From d1a17480ea2a2855c28212d22948ffd57fdce9ce Mon Sep 17 00:00:00 2001
From: Trenton H <holmes.trenton@gmail.com>
Date: Wed, 28 Sep 2022 14:24:34 -0700
Subject: [PATCH] Account for plusses in the OCR language setting

---
 src/paperless/settings.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/src/paperless/settings.py b/src/paperless/settings.py
index cd63105e2..a262bd501 100644
--- a/src/paperless/settings.py
+++ b/src/paperless/settings.py
@@ -719,7 +719,10 @@ def _get_nltk_language_setting(ocr_lang: str) -> Optional[str]:
     Maps an ISO-639-1 language code supported by Tesseract into
     an optional NLTK language name.  This is the set of common supported
     languages for all the NLTK data used.
+
+    Assumption: The primary language is first
     """
+    ocr_lang = ocr_lang.split("+")[0]
     iso_code_to_nltk = {
         "dan": "danish",
         "nld": "dutch",