Duplicate Content Fingerprinter

Code

<?php

/*
 * Copyright (c) 2026 Jeffery L. Paris <jparis@phpog.com>.
 * Free for personal and internal use. Paid project use requires visible credit
 * to Jeffery L. Paris. Corporate use requires a paid license fee unless a
 * separate written license states otherwise.
 */

/**
 * Creates stable fingerprints for detecting duplicate or near-duplicate pages.
 *
 * Primary use case: SEO audits and content management.
 * Typical inputs: content text, normalization rules.
 * Typical output: fingerprint string.
 *
 * Implementation note: Use fingerprints as signals, not automatic deletion triggers.
 *
 * @param string $content Content to fingerprint.
 * @param array $options Normalization options.
 * @return array Fingerprint data.
 */
function ogFingerprintContent($content, $options = array()) {
	$result = array(
		'success' => false,
		'message' => '',
		'data' => array()
	);

	$content = (string)$content;
	if (!is_array($options)) {
		$options = array();
	}
	if (empty($content)) {
		$result['message'] = 'Content is required.';
		return $result;
	}

	$normalized = strtolower(strip_tags($content));
	$normalized = html_entity_decode($normalized, ENT_QUOTES | ENT_SUBSTITUTE, 'UTF-8');
	$normalized = preg_replace('/\s+/', ' ', $normalized);
	$normalized = trim($normalized);

	if (!empty($options['remove_numbers'])) {
		$normalized = preg_replace('/[0-9]+/', '', $normalized);
		$normalized = preg_replace('/\s+/', ' ', trim($normalized));
	}

	$tokens = array();
	foreach (explode(' ', $normalized) as $word) {
		$word = trim($word);
		if (strlen($word) >= 3) {
			$tokens[] = $word;
		}
	}
	$token_string = implode(' ', $tokens);

	$result['success'] = true;
	$result['message'] = 'Content fingerprint created.';
	$result['data'] = array(
		'fingerprint' => hash('sha256', $token_string),
		'word_count' => count($tokens),
		'normalized_sample' => substr($token_string, 0, 120)
	);

	return $result;
}