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

175
src/paperless_tesseract/migrations/0001_initial.py
View File

@@ -1,175 +0,0 @@
# Generated by Django 4.2.7 on 2023-12-11 19:59
import django.core.validators
from django.db import migrations
from django.db import models
def _create_singleton(apps, schema_editor):
settings_model = apps.get_model("paperless_tesseract", "OcrSettings")
settings_model.objects.create()
class Migration(migrations.Migration):
initial = True
dependencies = []
operations = [
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",
),
),
(
"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(
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(1_000_000.0),
],
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.RunPython(
code=_create_singleton,
reverse_code=migrations.RunPython.noop,
),
]

0
src/paperless_tesseract/migrations/__init__.py
View File

140
src/paperless_tesseract/models.py
View File

@@ -1,140 +0,0 @@
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 _
DEFAULT_SINGLETON_INSTANCE_ID = 1
class OcrSettings(models.Model):
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"))
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,
)
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,
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 ""
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
def object(cls):
return cls._default_manager.all().first() # Since only one item

9
src/paperless_tesseract/serialisers.py
View File

@@ -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"]

14
src/paperless_tesseract/views.py
View File

@@ -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,)