[pypy-commit] extradoc extradoc: .
fijal
noreply at buildbot.pypy.org
Wed Mar 7 17:03:00 CET 2012
Author: Maciej Fijalkowski <fijall at gmail.com>
Branch: extradoc
Changeset: r4128:c950242a779b
Date: 2012-03-07 08:02 -0800
http://bitbucket.org/pypy/extradoc/changeset/c950242a779b/
Log: .
diff --git a/talk/pycon2012/tutorial/bench/json/__init__.py b/talk/pycon2012/tutorial/bench/json/__init__.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/__init__.py
@@ -0,0 +1,339 @@
+r"""JSON (JavaScript Object Notation) <http://json.org> is a subset of
+JavaScript syntax (ECMA-262 3rd edition) used as a lightweight data
+interchange format.
+
+:mod:`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::
+
+ >>> import json
+ >>> json.dumps(['foo', {'bar': ('baz', None, 1.0, 2)}])
+ '["foo", {"bar": ["baz", null, 1.0, 2]}]'
+ >>> print json.dumps("\"foo\bar")
+ "\"foo\bar"
+ >>> print json.dumps(u'\u1234')
+ "\u1234"
+ >>> print json.dumps('\\')
+ "\\"
+ >>> print json.dumps({"c": 0, "b": 0, "a": 0}, sort_keys=True)
+ {"a": 0, "b": 0, "c": 0}
+ >>> from StringIO import StringIO
+ >>> io = StringIO()
+ >>> json.dump(['streaming API'], io)
+ >>> io.getvalue()
+ '["streaming API"]'
+
+Compact encoding::
+
+ >>> import json
+ >>> json.dumps([1,2,3,{'4': 5, '6': 7}], separators=(',',':'))
+ '[1,2,3,{"4":5,"6":7}]'
+
+Pretty printing::
+
+ >>> import json
+ >>> s = json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=4)
+ >>> print '\n'.join([l.rstrip() for l in s.splitlines()])
+ {
+ "4": 5,
+ "6": 7
+ }
+
+Decoding JSON::
+
+ >>> import json
+ >>> obj = [u'foo', {u'bar': [u'baz', None, 1.0, 2]}]
+ >>> json.loads('["foo", {"bar":["baz", null, 1.0, 2]}]') == obj
+ True
+ >>> json.loads('"\\"foo\\bar"') == u'"foo\x08ar'
+ True
+ >>> from StringIO import StringIO
+ >>> io = StringIO('["streaming API"]')
+ >>> json.load(io)[0] == 'streaming API'
+ True
+
+Specializing JSON object decoding::
+
+ >>> import json
+ >>> def as_complex(dct):
+ ... if '__complex__' in dct:
+ ... return complex(dct['real'], dct['imag'])
+ ... return dct
+ ...
+ >>> json.loads('{"__complex__": true, "real": 1, "imag": 2}',
+ ... object_hook=as_complex)
+ (1+2j)
+ >>> from decimal import Decimal
+ >>> json.loads('1.1', parse_float=Decimal) == Decimal('1.1')
+ True
+
+Specializing JSON object encoding::
+
+ >>> import json
+ >>> def encode_complex(obj):
+ ... if isinstance(obj, complex):
+ ... return [obj.real, obj.imag]
+ ... raise TypeError(repr(o) + " is not JSON serializable")
+ ...
+ >>> json.dumps(2 + 1j, default=encode_complex)
+ '[2.0, 1.0]'
+ >>> json.JSONEncoder(default=encode_complex).encode(2 + 1j)
+ '[2.0, 1.0]'
+ >>> ''.join(json.JSONEncoder(default=encode_complex).iterencode(2 + 1j))
+ '[2.0, 1.0]'
+
+
+Using json.tool from the shell to validate and pretty-print::
+
+ $ echo '{"json":"obj"}' | python -m json.tool
+ {
+ "json": "obj"
+ }
+ $ echo '{ 1.2:3.4}' | python -m json.tool
+ Expecting property name: line 1 column 2 (char 2)
+"""
+__version__ = '2.0.9'
+__all__ = [
+ 'dump', 'dumps', 'load', 'loads',
+ 'JSONDecoder', 'JSONEncoder',
+]
+
+__author__ = 'Bob Ippolito <bob at redivi.com>'
+
+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, separators=None,
+ encoding='utf-8', default=None, **kw):
+ """Serialize ``obj`` as a JSON formatted stream to ``fp`` (a
+ ``.write()``-supporting file-like object).
+
+ If ``skipkeys`` is true then ``dict`` keys that are not basic types
+ (``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
+ will be skipped instead of raising a ``TypeError``.
+
+ If ``ensure_ascii`` is false, then the some chunks written to ``fp``
+ may be ``unicode`` instances, subject to normal Python ``str`` to
+ ``unicode`` coercion rules. Unless ``fp.write()`` explicitly
+ understands ``unicode`` (as in ``codecs.getwriter()``) this is likely
+ to cause an error.
+
+ If ``check_circular`` is false, then the circular reference check
+ for container types will be skipped and a circular reference will
+ result in an ``OverflowError`` (or worse).
+
+ If ``allow_nan`` is false, then it will be a ``ValueError`` to
+ serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``)
+ in strict compliance of the JSON specification, instead of using the
+ JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).
+
+ If ``indent`` is a 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.
+ ``(',', ':')`` 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; otherwise ``JSONEncoder`` is used.
+
+ """
+ # cached encoder
+ if (not skipkeys and ensure_ascii and
+ check_circular and allow_nan and
+ cls is None and indent is None and separators is None and
+ encoding == 'utf-8' and default is None and not kw):
+ iterable = _default_encoder.iterencode(obj)
+ else:
+ if cls is None:
+ cls = JSONEncoder
+ iterable = cls(skipkeys=skipkeys, ensure_ascii=ensure_ascii,
+ check_circular=check_circular, allow_nan=allow_nan, indent=indent,
+ separators=separators, encoding=encoding,
+ default=default, **kw).iterencode(obj)
+ # could accelerate with writelines in some versions of Python, at
+ # a debuggability cost
+ for chunk in iterable:
+ fp.write(chunk)
+
+
+def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True,
+ allow_nan=True, cls=None, indent=None, separators=None,
+ encoding='utf-8', default=None, **kw):
+ """Serialize ``obj`` to a JSON formatted ``str``.
+
+ If ``skipkeys`` is false then ``dict`` keys that are not basic types
+ (``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``)
+ will be skipped instead of raising a ``TypeError``.
+
+ If ``ensure_ascii`` is false, then the return value will be a
+ ``unicode`` instance subject to normal Python ``str`` to ``unicode``
+ coercion rules instead of being escaped to an ASCII ``str``.
+
+ If ``check_circular`` is false, then the circular reference check
+ for container types will be skipped and a circular reference will
+ result in an ``OverflowError`` (or worse).
+
+ If ``allow_nan`` is false, then it will be a ``ValueError`` to
+ serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``) in
+ strict compliance of the JSON specification, instead of using the
+ JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).
+
+ If ``indent`` is a 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.
+ ``(',', ':')`` 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; otherwise ``JSONEncoder`` is used.
+
+ """
+ # cached encoder
+ if (not skipkeys and ensure_ascii and
+ check_circular and allow_nan and
+ cls is None and indent is None and separators is None and
+ encoding == 'utf-8' and default is None and not kw):
+ return _default_encoder.encode(obj)
+ if cls is None:
+ cls = JSONEncoder
+ return cls(
+ skipkeys=skipkeys, ensure_ascii=ensure_ascii,
+ check_circular=check_circular, allow_nan=allow_nan, indent=indent,
+ separators=separators, encoding=encoding, default=default,
+ **kw).encode(obj)
+
+
+_default_decoder = JSONDecoder(encoding=None, object_hook=None,
+ object_pairs_hook=None)
+
+
+def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None,
+ parse_int=None, parse_constant=None, object_pairs_hook=None, **kw):
+ """Deserialize ``fp`` (a ``.read()``-supporting file-like object containing
+ a JSON document) to a Python object.
+
+ If the contents of ``fp`` is encoded with an ASCII based encoding other
+ than utf-8 (e.g. latin-1), then an appropriate ``encoding`` name must
+ be specified. Encodings that are not ASCII based (such as UCS-2) are
+ not allowed, and should be wrapped with
+ ``codecs.getreader(fp)(encoding)``, or simply decoded to a ``unicode``
+ object and passed to ``loads()``
+
+ ``object_hook`` is an optional function that will be called with the
+ result of any object literal decode (a ``dict``). The return value of
+ ``object_hook`` will be used instead of the ``dict``. This feature
+ 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; 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, 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, object_pairs_hook=None, **kw):
+ """Deserialize ``s`` (a ``str`` or ``unicode`` instance containing a JSON
+ document) to a Python object.
+
+ If ``s`` is a ``str`` instance and is encoded with an ASCII based encoding
+ other than utf-8 (e.g. latin-1) then an appropriate ``encoding`` name
+ must be specified. Encodings that are not ASCII based (such as UCS-2)
+ are not allowed and should be decoded to ``unicode`` first.
+
+ ``object_hook`` is an optional function that will be called with the
+ result of any object literal decode (a ``dict``). The return value of
+ ``object_hook`` will be used instead of the ``dict``. This feature
+ 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
+ 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; 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 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:
+ kw['parse_int'] = parse_int
+ if parse_constant is not None:
+ kw['parse_constant'] = parse_constant
+ return cls(encoding=encoding, **kw).decode(s)
diff --git a/talk/pycon2012/tutorial/bench/json/decoder.py b/talk/pycon2012/tutorial/bench/json/decoder.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/decoder.py
@@ -0,0 +1,385 @@
+"""Implementation of JSONDecoder
+"""
+import re
+import sys
+import struct
+
+from json import scanner
+try:
+ from _json import scanstring as c_scanstring
+except ImportError:
+ c_scanstring = None
+
+__all__ = ['JSONDecoder']
+
+FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL
+
+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):
+ lineno = doc.count('\n', 0, pos) + 1
+ if lineno == 1:
+ colno = pos
+ else:
+ colno = pos - doc.rindex('\n', 0, pos)
+ return lineno, colno
+
+
+def errmsg(msg, doc, pos, end=None):
+ # Note that this function is called from _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,
+}
+
+STRINGCHUNK = re.compile(r'(.*?)(["\\\x00-\x1f])', FLAGS)
+BACKSLASH = {
+ '"': u'"', '\\': u'\\', '/': u'/',
+ 'b': u'\b', 'f': u'\f', 'n': u'\n', 'r': u'\r', 't': u'\t',
+}
+
+DEFAULT_ENCODING = "utf-8"
+
+def py_scanstring(s, end, encoding=None, strict=True,
+ _b=BACKSLASH, _m=STRINGCHUNK.match):
+ """Scan the string s for a JSON string. End is the index of the
+ character in s after the quote that started the JSON string.
+ Unescapes all valid JSON string escape sequences and raises ValueError
+ on attempt to decode an invalid string. If strict is False then literal
+ control characters are allowed in the string.
+
+ Returns a tuple of the decoded string and the index of the character in s
+ after the end quote."""
+ if encoding is None:
+ encoding = DEFAULT_ENCODING
+ chunks = []
+ _append = chunks.append
+ begin = end - 1
+ while 1:
+ chunk = _m(s, end)
+ if chunk is None:
+ raise ValueError(
+ 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:
+ _append(terminator)
+ continue
+ try:
+ esc = s[end]
+ 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:
+ char = _b[esc]
+ except KeyError:
+ 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
+ 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 the unescaped character
+ _append(char)
+ return u''.join(chunks), end
+
+
+# Use speedup if available
+scanstring = c_scanstring or py_scanstring
+
+WHITESPACE = re.compile(r'[ \t\n\r]*', FLAGS)
+WHITESPACE_STR = ' \t\n\r'
+
+def JSONObject(s_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]
+ # Normally we expect nextchar == '"'
+ if nextchar != '"':
+ if nextchar in _ws:
+ end = _w(s, end).end()
+ nextchar = s[end:end + 1]
+ # Trivial empty object
+ if nextchar == '}':
+ if object_pairs_hook is not None:
+ result = object_pairs_hook(pairs)
+ return result, end
+ pairs = {}
+ if object_hook is not None:
+ pairs = object_hook(pairs)
+ return pairs, end + 1
+ elif nextchar != '"':
+ raise ValueError(errmsg("Expecting property name", s, end))
+ end += 1
+ while True:
+ key, end = scanstring(s, end, encoding, strict)
+
+ # To skip some function call overhead we optimize the fast paths where
+ # the JSON key separator is ": " or just ":".
+ if s[end:end + 1] != ':':
+ end = _w(s, end).end()
+ if s[end:end + 1] != ':':
+ raise ValueError(errmsg("Expecting : delimiter", s, end))
+
+ end += 1
+
+ try:
+ if s[end] in _ws:
+ end += 1
+ if s[end] in _ws:
+ end = _w(s, end + 1).end()
+ except IndexError:
+ pass
+
+ try:
+ value, end = scan_once(s, end)
+ except StopIteration:
+ raise ValueError(errmsg("Expecting object", s, end))
+ pairs_append((key, value))
+
+ try:
+ nextchar = s[end]
+ if nextchar in _ws:
+ end = _w(s, end + 1).end()
+ nextchar = s[end]
+ except IndexError:
+ nextchar = ''
+ end += 1
+
+ if nextchar == '}':
+ break
+ elif nextchar != ',':
+ raise ValueError(errmsg("Expecting , delimiter", s, end - 1))
+
+ try:
+ nextchar = s[end]
+ if nextchar in _ws:
+ end += 1
+ nextchar = s[end]
+ if nextchar in _ws:
+ end = _w(s, end + 1).end()
+ nextchar = s[end]
+ except IndexError:
+ nextchar = ''
+
+ end += 1
+ if nextchar != '"':
+ raise ValueError(errmsg("Expecting property name", s, end - 1))
+
+ if object_pairs_hook is not None:
+ result = object_pairs_hook(pairs)
+ return result, end
+ pairs = dict(pairs)
+ if object_hook is not None:
+ pairs = object_hook(pairs)
+ return pairs, end
+
+def JSONArray(s_and_end, scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR):
+ s, end = s_and_end
+ values = []
+ nextchar = s[end:end + 1]
+ if nextchar in _ws:
+ end = _w(s, end + 1).end()
+ nextchar = s[end:end + 1]
+ # Look-ahead for trivial empty array
+ if nextchar == ']':
+ return values, end + 1
+ _append = values.append
+ while True:
+ try:
+ value, end = scan_once(s, end)
+ except StopIteration:
+ raise ValueError(errmsg("Expecting object", s, end))
+ _append(value)
+ nextchar = s[end:end + 1]
+ if nextchar in _ws:
+ end = _w(s, end + 1).end()
+ nextchar = s[end:end + 1]
+ end += 1
+ if nextchar == ']':
+ break
+ elif nextchar != ',':
+ raise ValueError(errmsg("Expecting , delimiter", s, end))
+
+ try:
+ if s[end] in _ws:
+ end += 1
+ if s[end] in _ws:
+ end = _w(s, end + 1).end()
+ except IndexError:
+ pass
+
+ return values, end
+
+class JSONDecoder(object):
+ """Simple JSON <http://json.org> decoder
+
+ Performs the following translations in decoding by default:
+
+ +---------------+-------------------+
+ | JSON | Python |
+ +===============+===================+
+ | object | dict |
+ +---------------+-------------------+
+ | array | list |
+ +---------------+-------------------+
+ | string | unicode |
+ +---------------+-------------------+
+ | number (int) | int, long |
+ +---------------+-------------------+
+ | number (real) | float |
+ +---------------+-------------------+
+ | true | True |
+ +---------------+-------------------+
+ | false | False |
+ +---------------+-------------------+
+ | null | None |
+ +---------------+-------------------+
+
+ It also understands ``NaN``, ``Infinity``, and ``-Infinity`` as
+ their corresponding ``float`` values, which is outside the JSON spec.
+
+ """
+
+ def __init__(self, encoding=None, object_hook=None, parse_float=None,
+ parse_int=None, parse_constant=None, strict=True,
+ object_pairs_hook=None):
+ """``encoding`` determines the encoding used to interpret any ``str``
+ objects decoded by this instance (utf-8 by default). It has no
+ effect when decoding ``unicode`` objects.
+
+ 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
+ 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
+ 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.
+ 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.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``
+ instance containing a JSON document)
+
+ """
+ obj, end = self.raw_decode(s, idx=_w(s, 0).end())
+ end = _w(s, end).end()
+ if end != len(s):
+ raise ValueError(errmsg("Extra data", s, end, len(s)))
+ return obj
+
+ def raw_decode(self, s, idx=0):
+ """Decode a JSON document from ``s`` (a ``str`` or ``unicode``
+ beginning with a JSON document) and return a 2-tuple of the Python
+ representation and the index in ``s`` where the document ended.
+
+ This can be used to decode a JSON document from a string that may
+ have extraneous data at the end.
+
+ """
+ try:
+ obj, end = self.scan_once(s, idx)
+ except StopIteration:
+ raise ValueError("No JSON object could be decoded")
+ return obj, end
diff --git a/talk/pycon2012/tutorial/bench/json/encoder.py b/talk/pycon2012/tutorial/bench/json/encoder.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/encoder.py
@@ -0,0 +1,442 @@
+"""Implementation of JSONEncoder
+"""
+import re
+
+try:
+ from _json import encode_basestring_ascii as c_encode_basestring_ascii
+except ImportError:
+ c_encode_basestring_ascii = None
+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'([\\"]|[^\ -~])')
+HAS_UTF8 = re.compile(r'[\x80-\xff]')
+ESCAPE_DCT = {
+ '\\': '\\\\',
+ '"': '\\"',
+ '\b': '\\b',
+ '\f': '\\f',
+ '\n': '\\n',
+ '\r': '\\r',
+ '\t': '\\t',
+}
+for i in range(0x20):
+ ESCAPE_DCT.setdefault(chr(i), '\\u{0:04x}'.format(i))
+ #ESCAPE_DCT.setdefault(chr(i), '\\u%04x' % (i,))
+
+# Assume this produces an infinity on all machines (probably not guaranteed)
+INFINITY = float('1e66666')
+FLOAT_REPR = repr
+
+def encode_basestring(s):
+ """Return a JSON representation of a Python string
+
+ """
+ def replace(match):
+ return ESCAPE_DCT[match.group(0)]
+ return '"' + ESCAPE.sub(replace, 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):
+ s = match.group(0)
+ try:
+ return ESCAPE_DCT[s]
+ except KeyError:
+ n = ord(s)
+ if n < 0x10000:
+ return '\\u{0:04x}'.format(n)
+ #return '\\u%04x' % (n,)
+ else:
+ # surrogate pair
+ n -= 0x10000
+ s1 = 0xd800 | ((n >> 10) & 0x3ff)
+ s2 = 0xdc00 | (n & 0x3ff)
+ return '\\u{0:04x}\\u{1:04x}'.format(s1, s2)
+ #return '\\u%04x\\u%04x' % (s1, s2)
+ return '"' + str(ESCAPE_ASCII.sub(replace, s)) + '"'
+
+
+encode_basestring_ascii = (
+ c_encode_basestring_ascii or py_encode_basestring_ascii)
+
+class JSONEncoder(object):
+ """Extensible JSON <http://json.org> encoder for Python data structures.
+
+ Supports the following objects and types by default:
+
+ +-------------------+---------------+
+ | Python | JSON |
+ +===================+===============+
+ | dict | object |
+ +-------------------+---------------+
+ | list, tuple | array |
+ +-------------------+---------------+
+ | str, unicode | string |
+ +-------------------+---------------+
+ | int, long, float | number |
+ +-------------------+---------------+
+ | True | true |
+ +-------------------+---------------+
+ | False | false |
+ +-------------------+---------------+
+ | None | null |
+ +-------------------+---------------+
+
+ To extend this to recognize other objects, subclass and implement a
+ ``.default()`` method with another method that returns a serializable
+ object for ``o`` if possible, otherwise it should call the superclass
+ implementation (to raise ``TypeError``).
+
+ """
+ item_separator = ', '
+ key_separator = ': '
+ def __init__(self, skipkeys=False, ensure_ascii=True,
+ check_circular=True, allow_nan=True, sort_keys=False,
+ indent=None, separators=None, encoding='utf-8', default=None):
+ """Constructor for JSONEncoder, with sensible defaults.
+
+ If skipkeys is false, then it is a TypeError to attempt
+ encoding of keys that are not str, int, long, float or None. If
+ skipkeys is True, such items are simply skipped.
+
+ If ensure_ascii is true, the output is guaranteed to be str
+ objects with all incoming unicode characters escaped. If
+ ensure_ascii is false, the output will be unicode object.
+
+ If check_circular is true, then lists, dicts, and custom encoded
+ objects will be checked for circular references during encoding to
+ prevent an infinite recursion (which would cause an OverflowError).
+ Otherwise, no such check takes place.
+
+ If allow_nan is true, then NaN, Infinity, and -Infinity will be
+ encoded as such. This behavior is not JSON specification compliant,
+ but is consistent with most JavaScript based encoders and decoders.
+ Otherwise, it will be a ValueError to encode such floats.
+
+ If sort_keys is true, then the output of dictionaries will be
+ sorted by key; this is useful for regression tests to ensure
+ that JSON serializations can be compared on a day-to-day basis.
+
+ If indent is a 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 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
+ self.ensure_ascii = ensure_ascii
+ self.check_circular = check_circular
+ self.allow_nan = allow_nan
+ self.sort_keys = sort_keys
+ self.indent = indent
+ if separators is not None:
+ self.item_separator, self.key_separator = separators
+ if default is not None:
+ self.default = default
+ self.encoding = encoding
+
+ def default(self, o):
+ """Implement this method in a subclass such that it returns
+ a serializable object for ``o``, or calls the base implementation
+ (to raise a ``TypeError``).
+
+ For example, to support arbitrary iterators, you could
+ implement default like this::
+
+ def default(self, o):
+ try:
+ iterable = iter(o)
+ except TypeError:
+ pass
+ else:
+ return list(iterable)
+ return JSONEncoder.default(self, o)
+
+ """
+ raise TypeError(repr(o) + " is not JSON serializable")
+
+ def encode(self, o):
+ """Return a JSON string representation of a Python data structure.
+
+ >>> 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))
+
+ 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
+ if markers is not None:
+ markerid = id(lst)
+ if markerid in markers:
+ raise ValueError("Circular reference detected")
+ markers[markerid] = lst
+ buf = '['
+ if _indent is not None:
+ _current_indent_level += 1
+ newline_indent = '\n' + (' ' * (_indent * _current_indent_level))
+ separator = _item_separator + newline_indent
+ buf += newline_indent
+ else:
+ newline_indent = None
+ separator = _item_separator
+ first = True
+ for value in lst:
+ if first:
+ first = False
+ else:
+ buf = separator
+ if isinstance(value, basestring):
+ yield buf + _encoder(value)
+ elif value is None:
+ yield buf + 'null'
+ elif value is True:
+ yield buf + 'true'
+ elif value is False:
+ yield buf + 'false'
+ elif isinstance(value, (int, long)):
+ yield buf + str(value)
+ elif isinstance(value, float):
+ yield buf + _floatstr(value)
+ else:
+ yield buf
+ if isinstance(value, (list, tuple)):
+ chunks = _iterencode_list(value, _current_indent_level)
+ elif isinstance(value, dict):
+ chunks = _iterencode_dict(value, _current_indent_level)
+ else:
+ chunks = _iterencode(value, _current_indent_level)
+ for chunk in chunks:
+ yield chunk
+ if newline_indent is not None:
+ _current_indent_level -= 1
+ yield '\n' + (' ' * (_indent * _current_indent_level))
+ yield ']'
+ if markers is not None:
+ del markers[markerid]
+
+ def _iterencode_dict(dct, _current_indent_level):
+ if not dct:
+ yield '{}'
+ return
+ if markers is not None:
+ markerid = id(dct)
+ if markerid in markers:
+ raise ValueError("Circular reference detected")
+ markers[markerid] = dct
+ yield '{'
+ if _indent is not None:
+ _current_indent_level += 1
+ newline_indent = '\n' + (' ' * (_indent * _current_indent_level))
+ item_separator = _item_separator + newline_indent
+ yield newline_indent
+ else:
+ newline_indent = None
+ item_separator = _item_separator
+ first = True
+ if _sort_keys:
+ items = sorted(dct.items(), key=lambda kv: kv[0])
+ else:
+ items = dct.iteritems()
+ for key, value in items:
+ if isinstance(key, basestring):
+ pass
+ # JavaScript is weakly typed for these, so it makes sense to
+ # also allow them. Many encoders seem to do something like this.
+ elif isinstance(key, float):
+ key = _floatstr(key)
+ elif key is True:
+ key = 'true'
+ elif key is False:
+ key = 'false'
+ elif key is None:
+ key = 'null'
+ elif isinstance(key, (int, long)):
+ key = str(key)
+ elif _skipkeys:
+ continue
+ else:
+ raise TypeError("key " + repr(key) + " is not a string")
+ if first:
+ first = False
+ else:
+ yield item_separator
+ yield _encoder(key)
+ yield _key_separator
+ if isinstance(value, basestring):
+ yield _encoder(value)
+ elif value is None:
+ yield 'null'
+ elif value is True:
+ yield 'true'
+ elif value is False:
+ yield 'false'
+ elif isinstance(value, (int, long)):
+ yield str(value)
+ elif isinstance(value, float):
+ yield _floatstr(value)
+ else:
+ if isinstance(value, (list, tuple)):
+ chunks = _iterencode_list(value, _current_indent_level)
+ elif isinstance(value, dict):
+ chunks = _iterencode_dict(value, _current_indent_level)
+ else:
+ chunks = _iterencode(value, _current_indent_level)
+ for chunk in chunks:
+ yield chunk
+ if newline_indent is not None:
+ _current_indent_level -= 1
+ yield '\n' + (' ' * (_indent * _current_indent_level))
+ yield '}'
+ if markers is not None:
+ del markers[markerid]
+
+ def _iterencode(o, _current_indent_level):
+ if isinstance(o, basestring):
+ yield _encoder(o)
+ elif o is None:
+ yield 'null'
+ elif o is True:
+ yield 'true'
+ elif o is False:
+ yield 'false'
+ elif isinstance(o, (int, long)):
+ yield str(o)
+ elif isinstance(o, float):
+ yield _floatstr(o)
+ elif isinstance(o, (list, tuple)):
+ for chunk in _iterencode_list(o, _current_indent_level):
+ yield chunk
+ elif isinstance(o, dict):
+ for chunk in _iterencode_dict(o, _current_indent_level):
+ yield chunk
+ else:
+ if markers is not None:
+ markerid = id(o)
+ if markerid in markers:
+ raise ValueError("Circular reference detected")
+ markers[markerid] = o
+ o = _default(o)
+ for chunk in _iterencode(o, _current_indent_level):
+ yield chunk
+ if markers is not None:
+ del markers[markerid]
+
+ return _iterencode
diff --git a/talk/pycon2012/tutorial/bench/json/scanner.py b/talk/pycon2012/tutorial/bench/json/scanner.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/scanner.py
@@ -0,0 +1,67 @@
+"""JSON token scanner
+"""
+import re
+try:
+ from _json import make_scanner as c_make_scanner
+except ImportError:
+ c_make_scanner = None
+
+__all__ = ['make_scanner']
+
+NUMBER_RE = re.compile(
+ r'(-?(?:0|[1-9]\d*))(\.\d+)?([eE][-+]?\d+)?',
+ (re.VERBOSE | re.MULTILINE | re.DOTALL))
+
+def py_make_scanner(context):
+ parse_object = context.parse_object
+ parse_array = context.parse_array
+ parse_string = context.parse_string
+ match_number = NUMBER_RE.match
+ encoding = context.encoding
+ strict = context.strict
+ parse_float = context.parse_float
+ parse_int = context.parse_int
+ parse_constant = context.parse_constant
+ object_hook = context.object_hook
+ object_pairs_hook = context.object_pairs_hook
+
+ def _scan_once(string, idx):
+ try:
+ nextchar = string[idx]
+ except IndexError:
+ raise StopIteration
+
+ if nextchar == '"':
+ return parse_string(string, idx + 1, encoding, strict)
+ elif nextchar == '{':
+ return parse_object((string, idx + 1), encoding, strict,
+ _scan_once, object_hook, object_pairs_hook)
+ elif nextchar == '[':
+ return parse_array((string, idx + 1), _scan_once)
+ elif nextchar == 'n' and string[idx:idx + 4] == 'null':
+ return None, idx + 4
+ elif nextchar == 't' and string[idx:idx + 4] == 'true':
+ return True, idx + 4
+ elif nextchar == 'f' and string[idx:idx + 5] == 'false':
+ return False, idx + 5
+
+ m = match_number(string, idx)
+ if m is not None:
+ integer, frac, exp = m.groups()
+ if frac or exp:
+ res = parse_float(integer + (frac or '') + (exp or ''))
+ else:
+ res = parse_int(integer)
+ return res, m.end()
+ elif nextchar == 'N' and string[idx:idx + 3] == 'NaN':
+ return parse_constant('NaN'), idx + 3
+ elif nextchar == 'I' and string[idx:idx + 8] == 'Infinity':
+ return parse_constant('Infinity'), idx + 8
+ elif nextchar == '-' and string[idx:idx + 9] == '-Infinity':
+ return parse_constant('-Infinity'), idx + 9
+ else:
+ raise StopIteration
+
+ return _scan_once
+
+make_scanner = c_make_scanner or py_make_scanner
diff --git a/talk/pycon2012/tutorial/bench/json/tests/__init__.py b/talk/pycon2012/tutorial/bench/json/tests/__init__.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/__init__.py
@@ -0,0 +1,73 @@
+import os
+import sys
+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)
+
+ at 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__)
+
+def test_suite():
+ suite = additional_tests()
+ loader = unittest.TestLoader()
+ for fn in os.listdir(here):
+ if fn.startswith("test") and fn.endswith(".py"):
+ modname = "json.tests." + fn[:-3]
+ __import__(modname)
+ module = sys.modules[modname]
+ suite.addTests(loader.loadTestsFromModule(module))
+ return suite
+
+def additional_tests():
+ 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():
+ suite = test_suite()
+ runner = unittest.TextTestRunner()
+ runner.run(suite)
+
+if __name__ == '__main__':
+ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+ main()
diff --git a/talk/pycon2012/tutorial/bench/json/tests/test_check_circular.py b/talk/pycon2012/tutorial/bench/json/tests/test_check_circular.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/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/talk/pycon2012/tutorial/bench/json/tests/test_decode.py b/talk/pycon2012/tutorial/bench/json/tests/test_decode.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_decode.py
@@ -0,0 +1,50 @@
+import decimal
+from StringIO import StringIO
+from collections import OrderedDict
+from json.tests import PyTest, CTest
+
+
+class TestDecode(object):
+ def test_decimal(self):
+ 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 = 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/talk/pycon2012/tutorial/bench/json/tests/test_default.py b/talk/pycon2012/tutorial/bench/json/tests/test_default.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_default.py
@@ -0,0 +1,12 @@
+from json.tests import PyTest, CTest
+
+
+class TestDefault(object):
+ def test_default(self):
+ self.assertEqual(
+ self.dumps(type, default=repr),
+ self.dumps(repr(type)))
+
+
+class TestPyDefault(TestDefault, PyTest): pass
+class TestCDefault(TestDefault, CTest): pass
diff --git a/talk/pycon2012/tutorial/bench/json/tests/test_dump.py b/talk/pycon2012/tutorial/bench/json/tests/test_dump.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_dump.py
@@ -0,0 +1,23 @@
+from cStringIO import StringIO
+from json.tests import PyTest, CTest
+
+
+class TestDump(object):
+ def test_dump(self):
+ sio = StringIO()
+ self.json.dump({}, sio)
+ self.assertEqual(sio.getvalue(), '{}')
+
+ def test_dumps(self):
+ 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/talk/pycon2012/tutorial/bench/json/tests/test_encode_basestring_ascii.py b/talk/pycon2012/tutorial/bench/json/tests/test_encode_basestring_ascii.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_encode_basestring_ascii.py
@@ -0,0 +1,41 @@
+from collections import OrderedDict
+from json.tests import PyTest, CTest
+
+
+CASES = [
+ (u'/\\"\ucafe\ubabe\uab98\ufcde\ubcda\uef4a\x08\x0c\n\r\t`1~!@#$%^&*()_+-=[]{}|;:\',./<>?', '"/\\\\\\"\\ucafe\\ubabe\\uab98\\ufcde\\ubcda\\uef4a\\b\\f\\n\\r\\t`1~!@#$%^&*()_+-=[]{}|;:\',./<>?"'),
+ (u'\u0123\u4567\u89ab\ucdef\uabcd\uef4a', '"\\u0123\\u4567\\u89ab\\ucdef\\uabcd\\uef4a"'),
+ (u'controls', '"controls"'),
+ (u'\x08\x0c\n\r\t', '"\\b\\f\\n\\r\\t"'),
+ (u'{"object with 1 member":["array with 1 element"]}', '"{\\"object with 1 member\\":[\\"array with 1 element\\"]}"'),
+ (u' s p a c e d ', '" s p a c e d "'),
+ (u'\U0001d120', '"\\ud834\\udd20"'),
+ (u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
+ ('\xce\xb1\xce\xa9', '"\\u03b1\\u03a9"'),
+ (u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
+ ('\xce\xb1\xce\xa9', '"\\u03b1\\u03a9"'),
+ (u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
+ (u'\u03b1\u03a9', '"\\u03b1\\u03a9"'),
+ (u"`1~!@#$%^&*()_+-={':[,]}|;.</>?", '"`1~!@#$%^&*()_+-={\':[,]}|;.</>?"'),
+ (u'\x08\x0c\n\r\t', '"\\b\\f\\n\\r\\t"'),
+ (u'\u0123\u4567\u89ab\ucdef\uabcd\uef4a', '"\\u0123\\u4567\\u89ab\\ucdef\\uabcd\\uef4a"'),
+]
+
+class TestEncodeBasestringAscii(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_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}')
+
+
+class TestPyEncodeBasestringAscii(TestEncodeBasestringAscii, PyTest): pass
+class TestCEncodeBasestringAscii(TestEncodeBasestringAscii, CTest): pass
diff --git a/talk/pycon2012/tutorial/bench/json/tests/test_fail.py b/talk/pycon2012/tutorial/bench/json/tests/test_fail.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_fail.py
@@ -0,0 +1,87 @@
+from json.tests import PyTest, CTest
+
+# Fri Dec 30 18:57:26 2005
+JSONDOCS = [
+ # http://json.org/JSON_checker/test/fail1.json
+ '"A JSON payload should be an object or array, not a string."',
+ # http://json.org/JSON_checker/test/fail2.json
+ '["Unclosed array"',
+ # http://json.org/JSON_checker/test/fail3.json
+ '{unquoted_key: "keys must be quoted}',
+ # http://json.org/JSON_checker/test/fail4.json
+ '["extra comma",]',
+ # http://json.org/JSON_checker/test/fail5.json
+ '["double extra comma",,]',
+ # http://json.org/JSON_checker/test/fail6.json
+ '[ , "<-- missing value"]',
+ # http://json.org/JSON_checker/test/fail7.json
+ '["Comma after the close"],',
+ # http://json.org/JSON_checker/test/fail8.json
+ '["Extra close"]]',
+ # http://json.org/JSON_checker/test/fail9.json
+ '{"Extra comma": true,}',
+ # http://json.org/JSON_checker/test/fail10.json
+ '{"Extra value after close": true} "misplaced quoted value"',
+ # http://json.org/JSON_checker/test/fail11.json
+ '{"Illegal expression": 1 + 2}',
+ # http://json.org/JSON_checker/test/fail12.json
+ '{"Illegal invocation": alert()}',
+ # http://json.org/JSON_checker/test/fail13.json
+ '{"Numbers cannot have leading zeroes": 013}',
+ # http://json.org/JSON_checker/test/fail14.json
+ '{"Numbers cannot be hex": 0x14}',
+ # http://json.org/JSON_checker/test/fail15.json
+ '["Illegal backslash escape: \\x15"]',
+ # http://json.org/JSON_checker/test/fail16.json
+ '["Illegal backslash escape: \\\'"]',
+ # http://json.org/JSON_checker/test/fail17.json
+ '["Illegal backslash escape: \\017"]',
+ # http://json.org/JSON_checker/test/fail18.json
+ '[[[[[[[[[[[[[[[[[[[["Too deep"]]]]]]]]]]]]]]]]]]]]',
+ # http://json.org/JSON_checker/test/fail19.json
+ '{"Missing colon" null}',
+ # http://json.org/JSON_checker/test/fail20.json
+ '{"Double colon":: null}',
+ # http://json.org/JSON_checker/test/fail21.json
+ '{"Comma instead of colon", null}',
+ # http://json.org/JSON_checker/test/fail22.json
+ '["Colon instead of comma": false]',
+ # http://json.org/JSON_checker/test/fail23.json
+ '["Bad value", truth]',
+ # http://json.org/JSON_checker/test/fail24.json
+ "['single quote']",
+ # http://code.google.com/p/simplejson/issues/detail?id=3
+ u'["A\u001FZ control characters in string"]',
+]
+
+SKIPS = {
+ 1: "why not have a string payload?",
+ 18: "spec doesn't specify any nesting limitations",
+}
+
+class TestFail(object):
+ def test_failures(self):
+ for idx, doc in enumerate(JSONDOCS):
+ idx = idx + 1
+ if idx in SKIPS:
+ self.loads(doc)
+ continue
+ try:
+ self.loads(doc)
+ except ValueError:
+ pass
+ else:
+ 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/talk/pycon2012/tutorial/bench/json/tests/test_float.py b/talk/pycon2012/tutorial/bench/json/tests/test_float.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_float.py
@@ -0,0 +1,22 @@
+import math
+from json.tests import PyTest, CTest
+
+
+class TestFloat(object):
+ def test_floats(self):
+ 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/talk/pycon2012/tutorial/bench/json/tests/test_indent.py b/talk/pycon2012/tutorial/bench/json/tests/test_indent.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_indent.py
@@ -0,0 +1,60 @@
+import textwrap
+from StringIO import StringIO
+from json.tests import PyTest, CTest
+
+
+class TestIndent(object):
+ def test_indent(self):
+ h = [['blorpie'], ['whoops'], [], 'd-shtaeou', 'd-nthiouh', 'i-vhbjkhnth',
+ {'nifty': 87}, {'field': 'yes', 'morefield': False} ]
+
+ expect = textwrap.dedent("""\
+ [
+ [
+ "blorpie"
+ ],
+ [
+ "whoops"
+ ],
+ [],
+ "d-shtaeou",
+ "d-nthiouh",
+ "i-vhbjkhnth",
+ {
+ "nifty": 87
+ },
+ {
+ "field": "yes",
+ "morefield": false
+ }
+ ]""")
+
+
+ d1 = 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}')
+
+
+class TestPyIndent(TestIndent, PyTest): pass
+class TestCIndent(TestIndent, CTest): pass
diff --git a/talk/pycon2012/tutorial/bench/json/tests/test_pass1.py b/talk/pycon2012/tutorial/bench/json/tests/test_pass1.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_pass1.py
@@ -0,0 +1,79 @@
+from json.tests import PyTest, CTest
+
+
+# from http://json.org/JSON_checker/test/pass1.json
+JSON = r'''
+[
+ "JSON Test Pattern pass1",
+ {"object with 1 member":["array with 1 element"]},
+ {},
+ [],
+ -42,
+ true,
+ false,
+ null,
+ {
+ "integer": 1234567890,
+ "real": -9876.543210,
+ "e": 0.123456789e-12,
+ "E": 1.234567890E+34,
+ "": 23456789012E666,
+ "zero": 0,
+ "one": 1,
+ "space": " ",
+ "quote": "\"",
+ "backslash": "\\",
+ "controls": "\b\f\n\r\t",
+ "slash": "/ & \/",
+ "alpha": "abcdefghijklmnopqrstuvwyz",
+ "ALPHA": "ABCDEFGHIJKLMNOPQRSTUVWYZ",
+ "digit": "0123456789",
+ "special": "`1~!@#$%^&*()_+-={':[,]}|;.</>?",
+ "hex": "\u0123\u4567\u89AB\uCDEF\uabcd\uef4A",
+ "true": true,
+ "false": false,
+ "null": null,
+ "array":[ ],
+ "object":{ },
+ "address": "50 St. James Street",
+ "url": "http://www.JSON.org/",
+ "comment": "// /* <!-- --",
+ "# -- --> */": " ",
+ " s p a c e d " :[1,2 , 3
+
+,
+
+4 , 5 , 6 ,7 ],
+ "compact": [1,2,3,4,5,6,7],
+ "jsontext": "{\"object with 1 member\":[\"array with 1 element\"]}",
+ "quotes": "" \u0022 %22 0x22 034 "",
+ "\/\\\"\uCAFE\uBABE\uAB98\uFCDE\ubcda\uef4A\b\f\n\r\t`1~!@#$%^&*()_+-=[]{}|;:',./<>?"
+: "A key can be any string"
+ },
+ 0.5 ,98.6
+,
+99.44
+,
+
+1066
+
+
+,"rosebud"]
+'''
+
+class TestPass1(object):
+ def test_parse(self):
+ # test in/out equivalence and parsing
+ res = self.loads(JSON)
+ out = self.dumps(res)
+ self.assertEqual(res, self.loads(out))
+ try:
+ 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/talk/pycon2012/tutorial/bench/json/tests/test_pass2.py b/talk/pycon2012/tutorial/bench/json/tests/test_pass2.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_pass2.py
@@ -0,0 +1,18 @@
+from json.tests import PyTest, CTest
+
+
+# from http://json.org/JSON_checker/test/pass2.json
+JSON = r'''
+[[[[[[[[[[[[[[[[[[["Not too deep"]]]]]]]]]]]]]]]]]]]
+'''
+
+class TestPass2(object):
+ def test_parse(self):
+ # test in/out equivalence and parsing
+ 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/talk/pycon2012/tutorial/bench/json/tests/test_pass3.py b/talk/pycon2012/tutorial/bench/json/tests/test_pass3.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_pass3.py
@@ -0,0 +1,24 @@
+from json.tests import PyTest, CTest
+
+
+# from http://json.org/JSON_checker/test/pass3.json
+JSON = r'''
+{
+ "JSON Test Pattern pass3": {
+ "The outermost value": "must be an object or array.",
+ "In this test": "It is an object."
+ }
+}
+'''
+
+
+class TestPass3(object):
+ def test_parse(self):
+ # test in/out equivalence and parsing
+ 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/talk/pycon2012/tutorial/bench/json/tests/test_recursion.py b/talk/pycon2012/tutorial/bench/json/tests/test_recursion.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_recursion.py
@@ -0,0 +1,108 @@
+from json.tests import PyTest, CTest
+
+
+class JSONTestObject:
+ pass
+
+
+class TestRecursion(object):
+ def test_listrecursion(self):
+ x = []
+ x.append(x)
+ try:
+ self.dumps(x)
+ except ValueError:
+ pass
+ else:
+ self.fail("didn't raise ValueError on list recursion")
+ x = []
+ y = [x]
+ x.append(y)
+ try:
+ self.dumps(x)
+ except ValueError:
+ pass
+ else:
+ self.fail("didn't raise ValueError on alternating list recursion")
+ y = []
+ x = [y, y]
+ # ensure that the marker is cleared
+ self.dumps(x)
+
+ def test_dictrecursion(self):
+ x = {}
+ x["test"] = x
+ try:
+ self.dumps(x)
+ except ValueError:
+ pass
+ else:
+ self.fail("didn't raise ValueError on dict recursion")
+ x = {}
+ y = {"a": x, "b": x}
+ # ensure that the marker is cleared
+ 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.assertEqual(enc.encode(JSONTestObject), '"JSONTestObject"')
+ enc.recurse = True
+ try:
+ enc.encode(JSONTestObject)
+ except ValueError:
+ 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/talk/pycon2012/tutorial/bench/json/tests/test_scanstring.py b/talk/pycon2012/tutorial/bench/json/tests/test_scanstring.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_scanstring.py
@@ -0,0 +1,109 @@
+import sys
+from json.tests import PyTest, CTest
+
+
+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.assertEqual(
+ scanstring(u'"z\U0001d120x"', 1, None, True),
+ (u'z\U0001d120x', 6))
+ else:
+ self.assertEqual(
+ scanstring(u'"z\U0001d120x"', 1, None, True),
+ (u'z\U0001d120x', 5))
+
+ self.assertEqual(
+ scanstring('"\\u007b"', 1, None, True),
+ (u'{', 8))
+
+ 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.assertEqual(
+ scanstring('["Unclosed array"', 2, None, True),
+ (u'Unclosed array', 17))
+
+ self.assertEqual(
+ scanstring('["extra comma",]', 2, None, True),
+ (u'extra comma', 14))
+
+ self.assertEqual(
+ scanstring('["double extra comma",,]', 2, None, True),
+ (u'double extra comma', 21))
+
+ self.assertEqual(
+ scanstring('["Comma after the close"],', 2, None, True),
+ (u'Comma after the close', 24))
+
+ self.assertEqual(
+ scanstring('["Extra close"]]', 2, None, True),
+ (u'Extra close', 14))
+
+ self.assertEqual(
+ scanstring('{"Extra comma": true,}', 2, None, True),
+ (u'Extra comma', 14))
+
+ self.assertEqual(
+ scanstring('{"Extra value after close": true} "misplaced quoted value"', 2, None, True),
+ (u'Extra value after close', 26))
+
+ self.assertEqual(
+ scanstring('{"Illegal expression": 1 + 2}', 2, None, True),
+ (u'Illegal expression', 21))
+
+ self.assertEqual(
+ scanstring('{"Illegal invocation": alert()}', 2, None, True),
+ (u'Illegal invocation', 21))
+
+ self.assertEqual(
+ scanstring('{"Numbers cannot have leading zeroes": 013}', 2, None, True),
+ (u'Numbers cannot have leading zeroes', 37))
+
+ self.assertEqual(
+ scanstring('{"Numbers cannot be hex": 0x14}', 2, None, True),
+ (u'Numbers cannot be hex', 24))
+
+ self.assertEqual(
+ scanstring('[[[[[[[[[[[[[[[[[[[["Too deep"]]]]]]]]]]]]]]]]]]]]', 21, None, True),
+ (u'Too deep', 30))
+
+ self.assertEqual(
+ scanstring('{"Missing colon" null}', 2, None, True),
+ (u'Missing colon', 16))
+
+ self.assertEqual(
+ scanstring('{"Double colon":: null}', 2, None, True),
+ (u'Double colon', 15))
+
+ self.assertEqual(
+ scanstring('{"Comma instead of colon", null}', 2, None, True),
+ (u'Comma instead of colon', 25))
+
+ self.assertEqual(
+ scanstring('["Colon instead of comma": false]', 2, None, True),
+ (u'Colon instead of comma', 25))
+
+ self.assertEqual(
+ scanstring('["Bad value", truth]', 2, None, True),
+ (u'Bad value', 12))
+
+ def test_issue3623(self):
+ self.assertRaises(ValueError, self.json.decoder.scanstring, b"xxx", 1,
+ "xxx")
+ self.assertRaises(UnicodeDecodeError,
+ 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/talk/pycon2012/tutorial/bench/json/tests/test_separators.py b/talk/pycon2012/tutorial/bench/json/tests/test_separators.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_separators.py
@@ -0,0 +1,44 @@
+import textwrap
+from json.tests import PyTest, CTest
+
+
+class TestSeparators(object):
+ def test_separators(self):
+ h = [['blorpie'], ['whoops'], [], 'd-shtaeou', 'd-nthiouh', 'i-vhbjkhnth',
+ {'nifty': 87}, {'field': 'yes', 'morefield': False} ]
+
+ expect = textwrap.dedent("""\
+ [
+ [
+ "blorpie"
+ ] ,
+ [
+ "whoops"
+ ] ,
+ [] ,
+ "d-shtaeou" ,
+ "d-nthiouh" ,
+ "i-vhbjkhnth" ,
+ {
+ "nifty" : 87
+ } ,
+ {
+ "field" : "yes" ,
+ "morefield" : false
+ }
+ ]""")
+
+
+ d1 = 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)
+
+
+class TestPySeparators(TestSeparators, PyTest): pass
+class TestCSeparators(TestSeparators, CTest): pass
diff --git a/talk/pycon2012/tutorial/bench/json/tests/test_speedups.py b/talk/pycon2012/tutorial/bench/json/tests/test_speedups.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_speedups.py
@@ -0,0 +1,23 @@
+from json.tests import CTest
+
+
+class TestSpeedups(CTest):
+ def test_scanstring(self):
+ 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.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/talk/pycon2012/tutorial/bench/json/tests/test_unicode.py b/talk/pycon2012/tutorial/bench/json/tests/test_unicode.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tests/test_unicode.py
@@ -0,0 +1,85 @@
+from collections import OrderedDict
+from json.tests import PyTest, CTest
+
+
+class TestUnicode(object):
+ def test_encoding1(self):
+ 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.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 = 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 = 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 = 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 = 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 = self.dumps([u], ensure_ascii=False)
+ self.assertEqual(j, u'["{0}"]'.format(u))
+
+ def test_big_unicode_encode(self):
+ u = 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.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)
+ 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/talk/pycon2012/tutorial/bench/json/tool.py b/talk/pycon2012/tutorial/bench/json/tool.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json/tool.py
@@ -0,0 +1,37 @@
+r"""Command-line tool to validate and pretty-print JSON
+
+Usage::
+
+ $ echo '{"json":"obj"}' | python -m json.tool
+ {
+ "json": "obj"
+ }
+ $ echo '{ 1.2:3.4}' | python -m json.tool
+ Expecting property name: line 1 column 2 (char 2)
+
+"""
+import sys
+import json
+
+def main():
+ if len(sys.argv) == 1:
+ infile = sys.stdin
+ outfile = sys.stdout
+ elif len(sys.argv) == 2:
+ infile = open(sys.argv[1], 'rb')
+ outfile = sys.stdout
+ elif len(sys.argv) == 3:
+ infile = open(sys.argv[1], 'rb')
+ outfile = open(sys.argv[2], 'wb')
+ else:
+ raise SystemExit(sys.argv[0] + " [infile [outfile]]")
+ try:
+ obj = json.load(infile)
+ except ValueError, e:
+ raise SystemExit(e)
+ json.dump(obj, outfile, sort_keys=True, indent=4)
+ outfile.write('\n')
+
+
+if __name__ == '__main__':
+ main()
diff --git a/talk/pycon2012/tutorial/bench/json_bench.py b/talk/pycon2012/tutorial/bench/json_bench.py
new file mode 100644
--- /dev/null
+++ b/talk/pycon2012/tutorial/bench/json_bench.py
@@ -0,0 +1,27 @@
+import time
+import json
+
+# execution runtime per test case
+TARGET_RUNTIME = 10
+
+EMPTY = ({}, 200000)
+SIMPLE = ({'key1': 0, 'key2': True, 'key3': 'value', 'key4': 'foo', 'key5': 'string'}, 100000)
+NESTED = ({'key1': 0, 'key2': SIMPLE[0], 'key3': 'value', 'key4': SIMPLE[0], 'key5': SIMPLE[0], u'key': u'\u0105\u0107\u017c'}, 100000)
+HUGE = ([NESTED[0]] * 1000, 100)
+
+cases = ['EMPTY', 'SIMPLE', 'NESTED', 'HUGE']
+
+def main(n):
+ l = []
+ for i in range(n):
+ t0 = time.time()
+ for case in cases:
+ data, count = globals()[case]
+ for i in range(count):
+ json.dumps(data)
+ print time.time() - t0
+ l.append(time.time() - t0)
+ return l
+
+if __name__ == '__main__':
+ main(1)
More information about the pypy-commit
mailing list