chore: update documentation

Follow up of issue smalot#427 using the suggested code at issue smalot#472. Notes: Have PDF files that the pdfparser can't get the MediaBox, as fallback to get the page dimension is possible to use the BBox (Bounding Box). The Bounding Box could not have the real dimension of a page put is a solution to have a value that could be the page dimension at cases that isn't possible to found the MediaBox. Signed-off-by: Vitor Mattos <[email protected]>
vitormattos · Jan 24, 2025 · 2edc3ac · 2edc3ac
1 parent f44ada0
commit 2edc3ac
Show file tree

Hide file tree

Showing 3 changed files with 52 additions and 4 deletions.
diff --git a/doc/Usage.md b/doc/Usage.md
@@ -228,11 +228,22 @@ foreach ($pages as $page) {
     if (!isset($details['MediaBox'])) {
         $pages = $pdf->getObjectsByType('Pages');
         $details = reset($pages)->getHeader()->getDetails();
+        if (!isset($details['MediaBox'])) {
+            $objects = $page->getXObjects();
+            if (isset($objects[0])) {
+                $details = $objects[0]->getHeader()->getDetails();
+                if (isset($details['BBox'])) {
+                    $details['MediaBox'] = $details['BBox'];
+                }
+            }
+        }
+    }
+    if (isset($details['MediaBox'])) {
+        $mediaBox[] = [
+            'width' => $details['MediaBox'][2],
+            'height' => $details['MediaBox'][3]
+        ];
     }
-    $mediaBox[] = [
-        'width' => $details['MediaBox'][2],
-        'height' => $details['MediaBox'][3]
-    ];
 }
 ```
 

diff --git a/samples/bugs/Issue427.pdf b/samples/bugs/Issue427.pdf
diff --git a/tests/PHPUnit/Integration/PageTest.php b/tests/PHPUnit/Integration/PageTest.php
@@ -41,6 +41,7 @@
 use Smalot\PdfParser\Element\ElementMissing;
 use Smalot\PdfParser\Font;
 use Smalot\PdfParser\Page;
+use TypeError;
 
 class PageTest extends TestCase
 {
@@ -905,6 +906,42 @@ public function testIssue629WithDataTmFontInfo(): void
         $this->assertEquals('F2', $dataTm[0][2]);
     }
 
+    public function testIssue427GetPageDimensions(): void
+    {
+        $filename = $this->rootDir.'/samples/bugs/Issue427.pdf';
+        $parser = $this->getParserInstance();
+        $document = $parser->parseFile($filename);
+        $pages = $document->getPages();
+        $notFound = 0;
+        foreach ($pages as $page) {
+            $details = $page->getDetails();
+            if (!isset($details['MediaBox'])) {
+                $fallbackPages = $document->getObjectsByType('Pages');
+                $details = reset($fallbackPages)->getHeader()->getDetails();
+                if (!isset($details['MediaBox'])) {
+                    try {
+                        $objects = $page->getXObjects();
+                        if (isset($objects[0])) {
+                            $details = $objects[0]->getHeader()->getDetails();
+                            if (isset($details['BBox'])) {
+                                $this->assertArrayHasKey('BBox', $details);
+                                $this->assertArrayHasKey(2, $details['BBox']);
+                                $this->assertArrayHasKey(3, $details['BBox']);
+                                continue;
+                            }
+                        }
+                        $notFound++;
+                        continue;
+                    } catch (TypeError $e) {
+                        $notFound++;
+                        continue;
+                    }
+                }
+            }
+        }
+        $this->assertEquals(count($pages) - 1, $notFound);
+    }
+
     /**
      * Data TM font info is NOT included.
      *