mercurial/pure/charencode.py

interfaces: add the optional `bdiff.xdiffblocks()` method

PyCharm flagged where this was called on the protocol class in `mdiff.py` in the
previous commit, but pytype completely missed it.  PyCharm is correct here, but
I'm committing this separately to highlight this potential problem- some of the
implementations don't implement _all_ of the methods the others do, and there's
not a great way to indicate on a protocol class that a method or attribute is
optional- that's kinda the opposite of what static typing is about.

Making the method an `Optional[Callable]` attribute works here, and keeps both
PyCharm and pytype happy, and the generated `mdiff.pyi` and `modules.pyi` look
reasonable.  We might be getting a little lucky, because the method isn't
invoked directly- it is returned from another method that selects which block
function to use.  Except since it is declared on the protocol class, every
module needs this attribute (in theory, but in practice this doesn't seem to be
checked), so the check for it on the module has to change from `hasattr()` to
`getattr(..., None)`.  We defer defining the optional attrs to the type checking
phase as an extra precaution- that way it isn't an attr with a `None` value at
runtime if someone is still using `hasattr()`.

As to why pytype missed this, I have no clue.  The generated `mdiff.pyi` even
has the global variable typed as `bdiff: intmod.BDiff`, so uses of it really
should comply with what is on the class, protocol class or not.

# charencode.py - miscellaneous character encoding
#
#  Copyright 2005-2009 Olivia 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 annotations

import array

from .. import pycompat


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


def asciilower(s: bytes) -> bytes:
    """convert a string to lowercase if ASCII

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


def asciiupper(s: bytes) -> bytes:
    """convert a string to uppercase if ASCII

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


_jsonmap = []
_jsonmap.extend(b"\\u%04x" % x for x in range(32))
_jsonmap.extend(pycompat.bytechr(x) for x in range(32, 127))
_jsonmap.append(b'\\u007f')
_jsonmap[0x09] = b'\\t'
_jsonmap[0x0A] = b'\\n'
_jsonmap[0x22] = b'\\"'
_jsonmap[0x5C] = b'\\\\'
_jsonmap[0x08] = b'\\b'
_jsonmap[0x0C] = b'\\f'
_jsonmap[0x0D] = b'\\r'
_paranoidjsonmap = _jsonmap[:]
_paranoidjsonmap[0x3C] = b'\\u003c'  # '<' (e.g. escape "</script>")
_paranoidjsonmap[0x3E] = b'\\u003e'  # '>'
_jsonmap.extend(pycompat.bytechr(x) for x in range(128, 256))


def jsonescapeu8fast(u8chars: bytes, paranoid: bool) -> bytes:
    """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 b''.join(jm[x] for x in bytearray(u8chars))
    except IndexError:
        raise ValueError


_utf8strict = r'surrogatepass'


def jsonescapeu8fallback(u8chars: bytes, paranoid: bool) -> bytes:
    """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('H', u16b)
    u16codes.pop(0)  # drop BOM
    return b''.join(jm[x] if x < 128 else b'\\u%04x' % x for x in u16codes)