Mercurial > hg
view mercurial/pure/base85.py @ 42437:9609430d3625
rust-filepatterns: use bytes instead of String
In my initial patch, I introduced an unnecessary hard constraint on UTF-8
filenames and patterns which I forgot to remove. Although the performance
penalty for using String might be negligible, we don't want to break
compatibility with non-UTF-8 encodings for no reason.
Moreover, this change allows for a cleaner Rust core API.
This patch introduces a new utils module that is used with this fix.
Finally, PatternError was not put inside the Python module generated by
Rust, which would have raised a NameError.
Differential Revision: https://phab.mercurial-scm.org/D6485
author | Raphaël Gomès <rgomes@octobus.net> |
---|---|
date | Thu, 06 Jun 2019 15:30:56 +0200 |
parents | 80301c90a2dc |
children | 2372284d9457 |
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 from .. import pycompat _b85chars = pycompat.bytestr("0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdef" "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 += '\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] 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('>%dL' % (len(out)), *out) if cl: out = out[:-(5 - cl)] return out