orbitkit 0.8.32__tar.gz → 0.8.33__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-0.8.32/orbitkit.egg-info → orbitkit-0.8.33}/PKG-INFO +1 -1
- orbitkit-0.8.33/orbitkit/VERSION +1 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor/pdf_extractor_netmind_v3.py +6 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33/orbitkit.egg-info}/PKG-INFO +1 -1
- orbitkit-0.8.32/orbitkit/VERSION +0 -1
- {orbitkit-0.8.32 → orbitkit-0.8.33}/LICENSE +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/MANIFEST.in +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/README.md +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/__init__.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/airflow_handler/__init__.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/airflow_handler/data_preprocessing.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/airflow_handler/file_flow_entry_process.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/airflow_handler/file_flow_exit_process.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/airflow_handler/file_handler.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/airflow_handler/file_handler_v2.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/audio_transcoder/__init__.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/audio_transcoder/netmind_extract_v1.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/constant/__init__.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/constant/report_schema.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/id_srv/__init__.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/id_srv/id_gen.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/id_srv/id_perm_like.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/lark_send/__init__.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/lark_send/lark.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/llm_tools/__init__.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/llm_tools/quick_rag_chat.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/orbit_type/__init__.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/orbit_type/doc_4_compile_rule.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/orbit_type/orbit_type_simple.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/orbit_type/tools.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_embedding/__init__.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_embedding/pdf_txt_embedding.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_embedding/pdf_txt_embedding_v2.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor/__init__.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor/a_stock_extractor_v1.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor/exceptions.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor/pdf_block_extractor_base.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor/pdf_block_extractor_v1.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor/pdf_block_extractor_v2.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor/pdf_extractor_azure.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor/pdf_extractor_minerU_v1.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor/pdf_extractor_netmind_v1.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor/pdf_extractor_netmind_v2.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor/pdf_extractor_orbit.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor_simple/__init__.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor_simple/base.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor_simple/cloud_provider.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor_simple/core.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor_simple/exceptions.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor_simple/extractors.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_extractor_simple/utils.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_writer/__init__.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/pdf_writer/pdf_writer_simple.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/__init__.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/common.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/customize_regix_manager.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/secret_manager.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/util_aliyun.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/util_aliyun_oss_simple.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/util_aws.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/util_aws_s3_wrapper.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/util_date.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/util_html.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/util_kafka.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/util_md5.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/util_selenium.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/util_simple_timer.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/util_str.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/util_type_mapping.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit/util/util_url.py +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit.egg-info/SOURCES.txt +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit.egg-info/dependency_links.txt +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit.egg-info/not-zip-safe +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit.egg-info/requires.txt +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/orbitkit.egg-info/top_level.txt +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/setup.cfg +0 -0
- {orbitkit-0.8.32 → orbitkit-0.8.33}/setup.py +0 -0
|
@@ -0,0 +1 @@
|
|
|
1
|
+
0.8.33
|
|
@@ -46,6 +46,8 @@ class PdfExtractorNetmindFileAnalysis:
|
|
|
46
46
|
self.s3_path = s3_path
|
|
47
47
|
self.slice_option = slice_option
|
|
48
48
|
self.max_workers = max_workers
|
|
49
|
+
self.input_file_size = None
|
|
50
|
+
self.total_pages = None
|
|
49
51
|
self.aws_access_key_id = get_from_dict_or_env(kwargs, "aws_access_key_id", "AWS_ACCESS_KEY_ID")
|
|
50
52
|
self.aws_secret_access_key = get_from_dict_or_env(kwargs, "aws_secret_access_key", "AWS_SECRET_ACCESS_KEY")
|
|
51
53
|
self.s3_client = boto3.client('s3',
|
|
@@ -67,8 +69,12 @@ class PdfExtractorNetmindFileAnalysis:
|
|
|
67
69
|
def split_pdf(self, input_file: str, output_folder: str) -> List[Dict[str, str]]:
|
|
68
70
|
Path(output_folder).mkdir(parents=True, exist_ok=True)
|
|
69
71
|
hash_id = id_srv.get_random_short_id()
|
|
72
|
+
# 获取输入文件的大小
|
|
73
|
+
input_file_path = Path(input_file)
|
|
74
|
+
self.input_file_size = input_file_path.stat().st_size # 获取输入文件的大小(字节)
|
|
70
75
|
pdf_document = fitz.open(input_file)
|
|
71
76
|
total_pages = len(pdf_document)
|
|
77
|
+
self.total_pages = total_pages
|
|
72
78
|
pages_per_split = self.slice_option.split_page_number
|
|
73
79
|
file_path_list = []
|
|
74
80
|
|
orbitkit-0.8.32/orbitkit/VERSION
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
0.8.32
|
|
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
|