view mercurial/pure/charencode.py @ 40042:208303a8172c

obsolete: explicitly track folds inside the markers

We now record information to be able to recognize "fold" event from
obsolescence markers. To do so, we track the following pieces of information:

a) a fold ID. Unique to that fold (per successor),
b) the number of predecessors,
c) the index of the predecessor in that fold.

We will now be able to create an algorithm able to find "predecessorssets".

We now store this data in the generic "metadata" field of the markers.
Updating the format to have a more compact storage for this would be useful.

This way of tracking a fold through multiple markers could be applied to split
too. This would have two advantages:

1) We get a simpler format, since number of successors is limited to [0-1].
2) We can better deal with situations where only some of the split successors
   are pushed to a remote repository.

We should look into the relevance of such a change before updating the on-disk
format.

note: unlike splits, folds do not have to deal with cases where only some of
the markers have been synchronized. As they all share the same successor
changesets, they are all relevant to the same nodes.

# 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)