mxchat-basic / includes / pdf-parser / src / Smalot / PdfParser / Parser.php

Parser.php in MxChat – AI Chatbot & Content Generation for WordPress 2.6.1, at includes/pdf-parser/src/Smalot/PdfParser/Parser.php

332 lines 10.6 KB

Raw Download Zip

1	<?php
2
3	/**
4	* @file
5	* This file is part of the PdfParser library.
6	*
7	* @author Sébastien MALOT <sebastien@malot.fr>
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 <sebastien@malot.fr>
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 $rawDataParser;
62
63	public function __construct($cfg = [], ?Config $config = null)
64	{
65	$this->config = $config ?: new Config();
66	$this->rawDataParser = new RawDataParser($cfg, $this->config);
67	}
68
69	public function getConfig(): Config
70	{
71	return $this->config;
72	}
73
74	/**
75	* @throws \Exception
76	*/
77	public function parseFile(string $filename): Document
78	{
79	$content = file_get_contents($filename);
80
81	/*
82	* 2018/06/20 @doganoo as multiple times a
83	* users have complained that the parseFile()
84	* method dies silently, it is an better option
85	* to remove the error control operator (@) and
86	* let the users know that the method throws an exception
87	* by adding @throws tag to PHPDoc.
88	*
89	* See here for an example: https://github.com/smalot/pdfparser/issues/204
90	*/
91	return $this->parseContent($content);
92	}
93
94	/**
95	* @param string $content PDF content to parse
96	*
97	* @throws \Exception if secured PDF file was detected
98	* @throws \Exception if no object list was found
99	*/
100	public function parseContent(string $content): Document
101	{
102	// Create structure from raw data.
103	list($xref, $data) = $this->rawDataParser->parseData($content);
104
105	if (isset($xref['trailer']['encrypt']) && false === $this->config->getIgnoreEncryption()) {
106	throw new \Exception('Secured pdf file are currently not supported.');
107	}
108
109	if (empty($data)) {
110	throw new \Exception('Object list not found. Possible secured file.');
111	}
112
113	// Create destination object.
114	$document = new Document();
115	$this->objects = [];
116
117	foreach ($data as $id => $structure) {
118	$this->parseObject($id, $structure, $document);
119	unset($data[$id]);
120	}
121
122	$document->setTrailer($this->parseTrailer($xref['trailer'], $document));
123	$document->setObjects($this->objects);
124
125	return $document;
126	}
127
128	protected function parseTrailer(array $structure, ?Document $document)
129	{
130	$trailer = [];
131
132	foreach ($structure as $name => $values) {
133	$name = ucfirst($name);
134
135	if (is_numeric($values)) {
136	$trailer[$name] = new ElementNumeric($values);
137	} elseif (\is_array($values)) {
138	$value = $this->parseTrailer($values, null);
139	$trailer[$name] = new ElementArray($value, null);
140	} elseif (false !== strpos($values, '_')) {
141	$trailer[$name] = new ElementXRef($values, $document);
142	} else {
143	$trailer[$name] = $this->parseHeaderElement('(', $values, $document);
144	}
145	}
146
147	return new Header($trailer, $document);
148	}
149
150	protected function parseObject(string $id, array $structure, ?Document $document)
151	{
152	$header = new Header([], $document);
153	$content = '';
154
155	foreach ($structure as $position => $part) {
156	if (\is_int($part)) {
157	$part = [null, null];
158	}
159	switch ($part[0]) {
160	case '[':
161	$elements = [];
162
163	foreach ($part[1] as $sub_element) {
164	$sub_type = $sub_element[0];
165	$sub_value = $sub_element[1];
166	$elements[] = $this->parseHeaderElement($sub_type, $sub_value, $document);
167	}
168
169	$header = new Header($elements, $document);
170	break;
171
172	case '<<':
173	$header = $this->parseHeader($part[1], $document);
174	break;
175
176	case 'stream':
177	$content = isset($part[3][0]) ? $part[3][0] : $part[1];
178
179	if ($header->get('Type')->equals('ObjStm')) {
180	$match = [];
181
182	// Split xrefs and contents.
183	preg_match('/^((\d+\s+\d+\s))(.*)$/s', $content, $match);
184	$content = $match[3];
185
186	// Extract xrefs.
187	$xrefs = preg_split(
188	'/(\d+\s+\d+\s*)/s',
189	$match[1],
190	-1,
191	\PREG_SPLIT_NO_EMPTY \| \PREG_SPLIT_DELIM_CAPTURE
192	);
193	$table = [];
194
195	foreach ($xrefs as $xref) {
196	list($id, $position) = preg_split("/\s+/", trim($xref));
197	$table[$position] = $id;
198	}
199
200	ksort($table);
201
202	$ids = array_values($table);
203	$positions = array_keys($table);
204
205	foreach ($positions as $index => $position) {
206	$id = $ids[$index].'_0';
207	$next_position = isset($positions[$index + 1]) ? $positions[$index + 1] : \strlen($content);
208	$sub_content = substr($content, $position, (int) $next_position - (int) $position);
209
210	$sub_header = Header::parse($sub_content, $document);
211	$object = PDFObject::factory($document, $sub_header, '', $this->config);
212	$this->objects[$id] = $object;
213	}
214
215	// It is not necessary to store this content.
216
217	return;
218	} elseif ($header->get('Type')->equals('Metadata')) {
219	// Attempt to parse XMP XML Metadata
220	$document->extractXMPMetadata($content);
221	}
222	break;
223
224	default:
225	if ('null' != $part) {
226	$element = $this->parseHeaderElement($part[0], $part[1], $document);
227
228	if ($element) {
229	$header = new Header([$element], $document);
230	}
231	}
232	break;
233	}
234	}
235
236	if (!isset($this->objects[$id])) {
237	$this->objects[$id] = PDFObject::factory($document, $header, $content, $this->config);
238	}
239	}
240
241	/**
242	* @throws \Exception
243	*/
244	protected function parseHeader(array $structure, ?Document $document): Header
245	{
246	$elements = [];
247	$count = \count($structure);
248
249	for ($position = 0; $position < $count; $position += 2) {
250	$name = $structure[$position][1];
251	$type = $structure[$position + 1][0];
252	$value = $structure[$position + 1][1];
253
254	$elements[$name] = $this->parseHeaderElement($type, $value, $document);
255	}
256
257	return new Header($elements, $document);
258	}
259
260	/**
261	* @param string\|array $value
262	*
263	* @return Element\|Header\|null
264	*
265	* @throws \Exception
266	*/
267	protected function parseHeaderElement(?string $type, $value, ?Document $document)
268	{
269	$valueIsEmpty = null == $value \|\| '' == $value \|\| false == $value;
270	if (('<<' === $type \|\| '>>' === $type) && $valueIsEmpty) {
271	$value = [];
272	}
273
274	switch ($type) {
275	case '<<':
276	case '>>':
277	$header = $this->parseHeader($value, $document);
278	PDFObject::factory($document, $header, null, $this->config);
279
280	return $header;
281
282	case 'numeric':
283	return new ElementNumeric($value);
284
285	case 'boolean':
286	return new ElementBoolean($value);
287
288	case 'null':
289	return new ElementNull();
290
291	case '(':
292	if ($date = ElementDate::parse('('.$value.')', $document)) {
293	return $date;
294	}
295
296	return ElementString::parse('('.$value.')', $document);
297
298	case '<':
299	return $this->parseHeaderElement('(', ElementHexa::decode($value), $document);
300
301	case '/':
302	return ElementName::parse('/'.$value, $document);
303
304	case 'ojbref': // old mistake in tcpdf parser
305	case 'objref':
306	return new ElementXRef($value, $document);
307
308	case '[':
309	$values = [];
310
311	if (\is_array($value)) {
312	foreach ($value as $sub_element) {
313	$sub_type = $sub_element[0];
314	$sub_value = $sub_element[1];
315	$values[] = $this->parseHeaderElement($sub_type, $sub_value, $document);
316	}
317	}
318
319	return new ElementArray($values, $document);
320
321	case 'endstream':
322	case 'obj': // I don't know what it means but got my project fixed.
323	case '':
324	// Nothing to do with.
325	return null;
326
327	default:
328	throw new \Exception('Invalid type: "'.$type.'".');
329	}
330	}
331	}
332