Update completions

Closes #469

.docker/Dockerfile

@@ -39,6 +39,7 @@ RUN pip3 install --no-cache-dir \
   -r requirements/main.txt \
   -r requirements/webservice.txt \
   -r requirements/test.txt \
+  -r requirements/watcher.txt \
   .
 
 FROM base
@@ -69,6 +70,7 @@ COPY --from=builder /usr/local/lib/ /usr/local/lib/
 COPY --from=builder /usr/local/bin/ /usr/local/bin/
 
 COPY --from=builder /app/misc/webservice.py /app/
+COPY --from=builder /app/misc/watcher.py /app/
 
 # Copy minimal project files to get the test suite.
 COPY --from=builder /app/setup.cfg /app/setup.py /app/README.md /app/

.pre-commit-config.yaml

@@ -1,10 +1,4 @@
 repos:
-  - repo: https://github.com/psf/black
-    rev: stable
-    hooks:
-      - id: black
-        language_version: python3.7
-        exclude: ^src/ocrmypdf/lib/_leptonica.py
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v2.4.0
     hooks:
@@ -13,5 +7,17 @@ repos:
       - id: check-toml
       - id: check-yaml
       - id: debug-statements
-      - id: name-tests-test
-        args: ["--django"]
+  - repo: https://github.com/asottile/seed-isort-config
+    rev: v1.9.3
+    hooks:
+      - id: seed-isort-config
+  - repo: https://github.com/pre-commit/mirrors-isort
+    rev: v4.3.21 # pick the isort version you'd like to use from https://github.com/pre-commit/mirrors-isort/releases
+    hooks:
+      - id: isort
+  - repo: https://github.com/psf/black
+    rev: stable
+    hooks:
+      - id: black
+        language_version: python3.7
+        exclude: ^src/ocrmypdf/lib/_leptonica.py

README.md

@@ -79,7 +79,7 @@ and users of Fedora 29 or later may simply
 dnf install ocrmypdf
 ```
 
-and macOS users with Homebrew may simply
+and Homebrew users (macOS, Linux, Windows Subsystem for Linux) may simply
 
 ```bash
 brew install ocrmypdf
@@ -113,18 +113,12 @@ ocrmypdf --help
 
 Our [documentation is served on Read the Docs](https://ocrmypdf.readthedocs.io/en/latest/index.html).
 
-If you detect an issue, please:
-
-- Check whether your issue is already known
-- If no problem report exists on github, please create one here: <https://github.com/jbarlow83/OCRmyPDF/issues>
-- Describe your problem thoroughly
-- Append the console output of the script when running the debug mode (`-v 1` option)
-- If possible provide your input PDF file as well as the content of the temporary folder (using a file sharing service like Dropbox)
+Please report issues on our [GitHub issues](https://github.com/jbarlow83/OCRmyPDF/issues) page, and follow the issue template for quick response.
 
 Requirements
 ------------
 
-In addition to the required Python version (3.6+), OCRmyPDF requires external program installations of Ghostscript, Tesseract OCR, QPDF, and Leptonica. ocrmypdf is pure Python, but uses CFFI to portably generate library bindings.
+In addition to the required Python version (3.6+), OCRmyPDF requires external program installations of Ghostscript, Tesseract OCR, QPDF, and Leptonica. ocrmypdf is pure Python, but uses CFFI to portably generate library bindings. OCRmyPDF works on pretty much  everything: Linux, macOS, Windows and FreeBSD.
 
 Press & Media
 -------------

azure-pipelines.yml

@@ -34,27 +34,20 @@ stages:
             displayName: "Install system packages"
           - pwsh: |
               refreshenv
-              $env:path = "C:\Program Files\Tesseract-OCR;C:\Program Files\gs\gs9.50\bin;" + $env:path
-              pip install --upgrade pip wheel
-              pip install -r requirements/main.txt -r requirements/test.txt .
-              tesseract --version
+              python -m pip install --upgrade pip wheel
+              python -m pip install -r requirements/main.txt -r requirements/test.txt .
             displayName: "Install Python packages"
           - pwsh: |
               refreshenv
-              $env:path = "C:\Program Files\Tesseract-OCR;C:\Program Files\gs\gs9.50\bin;" + $env:path
               $env:pathext += ';.py'
               # -n auto helps Windows
-              pytest -n auto --junitxml=test.xml --cov=ocrmypdf --cov-report=xml
+              python -m pytest -n auto --junitxml=test.xml --cov=ocrmypdf --cov-report=xml
             displayName: "Test"
           - task: PublishTestResults@2
             inputs:
               testResultsFiles: "test.xml"
               testRunTitle: "$(Agent.OS) - $(Build.DefinitionName) - Python $(python.version)"
             condition: succeededOrFailed()
-          - task: PublishCodeCoverageResults@1
-            inputs:
-              codeCoverageTool: Cobertura
-              summaryFileLocation: "$(System.DefaultWorkingDirectory)/**/coverage.xml"
       - job: "Ubuntu_1804"
         pool:
           vmImage: "ubuntu-18.04"
@@ -105,10 +98,6 @@ stages:
               testResultsFiles: "test.xml"
               testRunTitle: "$(Agent.OS) - $(Build.DefinitionName) - Python $(python.version)"
             condition: succeededOrFailed()
-          - task: PublishCodeCoverageResults@1
-            inputs:
-              codeCoverageTool: Cobertura
-              summaryFileLocation: "$(System.DefaultWorkingDirectory)/**/coverage.xml"
       - job: "Ubuntu_1604"
         pool:
           vmImage: "ubuntu-16.04"
@@ -157,10 +146,6 @@ stages:
               testResultsFiles: "test.xml"
               testRunTitle: "$(Agent.OS) - $(Build.DefinitionName) - Python $(python.version)"
             condition: succeededOrFailed()
-          - task: PublishCodeCoverageResults@1
-            inputs:
-              codeCoverageTool: Cobertura
-              summaryFileLocation: "$(System.DefaultWorkingDirectory)/**/coverage.xml"
       - job: "macOS_Mojave"
         pool:
           vmImage: "macos-10.14"
@@ -176,6 +161,7 @@ stages:
               versionSpec: "$(python.version)"
           - bash: |
               brew update
+              brew unlink python@2
               brew install \
                 exempi \
                 ghostscript \

docs/batch.rst

@@ -198,6 +198,54 @@ and all inquiries are appreciated.
 Hot (watched) folders
 =====================
 
+Watched folders with Docker
+---------------------------
+
+The OCRmyPDF Docker image includes a watcher service. This service can
+be launched as follows:
+
+.. code-block:: bash
+
+    docker run \
+        -v <path to files to convert>:/input \
+        -v <path to store results>:/output \
+        -e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
+        -it --entrypoint python3 \
+        jbarlow83/ocrmypdf \
+        watcher.py
+
+This service will watch for a file that matches ``/input/\*.pdf`` and will
+convert it to a OCRed PDF in ``/output/``. The parameters to this image are:
+
+.. csv-table:: watcher.py parameters for Docker
+    :header: "Parameter", "Description"
+    :widths: 50, 50
+
+    "``-v <path to files to convert>:/input``", "Files placed in this location will be OCRed"
+    "``-v <path to store results>:/output``", "This is where OCRed files will be stored"
+    "``-e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "This will place files in the output in {output}/{year}/{month}/{filename}"
+
+This service relies on polling to check for changes to the filesystem. It
+may not be suitable for some environments, such as filesystems shared on a
+slow network.
+
+Watched folders with watcher.py
+-------------------------------
+
+The watcher service may also be run natively.
+
+.. code-block:: bash
+
+    pip3 install -r reqs/watcher.txt
+
+    env OCR_INPUT_DIRECTORY=/mnt/input-pdfs \
+        OCR_OUTPUT_DIRECTORY=/mnt/output-pdfs \
+        OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
+        python3 watcher.py
+
+Watched folders with CLI
+------------------------
+
 To set up a "hot folder" that will trigger OCR for every file inserted,
 use a program like Python
 `watchdog <https://pypi.python.org/pypi/watchdog>`__ (supports all major
@@ -225,12 +273,12 @@ told to run ``ocrmypdf`` on any .pdf added to the current directory
        --command='ocrmypdf "${watch_src_path}" "out/${watch_src_path}" ' \
        .  # don't forget the final dot
 
-For more complex behavior you can write a Python script around to use
-the watchdog API.
-
 On file servers, you could configure watchmedo as a system service so it
 will run all the time.
 
+For more complex behavior you can write a Python script around to use
+the watchdog API. You can refer to the watcher.py script as an example.
+
 Caveats
 -------
 
@@ -250,7 +298,7 @@ Caveats
 Alternatives
 ------------
 
--  `systemd user services <https://wiki.archlinux.org/index.php/Systemd/User>`__
+-  On Linux, `systemd user services <https://wiki.archlinux.org/index.php/Systemd/User>`__
    can be configured to automatically perform OCR on a collection of files.
 
 -  `Watchman <https://facebook.github.io/watchman/>`__ is a more

docs/contributing.rst

@@ -15,7 +15,10 @@ Code style
 ==========
 
 We use PEP8, ``black`` for code formatting and ``isort`` for import sorting. The
-settings for programs are in ``pyproject.toml`` and ``setup.cfg``.
+settings for these programs are in ``pyproject.toml`` and ``setup.cfg``. Pull
+requests should follow the style guide. One difference we use from "black" style
+is that strings shown to the user are always in double quotes (``"``) and strings
+for internal uses are in single quotes (``'``).
 
 Tests
 =====
@@ -36,3 +39,19 @@ New non-Python dependencies
 
 OCRmyPDF uses several external programs (Tesseract, Ghostscript and others) for
 its functionality. In general we prefer to avoid adding new external programs.
+
+Style guide: Is it OCRmyPDF or ocrmypdf?
+========================================
+
+The program/project is OCRmyPDF and the name of the executable or library is ocrmypdf.
+
+Known ports/packagers
+=====================
+
+OCRmyPDF has been ported to many platforms already. If you are interesting in
+porting to a new platform, check with
+`Repology <https://repology.org/projects/?search=ocrmypdf>`__ to see the status
+of that platform.
+
+Packager maintainers, please ensure that the command line completion scripts in
+``misc/`` are installed.

docs/installation.rst

@@ -8,11 +8,20 @@ Installing OCRmyPDF
 |latest|
 
 The easiest way to install OCRmyPDF is to follow the steps for your operating
-system/platform, although sometimes this version may be out of date.
+system/platform, although sometimes this version may be out of date. This
+installation guide provides information allowing you to compare the current
+version to the one provided by your platform.
 
-If you want to use the latest version of OCRmyPDF, your best bet is to install
-the most recent version your platform provides, and then upgrade that version by
-installing the Python binary wheels.
+If you want to use the latest version of OCRmyPDF and all of its optional
+dependencies, the easiest way to get that is install the Homebrew package. Homebrew
+is best known as a macOS package manger, but also works for
+`Linux and Windows Subsystem for Linux <https://docs.brew.sh/Homebrew-on-Linux>`__.
+After Homebrew is installed, simply run ``brew install ocrmypdf``.
+
+You can also use the more detailed procedures here to manually install OCRmyPDF
+from source or with the ``pip`` package manager for binary wheels. The reason
+for these varied steps is that OCRmyPDF requires third-party executables that are
+not part of Python.
 
 .. contents:: Platform-specific steps
     :depth: 2
@@ -55,8 +64,8 @@ Debian and Ubuntu 18.04 or newer
 | |ubu-1804| |ubu-1810| |ubu-1904| |ubu-1910|   |
 +-----------------------------------------------+
 
-Users of Debian 9 ("stretch") or later or Ubuntu 18.04 or later may
-simply
+Users of Debian 9 ("stretch") or later or Ubuntu 18.04 or later, including users
+of Windows Subsystem for Linux, may simply
 
 .. code-block:: bash
 
@@ -303,6 +312,19 @@ the following command.
 If you have any difficulties with installation, check the repository
 package page.
 
+Alpine Linux
+------------
+
+.. image:: https://repology.org/badge/version-for-repo/alpine_edge/ocrmypdf.svg
+    :alt: Alpine Linux
+    :target: https://repology.org/metapackage/ocrmypdf
+
+To install OCRmyPDF for Alpine Linux:
+
+.. code-block:: bash
+
+    apk add ocrmypdf
+
 Other Linux packages
 --------------------
 
@@ -380,7 +402,7 @@ packs. If you need other languages you can optionally install them all:
 
    .. code-block:: bash
 
-    brew install tesseract --with-all-languages  # Option 2: for all language packs
+    brew install tesseract-lang  # Option 2: for all language packs
 
 Update the homebrew pip:
 
@@ -427,8 +449,7 @@ Installing the Docker image
 ===========================
 
 For some users, installing the Docker image will be easier than
-installing all of OCRmyPDF's dependencies. For Windows, it is the only
-option.
+installing all of OCRmyPDF's dependencies.
 
 See `OCRmyPDF Docker Image <docker>`__ for more information.
 
@@ -448,7 +469,7 @@ Installing on Windows
 
 You must install the following for Windows:
 
-* Python 3.7 (64-bit recommended)
+* Python 3.7 (64-bit)
 * Tesseract 4.0 or later
 * Ghostscript 9.50 or later
 
@@ -463,11 +484,14 @@ Also consider adding:
 * ``choco install pngquant``
 
 Windows 10 64-bit and 64-bit versions of applications are recommended. Earlier
-versions of Windows and 32-bit versions of these programs are not tested.
+versions of Windows and 32-bit versions of these programs are not tested, and not
+supported at this time.
 
-Modify your ``PATH`` environment variable so that Tesseract and Ghostscript, and
-any optional executables can be found. You can enter it in the command line
-or `follow these directions <https://www.computerhope.com/issues/ch000549.htm#dospath>`_
+OCRmyPDF will check for Tesseract-OCR and Ghostscript in your Program Files folder.
+If they are in some other location, you may need to modify the ``PATH``
+environment variable so Tesseract, Ghostscript, and other any optional executables can
+be found. You can enter it in the command line or
+`follow these directions <https://www.computerhope.com/issues/ch000549.htm#dospath>`_
 to make the change persistent and system-wide.
 
 You may then use pip to install ocrmypdf:

docs/introduction.rst

@@ -2,7 +2,7 @@
 Introduction
 ============
 
-OCRmyPDF is a Python 3 package that adds OCR layers to PDFs.
+OCRmyPDF is a Python 3 application and library that adds OCR layers to PDFs.
 
 About OCR
 =========

docs/release_notes.rst

@@ -13,6 +13,19 @@ Note that it is licensed under GPLv3, so scripts that
 ``import ocrmypdf`` and are released publicly should probably also be
 licensed under GPLv3.
 
+v9.3.0
+======
+
+-  Improved native Windows support: we now check in the obvious places in
+   the "Program Files" folders installations of Tesseract and Ghostscript,
+   rather than relying on the user to edit ``PATH`` to specify their location.
+   The ``PATH`` environment variable can still be used to differentiate when
+   multiple installations are present or the programs are installed to non-
+   standard locations.
+-  Fixed an exception on parsing Ghostscript error messages.
+-  Added an improved example demonstrating how to set up a watched folder
+   for automated OCR processing (thanks to @ianalexander for the contribution).
+
 v9.2.0
 ======
 

misc/completion/ocrmypdf.bash

@@ -58,7 +58,7 @@ _ocrmypdf()
             COMPREPLY=( $( compgen -W '{1..13}' -- "$cur" ) )
             return
             ;;
-        --sidecar|--title|--author|--subject|--keywords|--unpaper-args|--pages)
+        --sidecar|--title|--author|--subject|--keywords|--unpaper-args|--pages|--fast-web-view)
             # argument required but no completions available
             return
             ;;
@@ -76,7 +76,8 @@ _ocrmypdf()
             --max-image-mpixels --tesseract-config --tesseract-pagesegmode
             --help --tesseract-oem --pdf-renderer --tesseract-timeout
             --rotate-pages-threshold --pdfa-image-compression --user-words
-            --user-patterns --keep-temporary-files --output-type' \
+            --user-patterns --keep-temporary-files --output-type
+            --no-progress-bar --pages --fast-web-view' \
             --  "$cur" ) )
         return
     else

misc/completion/ocrmypdf.fish

@@ -59,6 +59,8 @@ function __fish_ocrmypdf_verbose
 end
 complete -c ocrmypdf -x -s v -l verbose -a '(__fish_ocrmypdf_verbose)' -d "set verbosity level"
 
+complete -c ocrmypdf -x -l no-progress-bar -d "disable the progress bar"
+
 function __fish_ocrmypdf_pdfa_compression
     echo -e "auto\t"(_ "let Ghostscript decide how to compress images")
     echo -e "jpeg\t"(_ "convert color and grayscale images to JPEG")
@@ -111,5 +113,6 @@ complete -c ocrmypdf -x -l rotate-pages-threshold -d "page rotation confidence"
 
 complete -c ocrmypdf -r -l user-words -d "specify location of user words file"
 complete -c ocrmypdf -r -l user-patterns -d "specify location of user patterns file"
+complete -c ocrmypdf -x -l fast-web-view -d "if file size if above this amount in MB, linearize PDF"
 
 complete -c ocrmypdf -x -a "(__fish_complete_suffix .pdf)"

misc/watcher.py

@@ -0,0 +1,70 @@
+# Copyright (C) 2019 Ian Alexander: https://github.com/ianalexander
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+import os
+import time
+from datetime import datetime
+from pathlib import Path
+
+from watchdog.events import PatternMatchingEventHandler
+from watchdog.observers import Observer
+
+import ocrmypdf
+
+INPUT_DIRECTORY = os.getenv('OCR_INPUT_DIRECTORY', '/input')
+OUTPUT_DIRECTORY = os.getenv('OCR_OUTPUT_DIRECTORY', '/output')
+OUTPUT_DIRECTORY_YEAR_MONTH = bool(os.getenv('OCR_OUTPUT_DIRECTORY_YEAR_MONTH', False))
+PATTERNS = ['*.pdf']
+
+
+def execute_ocrmypdf(file_path):
+    filename = Path(file_path).name
+    if OUTPUT_DIRECTORY_YEAR_MONTH:
+        today = datetime.today()
+        output_directory_year_month = Path(
+            f'{OUTPUT_DIRECTORY}/{today.year}/{today.month}'
+        )
+        if not output_directory_year_month.exists():
+            output_directory_year_month.mkdir(parents=True, exist_ok=True)
+        output_path = Path(output_directory_year_month) / filename
+    else:
+        output_path = Path(OUTPUT_DIRECTORY) / filename
+    print(f'New file: {file_path}.\nAttempting to OCRmyPDF to: {output_path}')
+    ocrmypdf.ocr(file_path, output_path)
+
+
+class HandleObserverEvent(PatternMatchingEventHandler):
+    def on_any_event(self, event):
+        if event.event_type in ['created', 'modified']:
+            execute_ocrmypdf(event.src_path)
+
+
+if __name__ == "__main__":
+    print(
+        f"Starting OCRmyPDF watcher with config:\n"
+        f"Input Directory: {INPUT_DIRECTORY}\n"
+        f"Output Directory: {OUTPUT_DIRECTORY}\n"
+        f"Output Directory Year & Month: {OUTPUT_DIRECTORY_YEAR_MONTH}"
+    )
+    handler = HandleObserverEvent(patterns=PATTERNS)
+    observer = Observer()
+    observer.schedule(handler, INPUT_DIRECTORY, recursive=True)
+    observer.start()
+    try:
+        while True:
+            time.sleep(1)
+    except KeyboardInterrupt:
+        observer.stop()
+    observer.join()

pyproject.toml

@@ -10,7 +10,8 @@ build-backend = "setuptools.build_meta"
 
 [tool.black]
 line-length = 88
-target-version = ["py36", "py37", "py38"]
+target-version = ["py36",
+"py37", "py38"]
 skip-string-normalization = true
 include = '\.pyi?$'
 exclude = '''

requirements/watcher.txt

@@ -0,0 +1 @@
+watchdog >= 0.8.2, < 1.0

setup.cfg

@@ -22,6 +22,8 @@ include_trailing_comma=True
 force_grid_wrap=0
 use_parentheses=True
 line_length=88
+known_first_party = ocrmypdf
+known_third_party = PIL,PyPDF2,_cffi_backend,cffi,flask,gs,img2pdf,pdfminer,pikepdf,pkg_resources,pytest,reportlab,setuptools,sphinx_rtd_theme,tqdm,watchdog,werkzeug
 
 [metadata]
 license_file = LICENSE

src/ocrmypdf/_pipeline.py

@@ -41,7 +41,7 @@ from .helpers import safe_symlink
 from .hocrtransform import HocrTransform
 from .optimize import optimize
 from .pdfa import generate_pdfa_ps
-from .pdfinfo import Colorspace, PdfInfo, Encoding
+from .pdfinfo import Colorspace, Encoding, PdfInfo
 
 VECTOR_PAGE_DPI = 400
 

src/ocrmypdf/_sync.py

@@ -25,8 +25,8 @@ import threading
 from collections import namedtuple
 from tempfile import mkdtemp
 
-from tqdm import tqdm
 import PIL
+from tqdm import tqdm
 
 from ._graft import OcrGrafter
 from ._jobcontext import PDFContext, cleanup_working_files, make_logger

src/ocrmypdf/_validation.py

@@ -58,6 +58,15 @@ log = logging.getLogger(__name__)
 verify_python3_env()
 
 
+def check_platform():
+    if os.name == 'nt' and sys.maxsize <= 2 ** 32:  # pragma: no cover
+        # 32-bit interpreter on Windows
+        log.error(
+            "You are running OCRmyPDF in a 32-bit (x86) Python interpreter."
+            "Please use a 64-bit (x86-64) version of Python."
+        )
+
+
 def check_options_languages(options):
     if not options.language:
         options.language = [DEFAULT_LANGUAGE]
@@ -292,6 +301,7 @@ def check_options_pillow(options):
 
 
 def check_options(options):
+    check_platform()
     check_options_languages(options)
     check_options_metadata(options)
     check_options_output(options)

src/ocrmypdf/api.py

@@ -21,7 +21,7 @@ import sys
 import warnings
 from enum import IntEnum
 from pathlib import Path
-from typing import List, Optional, Dict
+from typing import Dict, List, Optional
 
 from tqdm import tqdm
 

src/ocrmypdf/exec/__init__.py

@@ -20,10 +20,12 @@
 import logging
 import os
 import re
-import sys
 import shutil
+import sys
 from collections.abc import Mapping
-from subprocess import PIPE, STDOUT, CalledProcessError, run as subprocess_run
+from functools import lru_cache
+from subprocess import PIPE, STDOUT, CalledProcessError
+from subprocess import run as subprocess_run
 
 from ..exceptions import ExitCode, MissingDependencyError
 
@@ -39,13 +41,42 @@ def _get_program(args, env=None):
 
 
 def run(args, *, env=None, **kwargs):
+    """Wrapper around subprocess.run()
+
+    The main purpose of this wrapper is to allow us to substitute the main program
+    for a spoof in the test suite. The hidden variable _OCRMYPDF_TEST_PATH replaces
+    the main PATH as a location to check for programs to run.
+
+    Secondly we have to account for behavioral differences in Windows in particular.
+    Creating symbolic links in Windows requires administrator privileges and
+    may not work if for some reason we're using a FAT file system or the temporary
+    folder is on a different drive from the working folder. The test suite
+    works around this by creating shim Python scripts that perform the same function
+    as a symbolic link, but those shims require support on this side, to ensure
+    we call them with Python.
+
+    """
     if not env:
         env = os.environ
+
+    # Search in spoof path if necessary
     program = _get_program(args, env)
+
+    # If we are running a .py on Windows, ensure we call it with this Python
+    # (to support test suite shims)
     if os.name == 'nt' and program.lower().endswith('.py'):
         args = [sys.executable, program] + args[1:]
     else:
         args = [program] + args[1:]
+
+    if os.name == 'nt':
+        paths = os.pathsep.join(os.get_exec_path(env))
+        if not shutil.which(args[0], path=paths):
+            shimmed_path = shim_paths_with_program_files(env)
+            new_args0 = shutil.which(args[0], path=shimmed_path)
+            if new_args0:
+                args[0] = new_args0
+
     log.debug(args)
     if sys.version_info < (3, 7) and os.name == 'nt':
         # Can't use close_fds=True on Windows with Python 3.6 or older
@@ -55,7 +86,7 @@ def run(args, *, env=None, **kwargs):
 
 
 def get_version(program, *, version_arg='--version', regex=r'(\d+(\.\d+)*)', env=None):
-    "Get the version of the specified program"
+    """Get the version of the specified program"""
     args_prog = [program, version_arg]
     try:
         proc = run(
@@ -91,6 +122,32 @@ def get_version(program, *, version_arg='--version', regex=r'(\d+(\.\d+)*)', env
     return version
 
 
+def shim_paths_with_program_files(env=None):
+    if not env:
+        env = os.environ
+    program_files = env.get('PROGRAMFILES', '')
+    if not program_files:
+        return env.get('PATH', '')
+    paths = []
+    try:
+        for dirname in os.listdir(program_files):
+            if dirname.lower() == 'tesseract-ocr':
+                paths.append(os.path.join(program_files, dirname))
+            elif dirname.lower() == 'gs':
+                try:
+                    latest_gs = max(
+                        os.listdir(os.path.join(program_files, dirname)),
+                        key=lambda d: float(d[2:]),
+                    )
+                except (FileNotFoundError, NotADirectoryError):
+                    continue
+                paths.append(os.path.join(program_files, dirname, latest_gs, 'bin'))
+    except EnvironmentError:
+        pass
+    paths.extend(path for path in os.get_exec_path(env) if path not in set(paths))
+    return os.pathsep.join(paths)
+
+
 missing_program = '''
 The program '{program}' could not be executed or was not found on your
 system PATH.

src/ocrmypdf/exec/ghostscript.py

@@ -18,20 +18,20 @@
 """Interface to Ghostscript executable"""
 
 import logging
-import re
 import os
+import re
 import warnings
 from contextlib import suppress
 from functools import lru_cache
 from io import BytesIO
 from os import fspath
 from pathlib import Path
-from subprocess import PIPE, CalledProcessError
 from shutil import which
+from subprocess import PIPE, CalledProcessError
 
 from PIL import Image
 
-from ..exceptions import SubprocessOutputError, MissingDependencyError
+from ..exceptions import MissingDependencyError, SubprocessOutputError
 from . import get_version, run
 
 gslog = logging.getLogger()
@@ -329,7 +329,7 @@ def generate_pdfa(
         if _gs_error_reported(stderr):
             last_part = None
             repcount = 0
-            for part in p.stdout.split('****'):
+            for part in stderr.split('****'):
                 if part != last_part:
                     if repcount > 1:
                         log.error(f"(previous error message repeated {repcount} times)")

src/ocrmypdf/exec/tesseract.py

@@ -17,11 +17,11 @@
 
 """Interface to Tesseract executable"""
 
+import logging
 import os
 import shutil
 from collections import namedtuple
 from contextlib import suppress
-import logging
 from os import fspath
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
 

src/ocrmypdf/exec/unpaper.py

@@ -29,7 +29,8 @@ from tempfile import TemporaryDirectory
 from PIL import Image
 
 from ..exceptions import MissingDependencyError, SubprocessOutputError
-from . import get_version, run as external_run
+from . import get_version
+from . import run as external_run
 
 
 @lru_cache(maxsize=1)

src/ocrmypdf/leptonica.py

@@ -33,8 +33,9 @@ from io import BytesIO
 from os import fspath
 from tempfile import TemporaryFile
 
-from .lib._leptonica import ffi
 from .exceptions import MissingDependencyError
+from .exec import shim_paths_with_program_files
+from .lib._leptonica import ffi
 
 # pylint: disable=protected-access
 
@@ -42,6 +43,7 @@ logger = logging.getLogger(__name__)
 
 if os.name == 'nt':
     libname = 'liblept-5'
+    os.environ['PATH'] = shim_paths_with_program_files()
 else:
     libname = 'lept'
 _libpath = find_library(libname)

tests/conftest.py

@@ -21,10 +21,11 @@ import platform
 import sys
 from pathlib import Path
 from subprocess import PIPE, run
-from ocrmypdf import api, cli
 
 import pytest
 
+from ocrmypdf import api, cli
+
 pytest_plugins = ['helpers_namespace']
 
 try:

tests/spoof/gs_feature_elision.py

@@ -25,14 +25,12 @@ import os
 import sys
 from subprocess import check_call
 
+from gs import real_ghostscript
 
 """Replicate one type of Ghostscript feature elision warning during
 PDF/A creation."""
 
 
-from gs import real_ghostscript
-
-
 elision_warning = """GPL Ghostscript 9.20: Setting Overprint Mode to 1
 not permitted in PDF/A-2, overprint mode not set"""
 

tests/spoof/gs_pdfa_failure.py

@@ -23,12 +23,12 @@
 import os
 import sys
 
+from gs import real_ghostscript
+
 
 """Replicate Ghostscript PDF/A conversion failure by suppressing some
 arguments"""
 
-from gs import real_ghostscript
-
 
 def main():
     if '--version' in sys.argv:

tests/spoof/gs_raster_failure.py

@@ -24,11 +24,10 @@
 import os
 import sys
 
-"""Replicate Ghostscript raster failure while allowing rendering"""
-
-
 from gs import real_ghostscript
 
+"""Replicate Ghostscript raster failure while allowing rendering"""
+
 
 def main():
     if '--version' in sys.argv:

tests/spoof/gs_render_failure.py

@@ -25,7 +25,6 @@
 import os
 import sys
 
-
 from gs import real_ghostscript
 
 

tests/spoof/tesseract_badutf8.py

@@ -22,7 +22,6 @@
 
 import sys
 
-
 """Tesseract bad utf8 spoof
 
 In 'hocr' mode or 'pdf' mode, return error code 1 and some non-Unicode

tests/spoof/tesseract_cache.py

@@ -59,7 +59,6 @@ import subprocess
 import sys
 from pathlib import Path
 
-
 __version__ = subprocess.check_output(
     ['tesseract', '--version'], stderr=subprocess.STDOUT
 ).decode()

tests/test_acroform.py

@@ -19,7 +19,6 @@ import pytest
 
 import ocrmypdf
 
-
 check_ocrmypdf = pytest.helpers.check_ocrmypdf
 
 

tests/test_completion.py

@@ -15,7 +15,7 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from subprocess import run, PIPE
+from subprocess import PIPE, run
 
 import pytest
 

tests/test_ghostscript.py

@@ -18,7 +18,6 @@
 import logging
 from decimal import Decimal
 
-
 import pikepdf
 import pytest
 from PIL import Image

tests/test_graft.py

@@ -18,10 +18,10 @@
 import os
 from unittest.mock import patch
 
+import pikepdf
 import pytest
 
 import ocrmypdf
-import pikepdf
 
 
 def test_no_glyphless_graft(resources, outdir):

tests/test_image_input.py

@@ -17,10 +17,10 @@
 
 from unittest.mock import patch
 
-import pytest
-from PIL import Image
 import img2pdf
 import pikepdf
+import pytest
+from PIL import Image
 
 import ocrmypdf
 

tests/test_lept.py

@@ -16,8 +16,8 @@
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
 
-from os import fspath
 import os
+from os import fspath
 from pickle import dumps, loads
 from unittest.mock import patch
 

tests/test_metadata.py

@@ -17,22 +17,22 @@
 
 
 import datetime
-from datetime import timezone
 import logging
 import mmap
-from os import fspath
 import os
+from datetime import timezone
+from os import fspath
 from pathlib import Path
 from shutil import copyfile, move
 from unittest.mock import MagicMock, patch
 
-import pytest
-
 import pikepdf
+import pytest
+from pikepdf.models.metadata import decode_pdf_date
+
 from ocrmypdf._jobcontext import PDFContext
 from ocrmypdf.exceptions import ExitCode
 from ocrmypdf.pdfa import SRGB_ICC_PROFILE, file_claims_pdfa, generate_pdfa_ps
-from pikepdf.models.metadata import decode_pdf_date
 
 try:
     import fitz

tests/test_optimize.py

@@ -19,10 +19,10 @@ import logging
 from os import fspath
 from pathlib import Path
 
+import pikepdf
 import pytest
 from PIL import Image
 
-import pikepdf
 from ocrmypdf import optimize as opt
 from ocrmypdf.exec import jbig2enc, pngquant
 from ocrmypdf.exec.ghostscript import rasterize_pdf

tests/test_page_numbers.py

@@ -19,8 +19,8 @@ import pytest
 
 import ocrmypdf
 from ocrmypdf._validation import _pages_from_ranges
-from ocrmypdf.pdfinfo import PdfInfo
 from ocrmypdf.exceptions import BadArgsError
+from ocrmypdf.pdfinfo import PdfInfo
 
 
 @pytest.mark.parametrize(

tests/test_pdfinfo.py

@@ -20,11 +20,11 @@ from math import isclose
 from tempfile import NamedTemporaryFile
 
 import img2pdf
+import pikepdf
 import pytest
 from PIL import Image
 from reportlab.pdfgen.canvas import Canvas
 
-import pikepdf
 from ocrmypdf import pdfinfo
 from ocrmypdf.pdfinfo import Colorspace, Encoding
 

tests/test_rotation.py

@@ -21,10 +21,10 @@ from os import fspath
 from unittest.mock import Mock
 
 import img2pdf
+import pikepdf
 import pytest
 from PIL import Image
 
-import pikepdf
 from ocrmypdf import leptonica
 from ocrmypdf.exec import ghostscript, tesseract
 from ocrmypdf.pdfinfo import PdfInfo

tests/test_stdio.py

@@ -18,7 +18,7 @@
 import os
 import sys
 from pathlib import Path
-from subprocess import DEVNULL, PIPE, run, Popen, CalledProcessError
+from subprocess import DEVNULL, PIPE, CalledProcessError, Popen, run
 
 import pytest
 

tests/test_unpaper.py

@@ -20,8 +20,8 @@ from unittest.mock import patch
 
 import pytest
 
-from ocrmypdf.cli import parser
 from ocrmypdf._validation import check_options
+from ocrmypdf.cli import parser
 from ocrmypdf.exceptions import ExitCode, MissingDependencyError
 from ocrmypdf.exec import unpaper
 

tests/test_validation.py

@@ -23,7 +23,7 @@ import pytest
 
 import ocrmypdf._validation as vd
 from ocrmypdf.api import create_options
-from ocrmypdf.exceptions import MissingDependencyError, BadArgsError
+from ocrmypdf.exceptions import BadArgsError, MissingDependencyError
 from ocrmypdf.pdfinfo import PdfInfo