From 71d7a8ab0c4e837c8cdb2221e45ce2dd960eddd2 Mon Sep 17 00:00:00 2001
From: Ben Greiner <code@bnavigator.de>
Date: Fri, 14 Feb 2025 18:34:56 +0100
Subject: [PATCH] respect settings.skip_archive_file before OCR fails

---
 src/paperless_tesseract/parsers.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/src/paperless_tesseract/parsers.py b/src/paperless_tesseract/parsers.py
index a8be899f5..ecdafde98 100644
--- a/src/paperless_tesseract/parsers.py
+++ b/src/paperless_tesseract/parsers.py
@@ -378,13 +378,13 @@ class RasterisedDocumentParser(DocumentParser):
             sidecar_file,
         )
 
+        if self.settings.skip_archive_file != ArchiveFileChoices.ALWAYS:
+            self.archive_path = archive_path        
+        
         try:
             self.log.debug(f"Calling OCRmyPDF with args: {args}")
             ocrmypdf.ocr(**args)
 
-            if self.settings.skip_archive_file != ArchiveFileChoices.ALWAYS:
-                self.archive_path = archive_path
-
             self.text = self.extract_text(sidecar_file, archive_path)
 
             if not self.text: