v12.7.0 release notes

When compiled without pybind11 2.8.0, pikepdf supplies a shim to implement
pikepdf._ObjectMapping.values() which has subtly different semantics
from a true dict-like objects; in particular it supports
next(objectmap.values())
where a standard dict requires
next(iter(objectmap.values()).

pybind11 2.8.0 now implements .values() properly, meaning some misuses of
protocol  in ocrmypdf fail.

If pybind11 < 2.8.0, pikepdf will
continue to offer its shim. If pybind11 >= 2.8.0, pikepdf does not add its shim.

Consequently no changes were needed in pikepdf.

Closes #843

docs/api.rst

@@ -12,7 +12,7 @@ subprocess call anyway, as this provides isolation of its activities.
 Example
 =======
 
-OCRmyPDF one high-level function to run its main engine from an
+OCRmyPDF provides one high-level function to run its main engine from an
 application. The parameters are symmetric to the command line arguments
 and largely have the same functions.
 
@@ -23,7 +23,7 @@ and largely have the same functions.
     if __name__ == '__main__':  # To ensure correct behavior on Windows and macOS
         ocrmypdf.ocr('input.pdf', 'output.pdf', deskew=True)
 
-With a few exceptions, all of the command line arguments are available
+With some exceptions, all of the command line arguments are available
 and may be passed as equivalent keywords.
 
 A few differences are that ``verbose`` and ``quiet`` are not available.
@@ -41,29 +41,29 @@ execution. To do this, it will:
 - manage the signal flags of its worker processes
 - execute other subprocesses (forking and executing other programs)
 
-The Python process that calls ``ocrmypdf.ocr()`` must be sufficiently
+The Python process that calls :func:`ocrmypdf.ocr()` must be sufficiently
 privileged to perform these actions.
 
 There currently is no option to manage how jobs are scheduled other
 than the argument ``jobs=`` which will limit the number of worker
 processes.
 
-Creating a child process to call ``ocrmypdf.ocr()`` is suggested. That
+Creating a child process to call :func:`ocrmypdf.ocr()` is suggested. That
 way your application will survive and remain interactive even if
 OCRmyPDF fails for any reason.
 
-Programs that call ``ocrmypdf.ocr()`` should also install a SIGBUS signal
+Programs that call :func:`ocrmypdf.ocr()` should also install a SIGBUS signal
 handler (except on Windows), to raise an exception if access to a memory
 mapped file fails. OCRmyPDF may use memory mapping.
 
-``ocrmypdf.ocr()`` will take a threading lock to prevent multiple runs of itself
+:func:`ocrmypdf.ocr()` will take a threading lock to prevent multiple runs of itself
 in the same Python interpreter process. This is not thread-safe, because of how
 OCRmyPDF's plugins and Python's library import system work. If you need to parallelize
 OCRmyPDF, use processes.
 
 .. warning::
 
-    On Windows and macOS, the script that calls ``ocrmypdf.ocr()`` must be
+    On Windows and macOS, the script that calls :func:`ocrmypdf.ocr()` must be
     protected by an "ifmain" guard (``if __name__ == '__main__'``). If you do
     not take at least one of these steps, process semantics will prevent
     OCRmyPDF from working correctly.
@@ -96,7 +96,7 @@ Exceptions
 
 OCRmyPDF may throw standard Python exceptions, ``ocrmypdf.exceptions.*``
 exceptions, some exceptions related to multiprocessing, and
-``KeyboardInterrupt``. The parent process should provide an exception
+:exc:`KeyboardInterrupt`. The parent process should provide an exception
 handler. OCRmyPDF will clean up its temporary files and worker processes
 automatically when an exception occurs.
 

docs/conf.py

@@ -40,6 +40,7 @@ extensions = [
 ]
 
 # Extension settings
+intersphinx_mapping = {'https://docs.python.org/': None}
 napoleon_use_rtype = False
 issues_github_path = "jbarlow83/OCRmyPDF"
 

docs/release_notes.rst

@@ -18,6 +18,18 @@ wish to use some of its features for working with PDFs.
    for Python 3.6 around that time. The change will be marked with a major
    release.
 
+v12.7.0
+=======
+
+-  Fixed test suite failure when using pikepdf 3.2.0 that was compiled with pybind11
+   2.8.0. :issue:`843`
+-  Improve advice to user about using ``--max-image-mpixels`` if OCR fails for this
+   reason.
+-  Minor documentation fixes. (Thanks to @mara004.)
+-  Don't require importlib-metadata and importlib-resources backports on versions of
+   Python where the standard library implementation is sufficient.
+   (Thanks to Marco Genasci.)
+
 v12.6.0
 =======
 

setup.cfg

@@ -49,8 +49,8 @@ install_requires =
     cffi>=1.9.1  # must be a setup and install requirement
     coloredlogs>=14.0  # strictly optional
     img2pdf>=0.3.0,<0.5  # pure Python
-    importlib-metadata>=4  # until Python 3.8
-    importlib-resources>=5  # until Python 3.9
+    importlib-metadata>=4;python_version<'3.8'  # until Python 3.8
+    importlib-resources>=5;python_version<'3.9'  # until Python 3.9
     pdfminer.six!=20200720,>=20191110,<=20201018
     pikepdf>=2.10.0
     pikepdf<3;implementation_name=="pypy" and python_version=='3.6'
@@ -112,4 +112,4 @@ ignore =
 ignore = D203,F401,W503,E501,E203,F841
 exclude = .git,__pycache__,docs/conf.py,build,dist,.venv,.venvpp,.eggs,tmp,src/ocrmypdf/lib/
 max-complexity = 10
-max-line-length = 100
+max-line-length = 100

src/ocrmypdf/_sync.py

@@ -414,6 +414,13 @@ def run_pipeline(options, *, plugin_manager, api=False):
         else:
             log.error(type(e).__name__)
         return e.exit_code
+    except (PIL.Image.DecompressionBombError if not api else NeverRaise) as e:
+        log.exception(
+            "A decompression bomb error was encountered while executing the "
+            "pipeline. Use the argument --max-image-mpixels to raise the maximum "
+            "image pixel limit."
+        )
+        return ExitCode.other_error
     except (Exception if not api else NeverRaise):  # pylint: disable=broad-except
         log.exception("An exception occurred while executing the pipeline")
         return ExitCode.other_error

src/ocrmypdf/_version.py

@@ -5,7 +5,10 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
-from importlib_metadata import version as _package_version
+try:
+    from importlib_metadata import version as _package_version
+except ImportError:
+    from importlib.metadata import version as _package_version
 
 PROGRAM_NAME = 'ocrmypdf'
 

src/ocrmypdf/optimize.py

@@ -454,7 +454,7 @@ def _transcode_png(pike: Pdf, filename: Path, xref: Xref) -> bool:
         img2pdf.convert(fspath(filename), outputstream=f)
 
     with Pdf.open(output) as pdf_image:
-        foreign_image = next(pdf_image.pages[0].images.values())
+        foreign_image = next(iter(pdf_image.pages[0].images.values()))
         local_image = pike.copy_foreign(foreign_image)
 
         im_obj = pike.get_object(xref, 0)

src/ocrmypdf/pdfa.py

@@ -13,7 +13,10 @@ import base64
 from pathlib import Path
 from typing import Dict, Iterator, Union
 
-import importlib_resources
+try:
+    from importlib_resources import read_binary
+except ImportError:
+    from importlib.resources import read_binary
 import pikepdf
 import pkg_resources  # deprecated
 
@@ -104,7 +107,7 @@ def generate_pdfa_ps(target_filename: Path, icc: str = 'sRGB'):
     if icc != 'sRGB':
         raise NotImplementedError("Only supporting sRGB")
 
-    bytes_icc_profile = importlib_resources.read_binary(
+    bytes_icc_profile = read_binary(
         'ocrmypdf.data', SRGB_ICC_PROFILE_NAME
     )
     ps = '\n'.join(_make_postscript(icc, bytes_icc_profile, 3))

tests/test_image_input.py

@@ -87,4 +87,4 @@ def test_jpeg_in_jpeg_out(resources, outpdf):
         'tests/plugins/tesseract_noop.py',
     )
     with pikepdf.open(outpdf) as pdf:
-        assert next(pdf.pages[0].images.values()).Filter == pikepdf.Name.DCTDecode
+        assert next(iter(pdf.pages[0].images.values())).Filter == pikepdf.Name.DCTDecode

tests/test_main.py

@@ -745,14 +745,13 @@ def test_pdfa_n(pdfa_level, resources, outpdf):
     assert pdfa_info['conformance'] == f'PDF/A-{pdfa_level}B'
 
 
-@pytest.mark.skipif(
-    PIL.__version__ < '5.0.0', reason="Pillow < 5.0.0 doesn't raise the exception"
-)
-@pytest.mark.slow
-def test_decompression_bomb(resources, outpdf):
+def test_decompression_bomb_error(resources, outpdf):
     p, _out, err = run_ocrmypdf(resources / 'hugemono.pdf', outpdf)
-    assert 'decompression bomb' in err
+    assert 'decompression bomb' in err and '--max-image-mpixels' in err
 
+
+@pytest.mark.slow
+def test_decompression_bomb_succeeds(resources, outpdf):
     p, _out, err = run_ocrmypdf(
         resources / 'hugemono.pdf', outpdf, '--max-image-mpixels', '2000'
     )