HTML2PDF_parsingHtml::_prepareTxt() - Code Metrics - Eoxia/wpshop - Measure and Improve Code Quality continuously with Scrutinizer

HTML2PDF_parsingHtml::_prepareTxt() A
last analyzed 2017-07-26 08:47 UTC

↳ Parent: HTML2PDF_parsingHtml

Complexity

Conditions	2
Paths	2

Size

Total Lines	7
Code Lines	5

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	2
eloc	5
nc	2
nop	2
dl	0
loc	7
rs	9.4285
c	0
b	0
f	0

<?php if ( !defined( 'ABSPATH' ) ) exit;
/**
 * HTML2PDF Librairy - parsingHtml class
 *
 * HTML => PDF convertor
 * distributed under the LGPL License
 *
 * @author      Laurent MINGUET <[email protected]>
 * @version     4.03
 */

class HTML2PDF_parsingHtml
{
    protected    $_html     = '';        // HTML code to parse
    protected    $_num      = 0;         // table number
    protected    $_level    = 0;         // table level
    protected    $_encoding = '';        // encoding
    public       $code      = array();   // parsed HTML codfe

    const HTML_TAB = '        ';

    /**
     * main constructor
     *
     * @param   string encoding
     * @access  public
     */
    public function __construct($encoding = 'UTF-8')
    {
        $this->_num   = 0;
        $this->_level = array($this->_num);

        $this->_html  = '';
        $this->code  = array();
        $this->setEncoding($encoding);
    }

    /**
     * change the encoding
     *
     * @param   string encoding
     * @access  public
     */
    public function setEncoding($encoding)
    {
        $this->_encoding = $encoding;
    }

    /**
     * Define the HTML code to parse
     *
     * @param   string HTML code
     * @access  public
     */
    public function setHTML($html)
    {
        // remove the HTML in comment
        $html = preg_replace('/<!--(.*)-->/isU', '', $html);

        // save the HTML code
        $this->_html = $html;
    }

    /**
     * parse the HTML code
     *
     * @access public
     */
    public function parse()
    {
        $parents = array();

        // flag : are we in a <pre> Tag ?
        $tagPreIn = false;

        // action to use for each line of the content of a <pre> Tag
        $tagPreBr = array(
                    'name' => 'br',
                    'close' => false,
                    'param' => array(
                        'style' => array(),
                        'num'    => 0
                    )
                );

        // tag that can be not closed
        $tagsNotClosed = array(
            'br', 'hr', 'img', 'col',
            'input', 'link', 'option',
            'circle', 'ellipse', 'path', 'rect', 'line', 'polygon', 'polyline'
        );

        // search the HTML tags
        $tmp = array();
        $this->_searchCode($tmp);

        // all the actions to do
        $actions = array();

        // foreach part of the HTML code
        foreach ($tmp as $part) {
            // if it is a tag code
            if ($part[0]=='code') {
                // analise the HTML code
                $res = $this->_analiseCode($part[1]);

                // if it is a real HTML tag
                if ($res) {
                    // save the current posistion in the HTML code
                    $res['html_pos'] = $part[2];

                    // if the tag must be closed
                    if (!in_array($res['name'], $tagsNotClosed)) {
                        // if it is a closure tag
                        if ($res['close']) {
                            // HTML validation
                            if (count($parents)<1)
                                throw new HTML2PDF_exception(3, $res['name'], $this->getHtmlErrorCode($res['html_pos']));
                            else if ($parents[count($parents)-1]!=$res['name'])
                                throw new HTML2PDF_exception(4, $parents, $this->getHtmlErrorCode($res['html_pos']));
                            else
                                unset($parents[count($parents)-1]);
                        } else {
                            // if it is a autoclosed tag
                            if ($res['autoclose']) {
                                // save the opened tag
                                $actions[] = $res;

                                // prepare the closed tag
                                $res['params'] = array();
                                $res['close'] = true;
                            }
                            // else :add a child for validation
                            else
                                $parents[count($parents)] = $res['name'];
                        }

                        // if it is a <pre> tag (or <code> tag) not auclosed => update the flag
                        if (($res['name']=='pre' || $res['name']=='code') && !$res['autoclose']) {
                            $tagPreIn = !$res['close'];
                        }
                    }

                    // save the actions to convert
                    $actions[] = $res;
                } else { // else (it is not a real HTML tag => we transform it in Texte
                    $part[0]='txt';
                }
            }
            // if it is text
            if ($part[0]=='txt') {
                // if we are not in a <pre> tag
                if (!$tagPreIn) {
                    // save the action
                    $actions[] = array(
                        'name'    => 'write',
                        'close'    => false,
                        'param' => array('txt' => $this->_prepareTxt($part[1])),
                    );
                } else { // else (if we are in a <pre> tag)
                    // prepare the text
                    $part[1] = str_replace("\r", '', $part[1]);
                    $part[1] = explode("\n", $part[1]);

                    // foreach line of the text
                    foreach ($part[1] as $k => $txt) {
                        // transform the line
                        $txt = str_replace("\t", self::HTML_TAB, $txt);
                        $txt = str_replace(' ', '&nbsp;', $txt);

                        // add a break line
                        if ($k>0) $actions[] = $tagPreBr;

                        // save the action
                        $actions[] = array(
                            'name'    => 'write',
                            'close'    => false,
                            'param' => array('txt' => $this->_prepareTxt($txt, false)),
                        );
                    }
                }
            }
        }

        // for each indentified action, we have to clean up the begin and the end of the texte
        // based on tags that surround it

        // list of the tags to clean
        $tagsToClean = array(
            'page', 'page_header', 'page_footer', 'form',
            'table', 'thead', 'tfoot', 'tr', 'td', 'th', 'br',
            'div', 'hr', 'p', 'ul', 'ol', 'li',
            'h1', 'h2', 'h3', 'h4', 'h5', 'h6',
            'bookmark', 'fieldset', 'legend',
            'draw', 'circle', 'ellipse', 'path', 'rect', 'line', 'g', 'polygon', 'polyline',
            'option'
        );

        // foreach action
        $nb = count($actions);
        for ($k=0; $k<$nb; $k++) {
            // if it is a Text
            if ($actions[$k]['name']=='write') {
                // if the tag before the text is a tag to clean => ltrim on the text
                if ($k>0 && in_array($actions[$k-1]['name'], $tagsToClean))

                    $actions[$k]['param']['txt'] = ltrim($actions[$k]['param']['txt']);

                // if the tag after the text is a tag to clean => rtrim on the text
                if ($k<$nb-1 && in_array($actions[$k+1]['name'], $tagsToClean))

                    $actions[$k]['param']['txt'] = rtrim($actions[$k]['param']['txt']);

                // if the text is empty => remove the action
                if (!strlen($actions[$k]['param']['txt']))
                    unset($actions[$k]);
            }
        }

        // if we are not on the level 0 => HTML validator ERROR
        if (count($parents)) throw new HTML2PDF_exception(5, $parents);

        // save the actions to do
        $this->code = array_values($actions);
    }

    /**
     * prepare the text
     *
     * @param   string texte
     * @param   boolean true => replace multiple space+\t+\r+\n by a single space
     * @return  string texte
     * @access  protected
     */
    protected function _prepareTxt($txt, $spaces = true)
    {
        if ($spaces) $txt = preg_replace('/\s+/is', ' ', $txt);
        $txt = str_replace('&euro;', '€', $txt);
        $txt = html_entity_decode($txt, ENT_QUOTES, $this->_encoding);
        return $txt;
    }

    /**
     * parse the HTML code
     *
     * @param    &array    array's result
     * @return   null
     */
    protected function _searchCode(&$tmp)
    {
        // initialise the array
        $tmp = array();

        // regexp to separate the tags from the texts
        $reg = '/(<[^>]+>)|([^<]+)+/isU';

        // last match found
        $str = '';
        $offset = 0;

        // As it finds a match
        while (preg_match($reg, $this->_html, $parse, PREG_OFFSET_CAPTURE, $offset)) {
            // if it is a tag
            if ($parse[1][0]) {
                // save the previous text if it exists
                if ($str!=='')    $tmp[] = array('txt', $str);

                // save the tag, with the offset
                $tmp[] = array('code', trim($parse[1][0]), $offset);

                // init the current text
                $str = '';
            } else { // else (if it is a text)
                // add the new text to the current text
                $str.= $parse[2][0];
            }

            // Update offset to the end of the match
            $offset = $parse[0][1] + strlen($parse[0][0]);
            unset($parse);
        }
        // if a text is present in the end, we save it
        if ($str!='') $tmp[] = array('txt', $str);
        unset($str);
    }

    /**
     * analise a HTML tag
     *
     * @param   string   HTML code to analise
     * @return  array    corresponding action
     */
    protected function _analiseCode($code)
    {
        // name of the tag, opening, closure, autoclosure
        $tag = '<([\/]{0,1})([_a-z0-9]+)([\/>\s]+)';
        if (!preg_match('/'.$tag.'/isU', $code, $match)) return null;
        $close     = ($match[1]=='/' ? true : false);
        $autoclose = preg_match('/\/>$/isU', $code);
        $name      = strtolower($match[2]);

        // required parameters (depends on the tag name)
        $param    = array();
        $param['style'] = '';
        if ($name=='img') {
            $param['alt'] = '';
            $param['src'] = '';
        }
        if ($name=='a') {
            $param['href'] = '';
        }

        // read the parameters : nom=valeur
        $prop = '([a-zA-Z0-9_]+)=([^"\'\s>]+)';
        preg_match_all('/'.$prop.'/is', $code, $match);
        for($k=0; $k<count($match[0]); $k++)
for ($i=0; $i<count($array); $i++) { // calls count() on each iteration
}

// Better
for ($i=0, $c=count($array); $i<$c; $i++) { // calls count() just once
}
            $param[trim(strtolower($match[1][$k]))] = trim($match[2][$k]);

        // read the parameters : nom="valeur"
        $prop = '([a-zA-Z0-9_]+)=["]([^"]*)["]';
        preg_match_all('/'.$prop.'/is', $code, $match);
        for($k=0; $k<count($match[0]); $k++)
for ($i=0; $i<count($array); $i++) { // calls count() on each iteration
}

// Better
for ($i=0, $c=count($array); $i<$c; $i++) { // calls count() just once
}
            $param[trim(strtolower($match[1][$k]))] = trim($match[2][$k]);

        // read the parameters : nom='valeur'
        $prop = "([a-zA-Z0-9_]+)=[']([^']*)[']";
        preg_match_all('/'.$prop.'/is', $code, $match);
        for($k=0; $k<count($match[0]); $k++)
for ($i=0; $i<count($array); $i++) { // calls count() on each iteration
}

// Better
for ($i=0, $c=count($array); $i<$c; $i++) { // calls count() just once
}
            $param[trim(strtolower($match[1][$k]))] = trim($match[2][$k]);

        // compliance of each parameter
        $color  = "#000000";
        $border = null;
        foreach ($param as $key => $val) {
            $key = strtolower($key);
            switch($key)
            {
                case 'width':
                    unset($param[$key]);
                    $param['style'] .= 'width: '.$val.'px; ';
                    break;

                case 'align':
                    if ($name==='img') {
                        unset($param[$key]);
                        $param['style'] .= 'float: '.$val.'; ';
                    } elseif ($name!=='table') {
                        unset($param[$key]);
                        $param['style'] .= 'text-align: '.$val.'; ';
                    }
                    break;

                case 'valign':
                    unset($param[$key]);
                    $param['style'] .= 'vertical-align: '.$val.'; ';
                    break;

                case 'height':
                    unset($param[$key]);
                    $param['style'] .= 'height: '.$val.'px; ';
                    break;

                case 'bgcolor':
                    unset($param[$key]);
                    $param['style'] .= 'background: '.$val.'; ';
                    break;

                case 'bordercolor':
                    unset($param[$key]);
                    $color = $val;
                    break;

                case 'border':
                    unset($param[$key]);
                    if (preg_match('/^[0-9]+$/isU', $val)) $val = $val.'px';
                    $border = $val;
                    break;

                case 'cellpadding':
                case 'cellspacing':
                    if (preg_match('/^([0-9]+)$/isU', $val)) $param[$key] = $val.'px';
                    break;

                case 'colspan':
                case 'rowspan':
                    $val = preg_replace('/[^0-9]/isU', '', $val);
                    if (!$val) $val = 1;
                    $param[$key] = $val;
                    break;
            }
        }

        // compliance of the border
        if ($border!==null) {
            if ($border)    $border = 'border: solid '.$border.' '.$color;
            else            $border = 'border: none';

            $param['style'] .= $border.'; ';
            $param['border'] = $border;
        }

        // reading styles: decomposition and standardization
        $styles = explode(';', $param['style']);
        $param['style'] = array();
        foreach ($styles as $style) {
            $tmp = explode(':', $style);
            if (count($tmp)>1) {
                $cod = $tmp[0];
                unset($tmp[0]);
                $tmp = implode(':', $tmp);
                $param['style'][trim(strtolower($cod))] = preg_replace('/[\s]+/isU', ' ', trim($tmp));
            }
        }

        // determining the level of table opening, with an added level
        if (in_array($name, array('ul', 'ol', 'table')) && !$close) {
            $this->_num++;
            $this->_level[count($this->_level)] = $this->_num;
        }

        // get the level of the table containing the element
        if (!isset($param['num'])) {
            $param['num'] = $this->_level[count($this->_level)-1];
        }

        // for closures table: remove a level
        if (in_array($name, array('ul', 'ol', 'table')) && $close) {
            unset($this->_level[count($this->_level)-1]);
        }

        // prepare the parameters
        if (isset($param['value']))  $param['value']  = $this->_prepareTxt($param['value']);
        if (isset($param['alt']))    $param['alt']    = $this->_prepareTxt($param['alt']);
        if (isset($param['title']))  $param['title']  = $this->_prepareTxt($param['title']);
        if (isset($param['class']))  $param['class']  = $this->_prepareTxt($param['class']);

        // return the new action to do
        return array('name' => $name, 'close' => $close ? 1 : 0, 'autoclose' => $autoclose, 'param' => $param);
    }

    /**
     * get a full level of HTML, between an opening and closing corresponding
     *
     * @param   integer key
     * @return  array   actions
     */
    public function getLevel($k)
    {
        // if the code does not exist => return empty
        if (!isset($this->code[$k])) return array();

        // the tag to detect
        $detect = $this->code[$k]['name'];

        // if it is a text => return
        if ($detect=='write') {
            return array($this->code[$k]);
        }

        //
        $level = 0;      // depth level
        $end = false;    // end of the search
        $code = array(); // extract code

        // while it's not ended
        while (!$end) {
            // current action
            $row = $this->code[$k];

            // if 'write' => we add the text
            if ($row['name']=='write') {
                $code[] = $row;
            } else { // else, it is a html tag
                $not = false; // flag for not taking into account the current tag

                // if it is the searched tag
                if ($row['name']==$detect) {
                    // if we are just at the root level => dont take it
                    if ($level==0) {
                        $not = true;
                    }

                    // update the level
                    $level+= ($row['close'] ? -1 : 1);

                    // if we are now at the root level => it is the end, and dont take it
                    if ($level==0) {
                        $not = true;
                        $end = true;
                    }
                }

                // if we can takin into account the current tag => save it
                if (!$not) {
                    if (isset($row['style']['text-align'])) unset($row['style']['text-align']);
                    $code[] = $row;
                }
            }

            // it continues as long as there has code to analise
            if (isset($this->code[$k+1]))
                $k++;
            else
                $end = true;
        }

        // return the extract
        return $code;
    }

    /**
     * return a part of the HTML code, for error message
     *
     * @param   integer position
     * @param   integer take before
     * @param   integer take after
     * @return  string  part of the html code
     */
    public function getHtmlErrorCode($pos, $before=30, $after=40)
    {
        return substr($this->_html, $pos-$before, $before+$after);
    }
}

1		<?php if ( !defined( 'ABSPATH' ) ) exit;
2		/**
3		* HTML2PDF Librairy - parsingHtml class
4		*
5		* HTML => PDF convertor
6		* distributed under the LGPL License
7		*
8		* @author Laurent MINGUET <[email protected]>
9		* @version 4.03
10		*/
11
12		class HTML2PDF_parsingHtml
13		{
14		protected $_html = ''; // HTML code to parse
15		protected $_num = 0; // table number
16		protected $_level = 0; // table level
17		protected $_encoding = ''; // encoding
18		public $code = array(); // parsed HTML codfe
19
20		const HTML_TAB = ' ';
21
22		/**
23		* main constructor
24		*
25		* @param string encoding
26		* @access public
27		*/
28		public function __construct($encoding = 'UTF-8')
29		{
30		$this->_num = 0;
31		$this->_level = array($this->_num);
		0 ignored issues – show Documentation Bug introduced 2016-05-17 10:17 UTC by Report Bug Copy Issue Report It seems like `array($this->_num)` of type `array<integer,integer,{"0":"integer"}>` is incompatible with the declared type `integer` of property `$_level`. Our type inference engine has found an assignment to a property that is incompatible with the declared type of that property. Either this assignment is in error or the assigned type should be added to the documentation/type hint for that property.. Loading history...
32		$this->_html = '';
33		$this->code = array();
34		$this->setEncoding($encoding);
35		}
36
37		/**
38		* change the encoding
39		*
40		* @param string encoding
41		* @access public
42		*/
43		public function setEncoding($encoding)
44		{
45		$this->_encoding = $encoding;
46		}
47
48		/**
49		* Define the HTML code to parse
50		*
51		* @param string HTML code
52		* @access public
53		*/
54		public function setHTML($html)
55		{
56		// remove the HTML in comment
57		$html = preg_replace('/<!--(.*)-->/isU', '', $html);
58
59		// save the HTML code
60		$this->_html = $html;
61		}
62
63		/**
64		* parse the HTML code
65		*
66		* @access public
67		*/
68		public function parse()
69		{
70		$parents = array();
71
72		// flag : are we in a <pre> Tag ?
73		$tagPreIn = false;
74
75		// action to use for each line of the content of a <pre> Tag
76		$tagPreBr = array(
77		'name' => 'br',
78		'close' => false,
79		'param' => array(
80		'style' => array(),
81		'num' => 0
82		)
83		);
84
85		// tag that can be not closed
86		$tagsNotClosed = array(
87		'br', 'hr', 'img', 'col',
88		'input', 'link', 'option',
89		'circle', 'ellipse', 'path', 'rect', 'line', 'polygon', 'polyline'
90		);
91
92		// search the HTML tags
93		$tmp = array();
94		$this->_searchCode($tmp);
95
96		// all the actions to do
97		$actions = array();
98
99		// foreach part of the HTML code
100		foreach ($tmp as $part) {
101		// if it is a tag code
102		if ($part[0]=='code') {
103		// analise the HTML code
104		$res = $this->_analiseCode($part[1]);
105
106		// if it is a real HTML tag
107		if ($res) {
108		// save the current posistion in the HTML code
109		$res['html_pos'] = $part[2];
110
111		// if the tag must be closed
112		if (!in_array($res['name'], $tagsNotClosed)) {
113		// if it is a closure tag
114		if ($res['close']) {
115		// HTML validation
116		if (count($parents)<1)
117		throw new HTML2PDF_exception(3, $res['name'], $this->getHtmlErrorCode($res['html_pos']));
118		else if ($parents[count($parents)-1]!=$res['name'])
119		throw new HTML2PDF_exception(4, $parents, $this->getHtmlErrorCode($res['html_pos']));
120		else
121		unset($parents[count($parents)-1]);
122		} else {
123		// if it is a autoclosed tag
124		if ($res['autoclose']) {
125		// save the opened tag
126		$actions[] = $res;
127
128		// prepare the closed tag
129		$res['params'] = array();
130		$res['close'] = true;
131		}
132		// else :add a child for validation
133		else
134		$parents[count($parents)] = $res['name'];
135		}
136
137		// if it is a <pre> tag (or <code> tag) not auclosed => update the flag
138		if (($res['name']=='pre' \|\| $res['name']=='code') && !$res['autoclose']) {
139		$tagPreIn = !$res['close'];
140		}
141		}
142
143		// save the actions to convert
144		$actions[] = $res;
145		} else { // else (it is not a real HTML tag => we transform it in Texte
146		$part[0]='txt';
147		}
148		}
149		// if it is text
150		if ($part[0]=='txt') {
151		// if we are not in a <pre> tag
152		if (!$tagPreIn) {
153		// save the action
154		$actions[] = array(
155		'name' => 'write',
156		'close' => false,
157		'param' => array('txt' => $this->_prepareTxt($part[1])),
158		);
159		} else { // else (if we are in a <pre> tag)
160		// prepare the text
161		$part[1] = str_replace("\r", '', $part[1]);
162		$part[1] = explode("\n", $part[1]);
163
164		// foreach line of the text
165		foreach ($part[1] as $k => $txt) {
166		// transform the line
167		$txt = str_replace("\t", self::HTML_TAB, $txt);
168		$txt = str_replace(' ', ' ', $txt);
169
170		// add a break line
171		if ($k>0) $actions[] = $tagPreBr;
172
173		// save the action
174		$actions[] = array(
175		'name' => 'write',
176		'close' => false,
177		'param' => array('txt' => $this->_prepareTxt($txt, false)),
178		);
179		}
180		}
181		}
182		}
183
184		// for each indentified action, we have to clean up the begin and the end of the texte
185		// based on tags that surround it
186
187		// list of the tags to clean
188		$tagsToClean = array(
189		'page', 'page_header', 'page_footer', 'form',
190		'table', 'thead', 'tfoot', 'tr', 'td', 'th', 'br',
191		'div', 'hr', 'p', 'ul', 'ol', 'li',
192		'h1', 'h2', 'h3', 'h4', 'h5', 'h6',
193		'bookmark', 'fieldset', 'legend',
194		'draw', 'circle', 'ellipse', 'path', 'rect', 'line', 'g', 'polygon', 'polyline',
195		'option'
196		);
197
198		// foreach action
199		$nb = count($actions);
200		for ($k=0; $k<$nb; $k++) {
201		// if it is a Text
202		if ($actions[$k]['name']=='write') {
203		// if the tag before the text is a tag to clean => ltrim on the text
204	View Code Duplication	if ($k>0 && in_array($actions[$k-1]['name'], $tagsToClean))
		0 ignored issues – show Duplication introduced 2016-05-17 10:17 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
205		$actions[$k]['param']['txt'] = ltrim($actions[$k]['param']['txt']);
206
207		// if the tag after the text is a tag to clean => rtrim on the text
208	View Code Duplication	if ($k<$nb-1 && in_array($actions[$k+1]['name'], $tagsToClean))
		0 ignored issues – show Duplication introduced 2016-05-17 10:17 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
209		$actions[$k]['param']['txt'] = rtrim($actions[$k]['param']['txt']);
210
211		// if the text is empty => remove the action
212		if (!strlen($actions[$k]['param']['txt']))
213		unset($actions[$k]);
214		}
215		}
216
217		// if we are not on the level 0 => HTML validator ERROR
218		if (count($parents)) throw new HTML2PDF_exception(5, $parents);
219
220		// save the actions to do
221		$this->code = array_values($actions);
222		}
223
224		/**
225		* prepare the text
226		*
227		* @param string texte
228		* @param boolean true => replace multiple space+\t+\r+\n by a single space
229		* @return string texte
230		* @access protected
231		*/
232		protected function _prepareTxt($txt, $spaces = true)
233		{
234		if ($spaces) $txt = preg_replace('/\s+/is', ' ', $txt);
235		$txt = str_replace('€', '€', $txt);
236		$txt = html_entity_decode($txt, ENT_QUOTES, $this->_encoding);
237		return $txt;
238		}
239
240		/**
241		* parse the HTML code
242		*
243		* @param &array array's result
244		* @return null
245		*/
246		protected function _searchCode(&$tmp)
247		{
248		// initialise the array
249		$tmp = array();
250
251		// regexp to separate the tags from the texts
252		$reg = '/(<[^>]+>)\|([^<]+)+/isU';
253
254		// last match found
255		$str = '';
256		$offset = 0;
257
258		// As it finds a match
259		while (preg_match($reg, $this->_html, $parse, PREG_OFFSET_CAPTURE, $offset)) {
260		// if it is a tag
261		if ($parse[1][0]) {
262		// save the previous text if it exists
263		if ($str!=='') $tmp[] = array('txt', $str);
264
265		// save the tag, with the offset
266		$tmp[] = array('code', trim($parse[1][0]), $offset);
267
268		// init the current text
269		$str = '';
270		} else { // else (if it is a text)
271		// add the new text to the current text
272		$str.= $parse[2][0];
273		}
274
275		// Update offset to the end of the match
276		$offset = $parse[0][1] + strlen($parse[0][0]);
277		unset($parse);
278		}
279		// if a text is present in the end, we save it
280		if ($str!='') $tmp[] = array('txt', $str);
281		unset($str);
282		}
283
284		/**
285		* analise a HTML tag
286		*
287		* @param string HTML code to analise
288		* @return array corresponding action
289		*/
290		protected function _analiseCode($code)
291		{
292		// name of the tag, opening, closure, autoclosure
293		$tag = '<([\/]{0,1})([_a-z0-9]+)([\/>\s]+)';
294		if (!preg_match('/'.$tag.'/isU', $code, $match)) return null;
295		$close = ($match[1]=='/' ? true : false);
296		$autoclose = preg_match('/\/>$/isU', $code);
297		$name = strtolower($match[2]);
298
299		// required parameters (depends on the tag name)
300		$param = array();
301		$param['style'] = '';
302		if ($name=='img') {
303		$param['alt'] = '';
304		$param['src'] = '';
305		}
306		if ($name=='a') {
307		$param['href'] = '';
308		}
309
310		// read the parameters : nom=valeur
311		$prop = '([a-zA-Z0-9_]+)=([^"\'\s>]+)';
312		preg_match_all('/'.$prop.'/is', $code, $match);
313	View Code Duplication	for($k=0; $k<count($match[0]); $k++)
		0 ignored issues – show Performance Best Practice introduced 2016-05-17 10:17 UTC by Report Bug Copy Issue Report It seems like you are calling the size function `count()` as part of the test condition. You might want to compute the size beforehand, and not on each iteration. If the size of the collection does not change during the iteration, it is generally a good practice to compute it beforehand, and not on each iteration: for ($i=0; $i<count($array); $i++) { // calls count() on each iteration } // Better for ($i=0, $c=count($array); $i<$c; $i++) { // calls count() just once } Loading history... Duplication introduced 2016-05-17 10:17 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
314		$param[trim(strtolower($match[1][$k]))] = trim($match[2][$k]);
315
316		// read the parameters : nom="valeur"
317		$prop = '([a-zA-Z0-9_]+)=["]([^"]*)["]';
318		preg_match_all('/'.$prop.'/is', $code, $match);
319	View Code Duplication	for($k=0; $k<count($match[0]); $k++)
		0 ignored issues – show Performance Best Practice introduced 2016-05-17 10:17 UTC by Report Bug Copy Issue Report It seems like you are calling the size function `count()` as part of the test condition. You might want to compute the size beforehand, and not on each iteration. If the size of the collection does not change during the iteration, it is generally a good practice to compute it beforehand, and not on each iteration: for ($i=0; $i<count($array); $i++) { // calls count() on each iteration } // Better for ($i=0, $c=count($array); $i<$c; $i++) { // calls count() just once } Loading history... Duplication introduced 2016-05-17 10:17 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
320		$param[trim(strtolower($match[1][$k]))] = trim($match[2][$k]);
321
322		// read the parameters : nom='valeur'
323		$prop = "([a-zA-Z0-9_]+)=[']([^']*)[']";
324		preg_match_all('/'.$prop.'/is', $code, $match);
325	View Code Duplication	for($k=0; $k<count($match[0]); $k++)
		0 ignored issues – show Performance Best Practice introduced 2016-05-17 10:17 UTC by Report Bug Copy Issue Report It seems like you are calling the size function `count()` as part of the test condition. You might want to compute the size beforehand, and not on each iteration. If the size of the collection does not change during the iteration, it is generally a good practice to compute it beforehand, and not on each iteration: for ($i=0; $i<count($array); $i++) { // calls count() on each iteration } // Better for ($i=0, $c=count($array); $i<$c; $i++) { // calls count() just once } Loading history... Duplication introduced 2016-05-17 10:17 UTC by Report Bug Copy Issue Report This code seems to be duplicated across your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
326		$param[trim(strtolower($match[1][$k]))] = trim($match[2][$k]);
327
328		// compliance of each parameter
329		$color = "#000000";
330		$border = null;
331		foreach ($param as $key => $val) {
332		$key = strtolower($key);
333		switch($key)
334		{
335		case 'width':
336		unset($param[$key]);
337		$param['style'] .= 'width: '.$val.'px; ';
338		break;
339
340		case 'align':
341		if ($name==='img') {
342		unset($param[$key]);
343		$param['style'] .= 'float: '.$val.'; ';
344		} elseif ($name!=='table') {
345		unset($param[$key]);
346		$param['style'] .= 'text-align: '.$val.'; ';
347		}
348		break;
349
350		case 'valign':
351		unset($param[$key]);
352		$param['style'] .= 'vertical-align: '.$val.'; ';
353		break;
354
355		case 'height':
356		unset($param[$key]);
357		$param['style'] .= 'height: '.$val.'px; ';
358		break;
359
360		case 'bgcolor':
361		unset($param[$key]);
362		$param['style'] .= 'background: '.$val.'; ';
363		break;
364
365		case 'bordercolor':
366		unset($param[$key]);
367		$color = $val;
368		break;
369
370		case 'border':
371		unset($param[$key]);
372		if (preg_match('/^[0-9]+$/isU', $val)) $val = $val.'px';
373		$border = $val;
374		break;
375
376		case 'cellpadding':
377		case 'cellspacing':
378		if (preg_match('/^([0-9]+)$/isU', $val)) $param[$key] = $val.'px';
379		break;
380
381		case 'colspan':
382		case 'rowspan':
383		$val = preg_replace('/[^0-9]/isU', '', $val);
384		if (!$val) $val = 1;
385		$param[$key] = $val;
386		break;
387		}
388		}
389
390		// compliance of the border
391		if ($border!==null) {
392		if ($border) $border = 'border: solid '.$border.' '.$color;
393		else $border = 'border: none';
394
395		$param['style'] .= $border.'; ';
396		$param['border'] = $border;
397		}
398
399		// reading styles: decomposition and standardization
400		$styles = explode(';', $param['style']);
401		$param['style'] = array();
402		foreach ($styles as $style) {
403		$tmp = explode(':', $style);
404		if (count($tmp)>1) {
405		$cod = $tmp[0];
406		unset($tmp[0]);
407		$tmp = implode(':', $tmp);
408		$param['style'][trim(strtolower($cod))] = preg_replace('/[\s]+/isU', ' ', trim($tmp));
409		}
410		}
411
412		// determining the level of table opening, with an added level
413		if (in_array($name, array('ul', 'ol', 'table')) && !$close) {
414		$this->_num++;
415		$this->_level[count($this->_level)] = $this->_num;
416		}
417
418		// get the level of the table containing the element
419		if (!isset($param['num'])) {
420		$param['num'] = $this->_level[count($this->_level)-1];
421		}
422
423		// for closures table: remove a level
424		if (in_array($name, array('ul', 'ol', 'table')) && $close) {
425		unset($this->_level[count($this->_level)-1]);
426		}
427
428		// prepare the parameters
429		if (isset($param['value'])) $param['value'] = $this->_prepareTxt($param['value']);
430		if (isset($param['alt'])) $param['alt'] = $this->_prepareTxt($param['alt']);
431		if (isset($param['title'])) $param['title'] = $this->_prepareTxt($param['title']);
432		if (isset($param['class'])) $param['class'] = $this->_prepareTxt($param['class']);
433
434		// return the new action to do
435		return array('name' => $name, 'close' => $close ? 1 : 0, 'autoclose' => $autoclose, 'param' => $param);
436		}
437
438		/**
439		* get a full level of HTML, between an opening and closing corresponding
440		*
441		* @param integer key
442		* @return array actions
443		*/
444		public function getLevel($k)
445		{
446		// if the code does not exist => return empty
447		if (!isset($this->code[$k])) return array();
448
449		// the tag to detect
450		$detect = $this->code[$k]['name'];
451
452		// if it is a text => return
453		if ($detect=='write') {
454		return array($this->code[$k]);
455		}
456
457		//
458		$level = 0; // depth level
459		$end = false; // end of the search
460		$code = array(); // extract code
461
462		// while it's not ended
463		while (!$end) {
464		// current action
465		$row = $this->code[$k];
466
467		// if 'write' => we add the text
468		if ($row['name']=='write') {
469		$code[] = $row;
470		} else { // else, it is a html tag
471		$not = false; // flag for not taking into account the current tag
472
473		// if it is the searched tag
474		if ($row['name']==$detect) {
475		// if we are just at the root level => dont take it
476		if ($level==0) {
477		$not = true;
478		}
479
480		// update the level
481		$level+= ($row['close'] ? -1 : 1);
482
483		// if we are now at the root level => it is the end, and dont take it
484		if ($level==0) {
485		$not = true;
486		$end = true;
487		}
488		}
489
490		// if we can takin into account the current tag => save it
491		if (!$not) {
492		if (isset($row['style']['text-align'])) unset($row['style']['text-align']);
493		$code[] = $row;
494		}
495		}
496
497		// it continues as long as there has code to analise
498		if (isset($this->code[$k+1]))
499		$k++;
500		else
501		$end = true;
502		}
503
504		// return the extract
505		return $code;
506		}
507
508		/**
509		* return a part of the HTML code, for error message
510		*
511		* @param integer position
512		* @param integer take before
513		* @param integer take after
514		* @return string part of the html code
515		*/
516		public function getHtmlErrorCode($pos, $before=30, $after=40)
517		{
518		return substr($this->_html, $pos-$before, $before+$after);
519		}
520		}

Eoxia / wpshop

HTML2PDF_parsingHtml::_prepareTxt() A last analyzed 2017-07-26 08:47 UTC

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

HTML2PDF_parsingHtml::_prepareTxt() A
last analyzed 2017-07-26 08:47 UTC