"""Implementation of JSONDecoder
"""
import re

from json import scanner
try:
    from _json import scanstring as c_scanstring
except ImportError:
    c_scanstring = None

__all__ = ['JSONDecoder', 'JSONDecodeError']

FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL

NaN = float('nan')
PosInf = float('inf')
NegInf = float('-inf')


class JSONDecodeError(ValueError):
    """Subclass of ValueError with the following additional properties:

    msg: The unformatted error message
    doc: The JSON document being parsed
    pos: The start index of doc where parsing failed
    lineno: The line corresponding to pos
    colno: The column corresponding to pos

    """
    # Note that this exception is used from _json
    def __init__(self, msg, doc, pos):
        lineno = doc.count('\n', 0, pos) + 1
        colno = pos - doc.rfind('\n', 0, pos)
        errmsg = '%s: line %d column %d (char %d)' % (msg, lineno, colno, pos)
        ValueError.__init__(self, errmsg)
        self.msg = msg
        self.doc = doc
        self.pos = pos
        self.lineno = lineno
        self.colno = colno

    def __reduce__(self):
        return self.__class__, (self.msg, self.doc, self.pos)


_CONSTANTS = {
    '-Infinity': NegInf,
    'Infinity': PosInf,
    'NaN': NaN,
}


STRINGCHUNK = re.compile(r'(.*?)(["\\\x00-\x1f])', FLAGS)
BACKSLASH = {
    '"': '"', '\\': '\\', '/': '/',
    'b': '\b', 'f': '\f', 'n': '\n', 'r': '\r', 't': '\t',
}

def _decode_uXXXX(s, pos):
    esc = s[pos + 1:pos + 5]
    if len(esc) == 4 and esc[1] not in 'xX':
        try:
            return int(esc, 16)
        except ValueError:
            pass
    msg = "Invalid \\uXXXX escape"
    raise JSONDecodeError(msg, s, pos)

def py_scanstring(s, end, strict=True,
        _b=BACKSLASH, _m=STRINGCHUNK.match):
    """Scan the string s for a JSON string. End is the index of the
    character in s after the quote that started the JSON string.
    Unescapes all valid JSON string escape sequences and raises ValueError
    on attempt to decode an invalid string. If strict is False then literal
    control characters are allowed in the string.

    Returns a tuple of the decoded string and the index of the character in s
    after the end quote."""
    chunks = []
    _append = chunks.append
    begin = end - 1
    while 1:
        chunk = _m(s, end)
        if chunk is None:
            raise JSONDecodeError("Unterminated string starting at", s, begin)
        end = chunk.end()
        content, terminator = chunk.groups()
        # Content is contains zero or more unescaped string characters
        if content:
            _append(content)
        # Terminator is the end of string, a literal control character,
        # or a backslash denoting that an escape sequence follows
        if terminator == '"':
            break
        elif terminator != '\\':
            if strict:
                #msg = "Invalid control character %r at" % (terminator,)
                msg = "Invalid control character {0!r} at".format(terminator)
                raise JSONDecodeError(msg, s, end)
            else:
                _append(terminator)
                continue
        try:
            esc = s[end]
        except IndexError:
            raise JSONDecodeError("Unterminated string starting at", s, begin)
        # If not a unicode escape sequence, must be in the lookup table
        if esc != 'u':
            try:
                char = _b[esc]
            except KeyError:
                msg = "Invalid \\escape: {0!r}".format(esc)
                raise JSONDecodeError(msg, s, end)
            end += 1
        else:
            uni = _decode_uXXXX(s, end)
            end += 5
            if 0xd800