Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
100.00% |
83 / 83 |
|
100.00% |
10 / 10 |
CRAP | |
100.00% |
1 / 1 |
| Parser | |
100.00% |
83 / 83 |
|
100.00% |
10 / 10 |
35 | |
100.00% |
1 / 1 |
| getObjectStreams | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| getObjectMap | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| getFonts | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| parseFile | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| parseData | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| parse | |
100.00% |
40 / 40 |
|
100.00% |
1 / 1 |
8 | |||
| initFile | |
100.00% |
8 / 8 |
|
100.00% |
1 / 1 |
2 | |||
| initData | |
100.00% |
5 / 5 |
|
100.00% |
1 / 1 |
1 | |||
| kidNumbers | |
100.00% |
7 / 7 |
|
100.00% |
1 / 1 |
4 | |||
| metadataFromDict | |
100.00% |
16 / 16 |
|
100.00% |
1 / 1 |
15 | |||
| 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; |
| 16 | |
| 17 | use Pop\Pdf\Document\AbstractDocument; |
| 18 | use Pop\Pdf\Document\Metadata; |
| 19 | use Pop\Pdf\Extract\Document as ExtractDocument; |
| 20 | use Pop\Pdf\Extract\Value; |
| 21 | |
| 22 | /** |
| 23 | * Pdf parser class |
| 24 | * |
| 25 | * @category Pop |
| 26 | * @package Pop\Pdf |
| 27 | * @author Nick Sagona, III <nick@popphp.org> |
| 28 | * @copyright Copyright (c) 2009-2026 Nick Sagona, III |
| 29 | * @license https://www.popphp.org/license New BSD License |
| 30 | * @version 6.0.0 |
| 31 | */ |
| 32 | class Parser extends AbstractParser |
| 33 | { |
| 34 | |
| 35 | /** |
| 36 | * Parsed object data streams - retained only for public API |
| 37 | * compatibility (getObjectStreams()); no longer populated under the |
| 38 | * Extract\Document-based implementation, since no consumer depends on |
| 39 | * its contents (only its array type). |
| 40 | * @var array |
| 41 | */ |
| 42 | protected array $objectStreams = []; |
| 43 | |
| 44 | /** |
| 45 | * Object map - retained only for public API compatibility |
| 46 | * (getObjectMap()); see $objectStreams. |
| 47 | * @var array |
| 48 | */ |
| 49 | protected array $objectMap = []; |
| 50 | |
| 51 | /** |
| 52 | * Document fonts - retained only for public API compatibility |
| 53 | * (getFonts()); font resources are now carried per-page via each |
| 54 | * translated PageObject's own structured font references instead of |
| 55 | * this document-wide bag. |
| 56 | * @var array |
| 57 | */ |
| 58 | protected array $fonts = []; |
| 59 | |
| 60 | /** |
| 61 | * Get the object streams |
| 62 | * |
| 63 | * @return array |
| 64 | */ |
| 65 | public function getObjectStreams(): array |
| 66 | { |
| 67 | return $this->objectStreams; |
| 68 | } |
| 69 | |
| 70 | /** |
| 71 | * Get the object map |
| 72 | * |
| 73 | * @return array |
| 74 | */ |
| 75 | public function getObjectMap(): array |
| 76 | { |
| 77 | return $this->objectMap; |
| 78 | } |
| 79 | |
| 80 | /** |
| 81 | * Get the document fonts |
| 82 | * |
| 83 | * @return array |
| 84 | */ |
| 85 | public function getFonts(): array |
| 86 | { |
| 87 | return $this->fonts; |
| 88 | } |
| 89 | |
| 90 | /** |
| 91 | * Parse from file |
| 92 | * |
| 93 | * @param string $file |
| 94 | * @param mixed $pages |
| 95 | * @throws Exception |
| 96 | * @return AbstractDocument |
| 97 | */ |
| 98 | public function parseFile(string $file, mixed $pages = null): AbstractDocument |
| 99 | { |
| 100 | $this->initFile($file); |
| 101 | return $this->parse($pages); |
| 102 | } |
| 103 | |
| 104 | /** |
| 105 | * Parse from raw data stream |
| 106 | * |
| 107 | * @param string $data |
| 108 | * @param mixed $pages |
| 109 | * @throws Exception |
| 110 | * @return AbstractDocument |
| 111 | */ |
| 112 | public function parseData(string $data, mixed $pages = null): AbstractDocument |
| 113 | { |
| 114 | $this->initData($data); |
| 115 | return $this->parse($pages); |
| 116 | } |
| 117 | |
| 118 | /** |
| 119 | * Parse the data stream |
| 120 | * |
| 121 | * @param mixed $pages |
| 122 | * @throws Exception |
| 123 | * @return AbstractDocument |
| 124 | */ |
| 125 | public function parse(mixed $pages = null): AbstractDocument |
| 126 | { |
| 127 | try { |
| 128 | $extractDoc = new ExtractDocument($this->data); |
| 129 | $graph = Import\ObjectGraphReader::read($extractDoc, 0); |
| 130 | } catch (\Pop\Pdf\Extract\Exception $e) { |
| 131 | throw new Exception($e->getMessage(), $e->getCode(), $e); |
| 132 | } |
| 133 | |
| 134 | $rootObjNum = $graph['nextOffset'] + 1; |
| 135 | $nextFree = $rootObjNum + 1; |
| 136 | |
| 137 | $parent = new PdfObject\ParentObject($graph['topPagesObjNum']); |
| 138 | $parent->setKids(self::kidNumbers($graph['topPagesDict'])); |
| 139 | $parent->setCount(count($graph['pageObjects'])); |
| 140 | $parent->setImported(true); |
| 141 | |
| 142 | $root = new PdfObject\RootObject($rootObjNum); |
| 143 | $root->setParentIndex($graph['topPagesObjNum']); |
| 144 | $root->setImported(true); |
| 145 | |
| 146 | $objects = $graph['objects']; |
| 147 | $objects[$graph['topPagesObjNum']] = $parent; |
| 148 | $objects[$rootObjNum] = $root; |
| 149 | |
| 150 | $doc = new \Pop\Pdf\Document(); |
| 151 | |
| 152 | if ($graph['infoDict'] !== null) { |
| 153 | $doc->setMetadata(self::metadataFromDict($graph['infoDict'])); |
| 154 | } |
| 155 | |
| 156 | $info = new PdfObject\InfoObject($nextFree); |
| 157 | $info->setImported(true); |
| 158 | $objects[$nextFree] = $info; |
| 159 | |
| 160 | $doc->importObjects($objects); |
| 161 | |
| 162 | $pageObjects = $graph['pageObjects']; |
| 163 | |
| 164 | if ($pages !== null) { |
| 165 | $pages = (!is_array($pages)) ? [$pages] : $pages; |
| 166 | $kept = []; |
| 167 | $keptKids = []; |
| 168 | |
| 169 | foreach ($pages as $pageNum) { |
| 170 | if (isset($pageObjects[$pageNum - 1])) { |
| 171 | $kept[] = $pageObjects[$pageNum - 1]; |
| 172 | $keptKids[] = $pageObjects[$pageNum - 1]->getIndex(); |
| 173 | } |
| 174 | } |
| 175 | |
| 176 | $pageObjects = $kept; |
| 177 | $parent->setKids($keptKids); |
| 178 | $parent->setCount(count($keptKids)); |
| 179 | } |
| 180 | |
| 181 | foreach ($pageObjects as $pageObject) { |
| 182 | $pg = new \Pop\Pdf\Document\Page($pageObject->getWidth(), $pageObject->getHeight(), $pageObject->getIndex()); |
| 183 | $pg->importPageObject($pageObject); |
| 184 | $doc->addPage($pg); |
| 185 | } |
| 186 | |
| 187 | return $doc; |
| 188 | } |
| 189 | |
| 190 | /** |
| 191 | * Initialize the file and get the data |
| 192 | * |
| 193 | * @param string $file |
| 194 | * @throws Exception |
| 195 | * @return Parser |
| 196 | */ |
| 197 | protected function initFile(string $file): Parser |
| 198 | { |
| 199 | if (!file_exists($file)) { |
| 200 | throw new Exception('Error: That PDF file does not exist.'); |
| 201 | } |
| 202 | |
| 203 | $this->file = $file; |
| 204 | $this->data = file_get_contents($this->file); |
| 205 | |
| 206 | $this->objectStreams = []; |
| 207 | $this->objectMap = []; |
| 208 | $this->fonts = []; |
| 209 | |
| 210 | return $this; |
| 211 | } |
| 212 | |
| 213 | /** |
| 214 | * Initialize data |
| 215 | * |
| 216 | * @param string $data |
| 217 | * @return Parser |
| 218 | */ |
| 219 | protected function initData(string $data): Parser |
| 220 | { |
| 221 | $this->data = $data; |
| 222 | |
| 223 | $this->objectStreams = []; |
| 224 | $this->objectMap = []; |
| 225 | $this->fonts = []; |
| 226 | |
| 227 | return $this; |
| 228 | } |
| 229 | |
| 230 | /** |
| 231 | * Extract a rewritten Pages node dict's Kids as a flat list of new object numbers |
| 232 | * |
| 233 | * @param array $topPagesDict |
| 234 | * @return array |
| 235 | */ |
| 236 | protected static function kidNumbers(array $topPagesDict): array |
| 237 | { |
| 238 | $numbers = []; |
| 239 | $kids = $topPagesDict['Kids'] ?? []; |
| 240 | |
| 241 | if (is_array($kids)) { |
| 242 | foreach ($kids as $kid) { |
| 243 | if ($kid instanceof Value\Reference) { |
| 244 | $numbers[] = $kid->objNum; |
| 245 | } |
| 246 | } |
| 247 | } |
| 248 | |
| 249 | return $numbers; |
| 250 | } |
| 251 | |
| 252 | /** |
| 253 | * Build a Document\Metadata from a rewritten Info dict |
| 254 | * |
| 255 | * @param array $infoDict |
| 256 | * @return Metadata |
| 257 | */ |
| 258 | protected static function metadataFromDict(array $infoDict): Metadata |
| 259 | { |
| 260 | $metadata = new Metadata(); |
| 261 | |
| 262 | if (isset($infoDict['Title']) && is_string($infoDict['Title'])) { |
| 263 | $metadata->setTitle($infoDict['Title']); |
| 264 | } |
| 265 | if (isset($infoDict['Author']) && is_string($infoDict['Author'])) { |
| 266 | $metadata->setAuthor($infoDict['Author']); |
| 267 | } |
| 268 | if (isset($infoDict['Subject']) && is_string($infoDict['Subject'])) { |
| 269 | $metadata->setSubject($infoDict['Subject']); |
| 270 | } |
| 271 | if (isset($infoDict['Creator']) && is_string($infoDict['Creator'])) { |
| 272 | $metadata->setCreator($infoDict['Creator']); |
| 273 | } |
| 274 | if (isset($infoDict['Producer']) && is_string($infoDict['Producer'])) { |
| 275 | $metadata->setProducer($infoDict['Producer']); |
| 276 | } |
| 277 | if (isset($infoDict['CreationDate']) && is_string($infoDict['CreationDate'])) { |
| 278 | $metadata->setCreationDate($infoDict['CreationDate']); |
| 279 | } |
| 280 | if (isset($infoDict['ModDate']) && is_string($infoDict['ModDate'])) { |
| 281 | $metadata->setModDate($infoDict['ModDate']); |
| 282 | } |
| 283 | |
| 284 | return $metadata; |
| 285 | } |
| 286 | |
| 287 | } |