comparison mercurial/manifest.py @ 47043:12450fbea288

manifests: push down expected node length into the parser

This strictly enforces the node length in the manifest lines according
to what the repository expects. One test case moves large hash testing
into the non-treemanifest part as treemanifests don't provide an
interface for overriding just the node length for now.

Differential Revision: https://phab.mercurial-scm.org/D10533

47042:c5e1cc0b4c77

# Allow tests to more easily test the alternate path in manifestdict.fastdelta()
FASTDELTA_TEXTDIFF_THRESHOLD = 1000


def _parse(data):
    # This method does a little bit of excessive-looking
    # precondition checking. This is so that the behavior of this
    # class exactly matches its C counterpart to try and help
    # prevent surprise breakage for anyone that develops against
    # the pure version.

        if flags in _manifestflags:
            n = n[:-1]
            nl -= 1
        else:
            flags = b''
        if nl not in (40, 64):
            raise ValueError(b'Invalid manifest line')

        yield f, bin(n), flags

        if flags in _manifestflags:
            hlen = nlpos - zeropos - 2
        else:
            hlen = nlpos - zeropos - 1
            flags = b''
        if hlen not in (40, 64):
            raise error.StorageError(b'Invalid manifest line')
        hashval = unhexlify(
            data, self.lm.extrainfo[self.pos], zeropos + 1, hlen
        )
        self.pos += 1

    modified since the manifest was created or compacted.
    """

    def __init__(
        self,
        data,
        positions=None,
        extrainfo=None,
        extradata=None,
        hasremovals=False,
    ):
        if positions is None:
            self.positions = self.findlines(data)
            self.extrainfo = [0] * len(self.positions)
            self.data = data
            self.extradata = []

        flags = data[nlpos - 1 : nlpos]
        if flags in _manifestflags:
            hlen -= 1
        else:
            flags = b''
        if hlen not in (40, 64):
            raise error.StorageError(b'Invalid manifest line')
        hashval = unhexlify(data, self.extrainfo[needle], zeropos + 1, hlen)
        return (hashval, flags)

    def __delitem__(self, key):

            )

    def copy(self):
        # XXX call _compact like in C?
        return _lazymanifest(
            self.data,
            self.positions,
            self.extrainfo,
            self.extradata,
            self.hasremovals,

    def __len__(self):
        return len(self.positions)

    def filtercopy(self, filterfn):
        # XXX should be optimized
        c = _lazymanifest(b'')
        for f, n, fl in self.iterentries():
            if filterfn(f):
                c[f] = n, fl
        return c

    pass


@interfaceutil.implementer(repository.imanifestdict)
class manifestdict(object):
    def __init__(self, data=b''):
        self._lm = _lazymanifest(data)

    def __getitem__(self, key):
        return self._lm[key][0]

    def find(self, key):

        '''generate a new manifest filtered by the match argument'''
        if match.always():
            return self.copy()

        if self._filesfastpath(match):
            m = manifestdict()
            lm = self._lm
            for fn in match.files():
                if fn in lm:
                    m._lm[fn] = lm[fn]
            return m

        m = manifestdict()
        m._lm = self._lm.filtercopy(match)
        return m

    def diff(self, m2, match=None, clean=False):
        """Finds changes between the current manifest and m2.

            return self._lm[key][1]
        except KeyError:
            return b''

    def copy(self):
        c = manifestdict()
        c._lm = self._lm.copy()
        return c

    def items(self):
        return (x[:2] for x in self._lm.iterentries())

class treemanifest(object):
    def __init__(self, nodeconstants, dir=b'', text=b''):
        self._dir = dir
        self.nodeconstants = nodeconstants
        self._node = self.nodeconstants.nullid
        self._loadfunc = _noop
        self._copyfunc = _noop
        self._dirty = False
        self._dirs = {}
        self._lazydirs = {}

    def unmodifiedsince(self, m2):
        return not self._dirty and not m2._dirty and self._node == m2._node

    def parse(self, text, readsubtree):
        selflazy = self._lazydirs
        for f, n, fl in _parse(text):
            if fl == b't':
                f = f + b'/'
                # False below means "doesn't need to be copied" and can use the
                # cached value from readsubtree directly.
                selflazy[f] = (n, readsubtree, False)

@interfaceutil.implementer(repository.imanifestrevisionwritable)
class memmanifestctx(object):
    def __init__(self, manifestlog):
        self._manifestlog = manifestlog
        self._manifestdict = manifestdict()

    def _storage(self):
        return self._manifestlog.getstorage(b'')

    def copy(self):

    def parents(self):
        return self._storage().parents(self._node)

    def read(self):
        if self._data is None:
            if self._node == self._manifestlog.nodeconstants.nullid:
                self._data = manifestdict()
            else:
                store = self._storage()
                if self._node in store.fulltextcache:
                    text = pycompat.bytestr(store.fulltextcache[self._node])
                else:
                    text = store.revision(self._node)
                    arraytext = bytearray(text)
                    store.fulltextcache[self._node] = arraytext
                self._data = manifestdict(text)
        return self._data

    def readfast(self, shallow=False):
        """Calls either readdelta or read, based on which would be less work.
        readdelta is called if the delta is against the p1, and therefore can be

        Changing the value of `shallow` has no effect on flat manifests.
        """
        store = self._storage()
        r = store.rev(self._node)
        d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
        return manifestdict(d)

    def find(self, key):
        return self.read().find(key)

        """
        store = self._storage()
        if shallow:
            r = store.rev(self._node)
            d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
            return manifestdict(d)
        else:
            # Need to perform a slow delta
            r0 = store.deltaparent(store.rev(self._node))
            m0 = self._manifestlog.get(self._dir, store.node(r0)).read()
            m1 = self.read()

        deltaparent = store.deltaparent(r)
        if deltaparent != nullrev and deltaparent in store.parentrevs(r):
            return self.readdelta(shallow=shallow)

        if shallow:
            return manifestdict(store.revision(self._node))
        else:
            return self.read()

    def find(self, key):
        return self.read().find(key)

47043:12450fbea288

# Allow tests to more easily test the alternate path in manifestdict.fastdelta()
FASTDELTA_TEXTDIFF_THRESHOLD = 1000


def _parse(nodelen, data):
    # This method does a little bit of excessive-looking
    # precondition checking. This is so that the behavior of this
    # class exactly matches its C counterpart to try and help
    # prevent surprise breakage for anyone that develops against
    # the pure version.

        if flags in _manifestflags:
            n = n[:-1]
            nl -= 1
        else:
            flags = b''
        if nl != 2 * nodelen:
            raise ValueError(b'Invalid manifest line')

        yield f, bin(n), flags

        if flags in _manifestflags:
            hlen = nlpos - zeropos - 2
        else:
            hlen = nlpos - zeropos - 1
            flags = b''
        if hlen != 2 * self.lm._nodelen:
            raise error.StorageError(b'Invalid manifest line')
        hashval = unhexlify(
            data, self.lm.extrainfo[self.pos], zeropos + 1, hlen
        )
        self.pos += 1

    modified since the manifest was created or compacted.
    """

    def __init__(
        self,
        nodelen,
        data,
        positions=None,
        extrainfo=None,
        extradata=None,
        hasremovals=False,
    ):
        self._nodelen = nodelen
        if positions is None:
            self.positions = self.findlines(data)
            self.extrainfo = [0] * len(self.positions)
            self.data = data
            self.extradata = []

        flags = data[nlpos - 1 : nlpos]
        if flags in _manifestflags:
            hlen -= 1
        else:
            flags = b''
        if hlen != 2 * self._nodelen:
            raise error.StorageError(b'Invalid manifest line')
        hashval = unhexlify(data, self.extrainfo[needle], zeropos + 1, hlen)
        return (hashval, flags)

    def __delitem__(self, key):

            )

    def copy(self):
        # XXX call _compact like in C?
        return _lazymanifest(
            self._nodelen,
            self.data,
            self.positions,
            self.extrainfo,
            self.extradata,
            self.hasremovals,

    def __len__(self):
        return len(self.positions)

    def filtercopy(self, filterfn):
        # XXX should be optimized
        c = _lazymanifest(self._nodelen, b'')
        for f, n, fl in self.iterentries():
            if filterfn(f):
                c[f] = n, fl
        return c

    pass


@interfaceutil.implementer(repository.imanifestdict)
class manifestdict(object):
    def __init__(self, nodelen, data=b''):
        self._nodelen = nodelen
        self._lm = _lazymanifest(nodelen, data)

    def __getitem__(self, key):
        return self._lm[key][0]

    def find(self, key):

        '''generate a new manifest filtered by the match argument'''
        if match.always():
            return self.copy()

        if self._filesfastpath(match):
            m = manifestdict(self._nodelen)
            lm = self._lm
            for fn in match.files():
                if fn in lm:
                    m._lm[fn] = lm[fn]
            return m

        m = manifestdict(self._nodelen)
        m._lm = self._lm.filtercopy(match)
        return m

    def diff(self, m2, match=None, clean=False):
        """Finds changes between the current manifest and m2.

            return self._lm[key][1]
        except KeyError:
            return b''

    def copy(self):
        c = manifestdict(self._nodelen)
        c._lm = self._lm.copy()
        return c

    def items(self):
        return (x[:2] for x in self._lm.iterentries())

class treemanifest(object):
    def __init__(self, nodeconstants, dir=b'', text=b''):
        self._dir = dir
        self.nodeconstants = nodeconstants
        self._node = self.nodeconstants.nullid
        self._nodelen = self.nodeconstants.nodelen
        self._loadfunc = _noop
        self._copyfunc = _noop
        self._dirty = False
        self._dirs = {}
        self._lazydirs = {}

    def unmodifiedsince(self, m2):
        return not self._dirty and not m2._dirty and self._node == m2._node

    def parse(self, text, readsubtree):
        selflazy = self._lazydirs
        for f, n, fl in _parse(self._nodelen, text):
            if fl == b't':
                f = f + b'/'
                # False below means "doesn't need to be copied" and can use the
                # cached value from readsubtree directly.
                selflazy[f] = (n, readsubtree, False)

@interfaceutil.implementer(repository.imanifestrevisionwritable)
class memmanifestctx(object):
    def __init__(self, manifestlog):
        self._manifestlog = manifestlog
        self._manifestdict = manifestdict(manifestlog.nodeconstants.nodelen)

    def _storage(self):
        return self._manifestlog.getstorage(b'')

    def copy(self):

    def parents(self):
        return self._storage().parents(self._node)

    def read(self):
        if self._data is None:
            nc = self._manifestlog.nodeconstants
            if self._node == nc.nullid:
                self._data = manifestdict(nc.nodelen)
            else:
                store = self._storage()
                if self._node in store.fulltextcache:
                    text = pycompat.bytestr(store.fulltextcache[self._node])
                else:
                    text = store.revision(self._node)
                    arraytext = bytearray(text)
                    store.fulltextcache[self._node] = arraytext
                self._data = manifestdict(nc.nodelen, text)
        return self._data

    def readfast(self, shallow=False):
        """Calls either readdelta or read, based on which would be less work.
        readdelta is called if the delta is against the p1, and therefore can be

        Changing the value of `shallow` has no effect on flat manifests.
        """
        store = self._storage()
        r = store.rev(self._node)
        d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
        return manifestdict(store.nodeconstants.nodelen, d)

    def find(self, key):
        return self.read().find(key)

        """
        store = self._storage()
        if shallow:
            r = store.rev(self._node)
            d = mdiff.patchtext(store.revdiff(store.deltaparent(r), r))
            return manifestdict(store.nodeconstants.nodelen, d)
        else:
            # Need to perform a slow delta
            r0 = store.deltaparent(store.rev(self._node))
            m0 = self._manifestlog.get(self._dir, store.node(r0)).read()
            m1 = self.read()

        deltaparent = store.deltaparent(r)
        if deltaparent != nullrev and deltaparent in store.parentrevs(r):
            return self.readdelta(shallow=shallow)

        if shallow:
            return manifestdict(
                store.nodeconstants.nodelen, store.revision(self._node)
            )
        else:
            return self.read()

    def find(self, key):
        return self.read().find(key)