mercurial/pure/base85.py
author Valentin Gatien-Baron <valentin.gatienbaron@gmail.com>
Tue, 25 Feb 2020 20:27:39 -0500
changeset 44439 edc8504bc26b
parent 43431 4cd911040ba5
child 48966 6000f5b25c9b
permissions -rw-r--r--
exchange: turn on option that makes concurrent pushes work better The motivation is simply to make hg work better out of the box. This is a slight backwards compatibility break, because client extensions could have assumed that the list of heads the client sees during discovery will be the list of heads during the entirety of the push. It seems unlikely to matter, and not worth mentioning. There's a fair amount of diff in tests, but this is just due to sending a few more bytes on the wire, except for test-acl.t. The extra "invalid branch cache" lines in test-acl.t don't seem to indicate a problem: the branchcache now get computed during the bundle application (because of the check:updated-heads bundle part), but doesn't get rolled back when transactions rollback, thus causing a message in the next operation computing the branch cache. Before this change, I assume the branchcache was only computed on transaction commit, so not computed at all when the transactions roll back, thus no messages. Differential Revision: https://phab.mercurial-scm.org/D8202

# base85.py: pure python base85 codec
#
# Copyright (C) 2009 Brendan Cully <brendan@kublai.com>
#
# 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