From 751b50b573a797b349198bfa9b4e5eb6d1145d04 Mon Sep 17 00:00:00 2001
From: Trenton H <797416+stumpylog@users.noreply.github.com>
Date: Fri, 30 Oct 2026 08:25:30 -0700
Subject: [PATCH] Chore: Read the OCRmyPDF sRGB profile on first use instead of
 at import

---
 src/paperless/parsers/tesseract.py | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/src/paperless/parsers/tesseract.py b/src/paperless/parsers/tesseract.py
index 5a3b77f88..e8ff0f3b5 100644
--- a/src/paperless/parsers/tesseract.py
+++ b/src/paperless/parsers/tesseract.py
@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import functools
 import importlib.resources
 import logging
 import os
@@ -39,9 +40,12 @@ if TYPE_CHECKING:
 
 logger = logging.getLogger("paperless.parsing.tesseract")
 
-_SRGB_ICC_DATA: Final[bytes] = (
-    importlib.resources.files("ocrmypdf.data").joinpath("sRGB.icc").read_bytes()
-)
+
+@functools.cache
+def _srgb_icc_data() -> bytes:
+    # Read on first use, importing ocrmypdf.data pulls in the whole ocrmypdf package
+    return importlib.resources.files("ocrmypdf.data").joinpath("sRGB.icc").read_bytes()
+
 
 _SUPPORTED_MIME_TYPES: Final[dict[str, str]] = {
     "application/pdf": ".pdf",
@@ -403,7 +407,7 @@ class RasterisedDocumentParser:
         pdfa_path = Path(self.tempdir) / "archive.pdf"
         try:
             with pikepdf.open(plain_pdf_path) as pdf:
-                cs = pdf.make_stream(_SRGB_ICC_DATA)
+                cs = pdf.make_stream(_srgb_icc_data())
                 cs["/N"] = 3
                 output_intent = pikepdf.Dictionary(
                     Type=pikepdf.Name("/OutputIntent"),