This repository has been archived by the owner on May 10, 2024. It is now read-only.
/
table.py
1363 lines (1099 loc) · 46.5 KB
/
table.py
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
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import boto
from boto.dynamodb2 import exceptions
from boto.dynamodb2.fields import (HashKey, RangeKey,
AllIndex, KeysOnlyIndex, IncludeIndex,
GlobalAllIndex, GlobalKeysOnlyIndex,
GlobalIncludeIndex)
from boto.dynamodb2.items import Item
from boto.dynamodb2.layer1 import DynamoDBConnection
from boto.dynamodb2.results import ResultSet, BatchGetResultSet
from boto.dynamodb2.types import Dynamizer, FILTER_OPERATORS, QUERY_OPERATORS
from boto.exception import JSONResponseError
class Table(object):
"""
Interacts & models the behavior of a DynamoDB table.
The ``Table`` object represents a set (or rough categorization) of
records within DynamoDB. The important part is that all records within the
table, while largely-schema-free, share the same schema & are essentially
namespaced for use in your application. For example, you might have a
``users`` table or a ``forums`` table.
"""
max_batch_get = 100
def __init__(self, table_name, schema=None, throughput=None, indexes=None,
global_indexes=None, connection=None):
"""
Sets up a new in-memory ``Table``.
This is useful if the table already exists within DynamoDB & you simply
want to use it for additional interactions. The only required parameter
is the ``table_name``. However, under the hood, the object will call
``describe_table`` to determine the schema/indexes/throughput. You
can avoid this extra call by passing in ``schema`` & ``indexes``.
**IMPORTANT** - If you're creating a new ``Table`` for the first time,
you should use the ``Table.create`` method instead, as it will
persist the table structure to DynamoDB.
Requires a ``table_name`` parameter, which should be a simple string
of the name of the table.
Optionally accepts a ``schema`` parameter, which should be a list of
``BaseSchemaField`` subclasses representing the desired schema.
Optionally accepts a ``throughput`` parameter, which should be a
dictionary. If provided, it should specify a ``read`` & ``write`` key,
both of which should have an integer value associated with them.
Optionally accepts a ``indexes`` parameter, which should be a list of
``BaseIndexField`` subclasses representing the desired indexes.
Optionally accepts a ``global_indexes`` parameter, which should be a
list of ``GlobalBaseIndexField`` subclasses representing the desired
indexes.
Optionally accepts a ``connection`` parameter, which should be a
``DynamoDBConnection`` instance (or subclass). This is primarily useful
for specifying alternate connection parameters.
Example::
# The simple, it-already-exists case.
>>> conn = Table('users')
# The full, minimum-extra-calls case.
>>> from boto import dynamodb2
>>> users = Table('users', schema=[
... HashKey('username'),
... RangeKey('date_joined', data_type=NUMBER)
... ], throughput={
... 'read':20,
... 'write': 10,
... }, indexes=[
... KeysOnlyIndex('MostRecentlyJoined', parts=[
... HashKey('username')
... RangeKey('date_joined')
... ]),
... ], global_indexes=[
... GlobalAllIndex('UsersByZipcode', parts=[
... HashKey('zipcode'),
... RangeKey('username'),
... ],
... throughput={
... 'read':10,
... 'write":10,
... }),
... ], connection=dynamodb2.connect_to_region('us-west-2',
... aws_access_key_id='key',
... aws_secret_access_key='key',
... ))
"""
self.table_name = table_name
self.connection = connection
self.throughput = {
'read': 5,
'write': 5,
}
self.schema = schema
self.indexes = indexes
self.global_indexes = global_indexes
if self.connection is None:
self.connection = DynamoDBConnection()
if throughput is not None:
self.throughput = throughput
self._dynamizer = Dynamizer()
@classmethod
def create(cls, table_name, schema, throughput=None, indexes=None,
global_indexes=None, connection=None):
"""
Creates a new table in DynamoDB & returns an in-memory ``Table`` object.
This will setup a brand new table within DynamoDB. The ``table_name``
must be unique for your AWS account. The ``schema`` is also required
to define the key structure of the table.
**IMPORTANT** - You should consider the usage pattern of your table
up-front, as the schema & indexes can **NOT** be modified once the
table is created, requiring the creation of a new table & migrating
the data should you wish to revise it.
**IMPORTANT** - If the table already exists in DynamoDB, additional
calls to this method will result in an error. If you just need
a ``Table`` object to interact with the existing table, you should
just initialize a new ``Table`` object, which requires only the
``table_name``.
Requires a ``table_name`` parameter, which should be a simple string
of the name of the table.
Requires a ``schema`` parameter, which should be a list of
``BaseSchemaField`` subclasses representing the desired schema.
Optionally accepts a ``throughput`` parameter, which should be a
dictionary. If provided, it should specify a ``read`` & ``write`` key,
both of which should have an integer value associated with them.
Optionally accepts a ``indexes`` parameter, which should be a list of
``BaseIndexField`` subclasses representing the desired indexes.
Optionally accepts a ``global_indexes`` parameter, which should be a
list of ``GlobalBaseIndexField`` subclasses representing the desired
indexes.
Optionally accepts a ``connection`` parameter, which should be a
``DynamoDBConnection`` instance (or subclass). This is primarily useful
for specifying alternate connection parameters.
Example::
>>> users = Table.create('users', schema=[
... HashKey('username'),
... RangeKey('date_joined', data_type=NUMBER)
... ], throughput={
... 'read':20,
... 'write': 10,
... }, indexes=[
... KeysOnlyIndex('MostRecentlyJoined', parts=[
... RangeKey('date_joined')
... ]), global_indexes=[
... GlobalAllIndex('UsersByZipcode', parts=[
... HashKey('zipcode'),
... RangeKey('username'),
... ],
... throughput={
... 'read':10,
... 'write':10,
... }),
... ])
"""
table = cls(table_name=table_name, connection=connection)
table.schema = schema
if throughput is not None:
table.throughput = throughput
if indexes is not None:
table.indexes = indexes
if global_indexes is not None:
table.global_indexes = global_indexes
# Prep the schema.
raw_schema = []
attr_defs = []
seen_attrs = set()
for field in table.schema:
raw_schema.append(field.schema())
# Build the attributes off what we know.
seen_attrs.add(field.name)
attr_defs.append(field.definition())
raw_throughput = {
'ReadCapacityUnits': int(table.throughput['read']),
'WriteCapacityUnits': int(table.throughput['write']),
}
kwargs = {}
kwarg_map = {
'indexes': 'local_secondary_indexes',
'global_indexes': 'global_secondary_indexes',
}
for index_attr in ('indexes', 'global_indexes'):
table_indexes = getattr(table, index_attr)
if table_indexes:
raw_indexes = []
for index_field in table_indexes:
raw_indexes.append(index_field.schema())
# Make sure all attributes specified in the indexes are
# added to the definition
for field in index_field.parts:
if field.name not in seen_attrs:
seen_attrs.add(field.name)
attr_defs.append(field.definition())
kwargs[kwarg_map[index_attr]] = raw_indexes
table.connection.create_table(
table_name=table.table_name,
attribute_definitions=attr_defs,
key_schema=raw_schema,
provisioned_throughput=raw_throughput,
**kwargs
)
return table
def _introspect_schema(self, raw_schema):
"""
Given a raw schema structure back from a DynamoDB response, parse
out & build the high-level Python objects that represent them.
"""
schema = []
for field in raw_schema:
if field['KeyType'] == 'HASH':
schema.append(HashKey(field['AttributeName']))
elif field['KeyType'] == 'RANGE':
schema.append(RangeKey(field['AttributeName']))
else:
raise exceptions.UnknownSchemaFieldError(
"%s was seen, but is unknown. Please report this at "
"https://github.com/boto/boto/issues." % field['KeyType']
)
return schema
def _introspect_indexes(self, raw_indexes):
"""
Given a raw index structure back from a DynamoDB response, parse
out & build the high-level Python objects that represent them.
"""
indexes = []
for field in raw_indexes:
index_klass = AllIndex
kwargs = {
'parts': []
}
if field['Projection']['ProjectionType'] == 'ALL':
index_klass = AllIndex
elif field['Projection']['ProjectionType'] == 'KEYS_ONLY':
index_klass = KeysOnlyIndex
elif field['Projection']['ProjectionType'] == 'INCLUDE':
index_klass = IncludeIndex
kwargs['includes'] = field['Projection']['NonKeyAttributes']
else:
raise exceptions.UnknownIndexFieldError(
"%s was seen, but is unknown. Please report this at "
"https://github.com/boto/boto/issues." % \
field['Projection']['ProjectionType']
)
name = field['IndexName']
kwargs['parts'] = self._introspect_schema(field['KeySchema'])
indexes.append(index_klass(name, **kwargs))
return indexes
def describe(self):
"""
Describes the current structure of the table in DynamoDB.
This information will be used to update the ``schema``, ``indexes``
and ``throughput`` information on the ``Table``. Some calls, such as
those involving creating keys or querying, will require this
information to be populated.
It also returns the full raw datastructure from DynamoDB, in the
event you'd like to parse out additional information (such as the
``ItemCount`` or usage information).
Example::
>>> users.describe()
{
# Lots of keys here...
}
>>> len(users.schema)
2
"""
result = self.connection.describe_table(self.table_name)
# Blindly update throughput, since what's on DynamoDB's end is likely
# more correct.
raw_throughput = result['Table']['ProvisionedThroughput']
self.throughput['read'] = int(raw_throughput['ReadCapacityUnits'])
self.throughput['write'] = int(raw_throughput['WriteCapacityUnits'])
if not self.schema:
# Since we have the data, build the schema.
raw_schema = result['Table'].get('KeySchema', [])
self.schema = self._introspect_schema(raw_schema)
if not self.indexes:
# Build the index information as well.
raw_indexes = result['Table'].get('LocalSecondaryIndexes', [])
self.indexes = self._introspect_indexes(raw_indexes)
# This is leaky.
return result
def update(self, throughput, global_indexes=None):
"""
Updates table attributes in DynamoDB.
Currently, the only thing you can modify about a table after it has
been created is the throughput.
Requires a ``throughput`` parameter, which should be a
dictionary. If provided, it should specify a ``read`` & ``write`` key,
both of which should have an integer value associated with them.
Returns ``True`` on success.
Example::
# For a read-heavier application...
>>> users.update(throughput={
... 'read': 20,
... 'write': 10,
... })
True
# To also update the global index(es) throughput.
>>> users.update(throughput={
... 'read': 20,
... 'write': 10,
... },
... global_secondary_indexes={
... 'TheIndexNameHere': {
... 'read': 15,
... 'write': 5,
... }
... })
True
"""
self.throughput = throughput
data = {
'ReadCapacityUnits': int(self.throughput['read']),
'WriteCapacityUnits': int(self.throughput['write']),
}
gsi_data = None
if global_indexes:
gsi_data = []
for gsi_name, gsi_throughput in global_indexes.items():
gsi_data.append({
"Update": {
"IndexName": gsi_name,
"ProvisionedThroughput": {
"ReadCapacityUnits": int(gsi_throughput['read']),
"WriteCapacityUnits": int(gsi_throughput['write']),
},
},
})
self.connection.update_table(
self.table_name,
provisioned_throughput=data,
global_secondary_index_updates=gsi_data
)
return True
def delete(self):
"""
Deletes a table in DynamoDB.
**IMPORTANT** - Be careful when using this method, there is no undo.
Returns ``True`` on success.
Example::
>>> users.delete()
True
"""
self.connection.delete_table(self.table_name)
return True
def _encode_keys(self, keys):
"""
Given a flat Python dictionary of keys/values, converts it into the
nested dictionary DynamoDB expects.
Converts::
{
'username': 'john',
'tags': [1, 2, 5],
}
...to...::
{
'username': {'S': 'john'},
'tags': {'NS': ['1', '2', '5']},
}
"""
raw_key = {}
for key, value in keys.items():
raw_key[key] = self._dynamizer.encode(value)
return raw_key
def get_item(self, consistent=False, attributes=None, **kwargs):
"""
Fetches an item (record) from a table in DynamoDB.
To specify the key of the item you'd like to get, you can specify the
key attributes as kwargs.
Optionally accepts a ``consistent`` parameter, which should be a
boolean. If you provide ``True``, it will perform
a consistent (but more expensive) read from DynamoDB.
(Default: ``False``)
Optionally accepts an ``attributes`` parameter, which should be a
list of fieldname to fetch. (Default: ``None``, which means all fields
should be fetched)
Returns an ``Item`` instance containing all the data for that record.
Example::
# A simple hash key.
>>> john = users.get_item(username='johndoe')
>>> john['first_name']
'John'
# A complex hash+range key.
>>> john = users.get_item(username='johndoe', last_name='Doe')
>>> john['first_name']
'John'
# A consistent read (assuming the data might have just changed).
>>> john = users.get_item(username='johndoe', consistent=True)
>>> john['first_name']
'Johann'
# With a key that is an invalid variable name in Python.
# Also, assumes a different schema than previous examples.
>>> john = users.get_item(**{
... 'date-joined': 127549192,
... })
>>> john['first_name']
'John'
"""
raw_key = self._encode_keys(kwargs)
item_data = self.connection.get_item(
self.table_name,
raw_key,
attributes_to_get=attributes,
consistent_read=consistent
)
if 'Item' not in item_data:
raise exceptions.ItemNotFound("Item %s couldn't be found." % kwargs)
item = Item(self)
item.load(item_data)
return item
def has_item(self, **kwargs):
"""
Return whether an item (record) exists within a table in DynamoDB.
To specify the key of the item you'd like to get, you can specify the
key attributes as kwargs.
Optionally accepts a ``consistent`` parameter, which should be a
boolean. If you provide ``True``, it will perform
a consistent (but more expensive) read from DynamoDB.
(Default: ``False``)
Optionally accepts an ``attributes`` parameter, which should be a
list of fieldnames to fetch. (Default: ``None``, which means all fields
should be fetched)
Returns ``True`` if an ``Item`` is present, ``False`` if not.
Example::
# Simple, just hash-key schema.
>>> users.has_item(username='johndoe')
True
# Complex schema, item not present.
>>> users.has_item(
... username='johndoe',
... date_joined='2014-01-07'
... )
False
"""
try:
self.get_item(**kwargs)
except (JSONResponseError, exceptions.ItemNotFound):
return False
return True
def lookup(self, *args, **kwargs):
"""
Look up an entry in DynamoDB. This is mostly backwards compatible
with boto.dynamodb. Unlike get_item, it takes hash_key and range_key first,
although you may still specify keyword arguments instead.
Also unlike the get_item command, if the returned item has no keys
(i.e., it does not exist in DynamoDB), a None result is returned, instead
of an empty key object.
Example::
>>> user = users.lookup(username)
>>> user = users.lookup(username, consistent=True)
>>> app = apps.lookup('my_customer_id', 'my_app_id')
"""
if not self.schema:
self.describe()
for x, arg in enumerate(args):
kwargs[self.schema[x].name] = arg
ret = self.get_item(**kwargs)
if not ret.keys():
return None
return ret
def new_item(self, *args):
"""
Returns a new, blank item
This is mostly for consistency with boto.dynamodb
"""
if not self.schema:
self.describe()
data = {}
for x, arg in enumerate(args):
data[self.schema[x].name] = arg
return Item(self, data=data)
def put_item(self, data, overwrite=False):
"""
Saves an entire item to DynamoDB.
By default, if any part of the ``Item``'s original data doesn't match
what's currently in DynamoDB, this request will fail. This prevents
other processes from updating the data in between when you read the
item & when your request to update the item's data is processed, which
would typically result in some data loss.
Requires a ``data`` parameter, which should be a dictionary of the data
you'd like to store in DynamoDB.
Optionally accepts an ``overwrite`` parameter, which should be a
boolean. If you provide ``True``, this will tell DynamoDB to blindly
overwrite whatever data is present, if any.
Returns ``True`` on success.
Example::
>>> users.put_item(data={
... 'username': 'jane',
... 'first_name': 'Jane',
... 'last_name': 'Doe',
... 'date_joined': 126478915,
... })
True
"""
item = Item(self, data=data)
return item.save(overwrite=overwrite)
def _put_item(self, item_data, expects=None):
"""
The internal variant of ``put_item`` (full data). This is used by the
``Item`` objects, since that operation is represented at the
table-level by the API, but conceptually maps better to telling an
individual ``Item`` to save itself.
"""
kwargs = {}
if expects is not None:
kwargs['expected'] = expects
self.connection.put_item(self.table_name, item_data, **kwargs)
return True
def _update_item(self, key, item_data, expects=None):
"""
The internal variant of ``put_item`` (partial data). This is used by the
``Item`` objects, since that operation is represented at the
table-level by the API, but conceptually maps better to telling an
individual ``Item`` to save itself.
"""
raw_key = self._encode_keys(key)
kwargs = {}
if expects is not None:
kwargs['expected'] = expects
self.connection.update_item(self.table_name, raw_key, item_data, **kwargs)
return True
def delete_item(self, **kwargs):
"""
Deletes an item in DynamoDB.
**IMPORTANT** - Be careful when using this method, there is no undo.
To specify the key of the item you'd like to get, you can specify the
key attributes as kwargs.
Returns ``True`` on success.
Example::
# A simple hash key.
>>> users.delete_item(username='johndoe')
True
# A complex hash+range key.
>>> users.delete_item(username='jane', last_name='Doe')
True
# With a key that is an invalid variable name in Python.
# Also, assumes a different schema than previous examples.
>>> users.delete_item(**{
... 'date-joined': 127549192,
... })
True
"""
raw_key = self._encode_keys(kwargs)
self.connection.delete_item(self.table_name, raw_key)
return True
def get_key_fields(self):
"""
Returns the fields necessary to make a key for a table.
If the ``Table`` does not already have a populated ``schema``,
this will request it via a ``Table.describe`` call.
Returns a list of fieldnames (strings).
Example::
# A simple hash key.
>>> users.get_key_fields()
['username']
# A complex hash+range key.
>>> users.get_key_fields()
['username', 'last_name']
"""
if not self.schema:
# We don't know the structure of the table. Get a description to
# populate the schema.
self.describe()
return [field.name for field in self.schema]
def batch_write(self):
"""
Allows the batching of writes to DynamoDB.
Since each write/delete call to DynamoDB has a cost associated with it,
when loading lots of data, it makes sense to batch them, creating as
few calls as possible.
This returns a context manager that will transparently handle creating
these batches. The object you get back lightly-resembles a ``Table``
object, sharing just the ``put_item`` & ``delete_item`` methods
(which are all that DynamoDB can batch in terms of writing data).
DynamoDB's maximum batch size is 25 items per request. If you attempt
to put/delete more than that, the context manager will batch as many
as it can up to that number, then flush them to DynamoDB & continue
batching as more calls come in.
Example::
# Assuming a table with one record...
>>> with users.batch_write() as batch:
... batch.put_item(data={
... 'username': 'johndoe',
... 'first_name': 'John',
... 'last_name': 'Doe',
... 'owner': 1,
... })
... # Nothing across the wire yet.
... batch.delete_item(username='bob')
... # Still no requests sent.
... batch.put_item(data={
... 'username': 'jane',
... 'first_name': 'Jane',
... 'last_name': 'Doe',
... 'date_joined': 127436192,
... })
... # Nothing yet, but once we leave the context, the
... # put/deletes will be sent.
"""
# PHENOMENAL COSMIC DOCS!!! itty-bitty code.
return BatchTable(self)
def _build_filters(self, filter_kwargs, using=QUERY_OPERATORS):
"""
An internal method for taking query/scan-style ``**kwargs`` & turning
them into the raw structure DynamoDB expects for filtering.
"""
filters = {}
for field_and_op, value in filter_kwargs.items():
field_bits = field_and_op.split('__')
fieldname = '__'.join(field_bits[:-1])
try:
op = using[field_bits[-1]]
except KeyError:
raise exceptions.UnknownFilterTypeError(
"Operator '%s' from '%s' is not recognized." % (
field_bits[-1],
field_and_op
)
)
lookup = {
'AttributeValueList': [],
'ComparisonOperator': op,
}
# Special-case the ``NULL/NOT_NULL`` case.
if field_bits[-1] == 'null':
del lookup['AttributeValueList']
if value is False:
lookup['ComparisonOperator'] = 'NOT_NULL'
else:
lookup['ComparisonOperator'] = 'NULL'
# Special-case the ``BETWEEN`` case.
elif field_bits[-1] == 'between':
if len(value) == 2 and isinstance(value, (list, tuple)):
lookup['AttributeValueList'].append(
self._dynamizer.encode(value[0])
)
lookup['AttributeValueList'].append(
self._dynamizer.encode(value[1])
)
# Special-case the ``IN`` case
elif field_bits[-1] == 'in':
for val in value:
lookup['AttributeValueList'].append(self._dynamizer.encode(val))
else:
# Fix up the value for encoding, because it was built to only work
# with ``set``s.
if isinstance(value, (list, tuple)):
value = set(value)
lookup['AttributeValueList'].append(
self._dynamizer.encode(value)
)
# Finally, insert it into the filters.
filters[fieldname] = lookup
return filters
def query(self, limit=None, index=None, reverse=False, consistent=False,
attributes=None, max_page_size=None, **filter_kwargs):
"""
Queries for a set of matching items in a DynamoDB table.
Queries can be performed against a hash key, a hash+range key or
against any data stored in your local secondary indexes.
**Note** - You can not query against arbitrary fields within the data
stored in DynamoDB.
To specify the filters of the items you'd like to get, you can specify
the filters as kwargs. Each filter kwarg should follow the pattern
``<fieldname>__<filter_operation>=<value_to_look_for>``.
Optionally accepts a ``limit`` parameter, which should be an integer
count of the total number of items to return. (Default: ``None`` -
all results)
Optionally accepts an ``index`` parameter, which should be a string of
name of the local secondary index you want to query against.
(Default: ``None``)
Optionally accepts a ``reverse`` parameter, which will present the
results in reverse order. (Default: ``False`` - normal order)
Optionally accepts a ``consistent`` parameter, which should be a
boolean. If you provide ``True``, it will force a consistent read of
the data (more expensive). (Default: ``False`` - use eventually
consistent reads)
Optionally accepts a ``attributes`` parameter, which should be a
tuple. If you provide any attributes only these will be fetched
from DynamoDB. This uses the ``AttributesToGet`` and set's
``Select`` to ``SPECIFIC_ATTRIBUTES`` API.
Optionally accepts a ``max_page_size`` parameter, which should be an
integer count of the maximum number of items to retrieve
**per-request**. This is useful in making faster requests & prevent
the scan from drowning out other queries. (Default: ``None`` -
fetch as many as DynamoDB will return)
Returns a ``ResultSet``, which transparently handles the pagination of
results you get back.
Example::
# Look for last names equal to "Doe".
>>> results = users.query(last_name__eq='Doe')
>>> for res in results:
... print res['first_name']
'John'
'Jane'
# Look for last names beginning with "D", in reverse order, limit 3.
>>> results = users.query(
... last_name__beginswith='D',
... reverse=True,
... limit=3
... )
>>> for res in results:
... print res['first_name']
'Alice'
'Jane'
'John'
# Use an LSI & a consistent read.
>>> results = users.query(
... date_joined__gte=1236451000,
... owner__eq=1,
... index='DateJoinedIndex',
... consistent=True
... )
>>> for res in results:
... print res['first_name']
'Alice'
'Bob'
'John'
'Fred'
"""
if self.schema:
if len(self.schema) == 1:
if len(filter_kwargs) <= 1:
if not self.global_indexes or not len(self.global_indexes):
# If the schema only has one field, there's <= 1 filter
# param & no Global Secondary Indexes, this is user
# error. Bail early.
raise exceptions.QueryError(
"You must specify more than one key to filter on."
)
if attributes is not None:
select = 'SPECIFIC_ATTRIBUTES'
else:
select = None
results = ResultSet(
max_page_size=max_page_size
)
kwargs = filter_kwargs.copy()
kwargs.update({
'limit': limit,
'index': index,
'reverse': reverse,
'consistent': consistent,
'select': select,
'attributes_to_get': attributes,
})
results.to_call(self._query, **kwargs)
return results
def query_count(self, index=None, consistent=False, **filter_kwargs):
"""
Queries the exact count of matching items in a DynamoDB table.
Queries can be performed against a hash key, a hash+range key or
against any data stored in your local secondary indexes.
To specify the filters of the items you'd like to get, you can specify
the filters as kwargs. Each filter kwarg should follow the pattern
``<fieldname>__<filter_operation>=<value_to_look_for>``.
Optionally accepts an ``index`` parameter, which should be a string of
name of the local secondary index you want to query against.
(Default: ``None``)
Optionally accepts a ``consistent`` parameter, which should be a
boolean. If you provide ``True``, it will force a consistent read of
the data (more expensive). (Default: ``False`` - use eventually
consistent reads)
Returns an integer which represents the exact amount of matched
items.
Example::
# Look for last names equal to "Doe".
>>> users.query_count(last_name__eq='Doe')
5
# Use an LSI & a consistent read.
>>> users.query_count(
... date_joined__gte=1236451000,
... owner__eq=1,
... index='DateJoinedIndex',
... consistent=True
... )
2
"""
key_conditions = self._build_filters(
filter_kwargs,
using=QUERY_OPERATORS
)
raw_results = self.connection.query(
self.table_name,
index_name=index,
consistent_read=consistent,
select='COUNT',
key_conditions=key_conditions,
)
return int(raw_results.get('Count', 0))
def _query(self, limit=None, index=None, reverse=False, consistent=False,
exclusive_start_key=None, select=None, attributes_to_get=None,
**filter_kwargs):
"""
The internal method that performs the actual queries. Used extensively
by ``ResultSet`` to perform each (paginated) request.
"""
kwargs = {
'limit': limit,
'index_name': index,
'consistent_read': consistent,
'select': select,
'attributes_to_get': attributes_to_get,
}
if reverse:
kwargs['scan_index_forward'] = False
if exclusive_start_key:
kwargs['exclusive_start_key'] = {}
for key, value in exclusive_start_key.items():
kwargs['exclusive_start_key'][key] = \
self._dynamizer.encode(value)
# Convert the filters into something we can actually use.
kwargs['key_conditions'] = self._build_filters(
filter_kwargs,
using=QUERY_OPERATORS
)
raw_results = self.connection.query(
self.table_name,