Add tests for surrogate pairs with RegExp atoms (#722)

test/language/literals/regexp/u-surrogate-pairs-atom-char-class.js

@@ -0,0 +1,33 @@
+// Copyright (C) 2016 the V8 project authors. All rights reserved.
+// This code is governed by the BSD license found in the LICENSE file.
+/*---
+esid: sec-atom
+es6id: 21.2.2.8
+description: >
+  Support for surrogate pairs within patterns match by the CharacterClass Atom
+info: |
+  The production Atom :: CharacterClass evaluates as follows:
+
+  1. Evaluate CharacterClass to obtain a CharSet A and a Boolean invert.
+  2. Call CharacterSetMatcher(A, invert) and return its Matcher result. 
+
+  Runtime Semantics: CharacterSetMatcher Abstract Operation
+
+  1. Return an internal Matcher closure that takes two arguments, a State x and
+     a Continuation c, and performs the following steps when evaluated:
+     [...]
+     d. Let cc be Canonicalize(ch).
+     [...]
+---*/
+
+assert(/^[\ud800\udc00]$/u.test('\ud800\udc00'));
+assert.sameValue(
+  /[\ud800\udc00]/u.test('\ud800'),
+  false,
+  '\\ud800 does not qualify as a class member'
+);
+assert.sameValue(
+  /[\ud800\udc00]/u.test('\udc00'),
+  false,
+  '\\udc00 does not qualify as a class member'
+);

test/language/literals/regexp/u-surrogate-pairs-atom-dot.js

@@ -0,0 +1,23 @@
+// Copyright (C) 2016 the V8 project authors. All rights reserved.
+// This code is governed by the BSD license found in the LICENSE file.
+/*---
+esid: sec-atom
+es6id: 21.2.2.8
+description: >
+  Support for surrogate pairs within patterns match by the "period" Atom
+info: |
+  The production Atom :: . evaluates as follows:
+
+  1. Let A be the set of all characters except LineTerminator.
+  2. Call CharacterSetMatcher(A, false) and return its Matcher result. 
+
+  Runtime Semantics: CharacterSetMatcher Abstract Operation
+
+  1. Return an internal Matcher closure that takes two arguments, a State x and
+     a Continuation c, and performs the following steps when evaluated:
+     [...]
+     d. Let cc be Canonicalize(ch).
+     [...]
+---*/
+
+assert(/^.$/u.test('\ud800\udc00'));

test/language/literals/regexp/u-surrogate-pairs-atom-escape-char-class.js

@@ -0,0 +1,24 @@
+// Copyright (C) 2016 the V8 project authors. All rights reserved.
+// This code is governed by the BSD license found in the LICENSE file.
+/*---
+esid: sec-atomescape
+es6id: 21.2.2.9
+description: >
+  Support for surrogate pairs within patterns match by the CharacterClassEscape
+  AtomEscape
+info: |
+  The production AtomEscape :: CharacterClassEscape evaluates as follows:
+
+  1. Evaluate CharacterClassEscape to obtain a CharSet A.
+  2. Call CharacterSetMatcher(A, false) and return its Matcher result. 
+
+  Runtime Semantics: CharacterSetMatcher Abstract Operation
+
+  1. Return an internal Matcher closure that takes two arguments, a State x and
+     a Continuation c, and performs the following steps when evaluated:
+     [...]
+     d. Let cc be Canonicalize(ch).
+     [...]
+---*/
+
+assert(/^\S$/u.test('\ud800\udc00'));

test/language/literals/regexp/u-surrogate-pairs-atom-escape-decimal.js

@@ -0,0 +1,29 @@
+// Copyright (C) 2016 the V8 project authors. All rights reserved.
+// This code is governed by the BSD license found in the LICENSE file.
+/*---
+esid: sec-atomescape
+es6id: 21.2.2.9
+description: >
+  Support for surrogate pairs within patterns match by the DecimalEscape
+  AtomEscape
+info: |
+  The production AtomEscape :: DecimalEscape evaluates as follows:
+
+  [...]
+  3. Return an internal Matcher closure that takes two arguments, a State x and
+     a Continuation c, and performs the following steps:
+     [...]
+     h. If there exists an integer i between 0 (inclusive) and len (exclusive)
+        such that Canonicalize(s[i]) is not the same character value as
+        Canonicalize(Input[e+i]), return failure.
+
+  Runtime Semantics: CharacterSetMatcher Abstract Operation
+
+  1. Return an internal Matcher closure that takes two arguments, a State x and
+     a Continuation c, and performs the following steps when evaluated:
+     [...]
+     d. Let cc be Canonicalize(ch).
+     [...]
+---*/
+
+assert.sameValue(/(.+).*\1/u.test('\ud800\udc00\ud800'), false);