21501721037

Committed 30 Jan 2026 02:00AM UTC coverage: 91.159% (-1.3%) from 92.426%

Build Type

push

github

Committed by

Commit Message

wip

Run Details

2681 of 2941 relevant lines covered (91.16%)

0.91 hits per line

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

95.35

/src/Texy/Helpers.php

<?php

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

declare(strict_types=1);

namespace Texy;

use Nette\Utils\Strings;
use function class_exists, function_exists, html_entity_decode, iconv, mb_strlen, mb_strtolower, mb_substr, min, preg_match, rtrim, str_replace, strlen, strncasecmp, strspn, strtolower, strtr, trim;
use const ENT_HTML5, ENT_QUOTES, ICONV_IMPL;


/**
 * Static utility helpers.
 */
final class Helpers
{
        public function __construct()
        {
                throw new \LogicException('Cannot instantiate static class ' . self::class);
        }


        /**
         * StrToLower in UTF-8.
         */
        public static function toLower(string $s): string
        {
                return function_exists('mb_strtolower')
                        ? mb_strtolower($s, 'UTF-8')
                        : $s;
        }


        public static function unescapeHtml(string $s): string
        {
                return html_entity_decode($s, ENT_QUOTES | ENT_HTML5, 'UTF-8');
        }


        /**
         * Translate all white spaces (\t \n \r space) to meta-spaces \x01-\x04.
         * which are ignored by Html\Formatter routine
         */
        public static function freezeSpaces(string $s): string
        {
                return strtr($s, " \t\r\n", "\x01\x02\x03\x04");
        }


        /**
         * Reverts meta-spaces back to normal spaces.
         */
        public static function unfreezeSpaces(string $s): string
        {
                return strtr($s, "\x01\x02\x03\x04", " \t\r\n");
        }


        /**
         * Removes special controls characters and normalizes line endings and spaces.
         */
        public static function normalize(string $s): string
        {
                // standardize line endings to unix-like
                $s = str_replace("\r\n", "\n", $s); // DOS
                $s = strtr($s, "\r", "\n"); // Mac

                // remove special chars; leave \t + \n
                $s = Regexp::replace($s, '~[\x00-\x08\x0B-\x1F]+~', '');

                // right trim
                $s = Regexp::replace($s, "~[\t ]+$~m", '');

                // trailing spaces
                $s = trim($s, "\n");

                return $s;
        }


        /**
         * Converts UTF-8 to ASCII.
         */
        public static function toAscii(string $s): string
        {
                if (class_exists(Strings::class)) {
                        return Strings::toAscii($s);
                }
                $s = strtr($s, '`\'"^~', '-----');
                if (ICONV_IMPL === 'glibc') {
                        $s = (string) @iconv('UTF-8', 'WINDOWS-1250//TRANSLIT', $s); // intentionally @
                        $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",
                                'ALLSSSSTZZZallssstzzzRAAAALCCCEEEEIIDDNNOOOOxRUUUUYTsraaaalccceeeeiiddnnooooruuuuyt',
                        );
                } else {
                        $s = (string) @iconv('UTF-8', 'ASCII//TRANSLIT', $s); // intentionally @
                }

                $s = str_replace(['`', "'", '"', '^', '~'], '', $s);
                return $s;
        }


        /**
         * Converts to web safe characters [a-z0-9-] text.
         */
        public static function webalize(string $s, string $charlist = ''): string
        {
                $s = self::toAscii($s);
                $s = strtolower($s);
                $s = Regexp::replace($s, '~[^a-z0-9' . Regexp::quote($charlist) . ']+~', '-');
                $s = trim($s, '-');
                return $s;
        }


        /**
         * Outdents text block.
         */
        public static function outdent(string $s, bool $firstLine = false): string
        {
                $s = trim($s, "\n");
                if ($firstLine) {
                        $min = strspn($s, ' ');
                } else {
                        $min = strlen($s);
                        foreach (Regexp::matchAll($s, '~^\ *\S~m') as $m) {
                                $min = min($min, strlen($m[0]) - 1);
                        }
                }

                if ($min) {
                        $s = Regexp::replace($s, "~^\\ {1,$min}~m", '');
                }

                return $s;
        }


        /**
         * Is given URL relative?
         */
        public static function isRelative(string $URL): bool
        {
                // check for scheme, or absolute path, or absolute URL
                return !Regexp::match($URL, '~[a-z][a-z0-9+.-]{0,20}:|[#/?]~Ai');
        }


        /**
         * Prepends root to URL, if possible.
         */
        public static function prependRoot(string $URL, ?string $root): string
        {
                if ($root == null || !self::isRelative($URL)) {
                        return $URL;
                }

                return rtrim($root, '/\\') . '/' . $URL;
        }


        /**
         * Extracts plain text content from AST node(s).
         * @param  Node|iterable<Node>  $node
         */
        public static function extractText(Node|iterable $node): string
        {
                if ($node instanceof Nodes\TextNode) {
                        return $node->content;
                }

                $text = '';
                $children = $node instanceof Node ? $node->getNodes() : $node;
                foreach ($children as $child) {
                        $text .= self::extractText($child);
                }

                return $text;
        }


        /**
         * Returns shortened URL for display (e.g., in autolinks).
         */
        public static function shortenUrl(string $url): string
        {
                $raw = strncasecmp($url, 'www.', 4) === 0
                        ? 'none://' . $url
                        : $url;

                // parse_url() in PHP damages UTF-8 - use regular expression
                if (!preg_match('~^
                        (?: (?P<scheme> [a-z]+ ) : )?
                        (?: // (?P<host> [^/?#]+ ) )?
                        (?P<path> (?: / | ^ ) (?! / ) [^?#]* )?
                        (?: \? (?P<query> [^#]* ) )?
                        (?: \# (?P<fragment> .* ) )?
                        $
                ~x', $raw, $parts)) {
                        return $url;
                }

                $res = '';
                if (($parts['scheme'] ?? null) !== null && $parts['scheme'] !== 'none') {
                        $res .= $parts['scheme'] . '://';
                }

                if (($parts['host'] ?? null) !== null) {
                        $res .= $parts['host'];
                }

                if (($parts['path'] ?? null) !== null) {
                        $res .= mb_strlen($parts['path']) > 16
                                ? "/\u{2026}" . mb_substr($parts['path'], -12)
                                : $parts['path'];
                }

                if (($parts['query'] ?? '') !== '') {
                        $res .= mb_strlen($parts['query']) > 4
                                ? "?\u{2026}"
                                : '?' . $parts['query'];
                } elseif (($parts['fragment'] ?? '') !== '') {
                        $res .= mb_strlen($parts['fragment']) > 4
                                ? "#\u{2026}"
                                : '#' . $parts['fragment'];
                }

                return $res;
        }
}

1	<?php
2
3	/**
4	* This file is part of the Texy! (https://texy.nette.org)
5	* Copyright (c) 2004 David Grudl (https://davidgrudl.com)
6	*/
7
8	declare(strict_types=1);
9
10	namespace Texy;
11
12	use Nette\Utils\Strings;
13	use function class_exists, function_exists, html_entity_decode, iconv, mb_strlen, mb_strtolower, mb_substr, min, preg_match, rtrim, str_replace, strlen, strncasecmp, strspn, strtolower, strtr, trim;
14	use const ENT_HTML5, ENT_QUOTES, ICONV_IMPL;
15
16
17	/**
18	* Static utility helpers.
19	*/
20	final class Helpers
21	{
22	public function __construct()
23	{
24	throw new \LogicException('Cannot instantiate static class ' . self::class);	×
25	}
26
27
28	/**
29	* StrToLower in UTF-8.
30	*/
31	public static function toLower(string $s): string	1✔
32	{
33	return function_exists('mb_strtolower')	1✔
34	? mb_strtolower($s, 'UTF-8')	1✔
35	: $s;	1✔
36	}
37
38
39	public static function unescapeHtml(string $s): string	1✔
40	{
41	return html_entity_decode($s, ENT_QUOTES \| ENT_HTML5, 'UTF-8');	1✔
42	}
43
44
45	/**
46	* Translate all white spaces (\t \n \r space) to meta-spaces \x01-\x04.
47	* which are ignored by Html\Formatter routine
48	*/
49	public static function freezeSpaces(string $s): string	1✔
50	{
51	return strtr($s, " \t\r\n", "\x01\x02\x03\x04");	1✔
52	}
53
54
55	/**
56	* Reverts meta-spaces back to normal spaces.
57	*/
58	public static function unfreezeSpaces(string $s): string	1✔
59	{
60	return strtr($s, "\x01\x02\x03\x04", " \t\r\n");	1✔
61	}
62
63
64	/**
65	* Removes special controls characters and normalizes line endings and spaces.
66	*/
67	public static function normalize(string $s): string	1✔
68	{
69	// standardize line endings to unix-like
70	$s = str_replace("\r\n", "\n", $s); // DOS	1✔
71	$s = strtr($s, "\r", "\n"); // Mac	1✔
72
73	// remove special chars; leave \t + \n
74	$s = Regexp::replace($s, '~[\x00-\x08\x0B-\x1F]+~', '');	1✔
75
76	// right trim
77	$s = Regexp::replace($s, "~[\t ]+$~m", '');	1✔
78
79	// trailing spaces
80	$s = trim($s, "\n");	1✔
81
82	return $s;	1✔
83	}
84
85
86	/**
87	* Converts UTF-8 to ASCII.
88	*/
89	public static function toAscii(string $s): string	1✔
90	{
91	if (class_exists(Strings::class)) {	1✔
92	return Strings::toAscii($s);	×
93	}
94	$s = strtr($s, '`\'"^~', '-----');	1✔
95	if (ICONV_IMPL === 'glibc') {	1✔
96	$s = (string) @iconv('UTF-8', 'WINDOWS-1250//TRANSLIT', $s); // intentionally @	1✔
97	$s = strtr(	1✔
98	$s,	1✔
99	"\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"
100	. "\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",	1✔
101	'ALLSSSSTZZZallssstzzzRAAAALCCCEEEEIIDDNNOOOOxRUUUUYTsraaaalccceeeeiiddnnooooruuuuyt',	1✔
102	);
103	} else {
104	$s = (string) @iconv('UTF-8', 'ASCII//TRANSLIT', $s); // intentionally @	×
105	}
106
107	$s = str_replace(['`', "'", '"', '^', '~'], '', $s);	1✔
108	return $s;	1✔
109	}
110
111
112	/**
113	* Converts to web safe characters [a-z0-9-] text.
114	*/
115	public static function webalize(string $s, string $charlist = ''): string	1✔
116	{
117	$s = self::toAscii($s);	1✔
118	$s = strtolower($s);	1✔
119	$s = Regexp::replace($s, '~[^a-z0-9' . Regexp::quote($charlist) . ']+~', '-');	1✔
120	$s = trim($s, '-');	1✔
121	return $s;	1✔
122	}
123
124
125	/**
126	* Outdents text block.
127	*/
128	public static function outdent(string $s, bool $firstLine = false): string	1✔
129	{
130	$s = trim($s, "\n");	1✔
131	if ($firstLine) {	1✔
132	$min = strspn($s, ' ');	1✔
133	} else {
134	$min = strlen($s);	1✔
135	foreach (Regexp::matchAll($s, '~^\ *\S~m') as $m) {	1✔
136	$min = min($min, strlen($m[0]) - 1);	1✔
137	}
138	}
139
140	if ($min) {	1✔
141	$s = Regexp::replace($s, "~^\\ {1,$min}~m", '');	1✔
142	}
143
144	return $s;	1✔
145	}
146
147
148	/**
149	* Is given URL relative?
150	*/
151	public static function isRelative(string $URL): bool	1✔
152	{
153	// check for scheme, or absolute path, or absolute URL
154	return !Regexp::match($URL, '~[a-z][a-z0-9+.-]{0,20}:\|[#/?]~Ai');	1✔
155	}
156
157
158	/**
159	* Prepends root to URL, if possible.
160	*/
161	public static function prependRoot(string $URL, ?string $root): string	1✔
162	{
163	if ($root == null \|\| !self::isRelative($URL)) {	1✔
164	return $URL;	1✔
165	}
166
167	return rtrim($root, '/\\') . '/' . $URL;	1✔
168	}
169
170
171	/**
172	* Extracts plain text content from AST node(s).
173	* @param Node\|iterable<Node> $node
174	*/
175	public static function extractText(Node\|iterable $node): string	1✔
176	{
177	if ($node instanceof Nodes\TextNode) {	1✔
178	return $node->content;	1✔
179	}
180
181	$text = '';	1✔
182	$children = $node instanceof Node ? $node->getNodes() : $node;	1✔
183	foreach ($children as $child) {	1✔
184	$text .= self::extractText($child);	1✔
185	}
186
187	return $text;	1✔
188	}
189
190
191	/**
192	* Returns shortened URL for display (e.g., in autolinks).
193	*/
194	public static function shortenUrl(string $url): string	1✔
195	{
196	$raw = strncasecmp($url, 'www.', 4) === 0	1✔
197	? 'none://' . $url	1✔
198	: $url;	1✔
199
200	// parse_url() in PHP damages UTF-8 - use regular expression
201	if (!preg_match('~^	1✔
202	(?: (?P<scheme> [a-z]+ ) : )?
203	(?: // (?P<host> [^/?#]+ ) )?
204	(?P<path> (?: / \| ^ ) (?! / ) [^?#]* )?
205	(?: \? (?P<query> [^#]* ) )?
206	(?: \# (?P<fragment> .* ) )?
207	$
208	~x', $raw, $parts)) {	1✔
209	return $url;	×
210	}
211
212	$res = '';	1✔
213	if (($parts['scheme'] ?? null) !== null && $parts['scheme'] !== 'none') {	1✔
214	$res .= $parts['scheme'] . '://';	1✔
215	}
216
217	if (($parts['host'] ?? null) !== null) {	1✔
218	$res .= $parts['host'];	1✔
219	}
220
221	if (($parts['path'] ?? null) !== null) {	1✔
222	$res .= mb_strlen($parts['path']) > 16	1✔
223	? "/\u{2026}" . mb_substr($parts['path'], -12)	1✔
224	: $parts['path'];	1✔
225	}
226
227	if (($parts['query'] ?? '') !== '') {	1✔
228	$res .= mb_strlen($parts['query']) > 4	1✔
229	? "?\u{2026}"	1✔
230	: '?' . $parts['query'];	1✔
231	} elseif (($parts['fragment'] ?? '') !== '') {	1✔
232	$res .= mb_strlen($parts['fragment']) > 4	1✔
233	? "#\u{2026}"	1✔
234	: '#' . $parts['fragment'];	1✔
235	}
236
237	return $res;	1✔
238	}
239	}

dg / texy / 21501721037

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