Skip to content

refactor: replace scraper with lol_html for HTML charset prescanning #398

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
barjin merged 4 commits into from
Mar 4, 2026
Merged

refactor: replace scraper with lol_html for HTML charset prescanning #398

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8baacbd
Initial plan
Copilot Mar 4, 2026
8c88c73
refactor: replace scraper with lol_html for HTML charset prescanning
Copilot Mar 4, 2026
eb547e8
chore: update yarn.lock for impit-node v0.10.1
Copilot Mar 4, 2026
6301f04
chore: extend `.text()` decoding tests
barjin Mar 4, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
173 changes: 44 additions & 129 deletions Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

12 changes: 6 additions & 6 deletions impit-node/package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,13 +54,13 @@
"packageManager": "yarn@4.12.0",
"description": "Impit for JavaScript",
"optionalDependencies": {
"impit-darwin-x64": "0.10.1",
"impit-darwin-arm64": "0.10.1",
"impit-win32-x64-msvc": "0.10.1",
"impit-win32-arm64-msvc": "0.10.1",
"impit-darwin-x64": "0.10.1",
"impit-linux-arm64-gnu": "0.10.1",
"impit-linux-arm64-musl": "0.10.1",
"impit-linux-x64-gnu": "0.10.1",
"impit-linux-x64-musl": "0.10.1",
"impit-linux-arm64-gnu": "0.10.1",
"impit-linux-arm64-musl": "0.10.1"
"impit-win32-arm64-msvc": "0.10.1",
"impit-win32-x64-msvc": "0.10.1"
}
}
}
16 changes: 15 additions & 1 deletion impit-node/test/basics.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -480,13 +480,27 @@ describe.each([
t.expect(text).toContain('Herman Melville');
});

test('.text() method works with decoding', async (t) => {
test('.text() decodes using Content-Type header charset param', async (t) => {
const response = await impit.fetch(new URL(routes.charset.path, "http://127.0.0.1:3001").href);
const text: string = await response.text();

t.expect(text).toContain(routes.charset.bodyString);
});

test('.text() decodes using <meta charset> prescan', async (t) => {
const response = await impit.fetch(new URL(routes.charsetMetaCharset.path, "http://127.0.0.1:3001").href);
const text: string = await response.text();

t.expect(text).toContain(routes.charsetMetaCharset.bodyString);
});

test('.text() decodes using <meta http-equiv> prescan', async (t) => {
const response = await impit.fetch(new URL(routes.charsetMetaHttpEquiv.path, "http://127.0.0.1:3001").href);
const text: string = await response.text();

t.expect(text).toContain(routes.charsetMetaHttpEquiv.bodyString);
});

test('.json() method works', async (t) => {
const response = await impit.fetch(getHttpBinUrl('/json'));
const json = await response.json();
Expand Down
36 changes: 34 additions & 2 deletions impit-node/test/mock.server.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,11 +2,23 @@ import express from 'express';
import { Server } from 'http';
import { Server as ProxyServer } from 'proxy-chain';

// "Příliš žluťoučký kůň úpěl ďábelské ódy" encoded in Windows-1250
const WIN1250_BODY = Buffer.from([0x50, 0xf8, 0xed, 0x6c, 0x69, 0x9a, 0x20, 0x9e, 0x6c, 0x75, 0x9d, 0x6f, 0x75, 0xe8, 0x6b, 0xfd, 0x20, 0x6b, 0xf9, 0xf2, 0x20, 0xfa, 0x70, 0xec, 0x6c, 0x20, 0xef, 0xe1, 0x62, 0x65, 0x6c, 0x73, 0x6b, 0xe9, 0x20, 0xf3, 0x64, 0x79]);
const WIN1250_STRING = 'Příliš žluťoučký kůň úpěl ďábelské ódy';

export const routes = {
charset: {
path: '/charset',
bodyBuffer: Buffer.from([0x50, 0xf8, 0xed, 0x6c, 0x69, 0x9a, 0x20, 0x9e, 0x6c, 0x75, 0x9d, 0x6f, 0x75, 0xe8, 0x6b, 0xfd, 0x20, 0x6b, 0xf9, 0xf2, 0x20, 0xfa, 0x70, 0xec, 0x6c, 0x20, 0xef, 0xe1, 0x62, 0x65, 0x6c, 0x73, 0x6b, 0xe9, 0x20, 0xf3, 0x64, 0x79]),
bodyString: 'Příliš žluťoučký kůň úpěl ďábelské ódy'
bodyBuffer: WIN1250_BODY,
bodyString: WIN1250_STRING,
},
charsetMetaCharset: {
path: '/charset/meta-charset',
bodyString: WIN1250_STRING,
},
charsetMetaHttpEquiv: {
path: '/charset/meta-http-equiv',
bodyString: WIN1250_STRING,
},
}

Expand All @@ -18,6 +30,26 @@ export async function runServer(port: number): Promise<Server> {
res.send(routes.charset.bodyBuffer);
});

app.get(routes.charsetMetaCharset.path, (req, res) => {
const html = Buffer.concat([
Buffer.from('<html><head><meta charset="windows-1250"></head><body>'),
WIN1250_BODY,
Buffer.from('</body></html>'),
]);
res.writeHead(200, { 'Content-Type': 'text/html' });
res.end(html);
});

app.get(routes.charsetMetaHttpEquiv.path, (req, res) => {
const html = Buffer.concat([
Buffer.from('<html><head><meta http-equiv="content-type" content="text/html; charset=windows-1250"></head><body>'),
WIN1250_BODY,
Buffer.from('</body></html>'),
]);
res.writeHead(200, { 'Content-Type': 'text/html' });
res.end(html);
});

app.get('/socket', (req, res) => {
const socket = req.socket;
const clientAddress = socket.remoteAddress;
Expand Down
Loading