diff options
Diffstat (limited to 'lib/simplejson/encoder.py')
| -rw-r--r-- | lib/simplejson/encoder.py | 534 |
1 files changed, 534 insertions, 0 deletions
diff --git a/lib/simplejson/encoder.py b/lib/simplejson/encoder.py new file mode 100644 index 000000000..5ec7440f1 --- /dev/null +++ b/lib/simplejson/encoder.py @@ -0,0 +1,534 @@ +"""Implementation of JSONEncoder +""" +import re +from decimal import Decimal + +def _import_speedups(): + try: + from simplejson import _speedups + return _speedups.encode_basestring_ascii, _speedups.make_encoder + except ImportError: + return None, None +c_encode_basestring_ascii, c_make_encoder = _import_speedups() + +from simplejson.decoder import PosInf + +ESCAPE = re.compile(ur'[\x00-\x1f\\"\b\f\n\r\t\u2028\u2029]') +ESCAPE_ASCII = re.compile(r'([\\"]|[^\ -~])') +HAS_UTF8 = re.compile(r'[\x80-\xff]') +ESCAPE_DCT = { + '\\': '\\\\', + '"': '\\"', + '\b': '\\b', + '\f': '\\f', + '\n': '\\n', + '\r': '\\r', + '\t': '\\t', + u'\u2028': '\\u2028', + u'\u2029': '\\u2029', +} +for i in range(0x20): + #ESCAPE_DCT.setdefault(chr(i), '\\u{0:04x}'.format(i)) + ESCAPE_DCT.setdefault(chr(i), '\\u%04x' % (i,)) + +FLOAT_REPR = repr + +def encode_basestring(s): + """Return a 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): + return ESCAPE_DCT[match.group(0)] + return u'"' + ESCAPE.sub(replace, s) + u'"' + + +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, namedtuple | 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, + use_decimal=True, namedtuple_as_object=True, + tuple_as_array=True): + """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 string, then JSON array elements and object members + will be pretty-printed with a newline followed by that string repeated + for each level of nesting. ``None`` (the default) selects the most compact + representation without any newlines. For backwards compatibility with + versions of simplejson earlier than 2.1.0, an integer is also accepted + and is converted to a string with that many spaces. + + 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. + + If use_decimal is true (not the default), ``decimal.Decimal`` will + be supported directly by the encoder. For the inverse, decode JSON + with ``parse_float=decimal.Decimal``. + + If namedtuple_as_object is true (the default), tuple subclasses with + ``_asdict()`` methods will be encoded as JSON objects. + + If tuple_as_array is true (the default), tuple (and subclasses) will + be encoded as JSON arrays. + """ + + self.skipkeys = skipkeys + self.ensure_ascii = ensure_ascii + self.check_circular = check_circular + self.allow_nan = allow_nan + self.sort_keys = sort_keys + self.use_decimal = use_decimal + self.namedtuple_as_object = namedtuple_as_object + self.tuple_as_array = tuple_as_array + if isinstance(indent, (int, long)): + indent = ' ' * indent + self.indent = indent + if separators is not None: + self.item_separator, self.key_separator = separators + elif indent is not None: + self.item_separator = ',' + 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. + + >>> from simplejson import JSONEncoder + >>> 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) + if self.ensure_ascii: + return ''.join(chunks) + else: + return u''.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=PosInf, _neginf=-PosInf): + # 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 + + + key_memo = {} + if (_one_shot and c_make_encoder is not None + and self.indent is None): + _iterencode = c_make_encoder( + markers, self.default, _encoder, self.indent, + self.key_separator, self.item_separator, self.sort_keys, + self.skipkeys, self.allow_nan, key_memo, self.use_decimal, + self.namedtuple_as_object, self.tuple_as_array) + else: + _iterencode = _make_iterencode( + markers, self.default, _encoder, self.indent, floatstr, + self.key_separator, self.item_separator, self.sort_keys, + self.skipkeys, _one_shot, self.use_decimal, + self.namedtuple_as_object, self.tuple_as_array) + try: + return _iterencode(o, 0) + finally: + key_memo.clear() + + +class JSONEncoderForHTML(JSONEncoder): + """An encoder that produces JSON safe to embed in HTML. + + To embed JSON content in, say, a script tag on a web page, the + characters &, < and > should be escaped. They cannot be escaped + with the usual entities (e.g. &) because they are not expanded + within <script> tags. + """ + + def encode(self, o): + # Override JSONEncoder.encode because it has hacks for + # performance that make things more complicated. + chunks = self.iterencode(o, True) + if self.ensure_ascii: + return ''.join(chunks) + else: + return u''.join(chunks) + + def iterencode(self, o, _one_shot=False): + chunks = super(JSONEncoderForHTML, self).iterencode(o, _one_shot) + for chunk in chunks: + chunk = chunk.replace('&', '\\u0026') + chunk = chunk.replace('<', '\\u003c') + chunk = chunk.replace('>', '\\u003e') + yield chunk + + +def _make_iterencode(markers, _default, _encoder, _indent, _floatstr, + _key_separator, _item_separator, _sort_keys, _skipkeys, _one_shot, + _use_decimal, _namedtuple_as_object, _tuple_as_array, + ## HACK: hand-optimized bytecode; turn globals into locals + False=False, + True=True, + ValueError=ValueError, + basestring=basestring, + Decimal=Decimal, + 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) + elif _use_decimal and isinstance(value, Decimal): + yield buf + str(value) + else: + yield buf + if isinstance(value, list): + chunks = _iterencode_list(value, _current_indent_level) + elif (_namedtuple_as_object and isinstance(value, tuple) and + hasattr(value, '_asdict')): + chunks = _iterencode_dict(value._asdict(), + _current_indent_level) + elif _tuple_as_array and isinstance(value, tuple): + chunks = _iterencode_list(value, _current_indent_level) + elif isinstance(value, dict): + chunks = _iterencode_dict(value, _current_indent_level) + else: + chunks = _iterencode(value, _current_indent_level) + for chunk in chunks: + yield chunk + if newline_indent is not None: + _current_indent_level -= 1 + yield '\n' + (_indent * _current_indent_level) + yield ']' + if markers is not None: + del markers[markerid] + + def _iterencode_dict(dct, _current_indent_level): + if not dct: + yield '{}' + return + if markers is not None: + markerid = id(dct) + if markerid in markers: + raise ValueError("Circular reference detected") + markers[markerid] = dct + yield '{' + if _indent is not None: + _current_indent_level += 1 + newline_indent = '\n' + (_indent * _current_indent_level) + item_separator = _item_separator + newline_indent + yield newline_indent + else: + newline_indent = None + item_separator = _item_separator + first = True + if _sort_keys: + items = dct.items() + items.sort(key=lambda kv: kv[0]) + else: + items = dct.iteritems() + for key, value in items: + if isinstance(key, basestring): + pass + # JavaScript is weakly typed for these, so it makes sense to + # also allow them. Many encoders seem to do something like this. + elif isinstance(key, float): + key = _floatstr(key) + elif 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) + elif _use_decimal and isinstance(value, Decimal): + yield str(value) + else: + if isinstance(value, list): + chunks = _iterencode_list(value, _current_indent_level) + elif (_namedtuple_as_object and isinstance(value, tuple) and + hasattr(value, '_asdict')): + chunks = _iterencode_dict(value._asdict(), + _current_indent_level) + elif _tuple_as_array and isinstance(value, 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): + for chunk in _iterencode_list(o, _current_indent_level): + yield chunk + elif (_namedtuple_as_object and isinstance(o, tuple) and + hasattr(o, '_asdict')): + for chunk in _iterencode_dict(o._asdict(), _current_indent_level): + yield chunk + elif (_tuple_as_array and isinstance(o, 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 + elif _use_decimal and isinstance(o, Decimal): + yield str(o) + 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 |