includes/normal/UtfNormalMemStress.php

   1 <?php
   2 /**
   3  * Approximate benchmark for some basic operations.
   4  * Runs large chunks of text through cleanup with a lowish memory limit,
   5  * to test regression on mem usage (bug 28146)
   6  *
   7  * Copyright © 2004-2011 Brion Vibber <brion@wikimedia.org>
   8  * http://www.mediawiki.org/
   9  *
  10  * This program is free software; you can redistribute it and/or modify
  11  * it under the terms of the GNU General Public License as published by
  12  * the Free Software Foundation; either version 2 of the License, or
  13  * (at your option) any later version.
  14  *
  15  * This program is distributed in the hope that it will be useful,
  16  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  17  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  18  * GNU General Public License for more details.
  19  *
  20  * You should have received a copy of the GNU General Public License along
  21  * with this program; if not, write to the Free Software Foundation, Inc.,
  22  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  23  * http://www.gnu.org/copyleft/gpl.html
  24  *
  25  * @file
  26  * @ingroup UtfNormal
  27  */
  28
  29 if( isset( $_SERVER['argv'] ) && in_array( '--icu', $_SERVER['argv'] ) ) {
  30         dl( 'php_utfnormal.so' );
  31 }
  32
  33 require_once 'UtfNormalUtil.php';
  34 require_once 'UtfNormal.php';
  35
  36 define( 'BENCH_CYCLES', 1 );
  37 define( 'BIGSIZE', 1024 * 1024 * 10); // 10m
  38 ini_set('memory_limit', BIGSIZE + 120 * 1024 * 1024);
  39
  40 if( php_sapi_name() != 'cli' ) {
  41         die( "Run me from the command line please.\n" );
  42 }
  43
  44 $testfiles = array(
  45         'testdata/washington.txt' => 'English text',
  46         'testdata/berlin.txt' => 'German text',
  47         'testdata/bulgakov.txt' => 'Russian text',
  48         'testdata/tokyo.txt' => 'Japanese text',
  49         'testdata/young.txt' => 'Korean text'
  50 );
  51 $normalizer = new UtfNormal;
  52 UtfNormal::loadData();
  53 foreach( $testfiles as $file => $desc ) {
  54         benchmarkTest( $normalizer, $file, $desc );
  55 }
  56
  57 # -------
  58
  59 function benchmarkTest( &$u, $filename, $desc ) {
  60         print "Testing $filename ($desc)...\n";
  61         $data = file_get_contents( $filename );
  62         $all = $data;
  63         while (strlen($all) < BIGSIZE) {
  64                 $all .= $all;
  65         }
  66         $data = $all;
  67         echo "Data is " . strlen($data) . " bytes.\n";
  68         $forms = array(
  69         'quickIsNFCVerify',
  70                 'cleanUp',
  71                 );
  72         foreach( $forms as $form ) {
  73                 if( is_array( $form ) ) {
  74                         $str = $data;
  75                         foreach( $form as $step ) {
  76                                 $str = benchmarkForm( $u, $str, $step );
  77                         }
  78                 } else {
  79                         benchmarkForm( $u, $data, $form );
  80                 }
  81         }
  82 }
  83
  84 function benchTime(){
  85         $st = explode( ' ', microtime() );
  86         return (float)$st[0] + (float)$st[1];
  87 }
  88
  89 function benchmarkForm( &$u, &$data, $form ) {
  90         #$start = benchTime();
  91         for( $i = 0; $i < BENCH_CYCLES; $i++ ) {
  92                 $start = benchTime();
  93                 $out = $u->$form( $data, UtfNormal::$utfCanonicalDecomp );
  94                 $deltas[] = (benchTime() - $start);
  95         }
  96         #$delta = (benchTime() - $start) / BENCH_CYCLES;
  97         sort( $deltas );
  98         $delta = $deltas[0]; # Take shortest time
  99
 100         $rate = intval( strlen( $data ) / $delta );
 101         $same = (0 == strcmp( $data, $out ) );
 102
 103         printf( " %20s %6.1fms %12s bytes/s (%s)\n",
 104                 $form,
 105                 $delta*1000.0,
 106                 number_format( $rate ),
 107                 ($same ? 'no change' : 'changed' ) );
 108         return $out;
 109 }