view mercurial/cffi/bdiff.py @ 45095:8e04607023e5

procutil: ensure that procutil.std{out,err}.write() writes all bytes

Python 3 offers different kind of streams and it’s not guaranteed for all of
them that calling write() writes all bytes.

When Python is started in unbuffered mode, sys.std{out,err}.buffer are
instances of io.FileIO, whose write() can write less bytes for
platform-specific reasons (e.g. Linux has a 0x7ffff000 bytes maximum and could
write less if interrupted by a signal; when writing to Windows consoles, it’s
limited to 32767 bytes to avoid the "not enough space" error). This can lead to
silent loss of data, both when using sys.std{out,err}.buffer (which may in fact
not be a buffered stream) and when using the text streams sys.std{out,err}
(I’ve created a CPython bug report for that:
https://bugs.python.org/issue41221).

Python may fix the problem at some point. For now, we implement our own wrapper
for procutil.std{out,err} that calls the raw stream’s write() method until all
bytes have been written. We don’t use sys.std{out,err} for larger writes, so I
think it’s not worth the effort to patch them.

# 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(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)