summaryrefslogtreecommitdiffstats
path: root/google_appengine/lib/django/django/utils/simplejson/decoder.py
blob: 66f68a200b0c2c6b3a65ac54e4fa6f2487451465 (plain) (blame)
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
"""
Implementation of JSONDecoder
"""
import re

from django.utils.simplejson.scanner import Scanner, pattern

FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL

def _floatconstants():
    import struct
    import sys
    _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):
    lineno, colno = linecol(doc, pos)
    if end is None:
        return '%s: line %d column %d (char %d)' % (msg, lineno, colno, pos)
    endlineno, endcolno = linecol(doc, end)
    return '%s: line %d column %d - line %d column %d (char %d - %d)' % (
        msg, lineno, colno, endlineno, endcolno, pos, end)

_CONSTANTS = {
    '-Infinity': NegInf,
    'Infinity': PosInf,
    'NaN': NaN,
    'true': True,
    'false': False,
    'null': None,
}

def JSONConstant(match, context, c=_CONSTANTS):
    return c[match.group(0)], None
pattern('(-?Infinity|NaN|true|false|null)')(JSONConstant)

def JSONNumber(match, context):
    match = JSONNumber.regex.match(match.string, *match.span())
    integer, frac, exp = match.groups()
    if frac or exp:
        res = float(integer + (frac or '') + (exp or ''))
    else:
        res = int(integer)
    return res, None
pattern(r'(-?(?:0|[1-9]\d*))(\.\d+)?([eE][-+]?\d+)?')(JSONNumber)

STRINGCHUNK = re.compile(r'(.*?)(["\\])', 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 scanstring(s, end, encoding=None, _b=BACKSLASH, _m=STRINGCHUNK.match):
    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()
        if content:
            if not isinstance(content, unicode):
                content = unicode(content, encoding)
            _append(content)
        if terminator == '"':
            break
        try:
            esc = s[end]
        except IndexError:
            raise ValueError(
                errmsg("Unterminated string starting at", s, begin))
        if esc != 'u':
            try:
                m = _b[esc]
            except KeyError:
                raise ValueError(
                    errmsg("Invalid \\escape: %r" % (esc,), s, end))
            end += 1
        else:
            esc = s[end + 1:end + 5]
            try:
                m = unichr(int(esc, 16))
                if len(esc) != 4 or not esc.isalnum():
                    raise ValueError
            except ValueError:
                raise ValueError(errmsg("Invalid \\uXXXX escape", s, end))
            end += 5
        _append(m)
    return u''.join(chunks), end

def JSONString(match, context):
    encoding = getattr(context, 'encoding', None)
    return scanstring(match.string, match.end(), encoding)
pattern(r'"')(JSONString)

WHITESPACE = re.compile(r'\s*', FLAGS)

def JSONObject(match, context, _w=WHITESPACE.match):
    pairs = {}
    s = match.string
    end = _w(s, match.end()).end()
    nextchar = s[end:end + 1]
    # trivial empty object
    if nextchar == '}':
        return pairs, end + 1
    if nextchar != '"':
        raise ValueError(errmsg("Expecting property name", s, end))
    end += 1
    encoding = getattr(context, 'encoding', None)
    iterscan = JSONScanner.iterscan
    while True:
        key, end = scanstring(s, end, encoding)
        end = _w(s, end).end()
        if s[end:end + 1] != ':':
            raise ValueError(errmsg("Expecting : delimiter", s, end))
        end = _w(s, end + 1).end()
        try:
            value, end = iterscan(s, idx=end, context=context).next()
        except StopIteration:
            raise ValueError(errmsg("Expecting object", s, end))
        pairs[key] = value
        end = _w(s, end).end()
        nextchar = s[end:end + 1]
        end += 1
        if nextchar == '}':
            break
        if nextchar != ',':
            raise ValueError(errmsg("Expecting , delimiter", s, end - 1))
        end = _w(s, end).end()
        nextchar = s[end:end + 1]
        end += 1
        if nextchar != '"':
            raise ValueError(errmsg("Expecting property name", s, end - 1))
    object_hook = getattr(context, 'object_hook', None)
    if object_hook is not None:
        pairs = object_hook(pairs)
    return pairs, end
pattern(r'{')(JSONObject)
            
def JSONArray(match, context, _w=WHITESPACE.match):
    values = []
    s = match.string
    end = _w(s, match.end()).end()
    # look-ahead for trivial empty array
    nextchar = s[end:end + 1]
    if nextchar == ']':
        return values, end + 1
    iterscan = JSONScanner.iterscan
    while True:
        try:
            value, end = iterscan(s, idx=end, context=context).next()
        except StopIteration:
            raise ValueError(errmsg("Expecting object", s, end))
        values.append(value)
        end = _w(s, end).end()
        nextchar = s[end:end + 1]
        end += 1
        if nextchar == ']':
            break
        if nextchar != ',':
            raise ValueError(errmsg("Expecting , delimiter", s, end))
        end = _w(s, end).end()
    return values, end
pattern(r'\[')(JSONArray)
 
ANYTHING = [
    JSONObject,
    JSONArray,
    JSONString,
    JSONConstant,
    JSONNumber,
]

JSONScanner = Scanner(ANYTHING)

class JSONDecoder(object):
    """
    Simple JSON <http://json.org> decoder

    Performs the following translations in decoding:
    
    +---------------+-------------------+
    | 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.
    """

    _scanner = Scanner(ANYTHING)
    __all__ = ['__init__', 'decode', 'raw_decode']

    def __init__(self, encoding=None, object_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).
        """
        self.encoding = encoding
        self.object_hook = object_hook

    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, **kw):
        """
        Decode a JSON document from ``s`` (a ``str`` or ``unicode`` beginning
        with a JSON document) and return a 2-tuple of the Python
        representation and the index in ``s`` where the document ended.

        This can be used to decode a JSON document from a string that may
        have extraneous data at the end.
        """
        kw.setdefault('context', self)
        try:
            obj, end = self._scanner.iterscan(s, **kw).next()
        except StopIteration:
            raise ValueError("No JSON object could be decoded")
        return obj, end

__all__ = ['JSONDecoder']