"""JSON token scanner
"""
import re
try:
    from _json import make_scanner as c_make_scanner
except ImportError:
    c_make_scanner = None
try:
    from _json import scanstring as c_scanstring
except ImportError:
    c_scanstring = None

__all__ = ['make_scanner', 'JSONDecodeError']


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)


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

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, parse_string, 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 <= uni <= 0xdbff and s[end:end + 2] == '\\u':
                uni2 = _decode_uXXXX(s, end + 1)
                if 0xdc00 <= uni2 <= 0xdfff:
                    uni = 0x10000 + (((uni - 0xd800) << 10) | (uni2 - 0xdc00))
                    end += 6
            char = chr(uni)
        _append(char)

    string = ''.join(chunks)
    if parse_string is not None:
        string = parse_string(string)
    return string, end


# Use speedup if available
scanstring = py_scanstring  # SWAP: scanstring = c_scanstring or py_scanstring

WHITESPACE = re.compile(r'[ \t\n\r]*', FLAGS)
WHITESPACE_STR = ' \t\n\r'


def scanobject(s, end, parse_key, parse_object, parse_ordered_object,
               strict, scan_once, memo=None,
               _w=WHITESPACE.match, _ws=WHITESPACE_STR):
    pairs = []
    pairs_append = pairs.append
    # Backwards compatibility
    if memo is None:
        memo = {}
    memo_get = memo.setdefault
    # Use a slice to prevent IndexError from being raised, the following
    # check will raise a more specific ValueError if the string is empty
    nextchar = s[end:end + 1]
    # Normally we expect nextchar == '"'
    if nextchar != '"':
        if nextchar in _ws:
            end = _w(s, end).end()
            nextchar = s[end:end + 1]
        # Trivial empty object
        if nextchar == '}':
            if parse_ordered_object is not None:
                result = parse_ordered_object(pairs)
                return result, end + 1
            pairs = {}
            if parse_object is not None:
                pairs = parse_object(pairs)
            return pairs, end + 1
        elif nextchar != '"':
            raise JSONDecodeError(
                "Expecting property name enclosed in double quotes", s, end)
    end += 1
    while True:
        key, end = scanstring(s, end, parse_key, strict)
        key = memo_get(key, key)
        # To skip some function call overhead we optimize the fast paths where
        # the JSON key separator is ": " or just ":".
        if s[end:end + 1] != ':':
            end = _w(s, end).end()
            if s[end:end + 1] != ':':
                raise JSONDecodeError("Expecting ':' delimiter", s, end)
        end += 1

        try:
            if s[end] in _ws:
                end += 1
                if s[end] in _ws:
                    end = _w(s, end + 1).end()
        except IndexError:
            pass

        try:
            value, end = scan_once(s, end)
        except StopIteration as err:
            raise JSONDecodeError("Expecting value", s, err.value) from None
        pairs_append((key, value))
        try:
            nextchar = s[end]
            if nextchar in _ws:
                end = _w(s, end + 1).end()
                nextchar = s[end]
        except IndexError:
            nextchar = ''
        end += 1

        if nextchar == '}':
            break
        elif nextchar != ',':
            raise JSONDecodeError("Expecting ',' delimiter", s, end - 1)
        end = _w(s, end).end()
        nextchar = s[end:end + 1]
        end += 1
        if nextchar != '"':
            raise JSONDecodeError(
                "Expecting property name enclosed in double quotes", s, end - 1)
    if parse_ordered_object is not None:
        result = parse_ordered_object(pairs)
        return result, end
    pairs = dict(pairs)
    if parse_object is not None:
        pairs = parse_object(pairs)
    return pairs, end


def scanarray(s, end, parse_array, scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
    values = []
    nextchar = s[end:end + 1]
    if nextchar in _ws:
        end = _w(s, end + 1).end()
        nextchar = s[end:end + 1]
    # Look-ahead for trivial empty array
    if nextchar == ']':
        if parse_array is not None:
            values = parse_array(values)
        return values, end + 1
    _append = values.append
    while True:
        try:
            value, end = scan_once(s, end)
        except StopIteration as err:
            raise JSONDecodeError("Expecting value", s, err.value) from None
        _append(value)
        nextchar = s[end:end + 1]
        if nextchar in _ws:
            end = _w(s, end + 1).end()
            nextchar = s[end:end + 1]
        end += 1
        if nextchar == ']':
            break
        elif nextchar != ',':
            raise JSONDecodeError("Expecting ',' delimiter", s, end - 1)
        try:
            if s[end] in _ws:
                end += 1
                if s[end] in _ws:
                    end = _w(s, end + 1).end()
        except IndexError:
            pass

    if parse_array is not None:
        values = parse_array(values)
    return values, end


NUMBER_RE = re.compile(r'(-?(?:0|[1-9]\d*))(\.\d+)?([eE][-+]?\d+)?', FLAGS)


def py_make_scanner(context):
    strict = context.strict
    parse_ordered_object = context.parse_ordered_object
    parse_object = context.parse_object
    parse_key = context.parse_key
    parse_array = context.parse_array
    parse_string = context.parse_string
    parse_float = context.parse_float
    parse_int = context.parse_int
    parse_constant = context.parse_constant
    memo = context.memo

    def _scan_once(string, idx):
        try:
            nextchar = string[idx]
        except IndexError:
            raise StopIteration(idx)

        if nextchar == '"':
            return scanstring(string, idx + 1, parse_string, strict)
        elif nextchar == '{':
            return scanobject(string, idx + 1, parse_key, parse_object, parse_ordered_object, strict, _scan_once, memo)
        elif nextchar == '[':
            return scanarray(string, idx + 1, parse_array, _scan_once)
        elif nextchar == 'n' and string[idx:idx + 4] == 'null':
            return None, idx + 4
        elif nextchar == 't' and string[idx:idx + 4] == 'true':
            return True, idx + 4
        elif nextchar == 'f' and string[idx:idx + 5] == 'false':
            return False, idx + 5

        m = NUMBER_RE.match(string, idx)
        if m is not None:
            integer, frac, exp = m.groups()
            if frac or exp:
                res = parse_float(integer + (frac or '') + (exp or ''))
            else:
                res = parse_int(integer)
            return res, m.end()
        elif nextchar == 'N' and string[idx:idx + 3] == 'NaN':
            return parse_constant('NaN'), idx + 3
        elif nextchar == 'I' and string[idx:idx + 8] == 'Infinity':
            return parse_constant('Infinity'), idx + 8
        elif nextchar == '-' and string[idx:idx + 9] == '-Infinity':
            return parse_constant('-Infinity'), idx + 9
        else:
            raise StopIteration(idx)

    def scan_once(string, idx):
        try:
            return _scan_once(string, idx)
        finally:
            memo.clear()

    return _scan_once


make_scanner = py_make_scanner  # SWAP: make_scanner = c_make_scanner or py_make_scanner