Skip to content
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

Jump to bottom

http: disallow two-byte characters in URL path #16237

Closed
wants to merge 4 commits into from
Closed

http: disallow two-byte characters in URL path #16237

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
844a470
http: disallow two-byte characters in URL path
bennofs Oct 16, 2017
eab523c
fixup! http: disallow two-byte characters in URL path
bennofs Oct 16, 2017
58ac26f
fixup! http: disallow two-byte characters in URL path
bennofs Oct 16, 2017
60b3290
http: always use regex for invalid path check
bennofs Oct 16, 2017
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
36 changes: 2 additions & 34 deletions lib/_http_client.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,33 +41,7 @@ const { outHeadersKey } = require('internal/http');
const { nextTick } = require('internal/process/next_tick');
const errors = require('internal/errors');

// The actual list of disallowed characters in regexp form is more like:
// /[^A-Za-z0-9\-._~!$&'()*+,;=/:@]/
// with an additional rule for ignoring percentage-escaped characters, but
// that's a) hard to capture in a regular expression that performs well, and
// b) possibly too restrictive for real-world usage. So instead we restrict the
// filter to just control characters and spaces.
//
// This function is used in the case of small paths, where manual character code
// checks can greatly outperform the equivalent regexp (tested in V8 5.4).
function isInvalidPath(s) {
var i = 0;
if (s.charCodeAt(0) <= 32) return true;
if (++i >= s.length) return false;
if (s.charCodeAt(1) <= 32) return true;
if (++i >= s.length) return false;
if (s.charCodeAt(2) <= 32) return true;
if (++i >= s.length) return false;
if (s.charCodeAt(3) <= 32) return true;
if (++i >= s.length) return false;
if (s.charCodeAt(4) <= 32) return true;
if (++i >= s.length) return false;
if (s.charCodeAt(5) <= 32) return true;
++i;
for (; i < s.length; ++i)
if (s.charCodeAt(i) <= 32) return true;
return false;
}
const INVALID_PATH_REGEX = /[\u0000-\u0020\u0100-\uffff]/;
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I'd simplify this with /[^\x21-\xff]/ or /[^\u0021-\u00ff]/


function validateHost(host, name) {
if (host != null && typeof host !== 'string') {
Expand Down Expand Up @@ -117,13 +91,7 @@ function ClientRequest(options, cb) {
var path;
if (options.path) {
path = String(options.path);
var invalidPath;
if (path.length <= 39) { // Determined experimentally in V8 5.4
invalidPath = isInvalidPath(path);
} else {
invalidPath = /[\u0000-\u0020]/.test(path);
}
if (invalidPath)
if (INVALID_PATH_REGEX.test(path))
throw new errors.TypeError('ERR_UNESCAPED_CHARACTERS', 'Request path');
}

Expand Down
12 changes: 12 additions & 0 deletions test/parallel/test-http-client-invalid-path.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
'use strict';
const common = require('../common');
const http = require('http');

common.expectsError(() => {
http.request({
path: '/thisisinvalid\uffe2'
}).end();
}, {
code: 'ERR_UNESCAPED_CHARACTERS',
type: TypeError
});