PHP code example of zbmowrey / weighted-levenshtein

    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

    

zbmowrey / weighted-levenshtein example snippets

use Zbmowrey\WeightedLevenshtein\Distance;

// Default (uniform) costs of 1.0 per operation.
echo Distance::levenshtein('kitten', 'sitting');             // 3
echo Distance::optimalStringAlignment('ca', 'ac');           // 1 (one transposition)
echo Distance::damerauLevenshtein('ab', 'bca');              // 2

use Zbmowrey\WeightedLevenshtein\CharCostMap;
use Zbmowrey\WeightedLevenshtein\Distance;

$insertCosts = CharCostMap::uniform()->withCost('D', 1.5);
echo Distance::levenshtein('BANANAS', 'BANDANAS', $insertCosts);  // 1.5

use Zbmowrey\WeightedLevenshtein\CharCostMap;
use Zbmowrey\WeightedLevenshtein\CharPairCostMap;
use Zbmowrey\WeightedLevenshtein\Distance;

// --- Insertion cost ---
$insertCosts = CharCostMap::uniform()->withCost('D', 1.5);
echo Distance::levenshtein('BANANAS', 'BANDANAS', $insertCosts);
// 1.5

// --- Deletion cost ---
$deleteCosts = CharCostMap::uniform()->withCost('S', 0.5);
echo Distance::levenshtein('BANANAS', 'BANANA', $insertCosts, $deleteCosts);
// 0.5

// --- Substitution cost (asymmetric!) ---
$subs = CharPairCostMap::uniform()->withCost('H', 'B', 1.25);
echo Distance::levenshtein('HANANA', 'BANANA', null, null, $subs);
// 1.25

// The reverse direction is unweighted because we never set ('B','H').
echo Distance::levenshtein('BANANA', 'HANANA', null, null, $subs);
// 1.0

// Make the reverse direction match by setting the other ordered pair.
$subs = $subs->withCost('B', 'H', 1.25);
echo Distance::levenshtein('BANANA', 'HANANA', null, null, $subs);
// 1.25

// --- Transposition cost (Damerau-Levenshtein) ---
$transposes = CharPairCostMap::uniform()->withCost('A', 'B', 0.75);
echo Distance::damerauLevenshtein('ABNANA', 'BANANA', null, null, null, $transposes);
// 0.75

// Like substitution, transposition is also asymmetric.
echo Distance::damerauLevenshtein('BANANA', 'ABNANA', null, null, null, $transposes);
// 1.0

// Set the other direction to make it symmetric.
$transposes = $transposes->withCost('B', 'A', 0.75);
echo Distance::damerauLevenshtein('BANANA', 'ABNANA', null, null, null, $transposes);
// 0.75

use function Zbmowrey\WeightedLevenshtein\{lev, osa, dam_lev};

echo lev('kitten', 'sitting');     // 3
echo osa('ca', 'ac');              // 1
echo dam_lev('ab', 'ba');          // 1

use Zbmowrey\WeightedLevenshtein\Distance;
use Zbmowrey\WeightedLevenshtein\Presets\OcrConfusions;

$substitute = OcrConfusions::common();              // default cost 0.25
echo Distance::levenshtein('FOOD', 'F00D', null, null, $substitute);  // 0.5
echo Distance::levenshtein('Hello', 'He11o', null, null, $substitute); // 0.5

$substitute = OcrConfusions::common()
    ->withCost('I', '1', 0.05)  // your OCR confuses I and 1 more strongly
    ->withCost('1', 'I', 0.05);

use Zbmowrey\WeightedLevenshtein\Distance;
use Zbmowrey\WeightedLevenshtein\Presets\QwertyKeyboard;

$substitute = QwertyKeyboard::substituteCosts();
$transpose  = QwertyKeyboard::transposeCosts();

echo Distance::damerauLevenshtein(
    'helo',
    'hwlo',
    null,
    null,
    $substitute,   // w is adjacent to e on the keyboard
    $transpose,
);
// 0.5

$strict = QwertyKeyboard::substituteCosts(adjacentCost: 0.2, nearCost: 0.5);