mercurial/pure/mpatch.py

phases: drop the list with phase of each rev, always comput phase sets

Change the C implementation of phasecache.loadphaserevs to provide only
the sets for draft and secret phase as well as the number of revisions
seen.

Change the pure Python implementation of the same functino to compute
the sets instead of the list of phases for each revision.

Change phasecache.phase to check the phase sets and assume public if the
revision is in neither draft nor secret set. This is computationally
slightly more expensive.

Change phasecache.getrevset for public() based queries to compute the
set of non-matching revisions and return the result as filtered
fullreposet. A shortcut is taken when no draft or secret revision
exists.

Bump the module version for the changed interface contract.

Overall, this saves around 16 Bytes per revision whenever the phasecache
is used, for the test case in issue5691 it is around 3MB. getrevset()
for a large repository is around 13% slower here, that seems an
acceptable trade off. Performance impact for phase() should be similar.

Differential Revision: https://phab.mercurial-scm.org/D1606

# 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.stringio

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