mercurial/pure/mpatch.py

revset: stop serializing node when using "%ln"

Turning hundred of thousand of node from node to hex and back can be slow… what
about we stop doing it?

In many case were we are using node id we should be using revision id. However
this is not a good reason to have a stupidly slow implementation of "%ln".

This caught my attention again because the phase discovery during push make an
extensive use of "%ln" or huge set. In absolute, that phase discovery probably
should use "%ld" and need to improves its algorithmic complexity, but improving
"%ln" seems simple and long overdue. This greatly speeds up `hg push` on
repository with many drafts.

Here are some relevant poulpe benchmarks:

### data-env-vars.name                             = mozilla-try-2023-03-22-zstd-sparse-revlog
  # benchmark.name                                 = hg.command.push
  # bin-env-vars.hg.flavor                         = default
  # bin-env-vars.hg.py-re2-module                  = default
  # benchmark.variants.explicit-rev                = all-out-heads
  # benchmark.variants.issue6528                   = disabled
  # benchmark.variants.protocol                    = ssh
  # benchmark.variants.reuse-external-delta-parent = default

 ## benchmark.variants.revs                        = any-1-extra-rev
before: 44.235070
after:  20.416329 (-53.85%, -23.82)
 ## benchmark.variants.revs                        = any-100-extra-rev
before: 49.234697
after:  26.519829 (-46.14%, -22.71)



### benchmark.name                = hg.command.bundle
  # bin-env-vars.hg.flavor        = default
  # bin-env-vars.hg.py-re2-module = default
  # benchmark.variants.revs       = all
  # benchmark.variants.type       = none-streamv2
 ## data-env-vars.name            = heptapod-public-2024-03-25-zstd-sparse-revlog
before:  10.138396
after:    7.750458  (-23.55%, -2.39)
 ## data-env-vars.name            = mercurial-public-2024-03-22-zstd-sparse-revlog
before:   1.263859
after:    0.700229  (-44.60%, -0.56)
 ## data-env-vars.name            = mozilla-try-2023-03-22-zstd-sparse-revlog
before: 399.484481
after:  346.5089 (-13.26%, -52.98)
 ## data-env-vars.name            = pypy-2024-03-22-zstd-sparse-revlog
before:   4.540080
after:    3.401700  (-25.07%, -1.14)
 ## data-env-vars.name            = tryton-public-2024-03-22-zstd-sparse-revlog
before:   2.975765
after:    1.870798  (-37.13%, -1.10)

# mpatch.py - Python implementation of mpatch.c
#
# Copyright 2009 Olivia 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.


import io
import struct

from typing import (
    List,
    Tuple,
)


stringio = io.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: List[Tuple[int, int]], src: List[Tuple[int, int]], l: int
) -> None:  # 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: stringio, dest: int, src: int, count: int) -> None:
    """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: stringio, buf: int, list: List[Tuple[int, int]]
) -> Tuple[int, int]:
    start = buf
    for l, p in reversed(list):
        _move(m, buf, p, l)
        buf += l
    return (buf - start, start)


def patches(a: bytes, bins: List[bytes]) -> bytes:
    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(b">lll", m.read(12))
            except struct.error:
                raise mpatchError(b"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: int, delta: bytes) -> int:
    outlen, last, bin = 0, 0, 0
    binend = len(delta)
    data = 12

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

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

    outlen += orig - last
    return outlen