Header::getDetails() - Code Metrics - Inspection of "Might avoid invalid characters message" - smalot/pdfparser - Measure and Improve Code Quality continuously with Scrutinizer

Test Failed

Pull Request — master (#510)

by Jeremy

created 2022-01-31 13:21 UTC

Header::getDetails() C

↳ Parent: Header

Complexity

Conditions	12
Paths	28

Size

Total Lines	34
Code Lines	21

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	16
CRAP Score	13.9437

Importance

Changes	1
Bugs	0	Features	0

Metric	Value
cc	12
eloc	21
c	1
b	0
f	0
nc	28
nop	1
dl	0
loc	34
ccs	16
cts	21
cp	0.7619
crap	13.9437
rs	6.9666

How to fix Complexity

<?php

/**
 * @file
 *          This file is part of the PdfParser library.
 *
 * @author  Sébastien MALOT <[email protected]>
 * @date    2017-01-03
 *
 * @license LGPLv3
 * @url     <https://github.com/smalot/pdfparser>
 *
 *  PdfParser is a pdf library written in PHP, extraction oriented.
 *  Copyright (C) 2017 - Sébastien MALOT <[email protected]>
 *
 *  This program is free software: you can redistribute it and/or modify
 *  it under the terms of the GNU Lesser General Public License as published by
 *  the Free Software Foundation, either version 3 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU Lesser General Public License for more details.
 *
 *  You should have received a copy of the GNU Lesser General Public License
 *  along with this program.
 *  If not, see <http://www.pdfparser.org/sites/default/LICENSE.txt>.
 */

namespace Smalot\PdfParser;

use Smalot\PdfParser\Element\ElementArray;
use Smalot\PdfParser\Element\ElementMissing;
use Smalot\PdfParser\Element\ElementStruct;
use Smalot\PdfParser\Element\ElementXRef;

/**
 * Class Header
 */
class Header
{
    /**
     * @var Document
     */
    protected $document = null;

    /**
     * @var Element[]
     */
    protected $elements = null;

    /**
     * @param Element[] $elements list of elements
     * @param Document  $document document
     */
    public function __construct(array $elements = [], ?Document $document = null)
    {
        $this->elements = $elements;
        $this->document = $document;
    }

    public function init()
    {
        foreach ($this->elements as $element) {
            if ($element instanceof Element) {
                $element->init();
            }
        }
    }

    /**
     * Returns all elements.
     */
    public function getElements()
    {
        foreach ($this->elements as $name => $element) {
            $this->resolveXRef($name);
        }

        return $this->elements;
    }

    /**
     * Used only for debug.
     */
    public function getElementTypes(): array
    {
        $types = [];

        foreach ($this->elements as $key => $element) {
            $types[$key] = \get_class($element);
        }

        return $types;
    }

    public function getDetails(bool $deep = true): array
    {
        $values = [];
        $elements = $this->getElements();

        foreach ($elements as $key => $element) {
            if ($element instanceof self && $deep) {
                $values[$key] = $element->getDetails($deep);
            } elseif ($element instanceof PDFObject && $deep) {
                $values[$key] = $element->getDetails(false);
            } elseif ($element instanceof ElementArray) {
                if ($deep) {
                    $values[$key] = $element->getDetails();
                }
            } elseif ($element instanceof Element) {
                $values[$key] = (string) $element;
            }
        }

        // ensure detail information aren't badly encoded
        foreach ($values as $key => $value) {
            if (false === preg_match('!!u', $value)) {
                $font = $this->document->getFirstFont();
                if ($font) {
                    $newValue = $font->decodeContent($value);
                } else {
                    $newValue = mb_convert_encoding($value, 'UTF-8', 'Windows-1252');
                }

                $values[$key] = $newValue;
            }
        }

        return $values;
    }

    /**
     * Indicate if an element name is available in header.
     *
     * @param string $name the name of the element
     */
    public function has(string $name): bool
    {
        return \array_key_exists($name, $this->elements);
    }

    /**
     * @return Element|PDFObject
     */
    public function get(string $name)
    {
        if (\array_key_exists($name, $this->elements)) {
            return $this->resolveXRef($name);
        }

        return new ElementMissing();
    }

    /**
     * Resolve XRef to object.
     *
     * @return Element|PDFObject
     *
     * @throws \Exception
     */
    protected function resolveXRef(string $name)
    {
        if (($obj = $this->elements[$name]) instanceof ElementXRef && null !== $this->document) {
            /** @var ElementXRef $obj */
            $object = $this->document->getObjectById($obj->getId());

            if (null === $object) {
                return new ElementMissing();
            }

            // Update elements list for future calls.
            $this->elements[$name] = $object;
        }

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

    /**
     * @param string   $content  The content to parse
     * @param Document $document The document
     * @param int      $position The new position of the cursor after parsing
     */
    public static function parse(string $content, Document $document, int &$position = 0): self
    {
        /* @var Header $header */
        if ('<<' == substr(trim($content), 0, 2)) {
            $header = ElementStruct::parse($content, $document, $position);
        } else {
            $elements = ElementArray::parse($content, $document, $position);
            $header = new self([], $document);

            if ($elements) {
                $header = new self($elements->getRawContent(), null);
            }
        }

        if ($header) {
            return $header;
        }

        // Build an empty header.
        return new self([], $document);
    }
}


1		<?php
2
3		/**
4		* @file
5		* This file is part of the PdfParser library.
6		*
7		* @author Sébastien MALOT <[email protected]>
8		* @date 2017-01-03
9		*
10		* @license LGPLv3
11		* @url <https://github.com/smalot/pdfparser>
12		*
13		* PdfParser is a pdf library written in PHP, extraction oriented.
14		* Copyright (C) 2017 - Sébastien MALOT <[email protected]>
15		*
16		* This program is free software: you can redistribute it and/or modify
17		* it under the terms of the GNU Lesser General Public License as published by
18		* the Free Software Foundation, either version 3 of the License, or
19		* (at your option) any later version.
20		*
21		* This program is distributed in the hope that it will be useful,
22		* but WITHOUT ANY WARRANTY; without even the implied warranty of
23		* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
24		* GNU Lesser General Public License for more details.
25		*
26		* You should have received a copy of the GNU Lesser General Public License
27		* along with this program.
28		* If not, see <http://www.pdfparser.org/sites/default/LICENSE.txt>.
29		*/
30
31		namespace Smalot\PdfParser;
32
33		use Smalot\PdfParser\Element\ElementArray;
34		use Smalot\PdfParser\Element\ElementMissing;
35		use Smalot\PdfParser\Element\ElementStruct;
36		use Smalot\PdfParser\Element\ElementXRef;
37
38		/**
39		* Class Header
40		*/
41		class Header
42		{
43		/**
44		* @var Document
45		*/
46		protected $document = null;
47
48		/**
49		* @var Element[]
50		*/
51		protected $elements = null;
52
53		/**
54		* @param Element[] $elements list of elements
55		* @param Document $document document
56		*/
57	65	public function __construct(array $elements = [], ?Document $document = null)
58		{
59	65	$this->elements = $elements;
60	65	$this->document = $document;
61	65	}
62
63	43	public function init()
64		{
65	43	foreach ($this->elements as $element) {
66	43	if ($element instanceof Element) {
67	43	$element->init();
68		}
69		}
70	43	}
71
72		/**
73		* Returns all elements.
74		*/
75	36	public function getElements()
76		{
77	36	foreach ($this->elements as $name => $element) {
78	36	$this->resolveXRef($name);
79		}
80
81	36	return $this->elements;
82		}
83
84		/**
85		* Used only for debug.
86		*/
87	1	public function getElementTypes(): array
88		{
89	1	$types = [];
90
91	1	foreach ($this->elements as $key => $element) {
92	1	$types[$key] = \get_class($element);
93		}
94
95	1	return $types;
96		}
97
98	34	public function getDetails(bool $deep = true): array
99		{
100	34	$values = [];
101	34	$elements = $this->getElements();
102
103	34	foreach ($elements as $key => $element) {
104	34	if ($element instanceof self && $deep) {
105		$values[$key] = $element->getDetails($deep);
106	34	} elseif ($element instanceof PDFObject && $deep) {
107		$values[$key] = $element->getDetails(false);
108	34	} elseif ($element instanceof ElementArray) {
109		if ($deep) {
110		$values[$key] = $element->getDetails();
111		}
112	34	} elseif ($element instanceof Element) {
113	34	$values[$key] = (string) $element;
114		}
115		}
116
117		// ensure detail information aren't badly encoded
118	34	foreach ($values as $key => $value) {
119	34	if (false === preg_match('!!u', $value)) {
120	4	$font = $this->document->getFirstFont();
121	4	if ($font) {
122	4	$newValue = $font->decodeContent($value);
123		} else {
124		$newValue = mb_convert_encoding($value, 'UTF-8', 'Windows-1252');
125		}
126
127	4	$values[$key] = $newValue;
128		}
129		}
130
131	34	return $values;
132		}
133
134		/**
135		* Indicate if an element name is available in header.
136		*
137		* @param string $name the name of the element
138		*/
139	47	public function has(string $name): bool
140		{
141	47	return \array_key_exists($name, $this->elements);
142		}
143
144		/**
145		* @return Element\|PDFObject
146		*/
147	50	public function get(string $name)
148		{
149	50	if (\array_key_exists($name, $this->elements)) {
150	49	return $this->resolveXRef($name);
151		}
152
153	47	return new ElementMissing();
154		}
155
156		/**
157		* Resolve XRef to object.
158		*
159		* @return Element\|PDFObject
160		*
161		* @throws \Exception
162		*/
163	50	protected function resolveXRef(string $name)
164		{
165	50	if (($obj = $this->elements[$name]) instanceof ElementXRef && null !== $this->document) {
166		/** @var ElementXRef $obj */
167	38	$object = $this->document->getObjectById($obj->getId());
168
169	38	if (null === $object) {
170	2	return new ElementMissing();
171		}
172
173		// Update elements list for future calls.
174	38	$this->elements[$name] = $object;
175		}
176
177	50	return $this->elements[$name];
178		}
179
180		/**
181		* @param string $content The content to parse
182		* @param Document $document The document
183		* @param int $position The new position of the cursor after parsing
184		*/
185	21	public static function parse(string $content, Document $document, int &$position = 0): self
186		{
187		/* @var Header $header */
188	21	if ('<<' == substr(trim($content), 0, 2)) {
189	20	$header = ElementStruct::parse($content, $document, $position);
190		} else {
191	8	$elements = ElementArray::parse($content, $document, $position);
192	8	$header = new self([], $document);
193
194	8	if ($elements) {
195	7	$header = new self($elements->getRawContent(), null);
196		}
197		}
198
199	21	if ($header) {
200	21	return $header;
201		}
202
203		// Build an empty header.
204		return new self([], $document);
205		}
206		}
207

smalot / pdfparser

Pull Request — master (#510)

Header::getDetails() C

Complexity

Size

Duplication

Code Coverage

Importance

How to fix Complexity

Long Method

Duplication Side-by-Side

Filter issues like