adai/MemoryBear
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[modify] mineru

Browse Source
This commit is contained in:
Mark
2026-04-09 14:11:01 +08:00
parent 3ff44f0108
commit 0f50537d7d
2 changed files with 126 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
api/app/core/rag/deepdoc/parser/mineru_parser.py
View File

@@ -292,9 +292,10 @@ class MinerUParser(RAGPdfParser):
self.page_from = page_from
self.page_to = page_to
try:
with pdfplumber.open(fnm) if isinstance(fnm, (str, PathLike)) else pdfplumber.open(BytesIO(fnm)) as pdf:
self.pdf = pdf
self.page_images = [p.to_image(resolution=72 * zoomin, antialias=True).original for _, p in enumerate(self.pdf.pages[page_from:page_to])]
with sys.modules[LOCK_KEY_pdfplumber]: # ← 加这一行，获取全局锁
with pdfplumber.open(fnm) if isinstance(fnm, (str, PathLike)) else pdfplumber.open(BytesIO(fnm)) as pdf:
self.pdf = pdf
self.page_images = [p.to_image(resolution=72 * zoomin, antialias=True).original for _, p in enumerate(self.pdf.pages[page_from:page_to])]
except Exception as e:
self.page_images = None
self.total_page = 0