orbitkit 0.8.42__tar.gz → 0.8.44__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 (78) hide show
  1. {orbitkit-0.8.42/orbitkit.egg-info → orbitkit-0.8.44}/PKG-INFO +1 -1
  2. orbitkit-0.8.44/orbitkit/VERSION +1 -0
  3. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/airflow_handler/file_flow_entry_process.py +4 -5
  4. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/airflow_handler/file_flow_exit_process.py +3 -2
  5. {orbitkit-0.8.42 → orbitkit-0.8.44/orbitkit.egg-info}/PKG-INFO +1 -1
  6. orbitkit-0.8.42/orbitkit/VERSION +0 -1
  7. {orbitkit-0.8.42 → orbitkit-0.8.44}/LICENSE +0 -0
  8. {orbitkit-0.8.42 → orbitkit-0.8.44}/MANIFEST.in +0 -0
  9. {orbitkit-0.8.42 → orbitkit-0.8.44}/README.md +0 -0
  10. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/__init__.py +0 -0
  11. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/airflow_handler/__init__.py +0 -0
  12. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/airflow_handler/data_preprocessing.py +0 -0
  13. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/airflow_handler/file_handler.py +0 -0
  14. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/airflow_handler/file_handler_v2.py +0 -0
  15. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/audio_transcoder/__init__.py +0 -0
  16. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/audio_transcoder/netmind_extract_v1.py +0 -0
  17. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/constant/__init__.py +0 -0
  18. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/constant/report_schema.py +0 -0
  19. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/id_srv/__init__.py +0 -0
  20. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/id_srv/id_gen.py +0 -0
  21. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/id_srv/id_perm_like.py +0 -0
  22. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/lark_send/__init__.py +0 -0
  23. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/lark_send/lark.py +0 -0
  24. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/llm_tools/__init__.py +0 -0
  25. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/llm_tools/quick_rag_chat.py +0 -0
  26. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/orbit_type/__init__.py +0 -0
  27. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/orbit_type/doc_4_compile_rule.py +0 -0
  28. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/orbit_type/orbit_type_simple.py +0 -0
  29. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/orbit_type/tools.py +0 -0
  30. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_embedding/__init__.py +0 -0
  31. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_embedding/pdf_txt_embedding.py +0 -0
  32. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_embedding/pdf_txt_embedding_v2.py +0 -0
  33. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor/__init__.py +0 -0
  34. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor/a_stock_extractor_v1.py +0 -0
  35. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor/exceptions.py +0 -0
  36. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor/pdf_block_extractor_base.py +0 -0
  37. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor/pdf_block_extractor_v1.py +0 -0
  38. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor/pdf_block_extractor_v2.py +0 -0
  39. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor/pdf_extractor_azure.py +0 -0
  40. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor/pdf_extractor_minerU_v1.py +0 -0
  41. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor/pdf_extractor_netmind_v1.py +0 -0
  42. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor/pdf_extractor_netmind_v2.py +0 -0
  43. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor/pdf_extractor_netmind_v3.py +0 -0
  44. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor/pdf_extractor_orbit.py +0 -0
  45. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor_simple/__init__.py +0 -0
  46. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor_simple/base.py +0 -0
  47. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor_simple/cloud_provider.py +0 -0
  48. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor_simple/core.py +0 -0
  49. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor_simple/exceptions.py +0 -0
  50. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor_simple/extractors.py +0 -0
  51. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_extractor_simple/utils.py +0 -0
  52. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_writer/__init__.py +0 -0
  53. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/pdf_writer/pdf_writer_simple.py +0 -0
  54. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/__init__.py +0 -0
  55. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/cache_asset_downloader.py +0 -0
  56. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/common.py +0 -0
  57. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/customize_regix_manager.py +0 -0
  58. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/secret_manager.py +0 -0
  59. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/util_aliyun.py +0 -0
  60. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/util_aliyun_oss_simple.py +0 -0
  61. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/util_aws.py +0 -0
  62. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/util_aws_s3_wrapper.py +0 -0
  63. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/util_date.py +0 -0
  64. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/util_html.py +0 -0
  65. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/util_kafka.py +0 -0
  66. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/util_md5.py +0 -0
  67. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/util_selenium.py +0 -0
  68. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/util_simple_timer.py +0 -0
  69. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/util_str.py +0 -0
  70. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/util_type_mapping.py +0 -0
  71. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit/util/util_url.py +0 -0
  72. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit.egg-info/SOURCES.txt +0 -0
  73. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit.egg-info/dependency_links.txt +0 -0
  74. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit.egg-info/not-zip-safe +0 -0
  75. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit.egg-info/requires.txt +0 -0
  76. {orbitkit-0.8.42 → orbitkit-0.8.44}/orbitkit.egg-info/top_level.txt +0 -0
  77. {orbitkit-0.8.42 → orbitkit-0.8.44}/setup.cfg +0 -0
  78. {orbitkit-0.8.42 → orbitkit-0.8.44}/setup.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: orbitkit
3
- Version: 0.8.42
3
+ Version: 0.8.44
4
4
  Summary: This project is only for Orbit Tech internal use.
5
5
  Home-page: https://github.com/clown-0726/orbitkit
6
6
  Author: Lilu Cao
@@ -0,0 +1 @@
1
+ 0.8.44
@@ -39,7 +39,6 @@ class FilingOfficialProcessor:
39
39
  (self.filing_data_collection, 'filing_data')
40
40
  ]
41
41
  }
42
- self.only_low_important_set = {'internal_seekingalpha'}
43
42
  postgres_uri = os.environ.get('PG_URI_AIRFLOW12_USER_NEWSFEEDSITE') if not postgres_uri else postgres_uri
44
43
  if not postgres_uri:
45
44
  raise KeyError('postgres_uri not set.')
@@ -136,10 +135,10 @@ class FilingOfficialProcessor:
136
135
  for step_info, records in file_flow_info.items():
137
136
  for record in records:
138
137
  if 'extends' in record and record.get('extends') is not None:
139
- tickers = []
138
+ tickers = set()
140
139
  for i in record['extends']['perm_id_list']:
141
- tickers.extend(orbit_entity_id_ticker_map.get(i, []))
142
- record['extends']['tickers'] = tickers
140
+ tickers.update(orbit_entity_id_ticker_map.get(i, []))
141
+ record['extends']['tickers'] = list(tickers)
143
142
 
144
143
  record['extends']['report_type_id_list_str'] = [self.report_type_id_name_map.get(i) for i in record['extends']['report_type_id_list_str']]
145
144
 
@@ -158,7 +157,7 @@ class FilingOfficialProcessor:
158
157
  f"{len(records)}--{start_stage}-{target_stage}-{x_spider_name} status: False, message: 'File has already completed the embedding stage.' ")
159
158
  continue
160
159
 
161
- if is_important and x_spider_name not in self.only_low_important_set:
160
+ if is_important:
162
161
  logger.info(f"is_important: {is_important} - {x_spider_name}")
163
162
  status, ids, message = self.file_handler.entry_point_urgent(records=records, start_stage=start_stage,
164
163
  target_stage=target_stage,
@@ -28,8 +28,6 @@ class FlowUpdater:
28
28
  return getattr(self, collection_name)
29
29
 
30
30
  def _handle_convert(self, status, attachments, db_store_path_set, attachments_pdf):
31
- if not attachments or not attachments_pdf:
32
- raise ValueError("Missing attachments: neither 'attachments' nor 'attachments_pdf' was provided.")
33
31
  if not status:
34
32
  return {
35
33
  'x_status_list.status_convert.status': 'convert_failed',
@@ -37,6 +35,9 @@ class FlowUpdater:
37
35
  'x_status_list.status_convert.status_meta': 'meta_init'
38
36
  }
39
37
 
38
+ if not attachments or not attachments_pdf:
39
+ raise ValueError("Missing attachments: neither 'attachments' nor 'attachments_pdf' was provided.")
40
+
40
41
  store_path_set = set()
41
42
  parent_id_store_path_map = {i['parent_id']: i['store_path'] for i in attachments_pdf}
42
43
  x_attachments_pdf = []
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: orbitkit
3
- Version: 0.8.42
3
+ Version: 0.8.44
4
4
  Summary: This project is only for Orbit Tech internal use.
5
5
  Home-page: https://github.com/clown-0726/orbitkit
6
6
  Author: Lilu Cao
@@ -1 +0,0 @@
1
- 0.8.42
File without changes
File without changes
File without changes
File without changes
File without changes