includes/normal/UtfNormalBench.php

   1 <?php
   2 /**
   3  * Approximate benchmark for some basic operations.
   4  *
   5  * Copyright © 2004 Brion Vibber <brion@pobox.com>
   6  * https://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 ( PHP_SAPI != 'cli' ) {
  28         die( "Run me from the command line please.\n" );
  29 }
  30
  31 if ( isset( $_SERVER['argv'] ) && in_array( '--icu', $_SERVER['argv'] ) ) {
  32         dl( 'php_utfnormal.so' );
  33 }
  34
  35 require_once 'UtfNormalDefines.php';
  36 require_once 'UtfNormalUtil.php';
  37 require_once 'UtfNormal.php';
  38
  39 define( 'BENCH_CYCLES', 5 );
  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
  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         $st = explode( ' ', microtime() );
  86
  87         return (float)$st[0] + (float)$st[1];
  88 }
  89
  90 function benchmarkForm( &$u, &$data, $form ) {
  91         #$start = benchTime();
  92         for ( $i = 0; $i < BENCH_CYCLES; $i++ ) {
  93                 $start = benchTime();
  94                 $out = $u->$form( $data, UtfNormal::$utfCanonicalDecomp );
  95                 $deltas[] = ( benchTime() - $start );
  96         }
  97         #$delta = (benchTime() - $start) / BENCH_CYCLES;
  98         sort( $deltas );
  99         $delta = $deltas[0]; # Take shortest time
 100
 101         $rate = intval( strlen( $data ) / $delta );
 102         $same = ( 0 == strcmp( $data, $out ) );
 103
 104         printf( " %20s %6.1fms %12s bytes/s (%s)\n",
 105                 $form,
 106                 $delta * 1000.0,
 107                 number_format( $rate ),
 108                 ( $same ? 'no change' : 'changed' ) );
 109
 110         return $out;
 111 }