Improved performance for our adler32 implementation

src/shared/utils/__tests__/adler32-test.js

@@ -0,0 +1,41 @@
+/**
+ * Copyright 2014-2015, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under the BSD-style license found in the
+ * LICENSE file in the root directory of this source tree. An additional grant
+ * of patent rights can be found in the PATENTS file in the same directory.
+ *
+ * @emails react-core
+ */
+
+'use strict';
+
+var adler32 = require('adler32');
+
+describe('shallowEqual', function() {
+  it('generates differing checksums', function() {
+    expect(adler32('foo')).not.toBe(adler32('bar'));
+  });
+
+  it('generates consistent checksums', function() {
+    expect(adler32('linux')).toBe(adler32('linux'));
+  });
+
+  it('is case sensitive', function() {
+    expect(adler32('a')).not.toBe(adler32('A'));
+  });
+
+  it('doesn\'t barf on large inputs', function() {
+    var str = '';
+    for (var i = 0; i < 100000; i++) {
+      str = str + 'This will be repeated to be very large indeed. ';
+    }
+    expect(adler32(str)).toBe(692898118);
+  });
+
+  it('doesn\'t barf on international inputs', function() {
+    var str = 'Linux 是一個真棒操作系統!';
+    expect(adler32(str)).toBe(-1183804097);
+  });
+});

src/shared/utils/adler32.js

@@ -13,17 +13,34 @@
 
 var MOD = 65521;
 
-// This is a clean-room implementation of adler32 designed for detecting
-// if markup is not what we expect it to be. It does not need to be
-// cryptographically strong, only reasonably good at detecting if markup
-// generated on the server is different than that on the client.
+// adler32 is not cryptographically strong, and is only used to sanity check that
+// markup generated on the server matches the markup generated on the client.
+// This implementation (a modified version of the SheetJS version) has been optimized
+// for our use case, at the expense of conforming to the adler32 specification
+// for non-ascii inputs.
 function adler32(data) {
   var a = 1;
   var b = 0;
-  for (var i = 0; i < data.length; i++) {
-    a = (a + data.charCodeAt(i)) % MOD;
-    b = (b + a) % MOD;
+  var i = 0;
+  var l = data.length;
+  var m = l & ~0x3;
+  while (i < m) {
+    for (; i < Math.min(i + 4096, m); i += 4) {
+      b += (
+        (a += data.charCodeAt(i)) +
+        (a += data.charCodeAt(i + 1)) +
+        (a += data.charCodeAt(i + 2)) +
+        (a += data.charCodeAt(i + 3))
+      );
+    }
+    a %= MOD;
+    b %= MOD;
   }
+  for (; i < l; i++) {
+    b += (a += data.charCodeAt(i));
+  }
+  a %= MOD;
+  b %= MOD;
   return a | (b << 16);
 }