forked from databricks/databricks-sql-python
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathutils.py
More file actions
925 lines (755 loc) · 31.9 KB
/
utils.py
File metadata and controls
925 lines (755 loc) · 31.9 KB
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
from __future__ import annotations
from typing import Any, Dict, List, Optional, Tuple, Union, Sequence
from dateutil import parser
import datetime
import decimal
from abc import ABC, abstractmethod
from collections import OrderedDict, namedtuple
from collections.abc import Mapping
from decimal import Decimal
from enum import Enum
import re
import lz4.frame
try:
import pyarrow
except ImportError:
pyarrow = None
from databricks.sql import OperationalError
from databricks.sql.cloudfetch.download_manager import ResultFileDownloadManager
from databricks.sql.thrift_api.TCLIService.ttypes import (
TRowSet,
TSparkArrowResultLink,
TSparkRowSetType,
)
from databricks.sql.types import SSLOptions
from databricks.sql.backend.types import CommandId
from databricks.sql.telemetry.models.event import StatementType
from databricks.sql.parameters.native import ParameterStructure, TDbsqlParameter
import logging
BIT_MASKS = [1, 2, 4, 8, 16, 32, 64, 128]
DEFAULT_ERROR_CONTEXT = "Unknown error"
logger = logging.getLogger(__name__)
class ResultSetQueue(ABC):
@abstractmethod
def next_n_rows(self, num_rows: int):
pass
@abstractmethod
def remaining_rows(self):
pass
@abstractmethod
def close(self):
pass
class ThriftResultSetQueueFactory(ABC):
@staticmethod
def build_queue(
row_set_type: TSparkRowSetType,
t_row_set: TRowSet,
arrow_schema_bytes: bytes,
max_download_threads: int,
ssl_options: SSLOptions,
session_id_hex: Optional[str],
statement_id: str,
chunk_id: int,
http_client,
lz4_compressed: bool = True,
description: List[Tuple] = [],
) -> ResultSetQueue:
"""
Factory method to build a result set queue for Thrift backend.
Args:
row_set_type (enum): Row set type (Arrow, Column, or URL).
t_row_set (TRowSet): Result containing arrow batches, columns, or cloud fetch links.
arrow_schema_bytes (bytes): Bytes representing the arrow schema.
lz4_compressed (bool): Whether result data has been lz4 compressed.
description (List[List[Any]]): Hive table schema description.
max_download_threads (int): Maximum number of downloader thread pool threads.
ssl_options (SSLOptions): SSLOptions object for CloudFetchQueue
Returns:
ResultSetQueue
"""
if row_set_type == TSparkRowSetType.ARROW_BASED_SET:
arrow_table, n_valid_rows = convert_arrow_based_set_to_arrow_table(
t_row_set.arrowBatches, lz4_compressed, arrow_schema_bytes
)
converted_arrow_table = convert_decimals_in_arrow_table(
arrow_table, description
)
return ArrowQueue(converted_arrow_table, n_valid_rows)
elif row_set_type == TSparkRowSetType.COLUMN_BASED_SET:
column_table, column_names = convert_column_based_set_to_column_table(
t_row_set.columns, description
)
converted_column_table = convert_to_assigned_datatypes_in_column_table(
column_table, description
)
return ColumnQueue(ColumnTable(converted_column_table, column_names))
elif row_set_type == TSparkRowSetType.URL_BASED_SET:
return ThriftCloudFetchQueue(
schema_bytes=arrow_schema_bytes,
start_row_offset=t_row_set.startRowOffset,
result_links=t_row_set.resultLinks,
lz4_compressed=lz4_compressed,
description=description,
max_download_threads=max_download_threads,
ssl_options=ssl_options,
session_id_hex=session_id_hex,
statement_id=statement_id,
chunk_id=chunk_id,
http_client=http_client,
)
else:
raise AssertionError("Row set type is not valid")
class ColumnTable:
def __init__(self, column_table, column_names):
self.column_table = column_table
self.column_names = column_names
@property
def num_rows(self):
if len(self.column_table) == 0:
return 0
else:
return len(self.column_table[0])
@property
def num_columns(self):
return len(self.column_names)
def get_item(self, col_index, row_index):
return self.column_table[col_index][row_index]
def slice(self, curr_index, length):
sliced_column_table = [
column[curr_index : curr_index + length] for column in self.column_table
]
return ColumnTable(sliced_column_table, self.column_names)
def __eq__(self, other):
return (
self.column_table == other.column_table
and self.column_names == other.column_names
)
class ColumnQueue(ResultSetQueue):
def __init__(self, column_table: ColumnTable):
self.column_table = column_table
self.cur_row_index = 0
self.n_valid_rows = column_table.num_rows
def next_n_rows(self, num_rows):
length = min(num_rows, self.n_valid_rows - self.cur_row_index)
slice = self.column_table.slice(self.cur_row_index, length)
self.cur_row_index += slice.num_rows
return slice
def remaining_rows(self):
slice = self.column_table.slice(
self.cur_row_index, self.n_valid_rows - self.cur_row_index
)
self.cur_row_index += slice.num_rows
return slice
def close(self):
return
class ArrowQueue(ResultSetQueue):
def __init__(
self,
arrow_table: "pyarrow.Table",
n_valid_rows: int,
start_row_index: int = 0,
):
"""
A queue-like wrapper over an Arrow table
:param arrow_table: The Arrow table from which we want to take rows
:param n_valid_rows: The index of the last valid row in the table
:param start_row_index: The first row in the table we should start fetching from
"""
self.cur_row_index = start_row_index
self.arrow_table = arrow_table
self.n_valid_rows = n_valid_rows
def next_n_rows(self, num_rows: int) -> "pyarrow.Table":
"""Get upto the next n rows of the Arrow dataframe"""
length = min(num_rows, self.n_valid_rows - self.cur_row_index)
# Note that the table.slice API is not the same as Python's slice
# The second argument should be length, not end index
slice = self.arrow_table.slice(self.cur_row_index, length)
self.cur_row_index += slice.num_rows
return slice
def remaining_rows(self) -> "pyarrow.Table":
slice = self.arrow_table.slice(
self.cur_row_index, self.n_valid_rows - self.cur_row_index
)
self.cur_row_index += slice.num_rows
return slice
def close(self):
return
class CloudFetchQueue(ResultSetQueue, ABC):
"""Base class for cloud fetch queues that handle EXTERNAL_LINKS disposition with ARROW format."""
def __init__(
self,
max_download_threads: int,
ssl_options: SSLOptions,
session_id_hex: Optional[str],
statement_id: str,
chunk_id: int,
http_client,
schema_bytes: Optional[bytes] = None,
lz4_compressed: bool = True,
description: List[Tuple] = [],
):
"""
Initialize the base CloudFetchQueue.
Args:
max_download_threads: Maximum number of download threads
ssl_options: SSL options for downloads
schema_bytes: Arrow schema bytes
lz4_compressed: Whether the data is LZ4 compressed
description: Column descriptions
"""
self.schema_bytes = schema_bytes
self.max_download_threads = max_download_threads
self.lz4_compressed = lz4_compressed
self.description = description
self._ssl_options = ssl_options
self.session_id_hex = session_id_hex
self.statement_id = statement_id
self.chunk_id = chunk_id
self._http_client = http_client
# Table state
self.table = None
self.table_row_index = 0
# Initialize download manager
self.download_manager = ResultFileDownloadManager(
links=[],
max_download_threads=max_download_threads,
lz4_compressed=lz4_compressed,
ssl_options=ssl_options,
session_id_hex=session_id_hex,
statement_id=statement_id,
chunk_id=chunk_id,
http_client=http_client,
)
def next_n_rows(self, num_rows: int) -> "pyarrow.Table":
"""
Get up to the next n rows of the cloud fetch Arrow dataframes.
Args:
num_rows (int): Number of rows to retrieve.
Returns:
pyarrow.Table
"""
if not self.table:
logger.debug("CloudFetchQueue: no more rows available")
# Return empty pyarrow table to cause retry of fetch
return self._create_empty_table()
logger.debug("CloudFetchQueue: trying to get {} next rows".format(num_rows))
results = self.table.slice(0, 0)
partial_result_chunks = [results]
while num_rows > 0 and self.table:
# Get remaining of num_rows or the rest of the current table, whichever is smaller
length = min(num_rows, self.table.num_rows - self.table_row_index)
table_slice = self.table.slice(self.table_row_index, length)
partial_result_chunks.append(table_slice)
self.table_row_index += table_slice.num_rows
# Replace current table with the next table if we are at the end of the current table
if self.table_row_index == self.table.num_rows:
self.table = self._create_next_table()
self.table_row_index = 0
num_rows -= table_slice.num_rows
logger.debug("CloudFetchQueue: collected {} next rows".format(results.num_rows))
return pyarrow.concat_tables(partial_result_chunks, use_threads=True)
def remaining_rows(self) -> "pyarrow.Table":
"""
Get all remaining rows of the cloud fetch Arrow dataframes.
Returns:
pyarrow.Table
"""
if not self.table:
# Return empty pyarrow table to cause retry of fetch
return self._create_empty_table()
results = self.table.slice(0, 0)
partial_result_chunks = [results]
while self.table:
table_slice = self.table.slice(
self.table_row_index, self.table.num_rows - self.table_row_index
)
partial_result_chunks.append(table_slice)
self.table_row_index += table_slice.num_rows
self.table = self._create_next_table()
self.table_row_index = 0
return pyarrow.concat_tables(partial_result_chunks, use_threads=True)
def _create_table_at_offset(self, offset: int) -> Union["pyarrow.Table", None]:
"""Create next table at the given row offset"""
# Create next table by retrieving the logical next downloaded file, or return None to signal end of queue
downloaded_file = self.download_manager.get_next_downloaded_file(offset)
if not downloaded_file:
logger.debug(
"CloudFetchQueue: Cannot find downloaded file for row {}".format(offset)
)
# None signals no more Arrow tables can be built from the remaining handlers if any remain
return None
arrow_table = create_arrow_table_from_arrow_file(
downloaded_file.file_bytes, self.description
)
# The server rarely prepares the exact number of rows requested by the client in cloud fetch.
# Subsequently, we drop the extraneous rows in the last file if more rows are retrieved than requested
if arrow_table.num_rows > downloaded_file.row_count:
arrow_table = arrow_table.slice(0, downloaded_file.row_count)
# At this point, whether the file has extraneous rows or not, the arrow table should have the correct num rows
assert downloaded_file.row_count == arrow_table.num_rows
return arrow_table
@abstractmethod
def _create_next_table(self) -> Union["pyarrow.Table", None]:
"""Create next table by retrieving the logical next downloaded file."""
pass
def _create_empty_table(self) -> "pyarrow.Table":
"""Create a 0-row table with just the schema bytes."""
if not self.schema_bytes:
return pyarrow.Table.from_pydict({})
return create_arrow_table_from_arrow_file(self.schema_bytes, self.description)
def close(self):
self.download_manager._shutdown_manager()
class ThriftCloudFetchQueue(CloudFetchQueue):
"""Queue implementation for EXTERNAL_LINKS disposition with ARROW format for Thrift backend."""
def __init__(
self,
schema_bytes,
max_download_threads: int,
ssl_options: SSLOptions,
session_id_hex: Optional[str],
statement_id: str,
chunk_id: int,
http_client,
start_row_offset: int = 0,
result_links: Optional[List[TSparkArrowResultLink]] = None,
lz4_compressed: bool = True,
description: List[Tuple] = [],
):
"""
Initialize the Thrift CloudFetchQueue.
Args:
schema_bytes: Table schema in bytes
max_download_threads: Maximum number of downloader thread pool threads
ssl_options: SSL options for downloads
start_row_offset: The offset of the first row of the cloud fetch links
result_links: Links containing the downloadable URL and metadata
lz4_compressed: Whether the files are lz4 compressed
description: Hive table schema description
"""
super().__init__(
max_download_threads=max_download_threads,
ssl_options=ssl_options,
schema_bytes=schema_bytes,
lz4_compressed=lz4_compressed,
description=description,
session_id_hex=session_id_hex,
statement_id=statement_id,
chunk_id=chunk_id,
http_client=http_client,
)
self.start_row_index = start_row_offset
self.result_links = result_links or []
self.session_id_hex = session_id_hex
self.statement_id = statement_id
self.chunk_id = chunk_id
logger.debug(
"Initialize CloudFetch loader, row set start offset: {}, file list:".format(
start_row_offset
)
)
if self.result_links:
for result_link in self.result_links:
logger.debug(
"- start row offset: {}, row count: {}".format(
result_link.startRowOffset, result_link.rowCount
)
)
self.download_manager.add_link(result_link)
# Initialize table and position
self.table = self._create_next_table()
def _create_next_table(self) -> Union["pyarrow.Table", None]:
logger.debug(
"ThriftCloudFetchQueue: Trying to get downloaded file for row {}".format(
self.start_row_index
)
)
arrow_table = self._create_table_at_offset(self.start_row_index)
if arrow_table:
self.start_row_index += arrow_table.num_rows
logger.debug(
"ThriftCloudFetchQueue: Found downloaded file, row count: {}, new start offset: {}".format(
arrow_table.num_rows, self.start_row_index
)
)
return arrow_table
def _bound(min_x, max_x, x):
"""Bound x by [min_x, max_x]
min_x or max_x being None means unbounded in that respective side.
"""
if min_x is None and max_x is None:
return x
if min_x is None:
return min(max_x, x)
if max_x is None:
return max(min_x, x)
return min(max_x, max(min_x, x))
class NoRetryReason(Enum):
OUT_OF_TIME = "out of time"
OUT_OF_ATTEMPTS = "out of attempts"
NOT_RETRYABLE = "non-retryable error"
class RequestErrorInfo(
namedtuple(
"RequestErrorInfo_", "error error_message retry_delay http_code method request"
)
):
@property
def request_session_id(self):
if hasattr(self.request, "sessionHandle"):
return self.request.sessionHandle.sessionId.guid
else:
return None
@property
def request_query_id(self):
if hasattr(self.request, "operationHandle"):
return self.request.operationHandle.operationId.guid
else:
return None
def full_info_logging_context(
self, no_retry_reason, attempt, max_attempts, elapsed, max_duration
):
log_base_data_dict = OrderedDict(
[
("method", self.method),
("session-id", self.request_session_id),
("query-id", self.request_query_id),
("http-code", self.http_code),
("error-message", self.error_message),
("original-exception", str(self.error)),
]
)
log_base_data_dict["no-retry-reason"] = (
no_retry_reason and no_retry_reason.value
)
log_base_data_dict["bounded-retry-delay"] = self.retry_delay
log_base_data_dict["attempt"] = "{}/{}".format(attempt, max_attempts)
log_base_data_dict["elapsed-seconds"] = "{}/{}".format(elapsed, max_duration)
return log_base_data_dict
def user_friendly_error_message(self, no_retry_reason, attempt, elapsed):
# This should be kept at the level that is appropriate to return to a Redash user
user_friendly_error_message = "Error during request to server"
if self.error_message:
user_friendly_error_message = "{}: {}".format(
user_friendly_error_message, self.error_message
)
try:
error_context = str(self.error)
except:
error_context = DEFAULT_ERROR_CONTEXT
return user_friendly_error_message + ". " + error_context
# Taken from PyHive
class ParamEscaper:
_DATE_FORMAT = "%Y-%m-%d"
_TIME_FORMAT = "%H:%M:%S.%f %z"
_DATETIME_FORMAT = "{} {}".format(_DATE_FORMAT, _TIME_FORMAT)
def escape_args(self, parameters):
if isinstance(parameters, dict):
return {k: self.escape_item(v) for k, v in parameters.items()}
elif isinstance(parameters, (list, tuple)):
return tuple(self.escape_item(x) for x in parameters)
else:
raise exc.ProgrammingError(
"Unsupported param format: {}".format(parameters)
)
def escape_number(self, item):
return item
def escape_string(self, item):
# Need to decode UTF-8 because of old sqlalchemy.
# Newer SQLAlchemy checks dialect.supports_unicode_binds before encoding Unicode strings
# as byte strings. The old version always encodes Unicode as byte strings, which breaks
# string formatting here.
if isinstance(item, bytes):
item = item.decode("utf-8")
# This is good enough when backslashes are literal, newlines are just followed, and the way
# to escape a single quote is to put two single quotes.
# (i.e. only special character is single quote)
return "'{}'".format(item.replace("\\", "\\\\").replace("'", "\\'"))
def escape_sequence(self, item):
l = map(self.escape_item, item)
l = list(map(str, l))
return "ARRAY(" + ",".join(l) + ")"
def escape_mapping(self, item):
l = map(
self.escape_item,
(element for key, value in item.items() for element in (key, value)),
)
l = list(map(str, l))
return "MAP(" + ",".join(l) + ")"
def escape_datetime(self, item, format, cutoff=0):
dt_str = item.strftime(format)
formatted = dt_str[:-cutoff] if cutoff and format.endswith(".%f") else dt_str
return "'{}'".format(formatted.strip())
def escape_decimal(self, item):
return str(item)
def escape_item(self, item):
if item is None:
return "NULL"
elif isinstance(item, (int, float)):
return self.escape_number(item)
elif isinstance(item, str):
return self.escape_string(item)
elif isinstance(item, datetime.datetime):
return self.escape_datetime(item, self._DATETIME_FORMAT)
elif isinstance(item, datetime.date):
return self.escape_datetime(item, self._DATE_FORMAT)
elif isinstance(item, decimal.Decimal):
return self.escape_decimal(item)
elif isinstance(item, Sequence):
return self.escape_sequence(item)
elif isinstance(item, Mapping):
return self.escape_mapping(item)
else:
raise exc.ProgrammingError("Unsupported object {}".format(item))
def inject_parameters(operation: str, parameters: Dict[str, str]):
return operation % parameters
def _dbsqlparameter_names(params: List[TDbsqlParameter]) -> list[str]:
return [p.name if p.name else "" for p in params]
def _generate_named_interpolation_values(
params: List[TDbsqlParameter],
) -> dict[str, str]:
"""Returns a dictionary of the form {name: ":name"} for each parameter in params"""
names = _dbsqlparameter_names(params)
return {name: f":{name}" for name in names}
def _may_contain_inline_positional_markers(operation: str) -> bool:
"""Check for the presence of `%s` in the operation string."""
interpolated = operation.replace("%s", "?")
return interpolated != operation
def _interpolate_named_markers(
operation: str, parameters: List[TDbsqlParameter]
) -> str:
"""Replace all instances of `%(param)s` in `operation` with `:param`.
If `operation` contains no instances of `%(param)s` then the input string is returned unchanged.
```
"SELECT * FROM table WHERE field = %(field)s and other_field = %(other_field)s"
```
Yields
```
SELECT * FROM table WHERE field = :field and other_field = :other_field
```
"""
_output_operation = operation
PYFORMAT_PARAMSTYLE_REGEX = r"%\((\w+)\)s"
pat = re.compile(PYFORMAT_PARAMSTYLE_REGEX)
NAMED_PARAMSTYLE_FMT = ":{}"
PYFORMAT_PARAMSTYLE_FMT = "%({})s"
pyformat_markers = pat.findall(operation)
for marker in pyformat_markers:
pyformat_marker = PYFORMAT_PARAMSTYLE_FMT.format(marker)
named_marker = NAMED_PARAMSTYLE_FMT.format(marker)
_output_operation = _output_operation.replace(pyformat_marker, named_marker)
return _output_operation
def transform_paramstyle(
operation: str,
parameters: List[TDbsqlParameter],
param_structure: ParameterStructure,
) -> str:
"""
Performs a Python string interpolation such that any occurence of `%(param)s` will be replaced with `:param`
This utility function is built to assist users in the transition between the default paramstyle in
this connector prior to version 3.0.0 (`pyformat`) and the new default paramstyle (`named`).
Args:
operation: The operation or SQL text to transform.
parameters: The parameters to use for the transformation.
Returns:
str
"""
output = operation
if (
param_structure == ParameterStructure.POSITIONAL
and _may_contain_inline_positional_markers(operation)
):
logger.warning(
"It looks like this query may contain un-named query markers like `%s`"
" This format is not supported when use_inline_params=False."
" Use `?` instead or set use_inline_params=True"
)
elif param_structure == ParameterStructure.NAMED:
output = _interpolate_named_markers(operation, parameters)
return output
def create_arrow_table_from_arrow_file(
file_bytes: bytes, description
) -> "pyarrow.Table":
arrow_table = convert_arrow_based_file_to_arrow_table(file_bytes)
return convert_decimals_in_arrow_table(arrow_table, description)
def convert_arrow_based_file_to_arrow_table(file_bytes: bytes):
try:
return pyarrow.ipc.open_stream(file_bytes).read_all()
except Exception as e:
raise RuntimeError("Failure to convert arrow based file to arrow table", e)
def convert_arrow_based_set_to_arrow_table(arrow_batches, lz4_compressed, schema_bytes):
ba = bytearray()
ba += schema_bytes
n_rows = 0
for arrow_batch in arrow_batches:
n_rows += arrow_batch.rowCount
ba += (
lz4.frame.decompress(arrow_batch.batch)
if lz4_compressed
else arrow_batch.batch
)
arrow_table = pyarrow.ipc.open_stream(ba).read_all()
return arrow_table, n_rows
def convert_decimals_in_arrow_table(table, description) -> "pyarrow.Table":
new_columns = []
new_fields = []
for i, col in enumerate(table.itercolumns()):
field = table.field(i)
if description[i][1] == "decimal":
precision, scale = description[i][4], description[i][5]
assert scale is not None
assert precision is not None
# create the target decimal type
dtype = pyarrow.decimal128(precision, scale)
new_col = col.cast(dtype)
new_field = field.with_type(dtype)
new_columns.append(new_col)
new_fields.append(new_field)
else:
new_columns.append(col)
new_fields.append(field)
new_schema = pyarrow.schema(new_fields)
return pyarrow.Table.from_arrays(new_columns, schema=new_schema)
def convert_to_assigned_datatypes_in_column_table(column_table, description):
converted_column_table = []
for i, col in enumerate(column_table):
if description[i][1] == "decimal":
converted_column_table.append(
tuple(v if v is None else Decimal(v) for v in col)
)
elif description[i][1] == "date":
converted_column_table.append(
tuple(v if v is None else datetime.date.fromisoformat(v) for v in col)
)
elif description[i][1] == "timestamp":
converted_column_table.append(
tuple((v if v is None else parser.parse(v)) for v in col)
)
else:
converted_column_table.append(col)
return converted_column_table
def convert_column_based_set_to_arrow_table(columns, description):
arrow_table = pyarrow.Table.from_arrays(
[_convert_column_to_arrow_array(c) for c in columns],
# Only use the column names from the schema, the types are determined by the
# physical types used in column based set, as they can differ from the
# mapping used in _hive_schema_to_arrow_schema.
names=[c[0] for c in description],
)
return arrow_table, arrow_table.num_rows
def convert_column_based_set_to_column_table(columns, description):
column_names = [c[0] for c in description]
column_table = [_convert_column_to_list(c) for c in columns]
return column_table, column_names
def _convert_column_to_arrow_array(t_col):
"""
Return a pyarrow array from the values in a TColumn instance.
Note that ColumnBasedSet has no native support for complex types, so they will be converted
to strings server-side.
"""
field_name_to_arrow_type = {
"boolVal": pyarrow.bool_(),
"byteVal": pyarrow.int8(),
"i16Val": pyarrow.int16(),
"i32Val": pyarrow.int32(),
"i64Val": pyarrow.int64(),
"doubleVal": pyarrow.float64(),
"stringVal": pyarrow.string(),
"binaryVal": pyarrow.binary(),
}
for field in field_name_to_arrow_type.keys():
wrapper = getattr(t_col, field)
if wrapper:
return _create_arrow_array(wrapper, field_name_to_arrow_type[field])
raise OperationalError("Empty TColumn instance {}".format(t_col))
def _convert_column_to_list(t_col):
SUPPORTED_FIELD_TYPES = (
"boolVal",
"byteVal",
"i16Val",
"i32Val",
"i64Val",
"doubleVal",
"stringVal",
"binaryVal",
)
for field in SUPPORTED_FIELD_TYPES:
wrapper = getattr(t_col, field)
if wrapper:
return _create_python_tuple(wrapper)
raise OperationalError("Empty TColumn instance {}".format(t_col))
def _create_arrow_array(t_col_value_wrapper, arrow_type):
result = t_col_value_wrapper.values
nulls = t_col_value_wrapper.nulls # bitfield describing which values are null
assert isinstance(nulls, bytes)
# The number of bits in nulls can be both larger or smaller than the number of
# elements in result, so take the minimum of both to iterate over.
length = min(len(result), len(nulls) * 8)
for i in range(length):
if nulls[i >> 3] & BIT_MASKS[i & 0x7]:
result[i] = None
return pyarrow.array(result, type=arrow_type)
def _create_python_tuple(t_col_value_wrapper):
result = t_col_value_wrapper.values
nulls = t_col_value_wrapper.nulls # bitfield describing which values are null
assert isinstance(nulls, bytes)
# The number of bits in nulls can be both larger or smaller than the number of
# elements in result, so take the minimum of both to iterate over.
length = min(len(result), len(nulls) * 8)
for i in range(length):
if nulls[i >> 3] & BIT_MASKS[i & 0x7]:
result[i] = None
return tuple(result)
def concat_table_chunks(
table_chunks: List[Union["pyarrow.Table", ColumnTable]]
) -> Union["pyarrow.Table", ColumnTable]:
if len(table_chunks) == 0:
return table_chunks
if isinstance(table_chunks[0], ColumnTable):
## Check if all have the same column names
if not all(
table.column_names == table_chunks[0].column_names for table in table_chunks
):
raise ValueError("The columns in the results don't match")
result_table: List[List[Any]] = [[] for _ in range(table_chunks[0].num_columns)]
for i in range(0, len(table_chunks)):
for j in range(table_chunks[i].num_columns):
result_table[j].extend(table_chunks[i].column_table[j])
return ColumnTable(result_table, table_chunks[0].column_names)
else:
return pyarrow.concat_tables(table_chunks, use_threads=True)
def build_client_context(server_hostname: str, version: str, **kwargs):
"""Build ClientContext for HTTP client configuration."""
from databricks.sql.auth.common import ClientContext
from databricks.sql.types import SSLOptions
# Extract SSL options
ssl_options = SSLOptions(
tls_verify=not kwargs.get("_tls_no_verify", False),
tls_verify_hostname=kwargs.get("_tls_verify_hostname", True),
tls_trusted_ca_file=kwargs.get("_tls_trusted_ca_file"),
tls_client_cert_file=kwargs.get("_tls_client_cert_file"),
tls_client_cert_key_file=kwargs.get("_tls_client_cert_key_file"),
tls_client_cert_key_password=kwargs.get("_tls_client_cert_key_password"),
)
# Build user agent
user_agent_entry = kwargs.get("user_agent_entry", "")
if user_agent_entry:
user_agent = f"PyDatabricksSqlConnector/{version} ({user_agent_entry})"
else:
user_agent = f"PyDatabricksSqlConnector/{version}"
# Explicitly construct ClientContext with proper types
return ClientContext(
hostname=server_hostname,
ssl_options=ssl_options,
user_agent=user_agent,
socket_timeout=kwargs.get("_socket_timeout"),
retry_stop_after_attempts_count=kwargs.get("_retry_stop_after_attempts_count"),
retry_delay_min=kwargs.get("_retry_delay_min"),
retry_delay_max=kwargs.get("_retry_delay_max"),
retry_stop_after_attempts_duration=kwargs.get(
"_retry_stop_after_attempts_duration"
),
retry_delay_default=kwargs.get("_retry_delay_default"),
retry_dangerous_codes=kwargs.get("_retry_dangerous_codes"),
proxy_auth_method=kwargs.get("_proxy_auth_method"),
pool_connections=kwargs.get("_pool_connections"),
pool_maxsize=kwargs.get("_pool_maxsize"),
)