From 5fdcb7602b44b35a9d6d1a0f5d0aab4c653ee59c Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <james@purplerock.ca>
Date: Sun, 7 Apr 2024 13:43:12 -0700
Subject: [PATCH] Make downsampling large images that Tesseract would otherwise
 error on into default behavior

Fixes #1281
---
 src/ocrmypdf/builtin_plugins/tesseract_ocr.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/src/ocrmypdf/builtin_plugins/tesseract_ocr.py b/src/ocrmypdf/builtin_plugins/tesseract_ocr.py
index ee51e902..3d6fc212 100644
--- a/src/ocrmypdf/builtin_plugins/tesseract_ocr.py
+++ b/src/ocrmypdf/builtin_plugins/tesseract_ocr.py
@@ -4,6 +4,7 @@
 
 from __future__ import annotations
 
+import argparse
 import logging
 import os
 
@@ -93,7 +94,8 @@ def add_options(parser):
     )
     tess.add_argument(
         '--tesseract-downsample-large-images',
-        action='store_true',
+        action=argparse.BooleanOptionalAction,
+        default=True,
         help=(
             "Downsample large images before OCR. Tesseract has an upper limit on the "
             "size images it will support. If this argument is given, OCRmyPDF will "