paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-02 13:45:10 -05:00
Code Issues Packages Projects Releases Wiki Activity

Enhancement: add timeout for Tika client (#8520)

Browse Source 
Co-authored-by: shamoon <4887959+shamoon@users.noreply.github.com>
This commit is contained in:
HiranChaudhuri 2024-12-19 17:58:26 +01:00 committed by GitHub
parent 2bcbed31e9
commit 452ea2ccf9
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
src/paperless_tika/parsers.py
View File

@ -33,7 +33,10 @@ class TikaDocumentParser(DocumentParser):
def extract_metadata(self, document_path, mime_type): def extract_metadata(self, document_path, mime_type):
try: try:
with TikaClient(tika_url=settings.TIKA_ENDPOINT) as client: with TikaClient(
tika_url=settings.TIKA_ENDPOINT,
timeout=settings.CELERY_TASK_TIME_LIMIT,
) as client:
parsed = client.metadata.from_file(document_path, mime_type) parsed = client.metadata.from_file(document_path, mime_type)
return [ return [
{ {
@ -54,7 +57,10 @@ class TikaDocumentParser(DocumentParser):
self.log.info(f"Sending {document_path} to Tika server") self.log.info(f"Sending {document_path} to Tika server")
try: try:
with TikaClient(tika_url=settings.TIKA_ENDPOINT) as client: with TikaClient(
tika_url=settings.TIKA_ENDPOINT,
timeout=settings.CELERY_TASK_TIME_LIMIT,
) as client:
try: try:
parsed = client.tika.as_text.from_file(document_path, mime_type) parsed = client.tika.as_text.from_file(document_path, mime_type)
except httpx.HTTPStatusError as err: except httpx.HTTPStatusError as err: