22262589061

Committed 21 Feb 2026 07:04PM UTC coverage: 92.991% (+1.8%) from 91.178%

Build Type

push

github

Committed by

Commit Message

LinkModule: deprecated label and modifiers in link definitions

Run Details

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

126 existing lines in 22 files now uncovered.

2083 of 2240 relevant lines covered (92.99%)

0.93 hits per line

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

98.18

/src/Texy/Modules/AutolinkModule.php

<?php declare(strict_types=1);

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

namespace Texy\Modules;

use Texy;
use Texy\HandlerInvocation;
use Texy\InlineParser;
use Texy\Link;
use Texy\Patterns;
use Texy\Regexp;
use function iconv_strlen, iconv_substr, str_replace, strncasecmp;


/**
 * Autodetects URLs and email addresses in text.
 */
final class AutolinkModule extends Texy\Module
{
        /** shorten URLs to more readable form? */
        public bool $shorten = true;


        public function __construct(
                private Texy\Texy $texy,
        ) {
                $texy->addHandler('linkEmail', $this->solveUrlEmail(...));
                $texy->addHandler('linkURL', $this->solveUrlEmail(...));
        }


        public function beforeParse(string &$text): void
        {
                // direct url; characters not allowed in URL <>[\]^`{|}
                $this->texy->registerLinePattern(
                        $this->parseUrlEmail(...),
                        '~
                                (?<= ^ | [\s([<:\x17] )            # must be preceded by these chars
                                (?: https?:// | www\. | ftp:// )   # protocol or www
                                [0-9.' . Patterns::CHAR . '-]      # first char
                                [/\d' . Patterns::CHAR . '+.\~%&?@=_:;#$!,*()\x{ad}-]{1,1000}  # URL body
                                [/\d' . Patterns::CHAR . '+\~?@=_#$*]  # last char
                        ~',
                        'link/url',
                        '~(?: https?:// | www\. | ftp://)~',
                );

                // direct email
                $this->texy->registerLinePattern(
                        $this->parseUrlEmail(...),
                        '~
                                (?<= ^ | [\s([<\x17] )             # must be preceded by these chars
                                ' . Patterns::EMAIL . '
                        ~',
                        'link/email',
                        '~' . Patterns::EMAIL . '~',
                );
        }


        /**
         * Parses http://davidgrudl.com david@grudl.com
         * @param  array<?string>  $matches
         */
        public function parseUrlEmail(InlineParser $parser, array $matches, string $name): Texy\HtmlElement|string|null
        {
                [$mURL] = $matches;
                // [0] => URL

                $link = new Link($mURL);
                $this->texy->linkModule->checkLink($link);

                return $this->texy->invokeAroundHandlers(
                        $name === 'link/email' ? 'linkEmail' : 'linkURL',
                        $parser,
                        [$link],
                );
        }


        /**
         * Handler for URL/email - creates textual content and link element.
         */
        private function solveUrlEmail(HandlerInvocation $invocation, Link $link): Texy\HtmlElement|string|null
        {
                $content = $this->textualUrl($link);
                $content = $this->texy->protect($content, Texy\Texy::CONTENT_TEXTUAL);
                return $this->texy->linkModule->solve(null, $link, $content);
        }


        /**
         * Returns textual representation of URL.
         */
        public function textualUrl(Link $link): string
        {
                if ($this->texy->obfuscateEmail && Regexp::match($link->raw, '~^' . Patterns::EMAIL . '$~')) { // email
                        return str_replace('@', '&#64;<!-- -->', $link->raw);
                }

                if ($this->shorten && Regexp::match($link->raw, '~^(https?://|ftp://|www\.|/)~i')) {
                        $raw = strncasecmp($link->raw, 'www.', 4) === 0
                                ? 'none://' . $link->raw
                                : $link->raw;

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

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

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

                        if ($parts['path'] !== null) {
                                $res .= (iconv_strlen($parts['path'], 'UTF-8') > 16 ? ("/\u{2026}" . iconv_substr($parts['path'], -12, 12, 'UTF-8')) : $parts['path']);
                        }

                        if ($parts['query'] > '') {
                                $res .= iconv_strlen($parts['query'], 'UTF-8') > 4
                                        ? "?\u{2026}"
                                        : ('?' . $parts['query']);
                        } elseif ($parts['fragment'] > '') {
                                $res .= iconv_strlen($parts['fragment'], 'UTF-8') > 4
                                        ? "#\u{2026}"
                                        : ('#' . $parts['fragment']);
                        }

                        return $res;
                }

                return $link->raw;
        }
}

1	<?php declare(strict_types=1);
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	namespace Texy\Modules;
9
10	use Texy;
11	use Texy\HandlerInvocation;
12	use Texy\InlineParser;
13	use Texy\Link;
14	use Texy\Patterns;
15	use Texy\Regexp;
16	use function iconv_strlen, iconv_substr, str_replace, strncasecmp;
17
18
19	/**
20	* Autodetects URLs and email addresses in text.
21	*/
22	final class AutolinkModule extends Texy\Module
23	{
24	/** shorten URLs to more readable form? */
25	public bool $shorten = true;
26
27
28	public function __construct(	1✔
29	private Texy\Texy $texy,
30	) {
31	$texy->addHandler('linkEmail', $this->solveUrlEmail(...));	1✔
32	$texy->addHandler('linkURL', $this->solveUrlEmail(...));	1✔
33	}	1✔
34
35
36	public function beforeParse(string &$text): void	1✔
37	{
38	// direct url; characters not allowed in URL <>[\]^`{\|}
39	$this->texy->registerLinePattern(	1✔
40	$this->parseUrlEmail(...),	1✔
41	'~
42	(?<= ^ \| [\s([<:\x17] ) # must be preceded by these chars
43	(?: https?:// \| www\. \| ftp:// ) # protocol or www
44	[0-9.' . Patterns::CHAR . '-] # first char	1✔
45	[/\d' . Patterns::CHAR . '+.\~%&?@=_:;#$!,*()\x{ad}-]{1,1000} # URL body	1✔
46	[/\d' . Patterns::CHAR . '+\~?@=_#$*] # last char	1✔
47	~',
48	'link/url',	1✔
49	'~(?: https?:// \| www\. \| ftp://)~',	1✔
50	);
51
52	// direct email
53	$this->texy->registerLinePattern(	1✔
54	$this->parseUrlEmail(...),	1✔
55	'~
56	(?<= ^ \| [\s([<\x17] ) # must be preceded by these chars
57	' . Patterns::EMAIL . '	1✔
58	~',
59	'link/email',	1✔
60	'~' . Patterns::EMAIL . '~',	1✔
61	);
62	}	1✔
63
64
65	/**
66	* Parses http://davidgrudl.com david@grudl.com
67	* @param array<?string> $matches
68	*/
69	public function parseUrlEmail(InlineParser $parser, array $matches, string $name): Texy\HtmlElement\|string\|null	1✔
70	{
71	[$mURL] = $matches;	1✔
72	// [0] => URL
73
74	$link = new Link($mURL);	1✔
75	$this->texy->linkModule->checkLink($link);	1✔
76
77	return $this->texy->invokeAroundHandlers(	1✔
78	$name === 'link/email' ? 'linkEmail' : 'linkURL',	1✔
79	$parser,
80	[$link],	1✔
81	);
82	}
83
84
85	/**
86	* Handler for URL/email - creates textual content and link element.
87	*/
88	private function solveUrlEmail(HandlerInvocation $invocation, Link $link): Texy\HtmlElement\|string\|null	1✔
89	{
90	$content = $this->textualUrl($link);	1✔
91	$content = $this->texy->protect($content, Texy\Texy::CONTENT_TEXTUAL);	1✔
92	return $this->texy->linkModule->solve(null, $link, $content);	1✔
93	}
94
95
96	/**
97	* Returns textual representation of URL.
98	*/
99	public function textualUrl(Link $link): string	1✔
100	{
101	if ($this->texy->obfuscateEmail && Regexp::match($link->raw, '~^' . Patterns::EMAIL . '$~')) { // email	1✔
102	return str_replace('@', '@<!-- -->', $link->raw);	1✔
103	}
104
105	if ($this->shorten && Regexp::match($link->raw, '~^(https?://\|ftp://\|www\.\|/)~i')) {	1✔
106	$raw = strncasecmp($link->raw, 'www.', 4) === 0	1✔
107	? 'none://' . $link->raw	1✔
108	: $link->raw;	1✔
109
110	// parse_url() in PHP damages UTF-8 - use regular expression
111	if (!($parts = Regexp::match($raw, '~^	1✔
112	(?: (?P<scheme> [a-z]+ ) : )?
113	(?: // (?P<host> [^/?#]+ ) )?
114	(?P<path> (?: / \| ^ ) (?! / ) [^?#]* )?
115	(?: \? (?P<query> [^#]* ) )?
116	(?: \# (?P<fragment> .* ) )?
117	$
118	~'))) {
UNCOV 119	return $link->raw;	×
120	}
121
122	$res = '';	1✔
123	if ($parts['scheme'] !== null && $parts['scheme'] !== 'none') {	1✔
124	$res .= $parts['scheme'] . '://';	1✔
125	}
126
127	if ($parts['host'] !== null) {	1✔
128	$res .= $parts['host'];	1✔
129	}
130
131	if ($parts['path'] !== null) {	1✔
132	$res .= (iconv_strlen($parts['path'], 'UTF-8') > 16 ? ("/\u{2026}" . iconv_substr($parts['path'], -12, 12, 'UTF-8')) : $parts['path']);	1✔
133	}
134
135	if ($parts['query'] > '') {	1✔
136	$res .= iconv_strlen($parts['query'], 'UTF-8') > 4	1✔
137	? "?\u{2026}"	1✔
138	: ('?' . $parts['query']);	1✔
139	} elseif ($parts['fragment'] > '') {	1✔
140	$res .= iconv_strlen($parts['fragment'], 'UTF-8') > 4	1✔
141	? "#\u{2026}"	1✔
142	: ('#' . $parts['fragment']);	1✔
143	}
144
145	return $res;	1✔
146	}
147
148	return $link->raw;	1✔
149	}
150	}

dg / texy / 22262589061

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