Akiba So
0cf58fb67a
Some checks failed
CI / Windows build (push) Has been cancelled
normalizeForIndex (lowercase + collapse whitespace runs incl. hard PDF/OCR newlines + trim) and matchesNormalized so a query matches across the line breaks in raw extracted text. Deliberately NO word-tokenization: Chinese has no inter-word spaces, so substring match over normalized text is correct for both Latin and CJK (段/word segmentation belongs in the DB FTS tokenizer). Verified on CJK inputs (你好/笔记应用). flutter analyze lib/editor clean; 181/181 tests (+9). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
52 lines
1.7 KiB
Dart
52 lines
1.7 KiB
Dart
// Tests for CJK-safe search text normalization + matching (F8).
|
|
|
|
import 'package:flutter_test/flutter_test.dart';
|
|
|
|
import 'package:badnote/editor/search/search_text.dart';
|
|
|
|
void main() {
|
|
group('normalizeForIndex', () {
|
|
test('lowercases and collapses whitespace runs to single spaces', () {
|
|
expect(normalizeForIndex('Hello World'), 'hello world');
|
|
expect(normalizeForIndex('a\t b\n\nc'), 'a b c');
|
|
});
|
|
|
|
test('trims leading/trailing whitespace', () {
|
|
expect(normalizeForIndex(' padded '), 'padded');
|
|
});
|
|
|
|
test('collapses hard newlines from PDF/OCR mid-sentence', () {
|
|
expect(normalizeForIndex('hello\nworld'), 'hello world');
|
|
});
|
|
|
|
test('leaves CJK intact (no tokenization/mangling)', () {
|
|
expect(normalizeForIndex('你好 世界'), '你好 世界');
|
|
expect(normalizeForIndex('笔记\n应用'), '笔记 应用');
|
|
});
|
|
});
|
|
|
|
group('matchesNormalized', () {
|
|
test('matches across a line break in the source', () {
|
|
expect(matchesNormalized('hello\nworld', 'hello world'), isTrue);
|
|
});
|
|
|
|
test('is case-insensitive', () {
|
|
expect(matchesNormalized('The Quick Fox', 'quick'), isTrue);
|
|
});
|
|
|
|
test('CJK substring match works', () {
|
|
expect(matchesNormalized('这是一个笔记应用', '笔记'), isTrue);
|
|
expect(matchesNormalized('这是一个笔记\n应用', '笔记 应用'), isTrue);
|
|
});
|
|
|
|
test('empty query never matches', () {
|
|
expect(matchesNormalized('anything', ''), isFalse);
|
|
expect(matchesNormalized('anything', ' '), isFalse);
|
|
});
|
|
|
|
test('non-match returns false', () {
|
|
expect(matchesNormalized('hello world', 'zzz'), isFalse);
|
|
});
|
|
});
|
|
}
|