16790351274

Committed 06 Aug 2025 10:42PM UTC coverage: 92.746% (+0.005%) from 92.741%

Build Type

push

github

Committed by

Commit Message

HtmlElement: removed toHtml() & toText()

Run Details

18 of 19 new or added lines in 5 files covered. (94.74%)

136 existing lines in 23 files now uncovered.

2391 of 2578 relevant lines covered (92.75%)

0.93 hits per line

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

96.43

/src/Texy/Modules/LongWordsModule.php

<?php

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

declare(strict_types=1);

namespace Texy\Modules;

use Texy;
use function array_flip, array_pop, array_splice, count, end, iconv_strlen, implode, ord, preg_match_all;


/**
 * Long words wrap module.
 */
final class LongWordsModule extends Texy\Module
{
        private const
                Dont = 0, // don't hyphenate
                Here = 1, // hyphenate here
                After = 2; // hyphenate after

        private const SafeLimit = 1000;

        public int $wordLimit = 20;

        private array $consonants = [
                'b', 'c', 'd', 'f', 'g', 'h', 'j', 'k', 'l', 'm', 'n', 'p', 'q', 'r', 's', 't', 'v', 'w', 'x', 'z',
                'B', 'C', 'D', 'F', 'G', 'H', 'J', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'V', 'W', 'X', 'Z',
                "\u{10D}", "\u{10F}", "\u{148}", "\u{159}", "\u{161}", "\u{165}", "\u{17E}", // Czech UTF-8
                "\u{10C}", "\u{10E}", "\u{147}", "\u{158}", "\u{160}", "\u{164}", "\u{17D}",
        ];

        private array $vowels = [
                'a', 'e', 'i', 'o', 'u', 'y',
                'A', 'E', 'I', 'O', 'U', 'Y',
                "\u{E1}", "\u{E9}", "\u{11B}", "\u{ED}", "\u{F3}", "\u{FA}", "\u{16F}", "\u{FD}", // Czech UTF-8
                "\u{C1}", "\u{C9}", "\u{11A}", "\u{CD}", "\u{D3}", "\u{DA}", "\u{16E}", "\u{DD}",
        ];

        private array $before_r = [
                'b', 'B', 'c', 'C', 'd', 'D', 'f', 'F', 'g', 'G', 'k', 'K', 'p', 'P', 'r', 'R', 't', 'T', 'v', 'V',
                "\u{10D}", "\u{10C}", "\u{10F}", "\u{10E}", "\u{159}", "\u{158}", "\u{165}", "\u{164}", // Czech UTF-8
        ];

        private array $before_l = [
                'b', 'B', 'c', 'C', 'd', 'D', 'f', 'F', 'g', 'G', 'k', 'K', 'l', 'L', 'p', 'P', 't', 'T', 'v', 'V',
                "\u{10D}", "\u{10C}", "\u{10F}", "\u{10E}", "\u{165}", "\u{164}", // Czech UTF-8
        ];

        private array $before_h = ['c', 'C', 's', 'S'];

        private array $doubleVowels = ['a', 'A', 'o', 'O'];


        public function __construct(Texy\Texy $texy)
        {
                $this->texy = $texy;

                $this->consonants = array_flip($this->consonants);
                $this->vowels = array_flip($this->vowels);
                $this->before_r = array_flip($this->before_r);
                $this->before_l = array_flip($this->before_l);
                $this->before_h = array_flip($this->before_h);
                $this->doubleVowels = array_flip($this->doubleVowels);

                $texy->registerPostLine($this->postLine(...), 'longwords');
        }


        public function postLine(string $text): string
        {
                return Texy\Regexp::replace(
                        $text,
                        '~[^ \n\t\x14\x15\x16\x{2013}\x{2014}\x{ad}-]{' . $this->wordLimit . ',}~',
                        $this->parse(...),
                );
        }


        /**
         * Callback for long words.
         */
        private function parse(array $matches): string
        {
                [$mWord] = $matches;
                // [0] => lllloooonnnnggggwwwoorrdddd

                if (iconv_strlen($mWord, 'UTF-8') > self::SafeLimit) {
                        return $mWord;
                }

                $chars = Texy\Regexp::matchAll(
                        $mWord,
                        '~[' . Texy\Patterns::MARK . ']+|.~',
                );

                $chars = array_column($chars, 0);
                if (count($chars) < $this->wordLimit) {
                        return $mWord;
                }

                $s = [''];
                $trans = [-1];
                foreach ($chars as $key => $char) {
                        if (ord($char[0]) < 32) {
                                continue;
                        }

                        $s[] = $char;
                        $trans[] = $key;
                }

                $s[] = '';
                $len = count($s) - 2;

                $positions = [];
                $a = 0;
                $last = 1;

                while (++$a < $len) {
                        if ($s[$a] === "\u{A0}") {
                                $a++;
                                continue;  // here and after never
                        }

                        $hyphen = $this->getHyphen($s[$a], $s[$a - 1], $s[$a + 1]);

                        if ($hyphen === self::Dont && ($a - $last > $this->wordLimit * 0.6)) {
                                $positions[] = $last = $a - 1; // Hyphenate here
                        }

                        if ($hyphen === self::Here) {
                                $positions[] = $last = $a - 1; // Hyphenate here
                        }

                        if ($hyphen === self::After) {
                                $positions[] = $last = $a;
                                $a++; // Hyphenate after
                        }
                }

                $a = end($positions);
                if (($a === $len - 1) && isset($this->consonants[$s[$len]])) {
                        array_pop($positions);
                }

                $syllables = [];
                $last = 0;
                foreach ($positions as $pos) {
                        if ($pos - $last > $this->wordLimit * 0.6) {
                                $syllables[] = implode('', array_splice($chars, 0, $trans[$pos] - $trans[$last]));
                                $last = $pos;
                        }
                }

                $syllables[] = implode('', $chars);
                return implode("\u{AD}", $syllables);
        }


        private function getHyphen(string $ch, string $prev, string $next): int
        {
                if ($ch === '.') {
                        return self::Here;

                } elseif (isset($this->consonants[$ch])) { // consonants
                        if (isset($this->vowels[$next])) {
                                return isset($this->vowels[$prev]) ? self::Here : self::Dont;

                        } elseif (($ch === 's') && ($prev === 'n') && isset($this->consonants[$next])) {
                                return self::After;

                        } elseif (isset($this->consonants[$next], $this->vowels[$prev])) {
                                if ($next === 'r') {
                                        return isset($this->before_r[$ch]) ? self::Here : self::After;

                                } elseif ($next === 'l') {
                                        return isset($this->before_l[$ch]) ? self::Here : self::After;

                                } elseif ($next === 'h') { // CH
                                        return isset($this->before_h[$ch])
                                                ? self::Dont
                                                : self::After;
                                }

                                return self::After;
                        }

                        return self::Dont;

                } elseif (($ch === 'u') && isset($this->doubleVowels[$prev])) {
                        return self::After;

                } elseif (isset($this->vowels[$ch], $this->vowels[$prev])) {
                        return self::Here;
                }

                return self::Dont; // Do not hyphenate
        }
}

1	<?php
2
3	/**
4	* This file is part of the Texy! (https://texy.info)
5	* Copyright (c) 2004 David Grudl (https://davidgrudl.com)
6	*/
7
8	declare(strict_types=1);
9
10	namespace Texy\Modules;
11
12	use Texy;
13	use function array_flip, array_pop, array_splice, count, end, iconv_strlen, implode, ord, preg_match_all;
14
15
16	/**
17	* Long words wrap module.
18	*/
19	final class LongWordsModule extends Texy\Module
20	{
21	private const
22	Dont = 0, // don't hyphenate
23	Here = 1, // hyphenate here
24	After = 2; // hyphenate after
25
26	private const SafeLimit = 1000;
27
28	public int $wordLimit = 20;
29
30	private array $consonants = [
31	'b', 'c', 'd', 'f', 'g', 'h', 'j', 'k', 'l', 'm', 'n', 'p', 'q', 'r', 's', 't', 'v', 'w', 'x', 'z',
32	'B', 'C', 'D', 'F', 'G', 'H', 'J', 'K', 'L', 'M', 'N', 'P', 'Q', 'R', 'S', 'T', 'V', 'W', 'X', 'Z',
33	"\u{10D}", "\u{10F}", "\u{148}", "\u{159}", "\u{161}", "\u{165}", "\u{17E}", // Czech UTF-8
34	"\u{10C}", "\u{10E}", "\u{147}", "\u{158}", "\u{160}", "\u{164}", "\u{17D}",
35	];
36
37	private array $vowels = [
38	'a', 'e', 'i', 'o', 'u', 'y',
39	'A', 'E', 'I', 'O', 'U', 'Y',
40	"\u{E1}", "\u{E9}", "\u{11B}", "\u{ED}", "\u{F3}", "\u{FA}", "\u{16F}", "\u{FD}", // Czech UTF-8
41	"\u{C1}", "\u{C9}", "\u{11A}", "\u{CD}", "\u{D3}", "\u{DA}", "\u{16E}", "\u{DD}",
42	];
43
44	private array $before_r = [
45	'b', 'B', 'c', 'C', 'd', 'D', 'f', 'F', 'g', 'G', 'k', 'K', 'p', 'P', 'r', 'R', 't', 'T', 'v', 'V',
46	"\u{10D}", "\u{10C}", "\u{10F}", "\u{10E}", "\u{159}", "\u{158}", "\u{165}", "\u{164}", // Czech UTF-8
47	];
48
49	private array $before_l = [
50	'b', 'B', 'c', 'C', 'd', 'D', 'f', 'F', 'g', 'G', 'k', 'K', 'l', 'L', 'p', 'P', 't', 'T', 'v', 'V',
51	"\u{10D}", "\u{10C}", "\u{10F}", "\u{10E}", "\u{165}", "\u{164}", // Czech UTF-8
52	];
53
54	private array $before_h = ['c', 'C', 's', 'S'];
55
56	private array $doubleVowels = ['a', 'A', 'o', 'O'];
57
58
59	public function __construct(Texy\Texy $texy)	1✔
60	{
61	$this->texy = $texy;	1✔
62
63	$this->consonants = array_flip($this->consonants);	1✔
64	$this->vowels = array_flip($this->vowels);	1✔
65	$this->before_r = array_flip($this->before_r);	1✔
66	$this->before_l = array_flip($this->before_l);	1✔
67	$this->before_h = array_flip($this->before_h);	1✔
68	$this->doubleVowels = array_flip($this->doubleVowels);	1✔
69
70	$texy->registerPostLine($this->postLine(...), 'longwords');	1✔
71	}	1✔
72
73
74	public function postLine(string $text): string	1✔
75	{
76	return Texy\Regexp::replace(	1✔
77	$text,	1✔
78	'~[^ \n\t\x14\x15\x16\x{2013}\x{2014}\x{ad}-]{' . $this->wordLimit . ',}~',	1✔
79	$this->parse(...),	1✔
80	);
81	}
82
83
84	/**
85	* Callback for long words.
86	*/
87	private function parse(array $matches): string	1✔
88	{
89	[$mWord] = $matches;	1✔
90	// [0] => lllloooonnnnggggwwwoorrdddd
91
92	if (iconv_strlen($mWord, 'UTF-8') > self::SafeLimit) {	1✔
93	return $mWord;	1✔
94	}
95
96	$chars = Texy\Regexp::matchAll(	1✔
97	$mWord,	1✔
98	'~[' . Texy\Patterns::MARK . ']+\|.~',	1✔
99	);
100
101	$chars = array_column($chars, 0);	1✔
102	if (count($chars) < $this->wordLimit) {	1✔
103	return $mWord;	1✔
104	}
105
106	$s = [''];	1✔
107	$trans = [-1];	1✔
108	foreach ($chars as $key => $char) {	1✔
109	if (ord($char[0]) < 32) {	1✔
110	continue;	1✔
111	}
112
113	$s[] = $char;	1✔
114	$trans[] = $key;	1✔
115	}
116
117	$s[] = '';	1✔
118	$len = count($s) - 2;	1✔
119
120	$positions = [];	1✔
121	$a = 0;	1✔
122	$last = 1;	1✔
123
124	while (++$a < $len) {	1✔
125	if ($s[$a] === "\u{A0}") {	1✔
126	$a++;	×
UNCOV 127	continue; // here and after never	×
128	}
129
130	$hyphen = $this->getHyphen($s[$a], $s[$a - 1], $s[$a + 1]);	1✔
131
132	if ($hyphen === self::Dont && ($a - $last > $this->wordLimit * 0.6)) {	1✔
133	$positions[] = $last = $a - 1; // Hyphenate here	1✔
134	}
135
136	if ($hyphen === self::Here) {	1✔
137	$positions[] = $last = $a - 1; // Hyphenate here	1✔
138	}
139
140	if ($hyphen === self::After) {	1✔
141	$positions[] = $last = $a;	1✔
142	$a++; // Hyphenate after	1✔
143	}
144	}
145
146	$a = end($positions);	1✔
147	if (($a === $len - 1) && isset($this->consonants[$s[$len]])) {	1✔
148	array_pop($positions);	1✔
149	}
150
151	$syllables = [];	1✔
152	$last = 0;	1✔
153	foreach ($positions as $pos) {	1✔
154	if ($pos - $last > $this->wordLimit * 0.6) {	1✔
155	$syllables[] = implode('', array_splice($chars, 0, $trans[$pos] - $trans[$last]));	1✔
156	$last = $pos;	1✔
157	}
158	}
159
160	$syllables[] = implode('', $chars);	1✔
161	return implode("\u{AD}", $syllables);	1✔
162	}
163
164
165	private function getHyphen(string $ch, string $prev, string $next): int	1✔
166	{
167	if ($ch === '.') {	1✔
168	return self::Here;	1✔
169
170	} elseif (isset($this->consonants[$ch])) { // consonants	1✔
171	if (isset($this->vowels[$next])) {	1✔
172	return isset($this->vowels[$prev]) ? self::Here : self::Dont;	1✔
173
174	} elseif (($ch === 's') && ($prev === 'n') && isset($this->consonants[$next])) {	1✔
UNCOV 175	return self::After;	×
176
177	} elseif (isset($this->consonants[$next], $this->vowels[$prev])) {	1✔
178	if ($next === 'r') {	1✔
179	return isset($this->before_r[$ch]) ? self::Here : self::After;	1✔
180
181	} elseif ($next === 'l') {	1✔
182	return isset($this->before_l[$ch]) ? self::Here : self::After;	1✔
183
184	} elseif ($next === 'h') { // CH	1✔
185	return isset($this->before_h[$ch])	1✔
186	? self::Dont	1✔
187	: self::After;	1✔
188	}
189
190	return self::After;	1✔
191	}
192
193	return self::Dont;	1✔
194
195	} elseif (($ch === 'u') && isset($this->doubleVowels[$prev])) {	1✔
196	return self::After;	1✔
197
198	} elseif (isset($this->vowels[$ch], $this->vowels[$prev])) {	1✔
199	return self::Here;	1✔
200	}
201
202	return self::Dont; // Do not hyphenate	1✔
203	}
204	}

dg / texy / 16790351274

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