apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-06-09 19:45:15 +02:00
Code Issues Projects Releases Packages Wiki Activity

Drop unnecessary docstring

Browse source
This commit is contained in:
Ray 2026-05-11 16:17:58 +08:00
parent 3b2ddef822
commit de58581900
1 changed files with 1 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

6
pageindex/retrieve.py
View file

@ -33,11 +33,7 @@ def _count_pages(doc_info: dict) -> int:
def _get_pdf_page_content(doc_info: dict, page_nums: list[int]) -> list[dict]:
"""Extract text for specific PDF pages (1-indexed). Prefer cached pages, fallback to PDF.
Honors the parser recorded on the document so cache-miss reads stay consistent
with the originally-indexed text. Defaults to PyPDF2 for legacy documents.
"""
"""Extract text for specific PDF pages (1-indexed). Prefer cached pages, fallback to PDF."""
cached_pages = doc_info.get('pages')
if cached_pages:
page_map = {p['page']: p['content'] for p in cached_pages}