From edaef40ad1fec372711178ca9e7ca8e51bcf1951 Mon Sep 17 00:00:00 2001
From: benoit74 <benoit74@users.noreply.github.com>
Date: Tue, 16 Jan 2024 10:15:18 +0100
Subject: [PATCH] Refactor code and add more tests

---
 src/kolibri2zim/entrypoint.py | 10 ++++++----
 tests/conftest.py             | 31 +++++++++++++++++++++++++------
 tests/test_sanitize_inputs.py | 31 +++++++++++++++++++++++++++++++
 3 files changed, 62 insertions(+), 10 deletions(-)

diff --git a/src/kolibri2zim/entrypoint.py b/src/kolibri2zim/entrypoint.py
index 163bebe..30f0032 100755
--- a/src/kolibri2zim/entrypoint.py
+++ b/src/kolibri2zim/entrypoint.py
@@ -5,9 +5,10 @@
 import sys
 
 from kolibri2zim.constants import NAME, SCRAPER, Global, get_logger, set_debug
+from kolibri2zim.scraper import Kolibri2Zim
 
 
-def main():
+def parse_args(raw_args):
     parser = argparse.ArgumentParser(
         prog=NAME,
         description="Scraper to create ZIM files from Kolibri channels",
@@ -200,13 +201,14 @@ def main():
         action="version",
         version=SCRAPER,
     )
+    return parser.parse_args(raw_args)
+
 
-    args = parser.parse_args()
+def main():
+    args = parse_args(sys.argv[1:])
     set_debug(args.debug)
     logger = get_logger()
 
-    from kolibri2zim.scraper import Kolibri2Zim
-
     try:
         scraper = Kolibri2Zim(**dict(args._get_kwargs()))
         sys.exit(scraper.run())
diff --git a/tests/conftest.py b/tests/conftest.py
index af47abf..33eff3e 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -6,9 +6,6 @@
 from kolibri2zim.scraper import Kolibri2Zim, KolibriDB
 from kolibri2zim.scraper import options as expected_options_keys
 
-CHANNEL_NAME = "channel_name"
-CHANNEL_DESCRIPTION = "a description"
-
 
 class FakeDb(KolibriDB):
     def __init__(
@@ -30,10 +27,32 @@ def get_channel_metadata(self, _):
 
 
 @pytest.fixture()
-def scraper_generator() -> Generator[Callable[..., Kolibri2Zim], None, None]:
+def channel_name() -> Generator[str, None, None]:
+    yield "channel name"
+
+
+@pytest.fixture()
+def channel_description() -> Generator[str, None, None]:
+    yield "channel description"
+
+
+@pytest.fixture()
+def channel_author() -> Generator[str, None, None]:
+    yield "channel author"
+
+
+@pytest.fixture()
+def zim_name() -> Generator[str, None, None]:
+    yield "a_name"
+
+
+@pytest.fixture()
+def scraper_generator(
+    channel_name, channel_description
+) -> Generator[Callable[..., Kolibri2Zim], None, None]:
     def _scraper(
-        channel_name: str = CHANNEL_NAME,
-        channel_description: str = CHANNEL_DESCRIPTION,
+        channel_name: str = channel_name,
+        channel_description: str = channel_description,
         channel_author: str | None = None,
         additional_options: dict[str, Any] | None = None,
     ) -> Kolibri2Zim:
diff --git a/tests/test_sanitize_inputs.py b/tests/test_sanitize_inputs.py
index 0569c09..5f0a18b 100644
--- a/tests/test_sanitize_inputs.py
+++ b/tests/test_sanitize_inputs.py
@@ -1,13 +1,16 @@
 import random
+import re
 import string
 from collections.abc import Callable
 
 import pytest
+from conftest import FakeDb
 from zimscraperlib.constants import MAXIMUM_DESCRIPTION_METADATA_LENGTH as MAX_DESC_LEN
 from zimscraperlib.constants import (
     MAXIMUM_LONG_DESCRIPTION_METADATA_LENGTH as MAX_LONG_DESC_LEN,
 )
 
+from kolibri2zim.entrypoint import parse_args
 from kolibri2zim.scraper import Kolibri2Zim
 
 
@@ -191,3 +194,31 @@ def test_description(
 
     assert scraper.description == expected_description
     assert scraper.long_description == expected_long_description
+
+
+def test_no_required_args():
+    with pytest.raises(expected_exception=SystemExit):
+        parse_args([])
+
+
+def test_defaults_args(channel_name, channel_description, channel_author, zim_name):
+    args = parse_args(["--name", zim_name])
+    scraper = Kolibri2Zim(**dict(args._get_kwargs()))
+    scraper.db = FakeDb(
+        channel_name=channel_name,
+        channel_description=channel_description,
+        channel_author=channel_author,
+    )
+    scraper.sanitize_inputs()
+    assert scraper.language == "eng"
+    assert scraper.publisher == "openZIM"
+    assert scraper.author == channel_author
+    assert scraper.title == channel_name
+    assert scraper.description == channel_description
+    assert scraper.name == zim_name
+    assert re.match(
+        pattern=f"{zim_name}_\\d{{4}}-\\d{{2}}\\.zim", string=scraper.clean_fname
+    )
+    # We compare sets because ordering does not matter
+    assert set(scraper.tags) == {"_category:other", "kolibri", "_videos:yes"}
+    assert len(scraper.tags) == 3