f = vfs.open(chgrpfile, b"rb")
     try:
         gen = exchange.readbundle(ui, f, chgrpfile, vfs)
         # silence internal shuffling chatter
         override = {(b'ui', b'quiet'): True}
         if ui.verbose:
             override = {}
         with ui.configoverride(override):
             if isinstance(gen, bundle2.unbundle20):
                 with repo.transaction(b'strip') as tr:
                     bundle2.processbundle(repo, gen, lambda: tr)
             else:
                 gen.apply(
                     repo, b'strip', b'bundle:' + vfs.join(chgrpfile), True
                 )
     finally:
         f.close()
 
     # remove undo files
     for undovfs, undofile in repo.undofiles():
         try:
             undovfs.unlink(undofile)
         except OSError as e:
             if e.errno != errno.ENOENT:
                 ui.warn(
                     _(b'error removing %s: %s\n')
                     % (undovfs.join(undofile), stringutil.forcebytestr(e))
                 )
 
     # Remove partial backup only if there were no exceptions
     op._widen_uninterr.__exit__(None, None, None)
     vfs.unlink(chgrpfile)
 
 
 def setup():
     """Enable narrow repo support in bundle2-related extension points."""
     getbundleargs = wireprototypes.GETBUNDLE_ARGUMENTS
 
     getbundleargs[b'narrow'] = b'boolean'
     getbundleargs[b'depth'] = b'plain'
     getbundleargs[b'oldincludepats'] = b'csv'
     getbundleargs[b'oldexcludepats'] = b'csv'
     getbundleargs[b'known'] = b'csv'
 
     # Extend changegroup serving to handle requests from narrow clients.
     origcgfn = exchange.getbundle2partsmapping[b'changegroup']
 
     def wrappedcgfn(*args, **kwargs):
         repo = args[1]
         if repo.ui.has_section(_NARROWACL_SECTION):
             kwargs = exchange.applynarrowacl(repo, kwargs)
 
         if kwargs.get(r'narrow', False) and repo.ui.configbool(
             b'experimental', b'narrowservebrokenellipses'
         ):
             getbundlechangegrouppart_narrow(*args, **kwargs)
         else:
             origcgfn(*args, **kwargs)
 
     exchange.getbundle2partsmapping[b'changegroup'] = wrappedcgfn
 
     # Extend changegroup receiver so client can fixup after widen requests.
     origcghandler = bundle2.parthandlermapping[b'changegroup']
 
     def wrappedcghandler(op, inpart):
         origcghandler(op, inpart)
-        if util.safehasattr(op, b'_widen_bundle'):
+        if util.safehasattr(op, '_widen_bundle'):
             handlechangegroup_widen(op, inpart)
-        if util.safehasattr(op, b'_bookmarksbackup'):
+        if util.safehasattr(op, '_bookmarksbackup'):
             localrepo.localrepository._bookmarks.set(
                 op.repo, op._bookmarksbackup
             )
             del op._bookmarksbackup
 
     wrappedcghandler.params = origcghandler.params
     bundle2.parthandlermapping[b'changegroup'] = wrappedcghandler

hgext/remotefilelog/connectionpool.py

@@ -1,88 +1,88 b''
 # connectionpool.py - class for pooling peer connections for reuse
 #
 # Copyright 2017 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 from mercurial import (
     extensions,
     hg,
     pycompat,
     sshpeer,
     util,
 )
 
 _sshv1peer = sshpeer.sshv1peer
 
 
 class connectionpool(object):
     def __init__(self, repo):
         self._repo = repo
         self._pool = dict()
 
     def get(self, path):
         pathpool = self._pool.get(path)
         if pathpool is None:
             pathpool = list()
             self._pool[path] = pathpool
 
         conn = None
         if len(pathpool) > 0:
             try:
                 conn = pathpool.pop()
                 peer = conn.peer
                 # If the connection has died, drop it
                 if isinstance(peer, _sshv1peer):
                     if peer._subprocess.poll() is not None:
                         conn = None
             except IndexError:
                 pass
 
         if conn is None:
 
             def _cleanup(orig):
                 # close pipee first so peer.cleanup reading it won't deadlock,
                 # if there are other processes with pipeo open (i.e. us).
                 peer = orig.im_self
-                if util.safehasattr(peer, b'pipee'):
+                if util.safehasattr(peer, 'pipee'):
                     peer.pipee.close()
                 return orig()
 
             peer = hg.peer(self._repo.ui, {}, path)
-            if util.safehasattr(peer, b'cleanup'):
+            if util.safehasattr(peer, 'cleanup'):
                 extensions.wrapfunction(peer, b'cleanup', _cleanup)
 
             conn = connection(pathpool, peer)
 
         return conn
 
     def close(self):
         for pathpool in pycompat.itervalues(self._pool):
             for conn in pathpool:
                 conn.close()
             del pathpool[:]
 
 
 class connection(object):
     def __init__(self, pool, peer):
         self._pool = pool
         self.peer = peer
 
     def __enter__(self):
         return self
 
     def __exit__(self, type, value, traceback):
         # Only add the connection back to the pool if there was no exception,
         # since an exception could mean the connection is not in a reusable
         # state.
         if type is None:
             self._pool.append(self)
         else:
             self.close()
 
     def close(self):
-        if util.safehasattr(self.peer, b'cleanup'):
+        if util.safehasattr(self.peer, 'cleanup'):
             self.peer.cleanup()

hgext/remotefilelog/fileserverclient.py

@@ -1,667 +1,667 b''
 # fileserverclient.py - client for communicating with the cache process
 #
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import hashlib
 import io
 import os
 import threading
 import time
 import zlib
 
 from mercurial.i18n import _
 from mercurial.node import bin, hex, nullid
 from mercurial import (
     error,
     node,
     pycompat,
     revlog,
     sshpeer,
     util,
     wireprotov1peer,
 )
 from mercurial.utils import procutil
 
 from . import (
     constants,
     contentstore,
     metadatastore,
 )
 
 _sshv1peer = sshpeer.sshv1peer
 
 # Statistics for debugging
 fetchcost = 0
 fetches = 0
 fetched = 0
 fetchmisses = 0
 
 _lfsmod = None
 
 
 def getcachekey(reponame, file, id):
     pathhash = node.hex(hashlib.sha1(file).digest())
     return os.path.join(reponame, pathhash[:2], pathhash[2:], id)
 
 
 def getlocalkey(file, id):
     pathhash = node.hex(hashlib.sha1(file).digest())
     return os.path.join(pathhash, id)
 
 
 def peersetup(ui, peer):
     class remotefilepeer(peer.__class__):
         @wireprotov1peer.batchable
         def x_rfl_getfile(self, file, node):
             if not self.capable(b'x_rfl_getfile'):
                 raise error.Abort(
                     b'configured remotefile server does not support getfile'
                 )
             f = wireprotov1peer.future()
             yield {b'file': file, b'node': node}, f
             code, data = f.value.split(b'\0', 1)
             if int(code):
                 raise error.LookupError(file, node, data)
             yield data
 
         @wireprotov1peer.batchable
         def x_rfl_getflogheads(self, path):
             if not self.capable(b'x_rfl_getflogheads'):
                 raise error.Abort(
                     b'configured remotefile server does not '
                     b'support getflogheads'
                 )
             f = wireprotov1peer.future()
             yield {b'path': path}, f
             heads = f.value.split(b'\n') if f.value else []
             yield heads
 
         def _updatecallstreamopts(self, command, opts):
             if command != b'getbundle':
                 return
             if (
                 constants.NETWORK_CAP_LEGACY_SSH_GETFILES
                 not in self.capabilities()
             ):
                 return
-            if not util.safehasattr(self, b'_localrepo'):
+            if not util.safehasattr(self, '_localrepo'):
                 return
             if (
                 constants.SHALLOWREPO_REQUIREMENT
                 not in self._localrepo.requirements
             ):
                 return
 
             bundlecaps = opts.get(b'bundlecaps')
             if bundlecaps:
                 bundlecaps = [bundlecaps]
             else:
                 bundlecaps = []
 
             # shallow, includepattern, and excludepattern are a hacky way of
             # carrying over data from the local repo to this getbundle
             # command. We need to do it this way because bundle1 getbundle
             # doesn't provide any other place we can hook in to manipulate
             # getbundle args before it goes across the wire. Once we get rid
             # of bundle1, we can use bundle2's _pullbundle2extraprepare to
             # do this more cleanly.
             bundlecaps.append(constants.BUNDLE2_CAPABLITY)
             if self._localrepo.includepattern:
                 patterns = b'\0'.join(self._localrepo.includepattern)
                 includecap = b"includepattern=" + patterns
                 bundlecaps.append(includecap)
             if self._localrepo.excludepattern:
                 patterns = b'\0'.join(self._localrepo.excludepattern)
                 excludecap = b"excludepattern=" + patterns
                 bundlecaps.append(excludecap)
             opts[b'bundlecaps'] = b','.join(bundlecaps)
 
         def _sendrequest(self, command, args, **opts):
             self._updatecallstreamopts(command, args)
             return super(remotefilepeer, self)._sendrequest(
                 command, args, **opts
             )
 
         def _callstream(self, command, **opts):
             supertype = super(remotefilepeer, self)
-            if not util.safehasattr(supertype, b'_sendrequest'):
+            if not util.safehasattr(supertype, '_sendrequest'):
                 self._updatecallstreamopts(command, pycompat.byteskwargs(opts))
             return super(remotefilepeer, self)._callstream(command, **opts)
 
     peer.__class__ = remotefilepeer
 
 
 class cacheconnection(object):
     """The connection for communicating with the remote cache. Performs
     gets and sets by communicating with an external process that has the
     cache-specific implementation.
     """
 
     def __init__(self):
         self.pipeo = self.pipei = self.pipee = None
         self.subprocess = None
         self.connected = False
 
     def connect(self, cachecommand):
         if self.pipeo:
             raise error.Abort(_(b"cache connection already open"))
         self.pipei, self.pipeo, self.pipee, self.subprocess = procutil.popen4(
             cachecommand
         )
         self.connected = True
 
     def close(self):
         def tryclose(pipe):
             try:
                 pipe.close()
             except Exception:
                 pass
 
         if self.connected:
             try:
                 self.pipei.write(b"exit\n")
             except Exception:
                 pass
             tryclose(self.pipei)
             self.pipei = None
             tryclose(self.pipeo)
             self.pipeo = None
             tryclose(self.pipee)
             self.pipee = None
             try:
                 # Wait for process to terminate, making sure to avoid deadlock.
                 # See https://docs.python.org/2/library/subprocess.html for
                 # warnings about wait() and deadlocking.
                 self.subprocess.communicate()
             except Exception:
                 pass
             self.subprocess = None
         self.connected = False
 
     def request(self, request, flush=True):
         if self.connected:
             try:
                 self.pipei.write(request)
                 if flush:
                     self.pipei.flush()
             except IOError:
                 self.close()
 
     def receiveline(self):
         if not self.connected:
             return None
         try:
             result = self.pipeo.readline()[:-1]
             if not result:
                 self.close()
         except IOError:
             self.close()
 
         return result
 
 
 def _getfilesbatch(
     remote, receivemissing, progresstick, missed, idmap, batchsize
 ):
     # Over http(s), iterbatch is a streamy method and we can start
     # looking at results early. This means we send one (potentially
     # large) request, but then we show nice progress as we process
     # file results, rather than showing chunks of $batchsize in
     # progress.
     #
     # Over ssh, iterbatch isn't streamy because batch() wasn't
     # explicitly designed as a streaming method. In the future we
     # should probably introduce a streambatch() method upstream and
     # use that for this.
     with remote.commandexecutor() as e:
         futures = []
         for m in missed:
             futures.append(
                 e.callcommand(
                     b'x_rfl_getfile', {b'file': idmap[m], b'node': m[-40:]}
                 )
             )
 
         for i, m in enumerate(missed):
             r = futures[i].result()
             futures[i] = None  # release memory
             file_ = idmap[m]
             node = m[-40:]
             receivemissing(io.BytesIO(b'%d\n%s' % (len(r), r)), file_, node)
             progresstick()
 
 
 def _getfiles_optimistic(
     remote, receivemissing, progresstick, missed, idmap, step
 ):
     remote._callstream(b"x_rfl_getfiles")
     i = 0
     pipeo = remote._pipeo
     pipei = remote._pipei
     while i < len(missed):
         # issue a batch of requests
         start = i
         end = min(len(missed), start + step)
         i = end
         for missingid in missed[start:end]:
             # issue new request
             versionid = missingid[-40:]
             file = idmap[missingid]
             sshrequest = b"%s%s\n" % (versionid, file)
             pipeo.write(sshrequest)
         pipeo.flush()
 
         # receive batch results
         for missingid in missed[start:end]:
             versionid = missingid[-40:]
             file = idmap[missingid]
             receivemissing(pipei, file, versionid)
             progresstick()
 
     # End the command
     pipeo.write(b'\n')
     pipeo.flush()
 
 
 def _getfiles_threaded(
     remote, receivemissing, progresstick, missed, idmap, step
 ):
     remote._callstream(b"getfiles")
     pipeo = remote._pipeo
     pipei = remote._pipei
 
     def writer():
         for missingid in missed:
             versionid = missingid[-40:]
             file = idmap[missingid]
             sshrequest = b"%s%s\n" % (versionid, file)
             pipeo.write(sshrequest)
         pipeo.flush()
 
     writerthread = threading.Thread(target=writer)
     writerthread.daemon = True
     writerthread.start()
 
     for missingid in missed:
         versionid = missingid[-40:]
         file = idmap[missingid]
         receivemissing(pipei, file, versionid)
         progresstick()
 
     writerthread.join()
     # End the command
     pipeo.write(b'\n')
     pipeo.flush()
 
 
 class fileserverclient(object):
     """A client for requesting files from the remote file server.
     """
 
     def __init__(self, repo):
         ui = repo.ui
         self.repo = repo
         self.ui = ui
         self.cacheprocess = ui.config(b"remotefilelog", b"cacheprocess")
         if self.cacheprocess:
             self.cacheprocess = util.expandpath(self.cacheprocess)
 
         # This option causes remotefilelog to pass the full file path to the
         # cacheprocess instead of a hashed key.
         self.cacheprocesspasspath = ui.configbool(
             b"remotefilelog", b"cacheprocess.includepath"
         )
 
         self.debugoutput = ui.configbool(b"remotefilelog", b"debug")
 
         self.remotecache = cacheconnection()
 
     def setstore(self, datastore, historystore, writedata, writehistory):
         self.datastore = datastore
         self.historystore = historystore
         self.writedata = writedata
         self.writehistory = writehistory
 
     def _connect(self):
         return self.repo.connectionpool.get(self.repo.fallbackpath)
 
     def request(self, fileids):
         """Takes a list of filename/node pairs and fetches them from the
         server. Files are stored in the local cache.
         A list of nodes that the server couldn't find is returned.
         If the connection fails, an exception is raised.
         """
         if not self.remotecache.connected:
             self.connect()
         cache = self.remotecache
         writedata = self.writedata
 
         repo = self.repo
         total = len(fileids)
         request = b"get\n%d\n" % total
         idmap = {}
         reponame = repo.name
         for file, id in fileids:
             fullid = getcachekey(reponame, file, id)
             if self.cacheprocesspasspath:
                 request += file + b'\0'
             request += fullid + b"\n"
             idmap[fullid] = file
 
         cache.request(request)
 
         progress = self.ui.makeprogress(_(b'downloading'), total=total)
         progress.update(0)
 
         missed = []
         while True:
             missingid = cache.receiveline()
             if not missingid:
                 missedset = set(missed)
                 for missingid in idmap:
                     if not missingid in missedset:
                         missed.append(missingid)
                 self.ui.warn(
                     _(
                         b"warning: cache connection closed early - "
                         + b"falling back to server\n"
                     )
                 )
                 break
             if missingid == b"0":
                 break
             if missingid.startswith(b"_hits_"):
                 # receive progress reports
                 parts = missingid.split(b"_")
                 progress.increment(int(parts[2]))
                 continue
 
             missed.append(missingid)
 
         global fetchmisses
         fetchmisses += len(missed)
 
         fromcache = total - len(missed)
         progress.update(fromcache, total=total)
         self.ui.log(
             b"remotefilelog",
             b"remote cache hit rate is %r of %r\n",
             fromcache,
             total,
             hit=fromcache,
             total=total,
         )
 
         oldumask = os.umask(0o002)
         try:
             # receive cache misses from master
             if missed:
                 # When verbose is true, sshpeer prints 'running ssh...'
                 # to stdout, which can interfere with some command
                 # outputs
                 verbose = self.ui.verbose
                 self.ui.verbose = False
                 try:
                     with self._connect() as conn:
                         remote = conn.peer
                         if remote.capable(
                             constants.NETWORK_CAP_LEGACY_SSH_GETFILES
                         ):
                             if not isinstance(remote, _sshv1peer):
                                 raise error.Abort(
                                     b'remotefilelog requires ssh ' b'servers'
                                 )
                             step = self.ui.configint(
                                 b'remotefilelog', b'getfilesstep'
                             )
                             getfilestype = self.ui.config(
                                 b'remotefilelog', b'getfilestype'
                             )
                             if getfilestype == b'threaded':
                                 _getfiles = _getfiles_threaded
                             else:
                                 _getfiles = _getfiles_optimistic
                             _getfiles(
                                 remote,
                                 self.receivemissing,
                                 progress.increment,
                                 missed,
                                 idmap,
                                 step,
                             )
                         elif remote.capable(b"x_rfl_getfile"):
                             if remote.capable(b'batch'):
                                 batchdefault = 100
                             else:
                                 batchdefault = 10
                             batchsize = self.ui.configint(
                                 b'remotefilelog', b'batchsize', batchdefault
                             )
                             self.ui.debug(
                                 b'requesting %d files from '
                                 b'remotefilelog server...\n' % len(missed)
                             )
                             _getfilesbatch(
                                 remote,
                                 self.receivemissing,
                                 progress.increment,
                                 missed,
                                 idmap,
                                 batchsize,
                             )
                         else:
                             raise error.Abort(
                                 b"configured remotefilelog server"
                                 b" does not support remotefilelog"
                             )
 
                     self.ui.log(
                         b"remotefilefetchlog",
                         b"Success\n",
                         fetched_files=progress.pos - fromcache,
                         total_to_fetch=total - fromcache,
                     )
                 except Exception:
                     self.ui.log(
                         b"remotefilefetchlog",
                         b"Fail\n",
                         fetched_files=progress.pos - fromcache,
                         total_to_fetch=total - fromcache,
                     )
                     raise
                 finally:
                     self.ui.verbose = verbose
                 # send to memcache
                 request = b"set\n%d\n%s\n" % (len(missed), b"\n".join(missed))
                 cache.request(request)
 
             progress.complete()
 
             # mark ourselves as a user of this cache
             writedata.markrepo(self.repo.path)
         finally:
             os.umask(oldumask)
 
     def receivemissing(self, pipe, filename, node):
         line = pipe.readline()[:-1]
         if not line:
             raise error.ResponseError(
                 _(b"error downloading file contents:"),
                 _(b"connection closed early"),
             )
         size = int(line)
         data = pipe.read(size)
         if len(data) != size:
             raise error.ResponseError(
                 _(b"error downloading file contents:"),
                 _(b"only received %s of %s bytes") % (len(data), size),
             )
 
         self.writedata.addremotefilelognode(
             filename, bin(node), zlib.decompress(data)
         )
 
     def connect(self):
         if self.cacheprocess:
             cmd = b"%s %s" % (self.cacheprocess, self.writedata._path)
             self.remotecache.connect(cmd)
         else:
             # If no cache process is specified, we fake one that always
             # returns cache misses.  This enables tests to run easily
             # and may eventually allow us to be a drop in replacement
             # for the largefiles extension.
             class simplecache(object):
                 def __init__(self):
                     self.missingids = []
                     self.connected = True
 
                 def close(self):
                     pass
 
                 def request(self, value, flush=True):
                     lines = value.split(b"\n")
                     if lines[0] != b"get":
                         return
                     self.missingids = lines[2:-1]
                     self.missingids.append(b'0')
 
                 def receiveline(self):
                     if len(self.missingids) > 0:
                         return self.missingids.pop(0)
                     return None
 
             self.remotecache = simplecache()
 
     def close(self):
         if fetches:
             msg = (
                 b"%d files fetched over %d fetches - "
                 + b"(%d misses, %0.2f%% hit ratio) over %0.2fs\n"
             ) % (
                 fetched,
                 fetches,
                 fetchmisses,
                 float(fetched - fetchmisses) / float(fetched) * 100.0,
                 fetchcost,
             )
             if self.debugoutput:
                 self.ui.warn(msg)
             self.ui.log(
                 b"remotefilelog.prefetch",
                 msg.replace(b"%", b"%%"),
                 remotefilelogfetched=fetched,
                 remotefilelogfetches=fetches,
                 remotefilelogfetchmisses=fetchmisses,
                 remotefilelogfetchtime=fetchcost * 1000,
             )
 
         if self.remotecache.connected:
             self.remotecache.close()
 
     def prefetch(
         self, fileids, force=False, fetchdata=True, fetchhistory=False
     ):
         """downloads the given file versions to the cache
         """
         repo = self.repo
         idstocheck = []
         for file, id in fileids:
             # hack
             # - we don't use .hgtags
             # - workingctx produces ids with length 42,
             #   which we skip since they aren't in any cache
             if (
                 file == b'.hgtags'
                 or len(id) == 42
                 or not repo.shallowmatch(file)
             ):
                 continue
 
             idstocheck.append((file, bin(id)))
 
         datastore = self.datastore
         historystore = self.historystore
         if force:
             datastore = contentstore.unioncontentstore(*repo.shareddatastores)
             historystore = metadatastore.unionmetadatastore(
                 *repo.sharedhistorystores
             )
 
         missingids = set()
         if fetchdata:
             missingids.update(datastore.getmissing(idstocheck))
         if fetchhistory:
             missingids.update(historystore.getmissing(idstocheck))
 
         # partition missing nodes into nullid and not-nullid so we can
         # warn about this filtering potentially shadowing bugs.
         nullids = len([None for unused, id in missingids if id == nullid])
         if nullids:
             missingids = [(f, id) for f, id in missingids if id != nullid]
             repo.ui.develwarn(
                 (
                     b'remotefilelog not fetching %d null revs'
                     b' - this is likely hiding bugs' % nullids
                 ),
                 config=b'remotefilelog-ext',
             )
         if missingids:
             global fetches, fetched, fetchcost
             fetches += 1
 
             # We want to be able to detect excess individual file downloads, so
             # let's log that information for debugging.
             if fetches >= 15 and fetches < 18:
                 if fetches == 15:
                     fetchwarning = self.ui.config(
                         b'remotefilelog', b'fetchwarning'
                     )
                     if fetchwarning:
                         self.ui.warn(fetchwarning + b'\n')
                 self.logstacktrace()
             missingids = [(file, hex(id)) for file, id in sorted(missingids)]
             fetched += len(missingids)
             start = time.time()
             missingids = self.request(missingids)
             if missingids:
                 raise error.Abort(
                     _(b"unable to download %d files") % len(missingids)
                 )
             fetchcost += time.time() - start
             self._lfsprefetch(fileids)
 
     def _lfsprefetch(self, fileids):
         if not _lfsmod or not util.safehasattr(
             self.repo.svfs, b'lfslocalblobstore'
         ):
             return
         if not _lfsmod.wrapper.candownload(self.repo):
             return
         pointers = []
         store = self.repo.svfs.lfslocalblobstore
         for file, id in fileids:
             node = bin(id)
             rlog = self.repo.file(file)
             if rlog.flags(node) & revlog.REVIDX_EXTSTORED:
                 text = rlog.rawdata(node)
                 p = _lfsmod.pointer.deserialize(text)
                 oid = p.oid()
                 if not store.has(oid):
                     pointers.append(p)
         if len(pointers) > 0:
             self.repo.svfs.lfsremoteblobstore.readbatch(pointers, store)
             assert all(store.has(p.oid()) for p in pointers)
 
     def logstacktrace(self):
         import traceback
 
         self.ui.log(
             b'remotefilelog',
             b'excess remotefilelog fetching:\n%s\n',
             b''.join(traceback.format_stack()),
         )

hgext/remotefilelog/repack.py

@@ -1,912 +1,912 b''
 from __future__ import absolute_import
 
 import os
 import time
 
 from mercurial.i18n import _
 from mercurial.node import (
     nullid,
     short,
 )
 from mercurial import (
     encoding,
     error,
     lock as lockmod,
     mdiff,
     policy,
     pycompat,
     scmutil,
     util,
     vfs,
 )
 from mercurial.utils import procutil
 from . import (
     constants,
     contentstore,
     datapack,
     historypack,
     metadatastore,
     shallowutil,
 )
 
 osutil = policy.importmod(r'osutil')
 
 
 class RepackAlreadyRunning(error.Abort):
     pass
 
 
 def backgroundrepack(
     repo, incremental=True, packsonly=False, ensurestart=False
 ):
     cmd = [procutil.hgexecutable(), b'-R', repo.origroot, b'repack']
     msg = _(b"(running background repack)\n")
     if incremental:
         cmd.append(b'--incremental')
         msg = _(b"(running background incremental repack)\n")
     if packsonly:
         cmd.append(b'--packsonly')
     repo.ui.warn(msg)
     # We know this command will find a binary, so don't block on it starting.
     procutil.runbgcommand(cmd, encoding.environ, ensurestart=ensurestart)
 
 
 def fullrepack(repo, options=None):
     """If ``packsonly`` is True, stores creating only loose objects are skipped.
     """
-    if util.safehasattr(repo, b'shareddatastores'):
+    if util.safehasattr(repo, 'shareddatastores'):
         datasource = contentstore.unioncontentstore(*repo.shareddatastores)
         historysource = metadatastore.unionmetadatastore(
             *repo.sharedhistorystores, allowincomplete=True
         )
 
         packpath = shallowutil.getcachepackpath(
             repo, constants.FILEPACK_CATEGORY
         )
         _runrepack(
             repo,
             datasource,
             historysource,
             packpath,
             constants.FILEPACK_CATEGORY,
             options=options,
         )
 
-    if util.safehasattr(repo.manifestlog, b'datastore'):
+    if util.safehasattr(repo.manifestlog, 'datastore'):
         localdata, shareddata = _getmanifeststores(repo)
         lpackpath, ldstores, lhstores = localdata
         spackpath, sdstores, shstores = shareddata
 
         # Repack the shared manifest store
         datasource = contentstore.unioncontentstore(*sdstores)
         historysource = metadatastore.unionmetadatastore(
             *shstores, allowincomplete=True
         )
         _runrepack(
             repo,
             datasource,
             historysource,
             spackpath,
             constants.TREEPACK_CATEGORY,
             options=options,
         )
 
         # Repack the local manifest store
         datasource = contentstore.unioncontentstore(
             *ldstores, allowincomplete=True
         )
         historysource = metadatastore.unionmetadatastore(
             *lhstores, allowincomplete=True
         )
         _runrepack(
             repo,
             datasource,
             historysource,
             lpackpath,
             constants.TREEPACK_CATEGORY,
             options=options,
         )
 
 
 def incrementalrepack(repo, options=None):
     """This repacks the repo by looking at the distribution of pack files in the
     repo and performing the most minimal repack to keep the repo in good shape.
     """
-    if util.safehasattr(repo, b'shareddatastores'):
+    if util.safehasattr(repo, 'shareddatastores'):
         packpath = shallowutil.getcachepackpath(
             repo, constants.FILEPACK_CATEGORY
         )
         _incrementalrepack(
             repo,
             repo.shareddatastores,
             repo.sharedhistorystores,
             packpath,
             constants.FILEPACK_CATEGORY,
             options=options,
         )
 
-    if util.safehasattr(repo.manifestlog, b'datastore'):
+    if util.safehasattr(repo.manifestlog, 'datastore'):
         localdata, shareddata = _getmanifeststores(repo)
         lpackpath, ldstores, lhstores = localdata
         spackpath, sdstores, shstores = shareddata
 
         # Repack the shared manifest store
         _incrementalrepack(
             repo,
             sdstores,
             shstores,
             spackpath,
             constants.TREEPACK_CATEGORY,
             options=options,
         )
 
         # Repack the local manifest store
         _incrementalrepack(
             repo,
             ldstores,
             lhstores,
             lpackpath,
             constants.TREEPACK_CATEGORY,
             allowincompletedata=True,
             options=options,
         )
 
 
 def _getmanifeststores(repo):
     shareddatastores = repo.manifestlog.shareddatastores
     localdatastores = repo.manifestlog.localdatastores
     sharedhistorystores = repo.manifestlog.sharedhistorystores
     localhistorystores = repo.manifestlog.localhistorystores
 
     sharedpackpath = shallowutil.getcachepackpath(
         repo, constants.TREEPACK_CATEGORY
     )
     localpackpath = shallowutil.getlocalpackpath(
         repo.svfs.vfs.base, constants.TREEPACK_CATEGORY
     )
 
     return (
         (localpackpath, localdatastores, localhistorystores),
         (sharedpackpath, shareddatastores, sharedhistorystores),
     )
 
 
 def _topacks(packpath, files, constructor):
     paths = list(os.path.join(packpath, p) for p in files)
     packs = list(constructor(p) for p in paths)
     return packs
 
 
 def _deletebigpacks(repo, folder, files):
     """Deletes packfiles that are bigger than ``packs.maxpacksize``.
 
     Returns ``files` with the removed files omitted."""
     maxsize = repo.ui.configbytes(b"packs", b"maxpacksize")
     if maxsize <= 0:
         return files
 
     # This only considers datapacks today, but we could broaden it to include
     # historypacks.
     VALIDEXTS = [b".datapack", b".dataidx"]
 
     # Either an oversize index or datapack will trigger cleanup of the whole
     # pack:
     oversized = {
         os.path.splitext(path)[0]
         for path, ftype, stat in files
         if (stat.st_size > maxsize and (os.path.splitext(path)[1] in VALIDEXTS))
     }
 
     for rootfname in oversized:
         rootpath = os.path.join(folder, rootfname)
         for ext in VALIDEXTS:
             path = rootpath + ext
             repo.ui.debug(
                 b'removing oversize packfile %s (%s)\n'
                 % (path, util.bytecount(os.stat(path).st_size))
             )
             os.unlink(path)
     return [row for row in files if os.path.basename(row[0]) not in oversized]
 
 
 def _incrementalrepack(
     repo,
     datastore,
     historystore,
     packpath,
     category,
     allowincompletedata=False,
     options=None,
 ):
     shallowutil.mkstickygroupdir(repo.ui, packpath)
 
     files = osutil.listdir(packpath, stat=True)
     files = _deletebigpacks(repo, packpath, files)
     datapacks = _topacks(
         packpath, _computeincrementaldatapack(repo.ui, files), datapack.datapack
     )
     datapacks.extend(
         s for s in datastore if not isinstance(s, datapack.datapackstore)
     )
 
     historypacks = _topacks(
         packpath,
         _computeincrementalhistorypack(repo.ui, files),
         historypack.historypack,
     )
     historypacks.extend(
         s
         for s in historystore
         if not isinstance(s, historypack.historypackstore)
     )
 
     # ``allhistory{files,packs}`` contains all known history packs, even ones we
     # don't plan to repack. They are used during the datapack repack to ensure
     # good ordering of nodes.
     allhistoryfiles = _allpackfileswithsuffix(
         files, historypack.PACKSUFFIX, historypack.INDEXSUFFIX
     )
     allhistorypacks = _topacks(
         packpath,
         (f for f, mode, stat in allhistoryfiles),
         historypack.historypack,
     )
     allhistorypacks.extend(
         s
         for s in historystore
         if not isinstance(s, historypack.historypackstore)
     )
     _runrepack(
         repo,
         contentstore.unioncontentstore(
             *datapacks, allowincomplete=allowincompletedata
         ),
         metadatastore.unionmetadatastore(*historypacks, allowincomplete=True),
         packpath,
         category,
         fullhistory=metadatastore.unionmetadatastore(
             *allhistorypacks, allowincomplete=True
         ),
         options=options,
     )
 
 
 def _computeincrementaldatapack(ui, files):
     opts = {
         b'gencountlimit': ui.configint(b'remotefilelog', b'data.gencountlimit'),
         b'generations': ui.configlist(b'remotefilelog', b'data.generations'),
         b'maxrepackpacks': ui.configint(
             b'remotefilelog', b'data.maxrepackpacks'
         ),
         b'repackmaxpacksize': ui.configbytes(
             b'remotefilelog', b'data.repackmaxpacksize'
         ),
         b'repacksizelimit': ui.configbytes(
             b'remotefilelog', b'data.repacksizelimit'
         ),
     }
 
     packfiles = _allpackfileswithsuffix(
         files, datapack.PACKSUFFIX, datapack.INDEXSUFFIX
     )
     return _computeincrementalpack(packfiles, opts)
 
 
 def _computeincrementalhistorypack(ui, files):
     opts = {
         b'gencountlimit': ui.configint(
             b'remotefilelog', b'history.gencountlimit'
         ),
         b'generations': ui.configlist(
             b'remotefilelog', b'history.generations', [b'100MB']
         ),
         b'maxrepackpacks': ui.configint(
             b'remotefilelog', b'history.maxrepackpacks'
         ),
         b'repackmaxpacksize': ui.configbytes(
             b'remotefilelog', b'history.repackmaxpacksize', b'400MB'
         ),
         b'repacksizelimit': ui.configbytes(
             b'remotefilelog', b'history.repacksizelimit'
         ),
     }
 
     packfiles = _allpackfileswithsuffix(
         files, historypack.PACKSUFFIX, historypack.INDEXSUFFIX
     )
     return _computeincrementalpack(packfiles, opts)
 
 
 def _allpackfileswithsuffix(files, packsuffix, indexsuffix):
     result = []
     fileset = set(fn for fn, mode, stat in files)
     for filename, mode, stat in files:
         if not filename.endswith(packsuffix):
             continue
 
         prefix = filename[: -len(packsuffix)]
 
         # Don't process a pack if it doesn't have an index.
         if (prefix + indexsuffix) not in fileset:
             continue
         result.append((prefix, mode, stat))
 
     return result
 
 
 def _computeincrementalpack(files, opts):
     """Given a set of pack files along with the configuration options, this
     function computes the list of files that should be packed as part of an
     incremental repack.
 
     It tries to strike a balance between keeping incremental repacks cheap (i.e.
     packing small things when possible, and rolling the packs up to the big ones
     over time).
     """
 
     limits = list(
         sorted((util.sizetoint(s) for s in opts[b'generations']), reverse=True)
     )
     limits.append(0)
 
     # Group the packs by generation (i.e. by size)
     generations = []
     for i in pycompat.xrange(len(limits)):
         generations.append([])
 
     sizes = {}
     for prefix, mode, stat in files:
         size = stat.st_size
         if size > opts[b'repackmaxpacksize']:
             continue
 
         sizes[prefix] = size
         for i, limit in enumerate(limits):
             if size > limit:
                 generations[i].append(prefix)
                 break
 
     # Steps for picking what packs to repack:
     # 1. Pick the largest generation with > gencountlimit pack files.
     # 2. Take the smallest three packs.
     # 3. While total-size-of-packs < repacksizelimit: add another pack
 
     # Find the largest generation with more than gencountlimit packs
     genpacks = []
     for i, limit in enumerate(limits):
         if len(generations[i]) > opts[b'gencountlimit']:
             # Sort to be smallest last, for easy popping later
             genpacks.extend(
                 sorted(generations[i], reverse=True, key=lambda x: sizes[x])
             )
             break
 
     # Take as many packs from the generation as we can
     chosenpacks = genpacks[-3:]
     genpacks = genpacks[:-3]
     repacksize = sum(sizes[n] for n in chosenpacks)
     while (
         repacksize < opts[b'repacksizelimit']
         and genpacks
         and len(chosenpacks) < opts[b'maxrepackpacks']
     ):
         chosenpacks.append(genpacks.pop())
         repacksize += sizes[chosenpacks[-1]]
 
     return chosenpacks
 
 
 def _runrepack(
     repo, data, history, packpath, category, fullhistory=None, options=None
 ):
     shallowutil.mkstickygroupdir(repo.ui, packpath)
 
     def isold(repo, filename, node):
         """Check if the file node is older than a limit.
         Unless a limit is specified in the config the default limit is taken.
         """
         filectx = repo.filectx(filename, fileid=node)
         filetime = repo[filectx.linkrev()].date()
 
         ttl = repo.ui.configint(b'remotefilelog', b'nodettl')
 
         limit = time.time() - ttl
         return filetime[0] < limit
 
     garbagecollect = repo.ui.configbool(b'remotefilelog', b'gcrepack')
     if not fullhistory:
         fullhistory = history
     packer = repacker(
         repo,
         data,
         history,
         fullhistory,
         category,
         gc=garbagecollect,
         isold=isold,
         options=options,
     )
 
     with datapack.mutabledatapack(repo.ui, packpath) as dpack:
         with historypack.mutablehistorypack(repo.ui, packpath) as hpack:
             try:
                 packer.run(dpack, hpack)
             except error.LockHeld:
                 raise RepackAlreadyRunning(
                     _(
                         b"skipping repack - another repack "
                         b"is already running"
                     )
                 )
 
 
 def keepset(repo, keyfn, lastkeepkeys=None):
     """Computes a keepset which is not garbage collected.
     'keyfn' is a function that maps filename, node to a unique key.
     'lastkeepkeys' is an optional argument and if provided the keepset
     function updates lastkeepkeys with more keys and returns the result.
     """
     if not lastkeepkeys:
         keepkeys = set()
     else:
         keepkeys = lastkeepkeys
 
     # We want to keep:
     # 1. Working copy parent
     # 2. Draft commits
     # 3. Parents of draft commits
     # 4. Pullprefetch and bgprefetchrevs revsets if specified
     revs = [b'.', b'draft()', b'parents(draft())']
     prefetchrevs = repo.ui.config(b'remotefilelog', b'pullprefetch', None)
     if prefetchrevs:
         revs.append(b'(%s)' % prefetchrevs)
     prefetchrevs = repo.ui.config(b'remotefilelog', b'bgprefetchrevs', None)
     if prefetchrevs:
         revs.append(b'(%s)' % prefetchrevs)
     revs = b'+'.join(revs)
 
     revs = [b'sort((%s), "topo")' % revs]
     keep = scmutil.revrange(repo, revs)
 
     processed = set()
     lastmanifest = None
 
     # process the commits in toposorted order starting from the oldest
     for r in reversed(keep._list):
         if repo[r].p1().rev() in processed:
             # if the direct parent has already been processed
             # then we only need to process the delta
             m = repo[r].manifestctx().readdelta()
         else:
             # otherwise take the manifest and diff it
             # with the previous manifest if one exists
             if lastmanifest:
                 m = repo[r].manifest().diff(lastmanifest)
             else:
                 m = repo[r].manifest()
         lastmanifest = repo[r].manifest()
         processed.add(r)
 
         # populate keepkeys with keys from the current manifest
         if type(m) is dict:
             # m is a result of diff of two manifests and is a dictionary that
             # maps filename to ((newnode, newflag), (oldnode, oldflag)) tuple
             for filename, diff in pycompat.iteritems(m):
                 if diff[0][0] is not None:
                     keepkeys.add(keyfn(filename, diff[0][0]))
         else:
             # m is a manifest object
             for filename, filenode in pycompat.iteritems(m):
                 keepkeys.add(keyfn(filename, filenode))
 
     return keepkeys
 
 
 class repacker(object):
     """Class for orchestrating the repack of data and history information into a
     new format.
     """
 
     def __init__(
         self,
         repo,
         data,
         history,
         fullhistory,
         category,
         gc=False,
         isold=None,
         options=None,
     ):
         self.repo = repo
         self.data = data
         self.history = history
         self.fullhistory = fullhistory
         self.unit = constants.getunits(category)
         self.garbagecollect = gc
         self.options = options
         if self.garbagecollect:
             if not isold:
                 raise ValueError(b"Function 'isold' is not properly specified")
             # use (filename, node) tuple as a keepset key
             self.keepkeys = keepset(repo, lambda f, n: (f, n))
             self.isold = isold
 
     def run(self, targetdata, targethistory):
         ledger = repackledger()
 
         with lockmod.lock(
             repacklockvfs(self.repo), b"repacklock", desc=None, timeout=0
         ):
             self.repo.hook(b'prerepack')
 
             # Populate ledger from source
             self.data.markledger(ledger, options=self.options)
             self.history.markledger(ledger, options=self.options)
 
             # Run repack
             self.repackdata(ledger, targetdata)
             self.repackhistory(ledger, targethistory)
 
             # Call cleanup on each source
             for source in ledger.sources:
                 source.cleanup(ledger)
 
     def _chainorphans(self, ui, filename, nodes, orphans, deltabases):
         """Reorderes ``orphans`` into a single chain inside ``nodes`` and
         ``deltabases``.
 
         We often have orphan entries (nodes without a base that aren't
         referenced by other nodes -- i.e., part of a chain) due to gaps in
         history. Rather than store them as individual fulltexts, we prefer to
         insert them as one chain sorted by size.
         """
         if not orphans:
             return nodes
 
         def getsize(node, default=0):
             meta = self.data.getmeta(filename, node)
             if constants.METAKEYSIZE in meta:
                 return meta[constants.METAKEYSIZE]
             else:
                 return default
 
         # Sort orphans by size; biggest first is preferred, since it's more
         # likely to be the newest version assuming files grow over time.
         # (Sort by node first to ensure the sort is stable.)
         orphans = sorted(orphans)
         orphans = list(sorted(orphans, key=getsize, reverse=True))
         if ui.debugflag:
             ui.debug(
                 b"%s: orphan chain: %s\n"
                 % (filename, b", ".join([short(s) for s in orphans]))
             )
 
         # Create one contiguous chain and reassign deltabases.
         for i, node in enumerate(orphans):
             if i == 0:
                 deltabases[node] = (nullid, 0)
             else:
                 parent = orphans[i - 1]
                 deltabases[node] = (parent, deltabases[parent][1] + 1)
         nodes = [n for n in nodes if n not in orphans]
         nodes += orphans
         return nodes
 
     def repackdata(self, ledger, target):
         ui = self.repo.ui
         maxchainlen = ui.configint(b'packs', b'maxchainlen', 1000)
 
         byfile = {}
         for entry in pycompat.itervalues(ledger.entries):
             if entry.datasource:
                 byfile.setdefault(entry.filename, {})[entry.node] = entry
 
         count = 0
         repackprogress = ui.makeprogress(
             _(b"repacking data"), unit=self.unit, total=len(byfile)
         )
         for filename, entries in sorted(pycompat.iteritems(byfile)):
             repackprogress.update(count)
 
             ancestors = {}
             nodes = list(node for node in entries)
             nohistory = []
             buildprogress = ui.makeprogress(
                 _(b"building history"), unit=b'nodes', total=len(nodes)
             )
             for i, node in enumerate(nodes):
                 if node in ancestors:
                     continue
                 buildprogress.update(i)
                 try:
                     ancestors.update(
                         self.fullhistory.getancestors(
                             filename, node, known=ancestors
                         )
                     )
                 except KeyError:
                     # Since we're packing data entries, we may not have the
                     # corresponding history entries for them. It's not a big
                     # deal, but the entries won't be delta'd perfectly.
                     nohistory.append(node)
             buildprogress.complete()
 
             # Order the nodes children first, so we can produce reverse deltas
             orderednodes = list(reversed(self._toposort(ancestors)))
             if len(nohistory) > 0:
                 ui.debug(
                     b'repackdata: %d nodes without history\n' % len(nohistory)
                 )
             orderednodes.extend(sorted(nohistory))
 
             # Filter orderednodes to just the nodes we want to serialize (it
             # currently also has the edge nodes' ancestors).
             orderednodes = list(
                 filter(lambda node: node in nodes, orderednodes)
             )
 
             # Garbage collect old nodes:
             if self.garbagecollect:
                 neworderednodes = []
                 for node in orderednodes:
                     # If the node is old and is not in the keepset, we skip it,
                     # and mark as garbage collected
                     if (filename, node) not in self.keepkeys and self.isold(
                         self.repo, filename, node
                     ):
                         entries[node].gced = True
                         continue
                     neworderednodes.append(node)
                 orderednodes = neworderednodes
 
             # Compute delta bases for nodes:
             deltabases = {}
             nobase = set()
             referenced = set()
             nodes = set(nodes)
             processprogress = ui.makeprogress(
                 _(b"processing nodes"), unit=b'nodes', total=len(orderednodes)
             )
             for i, node in enumerate(orderednodes):
                 processprogress.update(i)
                 # Find delta base
                 # TODO: allow delta'ing against most recent descendant instead
                 # of immediate child
                 deltatuple = deltabases.get(node, None)
                 if deltatuple is None:
                     deltabase, chainlen = nullid, 0
                     deltabases[node] = (nullid, 0)
                     nobase.add(node)
                 else:
                     deltabase, chainlen = deltatuple
                     referenced.add(deltabase)
 
                 # Use available ancestor information to inform our delta choices
                 ancestorinfo = ancestors.get(node)
                 if ancestorinfo:
                     p1, p2, linknode, copyfrom = ancestorinfo
 
                     # The presence of copyfrom means we're at a point where the
                     # file was copied from elsewhere. So don't attempt to do any
                     # deltas with the other file.
                     if copyfrom:
                         p1 = nullid
 
                     if chainlen < maxchainlen:
                         # Record this child as the delta base for its parents.
                         # This may be non optimal, since the parents may have
                         # many children, and this will only choose the last one.
                         # TODO: record all children and try all deltas to find
                         # best
                         if p1 != nullid:
                             deltabases[p1] = (node, chainlen + 1)
                         if p2 != nullid:
                             deltabases[p2] = (node, chainlen + 1)
 
             # experimental config: repack.chainorphansbysize
             if ui.configbool(b'repack', b'chainorphansbysize'):
                 orphans = nobase - referenced
                 orderednodes = self._chainorphans(
                     ui, filename, orderednodes, orphans, deltabases
                 )
 
             # Compute deltas and write to the pack
             for i, node in enumerate(orderednodes):
                 deltabase, chainlen = deltabases[node]
                 # Compute delta
                 # TODO: Optimize the deltachain fetching. Since we're
                 # iterating over the different version of the file, we may
                 # be fetching the same deltachain over and over again.
                 if deltabase != nullid:
                     deltaentry = self.data.getdelta(filename, node)
                     delta, deltabasename, origdeltabase, meta = deltaentry
                     size = meta.get(constants.METAKEYSIZE)
                     if (
                         deltabasename != filename
                         or origdeltabase != deltabase
                         or size is None
                     ):
                         deltabasetext = self.data.get(filename, deltabase)
                         original = self.data.get(filename, node)
                         size = len(original)
                         delta = mdiff.textdiff(deltabasetext, original)
                 else:
                     delta = self.data.get(filename, node)
                     size = len(delta)
                     meta = self.data.getmeta(filename, node)
 
                 # TODO: don't use the delta if it's larger than the fulltext
                 if constants.METAKEYSIZE not in meta:
                     meta[constants.METAKEYSIZE] = size
                 target.add(filename, node, deltabase, delta, meta)
 
                 entries[node].datarepacked = True
 
             processprogress.complete()
             count += 1
 
         repackprogress.complete()
         target.close(ledger=ledger)
 
     def repackhistory(self, ledger, target):
         ui = self.repo.ui
 
         byfile = {}
         for entry in pycompat.itervalues(ledger.entries):
             if entry.historysource:
                 byfile.setdefault(entry.filename, {})[entry.node] = entry
 
         progress = ui.makeprogress(
             _(b"repacking history"), unit=self.unit, total=len(byfile)
         )
         for filename, entries in sorted(pycompat.iteritems(byfile)):
             ancestors = {}
             nodes = list(node for node in entries)
 
             for node in nodes:
                 if node in ancestors:
                     continue
                 ancestors.update(
                     self.history.getancestors(filename, node, known=ancestors)
                 )
 
             # Order the nodes children first
             orderednodes = reversed(self._toposort(ancestors))
 
             # Write to the pack
             dontprocess = set()
             for node in orderednodes:
                 p1, p2, linknode, copyfrom = ancestors[node]
 
                 # If the node is marked dontprocess, but it's also in the
                 # explicit entries set, that means the node exists both in this
                 # file and in another file that was copied to this file.
                 # Usually this happens if the file was copied to another file,
                 # then the copy was deleted, then reintroduced without copy
                 # metadata. The original add and the new add have the same hash
                 # since the content is identical and the parents are null.
                 if node in dontprocess and node not in entries:
                     # If copyfrom == filename, it means the copy history
                     # went to come other file, then came back to this one, so we
                     # should continue processing it.
                     if p1 != nullid and copyfrom != filename:
                         dontprocess.add(p1)
                     if p2 != nullid:
                         dontprocess.add(p2)
                     continue
 
                 if copyfrom:
                     dontprocess.add(p1)
 
                 target.add(filename, node, p1, p2, linknode, copyfrom)
 
                 if node in entries:
                     entries[node].historyrepacked = True
 
             progress.increment()
 
         progress.complete()
         target.close(ledger=ledger)
 
     def _toposort(self, ancestors):
         def parentfunc(node):
             p1, p2, linknode, copyfrom = ancestors[node]
             parents = []
             if p1 != nullid:
                 parents.append(p1)
             if p2 != nullid:
                 parents.append(p2)
             return parents
 
         sortednodes = shallowutil.sortnodes(ancestors.keys(), parentfunc)
         return sortednodes
 
 
 class repackledger(object):
     """Storage for all the bookkeeping that happens during a repack. It contains
     the list of revisions being repacked, what happened to each revision, and
     which source store contained which revision originally (for later cleanup).
     """
 
     def __init__(self):
         self.entries = {}
         self.sources = {}
         self.created = set()
 
     def markdataentry(self, source, filename, node):
         """Mark the given filename+node revision as having a data rev in the
         given source.
         """
         entry = self._getorcreateentry(filename, node)
         entry.datasource = True
         entries = self.sources.get(source)
         if not entries:
             entries = set()
             self.sources[source] = entries
         entries.add(entry)
 
     def markhistoryentry(self, source, filename, node):
         """Mark the given filename+node revision as having a history rev in the
         given source.
         """
         entry = self._getorcreateentry(filename, node)
         entry.historysource = True
         entries = self.sources.get(source)
         if not entries:
             entries = set()
             self.sources[source] = entries
         entries.add(entry)
 
     def _getorcreateentry(self, filename, node):
         key = (filename, node)
         value = self.entries.get(key)
         if not value:
             value = repackentry(filename, node)
             self.entries[key] = value
 
         return value
 
     def addcreated(self, value):
         self.created.add(value)
 
 
 class repackentry(object):
     """Simple class representing a single revision entry in the repackledger.
     """
 
     __slots__ = (
         r'filename',
         r'node',
         r'datasource',
         r'historysource',
         r'datarepacked',
         r'historyrepacked',
         r'gced',
     )
 
     def __init__(self, filename, node):
         self.filename = filename
         self.node = node
         # If the revision has a data entry in the source
         self.datasource = False
         # If the revision has a history entry in the source
         self.historysource = False
         # If the revision's data entry was repacked into the repack target
         self.datarepacked = False
         # If the revision's history entry was repacked into the repack target
         self.historyrepacked = False
         # If garbage collected
         self.gced = False
 
 
 def repacklockvfs(repo):
-    if util.safehasattr(repo, b'name'):
+    if util.safehasattr(repo, 'name'):
         # Lock in the shared cache so repacks across multiple copies of the same
         # repo are coordinated.
         sharedcachepath = shallowutil.getcachepackpath(
             repo, constants.FILEPACK_CATEGORY
         )
         return vfs.vfs(sharedcachepath)
     else:
         return repo.svfs

hgext/remotefilelog/shallowrepo.py

@@ -1,354 +1,354 b''
 # shallowrepo.py - shallow repository that uses remote filelogs
 #
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 from __future__ import absolute_import
 
 import os
 
 from mercurial.i18n import _
 from mercurial.node import hex, nullid, nullrev
 from mercurial import (
     encoding,
     error,
     localrepo,
     match,
     pycompat,
     scmutil,
     sparse,
     util,
 )
 from mercurial.utils import procutil
 from . import (
     connectionpool,
     constants,
     contentstore,
     datapack,
     fileserverclient,
     historypack,
     metadatastore,
     remotefilectx,
     remotefilelog,
     shallowutil,
 )
 
 # These make*stores functions are global so that other extensions can replace
 # them.
 def makelocalstores(repo):
     """In-repo stores, like .hg/store/data; can not be discarded."""
     localpath = os.path.join(repo.svfs.vfs.base, b'data')
     if not os.path.exists(localpath):
         os.makedirs(localpath)
 
     # Instantiate local data stores
     localcontent = contentstore.remotefilelogcontentstore(
         repo, localpath, repo.name, shared=False
     )
     localmetadata = metadatastore.remotefilelogmetadatastore(
         repo, localpath, repo.name, shared=False
     )
     return localcontent, localmetadata
 
 
 def makecachestores(repo):
     """Typically machine-wide, cache of remote data; can be discarded."""
     # Instantiate shared cache stores
     cachepath = shallowutil.getcachepath(repo.ui)
     cachecontent = contentstore.remotefilelogcontentstore(
         repo, cachepath, repo.name, shared=True
     )
     cachemetadata = metadatastore.remotefilelogmetadatastore(
         repo, cachepath, repo.name, shared=True
     )
 
     repo.sharedstore = cachecontent
     repo.shareddatastores.append(cachecontent)
     repo.sharedhistorystores.append(cachemetadata)
 
     return cachecontent, cachemetadata
 
 
 def makeremotestores(repo, cachecontent, cachemetadata):
     """These stores fetch data from a remote server."""
     # Instantiate remote stores
     repo.fileservice = fileserverclient.fileserverclient(repo)
     remotecontent = contentstore.remotecontentstore(
         repo.ui, repo.fileservice, cachecontent
     )
     remotemetadata = metadatastore.remotemetadatastore(
         repo.ui, repo.fileservice, cachemetadata
     )
     return remotecontent, remotemetadata
 
 
 def makepackstores(repo):
     """Packs are more efficient (to read from) cache stores."""
     # Instantiate pack stores
     packpath = shallowutil.getcachepackpath(repo, constants.FILEPACK_CATEGORY)
     packcontentstore = datapack.datapackstore(repo.ui, packpath)
     packmetadatastore = historypack.historypackstore(repo.ui, packpath)
 
     repo.shareddatastores.append(packcontentstore)
     repo.sharedhistorystores.append(packmetadatastore)
     shallowutil.reportpackmetrics(
         repo.ui, b'filestore', packcontentstore, packmetadatastore
     )
     return packcontentstore, packmetadatastore
 
 
 def makeunionstores(repo):
     """Union stores iterate the other stores and return the first result."""
     repo.shareddatastores = []
     repo.sharedhistorystores = []
 
     packcontentstore, packmetadatastore = makepackstores(repo)
     cachecontent, cachemetadata = makecachestores(repo)
     localcontent, localmetadata = makelocalstores(repo)
     remotecontent, remotemetadata = makeremotestores(
         repo, cachecontent, cachemetadata
     )
 
     # Instantiate union stores
     repo.contentstore = contentstore.unioncontentstore(
         packcontentstore,
         cachecontent,
         localcontent,
         remotecontent,
         writestore=localcontent,
     )
     repo.metadatastore = metadatastore.unionmetadatastore(
         packmetadatastore,
         cachemetadata,
         localmetadata,
         remotemetadata,
         writestore=localmetadata,
     )
 
     fileservicedatawrite = cachecontent
     fileservicehistorywrite = cachemetadata
     repo.fileservice.setstore(
         repo.contentstore,
         repo.metadatastore,
         fileservicedatawrite,
         fileservicehistorywrite,
     )
     shallowutil.reportpackmetrics(
         repo.ui, b'filestore', packcontentstore, packmetadatastore
     )
 
 
 def wraprepo(repo):
     class shallowrepository(repo.__class__):
         @util.propertycache
         def name(self):
             return self.ui.config(b'remotefilelog', b'reponame')
 
         @util.propertycache
         def fallbackpath(self):
             path = repo.ui.config(
                 b"remotefilelog",
                 b"fallbackpath",
                 repo.ui.config(b'paths', b'default'),
             )
             if not path:
                 raise error.Abort(
                     b"no remotefilelog server "
                     b"configured - is your .hg/hgrc trusted?"
                 )
 
             return path
 
         def maybesparsematch(self, *revs, **kwargs):
             '''
             A wrapper that allows the remotefilelog to invoke sparsematch() if
             this is a sparse repository, or returns None if this is not a
             sparse repository.
             '''
             if revs:
                 ret = sparse.matcher(repo, revs=revs)
             else:
                 ret = sparse.matcher(repo)
 
             if ret.always():
                 return None
             return ret
 
         def file(self, f):
             if f[0] == b'/':
                 f = f[1:]
 
             if self.shallowmatch(f):
                 return remotefilelog.remotefilelog(self.svfs, f, self)
             else:
                 return super(shallowrepository, self).file(f)
 
         def filectx(self, path, *args, **kwargs):
             if self.shallowmatch(path):
                 return remotefilectx.remotefilectx(self, path, *args, **kwargs)
             else:
                 return super(shallowrepository, self).filectx(
                     path, *args, **kwargs
                 )
 
         @localrepo.unfilteredmethod
         def commitctx(self, ctx, error=False, origctx=None):
             """Add a new revision to current repository.
             Revision information is passed via the context argument.
             """
 
             # some contexts already have manifest nodes, they don't need any
             # prefetching (for example if we're just editing a commit message
             # we can reuse manifest
             if not ctx.manifestnode():
                 # prefetch files that will likely be compared
                 m1 = ctx.p1().manifest()
                 files = []
                 for f in ctx.modified() + ctx.added():
                     fparent1 = m1.get(f, nullid)
                     if fparent1 != nullid:
                         files.append((f, hex(fparent1)))
                 self.fileservice.prefetch(files)
             return super(shallowrepository, self).commitctx(
                 ctx, error=error, origctx=origctx
             )
 
         def backgroundprefetch(
             self,
             revs,
             base=None,
             repack=False,
             pats=None,
             opts=None,
             ensurestart=False,
         ):
             """Runs prefetch in background with optional repack
             """
             cmd = [procutil.hgexecutable(), b'-R', repo.origroot, b'prefetch']
             if repack:
                 cmd.append(b'--repack')
             if revs:
                 cmd += [b'-r', revs]
             # We know this command will find a binary, so don't block
             # on it starting.
             procutil.runbgcommand(
                 cmd, encoding.environ, ensurestart=ensurestart
             )
 
         def prefetch(self, revs, base=None, pats=None, opts=None):
             """Prefetches all the necessary file revisions for the given revs
             Optionally runs repack in background
             """
             with repo._lock(
                 repo.svfs,
                 b'prefetchlock',
                 True,
                 None,
                 None,
                 _(b'prefetching in %s') % repo.origroot,
             ):
                 self._prefetch(revs, base, pats, opts)
 
         def _prefetch(self, revs, base=None, pats=None, opts=None):
             fallbackpath = self.fallbackpath
             if fallbackpath:
                 # If we know a rev is on the server, we should fetch the server
                 # version of those files, since our local file versions might
                 # become obsolete if the local commits are stripped.
                 localrevs = repo.revs(b'outgoing(%s)', fallbackpath)
                 if base is not None and base != nullrev:
                     serverbase = list(
                         repo.revs(
                             b'first(reverse(::%s) - %ld)', base, localrevs
                         )
                     )
                     if serverbase:
                         base = serverbase[0]
             else:
                 localrevs = repo
 
             mfl = repo.manifestlog
             mfrevlog = mfl.getstorage(b'')
             if base is not None:
                 mfdict = mfl[repo[base].manifestnode()].read()
                 skip = set(pycompat.iteritems(mfdict))
             else:
                 skip = set()
 
             # Copy the skip set to start large and avoid constant resizing,
             # and since it's likely to be very similar to the prefetch set.
             files = skip.copy()
             serverfiles = skip.copy()
             visited = set()
             visited.add(nullrev)
             revcount = len(revs)
             progress = self.ui.makeprogress(_(b'prefetching'), total=revcount)
             progress.update(0)
             for rev in sorted(revs):
                 ctx = repo[rev]
                 if pats:
                     m = scmutil.match(ctx, pats, opts)
                 sparsematch = repo.maybesparsematch(rev)
 
                 mfnode = ctx.manifestnode()
                 mfrev = mfrevlog.rev(mfnode)
 
                 # Decompressing manifests is expensive.
                 # When possible, only read the deltas.
                 p1, p2 = mfrevlog.parentrevs(mfrev)
                 if p1 in visited and p2 in visited:
                     mfdict = mfl[mfnode].readfast()
                 else:
                     mfdict = mfl[mfnode].read()
 
                 diff = pycompat.iteritems(mfdict)
                 if pats:
                     diff = (pf for pf in diff if m(pf[0]))
                 if sparsematch:
                     diff = (pf for pf in diff if sparsematch(pf[0]))
                 if rev not in localrevs:
                     serverfiles.update(diff)
                 else:
                     files.update(diff)
 
                 visited.add(mfrev)
                 progress.increment()
 
             files.difference_update(skip)
             serverfiles.difference_update(skip)
             progress.complete()
 
             # Fetch files known to be on the server
             if serverfiles:
                 results = [(path, hex(fnode)) for (path, fnode) in serverfiles]
                 repo.fileservice.prefetch(results, force=True)
 
             # Fetch files that may or may not be on the server
             if files:
                 results = [(path, hex(fnode)) for (path, fnode) in files]
                 repo.fileservice.prefetch(results)
 
         def close(self):
             super(shallowrepository, self).close()
             self.connectionpool.close()
 
     repo.__class__ = shallowrepository
 
     repo.shallowmatch = match.always()
 
     makeunionstores(repo)
 
     repo.includepattern = repo.ui.configlist(
         b"remotefilelog", b"includepattern", None
     )
     repo.excludepattern = repo.ui.configlist(
         b"remotefilelog", b"excludepattern", None
     )
-    if not util.safehasattr(repo, b'connectionpool'):
+    if not util.safehasattr(repo, 'connectionpool'):
         repo.connectionpool = connectionpool.connectionpool(repo)
 
     if repo.includepattern or repo.excludepattern:
         repo.shallowmatch = match.match(
             repo.root, b'', None, repo.includepattern, repo.excludepattern
         )

mercurial/bundle2.py

@@ -1,2555 +1,2555 b''
 # bundle2.py - generic container format to transmit arbitrary data.
 #
 # Copyright 2013 Facebook, Inc.
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 """Handling of the new bundle2 format
 
 The goal of bundle2 is to act as an atomically packet to transmit a set of
 payloads in an application agnostic way. It consist in a sequence of "parts"
 that will be handed to and processed by the application layer.
 
 
 General format architecture
 ===========================
 
 The format is architectured as follow
 
  - magic string
  - stream level parameters
  - payload parts (any number)
  - end of stream marker.
 
 the Binary format
 ============================
 
 All numbers are unsigned and big-endian.
 
 stream level parameters
 ------------------------
 
 Binary format is as follow
 
 :params size: int32
 
   The total number of Bytes used by the parameters
 
 :params value: arbitrary number of Bytes
 
   A blob of `params size` containing the serialized version of all stream level
   parameters.
 
   The blob contains a space separated list of parameters. Parameters with value
   are stored in the form `<name>=<value>`. Both name and value are urlquoted.
 
   Empty name are obviously forbidden.
 
   Name MUST start with a letter. If this first letter is lower case, the
   parameter is advisory and can be safely ignored. However when the first
   letter is capital, the parameter is mandatory and the bundling process MUST
   stop if he is not able to proceed it.
 
   Stream parameters use a simple textual format for two main reasons:
 
   - Stream level parameters should remain simple and we want to discourage any
     crazy usage.
   - Textual data allow easy human inspection of a bundle2 header in case of
     troubles.
 
   Any Applicative level options MUST go into a bundle2 part instead.
 
 Payload part
 ------------------------
 
 Binary format is as follow
 
 :header size: int32
 
   The total number of Bytes used by the part header. When the header is empty
   (size = 0) this is interpreted as the end of stream marker.
 
 :header:
 
     The header defines how to interpret the part. It contains two piece of
     data: the part type, and the part parameters.
 
     The part type is used to route an application level handler, that can
     interpret payload.
 
     Part parameters are passed to the application level handler.  They are
     meant to convey information that will help the application level object to
     interpret the part payload.
 
     The binary format of the header is has follow
 
     :typesize: (one byte)
 
     :parttype: alphanumerical part name (restricted to [a-zA-Z0-9_:-]*)
 
     :partid: A 32bits integer (unique in the bundle) that can be used to refer
              to this part.
 
     :parameters:
 
         Part's parameter may have arbitrary content, the binary structure is::
 
             <mandatory-count><advisory-count><param-sizes><param-data>
 
         :mandatory-count: 1 byte, number of mandatory parameters
 
         :advisory-count:  1 byte, number of advisory parameters
 
         :param-sizes:
 
             N couple of bytes, where N is the total number of parameters. Each
             couple contains (<size-of-key>, <size-of-value) for one parameter.
 
         :param-data:
 
             A blob of bytes from which each parameter key and value can be
             retrieved using the list of size couples stored in the previous
             field.
 
             Mandatory parameters comes first, then the advisory ones.
 
             Each parameter's key MUST be unique within the part.
 
 :payload:
 
     payload is a series of `<chunksize><chunkdata>`.
 
     `chunksize` is an int32, `chunkdata` are plain bytes (as much as
     `chunksize` says)` The payload part is concluded by a zero size chunk.
 
     The current implementation always produces either zero or one chunk.
     This is an implementation limitation that will ultimately be lifted.
 
     `chunksize` can be negative to trigger special case processing. No such
     processing is in place yet.
 
 Bundle processing
 ============================
 
 Each part is processed in order using a "part handler". Handler are registered
 for a certain part type.
 
 The matching of a part to its handler is case insensitive. The case of the
 part type is used to know if a part is mandatory or advisory. If the Part type
 contains any uppercase char it is considered mandatory. When no handler is
 known for a Mandatory part, the process is aborted and an exception is raised.
 If the part is advisory and no handler is known, the part is ignored. When the
 process is aborted, the full bundle is still read from the stream to keep the
 channel usable. But none of the part read from an abort are processed. In the
 future, dropping the stream may become an option for channel we do not care to
 preserve.
 """
 
 from __future__ import absolute_import, division
 
 import collections
 import errno
 import os
 import re
 import string
 import struct
 import sys
 
 from .i18n import _
 from . import (
     bookmarks,
     changegroup,
     encoding,
     error,
     node as nodemod,
     obsolete,
     phases,
     pushkey,
     pycompat,
     streamclone,
     tags,
     url,
     util,
 )
 from .utils import stringutil
 
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 _pack = struct.pack
 _unpack = struct.unpack
 
 _fstreamparamsize = b'>i'
 _fpartheadersize = b'>i'
 _fparttypesize = b'>B'
 _fpartid = b'>I'
 _fpayloadsize = b'>i'
 _fpartparamcount = b'>BB'
 
 preferedchunksize = 32768
 
 _parttypeforbidden = re.compile(b'[^a-zA-Z0-9_:-]')
 
 
 def outdebug(ui, message):
     """debug regarding output stream (bundling)"""
     if ui.configbool(b'devel', b'bundle2.debug'):
         ui.debug(b'bundle2-output: %s\n' % message)
 
 
 def indebug(ui, message):
     """debug on input stream (unbundling)"""
     if ui.configbool(b'devel', b'bundle2.debug'):
         ui.debug(b'bundle2-input: %s\n' % message)
 
 
 def validateparttype(parttype):
     """raise ValueError if a parttype contains invalid character"""
     if _parttypeforbidden.search(parttype):
         raise ValueError(parttype)
 
 
 def _makefpartparamsizes(nbparams):
     """return a struct format to read part parameter sizes
 
     The number parameters is variable so we need to build that format
     dynamically.
     """
     return b'>' + (b'BB' * nbparams)
 
 
 parthandlermapping = {}
 
 
 def parthandler(parttype, params=()):
     """decorator that register a function as a bundle2 part handler
 
     eg::
 
         @parthandler('myparttype', ('mandatory', 'param', 'handled'))
         def myparttypehandler(...):
             '''process a part of type "my part".'''
             ...
     """
     validateparttype(parttype)
 
     def _decorator(func):
         lparttype = parttype.lower()  # enforce lower case matching.
         assert lparttype not in parthandlermapping
         parthandlermapping[lparttype] = func
         func.params = frozenset(params)
         return func
 
     return _decorator
 
 
 class unbundlerecords(object):
     """keep record of what happens during and unbundle
 
     New records are added using `records.add('cat', obj)`. Where 'cat' is a
     category of record and obj is an arbitrary object.
 
     `records['cat']` will return all entries of this category 'cat'.
 
     Iterating on the object itself will yield `('category', obj)` tuples
     for all entries.
 
     All iterations happens in chronological order.
     """
 
     def __init__(self):
         self._categories = {}
         self._sequences = []
         self._replies = {}
 
     def add(self, category, entry, inreplyto=None):
         """add a new record of a given category.
 
         The entry can then be retrieved in the list returned by
         self['category']."""
         self._categories.setdefault(category, []).append(entry)
         self._sequences.append((category, entry))
         if inreplyto is not None:
             self.getreplies(inreplyto).add(category, entry)
 
     def getreplies(self, partid):
         """get the records that are replies to a specific part"""
         return self._replies.setdefault(partid, unbundlerecords())
 
     def __getitem__(self, cat):
         return tuple(self._categories.get(cat, ()))
 
     def __iter__(self):
         return iter(self._sequences)
 
     def __len__(self):
         return len(self._sequences)
 
     def __nonzero__(self):
         return bool(self._sequences)
 
     __bool__ = __nonzero__
 
 
 class bundleoperation(object):
     """an object that represents a single bundling process
 
     Its purpose is to carry unbundle-related objects and states.
 
     A new object should be created at the beginning of each bundle processing.
     The object is to be returned by the processing function.
 
     The object has very little content now it will ultimately contain:
     * an access to the repo the bundle is applied to,
     * a ui object,
     * a way to retrieve a transaction to add changes to the repo,
     * a way to record the result of processing each part,
     * a way to construct a bundle response when applicable.
     """
 
     def __init__(self, repo, transactiongetter, captureoutput=True, source=b''):
         self.repo = repo
         self.ui = repo.ui
         self.records = unbundlerecords()
         self.reply = None
         self.captureoutput = captureoutput
         self.hookargs = {}
         self._gettransaction = transactiongetter
         # carries value that can modify part behavior
         self.modes = {}
         self.source = source
 
     def gettransaction(self):
         transaction = self._gettransaction()
 
         if self.hookargs:
             # the ones added to the transaction supercede those added
             # to the operation.
             self.hookargs.update(transaction.hookargs)
             transaction.hookargs = self.hookargs
 
         # mark the hookargs as flushed.  further attempts to add to
         # hookargs will result in an abort.
         self.hookargs = None
 
         return transaction
 
     def addhookargs(self, hookargs):
         if self.hookargs is None:
             raise error.ProgrammingError(
                 b'attempted to add hookargs to '
                 b'operation after transaction started'
             )
         self.hookargs.update(hookargs)
 
 
 class TransactionUnavailable(RuntimeError):
     pass
 
 
 def _notransaction():
     """default method to get a transaction while processing a bundle
 
     Raise an exception to highlight the fact that no transaction was expected
     to be created"""
     raise TransactionUnavailable()
 
 
 def applybundle(repo, unbundler, tr, source, url=None, **kwargs):
     # transform me into unbundler.apply() as soon as the freeze is lifted
     if isinstance(unbundler, unbundle20):
         tr.hookargs[b'bundle2'] = b'1'
         if source is not None and b'source' not in tr.hookargs:
             tr.hookargs[b'source'] = source
         if url is not None and b'url' not in tr.hookargs:
             tr.hookargs[b'url'] = url
         return processbundle(repo, unbundler, lambda: tr, source=source)
     else:
         # the transactiongetter won't be used, but we might as well set it
         op = bundleoperation(repo, lambda: tr, source=source)
         _processchangegroup(op, unbundler, tr, source, url, **kwargs)
         return op
 
 
 class partiterator(object):
     def __init__(self, repo, op, unbundler):
         self.repo = repo
         self.op = op
         self.unbundler = unbundler
         self.iterator = None
         self.count = 0
         self.current = None
 
     def __enter__(self):
         def func():
             itr = enumerate(self.unbundler.iterparts(), 1)
             for count, p in itr:
                 self.count = count
                 self.current = p
                 yield p
                 p.consume()
                 self.current = None
 
         self.iterator = func()
         return self.iterator
 
     def __exit__(self, type, exc, tb):
         if not self.iterator:
             return
 
         # Only gracefully abort in a normal exception situation. User aborts
         # like Ctrl+C throw a KeyboardInterrupt which is not a base Exception,
         # and should not gracefully cleanup.
         if isinstance(exc, Exception):
             # Any exceptions seeking to the end of the bundle at this point are
             # almost certainly related to the underlying stream being bad.
             # And, chances are that the exception we're handling is related to
             # getting in that bad state. So, we swallow the seeking error and
             # re-raise the original error.
             seekerror = False
             try:
                 if self.current:
                     # consume the part content to not corrupt the stream.
                     self.current.consume()
 
                 for part in self.iterator:
                     # consume the bundle content
                     part.consume()
             except Exception:
                 seekerror = True
 
             # Small hack to let caller code distinguish exceptions from bundle2
             # processing from processing the old format. This is mostly needed
             # to handle different return codes to unbundle according to the type
             # of bundle. We should probably clean up or drop this return code
             # craziness in a future version.
             exc.duringunbundle2 = True
             salvaged = []
             replycaps = None
             if self.op.reply is not None:
                 salvaged = self.op.reply.salvageoutput()
                 replycaps = self.op.reply.capabilities
             exc._replycaps = replycaps
             exc._bundle2salvagedoutput = salvaged
 
             # Re-raising from a variable loses the original stack. So only use
             # that form if we need to.
             if seekerror:
                 raise exc
 
         self.repo.ui.debug(
             b'bundle2-input-bundle: %i parts total\n' % self.count
         )
 
 
 def processbundle(repo, unbundler, transactiongetter=None, op=None, source=b''):
     """This function process a bundle, apply effect to/from a repo
 
     It iterates over each part then searches for and uses the proper handling
     code to process the part. Parts are processed in order.
 
     Unknown Mandatory part will abort the process.
 
     It is temporarily possible to provide a prebuilt bundleoperation to the
     function. This is used to ensure output is properly propagated in case of
     an error during the unbundling. This output capturing part will likely be
     reworked and this ability will probably go away in the process.
     """
     if op is None:
         if transactiongetter is None:
             transactiongetter = _notransaction
         op = bundleoperation(repo, transactiongetter, source=source)
     # todo:
     # - replace this is a init function soon.
     # - exception catching
     unbundler.params
     if repo.ui.debugflag:
         msg = [b'bundle2-input-bundle:']
         if unbundler.params:
             msg.append(b' %i params' % len(unbundler.params))
         if op._gettransaction is None or op._gettransaction is _notransaction:
             msg.append(b' no-transaction')
         else:
             msg.append(b' with-transaction')
         msg.append(b'\n')
         repo.ui.debug(b''.join(msg))
 
     processparts(repo, op, unbundler)
 
     return op
 
 
 def processparts(repo, op, unbundler):
     with partiterator(repo, op, unbundler) as parts:
         for part in parts:
             _processpart(op, part)
 
 
 def _processchangegroup(op, cg, tr, source, url, **kwargs):
     ret = cg.apply(op.repo, tr, source, url, **kwargs)
     op.records.add(b'changegroup', {b'return': ret,})
     return ret
 
 
 def _gethandler(op, part):
     status = b'unknown'  # used by debug output
     try:
         handler = parthandlermapping.get(part.type)
         if handler is None:
             status = b'unsupported-type'
             raise error.BundleUnknownFeatureError(parttype=part.type)
         indebug(op.ui, b'found a handler for part %s' % part.type)
         unknownparams = part.mandatorykeys - handler.params
         if unknownparams:
             unknownparams = list(unknownparams)
             unknownparams.sort()
             status = b'unsupported-params (%s)' % b', '.join(unknownparams)
             raise error.BundleUnknownFeatureError(
                 parttype=part.type, params=unknownparams
             )
         status = b'supported'
     except error.BundleUnknownFeatureError as exc:
         if part.mandatory:  # mandatory parts
             raise
         indebug(op.ui, b'ignoring unsupported advisory part %s' % exc)
         return  # skip to part processing
     finally:
         if op.ui.debugflag:
             msg = [b'bundle2-input-part: "%s"' % part.type]
             if not part.mandatory:
                 msg.append(b' (advisory)')
             nbmp = len(part.mandatorykeys)
             nbap = len(part.params) - nbmp
             if nbmp or nbap:
                 msg.append(b' (params:')
                 if nbmp:
                     msg.append(b' %i mandatory' % nbmp)
                 if nbap:
                     msg.append(b' %i advisory' % nbmp)
                 msg.append(b')')
             msg.append(b' %s\n' % status)
             op.ui.debug(b''.join(msg))
 
     return handler
 
 
 def _processpart(op, part):
     """process a single part from a bundle
 
     The part is guaranteed to have been fully consumed when the function exits
     (even if an exception is raised)."""
     handler = _gethandler(op, part)
     if handler is None:
         return
 
     # handler is called outside the above try block so that we don't
     # risk catching KeyErrors from anything other than the
     # parthandlermapping lookup (any KeyError raised by handler()
     # itself represents a defect of a different variety).
     output = None
     if op.captureoutput and op.reply is not None:
         op.ui.pushbuffer(error=True, subproc=True)
         output = b''
     try:
         handler(op, part)
     finally:
         if output is not None:
             output = op.ui.popbuffer()
         if output:
             outpart = op.reply.newpart(b'output', data=output, mandatory=False)
             outpart.addparam(
                 b'in-reply-to', pycompat.bytestr(part.id), mandatory=False
             )
 
 
 def decodecaps(blob):
     """decode a bundle2 caps bytes blob into a dictionary
 
     The blob is a list of capabilities (one per line)
     Capabilities may have values using a line of the form::
 
         capability=value1,value2,value3
 
     The values are always a list."""
     caps = {}
     for line in blob.splitlines():
         if not line:
             continue
         if b'=' not in line:
             key, vals = line, ()
         else:
             key, vals = line.split(b'=', 1)
             vals = vals.split(b',')
         key = urlreq.unquote(key)
         vals = [urlreq.unquote(v) for v in vals]
         caps[key] = vals
     return caps
 
 
 def encodecaps(caps):
     """encode a bundle2 caps dictionary into a bytes blob"""
     chunks = []
     for ca in sorted(caps):
         vals = caps[ca]
         ca = urlreq.quote(ca)
         vals = [urlreq.quote(v) for v in vals]
         if vals:
             ca = b"%s=%s" % (ca, b','.join(vals))
         chunks.append(ca)
     return b'\n'.join(chunks)
 
 
 bundletypes = {
     b"": (b"", b'UN'),  # only when using unbundle on ssh and old http servers
     # since the unification ssh accepts a header but there
     # is no capability signaling it.
     b"HG20": (),  # special-cased below
     b"HG10UN": (b"HG10UN", b'UN'),
     b"HG10BZ": (b"HG10", b'BZ'),
     b"HG10GZ": (b"HG10GZ", b'GZ'),
 }
 
 # hgweb uses this list to communicate its preferred type
 bundlepriority = [b'HG10GZ', b'HG10BZ', b'HG10UN']
 
 
 class bundle20(object):
     """represent an outgoing bundle2 container
 
     Use the `addparam` method to add stream level parameter. and `newpart` to
     populate it. Then call `getchunks` to retrieve all the binary chunks of
     data that compose the bundle2 container."""
 
     _magicstring = b'HG20'
 
     def __init__(self, ui, capabilities=()):
         self.ui = ui
         self._params = []
         self._parts = []
         self.capabilities = dict(capabilities)
         self._compengine = util.compengines.forbundletype(b'UN')
         self._compopts = None
         # If compression is being handled by a consumer of the raw
         # data (e.g. the wire protocol), unsetting this flag tells
         # consumers that the bundle is best left uncompressed.
         self.prefercompressed = True
 
     def setcompression(self, alg, compopts=None):
         """setup core part compression to <alg>"""
         if alg in (None, b'UN'):
             return
         assert not any(n.lower() == b'compression' for n, v in self._params)
         self.addparam(b'Compression', alg)
         self._compengine = util.compengines.forbundletype(alg)
         self._compopts = compopts
 
     @property
     def nbparts(self):
         """total number of parts added to the bundler"""
         return len(self._parts)
 
     # methods used to defines the bundle2 content
     def addparam(self, name, value=None):
         """add a stream level parameter"""
         if not name:
             raise error.ProgrammingError(b'empty parameter name')
         if name[0:1] not in pycompat.bytestr(string.ascii_letters):
             raise error.ProgrammingError(
                 b'non letter first character: %s' % name
             )
         self._params.append((name, value))
 
     def addpart(self, part):
         """add a new part to the bundle2 container
 
         Parts contains the actual applicative payload."""
         assert part.id is None
         part.id = len(self._parts)  # very cheap counter
         self._parts.append(part)
 
     def newpart(self, typeid, *args, **kwargs):
         """create a new part and add it to the containers
 
         As the part is directly added to the containers. For now, this means
         that any failure to properly initialize the part after calling
         ``newpart`` should result in a failure of the whole bundling process.
 
         You can still fall back to manually create and add if you need better
         control."""
         part = bundlepart(typeid, *args, **kwargs)
         self.addpart(part)
         return part
 
     # methods used to generate the bundle2 stream
     def getchunks(self):
         if self.ui.debugflag:
             msg = [b'bundle2-output-bundle: "%s",' % self._magicstring]
             if self._params:
                 msg.append(b' (%i params)' % len(self._params))
             msg.append(b' %i parts total\n' % len(self._parts))
             self.ui.debug(b''.join(msg))
         outdebug(self.ui, b'start emission of %s stream' % self._magicstring)
         yield self._magicstring
         param = self._paramchunk()
         outdebug(self.ui, b'bundle parameter: %s' % param)
         yield _pack(_fstreamparamsize, len(param))
         if param:
             yield param
         for chunk in self._compengine.compressstream(
             self._getcorechunk(), self._compopts
         ):
             yield chunk
 
     def _paramchunk(self):
         """return a encoded version of all stream parameters"""
         blocks = []
         for par, value in self._params:
             par = urlreq.quote(par)
             if value is not None:
                 value = urlreq.quote(value)
                 par = b'%s=%s' % (par, value)
             blocks.append(par)
         return b' '.join(blocks)
 
     def _getcorechunk(self):
         """yield chunk for the core part of the bundle
 
         (all but headers and parameters)"""
         outdebug(self.ui, b'start of parts')
         for part in self._parts:
             outdebug(self.ui, b'bundle part: "%s"' % part.type)
             for chunk in part.getchunks(ui=self.ui):
                 yield chunk
         outdebug(self.ui, b'end of bundle')
         yield _pack(_fpartheadersize, 0)
 
     def salvageoutput(self):
         """return a list with a copy of all output parts in the bundle
 
         This is meant to be used during error handling to make sure we preserve
         server output"""
         salvaged = []
         for part in self._parts:
             if part.type.startswith(b'output'):
                 salvaged.append(part.copy())
         return salvaged
 
 
 class unpackermixin(object):
     """A mixin to extract bytes and struct data from a stream"""
 
     def __init__(self, fp):
         self._fp = fp
 
     def _unpack(self, format):
         """unpack this struct format from the stream
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         data = self._readexact(struct.calcsize(format))
         return _unpack(format, data)
 
     def _readexact(self, size):
         """read exactly <size> bytes from the stream
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         return changegroup.readexactly(self._fp, size)
 
 
 def getunbundler(ui, fp, magicstring=None):
     """return a valid unbundler object for a given magicstring"""
     if magicstring is None:
         magicstring = changegroup.readexactly(fp, 4)
     magic, version = magicstring[0:2], magicstring[2:4]
     if magic != b'HG':
         ui.debug(
             b"error: invalid magic: %r (version %r), should be 'HG'\n"
             % (magic, version)
         )
         raise error.Abort(_(b'not a Mercurial bundle'))
     unbundlerclass = formatmap.get(version)
     if unbundlerclass is None:
         raise error.Abort(_(b'unknown bundle version %s') % version)
     unbundler = unbundlerclass(ui, fp)
     indebug(ui, b'start processing of %s stream' % magicstring)
     return unbundler
 
 
 class unbundle20(unpackermixin):
     """interpret a bundle2 stream
 
     This class is fed with a binary stream and yields parts through its
     `iterparts` methods."""
 
     _magicstring = b'HG20'
 
     def __init__(self, ui, fp):
         """If header is specified, we do not read it out of the stream."""
         self.ui = ui
         self._compengine = util.compengines.forbundletype(b'UN')
         self._compressed = None
         super(unbundle20, self).__init__(fp)
 
     @util.propertycache
     def params(self):
         """dictionary of stream level parameters"""
         indebug(self.ui, b'reading bundle2 stream parameters')
         params = {}
         paramssize = self._unpack(_fstreamparamsize)[0]
         if paramssize < 0:
             raise error.BundleValueError(
                 b'negative bundle param size: %i' % paramssize
             )
         if paramssize:
             params = self._readexact(paramssize)
             params = self._processallparams(params)
         return params
 
     def _processallparams(self, paramsblock):
         """"""
         params = util.sortdict()
         for p in paramsblock.split(b' '):
             p = p.split(b'=', 1)
             p = [urlreq.unquote(i) for i in p]
             if len(p) < 2:
                 p.append(None)
             self._processparam(*p)
             params[p[0]] = p[1]
         return params
 
     def _processparam(self, name, value):
         """process a parameter, applying its effect if needed
 
         Parameter starting with a lower case letter are advisory and will be
         ignored when unknown.  Those starting with an upper case letter are
         mandatory and will this function will raise a KeyError when unknown.
 
         Note: no option are currently supported. Any input will be either
               ignored or failing.
         """
         if not name:
             raise ValueError(r'empty parameter name')
         if name[0:1] not in pycompat.bytestr(string.ascii_letters):
             raise ValueError(r'non letter first character: %s' % name)
         try:
             handler = b2streamparamsmap[name.lower()]
         except KeyError:
             if name[0:1].islower():
                 indebug(self.ui, b"ignoring unknown parameter %s" % name)
             else:
                 raise error.BundleUnknownFeatureError(params=(name,))
         else:
             handler(self, name, value)
 
     def _forwardchunks(self):
         """utility to transfer a bundle2 as binary
 
         This is made necessary by the fact the 'getbundle' command over 'ssh'
         have no way to know then the reply end, relying on the bundle to be
         interpreted to know its end. This is terrible and we are sorry, but we
         needed to move forward to get general delta enabled.
         """
         yield self._magicstring
         assert b'params' not in vars(self)
         paramssize = self._unpack(_fstreamparamsize)[0]
         if paramssize < 0:
             raise error.BundleValueError(
                 b'negative bundle param size: %i' % paramssize
             )
         if paramssize:
             params = self._readexact(paramssize)
             self._processallparams(params)
             # The payload itself is decompressed below, so drop
             # the compression parameter passed down to compensate.
             outparams = []
             for p in params.split(b' '):
                 k, v = p.split(b'=', 1)
                 if k.lower() != b'compression':
                     outparams.append(p)
             outparams = b' '.join(outparams)
             yield _pack(_fstreamparamsize, len(outparams))
             yield outparams
         else:
             yield _pack(_fstreamparamsize, paramssize)
         # From there, payload might need to be decompressed
         self._fp = self._compengine.decompressorreader(self._fp)
         emptycount = 0
         while emptycount < 2:
             # so we can brainlessly loop
             assert _fpartheadersize == _fpayloadsize
             size = self._unpack(_fpartheadersize)[0]
             yield _pack(_fpartheadersize, size)
             if size:
                 emptycount = 0
             else:
                 emptycount += 1
                 continue
             if size == flaginterrupt:
                 continue
             elif size < 0:
                 raise error.BundleValueError(b'negative chunk size: %i')
             yield self._readexact(size)
 
     def iterparts(self, seekable=False):
         """yield all parts contained in the stream"""
         cls = seekableunbundlepart if seekable else unbundlepart
         # make sure param have been loaded
         self.params
         # From there, payload need to be decompressed
         self._fp = self._compengine.decompressorreader(self._fp)
         indebug(self.ui, b'start extraction of bundle2 parts')
         headerblock = self._readpartheader()
         while headerblock is not None:
             part = cls(self.ui, headerblock, self._fp)
             yield part
             # Ensure part is fully consumed so we can start reading the next
             # part.
             part.consume()
 
             headerblock = self._readpartheader()
         indebug(self.ui, b'end of bundle2 stream')
 
     def _readpartheader(self):
         """reads a part header size and return the bytes blob
 
         returns None if empty"""
         headersize = self._unpack(_fpartheadersize)[0]
         if headersize < 0:
             raise error.BundleValueError(
                 b'negative part header size: %i' % headersize
             )
         indebug(self.ui, b'part header size: %i' % headersize)
         if headersize:
             return self._readexact(headersize)
         return None
 
     def compressed(self):
         self.params  # load params
         return self._compressed
 
     def close(self):
         """close underlying file"""
-        if util.safehasattr(self._fp, b'close'):
+        if util.safehasattr(self._fp, 'close'):
             return self._fp.close()
 
 
 formatmap = {b'20': unbundle20}
 
 b2streamparamsmap = {}
 
 
 def b2streamparamhandler(name):
     """register a handler for a stream level parameter"""
 
     def decorator(func):
         assert name not in formatmap
         b2streamparamsmap[name] = func
         return func
 
     return decorator
 
 
 @b2streamparamhandler(b'compression')
 def processcompression(unbundler, param, value):
     """read compression parameter and install payload decompression"""
     if value not in util.compengines.supportedbundletypes:
         raise error.BundleUnknownFeatureError(params=(param,), values=(value,))
     unbundler._compengine = util.compengines.forbundletype(value)
     if value is not None:
         unbundler._compressed = True
 
 
 class bundlepart(object):
     """A bundle2 part contains application level payload
 
     The part `type` is used to route the part to the application level
     handler.
 
     The part payload is contained in ``part.data``. It could be raw bytes or a
     generator of byte chunks.
 
     You can add parameters to the part using the ``addparam`` method.
     Parameters can be either mandatory (default) or advisory. Remote side
     should be able to safely ignore the advisory ones.
 
     Both data and parameters cannot be modified after the generation has begun.
     """
 
     def __init__(
         self,
         parttype,
         mandatoryparams=(),
         advisoryparams=(),
         data=b'',
         mandatory=True,
     ):
         validateparttype(parttype)
         self.id = None
         self.type = parttype
         self._data = data
         self._mandatoryparams = list(mandatoryparams)
         self._advisoryparams = list(advisoryparams)
         # checking for duplicated entries
         self._seenparams = set()
         for pname, __ in self._mandatoryparams + self._advisoryparams:
             if pname in self._seenparams:
                 raise error.ProgrammingError(b'duplicated params: %s' % pname)
             self._seenparams.add(pname)
         # status of the part's generation:
         # - None: not started,
         # - False: currently generated,
         # - True: generation done.
         self._generated = None
         self.mandatory = mandatory
 
     def __repr__(self):
         cls = b"%s.%s" % (self.__class__.__module__, self.__class__.__name__)
         return b'<%s object at %x; id: %s; type: %s; mandatory: %s>' % (
             cls,
             id(self),
             self.id,
             self.type,
             self.mandatory,
         )
 
     def copy(self):
         """return a copy of the part
 
         The new part have the very same content but no partid assigned yet.
         Parts with generated data cannot be copied."""
-        assert not util.safehasattr(self.data, b'next')
+        assert not util.safehasattr(self.data, 'next')
         return self.__class__(
             self.type,
             self._mandatoryparams,
             self._advisoryparams,
             self._data,
             self.mandatory,
         )
 
     # methods used to defines the part content
     @property
     def data(self):
         return self._data
 
     @data.setter
     def data(self, data):
         if self._generated is not None:
             raise error.ReadOnlyPartError(b'part is being generated')
         self._data = data
 
     @property
     def mandatoryparams(self):
         # make it an immutable tuple to force people through ``addparam``
         return tuple(self._mandatoryparams)
 
     @property
     def advisoryparams(self):
         # make it an immutable tuple to force people through ``addparam``
         return tuple(self._advisoryparams)
 
     def addparam(self, name, value=b'', mandatory=True):
         """add a parameter to the part
 
         If 'mandatory' is set to True, the remote handler must claim support
         for this parameter or the unbundling will be aborted.
 
         The 'name' and 'value' cannot exceed 255 bytes each.
         """
         if self._generated is not None:
             raise error.ReadOnlyPartError(b'part is being generated')
         if name in self._seenparams:
             raise ValueError(b'duplicated params: %s' % name)
         self._seenparams.add(name)
         params = self._advisoryparams
         if mandatory:
             params = self._mandatoryparams
         params.append((name, value))
 
     # methods used to generates the bundle2 stream
     def getchunks(self, ui):
         if self._generated is not None:
             raise error.ProgrammingError(b'part can only be consumed once')
         self._generated = False
 
         if ui.debugflag:
             msg = [b'bundle2-output-part: "%s"' % self.type]
             if not self.mandatory:
                 msg.append(b' (advisory)')
             nbmp = len(self.mandatoryparams)
             nbap = len(self.advisoryparams)
             if nbmp or nbap:
                 msg.append(b' (params:')
                 if nbmp:
                     msg.append(b' %i mandatory' % nbmp)
                 if nbap:
                     msg.append(b' %i advisory' % nbmp)
                 msg.append(b')')
             if not self.data:
                 msg.append(b' empty payload')
-            elif util.safehasattr(self.data, b'next') or util.safehasattr(
+            elif util.safehasattr(self.data, 'next') or util.safehasattr(
                 self.data, b'__next__'
             ):
                 msg.append(b' streamed payload')
             else:
                 msg.append(b' %i bytes payload' % len(self.data))
             msg.append(b'\n')
             ui.debug(b''.join(msg))
 
         #### header
         if self.mandatory:
             parttype = self.type.upper()
         else:
             parttype = self.type.lower()
         outdebug(ui, b'part %s: "%s"' % (pycompat.bytestr(self.id), parttype))
         ## parttype
         header = [
             _pack(_fparttypesize, len(parttype)),
             parttype,
             _pack(_fpartid, self.id),
         ]
         ## parameters
         # count
         manpar = self.mandatoryparams
         advpar = self.advisoryparams
         header.append(_pack(_fpartparamcount, len(manpar), len(advpar)))
         # size
         parsizes = []
         for key, value in manpar:
             parsizes.append(len(key))
             parsizes.append(len(value))
         for key, value in advpar:
             parsizes.append(len(key))
             parsizes.append(len(value))
         paramsizes = _pack(_makefpartparamsizes(len(parsizes) // 2), *parsizes)
         header.append(paramsizes)
         # key, value
         for key, value in manpar:
             header.append(key)
             header.append(value)
         for key, value in advpar:
             header.append(key)
             header.append(value)
         ## finalize header
         try:
             headerchunk = b''.join(header)
         except TypeError:
             raise TypeError(
                 r'Found a non-bytes trying to '
                 r'build bundle part header: %r' % header
             )
         outdebug(ui, b'header chunk size: %i' % len(headerchunk))
         yield _pack(_fpartheadersize, len(headerchunk))
         yield headerchunk
         ## payload
         try:
             for chunk in self._payloadchunks():
                 outdebug(ui, b'payload chunk size: %i' % len(chunk))
                 yield _pack(_fpayloadsize, len(chunk))
                 yield chunk
         except GeneratorExit:
             # GeneratorExit means that nobody is listening for our
             # results anyway, so just bail quickly rather than trying
             # to produce an error part.
             ui.debug(b'bundle2-generatorexit\n')
             raise
         except BaseException as exc:
             bexc = stringutil.forcebytestr(exc)
             # backup exception data for later
             ui.debug(
                 b'bundle2-input-stream-interrupt: encoding exception %s' % bexc
             )
             tb = sys.exc_info()[2]
             msg = b'unexpected error: %s' % bexc
             interpart = bundlepart(
                 b'error:abort', [(b'message', msg)], mandatory=False
             )
             interpart.id = 0
             yield _pack(_fpayloadsize, -1)
             for chunk in interpart.getchunks(ui=ui):
                 yield chunk
             outdebug(ui, b'closing payload chunk')
             # abort current part payload
             yield _pack(_fpayloadsize, 0)
             pycompat.raisewithtb(exc, tb)
         # end of payload
         outdebug(ui, b'closing payload chunk')
         yield _pack(_fpayloadsize, 0)
         self._generated = True
 
     def _payloadchunks(self):
         """yield chunks of a the part payload
 
         Exists to handle the different methods to provide data to a part."""
         # we only support fixed size data now.
         # This will be improved in the future.
-        if util.safehasattr(self.data, b'next') or util.safehasattr(
+        if util.safehasattr(self.data, 'next') or util.safehasattr(
             self.data, b'__next__'
         ):
             buff = util.chunkbuffer(self.data)
             chunk = buff.read(preferedchunksize)
             while chunk:
                 yield chunk
                 chunk = buff.read(preferedchunksize)
         elif len(self.data):
             yield self.data
 
 
 flaginterrupt = -1
 
 
 class interrupthandler(unpackermixin):
     """read one part and process it with restricted capability
 
     This allows to transmit exception raised on the producer size during part
     iteration while the consumer is reading a part.
 
     Part processed in this manner only have access to a ui object,"""
 
     def __init__(self, ui, fp):
         super(interrupthandler, self).__init__(fp)
         self.ui = ui
 
     def _readpartheader(self):
         """reads a part header size and return the bytes blob
 
         returns None if empty"""
         headersize = self._unpack(_fpartheadersize)[0]
         if headersize < 0:
             raise error.BundleValueError(
                 b'negative part header size: %i' % headersize
             )
         indebug(self.ui, b'part header size: %i\n' % headersize)
         if headersize:
             return self._readexact(headersize)
         return None
 
     def __call__(self):
 
         self.ui.debug(
             b'bundle2-input-stream-interrupt:' b' opening out of band context\n'
         )
         indebug(self.ui, b'bundle2 stream interruption, looking for a part.')
         headerblock = self._readpartheader()
         if headerblock is None:
             indebug(self.ui, b'no part found during interruption.')
             return
         part = unbundlepart(self.ui, headerblock, self._fp)
         op = interruptoperation(self.ui)
         hardabort = False
         try:
             _processpart(op, part)
         except (SystemExit, KeyboardInterrupt):
             hardabort = True
             raise
         finally:
             if not hardabort:
                 part.consume()
         self.ui.debug(
             b'bundle2-input-stream-interrupt:' b' closing out of band context\n'
         )
 
 
 class interruptoperation(object):
     """A limited operation to be use by part handler during interruption
 
     It only have access to an ui object.
     """
 
     def __init__(self, ui):
         self.ui = ui
         self.reply = None
         self.captureoutput = False
 
     @property
     def repo(self):
         raise error.ProgrammingError(b'no repo access from stream interruption')
 
     def gettransaction(self):
         raise TransactionUnavailable(b'no repo access from stream interruption')
 
 
 def decodepayloadchunks(ui, fh):
     """Reads bundle2 part payload data into chunks.
 
     Part payload data consists of framed chunks. This function takes
     a file handle and emits those chunks.
     """
     dolog = ui.configbool(b'devel', b'bundle2.debug')
     debug = ui.debug
 
     headerstruct = struct.Struct(_fpayloadsize)
     headersize = headerstruct.size
     unpack = headerstruct.unpack
 
     readexactly = changegroup.readexactly
     read = fh.read
 
     chunksize = unpack(readexactly(fh, headersize))[0]
     indebug(ui, b'payload chunk size: %i' % chunksize)
 
     # changegroup.readexactly() is inlined below for performance.
     while chunksize:
         if chunksize >= 0:
             s = read(chunksize)
             if len(s) < chunksize:
                 raise error.Abort(
                     _(
                         b'stream ended unexpectedly '
                         b' (got %d bytes, expected %d)'
                     )
                     % (len(s), chunksize)
                 )
 
             yield s
         elif chunksize == flaginterrupt:
             # Interrupt "signal" detected. The regular stream is interrupted
             # and a bundle2 part follows. Consume it.
             interrupthandler(ui, fh)()
         else:
             raise error.BundleValueError(
                 b'negative payload chunk size: %s' % chunksize
             )
 
         s = read(headersize)
         if len(s) < headersize:
             raise error.Abort(
                 _(b'stream ended unexpectedly ' b' (got %d bytes, expected %d)')
                 % (len(s), chunksize)
             )
 
         chunksize = unpack(s)[0]
 
         # indebug() inlined for performance.
         if dolog:
             debug(b'bundle2-input: payload chunk size: %i\n' % chunksize)
 
 
 class unbundlepart(unpackermixin):
     """a bundle part read from a bundle"""
 
     def __init__(self, ui, header, fp):
         super(unbundlepart, self).__init__(fp)
-        self._seekable = util.safehasattr(fp, b'seek') and util.safehasattr(
+        self._seekable = util.safehasattr(fp, 'seek') and util.safehasattr(
             fp, b'tell'
         )
         self.ui = ui
         # unbundle state attr
         self._headerdata = header
         self._headeroffset = 0
         self._initialized = False
         self.consumed = False
         # part data
         self.id = None
         self.type = None
         self.mandatoryparams = None
         self.advisoryparams = None
         self.params = None
         self.mandatorykeys = ()
         self._readheader()
         self._mandatory = None
         self._pos = 0
 
     def _fromheader(self, size):
         """return the next <size> byte from the header"""
         offset = self._headeroffset
         data = self._headerdata[offset : (offset + size)]
         self._headeroffset = offset + size
         return data
 
     def _unpackheader(self, format):
         """read given format from header
 
         This automatically compute the size of the format to read."""
         data = self._fromheader(struct.calcsize(format))
         return _unpack(format, data)
 
     def _initparams(self, mandatoryparams, advisoryparams):
         """internal function to setup all logic related parameters"""
         # make it read only to prevent people touching it by mistake.
         self.mandatoryparams = tuple(mandatoryparams)
         self.advisoryparams = tuple(advisoryparams)
         # user friendly UI
         self.params = util.sortdict(self.mandatoryparams)
         self.params.update(self.advisoryparams)
         self.mandatorykeys = frozenset(p[0] for p in mandatoryparams)
 
     def _readheader(self):
         """read the header and setup the object"""
         typesize = self._unpackheader(_fparttypesize)[0]
         self.type = self._fromheader(typesize)
         indebug(self.ui, b'part type: "%s"' % self.type)
         self.id = self._unpackheader(_fpartid)[0]
         indebug(self.ui, b'part id: "%s"' % pycompat.bytestr(self.id))
         # extract mandatory bit from type
         self.mandatory = self.type != self.type.lower()
         self.type = self.type.lower()
         ## reading parameters
         # param count
         mancount, advcount = self._unpackheader(_fpartparamcount)
         indebug(self.ui, b'part parameters: %i' % (mancount + advcount))
         # param size
         fparamsizes = _makefpartparamsizes(mancount + advcount)
         paramsizes = self._unpackheader(fparamsizes)
         # make it a list of couple again
         paramsizes = list(zip(paramsizes[::2], paramsizes[1::2]))
         # split mandatory from advisory
         mansizes = paramsizes[:mancount]
         advsizes = paramsizes[mancount:]
         # retrieve param value
         manparams = []
         for key, value in mansizes:
             manparams.append((self._fromheader(key), self._fromheader(value)))
         advparams = []
         for key, value in advsizes:
             advparams.append((self._fromheader(key), self._fromheader(value)))
         self._initparams(manparams, advparams)
         ## part payload
         self._payloadstream = util.chunkbuffer(self._payloadchunks())
         # we read the data, tell it
         self._initialized = True
 
     def _payloadchunks(self):
         """Generator of decoded chunks in the payload."""
         return decodepayloadchunks(self.ui, self._fp)
 
     def consume(self):
         """Read the part payload until completion.
 
         By consuming the part data, the underlying stream read offset will
         be advanced to the next part (or end of stream).
         """
         if self.consumed:
             return
 
         chunk = self.read(32768)
         while chunk:
             self._pos += len(chunk)
             chunk = self.read(32768)
 
     def read(self, size=None):
         """read payload data"""
         if not self._initialized:
             self._readheader()
         if size is None:
             data = self._payloadstream.read()
         else:
             data = self._payloadstream.read(size)
         self._pos += len(data)
         if size is None or len(data) < size:
             if not self.consumed and self._pos:
                 self.ui.debug(
                     b'bundle2-input-part: total payload size %i\n' % self._pos
                 )
             self.consumed = True
         return data
 
 
 class seekableunbundlepart(unbundlepart):
     """A bundle2 part in a bundle that is seekable.
 
     Regular ``unbundlepart`` instances can only be read once. This class
     extends ``unbundlepart`` to enable bi-directional seeking within the
     part.
 
     Bundle2 part data consists of framed chunks. Offsets when seeking
     refer to the decoded data, not the offsets in the underlying bundle2
     stream.
 
     To facilitate quickly seeking within the decoded data, instances of this
     class maintain a mapping between offsets in the underlying stream and
     the decoded payload. This mapping will consume memory in proportion
     to the number of chunks within the payload (which almost certainly
     increases in proportion with the size of the part).
     """
 
     def __init__(self, ui, header, fp):
         # (payload, file) offsets for chunk starts.
         self._chunkindex = []
 
         super(seekableunbundlepart, self).__init__(ui, header, fp)
 
     def _payloadchunks(self, chunknum=0):
         '''seek to specified chunk and start yielding data'''
         if len(self._chunkindex) == 0:
             assert chunknum == 0, b'Must start with chunk 0'
             self._chunkindex.append((0, self._tellfp()))
         else:
             assert chunknum < len(self._chunkindex), (
                 b'Unknown chunk %d' % chunknum
             )
             self._seekfp(self._chunkindex[chunknum][1])
 
         pos = self._chunkindex[chunknum][0]
 
         for chunk in decodepayloadchunks(self.ui, self._fp):
             chunknum += 1
             pos += len(chunk)
             if chunknum == len(self._chunkindex):
                 self._chunkindex.append((pos, self._tellfp()))
 
             yield chunk
 
     def _findchunk(self, pos):
         '''for a given payload position, return a chunk number and offset'''
         for chunk, (ppos, fpos) in enumerate(self._chunkindex):
             if ppos == pos:
                 return chunk, 0
             elif ppos > pos:
                 return chunk - 1, pos - self._chunkindex[chunk - 1][0]
         raise ValueError(b'Unknown chunk')
 
     def tell(self):
         return self._pos
 
     def seek(self, offset, whence=os.SEEK_SET):
         if whence == os.SEEK_SET:
             newpos = offset
         elif whence == os.SEEK_CUR:
             newpos = self._pos + offset
         elif whence == os.SEEK_END:
             if not self.consumed:
                 # Can't use self.consume() here because it advances self._pos.
                 chunk = self.read(32768)
                 while chunk:
                     chunk = self.read(32768)
             newpos = self._chunkindex[-1][0] - offset
         else:
             raise ValueError(b'Unknown whence value: %r' % (whence,))
 
         if newpos > self._chunkindex[-1][0] and not self.consumed:
             # Can't use self.consume() here because it advances self._pos.
             chunk = self.read(32768)
             while chunk:
                 chunk = self.read(32668)
 
         if not 0 <= newpos <= self._chunkindex[-1][0]:
             raise ValueError(b'Offset out of range')
 
         if self._pos != newpos:
             chunk, internaloffset = self._findchunk(newpos)
             self._payloadstream = util.chunkbuffer(self._payloadchunks(chunk))
             adjust = self.read(internaloffset)
             if len(adjust) != internaloffset:
                 raise error.Abort(_(b'Seek failed\n'))
             self._pos = newpos
 
     def _seekfp(self, offset, whence=0):
         """move the underlying file pointer
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         if self._seekable:
             return self._fp.seek(offset, whence)
         else:
             raise NotImplementedError(_(b'File pointer is not seekable'))
 
     def _tellfp(self):
         """return the file offset, or None if file is not seekable
 
         This method is meant for internal usage by the bundle2 protocol only.
         They directly manipulate the low level stream including bundle2 level
         instruction.
 
         Do not use it to implement higher-level logic or methods."""
         if self._seekable:
             try:
                 return self._fp.tell()
             except IOError as e:
                 if e.errno == errno.ESPIPE:
                     self._seekable = False
                 else:
                     raise
         return None
 
 
 # These are only the static capabilities.
 # Check the 'getrepocaps' function for the rest.
 capabilities = {
     b'HG20': (),
     b'bookmarks': (),
     b'error': (b'abort', b'unsupportedcontent', b'pushraced', b'pushkey'),
     b'listkeys': (),
     b'pushkey': (),
     b'digests': tuple(sorted(util.DIGESTS.keys())),
     b'remote-changegroup': (b'http', b'https'),
     b'hgtagsfnodes': (),
     b'rev-branch-cache': (),
     b'phases': (b'heads',),
     b'stream': (b'v2',),
 }
 
 
 def getrepocaps(repo, allowpushback=False, role=None):
     """return the bundle2 capabilities for a given repo
 
     Exists to allow extensions (like evolution) to mutate the capabilities.
 
     The returned value is used for servers advertising their capabilities as
     well as clients advertising their capabilities to servers as part of
     bundle2 requests. The ``role`` argument specifies which is which.
     """
     if role not in (b'client', b'server'):
         raise error.ProgrammingError(b'role argument must be client or server')
 
     caps = capabilities.copy()
     caps[b'changegroup'] = tuple(
         sorted(changegroup.supportedincomingversions(repo))
     )
     if obsolete.isenabled(repo, obsolete.exchangeopt):
         supportedformat = tuple(b'V%i' % v for v in obsolete.formats)
         caps[b'obsmarkers'] = supportedformat
     if allowpushback:
         caps[b'pushback'] = ()
     cpmode = repo.ui.config(b'server', b'concurrent-push-mode')
     if cpmode == b'check-related':
         caps[b'checkheads'] = (b'related',)
     if b'phases' in repo.ui.configlist(b'devel', b'legacy.exchange'):
         caps.pop(b'phases')
 
     # Don't advertise stream clone support in server mode if not configured.
     if role == b'server':
         streamsupported = repo.ui.configbool(
             b'server', b'uncompressed', untrusted=True
         )
         featuresupported = repo.ui.configbool(b'server', b'bundle2.stream')
 
         if not streamsupported or not featuresupported:
             caps.pop(b'stream')
     # Else always advertise support on client, because payload support
     # should always be advertised.
 
     return caps
 
 
 def bundle2caps(remote):
     """return the bundle capabilities of a peer as dict"""
     raw = remote.capable(b'bundle2')
     if not raw and raw != b'':
         return {}
     capsblob = urlreq.unquote(remote.capable(b'bundle2'))
     return decodecaps(capsblob)
 
 
 def obsmarkersversion(caps):
     """extract the list of supported obsmarkers versions from a bundle2caps dict
     """
     obscaps = caps.get(b'obsmarkers', ())
     return [int(c[1:]) for c in obscaps if c.startswith(b'V')]
 
 
 def writenewbundle(
     ui,
     repo,
     source,
     filename,
     bundletype,
     outgoing,
     opts,
     vfs=None,
     compression=None,
     compopts=None,
 ):
     if bundletype.startswith(b'HG10'):
         cg = changegroup.makechangegroup(repo, outgoing, b'01', source)
         return writebundle(
             ui,
             cg,
             filename,
             bundletype,
             vfs=vfs,
             compression=compression,
             compopts=compopts,
         )
     elif not bundletype.startswith(b'HG20'):
         raise error.ProgrammingError(b'unknown bundle type: %s' % bundletype)
 
     caps = {}
     if b'obsolescence' in opts:
         caps[b'obsmarkers'] = (b'V1',)
     bundle = bundle20(ui, caps)
     bundle.setcompression(compression, compopts)
     _addpartsfromopts(ui, repo, bundle, source, outgoing, opts)
     chunkiter = bundle.getchunks()
 
     return changegroup.writechunks(ui, chunkiter, filename, vfs=vfs)
 
 
 def _addpartsfromopts(ui, repo, bundler, source, outgoing, opts):
     # We should eventually reconcile this logic with the one behind
     # 'exchange.getbundle2partsgenerator'.
     #
     # The type of input from 'getbundle' and 'writenewbundle' are a bit
     # different right now. So we keep them separated for now for the sake of
     # simplicity.
 
     # we might not always want a changegroup in such bundle, for example in
     # stream bundles
     if opts.get(b'changegroup', True):
         cgversion = opts.get(b'cg.version')
         if cgversion is None:
             cgversion = changegroup.safeversion(repo)
         cg = changegroup.makechangegroup(repo, outgoing, cgversion, source)
         part = bundler.newpart(b'changegroup', data=cg.getchunks())
         part.addparam(b'version', cg.version)
         if b'clcount' in cg.extras:
             part.addparam(
                 b'nbchanges', b'%d' % cg.extras[b'clcount'], mandatory=False
             )
         if opts.get(b'phases') and repo.revs(
             b'%ln and secret()', outgoing.missingheads
         ):
             part.addparam(
                 b'targetphase', b'%d' % phases.secret, mandatory=False
             )
 
     if opts.get(b'streamv2', False):
         addpartbundlestream2(bundler, repo, stream=True)
 
     if opts.get(b'tagsfnodescache', True):
         addparttagsfnodescache(repo, bundler, outgoing)
 
     if opts.get(b'revbranchcache', True):
         addpartrevbranchcache(repo, bundler, outgoing)
 
     if opts.get(b'obsolescence', False):
         obsmarkers = repo.obsstore.relevantmarkers(outgoing.missing)
         buildobsmarkerspart(bundler, obsmarkers)
 
     if opts.get(b'phases', False):
         headsbyphase = phases.subsetphaseheads(repo, outgoing.missing)
         phasedata = phases.binaryencode(headsbyphase)
         bundler.newpart(b'phase-heads', data=phasedata)
 
 
 def addparttagsfnodescache(repo, bundler, outgoing):
     # we include the tags fnode cache for the bundle changeset
     # (as an optional parts)
     cache = tags.hgtagsfnodescache(repo.unfiltered())
     chunks = []
 
     # .hgtags fnodes are only relevant for head changesets. While we could
     # transfer values for all known nodes, there will likely be little to
     # no benefit.
     #
     # We don't bother using a generator to produce output data because
     # a) we only have 40 bytes per head and even esoteric numbers of heads
     # consume little memory (1M heads is 40MB) b) we don't want to send the
     # part if we don't have entries and knowing if we have entries requires
     # cache lookups.
     for node in outgoing.missingheads:
         # Don't compute missing, as this may slow down serving.
         fnode = cache.getfnode(node, computemissing=False)
         if fnode is not None:
             chunks.extend([node, fnode])
 
     if chunks:
         bundler.newpart(b'hgtagsfnodes', data=b''.join(chunks))
 
 
 def addpartrevbranchcache(repo, bundler, outgoing):
     # we include the rev branch cache for the bundle changeset
     # (as an optional parts)
     cache = repo.revbranchcache()
     cl = repo.unfiltered().changelog
     branchesdata = collections.defaultdict(lambda: (set(), set()))
     for node in outgoing.missing:
         branch, close = cache.branchinfo(cl.rev(node))
         branchesdata[branch][close].add(node)
 
     def generate():
         for branch, (nodes, closed) in sorted(branchesdata.items()):
             utf8branch = encoding.fromlocal(branch)
             yield rbcstruct.pack(len(utf8branch), len(nodes), len(closed))
             yield utf8branch
             for n in sorted(nodes):
                 yield n
             for n in sorted(closed):
                 yield n
 
     bundler.newpart(b'cache:rev-branch-cache', data=generate(), mandatory=False)
 
 
 def _formatrequirementsspec(requirements):
     requirements = [req for req in requirements if req != b"shared"]
     return urlreq.quote(b','.join(sorted(requirements)))
 
 
 def _formatrequirementsparams(requirements):
     requirements = _formatrequirementsspec(requirements)
     params = b"%s%s" % (urlreq.quote(b"requirements="), requirements)
     return params
 
 
 def addpartbundlestream2(bundler, repo, **kwargs):
     if not kwargs.get(r'stream', False):
         return
 
     if not streamclone.allowservergeneration(repo):
         raise error.Abort(
             _(
                 b'stream data requested but server does not allow '
                 b'this feature'
             ),
             hint=_(
                 b'well-behaved clients should not be '
                 b'requesting stream data from servers not '
                 b'advertising it; the client may be buggy'
             ),
         )
 
     # Stream clones don't compress well. And compression undermines a
     # goal of stream clones, which is to be fast. Communicate the desire
     # to avoid compression to consumers of the bundle.
     bundler.prefercompressed = False
 
     # get the includes and excludes
     includepats = kwargs.get(r'includepats')
     excludepats = kwargs.get(r'excludepats')
 
     narrowstream = repo.ui.configbool(
         b'experimental', b'server.stream-narrow-clones'
     )
 
     if (includepats or excludepats) and not narrowstream:
         raise error.Abort(_(b'server does not support narrow stream clones'))
 
     includeobsmarkers = False
     if repo.obsstore:
         remoteversions = obsmarkersversion(bundler.capabilities)
         if not remoteversions:
             raise error.Abort(
                 _(
                     b'server has obsolescence markers, but client '
                     b'cannot receive them via stream clone'
                 )
             )
         elif repo.obsstore._version in remoteversions:
             includeobsmarkers = True
 
     filecount, bytecount, it = streamclone.generatev2(
         repo, includepats, excludepats, includeobsmarkers
     )
     requirements = _formatrequirementsspec(repo.requirements)
     part = bundler.newpart(b'stream2', data=it)
     part.addparam(b'bytecount', b'%d' % bytecount, mandatory=True)
     part.addparam(b'filecount', b'%d' % filecount, mandatory=True)
     part.addparam(b'requirements', requirements, mandatory=True)
 
 
 def buildobsmarkerspart(bundler, markers):
     """add an obsmarker part to the bundler with <markers>
 
     No part is created if markers is empty.
     Raises ValueError if the bundler doesn't support any known obsmarker format.
     """
     if not markers:
         return None
 
     remoteversions = obsmarkersversion(bundler.capabilities)
     version = obsolete.commonversion(remoteversions)
     if version is None:
         raise ValueError(b'bundler does not support common obsmarker format')
     stream = obsolete.encodemarkers(markers, True, version=version)
     return bundler.newpart(b'obsmarkers', data=stream)
 
 
 def writebundle(
     ui, cg, filename, bundletype, vfs=None, compression=None, compopts=None
 ):
     """Write a bundle file and return its filename.
 
     Existing files will not be overwritten.
     If no filename is specified, a temporary file is created.
     bz2 compression can be turned off.
     The bundle file will be deleted in case of errors.
     """
 
     if bundletype == b"HG20":
         bundle = bundle20(ui)
         bundle.setcompression(compression, compopts)
         part = bundle.newpart(b'changegroup', data=cg.getchunks())
         part.addparam(b'version', cg.version)
         if b'clcount' in cg.extras:
             part.addparam(
                 b'nbchanges', b'%d' % cg.extras[b'clcount'], mandatory=False
             )
         chunkiter = bundle.getchunks()
     else:
         # compression argument is only for the bundle2 case
         assert compression is None
         if cg.version != b'01':
             raise error.Abort(
                 _(b'old bundle types only supports v1 ' b'changegroups')
             )
         header, comp = bundletypes[bundletype]
         if comp not in util.compengines.supportedbundletypes:
             raise error.Abort(_(b'unknown stream compression type: %s') % comp)
         compengine = util.compengines.forbundletype(comp)
 
         def chunkiter():
             yield header
             for chunk in compengine.compressstream(cg.getchunks(), compopts):
                 yield chunk
 
         chunkiter = chunkiter()
 
     # parse the changegroup data, otherwise we will block
     # in case of sshrepo because we don't know the end of the stream
     return changegroup.writechunks(ui, chunkiter, filename, vfs=vfs)
 
 
 def combinechangegroupresults(op):
     """logic to combine 0 or more addchangegroup results into one"""
     results = [r.get(b'return', 0) for r in op.records[b'changegroup']]
     changedheads = 0
     result = 1
     for ret in results:
         # If any changegroup result is 0, return 0
         if ret == 0:
             result = 0
             break
         if ret < -1:
             changedheads += ret + 1
         elif ret > 1:
             changedheads += ret - 1
     if changedheads > 0:
         result = 1 + changedheads
     elif changedheads < 0:
         result = -1 + changedheads
     return result
 
 
 @parthandler(
     b'changegroup', (b'version', b'nbchanges', b'treemanifest', b'targetphase')
 )
 def handlechangegroup(op, inpart):
     """apply a changegroup part on the repo
 
     This is a very early implementation that will massive rework before being
     inflicted to any end-user.
     """
     from . import localrepo
 
     tr = op.gettransaction()
     unpackerversion = inpart.params.get(b'version', b'01')
     # We should raise an appropriate exception here
     cg = changegroup.getunbundler(unpackerversion, inpart, None)
     # the source and url passed here are overwritten by the one contained in
     # the transaction.hookargs argument. So 'bundle2' is a placeholder
     nbchangesets = None
     if b'nbchanges' in inpart.params:
         nbchangesets = int(inpart.params.get(b'nbchanges'))
     if (
         b'treemanifest' in inpart.params
         and b'treemanifest' not in op.repo.requirements
     ):
         if len(op.repo.changelog) != 0:
             raise error.Abort(
                 _(
                     b"bundle contains tree manifests, but local repo is "
                     b"non-empty and does not use tree manifests"
                 )
             )
         op.repo.requirements.add(b'treemanifest')
         op.repo.svfs.options = localrepo.resolvestorevfsoptions(
             op.repo.ui, op.repo.requirements, op.repo.features
         )
         op.repo._writerequirements()
     extrakwargs = {}
     targetphase = inpart.params.get(b'targetphase')
     if targetphase is not None:
         extrakwargs[r'targetphase'] = int(targetphase)
     ret = _processchangegroup(
         op,
         cg,
         tr,
         b'bundle2',
         b'bundle2',
         expectedtotal=nbchangesets,
         **extrakwargs
     )
     if op.reply is not None:
         # This is definitely not the final form of this
         # return. But one need to start somewhere.
         part = op.reply.newpart(b'reply:changegroup', mandatory=False)
         part.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         part.addparam(b'return', b'%i' % ret, mandatory=False)
     assert not inpart.read()
 
 
 _remotechangegroupparams = tuple(
     [b'url', b'size', b'digests']
     + [b'digest:%s' % k for k in util.DIGESTS.keys()]
 )
 
 
 @parthandler(b'remote-changegroup', _remotechangegroupparams)
 def handleremotechangegroup(op, inpart):
     """apply a bundle10 on the repo, given an url and validation information
 
     All the information about the remote bundle to import are given as
     parameters. The parameters include:
       - url: the url to the bundle10.
       - size: the bundle10 file size. It is used to validate what was
         retrieved by the client matches the server knowledge about the bundle.
       - digests: a space separated list of the digest types provided as
         parameters.
       - digest:<digest-type>: the hexadecimal representation of the digest with
         that name. Like the size, it is used to validate what was retrieved by
         the client matches what the server knows about the bundle.
 
     When multiple digest types are given, all of them are checked.
     """
     try:
         raw_url = inpart.params[b'url']
     except KeyError:
         raise error.Abort(_(b'remote-changegroup: missing "%s" param') % b'url')
     parsed_url = util.url(raw_url)
     if parsed_url.scheme not in capabilities[b'remote-changegroup']:
         raise error.Abort(
             _(b'remote-changegroup does not support %s urls')
             % parsed_url.scheme
         )
 
     try:
         size = int(inpart.params[b'size'])
     except ValueError:
         raise error.Abort(
             _(b'remote-changegroup: invalid value for param "%s"') % b'size'
         )
     except KeyError:
         raise error.Abort(
             _(b'remote-changegroup: missing "%s" param') % b'size'
         )
 
     digests = {}
     for typ in inpart.params.get(b'digests', b'').split():
         param = b'digest:%s' % typ
         try:
             value = inpart.params[param]
         except KeyError:
             raise error.Abort(
                 _(b'remote-changegroup: missing "%s" param') % param
             )
         digests[typ] = value
 
     real_part = util.digestchecker(url.open(op.ui, raw_url), size, digests)
 
     tr = op.gettransaction()
     from . import exchange
 
     cg = exchange.readbundle(op.repo.ui, real_part, raw_url)
     if not isinstance(cg, changegroup.cg1unpacker):
         raise error.Abort(
             _(b'%s: not a bundle version 1.0') % util.hidepassword(raw_url)
         )
     ret = _processchangegroup(op, cg, tr, b'bundle2', b'bundle2')
     if op.reply is not None:
         # This is definitely not the final form of this
         # return. But one need to start somewhere.
         part = op.reply.newpart(b'reply:changegroup')
         part.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         part.addparam(b'return', b'%i' % ret, mandatory=False)
     try:
         real_part.validate()
     except error.Abort as e:
         raise error.Abort(
             _(b'bundle at %s is corrupted:\n%s')
             % (util.hidepassword(raw_url), bytes(e))
         )
     assert not inpart.read()
 
 
 @parthandler(b'reply:changegroup', (b'return', b'in-reply-to'))
 def handlereplychangegroup(op, inpart):
     ret = int(inpart.params[b'return'])
     replyto = int(inpart.params[b'in-reply-to'])
     op.records.add(b'changegroup', {b'return': ret}, replyto)
 
 
 @parthandler(b'check:bookmarks')
 def handlecheckbookmarks(op, inpart):
     """check location of bookmarks
 
     This part is to be used to detect push race regarding bookmark, it
     contains binary encoded (bookmark, node) tuple. If the local state does
     not marks the one in the part, a PushRaced exception is raised
     """
     bookdata = bookmarks.binarydecode(inpart)
 
     msgstandard = (
         b'remote repository changed while pushing - please try again '
         b'(bookmark "%s" move from %s to %s)'
     )
     msgmissing = (
         b'remote repository changed while pushing - please try again '
         b'(bookmark "%s" is missing, expected %s)'
     )
     msgexist = (
         b'remote repository changed while pushing - please try again '
         b'(bookmark "%s" set on %s, expected missing)'
     )
     for book, node in bookdata:
         currentnode = op.repo._bookmarks.get(book)
         if currentnode != node:
             if node is None:
                 finalmsg = msgexist % (book, nodemod.short(currentnode))
             elif currentnode is None:
                 finalmsg = msgmissing % (book, nodemod.short(node))
             else:
                 finalmsg = msgstandard % (
                     book,
                     nodemod.short(node),
                     nodemod.short(currentnode),
                 )
             raise error.PushRaced(finalmsg)
 
 
 @parthandler(b'check:heads')
 def handlecheckheads(op, inpart):
     """check that head of the repo did not change
 
     This is used to detect a push race when using unbundle.
     This replaces the "heads" argument of unbundle."""
     h = inpart.read(20)
     heads = []
     while len(h) == 20:
         heads.append(h)
         h = inpart.read(20)
     assert not h
     # Trigger a transaction so that we are guaranteed to have the lock now.
     if op.ui.configbool(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
     if sorted(heads) != sorted(op.repo.heads()):
         raise error.PushRaced(
             b'remote repository changed while pushing - ' b'please try again'
         )
 
 
 @parthandler(b'check:updated-heads')
 def handlecheckupdatedheads(op, inpart):
     """check for race on the heads touched by a push
 
     This is similar to 'check:heads' but focus on the heads actually updated
     during the push. If other activities happen on unrelated heads, it is
     ignored.
 
     This allow server with high traffic to avoid push contention as long as
     unrelated parts of the graph are involved."""
     h = inpart.read(20)
     heads = []
     while len(h) == 20:
         heads.append(h)
         h = inpart.read(20)
     assert not h
     # trigger a transaction so that we are guaranteed to have the lock now.
     if op.ui.configbool(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
 
     currentheads = set()
     for ls in op.repo.branchmap().iterheads():
         currentheads.update(ls)
 
     for h in heads:
         if h not in currentheads:
             raise error.PushRaced(
                 b'remote repository changed while pushing - '
                 b'please try again'
             )
 
 
 @parthandler(b'check:phases')
 def handlecheckphases(op, inpart):
     """check that phase boundaries of the repository did not change
 
     This is used to detect a push race.
     """
     phasetonodes = phases.binarydecode(inpart)
     unfi = op.repo.unfiltered()
     cl = unfi.changelog
     phasecache = unfi._phasecache
     msg = (
         b'remote repository changed while pushing - please try again '
         b'(%s is %s expected %s)'
     )
     for expectedphase, nodes in enumerate(phasetonodes):
         for n in nodes:
             actualphase = phasecache.phase(unfi, cl.rev(n))
             if actualphase != expectedphase:
                 finalmsg = msg % (
                     nodemod.short(n),
                     phases.phasenames[actualphase],
                     phases.phasenames[expectedphase],
                 )
                 raise error.PushRaced(finalmsg)
 
 
 @parthandler(b'output')
 def handleoutput(op, inpart):
     """forward output captured on the server to the client"""
     for line in inpart.read().splitlines():
         op.ui.status(_(b'remote: %s\n') % line)
 
 
 @parthandler(b'replycaps')
 def handlereplycaps(op, inpart):
     """Notify that a reply bundle should be created
 
     The payload contains the capabilities information for the reply"""
     caps = decodecaps(inpart.read())
     if op.reply is None:
         op.reply = bundle20(op.ui, caps)
 
 
 class AbortFromPart(error.Abort):
     """Sub-class of Abort that denotes an error from a bundle2 part."""
 
 
 @parthandler(b'error:abort', (b'message', b'hint'))
 def handleerrorabort(op, inpart):
     """Used to transmit abort error over the wire"""
     raise AbortFromPart(
         inpart.params[b'message'], hint=inpart.params.get(b'hint')
     )
 
 
 @parthandler(
     b'error:pushkey',
     (b'namespace', b'key', b'new', b'old', b'ret', b'in-reply-to'),
 )
 def handleerrorpushkey(op, inpart):
     """Used to transmit failure of a mandatory pushkey over the wire"""
     kwargs = {}
     for name in (b'namespace', b'key', b'new', b'old', b'ret'):
         value = inpart.params.get(name)
         if value is not None:
             kwargs[name] = value
     raise error.PushkeyFailed(
         inpart.params[b'in-reply-to'], **pycompat.strkwargs(kwargs)
     )
 
 
 @parthandler(b'error:unsupportedcontent', (b'parttype', b'params'))
 def handleerrorunsupportedcontent(op, inpart):
     """Used to transmit unknown content error over the wire"""
     kwargs = {}
     parttype = inpart.params.get(b'parttype')
     if parttype is not None:
         kwargs[b'parttype'] = parttype
     params = inpart.params.get(b'params')
     if params is not None:
         kwargs[b'params'] = params.split(b'\0')
 
     raise error.BundleUnknownFeatureError(**pycompat.strkwargs(kwargs))
 
 
 @parthandler(b'error:pushraced', (b'message',))
 def handleerrorpushraced(op, inpart):
     """Used to transmit push race error over the wire"""
     raise error.ResponseError(_(b'push failed:'), inpart.params[b'message'])
 
 
 @parthandler(b'listkeys', (b'namespace',))
 def handlelistkeys(op, inpart):
     """retrieve pushkey namespace content stored in a bundle2"""
     namespace = inpart.params[b'namespace']
     r = pushkey.decodekeys(inpart.read())
     op.records.add(b'listkeys', (namespace, r))
 
 
 @parthandler(b'pushkey', (b'namespace', b'key', b'old', b'new'))
 def handlepushkey(op, inpart):
     """process a pushkey request"""
     dec = pushkey.decode
     namespace = dec(inpart.params[b'namespace'])
     key = dec(inpart.params[b'key'])
     old = dec(inpart.params[b'old'])
     new = dec(inpart.params[b'new'])
     # Grab the transaction to ensure that we have the lock before performing the
     # pushkey.
     if op.ui.configbool(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
     ret = op.repo.pushkey(namespace, key, old, new)
     record = {b'namespace': namespace, b'key': key, b'old': old, b'new': new}
     op.records.add(b'pushkey', record)
     if op.reply is not None:
         rpart = op.reply.newpart(b'reply:pushkey')
         rpart.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         rpart.addparam(b'return', b'%i' % ret, mandatory=False)
     if inpart.mandatory and not ret:
         kwargs = {}
         for key in (b'namespace', b'key', b'new', b'old', b'ret'):
             if key in inpart.params:
                 kwargs[key] = inpart.params[key]
         raise error.PushkeyFailed(
             partid=b'%d' % inpart.id, **pycompat.strkwargs(kwargs)
         )
 
 
 @parthandler(b'bookmarks')
 def handlebookmark(op, inpart):
     """transmit bookmark information
 
     The part contains binary encoded bookmark information.
 
     The exact behavior of this part can be controlled by the 'bookmarks' mode
     on the bundle operation.
 
     When mode is 'apply' (the default) the bookmark information is applied as
     is to the unbundling repository. Make sure a 'check:bookmarks' part is
     issued earlier to check for push races in such update. This behavior is
     suitable for pushing.
 
     When mode is 'records', the information is recorded into the 'bookmarks'
     records of the bundle operation. This behavior is suitable for pulling.
     """
     changes = bookmarks.binarydecode(inpart)
 
     pushkeycompat = op.repo.ui.configbool(
         b'server', b'bookmarks-pushkey-compat'
     )
     bookmarksmode = op.modes.get(b'bookmarks', b'apply')
 
     if bookmarksmode == b'apply':
         tr = op.gettransaction()
         bookstore = op.repo._bookmarks
         if pushkeycompat:
             allhooks = []
             for book, node in changes:
                 hookargs = tr.hookargs.copy()
                 hookargs[b'pushkeycompat'] = b'1'
                 hookargs[b'namespace'] = b'bookmarks'
                 hookargs[b'key'] = book
                 hookargs[b'old'] = nodemod.hex(bookstore.get(book, b''))
                 hookargs[b'new'] = nodemod.hex(
                     node if node is not None else b''
                 )
                 allhooks.append(hookargs)
 
             for hookargs in allhooks:
                 op.repo.hook(
                     b'prepushkey', throw=True, **pycompat.strkwargs(hookargs)
                 )
 
         bookstore.applychanges(op.repo, op.gettransaction(), changes)
 
         if pushkeycompat:
 
             def runhook():
                 for hookargs in allhooks:
                     op.repo.hook(b'pushkey', **pycompat.strkwargs(hookargs))
 
             op.repo._afterlock(runhook)
 
     elif bookmarksmode == b'records':
         for book, node in changes:
             record = {b'bookmark': book, b'node': node}
             op.records.add(b'bookmarks', record)
     else:
         raise error.ProgrammingError(
             b'unkown bookmark mode: %s' % bookmarksmode
         )
 
 
 @parthandler(b'phase-heads')
 def handlephases(op, inpart):
     """apply phases from bundle part to repo"""
     headsbyphase = phases.binarydecode(inpart)
     phases.updatephases(op.repo.unfiltered(), op.gettransaction, headsbyphase)
 
 
 @parthandler(b'reply:pushkey', (b'return', b'in-reply-to'))
 def handlepushkeyreply(op, inpart):
     """retrieve the result of a pushkey request"""
     ret = int(inpart.params[b'return'])
     partid = int(inpart.params[b'in-reply-to'])
     op.records.add(b'pushkey', {b'return': ret}, partid)
 
 
 @parthandler(b'obsmarkers')
 def handleobsmarker(op, inpart):
     """add a stream of obsmarkers to the repo"""
     tr = op.gettransaction()
     markerdata = inpart.read()
     if op.ui.config(b'experimental', b'obsmarkers-exchange-debug'):
         op.ui.writenoi18n(
             b'obsmarker-exchange: %i bytes received\n' % len(markerdata)
         )
     # The mergemarkers call will crash if marker creation is not enabled.
     # we want to avoid this if the part is advisory.
     if not inpart.mandatory and op.repo.obsstore.readonly:
         op.repo.ui.debug(
             b'ignoring obsolescence markers, feature not enabled\n'
         )
         return
     new = op.repo.obsstore.mergemarkers(tr, markerdata)
     op.repo.invalidatevolatilesets()
     op.records.add(b'obsmarkers', {b'new': new})
     if op.reply is not None:
         rpart = op.reply.newpart(b'reply:obsmarkers')
         rpart.addparam(
             b'in-reply-to', pycompat.bytestr(inpart.id), mandatory=False
         )
         rpart.addparam(b'new', b'%i' % new, mandatory=False)
 
 
 @parthandler(b'reply:obsmarkers', (b'new', b'in-reply-to'))
 def handleobsmarkerreply(op, inpart):
     """retrieve the result of a pushkey request"""
     ret = int(inpart.params[b'new'])
     partid = int(inpart.params[b'in-reply-to'])
     op.records.add(b'obsmarkers', {b'new': ret}, partid)
 
 
 @parthandler(b'hgtagsfnodes')
 def handlehgtagsfnodes(op, inpart):
     """Applies .hgtags fnodes cache entries to the local repo.
 
     Payload is pairs of 20 byte changeset nodes and filenodes.
     """
     # Grab the transaction so we ensure that we have the lock at this point.
     if op.ui.configbool(b'experimental', b'bundle2lazylocking'):
         op.gettransaction()
     cache = tags.hgtagsfnodescache(op.repo.unfiltered())
 
     count = 0
     while True:
         node = inpart.read(20)
         fnode = inpart.read(20)
         if len(node) < 20 or len(fnode) < 20:
             op.ui.debug(b'ignoring incomplete received .hgtags fnodes data\n')
             break
         cache.setfnode(node, fnode)
         count += 1
 
     cache.write()
     op.ui.debug(b'applied %i hgtags fnodes cache entries\n' % count)
 
 
 rbcstruct = struct.Struct(b'>III')
 
 
 @parthandler(b'cache:rev-branch-cache')
 def handlerbc(op, inpart):
     """receive a rev-branch-cache payload and update the local cache
 
     The payload is a series of data related to each branch
 
     1) branch name length
     2) number of open heads
     3) number of closed heads
     4) open heads nodes
     5) closed heads nodes
     """
     total = 0
     rawheader = inpart.read(rbcstruct.size)
     cache = op.repo.revbranchcache()
     cl = op.repo.unfiltered().changelog
     while rawheader:
         header = rbcstruct.unpack(rawheader)
         total += header[1] + header[2]
         utf8branch = inpart.read(header[0])
         branch = encoding.tolocal(utf8branch)
         for x in pycompat.xrange(header[1]):
             node = inpart.read(20)
             rev = cl.rev(node)
             cache.setdata(branch, rev, node, False)
         for x in pycompat.xrange(header[2]):
             node = inpart.read(20)
             rev = cl.rev(node)
             cache.setdata(branch, rev, node, True)
         rawheader = inpart.read(rbcstruct.size)
     cache.write()
 
 
 @parthandler(b'pushvars')
 def bundle2getvars(op, part):
     '''unbundle a bundle2 containing shellvars on the server'''
     # An option to disable unbundling on server-side for security reasons
     if op.ui.configbool(b'push', b'pushvars.server'):
         hookargs = {}
         for key, value in part.advisoryparams:
             key = key.upper()
             # We want pushed variables to have USERVAR_ prepended so we know
             # they came from the --pushvar flag.
             key = b"USERVAR_" + key
             hookargs[key] = value
         op.addhookargs(hookargs)
 
 
 @parthandler(b'stream2', (b'requirements', b'filecount', b'bytecount'))
 def handlestreamv2bundle(op, part):
 
     requirements = urlreq.unquote(part.params[b'requirements']).split(b',')
     filecount = int(part.params[b'filecount'])
     bytecount = int(part.params[b'bytecount'])
 
     repo = op.repo
     if len(repo):
         msg = _(b'cannot apply stream clone to non empty repository')
         raise error.Abort(msg)
 
     repo.ui.debug(b'applying stream bundle\n')
     streamclone.applybundlev2(repo, part, filecount, bytecount, requirements)
 
 
 def widen_bundle(
     bundler, repo, oldmatcher, newmatcher, common, known, cgversion, ellipses
 ):
     """generates bundle2 for widening a narrow clone
 
     bundler is the bundle to which data should be added
     repo is the localrepository instance
     oldmatcher matches what the client already has
     newmatcher matches what the client needs (including what it already has)
     common is set of common heads between server and client
     known is a set of revs known on the client side (used in ellipses)
     cgversion is the changegroup version to send
     ellipses is boolean value telling whether to send ellipses data or not
 
     returns bundle2 of the data required for extending
     """
     commonnodes = set()
     cl = repo.changelog
     for r in repo.revs(b"::%ln", common):
         commonnodes.add(cl.node(r))
     if commonnodes:
         # XXX: we should only send the filelogs (and treemanifest). user
         # already has the changelog and manifest
         packer = changegroup.getbundler(
             cgversion,
             repo,
             oldmatcher=oldmatcher,
             matcher=newmatcher,
             fullnodes=commonnodes,
         )
         cgdata = packer.generate(
             {nodemod.nullid},
             list(commonnodes),
             False,
             b'narrow_widen',
             changelog=False,
         )
 
         part = bundler.newpart(b'changegroup', data=cgdata)
         part.addparam(b'version', cgversion)
         if b'treemanifest' in repo.requirements:
             part.addparam(b'treemanifest', b'1')
 
     return bundler

mercurial/bundlerepo.py

@@ -1,670 +1,670 b''
 # bundlerepo.py - repository class for viewing uncompressed bundles
 #
 # Copyright 2006, 2007 Benoit Boissinot <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """Repository class for viewing uncompressed bundles.
 
 This provides a read-only repository interface to bundles as if they
 were part of the actual repository.
 """
 
 from __future__ import absolute_import
 
 import os
 import shutil
 
 from .i18n import _
 from .node import nullid, nullrev
 
 from . import (
     bundle2,
     changegroup,
     changelog,
     cmdutil,
     discovery,
     encoding,
     error,
     exchange,
     filelog,
     localrepo,
     manifest,
     mdiff,
     node as nodemod,
     pathutil,
     phases,
     pycompat,
     revlog,
     util,
     vfs as vfsmod,
 )
 
 
 class bundlerevlog(revlog.revlog):
     def __init__(self, opener, indexfile, cgunpacker, linkmapper):
         # How it works:
         # To retrieve a revision, we need to know the offset of the revision in
         # the bundle (an unbundle object). We store this offset in the index
         # (start). The base of the delta is stored in the base field.
         #
         # To differentiate a rev in the bundle from a rev in the revlog, we
         # check revision against repotiprev.
         opener = vfsmod.readonlyvfs(opener)
         revlog.revlog.__init__(self, opener, indexfile)
         self.bundle = cgunpacker
         n = len(self)
         self.repotiprev = n - 1
         self.bundlerevs = set()  # used by 'bundle()' revset expression
         for deltadata in cgunpacker.deltaiter():
             node, p1, p2, cs, deltabase, delta, flags = deltadata
 
             size = len(delta)
             start = cgunpacker.tell() - size
 
             link = linkmapper(cs)
             if node in self.nodemap:
                 # this can happen if two branches make the same change
                 self.bundlerevs.add(self.nodemap[node])
                 continue
 
             for p in (p1, p2):
                 if p not in self.nodemap:
                     raise error.LookupError(
                         p, self.indexfile, _(b"unknown parent")
                     )
 
             if deltabase not in self.nodemap:
                 raise LookupError(
                     deltabase, self.indexfile, _(b'unknown delta base')
                 )
 
             baserev = self.rev(deltabase)
             # start, size, full unc. size, base (unused), link, p1, p2, node
             e = (
                 revlog.offset_type(start, flags),
                 size,
                 -1,
                 baserev,
                 link,
                 self.rev(p1),
                 self.rev(p2),
                 node,
             )
             self.index.append(e)
             self.nodemap[node] = n
             self.bundlerevs.add(n)
             n += 1
 
     def _chunk(self, rev, df=None):
         # Warning: in case of bundle, the diff is against what we stored as
         # delta base, not against rev - 1
         # XXX: could use some caching
         if rev <= self.repotiprev:
             return revlog.revlog._chunk(self, rev)
         self.bundle.seek(self.start(rev))
         return self.bundle.read(self.length(rev))
 
     def revdiff(self, rev1, rev2):
         """return or calculate a delta between two revisions"""
         if rev1 > self.repotiprev and rev2 > self.repotiprev:
             # hot path for bundle
             revb = self.index[rev2][3]
             if revb == rev1:
                 return self._chunk(rev2)
         elif rev1 <= self.repotiprev and rev2 <= self.repotiprev:
             return revlog.revlog.revdiff(self, rev1, rev2)
 
         return mdiff.textdiff(self.rawdata(rev1), self.rawdata(rev2))
 
     def _rawtext(self, node, rev, _df=None):
         if rev is None:
             rev = self.rev(node)
         validated = False
         rawtext = None
         chain = []
         iterrev = rev
         # reconstruct the revision if it is from a changegroup
         while iterrev > self.repotiprev:
             if self._revisioncache and self._revisioncache[1] == iterrev:
                 rawtext = self._revisioncache[2]
                 break
             chain.append(iterrev)
             iterrev = self.index[iterrev][3]
         if iterrev == nullrev:
             rawtext = b''
         elif rawtext is None:
             r = super(bundlerevlog, self)._rawtext(
                 self.node(iterrev), iterrev, _df=_df
             )
             __, rawtext, validated = r
         if chain:
             validated = False
         while chain:
             delta = self._chunk(chain.pop())
             rawtext = mdiff.patches(rawtext, [delta])
         return rev, rawtext, validated
 
     def addrevision(self, *args, **kwargs):
         raise NotImplementedError
 
     def addgroup(self, *args, **kwargs):
         raise NotImplementedError
 
     def strip(self, *args, **kwargs):
         raise NotImplementedError
 
     def checksize(self):
         raise NotImplementedError
 
 
 class bundlechangelog(bundlerevlog, changelog.changelog):
     def __init__(self, opener, cgunpacker):
         changelog.changelog.__init__(self, opener)
         linkmapper = lambda x: x
         bundlerevlog.__init__(
             self, opener, self.indexfile, cgunpacker, linkmapper
         )
 
 
 class bundlemanifest(bundlerevlog, manifest.manifestrevlog):
     def __init__(
         self, opener, cgunpacker, linkmapper, dirlogstarts=None, dir=b''
     ):
         manifest.manifestrevlog.__init__(self, opener, tree=dir)
         bundlerevlog.__init__(
             self, opener, self.indexfile, cgunpacker, linkmapper
         )
         if dirlogstarts is None:
             dirlogstarts = {}
             if self.bundle.version == b"03":
                 dirlogstarts = _getfilestarts(self.bundle)
         self._dirlogstarts = dirlogstarts
         self._linkmapper = linkmapper
 
     def dirlog(self, d):
         if d in self._dirlogstarts:
             self.bundle.seek(self._dirlogstarts[d])
             return bundlemanifest(
                 self.opener,
                 self.bundle,
                 self._linkmapper,
                 self._dirlogstarts,
                 dir=d,
             )
         return super(bundlemanifest, self).dirlog(d)
 
 
 class bundlefilelog(filelog.filelog):
     def __init__(self, opener, path, cgunpacker, linkmapper):
         filelog.filelog.__init__(self, opener, path)
         self._revlog = bundlerevlog(
             opener, self.indexfile, cgunpacker, linkmapper
         )
 
 
 class bundlepeer(localrepo.localpeer):
     def canpush(self):
         return False
 
 
 class bundlephasecache(phases.phasecache):
     def __init__(self, *args, **kwargs):
         super(bundlephasecache, self).__init__(*args, **kwargs)
-        if util.safehasattr(self, b'opener'):
+        if util.safehasattr(self, 'opener'):
             self.opener = vfsmod.readonlyvfs(self.opener)
 
     def write(self):
         raise NotImplementedError
 
     def _write(self, fp):
         raise NotImplementedError
 
     def _updateroots(self, phase, newroots, tr):
         self.phaseroots[phase] = newroots
         self.invalidate()
         self.dirty = True
 
 
 def _getfilestarts(cgunpacker):
     filespos = {}
     for chunkdata in iter(cgunpacker.filelogheader, {}):
         fname = chunkdata[b'filename']
         filespos[fname] = cgunpacker.tell()
         for chunk in iter(lambda: cgunpacker.deltachunk(None), {}):
             pass
     return filespos
 
 
 class bundlerepository(object):
     """A repository instance that is a union of a local repo and a bundle.
 
     Instances represent a read-only repository composed of a local repository
     with the contents of a bundle file applied. The repository instance is
     conceptually similar to the state of a repository after an
     ``hg unbundle`` operation. However, the contents of the bundle are never
     applied to the actual base repository.
 
     Instances constructed directly are not usable as repository objects.
     Use instance() or makebundlerepository() to create instances.
     """
 
     def __init__(self, bundlepath, url, tempparent):
         self._tempparent = tempparent
         self._url = url
 
         self.ui.setconfig(b'phases', b'publish', False, b'bundlerepo')
 
         self.tempfile = None
         f = util.posixfile(bundlepath, b"rb")
         bundle = exchange.readbundle(self.ui, f, bundlepath)
 
         if isinstance(bundle, bundle2.unbundle20):
             self._bundlefile = bundle
             self._cgunpacker = None
 
             cgpart = None
             for part in bundle.iterparts(seekable=True):
                 if part.type == b'changegroup':
                     if cgpart:
                         raise NotImplementedError(
                             b"can't process " b"multiple changegroups"
                         )
                     cgpart = part
 
                 self._handlebundle2part(bundle, part)
 
             if not cgpart:
                 raise error.Abort(_(b"No changegroups found"))
 
             # This is required to placate a later consumer, which expects
             # the payload offset to be at the beginning of the changegroup.
             # We need to do this after the iterparts() generator advances
             # because iterparts() will seek to end of payload after the
             # generator returns control to iterparts().
             cgpart.seek(0, os.SEEK_SET)
 
         elif isinstance(bundle, changegroup.cg1unpacker):
             if bundle.compressed():
                 f = self._writetempbundle(
                     bundle.read, b'.hg10un', header=b'HG10UN'
                 )
                 bundle = exchange.readbundle(self.ui, f, bundlepath, self.vfs)
 
             self._bundlefile = bundle
             self._cgunpacker = bundle
         else:
             raise error.Abort(
                 _(b'bundle type %s cannot be read') % type(bundle)
             )
 
         # dict with the mapping 'filename' -> position in the changegroup.
         self._cgfilespos = {}
 
         self.firstnewrev = self.changelog.repotiprev + 1
         phases.retractboundary(
             self,
             None,
             phases.draft,
             [ctx.node() for ctx in self[self.firstnewrev :]],
         )
 
     def _handlebundle2part(self, bundle, part):
         if part.type != b'changegroup':
             return
 
         cgstream = part
         version = part.params.get(b'version', b'01')
         legalcgvers = changegroup.supportedincomingversions(self)
         if version not in legalcgvers:
             msg = _(b'Unsupported changegroup version: %s')
             raise error.Abort(msg % version)
         if bundle.compressed():
             cgstream = self._writetempbundle(part.read, b'.cg%sun' % version)
 
         self._cgunpacker = changegroup.getunbundler(version, cgstream, b'UN')
 
     def _writetempbundle(self, readfn, suffix, header=b''):
         """Write a temporary file to disk
         """
         fdtemp, temp = self.vfs.mkstemp(prefix=b"hg-bundle-", suffix=suffix)
         self.tempfile = temp
 
         with os.fdopen(fdtemp, r'wb') as fptemp:
             fptemp.write(header)
             while True:
                 chunk = readfn(2 ** 18)
                 if not chunk:
                     break
                 fptemp.write(chunk)
 
         return self.vfs.open(self.tempfile, mode=b"rb")
 
     @localrepo.unfilteredpropertycache
     def _phasecache(self):
         return bundlephasecache(self, self._phasedefaults)
 
     @localrepo.unfilteredpropertycache
     def changelog(self):
         # consume the header if it exists
         self._cgunpacker.changelogheader()
         c = bundlechangelog(self.svfs, self._cgunpacker)
         self.manstart = self._cgunpacker.tell()
         return c
 
     def _refreshchangelog(self):
         # changelog for bundle repo are not filecache, this method is not
         # applicable.
         pass
 
     @localrepo.unfilteredpropertycache
     def manifestlog(self):
         self._cgunpacker.seek(self.manstart)
         # consume the header if it exists
         self._cgunpacker.manifestheader()
         linkmapper = self.unfiltered().changelog.rev
         rootstore = bundlemanifest(self.svfs, self._cgunpacker, linkmapper)
         self.filestart = self._cgunpacker.tell()
 
         return manifest.manifestlog(
             self.svfs, self, rootstore, self.narrowmatch()
         )
 
     def _consumemanifest(self):
         """Consumes the manifest portion of the bundle, setting filestart so the
         file portion can be read."""
         self._cgunpacker.seek(self.manstart)
         self._cgunpacker.manifestheader()
         for delta in self._cgunpacker.deltaiter():
             pass
         self.filestart = self._cgunpacker.tell()
 
     @localrepo.unfilteredpropertycache
     def manstart(self):
         self.changelog
         return self.manstart
 
     @localrepo.unfilteredpropertycache
     def filestart(self):
         self.manifestlog
 
         # If filestart was not set by self.manifestlog, that means the
         # manifestlog implementation did not consume the manifests from the
         # changegroup (ex: it might be consuming trees from a separate bundle2
         # part instead). So we need to manually consume it.
         if r'filestart' not in self.__dict__:
             self._consumemanifest()
 
         return self.filestart
 
     def url(self):
         return self._url
 
     def file(self, f):
         if not self._cgfilespos:
             self._cgunpacker.seek(self.filestart)
             self._cgfilespos = _getfilestarts(self._cgunpacker)
 
         if f in self._cgfilespos:
             self._cgunpacker.seek(self._cgfilespos[f])
             linkmapper = self.unfiltered().changelog.rev
             return bundlefilelog(self.svfs, f, self._cgunpacker, linkmapper)
         else:
             return super(bundlerepository, self).file(f)
 
     def close(self):
         """Close assigned bundle file immediately."""
         self._bundlefile.close()
         if self.tempfile is not None:
             self.vfs.unlink(self.tempfile)
         if self._tempparent:
             shutil.rmtree(self._tempparent, True)
 
     def cancopy(self):
         return False
 
     def peer(self):
         return bundlepeer(self)
 
     def getcwd(self):
         return encoding.getcwd()  # always outside the repo
 
     # Check if parents exist in localrepo before setting
     def setparents(self, p1, p2=nullid):
         p1rev = self.changelog.rev(p1)
         p2rev = self.changelog.rev(p2)
         msg = _(b"setting parent to node %s that only exists in the bundle\n")
         if self.changelog.repotiprev < p1rev:
             self.ui.warn(msg % nodemod.hex(p1))
         if self.changelog.repotiprev < p2rev:
             self.ui.warn(msg % nodemod.hex(p2))
         return super(bundlerepository, self).setparents(p1, p2)
 
 
 def instance(ui, path, create, intents=None, createopts=None):
     if create:
         raise error.Abort(_(b'cannot create new bundle repository'))
     # internal config: bundle.mainreporoot
     parentpath = ui.config(b"bundle", b"mainreporoot")
     if not parentpath:
         # try to find the correct path to the working directory repo
         parentpath = cmdutil.findrepo(encoding.getcwd())
         if parentpath is None:
             parentpath = b''
     if parentpath:
         # Try to make the full path relative so we get a nice, short URL.
         # In particular, we don't want temp dir names in test outputs.
         cwd = encoding.getcwd()
         if parentpath == cwd:
             parentpath = b''
         else:
             cwd = pathutil.normasprefix(cwd)
             if parentpath.startswith(cwd):
                 parentpath = parentpath[len(cwd) :]
     u = util.url(path)
     path = u.localpath()
     if u.scheme == b'bundle':
         s = path.split(b"+", 1)
         if len(s) == 1:
             repopath, bundlename = parentpath, s[0]
         else:
             repopath, bundlename = s
     else:
         repopath, bundlename = parentpath, path
 
     return makebundlerepository(ui, repopath, bundlename)
 
 
 def makebundlerepository(ui, repopath, bundlepath):
     """Make a bundle repository object based on repo and bundle paths."""
     if repopath:
         url = b'bundle:%s+%s' % (util.expandpath(repopath), bundlepath)
     else:
         url = b'bundle:%s' % bundlepath
 
     # Because we can't make any guarantees about the type of the base
     # repository, we can't have a static class representing the bundle
     # repository. We also can't make any guarantees about how to even
     # call the base repository's constructor!
     #
     # So, our strategy is to go through ``localrepo.instance()`` to construct
     # a repo instance. Then, we dynamically create a new type derived from
     # both it and our ``bundlerepository`` class which overrides some
     # functionality. We then change the type of the constructed repository
     # to this new type and initialize the bundle-specific bits of it.
 
     try:
         repo = localrepo.instance(ui, repopath, create=False)
         tempparent = None
     except error.RepoError:
         tempparent = pycompat.mkdtemp()
         try:
             repo = localrepo.instance(ui, tempparent, create=True)
         except Exception:
             shutil.rmtree(tempparent)
             raise
 
     class derivedbundlerepository(bundlerepository, repo.__class__):
         pass
 
     repo.__class__ = derivedbundlerepository
     bundlerepository.__init__(repo, bundlepath, url, tempparent)
 
     return repo
 
 
 class bundletransactionmanager(object):
     def transaction(self):
         return None
 
     def close(self):
         raise NotImplementedError
 
     def release(self):
         raise NotImplementedError
 
 
 def getremotechanges(
     ui, repo, peer, onlyheads=None, bundlename=None, force=False
 ):
     '''obtains a bundle of changes incoming from peer
 
     "onlyheads" restricts the returned changes to those reachable from the
       specified heads.
     "bundlename", if given, stores the bundle to this file path permanently;
       otherwise it's stored to a temp file and gets deleted again when you call
       the returned "cleanupfn".
     "force" indicates whether to proceed on unrelated repos.
 
     Returns a tuple (local, csets, cleanupfn):
 
     "local" is a local repo from which to obtain the actual incoming
       changesets; it is a bundlerepo for the obtained bundle when the
       original "peer" is remote.
     "csets" lists the incoming changeset node ids.
     "cleanupfn" must be called without arguments when you're done processing
       the changes; it closes both the original "peer" and the one returned
       here.
     '''
     tmp = discovery.findcommonincoming(repo, peer, heads=onlyheads, force=force)
     common, incoming, rheads = tmp
     if not incoming:
         try:
             if bundlename:
                 os.unlink(bundlename)
         except OSError:
             pass
         return repo, [], peer.close
 
     commonset = set(common)
     rheads = [x for x in rheads if x not in commonset]
 
     bundle = None
     bundlerepo = None
     localrepo = peer.local()
     if bundlename or not localrepo:
         # create a bundle (uncompressed if peer repo is not local)
 
         # developer config: devel.legacy.exchange
         legexc = ui.configlist(b'devel', b'legacy.exchange')
         forcebundle1 = b'bundle2' not in legexc and b'bundle1' in legexc
         canbundle2 = (
             not forcebundle1
             and peer.capable(b'getbundle')
             and peer.capable(b'bundle2')
         )
         if canbundle2:
             with peer.commandexecutor() as e:
                 b2 = e.callcommand(
                     b'getbundle',
                     {
                         b'source': b'incoming',
                         b'common': common,
                         b'heads': rheads,
                         b'bundlecaps': exchange.caps20to10(
                             repo, role=b'client'
                         ),
                         b'cg': True,
                     },
                 ).result()
 
                 fname = bundle = changegroup.writechunks(
                     ui, b2._forwardchunks(), bundlename
                 )
         else:
             if peer.capable(b'getbundle'):
                 with peer.commandexecutor() as e:
                     cg = e.callcommand(
                         b'getbundle',
                         {
                             b'source': b'incoming',
                             b'common': common,
                             b'heads': rheads,
                         },
                     ).result()
             elif onlyheads is None and not peer.capable(b'changegroupsubset'):
                 # compat with older servers when pulling all remote heads
 
                 with peer.commandexecutor() as e:
                     cg = e.callcommand(
                         b'changegroup',
                         {b'nodes': incoming, b'source': b'incoming',},
                     ).result()
 
                 rheads = None
             else:
                 with peer.commandexecutor() as e:
                     cg = e.callcommand(
                         b'changegroupsubset',
                         {
                             b'bases': incoming,
                             b'heads': rheads,
                             b'source': b'incoming',
                         },
                     ).result()
 
             if localrepo:
                 bundletype = b"HG10BZ"
             else:
                 bundletype = b"HG10UN"
             fname = bundle = bundle2.writebundle(ui, cg, bundlename, bundletype)
         # keep written bundle?
         if bundlename:
             bundle = None
         if not localrepo:
             # use the created uncompressed bundlerepo
             localrepo = bundlerepo = makebundlerepository(
                 repo.baseui, repo.root, fname
             )
 
             # this repo contains local and peer now, so filter out local again
             common = repo.heads()
     if localrepo:
         # Part of common may be remotely filtered
         # So use an unfiltered version
         # The discovery process probably need cleanup to avoid that
         localrepo = localrepo.unfiltered()
 
     csets = localrepo.changelog.findmissing(common, rheads)
 
     if bundlerepo:
         reponodes = [ctx.node() for ctx in bundlerepo[bundlerepo.firstnewrev :]]
 
         with peer.commandexecutor() as e:
             remotephases = e.callcommand(
                 b'listkeys', {b'namespace': b'phases',}
             ).result()
 
         pullop = exchange.pulloperation(bundlerepo, peer, heads=reponodes)
         pullop.trmanager = bundletransactionmanager()
         exchange._pullapplyphases(pullop, remotephases)
 
     def cleanup():
         if bundlerepo:
             bundlerepo.close()
         if bundle:
             os.unlink(bundle)
         peer.close()
 
     return (localrepo, csets, cleanup)

mercurial/pvec.py

@@ -1,227 +1,227 b''
 # pvec.py - probabilistic vector clocks for Mercurial
 #
 # Copyright 2012 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.
 
 '''
 A "pvec" is a changeset property based on the theory of vector clocks
 that can be compared to discover relatedness without consulting a
 graph. This can be useful for tasks like determining how a
 disconnected patch relates to a repository.
 
 Currently a pvec consist of 448 bits, of which 24 are 'depth' and the
 remainder are a bit vector. It is represented as a 70-character base85
 string.
 
 Construction:
 
 - a root changeset has a depth of 0 and a bit vector based on its hash
 - a normal commit has a changeset where depth is increased by one and
   one bit vector bit is flipped based on its hash
 - a merge changeset pvec is constructed by copying changes from one pvec into
   the other to balance its depth
 
 Properties:
 
 - for linear changes, difference in depth is always <= hamming distance
 - otherwise, changes are probably divergent
 - when hamming distance is < 200, we can reliably detect when pvecs are near
 
 Issues:
 
 - hamming distance ceases to work over distances of ~ 200
 - detecting divergence is less accurate when the common ancestor is very close
   to either revision or total distance is high
 - this could probably be improved by modeling the relation between
   delta and hdist
 
 Uses:
 
 - a patch pvec can be used to locate the nearest available common ancestor for
   resolving conflicts
 - ordering of patches can be established without a DAG
 - two head pvecs can be compared to determine whether push/pull/merge is needed
   and approximately how many changesets are involved
 - can be used to find a heuristic divergence measure between changesets on
   different branches
 '''
 
 from __future__ import absolute_import
 
 from .node import nullrev
 from . import (
     pycompat,
     util,
 )
 
 _size = 448  # 70 chars b85-encoded
 _bytes = _size / 8
 _depthbits = 24
 _depthbytes = _depthbits / 8
 _vecbytes = _bytes - _depthbytes
 _vecbits = _vecbytes * 8
 _radius = (_vecbits - 30) / 2  # high probability vectors are related
 
 
 def _bin(bs):
     '''convert a bytestring to a long'''
     v = 0
     for b in bs:
         v = v * 256 + ord(b)
     return v
 
 
 def _str(v, l):
     bs = b""
     for p in pycompat.xrange(l):
         bs = chr(v & 255) + bs
         v >>= 8
     return bs
 
 
 def _split(b):
     '''depth and bitvec'''
     return _bin(b[:_depthbytes]), _bin(b[_depthbytes:])
 
 
 def _join(depth, bitvec):
     return _str(depth, _depthbytes) + _str(bitvec, _vecbytes)
 
 
 def _hweight(x):
     c = 0
     while x:
         if x & 1:
             c += 1
         x >>= 1
     return c
 
 
 _htab = [_hweight(x) for x in pycompat.xrange(256)]
 
 
 def _hamming(a, b):
     '''find the hamming distance between two longs'''
     d = a ^ b
     c = 0
     while d:
         c += _htab[d & 0xFF]
         d >>= 8
     return c
 
 
 def _mergevec(x, y, c):
     # Ideally, this function would be x ^ y ^ ancestor, but finding
     # ancestors is a nuisance. So instead we find the minimal number
     # of changes to balance the depth and hamming distance
 
     d1, v1 = x
     d2, v2 = y
     if d1 < d2:
         d1, d2, v1, v2 = d2, d1, v2, v1
 
     hdist = _hamming(v1, v2)
     ddist = d1 - d2
     v = v1
     m = v1 ^ v2  # mask of different bits
     i = 1
 
     if hdist > ddist:
         # if delta = 10 and hdist = 100, then we need to go up 55 steps
         # to the ancestor and down 45
         changes = (hdist - ddist + 1) / 2
     else:
         # must make at least one change
         changes = 1
     depth = d1 + changes
 
     # copy changes from v2
     if m:
         while changes:
             if m & i:
                 v ^= i
                 changes -= 1
             i <<= 1
     else:
         v = _flipbit(v, c)
 
     return depth, v
 
 
 def _flipbit(v, node):
     # converting bit strings to longs is slow
     bit = (hash(node) & 0xFFFFFFFF) % _vecbits
     return v ^ (1 << bit)
 
 
 def ctxpvec(ctx):
     '''construct a pvec for ctx while filling in the cache'''
     r = ctx.repo()
-    if not util.safehasattr(r, b"_pveccache"):
+    if not util.safehasattr(r, "_pveccache"):
         r._pveccache = {}
     pvc = r._pveccache
     if ctx.rev() not in pvc:
         cl = r.changelog
         for n in pycompat.xrange(ctx.rev() + 1):
             if n not in pvc:
                 node = cl.node(n)
                 p1, p2 = cl.parentrevs(n)
                 if p1 == nullrev:
                     # start with a 'random' vector at root
                     pvc[n] = (0, _bin((node * 3)[:_vecbytes]))
                 elif p2 == nullrev:
                     d, v = pvc[p1]
                     pvc[n] = (d + 1, _flipbit(v, node))
                 else:
                     pvc[n] = _mergevec(pvc[p1], pvc[p2], node)
     bs = _join(*pvc[ctx.rev()])
     return pvec(util.b85encode(bs))
 
 
 class pvec(object):
     def __init__(self, hashorctx):
         if isinstance(hashorctx, str):
             self._bs = hashorctx
             self._depth, self._vec = _split(util.b85decode(hashorctx))
         else:
             self._vec = ctxpvec(hashorctx)
 
     def __str__(self):
         return self._bs
 
     def __eq__(self, b):
         return self._vec == b._vec and self._depth == b._depth
 
     def __lt__(self, b):
         delta = b._depth - self._depth
         if delta < 0:
             return False  # always correct
         if _hamming(self._vec, b._vec) > delta:
             return False
         return True
 
     def __gt__(self, b):
         return b < self
 
     def __or__(self, b):
         delta = abs(b._depth - self._depth)
         if _hamming(self._vec, b._vec) <= delta:
             return False
         return True
 
     def __sub__(self, b):
         if self | b:
             raise ValueError(b"concurrent pvecs")
         return self._depth - b._depth
 
     def distance(self, b):
         d = abs(b._depth - self._depth)
         h = _hamming(self._vec, b._vec)
         return max(d, h)
 
     def near(self, b):
         dist = abs(b.depth - self._depth)
         if dist > _radius or _hamming(self._vec, b._vec) > _radius:
             return False

mercurial/registrar.py

@@ -1,534 +1,534 b''
 # registrar.py - utilities to register function for specific purpose
 #
 #  Copyright FUJIWARA Katsunori <[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
 
 from . import (
     configitems,
     error,
     pycompat,
     util,
 )
 
 # unlike the other registered items, config options are neither functions or
 # classes. Registering the option is just small function call.
 #
 # We still add the official API to the registrar module for consistency with
 # the other items extensions want might to register.
 configitem = configitems.getitemregister
 
 
 class _funcregistrarbase(object):
     """Base of decorator to register a function for specific purpose
 
     This decorator stores decorated functions into own dict 'table'.
 
     The least derived class can be defined by overriding 'formatdoc',
     for example::
 
         class keyword(_funcregistrarbase):
             _docformat = ":%s: %s"
 
     This should be used as below:
 
         keyword = registrar.keyword()
 
         @keyword('bar')
         def barfunc(*args, **kwargs):
             '''Explanation of bar keyword ....
             '''
             pass
 
     In this case:
 
     - 'barfunc' is stored as 'bar' in '_table' of an instance 'keyword' above
     - 'barfunc.__doc__' becomes ":bar: Explanation of bar keyword"
     """
 
     def __init__(self, table=None):
         if table is None:
             self._table = {}
         else:
             self._table = table
 
     def __call__(self, decl, *args, **kwargs):
         return lambda func: self._doregister(func, decl, *args, **kwargs)
 
     def _doregister(self, func, decl, *args, **kwargs):
         name = self._getname(decl)
 
         if name in self._table:
             msg = b'duplicate registration for name: "%s"' % name
             raise error.ProgrammingError(msg)
 
-        if func.__doc__ and not util.safehasattr(func, b'_origdoc'):
+        if func.__doc__ and not util.safehasattr(func, '_origdoc'):
             func._origdoc = func.__doc__.strip()
             doc = pycompat.sysbytes(func._origdoc)
             func.__doc__ = pycompat.sysstr(self._formatdoc(decl, doc))
 
         self._table[name] = func
         self._extrasetup(name, func, *args, **kwargs)
 
         return func
 
     def _merge(self, registrarbase):
         """Merge the entries of the given registrar object into this one.
 
         The other registrar object must not contain any entries already in the
         current one, or a ProgrammmingError is raised.  Additionally, the types
         of the two registrars must match.
         """
         if not isinstance(registrarbase, type(self)):
             msg = b"cannot merge different types of registrar"
             raise error.ProgrammingError(msg)
 
         dups = set(registrarbase._table).intersection(self._table)
 
         if dups:
             msg = b'duplicate registration for names: "%s"' % b'", "'.join(dups)
             raise error.ProgrammingError(msg)
 
         self._table.update(registrarbase._table)
 
     def _parsefuncdecl(self, decl):
         """Parse function declaration and return the name of function in it
         """
         i = decl.find(b'(')
         if i >= 0:
             return decl[:i]
         else:
             return decl
 
     def _getname(self, decl):
         """Return the name of the registered function from decl
 
         Derived class should override this, if it allows more
         descriptive 'decl' string than just a name.
         """
         return decl
 
     _docformat = None
 
     def _formatdoc(self, decl, doc):
         """Return formatted document of the registered function for help
 
         'doc' is '__doc__.strip()' of the registered function.
         """
         return self._docformat % (decl, doc)
 
     def _extrasetup(self, name, func):
         """Execute exra setup for registered function, if needed
         """
 
 
 class command(_funcregistrarbase):
     """Decorator to register a command function to table
 
     This class receives a command table as its argument. The table should
     be a dict.
 
     The created object can be used as a decorator for adding commands to
     that command table. This accepts multiple arguments to define a command.
 
     The first argument is the command name (as bytes).
 
     The `options` keyword argument is an iterable of tuples defining command
     arguments. See ``mercurial.fancyopts.fancyopts()`` for the format of each
     tuple.
 
     The `synopsis` argument defines a short, one line summary of how to use the
     command. This shows up in the help output.
 
     There are three arguments that control what repository (if any) is found
     and passed to the decorated function: `norepo`, `optionalrepo`, and
     `inferrepo`.
 
     The `norepo` argument defines whether the command does not require a
     local repository. Most commands operate against a repository, thus the
     default is False. When True, no repository will be passed.
 
     The `optionalrepo` argument defines whether the command optionally requires
     a local repository. If no repository can be found, None will be passed
     to the decorated function.
 
     The `inferrepo` argument defines whether to try to find a repository from
     the command line arguments. If True, arguments will be examined for
     potential repository locations. See ``findrepo()``. If a repository is
     found, it will be used and passed to the decorated function.
 
     The `intents` argument defines a set of intended actions or capabilities
     the command is taking. These intents can be used to affect the construction
     of the repository object passed to the command. For example, commands
     declaring that they are read-only could receive a repository that doesn't
     have any methods allowing repository mutation. Other intents could be used
     to prevent the command from running if the requested intent could not be
     fulfilled.
 
     If `helpcategory` is set (usually to one of the constants in the help
     module), the command will be displayed under that category in the help's
     list of commands.
 
     The following intents are defined:
 
     readonly
        The command is read-only
 
     The signature of the decorated function looks like this:
         def cmd(ui[, repo] [, <args>] [, <options>])
 
       `repo` is required if `norepo` is False.
       `<args>` are positional args (or `*args`) arguments, of non-option
       arguments from the command line.
       `<options>` are keyword arguments (or `**options`) of option arguments
       from the command line.
 
     See the WritingExtensions and MercurialApi documentation for more exhaustive
     descriptions and examples.
     """
 
     # Command categories for grouping them in help output.
     # These can also be specified for aliases, like:
     # [alias]
     # myalias = something
     # myalias:category = repo
     CATEGORY_REPO_CREATION = b'repo'
     CATEGORY_REMOTE_REPO_MANAGEMENT = b'remote'
     CATEGORY_COMMITTING = b'commit'
     CATEGORY_CHANGE_MANAGEMENT = b'management'
     CATEGORY_CHANGE_ORGANIZATION = b'organization'
     CATEGORY_FILE_CONTENTS = b'files'
     CATEGORY_CHANGE_NAVIGATION = b'navigation'
     CATEGORY_WORKING_DIRECTORY = b'wdir'
     CATEGORY_IMPORT_EXPORT = b'import'
     CATEGORY_MAINTENANCE = b'maintenance'
     CATEGORY_HELP = b'help'
     CATEGORY_MISC = b'misc'
     CATEGORY_NONE = b'none'
 
     def _doregister(
         self,
         func,
         name,
         options=(),
         synopsis=None,
         norepo=False,
         optionalrepo=False,
         inferrepo=False,
         intents=None,
         helpcategory=None,
         helpbasic=False,
     ):
         func.norepo = norepo
         func.optionalrepo = optionalrepo
         func.inferrepo = inferrepo
         func.intents = intents or set()
         func.helpcategory = helpcategory
         func.helpbasic = helpbasic
         if synopsis:
             self._table[name] = func, list(options), synopsis
         else:
             self._table[name] = func, list(options)
         return func
 
 
 INTENT_READONLY = b'readonly'
 
 
 class revsetpredicate(_funcregistrarbase):
     """Decorator to register revset predicate
 
     Usage::
 
         revsetpredicate = registrar.revsetpredicate()
 
         @revsetpredicate('mypredicate(arg1, arg2[, arg3])')
         def mypredicatefunc(repo, subset, x):
             '''Explanation of this revset predicate ....
             '''
             pass
 
     The first string argument is used also in online help.
 
     Optional argument 'safe' indicates whether a predicate is safe for
     DoS attack (False by default).
 
     Optional argument 'takeorder' indicates whether a predicate function
     takes ordering policy as the last argument.
 
     Optional argument 'weight' indicates the estimated run-time cost, useful
     for static optimization, default is 1. Higher weight means more expensive.
     Usually, revsets that are fast and return only one revision has a weight of
     0.5 (ex. a symbol); revsets with O(changelog) complexity and read only the
     changelog have weight 10 (ex. author); revsets reading manifest deltas have
     weight 30 (ex. adds); revset reading manifest contents have weight 100
     (ex. contains). Note: those values are flexible. If the revset has a
     same big-O time complexity as 'contains', but with a smaller constant, it
     might have a weight of 90.
 
     'revsetpredicate' instance in example above can be used to
     decorate multiple functions.
 
     Decorated functions are registered automatically at loading
     extension, if an instance named as 'revsetpredicate' is used for
     decorating in extension.
 
     Otherwise, explicit 'revset.loadpredicate()' is needed.
     """
 
     _getname = _funcregistrarbase._parsefuncdecl
     _docformat = b"``%s``\n    %s"
 
     def _extrasetup(self, name, func, safe=False, takeorder=False, weight=1):
         func._safe = safe
         func._takeorder = takeorder
         func._weight = weight
 
 
 class filesetpredicate(_funcregistrarbase):
     """Decorator to register fileset predicate
 
     Usage::
 
         filesetpredicate = registrar.filesetpredicate()
 
         @filesetpredicate('mypredicate()')
         def mypredicatefunc(mctx, x):
             '''Explanation of this fileset predicate ....
             '''
             pass
 
     The first string argument is used also in online help.
 
     Optional argument 'callstatus' indicates whether a predicate
      implies 'matchctx.status()' at runtime or not (False, by
      default).
 
     Optional argument 'weight' indicates the estimated run-time cost, useful
     for static optimization, default is 1. Higher weight means more expensive.
     There are predefined weights in the 'filesetlang' module.
 
     ====== =============================================================
     Weight Description and examples
     ====== =============================================================
     0.5    basic match patterns (e.g. a symbol)
     10     computing status (e.g. added()) or accessing a few files
     30     reading file content for each (e.g. grep())
     50     scanning working directory (ignored())
     ====== =============================================================
 
     'filesetpredicate' instance in example above can be used to
     decorate multiple functions.
 
     Decorated functions are registered automatically at loading
     extension, if an instance named as 'filesetpredicate' is used for
     decorating in extension.
 
     Otherwise, explicit 'fileset.loadpredicate()' is needed.
     """
 
     _getname = _funcregistrarbase._parsefuncdecl
     _docformat = b"``%s``\n    %s"
 
     def _extrasetup(self, name, func, callstatus=False, weight=1):
         func._callstatus = callstatus
         func._weight = weight
 
 
 class _templateregistrarbase(_funcregistrarbase):
     """Base of decorator to register functions as template specific one
     """
 
     _docformat = b":%s: %s"
 
 
 class templatekeyword(_templateregistrarbase):
     """Decorator to register template keyword
 
     Usage::
 
         templatekeyword = registrar.templatekeyword()
 
         # new API (since Mercurial 4.6)
         @templatekeyword('mykeyword', requires={'repo', 'ctx'})
         def mykeywordfunc(context, mapping):
             '''Explanation of this template keyword ....
             '''
             pass
 
     The first string argument is used also in online help.
 
     Optional argument 'requires' should be a collection of resource names
     which the template keyword depends on.
 
     'templatekeyword' instance in example above can be used to
     decorate multiple functions.
 
     Decorated functions are registered automatically at loading
     extension, if an instance named as 'templatekeyword' is used for
     decorating in extension.
 
     Otherwise, explicit 'templatekw.loadkeyword()' is needed.
     """
 
     def _extrasetup(self, name, func, requires=()):
         func._requires = requires
 
 
 class templatefilter(_templateregistrarbase):
     """Decorator to register template filer
 
     Usage::
 
         templatefilter = registrar.templatefilter()
 
         @templatefilter('myfilter', intype=bytes)
         def myfilterfunc(text):
             '''Explanation of this template filter ....
             '''
             pass
 
     The first string argument is used also in online help.
 
     Optional argument 'intype' defines the type of the input argument,
     which should be (bytes, int, templateutil.date, or None for any.)
 
     'templatefilter' instance in example above can be used to
     decorate multiple functions.
 
     Decorated functions are registered automatically at loading
     extension, if an instance named as 'templatefilter' is used for
     decorating in extension.
 
     Otherwise, explicit 'templatefilters.loadkeyword()' is needed.
     """
 
     def _extrasetup(self, name, func, intype=None):
         func._intype = intype
 
 
 class templatefunc(_templateregistrarbase):
     """Decorator to register template function
 
     Usage::
 
         templatefunc = registrar.templatefunc()
 
         @templatefunc('myfunc(arg1, arg2[, arg3])', argspec='arg1 arg2 arg3',
                       requires={'ctx'})
         def myfuncfunc(context, mapping, args):
             '''Explanation of this template function ....
             '''
             pass
 
     The first string argument is used also in online help.
 
     If optional 'argspec' is defined, the function will receive 'args' as
     a dict of named arguments. Otherwise 'args' is a list of positional
     arguments.
 
     Optional argument 'requires' should be a collection of resource names
     which the template function depends on.
 
     'templatefunc' instance in example above can be used to
     decorate multiple functions.
 
     Decorated functions are registered automatically at loading
     extension, if an instance named as 'templatefunc' is used for
     decorating in extension.
 
     Otherwise, explicit 'templatefuncs.loadfunction()' is needed.
     """
 
     _getname = _funcregistrarbase._parsefuncdecl
 
     def _extrasetup(self, name, func, argspec=None, requires=()):
         func._argspec = argspec
         func._requires = requires
 
 
 class internalmerge(_funcregistrarbase):
     """Decorator to register in-process merge tool
 
     Usage::
 
         internalmerge = registrar.internalmerge()
 
         @internalmerge('mymerge', internalmerge.mergeonly,
                        onfailure=None, precheck=None,
                        binary=False, symlink=False):
         def mymergefunc(repo, mynode, orig, fcd, fco, fca,
                         toolconf, files, labels=None):
             '''Explanation of this internal merge tool ....
             '''
             return 1, False # means "conflicted", "no deletion needed"
 
     The first string argument is used to compose actual merge tool name,
     ":name" and "internal:name" (the latter is historical one).
 
     The second argument is one of merge types below:
 
     ========== ======== ======== =========
     merge type precheck premerge fullmerge
     ========== ======== ======== =========
     nomerge     x        x        x
     mergeonly   o        x        o
     fullmerge   o        o        o
     ========== ======== ======== =========
 
     Optional argument 'onfailure' is the format of warning message
     to be used at failure of merging (target filename is specified
     at formatting). Or, None or so, if warning message should be
     suppressed.
 
     Optional argument 'precheck' is the function to be used
     before actual invocation of internal merge tool itself.
     It takes as same arguments as internal merge tool does, other than
     'files' and 'labels'. If it returns false value, merging is aborted
     immediately (and file is marked as "unresolved").
 
     Optional argument 'binary' is a binary files capability of internal
     merge tool. 'nomerge' merge type implies binary=True.
 
     Optional argument 'symlink' is a symlinks capability of inetrnal
     merge function. 'nomerge' merge type implies symlink=True.
 
     'internalmerge' instance in example above can be used to
     decorate multiple functions.
 
     Decorated functions are registered automatically at loading
     extension, if an instance named as 'internalmerge' is used for
     decorating in extension.
 
     Otherwise, explicit 'filemerge.loadinternalmerge()' is needed.
     """
 
     _docformat = b"``:%s``\n    %s"
 
     # merge type definitions:
     nomerge = None
     mergeonly = b'mergeonly'  # just the full merge, no premerge
     fullmerge = b'fullmerge'  # both premerge and merge
 
     def _extrasetup(
         self,
         name,
         func,
         mergetype,
         onfailure=None,
         precheck=None,
         binary=False,
         symlink=False,
     ):
         func.mergetype = mergetype
         func.onfailure = onfailure
         func.precheck = precheck
 
         binarycap = binary or mergetype == self.nomerge
         symlinkcap = symlink or mergetype == self.nomerge
 
         # actual capabilities, which this internal merge tool has
         func.capabilities = {b"binary": binarycap, b"symlink": symlinkcap}

mercurial/utils/procutil.py

@@ -1,633 +1,633 b''
 # procutil.py - utility for managing processes and executable environment
 #
 #  Copyright 2005 K. Thananchayan <[e-mail]>
 #  Copyright 2005-2007 Matt Mackall <[e-mail]>
 #  Copyright 2006 Vadim Gelfer <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import contextlib
 import errno
 import imp
 import io
 import os
 import signal
 import subprocess
 import sys
 import time
 
 from ..i18n import _
 from ..pycompat import (
     getattr,
     open,
 )
 
 from .. import (
     encoding,
     error,
     policy,
     pycompat,
 )
 
 osutil = policy.importmod(r'osutil')
 
 stderr = pycompat.stderr
 stdin = pycompat.stdin
 stdout = pycompat.stdout
 
 
 def isatty(fp):
     try:
         return fp.isatty()
     except AttributeError:
         return False
 
 
 # glibc determines buffering on first write to stdout - if we replace a TTY
 # destined stdout with a pipe destined stdout (e.g. pager), we want line
 # buffering (or unbuffered, on Windows)
 if isatty(stdout):
     if pycompat.iswindows:
         # Windows doesn't support line buffering
         stdout = os.fdopen(stdout.fileno(), r'wb', 0)
     else:
         stdout = os.fdopen(stdout.fileno(), r'wb', 1)
 
 if pycompat.iswindows:
     from .. import windows as platform
 
     stdout = platform.winstdout(stdout)
 else:
     from .. import posix as platform
 
 findexe = platform.findexe
 _gethgcmd = platform.gethgcmd
 getuser = platform.getuser
 getpid = os.getpid
 hidewindow = platform.hidewindow
 quotecommand = platform.quotecommand
 readpipe = platform.readpipe
 setbinary = platform.setbinary
 setsignalhandler = platform.setsignalhandler
 shellquote = platform.shellquote
 shellsplit = platform.shellsplit
 spawndetached = platform.spawndetached
 sshargs = platform.sshargs
 testpid = platform.testpid
 
 try:
     setprocname = osutil.setprocname
 except AttributeError:
     pass
 try:
     unblocksignal = osutil.unblocksignal
 except AttributeError:
     pass
 
 closefds = pycompat.isposix
 
 
 def explainexit(code):
     """return a message describing a subprocess status
     (codes from kill are negative - not os.system/wait encoding)"""
     if code >= 0:
         return _(b"exited with status %d") % code
     return _(b"killed by signal %d") % -code
 
 
 class _pfile(object):
     """File-like wrapper for a stream opened by subprocess.Popen()"""
 
     def __init__(self, proc, fp):
         self._proc = proc
         self._fp = fp
 
     def close(self):
         # unlike os.popen(), this returns an integer in subprocess coding
         self._fp.close()
         return self._proc.wait()
 
     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):
         self.close()
 
 
 def popen(cmd, mode=b'rb', bufsize=-1):
     if mode == b'rb':
         return _popenreader(cmd, bufsize)
     elif mode == b'wb':
         return _popenwriter(cmd, bufsize)
     raise error.ProgrammingError(b'unsupported mode: %r' % mode)
 
 
 def _popenreader(cmd, bufsize):
     p = subprocess.Popen(
         tonativestr(quotecommand(cmd)),
         shell=True,
         bufsize=bufsize,
         close_fds=closefds,
         stdout=subprocess.PIPE,
     )
     return _pfile(p, p.stdout)
 
 
 def _popenwriter(cmd, bufsize):
     p = subprocess.Popen(
         tonativestr(quotecommand(cmd)),
         shell=True,
         bufsize=bufsize,
         close_fds=closefds,
         stdin=subprocess.PIPE,
     )
     return _pfile(p, p.stdin)
 
 
 def popen2(cmd, env=None):
     # Setting bufsize to -1 lets the system decide the buffer size.
     # The default for bufsize is 0, meaning unbuffered. This leads to
     # poor performance on Mac OS X: http://bugs.python.org/issue4194
     p = subprocess.Popen(
         tonativestr(cmd),
         shell=True,
         bufsize=-1,
         close_fds=closefds,
         stdin=subprocess.PIPE,
         stdout=subprocess.PIPE,
         env=tonativeenv(env),
     )
     return p.stdin, p.stdout
 
 
 def popen3(cmd, env=None):
     stdin, stdout, stderr, p = popen4(cmd, env)
     return stdin, stdout, stderr
 
 
 def popen4(cmd, env=None, bufsize=-1):
     p = subprocess.Popen(
         tonativestr(cmd),
         shell=True,
         bufsize=bufsize,
         close_fds=closefds,
         stdin=subprocess.PIPE,
         stdout=subprocess.PIPE,
         stderr=subprocess.PIPE,
         env=tonativeenv(env),
     )
     return p.stdin, p.stdout, p.stderr, p
 
 
 def pipefilter(s, cmd):
     '''filter string S through command CMD, returning its output'''
     p = subprocess.Popen(
         tonativestr(cmd),
         shell=True,
         close_fds=closefds,
         stdin=subprocess.PIPE,
         stdout=subprocess.PIPE,
     )
     pout, perr = p.communicate(s)
     return pout
 
 
 def tempfilter(s, cmd):
     '''filter string S through a pair of temporary files with CMD.
     CMD is used as a template to create the real command to be run,
     with the strings INFILE and OUTFILE replaced by the real names of
     the temporary files generated.'''
     inname, outname = None, None
     try:
         infd, inname = pycompat.mkstemp(prefix=b'hg-filter-in-')
         fp = os.fdopen(infd, r'wb')
         fp.write(s)
         fp.close()
         outfd, outname = pycompat.mkstemp(prefix=b'hg-filter-out-')
         os.close(outfd)
         cmd = cmd.replace(b'INFILE', inname)
         cmd = cmd.replace(b'OUTFILE', outname)
         code = system(cmd)
         if pycompat.sysplatform == b'OpenVMS' and code & 1:
             code = 0
         if code:
             raise error.Abort(
                 _(b"command '%s' failed: %s") % (cmd, explainexit(code))
             )
         with open(outname, b'rb') as fp:
             return fp.read()
     finally:
         try:
             if inname:
                 os.unlink(inname)
         except OSError:
             pass
         try:
             if outname:
                 os.unlink(outname)
         except OSError:
             pass
 
 
 _filtertable = {
     b'tempfile:': tempfilter,
     b'pipe:': pipefilter,
 }
 
 
 def filter(s, cmd):
     b"filter a string through a command that transforms its input to its output"
     for name, fn in pycompat.iteritems(_filtertable):
         if cmd.startswith(name):
             return fn(s, cmd[len(name) :].lstrip())
     return pipefilter(s, cmd)
 
 
 def mainfrozen():
     """return True if we are a frozen executable.
 
     The code supports py2exe (most common, Windows only) and tools/freeze
     (portable, not much used).
     """
     return (
-        pycompat.safehasattr(sys, b"frozen")
-        or pycompat.safehasattr(sys, b"importers")  # new py2exe
+        pycompat.safehasattr(sys, "frozen")
+        or pycompat.safehasattr(sys, "importers")  # new py2exe
         or imp.is_frozen(r"__main__")  # old py2exe
     )  # tools/freeze
 
 
 _hgexecutable = None
 
 
 def hgexecutable():
     """return location of the 'hg' executable.
 
     Defaults to $HG or 'hg' in the search path.
     """
     if _hgexecutable is None:
         hg = encoding.environ.get(b'HG')
         mainmod = sys.modules[r'__main__']
         if hg:
             _sethgexecutable(hg)
         elif mainfrozen():
             if getattr(sys, 'frozen', None) == b'macosx_app':
                 # Env variable set by py2app
                 _sethgexecutable(encoding.environ[b'EXECUTABLEPATH'])
             else:
                 _sethgexecutable(pycompat.sysexecutable)
         elif (
             not pycompat.iswindows
             and os.path.basename(
                 pycompat.fsencode(getattr(mainmod, '__file__', b''))
             )
             == b'hg'
         ):
             _sethgexecutable(pycompat.fsencode(mainmod.__file__))
         else:
             _sethgexecutable(
                 findexe(b'hg') or os.path.basename(pycompat.sysargv[0])
             )
     return _hgexecutable
 
 
 def _sethgexecutable(path):
     """set location of the 'hg' executable"""
     global _hgexecutable
     _hgexecutable = path
 
 
 def _testfileno(f, stdf):
     fileno = getattr(f, 'fileno', None)
     try:
         return fileno and fileno() == stdf.fileno()
     except io.UnsupportedOperation:
         return False  # fileno() raised UnsupportedOperation
 
 
 def isstdin(f):
     return _testfileno(f, sys.__stdin__)
 
 
 def isstdout(f):
     return _testfileno(f, sys.__stdout__)
 
 
 def protectstdio(uin, uout):
     """Duplicate streams and redirect original if (uin, uout) are stdio
 
     If uin is stdin, it's redirected to /dev/null. If uout is stdout, it's
     redirected to stderr so the output is still readable.
 
     Returns (fin, fout) which point to the original (uin, uout) fds, but
     may be copy of (uin, uout). The returned streams can be considered
     "owned" in that print(), exec(), etc. never reach to them.
     """
     uout.flush()
     fin, fout = uin, uout
     if _testfileno(uin, stdin):
         newfd = os.dup(uin.fileno())
         nullfd = os.open(os.devnull, os.O_RDONLY)
         os.dup2(nullfd, uin.fileno())
         os.close(nullfd)
         fin = os.fdopen(newfd, r'rb')
     if _testfileno(uout, stdout):
         newfd = os.dup(uout.fileno())
         os.dup2(stderr.fileno(), uout.fileno())
         fout = os.fdopen(newfd, r'wb')
     return fin, fout
 
 
 def restorestdio(uin, uout, fin, fout):
     """Restore (uin, uout) streams from possibly duplicated (fin, fout)"""
     uout.flush()
     for f, uif in [(fin, uin), (fout, uout)]:
         if f is not uif:
             os.dup2(f.fileno(), uif.fileno())
             f.close()
 
 
 def shellenviron(environ=None):
     """return environ with optional override, useful for shelling out"""
 
     def py2shell(val):
         b'convert python object into string that is useful to shell'
         if val is None or val is False:
             return b'0'
         if val is True:
             return b'1'
         return pycompat.bytestr(val)
 
     env = dict(encoding.environ)
     if environ:
         env.update((k, py2shell(v)) for k, v in pycompat.iteritems(environ))
     env[b'HG'] = hgexecutable()
     return env
 
 
 if pycompat.iswindows:
 
     def shelltonative(cmd, env):
         return platform.shelltocmdexe(cmd, shellenviron(env))
 
     tonativestr = encoding.strfromlocal
 else:
 
     def shelltonative(cmd, env):
         return cmd
 
     tonativestr = pycompat.identity
 
 
 def tonativeenv(env):
     '''convert the environment from bytes to strings suitable for Popen(), etc.
     '''
     return pycompat.rapply(tonativestr, env)
 
 
 def system(cmd, environ=None, cwd=None, out=None):
     '''enhanced shell command execution.
     run with environment maybe modified, maybe in different dir.
 
     if out is specified, it is assumed to be a file-like object that has a
     write() method. stdout and stderr will be redirected to out.'''
     try:
         stdout.flush()
     except Exception:
         pass
     cmd = quotecommand(cmd)
     env = shellenviron(environ)
     if out is None or isstdout(out):
         rc = subprocess.call(
             tonativestr(cmd),
             shell=True,
             close_fds=closefds,
             env=tonativeenv(env),
             cwd=pycompat.rapply(tonativestr, cwd),
         )
     else:
         proc = subprocess.Popen(
             tonativestr(cmd),
             shell=True,
             close_fds=closefds,
             env=tonativeenv(env),
             cwd=pycompat.rapply(tonativestr, cwd),
             stdout=subprocess.PIPE,
             stderr=subprocess.STDOUT,
         )
         for line in iter(proc.stdout.readline, b''):
             out.write(line)
         proc.wait()
         rc = proc.returncode
     if pycompat.sysplatform == b'OpenVMS' and rc & 1:
         rc = 0
     return rc
 
 
 def gui():
     '''Are we running in a GUI?'''
     if pycompat.isdarwin:
         if b'SSH_CONNECTION' in encoding.environ:
             # handle SSH access to a box where the user is logged in
             return False
         elif getattr(osutil, 'isgui', None):
             # check if a CoreGraphics session is available
             return osutil.isgui()
         else:
             # pure build; use a safe default
             return True
     else:
         return pycompat.iswindows or encoding.environ.get(b"DISPLAY")
 
 
 def hgcmd():
     """Return the command used to execute current hg
 
     This is different from hgexecutable() because on Windows we want
     to avoid things opening new shell windows like batch files, so we
     get either the python call or current executable.
     """
     if mainfrozen():
         if getattr(sys, 'frozen', None) == b'macosx_app':
             # Env variable set by py2app
             return [encoding.environ[b'EXECUTABLEPATH']]
         else:
             return [pycompat.sysexecutable]
     return _gethgcmd()
 
 
 def rundetached(args, condfn):
     """Execute the argument list in a detached process.
 
     condfn is a callable which is called repeatedly and should return
     True once the child process is known to have started successfully.
     At this point, the child process PID is returned. If the child
     process fails to start or finishes before condfn() evaluates to
     True, return -1.
     """
     # Windows case is easier because the child process is either
     # successfully starting and validating the condition or exiting
     # on failure. We just poll on its PID. On Unix, if the child
     # process fails to start, it will be left in a zombie state until
     # the parent wait on it, which we cannot do since we expect a long
     # running process on success. Instead we listen for SIGCHLD telling
     # us our child process terminated.
     terminated = set()
 
     def handler(signum, frame):
         terminated.add(os.wait())
 
     prevhandler = None
     SIGCHLD = getattr(signal, 'SIGCHLD', None)
     if SIGCHLD is not None:
         prevhandler = signal.signal(SIGCHLD, handler)
     try:
         pid = spawndetached(args)
         while not condfn():
             if (pid in terminated or not testpid(pid)) and not condfn():
                 return -1
             time.sleep(0.1)
         return pid
     finally:
         if prevhandler is not None:
             signal.signal(signal.SIGCHLD, prevhandler)
 
 
 @contextlib.contextmanager
 def uninterruptible(warn):
     """Inhibit SIGINT handling on a region of code.
 
     Note that if this is called in a non-main thread, it turns into a no-op.
 
     Args:
       warn: A callable which takes no arguments, and returns True if the
             previous signal handling should be restored.
     """
 
     oldsiginthandler = [signal.getsignal(signal.SIGINT)]
     shouldbail = []
 
     def disabledsiginthandler(*args):
         if warn():
             signal.signal(signal.SIGINT, oldsiginthandler[0])
             del oldsiginthandler[0]
         shouldbail.append(True)
 
     try:
         try:
             signal.signal(signal.SIGINT, disabledsiginthandler)
         except ValueError:
             # wrong thread, oh well, we tried
             del oldsiginthandler[0]
         yield
     finally:
         if oldsiginthandler:
             signal.signal(signal.SIGINT, oldsiginthandler[0])
         if shouldbail:
             raise KeyboardInterrupt
 
 
 if pycompat.iswindows:
     # no fork on Windows, but we can create a detached process
     # https://msdn.microsoft.com/en-us/library/windows/desktop/ms684863.aspx
     # No stdlib constant exists for this value
     DETACHED_PROCESS = 0x00000008
     # Following creation flags might create a console GUI window.
     # Using subprocess.CREATE_NEW_CONSOLE might helps.
     # See https://phab.mercurial-scm.org/D1701 for discussion
     _creationflags = DETACHED_PROCESS | subprocess.CREATE_NEW_PROCESS_GROUP
 
     def runbgcommand(
         script, env, shell=False, stdout=None, stderr=None, ensurestart=True
     ):
         '''Spawn a command without waiting for it to finish.'''
         # we can't use close_fds *and* redirect stdin. I'm not sure that we
         # need to because the detached process has no console connection.
         subprocess.Popen(
             tonativestr(script),
             shell=shell,
             env=tonativeenv(env),
             close_fds=True,
             creationflags=_creationflags,
             stdout=stdout,
             stderr=stderr,
         )
 
 
 else:
 
     def runbgcommand(
         cmd, env, shell=False, stdout=None, stderr=None, ensurestart=True
     ):
         '''Spawn a command without waiting for it to finish.'''
         # double-fork to completely detach from the parent process
         # based on http://code.activestate.com/recipes/278731
         pid = os.fork()
         if pid:
             if not ensurestart:
                 return
             # Parent process
             (_pid, status) = os.waitpid(pid, 0)
             if os.WIFEXITED(status):
                 returncode = os.WEXITSTATUS(status)
             else:
                 returncode = -(os.WTERMSIG(status))
             if returncode != 0:
                 # The child process's return code is 0 on success, an errno
                 # value on failure, or 255 if we don't have a valid errno
                 # value.
                 #
                 # (It would be slightly nicer to return the full exception info
                 # over a pipe as the subprocess module does.  For now it
                 # doesn't seem worth adding that complexity here, though.)
                 if returncode == 255:
                     returncode = errno.EINVAL
                 raise OSError(
                     returncode,
                     b'error running %r: %s' % (cmd, os.strerror(returncode)),
                 )
             return
 
         returncode = 255
         try:
             # Start a new session
             os.setsid()
 
             stdin = open(os.devnull, b'r')
             if stdout is None:
                 stdout = open(os.devnull, b'w')
             if stderr is None:
                 stderr = open(os.devnull, b'w')
 
             # connect stdin to devnull to make sure the subprocess can't
             # muck up that stream for mercurial.
             subprocess.Popen(
                 cmd,
                 shell=shell,
                 env=env,
                 close_fds=True,
                 stdin=stdin,
                 stdout=stdout,
                 stderr=stderr,
             )
             returncode = 0
         except EnvironmentError as ex:
             returncode = ex.errno & 0xFF
             if returncode == 0:
                 # This shouldn't happen, but just in case make sure the
                 # return code is never 0 here.
                 returncode = 255
         except Exception:
             returncode = 255
         finally:
             # mission accomplished, this child needs to exit and not
             # continue the hg process here.
             os._exit(returncode)