Fast path for the regexp of bounded words.

test/mjsunit/string-replace-word-boundary.js

+// Copyright 2012 the V8 project authors. All rights reserved.
+// Redistribution and use in source and binary forms, with or without
+// modification, are permitted provided that the following conditions are
+// met:
+//
+//     * Redistributions of source code must retain the above copyright
+//       notice, this list of conditions and the following disclaimer.
+//     * Redistributions in binary form must reproduce the above
+//       copyright notice, this list of conditions and the following
+//       disclaimer in the documentation and/or other materials provided
+//       with the distribution.
+//     * Neither the name of Google Inc. nor the names of its
+//       contributors may be used to endorse or promote products derived
+//       from this software without specific prior written permission.
+//
+// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+function replace(match) { return '\u1234'; }
+
+assertEquals("\u1234", "Abz".replace(/\b\w+\b/g, replace));
+assertEquals("\u1234 ", "ABZ ".replace(/\b\w+\b/g, replace));
+assertEquals(" \u1234", " aBz".replace(/\b\w+\b/g, replace));
+assertEquals(" \u1234 ", " AbZ ".replace(/\b\w+\b/g, replace));
+assertEquals("\u1234-\u1234", "ABZ-012".replace(/\b\w+\b/g, replace));
+assertEquals(" \u1234-\u1234", " ABz-01_".replace(/\b\w+\b/g, replace));
+assertEquals("\u1234-\u1234 ", "ab_-012 ".replace(/\b\w+\b/g, replace));
+assertEquals(" \u1234-\u1234 ", " A_z-012 ".replace(/\b\w+\b/g, replace));
+assertEquals("!~", "!~".replace(/\b\w+\b/g, replace));
+assertEquals("", "".replace(/\b\w+\b/g, replace));
+
+var string = '';
+var expected = '';
+for (var i = 0; i < 100000; i++) {
+  var c = String.fromCharCode(i * 3 % 128);
+  string += c;
+  if ((c >= '0' && c <= '9') ||
+      (c >= 'a' && c <= 'z') ||
+      (c >= 'A' && c <= 'Z') || c == '_') {
+    expected += '\u1234';
+  } else {
+    expected += c;
+  }
+}
+
+var string = string.replace(/\b\w+\b/g, replace);
+var expected = expected.replace(/\u1234+/g, '\u1234');
+assertEquals(expected, string);