Revert "Merge pull request #2732 from bdr99/skip_neverarchive"

This reverts commit 77b23d3acb573232e4e307b63a83f8ff557c0e7e, reversing
changes made to 5d8aa278315dcf92bfa1abe9e1fbd4911f8ed258.

docs/configuration.md

@@ -419,10 +419,7 @@ modes are available:
         an archived version of your documents when it finds any text in
         them. This is useful if you don't want to have two
         almost-identical versions of your digital documents in the media
-        folder.
+        folder. This is the fastest option.
-
-    -   `skip_neverarchive`: In addition to skip, paperless will never
-        create an archive version of your documents. This is the fastest option.
 
     -   `redo`: Paperless will OCR all pages of your documents and
         attempt to replace any existing text layers with new text. This

src/paperless/checks.py

@@ -127,13 +127,7 @@ def settings_values_check(app_configs, **kwargs):
                 Error(f'OCR output type "{settings.OCR_OUTPUT_TYPE}" is not valid'),
             )
 
-        if settings.OCR_MODE not in {
+        if settings.OCR_MODE not in {"force", "skip", "redo", "skip_noarchive"}:
-            "force",
-            "skip",
-            "redo",
-            "skip_noarchive",
-            "skip_neverarchive",
-        }:
             msgs.append(Error(f'OCR output mode "{settings.OCR_MODE}" is not valid'))
 
         if settings.OCR_CLEAN not in {"clean", "clean-final", "none"}:

src/paperless_tesseract/parsers.py

@@ -192,7 +192,7 @@ class RasterisedDocumentParser(DocumentParser):
 
         if settings.OCR_MODE == "force" or safe_fallback:
             ocrmypdf_args["force_ocr"] = True
-        elif settings.OCR_MODE in ["skip", "skip_noarchive", "skip_neverarchive"]:
+        elif settings.OCR_MODE in ["skip", "skip_noarchive"]:
             ocrmypdf_args["skip_text"] = True
         elif settings.OCR_MODE == "redo":
             ocrmypdf_args["redo_ocr"] = True
@@ -294,10 +294,7 @@ class RasterisedDocumentParser(DocumentParser):
 
         # If the original has text, and the user doesn't want an archive,
         # we're done here
-        if (
+        if settings.OCR_MODE == "skip_noarchive" and original_has_text:
-            settings.OCR_MODE in ["skip_noarchive", "skip_neverarchive"]
-            and original_has_text
-        ):
             self.log("debug", "Document has text, skipping OCRmyPDF entirely.")
             self.text = text_original
             return
@@ -323,9 +320,7 @@ class RasterisedDocumentParser(DocumentParser):
             self.log("debug", f"Calling OCRmyPDF with args: {args}")
             ocrmypdf.ocr(**args)
 
-            # Only create archive file if archiving isn't being skipped
+            self.archive_path = archive_path
-            if settings.OCR_MODE != "skip_neverarchive":
-                self.archive_path = archive_path
 
             self.text = self.extract_text(sidecar_file, archive_path)
 

src/paperless_tesseract/tests/test_parser.py

@@ -438,52 +438,6 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
 
         self.assertIsNotNone(parser.archive_path)
 
-    @override_settings(OCR_MODE="skip_neverarchive")
-    def test_skip_neverarchive_withtext(self):
-        """
-        GIVEN:
-            - File with existing text layer
-            - OCR mode set to skip_neverarchive
-        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-digital.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_neverarchive")
-    def test_skip_neverarchive_notext(self):
-        """
-        GIVEN:
-            - File with text contained in images but no text layer
-            - OCR mode set to skip_neverarchive
-        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):
         """