mirror of
https://github.com/Mintplex-Labs/anything-llm.git
synced 2024-09-17 18:20:11 +02:00
c4eb46ca19
* implement dnd uploader show file upload progress write files to hotdirector build simple flaskAPI to process files one off * move document processor calls to util build out dockerfile to run both procs at the same time update UI to check for document processor before upload * disable pragma update on boot * dockerfile changes * add filetype restrictions based on python app support response and show rejected files in the UI * cleanup * stub migrations on boot to prevent exit condition * update CF template for AWS deploy
36 lines
1.4 KiB
Python
36 lines
1.4 KiB
Python
import os
|
|
from .filetypes import FILETYPES
|
|
from .utils import move_source
|
|
|
|
RESERVED = ['__HOTDIR__.md']
|
|
|
|
# This script will do a one-off processing of a specific document that exists in hotdir.
|
|
# For this function we remove the original source document since there is no need to keep it and it will
|
|
# only occupy additional disk space.
|
|
def process_single(directory, target_doc):
|
|
if os.path.isdir(f"{directory}/{target_doc}") or target_doc in RESERVED: return (False, "Not a file")
|
|
|
|
if os.path.exists(f"{directory}/{target_doc}") is False:
|
|
print(f"{directory}/{target_doc} does not exist.")
|
|
return (False, f"{directory}/{target_doc} does not exist.")
|
|
|
|
filename, fileext = os.path.splitext(target_doc)
|
|
if filename in ['.DS_Store'] or fileext == '': return False
|
|
if fileext == '.lock':
|
|
print(f"{filename} is locked - skipping until unlocked")
|
|
return (False, f"{filename} is locked - skipping until unlocked")
|
|
|
|
if fileext not in FILETYPES.keys():
|
|
print(f"{fileext} not a supported file type for conversion. It will not be processed.")
|
|
move_source(new_destination_filename=target_doc, failed=True, remove=True)
|
|
return (False, f"{fileext} not a supported file type for conversion. It will not be processed.")
|
|
|
|
FILETYPES[fileext](
|
|
directory=directory,
|
|
filename=filename,
|
|
ext=fileext,
|
|
remove_on_complete=True # remove source document to save disk space.
|
|
)
|
|
|
|
return (True, None)
|