diff options
Diffstat (limited to 'Lib/json/__init__.py')
| -rw-r--r-- | Lib/json/__init__.py | 159 |
1 files changed, 71 insertions, 88 deletions
diff --git a/Lib/json/__init__.py b/Lib/json/__init__.py index 1ccde87..6a18518 100644 --- a/Lib/json/__init__.py +++ b/Lib/json/__init__.py @@ -1,11 +1,13 @@ -r"""A simple, fast, extensible JSON encoder and decoder - -JSON (JavaScript Object Notation) <http://json.org> is a subset of +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. -json exposes an API familiar to uses of the standard library -marshal and pickle modules. +:mod:`json` exposes an API familiar to users of the standard library +:mod:`marshal` and :mod:`pickle` modules. It is the externally maintained +version of the :mod:`json` library contained in Python 2.6, but maintains +compatibility with Python 2.4 and Python 2.5 and (currently) has +significant performance advantages, even without using the optional C +extension for speedups. Encoding basic Python object hierarchies:: @@ -32,23 +34,28 @@ Compact encoding:: >>> json.dumps([1,2,3,{'4': 5, '6': 7}], separators=(',',':')) '[1,2,3,{"4":5,"6":7}]' -Pretty printing (using repr() because of extraneous whitespace in the output):: +Pretty printing:: >>> import json - >>> print(repr(json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=4))) - '{\n "4": 5, \n "6": 7\n}' + >>> s = json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=4) + >>> print('\n'.join([l.rstrip() for l in s.splitlines()])) + { + "4": 5, + "6": 7 + } Decoding JSON:: >>> import json - >>> json.loads('["foo", {"bar":["baz", null, 1.0, 2]}]') - ['foo', {'bar': ['baz', None, 1.0, 2]}] - >>> json.loads('"\\"foo\\bar"') - '"foo\x08ar' + >>> 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) - ['streaming API'] + >>> json.load(io)[0] == 'streaming API' + True Specializing JSON object decoding:: @@ -61,43 +68,36 @@ Specializing JSON object decoding:: >>> json.loads('{"__complex__": true, "real": 1, "imag": 2}', ... object_hook=as_complex) (1+2j) - >>> import decimal - >>> json.loads('1.1', parse_float=decimal.Decimal) - Decimal('1.1') + >>> from decimal import Decimal + >>> json.loads('1.1', parse_float=Decimal) == Decimal('1.1') + True -Extending JSONEncoder:: +Specializing JSON object encoding:: >>> import json - >>> class ComplexEncoder(json.JSONEncoder): - ... def default(self, obj): - ... if isinstance(obj, complex): - ... return [obj.real, obj.imag] - ... return json.JSONEncoder.default(self, obj) + >>> def encode_complex(obj): + ... if isinstance(obj, complex): + ... return [obj.real, obj.imag] + ... raise TypeError(repr(o) + " is not JSON serializable") ... - >>> dumps(2 + 1j, cls=ComplexEncoder) + >>> json.dumps(2 + 1j, default=encode_complex) + '[2.0, 1.0]' + >>> json.JSONEncoder(default=encode_complex).encode(2 + 1j) '[2.0, 1.0]' - >>> ComplexEncoder().encode(2 + 1j) + >>> ''.join(json.JSONEncoder(default=encode_complex).iterencode(2 + 1j)) '[2.0, 1.0]' - >>> list(ComplexEncoder().iterencode(2 + 1j)) - ['[', '2.0', ', ', '1.0', ']'] -Using json.tool from the shell to validate and -pretty-print:: +Using json.tool from the shell to validate and pretty-print:: - $ echo '{"json":"obj"}' | python -mjson.tool + $ echo '{"json":"obj"}' | python -m json.tool { "json": "obj" } - $ echo '{ 1.2:3.4}' | python -mjson.tool + $ echo '{ 1.2:3.4}' | python -m json.tool Expecting property name: line 1 column 2 (char 2) - -Note that the JSON produced by this module's default settings -is a subset of YAML, so it may be used as a serializer for that as well. - """ - -__version__ = '1.9' +__version__ = '2.0.9' __all__ = [ 'dump', 'dumps', 'load', 'loads', 'JSONDecoder', 'JSONEncoder', @@ -115,45 +115,43 @@ _default_encoder = JSONEncoder( allow_nan=True, indent=None, separators=None, - encoding='utf-8', default=None, ) def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True, allow_nan=True, cls=None, indent=None, separators=None, - encoding='utf-8', default=None, **kw): + default=None, **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``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``) - will be skipped instead of raising a ``TypeError``. + If ``skipkeys`` is true then ``dict`` keys that are not basic types + (``str``, ``unicode``, ``int``, ``float``, ``bool``, ``None``) will be + skipped instead of raising a ``TypeError``. - If ``ensure_ascii`` is ``False``, then the some chunks written to ``fp`` + If ``ensure_ascii`` is false, then the some chunks written to ``fp`` may be ``unicode`` instances, subject to normal Python ``str`` to ``unicode`` coercion rules. Unless ``fp.write()`` explicitly understands ``unicode`` (as in ``codecs.getwriter()``) this is likely to cause an error. - If ``check_circular`` is ``False``, then the circular reference check + If ``check_circular`` is false, then the circular reference check for container types will be skipped and a circular reference will result in an ``OverflowError`` (or worse). - If ``allow_nan`` is ``False``, then it will be a ``ValueError`` to + 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 ``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 ``separators`` is an ``(item_separator, dict_separator)`` tuple then it will be used instead of the default ``(', ', ': ')`` separators. ``(',', ':')`` is the most compact JSON representation. - ``encoding`` is the character encoding for str instances, default is UTF-8. - ``default(obj)`` is a function that should return a serializable version of obj or raise TypeError. The default simply raises TypeError. @@ -163,17 +161,17 @@ def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True, """ # cached encoder - if (skipkeys is False and ensure_ascii is True and - check_circular is True and allow_nan is True and + 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 - encoding == 'utf-8' and default is None and not kw): + default is None 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, encoding=encoding, + separators=separators, default=default, **kw).iterencode(obj) # could accelerate with writelines in some versions of Python, at # a debuggability cost @@ -183,22 +181,22 @@ def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True, def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True, allow_nan=True, cls=None, indent=None, separators=None, - encoding='utf-8', default=None, **kw): + default=None, **kw): """Serialize ``obj`` to a JSON formatted ``str``. - If ``skipkeys`` is ``True`` then ``dict`` keys that are not basic types - (``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``) - will be skipped instead of raising a ``TypeError``. + If ``skipkeys`` is false then ``dict`` keys that are not basic types + (``str``, ``unicode``, ``int``, ``float``, ``bool``, ``None``) will be + skipped instead of raising a ``TypeError``. - If ``ensure_ascii`` is ``False``, then the return value will be a + If ``ensure_ascii`` is false, then the return value will be a ``unicode`` instance subject to normal Python ``str`` to ``unicode`` coercion rules instead of being escaped to an ASCII ``str``. - If ``check_circular`` is ``False``, then the circular reference check + If ``check_circular`` is false, then the circular reference check for container types will be skipped and a circular reference will result in an ``OverflowError`` (or worse). - If ``allow_nan`` is ``False``, then it will be a ``ValueError`` to + 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``). @@ -212,8 +210,6 @@ def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True, then it will be used instead of the default ``(', ', ': ')`` separators. ``(',', ':')`` is the most compact JSON representation. - ``encoding`` is the character encoding for str instances, default is UTF-8. - ``default(obj)`` is a function that should return a serializable version of obj or raise TypeError. The default simply raises TypeError. @@ -223,35 +219,27 @@ def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True, """ # cached encoder - if (skipkeys is False and ensure_ascii is True and - check_circular is True and allow_nan is True and + 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 - encoding == 'utf-8' and default is None and not kw): + default is None 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, encoding=encoding, default=default, + separators=separators, default=default, **kw).encode(obj) -_default_decoder = JSONDecoder(encoding=None, object_hook=None, - object_pairs_hook=None) +_default_decoder = JSONDecoder(object_hook=None, object_pairs_hook=None) -def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None, +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. - - If the contents of ``fp`` is encoded with an ASCII based encoding other - than utf-8 (e.g. latin-1), then an appropriate ``encoding`` name must - be specified. Encodings that are not ASCII based (such as UCS-2) are - not allowed, and should be wrapped with - ``codecs.getreader(fp)(encoding)``, or simply decoded to a ``unicode`` - object and passed to ``loads()`` + """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 @@ -263,21 +251,16 @@ def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None, """ return loads(fp.read(), - encoding=encoding, cls=cls, object_hook=object_hook, + 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, encoding=None, cls=None, object_hook=None, parse_float=None, parse_int=None, parse_constant=None, object_pairs_hook=None, **kw): - """Deserialize ``s`` (a ``str`` or ``unicode`` instance containing a JSON + """Deserialize ``s`` (a ``str`` instance containing a JSON document) to a Python object. - If ``s`` is a ``str`` instance and is encoded with an ASCII based encoding - other than utf-8 (e.g. latin-1) then an appropriate ``encoding`` name - must be specified. Encodings that are not ASCII based (such as UCS-2) - are not allowed and should be decoded to ``unicode`` first. - ``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 @@ -302,7 +285,7 @@ def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None, kwarg. """ - if (cls is None and encoding is None and object_hook is None and + 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) @@ -318,4 +301,4 @@ def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None, kw['parse_int'] = parse_int if parse_constant is not None: kw['parse_constant'] = parse_constant - return cls(encoding=encoding, **kw).decode(s) + return cls(**kw).decode(s) |