yujunjun/olmocr
1
0
Fork 0
mirror of https://github.com/allenai/olmocr.git synced 2025-08-20 06:42:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

Trying to make it faster

Browse Source
This commit is contained in:
Jake Poznanski 2024-11-15 11:06:50 -08:00
parent 278422b8ff
commit fd17652d55
1 changed files with 1 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
pdelfin/prompts/anchor.py
View File

@ -121,13 +121,8 @@ class PageReport:
text_elements: List[TextElement]
image_elements: List[ImageElement]
@lru_cache(maxsize=5)
def _get_cached_pdf_reader(local_pdf_path: str) -> PdfReader:
# Cached, because you are going to often iterate through a whole pdf, so this will make it a lot faster on subsequent iterations
return PdfReader(local_pdf_path)
def _pdf_report(local_pdf_path: str, page_num: int) -> PageReport:
reader = _get_cached_pdf_reader(local_pdf_path)
reader = PdfReader(local_pdf_path)
page = reader.pages[page_num - 1]
resources = page.get("/Resources", {})
xobjects = resources.get("/XObject", {})