sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2024-11-23 23:48:56 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 18

Fix identifying pdf files on server

Browse source 
Introduced bug in previous commit that would stop indexing PDF files
as trying to check content_group instead of mime_type is application/pdf
This commit is contained in:
Debanjum Singh Solanky 2024-04-12 02:49:39 +05:30
parent 07f8fb5c5b
commit 7d2ef728e6
1 changed files with 6 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
src/khoj/utils/helpers.py
View file

@ -102,14 +102,16 @@ def get_file_type(file_type: str, file_content: bytes) -> tuple[str, str]:
# Infer content type from reading file content
try:
content_type = magika.identify_bytes(file_content).output.group
content_identity = magika.identify_bytes(file_content).output
content_type = content_identity.mime_type
content_group = content_identity.group
except Exception:
# Fallback to using just file type if content type cannot be inferred
content_type = file_type
if file_type in ["text/markdown"] and content_type in ["code", "text"]:
if file_type in ["text/markdown"] and content_group in ["code", "text"]:
return "markdown", encoding
elif file_type in ["text/org"] and content_type in ["code", "text"]:
elif file_type in ["text/org"] and content_group in ["code", "text"]:
return "org", encoding
elif file_type in ["application/pdf"] and content_type == "application/pdf":
return "pdf", encoding
@ -117,7 +119,7 @@ def get_file_type(file_type: str, file_content: bytes) -> tuple[str, str]:
return "jpeg", encoding
elif file_type in ["image/png"] and content_type == "image/png":
return "png", encoding
elif content_type in ["code", "text"]:
elif content_group in ["code", "text"]:
return "plaintext", encoding
else:
return "other", encoding