office-text-extractor
Version:
Yet another library to extract text from MS Office and PDF files
24 lines (23 loc) • 773 B
JavaScript
// source/parsers/docx.ts
// The text extracter for DOCX files.
import { extractRawText as parseWordFile } from 'mammoth';
export class DocExtractor {
/**
* The type(s) of input acceptable to this method.
*/
mimes = [
'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
];
/**
* Extract text from a DOCX file if possible.
*
* @param payload The input and its type.
* @returns The text extracted from the input.
*/
apply = async (input) => {
// Convert the DOCX to text and return the text.
// @ts-expect-error mammoth expects a Buffer, but we pass a Uint8Array.
const parsedDocx = await parseWordFile({ buffer: input });
return parsedDocx.value;
};
}