From d408900a916b02c5c5d5b52a17109a0cb9072852 Mon Sep 17 00:00:00 2001 From: Trenton Holmes Date: Fri, 9 Sep 2022 11:42:43 -0700 Subject: [PATCH] Adds validation and testing to cover some of the common settings --- src/paperless/__init__.py | 3 +- src/paperless/checks.py | 49 ++++++++++++++++ src/paperless/settings.py | 2 - src/paperless/tests/test_checks.py | 92 +++++++++++++++++++++++++++++- 4 files changed, 140 insertions(+), 6 deletions(-) diff --git a/src/paperless/__init__.py b/src/paperless/__init__.py index 8cdd600b3..1c7f09cbe 100644 --- a/src/paperless/__init__.py +++ b/src/paperless/__init__.py @@ -1,4 +1,5 @@ from .checks import binaries_check from .checks import paths_check +from .checks import settings_values_check -__all__ = ["binaries_check", "paths_check"] +__all__ = ["binaries_check", "paths_check", "settings_values_check"] diff --git a/src/paperless/checks.py b/src/paperless/checks.py index 26d18b692..c9ac5cb6a 100644 --- a/src/paperless/checks.py +++ b/src/paperless/checks.py @@ -96,3 +96,52 @@ def debug_mode_check(app_configs, **kwargs): ] else: return [] + + +@register() +def settings_values_check(app_configs, **kwargs): + """ + Validates at least some of the user provided settings + """ + + def _ocrmypdf_settings_check(): + """ + Validates some of the arguments which will be provided to ocrmypdf + against the valid options. Use "ocrmypdf --help" to see the valid + inputs + """ + msgs = [] + if settings.OCR_OUTPUT_TYPE not in { + "pdfa", + "pdf", + "pdfa-1", + "pdfa-2", + "pdfa-3", + }: + msgs.append( + Error(f'OCR output type "{settings.OCR_OUTPUT_TYPE}" is not valid'), + ) + + if settings.OCR_MODE not in {"force", "skip", "redo_ocr"}: + msgs.append(Error(f'OCR output mode "{settings.OCR_MODE}" is not valid')) + + if settings.OCR_CLEAN not in {"clean", "clean_final"}: + msgs.append(Error(f'OCR clean mode "{settings.OCR_CLEAN}" is not valid')) + return msgs + + def _timezone_validate(): + """ + Validates the user provided timezone is a valid timezone + """ + try: + import zoneinfo + except ImportError: # pragma: nocover + import backports.zoneinfo as zoneinfo + msgs = [] + if settings.TIME_ZONE not in zoneinfo.available_timezones(): + msgs.append( + Error(f'Timezone "{settings.TIME_ZONE}" is not a valid timezone'), + ) + return msgs + + return _ocrmypdf_settings_check() + _timezone_validate() diff --git a/src/paperless/settings.py b/src/paperless/settings.py index 515e2a05f..92042ac31 100644 --- a/src/paperless/settings.py +++ b/src/paperless/settings.py @@ -532,11 +532,9 @@ OCR_PAGES = int(os.getenv("PAPERLESS_OCR_PAGES", 0)) OCR_LANGUAGE = os.getenv("PAPERLESS_OCR_LANGUAGE", "eng") # OCRmyPDF --output-type options are available. -# TODO: validate this setting. OCR_OUTPUT_TYPE = os.getenv("PAPERLESS_OCR_OUTPUT_TYPE", "pdfa") # skip. redo, force -# TODO: validate this. OCR_MODE = os.getenv("PAPERLESS_OCR_MODE", "skip") OCR_IMAGE_DPI = os.getenv("PAPERLESS_OCR_IMAGE_DPI") diff --git a/src/paperless/tests/test_checks.py b/src/paperless/tests/test_checks.py index ba45ebf79..b2d8b5810 100644 --- a/src/paperless/tests/test_checks.py +++ b/src/paperless/tests/test_checks.py @@ -1,12 +1,12 @@ import os -import shutil from django.test import override_settings from django.test import TestCase from documents.tests.utils import DirectoriesMixin -from paperless import binaries_check -from paperless import paths_check +from paperless.checks import binaries_check from paperless.checks import debug_mode_check +from paperless.checks import paths_check +from paperless.checks import settings_values_check class TestChecks(DirectoriesMixin, TestCase): @@ -54,3 +54,89 @@ class TestChecks(DirectoriesMixin, TestCase): @override_settings(DEBUG=True) def test_debug_enabled(self): self.assertEqual(len(debug_mode_check(None)), 1) + + +class TestSettingsChecks(DirectoriesMixin, TestCase): + def test_all_valid(self): + """ + GIVEN: + - Default settings + WHEN: + - Settings are validated + THEN: + - No system check errors reported + """ + msgs = settings_values_check(None) + self.assertEqual(len(msgs), 0) + + @override_settings(OCR_OUTPUT_TYPE="notapdf") + def test_invalid_output_type(self): + """ + GIVEN: + - Default settings + - OCR output type is invalid + WHEN: + - Settings are validated + THEN: + - system check error reported for OCR output type + """ + msgs = settings_values_check(None) + self.assertEqual(len(msgs), 1) + + msg = msgs[0] + + self.assertIn('OCR output type "notapdf"', msg.msg) + + @override_settings(OCR_MODE="makeitso") + def test_invalid_ocr_type(self): + """ + GIVEN: + - Default settings + - OCR type is invalid + WHEN: + - Settings are validated + THEN: + - system check error reported for OCR type + """ + msgs = settings_values_check(None) + self.assertEqual(len(msgs), 1) + + msg = msgs[0] + + self.assertIn('OCR output mode "makeitso"', msg.msg) + + @override_settings(OCR_CLEAN="cleanme") + def test_invalid_ocr_clean(self): + """ + GIVEN: + - Default settings + - OCR cleaning type is invalid + WHEN: + - Settings are validated + THEN: + - system check error reported for OCR cleaning type + """ + msgs = settings_values_check(None) + self.assertEqual(len(msgs), 1) + + msg = msgs[0] + + self.assertIn('OCR clean mode "cleanme"', msg.msg) + + @override_settings(TIME_ZONE="TheMoon\\MyCrater") + def test_invalid_timezone(self): + """ + GIVEN: + - Default settings + - Timezone is invalid + WHEN: + - Settings are validated + THEN: + - system check error reported for timezone + """ + msgs = settings_values_check(None) + self.assertEqual(len(msgs), 1) + + msg = msgs[0] + + self.assertIn('Timezone "TheMoon\\MyCrater"', msg.msg)