Parser::getConfig() - Code Metrics - Inspection of "fix: allow to parse null or empty header element" - smalot/pdfparser - Measure and Improve Code Quality continuously with Scrutinizer

Test Failed

Pull Request — master (#560)

unknown

created 2022-12-02 13:01 UTC

Parser::getConfig() A

↳ Parent: Project

Complexity

Conditions	1
Paths	1

Size

Total Lines	3
Code Lines	1

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	2
CRAP Score	1

Importance

Changes

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

<?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\ElementBoolean;
use Smalot\PdfParser\Element\ElementDate;
use Smalot\PdfParser\Element\ElementHexa;
use Smalot\PdfParser\Element\ElementName;
use Smalot\PdfParser\Element\ElementNull;
use Smalot\PdfParser\Element\ElementNumeric;
use Smalot\PdfParser\Element\ElementString;
use Smalot\PdfParser\Element\ElementXRef;
use Smalot\PdfParser\RawData\RawDataParser;

/**
 * Class Parser
 */
class Parser
{
    /**
     * @var Config
     */
    private $config;

    /**
     * @var PDFObject[]
     */
    protected $objects = [];

    protected $rawDataParser;

    public function __construct($cfg = [], ?Config $config = null)
    {
        $this->config = $config ?: new Config();
        $this->rawDataParser = new RawDataParser($cfg, $this->config);
    }

    public function getConfig(): Config
    {
        return $this->config;
    }

    /**
     * @throws \Exception
     */
    public function parseFile(string $filename): Document
    {
        $content = file_get_contents($filename);
        /*
         * 2018/06/20 @doganoo as multiple times a
         * users have complained that the parseFile()
         * method dies silently, it is an better option
         * to remove the error control operator (@) and
         * let the users know that the method throws an exception
         * by adding @throws tag to PHPDoc.
         *
         * See here for an example: https://github.com/smalot/pdfparser/issues/204
         */
        return $this->parseContent($content);
    }

    /**
     * @param string $content PDF content to parse
     *
     * @throws \Exception if secured PDF file was detected
     * @throws \Exception if no object list was found
     */
    public function parseContent(string $content): Document
    {
        // Create structure from raw data.
        list($xref, $data) = $this->rawDataParser->parseData($content);

        if (isset($xref['trailer']['encrypt'])) {
            throw new \Exception('Secured pdf file are currently not supported.');
        }

        if (empty($data)) {
            throw new \Exception('Object list not found. Possible secured file.');
        }

        // Create destination object.
        $document = new Document();
        $this->objects = [];

        foreach ($data as $id => $structure) {
            $this->parseObject($id, $structure, $document);
            unset($data[$id]);
        }

        $document->setTrailer($this->parseTrailer($xref['trailer'], $document));
        $document->setObjects($this->objects);

        return $document;
    }

    protected function parseTrailer(array $structure, ?Document $document)
    {
        $trailer = [];

        foreach ($structure as $name => $values) {
            $name = ucfirst($name);

            if (is_numeric($values)) {
                $trailer[$name] = new ElementNumeric($values);
            } elseif (\is_array($values)) {
                $value = $this->parseTrailer($values, null);
                $trailer[$name] = new ElementArray($value, null);
            } elseif (false !== strpos($values, '_')) {
                $trailer[$name] = new ElementXRef($values, $document);
            } else {
                $trailer[$name] = $this->parseHeaderElement('(', $values, $document);
            }
        }

        return new Header($trailer, $document);
    }

    protected function parseObject(string $id, array $structure, ?Document $document)
    {
        $header = new Header([], $document);
        $content = '';

        foreach ($structure as $position => $part) {
            if (\is_int($part)) {
                $part = [null, null];
            }
            switch ($part[0]) {
                case '[':
                    $elements = [];

                    foreach ($part[1] as $sub_element) {
                        $sub_type = $sub_element[0];
                        $sub_value = $sub_element[1];
                        $elements[] = $this->parseHeaderElement($sub_type, $sub_value, $document);
                    }

                    $header = new Header($elements, $document);
                    break;

                case '<<':
                    $header = $this->parseHeader($part[1], $document);
                    break;

                case 'stream':
                    $content = isset($part[3][0]) ? $part[3][0] : $part[1];

                    if ($header->get('Type')->equals('ObjStm')) {
                        $match = [];

                        // Split xrefs and contents.
                        preg_match('/^((\d+\s+\d+\s*)*)(.*)$/s', $content, $match);
                        $content = $match[3];

                        // Extract xrefs.
                        $xrefs = preg_split(
                            '/(\d+\s+\d+\s*)/s',
                            $match[1],
                            -1,
                            \PREG_SPLIT_NO_EMPTY | \PREG_SPLIT_DELIM_CAPTURE
                        );
                        $table = [];

                        foreach ($xrefs as $xref) {
                            list($id, $position) = preg_split("/\s+/", trim($xref));
                            $table[$position] = $id;
                        }

                        ksort($table);

                        $ids = array_values($table);
                        $positions = array_keys($table);

                        foreach ($positions as $index => $position) {
                            $id = $ids[$index].'_0';
                            $next_position = isset($positions[$index + 1]) ? $positions[$index + 1] : \strlen($content);
                            $sub_content = substr($content, $position, (int) $next_position - (int) $position);

                            $sub_header = Header::parse($sub_content, $document);
                            $object = PDFObject::factory($document, $sub_header, '', $this->config);
                            $this->objects[$id] = $object;
                        }

                        // It is not necessary to store this content.

                        return;
                    }
                    break;

                default:
                    if ('null' != $part) {
                        $element = $this->parseHeaderElement($part[0], $part[1], $document);

                        if ($element) {
                            $header = new Header([$element], $document);
                        }
                    }
                    break;
            }
        }

        if (!isset($this->objects[$id])) {
            $this->objects[$id] = PDFObject::factory($document, $header, $content, $this->config);
        }
    }

    /**
     * @throws \Exception
     */
    protected function parseHeader(array $structure, ?Document $document): Header
    {
        $elements = [];
        $count = \count($structure);

        for ($position = 0; $position < $count; $position += 2) {
            $name = $structure[$position][1];
            $type = $structure[$position + 1][0];
            $value = $structure[$position + 1][1];

            $elements[$name] = $this->parseHeaderElement($type, $value, $document);
        }

        return new Header($elements, $document);
    }

    /**
     * @param string|array $value
     *
     * @return Element|Header|null
     *
     * @throws \Exception
     */
    protected function parseHeaderElement(?string $type, $value, ?Document $document)
    {
        $valueIsEmpty = null == $value || '' == $value || false == $value;
        if (('<<' === $type || '>>' === $type) && $valueIsEmpty)) {

            $value = [];
        }

        switch ($type) {
            case '<<':
            case '>>':
                $header = $this->parseHeader($value, $document);
                PDFObject::factory($document, $header, null, $this->config);

                return $header;

            case 'numeric':
                return new ElementNumeric($value);

            case 'boolean':
                return new ElementBoolean($value);

            case 'null':
                return new ElementNull();

            case '(':
                if ($date = ElementDate::parse('('.$value.')', $document)) {
                    return $date;
                }

                return ElementString::parse('('.$value.')', $document);

            case '<':
                return $this->parseHeaderElement('(', ElementHexa::decode($value), $document);

            case '/':
                return ElementName::parse('/'.$value, $document);

            case 'ojbref': // old mistake in tcpdf parser
            case 'objref':
                return new ElementXRef($value, $document);

            case '[':
                $values = [];

                if (\is_array($value)) {
                    foreach ($value as $sub_element) {
                        $sub_type = $sub_element[0];
                        $sub_value = $sub_element[1];
                        $values[] = $this->parseHeaderElement($sub_type, $sub_value, $document);
                    }
                }

                return new ElementArray($values, $document);

            case 'endstream':
            case 'obj': // I don't know what it means but got my project fixed.
            case '':
                // Nothing to do with.
                return null;

            default:
                throw new \Exception('Invalid type: "'.$type.'".');
        }
    }
}


1		<?php
2
3		/**
4		* @file
5		* This file is part of the PdfParser library.
6		*
7		* @author Sébastien MALOT <[email protected]>
8		*
9		* @date 2017-01-03
10		*
11		* @license LGPLv3
12		*
13		* @url <https://github.com/smalot/pdfparser>
14		*
15		* PdfParser is a pdf library written in PHP, extraction oriented.
16		* Copyright (C) 2017 - Sébastien MALOT <[email protected]>
17		*
18		* This program is free software: you can redistribute it and/or modify
19		* it under the terms of the GNU Lesser General Public License as published by
20		* the Free Software Foundation, either version 3 of the License, or
21		* (at your option) any later version.
22		*
23		* This program is distributed in the hope that it will be useful,
24		* but WITHOUT ANY WARRANTY; without even the implied warranty of
25		* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
26		* GNU Lesser General Public License for more details.
27		*
28		* You should have received a copy of the GNU Lesser General Public License
29		* along with this program.
30		* If not, see <http://www.pdfparser.org/sites/default/LICENSE.txt>.
31		*/
32
33		namespace Smalot\PdfParser;
34
35		use Smalot\PdfParser\Element\ElementArray;
36		use Smalot\PdfParser\Element\ElementBoolean;
37		use Smalot\PdfParser\Element\ElementDate;
38		use Smalot\PdfParser\Element\ElementHexa;
39		use Smalot\PdfParser\Element\ElementName;
40		use Smalot\PdfParser\Element\ElementNull;
41		use Smalot\PdfParser\Element\ElementNumeric;
42		use Smalot\PdfParser\Element\ElementString;
43		use Smalot\PdfParser\Element\ElementXRef;
44		use Smalot\PdfParser\RawData\RawDataParser;
45
46		/**
47		* Class Parser
48		*/
49		class Parser
50		{
51		/**
52		* @var Config
53		*/
54		private $config;
55
56		/**
57		* @var PDFObject[]
58		*/
59		protected $objects = [];
60
61		protected $rawDataParser;
62
63	41	public function __construct($cfg = [], ?Config $config = null)
64		{
65	41	$this->config = $config ?: new Config();
66	41	$this->rawDataParser = new RawDataParser($cfg, $this->config);
67	41	}
68
69	1	public function getConfig(): Config
70		{
71	1	return $this->config;
72		}
73
74		/**
75		* @throws \Exception
76		*/
77	39	public function parseFile(string $filename): Document
78		{
79	39	$content = file_get_contents($filename);
80		/*
81		* 2018/06/20 @doganoo as multiple times a
82		* users have complained that the parseFile()
83		* method dies silently, it is an better option
84		* to remove the error control operator (@) and
85		* let the users know that the method throws an exception
86		* by adding @throws tag to PHPDoc.
87		*
88		* See here for an example: https://github.com/smalot/pdfparser/issues/204
89		*/
90	39	return $this->parseContent($content);
91		}
92
93		/**
94		* @param string $content PDF content to parse
95		*
96		* @throws \Exception if secured PDF file was detected
97		* @throws \Exception if no object list was found
98		*/
99	39	public function parseContent(string $content): Document
100		{
101		// Create structure from raw data.
102	39	list($xref, $data) = $this->rawDataParser->parseData($content);
103
104	38	if (isset($xref['trailer']['encrypt'])) {
105		throw new \Exception('Secured pdf file are currently not supported.');
106		}
107
108	38	if (empty($data)) {
109		throw new \Exception('Object list not found. Possible secured file.');
110		}
111
112		// Create destination object.
113	38	$document = new Document();
114	38	$this->objects = [];
115
116	38	foreach ($data as $id => $structure) {
117	38	$this->parseObject($id, $structure, $document);
118	38	unset($data[$id]);
119		}
120
121	38	$document->setTrailer($this->parseTrailer($xref['trailer'], $document));
122	38	$document->setObjects($this->objects);
123
124	38	return $document;
125		}
126
127	38	protected function parseTrailer(array $structure, ?Document $document)
128		{
129	38	$trailer = [];
130
131	38	foreach ($structure as $name => $values) {
132	38	$name = ucfirst($name);
133
134	38	if (is_numeric($values)) {
135	38	$trailer[$name] = new ElementNumeric($values);
136	38	} elseif (\is_array($values)) {
137	33	$value = $this->parseTrailer($values, null);
138	33	$trailer[$name] = new ElementArray($value, null);
139	38	} elseif (false !== strpos($values, '_')) {
140	38	$trailer[$name] = new ElementXRef($values, $document);
141		} else {
142	33	$trailer[$name] = $this->parseHeaderElement('(', $values, $document);
143		}
144		}
145
146	38	return new Header($trailer, $document);
147		}
148
149	39	protected function parseObject(string $id, array $structure, ?Document $document)
150		{
151	39	$header = new Header([], $document);
152	39	$content = '';
153
154	39	foreach ($structure as $position => $part) {
155	39	if (\is_int($part)) {
156		$part = [null, null];
157		}
158	39	switch ($part[0]) {
159	39	case '[':
160	13	$elements = [];
161
162	13	foreach ($part[1] as $sub_element) {
163	13	$sub_type = $sub_element[0];
164	13	$sub_value = $sub_element[1];
165	13	$elements[] = $this->parseHeaderElement($sub_type, $sub_value, $document);
166		}
167
168	13	$header = new Header($elements, $document);
169	13	break;
170
171	39	case '<<':
172	39	$header = $this->parseHeader($part[1], $document);
173	39	break;
174
175	39	case 'stream':
176	39	$content = isset($part[3][0]) ? $part[3][0] : $part[1];
177
178	39	if ($header->get('Type')->equals('ObjStm')) {
179	11	$match = [];
180
181		// Split xrefs and contents.
182	11	preg_match('/^((\d+\s+\d+\s))(.*)$/s', $content, $match);
183	11	$content = $match[3];
184
185		// Extract xrefs.
186	11	$xrefs = preg_split(
187	11	'/(\d+\s+\d+\s*)/s',
188	11	$match[1],
189	11	-1,
190	11	\PREG_SPLIT_NO_EMPTY \| \PREG_SPLIT_DELIM_CAPTURE
191		);
192	11	$table = [];
193
194	11	foreach ($xrefs as $xref) {
195	11	list($id, $position) = preg_split("/\s+/", trim($xref));
196	11	$table[$position] = $id;
197		}
198
199	11	ksort($table);
200
201	11	$ids = array_values($table);
202	11	$positions = array_keys($table);
203
204	11	foreach ($positions as $index => $position) {
205	11	$id = $ids[$index].'_0';
206	11	$next_position = isset($positions[$index + 1]) ? $positions[$index + 1] : \strlen($content);
207	11	$sub_content = substr($content, $position, (int) $next_position - (int) $position);
208
209	11	$sub_header = Header::parse($sub_content, $document);
210	11	$object = PDFObject::factory($document, $sub_header, '', $this->config);
211	11	$this->objects[$id] = $object;
212		}
213
214		// It is not necessary to store this content.
215
216	11	return;
217		}
218	38	break;
219
220		default:
221	38	if ('null' != $part) {
222	38	$element = $this->parseHeaderElement($part[0], $part[1], $document);
223
224	38	if ($element) {
225	20	$header = new Header([$element], $document);
226		}
227		}
228	38	break;
229		}
230		}
231
232	38	if (!isset($this->objects[$id])) {
233	38	$this->objects[$id] = PDFObject::factory($document, $header, $content, $this->config);
234		}
235	38	}
236
237		/**
238		* @throws \Exception
239		*/
240	39	protected function parseHeader(array $structure, ?Document $document): Header
241		{
242	39	$elements = [];
243	39	$count = \count($structure);
244
245	39	for ($position = 0; $position < $count; $position += 2) {
246	39	$name = $structure[$position][1];
247	39	$type = $structure[$position + 1][0];
248	39	$value = $structure[$position + 1][1];
249
250	39	$elements[$name] = $this->parseHeaderElement($type, $value, $document);
251		}
252
253	39	return new Header($elements, $document);
254		}
255
256		/**
257		* @param string\|array $value
258		*
259		* @return Element\|Header\|null
260		*
261		* @throws \Exception
262		*/
263	39	protected function parseHeaderElement(?string $type, $value, ?Document $document)
264		{
265	39	$valueIsEmpty = null == $value \|\| '' == $value \|\| false == $value;
266	39	if (('<<' === $type \|\| '>>' === $type) && $valueIsEmpty)) {
		0 ignored issues – show Bug introduced 2022-12-02 13:08 UTC by Report Bug Copy Issue Report A parse error occurred: Syntax error, unexpected ')' on line 266 at column 64 Loading history...
267	39	$value = [];
268	38	}
269	38
270		switch ($type) {
271	38	case '<<':
272		case '>>':
273	39	$header = $this->parseHeader($value, $document);
274	38	PDFObject::factory($document, $header, null, $this->config);
275
276	39	return $header;
277	13
278		case 'numeric':
279	39	return new ElementNumeric($value);
280	3
281		case 'boolean':
282	39	return new ElementBoolean($value);
283	38
284	31	case 'null':
285		return new ElementNull();
286
287	38	case '(':
288		if ($date = ElementDate::parse('('.$value.')', $document)) {
289	39	return $date;
290	15	}
291
292	39	return ElementString::parse('('.$value.')', $document);
293	39
294		case '<':
295	38	return $this->parseHeaderElement('(', ElementHexa::decode($value), $document);
296	38
297	38	case '/':
298		return ElementName::parse('/'.$value, $document);
299	38
300	38	case 'ojbref': // old mistake in tcpdf parser
301		case 'objref':
302	38	return new ElementXRef($value, $document);
303	38
304	38	case '[':
305	38	$values = [];
306	38
307		if (\is_array($value)) {
308		foreach ($value as $sub_element) {
309		$sub_type = $sub_element[0];
310	38	$sub_value = $sub_element[1];
311		$values[] = $this->parseHeaderElement($sub_type, $sub_value, $document);
312	38	}
313	1	}
314
315		return new ElementArray($values, $document);
316	38
317		case 'endstream':
318		case 'obj': // I don't know what it means but got my project fixed.
319		case '':
320		// Nothing to do with.
321		return null;
322
323		default:
324		throw new \Exception('Invalid type: "'.$type.'".');
325		}
326		}
327		}
328

smalot / pdfparser

Pull Request — master (#560)

Parser::getConfig() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like