From c90eac7e0eefd6b2da62012a7b5bca524fe6cba2 Mon Sep 17 00:00:00 2001 From: Jonathan Johnson Date: Wed, 26 Nov 2014 20:02:25 -0600 Subject: url: change hostname regex to negate invalid chars Regarding joyent/node#8520 This changes hostname validation from a whitelist regex approach to a blacklist regex approach as described in https://url.spec.whatwg.org/#host-parsing. url.parse misinterpreted `https://good.com+.evil.org/` as `https://good.com/+.evil.org/`. If we use url.parse to check the validity of the hostname, the test passes, but in the browser the user is redirected to the evil.org website. --- lib/url.js | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'lib/url.js') diff --git a/lib/url.js b/lib/url.js index 56b1be9328..2231ea0ca7 100644 --- a/lib/url.js +++ b/lib/url.js @@ -72,8 +72,9 @@ var protocolPattern = /^([a-z0-9.+-]+:)/i, nonHostChars = ['%', '/', '?', ';', '#'].concat(autoEscape), hostEndingChars = ['/', '?', '#'], hostnameMaxLen = 255, - hostnamePartPattern = /^[a-z0-9A-Z_-]{0,63}$/, - hostnamePartStart = /^([a-z0-9A-Z_-]{0,63})(.*)$/, + hostnamePatternString = '[^' + nonHostChars.join('') + ']{0,63}', + hostnamePartPattern = new RegExp('^' + hostnamePatternString + '$'), + hostnamePartStart = new RegExp('^(' + hostnamePatternString + ')(.*)$'), // protocols that can allow "unsafe" and "unwise" chars. unsafeProtocol = { 'javascript': true, -- cgit v1.2.3