From dd833643268e718c1c8e86708f7da8bc2513bcee Mon Sep 17 00:00:00 2001
From: Jonas Winkler <jonas.winkler@jpwinkler.de>
Date: Wed, 25 Nov 2020 10:52:38 +0100
Subject: [PATCH] default language check

---
 src/documents/__init__.py           |  3 ++-
 src/paperless_tesseract/__init__.py |  2 ++
 src/paperless_tesseract/checks.py   | 24 ++++++++++++++++++++++++
 3 files changed, 28 insertions(+), 1 deletion(-)
 create mode 100644 src/paperless_tesseract/checks.py

diff --git a/src/documents/__init__.py b/src/documents/__init__.py
index 864b5f5fe..5c9f358c3 100644
--- a/src/documents/__init__.py
+++ b/src/documents/__init__.py
@@ -1 +1,2 @@
-from .checks import changed_password_check
+# this is here so that django finds the checks.
+from .checks import *
diff --git a/src/paperless_tesseract/__init__.py b/src/paperless_tesseract/__init__.py
index e69de29bb..5c9f358c3 100644
--- a/src/paperless_tesseract/__init__.py
+++ b/src/paperless_tesseract/__init__.py
@@ -0,0 +1,2 @@
+# this is here so that django finds the checks.
+from .checks import *
diff --git a/src/paperless_tesseract/checks.py b/src/paperless_tesseract/checks.py
new file mode 100644
index 000000000..21f229e65
--- /dev/null
+++ b/src/paperless_tesseract/checks.py
@@ -0,0 +1,24 @@
+import subprocess
+
+from django.conf import settings
+from django.core.checks import Error, register
+
+
+def get_tesseract_langs():
+    with subprocess.Popen(['tesseract', '--list-langs'], stdout=subprocess.PIPE) as p:
+        stdout, stderr = p.communicate()
+
+    return stdout.decode().strip().split("\n")[1:]
+
+
+@register()
+def check_default_language_available(app_configs, **kwargs):
+    langs = get_tesseract_langs()
+
+    if not settings.OCR_LANGUAGE in langs:
+        return [Error(
+            f"The default ocr language {settings.OCR_LANGUAGE} is "
+            f"not installed. Paperless cannot OCR your documents "
+            f"without it. Please fix PAPERLESS_OCR_LANGUAGE.")]
+    else:
+        return []