Article::setRawDoc() - Code Metrics - Inspection of "Make Guzzle response accessible via the Article cl..." - scotteh/php-goose - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 94a5f2...0612f1 )

by Andrew

created 2017-01-12 10:28 UTC

Article::setRawDoc() A

↳ Parent: Article

Complexity

Conditions	1
Paths	1

Size

Total Lines	3
Code Lines	2

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
dl	0
loc	3
rs	10
c	0
b	0
f	0
cc	1
eloc	2
nc	1
nop	1

<?php

namespace Goose;

use Goose\Images\Image;
use DOMWrap\Element;
use DOMWrap\Document;

/**
 * Article
 *
 * @package Goose
 * @license http://www.apache.org/licenses/LICENSE-2.0 Apache License 2.0
 */
class Article {
    /**
     * Language of the article
     *
     * @var string
     */
    protected $language;

    /** @param string $language */
    public function setLanguage($language) {
        $this->language = $language;
    }

    /** @return string */
    public function getLanguage() {
        return $this->language;
    }

    /**
     * OpenGraph meta data
     *
     * @var string[]
     */
    protected $openGraph;

    /** @param string[] $openGraph */
    public function setOpenGraph($openGraph) {
        $this->openGraph = $openGraph;
    }

    /** @return string[] */
    public function getOpenGraph() {
        return $this->openGraph;
    }

    /**
     * Title of the article
     *
     * @var string
     */
    protected $title;

    /** @param string $title */
    public function setTitle($title) {
        $this->title = $title;
    }

    /** @return string */
    public function getTitle() {
        return $this->title;
    }

    /**
     * Stores the lovely, pure text from the article, stripped of html, formatting, etc...
     * just raw text with paragraphs separated by newlines. This is probably what you want to use.
     *
     * @var string
     */
    protected $cleanedArticleText;

    /** @param string $cleanedArticleText */
    public function setCleanedArticleText($cleanedArticleText) {
        $this->cleanedArticleText = $cleanedArticleText;
    }

    /** @return string */
    public function getCleanedArticleText() {
        return $this->cleanedArticleText;
    }

    /**
     * Article with the originals HTML tags (<p>, <a>, ..)
     *
     * @var string
     */
    protected $htmlArticle;

    /** @param string $htmlArticle */
    public function setHtmlArticle($htmlArticle) {
        $this->htmlArticle = $htmlArticle;
    }

    /** @return string */
    public function getHtmlArticle() {
        return $this->htmlArticle;
    }

    /**
     * Meta description field in HTML source
     *
     * @var string
     */
    protected $metaDescription;

    /** @param string $metaDescription */
    public function setMetaDescription($metaDescription) {
        $this->metaDescription = $metaDescription;
    }

    /** @return string */
    public function getMetaDescription() {
        return $this->metaDescription;
    }

    /**
     * Meta keywords field in the HTML source
     *
     * @var string
     */
    protected $metaKeywords;

    /** @param string $metaKeywords */
    public function setMetaKeywords($metaKeywords) {
        $this->metaKeywords = $metaKeywords;
    }

    /** @return string */
    public function getMetaKeywords() {
        return $this->metaKeywords;
    }

    /**
     * The canonical link of this article if found in the meta data
     *
     * @var string
     */
    protected $canonicalLink;

    /** @param string $canonicalLink */
    public function setCanonicalLink($canonicalLink) {
        $this->canonicalLink = $canonicalLink;
    }

    /** @return string */
    public function getCanonicalLink() {
        return $this->canonicalLink;
    }

    /**
     * Domain of the article we're parsing
     *
     * @var string
     */
    protected $domain;

    /** @param string $domain */
    public function setDomain($domain) {
        $this->domain = $domain;
    }

    /** @return string */
    public function getDomain() {
        return $this->domain;
    }

    /**
     * Top Element we think is a candidate for the main body of the article
     *
     * @var Element|null
     */
    protected $topNode;

    /** @param Element|null $topNode */
    public function setTopNode(Element $topNode = null) {
        $this->topNode = $topNode;
    }

    /** @return Element|null */
    public function getTopNode() {
        return $this->topNode;
    }

    /**
     * Top Image object that we think represents this article
     *
     * @var Image|null
     */
    protected $topImage;

    /** @param Image|null $topImage */
    public function setTopImage(Image $topImage = null) {
        $this->topImage = $topImage;
    }

    /** @return Image|null */
    public function getTopImage() {
        return $this->topImage;
    }

    /**
     * All image candidates from article
     *
     * @var Image[]
     */
    protected $allImages = [];

    /** @param Image[] $allImages */
    public function setAllImages($allImages = []) {
        $this->allImages = $allImages;
    }

    /** @return Image[] */
    public function getAllImages() {
        return $this->allImages;
    }

    /**
     * Tags that may have been in the article, these are not meta keywords
     *
     * @var string[]
     */
    protected $tags = [];

    /** @param string[] $tags */
    public function setTags($tags) {
        $this->tags = $tags;
    }

    /** @return string[] */
    public function getTags() {
        return $this->tags;
    }

    /**
     *  List of links in the article
     *
     * @var string[]
     */
    protected $links = [];

    /** @param string[] $links */
    public function setLinks($links) {
        $this->links = $links;
    }

    /** @return string[] */
    public function getLinks() {
        return $this->links;
    }

    /**
     * List of any videos we found on the page like youtube, vimeo
     *
     * @var string[]
     */
    protected $videos = [];

    /** @param string[] $videos */
    public function setVideos($videos) {
        $this->videos = $videos;
    }

    /** @return string[] */
    public function getVideos() {
        return $this->videos;
    }

    /**
     * Final URL that we're going to try and fetch content against, this would be expanded if any
     * escaped fragments were found in the starting url
     *
     * @var string
     */
    protected $finalUrl;

    /** @param string $finalUrl */
    public function setFinalUrl($finalUrl) {
        $this->finalUrl = $finalUrl;
    }

    /** @return string */
    public function getFinalUrl() {
        return $this->finalUrl;
    }

    /**
     * MD5 hash of the url to use for various identification tasks
     *
     * @var string
     */
    protected $linkhash;

    /** @param string $linkhash */
    public function setLinkhash($linkhash) {
        $this->linkhash = $linkhash;
    }

    /** @return string */
    public function getLinkhash() {
        return $this->linkhash;
    }

    /**
     * Raw HTML straight from the network connection
     *
     * @var string
     */
    protected $rawHtml;

    /** @param string $rawHtml */
    public function setRawHtml($rawHtml) {
        $this->rawHtml = $rawHtml;
    }

    /** @return string */
    public function getRawHtml() {
        return $this->rawHtml;
    }

    /**
     * DOM Document object
     *
     * @var Document
     */
    protected $doc;

    /** @param Document $doc */
    public function setDoc(Document $doc) {
        $this->doc = $doc;
    }

    /** @return Document */
    public function getDoc() {
        return $this->doc;
    }

    /**
     * Original DOM document that contains a pure object from the original HTML without any cleaning
     * options done on it
     *
     * @var Document
     */
    protected $rawDoc;

    /** @param Document $rawDoc */
    public function setRawDoc(Document $rawDoc) {
        $this->rawDoc = $rawDoc;
    }

    /** @return Document */
    public function getRawDoc() {
        return $this->rawDoc;
    }

    /**
     * Original psr7 response object
     *
     * @var \Psr\Http\Message\ResponseInterface
     */
    protected $rawResponse;

    /** @param \Psr\Http\Message\ResponseInterface|null $rawResponse */
    public function setRawResponse(\Psr\Http\Message\ResponseInterface $rawResponse) {
        $this->rawResponse = $rawResponse;
    }

    /** @return \Psr\Http\Message\ResponseInterface */
    public function getRawResponse() {
        return $this->rawResponse;
    }

    /**
     * Sometimes useful to try and know when the publish date of an article was
     *
     * @var \DateTime|null
     */
    protected $publishDate;

    /** @param \DateTime|null $publishDate */
    public function setPublishDate(\DateTime $publishDate = null) {
        $this->publishDate = $publishDate;
    }

    /** @return \DateTime|null */
    public function getPublishDate() {
        return $this->publishDate;
    }

    /**
     * A property bucket for consumers of goose to store custom data extractions.
     *
     * @return string
     */
    protected $additionalData;

    /** @param string $additionalData */
    public function setAdditionalData($additionalData) {
        $this->additionalData = $additionalData;
    }

    /** @return string */
    public function getAdditionalData() {
        return $this->additionalData;
    }

    /**
     * Facebook Open Graph data that that is found in Article Meta tags
     *
     * @return string
     */
    protected $openGraphData;

    /** @param string $openGraphData */
    public function setOpenGraphData($openGraphData) {
        $this->openGraphData = $openGraphData;
    }

    /** @return string */
    public function getOpenGraphData() {
        return $this->openGraphData;
    }

    /**
     * Most popular words used in the lovely article
     *
     * @return string[]
     */
    protected $popularWords = [];

    /** @param string[] $popularWords */
    public function setPopularWords($popularWords) {
        $this->popularWords = $popularWords;
    }

    /** @return string[] */
    public function getPopularWords() {
        return $this->popularWords;
    }
}

1			<?php
2
3			namespace Goose;
4
5			use Goose\Images\Image;
6			use DOMWrap\Element;
7			use DOMWrap\Document;
8
9			/**
10			* Article
11			*
12			* @package Goose
13			* @license http://www.apache.org/licenses/LICENSE-2.0 Apache License 2.0
14			*/
15			class Article {
16			/**
17			* Language of the article
18			*
19			* @var string
20			*/
21			protected $language;
22
23			/** @param string $language */
24			public function setLanguage($language) {
25			$this->language = $language;
26			}
27
28			/** @return string */
29			public function getLanguage() {
30			return $this->language;
31			}
32
33			/**
34			* OpenGraph meta data
35			*
36			* @var string[]
37			*/
38			protected $openGraph;
39
40			/** @param string[] $openGraph */
41			public function setOpenGraph($openGraph) {
42			$this->openGraph = $openGraph;
43			}
44
45			/** @return string[] */
46			public function getOpenGraph() {
47			return $this->openGraph;
48			}
49
50			/**
51			* Title of the article
52			*
53			* @var string
54			*/
55			protected $title;
56
57			/** @param string $title */
58			public function setTitle($title) {
59			$this->title = $title;
60			}
61
62			/** @return string */
63			public function getTitle() {
64			return $this->title;
65			}
66
67			/**
68			* Stores the lovely, pure text from the article, stripped of html, formatting, etc...
69			* just raw text with paragraphs separated by newlines. This is probably what you want to use.
70			*
71			* @var string
72			*/
73			protected $cleanedArticleText;
74
75			/** @param string $cleanedArticleText */
76			public function setCleanedArticleText($cleanedArticleText) {
77			$this->cleanedArticleText = $cleanedArticleText;
78			}
79
80			/** @return string */
81			public function getCleanedArticleText() {
82			return $this->cleanedArticleText;
83			}
84
85			/**
86			* Article with the originals HTML tags (<p>, <a>, ..)
87			*
88			* @var string
89			*/
90			protected $htmlArticle;
91
92			/** @param string $htmlArticle */
93			public function setHtmlArticle($htmlArticle) {
94			$this->htmlArticle = $htmlArticle;
95			}
96
97			/** @return string */
98			public function getHtmlArticle() {
99			return $this->htmlArticle;
100			}
101
102			/**
103			* Meta description field in HTML source
104			*
105			* @var string
106			*/
107			protected $metaDescription;
108
109			/** @param string $metaDescription */
110			public function setMetaDescription($metaDescription) {
111			$this->metaDescription = $metaDescription;
112			}
113
114			/** @return string */
115			public function getMetaDescription() {
116			return $this->metaDescription;
117			}
118
119			/**
120			* Meta keywords field in the HTML source
121			*
122			* @var string
123			*/
124			protected $metaKeywords;
125
126			/** @param string $metaKeywords */
127			public function setMetaKeywords($metaKeywords) {
128			$this->metaKeywords = $metaKeywords;
129			}
130
131			/** @return string */
132			public function getMetaKeywords() {
133			return $this->metaKeywords;
134			}
135
136			/**
137			* The canonical link of this article if found in the meta data
138			*
139			* @var string
140			*/
141			protected $canonicalLink;
142
143			/** @param string $canonicalLink */
144			public function setCanonicalLink($canonicalLink) {
145			$this->canonicalLink = $canonicalLink;
146			}
147
148			/** @return string */
149			public function getCanonicalLink() {
150			return $this->canonicalLink;
151			}
152
153			/**
154			* Domain of the article we're parsing
155			*
156			* @var string
157			*/
158			protected $domain;
159
160			/** @param string $domain */
161			public function setDomain($domain) {
162			$this->domain = $domain;
163			}
164
165			/** @return string */
166			public function getDomain() {
167			return $this->domain;
168			}
169
170			/**
171			* Top Element we think is a candidate for the main body of the article
172			*
173			* @var Element\|null
174			*/
175			protected $topNode;
176
177			/** @param Element\|null $topNode */
178			public function setTopNode(Element $topNode = null) {
179			$this->topNode = $topNode;
180			}
181
182			/** @return Element\|null */
183			public function getTopNode() {
184			return $this->topNode;
185			}
186
187			/**
188			* Top Image object that we think represents this article
189			*
190			* @var Image\|null
191			*/
192			protected $topImage;
193
194			/** @param Image\|null $topImage */
195			public function setTopImage(Image $topImage = null) {
196			$this->topImage = $topImage;
197			}
198
199			/** @return Image\|null */
200			public function getTopImage() {
201			return $this->topImage;
202			}
203
204			/**
205			* All image candidates from article
206			*
207			* @var Image[]
208			*/
209			protected $allImages = [];
210
211			/** @param Image[] $allImages */
212			public function setAllImages($allImages = []) {
213			$this->allImages = $allImages;
214			}
215
216			/** @return Image[] */
217			public function getAllImages() {
218			return $this->allImages;
219			}
220
221			/**
222			* Tags that may have been in the article, these are not meta keywords
223			*
224			* @var string[]
225			*/
226			protected $tags = [];
227
228			/** @param string[] $tags */
229			public function setTags($tags) {
230			$this->tags = $tags;
231			}
232
233			/** @return string[] */
234			public function getTags() {
235			return $this->tags;
236			}
237
238			/**
239			* List of links in the article
240			*
241			* @var string[]
242			*/
243			protected $links = [];
244
245			/** @param string[] $links */
246			public function setLinks($links) {
247			$this->links = $links;
248			}
249
250			/** @return string[] */
251			public function getLinks() {
252			return $this->links;
253			}
254
255			/**
256			* List of any videos we found on the page like youtube, vimeo
257			*
258			* @var string[]
259			*/
260			protected $videos = [];
261
262			/** @param string[] $videos */
263			public function setVideos($videos) {
264			$this->videos = $videos;
265			}
266
267			/** @return string[] */
268			public function getVideos() {
269			return $this->videos;
270			}
271
272			/**
273			* Final URL that we're going to try and fetch content against, this would be expanded if any
274			* escaped fragments were found in the starting url
275			*
276			* @var string
277			*/
278			protected $finalUrl;
279
280			/** @param string $finalUrl */
281			public function setFinalUrl($finalUrl) {
282			$this->finalUrl = $finalUrl;
283			}
284
285			/** @return string */
286			public function getFinalUrl() {
287			return $this->finalUrl;
288			}
289
290			/**
291			* MD5 hash of the url to use for various identification tasks
292			*
293			* @var string
294			*/
295			protected $linkhash;
296
297			/** @param string $linkhash */
298			public function setLinkhash($linkhash) {
299			$this->linkhash = $linkhash;
300			}
301
302			/** @return string */
303			public function getLinkhash() {
304			return $this->linkhash;
305			}
306
307			/**
308			* Raw HTML straight from the network connection
309			*
310			* @var string
311			*/
312			protected $rawHtml;
313
314			/** @param string $rawHtml */
315			public function setRawHtml($rawHtml) {
316			$this->rawHtml = $rawHtml;
317			}
318
319			/** @return string */
320			public function getRawHtml() {
321			return $this->rawHtml;
322			}
323
324			/**
325			* DOM Document object
326			*
327			* @var Document
328			*/
329			protected $doc;
330
331			/** @param Document $doc */
332			public function setDoc(Document $doc) {
333			$this->doc = $doc;
334			}
335
336			/** @return Document */
337			public function getDoc() {
338			return $this->doc;
339			}
340
341			/**
342			* Original DOM document that contains a pure object from the original HTML without any cleaning
343			* options done on it
344			*
345			* @var Document
346			*/
347			protected $rawDoc;
348
349			/** @param Document $rawDoc */
350			public function setRawDoc(Document $rawDoc) {
351			$this->rawDoc = $rawDoc;
352			}
353
354			/** @return Document */
355			public function getRawDoc() {
356			return $this->rawDoc;
357			}
358
359			/**
360			* Original psr7 response object
361			*
362			* @var \Psr\Http\Message\ResponseInterface
363			*/
364			protected $rawResponse;
365
366			/** @param \Psr\Http\Message\ResponseInterface\|null $rawResponse */
367			public function setRawResponse(\Psr\Http\Message\ResponseInterface $rawResponse) {
368			$this->rawResponse = $rawResponse;
369			}
370
371			/** @return \Psr\Http\Message\ResponseInterface */
372			public function getRawResponse() {
373			return $this->rawResponse;
374			}
375
376			/**
377			* Sometimes useful to try and know when the publish date of an article was
378			*
379			* @var \DateTime\|null
380			*/
381			protected $publishDate;
382
383			/** @param \DateTime\|null $publishDate */
384			public function setPublishDate(\DateTime $publishDate = null) {
385			$this->publishDate = $publishDate;
386			}
387
388			/** @return \DateTime\|null */
389			public function getPublishDate() {
390			return $this->publishDate;
391			}
392
393			/**
394			* A property bucket for consumers of goose to store custom data extractions.
395			*
396			* @return string
397			*/
398			protected $additionalData;
399
400			/** @param string $additionalData */
401			public function setAdditionalData($additionalData) {
402			$this->additionalData = $additionalData;
403			}
404
405			/** @return string */
406			public function getAdditionalData() {
407			return $this->additionalData;
408			}
409
410			/**
411			* Facebook Open Graph data that that is found in Article Meta tags
412			*
413			* @return string
414			*/
415			protected $openGraphData;
416
417			/** @param string $openGraphData */
418			public function setOpenGraphData($openGraphData) {
419			$this->openGraphData = $openGraphData;
420			}
421
422			/** @return string */
423			public function getOpenGraphData() {
424			return $this->openGraphData;
425			}
426
427			/**
428			* Most popular words used in the lovely article
429			*
430			* @return string[]
431			*/
432			protected $popularWords = [];
433
434			/** @param string[] $popularWords */
435			public function setPopularWords($popularWords) {
436			$this->popularWords = $popularWords;
437			}
438
439			/** @return string[] */
440			public function getPopularWords() {
441			return $this->popularWords;
442			}
443			}

scotteh / php-goose

Push — master ( 94a5f2...0612f1 )

Article::setRawDoc() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like