Merge pull request #532 from paperless-ngx/feature-barcode-splitter

Feature barcode splitter

.github/workflows/ci.yml

@@ -132,7 +132,7 @@ jobs:
         name: Install system dependencies
         run: |
           sudo apt-get update -qq
-          sudo apt-get install -qq --no-install-recommends unpaper tesseract-ocr imagemagick ghostscript optipng
+          sudo apt-get install -qq --no-install-recommends unpaper tesseract-ocr imagemagick ghostscript optipng libzbar0 poppler-utils
       -
         name: Install Python dependencies
         run: |

Pipfile

@@ -51,6 +51,8 @@ concurrent-log-handler = "*"
 "backports.zoneinfo" = {version = "*", markers = "python_version < '3.9'"}
 "importlib-resources" = {version = "*", markers = "python_version < '3.9'"}
 zipp = {version = "*", markers = "python_version < '3.9'"}
+pyzbar = "*"
+pdf2image = "*"
 
 [dev-packages]
 coveralls = "*"

Pipfile.lock

@@ -693,6 +693,14 @@
             "index": "pypi",
             "version": "==2.5.0"
         },
+        "pdf2image": {
+            "hashes": [
+                "sha256:84f79f2b8fad943e36323ea4e937fcb05f26ded0caa0a01181df66049e42fb65",
+                "sha256:d58ed94d978a70c73c2bb7fdf8acbaf2a7089c29ff8141be5f45433c0c4293bb"
+            ],
+            "index": "pypi",
+            "version": "==1.16.0"
+        },
         "pdfminer.six": {
             "hashes": [
                 "sha256:af0630f98a292bad4170f54e80f82ca81b916dd0b2c996437ec45c02f11d8762",
@@ -960,6 +968,15 @@
             ],
             "version": "==6.0"
         },
+        "pyzbar": {
+            "hashes": [
+                "sha256:13e3ee5a2f3a545204a285f41814d5c0db571967e8d4af8699a03afc55182a9c",
+                "sha256:4559628b8192feb25766d954b36a3753baaf5c97c03135aec7e4a026036b475d",
+                "sha256:8f4c5264c9c7c6b9f20d01efc52a4eba1ded47d9ba857a94130afe33703eb518"
+            ],
+            "index": "pypi",
+            "version": "==0.1.9"
+        },
         "redis": {
             "hashes": [
                 "sha256:0e7e0cfca8660dea8b7d5cd8c4f6c5e29e11f31158c0b0ae91a397f00e5a05a2",
@@ -1784,6 +1801,13 @@
             ],
             "version": "==1.6.0"
         },
+        "mypy-extensions": {
+            "hashes": [
+                "sha256:090fedd75945a69ae91ce1303b5824f428daf5a028d2f6ab8a299250a846f15d",
+                "sha256:2d82818f5bb3e369420cb3c4060a7970edba416647068eb4c5343488a6c604a8"
+            ],
+            "version": "==0.4.3"
+        },
         "packaging": {
             "hashes": [
                 "sha256:dd47c42927d89ab911e606518907cc2d3a1f38bbd026385970643f9c5b8ecfeb",

docs/configuration.rst

@@ -613,6 +613,27 @@ PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS=<bool>
 
     Defaults to false.
 
+PAPERLESS_CONSUMER_ENABLE_BARCODES=<bool>
+    Enables the scanning and page separation based on detected barcodes.
+    This allows for scanning and adding multiple documents per uploaded
+    file, which are separated by one or multiple barcode pages.
+
+    For ease of use, it is suggested to use a standardized separation page,
+    e.g. `here <https://www.alliancegroup.co.uk/patch-codes.htm>`_.
+
+    If no barcodes are detected in the uploaded file, no page separation
+    will happen.
+
+    Defaults to false.
+
+
+PAPERLESS_CONSUMER_BARCODE_STRING=PATCHT
+  Defines the string to be detected as a separator barcode.
+  If paperless is used with the PATCH-T separator pages, users
+  shouldn't change this.
+
+  Defaults to "PATCHT"
+
 
 PAPERLESS_CONVERT_MEMORY_LIMIT=<num>
     On smaller systems, or even in the case of Very Large Documents, the consumer

paperless.conf.example

@@ -62,6 +62,8 @@
 #PAPERLESS_CONSUMER_RECURSIVE=false
 #PAPERLESS_CONSUMER_IGNORE_PATTERNS=[".DS_STORE/*", "._*", ".stfolder/*", ".stversions/*", ".localized/*", "desktop.ini"]
 #PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS=false
+#PAPERLESS_CONSUMER_ENABLE_BARCODES=false
+#PAPERLESS_CONSUMER_ENABLE_BARCODES=PATCHT
 #PAPERLESS_OPTIMIZE_THUMBNAILS=true
 #PAPERLESS_PRE_CONSUME_SCRIPT=/path/to/an/arbitrary/script.sh
 #PAPERLESS_POST_CONSUME_SCRIPT=/path/to/an/arbitrary/script.sh

requirements.txt

@@ -61,6 +61,7 @@ ocrmypdf==13.4.2
 packaging==21.3; python_version >= '3.6'
 pathvalidate==2.5.0
 pdfminer.six==20220319
+pdf2image==1.16.0
 pikepdf==5.1.1
 pillow==9.1.0
 pluggy==1.0.0; python_version >= '3.6'
@@ -79,6 +80,7 @@ python-magic==0.4.25
 pytz-deprecation-shim==0.1.0.post0; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3, 3.4, 3.5'
 pytz==2022.1
 pyyaml==6.0
+pyzbar==0.1.9
 redis==3.5.3
 regex==2022.3.2; python_version >= '3.6'
 reportlab==3.6.9; python_version >= '3.7' and python_version < '4'

src/documents/tasks.py

@@ -1,6 +1,12 @@
 import logging
+import os
+import shutil
+import tempfile
+from typing import List  # for type hinting. Can be removed, if only Python >3.8 is used
 
 import tqdm
+from asgiref.sync import async_to_sync
+from channels.layers import get_channel_layer
 from django.conf import settings
 from django.db.models.signals import post_save
 from documents import index
@@ -14,8 +20,12 @@ from documents.models import Document
 from documents.models import DocumentType
 from documents.models import Tag
 from documents.sanity_checker import SanityCheckFailedException
+from pdf2image import convert_from_path
+from pikepdf import Pdf
+from pyzbar import pyzbar
 from whoosh.writing import AsyncWriter
 
+
 logger = logging.getLogger("paperless.tasks")
 
 
@@ -62,6 +72,115 @@ def train_classifier():
         logger.warning("Classifier error: " + str(e))
 
 
+def barcode_reader(image) -> List[str]:
+    """
+    Read any barcodes contained in image
+    Returns a list containing all found barcodes
+    """
+    barcodes = []
+    # Decode the barcode image
+    detected_barcodes = pyzbar.decode(image)
+
+    if detected_barcodes:
+        # Traverse through all the detected barcodes in image
+        for barcode in detected_barcodes:
+            if barcode.data:
+                decoded_barcode = barcode.data.decode("utf-8")
+                barcodes.append(decoded_barcode)
+                logger.debug(
+                    f"Barcode of type {str(barcode.type)} found: {decoded_barcode}",
+                )
+    return barcodes
+
+
+def scan_file_for_separating_barcodes(filepath: str) -> List[int]:
+    """
+    Scan the provided file for page separating barcodes
+    Returns a list of pagenumbers, which separate the file
+    """
+    separator_page_numbers = []
+    separator_barcode = str(settings.CONSUMER_BARCODE_STRING)
+    # use a temporary directory in case the file os too big to handle in memory
+    with tempfile.TemporaryDirectory() as path:
+        pages_from_path = convert_from_path(filepath, output_folder=path)
+        for current_page_number, page in enumerate(pages_from_path):
+            current_barcodes = barcode_reader(page)
+            if separator_barcode in current_barcodes:
+                separator_page_numbers.append(current_page_number)
+    return separator_page_numbers
+
+
+def separate_pages(filepath: str, pages_to_split_on: List[int]) -> List[str]:
+    """
+    Separate the provided file on the pages_to_split_on.
+    The pages which are defined by page_numbers will be removed.
+    Returns a list of (temporary) filepaths to consume.
+    These will need to be deleted later.
+    """
+    os.makedirs(settings.SCRATCH_DIR, exist_ok=True)
+    tempdir = tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR)
+    fname = os.path.splitext(os.path.basename(filepath))[0]
+    pdf = Pdf.open(filepath)
+    document_paths = []
+    logger.debug(f"Temp dir is {str(tempdir)}")
+    if not pages_to_split_on:
+        logger.warning("No pages to split on!")
+    else:
+        # go from the first page to the first separator page
+        dst = Pdf.new()
+        for n, page in enumerate(pdf.pages):
+            if n < pages_to_split_on[0]:
+                dst.pages.append(page)
+        output_filename = "{}_document_0.pdf".format(fname)
+        savepath = os.path.join(tempdir, output_filename)
+        with open(savepath, "wb") as out:
+            dst.save(out)
+        document_paths = [savepath]
+
+        # iterate through the rest of the document
+        for count, page_number in enumerate(pages_to_split_on):
+            logger.debug(f"Count: {str(count)} page_number: {str(page_number)}")
+            dst = Pdf.new()
+            try:
+                next_page = pages_to_split_on[count + 1]
+            except IndexError:
+                next_page = len(pdf.pages)
+            # skip the first page_number. This contains the barcode page
+            for page in range(page_number + 1, next_page):
+                logger.debug(
+                    f"page_number: {str(page_number)} next_page: {str(next_page)}",
+                )
+                dst.pages.append(pdf.pages[page])
+            output_filename = "{}_document_{}.pdf".format(fname, str(count + 1))
+            logger.debug(f"pdf no:{str(count)} has {str(len(dst.pages))} pages")
+            savepath = os.path.join(tempdir, output_filename)
+            with open(savepath, "wb") as out:
+                dst.save(out)
+            document_paths.append(savepath)
+    logger.debug(f"Temp files are {str(document_paths)}")
+    return document_paths
+
+
+def save_to_dir(
+    filepath: str,
+    newname: str = None,
+    target_dir: str = settings.CONSUMPTION_DIR,
+):
+    """
+    Copies filepath to target_dir.
+    Optionally rename the file.
+    """
+    if os.path.isfile(filepath) and os.path.isdir(target_dir):
+        dst = shutil.copy(filepath, target_dir)
+        logging.debug(f"saved {str(filepath)} to {str(dst)}")
+        if newname:
+            dst_new = os.path.join(target_dir, newname)
+            logger.debug(f"moving {str(dst)} to {str(dst_new)}")
+            os.rename(dst, dst_new)
+    else:
+        logger.warning(f"{str(filepath)} or {str(target_dir)} don't exist.")
+
+
 def consume_file(
     path,
     override_filename=None,
@@ -72,6 +191,48 @@ def consume_file(
     task_id=None,
 ):
 
+    # check for separators in current document
+    if settings.CONSUMER_ENABLE_BARCODES:
+        separators = []
+        document_list = []
+        separators = scan_file_for_separating_barcodes(path)
+        if separators:
+            logger.debug(f"Pages with separators found in: {str(path)}")
+            document_list = separate_pages(path, separators)
+        if document_list:
+            for n, document in enumerate(document_list):
+                # save to consumption dir
+                # rename it to the original filename  with number prefix
+                if override_filename:
+                    newname = f"{str(n)}_" + override_filename
+                else:
+                    newname = None
+                save_to_dir(document, newname=newname)
+            # if we got here, the document was successfully split
+            # and can safely be deleted
+            logger.debug("Deleting file {}".format(path))
+            os.unlink(path)
+            # notify the sender, otherwise the progress bar
+            # in the UI stays stuck
+            payload = {
+                "filename": override_filename,
+                "task_id": task_id,
+                "current_progress": 100,
+                "max_progress": 100,
+                "status": "SUCCESS",
+                "message": "finished",
+            }
+            try:
+                async_to_sync(get_channel_layer().group_send)(
+                    "status_updates",
+                    {"type": "status_update", "data": payload},
+                )
+            except OSError as e:
+                logger.warning("OSError. It could be, the broker cannot be reached.")
+                logger.warning(str(e))
+            return "File successfully split"
+
+    # continue with consumption if no barcode was found
     document = Consumer().try_consume_file(
         path,
         override_filename=override_filename,

src/documents/tests/test_tasks.py

@@ -1,7 +1,10 @@
 import os
+import shutil
+import tempfile
 from unittest import mock
 
 from django.conf import settings
+from django.test import override_settings
 from django.test import TestCase
 from django.utils import timezone
 from documents import tasks
@@ -12,6 +15,7 @@ from documents.models import Tag
 from documents.sanity_checker import SanityCheckFailedException
 from documents.sanity_checker import SanityCheckMessages
 from documents.tests.utils import DirectoriesMixin
+from PIL import Image
 
 
 class TestTasks(DirectoriesMixin, TestCase):
@@ -89,6 +93,318 @@ class TestTasks(DirectoriesMixin, TestCase):
         mtime3 = os.stat(settings.MODEL_FILE).st_mtime
         self.assertNotEqual(mtime2, mtime3)
 
+    def test_barcode_reader(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "barcode-39-PATCHT.png",
+        )
+        img = Image.open(test_file)
+        separator_barcode = str(settings.CONSUMER_BARCODE_STRING)
+        self.assertEqual(tasks.barcode_reader(img), [separator_barcode])
+
+    def test_barcode_reader2(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "patch-code-t.pbm",
+        )
+        img = Image.open(test_file)
+        separator_barcode = str(settings.CONSUMER_BARCODE_STRING)
+        self.assertEqual(tasks.barcode_reader(img), [separator_barcode])
+
+    def test_barcode_reader_distorsion(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "barcode-39-PATCHT-distorsion.png",
+        )
+        img = Image.open(test_file)
+        separator_barcode = str(settings.CONSUMER_BARCODE_STRING)
+        self.assertEqual(tasks.barcode_reader(img), [separator_barcode])
+
+    def test_barcode_reader_distorsion2(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "barcode-39-PATCHT-distorsion2.png",
+        )
+        img = Image.open(test_file)
+        separator_barcode = str(settings.CONSUMER_BARCODE_STRING)
+        self.assertEqual(tasks.barcode_reader(img), [separator_barcode])
+
+    def test_barcode_reader_unreadable(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "barcode-39-PATCHT-unreadable.png",
+        )
+        img = Image.open(test_file)
+        self.assertEqual(tasks.barcode_reader(img), [])
+
+    def test_barcode_reader_qr(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "qr-code-PATCHT.png",
+        )
+        img = Image.open(test_file)
+        separator_barcode = str(settings.CONSUMER_BARCODE_STRING)
+        self.assertEqual(tasks.barcode_reader(img), [separator_barcode])
+
+    def test_barcode_reader_128(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "barcode-128-PATCHT.png",
+        )
+        img = Image.open(test_file)
+        separator_barcode = str(settings.CONSUMER_BARCODE_STRING)
+        self.assertEqual(tasks.barcode_reader(img), [separator_barcode])
+
+    def test_barcode_reader_no_barcode(self):
+        test_file = os.path.join(os.path.dirname(__file__), "samples", "simple.png")
+        img = Image.open(test_file)
+        self.assertEqual(tasks.barcode_reader(img), [])
+
+    def test_barcode_reader_custom_separator(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "barcode-39-custom.png",
+        )
+        img = Image.open(test_file)
+        self.assertEqual(tasks.barcode_reader(img), ["CUSTOM BARCODE"])
+
+    def test_barcode_reader_custom_qr_separator(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "barcode-qr-custom.png",
+        )
+        img = Image.open(test_file)
+        self.assertEqual(tasks.barcode_reader(img), ["CUSTOM BARCODE"])
+
+    def test_barcode_reader_custom_128_separator(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "barcode-128-custom.png",
+        )
+        img = Image.open(test_file)
+        self.assertEqual(tasks.barcode_reader(img), ["CUSTOM BARCODE"])
+
+    def test_scan_file_for_separating_barcodes(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "patch-code-t.pdf",
+        )
+        pages = tasks.scan_file_for_separating_barcodes(test_file)
+        self.assertEqual(pages, [0])
+
+    def test_scan_file_for_separating_barcodes2(self):
+        test_file = os.path.join(os.path.dirname(__file__), "samples", "simple.pdf")
+        pages = tasks.scan_file_for_separating_barcodes(test_file)
+        self.assertEqual(pages, [])
+
+    def test_scan_file_for_separating_barcodes3(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "patch-code-t-middle.pdf",
+        )
+        pages = tasks.scan_file_for_separating_barcodes(test_file)
+        self.assertEqual(pages, [1])
+
+    def test_scan_file_for_separating_barcodes4(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "several-patcht-codes.pdf",
+        )
+        pages = tasks.scan_file_for_separating_barcodes(test_file)
+        self.assertEqual(pages, [2, 5])
+
+    def test_scan_file_for_separating_barcodes_upsidedown(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "patch-code-t-middle_reverse.pdf",
+        )
+        pages = tasks.scan_file_for_separating_barcodes(test_file)
+        self.assertEqual(pages, [1])
+
+    def test_scan_file_for_separating_qr_barcodes(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "patch-code-t-qr.pdf",
+        )
+        pages = tasks.scan_file_for_separating_barcodes(test_file)
+        self.assertEqual(pages, [0])
+
+    @override_settings(CONSUMER_BARCODE_STRING="CUSTOM BARCODE")
+    def test_scan_file_for_separating_custom_barcodes(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "barcode-39-custom.pdf",
+        )
+        pages = tasks.scan_file_for_separating_barcodes(test_file)
+        self.assertEqual(pages, [0])
+
+    @override_settings(CONSUMER_BARCODE_STRING="CUSTOM BARCODE")
+    def test_scan_file_for_separating_custom_qr_barcodes(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "barcode-qr-custom.pdf",
+        )
+        pages = tasks.scan_file_for_separating_barcodes(test_file)
+        self.assertEqual(pages, [0])
+
+    @override_settings(CONSUMER_BARCODE_STRING="CUSTOM BARCODE")
+    def test_scan_file_for_separating_custom_128_barcodes(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "barcode-128-custom.pdf",
+        )
+        pages = tasks.scan_file_for_separating_barcodes(test_file)
+        self.assertEqual(pages, [0])
+
+    def test_scan_file_for_separating_wrong_qr_barcodes(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "barcode-39-custom.pdf",
+        )
+        pages = tasks.scan_file_for_separating_barcodes(test_file)
+        self.assertEqual(pages, [])
+
+    def test_separate_pages(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "patch-code-t-middle.pdf",
+        )
+        pages = tasks.separate_pages(test_file, [1])
+        self.assertEqual(len(pages), 2)
+
+    def test_separate_pages_no_list(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "patch-code-t-middle.pdf",
+        )
+        with self.assertLogs("paperless.tasks", level="WARNING") as cm:
+            pages = tasks.separate_pages(test_file, [])
+            self.assertEqual(pages, [])
+            self.assertEqual(
+                cm.output,
+                [
+                    f"WARNING:paperless.tasks:No pages to split on!",
+                ],
+            )
+
+    def test_save_to_dir(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "patch-code-t.pdf",
+        )
+        tempdir = tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR)
+        tasks.save_to_dir(test_file, target_dir=tempdir)
+        target_file = os.path.join(tempdir, "patch-code-t.pdf")
+        self.assertTrue(os.path.isfile(target_file))
+
+    def test_save_to_dir2(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "patch-code-t.pdf",
+        )
+        nonexistingdir = "/nowhere"
+        if os.path.isdir(nonexistingdir):
+            self.fail("non-existing dir exists")
+        else:
+            with self.assertLogs("paperless.tasks", level="WARNING") as cm:
+                tasks.save_to_dir(test_file, target_dir=nonexistingdir)
+            self.assertEqual(
+                cm.output,
+                [
+                    f"WARNING:paperless.tasks:{str(test_file)} or {str(nonexistingdir)} don't exist.",
+                ],
+            )
+
+    def test_save_to_dir3(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "patch-code-t.pdf",
+        )
+        tempdir = tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR)
+        tasks.save_to_dir(test_file, newname="newname.pdf", target_dir=tempdir)
+        target_file = os.path.join(tempdir, "newname.pdf")
+        self.assertTrue(os.path.isfile(target_file))
+
+    def test_barcode_splitter(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "patch-code-t-middle.pdf",
+        )
+        tempdir = tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR)
+        separators = tasks.scan_file_for_separating_barcodes(test_file)
+        self.assertTrue(separators)
+        document_list = tasks.separate_pages(test_file, separators)
+        self.assertTrue(document_list)
+        for document in document_list:
+            tasks.save_to_dir(document, target_dir=tempdir)
+        target_file1 = os.path.join(tempdir, "patch-code-t-middle_document_0.pdf")
+        target_file2 = os.path.join(tempdir, "patch-code-t-middle_document_1.pdf")
+        self.assertTrue(os.path.isfile(target_file1))
+        self.assertTrue(os.path.isfile(target_file2))
+
+    @override_settings(CONSUMER_ENABLE_BARCODES=True)
+    def test_consume_barcode_file(self):
+        test_file = os.path.join(
+            os.path.dirname(__file__),
+            "samples",
+            "barcodes",
+            "patch-code-t-middle.pdf",
+        )
+        dst = os.path.join(settings.SCRATCH_DIR, "patch-code-t-middle.pd")
+        shutil.copy(test_file, dst)
+
+        self.assertEqual(tasks.consume_file(dst), "File successfully split")
+
     @mock.patch("documents.tasks.sanity_checker.check_sanity")
     def test_sanity_check_success(self, m):
         m.return_value = SanityCheckMessages()

src/paperless/settings.py

@@ -498,6 +498,12 @@ CONSUMER_IGNORE_PATTERNS = list(
 
 CONSUMER_SUBDIRS_AS_TAGS = __get_boolean("PAPERLESS_CONSUMER_SUBDIRS_AS_TAGS")
 
+CONSUMER_ENABLE_BARCODES = __get_boolean(
+    "PAPERLESS_CONSUMER_ENABLE_BARCODES",
+)
+
+CONSUMER_BARCODE_STRING = os.getenv("PAPERLESS_CONSUMER_BARCODE_STRING", "PATCHT")
+
 OPTIMIZE_THUMBNAILS = __get_boolean("PAPERLESS_OPTIMIZE_THUMBNAILS", "true")
 
 OCR_PAGES = int(os.getenv("PAPERLESS_OCR_PAGES", 0))