Job - Code Metrics - Swader/diffbot-php-client - Measure and Improve Code Quality continuously with Scrutinizer

Job A
last analyzed 2018-07-04 11:05 UTC

↳ Parent: Project

Complexity

Total Complexity

Size/Duplication

Total Lines	332
Duplicated Lines	0 %

Coupling/Cohesion

Components	1
Dependencies	1

Test Coverage

Coverage

100%

Importance

Changes

Metric	Value
wmc	34
lcom	1
cbo	1
dl	0
loc	332
ccs	75
cts	75
cp	1
rs	9.68
c	0
b	0
f	0

28 Methods

Rating	Name	Size	Complexity
A	getName()	4	1
A	getType()	4	1
A	getJobCreationTimeUTC()	5	2
A	getJobCompletionTimeUTC()	5	2
A	getJobStatus()	5	2
A	getNotificationSent()	4	1
A	getObjectsFound()	4	1
A	getUrlsHarvested()	4	1
A	getPageCrawlInfo()	8	1
A	getPageProcessInfo()	8	1
A	getMaxRounds()	4	1
A	getRepeat()	4	1
A	getCrawlDelay()	4	1
A	getObeyRobots()	4	1
A	getRoundsCompleted()	4	1
A	getRoundStartTime()	4	1
A	getCurrentTime()	4	1
A	getCurrentTimeUTC()	4	1
A	getApiUrl()	4	1
A	getUrlCrawlPattern()	4	1
A	getUrlProcessPattern()	4	1
A	getPageProcessPattern()	4	1
A	getUrlCrawlRegex()	4	1
A	getUrlProcessRegex()	4	1
A	getMaxHops()	4	1
A	getDownloadUrl()	17	4
A	getNotifyEmail()	4	1
A	getNotifyWebhook()	4	1

<?php

namespace Swader\Diffbot\Abstracts;

use Swader\Diffbot\Exceptions\DiffbotException;

abstract class Job extends Entity
{

    /**
     * Returns the name of the crawljob
     * @return string
     */
    public function getName()
    {
        return (string)$this->data['name'];
    }

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

    /**
     * Timestamp of job creation
     *
     * @return int
     */
    public function getJobCreationTimeUTC()
    {
        return (isset($this->data['jobCreationTimeUTC']))
            ? (int)$this->data['jobCreationTimeUTC'] : null;
    }

    /**
     * Timestamp of job completion
     *
     * @return int
     */
    public function getJobCompletionTimeUTC()
    {
        return (isset($this->data['jobCompletionTimeUTC']))
            ? (int)$this->data['jobCompletionTimeUTC'] : null;
    }

    /**
     * Possible statuses
     *
     * 0    Job is initializing
     * 1    Job has reached maxRounds limit
     * 2    Job has reached maxToCrawl limit
     * 3    Job has reached maxToProcess limit
     * 4    Next round to start in _____ seconds
     * 5    No URLs were added to the crawl
     * 6    Job paused
     * 7    Job in progress
     * 8    All crawling temporarily paused by root administrator for maintenance.
     * 9    Job has completed and no repeat is scheduled
     *
     * @return array
     */
    public function getJobStatus()
    {
        return (isset($this->data['jobStatus']))
            ? $this->data['jobStatus'] : [];
    }

    /**
     * True or false, depending on whether "job complete" notification was sent
     *
     * @return bool
     */
    public function getNotificationSent()
    {
        return (bool)$this->data['sentJobDoneNotification'];
    }

    /**
     * Number of objects found
     *
     * @return int
     */
    public function getObjectsFound()
    {
        return (int)$this->data['objectsFound'];
    }

    /**
     * Number of URLs harvested
     *
     * @return int
     */
    public function getUrlsHarvested()
    {
        return (int)$this->data['urlsHarvested'];
    }

    /**
     * Returns an array with information about crawls - total attempts,
     * successes, and successes this round
     *
     * @return array
     */
    public function getPageCrawlInfo()
    {
        return [
            'attempts' => $this->data['pageCrawlAttempts'],
            'successes' => $this->data['pageCrawlSuccesses'],
            'successesThisRound' => $this->data['pageCrawlSuccessesThisRound']
        ];
    }

    /**
     * Returns an array with information about crawls - total attempts,
     * successes, and successes this round
     *
     * @return array
     */
    public function getPageProcessInfo()
    {
        return [
            'attempts' => $this->data['pageProcessAttempts'],
            'successes' => $this->data['pageProcessSuccesses'],
            'successesThisRound' => $this->data['pageProcessSuccessesThisRound']
        ];
    }

    /**
     * The maximum number of crawl repeats. By default (maxRounds=0) repeating
     * crawls will continue indefinitely.
     *
     * @return int
     */
    public function getMaxRounds()
    {
        return (int)$this->data['maxRounds'];
    }

    /**
     * The number of days as a floating-point (e.g. repeat=7.0) to repeat this
     * crawl. By default crawls will not be repeated.
     *
     * @return float
     */
    public function getRepeat()
    {
        return (float)$this->data['repeat'];
    }

    /**
     * Wait this many seconds between each URL crawled from a single IP address.
     * Number of seconds as an integer or floating-point number
     * (e.g., crawlDelay=0.25).
     *
     * @return float
     */
    public function getCrawlDelay()
    {
        return (float)$this->data['crawlDelay'];
    }

    /**
     * Whether or not the job was set to respect robots.txt
     *
     * @return bool
     */
    public function getObeyRobots()
    {
        return (bool)$this->data['obeyRobots'];
    }

    /**
     * How many rounds were completed with the job so far
     *
     * @return int
     */
    public function getRoundsCompleted()
    {
        return (int)$this->data['roundsCompleted'];
    }

    /**
     * Returns timestamp of when next crawl round is about to start or 0 if none
     *
     * @return int
     */
    public function getRoundStartTime()
    {
        return (int)$this->data['roundStartTime'];
    }

    /**
     * Returns timestamp of current time
     *
     * @return int
     */
    public function getCurrentTime()
    {
        return (int)$this->data['currentTime'];
    }

    /**
     * Returns timestamp of current time, UTC.
     * Should be the same as getCurrentTime
     *
     * @return int
     */
    public function getCurrentTimeUTC()
    {
        return (int)$this->data['currentTimeUTC'];
    }

    /**
     * The API URL is the URL of the API used to process pages found in the
     * crawl. If the job was created with this Diffbot lib, then it was
     * automatically built from a pre-configured API instance
     *
     * The API URL will be URL decoded, whereas it is submitted encoded.
     *
     * @return string
     */
    public function getApiUrl()
    {
        return (string)$this->data['apiUrl'];
    }

    /**
     * @see \Swader\Diffbot\Api\Crawl::setUrlCrawlPattern
     * @return string
     */
    public function getUrlCrawlPattern()
    {
        return (string)$this->data['urlCrawlPattern'];
    }

    /**
     * @see \Swader\Diffbot\Api\Crawl::setUrlProcessPattern
     * @return string
     */
    public function getUrlProcessPattern()
    {
        return (string)$this->data['urlProcessPattern'];
    }

    /**
     * @see \Swader\Diffbot\Api\Crawl::setPageProcessPattern
     * @return string
     */
    public function getPageProcessPattern()
    {
        return (string)$this->data['pageProcessPattern'];
    }

    /**
     * @see \Swader\Diffbot\Api\Crawl::setUrlCrawlRegex
     *
     * @return string
     */
    public function getUrlCrawlRegex()
    {
        return (string)$this->data['urlCrawlRegEx'];
    }

    /**
     * @see \Swader\Diffbot\Api\Crawl::setUrlProcessRegex
     *
     * @return string
     */
    public function getUrlProcessRegex()
    {
        return (string)$this->data['urlProcessRegEx'];
    }

    /**
     * @see \Swader\Diffbot\Api\Crawl::setMaxHops
     *
     * @return int
     */
    public function getMaxHops()
    {
        return (int)$this->data['maxHops'];
    }

    /**
     * Returns the link to the dataset the job produced.
     *
     * Accepted arguments are: "json", "csv" and "debug".
     * It is important to be aware of the difference between the types.
     * See "Retrieving Bulk Data" in link.
     *
     * @see https://www.diffbot.com/dev/docs/crawl/api.jsp
     *
     * @param string $type
     * @return string
     * @throws DiffbotException
     */
    public function getDownloadUrl($type = "json")
    {
        switch ($type) {
            case "json":
                return $this->data['downloadJson'];
            case "debug":
                return $this->data['downloadUrls'];
            case "csv":
                return rtrim($this->data['downloadJson'], '.json') . '.csv';
            default:
                break;
        }

        throw new \InvalidArgumentException(
            'Only json, debug, or csv download link available. You asked for: '
            . $type);
    }

    /**
     * Returns the email that was set to be notified after job's completion
     *
     * @return string
     */
    public function getNotifyEmail()
    {
        return (string)$this->data['notifyEmail'];
    }

    /**
     * Returns the webhook that was set to be pinged after job's completion
     *
     * @return string
     */
    public function getNotifyWebhook()
    {
        return (string)$this->data['notifyWebhook'];
    }
}

1		<?php
2
3		namespace Swader\Diffbot\Abstracts;
4
5		use Swader\Diffbot\Exceptions\DiffbotException;
6
7		abstract class Job extends Entity
8		{
9
10		/**
11		* Returns the name of the crawljob
12		* @return string
13		*/
14	1	public function getName()
15		{
16	1	return (string)$this->data['name'];
17		}
18
19		/**
20		* Should always return either "crawl" or "bulk"
21		* @return string
22		*/
23	2	public function getType()
24		{
25	2	return $this->data['type'];
26		}
27
28		/**
29		* Timestamp of job creation
30		*
31		* @return int
32		*/
33	1	public function getJobCreationTimeUTC()
34		{
35	1	return (isset($this->data['jobCreationTimeUTC']))
36	1	? (int)$this->data['jobCreationTimeUTC'] : null;
37		}
38
39		/**
40		* Timestamp of job completion
41		*
42		* @return int
43		*/
44	1	public function getJobCompletionTimeUTC()
45		{
46	1	return (isset($this->data['jobCompletionTimeUTC']))
47	1	? (int)$this->data['jobCompletionTimeUTC'] : null;
48		}
49
50		/**
51		* Possible statuses
52		*
53		* 0 Job is initializing
54		* 1 Job has reached maxRounds limit
55		* 2 Job has reached maxToCrawl limit
56		* 3 Job has reached maxToProcess limit
57		* 4 Next round to start in _____ seconds
58		* 5 No URLs were added to the crawl
59		* 6 Job paused
60		* 7 Job in progress
61		* 8 All crawling temporarily paused by root administrator for maintenance.
62		* 9 Job has completed and no repeat is scheduled
63		*
64		* @return array
65		*/
66	3	public function getJobStatus()
67		{
68	3	return (isset($this->data['jobStatus']))
69	3	? $this->data['jobStatus'] : [];
70		}
71
72		/**
73		* True or false, depending on whether "job complete" notification was sent
74		*
75		* @return bool
76		*/
77	1	public function getNotificationSent()
78		{
79	1	return (bool)$this->data['sentJobDoneNotification'];
80		}
81
82		/**
83		* Number of objects found
84		*
85		* @return int
86		*/
87	2	public function getObjectsFound()
88		{
89	2	return (int)$this->data['objectsFound'];
90		}
91
92		/**
93		* Number of URLs harvested
94		*
95		* @return int
96		*/
97	2	public function getUrlsHarvested()
98		{
99	2	return (int)$this->data['urlsHarvested'];
100		}
101
102		/**
103		* Returns an array with information about crawls - total attempts,
104		* successes, and successes this round
105		*
106		* @return array
107		*/
108	3	public function getPageCrawlInfo()
109		{
110		return [
111	3	'attempts' => $this->data['pageCrawlAttempts'],
112	3	'successes' => $this->data['pageCrawlSuccesses'],
113	3	'successesThisRound' => $this->data['pageCrawlSuccessesThisRound']
114	3	];
115		}
116
117		/**
118		* Returns an array with information about crawls - total attempts,
119		* successes, and successes this round
120		*
121		* @return array
122		*/
123	2	public function getPageProcessInfo()
124		{
125		return [
126	2	'attempts' => $this->data['pageProcessAttempts'],
127	2	'successes' => $this->data['pageProcessSuccesses'],
128	2	'successesThisRound' => $this->data['pageProcessSuccessesThisRound']
129	2	];
130		}
131
132		/**
133		* The maximum number of crawl repeats. By default (maxRounds=0) repeating
134		* crawls will continue indefinitely.
135		*
136		* @return int
137		*/
138	1	public function getMaxRounds()
139		{
140	1	return (int)$this->data['maxRounds'];
141		}
142
143		/**
144		* The number of days as a floating-point (e.g. repeat=7.0) to repeat this
145		* crawl. By default crawls will not be repeated.
146		*
147		* @return float
148		*/
149	1	public function getRepeat()
150		{
151	1	return (float)$this->data['repeat'];
152		}
153
154		/**
155		* Wait this many seconds between each URL crawled from a single IP address.
156		* Number of seconds as an integer or floating-point number
157		* (e.g., crawlDelay=0.25).
158		*
159		* @return float
160		*/
161	1	public function getCrawlDelay()
162		{
163	1	return (float)$this->data['crawlDelay'];
164		}
165
166		/**
167		* Whether or not the job was set to respect robots.txt
168		*
169		* @return bool
170		*/
171	1	public function getObeyRobots()
172		{
173	1	return (bool)$this->data['obeyRobots'];
174		}
175
176		/**
177		* How many rounds were completed with the job so far
178		*
179		* @return int
180		*/
181	1	public function getRoundsCompleted()
182		{
183	1	return (int)$this->data['roundsCompleted'];
184		}
185
186		/**
187		* Returns timestamp of when next crawl round is about to start or 0 if none
188		*
189		* @return int
190		*/
191	2	public function getRoundStartTime()
192		{
193	2	return (int)$this->data['roundStartTime'];
194		}
195
196		/**
197		* Returns timestamp of current time
198		*
199		* @return int
200		*/
201	2	public function getCurrentTime()
202		{
203	2	return (int)$this->data['currentTime'];
204		}
205
206		/**
207		* Returns timestamp of current time, UTC.
208		* Should be the same as getCurrentTime
209		*
210		* @return int
211		*/
212	1	public function getCurrentTimeUTC()
213		{
214	1	return (int)$this->data['currentTimeUTC'];
215		}
216
217		/**
218		* The API URL is the URL of the API used to process pages found in the
219		* crawl. If the job was created with this Diffbot lib, then it was
220		* automatically built from a pre-configured API instance
221		*
222		* The API URL will be URL decoded, whereas it is submitted encoded.
223		*
224		* @return string
225		*/
226	1	public function getApiUrl()
227		{
228	1	return (string)$this->data['apiUrl'];
229		}
230
231		/**
232		* @see \Swader\Diffbot\Api\Crawl::setUrlCrawlPattern
233		* @return string
234		*/
235	1	public function getUrlCrawlPattern()
236		{
237	1	return (string)$this->data['urlCrawlPattern'];
238		}
239
240		/**
241		* @see \Swader\Diffbot\Api\Crawl::setUrlProcessPattern
242		* @return string
243		*/
244	1	public function getUrlProcessPattern()
245		{
246	1	return (string)$this->data['urlProcessPattern'];
247		}
248
249		/**
250		* @see \Swader\Diffbot\Api\Crawl::setPageProcessPattern
251		* @return string
252		*/
253	1	public function getPageProcessPattern()
254		{
255	1	return (string)$this->data['pageProcessPattern'];
256		}
257
258		/**
259		* @see \Swader\Diffbot\Api\Crawl::setUrlCrawlRegex
260		*
261		* @return string
262		*/
263	1	public function getUrlCrawlRegex()
264		{
265	1	return (string)$this->data['urlCrawlRegEx'];
266		}
267
268		/**
269		* @see \Swader\Diffbot\Api\Crawl::setUrlProcessRegex
270		*
271		* @return string
272		*/
273	1	public function getUrlProcessRegex()
274		{
275	1	return (string)$this->data['urlProcessRegEx'];
276		}
277
278		/**
279		* @see \Swader\Diffbot\Api\Crawl::setMaxHops
280		*
281		* @return int
282		*/
283	1	public function getMaxHops()
284		{
285	1	return (int)$this->data['maxHops'];
286		}
287
288		/**
289		* Returns the link to the dataset the job produced.
290		*
291		* Accepted arguments are: "json", "csv" and "debug".
292		* It is important to be aware of the difference between the types.
293		* See "Retrieving Bulk Data" in link.
294		*
295		* @see https://www.diffbot.com/dev/docs/crawl/api.jsp
296		*
297		* @param string $type
298		* @return string
299		* @throws DiffbotException
300		*/
301	2	public function getDownloadUrl($type = "json")
302		{
303		switch ($type) {
304	2	case "json":
305	1	return $this->data['downloadJson'];
306	2	case "debug":
307	1	return $this->data['downloadUrls'];
308	2	case "csv":
309	1	return rtrim($this->data['downloadJson'], '.json') . '.csv';
310	1	default:
311	1	break;
312	1	}
313
314	1	throw new \InvalidArgumentException(
315		'Only json, debug, or csv download link available. You asked for: '
316	1	. $type);
317		}
318
319		/**
320		* Returns the email that was set to be notified after job's completion
321		*
322		* @return string
323		*/
324	1	public function getNotifyEmail()
325		{
326	1	return (string)$this->data['notifyEmail'];
327		}
328
329		/**
330		* Returns the webhook that was set to be pinged after job's completion
331		*
332		* @return string
333		*/
334	1	public function getNotifyWebhook()
335		{
336	1	return (string)$this->data['notifyWebhook'];
337		}
338		}

Swader / diffbot-php-client

Job A last analyzed 2018-07-04 11:05 UTC

Complexity

Size/Duplication

Coupling/Cohesion

Test Coverage

Importance

28 Methods

Duplication Side-by-Side

Filter issues like

Job A
last analyzed 2018-07-04 11:05 UTC