Mercurial > hg
view mercurial/pure/mpatch.py @ 42522:d29db0a0c4eb
update: fix spurious unclean status bug shown by previous commit
The crux of the problem is:
- the dirstate is corrupted (the sizes/dates are assigned to the wrong files)
- because when worker.worker is used with a return value (batchget in
merge.py here), the return value when worker.worker effectively parallelizes
is permuted
- this is because worker.worker's partition of input and combination of output
values are not inverses of one another: it split [1,2,3,4,5,6] into
[[1,3,5],[2,4,6]], but combines that into [1,3,5,2,4,6].
Given that worker.worker doesn't call its function argument on contiguous
chunks on the input arguments, sticking with lists means we'd need to
know the relation between the inputs of worker.worker function argument
(for instance, requiring that every input element is mapped to exactly
one output element). It seems better to instead switch return values to
dicts, which can combined reliably with a straighforward restriction.
Differential Revision: https://phab.mercurial-scm.org/D6581
author | Valentin Gatien-Baron <valentin.gatienbaron@gmail.com> |
---|---|
date | Thu, 27 Jun 2019 11:39:35 +0200 |
parents | 644a02f6b34f |
children | 2372284d9457 |
line wrap: on
line source
# mpatch.py - Python implementation of mpatch.c # # Copyright 2009 Matt Mackall <mpm@selenic.com> 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