From db6af2783a0187320e957427a789d1b1edfa9713 Mon Sep 17 00:00:00 2001
From: Brian Huisman <bhuisman@greywyvern.com>
Date: Wed, 26 Jun 2024 04:03:19 -0400
Subject: [PATCH] Merge XMP Metadata if dc:format tag not found (#722)

* If no `dc:format` XMP tag, merge metadata

Previously `extractXMPMetadata()` would check for the existence of a `dc:format` tag with an `application/pdf` MIME-type value before allowing found XMP metadata to be merged with the other document details.

If the tag doesn't exist, merge the metadata anyway. If it _does_ exist, _then_ check to see if it has the `application/pdf` MIME-type.

* DocumentTest.php: small code niceup

---------

Co-authored-by: Konrad Abicht <hi@inspirito.de>
---
 src/Smalot/PdfParser/Document.php          |  2 +-
 tests/PHPUnit/Integration/DocumentTest.php | 32 ++++++++++++++++++++++
 2 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/src/Smalot/PdfParser/Document.php b/src/Smalot/PdfParser/Document.php
index 016787af..df0a6402 100644
--- a/src/Smalot/PdfParser/Document.php
+++ b/src/Smalot/PdfParser/Document.php
@@ -287,7 +287,7 @@ public function extractXMPMetadata(string $content): void
             }
 
             // Only use this metadata if it's referring to a PDF
-            if (isset($metadata['dc:format']) && 'application/pdf' == $metadata['dc:format']) {
+            if (!isset($metadata['dc:format']) || 'application/pdf' == $metadata['dc:format']) {
                 // According to the XMP specifications: 'Conflict resolution
                 // for separate packets that describe the same resource is
                 // beyond the scope of this document.' - Section 6.1
diff --git a/tests/PHPUnit/Integration/DocumentTest.php b/tests/PHPUnit/Integration/DocumentTest.php
index 5f19b696..346ba633 100644
--- a/tests/PHPUnit/Integration/DocumentTest.php
+++ b/tests/PHPUnit/Integration/DocumentTest.php
@@ -232,4 +232,36 @@ public function testGetPagesMissingCatalog(): void
         $document = $this->getDocumentInstance();
         $document->getPages();
     }
+
+    /**
+     * @see https://github.com/smalot/pdfparser/issues/721
+     */
+    public function testExtractXMPMetadataIssue721(): void
+    {
+        $document = $this->getDocumentInstance();
+
+        // Check that XMP metadata is parsed even if missing a dc:format tag
+        $content = '<?xpacket begin="" id="W5M0MpCehiHzreSzNTczkc9d"?>
+<x:xmpmeta xmlns:x="adobe:ns:meta/" x:xmptk="Adobe XMP Core 5.6-c015 84.159810, 2016/09/10-02:41:30">
+   <rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
+      <rdf:Description>
+         <dc:creator>
+            <rdf:Seq>
+               <rdf:li>PdfParser</rdf:li>
+            </rdf:Seq>
+         </dc:creator>
+         <xmp:CreateDate>2018-02-07T11:51:44-05:00</xmp:CreateDate>
+         <xmp:ModifyDate>2019-10-23T09:56:01-04:00</xmp:ModifyDate>
+      </rdf:Description>
+   </rdf:RDF>
+</x:xmpmeta>';
+
+        $document->extractXMPMetadata($content);
+        $document->init();
+        $details = $document->getDetails();
+
+        $this->assertEquals(4, \count($details));
+        $this->assertEquals('PdfParser', $details['dc:creator']);
+        $this->assertEquals('2019-10-23T09:56:01-04:00', $details['xmp:modifydate']);
+    }
 }