http: optimize short path validation

PR-URL: #10654
Reviewed-By: James M Snell <[email protected]>
Reviewed-By: Fedor Indutny <[email protected]>

Author: mscdex

lib/_http_client.js

@@ -15,6 +15,34 @@ const Agent = require('_http_agent');
 const Buffer = require('buffer').Buffer;
 const urlToOptions = require('internal/url').urlToOptions;
 
+// 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;
+}
+
 function ClientRequest(options, cb) {
   var self = this;
   OutgoingMessage.call(self);
@@ -45,14 +73,20 @@ function ClientRequest(options, cb) {
   if (self.agent && self.agent.protocol)
     expectedProtocol = self.agent.protocol;
 
-  if (options.path && /[\u0000-\u0020]/.test(options.path)) {
-    // The actual regex 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.
-    // Restrict the filter to control characters and spaces.
-    throw new TypeError('Request path contains unescaped characters');
-  } else if (protocol !== expectedProtocol) {
+  var path;
+  if (options.path) {
+    path = '' + 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)
+      throw new TypeError('Request path contains unescaped characters');
+  }
+
+  if (protocol !== expectedProtocol) {
     throw new Error('Protocol "' + protocol + '" not supported. ' +
                     'Expected "' + expectedProtocol + '"');
   }