comparison mercurial/dirstatemap.py @ 48223:b4f83c9e7905

dirstate-v2: Add support when Rust is not enabled

This wires into `dirstatemap` the parser and serializer added in previous
changesets. The memory representation is still the same, with a flat `dict`
for `DirstateItem`s and another one for copy sources. Serialization always
creates a new dirstate-v2 data file and does not support (when Rust is not
enabled) appending to an existing one, since we don’t keep track of which
tree nodes are new or modified. Instead the tree is reconstructed during
serialization.

Differential Revision: https://phab.mercurial-scm.org/D11520

48222:7e78c72ee3ea

    - `dirfoldmap` is a dict mapping normalized directory names to the
      denormalized form that they appear as in the dirstate.
    """

    def __init__(self, ui, opener, root, nodeconstants, use_dirstate_v2):
        super(dirstatemap, self).__init__(
            ui, opener, root, nodeconstants, use_dirstate_v2
        )
        if self._use_dirstate_v2:
            msg = "Dirstate V2 not supportedi"
            msg += "(should have detected unsupported requirement)"
            raise error.ProgrammingError(msg)

    ### Core data storage and access

    @propertycache
    def _map(self):
        self._map = {}

        # ignore HG_PENDING because identity is used only for writing
        self.identity = util.filestat.frompath(
            self._opener.join(self._filename)
        )

        try:
            fp = self._opendirstatefile()
            try:
                st = fp.read()
            finally:
                fp.close()
        except IOError as err:
            if err.errno != errno.ENOENT:
                raise
            return
        if not st:
            return

        if util.safehasattr(parsers, b'dict_new_presized'):
            # Make an estimate of the number of files in the dirstate based on
            # its size. This trades wasting some memory for avoiding costly
            # resizes. Each entry have a prefix of 17 bytes followed by one or
            # two path names. Studies on various large-scale real-world repositories

        # Depending on when in the process's lifetime the dirstate is parsed,
        # this can get very expensive. As a workaround, disable GC while
        # parsing the dirstate.
        #
        # (we cannot decorate the function directly since it is in a C module)
        parse_dirstate = util.nogc(parsers.parse_dirstate)
        p = parse_dirstate(self._map, self.copymap, st)
        if not self._dirtyparents:
            self.setparents(*p)

        # Avoid excess attribute lookups by fast pathing certain checks
        self.__contains__ = self._map.__contains__
        self.__getitem__ = self._map.__getitem__
        self.get = self._map.get

    def write(self, _tr, st, now):
        d = parsers.pack_dirstate(self._map, self.copymap, self.parents(), now)
        st.write(d)
        st.close()
        self._dirtyparents = False

    @propertycache
    def identity(self):
        self._map

48223:b4f83c9e7905

    - `dirfoldmap` is a dict mapping normalized directory names to the
      denormalized form that they appear as in the dirstate.
    """

    ### Core data storage and access

    @propertycache
    def _map(self):
        self._map = {}

        # ignore HG_PENDING because identity is used only for writing
        self.identity = util.filestat.frompath(
            self._opener.join(self._filename)
        )

        if self._use_dirstate_v2:
            if not self.docket.uuid:
                return
            st = self._opener.read(self.docket.data_filename())
        else:
            st = self._readdirstatefile()

        if not st:
            return

        # TODO: adjust this estimate for dirstate-v2
        if util.safehasattr(parsers, b'dict_new_presized'):
            # Make an estimate of the number of files in the dirstate based on
            # its size. This trades wasting some memory for avoiding costly
            # resizes. Each entry have a prefix of 17 bytes followed by one or
            # two path names. Studies on various large-scale real-world repositories

        # Depending on when in the process's lifetime the dirstate is parsed,
        # this can get very expensive. As a workaround, disable GC while
        # parsing the dirstate.
        #
        # (we cannot decorate the function directly since it is in a C module)
        if self._use_dirstate_v2:
            p = self.docket.parents
            meta = self.docket.tree_metadata
            parse_dirstate = util.nogc(v2.parse_dirstate)
            parse_dirstate(self._map, self.copymap, st, meta)
        else:
            parse_dirstate = util.nogc(parsers.parse_dirstate)
            p = parse_dirstate(self._map, self.copymap, st)
        if not self._dirtyparents:
            self.setparents(*p)

        # Avoid excess attribute lookups by fast pathing certain checks
        self.__contains__ = self._map.__contains__
        self.__getitem__ = self._map.__getitem__
        self.get = self._map.get

    def write(self, tr, st, now):
        if self._use_dirstate_v2:
            packed, meta = v2.pack_dirstate(self._map, self.copymap, now)
            self.write_v2_no_append(tr, st, meta, packed)
        else:
            packed = parsers.pack_dirstate(
                self._map, self.copymap, self.parents(), now
            )
            st.write(packed)
            st.close()
        self._dirtyparents = False

    @propertycache
    def identity(self):
        self._map