view mercurial/pure/base85.py @ 34686:0d1b8be8d8a8

build: for the bootstrap phase of a deb/rpm build pure-py mercurial is enough When bootstrapping a deb/rpm build, packagelib.sh starts performing a local build for the sole purpose of parsing the output of "hg version". Then it "hg archive"s the source code, and builds everything again. For that initial step, we are perfectly good in using a pure python mercurial, without compiling the c modules (base85, bdiff, zstdlib, ...). On my personal system, this cuts down 22 seconds for a package build (the bootstrapping build goes from ~30 to ~8 seconds).
author muxator <a.mux@inwind.it>
date Fri, 13 Oct 2017 22:42:17 +0200
parents 9007f697e8ef
children 01b4d88ccb24
line wrap: on
line source

# 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

_b85chars = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ" \
            "abcdefghijklmnopqrstuvwxyz!#$%&()*+-;<=>?@^_`{|}~"
_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 += '\0' * (4 - r)
    longs = len(text) >> 2
    words = struct.unpack('>%dL' % (longs), text)

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

    return out