peter
ddb7818d38
YouTube channel descriptions pad their contact/link blocks with runs of blank lines, which the About popover renders verbatim (whitespace-pre-wrap) — wasted space and storage, and noise in the search_vector. Add normalize_description() and apply it at both channel store sites (full details + initial import) so the DB holds the clean text. New channels are clean immediately; existing rows heal on their next metadata re-sync. Unit-tested in test_utils.
53 lines
1.8 KiB
Python
53 lines
1.8 KiB
Python
"""iso(): the single date/datetime→JSON serializer the routes share (R6 S1a)."""
|
|
from datetime import date, datetime, timezone
|
|
|
|
from app.utils import iso, normalize_description
|
|
|
|
|
|
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"
|