WstatImport::getPageTitles() - Code Metrics - Inspection of "Fix LanguageData 'turc' => 'tr'" - Dispositif/Wikibot - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — dev ( 4ef148...eba0dc )

by Dispositif

created 2020-03-29 15:26 UTC

WstatImport::getPageTitles() A

↳ Parent: WstatImport

Complexity

Conditions	1
Paths	1

Size

Total Lines	2
Code Lines	0

Duplication

Lines	0
Ratio	0 %

Importance

Changes	1
Bugs	0	Features	0

Metric	Value
cc	1
eloc	0
c	1
b	0
f	0
nc	1
nop	0
dl	0
loc	2
rs	10

<?php
/**
 * This file is part of dispositif/wikibot application
 * 2019 : Philippe M. <[email protected]>
 * For the full copyright and MIT license information, please view the LICENSE file.
 */

declare(strict_types=1);

namespace App\Infrastructure;

use Exception;
use GuzzleHttp\Client;

/**
 * Data import from https://wstat.fr (frwiki daily dump parsing).
 * https://wstat.fr/template/index.php?title=Ouvrage&query=inclusions&param=isbn&start=50000&limit=50&format=json
 * Class WstatImport.
 */
class WstatImport implements PageListInterface
{
    const MAX_IMPORT = 50000;

    private $params = [];

    private $max = 100;

    private $client;

    public function __construct(Client $client, ?array $params = null, ?int $max = 500)
    {
        $this->client = $client;
        $this->max = min(self::MAX_IMPORT, $max);

        //example
        // "nom de page" : https://wstat.fr/template/index.php?title=Ouvrage&query=inclusions-title&start=105000&limit=5000
        // "modèle complet" : https://wstat.fr/template/index.php?title=Ouvrage&query=inclusions&start=105000&limit=5000
        if (!$params) {
            $params = [
                'title' => 'Ouvrage',
                'query' => 'inclusions-title',
//                'param' => 'isbn',
                'start' => 50000,
                'limit' => 5000,
            ];
        }
        $this->params = $params;
    }

    public function getUrl()
    {
        $this->params['format'] = 'json';

        return 'https://wstat.fr/template/index.php?'.http_build_query($this->params);
    }

    /**
     * @return array [ ['title' => ..., 'template' => ...] ]
     *
     * @throws Exception
     */
    public function getData(): array
    {
        $data = [];
        $flag = true;
        while ($flag) {
            $json = $this->import($this->getUrl());
            $raw = json_decode($json, true);
            if (empty($raw)) {
                return [];
            }
            $data = array_merge($data, $this->parsingWstatData($raw));
            echo count($data)." titles\n";
            if ($this->max <= 0) {
                $flag = false;


                break;
            }

            // next page initialisation
            $this->params['start'] = (intval($this->params['start']) + $this->params['limit']);
            sleep(3);
        }

        return $data;
    }

    /**
     * Explode raw string.
     *
     * @param array $raw
     *
     * @return array [['title' => ..., 'template' => ...]]
     */
    private function parsingWstatData(array $raw): array
    {
        // Generator ?
        // Alexandre S. Giffard|{{Ouvrage|langue=|auteur1=|prénom...
        $data = [];
        foreach ($raw as $line) {
            // end of page ?
            if ('<!-- + -->' === $line) {
                continue;
            }
            $this->max = ($this->max - 1);

            // validate and explode wstat data
            $pos = mb_strpos($line, '|', 0);
            if (false === $pos || 0 === $pos) {
                continue;
            }
            $title = trim(mb_substr($line, 0, $pos));
            $template = trim(mb_substr($line, $pos + 1));
            $data[] = ['title' => $title, 'template' => $template];
        }

        return (array) $data;
    }

    /**
     * @param string $url
     *
     * @return string
     *
     * @throws Exception
     */
    private function import(string $url)
    {
        $response = $this->client->get($url);
        if (200 !== $response->getStatusCode()) {
            throw new Exception(sprintf('Error code: %s reason: %s', $response->getStatusCode(), $response->getReasonPhrase()));
        }

        return $response->getBody()->getContents();
    }

    public function getPageTitles(): array
    {
        // TODO: Implement getPageTitles() method.
    }
interface ReturnsInt {
    public function returnsIntHinted(): int;
}

class MyClass implements ReturnsInt {
    public function returnsIntHinted(): int
    {
        if (foo()) {
            return 123;
        }
        // here: null is implicitly returned
    }
}
}


1			<?php
2			/**
3			* This file is part of dispositif/wikibot application
4			* 2019 : Philippe M. <[email protected]>
5			* For the full copyright and MIT license information, please view the LICENSE file.
6			*/
7
8			declare(strict_types=1);
9
10			namespace App\Infrastructure;
11
12			use Exception;
13			use GuzzleHttp\Client;
14
15			/**
16			* Data import from https://wstat.fr (frwiki daily dump parsing).
17			* https://wstat.fr/template/index.php?title=Ouvrage&query=inclusions&param=isbn&start=50000&limit=50&format=json
18			* Class WstatImport.
19			*/
20			class WstatImport implements PageListInterface
21			{
22			const MAX_IMPORT = 50000;
23
24			private $params = [];
25
26			private $max = 100;
27
28			private $client;
29
30			public function __construct(Client $client, ?array $params = null, ?int $max = 500)
31			{
32			$this->client = $client;
33			$this->max = min(self::MAX_IMPORT, $max);
34
35			//example
36			// "nom de page" : https://wstat.fr/template/index.php?title=Ouvrage&query=inclusions-title&start=105000&limit=5000
37			// "modèle complet" : https://wstat.fr/template/index.php?title=Ouvrage&query=inclusions&start=105000&limit=5000
38			if (!$params) {
39			$params = [
40			'title' => 'Ouvrage',
41			'query' => 'inclusions-title',
42			// 'param' => 'isbn',
43			'start' => 50000,
44			'limit' => 5000,
45			];
46			}
47			$this->params = $params;
48			}
49
50			public function getUrl()
51			{
52			$this->params['format'] = 'json';
53
54			return 'https://wstat.fr/template/index.php?'.http_build_query($this->params);
55			}
56
57			/**
58			* @return array [ ['title' => ..., 'template' => ...] ]
59			*
60			* @throws Exception
61			*/
62			public function getData(): array
63			{
64			$data = [];
65			$flag = true;
66			while ($flag) {
67			$json = $this->import($this->getUrl());
68			$raw = json_decode($json, true);
69			if (empty($raw)) {
70			return [];
71			}
72			$data = array_merge($data, $this->parsingWstatData($raw));
73			echo count($data)." titles\n";
74			if ($this->max <= 0) {
75			$flag = false;
			0 ignored issues – show Unused Code introduced 2019-11-25 16:53 UTC by Report Bug Copy Issue Report The assignment to `$flag` is dead and can be removed. Loading history...
76
77			break;
78			}
79
80			// next page initialisation
81			$this->params['start'] = (intval($this->params['start']) + $this->params['limit']);
82			sleep(3);
83			}
84
85			return $data;
86			}
87
88			/**
89			* Explode raw string.
90			*
91			* @param array $raw
92			*
93			* @return array [['title' => ..., 'template' => ...]]
94			*/
95			private function parsingWstatData(array $raw): array
96			{
97			// Generator ?
98			// Alexandre S. Giffard\|{{Ouvrage\|langue=\|auteur1=\|prénom...
99			$data = [];
100			foreach ($raw as $line) {
101			// end of page ?
102			if ('<!-- + -->' === $line) {
103			continue;
104			}
105			$this->max = ($this->max - 1);
106
107			// validate and explode wstat data
108			$pos = mb_strpos($line, '\|', 0);
109			if (false === $pos \|\| 0 === $pos) {
110			continue;
111			}
112			$title = trim(mb_substr($line, 0, $pos));
113			$template = trim(mb_substr($line, $pos + 1));
114			$data[] = ['title' => $title, 'template' => $template];
115			}
116
117			return (array) $data;
118			}
119
120			/**
121			* @param string $url
122			*
123			* @return string
124			*
125			* @throws Exception
126			*/
127			private function import(string $url)
128			{
129			$response = $this->client->get($url);
130			if (200 !== $response->getStatusCode()) {
131			throw new Exception(sprintf('Error code: %s reason: %s', $response->getStatusCode(), $response->getReasonPhrase()));
132			}
133
134			return $response->getBody()->getContents();
135			}
136
137			public function getPageTitles(): array
138			{
139			// TODO: Implement getPageTitles() method.
140			}
			1 ignored issue – show Bug Best Practice introduced 2020-03-29 15:33 UTC by Report Bug Copy Issue Report In this branch, the function will implicitly return `null` which is incompatible with the type-hinted return `array`. Consider adding a return statement or allowing `null` as return value. For hinted functions/methods where all return statements with the correct type are only reachable via conditions, ?null? gets implicitly returned which may be incompatible with the hinted type. Let?s take a look at an example: interface ReturnsInt { public function returnsIntHinted(): int; } class MyClass implements ReturnsInt { public function returnsIntHinted(): int { if (foo()) { return 123; } // here: null is implicitly returned } } Loading history...
141			}
142

Dispositif / Wikibot

Push — dev ( 4ef148...eba0dc )

WstatImport::getPageTitles() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like