diff options
Diffstat (limited to 'packages')
| -rw-r--r-- | packages/meshbay-node/src/meshbay_node/indexer/title_parse.py | 9 | ||||
| -rw-r--r-- | packages/meshbay-node/tests/test_title_parse.py | 18 |
2 files changed, 27 insertions, 0 deletions
diff --git a/packages/meshbay-node/src/meshbay_node/indexer/title_parse.py b/packages/meshbay-node/src/meshbay_node/indexer/title_parse.py index 985bd7a..24b423e 100644 --- a/packages/meshbay-node/src/meshbay_node/indexer/title_parse.py +++ b/packages/meshbay-node/src/meshbay_node/indexer/title_parse.py @@ -45,6 +45,12 @@ _SEASON_RE = re.compile( re.IGNORECASE, ) _SPECIALS_RE = re.compile(r"\b(?:bonus|extras?|specials?)\b", re.IGNORECASE) +# A bare "S" + number as the *whole* folder name — "S1", "S2", "S02" — a +# common abbreviated convention distinct from SEASON_WORDS' full words. +# Anchored to the entire name, not just `\b`-bounded within a longer +# string, so it only matches a folder actually named just that — never +# some other word that merely starts with "s" followed by digits. +_SEASON_ABBREV_RE = re.compile(r"^s(\d{1,2})$", re.IGNORECASE) _ROMAN_NUMERALS = { 2: "II", 3: "III", 4: "IV", 5: "V", 6: "VI", @@ -110,6 +116,9 @@ def season_from_folder_name(name: str) -> int | None: """ if _SPECIALS_RE.search(name): return 0 + m = _SEASON_ABBREV_RE.match(name.strip()) + if m: + return int(m.group(1)) m = _SEASON_RE.search(name) if not m: return None diff --git a/packages/meshbay-node/tests/test_title_parse.py b/packages/meshbay-node/tests/test_title_parse.py index cf51646..5f0977c 100644 --- a/packages/meshbay-node/tests/test_title_parse.py +++ b/packages/meshbay-node/tests/test_title_parse.py @@ -119,6 +119,24 @@ def test_season_folder_book_word_roman_numeral(): assert season_from_folder_name("Livre VI") == 6 +def test_season_folder_bare_s_abbreviation(): + # A common abbreviated convention distinct from SEASON_WORDS' full + # words — found live: a show with "S1"/"S2"/"S3" folders instead of + # "Season 1" etc, exactly the shape that grouped its later seasons as + # loose individual entries rather than under the show. + assert season_from_folder_name("S1") == 1 + assert season_from_folder_name("S2") == 2 + assert season_from_folder_name("S02") == 2 + + +def test_season_folder_bare_s_abbreviation_does_not_match_inside_a_longer_name(): + # Anchored to the whole folder name — a real folder that merely starts + # with "S" followed by digits somewhere in a longer, unrelated name + # must not be read as a season abbreviation. + assert season_from_folder_name("S1 Extended Cut") is None + assert season_from_folder_name("Something2") is None + + def test_specials_folder_maps_to_season_zero(): assert season_from_folder_name("Specials") == 0 assert season_from_folder_name("Bonus") == 0 |