Element::parseAttribute() - Code Metrics - kevintweber/HtmlTokenizer - Measure and Improve Code Quality continuously with Scrutinizer

Element::parseAttribute() B
last analyzed 2017-10-01 16:21 UTC

↳ Parent: Element

Complexity

Conditions	4
Paths	14

Size

Total Lines	29
Code Lines	17

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	16
CRAP Score	4

Importance

Changes

Metric	Value
dl	0
loc	29
ccs	16
cts	16
cp	1
rs	8.5806
c	0
b	0
f	0
cc	4
eloc	17
nc	14
nop	1
crap	4

<?php

namespace Kevintweber\HtmlTokenizer\Tokens;

use Kevintweber\HtmlTokenizer\Exceptions\ParseException;

class Element extends AbstractToken
{
    /** @var array */
    private $attributes;

    /** @var array[Token] */
    private $children;

    /** @var string */
    private $name;

    public function __construct(Token $parent = null, bool $throwOnError = true)
    {
        parent::__construct(Token::ELEMENT, $parent, $throwOnError);

        $this->attributes = array();
        $this->children = array();
        $this->name = null;
    }

    /**
     * Does the parent have an implied closing tag?
     *
     * @param string $html
     *
     * @return boolean
     */
    public function isClosingElementImplied(string $html) : bool
    {
        $parent = $this->getParent();
        if ($parent === null || !($parent instanceof self)) {
            return false;
        }

        $name = $this->parseElementName($html);
        $parentName = $parent->getName();

        // HEAD: no closing tag.
        if ($name === 'body' && $parentName === 'head') {
            return true;
        }

        // P
        $elementsNotChildrenOfP = array(
            'address',
            'article',
            'aside',
            'blockquote',
            'details',
            'div',
            'dl',
            'fieldset',
            'figcaption',
            'figure',
            'footer',
            'form',
            'h1',
            'h2',
            'h3',
            'h4',
            'h5',
            'h6',
            'header',
            'hgroup',
            'hr',
            'main',
            'menu',
            'nav',
            'ol',
            'p',
            'pre',
            'section',
            'table',
            'ul'
        );
        if ($parentName === 'p' && in_array($name, $elementsNotChildrenOfP)) {
            return true;
        }

        // LI
        if ($parentName === 'li' && $name === 'li') {
            return true;
        }

        // DT and DD
        if (($parentName === 'dt' || $parentName === 'dd') && ($name === 'dt' || $name === 'dd')) {
            return true;
        }

        // RP and RT
        if (($parentName === 'rp' || $parentName === 'rt') && ($name === 'rp' || $name === 'rt')) {
            return true;
        }

        return false;
    }

    /**
     * Will parse this element.
     *
     * @param string $html
     *
     * @return string Remaining HTML.
     */
    public function parse(string $html) : string
    {
        $html = ltrim($html);
        $this->setTokenPosition($html);

        try {
            $this->name = $this->parseElementName($html);
            $remainingHtml = $this->parseAttributes($html);
            $posOfClosingBracket = $this->getPositionOfElementEndTag($remainingHtml);

            // Is self-closing?
            $posOfSelfClosingBracket = mb_strpos($remainingHtml, '/>');
            $remainingHtml = mb_substr($remainingHtml, $posOfClosingBracket + 1);
            if ($posOfSelfClosingBracket !== false && $posOfSelfClosingBracket === $posOfClosingBracket - 1) {
                // Self-closing element. (Note: $this->valuue is unchanged.)
                return $remainingHtml;
            }

            // Lets close those closed-only elements that are left open.
            $closedOnlyElements = array(
                'area',
                'base',
                'br',
                'col',
                'embed',
                'hr',
                'img',
                'input',
                'link',
                'meta',
                'param',
                'source',
                'track',
                'wbr'
            );
            if (in_array($this->name, $closedOnlyElements)) {
                return $remainingHtml;
            }

            // Open element.
            return $this->parseContents($remainingHtml);
        } catch (ParseException $e) {
            if ($this->getThrowOnError()) {
                throw $e;
            }
        }

        return '';
    }

    /**
     * @param string $html
     *
     * @return string
     */
    private function parseAttributes(string $html) : string
    {
        $remainingHtml = mb_substr($html, mb_strlen($this->name) + 1);
        while (mb_strpos($remainingHtml, '>') !== false && preg_match("/^\s*[\/]?>/", $remainingHtml) === 0) {
            $remainingHtml = $this->parseAttribute($remainingHtml);
        }

        return $remainingHtml;
    }

    /**
     * Will parse attributes.
     *
     * @param string $html
     *
     * @return string Remaining HTML.
     */
    private function parseAttribute(string $html) : string
    {
        $remainingHtml = ltrim($html);

        try {
            // Will match the first entire name/value attribute pair.
            preg_match(
                "/((([a-z0-9\-_]+:)?[a-z0-9\-_]+)(\s*=\s*)?)/i",
                $remainingHtml,
                $attributeMatches
            );

            $attributeName = $attributeMatches[2];
            $remainingHtml = mb_substr(mb_strstr($remainingHtml, $attributeName), mb_strlen($attributeName));
            if ($this->isAttributeValueless($remainingHtml)) {
                $this->attributes[trim($attributeName)] = true;

                return $remainingHtml;
            }

            return $this->parseAttributeValue($html, $remainingHtml, $attributeName);
        } catch (ParseException $e) {
            if ($this->getThrowOnError()) {
                throw $e;
            }
        }

        return '';
    }

    private function parseAttributeValue(string $html, string $remainingHtml, string $attributeName) : string
    {
        $remainingHtml = ltrim($remainingHtml, ' =');
        if ($this->isAttributeValueQuoteEnclosed($remainingHtml)) {
            $attributeValue = $this->extractQuoteEnclosedAttributeValue($remainingHtml);
        } else {
            // No quotes enclosing the attribute value.
            $attributeValue = $this->extractQuotelessAttributeValue($remainingHtml);
        }

        $this->attributes[trim($attributeName)] = $attributeValue;
        $remainingHtml = $this->parseAttributeDetermineRemainingHtml($html, $attributeName, $attributeValue);

        return $remainingHtml;
    }

    /**
     * Will parse the contents of this element.
     *
     * @param string $html
     *
     * @return string Remaining HTML.
     */
    private function parseContents(string $html) : string
    {
        if (trim($html) === '') {
            return '';
        }

        // Determine value.
        $this->value = $html;
        if (preg_match("/(.*)<\/\s*" . $this->name . "\s*>/iU", $html, $valueMatches) === 1) {
            $this->value = $valueMatches[1];
        }

        // Don't parse contents of "iframe" element.
        if ($this->name === 'iframe') {
            return $this->parseNoContents('iframe', $html);
        }

        // Only TEXT inside a "script" element.
        if ($this->name === 'script') {
            return $this->parseForeignContents('script', $html);
        }

        // Only TEXT inside a "style" element.
        if ($this->name === 'style') {
            return $this->parseForeignContents('style', $html);
        }

        // Parse contents one token at a time.
        $remainingHtml = $html;
        while ($this->isAnotherTokenPresent($remainingHtml)) {
            $token = TokenFactory::buildFromHtml(
                $remainingHtml,
                $this,
                $this->getThrowOnError()
            );

            if (!$token instanceof Token || $token->isClosingElementImplied($remainingHtml)) {
                return $remainingHtml;
            }

            $remainingHtml = $token->parse($remainingHtml);
            $this->children[] = $token;
        }

        $this->removeLastTokenIfContainsOnlyWhitespace();

        // Remove remaining closing tag.
        $posOfClosingBracket = mb_strpos($remainingHtml, '>');

        return mb_substr($remainingHtml, $posOfClosingBracket + 1);
    }

    /**
     * Will get the element name from the html string.
     *
     * @param $html string
     *
     * @return string The element name.
     */
    private function parseElementName(string $html) : string
    {
        $html = trim($html);
        $elementMatchSuccessful = preg_match(
            "/^(<(([a-z0-9\-]+:)?[a-z0-9\-]+))/i",
            $html,
            $elementMatches
        );
        if ($elementMatchSuccessful !== 1) {
            if ($this->getThrowOnError()) {
                throw new ParseException('Invalid element name. Truncated html = ' . mb_substr($html, 0, 20));
            }

            return '';
        }

        return mb_strtolower($elementMatches[2]);
    }

    /**
     * Will parse the script and style contents correctly.
     *
     * @param $tag  string
     * @param $html string
     *
     * @return string The remaining HTML.
     */
    private function parseForeignContents(string $tag, string $html) : string
    {
        $remainingHtml = ltrim($html);

        // Find all contents.
        $remainingHtml = $this->determineRemainingHtmlOfForeignContents(
            $tag,
            $html,
            $remainingHtml
        );

        // Handle no contents.
        if ($this->value === '') {
            return $remainingHtml;
        }

        $text = new Text($this, $this->getThrowOnError(), $this->value);
        $this->children[] = $text;

        return $remainingHtml;
    }

    /**
     * Will not parse the contents of an element.
     *
     * "iframe" elements.
     *
     * @param $tag  string
     * @param $html string
     *
     * @return string The remaining HTML.
     */
    private function parseNoContents(string $tag, string $html) : string

    {
        $remainingHtml = ltrim($html);
        $matchingResult = preg_match(
            "/(<\/\s*" . $tag . "\s*>)/i",
            $html,
            $endOfScriptMatches
        );
        if ($matchingResult === 0) {
            return '';
        }

        $closingTag = $endOfScriptMatches[1];
        $this->value = mb_substr($remainingHtml, 0, mb_strpos($html, $closingTag));

        return mb_substr(
            mb_strstr($remainingHtml, $closingTag),
            mb_strlen($closingTag)
        );
    }

    /**
     * Getter for 'attributes'.
     *
     * @return array
     */
    public function getAttributes() : array
    {
        return $this->attributes;
    }

    /**
     * @return boolean
     */
    public function hasAttributes() : bool
    {
        return !empty($this->attributes);
    }

    /**
     * Getter for 'children'.
     *
     * @return array
     */
    public function getChildren() : array
    {
        return $this->children;
    }

    /**
     * @return boolean
     */
    public function hasChildren() : bool
    {
        return !empty($this->children);
    }

    /**
     * Getter for 'name'.
     *
     * @return string
     */
    public function getName() : string
    {
        return $this->name;
    }

    public function toArray() : array
    {
        $result = array(
            'type' => 'element',
            'name' => $this->name,
            'line' => $this->getLine(),
            'position' => $this->getPosition()
        );

        if (!empty($this->attributes)) {
            $result['attributes'] = array();
            foreach ($this->attributes as $name => $value) {
                $result['attributes'][$name] = $value;
            }
        }

        if (!empty($this->children)) {
            $result['children'] = array();
            foreach ($this->children as $child) {
                $result['children'][] = $child->toArray();
            }
        }

        return $result;
    }

    private function determineRemainingHtmlByRemovingAttributeName(string $html, string $name, string $value) : string
    {
        $remainingHtml = ltrim($html);

        $remainingHtml = mb_substr($remainingHtml, mb_strlen($name));
        $posOfAttributeValue = mb_strpos($remainingHtml, $value);
        $remainingHtml = ltrim(
            mb_substr(
                $remainingHtml,
                $posOfAttributeValue + mb_strlen($value)
            )
        );

        return $remainingHtml;
    }

    private function parseAttributeDetermineRemainingHtml(string $html, string $attributeName, string $value) : string
    {
        if ($value === '') {
            $remainingHtml = ltrim(mb_substr(ltrim($html), mb_strlen($attributeName) + 3));
        } else {
            $remainingHtml = $this->determineRemainingHtmlByRemovingAttributeName($html, $attributeName, $value);
        }

        return ltrim($remainingHtml, '\'"/ ');
    }

    private function isAttributeValueless(string $remainingHtml) : bool
    {
        return preg_match("/^\s*=\s*/", $remainingHtml) === 0;
    }

    private function getPositionOfElementEndTag(string $remainingHtml) : int
    {
        $posOfClosingBracket = mb_strpos($remainingHtml, '>');
        if ($posOfClosingBracket === false) {
            throw new ParseException('Invalid element: missing closing bracket.');
        }

        return $posOfClosingBracket;
    }

    private function removeLastTokenIfContainsOnlyWhitespace()
    {
        if (!empty($this->children)) {
            $lastChildArray = array_slice($this->children, -1);
            $lastChild = array_pop($lastChildArray);
            if ($lastChild->isText() && trim($lastChild->getValue()) === '') {
                array_pop($this->children);
            }
        }
    }

    private function isAnotherTokenPresent($remainingHtml) : bool
    {
        return preg_match("/^<\/\s*" . $this->name . "\s*>/is", $remainingHtml) === 0;
    }

    private function extractQuoteEnclosedAttributeValue(string $remainingHtml) : string
    {
        $quoteCharacter = $remainingHtml[0];
        $valueMatchSuccessful = preg_match(
            '/' . $quoteCharacter . "(.*?(?<!\\\))" . $quoteCharacter . "/s",
            $remainingHtml,
            $valueMatches
        );
        if ($valueMatchSuccessful !== 1) {
            throw new ParseException('Invalid quote enclosed attribute value encapsulation.');
        }

        return $valueMatches[1];
    }

    private function extractQuotelessAttributeValue(string $remainingHtml) : string
    {
        $valueMatchSuccessful = preg_match("/(\s*([^>\s]*(?<!\/)))/", $remainingHtml, $valueMatches);
        if ($valueMatchSuccessful !== 1) {
            throw new ParseException('Invalid quoteless attribute value encapsulation.');
        }

        return $valueMatches[2];
    }

    private function isAttributeValueQuoteEnclosed(string $remainingHtml) : bool
    {
        return $remainingHtml[0] === "'" || $remainingHtml[0] === '"';
    }

    private function determineRemainingHtmlOfForeignContents(string $tag, string $html, string $remainingHtml) : string

    {
        $matchingResult = preg_match(
            "/(<\/\s*" . $tag . "\s*>)/i",
            $html,
            $endOfScriptMatches
        );
        if ($matchingResult === 0) {
            $this->value = trim($remainingHtml);

            return '';
        }

        $closingTag = $endOfScriptMatches[1];
        $this->value = trim(
            mb_substr($remainingHtml, 0, mb_strpos($remainingHtml, $closingTag))
        );

        return mb_substr(
            mb_strstr($remainingHtml, $closingTag),
            mb_strlen($closingTag)
        );
    }
}


1			<?php
2
3			namespace Kevintweber\HtmlTokenizer\Tokens;
4
5			use Kevintweber\HtmlTokenizer\Exceptions\ParseException;
6
7			class Element extends AbstractToken
8			{
9			/** @var array */
10			private $attributes;
11
12			/** @var array[Token] */
13			private $children;
14
15			/** @var string */
16			private $name;
17
18	71		public function __construct(Token $parent = null, bool $throwOnError = true)
19			{
20	71		parent::__construct(Token::ELEMENT, $parent, $throwOnError);
21
22	71		$this->attributes = array();
23	71		$this->children = array();
24	71		$this->name = null;
25	71		}
26
27			/**
28			* Does the parent have an implied closing tag?
29			*
30			* @param string $html
31			*
32			* @return boolean
33			*/
34	27		public function isClosingElementImplied(string $html) : bool
35			{
36	27		$parent = $this->getParent();
37	27		if ($parent === null \|\| !($parent instanceof self)) {
38	1		return false;
39			}
40
41	26		$name = $this->parseElementName($html);
42	26		$parentName = $parent->getName();
43
44			// HEAD: no closing tag.
45	26		if ($name === 'body' && $parentName === 'head') {
46	2		return true;
47			}
48
49			// P
50			$elementsNotChildrenOfP = array(
51	25		'address',
52			'article',
53			'aside',
54			'blockquote',
55			'details',
56			'div',
57			'dl',
58			'fieldset',
59			'figcaption',
60			'figure',
61			'footer',
62			'form',
63			'h1',
64			'h2',
65			'h3',
66			'h4',
67			'h5',
68			'h6',
69			'header',
70			'hgroup',
71			'hr',
72			'main',
73			'menu',
74			'nav',
75			'ol',
76			'p',
77			'pre',
78			'section',
79			'table',
80			'ul'
81			);
82	25		if ($parentName === 'p' && in_array($name, $elementsNotChildrenOfP)) {
83	3		return true;
84			}
85
86			// LI
87	22		if ($parentName === 'li' && $name === 'li') {
88	1		return true;
89			}
90
91			// DT and DD
92	21		if (($parentName === 'dt' \|\| $parentName === 'dd') && ($name === 'dt' \|\| $name === 'dd')) {
93	4		return true;
94			}
95
96			// RP and RT
97	17		if (($parentName === 'rp' \|\| $parentName === 'rt') && ($name === 'rp' \|\| $name === 'rt')) {
98	4		return true;
99			}
100
101	13		return false;
102			}
103
104			/**
105			* Will parse this element.
106			*
107			* @param string $html
108			*
109			* @return string Remaining HTML.
110			*/
111	55		public function parse(string $html) : string
112			{
113	55		$html = ltrim($html);
114	55		$this->setTokenPosition($html);
115
116			try {
117	55		$this->name = $this->parseElementName($html);
118	55		$remainingHtml = $this->parseAttributes($html);
119	55		$posOfClosingBracket = $this->getPositionOfElementEndTag($remainingHtml);
120
121			// Is self-closing?
122	51		$posOfSelfClosingBracket = mb_strpos($remainingHtml, '/>');
123	51		$remainingHtml = mb_substr($remainingHtml, $posOfClosingBracket + 1);
124	51		if ($posOfSelfClosingBracket !== false && $posOfSelfClosingBracket === $posOfClosingBracket - 1) {
125			// Self-closing element. (Note: $this->valuue is unchanged.)
126	7		return $remainingHtml;
127			}
128
129			// Lets close those closed-only elements that are left open.
130			$closedOnlyElements = array(
131	45		'area',
132			'base',
133			'br',
134			'col',
135			'embed',
136			'hr',
137			'img',
138			'input',
139			'link',
140			'meta',
141			'param',
142			'source',
143			'track',
144			'wbr'
145			);
146	45		if (in_array($this->name, $closedOnlyElements)) {
147	6		return $remainingHtml;
148			}
149
150			// Open element.
151	44		return $this->parseContents($remainingHtml);
152	4		} catch (ParseException $e) {
153	4		if ($this->getThrowOnError()) {
154	3		throw $e;
155			}
156			}
157
158	3		return '';
159			}
160
161			/**
162			* @param string $html
163			*
164			* @return string
165			*/
166	55		private function parseAttributes(string $html) : string
167			{
168	55		$remainingHtml = mb_substr($html, mb_strlen($this->name) + 1);
169	55		while (mb_strpos($remainingHtml, '>') !== false && preg_match("/^\s*[\/]?>/", $remainingHtml) === 0) {
170	26		$remainingHtml = $this->parseAttribute($remainingHtml);
171			}
172
173	55		return $remainingHtml;
174			}
175
176			/**
177			* Will parse attributes.
178			*
179			* @param string $html
180			*
181			* @return string Remaining HTML.
182			*/
183	26		private function parseAttribute(string $html) : string
184			{
185	26		$remainingHtml = ltrim($html);
186
187			try {
188			// Will match the first entire name/value attribute pair.
189	26		preg_match(
190	26		"/((([a-z0-9\-_]+:)?[a-z0-9\-_]+)(\s=\s)?)/i",
191	26		$remainingHtml,
192	26		$attributeMatches
193			);
194
195	26		$attributeName = $attributeMatches[2];
196	26		$remainingHtml = mb_substr(mb_strstr($remainingHtml, $attributeName), mb_strlen($attributeName));
197	26		if ($this->isAttributeValueless($remainingHtml)) {
198	4		$this->attributes[trim($attributeName)] = true;
199
200	4		return $remainingHtml;
201			}
202
203	24		return $this->parseAttributeValue($html, $remainingHtml, $attributeName);
204	1		} catch (ParseException $e) {
205	1		if ($this->getThrowOnError()) {
206	1		throw $e;
207			}
208			}
209
210	1		return '';
211			}
212
213	24		private function parseAttributeValue(string $html, string $remainingHtml, string $attributeName) : string
214			{
215	24		$remainingHtml = ltrim($remainingHtml, ' =');
216	24		if ($this->isAttributeValueQuoteEnclosed($remainingHtml)) {
217	21		$attributeValue = $this->extractQuoteEnclosedAttributeValue($remainingHtml);
218			} else {
219			// No quotes enclosing the attribute value.
220	7		$attributeValue = $this->extractQuotelessAttributeValue($remainingHtml);
221			}
222
223	23		$this->attributes[trim($attributeName)] = $attributeValue;
224	23		$remainingHtml = $this->parseAttributeDetermineRemainingHtml($html, $attributeName, $attributeValue);
225
226	23		return $remainingHtml;
227			}
228
229			/**
230			* Will parse the contents of this element.
231			*
232			* @param string $html
233			*
234			* @return string Remaining HTML.
235			*/
236	44		private function parseContents(string $html) : string
237			{
238	44		if (trim($html) === '') {
239	13		return '';
240			}
241
242			// Determine value.
243	31		$this->value = $html;
244	31		if (preg_match("/(.)<\/\s" . $this->name . "\s*>/iU", $html, $valueMatches) === 1) {
245	28		$this->value = $valueMatches[1];
246			}
247
248			// Don't parse contents of "iframe" element.
249	31		if ($this->name === 'iframe') {
250	3		return $this->parseNoContents('iframe', $html);
251			}
252
253			// Only TEXT inside a "script" element.
254	30		if ($this->name === 'script') {
255	5		return $this->parseForeignContents('script', $html);
256			}
257
258			// Only TEXT inside a "style" element.
259	27		if ($this->name === 'style') {
260	2		return $this->parseForeignContents('style', $html);
261			}
262
263			// Parse contents one token at a time.
264	25		$remainingHtml = $html;
265	25		while ($this->isAnotherTokenPresent($remainingHtml)) {
266	23		$token = TokenFactory::buildFromHtml(
267	23		$remainingHtml,
268	23		$this,
269	23		$this->getThrowOnError()
270			);
271
272	23		if (!$token instanceof Token \|\| $token->isClosingElementImplied($remainingHtml)) {
273	2		return $remainingHtml;
274			}
275
276	23		$remainingHtml = $token->parse($remainingHtml);
277	23		$this->children[] = $token;
278			}
279
280	24		$this->removeLastTokenIfContainsOnlyWhitespace();
281
282			// Remove remaining closing tag.
283	24		$posOfClosingBracket = mb_strpos($remainingHtml, '>');
284
285	24		return mb_substr($remainingHtml, $posOfClosingBracket + 1);
286			}
287
288			/**
289			* Will get the element name from the html string.
290			*
291			* @param $html string
292			*
293			* @return string The element name.
294			*/
295	69		private function parseElementName(string $html) : string
296			{
297	69		$html = trim($html);
298	69		$elementMatchSuccessful = preg_match(
299	69		"/^(<(([a-z0-9\-]+:)?[a-z0-9\-]+))/i",
300	69		$html,
301	69		$elementMatches
302			);
303	69		if ($elementMatchSuccessful !== 1) {
304	1		if ($this->getThrowOnError()) {
305	1		throw new ParseException('Invalid element name. Truncated html = ' . mb_substr($html, 0, 20));
306			}
307
308	1		return '';
309			}
310
311	68		return mb_strtolower($elementMatches[2]);
312			}
313
314			/**
315			* Will parse the script and style contents correctly.
316			*
317			* @param $tag string
318			* @param $html string
319			*
320			* @return string The remaining HTML.
321			*/
322	7		private function parseForeignContents(string $tag, string $html) : string
323			{
324	7		$remainingHtml = ltrim($html);
325
326			// Find all contents.
327	7		$remainingHtml = $this->determineRemainingHtmlOfForeignContents(
328	7		$tag,
329	7		$html,
330	7		$remainingHtml
331			);
332
333			// Handle no contents.
334	7		if ($this->value === '') {
335	1		return $remainingHtml;
336			}
337
338	7		$text = new Text($this, $this->getThrowOnError(), $this->value);
339	7		$this->children[] = $text;
340
341	7		return $remainingHtml;
342			}
343
344			/**
345			* Will not parse the contents of an element.
346			*
347			* "iframe" elements.
348			*
349			* @param $tag string
350			* @param $html string
351			*
352			* @return string The remaining HTML.
353			*/
354	3	View Code Duplication	private function parseNoContents(string $tag, string $html) : string
			0 ignored issues – show Duplication introduced 2017-10-01 16:21 UTC by Report Bug Copy Issue Report This method seems to be duplicated in 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...
355			{
356	3		$remainingHtml = ltrim($html);
357	3		$matchingResult = preg_match(
358	3		"/(<\/\s" . $tag . "\s>)/i",
359	3		$html,
360	3		$endOfScriptMatches
361			);
362	3		if ($matchingResult === 0) {
363	1		return '';
364			}
365
366	2		$closingTag = $endOfScriptMatches[1];
367	2		$this->value = mb_substr($remainingHtml, 0, mb_strpos($html, $closingTag));
368
369	2		return mb_substr(
370	2		mb_strstr($remainingHtml, $closingTag),
371	2		mb_strlen($closingTag)
372			);
373			}
374
375			/**
376			* Getter for 'attributes'.
377			*
378			* @return array
379			*/
380	1		public function getAttributes() : array
381			{
382	1		return $this->attributes;
383			}
384
385			/**
386			* @return boolean
387			*/
388	1		public function hasAttributes() : bool
389			{
390	1		return !empty($this->attributes);
391			}
392
393			/**
394			* Getter for 'children'.
395			*
396			* @return array
397			*/
398	1		public function getChildren() : array
399			{
400	1		return $this->children;
401			}
402
403			/**
404			* @return boolean
405			*/
406	1		public function hasChildren() : bool
407			{
408	1		return !empty($this->children);
409			}
410
411			/**
412			* Getter for 'name'.
413			*
414			* @return string
415			*/
416	43		public function getName() : string
417			{
418	43		return $this->name;
419			}
420
421	30		public function toArray() : array
422			{
423			$result = array(
424	30		'type' => 'element',
425	30		'name' => $this->name,
426	30		'line' => $this->getLine(),
427	30		'position' => $this->getPosition()
428			);
429
430	30		if (!empty($this->attributes)) {
431	17		$result['attributes'] = array();
432	17		foreach ($this->attributes as $name => $value) {
433	17		$result['attributes'][$name] = $value;
434			}
435			}
436
437	30		if (!empty($this->children)) {
438	17		$result['children'] = array();
439	17		foreach ($this->children as $child) {
440	17		$result['children'][] = $child->toArray();
441			}
442			}
443
444	30		return $result;
445			}
446
447	21		private function determineRemainingHtmlByRemovingAttributeName(string $html, string $name, string $value) : string
448			{
449	21		$remainingHtml = ltrim($html);
450
451	21		$remainingHtml = mb_substr($remainingHtml, mb_strlen($name));
452	21		$posOfAttributeValue = mb_strpos($remainingHtml, $value);
453	21		$remainingHtml = ltrim(
454	21		mb_substr(
455	21		$remainingHtml,
456	21		$posOfAttributeValue + mb_strlen($value)
457			)
458			);
459
460	21		return $remainingHtml;
461			}
462
463	23		private function parseAttributeDetermineRemainingHtml(string $html, string $attributeName, string $value) : string
464			{
465	23		if ($value === '') {
466	2		$remainingHtml = ltrim(mb_substr(ltrim($html), mb_strlen($attributeName) + 3));
467			} else {
468	21		$remainingHtml = $this->determineRemainingHtmlByRemovingAttributeName($html, $attributeName, $value);
469			}
470
471	23		return ltrim($remainingHtml, '\'"/ ');
472			}
473
474	26		private function isAttributeValueless(string $remainingHtml) : bool
475			{
476	26		return preg_match("/^\s=\s/", $remainingHtml) === 0;
477			}
478
479	55		private function getPositionOfElementEndTag(string $remainingHtml) : int
480			{
481	55		$posOfClosingBracket = mb_strpos($remainingHtml, '>');
482	55		if ($posOfClosingBracket === false) {
483	4		throw new ParseException('Invalid element: missing closing bracket.');
484			}
485
486	51		return $posOfClosingBracket;
487			}
488
489	24		private function removeLastTokenIfContainsOnlyWhitespace()
490			{
491	24		if (!empty($this->children)) {
492	22		$lastChildArray = array_slice($this->children, -1);
493	22		$lastChild = array_pop($lastChildArray);
494	22		if ($lastChild->isText() && trim($lastChild->getValue()) === '') {
495	3		array_pop($this->children);
496			}
497			}
498	24		}
499
500	25		private function isAnotherTokenPresent($remainingHtml) : bool
501			{
502	25		return preg_match("/^<\/\s" . $this->name . "\s>/is", $remainingHtml) === 0;
503			}
504
505	21		private function extractQuoteEnclosedAttributeValue(string $remainingHtml) : string
506			{
507	21		$quoteCharacter = $remainingHtml[0];
508	21		$valueMatchSuccessful = preg_match(
509	21		'/' . $quoteCharacter . "(.*?(?<!\\\))" . $quoteCharacter . "/s",
510	21		$remainingHtml,
511	21		$valueMatches
512			);
513	21		if ($valueMatchSuccessful !== 1) {
514	1		throw new ParseException('Invalid quote enclosed attribute value encapsulation.');
515			}
516
517	20		return $valueMatches[1];
518			}
519
520	7		private function extractQuotelessAttributeValue(string $remainingHtml) : string
521			{
522	7		$valueMatchSuccessful = preg_match("/(\s([^>\s](?<!\/)))/", $remainingHtml, $valueMatches);
523	7		if ($valueMatchSuccessful !== 1) {
524			throw new ParseException('Invalid quoteless attribute value encapsulation.');
525			}
526
527	7		return $valueMatches[2];
528			}
529
530	24		private function isAttributeValueQuoteEnclosed(string $remainingHtml) : bool
531			{
532	24		return $remainingHtml[0] === "'" \|\| $remainingHtml[0] === '"';
533			}
534
535	7	View Code Duplication	private function determineRemainingHtmlOfForeignContents(string $tag, string $html, string $remainingHtml) : string
			0 ignored issues – show Duplication introduced 2017-10-01 16:21 UTC by Report Bug Copy Issue Report This method seems to be duplicated in 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...
536			{
537	7		$matchingResult = preg_match(
538	7		"/(<\/\s" . $tag . "\s>)/i",
539	7		$html,
540	7		$endOfScriptMatches
541			);
542	7		if ($matchingResult === 0) {
543	2		$this->value = trim($remainingHtml);
544
545	2		return '';
546			}
547
548	5		$closingTag = $endOfScriptMatches[1];
549	5		$this->value = trim(
550	5		mb_substr($remainingHtml, 0, mb_strpos($remainingHtml, $closingTag))
551			);
552
553	5		return mb_substr(
554	5		mb_strstr($remainingHtml, $closingTag),
555	5		mb_strlen($closingTag)
556			);
557			}
558			}
559

kevintweber / HtmlTokenizer

Element::parseAttribute() B last analyzed 2017-10-01 16:21 UTC

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like

Element::parseAttribute() B
last analyzed 2017-10-01 16:21 UTC