orbitkit 0.8.55__tar.gz → 0.8.57__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.
- {orbitkit-0.8.55/orbitkit.egg-info → orbitkit-0.8.57}/PKG-INFO +1 -1
- orbitkit-0.8.57/orbitkit/VERSION +1 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/airflow_handler/data_preprocessing.py +3 -1
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/airflow_handler/file_flow_exit_process.py +5 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57/orbitkit.egg-info}/PKG-INFO +1 -1
- orbitkit-0.8.55/orbitkit/VERSION +0 -1
- {orbitkit-0.8.55 → orbitkit-0.8.57}/LICENSE +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/MANIFEST.in +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/README.md +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/__init__.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/airflow_handler/__init__.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/airflow_handler/file_flow_entry_process.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/airflow_handler/file_handler.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/airflow_handler/file_handler_v2.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/audio_transcoder/__init__.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/audio_transcoder/netmind_extract_v1.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/constant/__init__.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/constant/report_schema.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/id_srv/__init__.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/id_srv/id_gen.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/id_srv/id_perm_like.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/lark_send/__init__.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/lark_send/lark.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/llm_tools/__init__.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/llm_tools/quick_rag_chat.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/orbit_type/__init__.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/orbit_type/doc_4_compile_rule.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/orbit_type/orbit_type_simple.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/orbit_type/tools.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_embedding/__init__.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_embedding/pdf_txt_embedding.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_embedding/pdf_txt_embedding_v2.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor/__init__.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor/a_stock_extractor_v1.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor/exceptions.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor/pdf_block_extractor_base.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor/pdf_block_extractor_v1.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor/pdf_block_extractor_v2.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor/pdf_extractor_azure.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor/pdf_extractor_minerU_v1.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor/pdf_extractor_netmind_v1.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor/pdf_extractor_netmind_v2.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor/pdf_extractor_netmind_v3.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor/pdf_extractor_orbit.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor_simple/__init__.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor_simple/base.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor_simple/cloud_provider.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor_simple/core.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor_simple/exceptions.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor_simple/extractors.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_extractor_simple/utils.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_writer/__init__.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/pdf_writer/pdf_writer_simple.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/__init__.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/cache_asset_downloader.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/common.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/customize_regix_manager.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/secret_manager.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/universal_extractor.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/util_aliyun.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/util_aliyun_oss_simple.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/util_aws.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/util_aws_s3_wrapper.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/util_date.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/util_html.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/util_kafka.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/util_md5.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/util_selenium.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/util_simple_timer.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/util_str.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/util_type_mapping.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit/util/util_url.py +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit.egg-info/SOURCES.txt +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit.egg-info/dependency_links.txt +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit.egg-info/not-zip-safe +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit.egg-info/requires.txt +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/orbitkit.egg-info/top_level.txt +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/setup.cfg +0 -0
- {orbitkit-0.8.55 → orbitkit-0.8.57}/setup.py +0 -0
|
@@ -0,0 +1 @@
|
|
|
1
|
+
0.8.57
|
|
@@ -68,7 +68,9 @@ class DocumentProcessor:
|
|
|
68
68
|
if not doc:
|
|
69
69
|
return None
|
|
70
70
|
suffixes = {cls.get_file_suffix(att['store_path']) for att in doc.get('x_attachments', [])}
|
|
71
|
-
|
|
71
|
+
if suffixes.issubset(cls.ALL_ALLOWED_SUFFIXES) or doc['x_status_list']['status_convert']['status'] == "convert_done":
|
|
72
|
+
return doc
|
|
73
|
+
return None
|
|
72
74
|
|
|
73
75
|
@classmethod
|
|
74
76
|
def xbrl_type_check(cls, doc):
|
|
@@ -133,6 +133,11 @@ class FlowUpdater:
|
|
|
133
133
|
db_doc = self._check_and_create_collection(data_source).find_one({'_id': report_id},
|
|
134
134
|
{'_id': 1, 'x_attachments': 1,
|
|
135
135
|
'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})
|
|
136
141
|
if not db_doc:
|
|
137
142
|
logger.warning(f"No document found with id {report_id}.")
|
|
138
143
|
return
|
orbitkit-0.8.55/orbitkit/VERSION
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
0.8.55
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|