summaryrefslogtreecommitdiffstats
path: root/third_party/simplejson/encoder.py
blob: d29919a1dd94c194db1cadc64d768b1469e62bf5 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
"""
Implementation of JSONEncoder
"""
import re
try:
    from simplejson import _speedups
except ImportError:
    _speedups = None

ESCAPE = re.compile(r'[\x00-\x19\\"\b\f\n\r\t]')
ESCAPE_ASCII = re.compile(r'([\\"/]|[^\ -~])')
ESCAPE_DCT = {
    # escape all forward slashes to prevent </script> attack
    '/': '\\/',
    '\\': '\\\\',
    '"': '\\"',
    '\b': '\\b',
    '\f': '\\f',
    '\n': '\\n',
    '\r': '\\r',
    '\t': '\\t',
}
for i in range(0x20):
    ESCAPE_DCT.setdefault(chr(i), '\\u%04x' % (i,))

# assume this produces an infinity on all machines (probably not guaranteed)
INFINITY = float('1e66666')

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 o != o:
        text = 'NaN'
    elif o == INFINITY:
        text = 'Infinity'
    elif o == -INFINITY:
        text = '-Infinity'
    else:
        return repr(o)

    if not allow_nan:
        raise ValueError("Out of range float values are not JSON compliant: %r"
            % (o,))

    return text


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 encode_basestring_ascii(s):
    def replace(match):
        s = match.group(0)
        try:
            return ESCAPE_DCT[s]
        except KeyError:
            n = ord(s)
            if n < 0x10000:
                return '\\u%04x' % (n,)
            else:
                # surrogate pair
                n -= 0x10000
                s1 = 0xd800 | ((n >> 10) & 0x3ff)
                s2 = 0xdc00 | (n & 0x3ff)
                return '\\u%04x\\u%04x' % (s1, s2)
    return '"' + str(ESCAPE_ASCII.sub(replace, s)) + '"'
        
try:
    encode_basestring_ascii = _speedups.encode_basestring_ascii
    _need_utf8 = True
except AttributeError:
    _need_utf8 = False

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``).
    """
    __all__ = ['__init__', 'default', 'encode', 'iterencode']
    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'):
        """
        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 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
        self.current_indent_level = 0
        if separators is not None:
            self.item_separator, self.key_separator = separators
        self.encoding = encoding

    def _newline_indent(self):
        return '\n' + (' ' * (self.indent * self.current_indent_level))

    def _iterencode_list(self, lst, markers=None):
        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
        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
        else:
            newline_indent = None
            separator = self.item_separator
        first = True
        for value in lst:
            if first:
                first = False
            else:
                yield separator
            for chunk in self._iterencode(value, markers):
                yield chunk
        if newline_indent is not None:
            self.current_indent_level -= 1
            yield self._newline_indent()
        yield ']'
        if markers is not None:
            del markers[markerid]

    def _iterencode_dict(self, dct, markers=None):
        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 '{'
        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
            yield newline_indent
        else:
            newline_indent = None
            item_separator = self.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]
        else:
            items = dct.iteritems()
        _encoding = self.encoding
        _do_decode = (_encoding is not None
            and not (_need_utf8 and _encoding == 'utf-8'))
        for key, value in items:
            if isinstance(key, str):
                if _do_decode:
                    key = key.decode(_encoding)
            elif isinstance(key, basestring):
                pass
            # JavaScript is weakly typed for these, so it makes sense to
            # also allow them.  Many encoders seem to do something like this.
            elif isinstance(key, float):
                key = floatstr(key, allow_nan)
            elif isinstance(key, (int, long)):
                key = str(key)
            elif key is True:
                key = 'true'
            elif key is False:
                key = 'false'
            elif key is None:
                key = 'null'
            elif self.skipkeys:
                continue
            else:
                raise TypeError("key %r is not a string" % (key,))
            if first:
                first = False
            else:
                yield item_separator
            yield encoder(key)
            yield key_separator
            for chunk in self._iterencode(value, markers):
                yield chunk
        if newline_indent is not None:
            self.current_indent_level -= 1
            yield self._newline_indent()
        yield '}'
        if markers is not None:
            del markers[markerid]

    def _iterencode(self, o, markers=None):
        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 (_need_utf8 and _encoding == 'utf-8')):
                o = o.decode(_encoding)
            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, self.allow_nan)
        elif isinstance(o, (list, tuple)):
            for chunk in self._iterencode_list(o, markers):
                yield chunk
        elif isinstance(o, dict):
            for chunk in self._iterencode_dict(o, markers):
                yield chunk
        else:
            if markers is not None:
                markerid = id(o)
                if markerid in markers:
                    raise ValueError("Circular reference detected")
                markers[markerid] = o
            for chunk in self._iterencode_default(o, markers):
                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("%r is not JSON serializable" % (o,))

    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' and _need_utf8)):
                    o = o.decode(_encoding)
            return encode_basestring_ascii(o)
        # This doesn't pass the iterator directly to ''.join() because it
        # sucks at reporting exceptions.  It's going to do this internally
        # anyway because it uses PySequence_Fast or similar.
        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)

__all__ = ['JSONEncoder']