sidedatacopies: deal with upgrading and downgrading to that format

This is quite useful to test this on real life data.

Differential Revision: https://phab.mercurial-scm.org/D6955

mercurial/copies.py

@@ -1,957 +1,1009 b''
 # copies.py - copy detection for Mercurial
 #
 # Copyright 2008 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import collections
 import heapq
 import os
 
 from .i18n import _
 
+
+from .revlogutils.flagutil import REVIDX_SIDEDATA
+
 from . import (
     error,
     match as matchmod,
     node,
     pathutil,
     pycompat,
     util,
 )
+
+from .revlogutils import sidedata as sidedatamod
+
 from .utils import stringutil
 
 
 def _findlimit(repo, ctxa, ctxb):
     """
     Find the last revision that needs to be checked to ensure that a full
     transitive closure for file copies can be properly calculated.
     Generally, this means finding the earliest revision number that's an
     ancestor of a or b but not both, except when a or b is a direct descendent
     of the other, in which case we can return the minimum revnum of a and b.
     """
 
     # basic idea:
     # - mark a and b with different sides
     # - if a parent's children are all on the same side, the parent is
     #   on that side, otherwise it is on no side
     # - walk the graph in topological order with the help of a heap;
     #   - add unseen parents to side map
     #   - clear side of any parent that has children on different sides
     #   - track number of interesting revs that might still be on a side
     #   - track the lowest interesting rev seen
     #   - quit when interesting revs is zero
 
     cl = repo.changelog
     wdirparents = None
     a = ctxa.rev()
     b = ctxb.rev()
     if a is None:
         wdirparents = (ctxa.p1(), ctxa.p2())
         a = node.wdirrev
     if b is None:
         assert not wdirparents
         wdirparents = (ctxb.p1(), ctxb.p2())
         b = node.wdirrev
 
     side = {a: -1, b: 1}
     visit = [-a, -b]
     heapq.heapify(visit)
     interesting = len(visit)
     limit = node.wdirrev
 
     while interesting:
         r = -(heapq.heappop(visit))
         if r == node.wdirrev:
             parents = [pctx.rev() for pctx in wdirparents]
         else:
             parents = cl.parentrevs(r)
         if parents[1] == node.nullrev:
             parents = parents[:1]
         for p in parents:
             if p not in side:
                 # first time we see p; add it to visit
                 side[p] = side[r]
                 if side[p]:
                     interesting += 1
                 heapq.heappush(visit, -p)
             elif side[p] and side[p] != side[r]:
                 # p was interesting but now we know better
                 side[p] = 0
                 interesting -= 1
         if side[r]:
             limit = r  # lowest rev visited
             interesting -= 1
 
     # Consider the following flow (see test-commit-amend.t under issue4405):
     # 1/ File 'a0' committed
     # 2/ File renamed from 'a0' to 'a1' in a new commit (call it 'a1')
     # 3/ Move back to first commit
     # 4/ Create a new commit via revert to contents of 'a1' (call it 'a1-amend')
     # 5/ Rename file from 'a1' to 'a2' and commit --amend 'a1-msg'
     #
     # During the amend in step five, we will be in this state:
     #
     # @  3 temporary amend commit for a1-amend
     # |
     # o  2 a1-amend
     # |
     # | o  1 a1
     # |/
     # o  0 a0
     #
     # When _findlimit is called, a and b are revs 3 and 0, so limit will be 2,
     # yet the filelog has the copy information in rev 1 and we will not look
     # back far enough unless we also look at the a and b as candidates.
     # This only occurs when a is a descendent of b or visa-versa.
     return min(limit, a, b)
 
 
 def _filter(src, dst, t):
     """filters out invalid copies after chaining"""
 
     # When _chain()'ing copies in 'a' (from 'src' via some other commit 'mid')
     # with copies in 'b' (from 'mid' to 'dst'), we can get the different cases
     # in the following table (not including trivial cases). For example, case 2
     # is where a file existed in 'src' and remained under that name in 'mid' and
     # then was renamed between 'mid' and 'dst'.
     #
     # case src mid dst result
     #   1   x   y   -    -
     #   2   x   y   y   x->y
     #   3   x   y   x    -
     #   4   x   y   z   x->z
     #   5   -   x   y    -
     #   6   x   x   y   x->y
     #
     # _chain() takes care of chaining the copies in 'a' and 'b', but it
     # cannot tell the difference between cases 1 and 2, between 3 and 4, or
     # between 5 and 6, so it includes all cases in its result.
     # Cases 1, 3, and 5 are then removed by _filter().
 
     for k, v in list(t.items()):
         # remove copies from files that didn't exist
         if v not in src:
             del t[k]
         # remove criss-crossed copies
         elif k in src and v in dst:
             del t[k]
         # remove copies to files that were then removed
         elif k not in dst:
             del t[k]
 
 
 def _chain(a, b):
     """chain two sets of copies 'a' and 'b'"""
     t = a.copy()
     for k, v in pycompat.iteritems(b):
         if v in t:
             t[k] = t[v]
         else:
             t[k] = v
     return t
 
 
 def _tracefile(fctx, am, basemf, limit):
     """return file context that is the ancestor of fctx present in ancestor
     manifest am, stopping after the first ancestor lower than limit"""
 
     for f in fctx.ancestors():
         path = f.path()
         if am.get(path, None) == f.filenode():
             return path
         if basemf and basemf.get(path, None) == f.filenode():
             return path
         if not f.isintroducedafter(limit):
             return None
 
 
 def _dirstatecopies(repo, match=None):
     ds = repo.dirstate
     c = ds.copies().copy()
     for k in list(c):
         if ds[k] not in b'anm' or (match and not match(k)):
             del c[k]
     return c
 
 
 def _computeforwardmissing(a, b, match=None):
     """Computes which files are in b but not a.
     This is its own function so extensions can easily wrap this call to see what
     files _forwardcopies is about to process.
     """
     ma = a.manifest()
     mb = b.manifest()
     return mb.filesnotin(ma, match=match)
 
 
 def usechangesetcentricalgo(repo):
     """Checks if we should use changeset-centric copy algorithms"""
     if repo.filecopiesmode == b'changeset-sidedata':
         return True
     readfrom = repo.ui.config(b'experimental', b'copies.read-from')
     changesetsource = (b'changeset-only', b'compatibility')
     return readfrom in changesetsource
 
 
 def _committedforwardcopies(a, b, base, match):
     """Like _forwardcopies(), but b.rev() cannot be None (working copy)"""
     # files might have to be traced back to the fctx parent of the last
     # one-side-only changeset, but not further back than that
     repo = a._repo
 
     if usechangesetcentricalgo(repo):
         return _changesetforwardcopies(a, b, match)
 
     debug = repo.ui.debugflag and repo.ui.configbool(b'devel', b'debug.copies')
     dbg = repo.ui.debug
     if debug:
         dbg(b'debug.copies:    looking into rename from %s to %s\n' % (a, b))
     limit = _findlimit(repo, a, b)
     if debug:
         dbg(b'debug.copies:      search limit: %d\n' % limit)
     am = a.manifest()
     basemf = None if base is None else base.manifest()
 
     # find where new files came from
     # we currently don't try to find where old files went, too expensive
     # this means we can miss a case like 'hg rm b; hg cp a b'
     cm = {}
 
     # Computing the forward missing is quite expensive on large manifests, since
     # it compares the entire manifests. We can optimize it in the common use
     # case of computing what copies are in a commit versus its parent (like
     # during a rebase or histedit). Note, we exclude merge commits from this
     # optimization, since the ctx.files() for a merge commit is not correct for
     # this comparison.
     forwardmissingmatch = match
     if b.p1() == a and b.p2().node() == node.nullid:
         filesmatcher = matchmod.exact(b.files())
         forwardmissingmatch = matchmod.intersectmatchers(match, filesmatcher)
     missing = _computeforwardmissing(a, b, match=forwardmissingmatch)
 
     ancestrycontext = a._repo.changelog.ancestors([b.rev()], inclusive=True)
 
     if debug:
         dbg(b'debug.copies:      missing files to search: %d\n' % len(missing))
 
     for f in sorted(missing):
         if debug:
             dbg(b'debug.copies:        tracing file: %s\n' % f)
         fctx = b[f]
         fctx._ancestrycontext = ancestrycontext
 
         if debug:
             start = util.timer()
         opath = _tracefile(fctx, am, basemf, limit)
         if opath:
             if debug:
                 dbg(b'debug.copies:          rename of: %s\n' % opath)
             cm[f] = opath
         if debug:
             dbg(
                 b'debug.copies:          time: %f seconds\n'
                 % (util.timer() - start)
             )
     return cm
 
 
 def _changesetforwardcopies(a, b, match):
     if a.rev() in (node.nullrev, b.rev()):
         return {}
 
     repo = a.repo()
     children = {}
     cl = repo.changelog
     missingrevs = cl.findmissingrevs(common=[a.rev()], heads=[b.rev()])
     for r in missingrevs:
         for p in cl.parentrevs(r):
             if p == node.nullrev:
                 continue
             if p not in children:
                 children[p] = [r]
             else:
                 children[p].append(r)
 
     roots = set(children) - set(missingrevs)
     # 'work' contains 3-tuples of a (revision number, parent number, copies).
     # The parent number is only used for knowing which parent the copies dict
     # came from.
     # NOTE: To reduce costly copying the 'copies' dicts, we reuse the same
     # instance for *one* of the child nodes (the last one). Once an instance
     # has been put on the queue, it is thus no longer safe to modify it.
     # Conversely, it *is* safe to modify an instance popped off the queue.
     work = [(r, 1, {}) for r in roots]
     heapq.heapify(work)
     alwaysmatch = match.always()
     while work:
         r, i1, copies = heapq.heappop(work)
         if work and work[0][0] == r:
             # We are tracing copies from both parents
             r, i2, copies2 = heapq.heappop(work)
             for dst, src in copies2.items():
                 # Unlike when copies are stored in the filelog, we consider
                 # it a copy even if the destination already existed on the
                 # other branch. It's simply too expensive to check if the
                 # file existed in the manifest.
                 if dst not in copies:
                     # If it was copied on the p1 side, leave it as copied from
                     # that side, even if it was also copied on the p2 side.
                     copies[dst] = copies2[dst]
         if r == b.rev():
             return copies
         for i, c in enumerate(children[r]):
             childctx = repo[c]
             if r == childctx.p1().rev():
                 parent = 1
                 childcopies = childctx.p1copies()
             else:
                 assert r == childctx.p2().rev()
                 parent = 2
                 childcopies = childctx.p2copies()
             if not alwaysmatch:
                 childcopies = {
                     dst: src for dst, src in childcopies.items() if match(dst)
                 }
             # Copy the dict only if later iterations will also need it
             if i != len(children[r]) - 1:
                 newcopies = copies.copy()
             else:
                 newcopies = copies
             if childcopies:
                 newcopies = _chain(newcopies, childcopies)
             for f in childctx.filesremoved():
                 if f in newcopies:
                     del newcopies[f]
             heapq.heappush(work, (c, parent, newcopies))
     assert False
 
 
 def _forwardcopies(a, b, base=None, match=None):
     """find {dst@b: src@a} copy mapping where a is an ancestor of b"""
 
     if base is None:
         base = a
     match = a.repo().narrowmatch(match)
     # check for working copy
     if b.rev() is None:
         cm = _committedforwardcopies(a, b.p1(), base, match)
         # combine copies from dirstate if necessary
         copies = _chain(cm, _dirstatecopies(b._repo, match))
     else:
         copies = _committedforwardcopies(a, b, base, match)
     return copies
 
 
 def _backwardrenames(a, b, match):
     if a._repo.ui.config(b'experimental', b'copytrace') == b'off':
         return {}
 
     # Even though we're not taking copies into account, 1:n rename situations
     # can still exist (e.g. hg cp a b; hg mv a c). In those cases we
     # arbitrarily pick one of the renames.
     # We don't want to pass in "match" here, since that would filter
     # the destination by it. Since we're reversing the copies, we want
     # to filter the source instead.
     f = _forwardcopies(b, a)
     r = {}
     for k, v in sorted(pycompat.iteritems(f)):
         if match and not match(v):
             continue
         # remove copies
         if v in a:
             continue
         r[v] = k
     return r
 
 
 def pathcopies(x, y, match=None):
     """find {dst@y: src@x} copy mapping for directed compare"""
     repo = x._repo
     debug = repo.ui.debugflag and repo.ui.configbool(b'devel', b'debug.copies')
     if debug:
         repo.ui.debug(
             b'debug.copies: searching copies from %s to %s\n' % (x, y)
         )
     if x == y or not x or not y:
         return {}
     a = y.ancestor(x)
     if a == x:
         if debug:
             repo.ui.debug(b'debug.copies: search mode: forward\n')
         if y.rev() is None and x == y.p1():
             # short-circuit to avoid issues with merge states
             return _dirstatecopies(repo, match)
         copies = _forwardcopies(x, y, match=match)
     elif a == y:
         if debug:
             repo.ui.debug(b'debug.copies: search mode: backward\n')
         copies = _backwardrenames(x, y, match=match)
     else:
         if debug:
             repo.ui.debug(b'debug.copies: search mode: combined\n')
         base = None
         if a.rev() != node.nullrev:
             base = x
         copies = _chain(
             _backwardrenames(x, a, match=match),
             _forwardcopies(a, y, base, match=match),
         )
     _filter(x, y, copies)
     return copies
 
 
 def mergecopies(repo, c1, c2, base):
     """
     Finds moves and copies between context c1 and c2 that are relevant for
     merging. 'base' will be used as the merge base.
 
     Copytracing is used in commands like rebase, merge, unshelve, etc to merge
     files that were moved/ copied in one merge parent and modified in another.
     For example:
 
     o          ---> 4 another commit
     |
     |   o      ---> 3 commit that modifies a.txt
     |  /
     o /        ---> 2 commit that moves a.txt to b.txt
     |/
     o          ---> 1 merge base
 
     If we try to rebase revision 3 on revision 4, since there is no a.txt in
     revision 4, and if user have copytrace disabled, we prints the following
     message:
 
     ```other changed <file> which local deleted```
 
     Returns five dicts: "copy", "movewithdir", "diverge", "renamedelete" and
     "dirmove".
 
     "copy" is a mapping from destination name -> source name,
     where source is in c1 and destination is in c2 or vice-versa.
 
     "movewithdir" is a mapping from source name -> destination name,
     where the file at source present in one context but not the other
     needs to be moved to destination by the merge process, because the
     other context moved the directory it is in.
 
     "diverge" is a mapping of source name -> list of destination names
     for divergent renames.
 
     "renamedelete" is a mapping of source name -> list of destination
     names for files deleted in c1 that were renamed in c2 or vice-versa.
 
     "dirmove" is a mapping of detected source dir -> destination dir renames.
     This is needed for handling changes to new files previously grafted into
     renamed directories.
 
     This function calls different copytracing algorithms based on config.
     """
     # avoid silly behavior for update from empty dir
     if not c1 or not c2 or c1 == c2:
         return {}, {}, {}, {}, {}
 
     narrowmatch = c1.repo().narrowmatch()
 
     # avoid silly behavior for parent -> working dir
     if c2.node() is None and c1.node() == repo.dirstate.p1():
         return _dirstatecopies(repo, narrowmatch), {}, {}, {}, {}
 
     copytracing = repo.ui.config(b'experimental', b'copytrace')
     if stringutil.parsebool(copytracing) is False:
         # stringutil.parsebool() returns None when it is unable to parse the
         # value, so we should rely on making sure copytracing is on such cases
         return {}, {}, {}, {}, {}
 
     if usechangesetcentricalgo(repo):
         # The heuristics don't make sense when we need changeset-centric algos
         return _fullcopytracing(repo, c1, c2, base)
 
     # Copy trace disabling is explicitly below the node == p1 logic above
     # because the logic above is required for a simple copy to be kept across a
     # rebase.
     if copytracing == b'heuristics':
         # Do full copytracing if only non-public revisions are involved as
         # that will be fast enough and will also cover the copies which could
         # be missed by heuristics
         if _isfullcopytraceable(repo, c1, base):
             return _fullcopytracing(repo, c1, c2, base)
         return _heuristicscopytracing(repo, c1, c2, base)
     else:
         return _fullcopytracing(repo, c1, c2, base)
 
 
 def _isfullcopytraceable(repo, c1, base):
     """ Checks that if base, source and destination are all no-public branches,
     if yes let's use the full copytrace algorithm for increased capabilities
     since it will be fast enough.
 
     `experimental.copytrace.sourcecommitlimit` can be used to set a limit for
     number of changesets from c1 to base such that if number of changesets are
     more than the limit, full copytracing algorithm won't be used.
     """
     if c1.rev() is None:
         c1 = c1.p1()
     if c1.mutable() and base.mutable():
         sourcecommitlimit = repo.ui.configint(
             b'experimental', b'copytrace.sourcecommitlimit'
         )
         commits = len(repo.revs(b'%d::%d', base.rev(), c1.rev()))
         return commits < sourcecommitlimit
     return False
 
 
 def _checksinglesidecopies(
     src, dsts1, m1, m2, mb, c2, base, copy, renamedelete
 ):
     if src not in m2:
         # deleted on side 2
         if src not in m1:
             # renamed on side 1, deleted on side 2
             renamedelete[src] = dsts1
     elif m2[src] != mb[src]:
         if not _related(c2[src], base[src]):
             return
         # modified on side 2
         for dst in dsts1:
             if dst not in m2:
                 # dst not added on side 2 (handle as regular
                 # "both created" case in manifestmerge otherwise)
                 copy[dst] = src
 
 
 def _fullcopytracing(repo, c1, c2, base):
     """ The full copytracing algorithm which finds all the new files that were
     added from merge base up to the top commit and for each file it checks if
     this file was copied from another file.
 
     This is pretty slow when a lot of changesets are involved but will track all
     the copies.
     """
     m1 = c1.manifest()
     m2 = c2.manifest()
     mb = base.manifest()
 
     copies1 = pathcopies(base, c1)
     copies2 = pathcopies(base, c2)
 
     inversecopies1 = {}
     inversecopies2 = {}
     for dst, src in copies1.items():
         inversecopies1.setdefault(src, []).append(dst)
     for dst, src in copies2.items():
         inversecopies2.setdefault(src, []).append(dst)
 
     copy = {}
     diverge = {}
     renamedelete = {}
     allsources = set(inversecopies1) | set(inversecopies2)
     for src in allsources:
         dsts1 = inversecopies1.get(src)
         dsts2 = inversecopies2.get(src)
         if dsts1 and dsts2:
             # copied/renamed on both sides
             if src not in m1 and src not in m2:
                 # renamed on both sides
                 dsts1 = set(dsts1)
                 dsts2 = set(dsts2)
                 # If there's some overlap in the rename destinations, we
                 # consider it not divergent. For example, if side 1 copies 'a'
                 # to 'b' and 'c' and deletes 'a', and side 2 copies 'a' to 'c'
                 # and 'd' and deletes 'a'.
                 if dsts1 & dsts2:
                     for dst in dsts1 & dsts2:
                         copy[dst] = src
                 else:
                     diverge[src] = sorted(dsts1 | dsts2)
             elif src in m1 and src in m2:
                 # copied on both sides
                 dsts1 = set(dsts1)
                 dsts2 = set(dsts2)
                 for dst in dsts1 & dsts2:
                     copy[dst] = src
             # TODO: Handle cases where it was renamed on one side and copied
             # on the other side
         elif dsts1:
             # copied/renamed only on side 1
             _checksinglesidecopies(
                 src, dsts1, m1, m2, mb, c2, base, copy, renamedelete
             )
         elif dsts2:
             # copied/renamed only on side 2
             _checksinglesidecopies(
                 src, dsts2, m2, m1, mb, c1, base, copy, renamedelete
             )
 
     renamedeleteset = set()
     divergeset = set()
     for dsts in diverge.values():
         divergeset.update(dsts)
     for dsts in renamedelete.values():
         renamedeleteset.update(dsts)
 
     # find interesting file sets from manifests
     addedinm1 = m1.filesnotin(mb, repo.narrowmatch())
     addedinm2 = m2.filesnotin(mb, repo.narrowmatch())
     u1 = sorted(addedinm1 - addedinm2)
     u2 = sorted(addedinm2 - addedinm1)
 
     header = b"  unmatched files in %s"
     if u1:
         repo.ui.debug(b"%s:\n   %s\n" % (header % b'local', b"\n   ".join(u1)))
     if u2:
         repo.ui.debug(b"%s:\n   %s\n" % (header % b'other', b"\n   ".join(u2)))
 
     fullcopy = copies1.copy()
     fullcopy.update(copies2)
     if not fullcopy:
         return copy, {}, diverge, renamedelete, {}
 
     if repo.ui.debugflag:
         repo.ui.debug(
             b"  all copies found (* = to merge, ! = divergent, "
             b"% = renamed and deleted):\n"
         )
         for f in sorted(fullcopy):
             note = b""
             if f in copy:
                 note += b"*"
             if f in divergeset:
                 note += b"!"
             if f in renamedeleteset:
                 note += b"%"
             repo.ui.debug(
                 b"   src: '%s' -> dst: '%s' %s\n" % (fullcopy[f], f, note)
             )
     del divergeset
 
     repo.ui.debug(b"  checking for directory renames\n")
 
     # generate a directory move map
     d1, d2 = c1.dirs(), c2.dirs()
     invalid = set()
     dirmove = {}
 
     # examine each file copy for a potential directory move, which is
     # when all the files in a directory are moved to a new directory
     for dst, src in pycompat.iteritems(fullcopy):
         dsrc, ddst = pathutil.dirname(src), pathutil.dirname(dst)
         if dsrc in invalid:
             # already seen to be uninteresting
             continue
         elif dsrc in d1 and ddst in d1:
             # directory wasn't entirely moved locally
             invalid.add(dsrc)
         elif dsrc in d2 and ddst in d2:
             # directory wasn't entirely moved remotely
             invalid.add(dsrc)
         elif dsrc in dirmove and dirmove[dsrc] != ddst:
             # files from the same directory moved to two different places
             invalid.add(dsrc)
         else:
             # looks good so far
             dirmove[dsrc] = ddst
 
     for i in invalid:
         if i in dirmove:
             del dirmove[i]
     del d1, d2, invalid
 
     if not dirmove:
         return copy, {}, diverge, renamedelete, {}
 
     dirmove = {k + b"/": v + b"/" for k, v in pycompat.iteritems(dirmove)}
 
     for d in dirmove:
         repo.ui.debug(
             b"   discovered dir src: '%s' -> dst: '%s'\n" % (d, dirmove[d])
         )
 
     movewithdir = {}
     # check unaccounted nonoverlapping files against directory moves
     for f in u1 + u2:
         if f not in fullcopy:
             for d in dirmove:
                 if f.startswith(d):
                     # new file added in a directory that was moved, move it
                     df = dirmove[d] + f[len(d) :]
                     if df not in copy:
                         movewithdir[f] = df
                         repo.ui.debug(
                             b"   pending file src: '%s' -> dst: '%s'\n"
                             % (f, df)
                         )
                     break
 
     return copy, movewithdir, diverge, renamedelete, dirmove
 
 
 def _heuristicscopytracing(repo, c1, c2, base):
     """ Fast copytracing using filename heuristics
 
     Assumes that moves or renames are of following two types:
 
     1) Inside a directory only (same directory name but different filenames)
     2) Move from one directory to another
                     (same filenames but different directory names)
 
     Works only when there are no merge commits in the "source branch".
     Source branch is commits from base up to c2 not including base.
 
     If merge is involved it fallbacks to _fullcopytracing().
 
     Can be used by setting the following config:
 
         [experimental]
         copytrace = heuristics
 
     In some cases the copy/move candidates found by heuristics can be very large
     in number and that will make the algorithm slow. The number of possible
     candidates to check can be limited by using the config
     `experimental.copytrace.movecandidateslimit` which defaults to 100.
     """
 
     if c1.rev() is None:
         c1 = c1.p1()
     if c2.rev() is None:
         c2 = c2.p1()
 
     copies = {}
 
     changedfiles = set()
     m1 = c1.manifest()
     if not repo.revs(b'%d::%d', base.rev(), c2.rev()):
         # If base is not in c2 branch, we switch to fullcopytracing
         repo.ui.debug(
             b"switching to full copytracing as base is not "
             b"an ancestor of c2\n"
         )
         return _fullcopytracing(repo, c1, c2, base)
 
     ctx = c2
     while ctx != base:
         if len(ctx.parents()) == 2:
             # To keep things simple let's not handle merges
             repo.ui.debug(b"switching to full copytracing because of merges\n")
             return _fullcopytracing(repo, c1, c2, base)
         changedfiles.update(ctx.files())
         ctx = ctx.p1()
 
     cp = _forwardcopies(base, c2)
     for dst, src in pycompat.iteritems(cp):
         if src in m1:
             copies[dst] = src
 
     # file is missing if it isn't present in the destination, but is present in
     # the base and present in the source.
     # Presence in the base is important to exclude added files, presence in the
     # source is important to exclude removed files.
     filt = lambda f: f not in m1 and f in base and f in c2
     missingfiles = [f for f in changedfiles if filt(f)]
 
     if missingfiles:
         basenametofilename = collections.defaultdict(list)
         dirnametofilename = collections.defaultdict(list)
 
         for f in m1.filesnotin(base.manifest()):
             basename = os.path.basename(f)
             dirname = os.path.dirname(f)
             basenametofilename[basename].append(f)
             dirnametofilename[dirname].append(f)
 
         for f in missingfiles:
             basename = os.path.basename(f)
             dirname = os.path.dirname(f)
             samebasename = basenametofilename[basename]
             samedirname = dirnametofilename[dirname]
             movecandidates = samebasename + samedirname
             # f is guaranteed to be present in c2, that's why
             # c2.filectx(f) won't fail
             f2 = c2.filectx(f)
             # we can have a lot of candidates which can slow down the heuristics
             # config value to limit the number of candidates moves to check
             maxcandidates = repo.ui.configint(
                 b'experimental', b'copytrace.movecandidateslimit'
             )
 
             if len(movecandidates) > maxcandidates:
                 repo.ui.status(
                     _(
                         b"skipping copytracing for '%s', more "
                         b"candidates than the limit: %d\n"
                     )
                     % (f, len(movecandidates))
                 )
                 continue
 
             for candidate in movecandidates:
                 f1 = c1.filectx(candidate)
                 if _related(f1, f2):
                     # if there are a few related copies then we'll merge
                     # changes into all of them. This matches the behaviour
                     # of upstream copytracing
                     copies[candidate] = f
 
     return copies, {}, {}, {}, {}
 
 
 def _related(f1, f2):
     """return True if f1 and f2 filectx have a common ancestor
 
     Walk back to common ancestor to see if the two files originate
     from the same file. Since workingfilectx's rev() is None it messes
     up the integer comparison logic, hence the pre-step check for
     None (f1 and f2 can only be workingfilectx's initially).
     """
 
     if f1 == f2:
         return True  # a match
 
     g1, g2 = f1.ancestors(), f2.ancestors()
     try:
         f1r, f2r = f1.linkrev(), f2.linkrev()
 
         if f1r is None:
             f1 = next(g1)
         if f2r is None:
             f2 = next(g2)
 
         while True:
             f1r, f2r = f1.linkrev(), f2.linkrev()
             if f1r > f2r:
                 f1 = next(g1)
             elif f2r > f1r:
                 f2 = next(g2)
             else:  # f1 and f2 point to files in the same linkrev
                 return f1 == f2  # true if they point to the same file
     except StopIteration:
         return False
 
 
 def duplicatecopies(repo, wctx, rev, fromrev, skiprev=None):
     """reproduce copies from fromrev to rev in the dirstate
 
     If skiprev is specified, it's a revision that should be used to
     filter copy records. Any copies that occur between fromrev and
     skiprev will not be duplicated, even if they appear in the set of
     copies between fromrev and rev.
     """
     exclude = {}
     ctraceconfig = repo.ui.config(b'experimental', b'copytrace')
     bctrace = stringutil.parsebool(ctraceconfig)
     if skiprev is not None and (
         ctraceconfig == b'heuristics' or bctrace or bctrace is None
     ):
         # copytrace='off' skips this line, but not the entire function because
         # the line below is O(size of the repo) during a rebase, while the rest
         # of the function is much faster (and is required for carrying copy
         # metadata across the rebase anyway).
         exclude = pathcopies(repo[fromrev], repo[skiprev])
     for dst, src in pycompat.iteritems(pathcopies(repo[fromrev], repo[rev])):
         if dst in exclude:
             continue
         if dst in wctx:
             wctx[dst].markcopied(src)
 
 
 def computechangesetfilesadded(ctx):
     """return the list of files added in a changeset
     """
     added = []
     for f in ctx.files():
         if not any(f in p for p in ctx.parents()):
             added.append(f)
     return added
 
 
 def computechangesetfilesremoved(ctx):
     """return the list of files removed in a changeset
     """
     removed = []
     for f in ctx.files():
         if f not in ctx:
             removed.append(f)
     return removed
 
 
 def computechangesetcopies(ctx):
     """return the copies data for a changeset
 
     The copies data are returned as a pair of dictionnary (p1copies, p2copies).
 
     Each dictionnary are in the form: `{newname: oldname}`
     """
     p1copies = {}
     p2copies = {}
     p1 = ctx.p1()
     p2 = ctx.p2()
     narrowmatch = ctx._repo.narrowmatch()
     for dst in ctx.files():
         if not narrowmatch(dst) or dst not in ctx:
             continue
         copied = ctx[dst].renamed()
         if not copied:
             continue
         src, srcnode = copied
         if src in p1 and p1[src].filenode() == srcnode:
             p1copies[dst] = src
         elif src in p2 and p2[src].filenode() == srcnode:
             p2copies[dst] = src
     return p1copies, p2copies
 
 
 def encodecopies(files, copies):
     items = []
     for i, dst in enumerate(files):
         if dst in copies:
             items.append(b'%d\0%s' % (i, copies[dst]))
     if len(items) != len(copies):
         raise error.ProgrammingError(
             b'some copy targets missing from file list'
         )
     return b"\n".join(items)
 
 
 def decodecopies(files, data):
     try:
         copies = {}
         if not data:
             return copies
         for l in data.split(b'\n'):
             strindex, src = l.split(b'\0')
             i = int(strindex)
             dst = files[i]
             copies[dst] = src
         return copies
     except (ValueError, IndexError):
         # Perhaps someone had chosen the same key name (e.g. "p1copies") and
         # used different syntax for the value.
         return None
 
 
 def encodefileindices(files, subset):
     subset = set(subset)
     indices = []
     for i, f in enumerate(files):
         if f in subset:
             indices.append(b'%d' % i)
     return b'\n'.join(indices)
 
 
 def decodefileindices(files, data):
     try:
         subset = []
         if not data:
             return subset
         for strindex in data.split(b'\n'):
             i = int(strindex)
             if i < 0 or i >= len(files):
                 return None
             subset.append(files[i])
         return subset
     except (ValueError, IndexError):
         # Perhaps someone had chosen the same key name (e.g. "added") and
         # used different syntax for the value.
         return None
+
+
+def _getsidedata(srcrepo, rev):
+    ctx = srcrepo[rev]
+    filescopies = computechangesetcopies(ctx)
+    filesadded = computechangesetfilesadded(ctx)
+    filesremoved = computechangesetfilesremoved(ctx)
+    sidedata = {}
+    if any([filescopies, filesadded, filesremoved]):
+        sortedfiles = sorted(ctx.files())
+        p1copies, p2copies = filescopies
+        p1copies = encodecopies(sortedfiles, p1copies)
+        p2copies = encodecopies(sortedfiles, p2copies)
+        filesadded = encodefileindices(sortedfiles, filesadded)
+        filesremoved = encodefileindices(sortedfiles, filesremoved)
+        sidedata[sidedatamod.SD_P1COPIES] = p1copies
+        sidedata[sidedatamod.SD_P2COPIES] = p2copies
+        sidedata[sidedatamod.SD_FILESADDED] = filesadded
+        sidedata[sidedatamod.SD_FILESREMOVED] = filesremoved
+    return sidedata
+
+
+def getsidedataadder(srcrepo, destrepo):
+    def sidedatacompanion(revlog, rev):
+        sidedata = {}
+        if util.safehasattr(revlog, 'filteredrevs'):  # this is a changelog
+            sidedata = _getsidedata(srcrepo, rev)
+        return False, (), sidedata
+
+    return sidedatacompanion
+
+
+def getsidedataremover(srcrepo, destrepo):
+    def sidedatacompanion(revlog, rev):
+        f = ()
+        if util.safehasattr(revlog, 'filteredrevs'):  # this is a changelog
+            if revlog.flags(rev) & REVIDX_SIDEDATA:
+                f = (
+                    sidedatamod.SD_P1COPIES,
+                    sidedatamod.SD_P2COPIES,
+                    sidedatamod.SD_FILESADDED,
+                    sidedatamod.SD_FILESREMOVED,
+                )
+        return False, f, {}
+
+    return sidedatacompanion

mercurial/upgrade.py

@@ -1,1379 +1,1387 b''
 # upgrade.py - functions for in place upgrade of Mercurial repository
 #
 # Copyright (c) 2016-present, Gregory Szorc
 #
 # 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 stat
 
 from .i18n import _
 from .pycompat import getattr
 from . import (
     changelog,
+    copies,
     error,
     filelog,
     hg,
     localrepo,
     manifest,
     pycompat,
     revlog,
     scmutil,
     util,
     vfs as vfsmod,
 )
 
 from .utils import compression
 
 # list of requirements that request a clone of all revlog if added/removed
 RECLONES_REQUIREMENTS = {
     b'generaldelta',
     localrepo.SPARSEREVLOG_REQUIREMENT,
-    localrepo.SIDEDATA_REQUIREMENT,
 }
 
 
 def requiredsourcerequirements(repo):
     """Obtain requirements required to be present to upgrade a repo.
 
     An upgrade will not be allowed if the repository doesn't have the
     requirements returned by this function.
     """
     return {
         # Introduced in Mercurial 0.9.2.
         b'revlogv1',
         # Introduced in Mercurial 0.9.2.
         b'store',
     }
 
 
 def blocksourcerequirements(repo):
     """Obtain requirements that will prevent an upgrade from occurring.
 
     An upgrade cannot be performed if the source repository contains a
     requirements in the returned set.
     """
     return {
         # The upgrade code does not yet support these experimental features.
         # This is an artificial limitation.
         b'treemanifest',
         # This was a precursor to generaldelta and was never enabled by default.
         # It should (hopefully) not exist in the wild.
         b'parentdelta',
         # Upgrade should operate on the actual store, not the shared link.
         b'shared',
     }
 
 
 def supportremovedrequirements(repo):
     """Obtain requirements that can be removed during an upgrade.
 
     If an upgrade were to create a repository that dropped a requirement,
     the dropped requirement must appear in the returned set for the upgrade
     to be allowed.
     """
     supported = {
         localrepo.SPARSEREVLOG_REQUIREMENT,
         localrepo.SIDEDATA_REQUIREMENT,
+        localrepo.COPIESSDC_REQUIREMENT,
     }
     for name in compression.compengines:
         engine = compression.compengines[name]
         if engine.available() and engine.revlogheader():
             supported.add(b'exp-compression-%s' % name)
             if engine.name() == b'zstd':
                 supported.add(b'revlog-compression-zstd')
     return supported
 
 
 def supporteddestrequirements(repo):
     """Obtain requirements that upgrade supports in the destination.
 
     If the result of the upgrade would create requirements not in this set,
     the upgrade is disallowed.
 
     Extensions should monkeypatch this to add their custom requirements.
     """
     supported = {
         b'dotencode',
         b'fncache',
         b'generaldelta',
         b'revlogv1',
         b'store',
         localrepo.SPARSEREVLOG_REQUIREMENT,
         localrepo.SIDEDATA_REQUIREMENT,
+        localrepo.COPIESSDC_REQUIREMENT,
     }
     for name in compression.compengines:
         engine = compression.compengines[name]
         if engine.available() and engine.revlogheader():
             supported.add(b'exp-compression-%s' % name)
             if engine.name() == b'zstd':
                 supported.add(b'revlog-compression-zstd')
     return supported
 
 
 def allowednewrequirements(repo):
     """Obtain requirements that can be added to a repository during upgrade.
 
     This is used to disallow proposed requirements from being added when
     they weren't present before.
 
     We use a list of allowed requirement additions instead of a list of known
     bad additions because the whitelist approach is safer and will prevent
     future, unknown requirements from accidentally being added.
     """
     supported = {
         b'dotencode',
         b'fncache',
         b'generaldelta',
         localrepo.SPARSEREVLOG_REQUIREMENT,
         localrepo.SIDEDATA_REQUIREMENT,
+        localrepo.COPIESSDC_REQUIREMENT,
     }
     for name in compression.compengines:
         engine = compression.compengines[name]
         if engine.available() and engine.revlogheader():
             supported.add(b'exp-compression-%s' % name)
             if engine.name() == b'zstd':
                 supported.add(b'revlog-compression-zstd')
     return supported
 
 
 def preservedrequirements(repo):
     return set()
 
 
 deficiency = b'deficiency'
 optimisation = b'optimization'
 
 
 class improvement(object):
     """Represents an improvement that can be made as part of an upgrade.
 
     The following attributes are defined on each instance:
 
     name
        Machine-readable string uniquely identifying this improvement. It
        will be mapped to an action later in the upgrade process.
 
     type
        Either ``deficiency`` or ``optimisation``. A deficiency is an obvious
        problem. An optimization is an action (sometimes optional) that
        can be taken to further improve the state of the repository.
 
     description
        Message intended for humans explaining the improvement in more detail,
        including the implications of it. For ``deficiency`` types, should be
        worded in the present tense. For ``optimisation`` types, should be
        worded in the future tense.
 
     upgrademessage
        Message intended for humans explaining what an upgrade addressing this
        issue will do. Should be worded in the future tense.
     """
 
     def __init__(self, name, type, description, upgrademessage):
         self.name = name
         self.type = type
         self.description = description
         self.upgrademessage = upgrademessage
 
     def __eq__(self, other):
         if not isinstance(other, improvement):
             # This is what python tell use to do
             return NotImplemented
         return self.name == other.name
 
     def __ne__(self, other):
         return not (self == other)
 
     def __hash__(self):
         return hash(self.name)
 
 
 allformatvariant = []
 
 
 def registerformatvariant(cls):
     allformatvariant.append(cls)
     return cls
 
 
 class formatvariant(improvement):
     """an improvement subclass dedicated to repository format"""
 
     type = deficiency
     ### The following attributes should be defined for each class:
 
     # machine-readable string uniquely identifying this improvement. it will be
     # mapped to an action later in the upgrade process.
     name = None
 
     # message intended for humans explaining the improvement in more detail,
     # including the implications of it ``deficiency`` types, should be worded
     # in the present tense.
     description = None
 
     # message intended for humans explaining what an upgrade addressing this
     # issue will do. should be worded in the future tense.
     upgrademessage = None
 
     # value of current Mercurial default for new repository
     default = None
 
     def __init__(self):
         raise NotImplementedError()
 
     @staticmethod
     def fromrepo(repo):
         """current value of the variant in the repository"""
         raise NotImplementedError()
 
     @staticmethod
     def fromconfig(repo):
         """current value of the variant in the configuration"""
         raise NotImplementedError()
 
 
 class requirementformatvariant(formatvariant):
     """formatvariant based on a 'requirement' name.
 
     Many format variant are controlled by a 'requirement'. We define a small
     subclass to factor the code.
     """
 
     # the requirement that control this format variant
     _requirement = None
 
     @staticmethod
     def _newreporequirements(ui):
         return localrepo.newreporequirements(
             ui, localrepo.defaultcreateopts(ui)
         )
 
     @classmethod
     def fromrepo(cls, repo):
         assert cls._requirement is not None
         return cls._requirement in repo.requirements
 
     @classmethod
     def fromconfig(cls, repo):
         assert cls._requirement is not None
         return cls._requirement in cls._newreporequirements(repo.ui)
 
 
 @registerformatvariant
 class fncache(requirementformatvariant):
     name = b'fncache'
 
     _requirement = b'fncache'
 
     default = True
 
     description = _(
         b'long and reserved filenames may not work correctly; '
         b'repository performance is sub-optimal'
     )
 
     upgrademessage = _(
         b'repository will be more resilient to storing '
         b'certain paths and performance of certain '
         b'operations should be improved'
     )
 
 
 @registerformatvariant
 class dotencode(requirementformatvariant):
     name = b'dotencode'
 
     _requirement = b'dotencode'
 
     default = True
 
     description = _(
         b'storage of filenames beginning with a period or '
         b'space may not work correctly'
     )
 
     upgrademessage = _(
         b'repository will be better able to store files '
         b'beginning with a space or period'
     )
 
 
 @registerformatvariant
 class generaldelta(requirementformatvariant):
     name = b'generaldelta'
 
     _requirement = b'generaldelta'
 
     default = True
 
     description = _(
         b'deltas within internal storage are unable to '
         b'choose optimal revisions; repository is larger and '
         b'slower than it could be; interaction with other '
         b'repositories may require extra network and CPU '
         b'resources, making "hg push" and "hg pull" slower'
     )
 
     upgrademessage = _(
         b'repository storage will be able to create '
         b'optimal deltas; new repository data will be '
         b'smaller and read times should decrease; '
         b'interacting with other repositories using this '
         b'storage model should require less network and '
         b'CPU resources, making "hg push" and "hg pull" '
         b'faster'
     )
 
 
 @registerformatvariant
 class sparserevlog(requirementformatvariant):
     name = b'sparserevlog'
 
     _requirement = localrepo.SPARSEREVLOG_REQUIREMENT
 
     default = True
 
     description = _(
         b'in order to limit disk reading and memory usage on older '
         b'version, the span of a delta chain from its root to its '
         b'end is limited, whatever the relevant data in this span. '
         b'This can severly limit Mercurial ability to build good '
         b'chain of delta resulting is much more storage space being '
         b'taken and limit reusability of on disk delta during '
         b'exchange.'
     )
 
     upgrademessage = _(
         b'Revlog supports delta chain with more unused data '
         b'between payload. These gaps will be skipped at read '
         b'time. This allows for better delta chains, making a '
         b'better compression and faster exchange with server.'
     )
 
 
 @registerformatvariant
 class sidedata(requirementformatvariant):
     name = b'sidedata'
 
     _requirement = localrepo.SIDEDATA_REQUIREMENT
 
     default = False
 
     description = _(
         b'Allows storage of extra data alongside a revision, '
         b'unlocking various caching options.'
     )
 
     upgrademessage = _(b'Allows storage of extra data alongside a revision.')
 
 
 @registerformatvariant
 class copiessdc(requirementformatvariant):
     name = b'copies-sdc'
 
     _requirement = localrepo.COPIESSDC_REQUIREMENT
 
     default = False
 
     description = _(b'Stores copies information alongside changesets.')
 
     upgrademessage = _(
         b'Allows to use more efficient algorithm to deal with ' b'copy tracing.'
     )
 
 
 @registerformatvariant
 class removecldeltachain(formatvariant):
     name = b'plain-cl-delta'
 
     default = True
 
     description = _(
         b'changelog storage is using deltas instead of '
         b'raw entries; changelog reading and any '
         b'operation relying on changelog data are slower '
         b'than they could be'
     )
 
     upgrademessage = _(
         b'changelog storage will be reformated to '
         b'store raw entries; changelog reading will be '
         b'faster; changelog size may be reduced'
     )
 
     @staticmethod
     def fromrepo(repo):
         # Mercurial 4.0 changed changelogs to not use delta chains. Search for
         # changelogs with deltas.
         cl = repo.changelog
         chainbase = cl.chainbase
         return all(rev == chainbase(rev) for rev in cl)
 
     @staticmethod
     def fromconfig(repo):
         return True
 
 
 @registerformatvariant
 class compressionengine(formatvariant):
     name = b'compression'
     default = b'zlib'
 
     description = _(
         b'Compresion algorithm used to compress data. '
         b'Some engine are faster than other'
     )
 
     upgrademessage = _(
         b'revlog content will be recompressed with the new algorithm.'
     )
 
     @classmethod
     def fromrepo(cls, repo):
         # we allow multiple compression engine requirement to co-exist because
         # strickly speaking, revlog seems to support mixed compression style.
         #
         # The compression used for new entries will be "the last one"
         compression = b'zlib'
         for req in repo.requirements:
             prefix = req.startswith
             if prefix(b'revlog-compression-') or prefix(b'exp-compression-'):
                 compression = req.split(b'-', 2)[2]
         return compression
 
     @classmethod
     def fromconfig(cls, repo):
         return repo.ui.config(b'format', b'revlog-compression')
 
 
 @registerformatvariant
 class compressionlevel(formatvariant):
     name = b'compression-level'
     default = b'default'
 
     description = _(b'compression level')
 
     upgrademessage = _(b'revlog content will be recompressed')
 
     @classmethod
     def fromrepo(cls, repo):
         comp = compressionengine.fromrepo(repo)
         level = None
         if comp == b'zlib':
             level = repo.ui.configint(b'storage', b'revlog.zlib.level')
         elif comp == b'zstd':
             level = repo.ui.configint(b'storage', b'revlog.zstd.level')
         if level is None:
             return b'default'
         return bytes(level)
 
     @classmethod
     def fromconfig(cls, repo):
         comp = compressionengine.fromconfig(repo)
         level = None
         if comp == b'zlib':
             level = repo.ui.configint(b'storage', b'revlog.zlib.level')
         elif comp == b'zstd':
             level = repo.ui.configint(b'storage', b'revlog.zstd.level')
         if level is None:
             return b'default'
         return bytes(level)
 
 
 def finddeficiencies(repo):
     """returns a list of deficiencies that the repo suffer from"""
     deficiencies = []
 
     # We could detect lack of revlogv1 and store here, but they were added
     # in 0.9.2 and we don't support upgrading repos without these
     # requirements, so let's not bother.
 
     for fv in allformatvariant:
         if not fv.fromrepo(repo):
             deficiencies.append(fv)
 
     return deficiencies
 
 
 # search without '-' to support older form on newer client.
 #
 # We don't enforce backward compatibility for debug command so this
 # might eventually be dropped. However, having to use two different
 # forms in script when comparing result is anoying enough to add
 # backward compatibility for a while.
 legacy_opts_map = {
     b'redeltaparent': b're-delta-parent',
     b'redeltamultibase': b're-delta-multibase',
     b'redeltaall': b're-delta-all',
     b'redeltafulladd': b're-delta-fulladd',
 }
 
 
 def findoptimizations(repo):
     """Determine optimisation that could be used during upgrade"""
     # These are unconditionally added. There is logic later that figures out
     # which ones to apply.
     optimizations = []
 
     optimizations.append(
         improvement(
             name=b're-delta-parent',
             type=optimisation,
             description=_(
                 b'deltas within internal storage will be recalculated to '
                 b'choose an optimal base revision where this was not '
                 b'already done; the size of the repository may shrink and '
                 b'various operations may become faster; the first time '
                 b'this optimization is performed could slow down upgrade '
                 b'execution considerably; subsequent invocations should '
                 b'not run noticeably slower'
             ),
             upgrademessage=_(
                 b'deltas within internal storage will choose a new '
                 b'base revision if needed'
             ),
         )
     )
 
     optimizations.append(
         improvement(
             name=b're-delta-multibase',
             type=optimisation,
             description=_(
                 b'deltas within internal storage will be recalculated '
                 b'against multiple base revision and the smallest '
                 b'difference will be used; the size of the repository may '
                 b'shrink significantly when there are many merges; this '
                 b'optimization will slow down execution in proportion to '
                 b'the number of merges in the repository and the amount '
                 b'of files in the repository; this slow down should not '
                 b'be significant unless there are tens of thousands of '
                 b'files and thousands of merges'
             ),
             upgrademessage=_(
                 b'deltas within internal storage will choose an '
                 b'optimal delta by computing deltas against multiple '
                 b'parents; may slow down execution time '
                 b'significantly'
             ),
         )
     )
 
     optimizations.append(
         improvement(
             name=b're-delta-all',
             type=optimisation,
             description=_(
                 b'deltas within internal storage will always be '
                 b'recalculated without reusing prior deltas; this will '
                 b'likely make execution run several times slower; this '
                 b'optimization is typically not needed'
             ),
             upgrademessage=_(
                 b'deltas within internal storage will be fully '
                 b'recomputed; this will likely drastically slow down '
                 b'execution time'
             ),
         )
     )
 
     optimizations.append(
         improvement(
             name=b're-delta-fulladd',
             type=optimisation,
             description=_(
                 b'every revision will be re-added as if it was new '
                 b'content. It will go through the full storage '
                 b'mechanism giving extensions a chance to process it '
                 b'(eg. lfs). This is similar to "re-delta-all" but even '
                 b'slower since more logic is involved.'
             ),
             upgrademessage=_(
                 b'each revision will be added as new content to the '
                 b'internal storage; this will likely drastically slow '
                 b'down execution time, but some extensions might need '
                 b'it'
             ),
         )
     )
 
     return optimizations
 
 
 def determineactions(repo, deficiencies, sourcereqs, destreqs):
     """Determine upgrade actions that will be performed.
 
     Given a list of improvements as returned by ``finddeficiencies`` and
     ``findoptimizations``, determine the list of upgrade actions that
     will be performed.
 
     The role of this function is to filter improvements if needed, apply
     recommended optimizations from the improvements list that make sense,
     etc.
 
     Returns a list of action names.
     """
     newactions = []
 
     knownreqs = supporteddestrequirements(repo)
 
     for d in deficiencies:
         name = d.name
 
         # If the action is a requirement that doesn't show up in the
         # destination requirements, prune the action.
         if name in knownreqs and name not in destreqs:
             continue
 
         newactions.append(d)
 
     # FUTURE consider adding some optimizations here for certain transitions.
     # e.g. adding generaldelta could schedule parent redeltas.
 
     return newactions
 
 
 def _revlogfrompath(repo, path):
     """Obtain a revlog from a repo path.
 
     An instance of the appropriate class is returned.
     """
     if path == b'00changelog.i':
         return changelog.changelog(repo.svfs)
     elif path.endswith(b'00manifest.i'):
         mandir = path[: -len(b'00manifest.i')]
         return manifest.manifestrevlog(repo.svfs, tree=mandir)
     else:
         # reverse of "/".join(("data", path + ".i"))
         return filelog.filelog(repo.svfs, path[5:-2])
 
 
 def _copyrevlog(tr, destrepo, oldrl, unencodedname):
     """copy all relevant files for `oldrl` into `destrepo` store
 
     Files are copied "as is" without any transformation. The copy is performed
     without extra checks. Callers are responsible for making sure the copied
     content is compatible with format of the destination repository.
     """
     oldrl = getattr(oldrl, '_revlog', oldrl)
     newrl = _revlogfrompath(destrepo, unencodedname)
     newrl = getattr(newrl, '_revlog', newrl)
 
     oldvfs = oldrl.opener
     newvfs = newrl.opener
     oldindex = oldvfs.join(oldrl.indexfile)
     newindex = newvfs.join(newrl.indexfile)
     olddata = oldvfs.join(oldrl.datafile)
     newdata = newvfs.join(newrl.datafile)
 
     with newvfs(newrl.indexfile, b'w'):
         pass  # create all the directories
 
     util.copyfile(oldindex, newindex)
     copydata = oldrl.opener.exists(oldrl.datafile)
     if copydata:
         util.copyfile(olddata, newdata)
 
     if not (
         unencodedname.endswith(b'00changelog.i')
         or unencodedname.endswith(b'00manifest.i')
     ):
         destrepo.svfs.fncache.add(unencodedname)
         if copydata:
             destrepo.svfs.fncache.add(unencodedname[:-2] + b'.d')
 
 
 UPGRADE_CHANGELOG = object()
 UPGRADE_MANIFEST = object()
 UPGRADE_FILELOG = object()
 
 UPGRADE_ALL_REVLOGS = frozenset(
     [UPGRADE_CHANGELOG, UPGRADE_MANIFEST, UPGRADE_FILELOG]
 )
 
 
 def getsidedatacompanion(srcrepo, dstrepo):
     sidedatacompanion = None
     removedreqs = srcrepo.requirements - dstrepo.requirements
+    addedreqs = dstrepo.requirements - srcrepo.requirements
     if localrepo.SIDEDATA_REQUIREMENT in removedreqs:
 
         def sidedatacompanion(rl, rev):
             rl = getattr(rl, '_revlog', rl)
             if rl.flags(rev) & revlog.REVIDX_SIDEDATA:
                 return True, (), {}
             return False, (), {}
 
+    elif localrepo.COPIESSDC_REQUIREMENT in addedreqs:
+        sidedatacompanion = copies.getsidedataadder(srcrepo, dstrepo)
+    elif localrepo.COPIESSDC_REQUIREMENT in removedreqs:
+        sidedatacompanion = copies.getsidedataremover(srcrepo, dstrepo)
     return sidedatacompanion
 
 
 def matchrevlog(revlogfilter, entry):
     """check is a revlog is selected for cloning
 
     The store entry is checked against the passed filter"""
     if entry.endswith(b'00changelog.i'):
         return UPGRADE_CHANGELOG in revlogfilter
     elif entry.endswith(b'00manifest.i'):
         return UPGRADE_MANIFEST in revlogfilter
     return UPGRADE_FILELOG in revlogfilter
 
 
 def _clonerevlogs(
     ui,
     srcrepo,
     dstrepo,
     tr,
     deltareuse,
     forcedeltabothparents,
     revlogs=UPGRADE_ALL_REVLOGS,
 ):
     """Copy revlogs between 2 repos."""
     revcount = 0
     srcsize = 0
     srcrawsize = 0
     dstsize = 0
     fcount = 0
     frevcount = 0
     fsrcsize = 0
     frawsize = 0
     fdstsize = 0
     mcount = 0
     mrevcount = 0
     msrcsize = 0
     mrawsize = 0
     mdstsize = 0
     crevcount = 0
     csrcsize = 0
     crawsize = 0
     cdstsize = 0
 
     alldatafiles = list(srcrepo.store.walk())
 
     # Perform a pass to collect metadata. This validates we can open all
     # source files and allows a unified progress bar to be displayed.
     for unencoded, encoded, size in alldatafiles:
         if unencoded.endswith(b'.d'):
             continue
 
         rl = _revlogfrompath(srcrepo, unencoded)
 
         info = rl.storageinfo(
             exclusivefiles=True,
             revisionscount=True,
             trackedsize=True,
             storedsize=True,
         )
 
         revcount += info[b'revisionscount'] or 0
         datasize = info[b'storedsize'] or 0
         rawsize = info[b'trackedsize'] or 0
 
         srcsize += datasize
         srcrawsize += rawsize
 
         # This is for the separate progress bars.
         if isinstance(rl, changelog.changelog):
             crevcount += len(rl)
             csrcsize += datasize
             crawsize += rawsize
         elif isinstance(rl, manifest.manifestrevlog):
             mcount += 1
             mrevcount += len(rl)
             msrcsize += datasize
             mrawsize += rawsize
         elif isinstance(rl, filelog.filelog):
             fcount += 1
             frevcount += len(rl)
             fsrcsize += datasize
             frawsize += rawsize
         else:
             error.ProgrammingError(b'unknown revlog type')
 
     if not revcount:
         return
 
     ui.write(
         _(
             b'migrating %d total revisions (%d in filelogs, %d in manifests, '
             b'%d in changelog)\n'
         )
         % (revcount, frevcount, mrevcount, crevcount)
     )
     ui.write(
         _(b'migrating %s in store; %s tracked data\n')
         % ((util.bytecount(srcsize), util.bytecount(srcrawsize)))
     )
 
     # Used to keep track of progress.
     progress = None
 
     def oncopiedrevision(rl, rev, node):
         progress.increment()
 
     sidedatacompanion = getsidedatacompanion(srcrepo, dstrepo)
 
     # Do the actual copying.
     # FUTURE this operation can be farmed off to worker processes.
     seen = set()
     for unencoded, encoded, size in alldatafiles:
         if unencoded.endswith(b'.d'):
             continue
 
         oldrl = _revlogfrompath(srcrepo, unencoded)
 
         if isinstance(oldrl, changelog.changelog) and b'c' not in seen:
             ui.write(
                 _(
                     b'finished migrating %d manifest revisions across %d '
                     b'manifests; change in size: %s\n'
                 )
                 % (mrevcount, mcount, util.bytecount(mdstsize - msrcsize))
             )
 
             ui.write(
                 _(
                     b'migrating changelog containing %d revisions '
                     b'(%s in store; %s tracked data)\n'
                 )
                 % (
                     crevcount,
                     util.bytecount(csrcsize),
                     util.bytecount(crawsize),
                 )
             )
             seen.add(b'c')
             progress = srcrepo.ui.makeprogress(
                 _(b'changelog revisions'), total=crevcount
             )
         elif isinstance(oldrl, manifest.manifestrevlog) and b'm' not in seen:
             ui.write(
                 _(
                     b'finished migrating %d filelog revisions across %d '
                     b'filelogs; change in size: %s\n'
                 )
                 % (frevcount, fcount, util.bytecount(fdstsize - fsrcsize))
             )
 
             ui.write(
                 _(
                     b'migrating %d manifests containing %d revisions '
                     b'(%s in store; %s tracked data)\n'
                 )
                 % (
                     mcount,
                     mrevcount,
                     util.bytecount(msrcsize),
                     util.bytecount(mrawsize),
                 )
             )
             seen.add(b'm')
             if progress:
                 progress.complete()
             progress = srcrepo.ui.makeprogress(
                 _(b'manifest revisions'), total=mrevcount
             )
         elif b'f' not in seen:
             ui.write(
                 _(
                     b'migrating %d filelogs containing %d revisions '
                     b'(%s in store; %s tracked data)\n'
                 )
                 % (
                     fcount,
                     frevcount,
                     util.bytecount(fsrcsize),
                     util.bytecount(frawsize),
                 )
             )
             seen.add(b'f')
             if progress:
                 progress.complete()
             progress = srcrepo.ui.makeprogress(
                 _(b'file revisions'), total=frevcount
             )
 
         if matchrevlog(revlogs, unencoded):
             ui.note(
                 _(b'cloning %d revisions from %s\n') % (len(oldrl), unencoded)
             )
             newrl = _revlogfrompath(dstrepo, unencoded)
             oldrl.clone(
                 tr,
                 newrl,
                 addrevisioncb=oncopiedrevision,
                 deltareuse=deltareuse,
                 forcedeltabothparents=forcedeltabothparents,
                 sidedatacompanion=sidedatacompanion,
             )
         else:
             msg = _(b'blindly copying %s containing %i revisions\n')
             ui.note(msg % (unencoded, len(oldrl)))
             _copyrevlog(tr, dstrepo, oldrl, unencoded)
 
             newrl = _revlogfrompath(dstrepo, unencoded)
 
         info = newrl.storageinfo(storedsize=True)
         datasize = info[b'storedsize'] or 0
 
         dstsize += datasize
 
         if isinstance(newrl, changelog.changelog):
             cdstsize += datasize
         elif isinstance(newrl, manifest.manifestrevlog):
             mdstsize += datasize
         else:
             fdstsize += datasize
 
     progress.complete()
 
     ui.write(
         _(
             b'finished migrating %d changelog revisions; change in size: '
             b'%s\n'
         )
         % (crevcount, util.bytecount(cdstsize - csrcsize))
     )
 
     ui.write(
         _(
             b'finished migrating %d total revisions; total change in store '
             b'size: %s\n'
         )
         % (revcount, util.bytecount(dstsize - srcsize))
     )
 
 
 def _filterstorefile(srcrepo, dstrepo, requirements, path, mode, st):
     """Determine whether to copy a store file during upgrade.
 
     This function is called when migrating store files from ``srcrepo`` to
     ``dstrepo`` as part of upgrading a repository.
 
     Args:
       srcrepo: repo we are copying from
       dstrepo: repo we are copying to
       requirements: set of requirements for ``dstrepo``
       path: store file being examined
       mode: the ``ST_MODE`` file type of ``path``
       st: ``stat`` data structure for ``path``
 
     Function should return ``True`` if the file is to be copied.
     """
     # Skip revlogs.
     if path.endswith((b'.i', b'.d')):
         return False
     # Skip transaction related files.
     if path.startswith(b'undo'):
         return False
     # Only copy regular files.
     if mode != stat.S_IFREG:
         return False
     # Skip other skipped files.
     if path in (b'lock', b'fncache'):
         return False
 
     return True
 
 
 def _finishdatamigration(ui, srcrepo, dstrepo, requirements):
     """Hook point for extensions to perform additional actions during upgrade.
 
     This function is called after revlogs and store files have been copied but
     before the new store is swapped into the original location.
     """
 
 
 def _upgraderepo(
     ui, srcrepo, dstrepo, requirements, actions, revlogs=UPGRADE_ALL_REVLOGS
 ):
     """Do the low-level work of upgrading a repository.
 
     The upgrade is effectively performed as a copy between a source
     repository and a temporary destination repository.
 
     The source repository is unmodified for as long as possible so the
     upgrade can abort at any time without causing loss of service for
     readers and without corrupting the source repository.
     """
     assert srcrepo.currentwlock()
     assert dstrepo.currentwlock()
 
     ui.write(
         _(
             b'(it is safe to interrupt this process any time before '
             b'data migration completes)\n'
         )
     )
 
     if b're-delta-all' in actions:
         deltareuse = revlog.revlog.DELTAREUSENEVER
     elif b're-delta-parent' in actions:
         deltareuse = revlog.revlog.DELTAREUSESAMEREVS
     elif b're-delta-multibase' in actions:
         deltareuse = revlog.revlog.DELTAREUSESAMEREVS
     elif b're-delta-fulladd' in actions:
         deltareuse = revlog.revlog.DELTAREUSEFULLADD
     else:
         deltareuse = revlog.revlog.DELTAREUSEALWAYS
 
     with dstrepo.transaction(b'upgrade') as tr:
         _clonerevlogs(
             ui,
             srcrepo,
             dstrepo,
             tr,
             deltareuse,
             b're-delta-multibase' in actions,
             revlogs=revlogs,
         )
 
     # Now copy other files in the store directory.
     # The sorted() makes execution deterministic.
     for p, kind, st in sorted(srcrepo.store.vfs.readdir(b'', stat=True)):
         if not _filterstorefile(srcrepo, dstrepo, requirements, p, kind, st):
             continue
 
         srcrepo.ui.write(_(b'copying %s\n') % p)
         src = srcrepo.store.rawvfs.join(p)
         dst = dstrepo.store.rawvfs.join(p)
         util.copyfile(src, dst, copystat=True)
 
     _finishdatamigration(ui, srcrepo, dstrepo, requirements)
 
     ui.write(_(b'data fully migrated to temporary repository\n'))
 
     backuppath = pycompat.mkdtemp(prefix=b'upgradebackup.', dir=srcrepo.path)
     backupvfs = vfsmod.vfs(backuppath)
 
     # Make a backup of requires file first, as it is the first to be modified.
     util.copyfile(srcrepo.vfs.join(b'requires'), backupvfs.join(b'requires'))
 
     # We install an arbitrary requirement that clients must not support
     # as a mechanism to lock out new clients during the data swap. This is
     # better than allowing a client to continue while the repository is in
     # an inconsistent state.
     ui.write(
         _(
             b'marking source repository as being upgraded; clients will be '
             b'unable to read from repository\n'
         )
     )
     scmutil.writerequires(
         srcrepo.vfs, srcrepo.requirements | {b'upgradeinprogress'}
     )
 
     ui.write(_(b'starting in-place swap of repository data\n'))
     ui.write(_(b'replaced files will be backed up at %s\n') % backuppath)
 
     # Now swap in the new store directory. Doing it as a rename should make
     # the operation nearly instantaneous and atomic (at least in well-behaved
     # environments).
     ui.write(_(b'replacing store...\n'))
     tstart = util.timer()
     util.rename(srcrepo.spath, backupvfs.join(b'store'))
     util.rename(dstrepo.spath, srcrepo.spath)
     elapsed = util.timer() - tstart
     ui.write(
         _(
             b'store replacement complete; repository was inconsistent for '
             b'%0.1fs\n'
         )
         % elapsed
     )
 
     # We first write the requirements file. Any new requirements will lock
     # out legacy clients.
     ui.write(
         _(
             b'finalizing requirements file and making repository readable '
             b'again\n'
         )
     )
     scmutil.writerequires(srcrepo.vfs, requirements)
 
     # The lock file from the old store won't be removed because nothing has a
     # reference to its new location. So clean it up manually. Alternatively, we
     # could update srcrepo.svfs and other variables to point to the new
     # location. This is simpler.
     backupvfs.unlink(b'store/lock')
 
     return backuppath
 
 
 def upgraderepo(
     ui,
     repo,
     run=False,
     optimize=None,
     backup=True,
     manifest=None,
     changelog=None,
 ):
     """Upgrade a repository in place."""
     if optimize is None:
         optimize = []
     optimize = set(legacy_opts_map.get(o, o) for o in optimize)
     repo = repo.unfiltered()
 
     revlogs = set(UPGRADE_ALL_REVLOGS)
     specentries = ((b'c', changelog), (b'm', manifest))
     specified = [(y, x) for (y, x) in specentries if x is not None]
     if specified:
         # we have some limitation on revlogs to be recloned
         if any(x for y, x in specified):
             revlogs = set()
             for r, enabled in specified:
                 if enabled:
                     if r == b'c':
                         revlogs.add(UPGRADE_CHANGELOG)
                     elif r == b'm':
                         revlogs.add(UPGRADE_MANIFEST)
         else:
             # none are enabled
             for r, __ in specified:
                 if r == b'c':
                     revlogs.discard(UPGRADE_CHANGELOG)
                 elif r == b'm':
                     revlogs.discard(UPGRADE_MANIFEST)
 
     # Ensure the repository can be upgraded.
     missingreqs = requiredsourcerequirements(repo) - repo.requirements
     if missingreqs:
         raise error.Abort(
             _(b'cannot upgrade repository; requirement missing: %s')
             % _(b', ').join(sorted(missingreqs))
         )
 
     blockedreqs = blocksourcerequirements(repo) & repo.requirements
     if blockedreqs:
         raise error.Abort(
             _(
                 b'cannot upgrade repository; unsupported source '
                 b'requirement: %s'
             )
             % _(b', ').join(sorted(blockedreqs))
         )
 
     # FUTURE there is potentially a need to control the wanted requirements via
     # command arguments or via an extension hook point.
     newreqs = localrepo.newreporequirements(
         repo.ui, localrepo.defaultcreateopts(repo.ui)
     )
     newreqs.update(preservedrequirements(repo))
 
     noremovereqs = (
         repo.requirements - newreqs - supportremovedrequirements(repo)
     )
     if noremovereqs:
         raise error.Abort(
             _(
                 b'cannot upgrade repository; requirement would be '
                 b'removed: %s'
             )
             % _(b', ').join(sorted(noremovereqs))
         )
 
     noaddreqs = newreqs - repo.requirements - allowednewrequirements(repo)
     if noaddreqs:
         raise error.Abort(
             _(
                 b'cannot upgrade repository; do not support adding '
                 b'requirement: %s'
             )
             % _(b', ').join(sorted(noaddreqs))
         )
 
     unsupportedreqs = newreqs - supporteddestrequirements(repo)
     if unsupportedreqs:
         raise error.Abort(
             _(
                 b'cannot upgrade repository; do not support '
                 b'destination requirement: %s'
             )
             % _(b', ').join(sorted(unsupportedreqs))
         )
 
     # Find and validate all improvements that can be made.
     alloptimizations = findoptimizations(repo)
 
     # Apply and Validate arguments.
     optimizations = []
     for o in alloptimizations:
         if o.name in optimize:
             optimizations.append(o)
             optimize.discard(o.name)
 
     if optimize:  # anything left is unknown
         raise error.Abort(
             _(b'unknown optimization action requested: %s')
             % b', '.join(sorted(optimize)),
             hint=_(b'run without arguments to see valid optimizations'),
         )
 
     deficiencies = finddeficiencies(repo)
     actions = determineactions(repo, deficiencies, repo.requirements, newreqs)
     actions.extend(
         o
         for o in sorted(optimizations)
         # determineactions could have added optimisation
         if o not in actions
     )
 
     removedreqs = repo.requirements - newreqs
     addedreqs = newreqs - repo.requirements
 
     if revlogs != UPGRADE_ALL_REVLOGS:
         incompatible = RECLONES_REQUIREMENTS & (removedreqs | addedreqs)
         if incompatible:
             msg = _(
                 b'ignoring revlogs selection flags, format requirements '
                 b'change: %s\n'
             )
             ui.warn(msg % b', '.join(sorted(incompatible)))
             revlogs = UPGRADE_ALL_REVLOGS
 
     def printrequirements():
         ui.write(_(b'requirements\n'))
         ui.write(
             _(b'   preserved: %s\n')
             % _(b', ').join(sorted(newreqs & repo.requirements))
         )
 
         if repo.requirements - newreqs:
             ui.write(
                 _(b'   removed: %s\n')
                 % _(b', ').join(sorted(repo.requirements - newreqs))
             )
 
         if newreqs - repo.requirements:
             ui.write(
                 _(b'   added: %s\n')
                 % _(b', ').join(sorted(newreqs - repo.requirements))
             )
 
         ui.write(b'\n')
 
     def printupgradeactions():
         for a in actions:
             ui.write(b'%s\n   %s\n\n' % (a.name, a.upgrademessage))
 
     if not run:
         fromconfig = []
         onlydefault = []
 
         for d in deficiencies:
             if d.fromconfig(repo):
                 fromconfig.append(d)
             elif d.default:
                 onlydefault.append(d)
 
         if fromconfig or onlydefault:
 
             if fromconfig:
                 ui.write(
                     _(
                         b'repository lacks features recommended by '
                         b'current config options:\n\n'
                     )
                 )
                 for i in fromconfig:
                     ui.write(b'%s\n   %s\n\n' % (i.name, i.description))
 
             if onlydefault:
                 ui.write(
                     _(
                         b'repository lacks features used by the default '
                         b'config options:\n\n'
                     )
                 )
                 for i in onlydefault:
                     ui.write(b'%s\n   %s\n\n' % (i.name, i.description))
 
             ui.write(b'\n')
         else:
             ui.write(
                 _(
                     b'(no feature deficiencies found in existing '
                     b'repository)\n'
                 )
             )
 
         ui.write(
             _(
                 b'performing an upgrade with "--run" will make the following '
                 b'changes:\n\n'
             )
         )
 
         printrequirements()
         printupgradeactions()
 
         unusedoptimize = [i for i in alloptimizations if i not in actions]
 
         if unusedoptimize:
             ui.write(
                 _(
                     b'additional optimizations are available by specifying '
                     b'"--optimize <name>":\n\n'
                 )
             )
             for i in unusedoptimize:
                 ui.write(_(b'%s\n   %s\n\n') % (i.name, i.description))
         return
 
     # Else we're in the run=true case.
     ui.write(_(b'upgrade will perform the following actions:\n\n'))
     printrequirements()
     printupgradeactions()
 
     upgradeactions = [a.name for a in actions]
 
     ui.write(_(b'beginning upgrade...\n'))
     with repo.wlock(), repo.lock():
         ui.write(_(b'repository locked and read-only\n'))
         # Our strategy for upgrading the repository is to create a new,
         # temporary repository, write data to it, then do a swap of the
         # data. There are less heavyweight ways to do this, but it is easier
         # to create a new repo object than to instantiate all the components
         # (like the store) separately.
         tmppath = pycompat.mkdtemp(prefix=b'upgrade.', dir=repo.path)
         backuppath = None
         try:
             ui.write(
                 _(
                     b'creating temporary repository to stage migrated '
                     b'data: %s\n'
                 )
                 % tmppath
             )
 
             # clone ui without using ui.copy because repo.ui is protected
             repoui = repo.ui.__class__(repo.ui)
             dstrepo = hg.repository(repoui, path=tmppath, create=True)
 
             with dstrepo.wlock(), dstrepo.lock():
                 backuppath = _upgraderepo(
                     ui, repo, dstrepo, newreqs, upgradeactions, revlogs=revlogs
                 )
             if not (backup or backuppath is None):
                 ui.write(_(b'removing old repository content%s\n') % backuppath)
                 repo.vfs.rmtree(backuppath, forcibly=True)
                 backuppath = None
 
         finally:
             ui.write(_(b'removing temporary repository %s\n') % tmppath)
             repo.vfs.rmtree(tmppath, forcibly=True)
 
             if backuppath:
                 ui.warn(
                     _(b'copy of old repository backed up at %s\n') % backuppath
                 )
                 ui.warn(
                     _(
                         b'the old repository will not be deleted; remove '
                         b'it to free up disk space once the upgraded '
                         b'repository is verified\n'
                     )
                 )

tests/test-copies-in-changeset.t

@@ -1,453 +1,540 b''
 #testcases extra sidedata
 
 #if extra
   $ cat >> $HGRCPATH << EOF
   > [experimental]
   > copies.write-to=changeset-only
   > copies.read-from=changeset-only
   > [alias]
   > changesetcopies = log -r . -T 'files: {files}
   >   {extras % "{ifcontains("files", key, "{key}: {value}\n")}"}
   >   {extras % "{ifcontains("copies", key, "{key}: {value}\n")}"}'
   > EOF
 #endif
 
 #if sidedata
   $ cat >> $HGRCPATH << EOF
   > [format]
   > exp-use-copies-side-data-changeset = yes
   > EOF
 #endif
 
   $ cat >> $HGRCPATH << EOF
   > [alias]
   > showcopies = log -r . -T '{file_copies % "{source} -> {name}\n"}'
   > [extensions]
   > rebase =
   > split =
   > EOF
 
 Check that copies are recorded correctly
 
   $ hg init repo
   $ cd repo
 #if sidedata
   $ hg debugformat -v
   format-variant    repo config default
   fncache:           yes    yes     yes
   dotencode:         yes    yes     yes
   generaldelta:      yes    yes     yes
   sparserevlog:      yes    yes     yes
   sidedata:          yes    yes      no
   copies-sdc:        yes    yes      no
   plain-cl-delta:    yes    yes     yes
   compression:       zlib   zlib    zlib
   compression-level: default default default
 #else
   $ hg debugformat -v
   format-variant    repo config default
   fncache:           yes    yes     yes
   dotencode:         yes    yes     yes
   generaldelta:      yes    yes     yes
   sparserevlog:      yes    yes     yes
   sidedata:           no     no      no
   copies-sdc:         no     no      no
   plain-cl-delta:    yes    yes     yes
   compression:       zlib   zlib    zlib
   compression-level: default default default
 #endif
   $ echo a > a
   $ hg add a
   $ hg ci -m initial
   $ hg cp a b
   $ hg cp a c
   $ hg cp a d
   $ hg ci -m 'copy a to b, c, and d'
 
 #if extra
 
   $ hg changesetcopies
   files: b c d
   filesadded: 0
   1
   2
   
   p1copies: 0\x00a (esc)
   1\x00a (esc)
   2\x00a (esc)
 #else
   $ hg debugsidedata -c -v -- -1
   4 sidedata entries
    entry-0010 size 11
     '0\x00a\n1\x00a\n2\x00a'
    entry-0011 size 0
     ''
    entry-0012 size 5
     '0\n1\n2'
    entry-0013 size 0
     ''
 #endif
 
   $ hg showcopies
   a -> b
   a -> c
   a -> d
 
 #if extra
 
   $ hg showcopies --config experimental.copies.read-from=compatibility
   a -> b
   a -> c
   a -> d
   $ hg showcopies --config experimental.copies.read-from=filelog-only
 
 #endif
 
 Check that renames are recorded correctly
 
   $ hg mv b b2
   $ hg ci -m 'rename b to b2'
 
 #if extra
 
   $ hg changesetcopies
   files: b b2
   filesadded: 1
   filesremoved: 0
   
   p1copies: 1\x00b (esc)
 
 #else
   $ hg debugsidedata -c -v -- -1
   4 sidedata entries
    entry-0010 size 3
     '1\x00b'
    entry-0011 size 0
     ''
    entry-0012 size 1
     '1'
    entry-0013 size 1
     '0'
 #endif
 
   $ hg showcopies
   b -> b2
 
 
 Rename onto existing file. This should get recorded in the changeset files list and in the extras,
 even though there is no filelog entry.
 
   $ hg cp b2 c --force
   $ hg st --copies
   M c
     b2
 
 #if extra
 
   $ hg debugindex c
      rev linkrev nodeid       p1           p2
        0       1 b789fdd96dc2 000000000000 000000000000
 
 #else
 
   $ hg debugindex c
      rev linkrev nodeid       p1           p2
        0       1 37d9b5d994ea 000000000000 000000000000
 
 #endif
 
 
   $ hg ci -m 'move b onto d'
 
 #if extra
 
   $ hg changesetcopies
   files: c
   
   p1copies: 0\x00b2 (esc)
 
 #else
   $ hg debugsidedata -c -v -- -1
   4 sidedata entries
    entry-0010 size 4
     '0\x00b2'
    entry-0011 size 0
     ''
    entry-0012 size 0
     ''
    entry-0013 size 0
     ''
 #endif
 
   $ hg showcopies
   b2 -> c
 
 #if extra
 
   $ hg debugindex c
      rev linkrev nodeid       p1           p2
        0       1 b789fdd96dc2 000000000000 000000000000
 
 #else
 
   $ hg debugindex c
      rev linkrev nodeid       p1           p2
        0       1 37d9b5d994ea 000000000000 000000000000
        1       3 029625640347 000000000000 000000000000
 
 #endif
 
 Create a merge commit with copying done during merge.
 
   $ hg co 0
   0 files updated, 0 files merged, 3 files removed, 0 files unresolved
   $ hg cp a e
   $ hg cp a f
   $ hg ci -m 'copy a to e and f'
   created new head
   $ hg merge 3
   3 files updated, 0 files merged, 0 files removed, 0 files unresolved
   (branch merge, don't forget to commit)
 File 'a' exists on both sides, so 'g' could be recorded as being from p1 or p2, but we currently
 always record it as being from p1
   $ hg cp a g
 File 'd' exists only in p2, so 'h' should be from p2
   $ hg cp d h
 File 'f' exists only in p1, so 'i' should be from p1
   $ hg cp f i
   $ hg ci -m 'merge'
 
 #if extra
 
   $ hg changesetcopies
   files: g h i
   filesadded: 0
   1
   2
   
   p1copies: 0\x00a (esc)
   2\x00f (esc)
   p2copies: 1\x00d (esc)
 
 #else
   $ hg debugsidedata -c -v -- -1
   4 sidedata entries
    entry-0010 size 7
     '0\x00a\n2\x00f'
    entry-0011 size 3
     '1\x00d'
    entry-0012 size 5
     '0\n1\n2'
    entry-0013 size 0
     ''
 #endif
 
   $ hg showcopies
   a -> g
   d -> h
   f -> i
 
 Test writing to both changeset and filelog
 
   $ hg cp a j
 #if extra
   $ hg ci -m 'copy a to j' --config experimental.copies.write-to=compatibility
   $ hg changesetcopies
   files: j
   filesadded: 0
   filesremoved: 
   
   p1copies: 0\x00a (esc)
   p2copies: 
 #else
   $ hg ci -m 'copy a to j'
   $ hg debugsidedata -c -v -- -1
   4 sidedata entries
    entry-0010 size 3
     '0\x00a'
    entry-0011 size 0
     ''
    entry-0012 size 1
     '0'
    entry-0013 size 0
     ''
 #endif
   $ hg debugdata j 0
   \x01 (esc)
   copy: a
   copyrev: b789fdd96dc2f3bd229c1dd8eedf0fc60e2b68e3
   \x01 (esc)
   a
   $ hg showcopies
   a -> j
   $ hg showcopies --config experimental.copies.read-from=compatibility
   a -> j
   $ hg showcopies --config experimental.copies.read-from=filelog-only
   a -> j
 Existing copy information in the changeset gets removed on amend and writing
 copy information on to the filelog
 #if extra
   $ hg ci --amend -m 'copy a to j, v2' \
   > --config experimental.copies.write-to=filelog-only
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/*-*-amend.hg (glob)
   $ hg changesetcopies
   files: j
   
 #else
   $ hg ci --amend -m 'copy a to j, v2'
   saved backup bundle to $TESTTMP/repo/.hg/strip-backup/*-*-amend.hg (glob)
   $ hg debugsidedata -c -v -- -1
   4 sidedata entries
    entry-0010 size 3
     '0\x00a'
    entry-0011 size 0
     ''
    entry-0012 size 1
     '0'
    entry-0013 size 0
     ''
 #endif
   $ hg showcopies --config experimental.copies.read-from=filelog-only
   a -> j
 The entries should be written to extras even if they're empty (so the client
 won't have to fall back to reading from filelogs)
   $ echo x >> j
 #if extra
   $ hg ci -m 'modify j' --config experimental.copies.write-to=compatibility
   $ hg changesetcopies
   files: j
   filesadded: 
   filesremoved: 
   
   p1copies: 
   p2copies: 
 #else
   $ hg ci -m 'modify j'
   $ hg debugsidedata -c -v -- -1
   4 sidedata entries
    entry-0010 size 0
     ''
    entry-0011 size 0
     ''
    entry-0012 size 0
     ''
    entry-0013 size 0
     ''
 #endif
 
 Test writing only to filelog
 
   $ hg cp a k
 #if extra
   $ hg ci -m 'copy a to k' --config experimental.copies.write-to=filelog-only
 
   $ hg changesetcopies
   files: k
   
 #else
   $ hg ci -m 'copy a to k'
   $ hg debugsidedata -c -v -- -1
   4 sidedata entries
    entry-0010 size 3
     '0\x00a'
    entry-0011 size 0
     ''
    entry-0012 size 1
     '0'
    entry-0013 size 0
     ''
 #endif
 
   $ hg debugdata k 0
   \x01 (esc)
   copy: a
   copyrev: b789fdd96dc2f3bd229c1dd8eedf0fc60e2b68e3
   \x01 (esc)
   a
 #if extra
   $ hg showcopies
 
   $ hg showcopies --config experimental.copies.read-from=compatibility
   a -> k
   $ hg showcopies --config experimental.copies.read-from=filelog-only
   a -> k
 #else
   $ hg showcopies
   a -> k
 #endif
 
   $ cd ..
 
 Test rebasing a commit with copy information
 
   $ hg init rebase-rename
   $ cd rebase-rename
   $ echo a > a
   $ hg ci -Aqm 'add a'
   $ echo a2 > a
   $ hg ci -m 'modify a'
   $ hg co -q 0
   $ hg mv a b
   $ hg ci -qm 'rename a to b'
   $ hg rebase -d 1 --config rebase.experimental.inmemory=yes
   rebasing 2:* "rename a to b" (tip) (glob)
   merging a and b to b
   saved backup bundle to $TESTTMP/rebase-rename/.hg/strip-backup/*-*-rebase.hg (glob)
   $ hg st --change . --copies
   A b
     a
   R a
   $ cd ..
 
 Test splitting a commit
 
   $ hg init split
   $ cd split
   $ echo a > a
   $ echo b > b
   $ hg ci -Aqm 'add a and b'
   $ echo a2 > a
   $ hg mv b c
   $ hg ci -m 'modify a, move b to c'
   $ hg --config ui.interactive=yes split <<EOF
   > y
   > y
   > n
   > y
   > EOF
   diff --git a/a b/a
   1 hunks, 1 lines changed
   examine changes to 'a'?
   (enter ? for help) [Ynesfdaq?] y
   
   @@ -1,1 +1,1 @@
   -a
   +a2
   record this change to 'a'?
   (enter ? for help) [Ynesfdaq?] y
   
   diff --git a/b b/c
   rename from b
   rename to c
   examine changes to 'b' and 'c'?
   (enter ? for help) [Ynesfdaq?] n
   
   created new head
   diff --git a/b b/c
   rename from b
   rename to c
   examine changes to 'b' and 'c'?
   (enter ? for help) [Ynesfdaq?] y
   
   saved backup bundle to $TESTTMP/split/.hg/strip-backup/*-*-split.hg (glob)
   $ cd ..
 
 Test committing half a rename
 
   $ hg init partial
   $ cd partial
   $ echo a > a
   $ hg ci -Aqm 'add a'
   $ hg mv a b
   $ hg ci -m 'remove a' a
+
+#if sidedata
+
+Test upgrading/downgrading to sidedata storage
+==============================================
+
+downgrading (keeping some sidedata)
+
+  $ hg debugformat -v
+  format-variant    repo config default
+  fncache:           yes    yes     yes
+  dotencode:         yes    yes     yes
+  generaldelta:      yes    yes     yes
+  sparserevlog:      yes    yes     yes
+  sidedata:          yes    yes      no
+  copies-sdc:        yes    yes      no
+  plain-cl-delta:    yes    yes     yes
+  compression:       zlib   zlib    zlib
+  compression-level: default default default
+  $ hg debugsidedata -c -- 0
+  4 sidedata entries
+   entry-0010 size 0
+   entry-0011 size 0
+   entry-0012 size 1
+   entry-0013 size 0
+  $ hg debugsidedata -c -- 1
+  4 sidedata entries
+   entry-0010 size 0
+   entry-0011 size 0
+   entry-0012 size 0
+   entry-0013 size 1
+  $ hg debugsidedata -m -- 0
+  $ cat << EOF > .hg/hgrc
+  > [format]
+  > use-side-data = yes
+  > exp-use-copies-side-data-changeset = no
+  > EOF
+  $ hg debugupgraderepo --run --quiet --no-backup > /dev/null
+  $ hg debugformat -v
+  format-variant    repo config default
+  fncache:           yes    yes     yes
+  dotencode:         yes    yes     yes
+  generaldelta:      yes    yes     yes
+  sparserevlog:      yes    yes     yes
+  sidedata:          yes    yes      no
+  copies-sdc:         no     no      no
+  plain-cl-delta:    yes    yes     yes
+  compression:       zlib   zlib    zlib
+  compression-level: default default default
+  $ hg debugsidedata -c -- 0
+  $ hg debugsidedata -c -- 1
+  $ hg debugsidedata -m -- 0
+
+upgrading
+
+  $ cat << EOF > .hg/hgrc
+  > [format]
+  > exp-use-copies-side-data-changeset = yes
+  > EOF
+  $ hg debugupgraderepo --run --quiet --no-backup > /dev/null
+  $ hg debugformat -v
+  format-variant    repo config default
+  fncache:           yes    yes     yes
+  dotencode:         yes    yes     yes
+  generaldelta:      yes    yes     yes
+  sparserevlog:      yes    yes     yes
+  sidedata:          yes    yes      no
+  copies-sdc:        yes    yes      no
+  plain-cl-delta:    yes    yes     yes
+  compression:       zlib   zlib    zlib
+  compression-level: default default default
+  $ hg debugsidedata -c -- 0
+  4 sidedata entries
+   entry-0010 size 0
+   entry-0011 size 0
+   entry-0012 size 1
+   entry-0013 size 0
+  $ hg debugsidedata -c -- 1
+  4 sidedata entries
+   entry-0010 size 0
+   entry-0011 size 0
+   entry-0012 size 0
+   entry-0013 size 1
+  $ hg debugsidedata -m -- 0
+
+#endif
+
   $ cd ..