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

ElementArray.php in MxChat – AI Chatbot & Content Generation for WordPress 3.2.3, at includes/pdf-parser/src/Smalot/PdfParser/Element/ElementArray.php

140 lines 3.9 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\Element;
34
35	use Smalot\PdfParser\Document;
36	use Smalot\PdfParser\Element;
37	use Smalot\PdfParser\Header;
38	use Smalot\PdfParser\PDFObject;
39
40	/**
41	* Class ElementArray
42	*/
43	class ElementArray extends Element
44	{
45	public function __construct($value, ?Document $document = null)
46	{
47	parent::__construct($value, $document);
48	}
49
50	public function getContent()
51	{
52	foreach ($this->value as $name => $element) {
53	$this->resolveXRef($name);
54	}
55
56	return parent::getContent();
57	}
58
59	public function getRawContent(): array
60	{
61	return $this->value;
62	}
63
64	public function getDetails(bool $deep = true): array
65	{
66	$values = [];
67	$elements = $this->getContent();
68
69	foreach ($elements as $key => $element) {
70	if ($element instanceof Header && $deep) {
71	$values[$key] = $element->getDetails($deep);
72	} elseif ($element instanceof PDFObject && $deep) {
73	$values[$key] = $element->getDetails(false);
74	} elseif ($element instanceof self) {
75	if ($deep) {
76	$values[$key] = $element->getDetails();
77	}
78	} elseif ($element instanceof Element && !($element instanceof self)) {
79	$values[$key] = $element->getContent();
80	}
81	}
82
83	return $values;
84	}
85
86	public function __toString(): string
87	{
88	return implode(',', $this->value);
89	}
90
91	/**
92	* @return Element\|PDFObject
93	*/
94	protected function resolveXRef(string $name)
95	{
96	if (($obj = $this->value[$name]) instanceof ElementXRef) {
97	/** @var ElementXRef $obj */
98	$obj = $this->document->getObjectById($obj->getId());
99	$this->value[$name] = $obj;
100	}
101
102	return $this->value[$name];
103	}
104
105	/**
106	* @todo: These methods return mixed and mismatched types throughout the hierarchy
107	*
108	* @return bool\|ElementArray
109	*/
110	public static function parse(string $content, ?Document $document = null, int &$offset = 0)
111	{
112	if (preg_match('/^\s\[(?P<array>.)/is', $content, $match)) {
113	preg_match_all('/(.*?)(\[\|\])/s', trim($content), $matches);
114
115	$level = 0;
116	$sub = '';
117	foreach ($matches[0] as $part) {
118	$sub .= $part;
119	$level += (false !== strpos($part, '[') ? 1 : -1);
120	if ($level <= 0) {
121	break;
122	}
123	}
124
125	// Removes 1 level [ and ].
126	$sub = substr(trim($sub), 1, -1);
127	$sub_offset = 0;
128	$values = Element::parse($sub, $document, $sub_offset, true);
129
130	$offset += strpos($content, '[') + 1;
131	// Find next ']' position
132	$offset += \strlen($sub) + 1;
133
134	return new self($values, $document);
135	}
136
137	return false;
138	}
139	}
140