view mercurial/pure/charencode.py @ 44975:1a4b9b602e54 stable

py3: fix broken man page generation, it was generating `(default: NUL*)` `bytes(default)` was producing things like `(default: \x00)` when handed non-bytes values such as `1`, `10`, or `True`. The man page generation would apparently ignore these bytes and produce man pages that had the string `(default: )`. Test Plan: - Ran `cd doc; python3 gendoc.py "hg.1.gendoc"` and grepped for bad output - Ran `make deb`, extracted the deb, manually inspected `hg.1` file. Differential Revision: https://phab.mercurial-scm.org/D8639
author Kyle Lippincott <spectral@google.com>
date Wed, 17 Jun 2020 16:11:11 -0700
parents 9f70512ae2cf
children 89a2afe31e82
line wrap: on
line source

# charencode.py - miscellaneous character encoding
#
#  Copyright 2005-2009 Matt Mackall <mpm@selenic.com> 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(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, 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 b''.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('H', u16b)
    u16codes.pop(0)  # drop BOM
    return b''.join(jm[x] if x < 128 else b'\\u%04x' % x for x in u16codes)