includes/normal/UtfNormalBench.php

   1 <?php
   2 # Copyright (C) 2004 Brion Vibber <brion@pobox.com>
   3 # http://www.mediawiki.org/
   4 #
   5 # This program is free software; you can redistribute it and/or modify
   6 # it under the terms of the GNU General Public License as published by
   7 # the Free Software Foundation; either version 2 of the License, or
   8 # (at your option) any later version.
   9 #
  10 # This program is distributed in the hope that it will be useful,
  11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13 # GNU General Public License for more details.
  14 #
  15 # You should have received a copy of the GNU General Public License along
  16 # with this program; if not, write to the Free Software Foundation, Inc.,
  17 # 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
  18 # http://www.gnu.org/copyleft/gpl.html
  19
  20 /**
  21  *
  22  * @package MediaWiki
  23  */
  24
  25 /** */
  26 require_once 'UtfNormalUtil.php';
  27 require_once 'UtfNormal.php';
  28
  29 define( 'BENCH_CYCLES', 3 );
  30
  31 if( php_sapi_name() != 'cli' ) {
  32         die( "Run me from the command line please.\n" );
  33 }
  34
  35 $testfiles = array(
  36         'testdata/washington.txt' => 'English text',
  37         'testdata/berlin.txt' => 'German text',
  38         'testdata/tokyo.txt' => 'Japanese text',
  39         'testdata/byzantium.txt' => 'Korean text'
  40 );
  41 $normalizer = new UtfNormal;
  42 foreach( $testfiles as $file => $desc ) {
  43         benchmarkTest( $normalizer, $file, $desc );
  44 }
  45
  46 # -------
  47
  48 function benchmarkTest( &$u, $filename, $desc ) {
  49         print "Testing $filename ($desc)...\n";
  50         $data = file_get_contents( $filename );
  51         $forms = array( 'placebo',
  52                 'cleanUp',
  53                 'toNFC',
  54 #               'toNFKC',
  55 #               'toNFD', 'toNFKD',
  56                 'NFC',
  57 #               'NFKC',
  58 #               'NFD', 'NFKD',
  59 #               'fastDecompose', 'fastCombiningSort', 'fastCompose',
  60                 'quickIsNFC', 'quickIsNFCVerify',
  61                 );
  62         foreach( $forms as $form ) {
  63                 benchmarkForm( $u, $data, $form );
  64         }
  65 }
  66
  67 function benchTime(){
  68         $st = explode( ' ', microtime() );
  69         return (float)$st[0] + (float)$st[1];
  70 }
  71
  72 function benchmarkForm( &$u, &$data, $form ) {
  73         global $utfCanonicalDecomp;
  74         $start = benchTime();
  75         for( $i = 0; $i < BENCH_CYCLES; $i++ ) {
  76                 $out = $u->$form( $data, $utfCanonicalDecomp );
  77         }
  78         $delta = (benchTime() - $start) / BENCH_CYCLES;
  79         $rate = IntVal( strlen( $data ) / $delta );
  80         $same = (0 == strcmp( $data, $out ) );
  81
  82         printf( " %20s %1.4fs %8d bytes/s (%s)\n", $form, $delta, $rate, ($same ? 'no change' : 'changed' ) );
  83 }
  84
  85 ?>