v11.4.4 release notes

Our method of getting data from pdfminer would silently consume a StopIteration
if pdfminer returned no processed pages, leading to odd error message.

We improve an error from pdfminer properly, and returning a more
descriptive error of our own.

It would be possible for ocrmypdf to repair the file before sending it to
pdfminer, but this seems to be rare enough that we won't do that yet.

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/advanced.rst

@@ -314,7 +314,7 @@ message is:
 .. code-block:: none
 
     Temporary working files retained at:
-    /tmp/com.github.ocrmypdf.u20wpz07
+    /tmp/ocrmypdf.io.u20wpz07
 
 The organization of this folder is an implementation detail and subject
 to change between releases. However the general organization is that

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 +12,38 @@ 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.
 
+v11.4.4
+=======
+
+-  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
+=======
+
+-  Fixed support for Cygwin, hopefully.
+-  watcher.py: Fixed an issue with the OCR_LOGLEVEL not being interpreted.
+
+v11.4.1
+=======
+
+-  Fixed an issue where invalid pages ranges passed using the ``pages`` argument,
+   such as "1-0" would cause unhandled exceptions.
+-  Accepted a user-contributed to the Synology demo script in misc/synology.py.
+-  Clarified documentation about change of temporary file location ``ocrmypdf.io``.
+-  Fixed Python wheel tag which was incorrectly set to py35 even though we long
+   since dropped support for Python 3.5.
+
 v11.4.0
 =======
 

misc/synology.py

@@ -79,8 +79,10 @@ for dir_name, subdirs, file_list in os.walk(start_dir):
                 stdout=output_file,
                 stderr=subprocess.PIPE,
                 check=False,
+                text=True,
+                errors='ignore',
             )
-        logging.info(proc.stderr.read())
+        logging.info(proc.stderr)
         os.chmod(full_path_ocr, 0o664)
         os.chmod(full_path, 0o664)
         full_path_ocr_archive = sys.argv[2]

misc/watcher.py

@@ -44,7 +44,7 @@ DESKEW = bool(os.getenv('OCR_DESKEW', ''))
 OCR_JSON_SETTINGS = json.loads(os.getenv('OCR_JSON_SETTINGS', '{}'))
 POLL_NEW_FILE_SECONDS = int(os.getenv('OCR_POLL_NEW_FILE_SECONDS', '1'))
 USE_POLLING = bool(os.getenv('OCR_USE_POLLING', ''))
-LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO').upper()
+LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO')
 PATTERNS = ['*.pdf', '*.PDF']
 
 log = logging.getLogger('ocrmypdf-watcher')
@@ -117,7 +117,12 @@ class HandleObserverEvent(PatternMatchingEventHandler):
 
 def main():
     ocrmypdf.configure_logging(
-        verbosity=ocrmypdf.Verbosity.default, manage_root_logger=True
+        verbosity=(
+            ocrmypdf.Verbosity.default
+            if LOGLEVEL != 'DEBUG'
+            else ocrmypdf.Verbosity.debug
+        ),
+        manage_root_logger=True,
     )
     log.setLevel(LOGLEVEL)
     log.info(
@@ -135,7 +140,7 @@ def main():
         f"ARGS: {OCR_JSON_SETTINGS}\n"
         f"POLL_NEW_FILE_SECONDS: {POLL_NEW_FILE_SECONDS}\n"
         f"USE_POLLING: {USE_POLLING}\n"
-        f"LOGLEVEL: {LOGLEVEL}\n"
+        f"LOGLEVEL: {LOGLEVEL}"
     )
 
     if 'input_file' in OCR_JSON_SETTINGS or 'output_file' in OCR_JSON_SETTINGS:

setup.cfg

@@ -1,5 +1,5 @@
 [bdist_wheel]
-python-tag = py35
+python-tag = py36
 
 [aliases]
 test=pytest

setup.py

@@ -82,7 +82,7 @@ setup(
     ],
     tests_require=tests_require,
     entry_points={'console_scripts': ['ocrmypdf = ocrmypdf.__main__:run']},
-    package_data={'ocrmypdf': ['data/sRGB.icc']},
+    package_data={'ocrmypdf': ['data/sRGB.icc', 'py.typed']},
     include_package_data=True,
     zip_safe=False,
     project_urls={

src/ocrmypdf/_concurrent.py

@@ -12,6 +12,7 @@ import os
 import signal
 import sys
 import threading
+from contextlib import suppress
 from multiprocessing import Pool as ProcessPool
 from multiprocessing.dummy import Pool as ThreadPool
 from typing import Callable, Iterable, Optional
@@ -56,7 +57,7 @@ def process_init(queue, user_init, loglevel):
     signal.signal(signal.SIGINT, signal.SIG_IGN)
 
     # Install SIGBUS handler (so our parent process can abort somewhat gracefully)
-    if hasattr(signal, 'SIGBUS'):
+    with suppress(AttributeError):  # Windows and Cygwin do not have SIGBUS
         signal.signal(signal.SIGBUS, process_sigbus)
 
     # Reconfigure the root logger for this process to send all messages to a queue
@@ -72,7 +73,8 @@ def process_init(queue, user_init, loglevel):
 
 def thread_init(_queue, user_init, _loglevel):
     # As a thread, block SIGBUS so the main thread deals with it...
-    if hasattr(signal, 'SIGBUS'):
+    with suppress(AttributeError):
+        # Windows and Cygwin do not have pthread_sigmask or SIGBUS
         signal.pthread_sigmask(signal.SIG_BLOCK, {signal.SIGBUS})
     if user_init:
         user_init()
@@ -107,15 +109,11 @@ def exec_progress_pool(
         )
         try:
             results = pool.imap_unordered(task, task_arguments)
-            while True:
-                try:
-                    result = results.next()
-                    if task_finished:
-                        task_finished(result, pbar)
-                    else:
-                        pbar.update()
-                except StopIteration:
-                    break
+            for result in results:
+                if task_finished:
+                    task_finished(result, pbar)
+                else:
+                    pbar.update()
         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

@@ -150,7 +150,7 @@ def get_pdfinfo(
     progbar=False,
     max_workers=None,
     check_pages=None,
-):
+) -> PdfInfo:
     try:
         return PdfInfo(
             input_file,
@@ -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.
-            # Reverse this, because PDF/A TechNote 0003:Metadata in PDF/A-1
-            # and the XMP Spec do not make this recommendation.
-            if meta.get('dc:title') == 'Untitled':
-                with original.open_metadata(
-                    set_pikepdf_as_editor=False, update_docinfo=False
-                ) as original_meta:
-                    if 'dc:title' not in original_meta:
+            with original.open_metadata(
+                set_pikepdf_as_editor=False, update_docinfo=False, strict=False
+            ) as meta_original:
+                if meta.get('dc:title') == 'Untitled':
+                    # Ghostscript likes to set title to Untitled if omitted from input.
+                    # Reverse this, because PDF/A TechNote 0003:Metadata in PDF/A-1
+                    # and the XMP Spec do not make this recommendation.
+                    if 'dc:title' not in meta_original:
                         del meta['dc:title']
-
-            meta_original = original.open_metadata()
-            missing = set(meta_original.keys()) - set(meta.keys())
-            report_on_metadata(missing)
+                missing = set(meta_original.keys()) - set(meta.keys())
+                report_on_metadata(missing)
 
         pdf.save(
             output_file,

src/ocrmypdf/_validation.py

@@ -13,7 +13,7 @@ import sys
 import unicodedata
 from pathlib import Path
 from shutil import copyfileobj
-from typing import Tuple
+from typing import List, Set, Tuple, Union
 
 import pikepdf
 import PIL
@@ -136,10 +136,10 @@ def check_options_preprocessing(options):
             raise BadArgsError(str(e))
 
 
-def _pages_from_ranges(ranges):
+def _pages_from_ranges(ranges: str) -> Set[int]:
     if is_iterable_notstr(ranges):
         return set(ranges)
-    pages = []
+    pages: List[int] = []
     page_groups = ranges.replace(' ', '').split(',')
     for g in page_groups:
         if not g:
@@ -150,9 +150,18 @@ def _pages_from_ranges(ranges):
             pages.append(int(g) - 1)
         else:
             try:
-                pages.extend(range(int(start) - 1, int(end)))
+                new_pages = list(range(int(start) - 1, int(end)))
+                if not new_pages:
+                    raise BadArgsError(f"invalid page subrange '{start}-{end}'")
+                pages.extend(new_pages)
             except ValueError:
-                raise BadArgsError("invalid page range")
+                raise BadArgsError("invalid page range") from None
+
+    if not pages:
+        raise BadArgsError(
+            f"The string of page ranges '{ranges}' did not contain any recognizable "
+            f"page ranges."
+        )
 
     if not monotonic(pages):
         log.warning(

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:
-        warn("ocrmypdf.ocr(verbose=) is ignored. Use ocrmypdf.configure_logging().")
+    with _api_lock:
+        # 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)
-    check_options(options, plugin_manager)
-    return run_pipeline(options=options, plugin_manager=plugin_manager, api=True)
+        plugin_manager = get_plugin_manager(plugins)
+        plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
+
+        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/pdfinfo/info.py

@@ -15,14 +15,14 @@ from functools import partial
 from math import hypot, isclose
 from os import PathLike
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Container, Dict, Iterator, List, Optional, Tuple, Union
 from warnings import warn
 
 import pikepdf
-from pikepdf import PdfMatrix
+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
 
@@ -115,7 +115,7 @@ def _normalize_stack(graphobjs):
             yield (operands, operator)
 
 
-def _interpret_contents(contentstream, initial_shorthand=UNIT_SQUARE):
+def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
     """Interpret the PDF content stream.
 
     The stack represents the state of the PDF graphics stack.  We are only
@@ -204,7 +204,7 @@ def _interpret_contents(contentstream, initial_shorthand=UNIT_SQUARE):
     )
 
 
-def _get_dpi(ctm_shorthand, image_size):
+def _get_dpi(ctm_shorthand, image_size) -> Resolution:
     """Given the transformation matrix and image size, find the image DPI.
 
     PDFs do not include image resolution information within image data.
@@ -271,8 +271,14 @@ def _get_dpi(ctm_shorthand, image_size):
 class ImageInfo:
     DPI_PREC = Decimal('1.000')
 
-    def __init__(self, *, name='', pdfimage=None, inline=None, shorthand=None):
-
+    def __init__(
+        self,
+        *,
+        name='',
+        pdfimage: Optional[Object] = None,
+        inline: Optional[Object] = None,
+        shorthand=None,
+    ):
         self._name = str(name)
         self._shorthand = shorthand
 
@@ -282,6 +288,8 @@ class ImageInfo:
         elif pdfimage is not None:
             self._origin = 'xobject'
             pim = pikepdf.PdfImage(pdfimage)
+        else:
+            raise ValueError("Either pdfimage or inline must be set")
         self._width = pim.width
         self._height = pim.height
 
@@ -371,7 +379,7 @@ class ImageInfo:
         ).format(**class_locals)
 
 
-def _find_inline_images(contentsinfo):
+def _find_inline_images(contentsinfo: ContentsInfo) -> Iterator[ImageInfo]:
     "Find inline images in the contentstream"
 
     for n, inline in enumerate(contentsinfo.inline_images):
@@ -380,7 +388,7 @@ def _find_inline_images(contentsinfo):
         )
 
 
-def _image_xobjects(container):
+def _image_xobjects(container) -> Iterator[Tuple[Object, str]]:
     """Search for all XObject-based images in the container
 
     Usually the container is a page, but it could also be a Form XObject
@@ -400,7 +408,7 @@ def _image_xobjects(container):
         return
     xobjs = resources['/XObject'].as_dict()
     for xobj in xobjs:
-        candidate = xobjs[xobj]
+        candidate: Object = xobjs[xobj]
         if not '/Subtype' in candidate:
             continue
         if candidate['/Subtype'] == '/Image':
@@ -408,7 +416,9 @@ def _image_xobjects(container):
             yield (pdfimage, xobj)
 
 
-def _find_regular_images(container, contentsinfo):
+def _find_regular_images(
+    container: Object, contentsinfo: ContentsInfo
+) -> Iterator[ImageInfo]:
     """Find images stored in the container's /Resources /XObject
 
     Usually the container is a page, but it could also be a Form XObject
@@ -432,7 +442,7 @@ def _find_regular_images(container, contentsinfo):
             yield ImageInfo(name=draw.name, pdfimage=pdfimage, shorthand=draw.shorthand)
 
 
-def _find_form_xobject_images(pdf, container, contentsinfo):
+def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: ContentsInfo):
     """Find any images that are in Form XObjects in the container
 
     The container may be a page, or a parent Form XObject.
@@ -464,7 +474,9 @@ def _find_form_xobject_images(pdf, container, contentsinfo):
             )
 
 
-def _process_content_streams(*, pdf, container, shorthand=None):
+def _process_content_streams(
+    *, pdf: Pdf, container: Object, shorthand=None
+) -> Iterator[Union[VectorMarker, TextMarker, ImageInfo]]:
     """Find all individual instances of images drawn in the container
 
     Usually the container is a page, but it may also be a Form XObject.
@@ -526,7 +538,7 @@ def _page_has_text(text_blocks, page_width, page_height) -> bool:
         margin_ratio * ph,  # bottom  (first quadrant: bottom < top)
     )
 
-    def rects_intersect(a, b):
+    def rects_intersect(a, b) -> bool:
         """
         Where (a,b) are 4-tuple rects (left-0, top-1, right-2, bottom-3)
         https://stackoverflow.com/questions/306316/determine-if-two-rectangles-overlap-each-other
@@ -542,7 +554,7 @@ def _page_has_text(text_blocks, page_width, page_height) -> bool:
     return has_text
 
 
-def simplify_textboxes(miner, textbox_getter):
+def simplify_textboxes(miner, textbox_getter) -> Iterator[TextboxInfo]:
     """Extract only limited content from text boxes
 
     We do this to save memory and ensure that our objects are pickleable.
@@ -556,74 +568,6 @@ def simplify_textboxes(miner, textbox_getter):
         yield TextboxInfo(box.bbox, visible, corrupt)
 
 
-def _pdf_get_pageinfo(
-    pdf, pageno: int, infile: PathLike, check_pages, detailed_analysis: bool
-):
-    pageinfo: Dict[str, Any] = {}
-    pageinfo['pageno'] = pageno
-    pageinfo['images'] = []
-
-    page = pdf.pages[pageno]
-    mediabox = [Decimal(d) for d in page.MediaBox.as_list()]
-    width_pt = mediabox[2] - mediabox[0]
-    height_pt = mediabox[3] - mediabox[1]
-
-    check_this_page = pageno in check_pages
-
-    if check_this_page and detailed_analysis:
-        pscript5_mode = str(pdf.docinfo.get('/Creator')).startswith('PScript5')
-        miner = get_page_analysis(infile, pageno, pscript5_mode)
-        pageinfo['textboxes'] = list(simplify_textboxes(miner, get_text_boxes))
-        bboxes = (box.bbox for box in pageinfo['textboxes'])
-
-        pageinfo['has_text'] = _page_has_text(bboxes, width_pt, height_pt)
-    else:
-        pageinfo['textboxes'] = []
-        pageinfo['has_text'] = None  # i.e. "no information"
-
-    userunit = page.get('/UserUnit', Decimal(1.0))
-    if not isinstance(userunit, Decimal):
-        userunit = Decimal(userunit)
-    pageinfo['userunit'] = userunit
-    pageinfo['width_inches'] = width_pt * userunit / Decimal(72.0)
-    pageinfo['height_inches'] = height_pt * userunit / Decimal(72.0)
-
-    try:
-        pageinfo['rotate'] = int(page['/Rotate'])
-    except KeyError:
-        pageinfo['rotate'] = 0
-
-    userunit_shorthand = (userunit, 0, 0, userunit, 0, 0)
-
-    if check_this_page:
-        pageinfo['has_vector'] = False
-        pageinfo['has_text'] = False
-        pageinfo['images'] = []
-        for ci in _process_content_streams(
-            pdf=pdf, container=page, shorthand=userunit_shorthand
-        ):
-            if isinstance(ci, VectorMarker):
-                pageinfo['has_vector'] = True
-            elif isinstance(ci, TextMarker):
-                pageinfo['has_text'] = True
-            elif isinstance(ci, ImageInfo):
-                pageinfo['images'].append(ci)
-            else:
-                raise NotImplementedError()
-    else:
-        pageinfo['has_vector'] = None  # i.e. "no information"
-        pageinfo['has_text'] = None
-        pageinfo['images'] = None
-
-    if pageinfo['images']:
-        dpi = Resolution(0.0, 0.0).take_max(image.dpi for image in pageinfo['images'])
-        pageinfo['dpi'] = dpi
-        pageinfo['width_pixels'] = int(round(dpi.x * float(pageinfo['width_inches'])))
-        pageinfo['height_pixels'] = int(round(dpi.y * float(pageinfo['height_inches'])))
-
-    return pageinfo
-
-
 worker_pdf = None
 
 
@@ -654,6 +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()
 
@@ -693,13 +639,85 @@ def _pdf_pageinfo_concurrent(
 
 
 class PageInfo:
-    def __init__(self, pdf, pageno, infile, check_pages, detailed_analysis=False):
+    def __init__(
+        self,
+        pdf: Pdf,
+        pageno: int,
+        infile: PathLike,
+        check_pages: Container[int],
+        detailed_analysis: bool = False,
+    ):
         self._pageno = pageno
         self._infile = infile
         self._detailed_analysis = detailed_analysis
-        self._pageinfo = _pdf_get_pageinfo(
-            pdf, pageno, infile, check_pages, detailed_analysis
-        )
+        self._gather_pageinfo(pdf, pageno, infile, check_pages, detailed_analysis)
+
+    def _gather_pageinfo(
+        self,
+        pdf: Pdf,
+        pageno: int,
+        infile: PathLike,
+        check_pages: Container[int],
+        detailed_analysis: bool,
+    ):
+        page = pdf.pages[pageno]
+        mediabox = [Decimal(d) for d in page.MediaBox.as_list()]
+        width_pt = mediabox[2] - mediabox[0]
+        height_pt = mediabox[3] - mediabox[1]
+
+        check_this_page = pageno in check_pages
+
+        if check_this_page and detailed_analysis:
+            pscript5_mode = str(pdf.docinfo.get('/Creator')).startswith('PScript5')
+            miner = get_page_analysis(infile, pageno, pscript5_mode)
+            self._textboxes = list(simplify_textboxes(miner, get_text_boxes))
+            bboxes = (box.bbox for box in self._textboxes)
+
+            self._has_text = _page_has_text(bboxes, width_pt, height_pt)
+        else:
+            self._textboxes = []
+            self._has_text = None  # i.e. "no information"
+
+        userunit = page.get('/UserUnit', Decimal(1.0))
+        if not isinstance(userunit, Decimal):
+            userunit = Decimal(userunit)
+        self._userunit = userunit
+        self._width_inches = width_pt * userunit / Decimal(72.0)
+        self._height_inches = height_pt * userunit / Decimal(72.0)
+
+        try:
+            self._rotate = int(page['/Rotate'])
+        except KeyError:
+            self._rotate = 0
+
+        userunit_shorthand = (userunit, 0, 0, userunit, 0, 0)
+
+        if check_this_page:
+            self._has_vector = False
+            self._has_text = False
+            self._images = []
+            for ci in _process_content_streams(
+                pdf=pdf, container=page, shorthand=userunit_shorthand
+            ):
+                if isinstance(ci, VectorMarker):
+                    self._has_vector = True
+                elif isinstance(ci, TextMarker):
+                    self._has_text = True
+                elif isinstance(ci, ImageInfo):
+                    self._images.append(ci)
+                else:
+                    raise NotImplementedError()
+        else:
+            self._has_vector = None  # i.e. "no information"
+            self._has_text = None
+            self._images = None
+
+        self._dpi = None
+        if self._images:
+            dpi = Resolution(0.0, 0.0).take_max(image.dpi for image in self._images)
+            self._dpi = dpi
+            self._width_pixels = int(round(dpi.x * float(self._width_inches)))
+            self._height_pixels = int(round(dpi.y * float(self._height_inches)))
 
     @property
     def pageno(self) -> int:
@@ -707,25 +725,25 @@ class PageInfo:
 
     @property
     def has_text(self) -> bool:
-        return self._pageinfo['has_text']
+        return self._has_text
 
     @property
     def has_corrupt_text(self) -> bool:
         if not self._detailed_analysis:
             raise NotImplementedError('Did not do detailed analysis')
-        return any(tbox.is_corrupt for tbox in self._pageinfo['textboxes'])
+        return any(tbox.is_corrupt for tbox in self._textboxes)
 
     @property
     def has_vector(self) -> bool:
-        return self._pageinfo['has_vector']
+        return self._has_vector
 
     @property
     def width_inches(self) -> Decimal:
-        return self._pageinfo['width_inches']
+        return self._width_inches
 
     @property
     def height_inches(self) -> Decimal:
-        return self._pageinfo['height_inches']
+        return self._height_inches
 
     @property
     def width_pixels(self) -> int:
@@ -737,18 +755,18 @@ class PageInfo:
 
     @property
     def rotation(self) -> int:
-        return self._pageinfo.get('rotate', None)
+        return self._rotate
 
     @rotation.setter
     def rotation(self, value):
         if value in (0, 90, 180, 270, 360, -90, -180, -270):
-            self._pageinfo['rotate'] = value
+            self._rotate = value
         else:
             raise ValueError("rotation must be a cardinal angle")
 
     @property
     def images(self):
-        return self._pageinfo['images']
+        return self._images
 
     def get_textareas(
         self, visible: Optional[bool] = None, corrupt: Optional[bool] = None
@@ -763,24 +781,22 @@ class PageInfo:
                     result = False
             return result
 
-        if 'textboxes' not in self._pageinfo:
+        if not self._textboxes:
             if visible is not None and corrupt is not None:
                 raise NotImplementedError('Incomplete information on textboxes')
-            return self._pageinfo['bboxes']
+            return self._textboxes
 
-        return (
-            obj.bbox
-            for obj in self._pageinfo['textboxes']
-            if predicate(obj, visible, corrupt)
-        )
+        return (obj.bbox for obj in self._textboxes if predicate(obj, visible, corrupt))
 
     @property
     def dpi(self) -> Resolution:
-        return self._pageinfo.get('dpi', Resolution(0.0, 0.0))
+        if self._dpi is None:
+            return Resolution(0.0, 0.0)
+        return self._dpi
 
     @property
     def userunit(self) -> Decimal:
-        return self._pageinfo.get('userunit', None)
+        return self._userunit
 
     @property
     def min_version(self) -> str:

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]+')
 
@@ -223,6 +223,7 @@ def get_page_analysis(infile, pageno, pscript5_mode):
     )
     interp = pdfminer.pdfinterp.PDFPageInterpreter(rman, dev)
 
+    patcher = None
     if pscript5_mode:
         patcher = patch.multiple(
             'pdfminer.pdffont.PDFType3Font',
@@ -235,12 +236,17 @@ 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)
-            interp.process_page(next(page))
-    except PDFTextExtractionNotAllowed:
-        raise EncryptedPdfError()
+            page_iter = PDFPage.get_pages(f, pagenos=[pageno], maxpages=0)
+            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:
-        if pscript5_mode:
+        if patcher is not None:
             patcher.stop()
 
     return dev.get_result()

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.stderr = b'\n'.join([proc.stderr, elision_warning.encode('utf-8')])
+    proc = run_polling_stderr(*args, **kwargs)
+    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_main.py

@@ -92,10 +92,10 @@ def test_skip_ocr(resources, outpdf):
 
 def test_redo_ocr(resources, outpdf):
     in_ = resources / 'graph_ocred.pdf'
-    before = PdfInfo(in_)
+    before = PdfInfo(in_, detailed_analysis=True)
     out = outpdf
     out = check_ocrmypdf(in_, out, '--redo-ocr')
-    after = PdfInfo(out)
+    after = PdfInfo(out, detailed_analysis=True)
     assert before[0].has_text and after[0].has_text
     assert (
         before[0].get_textareas() != after[0].get_textareas()

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(
-    not jbig2enc.available() or not pngquant.available(),
-    reason='need jbig2enc and pngquant',
-)
+@needs_pngquant
+@needs_jbig2enc
 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_page_numbers.py

@@ -28,6 +28,12 @@ from ocrmypdf.pdfinfo import PdfInfo
         ['1,3,-11', BadArgsError],
         ['1-,', BadArgsError],
         ['start-end', BadArgsError],
+        ['1-0', BadArgsError],
+        ['99-98', BadArgsError],
+        ['0-0', BadArgsError],
+        ['1-0,3-4', BadArgsError],
+        [',', BadArgsError],
+        ['', BadArgsError],
     ],
 )
 def test_pages(pages, result):

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:
-        mock_unpaper_version.side_effect = FileNotFoundError("unpaper")
+    with patch("ocrmypdf._exec.unpaper.version") as mock:
+        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:
-        mock_unpaper_version.return_value = '0.5'
+    with patch("ocrmypdf._exec.unpaper.version") as mock:
+        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()