1 /* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
2 /* ***** BEGIN LICENSE BLOCK *****
3 * Version: MPL 1.1/GPL 2.0/LGPL 2.1
5 * The contents of this file are subject to the Mozilla Public License Version
6 * 1.1 (the "License"); you may not use this file except in compliance with
7 * the License. You may obtain a copy of the License at
8 * http://www.mozilla.org/MPL/
10 * Software distributed under the License is distributed on an "AS IS" basis,
11 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
12 * for the specific language governing rights and limitations under the
15 * The Original Code is JavaScript Engine testing utilities.
17 * The Initial Developer of the Original Code is
18 * Netscape Communications Corp.
19 * Portions created by the Initial Developer are Copyright (C) 2002
20 * the Initial Developer. All Rights Reserved.
23 * rogerl@netscape.com, pschwartau@netscape.com
25 * Alternatively, the contents of this file may be used under the terms of
26 * either the GNU General Public License Version 2 or later (the "GPL"), or
27 * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
28 * in which case the provisions of the GPL or the LGPL are applicable instead
29 * of those above. If you wish to allow use of your version of this file only
30 * under the terms of either the GPL or the LGPL, and not to allow others to
31 * use your version of this file under the terms of the MPL, indicate your
32 * decision by deleting the provisions above and replace them with the notice
33 * and other provisions required by the GPL or the LGPL. If you do not delete
34 * the provisions above, a recipient may use your version of this file under
35 * the terms of any one of the MPL, the GPL or the LGPL.
37 * ***** END LICENSE BLOCK ***** */
42 * SUMMARY: Testing identifiers with double-byte names
43 * See http://bugzilla.mozilla.org/show_bug.cgi?id=58274
45 * Here is a sample of the problem:
47 * js> function f\u02B1 () {}
49 * js> f\u02B1.toSource();
52 * js> f\u02B1.toSource().toSource();
53 * (new String("function f\xB1() {}"))
56 * See how the high-byte information (the 02) has been lost?
57 * The same thing was happening with the toString() method:
59 * js> f\u02B1.toString();
64 * js> f\u02B1.toString().toSource();
65 * (new String("\nfunction f\xB1() {\n}\n"))
68 //-----------------------------------------------------------------------------
70 var BUGNUMBER = 58274;
71 var summary = 'Testing identifiers with double-byte names';
75 var actualvalues = [];
77 var expectedvalues = [];
81 * Define a function that uses double-byte identifiers in
82 * "every possible way"
84 * Then recover each double-byte identifier via f.toString().
85 * To make this easier, put a 'Z' token before every one.
87 * Our eval string will be:
89 * sEval = "function Z\u02b1(Z\u02b2, b) {
90 * try { Z\u02b3 : var Z\u02b4 = Z\u02b1; }
91 * catch (Z\u02b5) { for (var Z\u02b6 in Z\u02b5)
92 * {for (1; 1<0; Z\u02b7++) {new Array()[Z\u02b6] = 1;} };} }";
94 * It will be helpful to build this string in stages:
96 var s0 = 'function Z';
98 var s2 = '\u02b2, b) {try { Z';
99 var s3 = '\u02b3 : var Z';
100 var s4 = '\u02b4 = Z';
101 var s5 = '\u02b1; } catch (Z'
102 var s6 = '\u02b5) { for (var Z';
103 var s7 = '\u02b6 in Z';
104 var s8 = '\u02b5){for (1; 1<0; Z';
105 var s9 = '\u02b7++) {new Array()[Z';
106 var s10 = '\u02b6] = 1;} };} }';
110 * Concatenate these and eval() to create the function Z\u02b1
112 var sEval = s0 + s1 + s2 + s3 + s4 + s5 + s6 + s7 + s8 + s9 + s10;
117 * Recover all the double-byte identifiers via Z\u02b1.toString().
118 * We'll recover the 1st one as arrID[1], the 2nd one as arrID[2],
121 var arrID = getIdentifiers(Z\u02b1);
125 * Now check that we got back what we put in -
127 status = inSection(1);
129 expect = s1.charAt(0);
132 status = inSection(2);
134 expect = s2.charAt(0);
137 status = inSection(3);
139 expect = s3.charAt(0);
142 status = inSection(4);
144 expect = s4.charAt(0);
147 status = inSection(5);
149 expect = s5.charAt(0);
152 status = inSection(6);
154 expect = s6.charAt(0);
157 status = inSection(7);
159 expect = s7.charAt(0);
162 status = inSection(8);
164 expect = s8.charAt(0);
167 status = inSection(9);
169 expect = s9.charAt(0);
172 status = inSection(10);
174 expect = s10.charAt(0);
180 //-----------------------------------------------------------------------------
182 //-----------------------------------------------------------------------------
187 * Goal: recover the double-byte identifiers from f.toString()
188 * by getting the very next character after each 'Z' token.
190 * The return value will be an array |arr| indexed such that
191 * |arr[1]| is the 1st identifier, |arr[2]| the 2nd, and so on.
193 * Note, however, f.toString() is implementation-independent.
194 * For example, it may begin with '\nfunction' instead of 'function'.
196 * Rhino uses a Unicode representation for f.toString(); whereas
197 * SpiderMonkey uses an ASCII representation, putting escape sequences
198 * for non-ASCII characters. For example, if a function is called f\u02B1,
199 * then in Rhino the toString() method will present a 2-character Unicode
200 * string for its name, whereas SpiderMonkey will present a 7-character
201 * ASCII string for its name: the string literal 'f\u02B1'.
203 * So we force the lexer to condense the string before we use it.
204 * This will give uniform results in Rhino and SpiderMonkey.
206 function getIdentifiers(f)
208 var str = condenseStr(f.toString());
209 var arr = str.split('Z');
212 * The identifiers are the 1st char of each split substring
213 * EXCEPT the first one, which is just ('\n' +) 'function '.
215 * Thus note the 1st identifier will be stored in |arr[1]|,
216 * the 2nd one in |arr[2]|, etc., making the indexing easy -
219 arr[i] = arr[i].charAt(0);
225 * This function is the opposite of a functions like escape(), which take
226 * Unicode characters and return escape sequences for them. Here, we force
227 * the lexer to turn escape sequences back into single characters.
229 * Note we can't simply do |eval(str)|, since in practice |str| will be an
230 * identifier somewhere in the program (e.g. a function name); thus |eval(str)|
231 * would return the object that the identifier represents: not what we want.
233 * So we surround |str| lexicographically with quotes to force the lexer to
234 * evaluate it as a string. Have to strip out any linefeeds first, however -
236 function condenseStr(str)
239 * You won't be able to do the next step if |str| has
240 * any carriage returns or linefeeds in it. For example:
242 * js> eval("'" + '\nHello' + "'");
243 * 1: SyntaxError: unterminated string literal:
247 * So replace them with the empty string -
249 str = str.replace(/[\r\n]/g, '')
250 return eval("'" + str + "'")
256 statusitems[UBound] = status;
257 actualvalues[UBound] = actual;
258 expectedvalues[UBound] = expect;
266 printBugNumber(BUGNUMBER);
267 printStatus(summary);
269 for (var i=0; i<UBound; i++)
271 reportCompare(expectedvalues[i], actualvalues[i], statusitems[i]);