privatebin-mirror/lib/I18n.php

<?php declare(strict_types=1);
/**
 * PrivateBin
 *
 * a zero-knowledge paste bin
 *
 * @link      https://github.com/PrivateBin/PrivateBin
 * @copyright 2012 Sébastien SAUVAGE (sebsauvage.net)
 * @license   https://www.opensource.org/licenses/zlib-license.php The zlib/libpng License
 */

namespace PrivateBin;

use AppendIterator;
use GlobIterator;

use function array_key_exists;
use function in_array;

/**
 * I18n
 *
 * provides internationalization tools like translation, browser language detection, etc.
 */
class I18n
{
    /**
     * language
     *
     * @access protected
     * @static
     * @var    string
     */
    protected static $_language = 'en';

    /**
     * language fallback
     *
     * @access protected
     * @static
     * @var    string
     */
    protected static $_languageFallback = 'en';

    /**
     * language labels
     *
     * @access protected
     * @static
     * @var    array
     */
    protected static $_languageLabels = [];

    /**
     * available languages
     *
     * @access protected
     * @static
     * @var    array
     */
    protected static $_availableLanguages = [];

    /**
     * path to language files
     *
     * @access protected
     * @static
     * @var    string
     */
    protected static $_path = '';

    /**
     * translation cache
     *
     * @access protected
     * @static
     * @var    array
     */
    protected static $_translations = [];

    /**
     * translate a string, alias for translate()
     *
     * @access public
     * @static
     * @param  string|array $messageId
     * @param  mixed $args one or multiple parameters injected into placeholders
     * @return string
     */
    public static function _($messageId, ...$args)
    {
        return forward_static_call_array('PrivateBin\I18n::translate', func_get_args());
    }

    /**
     * translate a string
     *
     * @access public
     * @static
     * @param  string|array $messageId
     * @param  mixed $args one or multiple parameters injected into placeholders
     * @return string
     */
    public static function translate($messageId, ...$args)
    {
        if (empty($messageId)) {
            return $messageId;
        }
        if (empty(self::$_translations)) {
            self::loadTranslations();
        }
        $messages = $messageId;
        if (is_array($messageId)) {
            $messageId = count($messageId) > 1 ? $messageId[1] : $messageId[0];
        }
        if (!array_key_exists($messageId, self::$_translations)) {
            self::$_translations[$messageId] = $messages;
        }
        array_unshift($args, $messageId);
        if (is_array(self::$_translations[$messageId])) {
            $number = (int) $args[1];
            $key = self::_getPluralForm($number);
            $max = count(self::$_translations[$messageId]) - 1;
            if ($key > $max) {
                $key = $max;
            }

            $args[0] = self::$_translations[$messageId][$key];
            $args[1] = $number;
        } else {
            $args[0] = self::$_translations[$messageId];
        }
        // encode any non-integer arguments, but not the message itself
        // The message ID comes from trusted sources (code or translation JSON files),
        // while parameters may come from untrusted sources and need HTML entity encoding
        // to prevent XSS attacks when the message is inserted into HTML context
        $argsCount = count($args);
        for ($i = 1; $i < $argsCount; ++$i) {
            if (is_int($args[$i])) {
                continue;
            }
            $args[$i] = self::encode($args[$i]);
        }
        return call_user_func_array('sprintf', $args);
    }

    /**
     * encode HTML entities for output into an HTML5 document
     *
     * @access public
     * @static
     * @param  string $string
     * @return string
     */
    public static function encode($string)
    {
        return htmlspecialchars($string, ENT_QUOTES | ENT_HTML5 | ENT_DISALLOWED, 'UTF-8', false);
    }

    /**
     * loads translations
     *
     * From: https://stackoverflow.com/questions/3770513/detect-browser-language-in-php#3771447
     *
     * @access public
     * @static
     * @throws JsonException
     */
    public static function loadTranslations()
    {
        $availableLanguages = self::getAvailableLanguages();

        // check if the lang cookie was set and that language exists
        if (
            array_key_exists('lang', $_COOKIE) &&
            ($key = array_search($_COOKIE['lang'], $availableLanguages)) !== false
        ) {
            self::$_language = $availableLanguages[$key];
        }
        // find a translation file matching the browsers language preferences
        else {
            self::$_language = self::_getLanguageFromHttpHeader($availableLanguages);
        }

        // load translations
        if (self::$_language === 'en') {
            self::$_translations = [];
        } else {
            $data = file_get_contents(self::_getPath(self::$_language . '.json'));
            self::$_translations = Json::decode($data);
        }
    }

    /**
     * get languages based on the HTTP header
     *
     * @access private
     * @static
     * @param  array $availableLanguages
     * @return string
     */
    private static function _getLanguageFromHttpHeader($availableLanguages)
    {
        if (!array_key_exists('HTTP_ACCEPT_LANGUAGE', $_SERVER)) {
            return self::$_languageFallback;
        }

        /* TODO: Once https://github.com/php/php-src/issues/24074 makes it into
         * all supported PHP releases, we can use the intl module like so:
        if (function_exists('locale_accept_from_http')) {
            $detectedBestLanguage = locale_accept_from_http($_SERVER['HTTP_ACCEPT_LANGUAGE'], $availableLanguages);
            if ($detectedBestLanguage !== false) {
                return $detectedBestLanguage;
            }
        }
        * disabled for now as it's order depends on the ICU version installed
        * and showed large inconsistencies between different test environments
        */

        return self::_getMatchingLanguage(
            self::_normalizeBrowserLanguages(self::getBrowserLanguages(), $availableLanguages),
            $availableLanguages
        );
    }

    /**
     * get list of available translations based on files found
     *
     * @access public
     * @static
     * @return array
     */
    public static function getAvailableLanguages()
    {
        if (count(self::$_availableLanguages) === 0) {
            self::$_availableLanguages[] = 'en'; // en.json is not part of the release archive
            $languageIterator = new AppendIterator();
            $languageIterator->append(new GlobIterator(self::_getPath('??.json')));
            $languageIterator->append(new GlobIterator(self::_getPath('???.json'))); // for jbo
            $languageIterator->append(new GlobIterator(self::_getPath('??-??.json'))); // for regional variants like zh-tw
            foreach ($languageIterator as $file) {
                $language = $file->getBasename('.json');
                if ($language !== 'en') {
                    self::$_availableLanguages[] = $language;
                }
            }
        }
        return self::$_availableLanguages;
    }

    /**
     * detect the clients supported languages and return them ordered by preference
     *
     * From: https://stackoverflow.com/questions/3770513/detect-browser-language-in-php#3771447
     *
     * @access public
     * @static
     * @return array
     */
    public static function getBrowserLanguages()
    {
        $languages = [];
        if (array_key_exists('HTTP_ACCEPT_LANGUAGE', $_SERVER)) {
            $languageRanges = explode(',', trim($_SERVER['HTTP_ACCEPT_LANGUAGE']));
            foreach ($languageRanges as $languageRange) {
                if (preg_match(
                    '/^(\*|[a-zA-Z0-9]{1,8}(?:-[a-zA-Z0-9]{1,8})*)(?:\s*;\s*q\s*=\s*(0(?:\.\d{0,3})|1(?:\.0{0,3})))?$/',
                    trim($languageRange), $match
                )) {
                    if (!isset($match[2])) {
                        $match[2] = '1.0';
                    } else {
                        $match[2] = (string) floatval($match[2]);
                    }
                    if (!isset($languages[$match[2]])) {
                        $languages[$match[2]] = [];
                    }
                    $languages[$match[2]][] = strtolower($match[1]);
                }
            }
            krsort($languages);
        }
        return $languages;
    }

    /**
     * normalize browser language aliases to available locale IDs
     *
     * @access protected
     * @static
     * @param  array $languages
     * @param  array $availableLanguages
     * @return array
     */
    protected static function _normalizeBrowserLanguages($languages, $availableLanguages)
    {
        // Base zh stays before zh-tw because regional locales are appended after base locales.
        $hasSimplifiedChinese = in_array('zh', $availableLanguages, true);
        $hasTraditionalChinese = in_array('zh-tw', $availableLanguages, true);
        foreach ($languages as $quality => $languageRanges) {
            foreach ($languageRanges as $index => $languageRange) {
                $isSimplifiedChinese = $languageRange === 'zh-hans' || str_starts_with($languageRange, 'zh-hans-') ||
                    $languageRange === 'zh-cn' || str_starts_with($languageRange, 'zh-cn-') ||
                    $languageRange === 'zh-sg' || str_starts_with($languageRange, 'zh-sg-');
                $isTraditionalChinese = str_starts_with($languageRange, 'zh-tw-') ||
                    $languageRange === 'zh-hant' || str_starts_with($languageRange, 'zh-hant-') ||
                    $languageRange === 'zh-hk' || str_starts_with($languageRange, 'zh-hk-') ||
                    $languageRange === 'zh-mo' || str_starts_with($languageRange, 'zh-mo-');
                if ($hasSimplifiedChinese && $isSimplifiedChinese) {
                    $languages[$quality][$index] = 'zh';
                } elseif ($hasTraditionalChinese && $isTraditionalChinese) {
                    $languages[$quality][$index] = 'zh-tw';
                }
            }
        }
        return $languages;
    }

    /**
     * get currently loaded language
     *
     * @access public
     * @static
     * @return string
     */
    public static function getLanguage()
    {
        return self::$_language;
    }

    /**
     * get list of language labels
     *
     * Only for given language codes, otherwise all labels.
     *
     * @access public
     * @static
     * @param  array $languages
     * @throws JsonException
     * @return array
     */
    public static function getLanguageLabels($languages = [])
    {
        $file = self::_getPath('languages.json');
        if (count(self::$_languageLabels) === 0 && is_readable($file)) {
            $data = file_get_contents($file);
            self::$_languageLabels = Json::decode($data);
        }
        if (count($languages) === 0) {
            return self::$_languageLabels;
        }
        return array_intersect_key(self::$_languageLabels, array_flip($languages));
    }

    /**
     * determines if the current language is written right-to-left (RTL)
     *
     * @access public
     * @static
     * @return bool
     */
    public static function isRtl()
    {
        return in_array(self::$_language, ['ar', 'fa', 'he']);
    }

    /**
     * get OS-specific copy hotkey modifier key name based on user agent
     *
     * @access public
     * @static
     * @return string 'Cmd' on macOS, 'Ctrl' otherwise
     */
    public static function getCopyHotkey()
    {
        return array_key_exists('HTTP_USER_AGENT', $_SERVER) &&
            str_contains($_SERVER['HTTP_USER_AGENT'], 'Mac') ? self::_('Cmd') : self::_('Ctrl');
    }

    /**
     * set the default language
     *
     * @access public
     * @static
     * @param  string $lang
     */
    public static function setLanguageFallback($lang)
    {
        if (in_array($lang, self::getAvailableLanguages())) {
            self::$_languageFallback = $lang;
        }
    }

    /**
     * get language file path
     *
     * @access protected
     * @static
     * @param  string $file
     * @return string
     */
    protected static function _getPath($file = '')
    {
        if (empty(self::$_path)) {
            self::$_path = PUBLIC_PATH . DIRECTORY_SEPARATOR . 'i18n';
        }
        return self::$_path . (empty($file) ? '' : DIRECTORY_SEPARATOR . $file);
    }

    /**
     * determines the plural form to use based on current language and given number
     *
     * From: https://docs.translatehouse.org/projects/localization-guide/en/latest/l10n/pluralforms.html
     *
     * @access protected
     * @static
     * @param  int $n
     * @return int
     */
    protected static function _getPluralForm($n)
    {
        switch (self::$_language) {
            case 'ar':
                return $n === 0 ? 0 : ($n === 1 ? 1 : ($n === 2 ? 2 : ($n % 100 >= 3 && $n % 100 <= 10 ? 3 : ($n % 100 >= 11 ? 4 : 5))));
            case 'cs':
            case 'sk':
                return $n === 1 ? 0 : ($n >= 2 && $n <= 4 ? 1 : 2);
            case 'co':
            case 'fa':
            case 'fr':
            case 'oc':
            case 'tr':
            case 'zh':
            case 'zh-tw':
                return $n > 1 ? 1 : 0;
            case 'he':
                return $n === 1 ? 0 : ($n === 2 ? 1 : (($n < 0 || $n > 10) && ($n % 10 === 0) ? 2 : 3));
            case 'id':
            case 'ja':
            case 'jbo':
            case 'ko':
            case 'th':
                return 0;
            case 'lt':
                return $n % 10 === 1 && $n % 100 !== 11 ? 0 : (($n % 10 >= 2 && ($n % 100 < 10 || $n % 100 >= 20)) ? 1 : 2);
            case 'pl':
                return $n === 1 ? 0 : ($n % 10 >= 2 && $n % 10 <= 4 && ($n % 100 < 10 || $n % 100 >= 20) ? 1 : 2);
            case 'ro':
                return $n === 1 ? 0 : (($n === 0 || ($n % 100 > 0 && $n % 100 < 20)) ? 1 : 2);
            case 'ru':
            case 'uk':
                return $n % 10 === 1 && $n % 100 !== 11 ? 0 : ($n % 10 >= 2 && $n % 10 <= 4 && ($n % 100 < 10 || $n % 100 >= 20) ? 1 : 2);
            case 'sl':
                return $n % 100 === 1 ? 1 : ($n % 100 === 2 ? 2 : ($n % 100 === 3 || $n % 100 === 4 ? 3 : 0));
            default:
                // bg, ca, de, el, en, es, et, fi, hu, it, nl, no, pt, sv
                return $n !== 1 ? 1 : 0;
        }
    }

    /**
     * compares two language preference arrays and returns the preferred match
     *
     * From: https://stackoverflow.com/questions/3770513/detect-browser-language-in-php#3771447
     *
     * @access protected
     * @static
     * @param  array $acceptedLanguages
     * @param  array $availableLanguages
     * @return string
     */
    protected static function _getMatchingLanguage($acceptedLanguages, $availableLanguages)
    {
        $matches = [];
        $any = false;
        foreach ($acceptedLanguages as $acceptedQuality => $acceptedValues) {
            $acceptedQuality = floatval($acceptedQuality);
            if ($acceptedQuality === 0.0) {
                continue;
            }
            foreach ($acceptedValues as $acceptedValue) {
                if ($acceptedValue === '*') {
                    $any = true;
                }
                foreach ($availableLanguages as $availableValue) {
                    $availableQuality = 1.0;
                    $matchingGrade = self::_matchLanguage($acceptedValue, $availableValue);
                    if ($matchingGrade > 0) {
                        $q = (string) ($acceptedQuality * $availableQuality * $matchingGrade);
                        if (!isset($matches[$q])) {
                            $matches[$q] = [];
                        }
                        if (!in_array($availableValue, $matches[$q])) {
                            $matches[$q][] = $availableValue;
                        }
                    }
                }
            }
        }
        if (count($matches) === 0 && $any) {
            if (count($availableLanguages) > 0) {
                $matches['1.0'] = $availableLanguages;
            }
        }
        if (count($matches) === 0) {
            return self::$_languageFallback;
        }
        krsort($matches);
        $topmatches = current($matches);
        return current($topmatches);
    }

    /**
     * compare two language IDs and return the degree they match
     *
     * From: https://stackoverflow.com/questions/3770513/detect-browser-language-in-php#3771447
     *
     * @access protected
     * @static
     * @param  string $a
     * @param  string $b
     * @return float
     */
    protected static function _matchLanguage($a, $b)
    {
        $a = explode('-', $a);
        $b = explode('-', $b);
        for ($i = 0, $n = min(count($a), count($b)); $i < $n; ++$i) {
            if ($a[$i] !== $b[$i]) {
                break;
            }
        }
        return $i === 0 ? 0 : (float) $i / count($a);
    }
}