orbitkit 0.8.71__tar.gz → 0.8.73__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 (81) hide show
  1. {orbitkit-0.8.71/orbitkit.egg-info → orbitkit-0.8.73}/PKG-INFO +1 -1
  2. orbitkit-0.8.73/orbitkit/VERSION +1 -0
  3. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/airflow_handler/file_flow_entry_process.py +3 -3
  4. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/airflow_handler/file_flow_exit_process.py +6 -6
  5. {orbitkit-0.8.71 → orbitkit-0.8.73/orbitkit.egg-info}/PKG-INFO +1 -1
  6. orbitkit-0.8.71/orbitkit/VERSION +0 -1
  7. {orbitkit-0.8.71 → orbitkit-0.8.73}/LICENSE +0 -0
  8. {orbitkit-0.8.71 → orbitkit-0.8.73}/MANIFEST.in +0 -0
  9. {orbitkit-0.8.71 → orbitkit-0.8.73}/README.md +0 -0
  10. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/__init__.py +0 -0
  11. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/airflow_handler/__init__.py +0 -0
  12. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/airflow_handler/data_preprocessing.py +0 -0
  13. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/airflow_handler/file_handler.py +0 -0
  14. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/airflow_handler/file_handler_v2.py +0 -0
  15. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/audio_transcoder/__init__.py +0 -0
  16. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/audio_transcoder/netmind_extract_v1.py +0 -0
  17. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/constant/__init__.py +0 -0
  18. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/constant/report_schema.py +0 -0
  19. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/id_srv/__init__.py +0 -0
  20. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/id_srv/id_gen.py +0 -0
  21. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/id_srv/id_perm_like.py +0 -0
  22. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/lark_send/__init__.py +0 -0
  23. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/lark_send/lark.py +0 -0
  24. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/llm_tools/__init__.py +0 -0
  25. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/llm_tools/quick_rag_chat.py +0 -0
  26. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/orbit_type/__init__.py +0 -0
  27. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/orbit_type/doc_4_compile_rule.py +0 -0
  28. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/orbit_type/orbit_type_simple.py +0 -0
  29. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/orbit_type/tools.py +0 -0
  30. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_embedding/__init__.py +0 -0
  31. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_embedding/pdf_txt_embedding.py +0 -0
  32. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_embedding/pdf_txt_embedding_v2.py +0 -0
  33. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor/__init__.py +0 -0
  34. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor/a_stock_extractor_v1.py +0 -0
  35. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor/exceptions.py +0 -0
  36. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor/mineru_demo.py +0 -0
  37. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor/pdf_block_extractor_base.py +0 -0
  38. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor/pdf_block_extractor_v1.py +0 -0
  39. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor/pdf_block_extractor_v2.py +0 -0
  40. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor/pdf_extractor_azure.py +0 -0
  41. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor/pdf_extractor_minerU_v1.py +0 -0
  42. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor/pdf_extractor_netmind_v1.py +0 -0
  43. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor/pdf_extractor_netmind_v2.py +0 -0
  44. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor/pdf_extractor_netmind_v3.py +0 -0
  45. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor/pdf_extractor_orbit.py +0 -0
  46. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor_simple/__init__.py +0 -0
  47. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor_simple/base.py +0 -0
  48. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor_simple/cloud_provider.py +0 -0
  49. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor_simple/core.py +0 -0
  50. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor_simple/exceptions.py +0 -0
  51. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor_simple/extractors.py +0 -0
  52. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_extractor_simple/utils.py +0 -0
  53. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_writer/__init__.py +0 -0
  54. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/pdf_writer/pdf_writer_simple.py +0 -0
  55. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/__init__.py +0 -0
  56. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/cache_asset_downloader.py +0 -0
  57. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/common.py +0 -0
  58. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/customize_regix_manager.py +0 -0
  59. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/is_xbrl_structure.py +0 -0
  60. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/secret_manager.py +0 -0
  61. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/universal_extractor.py +0 -0
  62. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/util_aliyun.py +0 -0
  63. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/util_aliyun_oss_simple.py +0 -0
  64. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/util_aws.py +0 -0
  65. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/util_aws_s3_wrapper.py +0 -0
  66. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/util_date.py +0 -0
  67. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/util_html.py +0 -0
  68. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/util_kafka.py +0 -0
  69. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/util_md5.py +0 -0
  70. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/util_selenium.py +0 -0
  71. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/util_simple_timer.py +0 -0
  72. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/util_str.py +0 -0
  73. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/util_type_mapping.py +0 -0
  74. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit/util/util_url.py +0 -0
  75. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit.egg-info/SOURCES.txt +0 -0
  76. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit.egg-info/dependency_links.txt +0 -0
  77. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit.egg-info/not-zip-safe +0 -0
  78. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit.egg-info/requires.txt +0 -0
  79. {orbitkit-0.8.71 → orbitkit-0.8.73}/orbitkit.egg-info/top_level.txt +0 -0
  80. {orbitkit-0.8.71 → orbitkit-0.8.73}/setup.cfg +0 -0
  81. {orbitkit-0.8.71 → orbitkit-0.8.73}/setup.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: orbitkit
3
- Version: 0.8.71
3
+ Version: 0.8.73
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
+ 0.8.73
@@ -217,10 +217,10 @@ class FilingOfficialProcessor:
217
217
  query: dict, tags: list[str], priority: str,
218
218
  is_important: bool = False, custom_step: Optional[list[str]] = None, important_level = None, db_name: str = None, queue_type: str = 'Default'):
219
219
 
220
- if not important_level or not isinstance(important_level, int):
221
- important_level = 0
220
+ if source == 'filing_data':
221
+ raise ValueError(f"Cannot update documents from 'filing_data' source. ")
222
222
 
223
- if important_level == 0:
223
+ if important_level is None or not isinstance(important_level, int) or important_level <= 0:
224
224
  raise ValueError(f'important_level must be an integer (int) greater than 0. {important_level}')
225
225
 
226
226
  allowed_steps = {"convert", "extract", "embedding"}
@@ -96,7 +96,11 @@ class FlowUpdater:
96
96
  update_params.update({self.kafka_ignore.X_OTHERS_K_IGNORE_KEY: self.kafka_ignore.get_k_ignore_val()})
97
97
  update_params.update({"x_updated_date": datetime.now(tz=pytz.timezone('UTC')).strftime("%Y-%m-%dT%H:%M:%S%z")})
98
98
  collection = self._check_and_create_collection(data_source)
99
- result = collection.update_one({'_id': report_id}, {'$set': update_params})
99
+ # 2026-03-02 Status rollback. In special cases, it is necessary to reprocess attachments when the original success has now failed, addressing database constraint exceptions.
100
+ if update_params.get('x_status_list.status_convert.status') == 'convert_failed':
101
+ result = collection.update_one({'_id': report_id}, {'$set': update_params, '$unset': {'x_attachments_pdf': ''}})
102
+ else:
103
+ result = collection.update_one({'_id': report_id}, {'$set': update_params})
100
104
  if result.matched_count == 0:
101
105
  raise LookupError(f"No document found with id {report_id} to update. {data_source}")
102
106
  logger.info(f"Document with id {report_id} update attempted. Modified: {result.modified_count}")
@@ -133,11 +137,7 @@ class FlowUpdater:
133
137
  db_doc = self._check_and_create_collection(data_source).find_one({'_id': report_id},
134
138
  {'_id': 1, 'x_attachments': 1,
135
139
  'x_status_list': 1})
136
- if not db_doc and data_source == 'filing_data':
137
- data_source = 'filing_data_staging'
138
- db_doc = self._check_and_create_collection(data_source).find_one({'_id': report_id},
139
- {'_id': 1, 'x_attachments': 1,
140
- 'x_status_list': 1})
140
+
141
141
  if not db_doc:
142
142
  logger.warning(f"No document found with id {report_id}.")
143
143
  return
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: orbitkit
3
- Version: 0.8.71
3
+ Version: 0.8.73
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
- 0.8.71
File without changes
File without changes
File without changes
File without changes
File without changes