halkyon/halkyon_learn_curator/test/update_test.dart
Tizian 「ティツィアーン」 fb0ef7cdab
feat(dictionary): the radicals, each listing the kanji written with it
Beside Words and Kanji & kana, a Radicals tab lists the 214 Kangxi
radicals by their strokes, with the forms Japanese writes them as inside
kanji (亻, 氵, 艹, …). One chosen lists the kanji KANJIDIC2 files under
it, in the dictionary's order, to add or to see how one is written; the
tab shares the characters' bloc, so a kanji added there shows as held in
a search too.

The curator labels each kanji with its classical radical (`radical:N`),
so the server's existing label queries serve the tab unchanged. Its
files now say which conversion made them (`.conversion`): an instance
running a curator that converts differently converts again at once,
rather than at its weekly update, so the radicals appear right after a
deploy.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MMm7usAo6q9ZZRoPkWjoxi
Signed-off-by: Tizian 「ティツィアーン」 <raisondetredev@pm.me>
2026-10-10 09:46:46 +02:00

100 lines
3.2 KiB
Dart

import 'dart:convert';
import 'dart:io';
import 'package:halkyon_learn_curator/src/update.dart';
import 'package:test/test.dart';
void main() {
late Directory into;
setUp(() => into = Directory.systemTemp.createTempSync('dictionaries'));
tearDown(() => into.deleteSync(recursive: true));
/// Fetches the samples in place of EDRDG's files of the day.
Future<void> samples(Uri uri, File file) async {
final sample = uri == jmdictSource
? 'test/fixtures/jmdict-e-examp-sample.xml'
: 'test/fixtures/kanjidic2-sample.xml';
await file.writeAsBytes(gzip.encode(await File(sample).readAsBytes()));
}
/// The header of the dictionary file [name] in [into].
Map<String, Object?> header(String name) => jsonDecode(
utf8
.decode(gzip.decode(File('${into.path}/$name').readAsBytesSync()))
.split('\n')
.first,
) as Map<String, Object?>;
test("writes JMdict and KANJIDIC2 from EDRDG's files, the JLPT levels from "
"the curator's data", () async {
final written = await updateDictionaries(
into: into,
data: Directory('data'),
fetch: samples,
);
expect(
[for (final file in written) file.uri.pathSegments.last],
['jmdict-en.jsonl.gz', 'kanjidic-en.jsonl.gz'],
);
expect(header('jmdict-en.jsonl.gz')['sourceVersion'], '2026-10-09');
expect(
[
for (final credit in header('jmdict-en.jsonl.gz')['credits']! as List)
(credit as Map)['name'],
],
['JMdict', 'JLPT vocabulary lists', 'Tatoeba'],
);
expect(header('kanjidic-en.jsonl.gz')['kind'], 'characters');
// Nothing half-written left behind; which conversion made them.
expect(
[for (final entity in into.listSync()) entity.uri.pathSegments.last]
..sort(),
['.conversion', 'jmdict-en.jsonl.gz', 'kanjidic-en.jsonl.gz'],
);
expect(File('${into.path}/.conversion').readAsStringSync(), '$conversion');
expect(lastUpdated(into), isNotNull);
});
test('files another conversion made, or one from before the curator said, '
'are converted again at once', () async {
await updateDictionaries(
into: into,
data: Directory('data'),
fetch: samples,
);
final made = File('${into.path}/$conversionFile')
..writeAsStringSync('${conversion - 1}');
expect(lastUpdated(into), isNull);
made.deleteSync();
expect(lastUpdated(into), isNull);
});
test('a download that fails leaves the files there as they were', () async {
await updateDictionaries(
into: into,
data: Directory('data'),
fetch: samples,
);
final before = File('${into.path}/jmdict-en.jsonl.gz').readAsBytesSync();
await expectLater(
updateDictionaries(
into: into,
data: Directory('data'),
fetch: (uri, file) => uri == kanjidicSource
? Future.error(const HttpException('EDRDG answered 503.'))
: samples(uri, file),
),
throwsA(isA<HttpException>()),
);
expect(File('${into.path}/jmdict-en.jsonl.gz').readAsBytesSync(), before);
});
test('a folder missing a file was never brought up to date', () {
expect(lastUpdated(into), isNull);
});
}