view mercurial/pure/base85.py @ 44347:9c9cfecd4600

rebase: don't use rebased node as dirstate p2 (BC)

When rebasing a node, we currently use the rebased node as p2 in the
dirstate until just before we commit it (we then change to the desired
parents). This p2 is visible to the user when the rebase gets
interrupted because of merge conflicts. That can be useful to the user
as a reminder of which commit is currently being rebased, but I
believe it's incorrect for a few reasons:

 * I think the dirstate parents should be the ones that will be set
   when the commit is created.

 * I think having two parents means that you're merging those two
   commits, but when rebasing, you're generally grafting, not merging.

 * When rebasing a merge commit, we should use the two desired parents
   as dirstate parents (and we clearly can't have the rebased node as
   a third dirstate parent).

 * `hg graft` (and `hg update --merge`) sets only one parent and `hg
   rebase` should be consistent with that.

I realize that this is a somewhat large user-visible change, but I
think it's worth it because it will simplify things quite a bit.

Differential Revision: https://phab.mercurial-scm.org/D7827

# base85.py: pure python base85 codec
#
# Copyright (C) 2009 Brendan Cully <[e-mail]>
#
# 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

_b85chars = pycompat.bytestr(
    b"0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdef"
    b"ghijklmnopqrstuvwxyz!#$%&()*+-;<=>?@^_`{|}~"
)
_b85chars2 = [(a + b) for a in _b85chars for b in _b85chars]
_b85dec = {}


def _mkb85dec():
    for i, c in enumerate(_b85chars):
        _b85dec[c] = i


def b85encode(text, pad=False):
    """encode text in base85 format"""
    l = len(text)
    r = l % 4
    if r:
        text += b'\0' * (4 - r)
    longs = len(text) >> 2
    words = struct.unpack(b'>%dL' % longs, text)

    out = b''.join(
        _b85chars[(word // 52200625) % 85]
        + _b85chars2[(word // 7225) % 7225]
        + _b85chars2[word % 7225]
        for word in words
    )

    if pad:
        return out

    # Trim padding
    olen = l % 4
    if olen:
        olen += 1
    olen += l // 4 * 5
    return out[:olen]


def b85decode(text):
    """decode base85-encoded text"""
    if not _b85dec:
        _mkb85dec()

    l = len(text)
    out = []
    for i in range(0, len(text), 5):
        chunk = text[i : i + 5]
        chunk = pycompat.bytestr(chunk)
        acc = 0
        for j, c in enumerate(chunk):
            try:
                acc = acc * 85 + _b85dec[c]
            except KeyError:
                raise ValueError(
                    'bad base85 character at position %d' % (i + j)
                )
        if acc > 4294967295:
            raise ValueError('Base85 overflow in hunk starting at byte %d' % i)
        out.append(acc)

    # Pad final chunk if necessary
    cl = l % 5
    if cl:
        acc *= 85 ** (5 - cl)
        if cl > 1:
            acc += 0xFFFFFF >> (cl - 2) * 8
        out[-1] = acc

    out = struct.pack(b'>%dL' % (len(out)), *out)
    if cl:
        out = out[: -(5 - cl)]

    return out