Files
FastGPT/packages/service/worker/readFile/index.ts
Archer adf5377ebe Add image index and pdf parse (#3956)
* feat: think tag parse

* feat: parse think tag test

* feat: pdf parse ux

* feat: doc2x parse

* perf: rewrite training mode setting

* feat: image parse queue

* perf: image index

* feat: image parse process

* feat: add init sh

* fix: ts
2025-03-06 18:28:03 +08:00

56 lines
1.5 KiB
TypeScript

import { parentPort } from 'worker_threads';
import { readFileRawText } from './extension/rawText';
import { ReadRawTextByBuffer, ReadRawTextProps } from './type';
import { readHtmlRawText } from './extension/html';
import { readPdfFile } from './extension/pdf';
import { readDocsFile } from './extension/docx';
import { readPptxRawText } from './extension/pptx';
import { readXlsxRawText } from './extension/xlsx';
import { readCsvRawText } from './extension/csv';
parentPort?.on('message', async (props: ReadRawTextProps<Uint8Array>) => {
const read = async (params: ReadRawTextByBuffer) => {
switch (params.extension) {
case 'txt':
case 'md':
return readFileRawText(params);
case 'html':
return readHtmlRawText(params);
case 'pdf':
return readPdfFile(params);
case 'docx':
return readDocsFile(params);
case 'pptx':
return readPptxRawText(params);
case 'xlsx':
return readXlsxRawText(params);
case 'csv':
return readCsvRawText(params);
default:
return Promise.reject('Only support .txt, .md, .html, .pdf, .docx, pptx, .csv, .xlsx');
}
};
// params.buffer: Uint8Array -> buffer
const buffer = Buffer.from(props.buffer);
const newProps: ReadRawTextByBuffer = {
...props,
buffer
};
try {
parentPort?.postMessage({
type: 'success',
data: await read(newProps)
});
} catch (error) {
console.log(error);
parentPort?.postMessage({
type: 'error',
data: error
});
}
process.exit();
});