gmakstutis/cognee
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix: Changes exception handling to catch 'em all

Browse source
This commit is contained in:
hajdul88 2025-07-03 07:54:19 +02:00
parent 278ede9dbe
commit 6a7f5be561
1 changed files with 8 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
cognee/modules/data/processing/document_types/PdfDocument.py
View file

@ -16,8 +16,10 @@ class PdfDocument(Document):
logger.info(f"Reading PDF:{self.raw_data_location}")
try:
file = PdfReader(stream, strict=False)
except PdfReadError:
logger.warning(f"PyPDF couldn’t open PDF—skipping: {self.raw_data_location}")
except Exception as e:
logger.warning(
f"PyPDF couldn’t open PDF—skipping: {self.raw_data_location} with error: {e}"
)
return
def get_text():
@ -25,8 +27,10 @@ class PdfDocument(Document):
for page in file.pages:
page_text = page.extract_text()
yield page_text
except PdfReadError:
logger.warning(f"PyPDF couldn’t open PDF—skipping: {self.raw_data_location}")
except Exception as e:
logger.warning(
f"PyPDF couldn’t open PDF—skipping: {self.raw_data_location} with error: {e}"
)
return
chunker = chunker_cls(self, get_text=get_text, max_chunk_size=max_chunk_size)