gristlabs_grist-core/app/server/lib/httpEncoding.ts
Alex Hall 9fffb491f9 (core) External requests
Summary:
Adds a Python function `REQUEST` which makes an HTTP GET request. Behind the scenes it:

- Raises a special exception to stop trying to evaluate the current cell and just keep the existing value.
- Notes the request arguments which will be returned by `apply_user_actions`.
- Makes the actual request in NodeJS, which sends back the raw response data in a new action `RespondToRequests` which reevaluates the cell(s) that made the request.
- Wraps the response data in a class which mimics the `Response` class of the `requests` library.

In certain cases, this asynchronous flow doesn't work and the sandbox will instead synchronously call an exported JS method:

- When reevaluating a single cell to get a formula error, the request is made synchronously.
- When a formula makes multiple requests, the earlier responses are retrieved synchronously from files which store responses as long as needed to complete evaluating formulas. See https://grist.slack.com/archives/CL1LQ8AT0/p1653399747810139

Test Plan: Added Python and nbrowser tests.

Reviewers: georgegevoian

Reviewed By: georgegevoian

Subscribers: paulfitz, dsagal

Differential Revision: https://phab.getgrist.com/D3429
2022-06-17 21:53:20 +02:00

44 lines
1.0 KiB
TypeScript

// Based on the source code of the Body.textConverted method in node-fetch
export function httpEncoding(header: string | null, content: Buffer): string | undefined {
let res: RegExpExecArray | null = null;
// header
if (header) {
res = /charset=([^;]*)/i.exec(header);
}
// no charset in content type, peek at response body for at most 1024 bytes
const str = content.slice(0, 1024).toString();
// html5
if (!res && str) {
res = /<meta.+?charset=(['"])(.+?)\1/i.exec(str);
}
// html4
if (!res && str) {
res = /<meta\s+?http-equiv=(['"])content-type\1\s+?content=(['"])(.+?)\2/i.exec(str);
if (res) {
res = /charset=(.*)/i.exec(res.pop()!);
}
}
// xml
if (!res && str) {
res = /<\?xml.+?encoding=(['"])(.+?)\1/i.exec(str);
}
// found charset
if (res) {
let charset = res.pop();
// prevent decode issues when sites use incorrect encoding
// ref: https://hsivonen.fi/encoding-menu/
if (charset === 'gb2312' || charset === 'gbk') {
charset = 'gb18030';
}
return charset;
}
}