PDFTextExtractor::cleanupLigatures() - Code Metrics - Inspection of "API Whitelist bin paths for pdftotext" - silverstripe/silverstripe-textextraction - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#27)

by Damian

created 2016-02-25 03:28 UTC

PDFTextExtractor::cleanupLigatures() A

↳ Parent: PDFTextExtractor

Complexity

Conditions	1
Paths	1

Size

Total Lines	13
Code Lines	10

Duplication

Lines	0
Ratio	0 %

Metric	Value
dl	0
loc	13
rs	9.4285
cc	1
eloc	10
nc	1
nop	1

<?php

/**
 * Text extractor that calls pdftotext to do the conversion.
 * @author mstephens
 *
 */
class PDFTextExtractor extends FileTextExtractor
namespace YourVendor;

class YourClass { }
{
    /**
     * Set to bin path this extractor can execute
     *
     * @var string
     */
    private static $binary_location = null;


    /**
     * Used if binary_location isn't set.
     * List of locations to search for a given binary in
     *
     * @config
     * @var array
     */
    private static $search_binary_locations = array(

        '/usr/bin',
        '/usr/local/bin',
    );

    public function isAvailable()
    {
        $bin = $this->bin('pdftotext');
        return (file_exists($bin) && is_executable($bin));
    }

    public function supportsExtension($extension)
    {
        return strtolower($extension) === 'pdf';
    }

    public function supportsMime($mime)
    {
        return in_array(
            strtolower($mime),
            array(
                'application/pdf',
                'application/x-pdf',
                'application/x-bzpdf',
                'application/x-gzpdf'
            )
        );
    }

    /**
     * Accessor to get the location of the binary
     *
     * @param string $program Name of binary
     * @return string
     */
    protected function bin($program = '')
    {
        // Get list of allowed search paths
        if ($location = $this->config()->binary_location) {
            $locations = array($location);
        } else {
            $locations = $this->config()->search_binary_locations;
        }

        // Find program in each path
        foreach($locations as $location) {
            $path = "{$location}/{$program}";
            if(file_exists($path)) {
                return $path;
            }
        }
        
        // Not found
        return null;
    }

    public function getContent($path)
    {
        if (!$path) {
            return "";
        } // no file
        $content = $this->getRawOutput($path);
        return $this->cleanupLigatures($content);
    }

    /**
     * Invoke pdftotext with the given path
     *
     * @param string $path
     * @return string Output
     * @throws FileTextExtractor_Exception
     */
    protected function getRawOutput($path)
    {
        exec(sprintf('%s %s - 2>&1', $this->bin('pdftotext'), escapeshellarg($path)), $content, $err);
        if ($err) {
0   == false // true
0   == null  // true
123 == false // false
123 == null  // false

// It is often better to use strict comparison
0 === false // false
0 === null  // false
            throw new FileTextExtractor_Exception(sprintf(
                'PDFTextExtractor->getContent() failed for %s: %s',
                $path,
                implode('', $err)
            ));
        }
        return implode('', $content);
    }

    /**
     * Removes utf-8 ligatures.
     *
     * @link http://en.wikipedia.org/wiki/Typographic_ligature#Computer_typesetting
     *
     * @param string $input
     * @return string
     */
    protected function cleanupLigatures($input)
    {
        $mapping = array(
            'ﬀ' => 'ff',
            'ﬁ' => 'fi',
            'ﬂ' => 'fl',
            'ﬃ' => 'ffi',
            'ﬄ' => 'ffl',
            'ﬅ' => 'ft',
            'ﬆ' => 'st'
        );
        return str_replace(array_keys($mapping), array_values($mapping), $input);
    }
}


1			<?php
2
3			/**
4			* Text extractor that calls pdftotext to do the conversion.
5			* @author mstephens
6			*
7			*/
8			class PDFTextExtractor extends FileTextExtractor
			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 to bin path this extractor can execute
12			*
13			* @var string
14			*/
15			private static $binary_location = null;
			0 ignored issues – show Unused Code introduced 2016-02-25 03:05 UTC by Report Bug Copy Issue Report The property `$binary_location` 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...
16
17			/**
18			* Used if binary_location isn't set.
19			* List of locations to search for a given binary in
20			*
21			* @config
22			* @var array
23			*/
24			private static $search_binary_locations = array(
			0 ignored issues – show Unused Code introduced 2016-02-25 03:05 UTC by Report Bug Copy Issue Report The property `$search_binary_locations` 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...
25			'/usr/bin',
26			'/usr/local/bin',
27			);
28
29			public function isAvailable()
30			{
31			$bin = $this->bin('pdftotext');
32			return (file_exists($bin) && is_executable($bin));
33			}
34
35			public function supportsExtension($extension)
36			{
37			return strtolower($extension) === 'pdf';
38			}
39
40			public function supportsMime($mime)
41			{
42			return in_array(
43			strtolower($mime),
44			array(
45			'application/pdf',
46			'application/x-pdf',
47			'application/x-bzpdf',
48			'application/x-gzpdf'
49			)
50			);
51			}
52
53			/**
54			* Accessor to get the location of the binary
55			*
56			* @param string $program Name of binary
57			* @return string
58			*/
59			protected function bin($program = '')
60			{
61			// Get list of allowed search paths
62			if ($location = $this->config()->binary_location) {
63			$locations = array($location);
64			} else {
65			$locations = $this->config()->search_binary_locations;
66			}
67
68			// Find program in each path
69			foreach($locations as $location) {
70			$path = "{$location}/{$program}";
71			if(file_exists($path)) {
72			return $path;
73			}
74			}
75
76			// Not found
77			return null;
78			}
79
80			public function getContent($path)
81			{
82			if (!$path) {
83			return "";
84			} // no file
85			$content = $this->getRawOutput($path);
86			return $this->cleanupLigatures($content);
87			}
88
89			/**
90			* Invoke pdftotext with the given path
91			*
92			* @param string $path
93			* @return string Output
94			* @throws FileTextExtractor_Exception
95			*/
96			protected function getRawOutput($path)
97			{
98			exec(sprintf('%s %s - 2>&1', $this->bin('pdftotext'), escapeshellarg($path)), $content, $err);
99			if ($err) {
			0 ignored issues – show Bug Best Practice introduced 2015-11-20 23:53 UTC by Report Bug Copy Issue Report The expression `$err` of type `integer\|null` is loosely compared to `true`; this is ambiguous if the integer can be zero. You might want to explicitly use `!== null` instead. In PHP, under loose comparison (like `==`, or `!=`, or `switch` conditions), values of different types might be equal. For `integer` values, zero is a special case, in particular the following results might be unexpected: 0 == false // true 0 == null // true 123 == false // false 123 == null // false // It is often better to use strict comparison 0 === false // false 0 === null // false Loading history...
100			throw new FileTextExtractor_Exception(sprintf(
101			'PDFTextExtractor->getContent() failed for %s: %s',
102			$path,
103			implode('', $err)
104			));
105			}
106			return implode('', $content);
107			}
108
109			/**
110			* Removes utf-8 ligatures.
111			*
112			* @link http://en.wikipedia.org/wiki/Typographic_ligature#Computer_typesetting
113			*
114			* @param string $input
115			* @return string
116			*/
117			protected function cleanupLigatures($input)
118			{
119			$mapping = array(
120			'ﬀ' => 'ff',
121			'ﬁ' => 'fi',
122			'ﬂ' => 'fl',
123			'ﬃ' => 'ffi',
124			'ﬄ' => 'ffl',
125			'ﬅ' => 'ft',
126			'ﬆ' => 'st'
127			);
128			return str_replace(array_keys($mapping), array_values($mapping), $input);
129			}
130			}
131

silverstripe / silverstripe-textextraction

Pull Request — master (#27)

PDFTextExtractor::cleanupLigatures() A

Complexity

Size

Duplication

Duplication Side-by-Side

Filter issues like