mercurial/cffi/bdiff.py

tags-fnode-cache: skip building a changectx in getfnode

Building a changectx object is costly, doing it just to retrieve the revision
number is suboptimal. Directly fetching the revision number from the changelog
provide a sizeable speedup to `hg debugupdatecache`.

### data-env-vars.name           = mercurial-2018-08-01-zstd-sparse-revlog
  # benchmark.name               = debug-update-cache
  # benchmark.variants.pre-state = warm
before: 0.213229 seconds
after:  0.165577 seconds  (-22.35%)
  # data-env-vars.name           = mercurial-filtered-2019-11-22-zstd-sparse-revlog
before: 1.200383 seconds
after:  1.071618 seconds  (-10.73%)
  # data-env-vars.name           = mozilla-central-2018-08-01-zstd-sparse-revlog
before: 1.465735 seconds
after:  0.923128 seconds  (-37.02%)
  # data-env-vars.name           = mozilla-try-2019-02-18-zstd-sparse-revlog
before: 6.511771 seconds
after:  4.507316 seconds  (-30.78%)
  # data-env-vars.name           = netbeans-2018-08-01-zstd-sparse-revlog
before: 1.023007 seconds
after:  0.645026 seconds  (-36.95%)
  # data-env-vars.name           = pypy-2018-08-01-zstd-sparse-revlog
before: 0.381141 seconds
after:  0.268654 seconds  (-29.51%)

# 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.


import struct

from ..pure.bdiff import *
from . import _bdiff  # pytype: disable=import-error

ffi = _bdiff.ffi
lib = _bdiff.lib


def blocks(sa, sb):
    a = ffi.new(b"struct bdiff_line**")
    b = ffi.new(b"struct bdiff_line**")
    ac = ffi.new(b"char[]", str(sa))
    bc = ffi.new(b"char[]", str(sb))
    l = ffi.new(b"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(b"struct bdiff_line**")
    b = ffi.new(b"struct bdiff_line**")
    ac = ffi.new(b"char[]", str(sa))
    bc = ffi.new(b"char[]", str(sb))
    l = ffi.new(b"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(
                        b">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 b"".join(rl)