includes/normal/UtfNormalBench.php

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