From 38d60ea89b0711d68c9ffaeee0cd486a5e98ae30 Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <james@purplerock.ca>
Date: Wed, 29 Oct 2025 11:39:03 -0700
Subject: [PATCH] optimize: don't put flate on large jpegs unless compression
 is high

Putting flate on very large JPEGs can cause performance problems in PDF viewers, subjectively anyway.
---
 src/ocrmypdf/optimize.py | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/src/ocrmypdf/optimize.py b/src/ocrmypdf/optimize.py
index 8d9322f6..a7c6cded 100644
--- a/src/ocrmypdf/optimize.py
+++ b/src/ocrmypdf/optimize.py
@@ -42,6 +42,7 @@ log = logging.getLogger(__name__)
 
 DEFAULT_JPEG_QUALITY = 75
 DEFAULT_PNG_QUALITY = 70
+FLATE_JPEG_THRESHOLD = 10000
 
 
 Xref = NewType('Xref', int)
@@ -528,7 +529,19 @@ def _find_deflatable_jpeg(
         return None
     _pim, filtdp = result
 
-    if filtdp[0] == Name.DCTDecode and not filtdp[1] and options.optimize >= 1:
+    if (
+        filtdp[0] == Name.DCTDecode
+        and not filtdp[1]
+        and (
+            (
+                # Don't flate very large images because it will slow down PDF viewers
+                1 <= options.optimize <= 2
+                and image.get(Name.Width, 0) < FLATE_JPEG_THRESHOLD
+                and image.get(Name.Height, 0) < FLATE_JPEG_THRESHOLD
+            )
+            or options.optimize == 3
+        )
+    ):
         return XrefExt(xref, '.memory')
 
     return None