mirror of https://github.com/django/django.git
Fixed #7131 -- Updated included simplejson code to match the simplejson-1.9.2
release. This should be fully backwards-compatible for people using the public interfaces. git-svn-id: http://code.djangoproject.com/svn/django/trunk@8124 bcc190cf-cafb-0310-a4f2-bffc1f526a37
This commit is contained in:
Malcolm Tredinnick
parent
de9e2ae5bb
commit
d57ce3d6a9
|
|
@ -1,4 +1,3 @@
|
|||
simplejson 1.5
|
||||
Copyright (c) 2006 Bob Ippolito
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy of
|
||||
|
|
|
|||
|
|
@ -65,6 +65,9 @@ Specializing JSON object decoding::
|
|||
>>> simplejson.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")
|
||||
|
||||
Extending JSONEncoder::
|
||||
|
||||
|
|
@ -83,20 +86,48 @@ Extending JSONEncoder::
|
|||
['[', '2.0', ', ', '1.0', ']']
|
||||
|
||||
|
||||
Using simplejson from the shell to validate and
|
||||
pretty-print::
|
||||
|
||||
$ echo '{"json":"obj"}' | python -msimplejson.tool
|
||||
{
|
||||
"json": "obj"
|
||||
}
|
||||
$ 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__ = '1.5'
|
||||
__version__ = '1.9.2'
|
||||
__all__ = [
|
||||
'dump', 'dumps', 'load', 'loads',
|
||||
'JSONDecoder', 'JSONEncoder',
|
||||
]
|
||||
|
||||
from django.utils.simplejson.decoder import JSONDecoder
|
||||
from django.utils.simplejson.encoder import 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,
|
||||
ensure_ascii=True,
|
||||
check_circular=True,
|
||||
allow_nan=True,
|
||||
indent=None,
|
||||
separators=None,
|
||||
encoding='utf-8',
|
||||
default=None,
|
||||
)
|
||||
|
||||
def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True,
|
||||
allow_nan=True, cls=None, indent=None, **kw):
|
||||
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
|
||||
``.write()``-supporting file-like object).
|
||||
|
|
@ -107,7 +138,7 @@ def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True,
|
|||
|
||||
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
|
||||
``unicode`` coercion rules. Unless ``fp.write()`` explicitly
|
||||
understands ``unicode`` (as in ``codecs.getwriter()``) this is likely
|
||||
to cause an error.
|
||||
|
||||
|
|
@ -121,25 +152,44 @@ def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True,
|
|||
JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).
|
||||
|
||||
If ``indent`` is a non-negative integer, then JSON array elements and object
|
||||
members will be pretty-printed with that indent level. An indent level
|
||||
of 0 will only insert newlines. ``None`` is the most compact representation.
|
||||
members will be pretty-printed with that indent level. An indent level
|
||||
of 0 will only insert newlines. ``None`` is the most compact representation.
|
||||
|
||||
If ``separators`` is an ``(item_separator, dict_separator)`` tuple
|
||||
then it will be used instead of the default ``(', ', ': ')`` separators.
|
||||
``(',', ':')`` is the most compact JSON representation.
|
||||
|
||||
``encoding`` is the character encoding for str instances, default is UTF-8.
|
||||
|
||||
``default(obj)`` is a function that should return a serializable version
|
||||
of obj or raise TypeError. The default simply raises TypeError.
|
||||
|
||||
To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the
|
||||
``.default()`` method to serialize additional types), specify it with
|
||||
the ``cls`` kwarg.
|
||||
"""
|
||||
if cls is None:
|
||||
cls = JSONEncoder
|
||||
iterable = cls(skipkeys=skipkeys, ensure_ascii=ensure_ascii,
|
||||
check_circular=check_circular, allow_nan=allow_nan, indent=indent,
|
||||
**kw).iterencode(obj)
|
||||
# cached encoder
|
||||
if (skipkeys is False and ensure_ascii is True and
|
||||
check_circular is True and allow_nan is True 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, **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, **kw):
|
||||
allow_nan=True, cls=None, indent=None, separators=None,
|
||||
encoding='utf-8', default=None, **kw):
|
||||
"""
|
||||
Serialize ``obj`` to a JSON formatted ``str``.
|
||||
|
||||
|
|
@ -161,88 +211,159 @@ def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True,
|
|||
JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).
|
||||
|
||||
If ``indent`` is a non-negative integer, then JSON array elements and
|
||||
object members will be pretty-printed with that indent level. An indent
|
||||
level of 0 will only insert newlines. ``None`` is the most compact
|
||||
object members will be pretty-printed with that indent level. An indent
|
||||
level of 0 will only insert newlines. ``None`` is the most compact
|
||||
representation.
|
||||
|
||||
If ``separators`` is an ``(item_separator, dict_separator)`` tuple
|
||||
then it will be used instead of the default ``(', ', ': ')`` separators.
|
||||
``(',', ':')`` is the most compact JSON representation.
|
||||
|
||||
``encoding`` is the character encoding for str instances, default is UTF-8.
|
||||
|
||||
``default(obj)`` is a function that should return a serializable version
|
||||
of obj or raise TypeError. The default simply raises TypeError.
|
||||
|
||||
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
|
||||
check_circular is True and allow_nan is True and
|
||||
cls is None and indent is None and separators is None and
|
||||
encoding == 'utf-8' and default is None and not kw):
|
||||
return _default_encoder.encode(obj)
|
||||
if cls is None:
|
||||
cls = JSONEncoder
|
||||
return cls(
|
||||
skipkeys=skipkeys, ensure_ascii=ensure_ascii,
|
||||
check_circular=check_circular, allow_nan=allow_nan, indent=indent,
|
||||
separators=separators,
|
||||
separators=separators, encoding=encoding, default=default,
|
||||
**kw).encode(obj)
|
||||
|
||||
def load(fp, encoding=None, cls=None, object_hook=None, **kw):
|
||||
|
||||
_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
|
||||
a JSON document) to a Python object.
|
||||
|
||||
If the contents of ``fp`` is encoded with an ASCII based encoding other
|
||||
than utf-8 (e.g. latin-1), then an appropriate ``encoding`` name must
|
||||
be specified. Encodings that are not ASCII based (such as UCS-2) are
|
||||
be specified. Encodings that are not ASCII based (such as UCS-2) are
|
||||
not allowed, and should be wrapped with
|
||||
``codecs.getreader(fp)(encoding)``, or simply decoded to a ``unicode``
|
||||
object and passed to ``loads()``
|
||||
|
||||
``object_hook`` is an optional function that will be called with the
|
||||
result of any object literal decode (a ``dict``). The return value of
|
||||
``object_hook`` will be used instead of the ``dict``. This feature
|
||||
result of any object literal decode (a ``dict``). The return value of
|
||||
``object_hook`` will be used instead of the ``dict``. This feature
|
||||
can be used to implement custom decoders (e.g. JSON-RPC class hinting).
|
||||
|
||||
To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
|
||||
kwarg.
|
||||
"""
|
||||
if cls is None:
|
||||
cls = JSONDecoder
|
||||
if object_hook is not None:
|
||||
kw['object_hook'] = object_hook
|
||||
return cls(encoding=encoding, **kw).decode(fp.read())
|
||||
return loads(fp.read(),
|
||||
encoding=encoding, cls=cls, object_hook=object_hook,
|
||||
parse_float=parse_float, parse_int=parse_int,
|
||||
parse_constant=parse_constant, **kw)
|
||||
|
||||
def loads(s, encoding=None, cls=None, object_hook=None, **kw):
|
||||
|
||||
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
|
||||
document) to a Python object.
|
||||
|
||||
If ``s`` is a ``str`` instance and is encoded with an ASCII based encoding
|
||||
other than utf-8 (e.g. latin-1) then an appropriate ``encoding`` name
|
||||
must be specified. Encodings that are not ASCII based (such as UCS-2)
|
||||
must be specified. Encodings that are not ASCII based (such as UCS-2)
|
||||
are not allowed and should be decoded to ``unicode`` first.
|
||||
|
||||
``object_hook`` is an optional function that will be called with the
|
||||
result of any object literal decode (a ``dict``). The return value of
|
||||
``object_hook`` will be used instead of the ``dict``. This feature
|
||||
result of any object literal decode (a ``dict``). The return value of
|
||||
``object_hook`` will be used instead of the ``dict``. This feature
|
||||
can be used to implement custom decoders (e.g. JSON-RPC class hinting).
|
||||
|
||||
``parse_float``, if specified, will be called with the string
|
||||
of every JSON float to be decoded. By default this is equivalent to
|
||||
float(num_str). This can be used to use another datatype or parser
|
||||
for JSON floats (e.g. decimal.Decimal).
|
||||
|
||||
``parse_int``, if specified, will be called with the string
|
||||
of every JSON int to be decoded. By default this is equivalent to
|
||||
int(num_str). This can be used to use another datatype or parser
|
||||
for JSON integers (e.g. float).
|
||||
|
||||
``parse_constant``, if specified, will be called with one of the
|
||||
following strings: -Infinity, Infinity, NaN, null, true, false.
|
||||
This can be used to raise an exception if invalid JSON numbers
|
||||
are encountered.
|
||||
|
||||
To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
|
||||
kwarg.
|
||||
"""
|
||||
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 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 parse_float is not None:
|
||||
kw['parse_float'] = parse_float
|
||||
if parse_int is not None:
|
||||
kw['parse_int'] = parse_int
|
||||
if parse_constant is not None:
|
||||
kw['parse_constant'] = parse_constant
|
||||
return cls(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):
|
||||
"""
|
||||
json-py API compatibility hook. Use loads(s) instead.
|
||||
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):
|
||||
"""
|
||||
json-py API compatibility hook. Use dumps(s) instead.
|
||||
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)",
|
||||
|
|
@ -250,3 +371,6 @@ def write(obj):
|
|||
return dumps(obj)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
import simplejson.tool
|
||||
simplejson.tool.main()
|
||||
|
|
|
|||
|
|
@ -2,8 +2,13 @@
|
|||
Implementation of JSONDecoder
|
||||
"""
|
||||
import re
|
||||
import sys
|
||||
|
||||
from django.utils.simplejson.scanner import Scanner, pattern
|
||||
try:
|
||||
from django.utils.simplejson._speedups import scanstring as c_scanstring
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL
|
||||
|
||||
|
|
@ -18,6 +23,7 @@ def _floatconstants():
|
|||
|
||||
NaN, PosInf, NegInf = _floatconstants()
|
||||
|
||||
|
||||
def linecol(doc, pos):
|
||||
lineno = doc.count('\n', 0, pos) + 1
|
||||
if lineno == 1:
|
||||
|
|
@ -26,6 +32,7 @@ def linecol(doc, pos):
|
|||
colno = pos - doc.rindex('\n', 0, pos)
|
||||
return lineno, colno
|
||||
|
||||
|
||||
def errmsg(msg, doc, pos, end=None):
|
||||
lineno, colno = linecol(doc, pos)
|
||||
if end is None:
|
||||
|
|
@ -34,6 +41,7 @@ def errmsg(msg, doc, pos, end=None):
|
|||
return '%s: line %d column %d - line %d column %d (char %d - %d)' % (
|
||||
msg, lineno, colno, endlineno, endcolno, pos, end)
|
||||
|
||||
|
||||
_CONSTANTS = {
|
||||
'-Infinity': NegInf,
|
||||
'Infinity': PosInf,
|
||||
|
|
@ -44,20 +52,30 @@ _CONSTANTS = {
|
|||
}
|
||||
|
||||
def JSONConstant(match, context, c=_CONSTANTS):
|
||||
return c[match.group(0)], None
|
||||
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:
|
||||
res = float(integer + (frac or '') + (exp or ''))
|
||||
fn = getattr(context, 'parse_float', None) or float
|
||||
res = fn(integer + (frac or '') + (exp or ''))
|
||||
else:
|
||||
res = int(integer)
|
||||
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'(.*?)(["\\])', FLAGS)
|
||||
|
||||
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',
|
||||
|
|
@ -65,7 +83,7 @@ BACKSLASH = {
|
|||
|
||||
DEFAULT_ENCODING = "utf-8"
|
||||
|
||||
def scanstring(s, end, encoding=None, _b=BACKSLASH, _m=STRINGCHUNK.match):
|
||||
def py_scanstring(s, end, encoding=None, strict=True, _b=BACKSLASH, _m=STRINGCHUNK.match):
|
||||
if encoding is None:
|
||||
encoding = DEFAULT_ENCODING
|
||||
chunks = []
|
||||
|
|
@ -84,6 +102,12 @@ def scanstring(s, end, encoding=None, _b=BACKSLASH, _m=STRINGCHUNK.match):
|
|||
_append(content)
|
||||
if terminator == '"':
|
||||
break
|
||||
elif terminator != '\\':
|
||||
if strict:
|
||||
raise ValueError(errmsg("Invalid control character %r at", s, end))
|
||||
else:
|
||||
_append(terminator)
|
||||
continue
|
||||
try:
|
||||
esc = s[end]
|
||||
except IndexError:
|
||||
|
|
@ -98,21 +122,43 @@ def scanstring(s, end, encoding=None, _b=BACKSLASH, _m=STRINGCHUNK.match):
|
|||
end += 1
|
||||
else:
|
||||
esc = s[end + 1:end + 5]
|
||||
next_end = end + 5
|
||||
msg = "Invalid \\uXXXX escape"
|
||||
try:
|
||||
m = unichr(int(esc, 16))
|
||||
if len(esc) != 4 or not esc.isalnum():
|
||||
if len(esc) != 4:
|
||||
raise ValueError
|
||||
uni = int(esc, 16)
|
||||
if 0xd800 <= uni <= 0xdbff and sys.maxunicode > 65535:
|
||||
msg = "Invalid \\uXXXX\\uXXXX surrogate pair"
|
||||
if not s[end + 5:end + 7] == '\\u':
|
||||
raise ValueError
|
||||
esc2 = s[end + 7:end + 11]
|
||||
if len(esc2) != 4:
|
||||
raise ValueError
|
||||
uni2 = int(esc2, 16)
|
||||
uni = 0x10000 + (((uni - 0xd800) << 10) | (uni2 - 0xdc00))
|
||||
next_end += 6
|
||||
m = unichr(uni)
|
||||
except ValueError:
|
||||
raise ValueError(errmsg("Invalid \\uXXXX escape", s, end))
|
||||
end += 5
|
||||
raise ValueError(errmsg(msg, s, end))
|
||||
end = next_end
|
||||
_append(m)
|
||||
return u''.join(chunks), end
|
||||
|
||||
|
||||
# Use speedup
|
||||
try:
|
||||
scanstring = c_scanstring
|
||||
except NameError:
|
||||
scanstring = py_scanstring
|
||||
|
||||
def JSONString(match, context):
|
||||
encoding = getattr(context, 'encoding', None)
|
||||
return scanstring(match.string, match.end(), encoding)
|
||||
strict = getattr(context, 'strict', True)
|
||||
return scanstring(match.string, match.end(), encoding, strict)
|
||||
pattern(r'"')(JSONString)
|
||||
|
||||
|
||||
WHITESPACE = re.compile(r'\s*', FLAGS)
|
||||
|
||||
def JSONObject(match, context, _w=WHITESPACE.match):
|
||||
|
|
@ -120,16 +166,17 @@ def JSONObject(match, context, _w=WHITESPACE.match):
|
|||
s = match.string
|
||||
end = _w(s, match.end()).end()
|
||||
nextchar = s[end:end + 1]
|
||||
# trivial empty object
|
||||
# Trivial empty object
|
||||
if nextchar == '}':
|
||||
return pairs, end + 1
|
||||
if 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)
|
||||
key, end = scanstring(s, end, encoding, strict)
|
||||
end = _w(s, end).end()
|
||||
if s[end:end + 1] != ':':
|
||||
raise ValueError(errmsg("Expecting : delimiter", s, end))
|
||||
|
|
@ -156,12 +203,13 @@ def JSONObject(match, context, _w=WHITESPACE.match):
|
|||
pairs = object_hook(pairs)
|
||||
return pairs, end
|
||||
pattern(r'{')(JSONObject)
|
||||
|
||||
|
||||
|
||||
def JSONArray(match, context, _w=WHITESPACE.match):
|
||||
values = []
|
||||
s = match.string
|
||||
end = _w(s, match.end()).end()
|
||||
# look-ahead for trivial empty array
|
||||
# Look-ahead for trivial empty array
|
||||
nextchar = s[end:end + 1]
|
||||
if nextchar == ']':
|
||||
return values, end + 1
|
||||
|
|
@ -182,7 +230,8 @@ def JSONArray(match, context, _w=WHITESPACE.match):
|
|||
end = _w(s, end).end()
|
||||
return values, end
|
||||
pattern(r'\[')(JSONArray)
|
||||
|
||||
|
||||
|
||||
ANYTHING = [
|
||||
JSONObject,
|
||||
JSONArray,
|
||||
|
|
@ -193,11 +242,12 @@ ANYTHING = [
|
|||
|
||||
JSONScanner = Scanner(ANYTHING)
|
||||
|
||||
|
||||
class JSONDecoder(object):
|
||||
"""
|
||||
Simple JSON <http://json.org> decoder
|
||||
|
||||
Performs the following translations in decoding:
|
||||
Performs the following translations in decoding by default:
|
||||
|
||||
+---------------+-------------------+
|
||||
| JSON | Python |
|
||||
|
|
@ -226,7 +276,8 @@ class JSONDecoder(object):
|
|||
_scanner = Scanner(ANYTHING)
|
||||
__all__ = ['__init__', 'decode', 'raw_decode']
|
||||
|
||||
def __init__(self, encoding=None, object_hook=None):
|
||||
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``
|
||||
objects decoded by this instance (utf-8 by default). It has no
|
||||
|
|
@ -239,9 +290,28 @@ class JSONDecoder(object):
|
|||
of every JSON object decoded and its return value will be used in
|
||||
place of the given ``dict``. This can be used to provide custom
|
||||
deserializations (e.g. to support JSON-RPC class hinting).
|
||||
|
||||
``parse_float``, if specified, will be called with the string
|
||||
of every JSON float to be decoded. By default this is equivalent to
|
||||
float(num_str). This can be used to use another datatype or parser
|
||||
for JSON floats (e.g. decimal.Decimal).
|
||||
|
||||
``parse_int``, if specified, will be called with the string
|
||||
of every JSON int to be decoded. By default this is equivalent to
|
||||
int(num_str). This can be used to use another datatype or parser
|
||||
for JSON integers (e.g. float).
|
||||
|
||||
``parse_constant``, if specified, will be called with one of the
|
||||
following strings: -Infinity, Infinity, NaN, null, true, false.
|
||||
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.strict = strict
|
||||
|
||||
def decode(self, s, _w=WHITESPACE.match):
|
||||
"""
|
||||
|
|
|
|||
|
|
@ -3,11 +3,15 @@ Implementation of JSONEncoder
|
|||
"""
|
||||
import re
|
||||
|
||||
ESCAPE = re.compile(r'[\x00-\x19\\"\b\f\n\r\t]')
|
||||
ESCAPE_ASCII = re.compile(r'([\\"/]|[^\ -~])')
|
||||
try:
|
||||
from django.utils.simplejson._speedups import encode_basestring_ascii as c_encode_basestring_ascii
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
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 = {
|
||||
# escape all forward slashes to prevent </script> attack
|
||||
'/': '\\/',
|
||||
'\\': '\\\\',
|
||||
'"': '\\"',
|
||||
'\b': '\\b',
|
||||
|
|
@ -19,8 +23,9 @@ ESCAPE_DCT = {
|
|||
for i in range(0x20):
|
||||
ESCAPE_DCT.setdefault(chr(i), '\\u%04x' % (i,))
|
||||
|
||||
# assume this produces an infinity on all machines (probably not guaranteed)
|
||||
# Assume this produces an infinity on all machines (probably not guaranteed)
|
||||
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
|
||||
|
|
@ -33,7 +38,7 @@ def floatstr(o, allow_nan=True):
|
|||
elif o == -INFINITY:
|
||||
text = '-Infinity'
|
||||
else:
|
||||
return str(o)
|
||||
return FLOAT_REPR(o)
|
||||
|
||||
if not allow_nan:
|
||||
raise ValueError("Out of range float values are not JSON compliant: %r"
|
||||
|
|
@ -50,15 +55,32 @@ def encode_basestring(s):
|
|||
return ESCAPE_DCT[match.group(0)]
|
||||
return '"' + ESCAPE.sub(replace, s) + '"'
|
||||
|
||||
def encode_basestring_ascii(s):
|
||||
|
||||
def py_encode_basestring_ascii(s):
|
||||
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:
|
||||
return '\\u%04x' % (ord(s),)
|
||||
n = ord(s)
|
||||
if n < 0x10000:
|
||||
return '\\u%04x' % (n,)
|
||||
else:
|
||||
# surrogate pair
|
||||
n -= 0x10000
|
||||
s1 = 0xd800 | ((n >> 10) & 0x3ff)
|
||||
s2 = 0xdc00 | (n & 0x3ff)
|
||||
return '\\u%04x\\u%04x' % (s1, s2)
|
||||
return '"' + str(ESCAPE_ASCII.sub(replace, s)) + '"'
|
||||
|
||||
|
||||
|
||||
try:
|
||||
encode_basestring_ascii = c_encode_basestring_ascii
|
||||
except NameError:
|
||||
encode_basestring_ascii = py_encode_basestring_ascii
|
||||
|
||||
|
||||
class JSONEncoder(object):
|
||||
"""
|
||||
|
|
@ -94,7 +116,7 @@ class JSONEncoder(object):
|
|||
key_separator = ': '
|
||||
def __init__(self, skipkeys=False, ensure_ascii=True,
|
||||
check_circular=True, allow_nan=True, sort_keys=False,
|
||||
indent=None, separators=None):
|
||||
indent=None, separators=None, encoding='utf-8', default=None):
|
||||
"""
|
||||
Constructor for JSONEncoder, with sensible defaults.
|
||||
|
||||
|
|
@ -126,8 +148,16 @@ class JSONEncoder(object):
|
|||
None is the most compact representation.
|
||||
|
||||
If specified, separators should be a (item_separator, key_separator)
|
||||
tuple. The default is (', ', ': '). To get the most compact JSON
|
||||
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.
|
||||
"""
|
||||
|
||||
self.skipkeys = skipkeys
|
||||
|
|
@ -139,6 +169,9 @@ class JSONEncoder(object):
|
|||
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))
|
||||
|
|
@ -207,8 +240,14 @@ class JSONEncoder(object):
|
|||
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, basestring):
|
||||
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.
|
||||
|
|
@ -247,6 +286,10 @@ class JSONEncoder(object):
|
|||
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'
|
||||
|
|
@ -304,11 +347,22 @@ class JSONEncoder(object):
|
|||
Return a JSON string representation of a Python data structure.
|
||||
|
||||
>>> JSONEncoder().encode({"foo": ["bar", "baz"]})
|
||||
'{"foo":["bar", "baz"]}'
|
||||
'{"foo": ["bar", "baz"]}'
|
||||
"""
|
||||
# This doesn't pass the iterator directly to ''.join() because it
|
||||
# sucks at reporting exceptions. It's going to do this internally
|
||||
# anyway because it uses PySequence_Fast or similar.
|
||||
# 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 = list(self.iterencode(o))
|
||||
return ''.join(chunks)
|
||||
|
||||
|
|
|
|||
|
|
@ -1,40 +0,0 @@
|
|||
from django.utils import simplejson
|
||||
import cgi
|
||||
|
||||
class JSONFilter(object):
|
||||
def __init__(self, app, mime_type='text/x-json'):
|
||||
self.app = app
|
||||
self.mime_type = mime_type
|
||||
|
||||
def __call__(self, environ, start_response):
|
||||
# Read JSON POST input to jsonfilter.json if matching mime type
|
||||
response = {'status': '200 OK', 'headers': []}
|
||||
def json_start_response(status, headers):
|
||||
response['status'] = status
|
||||
response['headers'].extend(headers)
|
||||
environ['jsonfilter.mime_type'] = self.mime_type
|
||||
if environ.get('REQUEST_METHOD', '') == 'POST':
|
||||
if environ.get('CONTENT_TYPE', '') == self.mime_type:
|
||||
args = [_ for _ in [environ.get('CONTENT_LENGTH')] if _]
|
||||
data = environ['wsgi.input'].read(*map(int, args))
|
||||
environ['jsonfilter.json'] = simplejson.loads(data)
|
||||
res = simplejson.dumps(self.app(environ, json_start_response))
|
||||
jsonp = cgi.parse_qs(environ.get('QUERY_STRING', '')).get('jsonp')
|
||||
if jsonp:
|
||||
content_type = 'text/javascript'
|
||||
res = ''.join(jsonp + ['(', res, ')'])
|
||||
elif 'Opera' in environ.get('HTTP_USER_AGENT', ''):
|
||||
# Opera has bunk XMLHttpRequest support for most mime types
|
||||
content_type = 'text/plain'
|
||||
else:
|
||||
content_type = self.mime_type
|
||||
headers = [
|
||||
('Content-type', content_type),
|
||||
('Content-length', len(res)),
|
||||
]
|
||||
headers.extend(response['headers'])
|
||||
start_response(response['status'], headers)
|
||||
return [res]
|
||||
|
||||
def factory(app, global_conf, **kw):
|
||||
return JSONFilter(app, **kw)
|
||||
|
|
@ -1,18 +1,21 @@
|
|||
"""
|
||||
Iterator based sre token scanner
|
||||
"""
|
||||
import sre_parse, sre_compile, sre_constants
|
||||
from sre_constants import BRANCH, SUBPATTERN
|
||||
from re import VERBOSE, MULTILINE, DOTALL
|
||||
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
|
||||
# Combine phrases into a compound pattern
|
||||
s = sre_parse.Pattern()
|
||||
s.flags = flags
|
||||
p = []
|
||||
|
|
@ -26,10 +29,10 @@ class Scanner(object):
|
|||
p.append(subpattern)
|
||||
self.actions.append(token)
|
||||
|
||||
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)
|
||||
|
||||
|
||||
def iterscan(self, string, idx=0, context=None):
|
||||
"""
|
||||
Yield match, end_idx for each match
|
||||
|
|
@ -54,10 +57,11 @@ class Scanner(object):
|
|||
match = self.scanner.scanner(string, matchend).match
|
||||
yield rval, matchend
|
||||
lastend = matchend
|
||||
|
||||
|
||||
|
||||
def pattern(pattern, flags=FLAGS):
|
||||
def decorator(fn):
|
||||
fn.pattern = pattern
|
||||
fn.regex = re.compile(pattern, flags)
|
||||
return fn
|
||||
return decorator
|
||||
return decorator
|
||||
|
|
@ -0,0 +1,44 @@
|
|||
r"""
|
||||
Using simplejson from the shell to validate and
|
||||
pretty-print::
|
||||
|
||||
$ echo '{"json":"obj"}' | python -msimplejson
|
||||
{
|
||||
"json": "obj"
|
||||
}
|
||||
$ echo '{ 1.2:3.4}' | python -msimplejson
|
||||
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
|
||||
#
|
||||
|
||||
def main():
|
||||
import sys
|
||||
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("%s [infile [outfile]]" % (sys.argv[0],))
|
||||
try:
|
||||
obj = simplejson.load(infile)
|
||||
except ValueError, e:
|
||||
raise SystemExit(e)
|
||||
simplejson.dump(obj, outfile, sort_keys=True, indent=4)
|
||||
outfile.write('\n')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
Loading…
Reference in New Issue