ChineseTypesetting::full2Half() - Code Metrics - jxlwqq/chinese-typesetting - Measure and Improve Code Quality continuously with Scrutinizer

ChineseTypesetting::full2Half() A
last analyzed 2018-10-29 15:23 UTC

↳ Parent: ChineseTypesetting

Complexity

Conditions	1
Paths	1

Size

Total Lines	22
Code Lines	19

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	1
eloc	19
nc	1
nop	1
dl	0
loc	22
rs	9.6333
c	0
b	0
f	0

<?php

namespace Jxlwqq\ChineseTypesetting;

/**
 * Class ChineseTypesetting.
 */
class ChineseTypesetting
{
    /**
     * cjk 是中日韩统一表意文字缩写
     * cjk is short for Chinese, Japanese and Korean.
     *
     * @link http://unicode-table.com/en/
     *
     * @var string
     */
    private $cjk = ''.
    '\x{2e80}-\x{2eff}'.
    '\x{2f00}-\x{2fdf}'.
    '\x{3040}-\x{309f}'.
    '\x{30a0}-\x{30ff}'.
    '\x{3100}-\x{312f}'.
    '\x{3200}-\x{32ff}'.
    '\x{3400}-\x{4dbf}'.
    '\x{4e00}-\x{9fff}'.
    '\x{f900}-\x{faff}';

    /**
     * ln 是英文字母、希腊字母（用于数学、科学与工程）和阿拉伯数字的缩写
     * ln is short of alphabetical letters, greek letters and numerical digits and symbols.
     *
     * @link https://en.wikipedia.org/wiki/Greek_letters_used_in_mathematics,_science,_and_engineering
     *
     * @var string
     */
    private $ln = ''.
    'A-Za-z'.
    'Α-Ωα-ω'.
    '0-9';

    /**
     * 保留的全角标点符号.
     *
     * @var string
     */
    private $fullwidthPunctuation = '！？。，；：、“”‘’『』「」〖〗【】《》（）';

    /**
     * 空格
     *
     * @var string
     */
    private $space = '\s|&nbsp;|　';

    /**
     * 使用全部或指定的方法来纠正排版
     * Correct typesetting error.
     *
     * @param string $text
     * @param array  $methods
     *
     * @throws \ReflectionException
     *
     * @return mixed
     */
    public function correct($text, array $methods = [])
    {
        if (empty($methods)) {
            $class = new \ReflectionClass($this);
            $methodsList = $class->getMethods(\ReflectionMethod::IS_PUBLIC);
            foreach ($methodsList as $methodObj) {
                $methods[] = $methodObj->name;
            }
        }

        $methods = array_unique($methods);

        // removeEmptyTag 方法包含了 removeEmptyParagraph 方法的功能，如果这两个函数都存在，则需去除 removeEmptyParagraph 方法
        if (in_array('removeEmptyTag', $methods)) {
            $methods = array_diff($methods, ['removeEmptyParagraph']);
        }

        // insertSpace 方法应该是数组的最后一个元素
        // the method insertSpace should be the end of array
        if (in_array('insertSpace', $methods)) {
            $methods = array_diff($methods, ['insertSpace']);
            array_push($methods, 'insertSpace');
        }

        foreach ($methods as $method) {
            if (__FUNCTION__ == $method || !method_exists($this, $method)) {
                continue;
            }
            $text = $this->$method($text);
        }

        return $text;
    }

    /**
     * 修复错误的标点符号
     * Fix incorrect punctuations.
     *
     * update base on @link https://github.com/ricoa/copywriting-correct/blob/master/src/Correctors/CharacterCorrector.php
     *
     * @param string $text
     *
     * @return null|string|string[]
     */
    public function fixPunctuation($text)
    {
        // 正确使用省略号
        $text = preg_replace('/([。\.]){3,}|(…){1}/iu', '……', $text);
        $text = preg_replace('/(……){2,}/iu', '……', $text);

        // 中文以及中文标点符号）》后使用全角中文标点符号（包括！？。，（）：；）
        $text = preg_replace_callback('/(['.$this->cjk.'）》”])([!?\.,\(\):;])/iu', function ($matches) {
            $replace = [
                '!' => '！',
                '?' => '？',
                '.' => '。',
                ',' => '，',
                '(' => '（',
                ')' => '）',
                ':' => '：',
                ';' => '；',
            ];

            return $matches[1].$replace[$matches[2]];
        }, $text);

        // 不重复使用中文标点符号，重复时只保留第一个
        $text = preg_replace('/(['.$this->fullwidthPunctuation.'])\1{1,}/iu', '\1', $text);

        return $text;
    }

    /**
     * 有限度的全角转半角（英文、数字、空格以及某些特殊字符等使用半角字符）
     * Limited full-width to half-width transformer.
     *
     * @link https://github.com/mzlogin/chinese-copywriting-guidelines#全角和半角
     *
     * @param string $text
     *
     * @return null|string|string[]
     */
    public function full2Half($text)
    {
        $arr = ['０' => '0', '１' => '1', '２' => '2', '３' => '3', '４' => '4',
            '５'     => '5', '６' => '6', '７' => '7', '８' => '8', '９' => '9',
            'Ａ'     => 'A', 'Ｂ' => 'B', 'Ｃ' => 'C', 'Ｄ' => 'D', 'Ｅ' => 'E',
            'Ｆ'     => 'F', 'Ｇ' => 'G', 'Ｈ' => 'H', 'Ｉ' => 'I', 'Ｊ' => 'J',
            'Ｋ'     => 'K', 'Ｌ' => 'L', 'Ｍ' => 'M', 'Ｎ' => 'N', 'Ｏ' => 'O',
            'Ｐ'     => 'P', 'Ｑ' => 'Q', 'Ｒ' => 'R', 'Ｓ' => 'S', 'Ｔ' => 'T',
            'Ｕ'     => 'U', 'Ｖ' => 'V', 'Ｗ' => 'W', 'Ｘ' => 'X', 'Ｙ' => 'Y',
            'Ｚ'     => 'Z', 'ａ' => 'a', 'ｂ' => 'b', 'ｃ' => 'c', 'ｄ' => 'd',
            'ｅ'     => 'e', 'ｆ' => 'f', 'ｇ' => 'g', 'ｈ' => 'h', 'ｉ' => 'i',
            'ｊ'     => 'j', 'ｋ' => 'k', 'ｌ' => 'l', 'ｍ' => 'm', 'ｎ' => 'n',
            'ｏ'     => 'o', 'ｐ' => 'p', 'ｑ' => 'q', 'ｒ' => 'r', 'ｓ' => 's',
            'ｔ'     => 't', 'ｕ' => 'u', 'ｖ' => 'v', 'ｗ' => 'w', 'ｘ' => 'x',
            'ｙ'     => 'y', 'ｚ' => 'z',
            '－'     => '-', '　' => ' ', '／' => '/',
            '％'     => '%', '＃' => '#', '＠' => '@', '＆' => '&', '＜' => '<',
            '＞'     => '>', '［' => '[', '］' => ']', '｛' => '{', '｝' => '}',
            '＼'     => '\\', '｜' => '|', '＋' => '+', '＝' => '=', '＿' => '_',
            '＾'     => '^', '￣' => '~', '｀' => '`', ];

        return strtr($text, $arr);
    }

    /**
     * 在中文与英文字母/用于数学、科学和工程的希腊字母/数字之间添加空格
     * Insert a space between Chinese character and English/Greek/Number character.
     *
     * update base on @link https://github.com/Rakume/pangu.php/blob/master/pangu.php
     *
     * @link https://github.com/mzlogin/chinese-copywriting-guidelines#空格
     *
     * @param string $text
     *
     * @return null|string|string[]
     */
    public function insertSpace($text)
    {
        $patterns = [
            'cjk_quote' => [
                '(['.$this->cjk.'])(["\'])',
                '$1 $2',
            ],
            'quote_cjk' => [
                '(["\'])(['.$this->cjk.'])',
                '$1 $2',
            ],
            'fix_quote' => [
                '(["\']+)(\s*)(.+?)(\s*)(["\']+)',
                '$1$3$5',
            ],
            'cjk_hash' => [
                '(['.$this->cjk.'])(#(\S+))',
                '$1 $2',
            ],
            'hash_cjk' => [
                '((\S+)#)(['.$this->cjk.'])',
                '$1 $3',
            ],
            'cjk_operator_ans' => [
                '(['.$this->cjk.'])(['.$this->ln.'])([\+\-\*\/=&\\|<>])',
                '$1 $2 $3',
            ],
            'ans_operator_cjk' => [
                '([\+\-\*\/=&\\|<>])(['.$this->ln.'])(['.$this->cjk.'])',
                '$1 $2 $3',
            ],
            'bracket' => [
                [
                    '(['.$this->cjk.'])([<\[\{\(]+(.*?)[>\]\}\)]+)(['.$this->cjk.'])',
                    '$1 $2 $4',
                ],
                [
                    'cjk_bracket' => [
                        '(['.$this->cjk.'])([<>\[\]\{\}\(\)])',
                        '$1 $2',
                    ],
                    'bracket_cjk' => [
                        '([<>\[\]\{\}\(\)])(['.$this->cjk.'])',
                        '$1 $2',
                    ],
                ],
            ],
            'fix_bracket' => [
                '([<\[\{\(]+)(\s*)(.+?)(\s*)([>\]\}\)]+)',
                '$1$3$5',
            ],
            'cjk_ans' => [
                '(['.$this->cjk.'])(['.$this->ln.'`@&%\=\$\^\*\-\+\\/|\\\])',
                '$1 $2',
            ],
            'ans_cjk' => [
                '(['.$this->ln.'`~!%&=;\|\,\.\:\?\$\^\*\-\+\/\\\])(['.$this->cjk.'])',
                '$1 $2',
            ],
        ];
        foreach ($patterns as $key => $value) {
            if ($key === 'bracket') {
                $old = $text;
                $new = preg_replace('/'.$value[0][0].'/iu', $value[0][1], $text);
                $text = $new;
                if ($old === $new) {
                    foreach ($value[1] as $val) {
                        $text = preg_replace('/'.$val[0].'/iu', $val[1], $text);
                    }
                }
                continue;
            }
            $text = preg_replace('/'.$value[0].'/iu', $value[1], $text);
        }

        return $text;
    }

    /**
     * 全角标点符号与其他字符之间无需添加空格；.
     *
     * @param string $text
     *
     * @return null|string|string[]
     */
    public function removeSpace($text)
    {
        $patterns = [
            'fullwidth_space' => [
                '(['.$this->fullwidthPunctuation.'])(\s)+',
                '$1',
            ],
            'space_fullwidth' => [
                '(\s)+(['.$this->fullwidthPunctuation.'])',
                '$2',
            ],
        ];

        foreach ($patterns as $key => $value) {
            $text = preg_replace('/'.$value[0].'/u', $value[1], $text);
        }

        return $text;
    }

    /**
     * 专有名词使用正确的大小写
     * Correct English proper nouns.
     *
     * @param string $text
     * @param array  $extend
     * @param array  $ignore
     *
     * @return null|string|string[]
     */
    public function properNoun($text, array $extend = [], array $ignore = [])
    {
        $dict = include __DIR__.'/../data/dict.php';
        if (!empty($extend)) {
            $dict = array_merge($dict, $extend);
        }
        if (!empty($ignore)) {
            $dict = array_diff($dict, $ignore);
        }

        foreach ($dict as $noun) {
            // Matching proper nouns Outside Of Html Tags
            $text = preg_replace("/(?<!\.|[a-z]){$noun}(?!\.|[a-z])(?!([^<]+)?>)/i", $noun, $text);
        }

        return $text;
    }

    /**
     * 清除 Class 属性
     * Remove specific class of HTML tags.
     *
     * @param string $text
     *
     * @return null|string|string[]
     */
    public function removeClass($text)
    {
        return preg_replace('#\s(class)="[^"]+"#', '', $text);
    }

    /**
     * 清除 ID 属性
     * Remove specific id of HTML tags.
     *
     * @param string $text
     *
     * @return null|string|string[]
     */
    public function removeId($text)
    {
        return preg_replace('#\s(id)="[^"]+"#', '', $text);
    }

    /**
     * 清除 Style 属性
     * Remove specific style of HTML tags.
     *
     * @param string $text
     *
     * @return null|string|string[]
     */
    public function removeStyle($text)
    {
        return preg_replace('#\s(style)="[^"]+"#', '', $text);
    }

    /**
     * 清除空段落标签
     * Remove empty Paragraph tags.
     *
     * @param string $text
     * @param bool   $nested
     *
     * @return null|string|string[]
     */
    public function removeEmptyParagraph($text, $nested = true)
    {
        $pattern = '/<p[^>]*>(['.$this->space.']?)<\\/p[^>]*>/';
        if ($nested) {
            while (preg_match($pattern, $text)) {
                $text = preg_replace($pattern, '', $text);
            }
        } else {
            $text = preg_replace($pattern, '', $text);
        }

        return $text;
    }

    /**
     * 清除所有空标签
     * Remote all empty HTML tags.
     *
     * @param string $text
     * @param bool   $nested
     *
     * @return null|string|string[]
     */
    public function removeEmptyTag($text, $nested = true)
    {
        $pattern = '/<[^\/>]*>(['.$this->space.']?)*<\/[^>]*>/';
        if ($nested) {
            while (preg_match($pattern, $text)) {
                $text = preg_replace($pattern, '', $text);
            }
        } else {
            $text = preg_replace($pattern, '', $text);
        }

        return $text;
    }

    /**
     * 清除段首缩进.
     * Remove indent.
     *
     * @param string $text
     *
     * @return null|string|string[]
     */
    public function removeIndent($text)
    {
        return preg_replace('/<p([^>]*)>('.$this->space.')+/', '<p${1}>', $text);
    }
}


1			<?php
2
3			namespace Jxlwqq\ChineseTypesetting;
4
5			/**
6			* Class ChineseTypesetting.
7			*/
8			class ChineseTypesetting
9			{
10			/**
11			* cjk 是中日韩统一表意文字缩写
12			* cjk is short for Chinese, Japanese and Korean.
13			*
14			* @link http://unicode-table.com/en/
15			*
16			* @var string
17			*/
18			private $cjk = ''.
19			'\x{2e80}-\x{2eff}'.
20			'\x{2f00}-\x{2fdf}'.
21			'\x{3040}-\x{309f}'.
22			'\x{30a0}-\x{30ff}'.
23			'\x{3100}-\x{312f}'.
24			'\x{3200}-\x{32ff}'.
25			'\x{3400}-\x{4dbf}'.
26			'\x{4e00}-\x{9fff}'.
27			'\x{f900}-\x{faff}';
28
29			/**
30			* ln 是英文字母、希腊字母（用于数学、科学与工程）和阿拉伯数字的缩写
31			* ln is short of alphabetical letters, greek letters and numerical digits and symbols.
32			*
33			* @link https://en.wikipedia.org/wiki/Greek_letters_used_in_mathematics,_science,_and_engineering
34			*
35			* @var string
36			*/
37			private $ln = ''.
38			'A-Za-z'.
39			'Α-Ωα-ω'.
40			'0-9';
41
42			/**
43			* 保留的全角标点符号.
44			*
45			* @var string
46			*/
47			private $fullwidthPunctuation = '！？。，；：、“”‘’『』「」〖〗【】《》（）';
48
49			/**
50			* 空格
51			*
52			* @var string
53			*/
54			private $space = '\s\| \|　';
55
56			/**
57			* 使用全部或指定的方法来纠正排版
58			* Correct typesetting error.
59			*
60			* @param string $text
61			* @param array $methods
62			*
63			* @throws \ReflectionException
64			*
65			* @return mixed
66			*/
67			public function correct($text, array $methods = [])
68			{
69			if (empty($methods)) {
70			$class = new \ReflectionClass($this);
71			$methodsList = $class->getMethods(\ReflectionMethod::IS_PUBLIC);
72			foreach ($methodsList as $methodObj) {
73			$methods[] = $methodObj->name;
74			}
75			}
76
77			$methods = array_unique($methods);
78
79			// removeEmptyTag 方法包含了 removeEmptyParagraph 方法的功能，如果这两个函数都存在，则需去除 removeEmptyParagraph 方法
80			if (in_array('removeEmptyTag', $methods)) {
81			$methods = array_diff($methods, ['removeEmptyParagraph']);
82			}
83
84			// insertSpace 方法应该是数组的最后一个元素
85			// the method insertSpace should be the end of array
86			if (in_array('insertSpace', $methods)) {
87			$methods = array_diff($methods, ['insertSpace']);
88			array_push($methods, 'insertSpace');
89			}
90
91			foreach ($methods as $method) {
92			if (__FUNCTION__ == $method \|\| !method_exists($this, $method)) {
93			continue;
94			}
95			$text = $this->$method($text);
96			}
97
98			return $text;
99			}
100
101			/**
102			* 修复错误的标点符号
103			* Fix incorrect punctuations.
104			*
105			* update base on @link https://github.com/ricoa/copywriting-correct/blob/master/src/Correctors/CharacterCorrector.php
106			*
107			* @param string $text
108			*
109			* @return null\|string\|string[]
110			*/
111			public function fixPunctuation($text)
112			{
113			// 正确使用省略号
114			$text = preg_replace('/([。\.]){3,}\|(…){1}/iu', '……', $text);
115			$text = preg_replace('/(……){2,}/iu', '……', $text);
116
117			// 中文以及中文标点符号）》后使用全角中文标点符号（包括！？。，（）：；）
118			$text = preg_replace_callback('/(['.$this->cjk.'）》”])([!?\.,\(\):;])/iu', function ($matches) {
119			$replace = [
120			'!' => '！',
121			'?' => '？',
122			'.' => '。',
123			',' => '，',
124			'(' => '（',
125			')' => '）',
126			':' => '：',
127			';' => '；',
128			];
129
130			return $matches[1].$replace[$matches[2]];
131			}, $text);
132
133			// 不重复使用中文标点符号，重复时只保留第一个
134			$text = preg_replace('/(['.$this->fullwidthPunctuation.'])\1{1,}/iu', '\1', $text);
135
136			return $text;
137			}
138
139			/**
140			* 有限度的全角转半角（英文、数字、空格以及某些特殊字符等使用半角字符）
141			* Limited full-width to half-width transformer.
142			*
143			* @link https://github.com/mzlogin/chinese-copywriting-guidelines#全角和半角
144			*
145			* @param string $text
146			*
147			* @return null\|string\|string[]
148			*/
149			public function full2Half($text)
150			{
151			$arr = ['０' => '0', '１' => '1', '２' => '2', '３' => '3', '４' => '4',
152			'５' => '5', '６' => '6', '７' => '7', '８' => '8', '９' => '9',
153			'Ａ' => 'A', 'Ｂ' => 'B', 'Ｃ' => 'C', 'Ｄ' => 'D', 'Ｅ' => 'E',
154			'Ｆ' => 'F', 'Ｇ' => 'G', 'Ｈ' => 'H', 'Ｉ' => 'I', 'Ｊ' => 'J',
155			'Ｋ' => 'K', 'Ｌ' => 'L', 'Ｍ' => 'M', 'Ｎ' => 'N', 'Ｏ' => 'O',
156			'Ｐ' => 'P', 'Ｑ' => 'Q', 'Ｒ' => 'R', 'Ｓ' => 'S', 'Ｔ' => 'T',
157			'Ｕ' => 'U', 'Ｖ' => 'V', 'Ｗ' => 'W', 'Ｘ' => 'X', 'Ｙ' => 'Y',
158			'Ｚ' => 'Z', 'ａ' => 'a', 'ｂ' => 'b', 'ｃ' => 'c', 'ｄ' => 'd',
159			'ｅ' => 'e', 'ｆ' => 'f', 'ｇ' => 'g', 'ｈ' => 'h', 'ｉ' => 'i',
160			'ｊ' => 'j', 'ｋ' => 'k', 'ｌ' => 'l', 'ｍ' => 'm', 'ｎ' => 'n',
161			'ｏ' => 'o', 'ｐ' => 'p', 'ｑ' => 'q', 'ｒ' => 'r', 'ｓ' => 's',
162			'ｔ' => 't', 'ｕ' => 'u', 'ｖ' => 'v', 'ｗ' => 'w', 'ｘ' => 'x',
163			'ｙ' => 'y', 'ｚ' => 'z',
164			'－' => '-', '　' => ' ', '／' => '/',
165			'％' => '%', '＃' => '#', '＠' => '@', '＆' => '&', '＜' => '<',
166			'＞' => '>', '［' => '[', '］' => ']', '｛' => '{', '｝' => '}',
167			'＼' => '\\', '｜' => '\|', '＋' => '+', '＝' => '=', '＿' => '_',
168			'＾' => '^', '￣' => '~', '｀' => '`', ];
169
170			return strtr($text, $arr);
171			}
172
173			/**
174			* 在中文与英文字母/用于数学、科学和工程的希腊字母/数字之间添加空格
175			* Insert a space between Chinese character and English/Greek/Number character.
176			*
177			* update base on @link https://github.com/Rakume/pangu.php/blob/master/pangu.php
178			*
179			* @link https://github.com/mzlogin/chinese-copywriting-guidelines#空格
180			*
181			* @param string $text
182			*
183			* @return null\|string\|string[]
184			*/
185			public function insertSpace($text)
186			{
187			$patterns = [
188			'cjk_quote' => [
189			'(['.$this->cjk.'])(["\'])',
190			'$1 $2',
191			],
192			'quote_cjk' => [
193			'(["\'])(['.$this->cjk.'])',
194			'$1 $2',
195			],
196			'fix_quote' => [
197			'(["\']+)(\s)(.+?)(\s)(["\']+)',
198			'$1$3$5',
199			],
200			'cjk_hash' => [
201			'(['.$this->cjk.'])(#(\S+))',
202			'$1 $2',
203			],
204			'hash_cjk' => [
205			'((\S+)#)(['.$this->cjk.'])',
206			'$1 $3',
207			],
208			'cjk_operator_ans' => [
209			'(['.$this->cjk.'])(['.$this->ln.'])([\+\-\*\/=&\\\|<>])',
210			'$1 $2 $3',
211			],
212			'ans_operator_cjk' => [
213			'([\+\-\*\/=&\\\|<>])(['.$this->ln.'])(['.$this->cjk.'])',
214			'$1 $2 $3',
215			],
216			'bracket' => [
217			[
218			'(['.$this->cjk.'])([<\[\{\(]+(.*?)[>\]\}\)]+)(['.$this->cjk.'])',
219			'$1 $2 $4',
220			],
221			[
222			'cjk_bracket' => [
223			'(['.$this->cjk.'])([<>\[\]\{\}\(\)])',
224			'$1 $2',
225			],
226			'bracket_cjk' => [
227			'([<>\[\]\{\}\(\)])(['.$this->cjk.'])',
228			'$1 $2',
229			],
230			],
231			],
232			'fix_bracket' => [
233			'([<\[\{\(]+)(\s)(.+?)(\s)([>\]\}\)]+)',
234			'$1$3$5',
235			],
236			'cjk_ans' => [
237			'(['.$this->cjk.'])(['.$this->ln.'`@&%\=\$\^\*\-\+\\/\|\\\])',
238			'$1 $2',
239			],
240			'ans_cjk' => [
241			'(['.$this->ln.'`~!%&=;\\|\,\.\:\?\$\^\*\-\+\/\\\])(['.$this->cjk.'])',
242			'$1 $2',
243			],
244			];
245			foreach ($patterns as $key => $value) {
246			if ($key === 'bracket') {
247			$old = $text;
248			$new = preg_replace('/'.$value[0][0].'/iu', $value[0][1], $text);
249			$text = $new;
250			if ($old === $new) {
251			foreach ($value[1] as $val) {
252			$text = preg_replace('/'.$val[0].'/iu', $val[1], $text);
253			}
254			}
255			continue;
256			}
257			$text = preg_replace('/'.$value[0].'/iu', $value[1], $text);
258			}
259
260			return $text;
261			}
262
263			/**
264			* 全角标点符号与其他字符之间无需添加空格；.
265			*
266			* @param string $text
267			*
268			* @return null\|string\|string[]
269			*/
270			public function removeSpace($text)
271			{
272			$patterns = [
273			'fullwidth_space' => [
274			'(['.$this->fullwidthPunctuation.'])(\s)+',
275			'$1',
276			],
277			'space_fullwidth' => [
278			'(\s)+(['.$this->fullwidthPunctuation.'])',
279			'$2',
280			],
281			];
282
283			foreach ($patterns as $key => $value) {
284			$text = preg_replace('/'.$value[0].'/u', $value[1], $text);
285			}
286
287			return $text;
288			}
289
290			/**
291			* 专有名词使用正确的大小写
292			* Correct English proper nouns.
293			*
294			* @param string $text
295			* @param array $extend
296			* @param array $ignore
297			*
298			* @return null\|string\|string[]
299			*/
300			public function properNoun($text, array $extend = [], array $ignore = [])
301			{
302			$dict = include __DIR__.'/../data/dict.php';
303			if (!empty($extend)) {
304			$dict = array_merge($dict, $extend);
305			}
306			if (!empty($ignore)) {
307			$dict = array_diff($dict, $ignore);
308			}
309
310			foreach ($dict as $noun) {
311			// Matching proper nouns Outside Of Html Tags
312			$text = preg_replace("/(?<!\.\|[a-z]){$noun}(?!\.\|[a-z])(?!([^<]+)?>)/i", $noun, $text);
313			}
314
315			return $text;
316			}
317
318			/**
319			* 清除 Class 属性
320			* Remove specific class of HTML tags.
321			*
322			* @param string $text
323			*
324			* @return null\|string\|string[]
325			*/
326			public function removeClass($text)
327			{
328			return preg_replace('#\s(class)="[^"]+"#', '', $text);
329			}
330
331			/**
332			* 清除 ID 属性
333			* Remove specific id of HTML tags.
334			*
335			* @param string $text
336			*
337			* @return null\|string\|string[]
338			*/
339			public function removeId($text)
340			{
341			return preg_replace('#\s(id)="[^"]+"#', '', $text);
342			}
343
344			/**
345			* 清除 Style 属性
346			* Remove specific style of HTML tags.
347			*
348			* @param string $text
349			*
350			* @return null\|string\|string[]
351			*/
352			public function removeStyle($text)
353			{
354			return preg_replace('#\s(style)="[^"]+"#', '', $text);
355			}
356
357			/**
358			* 清除空段落标签
359			* Remove empty Paragraph tags.
360			*
361			* @param string $text
362			* @param bool $nested
363			*
364			* @return null\|string\|string[]
365			*/
366			public function removeEmptyParagraph($text, $nested = true)
367			{
368			$pattern = '/<p[^>]>(['.$this->space.']?)<\\/p[^>]>/';
369			if ($nested) {
370			while (preg_match($pattern, $text)) {
371			$text = preg_replace($pattern, '', $text);
372			}
373			} else {
374			$text = preg_replace($pattern, '', $text);
375			}
376
377			return $text;
378			}
379
380			/**
381			* 清除所有空标签
382			* Remote all empty HTML tags.
383			*
384			* @param string $text
385			* @param bool $nested
386			*
387			* @return null\|string\|string[]
388			*/
389			public function removeEmptyTag($text, $nested = true)
390			{
391			$pattern = '/<[^\/>]>(['.$this->space.']?)<\/[^>]*>/';
392			if ($nested) {
393			while (preg_match($pattern, $text)) {
394			$text = preg_replace($pattern, '', $text);
395			}
396			} else {
397			$text = preg_replace($pattern, '', $text);
398			}
399
400			return $text;
401			}
402
403			/**
404			* 清除段首缩进.
405			* Remove indent.
406			*
407			* @param string $text
408			*
409			* @return null\|string\|string[]
410			*/
411			public function removeIndent($text)
412			{
413			return preg_replace('/<p([^>]*)>('.$this->space.')+/', '<p${1}>', $text);
414			}
415			}
416

jxlwqq / chinese-typesetting

ChineseTypesetting::full2Half() A last analyzed 2018-10-29 15:23 UTC

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

ChineseTypesetting::full2Half() A
last analyzed 2018-10-29 15:23 UTC