ldc-boutique-cnc-sable/shared/Helpers/StringHelper.php

<?php

declare(strict_types=1);

namespace Shared\Helpers;

final readonly class StringHelper
{
    private function __construct()
    {
        // Static class
    }

    /**
     * Transliterates UTF-8 text to ASCII using ICU Transliterator with iconv fallback.
     */
    public static function transliterate(string $value): string
    {
        if (\function_exists('transliterator_transliterate')) {
            $transliterated = \transliterator_transliterate('Any-Latin; Latin-ASCII', $value);
            if ($transliterated !== false) {
                return $transliterated;
            }
        }

        return (string) iconv('UTF-8', 'ASCII//TRANSLIT//IGNORE', $value);
    }

    public static function mbStrtok(string $delimiters, ?string $str = null): string | false
    {
        /** @var int $pos */
        static $pos = 0;
        /** @var string $string */
        static $string = '';

        if ($str !== null) {
            $pos    = 0;
            $string = $str;
        }

        $token = '';
        $len   = mb_strlen($string, 'UTF-8');

        while ($pos < $len) {
            $char = mb_substr($string, $pos, 1, 'UTF-8');
            $pos++;

            if (mb_strpos($delimiters, $char, 0, 'UTF-8') === false) {
                $token .= $char;
            } else {
                if ($token !== '') {
                    return $token;
                }
            }
        }

        if ($token !== '') {
            return $token;
        }

        return false;
    }

    /**
     * Transliterates and formats a string into a URL-friendly slug.
     */
    public static function slugify(string $value, string $separator = '-'): string
    {
        $transliterated = self::transliterate($value);
        $cleaned        = preg_replace('/[^a-zA-Z0-9]+/u', $separator, $transliterated) ?? '';

        return strtolower(trim($cleaned, $separator));
    }

    /**
     * Convert a string to snake_case.
     */
    public static function snakeCase(string $value): string
    {
        return mb_strtolower(implode('_', self::splitWords($value)));
    }

    /**
     * Convert a string to kebab-case.
     */
    public static function kebabCase(string $value): string
    {
        return mb_strtolower(implode('-', self::splitWords($value)));
    }

    /**
     * Convert a string to Title Case.
     */
    public static function titleCase(string $value): string
    {
        $trimmed = trim($value);
        if ($trimmed === '') {
            return '';
        }

        return mb_convert_case(
            mb_strtolower($trimmed, 'UTF-8'),
            \MB_CASE_TITLE,
            'UTF-8'
        );
    }

    /**
     * Convert a string to PascalCase (StudlyCase).
     */
    public static function pascalCase(string $value): string
    {
        $words = array_map(
            static fn (string $word): string => mb_ucfirst(mb_strtolower($word)),
            self::splitWords($value)
        );

        return implode('', $words);
    }

    /**
     * Convert a string to camelCase.
     */
    public static function camelCase(string $value): string
    {
        return mb_lcfirst(self::pascalCase($value));
    }

    /**
     * Split a string into words, respecting Unicode word boundaries.
     */
    public static function words(string $value, int $words = 100, string $end = ' ...'): string
    {
        preg_match('/^\s*+(?:\S+\s*+){1,' . $words . '}/u', $value, $matches);

        if (! isset($matches[0]) || mb_strlen($value) === mb_strlen($matches[0])) {
            return $value;
        }

        return rtrim($matches[0]) . $end;
    }

    /**
     * Sanitizes and normalizes a text string (strips HTML, removes non-printable control characters, ensures valid UTF-8).
     */
    public static function sanitize(?string $value): ?string
    {
        if ($value === null || $value === '') {
            return $value;
        }

        // Decode HTML entities then strip tags
        $value = html_entity_decode($value, ENT_QUOTES | ENT_HTML5, 'UTF-8');
        $value = strip_tags($value);

        // Normalize newlines, temporarily convert to <br /> to preserve paragraph breaks
        $value = str_replace(["\r\n", "\r"], "\n", $value);
        $value = str_replace("\n", '<br />', $value);

        // Ensure valid UTF-8 (handling Windows-1252 / ISO-8859-1 legacy strings)
        $value = StringEncoder::detectAndConvertToUtf8($value);

        // Remove astral symbols (4-byte UTF-8) that may break storage/processing
        $value = preg_replace('/[\x{10000}-\x{10FFFF}]/u', '', $value) ?? '';

        // Remove control/non-printable characters but keep TAB(0x09), LF(0x0A) and CR(0x0D)
        $value = preg_replace('/[\x00-\x08\x0B\x0C\x0E-\x1F\x7F\xA0\xAD]/u', '', $value) ?? '';

        // Revert <br /> back to newlines and final strip_tags as safety
        $value = str_replace('<br />', "\n", $value);

        return strip_tags($value);
    }

    /**
     * Split an arbitrary string into individual word tokens.
     *
     * @return list<string>
     */
    private static function splitWords(string $value): array
    {
        // 1. Separate camelCase transitions (e.g., "fooBar" -> "foo Bar")
        $value = preg_replace('/(?<=[a-z0-9])([A-Z])/u', ' $1', $value) ?? $value;

        // 2. Separate acronyms followed by regular words (e.g., "HTTPResponse" -> "HTTP Response")
        $value = preg_replace('/(?<=[A-Z])([A-Z][a-z])/u', ' $1', $value) ?? $value;

        // 3. Replace non-alphanumeric characters with whitespace
        $value = preg_replace('/[^\p{L}\p{N}]+/u', ' ', $value) ?? $value;

        return array_values(array_filter(
            explode(' ', trim($value)),
            static fn (string $word): bool => $word !== ''
        ));
    }
}