simplejson-3.8.1/0000755000076500000240000000000012613714404013575 5ustar bobstaff00000000000000simplejson-3.8.1/CHANGES.txt0000644000076500000240000004432012613714261015412 0ustar bobstaff00000000000000Version 3.8.1 released 2015-10-27 * Fix issue with iterable_as_array and indent option https://github.com/simplejson/simplejson/issues/128 * Fix typo in keyword argument name introduced in 3.8.0 https://github.com/simplejson/simplejson/pull/123 Version 3.8.0 released 2015-07-18 * New iterable_as_array encoder option to perform lazy serialization of any iterable objects, without having to convert to tuple or list. Version 3.7.3 released 2015-05-31 * Fix typo introduced in 3.7.0 (behavior should be indistinguishable) https://github.com/simplejson/simplejson/commit/e18cc09b688ea1f3305c27616fd3cadd2adc6d31#commitcomment-11443842 Version 3.7.2 released 2015-05-22 * Do not cache Decimal class in encoder, only reference the decimal module. This may make reload work in more common scenarios. Version 3.7.1 released 2015-05-18 * Fix compilation with MSVC https://github.com/simplejson/simplejson/pull/119 Version 3.7.0 released 2015-05-18 * simplejson no longer trusts custom str/repr methods for int, long, float subclasses. These instances are now formatted as if they were exact instances of those types. https://github.com/simplejson/simplejson/issues/118 Version 3.6.5 released 2014-10-24 * Importing bug fix for reference leak when an error occurs during dict encoding https://github.com/simplejson/simplejson/issues/109 Version 3.6.4 released 2014-09-29 * Important bug fix for dump when only sort_keys is set https://github.com/simplejson/simplejson/issues/106 Version 3.6.3 released 2014-08-18 * Documentation updates https://github.com/simplejson/simplejson/issues/103 Version 3.6.2 released 2014-08-09 * Documentation updates http://bugs.python.org/issue21514 Version 3.6.1 released 2014-08-09 * Documentation updates https://github.com/simplejson/simplejson/issues/102 Version 3.6.0 released 2014-07-21 * Automatically strip any UTF-8 BOM from input to more closely follow the latest specs https://github.com/simplejson/simplejson/pull/101 Version 3.5.3 released 2014-06-24 * Fix lower bound checking in scan_once / raw_decode API https://github.com/simplejson/simplejson/issues/98 Version 3.5.2 released 2014-05-22 * Fix Windows build with VS2008 https://github.com/simplejson/simplejson/pull/97 Version 3.5.1 released 2014-05-21 * Consistently reject int_as_string_bitcount settings that are not positive integers Version 3.5.0 released 2014-05-20 * Added int_as_string_bitcount encoder option https://github.com/simplejson/pull/96 * Fixed potential crash when encoder created with incorrect options Version 3.4.1 released 2014-04-30 * Fixed tests to run on Python 3.4 Version 3.4.0 released 2014-04-02 * Native setuptools support re-introduced https://github.com/simplejson/simplejson/pull/92 Version 3.3.3 released 2014-02-14 * Improve test suite's Python 3.4 compatibility https://github.com/simplejson/simplejson/issues/87 Version 3.3.2 released 2014-01-06 * Docstring fix for decoded string types https://github.com/simplejson/simplejson/pull/82 Version 3.3.1 released 2013-10-05 * JSONDecodeError exceptions can now be pickled https://github.com/simplejson/simplejson/pull/78 Version 3.3.0 released 2013-05-07 * Unpaired surrogates once again pass through the decoder, to match older behavior and the RFC-4627 spec. https://github.com/simplejson/simplejson/issues/62 Version 3.2.0 released 2013-05-01 * New ignore_nan kwarg in encoder that serializes out of range floats (Infinity, -Infinity, NaN) as null for ECMA-262 compliance. https://github.com/simplejson/simplejson/pull/63 * New for_json kwarg in encoder to make it possible to for subclasses of dict and list to be specialized. https://github.com/simplejson/simplejson/pull/69 Version 3.1.3 released 2013-04-06 * Updated documentation to discourage subclassing whenever possible. default, object_hook, and object_pairs_hook provide almost all of the functionality of subclassing. Version 3.1.2 released 2013-03-20 * Updated documentation to reflect separators behavior when indent is not None https://github.com/simplejson/simplejson/issues/59 * Test suite should be compatible with debug builds of Python 2.x and 3.x https://github.com/simplejson/simplejson/pull/65 Version 3.1.1 released 2013-02-21 * setup.py now has another workaround for Windows machines without MSVC installed http://bugs.python.org/issue7511 Version 3.1.0 released 2013-02-21 * Updated JSON conformance test suite http://bugs.python.org/issue16559 * simplejson.tool tests and bugfix for Python 3.x http://bugs.python.org/issue16549 * Improve error messages for certain kinds of truncated input http://bugs.python.org/issue16009 * Moved JSONDecodeError to json.scanner (still available for import from json.decoder) * Changed scanner to use JSONDecodeError directly rather than StopIteration to improve error messages Version 3.0.9 released 2013-02-21 * Fix an off-by-one error in the colno property of JSONDecodeError (when lineno == 1) http://bugs.python.org/issue17225 Version 3.0.8 released 2013-02-19 * Fix a Python 2.x compiler warning for narrow unicode builds https://github.com/simplejson/simplejson/issues/56 Version 3.0.7 released 2013-01-11 * NOTE: this release only changes the license. * simplejson is now dual-licensed software, MIT or AFL v2.1. It is also made explicit that this code is also licensed to the PSF under a Contributor Agreement. Version 3.0.6 released 2013-01-11 * Fix for major Python 2.x ensure_ascii=False encoding regression introduced in simplejson 3.0.0. If you use this setting, please upgrade immediately. https://github.com/simplejson/simplejson/issues/50 Version 3.0.5 released 2013-01-03 * NOTE: this release only changes the tests, it is not essential to upgrade * Tests now run with deprecation warnings printed * Fixed Python 3 syntax error in simplejson.tool https://github.com/simplejson/simplejson/issues/49 * Fixed Python 3.3 deprecation warnings in test suite https://github.com/simplejson/simplejson/issues/48 Version 3.0.4 released 2013-01-02 * MSVC compatibility for Python 3.3 https://github.com/simplejson/simplejson/pull/47 Version 3.0.3 released 2013-01-01 * Fixes for bugs introduced in 3.0.2 * Fixes for Python 2.5 compatibility * MSVC compatibility for Python 2.x https://github.com/simplejson/simplejson/pull/46 Version 3.0.2 released 2013-01-01 * THIS VERSION HAS BEEN REMOVED * Missed a changeset to _speedups.c in the 3.0.1 branch cut Version 3.0.1 released 2013-01-01 * THIS VERSION HAS BEEN REMOVED * Add accumulator optimization to encoder, equivalent to the usage of `_Py_Accu` in the Python 3.3 json library. Only relevant if encoding very large JSON documents. Version 3.0.0 released 2012-12-30 * Python 3.3 is now supported, thanks to Vinay Sajip https://github.com/simplejson/simplejson/issues/8 * `sort_keys`/`item_sort_key` now sort on the stringified verison of the key, rather than the original object. This ensures that the sort only compares string types and makes the behavior consistent between Python 2.x and Python 3.x. * Like other number types, Decimal instances used as keys are now coerced to strings when use_decimal is True. Version 2.6.2 released 2012-09-21 * JSONEncoderForHTML was not exported in the simplejson module https://github.com/simplejson/simplejson/issues/41 Version 2.6.1 released 2012-07-27 * raw_decode() now skips whitespace before the object https://github.com/simplejson/simplejson/pull/38 Version 2.6.0 released 2012-06-26 * Error messages changed to match proposal for Python 3.3.1 http://bugs.python.org/issue5067 Version 2.5.2 released 2012-05-10 * Fix for regression introduced in 2.5.1 https://github.com/simplejson/simplejson/issues/35 Version 2.5.1 released 2012-05-10 * Support for use_decimal=True in environments that use Python sub-interpreters such as uWSGI https://github.com/simplejson/simplejson/issues/34 Version 2.5.0 released 2012-03-29 * New item_sort_key option for encoder to allow fine grained control of sorted output Version 2.4.0 released 2012-03-06 * New bigint_as_string option for encoder to trade JavaScript number precision issues for type issues. https://github.com/simplejson/simplejson/issues/31 Version 2.3.3 released 2012-02-27 * Allow unknown numerical types for indent parameter https://github.com/simplejson/simplejson/pull/29 Version 2.3.2 released 2011-12-30 * Fix crashing regression in speedups introduced in 2.3.1 Version 2.3.1 released 2011-12-29 * namedtuple_as_object now checks _asdict to ensure that it is callable. https://github.com/simplejson/simplejson/issues/26 Version 2.3.0 released 2011-12-05 * Any objects with _asdict() methods are now considered for namedtuple_as_object. https://github.com/simplejson/simplejson/pull/22 Version 2.2.1 released 2011-09-06 * Fix MANIFEST.in issue when building a sdist from a sdist. https://github.com/simplejson/simplejson/issues/16 Version 2.2.0 released 2011-09-04 * Remove setuptools requirement, reverted to pure distutils * use_decimal default for encoding (dump, dumps, JSONEncoder) is now True * tuple encoding as JSON objects can be turned off with new tuple_as_array=False option. https://github.com/simplejson/simplejson/pull/6 * namedtuple (or other tuple subclasses with _asdict methods) are now encoded as JSON objects rather than arrays by default. Can be disabled and treated as a tuple with the new namedtuple_as_object=False option. https://github.com/simplejson/simplejson/pull/6 * JSONDecodeError is now raised instead of ValueError when a document ends with an opening quote and the C speedups are in use. https://github.com/simplejson/simplejson/issues/15 * Updated documentation with information about JSONDecodeError * Force unicode linebreak characters to be escaped (U+2028 and U+2029) http://timelessrepo.com/json-isnt-a-javascript-subset * Moved documentation from a git submodule to http://simplejson.readthedocs.org/ Version 2.1.6 released 2011-05-08 * Prevent segfaults with deeply nested JSON documents https://github.com/simplejson/simplejson/issues/11 * Fix compatibility with Python 2.5 https://github.com/simplejson/simplejson/issues/5 Version 2.1.5 released 2011-04-17 * Built sdist tarball with setuptools_git installed. Argh. Version 2.1.4 released 2011-04-17 * Does not try to build the extension when using PyPy * Trailing whitespace after commas no longer emitted when indent is used * Migrated to github http://github.com/simplejson/simplejson Version 2.1.3 released 2011-01-17 * Support the sort_keys option in C encoding speedups http://code.google.com/p/simplejson/issues/detail?id=86 * Allow use_decimal to work with dump() http://code.google.com/p/simplejson/issues/detail?id=87 Version 2.1.2 released 2010-11-01 * Correct wrong end when object_pairs_hook is used http://code.google.com/p/simplejson/issues/detail?id=85 * Correct output for indent=0 http://bugs.python.org/issue10019 * Correctly raise TypeError when non-string keys are used with speedups http://code.google.com/p/simplejson/issues/detail?id=82 * Fix the endlineno, endcolno attributes of the JSONDecodeError exception. http://code.google.com/p/simplejson/issues/detail?id=81 Version 2.1.1 released 2010-03-31 * Change how setup.py imports ez_setup.py to try and workaround old versions of setuptools. http://code.google.com/p/simplejson/issues/detail?id=75 * Fix compilation on Windows platform (and other platforms with very picky compilers) * Corrected simplejson.__version__ and other minor doc changes. * Do not fail speedups tests if speedups could not be built. http://code.google.com/p/simplejson/issues/detail?id=73 Version 2.1.0 released 2010-03-10 * Decimal serialization officially supported for encoding with use_decimal=True. For encoding this encodes Decimal objects and for decoding it implies parse_float=Decimal * Python 2.4 no longer supported (may still work, but no longer tested) * Decoding performance and memory utilization enhancements http://bugs.python.org/issue7451 * JSONEncoderForHTML class for escaping &, <, > http://code.google.com/p/simplejson/issues/detail?id=66 * Memoization of object keys during encoding (when using speedups) * Encoder changed to use PyIter_Next for list iteration to avoid potential threading issues * Encoder changed to use iteritems rather than PyDict_Next in order to support dict subclasses that have a well defined ordering http://bugs.python.org/issue6105 * indent encoding parameter changed to be a string rather than an integer (integer use still supported for backwards compatibility) http://code.google.com/p/simplejson/issues/detail?id=56 * Test suite (python setup.py test) now automatically runs with and without speedups http://code.google.com/p/simplejson/issues/detail?id=55 * Fixed support for older versions of easy_install (e.g. stock Mac OS X config) http://code.google.com/p/simplejson/issues/detail?id=54 * Fixed str/unicode mismatches when using ensure_ascii=False http://code.google.com/p/simplejson/issues/detail?id=48 * Fixed error message when parsing an array with trailing comma with speedups http://code.google.com/p/simplejson/issues/detail?id=46 * Refactor decoder errors to raise JSONDecodeError instead of ValueError http://code.google.com/p/simplejson/issues/detail?id=45 * New ordered_pairs_hook feature in decoder which makes it possible to preserve key order. http://bugs.python.org/issue5381 * Fixed containerless unicode float decoding (same bug as 2.0.4, oops!) http://code.google.com/p/simplejson/issues/detail?id=43 * Share PosInf definition between encoder and decoder * Minor reformatting to make it easier to backport simplejson changes to Python 2.7/3.1 json module Version 2.0.9 released 2009-02-18 * Adds cyclic GC to the Encoder and Scanner speedups, which could've caused uncollectible cycles in some cases when using custom parser or encoder functions Version 2.0.8 released 2009-02-15 * Documentation fixes * Fixes encoding True and False as keys * Fixes checking for True and False by identity for several parameters Version 2.0.7 released 2009-01-04 * Documentation fixes * C extension now always returns unicode strings when the input string is unicode, even for empty strings Version 2.0.6 released 2008-12-19 * Windows build fixes Version 2.0.5 released 2008-11-23 * Fixes a segfault in the C extension when using check_circular=False and encoding an invalid document Version 2.0.4 released 2008-10-24 * Fixes a parsing error in the C extension when the JSON document is (only) a floating point number. It would consume one too few characters in that case, and claim the document invalid. Version 2.0.3 released 2008-10-11 * Fixes reference leaks in the encoding speedups (sorry about that!) * Fixes doctest suite for Python 2.6 * More optimizations for the decoder Version 2.0.2 released 2008-10-06 * Fixes MSVC2003 build regression * Fixes Python 2.4 compatibility in _speedups.c Version 2.0.1 released 2008-09-29 * Fixes long encoding regression introduced in 2.0.0 * Fixes MinGW build regression introduced in 2.0.0 Version 2.0.0 released 2008-09-27 * optimized Python encoding path * optimized Python decoding path * optimized C encoding path * optimized C decoding path * switched to sphinx docs (nearly the same as the json module in python 2.6) Version 1.9.3 released 2008-09-23 * Decoding is significantly faster (for our internal benchmarks) * Pretty-printing tool changed from simplejson to simplejson.tool for better Python 2.6 comaptibility * Misc. bug fixes Version 1.9 released 2008-05-03 * Rewrote test suite with unittest and doctest (no more nosetest dependency) * Better PEP 7 and PEP 8 source compliance * Removed simplejson.jsonfilter demo module * simplejson.jsonfilter is no longer included Version 1.8.1 released 2008-03-24 * Optional C extension for accelerating the decoding of JSON strings * Command line interface for pretty-printing JSON (via python -msimplejson) * Decoding of integers and floats is now extensible (e.g. to use Decimal) via parse_int, parse_float options. * Subversion and issue tracker moved to google code: http://code.google.com/p/simplejson/ * "/" is no longer escaped, so if you're embedding JSON directly in HTML you'll want to use .replace("/", "\\/") to prevent a close-tag attack. Version 1.7 released 2007-03-18 * Improves encoding performance with an optional C extension to speed up str/unicode encoding (by 10-150x or so), which yields an overall speed boost of 2x+ (JSON is string-heavy). * Support for encoding unicode code points outside the BMP to UTF-16 surrogate code pairs (specified by the Strings section of RFC 4627). Version 1.6 released 2007-03-03 * Improved str support for encoding. Previous versions of simplejson integrated strings directly into the output stream, this version ensures they're of a particular encoding (default is UTF-8) so that the output stream is valid. Version 1.5 released 2007-01-18 * Better Python 2.5 compatibility * Better Windows compatibility * indent encoding parameter for pretty printing * separators encoding parameter for generating optimally compact JSON Version 1.3 released 2006-04-01 * The optional object_hook function is called upon decoding of any JSON object literal, and its return value is used instead of the dict that would normally be used. This can be used to efficiently implement features such as JSON-RPC class hinting, or other custom decodings of JSON. See the documentation for more information. Version 1.1 released 2005-12-31 * Renamed from simple_json to simplejson to comply with PEP 8 module naming guidelines * Full set of documentation * More tests * The encoder and decoder have been extended to understand NaN, Infinity, and -Infinity (but this can be turned off via allow_nan=False for strict JSON compliance) * The decoder's scanner has been fixed so that it no longer accepts invalid JSON documents * The decoder now reports line and column information as well as character numbers for easier debugging * The encoder now has a circular reference checker, which can be optionally disabled with check_circular=False * dump, dumps, load, loads now accept an optional cls kwarg to use an alternate JSONEncoder or JSONDecoder class for convenience. * The read/write compatibility shim for json-py now have deprecation warnings Version 1.0 released 2005-12-25 * Initial release simplejson-3.8.1/conf.py0000644000076500000240000001306112572353113015075 0ustar bobstaff00000000000000# -*- coding: utf-8 -*- # # simplejson documentation build configuration file, created by # sphinx-quickstart on Fri Sep 26 18:58:30 2008. # # This file is execfile()d with the current directory set to its containing dir. # # The contents of this file are pickled, so don't put values in the namespace # that aren't pickleable (module imports are okay, they're removed automatically). # # All configuration values have a default value; values that are commented out # serve to show the default value. import sys, os # If your extensions are in another directory, add it here. If the directory # is relative to the documentation root, use os.path.abspath to make it # absolute, like shown here. #sys.path.append(os.path.abspath('some/directory')) # General configuration # --------------------- # Add any Sphinx extension module names here, as strings. They can be extensions # coming with Sphinx (named 'sphinx.ext.*') or your custom ones. extensions = [] # Add any paths that contain templates here, relative to this directory. templates_path = ['_templates'] # The suffix of source filenames. source_suffix = '.rst' # The master toctree document. master_doc = 'index' # General substitutions. project = 'simplejson' copyright = '2015, Bob Ippolito' # The default replacements for |version| and |release|, also used in various # other places throughout the built documents. # # The short X.Y version. version = '3.8' # The full version, including alpha/beta/rc tags. release = '3.8.1' # There are two options for replacing |today|: either, you set today to some # non-false value, then it is used: #today = '' # Else, today_fmt is used as the format for a strftime call. today_fmt = '%B %d, %Y' # List of documents that shouldn't be included in the build. #unused_docs = [] # List of directories, relative to source directories, that shouldn't be searched # for source files. #exclude_dirs = [] # The reST default role (used for this markup: `text`) to use for all documents. #default_role = None # If true, '()' will be appended to :func: etc. cross-reference text. #add_function_parentheses = True # If true, the current module name will be prepended to all description # unit titles (such as .. function::). #add_module_names = True # If true, sectionauthor and moduleauthor directives will be shown in the # output. They are ignored by default. #show_authors = False # The name of the Pygments (syntax highlighting) style to use. pygments_style = 'sphinx' # Options for HTML output # ----------------------- # The style sheet to use for HTML and HTML Help pages. A file of that name # must exist either in Sphinx' static/ path, or in one of the custom paths # given in html_static_path. html_style = 'default.css' # The name for this set of Sphinx documents. If None, it defaults to # " v documentation". #html_title = None # A shorter title for the navigation bar. Default is the same as html_title. #html_short_title = None # The name of an image file (within the static path) to place at the top of # the sidebar. #html_logo = None # The name of an image file (within the static path) to use as favicon of the # docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32 # pixels large. #html_favicon = None # Add any paths that contain custom static files (such as style sheets) here, # relative to this directory. They are copied after the builtin static files, # so a file named "default.css" will overwrite the builtin "default.css". html_static_path = ['_static'] # If not '', a 'Last updated on:' timestamp is inserted at every page bottom, # using the given strftime format. html_last_updated_fmt = '%b %d, %Y' # If true, SmartyPants will be used to convert quotes and dashes to # typographically correct entities. #html_use_smartypants = True # Custom sidebar templates, maps document names to template names. #html_sidebars = {} # Additional templates that should be rendered to pages, maps page names to # template names. #html_additional_pages = {} # If false, no module index is generated. html_use_modindex = False # If false, no index is generated. #html_use_index = True # If true, the index is split into individual pages for each letter. #html_split_index = False # If true, the reST sources are included in the HTML build as _sources/. #html_copy_source = True # If true, an OpenSearch description file will be output, and all pages will # contain a tag referring to it. The value of this option must be the # base URL from which the finished HTML is served. #html_use_opensearch = '' # If nonempty, this is the file name suffix for HTML files (e.g. ".xhtml"). html_file_suffix = '.html' # Output file base name for HTML help builder. htmlhelp_basename = 'simplejsondoc' # Options for LaTeX output # ------------------------ # The paper size ('letter' or 'a4'). #latex_paper_size = 'letter' # The font size ('10pt', '11pt' or '12pt'). #latex_font_size = '10pt' # Grouping the document tree into LaTeX files. List of tuples # (source start file, target name, title, author, document class [howto/manual]). latex_documents = [ ('index', 'simplejson.tex', 'simplejson Documentation', 'Bob Ippolito', 'manual'), ] # The name of an image file (relative to this directory) to place at the top of # the title page. #latex_logo = None # For "manual" documents, if this is true, then toplevel headings are parts, # not chapters. #latex_use_parts = False # Additional stuff for the LaTeX preamble. #latex_preamble = '' # Documents to append as an appendix to all manuals. #latex_appendices = [] # If false, no module index is generated. #latex_use_modindex = True simplejson-3.8.1/index.rst0000644000076500000240000011541412552544500015444 0ustar bobstaff00000000000000:mod:`simplejson` --- JSON encoder and decoder ============================================== .. module:: simplejson :synopsis: Encode and decode the JSON format. .. moduleauthor:: Bob Ippolito .. sectionauthor:: Bob Ippolito `JSON (JavaScript Object Notation) `_, specified by :rfc:`7159` (which obsoletes :rfc:`4627`) and by `ECMA-404 `_, is a lightweight data interchange format inspired by `JavaScript `_ object literal syntax (although it is not a strict subset of JavaScript [#rfc-errata]_ ). :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 2.5 and (currently) has significant performance advantages, even without using the optional C extension for speedups. :mod:`simplejson` is also supported on Python 3.3+. Development of simplejson happens on Github: http://github.com/simplejson/simplejson Encoding basic Python object hierarchies:: >>> import simplejson as json >>> json.dumps(['foo', {'bar': ('baz', None, 1.0, 2)}]) '["foo", {"bar": ["baz", null, 1.0, 2]}]' >>> print(json.dumps("\"foo\bar")) "\"foo\bar" >>> print(json.dumps(u'\u1234')) "\u1234" >>> print(json.dumps('\\')) "\\" >>> print(json.dumps({"c": 0, "b": 0, "a": 0}, sort_keys=True)) {"a": 0, "b": 0, "c": 0} >>> from simplejson.compat import StringIO >>> io = StringIO() >>> json.dump(['streaming API'], io) >>> io.getvalue() '["streaming API"]' Compact encoding:: >>> import simplejson as json >>> obj = [1,2,3,{'4': 5, '6': 7}] >>> json.dumps(obj, separators=(',', ':'), sort_keys=True) '[1,2,3,{"4":5,"6":7}]' Pretty printing:: >>> import simplejson as json >>> print(json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=4 * ' ')) { "4": 5, "6": 7 } Decoding JSON:: >>> 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 simplejson.compat import StringIO >>> io = StringIO('["streaming API"]') >>> json.load(io)[0] == 'streaming API' True Using Decimal instead of float:: >>> import simplejson as json >>> from decimal import Decimal >>> json.loads('1.1', use_decimal=True) == Decimal('1.1') True >>> json.dumps(Decimal('1.1'), use_decimal=True) == '1.1' True Specializing JSON object decoding:: >>> import simplejson as json >>> def as_complex(dct): ... if '__complex__' in dct: ... return complex(dct['real'], dct['imag']) ... return dct ... >>> 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 Specializing JSON object encoding:: >>> import simplejson as json >>> def encode_complex(obj): ... if isinstance(obj, complex): ... return [obj.real, obj.imag] ... raise TypeError(repr(obj) + " is not JSON serializable") ... >>> json.dumps(2 + 1j, default=encode_complex) '[2.0, 1.0]' >>> json.JSONEncoder(default=encode_complex).encode(2 + 1j) '[2.0, 1.0]' >>> ''.join(json.JSONEncoder(default=encode_complex).iterencode(2 + 1j)) '[2.0, 1.0]' .. highlight:: bash Using :mod:`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 enclosed in double quotes: line 1 column 3 (char 2) .. highlight:: python .. note:: JSON is a subset of `YAML `_ 1.2. The JSON produced by this module's default settings (in particular, the default *separators* value) is also a subset of YAML 1.0 and 1.1. This module can thus also be used as a YAML serializer. Basic Usage ----------- .. function:: dump(obj, fp, skipkeys=False, ensure_ascii=True, \ check_circular=True, allow_nan=True, cls=None, \ indent=None, separators=None, encoding='utf-8', \ default=None, use_decimal=True, \ namedtuple_as_object=True, tuple_as_array=True, \ bigint_as_string=False, sort_keys=False, \ item_sort_key=None, for_json=None, ignore_nan=False, \ int_as_string_bitcount=None, iterable_as_array=False, **kw) Serialize *obj* as a JSON formatted stream to *fp* (a ``.write()``-supporting file-like object) using this :ref:`conversion table `. If *skipkeys* is true (default: ``False``), then dict keys that are not of a basic type (:class:`str`, :class:`unicode`, :class:`int`, :class:`long`, :class:`float`, :class:`bool`, ``None``) will be skipped instead of raising a :exc:`TypeError`. The :mod:`simplejson` module will produce :class:`str` objects in Python 3, not :class:`bytes` objects. Therefore, ``fp.write()`` must support :class:`str` input. If *ensure_ascii* is false (default: ``True``), then some chunks written to *fp* may be :class:`unicode` instances, subject to normal Python :class:`str` to :class:`unicode` coercion rules. Unless ``fp.write()`` explicitly understands :class:`unicode` (as in :func:`codecs.getwriter`) this is likely to cause an error. It's best to leave the default settings, because they are safe and it is highly optimized. If *check_circular* is false (default: ``True``), then the circular reference check for container types will be skipped and a circular reference will result in an :exc:`OverflowError` (or worse). If *allow_nan* is false (default: ``True``), then it will be a :exc:`ValueError` to serialize out of range :class:`float` values (``nan``, ``inf``, ``-inf``) in strict compliance of the original JSON specification. If *allow_nan* is true, their JavaScript equivalents will be used (``NaN``, ``Infinity``, ``-Infinity``). See also *ignore_nan* for ECMA-262 compliant behavior. If *indent* is a string, then JSON array elements and object members will be pretty-printed with a newline followed by that string repeated for each level of nesting. ``None`` (the default) selects the most compact representation without any newlines. For backwards compatibility with versions of simplejson earlier than 2.1.0, an integer is also accepted and is converted to a string with that many spaces. .. versionchanged:: 2.1.0 Changed *indent* from an integer number of spaces to a string. If specified, *separators* should be an ``(item_separator, key_separator)`` tuple. The default is ``(', ', ': ')`` if *indent* is ``None`` and ``(',', ': ')`` otherwise. To get the most compact JSON representation, you should specify ``(',', ':')`` to eliminate whitespace. .. versionchanged:: 2.1.4 Use ``(',', ': ')`` as default if *indent* is not ``None``. *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 :exc:`TypeError`. The default simply raises :exc:`TypeError`. To use a custom :class:`JSONEncoder` subclass (e.g. one that overrides the :meth:`default` method to serialize additional types), specify it with the *cls* kwarg. .. note:: Subclassing is not recommended. Use the *default* kwarg or *for_json* instead. This is faster and more portable. If *use_decimal* is true (default: ``True``) then :class:`decimal.Decimal` will be natively serialized to JSON with full precision. .. versionchanged:: 2.1.0 *use_decimal* is new in 2.1.0. .. versionchanged:: 2.2.0 The default of *use_decimal* changed to ``True`` in 2.2.0. If *namedtuple_as_object* is true (default: ``True``), objects with ``_asdict()`` methods will be encoded as JSON objects. .. versionchanged:: 2.2.0 *namedtuple_as_object* is new in 2.2.0. .. versionchanged:: 2.3.0 *namedtuple_as_object* no longer requires that these objects be subclasses of :class:`tuple`. If *tuple_as_array* is true (default: ``True``), :class:`tuple` (and subclasses) will be encoded as JSON arrays. If *iterable_as_array* is true (default: ``False``), any object not in the above table that implements ``__iter__()`` will be encoded as a JSON array. .. versionchanged:: 3.8.0 *iterable_as_array* is new in 3.8.0. .. versionchanged:: 2.2.0 *tuple_as_array* is new in 2.2.0. If *bigint_as_string* is true (default: ``False``), :class:`int` ``2**53`` and higher or lower than ``-2**53`` will be encoded as strings. This is to avoid the rounding that happens in Javascript otherwise. Note that this option loses type information, so use with extreme caution. See also *int_as_string_bitcount*. .. versionchanged:: 2.4.0 *bigint_as_string* is new in 2.4.0. If *sort_keys* is true (not the default), 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. .. versionchanged:: 3.0.0 Sorting now happens after the keys have been coerced to strings, to avoid comparison of heterogeneously typed objects (since this does not work in Python 3.3+) If *item_sort_key* is a callable (not the default), then the output of dictionaries will be sorted with it. The callable will be used like this: ``sorted(dct.items(), key=item_sort_key)``. This option takes precedence over *sort_keys*. .. versionchanged:: 2.5.0 *item_sort_key* is new in 2.5.0. .. versionchanged:: 3.0.0 Sorting now happens after the keys have been coerced to strings, to avoid comparison of heterogeneously typed objects (since this does not work in Python 3.3+) If *for_json* is true (not the default), objects with a ``for_json()`` method will use the return value of that method for encoding as JSON instead of the object. .. versionchanged:: 3.2.0 *for_json* is new in 3.2.0. If *ignore_nan* is true (default: ``False``), then out of range :class:`float` values (``nan``, ``inf``, ``-inf``) will be serialized as ``null`` in compliance with the ECMA-262 specification. If true, this will override *allow_nan*. .. versionchanged:: 3.2.0 *ignore_nan* is new in 3.2.0. If *int_as_string_bitcount* is a positive number ``n`` (default: ``None``), :class:`int` ``2**n`` and higher or lower than ``-2**n`` will be encoded as strings. This is to avoid the rounding that happens in Javascript otherwise. Note that this option loses type information, so use with extreme caution. See also *bigint_as_string* (which is equivalent to `int_as_string_bitcount=53`). .. versionchanged:: 3.5.0 *int_as_string_bitcount* is new in 3.5.0. .. note:: JSON is not a framed protocol so unlike :mod:`pickle` or :mod:`marshal` it does not make sense to serialize more than one JSON document without some container protocol to delimit them. .. function:: dumps(obj, skipkeys=False, ensure_ascii=True, \ check_circular=True, allow_nan=True, cls=None, \ indent=None, separators=None, encoding='utf-8', \ default=None, use_decimal=True, \ namedtuple_as_object=True, tuple_as_array=True, \ bigint_as_string=False, sort_keys=False, \ item_sort_key=None, for_json=None, ignore_nan=False, \ int_as_string_bitcount=None, iterable_as_array=False, **kw) Serialize *obj* to a JSON formatted :class:`str`. If *ensure_ascii* is false, then the return value will be a :class:`unicode` instance. The other arguments have the same meaning as in :func:`dump`. Note that the default *ensure_ascii* setting has much better performance in Python 2. The other options have the same meaning as in :func:`dump`. .. function:: load(fp, encoding='utf-8', cls=None, object_hook=None, \ parse_float=None, parse_int=None, \ parse_constant=None, object_pairs_hook=None, \ use_decimal=None, **kw) Deserialize *fp* (a ``.read()``-supporting file-like object containing a JSON document) to a Python object using this :ref:`conversion table `. :exc:`JSONDecodeError` will be raised if the given JSON document is not valid. If the contents of *fp* are 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 :class:`unicode` object and passed to :func:`loads`. The default setting of ``'utf-8'`` is fastest and should be using whenever possible. If *fp.read()* returns :class:`str` then decoded JSON strings that contain only ASCII characters may be parsed as :class:`str` for performance and memory reasons. If your code expects only :class:`unicode` the appropriate solution is to wrap fp with a reader as demonstrated above. *object_hook* is an optional function that will be called with the result of any object literal decode (a :class:`dict`). The return value of *object_hook* will be used instead of the :class:`dict`. This feature can be used to implement custom decoders (e.g. `JSON-RPC `_ class hinting). *object_pairs_hook* is an optional function that will be called with the result of any object literal decode with an ordered list of pairs. The return value of *object_pairs_hook* will be used instead of the :class:`dict`. This feature can be used to implement custom decoders that rely on the order that the key and value pairs are decoded (for example, :class:`collections.OrderedDict` will remember the order of insertion). If *object_hook* is also defined, the *object_pairs_hook* takes priority. .. versionchanged:: 2.1.0 Added support for *object_pairs_hook*. *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. :class:`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. :class:`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. If *use_decimal* is true (default: ``False``) then *parse_float* is set to :class:`decimal.Decimal`. This is a convenience for parity with the :func:`dump` parameter. .. versionchanged:: 2.1.0 *use_decimal* is new in 2.1.0. If *iterable_as_array* is true (default: ``False``), any object not in the above table that implements ``__iter__()`` will be encoded as a JSON array. .. versionchanged:: 3.8.0 *iterable_as_array* is new in 3.8.0. To use a custom :class:`JSONDecoder` subclass, specify it with the ``cls`` kwarg. Additional keyword arguments will be passed to the constructor of the class. You probably shouldn't do this. .. note:: Subclassing is not recommended. You should use *object_hook* or *object_pairs_hook*. This is faster and more portable than subclassing. .. note:: :func:`load` will read the rest of the file-like object as a string and then call :func:`loads`. It does not stop at the end of the first valid JSON document it finds and it will raise an error if there is anything other than whitespace after the document. Except for files containing only one JSON document, it is recommended to use :func:`loads`. .. function:: loads(fp, encoding='utf-8', cls=None, object_hook=None, \ parse_float=None, parse_int=None, \ parse_constant=None, object_pairs_hook=None, \ use_decimal=None, **kw) Deserialize *s* (a :class:`str` or :class:`unicode` instance containing a JSON document) to a Python object. :exc:`JSONDecodeError` will be raised if the given JSON document is not valid. If *s* is a :class:`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 :class:`unicode` first. If *s* is a :class:`str` then decoded JSON strings that contain only ASCII characters may be parsed as :class:`str` for performance and memory reasons. If your code expects only :class:`unicode` the appropriate solution is decode *s* to :class:`unicode` prior to calling loads. The other arguments have the same meaning as in :func:`load`. Encoders and decoders --------------------- .. class:: JSONDecoder(encoding='utf-8', object_hook=None, parse_float=None, \ parse_int=None, parse_constant=None, \ object_pairs_hook=None, strict=True) Simple JSON decoder. Performs the following translations in decoding by default: .. _json-to-py-table: +---------------+-----------+-----------+ | JSON | Python 2 | Python 3 | +===============+===========+===========+ | object | dict | dict | +---------------+-----------+-----------+ | array | list | list | +---------------+-----------+-----------+ | string | unicode | str | +---------------+-----------+-----------+ | number (int) | int, long | int | +---------------+-----------+-----------+ | number (real) | float | float | +---------------+-----------+-----------+ | true | True | True | +---------------+-----------+-----------+ | false | False | False | +---------------+-----------+-----------+ | null | None | None | +---------------+-----------+-----------+ It also understands ``NaN``, ``Infinity``, and ``-Infinity`` as their corresponding ``float`` values, which is outside the JSON spec. *encoding* determines the encoding used to interpret any :class:`str` objects decoded by this instance (``'utf-8'`` by default). It has no effect when decoding :class:`unicode` objects. Note that currently only encodings that are a superset of ASCII work, strings of other encodings should be passed in as :class:`unicode`. *object_hook* is an optional function that will be called with the result of every JSON object decoded and its return value will be used in place of the given :class:`dict`. This can be used to provide custom deserializations (e.g. to support JSON-RPC class hinting). *object_pairs_hook* is an optional function that will be called with the result of any object literal decode with an ordered list of pairs. The return value of *object_pairs_hook* will be used instead of the :class:`dict`. This feature can be used to implement custom decoders that rely on the order that the key and value pairs are decoded (for example, :class:`collections.OrderedDict` will remember the order of insertion). If *object_hook* is also defined, the *object_pairs_hook* takes priority. .. versionchanged:: 2.1.0 Added support for *object_pairs_hook*. *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. :class:`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. :class:`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. *strict* controls the parser's behavior when it encounters an invalid control character in a string. The default setting of ``True`` means that unescaped control characters are parse errors, if ``False`` then control characters will be allowed in strings. .. method:: decode(s) Return the Python representation of *s* (a :class:`str` or :class:`unicode` instance containing a JSON document) If *s* is a :class:`str` then decoded JSON strings that contain only ASCII characters may be parsed as :class:`str` for performance and memory reasons. If your code expects only :class:`unicode` the appropriate solution is decode *s* to :class:`unicode` prior to calling decode. :exc:`JSONDecodeError` will be raised if the given JSON document is not valid. .. method:: raw_decode(s[, idx=0]) Decode a JSON document from *s* (a :class:`str` or :class:`unicode` beginning with a JSON document) starting from the index *idx* 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, or to decode a string that has a series of JSON objects. :exc:`JSONDecodeError` will be raised if the given JSON document is not valid. .. class:: JSONEncoder(skipkeys=False, ensure_ascii=True, \ check_circular=True, allow_nan=True, sort_keys=False, \ indent=None, separators=None, encoding='utf-8', \ default=None, use_decimal=True, \ namedtuple_as_object=True, tuple_as_array=True, \ bigint_as_string=False, item_sort_key=None, \ for_json=True, ignore_nan=False, \ int_as_string_bitcount=None, iterable_as_array=False) Extensible JSON encoder for Python data structures. Supports the following objects and types by default: .. _py-to-json-table: +-------------------+---------------+ | Python | JSON | +===================+===============+ | dict, namedtuple | object | +-------------------+---------------+ | list, tuple | array | +-------------------+---------------+ | str, unicode | string | +-------------------+---------------+ | int, long, float | number | +-------------------+---------------+ | True | true | +-------------------+---------------+ | False | false | +-------------------+---------------+ | None | null | +-------------------+---------------+ .. note:: The JSON format only permits strings to be used as object keys, thus any Python dicts to be encoded should only have string keys. For backwards compatibility, several other types are automatically coerced to strings: int, long, float, Decimal, bool, and None. It is error-prone to rely on this behavior, so avoid it when possible. Dictionaries with other types used as keys should be pre-processed or wrapped in another type with an appropriate `for_json` method to transform the keys during encoding. It also understands ``NaN``, ``Infinity``, and ``-Infinity`` as their corresponding ``float`` values, which is outside the JSON spec. .. versionchanged:: 2.2.0 Changed *namedtuple* encoding from JSON array to object. To extend this to recognize other objects, subclass and implement a :meth:`default` method with another method that returns a serializable object for ``o`` if possible, otherwise it should call the superclass implementation (to raise :exc:`TypeError`). .. note:: Subclassing is not recommended. You should use the *default* or *for_json* kwarg. This is faster and more portable than subclassing. If *skipkeys* is false (the default), then it is a :exc:`TypeError` to attempt encoding of keys that are not str, int, long, float, Decimal, bool, or None. If *skipkeys* is true, such items are simply skipped. If *ensure_ascii* is true (the default), the output is guaranteed to be :class:`str` objects with all incoming unicode characters escaped. If *ensure_ascii* is false, the output will be a unicode object. If *check_circular* is true (the default), then lists, dicts, and custom encoded objects will be checked for circular references during encoding to prevent an infinite recursion (which would cause an :exc:`OverflowError`). Otherwise, no such check takes place. If *allow_nan* is true (the default), 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 :exc:`ValueError` to encode such floats. See also *ignore_nan* for ECMA-262 compliant behavior. If *sort_keys* is true (not the default), 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. .. versionchanged:: 3.0.0 Sorting now happens after the keys have been coerced to strings, to avoid comparison of heterogeneously typed objects (since this does not work in Python 3.3+) If *item_sort_key* is a callable (not the default), then the output of dictionaries will be sorted with it. The callable will be used like this: ``sorted(dct.items(), key=item_sort_key)``. This option takes precedence over *sort_keys*. .. versionchanged:: 2.5.0 *item_sort_key* is new in 2.5.0. .. versionchanged:: 3.0.0 Sorting now happens after the keys have been coerced to strings, to avoid comparison of heterogeneously typed objects (since this does not work in Python 3.3+) If *indent* is a string, then JSON array elements and object members will be pretty-printed with a newline followed by that string repeated for each level of nesting. ``None`` (the default) selects the most compact representation without any newlines. For backwards compatibility with versions of simplejson earlier than 2.1.0, an integer is also accepted and is converted to a string with that many spaces. .. versionchanged:: 2.1.0 Changed *indent* from an integer number of spaces to a string. If specified, *separators* should be an ``(item_separator, key_separator)`` tuple. The default is ``(', ', ': ')`` if *indent* is ``None`` and ``(',', ': ')`` otherwise. To get the most compact JSON representation, you should specify ``(',', ':')`` to eliminate whitespace. .. versionchanged:: 2.1.4 Use ``(',', ': ')`` as default if *indent* is not ``None``. If specified, *default* should be 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 :exc:`TypeError`. 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'``. If *namedtuple_as_object* is true (default: ``True``), objects with ``_asdict()`` methods will be encoded as JSON objects. .. versionchanged:: 2.2.0 *namedtuple_as_object* is new in 2.2.0. .. versionchanged:: 2.3.0 *namedtuple_as_object* no longer requires that these objects be subclasses of :class:`tuple`. If *tuple_as_array* is true (default: ``True``), :class:`tuple` (and subclasses) will be encoded as JSON arrays. .. versionchanged:: 2.2.0 *tuple_as_array* is new in 2.2.0. If *iterable_as_array* is true (default: ``False``), any object not in the above table that implements ``__iter__()`` will be encoded as a JSON array. .. versionchanged:: 3.8.0 *iterable_as_array* is new in 3.8.0. If *bigint_as_string* is true (default: ``False``), :class:`int`` ``2**53`` and higher or lower than ``-2**53`` will be encoded as strings. This is to avoid the rounding that happens in Javascript otherwise. Note that this option loses type information, so use with extreme caution. .. versionchanged:: 2.4.0 *bigint_as_string* is new in 2.4.0. If *for_json* is true (default: ``False``), objects with a ``for_json()`` method will use the return value of that method for encoding as JSON instead of the object. .. versionchanged:: 3.2.0 *for_json* is new in 3.2.0. If *ignore_nan* is true (default: ``False``), then out of range :class:`float` values (``nan``, ``inf``, ``-inf``) will be serialized as ``null`` in compliance with the ECMA-262 specification. If true, this will override *allow_nan*. .. versionchanged:: 3.2.0 *ignore_nan* is new in 3.2.0. .. method:: default(o) Implement this method in a subclass such that it returns a serializable object for *o*, or calls the base implementation (to raise a :exc:`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) .. note:: Subclassing is not recommended. You should implement this as a function and pass it to the *default* kwarg of :func:`dumps`. This is faster and more portable than subclassing. The semantics are the same, but without the self argument or the call to the super implementation. .. method:: encode(o) Return a JSON string representation of a Python data structure, *o*. For example:: >>> import simplejson as json >>> json.JSONEncoder().encode({"foo": ["bar", "baz"]}) '{"foo": ["bar", "baz"]}' .. method:: iterencode(o) Encode the given object, *o*, and yield each string representation as available. For example:: for chunk in JSONEncoder().iterencode(bigobject): mysocket.write(chunk) Note that :meth:`encode` has much better performance than :meth:`iterencode`. .. class:: JSONEncoderForHTML(skipkeys=False, ensure_ascii=True, \ check_circular=True, allow_nan=True, \ sort_keys=False, indent=None, separators=None, \ encoding='utf-8', \ default=None, use_decimal=True, \ namedtuple_as_object=True, \ tuple_as_array=True, \ bigint_as_string=False, item_sort_key=None, \ for_json=True, ignore_nan=False, \ int_as_string_bitcount=None) Subclass of :class:`JSONEncoder` that escapes &, <, and > for embedding in HTML. .. versionchanged:: 2.1.0 New in 2.1.0 Exceptions ---------- .. exception:: JSONDecodeError(msg, doc, pos, end=None) Subclass of :exc:`ValueError` with the following additional attributes: .. attribute:: msg The unformatted error message .. attribute:: doc The JSON document being parsed .. attribute:: pos The start index of doc where parsing failed .. attribute:: end The end index of doc where parsing failed (may be ``None``) .. attribute:: lineno The line corresponding to pos .. attribute:: colno The column corresponding to pos .. attribute:: endlineno The line corresponding to end (may be ``None``) .. attribute:: endcolno The column corresponding to end (may be ``None``) Standard Compliance and Interoperability ---------------------------------------- The JSON format is specified by :rfc:`7159` and by `ECMA-404 `_. This section details this module's level of compliance with the RFC. For simplicity, :class:`JSONEncoder` and :class:`JSONDecoder` subclasses, and parameters other than those explicitly mentioned, are not considered. This module does not comply with the RFC in a strict fashion, implementing some extensions that are valid JavaScript but not valid JSON. In particular: - Infinite and NaN number values are accepted and output; - Repeated names within an object are accepted, and only the value of the last name-value pair is used. Since the RFC permits RFC-compliant parsers to accept input texts that are not RFC-compliant, this module's deserializer is technically RFC-compliant under default settings. Character Encodings ^^^^^^^^^^^^^^^^^^^ The RFC recommends that JSON be represented using either UTF-8, UTF-16, or UTF-32, with UTF-8 being the recommended default for maximum interoperability. As permitted, though not required, by the RFC, this module's serializer sets *ensure_ascii=True* by default, thus escaping the output so that the resulting strings only contain ASCII characters. Other than the *ensure_ascii* parameter, this module is defined strictly in terms of conversion between Python objects and :class:`Unicode strings `, and thus does not otherwise directly address the issue of character encodings. The RFC prohibits adding a byte order mark (BOM) to the start of a JSON text, and this module's serializer does not add a BOM to its output. The RFC permits, but does not require, JSON deserializers to ignore an initial BOM in their input. This module's deserializer will ignore an initial BOM, if present. .. versionchanged:: 3.6.0 Older versions would raise :exc:`ValueError` when an initial BOM is present The RFC does not explicitly forbid JSON strings which contain byte sequences that don't correspond to valid Unicode characters (e.g. unpaired UTF-16 surrogates), but it does note that they may cause interoperability problems. By default, this module accepts and outputs (when present in the original :class:`str`) codepoints for such sequences. Infinite and NaN Number Values ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ The RFC does not permit the representation of infinite or NaN number values. Despite that, by default, this module accepts and outputs ``Infinity``, ``-Infinity``, and ``NaN`` as if they were valid JSON number literal values:: >>> # Neither of these calls raises an exception, but the results are not valid JSON >>> json.dumps(float('-inf')) '-Infinity' >>> json.dumps(float('nan')) 'NaN' >>> # Same when deserializing >>> json.loads('-Infinity') -inf >>> json.loads('NaN') nan In the serializer, the *allow_nan* parameter can be used to alter this behavior. In the deserializer, the *parse_constant* parameter can be used to alter this behavior. Repeated Names Within an Object ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ The RFC specifies that the names within a JSON object should be unique, but does not mandate how repeated names in JSON objects should be handled. By default, this module does not raise an exception; instead, it ignores all but the last name-value pair for a given name:: >>> weird_json = '{"x": 1, "x": 2, "x": 3}' >>> json.loads(weird_json) == {'x': 3} True The *object_pairs_hook* parameter can be used to alter this behavior. Top-level Non-Object, Non-Array Values ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ The old version of JSON specified by the obsolete :rfc:`4627` required that the top-level value of a JSON text must be either a JSON object or array (Python :class:`dict` or :class:`list`), and could not be a JSON null, boolean, number, or string value. :rfc:`7159` removed that restriction, and this module does not and has never implemented that restriction in either its serializer or its deserializer. Regardless, for maximum interoperability, you may wish to voluntarily adhere to the restriction yourself. Implementation Limitations ^^^^^^^^^^^^^^^^^^^^^^^^^^ Some JSON deserializer implementations may set limits on: * the size of accepted JSON texts * the maximum level of nesting of JSON objects and arrays * the range and precision of JSON numbers * the content and maximum length of JSON strings This module does not impose any such limits beyond those of the relevant Python datatypes themselves or the Python interpreter itself. When serializing to JSON, beware any such limitations in applications that may consume your JSON. In particular, it is common for JSON numbers to be deserialized into IEEE 754 double precision numbers and thus subject to that representation's range and precision limitations. This is especially relevant when serializing Python :class:`int` values of extremely large magnitude, or when serializing instances of "exotic" numerical types such as :class:`decimal.Decimal`. .. highlight:: bash .. _json-commandline: Command Line Interface ---------------------- The :mod:`simplejson.tool` module provides a simple command line interface to validate and pretty-print JSON. If the optional :option:`infile` and :option:`outfile` arguments are not specified, :attr:`sys.stdin` and :attr:`sys.stdout` will be used respectively:: $ echo '{"json": "obj"}' | python -m simplejson.tool { "json": "obj" } $ echo '{1.2:3.4}' | python -m simplejson.tool Expecting property name enclosed in double quotes: line 1 column 2 (char 1) Command line options ^^^^^^^^^^^^^^^^^^^^ .. cmdoption:: infile The JSON file to be validated or pretty-printed:: $ python -m simplejson.tool mp_films.json [ { "title": "And Now for Something Completely Different", "year": 1971 }, { "title": "Monty Python and the Holy Grail", "year": 1975 } ] If *infile* is not specified, read from :attr:`sys.stdin`. .. cmdoption:: outfile Write the output of the *infile* to the given *outfile*. Otherwise, write it to :attr:`sys.stdout`. .. rubric:: Footnotes .. [#rfc-errata] As noted in `the errata for RFC 7159 `_, JSON permits literal U+2028 (LINE SEPARATOR) and U+2029 (PARAGRAPH SEPARATOR) characters in strings, whereas JavaScript (as of ECMAScript Edition 5.1) does not. simplejson-3.8.1/LICENSE.txt0000644000076500000240000002420712363544726015437 0ustar bobstaff00000000000000simplejson is dual-licensed software. It is available under the terms of the MIT license, or the Academic Free License version 2.1. The full text of each license agreement is included below. This code is also licensed to the Python Software Foundation (PSF) under a Contributor Agreement. MIT License =========== 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. Academic Free License v. 2.1 ============================ Copyright (c) 2006 Bob Ippolito. All rights reserved. This Academic Free License (the "License") applies to any original work of authorship (the "Original Work") whose owner (the "Licensor") has placed the following notice immediately following the copyright notice for the Original Work: Licensed under the Academic Free License version 2.1 1) Grant of Copyright License. Licensor hereby grants You a world-wide, royalty-free, non-exclusive, perpetual, sublicenseable license to do the following: a) to reproduce the Original Work in copies; b) to prepare derivative works ("Derivative Works") based upon the Original Work; c) to distribute copies of the Original Work and Derivative Works to the public; d) to perform the Original Work publicly; and e) to display the Original Work publicly. 2) Grant of Patent License. Licensor hereby grants You a world-wide, royalty-free, non-exclusive, perpetual, sublicenseable license, under patent claims owned or controlled by the Licensor that are embodied in the Original Work as furnished by the Licensor, to make, use, sell and offer for sale the Original Work and Derivative Works. 3) Grant of Source Code License. The term "Source Code" means the preferred form of the Original Work for making modifications to it and all available documentation describing how to modify the Original Work. Licensor hereby agrees to provide a machine-readable copy of the Source Code of the Original Work along with each copy of the Original Work that Licensor distributes. Licensor reserves the right to satisfy this obligation by placing a machine-readable copy of the Source Code in an information repository reasonably calculated to permit inexpensive and convenient access by You for as long as Licensor continues to distribute the Original Work, and by publishing the address of that information repository in a notice immediately following the copyright notice that applies to the Original Work. 4) Exclusions From License Grant. Neither the names of Licensor, nor the names of any contributors to the Original Work, nor any of their trademarks or service marks, may be used to endorse or promote products derived from this Original Work without express prior written permission of the Licensor. Nothing in this License shall be deemed to grant any rights to trademarks, copyrights, patents, trade secrets or any other intellectual property of Licensor except as expressly stated herein. No patent license is granted to make, use, sell or offer to sell embodiments of any patent claims other than the licensed claims defined in Section 2. No right is granted to the trademarks of Licensor even if such marks are included in the Original Work. Nothing in this License shall be interpreted to prohibit Licensor from licensing under different terms from this License any Original Work that Licensor otherwise would have a right to license. 5) This section intentionally omitted. 6) Attribution Rights. You must retain, in the Source Code of any Derivative Works that You create, all copyright, patent or trademark notices from the Source Code of the Original Work, as well as any notices of licensing and any descriptive text identified therein as an "Attribution Notice." You must cause the Source Code for any Derivative Works that You create to carry a prominent Attribution Notice reasonably calculated to inform recipients that You have modified the Original Work. 7) Warranty of Provenance and Disclaimer of Warranty. Licensor warrants that the copyright in and to the Original Work and the patent rights granted herein by Licensor are owned by the Licensor or are sublicensed to You under the terms of this License with the permission of the contributor(s) of those copyrights and patent rights. Except as expressly stated in the immediately proceeding sentence, the Original Work is provided under this License on an "AS IS" BASIS and WITHOUT WARRANTY, either express or implied, including, without limitation, the warranties of NON-INFRINGEMENT, MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY OF THE ORIGINAL WORK IS WITH YOU. This DISCLAIMER OF WARRANTY constitutes an essential part of this License. No license to Original Work is granted hereunder except under this disclaimer. 8) Limitation of Liability. Under no circumstances and under no legal theory, whether in tort (including negligence), contract, or otherwise, shall the Licensor be liable to any person for any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or the use of the Original Work including, without limitation, damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses. This limitation of liability shall not apply to liability for death or personal injury resulting from Licensor's negligence to the extent applicable law prohibits such limitation. Some jurisdictions do not allow the exclusion or limitation of incidental or consequential damages, so this exclusion and limitation may not apply to You. 9) Acceptance and Termination. If You distribute copies of the Original Work or a Derivative Work, You must make a reasonable effort under the circumstances to obtain the express assent of recipients to the terms of this License. Nothing else but this License (or another written agreement between Licensor and You) grants You permission to create Derivative Works based upon the Original Work or to exercise any of the rights granted in Section 1 herein, and any attempt to do so except under the terms of this License (or another written agreement between Licensor and You) is expressly prohibited by U.S. copyright law, the equivalent laws of other countries, and by international treaty. Therefore, by exercising any of the rights granted to You in Section 1 herein, You indicate Your acceptance of this License and all of its terms and conditions. 10) Termination for Patent Action. This License shall terminate automatically and You may no longer exercise any of the rights granted to You by this License as of the date You commence an action, including a cross-claim or counterclaim, against Licensor or any licensee alleging that the Original Work infringes a patent. This termination provision shall not apply for an action alleging patent infringement by combinations of the Original Work with other software or hardware. 11) Jurisdiction, Venue and Governing Law. Any action or suit relating to this License may be brought only in the courts of a jurisdiction wherein the Licensor resides or in which Licensor conducts its primary business, and under the laws of that jurisdiction excluding its conflict-of-law provisions. The application of the United Nations Convention on Contracts for the International Sale of Goods is expressly excluded. Any use of the Original Work outside the scope of this License or after its termination shall be subject to the requirements and penalties of the U.S. Copyright Act, 17 U.S.C. § 101 et seq., the equivalent laws of other countries, and international treaty. This section shall survive the termination of this License. 12) Attorneys Fees. In any action to enforce the terms of this License or seeking damages relating thereto, the prevailing party shall be entitled to recover its costs and expenses, including, without limitation, reasonable attorneys' fees and costs incurred in connection with such action, including any appeal of such action. This section shall survive the termination of this License. 13) Miscellaneous. This License represents the complete agreement concerning the subject matter hereof. If any provision of this License is held to be unenforceable, such provision shall be reformed only to the extent necessary to make it enforceable. 14) Definition of "You" in This License. "You" throughout this License, whether in upper or lower case, means an individual or a legal entity exercising rights under, and complying with all of the terms of, this License. For legal entities, "You" includes any entity that controls, is controlled by, or is under common control with you. For purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity. 15) Right to Use. You may use the Original Work in all ways not otherwise restricted or conditioned by this License or by law, and Licensor promises not to interfere with or be responsible for such uses by You. This license is Copyright (C) 2003-2004 Lawrence E. Rosen. All rights reserved. Permission is hereby granted to copy and distribute this license without modification. This license may not be modified without the express written permission of its copyright owner. simplejson-3.8.1/MANIFEST.in0000644000076500000240000000012212363544726015340 0ustar bobstaff00000000000000include *.py include *.txt include *.rst include scripts/*.py include MANIFEST.in simplejson-3.8.1/PKG-INFO0000644000076500000240000000525712613714404014703 0ustar bobstaff00000000000000Metadata-Version: 1.1 Name: simplejson Version: 3.8.1 Summary: Simple, fast, extensible JSON encoder/decoder for Python Home-page: http://github.com/simplejson/simplejson Author: Bob Ippolito Author-email: bob@redivi.com License: MIT License Description: simplejson is a simple, fast, complete, correct and extensible JSON encoder and decoder for Python 2.5+ and Python 3.3+. It is pure Python code with no dependencies, but includes an optional C extension for a serious speed boost. The latest documentation for simplejson can be read online here: http://simplejson.readthedocs.org/ simplejson is the externally maintained development version of the json library included with Python 2.6 and Python 3.0, but maintains backwards compatibility with Python 2.5. The encoder can be specialized to provide serialization in any kind of situation, without any special support by the objects to be serialized (somewhat like pickle). This is best done with the ``default`` kwarg to dumps. The decoder can handle incoming JSON strings of any specified encoding (UTF-8 by default). It can also be specialized to post-process JSON objects with the ``object_hook`` or ``object_pairs_hook`` kwargs. This is particularly useful for implementing protocols such as JSON-RPC that have a richer type system than JSON itself. For those of you that have legacy systems to maintain, there is a very old fork of simplejson in the `python2.2`_ branch that supports Python 2.2. This is based off of a very old version of simplejson, is not maintained, and should only be used as a last resort. .. _python2.2: https://github.com/simplejson/simplejson/tree/python2.2 Platform: any Classifier: Development Status :: 5 - Production/Stable Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: MIT License Classifier: License :: OSI Approved :: Academic Free License (AFL) Classifier: Programming Language :: Python Classifier: Programming Language :: Python :: 2 Classifier: Programming Language :: Python :: 2.5 Classifier: Programming Language :: Python :: 2.6 Classifier: Programming Language :: Python :: 2.7 Classifier: Programming Language :: Python :: 3 Classifier: Programming Language :: Python :: 3.3 Classifier: Programming Language :: Python :: 3.4 Classifier: Programming Language :: Python :: Implementation :: CPython Classifier: Programming Language :: Python :: Implementation :: PyPy Classifier: Topic :: Software Development :: Libraries :: Python Modules simplejson-3.8.1/README.rst0000644000076500000240000000260412363545501015270 0ustar bobstaff00000000000000simplejson is a simple, fast, complete, correct and extensible JSON encoder and decoder for Python 2.5+ and Python 3.3+. It is pure Python code with no dependencies, but includes an optional C extension for a serious speed boost. The latest documentation for simplejson can be read online here: http://simplejson.readthedocs.org/ simplejson is the externally maintained development version of the json library included with Python 2.6 and Python 3.0, but maintains backwards compatibility with Python 2.5. The encoder can be specialized to provide serialization in any kind of situation, without any special support by the objects to be serialized (somewhat like pickle). This is best done with the ``default`` kwarg to dumps. The decoder can handle incoming JSON strings of any specified encoding (UTF-8 by default). It can also be specialized to post-process JSON objects with the ``object_hook`` or ``object_pairs_hook`` kwargs. This is particularly useful for implementing protocols such as JSON-RPC that have a richer type system than JSON itself. For those of you that have legacy systems to maintain, there is a very old fork of simplejson in the `python2.2`_ branch that supports Python 2.2. This is based off of a very old version of simplejson, is not maintained, and should only be used as a last resort. .. _python2.2: https://github.com/simplejson/simplejson/tree/python2.2 simplejson-3.8.1/scripts/0000755000076500000240000000000012613714404015264 5ustar bobstaff00000000000000simplejson-3.8.1/scripts/make_docs.py0000755000076500000240000000064412363544726017604 0ustar bobstaff00000000000000#!/usr/bin/env python import os import subprocess import shutil SPHINX_BUILD = 'sphinx-build' DOCTREES_DIR = 'build/doctrees' HTML_DIR = 'docs' for dirname in DOCTREES_DIR, HTML_DIR: if not os.path.exists(dirname): os.makedirs(dirname) open(os.path.join(HTML_DIR, '.nojekyll'), 'w').close() res = subprocess.call([ SPHINX_BUILD, '-d', DOCTREES_DIR, '-b', 'html', '.', 'docs', ]) raise SystemExit(res) simplejson-3.8.1/setup.cfg0000644000076500000240000000007312613714404015416 0ustar bobstaff00000000000000[egg_info] tag_build = tag_date = 0 tag_svn_revision = 0 simplejson-3.8.1/setup.py0000644000076500000240000000734312572353106015320 0ustar bobstaff00000000000000#!/usr/bin/env python from __future__ import with_statement import sys try: from setuptools import setup, Extension, Command except ImportError: from distutils.core import setup, Extension, Command from distutils.command.build_ext import build_ext from distutils.errors import CCompilerError, DistutilsExecError, \ DistutilsPlatformError IS_PYPY = hasattr(sys, 'pypy_translation_info') VERSION = '3.8.1' DESCRIPTION = "Simple, fast, extensible JSON encoder/decoder for Python" with open('README.rst', 'r') as f: LONG_DESCRIPTION = f.read() CLASSIFIERS = filter(None, map(str.strip, """ Development Status :: 5 - Production/Stable Intended Audience :: Developers License :: OSI Approved :: MIT License License :: OSI Approved :: Academic Free License (AFL) Programming Language :: Python Programming Language :: Python :: 2 Programming Language :: Python :: 2.5 Programming Language :: Python :: 2.6 Programming Language :: Python :: 2.7 Programming Language :: Python :: 3 Programming Language :: Python :: 3.3 Programming Language :: Python :: 3.4 Programming Language :: Python :: Implementation :: CPython Programming Language :: Python :: Implementation :: PyPy Topic :: Software Development :: Libraries :: Python Modules """.splitlines())) if sys.platform == 'win32' and sys.version_info > (2, 6): # 2.6's distutils.msvc9compiler can raise an IOError when failing to # find the compiler # It can also raise ValueError http://bugs.python.org/issue7511 ext_errors = (CCompilerError, DistutilsExecError, DistutilsPlatformError, IOError, ValueError) else: ext_errors = (CCompilerError, DistutilsExecError, DistutilsPlatformError) class BuildFailed(Exception): pass class ve_build_ext(build_ext): # This class allows C extension building to fail. def run(self): try: build_ext.run(self) except DistutilsPlatformError: raise BuildFailed() def build_extension(self, ext): try: build_ext.build_extension(self, ext) except ext_errors: raise BuildFailed() class TestCommand(Command): user_options = [] def initialize_options(self): pass def finalize_options(self): pass def run(self): import sys, subprocess raise SystemExit( subprocess.call([sys.executable, # Turn on deprecation warnings '-Wd', 'simplejson/tests/__init__.py'])) def run_setup(with_binary): cmdclass = dict(test=TestCommand) if with_binary: kw = dict( ext_modules = [ Extension("simplejson._speedups", ["simplejson/_speedups.c"]), ], cmdclass=dict(cmdclass, build_ext=ve_build_ext), ) else: kw = dict(cmdclass=cmdclass) setup( name="simplejson", version=VERSION, description=DESCRIPTION, long_description=LONG_DESCRIPTION, classifiers=CLASSIFIERS, author="Bob Ippolito", author_email="bob@redivi.com", url="http://github.com/simplejson/simplejson", license="MIT License", packages=['simplejson', 'simplejson.tests'], platforms=['any'], **kw) try: run_setup(not IS_PYPY) except BuildFailed: BUILD_EXT_WARNING = ("WARNING: The C extension could not be compiled, " "speedups are not enabled.") print('*' * 75) print(BUILD_EXT_WARNING) print("Failure information, if any, is above.") print("I'm retrying the build without the C extension now.") print('*' * 75) run_setup(False) print('*' * 75) print(BUILD_EXT_WARNING) print("Plain-Python installation succeeded.") print('*' * 75) simplejson-3.8.1/simplejson/0000755000076500000240000000000012613714404015760 5ustar bobstaff00000000000000simplejson-3.8.1/simplejson/__init__.py0000644000076500000240000005621012572353120020073 0ustar bobstaff00000000000000r"""JSON (JavaScript Object Notation) is a subset of JavaScript syntax (ECMA-262 3rd edition) used as a lightweight data interchange format. :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 back to 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 as json >>> json.dumps(['foo', {'bar': ('baz', None, 1.0, 2)}]) '["foo", {"bar": ["baz", null, 1.0, 2]}]' >>> print(json.dumps("\"foo\bar")) "\"foo\bar" >>> print(json.dumps(u'\u1234')) "\u1234" >>> print(json.dumps('\\')) "\\" >>> print(json.dumps({"c": 0, "b": 0, "a": 0}, sort_keys=True)) {"a": 0, "b": 0, "c": 0} >>> from simplejson.compat import StringIO >>> io = StringIO() >>> json.dump(['streaming API'], io) >>> io.getvalue() '["streaming API"]' Compact encoding:: >>> import simplejson as json >>> obj = [1,2,3,{'4': 5, '6': 7}] >>> json.dumps(obj, separators=(',',':'), sort_keys=True) '[1,2,3,{"4":5,"6":7}]' Pretty printing:: >>> import simplejson as json >>> print(json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=' ')) { "4": 5, "6": 7 } Decoding JSON:: >>> 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 simplejson.compat import StringIO >>> io = StringIO('["streaming API"]') >>> json.load(io)[0] == 'streaming API' True Specializing JSON object decoding:: >>> import simplejson as json >>> def as_complex(dct): ... if '__complex__' in dct: ... return complex(dct['real'], dct['imag']) ... return dct ... >>> json.loads('{"__complex__": true, "real": 1, "imag": 2}', ... object_hook=as_complex) (1+2j) >>> from decimal import Decimal >>> json.loads('1.1', parse_float=Decimal) == Decimal('1.1') True 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]' >>> json.JSONEncoder(default=encode_complex).encode(2 + 1j) '[2.0, 1.0]' >>> ''.join(json.JSONEncoder(default=encode_complex).iterencode(2 + 1j)) '[2.0, 1.0]' 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 3 (char 2) """ from __future__ import absolute_import __version__ = '3.8.1' __all__ = [ 'dump', 'dumps', 'load', 'loads', 'JSONDecoder', 'JSONDecodeError', 'JSONEncoder', 'OrderedDict', 'simple_first', ] __author__ = 'Bob Ippolito ' from decimal import Decimal from .scanner import JSONDecodeError from .decoder import JSONDecoder from .encoder import JSONEncoder, JSONEncoderForHTML def _import_OrderedDict(): import collections try: return collections.OrderedDict except AttributeError: from . import ordered_dict return ordered_dict.OrderedDict OrderedDict = _import_OrderedDict() def _import_c_make_encoder(): try: from ._speedups import make_encoder return make_encoder except ImportError: return None _default_encoder = JSONEncoder( skipkeys=False, ensure_ascii=True, check_circular=True, allow_nan=True, indent=None, separators=None, encoding='utf-8', default=None, use_decimal=True, namedtuple_as_object=True, tuple_as_array=True, iterable_as_array=False, bigint_as_string=False, item_sort_key=None, for_json=False, ignore_nan=False, int_as_string_bitcount=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', default=None, use_decimal=True, namedtuple_as_object=True, tuple_as_array=True, bigint_as_string=False, sort_keys=False, item_sort_key=None, for_json=False, ignore_nan=False, int_as_string_bitcount=None, iterable_as_array=False, **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 original JSON specification, instead of using the JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``). See *ignore_nan* for ECMA-262 compliant behavior. If *indent* is a string, then JSON array elements and object members will be pretty-printed with a newline followed by that string repeated for each level of nesting. ``None`` (the default) selects the most compact representation without any newlines. For backwards compatibility with versions of simplejson earlier than 2.1.0, an integer is also accepted and is converted to a string with that many spaces. If specified, *separators* should be an ``(item_separator, key_separator)`` tuple. The default is ``(', ', ': ')`` if *indent* is ``None`` and ``(',', ': ')`` otherwise. To get the most compact JSON representation, you should specify ``(',', ':')`` to eliminate whitespace. *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``. If *use_decimal* is true (default: ``True``) then decimal.Decimal will be natively serialized to JSON with full precision. If *namedtuple_as_object* is true (default: ``True``), :class:`tuple` subclasses with ``_asdict()`` methods will be encoded as JSON objects. If *tuple_as_array* is true (default: ``True``), :class:`tuple` (and subclasses) will be encoded as JSON arrays. If *iterable_as_array* is true (default: ``False``), any object not in the above table that implements ``__iter__()`` will be encoded as a JSON array. If *bigint_as_string* is true (default: ``False``), ints 2**53 and higher or lower than -2**53 will be encoded as strings. This is to avoid the rounding that happens in Javascript otherwise. Note that this is still a lossy operation that will not round-trip correctly and should be used sparingly. If *int_as_string_bitcount* is a positive number (n), then int of size greater than or equal to 2**n or lower than or equal to -2**n will be encoded as strings. If specified, *item_sort_key* is a callable used to sort the items in each dictionary. This is useful if you want to sort items other than in alphabetical order by key. This option takes precedence over *sort_keys*. If *sort_keys* is true (default: ``False``), the output of dictionaries will be sorted by item. If *for_json* is true (default: ``False``), objects with a ``for_json()`` method will use the return value of that method for encoding as JSON instead of the object. If *ignore_nan* is true (default: ``False``), then out of range :class:`float` values (``nan``, ``inf``, ``-inf``) will be serialized as ``null`` in compliance with the ECMA-262 specification. If true, this will override *allow_nan*. To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the ``.default()`` method to serialize additional types), specify it with the ``cls`` kwarg. NOTE: You should use *default* or *for_json* instead of subclassing whenever possible. """ # cached encoder 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 default is None and use_decimal and namedtuple_as_object and tuple_as_array and not iterable_as_array and not bigint_as_string and not sort_keys and not item_sort_key and not for_json and not ignore_nan and int_as_string_bitcount 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, default=default, use_decimal=use_decimal, namedtuple_as_object=namedtuple_as_object, tuple_as_array=tuple_as_array, iterable_as_array=iterable_as_array, bigint_as_string=bigint_as_string, sort_keys=sort_keys, item_sort_key=item_sort_key, for_json=for_json, ignore_nan=ignore_nan, int_as_string_bitcount=int_as_string_bitcount, **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', default=None, use_decimal=True, namedtuple_as_object=True, tuple_as_array=True, bigint_as_string=False, sort_keys=False, item_sort_key=None, for_json=False, ignore_nan=False, int_as_string_bitcount=None, iterable_as_array=False, **kw): """Serialize ``obj`` to a JSON formatted ``str``. 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 ``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 string, then JSON array elements and object members will be pretty-printed with a newline followed by that string repeated for each level of nesting. ``None`` (the default) selects the most compact representation without any newlines. For backwards compatibility with versions of simplejson earlier than 2.1.0, an integer is also accepted and is converted to a string with that many spaces. If specified, ``separators`` should be an ``(item_separator, key_separator)`` tuple. The default is ``(', ', ': ')`` if *indent* is ``None`` and ``(',', ': ')`` otherwise. To get the most compact JSON representation, you should specify ``(',', ':')`` to eliminate whitespace. ``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. If *use_decimal* is true (default: ``True``) then decimal.Decimal will be natively serialized to JSON with full precision. If *namedtuple_as_object* is true (default: ``True``), :class:`tuple` subclasses with ``_asdict()`` methods will be encoded as JSON objects. If *tuple_as_array* is true (default: ``True``), :class:`tuple` (and subclasses) will be encoded as JSON arrays. If *iterable_as_array* is true (default: ``False``), any object not in the above table that implements ``__iter__()`` will be encoded as a JSON array. If *bigint_as_string* is true (not the default), ints 2**53 and higher or lower than -2**53 will be encoded as strings. This is to avoid the rounding that happens in Javascript otherwise. If *int_as_string_bitcount* is a positive number (n), then int of size greater than or equal to 2**n or lower than or equal to -2**n will be encoded as strings. If specified, *item_sort_key* is a callable used to sort the items in each dictionary. This is useful if you want to sort items other than in alphabetical order by key. This option takes precendence over *sort_keys*. If *sort_keys* is true (default: ``False``), the output of dictionaries will be sorted by item. If *for_json* is true (default: ``False``), objects with a ``for_json()`` method will use the return value of that method for encoding as JSON instead of the object. If *ignore_nan* is true (default: ``False``), then out of range :class:`float` values (``nan``, ``inf``, ``-inf``) will be serialized as ``null`` in compliance with the ECMA-262 specification. If true, this will override *allow_nan*. To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the ``.default()`` method to serialize additional types), specify it with the ``cls`` kwarg. NOTE: You should use *default* instead of subclassing whenever possible. """ # cached encoder 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 default is None and use_decimal and namedtuple_as_object and tuple_as_array and not iterable_as_array and not bigint_as_string and not sort_keys and not item_sort_key and not for_json and not ignore_nan and int_as_string_bitcount 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, default=default, use_decimal=use_decimal, namedtuple_as_object=namedtuple_as_object, tuple_as_array=tuple_as_array, iterable_as_array=iterable_as_array, bigint_as_string=bigint_as_string, sort_keys=sort_keys, item_sort_key=item_sort_key, for_json=for_json, ignore_nan=ignore_nan, int_as_string_bitcount=int_as_string_bitcount, **kw).encode(obj) _default_decoder = JSONDecoder(encoding=None, object_hook=None, object_pairs_hook=None) def load(fp, encoding=None, cls=None, object_hook=None, parse_float=None, parse_int=None, parse_constant=None, object_pairs_hook=None, use_decimal=False, namedtuple_as_object=True, tuple_as_array=True, **kw): """Deserialize ``fp`` (a ``.read()``-supporting file-like object containing a JSON document) to a Python object. *encoding* determines the encoding used to interpret any :class:`str` objects decoded by this instance (``'utf-8'`` by default). It has no effect when decoding :class:`unicode` objects. Note that currently only encodings that are a superset of ASCII work, strings of other encodings should be passed in as :class:`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 :class:`dict`. This can be used to provide custom deserializations (e.g. to support JSON-RPC class hinting). *object_pairs_hook* is an optional function that will be called with the result of any object literal decode with an ordered list of pairs. The return value of *object_pairs_hook* will be used instead of the :class:`dict`. This feature can be used to implement custom decoders that rely on the order that the key and value pairs are decoded (for example, :func:`collections.OrderedDict` will remember the order of insertion). If *object_hook* is also defined, the *object_pairs_hook* takes priority. *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. :class:`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. :class:`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. If *use_decimal* is true (default: ``False``) then it implies parse_float=decimal.Decimal for parity with ``dump``. To use a custom ``JSONDecoder`` subclass, specify it with the ``cls`` kwarg. NOTE: You should use *object_hook* or *object_pairs_hook* instead of subclassing whenever possible. """ return loads(fp.read(), encoding=encoding, cls=cls, object_hook=object_hook, parse_float=parse_float, parse_int=parse_int, parse_constant=parse_constant, object_pairs_hook=object_pairs_hook, use_decimal=use_decimal, **kw) def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None, parse_int=None, parse_constant=None, object_pairs_hook=None, use_decimal=False, **kw): """Deserialize ``s`` (a ``str`` or ``unicode`` instance containing a JSON document) to a Python object. *encoding* determines the encoding used to interpret any :class:`str` objects decoded by this instance (``'utf-8'`` by default). It has no effect when decoding :class:`unicode` objects. Note that currently only encodings that are a superset of ASCII work, strings of other encodings should be passed in as :class:`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 :class:`dict`. This can be used to provide custom deserializations (e.g. to support JSON-RPC class hinting). *object_pairs_hook* is an optional function that will be called with the result of any object literal decode with an ordered list of pairs. The return value of *object_pairs_hook* will be used instead of the :class:`dict`. This feature can be used to implement custom decoders that rely on the order that the key and value pairs are decoded (for example, :func:`collections.OrderedDict` will remember the order of insertion). If *object_hook* is also defined, the *object_pairs_hook* takes priority. *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. :class:`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. :class:`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. If *use_decimal* is true (default: ``False``) then it implies parse_float=decimal.Decimal for parity with ``dump``. To use a custom ``JSONDecoder`` subclass, specify it with the ``cls`` kwarg. NOTE: You should use *object_hook* or *object_pairs_hook* instead of subclassing whenever possible. """ 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 object_pairs_hook is None and not use_decimal 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 object_pairs_hook is not None: kw['object_pairs_hook'] = object_pairs_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 if use_decimal: if parse_float is not None: raise TypeError("use_decimal=True implies parse_float=Decimal") kw['parse_float'] = Decimal return cls(encoding=encoding, **kw).decode(s) def _toggle_speedups(enabled): from . import decoder as dec from . import encoder as enc from . import scanner as scan c_make_encoder = _import_c_make_encoder() if enabled: dec.scanstring = dec.c_scanstring or dec.py_scanstring enc.c_make_encoder = c_make_encoder enc.encode_basestring_ascii = (enc.c_encode_basestring_ascii or enc.py_encode_basestring_ascii) scan.make_scanner = scan.c_make_scanner or scan.py_make_scanner else: dec.scanstring = dec.py_scanstring enc.c_make_encoder = None enc.encode_basestring_ascii = enc.py_encode_basestring_ascii scan.make_scanner = scan.py_make_scanner dec.make_scanner = scan.make_scanner global _default_decoder _default_decoder = JSONDecoder( encoding=None, object_hook=None, object_pairs_hook=None, ) global _default_encoder _default_encoder = JSONEncoder( skipkeys=False, ensure_ascii=True, check_circular=True, allow_nan=True, indent=None, separators=None, encoding='utf-8', default=None, ) def simple_first(kv): """Helper function to pass to item_sort_key to sort simple elements to the top, then container elements. """ return (isinstance(kv[1], (list, dict, tuple)), kv[0]) simplejson-3.8.1/simplejson/_speedups.c0000644000076500000240000032443512572352702020131 0ustar bobstaff00000000000000/* -*- mode: C; c-file-style: "python"; c-basic-offset: 4 -*- */ #include "Python.h" #include "structmember.h" #if PY_MAJOR_VERSION >= 3 #define PyInt_FromSsize_t PyLong_FromSsize_t #define PyInt_AsSsize_t PyLong_AsSsize_t #define PyString_Check PyBytes_Check #define PyString_GET_SIZE PyBytes_GET_SIZE #define PyString_AS_STRING PyBytes_AS_STRING #define PyString_FromStringAndSize PyBytes_FromStringAndSize #define PyInt_Check(obj) 0 #define PyInt_CheckExact(obj) 0 #define JSON_UNICHR Py_UCS4 #define JSON_InternFromString PyUnicode_InternFromString #define JSON_Intern_GET_SIZE PyUnicode_GET_SIZE #define JSON_ASCII_Check PyUnicode_Check #define JSON_ASCII_AS_STRING PyUnicode_AsUTF8 #define PyInt_Type PyLong_Type #define PyInt_FromString PyLong_FromString #define PY2_UNUSED #define PY3_UNUSED UNUSED #define JSON_NewEmptyUnicode() PyUnicode_New(0, 127) #else /* PY_MAJOR_VERSION >= 3 */ #define PY2_UNUSED UNUSED #define PY3_UNUSED #define PyUnicode_READY(obj) 0 #define PyUnicode_KIND(obj) (sizeof(Py_UNICODE)) #define PyUnicode_DATA(obj) ((void *)(PyUnicode_AS_UNICODE(obj))) #define PyUnicode_READ(kind, data, index) ((JSON_UNICHR)((const Py_UNICODE *)(data))[(index)]) #define PyUnicode_GetLength PyUnicode_GET_SIZE #define JSON_UNICHR Py_UNICODE #define JSON_ASCII_Check PyString_Check #define JSON_ASCII_AS_STRING PyString_AS_STRING #define JSON_InternFromString PyString_InternFromString #define JSON_Intern_GET_SIZE PyString_GET_SIZE #define JSON_NewEmptyUnicode() PyUnicode_FromUnicode(NULL, 0) #endif /* PY_MAJOR_VERSION < 3 */ #if PY_VERSION_HEX < 0x02070000 #if !defined(PyOS_string_to_double) #define PyOS_string_to_double json_PyOS_string_to_double static double json_PyOS_string_to_double(const char *s, char **endptr, PyObject *overflow_exception); static double json_PyOS_string_to_double(const char *s, char **endptr, PyObject *overflow_exception) { double x; assert(endptr == NULL); assert(overflow_exception == NULL); PyFPE_START_PROTECT("json_PyOS_string_to_double", return -1.0;) x = PyOS_ascii_atof(s); PyFPE_END_PROTECT(x) return x; } #endif #endif /* PY_VERSION_HEX < 0x02070000 */ #if PY_VERSION_HEX < 0x02060000 #if !defined(Py_TYPE) #define Py_TYPE(ob) (((PyObject*)(ob))->ob_type) #endif #if !defined(Py_SIZE) #define Py_SIZE(ob) (((PyVarObject*)(ob))->ob_size) #endif #if !defined(PyVarObject_HEAD_INIT) #define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size, #endif #endif /* PY_VERSION_HEX < 0x02060000 */ #if PY_VERSION_HEX < 0x02050000 #if !defined(PY_SSIZE_T_MIN) typedef int Py_ssize_t; #define PY_SSIZE_T_MAX INT_MAX #define PY_SSIZE_T_MIN INT_MIN #define PyInt_FromSsize_t PyInt_FromLong #define PyInt_AsSsize_t PyInt_AsLong #endif #if !defined(Py_IS_FINITE) #define Py_IS_FINITE(X) (!Py_IS_INFINITY(X) && !Py_IS_NAN(X)) #endif #endif /* PY_VERSION_HEX < 0x02050000 */ #ifdef __GNUC__ #define UNUSED __attribute__((__unused__)) #else #define UNUSED #endif #define DEFAULT_ENCODING "utf-8" #define PyScanner_Check(op) PyObject_TypeCheck(op, &PyScannerType) #define PyScanner_CheckExact(op) (Py_TYPE(op) == &PyScannerType) #define PyEncoder_Check(op) PyObject_TypeCheck(op, &PyEncoderType) #define PyEncoder_CheckExact(op) (Py_TYPE(op) == &PyEncoderType) #define JSON_ALLOW_NAN 1 #define JSON_IGNORE_NAN 2 static PyTypeObject PyScannerType; static PyTypeObject PyEncoderType; typedef struct { PyObject *large_strings; /* A list of previously accumulated large strings */ PyObject *small_strings; /* Pending small strings */ } JSON_Accu; static int JSON_Accu_Init(JSON_Accu *acc); static int JSON_Accu_Accumulate(JSON_Accu *acc, PyObject *unicode); static PyObject * JSON_Accu_FinishAsList(JSON_Accu *acc); static void JSON_Accu_Destroy(JSON_Accu *acc); #define ERR_EXPECTING_VALUE "Expecting value" #define ERR_ARRAY_DELIMITER "Expecting ',' delimiter or ']'" #define ERR_ARRAY_VALUE_FIRST "Expecting value or ']'" #define ERR_OBJECT_DELIMITER "Expecting ',' delimiter or '}'" #define ERR_OBJECT_PROPERTY "Expecting property name enclosed in double quotes" #define ERR_OBJECT_PROPERTY_FIRST "Expecting property name enclosed in double quotes or '}'" #define ERR_OBJECT_PROPERTY_DELIMITER "Expecting ':' delimiter" #define ERR_STRING_UNTERMINATED "Unterminated string starting at" #define ERR_STRING_CONTROL "Invalid control character %r at" #define ERR_STRING_ESC1 "Invalid \\X escape sequence %r" #define ERR_STRING_ESC4 "Invalid \\uXXXX escape sequence" typedef struct _PyScannerObject { PyObject_HEAD PyObject *encoding; PyObject *strict; PyObject *object_hook; PyObject *pairs_hook; PyObject *parse_float; PyObject *parse_int; PyObject *parse_constant; PyObject *memo; } PyScannerObject; static PyMemberDef scanner_members[] = { {"encoding", T_OBJECT, offsetof(PyScannerObject, encoding), READONLY, "encoding"}, {"strict", T_OBJECT, offsetof(PyScannerObject, strict), READONLY, "strict"}, {"object_hook", T_OBJECT, offsetof(PyScannerObject, object_hook), READONLY, "object_hook"}, {"object_pairs_hook", T_OBJECT, offsetof(PyScannerObject, pairs_hook), READONLY, "object_pairs_hook"}, {"parse_float", T_OBJECT, offsetof(PyScannerObject, parse_float), READONLY, "parse_float"}, {"parse_int", T_OBJECT, offsetof(PyScannerObject, parse_int), READONLY, "parse_int"}, {"parse_constant", T_OBJECT, offsetof(PyScannerObject, parse_constant), READONLY, "parse_constant"}, {NULL} }; typedef struct _PyEncoderObject { PyObject_HEAD PyObject *markers; PyObject *defaultfn; PyObject *encoder; PyObject *indent; PyObject *key_separator; PyObject *item_separator; PyObject *sort_keys; PyObject *key_memo; PyObject *encoding; PyObject *Decimal; PyObject *skipkeys_bool; int skipkeys; int fast_encode; /* 0, JSON_ALLOW_NAN, JSON_IGNORE_NAN */ int allow_or_ignore_nan; int use_decimal; int namedtuple_as_object; int tuple_as_array; int iterable_as_array; PyObject *max_long_size; PyObject *min_long_size; PyObject *item_sort_key; PyObject *item_sort_kw; int for_json; } PyEncoderObject; static PyMemberDef encoder_members[] = { {"markers", T_OBJECT, offsetof(PyEncoderObject, markers), READONLY, "markers"}, {"default", T_OBJECT, offsetof(PyEncoderObject, defaultfn), READONLY, "default"}, {"encoder", T_OBJECT, offsetof(PyEncoderObject, encoder), READONLY, "encoder"}, {"encoding", T_OBJECT, offsetof(PyEncoderObject, encoder), READONLY, "encoding"}, {"indent", T_OBJECT, offsetof(PyEncoderObject, indent), READONLY, "indent"}, {"key_separator", T_OBJECT, offsetof(PyEncoderObject, key_separator), READONLY, "key_separator"}, {"item_separator", T_OBJECT, offsetof(PyEncoderObject, item_separator), READONLY, "item_separator"}, {"sort_keys", T_OBJECT, offsetof(PyEncoderObject, sort_keys), READONLY, "sort_keys"}, /* Python 2.5 does not support T_BOOl */ {"skipkeys", T_OBJECT, offsetof(PyEncoderObject, skipkeys_bool), READONLY, "skipkeys"}, {"key_memo", T_OBJECT, offsetof(PyEncoderObject, key_memo), READONLY, "key_memo"}, {"item_sort_key", T_OBJECT, offsetof(PyEncoderObject, item_sort_key), READONLY, "item_sort_key"}, {"max_long_size", T_OBJECT, offsetof(PyEncoderObject, max_long_size), READONLY, "max_long_size"}, {"min_long_size", T_OBJECT, offsetof(PyEncoderObject, min_long_size), READONLY, "min_long_size"}, {NULL} }; static PyObject * join_list_unicode(PyObject *lst); static PyObject * JSON_ParseEncoding(PyObject *encoding); static PyObject * JSON_UnicodeFromChar(JSON_UNICHR c); static PyObject * maybe_quote_bigint(PyEncoderObject* s, PyObject *encoded, PyObject *obj); static Py_ssize_t ascii_char_size(JSON_UNICHR c); static Py_ssize_t ascii_escape_char(JSON_UNICHR 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 UNUSED, PyObject *pystr); #if PY_MAJOR_VERSION < 3 static PyObject * join_list_string(PyObject *lst); static PyObject * scan_once_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr); static PyObject * scanstring_str(PyObject *pystr, Py_ssize_t end, char *encoding, int strict, Py_ssize_t *next_end_ptr); static PyObject * _parse_object_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr); #endif static PyObject * scanstring_unicode(PyObject *pystr, Py_ssize_t end, int strict, Py_ssize_t *next_end_ptr); static PyObject * scan_once_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr); static PyObject * _build_rval_index_tuple(PyObject *rval, Py_ssize_t idx); static PyObject * scanner_new(PyTypeObject *type, PyObject *args, PyObject *kwds); static int scanner_init(PyObject *self, PyObject *args, PyObject *kwds); static void scanner_dealloc(PyObject *self); static int scanner_clear(PyObject *self); static PyObject * encoder_new(PyTypeObject *type, PyObject *args, PyObject *kwds); static int encoder_init(PyObject *self, PyObject *args, PyObject *kwds); static void encoder_dealloc(PyObject *self); static int encoder_clear(PyObject *self); static PyObject * encoder_stringify_key(PyEncoderObject *s, PyObject *key); static int encoder_listencode_list(PyEncoderObject *s, JSON_Accu *rval, PyObject *seq, Py_ssize_t indent_level); static int encoder_listencode_obj(PyEncoderObject *s, JSON_Accu *rval, PyObject *obj, Py_ssize_t indent_level); static int encoder_listencode_dict(PyEncoderObject *s, JSON_Accu *rval, PyObject *dct, Py_ssize_t indent_level); static PyObject * _encoded_const(PyObject *obj); static void raise_errmsg(char *msg, PyObject *s, Py_ssize_t end); static PyObject * encoder_encode_string(PyEncoderObject *s, PyObject *obj); static int _convertPyInt_AsSsize_t(PyObject *o, Py_ssize_t *size_ptr); static PyObject * _convertPyInt_FromSsize_t(Py_ssize_t *size_ptr); static PyObject * encoder_encode_float(PyEncoderObject *s, PyObject *obj); static int _is_namedtuple(PyObject *obj); static int _has_for_json_hook(PyObject *obj); static PyObject * moduleinit(void); #define S_CHAR(c) (c >= ' ' && c <= '~' && c != '\\' && c != '"') #define IS_WHITESPACE(c) (((c) == ' ') || ((c) == '\t') || ((c) == '\n') || ((c) == '\r')) #define MIN_EXPANSION 6 static int JSON_Accu_Init(JSON_Accu *acc) { /* Lazily allocated */ acc->large_strings = NULL; acc->small_strings = PyList_New(0); if (acc->small_strings == NULL) return -1; return 0; } static int flush_accumulator(JSON_Accu *acc) { Py_ssize_t nsmall = PyList_GET_SIZE(acc->small_strings); if (nsmall) { int ret; PyObject *joined; if (acc->large_strings == NULL) { acc->large_strings = PyList_New(0); if (acc->large_strings == NULL) return -1; } #if PY_MAJOR_VERSION >= 3 joined = join_list_unicode(acc->small_strings); #else /* PY_MAJOR_VERSION >= 3 */ joined = join_list_string(acc->small_strings); #endif /* PY_MAJOR_VERSION < 3 */ if (joined == NULL) return -1; if (PyList_SetSlice(acc->small_strings, 0, nsmall, NULL)) { Py_DECREF(joined); return -1; } ret = PyList_Append(acc->large_strings, joined); Py_DECREF(joined); return ret; } return 0; } static int JSON_Accu_Accumulate(JSON_Accu *acc, PyObject *unicode) { Py_ssize_t nsmall; #if PY_MAJOR_VERSION >= 3 assert(PyUnicode_Check(unicode)); #else /* PY_MAJOR_VERSION >= 3 */ assert(JSON_ASCII_Check(unicode) || PyUnicode_Check(unicode)); #endif /* PY_MAJOR_VERSION < 3 */ if (PyList_Append(acc->small_strings, unicode)) return -1; nsmall = PyList_GET_SIZE(acc->small_strings); /* Each item in a list of unicode objects has an overhead (in 64-bit * builds) of: * - 8 bytes for the list slot * - 56 bytes for the header of the unicode object * that is, 64 bytes. 100000 such objects waste more than 6MB * compared to a single concatenated string. */ if (nsmall < 100000) return 0; return flush_accumulator(acc); } static PyObject * JSON_Accu_FinishAsList(JSON_Accu *acc) { int ret; PyObject *res; ret = flush_accumulator(acc); Py_CLEAR(acc->small_strings); if (ret) { Py_CLEAR(acc->large_strings); return NULL; } res = acc->large_strings; acc->large_strings = NULL; if (res == NULL) return PyList_New(0); return res; } static void JSON_Accu_Destroy(JSON_Accu *acc) { Py_CLEAR(acc->small_strings); Py_CLEAR(acc->large_strings); } static int IS_DIGIT(JSON_UNICHR c) { return c >= '0' && c <= '9'; } static PyObject * JSON_UnicodeFromChar(JSON_UNICHR c) { #if PY_MAJOR_VERSION >= 3 PyObject *rval = PyUnicode_New(1, c); if (rval) PyUnicode_WRITE(PyUnicode_KIND(rval), PyUnicode_DATA(rval), 0, c); return rval; #else /* PY_MAJOR_VERSION >= 3 */ return PyUnicode_FromUnicode(&c, 1); #endif /* PY_MAJOR_VERSION < 3 */ } static PyObject * maybe_quote_bigint(PyEncoderObject* s, PyObject *encoded, PyObject *obj) { if (s->max_long_size != Py_None && s->min_long_size != Py_None) { if (PyObject_RichCompareBool(obj, s->max_long_size, Py_GE) || PyObject_RichCompareBool(obj, s->min_long_size, Py_LE)) { #if PY_MAJOR_VERSION >= 3 PyObject* quoted = PyUnicode_FromFormat("\"%U\"", encoded); #else PyObject* quoted = PyString_FromFormat("\"%s\"", PyString_AsString(encoded)); #endif Py_DECREF(encoded); encoded = quoted; } } return encoded; } static int _is_namedtuple(PyObject *obj) { int rval = 0; PyObject *_asdict = PyObject_GetAttrString(obj, "_asdict"); if (_asdict == NULL) { PyErr_Clear(); return 0; } rval = PyCallable_Check(_asdict); Py_DECREF(_asdict); return rval; } static int _has_for_json_hook(PyObject *obj) { int rval = 0; PyObject *for_json = PyObject_GetAttrString(obj, "for_json"); if (for_json == NULL) { PyErr_Clear(); return 0; } rval = PyCallable_Check(for_json); Py_DECREF(for_json); return rval; } static int _convertPyInt_AsSsize_t(PyObject *o, Py_ssize_t *size_ptr) { /* PyObject to Py_ssize_t converter */ *size_ptr = PyInt_AsSsize_t(o); if (*size_ptr == -1 && PyErr_Occurred()) return 0; return 1; } static PyObject * _convertPyInt_FromSsize_t(Py_ssize_t *size_ptr) { /* Py_ssize_t to PyObject converter */ return PyInt_FromSsize_t(*size_ptr); } static Py_ssize_t ascii_escape_char(JSON_UNICHR c, char *output, Py_ssize_t chars) { /* Escape unicode code point c to ASCII escape sequences in char *output. output must have at least 12 bytes unused to accommodate an escaped surrogate pair "\uXXXX\uXXXX" */ if (S_CHAR(c)) { output[chars++] = (char)c; } else { output[chars++] = '\\'; switch (c) { 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: #if defined(Py_UNICODE_WIDE) || PY_MAJOR_VERSION >= 3 if (c >= 0x10000) { /* UTF-16 surrogate pair */ JSON_UNICHR v = c - 0x10000; c = 0xd800 | ((v >> 10) & 0x3ff); output[chars++] = 'u'; output[chars++] = "0123456789abcdef"[(c >> 12) & 0xf]; output[chars++] = "0123456789abcdef"[(c >> 8) & 0xf]; output[chars++] = "0123456789abcdef"[(c >> 4) & 0xf]; output[chars++] = "0123456789abcdef"[(c ) & 0xf]; c = 0xdc00 | (v & 0x3ff); output[chars++] = '\\'; } #endif output[chars++] = 'u'; output[chars++] = "0123456789abcdef"[(c >> 12) & 0xf]; output[chars++] = "0123456789abcdef"[(c >> 8) & 0xf]; output[chars++] = "0123456789abcdef"[(c >> 4) & 0xf]; output[chars++] = "0123456789abcdef"[(c ) & 0xf]; } } return chars; } static Py_ssize_t ascii_char_size(JSON_UNICHR c) { if (S_CHAR(c)) { return 1; } else if (c == '\\' || c == '"' || c == '\b' || c == '\f' || c == '\n' || c == '\r' || c == '\t') { return 2; } #if defined(Py_UNICODE_WIDE) || PY_MAJOR_VERSION >= 3 else if (c >= 0x10000U) { return 2 * MIN_EXPANSION; } #endif else { return MIN_EXPANSION; } } static PyObject * ascii_escape_unicode(PyObject *pystr) { /* Take a PyUnicode pystr and return a new ASCII-only escaped PyString */ Py_ssize_t i; Py_ssize_t input_chars; Py_ssize_t output_size; Py_ssize_t chars; PY2_UNUSED int kind; void *data; PyObject *rval; char *output; if (PyUnicode_READY(pystr)) return NULL; kind = PyUnicode_KIND(pystr); data = PyUnicode_DATA(pystr); input_chars = PyUnicode_GetLength(pystr); output_size = 2; for (i = 0; i < input_chars; i++) { output_size += ascii_char_size(PyUnicode_READ(kind, data, i)); } #if PY_MAJOR_VERSION >= 3 rval = PyUnicode_New(output_size, 127); if (rval == NULL) { return NULL; } assert(PyUnicode_KIND(rval) == PyUnicode_1BYTE_KIND); output = (char *)PyUnicode_DATA(rval); #else rval = PyString_FromStringAndSize(NULL, output_size); if (rval == NULL) { return NULL; } output = PyString_AS_STRING(rval); #endif chars = 0; output[chars++] = '"'; for (i = 0; i < input_chars; i++) { chars = ascii_escape_char(PyUnicode_READ(kind, data, i), output, chars); } output[chars++] = '"'; assert(chars == output_size); return rval; } #if PY_MAJOR_VERSION >= 3 static PyObject * ascii_escape_str(PyObject *pystr) { PyObject *rval; PyObject *input = PyUnicode_DecodeUTF8(PyString_AS_STRING(pystr), PyString_GET_SIZE(pystr), NULL); if (input == NULL) return NULL; rval = ascii_escape_unicode(input); Py_DECREF(input); return rval; } #else /* PY_MAJOR_VERSION >= 3 */ static PyObject * ascii_escape_str(PyObject *pystr) { /* Take a PyString pystr and return a new ASCII-only escaped PyString */ 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); output_size = 2; /* Fast path for a string that's already ASCII */ for (i = 0; i < input_chars; i++) { JSON_UNICHR c = (JSON_UNICHR)input_str[i]; if (c > 0x7f) { /* We hit a non-ASCII character, bail to unicode mode */ PyObject *uni; uni = PyUnicode_DecodeUTF8(input_str, input_chars, "strict"); if (uni == NULL) { return NULL; } rval = ascii_escape_unicode(uni); Py_DECREF(uni); return rval; } output_size += ascii_char_size(c); } rval = PyString_FromStringAndSize(NULL, output_size); if (rval == NULL) { return NULL; } chars = 0; output = PyString_AS_STRING(rval); output[chars++] = '"'; for (i = 0; i < input_chars; i++) { chars = ascii_escape_char((JSON_UNICHR)input_str[i], output, chars); } output[chars++] = '"'; assert(chars == output_size); return rval; } #endif /* PY_MAJOR_VERSION < 3 */ static PyObject * encoder_stringify_key(PyEncoderObject *s, PyObject *key) { if (PyUnicode_Check(key)) { Py_INCREF(key); return key; } else if (PyString_Check(key)) { #if PY_MAJOR_VERSION >= 3 return PyUnicode_Decode( PyString_AS_STRING(key), PyString_GET_SIZE(key), JSON_ASCII_AS_STRING(s->encoding), NULL); #else /* PY_MAJOR_VERSION >= 3 */ Py_INCREF(key); return key; #endif /* PY_MAJOR_VERSION < 3 */ } else if (PyFloat_Check(key)) { return encoder_encode_float(s, key); } else if (key == Py_True || key == Py_False || key == Py_None) { /* This must come before the PyInt_Check because True and False are also 1 and 0.*/ return _encoded_const(key); } else if (PyInt_Check(key) || PyLong_Check(key)) { if (!(PyInt_CheckExact(key) || PyLong_CheckExact(key))) { /* See #118, do not trust custom str/repr */ PyObject *res; PyObject *tmp = PyObject_CallFunctionObjArgs((PyObject *)&PyLong_Type, key, NULL); if (tmp == NULL) { return NULL; } res = PyObject_Str(tmp); Py_DECREF(tmp); return res; } else { return PyObject_Str(key); } } else if (s->use_decimal && PyObject_TypeCheck(key, (PyTypeObject *)s->Decimal)) { return PyObject_Str(key); } else if (s->skipkeys) { Py_INCREF(Py_None); return Py_None; } PyErr_SetString(PyExc_TypeError, "keys must be a string"); return NULL; } static PyObject * encoder_dict_iteritems(PyEncoderObject *s, PyObject *dct) { PyObject *items; PyObject *iter = NULL; PyObject *lst = NULL; PyObject *item = NULL; PyObject *kstr = NULL; static PyObject *sortfun = NULL; static PyObject *sortargs = NULL; if (sortargs == NULL) { sortargs = PyTuple_New(0); if (sortargs == NULL) return NULL; } if (PyDict_CheckExact(dct)) items = PyDict_Items(dct); else items = PyMapping_Items(dct); if (items == NULL) return NULL; iter = PyObject_GetIter(items); Py_DECREF(items); if (iter == NULL) return NULL; if (s->item_sort_kw == Py_None) return iter; lst = PyList_New(0); if (lst == NULL) goto bail; while ((item = PyIter_Next(iter))) { PyObject *key, *value; if (!PyTuple_Check(item) || Py_SIZE(item) != 2) { PyErr_SetString(PyExc_ValueError, "items must return 2-tuples"); goto bail; } key = PyTuple_GET_ITEM(item, 0); if (key == NULL) goto bail; #if PY_MAJOR_VERSION < 3 else if (PyString_Check(key)) { /* item can be added as-is */ } #endif /* PY_MAJOR_VERSION < 3 */ else if (PyUnicode_Check(key)) { /* item can be added as-is */ } else { PyObject *tpl; kstr = encoder_stringify_key(s, key); if (kstr == NULL) goto bail; else if (kstr == Py_None) { /* skipkeys */ Py_DECREF(kstr); continue; } value = PyTuple_GET_ITEM(item, 1); if (value == NULL) goto bail; tpl = PyTuple_Pack(2, kstr, value); if (tpl == NULL) goto bail; Py_CLEAR(kstr); Py_DECREF(item); item = tpl; } if (PyList_Append(lst, item)) goto bail; Py_DECREF(item); } Py_CLEAR(iter); if (PyErr_Occurred()) goto bail; sortfun = PyObject_GetAttrString(lst, "sort"); if (sortfun == NULL) goto bail; if (!PyObject_Call(sortfun, sortargs, s->item_sort_kw)) goto bail; Py_CLEAR(sortfun); iter = PyObject_GetIter(lst); Py_CLEAR(lst); return iter; bail: Py_XDECREF(sortfun); Py_XDECREF(kstr); Py_XDECREF(item); Py_XDECREF(lst); Py_XDECREF(iter); return NULL; } static void raise_errmsg(char *msg, PyObject *s, Py_ssize_t end) { /* Use JSONDecodeError exception to raise a nice looking ValueError subclass */ static PyObject *JSONDecodeError = NULL; PyObject *exc; if (JSONDecodeError == NULL) { PyObject *scanner = PyImport_ImportModule("simplejson.scanner"); if (scanner == NULL) return; JSONDecodeError = PyObject_GetAttrString(scanner, "JSONDecodeError"); Py_DECREF(scanner); if (JSONDecodeError == NULL) return; } exc = PyObject_CallFunction(JSONDecodeError, "(zOO&)", msg, s, _convertPyInt_FromSsize_t, &end); if (exc) { PyErr_SetObject(JSONDecodeError, exc); Py_DECREF(exc); } } static PyObject * join_list_unicode(PyObject *lst) { /* return u''.join(lst) */ static PyObject *joinfn = NULL; if (joinfn == NULL) { PyObject *ustr = JSON_NewEmptyUnicode(); if (ustr == NULL) return NULL; joinfn = PyObject_GetAttrString(ustr, "join"); Py_DECREF(ustr); if (joinfn == NULL) return NULL; } return PyObject_CallFunctionObjArgs(joinfn, lst, NULL); } #if PY_MAJOR_VERSION >= 3 #define join_list_string join_list_unicode #else /* PY_MAJOR_VERSION >= 3 */ static PyObject * join_list_string(PyObject *lst) { /* return ''.join(lst) */ static PyObject *joinfn = NULL; if (joinfn == NULL) { PyObject *ustr = PyString_FromStringAndSize(NULL, 0); if (ustr == NULL) return NULL; joinfn = PyObject_GetAttrString(ustr, "join"); Py_DECREF(ustr); if (joinfn == NULL) return NULL; } return PyObject_CallFunctionObjArgs(joinfn, lst, NULL); } #endif /* PY_MAJOR_VERSION < 3 */ static PyObject * _build_rval_index_tuple(PyObject *rval, Py_ssize_t idx) { /* return (rval, idx) tuple, stealing reference to rval */ PyObject *tpl; PyObject *pyidx; /* steal a reference to rval, returns (rval, idx) */ if (rval == NULL) { assert(PyErr_Occurred()); return NULL; } pyidx = PyInt_FromSsize_t(idx); if (pyidx == NULL) { Py_DECREF(rval); return NULL; } tpl = PyTuple_New(2); if (tpl == NULL) { Py_DECREF(pyidx); Py_DECREF(rval); return NULL; } PyTuple_SET_ITEM(tpl, 0, rval); PyTuple_SET_ITEM(tpl, 1, pyidx); return tpl; } #define APPEND_OLD_CHUNK \ if (chunk != NULL) { \ if (chunks == NULL) { \ chunks = PyList_New(0); \ if (chunks == NULL) { \ goto bail; \ } \ } \ if (PyList_Append(chunks, chunk)) { \ goto bail; \ } \ Py_CLEAR(chunk); \ } #if PY_MAJOR_VERSION < 3 static PyObject * scanstring_str(PyObject *pystr, Py_ssize_t end, char *encoding, int strict, Py_ssize_t *next_end_ptr) { /* Read the JSON string from PyString pystr. end is the index of the first character after the quote. encoding is the encoding of pystr (must be an ASCII superset) if strict is zero then literal control characters are allowed *next_end_ptr is a return-by-reference index of the character after the end quote Return value is a new PyString (if ASCII-only) or PyUnicode */ PyObject *rval; Py_ssize_t len = PyString_GET_SIZE(pystr); Py_ssize_t begin = end - 1; Py_ssize_t next = begin; int has_unicode = 0; char *buf = PyString_AS_STRING(pystr); PyObject *chunks = NULL; PyObject *chunk = NULL; PyObject *strchunk = NULL; if (len == end) { raise_errmsg(ERR_STRING_UNTERMINATED, pystr, begin); goto bail; } else if (end < 0 || len < end) { PyErr_SetString(PyExc_ValueError, "end is out of bounds"); goto bail; } while (1) { /* Find the end of the string or the next escape */ Py_UNICODE c = 0; for (next = end; next < len; next++) { c = (unsigned char)buf[next]; if (c == '"' || c == '\\') { break; } else if (strict && c <= 0x1f) { raise_errmsg(ERR_STRING_CONTROL, pystr, next); goto bail; } else if (c > 0x7f) { has_unicode = 1; } } if (!(c == '"' || c == '\\')) { raise_errmsg(ERR_STRING_UNTERMINATED, pystr, begin); goto bail; } /* Pick up this chunk if it's not zero length */ if (next != end) { APPEND_OLD_CHUNK #if PY_MAJOR_VERSION >= 3 if (!has_unicode) { chunk = PyUnicode_DecodeASCII(&buf[end], next - end, NULL); } else { chunk = PyUnicode_Decode(&buf[end], next - end, encoding, NULL); } if (chunk == NULL) { goto bail; } #else /* PY_MAJOR_VERSION >= 3 */ strchunk = PyString_FromStringAndSize(&buf[end], next - end); if (strchunk == NULL) { goto bail; } if (has_unicode) { chunk = PyUnicode_FromEncodedObject(strchunk, encoding, NULL); Py_DECREF(strchunk); if (chunk == NULL) { goto bail; } } else { chunk = strchunk; } #endif /* PY_MAJOR_VERSION < 3 */ } next++; if (c == '"') { end = next; break; } if (next == len) { raise_errmsg(ERR_STRING_UNTERMINATED, pystr, begin); goto bail; } c = buf[next]; if (c != 'u') { /* Non-unicode backslash escapes */ end = next + 1; switch (c) { case '"': break; case '\\': break; case '/': break; case 'b': c = '\b'; break; case 'f': c = '\f'; break; case 'n': c = '\n'; break; case 'r': c = '\r'; break; case 't': c = '\t'; break; default: c = 0; } if (c == 0) { raise_errmsg(ERR_STRING_ESC1, pystr, end - 2); goto bail; } } else { c = 0; next++; end = next + 4; if (end >= len) { raise_errmsg(ERR_STRING_ESC4, pystr, next - 1); goto bail; } /* Decode 4 hex digits */ for (; next < end; next++) { JSON_UNICHR digit = (JSON_UNICHR)buf[next]; c <<= 4; switch (digit) { case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': c |= (digit - '0'); break; case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': c |= (digit - 'a' + 10); break; case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': c |= (digit - 'A' + 10); break; default: raise_errmsg(ERR_STRING_ESC4, pystr, end - 5); goto bail; } } #if (PY_MAJOR_VERSION >= 3 || defined(Py_UNICODE_WIDE)) /* Surrogate pair */ if ((c & 0xfc00) == 0xd800) { if (end + 6 < len && buf[next] == '\\' && buf[next+1] == 'u') { JSON_UNICHR c2 = 0; end += 6; /* Decode 4 hex digits */ for (next += 2; next < end; next++) { c2 <<= 4; JSON_UNICHR digit = buf[next]; switch (digit) { case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': c2 |= (digit - '0'); break; case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': c2 |= (digit - 'a' + 10); break; case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': c2 |= (digit - 'A' + 10); break; default: raise_errmsg(ERR_STRING_ESC4, pystr, end - 5); goto bail; } } if ((c2 & 0xfc00) != 0xdc00) { /* not a low surrogate, rewind */ end -= 6; next = end; } else { c = 0x10000 + (((c - 0xd800) << 10) | (c2 - 0xdc00)); } } } #endif /* PY_MAJOR_VERSION >= 3 || Py_UNICODE_WIDE */ } if (c > 0x7f) { has_unicode = 1; } APPEND_OLD_CHUNK #if PY_MAJOR_VERSION >= 3 chunk = JSON_UnicodeFromChar(c); if (chunk == NULL) { goto bail; } #else /* PY_MAJOR_VERSION >= 3 */ if (has_unicode) { chunk = JSON_UnicodeFromChar(c); if (chunk == NULL) { goto bail; } } else { char c_char = Py_CHARMASK(c); chunk = PyString_FromStringAndSize(&c_char, 1); if (chunk == NULL) { goto bail; } } #endif } if (chunks == NULL) { if (chunk != NULL) rval = chunk; else rval = JSON_NewEmptyUnicode(); } else { APPEND_OLD_CHUNK rval = join_list_string(chunks); if (rval == NULL) { goto bail; } Py_CLEAR(chunks); } *next_end_ptr = end; return rval; bail: *next_end_ptr = -1; Py_XDECREF(chunk); Py_XDECREF(chunks); return NULL; } #endif /* PY_MAJOR_VERSION < 3 */ static PyObject * scanstring_unicode(PyObject *pystr, Py_ssize_t end, int strict, Py_ssize_t *next_end_ptr) { /* Read the JSON string from PyUnicode pystr. end is the index of the first character after the quote. if strict is zero then literal control characters are allowed *next_end_ptr is a return-by-reference index of the character after the end quote Return value is a new PyUnicode */ PyObject *rval; Py_ssize_t begin = end - 1; Py_ssize_t next = begin; PY2_UNUSED int kind = PyUnicode_KIND(pystr); Py_ssize_t len = PyUnicode_GetLength(pystr); void *buf = PyUnicode_DATA(pystr); PyObject *chunks = NULL; PyObject *chunk = NULL; if (len == end) { raise_errmsg(ERR_STRING_UNTERMINATED, pystr, begin); goto bail; } else if (end < 0 || len < end) { PyErr_SetString(PyExc_ValueError, "end is out of bounds"); goto bail; } while (1) { /* Find the end of the string or the next escape */ JSON_UNICHR c = 0; for (next = end; next < len; next++) { c = PyUnicode_READ(kind, buf, next); if (c == '"' || c == '\\') { break; } else if (strict && c <= 0x1f) { raise_errmsg(ERR_STRING_CONTROL, pystr, next); goto bail; } } if (!(c == '"' || c == '\\')) { raise_errmsg(ERR_STRING_UNTERMINATED, pystr, begin); goto bail; } /* Pick up this chunk if it's not zero length */ if (next != end) { APPEND_OLD_CHUNK #if PY_MAJOR_VERSION < 3 chunk = PyUnicode_FromUnicode(&((const Py_UNICODE *)buf)[end], next - end); #else chunk = PyUnicode_Substring(pystr, end, next); #endif if (chunk == NULL) { goto bail; } } next++; if (c == '"') { end = next; break; } if (next == len) { raise_errmsg(ERR_STRING_UNTERMINATED, pystr, begin); goto bail; } c = PyUnicode_READ(kind, buf, next); if (c != 'u') { /* Non-unicode backslash escapes */ end = next + 1; switch (c) { case '"': break; case '\\': break; case '/': break; case 'b': c = '\b'; break; case 'f': c = '\f'; break; case 'n': c = '\n'; break; case 'r': c = '\r'; break; case 't': c = '\t'; break; default: c = 0; } if (c == 0) { raise_errmsg(ERR_STRING_ESC1, pystr, end - 2); goto bail; } } else { c = 0; next++; end = next + 4; if (end >= len) { raise_errmsg(ERR_STRING_ESC4, pystr, next - 1); goto bail; } /* Decode 4 hex digits */ for (; next < end; next++) { JSON_UNICHR digit = PyUnicode_READ(kind, buf, next); c <<= 4; switch (digit) { case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': c |= (digit - '0'); break; case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': c |= (digit - 'a' + 10); break; case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': c |= (digit - 'A' + 10); break; default: raise_errmsg(ERR_STRING_ESC4, pystr, end - 5); goto bail; } } #if PY_MAJOR_VERSION >= 3 || defined(Py_UNICODE_WIDE) /* Surrogate pair */ if ((c & 0xfc00) == 0xd800) { JSON_UNICHR c2 = 0; if (end + 6 < len && PyUnicode_READ(kind, buf, next) == '\\' && PyUnicode_READ(kind, buf, next + 1) == 'u') { end += 6; /* Decode 4 hex digits */ for (next += 2; next < end; next++) { JSON_UNICHR digit = PyUnicode_READ(kind, buf, next); c2 <<= 4; switch (digit) { case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': c2 |= (digit - '0'); break; case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': c2 |= (digit - 'a' + 10); break; case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': c2 |= (digit - 'A' + 10); break; default: raise_errmsg(ERR_STRING_ESC4, pystr, end - 5); goto bail; } } if ((c2 & 0xfc00) != 0xdc00) { /* not a low surrogate, rewind */ end -= 6; next = end; } else { c = 0x10000 + (((c - 0xd800) << 10) | (c2 - 0xdc00)); } } } #endif } APPEND_OLD_CHUNK chunk = JSON_UnicodeFromChar(c); if (chunk == NULL) { goto bail; } } if (chunks == NULL) { if (chunk != NULL) rval = chunk; else rval = JSON_NewEmptyUnicode(); } else { APPEND_OLD_CHUNK rval = join_list_unicode(chunks); if (rval == NULL) { goto bail; } Py_CLEAR(chunks); } *next_end_ptr = end; return rval; bail: *next_end_ptr = -1; Py_XDECREF(chunk); Py_XDECREF(chunks); return NULL; } PyDoc_STRVAR(pydoc_scanstring, "scanstring(basestring, end, encoding, strict=True) -> (str, end)\n" "\n" "Scan the string s for a JSON string. End is the index of the\n" "character in s after the quote that started the JSON string.\n" "Unescapes all valid JSON string escape sequences and raises ValueError\n" "on attempt to decode an invalid string. If strict is False then literal\n" "control characters are allowed in the string.\n" "\n" "Returns a tuple of the decoded string and the index of the character in s\n" "after the end quote." ); static PyObject * py_scanstring(PyObject* self UNUSED, PyObject *args) { PyObject *pystr; PyObject *rval; Py_ssize_t end; Py_ssize_t next_end = -1; char *encoding = NULL; int strict = 1; if (!PyArg_ParseTuple(args, "OO&|zi:scanstring", &pystr, _convertPyInt_AsSsize_t, &end, &encoding, &strict)) { return NULL; } if (encoding == NULL) { encoding = DEFAULT_ENCODING; } if (PyUnicode_Check(pystr)) { rval = scanstring_unicode(pystr, end, strict, &next_end); } #if PY_MAJOR_VERSION < 3 /* Using a bytes input is unsupported for scanning in Python 3. It is coerced to str in the decoder before it gets here. */ else if (PyString_Check(pystr)) { rval = scanstring_str(pystr, end, encoding, strict, &next_end); } #endif else { PyErr_Format(PyExc_TypeError, "first argument must be a string, not %.80s", Py_TYPE(pystr)->tp_name); return NULL; } return _build_rval_index_tuple(rval, next_end); } PyDoc_STRVAR(pydoc_encode_basestring_ascii, "encode_basestring_ascii(basestring) -> str\n" "\n" "Return an ASCII-only JSON representation of a Python string" ); static PyObject * py_encode_basestring_ascii(PyObject* self UNUSED, PyObject *pystr) { /* Return an ASCII-only JSON representation of a Python string */ /* METH_O */ if (PyString_Check(pystr)) { return ascii_escape_str(pystr); } else if (PyUnicode_Check(pystr)) { return ascii_escape_unicode(pystr); } else { PyErr_Format(PyExc_TypeError, "first argument must be a string, not %.80s", Py_TYPE(pystr)->tp_name); return NULL; } } static void scanner_dealloc(PyObject *self) { /* Deallocate scanner object */ scanner_clear(self); Py_TYPE(self)->tp_free(self); } static int scanner_traverse(PyObject *self, visitproc visit, void *arg) { PyScannerObject *s; assert(PyScanner_Check(self)); s = (PyScannerObject *)self; Py_VISIT(s->encoding); Py_VISIT(s->strict); Py_VISIT(s->object_hook); Py_VISIT(s->pairs_hook); Py_VISIT(s->parse_float); Py_VISIT(s->parse_int); Py_VISIT(s->parse_constant); Py_VISIT(s->memo); return 0; } static int scanner_clear(PyObject *self) { PyScannerObject *s; assert(PyScanner_Check(self)); s = (PyScannerObject *)self; Py_CLEAR(s->encoding); Py_CLEAR(s->strict); Py_CLEAR(s->object_hook); Py_CLEAR(s->pairs_hook); Py_CLEAR(s->parse_float); Py_CLEAR(s->parse_int); Py_CLEAR(s->parse_constant); Py_CLEAR(s->memo); return 0; } #if PY_MAJOR_VERSION < 3 static PyObject * _parse_object_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) { /* Read a JSON object from PyString pystr. idx is the index of the first character after the opening curly brace. *next_idx_ptr is a return-by-reference index to the first character after the closing curly brace. Returns a new PyObject (usually a dict, but object_hook or object_pairs_hook can change that) */ char *str = PyString_AS_STRING(pystr); Py_ssize_t end_idx = PyString_GET_SIZE(pystr) - 1; PyObject *rval = NULL; PyObject *pairs = NULL; PyObject *item; PyObject *key = NULL; PyObject *val = NULL; char *encoding = JSON_ASCII_AS_STRING(s->encoding); int strict = PyObject_IsTrue(s->strict); int has_pairs_hook = (s->pairs_hook != Py_None); int did_parse = 0; Py_ssize_t next_idx; if (has_pairs_hook) { pairs = PyList_New(0); if (pairs == NULL) return NULL; } else { rval = PyDict_New(); if (rval == NULL) return NULL; } /* skip whitespace after { */ while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++; /* only loop if the object is non-empty */ if (idx <= end_idx && str[idx] != '}') { int trailing_delimiter = 0; while (idx <= end_idx) { PyObject *memokey; trailing_delimiter = 0; /* read key */ if (str[idx] != '"') { raise_errmsg(ERR_OBJECT_PROPERTY, pystr, idx); goto bail; } key = scanstring_str(pystr, idx + 1, encoding, strict, &next_idx); if (key == NULL) goto bail; memokey = PyDict_GetItem(s->memo, key); if (memokey != NULL) { Py_INCREF(memokey); Py_DECREF(key); key = memokey; } else { if (PyDict_SetItem(s->memo, key, key) < 0) goto bail; } idx = next_idx; /* skip whitespace between key and : delimiter, read :, skip whitespace */ while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++; if (idx > end_idx || str[idx] != ':') { raise_errmsg(ERR_OBJECT_PROPERTY_DELIMITER, pystr, idx); goto bail; } idx++; while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++; /* read any JSON data type */ val = scan_once_str(s, pystr, idx, &next_idx); if (val == NULL) goto bail; if (has_pairs_hook) { item = PyTuple_Pack(2, key, val); if (item == NULL) goto bail; Py_CLEAR(key); Py_CLEAR(val); if (PyList_Append(pairs, item) == -1) { Py_DECREF(item); goto bail; } Py_DECREF(item); } else { if (PyDict_SetItem(rval, key, val) < 0) goto bail; Py_CLEAR(key); Py_CLEAR(val); } idx = next_idx; /* skip whitespace before } or , */ while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++; /* bail if the object is closed or we didn't get the , delimiter */ did_parse = 1; if (idx > end_idx) break; if (str[idx] == '}') { break; } else if (str[idx] != ',') { raise_errmsg(ERR_OBJECT_DELIMITER, pystr, idx); goto bail; } idx++; /* skip whitespace after , delimiter */ while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++; trailing_delimiter = 1; } if (trailing_delimiter) { raise_errmsg(ERR_OBJECT_PROPERTY, pystr, idx); goto bail; } } /* verify that idx < end_idx, str[idx] should be '}' */ if (idx > end_idx || str[idx] != '}') { if (did_parse) { raise_errmsg(ERR_OBJECT_DELIMITER, pystr, idx); } else { raise_errmsg(ERR_OBJECT_PROPERTY_FIRST, pystr, idx); } goto bail; } /* if pairs_hook is not None: rval = object_pairs_hook(pairs) */ if (s->pairs_hook != Py_None) { val = PyObject_CallFunctionObjArgs(s->pairs_hook, pairs, NULL); if (val == NULL) goto bail; Py_DECREF(pairs); *next_idx_ptr = idx + 1; return val; } /* if object_hook is not None: rval = object_hook(rval) */ if (s->object_hook != Py_None) { val = PyObject_CallFunctionObjArgs(s->object_hook, rval, NULL); if (val == NULL) goto bail; Py_DECREF(rval); rval = val; val = NULL; } *next_idx_ptr = idx + 1; return rval; bail: Py_XDECREF(rval); Py_XDECREF(key); Py_XDECREF(val); Py_XDECREF(pairs); return NULL; } #endif /* PY_MAJOR_VERSION < 3 */ static PyObject * _parse_object_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) { /* Read a JSON object from PyUnicode pystr. idx is the index of the first character after the opening curly brace. *next_idx_ptr is a return-by-reference index to the first character after the closing curly brace. Returns a new PyObject (usually a dict, but object_hook can change that) */ void *str = PyUnicode_DATA(pystr); Py_ssize_t end_idx = PyUnicode_GetLength(pystr) - 1; PY2_UNUSED int kind = PyUnicode_KIND(pystr); PyObject *rval = NULL; PyObject *pairs = NULL; PyObject *item; PyObject *key = NULL; PyObject *val = NULL; int strict = PyObject_IsTrue(s->strict); int has_pairs_hook = (s->pairs_hook != Py_None); int did_parse = 0; Py_ssize_t next_idx; if (has_pairs_hook) { pairs = PyList_New(0); if (pairs == NULL) return NULL; } else { rval = PyDict_New(); if (rval == NULL) return NULL; } /* skip whitespace after { */ while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; /* only loop if the object is non-empty */ if (idx <= end_idx && PyUnicode_READ(kind, str, idx) != '}') { int trailing_delimiter = 0; while (idx <= end_idx) { PyObject *memokey; trailing_delimiter = 0; /* read key */ if (PyUnicode_READ(kind, str, idx) != '"') { raise_errmsg(ERR_OBJECT_PROPERTY, pystr, idx); goto bail; } key = scanstring_unicode(pystr, idx + 1, strict, &next_idx); if (key == NULL) goto bail; memokey = PyDict_GetItem(s->memo, key); if (memokey != NULL) { Py_INCREF(memokey); Py_DECREF(key); key = memokey; } else { if (PyDict_SetItem(s->memo, key, key) < 0) goto bail; } idx = next_idx; /* skip whitespace between key and : delimiter, read :, skip whitespace */ while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; if (idx > end_idx || PyUnicode_READ(kind, str, idx) != ':') { raise_errmsg(ERR_OBJECT_PROPERTY_DELIMITER, pystr, idx); goto bail; } idx++; while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; /* read any JSON term */ val = scan_once_unicode(s, pystr, idx, &next_idx); if (val == NULL) goto bail; if (has_pairs_hook) { item = PyTuple_Pack(2, key, val); if (item == NULL) goto bail; Py_CLEAR(key); Py_CLEAR(val); if (PyList_Append(pairs, item) == -1) { Py_DECREF(item); goto bail; } Py_DECREF(item); } else { if (PyDict_SetItem(rval, key, val) < 0) goto bail; Py_CLEAR(key); Py_CLEAR(val); } idx = next_idx; /* skip whitespace before } or , */ while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; /* bail if the object is closed or we didn't get the , delimiter */ did_parse = 1; if (idx > end_idx) break; if (PyUnicode_READ(kind, str, idx) == '}') { break; } else if (PyUnicode_READ(kind, str, idx) != ',') { raise_errmsg(ERR_OBJECT_DELIMITER, pystr, idx); goto bail; } idx++; /* skip whitespace after , delimiter */ while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; trailing_delimiter = 1; } if (trailing_delimiter) { raise_errmsg(ERR_OBJECT_PROPERTY, pystr, idx); goto bail; } } /* verify that idx < end_idx, str[idx] should be '}' */ if (idx > end_idx || PyUnicode_READ(kind, str, idx) != '}') { if (did_parse) { raise_errmsg(ERR_OBJECT_DELIMITER, pystr, idx); } else { raise_errmsg(ERR_OBJECT_PROPERTY_FIRST, pystr, idx); } goto bail; } /* if pairs_hook is not None: rval = object_pairs_hook(pairs) */ if (s->pairs_hook != Py_None) { val = PyObject_CallFunctionObjArgs(s->pairs_hook, pairs, NULL); if (val == NULL) goto bail; Py_DECREF(pairs); *next_idx_ptr = idx + 1; return val; } /* if object_hook is not None: rval = object_hook(rval) */ if (s->object_hook != Py_None) { val = PyObject_CallFunctionObjArgs(s->object_hook, rval, NULL); if (val == NULL) goto bail; Py_DECREF(rval); rval = val; val = NULL; } *next_idx_ptr = idx + 1; return rval; bail: Py_XDECREF(rval); Py_XDECREF(key); Py_XDECREF(val); Py_XDECREF(pairs); return NULL; } #if PY_MAJOR_VERSION < 3 static PyObject * _parse_array_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) { /* Read a JSON array from PyString pystr. idx is the index of the first character after the opening brace. *next_idx_ptr is a return-by-reference index to the first character after the closing brace. Returns a new PyList */ char *str = PyString_AS_STRING(pystr); Py_ssize_t end_idx = PyString_GET_SIZE(pystr) - 1; PyObject *val = NULL; PyObject *rval = PyList_New(0); Py_ssize_t next_idx; if (rval == NULL) return NULL; /* skip whitespace after [ */ while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++; /* only loop if the array is non-empty */ if (idx <= end_idx && str[idx] != ']') { int trailing_delimiter = 0; while (idx <= end_idx) { trailing_delimiter = 0; /* read any JSON term and de-tuplefy the (rval, idx) */ val = scan_once_str(s, pystr, idx, &next_idx); if (val == NULL) { goto bail; } if (PyList_Append(rval, val) == -1) goto bail; Py_CLEAR(val); idx = next_idx; /* skip whitespace between term and , */ while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++; /* bail if the array is closed or we didn't get the , delimiter */ if (idx > end_idx) break; if (str[idx] == ']') { break; } else if (str[idx] != ',') { raise_errmsg(ERR_ARRAY_DELIMITER, pystr, idx); goto bail; } idx++; /* skip whitespace after , */ while (idx <= end_idx && IS_WHITESPACE(str[idx])) idx++; trailing_delimiter = 1; } if (trailing_delimiter) { raise_errmsg(ERR_EXPECTING_VALUE, pystr, idx); goto bail; } } /* verify that idx < end_idx, str[idx] should be ']' */ if (idx > end_idx || str[idx] != ']') { if (PyList_GET_SIZE(rval)) { raise_errmsg(ERR_ARRAY_DELIMITER, pystr, idx); } else { raise_errmsg(ERR_ARRAY_VALUE_FIRST, pystr, idx); } goto bail; } *next_idx_ptr = idx + 1; return rval; bail: Py_XDECREF(val); Py_DECREF(rval); return NULL; } #endif /* PY_MAJOR_VERSION < 3 */ static PyObject * _parse_array_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) { /* Read a JSON array from PyString pystr. idx is the index of the first character after the opening brace. *next_idx_ptr is a return-by-reference index to the first character after the closing brace. Returns a new PyList */ PY2_UNUSED int kind = PyUnicode_KIND(pystr); void *str = PyUnicode_DATA(pystr); Py_ssize_t end_idx = PyUnicode_GetLength(pystr) - 1; PyObject *val = NULL; PyObject *rval = PyList_New(0); Py_ssize_t next_idx; if (rval == NULL) return NULL; /* skip whitespace after [ */ while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; /* only loop if the array is non-empty */ if (idx <= end_idx && PyUnicode_READ(kind, str, idx) != ']') { int trailing_delimiter = 0; while (idx <= end_idx) { trailing_delimiter = 0; /* read any JSON term */ val = scan_once_unicode(s, pystr, idx, &next_idx); if (val == NULL) { goto bail; } if (PyList_Append(rval, val) == -1) goto bail; Py_CLEAR(val); idx = next_idx; /* skip whitespace between term and , */ while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; /* bail if the array is closed or we didn't get the , delimiter */ if (idx > end_idx) break; if (PyUnicode_READ(kind, str, idx) == ']') { break; } else if (PyUnicode_READ(kind, str, idx) != ',') { raise_errmsg(ERR_ARRAY_DELIMITER, pystr, idx); goto bail; } idx++; /* skip whitespace after , */ while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; trailing_delimiter = 1; } if (trailing_delimiter) { raise_errmsg(ERR_EXPECTING_VALUE, pystr, idx); goto bail; } } /* verify that idx < end_idx, str[idx] should be ']' */ if (idx > end_idx || PyUnicode_READ(kind, str, idx) != ']') { if (PyList_GET_SIZE(rval)) { raise_errmsg(ERR_ARRAY_DELIMITER, pystr, idx); } else { raise_errmsg(ERR_ARRAY_VALUE_FIRST, pystr, idx); } goto bail; } *next_idx_ptr = idx + 1; return rval; bail: Py_XDECREF(val); Py_DECREF(rval); return NULL; } static PyObject * _parse_constant(PyScannerObject *s, char *constant, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) { /* Read a JSON constant from PyString pystr. constant is the constant string that was found ("NaN", "Infinity", "-Infinity"). idx is the index of the first character of the constant *next_idx_ptr is a return-by-reference index to the first character after the constant. Returns the result of parse_constant */ PyObject *cstr; PyObject *rval; /* constant is "NaN", "Infinity", or "-Infinity" */ cstr = JSON_InternFromString(constant); if (cstr == NULL) return NULL; /* rval = parse_constant(constant) */ rval = PyObject_CallFunctionObjArgs(s->parse_constant, cstr, NULL); idx += JSON_Intern_GET_SIZE(cstr); Py_DECREF(cstr); *next_idx_ptr = idx; return rval; } #if PY_MAJOR_VERSION < 3 static PyObject * _match_number_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t start, Py_ssize_t *next_idx_ptr) { /* Read a JSON number from PyString pystr. idx is the index of the first character of the number *next_idx_ptr is a return-by-reference index to the first character after the number. Returns a new PyObject representation of that number: PyInt, PyLong, or PyFloat. May return other types if parse_int or parse_float are set */ char *str = PyString_AS_STRING(pystr); Py_ssize_t end_idx = PyString_GET_SIZE(pystr) - 1; Py_ssize_t idx = start; int is_float = 0; PyObject *rval; PyObject *numstr; /* read a sign if it's there, make sure it's not the end of the string */ if (str[idx] == '-') { if (idx >= end_idx) { raise_errmsg(ERR_EXPECTING_VALUE, pystr, idx); return NULL; } idx++; } /* read as many integer digits as we find as long as it doesn't start with 0 */ if (str[idx] >= '1' && str[idx] <= '9') { idx++; while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++; } /* if it starts with 0 we only expect one integer digit */ else if (str[idx] == '0') { idx++; } /* no integer digits, error */ else { raise_errmsg(ERR_EXPECTING_VALUE, pystr, idx); return NULL; } /* if the next char is '.' followed by a digit then read all float digits */ if (idx < end_idx && str[idx] == '.' && str[idx + 1] >= '0' && str[idx + 1] <= '9') { is_float = 1; idx += 2; while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++; } /* if the next char is 'e' or 'E' then maybe read the exponent (or backtrack) */ if (idx < end_idx && (str[idx] == 'e' || str[idx] == 'E')) { /* save the index of the 'e' or 'E' just in case we need to backtrack */ Py_ssize_t e_start = idx; idx++; /* read an exponent sign if present */ if (idx < end_idx && (str[idx] == '-' || str[idx] == '+')) idx++; /* read all digits */ while (idx <= end_idx && str[idx] >= '0' && str[idx] <= '9') idx++; /* if we got a digit, then parse as float. if not, backtrack */ if (str[idx - 1] >= '0' && str[idx - 1] <= '9') { is_float = 1; } else { idx = e_start; } } /* copy the section we determined to be a number */ numstr = PyString_FromStringAndSize(&str[start], idx - start); if (numstr == NULL) return NULL; if (is_float) { /* parse as a float using a fast path if available, otherwise call user defined method */ if (s->parse_float != (PyObject *)&PyFloat_Type) { rval = PyObject_CallFunctionObjArgs(s->parse_float, numstr, NULL); } else { /* rval = PyFloat_FromDouble(PyOS_ascii_atof(PyString_AS_STRING(numstr))); */ double d = PyOS_string_to_double(PyString_AS_STRING(numstr), NULL, NULL); if (d == -1.0 && PyErr_Occurred()) return NULL; rval = PyFloat_FromDouble(d); } } else { /* parse as an int using a fast path if available, otherwise call user defined method */ if (s->parse_int != (PyObject *)&PyInt_Type) { rval = PyObject_CallFunctionObjArgs(s->parse_int, numstr, NULL); } else { rval = PyInt_FromString(PyString_AS_STRING(numstr), NULL, 10); } } Py_DECREF(numstr); *next_idx_ptr = idx; return rval; } #endif /* PY_MAJOR_VERSION < 3 */ static PyObject * _match_number_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t start, Py_ssize_t *next_idx_ptr) { /* Read a JSON number from PyUnicode pystr. idx is the index of the first character of the number *next_idx_ptr is a return-by-reference index to the first character after the number. Returns a new PyObject representation of that number: PyInt, PyLong, or PyFloat. May return other types if parse_int or parse_float are set */ PY2_UNUSED int kind = PyUnicode_KIND(pystr); void *str = PyUnicode_DATA(pystr); Py_ssize_t end_idx = PyUnicode_GetLength(pystr) - 1; Py_ssize_t idx = start; int is_float = 0; JSON_UNICHR c; PyObject *rval; PyObject *numstr; /* read a sign if it's there, make sure it's not the end of the string */ if (PyUnicode_READ(kind, str, idx) == '-') { if (idx >= end_idx) { raise_errmsg(ERR_EXPECTING_VALUE, pystr, idx); return NULL; } idx++; } /* read as many integer digits as we find as long as it doesn't start with 0 */ c = PyUnicode_READ(kind, str, idx); if (c == '0') { /* if it starts with 0 we only expect one integer digit */ idx++; } else if (IS_DIGIT(c)) { idx++; while (idx <= end_idx && IS_DIGIT(PyUnicode_READ(kind, str, idx))) { idx++; } } else { /* no integer digits, error */ raise_errmsg(ERR_EXPECTING_VALUE, pystr, idx); return NULL; } /* if the next char is '.' followed by a digit then read all float digits */ if (idx < end_idx && PyUnicode_READ(kind, str, idx) == '.' && IS_DIGIT(PyUnicode_READ(kind, str, idx + 1))) { is_float = 1; idx += 2; while (idx <= end_idx && IS_DIGIT(PyUnicode_READ(kind, str, idx))) idx++; } /* if the next char is 'e' or 'E' then maybe read the exponent (or backtrack) */ if (idx < end_idx && (PyUnicode_READ(kind, str, idx) == 'e' || PyUnicode_READ(kind, str, idx) == 'E')) { Py_ssize_t e_start = idx; idx++; /* read an exponent sign if present */ if (idx < end_idx && (PyUnicode_READ(kind, str, idx) == '-' || PyUnicode_READ(kind, str, idx) == '+')) idx++; /* read all digits */ while (idx <= end_idx && IS_DIGIT(PyUnicode_READ(kind, str, idx))) idx++; /* if we got a digit, then parse as float. if not, backtrack */ if (IS_DIGIT(PyUnicode_READ(kind, str, idx - 1))) { is_float = 1; } else { idx = e_start; } } /* copy the section we determined to be a number */ #if PY_MAJOR_VERSION >= 3 numstr = PyUnicode_Substring(pystr, start, idx); #else numstr = PyUnicode_FromUnicode(&((Py_UNICODE *)str)[start], idx - start); #endif if (numstr == NULL) return NULL; if (is_float) { /* parse as a float using a fast path if available, otherwise call user defined method */ if (s->parse_float != (PyObject *)&PyFloat_Type) { rval = PyObject_CallFunctionObjArgs(s->parse_float, numstr, NULL); } else { #if PY_MAJOR_VERSION >= 3 rval = PyFloat_FromString(numstr); #else rval = PyFloat_FromString(numstr, NULL); #endif } } else { /* no fast path for unicode -> int, just call */ rval = PyObject_CallFunctionObjArgs(s->parse_int, numstr, NULL); } Py_DECREF(numstr); *next_idx_ptr = idx; return rval; } #if PY_MAJOR_VERSION < 3 static PyObject * scan_once_str(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) { /* Read one JSON term (of any kind) from PyString pystr. idx is the index of the first character of the term *next_idx_ptr is a return-by-reference index to the first character after the number. Returns a new PyObject representation of the term. */ char *str = PyString_AS_STRING(pystr); Py_ssize_t length = PyString_GET_SIZE(pystr); PyObject *rval = NULL; int fallthrough = 0; if (idx < 0 || idx >= length) { raise_errmsg(ERR_EXPECTING_VALUE, pystr, idx); return NULL; } switch (str[idx]) { case '"': /* string */ rval = scanstring_str(pystr, idx + 1, JSON_ASCII_AS_STRING(s->encoding), PyObject_IsTrue(s->strict), next_idx_ptr); break; case '{': /* object */ if (Py_EnterRecursiveCall(" while decoding a JSON object " "from a string")) return NULL; rval = _parse_object_str(s, pystr, idx + 1, next_idx_ptr); Py_LeaveRecursiveCall(); break; case '[': /* array */ if (Py_EnterRecursiveCall(" while decoding a JSON array " "from a string")) return NULL; rval = _parse_array_str(s, pystr, idx + 1, next_idx_ptr); Py_LeaveRecursiveCall(); break; case 'n': /* null */ if ((idx + 3 < length) && str[idx + 1] == 'u' && str[idx + 2] == 'l' && str[idx + 3] == 'l') { Py_INCREF(Py_None); *next_idx_ptr = idx + 4; rval = Py_None; } else fallthrough = 1; break; case 't': /* true */ if ((idx + 3 < length) && str[idx + 1] == 'r' && str[idx + 2] == 'u' && str[idx + 3] == 'e') { Py_INCREF(Py_True); *next_idx_ptr = idx + 4; rval = Py_True; } else fallthrough = 1; break; case 'f': /* false */ if ((idx + 4 < length) && str[idx + 1] == 'a' && str[idx + 2] == 'l' && str[idx + 3] == 's' && str[idx + 4] == 'e') { Py_INCREF(Py_False); *next_idx_ptr = idx + 5; rval = Py_False; } else fallthrough = 1; break; case 'N': /* NaN */ if ((idx + 2 < length) && str[idx + 1] == 'a' && str[idx + 2] == 'N') { rval = _parse_constant(s, "NaN", idx, next_idx_ptr); } else fallthrough = 1; break; case 'I': /* Infinity */ if ((idx + 7 < length) && str[idx + 1] == 'n' && str[idx + 2] == 'f' && str[idx + 3] == 'i' && str[idx + 4] == 'n' && str[idx + 5] == 'i' && str[idx + 6] == 't' && str[idx + 7] == 'y') { rval = _parse_constant(s, "Infinity", idx, next_idx_ptr); } else fallthrough = 1; break; case '-': /* -Infinity */ if ((idx + 8 < length) && str[idx + 1] == 'I' && str[idx + 2] == 'n' && str[idx + 3] == 'f' && str[idx + 4] == 'i' && str[idx + 5] == 'n' && str[idx + 6] == 'i' && str[idx + 7] == 't' && str[idx + 8] == 'y') { rval = _parse_constant(s, "-Infinity", idx, next_idx_ptr); } else fallthrough = 1; break; default: fallthrough = 1; } /* Didn't find a string, object, array, or named constant. Look for a number. */ if (fallthrough) rval = _match_number_str(s, pystr, idx, next_idx_ptr); return rval; } #endif /* PY_MAJOR_VERSION < 3 */ static PyObject * scan_once_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) { /* Read one JSON term (of any kind) from PyUnicode pystr. idx is the index of the first character of the term *next_idx_ptr is a return-by-reference index to the first character after the number. Returns a new PyObject representation of the term. */ PY2_UNUSED int kind = PyUnicode_KIND(pystr); void *str = PyUnicode_DATA(pystr); Py_ssize_t length = PyUnicode_GetLength(pystr); PyObject *rval = NULL; int fallthrough = 0; if (idx < 0 || idx >= length) { raise_errmsg(ERR_EXPECTING_VALUE, pystr, idx); return NULL; } switch (PyUnicode_READ(kind, str, idx)) { case '"': /* string */ rval = scanstring_unicode(pystr, idx + 1, PyObject_IsTrue(s->strict), next_idx_ptr); break; case '{': /* object */ if (Py_EnterRecursiveCall(" while decoding a JSON object " "from a unicode string")) return NULL; rval = _parse_object_unicode(s, pystr, idx + 1, next_idx_ptr); Py_LeaveRecursiveCall(); break; case '[': /* array */ if (Py_EnterRecursiveCall(" while decoding a JSON array " "from a unicode string")) return NULL; rval = _parse_array_unicode(s, pystr, idx + 1, next_idx_ptr); Py_LeaveRecursiveCall(); break; case 'n': /* null */ if ((idx + 3 < length) && PyUnicode_READ(kind, str, idx + 1) == 'u' && PyUnicode_READ(kind, str, idx + 2) == 'l' && PyUnicode_READ(kind, str, idx + 3) == 'l') { Py_INCREF(Py_None); *next_idx_ptr = idx + 4; rval = Py_None; } else fallthrough = 1; break; case 't': /* true */ if ((idx + 3 < length) && PyUnicode_READ(kind, str, idx + 1) == 'r' && PyUnicode_READ(kind, str, idx + 2) == 'u' && PyUnicode_READ(kind, str, idx + 3) == 'e') { Py_INCREF(Py_True); *next_idx_ptr = idx + 4; rval = Py_True; } else fallthrough = 1; break; case 'f': /* false */ if ((idx + 4 < length) && PyUnicode_READ(kind, str, idx + 1) == 'a' && PyUnicode_READ(kind, str, idx + 2) == 'l' && PyUnicode_READ(kind, str, idx + 3) == 's' && PyUnicode_READ(kind, str, idx + 4) == 'e') { Py_INCREF(Py_False); *next_idx_ptr = idx + 5; rval = Py_False; } else fallthrough = 1; break; case 'N': /* NaN */ if ((idx + 2 < length) && PyUnicode_READ(kind, str, idx + 1) == 'a' && PyUnicode_READ(kind, str, idx + 2) == 'N') { rval = _parse_constant(s, "NaN", idx, next_idx_ptr); } else fallthrough = 1; break; case 'I': /* Infinity */ if ((idx + 7 < length) && PyUnicode_READ(kind, str, idx + 1) == 'n' && PyUnicode_READ(kind, str, idx + 2) == 'f' && PyUnicode_READ(kind, str, idx + 3) == 'i' && PyUnicode_READ(kind, str, idx + 4) == 'n' && PyUnicode_READ(kind, str, idx + 5) == 'i' && PyUnicode_READ(kind, str, idx + 6) == 't' && PyUnicode_READ(kind, str, idx + 7) == 'y') { rval = _parse_constant(s, "Infinity", idx, next_idx_ptr); } else fallthrough = 1; break; case '-': /* -Infinity */ if ((idx + 8 < length) && PyUnicode_READ(kind, str, idx + 1) == 'I' && PyUnicode_READ(kind, str, idx + 2) == 'n' && PyUnicode_READ(kind, str, idx + 3) == 'f' && PyUnicode_READ(kind, str, idx + 4) == 'i' && PyUnicode_READ(kind, str, idx + 5) == 'n' && PyUnicode_READ(kind, str, idx + 6) == 'i' && PyUnicode_READ(kind, str, idx + 7) == 't' && PyUnicode_READ(kind, str, idx + 8) == 'y') { rval = _parse_constant(s, "-Infinity", idx, next_idx_ptr); } else fallthrough = 1; break; default: fallthrough = 1; } /* Didn't find a string, object, array, or named constant. Look for a number. */ if (fallthrough) rval = _match_number_unicode(s, pystr, idx, next_idx_ptr); return rval; } static PyObject * scanner_call(PyObject *self, PyObject *args, PyObject *kwds) { /* Python callable interface to scan_once_{str,unicode} */ PyObject *pystr; PyObject *rval; Py_ssize_t idx; Py_ssize_t next_idx = -1; static char *kwlist[] = {"string", "idx", NULL}; PyScannerObject *s; assert(PyScanner_Check(self)); s = (PyScannerObject *)self; if (!PyArg_ParseTupleAndKeywords(args, kwds, "OO&:scan_once", kwlist, &pystr, _convertPyInt_AsSsize_t, &idx)) return NULL; if (PyUnicode_Check(pystr)) { rval = scan_once_unicode(s, pystr, idx, &next_idx); } #if PY_MAJOR_VERSION < 3 else if (PyString_Check(pystr)) { rval = scan_once_str(s, pystr, idx, &next_idx); } #endif /* PY_MAJOR_VERSION < 3 */ else { PyErr_Format(PyExc_TypeError, "first argument must be a string, not %.80s", Py_TYPE(pystr)->tp_name); return NULL; } PyDict_Clear(s->memo); return _build_rval_index_tuple(rval, next_idx); } static PyObject * scanner_new(PyTypeObject *type, PyObject *args, PyObject *kwds) { PyScannerObject *s; s = (PyScannerObject *)type->tp_alloc(type, 0); if (s != NULL) { s->encoding = NULL; s->strict = NULL; s->object_hook = NULL; s->pairs_hook = NULL; s->parse_float = NULL; s->parse_int = NULL; s->parse_constant = NULL; } return (PyObject *)s; } static PyObject * JSON_ParseEncoding(PyObject *encoding) { if (encoding == NULL) return NULL; if (encoding == Py_None) return JSON_InternFromString(DEFAULT_ENCODING); #if PY_MAJOR_VERSION < 3 if (PyUnicode_Check(encoding)) return PyUnicode_AsEncodedString(encoding, NULL, NULL); #endif if (JSON_ASCII_Check(encoding)) { Py_INCREF(encoding); return encoding; } PyErr_SetString(PyExc_TypeError, "encoding must be a string"); return NULL; } static int scanner_init(PyObject *self, PyObject *args, PyObject *kwds) { /* Initialize Scanner object */ PyObject *ctx; static char *kwlist[] = {"context", NULL}; PyScannerObject *s; PyObject *encoding; assert(PyScanner_Check(self)); s = (PyScannerObject *)self; if (!PyArg_ParseTupleAndKeywords(args, kwds, "O:make_scanner", kwlist, &ctx)) return -1; if (s->memo == NULL) { s->memo = PyDict_New(); if (s->memo == NULL) goto bail; } /* JSON_ASCII_AS_STRING is used on encoding */ encoding = PyObject_GetAttrString(ctx, "encoding"); s->encoding = JSON_ParseEncoding(encoding); Py_XDECREF(encoding); if (s->encoding == NULL) goto bail; /* All of these will fail "gracefully" so we don't need to verify them */ s->strict = PyObject_GetAttrString(ctx, "strict"); if (s->strict == NULL) goto bail; s->object_hook = PyObject_GetAttrString(ctx, "object_hook"); if (s->object_hook == NULL) goto bail; s->pairs_hook = PyObject_GetAttrString(ctx, "object_pairs_hook"); if (s->pairs_hook == NULL) goto bail; s->parse_float = PyObject_GetAttrString(ctx, "parse_float"); if (s->parse_float == NULL) goto bail; s->parse_int = PyObject_GetAttrString(ctx, "parse_int"); if (s->parse_int == NULL) goto bail; s->parse_constant = PyObject_GetAttrString(ctx, "parse_constant"); if (s->parse_constant == NULL) goto bail; return 0; bail: Py_CLEAR(s->encoding); Py_CLEAR(s->strict); Py_CLEAR(s->object_hook); Py_CLEAR(s->pairs_hook); Py_CLEAR(s->parse_float); Py_CLEAR(s->parse_int); Py_CLEAR(s->parse_constant); return -1; } PyDoc_STRVAR(scanner_doc, "JSON scanner object"); static PyTypeObject PyScannerType = { PyVarObject_HEAD_INIT(NULL, 0) "simplejson._speedups.Scanner", /* tp_name */ sizeof(PyScannerObject), /* tp_basicsize */ 0, /* tp_itemsize */ scanner_dealloc, /* tp_dealloc */ 0, /* tp_print */ 0, /* tp_getattr */ 0, /* tp_setattr */ 0, /* tp_compare */ 0, /* tp_repr */ 0, /* tp_as_number */ 0, /* tp_as_sequence */ 0, /* tp_as_mapping */ 0, /* tp_hash */ scanner_call, /* tp_call */ 0, /* tp_str */ 0,/* PyObject_GenericGetAttr, */ /* tp_getattro */ 0,/* PyObject_GenericSetAttr, */ /* tp_setattro */ 0, /* tp_as_buffer */ Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC, /* tp_flags */ scanner_doc, /* tp_doc */ scanner_traverse, /* tp_traverse */ scanner_clear, /* tp_clear */ 0, /* tp_richcompare */ 0, /* tp_weaklistoffset */ 0, /* tp_iter */ 0, /* tp_iternext */ 0, /* tp_methods */ scanner_members, /* tp_members */ 0, /* tp_getset */ 0, /* tp_base */ 0, /* tp_dict */ 0, /* tp_descr_get */ 0, /* tp_descr_set */ 0, /* tp_dictoffset */ scanner_init, /* tp_init */ 0,/* PyType_GenericAlloc, */ /* tp_alloc */ scanner_new, /* tp_new */ 0,/* PyObject_GC_Del, */ /* tp_free */ }; static PyObject * encoder_new(PyTypeObject *type, PyObject *args, PyObject *kwds) { PyEncoderObject *s; s = (PyEncoderObject *)type->tp_alloc(type, 0); if (s != NULL) { s->markers = NULL; s->defaultfn = NULL; s->encoder = NULL; s->encoding = NULL; s->indent = NULL; s->key_separator = NULL; s->item_separator = NULL; s->key_memo = NULL; s->sort_keys = NULL; s->item_sort_key = NULL; s->item_sort_kw = NULL; s->Decimal = NULL; s->max_long_size = NULL; s->min_long_size = NULL; } return (PyObject *)s; } static int encoder_init(PyObject *self, PyObject *args, PyObject *kwds) { static char *kwlist[] = { "markers", "default", "encoder", "indent", "key_separator", "item_separator", "sort_keys", "skipkeys", "allow_nan", "key_memo", "use_decimal", "namedtuple_as_object", "tuple_as_array", "int_as_string_bitcount", "item_sort_key", "encoding", "for_json", "ignore_nan", "Decimal", "iterable_as_array", NULL}; PyEncoderObject *s; PyObject *markers, *defaultfn, *encoder, *indent, *key_separator; PyObject *item_separator, *sort_keys, *skipkeys, *allow_nan, *key_memo; PyObject *use_decimal, *namedtuple_as_object, *tuple_as_array, *iterable_as_array; PyObject *int_as_string_bitcount, *item_sort_key, *encoding, *for_json; PyObject *ignore_nan, *Decimal; assert(PyEncoder_Check(self)); s = (PyEncoderObject *)self; if (!PyArg_ParseTupleAndKeywords(args, kwds, "OOOOOOOOOOOOOOOOOOOO:make_encoder", kwlist, &markers, &defaultfn, &encoder, &indent, &key_separator, &item_separator, &sort_keys, &skipkeys, &allow_nan, &key_memo, &use_decimal, &namedtuple_as_object, &tuple_as_array, &int_as_string_bitcount, &item_sort_key, &encoding, &for_json, &ignore_nan, &Decimal, &iterable_as_array)) return -1; Py_INCREF(markers); s->markers = markers; Py_INCREF(defaultfn); s->defaultfn = defaultfn; Py_INCREF(encoder); s->encoder = encoder; s->encoding = JSON_ParseEncoding(encoding); if (s->encoding == NULL) return -1; Py_INCREF(indent); s->indent = indent; Py_INCREF(key_separator); s->key_separator = key_separator; Py_INCREF(item_separator); s->item_separator = item_separator; Py_INCREF(skipkeys); s->skipkeys_bool = skipkeys; s->skipkeys = PyObject_IsTrue(skipkeys); Py_INCREF(key_memo); s->key_memo = key_memo; s->fast_encode = (PyCFunction_Check(s->encoder) && PyCFunction_GetFunction(s->encoder) == (PyCFunction)py_encode_basestring_ascii); s->allow_or_ignore_nan = ( (PyObject_IsTrue(ignore_nan) ? JSON_IGNORE_NAN : 0) | (PyObject_IsTrue(allow_nan) ? JSON_ALLOW_NAN : 0)); s->use_decimal = PyObject_IsTrue(use_decimal); s->namedtuple_as_object = PyObject_IsTrue(namedtuple_as_object); s->tuple_as_array = PyObject_IsTrue(tuple_as_array); s->iterable_as_array = PyObject_IsTrue(iterable_as_array); if (PyInt_Check(int_as_string_bitcount) || PyLong_Check(int_as_string_bitcount)) { static const unsigned int long_long_bitsize = SIZEOF_LONG_LONG * 8; int int_as_string_bitcount_val = (int)PyLong_AsLong(int_as_string_bitcount); if (int_as_string_bitcount_val > 0 && int_as_string_bitcount_val < long_long_bitsize) { s->max_long_size = PyLong_FromUnsignedLongLong(1ULL << int_as_string_bitcount_val); s->min_long_size = PyLong_FromLongLong(-1LL << int_as_string_bitcount_val); if (s->min_long_size == NULL || s->max_long_size == NULL) { return -1; } } else { PyErr_Format(PyExc_TypeError, "int_as_string_bitcount (%d) must be greater than 0 and less than the number of bits of a `long long` type (%u bits)", int_as_string_bitcount_val, long_long_bitsize); return -1; } } else if (int_as_string_bitcount == Py_None) { Py_INCREF(Py_None); s->max_long_size = Py_None; Py_INCREF(Py_None); s->min_long_size = Py_None; } else { PyErr_SetString(PyExc_TypeError, "int_as_string_bitcount must be None or an integer"); return -1; } if (item_sort_key != Py_None) { if (!PyCallable_Check(item_sort_key)) { PyErr_SetString(PyExc_TypeError, "item_sort_key must be None or callable"); return -1; } } else if (PyObject_IsTrue(sort_keys)) { static PyObject *itemgetter0 = NULL; if (!itemgetter0) { PyObject *operator = PyImport_ImportModule("operator"); if (!operator) return -1; itemgetter0 = PyObject_CallMethod(operator, "itemgetter", "i", 0); Py_DECREF(operator); } item_sort_key = itemgetter0; if (!item_sort_key) return -1; } if (item_sort_key == Py_None) { Py_INCREF(Py_None); s->item_sort_kw = Py_None; } else { s->item_sort_kw = PyDict_New(); if (s->item_sort_kw == NULL) return -1; if (PyDict_SetItemString(s->item_sort_kw, "key", item_sort_key)) return -1; } Py_INCREF(sort_keys); s->sort_keys = sort_keys; Py_INCREF(item_sort_key); s->item_sort_key = item_sort_key; Py_INCREF(Decimal); s->Decimal = Decimal; s->for_json = PyObject_IsTrue(for_json); return 0; } static PyObject * encoder_call(PyObject *self, PyObject *args, PyObject *kwds) { /* Python callable interface to encode_listencode_obj */ static char *kwlist[] = {"obj", "_current_indent_level", NULL}; PyObject *obj; Py_ssize_t indent_level; PyEncoderObject *s; JSON_Accu rval; assert(PyEncoder_Check(self)); s = (PyEncoderObject *)self; if (!PyArg_ParseTupleAndKeywords(args, kwds, "OO&:_iterencode", kwlist, &obj, _convertPyInt_AsSsize_t, &indent_level)) return NULL; if (JSON_Accu_Init(&rval)) return NULL; if (encoder_listencode_obj(s, &rval, obj, indent_level)) { JSON_Accu_Destroy(&rval); return NULL; } return JSON_Accu_FinishAsList(&rval); } static PyObject * _encoded_const(PyObject *obj) { /* Return the JSON string representation of None, True, False */ if (obj == Py_None) { static PyObject *s_null = NULL; if (s_null == NULL) { s_null = JSON_InternFromString("null"); } Py_INCREF(s_null); return s_null; } else if (obj == Py_True) { static PyObject *s_true = NULL; if (s_true == NULL) { s_true = JSON_InternFromString("true"); } Py_INCREF(s_true); return s_true; } else if (obj == Py_False) { static PyObject *s_false = NULL; if (s_false == NULL) { s_false = JSON_InternFromString("false"); } Py_INCREF(s_false); return s_false; } else { PyErr_SetString(PyExc_ValueError, "not a const"); return NULL; } } static PyObject * encoder_encode_float(PyEncoderObject *s, PyObject *obj) { /* Return the JSON representation of a PyFloat */ double i = PyFloat_AS_DOUBLE(obj); if (!Py_IS_FINITE(i)) { if (!s->allow_or_ignore_nan) { PyErr_SetString(PyExc_ValueError, "Out of range float values are not JSON compliant"); return NULL; } if (s->allow_or_ignore_nan & JSON_IGNORE_NAN) { return _encoded_const(Py_None); } /* JSON_ALLOW_NAN is set */ else if (i > 0) { static PyObject *sInfinity = NULL; if (sInfinity == NULL) sInfinity = JSON_InternFromString("Infinity"); if (sInfinity) Py_INCREF(sInfinity); return sInfinity; } else if (i < 0) { static PyObject *sNegInfinity = NULL; if (sNegInfinity == NULL) sNegInfinity = JSON_InternFromString("-Infinity"); if (sNegInfinity) Py_INCREF(sNegInfinity); return sNegInfinity; } else { static PyObject *sNaN = NULL; if (sNaN == NULL) sNaN = JSON_InternFromString("NaN"); if (sNaN) Py_INCREF(sNaN); return sNaN; } } /* Use a better float format here? */ if (PyFloat_CheckExact(obj)) { return PyObject_Repr(obj); } else { /* See #118, do not trust custom str/repr */ PyObject *res; PyObject *tmp = PyObject_CallFunctionObjArgs((PyObject *)&PyFloat_Type, obj, NULL); if (tmp == NULL) { return NULL; } res = PyObject_Repr(tmp); Py_DECREF(tmp); return res; } } static PyObject * encoder_encode_string(PyEncoderObject *s, PyObject *obj) { /* Return the JSON representation of a string */ if (s->fast_encode) return py_encode_basestring_ascii(NULL, obj); else return PyObject_CallFunctionObjArgs(s->encoder, obj, NULL); } static int _steal_accumulate(JSON_Accu *accu, PyObject *stolen) { /* Append stolen and then decrement its reference count */ int rval = JSON_Accu_Accumulate(accu, stolen); Py_DECREF(stolen); return rval; } static int encoder_listencode_obj(PyEncoderObject *s, JSON_Accu *rval, PyObject *obj, Py_ssize_t indent_level) { /* Encode Python object obj to a JSON term, rval is a PyList */ int rv = -1; do { if (obj == Py_None || obj == Py_True || obj == Py_False) { PyObject *cstr = _encoded_const(obj); if (cstr != NULL) rv = _steal_accumulate(rval, cstr); } else if (PyString_Check(obj) || PyUnicode_Check(obj)) { PyObject *encoded = encoder_encode_string(s, obj); if (encoded != NULL) rv = _steal_accumulate(rval, encoded); } else if (PyInt_Check(obj) || PyLong_Check(obj)) { PyObject *encoded; if (PyInt_CheckExact(obj) || PyLong_CheckExact(obj)) { encoded = PyObject_Str(obj); } else { /* See #118, do not trust custom str/repr */ PyObject *tmp = PyObject_CallFunctionObjArgs((PyObject *)&PyLong_Type, obj, NULL); if (tmp == NULL) { encoded = NULL; } else { encoded = PyObject_Str(tmp); Py_DECREF(tmp); } } if (encoded != NULL) { encoded = maybe_quote_bigint(s, encoded, obj); if (encoded == NULL) break; rv = _steal_accumulate(rval, encoded); } } else if (PyFloat_Check(obj)) { PyObject *encoded = encoder_encode_float(s, obj); if (encoded != NULL) rv = _steal_accumulate(rval, encoded); } else if (s->for_json && _has_for_json_hook(obj)) { PyObject *newobj; if (Py_EnterRecursiveCall(" while encoding a JSON object")) return rv; newobj = PyObject_CallMethod(obj, "for_json", NULL); if (newobj != NULL) { rv = encoder_listencode_obj(s, rval, newobj, indent_level); Py_DECREF(newobj); } Py_LeaveRecursiveCall(); } else if (s->namedtuple_as_object && _is_namedtuple(obj)) { PyObject *newobj; if (Py_EnterRecursiveCall(" while encoding a JSON object")) return rv; newobj = PyObject_CallMethod(obj, "_asdict", NULL); if (newobj != NULL) { rv = encoder_listencode_dict(s, rval, newobj, indent_level); Py_DECREF(newobj); } Py_LeaveRecursiveCall(); } else if (PyList_Check(obj) || (s->tuple_as_array && PyTuple_Check(obj))) { if (Py_EnterRecursiveCall(" while encoding a JSON object")) return rv; rv = encoder_listencode_list(s, rval, obj, indent_level); Py_LeaveRecursiveCall(); } else if (PyDict_Check(obj)) { if (Py_EnterRecursiveCall(" while encoding a JSON object")) return rv; rv = encoder_listencode_dict(s, rval, obj, indent_level); Py_LeaveRecursiveCall(); } else if (s->use_decimal && PyObject_TypeCheck(obj, (PyTypeObject *)s->Decimal)) { PyObject *encoded = PyObject_Str(obj); if (encoded != NULL) rv = _steal_accumulate(rval, encoded); } else { PyObject *ident = NULL; PyObject *newobj; if (s->iterable_as_array) { newobj = PyObject_GetIter(obj); if (newobj == NULL) PyErr_Clear(); else { rv = encoder_listencode_list(s, rval, newobj, indent_level); Py_DECREF(newobj); break; } } if (s->markers != Py_None) { int has_key; ident = PyLong_FromVoidPtr(obj); if (ident == NULL) break; has_key = PyDict_Contains(s->markers, ident); if (has_key) { if (has_key != -1) PyErr_SetString(PyExc_ValueError, "Circular reference detected"); Py_DECREF(ident); break; } if (PyDict_SetItem(s->markers, ident, obj)) { Py_DECREF(ident); break; } } if (Py_EnterRecursiveCall(" while encoding a JSON object")) return rv; newobj = PyObject_CallFunctionObjArgs(s->defaultfn, obj, NULL); if (newobj == NULL) { Py_XDECREF(ident); Py_LeaveRecursiveCall(); break; } rv = encoder_listencode_obj(s, rval, newobj, indent_level); Py_LeaveRecursiveCall(); Py_DECREF(newobj); if (rv) { Py_XDECREF(ident); rv = -1; } else if (ident != NULL) { if (PyDict_DelItem(s->markers, ident)) { Py_XDECREF(ident); rv = -1; } Py_XDECREF(ident); } } } while (0); return rv; } static int encoder_listencode_dict(PyEncoderObject *s, JSON_Accu *rval, PyObject *dct, Py_ssize_t indent_level) { /* Encode Python dict dct a JSON term */ static PyObject *open_dict = NULL; static PyObject *close_dict = NULL; static PyObject *empty_dict = NULL; PyObject *kstr = NULL; PyObject *ident = NULL; PyObject *iter = NULL; PyObject *item = NULL; PyObject *items = NULL; PyObject *encoded = NULL; Py_ssize_t idx; if (open_dict == NULL || close_dict == NULL || empty_dict == NULL) { open_dict = JSON_InternFromString("{"); close_dict = JSON_InternFromString("}"); empty_dict = JSON_InternFromString("{}"); if (open_dict == NULL || close_dict == NULL || empty_dict == NULL) return -1; } if (PyDict_Size(dct) == 0) return JSON_Accu_Accumulate(rval, empty_dict); if (s->markers != Py_None) { int has_key; ident = PyLong_FromVoidPtr(dct); if (ident == NULL) goto bail; has_key = PyDict_Contains(s->markers, ident); if (has_key) { if (has_key != -1) PyErr_SetString(PyExc_ValueError, "Circular reference detected"); goto bail; } if (PyDict_SetItem(s->markers, ident, dct)) { goto bail; } } if (JSON_Accu_Accumulate(rval, open_dict)) goto bail; if (s->indent != Py_None) { /* TODO: DOES NOT RUN */ indent_level += 1; /* newline_indent = '\n' + (_indent * _current_indent_level) separator = _item_separator + newline_indent buf += newline_indent */ } iter = encoder_dict_iteritems(s, dct); if (iter == NULL) goto bail; idx = 0; while ((item = PyIter_Next(iter))) { PyObject *encoded, *key, *value; if (!PyTuple_Check(item) || Py_SIZE(item) != 2) { PyErr_SetString(PyExc_ValueError, "items must return 2-tuples"); goto bail; } key = PyTuple_GET_ITEM(item, 0); if (key == NULL) goto bail; value = PyTuple_GET_ITEM(item, 1); if (value == NULL) goto bail; encoded = PyDict_GetItem(s->key_memo, key); if (encoded != NULL) { Py_INCREF(encoded); } else { kstr = encoder_stringify_key(s, key); if (kstr == NULL) goto bail; else if (kstr == Py_None) { /* skipkeys */ Py_DECREF(item); Py_DECREF(kstr); continue; } } if (idx) { if (JSON_Accu_Accumulate(rval, s->item_separator)) goto bail; } if (encoded == NULL) { encoded = encoder_encode_string(s, kstr); Py_CLEAR(kstr); if (encoded == NULL) goto bail; if (PyDict_SetItem(s->key_memo, key, encoded)) goto bail; } if (JSON_Accu_Accumulate(rval, encoded)) { goto bail; } Py_CLEAR(encoded); if (JSON_Accu_Accumulate(rval, s->key_separator)) goto bail; if (encoder_listencode_obj(s, rval, value, indent_level)) goto bail; Py_CLEAR(item); idx += 1; } Py_CLEAR(iter); if (PyErr_Occurred()) goto bail; if (ident != NULL) { if (PyDict_DelItem(s->markers, ident)) goto bail; Py_CLEAR(ident); } if (s->indent != Py_None) { /* TODO: DOES NOT RUN */ indent_level -= 1; /* yield '\n' + (_indent * _current_indent_level) */ } if (JSON_Accu_Accumulate(rval, close_dict)) goto bail; return 0; bail: Py_XDECREF(encoded); Py_XDECREF(items); Py_XDECREF(item); Py_XDECREF(iter); Py_XDECREF(kstr); Py_XDECREF(ident); return -1; } static int encoder_listencode_list(PyEncoderObject *s, JSON_Accu *rval, PyObject *seq, Py_ssize_t indent_level) { /* Encode Python list seq to a JSON term */ static PyObject *open_array = NULL; static PyObject *close_array = NULL; static PyObject *empty_array = NULL; PyObject *ident = NULL; PyObject *iter = NULL; PyObject *obj = NULL; int is_true; int i = 0; if (open_array == NULL || close_array == NULL || empty_array == NULL) { open_array = JSON_InternFromString("["); close_array = JSON_InternFromString("]"); empty_array = JSON_InternFromString("[]"); if (open_array == NULL || close_array == NULL || empty_array == NULL) return -1; } ident = NULL; is_true = PyObject_IsTrue(seq); if (is_true == -1) return -1; else if (is_true == 0) return JSON_Accu_Accumulate(rval, empty_array); if (s->markers != Py_None) { int has_key; ident = PyLong_FromVoidPtr(seq); if (ident == NULL) goto bail; has_key = PyDict_Contains(s->markers, ident); if (has_key) { if (has_key != -1) PyErr_SetString(PyExc_ValueError, "Circular reference detected"); goto bail; } if (PyDict_SetItem(s->markers, ident, seq)) { goto bail; } } iter = PyObject_GetIter(seq); if (iter == NULL) goto bail; if (JSON_Accu_Accumulate(rval, open_array)) goto bail; if (s->indent != Py_None) { /* TODO: DOES NOT RUN */ indent_level += 1; /* newline_indent = '\n' + (_indent * _current_indent_level) separator = _item_separator + newline_indent buf += newline_indent */ } while ((obj = PyIter_Next(iter))) { if (i) { if (JSON_Accu_Accumulate(rval, s->item_separator)) goto bail; } if (encoder_listencode_obj(s, rval, obj, indent_level)) goto bail; i++; Py_CLEAR(obj); } Py_CLEAR(iter); if (PyErr_Occurred()) goto bail; if (ident != NULL) { if (PyDict_DelItem(s->markers, ident)) goto bail; Py_CLEAR(ident); } if (s->indent != Py_None) { /* TODO: DOES NOT RUN */ indent_level -= 1; /* yield '\n' + (_indent * _current_indent_level) */ } if (JSON_Accu_Accumulate(rval, close_array)) goto bail; return 0; bail: Py_XDECREF(obj); Py_XDECREF(iter); Py_XDECREF(ident); return -1; } static void encoder_dealloc(PyObject *self) { /* Deallocate Encoder */ encoder_clear(self); Py_TYPE(self)->tp_free(self); } static int encoder_traverse(PyObject *self, visitproc visit, void *arg) { PyEncoderObject *s; assert(PyEncoder_Check(self)); s = (PyEncoderObject *)self; Py_VISIT(s->markers); Py_VISIT(s->defaultfn); Py_VISIT(s->encoder); Py_VISIT(s->encoding); Py_VISIT(s->indent); Py_VISIT(s->key_separator); Py_VISIT(s->item_separator); Py_VISIT(s->key_memo); Py_VISIT(s->sort_keys); Py_VISIT(s->item_sort_kw); Py_VISIT(s->item_sort_key); Py_VISIT(s->max_long_size); Py_VISIT(s->min_long_size); Py_VISIT(s->Decimal); return 0; } static int encoder_clear(PyObject *self) { /* Deallocate Encoder */ PyEncoderObject *s; assert(PyEncoder_Check(self)); s = (PyEncoderObject *)self; Py_CLEAR(s->markers); Py_CLEAR(s->defaultfn); Py_CLEAR(s->encoder); Py_CLEAR(s->encoding); Py_CLEAR(s->indent); Py_CLEAR(s->key_separator); Py_CLEAR(s->item_separator); Py_CLEAR(s->key_memo); Py_CLEAR(s->skipkeys_bool); Py_CLEAR(s->sort_keys); Py_CLEAR(s->item_sort_kw); Py_CLEAR(s->item_sort_key); Py_CLEAR(s->max_long_size); Py_CLEAR(s->min_long_size); Py_CLEAR(s->Decimal); return 0; } PyDoc_STRVAR(encoder_doc, "_iterencode(obj, _current_indent_level) -> iterable"); static PyTypeObject PyEncoderType = { PyVarObject_HEAD_INIT(NULL, 0) "simplejson._speedups.Encoder", /* tp_name */ sizeof(PyEncoderObject), /* tp_basicsize */ 0, /* tp_itemsize */ encoder_dealloc, /* tp_dealloc */ 0, /* tp_print */ 0, /* tp_getattr */ 0, /* tp_setattr */ 0, /* tp_compare */ 0, /* tp_repr */ 0, /* tp_as_number */ 0, /* tp_as_sequence */ 0, /* tp_as_mapping */ 0, /* tp_hash */ encoder_call, /* tp_call */ 0, /* tp_str */ 0, /* tp_getattro */ 0, /* tp_setattro */ 0, /* tp_as_buffer */ Py_TPFLAGS_DEFAULT | Py_TPFLAGS_HAVE_GC, /* tp_flags */ encoder_doc, /* tp_doc */ encoder_traverse, /* tp_traverse */ encoder_clear, /* tp_clear */ 0, /* tp_richcompare */ 0, /* tp_weaklistoffset */ 0, /* tp_iter */ 0, /* tp_iternext */ 0, /* tp_methods */ encoder_members, /* tp_members */ 0, /* tp_getset */ 0, /* tp_base */ 0, /* tp_dict */ 0, /* tp_descr_get */ 0, /* tp_descr_set */ 0, /* tp_dictoffset */ encoder_init, /* tp_init */ 0, /* tp_alloc */ encoder_new, /* tp_new */ 0, /* tp_free */ }; static PyMethodDef speedups_methods[] = { {"encode_basestring_ascii", (PyCFunction)py_encode_basestring_ascii, METH_O, pydoc_encode_basestring_ascii}, {"scanstring", (PyCFunction)py_scanstring, METH_VARARGS, pydoc_scanstring}, {NULL, NULL, 0, NULL} }; PyDoc_STRVAR(module_doc, "simplejson speedups\n"); #if PY_MAJOR_VERSION >= 3 static struct PyModuleDef moduledef = { PyModuleDef_HEAD_INIT, "_speedups", /* m_name */ module_doc, /* m_doc */ -1, /* m_size */ speedups_methods, /* m_methods */ NULL, /* m_reload */ NULL, /* m_traverse */ NULL, /* m_clear*/ NULL, /* m_free */ }; #endif static PyObject * moduleinit(void) { PyObject *m; PyScannerType.tp_new = PyType_GenericNew; if (PyType_Ready(&PyScannerType) < 0) return NULL; PyEncoderType.tp_new = PyType_GenericNew; if (PyType_Ready(&PyEncoderType) < 0) return NULL; #if PY_MAJOR_VERSION >= 3 m = PyModule_Create(&moduledef); #else m = Py_InitModule3("_speedups", speedups_methods, module_doc); #endif Py_INCREF((PyObject*)&PyScannerType); PyModule_AddObject(m, "make_scanner", (PyObject*)&PyScannerType); Py_INCREF((PyObject*)&PyEncoderType); PyModule_AddObject(m, "make_encoder", (PyObject*)&PyEncoderType); return m; } #if PY_MAJOR_VERSION >= 3 PyMODINIT_FUNC PyInit__speedups(void) { return moduleinit(); } #else void init_speedups(void) { moduleinit(); } #endif simplejson-3.8.1/simplejson/compat.py0000644000076500000240000000201412363544726017624 0ustar bobstaff00000000000000"""Python 3 compatibility shims """ import sys if sys.version_info[0] < 3: PY3 = False def b(s): return s def u(s): return unicode(s, 'unicode_escape') import cStringIO as StringIO StringIO = BytesIO = StringIO.StringIO text_type = unicode binary_type = str string_types = (basestring,) integer_types = (int, long) unichr = unichr reload_module = reload def fromhex(s): return s.decode('hex') else: PY3 = True if sys.version_info[:2] >= (3, 4): from importlib import reload as reload_module else: from imp import reload as reload_module import codecs def b(s): return codecs.latin_1_encode(s)[0] def u(s): return s import io StringIO = io.StringIO BytesIO = io.BytesIO text_type = str binary_type = bytes string_types = (str,) integer_types = (int,) def unichr(s): return u(chr(s)) def fromhex(s): return bytes.fromhex(s) long_type = integer_types[-1] simplejson-3.8.1/simplejson/decoder.py0000644000076500000240000003460112363544726017755 0ustar bobstaff00000000000000"""Implementation of JSONDecoder """ from __future__ import absolute_import import re import sys import struct from .compat import fromhex, b, u, text_type, binary_type, PY3, unichr from .scanner import make_scanner, JSONDecodeError def _import_c_scanstring(): try: from ._speedups import scanstring return scanstring except ImportError: return None c_scanstring = _import_c_scanstring() # NOTE (3.1.0): JSONDecodeError may still be imported from this module for # compatibility, but it was never in the __all__ __all__ = ['JSONDecoder'] FLAGS = re.VERBOSE | re.MULTILINE | re.DOTALL def _floatconstants(): _BYTES = fromhex('7FF80000000000007FF0000000000000') # The struct module in Python 2.4 would get frexp() out of range here # when an endian is specified in the format string. Fixed in Python 2.5+ 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() _CONSTANTS = { '-Infinity': NegInf, 'Infinity': PosInf, 'NaN': NaN, } STRINGCHUNK = re.compile(r'(.*?)(["\\\x00-\x1f])', FLAGS) BACKSLASH = { '"': u('"'), '\\': u('\u005c'), '/': u('/'), 'b': u('\b'), 'f': u('\f'), 'n': u('\n'), 'r': u('\r'), 't': u('\t'), } DEFAULT_ENCODING = "utf-8" def py_scanstring(s, end, encoding=None, strict=True, _b=BACKSLASH, _m=STRINGCHUNK.match, _join=u('').join, _PY3=PY3, _maxunicode=sys.maxunicode): """Scan the string s for a JSON string. End is the index of the character in s after the quote that started the JSON string. Unescapes all valid JSON string escape sequences and raises ValueError on attempt to decode an invalid string. If strict is False then literal control characters are allowed in the string. Returns a tuple of the decoded string and the index of the character in s after the end quote.""" if encoding is None: encoding = DEFAULT_ENCODING chunks = [] _append = chunks.append begin = end - 1 while 1: chunk = _m(s, end) if chunk is None: raise JSONDecodeError( "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 _PY3 and not isinstance(content, text_type): content = text_type(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" raise JSONDecodeError(msg, s, end) else: _append(terminator) continue try: esc = s[end] except IndexError: raise JSONDecodeError( "Unterminated string starting at", s, begin) # If not a unicode escape sequence, must be in the lookup table if esc != 'u': try: char = _b[esc] except KeyError: msg = "Invalid \\X escape sequence %r" raise JSONDecodeError(msg, s, end) end += 1 else: # Unicode escape sequence msg = "Invalid \\uXXXX escape sequence" esc = s[end + 1:end + 5] escX = esc[1:2] if len(esc) != 4 or escX == 'x' or escX == 'X': raise JSONDecodeError(msg, s, end - 1) try: uni = int(esc, 16) except ValueError: raise JSONDecodeError(msg, s, end - 1) end += 5 # Check for surrogate pair on UCS-4 systems # Note that this will join high/low surrogate pairs # but will also pass unpaired surrogates through if (_maxunicode > 65535 and uni & 0xfc00 == 0xd800 and s[end:end + 2] == '\\u'): esc2 = s[end + 2:end + 6] escX = esc2[1:2] if len(esc2) == 4 and not (escX == 'x' or escX == 'X'): try: uni2 = int(esc2, 16) except ValueError: raise JSONDecodeError(msg, s, end) if uni2 & 0xfc00 == 0xdc00: uni = 0x10000 + (((uni - 0xd800) << 10) | (uni2 - 0xdc00)) end += 6 char = unichr(uni) # Append the unescaped character _append(char) return _join(chunks), end # Use speedup if available scanstring = c_scanstring or py_scanstring WHITESPACE = re.compile(r'[ \t\n\r]*', FLAGS) WHITESPACE_STR = ' \t\n\r' def JSONObject(state, encoding, strict, scan_once, object_hook, object_pairs_hook, memo=None, _w=WHITESPACE.match, _ws=WHITESPACE_STR): (s, end) = state # Backwards compatibility if memo is None: memo = {} memo_get = memo.setdefault pairs = [] # Use a slice to prevent IndexError from being raised, the following # check will raise a more specific ValueError if the string is empty nextchar = s[end:end + 1] # Normally we expect nextchar == '"' if nextchar != '"': if nextchar in _ws: end = _w(s, end).end() nextchar = s[end:end + 1] # Trivial empty object if nextchar == '}': if object_pairs_hook is not None: result = object_pairs_hook(pairs) return result, end + 1 pairs = {} if object_hook is not None: pairs = object_hook(pairs) return pairs, end + 1 elif nextchar != '"': raise JSONDecodeError( "Expecting property name enclosed in double quotes", s, end) end += 1 while True: key, end = scanstring(s, end, encoding, strict) key = memo_get(key, key) # To skip some function call overhead we optimize the fast paths where # the JSON key separator is ": " or just ":". if s[end:end + 1] != ':': end = _w(s, end).end() if s[end:end + 1] != ':': raise JSONDecodeError("Expecting ':' delimiter", s, end) end += 1 try: if s[end] in _ws: end += 1 if s[end] in _ws: end = _w(s, end + 1).end() except IndexError: pass value, end = scan_once(s, end) pairs.append((key, value)) try: nextchar = s[end] if nextchar in _ws: end = _w(s, end + 1).end() nextchar = s[end] except IndexError: nextchar = '' end += 1 if nextchar == '}': break elif nextchar != ',': raise JSONDecodeError("Expecting ',' delimiter or '}'", s, end - 1) try: nextchar = s[end] if nextchar in _ws: end += 1 nextchar = s[end] if nextchar in _ws: end = _w(s, end + 1).end() nextchar = s[end] except IndexError: nextchar = '' end += 1 if nextchar != '"': raise JSONDecodeError( "Expecting property name enclosed in double quotes", s, end - 1) if object_pairs_hook is not None: result = object_pairs_hook(pairs) return result, end pairs = dict(pairs) if object_hook is not None: pairs = object_hook(pairs) return pairs, end def JSONArray(state, scan_once, _w=WHITESPACE.match, _ws=WHITESPACE_STR): (s, end) = state values = [] nextchar = s[end:end + 1] if nextchar in _ws: end = _w(s, end + 1).end() nextchar = s[end:end + 1] # Look-ahead for trivial empty array if nextchar == ']': return values, end + 1 elif nextchar == '': raise JSONDecodeError("Expecting value or ']'", s, end) _append = values.append while True: value, end = scan_once(s, end) _append(value) nextchar = s[end:end + 1] if nextchar in _ws: end = _w(s, end + 1).end() nextchar = s[end:end + 1] end += 1 if nextchar == ']': break elif nextchar != ',': raise JSONDecodeError("Expecting ',' delimiter or ']'", s, end - 1) try: if s[end] in _ws: end += 1 if s[end] in _ws: end = _w(s, end + 1).end() except IndexError: pass return values, end class JSONDecoder(object): """Simple JSON decoder Performs the following translations in decoding by default: +---------------+-------------------+ | JSON | Python | +===============+===================+ | object | dict | +---------------+-------------------+ | array | list | +---------------+-------------------+ | string | str, unicode | +---------------+-------------------+ | number (int) | int, long | +---------------+-------------------+ | number (real) | float | +---------------+-------------------+ | true | True | +---------------+-------------------+ | false | False | +---------------+-------------------+ | null | None | +---------------+-------------------+ It also understands ``NaN``, ``Infinity``, and ``-Infinity`` as their corresponding ``float`` values, which is outside the JSON spec. """ def __init__(self, encoding=None, object_hook=None, parse_float=None, parse_int=None, parse_constant=None, strict=True, object_pairs_hook=None): """ *encoding* determines the encoding used to interpret any :class:`str` objects decoded by this instance (``'utf-8'`` by default). It has no effect when decoding :class:`unicode` objects. Note that currently only encodings that are a superset of ASCII work, strings of other encodings should be passed in as :class:`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 :class:`dict`. This can be used to provide custom deserializations (e.g. to support JSON-RPC class hinting). *object_pairs_hook* is an optional function that will be called with the result of any object literal decode with an ordered list of pairs. The return value of *object_pairs_hook* will be used instead of the :class:`dict`. This feature can be used to implement custom decoders that rely on the order that the key and value pairs are decoded (for example, :func:`collections.OrderedDict` will remember the order of insertion). If *object_hook* is also defined, the *object_pairs_hook* takes priority. *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. :class:`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. :class:`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. *strict* controls the parser's behavior when it encounters an invalid control character in a string. The default setting of ``True`` means that unescaped control characters are parse errors, if ``False`` then control characters will be allowed in strings. """ if encoding is None: encoding = DEFAULT_ENCODING self.encoding = encoding self.object_hook = object_hook self.object_pairs_hook = object_pairs_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.memo = {} self.scan_once = make_scanner(self) def decode(self, s, _w=WHITESPACE.match, _PY3=PY3): """Return the Python representation of ``s`` (a ``str`` or ``unicode`` instance containing a JSON document) """ if _PY3 and isinstance(s, binary_type): s = s.decode(self.encoding) obj, end = self.raw_decode(s) end = _w(s, end).end() if end != len(s): raise JSONDecodeError("Extra data", s, end, len(s)) return obj def raw_decode(self, s, idx=0, _w=WHITESPACE.match, _PY3=PY3): """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. Optionally, ``idx`` can be used to specify an offset in ``s`` where the JSON document begins. This can be used to decode a JSON document from a string that may have extraneous data at the end. """ if idx < 0: # Ensure that raw_decode bails on negative indexes, the regex # would otherwise mask this behavior. #98 raise JSONDecodeError('Expecting value', s, idx) if _PY3 and not isinstance(s, text_type): raise TypeError("Input string must be text, not bytes") # strip UTF-8 bom if len(s) > idx: ord0 = ord(s[idx]) if ord0 == 0xfeff: idx += 1 elif ord0 == 0xef and s[idx:idx + 3] == '\xef\xbb\xbf': idx += 3 return self.scan_once(s, idx=_w(s, idx).end()) simplejson-3.8.1/simplejson/encoder.py0000644000076500000240000006421412613712744017765 0ustar bobstaff00000000000000"""Implementation of JSONEncoder """ from __future__ import absolute_import import re from operator import itemgetter # Do not import Decimal directly to avoid reload issues import decimal from .compat import u, unichr, binary_type, string_types, integer_types, PY3 def _import_speedups(): try: from . import _speedups return _speedups.encode_basestring_ascii, _speedups.make_encoder except ImportError: return None, None c_encode_basestring_ascii, c_make_encoder = _import_speedups() from simplejson.decoder import PosInf #ESCAPE = re.compile(ur'[\x00-\x1f\\"\b\f\n\r\t\u2028\u2029]') # This is required because u() will mangle the string and ur'' isn't valid # python3 syntax ESCAPE = re.compile(u'[\\x00-\\x1f\\\\"\\b\\f\\n\\r\\t\u2028\u2029]') ESCAPE_ASCII = re.compile(r'([\\"]|[^\ -~])') HAS_UTF8 = re.compile(r'[\x80-\xff]') ESCAPE_DCT = { '\\': '\\\\', '"': '\\"', '\b': '\\b', '\f': '\\f', '\n': '\\n', '\r': '\\r', '\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,)) for i in [0x2028, 0x2029]: ESCAPE_DCT.setdefault(unichr(i), '\\u%04x' % (i,)) FLOAT_REPR = repr def encode_basestring(s, _PY3=PY3, _q=u('"')): """Return a JSON representation of a Python string """ if _PY3: if isinstance(s, binary_type): s = s.decode('utf-8') else: if isinstance(s, str) and HAS_UTF8.search(s) is not None: s = s.decode('utf-8') def replace(match): return ESCAPE_DCT[match.group(0)] return _q + ESCAPE.sub(replace, s) + _q def py_encode_basestring_ascii(s, _PY3=PY3): """Return an ASCII-only JSON representation of a Python string """ if _PY3: if isinstance(s, binary_type): s = s.decode('utf-8') else: 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: return ESCAPE_DCT[s] 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)) + '"' encode_basestring_ascii = ( c_encode_basestring_ascii or py_encode_basestring_ascii) class JSONEncoder(object): """Extensible JSON encoder for Python data structures. Supports the following objects and types by default: +-------------------+---------------+ | Python | JSON | +===================+===============+ | dict, namedtuple | 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``). """ 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', default=None, use_decimal=True, namedtuple_as_object=True, tuple_as_array=True, bigint_as_string=False, item_sort_key=None, for_json=False, ignore_nan=False, int_as_string_bitcount=None, iterable_as_array=False): """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 string, then JSON array elements and object members will be pretty-printed with a newline followed by that string repeated for each level of nesting. ``None`` (the default) selects the most compact representation without any newlines. For backwards compatibility with versions of simplejson earlier than 2.1.0, an integer is also accepted and is converted to a string with that many spaces. If specified, separators should be an (item_separator, key_separator) tuple. The default is (', ', ': ') if *indent* is ``None`` and (',', ': ') otherwise. 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. The default is UTF-8. If use_decimal is true (not the default), ``decimal.Decimal`` will be supported directly by the encoder. For the inverse, decode JSON with ``parse_float=decimal.Decimal``. If namedtuple_as_object is true (the default), objects with ``_asdict()`` methods will be encoded as JSON objects. If tuple_as_array is true (the default), tuple (and subclasses) will be encoded as JSON arrays. If *iterable_as_array* is true (default: ``False``), any object not in the above table that implements ``__iter__()`` will be encoded as a JSON array. If bigint_as_string is true (not the default), ints 2**53 and higher or lower than -2**53 will be encoded as strings. This is to avoid the rounding that happens in Javascript otherwise. If int_as_string_bitcount is a positive number (n), then int of size greater than or equal to 2**n or lower than or equal to -2**n will be encoded as strings. If specified, item_sort_key is a callable used to sort the items in each dictionary. This is useful if you want to sort items other than in alphabetical order by key. If for_json is true (not the default), objects with a ``for_json()`` method will use the return value of that method for encoding as JSON instead of the object. If *ignore_nan* is true (default: ``False``), then out of range :class:`float` values (``nan``, ``inf``, ``-inf``) will be serialized as ``null`` in compliance with the ECMA-262 specification. If true, this will override *allow_nan*. """ self.skipkeys = skipkeys self.ensure_ascii = ensure_ascii self.check_circular = check_circular self.allow_nan = allow_nan self.sort_keys = sort_keys self.use_decimal = use_decimal self.namedtuple_as_object = namedtuple_as_object self.tuple_as_array = tuple_as_array self.iterable_as_array = iterable_as_array self.bigint_as_string = bigint_as_string self.item_sort_key = item_sort_key self.for_json = for_json self.ignore_nan = ignore_nan self.int_as_string_bitcount = int_as_string_bitcount if indent is not None and not isinstance(indent, string_types): indent = indent * ' ' self.indent = indent if separators is not None: self.item_separator, self.key_separator = separators elif indent is not None: self.item_separator = ',' if default is not None: self.default = default self.encoding = encoding 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(repr(o) + " is not JSON serializable") def encode(self, o): """Return a JSON string representation of a Python data structure. >>> from simplejson import JSONEncoder >>> JSONEncoder().encode({"foo": ["bar", "baz"]}) '{"foo": ["bar", "baz"]}' """ # This is for extremely simple cases and benchmarks. if isinstance(o, binary_type): _encoding = self.encoding if (_encoding is not None and not (_encoding == 'utf-8')): o = o.decode(_encoding) if isinstance(o, string_types): 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) if self.ensure_ascii: return ''.join(chunks) else: return u''.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, binary_type): o = o.decode(_encoding) return _orig_encoder(o) def floatstr(o, allow_nan=self.allow_nan, ignore_nan=self.ignore_nan, _repr=FLOAT_REPR, _inf=PosInf, _neginf=-PosInf): # 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: if type(o) != float: # See #118, do not trust custom str/repr o = float(o) return _repr(o) if ignore_nan: text = 'null' elif not allow_nan: raise ValueError( "Out of range float values are not JSON compliant: " + repr(o)) return text key_memo = {} int_as_string_bitcount = ( 53 if self.bigint_as_string else self.int_as_string_bitcount) if (_one_shot and c_make_encoder is not None and self.indent is None): _iterencode = c_make_encoder( markers, self.default, _encoder, self.indent, self.key_separator, self.item_separator, self.sort_keys, self.skipkeys, self.allow_nan, key_memo, self.use_decimal, self.namedtuple_as_object, self.tuple_as_array, int_as_string_bitcount, self.item_sort_key, self.encoding, self.for_json, self.ignore_nan, decimal.Decimal, self.iterable_as_array) else: _iterencode = _make_iterencode( markers, self.default, _encoder, self.indent, floatstr, self.key_separator, self.item_separator, self.sort_keys, self.skipkeys, _one_shot, self.use_decimal, self.namedtuple_as_object, self.tuple_as_array, int_as_string_bitcount, self.item_sort_key, self.encoding, self.for_json, self.iterable_as_array, Decimal=decimal.Decimal) try: return _iterencode(o, 0) finally: key_memo.clear() class JSONEncoderForHTML(JSONEncoder): """An encoder that produces JSON safe to embed in HTML. To embed JSON content in, say, a script tag on a web page, the characters &, < and > should be escaped. They cannot be escaped with the usual entities (e.g. &) because they are not expanded within ' self.assertEqual( r'"\u003c/script\u003e\u003cscript\u003e' r'alert(\"gotcha\")\u003c/script\u003e"', self.encoder.encode(bad_string)) self.assertEqual( bad_string, self.decoder.decode( self.encoder.encode(bad_string))) simplejson-3.8.1/simplejson/tests/test_errors.py0000644000076500000240000000301512363544726022060 0ustar bobstaff00000000000000import sys, pickle from unittest import TestCase import simplejson as json from simplejson.compat import u, b class TestErrors(TestCase): def test_string_keys_error(self): data = [{'a': 'A', 'b': (2, 4), 'c': 3.0, ('d',): 'D tuple'}] self.assertRaises(TypeError, json.dumps, data) def test_decode_error(self): err = None try: json.loads('{}\na\nb') except json.JSONDecodeError: err = sys.exc_info()[1] else: self.fail('Expected JSONDecodeError') self.assertEqual(err.lineno, 2) self.assertEqual(err.colno, 1) self.assertEqual(err.endlineno, 3) self.assertEqual(err.endcolno, 2) def test_scan_error(self): err = None for t in (u, b): try: json.loads(t('{"asdf": "')) except json.JSONDecodeError: err = sys.exc_info()[1] else: self.fail('Expected JSONDecodeError') self.assertEqual(err.lineno, 1) self.assertEqual(err.colno, 10) def test_error_is_pickable(self): err = None try: json.loads('{}\na\nb') except json.JSONDecodeError: err = sys.exc_info()[1] else: self.fail('Expected JSONDecodeError') s = pickle.dumps(err) e = pickle.loads(s) self.assertEqual(err.msg, e.msg) self.assertEqual(err.doc, e.doc) self.assertEqual(err.pos, e.pos) self.assertEqual(err.end, e.end) simplejson-3.8.1/simplejson/tests/test_fail.py0000644000076500000240000001431212363544726021461 0ustar bobstaff00000000000000import sys from unittest import TestCase import simplejson as json # 2007-10-05 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 '[\\naked]', # 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']", # http://json.org/JSON_checker/test/fail25.json '["\ttab\tcharacter\tin\tstring\t"]', # http://json.org/JSON_checker/test/fail26.json '["tab\\ character\\ in\\ string\\ "]', # http://json.org/JSON_checker/test/fail27.json '["line\nbreak"]', # http://json.org/JSON_checker/test/fail28.json '["line\\\nbreak"]', # http://json.org/JSON_checker/test/fail29.json '[0e]', # http://json.org/JSON_checker/test/fail30.json '[0e+]', # http://json.org/JSON_checker/test/fail31.json '[0e+-1]', # http://json.org/JSON_checker/test/fail32.json '{"Comma instead if closing brace": true,', # http://json.org/JSON_checker/test/fail33.json '["mismatch"}', # http://code.google.com/p/simplejson/issues/detail?id=3 u'["A\u001FZ control characters in string"]', # misc based on coverage '{', '{]', '{"foo": "bar"]', '{"foo": "bar"', 'nul', 'nulx', '-', '-x', '-e', '-e0', '-Infinite', '-Inf', 'Infinit', 'Infinite', 'NaM', 'NuN', 'falsy', 'fal', 'trug', 'tru', '1e', '1ex', '1e-', '1e-x', ] SKIPS = { 1: "why not have a string payload?", 18: "spec doesn't specify any nesting limitations", } class TestFail(TestCase): def test_failures(self): for idx, doc in enumerate(JSONDOCS): idx = idx + 1 if idx in SKIPS: json.loads(doc) continue try: json.loads(doc) except json.JSONDecodeError: pass else: self.fail("Expected failure for fail%d.json: %r" % (idx, doc)) def test_array_decoder_issue46(self): # http://code.google.com/p/simplejson/issues/detail?id=46 for doc in [u'[,]', '[,]']: try: json.loads(doc) except json.JSONDecodeError: e = sys.exc_info()[1] self.assertEqual(e.pos, 1) self.assertEqual(e.lineno, 1) self.assertEqual(e.colno, 2) except Exception: e = sys.exc_info()[1] self.fail("Unexpected exception raised %r %s" % (e, e)) else: self.fail("Unexpected success parsing '[,]'") def test_truncated_input(self): test_cases = [ ('', 'Expecting value', 0), ('[', "Expecting value or ']'", 1), ('[42', "Expecting ',' delimiter", 3), ('[42,', 'Expecting value', 4), ('["', 'Unterminated string starting at', 1), ('["spam', 'Unterminated string starting at', 1), ('["spam"', "Expecting ',' delimiter", 7), ('["spam",', 'Expecting value', 8), ('{', 'Expecting property name enclosed in double quotes', 1), ('{"', 'Unterminated string starting at', 1), ('{"spam', 'Unterminated string starting at', 1), ('{"spam"', "Expecting ':' delimiter", 7), ('{"spam":', 'Expecting value', 8), ('{"spam":42', "Expecting ',' delimiter", 10), ('{"spam":42,', 'Expecting property name enclosed in double quotes', 11), ('"', 'Unterminated string starting at', 0), ('"spam', 'Unterminated string starting at', 0), ('[,', "Expecting value", 1), ] for data, msg, idx in test_cases: try: json.loads(data) except json.JSONDecodeError: e = sys.exc_info()[1] self.assertEqual( e.msg[:len(msg)], msg, "%r doesn't start with %r for %r" % (e.msg, msg, data)) self.assertEqual( e.pos, idx, "pos %r != %r for %r" % (e.pos, idx, data)) except Exception: e = sys.exc_info()[1] self.fail("Unexpected exception raised %r %s" % (e, e)) else: self.fail("Unexpected success parsing '%r'" % (data,)) simplejson-3.8.1/simplejson/tests/test_float.py0000644000076500000240000000262612363544726021660 0ustar bobstaff00000000000000import math from unittest import TestCase from simplejson.compat import long_type, text_type import simplejson as json from simplejson.decoder import NaN, PosInf, NegInf class TestFloat(TestCase): def test_degenerates_allow(self): for inf in (PosInf, NegInf): self.assertEqual(json.loads(json.dumps(inf)), inf) # Python 2.5 doesn't have math.isnan nan = json.loads(json.dumps(NaN)) self.assertTrue((0 + nan) != nan) def test_degenerates_ignore(self): for f in (PosInf, NegInf, NaN): self.assertEqual(json.loads(json.dumps(f, ignore_nan=True)), None) def test_degenerates_deny(self): for f in (PosInf, NegInf, NaN): self.assertRaises(ValueError, json.dumps, f, allow_nan=False) def test_floats(self): for num in [1617161771.7650001, math.pi, math.pi**100, math.pi**-100, 3.1]: self.assertEqual(float(json.dumps(num)), num) self.assertEqual(json.loads(json.dumps(num)), num) self.assertEqual(json.loads(text_type(json.dumps(num))), num) def test_ints(self): for num in [1, long_type(1), 1<<32, 1<<64]: self.assertEqual(json.dumps(num), str(num)) self.assertEqual(int(json.dumps(num)), num) self.assertEqual(json.loads(json.dumps(num)), num) self.assertEqual(json.loads(text_type(json.dumps(num))), num) simplejson-3.8.1/simplejson/tests/test_for_json.py0000644000076500000240000000531712363544726022372 0ustar bobstaff00000000000000import unittest import simplejson as json class ForJson(object): def for_json(self): return {'for_json': 1} class NestedForJson(object): def for_json(self): return {'nested': ForJson()} class ForJsonList(object): def for_json(self): return ['list'] class DictForJson(dict): def for_json(self): return {'alpha': 1} class ListForJson(list): def for_json(self): return ['list'] class TestForJson(unittest.TestCase): def assertRoundTrip(self, obj, other, for_json=True): if for_json is None: # None will use the default s = json.dumps(obj) else: s = json.dumps(obj, for_json=for_json) self.assertEqual( json.loads(s), other) def test_for_json_encodes_stand_alone_object(self): self.assertRoundTrip( ForJson(), ForJson().for_json()) def test_for_json_encodes_object_nested_in_dict(self): self.assertRoundTrip( {'hooray': ForJson()}, {'hooray': ForJson().for_json()}) def test_for_json_encodes_object_nested_in_list_within_dict(self): self.assertRoundTrip( {'list': [0, ForJson(), 2, 3]}, {'list': [0, ForJson().for_json(), 2, 3]}) def test_for_json_encodes_object_nested_within_object(self): self.assertRoundTrip( NestedForJson(), {'nested': {'for_json': 1}}) def test_for_json_encodes_list(self): self.assertRoundTrip( ForJsonList(), ForJsonList().for_json()) def test_for_json_encodes_list_within_object(self): self.assertRoundTrip( {'nested': ForJsonList()}, {'nested': ForJsonList().for_json()}) def test_for_json_encodes_dict_subclass(self): self.assertRoundTrip( DictForJson(a=1), DictForJson(a=1).for_json()) def test_for_json_encodes_list_subclass(self): self.assertRoundTrip( ListForJson(['l']), ListForJson(['l']).for_json()) def test_for_json_ignored_if_not_true_with_dict_subclass(self): for for_json in (None, False): self.assertRoundTrip( DictForJson(a=1), {'a': 1}, for_json=for_json) def test_for_json_ignored_if_not_true_with_list_subclass(self): for for_json in (None, False): self.assertRoundTrip( ListForJson(['l']), ['l'], for_json=for_json) def test_raises_typeerror_if_for_json_not_true_with_object(self): self.assertRaises(TypeError, json.dumps, ForJson()) self.assertRaises(TypeError, json.dumps, ForJson(), for_json=False) simplejson-3.8.1/simplejson/tests/test_indent.py0000644000076500000240000000501012613711220022001 0ustar bobstaff00000000000000from unittest import TestCase import textwrap import simplejson as json from simplejson.compat import StringIO class TestIndent(TestCase): def test_indent(self): h = [['blorpie'], ['whoops'], [], 'd-shtaeou', 'd-nthiouh', 'i-vhbjkhnth', {'nifty': 87}, {'field': 'yes', 'morefield': False} ] expect = textwrap.dedent("""\ [ \t[ \t\t"blorpie" \t], \t[ \t\t"whoops" \t], \t[], \t"d-shtaeou", \t"d-nthiouh", \t"i-vhbjkhnth", \t{ \t\t"nifty": 87 \t}, \t{ \t\t"field": "yes", \t\t"morefield": false \t} ]""") d1 = json.dumps(h) d2 = json.dumps(h, indent='\t', sort_keys=True, separators=(',', ': ')) d3 = json.dumps(h, indent=' ', sort_keys=True, separators=(',', ': ')) d4 = json.dumps(h, indent=2, sort_keys=True, separators=(',', ': ')) h1 = json.loads(d1) h2 = json.loads(d2) h3 = json.loads(d3) h4 = json.loads(d4) self.assertEqual(h1, h) self.assertEqual(h2, h) self.assertEqual(h3, h) self.assertEqual(h4, h) self.assertEqual(d3, expect.replace('\t', ' ')) self.assertEqual(d4, expect.replace('\t', ' ')) # NOTE: Python 2.4 textwrap.dedent converts tabs to spaces, # so the following is expected to fail. Python 2.4 is not a # supported platform in simplejson 2.1.0+. self.assertEqual(d2, expect) def test_indent0(self): h = {3: 1} def check(indent, expected): d1 = json.dumps(h, indent=indent) self.assertEqual(d1, expected) sio = StringIO() json.dump(h, sio, indent=indent) self.assertEqual(sio.getvalue(), expected) # indent=0 should emit newlines check(0, '{\n"3": 1\n}') # indent=None is more compact check(None, '{"3": 1}') def test_separators(self): lst = [1,2,3,4] expect = '[\n1,\n2,\n3,\n4\n]' expect_spaces = '[\n1, \n2, \n3, \n4\n]' # Ensure that separators still works self.assertEqual( expect_spaces, json.dumps(lst, indent=0, separators=(', ', ': '))) # Force the new defaults self.assertEqual( expect, json.dumps(lst, indent=0, separators=(',', ': '))) # Added in 2.1.4 self.assertEqual( expect, json.dumps(lst, indent=0)) simplejson-3.8.1/simplejson/tests/test_item_sort_key.py0000644000076500000240000000214712363544726023426 0ustar bobstaff00000000000000from unittest import TestCase import simplejson as json from operator import itemgetter class TestItemSortKey(TestCase): def test_simple_first(self): a = {'a': 1, 'c': 5, 'jack': 'jill', 'pick': 'axe', 'array': [1, 5, 6, 9], 'tuple': (83, 12, 3), 'crate': 'dog', 'zeak': 'oh'} self.assertEqual( '{"a": 1, "c": 5, "crate": "dog", "jack": "jill", "pick": "axe", "zeak": "oh", "array": [1, 5, 6, 9], "tuple": [83, 12, 3]}', json.dumps(a, item_sort_key=json.simple_first)) def test_case(self): a = {'a': 1, 'c': 5, 'Jack': 'jill', 'pick': 'axe', 'Array': [1, 5, 6, 9], 'tuple': (83, 12, 3), 'crate': 'dog', 'zeak': 'oh'} self.assertEqual( '{"Array": [1, 5, 6, 9], "Jack": "jill", "a": 1, "c": 5, "crate": "dog", "pick": "axe", "tuple": [83, 12, 3], "zeak": "oh"}', json.dumps(a, item_sort_key=itemgetter(0))) self.assertEqual( '{"a": 1, "Array": [1, 5, 6, 9], "c": 5, "crate": "dog", "Jack": "jill", "pick": "axe", "tuple": [83, 12, 3], "zeak": "oh"}', json.dumps(a, item_sort_key=lambda kv: kv[0].lower())) simplejson-3.8.1/simplejson/tests/test_iterable.py0000644000076500000240000000255612613714150022330 0ustar bobstaff00000000000000import unittest from simplejson.compat import StringIO import simplejson as json def iter_dumps(obj, **kw): return ''.join(json.JSONEncoder(**kw).iterencode(obj)) def sio_dump(obj, **kw): sio = StringIO() json.dumps(obj, **kw) return sio.getvalue() class TestIterable(unittest.TestCase): def test_iterable(self): for l in ([], [1], [1, 2], [1, 2, 3]): for opts in [{}, {'indent': 2}]: for dumps in (json.dumps, iter_dumps, sio_dump): expect = dumps(l, **opts) default_expect = dumps(sum(l), **opts) # Default is False self.assertRaises(TypeError, dumps, iter(l), **opts) self.assertRaises(TypeError, dumps, iter(l), iterable_as_array=False, **opts) self.assertEqual(expect, dumps(iter(l), iterable_as_array=True, **opts)) # Ensure that the "default" gets called self.assertEqual(default_expect, dumps(iter(l), default=sum, **opts)) self.assertEqual(default_expect, dumps(iter(l), iterable_as_array=False, default=sum, **opts)) # Ensure that the "default" does not get called self.assertEqual( expect, dumps(iter(l), iterable_as_array=True, default=sum, **opts)) simplejson-3.8.1/simplejson/tests/test_namedtuple.py0000644000076500000240000000764412363544726022716 0ustar bobstaff00000000000000from __future__ import absolute_import import unittest import simplejson as json from simplejson.compat import StringIO try: from collections import namedtuple except ImportError: class Value(tuple): def __new__(cls, *args): return tuple.__new__(cls, args) def _asdict(self): return {'value': self[0]} class Point(tuple): def __new__(cls, *args): return tuple.__new__(cls, args) def _asdict(self): return {'x': self[0], 'y': self[1]} else: Value = namedtuple('Value', ['value']) Point = namedtuple('Point', ['x', 'y']) class DuckValue(object): def __init__(self, *args): self.value = Value(*args) def _asdict(self): return self.value._asdict() class DuckPoint(object): def __init__(self, *args): self.point = Point(*args) def _asdict(self): return self.point._asdict() class DeadDuck(object): _asdict = None class DeadDict(dict): _asdict = None CONSTRUCTORS = [ lambda v: v, lambda v: [v], lambda v: [{'key': v}], ] class TestNamedTuple(unittest.TestCase): def test_namedtuple_dumps(self): for v in [Value(1), Point(1, 2), DuckValue(1), DuckPoint(1, 2)]: d = v._asdict() self.assertEqual(d, json.loads(json.dumps(v))) self.assertEqual( d, json.loads(json.dumps(v, namedtuple_as_object=True))) self.assertEqual(d, json.loads(json.dumps(v, tuple_as_array=False))) self.assertEqual( d, json.loads(json.dumps(v, namedtuple_as_object=True, tuple_as_array=False))) def test_namedtuple_dumps_false(self): for v in [Value(1), Point(1, 2)]: l = list(v) self.assertEqual( l, json.loads(json.dumps(v, namedtuple_as_object=False))) self.assertRaises(TypeError, json.dumps, v, tuple_as_array=False, namedtuple_as_object=False) def test_namedtuple_dump(self): for v in [Value(1), Point(1, 2), DuckValue(1), DuckPoint(1, 2)]: d = v._asdict() sio = StringIO() json.dump(v, sio) self.assertEqual(d, json.loads(sio.getvalue())) sio = StringIO() json.dump(v, sio, namedtuple_as_object=True) self.assertEqual( d, json.loads(sio.getvalue())) sio = StringIO() json.dump(v, sio, tuple_as_array=False) self.assertEqual(d, json.loads(sio.getvalue())) sio = StringIO() json.dump(v, sio, namedtuple_as_object=True, tuple_as_array=False) self.assertEqual( d, json.loads(sio.getvalue())) def test_namedtuple_dump_false(self): for v in [Value(1), Point(1, 2)]: l = list(v) sio = StringIO() json.dump(v, sio, namedtuple_as_object=False) self.assertEqual( l, json.loads(sio.getvalue())) self.assertRaises(TypeError, json.dump, v, StringIO(), tuple_as_array=False, namedtuple_as_object=False) def test_asdict_not_callable_dump(self): for f in CONSTRUCTORS: self.assertRaises(TypeError, json.dump, f(DeadDuck()), StringIO(), namedtuple_as_object=True) sio = StringIO() json.dump(f(DeadDict()), sio, namedtuple_as_object=True) self.assertEqual( json.dumps(f({})), sio.getvalue()) def test_asdict_not_callable_dumps(self): for f in CONSTRUCTORS: self.assertRaises(TypeError, json.dumps, f(DeadDuck()), namedtuple_as_object=True) self.assertEqual( json.dumps(f({})), json.dumps(f(DeadDict()), namedtuple_as_object=True)) simplejson-3.8.1/simplejson/tests/test_pass1.py0000644000076500000240000000332212363544726021574 0ustar bobstaff00000000000000from unittest import TestCase import simplejson as json # 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, "": 23456789012E66, "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, 1e1, 0.1e1, 1e-1, 1e00,2e+00,2e-00 ,"rosebud"] ''' class TestPass1(TestCase): def test_parse(self): # test in/out equivalence and parsing res = json.loads(JSON) out = json.dumps(res) self.assertEqual(res, json.loads(out)) simplejson-3.8.1/simplejson/tests/test_pass2.py0000644000076500000240000000060212363544726021573 0ustar bobstaff00000000000000from unittest import TestCase import simplejson as json # from http://json.org/JSON_checker/test/pass2.json JSON = r''' [[[[[[[[[[[[[[[[[[["Not too deep"]]]]]]]]]]]]]]]]]]] ''' class TestPass2(TestCase): def test_parse(self): # test in/out equivalence and parsing res = json.loads(JSON) out = json.dumps(res) self.assertEqual(res, json.loads(out)) simplejson-3.8.1/simplejson/tests/test_pass3.py0000644000076500000240000000074212363544726021601 0ustar bobstaff00000000000000from unittest import TestCase import simplejson as json # 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." } } ''' class TestPass3(TestCase): def test_parse(self): # test in/out equivalence and parsing res = json.loads(JSON) out = json.dumps(res) self.assertEqual(res, json.loads(out)) simplejson-3.8.1/simplejson/tests/test_recursion.py0000644000076500000240000000321712363544726022561 0ustar bobstaff00000000000000from unittest import TestCase import simplejson as json class JSONTestObject: pass class RecursiveJSONEncoder(json.JSONEncoder): recurse = False def default(self, o): if o is JSONTestObject: if self.recurse: return [JSONTestObject] else: return 'JSONTestObject' return json.JSONEncoder.default(o) class TestRecursion(TestCase): def test_listrecursion(self): x = [] x.append(x) try: json.dumps(x) except ValueError: pass else: self.fail("didn't raise ValueError on list recursion") x = [] y = [x] x.append(y) try: json.dumps(x) except ValueError: pass else: self.fail("didn't raise ValueError on alternating list recursion") y = [] x = [y, y] # ensure that the marker is cleared json.dumps(x) def test_dictrecursion(self): x = {} x["test"] = x try: json.dumps(x) except ValueError: pass else: self.fail("didn't raise ValueError on dict recursion") x = {} y = {"a": x, "b": x} # ensure that the marker is cleared json.dumps(y) def test_defaultrecursion(self): enc = RecursiveJSONEncoder() self.assertEqual(enc.encode(JSONTestObject), '"JSONTestObject"') enc.recurse = True try: enc.encode(JSONTestObject) except ValueError: pass else: self.fail("didn't raise ValueError on default recursion") simplejson-3.8.1/simplejson/tests/test_scanstring.py0000644000076500000240000001621712363544726022727 0ustar bobstaff00000000000000import sys from unittest import TestCase import simplejson as json import simplejson.decoder from simplejson.compat import b, PY3 class TestScanString(TestCase): # The bytes type is intentionally not used in most of these tests # under Python 3 because the decoder immediately coerces to str before # calling scanstring. In Python 2 we are testing the code paths # for both unicode and str. # # The reason this is done is because Python 3 would require # entirely different code paths for parsing bytes and str. # def test_py_scanstring(self): self._test_scanstring(simplejson.decoder.py_scanstring) def test_c_scanstring(self): if not simplejson.decoder.c_scanstring: return self._test_scanstring(simplejson.decoder.c_scanstring) def _test_scanstring(self, scanstring): if sys.maxunicode == 65535: self.assertEqual( scanstring(u'"z\U0001d120x"', 1, None, True), (u'z\U0001d120x', 6)) else: self.assertEqual( scanstring(u'"z\U0001d120x"', 1, None, True), (u'z\U0001d120x', 5)) self.assertEqual( scanstring('"\\u007b"', 1, None, True), (u'{', 8)) self.assertEqual( scanstring('"A JSON payload should be an object or array, not a string."', 1, None, True), (u'A JSON payload should be an object or array, not a string.', 60)) self.assertEqual( scanstring('["Unclosed array"', 2, None, True), (u'Unclosed array', 17)) self.assertEqual( scanstring('["extra comma",]', 2, None, True), (u'extra comma', 14)) self.assertEqual( scanstring('["double extra comma",,]', 2, None, True), (u'double extra comma', 21)) self.assertEqual( scanstring('["Comma after the close"],', 2, None, True), (u'Comma after the close', 24)) self.assertEqual( scanstring('["Extra close"]]', 2, None, True), (u'Extra close', 14)) self.assertEqual( scanstring('{"Extra comma": true,}', 2, None, True), (u'Extra comma', 14)) self.assertEqual( scanstring('{"Extra value after close": true} "misplaced quoted value"', 2, None, True), (u'Extra value after close', 26)) self.assertEqual( scanstring('{"Illegal expression": 1 + 2}', 2, None, True), (u'Illegal expression', 21)) self.assertEqual( scanstring('{"Illegal invocation": alert()}', 2, None, True), (u'Illegal invocation', 21)) self.assertEqual( scanstring('{"Numbers cannot have leading zeroes": 013}', 2, None, True), (u'Numbers cannot have leading zeroes', 37)) self.assertEqual( scanstring('{"Numbers cannot be hex": 0x14}', 2, None, True), (u'Numbers cannot be hex', 24)) self.assertEqual( scanstring('[[[[[[[[[[[[[[[[[[[["Too deep"]]]]]]]]]]]]]]]]]]]]', 21, None, True), (u'Too deep', 30)) self.assertEqual( scanstring('{"Missing colon" null}', 2, None, True), (u'Missing colon', 16)) self.assertEqual( scanstring('{"Double colon":: null}', 2, None, True), (u'Double colon', 15)) self.assertEqual( scanstring('{"Comma instead of colon", null}', 2, None, True), (u'Comma instead of colon', 25)) self.assertEqual( scanstring('["Colon instead of comma": false]', 2, None, True), (u'Colon instead of comma', 25)) self.assertEqual( scanstring('["Bad value", truth]', 2, None, True), (u'Bad value', 12)) for c in map(chr, range(0x00, 0x1f)): self.assertEqual( scanstring(c + '"', 0, None, False), (c, 2)) self.assertRaises( ValueError, scanstring, c + '"', 0, None, True) self.assertRaises(ValueError, scanstring, '', 0, None, True) self.assertRaises(ValueError, scanstring, 'a', 0, None, True) self.assertRaises(ValueError, scanstring, '\\', 0, None, True) self.assertRaises(ValueError, scanstring, '\\u', 0, None, True) self.assertRaises(ValueError, scanstring, '\\u0', 0, None, True) self.assertRaises(ValueError, scanstring, '\\u01', 0, None, True) self.assertRaises(ValueError, scanstring, '\\u012', 0, None, True) self.assertRaises(ValueError, scanstring, '\\u0123', 0, None, True) if sys.maxunicode > 65535: self.assertRaises(ValueError, scanstring, '\\ud834\\u"', 0, None, True) self.assertRaises(ValueError, scanstring, '\\ud834\\x0123"', 0, None, True) def test_issue3623(self): self.assertRaises(ValueError, json.decoder.scanstring, "xxx", 1, "xxx") self.assertRaises(UnicodeDecodeError, json.encoder.encode_basestring_ascii, b("xx\xff")) def test_overflow(self): # Python 2.5 does not have maxsize, Python 3 does not have maxint maxsize = getattr(sys, 'maxsize', getattr(sys, 'maxint', None)) assert maxsize is not None self.assertRaises(OverflowError, json.decoder.scanstring, "xxx", maxsize + 1) def test_surrogates(self): scanstring = json.decoder.scanstring def assertScan(given, expect, test_utf8=True): givens = [given] if not PY3 and test_utf8: givens.append(given.encode('utf8')) for given in givens: (res, count) = scanstring(given, 1, None, True) self.assertEqual(len(given), count) self.assertEqual(res, expect) assertScan( u'"z\\ud834\\u0079x"', u'z\ud834yx') assertScan( u'"z\\ud834\\udd20x"', u'z\U0001d120x') assertScan( u'"z\\ud834\\ud834\\udd20x"', u'z\ud834\U0001d120x') assertScan( u'"z\\ud834x"', u'z\ud834x') assertScan( u'"z\\udd20x"', u'z\udd20x') assertScan( u'"z\ud834x"', u'z\ud834x') # It may look strange to join strings together, but Python is drunk. # https://gist.github.com/etrepum/5538443 assertScan( u'"z\\ud834\udd20x12345"', u''.join([u'z\ud834', u'\udd20x12345'])) assertScan( u'"z\ud834\\udd20x"', u''.join([u'z\ud834', u'\udd20x'])) # these have different behavior given UTF8 input, because the surrogate # pair may be joined (in maxunicode > 65535 builds) assertScan( u''.join([u'"z\ud834', u'\udd20x"']), u''.join([u'z\ud834', u'\udd20x']), test_utf8=False) self.assertRaises(ValueError, scanstring, u'"z\\ud83x"', 1, None, True) self.assertRaises(ValueError, scanstring, u'"z\\ud834\\udd2x"', 1, None, True) simplejson-3.8.1/simplejson/tests/test_separators.py0000644000076500000240000000165612363544726022740 0ustar bobstaff00000000000000import textwrap from unittest import TestCase import simplejson as json class TestSeparators(TestCase): def test_separators(self): 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 = json.dumps(h) d2 = json.dumps(h, indent=' ', sort_keys=True, separators=(' ,', ' : ')) h1 = json.loads(d1) h2 = json.loads(d2) self.assertEqual(h1, h) self.assertEqual(h2, h) self.assertEqual(d2, expect) simplejson-3.8.1/simplejson/tests/test_speedups.py0000644000076500000240000000176312363544726022404 0ustar bobstaff00000000000000import sys import unittest from unittest import TestCase from simplejson import encoder, scanner def has_speedups(): return encoder.c_make_encoder is not None def skip_if_speedups_missing(func): def wrapper(*args, **kwargs): if not has_speedups(): if hasattr(unittest, 'SkipTest'): raise unittest.SkipTest("C Extension not available") else: sys.stdout.write("C Extension not available") return return func(*args, **kwargs) return wrapper class TestDecode(TestCase): @skip_if_speedups_missing def test_make_scanner(self): self.assertRaises(AttributeError, scanner.c_make_scanner, 1) @skip_if_speedups_missing def test_make_encoder(self): self.assertRaises( TypeError, encoder.c_make_encoder, None, ("\xCD\x7D\x3D\x4E\x12\x4C\xF9\x79\xD7" "\x52\xBA\x82\xF2\x27\x4A\x7D\xA0\xCA\x75"), None ) simplejson-3.8.1/simplejson/tests/test_subclass.py0000644000076500000240000000214412526430441022352 0ustar bobstaff00000000000000from unittest import TestCase import simplejson as json from decimal import Decimal class AlternateInt(int): def __repr__(self): return 'invalid json' __str__ = __repr__ class AlternateFloat(float): def __repr__(self): return 'invalid json' __str__ = __repr__ # class AlternateDecimal(Decimal): # def __repr__(self): # return 'invalid json' class TestSubclass(TestCase): def test_int(self): self.assertEqual(json.dumps(AlternateInt(1)), '1') self.assertEqual(json.dumps(AlternateInt(-1)), '-1') self.assertEqual(json.loads(json.dumps({AlternateInt(1): 1})), {'1': 1}) def test_float(self): self.assertEqual(json.dumps(AlternateFloat(1.0)), '1.0') self.assertEqual(json.dumps(AlternateFloat(-1.0)), '-1.0') self.assertEqual(json.loads(json.dumps({AlternateFloat(1.0): 1})), {'1.0': 1}) # NOTE: Decimal subclasses are not supported as-is # def test_decimal(self): # self.assertEqual(json.dumps(AlternateDecimal('1.0')), '1.0') # self.assertEqual(json.dumps(AlternateDecimal('-1.0')), '-1.0') simplejson-3.8.1/simplejson/tests/test_tool.py0000644000076500000240000000544512363544726021532 0ustar bobstaff00000000000000from __future__ import with_statement import os import sys import textwrap import unittest import subprocess import tempfile try: # Python 3.x from test.support import strip_python_stderr except ImportError: # Python 2.6+ try: from test.test_support import strip_python_stderr except ImportError: # Python 2.5 import re def strip_python_stderr(stderr): return re.sub( r"\[\d+ refs\]\r?\n?$".encode(), "".encode(), stderr).strip() class TestTool(unittest.TestCase): data = """ [["blorpie"],[ "whoops" ] , [ ],\t"d-shtaeou",\r"d-nthiouh", "i-vhbjkhnth", {"nifty":87}, {"morefield" :\tfalse,"field" :"yes"} ] """ expect = textwrap.dedent("""\ [ [ "blorpie" ], [ "whoops" ], [], "d-shtaeou", "d-nthiouh", "i-vhbjkhnth", { "nifty": 87 }, { "field": "yes", "morefield": false } ] """) def runTool(self, args=None, data=None): argv = [sys.executable, '-m', 'simplejson.tool'] if args: argv.extend(args) proc = subprocess.Popen(argv, stdin=subprocess.PIPE, stderr=subprocess.PIPE, stdout=subprocess.PIPE) out, err = proc.communicate(data) self.assertEqual(strip_python_stderr(err), ''.encode()) self.assertEqual(proc.returncode, 0) return out def test_stdin_stdout(self): self.assertEqual( self.runTool(data=self.data.encode()), self.expect.encode()) def test_infile_stdout(self): with tempfile.NamedTemporaryFile() as infile: infile.write(self.data.encode()) infile.flush() self.assertEqual( self.runTool(args=[infile.name]), self.expect.encode()) def test_infile_outfile(self): with tempfile.NamedTemporaryFile() as infile: infile.write(self.data.encode()) infile.flush() # outfile will get overwritten by tool, so the delete # may not work on some platforms. Do it manually. outfile = tempfile.NamedTemporaryFile() try: self.assertEqual( self.runTool(args=[infile.name, outfile.name]), ''.encode()) with open(outfile.name, 'rb') as f: self.assertEqual(f.read(), self.expect.encode()) finally: outfile.close() if os.path.exists(outfile.name): os.unlink(outfile.name) simplejson-3.8.1/simplejson/tests/test_tuple.py0000644000076500000240000000344712552544500021674 0ustar bobstaff00000000000000import unittest from simplejson.compat import StringIO import simplejson as json class TestTuples(unittest.TestCase): def test_tuple_array_dumps(self): t = (1, 2, 3) expect = json.dumps(list(t)) # Default is True self.assertEqual(expect, json.dumps(t)) self.assertEqual(expect, json.dumps(t, tuple_as_array=True)) self.assertRaises(TypeError, json.dumps, t, tuple_as_array=False) # Ensure that the "default" does not get called self.assertEqual(expect, json.dumps(t, default=repr)) self.assertEqual(expect, json.dumps(t, tuple_as_array=True, default=repr)) # Ensure that the "default" gets called self.assertEqual( json.dumps(repr(t)), json.dumps(t, tuple_as_array=False, default=repr)) def test_tuple_array_dump(self): t = (1, 2, 3) expect = json.dumps(list(t)) # Default is True sio = StringIO() json.dump(t, sio) self.assertEqual(expect, sio.getvalue()) sio = StringIO() json.dump(t, sio, tuple_as_array=True) self.assertEqual(expect, sio.getvalue()) self.assertRaises(TypeError, json.dump, t, StringIO(), tuple_as_array=False) # Ensure that the "default" does not get called sio = StringIO() json.dump(t, sio, default=repr) self.assertEqual(expect, sio.getvalue()) sio = StringIO() json.dump(t, sio, tuple_as_array=True, default=repr) self.assertEqual(expect, sio.getvalue()) # Ensure that the "default" gets called sio = StringIO() json.dump(t, sio, tuple_as_array=False, default=repr) self.assertEqual( json.dumps(repr(t)), sio.getvalue()) simplejson-3.8.1/simplejson/tests/test_unicode.py0000644000076500000240000001552412363544726022202 0ustar bobstaff00000000000000import sys import codecs from unittest import TestCase import simplejson as json from simplejson.compat import unichr, text_type, b, u, BytesIO class TestUnicode(TestCase): def test_encoding1(self): encoder = json.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) self.assertEqual(ju, js) def test_encoding2(self): u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}' s = u.encode('utf-8') ju = json.dumps(u, encoding='utf-8') js = json.dumps(s, encoding='utf-8') self.assertEqual(ju, js) def test_encoding3(self): u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}' j = json.dumps(u) self.assertEqual(j, '"\\u03b1\\u03a9"') def test_encoding4(self): u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}' j = json.dumps([u]) self.assertEqual(j, '["\\u03b1\\u03a9"]') def test_encoding5(self): u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}' j = json.dumps(u, ensure_ascii=False) self.assertEqual(j, u'"' + u + u'"') def test_encoding6(self): u = u'\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}' j = json.dumps([u], ensure_ascii=False) self.assertEqual(j, u'["' + u + u'"]') def test_big_unicode_encode(self): u = u'\U0001d120' self.assertEqual(json.dumps(u), '"\\ud834\\udd20"') self.assertEqual(json.dumps(u, ensure_ascii=False), u'"\U0001d120"') def test_big_unicode_decode(self): u = u'z\U0001d120x' self.assertEqual(json.loads('"' + u + '"'), u) self.assertEqual(json.loads('"z\\ud834\\udd20x"'), u) def test_unicode_decode(self): for i in range(0, 0xd7ff): u = unichr(i) #s = '"\\u{0:04x}"'.format(i) s = '"\\u%04x"' % (i,) self.assertEqual(json.loads(s), u) def test_object_pairs_hook_with_unicode(self): s = u'{"xkd":1, "kcw":2, "art":3, "hxm":4, "qrt":5, "pad":6, "hoy":7}' p = [(u"xkd", 1), (u"kcw", 2), (u"art", 3), (u"hxm", 4), (u"qrt", 5), (u"pad", 6), (u"hoy", 7)] self.assertEqual(json.loads(s), eval(s)) self.assertEqual(json.loads(s, object_pairs_hook=lambda x: x), p) od = json.loads(s, object_pairs_hook=json.OrderedDict) self.assertEqual(od, json.OrderedDict(p)) self.assertEqual(type(od), json.OrderedDict) # the object_pairs_hook takes priority over the object_hook self.assertEqual(json.loads(s, object_pairs_hook=json.OrderedDict, object_hook=lambda x: None), json.OrderedDict(p)) def test_default_encoding(self): self.assertEqual(json.loads(u'{"a": "\xe9"}'.encode('utf-8')), {'a': u'\xe9'}) def test_unicode_preservation(self): self.assertEqual(type(json.loads(u'""')), text_type) self.assertEqual(type(json.loads(u'"a"')), text_type) self.assertEqual(type(json.loads(u'["a"]')[0]), text_type) def test_ensure_ascii_false_returns_unicode(self): # http://code.google.com/p/simplejson/issues/detail?id=48 self.assertEqual(type(json.dumps([], ensure_ascii=False)), text_type) self.assertEqual(type(json.dumps(0, ensure_ascii=False)), text_type) self.assertEqual(type(json.dumps({}, ensure_ascii=False)), text_type) self.assertEqual(type(json.dumps("", ensure_ascii=False)), text_type) def test_ensure_ascii_false_bytestring_encoding(self): # http://code.google.com/p/simplejson/issues/detail?id=48 doc1 = {u'quux': b('Arr\xc3\xaat sur images')} doc2 = {u'quux': u('Arr\xeat sur images')} doc_ascii = '{"quux": "Arr\\u00eat sur images"}' doc_unicode = u'{"quux": "Arr\xeat sur images"}' self.assertEqual(json.dumps(doc1), doc_ascii) self.assertEqual(json.dumps(doc2), doc_ascii) self.assertEqual(json.dumps(doc1, ensure_ascii=False), doc_unicode) self.assertEqual(json.dumps(doc2, ensure_ascii=False), doc_unicode) def test_ensure_ascii_linebreak_encoding(self): # http://timelessrepo.com/json-isnt-a-javascript-subset s1 = u'\u2029\u2028' s2 = s1.encode('utf8') expect = '"\\u2029\\u2028"' self.assertEqual(json.dumps(s1), expect) self.assertEqual(json.dumps(s2), expect) self.assertEqual(json.dumps(s1, ensure_ascii=False), expect) self.assertEqual(json.dumps(s2, ensure_ascii=False), expect) def test_invalid_escape_sequences(self): # incomplete escape sequence self.assertRaises(json.JSONDecodeError, json.loads, '"\\u') self.assertRaises(json.JSONDecodeError, json.loads, '"\\u1') self.assertRaises(json.JSONDecodeError, json.loads, '"\\u12') self.assertRaises(json.JSONDecodeError, json.loads, '"\\u123') self.assertRaises(json.JSONDecodeError, json.loads, '"\\u1234') # invalid escape sequence self.assertRaises(json.JSONDecodeError, json.loads, '"\\u123x"') self.assertRaises(json.JSONDecodeError, json.loads, '"\\u12x4"') self.assertRaises(json.JSONDecodeError, json.loads, '"\\u1x34"') self.assertRaises(json.JSONDecodeError, json.loads, '"\\ux234"') if sys.maxunicode > 65535: # invalid escape sequence for low surrogate self.assertRaises(json.JSONDecodeError, json.loads, '"\\ud800\\u"') self.assertRaises(json.JSONDecodeError, json.loads, '"\\ud800\\u0"') self.assertRaises(json.JSONDecodeError, json.loads, '"\\ud800\\u00"') self.assertRaises(json.JSONDecodeError, json.loads, '"\\ud800\\u000"') self.assertRaises(json.JSONDecodeError, json.loads, '"\\ud800\\u000x"') self.assertRaises(json.JSONDecodeError, json.loads, '"\\ud800\\u00x0"') self.assertRaises(json.JSONDecodeError, json.loads, '"\\ud800\\u0x00"') self.assertRaises(json.JSONDecodeError, json.loads, '"\\ud800\\ux000"') def test_ensure_ascii_still_works(self): # in the ascii range, ensure that everything is the same for c in map(unichr, range(0, 127)): self.assertEqual( json.dumps(c, ensure_ascii=False), json.dumps(c)) snowman = u'\N{SNOWMAN}' self.assertEqual( json.dumps(c, ensure_ascii=False), '"' + c + '"') def test_strip_bom(self): content = u"\u3053\u3093\u306b\u3061\u308f" json_doc = codecs.BOM_UTF8 + b(json.dumps(content)) self.assertEqual(json.load(BytesIO(json_doc)), content) for doc in json_doc, json_doc.decode('utf8'): self.assertEqual(json.loads(doc), content) simplejson-3.8.1/simplejson/tool.py0000644000076500000240000000216012371554637017321 0ustar bobstaff00000000000000r"""Command-line tool to validate and pretty-print JSON Usage:: $ 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) """ from __future__ import with_statement import sys import simplejson as json def main(): if len(sys.argv) == 1: infile = sys.stdin outfile = sys.stdout elif len(sys.argv) == 2: infile = open(sys.argv[1], 'r') outfile = sys.stdout elif len(sys.argv) == 3: infile = open(sys.argv[1], 'r') outfile = open(sys.argv[2], 'w') else: raise SystemExit(sys.argv[0] + " [infile [outfile]]") with infile: try: obj = json.load(infile, object_pairs_hook=json.OrderedDict, use_decimal=True) except ValueError: raise SystemExit(sys.exc_info()[1]) with outfile: json.dump(obj, outfile, sort_keys=True, indent=' ', use_decimal=True) outfile.write('\n') if __name__ == '__main__': main() simplejson-3.8.1/simplejson.egg-info/0000755000076500000240000000000012613714404017452 5ustar bobstaff00000000000000simplejson-3.8.1/simplejson.egg-info/dependency_links.txt0000644000076500000240000000000112613714377023531 0ustar bobstaff00000000000000 simplejson-3.8.1/simplejson.egg-info/PKG-INFO0000644000076500000240000000525712613714377020571 0ustar bobstaff00000000000000Metadata-Version: 1.1 Name: simplejson Version: 3.8.1 Summary: Simple, fast, extensible JSON encoder/decoder for Python Home-page: http://github.com/simplejson/simplejson Author: Bob Ippolito Author-email: bob@redivi.com License: MIT License Description: simplejson is a simple, fast, complete, correct and extensible JSON encoder and decoder for Python 2.5+ and Python 3.3+. It is pure Python code with no dependencies, but includes an optional C extension for a serious speed boost. The latest documentation for simplejson can be read online here: http://simplejson.readthedocs.org/ simplejson is the externally maintained development version of the json library included with Python 2.6 and Python 3.0, but maintains backwards compatibility with Python 2.5. The encoder can be specialized to provide serialization in any kind of situation, without any special support by the objects to be serialized (somewhat like pickle). This is best done with the ``default`` kwarg to dumps. The decoder can handle incoming JSON strings of any specified encoding (UTF-8 by default). It can also be specialized to post-process JSON objects with the ``object_hook`` or ``object_pairs_hook`` kwargs. This is particularly useful for implementing protocols such as JSON-RPC that have a richer type system than JSON itself. For those of you that have legacy systems to maintain, there is a very old fork of simplejson in the `python2.2`_ branch that supports Python 2.2. This is based off of a very old version of simplejson, is not maintained, and should only be used as a last resort. .. _python2.2: https://github.com/simplejson/simplejson/tree/python2.2 Platform: any Classifier: Development Status :: 5 - Production/Stable Classifier: Intended Audience :: Developers Classifier: License :: OSI Approved :: MIT License Classifier: License :: OSI Approved :: Academic Free License (AFL) Classifier: Programming Language :: Python Classifier: Programming Language :: Python :: 2 Classifier: Programming Language :: Python :: 2.5 Classifier: Programming Language :: Python :: 2.6 Classifier: Programming Language :: Python :: 2.7 Classifier: Programming Language :: Python :: 3 Classifier: Programming Language :: Python :: 3.3 Classifier: Programming Language :: Python :: 3.4 Classifier: Programming Language :: Python :: Implementation :: CPython Classifier: Programming Language :: Python :: Implementation :: PyPy Classifier: Topic :: Software Development :: Libraries :: Python Modules simplejson-3.8.1/simplejson.egg-info/SOURCES.txt0000644000076500000240000000260712613714377021354 0ustar bobstaff00000000000000CHANGES.txt LICENSE.txt MANIFEST.in README.rst conf.py index.rst setup.py scripts/make_docs.py simplejson/__init__.py simplejson/_speedups.c simplejson/compat.py simplejson/decoder.py simplejson/encoder.py simplejson/ordered_dict.py simplejson/scanner.py simplejson/tool.py simplejson.egg-info/PKG-INFO simplejson.egg-info/SOURCES.txt simplejson.egg-info/dependency_links.txt simplejson.egg-info/top_level.txt simplejson/tests/__init__.py simplejson/tests/test_bigint_as_string.py simplejson/tests/test_bitsize_int_as_string.py simplejson/tests/test_check_circular.py simplejson/tests/test_decimal.py simplejson/tests/test_decode.py simplejson/tests/test_default.py simplejson/tests/test_dump.py simplejson/tests/test_encode_basestring_ascii.py simplejson/tests/test_encode_for_html.py simplejson/tests/test_errors.py simplejson/tests/test_fail.py simplejson/tests/test_float.py simplejson/tests/test_for_json.py simplejson/tests/test_indent.py simplejson/tests/test_item_sort_key.py simplejson/tests/test_iterable.py simplejson/tests/test_namedtuple.py simplejson/tests/test_pass1.py simplejson/tests/test_pass2.py simplejson/tests/test_pass3.py simplejson/tests/test_recursion.py simplejson/tests/test_scanstring.py simplejson/tests/test_separators.py simplejson/tests/test_speedups.py simplejson/tests/test_subclass.py simplejson/tests/test_tool.py simplejson/tests/test_tuple.py simplejson/tests/test_unicode.pysimplejson-3.8.1/simplejson.egg-info/top_level.txt0000644000076500000240000000001312613714377022207 0ustar bobstaff00000000000000simplejson