mercurial/copies.py

43076:2372284d9457

def _dirstatecopies(repo, match=None):
    ds = repo.dirstate
    c = ds.copies().copy()
    for k in list(c):
        if ds[k] not in 'anm' or (match and not match(k)):
            del c[k]
    return c


def _computeforwardmissing(a, b, match=None):

    return mb.filesnotin(ma, match=match)


def usechangesetcentricalgo(repo):
    """Checks if we should use changeset-centric copy algorithms"""
    readfrom = repo.ui.config('experimental', 'copies.read-from')
    changesetsource = ('changeset-only', 'compatibility')
    return readfrom in changesetsource


def _committedforwardcopies(a, b, base, match):
    """Like _forwardcopies(), but b.rev() cannot be None (working copy)"""

    repo = a._repo

    if usechangesetcentricalgo(repo):
        return _changesetforwardcopies(a, b, match)

    debug = repo.ui.debugflag and repo.ui.configbool('devel', 'debug.copies')
    dbg = repo.ui.debug
    if debug:
        dbg('debug.copies:    looking into rename from %s to %s\n' % (a, b))
    limit = _findlimit(repo, a, b)
    if debug:
        dbg('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

    missing = _computeforwardmissing(a, b, match=forwardmissingmatch)

    ancestrycontext = a._repo.changelog.ancestors([b.rev()], inclusive=True)

    if debug:
        dbg('debug.copies:      missing files to search: %d\n' % len(missing))

    for f in sorted(missing):
        if debug:
            dbg('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('debug.copies:          rename of: %s\n' % opath)
            cm[f] = opath
        if debug:
            dbg(
                'debug.copies:          time: %f seconds\n'
                % (util.timer() - start)
            )
    return cm

        copies = _committedforwardcopies(a, b, base, match)
    return copies


def _backwardrenames(a, b, match):
    if a._repo.ui.config('experimental', 'copytrace') == '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.

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('devel', 'debug.copies')
    if debug:
        repo.ui.debug('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('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('debug.copies: search mode: backward\n')
        copies = _backwardrenames(x, y, match=match)
    else:
        if debug:
            repo.ui.debug('debug.copies: search mode: combined\n')
        base = None
        if a.rev() != node.nullrev:
            base = x
        copies = _chain(
            _backwardrenames(x, a, match=match),

    # 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('experimental', '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 {}, {}, {}, {}, {}

        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 == '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)

    """
    if c1.rev() is None:
        c1 = c1.p1()
    if c1.mutable() and base.mutable():
        sourcecommitlimit = repo.ui.configint(
            'experimental', 'copytrace.sourcecommitlimit'
        )
        commits = len(repo.revs('%d::%d', base.rev(), c1.rev()))
        return commits < sourcecommitlimit
    return False


def _checksinglesidecopies(

    addedinm1 = m1.filesnotin(mb, repo.narrowmatch())
    addedinm2 = m2.filesnotin(mb, repo.narrowmatch())
    u1 = sorted(addedinm1 - addedinm2)
    u2 = sorted(addedinm2 - addedinm1)

    header = "  unmatched files in %s"
    if u1:
        repo.ui.debug("%s:\n   %s\n" % (header % 'local', "\n   ".join(u1)))
    if u2:
        repo.ui.debug("%s:\n   %s\n" % (header % 'other', "\n   ".join(u2)))

    fullcopy = copies1.copy()
    fullcopy.update(copies2)
    if not fullcopy:
        return copy, {}, diverge, renamedelete, {}

    if repo.ui.debugflag:
        repo.ui.debug(
            "  all copies found (* = to merge, ! = divergent, "
            "% = renamed and deleted):\n"
        )
        for f in sorted(fullcopy):
            note = ""
            if f in copy:
                note += "*"
            if f in divergeset:
                note += "!"
            if f in renamedeleteset:
                note += "%"
            repo.ui.debug(
                "   src: '%s' -> dst: '%s' %s\n" % (fullcopy[f], f, note)
            )
    del divergeset

    repo.ui.debug("  checking for directory renames\n")

    # generate a directory move map
    d1, d2 = c1.dirs(), c2.dirs()
    invalid = set()
    dirmove = {}

    del d1, d2, invalid

    if not dirmove:
        return copy, {}, diverge, renamedelete, {}

    dirmove = {k + "/": v + "/" for k, v in dirmove.iteritems()}

    for d in dirmove:
        repo.ui.debug(
            "   discovered dir src: '%s' -> dst: '%s'\n" % (d, dirmove[d])
        )

    movewithdir = {}
    # check unaccounted nonoverlapping files against directory moves
    for f in u1 + u2:

                    # 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(
                            ("   pending file src: '%s' -> " "dst: '%s'\n")
                            % (f, df)
                        )
                    break

    return copy, movewithdir, diverge, renamedelete, dirmove

    copies = {}

    changedfiles = set()
    m1 = c1.manifest()
    if not repo.revs('%d::%d', base.rev(), c2.rev()):
        # If base is not in c2 branch, we switch to fullcopytracing
        repo.ui.debug(
            "switching to full copytracing as base is not "
            "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("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)

            # 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(
                'experimental', 'copytrace.movecandidateslimit'
            )

            if len(movecandidates) > maxcandidates:
                repo.ui.status(
                    _(
                        "skipping copytracing for '%s', more "
                        "candidates than the limit: %d\n"
                    )
                    % (f, len(movecandidates))
                )
                continue

    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('experimental', 'copytrace')
    bctrace = stringutil.parsebool(ctraceconfig)
    if skiprev is not None and (
        ctraceconfig == '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).

43077:687b865b95ad

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):

    return mb.filesnotin(ma, match=match)


def usechangesetcentricalgo(repo):
    """Checks if we should use changeset-centric copy algorithms"""
    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)"""

    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

    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

        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.

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),

    # 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 {}, {}, {}, {}, {}

        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)

    """
    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(

    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 = {}

    del d1, d2, invalid

    if not dirmove:
        return copy, {}, diverge, renamedelete, {}

    dirmove = {k + b"/": v + b"/" for k, v in dirmove.iteritems()}

    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:

                    # 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' -> " b"dst: '%s'\n")
                            % (f, df)
                        )
                    break

    return copy, movewithdir, diverge, renamedelete, dirmove

    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)

            # 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

    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).