orbitkit 0.8.58__tar.gz → 0.8.59__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 (79) hide show
  1. {orbitkit-0.8.58/orbitkit.egg-info → orbitkit-0.8.59}/PKG-INFO +1 -1
  2. orbitkit-0.8.59/orbitkit/VERSION +1 -0
  3. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/airflow_handler/file_flow_entry_process.py +8 -6
  4. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/airflow_handler/file_handler_v2.py +10 -5
  5. {orbitkit-0.8.58 → orbitkit-0.8.59/orbitkit.egg-info}/PKG-INFO +1 -1
  6. orbitkit-0.8.58/orbitkit/VERSION +0 -1
  7. {orbitkit-0.8.58 → orbitkit-0.8.59}/LICENSE +0 -0
  8. {orbitkit-0.8.58 → orbitkit-0.8.59}/MANIFEST.in +0 -0
  9. {orbitkit-0.8.58 → orbitkit-0.8.59}/README.md +0 -0
  10. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/__init__.py +0 -0
  11. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/airflow_handler/__init__.py +0 -0
  12. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/airflow_handler/data_preprocessing.py +0 -0
  13. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/airflow_handler/file_flow_exit_process.py +0 -0
  14. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/airflow_handler/file_handler.py +0 -0
  15. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/audio_transcoder/__init__.py +0 -0
  16. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/audio_transcoder/netmind_extract_v1.py +0 -0
  17. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/constant/__init__.py +0 -0
  18. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/constant/report_schema.py +0 -0
  19. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/id_srv/__init__.py +0 -0
  20. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/id_srv/id_gen.py +0 -0
  21. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/id_srv/id_perm_like.py +0 -0
  22. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/lark_send/__init__.py +0 -0
  23. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/lark_send/lark.py +0 -0
  24. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/llm_tools/__init__.py +0 -0
  25. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/llm_tools/quick_rag_chat.py +0 -0
  26. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/orbit_type/__init__.py +0 -0
  27. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/orbit_type/doc_4_compile_rule.py +0 -0
  28. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/orbit_type/orbit_type_simple.py +0 -0
  29. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/orbit_type/tools.py +0 -0
  30. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_embedding/__init__.py +0 -0
  31. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_embedding/pdf_txt_embedding.py +0 -0
  32. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_embedding/pdf_txt_embedding_v2.py +0 -0
  33. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor/__init__.py +0 -0
  34. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor/a_stock_extractor_v1.py +0 -0
  35. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor/exceptions.py +0 -0
  36. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor/pdf_block_extractor_base.py +0 -0
  37. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor/pdf_block_extractor_v1.py +0 -0
  38. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor/pdf_block_extractor_v2.py +0 -0
  39. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor/pdf_extractor_azure.py +0 -0
  40. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor/pdf_extractor_minerU_v1.py +0 -0
  41. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor/pdf_extractor_netmind_v1.py +0 -0
  42. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor/pdf_extractor_netmind_v2.py +0 -0
  43. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor/pdf_extractor_netmind_v3.py +0 -0
  44. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor/pdf_extractor_orbit.py +0 -0
  45. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor_simple/__init__.py +0 -0
  46. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor_simple/base.py +0 -0
  47. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor_simple/cloud_provider.py +0 -0
  48. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor_simple/core.py +0 -0
  49. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor_simple/exceptions.py +0 -0
  50. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor_simple/extractors.py +0 -0
  51. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_extractor_simple/utils.py +0 -0
  52. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_writer/__init__.py +0 -0
  53. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/pdf_writer/pdf_writer_simple.py +0 -0
  54. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/__init__.py +0 -0
  55. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/cache_asset_downloader.py +0 -0
  56. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/common.py +0 -0
  57. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/customize_regix_manager.py +0 -0
  58. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/secret_manager.py +0 -0
  59. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/universal_extractor.py +0 -0
  60. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/util_aliyun.py +0 -0
  61. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/util_aliyun_oss_simple.py +0 -0
  62. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/util_aws.py +0 -0
  63. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/util_aws_s3_wrapper.py +0 -0
  64. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/util_date.py +0 -0
  65. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/util_html.py +0 -0
  66. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/util_kafka.py +0 -0
  67. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/util_md5.py +0 -0
  68. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/util_selenium.py +0 -0
  69. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/util_simple_timer.py +0 -0
  70. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/util_str.py +0 -0
  71. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/util_type_mapping.py +0 -0
  72. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit/util/util_url.py +0 -0
  73. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit.egg-info/SOURCES.txt +0 -0
  74. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit.egg-info/dependency_links.txt +0 -0
  75. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit.egg-info/not-zip-safe +0 -0
  76. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit.egg-info/requires.txt +0 -0
  77. {orbitkit-0.8.58 → orbitkit-0.8.59}/orbitkit.egg-info/top_level.txt +0 -0
  78. {orbitkit-0.8.58 → orbitkit-0.8.59}/setup.cfg +0 -0
  79. {orbitkit-0.8.58 → orbitkit-0.8.59}/setup.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: orbitkit
3
- Version: 0.8.58
3
+ Version: 0.8.59
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
+ 0.8.59
@@ -151,7 +151,7 @@ class FilingOfficialProcessor:
151
151
 
152
152
  return file_flow_info
153
153
 
154
- def send_task(self, file_flow_info, tags, is_important, priority, spider_name_source_type):
154
+ def send_task(self, file_flow_info, tags, is_important, priority, spider_name_source_type, queue_type):
155
155
  for step_str, records in file_flow_info.items():
156
156
  steps = step_str.split('@__@')
157
157
  start_stage = steps[0]
@@ -172,12 +172,14 @@ class FilingOfficialProcessor:
172
172
  tag=x_spider_name,
173
173
  priority=priority,
174
174
  source_type=spider_name_source_type[
175
- x_spider_name])
175
+ x_spider_name],
176
+ queue_type=queue_type)
176
177
  else:
177
178
  status, ids, message = self.file_handler.entry_point(records=records, start_stage=start_stage,
178
179
  target_stage=target_stage, tags=tags,tag=x_spider_name,
179
180
  priority=priority,
180
- source_type=spider_name_source_type[x_spider_name])
181
+ source_type=spider_name_source_type[x_spider_name],
182
+ queue_type=queue_type)
181
183
  self.all_stat_count['file_flow'] += len(records)
182
184
  logger.info(f"{len(records)}--{start_stage}-{target_stage}-{x_spider_name} status: {status}, message: {message}")
183
185
 
@@ -213,7 +215,7 @@ class FilingOfficialProcessor:
213
215
 
214
216
  async def process_task_entry(self, source: str,
215
217
  query: dict, tags: list[str], priority: str,
216
- is_important: bool = False, custom_step: Optional[list[str]] = None, important_level = None, db_name: str = None):
218
+ is_important: bool = False, custom_step: Optional[list[str]] = None, important_level = None, db_name: str = None, queue_type: str = 'Default'):
217
219
 
218
220
  if not important_level or not isinstance(important_level, int):
219
221
  important_level = 0
@@ -251,7 +253,7 @@ class FilingOfficialProcessor:
251
253
  self.all_stat_count['doc_error'] += len(doc_error_list)
252
254
  self.all_stat_count['step_error'] += len(except_id_list)
253
255
  self.all_stat_count['xbrl'] += len(xbrl_data)
254
- self.send_task(file_flow_info, tags, is_important, priority, spider_name_source_type)
256
+ self.send_task(file_flow_info, tags, is_important, priority, spider_name_source_type, queue_type)
255
257
  self.send_xbrl_data_to_mongo(xbrl_data)
256
258
  self.update_doc_status_to_convert(collection, doc_error_list)
257
259
  process_data.clear()
@@ -264,7 +266,7 @@ class FilingOfficialProcessor:
264
266
  self.all_stat_count['doc_error'] += len(doc_error_list)
265
267
  self.all_stat_count['step_error'] += len(except_id_list)
266
268
  self.all_stat_count['xbrl'] += len(xbrl_data)
267
- self.send_task(file_flow_info, tags, is_important, priority, spider_name_source_type)
269
+ self.send_task(file_flow_info, tags, is_important, priority, spider_name_source_type, queue_type)
268
270
  self.send_xbrl_data_to_mongo(xbrl_data)
269
271
  self.update_doc_status_to_convert(collection, doc_error_list)
270
272
  process_data.clear()
@@ -141,7 +141,8 @@ class FileFlowHandleV2:
141
141
  'updated_at': now,
142
142
  'tags': params['tags'],
143
143
  'tag': params['tag'],
144
- 'important_level': record.get('important_level', 0)
144
+ 'important_level': record.get('important_level', 0),
145
+ 'queue': params['queue']
145
146
  }
146
147
 
147
148
  step = {
@@ -225,6 +226,7 @@ class FileFlowHandleV2:
225
226
  tag: str = None,
226
227
  priority: str = '1',
227
228
  source_type: Optional[str] = None,
229
+ queue_type: str = 'Default'
228
230
  ) -> Tuple[bool, Any, str]:
229
231
  """
230
232
  普通任务接口
@@ -252,7 +254,7 @@ class FileFlowHandleV2:
252
254
  """
253
255
  return self._file_flow_entry_point_internal(
254
256
  records, start_stage, target_stage, tags, priority, source_type,tag,
255
- urgent=False, clean_exist_data=False
257
+ urgent=False, clean_exist_data=False, queue_type=queue_type
256
258
  )
257
259
 
258
260
  def entry_point_urgent(
@@ -264,6 +266,7 @@ class FileFlowHandleV2:
264
266
  tag: str = None,
265
267
  priority: str = '1',
266
268
  source_type: Optional[str] = None,
269
+ queue_type: str = 'Default'
267
270
  ) -> Tuple[bool, Any, str]:
268
271
  """
269
272
  加急任务接口
@@ -291,7 +294,7 @@ class FileFlowHandleV2:
291
294
  """
292
295
  return self._file_flow_entry_point_internal(
293
296
  records, start_stage, target_stage, tags, priority, source_type, tag,
294
- urgent=True, clean_exist_data=True
297
+ urgent=True, clean_exist_data=True, queue_type=queue_type
295
298
  )
296
299
 
297
300
  def _file_flow_entry_point_internal(
@@ -304,7 +307,8 @@ class FileFlowHandleV2:
304
307
  source_type: Optional[str],
305
308
  tag: str,
306
309
  urgent: bool,
307
- clean_exist_data: bool = False
310
+ clean_exist_data: bool = False,
311
+ queue_type: str = 'Default'
308
312
  ) -> Tuple[bool, Any, str]:
309
313
  """核心处理逻辑"""
310
314
  params = {
@@ -315,7 +319,8 @@ class FileFlowHandleV2:
315
319
  'current_stage': start_stage,
316
320
  'source_type': source_type,
317
321
  'tag': tag,
318
- 'urgent': urgent
322
+ 'urgent': urgent,
323
+ 'queue': queue_type
319
324
  }
320
325
 
321
326
  is_valid, msg = self._validate_params(params)
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: orbitkit
3
- Version: 0.8.58
3
+ Version: 0.8.59
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
- 0.8.58
File without changes
File without changes
File without changes
File without changes
File without changes