From 7bfe3ecd5bdeb9a2b47e9481f5861cf82628f83f Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <james@purplerock.ca>
Date: Tue, 13 Jan 2026 01:41:59 -0800
Subject: [PATCH] Fix double-compression of already-deflated JPEGs

Images with [FlateDecode, DCTDecode] filter chain were incorrectly
being marked for additional FlateDecode compression, resulting in
double-compressed data and invalid output PDFs.

Add _already_flate_encoded() helper to check if an image already has
FlateDecode in its filter chain, and skip such images in
_find_deflatable_jpeg().
---
 src/ocrmypdf/optimize.py | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/src/ocrmypdf/optimize.py b/src/ocrmypdf/optimize.py
index e5a543e4..63c74427 100644
--- a/src/ocrmypdf/optimize.py
+++ b/src/ocrmypdf/optimize.py
@@ -18,6 +18,7 @@ from zlib import compress
 import img2pdf
 from packaging.version import Version
 from pikepdf import (
+    Array,
     Dictionary,
     Name,
     Object,
@@ -480,6 +481,16 @@ def transcode_jpegs(
     )
 
 
+def _already_flate_encoded(image: Stream) -> bool:
+    """Check if the image already has FlateDecode in its filter chain."""
+    filt = image.get(Name.Filter)
+    if filt is None:
+        return False
+    if isinstance(filt, Array):
+        return Name.FlateDecode in list(filt)
+    return filt == Name.FlateDecode
+
+
 def _find_deflatable_jpeg(
     *, pdf: Pdf, root: Path, image: Stream, xref: Xref, options
 ) -> XrefExt | None:
@@ -488,6 +499,10 @@ def _find_deflatable_jpeg(
         return None
     _pim, filtdp = result
 
+    # Skip if already FlateDecode compressed - would double-compress
+    if _already_flate_encoded(image):
+        return None
+
     if (
         filtdp[0] == Name.DCTDecode
         and not filtdp[1]