PHP code example of loupe / matcher

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

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

    

loupe / matcher example snippets

use Loupe\Matcher\Tokenizer\Tokenizer;
use Loupe\Matcher\Matcher;
use Loupe\Matcher\Formatter;
use Loupe\Matcher\FormatterOptions;

$tokenizer = new Tokenizer();
$matcher = new Matcher($tokenizer);
$formatter = new Formatter($matcher);

$options = (new FormatterOptions())
    ->withEnableHighlight()
    ->withEnableCrop()
    ->withCropLength(10);

$result = $formatter->format(
    'This is a long document with many words to search through and compare.',
    'search words',
    $options
);

// "...with many <em>words</em> to <em>search</em> through..."
echo $result->getFormattedText();

$tokenizer = new Tokenizer('en_US'); // Optional locale
$tokens = $tokenizer->tokenize('search for "exact phrase" -exclude');

$tokens->all();          // All tokens
$tokens->phraseGroups(); // Quoted phrases only
$tokens->allNegated();   // Terms to exclude

$matcher = new Matcher($tokenizer, ['the', 'and', 'or']); // Stop words
$matches = $matcher->calculateMatches('Text to search', 'search query');

// Get position information for highlighting
$spans = $matcher->calculateMatchSpans('Text to search', 'query', $matches);
foreach ($spans as $span) {
    echo "Match at position {$span->getStartPosition()}-{$span->getEndPosition()}";
}

$formatter = new Formatter($matcher);

$options = (new FormatterOptions())
    ->withEnableHighlight()
    ->withHighlightStartTag('<mark>')
    ->withHighlightEndTag('</mark>')
    ->withEnableCrop()
    ->withCropLength(150)
    ->withCropMarker('...');

$result = $formatter->format($text, $query, $options);
echo $result->getFormattedText();

class CustomTokenizer implements TokenizerInterface {
    public function tokenize(string $text): TokenCollection {
        // Your custom tokenization logic
    }

    public function matches(Token $token, TokenCollection $tokens): bool {
        // Your custom logic for checking if a token is a match
    }
}

$cropper = new \Loupe\Matcher\Formatting\Cropper(
    cropLength: 50,
    cropMarker: '…',
    highlightStartTag: '<em>',
    highlightEndTag: '</em>'
);

// "...text with <em>highlighted</em> terms."
echo $cropper->cropHighlightedText('Long text with <em>highlighted</em> terms.');

// Assume you already have matches from somewhere else
$existingMatches = new TokenCollection(/* ... */);

// Set up the tokenizer, matcher, and formatter as usual
$tokenizer = new Tokenizer();
$matcher = new Matcher($tokenizer);
$formatter = new Formatter($matcher);
$options = (new FormatterOptions())
    ->withEnableHighlight()
    ->withEnableCrop()
    ->withCropLength(100);

// Format using the existing matches - no duplicate processing
$result = $formatter->format($text, $query, $options, matches: $existingMatches);
echo $result->getFormattedText();