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 2008-07-27 23:38:28 +00:00
parent de9e2ae5bb
commit d57ce3d6a9
7 changed files with 367 additions and 112 deletions

View File

@ -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

View File

@ -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',
]
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).
@ -124,22 +155,41 @@ def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True,
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):
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,
**kw).iterencode(obj)
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``.
@ -169,19 +219,35 @@ def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True,
then it will be used instead of the default ``(', ', ': ')`` separators.
``(',', ':')`` is the most compact JSON representation.
``encoding`` is the character encoding for str instances, default is UTF-8.
``default(obj)`` is a function that should return a serializable version
of obj or raise TypeError. The default simply raises TypeError.
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.
@ -201,13 +267,14 @@ def load(fp, encoding=None, cls=None, object_hook=None, **kw):
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.
@ -222,27 +289,81 @@ def loads(s, encoding=None, cls=None, object_hook=None, **kw):
``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()

View File

@ -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))
@ -157,11 +204,12 @@ def JSONObject(match, context, _w=WHITESPACE.match):
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
@ -183,6 +231,7 @@ def JSONArray(match, context, _w=WHITESPACE.match):
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):
"""

View File

@ -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"
@ -50,16 +55,33 @@ 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):
"""
Extensible JSON <http://json.org> encoder for Python data structures.
@ -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.
@ -128,6 +150,14 @@ class JSONEncoder(object):
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.
"""
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'
@ -306,9 +349,20 @@ class JSONEncoder(object):
>>> JSONEncoder().encode({"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)

View File

@ -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)

View File

@ -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
@ -55,6 +58,7 @@ class Scanner(object):
yield rval, matchend
lastend = matchend
def pattern(pattern, flags=FLAGS):
def decorator(fn):
fn.pattern = pattern

View File

@ -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()