| 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\ElementNumeric; |
| 36 |
use Smalot\PdfParser\Encoding\EncodingLocator; |
| 37 |
use Smalot\PdfParser\Encoding\PostScriptGlyphs; |
| 38 |
use Smalot\PdfParser\Exception\EncodingNotFoundException; |
| 39 |
|
| 40 |
/** |
| 41 |
* Class Encoding |
| 42 |
*/ |
| 43 |
class Encoding extends PDFObject |
| 44 |
{ |
| 45 |
/** |
| 46 |
* @var array |
| 47 |
*/ |
| 48 |
protected $encoding; |
| 49 |
|
| 50 |
/** |
| 51 |
* @var array |
| 52 |
*/ |
| 53 |
protected $differences; |
| 54 |
|
| 55 |
/** |
| 56 |
* @var array |
| 57 |
*/ |
| 58 |
protected $mapping; |
| 59 |
|
| 60 |
public function init() |
| 61 |
{ |
| 62 |
$this->mapping = []; |
| 63 |
$this->differences = []; |
| 64 |
$this->encoding = []; |
| 65 |
|
| 66 |
if ($this->has('BaseEncoding')) { |
| 67 |
$this->encoding = EncodingLocator::getEncoding($this->getEncodingClass())->getTranslations(); |
| 68 |
|
| 69 |
// Build table including differences. |
| 70 |
$differences = $this->get('Differences')->getContent(); |
| 71 |
$code = 0; |
| 72 |
|
| 73 |
if (!\is_array($differences)) { |
| 74 |
return; |
| 75 |
} |
| 76 |
|
| 77 |
foreach ($differences as $difference) { |
| 78 |
/** @var ElementNumeric $difference */ |
| 79 |
if ($difference instanceof ElementNumeric) { |
| 80 |
$code = $difference->getContent(); |
| 81 |
continue; |
| 82 |
} |
| 83 |
|
| 84 |
// ElementName |
| 85 |
$this->differences[$code] = $difference; |
| 86 |
if (\is_object($difference)) { |
| 87 |
$this->differences[$code] = $difference->getContent(); |
| 88 |
} |
| 89 |
|
| 90 |
// For the next char. |
| 91 |
++$code; |
| 92 |
} |
| 93 |
|
| 94 |
$this->mapping = $this->encoding; |
| 95 |
foreach ($this->differences as $code => $difference) { |
| 96 |
/* @var string $difference */ |
| 97 |
$this->mapping[$code] = $difference; |
| 98 |
} |
| 99 |
} |
| 100 |
} |
| 101 |
|
| 102 |
public function getDetails(bool $deep = true): array |
| 103 |
{ |
| 104 |
$details = []; |
| 105 |
|
| 106 |
$details['BaseEncoding'] = ($this->has('BaseEncoding') ? (string) $this->get('BaseEncoding') : 'Ansi'); |
| 107 |
$details['Differences'] = ($this->has('Differences') ? (string) $this->get('Differences') : ''); |
| 108 |
|
| 109 |
$details += parent::getDetails($deep); |
| 110 |
|
| 111 |
return $details; |
| 112 |
} |
| 113 |
|
| 114 |
public function translateChar($dec): ?int |
| 115 |
{ |
| 116 |
if (isset($this->mapping[$dec])) { |
| 117 |
$dec = $this->mapping[$dec]; |
| 118 |
} |
| 119 |
|
| 120 |
return PostScriptGlyphs::getCodePoint($dec); |
| 121 |
} |
| 122 |
|
| 123 |
/** |
| 124 |
* Returns encoding class name if available or empty string (only prior PHP 7.4). |
| 125 |
* |
| 126 |
* @throws \Exception On PHP 7.4+ an exception is thrown if encoding class doesn't exist. |
| 127 |
*/ |
| 128 |
public function __toString(): string |
| 129 |
{ |
| 130 |
try { |
| 131 |
return $this->getEncodingClass(); |
| 132 |
} catch (\Exception $e) { |
| 133 |
// prior to PHP 7.4 toString has to return an empty string. |
| 134 |
if (version_compare(\PHP_VERSION, '7.4.0', '<')) { |
| 135 |
return ''; |
| 136 |
} |
| 137 |
throw $e; |
| 138 |
} |
| 139 |
} |
| 140 |
|
| 141 |
/** |
| 142 |
* @throws EncodingNotFoundException |
| 143 |
*/ |
| 144 |
protected function getEncodingClass(): string |
| 145 |
{ |
| 146 |
// Load reference table charset. |
| 147 |
$baseEncoding = preg_replace('/[^A-Z0-9]/is', '', $this->get('BaseEncoding')->getContent()); |
| 148 |
|
| 149 |
// Check for empty BaseEncoding field value |
| 150 |
if (!\is_string($baseEncoding) || 0 == \strlen($baseEncoding)) { |
| 151 |
$baseEncoding = 'StandardEncoding'; |
| 152 |
} |
| 153 |
|
| 154 |
$className = '\\Smalot\\PdfParser\\Encoding\\'.$baseEncoding; |
| 155 |
|
| 156 |
if (!class_exists($className)) { |
| 157 |
throw new EncodingNotFoundException('Missing encoding data for: "'.$baseEncoding.'".'); |
| 158 |
} |
| 159 |
|
| 160 |
return $className; |
| 161 |
} |
| 162 |
} |
| 163 |
|