unpaper: issue warning if image too large to clean

src/ocrmypdf/_exec/unpaper.py

@@ -22,14 +22,28 @@ from typing import List, Optional, Tuple, Union
 from PIL import Image
 
 from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
-from ocrmypdf.subprocess import get_version
-from ocrmypdf.subprocess import run as external_run
+from ocrmypdf.subprocess import get_version, run
+
+UNPAPER_IMAGE_PIXEL_LIMIT = 256 * 1024 * 1024
 
 DecFloat = Union[Decimal, float]
 
 log = logging.getLogger(__name__)
 
 
+class UnpaperImageTooLargeError(Exception):
+    def __init__(
+        self,
+        w,
+        h,
+        message="Image with size {}x{} is too large for cleaning with 'unpaper'.",
+    ):
+        self.w = w
+        self.h = h
+        self.message = message.format(w, h)
+        super().__init__(self.message)
+
+
 def version() -> str:
     return get_version('unpaper')
 
@@ -38,6 +52,8 @@ def _setup_unpaper_io(tmpdir: Path, input_file: Path) -> Tuple[Path, Path]:
     SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
     with Image.open(input_file) as im:
         im_modified = False
+        if im.width * im.height >= UNPAPER_IMAGE_PIXEL_LIMIT:
+            raise UnpaperImageTooLargeError(w=im.width, h=im.height)
         if im.mode not in SUFFIXES:
             log.info("Converting image to other colorspace")
             try:
@@ -68,7 +84,7 @@ def _setup_unpaper_io(tmpdir: Path, input_file: Path) -> Tuple[Path, Path]:
     return input_pnm, output_pnm
 
 
-def run(
+def run_unpaper(
     input_file: Path, output_file: Path, *, dpi: DecFloat, mode_args: List[str]
 ) -> None:
     args_unpaper = ['unpaper', '-v', '--dpi', str(round(dpi, 6))] + mode_args
@@ -84,7 +100,7 @@ def run(
         # This should ensure that a user cannot clobber some other file with
         # their unpaper arguments (whether intentionally or otherwise)
         args_unpaper.extend([os.fspath(input_pnm), os.fspath(output_pnm)])
-        external_run(
+        run(
             args_unpaper,
             close_fds=True,
             check=True,
@@ -117,7 +133,7 @@ def clean(
     *,
     dpi: DecFloat,
     unpaper_args: Optional[List[str]] = None,
-):
+) -> Path:
     default_args = [
         '--layout',
         'none',
@@ -131,4 +147,9 @@ def clean(
     ]
     if not unpaper_args:
         unpaper_args = default_args
-    run(input_file, output_file, dpi=dpi, mode_args=unpaper_args)
+    try:
+        run_unpaper(input_file, output_file, dpi=dpi, mode_args=unpaper_args)
+        return output_file
+    except UnpaperImageTooLargeError as e:
+        log.warning(str(e))
+        return input_file

src/ocrmypdf/_pipeline.py

@@ -494,13 +494,12 @@ def preprocess_deskew(input_file: Path, page_context: PageContext):
 def preprocess_clean(input_file: Path, page_context: PageContext):
     output_file = page_context.get_path('pp_clean.png')
     dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
-    unpaper.clean(
+    return unpaper.clean(
         input_file,
         output_file,
         dpi=dpi.x,
         unpaper_args=page_context.options.unpaper_args,
     )
-    return output_file
 
 
 def create_ocr_image(image: Path, page_context: PageContext):

tests/test_unpaper.py

@@ -5,19 +5,24 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+import logging
 from os import fspath
 from unittest.mock import patch
 
 import pytest
+from PIL import Image
 
+from ocrmypdf._exec import unpaper
 from ocrmypdf._plugin_manager import get_parser_options_plugins
 from ocrmypdf._validation import check_options
 from ocrmypdf.exceptions import ExitCode, MissingDependencyError
 
-from .conftest import check_ocrmypdf, have_unpaper, run_ocrmypdf
+from .conftest import check_ocrmypdf, have_unpaper, ocrmypdf_exec, run_ocrmypdf
 
 # pylint: disable=redefined-outer-name
 
+needs_unpaper = pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+
 
 def test_no_unpaper(resources, no_outpdf):
     input_ = fspath(resources / "c02-22.pdf")
@@ -45,7 +50,7 @@ def test_old_unpaper(resources, no_outpdf):
         mock.assert_called()
 
 
-@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+@needs_unpaper
 def test_clean(resources, outpdf):
     check_ocrmypdf(
         resources / "skew.pdf",
@@ -56,7 +61,7 @@ def test_clean(resources, outpdf):
     )
 
 
-@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+@needs_unpaper
 def test_unpaper_args_valid(resources, outpdf):
     check_ocrmypdf(
         resources / "skew.pdf",
@@ -69,7 +74,7 @@ def test_unpaper_args_valid(resources, outpdf):
     )
 
 
-@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+@needs_unpaper
 def test_unpaper_args_invalid_filename(resources, outpdf):
     p = run_ocrmypdf(
         resources / "skew.pdf",
@@ -84,7 +89,7 @@ def test_unpaper_args_invalid_filename(resources, outpdf):
     assert p.returncode == ExitCode.bad_args
 
 
-@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+@needs_unpaper
 def test_unpaper_args_invalid(resources, outpdf):
     p = run_ocrmypdf(
         resources / "skew.pdf",
@@ -98,3 +103,16 @@ def test_unpaper_args_invalid(resources, outpdf):
     # Can't tell difference between unpaper choking on bad arguments or some
     # other unpaper failure
     assert p.returncode == ExitCode.child_process_error
+
+
+@needs_unpaper
+def test_unpaper_image_too_big(resources, outdir, caplog):
+    with patch('ocrmypdf._exec.unpaper.UNPAPER_IMAGE_PIXEL_LIMIT', 42):
+        infile = resources / 'crom.png'
+        unpaper.clean(infile, outdir / 'out.png', dpi=300) == infile
+
+        assert any(
+            'too large for cleaning' in rec.message
+            for rec in caplog.get_records('call')
+            if rec.levelno == logging.WARNING
+        )