From d26c46e034d75ce5f04e16de3b171aa542bda5ab Mon Sep 17 00:00:00 2001
From: jonaswinkler <17569239+jonaswinkler@users.noreply.github.com>
Date: Mon, 22 Mar 2021 22:46:35 +0100
Subject: [PATCH] fixes #794

---
 src/paperless_tesseract/parsers.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/src/paperless_tesseract/parsers.py b/src/paperless_tesseract/parsers.py
index 589b25e37..944bda601 100644
--- a/src/paperless_tesseract/parsers.py
+++ b/src/paperless_tesseract/parsers.py
@@ -119,6 +119,8 @@ class RasterisedDocumentParser(DocumentParser):
         try:
             text = extract_text(pdf_file)
             stripped = strip_excess_whitespace(text)
+            stripped = stripped.replace("\0", " ")
+
             self.log("debug", f"Extracted text from PDF file {pdf_file}")
             return stripped
         except PDFException: