From 1b2cb13a216311202449c5d7808b340ab8942004 Mon Sep 17 00:00:00 2001
From: Trenton H <797416+stumpylog@users.noreply.github.com>
Date: Thu, 26 Jan 2023 08:00:02 -0800
Subject: [PATCH] Adds setting to Gotenberg API call for outputting the correct
 PDF/A format

---
 src/paperless_mail/parsers.py | 10 ++++++++++
 src/paperless_tika/parsers.py | 12 +++++++++++-
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/src/paperless_mail/parsers.py b/src/paperless_mail/parsers.py
index cc5d4e3c8..f1ee263aa 100644
--- a/src/paperless_mail/parsers.py
+++ b/src/paperless_mail/parsers.py
@@ -271,6 +271,16 @@ class MailDocumentParser(DocumentParser):
                 "paperHeight": "11.7",
                 "scale": "1.0",
             }
+
+            # Set the output format of the resulting PDF
+            # Valid inputs: https://gotenberg.dev/docs/modules/pdf-engines#uno
+            if settings.OCR_OUTPUT_TYPE in {"pdfa", "pdfa-2"}:
+                data["pdfFormat"] = "PDF/A-2b"
+            elif settings.OCR_OUTPUT_TYPE == "pdfa-1":
+                data["pdfFormat"] = "PDF/A-1a"
+            elif settings.OCR_OUTPUT_TYPE == "pdfa-3":
+                data["pdfFormat"] = "PDF/A-3b"
+
             try:
                 response = requests.post(
                     url,
diff --git a/src/paperless_tika/parsers.py b/src/paperless_tika/parsers.py
index 1cfb1eecb..f34ecbbab 100644
--- a/src/paperless_tika/parsers.py
+++ b/src/paperless_tika/parsers.py
@@ -95,9 +95,19 @@ class TikaDocumentParser(DocumentParser):
                 ),
             }
             headers = {}
+            data = {}
+
+            # Set the output format of the resulting PDF
+            # Valid inputs: https://gotenberg.dev/docs/modules/pdf-engines#uno
+            if settings.OCR_OUTPUT_TYPE in {"pdfa", "pdfa-2"}:
+                data["pdfFormat"] = "PDF/A-2b"
+            elif settings.OCR_OUTPUT_TYPE == "pdfa-1":
+                data["pdfFormat"] = "PDF/A-1a"
+            elif settings.OCR_OUTPUT_TYPE == "pdfa-3":
+                data["pdfFormat"] = "PDF/A-3b"
 
             try:
-                response = requests.post(url, files=files, headers=headers)
+                response = requests.post(url, files=files, headers=headers, data=data)
                 response.raise_for_status()  # ensure we notice bad responses
             except Exception as err:
                 raise ParseError(