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

Passed

Pull Request — master (#510)

by Jeremy

created 2022-01-31 13:28 UTC

Header::getElements() A

↳ Parent: Header

Complexity

Conditions	2
Paths	2

Size

Total Lines	7
Code Lines	3

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	4
CRAP Score	2

Importance

Changes	1
Bugs	0	Features	0

Metric	Value
eloc	3
dl	0
loc	7
rs	10
c	1
b	0
f	0
ccs	4
cts	4
cp	1
cc	2
nc	2
nop	0
crap	2

<?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;
            }
        }

        return $this->ensureProperDetailEncoding($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);
    }

    /**
     * Ensure detail information aren't badly encoded.
     */
    private function ensureProperDetailEncoding(array $values): array
    {
        foreach ($values as $key => $value) {
            if (\is_array($value)) {
                $values[$key] = $this->ensureProperDetailEncoding($value);

                continue;
            }

            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;
    }
}


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	68	public function __construct(array $elements = [], ?Document $document = null)
58		{
59	68	$this->elements = $elements;
60	68	$this->document = $document;
61	68	}
62
63	45	public function init()
64		{
65	45	foreach ($this->elements as $element) {
66	45	if ($element instanceof Element) {
67	45	$element->init();
68		}
69		}
70	45	}
71
72		/**
73		* Returns all elements.
74		*/
75	39	public function getElements()
76		{
77	39	foreach ($this->elements as $name => $element) {
78	39	$this->resolveXRef($name);
79		}
80
81	39	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	37	public function getDetails(bool $deep = true): array
99		{
100	37	$values = [];
101	37	$elements = $this->getElements();
102
103	37	foreach ($elements as $key => $element) {
104	37	if ($element instanceof self && $deep) {
105		$values[$key] = $element->getDetails($deep);
106	37	} elseif ($element instanceof PDFObject && $deep) {
107	2	$values[$key] = $element->getDetails(false);
108	37	} elseif ($element instanceof ElementArray) {
109	2	if ($deep) {
110	2	$values[$key] = $element->getDetails();
111		}
112	37	} elseif ($element instanceof Element) {
113	37	$values[$key] = (string) $element;
114		}
115		}
116
117	37	return $this->ensureProperDetailEncoding($values);
118		}
119
120		/**
121		* Indicate if an element name is available in header.
122		*
123		* @param string $name the name of the element
124		*/
125	49	public function has(string $name): bool
126		{
127	49	return \array_key_exists($name, $this->elements);
128		}
129
130		/**
131		* @return Element\|PDFObject
132		*/
133	52	public function get(string $name)
134		{
135	52	if (\array_key_exists($name, $this->elements)) {
136	51	return $this->resolveXRef($name);
137		}
138
139	49	return new ElementMissing();
140		}
141
142		/**
143		* Resolve XRef to object.
144		*
145		* @return Element\|PDFObject
146		*
147		* @throws \Exception
148		*/
149	53	protected function resolveXRef(string $name)
150		{
151	53	if (($obj = $this->elements[$name]) instanceof ElementXRef && null !== $this->document) {
152		/** @var ElementXRef $obj */
153	40	$object = $this->document->getObjectById($obj->getId());
154
155	40	if (null === $object) {
156	2	return new ElementMissing();
157		}
158
159		// Update elements list for future calls.
160	40	$this->elements[$name] = $object;
161		}
162
163	53	return $this->elements[$name];
164		}
165
166		/**
167		* @param string $content The content to parse
168		* @param Document $document The document
169		* @param int $position The new position of the cursor after parsing
170		*/
171	22	public static function parse(string $content, Document $document, int &$position = 0): self
172		{
173		/* @var Header $header */
174	22	if ('<<' == substr(trim($content), 0, 2)) {
175	21	$header = ElementStruct::parse($content, $document, $position);
176		} else {
177	8	$elements = ElementArray::parse($content, $document, $position);
178	8	$header = new self([], $document);
179
180	8	if ($elements) {
181	7	$header = new self($elements->getRawContent(), null);
182		}
183		}
184
185	22	if ($header) {
186	22	return $header;
187		}
188
189		// Build an empty header.
190		return new self([], $document);
191		}
192
193		/**
194		* Ensure detail information aren't badly encoded.
195		*/
196	37	private function ensureProperDetailEncoding(array $values): array
197		{
198	37	foreach ($values as $key => $value) {
199	37	if (\is_array($value)) {
200	3	$values[$key] = $this->ensureProperDetailEncoding($value);
201
202	3	continue;
203		}
204
205	37	if (false === preg_match('!!u', $value)) {
206	4	$font = $this->document->getFirstFont();
207	4	if ($font) {
208	4	$newValue = $font->decodeContent($value);
209		} else {
210		$newValue = mb_convert_encoding($value, 'UTF-8', 'Windows-1252');
211		}
212
213	4	$values[$key] = $newValue;
214		}
215		}
216
217	37	return $values;
218		}
219		}
220

smalot / pdfparser

Pull Request — master (#510)

Header::getElements() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like