mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-07-06 12:05:09 +00:00
Chore: Drop old signal and unneeded apps, transition to parser registry instead (#12405)
* refactor: switch consumer and callers to ParserRegistry (Phase 4) Replace all Django signal-based parser discovery with direct registry calls. Removes `_parser_cleanup`, `parser_is_new_style` shims, and all old-style isinstance checks. All parser instantiation now uses the `with parser_class() as parser:` context manager pattern. - documents/parsers.py: delegate to get_parser_registry(); drop lru_cache - documents/consumer.py: use registry + context manager; remove shims - documents/tasks.py: same pattern - documents/management/commands/document_thumbnails.py: same pattern - documents/views.py: get_metadata uses context manager - documents/checks.py: use get_parser_registry().all_parsers() - paperless/parsers/registry.py: add all_parsers() public method - tests: update mocks to target documents.consumer.get_parser_class_for_mime_type Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * refactor: drop get_parser_class_for_mime_type; callers use registry directly All callers now call get_parser_registry().get_parser_for_file() with the actual filename and path, enabling score() to use file extension hints. The MIME-only helper is removed. - consumer.py: passes self.filename + self.working_copy - tasks.py: passes document.original_filename + document.source_path - document_thumbnails.py: same pattern - views.py: passes Path(file).name + Path(file) - parsers.py: internal helpers inline the registry call with filename="" - test_parsers.py: drop TestParserDiscovery (was testing mock behavior); TestParserAvailability uses registry directly - test_consumer.py: mocks switch to documents.consumer.get_parser_registry Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * refactor: remove document_consumer_declaration signal infrastructure Remove the document_consumer_declaration signal that was previously used for parser registration. Each parser app no longer connects to this signal, and the signal declaration itself has been removed from documents/signals. Changes: - Remove document_consumer_declaration from documents/signals/__init__.py - Remove ready() methods and signal imports from all parser app configs - Delete signal shim files (signals.py) from all parser apps: - paperless_tesseract/signals.py - paperless_text/signals.py - paperless_tika/signals.py - paperless_mail/signals.py - paperless_remote/signals.py Parser discovery now happens exclusively through the ParserRegistry system introduced in the previous refactor phases. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * refactor: remove empty paperless_text and paperless_tika Django apps After parser classes were moved to paperless/parsers/ in the plugin refactor, these Django apps contained only empty AppConfig classes with no models, views, tasks, migrations, or other functionality. - Remove paperless_text and paperless_tika from INSTALLED_APPS - Delete empty app directories entirely - Update pyproject.toml test exclusions - Clean stale mypy baseline entries for moved parser files paperless_remote app is retained as it contains meaningful system checks for Azure AI configuration. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * Moves the checks and tests to the main application and removes the old applications * Adds a comment to satisy Sonar * refactor: remove automatic log_summary() call from get_parser_registry() The summary was logged once per process, causing it to appear repeatedly during Docker startup (management commands, web server, each Celery worker subprocess). External parsers are already announced individually at INFO when discovered; the full summary is redundant noise. log_summary() is retained on ParserRegistry for manual/debug use. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * Cleans up the duplicate test file/fixture * Fixes a race condition where webserver threads could race to populate the registry --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Trenton H
GitHub
@@ -3,6 +3,7 @@ import os
|
||||
import pwd
|
||||
import shutil
|
||||
import stat
|
||||
import subprocess
|
||||
from pathlib import Path
|
||||
|
||||
from django.conf import settings
|
||||
@@ -299,3 +300,62 @@ def check_deprecated_db_settings(
|
||||
)
|
||||
|
||||
return warnings
|
||||
|
||||
|
||||
@register()
|
||||
def check_remote_parser_configured(app_configs, **kwargs) -> list[Error]:
|
||||
if settings.REMOTE_OCR_ENGINE == "azureai" and not (
|
||||
settings.REMOTE_OCR_ENDPOINT and settings.REMOTE_OCR_API_KEY
|
||||
):
|
||||
return [
|
||||
Error(
|
||||
"Azure AI remote parser requires endpoint and API key to be configured.",
|
||||
),
|
||||
]
|
||||
|
||||
return []
|
||||
|
||||
|
||||
def get_tesseract_langs():
|
||||
proc = subprocess.run(
|
||||
[shutil.which("tesseract"), "--list-langs"],
|
||||
capture_output=True,
|
||||
)
|
||||
|
||||
# Decode bytes to string, split on newlines, trim out the header
|
||||
proc_lines = proc.stdout.decode("utf8", errors="ignore").strip().split("\n")[1:]
|
||||
|
||||
return [x.strip() for x in proc_lines]
|
||||
|
||||
|
||||
@register()
|
||||
def check_default_language_available(app_configs, **kwargs):
|
||||
errs = []
|
||||
|
||||
if not settings.OCR_LANGUAGE:
|
||||
errs.append(
|
||||
Warning(
|
||||
"No OCR language has been specified with PAPERLESS_OCR_LANGUAGE. "
|
||||
"This means that tesseract will fallback to english.",
|
||||
),
|
||||
)
|
||||
return errs
|
||||
|
||||
# binaries_check in paperless will check and report if this doesn't exist
|
||||
# So skip trying to do anything here and let that handle missing binaries
|
||||
if shutil.which("tesseract") is not None:
|
||||
installed_langs = get_tesseract_langs()
|
||||
|
||||
specified_langs = [x.strip() for x in settings.OCR_LANGUAGE.split("+")]
|
||||
|
||||
for lang in specified_langs:
|
||||
if lang not in installed_langs:
|
||||
errs.append(
|
||||
Error(
|
||||
f"The selected ocr language {lang} is "
|
||||
f"not installed. Paperless cannot OCR your documents "
|
||||
f"without it. Please fix PAPERLESS_OCR_LANGUAGE.",
|
||||
),
|
||||
)
|
||||
|
||||
return errs
|
||||
|
||||
@@ -33,6 +33,7 @@ name, version, author, url, supported_mime_types (callable), score (callable).
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import threading
|
||||
from importlib.metadata import entry_points
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
@@ -49,6 +50,7 @@ logger = logging.getLogger("paperless.parsers.registry")
|
||||
|
||||
_registry: ParserRegistry | None = None
|
||||
_discovery_complete: bool = False
|
||||
_lock = threading.Lock()
|
||||
|
||||
# Attribute names that every registered external parser class must expose.
|
||||
_REQUIRED_ATTRS: tuple[str, ...] = (
|
||||
@@ -74,7 +76,6 @@ def get_parser_registry() -> ParserRegistry:
|
||||
1. Creates a new ParserRegistry.
|
||||
2. Calls register_defaults to install built-in parsers.
|
||||
3. Calls discover to load third-party plugins via importlib.metadata entrypoints.
|
||||
4. Calls log_summary to emit a startup summary.
|
||||
|
||||
Subsequent calls return the same instance immediately.
|
||||
|
||||
@@ -85,14 +86,15 @@ def get_parser_registry() -> ParserRegistry:
|
||||
"""
|
||||
global _registry, _discovery_complete
|
||||
|
||||
if _registry is None:
|
||||
_registry = ParserRegistry()
|
||||
_registry.register_defaults()
|
||||
with _lock:
|
||||
if _registry is None:
|
||||
r = ParserRegistry()
|
||||
r.register_defaults()
|
||||
_registry = r
|
||||
|
||||
if not _discovery_complete:
|
||||
_registry.discover()
|
||||
_registry.log_summary()
|
||||
_discovery_complete = True
|
||||
if not _discovery_complete:
|
||||
_registry.discover()
|
||||
_discovery_complete = True
|
||||
|
||||
return _registry
|
||||
|
||||
@@ -113,9 +115,11 @@ def init_builtin_parsers() -> None:
|
||||
"""
|
||||
global _registry
|
||||
|
||||
if _registry is None:
|
||||
_registry = ParserRegistry()
|
||||
_registry.register_defaults()
|
||||
with _lock:
|
||||
if _registry is None:
|
||||
r = ParserRegistry()
|
||||
r.register_defaults()
|
||||
_registry = r
|
||||
|
||||
|
||||
def reset_parser_registry() -> None:
|
||||
@@ -304,6 +308,23 @@ class ParserRegistry:
|
||||
getattr(cls, "url", "unknown"),
|
||||
)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Inspection helpers
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def all_parsers(self) -> list[type[ParserProtocol]]:
|
||||
"""Return all registered parser classes (external first, then builtins).
|
||||
|
||||
Used by compatibility wrappers that need to iterate every parser to
|
||||
compute the full set of supported MIME types and file extensions.
|
||||
|
||||
Returns
|
||||
-------
|
||||
list[type[ParserProtocol]]
|
||||
External parsers followed by built-in parsers.
|
||||
"""
|
||||
return [*self._external, *self._builtins]
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Parser resolution
|
||||
# ------------------------------------------------------------------
|
||||
@@ -334,7 +355,7 @@ class ParserRegistry:
|
||||
mime_type:
|
||||
The detected MIME type of the file.
|
||||
filename:
|
||||
The original filename, including extension.
|
||||
The original filename, including extension. May be empty in some cases
|
||||
path:
|
||||
Optional filesystem path to the file. Forwarded to each
|
||||
parser's score method.
|
||||
|
||||
@@ -121,10 +121,7 @@ INSTALLED_APPS = [
|
||||
"django_extensions",
|
||||
"paperless",
|
||||
"documents.apps.DocumentsConfig",
|
||||
"paperless_tesseract.apps.PaperlessTesseractConfig",
|
||||
"paperless_text.apps.PaperlessTextConfig",
|
||||
"paperless_mail.apps.PaperlessMailConfig",
|
||||
"paperless_remote.apps.PaperlessRemoteParserConfig",
|
||||
"django.contrib.admin",
|
||||
"rest_framework",
|
||||
"rest_framework.authtoken",
|
||||
@@ -974,8 +971,8 @@ TIKA_GOTENBERG_ENDPOINT = os.getenv(
|
||||
"http://localhost:3000",
|
||||
)
|
||||
|
||||
if TIKA_ENABLED:
|
||||
INSTALLED_APPS.append("paperless_tika.apps.PaperlessTikaConfig")
|
||||
# Tika parser is now integrated into the main parser registry
|
||||
# No separate Django app needed
|
||||
|
||||
AUDIT_LOG_ENABLED = get_bool_from_env("PAPERLESS_AUDIT_LOG_ENABLED", "true")
|
||||
if AUDIT_LOG_ENABLED:
|
||||
|
||||
@@ -90,35 +90,6 @@ def text_parser() -> Generator[TextDocumentParser, None, None]:
|
||||
yield parser
|
||||
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Remote parser sample files
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def remote_samples_dir(samples_dir: Path) -> Path:
|
||||
"""Absolute path to the remote parser sample files directory.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
``<samples_dir>/remote/``
|
||||
"""
|
||||
return samples_dir / "remote"
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def sample_pdf_file(remote_samples_dir: Path) -> Path:
|
||||
"""Path to a simple digital PDF sample file.
|
||||
|
||||
Returns
|
||||
-------
|
||||
Path
|
||||
Absolute path to ``remote/simple-digital.pdf``.
|
||||
"""
|
||||
return remote_samples_dir / "simple-digital.pdf"
|
||||
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Remote parser instance
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@@ -277,20 +277,20 @@ class TestRemoteParserParse:
|
||||
def test_parse_returns_text_from_azure(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
sample_pdf_file: Path,
|
||||
simple_digital_pdf_file: Path,
|
||||
azure_client: Mock,
|
||||
) -> None:
|
||||
remote_parser.parse(sample_pdf_file, "application/pdf")
|
||||
remote_parser.parse(simple_digital_pdf_file, "application/pdf")
|
||||
|
||||
assert remote_parser.get_text() == _DEFAULT_TEXT
|
||||
|
||||
def test_parse_sets_archive_path(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
sample_pdf_file: Path,
|
||||
simple_digital_pdf_file: Path,
|
||||
azure_client: Mock,
|
||||
) -> None:
|
||||
remote_parser.parse(sample_pdf_file, "application/pdf")
|
||||
remote_parser.parse(simple_digital_pdf_file, "application/pdf")
|
||||
|
||||
archive = remote_parser.get_archive_path()
|
||||
assert archive is not None
|
||||
@@ -300,11 +300,11 @@ class TestRemoteParserParse:
|
||||
def test_parse_closes_client_on_success(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
sample_pdf_file: Path,
|
||||
simple_digital_pdf_file: Path,
|
||||
azure_client: Mock,
|
||||
) -> None:
|
||||
remote_parser.configure(ParserContext())
|
||||
remote_parser.parse(sample_pdf_file, "application/pdf")
|
||||
remote_parser.parse(simple_digital_pdf_file, "application/pdf")
|
||||
|
||||
azure_client.close.assert_called_once()
|
||||
|
||||
@@ -312,9 +312,9 @@ class TestRemoteParserParse:
|
||||
def test_parse_sets_empty_text_when_not_configured(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
sample_pdf_file: Path,
|
||||
simple_digital_pdf_file: Path,
|
||||
) -> None:
|
||||
remote_parser.parse(sample_pdf_file, "application/pdf")
|
||||
remote_parser.parse(simple_digital_pdf_file, "application/pdf")
|
||||
|
||||
assert remote_parser.get_text() == ""
|
||||
assert remote_parser.get_archive_path() is None
|
||||
@@ -328,10 +328,10 @@ class TestRemoteParserParse:
|
||||
def test_get_date_always_none(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
sample_pdf_file: Path,
|
||||
simple_digital_pdf_file: Path,
|
||||
azure_client: Mock,
|
||||
) -> None:
|
||||
remote_parser.parse(sample_pdf_file, "application/pdf")
|
||||
remote_parser.parse(simple_digital_pdf_file, "application/pdf")
|
||||
|
||||
assert remote_parser.get_date() is None
|
||||
|
||||
@@ -345,33 +345,33 @@ class TestRemoteParserParseError:
|
||||
def test_parse_returns_none_on_azure_error(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
sample_pdf_file: Path,
|
||||
simple_digital_pdf_file: Path,
|
||||
failing_azure_client: Mock,
|
||||
) -> None:
|
||||
remote_parser.parse(sample_pdf_file, "application/pdf")
|
||||
remote_parser.parse(simple_digital_pdf_file, "application/pdf")
|
||||
|
||||
assert remote_parser.get_text() is None
|
||||
|
||||
def test_parse_closes_client_on_error(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
sample_pdf_file: Path,
|
||||
simple_digital_pdf_file: Path,
|
||||
failing_azure_client: Mock,
|
||||
) -> None:
|
||||
remote_parser.parse(sample_pdf_file, "application/pdf")
|
||||
remote_parser.parse(simple_digital_pdf_file, "application/pdf")
|
||||
|
||||
failing_azure_client.close.assert_called_once()
|
||||
|
||||
def test_parse_logs_error_on_azure_failure(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
sample_pdf_file: Path,
|
||||
simple_digital_pdf_file: Path,
|
||||
failing_azure_client: Mock,
|
||||
mocker: MockerFixture,
|
||||
) -> None:
|
||||
mock_log = mocker.patch("paperless.parsers.remote.logger")
|
||||
|
||||
remote_parser.parse(sample_pdf_file, "application/pdf")
|
||||
remote_parser.parse(simple_digital_pdf_file, "application/pdf")
|
||||
|
||||
mock_log.error.assert_called_once()
|
||||
assert "Azure AI Vision parsing failed" in mock_log.error.call_args[0][0]
|
||||
@@ -386,18 +386,18 @@ class TestRemoteParserPageCount:
|
||||
def test_page_count_for_pdf(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
sample_pdf_file: Path,
|
||||
simple_digital_pdf_file: Path,
|
||||
) -> None:
|
||||
count = remote_parser.get_page_count(sample_pdf_file, "application/pdf")
|
||||
count = remote_parser.get_page_count(simple_digital_pdf_file, "application/pdf")
|
||||
assert isinstance(count, int)
|
||||
assert count >= 1
|
||||
|
||||
def test_page_count_returns_none_for_image_mime(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
sample_pdf_file: Path,
|
||||
simple_digital_pdf_file: Path,
|
||||
) -> None:
|
||||
count = remote_parser.get_page_count(sample_pdf_file, "image/png")
|
||||
count = remote_parser.get_page_count(simple_digital_pdf_file, "image/png")
|
||||
assert count is None
|
||||
|
||||
def test_page_count_returns_none_for_invalid_pdf(
|
||||
@@ -420,25 +420,31 @@ class TestRemoteParserMetadata:
|
||||
def test_extract_metadata_non_pdf_returns_empty(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
sample_pdf_file: Path,
|
||||
simple_digital_pdf_file: Path,
|
||||
) -> None:
|
||||
result = remote_parser.extract_metadata(sample_pdf_file, "image/png")
|
||||
result = remote_parser.extract_metadata(simple_digital_pdf_file, "image/png")
|
||||
assert result == []
|
||||
|
||||
def test_extract_metadata_pdf_returns_list(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
sample_pdf_file: Path,
|
||||
simple_digital_pdf_file: Path,
|
||||
) -> None:
|
||||
result = remote_parser.extract_metadata(sample_pdf_file, "application/pdf")
|
||||
result = remote_parser.extract_metadata(
|
||||
simple_digital_pdf_file,
|
||||
"application/pdf",
|
||||
)
|
||||
assert isinstance(result, list)
|
||||
|
||||
def test_extract_metadata_pdf_entries_have_required_keys(
|
||||
self,
|
||||
remote_parser: RemoteDocumentParser,
|
||||
sample_pdf_file: Path,
|
||||
simple_digital_pdf_file: Path,
|
||||
) -> None:
|
||||
result = remote_parser.extract_metadata(sample_pdf_file, "application/pdf")
|
||||
result = remote_parser.extract_metadata(
|
||||
simple_digital_pdf_file,
|
||||
"application/pdf",
|
||||
)
|
||||
for entry in result:
|
||||
assert "namespace" in entry
|
||||
assert "prefix" in entry
|
||||
|
||||
@@ -77,10 +77,10 @@ class TestTikaParserRegistryInterface:
|
||||
def test_get_page_count_returns_int_with_pdf_archive(
|
||||
self,
|
||||
tika_parser: TikaDocumentParser,
|
||||
sample_pdf_file: Path,
|
||||
simple_digital_pdf_file: Path,
|
||||
) -> None:
|
||||
tika_parser._archive_path = sample_pdf_file
|
||||
count = tika_parser.get_page_count(sample_pdf_file, "application/pdf")
|
||||
tika_parser._archive_path = simple_digital_pdf_file
|
||||
count = tika_parser.get_page_count(simple_digital_pdf_file, "application/pdf")
|
||||
assert isinstance(count, int)
|
||||
assert count > 0
|
||||
|
||||
|
||||
Binary file not shown.
@@ -5,6 +5,7 @@ from pathlib import Path
|
||||
from unittest import mock
|
||||
|
||||
import pytest
|
||||
from django.core.checks import ERROR
|
||||
from django.core.checks import Error
|
||||
from django.core.checks import Warning
|
||||
from pytest_django.fixtures import SettingsWrapper
|
||||
@@ -12,7 +13,9 @@ from pytest_mock import MockerFixture
|
||||
|
||||
from paperless.checks import audit_log_check
|
||||
from paperless.checks import binaries_check
|
||||
from paperless.checks import check_default_language_available
|
||||
from paperless.checks import check_deprecated_db_settings
|
||||
from paperless.checks import check_remote_parser_configured
|
||||
from paperless.checks import check_v3_minimum_upgrade_version
|
||||
from paperless.checks import debug_mode_check
|
||||
from paperless.checks import paths_check
|
||||
@@ -626,3 +629,116 @@ class TestV3MinimumUpgradeVersionCheck:
|
||||
conn.introspection.table_names.side_effect = OperationalError("DB unavailable")
|
||||
mocker.patch.dict("paperless.checks.connections", {"default": conn})
|
||||
assert check_v3_minimum_upgrade_version(None) == []
|
||||
|
||||
|
||||
class TestRemoteParserChecks:
|
||||
def test_no_engine(self, settings: SettingsWrapper) -> None:
|
||||
settings.REMOTE_OCR_ENGINE = None
|
||||
msgs = check_remote_parser_configured(None)
|
||||
|
||||
assert len(msgs) == 0
|
||||
|
||||
def test_azure_no_endpoint(self, settings: SettingsWrapper) -> None:
|
||||
|
||||
settings.REMOTE_OCR_ENGINE = "azureai"
|
||||
settings.REMOTE_OCR_API_KEY = "somekey"
|
||||
settings.REMOTE_OCR_ENDPOINT = None
|
||||
|
||||
msgs = check_remote_parser_configured(None)
|
||||
|
||||
assert len(msgs) == 1
|
||||
|
||||
msg = msgs[0]
|
||||
|
||||
assert (
|
||||
"Azure AI remote parser requires endpoint and API key to be configured."
|
||||
in msg.msg
|
||||
)
|
||||
|
||||
|
||||
class TestTesseractChecks:
|
||||
def test_default_language(self) -> None:
|
||||
check_default_language_available(None)
|
||||
|
||||
def test_no_language(self, settings: SettingsWrapper) -> None:
|
||||
|
||||
settings.OCR_LANGUAGE = ""
|
||||
|
||||
msgs = check_default_language_available(None)
|
||||
|
||||
assert len(msgs) == 1
|
||||
msg = msgs[0]
|
||||
|
||||
assert (
|
||||
"No OCR language has been specified with PAPERLESS_OCR_LANGUAGE" in msg.msg
|
||||
)
|
||||
|
||||
def test_invalid_language(
|
||||
self,
|
||||
settings: SettingsWrapper,
|
||||
mocker: MockerFixture,
|
||||
) -> None:
|
||||
|
||||
settings.OCR_LANGUAGE = "ita"
|
||||
|
||||
tesser_lang_mock = mocker.patch("paperless.checks.get_tesseract_langs")
|
||||
tesser_lang_mock.return_value = ["deu", "eng"]
|
||||
|
||||
msgs = check_default_language_available(None)
|
||||
|
||||
assert len(msgs) == 1
|
||||
msg = msgs[0]
|
||||
|
||||
assert msg.level == ERROR
|
||||
assert "The selected ocr language ita is not installed" in msg.msg
|
||||
|
||||
def test_multi_part_language(
|
||||
self,
|
||||
settings: SettingsWrapper,
|
||||
mocker: MockerFixture,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An OCR language which is multi part (ie chi-sim)
|
||||
- The language is correctly formatted
|
||||
WHEN:
|
||||
- Installed packages are checked
|
||||
THEN:
|
||||
- No errors are reported
|
||||
"""
|
||||
|
||||
settings.OCR_LANGUAGE = "chi_sim"
|
||||
|
||||
tesser_lang_mock = mocker.patch("paperless.checks.get_tesseract_langs")
|
||||
tesser_lang_mock.return_value = ["chi_sim", "eng"]
|
||||
|
||||
msgs = check_default_language_available(None)
|
||||
|
||||
assert len(msgs) == 0
|
||||
|
||||
def test_multi_part_language_bad_format(
|
||||
self,
|
||||
settings: SettingsWrapper,
|
||||
mocker: MockerFixture,
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- An OCR language which is multi part (ie chi-sim)
|
||||
- The language is correctly NOT formatted
|
||||
WHEN:
|
||||
- Installed packages are checked
|
||||
THEN:
|
||||
- No errors are reported
|
||||
"""
|
||||
settings.OCR_LANGUAGE = "chi-sim"
|
||||
|
||||
tesser_lang_mock = mocker.patch("paperless.checks.get_tesseract_langs")
|
||||
tesser_lang_mock.return_value = ["chi_sim", "eng"]
|
||||
|
||||
msgs = check_default_language_available(None)
|
||||
|
||||
assert len(msgs) == 1
|
||||
msg = msgs[0]
|
||||
|
||||
assert msg.level == ERROR
|
||||
assert "The selected ocr language chi-sim is not installed" in msg.msg
|
||||
|
||||
Reference in New Issue
Block a user