mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-05-23 15:05:23 +00:00
Chore: Split test_settings.py and add regression tests for Redis URL parsing
- Migrate tests for custom parsers to test_custom_parsers.py - Add TestParseIgnoreDates and test_parse_dateparser_languages - Add regression test cases for Redis URLs with credentials (PR #12239) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Trenton H
@@ -11,13 +11,14 @@ from typing import Final
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from compression_middleware.middleware import CompressionMiddleware
|
||||
from dateparser.languages.loader import LocaleDataLoader
|
||||
from django.utils.translation import gettext_lazy as _
|
||||
from dotenv import load_dotenv
|
||||
|
||||
from paperless.settings.custom import parse_beat_schedule
|
||||
from paperless.settings.custom import parse_dateparser_languages
|
||||
from paperless.settings.custom import parse_db_settings
|
||||
from paperless.settings.custom import parse_hosting_settings
|
||||
from paperless.settings.custom import parse_ignore_dates
|
||||
from paperless.settings.custom import parse_redis_url
|
||||
from paperless.settings.parsers import get_bool_from_env
|
||||
from paperless.settings.parsers import get_float_from_env
|
||||
@@ -934,23 +935,9 @@ DATE_ORDER = os.getenv("PAPERLESS_DATE_ORDER", "DMY")
|
||||
FILENAME_DATE_ORDER = os.getenv("PAPERLESS_FILENAME_DATE_ORDER")
|
||||
|
||||
|
||||
def _parse_dateparser_languages(languages: str | None):
|
||||
language_list = languages.split("+") if languages else []
|
||||
# There is an unfixed issue in zh-Hant and zh-Hans locales in the dateparser lib.
|
||||
# See: https://github.com/scrapinghub/dateparser/issues/875
|
||||
for index, language in enumerate(language_list):
|
||||
if language.startswith("zh-") and "zh" not in language_list:
|
||||
logger.warning(
|
||||
f'Chinese locale detected: {language}. dateparser might fail to parse some dates with this locale, so Chinese ("zh") will be used as a fallback.',
|
||||
)
|
||||
language_list.append("zh")
|
||||
|
||||
return list(LocaleDataLoader().get_locale_map(locales=language_list))
|
||||
|
||||
|
||||
# If not set, we will infer it at runtime
|
||||
DATE_PARSER_LANGUAGES = (
|
||||
_parse_dateparser_languages(
|
||||
parse_dateparser_languages(
|
||||
os.getenv("PAPERLESS_DATE_PARSER_LANGUAGES"),
|
||||
)
|
||||
if os.getenv("PAPERLESS_DATE_PARSER_LANGUAGES")
|
||||
@@ -996,42 +983,11 @@ if AUDIT_LOG_ENABLED:
|
||||
MIDDLEWARE.append("auditlog.middleware.AuditlogMiddleware")
|
||||
|
||||
|
||||
def _parse_ignore_dates(
|
||||
env_ignore: str,
|
||||
date_order: str = DATE_ORDER,
|
||||
) -> set[datetime.datetime]:
|
||||
"""
|
||||
If the PAPERLESS_IGNORE_DATES environment variable is set, parse the
|
||||
user provided string(s) into dates
|
||||
|
||||
Args:
|
||||
env_ignore (str): The value of the environment variable, comma separated dates
|
||||
date_order (str, optional): The format of the date strings.
|
||||
Defaults to DATE_ORDER.
|
||||
|
||||
Returns:
|
||||
Set[datetime.datetime]: The set of parsed date objects
|
||||
"""
|
||||
import dateparser
|
||||
|
||||
ignored_dates = set()
|
||||
for s in env_ignore.split(","):
|
||||
d = dateparser.parse(
|
||||
s,
|
||||
settings={
|
||||
"DATE_ORDER": date_order,
|
||||
},
|
||||
)
|
||||
if d:
|
||||
ignored_dates.add(d.date())
|
||||
return ignored_dates
|
||||
|
||||
|
||||
# List dates that should be ignored when trying to parse date from document text
|
||||
IGNORE_DATES: set[datetime.date] = set()
|
||||
|
||||
if os.getenv("PAPERLESS_IGNORE_DATES") is not None:
|
||||
IGNORE_DATES = _parse_ignore_dates(os.getenv("PAPERLESS_IGNORE_DATES"))
|
||||
IGNORE_DATES = parse_ignore_dates(os.getenv("PAPERLESS_IGNORE_DATES"), DATE_ORDER)
|
||||
|
||||
ENABLE_UPDATE_CHECK = os.getenv("PAPERLESS_ENABLE_UPDATE_CHECK", "default")
|
||||
if ENABLE_UPDATE_CHECK != "default":
|
||||
|
||||
@@ -1,13 +1,18 @@
|
||||
import datetime
|
||||
import logging
|
||||
import os
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from celery.schedules import crontab
|
||||
from dateparser.languages.loader import LocaleDataLoader
|
||||
|
||||
from paperless.settings.parsers import get_choice_from_env
|
||||
from paperless.settings.parsers import get_int_from_env
|
||||
from paperless.settings.parsers import parse_dict_from_str
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
def parse_hosting_settings() -> tuple[str | None, str, str, str, str]:
|
||||
script_name = os.getenv("PAPERLESS_FORCE_SCRIPT_NAME")
|
||||
@@ -295,3 +300,48 @@ def parse_db_settings(data_dir: Path) -> dict[str, dict[str, Any]]:
|
||||
)
|
||||
|
||||
return {"default": db_config}
|
||||
|
||||
|
||||
def parse_dateparser_languages(languages: str | None) -> list[str]:
|
||||
language_list = languages.split("+") if languages else []
|
||||
# There is an unfixed issue in zh-Hant and zh-Hans locales in the dateparser lib.
|
||||
# See: https://github.com/scrapinghub/dateparser/issues/875
|
||||
for index, language in enumerate(language_list):
|
||||
if language.startswith("zh-") and "zh" not in language_list:
|
||||
logger.warning(
|
||||
f"Chinese locale detected: {language}. dateparser might fail to parse"
|
||||
f' some dates with this locale, so Chinese ("zh") will be used as a fallback.',
|
||||
)
|
||||
language_list.append("zh")
|
||||
|
||||
return list(LocaleDataLoader().get_locale_map(locales=language_list))
|
||||
|
||||
|
||||
def parse_ignore_dates(
|
||||
env_ignore: str,
|
||||
date_order: str,
|
||||
) -> set[datetime.date]:
|
||||
"""
|
||||
If the PAPERLESS_IGNORE_DATES environment variable is set, parse the
|
||||
user provided string(s) into dates
|
||||
|
||||
Args:
|
||||
env_ignore (str): The value of the environment variable, comma separated dates
|
||||
date_order (str): The format of the date strings.
|
||||
|
||||
Returns:
|
||||
set[datetime.date]: The set of parsed date objects
|
||||
"""
|
||||
import dateparser
|
||||
|
||||
ignored_dates = set()
|
||||
for s in env_ignore.split(","):
|
||||
d = dateparser.parse(
|
||||
s,
|
||||
settings={
|
||||
"DATE_ORDER": date_order,
|
||||
},
|
||||
)
|
||||
if d:
|
||||
ignored_dates.add(d.date())
|
||||
return ignored_dates
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import datetime
|
||||
import os
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
@@ -7,8 +8,10 @@ from celery.schedules import crontab
|
||||
from pytest_mock import MockerFixture
|
||||
|
||||
from paperless.settings.custom import parse_beat_schedule
|
||||
from paperless.settings.custom import parse_dateparser_languages
|
||||
from paperless.settings.custom import parse_db_settings
|
||||
from paperless.settings.custom import parse_hosting_settings
|
||||
from paperless.settings.custom import parse_ignore_dates
|
||||
from paperless.settings.custom import parse_redis_url
|
||||
|
||||
|
||||
@@ -58,6 +61,24 @@ class TestRedisSocketConversion:
|
||||
("redis://myredishost:6379", "redis://myredishost:6379"),
|
||||
id="host_with_port_unchanged",
|
||||
),
|
||||
# Credentials in unix:// URL contain multiple colons (user:password@)
|
||||
# Regression test for https://github.com/paperless-ngx/paperless-ngx/pull/12239
|
||||
pytest.param(
|
||||
"unix://user:password@/run/redis/redis.sock",
|
||||
(
|
||||
"redis+socket://user:password@/run/redis/redis.sock",
|
||||
"unix://user:password@/run/redis/redis.sock",
|
||||
),
|
||||
id="redis_py_style_socket_with_credentials",
|
||||
),
|
||||
pytest.param(
|
||||
"redis+socket://user:password@/run/redis/redis.sock",
|
||||
(
|
||||
"redis+socket://user:password@/run/redis/redis.sock",
|
||||
"unix://user:password@/run/redis/redis.sock",
|
||||
),
|
||||
id="celery_style_socket_with_credentials",
|
||||
),
|
||||
],
|
||||
)
|
||||
def test_redis_socket_parsing(
|
||||
@@ -512,3 +533,85 @@ class TestParseDbSettings:
|
||||
settings = parse_db_settings(tmp_path)
|
||||
|
||||
assert settings == expected_database_settings
|
||||
|
||||
|
||||
class TestParseIgnoreDates:
|
||||
"""Tests the parsing of the PAPERLESS_IGNORE_DATES setting value."""
|
||||
|
||||
def test_no_ignore_dates_set(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- No ignore dates are set
|
||||
THEN:
|
||||
- No ignore dates are parsed
|
||||
"""
|
||||
assert parse_ignore_dates("", "YMD") == set()
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
("env_str", "date_format", "expected"),
|
||||
[
|
||||
pytest.param(
|
||||
"1985-05-01",
|
||||
"YMD",
|
||||
{datetime.date(1985, 5, 1)},
|
||||
id="single-ymd",
|
||||
),
|
||||
pytest.param(
|
||||
"1985-05-01,1991-12-05",
|
||||
"YMD",
|
||||
{datetime.date(1985, 5, 1), datetime.date(1991, 12, 5)},
|
||||
id="multiple-ymd",
|
||||
),
|
||||
pytest.param(
|
||||
"2010-12-13",
|
||||
"YMD",
|
||||
{datetime.date(2010, 12, 13)},
|
||||
id="single-ymd-2",
|
||||
),
|
||||
pytest.param(
|
||||
"11.01.10",
|
||||
"DMY",
|
||||
{datetime.date(2010, 1, 11)},
|
||||
id="single-dmy",
|
||||
),
|
||||
pytest.param(
|
||||
"11.01.2001,15-06-1996",
|
||||
"DMY",
|
||||
{datetime.date(2001, 1, 11), datetime.date(1996, 6, 15)},
|
||||
id="multiple-dmy",
|
||||
),
|
||||
],
|
||||
)
|
||||
def test_ignore_dates_parsed(
|
||||
self,
|
||||
env_str: str,
|
||||
date_format: str,
|
||||
expected: set[datetime.date],
|
||||
) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- Ignore dates are set per certain inputs
|
||||
THEN:
|
||||
- All ignore dates are parsed
|
||||
"""
|
||||
assert parse_ignore_dates(env_str, date_format) == expected
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
("languages", "expected"),
|
||||
[
|
||||
("de", ["de"]),
|
||||
("zh", ["zh"]),
|
||||
("fr+en", ["fr", "en"]),
|
||||
# Locales must be supported
|
||||
("en-001+fr-CA", ["en-001", "fr-CA"]),
|
||||
("en-001+fr", ["en-001", "fr"]),
|
||||
# Special case for Chinese: variants seem to miss some dates,
|
||||
# so we always add "zh" as a fallback.
|
||||
("en+zh-Hans-HK", ["en", "zh-Hans-HK", "zh"]),
|
||||
("en+zh-Hans", ["en", "zh-Hans", "zh"]),
|
||||
("en+zh-Hans+zh-Hant", ["en", "zh-Hans", "zh-Hant", "zh"]),
|
||||
],
|
||||
)
|
||||
def test_parse_dateparser_languages(languages: str, expected: list[str]) -> None:
|
||||
assert sorted(parse_dateparser_languages(languages)) == sorted(expected)
|
||||
|
||||
@@ -1,73 +1,11 @@
|
||||
import datetime
|
||||
import os
|
||||
from unittest import TestCase
|
||||
from unittest import mock
|
||||
|
||||
import pytest
|
||||
from celery.schedules import crontab
|
||||
|
||||
from paperless.settings import _parse_base_paths
|
||||
from paperless.settings import _parse_beat_schedule
|
||||
from paperless.settings import _parse_dateparser_languages
|
||||
from paperless.settings import _parse_ignore_dates
|
||||
from paperless.settings import _parse_paperless_url
|
||||
from paperless.settings import _parse_redis_url
|
||||
from paperless.settings import default_threads_per_worker
|
||||
|
||||
|
||||
class TestIgnoreDateParsing(TestCase):
|
||||
"""
|
||||
Tests the parsing of the PAPERLESS_IGNORE_DATES setting value
|
||||
"""
|
||||
|
||||
def _parse_checker(self, test_cases) -> None:
|
||||
"""
|
||||
Helper function to check ignore date parsing
|
||||
|
||||
Args:
|
||||
test_cases (_type_): _description_
|
||||
"""
|
||||
for env_str, date_format, expected_date_set in test_cases:
|
||||
self.assertSetEqual(
|
||||
_parse_ignore_dates(env_str, date_format),
|
||||
expected_date_set,
|
||||
)
|
||||
|
||||
def test_no_ignore_dates_set(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- No ignore dates are set
|
||||
THEN:
|
||||
- No ignore dates are parsed
|
||||
"""
|
||||
self.assertSetEqual(_parse_ignore_dates(""), set())
|
||||
|
||||
def test_single_ignore_dates_set(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- Ignore dates are set per certain inputs
|
||||
THEN:
|
||||
- All ignore dates are parsed
|
||||
"""
|
||||
test_cases = [
|
||||
("1985-05-01", "YMD", {datetime.date(1985, 5, 1)}),
|
||||
(
|
||||
"1985-05-01,1991-12-05",
|
||||
"YMD",
|
||||
{datetime.date(1985, 5, 1), datetime.date(1991, 12, 5)},
|
||||
),
|
||||
("2010-12-13", "YMD", {datetime.date(2010, 12, 13)}),
|
||||
("11.01.10", "DMY", {datetime.date(2010, 1, 11)}),
|
||||
(
|
||||
"11.01.2001,15-06-1996",
|
||||
"DMY",
|
||||
{datetime.date(2001, 1, 11), datetime.date(1996, 6, 15)},
|
||||
),
|
||||
]
|
||||
|
||||
self._parse_checker(test_cases)
|
||||
|
||||
|
||||
class TestThreadCalculation(TestCase):
|
||||
def test_workers_threads(self) -> None:
|
||||
"""
|
||||
@@ -94,289 +32,6 @@ class TestThreadCalculation(TestCase):
|
||||
self.assertLessEqual(default_workers * default_threads, i)
|
||||
|
||||
|
||||
class TestRedisSocketConversion(TestCase):
|
||||
def test_redis_socket_parsing(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- Various Redis connection URI formats
|
||||
WHEN:
|
||||
- The URI is parsed
|
||||
THEN:
|
||||
- Socket based URIs are translated
|
||||
- Non-socket URIs are unchanged
|
||||
- None provided uses default
|
||||
"""
|
||||
|
||||
for input, expected in [
|
||||
# Nothing is set
|
||||
(None, ("redis://localhost:6379", "redis://localhost:6379")),
|
||||
# celery style
|
||||
(
|
||||
"redis+socket:///run/redis/redis.sock",
|
||||
(
|
||||
"redis+socket:///run/redis/redis.sock",
|
||||
"unix:///run/redis/redis.sock",
|
||||
),
|
||||
),
|
||||
# redis-py / channels-redis style
|
||||
(
|
||||
"unix:///run/redis/redis.sock",
|
||||
(
|
||||
"redis+socket:///run/redis/redis.sock",
|
||||
"unix:///run/redis/redis.sock",
|
||||
),
|
||||
),
|
||||
# celery style with db
|
||||
(
|
||||
"redis+socket:///run/redis/redis.sock?virtual_host=5",
|
||||
(
|
||||
"redis+socket:///run/redis/redis.sock?virtual_host=5",
|
||||
"unix:///run/redis/redis.sock?db=5",
|
||||
),
|
||||
),
|
||||
# redis-py / channels-redis style with db
|
||||
(
|
||||
"unix:///run/redis/redis.sock?db=10",
|
||||
(
|
||||
"redis+socket:///run/redis/redis.sock?virtual_host=10",
|
||||
"unix:///run/redis/redis.sock?db=10",
|
||||
),
|
||||
),
|
||||
# Just a host with a port
|
||||
(
|
||||
"redis://myredishost:6379",
|
||||
("redis://myredishost:6379", "redis://myredishost:6379"),
|
||||
),
|
||||
]:
|
||||
result = _parse_redis_url(input)
|
||||
self.assertTupleEqual(expected, result)
|
||||
|
||||
|
||||
class TestCeleryScheduleParsing(TestCase):
|
||||
MAIL_EXPIRE_TIME = 9.0 * 60.0
|
||||
CLASSIFIER_EXPIRE_TIME = 59.0 * 60.0
|
||||
INDEX_EXPIRE_TIME = 23.0 * 60.0 * 60.0
|
||||
SANITY_EXPIRE_TIME = ((7.0 * 24.0) - 1.0) * 60.0 * 60.0
|
||||
EMPTY_TRASH_EXPIRE_TIME = 23.0 * 60.0 * 60.0
|
||||
RUN_SCHEDULED_WORKFLOWS_EXPIRE_TIME = 59.0 * 60.0
|
||||
LLM_INDEX_EXPIRE_TIME = 23.0 * 60.0 * 60.0
|
||||
CLEANUP_EXPIRED_SHARE_BUNDLES_EXPIRE_TIME = 23.0 * 60.0 * 60.0
|
||||
|
||||
def test_schedule_configuration_default(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- No configured task schedules
|
||||
WHEN:
|
||||
- The celery beat schedule is built
|
||||
THEN:
|
||||
- The default schedule is returned
|
||||
"""
|
||||
schedule = _parse_beat_schedule()
|
||||
|
||||
self.assertDictEqual(
|
||||
{
|
||||
"Check all e-mail accounts": {
|
||||
"task": "paperless_mail.tasks.process_mail_accounts",
|
||||
"schedule": crontab(minute="*/10"),
|
||||
"options": {"expires": self.MAIL_EXPIRE_TIME},
|
||||
},
|
||||
"Train the classifier": {
|
||||
"task": "documents.tasks.train_classifier",
|
||||
"schedule": crontab(minute="5", hour="*/1"),
|
||||
"options": {"expires": self.CLASSIFIER_EXPIRE_TIME},
|
||||
},
|
||||
"Optimize the index": {
|
||||
"task": "documents.tasks.index_optimize",
|
||||
"schedule": crontab(minute=0, hour=0),
|
||||
"options": {"expires": self.INDEX_EXPIRE_TIME},
|
||||
},
|
||||
"Perform sanity check": {
|
||||
"task": "documents.tasks.sanity_check",
|
||||
"schedule": crontab(minute=30, hour=0, day_of_week="sun"),
|
||||
"options": {"expires": self.SANITY_EXPIRE_TIME},
|
||||
},
|
||||
"Empty trash": {
|
||||
"task": "documents.tasks.empty_trash",
|
||||
"schedule": crontab(minute=0, hour="1"),
|
||||
"options": {"expires": self.EMPTY_TRASH_EXPIRE_TIME},
|
||||
},
|
||||
"Check and run scheduled workflows": {
|
||||
"task": "documents.tasks.check_scheduled_workflows",
|
||||
"schedule": crontab(minute="5", hour="*/1"),
|
||||
"options": {"expires": self.RUN_SCHEDULED_WORKFLOWS_EXPIRE_TIME},
|
||||
},
|
||||
"Rebuild LLM index": {
|
||||
"task": "documents.tasks.llmindex_index",
|
||||
"schedule": crontab(minute=10, hour=2),
|
||||
"options": {
|
||||
"expires": self.LLM_INDEX_EXPIRE_TIME,
|
||||
},
|
||||
},
|
||||
"Cleanup expired share link bundles": {
|
||||
"task": "documents.tasks.cleanup_expired_share_link_bundles",
|
||||
"schedule": crontab(minute=0, hour=2),
|
||||
"options": {
|
||||
"expires": self.CLEANUP_EXPIRED_SHARE_BUNDLES_EXPIRE_TIME,
|
||||
},
|
||||
},
|
||||
},
|
||||
schedule,
|
||||
)
|
||||
|
||||
def test_schedule_configuration_changed(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- Email task is configured non-default
|
||||
WHEN:
|
||||
- The celery beat schedule is built
|
||||
THEN:
|
||||
- The email task is configured per environment
|
||||
- The default schedule is returned for other tasks
|
||||
"""
|
||||
with mock.patch.dict(
|
||||
os.environ,
|
||||
{"PAPERLESS_EMAIL_TASK_CRON": "*/50 * * * mon"},
|
||||
):
|
||||
schedule = _parse_beat_schedule()
|
||||
|
||||
self.assertDictEqual(
|
||||
{
|
||||
"Check all e-mail accounts": {
|
||||
"task": "paperless_mail.tasks.process_mail_accounts",
|
||||
"schedule": crontab(minute="*/50", day_of_week="mon"),
|
||||
"options": {"expires": self.MAIL_EXPIRE_TIME},
|
||||
},
|
||||
"Train the classifier": {
|
||||
"task": "documents.tasks.train_classifier",
|
||||
"schedule": crontab(minute="5", hour="*/1"),
|
||||
"options": {"expires": self.CLASSIFIER_EXPIRE_TIME},
|
||||
},
|
||||
"Optimize the index": {
|
||||
"task": "documents.tasks.index_optimize",
|
||||
"schedule": crontab(minute=0, hour=0),
|
||||
"options": {"expires": self.INDEX_EXPIRE_TIME},
|
||||
},
|
||||
"Perform sanity check": {
|
||||
"task": "documents.tasks.sanity_check",
|
||||
"schedule": crontab(minute=30, hour=0, day_of_week="sun"),
|
||||
"options": {"expires": self.SANITY_EXPIRE_TIME},
|
||||
},
|
||||
"Empty trash": {
|
||||
"task": "documents.tasks.empty_trash",
|
||||
"schedule": crontab(minute=0, hour="1"),
|
||||
"options": {"expires": self.EMPTY_TRASH_EXPIRE_TIME},
|
||||
},
|
||||
"Check and run scheduled workflows": {
|
||||
"task": "documents.tasks.check_scheduled_workflows",
|
||||
"schedule": crontab(minute="5", hour="*/1"),
|
||||
"options": {"expires": self.RUN_SCHEDULED_WORKFLOWS_EXPIRE_TIME},
|
||||
},
|
||||
"Rebuild LLM index": {
|
||||
"task": "documents.tasks.llmindex_index",
|
||||
"schedule": crontab(minute=10, hour=2),
|
||||
"options": {
|
||||
"expires": self.LLM_INDEX_EXPIRE_TIME,
|
||||
},
|
||||
},
|
||||
"Cleanup expired share link bundles": {
|
||||
"task": "documents.tasks.cleanup_expired_share_link_bundles",
|
||||
"schedule": crontab(minute=0, hour=2),
|
||||
"options": {
|
||||
"expires": self.CLEANUP_EXPIRED_SHARE_BUNDLES_EXPIRE_TIME,
|
||||
},
|
||||
},
|
||||
},
|
||||
schedule,
|
||||
)
|
||||
|
||||
def test_schedule_configuration_disabled(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- Search index task is disabled
|
||||
WHEN:
|
||||
- The celery beat schedule is built
|
||||
THEN:
|
||||
- The search index task is not present
|
||||
- The default schedule is returned for other tasks
|
||||
"""
|
||||
with mock.patch.dict(os.environ, {"PAPERLESS_INDEX_TASK_CRON": "disable"}):
|
||||
schedule = _parse_beat_schedule()
|
||||
|
||||
self.assertDictEqual(
|
||||
{
|
||||
"Check all e-mail accounts": {
|
||||
"task": "paperless_mail.tasks.process_mail_accounts",
|
||||
"schedule": crontab(minute="*/10"),
|
||||
"options": {"expires": self.MAIL_EXPIRE_TIME},
|
||||
},
|
||||
"Train the classifier": {
|
||||
"task": "documents.tasks.train_classifier",
|
||||
"schedule": crontab(minute="5", hour="*/1"),
|
||||
"options": {"expires": self.CLASSIFIER_EXPIRE_TIME},
|
||||
},
|
||||
"Perform sanity check": {
|
||||
"task": "documents.tasks.sanity_check",
|
||||
"schedule": crontab(minute=30, hour=0, day_of_week="sun"),
|
||||
"options": {"expires": self.SANITY_EXPIRE_TIME},
|
||||
},
|
||||
"Empty trash": {
|
||||
"task": "documents.tasks.empty_trash",
|
||||
"schedule": crontab(minute=0, hour="1"),
|
||||
"options": {"expires": self.EMPTY_TRASH_EXPIRE_TIME},
|
||||
},
|
||||
"Check and run scheduled workflows": {
|
||||
"task": "documents.tasks.check_scheduled_workflows",
|
||||
"schedule": crontab(minute="5", hour="*/1"),
|
||||
"options": {"expires": self.RUN_SCHEDULED_WORKFLOWS_EXPIRE_TIME},
|
||||
},
|
||||
"Rebuild LLM index": {
|
||||
"task": "documents.tasks.llmindex_index",
|
||||
"schedule": crontab(minute=10, hour=2),
|
||||
"options": {
|
||||
"expires": self.LLM_INDEX_EXPIRE_TIME,
|
||||
},
|
||||
},
|
||||
"Cleanup expired share link bundles": {
|
||||
"task": "documents.tasks.cleanup_expired_share_link_bundles",
|
||||
"schedule": crontab(minute=0, hour=2),
|
||||
"options": {
|
||||
"expires": self.CLEANUP_EXPIRED_SHARE_BUNDLES_EXPIRE_TIME,
|
||||
},
|
||||
},
|
||||
},
|
||||
schedule,
|
||||
)
|
||||
|
||||
def test_schedule_configuration_disabled_all(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- All tasks are disabled
|
||||
WHEN:
|
||||
- The celery beat schedule is built
|
||||
THEN:
|
||||
- No tasks are scheduled
|
||||
"""
|
||||
with mock.patch.dict(
|
||||
os.environ,
|
||||
{
|
||||
"PAPERLESS_EMAIL_TASK_CRON": "disable",
|
||||
"PAPERLESS_TRAIN_TASK_CRON": "disable",
|
||||
"PAPERLESS_SANITY_TASK_CRON": "disable",
|
||||
"PAPERLESS_INDEX_TASK_CRON": "disable",
|
||||
"PAPERLESS_EMPTY_TRASH_TASK_CRON": "disable",
|
||||
"PAPERLESS_WORKFLOW_SCHEDULED_TASK_CRON": "disable",
|
||||
"PAPERLESS_LLM_INDEX_TASK_CRON": "disable",
|
||||
"PAPERLESS_SHARE_LINK_BUNDLE_CLEANUP_CRON": "disable",
|
||||
},
|
||||
):
|
||||
schedule = _parse_beat_schedule()
|
||||
|
||||
self.assertDictEqual(
|
||||
{},
|
||||
schedule,
|
||||
)
|
||||
|
||||
|
||||
class TestPaperlessURLSettings(TestCase):
|
||||
def test_paperless_url(self) -> None:
|
||||
"""
|
||||
@@ -399,84 +54,3 @@ class TestPaperlessURLSettings(TestCase):
|
||||
|
||||
self.assertIn(url, settings.CSRF_TRUSTED_ORIGINS)
|
||||
self.assertIn(url, settings.CORS_ALLOWED_ORIGINS)
|
||||
|
||||
|
||||
class TestPathSettings(TestCase):
|
||||
def test_default_paths(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- PAPERLESS_FORCE_SCRIPT_NAME is not set
|
||||
WHEN:
|
||||
- Settings are parsed
|
||||
THEN:
|
||||
- Paths are as expected
|
||||
"""
|
||||
base_paths = _parse_base_paths()
|
||||
self.assertEqual(None, base_paths[0]) # FORCE_SCRIPT_NAME
|
||||
self.assertEqual("/", base_paths[1]) # BASE_URL
|
||||
self.assertEqual("/accounts/login/", base_paths[2]) # LOGIN_URL
|
||||
self.assertEqual("/dashboard", base_paths[3]) # LOGIN_REDIRECT_URL
|
||||
self.assertEqual(
|
||||
"/accounts/login/?loggedout=1",
|
||||
base_paths[4],
|
||||
) # LOGOUT_REDIRECT_URL
|
||||
|
||||
@mock.patch("os.environ", {"PAPERLESS_FORCE_SCRIPT_NAME": "/paperless"})
|
||||
def test_subpath(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- PAPERLESS_FORCE_SCRIPT_NAME is set
|
||||
WHEN:
|
||||
- Settings are parsed
|
||||
THEN:
|
||||
- The path is returned and present in related settings
|
||||
"""
|
||||
base_paths = _parse_base_paths()
|
||||
self.assertEqual("/paperless", base_paths[0]) # FORCE_SCRIPT_NAME
|
||||
self.assertEqual("/paperless/", base_paths[1]) # BASE_URL
|
||||
self.assertEqual("/paperless/accounts/login/", base_paths[2]) # LOGIN_URL
|
||||
self.assertEqual("/paperless/dashboard", base_paths[3]) # LOGIN_REDIRECT_URL
|
||||
self.assertEqual(
|
||||
"/paperless/accounts/login/?loggedout=1",
|
||||
base_paths[4],
|
||||
) # LOGOUT_REDIRECT_URL
|
||||
|
||||
@mock.patch(
|
||||
"os.environ",
|
||||
{
|
||||
"PAPERLESS_FORCE_SCRIPT_NAME": "/paperless",
|
||||
"PAPERLESS_LOGOUT_REDIRECT_URL": "/foobar/",
|
||||
},
|
||||
)
|
||||
def test_subpath_with_explicit_logout_url(self) -> None:
|
||||
"""
|
||||
GIVEN:
|
||||
- PAPERLESS_FORCE_SCRIPT_NAME is set and so is PAPERLESS_LOGOUT_REDIRECT_URL
|
||||
WHEN:
|
||||
- Settings are parsed
|
||||
THEN:
|
||||
- The correct logout redirect URL is returned
|
||||
"""
|
||||
base_paths = _parse_base_paths()
|
||||
self.assertEqual("/paperless/", base_paths[1]) # BASE_URL
|
||||
self.assertEqual("/foobar/", base_paths[4]) # LOGOUT_REDIRECT_URL
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
("languages", "expected"),
|
||||
[
|
||||
("de", ["de"]),
|
||||
("zh", ["zh"]),
|
||||
("fr+en", ["fr", "en"]),
|
||||
# Locales must be supported
|
||||
("en-001+fr-CA", ["en-001", "fr-CA"]),
|
||||
("en-001+fr", ["en-001", "fr"]),
|
||||
# Special case for Chinese: variants seem to miss some dates,
|
||||
# so we always add "zh" as a fallback.
|
||||
("en+zh-Hans-HK", ["en", "zh-Hans-HK", "zh"]),
|
||||
("en+zh-Hans", ["en", "zh-Hans", "zh"]),
|
||||
("en+zh-Hans+zh-Hant", ["en", "zh-Hans", "zh-Hant", "zh"]),
|
||||
],
|
||||
)
|
||||
def test_parser_date_parser_languages(languages, expected) -> None:
|
||||
assert sorted(_parse_dateparser_languages(languages)) == sorted(expected)
|
||||
|
||||
Reference in New Issue
Block a user