mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-10-19 06:18:15 +00:00
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
This commit is contained in:
1 parent
a1f20c9fe7
commit
7f1609332a
20 files changed
+425
-1
No files matched your search
@@ -9,6 +9,7 @@ from paperless.models import CleanChoices
|
||||
from paperless.models import ColorConvertChoices
|
||||
from paperless.models import ModeChoices
|
||||
from paperless.models import OutputTypeChoices
|
||||
from paperless.models import RemoteOCRMode
|
||||
|
||||
|
||||
@dataclasses.dataclass
|
||||
@@ -194,6 +195,7 @@ class RemoteOCRConfig(BaseConfig):
|
||||
remote_ocr_engine: str | None = dataclasses.field(init=False)
|
||||
remote_ocr_api_key: str | None = dataclasses.field(init=False)
|
||||
remote_ocr_endpoint: str | None = dataclasses.field(init=False)
|
||||
remote_ocr_mode: RemoteOCRMode = dataclasses.field(init=False)
|
||||
|
||||
def __post_init__(self) -> None:
|
||||
app_config = self._get_config_instance()
|
||||
@@ -207,6 +209,20 @@ class RemoteOCRConfig(BaseConfig):
|
||||
self.remote_ocr_endpoint = (
|
||||
app_config.remote_ocr_endpoint or settings.REMOTE_OCR_ENDPOINT
|
||||
)
|
||||
self.remote_ocr_mode = app_config.remote_ocr_mode or RemoteOCRMode(
|
||||
settings.REMOTE_OCR_MODE,
|
||||
)
|
||||
|
||||
@property
|
||||
def remote_ocr_by_default(self) -> bool:
|
||||
"""
|
||||
Whether every supported document goes to the remote engine.
|
||||
|
||||
When False the remote engine is used only for documents that
|
||||
explicitly asked for it, i.e. a workflow matched during consumption or
|
||||
the user ticked the box when reprocessing.
|
||||
"""
|
||||
return self.remote_ocr_mode == RemoteOCRMode.ALWAYS
|
||||
|
||||
|
||||
@dataclasses.dataclass
|
||||
|
||||
@@ -0,0 +1,27 @@
|
||||
# Generated by Django 5.2.16 on 2026-08-10 15:43
|
||||
|
||||
from django.db import migrations
|
||||
from django.db import models
|
||||
|
||||
|
||||
class Migration(migrations.Migration):
|
||||
dependencies = [
|
||||
("paperless", "0014_applicationconfiguration_remote_ocr_api_key_and_more"),
|
||||
]
|
||||
|
||||
operations = [
|
||||
migrations.AddField(
|
||||
model_name="applicationconfiguration",
|
||||
name="remote_ocr_mode",
|
||||
field=models.CharField(
|
||||
blank=True,
|
||||
choices=[
|
||||
("always", "All supported documents"),
|
||||
("workflow_only", "Only when a workflow enables it"),
|
||||
],
|
||||
max_length=32,
|
||||
null=True,
|
||||
verbose_name="Sets which documents are sent to the remote OCR engine",
|
||||
),
|
||||
),
|
||||
]
|
||||
@@ -82,6 +82,15 @@ class RemoteOCREngine(models.TextChoices):
|
||||
AZURE_AI = ("azureai", _("Azure AI Document Intelligence"))
|
||||
|
||||
|
||||
class RemoteOCRMode(models.TextChoices):
|
||||
"""
|
||||
Matches to PAPERLESS_REMOTE_OCR_MODE
|
||||
"""
|
||||
|
||||
ALWAYS = ("always", _("All supported documents"))
|
||||
WORKFLOW_ONLY = ("workflow_only", _("Only when a workflow enables it"))
|
||||
|
||||
|
||||
class LLMEmbeddingBackend(models.TextChoices):
|
||||
OPENAI_LIKE = ("openai-like", _("OpenAI-compatible"))
|
||||
HUGGINGFACE = ("huggingface", _("Huggingface"))
|
||||
@@ -323,6 +332,15 @@ class ApplicationConfiguration(AbstractSingletonModel):
|
||||
max_length=256,
|
||||
)
|
||||
|
||||
# PAPERLESS_REMOTE_OCR_MODE
|
||||
remote_ocr_mode = models.CharField(
|
||||
verbose_name=_("Sets which documents are sent to the remote OCR engine"),
|
||||
blank=True,
|
||||
null=True,
|
||||
max_length=32,
|
||||
choices=RemoteOCRMode.choices,
|
||||
)
|
||||
|
||||
"""
|
||||
AI related settings
|
||||
"""
|
||||
|
||||
@@ -134,6 +134,11 @@ class ParserProtocol(Protocol):
|
||||
Author or organisation name.
|
||||
url : str
|
||||
URL for documentation, source code, or issue tracker.
|
||||
|
||||
Parsers that send document content to a remote service should additionally
|
||||
set ``uses_remote_service = True`` so the registry can exclude them when
|
||||
remote processing has not been requested for a document. The attribute is
|
||||
optional so a parser that omits it is treated as fully local.
|
||||
"""
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
@@ -145,6 +150,10 @@ class ParserProtocol(Protocol):
|
||||
author: str
|
||||
url: str
|
||||
|
||||
# NOTE: uses_remote_service is not declared here, the registry reads it
|
||||
# with getattr(cls, ..., False) for backwards-compatibility with existing
|
||||
# parsers
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Class methods
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@@ -334,6 +334,8 @@ class ParserRegistry:
|
||||
mime_type: str,
|
||||
filename: str,
|
||||
path: Path | None = None,
|
||||
*,
|
||||
allow_remote: bool = True,
|
||||
) -> type[ParserProtocol] | None:
|
||||
"""Return the best parser class for the given file, or None.
|
||||
|
||||
@@ -359,6 +361,11 @@ class ParserRegistry:
|
||||
path:
|
||||
Optional filesystem path to the file. Forwarded to each
|
||||
parser's score method.
|
||||
allow_remote:
|
||||
When False, parsers that declare ``uses_remote_service = True``
|
||||
are excluded from consideration, so a document is never sent to
|
||||
a remote service. Parsers that do not declare the attribute
|
||||
are treated as local and are always considered.
|
||||
|
||||
Returns
|
||||
-------
|
||||
@@ -374,6 +381,13 @@ class ParserRegistry:
|
||||
if mime_type not in parser_class.supported_mime_types():
|
||||
continue
|
||||
|
||||
if not allow_remote and getattr(
|
||||
parser_class,
|
||||
"uses_remote_service",
|
||||
False,
|
||||
):
|
||||
continue
|
||||
|
||||
score = parser_class.score(mime_type, filename, path)
|
||||
if score is None:
|
||||
continue
|
||||
|
||||
@@ -102,6 +102,9 @@ class RemoteDocumentParser:
|
||||
Maintainer name.
|
||||
url : str
|
||||
Issue tracker / source URL.
|
||||
uses_remote_service : bool
|
||||
Content is sent to a remote service, True so that the registry
|
||||
can skip this parser if remote processing was not requested.
|
||||
"""
|
||||
|
||||
name: str = "Paperless-ngx Remote OCR Parser"
|
||||
@@ -109,6 +112,8 @@ class RemoteDocumentParser:
|
||||
author: str = "Paperless-ngx Contributors"
|
||||
url: str = "https://github.com/paperless-ngx/paperless-ngx"
|
||||
|
||||
uses_remote_service: bool = True
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Class methods
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@@ -1203,6 +1203,11 @@ WEBHOOKS_ALLOW_INTERNAL_REQUESTS = get_bool_from_env(
|
||||
REMOTE_OCR_ENGINE = os.getenv("PAPERLESS_REMOTE_OCR_ENGINE")
|
||||
REMOTE_OCR_API_KEY = os.getenv("PAPERLESS_REMOTE_OCR_API_KEY")
|
||||
REMOTE_OCR_ENDPOINT = os.getenv("PAPERLESS_REMOTE_OCR_ENDPOINT")
|
||||
REMOTE_OCR_MODE = get_choice_from_env(
|
||||
"PAPERLESS_REMOTE_OCR_MODE",
|
||||
{"always", "workflow_only"},
|
||||
default="always",
|
||||
)
|
||||
|
||||
################################################################################
|
||||
# AI Settings #
|
||||
|
||||
@@ -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()."""
|
||||
|
||||
|
||||
@@ -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
|
||||
Reference in new issue
Block a user