Add PAPERLESS_OCR_SKIP_ARCHIVE_FILE config setting

src/paperless/checks.py

@@ -130,6 +130,23 @@ def settings_values_check(app_configs, **kwargs):
         if settings.OCR_MODE not in {"force", "skip", "redo", "skip_noarchive"}:
             msgs.append(Error(f'OCR output mode "{settings.OCR_MODE}" is not valid'))
 
+        if settings.OCR_MODE == "skip_noarchive":
+            msgs.append(
+                Warning(
+                    'OCR output mode "skip_noarchive" is deprecated and will be'
+                    "removed in a future version. Please use"
+                    "PAPERLESS_OCR_SKIP_ARCHIVE_FILE instead.",
+                ),
+            )
+
+        if settings.OCR_SKIP_ARCHIVE_FILE not in {"never", "with_text", "always"}:
+            msgs.append(
+                Error(
+                    "OCR_SKIP_ARCHIVE_FILE setting "
+                    f'"{settings.OCR_SKIP_ARCHIVE_FILE}" is not valid',
+                ),
+            )
+
         if settings.OCR_CLEAN not in {"clean", "clean-final", "none"}:
             msgs.append(Error(f'OCR clean mode "{settings.OCR_CLEAN}" is not valid'))
         return msgs

src/paperless/settings.py

@@ -725,6 +725,8 @@ OCR_OUTPUT_TYPE = os.getenv("PAPERLESS_OCR_OUTPUT_TYPE", "pdfa")
 # skip. redo, force
 OCR_MODE = os.getenv("PAPERLESS_OCR_MODE", "skip")
 
+OCR_SKIP_ARCHIVE_FILE = os.getenv("PAPERLESS_OCR_SKIP_ARCHIVE_FILE", "never")
+
 OCR_IMAGE_DPI = os.getenv("PAPERLESS_OCR_IMAGE_DPI")
 
 OCR_CLEAN = os.getenv("PAPERLESS_OCR_CLEAN", "clean")

src/paperless_tesseract/parsers.py

@@ -294,7 +294,11 @@ class RasterisedDocumentParser(DocumentParser):
 
         # If the original has text, and the user doesn't want an archive,
         # we're done here
-        if settings.OCR_MODE == "skip_noarchive" and original_has_text:
+        skip_archive_for_text = (
+            settings.OCR_MODE == "skip_noarchive"
+            or settings.OCR_SKIP_ARCHIVE_FILE in ["with_text", "always"]
+        )
+        if skip_archive_for_text and original_has_text:
             self.log("debug", "Document has text, skipping OCRmyPDF entirely.")
             self.text = text_original
             return
@@ -320,7 +324,8 @@ class RasterisedDocumentParser(DocumentParser):
             self.log("debug", f"Calling OCRmyPDF with args: {args}")
             ocrmypdf.ocr(**args)
 
-            self.archive_path = archive_path
+            if settings.OCR_SKIP_ARCHIVE_FILE != "always":
+                self.archive_path = archive_path
 
             self.text = self.extract_text(sidecar_file, archive_path)
 

src/paperless_tesseract/tests/test_parser.py

@@ -332,7 +332,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
             ["page 1", "page 2", "page 3"],
         )
 
-    @override_settings(OOCR_MODE="skip")
+    @override_settings(OCR_MODE="skip")
     def test_multi_page_analog_pages_skip(self):
         parser = RasterisedDocumentParser(None)
         parser.parse(
@@ -438,6 +438,144 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
 
         self.assertIsNotNone(parser.archive_path)
 
+    @override_settings(OCR_SKIP_ARCHIVE_FILE="never")
+    def test_skip_archive_never_withtext(self):
+        """
+        GIVEN:
+            - File with existing text layer
+            - OCR_SKIP_ARCHIVE_FILE set to never
+        WHEN:
+            - Document is parsed
+        THEN:
+            - Text from text layer is extracted
+            - Archive file is created
+        """
+        parser = RasterisedDocumentParser(None)
+        parser.parse(
+            os.path.join(self.SAMPLE_FILES, "multi-page-digital.pdf"),
+            "application/pdf",
+        )
+        self.assertIsNotNone(parser.archive_path)
+        self.assertContainsStrings(
+            parser.get_text().lower(),
+            ["page 1", "page 2", "page 3"],
+        )
+
+    @override_settings(OCR_SKIP_ARCHIVE_FILE="never")
+    def test_skip_archive_never_withimages(self):
+        """
+        GIVEN:
+            - File with text contained in images but no text layer
+            - OCR_SKIP_ARCHIVE_FILE set to never
+        WHEN:
+            - Document is parsed
+        THEN:
+            - Text from images is extracted
+            - Archive file is created
+        """
+        parser = RasterisedDocumentParser(None)
+        parser.parse(
+            os.path.join(self.SAMPLE_FILES, "multi-page-images.pdf"),
+            "application/pdf",
+        )
+        self.assertIsNotNone(parser.archive_path)
+        self.assertContainsStrings(
+            parser.get_text().lower(),
+            ["page 1", "page 2", "page 3"],
+        )
+
+    @override_settings(OCR_SKIP_ARCHIVE_FILE="with_text")
+    def test_skip_archive_withtext_withtext(self):
+        """
+        GIVEN:
+            - File with existing text layer
+            - OCR_SKIP_ARCHIVE_FILE set to with_text
+        WHEN:
+            - Document is parsed
+        THEN:
+            - Text from text layer is extracted
+            - No archive file is created
+        """
+        parser = RasterisedDocumentParser(None)
+        parser.parse(
+            os.path.join(self.SAMPLE_FILES, "multi-page-digital.pdf"),
+            "application/pdf",
+        )
+        self.assertIsNone(parser.archive_path)
+        self.assertContainsStrings(
+            parser.get_text().lower(),
+            ["page 1", "page 2", "page 3"],
+        )
+
+    @override_settings(OCR_SKIP_ARCHIVE_FILE="with_text")
+    def test_skip_archive_withtext_withimages(self):
+        """
+        GIVEN:
+            - File with text contained in images but no text layer
+            - OCR_SKIP_ARCHIVE_FILE set to with_text
+        WHEN:
+            - Document is parsed
+        THEN:
+            - Text from images is extracted
+            - Archive file is created
+        """
+        parser = RasterisedDocumentParser(None)
+        parser.parse(
+            os.path.join(self.SAMPLE_FILES, "multi-page-images.pdf"),
+            "application/pdf",
+        )
+        self.assertIsNotNone(parser.archive_path)
+        self.assertContainsStrings(
+            parser.get_text().lower(),
+            ["page 1", "page 2", "page 3"],
+        )
+
+    @override_settings(OCR_SKIP_ARCHIVE_FILE="always")
+    def test_skip_archive_always_withtext(self):
+        """
+        GIVEN:
+            - File with existing text layer
+            - OCR_SKIP_ARCHIVE_FILE set to always
+        WHEN:
+            - Document is parsed
+        THEN:
+            - Text from text layer is extracted
+            - No archive file is created
+        """
+        parser = RasterisedDocumentParser(None)
+        parser.parse(
+            os.path.join(self.SAMPLE_FILES, "multi-page-digital.pdf"),
+            "application/pdf",
+        )
+        self.assertIsNone(parser.archive_path)
+        self.assertContainsStrings(
+            parser.get_text().lower(),
+            ["page 1", "page 2", "page 3"],
+        )
+
+    @override_settings(OCR_SKIP_ARCHIVE_FILE="always")
+    def test_skip_archive_always_withimages(self):
+        """
+        GIVEN:
+            - File with text contained in images but no text layer
+            - OCR_SKIP_ARCHIVE_FILE set to always
+        WHEN:
+            - Document is parsed
+        THEN:
+            - Text from images is extracted
+            - No archive file is created
+        """
+        parser = RasterisedDocumentParser(None)
+        parser.parse(
+            os.path.join(self.SAMPLE_FILES, "multi-page-images.pdf"),
+            "application/pdf",
+        )
+        self.assertIsNone(parser.archive_path)
+        self.assertContainsStrings(
+            parser.get_text().lower(),
+            ["page 1", "page 2", "page 3"],
+        )
+
     @override_settings(OCR_MODE="skip")
     def test_multi_page_mixed(self):
         """