Add regex support to blacklist and whitelist filters. Strong code, many bananas! 🦍🦍🦍🦍

tests/test_blacklist.py

@@ -39,6 +39,13 @@ def test_has_black_tags() -> None:
     check_if_has_tag(reader, feed, "blacklist_title")
     check_if_has_tag(reader, feed, "blacklist_summary")
     check_if_has_tag(reader, feed, "blacklist_content")
+    check_if_has_tag(reader, feed, "blacklist_author")
+
+    # Test regex blacklist tags
+    check_if_has_tag(reader, feed, "regex_blacklist_title")
+    check_if_has_tag(reader, feed, "regex_blacklist_summary")
+    check_if_has_tag(reader, feed, "regex_blacklist_content")
+    check_if_has_tag(reader, feed, "regex_blacklist_author")
 
     # Clean up
     reader.delete_feed(feed_url)
@@ -74,6 +81,7 @@ def test_should_be_skipped() -> None:
     # Test entry without any blacklists
     assert entry_should_be_skipped(reader, first_entry[0]) is False, f"Entry should not be skipped: {first_entry[0]}"
 
+    # Test standard blacklist functionality
     reader.set_tag(feed, "blacklist_title", "fvnnnfnfdnfdnfd")  # pyright: ignore[reportArgumentType]
     assert entry_should_be_skipped(reader, first_entry[0]) is True, f"Entry should be skipped: {first_entry[0]}"
     reader.delete_tag(feed, "blacklist_title")
@@ -113,3 +121,81 @@ def test_should_be_skipped() -> None:
     assert entry_should_be_skipped(reader, first_entry[0]) is False, f"Entry should not be skipped: {first_entry[0]}"
     reader.delete_tag(feed, "blacklist_author")
     assert entry_should_be_skipped(reader, first_entry[0]) is False, f"Entry should not be skipped: {first_entry[0]}"
+
+
+def test_regex_should_be_skipped() -> None:
+    """Test the regex filtering functionality for blacklist."""
+    reader: Reader = get_reader()
+
+    # Add feed and update entries
+    reader.add_feed(feed_url)
+    feed: Feed = reader.get_feed(feed_url)
+    reader.update_feeds()
+
+    # Get first entry
+    first_entry: list[Entry] = []
+    entries: Iterable[Entry] = reader.get_entries(feed=feed)
+    assert entries is not None, f"Entries should not be None: {entries}"
+    for entry in entries:
+        first_entry.append(entry)
+        break
+    assert len(first_entry) == 1, f"First entry should be added: {first_entry}"
+
+    # Test entry without any regex blacklists
+    assert entry_should_be_skipped(reader, first_entry[0]) is False, f"Entry should not be skipped: {first_entry[0]}"
+
+    # Test regex blacklist for title
+    reader.set_tag(feed, "regex_blacklist_title", r"fvnnn\w+")  # pyright: ignore[reportArgumentType]
+    assert entry_should_be_skipped(reader, first_entry[0]) is True, (
+        f"Entry should be skipped with regex title match: {first_entry[0]}"
+    )
+    reader.delete_tag(feed, "regex_blacklist_title")
+    assert entry_should_be_skipped(reader, first_entry[0]) is False, f"Entry should not be skipped: {first_entry[0]}"
+
+    # Test regex blacklist for summary
+    reader.set_tag(feed, "regex_blacklist_summary", r"ffdnfdn\w+")  # pyright: ignore[reportArgumentType]
+    assert entry_should_be_skipped(reader, first_entry[0]) is True, (
+        f"Entry should be skipped with regex summary match: {first_entry[0]}"
+    )
+    reader.delete_tag(feed, "regex_blacklist_summary")
+    assert entry_should_be_skipped(reader, first_entry[0]) is False, f"Entry should not be skipped: {first_entry[0]}"
+
+    # Test regex blacklist for content
+    reader.set_tag(feed, "regex_blacklist_content", r"ffdnfdnfdn\w+")  # pyright: ignore[reportArgumentType]
+    assert entry_should_be_skipped(reader, first_entry[0]) is True, (
+        f"Entry should be skipped with regex content match: {first_entry[0]}"
+    )
+    reader.delete_tag(feed, "regex_blacklist_content")
+    assert entry_should_be_skipped(reader, first_entry[0]) is False, f"Entry should not be skipped: {first_entry[0]}"
+
+    # Test regex blacklist for author
+    reader.set_tag(feed, "regex_blacklist_author", r"TheLovinator\d*")  # pyright: ignore[reportArgumentType]
+    assert entry_should_be_skipped(reader, first_entry[0]) is True, (
+        f"Entry should be skipped with regex author match: {first_entry[0]}"
+    )
+    reader.delete_tag(feed, "regex_blacklist_author")
+    assert entry_should_be_skipped(reader, first_entry[0]) is False, f"Entry should not be skipped: {first_entry[0]}"
+
+    # Test invalid regex pattern (should not raise an exception)
+    reader.set_tag(feed, "regex_blacklist_title", r"[incomplete")  # pyright: ignore[reportArgumentType]
+    assert entry_should_be_skipped(reader, first_entry[0]) is False, (
+        f"Entry should not be skipped with invalid regex: {first_entry[0]}"
+    )
+    reader.delete_tag(feed, "regex_blacklist_title")
+
+    # Test multiple regex patterns separated by commas
+    reader.set_tag(feed, "regex_blacklist_author", r"pattern1,TheLovinator\d*,pattern3")  # pyright: ignore[reportArgumentType]
+    assert entry_should_be_skipped(reader, first_entry[0]) is True, (
+        f"Entry should be skipped with one matching pattern in list: {first_entry[0]}"
+    )
+    reader.delete_tag(feed, "regex_blacklist_author")
+    assert entry_should_be_skipped(reader, first_entry[0]) is False, f"Entry should not be skipped: {first_entry[0]}"
+
+    # Test newline-separated regex patterns
+    newline_patterns = "pattern1\nTheLovinator\\d*\npattern3"
+    reader.set_tag(feed, "regex_blacklist_author", newline_patterns)  # pyright: ignore[reportArgumentType]
+    assert entry_should_be_skipped(reader, first_entry[0]) is True, (
+        f"Entry should be skipped with newline-separated patterns: {first_entry[0]}"
+    )
+    reader.delete_tag(feed, "regex_blacklist_author")
+    assert entry_should_be_skipped(reader, first_entry[0]) is False, f"Entry should not be skipped: {first_entry[0]}"