summaryrefslogtreecommitdiff
path: root/Lib/json
diff options
context:
space:
mode:
Diffstat (limited to 'Lib/json')
-rw-r--r--Lib/json/__init__.py147
-rw-r--r--Lib/json/decoder.py304
-rw-r--r--Lib/json/encoder.py384
-rw-r--r--Lib/json/scanner.py116
-rw-r--r--Lib/json/tests/__init__.py46
-rw-r--r--Lib/json/tests/test_check_circular.py34
-rw-r--r--Lib/json/tests/test_decode.py53
-rw-r--r--Lib/json/tests/test_default.py15
-rw-r--r--Lib/json/tests/test_dump.py22
-rw-r--r--Lib/json/tests/test_encode_basestring_ascii.py30
-rw-r--r--Lib/json/tests/test_fail.py25
-rw-r--r--Lib/json/tests/test_float.py23
-rw-r--r--Lib/json/tests/test_indent.py41
-rw-r--r--Lib/json/tests/test_pass1.py17
-rw-r--r--Lib/json/tests/test_pass2.py16
-rw-r--r--Lib/json/tests/test_pass3.py16
-rw-r--r--Lib/json/tests/test_recursion.py81
-rw-r--r--Lib/json/tests/test_scanstring.py72
-rw-r--r--Lib/json/tests/test_separators.py24
-rw-r--r--Lib/json/tests/test_speedups.py28
-rw-r--r--Lib/json/tests/test_unicode.py74
-rw-r--r--Lib/json/tool.py6
22 files changed, 979 insertions, 595 deletions
diff --git a/Lib/json/__init__.py b/Lib/json/__init__.py
index 56116f482f..414c702629 100644
--- a/Lib/json/__init__.py
+++ b/Lib/json/__init__.py
@@ -1,11 +1,13 @@
-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.
-json exposes an API familiar to uses of the standard library
-marshal and pickle modules.
+:mod:`json` 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::
@@ -32,23 +34,28 @@ Compact encoding::
>>> json.dumps([1,2,3,{'4': 5, '6': 7}], separators=(',',':'))
'[1,2,3,{"4":5,"6":7}]'
-Pretty printing (using repr() because of extraneous whitespace in the output)::
+Pretty printing::
>>> import json
- >>> print repr(json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=4))
- '{\n "4": 5, \n "6": 7\n}'
+ >>> 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
+ }
Decoding JSON::
>>> import json
- >>> json.loads('["foo", {"bar":["baz", null, 1.0, 2]}]')
- [u'foo', {u'bar': [u'baz', None, 1.0, 2]}]
- >>> json.loads('"\\"foo\\bar"')
- u'"foo\x08ar'
+ >>> obj = [u'foo', {u'bar': [u'baz', None, 1.0, 2]}]
+ >>> json.loads('["foo", {"bar":["baz", null, 1.0, 2]}]') == obj
+ True
+ >>> json.loads('"\\"foo\\bar"') == u'"foo\x08ar'
+ True
>>> from StringIO import StringIO
>>> io = StringIO('["streaming API"]')
- >>> json.load(io)
- [u'streaming API']
+ >>> json.load(io)[0] == 'streaming API'
+ True
Specializing JSON object decoding::
@@ -61,43 +68,36 @@ Specializing JSON object decoding::
>>> json.loads('{"__complex__": true, "real": 1, "imag": 2}',
... object_hook=as_complex)
(1+2j)
- >>> import decimal
- >>> json.loads('1.1', parse_float=decimal.Decimal)
- Decimal('1.1')
+ >>> from decimal import Decimal
+ >>> json.loads('1.1', parse_float=Decimal) == Decimal('1.1')
+ True
-Extending JSONEncoder::
+Specializing JSON object encoding::
>>> import json
- >>> class ComplexEncoder(json.JSONEncoder):
- ... def default(self, obj):
- ... if isinstance(obj, complex):
- ... return [obj.real, obj.imag]
- ... return json.JSONEncoder.default(self, obj)
+ >>> def encode_complex(obj):
+ ... if isinstance(obj, complex):
+ ... return [obj.real, obj.imag]
+ ... raise TypeError(repr(o) + " is not JSON serializable")
...
- >>> dumps(2 + 1j, cls=ComplexEncoder)
+ >>> json.dumps(2 + 1j, default=encode_complex)
+ '[2.0, 1.0]'
+ >>> json.JSONEncoder(default=encode_complex).encode(2 + 1j)
'[2.0, 1.0]'
- >>> ComplexEncoder().encode(2 + 1j)
+ >>> ''.join(json.JSONEncoder(default=encode_complex).iterencode(2 + 1j))
'[2.0, 1.0]'
- >>> list(ComplexEncoder().iterencode(2 + 1j))
- ['[', '2.0', ', ', '1.0', ']']
-Using json.tool from the shell to validate and
-pretty-print::
+Using json.tool from the shell to validate and pretty-print::
- $ echo '{"json":"obj"}' | python -mjson.tool
+ $ echo '{"json":"obj"}' | python -m json.tool
{
"json": "obj"
}
- $ echo '{ 1.2:3.4}' | python -mjson.tool
+ $ echo '{ 1.2:3.4}' | python -m json.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'
+__version__ = '2.0.9'
__all__ = [
'dump', 'dumps', 'load', 'loads',
'JSONDecoder', 'JSONEncoder',
@@ -125,28 +125,29 @@ def dump(obj, fp, skipkeys=False, ensure_ascii=True, check_circular=True,
"""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
+ If ``skipkeys`` is true then ``dict`` keys that are not basic types
(``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
will be skipped instead of raising a ``TypeError``.
- If ``ensure_ascii`` is ``False``, then the some chunks written to ``fp``
+ If ``ensure_ascii`` is false, then the some chunks written to ``fp``
may be ``unicode`` instances, subject to normal Python ``str`` to
``unicode`` coercion rules. Unless ``fp.write()`` explicitly
understands ``unicode`` (as in ``codecs.getwriter()``) this is likely
to cause an error.
- If ``check_circular`` is ``False``, then the circular reference check
+ If ``check_circular`` is false, then the circular reference check
for container types will be skipped and a circular reference will
result in an ``OverflowError`` (or worse).
- If ``allow_nan`` is ``False``, then it will be a ``ValueError`` to
+ If ``allow_nan`` is false, then it will be a ``ValueError`` to
serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``)
in strict compliance of the JSON specification, instead of using the
JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).
- If ``indent`` is a 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.
+ 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.
If ``separators`` is an ``(item_separator, dict_separator)`` tuple
then it will be used instead of the default ``(', ', ': ')`` separators.
@@ -159,12 +160,12 @@ 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.
+ the ``cls`` kwarg; otherwise ``JSONEncoder`` is used.
"""
# cached encoder
- if (skipkeys is False and ensure_ascii is True and
- check_circular is True and allow_nan is True and
+ if (not skipkeys and ensure_ascii and
+ check_circular and allow_nan and
cls is None and indent is None and separators is None and
encoding == 'utf-8' and default is None and not kw):
iterable = _default_encoder.iterencode(obj)
@@ -186,19 +187,19 @@ def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True,
encoding='utf-8', default=None, **kw):
"""Serialize ``obj`` to a JSON formatted ``str``.
- If ``skipkeys`` is ``True`` then ``dict`` keys that are not basic types
+ If ``skipkeys`` is false then ``dict`` keys that are not basic types
(``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
will be skipped instead of raising a ``TypeError``.
- If ``ensure_ascii`` is ``False``, then the return value will be a
+ If ``ensure_ascii`` is false, then the return value will be a
``unicode`` instance subject to normal Python ``str`` to ``unicode``
coercion rules instead of being escaped to an ASCII ``str``.
- If ``check_circular`` is ``False``, then the circular reference check
+ If ``check_circular`` is false, then the circular reference check
for container types will be skipped and a circular reference will
result in an ``OverflowError`` (or worse).
- If ``allow_nan`` is ``False``, then it will be a ``ValueError`` to
+ If ``allow_nan`` is false, then it will be a ``ValueError`` to
serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``) in
strict compliance of the JSON specification, instead of using the
JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).
@@ -219,12 +220,12 @@ 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.
+ the ``cls`` kwarg; otherwise ``JSONEncoder`` is used.
"""
# cached encoder
- if (skipkeys is False and ensure_ascii is True and
- check_circular is True and allow_nan is True and
+ if (not skipkeys and ensure_ascii and
+ check_circular and allow_nan and
cls is None and indent is None and separators is None and
encoding == 'utf-8' and default is None and not kw):
return _default_encoder.encode(obj)
@@ -237,13 +238,14 @@ def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True,
**kw).encode(obj)
-_default_decoder = JSONDecoder(encoding=None, object_hook=None)
+_default_decoder = JSONDecoder(encoding=None, object_hook=None,
+ object_pairs_hook=None)
def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None,
- parse_int=None, parse_constant=None, **kw):
- """Deserialize ``fp`` (a ``.read()``-supporting file-like object
- containing a JSON document) to a Python object.
+ parse_int=None, parse_constant=None, object_pairs_hook=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
@@ -257,18 +259,27 @@ def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None,
``object_hook`` will be used instead of the ``dict``. This feature
can be used to implement custom decoders (e.g. JSON-RPC class hinting).
+ ``object_pairs_hook`` is an optional function that will be called with the
+ result of any object literal decoded with an ordered list of pairs. The
+ return value of ``object_pairs_hook`` will be used instead of the ``dict``.
+ This feature can be used to implement custom decoders that rely on the
+ order that the key and value pairs are decoded (for example,
+ collections.OrderedDict will remember the order of insertion). If
+ ``object_hook`` is also defined, the ``object_pairs_hook`` takes priority.
+
To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
- kwarg.
+ kwarg; otherwise ``JSONDecoder`` is used.
"""
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)
+ parse_constant=parse_constant, object_pairs_hook=object_pairs_hook,
+ **kw)
def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None,
- parse_int=None, parse_constant=None, **kw):
+ parse_int=None, parse_constant=None, object_pairs_hook=None, **kw):
"""Deserialize ``s`` (a ``str`` or ``unicode`` instance containing a JSON
document) to a Python object.
@@ -282,6 +293,14 @@ def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None,
``object_hook`` will be used instead of the ``dict``. This feature
can be used to implement custom decoders (e.g. JSON-RPC class hinting).
+ ``object_pairs_hook`` is an optional function that will be called with the
+ result of any object literal decoded with an ordered list of pairs. The
+ return value of ``object_pairs_hook`` will be used instead of the ``dict``.
+ This feature can be used to implement custom decoders that rely on the
+ order that the key and value pairs are decoded (for example,
+ collections.OrderedDict will remember the order of insertion). If
+ ``object_hook`` is also defined, the ``object_pairs_hook`` takes priority.
+
``parse_float``, if specified, will be called with the string
of every JSON float to be decoded. By default this is equivalent to
float(num_str). This can be used to use another datatype or parser
@@ -298,17 +317,19 @@ def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None,
are encountered.
To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``
- kwarg.
+ kwarg; otherwise ``JSONDecoder`` is used.
"""
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):
+ parse_constant is None and object_pairs_hook 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 object_pairs_hook is not None:
+ kw['object_pairs_hook'] = object_pairs_hook
if parse_float is not None:
kw['parse_float'] = parse_float
if parse_int is not None:
diff --git a/Lib/json/decoder.py b/Lib/json/decoder.py
index e80b93541b..1f2da72ffb 100644
--- a/Lib/json/decoder.py
+++ b/Lib/json/decoder.py
@@ -1,10 +1,10 @@
"""Implementation of JSONDecoder
"""
-
import re
import sys
+import struct
-from json.scanner import Scanner, pattern
+from json import scanner
try:
from _json import scanstring as c_scanstring
except ImportError:
@@ -14,7 +14,14 @@ __all__ = ['JSONDecoder']
FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL
-NaN, PosInf, NegInf = float('nan'), float('inf'), float('-inf')
+def _floatconstants():
+ _BYTES = '7FF80000000000007FF0000000000000'.decode('hex')
+ if sys.byteorder != 'big':
+ _BYTES = _BYTES[:8][::-1] + _BYTES[8:][::-1]
+ nan, inf = struct.unpack('dd', _BYTES)
+ return nan, inf, -inf
+
+NaN, PosInf, NegInf = _floatconstants()
def linecol(doc, pos):
@@ -27,49 +34,26 @@ def linecol(doc, pos):
def errmsg(msg, doc, pos, end=None):
+ # Note that this function is called from _json
lineno, colno = linecol(doc, pos)
if end is None:
fmt = '{0}: line {1} column {2} (char {3})'
return fmt.format(msg, lineno, colno, pos)
+ #fmt = '%s: line %d column %d (char %d)'
+ #return fmt % (msg, lineno, colno, pos)
endlineno, endcolno = linecol(doc, end)
fmt = '{0}: line {1} column {2} - line {3} column {4} (char {5} - {6})'
return fmt.format(msg, lineno, colno, endlineno, endcolno, pos, end)
+ #fmt = '%s: line %d column %d - line %d column %d (char %d - %d)'
+ #return fmt % (msg, lineno, colno, endlineno, endcolno, pos, end)
_CONSTANTS = {
'-Infinity': NegInf,
'Infinity': PosInf,
'NaN': NaN,
- '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'/',
@@ -78,8 +62,16 @@ 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.
-def py_scanstring(s, end, encoding=None, strict=True, _b=BACKSLASH, _m=STRINGCHUNK.match):
+ 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 = []
@@ -92,14 +84,18 @@ 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:
+ #msg = "Invalid control character %r at" % (terminator,)
msg = "Invalid control character {0!r} at".format(terminator)
raise ValueError(errmsg(msg, s, end))
else:
@@ -110,136 +106,170 @@ 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:
- msg = "Invalid \\escape: {0!r}".format(esc)
+ msg = "Invalid \\escape: " + repr(esc)
raise ValueError(errmsg(msg, 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
- 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:
+ if len(esc) != 4:
+ 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(errmsg(msg, s, end))
+ esc2 = s[end + 7:end + 11]
+ if len(esc2) != 4:
+ raise ValueError(errmsg(msg, s, end))
+ uni2 = int(esc2, 16)
+ uni = 0x10000 + (((uni - 0xd800) << 10) | (uni2 - 0xdc00))
+ next_end += 6
+ char = unichr(uni)
end = next_end
- _append(m)
+ # Append the unescaped character
+ _append(char)
return u''.join(chunks), end
-# Use speedup
-if c_scanstring is not None:
- scanstring = c_scanstring
-else:
- scanstring = 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)
+# Use speedup if available
+scanstring = c_scanstring or py_scanstring
+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):
- pairs = {}
- s = match.string
- end = _w(s, match.end()).end()
+def JSONObject(s_and_end, encoding, strict, scan_once, object_hook,
+ object_pairs_hook, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
+ s, end = s_and_end
+ pairs = []
+ pairs_append = pairs.append
+ # 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]
- # Trivial empty object
- if nextchar == '}':
- return pairs, end + 1
+ # Normally we expect nextchar == '"'
if nextchar != '"':
- raise ValueError(errmsg("Expecting property name", s, end))
+ if nextchar in _ws:
+ end = _w(s, end).end()
+ nextchar = s[end:end + 1]
+ # Trivial empty object
+ if nextchar == '}':
+ if object_pairs_hook is not None:
+ result = object_pairs_hook(pairs)
+ return result, end
+ pairs = {}
+ if object_hook is not None:
+ pairs = object_hook(pairs)
+ return pairs, end + 1
+ elif nextchar != '"':
+ raise 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)
- end = _w(s, end).end()
+
+ # To skip some function call overhead we optimize the fast paths where
+ # the JSON key separator is ": " or just ":".
if s[end:end + 1] != ':':
- raise ValueError(errmsg("Expecting : delimiter", s, end))
- end = _w(s, end + 1).end()
+ end = _w(s, end).end()
+ if s[end:end + 1] != ':':
+ raise ValueError(errmsg("Expecting : delimiter", s, 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]
+ pairs_append((key, value))
+
+ try:
+ nextchar = s[end]
+ if nextchar in _ws:
+ end = _w(s, end + 1).end()
+ nextchar = s[end]
+ except IndexError:
+ nextchar = ''
end += 1
+
if nextchar == '}':
break
- 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_pairs_hook is not None:
+ result = object_pairs_hook(pairs)
+ return result, end
+ pairs = dict(pairs)
if object_hook is not None:
pairs = object_hook(pairs)
return pairs, end
-pattern(r'{')(JSONObject)
-
-def JSONArray(match, context, _w=WHITESPACE.match):
+def JSONArray(s_and_end, scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
+ s, end = s_and_end
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()
- return values, end
-pattern(r'\[')(JSONArray)
-
-ANYTHING = [
- JSONObject,
- JSONArray,
- JSONString,
- JSONConstant,
- JSONNumber,
-]
-
-JSONScanner = Scanner(ANYTHING)
+ try:
+ if s[end] in _ws:
+ end += 1
+ if s[end] in _ws:
+ end = _w(s, end + 1).end()
+ except IndexError:
+ pass
+ return values, end
class JSONDecoder(object):
"""Simple JSON <http://json.org> decoder
@@ -268,13 +298,12 @@ 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):
+ parse_int=None, parse_constant=None, strict=True,
+ object_pairs_hook=None):
"""``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.
@@ -282,11 +311,20 @@ class JSONDecoder(object):
Note that currently only encodings that are a superset of ASCII work,
strings of other encodings should be passed in as ``unicode``.
- ``object_hook``, if specified, will be called with the result of
- every JSON object decoded and its return value will be used in
+ ``object_hook``, if specified, will be called with the result
+ of every JSON object decoded and its return value will be used in
place of the given ``dict``. This can be used to provide custom
deserializations (e.g. to support JSON-RPC class hinting).
+ ``object_pairs_hook``, if specified will be called with the result of
+ every JSON object decoded with an ordered list of pairs. The return
+ value of ``object_pairs_hook`` will be used instead of the ``dict``.
+ This feature can be used to implement custom decoders that rely on the
+ order that the key and value pairs are decoded (for example,
+ collections.OrderedDict will remember the order of insertion). If
+ ``object_hook`` is also defined, the ``object_pairs_hook`` takes
+ priority.
+
``parse_float``, if specified, will be called with the string
of every JSON float to be decoded. By default this is equivalent to
float(num_str). This can be used to use another datatype or parser
@@ -298,21 +336,30 @@ 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.
+ If ``strict`` is false (true is the default), then control
+ characters will be allowed inside strings. Control characters in
+ this context are those with character codes in the 0-31 range,
+ including ``'\\t'`` (tab), ``'\\n'``, ``'\\r'`` and ``'\\0'``.
+
"""
self.encoding = encoding
self.object_hook = object_hook
- self.parse_float = parse_float
- self.parse_int = parse_int
- self.parse_constant = parse_constant
+ self.object_pairs_hook = object_pairs_hook
+ self.parse_float = parse_float or float
+ self.parse_int = parse_int or int
+ self.parse_constant = parse_constant or _CONSTANTS.__getitem__
self.strict = strict
+ self.parse_object = JSONObject
+ self.parse_array = JSONArray
+ self.parse_string = scanstring
+ self.scan_once = scanner.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)
"""
@@ -322,18 +369,17 @@ 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
- with a JSON document) and return a 2-tuple of the Python
+ 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
diff --git a/Lib/json/encoder.py b/Lib/json/encoder.py
index b1dd5703dc..906c46216a 100644
--- a/Lib/json/encoder.py
+++ b/Lib/json/encoder.py
@@ -1,15 +1,15 @@
"""Implementation of JSONEncoder
"""
-
import re
-import math
try:
from _json import encode_basestring_ascii as c_encode_basestring_ascii
except ImportError:
c_encode_basestring_ascii = None
-
-__all__ = ['JSONEncoder']
+try:
+ from _json import make_encoder as c_make_encoder
+except ImportError:
+ c_make_encoder = None
ESCAPE = re.compile(r'[\x00-\x1f\\"\b\f\n\r\t]')
ESCAPE_ASCII = re.compile(r'([\\"]|[^\ -~])')
@@ -25,30 +25,12 @@ ESCAPE_DCT = {
}
for i in range(0x20):
ESCAPE_DCT.setdefault(chr(i), '\\u{0:04x}'.format(i))
+ #ESCAPE_DCT.setdefault(chr(i), '\\u%04x' % (i,))
+# 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
- # platform-specific, so do tests which don't depend on the internals.
-
- if math.isnan(o):
- text = 'NaN'
- elif math.isinf(o):
- if math.copysign(1., o) == 1.:
- text = 'Infinity'
- else:
- text = '-Infinity'
- else:
- return FLOAT_REPR(o)
-
- if not allow_nan:
- msg = "Out of range float values are not JSON compliant: " + repr(o)
- raise ValueError(msg)
-
- return text
-
-
def encode_basestring(s):
"""Return a JSON representation of a Python string
@@ -59,6 +41,9 @@ 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):
@@ -69,20 +54,19 @@ def py_encode_basestring_ascii(s):
n = ord(s)
if n < 0x10000:
return '\\u{0:04x}'.format(n)
+ #return '\\u%04x' % (n,)
else:
# surrogate pair
n -= 0x10000
s1 = 0xd800 | ((n >> 10) & 0x3ff)
s2 = 0xdc00 | (n & 0x3ff)
return '\\u{0:04x}\\u{1:04x}'.format(s1, s2)
+ #return '\\u%04x\\u%04x' % (s1, s2)
return '"' + str(ESCAPE_ASCII.sub(replace, s)) + '"'
-if c_encode_basestring_ascii is not None:
- encode_basestring_ascii = c_encode_basestring_ascii
-else:
- 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.
@@ -113,7 +97,6 @@ class JSONEncoder(object):
implementation (to raise ``TypeError``).
"""
- __all__ = ['__init__', 'default', 'encode', 'iterencode']
item_separator = ', '
key_separator = ': '
def __init__(self, skipkeys=False, ensure_ascii=True,
@@ -121,25 +104,25 @@ class JSONEncoder(object):
indent=None, separators=None, encoding='utf-8', default=None):
"""Constructor for JSONEncoder, with sensible defaults.
- If skipkeys is False, then it is a TypeError to attempt
+ If skipkeys is false, then it is a TypeError to attempt
encoding of keys that are not str, int, long, float or None. If
skipkeys is True, such items are simply skipped.
- If ensure_ascii is True, the output is guaranteed to be str
+ If ensure_ascii is true, the output is guaranteed to be str
objects with all incoming unicode characters escaped. If
ensure_ascii is false, the output will be unicode object.
- If check_circular is True, then lists, dicts, and custom encoded
+ If check_circular is true, then lists, dicts, and custom encoded
objects will be checked for circular references during encoding to
prevent an infinite recursion (which would cause an OverflowError).
Otherwise, no such check takes place.
- If allow_nan is True, then NaN, Infinity, and -Infinity will be
+ If allow_nan is true, then NaN, Infinity, and -Infinity will be
encoded as such. This behavior is not JSON specification compliant,
but is consistent with most JavaScript based encoders and decoders.
Otherwise, it will be a ValueError to encode such floats.
- If sort_keys is True, then the output of dictionaries will be
+ If sort_keys is true, then the output of dictionaries will be
sorted by key; this is useful for regression tests to ensure
that JSON serializations can be compared on a day-to-day basis.
@@ -161,23 +144,142 @@ class JSONEncoder(object):
The default is UTF-8.
"""
+
self.skipkeys = skipkeys
self.ensure_ascii = ensure_ascii
self.check_circular = check_circular
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 default(self, o):
+ """Implement this method in a subclass such that it returns
+ a serializable object for ``o``, or calls the base implementation
+ (to raise a ``TypeError``).
+
+ For example, to support arbitrary iterators, you could
+ implement default like this::
+
+ def default(self, o):
+ try:
+ iterable = iter(o)
+ except TypeError:
+ pass
+ else:
+ return list(iterable)
+ return JSONEncoder.default(self, o)
+
+ """
+ raise TypeError(repr(o) + " is not JSON serializable")
+
+ def encode(self, o):
+ """Return a JSON string representation of a Python data structure.
+
+ >>> JSONEncoder().encode({"foo": ["bar", "baz"]})
+ '{"foo": ["bar", "baz"]}'
+
+ """
+ # This is for extremely simple cases and benchmarks.
+ if isinstance(o, basestring):
+ if isinstance(o, str):
+ _encoding = self.encoding
+ if (_encoding is not None
+ and not (_encoding == 'utf-8')):
+ o = o.decode(_encoding)
+ if self.ensure_ascii:
+ return encode_basestring_ascii(o)
+ else:
+ return encode_basestring(o)
+ # This doesn't pass the iterator directly to ''.join() because the
+ # exceptions aren't as detailed. The list call should be roughly
+ # equivalent to the PySequence_Fast that ''.join() would do.
+ chunks = self.iterencode(o, _one_shot=True)
+ if not isinstance(chunks, (list, tuple)):
+ chunks = list(chunks)
+ return ''.join(chunks)
+
+ def iterencode(self, o, _one_shot=False):
+ """Encode the given object and yield each string
+ representation as available.
+
+ For example::
+
+ for chunk in JSONEncoder().iterencode(bigobject):
+ mysocket.write(chunk)
+
+ """
+ if self.check_circular:
+ markers = {}
+ else:
+ markers = None
+ if self.ensure_ascii:
+ _encoder = encode_basestring_ascii
+ else:
+ _encoder = encode_basestring
+ if self.encoding != 'utf-8':
+ def _encoder(o, _orig_encoder=_encoder, _encoding=self.encoding):
+ if isinstance(o, str):
+ o = o.decode(_encoding)
+ return _orig_encoder(o)
+
+ def floatstr(o, allow_nan=self.allow_nan,
+ _repr=FLOAT_REPR, _inf=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: " +
+ repr(o))
- def _iterencode_list(self, lst, markers=None):
+ return text
+
+
+ if (_one_shot and c_make_encoder is not None
+ and self.indent is None 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
+ 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
@@ -186,31 +288,51 @@ class JSONEncoder(object):
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
+ 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 = self.item_separator
+ separator = _item_separator
first = True
for value in lst:
if first:
first = False
else:
- yield separator
- for chunk in self._iterencode(value, markers):
- yield chunk
+ 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:
- self.current_indent_level -= 1
- yield self._newline_indent()
+ _current_indent_level -= 1
+ yield '\n' + (' ' * (_indent * _current_indent_level))
yield ']'
if markers is not None:
del markers[markerid]
- def _iterencode_dict(self, dct, markers=None):
+ def _iterencode_dict(dct, _current_indent_level):
if not dct:
yield '{}'
return
@@ -220,78 +342,75 @@ class JSONEncoder(object):
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
+ 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 = self.item_separator
+ item_separator = _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]
+ if _sort_keys:
+ items = sorted(dct.items(), key=lambda kv: kv[0])
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):
+ 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, allow_nan)
- elif isinstance(key, (int, long)):
- key = str(key)
+ key = _floatstr(key)
elif key is True:
key = 'true'
elif key is False:
key = 'false'
elif key is None:
key = 'null'
- elif self.skipkeys:
+ elif isinstance(key, (int, long)):
+ key = str(key)
+ elif _skipkeys:
continue
else:
- raise TypeError("key {0!r} is not a string".format(key))
+ raise TypeError("key " + repr(key) + " is not a string")
if first:
first = False
else:
yield item_separator
- yield encoder(key)
- yield key_separator
- for chunk in self._iterencode(value, markers):
- yield chunk
+ 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:
- self.current_indent_level -= 1
- yield self._newline_indent()
+ _current_indent_level -= 1
+ yield '\n' + (' ' * (_indent * _current_indent_level))
yield '}'
if markers is not None:
del markers[markerid]
- def _iterencode(self, o, markers=None):
+ def _iterencode(o, _current_indent_level):
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)
+ yield _encoder(o)
elif o is None:
yield 'null'
elif o is True:
@@ -301,12 +420,12 @@ class JSONEncoder(object):
elif isinstance(o, (int, long)):
yield str(o)
elif isinstance(o, float):
- yield floatstr(o, self.allow_nan)
+ yield _floatstr(o)
elif isinstance(o, (list, tuple)):
- for chunk in self._iterencode_list(o, markers):
+ for chunk in _iterencode_list(o, _current_indent_level):
yield chunk
elif isinstance(o, dict):
- for chunk in self._iterencode_dict(o, markers):
+ for chunk in _iterencode_dict(o, _current_indent_level):
yield chunk
else:
if markers is not None:
@@ -314,71 +433,10 @@ class JSONEncoder(object):
if markerid in markers:
raise ValueError("Circular reference detected")
markers[markerid] = o
- for chunk in self._iterencode_default(o, markers):
+ o = _default(o)
+ for chunk in _iterencode(o, _current_indent_level):
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 a serializable
- object for ``o``, or calls the base implementation (to raise a
- ``TypeError``).
-
- For example, to support arbitrary iterators, you could implement
- default like this::
-
- def default(self, o):
- try:
- iterable = iter(o)
- except TypeError:
- pass
- else:
- return list(iterable)
- return JSONEncoder.default(self, o)
-
- """
- raise TypeError(repr(o) + " is not JSON serializable")
-
- def encode(self, o):
- """Return a JSON string representation of a Python data structure.
-
- >>> JSONEncoder().encode({"foo": ["bar", "baz"]})
- '{"foo": ["bar", "baz"]}'
-
- """
- # This is for extremely simple cases and benchmarks.
- if isinstance(o, basestring):
- if isinstance(o, str):
- _encoding = self.encoding
- if (_encoding is not None
- and not (_encoding == 'utf-8')):
- o = o.decode(_encoding)
- if self.ensure_ascii:
- return encode_basestring_ascii(o)
- else:
- return encode_basestring(o)
- # This doesn't pass the iterator directly to ''.join() because the
- # exceptions aren't as detailed. The list call should be roughly
- # equivalent to the PySequence_Fast that ''.join() would do.
- chunks = list(self.iterencode(o))
- return ''.join(chunks)
-
- def iterencode(self, o):
- """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)
+ return _iterencode
diff --git a/Lib/json/scanner.py b/Lib/json/scanner.py
index 4b065abf75..74e6805155 100644
--- a/Lib/json/scanner.py
+++ b/Lib/json/scanner.py
@@ -1,69 +1,67 @@
-"""Iterator based sre token scanner
-
+"""JSON token scanner
"""
-
import re
-import sre_parse
-import sre_compile
-import sre_constants
-
-from re import VERBOSE, MULTILINE, DOTALL
-from sre_constants import BRANCH, SUBPATTERN
+try:
+ from _json import make_scanner as c_make_scanner
+except ImportError:
+ c_make_scanner = None
-__all__ = ['Scanner', 'pattern']
+__all__ = ['make_scanner']
-FLAGS = (VERBOSE | MULTILINE | DOTALL)
+NUMBER_RE = re.compile(
+ r'(-?(?:0|[1-9]\d*))(\.\d+)?([eE][-+]?\d+)?',
+ (re.VERBOSE | re.MULTILINE | re.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)
+def py_make_scanner(context):
+ parse_object = context.parse_object
+ parse_array = context.parse_array
+ parse_string = context.parse_string
+ match_number = NUMBER_RE.match
+ encoding = context.encoding
+ strict = context.strict
+ parse_float = context.parse_float
+ parse_int = context.parse_int
+ parse_constant = context.parse_constant
+ object_hook = context.object_hook
+ object_pairs_hook = context.object_pairs_hook
- 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 _scan_once(string, idx):
+ try:
+ nextchar = string[idx]
+ except IndexError:
+ raise StopIteration
- def iterscan(self, string, idx=0, context=None):
- """Yield match, end_idx for each match
+ if nextchar == '"':
+ return parse_string(string, idx + 1, encoding, strict)
+ elif nextchar == '{':
+ return parse_object((string, idx + 1), encoding, strict,
+ _scan_once, object_hook, object_pairs_hook)
+ 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
- """
- 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
+ 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
-def pattern(pattern, flags=FLAGS):
- def decorator(fn):
- fn.pattern = pattern
- fn.regex = re.compile(pattern, flags)
- return fn
- return decorator
+make_scanner = c_make_scanner or py_make_scanner
diff --git a/Lib/json/tests/__init__.py b/Lib/json/tests/__init__.py
index 1a1e3e6d5a..90cb2b7ad6 100644
--- a/Lib/json/tests/__init__.py
+++ b/Lib/json/tests/__init__.py
@@ -1,7 +1,46 @@
import os
import sys
-import unittest
+import json
import doctest
+import unittest
+
+from test import test_support
+
+# import json with and without accelerations
+cjson = test_support.import_fresh_module('json', fresh=['_json'])
+pyjson = test_support.import_fresh_module('json', blocked=['_json'])
+
+# create two base classes that will be used by the other tests
+class PyTest(unittest.TestCase):
+ json = pyjson
+ loads = staticmethod(pyjson.loads)
+ dumps = staticmethod(pyjson.dumps)
+
+@unittest.skipUnless(cjson, 'requires _json')
+class CTest(unittest.TestCase):
+ if cjson is not None:
+ json = cjson
+ loads = staticmethod(cjson.loads)
+ dumps = staticmethod(cjson.dumps)
+
+# test PyTest and CTest checking if the functions come from the right module
+class TestPyTest(PyTest):
+ def test_pyjson(self):
+ self.assertEqual(self.json.scanner.make_scanner.__module__,
+ 'json.scanner')
+ self.assertEqual(self.json.decoder.scanstring.__module__,
+ 'json.decoder')
+ self.assertEqual(self.json.encoder.encode_basestring_ascii.__module__,
+ 'json.encoder')
+
+class TestCTest(CTest):
+ def test_cjson(self):
+ self.assertEqual(self.json.scanner.make_scanner.__module__, '_json')
+ self.assertEqual(self.json.decoder.scanstring.__module__, '_json')
+ self.assertEqual(self.json.encoder.c_make_encoder.__module__, '_json')
+ self.assertEqual(self.json.encoder.encode_basestring_ascii.__module__,
+ '_json')
+
here = os.path.dirname(__file__)
@@ -17,12 +56,11 @@ def test_suite():
return suite
def additional_tests():
- import json
- import json.encoder
- import json.decoder
suite = unittest.TestSuite()
for mod in (json, json.encoder, json.decoder):
suite.addTest(doctest.DocTestSuite(mod))
+ suite.addTest(TestPyTest('test_pyjson'))
+ suite.addTest(TestCTest('test_cjson'))
return suite
def main():
diff --git a/Lib/json/tests/test_check_circular.py b/Lib/json/tests/test_check_circular.py
new file mode 100644
index 0000000000..3ad3d24196
--- /dev/null
+++ b/Lib/json/tests/test_check_circular.py
@@ -0,0 +1,34 @@
+from json.tests import PyTest, CTest
+
+
+def default_iterable(obj):
+ return list(obj)
+
+class TestCheckCircular(object):
+ def test_circular_dict(self):
+ dct = {}
+ dct['a'] = dct
+ self.assertRaises(ValueError, self.dumps, dct)
+
+ def test_circular_list(self):
+ lst = []
+ lst.append(lst)
+ self.assertRaises(ValueError, self.dumps, lst)
+
+ def test_circular_composite(self):
+ dct2 = {}
+ dct2['a'] = []
+ dct2['a'].append(dct2)
+ self.assertRaises(ValueError, self.dumps, dct2)
+
+ def test_circular_default(self):
+ self.dumps([set()], default=default_iterable)
+ self.assertRaises(TypeError, self.dumps, [set()])
+
+ def test_circular_off_default(self):
+ self.dumps([set()], default=default_iterable, check_circular=False)
+ self.assertRaises(TypeError, self.dumps, [set()], check_circular=False)
+
+
+class TestPyCheckCircular(TestCheckCircular, PyTest): pass
+class TestCCheckCircular(TestCheckCircular, CTest): pass
diff --git a/Lib/json/tests/test_decode.py b/Lib/json/tests/test_decode.py
index 609f62288c..aa8bbe9b54 100644
--- a/Lib/json/tests/test_decode.py
+++ b/Lib/json/tests/test_decode.py
@@ -1,15 +1,50 @@
import decimal
-from unittest import TestCase
+from StringIO import StringIO
+from collections import OrderedDict
+from json.tests import PyTest, CTest
-import json
-class TestDecode(TestCase):
+class TestDecode(object):
def test_decimal(self):
- rval = json.loads('1.1', parse_float=decimal.Decimal)
- self.assert_(isinstance(rval, decimal.Decimal))
- self.assertEquals(rval, decimal.Decimal('1.1'))
+ rval = self.loads('1.1', parse_float=decimal.Decimal)
+ self.assertTrue(isinstance(rval, decimal.Decimal))
+ self.assertEqual(rval, decimal.Decimal('1.1'))
def test_float(self):
- rval = json.loads('1', parse_int=float)
- self.assert_(isinstance(rval, float))
- self.assertEquals(rval, 1.0)
+ rval = self.loads('1', parse_int=float)
+ self.assertTrue(isinstance(rval, float))
+ self.assertEqual(rval, 1.0)
+
+ def test_decoder_optimizations(self):
+ # Several optimizations were made that skip over calls to
+ # the whitespace regex, so this test is designed to try and
+ # exercise the uncommon cases. The array cases are already covered.
+ rval = self.loads('{ "key" : "value" , "k":"v" }')
+ self.assertEqual(rval, {"key":"value", "k":"v"})
+
+ def test_empty_objects(self):
+ self.assertEqual(self.loads('{}'), {})
+ self.assertEqual(self.loads('[]'), [])
+ self.assertEqual(self.loads('""'), u"")
+ self.assertIsInstance(self.loads('""'), unicode)
+
+ def test_object_pairs_hook(self):
+ s = '{"xkd":1, "kcw":2, "art":3, "hxm":4, "qrt":5, "pad":6, "hoy":7}'
+ p = [("xkd", 1), ("kcw", 2), ("art", 3), ("hxm", 4),
+ ("qrt", 5), ("pad", 6), ("hoy", 7)]
+ self.assertEqual(self.loads(s), eval(s))
+ self.assertEqual(self.loads(s, object_pairs_hook=lambda x: x), p)
+ self.assertEqual(self.json.load(StringIO(s),
+ object_pairs_hook=lambda x: x), p)
+ od = self.loads(s, object_pairs_hook=OrderedDict)
+ self.assertEqual(od, OrderedDict(p))
+ self.assertEqual(type(od), OrderedDict)
+ # the object_pairs_hook takes priority over the object_hook
+ self.assertEqual(self.loads(s,
+ object_pairs_hook=OrderedDict,
+ object_hook=lambda x: None),
+ OrderedDict(p))
+
+
+class TestPyDecode(TestDecode, PyTest): pass
+class TestCDecode(TestDecode, CTest): pass
diff --git a/Lib/json/tests/test_default.py b/Lib/json/tests/test_default.py
index 49f05ad660..c2a07f605e 100644
--- a/Lib/json/tests/test_default.py
+++ b/Lib/json/tests/test_default.py
@@ -1,9 +1,12 @@
-from unittest import TestCase
+from json.tests import PyTest, CTest
-import json
-class TestDefault(TestCase):
+class TestDefault(object):
def test_default(self):
- self.assertEquals(
- json.dumps(type, default=repr),
- json.dumps(repr(type)))
+ self.assertEqual(
+ self.dumps(type, default=repr),
+ self.dumps(repr(type)))
+
+
+class TestPyDefault(TestDefault, PyTest): pass
+class TestCDefault(TestDefault, CTest): pass
diff --git a/Lib/json/tests/test_dump.py b/Lib/json/tests/test_dump.py
index d288c0d293..9a7c8ccdd0 100644
--- a/Lib/json/tests/test_dump.py
+++ b/Lib/json/tests/test_dump.py
@@ -1,13 +1,23 @@
-from unittest import TestCase
from cStringIO import StringIO
+from json.tests import PyTest, CTest
-import json
-class TestDump(TestCase):
+class TestDump(object):
def test_dump(self):
sio = StringIO()
- json.dump({}, sio)
- self.assertEquals(sio.getvalue(), '{}')
+ self.json.dump({}, sio)
+ self.assertEqual(sio.getvalue(), '{}')
def test_dumps(self):
- self.assertEquals(json.dumps({}), '{}')
+ self.assertEqual(self.dumps({}), '{}')
+
+ def test_encode_truefalse(self):
+ self.assertEqual(self.dumps(
+ {True: False, False: True}, sort_keys=True),
+ '{"false": true, "true": false}')
+ self.assertEqual(self.dumps(
+ {2: 3.0, 4.0: 5L, False: 1, 6L: True}, sort_keys=True),
+ '{"false": 1, "2": 3.0, "4.0": 5, "6": true}')
+
+class TestPyDump(TestDump, PyTest): pass
+class TestCDump(TestDump, CTest): pass
diff --git a/Lib/json/tests/test_encode_basestring_ascii.py b/Lib/json/tests/test_encode_basestring_ascii.py
index 352423ec6b..9f9d5a5deb 100644
--- a/Lib/json/tests/test_encode_basestring_ascii.py
+++ b/Lib/json/tests/test_encode_basestring_ascii.py
@@ -1,6 +1,6 @@
-from unittest import TestCase
+from collections import OrderedDict
+from json.tests import PyTest, CTest
-import json.encoder
CASES = [
(u'/\\"\ucafe\ubabe\uab98\ufcde\ubcda\uef4a\x08\x0c\n\r\t`1~!@#$%^&*()_+-=[]{}|;:\',./<>?', '"/\\\\\\"\\ucafe\\ubabe\\uab98\\ufcde\\ubcda\\uef4a\\b\\f\\n\\r\\t`1~!@#$%^&*()_+-=[]{}|;:\',./<>?"'),
@@ -21,15 +21,21 @@ CASES = [
(u'\u0123\u4567\u89ab\ucdef\uabcd\uef4a', '"\\u0123\\u4567\\u89ab\\ucdef\\uabcd\\uef4a"'),
]
-class TestEncodeBaseStringAscii(TestCase):
- def test_py_encode_basestring_ascii(self):
- self._test_encode_basestring_ascii(json.encoder.py_encode_basestring_ascii)
+class TestEncodeBasestringAscii(object):
+ def test_encode_basestring_ascii(self):
+ fname = self.json.encoder.encode_basestring_ascii.__name__
+ for input_string, expect in CASES:
+ result = self.json.encoder.encode_basestring_ascii(input_string)
+ self.assertEqual(result, expect,
+ '{0!r} != {1!r} for {2}({3!r})'.format(
+ result, expect, fname, input_string))
- def test_c_encode_basestring_ascii(self):
- self._test_encode_basestring_ascii(json.encoder.c_encode_basestring_ascii)
+ def test_ordered_dict(self):
+ # See issue 6105
+ items = [('one', 1), ('two', 2), ('three', 3), ('four', 4), ('five', 5)]
+ s = self.dumps(OrderedDict(items))
+ self.assertEqual(s, '{"one": 1, "two": 2, "three": 3, "four": 4, "five": 5}')
- def _test_encode_basestring_ascii(self, encode_basestring_ascii):
- fname = encode_basestring_ascii.__name__
- for input_string, expect in CASES:
- result = encode_basestring_ascii(input_string)
- self.assertEquals(result, expect)
+
+class TestPyEncodeBasestringAscii(TestEncodeBasestringAscii, PyTest): pass
+class TestCEncodeBasestringAscii(TestEncodeBasestringAscii, CTest): pass
diff --git a/Lib/json/tests/test_fail.py b/Lib/json/tests/test_fail.py
index ee31bfa980..ae962c88a4 100644
--- a/Lib/json/tests/test_fail.py
+++ b/Lib/json/tests/test_fail.py
@@ -1,6 +1,4 @@
-from unittest import TestCase
-
-import json
+from json.tests import PyTest, CTest
# Fri Dec 30 18:57:26 2005
JSONDOCS = [
@@ -61,16 +59,29 @@ SKIPS = {
18: "spec doesn't specify any nesting limitations",
}
-class TestFail(TestCase):
+class TestFail(object):
def test_failures(self):
for idx, doc in enumerate(JSONDOCS):
idx = idx + 1
if idx in SKIPS:
- json.loads(doc)
+ self.loads(doc)
continue
try:
- json.loads(doc)
+ self.loads(doc)
except ValueError:
pass
else:
- self.fail("Expected failure for fail%d.json: %r" % (idx, doc))
+ self.fail("Expected failure for fail{0}.json: {1!r}".format(idx, doc))
+
+ def test_non_string_keys_dict(self):
+ data = {'a' : 1, (1, 2) : 2}
+
+ #This is for c encoder
+ self.assertRaises(TypeError, self.dumps, data)
+
+ #This is for python encoder
+ self.assertRaises(TypeError, self.dumps, data, indent=True)
+
+
+class TestPyFail(TestFail, PyTest): pass
+class TestCFail(TestFail, CTest): pass
diff --git a/Lib/json/tests/test_float.py b/Lib/json/tests/test_float.py
index 9df6d1ee7a..12d35074c9 100644
--- a/Lib/json/tests/test_float.py
+++ b/Lib/json/tests/test_float.py
@@ -1,9 +1,22 @@
import math
-from unittest import TestCase
+from json.tests import PyTest, CTest
-import json
-class TestFloat(TestCase):
+class TestFloat(object):
def test_floats(self):
- for num in [1617161771.7650001, math.pi, math.pi**100, math.pi**-100]:
- self.assertEquals(float(json.dumps(num)), num)
+ for num in [1617161771.7650001, math.pi, math.pi**100,
+ math.pi**-100, 3.1]:
+ self.assertEqual(float(self.dumps(num)), num)
+ self.assertEqual(self.loads(self.dumps(num)), num)
+ self.assertEqual(self.loads(unicode(self.dumps(num))), num)
+
+ def test_ints(self):
+ for num in [1, 1L, 1<<32, 1<<64]:
+ self.assertEqual(self.dumps(num), str(num))
+ self.assertEqual(int(self.dumps(num)), num)
+ self.assertEqual(self.loads(self.dumps(num)), num)
+ self.assertEqual(self.loads(unicode(self.dumps(num))), num)
+
+
+class TestPyFloat(TestFloat, PyTest): pass
+class TestCFloat(TestFloat, CTest): pass
diff --git a/Lib/json/tests/test_indent.py b/Lib/json/tests/test_indent.py
index 605516230f..9b1876123a 100644
--- a/Lib/json/tests/test_indent.py
+++ b/Lib/json/tests/test_indent.py
@@ -1,9 +1,9 @@
-from unittest import TestCase
-
-import json
import textwrap
+from StringIO import StringIO
+from json.tests import PyTest, CTest
+
-class TestIndent(TestCase):
+class TestIndent(object):
def test_indent(self):
h = [['blorpie'], ['whoops'], [], 'd-shtaeou', 'd-nthiouh', 'i-vhbjkhnth',
{'nifty': 87}, {'field': 'yes', 'morefield': False} ]
@@ -30,12 +30,31 @@ class TestIndent(TestCase):
]""")
- d1 = json.dumps(h)
- d2 = json.dumps(h, indent=2, sort_keys=True, separators=(',', ': '))
+ d1 = self.dumps(h)
+ d2 = self.dumps(h, indent=2, sort_keys=True, separators=(',', ': '))
+
+ h1 = self.loads(d1)
+ h2 = self.loads(d2)
+
+ self.assertEqual(h1, h)
+ self.assertEqual(h2, h)
+ self.assertEqual(d2, expect)
+
+ def test_indent0(self):
+ h = {3: 1}
+ def check(indent, expected):
+ d1 = self.dumps(h, indent=indent)
+ self.assertEqual(d1, expected)
+
+ sio = StringIO()
+ self.json.dump(h, sio, indent=indent)
+ self.assertEqual(sio.getvalue(), expected)
+
+ # indent=0 should emit newlines
+ check(0, '{\n"3": 1\n}')
+ # indent=None is more compact
+ check(None, '{"3": 1}')
- h1 = json.loads(d1)
- h2 = json.loads(d2)
- self.assertEquals(h1, h)
- self.assertEquals(h2, h)
- self.assertEquals(d2, expect)
+class TestPyIndent(TestIndent, PyTest): pass
+class TestCIndent(TestIndent, CTest): pass
diff --git a/Lib/json/tests/test_pass1.py b/Lib/json/tests/test_pass1.py
index 216e2528de..82d71543ba 100644
--- a/Lib/json/tests/test_pass1.py
+++ b/Lib/json/tests/test_pass1.py
@@ -1,6 +1,5 @@
-from unittest import TestCase
+from json.tests import PyTest, CTest
-import json
# from http://json.org/JSON_checker/test/pass1.json
JSON = r'''
@@ -62,15 +61,19 @@ JSON = r'''
,"rosebud"]
'''
-class TestPass1(TestCase):
+class TestPass1(object):
def test_parse(self):
# test in/out equivalence and parsing
- res = json.loads(JSON)
- out = json.dumps(res)
- self.assertEquals(res, json.loads(out))
+ res = self.loads(JSON)
+ out = self.dumps(res)
+ self.assertEqual(res, self.loads(out))
try:
- json.dumps(res, allow_nan=False)
+ self.dumps(res, allow_nan=False)
except ValueError:
pass
else:
self.fail("23456789012E666 should be out of range")
+
+
+class TestPyPass1(TestPass1, PyTest): pass
+class TestCPass1(TestPass1, CTest): pass
diff --git a/Lib/json/tests/test_pass2.py b/Lib/json/tests/test_pass2.py
index 80d8433091..a2bb6d7211 100644
--- a/Lib/json/tests/test_pass2.py
+++ b/Lib/json/tests/test_pass2.py
@@ -1,14 +1,18 @@
-from unittest import TestCase
-import json
+from json.tests import PyTest, CTest
+
# from http://json.org/JSON_checker/test/pass2.json
JSON = r'''
[[[[[[[[[[[[[[[[[[["Not too deep"]]]]]]]]]]]]]]]]]]]
'''
-class TestPass2(TestCase):
+class TestPass2(object):
def test_parse(self):
# test in/out equivalence and parsing
- res = json.loads(JSON)
- out = json.dumps(res)
- self.assertEquals(res, json.loads(out))
+ res = self.loads(JSON)
+ out = self.dumps(res)
+ self.assertEqual(res, self.loads(out))
+
+
+class TestPyPass2(TestPass2, PyTest): pass
+class TestCPass2(TestPass2, CTest): pass
diff --git a/Lib/json/tests/test_pass3.py b/Lib/json/tests/test_pass3.py
index 77d87b2aa5..221f9a0c3d 100644
--- a/Lib/json/tests/test_pass3.py
+++ b/Lib/json/tests/test_pass3.py
@@ -1,6 +1,5 @@
-from unittest import TestCase
+from json.tests import PyTest, CTest
-import json
# from http://json.org/JSON_checker/test/pass3.json
JSON = r'''
@@ -12,9 +11,14 @@ JSON = r'''
}
'''
-class TestPass3(TestCase):
+
+class TestPass3(object):
def test_parse(self):
# test in/out equivalence and parsing
- res = json.loads(JSON)
- out = json.dumps(res)
- self.assertEquals(res, json.loads(out))
+ res = self.loads(JSON)
+ out = self.dumps(res)
+ self.assertEqual(res, self.loads(out))
+
+
+class TestPyPass3(TestPass3, PyTest): pass
+class TestCPass3(TestPass3, CTest): pass
diff --git a/Lib/json/tests/test_recursion.py b/Lib/json/tests/test_recursion.py
index 073d3c1bad..b5221e5d16 100644
--- a/Lib/json/tests/test_recursion.py
+++ b/Lib/json/tests/test_recursion.py
@@ -1,28 +1,16 @@
-from unittest import TestCase
+from json.tests import PyTest, CTest
-import json
class JSONTestObject:
pass
-class RecursiveJSONEncoder(json.JSONEncoder):
- recurse = False
- def default(self, o):
- if o is JSONTestObject:
- if self.recurse:
- return [JSONTestObject]
- else:
- return 'JSONTestObject'
- return json.JSONEncoder.default(o)
-
-
-class TestRecursion(TestCase):
+class TestRecursion(object):
def test_listrecursion(self):
x = []
x.append(x)
try:
- json.dumps(x)
+ self.dumps(x)
except ValueError:
pass
else:
@@ -31,7 +19,7 @@ class TestRecursion(TestCase):
y = [x]
x.append(y)
try:
- json.dumps(x)
+ self.dumps(x)
except ValueError:
pass
else:
@@ -39,13 +27,13 @@ class TestRecursion(TestCase):
y = []
x = [y, y]
# ensure that the marker is cleared
- json.dumps(x)
+ self.dumps(x)
def test_dictrecursion(self):
x = {}
x["test"] = x
try:
- json.dumps(x)
+ self.dumps(x)
except ValueError:
pass
else:
@@ -53,11 +41,21 @@ class TestRecursion(TestCase):
x = {}
y = {"a": x, "b": x}
# ensure that the marker is cleared
- json.dumps(x)
+ self.dumps(x)
def test_defaultrecursion(self):
+ class RecursiveJSONEncoder(self.json.JSONEncoder):
+ recurse = False
+ def default(self, o):
+ if o is JSONTestObject:
+ if self.recurse:
+ return [JSONTestObject]
+ else:
+ return 'JSONTestObject'
+ return pyjson.JSONEncoder.default(o)
+
enc = RecursiveJSONEncoder()
- self.assertEquals(enc.encode(JSONTestObject), '"JSONTestObject"')
+ self.assertEqual(enc.encode(JSONTestObject), '"JSONTestObject"')
enc.recurse = True
try:
enc.encode(JSONTestObject)
@@ -65,3 +63,46 @@ class TestRecursion(TestCase):
pass
else:
self.fail("didn't raise ValueError on default recursion")
+
+
+ def test_highly_nested_objects_decoding(self):
+ # test that loading highly-nested objects doesn't segfault when C
+ # accelerations are used. See #12017
+ # str
+ with self.assertRaises(RuntimeError):
+ self.loads('{"a":' * 100000 + '1' + '}' * 100000)
+ with self.assertRaises(RuntimeError):
+ self.loads('{"a":' * 100000 + '[1]' + '}' * 100000)
+ with self.assertRaises(RuntimeError):
+ self.loads('[' * 100000 + '1' + ']' * 100000)
+ # unicode
+ with self.assertRaises(RuntimeError):
+ self.loads(u'{"a":' * 100000 + u'1' + u'}' * 100000)
+ with self.assertRaises(RuntimeError):
+ self.loads(u'{"a":' * 100000 + u'[1]' + u'}' * 100000)
+ with self.assertRaises(RuntimeError):
+ self.loads(u'[' * 100000 + u'1' + u']' * 100000)
+
+ def test_highly_nested_objects_encoding(self):
+ # See #12051
+ l, d = [], {}
+ for x in xrange(100000):
+ l, d = [l], {'k':d}
+ with self.assertRaises(RuntimeError):
+ self.dumps(l)
+ with self.assertRaises(RuntimeError):
+ self.dumps(d)
+
+ def test_endless_recursion(self):
+ # See #12051
+ class EndlessJSONEncoder(self.json.JSONEncoder):
+ def default(self, o):
+ """If check_circular is False, this will keep adding another list."""
+ return [o]
+
+ with self.assertRaises(RuntimeError):
+ EndlessJSONEncoder(check_circular=False).encode(5j)
+
+
+class TestPyRecursion(TestRecursion, PyTest): pass
+class TestCRecursion(TestRecursion, CTest): pass
diff --git a/Lib/json/tests/test_scanstring.py b/Lib/json/tests/test_scanstring.py
index 6b600dbe16..4fef8cbabf 100644
--- a/Lib/json/tests/test_scanstring.py
+++ b/Lib/json/tests/test_scanstring.py
@@ -1,109 +1,109 @@
import sys
-import decimal
-from unittest import TestCase
+from json.tests import PyTest, CTest
-import json
-import json.decoder
-class TestScanString(TestCase):
- def test_py_scanstring(self):
- self._test_scanstring(json.decoder.py_scanstring)
-
- def test_c_scanstring(self):
- self._test_scanstring(json.decoder.c_scanstring)
-
- def _test_scanstring(self, scanstring):
- self.assertEquals(
+class TestScanstring(object):
+ def test_scanstring(self):
+ scanstring = self.json.decoder.scanstring
+ self.assertEqual(
scanstring('"z\\ud834\\udd20x"', 1, None, True),
(u'z\U0001d120x', 16))
if sys.maxunicode == 65535:
- self.assertEquals(
+ self.assertEqual(
scanstring(u'"z\U0001d120x"', 1, None, True),
(u'z\U0001d120x', 6))
else:
- self.assertEquals(
+ self.assertEqual(
scanstring(u'"z\U0001d120x"', 1, None, True),
(u'z\U0001d120x', 5))
- self.assertEquals(
+ self.assertEqual(
scanstring('"\\u007b"', 1, None, True),
(u'{', 8))
- self.assertEquals(
+ self.assertEqual(
scanstring('"A JSON payload should be an object or array, not a string."', 1, None, True),
(u'A JSON payload should be an object or array, not a string.', 60))
- self.assertEquals(
+ self.assertEqual(
scanstring('["Unclosed array"', 2, None, True),
(u'Unclosed array', 17))
- self.assertEquals(
+ self.assertEqual(
scanstring('["extra comma",]', 2, None, True),
(u'extra comma', 14))
- self.assertEquals(
+ self.assertEqual(
scanstring('["double extra comma",,]', 2, None, True),
(u'double extra comma', 21))
- self.assertEquals(
+ self.assertEqual(
scanstring('["Comma after the close"],', 2, None, True),
(u'Comma after the close', 24))
- self.assertEquals(
+ self.assertEqual(
scanstring('["Extra close"]]', 2, None, True),
(u'Extra close', 14))
- self.assertEquals(
+ self.assertEqual(
scanstring('{"Extra comma": true,}', 2, None, True),
(u'Extra comma', 14))
- self.assertEquals(
+ self.assertEqual(
scanstring('{"Extra value after close": true} "misplaced quoted value"', 2, None, True),
(u'Extra value after close', 26))
- self.assertEquals(
+ self.assertEqual(
scanstring('{"Illegal expression": 1 + 2}', 2, None, True),
(u'Illegal expression', 21))
- self.assertEquals(
+ self.assertEqual(
scanstring('{"Illegal invocation": alert()}', 2, None, True),
(u'Illegal invocation', 21))
- self.assertEquals(
+ self.assertEqual(
scanstring('{"Numbers cannot have leading zeroes": 013}', 2, None, True),
(u'Numbers cannot have leading zeroes', 37))
- self.assertEquals(
+ self.assertEqual(
scanstring('{"Numbers cannot be hex": 0x14}', 2, None, True),
(u'Numbers cannot be hex', 24))
- self.assertEquals(
+ self.assertEqual(
scanstring('[[[[[[[[[[[[[[[[[[[["Too deep"]]]]]]]]]]]]]]]]]]]]', 21, None, True),
(u'Too deep', 30))
- self.assertEquals(
+ self.assertEqual(
scanstring('{"Missing colon" null}', 2, None, True),
(u'Missing colon', 16))
- self.assertEquals(
+ self.assertEqual(
scanstring('{"Double colon":: null}', 2, None, True),
(u'Double colon', 15))
- self.assertEquals(
+ self.assertEqual(
scanstring('{"Comma instead of colon", null}', 2, None, True),
(u'Comma instead of colon', 25))
- self.assertEquals(
+ self.assertEqual(
scanstring('["Colon instead of comma": false]', 2, None, True),
(u'Colon instead of comma', 25))
- self.assertEquals(
+ self.assertEqual(
scanstring('["Bad value", truth]', 2, None, True),
(u'Bad value', 12))
def test_issue3623(self):
- self.assertRaises(ValueError, json.decoder.scanstring, b"xxx", 1,
+ self.assertRaises(ValueError, self.json.decoder.scanstring, b"xxx", 1,
"xxx")
self.assertRaises(UnicodeDecodeError,
- json.encoder.encode_basestring_ascii, b"xx\xff")
+ self.json.encoder.encode_basestring_ascii, b"xx\xff")
+
+ def test_overflow(self):
+ with self.assertRaises(OverflowError):
+ self.json.decoder.scanstring(b"xxx", sys.maxsize+1)
+
+
+class TestPyScanstring(TestScanstring, PyTest): pass
+class TestCScanstring(TestScanstring, CTest): pass
diff --git a/Lib/json/tests/test_separators.py b/Lib/json/tests/test_separators.py
index 32db341929..a4246e1f2d 100644
--- a/Lib/json/tests/test_separators.py
+++ b/Lib/json/tests/test_separators.py
@@ -1,10 +1,8 @@
import textwrap
-from unittest import TestCase
+from json.tests import PyTest, CTest
-import json
-
-class TestSeparators(TestCase):
+class TestSeparators(object):
def test_separators(self):
h = [['blorpie'], ['whoops'], [], 'd-shtaeou', 'd-nthiouh', 'i-vhbjkhnth',
{'nifty': 87}, {'field': 'yes', 'morefield': False} ]
@@ -31,12 +29,16 @@ class TestSeparators(TestCase):
]""")
- d1 = json.dumps(h)
- d2 = json.dumps(h, indent=2, sort_keys=True, separators=(' ,', ' : '))
+ d1 = self.dumps(h)
+ d2 = self.dumps(h, indent=2, sort_keys=True, separators=(' ,', ' : '))
+
+ h1 = self.loads(d1)
+ h2 = self.loads(d2)
+
+ self.assertEqual(h1, h)
+ self.assertEqual(h2, h)
+ self.assertEqual(d2, expect)
- h1 = json.loads(d1)
- h2 = json.loads(d2)
- self.assertEquals(h1, h)
- self.assertEquals(h2, h)
- self.assertEquals(d2, expect)
+class TestPySeparators(TestSeparators, PyTest): pass
+class TestCSeparators(TestSeparators, CTest): pass
diff --git a/Lib/json/tests/test_speedups.py b/Lib/json/tests/test_speedups.py
index 8ff9a3812f..7186a40932 100644
--- a/Lib/json/tests/test_speedups.py
+++ b/Lib/json/tests/test_speedups.py
@@ -1,15 +1,23 @@
-import decimal
-from unittest import TestCase
+from json.tests import CTest
-from json import decoder
-from json import encoder
-class TestSpeedups(TestCase):
+class TestSpeedups(CTest):
def test_scanstring(self):
- self.assertEquals(decoder.scanstring.__module__, "_json")
- self.assert_(decoder.scanstring is decoder.c_scanstring)
+ self.assertEqual(self.json.decoder.scanstring.__module__, "_json")
+ self.assertIs(self.json.decoder.scanstring, self.json.decoder.c_scanstring)
def test_encode_basestring_ascii(self):
- self.assertEquals(encoder.encode_basestring_ascii.__module__, "_json")
- self.assert_(encoder.encode_basestring_ascii is
- encoder.c_encode_basestring_ascii)
+ self.assertEqual(self.json.encoder.encode_basestring_ascii.__module__,
+ "_json")
+ self.assertIs(self.json.encoder.encode_basestring_ascii,
+ self.json.encoder.c_encode_basestring_ascii)
+
+class TestDecode(CTest):
+ def test_make_scanner(self):
+ self.assertRaises(AttributeError, self.json.scanner.c_make_scanner, 1)
+
+ def test_make_encoder(self):
+ self.assertRaises(TypeError, self.json.encoder.c_make_encoder,
+ None,
+ "\xCD\x7D\x3D\x4E\x12\x4C\xF9\x79\xD7\x52\xBA\x82\xF2\x27\x4A\x7D\xA0\xCA\x75",
+ None)
diff --git a/Lib/json/tests/test_unicode.py b/Lib/json/tests/test_unicode.py
index 3ac4541b6c..31cf38925c 100644
--- a/Lib/json/tests/test_unicode.py
+++ b/Lib/json/tests/test_unicode.py
@@ -1,55 +1,85 @@
-from unittest import TestCase
+from collections import OrderedDict
+from json.tests import PyTest, CTest
-import json
-class TestUnicode(TestCase):
+class TestUnicode(object):
def test_encoding1(self):
- encoder = json.JSONEncoder(encoding='utf-8')
+ encoder = self.json.JSONEncoder(encoding='utf-8')
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
s = u.encode('utf-8')
ju = encoder.encode(u)
js = encoder.encode(s)
- self.assertEquals(ju, js)
+ self.assertEqual(ju, js)
def test_encoding2(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
s = u.encode('utf-8')
- ju = json.dumps(u, encoding='utf-8')
- js = json.dumps(s, encoding='utf-8')
- self.assertEquals(ju, js)
+ ju = self.dumps(u, encoding='utf-8')
+ js = self.dumps(s, encoding='utf-8')
+ self.assertEqual(ju, js)
def test_encoding3(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
- j = json.dumps(u)
- self.assertEquals(j, '"\\u03b1\\u03a9"')
+ j = self.dumps(u)
+ self.assertEqual(j, '"\\u03b1\\u03a9"')
def test_encoding4(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
- j = json.dumps([u])
- self.assertEquals(j, '["\\u03b1\\u03a9"]')
+ j = self.dumps([u])
+ self.assertEqual(j, '["\\u03b1\\u03a9"]')
def test_encoding5(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
- j = json.dumps(u, ensure_ascii=False)
- self.assertEquals(j, u'"{0}"'.format(u))
+ j = self.dumps(u, ensure_ascii=False)
+ self.assertEqual(j, u'"{0}"'.format(u))
def test_encoding6(self):
u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
- j = json.dumps([u], ensure_ascii=False)
- self.assertEquals(j, u'["{0}"]'.format(u))
+ j = self.dumps([u], ensure_ascii=False)
+ self.assertEqual(j, u'["{0}"]'.format(u))
def test_big_unicode_encode(self):
u = u'\U0001d120'
- self.assertEquals(json.dumps(u), '"\\ud834\\udd20"')
- self.assertEquals(json.dumps(u, ensure_ascii=False), u'"\U0001d120"')
+ self.assertEqual(self.dumps(u), '"\\ud834\\udd20"')
+ self.assertEqual(self.dumps(u, ensure_ascii=False), u'"\U0001d120"')
def test_big_unicode_decode(self):
u = u'z\U0001d120x'
- self.assertEquals(json.loads('"' + u + '"'), u)
- self.assertEquals(json.loads('"z\\ud834\\udd20x"'), u)
+ self.assertEqual(self.loads('"' + u + '"'), u)
+ self.assertEqual(self.loads('"z\\ud834\\udd20x"'), u)
def test_unicode_decode(self):
for i in range(0, 0xd7ff):
u = unichr(i)
- js = '"\\u{0:04x}"'.format(i)
- self.assertEquals(json.loads(js), u)
+ s = '"\\u{0:04x}"'.format(i)
+ self.assertEqual(self.loads(s), u)
+
+ def test_object_pairs_hook_with_unicode(self):
+ s = u'{"xkd":1, "kcw":2, "art":3, "hxm":4, "qrt":5, "pad":6, "hoy":7}'
+ p = [(u"xkd", 1), (u"kcw", 2), (u"art", 3), (u"hxm", 4),
+ (u"qrt", 5), (u"pad", 6), (u"hoy", 7)]
+ self.assertEqual(self.loads(s), eval(s))
+ self.assertEqual(self.loads(s, object_pairs_hook = lambda x: x), p)
+ od = self.loads(s, object_pairs_hook = OrderedDict)
+ self.assertEqual(od, OrderedDict(p))
+ self.assertEqual(type(od), OrderedDict)
+ # the object_pairs_hook takes priority over the object_hook
+ self.assertEqual(self.loads(s,
+ object_pairs_hook = OrderedDict,
+ object_hook = lambda x: None),
+ OrderedDict(p))
+
+ def test_default_encoding(self):
+ self.assertEqual(self.loads(u'{"a": "\xe9"}'.encode('utf-8')),
+ {'a': u'\xe9'})
+
+ def test_unicode_preservation(self):
+ self.assertEqual(type(self.loads(u'""')), unicode)
+ self.assertEqual(type(self.loads(u'"a"')), unicode)
+ self.assertEqual(type(self.loads(u'["a"]')[0]), unicode)
+ # Issue 10038.
+ self.assertEqual(type(self.loads('"foo"')), unicode)
+
+
+class TestPyUnicode(TestUnicode, PyTest): pass
+class TestCUnicode(TestUnicode, CTest): pass
diff --git a/Lib/json/tool.py b/Lib/json/tool.py
index daedbb5e19..c37bb777ff 100644
--- a/Lib/json/tool.py
+++ b/Lib/json/tool.py
@@ -2,11 +2,11 @@ r"""Command-line tool to validate and pretty-print JSON
Usage::
- $ echo '{"json":"obj"}' | python -mjson.tool
+ $ echo '{"json":"obj"}' | python -m json.tool
{
"json": "obj"
}
- $ echo '{ 1.2:3.4}' | python -mjson.tool
+ $ echo '{ 1.2:3.4}' | python -m json.tool
Expecting property name: line 1 column 2 (char 2)
"""
@@ -24,7 +24,7 @@ def main():
infile = open(sys.argv[1], 'rb')
outfile = open(sys.argv[2], 'wb')
else:
- raise SystemExit("{0} [infile [outfile]]".format(sys.argv[0]))
+ raise SystemExit(sys.argv[0] + " [infile [outfile]]")
try:
obj = json.load(infile)
except ValueError, e:
View Lorry Controller Status