Article - Code Metrics - Inspection of "Merge pull request #59 from jonathantullett/master" - Swader/diffbot-php-client - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 3cdce8...5b29fc )

by Bruno

created 2017-12-15 00:31 UTC

Article A

↳ Parent: Project

Complexity

Total Complexity

Size/Duplication

Total Lines	280
Duplicated Lines	0 %

Coupling/Cohesion

Components	1
Dependencies	4

Test Coverage

Coverage

90.91%

Importance

Changes

Metric	Value
wmc	26
lcom	1
cbo	4
dl	0
loc	280
ccs	50
cts	55
cp	0.9091
rs	10
c	0
b	0
f	0

19 Methods

Rating	Name	Size	Complexity
A	__construct()	12	3
A	getType()	4	1
A	getText()	4	1
A	getHtml()	4	1
A	getDate()	13	4
A	getAuthor()	4	1
A	getAuthorUrl()	4	1
A	getTags()	4	1
A	getNumPages()	4	1
A	getNextPages()	4	1
A	getSentiment()	4	1
A	getImages()	4	1
A	getVideos()	4	1
A	getDiscussion()	4	1
A	getSiteName()	4	1
A	getPublisherCountry()	4	1
A	getPublisherRegion()	4	1
A	getEstimatedDate()	8	2
A	getCanonicalUrl()	4	2

<?php

namespace Swader\Diffbot\Entity;

use Swader\Diffbot\Abstracts\Entity;
use Swader\Diffbot\Traits\StandardEntity;

class Article extends Entity
{
    use StandardEntity;

    /** @var Discussion */
    protected $discussion = null;

    public function __construct(array $data)
    {
        if (class_exists('\Carbon\Carbon')) {
            $format = 'D, d M o H:i:s e';
            \Carbon\Carbon::setToStringFormat($format);
        }

        parent::__construct($data);
        if (isset($this->data['discussion'])) {
            $this->discussion = new Discussion($this->data['discussion']);
        }
    }

    /**
     * Should always return "article"
     * @return string
     */
    public function getType()
    {
        return $this->data['type'];
    }

    /**
     * Returns plaintext version of article (no HTML) as parsed by Diffbot.
     * Only the content is returned, the text in the surrounding (layout etc) elements is ignored.
     * @return string
     */
    public function getText()
    {
        return $this->data['text'];
    }

    /**
     * Returns full HTML of the article's content - only the content, not the surrounding layout HTML.
     * @return string
     */
    public function getHtml()
    {
        return $this->data['html'];
    }

    /**
     * Returns date as per http://www.w3.org/Protocols/rfc2616/rfc2616-sec3.html#sec3.3
     * Example date: "Wed, 18 Dec 2013 00:00:00 GMT"
     * This will be a Carbon (https://github.com/briannesbitt/Carbon) instance if Carbon is installed.
     * @return \Carbon\Carbon | string
     */
    public function getDate()
    {
        if (!isset($this->data['date'])) {
            return null;
        }
        try {
        return (class_exists('\Carbon\Carbon')) ?
            new \Carbon\Carbon($this->data['date'], 'GMT') :
            $this->data['date'];
        } catch (\Exception $e) {
            return null;
        }
    }

    /**
     * Returns the full name of the author, as signed on the article's page
     * @return string | null
     */
    public function getAuthor()
    {
        return $this->getOrDefault('author');
    }

    /**
     * Returns the URL of the author's profile, if available. Otherwise, null.
     * @return string | null
     */
    public function getAuthorUrl()
    {
        return $this->getOrDefault('authorUrl');
    }

    /**
     * The array returned will contain all tags that Diffbot's AI concluded match the content
     *
     * Note that these are *not* the meta tags as defined by the author, but machine learned ones.
     * The format of the array is:
     *
     * [
     *  [
     *      "id": 133907,
     *      "count": 3,
     *      "prevalence": 0.3103448275862069,
     *      "label": "Apache HTTP Server",
     *      "type": "Http://www.ontologydesignpatterns.org/ont/dul/DUL.owl#InformationEntity",
     *      "uri": "http://dbpedia.org/resource/Apache_HTTP_Server"
     *  ],
     *  [
     *      "id": 208652,
     *      "count": 5,
     *      "prevalence": 0.5172413793103449,
     *      "label": "PHP",
     *      "type": "Http://www.ontologydesignpatterns.org/ont/dul/DUL.owl#InformationEntity",
     *      "uri": "http://dbpedia.org/resource/PHP"
     *  ]
     * ]
     *
     * @return array
     */
    public function getTags()
    {
        return $this->getOrDefault('tags');
    }

    /**
     * Number of pages automatically concatenated to form the text or html response.
     * By default, Diffbot will automatically concatenate up to 20 pages of an article.
     * @see http://support.diffbot.com/automatic-apis/handling-multiple-page-articles/
     * @return int
     */
    public function getNumPages()
    {
        return $this->getOrDefault('numPages', 1);
    }

    /**
     * Array of all page URLs concatenated in a multipage article. Max 20 entries.
     * Empty array if article was not concatenated before being returned.
     * @see http://support.diffbot.com/automatic-apis/handling-multiple-page-articles/
     * @return array
     */
    public function getNextPages()
    {
        return $this->getOrDefault('nextPages', []);
    }

    /**
     * Returns the sentiment score of the analyzed article text, a value randing from
     * -1.0 (very negative) to 1.0 (very positive).
     * @return float|null
     */
    public function getSentiment()
    {
        return $this->getOrDefault('sentiment');
    }

    /**
     * Returns an array of images found in the page's content.
     *
     * Note that this (tries) to ignore content-unrelated images like ads arounds the page, etc.
     * The format of the array will be:
     *
     * [
     *  {
     *      "height": 808,
     *      "diffbotUri": "image|3|-543943368",
     *      "naturalHeight": 808,
     *      "width": 717,
     *      "primary": true,
     *      "naturalWidth": 717,
     *      "url": "https://example.com/image1.png"
     *  },
     *  {
     *      "height": 506,
     *      "diffbotUri": "image|3|-844014913",
     *      "naturalHeight": 506,
     *      "width": 715,
     *      "naturalWidth": 715,
     *      "url": "https://example.com/image1.jpeg"
     *  }
     * ]
     *
     * @return array
     */
    public function getImages()
    {
        return $this->getOrDefault('images', []);
    }

    /**
     * Returns an array of videos found in the article's content.
     *
     * Works on and off - the better choice is the Video API
     * @see https://www.diffbot.com/dev/docs/video
     * The format of the array will be:
     *
     * [
     *  {
     *      "diffbotUri": "video|3|-1138675744",
     *      "primary": true,
     *      "url": "http://player.vimeo.com/video/22439234"
     *  },
     *  {
     *      "diffbotUri": "video|3|-1138675744",
     *      "primary": true,
     *      "url": "http://player.vimeo.com/video/22439234"
     *  }
     * ]
     *
     * @return array
     */
    public function getVideos()
    {
        return $this->getOrDefault('videos', []);
    }

    /**
     * Returns the Discussion entity - comments of the article
     * @return Discussion
     */
    public function getDiscussion()
    {
        return $this->discussion;
    }

    /**
     * The plain-text name of the site (e.g. The New York Times or Diffbot).
     *
     * If no site name is automatically determined, the root domain (diffbot.com) will be returned.
     *
     * @return string | null
     */
    public function getSiteName()
    {
        return $this->getOrDefault('siteName');
    }

    /**
     * If known, the country of the article publication.
     *
     * @return string | null
     */
    public function getPublisherCountry()
    {
        return $this->getOrDefault('publisherCountry', null);
    }

    /**
     * If known, the region of the article publication.
     *
     * @return string | null
     */
    public function getPublisherRegion()
    {
        return $this->getOrDefault('publisherRegion', null);
    }

    /**
     * If an article's date is ambiguous, Diffbot will attempt to estimate a
     * more specific timestamp using various factors. This will not be
     * generated for articles older than two days, or articles without an identified date.
     *
     * @see Article::getDate() - used when estimatedDate isn't defined
     *
     * This will be a Carbon (https://github.com/briannesbitt/Carbon) instance if Carbon is installed.
     *
     * @return \Carbon\Carbon | string
     */
    public function getEstimatedDate()
    {
        $date = $this->getOrDefault('estimatedDate', $this->getDate());

        return (class_exists('\Carbon\Carbon')) ?
            new \Carbon\Carbon($date, 'GMT') :
            $date;
    }

    /**
     * Returns the canonical url from a page, if any.
     * @return string
     */
    public function getCanonicalUrl()
    {
        return isset($this->data['canonicalUrl']) ? $this->data['canonicalUrl'] : null;
    }
}


1		<?php
2
3		namespace Swader\Diffbot\Entity;
4
5		use Swader\Diffbot\Abstracts\Entity;
6		use Swader\Diffbot\Traits\StandardEntity;
7
8		class Article extends Entity
9		{
10		use StandardEntity;
11
12		/** @var Discussion */
13		protected $discussion = null;
14
15	45	public function __construct(array $data)
16		{
17	45	if (class_exists('\Carbon\Carbon')) {
18	45	$format = 'D, d M o H:i:s e';
19	45	\Carbon\Carbon::setToStringFormat($format);
20	45	}
21
22	45	parent::__construct($data);
23	45	if (isset($this->data['discussion'])) {
24	19	$this->discussion = new Discussion($this->data['discussion']);
25	19	}
26	45	}
27
28		/**
29		* Should always return "article"
30		* @return string
31		*/
32	5	public function getType()
33		{
34	5	return $this->data['type'];
35		}
36
37		/**
38		* Returns plaintext version of article (no HTML) as parsed by Diffbot.
39		* Only the content is returned, the text in the surrounding (layout etc) elements is ignored.
40		* @return string
41		*/
42	4	public function getText()
43		{
44	4	return $this->data['text'];
45		}
46
47		/**
48		* Returns full HTML of the article's content - only the content, not the surrounding layout HTML.
49		* @return string
50		*/
51	4	public function getHtml()
52		{
53	4	return $this->data['html'];
54		}
55
56		/**
57		* Returns date as per http://www.w3.org/Protocols/rfc2616/rfc2616-sec3.html#sec3.3
58		* Example date: "Wed, 18 Dec 2013 00:00:00 GMT"
59		* This will be a Carbon (https://github.com/briannesbitt/Carbon) instance if Carbon is installed.
60		* @return \Carbon\Carbon \| string
61		*/
62	5	public function getDate()
63		{
64	5	if (!isset($this->data['date'])) {
65		return null;
66		}
67		try {
68	5	return (class_exists('\Carbon\Carbon')) ?
69	5	new \Carbon\Carbon($this->data['date'], 'GMT') :
70	5	$this->data['date'];
71		} catch (\Exception $e) {
72		return null;
73		}
74		}
75
76		/**
77		* Returns the full name of the author, as signed on the article's page
78		* @return string \| null
79		*/
80	4	public function getAuthor()
81		{
82	4	return $this->getOrDefault('author');
83		}
84
85		/**
86		* Returns the URL of the author's profile, if available. Otherwise, null.
87		* @return string \| null
88		*/
89	4	public function getAuthorUrl()
90		{
91	4	return $this->getOrDefault('authorUrl');
92		}
93
94		/**
95		* The array returned will contain all tags that Diffbot's AI concluded match the content
96		*
97		* Note that these are not the meta tags as defined by the author, but machine learned ones.
98		* The format of the array is:
99		*
100		* [
101		* [
102		* "id": 133907,
103		* "count": 3,
104		* "prevalence": 0.3103448275862069,
105		* "label": "Apache HTTP Server",
106		* "type": "Http://www.ontologydesignpatterns.org/ont/dul/DUL.owl#InformationEntity",
107		* "uri": "http://dbpedia.org/resource/Apache_HTTP_Server"
108		* ],
109		* [
110		* "id": 208652,
111		* "count": 5,
112		* "prevalence": 0.5172413793103449,
113		* "label": "PHP",
114		* "type": "Http://www.ontologydesignpatterns.org/ont/dul/DUL.owl#InformationEntity",
115		* "uri": "http://dbpedia.org/resource/PHP"
116		* ]
117		* ]
118		*
119		* @return array
120		*/
121	4	public function getTags()
122		{
123	4	return $this->getOrDefault('tags');
124		}
125
126		/**
127		* Number of pages automatically concatenated to form the text or html response.
128		* By default, Diffbot will automatically concatenate up to 20 pages of an article.
129		* @see http://support.diffbot.com/automatic-apis/handling-multiple-page-articles/
130		* @return int
131		*/
132	4	public function getNumPages()
133		{
134	4	return $this->getOrDefault('numPages', 1);
135		}
136
137		/**
138		* Array of all page URLs concatenated in a multipage article. Max 20 entries.
139		* Empty array if article was not concatenated before being returned.
140		* @see http://support.diffbot.com/automatic-apis/handling-multiple-page-articles/
141		* @return array
142		*/
143	4	public function getNextPages()
144		{
145	4	return $this->getOrDefault('nextPages', []);
146		}
147
148		/**
149		* Returns the sentiment score of the analyzed article text, a value randing from
150		* -1.0 (very negative) to 1.0 (very positive).
151		* @return float\|null
152		*/
153	4	public function getSentiment()
154		{
155	4	return $this->getOrDefault('sentiment');
156		}
157
158		/**
159		* Returns an array of images found in the page's content.
160		*
161		* Note that this (tries) to ignore content-unrelated images like ads arounds the page, etc.
162		* The format of the array will be:
163		*
164		* [
165		* {
166		* "height": 808,
167		* "diffbotUri": "image\|3\|-543943368",
168		* "naturalHeight": 808,
169		* "width": 717,
170		* "primary": true,
171		* "naturalWidth": 717,
172		* "url": "https://example.com/image1.png"
173		* },
174		* {
175		* "height": 506,
176		* "diffbotUri": "image\|3\|-844014913",
177		* "naturalHeight": 506,
178		* "width": 715,
179		* "naturalWidth": 715,
180		* "url": "https://example.com/image1.jpeg"
181		* }
182		* ]
183		*
184		* @return array
185		*/
186	4	public function getImages()
187		{
188	4	return $this->getOrDefault('images', []);
189		}
190
191		/**
192		* Returns an array of videos found in the article's content.
193		*
194		* Works on and off - the better choice is the Video API
195		* @see https://www.diffbot.com/dev/docs/video
196		* The format of the array will be:
197		*
198		* [
199		* {
200		* "diffbotUri": "video\|3\|-1138675744",
201		* "primary": true,
202		* "url": "http://player.vimeo.com/video/22439234"
203		* },
204		* {
205		* "diffbotUri": "video\|3\|-1138675744",
206		* "primary": true,
207		* "url": "http://player.vimeo.com/video/22439234"
208		* }
209		* ]
210		*
211		* @return array
212		*/
213	4	public function getVideos()
214		{
215	4	return $this->getOrDefault('videos', []);
216		}
217
218		/**
219		* Returns the Discussion entity - comments of the article
220		* @return Discussion
221		*/
222	1	public function getDiscussion()
223		{
224	1	return $this->discussion;
225		}
226
227		/**
228		* The plain-text name of the site (e.g. The New York Times or Diffbot).
229		*
230		* If no site name is automatically determined, the root domain (diffbot.com) will be returned.
231		*
232		* @return string \| null
233		*/
234	1	public function getSiteName()
235		{
236	1	return $this->getOrDefault('siteName');
237		}
238
239		/**
240		* If known, the country of the article publication.
241		*
242		* @return string \| null
243		*/
244	1	public function getPublisherCountry()
245		{
246	1	return $this->getOrDefault('publisherCountry', null);
247		}
248
249		/**
250		* If known, the region of the article publication.
251		*
252		* @return string \| null
253		*/
254	1	public function getPublisherRegion()
255		{
256	1	return $this->getOrDefault('publisherRegion', null);
257		}
258
259		/**
260		* If an article's date is ambiguous, Diffbot will attempt to estimate a
261		* more specific timestamp using various factors. This will not be
262		* generated for articles older than two days, or articles without an identified date.
263		*
264		* @see Article::getDate() - used when estimatedDate isn't defined
265		*
266		* This will be a Carbon (https://github.com/briannesbitt/Carbon) instance if Carbon is installed.
267		*
268		* @return \Carbon\Carbon \| string
269		*/
270	1	public function getEstimatedDate()
271		{
272	1	$date = $this->getOrDefault('estimatedDate', $this->getDate());
273
274	1	return (class_exists('\Carbon\Carbon')) ?
275	1	new \Carbon\Carbon($date, 'GMT') :
276	1	$date;
277		}
278
279		/**
280		* Returns the canonical url from a page, if any.
281		* @return string
282		*/
283		public function getCanonicalUrl()
284		{
285		return isset($this->data['canonicalUrl']) ? $this->data['canonicalUrl'] : null;
286		}
287		}
288

Swader / diffbot-php-client

Push — master ( 3cdce8...5b29fc )

Article A

Complexity

Size/Duplication

Coupling/Cohesion

Test Coverage

Importance

19 Methods

Duplication Side-by-Side

Filter issues like