/usr/share/pyshared/bson/__init__.py is in python-bson 2.1-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 | # Copyright 2009-2010 10gen, Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""BSON (Binary JSON) encoding and decoding.
"""
import calendar
import datetime
import re
import struct
import warnings
from bson.binary import Binary, UUID_SUBTYPE
from bson.code import Code
from bson.dbref import DBRef
from bson.errors import (InvalidBSON,
InvalidDocument,
InvalidStringData)
from bson.max_key import MaxKey
from bson.min_key import MinKey
from bson.objectid import ObjectId
from bson.son import SON
from bson.timestamp import Timestamp
from bson.tz_util import utc
try:
import _cbson
_use_c = True
except ImportError:
_use_c = False
try:
import uuid
_use_uuid = True
except ImportError:
_use_uuid = False
# This sort of sucks, but seems to be as good as it gets...
RE_TYPE = type(re.compile(""))
MAX_INT32 = 2147483647
MIN_INT32 = -2147483648
MAX_INT64 = 9223372036854775807
MIN_INT64 = -9223372036854775808
EPOCH_AWARE = datetime.datetime.fromtimestamp(0, utc)
EPOCH_NAIVE = datetime.datetime.utcfromtimestamp(0)
def _get_int(data, position, as_class=None, tz_aware=False, unsigned=False):
format = unsigned and "I" or "i"
try:
value = struct.unpack("<%s" % format, data[position:position + 4])[0]
except struct.error:
raise InvalidBSON()
position += 4
return value, position
def _get_c_string(data, position, length=None):
if length is None:
try:
end = data.index("\x00", position)
except ValueError:
raise InvalidBSON()
else:
end = position + length
value = unicode(data[position:end], "utf-8")
position = end + 1
return value, position
def _make_c_string(string, check_null=False):
if check_null and "\x00" in string:
raise InvalidDocument("BSON keys / regex patterns must not "
"contain a NULL character")
if isinstance(string, unicode):
return string.encode("utf-8") + "\x00"
else:
try:
string.decode("utf-8")
return string + "\x00"
except UnicodeError:
raise InvalidStringData("strings in documents must be valid "
"UTF-8: %r" % string)
def _get_number(data, position, as_class, tz_aware):
num = struct.unpack("<d", data[position:position + 8])[0]
position += 8
return num, position
def _get_string(data, position, as_class, tz_aware):
length = struct.unpack("<i", data[position:position + 4])[0] - 1
position += 4
return _get_c_string(data, position, length)
def _get_object(data, position, as_class, tz_aware):
obj_size = struct.unpack("<i", data[position:position + 4])[0]
encoded = data[position + 4:position + obj_size - 1]
object = _elements_to_dict(encoded, as_class, tz_aware)
position += obj_size
if "$ref" in object:
return (DBRef(object.pop("$ref"), object.pop("$id"),
object.pop("$db", None), object), position)
return object, position
def _get_array(data, position, as_class, tz_aware):
obj, position = _get_object(data, position, as_class, tz_aware)
result = []
i = 0
while True:
try:
result.append(obj[str(i)])
i += 1
except KeyError:
break
return result, position
def _get_binary(data, position, as_class, tz_aware):
length, position = _get_int(data, position)
subtype = ord(data[position])
position += 1
if subtype == 2:
length2, position = _get_int(data, position)
if length2 != length - 4:
raise InvalidBSON("invalid binary (st 2) - lengths don't match!")
length = length2
if subtype in (3, 4) and _use_uuid:
value = uuid.UUID(bytes=data[position:position + length])
position += length
return (value, position)
value = Binary(data[position:position + length], subtype)
position += length
return value, position
def _get_oid(data, position, as_class, tz_aware):
value = ObjectId(data[position:position + 12])
position += 12
return value, position
def _get_boolean(data, position, as_class, tz_aware):
value = data[position] == "\x01"
position += 1
return value, position
def _get_date(data, position, as_class, tz_aware):
seconds = float(struct.unpack("<q", data[position:position + 8])[0]) / 1000.0
position += 8
if tz_aware:
return EPOCH_AWARE + datetime.timedelta(seconds=seconds), position
return EPOCH_NAIVE + datetime.timedelta(seconds=seconds), position
def _get_code_w_scope(data, position, as_class, tz_aware):
_, position = _get_int(data, position)
code, position = _get_string(data, position, as_class, tz_aware)
scope, position = _get_object(data, position, as_class, tz_aware)
return Code(code, scope), position
def _get_null(data, position, as_class, tz_aware):
return None, position
def _get_regex(data, position, as_class, tz_aware):
pattern, position = _get_c_string(data, position)
bson_flags, position = _get_c_string(data, position)
flags = 0
if "i" in bson_flags:
flags |= re.IGNORECASE
if "l" in bson_flags:
flags |= re.LOCALE
if "m" in bson_flags:
flags |= re.MULTILINE
if "s" in bson_flags:
flags |= re.DOTALL
if "u" in bson_flags:
flags |= re.UNICODE
if "x" in bson_flags:
flags |= re.VERBOSE
return re.compile(pattern, flags), position
def _get_ref(data, position, as_class, tz_aware):
position += 4
collection, position = _get_c_string(data, position)
oid, position = _get_oid(data, position)
return DBRef(collection, oid), position
def _get_timestamp(data, position, as_class, tz_aware):
inc, position = _get_int(data, position, unsigned=True)
timestamp, position = _get_int(data, position, unsigned=True)
return Timestamp(timestamp, inc), position
def _get_long(data, position, as_class, tz_aware):
# Have to cast to long; on 32-bit unpack may return an int.
value = long(struct.unpack("<q", data[position:position + 8])[0])
position += 8
return value, position
_element_getter = {
"\x01": _get_number,
"\x02": _get_string,
"\x03": _get_object,
"\x04": _get_array,
"\x05": _get_binary,
"\x06": _get_null, # undefined
"\x07": _get_oid,
"\x08": _get_boolean,
"\x09": _get_date,
"\x0A": _get_null,
"\x0B": _get_regex,
"\x0C": _get_ref,
"\x0D": _get_string, # code
"\x0E": _get_string, # symbol
"\x0F": _get_code_w_scope,
"\x10": _get_int, # number_int
"\x11": _get_timestamp,
"\x12": _get_long,
"\xFF": lambda w, x, y, z: (MinKey(), x),
"\x7F": lambda w, x, y, z: (MaxKey(), x)}
def _element_to_dict(data, position, as_class, tz_aware):
element_type = data[position]
position += 1
element_name, position = _get_c_string(data, position)
value, position = _element_getter[element_type](data, position,
as_class, tz_aware)
return element_name, value, position
def _elements_to_dict(data, as_class, tz_aware):
result = as_class()
position = 0
end = len(data) - 1
while position < end:
(key, value, position) = _element_to_dict(data, position, as_class, tz_aware)
result[key] = value
return result
def _bson_to_dict(data, as_class, tz_aware):
obj_size = struct.unpack("<i", data[:4])[0]
if len(data) < obj_size:
raise InvalidBSON("objsize too large")
if data[obj_size - 1] != "\x00":
raise InvalidBSON("bad eoo")
elements = data[4:obj_size - 1]
return (_elements_to_dict(elements, as_class, tz_aware), data[obj_size:])
if _use_c:
_bson_to_dict = _cbson._bson_to_dict
def _element_to_bson(key, value, check_keys, uuid_subtype):
if not isinstance(key, basestring):
raise InvalidDocument("documents must have only string keys, "
"key was %r" % key)
if check_keys:
if key.startswith("$"):
raise InvalidDocument("key %r must not start with '$'" % key)
if "." in key:
raise InvalidDocument("key %r must not contain '.'" % key)
name = _make_c_string(key, True)
if isinstance(value, float):
return "\x01" + name + struct.pack("<d", value)
# Use Binary w/ subtype 3 for UUID instances
if _use_uuid:
if isinstance(value, uuid.UUID):
value = Binary(value.bytes, subtype=uuid_subtype)
if isinstance(value, Binary):
subtype = value.subtype
if subtype == 2:
value = struct.pack("<i", len(value)) + value
return "\x05%s%s%s%s" % (name, struct.pack("<i", len(value)),
chr(subtype), value)
if isinstance(value, Code):
cstring = _make_c_string(value)
scope = _dict_to_bson(value.scope, False, uuid_subtype, False)
full_length = struct.pack("<i", 8 + len(cstring) + len(scope))
length = struct.pack("<i", len(cstring))
return "\x0F" + name + full_length + length + cstring + scope
if isinstance(value, str):
cstring = _make_c_string(value)
length = struct.pack("<i", len(cstring))
return "\x02" + name + length + cstring
if isinstance(value, unicode):
cstring = _make_c_string(value)
length = struct.pack("<i", len(cstring))
return "\x02" + name + length + cstring
if isinstance(value, dict):
return "\x03" + name + _dict_to_bson(value, check_keys, uuid_subtype, False)
if isinstance(value, (list, tuple)):
as_dict = SON(zip([str(i) for i in range(len(value))], value))
return "\x04" + name + _dict_to_bson(as_dict, check_keys, uuid_subtype, False)
if isinstance(value, ObjectId):
return "\x07" + name + value.binary
if value is True:
return "\x08" + name + "\x01"
if value is False:
return "\x08" + name + "\x00"
if isinstance(value, int):
# TODO this is an ugly way to check for this...
if value > MAX_INT64 or value < MIN_INT64:
raise OverflowError("BSON can only handle up to 8-byte ints")
if value > MAX_INT32 or value < MIN_INT32:
return "\x12" + name + struct.pack("<q", value)
return "\x10" + name + struct.pack("<i", value)
if isinstance(value, long):
# XXX No long type in Python 3
if value > MAX_INT64 or value < MIN_INT64:
raise OverflowError("BSON can only handle up to 8-byte ints")
return "\x12" + name + struct.pack("<q", value)
if isinstance(value, datetime.datetime):
if value.utcoffset() is not None:
value = value - value.utcoffset()
millis = int(calendar.timegm(value.timetuple()) * 1000 +
value.microsecond / 1000)
return "\x09" + name + struct.pack("<q", millis)
if isinstance(value, Timestamp):
time = struct.pack("<I", value.time)
inc = struct.pack("<I", value.inc)
return "\x11" + name + inc + time
if value is None:
return "\x0A" + name
if isinstance(value, RE_TYPE):
pattern = value.pattern
flags = ""
if value.flags & re.IGNORECASE:
flags += "i"
if value.flags & re.LOCALE:
flags += "l"
if value.flags & re.MULTILINE:
flags += "m"
if value.flags & re.DOTALL:
flags += "s"
if value.flags & re.UNICODE:
flags += "u"
if value.flags & re.VERBOSE:
flags += "x"
return "\x0B" + name + _make_c_string(pattern, True) + \
_make_c_string(flags)
if isinstance(value, DBRef):
return _element_to_bson(key, value.as_doc(), False, uuid_subtype)
if isinstance(value, MinKey):
return "\xFF" + name
if isinstance(value, MaxKey):
return "\x7F" + name
raise InvalidDocument("cannot convert value of type %s to bson" %
type(value))
def _dict_to_bson(dict, check_keys, uuid_subtype, top_level=True):
try:
elements = []
if top_level and "_id" in dict:
elements.append(_element_to_bson("_id", dict["_id"], False, uuid_subtype))
for (key, value) in dict.iteritems():
if not top_level or key != "_id":
elements.append(_element_to_bson(key, value, check_keys, uuid_subtype))
except AttributeError:
raise TypeError("encoder expected a mapping type but got: %r" % dict)
encoded = ''.join(elements)
length = len(encoded) + 5
return struct.pack("<i", length) + encoded + "\x00"
if _use_c:
_dict_to_bson = _cbson._dict_to_bson
def _to_dicts(data, as_class=dict, tz_aware=True):
"""DEPRECATED - `_to_dicts` has been renamed to `decode_all`.
.. versionchanged:: 1.9
Deprecated in favor of :meth:`decode_all`.
.. versionadded:: 1.7
The `as_class` parameter.
"""
warnings.warn("`_to_dicts` has been renamed to `decode_all`",
DeprecationWarning)
return decode_all(data, as_class, tz_aware)
def decode_all(data, as_class=dict, tz_aware=True):
"""Decode BSON data to multiple documents.
`data` must be a string of concatenated, valid, BSON-encoded
documents.
:Parameters:
- `data`: BSON data
- `as_class` (optional): the class to use for the resulting
documents
- `tz_aware` (optional): if ``True``, return timezone-aware
:class:`~datetime.datetime` instances
.. versionadded:: 1.9
"""
docs = []
position = 0
end = len(data) - 1
while position < end:
obj_size = struct.unpack("<i", data[position:position + 4])[0]
if len(data) - position < obj_size:
raise InvalidBSON("objsize too large")
if data[position + obj_size - 1] != "\x00":
raise InvalidBSON("bad eoo")
elements = data[position + 4:position + obj_size - 1]
position += obj_size
docs.append(_elements_to_dict(elements, as_class, tz_aware))
return docs
if _use_c:
decode_all = _cbson.decode_all
def is_valid(bson):
"""Check that the given string represents valid :class:`BSON` data.
Raises :class:`TypeError` if `bson` is not an instance of
:class:`str`. Returns ``True`` if `bson` is valid :class:`BSON`,
``False`` otherwise.
:Parameters:
- `bson`: the data to be validated
"""
if not isinstance(bson, str):
raise TypeError("BSON data must be an instance of a subclass of str")
try:
(_, remainder) = _bson_to_dict(bson, dict, True)
return remainder == ""
except:
return False
class BSON(str):
"""BSON (Binary JSON) data.
"""
@classmethod
def from_dict(cls, dct, check_keys=False):
"""DEPRECATED - `from_dict` has been renamed to `encode`.
.. versionchanged:: 1.9
Deprecated in favor of :meth:`encode`
"""
warnings.warn("`from_dict` has been renamed to `encode`",
DeprecationWarning)
return cls.encode(dct, check_keys)
@classmethod
def encode(cls, document, check_keys=False, uuid_subtype=UUID_SUBTYPE):
"""Encode a document to a new :class:`BSON` instance.
A document can be any mapping type (like :class:`dict`).
Raises :class:`TypeError` if `document` is not a mapping type,
or contains keys that are not instances of
:class:`basestring`. Raises
:class:`~bson.errors.InvalidDocument` if `document` cannot be
converted to :class:`BSON`.
:Parameters:
- `document`: mapping type representing a document
- `check_keys` (optional): check if keys start with '$' or
contain '.', raising :class:`~bson.errors.InvalidDocument` in
either case
.. versionadded:: 1.9
"""
return cls(_dict_to_bson(document, check_keys, uuid_subtype))
def to_dict(self, as_class=dict, tz_aware=False):
"""DEPRECATED - `to_dict` has been renamed to `decode`.
.. versionchanged:: 1.9
Deprecated in favor of :meth:`decode`
.. versionadded:: 1.8
The `tz_aware` parameter.
.. versionadded:: 1.7
The `as_class` parameter.
"""
warnings.warn("`to_dict` has been renamed to `decode`",
DeprecationWarning)
return self.decode(as_class, tz_aware)
def decode(self, as_class=dict, tz_aware=False):
"""Decode this BSON data.
The default type to use for the resultant document is
:class:`dict`. Any other class that supports
:meth:`__setitem__` can be used instead by passing it as the
`as_class` parameter.
If `tz_aware` is ``True`` (recommended), any
:class:`~datetime.datetime` instances returned will be
timezone-aware, with their timezone set to
:attr:`bson.tz_util.utc`. Otherwise (default), all
:class:`~datetime.datetime` instances will be naive (but
contain UTC).
:Parameters:
- `as_class` (optional): the class to use for the resulting
document
- `tz_aware` (optional): if ``True``, return timezone-aware
:class:`~datetime.datetime` instances
.. versionadded:: 1.9
"""
(document, _) = _bson_to_dict(self, as_class, tz_aware)
return document
def has_c():
"""Is the C extension installed?
.. versionadded:: 1.9
"""
try:
from bson import _cbson
return True
except ImportError:
return False
|