sensu-plugins-mongodb-mrtrotl 1.4.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/CHANGELOG.md +1 -0
- data/LICENSE +22 -0
- data/README.md +27 -0
- data/bin/check-mongodb-metric.rb +144 -0
- data/bin/check-mongodb-query-count.rb +267 -0
- data/bin/check-mongodb.py +1644 -0
- data/bin/check-mongodb.rb +5 -0
- data/bin/metrics-mongodb-replication.rb +254 -0
- data/bin/metrics-mongodb.rb +133 -0
- data/lib/bson/__init__.py +1347 -0
- data/lib/bson/__pycache__/__init__.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/_helpers.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/binary.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/code.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/codec_options.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/dbref.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/decimal128.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/errors.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/int64.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/json_util.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/max_key.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/min_key.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/objectid.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/raw_bson.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/regex.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/son.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/timestamp.cpython-310.pyc +0 -0
- data/lib/bson/__pycache__/tz_util.cpython-310.pyc +0 -0
- data/lib/bson/_cbson.cpython-310-x86_64-linux-gnu.so +0 -0
- data/lib/bson/_helpers.py +41 -0
- data/lib/bson/binary.py +364 -0
- data/lib/bson/code.py +101 -0
- data/lib/bson/codec_options.py +414 -0
- data/lib/bson/codec_options.pyi +100 -0
- data/lib/bson/dbref.py +133 -0
- data/lib/bson/decimal128.py +314 -0
- data/lib/bson/errors.py +35 -0
- data/lib/bson/int64.py +39 -0
- data/lib/bson/json_util.py +874 -0
- data/lib/bson/max_key.py +55 -0
- data/lib/bson/min_key.py +55 -0
- data/lib/bson/objectid.py +286 -0
- data/lib/bson/py.typed +2 -0
- data/lib/bson/raw_bson.py +175 -0
- data/lib/bson/regex.py +135 -0
- data/lib/bson/son.py +208 -0
- data/lib/bson/timestamp.py +124 -0
- data/lib/bson/tz_util.py +52 -0
- data/lib/gridfs/__init__.py +1015 -0
- data/lib/gridfs/__pycache__/__init__.cpython-310.pyc +0 -0
- data/lib/gridfs/__pycache__/errors.cpython-310.pyc +0 -0
- data/lib/gridfs/__pycache__/grid_file.cpython-310.pyc +0 -0
- data/lib/gridfs/errors.py +33 -0
- data/lib/gridfs/grid_file.py +907 -0
- data/lib/gridfs/py.typed +2 -0
- data/lib/pymongo/__init__.py +185 -0
- data/lib/pymongo/__pycache__/__init__.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/_csot.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/aggregation.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/auth.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/auth_aws.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/bulk.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/change_stream.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/client_options.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/client_session.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/collation.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/collection.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/command_cursor.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/common.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/compression_support.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/cursor.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/daemon.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/database.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/driver_info.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/encryption.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/encryption_options.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/errors.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/event_loggers.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/hello.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/helpers.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/max_staleness_selectors.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/message.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/mongo_client.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/monitor.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/monitoring.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/network.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/ocsp_cache.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/ocsp_support.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/operations.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/periodic_executor.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/pool.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/pyopenssl_context.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/read_concern.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/read_preferences.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/response.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/results.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/saslprep.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/server.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/server_api.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/server_description.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/server_selectors.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/server_type.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/settings.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/socket_checker.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/srv_resolver.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/ssl_context.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/ssl_support.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/topology.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/topology_description.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/typings.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/uri_parser.cpython-310.pyc +0 -0
- data/lib/pymongo/__pycache__/write_concern.cpython-310.pyc +0 -0
- data/lib/pymongo/_cmessage.cpython-310-x86_64-linux-gnu.so +0 -0
- data/lib/pymongo/_csot.py +118 -0
- data/lib/pymongo/aggregation.py +229 -0
- data/lib/pymongo/auth.py +549 -0
- data/lib/pymongo/auth_aws.py +94 -0
- data/lib/pymongo/bulk.py +513 -0
- data/lib/pymongo/change_stream.py +457 -0
- data/lib/pymongo/client_options.py +302 -0
- data/lib/pymongo/client_session.py +1112 -0
- data/lib/pymongo/collation.py +224 -0
- data/lib/pymongo/collection.py +3204 -0
- data/lib/pymongo/command_cursor.py +353 -0
- data/lib/pymongo/common.py +984 -0
- data/lib/pymongo/compression_support.py +149 -0
- data/lib/pymongo/cursor.py +1345 -0
- data/lib/pymongo/daemon.py +141 -0
- data/lib/pymongo/database.py +1202 -0
- data/lib/pymongo/driver_info.py +42 -0
- data/lib/pymongo/encryption.py +884 -0
- data/lib/pymongo/encryption_options.py +221 -0
- data/lib/pymongo/errors.py +365 -0
- data/lib/pymongo/event_loggers.py +221 -0
- data/lib/pymongo/hello.py +219 -0
- data/lib/pymongo/helpers.py +259 -0
- data/lib/pymongo/max_staleness_selectors.py +114 -0
- data/lib/pymongo/message.py +1440 -0
- data/lib/pymongo/mongo_client.py +2144 -0
- data/lib/pymongo/monitor.py +440 -0
- data/lib/pymongo/monitoring.py +1801 -0
- data/lib/pymongo/network.py +311 -0
- data/lib/pymongo/ocsp_cache.py +87 -0
- data/lib/pymongo/ocsp_support.py +372 -0
- data/lib/pymongo/operations.py +507 -0
- data/lib/pymongo/periodic_executor.py +183 -0
- data/lib/pymongo/pool.py +1660 -0
- data/lib/pymongo/py.typed +2 -0
- data/lib/pymongo/pyopenssl_context.py +383 -0
- data/lib/pymongo/read_concern.py +75 -0
- data/lib/pymongo/read_preferences.py +609 -0
- data/lib/pymongo/response.py +109 -0
- data/lib/pymongo/results.py +217 -0
- data/lib/pymongo/saslprep.py +113 -0
- data/lib/pymongo/server.py +247 -0
- data/lib/pymongo/server_api.py +170 -0
- data/lib/pymongo/server_description.py +285 -0
- data/lib/pymongo/server_selectors.py +153 -0
- data/lib/pymongo/server_type.py +32 -0
- data/lib/pymongo/settings.py +159 -0
- data/lib/pymongo/socket_checker.py +104 -0
- data/lib/pymongo/srv_resolver.py +126 -0
- data/lib/pymongo/ssl_context.py +39 -0
- data/lib/pymongo/ssl_support.py +99 -0
- data/lib/pymongo/topology.py +890 -0
- data/lib/pymongo/topology_description.py +639 -0
- data/lib/pymongo/typings.py +39 -0
- data/lib/pymongo/uri_parser.py +624 -0
- data/lib/pymongo/write_concern.py +129 -0
- data/lib/pymongo-4.2.0.dist-info/INSTALLER +1 -0
- data/lib/pymongo-4.2.0.dist-info/LICENSE +201 -0
- data/lib/pymongo-4.2.0.dist-info/METADATA +250 -0
- data/lib/pymongo-4.2.0.dist-info/RECORD +167 -0
- data/lib/pymongo-4.2.0.dist-info/REQUESTED +0 -0
- data/lib/pymongo-4.2.0.dist-info/WHEEL +6 -0
- data/lib/pymongo-4.2.0.dist-info/top_level.txt +3 -0
- data/lib/sensu-plugins-mongodb/metrics.rb +391 -0
- data/lib/sensu-plugins-mongodb/version.rb +9 -0
- data/lib/sensu-plugins-mongodb.rb +1 -0
- metadata +407 -0
@@ -0,0 +1,1347 @@
|
|
1
|
+
# Copyright 2009-present MongoDB, Inc.
|
2
|
+
#
|
3
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
4
|
+
# you may not use this file except in compliance with the License.
|
5
|
+
# You may obtain a copy of the License at
|
6
|
+
#
|
7
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
8
|
+
#
|
9
|
+
# Unless required by applicable law or agreed to in writing, software
|
10
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
11
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
12
|
+
# See the License for the specific language governing permissions and
|
13
|
+
# limitations under the License.
|
14
|
+
|
15
|
+
"""BSON (Binary JSON) encoding and decoding.
|
16
|
+
|
17
|
+
The mapping from Python types to BSON types is as follows:
|
18
|
+
|
19
|
+
======================================= ============= ===================
|
20
|
+
Python Type BSON Type Supported Direction
|
21
|
+
======================================= ============= ===================
|
22
|
+
None null both
|
23
|
+
bool boolean both
|
24
|
+
int [#int]_ int32 / int64 py -> bson
|
25
|
+
`bson.int64.Int64` int64 both
|
26
|
+
float number (real) both
|
27
|
+
str string both
|
28
|
+
list array both
|
29
|
+
dict / `SON` object both
|
30
|
+
datetime.datetime [#dt]_ [#dt2]_ date both
|
31
|
+
`bson.regex.Regex` regex both
|
32
|
+
compiled re [#re]_ regex py -> bson
|
33
|
+
`bson.binary.Binary` binary both
|
34
|
+
`bson.objectid.ObjectId` oid both
|
35
|
+
`bson.dbref.DBRef` dbref both
|
36
|
+
None undefined bson -> py
|
37
|
+
`bson.code.Code` code both
|
38
|
+
str symbol bson -> py
|
39
|
+
bytes [#bytes]_ binary both
|
40
|
+
======================================= ============= ===================
|
41
|
+
|
42
|
+
.. [#int] A Python int will be saved as a BSON int32 or BSON int64 depending
|
43
|
+
on its size. A BSON int32 will always decode to a Python int. A BSON
|
44
|
+
int64 will always decode to a :class:`~bson.int64.Int64`.
|
45
|
+
.. [#dt] datetime.datetime instances will be rounded to the nearest
|
46
|
+
millisecond when saved
|
47
|
+
.. [#dt2] all datetime.datetime instances are treated as *naive*. clients
|
48
|
+
should always use UTC.
|
49
|
+
.. [#re] :class:`~bson.regex.Regex` instances and regular expression
|
50
|
+
objects from ``re.compile()`` are both saved as BSON regular expressions.
|
51
|
+
BSON regular expressions are decoded as :class:`~bson.regex.Regex`
|
52
|
+
instances.
|
53
|
+
.. [#bytes] The bytes type is encoded as BSON binary with
|
54
|
+
subtype 0. It will be decoded back to bytes.
|
55
|
+
"""
|
56
|
+
|
57
|
+
import calendar
|
58
|
+
import datetime
|
59
|
+
import itertools
|
60
|
+
import re
|
61
|
+
import struct
|
62
|
+
import sys
|
63
|
+
import uuid
|
64
|
+
from codecs import utf_8_decode as _utf_8_decode # type: ignore[attr-defined]
|
65
|
+
from codecs import utf_8_encode as _utf_8_encode # type: ignore[attr-defined]
|
66
|
+
from collections import abc as _abc
|
67
|
+
from typing import (
|
68
|
+
IO,
|
69
|
+
TYPE_CHECKING,
|
70
|
+
Any,
|
71
|
+
BinaryIO,
|
72
|
+
Callable,
|
73
|
+
Dict,
|
74
|
+
Generator,
|
75
|
+
Iterator,
|
76
|
+
List,
|
77
|
+
Mapping,
|
78
|
+
MutableMapping,
|
79
|
+
NoReturn,
|
80
|
+
Optional,
|
81
|
+
Sequence,
|
82
|
+
Tuple,
|
83
|
+
Type,
|
84
|
+
TypeVar,
|
85
|
+
Union,
|
86
|
+
cast,
|
87
|
+
)
|
88
|
+
|
89
|
+
from bson.binary import (
|
90
|
+
ALL_UUID_SUBTYPES,
|
91
|
+
CSHARP_LEGACY,
|
92
|
+
JAVA_LEGACY,
|
93
|
+
OLD_UUID_SUBTYPE,
|
94
|
+
STANDARD,
|
95
|
+
UUID_SUBTYPE,
|
96
|
+
Binary,
|
97
|
+
UuidRepresentation,
|
98
|
+
)
|
99
|
+
from bson.code import Code
|
100
|
+
from bson.codec_options import (
|
101
|
+
DEFAULT_CODEC_OPTIONS,
|
102
|
+
CodecOptions,
|
103
|
+
_DocumentType,
|
104
|
+
_raw_document_class,
|
105
|
+
)
|
106
|
+
from bson.dbref import DBRef
|
107
|
+
from bson.decimal128 import Decimal128
|
108
|
+
from bson.errors import InvalidBSON, InvalidDocument, InvalidStringData
|
109
|
+
from bson.int64 import Int64
|
110
|
+
from bson.max_key import MaxKey
|
111
|
+
from bson.min_key import MinKey
|
112
|
+
from bson.objectid import ObjectId
|
113
|
+
from bson.regex import Regex
|
114
|
+
from bson.son import RE_TYPE, SON
|
115
|
+
from bson.timestamp import Timestamp
|
116
|
+
from bson.tz_util import utc
|
117
|
+
|
118
|
+
# Import some modules for type-checking only.
|
119
|
+
if TYPE_CHECKING:
|
120
|
+
from array import array
|
121
|
+
from mmap import mmap
|
122
|
+
|
123
|
+
|
124
|
+
try:
|
125
|
+
from bson import _cbson # type: ignore[attr-defined]
|
126
|
+
|
127
|
+
_USE_C = True
|
128
|
+
except ImportError:
|
129
|
+
_USE_C = False
|
130
|
+
|
131
|
+
__all__ = [
|
132
|
+
"ALL_UUID_SUBTYPES",
|
133
|
+
"CSHARP_LEGACY",
|
134
|
+
"JAVA_LEGACY",
|
135
|
+
"OLD_UUID_SUBTYPE",
|
136
|
+
"STANDARD",
|
137
|
+
"UUID_SUBTYPE",
|
138
|
+
"Binary",
|
139
|
+
"UuidRepresentation",
|
140
|
+
"Code",
|
141
|
+
"DEFAULT_CODEC_OPTIONS",
|
142
|
+
"CodecOptions",
|
143
|
+
"DBRef",
|
144
|
+
"Decimal128",
|
145
|
+
"InvalidBSON",
|
146
|
+
"InvalidDocument",
|
147
|
+
"InvalidStringData",
|
148
|
+
"Int64",
|
149
|
+
"MaxKey",
|
150
|
+
"MinKey",
|
151
|
+
"ObjectId",
|
152
|
+
"Regex",
|
153
|
+
"RE_TYPE",
|
154
|
+
"SON",
|
155
|
+
"Timestamp",
|
156
|
+
"utc",
|
157
|
+
"EPOCH_AWARE",
|
158
|
+
"EPOCH_NAIVE",
|
159
|
+
"BSONNUM",
|
160
|
+
"BSONSTR",
|
161
|
+
"BSONOBJ",
|
162
|
+
"BSONARR",
|
163
|
+
"BSONBIN",
|
164
|
+
"BSONUND",
|
165
|
+
"BSONOID",
|
166
|
+
"BSONBOO",
|
167
|
+
"BSONDAT",
|
168
|
+
"BSONNUL",
|
169
|
+
"BSONRGX",
|
170
|
+
"BSONREF",
|
171
|
+
"BSONCOD",
|
172
|
+
"BSONSYM",
|
173
|
+
"BSONCWS",
|
174
|
+
"BSONINT",
|
175
|
+
"BSONTIM",
|
176
|
+
"BSONLON",
|
177
|
+
"BSONDEC",
|
178
|
+
"BSONMIN",
|
179
|
+
"BSONMAX",
|
180
|
+
"get_data_and_view",
|
181
|
+
"gen_list_name",
|
182
|
+
"encode",
|
183
|
+
"decode",
|
184
|
+
"decode_all",
|
185
|
+
"decode_iter",
|
186
|
+
"decode_file_iter",
|
187
|
+
"is_valid",
|
188
|
+
"BSON",
|
189
|
+
"has_c",
|
190
|
+
]
|
191
|
+
|
192
|
+
EPOCH_AWARE = datetime.datetime.fromtimestamp(0, utc)
|
193
|
+
EPOCH_NAIVE = datetime.datetime.utcfromtimestamp(0)
|
194
|
+
|
195
|
+
|
196
|
+
BSONNUM = b"\x01" # Floating point
|
197
|
+
BSONSTR = b"\x02" # UTF-8 string
|
198
|
+
BSONOBJ = b"\x03" # Embedded document
|
199
|
+
BSONARR = b"\x04" # Array
|
200
|
+
BSONBIN = b"\x05" # Binary
|
201
|
+
BSONUND = b"\x06" # Undefined
|
202
|
+
BSONOID = b"\x07" # ObjectId
|
203
|
+
BSONBOO = b"\x08" # Boolean
|
204
|
+
BSONDAT = b"\x09" # UTC Datetime
|
205
|
+
BSONNUL = b"\x0A" # Null
|
206
|
+
BSONRGX = b"\x0B" # Regex
|
207
|
+
BSONREF = b"\x0C" # DBRef
|
208
|
+
BSONCOD = b"\x0D" # Javascript code
|
209
|
+
BSONSYM = b"\x0E" # Symbol
|
210
|
+
BSONCWS = b"\x0F" # Javascript code with scope
|
211
|
+
BSONINT = b"\x10" # 32bit int
|
212
|
+
BSONTIM = b"\x11" # Timestamp
|
213
|
+
BSONLON = b"\x12" # 64bit int
|
214
|
+
BSONDEC = b"\x13" # Decimal128
|
215
|
+
BSONMIN = b"\xFF" # Min key
|
216
|
+
BSONMAX = b"\x7F" # Max key
|
217
|
+
|
218
|
+
|
219
|
+
_UNPACK_FLOAT_FROM = struct.Struct("<d").unpack_from
|
220
|
+
_UNPACK_INT = struct.Struct("<i").unpack
|
221
|
+
_UNPACK_INT_FROM = struct.Struct("<i").unpack_from
|
222
|
+
_UNPACK_LENGTH_SUBTYPE_FROM = struct.Struct("<iB").unpack_from
|
223
|
+
_UNPACK_LONG_FROM = struct.Struct("<q").unpack_from
|
224
|
+
_UNPACK_TIMESTAMP_FROM = struct.Struct("<II").unpack_from
|
225
|
+
|
226
|
+
|
227
|
+
def get_data_and_view(data: Any) -> Tuple[Any, memoryview]:
|
228
|
+
if isinstance(data, (bytes, bytearray)):
|
229
|
+
return data, memoryview(data)
|
230
|
+
view = memoryview(data)
|
231
|
+
return view.tobytes(), view
|
232
|
+
|
233
|
+
|
234
|
+
def _raise_unknown_type(element_type: int, element_name: str) -> NoReturn:
|
235
|
+
"""Unknown type helper."""
|
236
|
+
raise InvalidBSON(
|
237
|
+
"Detected unknown BSON type %r for fieldname '%s'. Are "
|
238
|
+
"you using the latest driver version?" % (chr(element_type).encode(), element_name)
|
239
|
+
)
|
240
|
+
|
241
|
+
|
242
|
+
def _get_int(
|
243
|
+
data: Any, view: Any, position: int, dummy0: Any, dummy1: Any, dummy2: Any
|
244
|
+
) -> Tuple[int, int]:
|
245
|
+
"""Decode a BSON int32 to python int."""
|
246
|
+
return _UNPACK_INT_FROM(data, position)[0], position + 4
|
247
|
+
|
248
|
+
|
249
|
+
def _get_c_string(data: Any, view: Any, position: int, opts: CodecOptions) -> Tuple[str, int]:
|
250
|
+
"""Decode a BSON 'C' string to python str."""
|
251
|
+
end = data.index(b"\x00", position)
|
252
|
+
return _utf_8_decode(view[position:end], opts.unicode_decode_error_handler, True)[0], end + 1
|
253
|
+
|
254
|
+
|
255
|
+
def _get_float(
|
256
|
+
data: Any, view: Any, position: int, dummy0: Any, dummy1: Any, dummy2: Any
|
257
|
+
) -> Tuple[float, int]:
|
258
|
+
"""Decode a BSON double to python float."""
|
259
|
+
return _UNPACK_FLOAT_FROM(data, position)[0], position + 8
|
260
|
+
|
261
|
+
|
262
|
+
def _get_string(
|
263
|
+
data: Any, view: Any, position: int, obj_end: int, opts: CodecOptions, dummy: Any
|
264
|
+
) -> Tuple[str, int]:
|
265
|
+
"""Decode a BSON string to python str."""
|
266
|
+
length = _UNPACK_INT_FROM(data, position)[0]
|
267
|
+
position += 4
|
268
|
+
if length < 1 or obj_end - position < length:
|
269
|
+
raise InvalidBSON("invalid string length")
|
270
|
+
end = position + length - 1
|
271
|
+
if data[end] != 0:
|
272
|
+
raise InvalidBSON("invalid end of string")
|
273
|
+
return _utf_8_decode(view[position:end], opts.unicode_decode_error_handler, True)[0], end + 1
|
274
|
+
|
275
|
+
|
276
|
+
def _get_object_size(data: Any, position: int, obj_end: int) -> Tuple[int, int]:
|
277
|
+
"""Validate and return a BSON document's size."""
|
278
|
+
try:
|
279
|
+
obj_size = _UNPACK_INT_FROM(data, position)[0]
|
280
|
+
except struct.error as exc:
|
281
|
+
raise InvalidBSON(str(exc))
|
282
|
+
end = position + obj_size - 1
|
283
|
+
if data[end] != 0:
|
284
|
+
raise InvalidBSON("bad eoo")
|
285
|
+
if end >= obj_end:
|
286
|
+
raise InvalidBSON("invalid object length")
|
287
|
+
# If this is the top-level document, validate the total size too.
|
288
|
+
if position == 0 and obj_size != obj_end:
|
289
|
+
raise InvalidBSON("invalid object length")
|
290
|
+
return obj_size, end
|
291
|
+
|
292
|
+
|
293
|
+
def _get_object(
|
294
|
+
data: Any, view: Any, position: int, obj_end: int, opts: CodecOptions, dummy: Any
|
295
|
+
) -> Tuple[Any, int]:
|
296
|
+
"""Decode a BSON subdocument to opts.document_class or bson.dbref.DBRef."""
|
297
|
+
obj_size, end = _get_object_size(data, position, obj_end)
|
298
|
+
if _raw_document_class(opts.document_class):
|
299
|
+
return (opts.document_class(data[position : end + 1], opts), position + obj_size)
|
300
|
+
|
301
|
+
obj = _elements_to_dict(data, view, position + 4, end, opts)
|
302
|
+
|
303
|
+
position += obj_size
|
304
|
+
# If DBRef validation fails, return a normal doc.
|
305
|
+
if (
|
306
|
+
isinstance(obj.get("$ref"), str)
|
307
|
+
and "$id" in obj
|
308
|
+
and isinstance(obj.get("$db"), (str, type(None)))
|
309
|
+
):
|
310
|
+
return (DBRef(obj.pop("$ref"), obj.pop("$id", None), obj.pop("$db", None), obj), position)
|
311
|
+
return obj, position
|
312
|
+
|
313
|
+
|
314
|
+
def _get_array(
|
315
|
+
data: Any, view: Any, position: int, obj_end: int, opts: CodecOptions, element_name: str
|
316
|
+
) -> Tuple[Any, int]:
|
317
|
+
"""Decode a BSON array to python list."""
|
318
|
+
size = _UNPACK_INT_FROM(data, position)[0]
|
319
|
+
end = position + size - 1
|
320
|
+
if data[end] != 0:
|
321
|
+
raise InvalidBSON("bad eoo")
|
322
|
+
|
323
|
+
position += 4
|
324
|
+
end -= 1
|
325
|
+
result: List[Any] = []
|
326
|
+
|
327
|
+
# Avoid doing global and attribute lookups in the loop.
|
328
|
+
append = result.append
|
329
|
+
index = data.index
|
330
|
+
getter = _ELEMENT_GETTER
|
331
|
+
decoder_map = opts.type_registry._decoder_map
|
332
|
+
|
333
|
+
while position < end:
|
334
|
+
element_type = data[position]
|
335
|
+
# Just skip the keys.
|
336
|
+
position = index(b"\x00", position) + 1
|
337
|
+
try:
|
338
|
+
value, position = getter[element_type](
|
339
|
+
data, view, position, obj_end, opts, element_name
|
340
|
+
)
|
341
|
+
except KeyError:
|
342
|
+
_raise_unknown_type(element_type, element_name)
|
343
|
+
|
344
|
+
if decoder_map:
|
345
|
+
custom_decoder = decoder_map.get(type(value))
|
346
|
+
if custom_decoder is not None:
|
347
|
+
value = custom_decoder(value)
|
348
|
+
|
349
|
+
append(value)
|
350
|
+
|
351
|
+
if position != end + 1:
|
352
|
+
raise InvalidBSON("bad array length")
|
353
|
+
return result, position + 1
|
354
|
+
|
355
|
+
|
356
|
+
def _get_binary(
|
357
|
+
data: Any, view: Any, position: int, obj_end: int, opts: CodecOptions, dummy1: Any
|
358
|
+
) -> Tuple[Union[Binary, uuid.UUID], int]:
|
359
|
+
"""Decode a BSON binary to bson.binary.Binary or python UUID."""
|
360
|
+
length, subtype = _UNPACK_LENGTH_SUBTYPE_FROM(data, position)
|
361
|
+
position += 5
|
362
|
+
if subtype == 2:
|
363
|
+
length2 = _UNPACK_INT_FROM(data, position)[0]
|
364
|
+
position += 4
|
365
|
+
if length2 != length - 4:
|
366
|
+
raise InvalidBSON("invalid binary (st 2) - lengths don't match!")
|
367
|
+
length = length2
|
368
|
+
end = position + length
|
369
|
+
if length < 0 or end > obj_end:
|
370
|
+
raise InvalidBSON("bad binary object length")
|
371
|
+
|
372
|
+
# Convert UUID subtypes to native UUIDs.
|
373
|
+
if subtype in ALL_UUID_SUBTYPES:
|
374
|
+
uuid_rep = opts.uuid_representation
|
375
|
+
binary_value = Binary(data[position:end], subtype)
|
376
|
+
if (
|
377
|
+
(uuid_rep == UuidRepresentation.UNSPECIFIED)
|
378
|
+
or (subtype == UUID_SUBTYPE and uuid_rep != STANDARD)
|
379
|
+
or (subtype == OLD_UUID_SUBTYPE and uuid_rep == STANDARD)
|
380
|
+
):
|
381
|
+
return binary_value, end
|
382
|
+
return binary_value.as_uuid(uuid_rep), end
|
383
|
+
|
384
|
+
# Decode subtype 0 to 'bytes'.
|
385
|
+
if subtype == 0:
|
386
|
+
value = data[position:end]
|
387
|
+
else:
|
388
|
+
value = Binary(data[position:end], subtype)
|
389
|
+
|
390
|
+
return value, end
|
391
|
+
|
392
|
+
|
393
|
+
def _get_oid(
|
394
|
+
data: Any, view: Any, position: int, dummy0: Any, dummy1: Any, dummy2: Any
|
395
|
+
) -> Tuple[ObjectId, int]:
|
396
|
+
"""Decode a BSON ObjectId to bson.objectid.ObjectId."""
|
397
|
+
end = position + 12
|
398
|
+
return ObjectId(data[position:end]), end
|
399
|
+
|
400
|
+
|
401
|
+
def _get_boolean(
|
402
|
+
data: Any, view: Any, position: int, dummy0: Any, dummy1: Any, dummy2: Any
|
403
|
+
) -> Tuple[bool, int]:
|
404
|
+
"""Decode a BSON true/false to python True/False."""
|
405
|
+
end = position + 1
|
406
|
+
boolean_byte = data[position:end]
|
407
|
+
if boolean_byte == b"\x00":
|
408
|
+
return False, end
|
409
|
+
elif boolean_byte == b"\x01":
|
410
|
+
return True, end
|
411
|
+
raise InvalidBSON("invalid boolean value: %r" % boolean_byte)
|
412
|
+
|
413
|
+
|
414
|
+
def _get_date(
|
415
|
+
data: Any, view: Any, position: int, dummy0: int, opts: CodecOptions, dummy1: Any
|
416
|
+
) -> Tuple[datetime.datetime, int]:
|
417
|
+
"""Decode a BSON datetime to python datetime.datetime."""
|
418
|
+
return _millis_to_datetime(_UNPACK_LONG_FROM(data, position)[0], opts), position + 8
|
419
|
+
|
420
|
+
|
421
|
+
def _get_code(
|
422
|
+
data: Any, view: Any, position: int, obj_end: int, opts: CodecOptions, element_name: str
|
423
|
+
) -> Tuple[Code, int]:
|
424
|
+
"""Decode a BSON code to bson.code.Code."""
|
425
|
+
code, position = _get_string(data, view, position, obj_end, opts, element_name)
|
426
|
+
return Code(code), position
|
427
|
+
|
428
|
+
|
429
|
+
def _get_code_w_scope(
|
430
|
+
data: Any, view: Any, position: int, obj_end: int, opts: CodecOptions, element_name: str
|
431
|
+
) -> Tuple[Code, int]:
|
432
|
+
"""Decode a BSON code_w_scope to bson.code.Code."""
|
433
|
+
code_end = position + _UNPACK_INT_FROM(data, position)[0]
|
434
|
+
code, position = _get_string(data, view, position + 4, code_end, opts, element_name)
|
435
|
+
scope, position = _get_object(data, view, position, code_end, opts, element_name)
|
436
|
+
if position != code_end:
|
437
|
+
raise InvalidBSON("scope outside of javascript code boundaries")
|
438
|
+
return Code(code, scope), position
|
439
|
+
|
440
|
+
|
441
|
+
def _get_regex(
|
442
|
+
data: Any, view: Any, position: int, dummy0: Any, opts: CodecOptions, dummy1: Any
|
443
|
+
) -> Tuple[Regex, int]:
|
444
|
+
"""Decode a BSON regex to bson.regex.Regex or a python pattern object."""
|
445
|
+
pattern, position = _get_c_string(data, view, position, opts)
|
446
|
+
bson_flags, position = _get_c_string(data, view, position, opts)
|
447
|
+
bson_re = Regex(pattern, bson_flags)
|
448
|
+
return bson_re, position
|
449
|
+
|
450
|
+
|
451
|
+
def _get_ref(
|
452
|
+
data: Any, view: Any, position: int, obj_end: int, opts: CodecOptions, element_name: str
|
453
|
+
) -> Tuple[DBRef, int]:
|
454
|
+
"""Decode (deprecated) BSON DBPointer to bson.dbref.DBRef."""
|
455
|
+
collection, position = _get_string(data, view, position, obj_end, opts, element_name)
|
456
|
+
oid, position = _get_oid(data, view, position, obj_end, opts, element_name)
|
457
|
+
return DBRef(collection, oid), position
|
458
|
+
|
459
|
+
|
460
|
+
def _get_timestamp(
|
461
|
+
data: Any, view: Any, position: int, dummy0: Any, dummy1: Any, dummy2: Any
|
462
|
+
) -> Tuple[Timestamp, int]:
|
463
|
+
"""Decode a BSON timestamp to bson.timestamp.Timestamp."""
|
464
|
+
inc, timestamp = _UNPACK_TIMESTAMP_FROM(data, position)
|
465
|
+
return Timestamp(timestamp, inc), position + 8
|
466
|
+
|
467
|
+
|
468
|
+
def _get_int64(
|
469
|
+
data: Any, view: Any, position: int, dummy0: Any, dummy1: Any, dummy2: Any
|
470
|
+
) -> Tuple[Int64, int]:
|
471
|
+
"""Decode a BSON int64 to bson.int64.Int64."""
|
472
|
+
return Int64(_UNPACK_LONG_FROM(data, position)[0]), position + 8
|
473
|
+
|
474
|
+
|
475
|
+
def _get_decimal128(
|
476
|
+
data: Any, view: Any, position: int, dummy0: Any, dummy1: Any, dummy2: Any
|
477
|
+
) -> Tuple[Decimal128, int]:
|
478
|
+
"""Decode a BSON decimal128 to bson.decimal128.Decimal128."""
|
479
|
+
end = position + 16
|
480
|
+
return Decimal128.from_bid(data[position:end]), end
|
481
|
+
|
482
|
+
|
483
|
+
# Each decoder function's signature is:
|
484
|
+
# - data: bytes
|
485
|
+
# - view: memoryview that references `data`
|
486
|
+
# - position: int, beginning of object in 'data' to decode
|
487
|
+
# - obj_end: int, end of object to decode in 'data' if variable-length type
|
488
|
+
# - opts: a CodecOptions
|
489
|
+
_ELEMENT_GETTER: Dict[int, Callable[..., Tuple[Any, int]]] = {
|
490
|
+
ord(BSONNUM): _get_float,
|
491
|
+
ord(BSONSTR): _get_string,
|
492
|
+
ord(BSONOBJ): _get_object,
|
493
|
+
ord(BSONARR): _get_array,
|
494
|
+
ord(BSONBIN): _get_binary,
|
495
|
+
ord(BSONUND): lambda u, v, w, x, y, z: (None, w), # Deprecated undefined
|
496
|
+
ord(BSONOID): _get_oid,
|
497
|
+
ord(BSONBOO): _get_boolean,
|
498
|
+
ord(BSONDAT): _get_date,
|
499
|
+
ord(BSONNUL): lambda u, v, w, x, y, z: (None, w),
|
500
|
+
ord(BSONRGX): _get_regex,
|
501
|
+
ord(BSONREF): _get_ref, # Deprecated DBPointer
|
502
|
+
ord(BSONCOD): _get_code,
|
503
|
+
ord(BSONSYM): _get_string, # Deprecated symbol
|
504
|
+
ord(BSONCWS): _get_code_w_scope,
|
505
|
+
ord(BSONINT): _get_int,
|
506
|
+
ord(BSONTIM): _get_timestamp,
|
507
|
+
ord(BSONLON): _get_int64,
|
508
|
+
ord(BSONDEC): _get_decimal128,
|
509
|
+
ord(BSONMIN): lambda u, v, w, x, y, z: (MinKey(), w),
|
510
|
+
ord(BSONMAX): lambda u, v, w, x, y, z: (MaxKey(), w),
|
511
|
+
}
|
512
|
+
|
513
|
+
|
514
|
+
if _USE_C:
|
515
|
+
|
516
|
+
def _element_to_dict(
|
517
|
+
data: Any, view: Any, position: int, obj_end: int, opts: CodecOptions
|
518
|
+
) -> Any:
|
519
|
+
return _cbson._element_to_dict(data, position, obj_end, opts)
|
520
|
+
|
521
|
+
else:
|
522
|
+
|
523
|
+
def _element_to_dict(
|
524
|
+
data: Any, view: Any, position: int, obj_end: int, opts: CodecOptions
|
525
|
+
) -> Any:
|
526
|
+
"""Decode a single key, value pair."""
|
527
|
+
element_type = data[position]
|
528
|
+
position += 1
|
529
|
+
element_name, position = _get_c_string(data, view, position, opts)
|
530
|
+
try:
|
531
|
+
value, position = _ELEMENT_GETTER[element_type](
|
532
|
+
data, view, position, obj_end, opts, element_name
|
533
|
+
)
|
534
|
+
except KeyError:
|
535
|
+
_raise_unknown_type(element_type, element_name)
|
536
|
+
|
537
|
+
if opts.type_registry._decoder_map:
|
538
|
+
custom_decoder = opts.type_registry._decoder_map.get(type(value))
|
539
|
+
if custom_decoder is not None:
|
540
|
+
value = custom_decoder(value)
|
541
|
+
|
542
|
+
return element_name, value, position
|
543
|
+
|
544
|
+
|
545
|
+
_T = TypeVar("_T", bound=MutableMapping[Any, Any])
|
546
|
+
|
547
|
+
|
548
|
+
def _raw_to_dict(data: Any, position: int, obj_end: int, opts: CodecOptions, result: _T) -> _T:
|
549
|
+
data, view = get_data_and_view(data)
|
550
|
+
return _elements_to_dict(data, view, position, obj_end, opts, result)
|
551
|
+
|
552
|
+
|
553
|
+
def _elements_to_dict(
|
554
|
+
data: Any, view: Any, position: int, obj_end: int, opts: CodecOptions, result: Any = None
|
555
|
+
) -> Any:
|
556
|
+
"""Decode a BSON document into result."""
|
557
|
+
if result is None:
|
558
|
+
result = opts.document_class()
|
559
|
+
end = obj_end - 1
|
560
|
+
while position < end:
|
561
|
+
key, value, position = _element_to_dict(data, view, position, obj_end, opts)
|
562
|
+
result[key] = value
|
563
|
+
if position != obj_end:
|
564
|
+
raise InvalidBSON("bad object or element length")
|
565
|
+
return result
|
566
|
+
|
567
|
+
|
568
|
+
def _bson_to_dict(data: Any, opts: CodecOptions) -> Any:
|
569
|
+
"""Decode a BSON string to document_class."""
|
570
|
+
data, view = get_data_and_view(data)
|
571
|
+
try:
|
572
|
+
if _raw_document_class(opts.document_class):
|
573
|
+
return opts.document_class(data, opts)
|
574
|
+
_, end = _get_object_size(data, 0, len(data))
|
575
|
+
return _elements_to_dict(data, view, 4, end, opts)
|
576
|
+
except InvalidBSON:
|
577
|
+
raise
|
578
|
+
except Exception:
|
579
|
+
# Change exception type to InvalidBSON but preserve traceback.
|
580
|
+
_, exc_value, exc_tb = sys.exc_info()
|
581
|
+
raise InvalidBSON(str(exc_value)).with_traceback(exc_tb)
|
582
|
+
|
583
|
+
|
584
|
+
if _USE_C:
|
585
|
+
_bson_to_dict = _cbson._bson_to_dict # noqa: F811
|
586
|
+
|
587
|
+
|
588
|
+
_PACK_FLOAT = struct.Struct("<d").pack
|
589
|
+
_PACK_INT = struct.Struct("<i").pack
|
590
|
+
_PACK_LENGTH_SUBTYPE = struct.Struct("<iB").pack
|
591
|
+
_PACK_LONG = struct.Struct("<q").pack
|
592
|
+
_PACK_TIMESTAMP = struct.Struct("<II").pack
|
593
|
+
_LIST_NAMES = tuple((str(i) + "\x00").encode("utf8") for i in range(1000))
|
594
|
+
|
595
|
+
|
596
|
+
def gen_list_name() -> Generator[bytes, None, None]:
|
597
|
+
"""Generate "keys" for encoded lists in the sequence
|
598
|
+
b"0\x00", b"1\x00", b"2\x00", ...
|
599
|
+
|
600
|
+
The first 1000 keys are returned from a pre-built cache. All
|
601
|
+
subsequent keys are generated on the fly.
|
602
|
+
"""
|
603
|
+
for name in _LIST_NAMES:
|
604
|
+
yield name
|
605
|
+
|
606
|
+
counter = itertools.count(1000)
|
607
|
+
while True:
|
608
|
+
yield (str(next(counter)) + "\x00").encode("utf8")
|
609
|
+
|
610
|
+
|
611
|
+
def _make_c_string_check(string: Union[str, bytes]) -> bytes:
|
612
|
+
"""Make a 'C' string, checking for embedded NUL characters."""
|
613
|
+
if isinstance(string, bytes):
|
614
|
+
if b"\x00" in string:
|
615
|
+
raise InvalidDocument("BSON keys / regex patterns must not contain a NUL character")
|
616
|
+
try:
|
617
|
+
_utf_8_decode(string, None, True)
|
618
|
+
return string + b"\x00"
|
619
|
+
except UnicodeError:
|
620
|
+
raise InvalidStringData("strings in documents must be valid UTF-8: %r" % string)
|
621
|
+
else:
|
622
|
+
if "\x00" in string:
|
623
|
+
raise InvalidDocument("BSON keys / regex patterns must not contain a NUL character")
|
624
|
+
return cast(bytes, _utf_8_encode(string)[0]) + b"\x00"
|
625
|
+
|
626
|
+
|
627
|
+
def _make_c_string(string: Union[str, bytes]) -> bytes:
|
628
|
+
"""Make a 'C' string."""
|
629
|
+
if isinstance(string, bytes):
|
630
|
+
try:
|
631
|
+
_utf_8_decode(string, None, True)
|
632
|
+
return string + b"\x00"
|
633
|
+
except UnicodeError:
|
634
|
+
raise InvalidStringData("strings in documents must be valid UTF-8: %r" % string)
|
635
|
+
else:
|
636
|
+
return cast(bytes, _utf_8_encode(string)[0]) + b"\x00"
|
637
|
+
|
638
|
+
|
639
|
+
def _make_name(string: str) -> bytes:
|
640
|
+
"""Make a 'C' string suitable for a BSON key."""
|
641
|
+
# Keys can only be text in python 3.
|
642
|
+
if "\x00" in string:
|
643
|
+
raise InvalidDocument("BSON keys / regex patterns must not contain a NUL character")
|
644
|
+
return cast(bytes, _utf_8_encode(string)[0]) + b"\x00"
|
645
|
+
|
646
|
+
|
647
|
+
def _encode_float(name: bytes, value: float, dummy0: Any, dummy1: Any) -> bytes:
|
648
|
+
"""Encode a float."""
|
649
|
+
return b"\x01" + name + _PACK_FLOAT(value)
|
650
|
+
|
651
|
+
|
652
|
+
def _encode_bytes(name: bytes, value: bytes, dummy0: Any, dummy1: Any) -> bytes:
|
653
|
+
"""Encode a python bytes."""
|
654
|
+
# Python3 special case. Store 'bytes' as BSON binary subtype 0.
|
655
|
+
return b"\x05" + name + _PACK_INT(len(value)) + b"\x00" + value
|
656
|
+
|
657
|
+
|
658
|
+
def _encode_mapping(name: bytes, value: Any, check_keys: bool, opts: CodecOptions) -> bytes:
|
659
|
+
"""Encode a mapping type."""
|
660
|
+
if _raw_document_class(value):
|
661
|
+
return b"\x03" + name + value.raw
|
662
|
+
data = b"".join([_element_to_bson(key, val, check_keys, opts) for key, val in value.items()])
|
663
|
+
return b"\x03" + name + _PACK_INT(len(data) + 5) + data + b"\x00"
|
664
|
+
|
665
|
+
|
666
|
+
def _encode_dbref(name: bytes, value: DBRef, check_keys: bool, opts: CodecOptions) -> bytes:
|
667
|
+
"""Encode bson.dbref.DBRef."""
|
668
|
+
buf = bytearray(b"\x03" + name + b"\x00\x00\x00\x00")
|
669
|
+
begin = len(buf) - 4
|
670
|
+
|
671
|
+
buf += _name_value_to_bson(b"$ref\x00", value.collection, check_keys, opts)
|
672
|
+
buf += _name_value_to_bson(b"$id\x00", value.id, check_keys, opts)
|
673
|
+
if value.database is not None:
|
674
|
+
buf += _name_value_to_bson(b"$db\x00", value.database, check_keys, opts)
|
675
|
+
for key, val in value._DBRef__kwargs.items():
|
676
|
+
buf += _element_to_bson(key, val, check_keys, opts)
|
677
|
+
|
678
|
+
buf += b"\x00"
|
679
|
+
buf[begin : begin + 4] = _PACK_INT(len(buf) - begin)
|
680
|
+
return bytes(buf)
|
681
|
+
|
682
|
+
|
683
|
+
def _encode_list(name: bytes, value: Sequence[Any], check_keys: bool, opts: CodecOptions) -> bytes:
|
684
|
+
"""Encode a list/tuple."""
|
685
|
+
lname = gen_list_name()
|
686
|
+
data = b"".join([_name_value_to_bson(next(lname), item, check_keys, opts) for item in value])
|
687
|
+
return b"\x04" + name + _PACK_INT(len(data) + 5) + data + b"\x00"
|
688
|
+
|
689
|
+
|
690
|
+
def _encode_text(name: bytes, value: str, dummy0: Any, dummy1: Any) -> bytes:
|
691
|
+
"""Encode a python str."""
|
692
|
+
bvalue = _utf_8_encode(value)[0]
|
693
|
+
return b"\x02" + name + _PACK_INT(len(bvalue) + 1) + bvalue + b"\x00"
|
694
|
+
|
695
|
+
|
696
|
+
def _encode_binary(name: bytes, value: Binary, dummy0: Any, dummy1: Any) -> bytes:
|
697
|
+
"""Encode bson.binary.Binary."""
|
698
|
+
subtype = value.subtype
|
699
|
+
if subtype == 2:
|
700
|
+
value = _PACK_INT(len(value)) + value # type: ignore
|
701
|
+
return b"\x05" + name + _PACK_LENGTH_SUBTYPE(len(value), subtype) + value
|
702
|
+
|
703
|
+
|
704
|
+
def _encode_uuid(name: bytes, value: uuid.UUID, dummy: Any, opts: CodecOptions) -> bytes:
|
705
|
+
"""Encode uuid.UUID."""
|
706
|
+
uuid_representation = opts.uuid_representation
|
707
|
+
binval = Binary.from_uuid(value, uuid_representation=uuid_representation)
|
708
|
+
return _encode_binary(name, binval, dummy, opts)
|
709
|
+
|
710
|
+
|
711
|
+
def _encode_objectid(name: bytes, value: ObjectId, dummy: Any, dummy1: Any) -> bytes:
|
712
|
+
"""Encode bson.objectid.ObjectId."""
|
713
|
+
return b"\x07" + name + value.binary
|
714
|
+
|
715
|
+
|
716
|
+
def _encode_bool(name: bytes, value: bool, dummy0: Any, dummy1: Any) -> bytes:
|
717
|
+
"""Encode a python boolean (True/False)."""
|
718
|
+
return b"\x08" + name + (value and b"\x01" or b"\x00")
|
719
|
+
|
720
|
+
|
721
|
+
def _encode_datetime(name: bytes, value: datetime.datetime, dummy0: Any, dummy1: Any) -> bytes:
|
722
|
+
"""Encode datetime.datetime."""
|
723
|
+
millis = _datetime_to_millis(value)
|
724
|
+
return b"\x09" + name + _PACK_LONG(millis)
|
725
|
+
|
726
|
+
|
727
|
+
def _encode_none(name: bytes, dummy0: Any, dummy1: Any, dummy2: Any) -> bytes:
|
728
|
+
"""Encode python None."""
|
729
|
+
return b"\x0A" + name
|
730
|
+
|
731
|
+
|
732
|
+
def _encode_regex(name: bytes, value: Regex, dummy0: Any, dummy1: Any) -> bytes:
|
733
|
+
"""Encode a python regex or bson.regex.Regex."""
|
734
|
+
flags = value.flags
|
735
|
+
# Python 3 common case
|
736
|
+
if flags == re.UNICODE:
|
737
|
+
return b"\x0B" + name + _make_c_string_check(value.pattern) + b"u\x00"
|
738
|
+
elif flags == 0:
|
739
|
+
return b"\x0B" + name + _make_c_string_check(value.pattern) + b"\x00"
|
740
|
+
else:
|
741
|
+
sflags = b""
|
742
|
+
if flags & re.IGNORECASE:
|
743
|
+
sflags += b"i"
|
744
|
+
if flags & re.LOCALE:
|
745
|
+
sflags += b"l"
|
746
|
+
if flags & re.MULTILINE:
|
747
|
+
sflags += b"m"
|
748
|
+
if flags & re.DOTALL:
|
749
|
+
sflags += b"s"
|
750
|
+
if flags & re.UNICODE:
|
751
|
+
sflags += b"u"
|
752
|
+
if flags & re.VERBOSE:
|
753
|
+
sflags += b"x"
|
754
|
+
sflags += b"\x00"
|
755
|
+
return b"\x0B" + name + _make_c_string_check(value.pattern) + sflags
|
756
|
+
|
757
|
+
|
758
|
+
def _encode_code(name: bytes, value: Code, dummy: Any, opts: CodecOptions) -> bytes:
|
759
|
+
"""Encode bson.code.Code."""
|
760
|
+
cstring = _make_c_string(value)
|
761
|
+
cstrlen = len(cstring)
|
762
|
+
if value.scope is None:
|
763
|
+
return b"\x0D" + name + _PACK_INT(cstrlen) + cstring
|
764
|
+
scope = _dict_to_bson(value.scope, False, opts, False)
|
765
|
+
full_length = _PACK_INT(8 + cstrlen + len(scope))
|
766
|
+
return b"\x0F" + name + full_length + _PACK_INT(cstrlen) + cstring + scope
|
767
|
+
|
768
|
+
|
769
|
+
def _encode_int(name: bytes, value: int, dummy0: Any, dummy1: Any) -> bytes:
|
770
|
+
"""Encode a python int."""
|
771
|
+
if -2147483648 <= value <= 2147483647:
|
772
|
+
return b"\x10" + name + _PACK_INT(value)
|
773
|
+
else:
|
774
|
+
try:
|
775
|
+
return b"\x12" + name + _PACK_LONG(value)
|
776
|
+
except struct.error:
|
777
|
+
raise OverflowError("BSON can only handle up to 8-byte ints")
|
778
|
+
|
779
|
+
|
780
|
+
def _encode_timestamp(name: bytes, value: Any, dummy0: Any, dummy1: Any) -> bytes:
|
781
|
+
"""Encode bson.timestamp.Timestamp."""
|
782
|
+
return b"\x11" + name + _PACK_TIMESTAMP(value.inc, value.time)
|
783
|
+
|
784
|
+
|
785
|
+
def _encode_long(name: bytes, value: Any, dummy0: Any, dummy1: Any) -> bytes:
|
786
|
+
"""Encode a python long (python 2.x)"""
|
787
|
+
try:
|
788
|
+
return b"\x12" + name + _PACK_LONG(value)
|
789
|
+
except struct.error:
|
790
|
+
raise OverflowError("BSON can only handle up to 8-byte ints")
|
791
|
+
|
792
|
+
|
793
|
+
def _encode_decimal128(name: bytes, value: Decimal128, dummy0: Any, dummy1: Any) -> bytes:
|
794
|
+
"""Encode bson.decimal128.Decimal128."""
|
795
|
+
return b"\x13" + name + value.bid
|
796
|
+
|
797
|
+
|
798
|
+
def _encode_minkey(name: bytes, dummy0: Any, dummy1: Any, dummy2: Any) -> bytes:
|
799
|
+
"""Encode bson.min_key.MinKey."""
|
800
|
+
return b"\xFF" + name
|
801
|
+
|
802
|
+
|
803
|
+
def _encode_maxkey(name: bytes, dummy0: Any, dummy1: Any, dummy2: Any) -> bytes:
|
804
|
+
"""Encode bson.max_key.MaxKey."""
|
805
|
+
return b"\x7F" + name
|
806
|
+
|
807
|
+
|
808
|
+
# Each encoder function's signature is:
|
809
|
+
# - name: utf-8 bytes
|
810
|
+
# - value: a Python data type, e.g. a Python int for _encode_int
|
811
|
+
# - check_keys: bool, whether to check for invalid names
|
812
|
+
# - opts: a CodecOptions
|
813
|
+
_ENCODERS = {
|
814
|
+
bool: _encode_bool,
|
815
|
+
bytes: _encode_bytes,
|
816
|
+
datetime.datetime: _encode_datetime,
|
817
|
+
dict: _encode_mapping,
|
818
|
+
float: _encode_float,
|
819
|
+
int: _encode_int,
|
820
|
+
list: _encode_list,
|
821
|
+
str: _encode_text,
|
822
|
+
tuple: _encode_list,
|
823
|
+
type(None): _encode_none,
|
824
|
+
uuid.UUID: _encode_uuid,
|
825
|
+
Binary: _encode_binary,
|
826
|
+
Int64: _encode_long,
|
827
|
+
Code: _encode_code,
|
828
|
+
DBRef: _encode_dbref,
|
829
|
+
MaxKey: _encode_maxkey,
|
830
|
+
MinKey: _encode_minkey,
|
831
|
+
ObjectId: _encode_objectid,
|
832
|
+
Regex: _encode_regex,
|
833
|
+
RE_TYPE: _encode_regex,
|
834
|
+
SON: _encode_mapping,
|
835
|
+
Timestamp: _encode_timestamp,
|
836
|
+
Decimal128: _encode_decimal128,
|
837
|
+
# Special case. This will never be looked up directly.
|
838
|
+
_abc.Mapping: _encode_mapping,
|
839
|
+
}
|
840
|
+
|
841
|
+
|
842
|
+
_MARKERS = {
|
843
|
+
5: _encode_binary,
|
844
|
+
7: _encode_objectid,
|
845
|
+
11: _encode_regex,
|
846
|
+
13: _encode_code,
|
847
|
+
17: _encode_timestamp,
|
848
|
+
18: _encode_long,
|
849
|
+
100: _encode_dbref,
|
850
|
+
127: _encode_maxkey,
|
851
|
+
255: _encode_minkey,
|
852
|
+
}
|
853
|
+
|
854
|
+
|
855
|
+
_BUILT_IN_TYPES = tuple(t for t in _ENCODERS)
|
856
|
+
|
857
|
+
|
858
|
+
def _name_value_to_bson(
|
859
|
+
name: bytes,
|
860
|
+
value: Any,
|
861
|
+
check_keys: bool,
|
862
|
+
opts: CodecOptions,
|
863
|
+
in_custom_call: bool = False,
|
864
|
+
in_fallback_call: bool = False,
|
865
|
+
) -> bytes:
|
866
|
+
"""Encode a single name, value pair."""
|
867
|
+
# First see if the type is already cached. KeyError will only ever
|
868
|
+
# happen once per subtype.
|
869
|
+
try:
|
870
|
+
return _ENCODERS[type(value)](name, value, check_keys, opts) # type: ignore
|
871
|
+
except KeyError:
|
872
|
+
pass
|
873
|
+
|
874
|
+
# Second, fall back to trying _type_marker. This has to be done
|
875
|
+
# before the loop below since users could subclass one of our
|
876
|
+
# custom types that subclasses a python built-in (e.g. Binary)
|
877
|
+
marker = getattr(value, "_type_marker", None)
|
878
|
+
if isinstance(marker, int) and marker in _MARKERS:
|
879
|
+
func = _MARKERS[marker]
|
880
|
+
# Cache this type for faster subsequent lookup.
|
881
|
+
_ENCODERS[type(value)] = func
|
882
|
+
return func(name, value, check_keys, opts) # type: ignore
|
883
|
+
|
884
|
+
# Third, check if a type encoder is registered for this type.
|
885
|
+
# Note that subtypes of registered custom types are not auto-encoded.
|
886
|
+
if not in_custom_call and opts.type_registry._encoder_map:
|
887
|
+
custom_encoder = opts.type_registry._encoder_map.get(type(value))
|
888
|
+
if custom_encoder is not None:
|
889
|
+
return _name_value_to_bson(
|
890
|
+
name, custom_encoder(value), check_keys, opts, in_custom_call=True
|
891
|
+
)
|
892
|
+
|
893
|
+
# Fourth, test each base type. This will only happen once for
|
894
|
+
# a subtype of a supported base type. Unlike in the C-extensions, this
|
895
|
+
# is done after trying the custom type encoder because checking for each
|
896
|
+
# subtype is expensive.
|
897
|
+
for base in _BUILT_IN_TYPES:
|
898
|
+
if isinstance(value, base):
|
899
|
+
func = _ENCODERS[base]
|
900
|
+
# Cache this type for faster subsequent lookup.
|
901
|
+
_ENCODERS[type(value)] = func
|
902
|
+
return func(name, value, check_keys, opts) # type: ignore
|
903
|
+
|
904
|
+
# As a last resort, try using the fallback encoder, if the user has
|
905
|
+
# provided one.
|
906
|
+
fallback_encoder = opts.type_registry._fallback_encoder
|
907
|
+
if not in_fallback_call and fallback_encoder is not None:
|
908
|
+
return _name_value_to_bson(
|
909
|
+
name, fallback_encoder(value), check_keys, opts, in_fallback_call=True
|
910
|
+
)
|
911
|
+
|
912
|
+
raise InvalidDocument("cannot encode object: %r, of type: %r" % (value, type(value)))
|
913
|
+
|
914
|
+
|
915
|
+
def _element_to_bson(key: Any, value: Any, check_keys: bool, opts: CodecOptions) -> bytes:
|
916
|
+
"""Encode a single key, value pair."""
|
917
|
+
if not isinstance(key, str):
|
918
|
+
raise InvalidDocument("documents must have only string keys, key was %r" % (key,))
|
919
|
+
if check_keys:
|
920
|
+
if key.startswith("$"):
|
921
|
+
raise InvalidDocument("key %r must not start with '$'" % (key,))
|
922
|
+
if "." in key:
|
923
|
+
raise InvalidDocument("key %r must not contain '.'" % (key,))
|
924
|
+
|
925
|
+
name = _make_name(key)
|
926
|
+
return _name_value_to_bson(name, value, check_keys, opts)
|
927
|
+
|
928
|
+
|
929
|
+
def _dict_to_bson(doc: Any, check_keys: bool, opts: CodecOptions, top_level: bool = True) -> bytes:
|
930
|
+
"""Encode a document to BSON."""
|
931
|
+
if _raw_document_class(doc):
|
932
|
+
return cast(bytes, doc.raw)
|
933
|
+
try:
|
934
|
+
elements = []
|
935
|
+
if top_level and "_id" in doc:
|
936
|
+
elements.append(_name_value_to_bson(b"_id\x00", doc["_id"], check_keys, opts))
|
937
|
+
for key, value in doc.items():
|
938
|
+
if not top_level or key != "_id":
|
939
|
+
elements.append(_element_to_bson(key, value, check_keys, opts))
|
940
|
+
except AttributeError:
|
941
|
+
raise TypeError("encoder expected a mapping type but got: %r" % (doc,))
|
942
|
+
|
943
|
+
encoded = b"".join(elements)
|
944
|
+
return _PACK_INT(len(encoded) + 5) + encoded + b"\x00"
|
945
|
+
|
946
|
+
|
947
|
+
if _USE_C:
|
948
|
+
_dict_to_bson = _cbson._dict_to_bson # noqa: F811
|
949
|
+
|
950
|
+
|
951
|
+
def _millis_to_datetime(millis: int, opts: CodecOptions) -> datetime.datetime:
|
952
|
+
"""Convert milliseconds since epoch UTC to datetime."""
|
953
|
+
diff = ((millis % 1000) + 1000) % 1000
|
954
|
+
seconds = (millis - diff) // 1000
|
955
|
+
micros = diff * 1000
|
956
|
+
if opts.tz_aware:
|
957
|
+
dt = EPOCH_AWARE + datetime.timedelta(seconds=seconds, microseconds=micros)
|
958
|
+
if opts.tzinfo:
|
959
|
+
dt = dt.astimezone(opts.tzinfo)
|
960
|
+
return dt
|
961
|
+
else:
|
962
|
+
return EPOCH_NAIVE + datetime.timedelta(seconds=seconds, microseconds=micros)
|
963
|
+
|
964
|
+
|
965
|
+
def _datetime_to_millis(dtm: datetime.datetime) -> int:
|
966
|
+
"""Convert datetime to milliseconds since epoch UTC."""
|
967
|
+
if dtm.utcoffset() is not None:
|
968
|
+
dtm = dtm - dtm.utcoffset() # type: ignore
|
969
|
+
return int(calendar.timegm(dtm.timetuple()) * 1000 + dtm.microsecond // 1000)
|
970
|
+
|
971
|
+
|
972
|
+
_CODEC_OPTIONS_TYPE_ERROR = TypeError("codec_options must be an instance of CodecOptions")
|
973
|
+
|
974
|
+
|
975
|
+
_DocumentIn = Mapping[str, Any]
|
976
|
+
_ReadableBuffer = Union[bytes, memoryview, "mmap", "array"]
|
977
|
+
|
978
|
+
|
979
|
+
def encode(
|
980
|
+
document: _DocumentIn,
|
981
|
+
check_keys: bool = False,
|
982
|
+
codec_options: CodecOptions = DEFAULT_CODEC_OPTIONS,
|
983
|
+
) -> bytes:
|
984
|
+
"""Encode a document to BSON.
|
985
|
+
|
986
|
+
A document can be any mapping type (like :class:`dict`).
|
987
|
+
|
988
|
+
Raises :class:`TypeError` if `document` is not a mapping type,
|
989
|
+
or contains keys that are not instances of
|
990
|
+
:class:`basestring` (:class:`str` in python 3). Raises
|
991
|
+
:class:`~bson.errors.InvalidDocument` if `document` cannot be
|
992
|
+
converted to :class:`BSON`.
|
993
|
+
|
994
|
+
:Parameters:
|
995
|
+
- `document`: mapping type representing a document
|
996
|
+
- `check_keys` (optional): check if keys start with '$' or
|
997
|
+
contain '.', raising :class:`~bson.errors.InvalidDocument` in
|
998
|
+
either case
|
999
|
+
- `codec_options` (optional): An instance of
|
1000
|
+
:class:`~bson.codec_options.CodecOptions`.
|
1001
|
+
|
1002
|
+
.. versionadded:: 3.9
|
1003
|
+
"""
|
1004
|
+
if not isinstance(codec_options, CodecOptions):
|
1005
|
+
raise _CODEC_OPTIONS_TYPE_ERROR
|
1006
|
+
|
1007
|
+
return _dict_to_bson(document, check_keys, codec_options)
|
1008
|
+
|
1009
|
+
|
1010
|
+
def decode(
|
1011
|
+
data: _ReadableBuffer, codec_options: "Optional[CodecOptions[_DocumentType]]" = None
|
1012
|
+
) -> _DocumentType:
|
1013
|
+
"""Decode BSON to a document.
|
1014
|
+
|
1015
|
+
By default, returns a BSON document represented as a Python
|
1016
|
+
:class:`dict`. To use a different :class:`MutableMapping` class,
|
1017
|
+
configure a :class:`~bson.codec_options.CodecOptions`::
|
1018
|
+
|
1019
|
+
>>> import collections # From Python standard library.
|
1020
|
+
>>> import bson
|
1021
|
+
>>> from bson.codec_options import CodecOptions
|
1022
|
+
>>> data = bson.encode({'a': 1})
|
1023
|
+
>>> decoded_doc = bson.decode(data)
|
1024
|
+
<type 'dict'>
|
1025
|
+
>>> options = CodecOptions(document_class=collections.OrderedDict)
|
1026
|
+
>>> decoded_doc = bson.decode(data, codec_options=options)
|
1027
|
+
>>> type(decoded_doc)
|
1028
|
+
<class 'collections.OrderedDict'>
|
1029
|
+
|
1030
|
+
:Parameters:
|
1031
|
+
- `data`: the BSON to decode. Any bytes-like object that implements
|
1032
|
+
the buffer protocol.
|
1033
|
+
- `codec_options` (optional): An instance of
|
1034
|
+
:class:`~bson.codec_options.CodecOptions`.
|
1035
|
+
|
1036
|
+
.. versionadded:: 3.9
|
1037
|
+
"""
|
1038
|
+
opts: CodecOptions = codec_options or DEFAULT_CODEC_OPTIONS
|
1039
|
+
if not isinstance(opts, CodecOptions):
|
1040
|
+
raise _CODEC_OPTIONS_TYPE_ERROR
|
1041
|
+
|
1042
|
+
return _bson_to_dict(data, opts)
|
1043
|
+
|
1044
|
+
|
1045
|
+
def _decode_all(data: _ReadableBuffer, opts: "CodecOptions[_DocumentType]") -> List[_DocumentType]:
|
1046
|
+
"""Decode a BSON data to multiple documents."""
|
1047
|
+
data, view = get_data_and_view(data)
|
1048
|
+
data_len = len(data)
|
1049
|
+
docs: List[_DocumentType] = []
|
1050
|
+
position = 0
|
1051
|
+
end = data_len - 1
|
1052
|
+
use_raw = _raw_document_class(opts.document_class)
|
1053
|
+
try:
|
1054
|
+
while position < end:
|
1055
|
+
obj_size = _UNPACK_INT_FROM(data, position)[0]
|
1056
|
+
if data_len - position < obj_size:
|
1057
|
+
raise InvalidBSON("invalid object size")
|
1058
|
+
obj_end = position + obj_size - 1
|
1059
|
+
if data[obj_end] != 0:
|
1060
|
+
raise InvalidBSON("bad eoo")
|
1061
|
+
if use_raw:
|
1062
|
+
docs.append(opts.document_class(data[position : obj_end + 1], opts)) # type: ignore
|
1063
|
+
else:
|
1064
|
+
docs.append(_elements_to_dict(data, view, position + 4, obj_end, opts))
|
1065
|
+
position += obj_size
|
1066
|
+
return docs
|
1067
|
+
except InvalidBSON:
|
1068
|
+
raise
|
1069
|
+
except Exception:
|
1070
|
+
# Change exception type to InvalidBSON but preserve traceback.
|
1071
|
+
_, exc_value, exc_tb = sys.exc_info()
|
1072
|
+
raise InvalidBSON(str(exc_value)).with_traceback(exc_tb)
|
1073
|
+
|
1074
|
+
|
1075
|
+
if _USE_C:
|
1076
|
+
_decode_all = _cbson._decode_all # noqa: F811
|
1077
|
+
|
1078
|
+
|
1079
|
+
def decode_all(
|
1080
|
+
data: _ReadableBuffer, codec_options: "Optional[CodecOptions[_DocumentType]]" = None
|
1081
|
+
) -> List[_DocumentType]:
|
1082
|
+
"""Decode BSON data to multiple documents.
|
1083
|
+
|
1084
|
+
`data` must be a bytes-like object implementing the buffer protocol that
|
1085
|
+
provides concatenated, valid, BSON-encoded documents.
|
1086
|
+
|
1087
|
+
:Parameters:
|
1088
|
+
- `data`: BSON data
|
1089
|
+
- `codec_options` (optional): An instance of
|
1090
|
+
:class:`~bson.codec_options.CodecOptions`.
|
1091
|
+
|
1092
|
+
.. versionchanged:: 3.9
|
1093
|
+
Supports bytes-like objects that implement the buffer protocol.
|
1094
|
+
|
1095
|
+
.. versionchanged:: 3.0
|
1096
|
+
Removed `compile_re` option: PyMongo now always represents BSON regular
|
1097
|
+
expressions as :class:`~bson.regex.Regex` objects. Use
|
1098
|
+
:meth:`~bson.regex.Regex.try_compile` to attempt to convert from a
|
1099
|
+
BSON regular expression to a Python regular expression object.
|
1100
|
+
|
1101
|
+
Replaced `as_class`, `tz_aware`, and `uuid_subtype` options with
|
1102
|
+
`codec_options`.
|
1103
|
+
"""
|
1104
|
+
opts = codec_options or DEFAULT_CODEC_OPTIONS
|
1105
|
+
if not isinstance(opts, CodecOptions):
|
1106
|
+
raise _CODEC_OPTIONS_TYPE_ERROR
|
1107
|
+
|
1108
|
+
return _decode_all(data, opts) # type: ignore[arg-type]
|
1109
|
+
|
1110
|
+
|
1111
|
+
def _decode_selective(rawdoc: Any, fields: Any, codec_options: Any) -> Mapping[Any, Any]:
|
1112
|
+
if _raw_document_class(codec_options.document_class):
|
1113
|
+
# If document_class is RawBSONDocument, use vanilla dictionary for
|
1114
|
+
# decoding command response.
|
1115
|
+
doc = {}
|
1116
|
+
else:
|
1117
|
+
# Else, use the specified document_class.
|
1118
|
+
doc = codec_options.document_class()
|
1119
|
+
for key, value in rawdoc.items():
|
1120
|
+
if key in fields:
|
1121
|
+
if fields[key] == 1:
|
1122
|
+
doc[key] = _bson_to_dict(rawdoc.raw, codec_options)[key]
|
1123
|
+
else:
|
1124
|
+
doc[key] = _decode_selective(value, fields[key], codec_options)
|
1125
|
+
else:
|
1126
|
+
doc[key] = value
|
1127
|
+
return doc
|
1128
|
+
|
1129
|
+
|
1130
|
+
def _convert_raw_document_lists_to_streams(document: Any) -> None:
|
1131
|
+
cursor = document.get("cursor")
|
1132
|
+
if cursor:
|
1133
|
+
for key in ("firstBatch", "nextBatch"):
|
1134
|
+
batch = cursor.get(key)
|
1135
|
+
if batch:
|
1136
|
+
stream = b"".join(doc.raw for doc in batch)
|
1137
|
+
cursor[key] = [stream]
|
1138
|
+
|
1139
|
+
|
1140
|
+
def _decode_all_selective(data: Any, codec_options: CodecOptions, fields: Any) -> List[Any]:
|
1141
|
+
"""Decode BSON data to a single document while using user-provided
|
1142
|
+
custom decoding logic.
|
1143
|
+
|
1144
|
+
`data` must be a string representing a valid, BSON-encoded document.
|
1145
|
+
|
1146
|
+
:Parameters:
|
1147
|
+
- `data`: BSON data
|
1148
|
+
- `codec_options`: An instance of
|
1149
|
+
:class:`~bson.codec_options.CodecOptions` with user-specified type
|
1150
|
+
decoders. If no decoders are found, this method is the same as
|
1151
|
+
``decode_all``.
|
1152
|
+
- `fields`: Map of document namespaces where data that needs
|
1153
|
+
to be custom decoded lives or None. For example, to custom decode a
|
1154
|
+
list of objects in 'field1.subfield1', the specified value should be
|
1155
|
+
``{'field1': {'subfield1': 1}}``. If ``fields`` is an empty map or
|
1156
|
+
None, this method is the same as ``decode_all``.
|
1157
|
+
|
1158
|
+
:Returns:
|
1159
|
+
- `document_list`: Single-member list containing the decoded document.
|
1160
|
+
|
1161
|
+
.. versionadded:: 3.8
|
1162
|
+
"""
|
1163
|
+
if not codec_options.type_registry._decoder_map:
|
1164
|
+
return decode_all(data, codec_options)
|
1165
|
+
|
1166
|
+
if not fields:
|
1167
|
+
return decode_all(data, codec_options.with_options(type_registry=None))
|
1168
|
+
|
1169
|
+
# Decode documents for internal use.
|
1170
|
+
from bson.raw_bson import RawBSONDocument
|
1171
|
+
|
1172
|
+
internal_codec_options = codec_options.with_options(
|
1173
|
+
document_class=RawBSONDocument, type_registry=None
|
1174
|
+
)
|
1175
|
+
_doc = _bson_to_dict(data, internal_codec_options)
|
1176
|
+
return [
|
1177
|
+
_decode_selective(
|
1178
|
+
_doc,
|
1179
|
+
fields,
|
1180
|
+
codec_options,
|
1181
|
+
)
|
1182
|
+
]
|
1183
|
+
|
1184
|
+
|
1185
|
+
def decode_iter(
|
1186
|
+
data: bytes, codec_options: "Optional[CodecOptions[_DocumentType]]" = None
|
1187
|
+
) -> Iterator[_DocumentType]:
|
1188
|
+
"""Decode BSON data to multiple documents as a generator.
|
1189
|
+
|
1190
|
+
Works similarly to the decode_all function, but yields one document at a
|
1191
|
+
time.
|
1192
|
+
|
1193
|
+
`data` must be a string of concatenated, valid, BSON-encoded
|
1194
|
+
documents.
|
1195
|
+
|
1196
|
+
:Parameters:
|
1197
|
+
- `data`: BSON data
|
1198
|
+
- `codec_options` (optional): An instance of
|
1199
|
+
:class:`~bson.codec_options.CodecOptions`.
|
1200
|
+
|
1201
|
+
.. versionchanged:: 3.0
|
1202
|
+
Replaced `as_class`, `tz_aware`, and `uuid_subtype` options with
|
1203
|
+
`codec_options`.
|
1204
|
+
|
1205
|
+
.. versionadded:: 2.8
|
1206
|
+
"""
|
1207
|
+
opts = codec_options or DEFAULT_CODEC_OPTIONS
|
1208
|
+
if not isinstance(opts, CodecOptions):
|
1209
|
+
raise _CODEC_OPTIONS_TYPE_ERROR
|
1210
|
+
|
1211
|
+
position = 0
|
1212
|
+
end = len(data) - 1
|
1213
|
+
while position < end:
|
1214
|
+
obj_size = _UNPACK_INT_FROM(data, position)[0]
|
1215
|
+
elements = data[position : position + obj_size]
|
1216
|
+
position += obj_size
|
1217
|
+
|
1218
|
+
yield _bson_to_dict(elements, opts)
|
1219
|
+
|
1220
|
+
|
1221
|
+
def decode_file_iter(
|
1222
|
+
file_obj: Union[BinaryIO, IO], codec_options: "Optional[CodecOptions[_DocumentType]]" = None
|
1223
|
+
) -> Iterator[_DocumentType]:
|
1224
|
+
"""Decode bson data from a file to multiple documents as a generator.
|
1225
|
+
|
1226
|
+
Works similarly to the decode_all function, but reads from the file object
|
1227
|
+
in chunks and parses bson in chunks, yielding one document at a time.
|
1228
|
+
|
1229
|
+
:Parameters:
|
1230
|
+
- `file_obj`: A file object containing BSON data.
|
1231
|
+
- `codec_options` (optional): An instance of
|
1232
|
+
:class:`~bson.codec_options.CodecOptions`.
|
1233
|
+
|
1234
|
+
.. versionchanged:: 3.0
|
1235
|
+
Replaced `as_class`, `tz_aware`, and `uuid_subtype` options with
|
1236
|
+
`codec_options`.
|
1237
|
+
|
1238
|
+
.. versionadded:: 2.8
|
1239
|
+
"""
|
1240
|
+
opts = codec_options or DEFAULT_CODEC_OPTIONS
|
1241
|
+
while True:
|
1242
|
+
# Read size of next object.
|
1243
|
+
size_data = file_obj.read(4)
|
1244
|
+
if not size_data:
|
1245
|
+
break # Finished with file normaly.
|
1246
|
+
elif len(size_data) != 4:
|
1247
|
+
raise InvalidBSON("cut off in middle of objsize")
|
1248
|
+
obj_size = _UNPACK_INT_FROM(size_data, 0)[0] - 4
|
1249
|
+
elements = size_data + file_obj.read(max(0, obj_size))
|
1250
|
+
yield _bson_to_dict(elements, opts)
|
1251
|
+
|
1252
|
+
|
1253
|
+
def is_valid(bson: bytes) -> bool:
|
1254
|
+
"""Check that the given string represents valid :class:`BSON` data.
|
1255
|
+
|
1256
|
+
Raises :class:`TypeError` if `bson` is not an instance of
|
1257
|
+
:class:`str` (:class:`bytes` in python 3). Returns ``True``
|
1258
|
+
if `bson` is valid :class:`BSON`, ``False`` otherwise.
|
1259
|
+
|
1260
|
+
:Parameters:
|
1261
|
+
- `bson`: the data to be validated
|
1262
|
+
"""
|
1263
|
+
if not isinstance(bson, bytes):
|
1264
|
+
raise TypeError("BSON data must be an instance of a subclass of bytes")
|
1265
|
+
|
1266
|
+
try:
|
1267
|
+
_bson_to_dict(bson, DEFAULT_CODEC_OPTIONS)
|
1268
|
+
return True
|
1269
|
+
except Exception:
|
1270
|
+
return False
|
1271
|
+
|
1272
|
+
|
1273
|
+
class BSON(bytes):
|
1274
|
+
"""BSON (Binary JSON) data.
|
1275
|
+
|
1276
|
+
.. warning:: Using this class to encode and decode BSON adds a performance
|
1277
|
+
cost. For better performance use the module level functions
|
1278
|
+
:func:`encode` and :func:`decode` instead.
|
1279
|
+
"""
|
1280
|
+
|
1281
|
+
@classmethod
|
1282
|
+
def encode(
|
1283
|
+
cls: Type["BSON"],
|
1284
|
+
document: _DocumentIn,
|
1285
|
+
check_keys: bool = False,
|
1286
|
+
codec_options: CodecOptions = DEFAULT_CODEC_OPTIONS,
|
1287
|
+
) -> "BSON":
|
1288
|
+
"""Encode a document to a new :class:`BSON` instance.
|
1289
|
+
|
1290
|
+
A document can be any mapping type (like :class:`dict`).
|
1291
|
+
|
1292
|
+
Raises :class:`TypeError` if `document` is not a mapping type,
|
1293
|
+
or contains keys that are not instances of
|
1294
|
+
:class:`basestring` (:class:`str` in python 3). Raises
|
1295
|
+
:class:`~bson.errors.InvalidDocument` if `document` cannot be
|
1296
|
+
converted to :class:`BSON`.
|
1297
|
+
|
1298
|
+
:Parameters:
|
1299
|
+
- `document`: mapping type representing a document
|
1300
|
+
- `check_keys` (optional): check if keys start with '$' or
|
1301
|
+
contain '.', raising :class:`~bson.errors.InvalidDocument` in
|
1302
|
+
either case
|
1303
|
+
- `codec_options` (optional): An instance of
|
1304
|
+
:class:`~bson.codec_options.CodecOptions`.
|
1305
|
+
|
1306
|
+
.. versionchanged:: 3.0
|
1307
|
+
Replaced `uuid_subtype` option with `codec_options`.
|
1308
|
+
"""
|
1309
|
+
return cls(encode(document, check_keys, codec_options))
|
1310
|
+
|
1311
|
+
def decode(self, codec_options: CodecOptions = DEFAULT_CODEC_OPTIONS) -> _DocumentType: # type: ignore[override]
|
1312
|
+
"""Decode this BSON data.
|
1313
|
+
|
1314
|
+
By default, returns a BSON document represented as a Python
|
1315
|
+
:class:`dict`. To use a different :class:`MutableMapping` class,
|
1316
|
+
configure a :class:`~bson.codec_options.CodecOptions`::
|
1317
|
+
|
1318
|
+
>>> import collections # From Python standard library.
|
1319
|
+
>>> import bson
|
1320
|
+
>>> from bson.codec_options import CodecOptions
|
1321
|
+
>>> data = bson.BSON.encode({'a': 1})
|
1322
|
+
>>> decoded_doc = bson.BSON(data).decode()
|
1323
|
+
<type 'dict'>
|
1324
|
+
>>> options = CodecOptions(document_class=collections.OrderedDict)
|
1325
|
+
>>> decoded_doc = bson.BSON(data).decode(codec_options=options)
|
1326
|
+
>>> type(decoded_doc)
|
1327
|
+
<class 'collections.OrderedDict'>
|
1328
|
+
|
1329
|
+
:Parameters:
|
1330
|
+
- `codec_options` (optional): An instance of
|
1331
|
+
:class:`~bson.codec_options.CodecOptions`.
|
1332
|
+
|
1333
|
+
.. versionchanged:: 3.0
|
1334
|
+
Removed `compile_re` option: PyMongo now always represents BSON
|
1335
|
+
regular expressions as :class:`~bson.regex.Regex` objects. Use
|
1336
|
+
:meth:`~bson.regex.Regex.try_compile` to attempt to convert from a
|
1337
|
+
BSON regular expression to a Python regular expression object.
|
1338
|
+
|
1339
|
+
Replaced `as_class`, `tz_aware`, and `uuid_subtype` options with
|
1340
|
+
`codec_options`.
|
1341
|
+
"""
|
1342
|
+
return decode(self, codec_options)
|
1343
|
+
|
1344
|
+
|
1345
|
+
def has_c() -> bool:
|
1346
|
+
"""Is the C extension installed?"""
|
1347
|
+
return _USE_C
|