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 # 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18 # http://www.gnu.org/copyleft/gpl.html
  19
  20 /**
  21  * Approximate benchmark for some basic operations.
  22  *
  23  * @addtogroup UtfNormal
  24  * @access private
  25  */
  26
  27 /** */
  28 if( isset( $_SERVER['argv'] ) && in_array( '--icu', $_SERVER['argv'] ) ) {
  29         dl( 'php_utfnormal.so' );
  30 }
  31
  32 require_once 'UtfNormalUtil.php';
  33 require_once 'UtfNormal.php';
  34
  35 define( 'BENCH_CYCLES', 5 );
  36
  37 if( php_sapi_name() != 'cli' ) {
  38         die( "Run me from the command line please.\n" );
  39 }
  40
  41 $testfiles = array(
  42         'testdata/washington.txt' => 'English text',
  43         'testdata/berlin.txt' => 'German text',
  44         'testdata/bulgakov.txt' => 'Russian text',
  45         'testdata/tokyo.txt' => 'Japanese text',
  46         'testdata/young.txt' => 'Korean text'
  47 );
  48 $normalizer = new UtfNormal;
  49 UtfNormal::loadData();
  50 foreach( $testfiles as $file => $desc ) {
  51         benchmarkTest( $normalizer, $file, $desc );
  52 }
  53
  54 # -------
  55
  56 function benchmarkTest( &$u, $filename, $desc ) {
  57         print "Testing $filename ($desc)...\n";
  58         $data = file_get_contents( $filename );
  59         $forms = array(
  60 #               'placebo',
  61                 'cleanUp',
  62                 'toNFC',
  63 #               'toNFKC',
  64 #               'toNFD', 'toNFKD',
  65                 'NFC',
  66 #               'NFKC',
  67 #               'NFD', 'NFKD',
  68                 array( 'fastDecompose', 'fastCombiningSort', 'fastCompose' ),
  69 #               'quickIsNFC', 'quickIsNFCVerify',
  70                 );
  71         foreach( $forms as $form ) {
  72                 if( is_array( $form ) ) {
  73                         $str = $data;
  74                         foreach( $form as $step ) {
  75                                 $str = benchmarkForm( $u, $str, $step );
  76                         }
  77                 } else {
  78                         benchmarkForm( $u, $data, $form );
  79                 }
  80         }
  81 }
  82
  83 function benchTime(){
  84         $st = explode( ' ', microtime() );
  85         return (float)$st[0] + (float)$st[1];
  86 }
  87
  88 function benchmarkForm( &$u, &$data, $form ) {
  89         global $utfCanonicalDecomp;
  90         #$start = benchTime();
  91         for( $i = 0; $i < BENCH_CYCLES; $i++ ) {
  92                 $start = benchTime();
  93                 $out = $u->$form( $data, $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 }
 110
 111 ?>