view mercurial/pure/mpatch.py @ 41987:c1d83d916e85

revert: option to choose what to keep, not what to discard

I know the you (the reader) are probably tired of discussing how `hg
revert -i -r .` should behave and so am I. And I know I'm one of the
people who argued that showing the diff from the working copy to the
parent was confusing. I think it is less confusing now that we show
the diff from the parent to the working copy, but I still find it
confusing. I think showing the diff of hunks to keep might make it
easier to understand. So that's what this patch provides an option
for.

One argument doing it this way is that most people seem to find `hg
split` natural. I suspect that is because it shows the forward diff
(from parent commit to the commit) and asks you what to put in the
first commit. I think the new "keep" mode for revert (this patch)
matches that.

In "keep" mode, all the changes are still selected by default. That
means that `hg revert -i` followed by 'A' (keep all) (or 'c' in
curses) will be different from `hg revert -a`. That's mostly because
that was simplest. It can also be argued that it's safest. But it can
also be argued that it should be consistent with `hg revert -a`.

Note that in this mode, you can edit the hunks and it will do what you
expect (e.g. add new lines to your file if you added a new lines when
editing). The test case shows that that works.

Differential Revision: https://phab.mercurial-scm.org/D6125

# mpatch.py - Python implementation of mpatch.c
#
# Copyright 2009 Matt Mackall <[e-mail]> and others
#
# 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 .. import pycompat
stringio = pycompat.bytesio

class mpatchError(Exception):
    """error raised when a delta cannot be decoded
    """

# This attempts to apply a series of patches in time proportional to
# the total size of the patches, rather than patches * len(text). This
# means rather than shuffling strings around, we shuffle around
# pointers to fragments with fragment lists.
#
# When the fragment lists get too long, we collapse them. To do this
# efficiently, we do all our operations inside a buffer created by
# mmap and simply use memmove. This avoids creating a bunch of large
# temporary string buffers.

def _pull(dst, src, l): # pull l bytes from src
    while l:
        f = src.pop()
        if f[0] > l: # do we need to split?
            src.append((f[0] - l, f[1] + l))
            dst.append((l, f[1]))
            return
        dst.append(f)
        l -= f[0]

def _move(m, dest, src, count):
    """move count bytes from src to dest

    The file pointer is left at the end of dest.
    """
    m.seek(src)
    buf = m.read(count)
    m.seek(dest)
    m.write(buf)

def _collect(m, buf, list):
    start = buf
    for l, p in reversed(list):
        _move(m, buf, p, l)
        buf += l
    return (buf - start, start)

def patches(a, bins):
    if not bins:
        return a

    plens = [len(x) for x in bins]
    pl = sum(plens)
    bl = len(a) + pl
    tl = bl + bl + pl # enough for the patches and two working texts
    b1, b2 = 0, bl

    if not tl:
        return a

    m = stringio()

    # load our original text
    m.write(a)
    frags = [(len(a), b1)]

    # copy all the patches into our segment so we can memmove from them
    pos = b2 + bl
    m.seek(pos)
    for p in bins:
        m.write(p)

    for plen in plens:
        # if our list gets too long, execute it
        if len(frags) > 128:
            b2, b1 = b1, b2
            frags = [_collect(m, b1, frags)]

        new = []
        end = pos + plen
        last = 0
        while pos < end:
            m.seek(pos)
            try:
                p1, p2, l = struct.unpack(">lll", m.read(12))
            except struct.error:
                raise mpatchError("patch cannot be decoded")
            _pull(new, frags, p1 - last) # what didn't change
            _pull([], frags, p2 - p1)    # what got deleted
            new.append((l, pos + 12))   # what got added
            pos += l + 12
            last = p2
        frags.extend(reversed(new))     # what was left at the end

    t = _collect(m, b2, frags)

    m.seek(t[1])
    return m.read(t[0])

def patchedsize(orig, delta):
    outlen, last, bin = 0, 0, 0
    binend = len(delta)
    data = 12

    while data <= binend:
        decode = delta[bin:bin + 12]
        start, end, length = struct.unpack(">lll", decode)
        if start > end:
            break
        bin = data + length
        data = bin + 12
        outlen += start - last
        last = end
        outlen += length

    if bin != binend:
        raise mpatchError("patch cannot be decoded")

    outlen += orig - last
    return outlen