Document::getText() - Code Metrics - Inspection of "Enable PDFDocEncoding support for metadata" - smalot/pdfparser - Measure and Improve Code Quality continuously with Scrutinizer

Test Failed

Pull Request — master (#611)

unknown

created 2023-07-06 13:29 UTC

Document::getText() A

↳ Parent: Document

Complexity

Conditions	6
Paths	8

Size

Total Lines	23
Code Lines	10

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	0
CRAP Score	42

Importance

Changes	3
Bugs	1	Features	0

Metric	Value
cc	6
eloc	10
c	3
b	1
f	0
nc	8
nop	1
dl	0
loc	23
ccs	0
cts	0
cp	0
crap	42
rs	9.2222

<?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;

                // If the string is just PDFDocEncoding, remove any line-feeds
                // and decode the whole thing.
                } else {
                    $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	72	protected $metadata = [];
70
71	72	/**
72	72	* @var array
73		*/
74	49	protected $details;
75
76	49	public function __construct()
77		{
78	49	$this->trailer = new Header([], $this);
79		}
80
81	49	public function init()
82	49	{
83	49	$this->buildDictionary();
84
85	49	$this->buildDetails();
86
87		// Propagate init to objects.
88		foreach ($this->objects as $object) {
89		$object->getHeader()->init();
90	49	$object->init();
91		}
92		}
93	49
94		/**
95	49	* Build dictionary based on type header field.
96		*/
97	49	protected function buildDictionary()
98		{
99	49	// Build dictionary.
100	49	$this->dictionary = [];
101	49
102		foreach ($this->objects as $id => $object) {
103		// Cache objects by type and subtype
104		$type = $object->getHeader()->get('Type')->getContent();
105
106		if (null != $type) {
107	49	if (!isset($this->dictionary[$type])) {
108		$this->dictionary[$type] = [
109	49	'all' => [],
110	49	'subtype' => [],
111	42	];
112	42	}
113
114	42	$this->dictionary[$type]['all'][$id] = $object;
115
116		$subtype = $object->getHeader()->get('Subtype')->getContent();
117		if (null != $subtype) {
118	49	if (!isset($this->dictionary[$type]['subtype'][$subtype])) {
119		$this->dictionary[$type]['subtype'][$subtype] = [];
120		}
121		$this->dictionary[$type]['subtype'][$subtype][$id] = $object;
122		}
123	49	}
124		}
125		}
126	49
127		/**
128		* Build details array.
129	49	*/
130		protected function buildDetails()
131	40	{
132		// Build details array.
133		$details = [];
134	40
135	40	// Extract document info
136		if ($this->trailer->has('Info')) {
137		/** @var PDFObject $info */
138		$info = $this->trailer->get('Info');
139		// This could be an ElementMissing object, so we need to check for
140		// the getHeader method first.
141	49	if (null !== $info && method_exists($info, 'getHeader')) {
142	48	$details = $info->getHeader()->getDetails();
143	2	}
144	2	}
145
146		// Retrieve the page count
147	49	try {
148	49	$pages = $this->getPages();
149		$details['Pages'] = \count($pages);
150	1	} catch (\Exception $e) {
151		$details['Pages'] = 0;
152	1	}
153
154		// Decode and repair encoded document properties
155		foreach ($details as $key => $value) {
156		if (\is_string($value)) {
157
158	49	// If the string is already UTF-8 encoded, that means we only
159		// need to repair Adobe's ham-fisted insertion of line-feeds
160	49	// every ~127 characters, which doesn't seem to be multi-byte
161		// safe
162	49	if (mb_check_encoding($value, 'UTF-8')) {
163	49
164		// Remove literal backslash + line-feed "\\r"
165		$value = str_replace("\x5c\x0d", '', $value);
166
167		// Remove backslash plus bytes written into high part of
168	1	// multibyte unicode character
169		while (preg_match("/\x5c\x5c\xe0([\xb4-\xb8])(.)/", $value, $match)) {
170	1	$diff = (\ord($match[1]) - 182) * 64;
171		$newbyte = PDFDocEncoding::convertPDFDoc2UTF8(\chr(\ord($match[2]) + $diff));
172		$value = preg_replace("/\x5c\x5c\xe0".$match[1].$match[2]."/", $newbyte, $value);
173		}
174
175		// Remove bytes written into low part of multibyte unicode
176	46	// character
177		while (preg_match("/(.)\x9c\xe0([\xb3-\xb7])/", $value, $match)) {
178	46	$diff = \ord($match[2]) - 181;
179	46	$newbyte = \chr(\ord($match[1]) + $diff);
180		$value = preg_replace("/".$match[1]."\x9c\xe0".$match[2]."/", $newbyte, $value);
181		}
182	3
183		// Remove this byte string that Adobe occasionally adds
184		// between two single byte characters in a unicode string
185	50	$value = str_replace("\xe5\xb0\x8d", '', $value);
186
187	50	$details[$key] = $value;
188
189		// If the string is just PDFDocEncoding, remove any line-feeds
190	53	// and decode the whole thing.
191		} else {
192	53	$value = str_replace("\\\r", '', $value);
193	12	$details[$key] = PDFDocEncoding::convertPDFDoc2UTF8($value);
194		}
195		}
196	48	}
197
198		$details = array_merge($details, $this->metadata);
199
200		$this->details = $details;
201		}
202
203		/**
204	48	* Extract XMP Metadata
205		*/
206		public function extractXMPMetadata(string $content): void
207		{
208		$xml = xml_parser_create();
209		xml_parser_set_option($xml, \XML_OPTION_SKIP_WHITE, 1);
210	27
211		if (1 === xml_parse_into_struct($xml, $content, $values, $index)) {
212	27	/*
213		* short overview about the following code parts:
214		*
215	21	* The output of xml_parse_into_struct is a single dimensional array (= $values), and the $stack is a last-on,
216		* first-off array of pointers to positions in $metadata, while iterating through it, that potentially turn the
217	21	* results into a more intuitive multi-dimensional array. When an "open" XML tag is encountered,
218	21	* we save the current $metadata context in the $stack, then create a child array of $metadata and
219	3	* make that the current $metadata context. When a "close" XML tag is encountered, the operations are
220		* reversed: the most recently added $metadata context from $stack (IOW, the parent of the current
221		* element) is set as the current $metadata context.
222	18	*/
223		$metadata = [];
224		$stack = [];
225		foreach ($values as $val) {
226		// Standardize to lowercase
227		$val['tag'] = strtolower($val['tag']);
228
229		// Ignore structural x: and rdf: XML elements
230	50	if (0 === strpos($val['tag'], 'x:')) {
231		continue;
232	50	} elseif (0 === strpos($val['tag'], 'rdf:') && 'rdf:li' != $val['tag']) {
233		continue;
234	42	}
235	42
236		switch ($val['type']) {
237		case 'open':
238	42	// Create an array of list items
239	42	if ('rdf:li' == $val['tag']) {
240	42	$metadata[] = [];
241
242		// Move up one level in the stack
243		$stack[\count($stack)] = &$metadata;
244	9	$metadata = &$metadata[\count($metadata) - 1];
245		} else {
246	1	// Else create an array of named values
247		$metadata[$val['tag']] = [];
248
249	1	// Move up one level in the stack
250	1	$stack[\count($stack)] = &$metadata;
251	1	$metadata = &$metadata[$val['tag']];
252		}
253		break;
254	1
255		case 'complete':
256		if (isset($val['value'])) {
257	9	// Assign a value to this list item
258		if ('rdf:li' == $val['tag']) {
259	7	$metadata[] = $val['value'];
260
261	7	// Else assign a value to this property
262		} else {
263		$metadata[$val['tag']] = $val['value'];
264	3	}
265		}
266		break;
267	12
268		case 'close':
269	12	// If the value of this property is a single-
270	12	// element array where the element is of type
271		// string, use the value of the first list item
272		// as the value for this property
273	12	if (\is_array($metadata) && isset($metadata[0]) && 1 == \count($metadata) && \is_string($metadata[0])) {
274	1	$metadata = $metadata[0];
275		}
276
277	12	// Move down one level in the stack
278		$metadata = &$stack[\count($stack) - 1];
279		unset($stack[\count($stack) - 1]);
280		break;
281	12	}
282		}
283
284	12	// Only use this metadata if it's referring to a PDF
285	12	if (isset($metadata['dc:format']) && 'application/pdf' == $metadata['dc:format']) {
286		// According to the XMP specifications: 'Conflict resolution
287		// for separate packets that describe the same resource is
288		// beyond the scope of this document.' - Section 6.1
289	12	// Source: https://www.adobe.com/devnet/xmp.html
290		// Source: https://github.com/adobe/XMP-Toolkit-SDK/blob/main/docs/XMPSpecificationPart1.pdf
291		// So if there are multiple XMP blocks, just merge the values
292		// of each found block over top of the existing values
293		$this->metadata = array_merge($this->metadata, $metadata);
294		}
295		}
296		xml_parser_free($xml);
297	41	}
298
299	41	public function getDictionary(): array
300	41	{
301		return $this->dictionary;
302	12	}
303
304	12	/**
305		* @param PDFObject[] $objects
306		*/
307		public function setObjects($objects = [])
308		{
309		$this->objects = (array) $objects;
310
311		$this->init();
312		}
313
314		/**
315		* @return PDFObject[]
316		*/
317		public function getObjects()
318		{
319		return $this->objects;
320		}
321
322		/**
323		* @return PDFObject\|Font\|Page\|Element\|null
324		*/
325		public function getObjectById(string $id)
326		{
327		if (isset($this->objects[$id])) {
328		return $this->objects[$id];
329		}
330
331		return null;
332		}
333
334		public function hasObjectsByType(string $type, string $subtype = null): bool
335		{
336		return 0 < \count($this->getObjectsByType($type, $subtype));
337		}
338
339		public function getObjectsByType(string $type, string $subtype = null): array
340		{
341		if (!isset($this->dictionary[$type])) {
342		return [];
343		}
344
345		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...
346		if (!isset($this->dictionary[$type]['subtype'][$subtype])) {
347		return [];
348		}
349
350		return $this->dictionary[$type]['subtype'][$subtype];
351		}
352
353		return $this->dictionary[$type]['all'];
354		}
355
356		/**
357		* @return Font[]
358		*/
359		public function getFonts()
360		{
361		return $this->getObjectsByType('Font');
362		}
363
364		public function getFirstFont(): ?Font
365		{
366		$fonts = $this->getFonts();
367		if ([] === $fonts) {
368		return null;
369		}
370
371		return reset($fonts);
372		}
373
374		/**
375		* @return Page[]
376		*
377		* @throws \Exception
378		*/
379		public function getPages()
380		{
381		if ($this->hasObjectsByType('Catalog')) {
382		// Search for catalog to list pages.
383		$catalogues = $this->getObjectsByType('Catalog');
384		$catalogue = reset($catalogues);
385
386		/** @var Pages $object */
387		$object = $catalogue->get('Pages');
388		if (method_exists($object, 'getPages')) {
389		return $object->getPages(true);
390		}
391		}
392
393		if ($this->hasObjectsByType('Pages')) {
394		// Search for pages to list kids.
395		$pages = [];
396
397		/** @var Pages[] $objects */
398		$objects = $this->getObjectsByType('Pages');
399		foreach ($objects as $object) {
400		$pages = array_merge($pages, $object->getPages(true));
401		}
402
403		return $pages;
404		}
405
406		if ($this->hasObjectsByType('Page')) {
407		// Search for 'page' (unordered pages).
408		$pages = $this->getObjectsByType('Page');
409
410		return array_values($pages);
411		}
412
413		throw new \Exception('Missing catalog.');
414		}
415
416		public function getText(int $pageLimit = null): string
417		{
418		$texts = [];
419		$pages = $this->getPages();
420
421		// Only use the first X number of pages if $pageLimit is set and numeric.
422		if (\is_int($pageLimit) && 0 < $pageLimit) {
423		$pages = \array_slice($pages, 0, $pageLimit);
424		}
425
426		foreach ($pages as $index => $page) {
427		/**
428		* In some cases, the $page variable may be null.
429		*/
430		if (null === $page) {
431		continue;
432		}
433		if ($text = trim($page->getText())) {
434		$texts[] = $text;
435		}
436		}
437
438		return implode("\n\n", $texts);
439		}
440
441		public function getTrailer(): Header
442		{
443		return $this->trailer;
444		}
445
446		public function setTrailer(Header $trailer)
447		{
448		$this->trailer = $trailer;
449		}
450
451		public function getDetails(): array
452		{
453		return $this->details;
454		}
455		}
456

smalot / pdfparser

Pull Request — master (#611)

Document::getText() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like