| 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 |
|
| 37 |
/** |
| 38 |
* Class ElementHexa |
| 39 |
*/ |
| 40 |
class ElementHexa extends ElementString |
| 41 |
{ |
| 42 |
/** |
| 43 |
* @return bool|ElementHexa|ElementDate |
| 44 |
*/ |
| 45 |
public static function parse(string $content, ?Document $document = null, int &$offset = 0) |
| 46 |
{ |
| 47 |
if (preg_match('/^\s*\<(?P<name>[A-F0-9]+)\>/is', $content, $match)) { |
| 48 |
$name = $match['name']; |
| 49 |
$offset += strpos($content, '<'.$name) + \strlen($name) + 2; // 1 for '>' |
| 50 |
// repackage string as standard |
| 51 |
$name = '('.self::decode($name).')'; |
| 52 |
$element = ElementDate::parse($name, $document); |
| 53 |
|
| 54 |
if (!$element) { |
| 55 |
$element = ElementString::parse($name, $document); |
| 56 |
} |
| 57 |
|
| 58 |
return $element; |
| 59 |
} |
| 60 |
|
| 61 |
return false; |
| 62 |
} |
| 63 |
|
| 64 |
public static function decode(string $value): string |
| 65 |
{ |
| 66 |
$text = ''; |
| 67 |
|
| 68 |
// Filter $value of non-hexadecimal characters |
| 69 |
$value = (string) preg_replace('/[^0-9a-f]/i', '', $value); |
| 70 |
|
| 71 |
// Check for leading zeros (4-byte hexadecimal indicator), or |
| 72 |
// the BE BOM |
| 73 |
if ('00' === substr($value, 0, 2) || 'feff' === strtolower(substr($value, 0, 4))) { |
| 74 |
$value = (string) preg_replace('/^feff/i', '', $value); |
| 75 |
for ($i = 0, $length = \strlen($value); $i < $length; $i += 4) { |
| 76 |
$hex = substr($value, $i, 4); |
| 77 |
$text .= '&#'.str_pad(hexdec($hex), 4, '0', \STR_PAD_LEFT).';'; |
| 78 |
} |
| 79 |
} else { |
| 80 |
// Otherwise decode this as 2-byte hexadecimal |
| 81 |
for ($i = 0, $length = \strlen($value); $i < $length; $i += 2) { |
| 82 |
$hex = substr($value, $i, 2); |
| 83 |
$text .= \chr(hexdec($hex)); |
| 84 |
} |
| 85 |
} |
| 86 |
|
| 87 |
$text = html_entity_decode($text, \ENT_NOQUOTES, 'UTF-8'); |
| 88 |
|
| 89 |
return $text; |
| 90 |
} |
| 91 |
} |
| 92 |
|
