Text::extractParagraphs() - Code Metrics - Inspection of "fix scrutinizer issues" - pryley/site-reviews - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — develop ( 442c9f...b0c978 )

by Paul

created 2025-11-03 20:24 UTC

Text::extractParagraphs() B

↳ Parent: Text

Complexity

Conditions	7
Paths	4

Size

Total Lines	31
Code Lines	24

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	0
CRAP Score	56

Importance

Changes

Metric	Value
eloc	24
dl	0
loc	31
ccs	0
cts	27
cp	0
rs	8.6026
c	0
b	0
f	0
cc	7
nc	4
nop	2
crap	56

<?php

namespace GeminiLabs\SiteReviews\Helpers;

use GeminiLabs\SiteReviews\Modules\Html\Builder;
use GeminiLabs\SiteReviews\Modules\Sanitizers\SanitizeTextHtml;

class Text
{
    public static function excerpt(?string $text, int $limit = 55, bool $splitWords = true): string
    {
        [$text, $map] = static::replaceTags(static::normalize($text));
        $excerptLength = $limit;
        if ($splitWords) {
            $excerpt = static::words($text, $limit);
            $excerptLength = mb_strlen($excerpt);
        }
        $paragraphs = static::extractParagraphs($text, $excerptLength);
        $text = implode(PHP_EOL, $paragraphs);
        return static::restoreTags($text, $map);
    }

    public static function initials(?string $name, string $initialPunctuation = ''): string
    {
        preg_match_all('/(?<=\s|\b)\p{L}/u', (string) $name, $matches); // match the first letter of each word in the name
        $result = (string) array_reduce($matches[0], function ($carry, $word) use ($initialPunctuation) {
            $initial = mb_substr($word, 0, 1, 'UTF-8');
            $initial = mb_strtoupper($initial, 'UTF-8');
            return $carry.$initial.$initialPunctuation;
        });
        return trim($result);
    }

    /**
     * @param string $nameFormat  first|first_initial|last_initial|initials
     * @param string $initialType period|period_space|space
     */
    public static function name(?string $name, string $nameFormat = '', string $initialType = 'space'): string
    {
        $names = preg_split('/\W/u', (string) $name, 0, PREG_SPLIT_NO_EMPTY);
        $firstName = (string) array_shift($names);
        $lastName = (string) array_pop($names);
        $nameFormat = Str::restrictTo('first,first_initial,last_initial,initials', $nameFormat, '');
        $initialType = Str::restrictTo('period,period_space,space', $initialType, 'space');
        $initialTypes = [
            'period' => '.',
            'period_space' => '. ',
            'space' => ' ',
        ];
        $initialPunctuation = $initialTypes[$initialType];
        if ('initials' === $nameFormat) {
            return static::initials($name, $initialPunctuation);
        }
        $firstNameInitial = static::initials($firstName).$initialPunctuation;
        $lastNameInitial = $lastName ? static::initials($lastName).$initialPunctuation : '';
        $nameFormats = [
            'first' => $firstName,
            'first_initial' => $firstNameInitial.$lastName,
            'last' => $lastName,
            'last_initial' => "{$firstName} {$lastNameInitial}",
        ];
        return trim((string) Arr::get($nameFormats, $nameFormat, $name));
    }

    public static function normalize(?string $text): string
    {
        $text = (new SanitizeTextHtml($text))->run();
        $text = strip_shortcodes($text);
        $text = excerpt_remove_blocks($text); // just in case...
        $text = str_replace(']]>', ']]&gt;', $text);
        $text = normalize_whitespace($text); // normalize EOL characters and strip duplicate whitespace.
        $text = preg_replace('/\R{1,}/u', PHP_EOL.PHP_EOL, $text); // replace all line-breaks with a double line break
        $text = wptexturize($text); // replace common plain text characters with formatted entities.
        $text = ent2ncr($text); // convert named entities into numbered entities.
        $text = convert_chars($text); // converts lone & characters into &#038;
        $text = convert_invalid_entities($text); // convert invalid Unicode references range to valid range.
        $text = convert_smilies($text); // convert text smilies to emojis.
        $text = wp_specialchars_decode($text);
        return $text;
    }

    public static function text(?string $text): string
    {
        $text = static::normalize($text);
        if ($paragraphs = preg_split('/\R+/um', $text)) { // split text by line-breaks
            $paragraphs = array_map('trim', $paragraphs); // trim paragraphs
            $text = implode(PHP_EOL.PHP_EOL, $paragraphs);
        }
        return wpautop($text);
    }

    public static function wordCount(?string $text): int
    {
        $text = wp_strip_all_tags((string) $text, true);
        $iterator = static::iterator($text);
        if (empty($iterator)) {
            return count(preg_split('/[^\p{L}\p{N}\']+/u', $text));
        }
        $wordCount = 0;
        foreach ($iterator->getPartsIterator() as $part) {
            if (\IntlBreakIterator::WORD_NONE !== $iterator->getRuleStatus()) {
                ++$wordCount;
            }
        }
        return $wordCount;
    }

    public static function words(?string $text, int $limit = 0): string
    {
        $stringLength = static::excerptIntlSplit((string) $text, $limit);
        return mb_substr((string) $text, 0, $stringLength);
    }

    protected static function excerptIntlSplit(string $text, int $limit): int
    {
        $iterator = static::iterator($text);
        if (empty($iterator)) {
            return static::excerptSplit((string) $text, $limit);
        }
        $stringLength = 0;
        $wordCount = 0;
        foreach ($iterator->getPartsIterator() as $part) {
            $stringLength += mb_strlen($part);
            if (\IntlBreakIterator::WORD_NONE === $iterator->getRuleStatus()) {
                continue;
            }
            if (++$wordCount === $limit) {
                break;
            }
        }
        return $stringLength;
    }

    protected static function excerptSplit(string $text, int $limit): int
    {
        $length = mb_strlen($text);
        if ($limit < 1) {
            return $length;
        }
        preg_match('/^\s*+(?:\S++\s*+){1,'.$limit.'}/u', $text, $matches);
        $match = $matches[0] ?? '';
        if ($length === mb_strlen($match)) {
            return $length;
        }
        return mb_strlen(rtrim($match));
    }

    protected static function extractParagraphs(string $text, int $length): array
    {
        $paragraphs = preg_split('/\R+/um', $text);
        $paragraphs = array_map('trim', $paragraphs);
        $lastIndex = count($paragraphs) - 1;
        foreach ($paragraphs as $index => &$paragraph) {
            $paragraphLength = mb_strlen($paragraph);
            if ($length > $paragraphLength || ($length === $paragraphLength && $index === $lastIndex)) {
                $paragraph = sprintf('<p>%s</p>', $paragraph);
                $length -= $paragraphLength;
                continue;
            }
            if ($length > 0) {
                $hidden = mb_substr($paragraph, $length);
                $visible = mb_substr($paragraph, 0, $length);
                $paragraph = glsr(Builder::class)->p([
                    'class' => 'glsr-hidden-text',
                    'data-show-less' => __('Show less', 'site-reviews'),
                    'data-show-more' => __('Show more', 'site-reviews'),
                    'data-trigger' => glsr_get_option('reviews.excerpts_action') ?: 'expand',
                    'text' => sprintf('%s<span class="glsr-hidden">%s</span>', $visible, $hidden),
                ]);
                $length = 0;
                continue;
            }
            $paragraph = glsr(Builder::class)->p([
                'class' => 'glsr-hidden',
                'text' => $paragraph,
            ]);
        }
        return $paragraphs;
    }

    /**
     * @return \IntlRuleBasedBreakIterator|null
     */
    protected static function iterator(string $text)
    {
        if (!extension_loaded('intl')) {
            return null;
        }
        $iterator = \IntlRuleBasedBreakIterator::createWordInstance('');
        $normalizedText = \Normalizer::normalize($text);
        if (empty($normalizedText)) {
            return null;
        }
        if (!$iterator->setText($normalizedText)) {
            return null;
        }
        return $iterator;
    }

    protected static function replaceTags(string $text): array
    {
        $map = [];
        $result = preg_replace_callback('|<([a-z]+)[^>]*?>.*?</\\1>|siu', function ($matches) use (&$map) {
            $map[] = $matches[0];
            return '⍈';
        }, $text);
        return is_null($result)
            ? [$text, []]
            : [$result, $map];
    }

    protected static function restoreTags(string $text, array $map = []): string
    {
        if (empty($map)) {
            return $text;
        }
        $i = 0;
        $result = preg_replace_callback('|⍈|u', function ($matches) use (&$i, $map) {
            return $map[$i++] ?? '';
        }, $text);
        return $result ?? $text;
    }
}


1		<?php
2
3		namespace GeminiLabs\SiteReviews\Helpers;
4
5		use GeminiLabs\SiteReviews\Modules\Html\Builder;
6		use GeminiLabs\SiteReviews\Modules\Sanitizers\SanitizeTextHtml;
7
8		class Text
9		{
10		public static function excerpt(?string $text, int $limit = 55, bool $splitWords = true): string
11		{
12		[$text, $map] = static::replaceTags(static::normalize($text));
13		$excerptLength = $limit;
14		if ($splitWords) {
15		$excerpt = static::words($text, $limit);
16		$excerptLength = mb_strlen($excerpt);
17		}
18		$paragraphs = static::extractParagraphs($text, $excerptLength);
19		$text = implode(PHP_EOL, $paragraphs);
20		return static::restoreTags($text, $map);
21		}
22
23	29	public static function initials(?string $name, string $initialPunctuation = ''): string
24		{
25	29	preg_match_all('/(?<=\s\|\b)\p{L}/u', (string) $name, $matches); // match the first letter of each word in the name
26	29	$result = (string) array_reduce($matches[0], function ($carry, $word) use ($initialPunctuation) {
27	29	$initial = mb_substr($word, 0, 1, 'UTF-8');
28	29	$initial = mb_strtoupper($initial, 'UTF-8');
29	29	return $carry.$initial.$initialPunctuation;
30	29	});
31	29	return trim($result);
32		}
33
34		/**
35		* @param string $nameFormat first\|first_initial\|last_initial\|initials
36		* @param string $initialType period\|period_space\|space
37		*/
38	11	public static function name(?string $name, string $nameFormat = '', string $initialType = 'space'): string
39		{
40	11	$names = preg_split('/\W/u', (string) $name, 0, PREG_SPLIT_NO_EMPTY);
41	11	$firstName = (string) array_shift($names);
42	11	$lastName = (string) array_pop($names);
43	11	$nameFormat = Str::restrictTo('first,first_initial,last_initial,initials', $nameFormat, '');
44	11	$initialType = Str::restrictTo('period,period_space,space', $initialType, 'space');
45	11	$initialTypes = [
46	11	'period' => '.',
47	11	'period_space' => '. ',
48	11	'space' => ' ',
49	11	];
50	11	$initialPunctuation = $initialTypes[$initialType];
51	11	if ('initials' === $nameFormat) {
52	3	return static::initials($name, $initialPunctuation);
53		}
54	8	$firstNameInitial = static::initials($firstName).$initialPunctuation;
55	8	$lastNameInitial = $lastName ? static::initials($lastName).$initialPunctuation : '';
56	8	$nameFormats = [
57	8	'first' => $firstName,
58	8	'first_initial' => $firstNameInitial.$lastName,
59	8	'last' => $lastName,
60	8	'last_initial' => "{$firstName} {$lastNameInitial}",
61	8	];
62	8	return trim((string) Arr::get($nameFormats, $nameFormat, $name));
63		}
64
65		public static function normalize(?string $text): string
66		{
67		$text = (new SanitizeTextHtml($text))->run();
68		$text = strip_shortcodes($text);
69		$text = excerpt_remove_blocks($text); // just in case...
70		$text = str_replace(']]>', ']]>', $text);
71		$text = normalize_whitespace($text); // normalize EOL characters and strip duplicate whitespace.
72		$text = preg_replace('/\R{1,}/u', PHP_EOL.PHP_EOL, $text); // replace all line-breaks with a double line break
73		$text = wptexturize($text); // replace common plain text characters with formatted entities.
74		$text = ent2ncr($text); // convert named entities into numbered entities.
75		$text = convert_chars($text); // converts lone & characters into &
76		$text = convert_invalid_entities($text); // convert invalid Unicode references range to valid range.
77		$text = convert_smilies($text); // convert text smilies to emojis.
78		$text = wp_specialchars_decode($text);
79		return $text;
80		}
81
82		public static function text(?string $text): string
83		{
84		$text = static::normalize($text);
85		if ($paragraphs = preg_split('/\R+/um', $text)) { // split text by line-breaks
86		$paragraphs = array_map('trim', $paragraphs); // trim paragraphs
87		$text = implode(PHP_EOL.PHP_EOL, $paragraphs);
88		}
89		return wpautop($text);
90		}
91
92		public static function wordCount(?string $text): int
93		{
94		$text = wp_strip_all_tags((string) $text, true);
95		$iterator = static::iterator($text);
96		if (empty($iterator)) {
97		return count(preg_split('/[^\p{L}\p{N}\']+/u', $text));
98		}
99		$wordCount = 0;
100		foreach ($iterator->getPartsIterator() as $part) {
101		if (\IntlBreakIterator::WORD_NONE !== $iterator->getRuleStatus()) {
102		++$wordCount;
103		}
104		}
105		return $wordCount;
106		}
107
108		public static function words(?string $text, int $limit = 0): string
109		{
110		$stringLength = static::excerptIntlSplit((string) $text, $limit);
111		return mb_substr((string) $text, 0, $stringLength);
112		}
113
114		protected static function excerptIntlSplit(string $text, int $limit): int
115		{
116		$iterator = static::iterator($text);
117		if (empty($iterator)) {
118		return static::excerptSplit((string) $text, $limit);
119		}
120		$stringLength = 0;
121		$wordCount = 0;
122		foreach ($iterator->getPartsIterator() as $part) {
123		$stringLength += mb_strlen($part);
124		if (\IntlBreakIterator::WORD_NONE === $iterator->getRuleStatus()) {
125		continue;
126		}
127		if (++$wordCount === $limit) {
128		break;
129		}
130		}
131		return $stringLength;
132		}
133
134		protected static function excerptSplit(string $text, int $limit): int
135		{
136		$length = mb_strlen($text);
137		if ($limit < 1) {
138		return $length;
139		}
140		preg_match('/^\s+(?:\S++\s+){1,'.$limit.'}/u', $text, $matches);
141		$match = $matches[0] ?? '';
142		if ($length === mb_strlen($match)) {
143		return $length;
144		}
145		return mb_strlen(rtrim($match));
146		}
147
148		protected static function extractParagraphs(string $text, int $length): array
149		{
150		$paragraphs = preg_split('/\R+/um', $text);
151		$paragraphs = array_map('trim', $paragraphs);
152		$lastIndex = count($paragraphs) - 1;
153		foreach ($paragraphs as $index => &$paragraph) {
154		$paragraphLength = mb_strlen($paragraph);
155		if ($length > $paragraphLength \|\| ($length === $paragraphLength && $index === $lastIndex)) {
156		$paragraph = sprintf('<p>%s</p>', $paragraph);
157		$length -= $paragraphLength;
158		continue;
159		}
160		if ($length > 0) {
161		$hidden = mb_substr($paragraph, $length);
162		$visible = mb_substr($paragraph, 0, $length);
163		$paragraph = glsr(Builder::class)->p([
164		'class' => 'glsr-hidden-text',
165		'data-show-less' => __('Show less', 'site-reviews'),
166		'data-show-more' => __('Show more', 'site-reviews'),
167		'data-trigger' => glsr_get_option('reviews.excerpts_action') ?: 'expand',
168		'text' => sprintf('%s<span class="glsr-hidden">%s</span>', $visible, $hidden),
169		]);
170		$length = 0;
171		continue;
172		}
173		$paragraph = glsr(Builder::class)->p([
174		'class' => 'glsr-hidden',
175		'text' => $paragraph,
176		]);
177		}
178		return $paragraphs;
179		}
180
181		/**
182		* @return \IntlRuleBasedBreakIterator\|null
183		*/
184		protected static function iterator(string $text)
185		{
186		if (!extension_loaded('intl')) {
187		return null;
188		}
189		$iterator = \IntlRuleBasedBreakIterator::createWordInstance('');
190		$normalizedText = \Normalizer::normalize($text);
191		if (empty($normalizedText)) {
192		return null;
193		}
194		if (!$iterator->setText($normalizedText)) {
195		return null;
196		}
197		return $iterator;
198		}
199
200		protected static function replaceTags(string $text): array
201		{
202		$map = [];
203		$result = preg_replace_callback('\|<([a-z]+)[^>]?>.?</\\1>\|siu', function ($matches) use (&$map) {
204		$map[] = $matches[0];
205		return '⍈';
206		}, $text);
207		return is_null($result)
208		? [$text, []]
209		: [$result, $map];
210		}
211
212		protected static function restoreTags(string $text, array $map = []): string
213		{
214		if (empty($map)) {
215		return $text;
216		}
217		$i = 0;
218		$result = preg_replace_callback('\|⍈\|u', function ($matches) use (&$i, $map) {
219		return $map[$i++] ?? '';
220		}, $text);
221		return $result ?? $text;
222		}
223		}
224

pryley / site-reviews

Push — develop ( 442c9f...b0c978 )

Text::extractParagraphs() B

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like