view mercurial/pure/base85.py @ 46634:ad30b29bc23d

copies: choose target directory based on longest match

If one side of a merge renames `dir1/` to `dir2/` and the subdirectory
`dir1/subdir1/` to `dir2/subdir2/`, and the other side of the merge
adds a file in `dir1/subdir1/`, we should clearly move that into
`dir2/subdir2/`. We already detect the directories correctly before
this patch, but we iterate over them in arbitrary order. That results
in the new file sometimes ending up in `dir2/subdir1/` instead. This
patch fixes it by iterating over the source directories by visiting
subdirectories first. That's achieved by simply iterating over them in
reverse lexicographical order.

Without the fix, the test case still passes on Python 2 but fails on
Python 3. It depends on the iteration order of the dict. I did not
look into how it's built up and why it behaved differently before the
fix. I could probably have gotten it to fail on Python 2 as well by
choosing different directory names.

Differential Revision: https://phab.mercurial-scm.org/D10115

# 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