Merge branch 'dev' into feature-frontend-config

src/documents/migrations/1015_configurationoption.py

@@ -0,0 +1,21 @@
+# Generated by Django 3.1.7 on 2021-03-16 11:26
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('documents', '1014_auto_20210228_1614'),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='ConfigurationOption',
+            fields=[
+                ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('key', models.CharField(max_length=128, unique=True)),
+                ('value', models.CharField(blank=True, max_length=1024, null=True)),
+            ],
+        ),
+    ]

src/documents/models.py

@@ -411,6 +411,56 @@ class SavedViewFilterRule(models.Model):
         verbose_name_plural = _("filter rules")
 
 
+class ConfigurationOptionManager(models.Manager):
+
+    CONFIGURATION_KEYS = {
+        "OCR_MODE": {"type": str, "default": "skip"},
+        "OCR_ROTATE_PAGES": {"type": bool, "default": True}
+    }
+
+    def __getattr__(self, item):
+        if not item in self.CONFIGURATION_KEYS:
+            raise AttributeError()
+
+        query = self.filter(key=item)
+        if query.exists() and query.first().value:
+            return self.CONFIGURATION_KEYS[item]["type"](query.first().value)
+        else:
+            return self._get_default(item)
+
+    def set_config(self, key, value):
+        if key in self.CONFIGURATION_KEYS:
+            if not type(value) == self.CONFIGURATION_KEYS[key]["type"]:
+                raise TypeError()
+
+            self.filter(key=key).update(value=value)
+        else:
+            raise KeyError()
+
+    def _get_default(self, key):
+        if f"PAPERLESS_{key}" in os.environ:
+            return os.environ[f"PAPERLESS_{key}"]
+        elif "default" in self.CONFIGURATION_KEYS[key]:
+            return self.CONFIGURATION_KEYS[key]['default']
+        else:
+            return None
+
+
+class ConfigurationOption(models.Model):
+
+    objects = ConfigurationOptionManager()
+
+    key = models.CharField(
+        max_length=128, unique=True)
+
+    value = models.CharField(
+        max_length=1024, blank=True, null=True
+    )
+
+
+db_settings = ConfigurationOption.objects
+
+
 # TODO: why is this in the models file?
 class FileInfo:
 

src/paperless_tesseract/parsers.py

@@ -5,6 +5,7 @@ import re
 from PIL import Image
 from django.conf import settings
 
+from documents.models import db_settings
 from documents.parsers import DocumentParser, ParseError, \
     make_thumbnail_from_pdf
 
@@ -143,15 +144,15 @@ class RasterisedDocumentParser(DocumentParser):
             'progress_bar': False
         }
 
-        if settings.OCR_MODE == 'force' or safe_fallback:
+        if db_settings.OCR_MODE == 'force' or safe_fallback:
             ocrmypdf_args['force_ocr'] = True
-        elif settings.OCR_MODE in ['skip', 'skip_noarchive']:
+        elif db_settings.OCR_MODE in ['skip', 'skip_noarchive']:
             ocrmypdf_args['skip_text'] = True
-        elif settings.OCR_MODE == 'redo':
+        elif db_settings.OCR_MODE == 'redo':
             ocrmypdf_args['redo_ocr'] = True
         else:
             raise ParseError(
-                f"Invalid ocr mode: {settings.OCR_MODE}")
+                f"Invalid ocr mode: {db_settings.OCR_MODE}")
 
         if settings.OCR_CLEAN == 'clean':
             ocrmypdf_args['clean'] = True
@@ -161,7 +162,7 @@ class RasterisedDocumentParser(DocumentParser):
             else:
                 ocrmypdf_args['clean_final'] = True
 
-        if settings.OCR_DESKEW and not settings.OCR_MODE == 'redo':
+        if settings.OCR_DESKEW and not db_settings.OCR_MODE == 'redo':
             ocrmypdf_args['deskew'] = True
 
         if settings.OCR_ROTATE_PAGES:
@@ -212,7 +213,7 @@ class RasterisedDocumentParser(DocumentParser):
         text_original = self.extract_text(None, document_path)
         original_has_text = text_original and len(text_original) > 50
 
-        if settings.OCR_MODE == "skip_noarchive" and original_has_text:
+        if db_settings.OCR_MODE == "skip_noarchive" and original_has_text:
             self.log("debug",
                      "Document has text, skipping OCRmyPDF entirely.")
             self.text = text_original