cpython/Lib/json/__init__.py at main · python/cpython · GitHub

Repository navigation

History

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

r"""JSON (JavaScript Object Notation) <https://json.org> is a subset of

JavaScript syntax (ECMA-262 3rd edition) used as a lightweight data

interchange format.

:mod:`json` exposes an API familiar to users of the standard library

:mod:`marshal` and :mod:`pickle` modules. It is derived from a

version of the externally maintained simplejson library.

Encoding basic Python object hierarchies::

>>> import 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('\u1234'))

"\u1234"

>>> print(json.dumps('\\'))

"\\"

>>> print(json.dumps({"c": 0, "b": 0, "a": 0}, sort_keys=True))

{"a": 0, "b": 0, "c": 0}

>>> from io import StringIO

>>> io = StringIO()

>>> json.dump(['streaming API'], io)

>>> io.getvalue()

'["streaming API"]'

Compact encoding::

>>> import json

>>> mydict = {'4': 5, '6': 7}

>>> json.dumps([1,2,3,mydict], separators=(',', ':'))

'[1,2,3,{"4":5,"6":7}]'

Pretty printing::

>>> import json

>>> print(json.dumps({'4': 5, '6': 7}, sort_keys=True, indent=4))

{

"4": 5,

"6": 7

}

Decoding JSON::

>>> import json

>>> obj = ['foo', {'bar': ['baz', None, 1.0, 2]}]

>>> json.loads('["foo", {"bar":["baz", null, 1.0, 2]}]') == obj

True

>>> json.loads('"\\"foo\\bar"') == '"foo\x08ar'

True

>>> from io import StringIO

>>> io = StringIO('["streaming API"]')

>>> json.load(io)[0] == 'streaming API'

True

Specializing JSON object decoding::

>>> import 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 json

>>> def encode_complex(obj):

... if isinstance(obj, complex):

... return [obj.real, obj.imag]

... raise TypeError(f'Object of type {obj.__class__.__name__} '

... f'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 json from the shell to validate and pretty-print::

$ echo '{"json":"obj"}' | python -m json

{

"json": "obj"

}

$ echo '{ 1.2:3.4}' | python -m json

Expecting property name enclosed in double quotes: line 1 column 3 (char 2)

"""

__all__ = [

'dump', 'dumps', 'load', 'loads',

'JSONDecoder', 'JSONDecodeError', 'JSONEncoder',

]

__author__ = 'Bob Ippolito <bob@redivi.com>'

from .decoder import JSONDecoder, JSONDecodeError

from .encoder import JSONEncoder

import codecs

_default_encoder = JSONEncoder(

skipkeys=False,

ensure_ascii=True,

check_circular=True,

allow_nan=True,

indent=None,

separators=None,

default=None,

)

def dump(obj, fp, *, skipkeys=False, ensure_ascii=True, check_circular=True,

allow_nan=True, cls=None, indent=None, separators=None,

default=None, sort_keys=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``, ``int``, ``float``, ``bool``, ``None``) will be skipped

instead of raising a ``TypeError``.

If ``ensure_ascii`` is false, then the strings written to ``fp`` can

contain non-ASCII and non-printable characters if they appear in strings

contained in ``obj``. Otherwise, all such characters are escaped in JSON

strings.

If ``check_circular`` is false, then the circular reference check

for container types will be skipped and a circular reference will

result in an ``RecursionError`` (or worse).

If ``allow_nan`` is false, then it will be a ``ValueError`` to

serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``)

in strict compliance of the JSON specification, instead of using the

JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).

If ``indent`` is a non-negative integer, then JSON array elements and

object members will be pretty-printed with that indent level. An indent

level of 0 will only insert newlines. ``None`` is the default and gives

a representation with no newlines inserted.

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.

``default(obj)`` is a function that should return a serializable version

of obj or raise TypeError. The default simply raises TypeError.

If *sort_keys* is true (default: ``False``), then the output of

dictionaries will be sorted by key.

To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the

``.default()`` method to serialize additional types), specify it with

the ``cls`` kwarg; otherwise ``JSONEncoder`` is used.

"""

# 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

default is None and not sort_keys 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,

default=default, sort_keys=sort_keys, **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,

default=None, sort_keys=False, **kw):

"""Serialize ``obj`` to a JSON formatted ``str``.

If ``skipkeys`` is true then ``dict`` keys that are not basic types

(``str``, ``int``, ``float``, ``bool``, ``None``) will be skipped

instead of raising a ``TypeError``.

If ``ensure_ascii`` is false, then the return value can contain

non-ASCII and non-printable characters if they appear in strings

contained in ``obj``. Otherwise, all such characters are escaped in

JSON strings.

If ``check_circular`` is false, then the circular reference check

for container types will be skipped and a circular reference will

result in an ``RecursionError`` (or worse).

If ``allow_nan`` is false, then it will be a ``ValueError`` to

serialize out of range ``float`` values (``nan``, ``inf``, ``-inf``) in

strict compliance of the JSON specification, instead of using the

JavaScript equivalents (``NaN``, ``Infinity``, ``-Infinity``).

If ``indent`` is a non-negative integer, then JSON array elements and

object members will be pretty-printed with that indent level. An indent

level of 0 will only insert newlines. ``None`` is the default and gives

a representation with no newlines inserted.

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.

``default(obj)`` is a function that should return a serializable version

of obj or raise TypeError. The default simply raises TypeError.

If *sort_keys* is true (default: ``False``), then the output of

dictionaries will be sorted by key.

To use a custom ``JSONEncoder`` subclass (e.g. one that overrides the

``.default()`` method to serialize additional types), specify it with

the ``cls`` kwarg; otherwise ``JSONEncoder`` is used.

"""

# 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

default is None and not sort_keys 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, default=default, sort_keys=sort_keys,

**kw).encode(obj)

_default_decoder = JSONDecoder()

def detect_encoding(b):

bstartswith = b.startswith

if bstartswith((codecs.BOM_UTF32_BE, codecs.BOM_UTF32_LE)):

return 'utf-32'

if bstartswith((codecs.BOM_UTF16_BE, codecs.BOM_UTF16_LE)):

return 'utf-16'

if bstartswith(codecs.BOM_UTF8):

return 'utf-8-sig'

if len(b) >= 4:

if not b[0]:

# 00 00 -- -- - utf-32-be

# 00 XX -- -- - utf-16-be

return 'utf-16-be' if b[1] else 'utf-32-be'

if not b[1]:

# XX 00 00 00 - utf-32-le

# XX 00 00 XX - utf-16-le

# XX 00 XX -- - utf-16-le

return 'utf-16-le' if b[2] or b[3] else 'utf-32-le'

elif len(b) == 2:

if not b[0]:

# 00 XX - utf-16-be

return 'utf-16-be'

if not b[1]:

# XX 00 - utf-16-le

return 'utf-16-le'

# default

return 'utf-8'

def load(fp, *, cls=None, object_hook=None, parse_float=None,

parse_int=None, parse_constant=None, object_pairs_hook=None,

array_hook=None, **kw):

"""Deserialize ``fp`` (a ``.read()``-supporting file-like object containing

a JSON document) to a Python object.

``object_hook`` is an optional function that will be called with the

result of any object literal decode (a ``dict``). The return value of

``object_hook`` will be used instead of the ``dict``. This feature

can be used to implement custom decoders (e.g. JSON-RPC class hinting).

``object_pairs_hook`` is an optional function that will be called with

the result of any object literal decoded with an ordered list of pairs.

The return value of ``object_pairs_hook`` will be used instead of the

``dict``. This feature can be used to implement custom decoders. If

``object_hook`` is also defined, the ``object_pairs_hook`` takes

priority.

``array_hook`` is an optional function that will be called with the

result of any literal array decode (a ``list``). The return value of

this function will be used instead of the ``list``. This feature can

be used along ``object_pairs_hook`` to customize the resulting data

structure - for example, by setting that to ``frozendict`` and

``array_hook`` to ``tuple``, one can get a deep immutable data structure

from any JSON data.

To use a custom ``JSONDecoder`` subclass, specify it with the ``cls``

kwarg; otherwise ``JSONDecoder`` is used.

"""

return loads(fp.read(),

cls=cls, object_hook=object_hook,

parse_float=parse_float, parse_int=parse_int,

parse_constant=parse_constant, object_pairs_hook=object_pairs_hook,

array_hook=array_hook, **kw)

def loads(s, *, cls=None, object_hook=None, parse_float=None,

parse_int=None, parse_constant=None, object_pairs_hook=None,

array_hook=None, **kw):

"""Deserialize ``s`` (a ``str``, ``bytes`` or ``bytearray`` instance

containing a JSON document) to a Python object.