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.
54 lines
1.2 KiB
TypeScript
54 lines
1.2 KiB
TypeScript
import type { BaseDocument } from '../../../../../src/types/documents';
|
|
import type { ParsedPdfBlock, ParsedPdfBlockKind, ParsedPdfDocument, ParsedPdfPage } from '../../../../src/api/types';
|
|
|
|
export function makeBaseDocument(overrides: Partial<BaseDocument> = {}): BaseDocument {
|
|
return {
|
|
id: 'doc-1',
|
|
name: 'document.pdf',
|
|
size: 1_024,
|
|
lastModified: 1_700_000_000_000,
|
|
type: 'pdf',
|
|
...overrides,
|
|
};
|
|
}
|
|
|
|
export function makeParsedPdfBlock(input: {
|
|
id: string;
|
|
kind: ParsedPdfBlockKind;
|
|
text: string;
|
|
page: number;
|
|
readingOrder: number;
|
|
}): ParsedPdfBlock {
|
|
return {
|
|
id: input.id,
|
|
kind: input.kind,
|
|
text: input.text,
|
|
fragments: [
|
|
{
|
|
page: input.page,
|
|
bbox: [0, 0, 100, 10],
|
|
text: input.text,
|
|
readingOrder: input.readingOrder,
|
|
},
|
|
],
|
|
};
|
|
}
|
|
|
|
export function makeParsedPdfPage(pageNumber: number, blocks: ParsedPdfBlock[]): ParsedPdfPage {
|
|
return {
|
|
pageNumber,
|
|
width: 800,
|
|
height: 1_200,
|
|
blocks,
|
|
};
|
|
}
|
|
|
|
export function makeParsedPdfDocument(pages: ParsedPdfPage[]): ParsedPdfDocument {
|
|
return {
|
|
schemaVersion: 1,
|
|
documentId: 'doc-fixture',
|
|
parserVersion: 'test',
|
|
parsedAt: 1_700_000_000_000,
|
|
pages,
|
|
};
|
|
}
|