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

Fixes how a language code like chi-sim is treated in the checks

Browse Source
This commit is contained in:
Trenton Holmes 2022-11-27 08:28:22 -08:00
parent 2140d42098
commit f0497e7744
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
src/paperless_tesseract/checks.py
View File

@ -1,3 +1,4 @@
import shutil
import subprocess import subprocess
from django.conf import settings from django.conf import settings
@ -7,10 +8,16 @@ from django.core.checks import Warning
def get_tesseract_langs(): def get_tesseract_langs():
with subprocess.Popen(["tesseract", "--list-langs"], stdout=subprocess.PIPE) as p: proc = subprocess.run(
stdout, stderr = p.communicate() [shutil.which("tesseract"), "--list-langs"],
capture_output=True,
)
return stdout.decode().strip().split("\n")[1:] # Decode bytes to string, split on newlines, trim out the header
proc_lines = proc.stdout.decode("utf8", errors="ignore").strip().split("\n")[1:]
# Replace _ with - to convert two part languages to the expected code
return [x.replace("_", "-") for x in proc_lines]
@register() @register()