Merge remote-tracking branch 'origin/dev'

docs/configuration.md

@@ -733,7 +733,7 @@ they use underscores instead of dashes.
         Paperless has been tested to work with the OCR options provided
         above. There are many options that are incompatible with each other,
         so specifying invalid options may prevent paperless from consuming
-        any documents.
+        any documents.  Use with caution!
 
     Specify arguments as a JSON dictionary. Keep note of lower case
     booleans and double quoted parameter names and strings. Examples:

src-ui/src/app/components/common/edit-dialog/consumption-template-edit-dialog/consumption-template-edit-dialog.component.html

@@ -17,7 +17,7 @@
         <div class="col-md-4">
           <h5 class="border-bottom pb-2" i18n>Filters</h5>
           <p class="small" i18n>Process documents that match <em>all</em> filters specified below.</p>
-          <pngx-input-select i18n-title title="Filter sources" [items]="sourceOptions" [multiple]="true" formControlName="sources" [error]="error?.filter_filename"></pngx-input-select>
+          <pngx-input-select i18n-title title="Filter sources" [items]="sourceOptions" [multiple]="true" formControlName="sources" [error]="error?.sources"></pngx-input-select>
           <pngx-input-text i18n-title title="Filter filename" formControlName="filter_filename" i18n-hint hint="Apply to documents that match this filename. Wildcards such as *.pdf or *invoice* are allowed. Case insensitive." [error]="error?.filter_filename"></pngx-input-text>
           <pngx-input-text i18n-title title="Filter path" formControlName="filter_path" i18n-hint hint="Apply to documents that match this path. Wildcards specified as * are allowed. Case insensitive.</a>" [error]="error?.filter_path"></pngx-input-text>
           <pngx-input-select i18n-title title="Filter mail rule" [items]="mailRules" [allowNull]="true" formControlName="filter_mailrule" i18n-hint hint="Apply to documents consumed via this mail rule." [error]="error?.filter_mailrule"></pngx-input-select>

src-ui/src/app/components/common/input/select/select.component.html

@@ -9,7 +9,7 @@
       </button>
     </div>
     <div [class.col-md-9]="horizontal">
-      <div [class.input-group]="allowCreateNew || showFilter">
+      <div [class.input-group]="allowCreateNew || showFilter" [class.is-invalid]="error">
         <ng-select name="inputId" [(ngModel)]="value"
           [disabled]="disabled"
           [style.color]="textColor"
@@ -42,6 +42,9 @@
           </svg>
         </button>
       </div>
+      <div class="invalid-feedback">
+        {{error}}
+      </div>
       <small *ngIf="hint" class="form-text text-muted">{{hint}}</small>
       <small *ngIf="getSuggestions().length > 0">
         <span i18n>Suggestions:</span>&nbsp;

src-ui/src/app/components/common/input/select/select.component.scss

@@ -17,3 +17,12 @@
     font-style: italic;
     opacity: .75;
 }
+
+::ng-deep .is-invalid ng-select .ng-select-container input {
+    // replicate bootstrap
+    padding-right: calc(1.5em + 0.75rem) !important;
+    background-image: url("data:image/svg+xml,%3csvg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 12 12' width='12' height='12' fill='none' stroke='%23dc3545'%3e%3ccircle cx='6' cy='6' r='4.5'/%3e%3cpath stroke-linejoin='round' d='M5.8 3.6h.4L6 6.5z'/%3e%3ccircle cx='6' cy='8.2' r='.6' fill='%23dc3545' stroke='none'/%3e%3c/svg%3e") !important;
+    background-repeat: no-repeat !important;
+    background-position: right calc(0.375em + 0.1875rem) center !important;
+    background-size: calc(0.75em + 0.375rem) calc(0.75em + 0.375rem) !important;
+}

src-ui/src/environments/environment.prod.ts

@@ -5,7 +5,7 @@ export const environment = {
   apiBaseUrl: document.baseURI + 'api/',
   apiVersion: '3',
   appTitle: 'Paperless-ngx',
-  version: '2.1.2',
+  version: '2.1.2-dev',
   webSocketHost: window.location.host,
   webSocketProtocol: window.location.protocol == 'https:' ? 'wss:' : 'ws:',
   webSocketBaseUrl: base_url.pathname + 'ws/',

src-ui/src/locale/messages.fr_FR.xlf

@@ -10,13 +10,13 @@
         </context-group>
         <target state="final">Fermer</target>
       </trans-unit>
-      <trans-unit id="ngb.timepicker.HH" datatype="html">
+      <trans-unit id="ngb.timepicker.HH" datatype="html" approved="yes">
         <source>HH</source>
         <context-group purpose="location">
           <context context-type="sourcefile">node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
-        <target state="translated">HH</target>
+        <target state="final">HH</target>
       </trans-unit>
       <trans-unit id="ngb.toast.close-aria" datatype="html" approved="yes">
         <source>Close</source>
@@ -100,13 +100,13 @@
         </context-group>
         <target state="final">Précédent</target>
       </trans-unit>
-      <trans-unit id="ngb.timepicker.MM" datatype="html">
+      <trans-unit id="ngb.timepicker.MM" datatype="html" approved="yes">
         <source>MM</source>
         <context-group purpose="location">
           <context context-type="sourcefile">node_modules/src/ngb-config.ts</context>
           <context context-type="linenumber">13</context>
         </context-group>
-        <target state="translated">MM</target>
+        <target state="final">MM</target>
       </trans-unit>
       <trans-unit id="ngb.pagination.next" datatype="html" approved="yes">
         <source>»</source>

src-ui/src/locale/messages.hr_HR.xlf

@@ -288,7 +288,7 @@
           <context context-type="sourcefile">src/app/app.component.ts</context>
           <context context-type="linenumber">90</context>
         </context-group>
-        <target state="needs-translation">Document <x id="PH" equiv-text="status.filename"/> was added to Paperless-ngx.</target>
+        <target state="translated">Dokument <x id="PH" equiv-text="status.filename"/> je dodan u Paperless-ngx.</target>
       </trans-unit>
       <trans-unit id="1931214133925051574" datatype="html">
         <source>Open document</source>
@@ -316,7 +316,7 @@
           <context context-type="sourcefile">src/app/app.component.ts</context>
           <context context-type="linenumber">120</context>
         </context-group>
-        <target state="needs-translation">Document <x id="PH" equiv-text="status.filename"/> is being processed by Paperless-ngx.</target>
+        <target state="translated">Dokument <x id="PH" equiv-text="status.filename"/> je u fazi obrade.</target>
       </trans-unit>
       <trans-unit id="2501522447884928778" datatype="html">
         <source>Prev</source>
@@ -476,7 +476,7 @@
           <context context-type="sourcefile">src/app/components/admin/tasks/tasks.component.html</context>
           <context context-type="linenumber">15</context>
         </context-group>
-        <target state="needs-translation">Auto refresh</target>
+        <target state="translated">Automatsko osvježavanje</target>
       </trans-unit>
       <trans-unit id="3894950702316166331" datatype="html">
         <source>Loading...</source>
@@ -596,7 +596,7 @@
           <context context-type="sourcefile">src/app/components/admin/settings/settings.component.html</context>
           <context context-type="linenumber">15</context>
         </context-group>
-        <target state="needs-translation">General</target>
+        <target state="translated">Općenito</target>
       </trans-unit>
       <trans-unit id="8671234314555525900" datatype="html">
         <source>Appearance</source>
@@ -916,7 +916,7 @@
           <context context-type="sourcefile">src/app/components/admin/settings/settings.component.html</context>
           <context context-type="linenumber">178,180</context>
         </context-group>
-        <target state="needs-translation"> Settings apply to this user account for objects (Tags, Mail Rules, etc.) created via the web UI </target>
+        <target state="translated"> Postavke ovog korisničkog računa za objekte (Oznake, Pravila za e-poštu, itd.) stvorene putem web sučelja </target>
       </trans-unit>
       <trans-unit id="4292903881380648974" datatype="html">
         <source>Default Owner</source>
@@ -2074,7 +2074,7 @@
           <context context-type="sourcefile">src/app/components/admin/users-groups/users-groups.component.ts</context>
           <context context-type="linenumber">124</context>
         </context-group>
-        <target state="needs-translation">Deleted user</target>
+        <target state="translated">Izbrisani korisnik</target>
       </trans-unit>
       <trans-unit id="1942566571910298572" datatype="html">
         <source>Error deleting user.</source>
@@ -2479,7 +2479,7 @@
           <context context-type="sourcefile">src/app/components/app-frame/app-frame.component.ts</context>
           <context context-type="linenumber">276</context>
         </context-group>
-        <target state="needs-translation">An error occurred while saving update checking settings.</target>
+        <target state="translated">Došlo je do pogreške prilikom spremanja postavki ažuriranja.</target>
       </trans-unit>
       <trans-unit id="8700121026680200191" datatype="html">
         <source>Clear</source>
@@ -3039,7 +3039,7 @@
           <context context-type="sourcefile">src/app/components/common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component.html</context>
           <context context-type="linenumber">9</context>
         </context-group>
-        <target state="needs-translation">Data type</target>
+        <target state="translated">Tip podataka</target>
       </trans-unit>
       <trans-unit id="5933665691581884232" datatype="html">
         <source>Data type cannot be changed after a field is created</source>
@@ -3047,7 +3047,7 @@
           <context context-type="sourcefile">src/app/components/common/edit-dialog/custom-field-edit-dialog/custom-field-edit-dialog.component.html</context>
           <context context-type="linenumber">10</context>
         </context-group>
-        <target state="needs-translation">Data type cannot be changed after a field is created</target>
+        <target state="translated">Tip podataka ne može se promijeniti nakon što je polje stvoreno</target>
       </trans-unit>
       <trans-unit id="528950215505228201" datatype="html">
         <source>Create new custom field</source>
@@ -3175,7 +3175,7 @@
           <context context-type="sourcefile">src/app/components/common/edit-dialog/mail-account-edit-dialog/mail-account-edit-dialog.component.html</context>
           <context context-type="linenumber">19</context>
         </context-group>
-        <target state="needs-translation">Character Set</target>
+        <target state="translated">Skup znakova</target>
       </trans-unit>
       <trans-unit id="6563391987554512024" datatype="html">
         <source>Test</source>

src/documents/barcodes.py

@@ -14,6 +14,8 @@ from pikepdf import Pdf
 from PIL import Image
 
 from documents.converters import convert_from_tiff_to_pdf
+from documents.data_models import ConsumableDocument
+from documents.data_models import DocumentMetadataOverrides
 from documents.data_models import DocumentSource
 from documents.utils import copy_basic_file_stats
 from documents.utils import copy_file_with_basic_stats
@@ -53,6 +55,7 @@ class BarcodeReader:
         self.mime: Final[str] = mime_type
         self.pdf_file: Path = self.file
         self.barcodes: list[Barcode] = []
+        self._tiff_conversion_done = False
         self.temp_dir: Optional[tempfile.TemporaryDirectory] = None
 
         if settings.CONSUMER_BARCODE_TIFF_SUPPORT:
@@ -150,12 +153,14 @@ class BarcodeReader:
 
     def convert_from_tiff_to_pdf(self):
         """
-        May convert a TIFF image into a PDF, if the input is a TIFF
+        May convert a TIFF image into a PDF, if the input is a TIFF and
+        the TIFF has not been made into a PDF
         """
         # Nothing to do, pdf_file is already assigned correctly
-        if self.mime != "image/tiff":
+        if self.mime != "image/tiff" or self._tiff_conversion_done:
             return
 
+        self._tiff_conversion_done = True
         self.pdf_file = convert_from_tiff_to_pdf(self.file, Path(self.temp_dir.name))
 
     def detect(self) -> None:
@@ -167,6 +172,9 @@ class BarcodeReader:
         if self.barcodes:
             return
 
+        # No op if not a TIFF
+        self.convert_from_tiff_to_pdf()
+
         # Choose the library for reading
         if settings.CONSUMER_BARCODE_SCANNER == "PYZBAR":
             reader = self.read_barcodes_pyzbar
@@ -240,7 +248,7 @@ class BarcodeReader:
         """
 
         document_paths = []
-        fname = self.file.with_suffix("").name
+        fname = self.file.stem
         with Pdf.open(self.pdf_file) as input_pdf:
             # Start with an empty document
             current_document: list[Page] = []
@@ -290,7 +298,7 @@ class BarcodeReader:
     def separate(
         self,
         source: DocumentSource,
-        override_name: Optional[str] = None,
+        overrides: DocumentMetadataOverrides,
     ) -> bool:
         """
         Separates the document, based on barcodes and configuration, creating new
@@ -316,27 +324,23 @@ class BarcodeReader:
             logger.warning("No pages to split on!")
             return False
 
-        # Create the split documents
+        tmp_dir = Path(tempfile.mkdtemp(prefix="paperless-barcode-split-")).resolve()
-        doc_paths = self.separate_pages(separator_pages)
 
-        # Save the new documents to correct folder
+        from documents import tasks
-        if source != DocumentSource.ConsumeFolder:
-            # The given file is somewhere in SCRATCH_DIR,
-            # and new documents must be moved to the CONSUMPTION_DIR
-            # for the consumer to notice them
-            save_to_dir = settings.CONSUMPTION_DIR
-        else:
-            # The given file is somewhere in CONSUMPTION_DIR,
-            # and may be some levels down for recursive tagging
-            # so use the file's parent to preserve any metadata
-            save_to_dir = self.file.parent
 
-        for idx, document_path in enumerate(doc_paths):
+        # Create the split document tasks
-            if override_name is not None:
+        for new_document in self.separate_pages(separator_pages):
-                newname = f"{idx}_{override_name}"
+            copy_file_with_basic_stats(new_document, tmp_dir / new_document.name)
-                dest = save_to_dir / newname
+
-            else:
+            tasks.consume_file.delay(
-                dest = save_to_dir
+                ConsumableDocument(
-            logger.info(f"Saving {document_path} to {dest}")
+                    # Same source, for templates
-            copy_file_with_basic_stats(document_path, dest)
+                    source=source,
+                    # Can't use same folder or the consume might grab it again
+                    original_file=(tmp_dir / new_document.name).resolve(),
+                ),
+                # All the same metadata
+                overrides,
+            )
+        logger.info("Barcode splitting complete!")
         return True

src/documents/index.py

@@ -3,6 +3,7 @@ import math
 import os
 from collections import Counter
 from contextlib import contextmanager
+from datetime import datetime
 from typing import Optional
 
 from dateutil.parser import isoparse
@@ -371,7 +372,7 @@ class LocalDateParser(English):
         if isinstance(d, timespan):
             d.start = self.reverse_timezone_offset(d.start)
             d.end = self.reverse_timezone_offset(d.end)
-        else:
+        elif isinstance(d, datetime):
             d = self.reverse_timezone_offset(d)
         return d
 

src/documents/management/commands/document_exporter.py

@@ -238,18 +238,6 @@ class Command(BaseCommand):
                 serializers.serialize("json", StoragePath.objects.all()),
             )
 
-            notes = json.loads(
-                serializers.serialize("json", Note.objects.all()),
-            )
-            if not self.split_manifest:
-                manifest += notes
-
-            documents = Document.objects.order_by("id")
-            document_map = {d.pk: d for d in documents}
-            document_manifest = json.loads(serializers.serialize("json", documents))
-            if not self.split_manifest:
-                manifest += document_manifest
-
             manifest += json.loads(
                 serializers.serialize("json", MailAccount.objects.all()),
             )
@@ -303,10 +291,24 @@ class Command(BaseCommand):
                 serializers.serialize("json", CustomField.objects.all()),
             )
 
+            # These are treated specially and included in the per-document manifest
+            # if that setting is enabled.  Otherwise, they are just exported to the bulk
+            # manifest
+            documents = Document.objects.order_by("id")
+            document_map: dict[int, Document] = {d.pk: d for d in documents}
+            document_manifest = json.loads(serializers.serialize("json", documents))
+
+            notes = json.loads(
+                serializers.serialize("json", Note.objects.all()),
+            )
+
+            custom_field_instances = json.loads(
+                serializers.serialize("json", CustomFieldInstance.objects.all()),
+            )
             if not self.split_manifest:
-                manifest += json.loads(
+                manifest += document_manifest
-                    serializers.serialize("json", CustomFieldInstance.objects.all()),
+                manifest += notes
-                )
+                manifest += custom_field_instances
 
         # 3. Export files from each document
         for index, document_dict in tqdm.tqdm(
@@ -412,6 +414,12 @@ class Command(BaseCommand):
                         notes,
                     ),
                 )
+                content += list(
+                    filter(
+                        lambda d: d["fields"]["document"] == document_dict["pk"],
+                        custom_field_instances,
+                    ),
+                )
                 manifest_name.write_text(
                     json.dumps(content, indent=2, ensure_ascii=False),
                     encoding="utf-8",

src/documents/tasks.py

@@ -140,7 +140,7 @@ def consume_file(
         with BarcodeReader(input_doc.original_file, input_doc.mime_type) as reader:
             if settings.CONSUMER_ENABLE_BARCODES and reader.separate(
                 input_doc.source,
-                overrides.filename,
+                overrides,
             ):
                 # notify the sender, otherwise the progress bar
                 # in the UI stays stuck

src/documents/tests/test_api_search.py

@@ -455,6 +455,31 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
             # Assert subset in results
             self.assertDictEqual(result, {**result, **subset})
 
+    def test_search_added_invalid_date(self):
+        """
+        GIVEN:
+            - One document added right now
+        WHEN:
+            - Query with invalid added date
+        THEN:
+            - No documents returned
+        """
+        d1 = Document.objects.create(
+            title="invoice",
+            content="the thing i bought at a shop and paid with bank account",
+            checksum="A",
+            pk=1,
+        )
+
+        with index.open_index_writer() as writer:
+            index.update_document(writer, d1)
+
+        response = self.client.get("/api/documents/?query=added:invalid-date")
+        results = response.data["results"]
+
+        # Expect 0 document returned
+        self.assertEqual(len(results), 0)
+
     @mock.patch("documents.index.autocomplete")
     def test_search_autocomplete_limits(self, m):
         """

src/documents/tests/test_barcodes.py

@@ -1,5 +1,4 @@
 import shutil
-from pathlib import Path
 from unittest import mock
 
 import pytest
@@ -11,10 +10,13 @@ from documents import tasks
 from documents.barcodes import BarcodeReader
 from documents.consumer import ConsumerError
 from documents.data_models import ConsumableDocument
+from documents.data_models import DocumentMetadataOverrides
 from documents.data_models import DocumentSource
 from documents.models import Document
 from documents.tests.utils import DirectoriesMixin
+from documents.tests.utils import DocumentConsumeDelayMixin
 from documents.tests.utils import FileSystemAssertsMixin
+from documents.tests.utils import SampleDirMixin
 
 try:
     import zxingcpp  # noqa: F401
@@ -25,11 +27,7 @@ except ImportError:
 
 
 @override_settings(CONSUMER_BARCODE_SCANNER="PYZBAR")
-class TestBarcode(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
+class TestBarcode(DirectoriesMixin, FileSystemAssertsMixin, SampleDirMixin, TestCase):
-    SAMPLE_DIR = Path(__file__).parent / "samples"
-
-    BARCODE_SAMPLE_DIR = SAMPLE_DIR / "barcodes"
-
     def test_scan_file_for_separating_barcodes(self):
         """
         GIVEN:
@@ -48,6 +46,46 @@ class TestBarcode(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
             self.assertEqual(reader.pdf_file, test_file)
             self.assertDictEqual(separator_page_numbers, {0: False})
 
+    @override_settings(
+        CONSUMER_BARCODE_TIFF_SUPPORT=True,
+    )
+    def test_scan_tiff_for_separating_barcodes(self):
+        """
+        GIVEN:
+            - TIFF image containing barcodes
+        WHEN:
+            - Consume task returns
+        THEN:
+            - The file was split
+        """
+        test_file = self.BARCODE_SAMPLE_DIR / "patch-code-t-middle.tiff"
+
+        with BarcodeReader(test_file, "image/tiff") as reader:
+            reader.detect()
+            separator_page_numbers = reader.get_separation_pages()
+
+            self.assertDictEqual(separator_page_numbers, {1: False})
+
+    @override_settings(
+        CONSUMER_BARCODE_TIFF_SUPPORT=True,
+    )
+    def test_scan_tiff_with_alpha_for_separating_barcodes(self):
+        """
+        GIVEN:
+            - TIFF image containing barcodes
+        WHEN:
+            - Consume task returns
+        THEN:
+            - The file was split
+        """
+        test_file = self.BARCODE_SAMPLE_DIR / "patch-code-t-middle-alpha.tiff"
+
+        with BarcodeReader(test_file, "image/tiff") as reader:
+            reader.detect()
+            separator_page_numbers = reader.get_separation_pages()
+
+            self.assertDictEqual(separator_page_numbers, {1: False})
+
     def test_scan_file_for_separating_barcodes_none_present(self):
         """
         GIVEN:
@@ -285,6 +323,28 @@ class TestBarcode(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
             self.assertGreater(len(reader.barcodes), 0)
             self.assertDictEqual(separator_page_numbers, {1: False})
 
+    def test_scan_file_for_separating_barcodes_password(self):
+        """
+        GIVEN:
+            - Password protected PDF
+        WHEN:
+            - File is scanned for barcode
+        THEN:
+            - Scanning handles the exception without crashing
+        """
+        test_file = self.SAMPLE_DIR / "password-is-test.pdf"
+        with self.assertLogs("paperless.barcodes", level="WARNING") as cm:
+            with BarcodeReader(test_file, "application/pdf") as reader:
+                reader.detect()
+                warning = cm.output[0]
+                expected_str = "WARNING:paperless.barcodes:File is likely password protected, not checking for barcodes"
+                self.assertTrue(warning.startswith(expected_str))
+
+                separator_page_numbers = reader.get_separation_pages()
+
+                self.assertEqual(reader.pdf_file, test_file)
+                self.assertDictEqual(separator_page_numbers, {})
+
     def test_separate_pages(self):
         """
         GIVEN:
@@ -332,8 +392,12 @@ class TestBarcode(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
 
         with self.assertLogs("paperless.barcodes", level="WARNING") as cm:
             with BarcodeReader(test_file, "application/pdf") as reader:
-                success = reader.separate(DocumentSource.ApiUpload)
+                self.assertFalse(
-                self.assertFalse(success)
+                    reader.separate(
+                        DocumentSource.ApiUpload,
+                        DocumentMetadataOverrides(),
+                    ),
+                )
                 self.assertEqual(
                     cm.output,
                     [
@@ -341,215 +405,6 @@ class TestBarcode(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
                     ],
                 )
 
-    def test_save_to_dir_given_name(self):
-        """
-        GIVEN:
-            - File to save to a directory
-            - There is a name override
-        WHEN:
-            - The file is saved
-        THEN:
-            - The file exists
-        """
-        test_file = self.BARCODE_SAMPLE_DIR / "patch-code-t-middle.pdf"
-        with BarcodeReader(test_file, "application/pdf") as reader:
-            reader.separate(DocumentSource.ApiUpload, "newname.pdf")
-
-            self.assertEqual(reader.pdf_file, test_file)
-            target_file1 = settings.CONSUMPTION_DIR / "0_newname.pdf"
-            target_file2 = settings.CONSUMPTION_DIR / "1_newname.pdf"
-            self.assertIsFile(target_file1)
-            self.assertIsFile(target_file2)
-
-    def test_barcode_splitter_api_upload(self):
-        """
-        GIVEN:
-            - Input file containing barcodes
-        WHEN:
-            - Input file is split on barcodes
-        THEN:
-            - Correct number of files produced
-        """
-        sample_file = self.BARCODE_SAMPLE_DIR / "patch-code-t-middle.pdf"
-        test_file = settings.SCRATCH_DIR / "patch-code-t-middle.pdf"
-        shutil.copy(sample_file, test_file)
-
-        with BarcodeReader(test_file, "application/pdf") as reader:
-            reader.separate(DocumentSource.ApiUpload)
-
-            self.assertEqual(reader.pdf_file, test_file)
-
-            target_file1 = (
-                settings.CONSUMPTION_DIR / "patch-code-t-middle_document_0.pdf"
-            )
-
-            target_file2 = (
-                settings.CONSUMPTION_DIR / "patch-code-t-middle_document_1.pdf"
-            )
-
-            self.assertIsFile(target_file1)
-            self.assertIsFile(target_file2)
-
-    def test_barcode_splitter_consume_dir(self):
-        """
-        GIVEN:
-            - Input file containing barcodes
-        WHEN:
-            - Input file is split on barcodes
-        THEN:
-            - Correct number of files produced
-        """
-        sample_file = self.BARCODE_SAMPLE_DIR / "patch-code-t-middle.pdf"
-        test_file = settings.CONSUMPTION_DIR / "patch-code-t-middle.pdf"
-        shutil.copy(sample_file, test_file)
-
-        with BarcodeReader(test_file, "application/pdf") as reader:
-            reader.detect()
-            reader.separate(DocumentSource.ConsumeFolder)
-
-            self.assertEqual(reader.pdf_file, test_file)
-
-            target_file1 = (
-                settings.CONSUMPTION_DIR / "patch-code-t-middle_document_0.pdf"
-            )
-
-            target_file2 = (
-                settings.CONSUMPTION_DIR / "patch-code-t-middle_document_1.pdf"
-            )
-
-            self.assertIsFile(target_file1)
-            self.assertIsFile(target_file2)
-
-    def test_barcode_splitter_consume_dir_recursive(self):
-        """
-        GIVEN:
-            - Input file containing barcodes
-            - Input file is within a directory structure of the consume folder
-        WHEN:
-            - Input file is split on barcodes
-        THEN:
-            - Correct number of files produced
-            - Output files are within the same directory structure
-        """
-        sample_file = self.BARCODE_SAMPLE_DIR / "patch-code-t-middle.pdf"
-        test_file = (
-            settings.CONSUMPTION_DIR / "tag1" / "tag2" / "patch-code-t-middle.pdf"
-        )
-        test_file.parent.mkdir(parents=True)
-        shutil.copy(sample_file, test_file)
-
-        with BarcodeReader(test_file, "application/pdf") as reader:
-            reader.separate(DocumentSource.ConsumeFolder)
-
-            self.assertEqual(reader.pdf_file, test_file)
-
-            target_file1 = (
-                settings.CONSUMPTION_DIR
-                / "tag1"
-                / "tag2"
-                / "patch-code-t-middle_document_0.pdf"
-            )
-
-            target_file2 = (
-                settings.CONSUMPTION_DIR
-                / "tag1"
-                / "tag2"
-                / "patch-code-t-middle_document_1.pdf"
-            )
-
-            self.assertIsFile(target_file1)
-            self.assertIsFile(target_file2)
-
-    @override_settings(CONSUMER_ENABLE_BARCODES=True)
-    def test_consume_barcode_file(self):
-        """
-        GIVEN:
-            - Input file with barcodes given to consume task
-        WHEN:
-            - Consume task returns
-        THEN:
-            - The file was split
-        """
-        test_file = self.BARCODE_SAMPLE_DIR / "patch-code-t-middle.pdf"
-
-        dst = settings.SCRATCH_DIR / "patch-code-t-middle.pdf"
-        shutil.copy(test_file, dst)
-
-        with mock.patch("documents.tasks.async_to_sync"):
-            self.assertEqual(
-                tasks.consume_file(
-                    ConsumableDocument(
-                        source=DocumentSource.ConsumeFolder,
-                        original_file=dst,
-                    ),
-                    None,
-                ),
-                "File successfully split",
-            )
-
-    @override_settings(
-        CONSUMER_ENABLE_BARCODES=True,
-        CONSUMER_BARCODE_TIFF_SUPPORT=True,
-    )
-    def test_consume_barcode_tiff_file(self):
-        """
-        GIVEN:
-            - TIFF image containing barcodes
-        WHEN:
-            - Consume task returns
-        THEN:
-            - The file was split
-        """
-        test_file = self.BARCODE_SAMPLE_DIR / "patch-code-t-middle.tiff"
-
-        dst = settings.SCRATCH_DIR / "patch-code-t-middle.tiff"
-        shutil.copy(test_file, dst)
-
-        with mock.patch("documents.tasks.async_to_sync"):
-            self.assertEqual(
-                tasks.consume_file(
-                    ConsumableDocument(
-                        source=DocumentSource.ConsumeFolder,
-                        original_file=dst,
-                    ),
-                    None,
-                ),
-                "File successfully split",
-            )
-        self.assertIsNotFile(dst)
-
-    @override_settings(
-        CONSUMER_ENABLE_BARCODES=True,
-        CONSUMER_BARCODE_TIFF_SUPPORT=True,
-    )
-    def test_consume_barcode_tiff_file_with_alpha(self):
-        """
-        GIVEN:
-            - TIFF image containing barcodes
-            - TIFF image has an alpha layer
-        WHEN:
-            - Consume task handles the alpha layer and returns
-        THEN:
-            - The file was split without issue
-        """
-        test_file = self.BARCODE_SAMPLE_DIR / "patch-code-t-middle-alpha.tiff"
-
-        dst = settings.SCRATCH_DIR / "patch-code-t-middle.tiff"
-        shutil.copy(test_file, dst)
-
-        with mock.patch("documents.tasks.async_to_sync"):
-            self.assertEqual(
-                tasks.consume_file(
-                    ConsumableDocument(
-                        source=DocumentSource.ConsumeFolder,
-                        original_file=dst,
-                    ),
-                    None,
-                ),
-                "File successfully split",
-            )
-        self.assertIsNotFile(dst)
-
     @override_settings(
         CONSUMER_ENABLE_BARCODES=True,
         CONSUMER_BARCODE_TIFF_SUPPORT=True,
@@ -597,60 +452,6 @@ class TestBarcode(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         self.assertIsNone(kwargs["override_document_type_id"])
         self.assertIsNone(kwargs["override_tag_ids"])
 
-    @override_settings(
-        CONSUMER_ENABLE_BARCODES=True,
-        CONSUMER_BARCODE_TIFF_SUPPORT=True,
-    )
-    def test_consume_barcode_supported_no_extension_file(self):
-        """
-        GIVEN:
-            - TIFF image containing barcodes
-            - TIFF file is given without extension
-        WHEN:
-            - Consume task returns
-        THEN:
-            - The file was split
-        """
-        test_file = self.BARCODE_SAMPLE_DIR / "patch-code-t-middle.tiff"
-
-        dst = settings.SCRATCH_DIR / "patch-code-t-middle"
-        shutil.copy(test_file, dst)
-
-        with mock.patch("documents.tasks.async_to_sync"):
-            self.assertEqual(
-                tasks.consume_file(
-                    ConsumableDocument(
-                        source=DocumentSource.ConsumeFolder,
-                        original_file=dst,
-                    ),
-                    None,
-                ),
-                "File successfully split",
-            )
-        self.assertIsNotFile(dst)
-
-    def test_scan_file_for_separating_barcodes_password(self):
-        """
-        GIVEN:
-            - Password protected PDF
-        WHEN:
-            - File is scanned for barcode
-        THEN:
-            - Scanning handles the exception without crashing
-        """
-        test_file = self.SAMPLE_DIR / "password-is-test.pdf"
-        with self.assertLogs("paperless.barcodes", level="WARNING") as cm:
-            with BarcodeReader(test_file, "application/pdf") as reader:
-                reader.detect()
-                warning = cm.output[0]
-                expected_str = "WARNING:paperless.barcodes:File is likely password protected, not checking for barcodes"
-                self.assertTrue(warning.startswith(expected_str))
-
-                separator_page_numbers = reader.get_separation_pages()
-
-                self.assertEqual(reader.pdf_file, test_file)
-                self.assertDictEqual(separator_page_numbers, {})
-
     @override_settings(
         CONSUMER_ENABLE_BARCODES=True,
         CONSUMER_ENABLE_ASN_BARCODE=True,
@@ -722,11 +523,64 @@ class TestBarcode(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
             self.assertEqual(len(document_list), 5)
 
 
-class TestAsnBarcode(DirectoriesMixin, TestCase):
+@override_settings(CONSUMER_BARCODE_SCANNER="PYZBAR")
-    SAMPLE_DIR = Path(__file__).parent / "samples"
+class TestBarcodeNewConsume(
+    DirectoriesMixin,
+    FileSystemAssertsMixin,
+    SampleDirMixin,
+    DocumentConsumeDelayMixin,
+    TestCase,
+):
+    @override_settings(CONSUMER_ENABLE_BARCODES=True)
+    def test_consume_barcode_file(self):
+        """
+        GIVEN:
+            - Incoming file with at 1 barcode producing 2 documents
+            - Document includes metadata override information
+        WHEN:
+            - The document is split
+        THEN:
+            - Two new consume tasks are created
+            - Metadata overrides are preserved for the new consume
+            - The document source is unchanged (for consume templates)
+        """
+        test_file = self.BARCODE_SAMPLE_DIR / "patch-code-t-middle.pdf"
+        temp_copy = self.dirs.scratch_dir / test_file.name
+        shutil.copy(test_file, temp_copy)
 
-    BARCODE_SAMPLE_DIR = SAMPLE_DIR / "barcodes"
+        overrides = DocumentMetadataOverrides(tag_ids=[1, 2, 9])
 
+        with mock.patch("documents.tasks.async_to_sync") as progress_mocker:
+            self.assertEqual(
+                tasks.consume_file(
+                    ConsumableDocument(
+                        source=DocumentSource.ConsumeFolder,
+                        original_file=temp_copy,
+                    ),
+                    overrides,
+                ),
+                "File successfully split",
+            )
+            # We let the consumer know progress is done
+            progress_mocker.assert_called_once()
+            # 2 new document consume tasks created
+            self.assertEqual(self.consume_file_mock.call_count, 2)
+
+            self.assertIsNotFile(temp_copy)
+
+            # Check the split files exist
+            # Check the source is unchanged
+            # Check the overrides are unchanged
+            for (
+                new_input_doc,
+                new_doc_overrides,
+            ) in self.get_all_consume_delay_call_args():
+                self.assertEqual(new_input_doc.source, DocumentSource.ConsumeFolder)
+                self.assertIsFile(new_input_doc.original_file)
+                self.assertEqual(overrides, new_doc_overrides)
+
+
+class TestAsnBarcode(DirectoriesMixin, SampleDirMixin, TestCase):
     @override_settings(CONSUMER_ASN_BARCODE_PREFIX="CUSTOM-PREFIX-")
     def test_scan_file_for_asn_custom_prefix(self):
         """

src/documents/tests/test_management_exporter.py

@@ -646,10 +646,13 @@ class TestExportImport(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
 
         with paperless_environment():
             self.assertEqual(Document.objects.count(), 4)
+            self.assertEqual(CustomFieldInstance.objects.count(), 1)
             Document.objects.all().delete()
+            CustomFieldInstance.objects.all().delete()
             self.assertEqual(Document.objects.count(), 0)
             call_command("document_importer", "--no-progress-bar", self.target)
             self.assertEqual(Document.objects.count(), 4)
+            self.assertEqual(CustomFieldInstance.objects.count(), 1)
 
     def test_folder_prefix(self):
         """

src/documents/tests/utils.py

@@ -235,8 +235,10 @@ class DocumentConsumeDelayMixin:
         """
         Iterates over all calls to the async task and returns the arguments
         """
+        # Must be at least 1 call
+        self.consume_file_mock.assert_called()
 
-        for args, _ in self.consume_file_mock.call_args_list:
+        for args, kwargs in self.consume_file_mock.call_args_list:
             input_doc, overrides = args
 
             yield (input_doc, overrides)
@@ -244,7 +246,7 @@ class DocumentConsumeDelayMixin:
     def get_specific_consume_delay_call_args(
         self,
         index: int,
-    ) -> Iterator[tuple[ConsumableDocument, DocumentMetadataOverrides]]:
+    ) -> tuple[ConsumableDocument, DocumentMetadataOverrides]:
         """
         Returns the arguments of a specific call to the async task
         """
@@ -299,3 +301,9 @@ class TestMigrations(TransactionTestCase):
 
     def setUpBeforeMigration(self, apps):
         pass
+
+
+class SampleDirMixin:
+    SAMPLE_DIR = Path(__file__).parent / "samples"
+
+    BARCODE_SAMPLE_DIR = SAMPLE_DIR / "barcodes"

src/documents/views.py

@@ -182,10 +182,14 @@ class PassUserMixin(CreateModelMixin):
 class CorrespondentViewSet(ModelViewSet, PassUserMixin):
     model = Correspondent
 
-    queryset = Correspondent.objects.annotate(
+    queryset = (
-        document_count=Count("documents"),
+        Correspondent.objects.annotate(
-        last_correspondence=Max("documents__created"),
+            document_count=Count("documents"),
-    ).order_by(Lower("name"))
+            last_correspondence=Max("documents__created"),
+        )
+        .select_related("owner")
+        .order_by(Lower("name"))
+    )
 
     serializer_class = CorrespondentSerializer
     pagination_class = StandardPagination
@@ -208,8 +212,12 @@ class CorrespondentViewSet(ModelViewSet, PassUserMixin):
 class TagViewSet(ModelViewSet, PassUserMixin):
     model = Tag
 
-    queryset = Tag.objects.annotate(document_count=Count("documents")).order_by(
+    queryset = (
-        Lower("name"),
+        Tag.objects.annotate(document_count=Count("documents"))
+        .select_related("owner")
+        .order_by(
+            Lower("name"),
+        )
     )
 
     def get_serializer_class(self, *args, **kwargs):
@@ -232,9 +240,13 @@ class TagViewSet(ModelViewSet, PassUserMixin):
 class DocumentTypeViewSet(ModelViewSet, PassUserMixin):
     model = DocumentType
 
-    queryset = DocumentType.objects.annotate(
+    queryset = (
-        document_count=Count("documents"),
+        DocumentType.objects.annotate(
-    ).order_by(Lower("name"))
+            document_count=Count("documents"),
+        )
+        .select_related("owner")
+        .order_by(Lower("name"))
+    )
 
     serializer_class = DocumentTypeSerializer
     pagination_class = StandardPagination
@@ -283,7 +295,12 @@ class DocumentViewSet(
     )
 
     def get_queryset(self):
-        return Document.objects.distinct().annotate(num_notes=Count("notes"))
+        return (
+            Document.objects.distinct()
+            .annotate(num_notes=Count("notes"))
+            .select_related("correspondent", "storage_path", "document_type", "owner")
+            .prefetch_related("tags", "custom_fields", "notes")
+        )
 
     def get_serializer(self, *args, **kwargs):
         fields_param = self.request.query_params.get("fields", None)
@@ -627,9 +644,18 @@ class DocumentViewSet(
 
 class SearchResultSerializer(DocumentSerializer, PassUserMixin):
     def to_representation(self, instance):
-        doc = Document.objects.get(id=instance["id"])
+        doc = (
+            Document.objects.select_related(
+                "correspondent",
+                "storage_path",
+                "document_type",
+                "owner",
+            )
+            .prefetch_related("tags", "custom_fields", "notes")
+            .get(id=instance["id"])
+        )
         notes = ",".join(
-            [str(c.note) for c in Note.objects.filter(document=instance["id"])],
+            [str(c.note) for c in doc.notes.all()],
         )
         r = super().to_representation(doc)
         r["__search_hit__"] = {
@@ -752,7 +778,11 @@ class SavedViewViewSet(ModelViewSet, PassUserMixin):
 
     def get_queryset(self):
         user = self.request.user
-        return SavedView.objects.filter(owner=user)
+        return (
+            SavedView.objects.filter(owner=user)
+            .select_related("owner")
+            .prefetch_related("filter_rules")
+        )
 
     def perform_create(self, serializer):
         serializer.save(owner=self.request.user)
@@ -1080,8 +1110,12 @@ class BulkDownloadView(GenericAPIView):
 class StoragePathViewSet(ModelViewSet, PassUserMixin):
     model = StoragePath
 
-    queryset = StoragePath.objects.annotate(document_count=Count("documents")).order_by(
+    queryset = (
-        Lower("name"),
+        StoragePath.objects.annotate(document_count=Count("documents"))
+        .select_related("owner")
+        .order_by(
+            Lower("name"),
+        )
     )
 
     serializer_class = StoragePathSerializer
@@ -1347,7 +1381,18 @@ class ConsumptionTemplateViewSet(ModelViewSet):
 
     model = ConsumptionTemplate
 
-    queryset = ConsumptionTemplate.objects.all().order_by("order")
+    queryset = (
+        ConsumptionTemplate.objects.prefetch_related(
+            "assign_tags",
+            "assign_view_users",
+            "assign_view_groups",
+            "assign_change_users",
+            "assign_change_groups",
+            "assign_custom_fields",
+        )
+        .all()
+        .order_by("order")
+    )
 
 
 class CustomFieldViewSet(ModelViewSet):

src/locale/fr_FR/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2023-12-05 08:26-0800\n"
-"PO-Revision-Date: 2023-12-12 00:24\n"
+"PO-Revision-Date: 2023-12-14 00:23\n"
 "Last-Translator: \n"
 "Language-Team: French\n"
 "Language: fr_FR\n"

src/locale/hr_HR/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2023-12-05 08:26-0800\n"
-"PO-Revision-Date: 2023-12-05 16:27\n"
+"PO-Revision-Date: 2023-12-13 12:09\n"
 "Last-Translator: \n"
 "Language-Team: Croatian\n"
 "Language: hr_HR\n"

src/locale/ro_RO/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2023-12-05 08:26-0800\n"
-"PO-Revision-Date: 2023-12-05 16:27\n"
+"PO-Revision-Date: 2023-12-16 00:23\n"
 "Last-Translator: \n"
 "Language-Team: Romanian\n"
 "Language: ro_RO\n"
@@ -23,11 +23,11 @@ msgstr "Documente"
 
 #: documents/models.py:36 documents/models.py:734
 msgid "owner"
-msgstr ""
+msgstr "proprietar"
 
 #: documents/models.py:53
 msgid "None"
-msgstr ""
+msgstr "Nimic"
 
 #: documents/models.py:54
 msgid "Any word"
@@ -108,15 +108,15 @@ msgstr "tipuri de document"
 
 #: documents/models.py:124
 msgid "path"
-msgstr ""
+msgstr "cale"
 
 #: documents/models.py:129 documents/models.py:156
 msgid "storage path"
-msgstr ""
+msgstr "cale de stocare"
 
 #: documents/models.py:130
 msgid "storage paths"
-msgstr ""
+msgstr "căi de stocare"
 
 #: documents/models.py:137
 msgid "Unencrypted"
@@ -193,11 +193,11 @@ msgstr "Numele curent al arhivei stocate"
 
 #: documents/models.py:250
 msgid "original filename"
-msgstr ""
+msgstr "numele original al fișierului"
 
 #: documents/models.py:256
 msgid "The original name of the file when it was uploaded"
-msgstr ""
+msgstr "Numele original al fișierului când a fost încărcat"
 
 #: documents/models.py:263
 msgid "archive serial number"
@@ -381,47 +381,47 @@ msgstr ""
 
 #: documents/models.py:447
 msgid "storage path is"
-msgstr ""
+msgstr "calea de stocare este"
 
 #: documents/models.py:448
 msgid "has correspondent in"
-msgstr ""
+msgstr "are corespondent în"
 
 #: documents/models.py:449
 msgid "does not have correspondent in"
-msgstr ""
+msgstr "nu are corespondent în"
 
 #: documents/models.py:450
 msgid "has document type in"
-msgstr ""
+msgstr "are tip de document în"
 
 #: documents/models.py:451
 msgid "does not have document type in"
-msgstr ""
+msgstr "nu are tip document în"
 
 #: documents/models.py:452
 msgid "has storage path in"
-msgstr ""
+msgstr "are cale de stocare în"
 
 #: documents/models.py:453
 msgid "does not have storage path in"
-msgstr ""
+msgstr "nu are cale de stocare în"
 
 #: documents/models.py:454
 msgid "owner is"
-msgstr ""
+msgstr "proprietarul este"
 
 #: documents/models.py:455
 msgid "has owner in"
-msgstr ""
+msgstr "are proprietar în"
 
 #: documents/models.py:456
 msgid "does not have owner"
-msgstr ""
+msgstr "nu are proprietar"
 
 #: documents/models.py:457
 msgid "does not have owner in"
-msgstr ""
+msgstr "nu are proprietar în"
 
 #: documents/models.py:467
 msgid "rule type"
@@ -441,47 +441,47 @@ msgstr "reguli de filtrare"
 
 #: documents/models.py:584
 msgid "Task ID"
-msgstr ""
+msgstr "ID Sarcină"
 
 #: documents/models.py:585
 msgid "Celery ID for the Task that was run"
-msgstr ""
+msgstr "ID-ul sarcinii Celery care a fost rulată"
 
 #: documents/models.py:590
 msgid "Acknowledged"
-msgstr ""
+msgstr "Confirmat"
 
 #: documents/models.py:591
 msgid "If the task is acknowledged via the frontend or API"
-msgstr ""
+msgstr "Dacă sarcina este confirmată prin frontend sau API"
 
 #: documents/models.py:597
 msgid "Task Filename"
-msgstr ""
+msgstr "Numele fișierului sarcină"
 
 #: documents/models.py:598
 msgid "Name of the file which the Task was run for"
-msgstr ""
+msgstr "Numele fișierului pentru care sarcina a fost executată"
 
 #: documents/models.py:604
 msgid "Task Name"
-msgstr ""
+msgstr "Nume sarcină"
 
 #: documents/models.py:605
 msgid "Name of the Task which was run"
-msgstr ""
+msgstr "Numele sarcinii care a fost executată"
 
 #: documents/models.py:612
 msgid "Task State"
-msgstr ""
+msgstr "Stare sarcină"
 
 #: documents/models.py:613
 msgid "Current state of the task being run"
-msgstr ""
+msgstr "Stadiul actual al sarcinii în curs de desfășurare"
 
 #: documents/models.py:618
 msgid "Created DateTime"
-msgstr ""
+msgstr "Data creării"
 
 #: documents/models.py:619
 msgid "Datetime field when the task result was created in UTC"
@@ -489,7 +489,7 @@ msgstr ""
 
 #: documents/models.py:624
 msgid "Started DateTime"
-msgstr ""
+msgstr "Data începerii"
 
 #: documents/models.py:625
 msgid "Datetime field when the task was started in UTC"
@@ -497,7 +497,7 @@ msgstr ""
 
 #: documents/models.py:630
 msgid "Completed DateTime"
-msgstr ""
+msgstr "Data finalizării"
 
 #: documents/models.py:631
 msgid "Datetime field when the task was completed in UTC"
@@ -505,15 +505,15 @@ msgstr ""
 
 #: documents/models.py:636
 msgid "Result Data"
-msgstr ""
+msgstr "Datele rezultatului"
 
 #: documents/models.py:638
 msgid "The data returned by the task"
-msgstr ""
+msgstr "Datele returnate de sarcină"
 
 #: documents/models.py:650
 msgid "Note for the document"
-msgstr ""
+msgstr "Notă pentru document"
 
 #: documents/models.py:674
 msgid "user"
@@ -521,23 +521,23 @@ msgstr "utilizator"
 
 #: documents/models.py:679
 msgid "note"
-msgstr ""
+msgstr "notă"
 
 #: documents/models.py:680
 msgid "notes"
-msgstr ""
+msgstr "note"
 
 #: documents/models.py:688
 msgid "Archive"
-msgstr ""
+msgstr "Arhivă"
 
 #: documents/models.py:689
 msgid "Original"
-msgstr ""
+msgstr "Original"
 
 #: documents/models.py:700
 msgid "expiration"
-msgstr ""
+msgstr "expirare"
 
 #: documents/models.py:707
 msgid "slug"
@@ -545,35 +545,35 @@ msgstr ""
 
 #: documents/models.py:739
 msgid "share link"
-msgstr ""
+msgstr "link de partajare"
 
 #: documents/models.py:740
 msgid "share links"
-msgstr ""
+msgstr "link-uri de partajare"
 
 #: documents/models.py:752
 msgid "String"
-msgstr ""
+msgstr "Şir de caractere"
 
 #: documents/models.py:753
 msgid "URL"
-msgstr ""
+msgstr "Adresă URL"
 
 #: documents/models.py:754
 msgid "Date"
-msgstr ""
+msgstr "Dată"
 
 #: documents/models.py:755
 msgid "Boolean"
-msgstr ""
+msgstr "Boolean"
 
 #: documents/models.py:756
 msgid "Integer"
-msgstr ""
+msgstr "Număr întreg"
 
 #: documents/models.py:757
 msgid "Float"
-msgstr ""
+msgstr "Număr zecimal"
 
 #: documents/models.py:758
 msgid "Monetary"
@@ -581,11 +581,11 @@ msgstr ""
 
 #: documents/models.py:759
 msgid "Document Link"
-msgstr ""
+msgstr "Link document"
 
 #: documents/models.py:771
 msgid "data type"
-msgstr ""
+msgstr "tip date"
 
 #: documents/models.py:779
 msgid "custom field"

src/locale/zh_TW/LC_MESSAGES/django.po

@@ -3,7 +3,7 @@ msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
 "POT-Creation-Date: 2023-12-05 08:26-0800\n"
-"PO-Revision-Date: 2023-12-05 16:27\n"
+"PO-Revision-Date: 2023-12-14 00:23\n"
 "Last-Translator: \n"
 "Language-Team: Chinese Traditional\n"
 "Language: zh_TW\n"
@@ -47,7 +47,7 @@ msgstr ""
 
 #: documents/models.py:58
 msgid "Fuzzy word"
-msgstr ""
+msgstr "模糊詞"
 
 #: documents/models.py:59
 msgid "Automatic"
@@ -68,15 +68,15 @@ msgstr "比對演算法"
 
 #: documents/models.py:72
 msgid "is insensitive"
-msgstr ""
+msgstr "不區分大小寫"
 
 #: documents/models.py:95 documents/models.py:147
 msgid "correspondent"
-msgstr ""
+msgstr "聯繫者"
 
 #: documents/models.py:96
 msgid "correspondents"
-msgstr ""
+msgstr "聯繫者"
 
 #: documents/models.py:100
 msgid "color"
@@ -84,47 +84,47 @@ msgstr "顏色"
 
 #: documents/models.py:103
 msgid "is inbox tag"
-msgstr ""
+msgstr "收件匣標籤"
 
 #: documents/models.py:106
 msgid "Marks this tag as an inbox tag: All newly consumed documents will be tagged with inbox tags."
-msgstr ""
+msgstr "標記此標籤為收件匣標籤：所有新處理的文件將會以此收件匣標籤作標記。"
 
 #: documents/models.py:112
 msgid "tag"
-msgstr ""
+msgstr "標籤"
 
 #: documents/models.py:113 documents/models.py:185
 msgid "tags"
-msgstr ""
+msgstr "標籤"
 
 #: documents/models.py:118 documents/models.py:167
 msgid "document type"
-msgstr ""
+msgstr "文件類型"
 
 #: documents/models.py:119
 msgid "document types"
-msgstr ""
+msgstr "文件類型"
 
 #: documents/models.py:124
 msgid "path"
-msgstr ""
+msgstr "位址"
 
 #: documents/models.py:129 documents/models.py:156
 msgid "storage path"
-msgstr ""
+msgstr "儲存位址"
 
 #: documents/models.py:130
 msgid "storage paths"
-msgstr ""
+msgstr "儲存位址"
 
 #: documents/models.py:137
 msgid "Unencrypted"
-msgstr ""
+msgstr "未加密"
 
 #: documents/models.py:138
 msgid "Encrypted with GNU Privacy Guard"
-msgstr ""
+msgstr "已使用 GNU Privacy Guard 進行加密"
 
 #: documents/models.py:159
 msgid "title"
@@ -189,27 +189,27 @@ msgstr "存檔檔案名稱"
 
 #: documents/models.py:246
 msgid "Current archive filename in storage"
-msgstr ""
+msgstr "現時儲存空間封存的檔案名稱"
 
 #: documents/models.py:250
 msgid "original filename"
-msgstr ""
+msgstr "原先檔案名稱"
 
 #: documents/models.py:256
 msgid "The original name of the file when it was uploaded"
-msgstr ""
+msgstr "檔案上傳時的檔案名稱"
 
 #: documents/models.py:263
 msgid "archive serial number"
-msgstr ""
+msgstr "封存編號"
 
 #: documents/models.py:273
 msgid "The position of this document in your physical document archive."
-msgstr ""
+msgstr "此檔案在你實體儲存空間的位置。"
 
 #: documents/models.py:279 documents/models.py:665 documents/models.py:719
 msgid "document"
-msgstr ""
+msgstr "文件"
 
 #: documents/models.py:280
 msgid "documents"
@@ -217,47 +217,47 @@ msgstr "文件"
 
 #: documents/models.py:368
 msgid "debug"
-msgstr ""
+msgstr "偵錯"
 
 #: documents/models.py:369
 msgid "information"
-msgstr ""
+msgstr "資訊"
 
 #: documents/models.py:370
 msgid "warning"
-msgstr ""
+msgstr "警告"
 
 #: documents/models.py:371 paperless_mail/models.py:305
 msgid "error"
-msgstr ""
+msgstr "錯誤"
 
 #: documents/models.py:372
 msgid "critical"
-msgstr ""
+msgstr "嚴重"
 
 #: documents/models.py:375
 msgid "group"
-msgstr ""
+msgstr "群組"
 
 #: documents/models.py:377
 msgid "message"
-msgstr ""
+msgstr "訊息"
 
 #: documents/models.py:380
 msgid "level"
-msgstr ""
+msgstr "程度"
 
 #: documents/models.py:389
 msgid "log"
-msgstr ""
+msgstr "記錄"
 
 #: documents/models.py:390
 msgid "logs"
-msgstr ""
+msgstr "記錄"
 
 #: documents/models.py:399 documents/models.py:464
 msgid "saved view"
-msgstr ""
+msgstr "已儲存的檢視表"
 
 #: documents/models.py:400
 msgid "saved views"
@@ -265,207 +265,207 @@ msgstr "保存視圖"
 
 #: documents/models.py:405
 msgid "show on dashboard"
-msgstr ""
+msgstr "顯示在概覽"
 
 #: documents/models.py:408
 msgid "show in sidebar"
-msgstr ""
+msgstr "顯示在側邊欄"
 
 #: documents/models.py:412
 msgid "sort field"
-msgstr ""
+msgstr "排序欄位"
 
 #: documents/models.py:417
 msgid "sort reverse"
-msgstr ""
+msgstr "倒轉排序"
 
 #: documents/models.py:422
 msgid "title contains"
-msgstr ""
+msgstr "標題包含"
 
 #: documents/models.py:423
 msgid "content contains"
-msgstr ""
+msgstr "內容包含"
 
 #: documents/models.py:424
 msgid "ASN is"
-msgstr ""
+msgstr "ASN 為"
 
 #: documents/models.py:425
 msgid "correspondent is"
-msgstr ""
+msgstr "聯繫者為"
 
 #: documents/models.py:426
 msgid "document type is"
-msgstr ""
+msgstr "文件類型為"
 
 #: documents/models.py:427
 msgid "is in inbox"
-msgstr ""
+msgstr "在收件匣內"
 
 #: documents/models.py:428
 msgid "has tag"
-msgstr ""
+msgstr "包含標籤"
 
 #: documents/models.py:429
 msgid "has any tag"
-msgstr ""
+msgstr "包含任何標籤"
 
 #: documents/models.py:430
 msgid "created before"
-msgstr ""
+msgstr "建立時間之前"
 
 #: documents/models.py:431
 msgid "created after"
-msgstr ""
+msgstr "建立時間之後"
 
 #: documents/models.py:432
 msgid "created year is"
-msgstr ""
+msgstr "建立年份為"
 
 #: documents/models.py:433
 msgid "created month is"
-msgstr ""
+msgstr "建立月份為"
 
 #: documents/models.py:434
 msgid "created day is"
-msgstr ""
+msgstr "建立日期為"
 
 #: documents/models.py:435
 msgid "added before"
-msgstr ""
+msgstr "加入時間之前"
 
 #: documents/models.py:436
 msgid "added after"
-msgstr ""
+msgstr "加入時間之後"
 
 #: documents/models.py:437
 msgid "modified before"
-msgstr ""
+msgstr "修改之前"
 
 #: documents/models.py:438
 msgid "modified after"
-msgstr ""
+msgstr "修改之後"
 
 #: documents/models.py:439
 msgid "does not have tag"
-msgstr ""
+msgstr "沒有包含標籤"
 
 #: documents/models.py:440
 msgid "does not have ASN"
-msgstr ""
+msgstr "沒有包含 ASN"
 
 #: documents/models.py:441
 msgid "title or content contains"
-msgstr ""
+msgstr "標題或內容包含"
 
 #: documents/models.py:442
 msgid "fulltext query"
-msgstr ""
+msgstr "全文搜索"
 
 #: documents/models.py:443
 msgid "more like this"
-msgstr ""
+msgstr "其他類似內容"
 
 #: documents/models.py:444
 msgid "has tags in"
-msgstr ""
+msgstr "含有這個標籤"
 
 #: documents/models.py:445
 msgid "ASN greater than"
-msgstr ""
+msgstr "ASN 大於"
 
 #: documents/models.py:446
 msgid "ASN less than"
-msgstr ""
+msgstr "ASN 小於"
 
 #: documents/models.py:447
 msgid "storage path is"
-msgstr ""
+msgstr "儲存位址為"
 
 #: documents/models.py:448
 msgid "has correspondent in"
-msgstr ""
+msgstr "包含聯繫者"
 
 #: documents/models.py:449
 msgid "does not have correspondent in"
-msgstr ""
+msgstr "沒有包含聯繫者"
 
 #: documents/models.py:450
 msgid "has document type in"
-msgstr ""
+msgstr "文件類型包含"
 
 #: documents/models.py:451
 msgid "does not have document type in"
-msgstr ""
+msgstr "沒有包含的文件類型"
 
 #: documents/models.py:452
 msgid "has storage path in"
-msgstr ""
+msgstr "儲存位址包含"
 
 #: documents/models.py:453
 msgid "does not have storage path in"
-msgstr ""
+msgstr "沒有包含的儲存位址"
 
 #: documents/models.py:454
 msgid "owner is"
-msgstr ""
+msgstr "擁有者為"
 
 #: documents/models.py:455
 msgid "has owner in"
-msgstr ""
+msgstr "擁有者包含"
 
 #: documents/models.py:456
 msgid "does not have owner"
-msgstr ""
+msgstr "沒有包含的擁有者"
 
 #: documents/models.py:457
 msgid "does not have owner in"
-msgstr ""
+msgstr "沒有包含的擁有者"
 
 #: documents/models.py:467
 msgid "rule type"
-msgstr ""
+msgstr "規則類型"
 
 #: documents/models.py:469
 msgid "value"
-msgstr ""
+msgstr "數值"
 
 #: documents/models.py:472
 msgid "filter rule"
-msgstr ""
+msgstr "過濾規則"
 
 #: documents/models.py:473
 msgid "filter rules"
-msgstr ""
+msgstr "過濾規則"
 
 #: documents/models.py:584
 msgid "Task ID"
-msgstr ""
+msgstr "任務 ID"
 
 #: documents/models.py:585
 msgid "Celery ID for the Task that was run"
-msgstr ""
+msgstr "已執行任務的 Celery ID"
 
 #: documents/models.py:590
 msgid "Acknowledged"
-msgstr ""
+msgstr "已確認"
 
 #: documents/models.py:591
 msgid "If the task is acknowledged via the frontend or API"
-msgstr ""
+msgstr "如果任務已由前端 / API 確認"
 
 #: documents/models.py:597
 msgid "Task Filename"
-msgstr ""
+msgstr "任務檔案名稱"
 
 #: documents/models.py:598
 msgid "Name of the file which the Task was run for"
-msgstr ""
+msgstr "執行任務的目標檔案名稱"
 
 #: documents/models.py:604
 msgid "Task Name"
-msgstr ""
+msgstr "任務名稱"
 
 #: documents/models.py:605
 msgid "Name of the Task which was run"
@@ -473,7 +473,7 @@ msgstr ""
 
 #: documents/models.py:612
 msgid "Task State"
-msgstr ""
+msgstr "任務狀態"
 
 #: documents/models.py:613
 msgid "Current state of the task being run"
@@ -657,7 +657,7 @@ msgstr ""
 
 #: documents/models.py:967 paperless_mail/models.py:238
 msgid "assign this correspondent"
-msgstr ""
+msgstr "指派這個聯繫者"
 
 #: documents/models.py:975
 msgid "assign this storage path"
@@ -1128,7 +1128,7 @@ msgstr ""
 
 #: paperless_mail/models.py:88
 msgid "Do not assign a correspondent"
-msgstr ""
+msgstr "不要指派聯繫者"
 
 #: paperless_mail/models.py:89
 msgid "Use mail address"
@@ -1140,7 +1140,7 @@ msgstr ""
 
 #: paperless_mail/models.py:91
 msgid "Use correspondent selected below"
-msgstr ""
+msgstr "使用以下已選擇的聯繫者"
 
 #: paperless_mail/models.py:101
 msgid "account"
@@ -1220,7 +1220,7 @@ msgstr ""
 
 #: paperless_mail/models.py:228
 msgid "assign correspondent from"
-msgstr ""
+msgstr "指派聯繫者從"
 
 #: paperless_mail/models.py:242
 msgid "Assign the rule owner to documents"

src/paperless_tesseract/parsers.py

@@ -254,7 +254,7 @@ class RasterisedDocumentParser(DocumentParser):
                     f"Image DPI of {ocrmypdf_args['image_dpi']} is low, OCR may fail",
                 )
 
-        if settings.OCR_USER_ARGS and not safe_fallback:
+        if settings.OCR_USER_ARGS:
             try:
                 user_args = json.loads(settings.OCR_USER_ARGS)
                 ocrmypdf_args = {**ocrmypdf_args, **user_args}