DiscovererSet::addFilter() - Code Metrics - Inspection of "Feature/cleanup" - mvdbos/php-spider - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#16)

by Matthijs

created 2015-12-29 20:05 UTC

DiscovererSet::addFilter() A

↳ Parent: DiscovererSet

Complexity

Conditions	1
Paths	1

Size

Total Lines	4
Code Lines	2

Duplication

Lines	0
Ratio	0 %

Importance

Changes	1
Bugs	0	Features	0

Metric	Value
c	1
b	0
f	0
dl	0
loc	4
rs	10
cc	1
eloc	2
nc	1
nop	1

<?php

namespace VDB\Spider\Discoverer;

use VDB\Spider\Resource;
use VDB\Spider\Filter\PreFetchFilterInterface;
use VDB\Spider\Uri\FilterableUri;

class DiscovererSet implements \IteratorAggregate
{
    /**
     * @var Discoverer[]
     */
    private $discoverers = array();

    /** @var Filter[] */
    private $filters = array();

    /**
     * @var int maximum crawl depth
     */
    public $maxDepth = 3;

    /**
     * @var array the list of already visited URIs with the depth they were discovered on as value
     */
    private $alreadySeenUris = array();

    public function __construct(array $discoverers = array())
    {
        foreach ($discoverers as $alias => $discoverer) {
            $this->set($discoverer, is_int($alias) ? null : $alias);
        }
    }

    /**
     * @param FilterableUri $uri
     *
     * Mark an Uri as already seen.
     *
     * If it already exists, it is not overwritten, since we want to keep the
     * first depth it was found at.
     */
    private function markSeen(FilterableUri $uri)
    {
        $uriString = $uri->normalize()->toString();
        if (!array_key_exists($uriString, $this->alreadySeenUris)) {
            $this->alreadySeenUris[$uriString] = $uri->getDepthFound();
        }
    }

    /**
     * @return bool Returns true if this URI was found at max depth
     */
    private function isAtMaxDepth(FilterableUri $uri)
    {
        if ($uri->getDepthFound() === $this->maxDepth) {

            return true;
        }
        return false;
    }

    /**
     * @param Resource $resource
     * @return UriInterface[]
     */
    public function discover(Resource $resource)
    {
        $this->markSeen($resource->getUri());


        if ($this->isAtMaxDepth($resource->getUri())) {

            return [];
        }

        $discoveredUris = [];

        foreach ($this->discoverers as $discoverer) {
            $discoveredUris = array_merge($discoveredUris, $discoverer->discover($resource));
        }

        $this->normalize($discoveredUris);
        $this->removeDuplicates($discoveredUris);
        $this->filterAlreadySeen($discoveredUris);
        $this->filter($discoveredUris);

        foreach ($discoveredUris as $uri) {
            $uri->setDepthFound($resource->getUri()->getDepthFound() + 1);
interface User
{
    /** @return string */
    public function getPassword();
}

class MyUser implements User
{
    public function getPassword()
    {
        // return something
    }

    public function getDisplayName()
    {
        // return some name.
    }
}

class AuthSystem
{
    public function authenticate(User $user)
    {
        $this->logger->info(sprintf('Authenticating %s.', $user->getDisplayName()));
        // do something.
    }
}
            $this->markSeen($uri);
        }

        return $discoveredUris;
    }

    /**
     * Sets a discoverer.
     *
     * @param discovererInterface $discoverer The discoverer instance
     * @param string          $alias  An alias

     */
    public function set(DiscovererInterface $discoverer, $alias = null)
    {
        $this->discoverers[$discoverer->getName()] = $discoverer;
        if (null !== $alias) {
            $this->discoverers[$alias] = $discoverer;
        }

        $discoverer->setDiscovererSet($this);
    }

    /**
     * @param PreFetchFilterInterface $filter
     */
    public function addFilter(PreFetchFilterInterface $filter)
    {
        $this->filters[] = $filter;
    }

    /**
     * Returns true if the discoverer is defined.
     *
     * @param string $name The discoverer name
     *
     * @return bool true if the discoverer is defined, false otherwise
     */
    public function has($name)
    {
        return isset($this->discoverers[$name]);
    }

    /**
     * Gets a discoverer.
     *
     * @param string $name The discoverer name
     *
     * @return Discoverer The discoverer instance
     *
     * @throws InvalidArgumentException if the discoverer is not defined
     */
    public function get($name)
    {
        if (!$this->has($name)) {
            throw new \InvalidArgumentException(sprintf('The discoverer "%s" is not defined.', $name));
        }

        return $this->discoverers[$name];
    }

    public function getIterator()
    {
        return new \ArrayIterator($this->discoverers);
    }

    /**
     * @param UriInterface[] $discoveredUris
     */
    private function normalize(array &$discoveredUris)
    {
        foreach ($discoveredUris as &$uri) {
            $uri->normalize();
        }
    }

    /**
     * @param UriInterface[] $discoveredUris
     */
    private function filterAlreadySeen(array &$discoveredUris)
    {
        foreach ($discoveredUris as $k => &$uri) {
            if (array_key_exists($uri->toString(), $this->alreadySeenUris)) {
                unset($discoveredUris[$k]);
            }
        }
    }

    /**
     * @param UriInterface[] $discoveredUris
     */
    private function filter(array &$discoveredUris)
    {
        foreach ($discoveredUris as $k => &$uri) {
            $uri = new FilterableUri($uri);
            foreach ($this->filters as $filter) {
                if ($filter->match($uri)) {
                    unset($discoveredUris[$k]);
                }
            }
        }
    }

    /**
     * @param UriInterface[] $discoveredUris
     */
    private function removeDuplicates(array &$discoveredUris)
    {
        // make sure there are no duplicates in the list
        $tmp = array();
        /** @var Uri $uri */
        foreach ($discoveredUris as $k => $uri) {
            $tmp[$k] = $uri->toString();
        }

        // Find duplicates in temporary array
        $tmp = array_unique($tmp);

        // Remove the duplicates from original array
        foreach ($discoveredUris as $k => $uri) {
            if (!array_key_exists($k, $tmp)) {
                unset($discoveredUris[$k]);
            }
        }
    }
}


1			<?php
2
3			namespace VDB\Spider\Discoverer;
4
5			use VDB\Spider\Resource;
6			use VDB\Spider\Filter\PreFetchFilterInterface;
7			use VDB\Spider\Uri\FilterableUri;
8
9			class DiscovererSet implements \IteratorAggregate
10			{
11			/**
12			* @var Discoverer[]
13			*/
14			private $discoverers = array();
15
16			/** @var Filter[] */
17			private $filters = array();
18
19			/**
20			* @var int maximum crawl depth
21			*/
22			public $maxDepth = 3;
23
24			/**
25			* @var array the list of already visited URIs with the depth they were discovered on as value
26			*/
27			private $alreadySeenUris = array();
28
29			public function __construct(array $discoverers = array())
30			{
31			foreach ($discoverers as $alias => $discoverer) {
32			$this->set($discoverer, is_int($alias) ? null : $alias);
33			}
34			}
35
36			/**
37			* @param FilterableUri $uri
38			*
39			* Mark an Uri as already seen.
40			*
41			* If it already exists, it is not overwritten, since we want to keep the
42			* first depth it was found at.
43			*/
44			private function markSeen(FilterableUri $uri)
45			{
46			$uriString = $uri->normalize()->toString();
47			if (!array_key_exists($uriString, $this->alreadySeenUris)) {
48			$this->alreadySeenUris[$uriString] = $uri->getDepthFound();
49			}
50			}
51
52			/**
53			* @return bool Returns true if this URI was found at max depth
54			*/
55			private function isAtMaxDepth(FilterableUri $uri)
56			{
57			if ($uri->getDepthFound() === $this->maxDepth) {
			0 ignored issues – show Unused Code introduced 2015-12-29 18:36 UTC by Report Bug Copy Issue Report This `if` statement, and the following `return` statement can be replaced with `return $uri->getDepthFound() === $this->maxDepth;`. Loading history...
58			return true;
59			}
60			return false;
61			}
62
63			/**
64			* @param Resource $resource
65			* @return UriInterface[]
66			*/
67			public function discover(Resource $resource)
68			{
69			$this->markSeen($resource->getUri());
			0 ignored issues – show Compatibility introduced 2015-12-29 18:36 UTC by Report Bug Copy Issue Report `$resource->getUri()` of type `object<VDB\Uri\UriInterface>` is not a sub-type of `object<VDB\Spider\Uri\FilterableUri>`. It seems like you assume a concrete implementation of the interface `VDB\Uri\UriInterface` to be always present. This check looks for parameters that are defined as one type in their type hint or doc comment but seem to be used as a narrower type, i.e an implementation of an interface or a subclass. Consider changing the type of the parameter or doing an instanceof check before assuming your parameter is of the expected type. Loading history...
70
71			if ($this->isAtMaxDepth($resource->getUri())) {
			0 ignored issues – show Compatibility introduced 2015-12-29 18:36 UTC by Report Bug Copy Issue Report `$resource->getUri()` of type `object<VDB\Uri\UriInterface>` is not a sub-type of `object<VDB\Spider\Uri\FilterableUri>`. It seems like you assume a concrete implementation of the interface `VDB\Uri\UriInterface` to be always present. This check looks for parameters that are defined as one type in their type hint or doc comment but seem to be used as a narrower type, i.e an implementation of an interface or a subclass. Consider changing the type of the parameter or doing an instanceof check before assuming your parameter is of the expected type. Loading history...
72			return [];
73			}
74
75			$discoveredUris = [];
76
77			foreach ($this->discoverers as $discoverer) {
78			$discoveredUris = array_merge($discoveredUris, $discoverer->discover($resource));
79			}
80
81			$this->normalize($discoveredUris);
82			$this->removeDuplicates($discoveredUris);
83			$this->filterAlreadySeen($discoveredUris);
84			$this->filter($discoveredUris);
85
86			foreach ($discoveredUris as $uri) {
87			$uri->setDepthFound($resource->getUri()->getDepthFound() + 1);
			0 ignored issues – show Bug introduced 2015-12-29 18:36 UTC by Report Bug Copy Issue Report It seems like you code against a concrete implementation and not the interface `VDB\Uri\UriInterface` as the method `getDepthFound()` does only exist in the following implementations of said interface: `VDB\Spider\Uri\FilterableUri`. Let’s take a look at an example: interface User { /** @return string / public function getPassword(); } class MyUser implements User { public function getPassword() { // return something } public function getDisplayName() { // return some name. } } class AuthSystem { public function authenticate(User $user) { $this->logger->info(sprintf('Authenticating %s.', $user->getDisplayName())); // do something. } } In the above example, the authenticate() method works fine as long as you just pass instances of MyUser. However, if you now also want to pass a different implementation of User which does not have a getDisplayName() method, the code will break. Available Fixes Change the type-hint for the parameter: class AuthSystem { public function authenticate(MyUser $user) { / ... / } } Add an additional type-check: class AuthSystem { public function authenticate(User $user) { if ($user instanceof MyUser) { $this->logger->info(/* ... /); } // or alternatively if ( ! $user instanceof MyUser) { throw new \LogicException( '$user must be an instance of MyUser, ' .'other instances are not supported.' ); } } } Note:* PHP Analyzer uses reverse abstract interpretation to narrow down the types inside the if block in such a case. Add the method to the interface: interface User { /** @return string / public function getPassword(); /* @return string */ public function getDisplayName(); } Loading history...
88			$this->markSeen($uri);
89			}
90
91			return $discoveredUris;
92			}
93
94			/**
95			* Sets a discoverer.
96			*
97			* @param discovererInterface $discoverer The discoverer instance
98			* @param string $alias An alias
			0 ignored issues – show Documentation introduced 2015-12-29 13:45 UTC by Report Bug Copy Issue Report Should the type for parameter `$alias` not be `string\|null`? This check looks for `@param` annotations where the type inferred by our type inference engine differs from the declared type. It makes a suggestion as to what type it considers more descriptive. Most often this is a case of a parameter that can be null in addition to its declared types. Loading history...
99			*/
100			public function set(DiscovererInterface $discoverer, $alias = null)
101			{
102			$this->discoverers[$discoverer->getName()] = $discoverer;
103			if (null !== $alias) {
104			$this->discoverers[$alias] = $discoverer;
105			}
106
107			$discoverer->setDiscovererSet($this);
108			}
109
110			/**
111			* @param PreFetchFilterInterface $filter
112			*/
113			public function addFilter(PreFetchFilterInterface $filter)
114			{
115			$this->filters[] = $filter;
116			}
117
118			/**
119			* Returns true if the discoverer is defined.
120			*
121			* @param string $name The discoverer name
122			*
123			* @return bool true if the discoverer is defined, false otherwise
124			*/
125			public function has($name)
126			{
127			return isset($this->discoverers[$name]);
128			}
129
130			/**
131			* Gets a discoverer.
132			*
133			* @param string $name The discoverer name
134			*
135			* @return Discoverer The discoverer instance
136			*
137			* @throws InvalidArgumentException if the discoverer is not defined
138			*/
139			public function get($name)
140			{
141			if (!$this->has($name)) {
142			throw new \InvalidArgumentException(sprintf('The discoverer "%s" is not defined.', $name));
143			}
144
145			return $this->discoverers[$name];
146			}
147
148			public function getIterator()
149			{
150			return new \ArrayIterator($this->discoverers);
151			}
152
153			/**
154			* @param UriInterface[] $discoveredUris
155			*/
156			private function normalize(array &$discoveredUris)
157			{
158			foreach ($discoveredUris as &$uri) {
159			$uri->normalize();
160			}
161			}
162
163			/**
164			* @param UriInterface[] $discoveredUris
165			*/
166			private function filterAlreadySeen(array &$discoveredUris)
167			{
168			foreach ($discoveredUris as $k => &$uri) {
169			if (array_key_exists($uri->toString(), $this->alreadySeenUris)) {
170			unset($discoveredUris[$k]);
171			}
172			}
173			}
174
175			/**
176			* @param UriInterface[] $discoveredUris
177			*/
178			private function filter(array &$discoveredUris)
179			{
180			foreach ($discoveredUris as $k => &$uri) {
181			$uri = new FilterableUri($uri);
182			foreach ($this->filters as $filter) {
183			if ($filter->match($uri)) {
184			unset($discoveredUris[$k]);
185			}
186			}
187			}
188			}
189
190			/**
191			* @param UriInterface[] $discoveredUris
192			*/
193			private function removeDuplicates(array &$discoveredUris)
194			{
195			// make sure there are no duplicates in the list
196			$tmp = array();
197			/** @var Uri $uri */
198			foreach ($discoveredUris as $k => $uri) {
199			$tmp[$k] = $uri->toString();
200			}
201
202			// Find duplicates in temporary array
203			$tmp = array_unique($tmp);
204
205			// Remove the duplicates from original array
206			foreach ($discoveredUris as $k => $uri) {
207			if (!array_key_exists($k, $tmp)) {
208			unset($discoveredUris[$k]);
209			}
210			}
211			}
212			}
213

mvdbos / php-spider

Pull Request — master (#16)

DiscovererSet::addFilter() A

Complexity

Size

Duplication

Importance

Available Fixes

Duplication Side-by-Side

Filter issues like