From df64aece2c19215cf762b2ac62d476888cd21527 Mon Sep 17 00:00:00 2001
From: "google-labs-jules[bot]"
 <161369871+google-labs-jules[bot]@users.noreply.github.com>
Date: Mon, 16 Mar 2026 09:05:02 +0000
Subject: [PATCH] feat: Extract embedded PDF metadata using pypdf in
 upload_to_email

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
---
 app/tasks/upload_to_email.py | 19 +++++++++++++++++--
 tests/test_upload_email.py   | 26 ++++++++++++++++++++++++++
 2 files changed, 43 insertions(+), 2 deletions(-)

diff --git a/app/tasks/upload_to_email.py b/app/tasks/upload_to_email.py
index 8b9c8220..c68e4bf7 100644
--- a/app/tasks/upload_to_email.py
+++ b/app/tasks/upload_to_email.py
@@ -11,6 +11,7 @@ from email.mime.image import MIMEImage
 from email.mime.multipart import MIMEMultipart
 from email.mime.text import MIMEText
 
+import pypdf
 from jinja2 import Environment, FileSystemLoader, select_autoescape
 
 from app.celery_app import celery
@@ -80,8 +81,22 @@ def extract_metadata_from_file(file_path):
         except Exception as e:
             logger.warning(f"Failed to load metadata from JSON file: {str(e)}")
 
-    # TODO: For PDF files, try to extract embedded metadata using PyPDF2
-    # This would require additional dependencies, so for now we'll just check for external JSON
+    # Try to extract embedded metadata from PDF
+    if file_path.lower().endswith(".pdf") and os.path.exists(file_path):
+        try:
+            with open(file_path, "rb") as f:
+                pdf_reader = pypdf.PdfReader(f)
+                pdf_metadata = pdf_reader.metadata
+                if pdf_metadata:
+                    # Convert metadata to a standard dictionary
+                    for key, value in pdf_metadata.items():
+                        # Remove the leading slash from PDF metadata keys (e.g., '/Title' -> 'Title')
+                        clean_key = key[1:] if key.startswith("/") else key
+                        metadata[clean_key] = str(value)
+
+                    logger.info(f"Extracted embedded metadata from PDF: {file_path}")
+        except Exception as e:
+            logger.warning(f"Failed to extract metadata from PDF {file_path}: {str(e)}")
 
     return metadata
 
diff --git a/tests/test_upload_email.py b/tests/test_upload_email.py
index c92893a6..72be0587 100644
--- a/tests/test_upload_email.py
+++ b/tests/test_upload_email.py
@@ -121,6 +121,32 @@ class TestExtractMetadataFromFile:
 
         assert result == {}
 
+    def test_extract_metadata_from_pdf(self, tmp_path):
+        """Test extracting metadata from a PDF file using pypdf when JSON is missing."""
+        import pypdf
+
+        file_path = tmp_path / "test.pdf"
+
+        # Create a test PDF with metadata
+        writer = pypdf.PdfWriter()
+        writer.add_blank_page(width=100, height=100)
+        writer.add_metadata({
+            "/Title": "Test Title",
+            "/Author": "Test Author",
+            "/Subject": "Test Document",
+            "/Keywords": "test, metadata, pypdf"
+        })
+        with open(file_path, "wb") as f:
+            writer.write(f)
+
+        result = extract_metadata_from_file(str(file_path))
+
+        # Check that the leading slash is stripped and keys/values match
+        assert result.get("Title") == "Test Title"
+        assert result.get("Author") == "Test Author"
+        assert result.get("Subject") == "Test Document"
+        assert result.get("Keywords") == "test, metadata, pypdf"
+
 
 @pytest.mark.unit
 class TestAttachLogo: