| Index: trunk/phase3/includes/normal/UtfNormalMemStress.php |
| — | — | @@ -0,0 +1,109 @@ |
| | 2 | +<?php |
| | 3 | +/** |
| | 4 | + * Approximate benchmark for some basic operations. |
| | 5 | + * Runs large chunks of text through cleanup with a lowish memory limit, |
| | 6 | + * to test regression on mem usage (bug 28146) |
| | 7 | + * |
| | 8 | + * Copyright © 2004-2011 Brion Vibber <brion@wikimedia.org> |
| | 9 | + * http://www.mediawiki.org/ |
| | 10 | + * |
| | 11 | + * This program is free software; you can redistribute it and/or modify |
| | 12 | + * it under the terms of the GNU General Public License as published by |
| | 13 | + * the Free Software Foundation; either version 2 of the License, or |
| | 14 | + * (at your option) any later version. |
| | 15 | + * |
| | 16 | + * This program is distributed in the hope that it will be useful, |
| | 17 | + * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| | 18 | + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| | 19 | + * GNU General Public License for more details. |
| | 20 | + * |
| | 21 | + * You should have received a copy of the GNU General Public License along |
| | 22 | + * with this program; if not, write to the Free Software Foundation, Inc., |
| | 23 | + * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
| | 24 | + * http://www.gnu.org/copyleft/gpl.html |
| | 25 | + * |
| | 26 | + * @file |
| | 27 | + * @ingroup UtfNormal |
| | 28 | + */ |
| | 29 | + |
| | 30 | +if( isset( $_SERVER['argv'] ) && in_array( '--icu', $_SERVER['argv'] ) ) { |
| | 31 | + dl( 'php_utfnormal.so' ); |
| | 32 | +} |
| | 33 | + |
| | 34 | +require_once 'UtfNormalUtil.php'; |
| | 35 | +require_once 'UtfNormal.php'; |
| | 36 | + |
| | 37 | +define( 'BENCH_CYCLES', 1 ); |
| | 38 | +define( 'BIGSIZE', 1024 * 1024 * 10); // 10m |
| | 39 | +ini_set('memory_limit', BIGSIZE + 120 * 1024 * 1024); |
| | 40 | + |
| | 41 | +if( php_sapi_name() != 'cli' ) { |
| | 42 | + die( "Run me from the command line please.\n" ); |
| | 43 | +} |
| | 44 | + |
| | 45 | +$testfiles = array( |
| | 46 | + 'testdata/washington.txt' => 'English text', |
| | 47 | + 'testdata/berlin.txt' => 'German text', |
| | 48 | + 'testdata/bulgakov.txt' => 'Russian text', |
| | 49 | + 'testdata/tokyo.txt' => 'Japanese text', |
| | 50 | + 'testdata/young.txt' => 'Korean text' |
| | 51 | +); |
| | 52 | +$normalizer = new UtfNormal; |
| | 53 | +UtfNormal::loadData(); |
| | 54 | +foreach( $testfiles as $file => $desc ) { |
| | 55 | + benchmarkTest( $normalizer, $file, $desc ); |
| | 56 | +} |
| | 57 | + |
| | 58 | +# ------- |
| | 59 | + |
| | 60 | +function benchmarkTest( &$u, $filename, $desc ) { |
| | 61 | + print "Testing $filename ($desc)...\n"; |
| | 62 | + $data = file_get_contents( $filename ); |
| | 63 | + $all = $data; |
| | 64 | + while (strlen($all) < BIGSIZE) { |
| | 65 | + $all .= $all; |
| | 66 | + } |
| | 67 | + $data = $all; |
| | 68 | + echo "Data is " . strlen($data) . " bytes.\n"; |
| | 69 | + $forms = array( |
| | 70 | + 'quickIsNFCVerify', |
| | 71 | + 'cleanUp', |
| | 72 | + ); |
| | 73 | + foreach( $forms as $form ) { |
| | 74 | + if( is_array( $form ) ) { |
| | 75 | + $str = $data; |
| | 76 | + foreach( $form as $step ) { |
| | 77 | + $str = benchmarkForm( $u, $str, $step ); |
| | 78 | + } |
| | 79 | + } else { |
| | 80 | + benchmarkForm( $u, $data, $form ); |
| | 81 | + } |
| | 82 | + } |
| | 83 | +} |
| | 84 | + |
| | 85 | +function benchTime(){ |
| | 86 | + $st = explode( ' ', microtime() ); |
| | 87 | + return (float)$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 | + return $out; |
| | 110 | +} |