Parser::parseTxt() - Code Metrics - Inspection of "Refactoring" - VIPnytt/RobotsTxtParser - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( a7ec5f...7812c9 )

by Jan-Petter

created 2016-04-13 17:30 UTC

Parser::parseTxt() A

↳ Parent: Parser

Complexity

Conditions	2
Paths	2

Size

Total Lines	13
Code Lines	6

Duplication

Lines	0
Ratio	0 %

Importance

Changes	2
Bugs	0	Features	0

Metric	Value
c	2
b	0
f	0
dl	0
loc	13
rs	9.4285
cc	2
eloc	6
nc	2
nop	0

<?php
namespace vipnytt\RobotsTxtParser;

use vipnytt\RobotsTxtParser\Directives\CleanParam;
use vipnytt\RobotsTxtParser\Directives\Host;
use vipnytt\RobotsTxtParser\Directives\Sitemap;
use vipnytt\RobotsTxtParser\Directives\UserAgent;

class Parser implements RobotsTxtInterface
{
    use ObjectTools;

    const SUB_DIRECTIVES = [
        self::DIRECTIVE_CLEAN_PARAM,
        self::DIRECTIVE_HOST,
        self::DIRECTIVE_SITEMAP,
        self::DIRECTIVE_USER_AGENT,
    ];

    protected $raw;

    protected $cleanParam;
    protected $host;
    protected $sitemap;
    protected $userAgent;

    /**
     * Constructor
     *
     * @param string $content - file content
     * @param string $encoding - character encoding
     * @param integer|null $byteLimit - maximum of bytes to parse
     * @throws Exceptions\ParserException
     */
    public function __construct($content, $encoding = self::ENCODING, $byteLimit = self::BYTE_LIMIT)
    {
        if (!mb_internal_encoding($encoding)) {
            throw new Exceptions\ParserException('Unable to set internal character encoding to `' . $encoding . '`');
        }

        $this->cleanParam = new CleanParam([]);
        $this->host = new Host([]);
        $this->sitemap = new Sitemap([]);
function acceptsInteger($int) { }

$x = '123'; // string "123"

// Instead of
acceptsInteger($x);

// we recommend to use
acceptsInteger((integer) $x);
        $this->userAgent = new UserAgent([]);
function acceptsInteger($int) { }

$x = '123'; // string "123"

// Instead of
acceptsInteger($x);

// we recommend to use
acceptsInteger((integer) $x);


        $this->raw = is_int($byteLimit) ? mb_strcut($content, 0, $byteLimit, $encoding) : $content;
        $this->parseTxt();
    }

    /**
     * Parse robots.txt
     *
     * @return void
     */
    private function parseTxt()
    {
        $lines = array_filter(array_map('trim', mb_split('\r\n|\n|\r', $this->raw)));
        // Parse each line individually
        foreach ($lines as $line) {
            // Limit rule length
            $line = mb_substr($line, 0, self::MAX_LENGTH_RULE);
            // Remove comments
            $line = mb_split('#', $line, 2)[0];
            // Parse line
            $this->add($line);
        }
    }

    public function add($line)
    {
        $pair = $this->generateRulePair($line, self::SUB_DIRECTIVES);
        switch ($pair['directive']) {
            case self::DIRECTIVE_CLEAN_PARAM:
                return $this->cleanParam->add($pair['value']);
            case self::DIRECTIVE_HOST:
                return $this->host->add($pair['value']);
            case self::DIRECTIVE_SITEMAP:
                return $this->sitemap->add($pair['value']);
            case self::DIRECTIVE_USER_AGENT:
                return $this->userAgent->add($pair['value']);
        }
        return $this->userAgent->add($line);
    }

    public function export()
    {
        return $this->cleanParam->export()
        + $this->host->export()
        + $this->sitemap->export()
        + $this->userAgent->export();
    }

    /**
     * Check if URL is allowed to crawl
     *
     * @param  string $url - url to check
     * @return bool
     */
    public function isAllowed($url)
    {
        return $this->userAgent->check($url, self::DIRECTIVE_ALLOW);
    }

    /**
     * Check if URL is disallowed to crawl
     *
     * @param  string $url - url to check
     * @return bool
     */
    public function isDisallowed($url)
    {
        return $this->userAgent->check($url, self::DIRECTIVE_DISALLOW);
    }

    /**
     * Get sitemaps
     *
     * @return array
     */
    public function getSitemaps()
    {
        return $this->sitemap->export();
    }

    /**
     * Get host
     *
     * @return string|null
     */
    public function getHost()
    {
        return $this->host->export();
    }

    /**
     * Get Clean-param
     *
     * @return array
     */
    public function getCleanParam()
    {
        return $this->cleanParam->export();
    }
}


1			<?php
2			namespace vipnytt\RobotsTxtParser;
3
4			use vipnytt\RobotsTxtParser\Directives\CleanParam;
5			use vipnytt\RobotsTxtParser\Directives\Host;
6			use vipnytt\RobotsTxtParser\Directives\Sitemap;
7			use vipnytt\RobotsTxtParser\Directives\UserAgent;
8
9			class Parser implements RobotsTxtInterface
10			{
11			use ObjectTools;
12
13			const SUB_DIRECTIVES = [
14			self::DIRECTIVE_CLEAN_PARAM,
15			self::DIRECTIVE_HOST,
16			self::DIRECTIVE_SITEMAP,
17			self::DIRECTIVE_USER_AGENT,
18			];
19
20			protected $raw;
21
22			protected $cleanParam;
23			protected $host;
24			protected $sitemap;
25			protected $userAgent;
26
27			/**
28			* Constructor
29			*
30			* @param string $content - file content
31			* @param string $encoding - character encoding
32			* @param integer\|null $byteLimit - maximum of bytes to parse
33			* @throws Exceptions\ParserException
34			*/
35			public function __construct($content, $encoding = self::ENCODING, $byteLimit = self::BYTE_LIMIT)
36			{
37			if (!mb_internal_encoding($encoding)) {
38			throw new Exceptions\ParserException('Unable to set internal character encoding to `' . $encoding . '`');
39			}
40
41			$this->cleanParam = new CleanParam([]);
42			$this->host = new Host([]);
43			$this->sitemap = new Sitemap([]);
			0 ignored issues – show Documentation introduced 2016-04-13 17:32 UTC by Report Bug Copy Issue Report `array()` is of type `array`, but the function expects a `string`. It seems like the type of the argument is not accepted by the function/method which you are calling. In some cases, in particular if PHP’s automatic type-juggling kicks in this might be fine. In other cases, however this might be a bug. We suggest to add an explicit type cast like in the following example: function acceptsInteger($int) { } $x = '123'; // string "123" // Instead of acceptsInteger($x); // we recommend to use acceptsInteger((integer) $x); Loading history...
44			$this->userAgent = new UserAgent([]);
			0 ignored issues – show Documentation introduced 2016-04-13 17:32 UTC by Report Bug Copy Issue Report `array()` is of type `array`, but the function expects a `string`. It seems like the type of the argument is not accepted by the function/method which you are calling. In some cases, in particular if PHP’s automatic type-juggling kicks in this might be fine. In other cases, however this might be a bug. We suggest to add an explicit type cast like in the following example: function acceptsInteger($int) { } $x = '123'; // string "123" // Instead of acceptsInteger($x); // we recommend to use acceptsInteger((integer) $x); Loading history...
45
46
47			$this->raw = is_int($byteLimit) ? mb_strcut($content, 0, $byteLimit, $encoding) : $content;
48			$this->parseTxt();
49			}
50
51			/**
52			* Parse robots.txt
53			*
54			* @return void
55			*/
56			private function parseTxt()
57			{
58			$lines = array_filter(array_map('trim', mb_split('\r\n\|\n\|\r', $this->raw)));
59			// Parse each line individually
60			foreach ($lines as $line) {
61			// Limit rule length
62			$line = mb_substr($line, 0, self::MAX_LENGTH_RULE);
63			// Remove comments
64			$line = mb_split('#', $line, 2)[0];
65			// Parse line
66			$this->add($line);
67			}
68			}
69
70			public function add($line)
71			{
72			$pair = $this->generateRulePair($line, self::SUB_DIRECTIVES);
73			switch ($pair['directive']) {
74			case self::DIRECTIVE_CLEAN_PARAM:
75			return $this->cleanParam->add($pair['value']);
76			case self::DIRECTIVE_HOST:
77			return $this->host->add($pair['value']);
78			case self::DIRECTIVE_SITEMAP:
79			return $this->sitemap->add($pair['value']);
80			case self::DIRECTIVE_USER_AGENT:
81			return $this->userAgent->add($pair['value']);
82			}
83			return $this->userAgent->add($line);
84			}
85
86			public function export()
87			{
88			return $this->cleanParam->export()
89			+ $this->host->export()
90			+ $this->sitemap->export()
91			+ $this->userAgent->export();
92			}
93
94			/**
95			* Check if URL is allowed to crawl
96			*
97			* @param string $url - url to check
98			* @return bool
99			*/
100			public function isAllowed($url)
101			{
102			return $this->userAgent->check($url, self::DIRECTIVE_ALLOW);
103			}
104
105			/**
106			* Check if URL is disallowed to crawl
107			*
108			* @param string $url - url to check
109			* @return bool
110			*/
111			public function isDisallowed($url)
112			{
113			return $this->userAgent->check($url, self::DIRECTIVE_DISALLOW);
114			}
115
116			/**
117			* Get sitemaps
118			*
119			* @return array
120			*/
121			public function getSitemaps()
122			{
123			return $this->sitemap->export();
124			}
125
126			/**
127			* Get host
128			*
129			* @return string\|null
130			*/
131			public function getHost()
132			{
133			return $this->host->export();
134			}
135
136			/**
137			* Get Clean-param
138			*
139			* @return array
140			*/
141			public function getCleanParam()
142			{
143			return $this->cleanParam->export();
144			}
145			}
146

VIPnytt / RobotsTxtParser

Push — master ( a7ec5f...7812c9 )

Parser::parseTxt() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like