Files
FastGPT/packages/service/worker/readFile/extension/docx.ts
Theresa 2d3117c5da feat: update ESLint config with @typescript-eslint/consistent-type-imports (#4746)
* update: Add type

* fix: update import statement for NextApiRequest type

* fix: update imports to use type for LexicalEditor and EditorState

* Refactor imports to use 'import type' for type-only imports across multiple files

- Updated imports in various components and API files to use 'import type' for better clarity and to optimize TypeScript's type checking.
- Ensured consistent usage of type imports in files related to chat, dataset, workflow, and user management.
- Improved code readability and maintainability by distinguishing between value and type imports.

* refactor: remove old ESLint configuration and add new rules

- Deleted the old ESLint configuration file from the app project.
- Added a new ESLint configuration file with updated rules and settings.
- Changed imports to use type-only imports in various files for better clarity and performance.
- Updated TypeScript configuration to remove unnecessary options.
- Added an ESLint ignore file to exclude build and dependency directories from linting.

* fix: update imports to use 'import type' for type-only imports in schema files
2025-05-06 17:33:09 +08:00

44 lines
1.1 KiB
TypeScript

import mammoth, { images } from 'mammoth';
import { type ReadRawTextByBuffer, type ReadFileResponse, type ImageType } from '../type';
import { html2md } from '../../htmlStr2Md/utils';
/**
* read docx to markdown
*/
export const readDocsFile = async ({ buffer }: ReadRawTextByBuffer): Promise<ReadFileResponse> => {
const imageList: ImageType[] = [];
try {
const { value: html } = await mammoth.convertToHtml(
{
buffer
},
{
ignoreEmptyParagraphs: false,
convertImage: images.imgElement(async (image) => {
const imageBase64 = await image.readAsBase64String();
const uuid = crypto.randomUUID();
const mime = image.contentType;
imageList.push({
uuid,
base64: imageBase64,
mime
});
return {
src: uuid
};
})
}
);
const { rawText } = html2md(html);
return {
rawText,
imageList
};
} catch (error) {
console.log('error doc read:', error);
return Promise.reject('Can not read doc file, please convert to PDF');
}
};