view mercurial/cffi/bdiff.py @ 51723:9367571fea21

cext: correct the argument handling of `b85encode()`

The type stub indicated that this argument is `Optional`, which implies None is
allowed.  I don't see in the documentation where that's the case for `i`[1], and
trying it in `hg debugshell` resulted in the method failing with a TypeError.  I
guess it was typed as an `int` argument because the `p` format unit wasn't added
until Python 3.3[2].

In any event, 2 clients in core (`pvec` and `obsolete`) call this with no
argument supplied, and `mdiff` calls it with True.  So I guess we've avoided the
None arg case, and when no arg is supplied, it defaults to the 0 initialization
of the `pad` variable in C.  Since the `p` format unit accepts both `int` and
None, as well as `bool`, I'm not bothering to bump the module version- this code
is more permissive than it was, in addition to being more correct.

Interestingly, when I first imported the `cext` and `pure` methods in the same
manner as the previous commit, it dropped the `Optional` part of the argument
type when generating `util.pyi`.  No idea why.

[1] https://docs.python.org/3/c-api/arg.html#numbers
[2] https://docs.python.org/3/c-api/arg.html#other-objects

# 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 typing import (
    List,
    Tuple,
)

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

ffi = _bdiff.ffi
lib = _bdiff.lib


def blocks(sa: bytes, sb: bytes) -> List[Tuple[int, int, int, int]]:
    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 = [(0, 0, 0, 0)] * 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: bytes, sb: bytes) -> bytes:
    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)