peter
ac53a3b757
A 1-2 letter prefix matched most of the library and ts_rank scored every match: "m" took ~4-8 s on prod against ~150 ms now. The prefix match starts at three characters (MIN_PREFIX_LEN); shared by the YouTube feed and the Plex library search.
75 lines
2.6 KiB
Python
75 lines
2.6 KiB
Python
"""iso(): the single date/datetime→JSON serializer the routes share (R6 S1a); to_tsquery_str()."""
|
|
|
|
from datetime import date, datetime, timezone
|
|
|
|
from app.utils import iso, normalize_description, to_tsquery_str
|
|
|
|
|
|
def test_none_maps_to_none():
|
|
assert iso(None) is None
|
|
|
|
|
|
def test_plain_date_serializes_as_iso_date():
|
|
# MediaAsset.upload_date is a `date`, not a datetime — the contract must accept it.
|
|
assert iso(date(2026, 7, 26)) == "2026-07-26"
|
|
|
|
|
|
def test_aware_datetime_keeps_offset():
|
|
dt = datetime(2026, 7, 26, 12, 30, 0, tzinfo=timezone.utc)
|
|
assert iso(dt) == "2026-07-26T12:30:00+00:00"
|
|
|
|
|
|
def test_naive_datetime_serializes_without_offset():
|
|
dt = datetime(2026, 7, 26, 12, 30, 0)
|
|
assert iso(dt) == "2026-07-26T12:30:00"
|
|
|
|
|
|
def test_matches_datetime_isoformat_contract():
|
|
# iso is exactly `dt.isoformat()` for a present value — guards the routes that used to
|
|
# hand-roll `x.isoformat() if x else None`.
|
|
dt = datetime(2020, 1, 2, 3, 4, 5, 678901, tzinfo=timezone.utc)
|
|
assert iso(dt) == dt.isoformat()
|
|
|
|
|
|
def test_normalize_description_none_stays_none():
|
|
assert normalize_description(None) is None
|
|
|
|
|
|
def test_normalize_description_drops_blank_lines():
|
|
# A YouTube contact block padded with runs of blank lines — the waste we strip before storing.
|
|
raw = "Contact us\n\n\nEmail: a@b.com\n \nInstagram: @x\n\n\n"
|
|
assert normalize_description(raw) == "Contact us\nEmail: a@b.com\nInstagram: @x"
|
|
|
|
|
|
def test_normalize_description_right_strips_and_trims():
|
|
assert normalize_description(" hi there \n\n bye ") == " hi there\n bye"
|
|
|
|
|
|
def test_normalize_description_all_blank_collapses_to_empty():
|
|
assert normalize_description("\n \n\t\n") == ""
|
|
|
|
|
|
def test_normalize_description_single_line_unchanged():
|
|
assert normalize_description("just one line") == "just one line"
|
|
|
|
|
|
def test_normalize_description_folds_crlf_line_endings():
|
|
# splitlines() folds CR/CRLF to \n — a documented, benign line-ending normalization.
|
|
assert normalize_description("a\r\nb\r\n\r\nc") == "a\nb\nc"
|
|
|
|
|
|
def test_tsquery_prefix_matches_a_last_word_of_three_or_more():
|
|
assert to_tsquery_str("ti amo magyar") == "ti & amo & magyar:*"
|
|
assert to_tsquery_str("min") == "min:*"
|
|
|
|
|
|
def test_tsquery_matches_a_short_last_word_whole():
|
|
# A 1-2 letter prefix made ts_rank score most of the library (5-8 s on prod, E31 S4e).
|
|
assert to_tsquery_str("m") == "m"
|
|
assert to_tsquery_str("minecraft 4k") == "minecraft & 4k"
|
|
assert to_tsquery_str("ti amo m") == "ti & amo & m"
|
|
|
|
|
|
def test_tsquery_without_a_word_is_none():
|
|
assert to_tsquery_str("?! --") is None
|