view mercurial/pure/charencode.py @ 36958:644a02f6b34f

util: prefer "bytesio" to "stringio"

The io.BytesIO and io.StringIO types enforce the type of
data being operated on. On Python 2, we use cStringIO.StringIO(),
which is lax about mixing types. On Python 3, we actually use
io.BytesIO. Ideally, we'd use io.BytesIO on Python 2. But I believe
its performance is poor compared to cString.StringIO().

Anyway, we canonically define our pycompat type as "stringio."
That name is misleading, especially on Python 3.

This commit renames the canonical symbols to "bytesio."
"stringio" is preserved as an alias for API compatibility. There
are a lot of callers in the repo and I hesitate to take away the
old name. I also don't feel like changing everything at this time.
But at least new callers can use a "proper" name.

Differential Revision: https://phab.mercurial-scm.org/D2868

# 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)