Merge pull request #126 from christiancannata/ignore-error-headers

Fix for Issue #38: When there is no object reference, continue parsing PDF file
smalot · Nov 5, 2016 · 34fb40f · 34fb40f
2 parents 3cd6697 + 161b438
commit 34fb40f
Show file tree

Hide file tree

Showing 3 changed files with 12 additions and 13 deletions.
diff --git a/src/Smalot/PdfParser/Document.php b/src/Smalot/PdfParser/Document.php
@@ -119,13 +119,15 @@ protected function buildDetails()
         // Extract document info
         if ($this->trailer->has('Info')) {
             /** @var Object $info */
-            $info     = $this->trailer->get('Info');
-            $details  = $info->getHeader()->getDetails();
+            $info = $this->trailer->get('Info');
+            if ($info !== null) {
+                $details = $info->getHeader()->getDetails();
+            }
         }
 
         // Retrieve the page count
         try {
-            $pages            = $this->getPages();
+            $pages = $this->getPages();
             $details['Pages'] = count($pages);
         } catch (\Exception $e) {
             $details['Pages'] = 0;
@@ -216,7 +218,7 @@ public function getPages()
             /** @var Pages $object */
             $object = $this->objects[$id]->get('Pages');
             if (method_exists($object, 'getPages')) {
-                $pages  = $object->getPages(true);
+                $pages = $object->getPages(true);
                 return $pages;
             }
         }

diff --git a/src/Smalot/PdfParser/Header.php b/src/Smalot/PdfParser/Header.php
@@ -164,7 +164,7 @@ protected function resolveXRef($name)
             $object = $this->document->getObjectById($obj->getId());
 
             if (is_null($object)) {
-                throw new \Exception('Missing object reference #' . $obj->getId() . '.');
+                return null;
             }
 
             // Update elements list for future calls.

diff --git a/src/Smalot/PdfParser/Tests/Units/Header.php b/src/Smalot/PdfParser/Tests/Units/Header.php
@@ -118,13 +118,9 @@ public function testGet()
         $this->assert->object($header->get('SubType'))->isInstanceOf('\Smalot\PdfParser\Element\ElementName');
         $this->assert->object($header->get('Font'))->isInstanceOf('\Smalot\PdfParser\Page');
         $this->assert->object($header->get('Image'))->isInstanceOf('\Smalot\PdfParser\Element\ElementMissing');
+        $resources = $header->get('Resources');
 
-        try {
-            $resources = $header->get('Resources');
-            $this->assert->boolean(true)->isEqualTo(false);
-        } catch (\Exception $e) {
-            $this->assert->exception($e)->hasMessage('Missing object reference #8_0.');
-        }
+        $this->assert->variable($resources)->isNull();
     }
 
     public function testResolveXRef()
@@ -138,11 +134,12 @@ public function testResolveXRef()
 
         $this->assert->object($header->get('Font'))->isInstanceOf('\Smalot\PdfParser\Object');
 
+        $header=$header->get('Resources');
         try {
-            $this->assert->object($header->get('Resources'))->isInstanceOf('\Smalot\PdfParser\Element\ElementMissing');
+            $this->assert->variable($header)->isInstanceOf('\Smalot\PdfParser\Element\ElementMissing');
             $this->assert->boolean(true)->isEqualTo(false);
         } catch (\Exception $e) {
-            $this->assert->exception($e)->hasMessage('Missing object reference #8_0.');
+            $this->assert->variable($header)->isNull();
         }
     }
 }