mirror of https://github.com/perkeep/perkeep.git
438 lines
17 KiB
Python
438 lines
17 KiB
Python
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:`simplejson` 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::
|
|
|
|
>>> import simplejson as 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(u'\u1234')
|
|
"\u1234"
|
|
>>> print json.dumps('\\')
|
|
"\\"
|
|
>>> print json.dumps({"c": 0, "b": 0, "a": 0}, sort_keys=True)
|
|
{"a": 0, "b": 0, "c": 0}
|
|
>>> from StringIO import StringIO
|
|
>>> io = StringIO()
|
|
>>> json.dump(['streaming API'], io)
|
|
>>> io.getvalue()
|
|
'["streaming API"]'
|
|
|
|
Compact encoding::
|
|
|
|
>>> import simplejson as json
|
|
>>> json.dumps([1,2,3,{'4': 5, '6': 7}], separators=(',',':'))
|
|
'[1,2,3,{"4":5,"6":7}]'
|
|
|
|
Pretty printing::
|
|
|
|
>>> import simplejson as json
|
|
>>> s = json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=' ')
|
|
>>> print '\n'.join([l.rstrip() for l in s.splitlines()])
|
|
{
|
|
"4": 5,
|
|
"6": 7
|
|
}
|
|
|
|
Decoding JSON::
|
|
|
|
>>> import simplejson as json
|
|
>>> obj = [u'foo', {u'bar': [u'baz', None, 1.0, 2]}]
|
|
>>> json.loads('["foo", {"bar":["baz", null, 1.0, 2]}]') == obj
|
|
True
|
|
>>> json.loads('"\\"foo\\bar"') == u'"foo\x08ar'
|
|
True
|
|
>>> from StringIO import StringIO
|
|
>>> io = StringIO('["streaming API"]')
|
|
>>> json.load(io)[0] == 'streaming API'
|
|
True
|
|
|
|
Specializing JSON object decoding::
|
|
|
|
>>> import simplejson as 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 simplejson as json
|
|
>>> def encode_complex(obj):
|
|
... if isinstance(obj, complex):
|
|
... return [obj.real, obj.imag]
|
|
... raise TypeError(repr(o) + " 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 simplejson.tool from the shell to validate and pretty-print::
|
|
|
|
$ echo '{"json":"obj"}' | python -m simplejson.tool
|
|
{
|
|
"json": "obj"
|
|
}
|
|
$ echo '{ 1.2:3.4}' | python -m simplejson.tool
|
|
Expecting property name: line 1 column 2 (char 2)
|
|
"""
|
|
__version__ = '2.1.1'
|
|
__all__ = [
|
|
'dump', 'dumps', 'load', 'loads',
|
|
'JSONDecoder', 'JSONDecodeError', 'JSONEncoder',
|
|
'OrderedDict',
|
|
]
|
|
|
|
__author__ = 'Bob Ippolito <bob@redivi.com>'
|
|
|
|
from decimal import Decimal
|
|
|
|
from decoder import JSONDecoder, JSONDecodeError
|
|
from encoder import JSONEncoder
|
|
def _import_OrderedDict():
|
|
import collections
|
|
try:
|
|
return collections.OrderedDict
|
|
except AttributeError:
|
|
import ordered_dict
|
|
return ordered_dict.OrderedDict
|
|
OrderedDict = _import_OrderedDict()
|
|
|
|
def _import_c_make_encoder():
|
|
try:
|
|
from simplejson._speedups import make_encoder
|
|
return make_encoder
|
|
except ImportError:
|
|
return None
|
|
|
|
_default_encoder = JSONEncoder(
|
|
skipkeys=False,
|
|
ensure_ascii=True,
|
|
check_circular=True,
|
|
allow_nan=True,
|
|
indent=None,
|
|
separators=None,
|
|
encoding='utf-8',
|
|
default=None,
|
|
use_decimal=False,
|
|
)
|
|
|
|
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, use_decimal=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``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
|
|
will be skipped instead of raising a ``TypeError``.
|
|
|
|
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
|
|
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
|
|
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 string, then JSON array elements and object members
|
|
will be pretty-printed with a newline followed by that string repeated
|
|
for each level of nesting. ``None`` (the default) selects the most compact
|
|
representation without any newlines. For backwards compatibility with
|
|
versions of simplejson earlier than 2.1.0, an integer is also accepted
|
|
and is converted to a string with that many spaces.
|
|
|
|
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.
|
|
|
|
If *use_decimal* is true (default: ``False``) then decimal.Decimal
|
|
will be natively serialized to JSON with full precision.
|
|
|
|
To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the
|
|
``.default()`` method to serialize additional types), specify it with
|
|
the ``cls`` kwarg.
|
|
|
|
"""
|
|
# 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
|
|
encoding == 'utf-8' and 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,
|
|
default=default, use_decimal=use_decimal, **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,
|
|
encoding='utf-8', default=None, use_decimal=False, **kw):
|
|
"""Serialize ``obj`` to a JSON formatted ``str``.
|
|
|
|
If ``skipkeys`` is false then ``dict`` keys that are not basic types
|
|
(``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
|
|
will be skipped instead of raising a ``TypeError``.
|
|
|
|
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
|
|
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
|
|
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 string, then JSON array elements and object members
|
|
will be pretty-printed with a newline followed by that string repeated
|
|
for each level of nesting. ``None`` (the default) selects the most compact
|
|
representation without any newlines. For backwards compatibility with
|
|
versions of simplejson earlier than 2.1.0, an integer is also accepted
|
|
and is converted to a string with that many spaces.
|
|
|
|
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.
|
|
|
|
If *use_decimal* is true (default: ``False``) then decimal.Decimal
|
|
will be natively serialized to JSON with full precision.
|
|
|
|
To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the
|
|
``.default()`` method to serialize additional types), specify it with
|
|
the ``cls`` kwarg.
|
|
|
|
"""
|
|
# 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
|
|
encoding == 'utf-8' and default is None and not use_decimal
|
|
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,
|
|
use_decimal=use_decimal, **kw).encode(obj)
|
|
|
|
|
|
_default_decoder = JSONDecoder(encoding=None, object_hook=None,
|
|
object_pairs_hook=None)
|
|
|
|
|
|
def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None,
|
|
parse_int=None, parse_constant=None, object_pairs_hook=None,
|
|
use_decimal=False, **kw):
|
|
"""Deserialize ``fp`` (a ``.read()``-supporting file-like object containing
|
|
a JSON document) to a Python object.
|
|
|
|
*encoding* determines the encoding used to interpret any
|
|
:class:`str` objects decoded by this instance (``'utf-8'`` by
|
|
default). It has no effect when decoding :class:`unicode` objects.
|
|
|
|
Note that currently only encodings that are a superset of ASCII work,
|
|
strings of other encodings should be passed in as :class:`unicode`.
|
|
|
|
*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 :class:`dict`. This can be used to provide custom
|
|
deserializations (e.g. to support JSON-RPC class hinting).
|
|
|
|
*object_pairs_hook* is an optional function that will be called with
|
|
the result of any object literal decode with an ordered list of pairs.
|
|
The return value of *object_pairs_hook* will be used instead of the
|
|
:class:`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, :func:`collections.OrderedDict` will remember the order of
|
|
insertion). 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. :class:`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. :class:`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.
|
|
|
|
If *use_decimal* is true (default: ``False``) then it implies
|
|
parse_float=decimal.Decimal for parity with ``dump``.
|
|
|
|
To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
|
|
kwarg.
|
|
|
|
"""
|
|
return loads(fp.read(),
|
|
encoding=encoding, cls=cls, object_hook=object_hook,
|
|
parse_float=parse_float, parse_int=parse_int,
|
|
parse_constant=parse_constant, object_pairs_hook=object_pairs_hook,
|
|
use_decimal=use_decimal, **kw)
|
|
|
|
|
|
def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None,
|
|
parse_int=None, parse_constant=None, object_pairs_hook=None,
|
|
use_decimal=False, **kw):
|
|
"""Deserialize ``s`` (a ``str`` or ``unicode`` instance containing a JSON
|
|
document) to a Python object.
|
|
|
|
*encoding* determines the encoding used to interpret any
|
|
:class:`str` objects decoded by this instance (``'utf-8'`` by
|
|
default). It has no effect when decoding :class:`unicode` objects.
|
|
|
|
Note that currently only encodings that are a superset of ASCII work,
|
|
strings of other encodings should be passed in as :class:`unicode`.
|
|
|
|
*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 :class:`dict`. This can be used to provide custom
|
|
deserializations (e.g. to support JSON-RPC class hinting).
|
|
|
|
*object_pairs_hook* is an optional function that will be called with
|
|
the result of any object literal decode with an ordered list of pairs.
|
|
The return value of *object_pairs_hook* will be used instead of the
|
|
:class:`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, :func:`collections.OrderedDict` will remember the order of
|
|
insertion). 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. :class:`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. :class:`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.
|
|
|
|
If *use_decimal* is true (default: ``False``) then it implies
|
|
parse_float=decimal.Decimal for parity with ``dump``.
|
|
|
|
To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
|
|
kwarg.
|
|
|
|
"""
|
|
if (cls is None and encoding 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 use_decimal 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
|
|
if use_decimal:
|
|
if parse_float is not None:
|
|
raise TypeError("use_decimal=True implies parse_float=Decimal")
|
|
kw['parse_float'] = Decimal
|
|
return cls(encoding=encoding, **kw).decode(s)
|
|
|
|
|
|
def _toggle_speedups(enabled):
|
|
import simplejson.decoder as dec
|
|
import simplejson.encoder as enc
|
|
import simplejson.scanner as scan
|
|
c_make_encoder = _import_c_make_encoder()
|
|
if enabled:
|
|
dec.scanstring = dec.c_scanstring or dec.py_scanstring
|
|
enc.c_make_encoder = c_make_encoder
|
|
enc.encode_basestring_ascii = (enc.c_encode_basestring_ascii or
|
|
enc.py_encode_basestring_ascii)
|
|
scan.make_scanner = scan.c_make_scanner or scan.py_make_scanner
|
|
else:
|
|
dec.scanstring = dec.py_scanstring
|
|
enc.c_make_encoder = None
|
|
enc.encode_basestring_ascii = enc.py_encode_basestring_ascii
|
|
scan.make_scanner = scan.py_make_scanner
|
|
dec.make_scanner = scan.make_scanner
|
|
global _default_decoder
|
|
_default_decoder = JSONDecoder(
|
|
encoding=None,
|
|
object_hook=None,
|
|
object_pairs_hook=None,
|
|
)
|
|
global _default_encoder
|
|
_default_encoder = JSONEncoder(
|
|
skipkeys=False,
|
|
ensure_ascii=True,
|
|
check_circular=True,
|
|
allow_nan=True,
|
|
indent=None,
|
|
separators=None,
|
|
encoding='utf-8',
|
|
default=None,
|
|
)
|