tests/mozilla/ecma_3/RegExp/regress-85721.js

   1 /* ***** BEGIN LICENSE BLOCK *****
   2 * Version: NPL 1.1/GPL 2.0/LGPL 2.1
   3 *
   4 * The contents of this file are subject to the Netscape Public License
   5 * Version 1.1 (the "License"); you may not use this file except in
   6 * compliance with the License. You may obtain a copy of the License at
   7 * http://www.mozilla.org/NPL/
   8 *
   9 * Software distributed under the License is distributed on an "AS IS" basis,
  10 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
  11 * for the specific language governing rights and limitations under the
  12 * License.
  13 *
  14 * The Original Code is JavaScript Engine testing utilities.
  15 *
  16 * The Initial Developer of the Original Code is Netscape Communications Corp.
  17 * Portions created by the Initial Developer are Copyright (C) 2002
  18 * the Initial Developer. All Rights Reserved.
  19 *
  20 * Contributor(s): rogerl@netscape.com, pschwartau@netscape.com
  21 *
  22 * Alternatively, the contents of this file may be used under the terms of
  23 * either the GNU General Public License Version 2 or later (the "GPL"), or
  24 * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
  25 * in which case the provisions of the GPL or the LGPL are applicable instead
  26 * of those above. If you wish to allow use of your version of this file only
  27 * under the terms of either the GPL or the LGPL, and not to allow others to
  28 * use your version of this file under the terms of the NPL, indicate your
  29 * decision by deleting the provisions above and replace them with the notice
  30 * and other provisions required by the GPL or the LGPL. If you do not delete
  31 * the provisions above, a recipient may use your version of this file under
  32 * the terms of any one of the NPL, the GPL or the LGPL.
  33 *
  34 * ***** END LICENSE BLOCK *****
  35 *
  36 *
  37 * Date:    14 Feb 2002
  38 * SUMMARY: Performance: Regexp performance degraded from 4.7
  39 * See http://bugzilla.mozilla.org/show_bug.cgi?id=85721
  40 *
  41 * Adjust this testcase if necessary. The FAST constant defines
  42 * an upper bound in milliseconds for any execution to take.
  43 *
  44 */
  45 //-----------------------------------------------------------------------------
  46 var bug = 85721;
  47 var summary = 'Performance: execution of regular expression';
  48 var FAST = 100; // execution should be 100 ms or less to pass the test
  49 var MSG_FAST = 'Execution took less than ' + FAST + ' ms';
  50 var MSG_SLOW = 'Execution took ';
  51 var MSG_MS = ' ms';
  52 var str = '';
  53 var re = '';
  54 var status = '';
  55 var actual = '';
  56 var expect= '';
  57
  58 printBugNumber (bug);
  59 printStatus (summary);
  60
  61
  62 function elapsedTime(startTime)
  63 {
  64   return new Date() - startTime;
  65 }
  66
  67
  68 function isThisFast(ms)
  69 {
  70   if (ms <= FAST)
  71     return MSG_FAST;
  72   return MSG_SLOW + ms + MSG_MS;
  73 }
  74
  75
  76
  77 /*
  78  * The first regexp. We'll test for performance (Section 1) and accuracy (Section 2).
  79  */
  80 str='<sql:connection id="conn1"> <sql:url>www.m.com</sql:url> <sql:driver>drive.class</sql:driver>\n<sql:userId>foo</sql:userId> <sql:password>goo</sql:password> </sql:connection>';
  81 re = /<sql:connection id="([^\r\n]*?)">\s*<sql:url>\s*([^\r\n]*?)\s*<\/sql:url>\s*<sql:driver>\s*([^\r\n]*?)\s*<\/sql:driver>\s*(\s*<sql:userId>\s*([^\r\n]*?)\s*<\/sql:userId>\s*)?\s*(\s*<sql:password>\s*([^\r\n]*?)\s*<\/sql:password>\s*)?\s*<\/sql:connection>/;
  82 expect = Array("<sql:connection id=\"conn1\"> <sql:url>www.m.com</sql:url> <sql:driver>drive.class</sql:driver>\n<sql:userId>foo</sql:userId> <sql:password>goo</sql:password> </sql:connection>","conn1","www.m.com","drive.class","<sql:userId>foo</sql:userId> ","foo","<sql:password>goo</sql:password> ","goo");
  83
  84 /*
  85  *  Check performance -
  86  */
  87 status = inSection(1);
  88 var start = new Date();
  89 var result = re.exec(str);
  90 actual = elapsedTime(start);
  91 reportCompare(isThisFast(FAST), isThisFast(actual), status);
  92
  93 /*
  94  *  Check accuracy -
  95  */
  96 status = inSection(2);
  97 testRegExp([status], [re], [str], [result], [expect]);
  98
  99
 100
 101 /*
 102  * The second regexp (HUGE!). We'll test for performance (Section 3) and accuracy (Section 4).
 103  * It comes from the O'Reilly book "Mastering Regular Expressions" by Jeffrey Friedl, Appendix B
 104  */
 105
 106 //# Some things for avoiding backslashitis later on.
 107 $esc        = '\\\\';
 108 $Period      = '\.';
 109 $space      = '\040';              $tab         = '\t';
 110 $OpenBR     = '\\[';               $CloseBR     = '\\]';
 111 $OpenParen  = '\\(';               $CloseParen  = '\\)';
 112 $NonASCII   = '\x80-\xff';         $ctrl        = '\000-\037';
 113 $CRlist     = '\n\015';  //# note: this should really be only \015.
 114 // Items 19, 20, 21
 115 $qtext = '[^' + $esc + $NonASCII + $CRlist + '\"]';                                               // # for within "..."
 116 $dtext = '[^' + $esc + $NonASCII + $CRlist + $OpenBR + $CloseBR + ']';    // # for within [...]
 117 $quoted_pair = $esc + '[^' + $NonASCII + ']';                                                     // # an escaped character
 118
 119 //##############################################################################
 120 //# Items 22 and 23, comment.
 121 //# Impossible to do properly with a regex, I make do by allowing at most one level of nesting.
 122 $ctext   =  '[^' + $esc + $NonASCII + $CRlist + '()]';
 123
 124 //# $Cnested matches one non-nested comment.
 125 //# It is unrolled, with normal of $ctext, special of $quoted_pair.
 126 $Cnested =
 127    $OpenParen +                                 // #  (
 128       $ctext + '*' +                            // #     normal*
 129       '(?:' + $quoted_pair + $ctext + '*)*' +   // #     (special normal*)*
 130    $CloseParen;                                 // #                       )
 131
 132
 133 //# $comment allows one level of nested parentheses
 134 //# It is unrolled, with normal of $ctext, special of ($quoted_pair|$Cnested)
 135 $comment =
 136    $OpenParen +                                           // #  (
 137        $ctext + '*' +                                     // #     normal*
 138        '(?:' +                                            // #       (
 139           '(?:' + $quoted_pair + '|' + $Cnested + ')' +   // #         special
 140            $ctext + '*' +                                 // #         normal*
 141        ')*' +                                             // #            )*
 142    $CloseParen;                                           // #                )
 143
 144
 145 //##############################################################################
 146 //# $X is optional whitespace/comments.
 147 $X =
 148    '[' + $space + $tab + ']*' +                                        // # Nab whitespace.
 149    '(?:' + $comment + '[' + $space + $tab + ']*)*';    // # If comment found, allow more spaces.
 150
 151
 152 //# Item 10: atom
 153 $atom_char   = '[^(' + $space + '<>\@,;:\".' + $esc + $OpenBR + $CloseBR + $ctrl + $NonASCII + ']';
 154 $atom =
 155   $atom_char + '+' +            // # some number of atom characters...
 156   '(?!' + $atom_char + ')';     // # ..not followed by something that could be part of an atom
 157
 158 // # Item 11: doublequoted string, unrolled.
 159 $quoted_str =
 160     '\"' +                                         // # "
 161        $qtext + '*' +                              // #   normal
 162        '(?:' + $quoted_pair + $qtext + '*)*' +     // #   ( special normal* )*
 163     '\"';                                          // # "
 164
 165 //# Item 7: word is an atom or quoted string
 166 $word =
 167     '(?:' +
 168        $atom +                // # Atom
 169        '|' +                  //     #  or
 170        $quoted_str +          // # Quoted string
 171      ')'
 172
 173 //# Item 12: domain-ref is just an atom
 174 $domain_ref  = $atom;
 175
 176 //# Item 13: domain-literal is like a quoted string, but [...] instead of  "..."
 177 $domain_lit  =
 178     $OpenBR +                                                                        // # [
 179     '(?:' + $dtext + '|' + $quoted_pair + ')*' +     // #    stuff
 180     $CloseBR;                                        // #           ]
 181
 182 // # Item 9: sub-domain is a domain-ref or domain-literal
 183 $sub_domain  =
 184   '(?:' +
 185     $domain_ref +
 186     '|' +
 187     $domain_lit +
 188    ')' +
 189    $X;                 // # optional trailing comments
 190
 191 // # Item 6: domain is a list of subdomains separated by dots.
 192 $domain =
 193      $sub_domain +
 194      '(?:' +
 195         $Period + $X + $sub_domain +
 196      ')*';
 197
 198 //# Item 8: a route. A bunch of "@ $domain" separated by commas, followed by a colon.
 199 $route =
 200     '\@' + $X + $domain +
 201     '(?:,' + $X + '\@' + $X + $domain + ')*' +  // # additional domains
 202     ':' +
 203     $X;                                 // # optional trailing comments
 204
 205 //# Item 6: local-part is a bunch of $word separated by periods
 206 $local_part =
 207     $word + $X
 208     '(?:' +
 209         $Period + $X + $word + $X +             // # additional words
 210     ')*';
 211
 212 // # Item 2: addr-spec is local@domain
 213 $addr_spec  =
 214   $local_part + '\@' + $X + $domain;
 215
 216 //# Item 4: route-addr is <route? addr-spec>
 217 $route_addr =
 218     '<' + $X +                     // # <
 219        '(?:' + $route + ')?' +     // #       optional route
 220        $addr_spec +                // #       address spec
 221     '>';                           // #                 >
 222
 223 //# Item 3: phrase........
 224 $phrase_ctrl = '\000-\010\012-\037'; // # like ctrl, but without tab
 225
 226 //# Like atom-char, but without listing space, and uses phrase_ctrl.
 227 //# Since the class is negated, this matches the same as atom-char plus space and tab
 228 $phrase_char =
 229    '[^()<>\@,;:\".' + $esc + $OpenBR + $CloseBR + $NonASCII + $phrase_ctrl + ']';
 230
 231 // # We've worked it so that $word, $comment, and $quoted_str to not consume trailing $X
 232 // # because we take care of it manually.
 233 $phrase =
 234    $word +                                                  // # leading word
 235    $phrase_char + '*' +                                     // # "normal" atoms and/or spaces
 236    '(?:' +
 237       '(?:' + $comment + '|' + $quoted_str + ')' +          // # "special" comment or quoted string
 238       $phrase_char + '*' +                                  // #  more "normal"
 239    ')*';
 240
 241 // ## Item #1: mailbox is an addr_spec or a phrase/route_addr
 242 $mailbox =
 243     $X +                                // # optional leading comment
 244     '(?:' +
 245             $phrase + $route_addr +     // # name and address
 246             '|' +                       //     #  or
 247             $addr_spec +                // # address
 248      ')';
 249
 250
 251 //###########################################################################
 252
 253
 254 re = new RegExp($mailbox, "g");
 255 str = 'Jeffy<"That Tall Guy"@ora.com (this address is no longer active)>';
 256 expect = Array('Jeffy<"That Tall Guy"@ora.com (this address is no longer active)>');
 257
 258 /*
 259  *  Check performance -
 260  */
 261 status = inSection(3);
 262 var start = new Date();
 263 var result = re.exec(str);
 264 actual = elapsedTime(start);
 265 reportCompare(isThisFast(FAST), isThisFast(actual), status);
 266
 267 /*
 268  *  Check accuracy -
 269  */
 270 status = inSection(4);
 271 testRegExp([status], [re], [str], [result], [expect]);