PHP String Comparison Benchmarks

0 PHP substring comparison benchmark.md

PHP String Comparison Benchmark Results

Performance comparison of different string matching methods in PHP.

Case-Sensitive Comparison Results

Test Setup:

• String length: 76,000 bytes
• Iterations: 1000 per method
• Each test run was a separate, sequential php CLI call to minimize interference

php benchmark.php char-by-char
php benchmark.php substr-compare
php benchmark.php substr-equals
php benchmark.php char-by-char-ci
php benchmark.php substr-compare-ci
php benchmark.php strncasecmp
php benchmark.php strtolower-substr

Results

Method	Time (seconds)
substr with ===	1.56
substr_compare	1.82
Character-by-character	1.91

Code Examples

substr with === :

if ('SYSTEM' === substr($string, $at, 6)) {
    // match found
}

substr_compare:

if (0 === substr_compare($string, 'SYSTEM', $at, 6)) {
    // match found
}

Character-by-character:

if (
    'S' === $string[$at] &&
    'Y' === $string[$at + 1] &&
    'S' === $string[$at + 2] &&
    'T' === $string[$at + 3] &&
    'E' === $string[$at + 4] &&
    'M' === $string[$at + 5]
) {
    // match found
}

---

Case-Insensitive Comparison Results

Test Setup:

• String length: 83,000 bytes
• Iterations: 1,000 per method
• Each method tested independently
• Mixed case test string with SYSTEM, SyStEm, system, SySteM

Results

Method	Time (seconds)
substr_compare(..., true)	2.46
strtolower(substr()) ===	2.90
Character-by-character (OR)	3.34
strncasecmp()	38.94

Code Examples

substr_compare with case-insensitive flag:

if (0 === substr_compare($string, 'SYSTEM', $at, 6, true)) {
    // match found
}

strtolower(substr()) ===:

if ('system' === strtolower(substr($string, $at, 6))) {
    // match found
}

Character-by-character with OR checks:

if (
    ('S' === $string[$at] || 's' === $string[$at]) &&
    ('Y' === $string[$at + 1] || 'y' === $string[$at + 1]) &&
    ('S' === $string[$at + 2] || 's' === $string[$at + 2]) &&
    ('T' === $string[$at + 3] || 't' === $string[$at + 3]) &&
    ('E' === $string[$at + 4] || 'e' === $string[$at + 4]) &&
    ('M' === $string[$at + 5] || 'm' === $string[$at + 5])
) {
    // match found
}

strncasecmp():

if (0 === strncasecmp(substr($string, $at), 'SYSTEM', 6)) {
    // match found
}

Test Environment

• PHP Version: (detected from system)
• Platform: macOS (Darwin 24.6.0)
• Test Date: 2025-11-02

Methodology

• Each benchmark script runs only one comparison method to minimize interference
• Tests were run sequentially, not simultaneously

benchmark.php

<?php
/**
 * Consolidated String Comparison Benchmark
 *
 * Usage: php benchmark.php <method>
 *
 * Methods:
 *   char-by-char           Character-by-character (case-sensitive)
 *   substr-compare         substr_compare() (case-sensitive)
 *   substr-equals          substr() with === (case-sensitive)
 *   char-by-char-ci        Character-by-character (case-insensitive)
 *   substr-compare-ci      substr_compare() with case-insensitive flag
 *   strncasecmp            strncasecmp() (case-insensitive)
 *   strtolower-substr      strtolower(substr()) === (case-insensitive)
 */

// Configuration.
$config = array(
	'case_sensitive' => array(
		'test_string' => str_repeat( 'Lorem ipsum SYSTEM dolor sit amet SYSTEM consectetur SYSTEM adipiscing elit ', 1000 ),
		'iterations' => 1000,
	),
	'case_insensitive' => array(
		'test_string' => str_repeat( 'Lorem ipsum SYSTEM dolor sit SyStEm amet system consectetur SySteM adipiscing elit ', 1000 ),
		'iterations' => 1000,
	),
);

// Benchmark methods.
$methods = array(
	'char-by-char' => array(
		'name' => 'Character-by-character comparison (case-sensitive)',
		'case_sensitive' => true,
		'function' => function ( $test_string, $iterations ) {
			$matches = 0;
			for ( $i = 0; $i < $iterations; $i++ ) {
				for ( $at = 0; $at < strlen( $test_string ) - 6; $at++ ) {
					if (
						'S' === $test_string[ $at ] &&
						'Y' === $test_string[ $at + 1 ] &&
						'S' === $test_string[ $at + 2 ] &&
						'T' === $test_string[ $at + 3 ] &&
						'E' === $test_string[ $at + 4 ] &&
						'M' === $test_string[ $at + 5 ]
					) {
						++$matches;
					}
				}
			}
			return $matches;
		},
	),
	'substr-compare' => array(
		'name' => 'substr_compare() (case-sensitive)',
		'case_sensitive' => true,
		'function' => function ( $test_string, $iterations ) {
			$matches = 0;
			for ( $i = 0; $i < $iterations; $i++ ) {
				for ( $at = 0; $at < strlen( $test_string ) - 6; $at++ ) {
					if ( 0 === substr_compare( $test_string, 'SYSTEM', $at, 6 ) ) {
						++$matches;
					}
				}
			}
			return $matches;
		},
	),
	'substr-equals' => array(
		'name' => 'substr() with === comparison (case-sensitive)',
		'case_sensitive' => true,
		'function' => function ( $test_string, $iterations ) {
			$matches = 0;
			for ( $i = 0; $i < $iterations; $i++ ) {
				for ( $at = 0; $at < strlen( $test_string ) - 6; $at++ ) {
					if ( 'SYSTEM' === substr( $test_string, $at, 6 ) ) {
						++$matches;
					}
				}
			}
			return $matches;
		},
	),
	'char-by-char-ci' => array(
		'name' => 'Character-by-character comparison (case-insensitive)',
		'case_sensitive' => false,
		'function' => function ( $test_string, $iterations ) {
			$matches = 0;
			for ( $i = 0; $i < $iterations; $i++ ) {
				for ( $at = 0; $at < strlen( $test_string ) - 6; $at++ ) {
					if (
						( 'S' === $test_string[ $at ] || 's' === $test_string[ $at ] ) &&
						( 'Y' === $test_string[ $at + 1 ] || 'y' === $test_string[ $at + 1 ] ) &&
						( 'S' === $test_string[ $at + 2 ] || 's' === $test_string[ $at + 2 ] ) &&
						( 'T' === $test_string[ $at + 3 ] || 't' === $test_string[ $at + 3 ] ) &&
						( 'E' === $test_string[ $at + 4 ] || 'e' === $test_string[ $at + 4 ] ) &&
						( 'M' === $test_string[ $at + 5 ] || 'm' === $test_string[ $at + 5 ] )
					) {
						++$matches;
					}
				}
			}
			return $matches;
		},
	),
	'substr-compare-ci' => array(
		'name' => 'substr_compare() with case-insensitive flag',
		'case_sensitive' => false,
		'function' => function ( $test_string, $iterations ) {
			$matches = 0;
			for ( $i = 0; $i < $iterations; $i++ ) {
				for ( $at = 0; $at < strlen( $test_string ) - 6; $at++ ) {
					if ( 0 === substr_compare( $test_string, 'SYSTEM', $at, 6, true ) ) {
						++$matches;
					}
				}
			}
			return $matches;
		},
	),
	'strncasecmp' => array(
		'name' => 'strncasecmp() (case-insensitive)',
		'case_sensitive' => false,
		'function' => function ( $test_string, $iterations ) {
			$matches = 0;
			for ( $i = 0; $i < $iterations; $i++ ) {
				for ( $at = 0; $at < strlen( $test_string ) - 6; $at++ ) {
					if ( 0 === strncasecmp( substr( $test_string, $at ), 'SYSTEM', 6 ) ) {
						++$matches;
					}
				}
			}
			return $matches;
		},
	),
	'strtolower-substr' => array(
		'name' => 'strtolower(substr()) === (case-insensitive)',
		'case_sensitive' => false,
		'function' => function ( $test_string, $iterations ) {
			$matches = 0;
			for ( $i = 0; $i < $iterations; $i++ ) {
				for ( $at = 0; $at < strlen( $test_string ) - 6; $at++ ) {
					if ( 'system' === strtolower( substr( $test_string, $at, 6 ) ) ) {
						++$matches;
					}
				}
			}
			return $matches;
		},
	),
);

// Parse CLI arguments.
if ( $argc < 2 ) {
	echo "Usage: php benchmark.php <method>\n\n";
	echo "Available methods:\n";
	foreach ( $methods as $key => $method ) {
		$type = $method['case_sensitive'] ? 'case-sensitive' : 'case-insensitive';
		echo "  {$key}\n    {$method['name']} ({$type})\n";
	}
	exit( 1 );
}

$selected_method = $argv[1];

if ( ! isset( $methods[ $selected_method ] ) ) {
	echo "Error: Unknown method '{$selected_method}'\n";
	echo "Run 'php benchmark.php' to see available methods.\n";
	exit( 1 );
}

// Get configuration for this method.
$method      = $methods[ $selected_method ];
$test_config = $method['case_sensitive'] ? $config['case_sensitive'] : $config['case_insensitive'];
$test_string = $test_config['test_string'];
$iterations  = $test_config['iterations'];

// Display test information.
echo "Benchmarking: {$method['name']}\n";
echo 'String length: ' . number_format( strlen( $test_string ) ) . " bytes\n";
echo 'Iterations: ' . number_format( $iterations ) . "\n";

// Run benchmark.
$start   = microtime( true );
$matches = $method['function']( $test_string, $iterations );
$elapsed = microtime( true ) - $start;

// Display results.
echo "\nTime: " . number_format( $elapsed, 2 ) . " seconds\n";
echo 'Matches found: ' . number_format( $matches ) . "\n";
echo "--------------------------------\n";