Moving the settings to main paperless application

src/paperless/migrations/0001_initial.py

@@ -1,4 +1,4 @@
-# Generated by Django 4.2.7 on 2023-12-11 19:59
+# Generated by Django 4.2.7 on 2023-12-14 17:12
 
 import django.core.validators
 from django.db import migrations
@@ -6,8 +6,12 @@ from django.db import models
 
 
 def _create_singleton(apps, schema_editor):
-    settings_model = apps.get_model("paperless_tesseract", "OcrSettings")
+    """
-    settings_model.objects.create()
+    Creates the first and only instance of the settings models
+    """
+    for model_name in ["CommonSettings", "OcrSettings", "TextSettings", "TikaSettings"]:
+        settings_model = apps.get_model("paperless", model_name)
+        settings_model.objects.create()
 
 
 class Migration(migrations.Migration):
@@ -16,6 +20,39 @@ class Migration(migrations.Migration):
     dependencies = []
 
     operations = [
+        migrations.CreateModel(
+            name="CommonSettings",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "output_type",
+                    models.CharField(
+                        blank=True,
+                        choices=[
+                            ("pdf", "pdf"),
+                            ("pdfa", "pdfa"),
+                            ("pdfa-1", "pdfa-1"),
+                            ("pdfa-2", "pdfa-2"),
+                            ("pdfa-3", "pdfa-3"),
+                        ],
+                        max_length=8,
+                        null=True,
+                        verbose_name="Sets the output PDF type",
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
         migrations.CreateModel(
             name="OcrSettings",
             fields=[
@@ -45,22 +82,6 @@ class Migration(migrations.Migration):
                         verbose_name="Do OCR using these languages",
                     ),
                 ),
-                (
-                    "output_type",
-                    models.CharField(
-                        blank=True,
-                        choices=[
-                            ("pdf", "pdf"),
-                            ("pdfa", "pdfa"),
-                            ("pdfa-1", "pdfa-1"),
-                            ("pdfa-2", "pdfa-2"),
-                            ("pdfa-3", "pdfa-3"),
-                        ],
-                        max_length=8,
-                        null=True,
-                        verbose_name="Sets the output PDF type",
-                    ),
-                ),
                 (
                     "mode",
                     models.CharField(
@@ -135,7 +156,7 @@ class Migration(migrations.Migration):
                     models.FloatField(
                         null=True,
                         validators=[
-                            django.core.validators.MinValueValidator(1_000_000.0),
+                            django.core.validators.MinValueValidator(1000000.0),
                         ],
                         verbose_name="Sets the maximum image size for decompression",
                     ),
@@ -168,8 +189,60 @@ class Migration(migrations.Migration):
                 "verbose_name": "ocr settings",
             },
         ),
-        migrations.RunPython(
+        migrations.CreateModel(
-            code=_create_singleton,
+            name="TextSettings",
-            reverse_code=migrations.RunPython.noop,
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "thumbnail_font_name",
+                    models.CharField(
+                        blank=True,
+                        max_length=64,
+                        null=True,
+                        verbose_name="Sets the output PDF type",
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
         ),
+        migrations.CreateModel(
+            name="TikaSettings",
+            fields=[
+                (
+                    "id",
+                    models.AutoField(
+                        auto_created=True,
+                        primary_key=True,
+                        serialize=False,
+                        verbose_name="ID",
+                    ),
+                ),
+                (
+                    "tika_url",
+                    models.URLField(blank=True, null=True, verbose_name="Tika URL"),
+                ),
+                (
+                    "gotenberg_url",
+                    models.URLField(
+                        blank=True,
+                        null=True,
+                        verbose_name="Gotenberg URL",
+                    ),
+                ),
+            ],
+            options={
+                "abstract": False,
+            },
+        ),
+        migrations.RunPython(_create_singleton, migrations.RunPython.noop),
     ]

src/paperless/models.py

@@ -1,4 +1,3 @@
-from django.core.exceptions import ValidationError
 from django.core.validators import MinValueValidator
 from django.db import models
 from django.utils.translation import gettext_lazy as _
@@ -6,7 +5,23 @@ from django.utils.translation import gettext_lazy as _
 DEFAULT_SINGLETON_INSTANCE_ID = 1
 
 
-class OcrSettings(models.Model):
+class AbstractSingletonModel(models.Model):
+    class Meta:
+        abstract = True
+
+    def save(self, *args, **kwargs):
+        """
+        Always save as the first and only model
+        """
+        self.pk = DEFAULT_SINGLETON_INSTANCE_ID
+        super().save(*args, **kwargs)
+
+
+class CommonSettings(AbstractSingletonModel):
+    """
+    Settings which are common across more than 1 parser
+    """
+
     class OutputTypeChoices(models.TextChoices):
         PDF = ("pdf", _("pdf"))
         PDF_A = ("pdfa", _("pdfa"))
@@ -14,6 +29,20 @@ class OcrSettings(models.Model):
         PDF_A2 = ("pdfa-2", _("pdfa-2"))
         PDF_A3 = ("pdfa-3", _("pdfa-3"))
 
+    output_type = models.CharField(
+        verbose_name=_("Sets the output PDF type"),
+        null=True,
+        blank=True,
+        max_length=8,
+        choices=OutputTypeChoices.choices,
+    )
+
+
+class OcrSettings(AbstractSingletonModel):
+    """
+    Settings for the Tesseract based OCR parser
+    """
+
     class ModeChoices(models.TextChoices):
         SKIP = ("skip", _("skip"))
         SKIP_NO_ARCHIVE = ("skip_noarchive", _("skip_noarchive"))
@@ -50,14 +79,6 @@ class OcrSettings(models.Model):
         max_length=32,
     )
 
-    output_type = models.CharField(
-        verbose_name=_("Sets the output PDF type"),
-        null=True,
-        blank=True,
-        max_length=8,
-        choices=OutputTypeChoices.choices,
-    )
-
     mode = models.CharField(
         verbose_name=_("Sets the OCR mode"),
         null=True,
@@ -124,17 +145,34 @@ class OcrSettings(models.Model):
         verbose_name = _("ocr settings")
 
     def __str__(self) -> str:
-        return ""
+        return "OcrSettings"
 
-    def save(self, *args, **kwargs):
-        if not self.pk and OcrSettings.objects.exists():
-            # if you'll not check for self.pk
-            # then error will also be raised in the update of exists model
-            raise ValidationError(
-                "There is can be only one OcrSettings instance",
-            )
-        return super().save(*args, **kwargs)
 
-    @classmethod
+class TextSettings(AbstractSingletonModel):
-    def object(cls):
+    """
-        return cls._default_manager.all().first()  # Since only one item
+    Settings for the text parser
+    """
+
+    thumbnail_font_name = models.CharField(
+        verbose_name=_("Sets the output PDF type"),
+        null=True,
+        blank=True,
+        max_length=64,
+    )
+
+
+class TikaSettings(AbstractSingletonModel):
+    """
+    Settings for the Tika parser
+    """
+
+    tika_url = models.URLField(
+        verbose_name=_("Tika URL"),
+        null=True,
+        blank=True,
+    )
+    gotenberg_url = models.URLField(
+        verbose_name=_("Gotenberg URL"),
+        null=True,
+        blank=True,
+    )

src/paperless/serialisers.py

@@ -3,6 +3,8 @@ from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
 from rest_framework import serializers
 
+from paperless.models import OcrSettings
+
 
 class ObfuscatedUserPasswordField(serializers.Field):
     """
@@ -113,3 +115,9 @@ class ProfileSerializer(serializers.ModelSerializer):
             "last_name",
             "auth_token",
         )
+
+
+class OcrSettingsSerializer(serializers.ModelSerializer):
+    class Meta:
+        model = OcrSettings
+        fields = ["all"]

src/paperless/views.py

@@ -18,7 +18,9 @@ from rest_framework.viewsets import ModelViewSet
 from documents.permissions import PaperlessObjectPermissions
 from paperless.filters import GroupFilterSet
 from paperless.filters import UserFilterSet
+from paperless.models import OcrSettings
 from paperless.serialisers import GroupSerializer
+from paperless.serialisers import OcrSettingsSerializer
 from paperless.serialisers import ProfileSerializer
 from paperless.serialisers import UserSerializer
 
@@ -160,3 +162,12 @@ class GenerateAuthTokenView(GenericAPIView):
         return Response(
             token.key,
         )
+
+
+class OcrSettingsViewSet(ModelViewSet):
+    model = OcrSettings
+
+    queryset = OcrSettings.objects
+
+    serializer_class = OcrSettingsSerializer
+    permission_classes = (IsAuthenticated,)

src/paperless_tesseract/serialisers.py

@@ -1,9 +0,0 @@
-from rest_framework import serializers
-
-from paperless_tesseract.models import OcrSettings
-
-
-class OcrSettingsSerializer(serializers.ModelSerializer):
-    class Meta:
-        model = OcrSettings
-        fields = ["all"]

src/paperless_tesseract/views.py

@@ -1,14 +0,0 @@
-from rest_framework.permissions import IsAuthenticated
-from rest_framework.viewsets import ModelViewSet
-
-from paperless_tesseract.models import OcrSettings
-from paperless_tesseract.serialisers import OcrSettingsSerializer
-
-
-class OcrSettingsViewSet(ModelViewSet):
-    model = OcrSettings
-
-    queryset = OcrSettings.objects
-
-    serializer_class = OcrSettingsSerializer
-    permission_classes = (IsAuthenticated,)