paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-25 10:49:30 -05:00
Code Issues Packages Projects Releases Wiki Activity

Ensure the tika parse function gets a string, not a PathLike

Browse Source
This commit is contained in:
Trenton Holmes 2022-09-14 07:48:12 -07:00
parent 17ae2aacbf
commit d4cb84ff76
1 changed files with 11 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/paperless_tika/parsers.py
View File

@ -1,4 +1,5 @@
import os
from pathlib import Path
import dateutil.parser
import requests
@ -28,6 +29,11 @@ class TikaDocumentParser(DocumentParser):
def extract_metadata(self, document_path, mime_type):
tika_server = settings.TIKA_ENDPOINT
# tika does not support a PathLike, only strings
# ensure this is a string
document_path = str(document_path)
try:
parsed = parser.from_file(document_path, tika_server)
except Exception as e:
@ -47,10 +53,14 @@ class TikaDocumentParser(DocumentParser):
for key in parsed["metadata"]
]
def parse(self, document_path, mime_type, file_name=None):
def parse(self, document_path: Path, mime_type, file_name=None):
self.log("info", f"Sending {document_path} to Tika server")
tika_server = settings.TIKA_ENDPOINT
# tika does not support a PathLike, only strings
# ensure this is a string
document_path = str(document_path)
try:
parsed = parser.from_file(document_path, tika_server)
except Exception as err: