ScanCommand::configure() - Code Metrics - Inspection of "WIP: Output full crawl log to CSV file" - spatie/http-status-check - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#67)

unknown

created 2020-02-17 20:00 UTC

ScanCommand::configure() B

↳ Parent: ScanCommand

Complexity

Conditions	1
Paths	1

Size

Total Lines

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
dl	0
loc	68
rs	8.6981
c	0
b	0
f	0
cc	1
nc	1
nop	0

How to fix Long Method

<?php

namespace Spatie\HttpStatusCheck;

use GuzzleHttp\RequestOptions;
use Spatie\Crawler\CrawlAllUrls;
use Spatie\Crawler\Crawler;
use Spatie\Crawler\CrawlInternalUrls;
use Symfony\Component\Console\Command\Command;
use Symfony\Component\Console\Input\InputArgument;
use Symfony\Component\Console\Input\InputInterface;
use Symfony\Component\Console\Input\InputOption;
use Symfony\Component\Console\Output\OutputInterface;
use Symfony\Component\Console\Question\ConfirmationQuestion;

class ScanCommand extends Command
{
    protected function configure()
    {
        $this->setName('scan')
            ->setDescription('Check the http status code of all links on a website.')
            ->addArgument(
                'url',
                InputArgument::REQUIRED,
                'The url to check'
            )
            ->addOption(
                'concurrency',
                'c',
                InputOption::VALUE_REQUIRED,
                'The amount of concurrent connections to use',
                10
            )
            ->addOption(
                'output',
                'o',
                InputOption::VALUE_REQUIRED,
                'Log all non-2xx and non-3xx responses in this file'
            )
            ->addOption(
                'csv',
                'f',
                InputOption::VALUE_REQUIRED,
                'Log all responses in this csv file'
            )
            ->addOption(
                'dont-crawl-external-links',
                'x',
                InputOption::VALUE_NONE,
                'Dont crawl external links'
            )
            ->addOption(
                'timeout',
                't',
                InputOption::VALUE_OPTIONAL,
                'The maximum number of seconds the request can take',
                10
            )
            ->addOption(
                'user-agent',
                'u',
                InputOption::VALUE_OPTIONAL,
                'The User Agent to pass for the request',
                ''
            )
            ->addOption(
                'skip-verification',
                's',
                InputOption::VALUE_NONE,
                'Skips checking the SSL certificate'
            )
            ->addOption(
                'options',
                'opt',
                InputOption::VALUE_IS_ARRAY | InputOption::VALUE_OPTIONAL,
                'Additional options to the request',
                []
            )
            ->addOption(
                'ignore-robots',
                null,
                InputOption::VALUE_NONE,
                'Ignore robots checks'
            );
    }

    /**
     * @param \Symfony\Component\Console\Input\InputInterface $input
     * @param \Symfony\Component\Console\Output\OutputInterface $output
     *
     * @return int
     */
    protected function execute(InputInterface $input, OutputInterface $output)
    {
        $baseUrl = $input->getArgument('url');
        $crawlProfile = $input->getOption('dont-crawl-external-links') ? new CrawlInternalUrls($baseUrl) : new CrawlAllUrls();

        $output->writeln("Start scanning {$baseUrl}");
        $output->writeln('');

        $crawlLogger = new CrawlLogger($output);

        if ($input->getOption('output')) {

            $outputFile = $input->getOption('output');

            if (file_exists($outputFile)) {
                $helper = $this->getHelper('question');
                $question = new ConfirmationQuestion(
                    "The output file `{$outputFile}` already exists. Overwrite it? (y/n)",
                    false
                );

                if (! $helper->ask($input, $output, $question)) {
                    $output->writeln('Aborting...');

                    return 0;
                }
            }

            $crawlLogger->setOutputFile($input->getOption('output'));
        }

        if ($input->getOption('csv')) {

            $csvFile = $input->getOption('csv');

            if (file_exists($csvFile)) {
                $helper = $this->getHelper('question');
                $question = new ConfirmationQuestion(
                    "The csv file `{$csvFile}` already exists. Overwrite it? (y/n)",
                    false
                );

                if (! $helper->ask($input, $output, $question)) {
                    $output->writeln('Aborting...');

                    return 0;
                }
            }

            $crawlLogger->setCsvFile($input->getOption('csv'));
        }

        $clientOptions = [
            RequestOptions::TIMEOUT => $input->getOption('timeout'),
            RequestOptions::VERIFY => ! $input->getOption('skip-verification'),
            RequestOptions::ALLOW_REDIRECTS => false,
        ];

        $clientOptions = array_merge($clientOptions, $input->getOption('options'));

        if ($input->getOption('user-agent')) {
            $clientOptions[RequestOptions::HEADERS]['user-agent'] = $input->getOption('user-agent');
        }

        $crawler = Crawler::create($clientOptions)
            ->setConcurrency($input->getOption('concurrency'))
            ->setCrawlObserver($crawlLogger)
            ->setCrawlProfile($crawlProfile);

        if ($input->getOption('ignore-robots')) {
            $crawler->ignoreRobots();
        }

        $crawler->startCrawling($baseUrl);
/**
 * @return array|string
 */
function returnsDifferentValues($x) {
    if ($x) {
        return 'foo';
    }

    return array();
}

$x = returnsDifferentValues($y);
if (is_array($x)) {
    // $x is an array.
}

        return 0;
    }
}


1		<?php
2
3		namespace Spatie\HttpStatusCheck;
4
5		use GuzzleHttp\RequestOptions;
6		use Spatie\Crawler\CrawlAllUrls;
7		use Spatie\Crawler\Crawler;
8		use Spatie\Crawler\CrawlInternalUrls;
9		use Symfony\Component\Console\Command\Command;
10		use Symfony\Component\Console\Input\InputArgument;
11		use Symfony\Component\Console\Input\InputInterface;
12		use Symfony\Component\Console\Input\InputOption;
13		use Symfony\Component\Console\Output\OutputInterface;
14		use Symfony\Component\Console\Question\ConfirmationQuestion;
15
16		class ScanCommand extends Command
17		{
18		protected function configure()
19		{
20		$this->setName('scan')
21		->setDescription('Check the http status code of all links on a website.')
22		->addArgument(
23		'url',
24		InputArgument::REQUIRED,
25		'The url to check'
26		)
27		->addOption(
28		'concurrency',
29		'c',
30		InputOption::VALUE_REQUIRED,
31		'The amount of concurrent connections to use',
32		10
33		)
34		->addOption(
35		'output',
36		'o',
37		InputOption::VALUE_REQUIRED,
38		'Log all non-2xx and non-3xx responses in this file'
39		)
40		->addOption(
41		'csv',
42		'f',
43		InputOption::VALUE_REQUIRED,
44		'Log all responses in this csv file'
45		)
46		->addOption(
47		'dont-crawl-external-links',
48		'x',
49		InputOption::VALUE_NONE,
50		'Dont crawl external links'
51		)
52		->addOption(
53		'timeout',
54		't',
55		InputOption::VALUE_OPTIONAL,
56		'The maximum number of seconds the request can take',
57		10
58		)
59		->addOption(
60		'user-agent',
61		'u',
62		InputOption::VALUE_OPTIONAL,
63		'The User Agent to pass for the request',
64		''
65		)
66		->addOption(
67		'skip-verification',
68		's',
69		InputOption::VALUE_NONE,
70		'Skips checking the SSL certificate'
71		)
72		->addOption(
73		'options',
74		'opt',
75		InputOption::VALUE_IS_ARRAY \| InputOption::VALUE_OPTIONAL,
76		'Additional options to the request',
77		[]
78		)
79		->addOption(
80		'ignore-robots',
81		null,
82		InputOption::VALUE_NONE,
83		'Ignore robots checks'
84		);
85		}
86
87		/**
88		* @param \Symfony\Component\Console\Input\InputInterface $input
89		* @param \Symfony\Component\Console\Output\OutputInterface $output
90		*
91		* @return int
92		*/
93		protected function execute(InputInterface $input, OutputInterface $output)
94		{
95		$baseUrl = $input->getArgument('url');
96		$crawlProfile = $input->getOption('dont-crawl-external-links') ? new CrawlInternalUrls($baseUrl) : new CrawlAllUrls();
97
98		$output->writeln("Start scanning {$baseUrl}");
99		$output->writeln('');
100
101		$crawlLogger = new CrawlLogger($output);
102
103	View Code Duplication	if ($input->getOption('output')) {
		0 ignored issues – show Duplication introduced 2020-02-17 20:01 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...
104		$outputFile = $input->getOption('output');
105
106		if (file_exists($outputFile)) {
107		$helper = $this->getHelper('question');
108		$question = new ConfirmationQuestion(
109		"The output file `{$outputFile}` already exists. Overwrite it? (y/n)",
110		false
111		);
112
113		if (! $helper->ask($input, $output, $question)) {
114		$output->writeln('Aborting...');
115
116		return 0;
117		}
118		}
119
120		$crawlLogger->setOutputFile($input->getOption('output'));
121		}
122
123	View Code Duplication	if ($input->getOption('csv')) {
		0 ignored issues – show Duplication introduced 2020-02-17 20:01 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...
124		$csvFile = $input->getOption('csv');
125
126		if (file_exists($csvFile)) {
127		$helper = $this->getHelper('question');
128		$question = new ConfirmationQuestion(
129		"The csv file `{$csvFile}` already exists. Overwrite it? (y/n)",
130		false
131		);
132
133		if (! $helper->ask($input, $output, $question)) {
134		$output->writeln('Aborting...');
135
136		return 0;
137		}
138		}
139
140		$crawlLogger->setCsvFile($input->getOption('csv'));
141		}
142
143		$clientOptions = [
144		RequestOptions::TIMEOUT => $input->getOption('timeout'),
145		RequestOptions::VERIFY => ! $input->getOption('skip-verification'),
146		RequestOptions::ALLOW_REDIRECTS => false,
147		];
148
149		$clientOptions = array_merge($clientOptions, $input->getOption('options'));
150
151		if ($input->getOption('user-agent')) {
152		$clientOptions[RequestOptions::HEADERS]['user-agent'] = $input->getOption('user-agent');
153		}
154
155		$crawler = Crawler::create($clientOptions)
156		->setConcurrency($input->getOption('concurrency'))
157		->setCrawlObserver($crawlLogger)
158		->setCrawlProfile($crawlProfile);
159
160		if ($input->getOption('ignore-robots')) {
161		$crawler->ignoreRobots();
162		}
163
164		$crawler->startCrawling($baseUrl);
		0 ignored issues – show Bug introduced 2019-11-19 17:11 UTC by Report Bug Copy Issue Report It seems like `$baseUrl` defined by `$input->getArgument('url')` on line `95` can also be of type `array<integer,string>` or `null`; however, `Spatie\Crawler\Crawler::startCrawling()` does only seem to accept `object<Psr\Http\Message\UriInterface>\|string`, maybe add an additional type check? If a method or function can return multiple different values and unless you are sure that you only can receive a single value in this context, we recommend to add an additional type check: /** * @return array\|string */ function returnsDifferentValues($x) { if ($x) { return 'foo'; } return array(); } $x = returnsDifferentValues($y); if (is_array($x)) { // $x is an array. } If this a common case that PHP Analyzer should handle natively, please let us know by opening an issue. Loading history...
165
166		return 0;
167		}
168		}
169

spatie / http-status-check

GitHub Access Token became invalid

Pull Request — master (#67)

ScanCommand::configure() B

Complexity

Size

Duplication

Importance

How to fix Long Method

Long Method

Duplication Side-by-Side

Filter issues like