apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-06-21 20:18:09 +02:00
Code Issues Projects Releases Packages Wiki Activity

Move pdf_parser off doc dict, pass via call args

Browse source
This commit is contained in:
Ray 2026-05-11 16:40:32 +08:00
parent ec1aaca4c9
commit 108cb28518
2 changed files with 5 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

9
pageindex/retrieve.py
View file

@ -32,7 +32,7 @@ def _count_pages(doc_info: dict) -> int:
return get_number_of_pages(doc_info['path'])
def _get_pdf_page_content(doc_info: dict, page_nums: list[int]) -> list[dict]:
def _get_pdf_page_content(doc_info: dict, page_nums: list[int], pdf_parser: str = DEFAULT_PDF_PARSER) -> list[dict]:
"""Extract text for specific PDF pages (1-indexed). Prefer cached pages, fallback to PDF."""
cached_pages = doc_info.get('pages')
if cached_pages:
@ -41,8 +41,7 @@ def _get_pdf_page_content(doc_info: dict, page_nums: list[int]) -> list[dict]:
{'page': p, 'content': page_map[p]}
for p in page_nums if p in page_map
]
parser = doc_info.get('pdf_parser') or DEFAULT_PDF_PARSER
all_pages = read_pdf_pages(doc_info['path'], pdf_parser=parser)
all_pages = read_pdf_pages(doc_info['path'], pdf_parser=pdf_parser)
total = len(all_pages)
valid_pages = [p for p in page_nums if 1 <= p <= total]
return [
@ -105,7 +104,7 @@ def get_document_structure(documents: dict, doc_id: str) -> str:
return json.dumps(structure_no_text, ensure_ascii=False)
def get_page_content(documents: dict, doc_id: str, pages: str) -> str:
def get_page_content(documents: dict, doc_id: str, pages: str, pdf_parser: str = DEFAULT_PDF_PARSER) -> str:
"""
Retrieve page content for a document.
@ -126,7 +125,7 @@ def get_page_content(documents: dict, doc_id: str, pages: str) -> str:
try:
if doc_info.get('type') == 'pdf':
content = _get_pdf_page_content(doc_info, page_nums)
content = _get_pdf_page_content(doc_info, page_nums, pdf_parser=pdf_parser)
else:
content = _get_md_page_content(doc_info, page_nums)
except Exception as e: