5707056869

Build Type

push

github

Committed by

Commit Message

support for PHP 8.3

Run Details

3 of 3 new or added lines in 1 file covered. (100.0%)

1580 of 1753 relevant lines covered (90.13%)

0.9 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

87.44

/src/Utils/Strings.php

<?php

/**
 * This file is part of the Nette Framework (https://nette.org)
 * Copyright (c) 2004 David Grudl (https://davidgrudl.com)
 */

declare(strict_types=1);

namespace Nette\Utils;

use JetBrains\PhpStorm\Language;
use Nette;
use function is_array, is_object, strlen;


/**
 * String tools library.
 */
class Strings
{
        use Nette\StaticClass;

        public const TRIM_CHARACTERS = " \t\n\r\0\x0B\u{A0}";


        /**
         * Checks if the string is valid in UTF-8 encoding.
         */
        public static function checkEncoding(string $s): bool
        {
                return $s === self::fixEncoding($s);
        }


        /**
         * Removes all invalid UTF-8 characters from a string.
         */
        public static function fixEncoding(string $s): string
        {
                // removes xD800-xDFFF, x110000 and higher
                return htmlspecialchars_decode(htmlspecialchars($s, ENT_NOQUOTES | ENT_IGNORE, 'UTF-8'), ENT_NOQUOTES);
        }


        /**
         * Returns a specific character in UTF-8 from code point (number in range 0x0000..D7FF or 0xE000..10FFFF).
         * @throws Nette\InvalidArgumentException if code point is not in valid range
         */
        public static function chr(int $code): string
        {
                if ($code < 0 || ($code >= 0xD800 && $code <= 0xDFFF) || $code > 0x10FFFF) {
                        throw new Nette\InvalidArgumentException('Code point must be in range 0x0 to 0xD7FF or 0xE000 to 0x10FFFF.');
                } elseif (!extension_loaded('iconv')) {
                        throw new Nette\NotSupportedException(__METHOD__ . '() requires ICONV extension that is not loaded.');
                }

                return iconv('UTF-32BE', 'UTF-8//IGNORE', pack('N', $code));
        }


        /**
         * Starts the $haystack string with the prefix $needle?
         */
        public static function startsWith(string $haystack, string $needle): bool
        {
                return strncmp($haystack, $needle, strlen($needle)) === 0;
        }


        /**
         * Ends the $haystack string with the suffix $needle?
         */
        public static function endsWith(string $haystack, string $needle): bool
        {
                return $needle === '' || substr($haystack, -strlen($needle)) === $needle;
        }


        /**
         * Does $haystack contain $needle?
         */
        public static function contains(string $haystack, string $needle): bool
        {
                return strpos($haystack, $needle) !== false;
        }


        /**
         * Returns a part of UTF-8 string specified by starting position and length. If start is negative,
         * the returned string will start at the start'th character from the end of string.
         */
        public static function substring(string $s, int $start, ?int $length = null): string
        {
                if (function_exists('mb_substr')) {
                        return mb_substr($s, $start, $length, 'UTF-8'); // MB is much faster
                } elseif (!extension_loaded('iconv')) {
                        throw new Nette\NotSupportedException(__METHOD__ . '() requires extension ICONV or MBSTRING, neither is loaded.');
                } elseif ($length === null) {
                        $length = self::length($s);
                } elseif ($start < 0 && $length < 0) {
                        $start += self::length($s); // unifies iconv_substr behavior with mb_substr
                }

                return iconv_substr($s, $start, $length, 'UTF-8');
        }


        /**
         * Removes control characters, normalizes line breaks to `\n`, removes leading and trailing blank lines,
         * trims end spaces on lines, normalizes UTF-8 to the normal form of NFC.
         */
        public static function normalize(string $s): string
        {
                // convert to compressed normal form (NFC)
                if (class_exists('Normalizer', false) && ($n = \Normalizer::normalize($s, \Normalizer::FORM_C)) !== false) {
                        $s = $n;
                }

                $s = self::normalizeNewLines($s);

                // remove control characters; leave \t + \n
                $s = self::pcre('preg_replace', ['#[\x00-\x08\x0B-\x1F\x7F-\x9F]+#u', '', $s]);

                // right trim
                $s = self::pcre('preg_replace', ['#[\t ]+$#m', '', $s]);

                // leading and trailing blank lines
                $s = trim($s, "\n");

                return $s;
        }


        /**
         * Standardize line endings to unix-like.
         */
        public static function normalizeNewLines(string $s): string
        {
                return str_replace(["\r\n", "\r"], "\n", $s);
        }


        /**
         * Converts UTF-8 string to ASCII, ie removes diacritics etc.
         */
        public static function toAscii(string $s): string
        {
                $iconv = defined('ICONV_IMPL') ? trim(ICONV_IMPL, '"\'') : null;
                static $transliterator = null;
                if ($transliterator === null) {
                        if (class_exists('Transliterator', false)) {
                                $transliterator = \Transliterator::create('Any-Latin; Latin-ASCII');
                        } else {
                                trigger_error(__METHOD__ . "(): it is recommended to enable PHP extensions 'intl'.", E_USER_NOTICE);
                                $transliterator = false;
                        }
                }

                // remove control characters and check UTF-8 validity
                $s = self::pcre('preg_replace', ['#[^\x09\x0A\x0D\x20-\x7E\xA0-\x{2FF}\x{370}-\x{10FFFF}]#u', '', $s]);

                // transliteration (by Transliterator and iconv) is not optimal, replace some characters directly
                $s = strtr($s, ["\u{201E}" => '"', "\u{201C}" => '"', "\u{201D}" => '"', "\u{201A}" => "'", "\u{2018}" => "'", "\u{2019}" => "'", "\u{B0}" => '^', "\u{42F}" => 'Ya', "\u{44F}" => 'ya', "\u{42E}" => 'Yu', "\u{44E}" => 'yu', "\u{c4}" => 'Ae', "\u{d6}" => 'Oe', "\u{dc}" => 'Ue', "\u{1e9e}" => 'Ss', "\u{e4}" => 'ae', "\u{f6}" => 'oe', "\u{fc}" => 'ue', "\u{df}" => 'ss']); // „ “ ” ‚ ‘ ’ ° Я я Ю ю Ä Ö Ü ẞ ä ö ü ß
                if ($iconv !== 'libiconv') {
                        $s = strtr($s, ["\u{AE}" => '(R)', "\u{A9}" => '(c)', "\u{2026}" => '...', "\u{AB}" => '<<', "\u{BB}" => '>>', "\u{A3}" => 'lb', "\u{A5}" => 'yen', "\u{B2}" => '^2', "\u{B3}" => '^3', "\u{B5}" => 'u', "\u{B9}" => '^1', "\u{BA}" => 'o', "\u{BF}" => '?', "\u{2CA}" => "'", "\u{2CD}" => '_', "\u{2DD}" => '"', "\u{1FEF}" => '', "\u{20AC}" => 'EUR', "\u{2122}" => 'TM', "\u{212E}" => 'e', "\u{2190}" => '<-', "\u{2191}" => '^', "\u{2192}" => '->', "\u{2193}" => 'V', "\u{2194}" => '<->']); // ® © … « » £ ¥ ² ³ µ ¹ º ¿ ˊ ˍ ˝ ` € ™ ℮ ← ↑ → ↓ ↔
                }

                if ($transliterator) {
                        $s = $transliterator->transliterate($s);
                        // use iconv because The transliterator leaves some characters out of ASCII, eg → ʾ
                        if ($iconv === 'glibc') {
                                $s = strtr($s, '?', "\x01"); // temporarily hide ? to distinguish them from the garbage that iconv creates
                                $s = iconv('UTF-8', 'ASCII//TRANSLIT//IGNORE', $s);
                                $s = str_replace(['?', "\x01"], ['', '?'], $s); // remove garbage and restore ? characters
                        } elseif ($iconv === 'libiconv') {
                                $s = iconv('UTF-8', 'ASCII//TRANSLIT//IGNORE', $s);
                        } else { // null or 'unknown' (#216)
                                $s = self::pcre('preg_replace', ['#[^\x00-\x7F]++#', '', $s]); // remove non-ascii chars
                        }
                } elseif ($iconv === 'glibc' || $iconv === 'libiconv') {
                        // temporarily hide these characters to distinguish them from the garbage that iconv creates
                        $s = strtr($s, '`\'"^~?', "\x01\x02\x03\x04\x05\x06");
                        if ($iconv === 'glibc') {
                                // glibc implementation is very limited. transliterate into Windows-1250 and then into ASCII, so most Eastern European characters are preserved
                                $s = iconv('UTF-8', 'WINDOWS-1250//TRANSLIT//IGNORE', $s);
                                $s = strtr(
                                        $s,
                                        "\xa5\xa3\xbc\x8c\xa7\x8a\xaa\x8d\x8f\x8e\xaf\xb9\xb3\xbe\x9c\x9a\xba\x9d\x9f\x9e\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf8\xf9\xfa\xfb\xfc\xfd\xfe\x96\xa0\x8b\x97\x9b\xa6\xad\xb7",
                                        'ALLSSSSTZZZallssstzzzRAAAALCCCEEEEIIDDNNOOOOxRUUUUYTsraaaalccceeeeiiddnnooooruuuuyt- <->|-.'
                                );
                                $s = self::pcre('preg_replace', ['#[^\x00-\x7F]++#', '', $s]);
                        } else {
                                $s = iconv('UTF-8', 'ASCII//TRANSLIT//IGNORE', $s);
                        }

                        // remove garbage that iconv creates during transliteration (eg Ý -> Y')
                        $s = str_replace(['`', "'", '"', '^', '~', '?'], '', $s);
                        // restore temporarily hidden characters
                        $s = strtr($s, "\x01\x02\x03\x04\x05\x06", '`\'"^~?');
                } else {
                        $s = self::pcre('preg_replace', ['#[^\x00-\x7F]++#', '', $s]); // remove non-ascii chars
                }

                return $s;
        }


        /**
         * Modifies the UTF-8 string to the form used in the URL, ie removes diacritics and replaces all characters
         * except letters of the English alphabet and numbers with a hyphens.
         */
        public static function webalize(string $s, ?string $charlist = null, bool $lower = true): string
        {
                $s = self::toAscii($s);
                if ($lower) {
                        $s = strtolower($s);
                }

                $s = self::pcre('preg_replace', ['#[^a-z0-9' . ($charlist !== null ? preg_quote($charlist, '#') : '') . ']+#i', '-', $s]);
                $s = trim($s, '-');
                return $s;
        }


        /**
         * Truncates a UTF-8 string to given maximal length, while trying not to split whole words. Only if the string is truncated,
         * an ellipsis (or something else set with third argument) is appended to the string.
         */
        public static function truncate(string $s, int $maxLen, string $append = "\u{2026}"): string
        {
                if (self::length($s) > $maxLen) {
                        $maxLen -= self::length($append);
                        if ($maxLen < 1) {
                                return $append;

                        } elseif ($matches = self::match($s, '#^.{1,' . $maxLen . '}(?=[\s\x00-/:-@\[-`{-~])#us')) {
                                return $matches[0] . $append;

                        } else {
                                return self::substring($s, 0, $maxLen) . $append;
                        }
                }

                return $s;
        }


        /**
         * Indents a multiline text from the left. Second argument sets how many indentation chars should be used,
         * while the indent itself is the third argument (*tab* by default).
         */
        public static function indent(string $s, int $level = 1, string $chars = "\t"): string
        {
                if ($level > 0) {
                        $s = self::replace($s, '#(?:^|[\r\n]+)(?=[^\r\n])#', '$0' . str_repeat($chars, $level));
                }

                return $s;
        }


        /**
         * Converts all characters of UTF-8 string to lower case.
         */
        public static function lower(string $s): string
        {
                return mb_strtolower($s, 'UTF-8');
        }


        /**
         * Converts the first character of a UTF-8 string to lower case and leaves the other characters unchanged.
         */
        public static function firstLower(string $s): string
        {
                return self::lower(self::substring($s, 0, 1)) . self::substring($s, 1);
        }


        /**
         * Converts all characters of a UTF-8 string to upper case.
         */
        public static function upper(string $s): string
        {
                return mb_strtoupper($s, 'UTF-8');
        }


        /**
         * Converts the first character of a UTF-8 string to upper case and leaves the other characters unchanged.
         */
        public static function firstUpper(string $s): string
        {
                return self::upper(self::substring($s, 0, 1)) . self::substring($s, 1);
        }


        /**
         * Converts the first character of every word of a UTF-8 string to upper case and the others to lower case.
         */
        public static function capitalize(string $s): string
        {
                return mb_convert_case($s, MB_CASE_TITLE, 'UTF-8');
        }


        /**
         * Compares two UTF-8 strings or their parts, without taking character case into account. If length is null, whole strings are compared,
         * if it is negative, the corresponding number of characters from the end of the strings is compared,
         * otherwise the appropriate number of characters from the beginning is compared.
         */
        public static function compare(string $left, string $right, ?int $length = null): bool
        {
                if (class_exists('Normalizer', false)) {
                        $left = \Normalizer::normalize($left, \Normalizer::FORM_D); // form NFD is faster
                        $right = \Normalizer::normalize($right, \Normalizer::FORM_D); // form NFD is faster
                }

                if ($length < 0) {
                        $left = self::substring($left, $length, -$length);
                        $right = self::substring($right, $length, -$length);
                } elseif ($length !== null) {
                        $left = self::substring($left, 0, $length);
                        $right = self::substring($right, 0, $length);
                }

                return self::lower($left) === self::lower($right);
        }


        /**
         * Finds the common prefix of strings or returns empty string if the prefix was not found.
         * @param  string[]  $strings
         */
        public static function findPrefix(array $strings): string
        {
                $first = array_shift($strings);
                for ($i = 0; $i < strlen($first); $i++) {
                        foreach ($strings as $s) {
                                if (!isset($s[$i]) || $first[$i] !== $s[$i]) {
                                        while ($i && $first[$i - 1] >= "\x80" && $first[$i] >= "\x80" && $first[$i] < "\xC0") {
                                                $i--;
                                        }

                                        return substr($first, 0, $i);
                                }
                        }
                }

                return $first;
        }


        /**
         * Returns number of characters (not bytes) in UTF-8 string.
         * That is the number of Unicode code points which may differ from the number of graphemes.
         */
        public static function length(string $s): int
        {
                return function_exists('mb_strlen')
                        ? mb_strlen($s, 'UTF-8')
                        : strlen(utf8_decode($s));
        }


        /**
         * Removes all left and right side spaces (or the characters passed as second argument) from a UTF-8 encoded string.
         */
        public static function trim(string $s, string $charlist = self::TRIM_CHARACTERS): string
        {
                $charlist = preg_quote($charlist, '#');
                return self::replace($s, '#^[' . $charlist . ']+|[' . $charlist . ']+$#Du', '');
        }


        /**
         * Pads a UTF-8 string to given length by prepending the $pad string to the beginning.
         * @param  non-empty-string  $pad
         */
        public static function padLeft(string $s, int $length, string $pad = ' '): string
        {
                $length = max(0, $length - self::length($s));
                $padLen = self::length($pad);
                return str_repeat($pad, (int) ($length / $padLen)) . self::substring($pad, 0, $length % $padLen) . $s;
        }


        /**
         * Pads UTF-8 string to given length by appending the $pad string to the end.
         * @param  non-empty-string  $pad
         */
        public static function padRight(string $s, int $length, string $pad = ' '): string
        {
                $length = max(0, $length - self::length($s));
                $padLen = self::length($pad);
                return $s . str_repeat($pad, (int) ($length / $padLen)) . self::substring($pad, 0, $length % $padLen);
        }


        /**
         * Reverses UTF-8 string.
         */
        public static function reverse(string $s): string
        {
                if (!extension_loaded('iconv')) {
                        throw new Nette\NotSupportedException(__METHOD__ . '() requires ICONV extension that is not loaded.');
                }

                return iconv('UTF-32LE', 'UTF-8', strrev(iconv('UTF-8', 'UTF-32BE', $s)));
        }


        /**
         * Returns part of $haystack before $nth occurence of $needle or returns null if the needle was not found.
         * Negative value means searching from the end.
         */
        public static function before(string $haystack, string $needle, int $nth = 1): ?string
        {
                $pos = self::pos($haystack, $needle, $nth);
                return $pos === null
                        ? null
                        : substr($haystack, 0, $pos);
        }


        /**
         * Returns part of $haystack after $nth occurence of $needle or returns null if the needle was not found.
         * Negative value means searching from the end.
         */
        public static function after(string $haystack, string $needle, int $nth = 1): ?string
        {
                $pos = self::pos($haystack, $needle, $nth);
                return $pos === null
                        ? null
                        : substr($haystack, $pos + strlen($needle));
        }


        /**
         * Returns position in characters of $nth occurence of $needle in $haystack or null if the $needle was not found.
         * Negative value of `$nth` means searching from the end.
         */
        public static function indexOf(string $haystack, string $needle, int $nth = 1): ?int
        {
                $pos = self::pos($haystack, $needle, $nth);
                return $pos === null
                        ? null
                        : self::length(substr($haystack, 0, $pos));
        }


        /**
         * Returns position in characters of $nth occurence of $needle in $haystack or null if the needle was not found.
         */
        private static function pos(string $haystack, string $needle, int $nth = 1): ?int
        {
                if (!$nth) {
                        return null;
                } elseif ($nth > 0) {
                        if ($needle === '') {
                                return 0;
                        }

                        $pos = 0;
                        while (($pos = strpos($haystack, $needle, $pos)) !== false && --$nth) {
                                $pos++;
                        }
                } else {
                        $len = strlen($haystack);
                        if ($needle === '') {
                                return $len;
                        } elseif ($len === 0) {
                                return null;
                        }

                        $pos = $len - 1;
                        while (($pos = strrpos($haystack, $needle, $pos - $len)) !== false && ++$nth) {
                                $pos--;
                        }
                }

                return Helpers::falseToNull($pos);
        }


        /**
         * Splits a string into array by the regular expression. Parenthesized expression in the delimiter are captured.
         * Parameter $flags can be any combination of PREG_SPLIT_NO_EMPTY and PREG_OFFSET_CAPTURE flags.
         */
        public static function split(
                string $subject,
                #[Language('RegExp')]
                string $pattern,
                int $flags = 0
        ): array
        {
                return self::pcre('preg_split', [$pattern, $subject, -1, $flags | PREG_SPLIT_DELIM_CAPTURE]);
        }


        /**
         * Checks if given string matches a regular expression pattern and returns an array with first found match and each subpattern.
         * Parameter $flags can be any combination of PREG_OFFSET_CAPTURE and PREG_UNMATCHED_AS_NULL flags.
         */
        public static function match(
                string $subject,
                #[Language('RegExp')]
                string $pattern,
                int $flags = 0,
                int $offset = 0
        ): ?array
        {
                if ($offset > strlen($subject)) {
                        return null;
                }

                return self::pcre('preg_match', [$pattern, $subject, &$m, $flags, $offset])
                        ? $m
                        : null;
        }


        /**
         * Finds all occurrences matching regular expression pattern and returns a two-dimensional array. Result is array of matches (ie uses by default PREG_SET_ORDER).
         * Parameter $flags can be any combination of PREG_OFFSET_CAPTURE, PREG_UNMATCHED_AS_NULL and PREG_PATTERN_ORDER flags.
         */
        public static function matchAll(
                string $subject,
                #[Language('RegExp')]
                string $pattern,
                int $flags = 0,
                int $offset = 0
        ): array
        {
                if ($offset > strlen($subject)) {
                        return [];
                }

                self::pcre('preg_match_all', [
                        $pattern, $subject, &$m,
                        ($flags & PREG_PATTERN_ORDER) ? $flags : ($flags | PREG_SET_ORDER),
                        $offset,
                ]);
                return $m;
        }


        /**
         * Replaces all occurrences matching regular expression $pattern which can be string or array in the form `pattern => replacement`.
         * @param  string|array  $pattern
         * @param  string|callable  $replacement
         */
        public static function replace(
                string $subject,
                #[Language('RegExp')]
                $pattern,
                $replacement = '',
                int $limit = -1
        ): string
        {
                if (is_object($replacement) || is_array($replacement)) {
                        if (!is_callable($replacement, false, $textual)) {
                                throw new Nette\InvalidStateException("Callback '$textual' is not callable.");
                        }

                        return self::pcre('preg_replace_callback', [$pattern, $replacement, $subject, $limit]);

                } elseif (is_array($pattern) && is_string(key($pattern))) {
                        $replacement = array_values($pattern);
                        $pattern = array_keys($pattern);
                }

                return self::pcre('preg_replace', [$pattern, $replacement, $subject, $limit]);
        }


        /** @internal */
        public static function pcre(string $func, array $args)
        {
                $res = Callback::invokeSafe($func, $args, function (string $message) use ($args): void {
                        // compile-time error, not detectable by preg_last_error
                        throw new RegexpException($message . ' in pattern: ' . implode(' or ', (array) $args[0]));
                });

                if (($code = preg_last_error()) // run-time error, but preg_last_error & return code are liars
                        && ($res === null || !in_array($func, ['preg_filter', 'preg_replace_callback', 'preg_replace'], true))
                ) {
                        throw new RegexpException((RegexpException::MESSAGES[$code] ?? 'Unknown error')
                                . ' (pattern: ' . implode(' or ', (array) $args[0]) . ')', $code);
                }

                return $res;
        }
}

1	<?php
2
3	/**
4	* This file is part of the Nette Framework (https://nette.org)
5	* Copyright (c) 2004 David Grudl (https://davidgrudl.com)
6	*/
7
8	declare(strict_types=1);
9
10	namespace Nette\Utils;
11
12	use JetBrains\PhpStorm\Language;
13	use Nette;
14	use function is_array, is_object, strlen;
15
16
17	/**
18	* String tools library.
19	*/
20	class Strings
21	{
22	use Nette\StaticClass;
23
24	public const TRIM_CHARACTERS = " \t\n\r\0\x0B\u{A0}";
25
26
27	/**
28	* Checks if the string is valid in UTF-8 encoding.
29	*/
30	public static function checkEncoding(string $s): bool	1✔
31	{
32	return $s === self::fixEncoding($s);	1✔
33	}
34
35
36	/**
37	* Removes all invalid UTF-8 characters from a string.
38	*/
39	public static function fixEncoding(string $s): string	1✔
40	{
41	// removes xD800-xDFFF, x110000 and higher
42	return htmlspecialchars_decode(htmlspecialchars($s, ENT_NOQUOTES \| ENT_IGNORE, 'UTF-8'), ENT_NOQUOTES);	1✔
43	}
44
45
46	/**
47	* Returns a specific character in UTF-8 from code point (number in range 0x0000..D7FF or 0xE000..10FFFF).
48	* @throws Nette\InvalidArgumentException if code point is not in valid range
49	*/
50	public static function chr(int $code): string	1✔
51	{
52	if ($code < 0 \|\| ($code >= 0xD800 && $code <= 0xDFFF) \|\| $code > 0x10FFFF) {	1✔
53	throw new Nette\InvalidArgumentException('Code point must be in range 0x0 to 0xD7FF or 0xE000 to 0x10FFFF.');	1✔
54	} elseif (!extension_loaded('iconv')) {	1✔
55	throw new Nette\NotSupportedException(__METHOD__ . '() requires ICONV extension that is not loaded.');	×
56	}
57
58	return iconv('UTF-32BE', 'UTF-8//IGNORE', pack('N', $code));	1✔
59	}
60
61
62	/**
63	* Starts the $haystack string with the prefix $needle?
64	*/
65	public static function startsWith(string $haystack, string $needle): bool	1✔
66	{
67	return strncmp($haystack, $needle, strlen($needle)) === 0;	1✔
68	}
69
70
71	/**
72	* Ends the $haystack string with the suffix $needle?
73	*/
74	public static function endsWith(string $haystack, string $needle): bool	1✔
75	{
76	return $needle === '' \|\| substr($haystack, -strlen($needle)) === $needle;	1✔
77	}
78
79
80	/**
81	* Does $haystack contain $needle?
82	*/
83	public static function contains(string $haystack, string $needle): bool	1✔
84	{
85	return strpos($haystack, $needle) !== false;	1✔
86	}
87
88
89	/**
90	* Returns a part of UTF-8 string specified by starting position and length. If start is negative,
91	* the returned string will start at the start'th character from the end of string.
92	*/
93	public static function substring(string $s, int $start, ?int $length = null): string	1✔
94	{
95	if (function_exists('mb_substr')) {	1✔
96	return mb_substr($s, $start, $length, 'UTF-8'); // MB is much faster	1✔
97	} elseif (!extension_loaded('iconv')) {	×
98	throw new Nette\NotSupportedException(__METHOD__ . '() requires extension ICONV or MBSTRING, neither is loaded.');	×
99	} elseif ($length === null) {	×
100	$length = self::length($s);	×
101	} elseif ($start < 0 && $length < 0) {	×
102	$start += self::length($s); // unifies iconv_substr behavior with mb_substr	×
103	}
104
105	return iconv_substr($s, $start, $length, 'UTF-8');	×
106	}
107
108
109	/**
110	* Removes control characters, normalizes line breaks to `\n`, removes leading and trailing blank lines,
111	* trims end spaces on lines, normalizes UTF-8 to the normal form of NFC.
112	*/
113	public static function normalize(string $s): string	1✔
114	{
115	// convert to compressed normal form (NFC)
116	if (class_exists('Normalizer', false) && ($n = \Normalizer::normalize($s, \Normalizer::FORM_C)) !== false) {	1✔
117	$s = $n;	1✔
118	}
119
120	$s = self::normalizeNewLines($s);	1✔
121
122	// remove control characters; leave \t + \n
123	$s = self::pcre('preg_replace', ['#[\x00-\x08\x0B-\x1F\x7F-\x9F]+#u', '', $s]);	1✔
124
125	// right trim
126	$s = self::pcre('preg_replace', ['#[\t ]+$#m', '', $s]);	1✔
127
128	// leading and trailing blank lines
129	$s = trim($s, "\n");	1✔
130
131	return $s;	1✔
132	}
133
134
135	/**
136	* Standardize line endings to unix-like.
137	*/
138	public static function normalizeNewLines(string $s): string	1✔
139	{
140	return str_replace(["\r\n", "\r"], "\n", $s);	1✔
141	}
142
143
144	/**
145	* Converts UTF-8 string to ASCII, ie removes diacritics etc.
146	*/
147	public static function toAscii(string $s): string	1✔
148	{
149	$iconv = defined('ICONV_IMPL') ? trim(ICONV_IMPL, '"\'') : null;	1✔
150	static $transliterator = null;	1✔
151	if ($transliterator === null) {	1✔
152	if (class_exists('Transliterator', false)) {	1✔
153	$transliterator = \Transliterator::create('Any-Latin; Latin-ASCII');	1✔
154	} else {
155	trigger_error(__METHOD__ . "(): it is recommended to enable PHP extensions 'intl'.", E_USER_NOTICE);	×
156	$transliterator = false;	×
157	}
158	}
159
160	// remove control characters and check UTF-8 validity
161	$s = self::pcre('preg_replace', ['#[^\x09\x0A\x0D\x20-\x7E\xA0-\x{2FF}\x{370}-\x{10FFFF}]#u', '', $s]);	1✔
162
163	// transliteration (by Transliterator and iconv) is not optimal, replace some characters directly
164	$s = strtr($s, ["\u{201E}" => '"', "\u{201C}" => '"', "\u{201D}" => '"', "\u{201A}" => "'", "\u{2018}" => "'", "\u{2019}" => "'", "\u{B0}" => '^', "\u{42F}" => 'Ya', "\u{44F}" => 'ya', "\u{42E}" => 'Yu', "\u{44E}" => 'yu', "\u{c4}" => 'Ae', "\u{d6}" => 'Oe', "\u{dc}" => 'Ue', "\u{1e9e}" => 'Ss', "\u{e4}" => 'ae', "\u{f6}" => 'oe', "\u{fc}" => 'ue', "\u{df}" => 'ss']); // „ “ ” ‚ ‘ ’ ° Я я Ю ю Ä Ö Ü ẞ ä ö ü ß	1✔
165	if ($iconv !== 'libiconv') {	1✔
166	$s = strtr($s, ["\u{AE}" => '(R)', "\u{A9}" => '(c)', "\u{2026}" => '...', "\u{AB}" => '<<', "\u{BB}" => '>>', "\u{A3}" => 'lb', "\u{A5}" => 'yen', "\u{B2}" => '^2', "\u{B3}" => '^3', "\u{B5}" => 'u', "\u{B9}" => '^1', "\u{BA}" => 'o', "\u{BF}" => '?', "\u{2CA}" => "'", "\u{2CD}" => '_', "\u{2DD}" => '"', "\u{1FEF}" => '', "\u{20AC}" => 'EUR', "\u{2122}" => 'TM', "\u{212E}" => 'e', "\u{2190}" => '<-', "\u{2191}" => '^', "\u{2192}" => '->', "\u{2193}" => 'V', "\u{2194}" => '<->']); // ® © … « » £ ¥ ² ³ µ ¹ º ¿ ˊ ˍ ˝ ` € ™ ℮ ← ↑ → ↓ ↔	1✔
167	}
168
169	if ($transliterator) {	1✔
170	$s = $transliterator->transliterate($s);	1✔
171	// use iconv because The transliterator leaves some characters out of ASCII, eg → ʾ
172	if ($iconv === 'glibc') {	1✔
173	$s = strtr($s, '?', "\x01"); // temporarily hide ? to distinguish them from the garbage that iconv creates	1✔
174	$s = iconv('UTF-8', 'ASCII//TRANSLIT//IGNORE', $s);	1✔
175	$s = str_replace(['?', "\x01"], ['', '?'], $s); // remove garbage and restore ? characters	1✔
176	} elseif ($iconv === 'libiconv') {	×
177	$s = iconv('UTF-8', 'ASCII//TRANSLIT//IGNORE', $s);	×
178	} else { // null or 'unknown' (#216)
179	$s = self::pcre('preg_replace', ['#[^\x00-\x7F]++#', '', $s]); // remove non-ascii chars	1✔
180	}
181	} elseif ($iconv === 'glibc' \|\| $iconv === 'libiconv') {	×
182	// temporarily hide these characters to distinguish them from the garbage that iconv creates
183	$s = strtr($s, '`\'"^~?', "\x01\x02\x03\x04\x05\x06");	×
184	if ($iconv === 'glibc') {	×
185	// glibc implementation is very limited. transliterate into Windows-1250 and then into ASCII, so most Eastern European characters are preserved
186	$s = iconv('UTF-8', 'WINDOWS-1250//TRANSLIT//IGNORE', $s);	×
187	$s = strtr(	×
188	$s,	×
189	"\xa5\xa3\xbc\x8c\xa7\x8a\xaa\x8d\x8f\x8e\xaf\xb9\xb3\xbe\x9c\x9a\xba\x9d\x9f\x9e\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf8\xf9\xfa\xfb\xfc\xfd\xfe\x96\xa0\x8b\x97\x9b\xa6\xad\xb7",	×
190	'ALLSSSSTZZZallssstzzzRAAAALCCCEEEEIIDDNNOOOOxRUUUUYTsraaaalccceeeeiiddnnooooruuuuyt- <->\|-.'	×
191	);
192	$s = self::pcre('preg_replace', ['#[^\x00-\x7F]++#', '', $s]);	×
193	} else {
194	$s = iconv('UTF-8', 'ASCII//TRANSLIT//IGNORE', $s);	×
195	}
196
197	// remove garbage that iconv creates during transliteration (eg Ý -> Y')
198	$s = str_replace(['`', "'", '"', '^', '~', '?'], '', $s);	×
199	// restore temporarily hidden characters
200	$s = strtr($s, "\x01\x02\x03\x04\x05\x06", '`\'"^~?');	×
201	} else {
202	$s = self::pcre('preg_replace', ['#[^\x00-\x7F]++#', '', $s]); // remove non-ascii chars	×
203	}
204
205	return $s;	1✔
206	}
207
208
209	/**
210	* Modifies the UTF-8 string to the form used in the URL, ie removes diacritics and replaces all characters
211	* except letters of the English alphabet and numbers with a hyphens.
212	*/
213	public static function webalize(string $s, ?string $charlist = null, bool $lower = true): string	1✔
214	{
215	$s = self::toAscii($s);	1✔
216	if ($lower) {	1✔
217	$s = strtolower($s);	1✔
218	}
219
220	$s = self::pcre('preg_replace', ['#[^a-z0-9' . ($charlist !== null ? preg_quote($charlist, '#') : '') . ']+#i', '-', $s]);	1✔
221	$s = trim($s, '-');	1✔
222	return $s;	1✔
223	}
224
225
226	/**
227	* Truncates a UTF-8 string to given maximal length, while trying not to split whole words. Only if the string is truncated,
228	* an ellipsis (or something else set with third argument) is appended to the string.
229	*/
230	public static function truncate(string $s, int $maxLen, string $append = "\u{2026}"): string	1✔
231	{
232	if (self::length($s) > $maxLen) {	1✔
233	$maxLen -= self::length($append);	1✔
234	if ($maxLen < 1) {	1✔
235	return $append;	1✔
236
237	} elseif ($matches = self::match($s, '#^.{1,' . $maxLen . '}(?=[\s\x00-/:-@\[-`{-~])#us')) {	1✔
238	return $matches[0] . $append;	1✔
239
240	} else {
241	return self::substring($s, 0, $maxLen) . $append;	1✔
242	}
243	}
244
245	return $s;	1✔
246	}
247
248
249	/**
250	* Indents a multiline text from the left. Second argument sets how many indentation chars should be used,
251	* while the indent itself is the third argument (tab by default).
252	*/
253	public static function indent(string $s, int $level = 1, string $chars = "\t"): string	1✔
254	{
255	if ($level > 0) {	1✔
256	$s = self::replace($s, '#(?:^\|[\r\n]+)(?=[^\r\n])#', '$0' . str_repeat($chars, $level));	1✔
257	}
258
259	return $s;	1✔
260	}
261
262
263	/**
264	* Converts all characters of UTF-8 string to lower case.
265	*/
266	public static function lower(string $s): string	1✔
267	{
268	return mb_strtolower($s, 'UTF-8');	1✔
269	}
270
271
272	/**
273	* Converts the first character of a UTF-8 string to lower case and leaves the other characters unchanged.
274	*/
275	public static function firstLower(string $s): string	1✔
276	{
277	return self::lower(self::substring($s, 0, 1)) . self::substring($s, 1);	1✔
278	}
279
280
281	/**
282	* Converts all characters of a UTF-8 string to upper case.
283	*/
284	public static function upper(string $s): string	1✔
285	{
286	return mb_strtoupper($s, 'UTF-8');	1✔
287	}
288
289
290	/**
291	* Converts the first character of a UTF-8 string to upper case and leaves the other characters unchanged.
292	*/
293	public static function firstUpper(string $s): string	1✔
294	{
295	return self::upper(self::substring($s, 0, 1)) . self::substring($s, 1);	1✔
296	}
297
298
299	/**
300	* Converts the first character of every word of a UTF-8 string to upper case and the others to lower case.
301	*/
302	public static function capitalize(string $s): string	1✔
303	{
304	return mb_convert_case($s, MB_CASE_TITLE, 'UTF-8');	1✔
305	}
306
307
308	/**
309	* Compares two UTF-8 strings or their parts, without taking character case into account. If length is null, whole strings are compared,
310	* if it is negative, the corresponding number of characters from the end of the strings is compared,
311	* otherwise the appropriate number of characters from the beginning is compared.
312	*/
313	public static function compare(string $left, string $right, ?int $length = null): bool	1✔
314	{
315	if (class_exists('Normalizer', false)) {	1✔
316	$left = \Normalizer::normalize($left, \Normalizer::FORM_D); // form NFD is faster	1✔
317	$right = \Normalizer::normalize($right, \Normalizer::FORM_D); // form NFD is faster	1✔
318	}
319
320	if ($length < 0) {	1✔
321	$left = self::substring($left, $length, -$length);	1✔
322	$right = self::substring($right, $length, -$length);	1✔
323	} elseif ($length !== null) {	1✔
324	$left = self::substring($left, 0, $length);	1✔
325	$right = self::substring($right, 0, $length);	1✔
326	}
327
328	return self::lower($left) === self::lower($right);	1✔
329	}
330
331
332	/**
333	* Finds the common prefix of strings or returns empty string if the prefix was not found.
334	* @param string[] $strings
335	*/
336	public static function findPrefix(array $strings): string	1✔
337	{
338	$first = array_shift($strings);	1✔
339	for ($i = 0; $i < strlen($first); $i++) {	1✔
340	foreach ($strings as $s) {	1✔
341	if (!isset($s[$i]) \|\| $first[$i] !== $s[$i]) {	1✔
342	while ($i && $first[$i - 1] >= "\x80" && $first[$i] >= "\x80" && $first[$i] < "\xC0") {	1✔
343	$i--;	1✔
344	}
345
346	return substr($first, 0, $i);	1✔
347	}
348	}
349	}
350
351	return $first;	1✔
352	}
353
354
355	/**
356	* Returns number of characters (not bytes) in UTF-8 string.
357	* That is the number of Unicode code points which may differ from the number of graphemes.
358	*/
359	public static function length(string $s): int	1✔
360	{
361	return function_exists('mb_strlen')	1✔
362	? mb_strlen($s, 'UTF-8')	1✔
363	: strlen(utf8_decode($s));	1✔
364	}
365
366
367	/**
368	* Removes all left and right side spaces (or the characters passed as second argument) from a UTF-8 encoded string.
369	*/
370	public static function trim(string $s, string $charlist = self::TRIM_CHARACTERS): string	1✔
371	{
372	$charlist = preg_quote($charlist, '#');	1✔
373	return self::replace($s, '#^[' . $charlist . ']+\|[' . $charlist . ']+$#Du', '');	1✔
374	}
375
376
377	/**
378	* Pads a UTF-8 string to given length by prepending the $pad string to the beginning.
379	* @param non-empty-string $pad
380	*/
381	public static function padLeft(string $s, int $length, string $pad = ' '): string	1✔
382	{
383	$length = max(0, $length - self::length($s));	1✔
384	$padLen = self::length($pad);	1✔
385	return str_repeat($pad, (int) ($length / $padLen)) . self::substring($pad, 0, $length % $padLen) . $s;	1✔
386	}
387
388
389	/**
390	* Pads UTF-8 string to given length by appending the $pad string to the end.
391	* @param non-empty-string $pad
392	*/
393	public static function padRight(string $s, int $length, string $pad = ' '): string	1✔
394	{
395	$length = max(0, $length - self::length($s));	1✔
396	$padLen = self::length($pad);	1✔
397	return $s . str_repeat($pad, (int) ($length / $padLen)) . self::substring($pad, 0, $length % $padLen);	1✔
398	}
399
400
401	/**
402	* Reverses UTF-8 string.
403	*/
404	public static function reverse(string $s): string	1✔
405	{
406	if (!extension_loaded('iconv')) {	1✔
407	throw new Nette\NotSupportedException(__METHOD__ . '() requires ICONV extension that is not loaded.');	×
408	}
409
410	return iconv('UTF-32LE', 'UTF-8', strrev(iconv('UTF-8', 'UTF-32BE', $s)));	1✔
411	}
412
413
414	/**
415	* Returns part of $haystack before $nth occurence of $needle or returns null if the needle was not found.
416	* Negative value means searching from the end.
417	*/
418	public static function before(string $haystack, string $needle, int $nth = 1): ?string	1✔
419	{
420	$pos = self::pos($haystack, $needle, $nth);	1✔
421	return $pos === null	1✔
422	? null	1✔
423	: substr($haystack, 0, $pos);	1✔
424	}
425
426
427	/**
428	* Returns part of $haystack after $nth occurence of $needle or returns null if the needle was not found.
429	* Negative value means searching from the end.
430	*/
431	public static function after(string $haystack, string $needle, int $nth = 1): ?string	1✔
432	{
433	$pos = self::pos($haystack, $needle, $nth);	1✔
434	return $pos === null	1✔
435	? null	1✔
436	: substr($haystack, $pos + strlen($needle));	1✔
437	}
438
439
440	/**
441	* Returns position in characters of $nth occurence of $needle in $haystack or null if the $needle was not found.
442	* Negative value of `$nth` means searching from the end.
443	*/
444	public static function indexOf(string $haystack, string $needle, int $nth = 1): ?int	1✔
445	{
446	$pos = self::pos($haystack, $needle, $nth);	1✔
447	return $pos === null	1✔
448	? null	1✔
449	: self::length(substr($haystack, 0, $pos));	1✔
450	}
451
452
453	/**
454	* Returns position in characters of $nth occurence of $needle in $haystack or null if the needle was not found.
455	*/
456	private static function pos(string $haystack, string $needle, int $nth = 1): ?int	1✔
457	{
458	if (!$nth) {	1✔
459	return null;	1✔
460	} elseif ($nth > 0) {	1✔
461	if ($needle === '') {	1✔
462	return 0;	1✔
463	}
464
465	$pos = 0;	1✔
466	while (($pos = strpos($haystack, $needle, $pos)) !== false && --$nth) {	1✔
467	$pos++;	1✔
468	}
469	} else {
470	$len = strlen($haystack);	1✔
471	if ($needle === '') {	1✔
472	return $len;	1✔
473	} elseif ($len === 0) {	1✔
474	return null;	1✔
475	}
476
477	$pos = $len - 1;	1✔
478	while (($pos = strrpos($haystack, $needle, $pos - $len)) !== false && ++$nth) {	1✔
479	$pos--;	1✔
480	}
481	}
482
483	return Helpers::falseToNull($pos);	1✔
484	}
485
486
487	/**
488	* Splits a string into array by the regular expression. Parenthesized expression in the delimiter are captured.
489	* Parameter $flags can be any combination of PREG_SPLIT_NO_EMPTY and PREG_OFFSET_CAPTURE flags.
490	*/
491	public static function split(	1✔
492	string $subject,
493	#[Language('RegExp')]
494	string $pattern,
495	int $flags = 0
496	): array
497	{
498	return self::pcre('preg_split', [$pattern, $subject, -1, $flags \| PREG_SPLIT_DELIM_CAPTURE]);	1✔
499	}
500
501
502	/**
503	* Checks if given string matches a regular expression pattern and returns an array with first found match and each subpattern.
504	* Parameter $flags can be any combination of PREG_OFFSET_CAPTURE and PREG_UNMATCHED_AS_NULL flags.
505	*/
506	public static function match(	1✔
507	string $subject,
508	#[Language('RegExp')]
509	string $pattern,
510	int $flags = 0,
511	int $offset = 0
512	): ?array
513	{
514	if ($offset > strlen($subject)) {	1✔
515	return null;	1✔
516	}
517
518	return self::pcre('preg_match', [$pattern, $subject, &$m, $flags, $offset])	1✔
519	? $m	1✔
520	: null;	1✔
521	}
522
523
524	/**
525	* Finds all occurrences matching regular expression pattern and returns a two-dimensional array. Result is array of matches (ie uses by default PREG_SET_ORDER).
526	* Parameter $flags can be any combination of PREG_OFFSET_CAPTURE, PREG_UNMATCHED_AS_NULL and PREG_PATTERN_ORDER flags.
527	*/
528	public static function matchAll(	1✔
529	string $subject,
530	#[Language('RegExp')]
531	string $pattern,
532	int $flags = 0,
533	int $offset = 0
534	): array
535	{
536	if ($offset > strlen($subject)) {	1✔
537	return [];	1✔
538	}
539
540	self::pcre('preg_match_all', [	1✔
541	$pattern, $subject, &$m,	1✔
542	($flags & PREG_PATTERN_ORDER) ? $flags : ($flags \| PREG_SET_ORDER),	1✔
543	$offset,	1✔
544	]);
545	return $m;	1✔
546	}
547
548
549	/**
550	* Replaces all occurrences matching regular expression $pattern which can be string or array in the form `pattern => replacement`.
551	* @param string\|array $pattern
552	* @param string\|callable $replacement
553	*/
554	public static function replace(	1✔
555	string $subject,
556	#[Language('RegExp')]
557	$pattern,
558	$replacement = '',
559	int $limit = -1
560	): string
561	{
562	if (is_object($replacement) \|\| is_array($replacement)) {	1✔
563	if (!is_callable($replacement, false, $textual)) {	1✔
564	throw new Nette\InvalidStateException("Callback '$textual' is not callable.");	1✔
565	}
566
567	return self::pcre('preg_replace_callback', [$pattern, $replacement, $subject, $limit]);	1✔
568
569	} elseif (is_array($pattern) && is_string(key($pattern))) {	1✔
570	$replacement = array_values($pattern);	1✔
571	$pattern = array_keys($pattern);	1✔
572	}
573
574	return self::pcre('preg_replace', [$pattern, $replacement, $subject, $limit]);	1✔
575	}
576
577
578	/** @internal */
579	public static function pcre(string $func, array $args)	1✔
580	{
581	$res = Callback::invokeSafe($func, $args, function (string $message) use ($args): void {	1✔
582	// compile-time error, not detectable by preg_last_error
583	throw new RegexpException($message . ' in pattern: ' . implode(' or ', (array) $args[0]));	1✔
584	});	1✔
585
586	if (($code = preg_last_error()) // run-time error, but preg_last_error & return code are liars	1✔
587	&& ($res === null \|\| !in_array($func, ['preg_filter', 'preg_replace_callback', 'preg_replace'], true))	1✔
588	) {
589	throw new RegexpException((RegexpException::MESSAGES[$code] ?? 'Unknown error')	1✔
590	. ' (pattern: ' . implode(' or ', (array) $args[0]) . ')', $code);	1✔
591	}
592
593	return $res;	1✔
594	}
595	}

nette / utils / 5707056869

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous