lgcosta/paperless-ngx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Moving the settings to main paperless application

Browse Source
This commit is contained in:
Trenton H
2023-12-14 09:57:50 -08:00
parent c7876dc0f1
commit d8b254e55e
7 changed files with 175 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

248
src/paperless/migrations/0001_initial.py Normal file
View File

@@ -0,0 +1,248 @@
# Generated by Django 4.2.7 on 2023-12-14 17:12
import django.core.validators
from django.db import migrations
from django.db import models
def _create_singleton(apps, schema_editor):
"""
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):
initial = True
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=[
(
"id",
models.AutoField(
auto_created=True,
primary_key=True,
serialize=False,
verbose_name="ID",
),
),
(
"pages",
models.PositiveIntegerField(
blank=True,
null=True,
verbose_name="Do OCR from page 1 to this value",
),
),
(
"language",
models.CharField(
blank=True,
max_length=32,
null=True,
verbose_name="Do OCR using these languages",
),
),
(
"mode",
models.CharField(
blank=True,
choices=[
("skip", "skip"),
("skip_noarchive", "skip_noarchive"),
("redo", "redo"),
("force", "force"),
],
max_length=8,
null=True,
verbose_name="Sets the OCR mode",
),
),
(
"skip_archive_file",
models.CharField(
blank=True,
choices=[
("never", "never"),
("with_text", "with_text"),
("always", "always"),
],
max_length=16,
null=True,
verbose_name="Controls the generation of an archive file",
),
),
(
"image_dpi",
models.PositiveIntegerField(
null=True,
verbose_name="Sets image DPI fallback value",
),
),
(
"unpaper_clean",
models.CharField(
blank=True,
choices=[
("clean", "clean"),
("clean-final", "clean-final"),
("none", "none"),
],
max_length=16,
null=True,
verbose_name="Controls the unpaper cleaning",
),
),
(
"deskew",
models.BooleanField(null=True, verbose_name="Enables deskew"),
),
(
"rotate_pages",
models.BooleanField(
null=True,
verbose_name="Enables page rotation",
),
),
(
"rotate_pages_threshold",
models.FloatField(
null=True,
validators=[django.core.validators.MinValueValidator(0.0)],
verbose_name="Sets the threshold for rotation of pages",
),
),
(
"max_image_pixels",
models.FloatField(
null=True,
validators=[
django.core.validators.MinValueValidator(1000000.0),
],
verbose_name="Sets the maximum image size for decompression",
),
),
(
"color_conversion_strategy",
models.CharField(
blank=True,
choices=[
("LeaveColorUnchanged", "LeaveColorUnchanged"),
("RGB", "RGB"),
("UseDeviceIndependentColor", "UseDeviceIndependentColor"),
("Gray", "Gray"),
("CMYK", "CMYK"),
],
max_length=32,
null=True,
verbose_name="Sets the Ghostscript color conversion strategy",
),
),
(
"user_args",
models.JSONField(
null=True,
verbose_name="Adds additional user arguments for OCRMyPDF",
),
),
],
options={
"verbose_name": "ocr settings",
},
),
migrations.CreateModel(
name="TextSettings",
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),
]

0
src/paperless/migrations/__init__.py Normal file
View File

178
src/paperless/models.py Normal file
View File

@@ -0,0 +1,178 @@
from django.core.validators import MinValueValidator
from django.db import models
from django.utils.translation import gettext_lazy as _
DEFAULT_SINGLETON_INSTANCE_ID = 1
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"))
PDF_A1 = ("pdfa-1", _("pdfa-1"))
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"))
REDO = ("redo", _("redo"))
FORCE = ("force", _("force"))
class ArchiveFileChoices(models.TextChoices):
NEVER = ("never", _("never"))
WITH_TEXT = ("with_text", _("with_text"))
ALWAYS = ("always", _("always"))
class CleanChoices(models.TextChoices):
CLEAN = ("clean", _("clean"))
FINAL = ("clean-final", _("clean-final"))
NONE = ("none", _("none"))
class ColorConvertChoices(models.TextChoices):
UNCHANGED = ("LeaveColorUnchanged", _("LeaveColorUnchanged"))
RGB = ("RGB", _("RGB"))
INDEPENDENT = ("UseDeviceIndependentColor", _("UseDeviceIndependentColor"))
GRAY = ("Gray", _("Gray"))
CMYK = ("CMYK", _("CMYK"))
pages = models.PositiveIntegerField(
verbose_name=_("Do OCR from page 1 to this value"),
null=True,
blank=True,
)
language = models.CharField(
verbose_name=_("Do OCR using these languages"),
null=True,
blank=True,
max_length=32,
)
mode = models.CharField(
verbose_name=_("Sets the OCR mode"),
null=True,
blank=True,
max_length=8,
choices=ModeChoices.choices,
)
skip_archive_file = models.CharField(
verbose_name=_("Controls the generation of an archive file"),
null=True,
blank=True,
max_length=16,
choices=ArchiveFileChoices.choices,
)
image_dpi = models.PositiveIntegerField(
verbose_name=_("Sets image DPI fallback value"),
null=True,
)
# Can't call it clean, that's a model method
unpaper_clean = models.CharField(
verbose_name=_("Controls the unpaper cleaning"),
null=True,
blank=True,
max_length=16,
choices=CleanChoices.choices,
)
deskew = models.BooleanField(verbose_name=_("Enables deskew"), null=True)
rotate_pages = models.BooleanField(
verbose_name=_("Enables page rotation"),
null=True,
)
rotate_pages_threshold = models.FloatField(
verbose_name=_("Sets the threshold for rotation of pages"),
null=True,
validators=[MinValueValidator(0.0)],
)
max_image_pixels = models.FloatField(
verbose_name=_("Sets the maximum image size for decompression"),
null=True,
validators=[MinValueValidator(1_000_000.0)],
)
color_conversion_strategy = models.CharField(
verbose_name=_("Sets the Ghostscript color conversion strategy"),
blank=True,
null=True,
max_length=32,
choices=ColorConvertChoices.choices,
)
user_args = models.JSONField(
verbose_name=_("Adds additional user arguments for OCRMyPDF"),
null=True,
)
class Meta:
verbose_name = _("ocr settings")
def __str__(self) -> str:
return "OcrSettings"
class TextSettings(AbstractSingletonModel):
"""
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,
)

8
src/paperless/serialisers.py
View File

@@ -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"]

11
src/paperless/views.py
View File

@@ -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,)