diff options
Diffstat (limited to 'simplejson/decoder.py')
| -rw-r--r-- | simplejson/decoder.py | 354 |
1 files changed, 354 insertions, 0 deletions
diff --git a/simplejson/decoder.py b/simplejson/decoder.py new file mode 100644 index 0000000..b769ea4 --- /dev/null +++ b/simplejson/decoder.py @@ -0,0 +1,354 @@ +"""Implementation of JSONDecoder +""" +import re +import sys +import struct + +from simplejson.scanner import make_scanner +try: + from simplejson._speedups 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 _speedups + 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, end), encoding, strict, scan_once, object_hook, _w=WHITESPACE.match, _ws=WHITESPACE_STR): + pairs = {} + # 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 == '}': + 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[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_hook is not None: + pairs = object_hook(pairs) + return pairs, end + +def JSONArray((s, end), scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR): + 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): + """``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). + + ``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. + + """ + self.encoding = encoding + self.object_hook = object_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 = 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 |