Mercurial > hg
view mercurial/pure/mpatch.py @ 47072:4c041c71ec01
revlog: introduce an explicit tracking of what the revlog is about
Since the dawn of time, people have been forced to rely to lossy introspection
of the index filename to determine what the purpose and role of the revlog they
encounter is. This is hacky, error prone, inflexible, abstraction-leaky,
<insert-your-own-complaints-here>.
In f63299ee7e4d Raphaël introduced a new attribute to track this information:
`revlog_kind`. However it is initialized in an odd place and various instances
end up not having it set. In addition is only tracking some of the information
we end up having to introspect in various pieces of code.
So we add a new attribute that holds more data and is more strictly enforced.
This work is done in collaboration with Raphaël.
The `revlog_kind` one will be removed/adapted in the next changeset. We expect
to be able to clean up various existing piece of code and to simplify coming
work around the newer revlog format.
Differential Revision: https://phab.mercurial-scm.org/D10352
author | Pierre-Yves David <pierre-yves.david@octobus.net> |
---|---|
date | Tue, 06 Apr 2021 05:20:24 +0200 |
parents | d4ba4d51f85f |
children | 5aafc3c5bdec |
line wrap: on
line source
# mpatch.py - Python implementation of mpatch.c # # Copyright 2009 Olivia Mackall <olivia@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(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, 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(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