v11.4.5 release notes

Co-authored-by: Jonas Winkler <jonas.winkler@jpwinkler.de>

.coveragerc

@@ -1,24 +0,0 @@
-[paths]
-source =
-	src
-	*/site-packages
-
-[run]
-branch = true
-parallel = true
-concurrency =
-	thread
-	multiprocessing
-source =
-	src/ocrmypdf
-
-[report]
-exclude_lines =
-	pragma: no cover
-	def __repr__
-	raise AssertionError
-	raise NotImplementedError
-	if 0:
-	if False:
-	if __name__ == .__main__.:
-	if TYPE_CHECKING:

azure-pipelines.yml

@@ -32,7 +32,7 @@ stages:
               choco install --yes --no-progress --pre tesseract
               choco install --yes --no-progress python3
               choco install --yes --no-progress ghostscript
-              choco install --yes --no-progress pngquant
+              # choco install --yes --no-progress pngquant
             displayName: "Install system packages"
           - pwsh: |
               refreshenv

docs/api.rst

@@ -56,6 +56,11 @@ Programs that call ``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
+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

docs/installation.rst

@@ -637,7 +637,7 @@ Installing with Python pip
 OCRmyPDF is delivered by PyPI because it is a convenient way to install
 the latest version. However, PyPI and ``pip`` cannot address the fact
 that ``ocrmypdf`` depends on certain non-Python system libraries and
-programs being instsalled.
+programs being installed.
 
 For best results, first install `your platform's
 version <https://repology.org/metapackage/ocrmypdf/versions>`__ of

docs/release_notes.rst

@@ -12,6 +12,28 @@ may be unreliable. Use the API to depend on precise behavior.
 The public API may be useful in scripts that launch OCRmyPDF processes or that
 wish to use some of its features for working with PDFs.
 
+v11.4.5
+=======
+
+-  Fixed an issue where files may not be closed when the API is used.
+-  Improved ``setup.cfg`` with better settings for test coverage.
+
+v11.4.4
+=======
+
+-  Fixed ``AttributeError: 'NoneType' object has no attribute 'userunit'``, issue #700,
+   related to OCRmyPDF not properly forwarded an error message from pdfminer.six.
+-  Adjusted typing of some arguments.
+-  ``ocrmypdf.ocr`` now takes a ``threading.Lock`` for reasons outlined in the
+   documentation.
+
+v11.4.3
+=======
+
+-  Removed a redundant debug message.
+-  Test suite now asserts that most patched functions are called when they should be.
+-  Test suite now skips a test that fails on two particular versions of piekpdf.
+
 v11.4.2
 =======
 

setup.cfg

@@ -15,6 +15,8 @@ filterwarnings =
 	ignore:.*XMLParser.*:DeprecationWarning
 markers =
 	slow
+addopts =
+	-n auto
 
 [isort]
 multi_line_output=3
@@ -27,3 +29,30 @@ known_third_party = PIL,_cffi_backend,cffi,flask,img2pdf,pdfminer,pikepdf,pkg_re
 
 [metadata]
 license_file = LICENSE
+
+[coverage:paths]
+source =
+	src/
+
+[coverage:run]
+branch = true
+parallel = true
+concurrency = multiprocessing
+source =
+	src/ocrmypdf
+
+[coverage:report]
+# Regexes for lines to exclude from consideration
+exclude_lines =
+    # Have to re-enable the standard pragma
+    pragma: no cover
+
+    # Don't complain if tests don't hit defensive assertion code:
+    raise AssertionError
+    raise NotImplementedError
+
+    # Don't complain if non-runnable code isn't run:
+    if 0:
+	if False:
+    if __name__ == .__main__.:
+	if TYPE_CHECKING:

src/ocrmypdf/_concurrent.py

@@ -109,15 +109,11 @@ def exec_progress_pool(
         )
         try:
             results = pool.imap_unordered(task, task_arguments)
-            while True:
+            for result in results:
-                try:
+                if task_finished:
-                    result = results.next()
+                    task_finished(result, pbar)
-                    if task_finished:
+                else:
-                        task_finished(result, pbar)
+                    pbar.update()
-                    else:
-                        pbar.update()
-                except StopIteration:
-                    break
         except KeyboardInterrupt:
             # Terminate pool so we exit instantly
             pool.terminate()

src/ocrmypdf/_exec/ghostscript.py

@@ -254,6 +254,8 @@ def generate_pdfa(
         raise SubprocessOutputError('Ghostscript PDF/A rendering failed') from e
     else:
         stderr = p.stderr
+        # If there is an error we log the whole stderr, except for filtering
+        # duplicates.
         if _gs_error_reported(stderr):
             last_part = None
             repcount = 0
@@ -266,11 +268,3 @@ def generate_pdfa(
                 else:
                     repcount += 1
                 last_part = part
-        elif 'overprint mode not set' in stderr:
-            # Unless someone is going to print PDF/A documents on a
-            # magical sRGB printer I can't see the removal of overprinting
-            # being a problem....
-            log.debug(
-                "Ghostscript had to remove PDF 'overprinting' from the "
-                "input file to complete PDF/A conversion. "
-            )

src/ocrmypdf/_exec/tesseract.py

@@ -14,7 +14,7 @@ from collections import namedtuple
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
-from typing import List
+from typing import List, Optional
 
 from PIL import Image
 
@@ -118,7 +118,7 @@ def get_languages():
     return set(lang.strip() for lang in rest)
 
 
-def tess_base_args(langs: List[str], engine_mode: int) -> List[str]:
+def tess_base_args(langs: List[str], engine_mode: Optional[int]) -> List[str]:
     args = ['tesseract']
     if langs:
         args.extend(['-l', '+'.join(langs)])
@@ -127,7 +127,7 @@ def tess_base_args(langs: List[str], engine_mode: int) -> List[str]:
     return args
 
 
-def get_orientation(input_file: Path, engine_mode: int, timeout: float):
+def get_orientation(input_file: Path, engine_mode: Optional[int], timeout: float):
     args_tesseract = tess_base_args(['osd'], engine_mode) + [
         '--psm',
         '0',

src/ocrmypdf/_pipeline.py

@@ -756,19 +756,17 @@ def metadata_fixup(working_file: Path, context: PdfContext):
             if 'xmp:CreateDate' not in meta:
                 meta['xmp:CreateDate'] = meta.get('xmp:ModifyDate', '')
 
-            # Ghostscript likes to set title to Untitled if omitted from input.
+            with original.open_metadata(
-            # Reverse this, because PDF/A TechNote 0003:Metadata in PDF/A-1
+                set_pikepdf_as_editor=False, update_docinfo=False, strict=False
-            # and the XMP Spec do not make this recommendation.
+            ) as meta_original:
-            if meta.get('dc:title') == 'Untitled':
+                if meta.get('dc:title') == 'Untitled':
-                with original.open_metadata(
+                    # Ghostscript likes to set title to Untitled if omitted from input.
-                    set_pikepdf_as_editor=False, update_docinfo=False
+                    # Reverse this, because PDF/A TechNote 0003:Metadata in PDF/A-1
-                ) as original_meta:
+                    # and the XMP Spec do not make this recommendation.
-                    if 'dc:title' not in original_meta:
+                    if 'dc:title' not in meta_original:
                         del meta['dc:title']
-
+                missing = set(meta_original.keys()) - set(meta.keys())
-            meta_original = original.open_metadata()
+                report_on_metadata(missing)
-            missing = set(meta_original.keys()) - set(meta.keys())
-            report_on_metadata(missing)
 
         pdf.save(
             output_file,

src/ocrmypdf/_sync.py

@@ -338,6 +338,8 @@ def run_pipeline(options, *, plugin_manager, api=False):
         and not api
     ):
         # Debug log for command line interface only with verbose output
+        # See https://github.com/pytest-dev/pytest/issues/5502 for why we skip this
+        # when pytest is running
         debug_log_handler = configure_debug_logging(Path(work_folder) / "debug.log")
 
     pikepdf_enable_mmap()

src/ocrmypdf/api.py

@@ -8,6 +8,7 @@
 import logging
 import os
 import sys
+import threading
 from enum import IntEnum
 from io import IOBase
 from pathlib import Path
@@ -30,6 +31,8 @@ except ModuleNotFoundError:
 StrPath = Union[os.PathLike, AnyStr]
 PathOrIO = Union[BinaryIO, StrPath]
 
+_api_lock = threading.Lock()
+
 
 class Verbosity(IntEnum):
     """Verbosity level for configure_logging."""
@@ -306,12 +309,18 @@ def ocr(  # pylint: disable=unused-argument
 
     parser = get_parser()
     create_options_kwargs['parser'] = parser
-    plugin_manager = get_plugin_manager(plugins)
-    plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
 
-    if 'verbose' in kwargs:
+    with _api_lock:
-        warn("ocrmypdf.ocr(verbose=) is ignored. Use ocrmypdf.configure_logging().")
+        # We can't allow multiple ocrmypdf.ocr() threads to run in parallel, because
+        # they might install different plugins, and generally speaking we have areas
+        # of code that use global state.
 
-    options = create_options(**create_options_kwargs)
+        plugin_manager = get_plugin_manager(plugins)
-    check_options(options, plugin_manager)
+        plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
-    return run_pipeline(options=options, plugin_manager=plugin_manager, api=True)
+
+        if 'verbose' in kwargs:
+            warn("ocrmypdf.ocr(verbose=) is ignored. Use ocrmypdf.configure_logging().")
+
+        options = create_options(**create_options_kwargs)
+        check_options(options, plugin_manager)
+        return run_pipeline(options=options, plugin_manager=plugin_manager, api=True)

src/ocrmypdf/optimize.py

@@ -498,7 +498,7 @@ def transcode_pngs(
 
 
 @deprecated
-def rewrite_png_as_g4(pike: Pdf, im_obj: Object, compdata) -> None:
+def rewrite_png_as_g4(pike: Pdf, im_obj: Object, compdata) -> None:  # pragma: no cover
     im_obj.BitsPerComponent = 1
     im_obj.Width = compdata.w
     im_obj.Height = compdata.h
@@ -519,7 +519,7 @@ def rewrite_png_as_g4(pike: Pdf, im_obj: Object, compdata) -> None:
 
 
 @deprecated
-def rewrite_png(pike: Pdf, im_obj: Object, compdata) -> None:
+def rewrite_png(pike: Pdf, im_obj: Object, compdata) -> None:  # pragma: no cover
     # When a PNG is inserted into a PDF, we more or less copy the IDAT section from
     # the PDF and transfer the rest of the PNG headers to PDF image metadata.
     # One thing we have to do is tell the PDF reader whether a predictor was used

src/ocrmypdf/pdfinfo/info.py

@@ -22,7 +22,7 @@ import pikepdf
 from pikepdf import Object, Pdf, PdfMatrix
 
 from ocrmypdf._concurrent import exec_progress_pool
-from ocrmypdf.exceptions import EncryptedPdfError
+from ocrmypdf.exceptions import EncryptedPdfError, InputFileError
 from ocrmypdf.helpers import Resolution, available_cpu_count, pikepdf_enable_mmap
 from ocrmypdf.pdfinfo.layout import get_page_analysis, get_text_boxes
 
@@ -598,6 +598,8 @@ def _pdf_pageinfo_concurrent(
 
     def update_pageinfo(result, pbar):
         page = result
+        if not page:
+            raise InputFileError("Could read a page in the PDF")
         pages[page.pageno] = page
         pbar.update()
 

src/ocrmypdf/pdfinfo/layout.py

@@ -21,7 +21,7 @@ from pdfminer.pdffont import PDFSimpleFont, PDFUnicodeNotDefined
 from pdfminer.pdfpage import PDFPage
 from pdfminer.utils import bbox2str, matrix2str
 
-from ocrmypdf.exceptions import EncryptedPdfError
+from ocrmypdf.exceptions import EncryptedPdfError, InputFileError
 
 STRIP_NAME = re.compile(r'[0-9]+')
 
@@ -236,8 +236,13 @@ def get_page_analysis(infile, pageno, pscript5_mode):
 
     try:
         with Path(infile).open('rb') as f:
-            page = PDFPage.get_pages(f, pagenos=[pageno], maxpages=0)
+            page_iter = PDFPage.get_pages(f, pagenos=[pageno], maxpages=0)
-            interp.process_page(next(page))
+            page = next(page_iter, None)
+            if page is None:
+                raise InputFileError(
+                    f"pdfminer could not process page {pageno} (counting from 0)."
+                )
+            interp.process_page(page)
     except PDFTextExtractionNotAllowed as e:
         raise EncryptedPdfError() from e
     finally:

src/ocrmypdf/subprocess/__init__.py

@@ -77,20 +77,19 @@ def run_polling_stderr(args, *, callback, check=False, env=None, **kwargs):
     args, env, process_log, text = _fix_process_args(args, env, kwargs)
     assert text, "Must use text=True"
 
-    proc = Popen(args, env=env, **kwargs)
+    with Popen(args, env=env, **kwargs) as proc:
+        lines = []
+        while proc.poll() is None:
+            for msg in iter(proc.stderr.readline, ''):
+                if process_log.isEnabledFor(logging.DEBUG):
+                    process_log.debug(msg.strip())
+                callback(msg)
+                lines.append(msg)
+        stderr = ''.join(lines)
 
-    lines = []
+        if check and proc.returncode != 0:
-    while proc.poll() is None:
+            raise CalledProcessError(proc.returncode, args, output=None, stderr=stderr)
-        for msg in iter(proc.stderr.readline, ''):
+        return CompletedProcess(args, proc.returncode, None, stderr=stderr)
-            if process_log.isEnabledFor(logging.DEBUG):
-                process_log.debug(msg.strip())
-            callback(msg)
-            lines.append(msg)
-    stderr = ''.join(lines)
-
-    if check and proc.returncode != 0:
-        raise CalledProcessError(proc.returncode, args, output=None, stderr=stderr)
-    return CompletedProcess(args, proc.returncode, None, stderr=stderr)
 
 
 def _fix_process_args(args, env, kwargs):

tests/conftest.py

@@ -137,16 +137,7 @@ def run_ocrmypdf(input_file, output_file, *args, text=True):
         + [str(input_file), str(output_file)]
     )
 
-    # Tell subprocess where to find coverage.py configuration
-    # This has no unless except when coverage is running
-    # Details: https://coverage.readthedocs.io/en/coverage-5.0/subprocess.html
-    coverage_rc = Path(__file__).parent.parent / '.coveragerc'
     env = os.environ.copy()
-    if coverage_rc.exists():
-        env['COVERAGE_PROCESS_START'] = os.fspath(coverage_rc)
-    elif not running_in_docker():
-        assert False, "could not find .coveragerc"
-
     p = run(
         p_args,
         stdout=PIPE,

tests/plugins/gs_feature_elision.py

@@ -23,21 +23,22 @@ from unittest.mock import patch
 
 from ocrmypdf import hookimpl
 from ocrmypdf.builtin_plugins import ghostscript
-from ocrmypdf.subprocess import run
+from ocrmypdf.subprocess import run_polling_stderr
 
 elision_warning = """GPL Ghostscript 9.20: Setting Overprint Mode to 1
 not permitted in PDF/A-2, overprint mode not set"""
 
 
 def run_append_stderr(*args, **kwargs):
-    proc = run(*args, **kwargs)
+    proc = run_polling_stderr(*args, **kwargs)
-    proc.stderr = b'\n'.join([proc.stderr, elision_warning.encode('utf-8')])
+    proc.stderr += '\n' + elision_warning + '\n'
     return proc
 
 
 @hookimpl
 def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdfa_part):
-    with patch('ocrmypdf._exec.ghostscript.run', new=run_append_stderr):
+    with patch('ocrmypdf._exec.ghostscript.run_polling_stderr') as mock:
+        mock.side_effect = run_append_stderr
         ghostscript.generate_pdfa(
             pdf_pages=pdf_pages,
             pdfmark=pdfmark,
@@ -47,4 +48,5 @@ def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdf
             pdfa_part=pdfa_part,
             progressbar_class=None,
         )
-        return output_file
+        mock.assert_called_once()
+    return output_file

tests/plugins/gs_pdfa_failure.py

@@ -39,7 +39,8 @@ def run_rig_args(args, **kwargs):
 
 @hookimpl
 def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdfa_part):
-    with patch('ocrmypdf._exec.ghostscript.run_polling_stderr', new=run_rig_args):
+    with patch('ocrmypdf._exec.ghostscript.run_polling_stderr') as mock:
+        mock.side_effect = run_rig_args
         ghostscript.generate_pdfa(
             pdf_pages=pdf_pages,
             pdfmark=pdfmark,
@@ -49,4 +50,5 @@ def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdf
             pdfa_part=pdfa_part,
             progressbar_class=None,
         )
+        mock.assert_called()
         return output_file

tests/plugins/gs_raster_failure.py

@@ -44,7 +44,8 @@ def rasterize_pdf_page(
     rotation=None,
     filter_vector=False,
 ) -> Path:
-    with patch('ocrmypdf._exec.ghostscript.run', new=raise_gs_fail):
+    with patch('ocrmypdf._exec.ghostscript.run') as mock:
+        mock.side_effect = raise_gs_fail
         ghostscript.rasterize_pdf_page(
             input_file=input_file,
             output_file=output_file,
@@ -55,4 +56,5 @@ def rasterize_pdf_page(
             rotation=rotation,
             filter_vector=filter_vector,
         )
+        mock.assert_called()
         return output_file

tests/plugins/gs_render_failure.py

@@ -34,7 +34,8 @@ def raise_gs_fail(*args, **kwargs):
 
 @hookimpl
 def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdfa_part):
-    with patch('ocrmypdf._exec.ghostscript.run_polling_stderr', new=raise_gs_fail):
+    with patch('ocrmypdf._exec.ghostscript.run_polling_stderr') as mock:
+        mock.side_effect = raise_gs_fail
         ghostscript.generate_pdfa(
             pdf_pages=pdf_pages,
             pdfmark=pdfmark,
@@ -44,4 +45,5 @@ def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdf
             pdfa_part=pdfa_part,
             progressbar_class=None,
         )
+        mock.assert_called()
         return output_file

tests/plugins/tesseract_badutf8.py

@@ -26,6 +26,7 @@ that is not UTF-8 compatible, so we are forced to check that we can convert it
 and present it to the user.
 """
 
+from contextlib import contextmanager
 from subprocess import CalledProcessError
 from unittest.mock import patch
 
@@ -42,17 +43,25 @@ def bad_utf8(*args, **kwargs):
     )
 
 
+@contextmanager
+def patch_tesseract_run():
+    with patch('ocrmypdf._exec.tesseract.run') as mock:
+        mock.side_effect = bad_utf8
+        yield
+        mock.assert_called()
+
+
 class BadUtf8OcrEngine(TesseractOcrEngine):
     @staticmethod
     def generate_hocr(input_file, output_hocr, output_text, options):
-        with patch('ocrmypdf._exec.tesseract.run', new=bad_utf8):
+        with patch_tesseract_run():
             TesseractOcrEngine.generate_hocr(
                 input_file, output_hocr, output_text, options
             )
 
     @staticmethod
     def generate_pdf(input_file, output_pdf, output_text, options):
-        with patch('ocrmypdf._exec.tesseract.run', new=bad_utf8):
+        with patch_tesseract_run():
             TesseractOcrEngine.generate_pdf(
                 input_file, output_pdf, output_text, options
             )

tests/plugins/tesseract_big_image_error.py

@@ -19,6 +19,7 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
+from contextlib import contextmanager
 from subprocess import CalledProcessError
 from unittest.mock import patch
 
@@ -35,22 +36,30 @@ def raise_size_exception(*args, **kwargs):
     )
 
 
+@contextmanager
+def patch_tesseract_run():
+    with patch('ocrmypdf._exec.tesseract.run') as mock:
+        mock.side_effect = raise_size_exception
+        yield
+        mock.assert_called()
+
+
 class BigImageErrorOcrEngine(TesseractOcrEngine):
     @staticmethod
     def get_orientation(input_file, options):
-        with patch('ocrmypdf._exec.tesseract.run', new=raise_size_exception):
+        with patch_tesseract_run():
             return TesseractOcrEngine.get_orientation(input_file, options)
 
     @staticmethod
     def generate_hocr(input_file, output_hocr, output_text, options):
-        with patch('ocrmypdf._exec.tesseract.run', new=raise_size_exception):
+        with patch_tesseract_run():
             TesseractOcrEngine.generate_hocr(
                 input_file, output_hocr, output_text, options
             )
 
     @staticmethod
     def generate_pdf(input_file, output_pdf, output_text, options):
-        with patch('ocrmypdf._exec.tesseract.run', new=raise_size_exception):
+        with patch_tesseract_run():
             TesseractOcrEngine.generate_pdf(
                 input_file, output_pdf, output_text, options
             )

tests/plugins/tesseract_crash.py

@@ -20,6 +20,7 @@
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 import signal
+from contextlib import contextmanager
 from subprocess import CalledProcessError
 from unittest.mock import patch
 
@@ -37,22 +38,30 @@ def raise_crash(*args, **kwargs):
     )
 
 
+@contextmanager
+def patch_tesseract_run():
+    with patch('ocrmypdf._exec.tesseract.run') as mock:
+        mock.side_effect = raise_crash
+        yield
+        mock.assert_called()
+
+
 class CrashOcrEngine(TesseractOcrEngine):
     @staticmethod
     def get_orientation(input_file, options):
-        with patch('ocrmypdf._exec.tesseract.run', new=raise_crash):
+        with patch_tesseract_run():
             return TesseractOcrEngine.get_orientation(input_file, options)
 
     @staticmethod
     def generate_hocr(input_file, output_hocr, output_text, options):
-        with patch('ocrmypdf._exec.tesseract.run', new=raise_crash):
+        with patch_tesseract_run():
             TesseractOcrEngine.generate_hocr(
                 input_file, output_hocr, output_text, options
             )
 
     @staticmethod
     def generate_pdf(input_file, output_pdf, output_text, options):
-        with patch('ocrmypdf._exec.tesseract.run', new=raise_crash):
+        with patch_tesseract_run():
             TesseractOcrEngine.generate_pdf(
                 input_file, output_pdf, output_text, options
             )

tests/test_helpers.py

@@ -36,12 +36,17 @@ class TestSafeSymlink:
 
 
 def test_no_cpu_count(monkeypatch):
+    invoked = False
+
     def cpu_count_raises():
+        nonlocal invoked
+        invoked = True
         raise NotImplementedError()
 
     monkeypatch.setattr(multiprocessing, 'cpu_count', cpu_count_raises)
     with pytest.warns(expected_warning=UserWarning):
         assert helpers.available_cpu_count() == 1
+    assert invoked, "Patched function called during test"
 
 
 def test_deprecated():

tests/test_image_input.py

@@ -65,11 +65,12 @@ def test_cmyk_no_icc(caplog, resources, no_outpdf):
 def test_img2pdf_fails(resources, no_outpdf):
     with patch(
         'ocrmypdf._pipeline.img2pdf.convert', side_effect=img2pdf.ImageOpenError()
-    ):
+    ) as mock:
         rc = run_ocrmypdf_api(
             resources / 'baiona_gray.png', no_outpdf, '--image-dpi', '200'
         )
         assert rc == ocrmypdf.ExitCode.input_file
+        mock.assert_called()
 
 
 def test_jpeg_in_jpeg_out(resources, outpdf):

tests/test_metadata.py

@@ -306,6 +306,9 @@ def test_kodak_toc(resources, outpdf):
         assert isinstance(p.Root.Outlines.First, pikepdf.Dictionary)
 
 
+@pytest.mark.skipif(
+    pikepdf.__version__ in ('2.2.2', '2.2.3'), reason="Raises wrong warning"
+)
 def test_metadata_fixup_warning(resources, outdir, caplog):
     options = get_parser().parse_args(
         args=['--output-type', 'pdfa-2', 'graph.pdf', 'out.pdf']
@@ -318,7 +321,7 @@ def test_metadata_fixup_warning(resources, outdir, caplog):
     )
     metadata_fixup(working_file=outdir / 'graph.pdf', context=context)
     for record in caplog.records:
-        assert record.levelname != 'WARNING'
+        assert record.levelname != 'WARNING', "Unexpected warning"
 
     # Now add some metadata that will not be copyable
     graph = pikepdf.open(outdir / 'graph.pdf')

tests/test_optimize.py

@@ -21,7 +21,15 @@ from ocrmypdf.helpers import Resolution
 
 check_ocrmypdf = pytest.helpers.check_ocrmypdf  # pylint: disable=e1101
 
+needs_pngquant = pytest.mark.skipif(
+    not pngquant.available(), reason="pngquant not installed"
+)
+needs_jbig2enc = pytest.mark.skipif(
+    not jbig2enc.available(), reason="jbig2enc not installed"
+)
 
+
+@needs_pngquant
 @pytest.mark.parametrize('pdf', ['multipage.pdf', 'palette.pdf'])
 def test_basic(resources, pdf, outpdf):
     infile = resources / pdf
@@ -30,6 +38,7 @@ def test_basic(resources, pdf, outpdf):
     assert 0.98 * Path(outpdf).stat().st_size <= Path(infile).stat().st_size
 
 
+@needs_pngquant
 def test_mono_not_inverted(resources, outdir):
     infile = resources / '2400dpi.pdf'
     opt.main(infile, outdir / 'out.pdf', level=3)
@@ -45,7 +54,7 @@ def test_mono_not_inverted(resources, outdir):
         assert im.getpixel((0, 0)) == 255, "Expected white background"
 
 
-@pytest.mark.skipif(not pngquant.available(), reason='need pngquant')
+@needs_pngquant
 def test_jpg_png_params(resources, outpdf):
     check_ocrmypdf(
         resources / 'crom.png',
@@ -63,7 +72,7 @@ def test_jpg_png_params(resources, outpdf):
     )
 
 
-@pytest.mark.skipif(not jbig2enc.available(), reason='need jbig2enc')
+@needs_jbig2enc
 @pytest.mark.parametrize('lossy', [False, True])
 def test_jbig2_lossy(lossy, resources, outpdf):
     args = [
@@ -95,10 +104,8 @@ def test_jbig2_lossy(lossy, resources, outpdf):
         assert len(pim.decode_parms) == 0
 
 
-@pytest.mark.skipif(
+@needs_pngquant
-    not jbig2enc.available() or not pngquant.available(),
+@needs_jbig2enc
-    reason='need jbig2enc and pngquant',
-)
 def test_flate_to_jbig2(resources, outdir):
     # This test requires an image that pngquant is capable of converting to
     # to 1bpp - so use an existing 1bpp image, convert up, confirm it can
@@ -126,6 +133,7 @@ def test_flate_to_jbig2(resources, outdir):
     assert pim.filters[0] == '/JBIG2Decode'
 
 
+@needs_pngquant
 def test_multiple_pngs(resources, outdir):
     with Path.open(outdir / 'in.pdf', 'wb') as inpdf:
         img2pdf.convert(
@@ -141,7 +149,8 @@ def test_multiple_pngs(resources, outdir):
             draw.rectangle((0, 0, im.width, im.height), fill=128)
             im.save(output_file)
 
-    with patch('ocrmypdf.optimize.pngquant.quantize', new=mockquant):
+    with patch('ocrmypdf.optimize.pngquant.quantize') as mock:
+        mock.side_effect = mockquant
         check_ocrmypdf(
             outdir / 'in.pdf',
             outdir / 'out.pdf',
@@ -155,6 +164,7 @@ def test_multiple_pngs(resources, outdir):
             '--plugin',
             'tests/plugins/tesseract_noop.py',
         )
+        mock.assert_called()
 
     with pikepdf.open(outdir / 'in.pdf') as inpdf, pikepdf.open(
         outdir / 'out.pdf'

tests/test_pdfinfo.py

@@ -15,7 +15,11 @@ from PIL import Image
 from reportlab.pdfgen.canvas import Canvas
 
 from ocrmypdf import pdfinfo
+from ocrmypdf.exceptions import InputFileError
 from ocrmypdf.pdfinfo import Colorspace, Encoding
+from ocrmypdf.pdfinfo.layout import PDFPage
+
+run_ocrmypdf_api = pytest.helpers.run_ocrmypdf_api
 
 # pylint: disable=protected-access
 
@@ -179,3 +183,18 @@ def test_stack_abuse():
     with pytest.warns(None):
         with pytest.raises(RuntimeError):
             pdfinfo.info._interpret_contents(stream)
+
+
+def test_pages_issue700(monkeypatch, resources):
+    def get_no_pages(*args, **kwargs):
+        return iter([])
+
+    monkeypatch.setattr(PDFPage, 'get_pages', get_no_pages)
+
+    with pytest.raises(InputFileError, match="pdfminer"):
+        pdfinfo.PdfInfo(
+            resources / 'cardinal.pdf',
+            detailed_analysis=True,
+            progbar=False,
+            max_workers=1,
+        )

tests/test_unpaper.py

@@ -28,11 +28,12 @@ def test_no_unpaper(resources, no_outpdf):
     output = fspath(no_outpdf)
 
     _parser, options, pm = get_parser_options_plugins(["--clean", input_, output])
-    with patch("ocrmypdf._exec.unpaper.version") as mock_unpaper_version:
+    with patch("ocrmypdf._exec.unpaper.version") as mock:
-        mock_unpaper_version.side_effect = FileNotFoundError("unpaper")
+        mock.side_effect = FileNotFoundError("unpaper")
 
         with pytest.raises(MissingDependencyError):
             check_options(options, pm)
+        mock.assert_called()
 
 
 def test_old_unpaper(resources, no_outpdf):
@@ -40,11 +41,12 @@ def test_old_unpaper(resources, no_outpdf):
     output = fspath(no_outpdf)
 
     _parser, options, pm = get_parser_options_plugins(["--clean", input_, output])
-    with patch("ocrmypdf._exec.unpaper.version") as mock_unpaper_version:
+    with patch("ocrmypdf._exec.unpaper.version") as mock:
-        mock_unpaper_version.return_value = '0.5'
+        mock.return_value = '0.5'
 
         with pytest.raises(MissingDependencyError):
             check_options(options, pm)
+        mock.assert_called()
 
 
 @pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")

tests/test_validation.py

@@ -188,18 +188,20 @@ def test_language_warning(caplog):
     caplog.set_level(logging.DEBUG)
     with patch(
         'ocrmypdf._validation.locale.getlocale', return_value=('en_US', 'UTF-8')
-    ):
+    ) as mock:
         vd.check_options_languages(opts, {'eng'})
         assert opts.languages == {'eng'}
         assert '' in caplog.text
+        mock.assert_called_once()
 
     opts = make_opts(language=None)
     with patch(
         'ocrmypdf._validation.locale.getlocale', return_value=('fr_FR', 'UTF-8')
-    ):
+    ) as mock:
         vd.check_options_languages(opts, {'eng'})
         assert opts.languages == {'eng'}
         assert 'assuming --language' in caplog.text
+        mock.assert_called_once()
 
 
 def test_version_comparison():
@@ -265,7 +267,8 @@ def test_pagesegmode_warning(caplog):
 
 
 def test_two_languages():
-    with patch('ocrmypdf._exec.tesseract.has_textonly_pdf', return_value=True):
+    with patch('ocrmypdf._exec.tesseract.has_textonly_pdf', return_value=True) as mock:
         vd._check_options(
             *make_opts_pm(language='fakelang1+fakelang2'), {'fakelang1', 'fakelang2'}
         )
+        mock.assert_called()