feat(species): expand catalog to ~1200 edible species from Wikidata
Grow the bundled species catalog from 14 hand-curated entries to ~1200 edible/cultivated species, internationalized in 13 languages (es, en, fr, de, it, pt, ca, gl, eu, ar, zh, ja, ru — Latin + Arabic RTL + CJK + Cyrillic). - Add a reproducible generator (tool/gen_species_catalog.dart) that queries Wikidata (CC0, no attribution burden) in two phases, filters out non-vernacular noise (author citations, ranks, initials) and applies a relevance floor, then merges hand-curated, authoritative core-crop data (tool/curated_overrides.json: names, family, viability_years). GBIF is used only as an identifier. The generated species.json (v3) is committed. - Carry wikidata_qid and gbif_key through the parse/seed pipeline; the columns already existed, so no DB migration. - Rewrite seedBundled to one read + one batch (was a SELECT per species on every startup — a real cost at ~1200 rows) and keep it idempotent with backfill of the new reference fields. - Move species search filtering to SQL (LIKE) so a large catalog is not pulled into memory on every keystroke. - Cover the generator transform, the generated asset, and the new fields with tests.
This commit is contained in:
parent
ba87bf2719
commit
959fa2551c
9 changed files with 68483 additions and 120 deletions
|
|
@ -39,12 +39,14 @@ void main() {
|
|||
'parseSpeciesCatalog reads scientific name, family and common names',
|
||||
() {
|
||||
const json = '''
|
||||
{"version":1,"species":[
|
||||
{"scientific_name":"Zea mays","family":"Poaceae","common":{"en":["Maize"],"es":["Maíz"]}}
|
||||
{"version":3,"species":[
|
||||
{"scientific_name":"Zea mays","family":"Poaceae","wikidata_qid":"Q11575","gbif_key":2703077,"common":{"en":["Maize"],"es":["Maíz"]}}
|
||||
]}''';
|
||||
final seeds = parseSpeciesCatalog(json);
|
||||
expect(seeds.single.scientificName, 'Zea mays');
|
||||
expect(seeds.single.family, 'Poaceae');
|
||||
expect(seeds.single.wikidataQid, 'Q11575');
|
||||
expect(seeds.single.gbifKey, 2703077);
|
||||
expect(seeds.single.commonNames['es'], ['Maíz']);
|
||||
},
|
||||
);
|
||||
|
|
@ -80,4 +82,86 @@ void main() {
|
|||
await repo.seedBundled(_seeds);
|
||||
expect(await repo.search(' '), isEmpty);
|
||||
});
|
||||
|
||||
test('seedBundled stores wikidata id and gbif key', () async {
|
||||
await repo.seedBundled(const [
|
||||
SpeciesSeed(
|
||||
scientificName: 'Solanum lycopersicum',
|
||||
family: 'Solanaceae',
|
||||
wikidataQid: 'Q13223',
|
||||
gbifKey: 2930137,
|
||||
commonNames: {
|
||||
'en': ['Tomato'],
|
||||
},
|
||||
),
|
||||
]);
|
||||
|
||||
final row = await db.select(db.species).getSingle();
|
||||
expect(row.wikidataQid, 'Q13223');
|
||||
expect(row.gbifKey, 2930137);
|
||||
});
|
||||
|
||||
test('seedBundled backfills reference fields added later', () async {
|
||||
// First seed lacks the enrichment fields (an older catalog).
|
||||
await repo.seedBundled(const [
|
||||
SpeciesSeed(
|
||||
scientificName: 'Allium cepa',
|
||||
commonNames: {
|
||||
'en': ['Onion'],
|
||||
},
|
||||
),
|
||||
]);
|
||||
// A later catalog carries them; identity is preserved, fields are filled.
|
||||
await repo.seedBundled(const [
|
||||
SpeciesSeed(
|
||||
scientificName: 'Allium cepa',
|
||||
wikidataQid: 'Q23485',
|
||||
gbifKey: 2857697,
|
||||
viabilityYears: 1,
|
||||
commonNames: {
|
||||
'en': ['Onion'],
|
||||
},
|
||||
),
|
||||
]);
|
||||
|
||||
final rows = await db.select(db.species).get();
|
||||
expect(rows.length, 1);
|
||||
expect(rows.single.wikidataQid, 'Q23485');
|
||||
expect(rows.single.gbifKey, 2857697);
|
||||
expect(rows.single.viabilityYears, 1);
|
||||
});
|
||||
|
||||
test('search matches a non-Latin common name', () async {
|
||||
await repo.seedBundled(const [
|
||||
SpeciesSeed(
|
||||
scientificName: 'Solanum lycopersicum',
|
||||
commonNames: {
|
||||
'ar': ['طماطم'],
|
||||
'zh': ['番茄'],
|
||||
},
|
||||
),
|
||||
]);
|
||||
|
||||
final ar = await repo.search('طماطم', languageCode: 'ar');
|
||||
expect(ar.single.scientificName, 'Solanum lycopersicum');
|
||||
expect(ar.single.commonName, 'طماطم');
|
||||
|
||||
final zh = await repo.search('番茄', languageCode: 'zh');
|
||||
expect(zh.single.commonName, '番茄');
|
||||
});
|
||||
|
||||
test('search respects the limit', () async {
|
||||
final many = [
|
||||
for (var i = 0; i < 20; i++)
|
||||
SpeciesSeed(
|
||||
scientificName: 'Genus species$i',
|
||||
commonNames: const {
|
||||
'en': ['Plant'],
|
||||
},
|
||||
),
|
||||
];
|
||||
await repo.seedBundled(many);
|
||||
final results = await repo.search('Genus', limit: 5);
|
||||
expect(results.length, 5);
|
||||
});
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue