WikiTextUtil::extractRefsAndListOfLinks() - Code Metrics - Inspection of "Add WikiText:: extract ExternalLinksList" - Dispositif/Wikibot - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( b8fbf6...e42360 )

by Dispositif

created 2020-06-06 17:50 UTC

WikiTextUtil::extractRefsAndListOfLinks() A

↳ Parent: WikiTextUtil

Complexity

Conditions	3
Paths	3

Size

Total Lines	16
Code Lines	6

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	0
CRAP Score	12

Importance

Changes

Metric	Value
cc	3
eloc	6
nc	3
nop	1
dl	0
loc	16
ccs	0
cts	4
cp	0
crap	12
rs	10
c	0
b	0
f	0

<?php
/**
 * This file is part of dispositif/wikibot application
 * 2019 : Philippe M. <[email protected]>
 * For the full copyright and MIT license information, please view the LICENSE file.
 */

declare(strict_types=1);

namespace App\Domain\Utils;

class WikiTextUtil extends TextUtil
{
    /**
     * todo {{ref}}
     *
     * @param string $text
     *
     * @return array [0=>['<ref>fu</ref>', 'fu'], 1=> ...]
     */
    public static function extractRefsAndListOfLinks(string $text): array
    {
        // s = "\n" include in "." // m = ^multiline$
        // Exclusion des imbrications
        if (!preg_match_all('#<ref[^>/]*>((?:(?!</ref>).)*)</ref>#ism', $text, $refs, PREG_SET_ORDER)) {
            return [];
        }
        $result = $refs;

        // extraction des liens externes
        // ^\* *(https?:\/\/[^ ]+[^ .])$
        if (preg_match_all('#^\* *(https?://[^ \n]+[^ \n.])\.? *\n#im', $text, $liensExternes, PREG_SET_ORDER)) {
            $result = array_merge($result, $liensExternes);
        }

        return $result;
    }

    /**
     * remove wiki encoding : italic, bold, links [ ] and [[fu|bar]] => bar
     * replace non-breaking spaces
     * replace {{lang|en|fubar}} => fubar.
     *
     * @param      $text
     * @param bool $stripcomment
     *
     * @return string
     */
    public static function unWikify(string $text, ?bool $stripcomment = true): string
    {
        if (true === $stripcomment) {
            $text = self::removeHTMLcomments($text);
        }

        $text = str_replace(
            ['[', ']', "'''", "''", ' '],
            ['', '', '', '', ' '],
            preg_replace(
                [
                    "#\[\[[^|\]]*\|([^]]*)]]#",
                    '#{{ ?(?:lang|langue) ?\|[^|]+\| ?(?:texte=)?([^{}=]+)(?:\|dir=rtl)?}}#i',
                    "#&[\w\d]{2,7};#",
                ],
                ['$1', '$1', ''],
                $text
            )
        );
        // {{Lien|Jeffrey Robinson}} => Jeffrey Robinson
        $text = preg_replace('#{{ ?lien ?\| ?([^|}]+) ?}}#i', '${1}', $text);

        $text = strip_tags($text, '<sup><sub>');

        return $text;
    }

    public static function isWikify(string $text): bool
    {
        if (self::unWikify($text) !== $text) {
            return true;
        }

        return false;
    }

    /**
     * Generate wikilink from string.
     *
     * @param string      $label
     * @param string|null $page
     *
     * @return string
     */
    public static function wikilink(string $label, ?string $page = null): string
    {
        $label = trim(str_replace('_', ' ', self::unWikify($label)));
        $page = ($page) ? trim(self::unWikify($page)) : null;

        // fu_bar => [[fu_bar]] / Fu, fu => [[fu]]
        if (empty($page) || self::str2WikiTitle($label) === self::str2WikiTitle($page)) {
            return '[['.$label.']]';
        }

        // fu, bar => [[Bar|fu]]
        return sprintf(
            '[[%s|%s]]',
            self::str2WikiTitle($page),
            $label
        );
    }

    /**
     * "fu_bar_ " => "Fu bar".
     * @param string $str
     *
     * @return string
     */
    private static function str2WikiTitle(string $str): string
    {
        return TextUtil::mb_ucfirst(trim(str_replace('_', ' ', $str)));
    }

    /**
     * Get page titles from wiki encoded links.
     * (but not others projects links like [[wikt:bla]].
     *
     * @param string $text
     *
     * @return array|null
     */
    public static function getWikilinkPages(string $text): ?array
    {
        if (preg_match_all('#\[\[([^:|\]]+)(?:\|[^|\]]*)?]]#', $text, $matches) > 0) {
            return $matches[1];
        }

        return null;
    }

    /**
     * Strip external links (http://) from wiki text.
     * "[http://google.fr Google]" => "Google"
     * "bla [http://google.fr]" => "bla"
     *
     * @param string $text
     *
     * @return string
     */
    public static function stripExternalLink(string $text): string
    {
        $text = preg_replace('#\[(https?://[^][<>\s"]+) *((?<= )[^\n\]]*|)\]#i', '${2}', $text);

        return trim($text);
    }

    /**
     * @param string $text
     *
     * @return bool
     */
    public static function isCommented(string $text): bool
    {
        $text = str_replace('<!-- Paramètre obligatoire -->', '', $text);

        //ou preg_match('#<\!--(?!-->).*-->#s', '', $text); // plus lourd mais précis
        return (preg_match('#<!--[^>]*-->#', $text) > 0) ? true : false;
    }

    /**
     * Remove '<!--', '-->', and everything between.
     * To avoid leaving blank lines, when a comment is both preceded
     * and followed by a newline (ignoring spaces), trim leading and
     * trailing spaces and one of the newlines.
     * (c) WikiMedia /includes/parser/Sanitizer.php.
     *
     * @param string $text
     *
     * @return string
     */
    public static function removeHTMLcomments(string $text)
    {
        while (false !== ($start = mb_strpos($text, '<!--'))) {
            $end = mb_strpos($text, '-->', $start + 4);
            if (false === $end) {
                // Unterminated comment; bail out
                break;
            }
            $end += 3;
            // Trim space and newline if the comment is both
            // preceded and followed by a newline
            $spaceStart = max($start - 1, 0);
            $spaceLen = $end - $spaceStart;
            while (' ' === substr($text, $spaceStart, 1) && $spaceStart > 0) {
                --$spaceStart;
                ++$spaceLen;
            }
            while (' ' === substr($text, $spaceStart + $spaceLen, 1)) {
                ++$spaceLen;
            }
            if ("\n" === substr($text, $spaceStart, 1)
                && "\n" === substr($text, $spaceStart + $spaceLen, 1)
            ) {
                // Remove the comment, leading and trailing
                // spaces, and leave only one newline.
                $text = substr_replace($text, "\n", $spaceStart, $spaceLen + 1);
            } else {
                // Remove just the comment.
                $text = substr_replace($text, '', $start, $end - $start);
            }
        }

        return $text;
    }

    /**
     * Strip the final point (".") as in <ref> ending.
     *
     * @param string $str
     *
     * @return string
     */
    public static function stripFinalPoint(string $str): string
    {
        if (substr($str, -1, 1) === '.') {
            return substr($str, 0, strlen($str) - 1);
        }

        return $str;
    }
}


1		<?php
2		/**
3		* This file is part of dispositif/wikibot application
4		* 2019 : Philippe M. <[email protected]>
5		* For the full copyright and MIT license information, please view the LICENSE file.
6		*/
7
8		declare(strict_types=1);
9
10		namespace App\Domain\Utils;
11
12		class WikiTextUtil extends TextUtil
13		{
14		/**
15		* todo {{ref}}
16		*
17		* @param string $text
18		*
19		* @return array [0=>['<ref>fu</ref>', 'fu'], 1=> ...]
20		*/
21		public static function extractRefsAndListOfLinks(string $text): array
22		{
23		// s = "\n" include in "." // m = ^multiline$
24		// Exclusion des imbrications
25		if (!preg_match_all('#<ref[^>/]>((?:(?!</ref>).))</ref>#ism', $text, $refs, PREG_SET_ORDER)) {
26		return [];
27		}
28		$result = $refs;
29
30		// extraction des liens externes
31		// ^\* *(https?:\/\/[^ ]+[^ .])$
32		if (preg_match_all('#^\* (https?://[^ \n]+[^ \n.])\.? \n#im', $text, $liensExternes, PREG_SET_ORDER)) {
33		$result = array_merge($result, $liensExternes);
34		}
35
36		return $result;
37		}
38
39		/**
40		* remove wiki encoding : italic, bold, links [ ] and [[fu\|bar]] => bar
41		* replace non-breaking spaces
42	60	* replace {{lang\|en\|fubar}} => fubar.
43		*
44	60	* @param $text
45	60	* @param bool $stripcomment
46		*
47		* @return string
48	60	*/
49	60	public static function unWikify(string $text, ?bool $stripcomment = true): string
50	60	{
51	60	if (true === $stripcomment) {
52		$text = self::removeHTMLcomments($text);
53	60	}
54
55		$text = str_replace(
56		['[', ']', "'''", "''", ' '],
57	60	['', '', '', '', ' '],
58	60	preg_replace(
59		[
60		"#\[\[[^\|\]]\\|([^]])]]#",
61		'#{{ ?(?:lang\|langue) ?\\|[^\|]+\\| ?(?:texte=)?([^{}=]+)(?:\\|dir=rtl)?}}#i',
62	60	"#&[\w\d]{2,7};#",
63		],
64	60	['$1', '$1', ''],
65		$text
66	60	)
67		);
68		// {{Lien\|Jeffrey Robinson}} => Jeffrey Robinson
69	24	$text = preg_replace('#{{ ?lien ?\\| ?([^\|}]+) ?}}#i', '${1}', $text);
70
71	24	$text = strip_tags($text, '<sup><sub>');
72	3
73		return $text;
74		}
75	21
76		public static function isWikify(string $text): bool
77		{
78		if (self::unWikify($text) !== $text) {
79		return true;
80		}
81
82		return false;
83		}
84
85		/**
86	4	* Generate wikilink from string.
87		*
88	4	* @param string $label
89	4	* @param string\|null $page
90		*
91		* @return string
92	4	*/
93	3	public static function wikilink(string $label, ?string $page = null): string
94		{
95		$label = trim(str_replace('_', ' ', self::unWikify($label)));
96		$page = ($page) ? trim(self::unWikify($page)) : null;
97	2
98	2	// fu_bar => [[fu_bar]] / Fu, fu => [[fu]]
99	2	if (empty($page) \|\| self::str2WikiTitle($label) === self::str2WikiTitle($page)) {
100	2	return '[['.$label.']]';
101		}
102
103		// fu, bar => [[Bar\|fu]]
104		return sprintf(
105		'[[%s\|%s]]',
106		self::str2WikiTitle($page),
107	4	$label
108		);
109	4	}
110
111		/**
112		* "fu_bar_ " => "Fu bar".
113		* @param string $str
114		*
115		* @return string
116		*/
117		private static function str2WikiTitle(string $str): string
118		{
119		return TextUtil::mb_ucfirst(trim(str_replace('_', ' ', $str)));
120	1	}
121
122	1	/**
123	1	* Get page titles from wiki encoded links.
124		* (but not others projects links like [[wikt:bla]].
125		*
126		* @param string $text
127		*
128		* @return array\|null
129		*/
130		public static function getWikilinkPages(string $text): ?array
131		{
132		if (preg_match_all('#\[\[([^:\|\]]+)(?:\\|[^\|\]]*)?]]#', $text, $matches) > 0) {
133		return $matches[1];
134		}
135
136		return null;
137		}
138	2
139		/**
140	2	* Strip external links (http://) from wiki text.
141		* "[http://google.fr Google]" => "Google"
142	2	* "bla [http://google.fr]" => "bla"
143		*
144		* @param string $text
145		*
146		* @return string
147		*/
148		public static function stripExternalLink(string $text): string
149		{
150	24	$text = preg_replace('#\[(https?://[^][<>\s"]+) ((?<= )[^\n\]]\|)\]#i', '${2}', $text);
151
152	24	return trim($text);
153		}
154
155	24	/**
156		* @param string $text
157		*
158		* @return bool
159		*/
160		public static function isCommented(string $text): bool
161		{
162		$text = str_replace('<!-- Paramètre obligatoire -->', '', $text);
163
164		//ou preg_match('#<\!--(?!-->).*-->#s', '', $text); // plus lourd mais précis
165		return (preg_match('#<!--[^>]*-->#', $text) > 0) ? true : false;
166		}
167
168		/**
169	61	* Remove '<!--', '-->', and everything between.
170		* To avoid leaving blank lines, when a comment is both preceded
171	61	* and followed by a newline (ignoring spaces), trim leading and
172	2	* trailing spaces and one of the newlines.
173	2	* (c) WikiMedia /includes/parser/Sanitizer.php.
174		*
175		* @param string $text
176		*
177	2	* @return string
178		*/
179		public static function removeHTMLcomments(string $text)
180	2	{
181	2	while (false !== ($start = mb_strpos($text, '<!--'))) {
182	2	$end = mb_strpos($text, '-->', $start + 4);
183		if (false === $end) {
184		// Unterminated comment; bail out
185		break;
186	2	}
187	1	$end += 3;
188		// Trim space and newline if the comment is both
189	2	// preceded and followed by a newline
190	2	$spaceStart = max($start - 1, 0);
191		$spaceLen = $end - $spaceStart;
192		while (' ' === substr($text, $spaceStart, 1) && $spaceStart > 0) {
193		--$spaceStart;
194		++$spaceLen;
195		}
196		while (' ' === substr($text, $spaceStart + $spaceLen, 1)) {
197	2	++$spaceLen;
198		}
199		if ("\n" === substr($text, $spaceStart, 1)
200		&& "\n" === substr($text, $spaceStart + $spaceLen, 1)
201	61	) {
202		// Remove the comment, leading and trailing
203		// spaces, and leave only one newline.
204		$text = substr_replace($text, "\n", $spaceStart, $spaceLen + 1);
205		} else {
206		// Remove just the comment.
207		$text = substr_replace($text, '', $start, $end - $start);
208		}
209		}
210
211		return $text;
212		}
213
214		/**
215		* Strip the final point (".") as in <ref> ending.
216		*
217		* @param string $str
218		*
219		* @return string
220		*/
221		public static function stripFinalPoint(string $str): string
222		{
223		if (substr($str, -1, 1) === '.') {
224		return substr($str, 0, strlen($str) - 1);
225		}
226
227		return $str;
228		}
229		}
230

Dispositif / Wikibot

Push — master ( b8fbf6...e42360 )

WikiTextUtil::extractRefsAndListOfLinks() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like