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  * Approximate benchmark for some basic operations.
  22  *
  23  * @package 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', 3 );
  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/tokyo.txt' => 'Japanese text',
  45         'testdata/sociology.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( 'placebo',
  59                 'cleanUp',
  60                 'toNFC',
  61 #               'toNFKC',
  62 #               'toNFD', 'toNFKD',
  63                 'NFC',
  64 #               'NFKC',
  65 #               'NFD', 'NFKD',
  66                 'fastDecompose', 'fastCombiningSort', 'fastCompose',
  67                 'quickIsNFC', 'quickIsNFCVerify',
  68                 );
  69         foreach( $forms as $form ) {
  70                 benchmarkForm( $u, $data, $form );
  71         }
  72 }
  73
  74 function benchTime(){
  75         $st = explode( ' ', microtime() );
  76         return (float)$st[0] + (float)$st[1];
  77 }
  78
  79 function benchmarkForm( &$u, &$data, $form ) {
  80         global $utfCanonicalDecomp;
  81         $start = benchTime();
  82         for( $i = 0; $i < BENCH_CYCLES; $i++ ) {
  83                 $out = $u->$form( $data, $utfCanonicalDecomp );
  84         }
  85         $delta = (benchTime() - $start) / BENCH_CYCLES;
  86         $rate = IntVal( strlen( $data ) / $delta );
  87         $same = (0 == strcmp( $data, $out ) );
  88
  89         printf( " %20s %1.4fs %8d bytes/s (%s)\n", $form, $delta, $rate, ($same ? 'no change' : 'changed' ) );
  90 }
  91
  92 ?>