6e69b48103
- Remove legacy inference and platform files from `src/inference/` and migrate responsibilities to new modular locations under `src/infrastructure/`, `src/inference/pdf/`, and `src/inference/whisper/` - Consolidate environment/config logic into `src/infrastructure/config.ts` - Move docstore and ffmpeg platform utilities to `src/infrastructure/platform.ts` - Refactor PDF and Whisper inference code to use new document layout, layout model, and timestamp utilities - Update API contracts to define and export types and constants previously scattered in inference/types - Adjust all imports in jobs, storage, and tests to reference new module structure and type locations - Inline parser version and encoding logic into API contracts - Remove obsolete files and update test fixtures for new type locations This update improves codebase modularity, maintainability, and separation of concerns. No changes to inference or orchestration functionality. BREAKING CHANGE: inference module structure, type imports, and config utilities have changed; downstream code must update imports and integration points.
35 lines
1.6 KiB
TypeScript
35 lines
1.6 KiB
TypeScript
import { describe, expect, test } from 'vitest';
|
|
import {
|
|
mapWordsToSentenceOffsets,
|
|
} from '../../../src/inference/whisper/timestamps';
|
|
|
|
describe('whisper alignment mapping', () => {
|
|
test('maps words to sentence offsets with punctuation and repeated spaces', () => {
|
|
const aligned = mapWordsToSentenceOffsets('Hello, world again.', [
|
|
{ word: 'Hello', start: 0, end: 0.25 },
|
|
{ word: 'world', start: 0.25, end: 0.5 },
|
|
{ word: 'again', start: 0.5, end: 1.0 },
|
|
]);
|
|
|
|
expect(aligned.words).toHaveLength(3);
|
|
expect(aligned.words[0].charStart).toBe(0);
|
|
expect(aligned.words[0].charEnd).toBe(5);
|
|
expect(aligned.words[1].charStart).toBeGreaterThan(aligned.words[0].charEnd);
|
|
expect(aligned.words[2].charStart).toBeGreaterThan(aligned.words[1].charEnd);
|
|
expect(aligned.words[2].charEnd).toBeLessThanOrEqual('Hello, world again.'.length);
|
|
});
|
|
|
|
test('joins line-break hyphenation across unicode letters', () => {
|
|
// "Über-\n mensch" must normalize to "Übermensch" so the offsets match the
|
|
// client char map. This only works with the unicode-aware hyphen regex that
|
|
// is kept in lock-step across nlp.ts / alignment-map.ts / highlight-char-map.ts.
|
|
const aligned = mapWordsToSentenceOffsets('Über-\n mensch walks', [
|
|
{ word: 'Übermensch', start: 0, end: 0.5 },
|
|
{ word: 'walks', start: 0.5, end: 1.0 },
|
|
]);
|
|
|
|
expect(aligned.words[0].charStart).toBe(0);
|
|
expect(aligned.words[0].charEnd).toBe('Übermensch'.length);
|
|
expect(aligned.words[1].charStart).toBeGreaterThanOrEqual(aligned.words[0].charEnd);
|
|
});
|
|
});
|