SniffHeaderByDataType::getType() - Code Metrics - Inspection of "Release v0.3" - nozavroni/csvelte - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#183)

by Luke

created 2018-07-20 00:54 UTC

SniffHeaderByDataType::getType() B

↳ Parent: SniffHeaderByDataType

Complexity

Conditions	9
Paths	9

Size

Total Lines

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	16
CRAP Score	9.648

Importance

Changes

Metric	Value
cc	9
nc	9
nop	1
dl	0
loc	28
ccs	16
cts	20
cp	0.8
crap	9.648
rs	8.0555
c	0
b	0
f	0

<?php
/**
 * CSVelte: Slender, elegant CSV for PHP
 *
 * Inspired by Python's CSV module and Frictionless Data and the W3C's CSV
 * standardization efforts, CSVelte was written in an effort to take all the
 * suck out of working with CSV.
 *
 * @copyright Copyright (c) 2018 Luke Visinoni
 * @author    Luke Visinoni <[email protected]>
 * @license   See LICENSE file (MIT license)
 */
namespace CSVelte\Sniffer;

use function Noz\collect;
use function Stringy\create as s;
use Stringy\Stringy;

class SniffHeaderByDataType extends AbstractSniffer
{
     /**
     * Guess whether there is a header row
     *
     * Guesses whether the data has a header row by comparing the data types of the first row with the types of
     * corresponding columns in other rows.
     *
     * @note Unlike the original version of this method, this one will be used to ALSO determine HOW MANY header rows
     *       there likely are. So, compare the header to rows at the END of the sample.
     *
     * @param string $data The data to analyze
     *
     * @return bool
     */
    public function sniff($data)
    {
        $delimiter = $this->getOption('delimiter');
        $data = s($data);
        $lines = collect($data->lines())
            ->map(function($line) use ($delimiter) {
                return s($this->replaceQuotedSpecialChars($line, $delimiter));
            });
        $header = collect($lines->shift()->split($delimiter))
            ->map(function($val){ return $this->unQuote($val); })
            ->map(function($val) {
                return [
                    'type' => $this->getType($val),
                    'length' => s($val)->length()
                ];
            });
        $lines->pop(); // get rid of the last line because it may be incomplete
        $comparison = $lines->slice(0, 10)
            ->map(function($line, $line_no) use ($header, $delimiter) {

                /** @var Stringy $line */
                $values = collect($line->split($delimiter));
                return $values->map(function($str, $pos) use ($header) {
                    $comp = $header->get($pos);
                    $type = $this->getType($str);
                    return [
                        // true if same, false otherwise

                        'type' => $comp['type'] == $type,
                        // return the difference in length
                        'length' => $comp['length'] - s($str)->length()
                    ];
                });
            });

        $hasHeader = collect();
        $comparison->each(function($line) use ($hasHeader) {
            foreach ($line as $val) {
                if ($val['type']) {
                    $hasHeader->add(1);
                } else {
                    if ($val['length'] === 0) {
                        $hasHeader->add(1);
                    } else {
                        $hasHeader->add(-1);
                    }
                }
            }
        });

        return $hasHeader->sum() > 0;
class Author {
    private $name;

    public function __construct($name) {
        $this->name = $name;
    }

    public function getName() {
        return $this->name;
    }
}

abstract class Post {
    public function getAuthor() {
        return 'Johannes';
    }
}

class BlogPost extends Post {
    public function getAuthor() {
        return new Author('Johannes');
    }
}

class ForumPost extends Post { /* ... */ }

function my_function(Post $post) {
    echo strtoupper($post->getAuthor());
}
    }

    protected function getType($value)
    {
        $str = s($value);
        switch (true) {
            case is_numeric($value):
                return 'numeric';
            case is_string($value):
                if (strtotime($value) !== false) {
                    return 'datetime';
                }
                if (preg_match('/^[+-]?[¥£€$]\d+(\.\d+)$/', $value)) {
                    return 'currency';
                }
                if ($str->isAlpha()) {
                    return 'alpha';
                }
                if ($str->isAlphanumeric()) {
                    return 'alnum';
                }
                if ($str->isBlank()) {
                    return 'blank';
                }
                if ($str->isJson()) {
                    return 'json';
                }
        }
        return 'unknown';
    }
}

1		<?php
2		/**
3		* CSVelte: Slender, elegant CSV for PHP
4		*
5		* Inspired by Python's CSV module and Frictionless Data and the W3C's CSV
6		* standardization efforts, CSVelte was written in an effort to take all the
7		* suck out of working with CSV.
8		*
9		* @copyright Copyright (c) 2018 Luke Visinoni
10		* @author Luke Visinoni <[email protected]>
11		* @license See LICENSE file (MIT license)
12		*/
13		namespace CSVelte\Sniffer;
14
15		use function Noz\collect;
16		use function Stringy\create as s;
17		use Stringy\Stringy;
18
19		class SniffHeaderByDataType extends AbstractSniffer
20		{
21		/**
22		* Guess whether there is a header row
23		*
24		* Guesses whether the data has a header row by comparing the data types of the first row with the types of
25		* corresponding columns in other rows.
26		*
27		* @note Unlike the original version of this method, this one will be used to ALSO determine HOW MANY header rows
28		* there likely are. So, compare the header to rows at the END of the sample.
29		*
30		* @param string $data The data to analyze
31		*
32		* @return bool
33		*/
34	1	public function sniff($data)
35		{
36	1	$delimiter = $this->getOption('delimiter');
37	1	$data = s($data);
38	1	$lines = collect($data->lines())
39		->map(function($line) use ($delimiter) {
40	1	return s($this->replaceQuotedSpecialChars($line, $delimiter));
41	1	});
42	1	$header = collect($lines->shift()->split($delimiter))
43		->map(function($val){ return $this->unQuote($val); })
44		->map(function($val) {
45		return [
46	1	'type' => $this->getType($val),
47	1	'length' => s($val)->length()
48	1	];
49	1	});
50	1	$lines->pop(); // get rid of the last line because it may be incomplete
51	1	$comparison = $lines->slice(0, 10)
52		->map(function($line, $line_no) use ($header, $delimiter) {
		0 ignored issues – show Unused Code introduced 2018-07-20 01:01 UTC by Report Bug Copy Issue Report The parameter `$line_no` is not used and could be removed. This check looks from parameters that have been defined for a function or method, but which are not used in the method body. Loading history...
53		/** @var Stringy $line */
54	1	$values = collect($line->split($delimiter));
55		return $values->map(function($str, $pos) use ($header) {
56	1	$comp = $header->get($pos);
57	1	$type = $this->getType($str);
58		return [
59		// true if same, false otherwise
		0 ignored issues – show Unused Code Comprehensibility introduced 2018-07-20 01:01 UTC by Report Bug Copy Issue Report `37%` of this comment could be valid code. Did you maybe forget this after debugging? Sometimes obsolete code just ends up commented out instead of removed. In this case it is better to remove the code once you have checked you do not need it. The code might also have been commented out for debugging purposes. In this case it is vital that someone uncomments it again or your project may behave in very unexpected ways in production. This check looks for comments that seem to be mostly valid code and reports them. Loading history...
60	1	'type' => $comp['type'] == $type,
61		// return the difference in length
62	1	'length' => $comp['length'] - s($str)->length()
63	1	];
64	1	});
65	1	});
66
67	1	$hasHeader = collect();
68	1	$comparison->each(function($line) use ($hasHeader) {
69	1	foreach ($line as $val) {
70	1	if ($val['type']) {
71	1	$hasHeader->add(1);
72	1	} else {
73	1	if ($val['length'] === 0) {
74	1	$hasHeader->add(1);
75	1	} else {
76	1	$hasHeader->add(-1);
77		}
78		}
79	1	}
80	1	});
81
82	1	return $hasHeader->sum() > 0;
		0 ignored issues – show Bug Best Practice introduced 2018-07-20 01:01 UTC by Report Bug Copy Issue Report The return type of `return $hasHeader->sum() > 0;` (`boolean`) is incompatible with the return type declared by the abstract method `CSVelte\Sniffer\AbstractSniffer::sniff` of type `string\|string[]`. If you return a value from a function or method, it should be a sub-type of the type that is given by the parent type f.e. an interface, or abstract method. This is more formally defined by the Lizkov substitution principle, and guarantees that classes that depend on the parent type can use any instance of a child type interchangably. This principle also belongs to the SOLID principles for object oriented design. Let’s take a look at an example: class Author { private $name; public function __construct($name) { $this->name = $name; } public function getName() { return $this->name; } } abstract class Post { public function getAuthor() { return 'Johannes'; } } class BlogPost extends Post { public function getAuthor() { return new Author('Johannes'); } } class ForumPost extends Post { /* ... */ } function my_function(Post $post) { echo strtoupper($post->getAuthor()); } Our function `my_function` expects a `Post` object, and outputs the author of the post. The base class `Post` returns a simple string and outputting a simple string will work just fine. However, the child class `BlogPost` which is a sub-type of `Post` instead decided to return an `object`, and is therefore violating the SOLID principles. If a `BlogPost` were passed to `my_function`, PHP would not complain, but ultimately fail when executing the `strtoupper` call in its body. Loading history...
83		}
84
85	1	protected function getType($value)
86		{
87	1	$str = s($value);
88	1	switch (true) {
89	1	case is_numeric($value):
90	1	return 'numeric';
91	1	case is_string($value):
92	1	if (strtotime($value) !== false) {
93	1	return 'datetime';
94		}
95	1	if (preg_match('/^[+-]?[¥£€$]\d+(\.\d+)$/', $value)) {
96		return 'currency';
97		}
98	1	if ($str->isAlpha()) {
99	1	return 'alpha';
100		}
101	1	if ($str->isAlphanumeric()) {
102		return 'alnum';
103		}
104	1	if ($str->isBlank()) {
105		return 'blank';
106		}
107	1	if ($str->isJson()) {
108		return 'json';
109		}
110	1	}
111	1	return 'unknown';
112		}
113		}

nozavroni / csvelte

Pull Request — master (#183)

SniffHeaderByDataType::getType() B

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like