[qooxdoo-commit] SF.net SVN: qooxdoo:[20233] trunk/qooxdoo/tool/pylib/simplejson
Brought to you by:
ecker,
martinwittemann
From: <th...@us...> - 2009-09-29 13:13:17
|
Revision: 20233 http://qooxdoo.svn.sourceforge.net/qooxdoo/?rev=20233&view=rev Author: thron7 Date: 2009-09-29 12:14:34 +0000 (Tue, 29 Sep 2009) Log Message: ----------- upgraded to simplejson 2.0.9 Modified Paths: -------------- trunk/qooxdoo/tool/pylib/simplejson/__init__.py trunk/qooxdoo/tool/pylib/simplejson/decoder.py trunk/qooxdoo/tool/pylib/simplejson/encoder.py trunk/qooxdoo/tool/pylib/simplejson/scanner.py Added Paths: ----------- trunk/qooxdoo/tool/pylib/simplejson/LICENSE.txt trunk/qooxdoo/tool/pylib/simplejson/tool.py Added: trunk/qooxdoo/tool/pylib/simplejson/LICENSE.txt =================================================================== --- trunk/qooxdoo/tool/pylib/simplejson/LICENSE.txt (rev 0) +++ trunk/qooxdoo/tool/pylib/simplejson/LICENSE.txt 2009-09-29 12:14:34 UTC (rev 20233) @@ -0,0 +1,19 @@ +Copyright (c) 2006 Bob Ippolito + +Permission is hereby granted, free of charge, to any person obtaining a copy of +this software and associated documentation files (the "Software"), to deal in +the Software without restriction, including without limitation the rights to +use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies +of the Software, and to permit persons to whom the Software is furnished to do +so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. Property changes on: trunk/qooxdoo/tool/pylib/simplejson/LICENSE.txt ___________________________________________________________________ Added: svn:eol-style + native Modified: trunk/qooxdoo/tool/pylib/simplejson/__init__.py =================================================================== --- trunk/qooxdoo/tool/pylib/simplejson/__init__.py 2009-09-29 09:04:04 UTC (rev 20232) +++ trunk/qooxdoo/tool/pylib/simplejson/__init__.py 2009-09-29 12:14:34 UTC (rev 20233) @@ -1,97 +1,110 @@ -r""" -A simple, fast, extensible JSON encoder and decoder - -JSON (JavaScript Object Notation) <http://json.org> is a subset of +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. -simplejson exposes an API familiar to uses of the standard library -marshal and pickle modules. +:mod:`simplejson` 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 simplejson - >>> simplejson.dumps(['foo', {'bar': ('baz', None, 1.0, 2)}]) + + >>> import simplejson as json + >>> json.dumps(['foo', {'bar': ('baz', None, 1.0, 2)}]) '["foo", {"bar": ["baz", null, 1.0, 2]}]' - >>> print simplejson.dumps("\"foo\bar") + >>> print json.dumps("\"foo\bar") "\"foo\bar" - >>> print simplejson.dumps(u'\u1234') + >>> print json.dumps(u'\u1234') "\u1234" - >>> print simplejson.dumps('\\') + >>> print json.dumps('\\') "\\" - >>> print simplejson.dumps({"c": 0, "b": 0, "a": 0}, sort_keys=True) + >>> print json.dumps({"c": 0, "b": 0, "a": 0}, sort_keys=True) {"a": 0, "b": 0, "c": 0} >>> from StringIO import StringIO >>> io = StringIO() - >>> simplejson.dump(['streaming API'], io) + >>> json.dump(['streaming API'], io) >>> io.getvalue() '["streaming API"]' Compact encoding:: - >>> import simplejson - >>> simplejson.dumps([1,2,3,{'4': 5, '6': 7}], separators=(',',':')) + >>> import simplejson as json + >>> json.dumps([1,2,3,{'4': 5, '6': 7}], separators=(',',':')) '[1,2,3,{"4":5,"6":7}]' Pretty printing:: - >>> import simplejson - >>> print simplejson.dumps({'4': 5, '6': 7}, sort_keys=True, indent=4) + >>> import simplejson as 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, + "4": 5, "6": 7 } Decoding JSON:: - - >>> import simplejson - >>> simplejson.loads('["foo", {"bar":["baz", null, 1.0, 2]}]') - [u'foo', {u'bar': [u'baz', None, 1.0, 2]}] - >>> simplejson.loads('"\\"foo\\bar"') - u'"foo\x08ar' + + >>> import simplejson as 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"]') - >>> simplejson.load(io) - [u'streaming API'] + >>> json.load(io)[0] == 'streaming API' + True Specializing JSON object decoding:: - >>> import simplejson + >>> import simplejson as json >>> def as_complex(dct): ... if '__complex__' in dct: ... return complex(dct['real'], dct['imag']) ... return dct - ... - >>> simplejson.loads('{"__complex__": true, "real": 1, "imag": 2}', + ... + >>> json.loads('{"__complex__": true, "real": 1, "imag": 2}', ... object_hook=as_complex) (1+2j) + >>> import decimal + >>> json.loads('1.1', parse_float=decimal.Decimal) == decimal.Decimal('1.1') + True -Extending JSONEncoder:: - - >>> import simplejson - >>> class ComplexEncoder(simplejson.JSONEncoder): - ... def default(self, obj): - ... if isinstance(obj, complex): - ... return [obj.real, obj.imag] - ... return simplejson.JSONEncoder.default(self, obj) - ... - >>> dumps(2 + 1j, cls=ComplexEncoder) +Specializing JSON object encoding:: + + >>> import simplejson as 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]' - >>> ComplexEncoder().encode(2 + 1j) + >>> json.JSONEncoder(default=encode_complex).encode(2 + 1j) '[2.0, 1.0]' - >>> list(ComplexEncoder().iterencode(2 + 1j)) - ['[', '2.0', ', ', '1.0', ']'] - + >>> ''.join(json.JSONEncoder(default=encode_complex).iterencode(2 + 1j)) + '[2.0, 1.0]' -Note that the JSON produced by this module's default settings -is a subset of YAML, so it may be used as a serializer for that as well. + +Using simplejson.tool from the shell to validate and pretty-print:: + + $ echo '{"json":"obj"}' | python -m simplejson.tool + { + "json": "obj" + } + $ echo '{ 1.2:3.4}' | python -m simplejson.tool + Expecting property name: line 1 column 2 (char 2) """ -__version__ = '1.7.1' +__version__ = '2.0.9' __all__ = [ 'dump', 'dumps', 'load', 'loads', 'JSONDecoder', 'JSONEncoder', ] +__author__ = 'Bob Ippolito <bo...@re...>' + from decoder import JSONDecoder from encoder import JSONEncoder @@ -102,31 +115,31 @@ allow_nan=True, indent=None, separators=None, - encoding='utf-8' + 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', **kw): - """ - Serialize ``obj`` as a JSON formatted stream to ``fp`` (a + 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``) + 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`` + 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 + 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 + 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``). @@ -141,22 +154,27 @@ ``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. + """ # cached encoder - if (skipkeys is False and ensure_ascii is True and - check_circular is True and allow_nan is True and + 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 not kw): + 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, **kw).iterencode(obj) + 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: @@ -165,23 +183,22 @@ def dumps(obj, skipkeys=False, ensure_ascii=True, check_circular=True, allow_nan=True, cls=None, indent=None, separators=None, - encoding='utf-8', **kw): - """ - Serialize ``obj`` to a JSON formatted ``str``. + encoding='utf-8', default=None, **kw): + """Serialize ``obj`` to a JSON formatted ``str``. - If ``skipkeys`` is ``True`` then ``dict`` keys that are not basic types - (``str``, ``unicode``, ``int``, ``long``, ``float``, ``bool``, ``None``) + 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 + 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 + 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 + 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``). @@ -197,29 +214,35 @@ ``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. + """ # cached encoder - if (skipkeys is False and ensure_ascii is True and - check_circular is True and allow_nan is True and + 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 not kw): + 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, + separators=separators, encoding=encoding, default=default, **kw).encode(obj) + _default_decoder = JSONDecoder(encoding=None, object_hook=None) -def load(fp, encoding=None, cls=None, object_hook=None, **kw): - """ - Deserialize ``fp`` (a ``.read()``-supporting file-like object containing + +def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None, + parse_int=None, parse_constant=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 @@ -233,16 +256,20 @@ 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). - + To use a custom ``JSONDecoder`` subclass, specify it with the ``cls`` kwarg. + """ return loads(fp.read(), - encoding=encoding, cls=cls, object_hook=object_hook, **kw) + encoding=encoding, cls=cls, object_hook=object_hook, + parse_float=parse_float, parse_int=parse_int, + parse_constant=parse_constant, **kw) -def loads(s, encoding=None, cls=None, object_hook=None, **kw): - """ - Deserialize ``s`` (a ``str`` or ``unicode`` instance containing a JSON + +def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None, + parse_int=None, parse_constant=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 @@ -255,33 +282,37 @@ ``object_hook`` will be used instead of the ``dict``. This feature can be used to implement custom decoders (e.g. 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, 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. + """ - if cls is None and encoding is None and object_hook is None and not kw: + 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 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 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) - -def read(s): - """ - json-py API compatibility hook. Use loads(s) instead. - """ - import warnings - warnings.warn("simplejson.loads(s) should be used instead of read(s)", - DeprecationWarning) - return loads(s) - -def write(obj): - """ - json-py API compatibility hook. Use dumps(s) instead. - """ - import warnings - warnings.warn("simplejson.dumps(s) should be used instead of write(s)", - DeprecationWarning) - return dumps(obj) - - Modified: trunk/qooxdoo/tool/pylib/simplejson/decoder.py =================================================================== --- trunk/qooxdoo/tool/pylib/simplejson/decoder.py 2009-09-29 09:04:04 UTC (rev 20232) +++ trunk/qooxdoo/tool/pylib/simplejson/decoder.py 2009-09-29 12:14:34 UTC (rev 20233) @@ -1,15 +1,20 @@ +"""Implementation of JSONDecoder """ -Implementation of JSONDecoder -""" import re +import sys +import struct -from simplejson.scanner import Scanner, pattern +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(): - import struct - import sys _BYTES = '7FF80000000000007FF0000000000000'.decode('hex') if sys.byteorder != 'big': _BYTES = _BYTES[:8][::-1] + _BYTES[8:][::-1] @@ -18,6 +23,7 @@ NaN, PosInf, NegInf = _floatconstants() + def linecol(doc, pos): lineno = doc.count('\n', 0, pos) + 1 if lineno == 1: @@ -26,38 +32,29 @@ 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: - return '%s: line %d column %d (char %d)' % (msg, lineno, colno, pos) + #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) - return '%s: line %d column %d - line %d column %d (char %d - %d)' % ( - msg, lineno, colno, endlineno, endcolno, pos, 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, - '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) +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', @@ -65,7 +62,15 @@ DEFAULT_ENCODING = "utf-8" -def scanstring(s, end, encoding=None, _b=BACKSLASH, _m=STRINGCHUNK.match): +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 = [] @@ -78,127 +83,184 @@ 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: - m = _b[esc] + char = _b[esc] except KeyError: - raise ValueError( - errmsg("Invalid \\escape: %r" % (esc,), s, end)) + msg = "Invalid \\escape: " + repr(esc) + raise ValueError(errmsg(msg, s, end)) end += 1 else: + # Unicode escape sequence 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) + 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 -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) +# Use speedup if available +scanstring = c_scanstring or py_scanstring -def JSONObject(match, context, _w=WHITESPACE.match): +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 = {} - s = match.string - end = _w(s, match.end()).end() + # 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] - # trivial empty object - if nextchar == '}': - return pairs, end + 1 + # Normally we expect nextchar == '"' if nextchar != '"': - raise ValueError(errmsg("Expecting property name", s, end)) + 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 - encoding = getattr(context, 'encoding', None) - iterscan = JSONScanner.iterscan while True: - key, end = scanstring(s, end, encoding) - end = _w(s, end).end() + 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] != ':': - raise ValueError(errmsg("Expecting : delimiter", s, end)) - end = _w(s, end + 1).end() + end = _w(s, end).end() + if s[end:end + 1] != ':': + raise ValueError(errmsg("Expecting : delimiter", s, end)) + + end += 1 + try: - value, end = iterscan(s, idx=end, context=context).next() + 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 - end = _w(s, end).end() - nextchar = s[end:end + 1] + + 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 - if nextchar != ',': + elif nextchar != ',': raise ValueError(errmsg("Expecting , delimiter", s, end - 1)) - end = _w(s, end).end() - nextchar = s[end: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)) - 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): + +def JSONArray((s, end), scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR): values = [] - s = match.string - end = _w(s, match.end()).end() - # look-ahead for trivial empty array 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 - iterscan = JSONScanner.iterscan + _append = values.append while True: try: - value, end = iterscan(s, idx=end, context=context).next() + value, end = scan_once(s, end) except StopIteration: raise ValueError(errmsg("Expecting object", s, end)) - values.append(value) - end = _w(s, end).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 - if nextchar != ',': + elif nextchar != ',': raise ValueError(errmsg("Expecting , delimiter", s, end)) - end = _w(s, end).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 -pattern(r'\[')(JSONArray) - -ANYTHING = [ - JSONObject, - JSONArray, - JSONString, - JSONConstant, - JSONNumber, -] -JSONScanner = Scanner(ANYTHING) - class JSONDecoder(object): - """ - Simple JSON <http://json.org> decoder + """Simple JSON <http://json.org> decoder - Performs the following translations in decoding: - + Performs the following translations in decoding by default: + +---------------+-------------------+ | JSON | Python | +===============+===================+ @@ -221,17 +283,15 @@ 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`` + 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``. @@ -239,14 +299,38 @@ 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`` + """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() @@ -254,20 +338,17 @@ 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 + 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. + """ - kw.setdefault('context', self) try: - obj, end = self._scanner.iterscan(s, **kw).next() + obj, end = self.scan_once(s, idx) except StopIteration: raise ValueError("No JSON object could be decoded") return obj, end - -__all__ = ['JSONDecoder'] Modified: trunk/qooxdoo/tool/pylib/simplejson/encoder.py =================================================================== --- trunk/qooxdoo/tool/pylib/simplejson/encoder.py 2009-09-29 09:04:04 UTC (rev 20232) +++ trunk/qooxdoo/tool/pylib/simplejson/encoder.py 2009-09-29 12:14:34 UTC (rev 20233) @@ -1,17 +1,20 @@ +"""Implementation of JSONEncoder """ -Implementation of JSONEncoder -""" import re + try: - from simplejson import _speedups + from simplejson._speedups import encode_basestring_ascii as c_encode_basestring_ascii except ImportError: - _speedups = None + c_encode_basestring_ascii = None +try: + from simplejson._speedups import make_encoder as c_make_encoder +except ImportError: + c_make_encoder = None -ESCAPE = re.compile(r'[\x00-\x19\\"\b\f\n\r\t]') -ESCAPE_ASCII = re.compile(r'([\\"/]|[^\ -~])') +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 = { - # escape all forward slashes to prevent </script> attack - '/': '\\/', '\\': '\\\\', '"': '\\"', '\b': '\\b', @@ -21,40 +24,28 @@ '\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) +# Assume this produces an infinity on all machines (probably not guaranteed) INFINITY = float('1e66666') +FLOAT_REPR = repr -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. +def encode_basestring(s): + """Return a JSON representation of a Python string - if o != o: - text = 'NaN' - elif o == INFINITY: - text = 'Infinity' - elif o == -INFINITY: - text = '-Infinity' - else: - return str(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 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: @@ -62,27 +53,25 @@ 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)) + '"' - -try: - encode_basestring_ascii = _speedups.encode_basestring_ascii - _need_utf8 = True -except AttributeError: - _need_utf8 = False + +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. + """Extensible JSON <http://json.org> encoder for Python data structures. Supports the following objects and types by default: - + +-------------------+---------------+ | Python | JSON | +===================+===============+ @@ -105,35 +94,34 @@ ``.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. + 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 + 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 + 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 + 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 + 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 + 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. @@ -143,12 +131,17 @@ 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 + 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. + transformed into unicode using that encoding prior to JSON-encoding. The default is UTF-8. + """ self.skipkeys = skipkeys @@ -157,15 +150,133 @@ 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 + if default is not None: + self.default = default self.encoding = encoding - def _newline_indent(self): - return '\n' + (' ' * (self.indent * self.current_indent_level)) + 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``). - def _iterencode_list(self, lst, markers=None): + 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 not self.indent 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 + False=False, + True=True, + 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 @@ -174,31 +285,51 @@ 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 + 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 = self.item_separator + separator = _item_separator first = True for value in lst: if first: first = False else: - yield separator - for chunk in self._iterencode(value, markers): - yield chunk + 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: - self.current_indent_level -= 1 - yield self._newline_indent() + _current_indent_level -= 1 + yield '\n' + (' ' * (_indent * _current_indent_level)) yield ']' if markers is not None: del markers[markerid] - def _iterencode_dict(self, dct, markers=None): + def _iterencode_dict(dct, _current_indent_level): if not dct: yield '{}' return @@ -208,78 +339,76 @@ 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 + 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 = self.item_separator + item_separator = _item_separator first = True - if self.ensure_ascii: - encoder = encode_basestring_ascii + if _sort_keys: + items = dct.items() + items.sort(key=lambda kv: kv[0]) 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): + 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, allow_nan) - elif isinstance(key, (int, long)): - key = str(key) + key = _floatstr(key) elif key is True: key = 'true' elif key is False: key = 'false' elif key is None: key = 'null' - elif self.skipkeys: + elif isinstance(key, (int, long)): + key = str(key) + elif _skipkeys: continue else: - raise TypeError("key %r is not a string" % (key,)) + raise TypeError("key " + repr(key) + " is not a string") if first: first = False else: yield item_separator - yield encoder(key) - yield key_separator - for chunk in self._iterencode(value, markers): - yield chunk + 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: - self.current_indent_level -= 1 - yield self._newline_indent() + _current_indent_level -= 1 + yield '\n' + (' ' * (_indent * _current_indent_level)) yield '}' if markers is not None: del markers[markerid] - def _iterencode(self, o, markers=None): + def _iterencode(o, _current_indent_level): 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) + yield _encoder(o) elif o is None: yield 'null' elif o is True: @@ -289,12 +418,12 @@ elif isinstance(o, (int, long)): yield str(o) elif isinstance(o, float): - yield floatstr(o, self.allow_nan) + yield _floatstr(o) elif isinstance(o, (list, tuple)): - for chunk in self._iterencode_list(o, markers): + for chunk in _iterencode_list(o, _current_indent_level): yield chunk elif isinstance(o, dict): - for chunk in self._iterencode_dict(o, markers): + for chunk in _iterencode_dict(o, _current_indent_level): yield chunk else: if markers is not None: @@ -302,70 +431,10 @@ if markerid in markers: raise ValueError("Circular reference detected") markers[markerid] = o - for chunk in self._iterencode_default(o, markers): + o = _default(o) + for chunk in _iterencode(o, _current_indent_level): 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'] + return _iterencode Modified: trunk/qooxdoo/tool/pylib/simplejson/scanner.py =================================================================== --- trunk/qooxdoo/tool/pylib/simplejson/scanner.py 2009-09-29 09:04:04 UTC (rev 20232) +++ trunk/qooxdoo/tool/pylib/simplejson/scanner.py 2009-09-29 12:14:34 UTC (rev 20233) @@ -1,63 +1,65 @@ +"""JSON token scanner """ -Iterator based sre token scanner -""" -import sre_parse, sre_compile, sre_constants -from sre_constants import BRANCH, SUBPATTERN -from re import VERBOSE, MULTILINE, DOTALL import re +try: + from simplejson._speedups import make_scanner as c_make_scanner +except ImportError: + c_make_scanner = None -__all__ = ['Scanner', 'pattern'] +__all__ = ['make_scanner'] -FLAGS = (VERBOSE | MULTILINE | DOTALL) -class Scanner(object): - def __init__(self, lexicon, flags=FLAGS): - self.actions = [None] - # combine phrases into a compound pattern - s = sre_parse.Pattern() - s.flags = flags - p = [] - for idx, token in enumerate(lexicon): - phrase = token.pattern - try: - subpattern = sre_parse.SubPattern(s, - [(SUBPATTERN, (idx + 1, sre_parse.parse(phrase, flags)))]) - except sre_constants.error: - raise - p.append(subpattern) - self.actions.append(token) +NUMBER_RE = re.compile( + r'(-?(?:0|[1-9]\d*))(\.\d+)?([eE][-+]?\d+)?', + (re.VERBOSE | re.MULTILINE | re.DOTALL)) - p = sre_parse.SubPattern(s, [(BRANCH, (None, p))]) - self.scanner = sre_compile.compile(p) +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 + def _scan_once(string, idx): + try: + nextchar = string[idx] + except IndexError: + raise StopIteration - def iterscan(self, string, idx=0, context=None): - """ - Yield match, end_idx for each match - """ - match = self.scanner.scanner(string, idx).match - actions = self.actions - lastend = idx - end = len(string) - while True: - m = match() - if m is None: - break - matchbegin, matchend = m.span() - if lastend == matchend: - break - action = actions[m.lastindex] - if action is not None: - rval, next_pos = action(m, context) - if next_pos is not None and next_pos != matchend: - # "fast forward" the scanner - matchend = next_pos - match = self.scanner.scanner(string, matchend).match - yield rval, matchend - lastend = matchend - -def pattern(pattern, flags=FLAGS): - def decorator(fn): - fn.pattern = pattern - fn.regex = re.compile(pattern, flags) - return fn - return decorator + if nextchar == '"': + return parse_string(string, idx + 1, encoding, strict) + elif nextchar == '{': + return parse_object((string, idx + 1), encoding, strict, _scan_once, object_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 + ... [truncated message content] |