Skip to content

GitLab

"docs/git@developer.sourcefind.cn:OpenDAS/torch-scatter.git" did not exist on "4cac2a2b3a15fca5e6a27a136aa0cdb00fcecb55"
Commit 044bd019 authored by kernel.h@qq.com's avatar kernel.h@qq.com
Browse files

delete 无用字段

parent 696906ed
Hide whitespace changes
Inline Side-by-side
Showing with 5 additions and 4 deletions
magic_pdf/pipeline_txt.py
View file @ 044bd019
...@@ -57,12 +57,13 @@ def txt_pdf_to_mm_markdown_format(jso: dict, debug_mode=False) -> dict: ...@@ -57,12 +57,13 @@ def txt_pdf_to_mm_markdown_format(jso: dict, debug_mode=False) -> dict:
pdf_intermediate_dict = JsonCompressor.decompress_json(pdf_intermediate_dict) pdf_intermediate_dict = JsonCompressor.decompress_json(pdf_intermediate_dict)
standard_format = mk_universal_format(pdf_intermediate_dict) standard_format = mk_universal_format(pdf_intermediate_dict)
mm_content = mk_mm_markdown(standard_format) mm_content = mk_mm_markdown(standard_format)
jso["content_list"] = mm_content jso["content"] = mm_content
logger.info(f"book_name is:{get_data_source(jso)}/{jso['file_id']},content_list length is {len(standard_format)}",) logger.info(f"book_name is:{get_data_source(jso)}/{jso['file_id']},content_list length is {len(standard_format)}",)
# 把无用的信息清空 # 把无用的信息清空
jso["doc_layout_result"] = "" to_del_keys = ["doc_layout_result", "pdf_intermediate_dict", "pdf_meta", "parsed_result"]
jso["pdf_intermediate_dict"] = "" for key in to_del_keys:
jso["pdf_meta"] = "" if jso.get(key):
del jso[key]
except Exception as e: except Exception as e:
jso = exception_handler(jso, e) jso = exception_handler(jso, e)
return jso return jso
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment