url: trim leading and trailing C0 control chars

Emulate the WHATWHG URL parse behavior of trimming leading and trailing C0 control characters. This moves url.parse() slightly closer to WHATWHG URL behavior. The current behavior is possibly insecure for some uses. (The url.parse() API is marked as Legacy and the documentation specifically says it has known bugs and insecure behaviors. Still this change makes a lot of sense.) This issue was reported by P0cas. https://github.com/P0cas PR-URL: #42196 Reviewed-By: Luigi Pinca <luigipinca@gmail.com> Reviewed-By: Darshan Sen <raisinten@gmail.com> Reviewed-By: Matteo Collina <matteo.collina@gmail.com> Reviewed-By: Mestery <mestery@protonmail.com> Reviewed-By: Anto Aravinth <anto.aravinth.cse@gmail.com> Reviewed-By: Anna Henningsen <anna@addaleax.net>
nodejs · Apr 24, 2022 · 962a8ec350f2d0d7cf09377966bf7dd97ed31dbc · 962a8ec
1 parent c5da1dd
commit 962a8ec350f2d0d7cf09377966bf7dd97ed31dbc
Showing with 16 additions and 6 deletions.

+1 −6 lib/url.js

+15 −0 test/parallel/test-url-parse-format.js
diff --git a/lib/url.js b/lib/url.js
@@ -116,7 +116,6 @@ const {
   CHAR_TAB,
   CHAR_CARRIAGE_RETURN,
   CHAR_LINE_FEED,
-  CHAR_FORM_FEED,
   CHAR_NO_BREAK_SPACE,
   CHAR_ZERO_WIDTH_NOBREAK_SPACE,
   CHAR_HASH,
@@ -181,11 +180,7 @@ Url.prototype.parse = function parse(url, parseQueryString, slashesDenoteHost) {
     const code = url.charCodeAt(i);
 
     // Find first and last non-whitespace characters for trimming
-    const isWs = code === CHAR_SPACE ||
-                 code === CHAR_TAB ||
-                 code === CHAR_CARRIAGE_RETURN ||
-                 code === CHAR_LINE_FEED ||
-                 code === CHAR_FORM_FEED ||
+    const isWs = code < 33 ||
                  code === CHAR_NO_BREAK_SPACE ||
                  code === CHAR_ZERO_WIDTH_NOBREAK_SPACE;
     if (start === -1) {

diff --git a/test/parallel/test-url-parse-format.js b/test/parallel/test-url-parse-format.js
@@ -977,6 +977,21 @@ const parseTests = {
     path: '/everybody',
     href: '//fhqwhgads@example.com/everybody#to-the-limit'
   },
+
+  '\bhttp://example.com/\b': {
+    protocol: 'http:',
+    slashes: true,
+    auth: null,
+    host: 'example.com',
+    port: null,
+    hostname: 'example.com',
+    hash: null,
+    search: null,
+    query: null,
+    pathname: '/',
+    path: '/',
+    href: 'http://example.com/'
+  }
 };
 
 for (const u in parseTests) {