Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
96.77% |
30 / 31 |
|
66.67% |
2 / 3 |
CRAP | |
0.00% |
0 / 1 |
| Extractor | |
96.77% |
30 / 31 |
|
66.67% |
2 / 3 |
11 | |
0.00% |
0 / 1 |
| __construct | |
50.00% |
1 / 2 |
|
0.00% |
0 / 1 |
2.50 | |||
| countPages | |
100.00% |
7 / 7 |
|
100.00% |
1 / 1 |
2 | |||
| extract | |
100.00% |
22 / 22 |
|
100.00% |
1 / 1 |
7 | |||
| 1 | <?php |
| 2 | declare(strict_types=1); |
| 3 | /** |
| 4 | * Pop PHP Framework (https://www.popphp.org/) |
| 5 | * |
| 6 | * @link https://github.com/popphp/popphp-framework |
| 7 | * @author Nick Sagona, III <nick@popphp.org> |
| 8 | * @copyright Copyright (c) 2009-2026 Nick Sagona, III |
| 9 | * @license https://www.popphp.org/license New BSD License |
| 10 | */ |
| 11 | |
| 12 | /** |
| 13 | * @namespace |
| 14 | */ |
| 15 | namespace Pop\Pdf\Build\Image; |
| 16 | |
| 17 | use Pop\Pdf\Build\Exception; |
| 18 | |
| 19 | /** |
| 20 | * Pdf page-to-image extractor class |
| 21 | * |
| 22 | * Rasterizes pages of an existing PDF into standalone image files via |
| 23 | * Imagick. The opposite direction of Parser (which turns a raster image |
| 24 | * into a PDF page). |
| 25 | * |
| 26 | * @category Pop |
| 27 | * @package Pop\Pdf |
| 28 | * @author Nick Sagona, III <nick@popphp.org> |
| 29 | * @copyright Copyright (c) 2009-2026 Nick Sagona, III |
| 30 | * @license https://www.popphp.org/license New BSD License |
| 31 | * @version 6.2.0 |
| 32 | */ |
| 33 | class Extractor |
| 34 | { |
| 35 | |
| 36 | /** |
| 37 | * Supported output image formats |
| 38 | * @var array |
| 39 | */ |
| 40 | protected const array SUPPORTED_FORMATS = ['jpg', 'jpeg', 'png', 'webp', 'tiff', 'tif']; |
| 41 | |
| 42 | /** |
| 43 | * Constructor |
| 44 | * |
| 45 | * Instantiate the extractor object |
| 46 | * |
| 47 | * @throws Exception |
| 48 | */ |
| 49 | public function __construct() |
| 50 | { |
| 51 | if (!class_exists('Imagick', false)) { |
| 52 | throw new Exception('Error: The Imagick extension is required to extract PDF pages as images.'); |
| 53 | } |
| 54 | } |
| 55 | |
| 56 | /** |
| 57 | * Get the total number of pages in the PDF file |
| 58 | * |
| 59 | * @param string $file |
| 60 | * @throws Exception |
| 61 | * @return int |
| 62 | */ |
| 63 | public function countPages(string $file): int |
| 64 | { |
| 65 | if (!file_exists($file)) { |
| 66 | throw new Exception("Error: The PDF file '{$file}' does not exist."); |
| 67 | } |
| 68 | |
| 69 | $imagick = new \Imagick(); |
| 70 | $imagick->pingImage($file); |
| 71 | $totalPages = $imagick->getNumberImages(); |
| 72 | $imagick->clear(); |
| 73 | |
| 74 | return $totalPages; |
| 75 | } |
| 76 | |
| 77 | /** |
| 78 | * Extract the given page numbers of the PDF file as individual image files |
| 79 | * |
| 80 | * @param string $file |
| 81 | * @param string $location |
| 82 | * @param string $format |
| 83 | * @param int $resolution |
| 84 | * @param string $filenameFormat sprintf() format string, given the file's basename and the |
| 85 | * 1-indexed page number (e.g. '%1$s-%2$02d' => 'document-01', |
| 86 | * 'page-%2$02d' => 'page-01') |
| 87 | * @param array $pageNumbers 1-indexed page numbers to extract |
| 88 | * @throws Exception |
| 89 | * @return array |
| 90 | */ |
| 91 | public function extract( |
| 92 | string $file, string $location, string $format, int $resolution, string $filenameFormat, array $pageNumbers |
| 93 | ): array |
| 94 | { |
| 95 | if (!file_exists($file)) { |
| 96 | throw new Exception("Error: The PDF file '{$file}' does not exist."); |
| 97 | } |
| 98 | if (!is_dir($location) || !is_writable($location)) { |
| 99 | throw new Exception("Error: The location '{$location}' is not a writable directory."); |
| 100 | } |
| 101 | |
| 102 | $format = strtolower($format); |
| 103 | if (!in_array($format, self::SUPPORTED_FORMATS)) { |
| 104 | throw new Exception("Error: The format '{$format}' is not supported."); |
| 105 | } |
| 106 | |
| 107 | $basename = pathinfo($file, PATHINFO_FILENAME); |
| 108 | $location = rtrim($location, '/\\'); |
| 109 | $images = []; |
| 110 | |
| 111 | foreach ($pageNumbers as $pageNum) { |
| 112 | // setResolution() must be called before readImage() - Imagick |
| 113 | // only honors DPI at rasterization time, not after the fact. |
| 114 | $page = new \Imagick(); |
| 115 | $page->setResolution($resolution, $resolution); |
| 116 | $page->readImage($file . '[' . ($pageNum - 1) . ']'); |
| 117 | $page->setImageFormat($format); |
| 118 | |
| 119 | // The primary use case for extracted pages is OCR, so JPEG/WebP - |
| 120 | // both lossy by default - are forced to a high quality to avoid |
| 121 | // compression artifacts that degrade text edges. PNG and TIFF |
| 122 | // are already lossless and left alone. |
| 123 | if (in_array($format, ['jpg', 'jpeg', 'webp'])) { |
| 124 | $page->setImageCompressionQuality(90); |
| 125 | } |
| 126 | |
| 127 | $path = $location . DIRECTORY_SEPARATOR . sprintf($filenameFormat, $basename, $pageNum) . '.' . $format; |
| 128 | $page->writeImage($path); |
| 129 | $page->clear(); |
| 130 | |
| 131 | $images[$pageNum] = $path; |
| 132 | } |
| 133 | |
| 134 | return $images; |
| 135 | } |
| 136 | |
| 137 | } |