| name file | size | edit | permission | action |
|---|---|---|---|---|
| .env | 2733 KB | December 22 2024 06:20:07 | 0644 | |
| 404.html | 58370 KB | November 20 2024 15:32:22 | 0644 | |
| 502.html | 58368 KB | November 20 2024 15:32:22 | 0644 | |
| Modules | - | December 11 2024 21:02:56 | 0755 | |
| README.md | 4158 KB | February 14 2023 12:31:56 | 0644 | |
| app | - | December 11 2024 17:57:48 | 0755 | |
| artisan | 1686 KB | February 14 2023 12:31:56 | 0644 | |
| bootstrap | - | December 11 2024 20:23:36 | 0755 | |
| composer.json | 3761 KB | December 11 2024 22:15:00 | 0644 | |
| composer.lock | 512048 KB | December 11 2024 22:13:28 | 0644 | |
| config | - | June 15 2025 02:09:36 | 0755 | |
| database | - | December 05 2024 20:18:12 | 0755 | |
| dfsdf dfds fd fds findex.html | 1420 KB | November 20 2024 15:32:24 | 0644 | |
| error_log | 1184774 KB | July 19 2025 09:36:23 | 0644 | |
| firoz | - | December 23 2024 13:24:46 | 0755 | |
| index.php | 1667 KB | December 14 2024 05:20:36 | 0644 | |
| lang | - | December 11 2024 21:02:48 | 0755 | |
| modules_statuses.json | 472 KB | November 20 2024 15:32:24 | 0644 | |
| mpos | - | March 31 2025 02:36:31 | 0755 | |
| package.json | 226 KB | February 14 2023 12:31:56 | 0644 | |
| phpunit.xml | 1146 KB | February 14 2023 12:31:56 | 0644 | |
| public | - | March 31 2025 02:36:31 | 0755 | |
| resources | - | December 11 2024 21:10:22 | 0755 | |
| routes | - | June 15 2025 02:09:31 | 0755 | |
| storage | - | December 11 2024 21:12:44 | 0755 | |
| tests | - | December 05 2024 20:18:12 | 0755 | |
| vendor | - | December 11 2024 22:13:30 | 0755 | |
| vite.config.js | 263 KB | February 14 2023 12:31:56 | 0644 |
An associative array where the key is the language code in lowercase * and the value is the corresponding language string.
*/ public static function getAllLanguages(): array { // init static $LANGUAGES = []; if ($LANGUAGES !== []) { return $LANGUAGES; } foreach ((new \ReflectionClass(__CLASS__))->getConstants() as $constant => $lang) { if (\strpos($constant, 'EXTRA') !== false) { $LANGUAGES[\strtolower($constant)] = $lang; } else { $LANGUAGES[\strtolower(\str_replace('_LANGUAGE_CODE', '', $constant))] = $lang; } } return $LANGUAGES; } /** * Returns an replacement array for ASCII methods. * * EXAMPLE:
* $array = ASCII::charsArray();
* var_dump($array['ru']['б']); // 'b'
*
*
* @param bool $replace_extra_symbols [optional] Add some more replacements e.g. "£" with " pound ".
* * @psalm-pure * * @return arrayAn array where the key is the language code, and the value is * an associative array mapping original characters to their replacements.
*/ public static function charsArray(bool $replace_extra_symbols = false): array { if ($replace_extra_symbols) { self::prepareAsciiAndExtrasMaps(); return self::$ASCII_MAPS_AND_EXTRAS ?? []; } self::prepareAsciiMaps(); return self::$ASCII_MAPS ?? []; } /** * Returns an replacement array for ASCII methods with a mix of multiple languages. * * EXAMPLE:
* $array = ASCII::charsArrayWithMultiLanguageValues();
* var_dump($array['b']); // ['β', 'б', 'ဗ', 'ბ', 'ب']
*
*
* @param bool $replace_extra_symbols [optional] Add some more replacements e.g. "£" with " pound ".
* * @psalm-pure * * @return arrayAn array of replacements.
*/ public static function charsArrayWithMultiLanguageValues(bool $replace_extra_symbols = false): array { static $CHARS_ARRAY = []; $cacheKey = '' . $replace_extra_symbols; if (isset($CHARS_ARRAY[$cacheKey])) { return $CHARS_ARRAY[$cacheKey]; } // init $return = []; $language_all_chars = self::charsArrayWithSingleLanguageValues( $replace_extra_symbols, false ); /* @noinspection AlterInForeachInspection | ok here */ foreach ($language_all_chars as $key => &$value) { $return[$value][] = $key; } $CHARS_ARRAY[$cacheKey] = $return; return $return; } /** * Returns an replacement array for ASCII methods with one language. * * For example, German will map 'ä' to 'ae', while other languages * will simply return e.g. 'a'. * * EXAMPLE:
* $array = ASCII::charsArrayWithOneLanguage('ru');
* $tmpKey = \array_search('yo', $array['replace']);
* echo $array['orig'][$tmpKey]; // 'ё'
*
*
* @param string $language [optional] Language of the source string e.g.: en, de_at, or de-ch. * (default is 'en') | ASCII::*_LANGUAGE_CODE
* @param bool $replace_extra_symbols [optional]Add some more replacements e.g. "£" with " pound ".
* @param bool $asOrigReplaceArray [optional]TRUE === return {orig: list
* $array = ASCII::charsArrayWithSingleLanguageValues();
* $tmpKey = \array_search('hnaik', $array['replace']);
* echo $array['orig'][$tmpKey]; // '၌'
*
*
* @param bool $replace_extra_symbols [optional] Add some more replacements e.g. "£" with " pound ".
* @param bool $asOrigReplaceArray [optional]TRUE === return {orig: list
The string to be sanitized.
* @param bool $normalize_whitespace [optional]Set to true, if you need to normalize the * whitespace.
* @param bool $normalize_msword [optional]Set to true, if you need to normalize MS Word chars * e.g.: "…" * => "..."
* @param bool $keep_non_breaking_space [optional]Set to true, to keep non-breaking-spaces, in * combination with * $normalize_whitespace
* @param bool $remove_invisible_characters [optional]Set to false, if you not want to remove invisible * characters e.g.: "\0"
* * @psalm-pure * * @return string *A clean UTF-8 string.
*/ public static function clean( string $str, bool $normalize_whitespace = true, bool $keep_non_breaking_space = false, bool $normalize_msword = true, bool $remove_invisible_characters = true ): string { // http://stackoverflow.com/questions/1401317/remove-non-utf8-characters-from-string // caused connection reset problem on larger strings $regex = '/ ( (?: [\x00-\x7F] # single-byte sequences 0xxxxxxx | [\xC0-\xDF][\x80-\xBF] # double-byte sequences 110xxxxx 10xxxxxx | [\xE0-\xEF][\x80-\xBF]{2} # triple-byte sequences 1110xxxx 10xxxxxx * 2 | [\xF0-\xF7][\x80-\xBF]{3} # quadruple-byte sequence 11110xxx 10xxxxxx * 3 ){1,100} # ...one or more times ) | ( [\x80-\xBF] ) # invalid byte in range 10000000 - 10111111 | ( [\xC0-\xFF] ) # invalid byte in range 11000000 - 11111111 /x'; $str = (string) \preg_replace($regex, '$1', $str); if ($normalize_whitespace) { $str = self::normalize_whitespace($str, $keep_non_breaking_space); } if ($normalize_msword) { $str = self::normalize_msword($str); } if ($remove_invisible_characters) { $str = self::remove_invisible_characters($str); } return $str; } /** * Checks if a string is 7 bit ASCII. * * EXAMPLE:
* ASCII::is_ascii('白'); // false
*
*
* @param string $str The string to check.
* * @psalm-pure * * @return bool *
* true if it is ASCII
* false otherwise
*
* ASCII::normalize_msword('„Abcdef…”'); // '"Abcdef..."'
*
*
* @param string $str The string to be normalized.
* * @psalm-pure * * @return string *A string with normalized characters for commonly used chars in Word documents.
*/ public static function normalize_msword(string $str): string { if ($str === '') { return ''; } static $MSWORD_CACHE = ['orig' => [], 'replace' => []]; if (empty($MSWORD_CACHE['orig'])) { self::prepareAsciiMaps(); $map = self::$ASCII_MAPS[self::EXTRA_MSWORD_CHARS_LANGUAGE_CODE] ?? []; $MSWORD_CACHE = [ 'orig' => \array_keys($map), 'replace' => \array_values($map), ]; } return \str_replace($MSWORD_CACHE['orig'], $MSWORD_CACHE['replace'], $str); } /** * Normalize the whitespace. * * EXAMPLE:
* ASCII::normalize_whitespace("abc-\xc2\xa0-öäü-\xe2\x80\xaf-\xE2\x80\xAC", true); // "abc-\xc2\xa0-öäü- -"
*
*
* @param string $str The string to be normalized.
* @param bool $keepNonBreakingSpace [optional]Set to true, to keep non-breaking-spaces.
* @param bool $keepBidiUnicodeControls [optional]Set to true, to keep non-printable (for the web) * bidirectional text chars.
* @param bool $normalize_control_characters [optional]Set to true, to convert e.g. LINE-, PARAGRAPH-SEPARATOR with "\n" and LINE TABULATION with "\t".
* * @psalm-pure * * @return string *A string with normalized whitespace.
*/ public static function normalize_whitespace( string $str, bool $keepNonBreakingSpace = false, bool $keepBidiUnicodeControls = false, bool $normalize_control_characters = false ): string { if ($str === '') { return ''; } static $WHITESPACE_CACHE = []; $cacheKey = (int) $keepNonBreakingSpace; if ($normalize_control_characters) { $str = \str_replace( [ "\x0d\x0c", // 'END OF LINE' "\xe2\x80\xa8", // 'LINE SEPARATOR' "\xe2\x80\xa9", // 'PARAGRAPH SEPARATOR' "\x0c", // 'FORM FEED' // "\f" "\x0b", // 'VERTICAL TAB' // "\v" ], [ "\n", "\n", "\n", "\n", "\t", ], $str ); } if (!isset($WHITESPACE_CACHE[$cacheKey])) { self::prepareAsciiMaps(); $WHITESPACE_CACHE[$cacheKey] = self::$ASCII_MAPS[self::EXTRA_WHITESPACE_CHARS_LANGUAGE_CODE] ?? []; if ($keepNonBreakingSpace) { unset($WHITESPACE_CACHE[$cacheKey]["\xc2\xa0"]); } $WHITESPACE_CACHE[$cacheKey] = array_keys($WHITESPACE_CACHE[$cacheKey]); } if (!$keepBidiUnicodeControls) { static $BIDI_UNICODE_CONTROLS_CACHE = null; if ($BIDI_UNICODE_CONTROLS_CACHE === null) { $BIDI_UNICODE_CONTROLS_CACHE = self::$BIDI_UNI_CODE_CONTROLS_TABLE; } $str = \str_replace($BIDI_UNICODE_CONTROLS_CACHE, '', $str); } return \str_replace($WHITESPACE_CACHE[$cacheKey], ' ', $str); } /** * Remove invisible characters from a string. * * This prevents malicious code injection through null bytes or other control characters. * * copy&past from https://github.com/bcit-ci/CodeIgniter/blob/develop/system/core/Common.php * * @param string $str * @param bool $url_encoded * @param string $replacement * @param bool $keep_basic_control_characters * * @psalm-pure * * @return string */ public static function remove_invisible_characters( string $str, bool $url_encoded = false, string $replacement = '', bool $keep_basic_control_characters = true ): string { // init $non_displayables = []; // every control character except: // - newline (dec 10), // - carriage return (dec 13), // - horizontal tab (dec 09) if ($url_encoded) { $non_displayables[] = '/%0[0-8bcefBCEF]/'; // url encoded 00-08, 11, 12, 14, 15 $non_displayables[] = '/%1[0-9a-fA-F]/'; // url encoded 16-31 } if ($keep_basic_control_characters) { $non_displayables[] = '/[\x00-\x08\x0B\x0C\x0E-\x1F\x7F]+/S'; // 00-08, 11, 12, 14-31, 127 } else { $str = self::normalize_whitespace($str, false, false, true); $non_displayables[] = '/[^\P{C}\s]/u'; } do { $str = (string) \preg_replace($non_displayables, $replacement, $str, -1, $count); } while ($count !== 0); return $str; } /** * WARNING: This method will return broken characters and is only for special cases. * * Convert two UTF-8 encoded strings to a single-byte strings suitable for * functions that need the same string length after the conversion. * * The function simply uses (and updates) a tailored dynamic encoding * (in/out map parameter) where non-ascii characters are remapped to * the range [128-255] in order of appearance. * * @return array{0: string, 1: string} */ public static function to_ascii_remap(string $str1, string $str2): array { $charMap = []; $str1 = self::to_ascii_remap_intern($str1, $charMap); $str2 = self::to_ascii_remap_intern($str2, $charMap); return [$str1, $str2]; } /** * Returns an ASCII version of the string. A set of non-ASCII characters are * replaced with their closest ASCII counterparts, and the rest are removed * by default. The language or locale of the source string can be supplied * for language-specific transliteration in any of the following formats: * en, en_GB, or en-GB. For example, passing "de" results in "äöü" mapping * to "aeoeue" rather than "aou" as in other languages. * * EXAMPLE:
* ASCII::to_ascii('�Düsseldorf�', 'en'); // Dusseldorf
*
*
* @param string $str The input string.
* @param string $language [optional]Language of the source string. * (default is 'en') | ASCII::*_LANGUAGE_CODE
* @param bool $remove_unsupported_chars [optional]Whether to remove the * unsupported characters.
* @param bool $replace_extra_symbols [optional]Add some more replacements e.g. "£" with " pound * ".
* @param bool $use_transliterate [optional]Use ASCII::to_transliterate() for unknown chars.
* @param bool $replace_single_chars_only [optional]Single char replacement is better for the * performance, but some languages need to replace more than one char * at the same time. If FALSE === auto-setting, depended on the * language
* * @psalm-pure * * @return string *A string that contains only ASCII characters.
* * @phpstan-param ASCII::*_LANGUAGE_CODE $language */ public static function to_ascii( string $str, string $language = self::ENGLISH_LANGUAGE_CODE, bool $remove_unsupported_chars = true, bool $replace_extra_symbols = false, bool $use_transliterate = false, bool $replace_single_chars_only = false ): string { if ($str === '') { return ''; } /** @phpstan-var ASCII::*_LANGUAGE_CODE $language - hack for phpstan */ $language = self::get_language($language); static $EXTRA_SYMBOLS_CACHE = null; static $REPLACE_HELPER_CACHE = []; $cacheKey = $language . '-' . $replace_extra_symbols; if (!isset($REPLACE_HELPER_CACHE[$cacheKey])) { $langAll = self::charsArrayWithSingleLanguageValues($replace_extra_symbols, false); $langSpecific = self::charsArrayWithOneLanguage($language, $replace_extra_symbols, false); if ($langSpecific === []) { $REPLACE_HELPER_CACHE[$cacheKey] = $langAll; } else { $REPLACE_HELPER_CACHE[$cacheKey] = \array_merge([], $langAll, $langSpecific); } } if ( $replace_extra_symbols && $EXTRA_SYMBOLS_CACHE === null ) { $EXTRA_SYMBOLS_CACHE = []; foreach (self::$ASCII_EXTRAS ?? [] as $extrasDataTmp) { foreach ($extrasDataTmp as $extrasDataKeyTmp => $extrasDataValueTmp) { $EXTRA_SYMBOLS_CACHE[$extrasDataKeyTmp] = $extrasDataKeyTmp; } } $EXTRA_SYMBOLS_CACHE = \implode('', $EXTRA_SYMBOLS_CACHE); } $charDone = []; if (\preg_match_all('/' . self::$REGEX_ASCII . ($replace_extra_symbols ? '|[' . $EXTRA_SYMBOLS_CACHE . ']' : '') . '/u', $str, $matches)) { if (!$replace_single_chars_only) { if (self::$LANGUAGE_MAX_KEY === null) { self::$LANGUAGE_MAX_KEY = self::getData('ascii_language_max_key'); } $maxKeyLength = self::$LANGUAGE_MAX_KEY[$language] ?? 0; if ($maxKeyLength >= 5) { foreach ($matches[0] as $keyTmp => $char) { if (isset($matches[0][$keyTmp + 4])) { $fiveChars = $matches[0][$keyTmp + 0] . $matches[0][$keyTmp + 1] . $matches[0][$keyTmp + 2] . $matches[0][$keyTmp + 3] . $matches[0][$keyTmp + 4]; } else { $fiveChars = null; } if ( $fiveChars && !isset($charDone[$fiveChars]) && isset($REPLACE_HELPER_CACHE[$cacheKey][$fiveChars]) && \strpos($str, $fiveChars) !== false ) { // DEBUG //\var_dump($str, $fiveChars, $REPLACE_HELPER_CACHE[$cacheKey][$fiveChars]); $charDone[$fiveChars] = true; $str = \str_replace($fiveChars, $REPLACE_HELPER_CACHE[$cacheKey][$fiveChars], $str); // DEBUG //\var_dump($str, "\n"); } } } if ($maxKeyLength >= 4) { foreach ($matches[0] as $keyTmp => $char) { if (isset($matches[0][$keyTmp + 3])) { $fourChars = $matches[0][$keyTmp + 0] . $matches[0][$keyTmp + 1] . $matches[0][$keyTmp + 2] . $matches[0][$keyTmp + 3]; } else { $fourChars = null; } if ( $fourChars && !isset($charDone[$fourChars]) && isset($REPLACE_HELPER_CACHE[$cacheKey][$fourChars]) && \strpos($str, $fourChars) !== false ) { // DEBUG //\var_dump($str, $fourChars, $REPLACE_HELPER_CACHE[$cacheKey][$fourChars]); $charDone[$fourChars] = true; $str = \str_replace($fourChars, $REPLACE_HELPER_CACHE[$cacheKey][$fourChars], $str); // DEBUG //\var_dump($str, "\n"); } } } foreach ($matches[0] as $keyTmp => $char) { if (isset($matches[0][$keyTmp + 2])) { $threeChars = $matches[0][$keyTmp + 0] . $matches[0][$keyTmp + 1] . $matches[0][$keyTmp + 2]; } else { $threeChars = null; } if ( $threeChars && !isset($charDone[$threeChars]) && isset($REPLACE_HELPER_CACHE[$cacheKey][$threeChars]) && \strpos($str, $threeChars) !== false ) { // DEBUG //\var_dump($str, $threeChars, $REPLACE_HELPER_CACHE[$cacheKey][$threeChars]); $charDone[$threeChars] = true; $str = \str_replace($threeChars, $REPLACE_HELPER_CACHE[$cacheKey][$threeChars], $str); // DEBUG //\var_dump($str, "\n"); } } foreach ($matches[0] as $keyTmp => $char) { if (isset($matches[0][$keyTmp + 1])) { $twoChars = $matches[0][$keyTmp + 0] . $matches[0][$keyTmp + 1]; } else { $twoChars = null; } if ( $twoChars && !isset($charDone[$twoChars]) && isset($REPLACE_HELPER_CACHE[$cacheKey][$twoChars]) && \strpos($str, $twoChars) !== false ) { // DEBUG //\var_dump($str, $twoChars, $REPLACE_HELPER_CACHE[$cacheKey][$twoChars]); $charDone[$twoChars] = true; $str = \str_replace($twoChars, $REPLACE_HELPER_CACHE[$cacheKey][$twoChars], $str); // DEBUG //\var_dump($str, "\n"); } } } foreach ($matches[0] as $char) { if ( !isset($charDone[$char]) && isset($REPLACE_HELPER_CACHE[$cacheKey][$char]) && \strpos($str, $char) !== false ) { // DEBUG //\var_dump($str, $char, $REPLACE_HELPER_CACHE[$cacheKey][$char]); $charDone[$char] = true; $str = \str_replace($char, $REPLACE_HELPER_CACHE[$cacheKey][$char], $str); // DEBUG //\var_dump($str, "\n"); } } } if (!isset(self::$ASCII_MAPS[$language])) { $use_transliterate = true; } if ($use_transliterate) { $str = self::to_transliterate($str, null, false); } if ($remove_unsupported_chars) { $str = (string) \str_replace(["\n\r", "\n", "\r", "\t"], ' ', $str); $str = (string) \preg_replace('/' . self::$REGEX_ASCII . '/', '', $str); } return $str; } /** * Convert given string to safe filename (and keep string case). * * EXAMPLE:
* ASCII::to_filename('שדגשדג.png', true)); // 'shdgshdg.png'
*
*
* @param string $str The string input.
* @param bool $use_transliterateASCII::to_transliterate() is used by default - unsafe characters are * simply replaced with hyphen otherwise.
* @param string $fallback_charThe fallback character. - "-" is the default
* * @psalm-pure * * @return string *A string that contains only safe characters for a filename.
*/ public static function to_filename( string $str, bool $use_transliterate = true, string $fallback_char = '-' ): string { if ($use_transliterate) { $str = self::to_transliterate($str, $fallback_char); } $fallback_char_escaped = \preg_quote($fallback_char, '/'); $str = (string) \preg_replace( [ '/[^' . $fallback_char_escaped . '.\\-a-zA-Z\d\\s]/', // 1) remove un-needed chars '/\s+/u', // 2) convert spaces to $fallback_char '/[' . $fallback_char_escaped . ']+/u', // 3) remove double $fallback_char's ], [ '', $fallback_char, $fallback_char, ], $str ); return \trim($str, $fallback_char); } /** * Converts a string into a URL-friendly slug. * * - This includes replacing non-ASCII characters with their closest ASCII equivalents, removing remaining * non-ASCII and non-alphanumeric characters, and replacing whitespace with $separator. * - The separator defaults to a single dash, and the string is also converted to lowercase. * - The language of the source string can also be supplied for language-specific transliteration. * * @param string $strThe string input.
* @param string $separator [optional]The string used to replace whitespace.
* @param string $language [optional]Language of the source string. * (default is 'en') | ASCII::*_LANGUAGE_CODE
* @param arrayA map of replaceable strings.
* @param bool $replace_extra_symbols [optional]Add some more replacements e.g. "£" with " * pound ".
* @param bool $use_str_to_lower [optional]Use "string to lower" for the input.
* @param bool $use_transliterate [optional]Use ASCII::to_transliterate() for unknown * chars.
* @psalm-pure * * @return string *The URL-friendly slug.
* * @phpstan-param ASCII::*_LANGUAGE_CODE $language */ public static function to_slugify( string $str, string $separator = '-', string $language = self::ENGLISH_LANGUAGE_CODE, array $replacements = [], bool $replace_extra_symbols = false, bool $use_str_to_lower = true, bool $use_transliterate = false ): string { if ($str === '') { return ''; } foreach ($replacements as $from => $to) { $str = \str_replace($from, $to, $str); } $str = self::to_ascii( $str, $language, false, $replace_extra_symbols, $use_transliterate ); $str = \str_replace('@', $separator, $str); $str = (string) \preg_replace( '/[^a-zA-Z\\d\\s\\-_' . \preg_quote($separator, '/') . ']/', '', $str ); if ($use_str_to_lower) { $str = \strtolower($str); } $str = (string) \preg_replace('/^[\'\\s]+|[\'\\s]+$/', '', $str); $str = (string) \preg_replace('/\\B([A-Z])/', '-\1', $str); $str = (string) \preg_replace('/[\\-_\\s]+/', $separator, $str); $l = \strlen($separator); if ($l && \strpos($str, $separator) === 0) { $str = (string) \substr($str, $l); } if (\substr($str, -$l) === $separator) { $str = (string) \substr($str, 0, \strlen($str) - $l); } return $str; } /** * Returns an ASCII version of the string. A set of non-ASCII characters are * replaced with their closest ASCII counterparts, and the rest are removed * unless instructed otherwise. * * EXAMPLE:
* ASCII::to_transliterate('déjà σσς iıii'); // 'deja sss iiii'
*
*
* @param string $str The input string.
* @param string|null $unknown [optional]Character use if character unknown. (default is '?') * But you can also use NULL to keep the unknown chars.
* @param bool $strict [optional]Use "transliterator_transliterate()" from PHP-Intl * * @psalm-pure * * @return string *
A String that contains only ASCII characters.
*/ public static function to_transliterate( string $str, $unknown = '?', bool $strict = false ): string { static $UTF8_TO_TRANSLIT = null; static $TRANSLITERATOR = null; static $SUPPORT_INTL = null; if ($str === '') { return ''; } if ($SUPPORT_INTL === null) { $SUPPORT_INTL = \extension_loaded('intl'); } // check if we only have ASCII, first (better performance) $str_tmp = $str; if (self::is_ascii($str)) { return $str; } $str = self::clean($str); // check again if we only have ASCII, now ... if ( $str_tmp !== $str && self::is_ascii($str) ) { return $str; } if ( $strict && $SUPPORT_INTL === true ) { if (!isset($TRANSLITERATOR)) { // INFO: see "*-Latin" rules via "transliterator_list_ids()" $TRANSLITERATOR = \transliterator_create('NFKC; [:Nonspacing Mark:] Remove; NFKC; Any-Latin; Latin-ASCII;'); } // INFO: https://unicode.org/cldr/utility/character.jsp $str_tmp = \transliterator_transliterate($TRANSLITERATOR, $str); if ($str_tmp !== false) { // check again if we only have ASCII, now ... if ( $str_tmp !== $str && self::is_ascii($str_tmp) ) { return $str_tmp; } $str = $str_tmp; } } if (self::$ORD === null) { self::$ORD = self::getData('ascii_ord'); } \preg_match_all('/.|[^\x00]$/us', $str, $array_tmp); $chars = $array_tmp[0]; $ord = null; $str_tmp = ''; foreach ($chars as &$c) { $ordC0 = self::$ORD[$c[0]]; if ($ordC0 >= 0 && $ordC0 <= 127) { $str_tmp .= $c; continue; } $ordC1 = self::$ORD[$c[1]]; // ASCII - next please if ($ordC0 >= 192 && $ordC0 <= 223) { $ord = ($ordC0 - 192) * 64 + ($ordC1 - 128); } if ($ordC0 >= 224) { $ordC2 = self::$ORD[$c[2]]; if ($ordC0 <= 239) { $ord = ($ordC0 - 224) * 4096 + ($ordC1 - 128) * 64 + ($ordC2 - 128); } if ($ordC0 >= 240) { $ordC3 = self::$ORD[$c[3]]; if ($ordC0 <= 247) { $ord = ($ordC0 - 240) * 262144 + ($ordC1 - 128) * 4096 + ($ordC2 - 128) * 64 + ($ordC3 - 128); } // We only process valid UTF-8 chars (<= 4 byte), so we don't need this code here ... /* if ($ordC0 >= 248) { $ordC4 = self::$ORD[$c[4]]; if ($ordC0 <= 251) { $ord = ($ordC0 - 248) * 16777216 + ($ordC1 - 128) * 262144 + ($ordC2 - 128) * 4096 + ($ordC3 - 128) * 64 + ($ordC4 - 128); } if ($ordC0 >= 252) { $ordC5 = self::$ORD[$c[5]]; if ($ordC0 <= 253) { $ord = ($ordC0 - 252) * 1073741824 + ($ordC1 - 128) * 16777216 + ($ordC2 - 128) * 262144 + ($ordC3 - 128) * 4096 + ($ordC4 - 128) * 64 + ($ordC5 - 128); } } } */ } } if ( $ordC0 === 254 || $ordC0 === 255 || $ord === null ) { $str_tmp .= $unknown ?? $c; continue; } $bank = $ord >> 8; if (!isset($UTF8_TO_TRANSLIT[$bank])) { $UTF8_TO_TRANSLIT[$bank] = self::getDataIfExists(\sprintf('x%03x', $bank)); } $new_char = $ord & 255; if (isset($UTF8_TO_TRANSLIT[$bank][$new_char])) { // keep for debugging /* echo "file: " . sprintf('x%02x', $bank) . "\n"; echo "char: " . $c . "\n"; echo "ord: " . $ord . "\n"; echo "new_char: " . $new_char . "\n"; echo "new_char: " . mb_chr($new_char) . "\n"; echo "ascii: " . $UTF8_TO_TRANSLIT[$bank][$new_char] . "\n"; echo "bank:" . $bank . "\n\n"; */ $new_char = $UTF8_TO_TRANSLIT[$bank][$new_char]; /* @noinspection PhpStatementHasEmptyBodyInspection */ if ($unknown === null && $new_char === '') { // nothing } elseif ( $new_char === '[?]' || $new_char === '[?] ' ) { $c = $unknown ?? $c; } else { $c = $new_char; } } else { // keep for debugging missing chars /* echo "file: " . sprintf('x%02x', $bank) . "\n"; echo "char: " . $c . "\n"; echo "ord: " . $ord . "\n"; echo "new_char: " . $new_char . "\n"; echo "new_char: " . mb_chr($new_char) . "\n"; echo "bank:" . $bank . "\n\n"; */ $c = $unknown ?? $c; } $str_tmp .= $c; } return $str_tmp; } /** * WARNING: This method will return broken characters and is only for special cases. * * Convert a UTF-8 encoded string to a single-byte string suitable for * functions that need the same string length after the conversion. * * The function simply uses (and updates) a tailored dynamic encoding * (in/out map parameter) where non-ascii characters are remapped to * the range [128-255] in order of appearance. * * Thus, it supports up to 128 different multibyte code points max over * the whole set of strings sharing this encoding. * * Source: https://github.com/KEINOS/mb_levenshtein * * @param string $strUTF-8 string to be converted to extended ASCII.
* @param array $mapInternal-Map of code points to ASCII characters.
* * @return string *Mapped broken string.
* * @phpstan-param array