orbitkit 0.9.26__tar.gz → 0.9.27__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-0.9.26/orbitkit.egg-info → orbitkit-0.9.27}/PKG-INFO +1 -1
- orbitkit-0.9.27/orbitkit/VERSION +1 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_transformer/mineru/result_transformer.py +2 -2
- {orbitkit-0.9.26 → orbitkit-0.9.27/orbitkit.egg-info}/PKG-INFO +1 -1
- orbitkit-0.9.26/orbitkit/VERSION +0 -1
- {orbitkit-0.9.26 → orbitkit-0.9.27}/LICENSE +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/MANIFEST.in +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/README.md +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/airflow_handler/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/airflow_handler/data_preprocessing.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/airflow_handler/file_flow_entry.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/airflow_handler/file_flow_entry_process.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/airflow_handler/file_flow_exit_process.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/airflow_handler/file_handler.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/airflow_handler/file_handler_v2.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/audio_transcoder/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/audio_transcoder/netmind_extract_v1.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/constant/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/constant/report_schema.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/id_srv/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/id_srv/id_gen.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/id_srv/id_perm_like.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/lark_send/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/lark_send/lark.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/llm_tools/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/llm_tools/quick_rag_chat.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/orbit_type/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/orbit_type/doc_4_compile_rule.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/orbit_type/orbit_type_simple.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/orbit_type/tools.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_chunking/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_chunking/chunk_fallback.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_chunking/chunk_plan.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_chunking/page_limit.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_chunking/pdf_metadata.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_embedding/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_embedding/pdf_txt_embedding.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_embedding/pdf_txt_embedding_v2.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor/a_stock_extractor_v1.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor/exceptions.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor/mineru_demo.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor/pdf_block_extractor_base.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor/pdf_block_extractor_v1.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor/pdf_block_extractor_v2.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor/pdf_extractor_azure.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor/pdf_extractor_minerU_v1.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor/pdf_extractor_netmind_v1.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor/pdf_extractor_netmind_v2.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor/pdf_extractor_netmind_v3.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor/pdf_extractor_orbit.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor_simple/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor_simple/base.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor_simple/cloud_provider.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor_simple/core.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor_simple/exceptions.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor_simple/extractors.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_extractor_simple/utils.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_pipeline_io/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_pipeline_io/cdn.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_pipeline_io/pg_task_store.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_quality/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_quality/failure_codes.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_quality/ocr_lang.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_quality/parse_record.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_quality/verdict.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_transformer/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_transformer/mineru/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_transformer/mineru/backends.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_transformer/mineru/bbox_rotation.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_validator/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_validator/filters/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_validator/filters/drop_invalid_bbox.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_validator/filters/drop_non_text.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_validator/filters/drop_vlm_artifacts.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_validator/filters/repeated_text.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_validator/pipeline.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_validator/registry.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_validator/validate.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_writer/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/pdf_writer/pdf_writer_simple.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/__init__.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/cache_asset_downloader.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/common.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/customize_regix_manager.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/is_xbrl_structure.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/secret_manager.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/universal_extractor.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/util_aliyun.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/util_aliyun_oss_simple.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/util_aws.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/util_aws_s3_wrapper.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/util_date.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/util_html.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/util_kafka.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/util_md5.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/util_selenium.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/util_simple_timer.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/util_str.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/util_type_mapping.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit/util/util_url.py +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit.egg-info/SOURCES.txt +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit.egg-info/dependency_links.txt +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit.egg-info/not-zip-safe +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit.egg-info/requires.txt +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/orbitkit.egg-info/top_level.txt +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/setup.cfg +0 -0
- {orbitkit-0.9.26 → orbitkit-0.9.27}/setup.py +0 -0
|
@@ -0,0 +1 @@
|
|
|
1
|
+
0.9.27
|
|
@@ -598,7 +598,7 @@ def _jsonl_bytes(records: List[dict]) -> bytes:
|
|
|
598
598
|
# - para_blocks 然后 discarded_blocks
|
|
599
599
|
# - btype=page_number 直接跳过
|
|
600
600
|
# - 文本类(text/title/discarded/index/header/footer/aside_text/footnote/
|
|
601
|
-
# reference/ref_text/equation/page_footnote/caption/abstract/code)走
|
|
601
|
+
# reference/ref_text/phonetic/equation/page_footnote/caption/abstract/code)走
|
|
602
602
|
# get_com_lines 提文本,title/header → out_type=title,其它 → sentence
|
|
603
603
|
# - list 递归 blk['blocks'](如有)
|
|
604
604
|
# - table 提 HTML(span.type=table 取 span.html),text spans 拆为单独 block
|
|
@@ -612,7 +612,7 @@ def _jsonl_bytes(records: List[dict]) -> bytes:
|
|
|
612
612
|
_TEXT_LIKE_TYPES = frozenset({
|
|
613
613
|
"text", "discarded", "title", "index",
|
|
614
614
|
"header", "footer", "aside_text",
|
|
615
|
-
"footnote", "reference", "ref_text",
|
|
615
|
+
"footnote", "reference", "ref_text", "phonetic",
|
|
616
616
|
"equation", "page_footnote",
|
|
617
617
|
"caption", "abstract", "code",
|
|
618
618
|
})
|
orbitkit-0.9.26/orbitkit/VERSION
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
0.9.26
|
|
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
|
|
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
|