ChineseTypesetting::fixPunctuation() - Code Metrics - Inspection of "新增 removeSpace 方法" - jxlwqq/chinese-typesetting - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( 6e7810...23e828 )

by jxlwqq

created 2018-08-26 03:01 UTC

ChineseTypesetting::fixPunctuation() A

↳ Parent: ChineseTypesetting

Complexity

Conditions	1
Paths	1

Size

Total Lines	26
Code Lines	16

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	1
eloc	16
nc	1
nop	1
dl	0
loc	26
rs	9.7333
c	0
b	0
f	0

<?php
/**
 * Created by PhpStorm.
 * User: jxlwqq
 * Date: 2018/7/26
 * Time: 09:33.
 */

namespace Jxlwqq\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 $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 $text
     *
     * @return null|string|string[]
     */
    public function fixPunctuation($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 $text
     *
     * @return null|string|string[]
     */
    public function full2Half($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 $text
     *
     * @return null|string|string[]
     */
    public function insertSpace($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 $text
     *
     * @return null|string|string[]
     */
    public function removeSpace($text)
    {
        $patterns = [
            'fullwidth_space' => [
                '(['.$this->fullwidthPunctuation.'])(['.$this->space.'])',
                '$1'
            ],
            'space_fullwidth' => [
                '(['.$this->space.'])(['.$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 $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 $text
     *
     * @return null|string|string[]
     */
    public function removeClass($text)
    {
        return preg_replace('#\s(class)="[^"]+"#', '', $text);
    }

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

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

    /**
     * 清除空段落标签
     * Remove empty Paragraph tags.
     *
     * @param $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 $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 $text
     *
     * @return null|string|string[]
     */
    public function removeIndent($text)
    {
        return preg_replace('/<p([^>]*)>('.$this->space.')+/', '<p${1}>', $text);
    }
}


1			<?php
2			/**
3			* Created by PhpStorm.
4			* User: jxlwqq
5			* Date: 2018/7/26
6			* Time: 09:33.
7			*/
8
9			namespace Jxlwqq\ChineseTypesetting;
10
11			class ChineseTypesetting
12			{
13			/**
14			* cjk 是中日韩统一表意文字缩写
15			* cjk is short for Chinese, Japanese and Korean.
16			*
17			* @link http://unicode-table.com/en/
18			*
19			* @var string
20			*/
21			private $cjk = ''.
22			'\x{2e80}-\x{2eff}'.
23			'\x{2f00}-\x{2fdf}'.
24			'\x{3040}-\x{309f}'.
25			'\x{30a0}-\x{30ff}'.
26			'\x{3100}-\x{312f}'.
27			'\x{3200}-\x{32ff}'.
28			'\x{3400}-\x{4dbf}'.
29			'\x{4e00}-\x{9fff}'.
30			'\x{f900}-\x{faff}';
31
32			/**
33			* 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
34			* ln is short of alphabetical letters, greek letters and numerical digits and symbols.
35			*
36			* @link https://en.wikipedia.org/wiki/Greek_letters_used_in_mathematics,_science,_and_engineering
37			*
38			* @var string
39			*/
40			private $ln = ''.
41			'A-Za-z'.
42			'Α-Ωα-ω'.
43			'0-9';
44
45			/**
46			* 保留的全角标点符号
47			*
48			* @var string
49			*/
50			private $fullwidthPunctuation = '！？。，；：、“”‘’『』「」〖〗【】《》（）';
51
52			/**
53			* 空格
54			*
55			* @var string
56			*/
57			private $space = '\s\| \|　';
58
59			/**
60			* 使用全部或指定的方法来纠正排版
61			* Correct typesetting error.
62			*
63			* @param $text
64			* @param array $methods
65			*
66			* @throws \ReflectionException
67			*
68			* @return mixed
69			*/
70			public function correct($text, array $methods = [])
71			{
72			if (empty($methods)) {
73			$class = new \ReflectionClass($this);
74			$methodsList = $class->getMethods(\ReflectionMethod::IS_PUBLIC);
75			foreach ($methodsList as $methodObj) {
76			$methods[] = $methodObj->name;
77			}
78			}
79
80			$methods = array_unique($methods);
81
82			// 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
83			if (in_array('removeEmptyTag', $methods)) {
84			$methods = array_diff($methods, ['removeEmptyParagraph']);
85			}
86
87			// insertSpace 方法应该是数组的最后一个元素
88			// the method insertSpace should be the end of array
89			if (in_array('insertSpace', $methods)) {
90			$methods = array_diff($methods, ['insertSpace']);
91			array_push($methods, 'insertSpace');
92			}
93
94			foreach ($methods as $method) {
95			if (__FUNCTION__ == $method \|\| !method_exists($this, $method)) {
96			continue;
97			}
98			$text = $this->$method($text);
99			}
100
101			return $text;
102			}
103
104			/**
105			* 修复错误的标点符号
106			* Fix incorrect punctuations.
107			*
108			* update base on @link https://github.com/ricoa/copywriting-correct/blob/master/src/Correctors/CharacterCorrector.php
109			*
110			* @param $text
111			*
112			* @return null\|string\|string[]
113			*/
114			public function fixPunctuation($text)
115			{
116			// 正确使用省略号
117			$text = preg_replace('/([。\.]){3,}\|(…){1}/iu', '……', $text);
118			$text = preg_replace('/(……){2,}/iu', '……', $text);
119
120			// 中文以及中文标点符号）》后使用全角中文标点符号（包括！？。，（）：；）
121			$text = preg_replace_callback('/(['.$this->cjk.'）》”])([!?\.,\(\):;])/iu', function ($matches) {
122			$replace = [
123			'!' => '！',
124			'?' => '？',
125			'.' => '。',
126			',' => '，',
127			'(' => '（',
128			')' => '）',
129			':' => '：',
130			';' => '；',
131			];
132
133			return $matches[1].$replace[$matches[2]];
134			}, $text);
135
136			// 不重复使用中文标点符号，重复时只保留第一个
137			$text = preg_replace('/(['.$this->fullwidthPunctuation.'])\1{1,}/iu', '\1', $text);
138
139			return $text;
140			}
141
142			/**
143			* 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）
144			* Limited full-width to half-width transformer.
145			*
146			* @link https://github.com/mzlogin/chinese-copywriting-guidelines#全角和半角
147			*
148			* @param $text
149			*
150			* @return null\|string\|string[]
151			*/
152			public function full2Half($text)
153			{
154			$arr = ['０' => '0', '１' => '1', '２' => '2', '３' => '3', '４' => '4',
155			'５' => '5', '６' => '6', '７' => '7', '８' => '8', '９' => '9',
156			'Ａ' => 'A', 'Ｂ' => 'B', 'Ｃ' => 'C', 'Ｄ' => 'D', 'Ｅ' => 'E',
157			'Ｆ' => 'F', 'Ｇ' => 'G', 'Ｈ' => 'H', 'Ｉ' => 'I', 'Ｊ' => 'J',
158			'Ｋ' => 'K', 'Ｌ' => 'L', 'Ｍ' => 'M', 'Ｎ' => 'N', 'Ｏ' => 'O',
159			'Ｐ' => 'P', 'Ｑ' => 'Q', 'Ｒ' => 'R', 'Ｓ' => 'S', 'Ｔ' => 'T',
160			'Ｕ' => 'U', 'Ｖ' => 'V', 'Ｗ' => 'W', 'Ｘ' => 'X', 'Ｙ' => 'Y',
161			'Ｚ' => 'Z', 'ａ' => 'a', 'ｂ' => 'b', 'ｃ' => 'c', 'ｄ' => 'd',
162			'ｅ' => 'e', 'ｆ' => 'f', 'ｇ' => 'g', 'ｈ' => 'h', 'ｉ' => 'i',
163			'ｊ' => 'j', 'ｋ' => 'k', 'ｌ' => 'l', 'ｍ' => 'm', 'ｎ' => 'n',
164			'ｏ' => 'o', 'ｐ' => 'p', 'ｑ' => 'q', 'ｒ' => 'r', 'ｓ' => 's',
165			'ｔ' => 't', 'ｕ' => 'u', 'ｖ' => 'v', 'ｗ' => 'w', 'ｘ' => 'x',
166			'ｙ' => 'y', 'ｚ' => 'z',
167			'－' => '-', '　' => ' ', '／' => '/',
168			'％' => '%', '＃' => '#', '＠' => '@', '＆' => '&', '＜' => '<',
169			'＞' => '>', '［' => '[', '］' => ']', '｛' => '{', '｝' => '}',
170			'＼' => '\\', '｜' => '\|', '＋' => '+', '＝' => '=', '＿' => '_',
171			'＾' => '^', '￣' => '~', '｀' => '`', ];
172
173			return strtr($text, $arr);
174			}
175
176			/**
177			* 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
178			* Insert a space between Chinese character and English/Greek/Number character.
179			*
180			* update base on @link https://github.com/Rakume/pangu.php/blob/master/pangu.php
181			*
182			* @link https://github.com/mzlogin/chinese-copywriting-guidelines#空格
183			*
184			* @param $text
185			*
186			* @return null\|string\|string[]
187			*/
188			public function insertSpace($text)
189			{
190			$patterns = [
191			'cjk_quote' => [
192			'(['.$this->cjk.'])(["\'])',
193			'$1 $2',
194			],
195			'quote_cjk' => [
196			'(["\'])(['.$this->cjk.'])',
197			'$1 $2',
198			],
199			'fix_quote' => [
200			'(["\']+)(\s)(.+?)(\s)(["\']+)',
201			'$1$3$5',
202			],
203			'cjk_hash' => [
204			'(['.$this->cjk.'])(#(\S+))',
205			'$1 $2',
206			],
207			'hash_cjk' => [
208			'((\S+)#)(['.$this->cjk.'])',
209			'$1 $3',
210			],
211			'cjk_operator_ans' => [
212			'(['.$this->cjk.'])(['.$this->ln.'])([\+\-\*\/=&\\\|<>])',
213			'$1 $2 $3',
214			],
215			'ans_operator_cjk' => [
216			'([\+\-\*\/=&\\\|<>])(['.$this->ln.'])(['.$this->cjk.'])',
217			'$1 $2 $3',
218			],
219			'bracket' => [
220			[
221			'(['.$this->cjk.'])([<\[\{\(]+(.*?)[>\]\}\)]+)(['.$this->cjk.'])',
222			'$1 $2 $4',
223			],
224			[
225			'cjk_bracket' => [
226			'(['.$this->cjk.'])([<>\[\]\{\}\(\)])',
227			'$1 $2',
228			],
229			'bracket_cjk' => [
230			'([<>\[\]\{\}\(\)])(['.$this->cjk.'])',
231			'$1 $2',
232			],
233			],
234			],
235			'fix_bracket' => [
236			'([<\[\{\(]+)(\s)(.+?)(\s)([>\]\}\)]+)',
237			'$1$3$5',
238			],
239			'cjk_ans' => [
240			'(['.$this->cjk.'])(['.$this->ln.'`@&%\=\$\^\*\-\+\\/\|\\\])',
241			'$1 $2',
242			],
243			'ans_cjk' => [
244			'(['.$this->ln.'`~!%&=;\\|\,\.\:\?\$\^\*\-\+\/\\\])(['.$this->cjk.'])',
245			'$1 $2',
246			],
247			];
248			foreach ($patterns as $key => $value) {
249			if ($key === 'bracket') {
250			$old = $text;
251			$new = preg_replace('/'.$value[0][0].'/iu', $value[0][1], $text);
252			$text = $new;
253			if ($old === $new) {
254			foreach ($value[1] as $val) {
255			$text = preg_replace('/'.$val[0].'/iu', $val[1], $text);
256			}
257			}
258			continue;
259			}
260			$text = preg_replace('/'.$value[0].'/iu', $value[1], $text);
261			}
262
263			return $text;
264			}
265
266			/**
267			* 全角标点符号与其他字符之间无需添加空格；
268			*
269			* @param $text
270			*
271			* @return null\|string\|string[]
272			*/
273			public function removeSpace($text)
274			{
275			$patterns = [
276			'fullwidth_space' => [
277			'(['.$this->fullwidthPunctuation.'])(['.$this->space.'])',
278			'$1'
279			],
280			'space_fullwidth' => [
281			'(['.$this->space.'])(['.$this->fullwidthPunctuation.'])',
282			'$2'
283			]
284			];
285
286			foreach ($patterns as $key => $value) {
287			$text = preg_replace('/'.$value[0].'/u', $value[1], $text);
288			}
289			return $text;
290			}
291			/**
292			* 专有名词使用正确的大小写
293			* Correct English proper nouns.
294			*
295			* @param $text
296			* @param array $extend
297			* @param array $ignore
298			*
299			* @return null\|string\|string[]
300			*/
301			public function properNoun($text, array $extend = [], array $ignore = [])
302			{
303			$dict = include __DIR__.'/../data/dict.php';
304			if (!empty($extend)) {
305			$dict = array_merge($dict, $extend);
306			}
307			if (!empty($ignore)) {
308			$dict = array_diff($dict, $ignore);
309			}
310
311			foreach ($dict as $noun) {
312			// Matching proper nouns Outside Of Html Tags
313			$text = preg_replace("/(?<!\.\|[a-z]){$noun}(?!\.\|[a-z])(?!([^<]+)?>)/i", $noun, $text);
314			}
315
316			return $text;
317			}
318
319			/**
320			* 清除 Class 属性
321			* Remove specific class of HTML tags.
322			*
323			* @param $text
324			*
325			* @return null\|string\|string[]
326			*/
327			public function removeClass($text)
328			{
329			return preg_replace('#\s(class)="[^"]+"#', '', $text);
330			}
331
332			/**
333			* 清除 ID 属性
334			* Remove specific id of HTML tags.
335			*
336			* @param $text
337			*
338			* @return null\|string\|string[]
339			*/
340			public function removeId($text)
341			{
342			return preg_replace('#\s(id)="[^"]+"#', '', $text);
343			}
344
345			/**
346			* 清除 Style 属性
347			* Remove specific style of HTML tags.
348			*
349			* @param $text
350			*
351			* @return null\|string\|string[]
352			*/
353			public function removeStyle($text)
354			{
355			return preg_replace('#\s(style)="[^"]+"#', '', $text);
356			}
357
358			/**
359			* 清除空段落标签
360			* Remove empty Paragraph tags.
361			*
362			* @param $text
363			* @param bool $nested
364			*
365			* @return null\|string\|string[]
366			*/
367			public function removeEmptyParagraph($text, $nested = true)
368			{
369			$pattern = '/<p[^>]>(['.$this->space.']?)<\\/p[^>]>/';
370			if ($nested) {
371			while (preg_match($pattern, $text)) {
372			$text = preg_replace($pattern, '', $text);
373			}
374			} else {
375			$text = preg_replace($pattern, '', $text);
376			}
377
378			return $text;
379			}
380
381			/**
382			* 清除所有空标签
383			* Remote all empty HTML tags.
384			*
385			* @param $text
386			* @param bool $nested
387			*
388			* @return null\|string\|string[]
389			*/
390			public function removeEmptyTag($text, $nested = true)
391			{
392			$pattern = '/<[^\/>]>(['.$this->space.']?)<\/[^>]*>/';
393			if ($nested) {
394			while (preg_match($pattern, $text)) {
395			$text = preg_replace($pattern, '', $text);
396			}
397			} else {
398			$text = preg_replace($pattern, '', $text);
399			}
400
401			return $text;
402			}
403
404			/**
405			* 清除段首缩进.
406			* Remove indent.
407			*
408			* @param $text
409			*
410			* @return null\|string\|string[]
411			*/
412			public function removeIndent($text)
413			{
414			return preg_replace('/<p([^>]*)>('.$this->space.')+/', '<p${1}>', $text);
415			}
416			}
417

jxlwqq / chinese-typesetting

Push — master ( 6e7810...23e828 )

ChineseTypesetting::fixPunctuation() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like