Allow parsers to declare uses remote, and remote ocr_mode (#13634)

* uses_remote_service + allow_remote to allow opt-in / out of remote OCR

* Add to parser dev docs

* remote_ocr_mode config setting

* Checks for remote_ocr_mode and fix import

* Update config.component.spec.ts

* More tests for remote_ocr_mode

* Docs for remote_ocr_mode

* Ok, wire up the remote_ocr_mode with allow_remote for consumer

* Update consumer.py

* Format remote OCR mode check tests

* Use get_choice_from_env

src/paperless/tests/test_registry.py

@@ -468,6 +468,124 @@ class TestParserRegistryGetParserForFile:
         assert result is AcceptingBuiltin
 
 
+class TestParserRegistryRemoteParsers:
+    """Verify the allow_remote filter in ParserRegistry.get_parser_for_file()."""
+
+    @staticmethod
+    def _remote_parser_cls() -> type:
+        class RemoteParser:
+            name = "remote"
+            version = "1.0"
+            author = "A"
+            url = "https://example.com/remote"
+            uses_remote_service = True
+
+            @classmethod
+            def supported_mime_types(cls):
+                return {"text/plain": ".txt"}
+
+            @classmethod
+            def score(cls, mime_type, filename, path=None):
+                return 20
+
+        return RemoteParser
+
+    def test_remote_parser_wins_when_remote_allowed(
+        self,
+        dummy_parser_cls: type,
+    ) -> None:
+        """
+        GIVEN: A remote parser scoring 20 and a local parser scoring 10.
+        WHEN:  get_parser_for_file() is called with allow_remote=True.
+        THEN:  The remote parser is returned.
+        """
+        remote_parser_cls = self._remote_parser_cls()
+        registry = ParserRegistry()
+        registry.register_builtin(dummy_parser_cls)
+        registry.register_builtin(remote_parser_cls)
+
+        result = registry.get_parser_for_file(
+            "text/plain",
+            "readme.txt",
+            allow_remote=True,
+        )
+        assert result is remote_parser_cls
+
+    def test_remote_parser_skipped_when_remote_not_allowed(
+        self,
+        dummy_parser_cls: type,
+    ) -> None:
+        """
+        GIVEN: A remote parser scoring 20 and a local parser scoring 10.
+        WHEN:  get_parser_for_file() is called with allow_remote=False.
+        THEN:  The local parser is returned despite its lower score.
+        """
+        registry = ParserRegistry()
+        registry.register_builtin(dummy_parser_cls)
+        registry.register_builtin(self._remote_parser_cls())
+
+        result = registry.get_parser_for_file(
+            "text/plain",
+            "readme.txt",
+            allow_remote=False,
+        )
+        assert result is dummy_parser_cls
+
+    def test_no_parser_when_only_remote_available_and_not_allowed(self) -> None:
+        """
+        GIVEN: A registry whose only candidate declares uses_remote_service.
+        WHEN:  get_parser_for_file() is called with allow_remote=False.
+        THEN:  None is returned — the remote parser is never used as a
+               fallback when remote processing was not requested.
+        """
+        registry = ParserRegistry()
+        registry.register_builtin(self._remote_parser_cls())
+
+        result = registry.get_parser_for_file(
+            "text/plain",
+            "readme.txt",
+            allow_remote=False,
+        )
+        assert result is None
+
+    def test_parser_without_attribute_treated_as_local(
+        self,
+        dummy_parser_cls: type,
+    ) -> None:
+        """
+        GIVEN: A third-party parser predating uses_remote_service, so it does
+               not declare the attribute at all.
+        WHEN:  get_parser_for_file() is called with allow_remote=False.
+        THEN:  It is still considered, i.e. treated as fully local, rather
+               than raising AttributeError.
+        """
+        assert not hasattr(dummy_parser_cls, "uses_remote_service")
+
+        registry = ParserRegistry()
+        registry.register_builtin(dummy_parser_cls)
+
+        result = registry.get_parser_for_file(
+            "text/plain",
+            "readme.txt",
+            allow_remote=False,
+        )
+        assert result is dummy_parser_cls
+
+    def test_remote_allowed_by_default(self) -> None:
+        """
+        GIVEN: A registry containing only a remote parser.
+        WHEN:  get_parser_for_file() is called without allow_remote.
+        THEN:  The remote parser is returned — callers that do not opt in to
+               the filter keep the previous behaviour.
+        """
+        remote_parser_cls = self._remote_parser_cls()
+        registry = ParserRegistry()
+        registry.register_builtin(remote_parser_cls)
+
+        result = registry.get_parser_for_file("text/plain", "readme.txt")
+        assert result is remote_parser_cls
+
+
 class TestDiscover:
     """Verify entrypoint discovery in ParserRegistry.discover()."""
 

src/paperless/tests/test_remote_ocr_config.py

@@ -8,6 +8,7 @@ import pytest
 from django.test import override_settings
 
 from paperless.config import RemoteOCRConfig
+from paperless.models import RemoteOCRMode
 
 if TYPE_CHECKING:
     from unittest.mock import MagicMock
@@ -20,6 +21,7 @@ def null_app_config(mocker) -> MagicMock:
         remote_ocr_engine=None,
         remote_ocr_api_key=None,
         remote_ocr_endpoint=None,
+        remote_ocr_mode=None,
     )
 
 
@@ -47,10 +49,12 @@ class TestRemoteOCRConfig:
             REMOTE_OCR_ENGINE="azureai",
             REMOTE_OCR_API_KEY="env-key",
             REMOTE_OCR_ENDPOINT="https://env.cognitiveservices.azure.com",
+            REMOTE_OCR_MODE=RemoteOCRMode.WORKFLOW_ONLY,
         )
         assert cfg.remote_ocr_engine == "azureai"
         assert cfg.remote_ocr_api_key == "env-key"
         assert cfg.remote_ocr_endpoint == "https://env.cognitiveservices.azure.com"
+        assert cfg.remote_ocr_mode == RemoteOCRMode.WORKFLOW_ONLY
 
     def test_app_config_takes_precedence(
         self,
@@ -61,16 +65,19 @@ class TestRemoteOCRConfig:
             remote_ocr_engine="azureai",
             remote_ocr_api_key="db-key",
             remote_ocr_endpoint="https://db.cognitiveservices.azure.com",
+            remote_ocr_mode=RemoteOCRMode.WORKFLOW_ONLY,
         )
         cfg = make_remote_ocr_config(
             app_config,
             REMOTE_OCR_ENGINE=None,
             REMOTE_OCR_API_KEY="env-key",
             REMOTE_OCR_ENDPOINT="https://env.cognitiveservices.azure.com",
+            REMOTE_OCR_MODE=RemoteOCRMode.ALWAYS,
         )
         assert cfg.remote_ocr_engine == "azureai"
         assert cfg.remote_ocr_api_key == "db-key"
         assert cfg.remote_ocr_endpoint == "https://db.cognitiveservices.azure.com"
+        assert cfg.remote_ocr_mode == RemoteOCRMode.WORKFLOW_ONLY
 
     def test_unset_everywhere(
         self,
@@ -86,3 +93,21 @@ class TestRemoteOCRConfig:
         assert cfg.remote_ocr_engine is None
         assert cfg.remote_ocr_api_key is None
         assert cfg.remote_ocr_endpoint is None
+
+
+class TestRemoteOCRByDefault:
+    def test_always_mode(self, make_remote_ocr_config, null_app_config) -> None:
+        cfg = make_remote_ocr_config(
+            null_app_config,
+            REMOTE_OCR_MODE=RemoteOCRMode.ALWAYS,
+        )
+
+        assert cfg.remote_ocr_by_default is True
+
+    def test_workflow_only_mode(self, make_remote_ocr_config, null_app_config) -> None:
+        cfg = make_remote_ocr_config(
+            null_app_config,
+            REMOTE_OCR_MODE=RemoteOCRMode.WORKFLOW_ONLY,
+        )
+
+        assert cfg.remote_ocr_by_default is False