http: speed up checkIsHttpToken

The Regex implementation is not faster than ascii code compare. the field name is shorter, the speed is faster. benchmark result here: https://bitbucket.org/snippets/JacksonTian/Rnbad/benchmark-result PR-URL: nodejs#4790 Reviewed-By: James M Snell <[email protected]> Reviewed-By: Brian White <[email protected]>
lefrog · Mar 27, 2016 · 089c6a4 · 089c6a4
1 parent 293fd04
commit 089c6a4
Show file tree

Hide file tree

Showing 2 changed files with 100 additions and 2 deletions.
diff --git a/benchmark/http/check_is_http_token.js b/benchmark/http/check_is_http_token.js
@@ -0,0 +1,52 @@
+'use strict';
+
+const common = require('../common.js');
+const _checkIsHttpToken = require('_http_common')._checkIsHttpToken;
+
+const bench = common.createBenchmark(main, {
+  key: [
+    'TCN',
+    'ETag',
+    'date',
+    'Vary',
+    'server',
+    'Server',
+    'status',
+    'version',
+    'Expires',
+    'alt-svc',
+    'location',
+    'Connection',
+    'Keep-Alive',
+    'content-type',
+    'Content-Type',
+    'Cache-Control',
+    'Last-Modified',
+    'Accept-Ranges',
+    'content-length',
+    'x-frame-options',
+    'x-xss-protection',
+    'Content-Encoding',
+    'Content-Location',
+    'Transfer-Encoding',
+    'alternate-protocol',
+    ':', // invalid input
+    '@@',
+    '中文呢', // unicode
+    '((((())))', // invalid
+    ':alternate-protocol', // fast bailout
+    'alternate-protocol:' // slow bailout
+  ],
+  n: [1e6],
+});
+
+function main(conf) {
+  var n = +conf.n;
+  var key = conf.key;
+
+  bench.start();
+  for (var i = 0; i < n; i++) {
+    _checkIsHttpToken(key);
+  }
+  bench.end(n);
+}
diff --git a/lib/_http_common.js b/lib/_http_common.js
@@ -225,10 +225,56 @@ exports.httpSocketSetup = httpSocketSetup;
 /**
  * Verifies that the given val is a valid HTTP token
  * per the rules defined in RFC 7230
+ * See https://tools.ietf.org/html/rfc7230#section-3.2.6
+ *
+ * This implementation of checkIsHttpToken() loops over the string instead of
+ * using a regular expression since the former is up to 180% faster with v8 4.9
+ * depending on the string length (the shorter the string, the larger the
+ * performance difference)
  **/
-const token = /^[a-zA-Z0-9_!#$%&'*+.^`|~-]+$/;
 function checkIsHttpToken(val) {
-  return typeof val === 'string' && token.test(val);
+  if (typeof val !== 'string' || val.length === 0)
+    return false;
+
+  for (var i = 0, len = val.length; i < len; i++) {
+    var ch = val.charCodeAt(i);
+
+    if (ch >= 65 && ch <= 90) // A-Z
+      continue;
+
+    if (ch >= 97 && ch <= 122) // a-z
+      continue;
+
+    // ^ => 94
+    // _ => 95
+    // ` => 96
+    // | => 124
+    // ~ => 126
+    if (ch === 94 || ch === 95 || ch === 96 || ch === 124 || ch === 126)
+      continue;
+
+    if (ch >= 48 && ch <= 57) // 0-9
+      continue;
+
+    // ! => 33
+    // # => 35
+    // $ => 36
+    // % => 37
+    // & => 38
+    // ' => 39
+    // * => 42
+    // + => 43
+    // - => 45
+    // . => 46
+    if (ch >= 33 && ch <= 46) {
+      if (ch === 34 || ch === 40 || ch === 41 || ch === 44)
+        return false;
+      continue;
+    }
+
+    return false;
+  }
+  return true;
 }
 exports._checkIsHttpToken = checkIsHttpToken;