fix(shipwrecks): skip every wrecksite.eu row, even when the name comes after the 80-character cut or only in the link

The exclusion tested the provenance after it was cut to 80 characters, so a
long source list ending in wrecksite.eu kept the row, and a row whose only
trace was a wrecksite.eu page link was kept too. Both raw values are now
checked before anything is cut.
This commit is contained in:
Sameh Khamis committed 2026-11-10 13:16:42 -08:00
1 parent 584138decf
commit 32e7a1a913
2 files changed
+22 -2

No files matched your search

+12
View File
@@ -47,6 +47,18 @@ test('EMODnet wrecks keep ship facts and drop text that names people', () => {
feature('w.4', { name: 'Null island' }, [0, 0]),
],
});
const ids = normalizeEmodnetFeatures({
features: [
feature('w.3', { name: 'Copied', source_inf: 'www.wrecksite.eu' }),
feature('w.5', {
source_inf: `${'SHOM; '.repeat(20)}wrecksite.eu`,
}),
feature('w.6', { website1: 'https://www.wrecksite.eu/wreck.aspx?1' }),
feature('w.7', { website1: 'wrecksite.eu/wreck/1' }),
feature('w.8', { name: 'Kept', source_inf: 'SHOM' }),
],
}).map((record) => record.id);
assert.deepEqual(ids, ['emodnet:w.8'], 'wrecksite.eu rows are all skipped');
assert.equal(wreck.id, 'emodnet:w.1');
assert.equal(wreck.year, 1987);
assert.equal(wreck.vesselType, 'Pusher or tug');