mercurial/pure/charencode.py

sslutil: add support for clients to set TLSv1.3 as the minimum protocol

AFAICT, all of the TLS versions are supported by the server without doing any
explicit work, and there's only a `devel` config to specify an exact version on
the server side.  Clients would also use TLSv1.3 if available, but this prevents
the server from negotiating down.  This also causes "tls1.3" to be listed in
`hg debuginstall`, even though it was previously supported (if the Python
intepreter supported it- IDK if there's a good way to proactively test for and
show future protocols without requiring manual updates like this).

The v1.3 tests are nested inside the v1.2 tests for simplicity.  The v1.2 blocks
already assume v1.0 and v1.1 support, so this seems reasonable for now.  If/when
the older protocols start getting dropped, this will have to be reworked anyway.

# 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)