mirror of
https://github.com/labring/FastGPT.git
synced 2025-08-06 07:28:56 +00:00
Feat: pptx and xlsx loader (#1118)
* perf: plan tip * perf: upload size controller * feat: add image ttl index * feat: new upload file ux * remove file * feat: support read pptx * feat: support xlsx * fix: rerank docker flie
This commit is contained in:
45
packages/service/common/file/read/xlsx.ts
Normal file
45
packages/service/common/file/read/xlsx.ts
Normal file
@@ -0,0 +1,45 @@
|
||||
import { ReadFileByBufferParams, ReadFileResponse } from './type.d';
|
||||
import xlsx from 'node-xlsx';
|
||||
import Papa from 'papaparse';
|
||||
|
||||
export const readXlsxRawText = async ({
|
||||
buffer
|
||||
}: ReadFileByBufferParams): Promise<ReadFileResponse> => {
|
||||
const result = xlsx.parse(buffer, {
|
||||
skipHidden: false,
|
||||
defval: ''
|
||||
});
|
||||
|
||||
const format2Csv = result.map(({ name, data }) => {
|
||||
return {
|
||||
title: `#${name}`,
|
||||
csvText: data.map((item) => item.join(',')).join('\n')
|
||||
};
|
||||
});
|
||||
|
||||
const rawText = format2Csv.map((item) => item.csvText).join('\n');
|
||||
const formatText = format2Csv
|
||||
.map((item) => {
|
||||
const csvArr = Papa.parse(item.csvText).data as string[][];
|
||||
const header = csvArr[0];
|
||||
|
||||
const formatText = header
|
||||
? csvArr
|
||||
.map((item) =>
|
||||
item
|
||||
.map((item, i) => (item ? `${header[i]}:${item}` : ''))
|
||||
.filter(Boolean)
|
||||
.join('\n')
|
||||
)
|
||||
.join('\n')
|
||||
: '';
|
||||
|
||||
return `${item.title}\n${formatText}`;
|
||||
})
|
||||
.join('\n');
|
||||
|
||||
return {
|
||||
rawText: rawText,
|
||||
formatText
|
||||
};
|
||||
};
|
Reference in New Issue
Block a user