Text::wordCount() - Code Metrics - Inspection of "v6.7.6 release" - pryley/site-reviews - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — main ( 62790e...23fbb2 )

by Paul

created 2023-04-20 13:51 UTC

Text::wordCount() A

↳ Parent: Text

Complexity

Conditions	4
Paths	4

Size

Total Lines	16
Code Lines	11

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	0
CRAP Score	20

Importance

Changes

Metric	Value
eloc	11
c	0
b	0
f	0
dl	0
loc	16
ccs	0
cts	12
cp	0
rs	9.9
cc	4
nc	4
nop	1
crap	20

<?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
    {
        $map = [];
        $text = static::normalize($text);
        // replace tags with placeholder
        $text = preg_replace_callback('|<([a-z+])[^>]*?>.*?</\\1>|siu', function ($match) use (&$map) {
            $map[] = $match[0];
            return '⍈';
        }, $text);
        $excerptLength = $limit;
        if ($splitWords) {
            $excerpt = static::words($text, $limit);
            $excerptLength = mb_strlen($excerpt);
        }
        $paragraphs = static::extractParagraphs($text, $excerptLength);
        $text = implode(PHP_EOL, $paragraphs);
        $i = 0;
        // replace placeholder with tags
        $text = preg_replace_callback('|⍈|u', function ($match) use (&$i, $map) {
            return $map[$i++];
        }, $text);
        return $text;
    }

    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', $name, 0, PREG_SPLIT_NO_EMPTY);
        $firstName = array_shift($names);
        $lastName = array_pop($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.
        $text = html_entity_decode($text);
        return $text;
    }

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

    public static function wordCount(string $text): int
    {
        $text = wp_strip_all_tags($text, true);
        if (!extension_loaded('intl')) {
            return count(preg_split('/[^\p{L}\p{N}\']+/u', $text));
        }
        $text = \Normalizer::normalize($text);
        $iterator = \IntlRuleBasedBreakIterator::createWordInstance('');
        $iterator->setText($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
    {
        $stringLength = extension_loaded('intl')
            ? static::excerptIntlSplit($text, $limit)
            : static::excerptSplit($text, $limit);
        return mb_substr($text, 0, $stringLength);
    }

    protected static function excerptIntlSplit(string $text, int $limit): int
    {
        $text = \Normalizer::normalize($text);
        $iterator = \IntlRuleBasedBreakIterator::createWordInstance('');
        $iterator->setText($text);
        $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 $limit): int
    {
        preg_match('/^\s*+(?:\S++\s*+){1,'.$limit.'}/u', $text, $matches);
        if (mb_strlen($text) === mb_strlen($matches[0] ?? '')) {
            return mb_strlen($text);
        }
        return mb_strlen(rtrim($matches[0]));
    }

    protected static function extractParagraphs(string $text, int $length): array
    {
        $paragraphs = preg_split('/\R+/um', $text);
        $paragraphs = array_map('trim', $paragraphs);
        foreach ($paragraphs as &$paragraph) {
            $paragraphLength = mb_strlen($paragraph);
            if ($length >= $paragraphLength) {
                $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;
    }
}


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

pryley / site-reviews

Push — main ( 62790e...23fbb2 )

Text::wordCount() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like