outman/dify
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: properly close pdf reader resources in pdf_extractor

Browse Source
This commit is contained in:
zhouyy 2025-03-12 18:00:16 +08:00 committed by crazywoola
parent 2524f16525
commit 683b4ac615
1 changed files with 11 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
api/core/rag/extractor/pdf_extractor.py
View File

@ -55,14 +55,18 @@ class PdfExtractor(BaseExtractor):
import pypdfium2 # type: ignore
with blob.as_bytes_io() as file_path:
pdf_reader = pypdfium2.PdfDocument(file_path, autoclose=True)
try:
pdf_reader = pypdfium2.PdfDocument(file_path, autoclose=True)
for page_number, page in enumerate(pdf_reader):
text_page = page.get_textpage()
content = text_page.get_text_range()
text_page.close()
page.close()
metadata = {"source": blob.source, "page": page_number}
yield Document(page_content=content, metadata=metadata)
try:
text_page = page.get_textpage()
try:
content = text_page.get_text_range()
metadata = {"source": blob.source, "page": page_number}
yield Document(page_content=content, metadata=metadata)
finally:
text_page.close()
finally:
page.close()
finally:
pdf_reader.close()