fix(curator): HSK levels by the syllabus's tones; variants find their word
The syllabus's reading is matched with its tones first, so 和 hé gets HSK 1 and 和 hè doesn't; only where no entry of a word reads it so (the syllabus marks the tone changes of 一 and 不, 一下 yíxià, CC-CEDICT doesn't) are the letters alone compared. CC-CEDICT's 2,885 entries that are only "variant of …" (咊, an old variant of 和) are no entries of their own any more, which repeated their word in the simplified file, but written forms of that word, finding it in text and searches. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Signed-off-by: Tizian 「ティツィアーン」 <raisondetredev@pm.me>
This commit is contained in:
parent
9d21f7f20e
commit
7b94eda592
1 changed files with 116 additions and 18 deletions
|
|
@ -82,6 +82,9 @@ void main() {
|
|||
'de, not dì; 书 shū, not the Book of Documents, Shū', () {
|
||||
expect(entryOf('的 的 [de5]')['labels'], contains('hsk:1'));
|
||||
expect(entryOf('的 的 [di4]')['labels'], isNot(contains('hsk:1')));
|
||||
// Read with its tones: 说 shuō, not shuì.
|
||||
expect(entryOf('說 说 [shuo1]')['labels'], contains('hsk:1'));
|
||||
expect(entryOf('說 说 [shui4]')['labels'], isEmpty);
|
||||
expect(entryOf('書 书 [shu1]')['labels'], contains('hsk:1'));
|
||||
expect(entryOf('書 书 [Shu1]')['labels'], isEmpty);
|
||||
expect(entryOf('中國 中国 [Zhong1 guo2]')['labels'], contains('hsk:1'));
|
||||
|
|
@ -97,6 +100,18 @@ void main() {
|
|||
);
|
||||
});
|
||||
|
||||
test('an entry that is only a variant of another is no entry, but finds '
|
||||
'that one', () {
|
||||
final ids = [
|
||||
for (final line in linesOf(traditional: false).skip(1)) line['id'],
|
||||
];
|
||||
expect(ids, isNot(contains('咊 和 [he2]')));
|
||||
expect(
|
||||
(entryOf('和 和 [he2]')['textKeys']! as List).cast<String>(),
|
||||
contains('咊'),
|
||||
);
|
||||
});
|
||||
|
||||
test('measure words are a remark beside the meanings, pinyin marked', () {
|
||||
final book = entryOf('書 书 [shu1]')['entry']! as Map;
|
||||
expect(book['classifiers'], ['本 běn', '冊|册 cè', '部 bù']);
|
||||
|
|
|
|||
Loading…
Reference in a new issue