Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
100.00% |
94 / 94 |
|
100.00% |
23 / 23 |
CRAP | |
100.00% |
1 / 1 |
| |
100.00% |
94 / 94 |
|
100.00% |
23 / 23 |
46 | |
100.00% |
1 / 1 |
|
| writeToFile | |
100.00% |
3 / 3 |
|
100.00% |
1 / 1 |
1 | |||
| outputToHttp | |
100.00% |
9 / 9 |
|
100.00% |
1 / 1 |
4 | |||
| importFromHtml | |
100.00% |
3 / 3 |
|
100.00% |
1 / 1 |
1 | |||
| importFromHtmlFile | |
100.00% |
3 / 3 |
|
100.00% |
1 / 1 |
1 | |||
| importFromHtmlUri | |
100.00% |
3 / 3 |
|
100.00% |
1 / 1 |
1 | |||
| importFromFile | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| importRawData | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| merge | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| mergeRawData | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| importFromImages | |
100.00% |
6 / 6 |
|
100.00% |
1 / 1 |
3 | |||
| extractAsImages | |
100.00% |
6 / 6 |
|
100.00% |
1 / 1 |
2 | |||
| extractTextFromFile | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| extractTextFromData | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| extractTextFromDocument | |
100.00% |
10 / 10 |
|
100.00% |
1 / 1 |
3 | |||
| extractTextFromPage | |
100.00% |
15 / 15 |
|
100.00% |
1 / 1 |
7 | |||
| isImageOnlyDocument | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| isImageOnlyData | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| getImageOnlyPages | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| getImageOnlyPagesFromData | |
100.00% |
2 / 2 |
|
100.00% |
1 / 1 |
1 | |||
| classifyPages | |
100.00% |
7 / 7 |
|
100.00% |
1 / 1 |
2 | |||
| normalizePages | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
3 | |||
| selectByPageFilter | |
100.00% |
9 / 9 |
|
100.00% |
1 / 1 |
6 | |||
| allPagesImageOnly | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
2 | |||
| 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; |
| 16 | |
| 17 | use Pop\Pdf\Document\AbstractDocument; |
| 18 | use Pop\Pdf\Document\Exception; |
| 19 | |
| 20 | /** |
| 21 | * Pop Pdf class |
| 22 | * |
| 23 | * @category Pop |
| 24 | * @package Pop\Pdf |
| 25 | * @author Nick Sagona, III <nick@popphp.org> |
| 26 | * @copyright Copyright (c) 2009-2026 Nick Sagona, III |
| 27 | * @license https://www.popphp.org/license New BSD License |
| 28 | * @version 6.2.0 |
| 29 | */ |
| 30 | class Pdf |
| 31 | { |
| 32 | |
| 33 | /** |
| 34 | * Write document to file |
| 35 | * |
| 36 | * @param Document $document |
| 37 | * @param string $filename |
| 38 | * @return void |
| 39 | */ |
| 40 | public static function writeToFile(Document $document, string $filename = 'pop.pdf'): void |
| 41 | { |
| 42 | $compiler = new Build\Compiler(); |
| 43 | $compiler->finalize($document); |
| 44 | file_put_contents($filename, $compiler->getOutput()); |
| 45 | } |
| 46 | |
| 47 | /** |
| 48 | * Output to HTTP response |
| 49 | * |
| 50 | * @param Document $document |
| 51 | * @param string $filename |
| 52 | * @param bool $forceDownload |
| 53 | * @param array $headers |
| 54 | * @return void |
| 55 | */ |
| 56 | public static function outputToHttp( |
| 57 | Document $document, string $filename = 'pop.pdf', bool $forceDownload = false, array $headers = [] |
| 58 | ): void |
| 59 | { |
| 60 | $headers['Content-type'] = 'application/pdf'; |
| 61 | $headers['Content-disposition'] = (($forceDownload) ? 'attachment; ' : null) . 'filename=' . $filename; |
| 62 | |
| 63 | $compiler = new Build\Compiler(); |
| 64 | $compiler->finalize($document); |
| 65 | |
| 66 | // Send the headers and output the PDF |
| 67 | if (!headers_sent()) { |
| 68 | header('HTTP/1.1 200 OK'); |
| 69 | foreach ($headers as $name => $value) { |
| 70 | header($name . ': ' . $value); |
| 71 | } |
| 72 | } |
| 73 | |
| 74 | echo $compiler->getOutput(); |
| 75 | } |
| 76 | |
| 77 | /** |
| 78 | * Import from an HTML string |
| 79 | * |
| 80 | * @param string $html |
| 81 | * @param Document $document |
| 82 | * @param string|array|null $pageSize |
| 83 | * @return AbstractDocument |
| 84 | */ |
| 85 | public static function importFromHtml( |
| 86 | string $html, Document $document = new Document(), string|array|null $pageSize = null |
| 87 | ): AbstractDocument |
| 88 | { |
| 89 | $parser = new Build\Html\Parser($document, $pageSize); |
| 90 | $parser->parseHtml($html)->process(); |
| 91 | |
| 92 | return $parser->document(); |
| 93 | } |
| 94 | |
| 95 | /** |
| 96 | * Import from an HTML file |
| 97 | * |
| 98 | * @param string $htmlFile |
| 99 | * @param Document $document |
| 100 | * @param string|array|null $pageSize |
| 101 | * @return AbstractDocument |
| 102 | */ |
| 103 | public static function importFromHtmlFile( |
| 104 | string $htmlFile, Document $document = new Document(), string|array|null $pageSize = null |
| 105 | ): AbstractDocument |
| 106 | { |
| 107 | $parser = new Build\Html\Parser($document, $pageSize); |
| 108 | $parser->parseHtmlFile($htmlFile)->process(); |
| 109 | |
| 110 | return $parser->document(); |
| 111 | } |
| 112 | |
| 113 | /** |
| 114 | * Import from an HTML URI |
| 115 | * |
| 116 | * @param string $htmlUri |
| 117 | * @param Document $document |
| 118 | * @param string|array|null $pageSize |
| 119 | * @return AbstractDocument |
| 120 | */ |
| 121 | public static function importFromHtmlUri( |
| 122 | string $htmlUri, Document $document = new Document(), string|array|null $pageSize = null |
| 123 | ): AbstractDocument |
| 124 | { |
| 125 | $parser = new Build\Html\Parser($document, $pageSize); |
| 126 | $parser->parseHtmlUri($htmlUri)->process(); |
| 127 | |
| 128 | return $parser->document(); |
| 129 | } |
| 130 | |
| 131 | /** |
| 132 | * Import from an existing PDF file |
| 133 | * |
| 134 | * @param string $file |
| 135 | * @param mixed $pages |
| 136 | * @param ?string $password |
| 137 | * @return AbstractDocument |
| 138 | */ |
| 139 | public static function importFromFile(string $file, mixed $pages = null, ?string $password = null): AbstractDocument |
| 140 | { |
| 141 | $parser = new Build\Parser(); |
| 142 | return $parser->parseFile($file, $pages, $password); |
| 143 | } |
| 144 | |
| 145 | /** |
| 146 | * Import from raw data stream |
| 147 | * |
| 148 | * @param string $data |
| 149 | * @param mixed $pages |
| 150 | * @param ?string $password |
| 151 | * @return AbstractDocument |
| 152 | */ |
| 153 | public static function importRawData(string $data, mixed $pages = null, ?string $password = null): AbstractDocument |
| 154 | { |
| 155 | $parser = new Build\Parser(); |
| 156 | return $parser->parseData($data, $pages, $password); |
| 157 | } |
| 158 | |
| 159 | /** |
| 160 | * Merge PDF files into one document |
| 161 | * |
| 162 | * @param array $files |
| 163 | * @param Document $document |
| 164 | * @param array $passwords per-source decryption passwords, keyed the same way as $files |
| 165 | * (e.g. [1 => 'secret'] to supply a password only for $files[1]); |
| 166 | * a source with no entry (or a null entry) is opened with no password. |
| 167 | * @return AbstractDocument |
| 168 | */ |
| 169 | public static function merge(array $files, Document $document = new Document(), array $passwords = []): AbstractDocument |
| 170 | { |
| 171 | $merger = new Build\Merger(); |
| 172 | return $merger->mergeFiles($files, $document, $passwords); |
| 173 | } |
| 174 | |
| 175 | /** |
| 176 | * Merge raw PDF data streams into one document |
| 177 | * |
| 178 | * @param array $data |
| 179 | * @param Document $document |
| 180 | * @param array $passwords per-source decryption passwords, keyed the same way as $data |
| 181 | * (e.g. [1 => 'secret'] to supply a password only for $data[1]); |
| 182 | * a source with no entry (or a null entry) is opened with no password. |
| 183 | * @return AbstractDocument |
| 184 | */ |
| 185 | public static function mergeRawData(array $data, Document $document = new Document(), array $passwords = []): AbstractDocument |
| 186 | { |
| 187 | $merger = new Build\Merger(); |
| 188 | return $merger->mergeData($data, $document, $passwords); |
| 189 | } |
| 190 | |
| 191 | /** |
| 192 | * Import from an existing PDF file |
| 193 | * |
| 194 | * @param string|array $images |
| 195 | * @param int $quality |
| 196 | * @throws Exception |
| 197 | * @return AbstractDocument |
| 198 | */ |
| 199 | public static function importFromImages(string|array $images, int $quality = 70): AbstractDocument |
| 200 | { |
| 201 | if (!is_array($images)) { |
| 202 | $images = [$images]; |
| 203 | } |
| 204 | |
| 205 | $document = new Document(); |
| 206 | |
| 207 | foreach ($images as $image) { |
| 208 | $document->addPage(Document\Page::createFromImage($image, $quality)); |
| 209 | } |
| 210 | |
| 211 | return $document; |
| 212 | } |
| 213 | |
| 214 | /** |
| 215 | * Extract as images |
| 216 | * |
| 217 | * @param string $file |
| 218 | * @param string $location |
| 219 | * @param string $format |
| 220 | * @param int $resolution |
| 221 | * @param string $filenameFormat sprintf() format string, given the file's basename and the 1-indexed |
| 222 | * page number (e.g. '%1$s-%2$02d' => 'document-01', 'page-%2$02d' => 'page-01') |
| 223 | * @param mixed $pages |
| 224 | * @param ?int $pageLimit |
| 225 | * @return array |
| 226 | *@throws Build\Exception |
| 227 | */ |
| 228 | public static function extractAsImages( |
| 229 | string $file, string $location, string $format = 'jpg', int $resolution = 300, |
| 230 | string $filenameFormat = '%1$s-%2$02d', mixed $pages = null, ?int $pageLimit = null |
| 231 | ): array |
| 232 | { |
| 233 | $extractor = new Build\Image\Extractor(); |
| 234 | $totalPages = $extractor->countPages($file); |
| 235 | $allPages = ($totalPages > 0) ? range(1, $totalPages) : []; |
| 236 | |
| 237 | $pages = self::normalizePages($pages); |
| 238 | $pageNumbers = self::selectByPageFilter($allPages, $pages, $pageLimit); |
| 239 | |
| 240 | return $extractor->extract($file, $location, $format, $resolution, $filenameFormat, $pageNumbers); |
| 241 | } |
| 242 | |
| 243 | /** |
| 244 | * Extract text from file |
| 245 | * |
| 246 | * @param string $file |
| 247 | * @param mixed $pages |
| 248 | * @param ?int $pageLimit |
| 249 | * @param ?string $password |
| 250 | * @return string |
| 251 | */ |
| 252 | public static function extractTextFromFile( |
| 253 | string $file, mixed $pages = null, ?int $pageLimit = null, ?string $password = null |
| 254 | ): string |
| 255 | { |
| 256 | $doc = Extract\Document::fromFile($file, $password); |
| 257 | return self::extractTextFromDocument($doc, $pages, $pageLimit); |
| 258 | } |
| 259 | |
| 260 | /** |
| 261 | * Extract text from raw data stream |
| 262 | * |
| 263 | * @param string $data |
| 264 | * @param mixed $pages |
| 265 | * @param ?int $pageLimit |
| 266 | * @param ?string $password |
| 267 | * @return string |
| 268 | */ |
| 269 | public static function extractTextFromData( |
| 270 | string $data, mixed $pages = null, ?int $pageLimit = null, ?string $password = null |
| 271 | ): string |
| 272 | { |
| 273 | $doc = new Extract\Document($data, $password); |
| 274 | return self::extractTextFromDocument($doc, $pages, $pageLimit); |
| 275 | } |
| 276 | |
| 277 | /** |
| 278 | * Extract text from a parsed Extract\Document, joining pages/runs |
| 279 | * |
| 280 | * @param Extract\Document $doc |
| 281 | * @param mixed $pages |
| 282 | * @param ?int $pageLimit |
| 283 | * @return string |
| 284 | */ |
| 285 | protected static function extractTextFromDocument(Extract\Document $doc, mixed $pages, ?int $pageLimit): string |
| 286 | { |
| 287 | $pages = self::normalizePages($pages); |
| 288 | $docPages = Extract\Content\PageWalker::walk($doc, $pages, $pageLimit); |
| 289 | $docPages = self::selectByPageFilter($docPages, $pages, $pageLimit); |
| 290 | |
| 291 | $texts = []; |
| 292 | |
| 293 | foreach ($docPages as $docPage) { |
| 294 | $pageText = self::extractTextFromPage($doc, $docPage); |
| 295 | $pageText = trim($pageText); |
| 296 | |
| 297 | if ($pageText !== '') { |
| 298 | $texts[] = $pageText; |
| 299 | } |
| 300 | } |
| 301 | |
| 302 | return implode("\n\n", $texts); |
| 303 | } |
| 304 | |
| 305 | /** |
| 306 | * Extract text from a single page, joining runs by their separator |
| 307 | * |
| 308 | * @param Extract\Document $doc |
| 309 | * @param Extract\Content\PageInfo $page |
| 310 | * @return string |
| 311 | */ |
| 312 | protected static function extractTextFromPage(Extract\Document $doc, Extract\Content\PageInfo $page): string |
| 313 | { |
| 314 | $interpreter = new Extract\Content\Interpreter(); |
| 315 | $runs = $interpreter->run($doc, $page->content, $page->resources); |
| 316 | |
| 317 | $text = ''; |
| 318 | |
| 319 | foreach ($runs as $run) { |
| 320 | $text .= match ($run->separator) { |
| 321 | Extract\Content\TextRun::SEPARATOR_SPACE => ' ', |
| 322 | Extract\Content\TextRun::SEPARATOR_TAB => "\t", |
| 323 | Extract\Content\TextRun::SEPARATOR_NEWLINE => "\n", |
| 324 | default => '', |
| 325 | }; |
| 326 | |
| 327 | $decoded = Extract\Font\Resolver::decodeRun($run, $doc); |
| 328 | |
| 329 | if ($run->reversed) { |
| 330 | // /ReversedChars marked content (Interpreter::isReversedActive()) |
| 331 | // stores its character stream in reversed logical order - the |
| 332 | // decoder faithfully decodes byte-for-byte, so the CONSUMER |
| 333 | // (here) is responsible for restoring logical reading order. |
| 334 | // mb_str_split(), not strrev(), since the decoded text is |
| 335 | // UTF-8 and a byte-level reverse would corrupt multi-byte |
| 336 | // sequences. |
| 337 | $decoded = implode('', array_reverse(mb_str_split($decoded))); |
| 338 | } |
| 339 | |
| 340 | $text .= $decoded; |
| 341 | } |
| 342 | |
| 343 | return $text; |
| 344 | } |
| 345 | |
| 346 | /** |
| 347 | * Determine if every page of a PDF file is nothing but a single scanned/drawn image |
| 348 | * |
| 349 | * @param string $file |
| 350 | * @param mixed $pages |
| 351 | * @param ?int $pageLimit |
| 352 | * @param ?string $password |
| 353 | * @return bool |
| 354 | */ |
| 355 | public static function isImageOnlyDocument( |
| 356 | string $file, mixed $pages = null, ?int $pageLimit = null, ?string $password = null |
| 357 | ): bool |
| 358 | { |
| 359 | return self::allPagesImageOnly(self::getImageOnlyPages($file, $pages, $pageLimit, $password)); |
| 360 | } |
| 361 | |
| 362 | /** |
| 363 | * Determine if every page of raw PDF data is nothing but a single scanned/drawn image |
| 364 | * |
| 365 | * @param string $data |
| 366 | * @param mixed $pages |
| 367 | * @param ?int $pageLimit |
| 368 | * @param ?string $password |
| 369 | * @return bool |
| 370 | */ |
| 371 | public static function isImageOnlyData( |
| 372 | string $data, mixed $pages = null, ?int $pageLimit = null, ?string $password = null |
| 373 | ): bool |
| 374 | { |
| 375 | return self::allPagesImageOnly(self::getImageOnlyPagesFromData($data, $pages, $pageLimit, $password)); |
| 376 | } |
| 377 | |
| 378 | /** |
| 379 | * Get a per-page image-only classification for a PDF file |
| 380 | * |
| 381 | * @param string $file |
| 382 | * @param mixed $pages |
| 383 | * @param ?int $pageLimit |
| 384 | * @param ?string $password |
| 385 | * @return array |
| 386 | */ |
| 387 | public static function getImageOnlyPages( |
| 388 | string $file, mixed $pages = null, ?int $pageLimit = null, ?string $password = null |
| 389 | ): array |
| 390 | { |
| 391 | $doc = Extract\Document::fromFile($file, $password); |
| 392 | return self::classifyPages($doc, $pages, $pageLimit); |
| 393 | } |
| 394 | |
| 395 | /** |
| 396 | * Get a per-page image-only classification for raw PDF data |
| 397 | * |
| 398 | * @param string $data |
| 399 | * @param mixed $pages |
| 400 | * @param ?int $pageLimit |
| 401 | * @param ?string $password |
| 402 | * @return array |
| 403 | */ |
| 404 | public static function getImageOnlyPagesFromData( |
| 405 | string $data, mixed $pages = null, ?int $pageLimit = null, ?string $password = null |
| 406 | ): array |
| 407 | { |
| 408 | $doc = new Extract\Document($data, $password); |
| 409 | return self::classifyPages($doc, $pages, $pageLimit); |
| 410 | } |
| 411 | |
| 412 | /** |
| 413 | * Classify every page of a parsed Extract\Document as image-only or not |
| 414 | * |
| 415 | * @param Extract\Document $doc |
| 416 | * @param mixed $pages |
| 417 | * @param ?int $pageLimit |
| 418 | * @return array |
| 419 | */ |
| 420 | protected static function classifyPages(Extract\Document $doc, mixed $pages = null, ?int $pageLimit = null): array |
| 421 | { |
| 422 | $pages = self::normalizePages($pages); |
| 423 | $docPages = Extract\Content\PageWalker::walk($doc, $pages, $pageLimit); |
| 424 | $docPages = self::selectByPageFilter($docPages, $pages, $pageLimit); |
| 425 | |
| 426 | $result = []; |
| 427 | |
| 428 | foreach ($docPages as $i => $docPage) { |
| 429 | $result[$i] = Extract\Content\PageClassifier::isImageOnly($doc, $docPage); |
| 430 | } |
| 431 | |
| 432 | return $result; |
| 433 | } |
| 434 | |
| 435 | /** |
| 436 | * Normalize a $pages argument (int, array, or null) into an array or null |
| 437 | * |
| 438 | * @param mixed $pages |
| 439 | * @return ?array |
| 440 | */ |
| 441 | protected static function normalizePages(mixed $pages): ?array |
| 442 | { |
| 443 | return ($pages !== null) ? ((!is_array($pages)) ? [$pages] : $pages) : null; |
| 444 | } |
| 445 | |
| 446 | /** |
| 447 | * Select items by 1-indexed position, either an explicit page list or a page limit |
| 448 | * |
| 449 | * An explicit $pages list wins outright; $pageLimit only applies when |
| 450 | * $pages is null. Shared by every extract-style method that filters a |
| 451 | * per-page result set the same way (text extraction, image-only |
| 452 | * classification, image extraction). |
| 453 | * |
| 454 | * @param array $items |
| 455 | * @param ?array $pages |
| 456 | * @param ?int $pageLimit |
| 457 | * @return array |
| 458 | */ |
| 459 | protected static function selectByPageFilter(array $items, ?array $pages, ?int $pageLimit): array |
| 460 | { |
| 461 | if ($pages !== null) { |
| 462 | $selected = []; |
| 463 | foreach ($items as $i => $item) { |
| 464 | if (in_array(($i + 1), $pages)) { |
| 465 | $selected[] = $item; |
| 466 | } |
| 467 | } |
| 468 | return $selected; |
| 469 | } elseif (is_int($pageLimit) && ($pageLimit > 0)) { |
| 470 | return array_slice($items, 0, $pageLimit); |
| 471 | } |
| 472 | |
| 473 | return $items; |
| 474 | } |
| 475 | |
| 476 | /** |
| 477 | * Determine if a set of per-page image-only results means the whole document is image-only |
| 478 | * |
| 479 | * @param array $pages |
| 480 | * @return bool |
| 481 | */ |
| 482 | protected static function allPagesImageOnly(array $pages): bool |
| 483 | { |
| 484 | return (!empty($pages)) && !in_array(false, $pages, true); |
| 485 | } |
| 486 | |
| 487 | } |