diff --git a/scrapy/trunk/INSTALL b/scrapy/trunk/INSTALL index ea6b39db2..b101fd26f 100644 --- a/scrapy/trunk/INSTALL +++ b/scrapy/trunk/INSTALL @@ -5,6 +5,7 @@ You need: * pyopenssl for HTTPS support * for win32: http://webcleaner.sourceforge.net/pyOpenSSL-0.6.win32-py2.5.exe * spidermonkey (optional) - required for JSParser + * simplejson (optional) - required for url2guid web service The python interpreter should have sys.getdefaultencoding() == 'utf-8' If this is not the case, you can add the following lines to a file diff --git a/scrapy/trunk/scrapy/lib/simplejson/__init__.py b/scrapy/trunk/scrapy/lib/simplejson/__init__.py deleted file mode 100644 index 7738592b6..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/__init__.py +++ /dev/null @@ -1,287 +0,0 @@ -r""" -A simple, fast, extensible JSON encoder and decoder - -JSON (JavaScript Object Notation) 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. - -Encoding basic Python object hierarchies:: - - >>> import simplejson - >>> simplejson.dumps(['foo', {'bar': ('baz', None, 1.0, 2)}]) - '["foo", {"bar": ["baz", null, 1.0, 2]}]' - >>> print simplejson.dumps("\"foo\bar") - "\"foo\bar" - >>> print simplejson.dumps(u'\u1234') - "\u1234" - >>> print simplejson.dumps('\\') - "\\" - >>> print simplejson.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) - >>> io.getvalue() - '["streaming API"]' - -Compact encoding:: - - >>> import simplejson - >>> simplejson.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) - { - "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' - >>> from StringIO import StringIO - >>> io = StringIO('["streaming API"]') - >>> simplejson.load(io) - [u'streaming API'] - -Specializing JSON object decoding:: - - >>> import simplejson - >>> def as_complex(dct): - ... if '__complex__' in dct: - ... return complex(dct['real'], dct['imag']) - ... return dct - ... - >>> simplejson.loads('{"__complex__": true, "real": 1, "imag": 2}', - ... object_hook=as_complex) - (1+2j) - -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) - '[2.0, 1.0]' - >>> ComplexEncoder().encode(2 + 1j) - '[2.0, 1.0]' - >>> list(ComplexEncoder().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. -""" -__version__ = '1.7.2' -__all__ = [ - 'dump', 'dumps', 'load', 'loads', - 'JSONDecoder', 'JSONEncoder', -] - -from decoder import JSONDecoder -from encoder import JSONEncoder - -_default_encoder = JSONEncoder( - skipkeys=False, - ensure_ascii=True, - check_circular=True, - allow_nan=True, - indent=None, - separators=None, - encoding='utf-8' -) - -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 - ``.write()``-supporting file-like object). - - 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`` - 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 - 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 - 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``). - - 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 ``separators`` is an ``(item_separator, dict_separator)`` tuple - then it will be used instead of the default ``(', ', ': ')`` separators. - ``(',', ':')`` is the most compact JSON representation. - - ``encoding`` is the character encoding for str instances, default is UTF-8. - - 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 - cls is None and indent is None and separators is None and - encoding == 'utf-8' 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) - # could accelerate with writelines in some versions of Python, at - # a debuggability cost - for chunk in iterable: - fp.write(chunk) - - -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``. - - 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 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 - 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 - 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``). - - 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 ``separators`` is an ``(item_separator, dict_separator)`` tuple - then it will be used instead of the default ``(', ', ': ')`` separators. - ``(',', ':')`` is the most compact JSON representation. - - ``encoding`` is the character encoding for str instances, default is UTF-8. - - 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 - cls is None and indent is None and separators is None and - encoding == 'utf-8' 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, - **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 - a JSON document) to a Python object. - - If the contents of ``fp`` is encoded with an ASCII based encoding other - than utf-8 (e.g. latin-1), then an appropriate ``encoding`` name must - be specified. Encodings that are not ASCII based (such as UCS-2) are - not allowed, and should be wrapped with - ``codecs.getreader(fp)(encoding)``, or simply decoded to a ``unicode`` - object and passed to ``loads()`` - - ``object_hook`` is an optional function that will be called with the - 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) - -def loads(s, encoding=None, cls=None, object_hook=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 - other than utf-8 (e.g. latin-1) then an appropriate ``encoding`` name - must be specified. Encodings that are not ASCII based (such as UCS-2) - are not allowed and should be decoded to ``unicode`` first. - - ``object_hook`` is an optional function that will be called with the - 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. - """ - if cls is None and encoding is None and object_hook 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 - 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) - - diff --git a/scrapy/trunk/scrapy/lib/simplejson/_speedups.c b/scrapy/trunk/scrapy/lib/simplejson/_speedups.c deleted file mode 100644 index 8f290bb47..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/_speedups.c +++ /dev/null @@ -1,215 +0,0 @@ -#include "Python.h" -#if PY_VERSION_HEX < 0x02050000 && !defined(PY_SSIZE_T_MIN) -typedef int Py_ssize_t; -#define PY_SSIZE_T_MAX INT_MAX -#define PY_SSIZE_T_MIN INT_MIN -#endif - -static Py_ssize_t -ascii_escape_char(Py_UNICODE c, char *output, Py_ssize_t chars); -static PyObject * -ascii_escape_unicode(PyObject *pystr); -static PyObject * -ascii_escape_str(PyObject *pystr); -static PyObject * -py_encode_basestring_ascii(PyObject* self __attribute__((__unused__)), PyObject *pystr); -void init_speedups(void); - -#define S_CHAR(c) (c >= ' ' && c <= '~' && c != '\\' && c != '/' && c != '"') - -#define MIN_EXPANSION 6 -#ifdef Py_UNICODE_WIDE -#define MAX_EXPANSION (2 * MIN_EXPANSION) -#else -#define MAX_EXPANSION MIN_EXPANSION -#endif - -static Py_ssize_t -ascii_escape_char(Py_UNICODE c, char *output, Py_ssize_t chars) { - Py_UNICODE x; - output[chars++] = '\\'; - switch (c) { - case '/': output[chars++] = (char)c; break; - case '\\': output[chars++] = (char)c; break; - case '"': output[chars++] = (char)c; break; - case '\b': output[chars++] = 'b'; break; - case '\f': output[chars++] = 'f'; break; - case '\n': output[chars++] = 'n'; break; - case '\r': output[chars++] = 'r'; break; - case '\t': output[chars++] = 't'; break; - default: -#ifdef Py_UNICODE_WIDE - if (c >= 0x10000) { - /* UTF-16 surrogate pair */ - Py_UNICODE v = c - 0x10000; - c = 0xd800 | ((v >> 10) & 0x3ff); - output[chars++] = 'u'; - x = (c & 0xf000) >> 12; - output[chars++] = (x < 10) ? '0' + x : 'a' + (x - 10); - x = (c & 0x0f00) >> 8; - output[chars++] = (x < 10) ? '0' + x : 'a' + (x - 10); - x = (c & 0x00f0) >> 4; - output[chars++] = (x < 10) ? '0' + x : 'a' + (x - 10); - x = (c & 0x000f); - output[chars++] = (x < 10) ? '0' + x : 'a' + (x - 10); - c = 0xdc00 | (v & 0x3ff); - output[chars++] = '\\'; - } -#endif - output[chars++] = 'u'; - x = (c & 0xf000) >> 12; - output[chars++] = (x < 10) ? '0' + x : 'a' + (x - 10); - x = (c & 0x0f00) >> 8; - output[chars++] = (x < 10) ? '0' + x : 'a' + (x - 10); - x = (c & 0x00f0) >> 4; - output[chars++] = (x < 10) ? '0' + x : 'a' + (x - 10); - x = (c & 0x000f); - output[chars++] = (x < 10) ? '0' + x : 'a' + (x - 10); - } - return chars; -} - -static PyObject * -ascii_escape_unicode(PyObject *pystr) { - Py_ssize_t i; - Py_ssize_t input_chars; - Py_ssize_t output_size; - Py_ssize_t chars; - PyObject *rval; - char *output; - Py_UNICODE *input_unicode; - - input_chars = PyUnicode_GET_SIZE(pystr); - input_unicode = PyUnicode_AS_UNICODE(pystr); - /* One char input can be up to 6 chars output, estimate 4 of these */ - output_size = 2 + (MIN_EXPANSION * 4) + input_chars; - rval = PyString_FromStringAndSize(NULL, output_size); - if (rval == NULL) { - return NULL; - } - output = PyString_AS_STRING(rval); - chars = 0; - output[chars++] = '"'; - for (i = 0; i < input_chars; i++) { - Py_UNICODE c = input_unicode[i]; - if (S_CHAR(c)) { - output[chars++] = (char)c; - } else { - chars = ascii_escape_char(c, output, chars); - } - if (output_size - chars < (1 + MAX_EXPANSION)) { - /* There's more than four, so let's resize by a lot */ - output_size *= 2; - /* This is an upper bound */ - if (output_size > 2 + (input_chars * MAX_EXPANSION)) { - output_size = 2 + (input_chars * MAX_EXPANSION); - } - if (_PyString_Resize(&rval, output_size) == -1) { - return NULL; - } - output = PyString_AS_STRING(rval); - } - } - output[chars++] = '"'; - if (_PyString_Resize(&rval, chars) == -1) { - return NULL; - } - return rval; -} - -static PyObject * -ascii_escape_str(PyObject *pystr) { - Py_ssize_t i; - Py_ssize_t input_chars; - Py_ssize_t output_size; - Py_ssize_t chars; - PyObject *rval; - char *output; - char *input_str; - - input_chars = PyString_GET_SIZE(pystr); - input_str = PyString_AS_STRING(pystr); - /* One char input can be up to 6 chars output, estimate 4 of these */ - output_size = 2 + (MIN_EXPANSION * 4) + input_chars; - rval = PyString_FromStringAndSize(NULL, output_size); - if (rval == NULL) { - return NULL; - } - output = PyString_AS_STRING(rval); - chars = 0; - output[chars++] = '"'; - for (i = 0; i < input_chars; i++) { - Py_UNICODE c = (Py_UNICODE)input_str[i]; - if (S_CHAR(c)) { - output[chars++] = (char)c; - } else if (c > 0x7F) { - /* We hit a non-ASCII character, bail to unicode mode */ - PyObject *uni; - Py_DECREF(rval); - uni = PyUnicode_DecodeUTF8(input_str, input_chars, "strict"); - if (uni == NULL) { - return NULL; - } - rval = ascii_escape_unicode(uni); - Py_DECREF(uni); - return rval; - } else { - chars = ascii_escape_char(c, output, chars); - } - /* An ASCII char can't possibly expand to a surrogate! */ - if (output_size - chars < (1 + MIN_EXPANSION)) { - /* There's more than four, so let's resize by a lot */ - output_size *= 2; - if (output_size > 2 + (input_chars * MIN_EXPANSION)) { - output_size = 2 + (input_chars * MIN_EXPANSION); - } - if (_PyString_Resize(&rval, output_size) == -1) { - return NULL; - } - output = PyString_AS_STRING(rval); - } - } - output[chars++] = '"'; - if (_PyString_Resize(&rval, chars) == -1) { - return NULL; - } - return rval; -} - -PyDoc_STRVAR(pydoc_encode_basestring_ascii, - "encode_basestring_ascii(basestring) -> str\n" - "\n" - "..." -); - -static PyObject * -py_encode_basestring_ascii(PyObject* self __attribute__((__unused__)), PyObject *pystr) { - /* METH_O */ - if (PyString_Check(pystr)) { - return ascii_escape_str(pystr); - } else if (PyUnicode_Check(pystr)) { - return ascii_escape_unicode(pystr); - } - PyErr_SetString(PyExc_TypeError, "first argument must be a string"); - return NULL; -} - -#define DEFN(n, k) \ - { \ - #n, \ - (PyCFunction)py_ ##n, \ - k, \ - pydoc_ ##n \ - } -static PyMethodDef speedups_methods[] = { - DEFN(encode_basestring_ascii, METH_O), - {} -}; -#undef DEFN - -void -init_speedups(void) -{ - PyObject *m; - m = Py_InitModule4("_speedups", speedups_methods, NULL, NULL, PYTHON_API_VERSION); -} diff --git a/scrapy/trunk/scrapy/lib/simplejson/decoder.py b/scrapy/trunk/scrapy/lib/simplejson/decoder.py deleted file mode 100644 index a1b53b2a8..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/decoder.py +++ /dev/null @@ -1,273 +0,0 @@ -""" -Implementation of JSONDecoder -""" -import re - -from 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 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'] diff --git a/scrapy/trunk/scrapy/lib/simplejson/encoder.py b/scrapy/trunk/scrapy/lib/simplejson/encoder.py deleted file mode 100644 index eec9c7ffd..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/encoder.py +++ /dev/null @@ -1,371 +0,0 @@ -""" -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 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 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 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 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'] diff --git a/scrapy/trunk/scrapy/lib/simplejson/jsonfilter.py b/scrapy/trunk/scrapy/lib/simplejson/jsonfilter.py deleted file mode 100644 index 01ca21df6..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/jsonfilter.py +++ /dev/null @@ -1,40 +0,0 @@ -import simplejson -import cgi - -class JSONFilter(object): - def __init__(self, app, mime_type='text/x-json'): - self.app = app - self.mime_type = mime_type - - def __call__(self, environ, start_response): - # Read JSON POST input to jsonfilter.json if matching mime type - response = {'status': '200 OK', 'headers': []} - def json_start_response(status, headers): - response['status'] = status - response['headers'].extend(headers) - environ['jsonfilter.mime_type'] = self.mime_type - if environ.get('REQUEST_METHOD', '') == 'POST': - if environ.get('CONTENT_TYPE', '') == self.mime_type: - args = [_ for _ in [environ.get('CONTENT_LENGTH')] if _] - data = environ['wsgi.input'].read(*map(int, args)) - environ['jsonfilter.json'] = simplejson.loads(data) - res = simplejson.dumps(self.app(environ, json_start_response)) - jsonp = cgi.parse_qs(environ.get('QUERY_STRING', '')).get('jsonp') - if jsonp: - content_type = 'text/javascript' - res = ''.join(jsonp + ['(', res, ')']) - elif 'Opera' in environ.get('HTTP_USER_AGENT', ''): - # Opera has bunk XMLHttpRequest support for most mime types - content_type = 'text/plain' - else: - content_type = self.mime_type - headers = [ - ('Content-type', content_type), - ('Content-length', len(res)), - ] - headers.extend(response['headers']) - start_response(response['status'], headers) - return [res] - -def factory(app, global_conf, **kw): - return JSONFilter(app, **kw) diff --git a/scrapy/trunk/scrapy/lib/simplejson/scanner.py b/scrapy/trunk/scrapy/lib/simplejson/scanner.py deleted file mode 100644 index 64f4999fb..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/scanner.py +++ /dev/null @@ -1,63 +0,0 @@ -""" -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 - -__all__ = ['Scanner', 'pattern'] - -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) - - p = sre_parse.SubPattern(s, [(BRANCH, (None, p))]) - self.scanner = sre_compile.compile(p) - - - 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 diff --git a/scrapy/trunk/scrapy/lib/simplejson/tests/__init__.py b/scrapy/trunk/scrapy/lib/simplejson/tests/__init__.py deleted file mode 100644 index e69de29bb..000000000 diff --git a/scrapy/trunk/scrapy/lib/simplejson/tests/test_attacks.py b/scrapy/trunk/scrapy/lib/simplejson/tests/test_attacks.py deleted file mode 100644 index 8ecfed8f2..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/tests/test_attacks.py +++ /dev/null @@ -1,6 +0,0 @@ -def test_script_close_attack(): - import simplejson - res = simplejson.dumps('') - assert '' not in res - res = simplejson.dumps(simplejson.loads('""')) - assert '' not in res diff --git a/scrapy/trunk/scrapy/lib/simplejson/tests/test_dump.py b/scrapy/trunk/scrapy/lib/simplejson/tests/test_dump.py deleted file mode 100644 index b4e236e56..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/tests/test_dump.py +++ /dev/null @@ -1,10 +0,0 @@ -from cStringIO import StringIO -import simplejson as S - -def test_dump(): - sio = StringIO() - S.dump({}, sio) - assert sio.getvalue() == '{}' - -def test_dumps(): - assert S.dumps({}) == '{}' diff --git a/scrapy/trunk/scrapy/lib/simplejson/tests/test_fail.py b/scrapy/trunk/scrapy/lib/simplejson/tests/test_fail.py deleted file mode 100644 index a99d9c40c..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/tests/test_fail.py +++ /dev/null @@ -1,70 +0,0 @@ -# Fri Dec 30 18:57:26 2005 -JSONDOCS = [ - # http://json.org/JSON_checker/test/fail1.json - '"A JSON payload should be an object or array, not a string."', - # http://json.org/JSON_checker/test/fail2.json - '["Unclosed array"', - # http://json.org/JSON_checker/test/fail3.json - '{unquoted_key: "keys must be quoted}', - # http://json.org/JSON_checker/test/fail4.json - '["extra comma",]', - # http://json.org/JSON_checker/test/fail5.json - '["double extra comma",,]', - # http://json.org/JSON_checker/test/fail6.json - '[ , "<-- missing value"]', - # http://json.org/JSON_checker/test/fail7.json - '["Comma after the close"],', - # http://json.org/JSON_checker/test/fail8.json - '["Extra close"]]', - # http://json.org/JSON_checker/test/fail9.json - '{"Extra comma": true,}', - # http://json.org/JSON_checker/test/fail10.json - '{"Extra value after close": true} "misplaced quoted value"', - # http://json.org/JSON_checker/test/fail11.json - '{"Illegal expression": 1 + 2}', - # http://json.org/JSON_checker/test/fail12.json - '{"Illegal invocation": alert()}', - # http://json.org/JSON_checker/test/fail13.json - '{"Numbers cannot have leading zeroes": 013}', - # http://json.org/JSON_checker/test/fail14.json - '{"Numbers cannot be hex": 0x14}', - # http://json.org/JSON_checker/test/fail15.json - '["Illegal backslash escape: \\x15"]', - # http://json.org/JSON_checker/test/fail16.json - '["Illegal backslash escape: \\\'"]', - # http://json.org/JSON_checker/test/fail17.json - '["Illegal backslash escape: \\017"]', - # http://json.org/JSON_checker/test/fail18.json - '[[[[[[[[[[[[[[[[[[[["Too deep"]]]]]]]]]]]]]]]]]]]]', - # http://json.org/JSON_checker/test/fail19.json - '{"Missing colon" null}', - # http://json.org/JSON_checker/test/fail20.json - '{"Double colon":: null}', - # http://json.org/JSON_checker/test/fail21.json - '{"Comma instead of colon", null}', - # http://json.org/JSON_checker/test/fail22.json - '["Colon instead of comma": false]', - # http://json.org/JSON_checker/test/fail23.json - '["Bad value", truth]', - # http://json.org/JSON_checker/test/fail24.json - "['single quote']", -] - -SKIPS = { - 1: "why not have a string payload?", - 18: "spec doesn't specify any nesting limitations", -} - -def test_failures(): - import simplejson - for idx, doc in enumerate(JSONDOCS): - idx = idx + 1 - if idx in SKIPS: - simplejson.loads(doc) - continue - try: - simplejson.loads(doc) - except ValueError: - pass - else: - assert False, "Expected failure for fail%d.json: %r" % (idx, doc) diff --git a/scrapy/trunk/scrapy/lib/simplejson/tests/test_indent.py b/scrapy/trunk/scrapy/lib/simplejson/tests/test_indent.py deleted file mode 100644 index 47dd4dc2e..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/tests/test_indent.py +++ /dev/null @@ -1,41 +0,0 @@ - - - -def test_indent(): - import simplejson - import textwrap - - h = [['blorpie'], ['whoops'], [], 'd-shtaeou', 'd-nthiouh', 'i-vhbjkhnth', - {'nifty': 87}, {'field': 'yes', 'morefield': False} ] - - expect = textwrap.dedent("""\ - [ - [ - "blorpie" - ], - [ - "whoops" - ], - [], - "d-shtaeou", - "d-nthiouh", - "i-vhbjkhnth", - { - "nifty": 87 - }, - { - "field": "yes", - "morefield": false - } - ]""") - - - d1 = simplejson.dumps(h) - d2 = simplejson.dumps(h, indent=2, sort_keys=True, separators=(',', ': ')) - - h1 = simplejson.loads(d1) - h2 = simplejson.loads(d2) - - assert h1 == h - assert h2 == h - assert d2 == expect diff --git a/scrapy/trunk/scrapy/lib/simplejson/tests/test_pass1.py b/scrapy/trunk/scrapy/lib/simplejson/tests/test_pass1.py deleted file mode 100644 index 4eda19258..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/tests/test_pass1.py +++ /dev/null @@ -1,72 +0,0 @@ -# from http://json.org/JSON_checker/test/pass1.json -JSON = r''' -[ - "JSON Test Pattern pass1", - {"object with 1 member":["array with 1 element"]}, - {}, - [], - -42, - true, - false, - null, - { - "integer": 1234567890, - "real": -9876.543210, - "e": 0.123456789e-12, - "E": 1.234567890E+34, - "": 23456789012E666, - "zero": 0, - "one": 1, - "space": " ", - "quote": "\"", - "backslash": "\\", - "controls": "\b\f\n\r\t", - "slash": "/ & \/", - "alpha": "abcdefghijklmnopqrstuvwyz", - "ALPHA": "ABCDEFGHIJKLMNOPQRSTUVWYZ", - "digit": "0123456789", - "special": "`1~!@#$%^&*()_+-={':[,]}|;.?", - "hex": "\u0123\u4567\u89AB\uCDEF\uabcd\uef4A", - "true": true, - "false": false, - "null": null, - "array":[ ], - "object":{ }, - "address": "50 St. James Street", - "url": "http://www.JSON.org/", - "comment": "// /* */": " ", - " s p a c e d " :[1,2 , 3 - -, - -4 , 5 , 6 ,7 ], - "compact": [1,2,3,4,5,6,7], - "jsontext": "{\"object with 1 member\":[\"array with 1 element\"]}", - "quotes": "" \u0022 %22 0x22 034 "", - "\/\\\"\uCAFE\uBABE\uAB98\uFCDE\ubcda\uef4A\b\f\n\r\t`1~!@#$%^&*()_+-=[]{}|;:',./<>?" -: "A key can be any string" - }, - 0.5 ,98.6 -, -99.44 -, - -1066 - - -,"rosebud"] -''' - -def test_parse(): - # test in/out equivalence and parsing - import simplejson - res = simplejson.loads(JSON) - out = simplejson.dumps(res) - assert res == simplejson.loads(out) - try: - simplejson.dumps(res, allow_nan=False) - except ValueError: - pass - else: - assert False, "23456789012E666 should be out of range" diff --git a/scrapy/trunk/scrapy/lib/simplejson/tests/test_pass2.py b/scrapy/trunk/scrapy/lib/simplejson/tests/test_pass2.py deleted file mode 100644 index ae74abbf5..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/tests/test_pass2.py +++ /dev/null @@ -1,11 +0,0 @@ -# from http://json.org/JSON_checker/test/pass2.json -JSON = r''' -[[[[[[[[[[[[[[[[[[["Not too deep"]]]]]]]]]]]]]]]]]]] -''' - -def test_parse(): - # test in/out equivalence and parsing - import simplejson - res = simplejson.loads(JSON) - out = simplejson.dumps(res) - assert res == simplejson.loads(out) diff --git a/scrapy/trunk/scrapy/lib/simplejson/tests/test_pass3.py b/scrapy/trunk/scrapy/lib/simplejson/tests/test_pass3.py deleted file mode 100644 index d94893ffa..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/tests/test_pass3.py +++ /dev/null @@ -1,16 +0,0 @@ -# from http://json.org/JSON_checker/test/pass3.json -JSON = r''' -{ - "JSON Test Pattern pass3": { - "The outermost value": "must be an object or array.", - "In this test": "It is an object." - } -} -''' - -def test_parse(): - # test in/out equivalence and parsing - import simplejson - res = simplejson.loads(JSON) - out = simplejson.dumps(res) - assert res == simplejson.loads(out) diff --git a/scrapy/trunk/scrapy/lib/simplejson/tests/test_recursion.py b/scrapy/trunk/scrapy/lib/simplejson/tests/test_recursion.py deleted file mode 100644 index 756b06612..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/tests/test_recursion.py +++ /dev/null @@ -1,62 +0,0 @@ -import simplejson - -def test_listrecursion(): - x = [] - x.append(x) - try: - simplejson.dumps(x) - except ValueError: - pass - else: - assert False, "didn't raise ValueError on list recursion" - x = [] - y = [x] - x.append(y) - try: - simplejson.dumps(x) - except ValueError: - pass - else: - assert False, "didn't raise ValueError on alternating list recursion" - y = [] - x = [y, y] - # ensure that the marker is cleared - simplejson.dumps(x) - -def test_dictrecursion(): - x = {} - x["test"] = x - try: - simplejson.dumps(x) - except ValueError: - pass - else: - assert False, "didn't raise ValueError on dict recursion" - x = {} - y = {"a": x, "b": x} - # ensure that the marker is cleared - simplejson.dumps(x) - -class TestObject: - pass - -class RecursiveJSONEncoder(simplejson.JSONEncoder): - recurse = False - def default(self, o): - if o is TestObject: - if self.recurse: - return [TestObject] - else: - return 'TestObject' - simplejson.JSONEncoder.default(o) - -def test_defaultrecursion(): - enc = RecursiveJSONEncoder() - assert enc.encode(TestObject) == '"TestObject"' - enc.recurse = True - try: - enc.encode(TestObject) - except ValueError: - pass - else: - assert False, "didn't raise ValueError on default recursion" diff --git a/scrapy/trunk/scrapy/lib/simplejson/tests/test_separators.py b/scrapy/trunk/scrapy/lib/simplejson/tests/test_separators.py deleted file mode 100644 index a61535478..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/tests/test_separators.py +++ /dev/null @@ -1,41 +0,0 @@ - - - -def test_separators(): - import simplejson - import textwrap - - h = [['blorpie'], ['whoops'], [], 'd-shtaeou', 'd-nthiouh', 'i-vhbjkhnth', - {'nifty': 87}, {'field': 'yes', 'morefield': False} ] - - expect = textwrap.dedent("""\ - [ - [ - "blorpie" - ] , - [ - "whoops" - ] , - [] , - "d-shtaeou" , - "d-nthiouh" , - "i-vhbjkhnth" , - { - "nifty" : 87 - } , - { - "field" : "yes" , - "morefield" : false - } - ]""") - - - d1 = simplejson.dumps(h) - d2 = simplejson.dumps(h, indent=2, sort_keys=True, separators=(' ,', ' : ')) - - h1 = simplejson.loads(d1) - h2 = simplejson.loads(d2) - - assert h1 == h - assert h2 == h - assert d2 == expect diff --git a/scrapy/trunk/scrapy/lib/simplejson/tests/test_unicode.py b/scrapy/trunk/scrapy/lib/simplejson/tests/test_unicode.py deleted file mode 100644 index 88d09393e..000000000 --- a/scrapy/trunk/scrapy/lib/simplejson/tests/test_unicode.py +++ /dev/null @@ -1,16 +0,0 @@ -import simplejson as S - -def test_encoding1(): - encoder = S.JSONEncoder(encoding='utf-8') - u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}' - s = u.encode('utf-8') - ju = encoder.encode(u) - js = encoder.encode(s) - assert ju == js - -def test_encoding2(): - u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}' - s = u.encode('utf-8') - ju = S.dumps(u, encoding='utf-8') - js = S.dumps(s, encoding='utf-8') - assert ju == js