From 6edc749023cf7457ffae77aebfcad3927bc48999 Mon Sep 17 00:00:00 2001
From: "James R. Barlow" <james@purplerock.ca>
Date: Tue, 7 Jan 2025 00:27:07 -0800
Subject: [PATCH] Fix error handling when PDF contains an invalid image with
 both ImageMask and ColorSpace set

Fixes #1453
---
 src/ocrmypdf/_exec/ghostscript.py | 15 +++++++--
 tests/test_ghostscript.py         | 56 ++++++++++++++++++++++++++++++-
 2 files changed, 68 insertions(+), 3 deletions(-)

diff --git a/src/ocrmypdf/_exec/ghostscript.py b/src/ocrmypdf/_exec/ghostscript.py
index ee8a5d407..bd8bd105d 100644
--- a/src/ocrmypdf/_exec/ghostscript.py
+++ b/src/ocrmypdf/_exec/ghostscript.py
@@ -17,7 +17,11 @@
 from packaging.version import Version
 from PIL import Image, UnidentifiedImageError
 
-from ocrmypdf.exceptions import ColorConversionNeededError, SubprocessOutputError
+from ocrmypdf.exceptions import (
+    ColorConversionNeededError,
+    InputFileError,
+    SubprocessOutputError,
+)
 from ocrmypdf.helpers import Resolution
 from ocrmypdf.subprocess import get_version, run, run_polling_stderr
 
@@ -111,7 +115,6 @@ def rasterize_pdf(
     args_gs = (
         [
             GS,
-            '-dQUIET',
             '-dSAFER',
             '-dBATCH',
             '-dNOPAUSE',
@@ -143,6 +146,14 @@ def rasterize_pdf(
     stderr = p.stderr.decode(errors='replace')
     if _gs_error_reported(stderr):
         log.error(stderr)
+        if stop_on_error and "recoverable image error" in stderr:
+            Path(output_file).unlink(missing_ok=True)
+            raise InputFileError(
+                "Ghostscript rasterizing failed. The input file contains errors that "
+                "cause PDF viewers to interpret it differently and incorrectly. "
+                "Try using --continue-on-soft-render-error and manually inspect the "
+                "input and output files to check for visual differences or errors."
+            )
 
     try:
         with Image.open(output_file) as im:
diff --git a/tests/test_ghostscript.py b/tests/test_ghostscript.py
index 0c2a69bda..ca9c14dc2 100644
--- a/tests/test_ghostscript.py
+++ b/tests/test_ghostscript.py
@@ -14,7 +14,7 @@
 from PIL import Image, UnidentifiedImageError
 
 from ocrmypdf._exec.ghostscript import DuplicateFilter, rasterize_pdf
-from ocrmypdf.exceptions import ColorConversionNeededError, ExitCode
+from ocrmypdf.exceptions import ColorConversionNeededError, ExitCode, InputFileError
 from ocrmypdf.helpers import Resolution
 
 from .conftest import check_ocrmypdf, run_ocrmypdf_api
@@ -208,3 +208,57 @@ def test_filter_alt_messages(self, duplicate_filter_logger, caplog):
         assert caplog.records[1].msg == "another error message"
         assert caplog.records[2].msg == "(suppressed 5 repeated lines)"
         assert caplog.records[3].msg == "yet another error message"
+
+
+def test_recoverable_image_error_path(outdir, caplog):
+    # issue 1451
+    Name = pikepdf.Name
+    pdf = pikepdf.new()
+    pdf.add_blank_page()
+    pdf.pages[0].Contents = pdf.make_stream(b'612 0 0 612 0 0 cm /Image Do')
+    # Create an invalid image object that has both ColorSpace and ImageMask set
+    pdf.pages[0].Resources = pikepdf.Dictionary(
+        XObject=pdf.make_indirect(
+            pikepdf.Dictionary(
+                Image=pdf.make_stream(
+                    b"\xf0\x0f" * 8,
+                    ColorSpace=Name.DeviceGray,
+                    BitsPerComponent=1,
+                    Width=8,
+                    Height=8,
+                    ImageMask=True,
+                    Subtype=Name.Image,
+                    Type=Name.XObject,
+                )
+            )
+        )
+    )
+    pdf.save(outdir / 'invalid_image.pdf')
+    pdf.save('invalid_image.pdf')
+
+    # When stop_on_error is False, we expect Ghostscript to print an error
+    # but continue
+    rasterize_pdf(
+        outdir / 'invalid_image.pdf',
+        outdir / 'out1.png',
+        raster_device='pngmono',
+        raster_dpi=Resolution(10, 10),
+        stop_on_error=False,
+    )
+    assert 'Image has both ImageMask and ColorSpace' in caplog.text
+
+    # When stop_on_error is True, Ghostscript will print an error and exit
+    # but still produce a viable image. We intercept this case and raise
+    # InputFileError because it will contain an image of the whole page minus
+    # the image we are rendering.
+    with pytest.raises(
+        InputFileError, match="Try using --continue-on-soft-render-error"
+    ):
+        rasterize_pdf(
+            outdir / 'invalid_image.pdf',
+            outdir / 'out2.png',
+            raster_device='pngmono',
+            raster_dpi=Resolution(100, 100),
+            stop_on_error=True,
+        )
+    # out2.png will not be created; if it were it would be blank.