123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359 |
- r"""JSON (JavaScript Object Notation) <http://json.org> is a subset of
- JavaScript syntax (ECMA-262 3rd edition) used as a lightweight data
- interchange format.
- :mod:`json` exposes an API familiar to users of the standard library
- :mod:`marshal` and :mod:`pickle` modules. It is derived from a
- version of the externally maintained simplejson library.
- Encoding basic Python object hierarchies::
- >>> import json
- >>> json.dumps(['foo', {'bar': ('baz', None, 1.0, 2)}])
- '["foo", {"bar": ["baz", null, 1.0, 2]}]'
- >>> print(json.dumps("\"foo\bar"))
- "\"foo\bar"
- >>> print(json.dumps('\u1234'))
- "\u1234"
- >>> print(json.dumps('\\'))
- "\\"
- >>> print(json.dumps({"c": 0, "b": 0, "a": 0}, sort_keys=True))
- {"a": 0, "b": 0, "c": 0}
- >>> from io import StringIO
- >>> io = StringIO()
- >>> json.dump(['streaming API'], io)
- >>> io.getvalue()
- '["streaming API"]'
- Compact encoding::
- >>> import json
- >>> mydict = {'4': 5, '6': 7}
- >>> json.dumps([1,2,3,mydict], separators=(',', ':'))
- '[1,2,3,{"4":5,"6":7}]'
- Pretty printing::
- >>> import json
- >>> print(json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=4))
- {
- "4": 5,
- "6": 7
- }
- Decoding JSON::
- >>> import json
- >>> obj = ['foo', {'bar': ['baz', None, 1.0, 2]}]
- >>> json.loads('["foo", {"bar":["baz", null, 1.0, 2]}]') == obj
- True
- >>> json.loads('"\\"foo\\bar"') == '"foo\x08ar'
- True
- >>> from io import StringIO
- >>> io = StringIO('["streaming API"]')
- >>> json.load(io)[0] == 'streaming API'
- True
- Specializing JSON object decoding::
- >>> import json
- >>> def as_complex(dct):
- ... if '__complex__' in dct:
- ... return complex(dct['real'], dct['imag'])
- ... return dct
- ...
- >>> json.loads('{"__complex__": true, "real": 1, "imag": 2}',
- ... object_hook=as_complex)
- (1+2j)
- >>> from decimal import Decimal
- >>> json.loads('1.1', parse_float=Decimal) == Decimal('1.1')
- True
- Specializing JSON object encoding::
- >>> import json
- >>> def encode_complex(obj):
- ... if isinstance(obj, complex):
- ... return [obj.real, obj.imag]
- ... raise TypeError(f'Object of type {obj.__class__.__name__} '
- ... f'is not JSON serializable')
- ...
- >>> json.dumps(2 + 1j, default=encode_complex)
- '[2.0, 1.0]'
- >>> json.JSONEncoder(default=encode_complex).encode(2 + 1j)
- '[2.0, 1.0]'
- >>> ''.join(json.JSONEncoder(default=encode_complex).iterencode(2 + 1j))
- '[2.0, 1.0]'
- Using json.tool from the shell to validate and pretty-print::
- $ echo '{"json":"obj"}' | python -m json.tool
- {
- "json": "obj"
- }
- $ echo '{ 1.2:3.4}' | python -m json.tool
- Expecting property name enclosed in double quotes: line 1 column 3 (char 2)
- """
- __version__ = '2.0.9'
- __all__ = [
- 'dump', 'dumps', 'load', 'loads',
- 'JSONDecoder', 'JSONDecodeError', 'JSONEncoder',
- ]
- __author__ = 'Bob Ippolito <bob@redivi.com>'
- from .decoder import JSONDecoder, JSONDecodeError
- from .encoder import JSONEncoder
- import codecs
- _default_encoder = JSONEncoder(
- skipkeys=False,
- ensure_ascii=True,
- check_circular=True,
- allow_nan=True,
- indent=None,
- separators=None,
- default=None,
- )
- def dump(obj, fp, *, skipkeys=False, ensure_ascii=True, check_circular=True,
- allow_nan=True, cls=None, indent=None, separators=None,
- default=None, sort_keys=False, **kw):
- """Serialize ``obj`` as a JSON formatted stream to ``fp`` (a
- ``.write()``-supporting file-like object).
- If ``skipkeys`` is true then ``dict`` keys that are not basic types
- (``str``, ``int``, ``float``, ``bool``, ``None``) will be skipped
- instead of raising a ``TypeError``.
- If ``ensure_ascii`` is false, then the strings written to ``fp`` can
- contain non-ASCII characters if they appear in strings contained in
- ``obj``. Otherwise, all such characters are escaped in JSON strings.
- If ``check_circular`` is false, then the circular reference check
- for container types will be skipped and a circular reference will
- result in an ``RecursionError`` (or worse).
- If ``allow_nan`` is false, then it will be a ``ValueError`` to
- serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``)
- in strict compliance of the JSON specification, instead of using the
- JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).
- If ``indent`` is a non-negative integer, then JSON array elements and
- object members will be pretty-printed with that indent level. An indent
- level of 0 will only insert newlines. ``None`` is the most compact
- representation.
- If specified, ``separators`` should be an ``(item_separator, key_separator)``
- tuple. The default is ``(', ', ': ')`` if *indent* is ``None`` and
- ``(',', ': ')`` otherwise. To get the most compact JSON representation,
- you should specify ``(',', ':')`` to eliminate whitespace.
- ``default(obj)`` is a function that should return a serializable version
- of obj or raise TypeError. The default simply raises TypeError.
- If *sort_keys* is true (default: ``False``), then the output of
- dictionaries will be sorted by key.
- To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the
- ``.default()`` method to serialize additional types), specify it with
- the ``cls`` kwarg; otherwise ``JSONEncoder`` is used.
- """
- # cached encoder
- if (not skipkeys and ensure_ascii and
- check_circular and allow_nan and
- cls is None and indent is None and separators is None and
- default is None and not sort_keys and not kw):
- iterable = _default_encoder.iterencode(obj)
- else:
- if cls is None:
- cls = JSONEncoder
- iterable = cls(skipkeys=skipkeys, ensure_ascii=ensure_ascii,
- check_circular=check_circular, allow_nan=allow_nan, indent=indent,
- separators=separators,
- default=default, sort_keys=sort_keys, **kw).iterencode(obj)
- # could accelerate with writelines in some versions of Python, at
- # a debuggability cost
- for chunk in iterable:
- fp.write(chunk)
- def dumps(obj, *, skipkeys=False, ensure_ascii=True, check_circular=True,
- allow_nan=True, cls=None, indent=None, separators=None,
- default=None, sort_keys=False, **kw):
- """Serialize ``obj`` to a JSON formatted ``str``.
- If ``skipkeys`` is true then ``dict`` keys that are not basic types
- (``str``, ``int``, ``float``, ``bool``, ``None``) will be skipped
- instead of raising a ``TypeError``.
- If ``ensure_ascii`` is false, then the return value can contain non-ASCII
- characters if they appear in strings contained in ``obj``. Otherwise, all
- such characters are escaped in JSON strings.
- If ``check_circular`` is false, then the circular reference check
- for container types will be skipped and a circular reference will
- result in an ``RecursionError`` (or worse).
- If ``allow_nan`` is false, then it will be a ``ValueError`` to
- serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``) in
- strict compliance of the JSON specification, instead of using the
- JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).
- If ``indent`` is a non-negative integer, then JSON array elements and
- object members will be pretty-printed with that indent level. An indent
- level of 0 will only insert newlines. ``None`` is the most compact
- representation.
- If specified, ``separators`` should be an ``(item_separator, key_separator)``
- tuple. The default is ``(', ', ': ')`` if *indent* is ``None`` and
- ``(',', ': ')`` otherwise. To get the most compact JSON representation,
- you should specify ``(',', ':')`` to eliminate whitespace.
- ``default(obj)`` is a function that should return a serializable version
- of obj or raise TypeError. The default simply raises TypeError.
- If *sort_keys* is true (default: ``False``), then the output of
- dictionaries will be sorted by key.
- To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the
- ``.default()`` method to serialize additional types), specify it with
- the ``cls`` kwarg; otherwise ``JSONEncoder`` is used.
- """
- # cached encoder
- if (not skipkeys and ensure_ascii and
- check_circular and allow_nan and
- cls is None and indent is None and separators is None and
- default is None and not sort_keys and not kw):
- return _default_encoder.encode(obj)
- if cls is None:
- cls = JSONEncoder
- return cls(
- skipkeys=skipkeys, ensure_ascii=ensure_ascii,
- check_circular=check_circular, allow_nan=allow_nan, indent=indent,
- separators=separators, default=default, sort_keys=sort_keys,
- **kw).encode(obj)
- _default_decoder = JSONDecoder(object_hook=None, object_pairs_hook=None)
- def detect_encoding(b):
- bstartswith = b.startswith
- if bstartswith((codecs.BOM_UTF32_BE, codecs.BOM_UTF32_LE)):
- return 'utf-32'
- if bstartswith((codecs.BOM_UTF16_BE, codecs.BOM_UTF16_LE)):
- return 'utf-16'
- if bstartswith(codecs.BOM_UTF8):
- return 'utf-8-sig'
- if len(b) >= 4:
- if not b[0]:
- # 00 00 -- -- - utf-32-be
- # 00 XX -- -- - utf-16-be
- return 'utf-16-be' if b[1] else 'utf-32-be'
- if not b[1]:
- # XX 00 00 00 - utf-32-le
- # XX 00 00 XX - utf-16-le
- # XX 00 XX -- - utf-16-le
- return 'utf-16-le' if b[2] or b[3] else 'utf-32-le'
- elif len(b) == 2:
- if not b[0]:
- # 00 XX - utf-16-be
- return 'utf-16-be'
- if not b[1]:
- # XX 00 - utf-16-le
- return 'utf-16-le'
- # default
- return 'utf-8'
- def load(fp, *, cls=None, object_hook=None, parse_float=None,
- parse_int=None, parse_constant=None, object_pairs_hook=None, **kw):
- """Deserialize ``fp`` (a ``.read()``-supporting file-like object containing
- a JSON document) to a Python object.
- ``object_hook`` is an optional function that will be called with the
- result of any object literal decode (a ``dict``). The return value of
- ``object_hook`` will be used instead of the ``dict``. This feature
- can be used to implement custom decoders (e.g. JSON-RPC class hinting).
- ``object_pairs_hook`` is an optional function that will be called with the
- result of any object literal 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. If ``object_hook``
- is also defined, the ``object_pairs_hook`` takes priority.
- To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
- kwarg; otherwise ``JSONDecoder`` is used.
- """
- return loads(fp.read(),
- cls=cls, object_hook=object_hook,
- parse_float=parse_float, parse_int=parse_int,
- parse_constant=parse_constant, object_pairs_hook=object_pairs_hook, **kw)
- def loads(s, *, cls=None, object_hook=None, parse_float=None,
- parse_int=None, parse_constant=None, object_pairs_hook=None, **kw):
- """Deserialize ``s`` (a ``str``, ``bytes`` or ``bytearray`` instance
- containing a JSON document) to a Python object.
- ``object_hook`` is an optional function that will be called with the
- result of any object literal decode (a ``dict``). The return value of
- ``object_hook`` will be used instead of the ``dict``. This feature
- can be used to implement custom decoders (e.g. JSON-RPC class hinting).
- ``object_pairs_hook`` is an optional function that will be called with the
- result of any object literal 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. If ``object_hook``
- is also defined, the ``object_pairs_hook`` takes priority.
- ``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
- are encountered.
- To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
- kwarg; otherwise ``JSONDecoder`` is used.
- """
- if isinstance(s, str):
- if s.startswith('\ufeff'):
- raise JSONDecodeError("Unexpected UTF-8 BOM (decode using utf-8-sig)",
- s, 0)
- else:
- if not isinstance(s, (bytes, bytearray)):
- raise TypeError(f'the JSON object must be str, bytes or bytearray, '
- f'not {s.__class__.__name__}')
- s = s.decode(detect_encoding(s), 'surrogatepass')
- if (cls is None and object_hook is None and
- parse_int is None and parse_float is None and
- parse_constant is None and object_pairs_hook is None and not kw):
- return _default_decoder.decode(s)
- if cls is None:
- cls = JSONDecoder
- if object_hook is not None:
- kw['object_hook'] = object_hook
- if object_pairs_hook is not None:
- kw['object_pairs_hook'] = object_pairs_hook
- if parse_float is not None:
- kw['parse_float'] = parse_float
- if parse_int is not None:
- kw['parse_int'] = parse_int
- if parse_constant is not None:
- kw['parse_constant'] = parse_constant
- return cls(**kw).decode(s)
|