# simplestorerepo.py - Extension that swaps in alternate repository storage.

#

# Copyright 2018 Gregory Szorc <gregory.szorc@gmail.com>

#

# This software may be used and distributed according to the terms of the

# GNU General Public License version 2 or any later version.

# To use this with the test suite:

#

#   $ HGREPOFEATURES="simplestore" ./run-tests.py \

#       --extra-config-opt extensions.simplestore=`pwd`/simplestorerepo.py

from __future__ import absolute_import

import stat

from mercurial.i18n import _

from mercurial.node import (

    bin,

    hex,

    nullid,

    nullrev,

)

from mercurial.thirdparty import (

    cbor,

)

from mercurial import (

    ancestor,

    bundlerepo,

    error,

    extensions,

    filelog,

    localrepo,

    mdiff,

    pycompat,

    revlog,

    store,

    verify,

)

# Note for extension authors: ONLY specify testedwith = 'ships-with-hg-core' for

# extensions which SHIP WITH MERCURIAL. Non-mainline extensions should

# be specifying the version(s) of Mercurial they are tested with, or

# leave the attribute unspecified.

testedwith = 'ships-with-hg-core'

REQUIREMENT = 'testonly-simplestore'

def validatenode(node):

    if isinstance(node, int):

        raise ValueError('expected node; got int')

    if len(node) != 20:

        raise ValueError('expected 20 byte node')

def validaterev(rev):

    if not isinstance(rev, int):

        raise ValueError('expected int')

class filestorage(object):

    """Implements storage for a tracked path.

    Data is stored in the VFS in a directory corresponding to the tracked

    path.

    Index data is stored in an ``index`` file using CBOR.

    Fulltext data is stored in files having names of the node.

    """

    def __init__(self, svfs, path):

        self._svfs = svfs

        self._path = path

        self._storepath = b'/'.join([b'data', path])

        self._indexpath = b'/'.join([self._storepath, b'index'])

        indexdata = self._svfs.tryread(self._indexpath)

        if indexdata:

            indexdata = cbor.loads(indexdata)

        self._indexdata = indexdata or []

        self._indexbynode = {}

        self._indexbyrev = {}

        self.index = []

        self._refreshindex()

        # This is used by changegroup code :/

        self._generaldelta = True

        self.storedeltachains = False

        self.version = 1

    def _refreshindex(self):

        self._indexbynode.clear()

        self._indexbyrev.clear()

        self.index = []

        for i, entry in enumerate(self._indexdata):

            self._indexbynode[entry[b'node']] = entry

            self._indexbyrev[i] = entry

        self._indexbynode[nullid] = {

            b'node': nullid,

            b'p1': nullid,

            b'p2': nullid,

            b'linkrev': nullrev,

            b'flags': 0,

        }

        self._indexbyrev[nullrev] = {

            b'node': nullid,

            b'p1': nullid,

            b'p2': nullid,

            b'linkrev': nullrev,

            b'flags': 0,

        }

        for i, entry in enumerate(self._indexdata):

            p1rev, p2rev = self.parentrevs(self.rev(entry[b'node']))

            # start, length, rawsize, chainbase, linkrev, p1, p2, node

            self.index.append((0, 0, 0, -1, entry[b'linkrev'], p1rev, p2rev,

                               entry[b'node']))

        self.index.append((0, 0, 0, -1, -1, -1, -1, nullid))

    def __len__(self):

        return len(self._indexdata)

    def __iter__(self):

        return iter(range(len(self)))

    def revs(self, start=0, stop=None):

        step = 1

        if stop is not None:

            if start > stop:

                step = -1

            stop += step

        else:

            stop = len(self)

        return range(start, stop, step)

    def parents(self, node):

        validatenode(node)

        if node not in self._indexbynode:

            raise KeyError('unknown node')

        entry = self._indexbynode[node]

        return entry[b'p1'], entry[b'p2']

    def parentrevs(self, rev):

        p1, p2 = self.parents(self._indexbyrev[rev][b'node'])

        return self.rev(p1), self.rev(p2)

    def rev(self, node):

        validatenode(node)

        try:

            self._indexbynode[node]

        except KeyError:

            raise error.LookupError(node, self._indexpath, _('no node'))

        for rev, entry in self._indexbyrev.items():

            if entry[b'node'] == node:

                return rev

        raise error.ProgrammingError('this should not occur')

    def node(self, rev):

        validaterev(rev)

        return self._indexbyrev[rev][b'node']

    def lookup(self, node):

        if isinstance(node, int):

            return self.node(node)

        if len(node) == 20:

            self.rev(node)

            return node

        try:

            rev = int(node)

            if '%d' % rev != node:

                raise ValueError

            if rev < 0:

                rev = len(self) + rev

            if rev < 0 or rev >= len(self):

                raise ValueError

            return self.node(rev)

        except (ValueError, OverflowError):

            pass

        if len(node) == 40:

            try:

                rawnode = bin(node)

                self.rev(rawnode)

                return rawnode

            except TypeError:

                pass

        raise error.LookupError(node, self._path, _('invalid lookup input'))

    def linkrev(self, rev):

        validaterev(rev)

        return self._indexbyrev[rev][b'linkrev']

    def flags(self, rev):

        validaterev(rev)

        return self._indexbyrev[rev][b'flags']

    def deltaparent(self, rev):

        validaterev(rev)

        p1node = self.parents(self.node(rev))[0]

        return self.rev(p1node)

    def candelta(self, baserev, rev):

        validaterev(baserev)

        validaterev(rev)

        if ((self.flags(baserev) & revlog.REVIDX_RAWTEXT_CHANGING_FLAGS)

            or (self.flags(rev) & revlog.REVIDX_RAWTEXT_CHANGING_FLAGS)):

            return False

        return True

    def rawsize(self, rev):

        validaterev(rev)

        node = self.node(rev)

        return len(self.revision(node, raw=True))

    def _processflags(self, text, flags, operation, raw=False):

        if flags == 0:

            return text, True

        validatehash = True

        # Depending on the operation (read or write), the order might be

        # reversed due to non-commutative transforms.

        orderedflags = revlog.REVIDX_FLAGS_ORDER

        if operation == 'write':

            orderedflags = reversed(orderedflags)

        for flag in orderedflags:

            # If a flagprocessor has been registered for a known flag, apply the

            # related operation transform and update result tuple.

            if flag & flags:

                vhash = True

                if flag not in revlog._flagprocessors:

                    message = _("missing processor for flag '%#x'") % (flag)

                    raise revlog.RevlogError(message)

                processor = revlog._flagprocessors[flag]

                if processor is not None:

                    readtransform, writetransform, rawtransform = processor

                    if raw:

                        vhash = rawtransform(self, text)

                    elif operation == 'read':

                        text, vhash = readtransform(self, text)

                    else:  # write operation

                        text, vhash = writetransform(self, text)

                validatehash = validatehash and vhash

        return text, validatehash

    def checkhash(self, text, node, p1=None, p2=None, rev=None):

        if p1 is None and p2 is None:

            p1, p2 = self.parents(node)

        if node != revlog.hash(text, p1, p2):

            raise error.RevlogError(_("integrity check failed on %s") %

                self._path)

    def revision(self, node, raw=False):

        validatenode(node)

        if node == nullid:

            return b''

        rev = self.rev(node)

        flags = self.flags(rev)

        path = b'/'.join([self._storepath, hex(node)])

        rawtext = self._svfs.read(path)

        text, validatehash = self._processflags(rawtext, flags, 'read', raw=raw)

        if validatehash:

            self.checkhash(text, node, rev=rev)

        return text

    def read(self, node):

        validatenode(node)

        revision = self.revision(node)

        if not revision.startswith(b'\1\n'):

            return revision

        start = revision.index(b'\1\n', 2)

        return revision[start + 2:]

    def renamed(self, node):

        validatenode(node)

        if self.parents(node)[0] != nullid:

            return False

        fulltext = self.revision(node)

        m = filelog.parsemeta(fulltext)[0]

        if m and 'copy' in m:

            return m['copy'], bin(m['copyrev'])

        return False

    def cmp(self, node, text):

        validatenode(node)

        t = text

        if text.startswith(b'\1\n'):

            t = b'\1\n\1\n' + text

        p1, p2 = self.parents(node)

        if revlog.hash(t, p1, p2) == node:

            return False

        if self.iscensored(self.rev(node)):

            return text != b''

        if self.renamed(node):

            t2 = self.read(node)

            return t2 != text

        return True

    def size(self, rev):

        validaterev(rev)

        node = self._indexbyrev[rev][b'node']

        if self.renamed(node):

            return len(self.read(node))

        if self.iscensored(rev):

            return 0

        return len(self.revision(node))

    def iscensored(self, rev):

        validaterev(rev)

        return self.flags(rev) & revlog.REVIDX_ISCENSORED

    def commonancestorsheads(self, a, b):

        validatenode(a)

        validatenode(b)

        a = self.rev(a)

        b = self.rev(b)

        ancestors = ancestor.commonancestorsheads(self.parentrevs, a, b)

        return pycompat.maplist(self.node, ancestors)

    def descendants(self, revs):

        # This is a copy of revlog.descendants()

        first = min(revs)

        if first == nullrev:

            for i in self:

                yield i

            return

        seen = set(revs)

        for i in self.revs(start=first + 1):

            for x in self.parentrevs(i):

                if x != nullrev and x in seen:

                    seen.add(i)

                    yield i

                    break

    # Required by verify.

    def files(self):

        entries = self._svfs.listdir(self._storepath)

        # Strip out undo.backup.* files created as part of transaction

        # recording.

        entries = [f for f in entries if not f.startswith('undo.backup.')]

        return [b'/'.join((self._storepath, f)) for f in entries]