feat!: rename OCR_SKIP_ARCHIVE_FILE to ARCHIVE_FILE_GENERATION

Rename the Django setting OCR_SKIP_ARCHIVE_FILE to ARCHIVE_FILE_GENERATION
and the env var PAPERLESS_OCR_SKIP_ARCHIVE_FILE to PAPERLESS_ARCHIVE_FILE_GENERATION.
Rename the OcrConfig attribute skip_archive_file to archive_file_generation.
Update checks.py error messages and all tests accordingly.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

src/paperless/checks.py

@@ -135,11 +135,11 @@ def settings_values_check(app_configs, **kwargs):
         if settings.OCR_MODE not in {"auto", "force", "redo", "off"}:
             msgs.append(Error(f'OCR output mode "{settings.OCR_MODE}" is not valid'))
 
-        if settings.OCR_SKIP_ARCHIVE_FILE not in {"auto", "always", "never"}:
+        if settings.ARCHIVE_FILE_GENERATION not in {"auto", "always", "never"}:
             msgs.append(
                 Error(
-                    "OCR_SKIP_ARCHIVE_FILE setting "
-                    f'"{settings.OCR_SKIP_ARCHIVE_FILE}" is not valid',
+                    "PAPERLESS_ARCHIVE_FILE_GENERATION setting "
+                    f'"{settings.ARCHIVE_FILE_GENERATION}" is not valid',
                 ),
             )
 

src/paperless/config.py

@@ -46,7 +46,7 @@ class OcrConfig(OutputTypeConfig):
     pages: int | None = dataclasses.field(init=False)
     language: str = dataclasses.field(init=False)
     mode: str = dataclasses.field(init=False)
-    skip_archive_file: str = dataclasses.field(init=False)
+    archive_file_generation: str = dataclasses.field(init=False)
     image_dpi: int | None = dataclasses.field(init=False)
     clean: str = dataclasses.field(init=False)
     deskew: bool = dataclasses.field(init=False)
@@ -64,8 +64,8 @@ class OcrConfig(OutputTypeConfig):
         self.pages = app_config.pages or settings.OCR_PAGES
         self.language = app_config.language or settings.OCR_LANGUAGE
         self.mode = app_config.mode or settings.OCR_MODE
-        self.skip_archive_file = (
-            app_config.skip_archive_file or settings.OCR_SKIP_ARCHIVE_FILE
+        self.archive_file_generation = (
+            app_config.skip_archive_file or settings.ARCHIVE_FILE_GENERATION
         )
         self.image_dpi = app_config.image_dpi or settings.OCR_IMAGE_DPI
         self.clean = app_config.unpaper_clean or settings.OCR_CLEAN

src/paperless/parsers/tesseract.py

@@ -422,7 +422,7 @@ class RasterisedDocumentParser:
         skip_archive_for_text = self.settings.mode not in {
             ModeChoices.FORCE,
             ModeChoices.REDO,
-        } and self.settings.skip_archive_file in {
+        } and self.settings.archive_file_generation in {
             ArchiveFileGenerationChoices.NEVER,
             ArchiveFileGenerationChoices.AUTO,
         }
@@ -455,7 +455,10 @@ class RasterisedDocumentParser:
             self.log.debug(f"Calling OCRmyPDF with args: {args}")
             ocrmypdf.ocr(**args)
 
-            if self.settings.skip_archive_file != ArchiveFileGenerationChoices.NEVER:
+            if (
+                self.settings.archive_file_generation
+                != ArchiveFileGenerationChoices.NEVER
+            ):
                 self.archive_path = archive_path
 
             self.text = self.extract_text(sidecar_file, archive_path)

src/paperless/settings/__init__.py

@@ -881,8 +881,8 @@ OCR_MODE = get_choice_from_env(
     default="auto",
 )
 
-OCR_SKIP_ARCHIVE_FILE = get_choice_from_env(
-    "PAPERLESS_OCR_SKIP_ARCHIVE_FILE",
+ARCHIVE_FILE_GENERATION = get_choice_from_env(
+    "PAPERLESS_ARCHIVE_FILE_GENERATION",
     {"auto", "always", "never"},
     default="auto",
 )

src/paperless/tests/parsers/test_tesseract_parser.py

@@ -386,7 +386,7 @@ class TestParsePdf:
         tesseract_parser: RasterisedDocumentParser,
         tesseract_samples_dir: Path,
     ) -> None:
-        tesseract_parser.settings.skip_archive_file = "always"
+        tesseract_parser.settings.archive_file_generation = "always"
         tesseract_parser.parse(
             tesseract_samples_dir / "with-form.pdf",
             "application/pdf",
@@ -546,7 +546,7 @@ class TestParseMultiPage:
         tesseract_parser: RasterisedDocumentParser,
         tesseract_samples_dir: Path,
     ) -> None:
-        tesseract_parser.settings.skip_archive_file = "always"
+        tesseract_parser.settings.archive_file_generation = "always"
         tesseract_parser.parse(
             tesseract_samples_dir / "multi-page-digital.pdf",
             "application/pdf",
@@ -574,7 +574,7 @@ class TestParseMultiPage:
     ) -> None:
         tesseract_parser.settings.pages = 2
         tesseract_parser.settings.mode = mode
-        tesseract_parser.settings.skip_archive_file = "always"
+        tesseract_parser.settings.archive_file_generation = "always"
         tesseract_parser.parse(
             tesseract_samples_dir / "multi-page-digital.pdf",
             "application/pdf",
@@ -819,7 +819,7 @@ class TestSkipArchive:
         tesseract_parser: RasterisedDocumentParser,
         tesseract_samples_dir: Path,
     ) -> None:
-        tesseract_parser.settings.skip_archive_file = skip_archive_file
+        tesseract_parser.settings.archive_file_generation = skip_archive_file
         tesseract_parser.parse(tesseract_samples_dir / filename, "application/pdf")
         text = tesseract_parser.get_text().lower()
         assert_ordered_substrings(text, ["page 1", "page 2", "page 3"])
@@ -850,7 +850,7 @@ class TestParseMixed:
             - All pages extracted; archive created; sidecar notes skipped pages
         """
         tesseract_parser.settings.mode = "auto"
-        tesseract_parser.settings.skip_archive_file = "always"
+        tesseract_parser.settings.archive_file_generation = "always"
         tesseract_parser.parse(
             tesseract_samples_dir / "multi-page-mixed.pdf",
             "application/pdf",

src/paperless/tests/test_checks.py

@@ -136,9 +136,9 @@ class TestOcrSettingsChecks:
                 id="deprecated-mode-now-invalid",
             ),
             pytest.param(
-                "OCR_SKIP_ARCHIVE_FILE",
+                "ARCHIVE_FILE_GENERATION",
                 "invalid",
-                'OCR_SKIP_ARCHIVE_FILE setting "invalid"',
+                'PAPERLESS_ARCHIVE_FILE_GENERATION setting "invalid"',
                 id="invalid-skip-archive-file",
             ),
             pytest.param(