-
Notifications
You must be signed in to change notification settings - Fork 308
/
utils.py
2192 lines (1823 loc) · 76.4 KB
/
utils.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
# -*- coding: utf-8 -*-
# Copyright European Organization for Nuclear Research (CERN) since 2012
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import argparse
import base64
import copy
import datetime
import errno
import getpass
import hashlib
import io
import ipaddress
import itertools
import json
import logging
import os
import os.path
import re
import signal
import socket
import subprocess
import tempfile
import threading
import time
from collections import OrderedDict
from configparser import NoOptionError, NoSectionError
from enum import Enum
from functools import partial, wraps
from io import StringIO
from itertools import zip_longest
from typing import Any, Callable, Optional, TYPE_CHECKING
from urllib.parse import urlparse, urlencode, quote, parse_qsl, urlunparse
from uuid import uuid4 as uuid
from xml.etree import ElementTree
import math
import mmap
import requests
import zlib
from rucio.common.config import config_get, config_has_section
from rucio.common.exception import MissingModuleException, InvalidType, InputValidationError, MetalinkJsonParsingError, RucioException, \
DuplicateCriteriaInDIDFilter, DIDFilterSyntaxError, InvalidAlgorithmName, PolicyPackageVersionError
from rucio.common.extra import import_extras
from rucio.common.types import InternalAccount, InternalScope
EXTRA_MODULES = import_extras(['paramiko'])
if EXTRA_MODULES['paramiko']:
try:
from paramiko import RSAKey
except Exception:
EXTRA_MODULES['paramiko'] = False
if TYPE_CHECKING:
from typing import TypeVar
T = TypeVar('T')
# HTTP code dictionary. Not complete. Can be extended if needed.
codes = {
# Informational.
200: '200 OK',
201: '201 Created',
202: '202 Accepted',
# Client Error.
400: '400 Bad Request',
401: '401 Unauthorized',
403: '403 Forbidden',
404: '404 Not Found',
405: '405 Method Not Allowed',
406: '406 Not Acceptable',
408: '408 Request Timeout',
409: '409 Conflict',
410: '410 Gone',
# Server Error.
500: '500 Internal Server Error',
501: '501 Not Implemented',
502: '502 Bad Gateway',
503: '503 Service Unavailable',
504: '504 Gateway Timeout'
}
# RFC 1123 (ex RFC 822)
DATE_FORMAT = '%a, %d %b %Y %H:%M:%S UTC'
def invert_dict(d):
"""
Invert the dictionary.
CAUTION: this function is not deterministic unless the input dictionary is one-to-one mapping.
:param d: source dictionary
:returns: dictionary {value: key for key, value in d.items()}
"""
return {value: key for key, value in d.items()}
def dids_as_dicts(did_list):
"""
Converts list of DIDs to list of dictionaries
:param did_list: list of DIDs as either "scope:name" or {"scope":"scope", "name","name"}
:returns: list of dictionaries {"scope":"scope", "name","name"}
"""
out = []
for did in did_list:
if isinstance(did, str):
scope, name = did.split(":", 1)
did = dict(scope=scope, name=name)
if isinstance(did, dict):
if not ("name" in did and "scope" in did):
raise ValueError("Scope or name missing in: %s" % (did,))
else:
raise ValueError("Can not convert item %s (%s) to a DID" % (did, type(did)))
out.append(did)
return out
def build_url(url, path=None, params=None, doseq=False):
"""
utitily function to build an url for requests to the rucio system.
If the optional parameter doseq is evaluates to True, individual key=value pairs
separated by '&' are generated for each element of the value sequence for the key.
"""
complete_url = url
if path is not None:
complete_url += "/" + path
if params is not None:
complete_url += "?"
if isinstance(params, str):
complete_url += quote(params)
else:
complete_url += urlencode(params, doseq=doseq)
return complete_url
def all_oidc_req_claims_present(scope, audience, required_scope, required_audience, sepatator=" "):
"""
Checks if both of the following statements are true:
- all items in required_scope are present in scope string
- all items in required_audience are present in audience
returns false otherwise. audience and scope must be both strings
or both lists. Similarly for required_* variables.
If this condition is satisfied, False is returned.
:params scope: list of strings or one string where items are separated by a separator input variable
:params audience: list of strings or one string where items are separated by a separator input variable
:params required_scope: list of strings or one string where items are separated by a separator input variable
:params required_audience: list of strings or one string where items are separated by a separator input variable
:params sepatator: separator string, space by default
:returns : True or False
"""
if not scope:
scope = ""
if not audience:
audience = ""
if not required_scope:
required_scope = ""
if not required_audience:
required_audience = ""
if (isinstance(scope, list) and isinstance(audience, list) and isinstance(required_scope, list) and isinstance(required_audience, list)):
scope = [str(it) for it in scope]
audience = [str(it) for it in audience]
required_scope = [str(it) for it in required_scope]
required_audience = [str(it) for it in required_audience]
req_scope_present = all(elem in scope for elem in required_scope)
req_audience_present = all(elem in audience for elem in required_audience)
return req_scope_present and req_audience_present
elif (isinstance(scope, str) and isinstance(audience, str) and isinstance(required_scope, str) and isinstance(required_audience, str)):
scope = str(scope)
audience = str(audience)
required_scope = str(required_scope)
required_audience = str(required_audience)
req_scope_present = all(elem in scope.split(sepatator) for elem in required_scope.split(sepatator))
req_audience_present = all(elem in audience.split(sepatator) for elem in required_audience.split(sepatator))
return req_scope_present and req_audience_present
elif (isinstance(scope, list) and isinstance(audience, list) and isinstance(required_scope, str) and isinstance(required_audience, str)):
scope = [str(it) for it in scope]
audience = [str(it) for it in audience]
required_scope = str(required_scope)
required_audience = str(required_audience)
req_scope_present = all(elem in scope for elem in required_scope.split(sepatator))
req_audience_present = all(elem in audience for elem in required_audience.split(sepatator))
return req_scope_present and req_audience_present
elif (isinstance(scope, str) and isinstance(audience, str) and isinstance(required_scope, list) and isinstance(required_audience, list)):
scope = str(scope)
audience = str(audience)
required_scope = [str(it) for it in required_scope]
required_audience = [str(it) for it in required_audience]
req_scope_present = all(elem in scope.split(sepatator) for elem in required_scope)
req_audience_present = all(elem in audience.split(sepatator) for elem in required_audience)
return req_scope_present and req_audience_present
else:
return False
def generate_uuid():
return str(uuid()).replace('-', '').lower()
def generate_uuid_bytes():
return uuid().bytes
# GLOBALLY_SUPPORTED_CHECKSUMS = ['adler32', 'md5', 'sha256', 'crc32']
GLOBALLY_SUPPORTED_CHECKSUMS = ['adler32', 'md5']
CHECKSUM_ALGO_DICT = {}
PREFERRED_CHECKSUM = GLOBALLY_SUPPORTED_CHECKSUMS[0]
CHECKSUM_KEY = 'supported_checksums'
def is_checksum_valid(checksum_name):
"""
A simple function to check wether a checksum algorithm is supported.
Relies on GLOBALLY_SUPPORTED_CHECKSUMS to allow for expandability.
:param checksum_name: The name of the checksum to be verified.
:returns: True if checksum_name is in GLOBALLY_SUPPORTED_CHECKSUMS list, False otherwise.
"""
return checksum_name in GLOBALLY_SUPPORTED_CHECKSUMS
def set_preferred_checksum(checksum_name):
"""
A simple function to check wether a checksum algorithm is supported.
Relies on GLOBALLY_SUPPORTED_CHECKSUMS to allow for expandability.
:param checksum_name: The name of the checksum to be verified.
:returns: True if checksum_name is in GLOBALLY_SUPPORTED_CHECKSUMS list, False otherwise.
"""
if is_checksum_valid(checksum_name):
global PREFERRED_CHECKSUM
PREFERRED_CHECKSUM = checksum_name
def adler32(file):
"""
An Adler-32 checksum is obtained by calculating two 16-bit checksums A and B
and concatenating their bits into a 32-bit integer. A is the sum of all bytes in the
stream plus one, and B is the sum of the individual values of A from each step.
:param file: file name
:returns: Hexified string, padded to 8 values.
"""
# adler starting value is _not_ 0
adler = 1
can_mmap = False
# try:
# with open(file, 'r+b') as f:
# can_mmap = True
# except:
# pass
try:
# use mmap if possible
if can_mmap:
with open(file, 'r+b') as f:
m = mmap.mmap(f.fileno(), 0)
# partial block reads at slightly increased buffer sizes
for block in iter(partial(m.read, io.DEFAULT_BUFFER_SIZE * 8), b''):
adler = zlib.adler32(block, adler)
else:
with open(file, 'rb') as f:
# partial block reads at slightly increased buffer sizes
for block in iter(partial(f.read, io.DEFAULT_BUFFER_SIZE * 8), b''):
adler = zlib.adler32(block, adler)
except Exception as e:
raise Exception('FATAL - could not get Adler-32 checksum of file %s: %s' % (file, e))
# backflip on 32bit -- can be removed once everything is fully migrated to 64bit
if adler < 0:
adler = adler + 2 ** 32
return str('%08x' % adler)
CHECKSUM_ALGO_DICT['adler32'] = adler32
def md5(file):
"""
Runs the MD5 algorithm (RFC-1321) on the binary content of the file named file and returns the hexadecimal digest
:param file: file name
:returns: string of 32 hexadecimal digits
"""
hash_md5 = hashlib.md5()
try:
with open(file, "rb") as f:
list(map(hash_md5.update, iter(lambda: f.read(4096), b"")))
except Exception as e:
raise Exception('FATAL - could not get MD5 checksum of file %s - %s' % (file, e))
return hash_md5.hexdigest()
CHECKSUM_ALGO_DICT['md5'] = md5
def sha256(file):
"""
Runs the SHA256 algorithm on the binary content of the file named file and returns the hexadecimal digest
:param file: file name
:returns: string of 32 hexadecimal digits
"""
with open(file, "rb") as f:
bytes_ = f.read() # read entire file as bytes
readable_hash = hashlib.sha256(bytes_).hexdigest()
print(readable_hash)
return readable_hash
CHECKSUM_ALGO_DICT['sha256'] = sha256
def crc32(file):
"""
Runs the CRC32 algorithm on the binary content of the file named file and returns the hexadecimal digest
:param file: file name
:returns: string of 32 hexadecimal digits
"""
prev = 0
for eachLine in open(file, "rb"):
prev = zlib.crc32(eachLine, prev)
return "%X" % (prev & 0xFFFFFFFF)
CHECKSUM_ALGO_DICT['crc32'] = crc32
def _next_pow2(num):
if not num:
return 0
return math.ceil(math.log2(num))
def _bittorrent_v2_piece_length_pow2(file_size: int) -> int:
"""
Automatically chooses the `piece size` so that `piece layers`
is kept small(er) than usually. This is a balancing act:
having a big piece_length requires more work on bittorrent client
side to validate hashes, but having it small requires more
place to store the `piece layers` in the database.
Returns the result as the exponent 'x' for power of 2.
To get the actual length in bytes, the caller should compute 2^x.
"""
# by the bittorrent v2 specification, the piece size is equal to block size = 16KiB
min_piece_len_pow2 = 14 # 2 ** 14 == 16 KiB
if not file_size:
return min_piece_len_pow2
# Limit the maximum size of pieces_layers hash chain for bittorrent v2,
# because we'll have to store it in the database
max_pieces_layers_size_pow2 = 20 # 2 ** 20 == 1 MiB
# sha256 requires 2 ** 5 == 32 Bytes == 256 bits
hash_size_pow2 = 5
# The closest power of two bigger than the file size
file_size_pow2 = _next_pow2(file_size)
# Compute the target size for the 'pieces layers' in the torrent
# (as power of two: the closest power-of-two smaller than the number)
# Will cap at max_pieces_layers_size for files larger than 1TB.
target_pieces_layers_size = math.sqrt(file_size)
target_pieces_layers_size_pow2 = min(math.floor(math.log2(target_pieces_layers_size)), max_pieces_layers_size_pow2)
target_piece_num_pow2 = max(target_pieces_layers_size_pow2 - hash_size_pow2, 0)
piece_length_pow2 = max(file_size_pow2 - target_piece_num_pow2, min_piece_len_pow2)
return piece_length_pow2
def bittorrent_v2_piece_length(file_size: int) -> int:
return 2 ** _bittorrent_v2_piece_length_pow2(file_size)
def bittorrent_v2_merkle_sha256(file) -> tuple[bytes, bytes, int]:
"""
Compute the .torrent v2 hash tree for the given file.
(http://www.bittorrent.org/beps/bep_0052.html)
In particular, it will return the root of the merkle hash
tree of the file, the 'piece layers' as described in the
previous BEP, and the chosen `piece size`
This function will read the file in chunks of 16KiB
(which is the imposed block size by bittorrent v2) and compute
the sha256 hash of each block. When enough blocks are read
to form a `piece`, will compute the merkle hash root of the
piece from the hashes of its blocks. At the end, the hashes
of pieces are combined to create the global pieces_root.
"""
# by the bittorrent v2 specification, the block size and the
# minimum piece size are both fixed to 16KiB
block_size = 16384
block_size_pow2 = 14 # 2 ** 14 == 16 KiB
# sha256 requires 2 ** 5 == 32 Bytes == 256 bits
hash_size = 32
def _merkle_root(leafs: list[bytes], nb_levels: int, padding: bytes) -> bytes:
"""
Build the root of the merkle hash tree from the (possibly incomplete) leafs layer.
If len(leafs) < 2 ** nb_levels, it will be padded with the padding repeated as many times
as needed to have 2 ** nb_levels leafs in total.
"""
nodes = copy.copy(leafs)
level = nb_levels
while level > 0:
for i in range(2 ** (level - 1)):
node1 = nodes[2 * i] if 2 * i < len(nodes) else padding
node2 = nodes[2 * i + 1] if 2 * i + 1 < len(nodes) else padding
h = hashlib.sha256(node1)
h.update(node2)
if i < len(nodes):
nodes[i] = h.digest()
else:
nodes.append(h.digest())
level -= 1
return nodes[0] if nodes else padding
file_size = os.stat(file).st_size
piece_length_pow2 = _bittorrent_v2_piece_length_pow2(file_size)
block_per_piece_pow2 = piece_length_pow2 - block_size_pow2
piece_length = 2 ** piece_length_pow2
block_per_piece = 2 ** block_per_piece_pow2
piece_num = math.ceil(file_size / piece_length)
remaining = file_size
remaining_in_block = min(file_size, block_size)
block_hashes = []
piece_hashes = []
current_hash = hashlib.sha256()
block_padding = bytes(hash_size)
with open(file, 'rb') as f:
while True:
data = f.read(remaining_in_block)
if not data:
break
current_hash.update(data)
remaining_in_block -= len(data)
remaining -= len(data)
if not remaining_in_block:
block_hashes.append(current_hash.digest())
if len(block_hashes) == block_per_piece or not remaining:
piece_hashes.append(_merkle_root(block_hashes, nb_levels=block_per_piece_pow2, padding=block_padding))
block_hashes = []
current_hash = hashlib.sha256()
remaining_in_block = min(block_size, remaining)
if not remaining:
break
if remaining or remaining_in_block or len(piece_hashes) != piece_num:
raise RucioException(f'Error while computing merkle sha256 of {file}')
piece_padding = _merkle_root([], nb_levels=block_per_piece_pow2, padding=block_padding)
pieces_root = _merkle_root(piece_hashes, nb_levels=_next_pow2(piece_num), padding=piece_padding)
pieces_layers = b''.join(piece_hashes) if len(piece_hashes) > 1 else b''
return pieces_root, pieces_layers, piece_length
def merkle_sha256(file) -> str:
"""
The root of the sha256 merkle hash tree with leaf size of 16 KiB.
"""
pieces_root, _, _ = bittorrent_v2_merkle_sha256(file)
return pieces_root.hex()
CHECKSUM_ALGO_DICT['merkle_sha256'] = merkle_sha256
def bencode(obj) -> bytes:
"""
Copied from the reference implementation of v2 bittorrent:
http://bittorrent.org/beps/bep_0052_torrent_creator.py
"""
if isinstance(obj, int):
return b"i" + str(obj).encode() + b"e"
elif isinstance(obj, bytes):
return str(len(obj)).encode() + b":" + obj
elif isinstance(obj, str):
return bencode(obj.encode("utf-8"))
elif isinstance(obj, list):
return b"l" + b"".join(map(bencode, obj)) + b"e"
elif isinstance(obj, dict):
if all(isinstance(i, bytes) for i in obj.keys()):
items = list(obj.items())
items.sort()
return b"d" + b"".join(map(bencode, itertools.chain(*items))) + b"e"
else:
raise ValueError("dict keys should be bytes " + str(obj.keys()))
raise ValueError("Allowed types: int, bytes, list, dict; not %s", type(obj))
def construct_torrent(
scope: str,
name: str,
length: int,
piece_length: int,
pieces_root: bytes,
pieces_layers: "Optional[bytes]" = None,
trackers: "Optional[list[str]]" = None,
) -> "tuple[str, bytes]":
torrent_dict = {
b'creation date': int(time.time()),
b'info': {
b'meta version': 2,
b'private': 1,
b'name': f'{scope}:{name}'.encode(),
b'piece length': piece_length,
b'file tree': {
name.encode(): {
b'': {
b'length': length,
b'pieces root': pieces_root,
}
}
}
},
b'piece layers': {},
}
if trackers:
torrent_dict[b'announce'] = trackers[0].encode()
if len(trackers) > 1:
torrent_dict[b'announce-list'] = [t.encode() for t in trackers]
if pieces_layers:
torrent_dict[b'piece layers'][pieces_root] = pieces_layers
torrent_id = hashlib.sha256(bencode(torrent_dict[b'info'])).hexdigest()[:40]
torrent = bencode(torrent_dict)
return torrent_id, torrent
def str_to_date(string):
""" Converts a RFC-1123 string to the corresponding datetime value.
:param string: the RFC-1123 string to convert to datetime value.
"""
return datetime.datetime.strptime(string, DATE_FORMAT) if string else None
def val_to_space_sep_str(vallist: Any) -> str:
""" Converts a list of values into a string of space separated values
:param vallist: the list of values to to convert into string
:return: the string of space separated values or the value initially passed as parameter
"""
try:
if isinstance(vallist, list):
return str(" ".join(vallist))
else:
return str(vallist)
except:
return str('')
def date_to_str(date):
""" Converts a datetime value to the corresponding RFC-1123 string.
:param date: the datetime value to convert.
"""
return datetime.datetime.strftime(date, DATE_FORMAT) if date else None
class APIEncoder(json.JSONEncoder):
""" Propretary JSONEconder subclass used by the json render function.
This is needed to address the encoding of special values.
"""
def default(self, obj): # pylint: disable=E0202
if isinstance(obj, datetime.datetime):
# convert any datetime to RFC 1123 format
return date_to_str(obj)
elif isinstance(obj, (datetime.time, datetime.date)):
# should not happen since the only supported date-like format
# supported at dmain schema level is 'datetime' .
return obj.isoformat()
elif isinstance(obj, datetime.timedelta):
return obj.days * 24 * 60 * 60 + obj.seconds
elif isinstance(obj, Enum):
return obj.name
elif isinstance(obj, (InternalAccount, InternalScope)):
return obj.external
return json.JSONEncoder.default(self, obj)
def render_json(**data):
""" JSON render function
"""
return json.dumps(data, cls=APIEncoder)
def render_json_list(list_):
""" JSON render function for list
"""
return json.dumps(list_, cls=APIEncoder)
def datetime_parser(dct):
""" datetime parser
"""
for k, v in list(dct.items()):
if isinstance(v, str) and re.search(" UTC", v):
try:
dct[k] = datetime.datetime.strptime(v, DATE_FORMAT)
except Exception:
pass
return dct
def parse_response(data):
"""
JSON render function
"""
if hasattr(data, 'decode'):
data = data.decode('utf-8')
return json.loads(data, object_hook=datetime_parser)
def execute(cmd) -> tuple[int, str, str]:
"""
Executes a command in a subprocess. Returns a tuple
of (exitcode, out, err), where out is the string output
from stdout and err is the string output from stderr when
executing the command.
:param cmd: Command string to execute
"""
process = subprocess.Popen(cmd,
shell=True,
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
result = process.communicate()
(out, err) = result
exitcode = process.returncode
return exitcode, out.decode(encoding='utf-8'), err.decode(encoding='utf-8')
def rse_supported_protocol_operations():
""" Returns a list with operations supported by all RSE protocols."""
return ['read', 'write', 'delete', 'third_party_copy_read', 'third_party_copy_write']
def rse_supported_protocol_domains():
""" Returns a list with all supoorted RSE protocol domains."""
return ['lan', 'wan']
def grouper(iterable, n, fillvalue=None):
""" Collect data into fixed-length chunks or blocks """
# grouper('ABCDEFG', 3, 'x') --> ABC DEF Gxx
args = [iter(iterable)] * n
return zip_longest(*args, fillvalue=fillvalue)
def chunks(iterable, n):
"""
Yield successive n-sized chunks from l.
"""
if isinstance(iterable, list):
for i in range(0, len(iterable), n):
yield iterable[i:i + n]
else:
it = iter(iterable)
while True:
chunk = list(itertools.islice(it, n))
if not chunk:
return
yield chunk
def dict_chunks(dict_, n):
"""
Iterate over the dictionary in groups of the requested size
"""
it = iter(dict_)
for _ in range(0, len(dict_), n):
yield {k: dict_[k] for k in itertools.islice(it, n)}
def my_key_generator(namespace, fn, **kw):
"""
Customyzed key generator for dogpile
"""
fname = fn.__name__
def generate_key(*arg, **kw):
return namespace + "_" + fname + "_".join(str(s) for s in filter(None, arg))
return generate_key
def construct_surl_DQ2(dsn: str, scope: str, filename: str) -> str:
"""
Defines relative SURL for new replicas. This method
contains DQ2 convention. To be used for non-deterministic sites.
Method imported from DQ2.
@return: relative SURL for new replica.
@rtype: str
"""
# check how many dots in dsn
fields = dsn.split('.')
nfields = len(fields)
if nfields == 0:
return '/other/other/%s' % (filename)
elif nfields == 1:
stripped_dsn = __strip_dsn(dsn)
return '/other/%s/%s' % (stripped_dsn, filename)
elif nfields == 2:
project = fields[0]
stripped_dsn = __strip_dsn(dsn)
return '/%s/%s/%s' % (project, stripped_dsn, filename)
elif nfields < 5 or re.match('user*|group*', fields[0]):
project = fields[0]
f2 = fields[1]
f3 = fields[2]
stripped_dsn = __strip_dsn(dsn)
return '/%s/%s/%s/%s/%s' % (project, f2, f3, stripped_dsn, filename)
else:
project = fields[0]
dataset_type = fields[4]
if nfields == 5:
tag = 'other'
else:
tag = __strip_tag(fields[-1])
stripped_dsn = __strip_dsn(dsn)
return '/%s/%s/%s/%s/%s' % (project, dataset_type, tag, stripped_dsn, filename)
def construct_surl_T0(dsn: str, scope: str, filename: str) -> str:
"""
Defines relative SURL for new replicas. This method
contains Tier0 convention. To be used for non-deterministic sites.
@return: relative SURL for new replica.
@rtype: str
"""
fields = dsn.split('.')
nfields = len(fields)
if nfields >= 3:
return '/%s/%s/%s/%s/%s' % (fields[0], fields[2], fields[1], dsn, filename)
elif nfields == 1:
return '/%s/%s/%s/%s/%s' % (fields[0], 'other', 'other', dsn, filename)
elif nfields == 2:
return '/%s/%s/%s/%s/%s' % (fields[0], fields[2], 'other', dsn, filename)
elif nfields == 0:
return '/other/other/other/other/%s' % (filename)
def construct_surl_BelleII(dsn: str, scope: str, filename: str) -> str:
"""
Defines relative SURL for Belle II specific replicas.
This method contains the Belle II convention.
To be used for non-deterministic Belle II sites.
DSN (or datablock in the Belle II naming) contains /
"""
fields = dsn.split("/")
nfields = len(fields)
if nfields == 0:
return '/other/%s' % (filename)
else:
return '%s/%s' % (dsn, filename)
_SURL_ALGORITHMS = {}
_DEFAULT_SURL = 'DQ2'
_loaded_policy_modules = False
def register_surl_algorithm(surl_callable, name=None):
if name is None:
name = surl_callable.__name__
_SURL_ALGORITHMS[name] = surl_callable
register_surl_algorithm(construct_surl_T0, 'T0')
register_surl_algorithm(construct_surl_DQ2, 'DQ2')
register_surl_algorithm(construct_surl_BelleII, 'BelleII')
def construct_surl(dsn: str, scope: str, filename: str, naming_convention: str = None) -> str:
"""
Applies non-deterministic source url convention to the given replica.
use the naming_convention to call the actual function which will do the job.
Rucio administrators can potentially register additional surl generation algorithms,
which are not implemented inside this main rucio repository, so changing the
argument list must be done with caution.
"""
global _loaded_policy_modules
if not _loaded_policy_modules:
# on first call, register any SURL functions from the policy packages
register_policy_package_algorithms('surl', _SURL_ALGORITHMS)
_loaded_policy_modules = True
if naming_convention is None or naming_convention not in _SURL_ALGORITHMS:
naming_convention = _DEFAULT_SURL
return _SURL_ALGORITHMS[naming_convention](dsn, scope, filename)
def __strip_dsn(dsn):
"""
Drop the _sub and _dis suffixes for panda datasets from the lfc path
they will be registered in.
Method imported from DQ2.
"""
suffixes_to_drop = ['_dis', '_sub', '_frag']
fields = dsn.split('.')
last_field = fields[-1]
try:
for suffix in suffixes_to_drop:
last_field = re.sub('%s.*$' % suffix, '', last_field)
except IndexError:
return dsn
fields[-1] = last_field
stripped_dsn = '.'.join(fields)
return stripped_dsn
def __strip_tag(tag):
"""
Drop the _sub and _dis suffixes for panda datasets from the lfc path
they will be registered in
Method imported from DQ2.
"""
suffixes_to_drop = ['_dis', '_sub', '_tid']
stripped_tag = tag
try:
for suffix in suffixes_to_drop:
stripped_tag = re.sub('%s.*$' % suffix, '', stripped_tag)
except IndexError:
return stripped_tag
return stripped_tag
def clean_surls(surls):
res = []
for surl in surls:
if surl.startswith('srm'):
surl = re.sub(':[0-9]+/', '/', surl)
surl = re.sub(r'/srm/managerv1\?SFN=', '', surl)
surl = re.sub(r'/srm/v2/server\?SFN=', '', surl)
surl = re.sub(r'/srm/managerv2\?SFN=', '', surl)
if '?GoogleAccessId' in surl:
surl = surl.split('?GoogleAccessId')[0]
if '?X-Amz' in surl:
surl = surl.split('?X-Amz')[0]
res.append(surl)
res.sort()
return res
_EXTRACT_SCOPE_ALGORITHMS = {}
_DEFAULT_EXTRACT = 'atlas'
_loaded_policy_package_scope_algorithms = False
def extract_scope_atlas(did, scopes):
# Try to extract the scope from the DSN
if did.find(':') > -1:
if len(did.split(':')) > 2:
raise RucioException('Too many colons. Cannot extract scope and name')
scope, name = did.split(':')[0], did.split(':')[1]
if name.endswith('/'):
name = name[:-1]
return scope, name
else:
scope = did.split('.')[0]
if did.startswith('user') or did.startswith('group'):
scope = ".".join(did.split('.')[0:2])
if did.endswith('/'):
did = did[:-1]
return scope, did
def extract_scope_dirac(did, scopes):
# Default dirac scope extract algorithm. Scope is the second element in the LFN or the first one (VO name)
# if only one element is the result of a split.
elem = did.rstrip('/').split('/')
if len(elem) > 2:
scope = elem[2]
else:
scope = elem[1]
return scope, did
def extract_scope_belleii(did, scopes):
split_did = did.split('/')
if did.startswith('/belle/mock/'):
return 'mock', did
if did.startswith('/belle/MC/'):
if did.startswith('/belle/MC/BG') or \
did.startswith('/belle/MC/build') or \
did.startswith('/belle/MC/generic') or \
did.startswith('/belle/MC/log') or \
did.startswith('/belle/MC/mcprod') or \
did.startswith('/belle/MC/prerelease') or \
did.startswith('/belle/MC/release'):
return 'mc', did
if did.startswith('/belle/MC/cert') or \
did.startswith('/belle/MC/dirac') or \
did.startswith('/belle/MC/dr3') or \
did.startswith('/belle/MC/fab') or \
did.startswith('/belle/MC/hideki') or \
did.startswith('/belle/MC/merge') or \
did.startswith('/belle/MC/migration') or \
did.startswith('/belle/MC/skim') or \
did.startswith('/belle/MC/test'):
return 'mc_tmp', did
if len(split_did) > 4:
if split_did[3].find('fab') > -1 or split_did[3].find('merge') > -1 or split_did[3].find('skim') > -1:
return 'mc_tmp', did
if split_did[3].find('release') > -1:
return 'mc', did
return 'mc_tmp', did
if did.startswith('/belle/Raw/'):
return 'raw', did
if did.startswith('/belle/hRaw'):
return 'hraw', did
if did.startswith('/belle/user/'):
if len(split_did) > 4:
if len(split_did[3]) == 1 and 'user.%s' % (split_did[4]) in scopes:
return 'user.%s' % split_did[4], did
if len(split_did) > 3:
if 'user.%s' % (split_did[3]) in scopes:
return 'user.%s' % split_did[3], did
return 'user', did
if did.startswith('/belle/group/'):
if len(split_did) > 4:
if 'group.%s' % (split_did[4]) in scopes:
return 'group.%s' % split_did[4], did
return 'group', did
if did.startswith('/belle/data/') or did.startswith('/belle/Data/'):
if len(split_did) > 4:
if split_did[3] in ['fab', 'skim']: # /belle/Data/fab --> data_tmp
return 'data_tmp', did
if split_did[3].find('release') > -1: # /belle/Data/release --> data
return 'data', did
if len(split_did) > 5:
if split_did[3] in ['proc']: # /belle/Data/proc
if split_did[4].find('release') > -1: # /belle/Data/proc/release*
if len(split_did) > 7 and split_did[6] in ['GCR2c', 'prod00000007', 'prod6b', 'proc7b',
'proc8b', 'Bucket4', 'Bucket6test', 'bucket6',
'proc9', 'bucket7', 'SKIMDATAx1', 'proc10Valid',
'proc10', 'SkimP10x1', 'SkimP11x1', 'SkimB9x1',
'SkimB10x1', 'SkimB11x1']: # /belle/Data/proc/release*/*/proc10/* --> data_tmp (Old convention)
return 'data_tmp', did
else: # /belle/Data/proc/release*/*/proc11/* --> data (New convention)
return 'data', did
if split_did[4].find('fab') > -1: # /belle/Data/proc/fab* --> data_tmp
return 'data_tmp', did
return 'data_tmp', did
if did.startswith('/belle/ddm/functional_tests/') or did.startswith('/belle/ddm/tests/') or did.startswith('/belle/test/ddm_test'):
return 'test', did
if did.startswith('/belle/BG/'):
return 'data', did
if did.startswith('/belle/collection'):
return 'collection', did
return 'other', did
def register_extract_scope_algorithm(extract_callable, name=[]):
if name is None: