Document::getDetails() - Code Metrics - Inspection of "Fix failing Scrutinizer CI tests" - smalot/pdfparser - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Pull Request — master (#615)

by Jeffrey

created 2023-07-16 00:08 UTC

Document::getDetails() A

↳ Parent: Document

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

<?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\Encoding\PDFDocEncoding;

/**
 * Technical references :
 * - http://www.mactech.com/articles/mactech/Vol.15/15.09/PDFIntro/index.html
 * - http://framework.zend.com/issues/secure/attachment/12512/Pdf.php
 * - http://www.php.net/manual/en/ref.pdf.php#74211
 * - http://cpansearch.perl.org/src/JV/PostScript-Font-1.10.02/lib/PostScript/ISOLatin1Encoding.pm
 * - http://cpansearch.perl.org/src/JV/PostScript-Font-1.10.02/lib/PostScript/ISOLatin9Encoding.pm
 * - http://cpansearch.perl.org/src/JV/PostScript-Font-1.10.02/lib/PostScript/StandardEncoding.pm
 * - http://cpansearch.perl.org/src/JV/PostScript-Font-1.10.02/lib/PostScript/WinAnsiEncoding.pm
 *
 * Class Document
 */
class Document
{
    /**
     * @var PDFObject[]
     */
    protected $objects = [];

    /**
     * @var array
     */
    protected $dictionary = [];

    /**
     * @var Header
     */
    protected $trailer;

    /**
     * @var array<mixed>
     */
    protected $metadata = [];

    /**
     * @var array
     */
    protected $details;

    public function __construct()
    {
        $this->trailer = new Header([], $this);
    }

    public function init()
    {
        $this->buildDictionary();

        $this->buildDetails();

        // Propagate init to objects.
        foreach ($this->objects as $object) {
            $object->getHeader()->init();
            $object->init();
        }
    }

    /**
     * Build dictionary based on type header field.
     */
    protected function buildDictionary()
    {
        // Build dictionary.
        $this->dictionary = [];

        foreach ($this->objects as $id => $object) {
            // Cache objects by type and subtype
            $type = $object->getHeader()->get('Type')->getContent();

            if (null != $type) {
                if (!isset($this->dictionary[$type])) {
                    $this->dictionary[$type] = [
                        'all' => [],
                        'subtype' => [],
                    ];
                }

                $this->dictionary[$type]['all'][$id] = $object;

                $subtype = $object->getHeader()->get('Subtype')->getContent();
                if (null != $subtype) {
                    if (!isset($this->dictionary[$type]['subtype'][$subtype])) {
                        $this->dictionary[$type]['subtype'][$subtype] = [];
                    }
                    $this->dictionary[$type]['subtype'][$subtype][$id] = $object;
                }
            }
        }
    }

    /**
     * Build details array.
     */
    protected function buildDetails()
    {
        // Build details array.
        $details = [];

        // Extract document info
        if ($this->trailer->has('Info')) {
            /** @var PDFObject $info */
            $info = $this->trailer->get('Info');
            // This could be an ElementMissing object, so we need to check for
            // the getHeader method first.
            if (null !== $info && method_exists($info, 'getHeader')) {
                $details = $info->getHeader()->getDetails();
            }
        }

        // Retrieve the page count
        try {
            $pages = $this->getPages();
            $details['Pages'] = \count($pages);
        } catch (\Exception $e) {
            $details['Pages'] = 0;
        }

        // Decode and repair encoded document properties
        foreach ($details as $key => $value) {
            if (\is_string($value)) {
                // If the string is already UTF-8 encoded, that means we only
                // need to repair Adobe's ham-fisted insertion of line-feeds
                // every ~127 characters, which doesn't seem to be multi-byte
                // safe
                if (mb_check_encoding($value, 'UTF-8')) {
                    // Remove literal backslash + line-feed "\\r"
                    $value = str_replace("\x5c\x0d", '', $value);

                    // Remove backslash plus bytes written into high part of
                    // multibyte unicode character
                    while (preg_match("/\x5c\x5c\xe0([\xb4-\xb8])(.)/", $value, $match)) {
                        $diff = (\ord($match[1]) - 182) * 64;
                        $newbyte = PDFDocEncoding::convertPDFDoc2UTF8(\chr(\ord($match[2]) + $diff));
                        $value = preg_replace("/\x5c\x5c\xe0".$match[1].$match[2].'/', $newbyte, $value);
                    }

                    // Remove bytes written into low part of multibyte unicode
                    // character
                    while (preg_match("/(.)\x9c\xe0([\xb3-\xb7])/", $value, $match)) {
                        $diff = \ord($match[2]) - 181;
                        $newbyte = \chr(\ord($match[1]) + $diff);
                        $value = preg_replace('/'.$match[1]."\x9c\xe0".$match[2].'/', $newbyte, $value);
                    }

                    // Remove this byte string that Adobe occasionally adds
                    // between two single byte characters in a unicode string
                    $value = str_replace("\xe5\xb0\x8d", '', $value);

                    $details[$key] = $value;
                } else {
                    // If the string is just PDFDocEncoding, remove any line-feeds
                    // and decode the whole thing.
                    $value = str_replace("\\\r", '', $value);
                    $details[$key] = PDFDocEncoding::convertPDFDoc2UTF8($value);
                }
            }
        }

        $details = array_merge($details, $this->metadata);

        $this->details = $details;
    }

    /**
     * Extract XMP Metadata
     */
    public function extractXMPMetadata(string $content): void
    {
        $xml = xml_parser_create();
        xml_parser_set_option($xml, \XML_OPTION_SKIP_WHITE, 1);

        if (1 === xml_parse_into_struct($xml, $content, $values, $index)) {
            /*
             * short overview about the following code parts:
             *
             * The output of xml_parse_into_struct is a single dimensional array (= $values), and the $stack is a last-on,
             * first-off array of pointers to positions in $metadata, while iterating through it, that potentially turn the
             * results into a more intuitive multi-dimensional array. When an "open" XML tag is encountered,
             * we save the current $metadata context in the $stack, then create a child array of $metadata and
             * make that the current $metadata context. When a "close" XML tag is encountered, the operations are
             * reversed: the most recently added $metadata context from $stack (IOW, the parent of the current
             * element) is set as the current $metadata context.
             */
            $metadata = [];
            $stack = [];
            foreach ($values as $val) {
                // Standardize to lowercase
                $val['tag'] = strtolower($val['tag']);

                // Ignore structural x: and rdf: XML elements
                if (0 === strpos($val['tag'], 'x:')) {
                    continue;
                } elseif (0 === strpos($val['tag'], 'rdf:') && 'rdf:li' != $val['tag']) {
                    continue;
                }

                switch ($val['type']) {
                    case 'open':
                        // Create an array of list items
                        if ('rdf:li' == $val['tag']) {
                            $metadata[] = [];

                            // Move up one level in the stack
                            $stack[\count($stack)] = &$metadata;
                            $metadata = &$metadata[\count($metadata) - 1];
                        } else {
                            // Else create an array of named values
                            $metadata[$val['tag']] = [];

                            // Move up one level in the stack
                            $stack[\count($stack)] = &$metadata;
                            $metadata = &$metadata[$val['tag']];
                        }
                        break;

                    case 'complete':
                        if (isset($val['value'])) {
                            // Assign a value to this list item
                            if ('rdf:li' == $val['tag']) {
                                $metadata[] = $val['value'];

                                // Else assign a value to this property
                            } else {
                                $metadata[$val['tag']] = $val['value'];
                            }
                        }
                        break;

                    case 'close':
                        // If the value of this property is a single-
                        // element array where the element is of type
                        // string, use the value of the first list item
                        // as the value for this property
                        if (\is_array($metadata) && isset($metadata[0]) && 1 == \count($metadata) && \is_string($metadata[0])) {
                            $metadata = $metadata[0];
                        }

                        // Move down one level in the stack
                        $metadata = &$stack[\count($stack) - 1];
                        unset($stack[\count($stack) - 1]);
                        break;
                }
            }

            // Only use this metadata if it's referring to a PDF
            if (isset($metadata['dc:format']) && 'application/pdf' == $metadata['dc:format']) {
                // According to the XMP specifications: 'Conflict resolution
                // for separate packets that describe the same resource is
                // beyond the scope of this document.' - Section 6.1
                // Source: https://www.adobe.com/devnet/xmp.html
                // Source: https://github.com/adobe/XMP-Toolkit-SDK/blob/main/docs/XMPSpecificationPart1.pdf
                // So if there are multiple XMP blocks, just merge the values
                // of each found block over top of the existing values
                $this->metadata = array_merge($this->metadata, $metadata);
            }
        }
        xml_parser_free($xml);
    }

    public function getDictionary(): array
    {
        return $this->dictionary;
    }

    /**
     * @param PDFObject[] $objects
     */
    public function setObjects($objects = [])
    {
        $this->objects = (array) $objects;

        $this->init();
    }

    /**
     * @return PDFObject[]
     */
    public function getObjects()
    {
        return $this->objects;
    }

    /**
     * @return PDFObject|Font|Page|Element|null
     */
    public function getObjectById(string $id)
    {
        if (isset($this->objects[$id])) {
            return $this->objects[$id];
        }

        return null;
    }

    public function hasObjectsByType(string $type, string $subtype = null): bool
    {
        return 0 < \count($this->getObjectsByType($type, $subtype));
    }

    public function getObjectsByType(string $type, string $subtype = null): array
    {
        if (!isset($this->dictionary[$type])) {
            return [];
        }

        if (null != $subtype) {

            if (!isset($this->dictionary[$type]['subtype'][$subtype])) {
                return [];
            }

            return $this->dictionary[$type]['subtype'][$subtype];
        }

        return $this->dictionary[$type]['all'];
    }

    /**
     * @return Font[]
     */
    public function getFonts()
    {
        return $this->getObjectsByType('Font');
    }

    public function getFirstFont(): ?Font
    {
        $fonts = $this->getFonts();
        if ([] === $fonts) {
            return null;
        }

        return reset($fonts);
    }

    /**
     * @return Page[]
     *
     * @throws \Exception
     */
    public function getPages()
    {
        if ($this->hasObjectsByType('Catalog')) {
            // Search for catalog to list pages.
            $catalogues = $this->getObjectsByType('Catalog');
            $catalogue = reset($catalogues);

            /** @var Pages $object */
            $object = $catalogue->get('Pages');
            if (method_exists($object, 'getPages')) {
                return $object->getPages(true);
            }
        }

        if ($this->hasObjectsByType('Pages')) {
            // Search for pages to list kids.
            $pages = [];

            /** @var Pages[] $objects */
            $objects = $this->getObjectsByType('Pages');
            foreach ($objects as $object) {
                $pages = array_merge($pages, $object->getPages(true));
            }

            return $pages;
        }

        if ($this->hasObjectsByType('Page')) {
            // Search for 'page' (unordered pages).
            $pages = $this->getObjectsByType('Page');

            return array_values($pages);
        }

        throw new \Exception('Missing catalog.');
    }

    public function getText(int $pageLimit = null): string
    {
        $texts = [];
        $pages = $this->getPages();

        // Only use the first X number of pages if $pageLimit is set and numeric.
        if (\is_int($pageLimit) && 0 < $pageLimit) {
            $pages = \array_slice($pages, 0, $pageLimit);
        }

        foreach ($pages as $index => $page) {
            /**
             * In some cases, the $page variable may be null.
             */
            if (null === $page) {
                continue;
            }
            if ($text = trim($page->getText())) {
                $texts[] = $text;
            }
        }

        return implode("\n\n", $texts);
    }

    public function getTrailer(): Header
    {
        return $this->trailer;
    }

    public function setTrailer(Header $trailer)
    {
        $this->trailer = $trailer;
    }

    public function getDetails(): array
    {
        return $this->details;
    }
}


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\Encoding\PDFDocEncoding;
36
37		/**
38		* Technical references :
39		* - http://www.mactech.com/articles/mactech/Vol.15/15.09/PDFIntro/index.html
40		* - http://framework.zend.com/issues/secure/attachment/12512/Pdf.php
41		* - http://www.php.net/manual/en/ref.pdf.php#74211
42		* - http://cpansearch.perl.org/src/JV/PostScript-Font-1.10.02/lib/PostScript/ISOLatin1Encoding.pm
43		* - http://cpansearch.perl.org/src/JV/PostScript-Font-1.10.02/lib/PostScript/ISOLatin9Encoding.pm
44		* - http://cpansearch.perl.org/src/JV/PostScript-Font-1.10.02/lib/PostScript/StandardEncoding.pm
45		* - http://cpansearch.perl.org/src/JV/PostScript-Font-1.10.02/lib/PostScript/WinAnsiEncoding.pm
46		*
47		* Class Document
48		*/
49		class Document
50		{
51		/**
52		* @var PDFObject[]
53		*/
54		protected $objects = [];
55
56		/**
57		* @var array
58		*/
59		protected $dictionary = [];
60
61		/**
62		* @var Header
63		*/
64		protected $trailer;
65
66		/**
67		* @var array<mixed>
68		*/
69		protected $metadata = [];
70
71		/**
72		* @var array
73		*/
74		protected $details;
75
76	74	public function __construct()
77		{
78	74	$this->trailer = new Header([], $this);
79	74	}
80
81	51	public function init()
82		{
83	51	$this->buildDictionary();
84
85	51	$this->buildDetails();
86
87		// Propagate init to objects.
88	51	foreach ($this->objects as $object) {
89	51	$object->getHeader()->init();
90	51	$object->init();
91		}
92	51	}
93
94		/**
95		* Build dictionary based on type header field.
96		*/
97	51	protected function buildDictionary()
98		{
99		// Build dictionary.
100	51	$this->dictionary = [];
101
102	51	foreach ($this->objects as $id => $object) {
103		// Cache objects by type and subtype
104	51	$type = $object->getHeader()->get('Type')->getContent();
105
106	51	if (null != $type) {
107	51	if (!isset($this->dictionary[$type])) {
108	51	$this->dictionary[$type] = [
109		'all' => [],
110		'subtype' => [],
111		];
112		}
113
114	51	$this->dictionary[$type]['all'][$id] = $object;
115
116	51	$subtype = $object->getHeader()->get('Subtype')->getContent();
117	51	if (null != $subtype) {
118	44	if (!isset($this->dictionary[$type]['subtype'][$subtype])) {
119	44	$this->dictionary[$type]['subtype'][$subtype] = [];
120		}
121	44	$this->dictionary[$type]['subtype'][$subtype][$id] = $object;
122		}
123		}
124		}
125	51	}
126
127		/**
128		* Build details array.
129		*/
130	51	protected function buildDetails()
131		{
132		// Build details array.
133	51	$details = [];
134
135		// Extract document info
136	51	if ($this->trailer->has('Info')) {
137		/** @var PDFObject $info */
138	42	$info = $this->trailer->get('Info');
139		// This could be an ElementMissing object, so we need to check for
140		// the getHeader method first.
141	42	if (null !== $info && method_exists($info, 'getHeader')) {
142	42	$details = $info->getHeader()->getDetails();
143		}
144		}
145
146		// Retrieve the page count
147		try {
148	51	$pages = $this->getPages();
149	50	$details['Pages'] = \count($pages);
150	2	} catch (\Exception $e) {
151	2	$details['Pages'] = 0;
152		}
153
154		// Decode and repair encoded document properties
155	51	foreach ($details as $key => $value) {
156	51	if (\is_string($value)) {
157		// If the string is already UTF-8 encoded, that means we only
158		// need to repair Adobe's ham-fisted insertion of line-feeds
159		// every ~127 characters, which doesn't seem to be multi-byte
160		// safe
161	41	if (mb_check_encoding($value, 'UTF-8')) {
162		// Remove literal backslash + line-feed "\\r"
163	41	$value = str_replace("\x5c\x0d", '', $value);
164
165		// Remove backslash plus bytes written into high part of
166		// multibyte unicode character
167	41	while (preg_match("/\x5c\x5c\xe0([\xb4-\xb8])(.)/", $value, $match)) {
168	1	$diff = (\ord($match[1]) - 182) * 64;
169	1	$newbyte = PDFDocEncoding::convertPDFDoc2UTF8(\chr(\ord($match[2]) + $diff));
170	1	$value = preg_replace("/\x5c\x5c\xe0".$match[1].$match[2].'/', $newbyte, $value);
171		}
172
173		// Remove bytes written into low part of multibyte unicode
174		// character
175	41	while (preg_match("/(.)\x9c\xe0([\xb3-\xb7])/", $value, $match)) {
176		$diff = \ord($match[2]) - 181;
177		$newbyte = \chr(\ord($match[1]) + $diff);
178		$value = preg_replace('/'.$match[1]."\x9c\xe0".$match[2].'/', $newbyte, $value);
179		}
180
181		// Remove this byte string that Adobe occasionally adds
182		// between two single byte characters in a unicode string
183	41	$value = str_replace("\xe5\xb0\x8d", '', $value);
184
185	41	$details[$key] = $value;
186		} else {
187		// If the string is just PDFDocEncoding, remove any line-feeds
188		// and decode the whole thing.
189	7	$value = str_replace("\\\r", '', $value);
190	7	$details[$key] = PDFDocEncoding::convertPDFDoc2UTF8($value);
191		}
192		}
193		}
194
195	51	$details = array_merge($details, $this->metadata);
196
197	51	$this->details = $details;
198	51	}
199
200		/**
201		* Extract XMP Metadata
202		*/
203	30	public function extractXMPMetadata(string $content): void
204		{
205	30	$xml = xml_parser_create();
206	30	xml_parser_set_option($xml, \XML_OPTION_SKIP_WHITE, 1);
207
208	30	if (1 === xml_parse_into_struct($xml, $content, $values, $index)) {
209		/*
210		* short overview about the following code parts:
211		*
212		* The output of xml_parse_into_struct is a single dimensional array (= $values), and the $stack is a last-on,
213		* first-off array of pointers to positions in $metadata, while iterating through it, that potentially turn the
214		* results into a more intuitive multi-dimensional array. When an "open" XML tag is encountered,
215		* we save the current $metadata context in the $stack, then create a child array of $metadata and
216		* make that the current $metadata context. When a "close" XML tag is encountered, the operations are
217		* reversed: the most recently added $metadata context from $stack (IOW, the parent of the current
218		* element) is set as the current $metadata context.
219		*/
220	30	$metadata = [];
221	30	$stack = [];
222	30	foreach ($values as $val) {
223		// Standardize to lowercase
224	30	$val['tag'] = strtolower($val['tag']);
225
226		// Ignore structural x: and rdf: XML elements
227	30	if (0 === strpos($val['tag'], 'x:')) {
228	30	continue;
229	30	} elseif (0 === strpos($val['tag'], 'rdf:') && 'rdf:li' != $val['tag']) {
230	30	continue;
231		}
232
233	30	switch ($val['type']) {
234	30	case 'open':
235		// Create an array of list items
236	28	if ('rdf:li' == $val['tag']) {
237	3	$metadata[] = [];
238
239		// Move up one level in the stack
240	3	$stack[\count($stack)] = &$metadata;
241	3	$metadata = &$metadata[\count($metadata) - 1];
242		} else {
243		// Else create an array of named values
244	28	$metadata[$val['tag']] = [];
245
246		// Move up one level in the stack
247	28	$stack[\count($stack)] = &$metadata;
248	28	$metadata = &$metadata[$val['tag']];
249		}
250	28	break;
251
252	30	case 'complete':
253	30	if (isset($val['value'])) {
254		// Assign a value to this list item
255	30	if ('rdf:li' == $val['tag']) {
256	27	$metadata[] = $val['value'];
257
258		// Else assign a value to this property
259		} else {
260	30	$metadata[$val['tag']] = $val['value'];
261		}
262		}
263	30	break;
264
265	28	case 'close':
266		// If the value of this property is a single-
267		// element array where the element is of type
268		// string, use the value of the first list item
269		// as the value for this property
270	28	if (\is_array($metadata) && isset($metadata[0]) && 1 == \count($metadata) && \is_string($metadata[0])) {
271	27	$metadata = $metadata[0];
272		}
273
274		// Move down one level in the stack
275	28	$metadata = &$stack[\count($stack) - 1];
276	28	unset($stack[\count($stack) - 1]);
277	28	break;
278		}
279		}
280
281		// Only use this metadata if it's referring to a PDF
282	30	if (isset($metadata['dc:format']) && 'application/pdf' == $metadata['dc:format']) {
283		// According to the XMP specifications: 'Conflict resolution
284		// for separate packets that describe the same resource is
285		// beyond the scope of this document.' - Section 6.1
286		// Source: https://www.adobe.com/devnet/xmp.html
287		// Source: https://github.com/adobe/XMP-Toolkit-SDK/blob/main/docs/XMPSpecificationPart1.pdf
288		// So if there are multiple XMP blocks, just merge the values
289		// of each found block over top of the existing values
290	13	$this->metadata = array_merge($this->metadata, $metadata);
291		}
292		}
293	30	xml_parser_free($xml);
294	30	}
295
296	1	public function getDictionary(): array
297		{
298	1	return $this->dictionary;
299		}
300
301		/**
302		* @param PDFObject[] $objects
303		*/
304	51	public function setObjects($objects = [])
305		{
306	51	$this->objects = (array) $objects;
307
308	51	$this->init();
309	51	}
310
311		/**
312		* @return PDFObject[]
313		*/
314	1	public function getObjects()
315		{
316	1	return $this->objects;
317		}
318
319		/**
320		* @return PDFObject\|Font\|Page\|Element\|null
321		*/
322	48	public function getObjectById(string $id)
323		{
324	48	if (isset($this->objects[$id])) {
325	48	return $this->objects[$id];
326		}
327
328	3	return null;
329		}
330
331	52	public function hasObjectsByType(string $type, string $subtype = null): bool
332		{
333	52	return 0 < \count($this->getObjectsByType($type, $subtype));
334		}
335
336	55	public function getObjectsByType(string $type, string $subtype = null): array
337		{
338	55	if (!isset($this->dictionary[$type])) {
339	12	return [];
340		}
341
342	50	if (null != $subtype) {
		0 ignored issues – show Bug introduced 2021-06-13 00:39 UTC by Report Bug Copy Issue Report It seems like you are loosely comparing `$subtype` of type `null\|string` against `null`; this is ambiguous if the string can be empty. Consider using a strict comparison `!==` instead. Loading history...
343		if (!isset($this->dictionary[$type]['subtype'][$subtype])) {
344		return [];
345		}
346
347		return $this->dictionary[$type]['subtype'][$subtype];
348		}
349
350	50	return $this->dictionary[$type]['all'];
351		}
352
353		/**
354		* @return Font[]
355		*/
356	27	public function getFonts()
357		{
358	27	return $this->getObjectsByType('Font');
359		}
360
361	21	public function getFirstFont(): ?Font
362		{
363	21	$fonts = $this->getFonts();
364	21	if ([] === $fonts) {
365	3	return null;
366		}
367
368	18	return reset($fonts);
369		}
370
371		/**
372		* @return Page[]
373		*
374		* @throws \Exception
375		*/
376	52	public function getPages()
377		{
378	52	if ($this->hasObjectsByType('Catalog')) {
379		// Search for catalog to list pages.
380	44	$catalogues = $this->getObjectsByType('Catalog');
381	44	$catalogue = reset($catalogues);
382
383		/** @var Pages $object */
384	44	$object = $catalogue->get('Pages');
385	44	if (method_exists($object, 'getPages')) {
386	44	return $object->getPages(true);
387		}
388		}
389
390	9	if ($this->hasObjectsByType('Pages')) {
391		// Search for pages to list kids.
392	1	$pages = [];
393
394		/** @var Pages[] $objects */
395	1	$objects = $this->getObjectsByType('Pages');
396	1	foreach ($objects as $object) {
397	1	$pages = array_merge($pages, $object->getPages(true));
398		}
399
400	1	return $pages;
401		}
402
403	9	if ($this->hasObjectsByType('Page')) {
404		// Search for 'page' (unordered pages).
405	7	$pages = $this->getObjectsByType('Page');
406
407	7	return array_values($pages);
408		}
409
410	3	throw new \Exception('Missing catalog.');
411		}
412
413	12	public function getText(int $pageLimit = null): string
414		{
415	12	$texts = [];
416	12	$pages = $this->getPages();
417
418		// Only use the first X number of pages if $pageLimit is set and numeric.
419	12	if (\is_int($pageLimit) && 0 < $pageLimit) {
420	1	$pages = \array_slice($pages, 0, $pageLimit);
421		}
422
423	12	foreach ($pages as $index => $page) {
424		/**
425		* In some cases, the $page variable may be null.
426		*/
427	12	if (null === $page) {
428		continue;
429		}
430	12	if ($text = trim($page->getText())) {
431	12	$texts[] = $text;
432		}
433		}
434
435	12	return implode("\n\n", $texts);
436		}
437
438		public function getTrailer(): Header
439		{
440		return $this->trailer;
441		}
442
443	43	public function setTrailer(Header $trailer)
444		{
445	43	$this->trailer = $trailer;
446	43	}
447
448	14	public function getDetails(): array
449		{
450	14	return $this->details;
451		}
452		}
453

smalot / pdfparser

Pull Request — master (#615)

Document::getDetails() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like