view mercurial/pure/charencode.py @ 42522:d29db0a0c4eb

update: fix spurious unclean status bug shown by previous commit

The crux of the problem is:
- the dirstate is corrupted (the sizes/dates are assigned to the wrong files)
- because when worker.worker is used with a return value (batchget in
  merge.py here), the return value when worker.worker effectively parallelizes
  is permuted
- this is because worker.worker's partition of input and combination of output
  values are not inverses of one another: it split [1,2,3,4,5,6] into
  [[1,3,5],[2,4,6]], but combines that into [1,3,5,2,4,6].

Given that worker.worker doesn't call its function argument on contiguous
chunks on the input arguments, sticking with lists means we'd need to
know the relation between the inputs of worker.worker function argument
(for instance, requiring that every input element is mapped to exactly
one output element). It seems better to instead switch return values to
dicts, which can combined reliably with a straighforward restriction.

Differential Revision: https://phab.mercurial-scm.org/D6581

# charencode.py - miscellaneous character encoding
#
#  Copyright 2005-2009 Matt Mackall <[e-mail]> and others
#
# 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 array

from .. import (
    pycompat,
)

def isasciistr(s):
    try:
        s.decode('ascii')
        return True
    except UnicodeDecodeError:
        return False

def asciilower(s):
    '''convert a string to lowercase if ASCII

    Raises UnicodeDecodeError if non-ASCII characters are found.'''
    s.decode('ascii')
    return s.lower()

def asciiupper(s):
    '''convert a string to uppercase if ASCII

    Raises UnicodeDecodeError if non-ASCII characters are found.'''
    s.decode('ascii')
    return s.upper()

_jsonmap = []
_jsonmap.extend("\\u%04x" % x for x in range(32))
_jsonmap.extend(pycompat.bytechr(x) for x in range(32, 127))
_jsonmap.append('\\u007f')
_jsonmap[0x09] = '\\t'
_jsonmap[0x0a] = '\\n'
_jsonmap[0x22] = '\\"'
_jsonmap[0x5c] = '\\\\'
_jsonmap[0x08] = '\\b'
_jsonmap[0x0c] = '\\f'
_jsonmap[0x0d] = '\\r'
_paranoidjsonmap = _jsonmap[:]
_paranoidjsonmap[0x3c] = '\\u003c'  # '<' (e.g. escape "</script>")
_paranoidjsonmap[0x3e] = '\\u003e'  # '>'
_jsonmap.extend(pycompat.bytechr(x) for x in range(128, 256))

def jsonescapeu8fast(u8chars, paranoid):
    """Convert a UTF-8 byte string to JSON-escaped form (fast path)

    Raises ValueError if non-ASCII characters have to be escaped.
    """
    if paranoid:
        jm = _paranoidjsonmap
    else:
        jm = _jsonmap
    try:
        return ''.join(jm[x] for x in bytearray(u8chars))
    except IndexError:
        raise ValueError

if pycompat.ispy3:
    _utf8strict = r'surrogatepass'
else:
    _utf8strict = r'strict'

def jsonescapeu8fallback(u8chars, paranoid):
    """Convert a UTF-8 byte string to JSON-escaped form (slow path)

    Escapes all non-ASCII characters no matter if paranoid is False.
    """
    if paranoid:
        jm = _paranoidjsonmap
    else:
        jm = _jsonmap
    # non-BMP char is represented as UTF-16 surrogate pair
    u16b = u8chars.decode('utf-8', _utf8strict).encode('utf-16', _utf8strict)
    u16codes = array.array(r'H', u16b)
    u16codes.pop(0)  # drop BOM
    return ''.join(jm[x] if x < 128 else '\\u%04x' % x for x in u16codes)