assemblyline-core 4.7.5.dev13__tar.gz → 4.7.5.dev16__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (80) hide show
  1. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/PKG-INFO +1 -1
  2. assemblyline_core-4.7.5.dev16/assemblyline_core/VERSION +1 -0
  3. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/expiry/run_expiry.py +33 -21
  4. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core.egg-info/PKG-INFO +1 -1
  5. assemblyline_core-4.7.5.dev13/assemblyline_core/VERSION +0 -1
  6. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/LICENCE.md +0 -0
  7. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/README.md +0 -0
  8. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/__init__.py +0 -0
  9. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/alerter/__init__.py +0 -0
  10. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/alerter/processing.py +0 -0
  11. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/alerter/run_alerter.py +0 -0
  12. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/archiver/__init__.py +0 -0
  13. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/archiver/run_archiver.py +0 -0
  14. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/badlist_client.py +0 -0
  15. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/dispatching/__init__.py +0 -0
  16. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/dispatching/client.py +0 -0
  17. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/dispatching/dispatcher.py +0 -0
  18. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/dispatching/schedules.py +0 -0
  19. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/expiry/__init__.py +0 -0
  20. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/ingester/__init__.py +0 -0
  21. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/ingester/constants.py +0 -0
  22. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/ingester/ingester.py +0 -0
  23. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/metrics/__init__.py +0 -0
  24. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/metrics/es_metrics.py +0 -0
  25. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/metrics/heartbeat_formatter.py +0 -0
  26. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/metrics/helper.py +0 -0
  27. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/metrics/metrics_server.py +0 -0
  28. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/metrics/run_heartbeat_manager.py +0 -0
  29. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/metrics/run_metrics_aggregator.py +0 -0
  30. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/metrics/run_statistics_aggregator.py +0 -0
  31. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/replay/__init__.py +0 -0
  32. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/replay/client.py +0 -0
  33. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/replay/creator/__init__.py +0 -0
  34. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/replay/creator/run.py +0 -0
  35. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/replay/creator/run_worker.py +0 -0
  36. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/replay/loader/__init__.py +0 -0
  37. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/replay/loader/run.py +0 -0
  38. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/replay/loader/run_worker.py +0 -0
  39. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/replay/replay.py +0 -0
  40. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/safelist_client.py +0 -0
  41. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/scaler/__init__.py +0 -0
  42. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/scaler/collection.py +0 -0
  43. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/scaler/controllers/__init__.py +0 -0
  44. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/scaler/controllers/docker_ctl.py +0 -0
  45. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/scaler/controllers/interface.py +0 -0
  46. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/scaler/controllers/kubernetes_ctl.py +0 -0
  47. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/scaler/run_scaler.py +0 -0
  48. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/scaler/scaler_server.py +0 -0
  49. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/server_base.py +0 -0
  50. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/signature_client.py +0 -0
  51. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/submission_client.py +0 -0
  52. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/tasking_client.py +0 -0
  53. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/updater/__init__.py +0 -0
  54. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/updater/helper.py +0 -0
  55. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/updater/run_updater.py +0 -0
  56. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/vacuum/__init__.py +0 -0
  57. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/vacuum/crawler.py +0 -0
  58. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/vacuum/department_map.py +0 -0
  59. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/vacuum/safelist.py +0 -0
  60. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/vacuum/stream_map.py +0 -0
  61. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/vacuum/worker.py +0 -0
  62. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/workflow/__init__.py +0 -0
  63. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core/workflow/run_workflow.py +0 -0
  64. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core.egg-info/SOURCES.txt +0 -0
  65. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core.egg-info/dependency_links.txt +0 -0
  66. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core.egg-info/requires.txt +0 -0
  67. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/assemblyline_core.egg-info/top_level.txt +0 -0
  68. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/setup.cfg +0 -0
  69. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/setup.py +0 -0
  70. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/test/test_alerter.py +0 -0
  71. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/test/test_badlist_client.py +0 -0
  72. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/test/test_expiry.py +0 -0
  73. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/test/test_replay.py +0 -0
  74. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/test/test_safelist_client.py +0 -0
  75. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/test/test_scaler.py +0 -0
  76. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/test/test_scheduler.py +0 -0
  77. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/test/test_signature_client.py +0 -0
  78. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/test/test_tasking_client.py +0 -0
  79. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/test/test_vacuum.py +0 -0
  80. {assemblyline_core-4.7.5.dev13 → assemblyline_core-4.7.5.dev16}/test/test_workflow.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: assemblyline-core
3
- Version: 4.7.5.dev13
3
+ Version: 4.7.5.dev16
4
4
  Summary: Assemblyline 4 - Core components
5
5
  Home-page: https://github.com/CybercentreCanada/assemblyline-core/
6
6
  Author: CCCS Assemblyline development team
@@ -0,0 +1 @@
1
+ 4.7.5.dev16
@@ -14,7 +14,7 @@ from datemath import dm
14
14
 
15
15
  from assemblyline_core.server_base import ServerBase
16
16
  from assemblyline_core.dispatching.dispatcher import BAD_SID_HASH
17
- from assemblyline.common import forge
17
+ from assemblyline.common import forge, chunk
18
18
  from assemblyline.common.isotime import epoch_to_iso, now_as_iso
19
19
  from assemblyline.common.metrics import MetricsFactory
20
20
  from assemblyline.filestore import FileStore
@@ -27,7 +27,8 @@ if TYPE_CHECKING:
27
27
  from assemblyline.datastore.collection import ESCollection
28
28
 
29
29
 
30
- def file_delete_worker(logger, filestore_urls, file_batch, archive_filestore_urls=None) -> list[tuple[str, bool]]:
30
+ def file_delete_worker(logger, filestore_urls, file_batch: list[tuple[str, bool]],
31
+ archive_filestore_urls=None) -> list[tuple[str, bool]]:
31
32
  try:
32
33
  filestore = FileStore(*filestore_urls)
33
34
  if archive_filestore_urls and filestore_urls != archive_filestore_urls:
@@ -35,37 +36,48 @@ def file_delete_worker(logger, filestore_urls, file_batch, archive_filestore_url
35
36
  else:
36
37
  archivestore = filestore
37
38
 
38
- def filestore_delete(item: tuple[str, bool]) -> tuple[Optional[str], Optional[bool]]:
39
- sha256, from_archive = item
40
- if from_archive:
41
- archivestore.delete(sha256)
42
- if not archivestore.exists(sha256):
43
- return sha256, True
44
- else:
45
- filestore.delete(sha256)
46
- if not filestore.exists(sha256):
47
- return sha256, False
48
- return None, None
49
-
50
- return _file_delete_worker(logger, filestore_delete, file_batch)
39
+ return _file_delete_worker(logger, filestore, archivestore, file_batch)
51
40
 
52
41
  except Exception as error:
53
42
  logger.exception("Error in filestore worker: " + str(error))
54
43
  return []
55
44
 
56
45
 
57
- ActionSignature = Callable[[tuple[str, bool]], tuple[Optional[str], Optional[bool]]]
46
+ def _confirm_delete(store, from_archive, sha256: str) -> tuple[Optional[str], Optional[bool]]:
47
+ if not store.exists(sha256):
48
+ return sha256, from_archive
49
+ return None, None
58
50
 
59
51
 
60
- def _file_delete_worker(logger, delete_action: ActionSignature, file_batch) -> list[tuple[str, bool]]:
52
+ def _file_delete_worker(logger, filestore, archivestore, file_batch: list[tuple[str, bool]]) -> list[tuple[str, bool]]:
61
53
  finished_files: list[tuple[str, bool]] = []
62
54
  try:
63
- futures = []
64
55
 
65
- with ThreadPoolExecutor(8) as pool:
66
- for filename in file_batch:
67
- futures.append(pool.submit(delete_action, filename))
56
+ with ThreadPoolExecutor(16) as pool:
57
+ # Delete the two batches in parallel if needed
58
+ futures: list[Future] = []
59
+ archive_files = [sha256 for sha256, from_archive in file_batch if from_archive]
60
+ hot_files = [sha256 for sha256, from_archive in file_batch if not from_archive]
61
+ futures.extend(
62
+ pool.submit(archivestore.delete_batch, batch)
63
+ for batch in chunk.chunk(archive_files, archivestore.delete_batch_chunk_size())
64
+ )
65
+ futures.extend(
66
+ pool.submit(filestore.delete_batch, batch)
67
+ for batch in chunk.chunk(hot_files, filestore.delete_batch_chunk_size())
68
+ )
69
+
70
+ for future in as_completed(futures):
71
+ try:
72
+ future.result()
73
+ except Exception as error:
74
+ logger.exception("Error in filestore worker: " + str(error))
68
75
 
76
+ # It is CRITICALLY IMPORTANT that we don't delete the file records
77
+ # for files that do exists, confirm that we have actually deleted files
78
+ # before we procede with removing the datastore records
79
+ futures = [pool.submit(_confirm_delete, filestore, False, filename) for filename in hot_files]
80
+ futures.extend(pool.submit(_confirm_delete, archivestore, True, filename) for filename in archive_files)
69
81
  for future in as_completed(futures):
70
82
  try:
71
83
  erased_name, from_archive = future.result()
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: assemblyline-core
3
- Version: 4.7.5.dev13
3
+ Version: 4.7.5.dev16
4
4
  Summary: Assemblyline 4 - Core components
5
5
  Home-page: https://github.com/CybercentreCanada/assemblyline-core/
6
6
  Author: CCCS Assemblyline development team
@@ -1 +0,0 @@
1
- 4.7.5.dev13