Tizian 「ティツィアーン」
e42cdfbfcb
A dictionary file now says whether it holds words or characters (`kind`). The kanjidic adapter turns KANJIDIC2 into one entry per kanji that has a Japanese reading or an English meaning (12,633), with its readings, meanings, school grade, strokes, frequency and JLPT level (Jonathan Waller's, through kanji-data's kanji.json), labelled `jlpt:nX`, `grade:N`/`grade:secondary`, followed by the 71 hiragana and katakana of the kana table with their romaji. A kun reading is found whole; its kanji part only as a loose key, so typing "ta" brings た before every kanji read so. `curate kanjivg` writes KanjiVG's strokes and components as the app's stroke files, one gzipped JSON file per 256 code points, keyed by the code point in each entry's id (KanjiVG's 橅 names itself 機). 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>
49 lines
1.6 KiB
Dart
49 lines
1.6 KiB
Dart
import 'dart:io';
|
|
|
|
import 'package:halkyon_learn_curator/src/sources/kanjivg.dart';
|
|
import 'package:test/test.dart';
|
|
|
|
void main() {
|
|
late Map<String, CharacterStrokes> strokes;
|
|
|
|
setUpAll(() async {
|
|
strokes = kanjivgStrokes(
|
|
await File('test/fixtures/kanjivg-sample.xml').readAsString(),
|
|
);
|
|
});
|
|
|
|
test("a character's strokes are its paths in the order they're written", () {
|
|
final eat = strokes['食']!;
|
|
expect(eat.strokes, hasLength(9));
|
|
expect(eat.strokes.first, startsWith('M52.75,10.5c'));
|
|
expect(eat.strokes.last, startsWith('M51.5,71C'));
|
|
expect(strokes['あ']!.strokes, hasLength(3));
|
|
});
|
|
|
|
test('its components are the characters KanjiVG first splits it into, '
|
|
'looking through groups that are none', () {
|
|
expect(strokes['語']!.components, ['言', '吾']);
|
|
expect(strokes['食']!.components, isEmpty);
|
|
});
|
|
|
|
test("the character is the code point in the entry's id, not KanjiVG's "
|
|
'element name, which can be wrong', () {
|
|
// KanjiVG's U+6A45 (橅) names itself 機.
|
|
expect(strokes.keys, containsAll(['橅', 'あ', '食', '語']));
|
|
expect(strokes.keys, isNot(contains('機')));
|
|
});
|
|
|
|
test('the stroke files hold every 256 code points, named by their upper '
|
|
'bits', () {
|
|
expect(strokeFileOf('食'), '098');
|
|
expect(strokeFileOf('あ'), '030');
|
|
expect(strokeFileOf('𠀋'), '200');
|
|
final files = strokeFiles(strokes);
|
|
expect(files.keys, containsAll(['030', '098', '08a', '06a']));
|
|
expect(files['08a']!['語'], {
|
|
's': strokes['語']!.strokes,
|
|
'c': ['言', '吾'],
|
|
});
|
|
expect(files['098']!['食'], {'s': strokes['食']!.strokes});
|
|
});
|
|
}
|