11 files changed, 482 insertions, 0 deletions
diff --git a/js/src/tests/non262/Unicode/browser.js b/js/src/tests/non262/Unicode/browser.js
new file mode 100644
index 0000000000..e69de29bb2
--- /dev/null
+++ b/js/src/tests/non262/Unicode/browser.js
diff --git a/js/src/tests/non262/Unicode/non-bmp-non-spaces.js b/js/src/tests/non262/Unicode/non-bmp-non-spaces.js
new file mode 100644
index 0000000000..809eb81d28
--- /dev/null
+++ b/js/src/tests/non262/Unicode/non-bmp-non-spaces.js
@@ -0,0 +1,60 @@
+/* -*- indent-tabs-mode: nil; js-indent-level: 4 -*-
+ * This Source Code Form is subject to the terms of the Mozilla Public
+ * License, v. 2.0. If a copy of the MPL was not distributed with this
+ * file, You can obtain one at http://mozilla.org/MPL/2.0/. */
+
+// White space must not be determined by truncating char32_t to char16_t.
+
+assertThrowsInstanceOf(() => eval("\u{40008}"), SyntaxError);
+assertThrowsInstanceOf(() => eval("\u{40009}"), SyntaxError); // U+0009 CHARACTER TABULATION
+assertThrowsInstanceOf(() => eval("\u{4000A}"), SyntaxError); // U+000A LINE FEED
+assertThrowsInstanceOf(() => eval("\u{4000B}"), SyntaxError); // U+000B LINE TABULATION
+assertThrowsInstanceOf(() => eval("\u{4000C}"), SyntaxError); // U+000C FORM FEED
+assertThrowsInstanceOf(() => eval("\u{4000D}"), SyntaxError); // U+000D CARRIAGE RETURN
+assertThrowsInstanceOf(() => eval("\u{4000E}"), SyntaxError);
+
+assertThrowsInstanceOf(() => eval("\u{4001F}"), SyntaxError);
+assertThrowsInstanceOf(() => eval("\u{40020}"), SyntaxError); // U+0020 SPACE
+assertThrowsInstanceOf(() => eval("\u{40021}"), SyntaxError);
+
+assertThrowsInstanceOf(() => eval("\u{4009F}"), SyntaxError);
+assertThrowsInstanceOf(() => eval("\u{400A0}"), SyntaxError); // U+00A0 NO-BREAK SPACE
+assertThrowsInstanceOf(() => eval("\u{400A1}"), SyntaxError);
+
+assertThrowsInstanceOf(() => eval("\u{4167F}"), SyntaxError);
+assertThrowsInstanceOf(() => eval("\u{41680}"), SyntaxError); // U+1680 OGHAM SPACE MARK
+assertThrowsInstanceOf(() => eval("\u{41681}"), SyntaxError);
+
+assertThrowsInstanceOf(() => eval("\u{41FFF}"), SyntaxError);
+assertThrowsInstanceOf(() => eval("\u{42000}"), SyntaxError); // U+2000 EN QUAD
+assertThrowsInstanceOf(() => eval("\u{42001}"), SyntaxError); // U+2001 EM QUAD
+assertThrowsInstanceOf(() => eval("\u{42002}"), SyntaxError); // U+2002 EN SPACE
+assertThrowsInstanceOf(() => eval("\u{42003}"), SyntaxError); // U+2003 EM SPACE
+assertThrowsInstanceOf(() => eval("\u{42004}"), SyntaxError); // U+2004 THREE-PER-EM SPACE
+assertThrowsInstanceOf(() => eval("\u{42005}"), SyntaxError); // U+2005 FOUR-PER-EM SPACE
+assertThrowsInstanceOf(() => eval("\u{42006}"), SyntaxError); // U+2006 SIX-PER-EM SPACE
+assertThrowsInstanceOf(() => eval("\u{42007}"), SyntaxError); // U+2007 FIGURE SPACE
+assertThrowsInstanceOf(() => eval("\u{42008}"), SyntaxError); // U+2008 PUNCTUATION SPACE
+assertThrowsInstanceOf(() => eval("\u{42009}"), SyntaxError); // U+2009 THIN SPACE
+assertThrowsInstanceOf(() => eval("\u{4200A}"), SyntaxError); // U+200A HAIR SPACE
+assertThrowsInstanceOf(() => eval("\u{4200B}"), SyntaxError);
+
+assertThrowsInstanceOf(() => eval("\u{42027}"), SyntaxError);
+assertThrowsInstanceOf(() => eval("\u{42028}"), SyntaxError); // U+2028 LINE SEPARATOR
+assertThrowsInstanceOf(() => eval("\u{42029}"), SyntaxError); // U+2028 PARAGRAPH SEPARATOR
+assertThrowsInstanceOf(() => eval("\u{4202A}"), SyntaxError);
+
+assertThrowsInstanceOf(() => eval("\u{4202E}"), SyntaxError);
+assertThrowsInstanceOf(() => eval("\u{4202F}"), SyntaxError); // U+202F NARROW NO-BREAK SPACE
+assertThrowsInstanceOf(() => eval("\u{42030}"), SyntaxError);
+
+assertThrowsInstanceOf(() => eval("\u{4205E}"), SyntaxError);
+assertThrowsInstanceOf(() => eval("\u{4205F}"), SyntaxError); // U+205F MEDIUM MATHEMATICAL SPACE
+assertThrowsInstanceOf(() => eval("\u{42060}"), SyntaxError);
+
+assertThrowsInstanceOf(() => eval("\u{42FFF}"), SyntaxError);
+assertThrowsInstanceOf(() => eval("\u{43000}"), SyntaxError); // U+3000 IDEOGRAPHIC SPACE
+assertThrowsInstanceOf(() => eval("\u{43001}"), SyntaxError);
+
+if (typeof reportCompare === "function")
+  reportCompare(true, true);
diff --git a/js/src/tests/non262/Unicode/regress-352044-01.js b/js/src/tests/non262/Unicode/regress-352044-01.js
new file mode 100644
index 0000000000..bdbb4371b9
--- /dev/null
+++ b/js/src/tests/non262/Unicode/regress-352044-01.js
@@ -0,0 +1,36 @@
+/* -*- indent-tabs-mode: nil; js-indent-level: 2 -*- */
+/* This Source Code Form is subject to the terms of the Mozilla Public
+ * License, v. 2.0. If a copy of the MPL was not distributed with this
+ * file, You can obtain one at http://mozilla.org/MPL/2.0/. */
+
+//-----------------------------------------------------------------------------
+var BUGNUMBER = 352044;
+var summary = 'issues with Unicode escape sequences in JavaScript source code';
+var actual = '';
+var expect = '';
+
+
+//-----------------------------------------------------------------------------
+test();
+//-----------------------------------------------------------------------------
+
+function test()
+{
+  printBugNumber(BUGNUMBER);
+  printStatus (summary);
+ 
+  expect = 'SyntaxError';
+
+  try
+  {
+    var i = 1;
+    eval('i \\u002b= 1'); 
+    print(i);
+  }
+  catch(ex)
+  {
+    actual = ex.constructor.name;
+  }
+
+  reportCompare(expect, actual, summary);
+}
diff --git a/js/src/tests/non262/Unicode/regress-352044-02-n.js b/js/src/tests/non262/Unicode/regress-352044-02-n.js
new file mode 100644
index 0000000000..d3f41c3e8a
--- /dev/null
+++ b/js/src/tests/non262/Unicode/regress-352044-02-n.js
@@ -0,0 +1,36 @@
+/* -*- indent-tabs-mode: nil; js-indent-level: 2 -*- */
+/* This Source Code Form is subject to the terms of the Mozilla Public
+ * License, v. 2.0. If a copy of the MPL was not distributed with this
+ * file, You can obtain one at http://mozilla.org/MPL/2.0/. */
+
+//-----------------------------------------------------------------------------
+var BUGNUMBER = 352044;
+var summary = 'issues with Unicode escape sequences in JavaScript source code';
+var actual = 'No Error';
+var expect = 'SyntaxError';
+
+
+//-----------------------------------------------------------------------------
+test();
+//-----------------------------------------------------------------------------
+
+function test()
+{
+  printBugNumber(BUGNUMBER);
+  printStatus (summary);
+
+  print('This test case is expected to throw an uncaught SyntaxError');
+
+  try
+  {
+    var i = 1;
+    i \u002b= 1; 
+    print(i);
+  }
+  catch(ex)
+  {
+    actual = ex + '';
+  }
+
+  reportCompare(expect, actual, summary);
+}
diff --git a/js/src/tests/non262/Unicode/shell.js b/js/src/tests/non262/Unicode/shell.js
new file mode 100644
index 0000000000..e69de29bb2
--- /dev/null
+++ b/js/src/tests/non262/Unicode/shell.js
diff --git a/js/src/tests/non262/Unicode/uc-001-n.js b/js/src/tests/non262/Unicode/uc-001-n.js
new file mode 100644
index 0000000000..4ac78b5c2c
--- /dev/null
+++ b/js/src/tests/non262/Unicode/uc-001-n.js
@@ -0,0 +1,23 @@
+/* -*- tab-width: 8; indent-tabs-mode: nil; js-indent-level: 4 -*-
+ * This Source Code Form is subject to the terms of the Mozilla Public
+ * License, v. 2.0. If a copy of the MPL was not distributed with this
+ * file, You can obtain one at http://mozilla.org/MPL/2.0/. */
+
+var BUGNUMBER = 23612;
+
+test();
+
+function test()
+{
+  printStatus ("Unicode Characters 1C-1F negative test.");
+  printBugNumber (BUGNUMBER);
+   
+  reportCompare ("error", eval ("'no'\u001C+' error'"),
+		 "Unicode whitespace test (1C.)");
+  reportCompare ("error", eval ("'no'\u001D+' error'"),
+		 "Unicode whitespace test (1D.)");
+  reportCompare ("error", eval ("'no'\u001E+' error'"),
+		 "Unicode whitespace test (1E.)");
+  reportCompare ("error", eval ("'no'\u001F+' error'"),
+		 "Unicode whitespace test (1F.)");
+}
diff --git a/js/src/tests/non262/Unicode/uc-002-n.js b/js/src/tests/non262/Unicode/uc-002-n.js
new file mode 100644
index 0000000000..5b1512a70e
--- /dev/null
+++ b/js/src/tests/non262/Unicode/uc-002-n.js
@@ -0,0 +1,14 @@
+/* -*- indent-tabs-mode: nil; js-indent-level: 4 -*-
+ * This Source Code Form is subject to the terms of the Mozilla Public
+ * License, v. 2.0. If a copy of the MPL was not distributed with this
+ * file, You can obtain one at http://mozilla.org/MPL/2.0/. */
+
+var BUGNUMBER = 23607;
+DESCRIPTION = "Non-character escapes in identifiers negative test.";
+
+printStatus ("Non-character escapes in identifiers negative test.");
+printBugNumber (BUGNUMBER);
+
+eval("\u0020 = 5");
+reportCompare('PASS', 'FAIL', "Previous statement should have thrown an error.");
+
diff --git a/js/src/tests/non262/Unicode/uc-002.js b/js/src/tests/non262/Unicode/uc-002.js
new file mode 100644
index 0000000000..e96d95d377
--- /dev/null
+++ b/js/src/tests/non262/Unicode/uc-002.js
@@ -0,0 +1,21 @@
+/* -*- tab-width: 8; indent-tabs-mode: nil; js-indent-level: 4 -*-
+ * This Source Code Form is subject to the terms of the Mozilla Public
+ * License, v. 2.0. If a copy of the MPL was not distributed with this
+ * file, You can obtain one at http://mozilla.org/MPL/2.0/. */
+
+var BUGNUMBER = 23613;
+
+test();
+
+function test()
+{
+  printStatus ("Unicode non-breaking space character test.");
+  printBugNumber (BUGNUMBER);
+
+  reportCompare ("no error", eval("'no'\u00A0+ ' error'"),
+		 "Unicode non-breaking space character test.");
+
+  var str = "\u00A0foo";
+  reportCompare (0, str.search(/^\sfoo$/),
+		 "Unicode non-breaking space character regexp test.");
+}
diff --git a/js/src/tests/non262/Unicode/uc-003.js b/js/src/tests/non262/Unicode/uc-003.js
new file mode 100644
index 0000000000..12207809ad
--- /dev/null
+++ b/js/src/tests/non262/Unicode/uc-003.js
@@ -0,0 +1,27 @@
+/* -*- tab-width: 8; indent-tabs-mode: nil; js-indent-level: 4 -*-
+ * This Source Code Form is subject to the terms of the Mozilla Public
+ * License, v. 2.0. If a copy of the MPL was not distributed with this
+ * file, You can obtain one at http://mozilla.org/MPL/2.0/. */
+
+var BUGNUMBER = 23608;
+var BUGNUMBER = 23607;
+
+test();
+
+function test()
+{
+  var \u0041 = 5;
+  var A\u03B2 = 15;
+
+  printStatus ("Escapes in identifiers test.");
+  printBugNumber (BUGNUMBER);
+
+  reportCompare (5, eval("\u0041"),
+		 "Escaped ASCII Identifier test.");
+  reportCompare (6, eval("++\u0041"),
+		 "Escaped ASCII Identifier test");
+  reportCompare (15, eval("A\u03B2"),
+		 "Escaped non-ASCII Identifier test");
+  reportCompare (16, eval("++A\u03B2"),
+		 "Escaped non-ASCII Identifier test");
+}
diff --git a/js/src/tests/non262/Unicode/uc-004.js b/js/src/tests/non262/Unicode/uc-004.js
new file mode 100644
index 0000000000..4490753491
--- /dev/null
+++ b/js/src/tests/non262/Unicode/uc-004.js
@@ -0,0 +1,26 @@
+/* -*- tab-width: 8; indent-tabs-mode: nil; js-indent-level: 4 -*-
+ * This Source Code Form is subject to the terms of the Mozilla Public
+ * License, v. 2.0. If a copy of the MPL was not distributed with this
+ * file, You can obtain one at http://mozilla.org/MPL/2.0/. */
+
+var BUGNUMBER = 23612;
+
+test();
+
+function test()
+{
+  printStatus ("Unicode Characters 1C-1F with regexps test.");
+  printBugNumber (BUGNUMBER);
+   
+  var ary = ["\u001Cfoo", "\u001Dfoo", "\u001Efoo", "\u001Ffoo"];
+   
+  for (var i in ary)
+  {      
+    reportCompare (0, ary[Number(i)].search(/^\Sfoo$/),
+		   "Unicode characters 1C-1F in regexps, ary[" +
+		   i + "] did not match \\S test (it should not.)");
+    reportCompare (-1, ary[Number(i)].search(/^\sfoo$/),
+		   "Unicode characters 1C-1F in regexps, ary[" +
+		   i + "] matched \\s test (it should not.)");
+  }
+}
diff --git a/js/src/tests/non262/Unicode/uc-005.js b/js/src/tests/non262/Unicode/uc-005.js
new file mode 100644
index 0000000000..fe28b460fc
--- /dev/null
+++ b/js/src/tests/non262/Unicode/uc-005.js
@@ -0,0 +1,239 @@
+/* -*- indent-tabs-mode: nil; js-indent-level: 2 -*- */
+/* This Source Code Form is subject to the terms of the Mozilla Public
+ * License, v. 2.0. If a copy of the MPL was not distributed with this
+ * file, You can obtain one at http://mozilla.org/MPL/2.0/. */
+
+/*
+ *
+ * Date:    15 July 2002
+ * SUMMARY: Testing identifiers with double-byte names
+ * See http://bugzilla.mozilla.org/show_bug.cgi?id=58274
+ *
+ * Here is a sample of the problem:
+ *
+ *    js> function f\u02B1 () {}
+ *
+ *    js> f\u02B1.toSource();
+ *    function f¦() {}
+ *
+ *    js> f\u02B1.toSource().toSource();
+ *    (new String("function f\xB1() {}"))
+ *
+ *
+ * See how the high-byte information (the 02) has been lost?
+ * The same thing was happening with the toString() method:
+ *
+ *    js> f\u02B1.toString();
+ *
+ *    function f¦() {
+ *    }
+ *
+ *    js> f\u02B1.toString().toSource();
+ *    (new String("\nfunction f\xB1() {\n}\n"))
+ *
+ */
+//-----------------------------------------------------------------------------
+var UBound = 0;
+var BUGNUMBER = 58274;
+var summary = 'Testing identifiers with double-byte names';
+var status = '';
+var statusitems = [];
+var actual = '';
+var actualvalues = [];
+var expect= '';
+var expectedvalues = [];
+
+
+/*
+ * Define a function that uses double-byte identifiers in
+ * "every possible way"
+ *
+ * Then recover each double-byte identifier via f.toString().
+ * To make this easier, put a 'Z' token before every one.
+ *
+ * Our eval string will be:
+ *
+ * sEval = "function Z\u02b1(Z\u02b2, b) {
+ *          try { Z\u02b3 : var Z\u02b4 = Z\u02b1; }
+ *          catch (Z\u02b5) { for (var Z\u02b6 in Z\u02b5)
+ *          {for (1; 1<0; Z\u02b7++) {new Array()[Z\u02b6] = 1;} };} }";
+ *
+ * It will be helpful to build this string in stages:
+ */
+var s0 =  'function Z';
+var s1 =  '\u02b1(Z';
+var s2 =  '\u02b2, b) {try { Z';
+var s3 =  '\u02b3 : var Z';
+var s4 =  '\u02b4 = Z';
+var s5 =  '\u02b1; } catch (Z'
+  var s6 =  '\u02b5) { for (var Z';
+var s7 =  '\u02b6 in Z';
+var s8 =  '\u02b5){for (1; 1<0; Z';
+var s9 =  '\u02b7++) {new Array()[Z';
+var s10 = '\u02b6] = 1;} };} }';
+
+
+/*
+ * Concatenate these and eval() to create the function Z\u02b1
+ */
+var sEval = s0 + s1 + s2 + s3 + s4 + s5 + s6 + s7 + s8 + s9 + s10;
+eval(sEval);
+
+
+/*
+ * Recover all the double-byte identifiers via Z\u02b1.toString().
+ * We'll recover the 1st one as arrID[1], the 2nd one as arrID[2],
+ * and so on ...
+ */
+var arrID = getIdentifiers(Z\u02b1);
+
+
+/*
+ * Now check that we got back what we put in -
+ */
+status = inSection(1);
+actual = arrID[1];
+expect = s1.charAt(0);
+addThis();
+
+status = inSection(2);
+actual = arrID[2];
+expect = s2.charAt(0);
+addThis();
+
+status = inSection(3);
+actual = arrID[3];
+expect = s3.charAt(0);
+addThis();
+
+status = inSection(4);
+actual = arrID[4];
+expect = s4.charAt(0);
+addThis();
+
+status = inSection(5);
+actual = arrID[5];
+expect = s5.charAt(0);
+addThis();
+
+status = inSection(6);
+actual = arrID[6];
+expect = s6.charAt(0);
+addThis();
+
+status = inSection(7);
+actual = arrID[7];
+expect = s7.charAt(0);
+addThis();
+
+status = inSection(8);
+actual = arrID[8];
+expect = s8.charAt(0);
+addThis();
+
+status = inSection(9);
+actual = arrID[9];
+expect = s9.charAt(0);
+addThis();
+
+status = inSection(10);
+actual = arrID[10];
+expect = s10.charAt(0);
+addThis();
+
+
+
+
+//-----------------------------------------------------------------------------
+test();
+//-----------------------------------------------------------------------------
+
+
+
+/*
+ * Goal: recover the double-byte identifiers from f.toString()
+ * by getting the very next character after each 'Z' token.
+ *
+ * The return value will be an array |arr| indexed such that
+ * |arr[1]| is the 1st identifier, |arr[2]| the 2nd, and so on.
+ *
+ * Note, however, f.toString() is implementation-independent.
+ * For example, it may begin with '\nfunction' instead of 'function'.
+ *
+ * Rhino uses a Unicode representation for f.toString(); whereas
+ * SpiderMonkey uses an ASCII representation, putting escape sequences
+ * for non-ASCII characters. For example, if a function is called f\u02B1,
+ * then in Rhino the toString() method will present a 2-character Unicode
+ * string for its name, whereas SpiderMonkey will present a 7-character
+ * ASCII string for its name: the string literal 'f\u02B1'.
+ *
+ * So we force the lexer to condense the string before we use it.
+ * This will give uniform results in Rhino and SpiderMonkey.
+ */
+function getIdentifiers(f)
+{
+  var str = condenseStr(f.toString());
+  var arr = str.split('Z');
+
+  /*
+   * The identifiers are the 1st char of each split substring
+   * EXCEPT the first one, which is just ('\n' +) 'function '.
+   *
+   * Thus note the 1st identifier will be stored in |arr[1]|,
+   * the 2nd one in |arr[2]|, etc., making the indexing easy -
+   */
+  for (i in arr)
+    arr[i] = arr[i].charAt(0);
+  return arr;
+}
+
+
+/*
+ * This function is the opposite of a functions like escape(), which take
+ * Unicode characters and return escape sequences for them. Here, we force
+ * the lexer to turn escape sequences back into single characters.
+ *
+ * Note we can't simply do |eval(str)|, since in practice |str| will be an
+ * identifier somewhere in the program (e.g. a function name); thus |eval(str)|
+ * would return the object that the identifier represents: not what we want.
+ *
+ * So we surround |str| lexicographically with quotes to force the lexer to
+ * evaluate it as a string. Have to strip out any linefeeds first, however -
+ */
+function condenseStr(str)
+{
+  /*
+   * You won't be able to do the next step if |str| has
+   * any carriage returns or linefeeds in it. For example:
+   *
+   *  js> eval("'" + '\nHello' + "'");
+   *  1: SyntaxError: unterminated string literal:
+   *  1: '
+   *  1: ^
+   *
+   * So replace them with the empty string -
+   */
+  str = str.replace(/[\r\n]/g, '')
+    return eval("'" + str + "'")
+    }
+
+
+function addThis()
+{
+  statusitems[UBound] = status;
+  actualvalues[UBound] = actual;
+  expectedvalues[UBound] = expect;
+  UBound++;
+}
+
+
+function test()
+{
+  printBugNumber(BUGNUMBER);
+  printStatus(summary);
+
+  for (var i=0; i<UBound; i++)
+  {
+    reportCompare(expectedvalues[i], actualvalues[i], statusitems[i]);
+  }
+}