From 2824410be225e43d5b22335776ca009c8c1ae2d1 Mon Sep 17 00:00:00 2001
From: Anish Sarkar <104695310+AnishSarkar22@users.noreply.github.com>
Date: Sun, 5 Apr 2026 17:26:42 +0530
Subject: [PATCH] feat: add plaintext parser to ETL pipeline for reading text
 files

---
 surfsense_backend/app/etl_pipeline/parsers/plaintext.py | 8 ++++++++
 1 file changed, 8 insertions(+)
 create mode 100644 surfsense_backend/app/etl_pipeline/parsers/plaintext.py

diff --git a/surfsense_backend/app/etl_pipeline/parsers/plaintext.py b/surfsense_backend/app/etl_pipeline/parsers/plaintext.py
new file mode 100644
index 000000000..24bfb71e5
--- /dev/null
+++ b/surfsense_backend/app/etl_pipeline/parsers/plaintext.py
@@ -0,0 +1,8 @@
+def read_plaintext(file_path: str) -> str:
+    with open(file_path, encoding="utf-8", errors="replace") as f:
+        content = f.read()
+    if "\x00" in content:
+        raise ValueError(
+            f"File contains null bytes — likely a binary file opened as text: {file_path}"
+        )
+    return content