mirror of https://github.com/django/django.git
Upgraded included simplejson to 2.0.7.
Also changed importing logic to prefer a system-installed version of simplejson (unless it's an earlier version that does not contian the C speedups), then the json module from Python 2.6, then the version shipped with Django. Fixed #9266. git-svn-id: http://code.djangoproject.com/svn/django/trunk@9707 bcc190cf-cafb-0310-a4f2-bffc1f526a37
This commit is contained in:
Malcolm Tredinnick
parent
3b489b7742
commit
a9c2f033cd
|
|
@ -1,42 +1,44 @@
|
|||
r"""
|
||||
A simple, fast, extensible JSON encoder and decoder
|
||||
|
||||
JSON (JavaScript Object Notation) <http://json.org> is a subset of
|
||||
r"""JSON (JavaScript Object Notation) <http://json.org> is a subset of
|
||||
JavaScript syntax (ECMA-262 3rd edition) used as a lightweight data
|
||||
interchange format.
|
||||
|
||||
simplejson exposes an API familiar to uses of the standard library
|
||||
marshal and pickle modules.
|
||||
: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
|
||||
>>> simplejson.dumps(['foo', {'bar': ('baz', None, 1.0, 2)}])
|
||||
>>> import simplejson as json
|
||||
>>> json.dumps(['foo', {'bar': ('baz', None, 1.0, 2)}])
|
||||
'["foo", {"bar": ["baz", null, 1.0, 2]}]'
|
||||
>>> print simplejson.dumps("\"foo\bar")
|
||||
>>> print json.dumps("\"foo\bar")
|
||||
"\"foo\bar"
|
||||
>>> print simplejson.dumps(u'\u1234')
|
||||
>>> print json.dumps(u'\u1234')
|
||||
"\u1234"
|
||||
>>> print simplejson.dumps('\\')
|
||||
>>> print json.dumps('\\')
|
||||
"\\"
|
||||
>>> print simplejson.dumps({"c": 0, "b": 0, "a": 0}, sort_keys=True)
|
||||
>>> print json.dumps({"c": 0, "b": 0, "a": 0}, sort_keys=True)
|
||||
{"a": 0, "b": 0, "c": 0}
|
||||
>>> from StringIO import StringIO
|
||||
>>> io = StringIO()
|
||||
>>> simplejson.dump(['streaming API'], io)
|
||||
>>> json.dump(['streaming API'], io)
|
||||
>>> io.getvalue()
|
||||
'["streaming API"]'
|
||||
|
||||
Compact encoding::
|
||||
|
||||
>>> import simplejson
|
||||
>>> simplejson.dumps([1,2,3,{'4': 5, '6': 7}], separators=(',',':'))
|
||||
>>> 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
|
||||
>>> print simplejson.dumps({'4': 5, '6': 7}, sort_keys=True, indent=4)
|
||||
>>> import simplejson as json
|
||||
>>> s = json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=4)
|
||||
>>> print '\n'.join([l.rstrip() for l in s.splitlines()])
|
||||
{
|
||||
"4": 5,
|
||||
"6": 7
|
||||
|
|
@ -44,50 +46,49 @@ Pretty printing::
|
|||
|
||||
Decoding JSON::
|
||||
|
||||
>>> import simplejson
|
||||
>>> simplejson.loads('["foo", {"bar":["baz", null, 1.0, 2]}]')
|
||||
[u'foo', {u'bar': [u'baz', None, 1.0, 2]}]
|
||||
>>> simplejson.loads('"\\"foo\\bar"')
|
||||
u'"foo\x08ar'
|
||||
>>> 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"]')
|
||||
>>> simplejson.load(io)
|
||||
[u'streaming API']
|
||||
>>> json.load(io)[0] == 'streaming API'
|
||||
True
|
||||
|
||||
Specializing JSON object decoding::
|
||||
|
||||
>>> import simplejson
|
||||
>>> import simplejson as json
|
||||
>>> def as_complex(dct):
|
||||
... if '__complex__' in dct:
|
||||
... return complex(dct['real'], dct['imag'])
|
||||
... return dct
|
||||
...
|
||||
>>> simplejson.loads('{"__complex__": true, "real": 1, "imag": 2}',
|
||||
>>> json.loads('{"__complex__": true, "real": 1, "imag": 2}',
|
||||
... object_hook=as_complex)
|
||||
(1+2j)
|
||||
>>> import decimal
|
||||
>>> simplejson.loads('1.1', parse_float=decimal.Decimal)
|
||||
Decimal("1.1")
|
||||
>>> json.loads('1.1', parse_float=decimal.Decimal) == decimal.Decimal('1.1')
|
||||
True
|
||||
|
||||
Extending JSONEncoder::
|
||||
Specializing JSON object encoding::
|
||||
|
||||
>>> import simplejson
|
||||
>>> class ComplexEncoder(simplejson.JSONEncoder):
|
||||
... def default(self, obj):
|
||||
>>> import simplejson as json
|
||||
>>> def encode_complex(obj):
|
||||
... if isinstance(obj, complex):
|
||||
... return [obj.real, obj.imag]
|
||||
... return simplejson.JSONEncoder.default(self, obj)
|
||||
... raise TypeError("%r is not JSON serializable" % (o,))
|
||||
...
|
||||
>>> dumps(2 + 1j, cls=ComplexEncoder)
|
||||
>>> json.dumps(2 + 1j, default=encode_complex)
|
||||
'[2.0, 1.0]'
|
||||
>>> ComplexEncoder().encode(2 + 1j)
|
||||
>>> 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]'
|
||||
>>> list(ComplexEncoder().iterencode(2 + 1j))
|
||||
['[', '2.0', ', ', '1.0', ']']
|
||||
|
||||
|
||||
Using simplejson from the shell to validate and
|
||||
pretty-print::
|
||||
Using simplejson.tool from the shell to validate and pretty-print::
|
||||
|
||||
$ echo '{"json":"obj"}' | python -msimplejson.tool
|
||||
{
|
||||
|
|
@ -95,24 +96,42 @@ pretty-print::
|
|||
}
|
||||
$ echo '{ 1.2:3.4}' | python -msimplejson.tool
|
||||
Expecting property name: line 1 column 2 (char 2)
|
||||
|
||||
Note that the JSON produced by this module's default settings
|
||||
is a subset of YAML, so it may be used as a serializer for that as well.
|
||||
"""
|
||||
__version__ = '1.9.2'
|
||||
|
||||
# Django modification: try to use the system version first, providing it's
|
||||
# either of a later version of has the C speedups in place. Otherwise, fall
|
||||
# back to our local copy.
|
||||
|
||||
__version__ = '2.0.7'
|
||||
|
||||
use_system_version = False
|
||||
try:
|
||||
# The system-installed version has priority providing it is either not an
|
||||
# earlier version or it contains the C speedups.
|
||||
import simplejson
|
||||
if (simplejson.__version__.split('.') >= __version__.split('.') or
|
||||
hasattr(simplejson, '_speedups')):
|
||||
from simplejson import *
|
||||
use_system_version = True
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
if not use_system_version:
|
||||
try:
|
||||
from json import * # Python 2.6 preferred over local copy.
|
||||
use_system_version = True
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
# If all else fails, we have a bundled version that can be used.
|
||||
if not use_system_version:
|
||||
__all__ = [
|
||||
'dump', 'dumps', 'load', 'loads',
|
||||
'JSONDecoder', 'JSONEncoder',
|
||||
]
|
||||
|
||||
if __name__ == '__main__':
|
||||
import warnings
|
||||
warnings.warn('python -msimplejson is deprecated, use python -msiplejson.tool', DeprecationWarning)
|
||||
from django.utils.simplejson.decoder import JSONDecoder
|
||||
from django.utils.simplejson.encoder import JSONEncoder
|
||||
else:
|
||||
from decoder import JSONDecoder
|
||||
from encoder import JSONEncoder
|
||||
|
||||
_default_encoder = JSONEncoder(
|
||||
skipkeys=False,
|
||||
|
|
@ -128,8 +147,7 @@ _default_encoder = JSONEncoder(
|
|||
def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True,
|
||||
allow_nan=True, cls=None, indent=None, separators=None,
|
||||
encoding='utf-8', default=None, **kw):
|
||||
"""
|
||||
Serialize ``obj`` as a JSON formatted stream to ``fp`` (a
|
||||
"""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
|
||||
|
|
@ -167,6 +185,7 @@ def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True,
|
|||
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 (skipkeys is False and ensure_ascii is True and
|
||||
|
|
@ -190,8 +209,7 @@ def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True,
|
|||
def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True,
|
||||
allow_nan=True, cls=None, indent=None, separators=None,
|
||||
encoding='utf-8', default=None, **kw):
|
||||
"""
|
||||
Serialize ``obj`` to a JSON formatted ``str``.
|
||||
"""Serialize ``obj`` to a JSON formatted ``str``.
|
||||
|
||||
If ``skipkeys`` is ``True`` then ``dict`` keys that are not basic types
|
||||
(``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
|
||||
|
|
@ -227,6 +245,7 @@ def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True,
|
|||
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 (skipkeys is False and ensure_ascii is True and
|
||||
|
|
@ -248,8 +267,7 @@ _default_decoder = JSONDecoder(encoding=None, object_hook=None)
|
|||
|
||||
def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None,
|
||||
parse_int=None, parse_constant=None, **kw):
|
||||
"""
|
||||
Deserialize ``fp`` (a ``.read()``-supporting file-like object containing
|
||||
"""Deserialize ``fp`` (a ``.read()``-supporting file-like object containing
|
||||
a JSON document) to a Python object.
|
||||
|
||||
If the contents of ``fp`` is encoded with an ASCII based encoding other
|
||||
|
|
@ -266,6 +284,7 @@ def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None,
|
|||
|
||||
To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
|
||||
kwarg.
|
||||
|
||||
"""
|
||||
return loads(fp.read(),
|
||||
encoding=encoding, cls=cls, object_hook=object_hook,
|
||||
|
|
@ -275,8 +294,7 @@ def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None,
|
|||
|
||||
def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None,
|
||||
parse_int=None, parse_constant=None, **kw):
|
||||
"""
|
||||
Deserialize ``s`` (a ``str`` or ``unicode`` instance containing a JSON
|
||||
"""Deserialize ``s`` (a ``str`` or ``unicode`` instance containing a JSON
|
||||
document) to a Python object.
|
||||
|
||||
If ``s`` is a ``str`` instance and is encoded with an ASCII based encoding
|
||||
|
|
@ -306,6 +324,7 @@ def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None,
|
|||
|
||||
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
|
||||
|
|
@ -322,55 +341,3 @@ def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None,
|
|||
if parse_constant is not None:
|
||||
kw['parse_constant'] = parse_constant
|
||||
return cls(encoding=encoding, **kw).decode(s)
|
||||
|
||||
|
||||
#
|
||||
# Compatibility cruft from other libraries
|
||||
#
|
||||
|
||||
|
||||
def decode(s):
|
||||
"""
|
||||
demjson, python-cjson API compatibility hook. Use loads(s) instead.
|
||||
"""
|
||||
import warnings
|
||||
warnings.warn("simplejson.loads(s) should be used instead of decode(s)",
|
||||
DeprecationWarning)
|
||||
return loads(s)
|
||||
|
||||
|
||||
def encode(obj):
|
||||
"""
|
||||
demjson, python-cjson compatibility hook. Use dumps(s) instead.
|
||||
"""
|
||||
import warnings
|
||||
warnings.warn("simplejson.dumps(s) should be used instead of encode(s)",
|
||||
DeprecationWarning)
|
||||
return dumps(obj)
|
||||
|
||||
|
||||
def read(s):
|
||||
"""
|
||||
jsonlib, JsonUtils, python-json, json-py API compatibility hook.
|
||||
Use loads(s) instead.
|
||||
"""
|
||||
import warnings
|
||||
warnings.warn("simplejson.loads(s) should be used instead of read(s)",
|
||||
DeprecationWarning)
|
||||
return loads(s)
|
||||
|
||||
|
||||
def write(obj):
|
||||
"""
|
||||
jsonlib, JsonUtils, python-json, json-py API compatibility hook.
|
||||
Use dumps(s) instead.
|
||||
"""
|
||||
import warnings
|
||||
warnings.warn("simplejson.dumps(s) should be used instead of write(s)",
|
||||
DeprecationWarning)
|
||||
return dumps(obj)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
import simplejson.tool
|
||||
simplejson.tool.main()
|
||||
|
|
|
|||
|
|
@ -1,20 +1,17 @@
|
|||
"""
|
||||
Implementation of JSONDecoder
|
||||
"""Implementation of JSONDecoder
|
||||
"""
|
||||
import re
|
||||
import sys
|
||||
import struct
|
||||
|
||||
from django.utils.simplejson.scanner import Scanner, pattern
|
||||
try:
|
||||
from django.utils.simplejson._speedups import scanstring as c_scanstring
|
||||
except ImportError:
|
||||
pass
|
||||
from django.utils.simplejson.scanner import make_scanner
|
||||
c_scanstring = None
|
||||
|
||||
__all__ = ['JSONDecoder']
|
||||
|
||||
FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL
|
||||
|
||||
def _floatconstants():
|
||||
import struct
|
||||
import sys
|
||||
_BYTES = '7FF80000000000007FF0000000000000'.decode('hex')
|
||||
if sys.byteorder != 'big':
|
||||
_BYTES = _BYTES[:8][::-1] + _BYTES[8:][::-1]
|
||||
|
|
@ -34,6 +31,7 @@ def linecol(doc, pos):
|
|||
|
||||
|
||||
def errmsg(msg, doc, pos, end=None):
|
||||
# Note that this function is called from _speedups
|
||||
lineno, colno = linecol(doc, pos)
|
||||
if end is None:
|
||||
return '%s: line %d column %d (char %d)' % (msg, lineno, colno, pos)
|
||||
|
|
@ -46,35 +44,8 @@ _CONSTANTS = {
|
|||
'-Infinity': NegInf,
|
||||
'Infinity': PosInf,
|
||||
'NaN': NaN,
|
||||
'true': True,
|
||||
'false': False,
|
||||
'null': None,
|
||||
}
|
||||
|
||||
def JSONConstant(match, context, c=_CONSTANTS):
|
||||
s = match.group(0)
|
||||
fn = getattr(context, 'parse_constant', None)
|
||||
if fn is None:
|
||||
rval = c[s]
|
||||
else:
|
||||
rval = fn(s)
|
||||
return rval, None
|
||||
pattern('(-?Infinity|NaN|true|false|null)')(JSONConstant)
|
||||
|
||||
|
||||
def JSONNumber(match, context):
|
||||
match = JSONNumber.regex.match(match.string, *match.span())
|
||||
integer, frac, exp = match.groups()
|
||||
if frac or exp:
|
||||
fn = getattr(context, 'parse_float', None) or float
|
||||
res = fn(integer + (frac or '') + (exp or ''))
|
||||
else:
|
||||
fn = getattr(context, 'parse_int', None) or int
|
||||
res = fn(integer)
|
||||
return res, None
|
||||
pattern(r'(-?(?:0|[1-9]\d*))(\.\d+)?([eE][-+]?\d+)?')(JSONNumber)
|
||||
|
||||
|
||||
STRINGCHUNK = re.compile(r'(.*?)(["\\\x00-\x1f])', FLAGS)
|
||||
BACKSLASH = {
|
||||
'"': u'"', '\\': u'\\', '/': u'/',
|
||||
|
|
@ -84,6 +55,14 @@ BACKSLASH = {
|
|||
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 = []
|
||||
|
|
@ -96,15 +75,19 @@ def py_scanstring(s, end, encoding=None, strict=True, _b=BACKSLASH, _m=STRINGCHU
|
|||
errmsg("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:
|
||||
raise ValueError(errmsg("Invalid control character %r at", s, end))
|
||||
msg = "Invalid control character %r at" % (terminator,)
|
||||
raise ValueError(msg, s, end)
|
||||
else:
|
||||
_append(terminator)
|
||||
continue
|
||||
|
|
@ -113,139 +96,159 @@ def py_scanstring(s, end, encoding=None, strict=True, _b=BACKSLASH, _m=STRINGCHU
|
|||
except IndexError:
|
||||
raise ValueError(
|
||||
errmsg("Unterminated string starting at", s, begin))
|
||||
# If not a unicode escape sequence, must be in the lookup table
|
||||
if esc != 'u':
|
||||
try:
|
||||
m = _b[esc]
|
||||
char = _b[esc]
|
||||
except KeyError:
|
||||
raise ValueError(
|
||||
errmsg("Invalid \\escape: %r" % (esc,), s, end))
|
||||
end += 1
|
||||
else:
|
||||
# Unicode escape sequence
|
||||
esc = s[end + 1:end + 5]
|
||||
next_end = end + 5
|
||||
msg = "Invalid \\uXXXX escape"
|
||||
try:
|
||||
if len(esc) != 4:
|
||||
raise ValueError
|
||||
msg = "Invalid \\uXXXX escape"
|
||||
raise ValueError(errmsg(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 ValueError
|
||||
raise ValueError(errmsg(msg, s, end))
|
||||
esc2 = s[end + 7:end + 11]
|
||||
if len(esc2) != 4:
|
||||
raise ValueError
|
||||
raise ValueError(errmsg(msg, s, end))
|
||||
uni2 = int(esc2, 16)
|
||||
uni = 0x10000 + (((uni - 0xd800) << 10) | (uni2 - 0xdc00))
|
||||
next_end += 6
|
||||
m = unichr(uni)
|
||||
except ValueError:
|
||||
raise ValueError(errmsg(msg, s, end))
|
||||
char = unichr(uni)
|
||||
end = next_end
|
||||
_append(m)
|
||||
# Append the unescaped character
|
||||
_append(char)
|
||||
return u''.join(chunks), end
|
||||
|
||||
|
||||
# Use speedup
|
||||
try:
|
||||
scanstring = c_scanstring
|
||||
except NameError:
|
||||
scanstring = py_scanstring
|
||||
# Use speedup if available
|
||||
scanstring = c_scanstring or py_scanstring
|
||||
|
||||
def JSONString(match, context):
|
||||
encoding = getattr(context, 'encoding', None)
|
||||
strict = getattr(context, 'strict', True)
|
||||
return scanstring(match.string, match.end(), encoding, strict)
|
||||
pattern(r'"')(JSONString)
|
||||
WHITESPACE = re.compile(r'[ \t\n\r]*', FLAGS)
|
||||
WHITESPACE_STR = ' \t\n\r'
|
||||
|
||||
|
||||
WHITESPACE = re.compile(r'\s*', FLAGS)
|
||||
|
||||
def JSONObject(match, context, _w=WHITESPACE.match):
|
||||
def JSONObject((s, end), encoding, strict, scan_once, object_hook, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
|
||||
pairs = {}
|
||||
s = match.string
|
||||
end = _w(s, match.end()).end()
|
||||
# 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 == '}':
|
||||
return pairs, end + 1
|
||||
if nextchar != '"':
|
||||
elif nextchar != '"':
|
||||
raise ValueError(errmsg("Expecting property name", s, end))
|
||||
end += 1
|
||||
encoding = getattr(context, 'encoding', None)
|
||||
strict = getattr(context, 'strict', True)
|
||||
iterscan = JSONScanner.iterscan
|
||||
while True:
|
||||
key, end = scanstring(s, end, encoding, strict)
|
||||
|
||||
# To skip some function call overhead we optimize the fast paths where
|
||||
# the JSON key separator is ": " or just ":".
|
||||
if s[end:end + 1] != ':':
|
||||
end = _w(s, end).end()
|
||||
if s[end:end + 1] != ':':
|
||||
raise ValueError(errmsg("Expecting : delimiter", s, end))
|
||||
end = _w(s, end + 1).end()
|
||||
|
||||
end += 1
|
||||
|
||||
try:
|
||||
value, end = iterscan(s, idx=end, context=context).next()
|
||||
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 ValueError(errmsg("Expecting object", s, end))
|
||||
pairs[key] = value
|
||||
end = _w(s, end).end()
|
||||
nextchar = s[end:end + 1]
|
||||
|
||||
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
|
||||
if nextchar != ',':
|
||||
elif nextchar != ',':
|
||||
raise ValueError(errmsg("Expecting , delimiter", s, end - 1))
|
||||
end = _w(s, end).end()
|
||||
nextchar = s[end: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 ValueError(errmsg("Expecting property name", s, end - 1))
|
||||
object_hook = getattr(context, 'object_hook', None)
|
||||
|
||||
if object_hook is not None:
|
||||
pairs = object_hook(pairs)
|
||||
return pairs, end
|
||||
pattern(r'{')(JSONObject)
|
||||
|
||||
|
||||
def JSONArray(match, context, _w=WHITESPACE.match):
|
||||
def JSONArray((s, end), scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
|
||||
values = []
|
||||
s = match.string
|
||||
end = _w(s, match.end()).end()
|
||||
# Look-ahead for trivial empty array
|
||||
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
|
||||
iterscan = JSONScanner.iterscan
|
||||
_append = values.append
|
||||
while True:
|
||||
try:
|
||||
value, end = iterscan(s, idx=end, context=context).next()
|
||||
value, end = scan_once(s, end)
|
||||
except StopIteration:
|
||||
raise ValueError(errmsg("Expecting object", s, end))
|
||||
values.append(value)
|
||||
end = _w(s, end).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
|
||||
if nextchar != ',':
|
||||
elif nextchar != ',':
|
||||
raise ValueError(errmsg("Expecting , delimiter", s, end))
|
||||
end = _w(s, end).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
|
||||
pattern(r'\[')(JSONArray)
|
||||
|
||||
|
||||
ANYTHING = [
|
||||
JSONObject,
|
||||
JSONArray,
|
||||
JSONString,
|
||||
JSONConstant,
|
||||
JSONNumber,
|
||||
]
|
||||
|
||||
JSONScanner = Scanner(ANYTHING)
|
||||
|
||||
|
||||
class JSONDecoder(object):
|
||||
"""
|
||||
Simple JSON <http://json.org> decoder
|
||||
"""Simple JSON <http://json.org> decoder
|
||||
|
||||
Performs the following translations in decoding by default:
|
||||
|
||||
|
|
@ -271,15 +274,12 @@ class JSONDecoder(object):
|
|||
|
||||
It also understands ``NaN``, ``Infinity``, and ``-Infinity`` as
|
||||
their corresponding ``float`` values, which is outside the JSON spec.
|
||||
"""
|
||||
|
||||
_scanner = Scanner(ANYTHING)
|
||||
__all__ = ['__init__', 'decode', 'raw_decode']
|
||||
"""
|
||||
|
||||
def __init__(self, encoding=None, object_hook=None, parse_float=None,
|
||||
parse_int=None, parse_constant=None, strict=True):
|
||||
"""
|
||||
``encoding`` determines the encoding used to interpret any ``str``
|
||||
"""``encoding`` determines the encoding used to interpret any ``str``
|
||||
objects decoded by this instance (utf-8 by default). It has no
|
||||
effect when decoding ``unicode`` objects.
|
||||
|
||||
|
|
@ -302,21 +302,26 @@ class JSONDecoder(object):
|
|||
for JSON integers (e.g. float).
|
||||
|
||||
``parse_constant``, if specified, will be called with one of the
|
||||
following strings: -Infinity, Infinity, NaN, null, true, false.
|
||||
following strings: -Infinity, Infinity, NaN.
|
||||
This can be used to raise an exception if invalid JSON numbers
|
||||
are encountered.
|
||||
|
||||
"""
|
||||
self.encoding = encoding
|
||||
self.object_hook = object_hook
|
||||
self.parse_float = parse_float
|
||||
self.parse_int = parse_int
|
||||
self.parse_constant = parse_constant
|
||||
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.scan_once = make_scanner(self)
|
||||
|
||||
def decode(self, s, _w=WHITESPACE.match):
|
||||
"""
|
||||
Return the Python representation of ``s`` (a ``str`` or ``unicode``
|
||||
"""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()
|
||||
|
|
@ -324,20 +329,17 @@ class JSONDecoder(object):
|
|||
raise ValueError(errmsg("Extra data", s, end, len(s)))
|
||||
return obj
|
||||
|
||||
def raw_decode(self, s, **kw):
|
||||
"""
|
||||
Decode a JSON document from ``s`` (a ``str`` or ``unicode`` beginning
|
||||
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.
|
||||
|
||||
"""
|
||||
kw.setdefault('context', self)
|
||||
try:
|
||||
obj, end = self._scanner.iterscan(s, **kw).next()
|
||||
obj, end = self.scan_once(s, idx)
|
||||
except StopIteration:
|
||||
raise ValueError("No JSON object could be decoded")
|
||||
return obj, end
|
||||
|
||||
__all__ = ['JSONDecoder']
|
||||
|
|
|
|||
|
|
@ -1,12 +1,9 @@
|
|||
"""
|
||||
Implementation of JSONEncoder
|
||||
"""Implementation of JSONEncoder
|
||||
"""
|
||||
import re
|
||||
|
||||
try:
|
||||
from django.utils.simplejson._speedups import encode_basestring_ascii as c_encode_basestring_ascii
|
||||
except ImportError:
|
||||
pass
|
||||
c_encode_basestring_ascii = None
|
||||
c_make_encoder = None
|
||||
|
||||
ESCAPE = re.compile(r'[\x00-\x1f\\"\b\f\n\r\t]')
|
||||
ESCAPE_ASCII = re.compile(r'([\\"]|[^\ -~])')
|
||||
|
|
@ -27,29 +24,9 @@ for i in range(0x20):
|
|||
INFINITY = float('1e66666')
|
||||
FLOAT_REPR = repr
|
||||
|
||||
def floatstr(o, allow_nan=True):
|
||||
# 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 == INFINITY:
|
||||
text = 'Infinity'
|
||||
elif o == -INFINITY:
|
||||
text = '-Infinity'
|
||||
else:
|
||||
return FLOAT_REPR(o)
|
||||
|
||||
if not allow_nan:
|
||||
raise ValueError("Out of range float values are not JSON compliant: %r"
|
||||
% (o,))
|
||||
|
||||
return text
|
||||
|
||||
|
||||
def encode_basestring(s):
|
||||
"""
|
||||
Return a JSON representation of a Python string
|
||||
"""Return a JSON representation of a Python string
|
||||
|
||||
"""
|
||||
def replace(match):
|
||||
return ESCAPE_DCT[match.group(0)]
|
||||
|
|
@ -57,6 +34,9 @@ def encode_basestring(s):
|
|||
|
||||
|
||||
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):
|
||||
|
|
@ -76,15 +56,10 @@ def py_encode_basestring_ascii(s):
|
|||
return '"' + str(ESCAPE_ASCII.sub(replace, s)) + '"'
|
||||
|
||||
|
||||
try:
|
||||
encode_basestring_ascii = c_encode_basestring_ascii
|
||||
except NameError:
|
||||
encode_basestring_ascii = py_encode_basestring_ascii
|
||||
|
||||
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.
|
||||
"""Extensible JSON <http://json.org> encoder for Python data structures.
|
||||
|
||||
Supports the following objects and types by default:
|
||||
|
||||
|
|
@ -110,15 +85,14 @@ class JSONEncoder(object):
|
|||
``.default()`` method with another method that returns a serializable
|
||||
object for ``o`` if possible, otherwise it should call the superclass
|
||||
implementation (to raise ``TypeError``).
|
||||
|
||||
"""
|
||||
__all__ = ['__init__', 'default', 'encode', 'iterencode']
|
||||
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):
|
||||
"""
|
||||
Constructor for JSONEncoder, with sensible defaults.
|
||||
"""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
|
||||
|
|
@ -158,6 +132,7 @@ class JSONEncoder(object):
|
|||
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.
|
||||
|
||||
"""
|
||||
|
||||
self.skipkeys = skipkeys
|
||||
|
|
@ -166,165 +141,14 @@ class JSONEncoder(object):
|
|||
self.allow_nan = allow_nan
|
||||
self.sort_keys = sort_keys
|
||||
self.indent = indent
|
||||
self.current_indent_level = 0
|
||||
if separators is not None:
|
||||
self.item_separator, self.key_separator = separators
|
||||
if default is not None:
|
||||
self.default = default
|
||||
self.encoding = encoding
|
||||
|
||||
def _newline_indent(self):
|
||||
return '\n' + (' ' * (self.indent * self.current_indent_level))
|
||||
|
||||
def _iterencode_list(self, lst, markers=None):
|
||||
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
|
||||
yield '['
|
||||
if self.indent is not None:
|
||||
self.current_indent_level += 1
|
||||
newline_indent = self._newline_indent()
|
||||
separator = self.item_separator + newline_indent
|
||||
yield newline_indent
|
||||
else:
|
||||
newline_indent = None
|
||||
separator = self.item_separator
|
||||
first = True
|
||||
for value in lst:
|
||||
if first:
|
||||
first = False
|
||||
else:
|
||||
yield separator
|
||||
for chunk in self._iterencode(value, markers):
|
||||
yield chunk
|
||||
if newline_indent is not None:
|
||||
self.current_indent_level -= 1
|
||||
yield self._newline_indent()
|
||||
yield ']'
|
||||
if markers is not None:
|
||||
del markers[markerid]
|
||||
|
||||
def _iterencode_dict(self, dct, markers=None):
|
||||
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 '{'
|
||||
key_separator = self.key_separator
|
||||
if self.indent is not None:
|
||||
self.current_indent_level += 1
|
||||
newline_indent = self._newline_indent()
|
||||
item_separator = self.item_separator + newline_indent
|
||||
yield newline_indent
|
||||
else:
|
||||
newline_indent = None
|
||||
item_separator = self.item_separator
|
||||
first = True
|
||||
if self.ensure_ascii:
|
||||
encoder = encode_basestring_ascii
|
||||
else:
|
||||
encoder = encode_basestring
|
||||
allow_nan = self.allow_nan
|
||||
if self.sort_keys:
|
||||
keys = dct.keys()
|
||||
keys.sort()
|
||||
items = [(k, dct[k]) for k in keys]
|
||||
else:
|
||||
items = dct.iteritems()
|
||||
_encoding = self.encoding
|
||||
_do_decode = (_encoding is not None
|
||||
and not (_encoding == 'utf-8'))
|
||||
for key, value in items:
|
||||
if isinstance(key, str):
|
||||
if _do_decode:
|
||||
key = key.decode(_encoding)
|
||||
elif 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, allow_nan)
|
||||
elif isinstance(key, (int, long)):
|
||||
key = str(key)
|
||||
elif key is True:
|
||||
key = 'true'
|
||||
elif key is False:
|
||||
key = 'false'
|
||||
elif key is None:
|
||||
key = 'null'
|
||||
elif self.skipkeys:
|
||||
continue
|
||||
else:
|
||||
raise TypeError("key %r is not a string" % (key,))
|
||||
if first:
|
||||
first = False
|
||||
else:
|
||||
yield item_separator
|
||||
yield encoder(key)
|
||||
yield key_separator
|
||||
for chunk in self._iterencode(value, markers):
|
||||
yield chunk
|
||||
if newline_indent is not None:
|
||||
self.current_indent_level -= 1
|
||||
yield self._newline_indent()
|
||||
yield '}'
|
||||
if markers is not None:
|
||||
del markers[markerid]
|
||||
|
||||
def _iterencode(self, o, markers=None):
|
||||
if isinstance(o, basestring):
|
||||
if self.ensure_ascii:
|
||||
encoder = encode_basestring_ascii
|
||||
else:
|
||||
encoder = encode_basestring
|
||||
_encoding = self.encoding
|
||||
if (_encoding is not None and isinstance(o, str)
|
||||
and not (_encoding == 'utf-8')):
|
||||
o = o.decode(_encoding)
|
||||
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, self.allow_nan)
|
||||
elif isinstance(o, (list, tuple)):
|
||||
for chunk in self._iterencode_list(o, markers):
|
||||
yield chunk
|
||||
elif isinstance(o, dict):
|
||||
for chunk in self._iterencode_dict(o, markers):
|
||||
yield chunk
|
||||
else:
|
||||
if markers is not None:
|
||||
markerid = id(o)
|
||||
if markerid in markers:
|
||||
raise ValueError("Circular reference detected")
|
||||
markers[markerid] = o
|
||||
for chunk in self._iterencode_default(o, markers):
|
||||
yield chunk
|
||||
if markers is not None:
|
||||
del markers[markerid]
|
||||
|
||||
def _iterencode_default(self, o, markers=None):
|
||||
newobj = self.default(o)
|
||||
return self._iterencode(newobj, markers)
|
||||
|
||||
def default(self, o):
|
||||
"""
|
||||
Implement this method in a subclass such that it returns
|
||||
"""Implement this method in a subclass such that it returns
|
||||
a serializable object for ``o``, or calls the base implementation
|
||||
(to raise a ``TypeError``).
|
||||
|
||||
|
|
@ -339,15 +163,16 @@ class JSONEncoder(object):
|
|||
else:
|
||||
return list(iterable)
|
||||
return JSONEncoder.default(self, o)
|
||||
|
||||
"""
|
||||
raise TypeError("%r is not JSON serializable" % (o,))
|
||||
|
||||
def encode(self, o):
|
||||
"""
|
||||
Return a JSON string representation of a Python data structure.
|
||||
"""Return a JSON string representation of a Python data structure.
|
||||
|
||||
>>> JSONEncoder().encode({"foo": ["bar", "baz"]})
|
||||
'{"foo": ["bar", "baz"]}'
|
||||
|
||||
"""
|
||||
# This is for extremely simple cases and benchmarks.
|
||||
if isinstance(o, basestring):
|
||||
|
|
@ -363,23 +188,243 @@ class JSONEncoder(object):
|
|||
# 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 = list(self.iterencode(o))
|
||||
chunks = self.iterencode(o, _one_shot=True)
|
||||
if not isinstance(chunks, (list, tuple)):
|
||||
chunks = list(chunks)
|
||||
return ''.join(chunks)
|
||||
|
||||
def iterencode(self, o):
|
||||
"""
|
||||
Encode the given object and yield each string
|
||||
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
|
||||
return self._iterencode(o, markers)
|
||||
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)
|
||||
|
||||
__all__ = ['JSONEncoder']
|
||||
def floatstr(o, allow_nan=self.allow_nan, _repr=FLOAT_REPR, _inf=INFINITY, _neginf=-INFINITY):
|
||||
# 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: %r"
|
||||
% (o,))
|
||||
|
||||
return text
|
||||
|
||||
|
||||
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)
|
||||
else:
|
||||
_iterencode = _make_iterencode(
|
||||
markers, self.default, _encoder, self.indent, floatstr,
|
||||
self.key_separator, self.item_separator, self.sort_keys,
|
||||
self.skipkeys, _one_shot)
|
||||
return _iterencode(o, 0)
|
||||
|
||||
def _make_iterencode(markers, _default, _encoder, _indent, _floatstr, _key_separator, _item_separator, _sort_keys, _skipkeys, _one_shot,
|
||||
## HACK: hand-optimized bytecode; turn globals into locals
|
||||
False=False,
|
||||
True=True,
|
||||
ValueError=ValueError,
|
||||
basestring=basestring,
|
||||
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)
|
||||
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 isinstance(key, (int, long)):
|
||||
key = str(key)
|
||||
elif key is True:
|
||||
key = 'true'
|
||||
elif key is False:
|
||||
key = 'false'
|
||||
elif key is None:
|
||||
key = 'null'
|
||||
elif _skipkeys:
|
||||
continue
|
||||
else:
|
||||
raise TypeError("key %r is not a string" % (key,))
|
||||
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)
|
||||
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
|
||||
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
|
||||
|
|
|
|||
|
|
@ -1,67 +1,65 @@
|
|||
"""
|
||||
Iterator based sre token scanner
|
||||
"""JSON token scanner
|
||||
"""
|
||||
import re
|
||||
from re import VERBOSE, MULTILINE, DOTALL
|
||||
import sre_parse
|
||||
import sre_compile
|
||||
import sre_constants
|
||||
from sre_constants import BRANCH, SUBPATTERN
|
||||
|
||||
__all__ = ['Scanner', 'pattern']
|
||||
|
||||
FLAGS = (VERBOSE | MULTILINE | DOTALL)
|
||||
|
||||
class Scanner(object):
|
||||
def __init__(self, lexicon, flags=FLAGS):
|
||||
self.actions = [None]
|
||||
# Combine phrases into a compound pattern
|
||||
s = sre_parse.Pattern()
|
||||
s.flags = flags
|
||||
p = []
|
||||
for idx, token in enumerate(lexicon):
|
||||
phrase = token.pattern
|
||||
try:
|
||||
subpattern = sre_parse.SubPattern(s,
|
||||
[(SUBPATTERN, (idx + 1, sre_parse.parse(phrase, flags)))])
|
||||
except sre_constants.error:
|
||||
raise
|
||||
p.append(subpattern)
|
||||
self.actions.append(token)
|
||||
from simplejson._speedups import make_scanner as c_make_scanner
|
||||
except ImportError:
|
||||
c_make_scanner = None
|
||||
|
||||
s.groups = len(p) + 1 # NOTE(guido): Added to make SRE validation work
|
||||
p = sre_parse.SubPattern(s, [(BRANCH, (None, p))])
|
||||
self.scanner = sre_compile.compile(p)
|
||||
__all__ = ['make_scanner']
|
||||
|
||||
def iterscan(self, string, idx=0, context=None):
|
||||
"""
|
||||
Yield match, end_idx for each match
|
||||
"""
|
||||
match = self.scanner.scanner(string, idx).match
|
||||
actions = self.actions
|
||||
lastend = idx
|
||||
end = len(string)
|
||||
while True:
|
||||
m = match()
|
||||
if m is None:
|
||||
break
|
||||
matchbegin, matchend = m.span()
|
||||
if lastend == matchend:
|
||||
break
|
||||
action = actions[m.lastindex]
|
||||
if action is not None:
|
||||
rval, next_pos = action(m, context)
|
||||
if next_pos is not None and next_pos != matchend:
|
||||
# "fast forward" the scanner
|
||||
matchend = next_pos
|
||||
match = self.scanner.scanner(string, matchend).match
|
||||
yield rval, matchend
|
||||
lastend = matchend
|
||||
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
|
||||
|
||||
def pattern(pattern, flags=FLAGS):
|
||||
def decorator(fn):
|
||||
fn.pattern = pattern
|
||||
fn.regex = re.compile(pattern, flags)
|
||||
return fn
|
||||
return decorator
|
||||
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)
|
||||
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
|
||||
|
||||
return _scan_once
|
||||
|
||||
make_scanner = c_make_scanner or py_make_scanner
|
||||
|
|
|
|||
|
|
@ -1,23 +1,14 @@
|
|||
r"""
|
||||
Using simplejson from the shell to validate and
|
||||
r"""Using simplejson from the shell to validate and
|
||||
pretty-print::
|
||||
|
||||
$ echo '{"json":"obj"}' | python -msimplejson
|
||||
$ echo '{"json":"obj"}' | python -msimplejson.tool
|
||||
{
|
||||
"json": "obj"
|
||||
}
|
||||
$ echo '{ 1.2:3.4}' | python -msimplejson
|
||||
$ echo '{ 1.2:3.4}' | python -msimplejson.tool
|
||||
Expecting property name: line 1 column 2 (char 2)
|
||||
|
||||
Note that the JSON produced by this module's default settings
|
||||
is a subset of YAML, so it may be used as a serializer for that as well.
|
||||
"""
|
||||
import django.utils.simplejson
|
||||
|
||||
#
|
||||
# Pretty printer:
|
||||
# curl http://mochikit.com/examples/ajax_tables/domains.json | python -msimplejson.tool
|
||||
#
|
||||
from django.utils import simplejson
|
||||
|
||||
def main():
|
||||
import sys
|
||||
|
|
|
|||
|
|
@ -162,11 +162,17 @@ For example::
|
|||
json_serializer = serializers.get_serializer("json")()
|
||||
json_serializer.serialize(queryset, ensure_ascii=False, stream=response)
|
||||
|
||||
The Django source code includes the simplejson_ module. Be aware that if you're
|
||||
serializing using that module directly, not all Django output can be passed
|
||||
unmodified to simplejson. In particular, :ref:`lazy translation objects
|
||||
<lazy-translations>` need a `special encoder`_ written for them. Something like
|
||||
this will work::
|
||||
The Django source code includes the simplejson_ module. However, if you're
|
||||
using Python 2.6 (which includes a builtin version of the module), Django will
|
||||
use the builtin ``json`` module automatically. If you have a system installed
|
||||
version that includes the C-based speedup extension, or your system version is
|
||||
more recent than the version shipped with Django (currently, 2.0.7), the
|
||||
system version will be used instead of the version included with Django.
|
||||
|
||||
Be aware that if you're serializing using that module directly, not all Django
|
||||
output can be passed unmodified to simplejson. In particular, :ref:`lazy
|
||||
translation objects <lazy-translations>` need a `special encoder`_ written for
|
||||
them. Something like this will work::
|
||||
|
||||
from django.utils.functional import Promise
|
||||
from django.utils.encoding import force_unicode
|
||||
|
|
@ -178,3 +184,4 @@ this will work::
|
|||
return obj
|
||||
|
||||
.. _special encoder: http://svn.red-bean.com/bob/simplejson/tags/simplejson-1.7/docs/index.html
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue