This commit is contained in:
jcgregorio@wpgntai-ubiq72.hot.corp.google.com
2010-04-19 11:12:52 -07:00
commit ed1325284e
48 changed files with 5522 additions and 0 deletions

396
discovery.json Normal file
View File

@@ -0,0 +1,396 @@
{
"data": {
"buzz": {
"0.1": {
"baseUrl": "https://apiary-test.corp.google.com/",
"resources": {
"feeds": {
"methods": {
"list": {
"pathUrl": "buzz/v1/feeds/{userId}/{scope}",
"rpcName": "chili.feeds.list",
"httpMethod": "GET",
"methodType": "rest",
"parameters": {
"scope": {
"parameterType": "path",
"pattern": "@.*"
},
"userId": {
"parameterType": "path"
}
}
},
"delete": {
"pathUrl": "buzz/v1/feeds/{userId}/@self/{siteId}",
"rpcName": "chili.feeds.delete",
"httpMethod": "DELETE",
"methodType": "rest",
"parameters": {
"siteId": {
"parameterType": "path"
},
"userId": {
"parameterType": "path"
}
}
},
"insert": {
"pathUrl": "buzz/v1/feeds/{userId}/@self",
"rpcName": "chili.feeds.insert",
"httpMethod": "POST",
"methodType": "rest",
"parameters": {
"userId": {
"parameterType": "path"
}
}
},
"update": {
"pathUrl": "buzz/v1/feeds/{userId}/@self/{siteId}",
"rpcName": "chili.feeds.update",
"httpMethod": "PUT",
"methodType": "rest",
"parameters": {
"siteId": {
"parameterType": "path"
},
"max-results": {
"parameterType": "query"
},
"c": {
"parameterType": "query"
},
"userId": {
"parameterType": "path"
}
}
}
}
},
"activities": {
"methods": {
"update": {
"pathUrl": "buzz/v1/activities/{userId}/{scope}/{postId}",
"rpcName": "chili.activities.update",
"httpMethod": "PUT",
"methodType": "rest",
"parameters": {
"scope": {
"parameterType": "path",
"pattern": "@.*"
},
"userId": {
"parameterType": "path"
},
"postId": {
"parameterType": "path"
}
}
},
"delete": {
"pathUrl": "buzz/v1/activities/{userId}/{scope}/{postId}",
"rpcName": "chili.activities.delete",
"httpMethod": "DELETE",
"methodType": "rest",
"parameters": {
"scope": {
"parameterType": "path",
"pattern": "@.*"
},
"userId": {
"parameterType": "path"
},
"postId": {
"parameterType": "path"
}
}
},
"list": {
"pathUrl": "buzz/v1/activities/{userId}/{scope}",
"rpcName": "chili.activities.list",
"httpMethod": "GET",
"methodType": "rest",
"parameters": {
"scope": {
"parameterType": "path",
"pattern": "@.*"
},
"max-results": {
"parameterType": "query"
},
"c": {
"parameterType": "query"
},
"userId": {
"parameterType": "path"
}
}
},
"insert": {
"pathUrl": "buzz/v1/activities/{userId}/@self",
"rpcName": "chili.activities.insert",
"httpMethod": "POST",
"methodType": "rest",
"parameters": {
"preview": {
"parameterType": "query"
},
"userId": {
"parameterType": "path"
}
}
},
"get": {
"pathUrl": "buzz/v1/activities/{userId}/@self/{postId}",
"rpcName": "chili.activities.get",
"httpMethod": "GET",
"methodType": "rest",
"parameters": {
"userId": {
"parameterType": "path"
},
"postId": {
"parameterType": "path"
}
}
},
"search": {
"pathUrl": "buzz/v1/activities/search",
"rpcName": "chili.activities.search",
"httpMethod": "GET",
"methodType": "rest",
"parameters": {
"geocode": {
"parameterType": "query"
},
"max-results": {
"parameterType": "query"
},
"c": {
"parameterType": "query"
},
"q": {
"parameterType": "query"
}
}
}
}
},
"people": {
"methods": {
"list": {
"pathUrl": "buzz/v1/people/{userId}/{scope}",
"rpcName": "chili.people.list",
"httpMethod": "GET",
"methodType": "rest",
"parameters": {
"scope": {
"parameterType": "path",
"pattern": "@.*"
},
"max-results": {
"parameterType": "query"
},
"c": {
"parameterType": "query"
},
"userId": {
"parameterType": "path"
}
}
},
"delete": {
"pathUrl": "buzz/v1/people/{userId}/{scope}/{personId}",
"rpcName": "chili.people.delete",
"httpMethod": "DELETE",
"methodType": "rest",
"parameters": {
"scope": {
"parameterType": "path",
"pattern": "@.*"
},
"userId": {
"parameterType": "path"
},
"personId": {
"parameterType": "path"
}
}
},
"get": {
"pathUrl": "buzz/v1/people/{userId}/@self",
"rpcName": "chili.people.get",
"httpMethod": "GET",
"methodType": "rest",
"parameters": {
"userId": {
"parameterType": "path"
}
}
},
"update": {
"pathUrl": "buzz/v1/people/{userId/{scope}/{personId}",
"rpcName": "chili.people.update",
"httpMethod": "PUT",
"methodType": "rest",
"parameters": {
"scope": {
"parameterType": "query"
},
"userId": {
"parameterType": "query"
},
"personId": {
"parameterType": "path"
}
}
}
}
},
"groups": {
"methods": {
"get": {
"pathUrl": "buzz/v1/groups/{userId}/{groupId}",
"rpcName": "chili.groups.get",
"httpMethod": "GET",
"methodType": "rest",
"parameters": {
"groupId": {
"parameterType": "path"
},
"userId": {
"parameterType": "path"
}
}
},
"list": {
"pathUrl": "buzz/v1/groups/{userId}",
"rpcName": "chili.groups.list",
"httpMethod": "GET",
"methodType": "rest",
"parameters": {
"max-results": {
"parameterType": "query"
},
"c": {
"parameterType": "query"
},
"userId": {
"parameterType": "path"
}
}
},
"delete": {
"pathUrl": "buzz/v1/groups/{userId}/{groupId}/{personId}",
"rpcName": "chili.groups.delete",
"httpMethod": "DELETE",
"methodType": "rest",
"parameters": {
"groupId": {
"parameterType": "path"
},
"userId": {
"parameterType": "path"
},
"personId": {
"parameterType": "path"
}
}
},
"update": {
"pathUrl": "buzz/v1/groups/{userId}/{groupId}/{personId}",
"rpcName": "chili.groups.update",
"httpMethod": "PUT",
"methodType": "rest",
"parameters": {
"groupId": {
"parameterType": "path"
},
"userId": {
"parameterType": "path"
},
"personId": {
"parameterType": "path"
}
}
}
}
},
"comments": {
"methods": {
"update": {
"pathUrl": "buzz/v1/activities/{userId}/@self/{postId}/@comments/{commentId}",
"rpcName": "chili.comments.update",
"httpMethod": "PUT",
"methodType": "rest",
"parameters": {
"userId": {
"parameterType": "path"
},
"commentId": {
"parameterType": "path"
},
"postId": {
"parameterType": "path"
}
}
},
"insert": {
"pathUrl": "buzz/v1/activities/{userId}/@self/{postId}/@comments",
"rpcName": "chili.comments.insert",
"httpMethod": "POST",
"methodType": "rest",
"parameters": {
"userId": {
"parameterType": "path"
},
"postId": {
"parameterType": "path"
}
}
},
"list": {
"pathUrl": "buzz/v1/activities/{userId}/@self/{postId}/@comments",
"rpcName": "chili.comments.list",
"httpMethod": "GET",
"methodType": "rest",
"parameters": {
"max-results": {
"parameterType": "query"
},
"c": {
"parameterType": "query"
},
"userId": {
"parameterType": "path"
},
"postId": {
"parameterType": "path"
}
}
},
"delete": {
"pathUrl": "buzz/v1/activities/{userId}/@self/{postId}/@comments/{commentId}",
"rpcName": "chili.comments.delete",
"httpMethod": "DELETE",
"methodType": "rest",
"parameters": {
"userId": {
"parameterType": "path"
},
"commentId": {
"parameterType": "path"
},
"postId": {
"parameterType": "path"
}
}
}
}
}
}
}
}
}
}

44
discovery.py Normal file
View File

@@ -0,0 +1,44 @@
#!/usr/bin/python2.4
#
# Copyright 2010 Google Inc. All Rights Reserved.
"""One-line documentation for discovery module.
A detailed description of discovery.
"""
__author__ = 'jcgregorio@google.com (Joe Gregorio)'
import simplejson
def discovery():
d = simplejson.load(open("discovery.json", "r"))
desc = d["data"]["buzz"]["0.1"]
base = desc["baseUrl"]
feeds = desc["resources"]["feeds"]
methods = feeds["methods"]
list_method = methods["list"]
print list_method
class Proto(object):
"""A class for interacting with a service"""
pass
def doList(self, scope, userId):
print "Hello"
setattr(doList, "__doc__", "A description of how to use this function")
setattr(Proto, "list", doList)
return Proto()
def main():
p = discovery()
p.list("foo", "bar")
print dir(p)
print help(p)
if __name__ == '__main__':
main()

BIN
simplejson/.__speedups.c Normal file

Binary file not shown.

BIN
simplejson/._decoder.py Normal file

Binary file not shown.

BIN
simplejson/._encoder.py Normal file

Binary file not shown.

Binary file not shown.

BIN
simplejson/._scanner.py Normal file

Binary file not shown.

BIN
simplejson/._tool.py Normal file

Binary file not shown.

437
simplejson/__init__.py Normal file
View File

@@ -0,0 +1,437 @@
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,
)

BIN
simplejson/__init__.pyc Normal file

Binary file not shown.

2561
simplejson/_speedups.c Normal file

File diff suppressed because it is too large Load Diff

421
simplejson/decoder.py Normal file
View File

@@ -0,0 +1,421 @@
"""Implementation of JSONDecoder
"""
import re
import sys
import struct
from simplejson.scanner import make_scanner
def _import_c_scanstring():
try:
from simplejson._speedups import scanstring
return scanstring
except ImportError:
return None
c_scanstring = _import_c_scanstring()
__all__ = ['JSONDecoder']
FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL
def _floatconstants():
_BYTES = '7FF80000000000007FF0000000000000'.decode('hex')
# The struct module in Python 2.4 would get frexp() out of range here
# when an endian is specified in the format string. Fixed in Python 2.5+
if sys.byteorder != 'big':
_BYTES = _BYTES[:8][::-1] + _BYTES[8:][::-1]
nan, inf = struct.unpack('dd', _BYTES)
return nan, inf, -inf
NaN, PosInf, NegInf = _floatconstants()
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
end: The end index of doc where parsing failed (may be None)
lineno: The line corresponding to pos
colno: The column corresponding to pos
endlineno: The line corresponding to end (may be None)
endcolno: The column corresponding to end (may be None)
"""
def __init__(self, msg, doc, pos, end=None):
ValueError.__init__(self, errmsg(msg, doc, pos, end=end))
self.msg = msg
self.doc = doc
self.pos = pos
self.end = end
self.lineno, self.colno = linecol(doc, pos)
if end is not None:
self.endlineno, self.endcolno = linecol(doc, pos)
else:
self.endlineno, self.endcolno = None, None
def linecol(doc, pos):
lineno = doc.count('\n', 0, pos) + 1
if lineno == 1:
colno = pos
else:
colno = pos - doc.rindex('\n', 0, pos)
return lineno, colno
def errmsg(msg, doc, pos, end=None):
# Note that this function is called from _speedups
lineno, colno = linecol(doc, pos)
if end is None:
#fmt = '{0}: line {1} column {2} (char {3})'
#return fmt.format(msg, lineno, colno, pos)
fmt = '%s: line %d column %d (char %d)'
return fmt % (msg, lineno, colno, pos)
endlineno, endcolno = linecol(doc, end)
#fmt = '{0}: line {1} column {2} - line {3} column {4} (char {5} - {6})'
#return fmt.format(msg, lineno, colno, endlineno, endcolno, pos, end)
fmt = '%s: line %d column %d - line %d column %d (char %d - %d)'
return fmt % (msg, lineno, colno, endlineno, endcolno, pos, end)
_CONSTANTS = {
'-Infinity': NegInf,
'Infinity': PosInf,
'NaN': NaN,
}
STRINGCHUNK = re.compile(r'(.*?)(["\\\x00-\x1f])', FLAGS)
BACKSLASH = {
'"': u'"', '\\': u'\\', '/': u'/',
'b': u'\b', 'f': u'\f', 'n': u'\n', 'r': u'\r', 't': u'\t',
}
DEFAULT_ENCODING = "utf-8"
def py_scanstring(s, end, encoding=None, 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."""
if encoding is None:
encoding = DEFAULT_ENCODING
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:
if not isinstance(content, unicode):
content = unicode(content, encoding)
_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: " + repr(esc)
raise JSONDecodeError(msg, s, end)
end += 1
else:
# Unicode escape sequence
esc = s[end + 1:end + 5]
next_end = end + 5
if len(esc) != 4:
msg = "Invalid \\uXXXX escape"
raise JSONDecodeError(msg, s, end)
uni = int(esc, 16)
# Check for surrogate pair on UCS-4 systems
if 0xd800 <= uni <= 0xdbff and sys.maxunicode > 65535:
msg = "Invalid \\uXXXX\\uXXXX surrogate pair"
if not s[end + 5:end + 7] == '\\u':
raise JSONDecodeError(msg, s, end)
esc2 = s[end + 7:end + 11]
if len(esc2) != 4:
raise JSONDecodeError(msg, s, end)
uni2 = int(esc2, 16)
uni = 0x10000 + (((uni - 0xd800) << 10) | (uni2 - 0xdc00))
next_end += 6
char = unichr(uni)
end = next_end
# Append the unescaped character
_append(char)
return u''.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, end), encoding, strict, scan_once, object_hook,
object_pairs_hook, memo=None,
_w=WHITESPACE.match, _ws=WHITESPACE_STR):
# Backwards compatibility
if memo is None:
memo = {}
memo_get = memo.setdefault
pairs = []
# 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 object_pairs_hook is not None:
result = object_pairs_hook(pairs)
return result, end
pairs = {}
if object_hook is not None:
pairs = object_hook(pairs)
return pairs, end + 1
elif nextchar != '"':
raise JSONDecodeError("Expecting property name", s, end)
end += 1
while True:
key, end = scanstring(s, end, encoding, 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:
raise JSONDecodeError("Expecting object", s, end)
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)
try:
nextchar = s[end]
if nextchar in _ws:
end += 1
nextchar = s[end]
if nextchar in _ws:
end = _w(s, end + 1).end()
nextchar = s[end]
except IndexError:
nextchar = ''
end += 1
if nextchar != '"':
raise JSONDecodeError("Expecting property name", s, end - 1)
if object_pairs_hook is not None:
result = object_pairs_hook(pairs)
return result, end
pairs = dict(pairs)
if object_hook is not None:
pairs = object_hook(pairs)
return pairs, end
def JSONArray((s, end), 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 == ']':
return values, end + 1
_append = values.append
while True:
try:
value, end = scan_once(s, end)
except StopIteration:
raise JSONDecodeError("Expecting object", s, end)
_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)
try:
if s[end] in _ws:
end += 1
if s[end] in _ws:
end = _w(s, end + 1).end()
except IndexError:
pass
return values, end
class JSONDecoder(object):
"""Simple JSON <http://json.org> decoder
Performs the following translations in decoding by default:
+---------------+-------------------+
| JSON | Python |
+===============+===================+
| object | dict |
+---------------+-------------------+
| array | list |
+---------------+-------------------+
| string | unicode |
+---------------+-------------------+
| number (int) | int, long |
+---------------+-------------------+
| number (real) | float |
+---------------+-------------------+
| true | True |
+---------------+-------------------+
| false | False |
+---------------+-------------------+
| null | None |
+---------------+-------------------+
It also understands ``NaN``, ``Infinity``, and ``-Infinity`` as
their corresponding ``float`` values, which is outside the JSON spec.
"""
def __init__(self, encoding=None, object_hook=None, parse_float=None,
parse_int=None, parse_constant=None, strict=True,
object_pairs_hook=None):
"""
*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.
*strict* controls the parser's behavior when it encounters an
invalid control character in a string. The default setting of
``True`` means that unescaped control characters are parse errors, if
``False`` then control characters will be allowed in strings.
"""
self.encoding = encoding
self.object_hook = object_hook
self.object_pairs_hook = object_pairs_hook
self.parse_float = parse_float or float
self.parse_int = parse_int or int
self.parse_constant = parse_constant or _CONSTANTS.__getitem__
self.strict = strict
self.parse_object = JSONObject
self.parse_array = JSONArray
self.parse_string = scanstring
self.memo = {}
self.scan_once = make_scanner(self)
def decode(self, s, _w=WHITESPACE.match):
"""Return the Python representation of ``s`` (a ``str`` or ``unicode``
instance containing a JSON document)
"""
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
end = _w(s, end).end()
if end != len(s):
raise JSONDecodeError("Extra data", s, end, len(s))
return obj
def raw_decode(self, s, idx=0):
"""Decode a JSON document from ``s`` (a ``str`` or ``unicode``
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.
"""
try:
obj, end = self.scan_once(s, idx)
except StopIteration:
raise JSONDecodeError("No JSON object could be decoded", s, idx)
return obj, end

BIN
simplejson/decoder.pyc Normal file

Binary file not shown.

501
simplejson/encoder.py Normal file
View File

@@ -0,0 +1,501 @@
"""Implementation of JSONEncoder
"""
import re
from decimal import Decimal
def _import_speedups():
try:
from simplejson import _speedups
return _speedups.encode_basestring_ascii, _speedups.make_encoder
except ImportError:
return None, None
c_encode_basestring_ascii, c_make_encoder = _import_speedups()
from simplejson.decoder import PosInf
ESCAPE = re.compile(r'[\x00-\x1f\\"\b\f\n\r\t]')
ESCAPE_ASCII = re.compile(r'([\\"]|[^\ -~])')
HAS_UTF8 = re.compile(r'[\x80-\xff]')
ESCAPE_DCT = {
'\\': '\\\\',
'"': '\\"',
'\b': '\\b',
'\f': '\\f',
'\n': '\\n',
'\r': '\\r',
'\t': '\\t',
}
for i in range(0x20):
#ESCAPE_DCT.setdefault(chr(i), '\\u{0:04x}'.format(i))
ESCAPE_DCT.setdefault(chr(i), '\\u%04x' % (i,))
FLOAT_REPR = repr
def encode_basestring(s):
"""Return a JSON representation of a Python string
"""
if isinstance(s, str) and HAS_UTF8.search(s) is not None:
s = s.decode('utf-8')
def replace(match):
return ESCAPE_DCT[match.group(0)]
return u'"' + ESCAPE.sub(replace, s) + u'"'
def py_encode_basestring_ascii(s):
"""Return an ASCII-only JSON representation of a Python string
"""
if isinstance(s, str) and HAS_UTF8.search(s) is not None:
s = s.decode('utf-8')
def replace(match):
s = match.group(0)
try:
return ESCAPE_DCT[s]
except KeyError:
n = ord(s)
if n < 0x10000:
#return '\\u{0:04x}'.format(n)
return '\\u%04x' % (n,)
else:
# surrogate pair
n -= 0x10000
s1 = 0xd800 | ((n >> 10) & 0x3ff)
s2 = 0xdc00 | (n & 0x3ff)
#return '\\u{0:04x}\\u{1:04x}'.format(s1, s2)
return '\\u%04x\\u%04x' % (s1, s2)
return '"' + str(ESCAPE_ASCII.sub(replace, s)) + '"'
encode_basestring_ascii = (
c_encode_basestring_ascii or py_encode_basestring_ascii)
class JSONEncoder(object):
"""Extensible JSON <http://json.org> encoder for Python data structures.
Supports the following objects and types by default:
+-------------------+---------------+
| Python | JSON |
+===================+===============+
| dict | object |
+-------------------+---------------+
| list, tuple | array |
+-------------------+---------------+
| str, unicode | string |
+-------------------+---------------+
| int, long, float | number |
+-------------------+---------------+
| True | true |
+-------------------+---------------+
| False | false |
+-------------------+---------------+
| None | null |
+-------------------+---------------+
To extend this to recognize other objects, subclass and implement a
``.default()`` method with another method that returns a serializable
object for ``o`` if possible, otherwise it should call the superclass
implementation (to raise ``TypeError``).
"""
item_separator = ', '
key_separator = ': '
def __init__(self, skipkeys=False, ensure_ascii=True,
check_circular=True, allow_nan=True, sort_keys=False,
indent=None, separators=None, encoding='utf-8', default=None,
use_decimal=False):
"""Constructor for JSONEncoder, with sensible defaults.
If skipkeys is false, then it is a TypeError to attempt
encoding of keys that are not str, int, long, float or None. If
skipkeys is True, such items are simply skipped.
If ensure_ascii is true, the output is guaranteed to be str
objects with all incoming unicode characters escaped. If
ensure_ascii is false, the output will be unicode object.
If check_circular is true, then lists, dicts, and custom encoded
objects will be checked for circular references during encoding to
prevent an infinite recursion (which would cause an OverflowError).
Otherwise, no such check takes place.
If allow_nan is true, then NaN, Infinity, and -Infinity will be
encoded as such. This behavior is not JSON specification compliant,
but is consistent with most JavaScript based encoders and decoders.
Otherwise, it will be a ValueError to encode such floats.
If sort_keys is true, then the output of dictionaries will be
sorted by key; this is useful for regression tests to ensure
that JSON serializations can be compared on a day-to-day basis.
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 specified, separators should be a (item_separator, key_separator)
tuple. The default is (', ', ': '). To get the most compact JSON
representation you should specify (',', ':') to eliminate whitespace.
If specified, default is a function that gets called for objects
that can't otherwise be serialized. It should return a JSON encodable
version of the object or raise a ``TypeError``.
If encoding is not None, then all input strings will be
transformed into unicode using that encoding prior to JSON-encoding.
The default is UTF-8.
If use_decimal is true (not the default), ``decimal.Decimal`` will
be supported directly by the encoder. For the inverse, decode JSON
with ``parse_float=decimal.Decimal``.
"""
self.skipkeys = skipkeys
self.ensure_ascii = ensure_ascii
self.check_circular = check_circular
self.allow_nan = allow_nan
self.sort_keys = sort_keys
self.use_decimal = use_decimal
if isinstance(indent, (int, long)):
indent = ' ' * indent
self.indent = indent
if separators is not None:
self.item_separator, self.key_separator = separators
if default is not None:
self.default = default
self.encoding = encoding
def default(self, o):
"""Implement this method in a subclass such that it returns
a serializable object for ``o``, or calls the base implementation
(to raise a ``TypeError``).
For example, to support arbitrary iterators, you could
implement default like this::
def default(self, o):
try:
iterable = iter(o)
except TypeError:
pass
else:
return list(iterable)
return JSONEncoder.default(self, o)
"""
raise TypeError(repr(o) + " is not JSON serializable")
def encode(self, o):
"""Return a JSON string representation of a Python data structure.
>>> from simplejson import JSONEncoder
>>> JSONEncoder().encode({"foo": ["bar", "baz"]})
'{"foo": ["bar", "baz"]}'
"""
# This is for extremely simple cases and benchmarks.
if isinstance(o, basestring):
if isinstance(o, str):
_encoding = self.encoding
if (_encoding is not None
and not (_encoding == 'utf-8')):
o = o.decode(_encoding)
if self.ensure_ascii:
return encode_basestring_ascii(o)
else:
return encode_basestring(o)
# This doesn't pass the iterator directly to ''.join() because the
# exceptions aren't as detailed. The list call should be roughly
# equivalent to the PySequence_Fast that ''.join() would do.
chunks = self.iterencode(o, _one_shot=True)
if not isinstance(chunks, (list, tuple)):
chunks = list(chunks)
if self.ensure_ascii:
return ''.join(chunks)
else:
return u''.join(chunks)
def iterencode(self, o, _one_shot=False):
"""Encode the given object and yield each string
representation as available.
For example::
for chunk in JSONEncoder().iterencode(bigobject):
mysocket.write(chunk)
"""
if self.check_circular:
markers = {}
else:
markers = None
if self.ensure_ascii:
_encoder = encode_basestring_ascii
else:
_encoder = encode_basestring
if self.encoding != 'utf-8':
def _encoder(o, _orig_encoder=_encoder, _encoding=self.encoding):
if isinstance(o, str):
o = o.decode(_encoding)
return _orig_encoder(o)
def floatstr(o, allow_nan=self.allow_nan,
_repr=FLOAT_REPR, _inf=PosInf, _neginf=-PosInf):
# Check for specials. Note that this type of test is processor
# and/or platform-specific, so do tests which don't depend on
# the internals.
if o != o:
text = 'NaN'
elif o == _inf:
text = 'Infinity'
elif o == _neginf:
text = '-Infinity'
else:
return _repr(o)
if not allow_nan:
raise ValueError(
"Out of range float values are not JSON compliant: " +
repr(o))
return text
key_memo = {}
if (_one_shot and c_make_encoder is not None
and not self.indent and not self.sort_keys):
_iterencode = c_make_encoder(
markers, self.default, _encoder, self.indent,
self.key_separator, self.item_separator, self.sort_keys,
self.skipkeys, self.allow_nan, key_memo, self.use_decimal)
else:
_iterencode = _make_iterencode(
markers, self.default, _encoder, self.indent, floatstr,
self.key_separator, self.item_separator, self.sort_keys,
self.skipkeys, _one_shot, self.use_decimal)
try:
return _iterencode(o, 0)
finally:
key_memo.clear()
class JSONEncoderForHTML(JSONEncoder):
"""An encoder that produces JSON safe to embed in HTML.
To embed JSON content in, say, a script tag on a web page, the
characters &, < and > should be escaped. They cannot be escaped
with the usual entities (e.g. &amp;) because they are not expanded
within <script> tags.
"""
def encode(self, o):
# Override JSONEncoder.encode because it has hacks for
# performance that make things more complicated.
chunks = self.iterencode(o, True)
if self.ensure_ascii:
return ''.join(chunks)
else:
return u''.join(chunks)
def iterencode(self, o, _one_shot=False):
chunks = super(JSONEncoderForHTML, self).iterencode(o, _one_shot)
for chunk in chunks:
chunk = chunk.replace('&', '\\u0026')
chunk = chunk.replace('<', '\\u003c')
chunk = chunk.replace('>', '\\u003e')
yield chunk
def _make_iterencode(markers, _default, _encoder, _indent, _floatstr,
_key_separator, _item_separator, _sort_keys, _skipkeys, _one_shot,
_use_decimal,
## HACK: hand-optimized bytecode; turn globals into locals
False=False,
True=True,
ValueError=ValueError,
basestring=basestring,
Decimal=Decimal,
dict=dict,
float=float,
id=id,
int=int,
isinstance=isinstance,
list=list,
long=long,
str=str,
tuple=tuple,
):
def _iterencode_list(lst, _current_indent_level):
if not lst:
yield '[]'
return
if markers is not None:
markerid = id(lst)
if markerid in markers:
raise ValueError("Circular reference detected")
markers[markerid] = lst
buf = '['
if _indent is not None:
_current_indent_level += 1
newline_indent = '\n' + (_indent * _current_indent_level)
separator = _item_separator + newline_indent
buf += newline_indent
else:
newline_indent = None
separator = _item_separator
first = True
for value in lst:
if first:
first = False
else:
buf = separator
if isinstance(value, basestring):
yield buf + _encoder(value)
elif value is None:
yield buf + 'null'
elif value is True:
yield buf + 'true'
elif value is False:
yield buf + 'false'
elif isinstance(value, (int, long)):
yield buf + str(value)
elif isinstance(value, float):
yield buf + _floatstr(value)
elif _use_decimal and isinstance(value, Decimal):
yield buf + str(value)
else:
yield buf
if isinstance(value, (list, tuple)):
chunks = _iterencode_list(value, _current_indent_level)
elif isinstance(value, dict):
chunks = _iterencode_dict(value, _current_indent_level)
else:
chunks = _iterencode(value, _current_indent_level)
for chunk in chunks:
yield chunk
if newline_indent is not None:
_current_indent_level -= 1
yield '\n' + (_indent * _current_indent_level)
yield ']'
if markers is not None:
del markers[markerid]
def _iterencode_dict(dct, _current_indent_level):
if not dct:
yield '{}'
return
if markers is not None:
markerid = id(dct)
if markerid in markers:
raise ValueError("Circular reference detected")
markers[markerid] = dct
yield '{'
if _indent is not None:
_current_indent_level += 1
newline_indent = '\n' + (_indent * _current_indent_level)
item_separator = _item_separator + newline_indent
yield newline_indent
else:
newline_indent = None
item_separator = _item_separator
first = True
if _sort_keys:
items = dct.items()
items.sort(key=lambda kv: kv[0])
else:
items = dct.iteritems()
for key, value in items:
if isinstance(key, basestring):
pass
# JavaScript is weakly typed for these, so it makes sense to
# also allow them. Many encoders seem to do something like this.
elif isinstance(key, float):
key = _floatstr(key)
elif key is True:
key = 'true'
elif key is False:
key = 'false'
elif key is None:
key = 'null'
elif isinstance(key, (int, long)):
key = str(key)
elif _skipkeys:
continue
else:
raise TypeError("key " + repr(key) + " is not a string")
if first:
first = False
else:
yield item_separator
yield _encoder(key)
yield _key_separator
if isinstance(value, basestring):
yield _encoder(value)
elif value is None:
yield 'null'
elif value is True:
yield 'true'
elif value is False:
yield 'false'
elif isinstance(value, (int, long)):
yield str(value)
elif isinstance(value, float):
yield _floatstr(value)
elif _use_decimal and isinstance(value, Decimal):
yield str(value)
else:
if isinstance(value, (list, tuple)):
chunks = _iterencode_list(value, _current_indent_level)
elif isinstance(value, dict):
chunks = _iterencode_dict(value, _current_indent_level)
else:
chunks = _iterencode(value, _current_indent_level)
for chunk in chunks:
yield chunk
if newline_indent is not None:
_current_indent_level -= 1
yield '\n' + (_indent * _current_indent_level)
yield '}'
if markers is not None:
del markers[markerid]
def _iterencode(o, _current_indent_level):
if isinstance(o, basestring):
yield _encoder(o)
elif o is None:
yield 'null'
elif o is True:
yield 'true'
elif o is False:
yield 'false'
elif isinstance(o, (int, long)):
yield str(o)
elif isinstance(o, float):
yield _floatstr(o)
elif isinstance(o, (list, tuple)):
for chunk in _iterencode_list(o, _current_indent_level):
yield chunk
elif isinstance(o, dict):
for chunk in _iterencode_dict(o, _current_indent_level):
yield chunk
elif _use_decimal and isinstance(o, Decimal):
yield str(o)
else:
if markers is not None:
markerid = id(o)
if markerid in markers:
raise ValueError("Circular reference detected")
markers[markerid] = o
o = _default(o)
for chunk in _iterencode(o, _current_indent_level):
yield chunk
if markers is not None:
del markers[markerid]
return _iterencode

BIN
simplejson/encoder.pyc Normal file

Binary file not shown.

119
simplejson/ordered_dict.py Normal file
View File

@@ -0,0 +1,119 @@
"""Drop-in replacement for collections.OrderedDict by Raymond Hettinger
http://code.activestate.com/recipes/576693/
"""
from UserDict import DictMixin
# Modified from original to support Python 2.4, see
# http://code.google.com/p/simplejson/issues/detail?id=53
try:
all
except NameError:
def all(seq):
for elem in seq:
if not elem:
return False
return True
class OrderedDict(dict, DictMixin):
def __init__(self, *args, **kwds):
if len(args) > 1:
raise TypeError('expected at most 1 arguments, got %d' % len(args))
try:
self.__end
except AttributeError:
self.clear()
self.update(*args, **kwds)
def clear(self):
self.__end = end = []
end += [None, end, end] # sentinel node for doubly linked list
self.__map = {} # key --> [key, prev, next]
dict.clear(self)
def __setitem__(self, key, value):
if key not in self:
end = self.__end
curr = end[1]
curr[2] = end[1] = self.__map[key] = [key, curr, end]
dict.__setitem__(self, key, value)
def __delitem__(self, key):
dict.__delitem__(self, key)
key, prev, next = self.__map.pop(key)
prev[2] = next
next[1] = prev
def __iter__(self):
end = self.__end
curr = end[2]
while curr is not end:
yield curr[0]
curr = curr[2]
def __reversed__(self):
end = self.__end
curr = end[1]
while curr is not end:
yield curr[0]
curr = curr[1]
def popitem(self, last=True):
if not self:
raise KeyError('dictionary is empty')
# Modified from original to support Python 2.4, see
# http://code.google.com/p/simplejson/issues/detail?id=53
if last:
key = reversed(self).next()
else:
key = iter(self).next()
value = self.pop(key)
return key, value
def __reduce__(self):
items = [[k, self[k]] for k in self]
tmp = self.__map, self.__end
del self.__map, self.__end
inst_dict = vars(self).copy()
self.__map, self.__end = tmp
if inst_dict:
return (self.__class__, (items,), inst_dict)
return self.__class__, (items,)
def keys(self):
return list(self)
setdefault = DictMixin.setdefault
update = DictMixin.update
pop = DictMixin.pop
values = DictMixin.values
items = DictMixin.items
iterkeys = DictMixin.iterkeys
itervalues = DictMixin.itervalues
iteritems = DictMixin.iteritems
def __repr__(self):
if not self:
return '%s()' % (self.__class__.__name__,)
return '%s(%r)' % (self.__class__.__name__, self.items())
def copy(self):
return self.__class__(self)
@classmethod
def fromkeys(cls, iterable, value=None):
d = cls()
for key in iterable:
d[key] = value
return d
def __eq__(self, other):
if isinstance(other, OrderedDict):
return len(self)==len(other) and \
all(p==q for p, q in zip(self.items(), other.items()))
return dict.__eq__(self, other)
def __ne__(self, other):
return not self == other

BIN
simplejson/ordered_dict.pyc Normal file

Binary file not shown.

77
simplejson/scanner.py Normal file
View File

@@ -0,0 +1,77 @@
"""JSON token scanner
"""
import re
def _import_c_make_scanner():
try:
from simplejson._speedups import make_scanner
return make_scanner
except ImportError:
return None
c_make_scanner = _import_c_make_scanner()
__all__ = ['make_scanner']
NUMBER_RE = re.compile(
r'(-?(?:0|[1-9]\d*))(\.\d+)?([eE][-+]?\d+)?',
(re.VERBOSE | re.MULTILINE | re.DOTALL))
def py_make_scanner(context):
parse_object = context.parse_object
parse_array = context.parse_array
parse_string = context.parse_string
match_number = NUMBER_RE.match
encoding = context.encoding
strict = context.strict
parse_float = context.parse_float
parse_int = context.parse_int
parse_constant = context.parse_constant
object_hook = context.object_hook
object_pairs_hook = context.object_pairs_hook
memo = context.memo
def _scan_once(string, idx):
try:
nextchar = string[idx]
except IndexError:
raise StopIteration
if nextchar == '"':
return parse_string(string, idx + 1, encoding, strict)
elif nextchar == '{':
return parse_object((string, idx + 1), encoding, strict,
_scan_once, object_hook, object_pairs_hook, memo)
elif nextchar == '[':
return parse_array((string, idx + 1), _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 = match_number(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
def scan_once(string, idx):
try:
return _scan_once(string, idx)
finally:
memo.clear()
return scan_once
make_scanner = c_make_scanner or py_make_scanner

BIN
simplejson/scanner.pyc Normal file

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

Binary file not shown.

View File

@@ -0,0 +1,63 @@
import unittest
import doctest
class OptionalExtensionTestSuite(unittest.TestSuite):
def run(self, result):
import simplejson
run = unittest.TestSuite.run
run(self, result)
simplejson._toggle_speedups(False)
run(self, result)
simplejson._toggle_speedups(True)
return result
def additional_tests(suite=None):
import simplejson
import simplejson.encoder
import simplejson.decoder
if suite is None:
suite = unittest.TestSuite()
for mod in (simplejson, simplejson.encoder, simplejson.decoder):
suite.addTest(doctest.DocTestSuite(mod))
suite.addTest(doctest.DocFileSuite('../../index.rst'))
return suite
def all_tests_suite():
suite = unittest.TestLoader().loadTestsFromNames([
'simplejson.tests.test_check_circular',
'simplejson.tests.test_decode',
'simplejson.tests.test_default',
'simplejson.tests.test_dump',
'simplejson.tests.test_encode_basestring_ascii',
'simplejson.tests.test_encode_for_html',
'simplejson.tests.test_fail',
'simplejson.tests.test_float',
'simplejson.tests.test_indent',
'simplejson.tests.test_pass1',
'simplejson.tests.test_pass2',
'simplejson.tests.test_pass3',
'simplejson.tests.test_recursion',
'simplejson.tests.test_scanstring',
'simplejson.tests.test_separators',
'simplejson.tests.test_speedups',
'simplejson.tests.test_unicode',
'simplejson.tests.test_decimal',
])
suite = additional_tests(suite)
return OptionalExtensionTestSuite([suite])
def main():
runner = unittest.TextTestRunner()
suite = all_tests_suite()
runner.run(suite)
if __name__ == '__main__':
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
main()

View File

@@ -0,0 +1,30 @@
from unittest import TestCase
import simplejson as json
def default_iterable(obj):
return list(obj)
class TestCheckCircular(TestCase):
def test_circular_dict(self):
dct = {}
dct['a'] = dct
self.assertRaises(ValueError, json.dumps, dct)
def test_circular_list(self):
lst = []
lst.append(lst)
self.assertRaises(ValueError, json.dumps, lst)
def test_circular_composite(self):
dct2 = {}
dct2['a'] = []
dct2['a'].append(dct2)
self.assertRaises(ValueError, json.dumps, dct2)
def test_circular_default(self):
json.dumps([set()], default=default_iterable)
self.assertRaises(TypeError, json.dumps, [set()])
def test_circular_off_default(self):
json.dumps([set()], default=default_iterable, check_circular=False)
self.assertRaises(TypeError, json.dumps, [set()], check_circular=False)

View File

@@ -0,0 +1,33 @@
from decimal import Decimal
from unittest import TestCase
import simplejson as json
class TestDecimal(TestCase):
NUMS = "1.0", "10.00", "1.1", "1234567890.1234567890", "500"
def test_decimal_encode(self):
for d in map(Decimal, self.NUMS):
self.assertEquals(json.dumps(d, use_decimal=True), str(d))
def test_decimal_decode(self):
for s in self.NUMS:
self.assertEquals(json.loads(s, parse_float=Decimal), Decimal(s))
def test_decimal_roundtrip(self):
for d in map(Decimal, self.NUMS):
# The type might not be the same (int and Decimal) but they
# should still compare equal.
self.assertEquals(
json.loads(
json.dumps(d, use_decimal=True), parse_float=Decimal),
d)
self.assertEquals(
json.loads(
json.dumps([d], use_decimal=True), parse_float=Decimal),
[d])
def test_decimal_defaults(self):
d = Decimal(1)
# use_decimal=False is the default
self.assertRaises(TypeError, json.dumps, d, use_decimal=False)
self.assertRaises(TypeError, json.dumps, d)

View File

@@ -0,0 +1,73 @@
import decimal
from unittest import TestCase
from StringIO import StringIO
import simplejson as json
from simplejson import OrderedDict
class TestDecode(TestCase):
if not hasattr(TestCase, 'assertIs'):
def assertIs(self, a, b):
self.assertTrue(a is b, '%r is %r' % (a, b))
def test_decimal(self):
rval = json.loads('1.1', parse_float=decimal.Decimal)
self.assertTrue(isinstance(rval, decimal.Decimal))
self.assertEquals(rval, decimal.Decimal('1.1'))
def test_float(self):
rval = json.loads('1', parse_int=float)
self.assertTrue(isinstance(rval, float))
self.assertEquals(rval, 1.0)
def test_decoder_optimizations(self):
# Several optimizations were made that skip over calls to
# the whitespace regex, so this test is designed to try and
# exercise the uncommon cases. The array cases are already covered.
rval = json.loads('{ "key" : "value" , "k":"v" }')
self.assertEquals(rval, {"key":"value", "k":"v"})
def test_empty_objects(self):
s = '{}'
self.assertEqual(json.loads(s), eval(s))
s = '[]'
self.assertEqual(json.loads(s), eval(s))
s = '""'
self.assertEqual(json.loads(s), eval(s))
def test_object_pairs_hook(self):
s = '{"xkd":1, "kcw":2, "art":3, "hxm":4, "qrt":5, "pad":6, "hoy":7}'
p = [("xkd", 1), ("kcw", 2), ("art", 3), ("hxm", 4),
("qrt", 5), ("pad", 6), ("hoy", 7)]
self.assertEqual(json.loads(s), eval(s))
self.assertEqual(json.loads(s, object_pairs_hook=lambda x: x), p)
self.assertEqual(json.load(StringIO(s),
object_pairs_hook=lambda x: x), p)
od = json.loads(s, object_pairs_hook=OrderedDict)
self.assertEqual(od, OrderedDict(p))
self.assertEqual(type(od), OrderedDict)
# the object_pairs_hook takes priority over the object_hook
self.assertEqual(json.loads(s,
object_pairs_hook=OrderedDict,
object_hook=lambda x: None),
OrderedDict(p))
def check_keys_reuse(self, source, loads):
rval = loads(source)
(a, b), (c, d) = sorted(rval[0]), sorted(rval[1])
self.assertIs(a, c)
self.assertIs(b, d)
def test_keys_reuse_str(self):
s = u'[{"a_key": 1, "b_\xe9": 2}, {"a_key": 3, "b_\xe9": 4}]'.encode('utf8')
self.check_keys_reuse(s, json.loads)
def test_keys_reuse_unicode(self):
s = u'[{"a_key": 1, "b_\xe9": 2}, {"a_key": 3, "b_\xe9": 4}]'
self.check_keys_reuse(s, json.loads)
def test_empty_strings(self):
self.assertEqual(json.loads('""'), "")
self.assertEqual(json.loads(u'""'), u"")
self.assertEqual(json.loads('[""]'), [""])
self.assertEqual(json.loads(u'[""]'), [u""])

View File

@@ -0,0 +1,9 @@
from unittest import TestCase
import simplejson as json
class TestDefault(TestCase):
def test_default(self):
self.assertEquals(
json.dumps(type, default=repr),
json.dumps(repr(type)))

View File

@@ -0,0 +1,27 @@
from unittest import TestCase
from cStringIO import StringIO
import simplejson as json
class TestDump(TestCase):
def test_dump(self):
sio = StringIO()
json.dump({}, sio)
self.assertEquals(sio.getvalue(), '{}')
def test_dumps(self):
self.assertEquals(json.dumps({}), '{}')
def test_encode_truefalse(self):
self.assertEquals(json.dumps(
{True: False, False: True}, sort_keys=True),
'{"false": true, "true": false}')
self.assertEquals(json.dumps(
{2: 3.0, 4.0: 5L, False: 1, 6L: True, "7": 0}, sort_keys=True),
'{"false": 1, "2": 3.0, "4.0": 5, "6": true, "7": 0}')
def test_ordered_dict(self):
# http://bugs.python.org/issue6105
items = [('one', 1), ('two', 2), ('three', 3), ('four', 4), ('five', 5)]
s = json.dumps(json.OrderedDict(items))
self.assertEqual(s, '{"one": 1, "two": 2, "three": 3, "four": 4, "five": 5}')

View File

@@ -0,0 +1,41 @@
from unittest import TestCase
import simplejson.encoder
CASES = [
(u'/\\"\ucafe\ubabe\uab98\ufcde\ubcda\uef4a\x08\x0c\n\r\t`1~!@#$%^&*()_+-=[]{}|;:\',./<>?', '"/\\\\\\"\\ucafe\\ubabe\\uab98\\ufcde\\ubcda\\uef4a\\b\\f\\n\\r\\t`1~!@#$%^&*()_+-=[]{}|;:\',./<>?"'),
(u'\u0123\u4567\u89ab\ucdef\uabcd\uef4a', '"\\u0123\\u4567\\u89ab\\ucdef\\uabcd\\uef4a"'),
(u'controls', '"controls"'),
(u'\x08\x0c\n\r\t', '"\\b\\f\\n\\r\\t"'),
(u'{"object with 1 member":["array with 1 element"]}', '"{\\"object with 1 member\\":[\\"array with 1 element\\"]}"'),
(u' s p a c e d ', '" s p a c e d "'),
(u'\U0001d120', '"\\ud834\\udd20"'),
(u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
('\xce\xb1\xce\xa9', '"\\u03b1\\u03a9"'),
(u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
('\xce\xb1\xce\xa9', '"\\u03b1\\u03a9"'),
(u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
(u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
(u"`1~!@#$%^&*()_+-={':[,]}|;.</>?", '"`1~!@#$%^&*()_+-={\':[,]}|;.</>?"'),
(u'\x08\x0c\n\r\t', '"\\b\\f\\n\\r\\t"'),
(u'\u0123\u4567\u89ab\ucdef\uabcd\uef4a', '"\\u0123\\u4567\\u89ab\\ucdef\\uabcd\\uef4a"'),
]
class TestEncodeBaseStringAscii(TestCase):
def test_py_encode_basestring_ascii(self):
self._test_encode_basestring_ascii(simplejson.encoder.py_encode_basestring_ascii)
def test_c_encode_basestring_ascii(self):
if not simplejson.encoder.c_encode_basestring_ascii:
return
self._test_encode_basestring_ascii(simplejson.encoder.c_encode_basestring_ascii)
def _test_encode_basestring_ascii(self, encode_basestring_ascii):
fname = encode_basestring_ascii.__name__
for input_string, expect in CASES:
result = encode_basestring_ascii(input_string)
#self.assertEquals(result, expect,
# '{0!r} != {1!r} for {2}({3!r})'.format(
# result, expect, fname, input_string))
self.assertEquals(result, expect,
'%r != %r for %s(%r)' % (result, expect, fname, input_string))

View File

@@ -0,0 +1,32 @@
import unittest
import simplejson.decoder
import simplejson.encoder
class TestEncodeForHTML(unittest.TestCase):
def setUp(self):
self.decoder = simplejson.decoder.JSONDecoder()
self.encoder = simplejson.encoder.JSONEncoderForHTML()
def test_basic_encode(self):
self.assertEqual(r'"\u0026"', self.encoder.encode('&'))
self.assertEqual(r'"\u003c"', self.encoder.encode('<'))
self.assertEqual(r'"\u003e"', self.encoder.encode('>'))
def test_basic_roundtrip(self):
for char in '&<>':
self.assertEqual(
char, self.decoder.decode(
self.encoder.encode(char)))
def test_prevent_script_breakout(self):
bad_string = '</script><script>alert("gotcha")</script>'
self.assertEqual(
r'"\u003c/script\u003e\u003cscript\u003e'
r'alert(\"gotcha\")\u003c/script\u003e"',
self.encoder.encode(bad_string))
self.assertEqual(
bad_string, self.decoder.decode(
self.encoder.encode(bad_string)))

View File

@@ -0,0 +1,91 @@
from unittest import TestCase
import simplejson as json
# Fri Dec 30 18:57:26 2005
JSONDOCS = [
# http://json.org/JSON_checker/test/fail1.json
'"A JSON payload should be an object or array, not a string."',
# http://json.org/JSON_checker/test/fail2.json
'["Unclosed array"',
# http://json.org/JSON_checker/test/fail3.json
'{unquoted_key: "keys must be quoted}',
# http://json.org/JSON_checker/test/fail4.json
'["extra comma",]',
# http://json.org/JSON_checker/test/fail5.json
'["double extra comma",,]',
# http://json.org/JSON_checker/test/fail6.json
'[ , "<-- missing value"]',
# http://json.org/JSON_checker/test/fail7.json
'["Comma after the close"],',
# http://json.org/JSON_checker/test/fail8.json
'["Extra close"]]',
# http://json.org/JSON_checker/test/fail9.json
'{"Extra comma": true,}',
# http://json.org/JSON_checker/test/fail10.json
'{"Extra value after close": true} "misplaced quoted value"',
# http://json.org/JSON_checker/test/fail11.json
'{"Illegal expression": 1 + 2}',
# http://json.org/JSON_checker/test/fail12.json
'{"Illegal invocation": alert()}',
# http://json.org/JSON_checker/test/fail13.json
'{"Numbers cannot have leading zeroes": 013}',
# http://json.org/JSON_checker/test/fail14.json
'{"Numbers cannot be hex": 0x14}',
# http://json.org/JSON_checker/test/fail15.json
'["Illegal backslash escape: \\x15"]',
# http://json.org/JSON_checker/test/fail16.json
'["Illegal backslash escape: \\\'"]',
# http://json.org/JSON_checker/test/fail17.json
'["Illegal backslash escape: \\017"]',
# http://json.org/JSON_checker/test/fail18.json
'[[[[[[[[[[[[[[[[[[[["Too deep"]]]]]]]]]]]]]]]]]]]]',
# http://json.org/JSON_checker/test/fail19.json
'{"Missing colon" null}',
# http://json.org/JSON_checker/test/fail20.json
'{"Double colon":: null}',
# http://json.org/JSON_checker/test/fail21.json
'{"Comma instead of colon", null}',
# http://json.org/JSON_checker/test/fail22.json
'["Colon instead of comma": false]',
# http://json.org/JSON_checker/test/fail23.json
'["Bad value", truth]',
# http://json.org/JSON_checker/test/fail24.json
"['single quote']",
# http://code.google.com/p/simplejson/issues/detail?id=3
u'["A\u001FZ control characters in string"]',
]
SKIPS = {
1: "why not have a string payload?",
18: "spec doesn't specify any nesting limitations",
}
class TestFail(TestCase):
def test_failures(self):
for idx, doc in enumerate(JSONDOCS):
idx = idx + 1
if idx in SKIPS:
json.loads(doc)
continue
try:
json.loads(doc)
except json.JSONDecodeError:
pass
else:
#self.fail("Expected failure for fail{0}.json: {1!r}".format(idx, doc))
self.fail("Expected failure for fail%d.json: %r" % (idx, doc))
def test_array_decoder_issue46(self):
# http://code.google.com/p/simplejson/issues/detail?id=46
for doc in [u'[,]', '[,]']:
try:
json.loads(doc)
except json.JSONDecodeError, e:
self.assertEquals(e.pos, 1)
self.assertEquals(e.lineno, 1)
self.assertEquals(e.colno, 1)
except Exception, e:
self.fail("Unexpected exception raised %r %s" % (e, e))
else:
self.fail("Unexpected success parsing '[,]'")

View File

@@ -0,0 +1,19 @@
import math
from unittest import TestCase
import simplejson as json
class TestFloat(TestCase):
def test_floats(self):
for num in [1617161771.7650001, math.pi, math.pi**100,
math.pi**-100, 3.1]:
self.assertEquals(float(json.dumps(num)), num)
self.assertEquals(json.loads(json.dumps(num)), num)
self.assertEquals(json.loads(unicode(json.dumps(num))), num)
def test_ints(self):
for num in [1, 1L, 1<<32, 1<<64]:
self.assertEquals(json.dumps(num), str(num))
self.assertEquals(int(json.dumps(num)), num)
self.assertEquals(json.loads(json.dumps(num)), num)
self.assertEquals(json.loads(unicode(json.dumps(num))), num)

View File

@@ -0,0 +1,53 @@
from unittest import TestCase
import simplejson as json
import textwrap
class TestIndent(TestCase):
def test_indent(self):
h = [['blorpie'], ['whoops'], [], 'd-shtaeou', 'd-nthiouh',
'i-vhbjkhnth',
{'nifty': 87}, {'field': 'yes', 'morefield': False} ]
expect = textwrap.dedent("""\
[
\t[
\t\t"blorpie"
\t],
\t[
\t\t"whoops"
\t],
\t[],
\t"d-shtaeou",
\t"d-nthiouh",
\t"i-vhbjkhnth",
\t{
\t\t"nifty": 87
\t},
\t{
\t\t"field": "yes",
\t\t"morefield": false
\t}
]""")
d1 = json.dumps(h)
d2 = json.dumps(h, indent='\t', sort_keys=True, separators=(',', ': '))
d3 = json.dumps(h, indent=' ', sort_keys=True, separators=(',', ': '))
d4 = json.dumps(h, indent=2, sort_keys=True, separators=(',', ': '))
h1 = json.loads(d1)
h2 = json.loads(d2)
h3 = json.loads(d3)
h4 = json.loads(d4)
self.assertEquals(h1, h)
self.assertEquals(h2, h)
self.assertEquals(h3, h)
self.assertEquals(h4, h)
self.assertEquals(d3, expect.replace('\t', ' '))
self.assertEquals(d4, expect.replace('\t', ' '))
# NOTE: Python 2.4 textwrap.dedent converts tabs to spaces,
# so the following is expected to fail. Python 2.4 is not a
# supported platform in simplejson 2.1.0+.
self.assertEquals(d2, expect)

View File

@@ -0,0 +1,76 @@
from unittest import TestCase
import simplejson as json
# from http://json.org/JSON_checker/test/pass1.json
JSON = r'''
[
"JSON Test Pattern pass1",
{"object with 1 member":["array with 1 element"]},
{},
[],
-42,
true,
false,
null,
{
"integer": 1234567890,
"real": -9876.543210,
"e": 0.123456789e-12,
"E": 1.234567890E+34,
"": 23456789012E666,
"zero": 0,
"one": 1,
"space": " ",
"quote": "\"",
"backslash": "\\",
"controls": "\b\f\n\r\t",
"slash": "/ & \/",
"alpha": "abcdefghijklmnopqrstuvwyz",
"ALPHA": "ABCDEFGHIJKLMNOPQRSTUVWYZ",
"digit": "0123456789",
"special": "`1~!@#$%^&*()_+-={':[,]}|;.</>?",
"hex": "\u0123\u4567\u89AB\uCDEF\uabcd\uef4A",
"true": true,
"false": false,
"null": null,
"array":[ ],
"object":{ },
"address": "50 St. James Street",
"url": "http://www.JSON.org/",
"comment": "// /* <!-- --",
"# -- --> */": " ",
" s p a c e d " :[1,2 , 3
,
4 , 5 , 6 ,7 ],
"compact": [1,2,3,4,5,6,7],
"jsontext": "{\"object with 1 member\":[\"array with 1 element\"]}",
"quotes": "&#34; \u0022 %22 0x22 034 &#x22;",
"\/\\\"\uCAFE\uBABE\uAB98\uFCDE\ubcda\uef4A\b\f\n\r\t`1~!@#$%^&*()_+-=[]{}|;:',./<>?"
: "A key can be any string"
},
0.5 ,98.6
,
99.44
,
1066
,"rosebud"]
'''
class TestPass1(TestCase):
def test_parse(self):
# test in/out equivalence and parsing
res = json.loads(JSON)
out = json.dumps(res)
self.assertEquals(res, json.loads(out))
try:
json.dumps(res, allow_nan=False)
except ValueError:
pass
else:
self.fail("23456789012E666 should be out of range")

View File

@@ -0,0 +1,14 @@
from unittest import TestCase
import simplejson as json
# from http://json.org/JSON_checker/test/pass2.json
JSON = r'''
[[[[[[[[[[[[[[[[[[["Not too deep"]]]]]]]]]]]]]]]]]]]
'''
class TestPass2(TestCase):
def test_parse(self):
# test in/out equivalence and parsing
res = json.loads(JSON)
out = json.dumps(res)
self.assertEquals(res, json.loads(out))

View File

@@ -0,0 +1,20 @@
from unittest import TestCase
import simplejson as json
# from http://json.org/JSON_checker/test/pass3.json
JSON = r'''
{
"JSON Test Pattern pass3": {
"The outermost value": "must be an object or array.",
"In this test": "It is an object."
}
}
'''
class TestPass3(TestCase):
def test_parse(self):
# test in/out equivalence and parsing
res = json.loads(JSON)
out = json.dumps(res)
self.assertEquals(res, json.loads(out))

View File

@@ -0,0 +1,67 @@
from unittest import TestCase
import simplejson as json
class JSONTestObject:
pass
class RecursiveJSONEncoder(json.JSONEncoder):
recurse = False
def default(self, o):
if o is JSONTestObject:
if self.recurse:
return [JSONTestObject]
else:
return 'JSONTestObject'
return json.JSONEncoder.default(o)
class TestRecursion(TestCase):
def test_listrecursion(self):
x = []
x.append(x)
try:
json.dumps(x)
except ValueError:
pass
else:
self.fail("didn't raise ValueError on list recursion")
x = []
y = [x]
x.append(y)
try:
json.dumps(x)
except ValueError:
pass
else:
self.fail("didn't raise ValueError on alternating list recursion")
y = []
x = [y, y]
# ensure that the marker is cleared
json.dumps(x)
def test_dictrecursion(self):
x = {}
x["test"] = x
try:
json.dumps(x)
except ValueError:
pass
else:
self.fail("didn't raise ValueError on dict recursion")
x = {}
y = {"a": x, "b": x}
# ensure that the marker is cleared
json.dumps(x)
def test_defaultrecursion(self):
enc = RecursiveJSONEncoder()
self.assertEquals(enc.encode(JSONTestObject), '"JSONTestObject"')
enc.recurse = True
try:
enc.encode(JSONTestObject)
except ValueError:
pass
else:
self.fail("didn't raise ValueError on default recursion")

View File

@@ -0,0 +1,117 @@
import sys
from unittest import TestCase
import simplejson as json
import simplejson.decoder
class TestScanString(TestCase):
def test_py_scanstring(self):
self._test_scanstring(simplejson.decoder.py_scanstring)
def test_c_scanstring(self):
if not simplejson.decoder.c_scanstring:
return
self._test_scanstring(simplejson.decoder.c_scanstring)
def _test_scanstring(self, scanstring):
self.assertEquals(
scanstring('"z\\ud834\\udd20x"', 1, None, True),
(u'z\U0001d120x', 16))
if sys.maxunicode == 65535:
self.assertEquals(
scanstring(u'"z\U0001d120x"', 1, None, True),
(u'z\U0001d120x', 6))
else:
self.assertEquals(
scanstring(u'"z\U0001d120x"', 1, None, True),
(u'z\U0001d120x', 5))
self.assertEquals(
scanstring('"\\u007b"', 1, None, True),
(u'{', 8))
self.assertEquals(
scanstring('"A JSON payload should be an object or array, not a string."', 1, None, True),
(u'A JSON payload should be an object or array, not a string.', 60))
self.assertEquals(
scanstring('["Unclosed array"', 2, None, True),
(u'Unclosed array', 17))
self.assertEquals(
scanstring('["extra comma",]', 2, None, True),
(u'extra comma', 14))
self.assertEquals(
scanstring('["double extra comma",,]', 2, None, True),
(u'double extra comma', 21))
self.assertEquals(
scanstring('["Comma after the close"],', 2, None, True),
(u'Comma after the close', 24))
self.assertEquals(
scanstring('["Extra close"]]', 2, None, True),
(u'Extra close', 14))
self.assertEquals(
scanstring('{"Extra comma": true,}', 2, None, True),
(u'Extra comma', 14))
self.assertEquals(
scanstring('{"Extra value after close": true} "misplaced quoted value"', 2, None, True),
(u'Extra value after close', 26))
self.assertEquals(
scanstring('{"Illegal expression": 1 + 2}', 2, None, True),
(u'Illegal expression', 21))
self.assertEquals(
scanstring('{"Illegal invocation": alert()}', 2, None, True),
(u'Illegal invocation', 21))
self.assertEquals(
scanstring('{"Numbers cannot have leading zeroes": 013}', 2, None, True),
(u'Numbers cannot have leading zeroes', 37))
self.assertEquals(
scanstring('{"Numbers cannot be hex": 0x14}', 2, None, True),
(u'Numbers cannot be hex', 24))
self.assertEquals(
scanstring('[[[[[[[[[[[[[[[[[[[["Too deep"]]]]]]]]]]]]]]]]]]]]', 21, None, True),
(u'Too deep', 30))
self.assertEquals(
scanstring('{"Missing colon" null}', 2, None, True),
(u'Missing colon', 16))
self.assertEquals(
scanstring('{"Double colon":: null}', 2, None, True),
(u'Double colon', 15))
self.assertEquals(
scanstring('{"Comma instead of colon", null}', 2, None, True),
(u'Comma instead of colon', 25))
self.assertEquals(
scanstring('["Colon instead of comma": false]', 2, None, True),
(u'Colon instead of comma', 25))
self.assertEquals(
scanstring('["Bad value", truth]', 2, None, True),
(u'Bad value', 12))
def test_issue3623(self):
self.assertRaises(ValueError, json.decoder.scanstring, "xxx", 1,
"xxx")
self.assertRaises(UnicodeDecodeError,
json.encoder.encode_basestring_ascii, "xx\xff")
def test_overflow(self):
# Python 2.5 does not have maxsize
maxsize = getattr(sys, 'maxsize', sys.maxint)
self.assertRaises(OverflowError, json.decoder.scanstring, "xxx",
maxsize + 1)

View File

@@ -0,0 +1,42 @@
import textwrap
from unittest import TestCase
import simplejson as json
class TestSeparators(TestCase):
def test_separators(self):
h = [['blorpie'], ['whoops'], [], 'd-shtaeou', 'd-nthiouh', 'i-vhbjkhnth',
{'nifty': 87}, {'field': 'yes', 'morefield': False} ]
expect = textwrap.dedent("""\
[
[
"blorpie"
] ,
[
"whoops"
] ,
[] ,
"d-shtaeou" ,
"d-nthiouh" ,
"i-vhbjkhnth" ,
{
"nifty" : 87
} ,
{
"field" : "yes" ,
"morefield" : false
}
]""")
d1 = json.dumps(h)
d2 = json.dumps(h, indent=' ', sort_keys=True, separators=(' ,', ' : '))
h1 = json.loads(d1)
h2 = json.loads(d2)
self.assertEquals(h1, h)
self.assertEquals(h2, h)
self.assertEquals(d2, expect)

View File

@@ -0,0 +1,21 @@
import decimal
from unittest import TestCase
from simplejson import decoder, encoder, scanner
def has_speedups():
return encoder.c_make_encoder is not None
class TestDecode(TestCase):
def test_make_scanner(self):
if not has_speedups():
return
self.assertRaises(AttributeError, scanner.c_make_scanner, 1)
def test_make_encoder(self):
if not has_speedups():
return
self.assertRaises(TypeError, encoder.c_make_encoder,
None,
"\xCD\x7D\x3D\x4E\x12\x4C\xF9\x79\xD7\x52\xBA\x82\xF2\x27\x4A\x7D\xA0\xCA\x75",
None)

View File

@@ -0,0 +1,99 @@
from unittest import TestCase
import simplejson as json
class TestUnicode(TestCase):
def test_encoding1(self):
encoder = json.JSONEncoder(encoding='utf-8')
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
s = u.encode('utf-8')
ju = encoder.encode(u)
js = encoder.encode(s)
self.assertEquals(ju, js)
def test_encoding2(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
s = u.encode('utf-8')
ju = json.dumps(u, encoding='utf-8')
js = json.dumps(s, encoding='utf-8')
self.assertEquals(ju, js)
def test_encoding3(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
j = json.dumps(u)
self.assertEquals(j, '"\\u03b1\\u03a9"')
def test_encoding4(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
j = json.dumps([u])
self.assertEquals(j, '["\\u03b1\\u03a9"]')
def test_encoding5(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
j = json.dumps(u, ensure_ascii=False)
self.assertEquals(j, u'"' + u + u'"')
def test_encoding6(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
j = json.dumps([u], ensure_ascii=False)
self.assertEquals(j, u'["' + u + u'"]')
def test_big_unicode_encode(self):
u = u'\U0001d120'
self.assertEquals(json.dumps(u), '"\\ud834\\udd20"')
self.assertEquals(json.dumps(u, ensure_ascii=False), u'"\U0001d120"')
def test_big_unicode_decode(self):
u = u'z\U0001d120x'
self.assertEquals(json.loads('"' + u + '"'), u)
self.assertEquals(json.loads('"z\\ud834\\udd20x"'), u)
def test_unicode_decode(self):
for i in range(0, 0xd7ff):
u = unichr(i)
#s = '"\\u{0:04x}"'.format(i)
s = '"\\u%04x"' % (i,)
self.assertEquals(json.loads(s), u)
def test_object_pairs_hook_with_unicode(self):
s = u'{"xkd":1, "kcw":2, "art":3, "hxm":4, "qrt":5, "pad":6, "hoy":7}'
p = [(u"xkd", 1), (u"kcw", 2), (u"art", 3), (u"hxm", 4),
(u"qrt", 5), (u"pad", 6), (u"hoy", 7)]
self.assertEqual(json.loads(s), eval(s))
self.assertEqual(json.loads(s, object_pairs_hook=lambda x: x), p)
od = json.loads(s, object_pairs_hook=json.OrderedDict)
self.assertEqual(od, json.OrderedDict(p))
self.assertEqual(type(od), json.OrderedDict)
# the object_pairs_hook takes priority over the object_hook
self.assertEqual(json.loads(s,
object_pairs_hook=json.OrderedDict,
object_hook=lambda x: None),
json.OrderedDict(p))
def test_default_encoding(self):
self.assertEquals(json.loads(u'{"a": "\xe9"}'.encode('utf-8')),
{'a': u'\xe9'})
def test_unicode_preservation(self):
self.assertEquals(type(json.loads(u'""')), unicode)
self.assertEquals(type(json.loads(u'"a"')), unicode)
self.assertEquals(type(json.loads(u'["a"]')[0]), unicode)
def test_ensure_ascii_false_returns_unicode(self):
# http://code.google.com/p/simplejson/issues/detail?id=48
self.assertEquals(type(json.dumps([], ensure_ascii=False)), unicode)
self.assertEquals(type(json.dumps(0, ensure_ascii=False)), unicode)
self.assertEquals(type(json.dumps({}, ensure_ascii=False)), unicode)
self.assertEquals(type(json.dumps("", ensure_ascii=False)), unicode)
def test_ensure_ascii_false_bytestring_encoding(self):
# http://code.google.com/p/simplejson/issues/detail?id=48
doc1 = {u'quux': 'Arr\xc3\xaat sur images'}
doc2 = {u'quux': u'Arr\xeat sur images'}
doc_ascii = '{"quux": "Arr\\u00eat sur images"}'
doc_unicode = u'{"quux": "Arr\xeat sur images"}'
self.assertEquals(json.dumps(doc1), doc_ascii)
self.assertEquals(json.dumps(doc2), doc_ascii)
self.assertEquals(json.dumps(doc1, ensure_ascii=False), doc_unicode)
self.assertEquals(json.dumps(doc2, ensure_ascii=False), doc_unicode)

39
simplejson/tool.py Normal file
View File

@@ -0,0 +1,39 @@
r"""Command-line tool to validate and pretty-print JSON
Usage::
$ 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)
"""
import sys
import simplejson as json
def main():
if len(sys.argv) == 1:
infile = sys.stdin
outfile = sys.stdout
elif len(sys.argv) == 2:
infile = open(sys.argv[1], 'rb')
outfile = sys.stdout
elif len(sys.argv) == 3:
infile = open(sys.argv[1], 'rb')
outfile = open(sys.argv[2], 'wb')
else:
raise SystemExit(sys.argv[0] + " [infile [outfile]]")
try:
obj = json.load(infile,
object_pairs_hook=json.OrderedDict,
use_decimal=True)
except ValueError, e:
raise SystemExit(e)
json.dump(obj, outfile, sort_keys=True, indent=' ', use_decimal=True)
outfile.write('\n')
if __name__ == '__main__':
main()