view mercurial/cffi/bdiff.py @ 40042:208303a8172c

obsolete: explicitly track folds inside the markers

We now record information to be able to recognize "fold" event from
obsolescence markers. To do so, we track the following pieces of information:

a) a fold ID. Unique to that fold (per successor),
b) the number of predecessors,
c) the index of the predecessor in that fold.

We will now be able to create an algorithm able to find "predecessorssets".

We now store this data in the generic "metadata" field of the markers.
Updating the format to have a more compact storage for this would be useful.

This way of tracking a fold through multiple markers could be applied to split
too. This would have two advantages:

1) We get a simpler format, since number of successors is limited to [0-1].
2) We can better deal with situations where only some of the split successors
   are pushed to a remote repository.

We should look into the relevance of such a change before updating the on-disk
format.

note: unlike splits, folds do not have to deal with cases where only some of
the markers have been synchronized. As they all share the same successor
changesets, they are all relevant to the same nodes.

# bdiff.py - CFFI implementation of bdiff.c
#
# Copyright 2016 Maciej Fijalkowski <[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 struct

from ..pure.bdiff import *
from . import _bdiff

ffi = _bdiff.ffi
lib = _bdiff.lib

def blocks(sa, sb):
    a = ffi.new("struct bdiff_line**")
    b = ffi.new("struct bdiff_line**")
    ac = ffi.new("char[]", str(sa))
    bc = ffi.new("char[]", str(sb))
    l = ffi.new("struct bdiff_hunk*")
    try:
        an = lib.bdiff_splitlines(ac, len(sa), a)
        bn = lib.bdiff_splitlines(bc, len(sb), b)
        if not a[0] or not b[0]:
            raise MemoryError
        count = lib.bdiff_diff(a[0], an, b[0], bn, l)
        if count < 0:
            raise MemoryError
        rl = [None] * count
        h = l.next
        i = 0
        while h:
            rl[i] = (h.a1, h.a2, h.b1, h.b2)
            h = h.next
            i += 1
    finally:
        lib.free(a[0])
        lib.free(b[0])
        lib.bdiff_freehunks(l.next)
    return rl

def bdiff(sa, sb):
    a = ffi.new("struct bdiff_line**")
    b = ffi.new("struct bdiff_line**")
    ac = ffi.new("char[]", str(sa))
    bc = ffi.new("char[]", str(sb))
    l = ffi.new("struct bdiff_hunk*")
    try:
        an = lib.bdiff_splitlines(ac, len(sa), a)
        bn = lib.bdiff_splitlines(bc, len(sb), b)
        if not a[0] or not b[0]:
            raise MemoryError
        count = lib.bdiff_diff(a[0], an, b[0], bn, l)
        if count < 0:
            raise MemoryError
        rl = []
        h = l.next
        la = lb = 0
        while h:
            if h.a1 != la or h.b1 != lb:
                lgt = (b[0] + h.b1).l - (b[0] + lb).l
                rl.append(struct.pack(">lll", (a[0] + la).l - a[0].l,
                                      (a[0] + h.a1).l - a[0].l, lgt))
                rl.append(str(ffi.buffer((b[0] + lb).l, lgt)))
            la = h.a2
            lb = h.b2
            h = h.next

    finally:
        lib.free(a[0])
        lib.free(b[0])
        lib.bdiff_freehunks(l.next)
    return "".join(rl)