"""Implementation of JSONDecoder
from _json import scanstring as c_scanstring
__all__ = ['JSONDecoder', 'JSONDecodeError']
FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL
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)
return self.__class__, (self.msg, self.doc, self.pos)
STRINGCHUNK = re.compile(r'(.*?)(["\\\x00-\x1f])', FLAGS)
'"': '"', '\\': '\\', '/': '/',
'b': '\b', 'f': '\f', 'n': '\n', 'r': '\r', 't': '\t',
def _decode_uXXXX(s, pos):
if len(esc) == 4 and esc[1] not in 'xX':
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
raise JSONDecodeError("Unterminated string starting at", s, begin)
content, terminator = chunk.groups()
# Content is contains zero or more unescaped string characters
# Terminator is the end of string, a literal control character,
# or a backslash denoting that an escape sequence follows
#msg = "Invalid control character %r at" % (terminator,)
msg = "Invalid control character {0!r} at".format(terminator)
raise JSONDecodeError(msg, s, end)
raise JSONDecodeError("Unterminated string starting at", s, begin)
# If not a unicode escape sequence, must be in the lookup table
msg = "Invalid \\escape: {0!r}".format(esc)
raise JSONDecodeError(msg, s, end)
uni = _decode_uXXXX(s, end)
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))
return ''.join(chunks), end
# Use speedup if available
scanstring = c_scanstring or py_scanstring
WHITESPACE = re.compile(r'[ \t\n\r]*', FLAGS)
WHITESPACE_STR = ' \t\n\r'
def JSONObject(s_and_end, strict, scan_once, object_hook, object_pairs_hook,
memo=None, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
pairs_append = pairs.append
# Backwards compatibility
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 == '"'
nextchar = s[end:end + 1]
if object_pairs_hook is not None:
result = object_pairs_hook(pairs)
if object_hook is not None:
pairs = object_hook(pairs)
"Expecting property name enclosed in double quotes", s, end)
key, end = scanstring(s, end, strict)
# To skip some function call overhead we optimize the fast paths where
# the JSON key separator is ": " or just ":".
if s[end:end + 1] != ':':
if s[end:end + 1] != ':':
raise JSONDecodeError("Expecting ':' delimiter", s, end)
end = _w(s, end + 1).end()
value, end = scan_once(s, end)
except StopIteration as err:
raise JSONDecodeError("Expecting value", s, err.value) from None
pairs_append((key, value))
end = _w(s, end + 1).end()
raise JSONDecodeError("Expecting ',' delimiter", s, end - 1)
nextchar = s[end:end + 1]
"Expecting property name enclosed in double quotes", s, end - 1)
if object_pairs_hook is not None:
result = object_pairs_hook(pairs)
if object_hook is not None:
pairs = object_hook(pairs)
def JSONArray(s_and_end, scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
nextchar = s[end:end + 1]
end = _w(s, end + 1).end()
nextchar = s[end:end + 1]
# Look-ahead for trivial empty array
value, end = scan_once(s, end)
except StopIteration as err:
raise JSONDecodeError("Expecting value", s, err.value) from None
nextchar = s[end:end + 1]
end = _w(s, end + 1).end()
nextchar = s[end:end + 1]
raise JSONDecodeError("Expecting ',' delimiter", s, end - 1)
end = _w(s, end + 1).end()
class JSONDecoder(object):
"""Simple JSON <http://json.org> decoder
Performs the following translations in decoding by default:
+---------------+-------------------+
+===============+===================+
+---------------+-------------------+
+---------------+-------------------+
+---------------+-------------------+
+---------------+-------------------+
| number (real) | float |
+---------------+-------------------+
+---------------+-------------------+
+---------------+-------------------+
+---------------+-------------------+
It also understands ``NaN``, ``Infinity``, and ``-Infinity`` as
their corresponding ``float`` values, which is outside the JSON spec.
def __init__(self, *, object_hook=None, parse_float=None,
parse_int=None, parse_constant=None, strict=True,
"""``object_hook``, if specified, will be called with the result
of every JSON object decoded and its return value will be used in
place of the given ``dict``. This can be used to provide custom
deserializations (e.g. to support JSON-RPC class hinting).
``object_pairs_hook``, if specified will be called with the result of
every JSON object decoded with an ordered list of pairs. The return
value of ``object_pairs_hook`` will be used instead of the ``dict``.
This feature can be used to implement custom decoders that rely on the
order that the key and value pairs are decoded (for example,
collections.OrderedDict will remember the order of insertion). If
``object_hook`` is also defined, the ``object_pairs_hook`` takes
``parse_float``, if specified, will be called with the string
of every JSON float to be decoded. By default this is equivalent to
float(num_str). This can be used to use another datatype or parser
for JSON floats (e.g. decimal.Decimal).
``parse_int``, if specified, will be called with the string
of every JSON int to be decoded. By default this is equivalent to
int(num_str). This can be used to use another datatype or parser
for JSON integers (e.g. float).
``parse_constant``, if specified, will be called with one of the
following strings: -Infinity, Infinity, NaN.
This can be used to raise an exception if invalid JSON numbers
If ``strict`` is false (true is the default), then control
characters will be allowed inside strings. Control characters in
this context are those with character codes in the 0-31 range,
including ``'\\t'`` (tab), ``'\\n'``, ``'\\r'`` and ``'\\0'``.
self.object_hook = object_hook
self.parse_float = parse_float or float
self.parse_int = parse_int or int
self.parse_constant = parse_constant or _CONSTANTS.__getitem__
self.object_pairs_hook = object_pairs_hook
self.parse_object = JSONObject
self.parse_array = JSONArray
self.parse_string = scanstring
self.scan_once = scanner.make_scanner(self)
def decode(self, s, _w=WHITESPACE.match):
"""Return the Python representation of ``s`` (a ``str`` instance
containing a JSON document).
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
raise JSONDecodeError("Extra data", s, end)
def raw_decode(self, s, idx=0):
"""Decode a JSON document from ``s`` (a ``str`` beginning with
a JSON document) and return a 2-tuple of the Python
representation and the index in ``s`` where the document ended.
This can be used to decode a JSON document from a string that may
have extraneous data at the end.
obj, end = self.scan_once(s, idx)
except StopIteration as err:
raise JSONDecodeError("Expecting value", s, err.value) from None