FileTextExtractor::for_file() - Code Metrics - Inspection of "fix(PDFTextExtractor): Added support for Windows,..." - silverstripe/silverstripe-textextraction - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#28)

unknown

created 2016-05-13 05:17 UTC

FileTextExtractor::for_file() D

↳ Parent: FileTextExtractor

Complexity

Conditions	9
Paths	6

Size

Total Lines	27
Code Lines	13

Duplication

Lines	0
Ratio	0 %

Importance

Changes	6
Bugs	1	Features	1

Metric	Value
c	6
b	1
f	1
dl	0
loc	27
rs	4.909
cc	9
eloc	13
nc	6
nop	1

<?php

/**
 * A decorator for File or a subclass that provides a method for extracting full-text from the file's external contents.
 * @author mstephens
 *
 */
abstract class FileTextExtractor extends Object
namespace YourVendor;

class YourClass { }
{
    /**
     * Set priority from 0-100.
     * The highest priority extractor for a given content type will be selected.
     *
     * @config
     * @var integer
     */
    private static $priority = 50;


    /**
     * Cache of extractor class names, sorted by priority
     *
     * @var array
     */
    protected static $sorted_extractor_classes = null;

    /**
     * Gets the list of prioritised extractor classes
     *
     * @return array
     */
    protected static function get_extractor_classes()
    {
        // Check cache
        if (self::$sorted_extractor_classes) {

            return self::$sorted_extractor_classes;
        }
        
        // Generate the sorted list of extractors on demand.
        $classes = ClassInfo::subclassesFor("FileTextExtractor");
        array_shift($classes);
        $classPriorities = array();
        foreach ($classes as $class) {
            $classPriorities[$class] = Config::inst()->get($class, 'priority');
        }
        arsort($classPriorities);

        // Save classes
        $sortedClasses = array_keys($classPriorities);
        return self::$sorted_extractor_classes = $sortedClasses;
    }

    /**
     * Get the text file extractor for the given class
     *
     * @param string $class
     * @return FileTextExtractor
     */
    protected static function get_extractor($class)
    {
        return Injector::inst()->get($class);
    }

    /**
     * Attempt to detect mime type for given file
     *
     * @param string $path
     * @return string Mime type if found
     */
    protected static function get_mime($path)
    {
        $file = new Symfony\Component\HttpFoundation\File\File($path);

        return $file->getMimeType();
    }

    /**
     * @param string $path
     * @return FileTextExtractor|null
     */
    public static function for_file($path)
    {
        if (!file_exists($path) || is_dir($path)) {
            return;
        }

        $extension = pathinfo($path, PATHINFO_EXTENSION);
        $mime = self::get_mime($path);
        foreach (self::get_extractor_classes() as $className) {
            $extractor = self::get_extractor($className);

            // Skip unavailable extractors
            if (!$extractor->isAvailable()) {
                continue;
            }

            // Check extension
            if ($extension && $extractor->supportsExtension($extension)) {
                return $extractor;
            }

            // Check mime
            if ($mime && $extractor->supportsMime($mime)) {
                return $extractor;
            }
        }
    }

    /**
     * Checks if the extractor is supported on the current environment,
     * for example if the correct binaries or libraries are available.
     * 
     * @return boolean
     */
    abstract public function isAvailable();

    /**
     * Determine if this extractor supports the given extension.
     * If support is determined by mime/type only, then this should return false.
     *
     * @param string $extension
     * @return boolean
     */
    abstract public function supportsExtension($extension);

    /**
     * Determine if this extractor suports the given mime type.
     * Will only be called if supportsExtension returns false.
     * 
     * @param string $mime
     * @return boolean
     */
    abstract public function supportsMime($mime);

    /**
     * Given a file path, extract the contents as text.
     * 
     * @param string $path
     * @return string
     */
    abstract public function getContent($path);
}

class FileTextExtractor_Exception extends Exception
namespace YourVendor;

class YourClass { }
{
}


1			<?php
2
3			/**
4			* A decorator for File or a subclass that provides a method for extracting full-text from the file's external contents.
5			* @author mstephens
6			*
7			*/
8			abstract class FileTextExtractor extends Object
			0 ignored issues – show Coding Style Compatibility introduced 2015-11-20 23:53 UTC by Report Bug Copy Issue Report PSR1 recommends that each class must be in a namespace of at least one level to avoid collisions. You can fix this by adding a namespace to your class: namespace YourVendor; class YourClass { } When choosing a vendor namespace, try to pick something that is not too generic to avoid conflicts with other libraries. Loading history...
9			{
10			/**
11			* Set priority from 0-100.
12			* The highest priority extractor for a given content type will be selected.
13			*
14			* @config
15			* @var integer
16			*/
17			private static $priority = 50;
			0 ignored issues – show Unused Code introduced 2015-11-20 23:53 UTC by Report Bug Copy Issue Report The property `$priority` is not used and could be removed. This check marks private properties in classes that are never used. Those properties can be removed. Loading history...
18
19			/**
20			* Cache of extractor class names, sorted by priority
21			*
22			* @var array
23			*/
24			protected static $sorted_extractor_classes = null;
25
26			/**
27			* Gets the list of prioritised extractor classes
28			*
29			* @return array
30			*/
31			protected static function get_extractor_classes()
32			{
33			// Check cache
34			if (self::$sorted_extractor_classes) {
			0 ignored issues – show Bug Best Practice introduced 2015-11-20 23:53 UTC by Report Bug Copy Issue Report The expression `self::$sorted_extractor_classes` of type `array` is implicitly converted to a boolean; are you sure this is intended? If so, consider using `! empty($expr)` instead to make it clear that you intend to check for an array without elements. This check marks implicit conversions of arrays to boolean values in a comparison. While in PHP an empty array is considered to be equal (but not identical) to false, this is not always apparent. Consider making the comparison explicit by using `empty(..)` or `! empty(...)` instead. Loading history...
35			return self::$sorted_extractor_classes;
36			}
37
38			// Generate the sorted list of extractors on demand.
39			$classes = ClassInfo::subclassesFor("FileTextExtractor");
40			array_shift($classes);
41			$classPriorities = array();
42			foreach ($classes as $class) {
43			$classPriorities[$class] = Config::inst()->get($class, 'priority');
44			}
45			arsort($classPriorities);
46
47			// Save classes
48			$sortedClasses = array_keys($classPriorities);
49			return self::$sorted_extractor_classes = $sortedClasses;
50			}
51
52			/**
53			* Get the text file extractor for the given class
54			*
55			* @param string $class
56			* @return FileTextExtractor
57			*/
58			protected static function get_extractor($class)
59			{
60			return Injector::inst()->get($class);
61			}
62
63			/**
64			* Attempt to detect mime type for given file
65			*
66			* @param string $path
67			* @return string Mime type if found
68			*/
69			protected static function get_mime($path)
70			{
71			$file = new Symfony\Component\HttpFoundation\File\File($path);
72
73			return $file->getMimeType();
74			}
75
76			/**
77			* @param string $path
78			* @return FileTextExtractor\|null
79			*/
80			public static function for_file($path)
81			{
82			if (!file_exists($path) \|\| is_dir($path)) {
83			return;
84			}
85
86			$extension = pathinfo($path, PATHINFO_EXTENSION);
87			$mime = self::get_mime($path);
88			foreach (self::get_extractor_classes() as $className) {
89			$extractor = self::get_extractor($className);
90
91			// Skip unavailable extractors
92			if (!$extractor->isAvailable()) {
93			continue;
94			}
95
96			// Check extension
97			if ($extension && $extractor->supportsExtension($extension)) {
98			return $extractor;
99			}
100
101			// Check mime
102			if ($mime && $extractor->supportsMime($mime)) {
103			return $extractor;
104			}
105			}
106			}
107
108			/**
109			* Checks if the extractor is supported on the current environment,
110			* for example if the correct binaries or libraries are available.
111			*
112			* @return boolean
113			*/
114			abstract public function isAvailable();
115
116			/**
117			* Determine if this extractor supports the given extension.
118			* If support is determined by mime/type only, then this should return false.
119			*
120			* @param string $extension
121			* @return boolean
122			*/
123			abstract public function supportsExtension($extension);
124
125			/**
126			* Determine if this extractor suports the given mime type.
127			* Will only be called if supportsExtension returns false.
128			*
129			* @param string $mime
130			* @return boolean
131			*/
132			abstract public function supportsMime($mime);
133
134			/**
135			* Given a file path, extract the contents as text.
136			*
137			* @param string $path
138			* @return string
139			*/
140			abstract public function getContent($path);
141			}
142
143			class FileTextExtractor_Exception extends Exception
			0 ignored issues – show Coding Style Compatibility introduced 2015-11-20 23:53 UTC by Report Bug Copy Issue Report PSR1 recommends that each class should be in its own file to aid autoloaders. Having each class in a dedicated file usually plays nice with PSR autoloaders and is therefore a well established practice. If you use other autoloaders, you might not want to follow this rule. Loading history... Coding Style Compatibility introduced 2015-11-20 23:53 UTC by Report Bug Copy Issue Report PSR1 recommends that each class must be in a namespace of at least one level to avoid collisions. You can fix this by adding a namespace to your class: namespace YourVendor; class YourClass { } When choosing a vendor namespace, try to pick something that is not too generic to avoid conflicts with other libraries. Loading history...
144			{
145			}
146

silverstripe / silverstripe-textextraction

Pull Request — master (#28)

FileTextExtractor::for_file() D

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like