TextUtil::cutTextOnSpace() - Code Metrics - Inspection of "style, cosmetic" - Dispositif/Wikibot - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( dff8a4...2556d0 )

by Dispositif

created 2023-04-08 11:33 UTC

TextUtil::cutTextOnSpace() A

↳ Parent: TextUtil

Complexity

Conditions	3
Paths	3

Size

Total Lines	9
Code Lines	5

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	0
CRAP Score	12

Importance

Changes

Metric	Value
cc	3
eloc	5
c	0
b	0
f	0
nc	3
nop	2
dl	0
loc	9
ccs	0
cts	0
cp	0
crap	12
rs	10

<?php
/*
 * This file is part of dispositif/wikibot application (@github)
 * 2019-2023 © Philippe M./Irønie  <[email protected]>
 * For the full copyright and MIT license information, view the license file.
 */

declare(strict_types=1);

namespace App\Domain\Utils;

/**
 * Class TextUtil.
 */
abstract class TextUtil
{
    public const SYMBOL_TEXT_CUT = '…';

    public const SKIP_PREDICT_PARAM = ['issue'];

    public const NO_BREAK_SPACE = "\xC2\xA0"; // &#160;

    public const NO_BREAK_THIN_SPACE = "\xE2\x80\xAF";

    public const ALL_PUNCTUATION
        = [
            '!',
            '"',
            '«',
            '»',
            '#',
            '$',
            '%',
            "'",
            '’',
            '´',
            '`',
            '^',
            '…',
            '‽',
            '(',
            ')',
            '*',
            '⁂',
            '+',
            '–',
            '—',
            '/',
            ':',
            ';',
            '?',
            '@',
            '[',
            '\\',
            ']',
            '_',
            '`',
            '{',
            '|',
            '¦',
            '}',
            '~',
            '<',
            '>',
            '№',
            '©',
            '®',
            '°',
            '†',
            '§',
            '∴',
            '∵',
            '¶',
            '•',
            '+',
        ];

    // &#8239;
    //    const ELLIPSIS = '…';
    //    const LAQUO = '«'; // &laquo;
    //    const RAQUO = '»'; // &raquo;
    //    const RSQUO = '’'; // &rsquo;
    //    const TIMES = '×'; // &times;
    //    const NDASH = '–'; // &ndash; or &#x2013;
    //    const MDASH = '—'; // &mdash; or &#x2014;
    //    const LDQUO = '“'; // &ldquo; or &#8220;
    //    const RDQUO = '”'; // &rdquo; or &#8221;
    //    const BDQUO = '„'; // &bdquo; or &#8222;
    //    const SHY = "\xC2\xAD"; // &shy;
    //    const TRADE = '™'; // &trade;
    //    const REG = '®'; // &reg;
    //    const COPY = '©'; // &copy;
    public const ALL_SPACES = "\xE2\x80\xAF|\xC2\xAD|\xC2\xA0|\\s"; // Used in regexps. Better than \s

    /**
     * UTF8 first letter in upper case.
     * "économie" => "Économie".
     */
    public static function mb_ucfirst(string $str, ?string $e = 'UTF-8'): string
    {
        $first = mb_strtoupper(mb_substr($str, 0, 1, $e), $e);
        $rest = mb_substr($str, 1, mb_strlen($str, $e), $e);

        return $first.$rest;
    }

    /**
     * UTF8 first letter in lower case.
     * "Économie" => "économie".
     *
     * @param string      $str
     * @param string|null $e
     *
     * @return string
     */
    public static function mb_lowerfirst(string $str, ?string $e = 'UTF-8'): string
    {
        $first = mb_strtolower(mb_substr($str, 0, 1, $e), $e);
        $rest = mb_substr($str, 1, mb_strlen($str, $e), $e);

        return $first.$rest;
    }

    public static function replaceNonBreakingSpaces(string $text): string
    {
        return str_replace([self::NO_BREAK_SPACE, self::NO_BREAK_THIN_SPACE], ' ', $text);
    }

    /**
     * Trim also non-breaking space and carriage return.
     */
    public static function trim(string $string): string
    {
        return trim($string, self::NO_BREAK_SPACE.self::NO_BREAK_THIN_SPACE."\n\t\r");
    }

    /**
     * Todo verify/correct.
     *
     * @param string $str
     *
     * @return bool
     */
    //    static public function containsNonLatinCharacters(string $str): bool
    //    {
    //        return preg_match('/[^\\p{Common}\\p{Latin}]/u', $str);
    //    }

    /**
     * Simplest levenshtein distance prediction of the correct param name.
     * Weird results with ASCII extended chars :
     * levenshtein('notre','nôtre') => 2
     * TODO move.
     *
     * @param string $str
     * @param array  $names
     * @param int    $max Maximum number of permutation/add/subtraction)
     *
     * @return string|null
     */
    public static function predictCorrectParam(string $str, array $names, int $max = 2): ?string
    {
        $sanitized = self::sanitizeParamForPredict($str);
        $closest = null;
        foreach ($names as $name) {
            $sanitizedName = self::sanitizeParamForPredict($name);
            if ($str === $name || $sanitized === $sanitizedName) {
                return $name; // exact match
            }
            $lev = levenshtein($str, $name);
            $lev2 = levenshtein($sanitized, $sanitizedName);

            if (!isset($shortest) || $lev < $shortest || $lev2 < $shortest) {
                $closest = $name;
                $shortest = $lev;
            }
        }
        if (isset($shortest) && $shortest <= $max && !in_array($sanitized, self::SKIP_PREDICT_PARAM)) {
            return $closest;
        }

        return null;
    }

    /**
     * For predictCorrectParam().
     *
     * @param string $str
     *
     * @return string
     */
    private static function sanitizeParamForPredict(string $str): string
    {
        $sanitized = mb_strtolower(self::stripPunctuation(self::stripAccents($str)));

        return trim(preg_replace('#[^a-z0-9 ]#', '', $sanitized));
    }

    /**
     * Strip punctuation
     * UTF-8 compatible ??
     * Note : can't use str_split() which cut on 1 byte length
     * See http://fr.wikipedia.org/wiki/Ponctuation.
     */
    public static function stripPunctuation(string $str): string
    {
        return str_replace(
            self::ALL_PUNCTUATION,
            '',
            $str
        );
    }

    /**
     * Strip accents
     * OK : grec, cyrillique, macron, hatchek, brève, rond en chef, tilde
     * UTF-8 compatible.
     *
     * @param string $string
     *
     * @return string
     */
    public static function stripAccents(string $string): string
    {
        return strtr(
            utf8_decode($string),
            utf8_decode(
                'àáâãäçèéêëìíîïñòóôõöùúûüýÿÀÁÂÃÄÇÈÉÊËÌÍÎÏÑÒÓÔÕÖÙÚÛÜÝøāǟǡēḕḗḡḹīōȫȭȱṑṓǭṝūǖṻȳǣӣᾱῑῡčšžйўŭăӗğÅåůẘẙ'
            ),
            utf8_decode(
                'aaaaaceeeeiiiinooooouuuuyyAAAAACEEEEIIIINOOOOOUUUUYoaaaeeeglioooooooruuuyæиαιυcszиyuaegAauwy'
            )
        );
    }

    /**
     * Like PHP8 str_ends_with(). Multibytes ok.
     *
     * @param string $haystack
     * @param string $needle
     *
     * @return bool
     */
    public static function str_ends_with(string $haystack, string $needle): bool
    {
        $len = mb_strlen($needle);
        if ($len === 0) {
            return true;
        }

        return (mb_substr($haystack, -$len) === $needle);
    }

    /**
     * Like PHP8 str_starts_with().
     *
     * @param string $haystack
     * @param string $needle
     *
     * @return bool
     */
    public static function str_starts_with(string $haystack, string $needle): bool
    {
        $len = mb_strlen($needle);

        return (mb_substr($haystack, 0, $len) === $needle);
    }

    /**
     * Cut string at position of last space before Xth character.
     */
    public static function cutTextOnSpace(string $text, int $maxLength = 70): string
    {
        if (mb_strlen($text) > $maxLength) {
            $spacePos = mb_strrpos(mb_substr($text, 0, $maxLength), ' ');
            $spacePos = ($spacePos > ($maxLength - 12)) ? $spacePos : $maxLength;
            $text = trim(mb_substr($text, 0, $spacePos)) . self::SYMBOL_TEXT_CUT;
        }

        return $text;
    }

    public static function countAllCapsWords(string $text): int
    {
        $words = explode(' ', $text);
        $count = 0;
        foreach ($words as $word) {
            if (mb_strlen($word) > 2 && mb_strtoupper($word) === $word) {
                ++$count;
            }
        }

        return $count;
    }
}


1		<?php
2		/*
3		* This file is part of dispositif/wikibot application (@github)
4		* 2019-2023 © Philippe M./Irønie <[email protected]>
5		* For the full copyright and MIT license information, view the license file.
6		*/
7
8		declare(strict_types=1);
9
10		namespace App\Domain\Utils;
11
12		/**
13		* Class TextUtil.
14		*/
15		abstract class TextUtil
16		{
17		public const SYMBOL_TEXT_CUT = '…';
18
19		public const SKIP_PREDICT_PARAM = ['issue'];
20
21		public const NO_BREAK_SPACE = "\xC2\xA0"; //
22
23		public const NO_BREAK_THIN_SPACE = "\xE2\x80\xAF";
24
25		public const ALL_PUNCTUATION
26		= [
27		'!',
28		'"',
29		'«',
30		'»',
31		'#',
32		'$',
33		'%',
34		"'",
35		'’',
36		'´',
37		'`',
38		'^',
39		'…',
40		'‽',
41		'(',
42		')',
43		'*',
44		'⁂',
45		'+',
46		'–',
47		'—',
48		'/',
49		':',
50		';',
51		'?',
52		'@',
53		'[',
54		'\\',
55		']',
56		'_',
57		'`',
58		'{',
59		'\|',
60		'¦',
61		'}',
62		'~',
63		'<',
64		'>',
65		'№',
66		'©',
67		'®',
68		'°',
69		'†',
70		'§',
71		'∴',
72		'∵',
73		'¶',
74		'•',
75		'+',
76		];
77
78		//
79		// const ELLIPSIS = '…';
80		// const LAQUO = '«'; // «
81		// const RAQUO = '»'; // »
82		// const RSQUO = '’'; // ’
83		// const TIMES = '×'; // ×
84		// const NDASH = '–'; // – or –
85		// const MDASH = '—'; // — or —
86		// const LDQUO = '“'; // “ or “
87		// const RDQUO = '”'; // ” or ”
88		// const BDQUO = '„'; // &bdquo; or „
89		// const SHY = "\xC2\xAD"; //
90		// const TRADE = '™'; // ™
91		// const REG = '®'; // ®
92		// const COPY = '©'; // ©
93		public const ALL_SPACES = "\xE2\x80\xAF\|\xC2\xAD\|\xC2\xA0\|\\s"; // Used in regexps. Better than \s
94
95		/**
96		* UTF8 first letter in upper case.
97		* "économie" => "Économie".
98		*/
99		public static function mb_ucfirst(string $str, ?string $e = 'UTF-8'): string
100		{
101		$first = mb_strtoupper(mb_substr($str, 0, 1, $e), $e);
102	28	$rest = mb_substr($str, 1, mb_strlen($str, $e), $e);
103
104	28	return $first.$rest;
105	28	}
106
107	28	/**
108		* UTF8 first letter in lower case.
109		* "Économie" => "économie".
110		*
111		* @param string $str
112		* @param string\|null $e
113		*
114		* @return string
115		*/
116		public static function mb_lowerfirst(string $str, ?string $e = 'UTF-8'): string
117		{
118		$first = mb_strtolower(mb_substr($str, 0, 1, $e), $e);
119	1	$rest = mb_substr($str, 1, mb_strlen($str, $e), $e);
120
121	1	return $first.$rest;
122	1	}
123
124	1	public static function replaceNonBreakingSpaces(string $text): string
125		{
126		return str_replace([self::NO_BREAK_SPACE, self::NO_BREAK_THIN_SPACE], ' ', $text);
127		}
128
129		/**
130		* Trim also non-breaking space and carriage return.
131		*/
132	33	public static function trim(string $string): string
133		{
134	33	return trim($string, self::NO_BREAK_SPACE.self::NO_BREAK_THIN_SPACE."\n\t\r");
135		}
136
137		/**
138		* Todo verify/correct.
139		*
140		* @param string $str
141		*
142		* @return bool
143		*/
144	1	// static public function containsNonLatinCharacters(string $str): bool
145		// {
146	1	// return preg_match('/[^\\p{Common}\\p{Latin}]/u', $str);
147		// }
148
149		/**
150		* Simplest levenshtein distance prediction of the correct param name.
151		* Weird results with ASCII extended chars :
152		* levenshtein('notre','nôtre') => 2
153		* TODO move.
154		*
155		* @param string $str
156		* @param array $names
157		* @param int $max Maximum number of permutation/add/subtraction)
158		*
159		* @return string\|null
160		*/
161		public static function predictCorrectParam(string $str, array $names, int $max = 2): ?string
162		{
163		$sanitized = self::sanitizeParamForPredict($str);
164		$closest = null;
165		foreach ($names as $name) {
166		$sanitizedName = self::sanitizeParamForPredict($name);
167		if ($str === $name \|\| $sanitized === $sanitizedName) {
168		return $name; // exact match
169		}
170		$lev = levenshtein($str, $name);
171		$lev2 = levenshtein($sanitized, $sanitizedName);
172
173	3	if (!isset($shortest) \|\| $lev < $shortest \|\| $lev2 < $shortest) {
174		$closest = $name;
175	3	$shortest = $lev;
176	3	}
177	3	}
178	3	if (isset($shortest) && $shortest <= $max && !in_array($sanitized, self::SKIP_PREDICT_PARAM)) {
179	3	return $closest;
180		}
181
182	3	return null;
183	3	}
184
185	3	/**
186	3	* For predictCorrectParam().
187	3	*
188		* @param string $str
189		*
190	3	* @return string
191	3	*/
192		private static function sanitizeParamForPredict(string $str): string
193		{
194		$sanitized = mb_strtolower(self::stripPunctuation(self::stripAccents($str)));
195
196		return trim(preg_replace('#[^a-z0-9 ]#', '', $sanitized));
197		}
198
199		/**
200		* Strip punctuation
201		* UTF-8 compatible ??
202		* Note : can't use str_split() which cut on 1 byte length
203		* See http://fr.wikipedia.org/wiki/Ponctuation.
204	3	*/
205		public static function stripPunctuation(string $str): string
206	3	{
207	3	return str_replace(
208		self::ALL_PUNCTUATION,
209	3	'',
210		$str
211		);
212		}
213
214		/**
215		* Strip accents
216		* OK : grec, cyrillique, macron, hatchek, brève, rond en chef, tilde
217		* UTF-8 compatible.
218		*
219		* @param string $string
220		*
221		* @return string
222	22	*/
223		public static function stripAccents(string $string): string
224	22	{
225	22	return strtr(
226	22	utf8_decode($string),
227	22	utf8_decode(
228		'àáâãäçèéêëìíîïñòóôõöùúûüýÿÀÁÂÃÄÇÈÉÊËÌÍÎÏÑÒÓÔÕÖÙÚÛÜÝøāǟǡēḕḗḡḹīōȫȭȱṑṓǭṝūǖṻȳǣӣᾱῑῡčšžйўŭăӗğÅåůẘẙ'
229		),
230		utf8_decode(
231		'aaaaaceeeeiiiinooooouuuuyyAAAAACEEEEIIIINOOOOOUUUUYoaaaeeeglioooooooruuuyæиαιυcszиyuaegAauwy'
232		)
233		);
234		}
235
236		/**
237		* Like PHP8 str_ends_with(). Multibytes ok.
238		*
239		* @param string $haystack
240	22	* @param string $needle
241		*
242	22	* @return bool
243	22	*/
244	22	public static function str_ends_with(string $haystack, string $needle): bool
245	22	{
246		$len = mb_strlen($needle);
247	22	if ($len === 0) {
248	22	return true;
249		}
250
251		return (mb_substr($haystack, -$len) === $needle);
252		}
253
254		/**
255		* Like PHP8 str_starts_with().
256		*
257		* @param string $haystack
258		* @param string $needle
259		*
260		* @return bool
261		*/
262		public static function str_starts_with(string $haystack, string $needle): bool
263		{
264		$len = mb_strlen($needle);
265
266		return (mb_substr($haystack, 0, $len) === $needle);
267		}
268
269		/**
270		* Cut string at position of last space before Xth character.
271		*/
272		public static function cutTextOnSpace(string $text, int $maxLength = 70): string
273		{
274		if (mb_strlen($text) > $maxLength) {
275		$spacePos = mb_strrpos(mb_substr($text, 0, $maxLength), ' ');
276		$spacePos = ($spacePos > ($maxLength - 12)) ? $spacePos : $maxLength;
277		$text = trim(mb_substr($text, 0, $spacePos)) . self::SYMBOL_TEXT_CUT;
278		}
279
280		return $text;
281		}
282
283		public static function countAllCapsWords(string $text): int
284		{
285		$words = explode(' ', $text);
286		$count = 0;
287		foreach ($words as $word) {
288		if (mb_strlen($word) > 2 && mb_strtoupper($word) === $word) {
289		++$count;
290		}
291		}
292
293		return $count;
294		}
295		}
296

Dispositif / Wikibot

Push — master ( dff8a4...2556d0 )

TextUtil::cutTextOnSpace() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like