v12.7.2 release notes

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

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

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

Consequently no changes were needed in pikepdf.

Closes #843

.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:

.docker/Dockerfile

@@ -1,17 +1,27 @@
 # OCRmyPDF
 #
-FROM ubuntu:20.04 as base
 
-FROM base as builder
+FROM ubuntu:21.04 as base
 
 ENV LANG=C.UTF-8
+ENV TZ=UTC
+RUN echo 'debconf debconf/frontend select Noninteractive' | debconf-set-selections
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  python3 \
+  libqpdf-dev \
+  zlib1g \
+  liblept5
+
+FROM base as builder
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
   build-essential autoconf automake libtool \
   libleptonica-dev \
   zlib1g-dev \
-  python3 \
+  python3-dev \
   python3-distutils \
+  libffi-dev \
   ca-certificates \
   curl \
   git
@@ -35,26 +45,15 @@ COPY . /app
 
 WORKDIR /app
 
-RUN pip3 install --no-cache-dir \
-  -r requirements/main.txt \
-  -r requirements/webservice.txt \
-  -r requirements/test.txt \
-  -r requirements/watcher.txt \
-  .
+RUN pip3 install --no-cache-dir .[test,webservice,watcher]
 
 FROM base
 
-ENV LANG=C.UTF-8
-
 RUN apt-get update && apt-get install -y --no-install-recommends \
   ghostscript \
   img2pdf \
-  liblept5 \
   libsm6 libxext6 libxrender-dev \
-  zlib1g \
   pngquant \
-  python3 \
-  qpdf \
   tesseract-ocr \
   tesseract-ocr-chi-sim \
   tesseract-ocr-deu \
@@ -62,7 +61,8 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
   tesseract-ocr-fra \
   tesseract-ocr-por \
   tesseract-ocr-spa \
-  unpaper
+  unpaper \
+  && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app
 
@@ -76,6 +76,5 @@ COPY --from=builder /app/misc/watcher.py /app/
 COPY --from=builder /app/setup.cfg /app/setup.py /app/README.md /app/
 COPY --from=builder /app/requirements /app/requirements
 COPY --from=builder /app/tests /app/tests
-COPY --from=builder /app/src /app/src
 
 ENTRYPOINT ["/usr/local/bin/ocrmypdf"]

.github/ISSUE_TEMPLATE/1-general-issues.md

@@ -0,0 +1,32 @@
+---
+name: General issues
+about: Installation, packages, dependencies, "nothing works", test suite failures...
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+What's the problem?
+
+**To Reproduce**
+Steps to reproduce the behavior.
+
+**Expected behavior**
+What did you expected to happen?
+
+**Screenshots**
+If applicable, add screenshots to help explain your problem.
+
+**System (please complete the following information):**
+ - OS:
+ - Python version:
+ - OCRmyPDF version:
+
+**Installation**
+How did you install OCRmyPDF? Did you install it from your operating system's
+package manager, or using pip?
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/2-problem-with-a-specific-input-file.md

@@ -1,6 +1,6 @@
 ---
-name: Bug report
-about: Create a report to help us improve
+name: Problem with a specific input file
+about: Something went wrong while trying to OCR a specific file
 title: ''
 labels: ''
 assignees: ''
@@ -20,13 +20,13 @@ ocrmypdf  ...arguments... input.pdf output.pdf
 Run with verbosity or higher `-v1` to see more detailed logging. This information may be helpful.
 
 **Example file**
-Include an input PDF or image that demonstrates your issue.
+If your issue is a problem that affects only certain files, and we will require an input file (PDF or image) that demonstrates your issue.
 
-Please provide an input file with no personal or confidential information. At your option you may `GPG-encrypt the file <https://github.com/jbarlow83/OCRmyPDF/wiki>` for OCRmyPDF's author only.
+Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/jbarlow83/OCRmyPDF/wiki) for OCRmyPDF's author only.
 
 Links to files hosted elsewhere are perfectly acceptable. You could also look in ``tests/resources`` and see if any of those files reproduce your issue.
 
-(Exceptions: Issues with installation, command line argument parsing, test suite failures.Issues without example files usually cannot be resolved.)
+*(Issues without example files usually cannot be resolved. It's like reporting an issue against a web browser without providing a URL.)*
 
 **Expected behavior**
 A clear and concise description of what you expected to happen.

.github/ISSUE_TEMPLATE/3-feature_request.md

@@ -0,0 +1,27 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered. Please include the versions of OCRmyPDF and other supporting programs (Tesseract OCR, Ghostscript) - maybe an alternative already exists in a newer version.
+
+**Example file**
+If your issue concerns how OCRmyPDF processes certain files, and please provide an example file that helps illustrate how OCRmyPDF's output could be improve.
+
+Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/jbarlow83/OCRmyPDF/wiki) for OCRmyPDF's author only.
+
+Links to files hosted elsewhere are perfectly acceptable. You could also look in ``tests/resources`` and see if any of those files reproduce your issue.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,17 +0,0 @@
----
-name: Feature request
-about: Suggest an idea for this project
-title: ''
-labels: enhancement
-assignees: ''
-
----
-
-**Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-
-**Describe the solution you'd like**
-A clear and concise description of what you want to happen.
-
-**Additional context**
-Add any other context or screenshots about the feature request here.

.github/issue_template.md

@@ -1,33 +0,0 @@
-**Describe the issue**
-A clear and concise description of what the issue is.
-
-**To Reproduce**
-What command line were you trying to run?
-
-```bash
-ocrmypdf  ...arguments... input.pdf output.pdf
-```
-
-**Example file**
-Please include an example *input* PDF (or image). The input file is more helpful.
-
-Please check any or all that apply about the test file:
-
-- [ ] This is the input file
-- [ ] The file contains no personal or confidential information
-- [ ] I am the copyright holder for this file
-- [ ] I permit this file to be included in the OCRmyPDF test suite under the CC-BY-SA 4.0 license
-- [ ] I am not the copyright holder, but this file is available under a free software license
-
-Files that are not free for inclusion in this project are quite welcome, but we like to collect free files for our test suite when possible. Please do *not* submit files with confidential information. At your option you may encrypt files for OCRmyPDF's author only.
-
-**Expected behavior**
-A clear and concise description of what you expected to happen. Include screenshots if applicable.
-
-**System:**
-
-- OS: [e.g. Linux, macOS]
-- OCRmyPDF Version: [e.g. v7.4.0]
-
-**Additional context**
-Add any other context about the problem here.

.github/workflows/build.yml

@@ -0,0 +1,306 @@
+name: Test and deploy
+
+on:
+  push:
+    branches:
+      - master
+      - ci
+      - release/*
+      - feature/*
+    tags:
+      - v*
+    paths-ignore:
+      - README*
+  pull_request:
+
+jobs:
+  test_linux:
+    name: Test ${{ matrix.os }} with Python ${{ matrix.python }}
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        include:
+          - os: ubuntu-18.04
+            python: 3.6
+          - os: ubuntu-18.04
+            python: 3.7
+          - os: ubuntu-20.04
+            python: 3.8
+          - os: ubuntu-20.04
+            python: 3.9
+          - os: ubuntu-latest
+            python: 3.9
+          - os: ubuntu-20.04
+            python: "pypy-3.6"
+          - os: ubuntu-latest
+            python: "pypy-3.7"
+          - os: ubuntu-latest
+            python: 3.9
+            tesseract5: true
+
+    env:
+      OS: ${{ matrix.os }}
+      PYTHON: ${{ matrix.python }}
+
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+
+      - uses: actions/setup-python@v2
+        name: Install Python
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: Install Tesseract 5
+        if: matrix.tesseract5
+        run: |
+          sudo add-apt-repository ppa:alex-p/tesseract-ocr-devel
+
+      - name: Install common packages
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y --no-install-recommends \
+            curl \
+            ghostscript \
+            img2pdf \
+            libffi-dev \
+            liblept5 \
+            libsm6 libxext6 libxrender-dev \
+            pngquant \
+            poppler-utils \
+            tesseract-ocr \
+            tesseract-ocr-deu \
+            tesseract-ocr-eng \
+            unpaper \
+            zlib1g
+
+      - name: Install Ubuntu 18.04 packages
+        if: matrix.os == 'ubuntu-18.04'
+        run: |
+          sudo apt-get install -y --no-install-recommends \
+            libexempi3
+
+      - name: Install Ubuntu 20.04 packages
+        if: matrix.os == 'ubuntu-20.04'
+        run: |
+          sudo apt-get install -y --no-install-recommends \
+            libexempi8
+
+      - name: Install Ubuntu packages for PyPy
+        if: startsWith(matrix.python, 'pypy')
+        run: |
+          sudo apt-get install -y --no-install-recommends \
+            libxml2-dev \
+            libxslt1-dev \
+            pypy3-dev
+
+      - name: Install Python packages
+        run: |
+          python -m pip install .[test]
+
+      - name: Report versions
+        run: |
+          tesseract --version
+          gs --version
+          pngquant --version
+          unpaper --version
+          img2pdf --version
+
+      - name: Test
+        run: |
+          python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v1
+        with:
+          files: ./coverage.xml
+          env_vars: OS,PYTHON
+
+  test_macos:
+    name: Test macOS
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [macos-latest]
+        python: ["3.9"]
+
+    env:
+      OS: ${{ matrix.os }}
+      PYTHON: ${{ matrix.python }}
+
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+
+      - uses: actions/setup-python@v2
+        name: Install Python
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: Install Homebrew deps
+        run: |
+          brew update
+          brew install \
+            exempi \
+            ghostscript \
+            jbig2enc \
+            leptonica \
+            openjpeg \
+            pngquant \
+            tesseract
+
+      - name: Install Python packages
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install .[test]
+
+      - name: Report versions
+        run: |
+          tesseract --version
+          gs --version
+          pngquant --version
+          img2pdf --version
+
+      - name: Test
+        run: |
+          python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v1
+        with:
+          files: ./coverage.xml
+          env_vars: OS,PYTHON
+
+  test_windows:
+    name: Test Windows
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [windows-latest]
+        python: ["3.9"]
+
+    env:
+      OS: ${{ matrix.os }}
+      PYTHON: ${{ matrix.python }}
+
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+
+      - uses: actions/setup-python@v2
+        name: Install Python
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: Install system packages
+        run: |
+          choco install --yes --no-progress --pre tesseract
+          choco install --yes --no-progress ghostscript
+          choco install --yes --no-progress pngquant
+
+      - name: Install Python packages
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install .[test]
+
+      - name: Test
+        run: |
+          python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v1
+        with:
+          files: ./coverage.xml
+          env_vars: OS,PYTHON
+
+  wheel_sdist_linux:
+    name: Build sdist and wheels
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+
+      - uses: actions/setup-python@v2
+        name: Install Python
+        with:
+          python-version: "3.6"
+
+      - name: Make wheels and sdist
+        run: |
+          python -m pip install --upgrade pip wheel
+          python setup.py sdist
+          python setup.py bdist_wheel
+
+      - uses: actions/upload-artifact@v2
+        with:
+          path: |
+            ./dist/*.whl
+            ./dist/*.tar.gz
+
+  upload_pypi:
+    name: Deploy artifacts to PyPI
+    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
+    steps:
+      - uses: actions/download-artifact@v2
+        with:
+          name: artifact
+          path: dist
+
+      - uses: pypa/gh-action-pypi-publish@master
+        with:
+          user: __token__
+          password: ${{ secrets.TOKEN_PYPI }}
+          # repository_url: https://test.pypi.org/legacy/
+
+  docker:
+    name: Build Docker images
+    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    runs-on: ubuntu-latest
+    if: github.event_name != 'pull_request'
+    steps:
+      - name: Set image tag to release or branch
+        run: echo "DOCKER_IMAGE_TAG=${GITHUB_REF##*/}" >> $GITHUB_ENV
+
+      - name: If master, set to latest
+        run: echo 'DOCKER_IMAGE_TAG=latest' >> $GITHUB_ENV
+        if: env.DOCKER_IMAGE_TAG == 'master'
+
+      - name: Set Docker Hub repository to username
+        run: echo "DOCKER_REPOSITORY=jbarlow83" >> $GITHUB_ENV
+
+      - name: Set image name
+        run: echo "DOCKER_IMAGE_NAME=ocrmypdf" >> $GITHUB_ENV
+
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v1
+        with:
+          username: jbarlow83
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v1
+
+      - name: Set up Docker Buildx
+        id: buildx
+        uses: docker/setup-buildx-action@v1
+
+      - name: Print image tag
+        run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"
+
+      - name: Build
+        run: |
+          docker buildx build \
+            --push \
+            --platform linux/arm64/v8,linux/amd64  \
+            --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}" \
+            --file .docker/Dockerfile .

.gitignore

@@ -6,7 +6,9 @@
 !.gitattributes
 !.gitignore
 !.pre-commit-config.yaml
-!.readthedocs.yml
+!.readthedocs.yaml
+!.github/
+!.docker/
 
 # Dev scratch
 *.ipynb
@@ -23,6 +25,7 @@ venv*/
 /debug_tests.py
 *.traineddata
 /private
+/coverage.xml
 
 # Package building
 *.egg-info/

.pre-commit-config.yaml

@@ -1,23 +1,38 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v2.4.0
+    rev: v4.0.1
     hooks:
       - id: check-case-conflict
       - id: check-merge-conflict
       - id: check-toml
       - id: check-yaml
       - id: debug-statements
-  - 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
+  - repo: https://github.com/pycqa/isort
+    rev: 5.9.3
     hooks:
       - id: isort
+        args: ["--profile", "black"]
   - repo: https://github.com/psf/black
-    rev: stable
+    rev: 21.9b0
     hooks:
       - id: black
-        language_version: python3.7
+        language_version: python
         exclude: ^src/ocrmypdf/lib/_leptonica.py
+  - repo: https://github.com/asottile/setup-cfg-fmt
+    rev: v1.19.0
+    hooks:
+      - id: setup-cfg-fmt
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v2.29.0
+    hooks:
+      - id: pyupgrade
+        args: ["--py36-plus"]
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v0.910-1
+    hooks:
+      - id: mypy
+        additional_dependencies:
+          - types-toml
+          - types-setuptools
+          - types-requests
+          - types-Pillow

.readthedocs.yaml

@@ -0,0 +1,22 @@
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+  configuration: docs/conf.py
+
+# Optionally build your docs in additional formats such as PDF
+formats:
+  - pdf
+
+# Optionally set the version of Python and requirements required to build your docs
+python:
+  version: 3.7
+  install:
+    - method: pip
+      path: .
+      extra_requirements:
+        - docs

.readthedocs.yml

@@ -1,10 +0,0 @@
-build:
-  image: latest
-
-python:
-  version: 3.6
-
-formats:
-  - pdf
-
-requirements_file: requirements/main.txt

README.md

@@ -1,17 +1,12 @@
 <img src="docs/images/logo.svg" width="240" alt="OCRmyPDF">
 
-[![Build Status][azure]](https://dev.azure.com/jim0585/ocrmypdf/_build/latest?definitionId=2&branchName=master) [![PyPI version][pypi]](https://pypi.org/project/ocrmypdf/) ![Homebrew version][homebrew] ![ReadTheDocs][docs] ![Python versions][pyversions]
+[![Build Status](https://github.com/jbarlow83/OCRmyPDF/actions/workflows/build.yml/badge.svg)](https://github.com/jbarlow83/OCRmyPDF/actions/workflows/build.yml) [![PyPI version][pypi]](https://pypi.org/project/ocrmypdf/) ![Homebrew version][homebrew] ![ReadTheDocs][docs] ![Python versions][pyversions]
 
 [azure]: https://dev.azure.com/jim0585/ocrmypdf/_apis/build/status/jbarlow83.OCRmyPDF?branchName=master
-
 [travis]: https://travis-ci.org/jbarlow83/OCRmyPDF.svg?branch=master "Travis build status"
-
 [pypi]: https://img.shields.io/pypi/v/ocrmypdf.svg "PyPI version"
-
 [homebrew]: https://img.shields.io/homebrew/v/ocrmypdf.svg "Homebrew version"
-
 [docs]: https://readthedocs.org/projects/ocrmypdf/badge/?version=latest "RTD"
-
 [pyversions]: https://img.shields.io/pypi/pyversions/ocrmypdf "Supported Python versions"
 
 OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched or copy-pasted.
@@ -30,8 +25,7 @@ ocrmypdf                      # it's a scriptable command line program
 
 [See the release notes for details on the latest changes](https://ocrmypdf.readthedocs.io/en/latest/release_notes.html).
 
-Main features
--------------
+## Main features
 
 - Generates a searchable [PDF/A](https://en.wikipedia.org/?title=PDF/A) file from a regular PDF
 - Places OCR text accurately below the image to ease copy / paste
@@ -47,8 +41,7 @@ Main features
 
 For details: please consult the [documentation](https://ocrmypdf.readthedocs.io/en/latest/).
 
-Motivation
-----------
+## Motivation
 
 I searched the web for a free command line tool to OCR PDF files: I found many, but none of them were really satisfying:
 
@@ -62,33 +55,23 @@ I searched the web for a free command line tool to OCR PDF files: I found many,
 
 ...so I decided to develop my own tool.
 
-Installation
-------------
+## Installation
 
-Linux, Windows, macOS and FreeBSD are supported. Docker images are also available.
+Linux, Windows, macOS and FreeBSD are supported. Docker images are also available, for both x64 and ARM.
 
-Users of Debian 9 or later or Ubuntu 16.10 or later may simply
-
-```bash
-apt-get install ocrmypdf
-```
-
-and users of Fedora 29 or later may simply
-
-```bash
-dnf install ocrmypdf
-```
-
-and Homebrew users (macOS, Linux, Windows Subsystem for Linux) may simply
-
-```bash
-brew install ocrmypdf
-```
+| Operating system              | Install command               |
+| ----------------------------- | ------------------------------|
+| Debian, Ubuntu                | ``apt install ocrmypdf``      |
+| Windows Subsystem for Linux   | ``apt install ocrmypdf``      |
+| Fedora                        | ``dnf install ocrmypdf``      |
+| macOS                         | ``brew install ocrmypdf``     |
+| LinuxBrew                     | ``brew install ocrmypdf``     |
+| FreeBSD                       | ``pkg install py37-ocrmypdf`` |
+| Conda                         | ``conda install ocrmypdf``    |
 
 For everyone else, [see our documentation](https://ocrmypdf.readthedocs.io/en/latest/installation.html) for installation steps.
 
-Languages
----------
+## Languages
 
 OCRmyPDF uses Tesseract for OCR, and relies on its language packs. For Linux users, you can often find packages that provide language packs:
 
@@ -101,12 +84,19 @@ apt-get install tesseract-ocr-chi-sim  # Example: Install Chinese Simplified lan
 
 # Arch Linux users
 pacman -S tesseract-data-eng tesseract-data-deu # Example: Install the English and German language packs
+
+# brew macOS users
+brew install tesseract-lang
 ```
 
 You can then pass the `-l LANG` argument to OCRmyPDF to give a hint as to what languages it should search for. Multiple languages can be requested.
 
-Documentation and support
--------------------------
+OCRmyPDF supports Tesseract 4.0 and the beta versions of Tesseract 5.0. It will
+automatically use whichever version it finds first on the `PATH` environment
+variable. On Windows, if `PATH` does not provide a Tesseract binary, we use
+the highest version number that is installed according to the Windows Registry.
+
+## Documentation and support
 
 Once OCRmyPDF is installed, the built-in help which explains the command syntax and options can be accessed via:
 
@@ -118,35 +108,36 @@ Our [documentation is served on Read the Docs](https://ocrmypdf.readthedocs.io/e
 
 Please report issues on our [GitHub issues](https://github.com/jbarlow83/OCRmyPDF/issues) page, and follow the issue template for quick response.
 
-Requirements
-------------
+## 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. OCRmyPDF works on pretty much everything: Linux, macOS, Windows and FreeBSD.
 
-Press & Media
--------------
+## Press & Media
 
 - [Going paperless with OCRmyPDF](https://medium.com/@ikirichenko/going-paperless-with-ocrmypdf-e2f36143f46a)
 - [Converting a scanned document into a compressed searchable PDF with redactions](https://medium.com/@treyharris/converting-a-scanned-document-into-a-compressed-searchable-pdf-with-redactions-63f61c34fe4c)
 - [c't 1-2014, page 59](https://heise.de/-2279695): Detailed presentation of OCRmyPDF v1.0 in the leading German IT magazine c't
 - [heise Open Source, 09/2014: Texterkennung mit OCRmyPDF](https://heise.de/-2356670)
 - [heise Durchsuchbare PDF-Dokumente mit OCRmyPDF erstellen](https://www.heise.de/ratgeber/Durchsuchbare-PDF-Dokumente-mit-OCRmyPDF-erstellen-4607592.html)
+- [Excellent Utilities: OCRmyPDF](https://www.linuxlinks.com/excellent-utilities-ocrmypdf-add-ocr-text-layer-scanned-pdfs/)
+- [LinuxUser Texterkennung mit OCRmyPDF und Scanbd automatisieren](https://www.linux-community.de/ausgaben/linuxuser/2021/06/texterkennung-mit-ocrmypdf-und-scanbd-automatisieren/)
 
-Business enquiries
-------------------
+## Business enquiries
 
 OCRmyPDF would not be the software that it is today without companies and users choosing to provide support for feature development and consulting enquiries. We are happy to discuss all enquiries, whether for extending the existing feature set, or integrating OCRmyPDF into a larger system.
 
-License
--------
+## License
 
-The OCRmyPDF software is licensed under the GNU GPLv3. Certain files are covered by other licenses, as noted in their source files.
+The OCRmyPDF software is licensed under the Mozilla Public License 2.0
+(MPL-2.0). This license permits integration of OCRmyPDF with other code,
+included commercial and closed source, but asks you to publish source-level
+modifications you make to OCRmyPDF.
 
-The license for each test file varies, and is noted in tests/resources/README.rst. The documentation is licensed under Creative Commons Attribution-ShareAlike 4.0 (CC-BY-SA 4.0).
+Some components of OCRmyPDF have other licenses, as noted in those files and the
+``debian/copyright`` file. Most files in ``misc/`` use the MIT license, and the
+documentation and test files are generally licensed under Creative Commons
+ShareAlike 4.0 (CC-BY-SA 4.0).
 
-OCRmyPDF versions prior to 6.0 were distributed under the MIT License.
-
-Disclaimer
-----------
+## Disclaimer
 
 The software is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

azure-pipelines.yml

@@ -1,253 +0,0 @@
-trigger:
-  tags:
-    include:
-      - v*
-  branches:
-    include:
-      - "*"
-    exclude:
-      - "travis"
-
-stages:
-  - stage: "Test"
-    jobs:
-      - job: Windows
-        pool:
-          vmImage: "vs2017-win2016"
-        strategy:
-          matrix:
-            Python36:
-              python.version: "3.6"
-            Python37:
-              python.version: "3.7"
-            Python38:
-              python.version: "3.8"
-        steps:
-          - task: UsePythonVersion@0
-            inputs:
-              versionSpec: "$(python.version)"
-          - pwsh: |
-              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
-            displayName: "Install system packages"
-          - pwsh: |
-              refreshenv
-              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
-              $env:pathext += ';.py'
-              # -n auto helps Windows
-              python -m pytest -n auto --junitxml=test.xml --cov=ocrmypdf --cov-report=xml
-            displayName: "Test"
-          - task: PublishTestResults@2
-            inputs:
-              testResultsFiles: "test.xml"
-              testRunTitle: "$(Agent.OS) - $(Build.DefinitionName) - Python $(python.version)"
-            condition: succeededOrFailed()
-      - job: "Ubuntu_1804"
-        pool:
-          vmImage: "ubuntu-18.04"
-        strategy:
-          matrix:
-            Python36:
-              python.version: "3.6"
-            Python37:
-              python.version: "3.7"
-            Python38:
-              python.version: "3.8"
-        steps:
-          - task: UsePythonVersion@0
-            inputs:
-              versionSpec: "$(python.version)"
-          - bash: |
-              sudo apt-get update
-              sudo apt-get install -y --no-install-recommends \
-                python3-software-properties \
-                curl \
-                ghostscript \
-                img2pdf \
-                libexempi3 \
-                libffi-dev \
-                liblept5 \
-                libsm6 libxext6 libxrender-dev \
-                pngquant \
-                poppler-utils \
-                tesseract-ocr \
-                tesseract-ocr-deu \
-                tesseract-ocr-eng \
-                unpaper \
-                zlib1g
-            displayName: "Install system packages"
-          - bash: |
-              curl https://bootstrap.pypa.io/get-pip.py | python3
-              pip3 install -r requirements/main.txt -r requirements/test.txt .
-            displayName: "Install Python packages"
-          - bash: |
-              tesseract --version
-            displayName: "Record versions"
-          - bash: |
-              # -n auto is slower on Linux and breaks on Python 3.8
-              pytest -n0 --junitxml=test.xml --cov=ocrmypdf --cov-report=xml
-            displayName: "Test"
-          - task: PublishTestResults@2
-            inputs:
-              testResultsFiles: "test.xml"
-              testRunTitle: "$(Agent.OS) - $(Build.DefinitionName) - Python $(python.version)"
-            condition: succeededOrFailed()
-      - job: "Ubuntu_1604"
-        pool:
-          vmImage: "ubuntu-16.04"
-        strategy:
-          matrix:
-            Python36:
-              python.version: "3.6"
-        steps:
-          - task: UsePythonVersion@0
-            inputs:
-              versionSpec: "$(python.version)"
-          - bash: |
-              sudo apt-get update
-              sudo apt-get install -y --no-install-recommends \
-                software-properties-common
-              sudo add-apt-repository -y ppa:alex-p/tesseract-ocr
-              sudo apt-get update
-              sudo apt-get install -y --no-install-recommends \
-                ghostscript \
-                img2pdf \
-                libexempi3 \
-                libffi-dev \
-                liblept5 \
-                libsm6 libxext6 libxrender-dev \
-                pngquant \
-                poppler-utils \
-                tesseract-ocr \
-                tesseract-ocr-deu \
-                tesseract-ocr-eng \
-                unpaper \
-                zlib1g
-            displayName: "Install system packages"
-          - bash: |
-              curl https://bootstrap.pypa.io/get-pip.py | python3
-              pip3 install -r requirements/main.txt -r requirements/test.txt .
-            displayName: "Install Python packages"
-          - bash: |
-              tesseract --version
-            displayName: "Record versions"
-          - bash: |
-              # -n auto is slower on Linux and breaks on Python 3.8
-              pytest -n0 --junitxml=test.xml --cov=ocrmypdf --cov-report=xml
-            displayName: "Test"
-          - task: PublishTestResults@2
-            inputs:
-              testResultsFiles: "test.xml"
-              testRunTitle: "$(Agent.OS) - $(Build.DefinitionName) - Python $(python.version)"
-            condition: succeededOrFailed()
-      - job: "macOS_Mojave"
-        pool:
-          vmImage: "macos-10.14"
-        strategy:
-          matrix:
-            Python37:
-              python.version: "3.7"
-            # Python38:
-            #   python.version: "3.8"
-        steps:
-          # https://github.com/actions/virtual-environments/issues/664
-          # - task: UsePythonVersion@0
-          #   inputs:
-          #     versionSpec: "$(python.version)"
-          - bash: |
-              brew update
-              brew unlink python@2
-              brew install \
-                exempi \
-                ghostscript \
-                jbig2enc \
-                leptonica \
-                openjpeg \
-                pngquant \
-                python \
-                tesseract \
-                unpaper
-            displayName: "Install system packages"
-          - bash: |
-              pip3 install --upgrade pip
-              pip3 install -r requirements/main.txt -r requirements/test.txt .
-            displayName: "Install Python packages"
-          - bash: |
-              tesseract --version
-            displayName: "Record versions"
-          - bash: pytest -nauto --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"
-
-  - stage: "Artifacts"
-    jobs:
-      - job: "sdist_wheel"
-        pool:
-          vmImage: "ubuntu-18.04"
-        steps:
-          - task: UsePythonVersion@0
-            inputs:
-              versionSpec: "3.7"
-          - bash: |
-              python -m pip install --upgrade pip wheel
-              python setup.py sdist bdist_wheel
-          - publish: dist
-            artifact: sdist_wheel
-
-  - stage: "Deploy"
-    jobs:
-      - deployment: "PyPI"
-        pool:
-          vmImage: "ubuntu-18.04"
-        environment: "deploy"
-        strategy:
-          runOnce:
-            deploy:
-              steps:
-                - download: current
-                  artifact: sdist_wheel
-                - script: |
-                    mkdir -p dist
-                    mv $(Pipeline.Workspace)/sdist_wheel/* dist
-                  displayName: "Move dist files"
-                - task: UsePythonVersion@0
-                  inputs:
-                    versionSpec: "3.8"
-                    architecture: x64
-                - script: |
-                    pip install --upgrade twine
-                  displayName: "Generate artifacts"
-                - script: |
-                    cat <<FILE >.pypirc
-                    [distutils]
-                    index-servers =
-                        pypi
-
-                    [pypi]
-                    username: __token__
-                    password: $(TOKEN_PYPI)
-
-                    FILE
-                  displayName: "Generate PyPI auth file"
-                - script: |
-                    python -m twine upload --config-file .pypirc dist/*
-                  displayName: "Upload to PyPI"
-                  condition: and(succeeded(), startsWith(variables['Build.SourceBranch'], 'refs/tags/'))
-                - script: |
-                    curl -X POST -d "token=$(TOKEN_RTD)" https://readthedocs.org/api/v2/webhook/pikepdf/39557/
-                  displayName: "Trigger ReadTheDocs"
-                  condition: and(succeeded(), or(startsWith(variables['Build.SourceBranch'], 'refs/tags/'), startsWith(variables['Build.SourceBranch'], 'refs/heads/master')))

debian/copyright

@@ -2,35 +2,70 @@ Format: https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
 Upstream-Name: OCRmyPDF
 Upstream-Contact: James R. Barlow <barlow.jim@gmail.com>
 Source: https://github.com/jbarlow83/OCRmyPDF
-Files-Excluded: tests/resources/milk.pdf
 
 Files: *
 Copyright:
- (C) 2013-2017 The OCRmyPDF Authors
- (C) 2013-2016, 2015-2017 2016, 2017, 2017-2018, 2018 James R. Barlow
-License: GPL-3+
+ (C) 2013-2015 Julien Pfefferkorn
+ (C) 2015-2020 James R. Barlow
+ (C) 2019 Martin Wind
+License: MPL-2.0
+
+Files: misc/*
+Copyright:
+ (C) 2020 James R. Barlow
+License: Expat
+
+Files: misc/completion/ocrmypdf.bash
+Copyright:
+ (C) 2019 Frank Pille
+ (C) 2020 Alex Willner
+License: Expat
+
+Files: misc/completion/ocrmypdf.fish
+Copyright:
+ (C) 2020 James R. Barlow
+License: Expat
+
+Files: misc/batch.py
+Copyright:
+ (C) 2016 findingorder: https://github.com/findingorder
+License: Expat
+
+Files: misc/synology.py
+Copyright:
+ (C) github.com/Enantiomerie
+License: Expat
+
+Files: misc/watcher.py
+Copyright:
+ (C) 2019 Ian Alexander: https://github.com/ianalexander
+ (C) 2020 James R. Barlow
+License: Expat
+
+Files: misc/webservice.py
+Copyright: (C) 2019 James R. Barlow
+License: AGPL-3+
 
 Files: docs tests/resources/*
 Copyright: (C) 2013-2018 James R. Barlow
 License: CC-BY-SA-4.0
 
+Files: docs/images/bitmap_vs_svg.svg
+Copyright: (C) 2006 Yug
+License: CC-BY-SA-2.5
+
 Files: src/ocrmypdf/hocrtransform.py
 Copyright: (C) 2010 Jonathan Brinley <jonathanbrinley@gmail.com>
  (C) 2013-14 Julien Pfefferkorn
  (C) 2015-16 James R. Barlow
 License: Expat
 
-Files: src/ocrmypdf/pdfa.py
-Copyright: (C) 2015 James R. Barlow
- (C) 1986-2017 The authors of GhostScript
-License: GPL-3+
-
 Files: src/ocrmypdf/_unicodefun.py
 Copyright: (C) 2014 Armin Ronacher
  (C) 2017 James R. Barlow
 License: BSD-3-clause
 
-Files: tests/spoof/*
+Files: tests/plugins/*
 Copyright: (C) 2016, 2017, 2016-2018 James R. Barlow
 License: Expat
 
@@ -79,15 +114,20 @@ Copyright: held by the contributors to the Wikipedia article "Optical character
  (epson.pdf generated from Wikipedia article as of 2016-09-14)
 License: CC-BY-SA-3.0
 
-Files: tests/resources/typewriter.png tests/resources/2400dpi.pdf tests/resources/3small.pdf
+Files: tests/resources/typewriter.png tests/resources/2400dpi.pdf
 Copyright: (C) 2005 Ellywa
 License: GFDL-1.2+ or CC-BY-SA-1.0 or CC-BY-SA-2.0 or CC-BY-SA-2.5 or CC-BY-SA-3.0
+Comment:
+ Obtained from: https://commons.wikimedia.org/wiki/File:Triumph.typewriter_text_Linzensoep.gif
 
 Files: tests/resources/overlay.pdf
 Copyright: (C) 2017 Max Anderson
 License: Expat
 
-Files: tests/resources/baiona*.png tests/resources/3small.pdf
+Files:
+ tests/resources/baiona*.png
+ tests/resources/baiona*.jpg
+ tests/resources/link.pdf
 Copyright: (C) 2014 Euskaldunaa
 License: CC-BY-SA-4.0
 
@@ -95,6 +135,13 @@ Files: tests/resources/vector.pdf
 Copyright: (C) 2018 Catscratch
 License: Expat
 
+Files: tests/resources/3small.pdf
+Copyright: (C) 2014 Euskaldunaa
+ (C) 2017 James R. Barlow
+ (C) 2005 Ellywa
+License: CC-BY-SA-4.0 and (GFDL-1.2+ or CC-BY-SA-1.0 or CC-BY-SA-2.0 or CC-BY-SA-2.5 or CC-BY-SA-3.0)
+Comment: concatenation of baiona_gray.png, crom.png and typewriter.png/2400dpi.pdf
+
 Files: src/ocrmypdf/data/sRGB.icc
 Copyright:  Kai-Uwe Behrmann <www.behrmann.name>
             Marti Maria <www.littlecms.com>
@@ -107,6 +154,13 @@ Files: debian/*
 Copyright: (C) 2016 Sean Whitton <spwhitton@spwhitton.name>
 License: GPL-3+
 
+License: MPL-2.0
+ This Source Code Form is subject to the terms of the Mozilla Public
+ License, v. 2.0.
+ .
+ On Debian systems the full text of the MPL-2.0 can be found in
+ /usr/share/common-licenses/MPL-2.0.
+
 License: GPL-3+
  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
@@ -124,6 +178,669 @@ License: GPL-3+
  On Debian systems, the complete text of the GNU General
  Public License version 3 can be found in "/usr/share/common-licenses/GPL-3".
 
+License: AGPL-3+
+                     GNU AFFERO GENERAL PUBLIC LICENSE
+                        Version 3, 19 November 2007
+ .
+  Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+  Everyone is permitted to copy and distribute verbatim copies
+  of this license document, but changing it is not allowed.
+ .
+                             Preamble
+ .
+   The GNU Affero General Public License is a free, copyleft license for
+ software and other kinds of works, specifically designed to ensure
+ cooperation with the community in the case of network server software.
+ .
+   The licenses for most software and other practical works are designed
+ to take away your freedom to share and change the works.  By contrast,
+ our General Public Licenses are intended to guarantee your freedom to
+ share and change all versions of a program--to make sure it remains free
+ software for all its users.
+ .
+   When we speak of free software, we are referring to freedom, not
+ price.  Our General Public Licenses are designed to make sure that you
+ have the freedom to distribute copies of free software (and charge for
+ them if you wish), that you receive source code or can get it if you
+ want it, that you can change the software or use pieces of it in new
+ free programs, and that you know you can do these things.
+ .
+   Developers that use our General Public Licenses protect your rights
+ with two steps: (1) assert copyright on the software, and (2) offer
+ you this License which gives you legal permission to copy, distribute
+ and/or modify the software.
+ .
+   A secondary benefit of defending all users' freedom is that
+ improvements made in alternate versions of the program, if they
+ receive widespread use, become available for other developers to
+ incorporate.  Many developers of free software are heartened and
+ encouraged by the resulting cooperation.  However, in the case of
+ software used on network servers, this result may fail to come about.
+ The GNU General Public License permits making a modified version and
+ letting the public access it on a server without ever releasing its
+ source code to the public.
+ .
+   The GNU Affero General Public License is designed specifically to
+ ensure that, in such cases, the modified source code becomes available
+ to the community.  It requires the operator of a network server to
+ provide the source code of the modified version running there to the
+ users of that server.  Therefore, public use of a modified version, on
+ a publicly accessible server, gives the public access to the source
+ code of the modified version.
+ .
+   An older license, called the Affero General Public License and
+ published by Affero, was designed to accomplish similar goals.  This is
+ a different license, not a version of the Affero GPL, but Affero has
+ released a new version of the Affero GPL which permits relicensing under
+ this license.
+ .
+   The precise terms and conditions for copying, distribution and
+ modification follow.
+ .
+                        TERMS AND CONDITIONS
+ .
+   0. Definitions.
+ .
+   "This License" refers to version 3 of the GNU Affero General Public License.
+ .
+   "Copyright" also means copyright-like laws that apply to other kinds of
+ works, such as semiconductor masks.
+ .
+   "The Program" refers to any copyrightable work licensed under this
+ License.  Each licensee is addressed as "you".  "Licensees" and
+ "recipients" may be individuals or organizations.
+ .
+   To "modify" a work means to copy from or adapt all or part of the work
+ in a fashion requiring copyright permission, other than the making of an
+ exact copy.  The resulting work is called a "modified version" of the
+ earlier work or a work "based on" the earlier work.
+ .
+   A "covered work" means either the unmodified Program or a work based
+ on the Program.
+ .
+   To "propagate" a work means to do anything with it that, without
+ permission, would make you directly or secondarily liable for
+ infringement under applicable copyright law, except executing it on a
+ computer or modifying a private copy.  Propagation includes copying,
+ distribution (with or without modification), making available to the
+ public, and in some countries other activities as well.
+ .
+   To "convey" a work means any kind of propagation that enables other
+ parties to make or receive copies.  Mere interaction with a user through
+ a computer network, with no transfer of a copy, is not conveying.
+ .
+   An interactive user interface displays "Appropriate Legal Notices"
+ to the extent that it includes a convenient and prominently visible
+ feature that (1) displays an appropriate copyright notice, and (2)
+ tells the user that there is no warranty for the work (except to the
+ extent that warranties are provided), that licensees may convey the
+ work under this License, and how to view a copy of this License.  If
+ the interface presents a list of user commands or options, such as a
+ menu, a prominent item in the list meets this criterion.
+ .
+   1. Source Code.
+ .
+   The "source code" for a work means the preferred form of the work
+ for making modifications to it.  "Object code" means any non-source
+ form of a work.
+ .
+   A "Standard Interface" means an interface that either is an official
+ standard defined by a recognized standards body, or, in the case of
+ interfaces specified for a particular programming language, one that
+ is widely used among developers working in that language.
+ .
+   The "System Libraries" of an executable work include anything, other
+ than the work as a whole, that (a) is included in the normal form of
+ packaging a Major Component, but which is not part of that Major
+ Component, and (b) serves only to enable use of the work with that
+ Major Component, or to implement a Standard Interface for which an
+ implementation is available to the public in source code form.  A
+ "Major Component", in this context, means a major essential component
+ (kernel, window system, and so on) of the specific operating system
+ (if any) on which the executable work runs, or a compiler used to
+ produce the work, or an object code interpreter used to run it.
+ .
+   The "Corresponding Source" for a work in object code form means all
+ the source code needed to generate, install, and (for an executable
+ work) run the object code and to modify the work, including scripts to
+ control those activities.  However, it does not include the work's
+ System Libraries, or general-purpose tools or generally available free
+ programs which are used unmodified in performing those activities but
+ which are not part of the work.  For example, Corresponding Source
+ includes interface definition files associated with source files for
+ the work, and the source code for shared libraries and dynamically
+ linked subprograms that the work is specifically designed to require,
+ such as by intimate data communication or control flow between those
+ subprograms and other parts of the work.
+ .
+   The Corresponding Source need not include anything that users
+ can regenerate automatically from other parts of the Corresponding
+ Source.
+ .
+   The Corresponding Source for a work in source code form is that
+ same work.
+ .
+   2. Basic Permissions.
+ .
+   All rights granted under this License are granted for the term of
+ copyright on the Program, and are irrevocable provided the stated
+ conditions are met.  This License explicitly affirms your unlimited
+ permission to run the unmodified Program.  The output from running a
+ covered work is covered by this License only if the output, given its
+ content, constitutes a covered work.  This License acknowledges your
+ rights of fair use or other equivalent, as provided by copyright law.
+ .
+   You may make, run and propagate covered works that you do not
+ convey, without conditions so long as your license otherwise remains
+ in force.  You may convey covered works to others for the sole purpose
+ of having them make modifications exclusively for you, or provide you
+ with facilities for running those works, provided that you comply with
+ the terms of this License in conveying all material for which you do
+ not control copyright.  Those thus making or running the covered works
+ for you must do so exclusively on your behalf, under your direction
+ and control, on terms that prohibit them from making any copies of
+ your copyrighted material outside their relationship with you.
+ .
+   Conveying under any other circumstances is permitted solely under
+ the conditions stated below.  Sublicensing is not allowed; section 10
+ makes it unnecessary.
+ .
+   3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+ .
+   No covered work shall be deemed part of an effective technological
+ measure under any applicable law fulfilling obligations under article
+ 11 of the WIPO copyright treaty adopted on 20 December 1996, or
+ similar laws prohibiting or restricting circumvention of such
+ measures.
+ .
+   When you convey a covered work, you waive any legal power to forbid
+ circumvention of technological measures to the extent such circumvention
+ is effected by exercising rights under this License with respect to
+ the covered work, and you disclaim any intention to limit operation or
+ modification of the work as a means of enforcing, against the work's
+ users, your or third parties' legal rights to forbid circumvention of
+ technological measures.
+ .
+   4. Conveying Verbatim Copies.
+ .
+   You may convey verbatim copies of the Program's source code as you
+ receive it, in any medium, provided that you conspicuously and
+ appropriately publish on each copy an appropriate copyright notice;
+ keep intact all notices stating that this License and any
+ non-permissive terms added in accord with section 7 apply to the code;
+ keep intact all notices of the absence of any warranty; and give all
+ recipients a copy of this License along with the Program.
+ .
+   You may charge any price or no price for each copy that you convey,
+ and you may offer support or warranty protection for a fee.
+ .
+   5. Conveying Modified Source Versions.
+ .
+   You may convey a work based on the Program, or the modifications to
+ produce it from the Program, in the form of source code under the
+ terms of section 4, provided that you also meet all of these conditions:
+ .
+     a) The work must carry prominent notices stating that you modified
+     it, and giving a relevant date.
+ .
+     b) The work must carry prominent notices stating that it is
+     released under this License and any conditions added under section
+     7.  This requirement modifies the requirement in section 4 to
+     "keep intact all notices".
+ .
+     c) You must license the entire work, as a whole, under this
+     License to anyone who comes into possession of a copy.  This
+     License will therefore apply, along with any applicable section 7
+     additional terms, to the whole of the work, and all its parts,
+     regardless of how they are packaged.  This License gives no
+     permission to license the work in any other way, but it does not
+     invalidate such permission if you have separately received it.
+ .
+     d) If the work has interactive user interfaces, each must display
+     Appropriate Legal Notices; however, if the Program has interactive
+     interfaces that do not display Appropriate Legal Notices, your
+     work need not make them do so.
+ .
+   A compilation of a covered work with other separate and independent
+ works, which are not by their nature extensions of the covered work,
+ and which are not combined with it such as to form a larger program,
+ in or on a volume of a storage or distribution medium, is called an
+ "aggregate" if the compilation and its resulting copyright are not
+ used to limit the access or legal rights of the compilation's users
+ beyond what the individual works permit.  Inclusion of a covered work
+ in an aggregate does not cause this License to apply to the other
+ parts of the aggregate.
+ .
+   6. Conveying Non-Source Forms.
+ .
+   You may convey a covered work in object code form under the terms
+ of sections 4 and 5, provided that you also convey the
+ machine-readable Corresponding Source under the terms of this License,
+ in one of these ways:
+ .
+     a) Convey the object code in, or embodied in, a physical product
+     (including a physical distribution medium), accompanied by the
+     Corresponding Source fixed on a durable physical medium
+     customarily used for software interchange.
+ .
+     b) Convey the object code in, or embodied in, a physical product
+     (including a physical distribution medium), accompanied by a
+     written offer, valid for at least three years and valid for as
+     long as you offer spare parts or customer support for that product
+     model, to give anyone who possesses the object code either (1) a
+     copy of the Corresponding Source for all the software in the
+     product that is covered by this License, on a durable physical
+     medium customarily used for software interchange, for a price no
+     more than your reasonable cost of physically performing this
+     conveying of source, or (2) access to copy the
+     Corresponding Source from a network server at no charge.
+ .
+     c) Convey individual copies of the object code with a copy of the
+     written offer to provide the Corresponding Source.  This
+     alternative is allowed only occasionally and noncommercially, and
+     only if you received the object code with such an offer, in accord
+     with subsection 6b.
+ .
+     d) Convey the object code by offering access from a designated
+     place (gratis or for a charge), and offer equivalent access to the
+     Corresponding Source in the same way through the same place at no
+     further charge.  You need not require recipients to copy the
+     Corresponding Source along with the object code.  If the place to
+     copy the object code is a network server, the Corresponding Source
+     may be on a different server (operated by you or a third party)
+     that supports equivalent copying facilities, provided you maintain
+     clear directions next to the object code saying where to find the
+     Corresponding Source.  Regardless of what server hosts the
+     Corresponding Source, you remain obligated to ensure that it is
+     available for as long as needed to satisfy these requirements.
+ .
+     e) Convey the object code using peer-to-peer transmission, provided
+     you inform other peers where the object code and Corresponding
+     Source of the work are being offered to the general public at no
+     charge under subsection 6d.
+ .
+   A separable portion of the object code, whose source code is excluded
+ from the Corresponding Source as a System Library, need not be
+ included in conveying the object code work.
+ .
+   A "User Product" is either (1) a "consumer product", which means any
+ tangible personal property which is normally used for personal, family,
+ or household purposes, or (2) anything designed or sold for incorporation
+ into a dwelling.  In determining whether a product is a consumer product,
+ doubtful cases shall be resolved in favor of coverage.  For a particular
+ product received by a particular user, "normally used" refers to a
+ typical or common use of that class of product, regardless of the status
+ of the particular user or of the way in which the particular user
+ actually uses, or expects or is expected to use, the product.  A product
+ is a consumer product regardless of whether the product has substantial
+ commercial, industrial or non-consumer uses, unless such uses represent
+ the only significant mode of use of the product.
+ .
+   "Installation Information" for a User Product means any methods,
+ procedures, authorization keys, or other information required to install
+ and execute modified versions of a covered work in that User Product from
+ a modified version of its Corresponding Source.  The information must
+ suffice to ensure that the continued functioning of the modified object
+ code is in no case prevented or interfered with solely because
+ modification has been made.
+ .
+   If you convey an object code work under this section in, or with, or
+ specifically for use in, a User Product, and the conveying occurs as
+ part of a transaction in which the right of possession and use of the
+ User Product is transferred to the recipient in perpetuity or for a
+ fixed term (regardless of how the transaction is characterized), the
+ Corresponding Source conveyed under this section must be accompanied
+ by the Installation Information.  But this requirement does not apply
+ if neither you nor any third party retains the ability to install
+ modified object code on the User Product (for example, the work has
+ been installed in ROM).
+ .
+   The requirement to provide Installation Information does not include a
+ requirement to continue to provide support service, warranty, or updates
+ for a work that has been modified or installed by the recipient, or for
+ the User Product in which it has been modified or installed.  Access to a
+ network may be denied when the modification itself materially and
+ adversely affects the operation of the network or violates the rules and
+ protocols for communication across the network.
+ .
+   Corresponding Source conveyed, and Installation Information provided,
+ in accord with this section must be in a format that is publicly
+ documented (and with an implementation available to the public in
+ source code form), and must require no special password or key for
+ unpacking, reading or copying.
+ .
+   7. Additional Terms.
+ .
+   "Additional permissions" are terms that supplement the terms of this
+ License by making exceptions from one or more of its conditions.
+ Additional permissions that are applicable to the entire Program shall
+ be treated as though they were included in this License, to the extent
+ that they are valid under applicable law.  If additional permissions
+ apply only to part of the Program, that part may be used separately
+ under those permissions, but the entire Program remains governed by
+ this License without regard to the additional permissions.
+ .
+   When you convey a copy of a covered work, you may at your option
+ remove any additional permissions from that copy, or from any part of
+ it.  (Additional permissions may be written to require their own
+ removal in certain cases when you modify the work.)  You may place
+ additional permissions on material, added by you to a covered work,
+ for which you have or can give appropriate copyright permission.
+ .
+   Notwithstanding any other provision of this License, for material you
+ add to a covered work, you may (if authorized by the copyright holders of
+ that material) supplement the terms of this License with terms:
+ .
+     a) Disclaiming warranty or limiting liability differently from the
+     terms of sections 15 and 16 of this License; or
+ .
+     b) Requiring preservation of specified reasonable legal notices or
+     author attributions in that material or in the Appropriate Legal
+     Notices displayed by works containing it; or
+ .
+     c) Prohibiting misrepresentation of the origin of that material, or
+     requiring that modified versions of such material be marked in
+     reasonable ways as different from the original version; or
+ .
+     d) Limiting the use for publicity purposes of names of licensors or
+     authors of the material; or
+ .
+     e) Declining to grant rights under trademark law for use of some
+     trade names, trademarks, or service marks; or
+ .
+     f) Requiring indemnification of licensors and authors of that
+     material by anyone who conveys the material (or modified versions of
+     it) with contractual assumptions of liability to the recipient, for
+     any liability that these contractual assumptions directly impose on
+     those licensors and authors.
+ .
+   All other non-permissive additional terms are considered "further
+ restrictions" within the meaning of section 10.  If the Program as you
+ received it, or any part of it, contains a notice stating that it is
+ governed by this License along with a term that is a further
+ restriction, you may remove that term.  If a license document contains
+ a further restriction but permits relicensing or conveying under this
+ License, you may add to a covered work material governed by the terms
+ of that license document, provided that the further restriction does
+ not survive such relicensing or conveying.
+ .
+   If you add terms to a covered work in accord with this section, you
+ must place, in the relevant source files, a statement of the
+ additional terms that apply to those files, or a notice indicating
+ where to find the applicable terms.
+ .
+   Additional terms, permissive or non-permissive, may be stated in the
+ form of a separately written license, or stated as exceptions;
+ the above requirements apply either way.
+ .
+   8. Termination.
+ .
+   You may not propagate or modify a covered work except as expressly
+ provided under this License.  Any attempt otherwise to propagate or
+ modify it is void, and will automatically terminate your rights under
+ this License (including any patent licenses granted under the third
+ paragraph of section 11).
+ .
+   However, if you cease all violation of this License, then your
+ license from a particular copyright holder is reinstated (a)
+ provisionally, unless and until the copyright holder explicitly and
+ finally terminates your license, and (b) permanently, if the copyright
+ holder fails to notify you of the violation by some reasonable means
+ prior to 60 days after the cessation.
+ .
+   Moreover, your license from a particular copyright holder is
+ reinstated permanently if the copyright holder notifies you of the
+ violation by some reasonable means, this is the first time you have
+ received notice of violation of this License (for any work) from that
+ copyright holder, and you cure the violation prior to 30 days after
+ your receipt of the notice.
+ .
+   Termination of your rights under this section does not terminate the
+ licenses of parties who have received copies or rights from you under
+ this License.  If your rights have been terminated and not permanently
+ reinstated, you do not qualify to receive new licenses for the same
+ material under section 10.
+ .
+   9. Acceptance Not Required for Having Copies.
+ .
+   You are not required to accept this License in order to receive or
+ run a copy of the Program.  Ancillary propagation of a covered work
+ occurring solely as a consequence of using peer-to-peer transmission
+ to receive a copy likewise does not require acceptance.  However,
+ nothing other than this License grants you permission to propagate or
+ modify any covered work.  These actions infringe copyright if you do
+ not accept this License.  Therefore, by modifying or propagating a
+ covered work, you indicate your acceptance of this License to do so.
+ .
+   10. Automatic Licensing of Downstream Recipients.
+ .
+   Each time you convey a covered work, the recipient automatically
+ receives a license from the original licensors, to run, modify and
+ propagate that work, subject to this License.  You are not responsible
+ for enforcing compliance by third parties with this License.
+ .
+   An "entity transaction" is a transaction transferring control of an
+ organization, or substantially all assets of one, or subdividing an
+ organization, or merging organizations.  If propagation of a covered
+ work results from an entity transaction, each party to that
+ transaction who receives a copy of the work also receives whatever
+ licenses to the work the party's predecessor in interest had or could
+ give under the previous paragraph, plus a right to possession of the
+ Corresponding Source of the work from the predecessor in interest, if
+ the predecessor has it or can get it with reasonable efforts.
+ .
+   You may not impose any further restrictions on the exercise of the
+ rights granted or affirmed under this License.  For example, you may
+ not impose a license fee, royalty, or other charge for exercise of
+ rights granted under this License, and you may not initiate litigation
+ (including a cross-claim or counterclaim in a lawsuit) alleging that
+ any patent claim is infringed by making, using, selling, offering for
+ sale, or importing the Program or any portion of it.
+ .
+   11. Patents.
+ .
+   A "contributor" is a copyright holder who authorizes use under this
+ License of the Program or a work on which the Program is based.  The
+ work thus licensed is called the contributor's "contributor version".
+ .
+   A contributor's "essential patent claims" are all patent claims
+ owned or controlled by the contributor, whether already acquired or
+ hereafter acquired, that would be infringed by some manner, permitted
+ by this License, of making, using, or selling its contributor version,
+ but do not include claims that would be infringed only as a
+ consequence of further modification of the contributor version.  For
+ purposes of this definition, "control" includes the right to grant
+ patent sublicenses in a manner consistent with the requirements of
+ this License.
+ .
+   Each contributor grants you a non-exclusive, worldwide, royalty-free
+ patent license under the contributor's essential patent claims, to
+ make, use, sell, offer for sale, import and otherwise run, modify and
+ propagate the contents of its contributor version.
+ .
+   In the following three paragraphs, a "patent license" is any express
+ agreement or commitment, however denominated, not to enforce a patent
+ (such as an express permission to practice a patent or covenant not to
+ sue for patent infringement).  To "grant" such a patent license to a
+ party means to make such an agreement or commitment not to enforce a
+ patent against the party.
+ .
+   If you convey a covered work, knowingly relying on a patent license,
+ and the Corresponding Source of the work is not available for anyone
+ to copy, free of charge and under the terms of this License, through a
+ publicly available network server or other readily accessible means,
+ then you must either (1) cause the Corresponding Source to be so
+ available, or (2) arrange to deprive yourself of the benefit of the
+ patent license for this particular work, or (3) arrange, in a manner
+ consistent with the requirements of this License, to extend the patent
+ license to downstream recipients.  "Knowingly relying" means you have
+ actual knowledge that, but for the patent license, your conveying the
+ covered work in a country, or your recipient's use of the covered work
+ in a country, would infringe one or more identifiable patents in that
+ country that you have reason to believe are valid.
+ .
+   If, pursuant to or in connection with a single transaction or
+ arrangement, you convey, or propagate by procuring conveyance of, a
+ covered work, and grant a patent license to some of the parties
+ receiving the covered work authorizing them to use, propagate, modify
+ or convey a specific copy of the covered work, then the patent license
+ you grant is automatically extended to all recipients of the covered
+ work and works based on it.
+ .
+   A patent license is "discriminatory" if it does not include within
+ the scope of its coverage, prohibits the exercise of, or is
+ conditioned on the non-exercise of one or more of the rights that are
+ specifically granted under this License.  You may not convey a covered
+ work if you are a party to an arrangement with a third party that is
+ in the business of distributing software, under which you make payment
+ to the third party based on the extent of your activity of conveying
+ the work, and under which the third party grants, to any of the
+ parties who would receive the covered work from you, a discriminatory
+ patent license (a) in connection with copies of the covered work
+ conveyed by you (or copies made from those copies), or (b) primarily
+ for and in connection with specific products or compilations that
+ contain the covered work, unless you entered into that arrangement,
+ or that patent license was granted, prior to 28 March 2007.
+ .
+   Nothing in this License shall be construed as excluding or limiting
+ any implied license or other defenses to infringement that may
+ otherwise be available to you under applicable patent law.
+ .
+   12. No Surrender of Others' Freedom.
+ .
+   If conditions are imposed on you (whether by court order, agreement or
+ otherwise) that contradict the conditions of this License, they do not
+ excuse you from the conditions of this License.  If you cannot convey a
+ covered work so as to satisfy simultaneously your obligations under this
+ License and any other pertinent obligations, then as a consequence you may
+ not convey it at all.  For example, if you agree to terms that obligate you
+ to collect a royalty for further conveying from those to whom you convey
+ the Program, the only way you could satisfy both those terms and this
+ License would be to refrain entirely from conveying the Program.
+ .
+   13. Remote Network Interaction; Use with the GNU General Public License.
+ .
+   Notwithstanding any other provision of this License, if you modify the
+ Program, your modified version must prominently offer all users
+ interacting with it remotely through a computer network (if your version
+ supports such interaction) an opportunity to receive the Corresponding
+ Source of your version by providing access to the Corresponding Source
+ from a network server at no charge, through some standard or customary
+ means of facilitating copying of software.  This Corresponding Source
+ shall include the Corresponding Source for any work covered by version 3
+ of the GNU General Public License that is incorporated pursuant to the
+ following paragraph.
+ .
+   Notwithstanding any other provision of this License, you have
+ permission to link or combine any covered work with a work licensed
+ under version 3 of the GNU General Public License into a single
+ combined work, and to convey the resulting work.  The terms of this
+ License will continue to apply to the part which is the covered work,
+ but the work with which it is combined will remain governed by version
+ 3 of the GNU General Public License.
+ .
+   14. Revised Versions of this License.
+ .
+   The Free Software Foundation may publish revised and/or new versions of
+ the GNU Affero General Public License from time to time.  Such new versions
+ will be similar in spirit to the present version, but may differ in detail to
+ address new problems or concerns.
+ .
+   Each version is given a distinguishing version number.  If the
+ Program specifies that a certain numbered version of the GNU Affero General
+ Public License "or any later version" applies to it, you have the
+ option of following the terms and conditions either of that numbered
+ version or of any later version published by the Free Software
+ Foundation.  If the Program does not specify a version number of the
+ GNU Affero General Public License, you may choose any version ever published
+ by the Free Software Foundation.
+ .
+   If the Program specifies that a proxy can decide which future
+ versions of the GNU Affero General Public License can be used, that proxy's
+ public statement of acceptance of a version permanently authorizes you
+ to choose that version for the Program.
+ .
+   Later license versions may give you additional or different
+ permissions.  However, no additional obligations are imposed on any
+ author or copyright holder as a result of your choosing to follow a
+ later version.
+ .
+   15. Disclaimer of Warranty.
+ .
+   THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+ APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+ HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+ OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+ THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+ PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+ IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+ .
+   16. Limitation of Liability.
+ .
+   IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+ WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+ THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+ GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+ USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+ DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+ PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+ EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+ SUCH DAMAGES.
+ .
+   17. Interpretation of Sections 15 and 16.
+ .
+   If the disclaimer of warranty and limitation of liability provided
+ above cannot be given local legal effect according to their terms,
+ reviewing courts shall apply local law that most closely approximates
+ an absolute waiver of all civil liability in connection with the
+ Program, unless a warranty or assumption of liability accompanies a
+ copy of the Program in return for a fee.
+ .
+                      END OF TERMS AND CONDITIONS
+ .
+             How to Apply These Terms to Your New Programs
+ .
+   If you develop a new program, and you want it to be of the greatest
+ possible use to the public, the best way to achieve this is to make it
+ free software which everyone can redistribute and change under these terms.
+ .
+   To do so, attach the following notices to the program.  It is safest
+ to attach them to the start of each source file to most effectively
+ state the exclusion of warranty; and each file should have at least
+ the "copyright" line and a pointer to where the full notice is found.
+ .
+     <one line to give the program's name and a brief idea of what it does.>
+     Copyright (C) <year>  <name of author>
+ .
+     This program is free software: you can redistribute it and/or modify
+     it under the terms of the GNU Affero 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 Affero General Public License for more details.
+ .
+     You should have received a copy of the GNU Affero General Public License
+     along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ .
+ Also add information on how to contact you by electronic and paper mail.
+ .
+   If your software can interact with users remotely through a computer
+ network, you should also make sure that it provides a way for users to
+ get its source.  For example, if your program is a web application, its
+ interface could display a "Source" link that leads users to an archive
+ of the code.  There are many ways you could offer source, and different
+ solutions will be better for different programs; see section 13 for the
+ specific requirements.
+ .
+   You should also get your employer (if you work as a programmer) or school,
+ if any, to sign a "copyright disclaimer" for the program, if necessary.
+ For more information on this, and how to apply and follow the GNU AGPL, see
+ <http://www.gnu.org/licenses/>.
+
 License: Expat
  Permission is hereby granted, free of charge, to any person obtaining
  a copy of this software and associated documentation files (the

docs/advanced.rst

@@ -125,8 +125,7 @@ include:
 .. envvar:: OMP_THREAD_LIMIT
 
    Controls the number of threads Tesseract will use. OCRmyPDF will
-   manage this environment if it is not already set. (Currently, it will
-   set it to 1 because this gives the best results in testing.)
+   manage this environment variable if it is not already set.
 
 For example, if you have a development build of Tesseract don't wish to
 use the system installation, you can launch OCRmyPDF as follows:
@@ -229,8 +228,8 @@ preprocessing is specified, then the image layer is a new PDF.
 Unlike ``sandwich`` this renderer is implemented within OCRmyPDF; anyone
 looking to customize how OCR is presented should look here. A major
 disadvantage of this renderer is it not capable of correctly handling
-text outside the Latin alphabet. Pull requests to improve the situation
-are welcome.
+text outside the Latin alphabet (specifically, it supports the ISO 8859-1
+character). Pull requests to improve the situation are welcome.
 
 Currently, this renderer has the best compatibility with Mozilla's
 PDF.js viewer.
@@ -315,7 +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

@@ -12,7 +12,7 @@ subprocess call anyway, as this provides isolation of its activities.
 Example
 =======
 
-OCRmyPDF one high-level function to run its main engine from an
+OCRmyPDF provides one high-level function to run its main engine from an
 application. The parameters are symmetric to the command line arguments
 and largely have the same functions.
 
@@ -20,9 +20,10 @@ and largely have the same functions.
 
     import ocrmypdf
 
-    ocrmypdf.ocr('input.pdf', 'output.pdf', deskew=True)
+    if __name__ == '__main__':  # To ensure correct behavior on Windows and macOS
+        ocrmypdf.ocr('input.pdf', 'output.pdf', deskew=True)
 
-With a few exceptions, all of the command line arguments are available
+With some exceptions, all of the command line arguments are available
 and may be passed as equivalent keywords.
 
 A few differences are that ``verbose`` and ``quiet`` are not available.
@@ -35,29 +36,37 @@ The :func:`ocrmypdf.ocr` function runs OCRmyPDF similar to command line
 execution. To do this, it will:
 
 - create a monitoring thread
-- create worker processes (forking itself)
-- manage the signal flags of worker processes
+- create worker processes (on Linux, forking itself; on Windows and macOS, by
+  spawning)
+- manage the signal flags of its worker processes
 - execute other subprocesses (forking and executing other programs)
 
-The Python process that calls ``ocrmypdf.ocr()`` must be sufficiently
-privileged to perform these actions. If it is not, ``ocrmypdf()`` will
-fail.
+The Python process that calls :func:`ocrmypdf.ocr()` must be sufficiently
+privileged to perform these actions.
 
-There is no currently no option to manage how jobs are scheduled other
+There currently is no option to manage how jobs are scheduled other
 than the argument ``jobs=`` which will limit the number of worker
 processes.
 
-Forking a child process to call ``ocrmypdf.ocr()`` is suggested. That
+Creating a child process to call :func:`ocrmypdf.ocr()` is suggested. That
 way your application will survive and remain interactive even if
-OCRmyPDF does not.
+OCRmyPDF fails for any reason.
+
+Programs that call :func:`ocrmypdf.ocr()` should also install a SIGBUS signal
+handler (except on Windows), to raise an exception if access to a memory
+mapped file fails. OCRmyPDF may use memory mapping.
+
+:func:`ocrmypdf.ocr()` will take a threading lock to prevent multiple runs of itself
+in the same Python interpreter process. This is not thread-safe, because of how
+OCRmyPDF's plugins and Python's library import system work. If you need to parallelize
+OCRmyPDF, use processes.
 
 .. warning::
 
-    On Windows, the script that calls ``ocrmypdf.ocr()`` must be protected
-    by an "ifmain" guard (``if __name__ == '__main__'``) or you must use
-    ``ocrmypdf.ocr(...use_threads=True)``. If you do not take at least one
-    of these steps, Windows process semantics will prevent OCRmyPDF from working
-    correctly.
+    On Windows and macOS, the script that calls :func:`ocrmypdf.ocr()` must be
+    protected by an "ifmain" guard (``if __name__ == '__main__'``). If you do
+    not take at least one of these steps, process semantics will prevent
+    OCRmyPDF from working correctly.
 
 Logging
 -------
@@ -87,7 +96,7 @@ Exceptions
 
 OCRmyPDF may throw standard Python exceptions, ``ocrmypdf.exceptions.*``
 exceptions, some exceptions related to multiprocessing, and
-``KeyboardInterrupt``. The parent process should provide an exception
+:exc:`KeyboardInterrupt`. The parent process should provide an exception
 handler. OCRmyPDF will clean up its temporary files and worker processes
 automatically when an exception occurs.
 
@@ -106,7 +115,3 @@ Reference
     :undoc-members:
 
 .. autofunction:: ocrmypdf.configure_logging
-
-.. automodule:: ocrmypdf.exceptions
-    :members:
-    :undoc-members:

docs/apiref.rst

@@ -0,0 +1,55 @@
+=============
+API Reference
+=============
+
+This page summarizes the rest of the public API. Generally speaking this
+should mainly of interest to plugin developers.
+
+ocrmypdf
+========
+
+.. autoclass:: ocrmypdf.PageContext
+    :members:
+
+.. autoclass:: ocrmypdf.PdfContext
+    :members:
+
+ocrmypdf.exceptions
+===================
+
+.. automodule:: ocrmypdf.exceptions
+    :members:
+    :undoc-members:
+
+ocrmypdf.helpers
+================
+
+.. automodule:: ocrmypdf.helpers
+    :members:
+    :noindex: deprecated
+
+    .. autodecorator:: deprecated
+
+ocrmypdf.hocrtransform
+======================
+
+.. automodule:: ocrmypdf.hocrtransform
+    :members:
+
+ocrmypdf.pdfa
+=============
+
+.. automodule:: ocrmypdf.pdfa
+    :members:
+
+ocrmypdf.quality
+================
+
+.. automodule:: ocrmypdf.quality
+    :members:
+
+ocrmypdf.subprocess
+===================
+
+.. automodule:: ocrmypdf.subprocess
+    :members:

docs/batch.rst

@@ -111,7 +111,7 @@ Users may need to customize the script to meet their requirements.
 
 .. code-block:: bash
 
-    pip3 install -r requirements/watcher.txt
+    pip3 install ocrmypdf[watcher]
 
     env OCR_INPUT_DIRECTORY=/mnt/input-pdfs \
         OCR_OUTPUT_DIRECTORY=/mnt/output-pdfs \
@@ -127,7 +127,7 @@ Users may need to customize the script to meet their requirements.
     "OCR_ON_SUCCESS_DELETE", "This will delete the input file if the exit code is 0 (OK)"
     "OCR_OUTPUT_DIRECTORY_YEAR_MONTH", "This will place files in the output in ``{output}/{year}/{month}/{filename}``"
     "OCR_DESKEW", "Apply deskew to crooked input PDFs"
-    "OCR_JSON_SETTINGS", "A JSON string specifying any other arguments for ``ocrmypdf.ocr``"
+    "OCR_JSON_SETTINGS", "A JSON string specifying any other arguments for ``ocrmypdf.ocr``, e.g. ``'OCR_JSON_SETTINGS={""rotate_pages"": true}'``."
     "OCR_POLL_NEW_FILE_SECONDS", "Polling interval"
     "OCR_LOGLEVEL", "Level of log messages to report"
 
@@ -202,13 +202,6 @@ Alternatives
 -  `Watchman <https://facebook.github.io/watchman/>`__ is a more
    powerful alternative to ``watchmedo``.
 
-AWS Lambda is not viable
-------------------------
-
-AWS Lambda and its equivalents have low limits on execution time and payload
-size, relative to OCRmyPDF's needs. As of this writing, the request/response
-payload for AWS Lambda was 6 MB, which means many PDFs will not fit.
-
 macOS Automator
 ===============
 

docs/conf.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 #
 # ocrmypdf documentation build configuration file, created by
 # sphinx-quickstart on Sun Sep  4 14:29:43 2016.
@@ -21,6 +20,8 @@
 # import sys
 # sys.path.insert(0, os.path.abspath('.'))
 
+"""isort:skip_file"""
+
 # -- General configuration ------------------------------------------------
 
 # If your documentation needs a minimal Sphinx version, state it here.
@@ -30,7 +31,18 @@
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
-extensions = ['sphinx.ext.napoleon']
+extensions = [
+    'sphinx.ext.autodoc',
+    'sphinx.ext.intersphinx',
+    'sphinx.ext.autosummary',
+    'sphinx.ext.napoleon',
+    'sphinx_issues',
+]
+
+# Extension settings
+intersphinx_mapping = {'https://docs.python.org/': None}
+napoleon_use_rtype = False
+issues_github_path = "jbarlow83/OCRmyPDF"
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']
@@ -51,7 +63,7 @@ master_doc = 'index'
 # General information about the project.
 project = 'ocrmypdf'
 copyright = (
-    '2019, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
+    '2021, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
 )
 author = 'James R. Barlow'
 
@@ -83,13 +95,13 @@ if on_rtd:
     ]
     sys.modules.update((mod_name, Mock()) for mod_name in MOCK_MODULES)
 
-
-from pkg_resources import get_distribution, DistributionNotFound
+from importlib_metadata import version as package_version
 
 # The full version, including alpha/beta/rc tags.
-release = get_distribution('ocrmypdf').version
+release = package_version('ocrmypdf')
 version = '.'.join(release.split('.')[:2])
 
+
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
 #
@@ -174,7 +186,7 @@ html_theme_options = {'display_version': False}
 # The name of an image file (relative to this directory) to place at the top
 # of the sidebar.
 #
-# html_logo = None
+# html_logo = "images/logo.svg"  # looks bad
 
 # The name of an image file (relative to this directory) to use as a favicon of
 # the docs.  This file should be a Windows icon file (.ico) being 16x16 or 32x32
@@ -269,7 +281,7 @@ htmlhelp_basename = 'ocrmypdfdoc'
 
 # -- Options for LaTeX output ---------------------------------------------
 
-latex_elements = {
+latex_elements = {  # type: ignore
     # The paper size ('letterpaper' or 'a4paper').
     #
     # 'papersize': 'letterpaper',

docs/contributing.rst

@@ -32,7 +32,8 @@ If you are proposing a change that will require a new Python dependency, we
 prefer dependencies that are already packaged by Debian or Red Hat. This makes
 life much easier for our downstream package maintainers.
 
-Python dependencies must also be GPLv3 compatible.
+Python dependencies must also be license-compatible. GPLv3 or AGPLv3 are likely
+incompatible with the project's license, but LGPLv3 is compatible.
 
 New non-Python dependencies
 ===========================
@@ -55,3 +56,12 @@ of that platform.
 
 Packager maintainers, please ensure that the command line completion scripts in
 ``misc/`` are installed.
+
+Copyright and license
+=====================
+
+For contributions over 10 lines of code, please include your name to list of
+copyright holders for that file. The core program is licensed under MPL-2.0,
+test files and documentation under CC-BY-SA 4.0, and miscellaneous files under
+MIT. Please contribute code only that you wrote and you have the permission to
+contribute or license to us.

docs/cookbook.rst

@@ -58,9 +58,11 @@ portrait pages.
 You can increase (decrease) the parameter ``--rotate-pages-threshold``
 to make page rotation more (less) aggressive. The threshold number is the ratio
 of how confidence the OCR engine is that the document image should be changed,
-compared to kept the same. A value of ``15.0`` is the default, and is fairly
-conservative. A value of ``2.0`` will produce more rotations, and more false
-positives.
+compared to kept the same. The default value is quite conservative; on some files
+it may not attempt rotations at all unless it is very confident that the current
+rotation is wrong. A lower value of ``2.0`` will produce more rotations, and
+more false positives. Run with ``-v1`` to see the confidence level for each
+page to see if there may be a better value for your files.
 
 If the page is "just a little off horizontal", like a crooked picture,
 then you want ``--deskew``. ``--rotate-pages`` is for when the cardinal

docs/docker.rst

@@ -1,3 +1,5 @@
+.. _docker:
+
 =====================
 OCRmyPDF Docker image
 =====================
@@ -101,16 +103,41 @@ Adding languages to the Docker image
 By default the Docker image includes English, German, Simplified Chinese,
 French, Portuguese and Spanish, the most popular languages for OCRmyPDF
 users based on feedback. You may add other languages by creating a new
-Dockerfile based on the public one:
+Dockerfile based on the public one.
 
 .. code-block:: dockerfile
 
    FROM jbarlow83/ocrmypdf
 
-   # Add French
-   RUN apt install tesseract-ocr-fra
+   # Example: add Italian
+   RUN apt install tesseract-ocr-ita
 
-You can also copy training data to ``/usr/share/tesseract-ocr/<tesseract version>/tessdata``.
+To install language packs (training data) such as the 
+`tessdata_best <https://github.com/tesseract-ocr/tessdata_best>`_ suite or
+custom data, you first need to determine the version of Tesseract data files, which
+may differ from the Tesseract program version. Use this command to determine the data
+file version:
+
+.. code-block:: bash
+
+   docker run -i --rm --entrypoint /bin/ls jbarlow83/ocrmypdf /usr/share/tesseract-ocr
+
+As of 2021, the data file version is probably ``4.00``.
+
+You can then add new data with either a Dockerfile:
+
+.. code-block:: dockerfile
+
+   FROM jbarlow83/ocrmypdf
+
+   # Example: add a tessdata_best file
+   COPY chi_tra_vert.traineddata /usr/share/tesseract-ocr/<data version>/tessdata/
+
+Alternately, you can copy training data into a Docker container as follows:
+
+.. code-block:: bash
+
+   docker cp mycustomtraining.traineddata name_of_container:/usr/share/tesseract-ocr/<tesseract version>/tessdata/
 
 Executing the test suite
 ========================
@@ -163,8 +190,7 @@ complete. This may entail setting a long timeout; this interface is more
 useful for internal HTTP API calls.
 
 Unlike the rest of OCRmyPDF, this web service is licensed under the
-Affero GPLv3 (AGPLv3) since Ghostscript, a dependency of OCRmyPDF, is
-also licensed in this way.
+Affero GPLv3 (AGPLv3) since Ghostscript is also licensed in this way.
 
 In addition to the above, please read our
 :ref:`general remarks on using OCRmyPDF as a service <ocr-service>`.

docs/images/logo-square.svg

@@ -0,0 +1,233 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   xmlns:serif="http://www.serif.com/"
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   width="503"
+   height="503"
+   viewBox="0 0 503 503"
+   version="1.1"
+   xml:space="preserve"
+   style="clip-rule:evenodd;fill-rule:evenodd;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:1.5"
+   id="svg270"
+   sodipodi:docname="logo-square.svg"
+   inkscape:export-filename="/home/jb/src/ocrmypdf/docs/images/logo-square.png"
+   inkscape:export-xdpi="96"
+   inkscape:export-ydpi="96"
+   inkscape:version="1.0.2 (e86c870879, 2021-01-15)"><metadata
+   id="metadata276"><rdf:RDF><cc:Work
+       rdf:about=""><dc:format>image/svg+xml</dc:format><dc:type
+         rdf:resource="http://purl.org/dc/dcmitype/StillImage" /><dc:title></dc:title></cc:Work></rdf:RDF></metadata><defs
+   id="defs274" /><sodipodi:namedview
+   pagecolor="#ffffff"
+   bordercolor="#666666"
+   borderopacity="1"
+   objecttolerance="10"
+   gridtolerance="10"
+   guidetolerance="10"
+   inkscape:pageopacity="0"
+   inkscape:pageshadow="2"
+   inkscape:window-width="2396"
+   inkscape:window-height="1691"
+   id="namedview272"
+   showgrid="false"
+   lock-margins="false"
+   inkscape:zoom="2.0079523"
+   inkscape:cx="251.5"
+   inkscape:cy="193.18317"
+   inkscape:window-x="26"
+   inkscape:window-y="23"
+   inkscape:window-maximized="0"
+   inkscape:current-layer="svg270" />
+    <g
+   id="svg"
+   transform="matrix(0.965977,0,0,0.807602,0,138.43572)">
+        <rect
+   x="0"
+   y="0"
+   width="520"
+   height="280"
+   style="fill:#ffffff"
+   id="rect188" />
+        <g
+   transform="matrix(1.03522,0,0,1.23823,-69.7528,-83.422)"
+   id="g267">
+            <g
+   transform="translate(243.977,20.0703)"
+   id="g218">
+                <g
+   id="Page">
+                    <g
+   transform="matrix(0.961773,0,0,1.05962,6.19811,-3.01071)"
+   id="g192">
+                        <path
+   d="m 328.5,97.682 c 0,-1.217 -0.517,-2.386 -1.444,-3.264 -7.03,-6.66 -37.614,-35.638 -44.828,-42.474 -0.977,-0.925 -2.327,-1.448 -3.738,-1.448 -13.997,0 -90.407,0 -111.151,0 -2.871,0 -5.198,2.113 -5.198,4.718 0,27.837 0,170.351 0,198.186 0,2.605 2.327,4.717 5.197,4.717 24.904,0 131.821,0 156.2,0 2.74,0 4.962,-2.016 4.962,-4.504 0,-24.345 0,-139.717 0,-155.931 z"
+   style="fill:#fdfdfd;stroke:#333333;stroke-width:3.95px"
+   id="path190" />
+                    </g>
+                    <g
+   id="Dog-ear"
+   serif:id="Dog ear"
+   transform="translate(-4,2)">
+                        <path
+   d="m 277.072,48.496 v 45.352 c 0,1.324 0.526,2.593 1.462,3.529 0.936,0.936 2.205,1.462 3.529,1.462 12.485,0 44.078,0 44.078,0"
+   style="fill:#f5f5f5;stroke:#333333;stroke-width:4px"
+   id="path194" />
+                    </g>
+                </g>
+                <g
+   transform="translate(-29.6816,-0.395178)"
+   id="g216">
+                    <g
+   transform="matrix(1.00243,0,0,1.11818,-144.72,-8.80181)"
+   id="g200">
+                        <path
+   d="m 465.73,119.654 c 0,-2.049 -1.856,-3.713 -4.142,-3.713 H 310.259 c -2.286,0 -4.142,1.664 -4.142,3.713 v 63.454 c 0,2.049 1.856,3.713 4.142,3.713 h 151.329 c 2.286,0 4.142,-1.664 4.142,-3.713 z"
+   style="fill:#f80000;stroke:#ffffff;stroke-width:3.77px"
+   id="path198" />
+                    </g>
+                    <g
+   transform="matrix(1.24571,0,0,1.35864,116.812,84.3924)"
+   id="g214">
+                        <g
+   transform="matrix(64,0,0,64,42.1437,77.6203)"
+   id="g204">
+                            <path
+   d="m 0.084,0 v -0.68 h 0.213 c 0.074,0 0.137,0.017 0.19,0.05 0.053,0.034 0.079,0.09 0.079,0.168 0,0.077 -0.028,0.134 -0.085,0.17 -0.057,0.037 -0.121,0.055 -0.193,0.055 H 0.213 V 0 Z m 0.209,-0.572 h -0.08 v 0.228 h 0.082 c 0.039,0 0.07,-0.009 0.094,-0.027 0.024,-0.017 0.037,-0.045 0.04,-0.083 0,-0.044 -0.012,-0.075 -0.036,-0.092 -0.024,-0.017 -0.057,-0.026 -0.1,-0.026 z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path202" />
+                        </g>
+                        <g
+   transform="matrix(64,0,0,64,79.7117,77.6203)"
+   id="g208">
+                            <path
+   d="M 0.332,0 H 0.084 v -0.68 h 0.252 c 0.105,0 0.182,0.032 0.233,0.095 0.051,0.063 0.076,0.144 0.076,0.241 0,0.105 -0.027,0.189 -0.082,0.251 C 0.508,-0.031 0.431,0 0.332,0 Z M 0.337,-0.57 H 0.213 v 0.461 H 0.33 c 0.055,0 0.099,-0.018 0.132,-0.054 C 0.495,-0.199 0.511,-0.259 0.511,-0.344 0.511,-0.415 0.497,-0.47 0.469,-0.51 0.441,-0.55 0.397,-0.57 0.337,-0.57 Z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path206" />
+                        </g>
+                        <g
+   transform="matrix(64,0,0,64,123.424,77.6203)"
+   id="g212">
+                            <path
+   d="M 0.405,-0.288 H 0.213 V 0 H 0.084 v -0.68 h 0.385 l 0.02,0.102 H 0.213 v 0.189 h 0.173 z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path210" />
+                        </g>
+                    </g>
+                </g>
+            </g>
+            <g
+   transform="matrix(1,0,0,1.52217,67.3796,10.7507)"
+   id="g222">
+                <rect
+   x="23.500999"
+   y="81.300003"
+   width="162.30499"
+   height="61.77"
+   style="fill:#b4d5ff"
+   id="rect220" />
+            </g>
+            <g
+   transform="matrix(0.967536,0,0,0.961535,5.90498,47.9703)"
+   id="g236">
+                <g
+   transform="matrix(90.4804,0,0,90.4804,82.6698,167.705)"
+   id="g226">
+                    <path
+   d="m 0.057,-0.337 c 0,-0.105 0.027,-0.19 0.082,-0.257 0.055,-0.066 0.132,-0.1 0.231,-0.102 0.107,0 0.186,0.034 0.237,0.103 0.051,0.069 0.077,0.152 0.077,0.249 0,0.105 -0.027,0.191 -0.082,0.258 -0.055,0.067 -0.133,0.1 -0.232,0.1 C 0.264,0.014 0.185,-0.02 0.134,-0.089 0.083,-0.157 0.057,-0.24 0.057,-0.337 Z m 0.135,-0.001 c 0,0.071 0.014,0.13 0.043,0.175 0.029,0.045 0.073,0.068 0.134,0.068 0.055,0 0.098,-0.02 0.131,-0.061 0.033,-0.041 0.049,-0.103 0.049,-0.188 0,-0.071 -0.014,-0.129 -0.043,-0.174 -0.029,-0.045 -0.073,-0.068 -0.134,-0.068 -0.053,0 -0.097,0.022 -0.13,0.067 -0.033,0.045 -0.05,0.105 -0.05,0.181 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path224" />
+                </g>
+                <g
+   transform="matrix(90.4804,0,0,90.4804,147.906,167.705)"
+   id="g230">
+                    <path
+   d="M 0.505,-0.557 C 0.473,-0.567 0.448,-0.574 0.429,-0.579 0.41,-0.583 0.388,-0.585 0.361,-0.585 c -0.054,0 -0.096,0.022 -0.125,0.066 -0.029,0.044 -0.044,0.104 -0.044,0.181 0,0.066 0.012,0.123 0.037,0.171 0.025,0.048 0.066,0.072 0.124,0.072 0.029,0 0.056,-0.003 0.081,-0.009 0.025,-0.006 0.047,-0.013 0.068,-0.022 L 0.551,-0.03 C 0.525,-0.017 0.494,-0.006 0.457,0.002 0.42,0.01 0.388,0.014 0.36,0.014 0.254,0.014 0.177,-0.02 0.129,-0.088 0.081,-0.156 0.057,-0.239 0.057,-0.337 c 0,-0.105 0.027,-0.19 0.08,-0.257 0.053,-0.067 0.129,-0.1 0.228,-0.1 0.02,0 0.048,0.003 0.083,0.01 0.035,0.007 0.068,0.018 0.097,0.034 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path228" />
+                </g>
+                <g
+   transform="matrix(90.4804,0,0,90.4804,199.751,167.705)"
+   id="g234">
+                    <path
+   d="m 0.293,-0.572 h -0.08 v 0.208 h 0.082 c 0.039,0 0.071,-0.008 0.096,-0.024 0.025,-0.015 0.038,-0.041 0.038,-0.077 0,-0.038 -0.012,-0.065 -0.036,-0.082 -0.024,-0.017 -0.057,-0.025 -0.1,-0.025 z M 0.479,0 0.335,-0.26 C 0.328,-0.259 0.32,-0.259 0.312,-0.259 0.304,-0.258 0.296,-0.258 0.288,-0.258 H 0.213 V 0 H 0.084 v -0.68 h 0.213 c 0.074,0 0.137,0.017 0.19,0.051 0.053,0.034 0.079,0.087 0.079,0.158 0,0.042 -0.011,0.078 -0.032,0.108 -0.022,0.031 -0.05,0.054 -0.084,0.071 L 0.617,0 Z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path232" />
+                </g>
+            </g>
+            <g
+   transform="matrix(0.916882,0,0,1,121.475,-32.6535)"
+   id="g246">
+                <g
+   transform="matrix(86.953,0,0,86.953,152.996,241.878)"
+   id="g240">
+                    <path
+   d="M 0.479,-0.428 C 0.5,-0.451 0.527,-0.47 0.562,-0.484 c 0.034,-0.013 0.065,-0.02 0.092,-0.02 0.066,0 0.113,0.019 0.141,0.058 0.027,0.039 0.041,0.086 0.041,0.142 V 0 H 0.705 v -0.298 c 0,-0.031 -0.007,-0.054 -0.022,-0.071 -0.015,-0.016 -0.036,-0.024 -0.064,-0.024 -0.019,0 -0.038,0.005 -0.059,0.015 -0.021,0.01 -0.039,0.021 -0.056,0.034 0.001,0.007 0.001,0.013 0.002,0.02 0.001,0.007 0.001,0.013 0.001,0.02 V 0 H 0.376 v -0.298 c 0,-0.031 -0.007,-0.054 -0.022,-0.071 -0.015,-0.016 -0.036,-0.024 -0.063,-0.024 -0.017,0 -0.033,0.003 -0.05,0.01 -0.017,0.007 -0.034,0.016 -0.049,0.027 V 0 H 0.062 V -0.485 H 0.13 l 0.032,0.044 c 0.022,-0.02 0.049,-0.035 0.08,-0.047 0.031,-0.011 0.058,-0.016 0.083,-0.016 0.038,0 0.07,0.007 0.095,0.02 0.025,0.014 0.045,0.033 0.059,0.056 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path238" />
+                </g>
+                <g
+   transform="matrix(86.953,0,0,86.953,228.906,241.878)"
+   id="g244">
+                    <path
+   d="M 0.156,0.023 0.179,-0.034 0.006,-0.467 0.14,-0.485 0.252,-0.191 0.358,-0.485 H 0.495 L 0.278,0.064 C 0.263,0.103 0.236,0.137 0.197,0.165 0.158,0.193 0.118,0.212 0.075,0.222 L 0.029,0.115 C 0.052,0.105 0.077,0.093 0.104,0.079 0.13,0.064 0.147,0.046 0.156,0.023 Z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path242" />
+                </g>
+            </g>
+            <g
+   id="Selectors"
+   transform="matrix(0.965977,0,0,0.807602,67.3796,67.3718)">
+                <g
+   id="Right-selector"
+   serif:id="Right selector">
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,2.07044,0)"
+   id="g250">
+                        <path
+   d="M 185.806,161.156 V 67.132"
+   style="fill:none;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="path248" />
+                    </g>
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,161.788,169.469)"
+   id="g254">
+                        <circle
+   cx="31.523001"
+   cy="34.313999"
+   r="10.021"
+   style="fill:#4c9fff;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="circle252" />
+                    </g>
+                </g>
+                <g
+   id="Left-selector"
+   serif:id="Left selector">
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,-170.092,0)"
+   id="g259">
+                        <path
+   d="M 185.806,161.156 V 67.132"
+   style="fill:none;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="path257" />
+                    </g>
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,-10.3742,28.2274)"
+   id="g263">
+                        <circle
+   cx="31.523001"
+   cy="34.313999"
+   r="10.021"
+   style="fill:#4c9fff;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="circle261" />
+                    </g>
+                </g>
+            </g>
+        </g>
+    </g>
+</svg>

docs/index.rst

@@ -1,7 +1,9 @@
 OCRmyPDF documentation
 ======================
 
-OCRmyPDF adds an optical charcter recognition (OCR) text layer to scanned PDF
+.. figure:: images/logo.svg
+
+OCRmyPDF adds an optical character recognition (OCR) text layer to scanned PDF
 files, allowing them to be searched.
 
 PDF is the best format for storing and exchanging scanned documents.
@@ -36,6 +38,7 @@ image processing and OCR to existing PDFs.
 
    api
    plugins
+   apiref
    contributing
 
 Indices and tables

docs/installation.rst

@@ -8,20 +8,28 @@ 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. This
-installation guide provides information allowing you to compare the current
-version to the one provided by your platform.
+system/platform. This version may be out of date, however.
 
-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``.
+These platforms have one-liner installs:
 
-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.
++-------------------------------+-------------------------------+
+| Debian, Ubuntu                | ``apt install ocrmypdf``      |
++-------------------------------+-------------------------------+
+| Windows Subsystem for Linux   | ``apt install ocrmypdf``      |
++-------------------------------+-------------------------------+
+| Fedora                        | ``dnf install ocrmypdf``      |
++-------------------------------+-------------------------------+
+| macOS                         | ``brew install ocrmypdf``     |
++-------------------------------+-------------------------------+
+| LinuxBrew                     | ``brew install ocrmypdf``     |
++-------------------------------+-------------------------------+
+| FreeBSD                       | ``pkg install py38-ocrmypdf`` |
++-------------------------------+-------------------------------+
+| Conda (WSL, macOS, Linux)     | ``conda install ocrmypdf``    |
++-------------------------------+-------------------------------+
+
+More detailed procedures are outlined below. If you want to do a manual
+install, or install a more recent version than your platform provides, read on.
 
 .. contents:: Platform-specific steps
     :depth: 2
@@ -48,6 +56,9 @@ Debian and Ubuntu 18.04 or newer
 .. |ubu-2004| image:: https://repology.org/badge/version-for-repo/ubuntu_20_04/ocrmypdf.svg
     :alt: Ubuntu 20.04 LTS
 
+.. |ubu-2010| image:: https://repology.org/badge/version-for-repo/ubuntu_20_10/ocrmypdf.svg
+    :alt: Ubuntu 20.10
+
 +-----------------------------------------------+
 | **OCRmyPDF versions in Debian & Ubuntu**      |
 +-----------------------------------------------+
@@ -55,10 +66,10 @@ Debian and Ubuntu 18.04 or newer
 +-----------------------------------------------+
 | |deb-stable| |deb-testing| |deb-unstable|     |
 +-----------------------------------------------+
-| |ubu-1804| |ubu-2004|                         |
+| |ubu-1804| |ubu-2004| |ubu-2010|              |
 +-----------------------------------------------+
 
-Users of Debian 9 ("stretch") or later or Ubuntu 18.04 or later, including users
+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
@@ -84,14 +95,14 @@ For full details on version availability for your platform, check the
    automatically detect it (specifically the ``jbig2`` binary) on the
    ``PATH``. To add JBIG2 encoding, see :ref:`jbig2`.
 
-Fedora 29 or newer
-------------------
+Fedora
+------
 
-.. |fedora-29| image:: https://repology.org/badge/version-for-repo/fedora_29/ocrmypdf.svg
-    :alt: Fedora 29
+.. |fedora-32| image:: https://repology.org/badge/version-for-repo/fedora_32/ocrmypdf.svg
+    :alt: Fedora 32
 
-.. |fedora-30| image:: https://repology.org/badge/version-for-repo/fedora_30/ocrmypdf.svg
-    :alt: Fedora 30
+.. |fedora-33| image:: https://repology.org/badge/version-for-repo/fedora_33/ocrmypdf.svg
+    :alt: Fedora 33
 
 .. |fedora-rawhide| image:: https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg
     :alt: Fedore Rawhide
@@ -101,7 +112,7 @@ Fedora 29 or newer
 +-----------------------------------------------+
 | |latest|                                      |
 +-----------------------------------------------+
-| |fedora-29| |fedora-30| |fedora-rawhide|      |
+| |fedora-32| |fedora-33| |fedora-rawhide|      |
 +-----------------------------------------------+
 
 Users of Fedora 29 or later may simply
@@ -152,7 +163,7 @@ To install ocrmypdf for the system:
 
 .. code-block:: bash
 
-    sudo pip3 install ocrmypdf
+    pip3 install ocrmypdf
 
 To install for the current user only:
 
@@ -162,7 +173,7 @@ To install for the current user only:
     pip3 install --user ocrmypdf
 
 Ubuntu 18.04 LTS
--------------------------------------------------
+----------------
 
 Ubuntu 18.04 includes ocrmypdf 6.1.2 - you can install that with ``apt``, but
 it is quite old now. To install a more recent version, uninstall the old version
@@ -184,7 +195,8 @@ of ocrmypdf, and install the following dependencies:
         python3-reportlab \
         qpdf \
         tesseract-ocr \
-        zlib1g
+        zlib1g \
+        unpaper
 
 We will need a newer version of ``pip`` then was available for Ubuntu 18.04:
 
@@ -265,68 +277,6 @@ environment variable contains ``$HOME/.local/bin``.
 
 To add JBIG2 encoding, see :ref:`jbig2`.
 
-Ubuntu 14.04 LTS
-----------------
-
-Installing on Ubuntu 14.04 LTS (trusty) is more difficult than some
-other options, because of its age. Several backports are required. For
-explanations of some steps of this procedure, see the similar steps for
-Ubuntu 16.04.
-
-Install system dependencies:
-
-.. code-block:: bash
-
-    sudo apt-get update
-    sudo apt-get install \
-        software-properties-common python-software-properties \
-        zlib1g-dev \
-        libexempi3 \
-        libjpeg-dev \
-        libffi-dev \
-        pngquant \
-        qpdf
-
-We will need backports of Ghostscript 9.16, libav-11 (for unpaper 6.1),
-Tesseract 4.00 (alpha), and Python 3.6. This will replace Ghostscript
-and Tesseract 3.x on your system. Python 3.6 will be installed alongside
-the system Python 3.4.
-
-If you prefer to not modify your system in this matter, consider using a
-Docker container.
-
-.. code-block:: bash
-
-    sudo add-apt-repository ppa:vshn/ghostscript -y
-    sudo add-apt-repository ppa:heyarje/libav-11 -y
-    sudo add-apt-repository ppa:alex-p/tesseract-ocr -y
-    sudo add-apt-repository ppa:jonathonf/python-3.6 -y
-
-    sudo apt-get update
-
-    sudo apt-get install \
-        python3.6-dev \
-        ghostscript \
-        tesseract-ocr \
-        tesseract-ocr-eng \
-        libavformat56 libavcodec56 libavutil54 \
-        wget
-
-Now we need to install ``pip`` and let it install ocrmypdf:
-
-.. code-block:: bash
-
-    curl https://bootstrap.pypa.io/ez_setup.py -o - | python3.6 && python3.6 -m easy_install pip
-    pip3.6 install ocrmypdf
-
-The optional dependency ``unpaper`` is only available at 0.4.2 in Ubuntu 14.04,
-and no backports are available. Previously the author maintained a backported
-.deb package for unpaper 6.1, but since Ubuntu 14.04 is now end of life, this is
-not supported. As such, ``unpaper`` is not available on Ubuntu 14.04 or must by
-compiled by hand.
-
-To add JBIG2 encoding, see :ref:`jbig2`.
-
 Arch Linux (AUR)
 ----------------
 
@@ -407,6 +357,48 @@ To install OCRmyPDF for Alpine Linux:
 
     apk add ocrmypdf
 
+Mageia 7
+--------
+
+There is no OS-level packaging available for Mageia, so you must install the
+dependencies:
+
+.. code-block:: bash
+
+    # As root user
+    urpmi.update -a
+    urpmi \
+        ghostscript \
+        icc-profiles-openicc \
+        jbig2dec \
+        lib64leptonica5 \
+        pngquant \
+        python3-pip \
+        python3-cffi \
+        python3-distutils-extra \
+        python3-pkg-resources \
+        python3-reportlab \
+        qpdf \
+        tesseract \
+        tesseract-osd \
+        tesseract-eng \
+        tesseract-fra
+
+To install ocrmypdf for the system:
+
+.. code-block:: bash
+
+    # As root user
+    pip3 install ocrmypdf
+    ldconfig
+
+Or, to install for the current user only:
+
+.. code-block:: bash
+
+    export PATH=$HOME/.local/bin:$PATH
+    pip3 install --user ocrmypdf
+
 Other Linux packages
 --------------------
 
@@ -472,7 +464,7 @@ Update Homebrew:
 
 Install or upgrade the required Homebrew packages, if any are missing.
 To do this, use ``brew edit ocrmypdf`` to obtain a recent list of Homebrew
-dependencies. You could also check the ``azure-pipelines.yml``.
+dependencies. You could also check the ``.workflows/build.yml``.
 
 This will include the English, French, German and Spanish language
 packs. If you need other languages you can optionally install them all:
@@ -507,40 +499,11 @@ The command line program should now be available:
 
     ocrmypdf --help
 
-Installing on FreeBSD
-=====================
-
-.. image:: https://repology.org/badge/version-for-repo/freebsd/python:ocrmypdf.svg
-    :alt: FreeBSD
-    :target: https://repology.org/project/python:ocrmypdf/versions
-
-FreeBSD 11.3, 12.0, 12.1-RELEASE and 13.0-CURRENT are supported. Other
-versions likely work but have not been tested.
-
-.. code-block:: bash
-
-    pkg install py37-ocrmypdf
-
-To install a more recent version, you could attempt to first install the system
-version with ``pkg``, then use ``pip install --user ocrmypdf``.
-
-Installing the Docker image
-===========================
-
-For some users, installing the Docker image will be easier than
-installing all of OCRmyPDF's dependencies.
-
-See `OCRmyPDF Docker Image <docker>`__ for more information.
-
 Installing on Windows
 =====================
 
-.. warning::
-
-    Native Windows support is new. Consider it "beta" software. Some
-    functionality is missing or may be more difficult to enable. If you need a
-    production-ready solution, use Windows Subsystem for Linux or a Docker
-    image.
+Native Windows
+--------------
 
 .. note::
 
@@ -548,37 +511,47 @@ Installing on Windows
 
 You must install the following for Windows:
 
-* Python 3.7 (64-bit)
+* Python 3.7 (64-bit) or later
 * Tesseract 4.0 or later
 * Ghostscript 9.50 or later
 
-You can install these with the Chocolatey package manager:
+Using the `Chocolatey <https://chocolatey.org/>`_ package manager, install the
+following when running in an Administrator command prompt:
 
 * ``choco install python3``
 * ``choco install --pre tesseract``
 * ``choco install ghostscript``
+* ``choco install pngquant`` (optional)
 
-Also consider adding:
+The commands above will install Python 3.x (latest version), Tesseract, Ghostscript
+and pngquant. Chocolatey may also need to install the Windows Visual C++ Runtime
+DLLs or other Windows patches, and may require a reboot.
 
-* ``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, and not
-supported at this time.
-
-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:
+You may then use ``pip`` to install ocrmypdf. (This can performed by a user or
+Administrator.):
 
 * ``pip install ocrmypdf``
 
-Installing on Windows Subsystem for Linux
-=========================================
+Chocolatey automatically selects appropriate versions of these applications. If you
+are installing them manually, please install 64-bit versions of all applications for
+64-bit Windows, or 32-bit versions of all applications for 32-bit Windows. Mixing
+the "bitness" of these programs will lead to errors.
+
+OCRmyPDF will check the Windows Registry and standard locations in your Program Files
+for third party software it needs (specifically, Tesseract and Ghostscript). To
+override the versions OCRmyPDF selects, you can modify the ``PATH`` environment
+variable. `Follow these directions <https://www.computerhope.com/issues/ch000549.htm#dospath>`_
+to change the PATH.
+
+.. warning::
+
+    As of early 2021, users have reported problems with the Microsoft Store version of
+    Python and OCRmyPDF. These issues affect many other third party Python packages.
+    Please download Python from Python.org or Chocolatey instead, and do not use the
+    Microsoft Store version.
+
+Windows Subsystem for Linux
+---------------------------
 
 #. Install Ubuntu 18.04 for Windows Subsystem for Linux, if not already installed.
 #. Follow the procedure to install :ref:`OCRmyPDF on Ubuntu 18.04 <ubuntu-lts-latest>`.
@@ -597,14 +570,8 @@ Then confirm that the expected version from PyPI (|latest|) is installed:
 You can then run OCRmyPDF in the Windows command prompt or Powershell, prefixing
 ``wsl``, and call it from Windows programs or batch files.
 
-Docker
-^^^^^^
-
-You can also :ref:`Install the Docker <docker-install>` container on Windows. Ensure that
-your command prompt can run the docker "hello world" container.
-
-Installing on Cygwin64 under Windows
-====================================
+Cygwin64
+--------
 
 First install the the following prerequisite Cygwin packages using ``setup-x86_64.exe``::
 
@@ -650,13 +617,59 @@ The optional dependency "unpaper" that is currently not available under Cygwin.
 Without it, certain options such as ``--clean`` will produce an error message.
 However, the OCR-to-text-layer functionality is available.
 
+Docker
+------
+
+You can also :ref:`Install the Docker <docker>` container on Windows. Ensure that
+your command prompt can run the docker "hello world" container.
+
+Installing on FreeBSD
+=====================
+
+.. image:: https://repology.org/badge/version-for-repo/freebsd/python:ocrmypdf.svg
+    :alt: FreeBSD
+    :target: https://repology.org/project/python:ocrmypdf/versions
+
+FreeBSD 11.3, 12.0, 12.1-RELEASE and 13.0-CURRENT are supported. Other
+versions likely work but have not been tested.
+
+.. code-block:: bash
+
+    pkg install py38-ocrmypdf
+
+To install a more recent version, you could attempt to first install the system
+version with ``pkg``, then use ``pip install --user ocrmypdf``.
+
+Installing the Docker image
+===========================
+
+For some users, installing the Docker image will be easier than
+installing all of OCRmyPDF's dependencies.
+
+See :ref:`docker` for more information.
+
 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.
+
+.. warning::
+
+    Debian and Ubuntu users: unfortunately, Debian and Ubuntu customize
+    Python in non-standard ways, and the nature of these customizations
+    varies from release to release. This can make for a frustrating
+    user experience. The instructions below work on almost all platforms that
+    have Python installed, except for Debian and Ubuntu, where you may need
+    to take additional steps. For best results on Debian and Ubuntu, use the
+    ``apt`` packages; or if these are too old, run
+    ``apt install python3-pip python3-venv``, create a virtual environment,
+    and install OCRmyPDF in that environment.
+
+    `See here for more inforation on Debian-Python issues
+    <https://gist.github.com/tiran/2dec9e03c6f901814f6d1e8dad09528e>`__.
 
 For best results, first install `your platform's
 version <https://repology.org/metapackage/ocrmypdf/versions>`__ of
@@ -684,6 +697,13 @@ instead use this for a system wide installation:
 
     pip3 install ocrmypdf
 
+.. note::
+
+    AArch64 (ARM64) users: this process will be difficult because most
+    Python packages are not available as binary wheels for your platform.
+    You're probably better off using a platform install on Debian, Ubuntu,
+    or Fedora.
+
 Requirements for pip and HEAD install
 -------------------------------------
 
@@ -792,8 +812,7 @@ To install all of the development and test requirements:
     python3 -m venv
     source venv/bin/activate
     cd OCRmyPDF
-    pip install -e .
-    pip install -r requirements/dev.txt -r requirements/test.txt
+    pip install -e .[test]
 
 To add JBIG2 encoding, see :ref:`jbig2`.
 

docs/introduction.rst

@@ -2,7 +2,12 @@
 Introduction
 ============
 
-OCRmyPDF is a Python 3 application and library that adds OCR layers to PDFs.
+OCRmyPDF is an application and library that adds text "layers" to images
+in PDFs, making scanned image PDFs searchable. It uses OCR to guess what text
+is contained in images. It is written in Python. OCRmyPDF supports plugins
+that allow customization of its processing steps, and is very tolerant of
+PDFs that contain scanned images and "born digital" content that needs no
+text recognition.
 
 About OCR
 =========
@@ -26,7 +31,7 @@ exactly. They contain `vector
 graphics <http://vector-conversions.com/vectorizing/raster_vs_vector.html>`__
 that can contain raster objects such as scanned images. Because PDFs can
 contain multiple pages (unlike many image formats) and can contain fonts
-and text, it is a good formats for exchanging scanned documents.
+and text, it is a good format for exchanging scanned documents.
 
 |image|
 
@@ -35,9 +40,9 @@ have one image. Some scanners or scanning software will segment pages
 into monochromatic text and color regions for example, to improve the
 compression ratio and appearance of the page.
 
-Rasterizing a PDF is the process of generating an image suitable for
-display or analyzing with an OCR engine. OCR engines like Tesseract work
-with images, not vector objects.
+Rasterizing a PDF is the process of generating corresponding raster images.
+OCR engines like Tesseract work with images, not scalable vector graphics
+or mixed raster-vector-text graphics such as PDF.
 
 About PDF/A
 ===========
@@ -76,7 +81,7 @@ OCRmyPDF analyzes each page of a PDF to determine the colorspace and
 resolution (DPI) needed to capture all of the information on that page
 without losing content. It uses
 `Ghostscript <http://ghostscript.com/>`__ to rasterize the page, and
-then performs on OCR on the rasterized image to create an OCR "layer".
+then performs on OCR the rasterized image to create an OCR "layer".
 The layer is then grafted back onto the original PDF.
 
 While one can use a program like Ghostscript or ImageMagick to get an
@@ -84,9 +89,9 @@ image and put the image through Tesseract, that actually creates a new
 PDF and many details may be lost. OCRmyPDF can produce a minimally
 changed PDF as output.
 
-OCRmyPDF also some image processing options like deskew which improve
-the appearance of files and quality of OCR. When these are used, the OCR
-layer is grafted onto the processed image instead.
+OCRmyPDF also provides some image processing options, like deskew, which
+improves the appearance of files and quality of OCR. When these are used,
+the OCR layer is grafted onto the processed image instead.
 
 By default, OCRmyPDF produces archival PDFs – PDF/A, which are a
 stricter subset of PDF features designed for long term archives. If
@@ -139,7 +144,7 @@ Limitations
 OCRmyPDF is limited by the Tesseract OCR engine. As such it experiences
 these limitations, as do any other programs that rely on Tesseract:
 
--  The OCR is not as accurate as commercial solutions such as Abbyy.
+-  The OCR is not as accurate as commercial OCR solutions.
 -  It is not capable of recognizing handwriting.
 -  It may find gibberish and report this as OCR output.
 -  If a document contains languages outside of those given in the
@@ -186,6 +191,11 @@ Ghostscript also imposes some limitations:
 -  Ghostscript's PDF/A conversion removes any XMP metadata that is not
    one of the standard XMP metadata namespaces for PDFs. In particular,
    PRISM Metdata is removed.
+-  Ghostscript's PDF/A conversion seems to remove or deactivate
+   hyperlinks and other active content.
+
+You can use ``--output-type pdf`` to disable PDF/A conversion and produce
+a standard, non-archival PDF.
 
 Regarding OCRmyPDF itself:
 
@@ -202,8 +212,9 @@ consider one of these similar open source programs:
 
 -  pdf2pdfocr
 -  pdfsandwich
--  pypdfocr
--  pdfbeads
+
+Ghostscript recently added three "pdfocr" output devices. They work by
+rasterizing all content and converting all pages to a single colour space.
 
 Web front-ends
 ==============

docs/jbig2.rst

@@ -9,11 +9,11 @@ encoding was patented for a long time. All known JBIG2 US patents have
 expired as of 2017, but it is possible that unknown patents exist.
 
 JBIG2 encoding is recommended for OCRmyPDF and is used to losslessly
-create smaller PDFs. If JBIG2 encoding not available, lower quality
+create smaller PDFs. If JBIG2 encoding is not available, lower quality
 encodings will be used.
 
 JBIG2 decoding is not patented and is performed automatically by most
-PDF viewers. It is widely supported has been part of the PDF
+PDF viewers. It is widely supported and has been part of the PDF
 specification since 2001.
 
 On macOS, Homebrew packages jbig2enc and OCRmyPDF includes it by
@@ -37,7 +37,7 @@ Lossy mode JBIG2
 
 OCRmyPDF provides lossy mode JBIG2 as an advanced feature. Users should
 `review the technical concerns with JBIG2 in lossy
-mode <https://abbyy.technology/en:kb:tip:jbig2_compression_and_ocr>`__
+mode <https://en.wikipedia.org/wiki/JBIG2#Disadvantages>`__
 and decide if this feature is acceptable for their use case.
 
 JBIG2 lossy mode does achieve higher compression ratios than any other

docs/languages.rst

@@ -12,9 +12,9 @@ languages <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.
 Languages are identified by standardized three-letter codes (called ISO 639-2 Alpha-3).
 Tesseract's documentation also lists the three-letter code for your language.
 Some are anglicized, e.g. Spanish is ``spa`` rather than ``esp``, while others
-are not, e.g. German is ``deu``.
+are not, e.g. German is ``deu`` and French is ``fra``.
 
-After you have installed a language pack, you can use it ``ocrmypdf -l <language>``,
+After you have installed a language pack, you can use it with ``ocrmypdf -l <language>``,
 for example ``ocrmypdf -l spa``. For multilingual documents, you can specify
 all languages to be expected, e.g. ``ocrmypdf -l eng+fra`` for English and French.
 English is assumed by default unless other language(s) are specified.
@@ -35,8 +35,8 @@ Debian and Ubuntu users
 
 You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as
 to what languages it should search for. Multiple languages can be
-requested using either ``-l eng+fre`` (English and French) or
-``-l eng -l fre``.
+requested using either ``-l eng+fra`` (English and French) or
+``-l eng -l fra``.
 
 Fedora users
 ============
@@ -51,8 +51,8 @@ Fedora users
 
 You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as
 to what languages it should search for. Multiple languages can be
-requested using either ``-l eng+fre`` (English and French) or
-``-l eng -l fre``.
+requested using either ``-l eng+fra`` (English and French) or
+``-l eng -l fra``.
 
 macOS users
 ===========
@@ -70,4 +70,7 @@ derived Docker image as
 Windows users
 =============
 
-The Tesseract installer provided by Chocolatey already includes 100 languages.
+The Tesseract installer provided by Chocolatey currently includes only English language. 
+To install other languages, download the respective language pack (``.traineddata`` file) 
+from https://github.com/tesseract-ocr/tessdata/ and place it in 
+``C:\\Program Files\\Tesseract-OCR\\tessdata`` (or wherever Tesseract OCR is installed).

docs/pdfsecurity.rst

@@ -19,7 +19,7 @@ PDF is a rich, complex file format. The official PDF 1.7 specification,
 ISO 32000:2008, is hundreds of pages long and references several annexes
 each of which are similar in length. PDFs can contain video, audio, XML,
 JavaScript and other programming, and forms. In some cases, they can
-open internet connections to pre-selected URLs. All of these possible
+open internet connections to pre-selected URLs. All of these are possible
 attack vectors.
 
 In short, PDFs `may contain
@@ -31,7 +31,7 @@ describes a high-paranoia method which allows potentially hostile PDFs
 to be viewed and rasterized safely in a disposable virtual machine. A
 trusted PDF created in this manner is converted to images and loses all
 information making it searchable and losing all compression. OCRmyPDF
-could be used restore searchability.
+could be used to restore searchability.
 
 How OCRmyPDF processes PDFs
 ===========================
@@ -41,8 +41,8 @@ layer. First, it runs all PDFs through
 `pikepdf <https://github.com/pikepdf/pikepdf>`__, a library based on
 `qpdf <https://github.com/qpdf/qpdf>`__, a program that repairs PDFs
 with syntax errors. This is done because, in the author's experience, a
-significant number of PDFs in the wild especially those created by
-scanners are not well-formed files. qpdf makes it more likely that
+significant number of PDFs in the wild, especially those created by
+scanners, are not well-formed files. qpdf makes it more likely that
 OCRmyPDF will succeed, but offers no security guarantees. qpdf is also
 used to split the PDF into single page PDFs.
 
@@ -64,10 +64,10 @@ malicious user could upload a chosen PDF. In particular, it is not
 necessarily secure against PDF malware or PDFs that cause denial of
 service. OCRmyPDF relies on Ghostscript, and therefore, if deployed
 online one should be prepared to comply with Ghostscript's Affero GPL
-license, OCRmyPDF's GPL license, and any other licenses.
+license, and any other licenses.
 
-Setting aside these concerns, a side effect of OCRmyPDF is it may
-incidentally sanitize PDFs that contain certain types of malware. It
+Setting aside these concerns, a side effect of OCRmyPDF is that it may
+incidentally sanitize PDFs containing certain types of malware. It
 repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF
 structures that are part of an attack. When PDF/A output is selected
 (the default), the input PDF is partially reconstructed by Ghostscript.
@@ -83,7 +83,7 @@ Limiting CPU usage
 OCRmyPDF will attempt to use all available CPUs and storage, so
 executing ``nice ocrmypdf`` or limiting the number of jobs with the
 ``-j`` argument may ensure the server remains available. Another option
-would be run OCRmyPDF jobs inside a Docker container, a virtual machine,
+would be to run OCRmyPDF jobs inside a Docker container, a virtual machine,
 or a cloud instance, which can impose its own limits on CPU usage and be
 terminated "from orbit" if it fails to complete.
 
@@ -128,8 +128,9 @@ Commercial alternatives
 The author also provides professional services that include OCR and
 building databases around PDFs, and is happy to provide consultation.
 
-Abbyy Cloud OCR is a viable commercial alternative with a web services
-API.
+Abbyy Cloud OCR is viable commercial alternative with a web services
+API. Amazon Textract, Google Cloud Vision, and Microsoft Azure 
+Computer Vision provide advanced OCR but have less PDF rendering capability.
 
 Password protection, digital signatures and certification
 =========================================================

docs/pipeline.svg

@@ -1,392 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?>
-<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
- "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
-<!-- Generated by graphviz version 2.40.1 (20161225.0304)
- -->
-<!-- Title: Pipeline: Pages: 1 -->
-<svg width="1484pt" height="1277pt"
- viewBox="0.00 0.00 1484.00 1277.20" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
-<g id="graph0" class="graph" transform="scale(1 1) rotate(0) translate(4 1273.1977)">
-<title>Pipeline:</title>
-<polygon fill="#ffffff" stroke="transparent" points="-4,4 -4,-1273.1977 1480,-1273.1977 1480,4 -4,4"/>
-<g id="clust1" class="cluster">
-<title>clustertasks</title>
-<polygon fill="none" stroke="#000000" points="8,-8 8,-1261.1977 1468,-1261.1977 1468,-8 8,-8"/>
-<text text-anchor="middle" x="738" y="-1233.1977" font-family="Times,serif" font-size="30.00" fill="#ff3232">Pipeline:</text>
-</g>
-<!-- t0 -->
-<g id="node1" class="node">
-<title>t0</title>
-<polygon fill="#efa03b" stroke="#000000" points="1215.7053,-1215.1977 1006.2947,-1215.1977 1002.2947,-1211.1977 1002.2947,-1179.1977 1211.7053,-1179.1977 1215.7053,-1183.1977 1215.7053,-1215.1977"/>
-<polyline fill="none" stroke="#000000" points="1211.7053,-1211.1977 1002.2947,-1211.1977 "/>
-<polyline fill="none" stroke="#000000" points="1211.7053,-1211.1977 1211.7053,-1179.1977 "/>
-<polyline fill="none" stroke="#000000" points="1211.7053,-1211.1977 1215.7053,-1215.1977 "/>
-<text text-anchor="middle" x="1109" y="-1191.1977" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.triage</text>
-</g>
-<!-- t1 -->
-<g id="node2" class="node">
-<title>t1</title>
-<polygon fill="#efa03b" stroke="#000000" points="1280.0433,-1157.1977 941.9567,-1157.1977 937.9567,-1153.1977 937.9567,-1121.1977 1276.0433,-1121.1977 1280.0433,-1125.1977 1280.0433,-1157.1977"/>
-<polyline fill="none" stroke="#000000" points="1276.0433,-1153.1977 937.9567,-1153.1977 "/>
-<polyline fill="none" stroke="#000000" points="1276.0433,-1153.1977 1276.0433,-1121.1977 "/>
-<polyline fill="none" stroke="#000000" points="1276.0433,-1153.1977 1280.0433,-1157.1977 "/>
-<text text-anchor="middle" x="1109" y="-1133.1977" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.repair_and_parse_pdf</text>
-</g>
-<!-- t0&#45;&gt;t1 -->
-<g id="edge1" class="edge">
-<title>t0&#45;&gt;t1</title>
-<path fill="none" stroke="#0044a0" d="M1109,-1179.1641C1109,-1175.4895 1109,-1171.5395 1109,-1167.604"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1112.5001,-1167.4199 1109,-1157.4199 1105.5001,-1167.42 1112.5001,-1167.4199"/>
-</g>
-<!-- t2 -->
-<g id="node3" class="node">
-<title>t2</title>
-<polygon fill="#efa03b" stroke="#000000" points="1030.0926,-1078.2732 785,-1095.1731 539.9074,-1078.2732 540.1362,-1050.9285 1029.8638,-1050.9285 1030.0926,-1078.2732"/>
-<polygon fill="none" stroke="#000000" points="1034.1249,-1082.0021 785,-1099.1801 535.8751,-1082.0021 536.1685,-1046.931 1033.8315,-1046.931 1034.1249,-1082.0021"/>
-<text text-anchor="middle" x="785" y="-1064.7153" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.marker_pages</text>
-</g>
-<!-- t1&#45;&gt;t2 -->
-<g id="edge2" class="edge">
-<title>t1&#45;&gt;t2</title>
-<path fill="none" stroke="#0044a0" d="M1023.449,-1121.1152C984.5695,-1112.8974 938.0675,-1103.0685 896.4957,-1094.2816"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="897.1066,-1090.8335 886.5989,-1092.1898 895.6589,-1097.6822 897.1066,-1090.8335"/>
-</g>
-<!-- t16 -->
-<g id="node17" class="node">
-<title>t16</title>
-<polygon fill="#00cc66" stroke="#000000" points="1215.5059,-328.1861 942.4941,-328.1861 938.4941,-324.1861 938.4941,-292.1861 1211.5059,-292.1861 1215.5059,-296.1861 1215.5059,-328.1861"/>
-<polyline fill="none" stroke="#000000" points="1211.5059,-324.1861 938.4941,-324.1861 "/>
-<polyline fill="none" stroke="#000000" points="1211.5059,-324.1861 1211.5059,-292.1861 "/>
-<polyline fill="none" stroke="#000000" points="1211.5059,-324.1861 1215.5059,-328.1861 "/>
-<text text-anchor="middle" x="1077" y="-304.1861" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.weave_layers</text>
-</g>
-<!-- t1&#45;&gt;t16 -->
-<g id="edge24" class="edge">
-<title>t1&#45;&gt;t16</title>
-<path fill="none" stroke="#0044a0" d="M1097.2373,-1120.9576C1077.987,-1088.7184 1043.7317,-1019.7372 1063,-963.2656 1106.87,-834.6914 1482.8098,-573.3183 1409,-459.2656 1362.7595,-387.8137 1273.2613,-350.2799 1198.8305,-330.7528"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1199.4555,-327.3005 1188.9015,-328.2301 1197.7316,-334.0849 1199.4555,-327.3005"/>
-</g>
-<!-- t17 -->
-<g id="node18" class="node">
-<title>t17</title>
-<polygon fill="#efa03b" stroke="#000000" points="1439.5156,-1009.7492 1076.4844,-1009.7492 1072.4844,-1005.7492 1072.4844,-973.7492 1435.5156,-973.7492 1439.5156,-977.7492 1439.5156,-1009.7492"/>
-<polyline fill="none" stroke="#000000" points="1435.5156,-1005.7492 1072.4844,-1005.7492 "/>
-<polyline fill="none" stroke="#000000" points="1435.5156,-1005.7492 1435.5156,-973.7492 "/>
-<polyline fill="none" stroke="#000000" points="1435.5156,-1005.7492 1439.5156,-1009.7492 "/>
-<text text-anchor="middle" x="1256" y="-985.7492" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.generate_postscript_stub</text>
-</g>
-<!-- t1&#45;&gt;t17 -->
-<g id="edge25" class="edge">
-<title>t1&#45;&gt;t17</title>
-<path fill="none" stroke="#0044a0" d="M1127.0251,-1121.1176C1153.0342,-1095.0292 1201.2007,-1046.7157 1230.7429,-1017.0834"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1233.2458,-1019.5302 1237.8275,-1009.9772 1228.2885,-1014.5879 1233.2458,-1019.5302"/>
-</g>
-<!-- t18 -->
-<g id="node19" class="node">
-<title>t18</title>
-<polygon fill="#efa03b" stroke="#000000" points="1070.189,-214.4288 1263,-187.1099 1455.811,-214.4288 1455.631,-258.6317 1070.369,-258.6317 1070.189,-214.4288"/>
-<polygon fill="none" stroke="#000000" points="1066.1715,-210.9543 1263,-183.0662 1459.8285,-210.9543 1459.6181,-262.6353 1066.3819,-262.6353 1066.1715,-210.9543"/>
-<text text-anchor="middle" x="1263" y="-220.6461" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.metadata_fixup</text>
-</g>
-<!-- t1&#45;&gt;t18 -->
-<g id="edge28" class="edge">
-<title>t1&#45;&gt;t18</title>
-<path fill="none" stroke="#0044a0" d="M1241.1115,-1121.1192C1311.0076,-1105.2558 1393.5851,-1075.5895 1449,-1020.2329 1458.4922,-1010.7507 1459,-1005.1661 1459,-991.7492 1459,-991.7492 1459,-991.7492 1459,-393.7258 1459,-341.9727 1441.8377,-325.2216 1402,-292.1861 1390.9869,-283.0534 1378.4885,-274.871 1365.6104,-267.6415"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1367.1079,-264.4723 1356.6476,-262.7888 1363.775,-270.6279 1367.1079,-264.4723"/>
-</g>
-<!-- t3 -->
-<g id="node4" class="node">
-<title>t3</title>
-<polygon fill="#efa03b" stroke="#000000" points="1015.5194,-999.3074 785,-1016.2081 554.4806,-999.3074 554.6958,-971.9616 1015.3042,-971.9616 1015.5194,-999.3074"/>
-<polygon fill="none" stroke="#000000" points="1019.5491,-1003.0204 785,-1020.2165 550.4509,-1003.0204 550.7267,-967.9639 1019.2733,-967.9639 1019.5491,-1003.0204"/>
-<text text-anchor="middle" x="785" y="-985.7492" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.ocr_or_skip</text>
-</g>
-<!-- t2&#45;&gt;t3 -->
-<g id="edge3" class="edge">
-<title>t2&#45;&gt;t3</title>
-<path fill="none" stroke="#0044a0" d="M785,-1046.5938C785,-1041.5635 785,-1036.139 785,-1030.7273"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="788.5001,-1030.4427 785,-1020.4427 781.5001,-1030.4428 788.5001,-1030.4427"/>
-</g>
-<!-- t4 -->
-<g id="node5" class="node">
-<title>t4</title>
-<polygon fill="#efa03b" stroke="#000000" points="889.3166,-941.2656 582.6834,-941.2656 578.6834,-937.2656 578.6834,-905.2656 885.3166,-905.2656 889.3166,-909.2656 889.3166,-941.2656"/>
-<polyline fill="none" stroke="#000000" points="885.3166,-937.2656 578.6834,-937.2656 "/>
-<polyline fill="none" stroke="#000000" points="885.3166,-937.2656 885.3166,-905.2656 "/>
-<polyline fill="none" stroke="#000000" points="885.3166,-937.2656 889.3166,-941.2656 "/>
-<text text-anchor="middle" x="734" y="-917.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.rasterize_preview</text>
-</g>
-<!-- t3&#45;&gt;t4 -->
-<g id="edge4" class="edge">
-<title>t3&#45;&gt;t4</title>
-<path fill="none" stroke="#0044a0" d="M767.1627,-967.797C762.8396,-961.9919 758.1927,-955.7519 753.7858,-949.8343"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="756.3465,-947.4129 747.5666,-941.483 750.7323,-951.5939 756.3465,-947.4129"/>
-</g>
-<!-- t5 -->
-<g id="node6" class="node">
-<title>t5</title>
-<polygon fill="#efa03b" stroke="#000000" points="1028.0824,-883.2656 769.9176,-883.2656 765.9176,-879.2656 765.9176,-847.2656 1024.0824,-847.2656 1028.0824,-851.2656 1028.0824,-883.2656"/>
-<polyline fill="none" stroke="#000000" points="1024.0824,-879.2656 765.9176,-879.2656 "/>
-<polyline fill="none" stroke="#000000" points="1024.0824,-879.2656 1024.0824,-847.2656 "/>
-<polyline fill="none" stroke="#000000" points="1024.0824,-879.2656 1028.0824,-883.2656 "/>
-<text text-anchor="middle" x="897" y="-859.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.orient_page</text>
-</g>
-<!-- t3&#45;&gt;t5 -->
-<g id="edge6" class="edge">
-<title>t3&#45;&gt;t5</title>
-<path fill="none" stroke="#0044a0" d="M869.1177,-967.8063C880.553,-961.0264 890.81,-952.3527 898,-941.2656 907.042,-927.3226 906.9457,-908.7053 904.5139,-893.387"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="907.914,-892.5383 902.5408,-883.4071 901.0469,-893.8961 907.914,-892.5383"/>
-</g>
-<!-- t4&#45;&gt;t5 -->
-<g id="edge5" class="edge">
-<title>t4&#45;&gt;t5</title>
-<path fill="none" stroke="#0044a0" d="M784.6807,-905.2319C801.0865,-899.3943 819.4462,-892.8614 836.4913,-886.7963"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="838.1026,-889.938 846.3506,-883.288 835.7559,-883.343 838.1026,-889.938"/>
-</g>
-<!-- t6 -->
-<g id="node7" class="node">
-<title>t6</title>
-<polygon fill="#efa03b" stroke="#000000" points="1064.7325,-825.2656 689.2675,-825.2656 685.2675,-821.2656 685.2675,-789.2656 1060.7325,-789.2656 1064.7325,-793.2656 1064.7325,-825.2656"/>
-<polyline fill="none" stroke="#000000" points="1060.7325,-821.2656 685.2675,-821.2656 "/>
-<polyline fill="none" stroke="#000000" points="1060.7325,-821.2656 1060.7325,-789.2656 "/>
-<polyline fill="none" stroke="#000000" points="1060.7325,-821.2656 1064.7325,-825.2656 "/>
-<text text-anchor="middle" x="875" y="-801.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.rasterize_with_ghostscript</text>
-</g>
-<!-- t5&#45;&gt;t6 -->
-<g id="edge7" class="edge">
-<title>t5&#45;&gt;t6</title>
-<path fill="none" stroke="#0044a0" d="M890.1597,-847.2319C888.6839,-843.3412 887.0909,-839.1417 885.5115,-834.9776"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="888.731,-833.5965 881.9119,-825.4878 882.186,-836.0791 888.731,-833.5965"/>
-</g>
-<!-- t13 -->
-<g id="node16" class="node">
-<title>t13</title>
-<polygon fill="#00cc66" stroke="#000000" points="1077,-515.2656 754.4141,-487.2656 1077,-459.2656 1399.5859,-487.2656 1077,-515.2656"/>
-<text text-anchor="middle" x="1077" y="-481.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.select_image_layer</text>
-</g>
-<!-- t5&#45;&gt;t13 -->
-<g id="edge20" class="edge">
-<title>t5&#45;&gt;t13</title>
-<path fill="none" stroke="#0044a0" d="M1000.2704,-847.241C1031.2359,-840.6873 1060.5415,-832.9862 1074,-825.2656 1114.0954,-802.2644 1145,-795.4899 1145,-749.2656 1145,-749.2656 1145,-749.2656 1145,-633.2656 1145,-590.368 1154.8687,-575.2844 1135,-537.2656 1131.571,-530.7041 1126.8893,-524.6314 1121.6622,-519.1451"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1123.8989,-516.4405 1114.2626,-512.0367 1119.0494,-521.4885 1123.8989,-516.4405"/>
-</g>
-<!-- t7 -->
-<g id="node8" class="node">
-<title>t7</title>
-<polygon fill="#efa03b" stroke="#000000" points="856.0801,-767.2656 431.9199,-767.2656 427.9199,-763.2656 427.9199,-731.2656 852.0801,-731.2656 856.0801,-735.2656 856.0801,-767.2656"/>
-<polyline fill="none" stroke="#000000" points="852.0801,-763.2656 427.9199,-763.2656 "/>
-<polyline fill="none" stroke="#000000" points="852.0801,-763.2656 852.0801,-731.2656 "/>
-<polyline fill="none" stroke="#000000" points="852.0801,-763.2656 856.0801,-767.2656 "/>
-<text text-anchor="middle" x="642" y="-743.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.preprocess_remove_background</text>
-</g>
-<!-- t6&#45;&gt;t7 -->
-<g id="edge8" class="edge">
-<title>t6&#45;&gt;t7</title>
-<path fill="none" stroke="#0044a0" d="M802.5546,-789.2319C777.7884,-783.067 749.9071,-776.1266 724.4138,-769.7806"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="724.95,-766.3073 714.4006,-767.288 723.259,-773.1 724.95,-766.3073"/>
-</g>
-<!-- t12 -->
-<g id="node15" class="node">
-<title>t12</title>
-<polygon fill="#efa03b" stroke="#000000" points="742,-593.2656 358.1874,-565.2656 742,-537.2656 1125.8126,-565.2656 742,-593.2656"/>
-<text text-anchor="middle" x="742" y="-559.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.select_visible_page_image</text>
-</g>
-<!-- t6&#45;&gt;t12 -->
-<g id="edge18" class="edge">
-<title>t6&#45;&gt;t12</title>
-<path fill="none" stroke="#0044a0" d="M875.1443,-789.1129C874.6867,-773.2956 872.5831,-750.0189 865,-731.2656 844.2991,-680.0716 804.0126,-630.4165 775.1838,-598.9641"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="777.4937,-596.3085 768.1202,-591.3701 772.3682,-601.076 777.4937,-596.3085"/>
-</g>
-<!-- t8 -->
-<g id="node9" class="node">
-<title>t8</title>
-<polygon fill="#efa03b" stroke="#000000" points="732.6759,-709.2656 413.3241,-709.2656 409.3241,-705.2656 409.3241,-673.2656 728.6759,-673.2656 732.6759,-677.2656 732.6759,-709.2656"/>
-<polyline fill="none" stroke="#000000" points="728.6759,-705.2656 409.3241,-705.2656 "/>
-<polyline fill="none" stroke="#000000" points="728.6759,-705.2656 728.6759,-673.2656 "/>
-<polyline fill="none" stroke="#000000" points="728.6759,-705.2656 732.6759,-709.2656 "/>
-<text text-anchor="middle" x="571" y="-685.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.preprocess_deskew</text>
-</g>
-<!-- t7&#45;&gt;t8 -->
-<g id="edge9" class="edge">
-<title>t7&#45;&gt;t8</title>
-<path fill="none" stroke="#0044a0" d="M619.9243,-731.2319C613.9709,-726.3685 607.4267,-721.0226 601.115,-715.8666"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="603.2653,-713.1037 593.3065,-709.4878 598.8367,-718.5248 603.2653,-713.1037"/>
-</g>
-<!-- t7&#45;&gt;t12 -->
-<g id="edge17" class="edge">
-<title>t7&#45;&gt;t12</title>
-<path fill="none" stroke="#0044a0" d="M717.0346,-731.1646C726.8757,-725.6884 735.7103,-718.5557 742,-709.2656 763.0291,-678.205 759.4083,-634.0888 752.8082,-602.8898"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="756.1481,-601.7976 750.487,-592.842 749.3278,-603.3733 756.1481,-601.7976"/>
-</g>
-<!-- t9 -->
-<g id="node10" class="node">
-<title>t9</title>
-<polygon fill="#efa03b" stroke="#000000" points="712.8828,-651.2656 411.1172,-651.2656 407.1172,-647.2656 407.1172,-615.2656 708.8828,-615.2656 712.8828,-619.2656 712.8828,-651.2656"/>
-<polyline fill="none" stroke="#000000" points="708.8828,-647.2656 407.1172,-647.2656 "/>
-<polyline fill="none" stroke="#000000" points="708.8828,-647.2656 708.8828,-615.2656 "/>
-<polyline fill="none" stroke="#000000" points="708.8828,-647.2656 712.8828,-651.2656 "/>
-<text text-anchor="middle" x="560" y="-627.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.preprocess_clean</text>
-</g>
-<!-- t8&#45;&gt;t9 -->
-<g id="edge10" class="edge">
-<title>t8&#45;&gt;t9</title>
-<path fill="none" stroke="#0044a0" d="M567.5798,-673.2319C566.8624,-669.4493 566.0897,-665.3747 565.3216,-661.3247"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="568.7581,-660.6605 563.4559,-651.4878 561.8807,-661.9649 568.7581,-660.6605"/>
-</g>
-<!-- t8&#45;&gt;t12 -->
-<g id="edge16" class="edge">
-<title>t8&#45;&gt;t12</title>
-<path fill="none" stroke="#0044a0" d="M670.0045,-673.2618C693.2528,-667.2338 713.6919,-659.8307 722,-651.2656 734.1971,-638.6912 739.4901,-620.2051 741.6123,-603.5914"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="745.1041,-603.8427 742.5574,-593.5585 738.1349,-603.1862 745.1041,-603.8427"/>
-</g>
-<!-- t10 -->
-<g id="node11" class="node">
-<title>t10</title>
-<polygon fill="#efa03b" stroke="#000000" points="340.1094,-583.2656 35.8906,-583.2656 31.8906,-579.2656 31.8906,-547.2656 336.1094,-547.2656 340.1094,-551.2656 340.1094,-583.2656"/>
-<polyline fill="none" stroke="#000000" points="336.1094,-579.2656 31.8906,-579.2656 "/>
-<polyline fill="none" stroke="#000000" points="336.1094,-579.2656 336.1094,-547.2656 "/>
-<polyline fill="none" stroke="#000000" points="336.1094,-579.2656 340.1094,-583.2656 "/>
-<text text-anchor="middle" x="186" y="-559.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.select_ocr_image</text>
-</g>
-<!-- t9&#45;&gt;t10 -->
-<g id="edge11" class="edge">
-<title>t9&#45;&gt;t10</title>
-<path fill="none" stroke="#0044a0" d="M460.7568,-615.2213C409.7279,-605.9434 347.4237,-594.6153 295.0537,-585.0935"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="295.5223,-581.6214 285.0575,-583.276 294.2701,-588.5085 295.5223,-581.6214"/>
-</g>
-<!-- t9&#45;&gt;t12 -->
-<g id="edge15" class="edge">
-<title>t9&#45;&gt;t12</title>
-<path fill="none" stroke="#0044a0" d="M608.2948,-615.2213C627.0226,-608.2242 648.8712,-600.0609 669.4134,-592.3859"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="670.9148,-595.5613 679.0573,-588.7826 668.4648,-589.004 670.9148,-595.5613"/>
-</g>
-<!-- t11 -->
-<g id="node12" class="node">
-<title>t11</title>
-<polygon fill="#00cc66" stroke="#000000" points="334.0996,-505.2656 19.9004,-505.2656 15.9004,-501.2656 15.9004,-469.2656 330.0996,-469.2656 334.0996,-473.2656 334.0996,-505.2656"/>
-<polyline fill="none" stroke="#000000" points="330.0996,-501.2656 15.9004,-501.2656 "/>
-<polyline fill="none" stroke="#000000" points="330.0996,-501.2656 330.0996,-469.2656 "/>
-<polyline fill="none" stroke="#000000" points="330.0996,-501.2656 334.0996,-505.2656 "/>
-<text text-anchor="middle" x="175" y="-481.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.ocr_tesseract_hocr</text>
-</g>
-<!-- t10&#45;&gt;t11 -->
-<g id="edge12" class="edge">
-<title>t10&#45;&gt;t11</title>
-<path fill="none" stroke="#0044a0" d="M183.4487,-547.1748C182.1254,-537.7914 180.4788,-526.1154 178.9917,-515.5701"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="182.4378,-514.9417 177.5755,-505.5285 175.5064,-515.9193 182.4378,-514.9417"/>
-</g>
-<!-- t15 -->
-<g id="node14" class="node">
-<title>t15</title>
-<polygon fill="#ff69b4" stroke="#000000" points="736.2696,-505.2656 355.7304,-505.2656 351.7304,-501.2656 351.7304,-469.2656 732.2696,-469.2656 736.2696,-473.2656 736.2696,-505.2656"/>
-<polyline fill="none" stroke="#000000" points="732.2696,-501.2656 351.7304,-501.2656 "/>
-<polyline fill="none" stroke="#000000" points="732.2696,-501.2656 732.2696,-469.2656 "/>
-<polyline fill="none" stroke="#000000" points="732.2696,-501.2656 736.2696,-505.2656 "/>
-<text text-anchor="middle" x="544" y="-481.2656" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.ocr_tesseract_textonly_pdf</text>
-</g>
-<!-- t10&#45;&gt;t15 -->
-<g id="edge14" class="edge">
-<title>t10&#45;&gt;t15</title>
-<path fill="none" stroke="#0044a0" d="M269.0322,-547.1748C323.4947,-535.3086 394.7854,-519.776 451.1284,-507.5002"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="452.0829,-510.8744 461.1086,-505.3257 450.5927,-504.0348 452.0829,-510.8744"/>
-</g>
-<!-- t14 -->
-<g id="node13" class="node">
-<title>t14</title>
-<polygon fill="#00cc66" stroke="#000000" points="330.0433,-411.7258 21.9567,-411.7258 17.9567,-407.7258 17.9567,-375.7258 326.0433,-375.7258 330.0433,-379.7258 330.0433,-411.7258"/>
-<polyline fill="none" stroke="#000000" points="326.0433,-407.7258 17.9567,-407.7258 "/>
-<polyline fill="none" stroke="#000000" points="326.0433,-407.7258 326.0433,-375.7258 "/>
-<polyline fill="none" stroke="#000000" points="326.0433,-407.7258 330.0433,-411.7258 "/>
-<text text-anchor="middle" x="174" y="-387.7258" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.render_hocr_page</text>
-</g>
-<!-- t11&#45;&gt;t14 -->
-<g id="edge13" class="edge">
-<title>t11&#45;&gt;t14</title>
-<path fill="none" stroke="#0044a0" d="M174.8072,-469.2302C174.6642,-455.8584 174.4666,-437.3702 174.3027,-422.0357"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="177.8024,-421.987 174.1956,-412.025 170.8028,-422.0619 177.8024,-421.987"/>
-</g>
-<!-- t19 -->
-<g id="node22" class="node">
-<title>t19</title>
-<polygon fill="#efa03b" stroke="#000000" points="351.7205,-381.5085 545,-354.1897 738.2795,-381.5085 738.0991,-425.7112 351.9009,-425.7112 351.7205,-381.5085"/>
-<polygon fill="none" stroke="#000000" points="347.7033,-378.0329 545,-350.1463 742.2967,-378.0329 742.0858,-429.7148 347.9142,-429.7148 347.7033,-378.0329"/>
-<text text-anchor="middle" x="545" y="-387.7258" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.merge_sidecars</text>
-</g>
-<!-- t11&#45;&gt;t19 -->
-<g id="edge32" class="edge">
-<title>t11&#45;&gt;t19</title>
-<path fill="none" stroke="#0044a0" d="M246.3397,-469.2302C287.966,-458.7066 342.1269,-445.0142 392.8772,-432.184"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="393.8058,-435.5594 402.6429,-429.7151 392.0901,-428.773 393.8058,-435.5594"/>
-</g>
-<!-- t14&#45;&gt;t16 -->
-<g id="edge22" class="edge">
-<title>t14&#45;&gt;t16</title>
-<path fill="none" stroke="#0044a0" d="M230.6615,-375.7128C262.2207,-366.4581 302.4172,-355.9425 339,-350.1861 448.3957,-332.9725 745.7869,-320.7866 927.9215,-314.6743"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="928.248,-318.1655 938.1258,-314.3342 928.0148,-311.1693 928.248,-318.1655"/>
-</g>
-<!-- t15&#45;&gt;t16 -->
-<g id="edge21" class="edge">
-<title>t15&#45;&gt;t16</title>
-<path fill="none" stroke="#0044a0" d="M630.0636,-469.2083C667.5329,-460.6467 711.76,-449.5912 751,-437.2656 850.4985,-406.0121 963.1653,-359.5222 1026.586,-332.2894"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1028.1566,-335.4238 1035.9553,-328.2523 1025.3866,-328.9951 1028.1566,-335.4238"/>
-</g>
-<!-- t15&#45;&gt;t19 -->
-<g id="edge31" class="edge">
-<title>t15&#45;&gt;t19</title>
-<path fill="none" stroke="#0044a0" d="M544.1928,-469.2302C544.2822,-460.8687 544.393,-450.5066 544.5035,-440.166"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="548.006,-439.9443 544.6132,-429.9075 541.0064,-439.8694 548.006,-439.9443"/>
-</g>
-<!-- t12&#45;&gt;t13 -->
-<g id="edge19" class="edge">
-<title>t12&#45;&gt;t13</title>
-<path fill="none" stroke="#0044a0" d="M833.9833,-543.8486C879.0975,-533.3444 933.4556,-520.6879 979.3116,-510.0109"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="980.3156,-513.3709 989.2614,-507.6943 978.7282,-506.5532 980.3156,-513.3709"/>
-</g>
-<!-- t13&#45;&gt;t16 -->
-<g id="edge23" class="edge">
-<title>t13&#45;&gt;t16</title>
-<path fill="none" stroke="#0044a0" d="M1077,-459.2068C1077,-426.2624 1077,-371.9187 1077,-338.7552"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1080.5001,-338.3818 1077,-328.3819 1073.5001,-338.3819 1080.5001,-338.3818"/>
-</g>
-<!-- t16&#45;&gt;t18 -->
-<g id="edge27" class="edge">
-<title>t16&#45;&gt;t18</title>
-<path fill="none" stroke="#0044a0" d="M1117.3592,-292.0592C1133.8695,-284.6437 1153.6803,-275.7459 1173.2953,-266.9361"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1174.8979,-270.0531 1182.586,-262.7632 1172.0299,-263.6676 1174.8979,-270.0531"/>
-</g>
-<!-- t17&#45;&gt;t18 -->
-<g id="edge26" class="edge">
-<title>t17&#45;&gt;t18</title>
-<path fill="none" stroke="#0044a0" d="M1326.2292,-973.7283C1377.8362,-955.768 1439,-922.4247 1439,-865.2656 1439,-865.2656 1439,-865.2656 1439,-393.7258 1439,-338.7092 1393.2056,-296.3464 1348.3356,-268.0433"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1350.0403,-264.9831 1339.6842,-262.7465 1346.3852,-270.9531 1350.0403,-264.9831"/>
-</g>
-<!-- t20 -->
-<g id="node20" class="node">
-<title>t20</title>
-<polygon fill="#efa03b" stroke="#000000" points="1400.3184,-161.1062 1129.6816,-161.1062 1125.6816,-157.1062 1125.6816,-125.1062 1396.3184,-125.1062 1400.3184,-129.1062 1400.3184,-161.1062"/>
-<polyline fill="none" stroke="#000000" points="1396.3184,-157.1062 1125.6816,-157.1062 "/>
-<polyline fill="none" stroke="#000000" points="1396.3184,-157.1062 1396.3184,-125.1062 "/>
-<polyline fill="none" stroke="#000000" points="1396.3184,-157.1062 1400.3184,-161.1062 "/>
-<text text-anchor="middle" x="1263" y="-137.1062" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.optimize_pdf</text>
-</g>
-<!-- t18&#45;&gt;t20 -->
-<g id="edge29" class="edge">
-<title>t18&#45;&gt;t20</title>
-<path fill="none" stroke="#0044a0" d="M1263,-182.9188C1263,-179.129 1263,-175.3607 1263,-171.739"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1266.5001,-171.4394 1263,-161.4394 1259.5001,-171.4394 1266.5001,-171.4394"/>
-</g>
-<!-- t21 -->
-<g id="node21" class="node">
-<title>t21</title>
-<polygon fill="#efa03b" stroke="#000000" points="1096.0652,-47.332 1263,-20.0049 1429.9348,-47.332 1429.779,-91.5483 1096.221,-91.5483 1096.0652,-47.332"/>
-<polygon fill="none" stroke="#000000" points="1092.0538,-43.9306 1263,-15.9468 1433.9462,-43.9306 1433.7643,-95.5532 1092.2357,-95.5532 1092.0538,-43.9306"/>
-<text text-anchor="middle" x="1263" y="-53.5531" font-family="Times,serif" font-size="20.00" fill="#000000">ocrmypdf.pipeline.copy_final</text>
-</g>
-<!-- t20&#45;&gt;t21 -->
-<g id="edge30" class="edge">
-<title>t20&#45;&gt;t21</title>
-<path fill="none" stroke="#0044a0" d="M1263,-124.9764C1263,-119.37 1263,-112.9163 1263,-106.2938"/>
-<polygon fill="#0044a0" stroke="#0044a0" points="1266.5001,-105.8456 1263,-95.8457 1259.5001,-105.8457 1266.5001,-105.8456"/>
-</g>
-</g>
-</svg>

docs/plugins.rst

@@ -2,6 +2,11 @@
 Plugins
 =======
 
+    The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL
+    NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED",  "MAY", and
+    "OPTIONAL" in this document are to be interpreted as described in
+    RFC 2119.
+
 You can use plugins to customize the behavior of OCRmyPDF at certain points of
 interest.
 
@@ -11,39 +16,34 @@ Currently, it is possible to:
 - override the decision for whether or not to perform OCR on a particular file
 - modify the image is about to be sent for OCR
 - modify the page image before it is converted to PDF
+- replace the Tesseract OCR with another OCR engine that has similar behavior
+- replace Ghostscript with another PDF to image converter (rasterizer) or
+  PDF/A generator
 
 OCRmyPDF plugins are based on the Python ``pluggy`` package and conform to its
 conventions. Note that: plugins installed with as setuptools entrypoints are
 not checked currently, because OCRmyPDF assumes you may not want to enable
-plugins for all files. Also, plugins must be functions, not classes.
-
-How plugins are imported
-========================
-
-Plugins are imported on demand, by the OCRmyPDF worker process that needs to use
-them. As such, plugins cannot share state with other plugins, cannot rely on
-their module's or the interpreter's global state, and should expect asynchronous
-copies of themselves to be running. Plugins can write intermediate files to the
-folder specified in ``options.work_folder``.
-
-Plugins should work whether executed in threads or processes.
+plugins for all files.
 
 Script plugins
 ==============
 
 Script plugins may be called from the command line, by specifying the name of a file.
+Script plugins may be convenient for informal or "one-off" plugins, when a certain
+batch of files needs a special processing step for example.
 
 .. code-block:: bash
 
-    ocrmypdf --plugin example_plugin.py input.pdf output.pdf
+    ocrmypdf --plugin ocrmypdf_example_plugin.py input.pdf output.pdf
 
-Multiple plugins may be called by issuing the ``--plugin`` argument multiple times.
+Multiple plugins may be installed by issuing the ``--plugin`` argument multiple times.
 
 Packaged plugins
 ================
 
 Installed plugins may be installed into the same virtual environment as OCRmyPDF
 is installed into. They may be invoked using Python standard module naming.
+If you are intending to distribute a plugin, please package it.
 
 .. code-block:: bash
 
@@ -59,10 +59,74 @@ as packaged plugins, and these modules should begin with the name ``ocrmypdf_``
 similar to ``pytest`` packages such as ``pytest-cov`` (the package) and
 ``pytest_cov`` (the module).
 
+.. note::
+
+    We recommend plugin authors name their plugins with the prefix
+    ``ocrmypdf-`` (for the package name on PyPI) and ``ocrmypdf_`` (for the
+    module), just like pytest plugins. At the same time, please make it clear
+    that your package is not official.
+
+Setuptools plugins
+==================
+
+You can also create a plugin that OCRmyPDF will always automatically load if both are
+installed in the same virtual environment, using a setuptools entrypoint.
+
+Your package's ``setup.py`` would need to contain the following, for a plugin
+named ``ocrmypdf-exampleplugin``:
+
+.. code-block:: python
+
+    # sample ./setup.py file
+    from setuptools import setup
+
+    setup(
+        name="ocrmypdf-exampleplugin",
+        packages=["exampleplugin"],
+        # the following makes a plugin available to pytest
+        entry_points={"ocrmypdf": ["exampleplugin = exampleplugin.pluginmodule"]},
+    )
+
+.. code-block:: ini
+
+    # equivalent setup.cfg
+    [options.entry_points]
+    ocrmypdf =
+        exampleplugin = exampleplugin.pluginmodule
+
+Plugin requirements
+===================
+
+OCRmyPDF generally uses multiple worker processes. When a new worker is started,
+Python will import all plugins again, including all plugins that were imported earlier.
+This means that the global state of a plugin in one worker will not be shared with
+other workers. As such, plugin hook implementations should be stateless, relying
+only on their inputs. Hook implementations may use their input parameters to
+to obtain a reference to shared state prepared by another hook implementation.
+Plugins must expect that other instances of the plugin will be running
+simultaneously.
+
+The ``context`` object that is passed to many hooks can be used to share information
+about a file being worked on. Plugins must write private, plugin-specific data to
+a subfolder named ``{options.work_folder}/ocrmypdf-plugin-name``. Plugins MAY
+read and write files in ``options.work_folder``, but should be aware that their
+semantics are subject to change.
+
+OCRmyPDF will delete ``options.work_folder`` when it has finished OCRing
+a file, unless invoked with ``--keep-temporary-files``.
+
+The documentation for some plugin hooks contain a detailed description of the
+execution context in which they will be called.
+
+Plugins should be prepared to work whether executed in worker threads or worker
+processes. Generally, OCRmyPDF uses processes, but has a semi-hidden threaded
+argument that simplifies debugging.
+
+
 Plugin hooks
 ============
 
-A plugin may provide the following hooks. Hooks should be decorated with
+A plugin may provide the following hooks. Hooks must be decorated with
 ``ocrmypdf.hookimpl``, for example:
 
 .. code-block:: python
@@ -73,8 +137,72 @@ A plugin may provide the following hooks. Hooks should be decorated with
     def add_options(parser):
         pass
 
-The following is a complete list of hooks that may be installed and when
+The following is a complete list of hooks that are available, and when
 they are called.
 
-.. automodule:: ocrmypdf.pluginspec
+.. _firstresult:
+
+**Note on firstresult hooks**
+
+If multiple plugins install implementations for this hook, they will be called in
+the reverse of the order in which they are installed (i.e., last plugin wins).
+When each hook implementation is called in order, the first implementation that
+returns a value other than ``None`` will "win" and prevent execution of all other
+hooks. As such, you cannot "chain" a series of plugin filters together in this
+way. Instead, a single hook implementation should be responsible for any such
+chaining operations.
+
+Custom command line arguments
+-----------------------------
+
+.. autofunction:: ocrmypdf.pluginspec.add_options
+
+.. autofunction:: ocrmypdf.pluginspec.check_options
+
+Execution and progress reporting
+--------------------------------
+
+.. autoclass: ocrmypdf.pluginspec.Executor
     :members:
+
+.. autofunction:: ocrmypdf.pluginspec.get_logging_console
+
+.. autofunction:: ocrmypdf.pluginspec.get_executor
+
+.. autofunction:: ocrmypdf.pluginspec.get_progressbar_class
+
+Applying special behavior before processing
+-------------------------------------------
+
+.. autofunction:: ocrmypdf.pluginspec.validate
+
+PDF page to image
+-----------------
+
+.. autofunction:: ocrmypdf.pluginspec.rasterize_pdf_page
+
+Modifying intermediate images
+-----------------------------
+
+.. autofunction:: ocrmypdf.pluginspec.filter_ocr_image
+
+.. autofunction:: ocrmypdf.pluginspec.filter_page_image
+
+.. autofunction:: ocrmypdf.pluginspec.filter_pdf_page
+
+OCR engine
+----------
+
+.. autofunction:: ocrmypdf.pluginspec.get_ocr_engine
+
+.. autoclass:: ocrmypdf.pluginspec.OcrEngine
+    :members:
+
+    .. automethod:: __str__
+
+.. autoclass:: ocrmypdf.pluginspec.OrientationConfidence
+
+PDF/A production
+----------------
+
+.. autofunction:: ocrmypdf.pluginspec.generate_pdfa

misc/batch.py

@@ -1,50 +1,62 @@
 #!/usr/bin/env python3
-# Original version by DeliciousPickle@github; modified
+# Copyright 2016 findingorder: https://github.com/findingorder
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
 
 # This script must be edited to meet your needs.
 
 import logging
 import os
 import sys
+from pathlib import Path
 
 import ocrmypdf
 
 # pylint: disable=logging-format-interpolation
 # pylint: disable=logging-not-lazy
 
-script_dir = os.path.dirname(os.path.realpath(__file__))
-print(script_dir + '/batch.py: Start')
+script_dir = Path(__file__).parent
 
 if len(sys.argv) > 1:
-    start_dir = sys.argv[1]
+    start_dir = Path(sys.argv[1])
 else:
-    start_dir = '.'
+    start_dir = Path('.')
 
 if len(sys.argv) > 2:
-    log_file = sys.argv[2]
+    log_file = Path(sys.argv[2])
 else:
-    log_file = script_dir + '/ocr-tree.log'
+    log_file = script_dir.with_name('ocr-tree.log')
 
 logging.basicConfig(
     level=logging.INFO,
     format='%(asctime)s %(message)s',
     filename=log_file,
-    filemode='w',
+    filemode='a',
 )
 
 ocrmypdf.configure_logging(ocrmypdf.Verbosity.default)
 
-for dir_name, subdirs, file_list in os.walk(start_dir):
-    logging.info(dir_name + '\n')
-    os.chdir(dir_name)
-    for filename in file_list:
-        file_ext = os.path.splitext(filename)[1]
-        if file_ext == '.pdf':
-            full_path = dir_name + '/' + filename
-            print(full_path)
-            result = ocrmypdf.ocr(filename, filename, deskew=True)
-            if result == ocrmypdf.ExitCode.already_done_ocr:
-                print("Skipped document because it already contained text")
-            elif result == ocrmypdf.ExitCode.ok:
-                print("OCR complete")
-            logging.info(result)
+for filename in start_dir.glob("**/*.py"):
+    logging.info(f"Processing {filename}")
+    result = ocrmypdf.ocr(filename, filename, deskew=True)
+    if result == ocrmypdf.ExitCode.already_done_ocr:
+        logging.error("Skipped document because it already contained text")
+    elif result == ocrmypdf.ExitCode.ok:
+        logging.info("OCR complete")
+    logging.info(result)

misc/completion/ocrmypdf.bash

@@ -1,5 +1,26 @@
 # ocrmypdf completion                                     -*- shell-script -*-
 
+# Copyright 2019 Frank Pille
+# Copyright 2020 Alex Willner
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
 set -o errexit
 
 _ocrmypdf()

misc/completion/ocrmypdf.fish

@@ -1,3 +1,23 @@
+# Copyright 2020 James R. Barlow
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
 complete -c ocrmypdf -x -n '__fish_is_first_arg' -l version
 complete -c ocrmypdf -x -n '__fish_is_first_arg' -s h -s "?" -l help
 
@@ -34,12 +54,14 @@ function __fish_ocrmypdf_output_type
     echo -e "pdfa-1\t"(_ "output a PDF/A-1b")
     echo -e "pdfa-2\t"(_ "output a PDF/A-2b")
     echo -e "pdfa-3\t"(_ "output a PDF/A-3b")
+    echo -e "none\t"(_ "do not produce an output PDF (for example, if you only care about --sidecar)")
 end
 complete -c ocrmypdf -x -l output-type -a '(__fish_ocrmypdf_output_type)' -d "select PDF output options"
 
 function __fish_ocrmypdf_pdf_renderer
     echo -e "auto\t"(_ "auto select PDF renderer")
-    echo -e "hocr\t"(_ "use hocr renderer")
+    echo -e "hocr\t"(_ "use hOCR renderer")
+    echo -e "hocrdebug\t"(_ "uses hOCR renderer in debug mode, showing recognized text")
     echo -e "sandwich\t"(_ "use sandwich renderer")
 end
 complete -c ocrmypdf -x -l pdf-renderer -a '(__fish_ocrmypdf_pdf_renderer)' -d "select PDF renderer options"
@@ -115,4 +137,4 @@ 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)"
+complete -c ocrmypdf -x -a "(__fish_complete_suffix .pdf; __fish_complete_suffix .PDF; __fish_complete_suffix .jpg; __fish_complete_suffix .png)"

misc/docker-compose.example.yml

@@ -9,7 +9,7 @@ services:
       - "/media/scan:/input"
       - "/mnt/scan:/output"
     environment:
-      - OCR_OUTPUT_DIRECTORY_YEAR_MONT=0
+      - OCR_OUTPUT_DIRECTORY_YEAR_MONTH=0
     user: "<SET TO YOUR USER ID>:<SET TO YOUR GROUP ID>"
     entrypoint: python3
     command: watcher.py

misc/example_plugin.py

@@ -1,17 +1,41 @@
 # © 2020 James R Barlow: https://github.com/jbarlow83
 #
-# 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.
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
 #
-# 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.
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
 #
-# You should have received a copy of the GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+"""
+An example of an OCRmyPDF plugin.
+
+This plugin adds two new command line arguments
+    --grayscale-ocr: converts the image to grayscale before performing OCR on it
+        (This is occasionally useful for images whose color confounds OCR. It only
+        affects the image shown to OCR. The image is not saved.)
+    --mono-page: converts pages all pages in the output file to black and white
+
+To use this from the command line:
+    ocrmypdf --plugin path/to/example_plugin.py --mono-page input.pdf output.pdf
+
+To use this as an API:
+    import ocrmypdf
+    ocrmypdf.ocr('input.pdf', 'output.pdf',
+        plugins=['path/to/example_plugin.py'], mono_page=True
+    )
+"""
 
 import logging
 
@@ -25,6 +49,7 @@ log = logging.getLogger(__name__)
 @hookimpl
 def add_options(parser):
     parser.add_argument('--grayscale-ocr', action='store_true')
+    parser.add_argument('--mono-page', action='store_true')
 
 
 @hookimpl
@@ -47,7 +72,13 @@ def filter_ocr_image(page, image):
 
 @hookimpl
 def filter_page_image(page, image_filename):
-    output = image_filename.with_suffix('.jpg')
-    with Image.open(image_filename) as im:
-        im.save(output)
-    return output
+    if page.options.mono_page:
+        with Image.open(image_filename) as im:
+            im = im.convert('1')
+            im.save(image_filename)
+        return image_filename
+    else:
+        output = image_filename.with_suffix('.jpg')
+        with Image.open(image_filename) as im:
+            im.save(output)
+        return output

misc/synology.py

@@ -1,5 +1,23 @@
 #!/bin/env python3
-# Contributed by github.com/Enantiomerie
+# Copyright 2017 github.com/Enantiomerie
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
 
 # This script must be edited to meet your needs.
 
@@ -28,7 +46,7 @@ if len(sys.argv) > 1:
 else:
     start_dir = '.'
 
-for dir_name, subdirs, file_list in os.walk(start_dir):
+for dir_name, _subdirs, file_list in os.walk(start_dir):
     logging.info(dir_name)
     os.chdir(dir_name)
     for filename in file_list:
@@ -61,8 +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

@@ -1,18 +1,24 @@
+#!/usr/bin/env python3
 # Copyright (C) 2019 Ian Alexander: https://github.com/ianalexander
 # Copyright (C) 2020 James R Barlow: https://github.com/jbarlow83
 #
-# 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.
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
 #
-# 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.
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
 #
-# You should have received a copy of the GNU General Public License
-# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
 
 import json
 import logging
@@ -31,16 +37,21 @@ import ocrmypdf
 
 # pylint: disable=logging-format-interpolation
 
+
+def getenv_bool(name: str, default: str = 'False'):
+    return os.getenv(name, default).lower() in ('true', 'yes', 'y', '1')
+
+
 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', ''))
-ON_SUCCESS_DELETE = bool(os.getenv('OCR_ON_SUCCESS_DELETE', ''))
-DESKEW = bool(os.getenv('OCR_DESKEW', ''))
+OUTPUT_DIRECTORY_YEAR_MONTH = getenv_bool('OCR_OUTPUT_DIRECTORY_YEAR_MONTH')
+ON_SUCCESS_DELETE = getenv_bool('OCR_ON_SUCCESS_DELETE')
+DESKEW = getenv_bool('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()
-PATTERNS = ['*.pdf']
+USE_POLLING = getenv_bool('OCR_USE_POLLING')
+LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO')
+PATTERNS = ['*.pdf', '*.PDF']
 
 log = logging.getLogger('ocrmypdf-watcher')
 
@@ -112,7 +123,12 @@ 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(
@@ -130,7 +146,7 @@ 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:

misc/webservice.py

@@ -1,3 +1,4 @@
+#!/usr/bin/env python3
 # webservice.py wrapper for OCRmyPDF
 # Copyright (C) 2019 James R. Barlow: github.com/jbarlow83
 #
@@ -28,16 +29,7 @@ import shlex
 from subprocess import PIPE, run
 from tempfile import TemporaryDirectory
 
-from flask import (
-    Flask,
-    Response,
-    abort,
-    flash,
-    redirect,
-    request,
-    send_from_directory,
-    url_for,
-)
+from flask import Flask, Response, request, send_from_directory
 from werkzeug.utils import secure_filename
 
 app = Flask(__name__)
@@ -45,7 +37,7 @@ app.secret_key = "secret"
 app.config['MAX_CONTENT_LENGTH'] = 50_000_000
 app.config.from_envvar("OCRMYPDF_WEBSERVICE_SETTINGS", silent=True)
 
-ALLOWED_EXTENSIONS = set(["pdf"])
+ALLOWED_EXTENSIONS = {"pdf"}
 
 
 def allowed_file(filename):

pyproject.toml

@@ -3,15 +3,17 @@ requires = [
   "setuptools >= 30.3.0",
   "wheel",
   "cffi",
-  "setuptools_scm",
+  "setuptools_scm[toml] >= 3.4",
   "setuptools_scm_git_archive"
 ]
 build-backend = "setuptools.build_meta"
 
+[tool.setuptools_scm]
+version_scheme = "post-release"
+
 [tool.black]
 line-length = 88
-target-version = ["py36",
-"py37", "py38"]
+target-version = ["py36", "py37", "py38"]
 skip-string-normalization = true
 include = '\.pyi?$'
 exclude = '''
@@ -32,3 +34,49 @@ exclude = '''
   | src/ocrmypdf/lib/_leptonica.py
 )/
 '''
+
+[tool.coverage.run]
+branch = true
+parallel = true
+concurrency = ["multiprocessing"]
+
+[tool.coverage.paths]
+source = ["src/ocrmypdf"]
+
+[tool.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:"
+]
+
+[tool.isort]
+profile = "black"
+known_first_party = "ocrmypdf"
+known_third_party = ["PIL", "_cffi_backend", "cffi", "flask", "img2pdf", "ocrmypdf", "pdfminer", "pikepdf", "pkg_resources", "pluggy", "pytest", "reportlab", "setuptools", "sphinx_rtd_theme", "tqdm", "watchdog", "werkzeug"]
+
+[tool.pytest.ini_options]
+minversion = "6.0"
+norecursedirs = ["lib", ".pc", ".git", "venv", "output", "cache", "resources"]
+testpaths = ["tests"]
+addopts = "-n auto"
+markers = ["slow"]
+filterwarnings = ["ignore:.*XMLParser.*:DeprecationWarning"]
+
+[tool.mypy]
+
+[[tool.mypy.overrides]]
+module = [
+  'pluggy', 'tqdm', 'coloredlogs', 'img2pdf', 'cffi', '_cffi_backend', 'pdfminer.*', 'reportlab.*'
+]
+ignore_missing_imports = true

requirements/main.txt

@@ -1,12 +1,10 @@
-# requirements.txt can be used to replicate the developer's build environment
-# setup.py lists a separate set of requirements that are looser to simplify
-# installation
-cffi == 1.14.0
-coloredlogs == 14.0  # technically optional
-img2pdf == 0.3.6
-pdfminer.six == 20200517
-pikepdf == 1.15.1
+# Deprecated and not maintained; use "pip install ocrmypdf" instead
+cffi == 1.14.5
+coloredlogs == 15.0  # technically optional
+img2pdf == 0.4.0
+pdfminer.six == 20201018
+pikepdf == 2.10.0
 pluggy == 0.13.1
-Pillow == 7.1.2
-reportlab == 3.5.42
-tqdm == 4.46.1
+Pillow == 8.3.2
+reportlab == 3.5.66
+tqdm == 4.59.0

requirements/test.txt

@@ -1,7 +1,7 @@
-pytest >= 5.0.0
-pytest-helpers-namespace >= 2019.1.8
-pytest-xdist >= 1.31.0
-pytest-cov >= 2.10.0
+# Deprecated and not maintained; use "pip install ocrmypdf[test]" instead
+pytest >= 6.0.0
+pytest-xdist >= 2.2.0
+pytest-cov >= 2.11.1
 python-xmp-toolkit == 2.0.1  # requires apt-get install libexempi3
                      # or brew install exempi
 #PyMuPDF == 1.13.4    # optional

requirements/watcher.txt

@@ -1 +1,2 @@
-watchdog == 0.10.2
+# Deprecated and not maintained; use "pip install ocrmypdf[watcher]" instead
+watchdog == 1.0.2

requirements/webservice.txt

@@ -1 +1,2 @@
+# Deprecated and not maintained; use "pip install ocrmypdf[webservice]" instead
 Flask >= 1, < 2

setup.cfg

@@ -1,29 +1,116 @@
+[metadata]
+name = ocrmypdf
+description = OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
+long_description = file: README.md
+long_description_content_type = text/markdown
+url = https://github.com/jbarlow83/OCRmyPDF
+author = James R. Barlow
+author_email = james@purplerock.ca
+license = MPL-2.0
+license_file = LICENSE
+license_files =
+    LICENSE
+classifiers =
+    Development Status :: 5 - Production/Stable
+    Environment :: Console
+    Intended Audience :: End Users/Desktop
+    Intended Audience :: Science/Research
+    Intended Audience :: System Administrators
+    License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
+    Operating System :: MacOS :: MacOS X
+    Operating System :: Microsoft :: Windows :: Windows 10
+    Operating System :: POSIX
+    Operating System :: POSIX :: BSD
+    Operating System :: POSIX :: Linux
+    Programming Language :: Python :: 3
+    Programming Language :: Python :: 3 :: Only
+    Programming Language :: Python :: 3.6
+    Programming Language :: Python :: 3.7
+    Programming Language :: Python :: 3.8
+    Programming Language :: Python :: 3.9
+    Programming Language :: Python :: 3.10
+    Topic :: Scientific/Engineering :: Image Recognition
+    Topic :: Text Processing :: Indexing
+    Topic :: Text Processing :: Linguistic
+keywords =
+    PDF
+    OCR
+    optical character recognition
+    PDF/A
+    scanning
+project_urls =
+    Documentation = https://ocrmypdf.readthedocs.io/
+    Source = https://github.com/jbarlow83/ocrmypdf
+    Tracker = https://github.com/jbarlow83/ocrmypdf/issues
+
+[options]
+packages = find:
+install_requires =
+    Pillow>=8.2.0
+    cffi>=1.9.1  # must be a setup and install requirement
+    coloredlogs>=14.0  # strictly optional
+    img2pdf>=0.3.0,<0.5  # pure Python
+    pdfminer.six!=20200720,>=20191110,<=20211012
+    pikepdf>=2.10.0
+    pluggy>=0.13.0,<2
+    reportlab>=3.5.66
+    tqdm>=4
+    importlib-metadata>=4;python_version<'3.8'  # until Python 3.8
+    importlib-resources>=5;python_version<'3.9'  # until Python 3.9
+    pikepdf<3;implementation_name=="pypy" and python_version=='3.6'
+python_requires = >=3.6
+include_package_data = True
+package_dir =
+    =src
+platforms = any
+setup_requires =
+    cffi>=1.9.1  # to build the leptonica module
+    setuptools-scm
+    setuptools-scm-git-archive
+zip_safe = False
+
+[options.packages.find]
+where = src
+
+[options.entry_points]
+console_scripts =
+    ocrmypdf = ocrmypdf.__main__:run
+
+[options.extras_require]
+docs =
+    sphinx
+    sphinx-issues
+    sphinx-rtd-theme
+extended_test =
+    PyMuPDF==1.13.4
+test =
+    coverage[toml]>=5
+    pytest>=6.0.0
+    pytest-cov>=2.11.1
+    pytest-xdist>=2.2.0
+    python-xmp-toolkit==2.0.1  # also requires apt-get install libexempi3
+watcher =
+    watchdog>=1.0.2,<3
+webservice =
+    Flask>=1,<3
+
+[options.package_data]
+ocrmypdf =
+    data/sRGB.icc
+    py.typed
+
 [bdist_wheel]
-python-tag = py35
+python-tag = py36
 
 [aliases]
-test=pytest
+test = pytest
 
 [check-manifest]
 ignore =
-	.github
+    .github
 
-[tool:pytest]
-norecursedirs = lib .pc .git output cache resources
-testpaths = tests
-filterwarnings =
-	ignore:.*XMLParser.*:DeprecationWarning
-markers =
-	slow
-
-[isort]
-multi_line_output=3
-include_trailing_comma=True
-force_grid_wrap=0
-use_parentheses=True
-line_length=88
-known_first_party = ocrmypdf
-known_third_party = PIL,_cffi_backend,cffi,flask,img2pdf,pdfminer,pikepdf,pkg_resources,pluggy,pytest,reportlab,setuptools,sphinx_rtd_theme,tqdm,watchdog,werkzeug
-
-[metadata]
-license_file = LICENSE
+[flake8]
+ignore = D203,F401,W503,E501,E203,F841
+exclude = .git,__pycache__,docs/conf.py,build,dist,.venv,.venvpp,.eggs,tmp,src/ocrmypdf/lib/
+max-complexity = 10
+max-line-length = 100

setup.py

@@ -1,102 +1,19 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-# © 2015 James R. Barlow: github.com/jbarlow83
+# © 2021 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
-
-from __future__ import print_function, unicode_literals
-
-import sys
-
-from setuptools import find_packages, setup
-
-if sys.version_info < (3, 6):
-    print("Python 3.6 or newer is required", file=sys.stderr)
-    sys.exit(1)
-
-if 'upload' in sys.argv[1:]:
-    print('Use twine to upload the package - setup.py upload is insecure')
-    sys.exit(1)
-
-tests_require = open('requirements/test.txt', encoding='utf-8').read().splitlines()
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
-def readme():
-    with open('README.md', encoding='utf-8') as f:
-        return f.read()
-
+from setuptools import setup
 
+# Minimal setup to support older setuptools/setuptools_scm
 setup(
-    name='ocrmypdf',
-    description='OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched',
-    long_description=readme(),
-    long_description_content_type='text/markdown',
-    url='https://github.com/jbarlow83/OCRmyPDF',
-    author='James R. Barlow',
-    author_email='james@purplerock.ca',
-    packages=find_packages('src', exclude=["tests", "tests.*"]),
-    package_dir={'': 'src'},
-    keywords=['PDF', 'OCR', 'optical character recognition', 'PDF/A', 'scanning'],
-    classifiers=[
-        "Programming Language :: Python :: 3.6",
-        "Programming Language :: Python :: 3.7",
-        "Programming Language :: Python :: 3.8",
-        "Development Status :: 5 - Production/Stable",
-        "Environment :: Console",
-        "Intended Audience :: End Users/Desktop",
-        "Intended Audience :: Science/Research",
-        "Intended Audience :: System Administrators",
-        "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
-        "Operating System :: MacOS :: MacOS X",
-        "Operating System :: Microsoft :: Windows :: Windows 10",
-        "Operating System :: POSIX",
-        "Operating System :: POSIX :: BSD",
-        "Operating System :: POSIX :: Linux",
-        "Topic :: Scientific/Engineering :: Image Recognition",
-        "Topic :: Text Processing :: Indexing",
-        "Topic :: Text Processing :: Linguistic",
-    ],
-    python_requires=' >= 3.6',
     setup_requires=[  # can be removed whenever we can drop pip 9 support
         'cffi >= 1.9.1',  # to build the leptonica module
-        'pytest-runner',  # to enable python setup.py test
         'setuptools_scm',  # so that version will work
         'setuptools_scm_git_archive',  # enable version from github tarballs
     ],
     use_scm_version={'version_scheme': 'post-release'},
     cffi_modules=['src/ocrmypdf/lib/compile_leptonica.py:ffibuilder'],
-    install_requires=[
-        'cffi >= 1.9.1',  # must be a setup and install requirement
-        'coloredlogs >= 14.0',  # strictly optional
-        'img2pdf >= 0.3.0, < 0.4',  # pure Python, so track HEAD closely
-        'pdfminer.six >= 20191110, <= 20200517',
-        'pikepdf >= 1.14.0, < 2',
-        'Pillow >= 7.0.0',
-        'pluggy >= 0.13.0',
-        'reportlab >= 3.3.0',  # oldest released version with sane image handling
-        'tqdm >= 4',
-    ],
-    tests_require=tests_require,
-    entry_points={'console_scripts': ['ocrmypdf = ocrmypdf.__main__:run']},
-    package_data={'ocrmypdf': ['data/sRGB.icc']},
-    include_package_data=True,
-    zip_safe=False,
-    project_urls={
-        'Documentation': 'https://ocrmypdf.readthedocs.io/',
-        'Source': 'https://github.com/jbarlow83/ocrmypdf',
-        'Tracker': 'https://github.com/jbarlow83/ocrmypdf/issues',
-    },
 )

src/ocrmypdf/RELEASE.md

@@ -0,0 +1,35 @@
+# Release checklist
+
+## Patch release
+
+- Check `pytest`
+
+- Update release notes
+
+## Minor release
+
+## Major release
+
+- Run `pre-commit autoupdate`
+
+- Check README.md
+
+- Check setup.py
+
+    - Are classifiers up to date?
+    - Is `python_requires` correct?
+    - Python 3.6 is EOL on December 2021-12. Could drop support then.
+    - Can we tighten any `install_requires` dependencies?
+
+- Search for old version shims we can remove
+
+    - "shim"
+    - ` pikepdf.__version__`
+
+- Search for deprecation: search all files for deprec*, etc.
+
+- Check requirements in setup.cfg
+
+- Delete `tests/cache`, do `pytest --runslow`, and update cache.
+
+- Do `pytest --cov-report html`

src/ocrmypdf/__init__.py

@@ -1,24 +1,15 @@
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
 from pluggy import HookimplMarker as _HookimplMarker
 
 from ocrmypdf import helpers, hocrtransform, leptonica, pdfa, pdfinfo
+from ocrmypdf._concurrent import Executor
+from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._version import PROGRAM_NAME, __version__
 from ocrmypdf.api import Verbosity, configure_logging, ocr
 from ocrmypdf.exceptions import (

src/ocrmypdf/__main__.py

@@ -1,23 +1,14 @@
 #!/usr/bin/env python3
 # © 2015-19 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 import logging
 import os
+import signal
 import sys
 from multiprocessing import set_start_method
 
@@ -26,11 +17,20 @@ from ocrmypdf._plugin_manager import get_parser_options_plugins
 from ocrmypdf._sync import run_pipeline
 from ocrmypdf._validation import check_closed_streams, check_options
 from ocrmypdf.api import Verbosity, configure_logging
-from ocrmypdf.exceptions import BadArgsError, ExitCode, MissingDependencyError
+from ocrmypdf.exceptions import (
+    BadArgsError,
+    ExitCode,
+    InputFileError,
+    MissingDependencyError,
+)
 
 log = logging.getLogger('ocrmypdf')
 
 
+def sigbus(*args):
+    raise InputFileError("Lost access to the input file")
+
+
 def run(args=None):
     _parser, options, plugin_manager = get_parser_options_plugins(args=args)
 
@@ -47,7 +47,10 @@ def run(args=None):
         verbosity = Verbosity.quiet
         options.progress_bar = False
     configure_logging(
-        verbosity, progress_bar_friendly=options.progress_bar, manage_root_logger=True
+        verbosity,
+        progress_bar_friendly=options.progress_bar,
+        manage_root_logger=True,
+        plugin_manager=plugin_manager,
     )
     log.debug('ocrmypdf %s', __version__)
     try:
@@ -62,6 +65,9 @@ def run(args=None):
         log.error(e)
         return ExitCode.missing_dependency
 
+    if hasattr(signal, 'SIGBUS'):
+        signal.signal(signal.SIGBUS, sigbus)
+
     result = run_pipeline(options=options, plugin_manager=plugin_manager)
     return result
 

src/ocrmypdf/_concurrent.py

@@ -1,135 +1,133 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
-import logging
-import logging.handlers
-import multiprocessing
-import os
-import signal
-import sys
 import threading
-from multiprocessing import Pool as ProcessPool
-from multiprocessing.dummy import Pool as ThreadPool
+from abc import ABC, abstractmethod
 from typing import Callable, Iterable, Optional
 
-from tqdm import tqdm
+
+def _task_noop(*_args, **_kwargs):
+    return
 
 
-def log_listener(queue):
-    """Listen to the worker processes and forward the messages to logging
+class NullProgressBar:
+    def __init__(self, **kwargs):
+        pass
 
-    For simplicity this is a thread rather than a process. Only one process
-    should actually write to sys.stderr or whatever we're using, so if this is
-    made into a process the main application needs to be directed to it.
+    def __enter__(self):
+        return self
 
-    See https://docs.python.org/3/howto/logging-cookbook.html#logging-to-a-single-file-from-multiple-processes
+    def __exit__(self, exc_type, exc_value, traceback):
+        return False
+
+    def update(self, _arg=None):
+        return
+
+
+class Executor(ABC):
+    pool_lock = threading.Lock()
+    pbar_class = NullProgressBar
+
+    def __init__(self, *, pbar_class=None):
+        if pbar_class:
+            self.pbar_class = pbar_class
+
+    def __call__(
+        self,
+        *,
+        use_threads: bool,
+        max_workers: int,
+        tqdm_kwargs: dict,
+        worker_initializer: Optional[Callable] = None,
+        task: Optional[Callable] = None,
+        task_arguments: Optional[Iterable] = None,
+        task_finished: Optional[Callable] = None,
+    ) -> None:
+        """
+        Set up parallel execution and progress reporting.
+
+        Args:
+            use_threads: If ``False``, the workload is the sort that will benefit from
+                running in a multiprocessing context (for example, it uses Python
+                heavily, and parallelizing it with threads is not expected to be
+                performant).
+            max_workers: The maximum number of workers that should be run.
+            tdqm_kwargs: Arguments to set up the progress bar.
+            worker_initializer: Called when a worker is initialized, in the worker's
+                execution context. If the child workers are processes, it must be
+                possible to marshall/pickle the worker initializer.
+                ``functools.partial`` can be used to bind parameters.
+            task: Called when the worker starts a new task, in the worker's execution
+                context. Must be possible to marshall to the worker.
+            task_finished: Called when a worker finishes a task, in the parent's
+                context.
+            task_arguments: An iterable that generates a group of parameters for each
+                task. This runs in the parent's context, but the parameters must be
+                marshallable to the worker.
+        """
+
+        if not task_arguments:
+            return  # Nothing to do!
+        if not worker_initializer:
+            worker_initializer = _task_noop
+        if not task_finished:
+            task_finished = _task_noop
+        if not task:
+            task = _task_noop
+
+        with self.pool_lock:
+            self._execute(
+                use_threads=use_threads,
+                max_workers=max_workers,
+                tqdm_kwargs=tqdm_kwargs,
+                worker_initializer=worker_initializer,
+                task=task,
+                task_arguments=task_arguments,
+                task_finished=task_finished,
+            )
+
+    @abstractmethod
+    def _execute(
+        self,
+        *,
+        use_threads: bool,
+        max_workers: int,
+        tqdm_kwargs: dict,
+        worker_initializer: Callable,
+        task: Callable,
+        task_arguments: Iterable,
+        task_finished: Callable,
+    ):
+        """Custom executors should override this method."""
+
+
+def setup_executor(plugin_manager) -> Executor:
+    pbar_class = plugin_manager.hook.get_progressbar_class()
+    return plugin_manager.hook.get_executor(progressbar_class=pbar_class)
+
+
+class SerialExecutor(Executor):
+    """Implements a purely sequential executor using the parallel protocol.
+
+    The current process/thread will be the worker that executes all tasks
+    in order. As such, ``worker_initializer`` will never be called.
     """
 
-    while True:
-        try:
-            record = queue.get()
-            if record is None:
-                break
-            logger = logging.getLogger(record.name)
-            logger.handle(record)
-        except Exception:  # pylint: disable=broad-except
-            import traceback  # pylint: disable=import-outside-toplevel
-
-            print("Logging problem", file=sys.stderr)
-            traceback.print_exc(file=sys.stderr)
-
-
-def process_init(queue, user_init):
-    """Initialize a process pool worker"""
-
-    # Ignore SIGINT (our parent process will kill us gracefully)
-    signal.signal(signal.SIGINT, signal.SIG_IGN)
-
-    # Reconfigure the root logger for this process to send all messages to a queue
-    h = logging.handlers.QueueHandler(queue)
-    root = logging.getLogger()
-    root.handlers = []
-    root.addHandler(h)
-
-    if user_init:
-        user_init()
-
-
-def thread_init(_queue, user_init):
-    if user_init:
-        user_init()
-
-
-def exec_progress_pool(
-    *,
-    use_threads: bool,
-    max_workers: int,
-    tqdm_kwargs: dict,
-    task_initializer: Optional[Callable] = None,
-    task: Optional[Callable] = None,
-    task_arguments: Optional[Iterable] = None,
-    task_finished: Optional[Callable] = None,
-):
-    log_queue = multiprocessing.Queue(-1)
-    listener = threading.Thread(target=log_listener, args=(log_queue,))
-
-    if use_threads:
-        pool_class = ThreadPool
-        initializer = thread_init
-    else:
-        pool_class = ProcessPool
-        initializer = process_init
-    listener.start()
-
-    with tqdm(**tqdm_kwargs) as pbar:
-        pool = pool_class(
-            processes=max_workers,
-            initializer=initializer,
-            initargs=(log_queue, task_initializer),
-        )
-        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
-        except KeyboardInterrupt:
-            # Terminate pool so we exit instantly
-            pool.terminate()
-            # Don't try listener.join() here, will deadlock
-            raise
-        except Exception:
-            if not os.environ.get("PYTEST_CURRENT_TEST", ""):
-                # Unless inside pytest, exit immediately because no one wants
-                # to wait for child processes to finalize results that will be
-                # thrown away. Inside pytest, we want child processes to exit
-                # cleanly so that they output an error messages or coverage data
-                # we need from them.
-                pool.terminate()
-            raise
-        finally:
-            # Terminate log listener
-            log_queue.put_nowait(None)
-            pool.close()
-            pool.join()
-
-    listener.join()
+    def _execute(
+        self,
+        *,
+        use_threads: bool,
+        max_workers: int,
+        tqdm_kwargs: dict,
+        worker_initializer: Callable,
+        task: Callable,
+        task_arguments: Iterable,
+        task_finished: Callable,
+    ):  # pylint: disable=unused-argument
+        with self.pbar_class(**tqdm_kwargs) as pbar:
+            for args in task_arguments:
+                result = task(args)
+                task_finished(result, pbar)

src/ocrmypdf/_exec/__init__.py

@@ -1,18 +1,8 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 """Manage third party executables"""

src/ocrmypdf/_exec/ghostscript.py

@@ -1,19 +1,9 @@
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 """Interface to Ghostscript executable"""
 
@@ -25,34 +15,38 @@ from os import fspath
 from pathlib import Path
 from shutil import which
 from subprocess import PIPE, CalledProcessError
+from typing import Optional
 
 from PIL import Image
 
 from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
 from ocrmypdf.helpers import Resolution
-from ocrmypdf.subprocess import get_version, run
+from ocrmypdf.subprocess import get_version, run, run_polling_stderr
 
 log = logging.getLogger(__name__)
 
-GS = 'gs'
-if os.name == 'nt':
-    GS = which('gswin64c')
-    if not GS:
-        GS = which('gswin32c')
-        if not GS:
-            raise MissingDependencyError(
-                """
-                ---------------------------------------------------------------------
-                This error normally occurs when ocrmypdf can't Ghostscript.  Please
-                ensure Ghostscript is installed and its location is added to the
-                system PATH environment variable.
+missing_gs_error = """
+---------------------------------------------------------------------
+This error normally occurs when ocrmypdf find can't Ghostscript.
+Please ensure Ghostscript is installed and its location is added to
+the system PATH environment variable.
 
-                For details see:
-                    https://ocrmypdf.readthedocs.io/en/latest/installation.html
-                ---------------------------------------------------------------------
-                """
-            )
-    GS = Path(GS).stem
+For details see:
+    https://ocrmypdf.readthedocs.io/en/latest/installation.html
+---------------------------------------------------------------------
+"""
+
+_gswin = None
+if os.name == 'nt':
+    _gswin = which('gswin64c')
+    if not _gswin:
+        _gswin = which('gswin32c')
+        if not _gswin:
+            raise MissingDependencyError(missing_gs_error)
+    _gswin = Path(_gswin).stem
+
+GS = _gswin if _gswin else 'gs'
+del _gswin
 
 
 def version():
@@ -62,22 +56,20 @@ def version():
 def jpeg_passthrough_available() -> bool:
     """Returns True if the installed version of Ghostscript supports JPEG passthru
 
-    Prior to 9.23, Ghostscript decode and re-encoded JPEGs internally. In 9.23
+    Prior to 9.23, Ghostscript decoded and re-encoded JPEGs internally. In 9.23
     it gained the ability to keep JPEGs unmodified. However, the 9.23
     implementation was buggy and would deletes the last two bytes of images in
     some cases, as reported here.
     https://bugs.ghostscript.com/show_bug.cgi?id=699216
 
     The issue was fixed for 9.24, hence that is the first version we consider
-    the feature available. (However, we don't use 9.24 at all, so the first
-    version that allows JPEG passthrough is 9.25.
-
+    the feature available. (Ghostscript 9.24 has its own problems is blacklisted.)
     """
     return version() >= '9.24'
 
 
 def _gs_error_reported(stream) -> bool:
-    return re.search(r'error', stream, flags=re.IGNORECASE)
+    return True if re.search(r'error', stream, flags=re.IGNORECASE) else False
 
 
 def rasterize_pdf(
@@ -87,8 +79,8 @@ def rasterize_pdf(
     raster_device: str,
     raster_dpi: Resolution,
     pageno: int = 1,
-    page_dpi: Resolution = None,
-    rotation: int = None,
+    page_dpi: Optional[Resolution] = None,
+    rotation: Optional[int] = None,
     filter_vector: bool = False,
 ):
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units."""
@@ -128,8 +120,6 @@ def rasterize_pdf(
         stderr = p.stderr.decode(errors='replace')
         if _gs_error_reported(stderr):
             log.error(stderr)
-        elif stderr:
-            log.debug(stderr)
 
     with Image.open(BytesIO(p.stdout)) as im:
         if rotation is not None:
@@ -147,13 +137,44 @@ def rasterize_pdf(
         im.save(fspath(output_file), dpi=page_dpi)
 
 
+class GhostscriptFollower:
+    re_process = re.compile(r"Processing pages \d+ through (\d+).")
+    re_page = re.compile(r"Page (\d+)")
+
+    def __init__(self, progressbar_class):
+        self.count = 0
+        self.progressbar_class = progressbar_class
+        self.progressbar = None
+
+    def __call__(self, line):
+        if not self.progressbar_class:
+            return
+        if not self.progressbar:
+            m = self.re_process.match(line.strip())
+            if m:
+                self.count = int(m.group(1))
+                self.progressbar = self.progressbar_class(
+                    total=self.count, desc="PDF/A conversion", unit='page'
+                )
+                return
+        else:
+            m = self.re_page.match(line.strip())
+            if m:
+                self.progressbar.update()
+
+
 def generate_pdfa(
     pdf_pages,
     output_file: os.PathLike,
+    *,
     compression: str,
     pdf_version: str = '1.5',
     pdfa_part: str = '2',
+    progressbar_class=None,
 ):
+    # Ghostscript's compression is all or nothing. We can either force all images
+    # to JPEG, force all to Flate/PNG, or let it decide how to encode the images.
+    # In most case it's best to let it decide.
     compression_args = []
     if compression == 'jpeg':
         compression_args = [
@@ -175,14 +196,16 @@ def generate_pdfa(
             "-dAutoFilterGrayImages=true",
         ]
 
+    strategy = 'LeaveColorUnchanged'
     # Older versions of Ghostscript expect a leading slash in
     # sColorConversionStrategy, newer ones should not have it. See Ghostscript
     # git commit fe1c025d.
-    strategy = 'RGB' if version() >= '9.19' else '/RGB'
+    strategy = ('/' + strategy) if version() < '9.19' else strategy
 
     if version() == '9.23':
-        # 9.23: new feature JPEG passthrough is broken in some cases, best to
-        # disable it always
+        # 9.23: added JPEG passthrough as a new feature, but with a bug that
+        # incorrectly formats some images. Fixed as of 9.24. So we disable this
+        # feature for 9.23.
         # https://bugs.ghostscript.com/show_bug.cgi?id=699216
         compression_args.append('-dPassThroughJPEGImages=false')
 
@@ -192,7 +215,6 @@ def generate_pdfa(
     args_gs = (
         [
             GS,
-            "-dQUIET",
             "-dBATCH",
             "-dNOPAUSE",
             "-dSAFER",
@@ -212,16 +234,28 @@ def generate_pdfa(
         ]
     )
     args_gs.extend(fspath(s) for s in pdf_pages)  # Stringify Path objs
+
     try:
         with Path(output_file).open('wb') as output:
-            p = run(args_gs, stdout=output, stderr=PIPE, check=True)
+            p = run_polling_stderr(
+                args_gs,
+                stdout=output,
+                stderr=PIPE,
+                check=True,
+                text=True,
+                encoding='utf-8',
+                errors='replace',
+                callback=GhostscriptFollower(progressbar_class),
+            )
     except CalledProcessError as e:
         # Ghostscript does not change return code when it fails to create
         # PDF/A - check PDF/A status elsewhere
-        log.error(e.stderr.decode(errors='replace'))
-        raise SubprocessOutputError('Ghostscript PDF/A rendering failed')
+        log.error(e.stderr)
+        raise SubprocessOutputError('Ghostscript PDF/A rendering failed') from e
     else:
-        stderr = p.stderr.decode('utf-8', errors='replace')
+        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
@@ -234,11 +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/jbig2enc.py

@@ -1,19 +1,9 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 """Interface to jbig2 executable"""
 
@@ -51,9 +41,17 @@ def convert_group(*, cwd, infiles, out_prefix):
     return proc
 
 
+def convert_group_mp(args):
+    return convert_group(cwd=args[0], infiles=args[1], out_prefix=args[2])
+
+
 def convert_single(*, cwd, infile, outfile):
     args = ['jbig2', '-p', infile]
     with open(outfile, 'wb') as fstdout:
         proc = run(args, cwd=cwd, stdout=fstdout, stderr=PIPE)
     proc.check_returncode()
     return proc
+
+
+def convert_single_mp(args):
+    return convert_single(cwd=args[0], infile=args[1], outfile=args[2])

src/ocrmypdf/_exec/pngquant.py

@@ -1,23 +1,16 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 """Interface to pngquant executable"""
 
-from tempfile import NamedTemporaryFile
+from contextlib import contextmanager
+from io import BytesIO
+from pathlib import Path
+from subprocess import PIPE
 
 from PIL import Image
 
@@ -37,32 +30,36 @@ def available():
     return True
 
 
-def quantize(input_file, output_file, quality_min, quality_max):
-    if input_file.endswith('.jpg'):
-        with Image.open(input_file) as im, NamedTemporaryFile(suffix='.png') as tmp:
-            im.save(tmp)
-            args = [
-                'pngquant',
-                '--force',
-                '--skip-if-larger',
-                '--output',
-                output_file,
-                '--quality',
-                f'{quality_min}-{quality_max}',
-                '--',
-                tmp.name,
-            ]
-            run(args)
+@contextmanager
+def input_as_png(input_file: Path):
+    if not input_file.name.endswith('.png'):
+        with Image.open(input_file) as im:
+            bio = BytesIO()
+            im.save(bio, format='png')
+            bio.seek(0)
+            yield bio
     else:
+        with open(input_file, 'rb') as f:
+            yield f
+
+
+def quantize(input_file: Path, output_file: Path, quality_min: int, quality_max: int):
+    with input_as_png(input_file) as input_stream:
         args = [
             'pngquant',
             '--force',
             '--skip-if-larger',
-            '--output',
-            output_file,
             '--quality',
             f'{quality_min}-{quality_max}',
-            '--',
-            input_file,
+            '--',  # pngquant: stop processing arguments
+            '-',  # pngquant: stream input and output
         ]
-        run(args)
+        result = run(args, stdin=input_stream, stdout=PIPE, stderr=PIPE, check=False)
+
+    if result.returncode == 0:
+        # input_file could be the same as output_file, so we defer the write
+        output_file.write_bytes(result.stdout)
+
+
+def quantize_mp(args):
+    return quantize(*args)

src/ocrmypdf/_exec/tesseract.py

@@ -1,30 +1,20 @@
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 """Interface to Tesseract executable"""
 
 import logging
-import os
-import shutil
+import re
 from collections import namedtuple
+from distutils.version import StrictVersion
 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
 
@@ -63,31 +53,31 @@ class TesseractLoggerAdapter(logging.LoggerAdapter):
         return '[tesseract] %s' % (msg), kwargs
 
 
+class TesseractVersion(StrictVersion):
+
+    version_re = re.compile(
+        r'''
+        ^(\d+) \. (\d+) (\. (\d+))?  # groups: 1/major, 2/minor, 3/[skip], 4/patch
+        [-]?  # optional hyphen separator
+        (?: ((?:alpha|beta|rc|dev)\d*)? [.\-\ ]? (\d+)? )?  # 5/prerelease, 6/prerelease_num
+        (?:(?:-\d+)?-g[0-9a-f]+)?  # untagged git version
+        $
+        ''',
+        re.VERBOSE | re.ASCII,
+    )
+
+    def parse(self, vstring):
+        try:
+            super().parse(vstring)
+        except TypeError as e:
+            if 'int() argument must be a string' in str(e):
+                super().parse(vstring + '-0')
+
+
 def version():
     return get_version('tesseract', regex=r'tesseract\s(.+)')
 
 
-def has_textonly_pdf(langs=None):
-    """Does Tesseract have textonly_pdf capability?
-
-    Available in v4.00.00alpha since January 2017. Best to
-    parse the parameter list.
-    """
-    args_tess = tess_base_args(langs, engine_mode=None) + ['--print-parameters', 'pdf']
-    params = ''
-    try:
-        proc = run(args_tess, check=True, stdout=PIPE, stderr=STDOUT)
-        params = proc.stdout
-    except CalledProcessError as e:
-        raise MissingDependencyError(
-            "Could not --print-parameters from tesseract. This can happen if the "
-            "TESSDATA_PREFIX environment is not set to a valid tessdata folder. "
-        ) from e
-    if b'textonly_pdf' in params:
-        return True
-    return False
-
-
 def has_user_words():
     """Does Tesseract have --user-words capability?
 
@@ -110,7 +100,12 @@ def get_languages():
     args_tess = ['tesseract', '--list-langs']
     try:
         proc = run(
-            args_tess, universal_newlines=True, stdout=PIPE, stderr=STDOUT, check=True
+            args_tess,
+            text=True,
+            stdout=PIPE,
+            stderr=STDOUT,
+            logs_errors_to_stdout=True,
+            check=True,
         )
         output = proc.stdout
     except CalledProcessError as e:
@@ -120,10 +115,10 @@ def get_languages():
         if line.startswith('Error'):
             raise MissingDependencyError(lang_error(output))
     _header, *rest = output.splitlines()
-    return set(lang.strip() for lang in rest)
+    return {lang.strip() for lang in rest}
 
 
-def tess_base_args(langs: List[str], engine_mode) -> List[str]:
+def tess_base_args(langs: List[str], engine_mode: Optional[int]) -> List[str]:
     args = ['tesseract']
     if langs:
         args.extend(['-l', '+'.join(langs)])
@@ -132,7 +127,7 @@ def tess_base_args(langs: List[str], engine_mode) -> List[str]:
     return args
 
 
-def get_orientation(input_file: Path, engine_mode, timeout: float):
+def get_orientation(input_file: Path, engine_mode: Optional[int], timeout: float):
     args_tesseract = tess_base_args(['osd'], engine_mode) + [
         '--psm',
         '0',
@@ -226,12 +221,13 @@ def _generate_null_hocr(output_hocr, output_text, image):
 
 
 def generate_hocr(
+    *,
     input_file: Path,
     output_hocr: Path,
     output_text: Path,
-    languages: list,
-    engine_mode,
-    tessconfig: list,
+    languages: List[str],
+    engine_mode: int,
+    tessconfig: List[str],
     timeout: float,
     pagesegmode: int,
     user_words,
@@ -252,7 +248,8 @@ def generate_hocr(
 
     # Reminder: test suite tesseract test plugins will break after any changes
     # to the number of order parameters here
-    args_tesseract.extend([input_file, prefix, 'hocr', 'txt'] + tessconfig)
+    args_tesseract.extend([fspath(input_file), fspath(prefix), 'hocr', 'txt'])
+    args_tesseract.extend(tessconfig)
     try:
         p = run(args_tesseract, stdout=PIPE, stderr=STDOUT, timeout=timeout, check=True)
         stdout = p.stdout
@@ -274,7 +271,7 @@ def generate_hocr(
         # The sidecar text file will get the suffix .txt; rename it to
         # whatever caller wants it named
         if prefix.with_suffix('.txt').exists():
-            shutil.move(prefix.with_suffix('.txt'), output_text)
+            prefix.with_suffix('.txt').replace(output_text)
 
 
 def use_skip_page(output_pdf, output_text):
@@ -290,7 +287,7 @@ def generate_pdf(
     output_pdf: Path,
     output_text: Path,
     languages: List[str],
-    engine_mode,
+    engine_mode: int,
     tessconfig: List[str],
     timeout: float,
     pagesegmode: int,
@@ -321,17 +318,18 @@ def generate_pdf(
     if user_patterns:
         args_tesseract.extend(['--user-patterns', user_patterns])
 
-    prefix = os.path.splitext(output_pdf)[0]  # Tesseract appends suffixes
+    prefix = output_pdf.parent / Path(output_pdf.stem)
 
     # Reminder: test suite tesseract test plugins might break after any changes
     # to the number of order parameters here
 
-    args_tesseract.extend([input_file, prefix, 'pdf', 'txt'] + tessconfig)
+    args_tesseract.extend([fspath(input_file), fspath(prefix), 'pdf', 'txt'])
+    args_tesseract.extend(tessconfig)
     try:
         p = run(args_tesseract, stdout=PIPE, stderr=STDOUT, timeout=timeout, check=True)
         stdout = p.stdout
-        if os.path.exists(prefix + '.txt'):
-            shutil.move(prefix + '.txt', output_text)
+        if prefix.with_suffix('.txt').exists():
+            prefix.with_suffix('.txt').replace(output_text)
     except TimeoutExpired:
         page_timedout(timeout)
         use_skip_page(output_pdf, output_text)

src/ocrmypdf/_exec/unpaper.py

@@ -1,19 +1,9 @@
 # © 2015 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 # unpaper documentation:
 # https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
@@ -23,10 +13,11 @@
 import logging
 import os
 import shlex
+from decimal import Decimal
 from pathlib import Path
-from subprocess import PIPE, STDOUT, CalledProcessError
+from subprocess import PIPE, STDOUT
 from tempfile import TemporaryDirectory
-from typing import Tuple
+from typing import List, Optional, Tuple, Union
 
 from PIL import Image
 
@@ -34,10 +25,12 @@ from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
 from ocrmypdf.subprocess import get_version
 from ocrmypdf.subprocess import run as external_run
 
+DecFloat = Union[Decimal, float]
+
 log = logging.getLogger(__name__)
 
 
-def version():
+def version() -> str:
     return get_version('unpaper')
 
 
@@ -52,7 +45,7 @@ def _setup_unpaper_io(tmpdir: Path, input_file: Path) -> Tuple[Path, Path]:
                     im = im.convert(mode='1')
                 else:
                     im = im.convert(mode='RGB')
-            except IOError as e:
+            except OSError as e:
                 raise MissingDependencyError(
                     "Could not convert image with type " + im.mode
                 ) from e
@@ -63,23 +56,25 @@ def _setup_unpaper_io(tmpdir: Path, input_file: Path) -> Tuple[Path, Path]:
         except KeyError:
             raise MissingDependencyError(
                 "Failed to convert image to a supported format."
-            ) from e
+            ) from None
 
-        if im_modified or input_file.suffix != '.png':
-            input_png = tmpdir / 'input.png'
-            im.save(input_png, format='PNG', compress_level=1)
+        if im_modified or input_file.suffix != '.pnm':
+            input_pnm = tmpdir / 'input.pnm'
+            im.save(input_pnm, format='PPM')
         else:
             # No changes, PNG input, just use the file we already have
-            input_png = input_file
+            input_pnm = input_file
         output_pnm = tmpdir / f'output{suffix}'
-    return input_png, output_pnm
+    return input_pnm, output_pnm
 
 
-def run(input_file, output_file, dpi, mode_args):
-    args_unpaper = ['unpaper', '-v', '--dpi', str(dpi)] + mode_args
+def run(
+    input_file: Path, output_file: Path, *, dpi: DecFloat, mode_args: List[str]
+) -> None:
+    args_unpaper = ['unpaper', '-v', '--dpi', str(round(dpi, 6))] + mode_args
 
     with TemporaryDirectory() as tmpdir:
-        input_png, output_pnm = _setup_unpaper_io(Path(tmpdir), input_file)
+        input_pnm, output_pnm = _setup_unpaper_io(Path(tmpdir), input_file)
 
         # To prevent any shenanigans from accepting arbitrary parameters in
         # --unpaper-args, we:
@@ -88,41 +83,41 @@ def run(input_file, output_file, dpi, mode_args):
         # 3) append absolute paths for the input and output file
         # This should ensure that a user cannot clobber some other file with
         # their unpaper arguments (whether intentionally or otherwise)
-        args_unpaper.extend([os.fspath(input_png), os.fspath(output_pnm)])
+        args_unpaper.extend([os.fspath(input_pnm), os.fspath(output_pnm)])
+        external_run(
+            args_unpaper,
+            close_fds=True,
+            check=True,
+            stderr=STDOUT,  # unpaper writes logging output to stdout and stderr
+            stdout=PIPE,  # and cannot send file output to stdout
+            cwd=tmpdir,
+            logs_errors_to_stdout=True,
+        )
         try:
-            proc = external_run(
-                args_unpaper,
-                check=True,
-                close_fds=True,
-                universal_newlines=True,
-                stderr=STDOUT,  # unpaper writes logging output to stdout and stderr
-                cwd=tmpdir,  # and cannot send file output to stdout
-                stdout=PIPE,
-            )
-        except CalledProcessError as e:
-            log.debug(e.stderr)
-            raise e from e
-        else:
-            log.debug(proc.stderr)
-            try:
-                with Image.open(output_pnm) as imout:
-                    imout.save(output_file, dpi=(dpi, dpi))
-            except (FileNotFoundError, OSError):
-                raise SubprocessOutputError(
-                    "unpaper: failed to produce the expected output file. "
-                    + " Called with: "
-                    + str(args_unpaper)
-                ) from None
+            with Image.open(output_pnm) as imout:
+                imout.save(output_file, dpi=(dpi, dpi))
+        except OSError as e:
+            raise SubprocessOutputError(
+                "unpaper: failed to produce the expected output file. "
+                + " Called with: "
+                + str(args_unpaper)
+            ) from e
 
 
-def validate_custom_args(args: str):
+def validate_custom_args(args: str) -> List[str]:
     unpaper_args = shlex.split(args)
-    if any('/' in arg for arg in unpaper_args):
+    if any(('/' in arg or arg == '.' or arg == '..') for arg in unpaper_args):
         raise ValueError('No filenames allowed in --unpaper-args')
     return unpaper_args
 
 
-def clean(input_file, output_file, dpi, unpaper_args=None):
+def clean(
+    input_file: Path,
+    output_file: Path,
+    *,
+    dpi: DecFloat,
+    unpaper_args: Optional[List[str]] = None,
+):
     default_args = [
         '--layout',
         'none',
@@ -136,4 +131,4 @@ def clean(input_file, output_file, dpi, unpaper_args=None):
     ]
     if not unpaper_args:
         unpaper_args = default_args
-    run(input_file, output_file, dpi, unpaper_args)
+    run(input_file, output_file, dpi=dpi, mode_args=unpaper_args)

src/ocrmypdf/_graft.py

@@ -1,48 +1,55 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 import logging
+import uuid
 from contextlib import suppress
 from pathlib import Path
 from typing import Optional
 
-import pikepdf
+from pikepdf import (
+    Dictionary,
+    Name,
+    Object,
+    Operator,
+    Page,
+    Pdf,
+    PdfError,
+    PdfMatrix,
+    Stream,
+    parse_content_stream,
+    unparse_content_stream,
+)
 
 log = logging.getLogger(__name__)
 MAX_REPLACE_PAGES = 100
 
 
-def _update_page_resources(*, page, font, font_key, procset):
-    """Update this page's fonts with a reference to the Glyphless font"""
+def _ensure_dictionary(obj, name):
+    if name not in obj:
+        obj[name] = Dictionary({})
+    return obj[name]
 
-    if '/Resources' not in page:
-        page['/Resources'] = pikepdf.Dictionary({})
-    resources = page['/Resources']
-    try:
-        fonts = resources['/Font']
-    except KeyError:
-        fonts = pikepdf.Dictionary({})
+
+def _update_resources(*, obj, font, font_key, procset):
+    """Update this obj's fonts with a reference to the Glyphless font.
+
+    obj can be a page or Form XObject.
+    """
+
+    resources = _ensure_dictionary(obj, Name.Resources)
+    fonts = _ensure_dictionary(resources, Name.Font)
     if font_key is not None and font_key not in fonts:
         fonts[font_key] = font
-    resources['/Font'] = fonts
 
     # Reassign /ProcSet to one that just lists everything - ProcSet is
     # obsolete and doesn't matter but recommended for old viewer support
-    resources['/ProcSet'] = procset
+    if procset:
+        resources['/ProcSet'] = procset
 
 
 def strip_invisible_text(pdf, page):
@@ -51,43 +58,28 @@ def strip_invisible_text(pdf, page):
     render_mode = 0
     text_objects = []
 
-    page.page_contents_coalesce()
-    for operands, operator in pikepdf.parse_content_stream(page, ''):
+    rich_page = Page(page)
+    rich_page.contents_coalesce()
+    for operands, operator in parse_content_stream(page, ''):
         if not in_text_obj:
-            if operator == pikepdf.Operator('BT'):
+            if operator == Operator('BT'):
                 in_text_obj = True
                 render_mode = 0
                 text_objects.append((operands, operator))
             else:
                 stream.append((operands, operator))
         else:
-            if operator == pikepdf.Operator('Tr'):
+            if operator == Operator('Tr'):
                 render_mode = operands[0]
             text_objects.append((operands, operator))
-            if operator == pikepdf.Operator('ET'):
+            if operator == Operator('ET'):
                 in_text_obj = False
                 if render_mode != 3:
                     stream.extend(text_objects)
                 text_objects.clear()
 
-    def convert(op):
-        try:
-            return op.unparse()
-        except AttributeError:
-            return str(op).encode('ascii')
-
-    lines = []
-
-    for operands, operator in stream:
-        if operator == pikepdf.Operator('INLINE IMAGE'):
-            iim = operands[0]
-            line = iim.unparse()
-        else:
-            line = b' '.join(convert(op) for op in operands) + b' ' + operator.unparse()
-        lines.append(line)
-
-    content_stream = b'\n'.join(lines)
-    page.Contents = pikepdf.Stream(pdf, content_stream)
+    content_stream = unparse_content_stream(stream)
+    page.Contents = Stream(pdf, content_stream)
 
 
 class OcrGrafter:
@@ -95,14 +87,14 @@ class OcrGrafter:
         self.context = context
         self.path_base = context.origin
 
-        self.pdf_base = pikepdf.open(self.path_base)
+        self.pdf_base = Pdf.open(self.path_base)
         self.font, self.font_key = None, None
 
         self.pdfinfo = context.pdfinfo
         self.output_file = context.get_path('graft_layers.pdf')
 
         self.procset = self.pdf_base.make_indirect(
-            pikepdf.Object.parse(b'[ /PDF /Text /ImageB /ImageC /ImageI ]')
+            Object.parse(b'[ /PDF /Text /ImageB /ImageC /ImageI ]')
         )
 
         self.emplacements = 1
@@ -126,7 +118,7 @@ class OcrGrafter:
             # We are updating the old page with a rasterized PDF of the new
             # page (without changing objgen, to preserve references)
             log.debug("Emplacement update")
-            with pikepdf.open(image) as pdf_image:
+            with Pdf.open(path_image) as pdf_image:
                 self.emplacements += 1
                 foreign_image_page = pdf_image.pages[0]
                 self.pdf_base.pages.append(foreign_image_page)
@@ -135,34 +127,38 @@ class OcrGrafter:
                 del self.pdf_base.pages[-1]
             emplaced_page = True
 
+        # Calculate if the text is misaligned compared to the content
         if emplaced_page:
             content_rotation = autorotate_correction
         text_rotation = autorotate_correction
         text_misaligned = (text_rotation - content_rotation) % 360
         log.debug(
-            f"Rotations for page {pageno}: [text, auto, misalign, content] = "
-            f"{text_rotation}, {autorotate_correction}, "
-            f"{text_misaligned}, {content_rotation}"
+            f"Text rotation: (text, autorotate, content) -> text misalignment = "
+            f"({text_rotation}, {autorotate_correction}, {content_rotation}) -> {text_misaligned}"
         )
 
         if textpdf and self.font:
-            # Graft the text layer onto this page, whether new or old
+            # Graft the text layer onto this page, whether new or old, possibly
+            # rotating the text layer by the amount is misaligned.
             strip_old = self.context.options.redo_ocr
             self._graft_text_layer(
                 page_num=pageno + 1,
                 textpdf=textpdf,
                 font=self.font,
                 font_key=self.font_key,
-                rotation=text_misaligned,
+                text_rotation=text_misaligned,
                 procset=self.procset,
                 strip_old_text=strip_old,
             )
 
-        # Correct the rotation if applicable
-        self.pdf_base.pages[pageno].Rotate = (
-            content_rotation - autorotate_correction
-        ) % 360
-
+        # Correct the overall page rotation if needed, now that the text and content
+        # are aligned
+        page_rotation = (content_rotation - autorotate_correction) % 360
+        self.pdf_base.pages[pageno].Rotate = page_rotation
+        log.debug(
+            f"Page rotation: (content, auto) -> page = "
+            f"({content_rotation}, {autorotate_correction}) -> {page_rotation}"
+        )
         if self.emplacements % MAX_REPLACE_PAGES == 0:
             self.save_and_reload()
 
@@ -175,13 +171,13 @@ class OcrGrafter:
         """
 
         page0 = self.pdf_base.pages[0]
-        _update_page_resources(
-            page=page0, font=self.font, font_key=self.font_key, procset=self.procset
+        _update_resources(
+            obj=page0, font=self.font, font_key=self.font_key, procset=self.procset
         )
 
         # We cannot read and write the same file, that will corrupt it
         # but we don't to keep more copies than we need to. Delete intermediates.
-        # {interim_count} is the opened file we were updateing
+        # {interim_count} is the opened file we were updating
         # {interim_count - 1} can be deleted
         # {interim_count + 1} is the new file will produce and open
         old_file = self.output_file.with_suffix(f'.working{self.interim_count - 1}.pdf')
@@ -195,7 +191,7 @@ class OcrGrafter:
         self.pdf_base.save(next_file)
         self.pdf_base.close()
 
-        self.pdf_base = pikepdf.open(next_file)
+        self.pdf_base = Pdf.open(next_file)
         self.procset = self.pdf_base.pages[0].Resources.ProcSet
         self.font, self.font_key = None, None  # Ensure we reacquire this information
         self.interim_count += 1
@@ -211,11 +207,12 @@ class OcrGrafter:
         font, font_key = None, None
         possible_font_names = ('/f-0-0', '/F1')
         try:
-            with pikepdf.open(text) as pdf_text:
+            with Pdf.open(text) as pdf_text:
                 try:
                     pdf_text_fonts = pdf_text.pages[0].Resources.get('/Font', {})
                 except (AttributeError, IndexError, KeyError):
                     return None, None
+                pdf_text_font = None
                 for f in possible_font_names:
                     pdf_text_font = pdf_text_fonts.get(f, None)
                     if pdf_text_font is not None:
@@ -224,7 +221,7 @@ class OcrGrafter:
                 if pdf_text_font:
                     font = self.pdf_base.copy_foreign(pdf_text_font)
                 return font, font_key
-        except (FileNotFoundError, pikepdf.PdfError):
+        except (FileNotFoundError, PdfError):
             # PdfError occurs if a 0-length file is written e.g. due to OCR timeout
             return None, None
 
@@ -233,10 +230,10 @@ class OcrGrafter:
         *,
         page_num: int,
         textpdf: Path,
-        font: pikepdf.Object,
-        font_key: pikepdf.Object,
-        procset: pikepdf.Object,
-        rotation: int,
+        font: Object,
+        font_key: Object,
+        procset: Object,
+        text_rotation: int,
         strip_old_text: bool,
     ):
         """Insert the text layer from text page 0 on to pdf_base at page_num"""
@@ -246,7 +243,7 @@ class OcrGrafter:
             return
 
         # This is a pointer indicating a specific page in the base file
-        with pikepdf.open(textpdf) as pdf_text:
+        with Pdf.open(textpdf) as pdf_text:
             pdf_text_contents = pdf_text.pages[0].Contents.read_bytes()
 
             base_page = self.pdf_base.pages.p(page_num)
@@ -261,41 +258,60 @@ class OcrGrafter:
             mediabox = [float(base_page.MediaBox[v]) for v in range(4)]
             wp, hp = mediabox[2] - mediabox[0], mediabox[3] - mediabox[1]
 
-            translate = pikepdf.PdfMatrix().translated(-wt / 2, -ht / 2)
-            untranslate = pikepdf.PdfMatrix().translated(wp / 2, hp / 2)
-            corner = pikepdf.PdfMatrix().translated(mediabox[0], mediabox[1])
+            translate = PdfMatrix().translated(-wt / 2, -ht / 2)
+            untranslate = PdfMatrix().translated(wp / 2, hp / 2)
+            corner = PdfMatrix().translated(mediabox[0], mediabox[1])
             # -rotation because the input is a clockwise angle and this formula
             # uses CCW
-            rotation = -rotation % 360
-            rotate = pikepdf.PdfMatrix().rotated(rotation)
+            text_rotation = -text_rotation % 360
+            rotate = PdfMatrix().rotated(text_rotation)
 
             # Because of rounding of DPI, we might get a text layer that is not
             # identically sized to the target page. Scale to adjust. Normally this
             # is within 0.998.
-            if rotation in (90, 270):
+            if text_rotation in (90, 270):
                 wt, ht = ht, wt
             scale_x = wp / wt
             scale_y = hp / ht
 
             # log.debug('%r', scale_x, scale_y)
-            scale = pikepdf.PdfMatrix().scaled(scale_x, scale_y)
+            scale = PdfMatrix().scaled(scale_x, scale_y)
 
             # Translate the text so it is centered at (0, 0), rotate it there, adjust
             # for a size different between initial and text PDF, then untranslate, and
             # finally move the lower left corner to match the mediabox
             ctm = translate @ rotate @ scale @ untranslate @ corner
 
-            pdf_text_contents = (
-                b'q %s cm\n' % ctm.encode() + pdf_text_contents + b'\nQ\n'
+            base_resources = _ensure_dictionary(base_page, Name.Resources)
+            base_xobjs = _ensure_dictionary(base_resources, Name.XObject)
+            text_xobj_name = Name('/' + str(uuid.uuid4()))
+            xobj = self.pdf_base.make_stream(pdf_text_contents)
+            base_xobjs[text_xobj_name] = xobj
+            xobj.Type = Name.XObject
+            xobj.Subtype = Name.Form
+            xobj.FormType = 1
+            xobj.BBox = mediabox
+            _update_resources(
+                obj=xobj, font=font, font_key=font_key, procset=[Name.PDF]
             )
 
-            new_text_layer = pikepdf.Stream(self.pdf_base, pdf_text_contents)
+            pdf_draw_xobj = (
+                (b'q %s cm\n' % ctm.encode()) + (b'%s Do\n' % text_xobj_name) + b'\nQ\n'
+            )
+            new_text_layer = Stream(self.pdf_base, pdf_draw_xobj)
 
             if strip_old_text:
                 strip_invisible_text(self.pdf_base, base_page)
 
-            base_page.page_contents_add(new_text_layer, prepend=True)
+            if hasattr(Page, 'contents_add'):
+                # pikepdf >= 2.14 adds this method and deprecates the one below
+                Page(base_page).contents_add(new_text_layer, prepend=True)
+            else:
+                # pikepdf < 2.14
+                base_page.page_contents_add(
+                    new_text_layer, prepend=True
+                )  # pragma: no cover
 
-            _update_page_resources(
-                page=base_page, font=font, font_key=font_key, procset=procset
+            _update_resources(
+                obj=base_page, font=font, font_key=font_key, procset=procset
             )

src/ocrmypdf/_jobcontext.py

@@ -1,34 +1,31 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 import os
 import shutil
 import sys
 from argparse import Namespace
 from copy import copy
-from io import IOBase
 from pathlib import Path
 from typing import Iterator
 
+from pluggy import PluginManager
+
 from ocrmypdf.pdfinfo import PdfInfo
+from ocrmypdf.pdfinfo.info import PageInfo
 
 
 class PdfContext:
-    """Holds our context for a particular run of the pipeline"""
+    """Holds the context for a particular run of the pipeline."""
+
+    options: Namespace  #: The specified options for processing this PDF.
+    origin: Path  #: The filename of the original input file.
+    pdfinfo: PdfInfo  #: Detailed data for this PDF.
+    plugin_manager: PluginManager  #: PluginManager for processing the current PDF.
 
     def __init__(
         self,
@@ -45,21 +42,33 @@ class PdfContext:
         self.plugin_manager = plugin_manager
 
     def get_path(self, name: str) -> Path:
+        """Generate a ``Path`` for an intermediate file involved in processing.
+
+        The path will be in a temporary folder that is common for all processing
+        of this particular PDF.
+        """
         return self.work_folder / name
 
     def get_page_contexts(self) -> Iterator['PageContext']:
+        """Get all ``PageContext`` for this PDF."""
         npages = len(self.pdfinfo)
         for n in range(npages):
             yield PageContext(self, n)
 
 
 class PageContext:
-    """Holds our context for a page
+    """Holds our context for a page.
 
     Must be pickable, so stores only intrinsic/simple data elements or those
-    capable of their serializing themselves via __getstate__.
+    capable of their serializing themselves via ``__getstate__``.
     """
 
+    options: Namespace  #: The specified options for processing this PDF.
+    origin: Path  #: The filename of the original input file.
+    pageno: int  #: This page number (zero-based).
+    pageinfo: PageInfo  #: Information on this page.
+    plugin_manager: PluginManager  #: PluginManager for processing the current PDF.
+
     def __init__(self, pdf_context: PdfContext, pageno):
         self.work_folder = pdf_context.work_folder
         self.origin = pdf_context.origin
@@ -69,6 +78,11 @@ class PageContext:
         self.plugin_manager = pdf_context.plugin_manager
 
     def get_path(self, name: str) -> Path:
+        """Generate a ``Path`` for a file that is part of processing this page.
+
+        The path will be based in a common temporary folder and have a prefix based
+        on the page number.
+        """
         return self.work_folder / ("%06d_%s" % (self.pageno + 1, name))
 
     def __getstate__(self):

src/ocrmypdf/_logging.py

@@ -1,19 +1,9 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 import logging
 import sys

src/ocrmypdf/_pipeline.py

@@ -1,19 +1,9 @@
 # © 2016 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 import logging
 import os
@@ -23,7 +13,7 @@ from contextlib import suppress
 from datetime import datetime, timezone
 from pathlib import Path
 from shutil import copyfileobj
-from typing import BinaryIO, Dict, Iterable, Optional, Union, cast
+from typing import Dict, Iterable, Optional
 
 import img2pdf
 import pikepdf
@@ -31,6 +21,7 @@ from pikepdf.models.metadata import encode_pdf_date
 from PIL import Image, ImageColor, ImageDraw
 
 from ocrmypdf import leptonica
+from ocrmypdf._concurrent import Executor
 from ocrmypdf._exec import unpaper
 from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._version import PROGRAM_NAME
@@ -57,7 +48,7 @@ def triage_image_file(input_file, output_file, options):
     log.info("Input file is not a PDF, checking if it is an image...")
     try:
         im = Image.open(input_file)
-    except EnvironmentError as e:
+    except OSError as e:
         # Recover the original filename
         log.error(str(e).replace(str(input_file), str(options.input_file)))
         raise UnsupportedImageFormatError() from e
@@ -144,7 +135,7 @@ def triage(original_filename, input_file, output_file, options):
             # Origin file is a pdf create a symlink with pdf extension
             safe_symlink(input_file, output_file)
             return output_file
-    except EnvironmentError as e:
+    except OSError as e:
         log.debug(f"Temporary file was at: {input_file}")
         msg = str(e).replace(str(input_file), original_filename)
         raise InputFileError(msg) from e
@@ -155,11 +146,13 @@ def triage(original_filename, input_file, output_file, options):
 
 def get_pdfinfo(
     input_file,
+    *,
+    executor: Executor,
     detailed_analysis=False,
     progbar=False,
     max_workers=None,
     check_pages=None,
-):
+) -> PdfInfo:
     try:
         return PdfInfo(
             input_file,
@@ -167,11 +160,12 @@ def get_pdfinfo(
             progbar=progbar,
             max_workers=max_workers,
             check_pages=check_pages,
+            executor=executor,
         )
-    except pikepdf.PasswordError:
-        raise EncryptedPdfError()
-    except pikepdf.PdfError:
-        raise InputFileError()
+    except pikepdf.PasswordError as e:
+        raise EncryptedPdfError() from e
+    except pikepdf.PdfError as e:
+        raise InputFileError() from e
 
 
 def validate_pdfinfo_options(context: PdfContext):
@@ -215,17 +209,21 @@ def validate_pdfinfo_options(context: PdfContext):
     context.plugin_manager.hook.validate(pdfinfo=pdfinfo, options=options)
 
 
+def _vector_page_dpi(pageinfo):
+    return VECTOR_PAGE_DPI if pageinfo.has_vector or pageinfo.has_text else 0.0
+
+
 def get_page_dpi(pageinfo, options):
     "Get the DPI when nonsquare DPI is tolerable"
     xres = max(
         pageinfo.dpi.x or VECTOR_PAGE_DPI,
         options.oversample or 0.0,
-        VECTOR_PAGE_DPI if pageinfo.has_vector else 0.0,
+        _vector_page_dpi(pageinfo),
     )
     yres = max(
         pageinfo.dpi.y or VECTOR_PAGE_DPI,
         options.oversample or 0,
-        VECTOR_PAGE_DPI if pageinfo.has_vector else 0.0,
+        _vector_page_dpi(pageinfo),
     )
     return Resolution(float(xres), float(yres))
 
@@ -239,7 +237,7 @@ def get_page_square_dpi(pageinfo, options) -> Resolution:
         max(
             (xres * userunit) or VECTOR_PAGE_DPI,
             (yres * userunit) or VECTOR_PAGE_DPI,
-            VECTOR_PAGE_DPI if pageinfo.has_vector else 0.0,
+            _vector_page_dpi(pageinfo),
             options.oversample or 0.0,
         )
     )
@@ -252,7 +250,7 @@ def get_canvas_square_dpi(pageinfo, options) -> Resolution:
         max(
             (pageinfo.dpi.x) or VECTOR_PAGE_DPI,
             (pageinfo.dpi.y) or VECTOR_PAGE_DPI,
-            VECTOR_PAGE_DPI if pageinfo.has_vector else 0.0,
+            _vector_page_dpi(pageinfo),
             options.oversample or 0.0,
         )
     )
@@ -342,8 +340,10 @@ def rasterize_preview(input_file: Path, page_context: PageContext):
         output_file=output_file,
         raster_device='jpeggray',
         raster_dpi=canvas_dpi,
-        page_dpi=page_dpi,
         pageno=page_context.pageinfo.pageno + 1,
+        page_dpi=page_dpi,
+        rotation=0,
+        filter_vector=False,
     )
     return output_file
 
@@ -443,7 +443,7 @@ def rasterize(
 
     device = colorspaces[device_idx]
 
-    log.debug(f"Rasterize with {device}")
+    log.debug(f"Rasterize with {device}, rotation {correction}")
 
     # Produce the page image with square resolution or else deskew and OCR
     # will not work properly.
@@ -483,7 +483,12 @@ def preprocess_deskew(input_file: Path, page_context: PageContext):
 def preprocess_clean(input_file: Path, page_context: PageContext):
     output_file = page_context.get_path('pp_clean.png')
     dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
-    unpaper.clean(input_file, output_file, dpi.x, page_context.options.unpaper_args)
+    unpaper.clean(
+        input_file,
+        output_file,
+        dpi=dpi.x,
+        unpaper_args=page_context.options.unpaper_args,
+    )
     return output_file
 
 
@@ -516,13 +521,12 @@ def create_ocr_image(image: Path, page_context: PageContext):
                 # be None)
                 bbox = [float(v) for v in textarea]
                 xyscale = tuple(float(coord) / 72.0 for coord in im.info['dpi'])
-                pixcoords = [
+                pixcoords = (
                     bbox[0] * xyscale[0],
                     im.height - bbox[3] * xyscale[1],
                     bbox[2] * xyscale[0],
                     im.height - bbox[1] * xyscale[1],
-                ]
-                pixcoords = [int(round(c)) for c in pixcoords]
+                )
                 log.debug('blanking %r', pixcoords)
                 draw.rectangle(pixcoords, fill=white)
                 # draw.rectangle(pixcoords, outline=pink)
@@ -530,7 +534,9 @@ def create_ocr_image(image: Path, page_context: PageContext):
         if options.threshold:
             pix = leptonica.Pix.frompil(im)
             pix = pix.masked_threshold_on_background_norm()
-            im = pix.topil()
+            im_pix = pix.topil()
+            im_pix.info['dpi'] = im.info['dpi']
+            im = im_pix
 
         del draw
 
@@ -585,7 +591,9 @@ def create_visible_page_jpg(image: Path, page_context: PageContext) -> Path:
     return output_file
 
 
-def create_pdf_page_from_image(image: Path, page_context: PageContext):
+def create_pdf_page_from_image(
+    image: Path, page_context: PageContext, orientation_correction
+):
     # We rasterize a square DPI version of each page because most image
     # processing tools don't support rectangular DPI. Use the square DPI as it
     # accurately describes the image. It would be possible to resample the image
@@ -593,28 +601,42 @@ def create_pdf_page_from_image(image: Path, page_context: PageContext):
     # except that the hocr renderer does not understand non-square DPI. The
     # sandwich renderer would be fine.
     output_file = page_context.get_path('visible.pdf')
-    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
-    layout_fun = img2pdf.get_fixed_dpi_layout_fun(dpi)
+
+    pageinfo = page_context.pageinfo
+    pagesize = 72.0 * float(pageinfo.width_inches), 72.0 * float(pageinfo.height_inches)
+    effective_rotation = (pageinfo.rotation - orientation_correction) % 360
+    if effective_rotation % 180 == 90:
+        pagesize = pagesize[1], pagesize[0]
 
     # This create a single page PDF
     with open(image, 'rb') as imfile, open(output_file, 'wb') as pdf:
         log.debug('convert')
+
+        layout_fun = img2pdf.get_layout_fun(pagesize)
         img2pdf.convert(
             imfile, with_pdfrw=False, layout_fun=layout_fun, outputstream=pdf
         )
         log.debug('convert done')
+
+    output_file = page_context.plugin_manager.hook.filter_pdf_page(
+        page=page_context, image_filename=image, output_pdf=output_file
+    )
+
     return output_file
 
 
 def render_hocr_page(hocr: Path, page_context: PageContext):
+    options = page_context.options
     output_file = page_context.get_path('ocr_hocr.pdf')
-    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
-    hocrtransform = HocrTransform(hocr, dpi.x)  # square
+    dpi = get_page_square_dpi(page_context.pageinfo, options)
+    debug_mode = options.pdf_renderer == 'hocrdebug'
+
+    hocrtransform = HocrTransform(hocr_filename=hocr, dpi=dpi.x)  # square
     hocrtransform.to_pdf(
-        output_file,
+        out_filename=output_file,
         image_filename=None,
-        show_bounding_boxes=False,
-        invisible_text=True,
+        show_bounding_boxes=False if not debug_mode else True,
+        invisible_text=True if not debug_mode else False,
         interword_spaces=True,
     )
     return output_file
@@ -663,11 +685,6 @@ def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> Dict[str, str]:
 
     pdfmark['/Creator'] = f'{PROGRAM_NAME} {VERSION} / {creator_tag}'
     pdfmark['/Producer'] = f'pikepdf {pikepdf.__version__}'
-    if 'OCRMYPDF_CREATOR' in os.environ:
-        pdfmark['/Creator'] = os.environ['OCRMYPDF_CREATOR']
-    if 'OCRMYPDF_PRODUCER' in os.environ:
-        pdfmark['/Producer'] = os.environ['OCRMYPDF_PRODUCER']
-
     pdfmark['/ModDate'] = encode_pdf_date(datetime.now(timezone.utc))
     return pdfmark
 
@@ -715,6 +732,11 @@ def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext):
         output_file=output_file,
         compression=options.pdfa_image_compression,
         pdfa_part=options.output_type[-1],  # is pdfa-1, pdfa-2, or pdfa-3
+        progressbar_class=(
+            context.plugin_manager.hook.get_progressbar_class()
+            if options.progress_bar
+            else None
+        ),
     )
 
     return output_file
@@ -727,6 +749,24 @@ def should_linearize(working_file: Path, context: PdfContext):
     return False
 
 
+def get_pdf_save_settings(output_type: str):
+    if output_type == 'pdfa-1':
+        # Trigger recompression to ensure object streams are removed, because
+        # Acrobat complains about them in PDF/A-1b validation.
+        return dict(
+            preserve_pdfa=True,
+            compress_streams=True,
+            stream_decode_level=pikepdf.StreamDecodeLevel.generalized,
+            object_stream_mode=pikepdf.ObjectStreamMode.disable,
+        )
+    else:
+        return dict(
+            preserve_pdfa=True,
+            compress_streams=True,
+            object_stream_mode=(pikepdf.ObjectStreamMode.generate),
+        )
+
+
 def metadata_fixup(working_file: Path, context: PdfContext):
     output_file = context.get_path('metafix.pdf')
     options = context.options
@@ -757,23 +797,21 @@ 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() 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,
-            compress_streams=True,
-            preserve_pdfa=True,
-            object_stream_mode=pikepdf.ObjectStreamMode.generate,
+            **get_pdf_save_settings(options.output_type),
             linearize=(  # Don't linearize if optimize() will be linearizing too
                 should_linearize(working_file, context)
                 if options.optimize == 0
@@ -784,26 +822,40 @@ def metadata_fixup(working_file: Path, context: PdfContext):
     return output_file
 
 
-def optimize_pdf(input_file: Path, context: PdfContext):
+def optimize_pdf(input_file: Path, context: PdfContext, executor: Executor):
     output_file = context.get_path('optimize.pdf')
     save_settings = dict(
-        compress_streams=True,
-        preserve_pdfa=True,
-        object_stream_mode=pikepdf.ObjectStreamMode.generate,
         linearize=should_linearize(input_file, context),
+        **get_pdf_save_settings(context.options.output_type),
     )
-    optimize(input_file, output_file, context, save_settings)
+    optimize(input_file, output_file, context, save_settings, executor)
     return output_file
 
 
+def enumerate_compress_ranges(iterable):
+    skipped_from, index = None, None
+    for index, txt_file in enumerate(iterable):
+        index += 1
+        if txt_file:
+            if skipped_from is not None:
+                yield (skipped_from, index - 1), None
+                skipped_from = None
+            yield (index, index), txt_file
+        else:
+            if skipped_from is None:
+                skipped_from = index
+    if skipped_from is not None:
+        yield (skipped_from, index), None
+
+
 def merge_sidecars(txt_files: Iterable[Optional[Path]], context: PdfContext):
     output_file = context.get_path('sidecar.txt')
     with open(output_file, 'w', encoding="utf-8") as stream:
-        for page_num, txt_file in enumerate(txt_files):
-            if page_num != 0:
+        for (frm, to), txt_file in enumerate_compress_ranges(txt_files):
+            if frm != 1:
                 stream.write('\f')  # Form feed between pages
             if txt_file:
-                with open(txt_file, 'r', encoding="utf-8") as in_:
+                with open(txt_file, encoding="utf-8") as in_:
                     txt = in_.read()
                     # Some OCR engines (e.g. Tesseract v4 alpha) add form feeds
                     # between pages, and some do not. For consistency, we ignore
@@ -813,7 +865,11 @@ def merge_sidecars(txt_files: Iterable[Optional[Path]], context: PdfContext):
                     else:
                         stream.write(txt)
             else:
-                stream.write(f'[OCR skipped on page {(page_num + 1)}]')
+                if frm != to:
+                    pages = f'{frm}-{to}'
+                else:
+                    pages = f'{frm}'
+                stream.write(f'[OCR skipped on page(s) {pages}]')
     return output_file
 
 

src/ocrmypdf/_plugin_manager.py

@@ -1,30 +1,21 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 import argparse
 import importlib
 import importlib.util
+import pkgutil
 import sys
-from functools import partial
 from pathlib import Path
-from typing import Callable, List, Tuple
+from typing import List, Tuple, Union
 
 import pluggy
 
+import ocrmypdf.builtin_plugins
 from ocrmypdf import pluginspec
 from ocrmypdf.cli import get_parser, plugins_only_parser
 
@@ -40,58 +31,80 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
     """
 
     def __init__(
-        self, *args, setup_func: Callable[[pluggy.PluginManager], None], **kwargs
+        self,
+        *args,
+        plugins: List[Union[str, Path]],
+        builtins: bool = True,
+        **kwargs,
     ):
-        self._init_args = args
-        self._setup_func = setup_func
-        self._init_kwargs = kwargs
+        self.__init_args = args
+        self.__init_kwargs = kwargs
+        self.__plugins = plugins
+        self.__builtins = builtins
         super().__init__(*args, **kwargs)
-        setup_func(self)
+        self.setup_plugins()
 
     def __getstate__(self):
         state = dict(
-            _init_args=self._init_args,
-            _setup_func=self._setup_func,
-            _init_kwargs=self._init_kwargs,
+            init_args=self.__init_args,
+            plugins=self.__plugins,
+            builtins=self.__builtins,
+            init_kwargs=self.__init_kwargs,
         )
         return state
 
     def __setstate__(self, state):
         self.__init__(
-            *state['_init_args'],
-            setup_func=state['_setup_func'],
-            **state['_init_kwargs'],
+            *state['init_args'],
+            plugins=state['plugins'],
+            builtins=state['builtins'],
+            **state['init_kwargs'],
         )
 
+    def setup_plugins(self):
+        self.add_hookspecs(pluginspec)
 
-def _setup_plugins(pm: pluggy.PluginManager, plugins: List[str], builtins: bool = True):
-    pm.add_hookspecs(pluginspec)
+        # 1. Register builtins
+        if self.__builtins:
+            for module in sorted(
+                pkgutil.iter_modules(ocrmypdf.builtin_plugins.__path__)
+            ):
+                name = f'ocrmypdf.builtin_plugins.{module.name}'
+                module = importlib.import_module(name)
+                self.register(module)
 
-    if builtins:
-        all_plugins = [
-            'ocrmypdf.builtin_plugins.ghostscript',
-            'ocrmypdf.builtin_plugins.tesseract_ocr',
-        ] + plugins
-    else:
-        all_plugins = plugins
-    for name in all_plugins:
-        if name.endswith('.py'):
-            # Import by filename
-            module_name = Path(name).stem
-            spec = importlib.util.spec_from_file_location(module_name, name)
-            module = importlib.util.module_from_spec(spec)
-            sys.modules[module_name] = module
-            spec.loader.exec_module(module)
-        else:
-            # Import by dotted module name
-            module = importlib.import_module(name)
-        pm.register(module)
+        # 2. Install semfree if needed
+        try:
+            # pylint: disable=import-outside-toplevel
+            from multiprocessing.synchronize import SemLock
+
+            del SemLock
+        except ImportError:
+            self.register(importlib.import_module('ocrmypdf.extra_plugins.semfree'))
+
+        # 3. Register setuptools plugins
+        self.load_setuptools_entrypoints('ocrmypdf')
+
+        # 4. Register plugins specified on command line
+        for name in self.__plugins:
+            if isinstance(name, Path) or name.endswith('.py'):
+                # Import by filename
+                module_name = Path(name).stem
+                spec = importlib.util.spec_from_file_location(module_name, name)
+                module = importlib.util.module_from_spec(spec)
+                sys.modules[module_name] = module
+                spec.loader.exec_module(module)
+            else:
+                # Import by dotted module name
+                module = importlib.import_module(name)
+            self.register(module)
 
 
-def get_plugin_manager(plugins: List[str], builtins=True):
+def get_plugin_manager(plugins: List[Union[str, Path]], builtins=True):
     pm = OcrmypdfPluginManager(
         project_name='ocrmypdf',
-        setup_func=partial(_setup_plugins, plugins=plugins, builtins=builtins),
+        plugins=plugins,
+        builtins=builtins,
     )
     return pm
 

src/ocrmypdf/_sync.py

@@ -1,19 +1,9 @@
 # © 2016 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 import logging
 import logging.handlers
@@ -27,9 +17,10 @@ from typing import List, NamedTuple, Optional, Tuple
 
 import PIL
 
-from ocrmypdf._concurrent import exec_progress_pool
+from ocrmypdf._concurrent import Executor, setup_executor
 from ocrmypdf._graft import OcrGrafter
 from ocrmypdf._jobcontext import PageContext, PdfContext, cleanup_working_files
+from ocrmypdf._logging import PageNumberFilter
 from ocrmypdf._pipeline import (
     convert_to_pdfa,
     copy_final,
@@ -62,13 +53,19 @@ from ocrmypdf._validation import (
     report_output_file_size,
 )
 from ocrmypdf.exceptions import ExitCode, ExitCodeException
-from ocrmypdf.helpers import available_cpu_count, check_pdf, samefile
+from ocrmypdf.helpers import (
+    NeverRaise,
+    available_cpu_count,
+    check_pdf,
+    pikepdf_enable_mmap,
+    samefile,
+)
 from ocrmypdf.pdfa import file_claims_pdfa
 
 log = logging.getLogger(__name__)
 
 
-class PageResult(NamedTuple):
+class PageResult(NamedTuple):  # pylint: disable=inherit-non-class
     pageno: int
     pdf_page_from_image: Optional[Path]
     ocr: Optional[Path]
@@ -206,15 +203,16 @@ def exec_page_sync(page_context: PageContext):
         if filtered_image:
             visible_image_out = filtered_image
         pdf_page_from_image_out = create_pdf_page_from_image(
-            visible_image_out, page_context
+            visible_image_out, page_context, orientation_correction
         )
 
-    if options.pdf_renderer == 'hocr':
+    if options.pdf_renderer.startswith('hocr'):
         (hocr_out, text_out) = ocr_engine_hocr(ocr_image_out, page_context)
         ocr_out = render_hocr_page(hocr_out, page_context)
-
-    if options.pdf_renderer == 'sandwich':
+    elif options.pdf_renderer == 'sandwich':
         (ocr_out, text_out) = ocr_engine_textonly_pdf(ocr_image_out, page_context)
+    else:
+        raise NotImplementedError(f"pdf_renderer {options.pdf_renderer}")
 
     return PageResult(
         pageno=page_context.pageno,
@@ -225,14 +223,14 @@ def exec_page_sync(page_context: PageContext):
     )
 
 
-def post_process(pdf_file, context: PdfContext):
+def post_process(pdf_file, context: PdfContext, executor: Executor):
     pdf_out = pdf_file
     if context.options.output_type.startswith('pdfa'):
         ps_stub_out = generate_postscript_stub(context)
         pdf_out = convert_to_pdfa(pdf_out, ps_stub_out, context)
 
     pdf_out = metadata_fixup(pdf_out, context)
-    return optimize_pdf(pdf_out, context)
+    return optimize_pdf(pdf_out, context, executor)
 
 
 def worker_init(max_pixels: int):
@@ -240,13 +238,15 @@ def worker_init(max_pixels: int):
     # the parent process, so ensure workers get it set. Not needed when running
     # threaded, but harmless to set again.
     PIL.Image.MAX_IMAGE_PIXELS = max_pixels
+    pikepdf_enable_mmap()
 
 
-def exec_concurrent(context: PdfContext):
+def exec_concurrent(context: PdfContext, executor: Executor):
     """Execute the pipeline concurrently"""
 
     # Run exec_page_sync on every page context
-    max_workers = min(len(context.pdfinfo), context.options.jobs)
+    options = context.options
+    max_workers = min(len(context.pdfinfo), options.jobs)
     if max_workers > 1:
         log.info("Start processing %d pages concurrently", max_workers)
 
@@ -254,61 +254,69 @@ def exec_concurrent(context: PdfContext):
     ocrgraft = OcrGrafter(context)
 
     def update_page(result: PageResult, pbar):
-        sidecars[result.pageno] = result.text
-        pbar.update()
-        ocrgraft.graft_page(
-            pageno=result.pageno,
-            image=result.pdf_page_from_image,
-            textpdf=result.ocr,
-            autorotate_correction=result.orientation_correction,
-        )
-        pbar.update()
+        try:
+            tls.pageno = result.pageno + 1
+            sidecars[result.pageno] = result.text
+            pbar.update()
+            ocrgraft.graft_page(
+                pageno=result.pageno,
+                image=result.pdf_page_from_image,
+                textpdf=result.ocr,
+                autorotate_correction=result.orientation_correction,
+            )
+            pbar.update()
+        finally:
+            tls.pageno = None
 
-    exec_progress_pool(
-        use_threads=context.options.use_threads,
+    executor(
+        use_threads=options.use_threads,
         max_workers=max_workers,
         tqdm_kwargs=dict(
             total=(2 * len(context.pdfinfo)),
-            desc='OCR',
+            desc='OCR' if options.tesseract_timeout > 0 else 'Image processing',
             unit='page',
             unit_scale=0.5,
-            disable=not context.options.progress_bar,
+            disable=not options.progress_bar,
         ),
-        task_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
+        worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
         task=exec_page_sync,
         task_arguments=context.get_page_contexts(),
         task_finished=update_page,
     )
 
     # Output sidecar text
-    if context.options.sidecar:
+    if options.sidecar:
         text = merge_sidecars(sidecars, context)
         # Copy text file to destination
-        copy_final(text, context.options.sidecar, context)
+        copy_final(text, options.sidecar, context)
 
     # Merge layers to one single pdf
     pdf = ocrgraft.finalize()
 
-    # PDF/A and metadata
-    pdf = post_process(pdf, context)
+    if options.output_type != 'none':
+        # PDF/A and metadata
+        log.info("Postprocessing...")
+        pdf = post_process(pdf, context, executor)
 
-    # Copy PDF file to destination
-    copy_final(pdf, context.options.output_file, context)
+        # Copy PDF file to destination
+        copy_final(pdf, options.output_file, context)
 
 
-class NeverRaise(Exception):
-    """An exception that is never raised"""
+def configure_debug_logging(log_filename: Path, prefix: str = ''):
+    """
+    Create a debug log file at a specified location.
 
-    pass  # pylint: disable=unnecessary-pass
-
-
-def configure_debug_logging(log_filename, prefix=''):
+    Arguments:
+        log_filename: Where to the put the log file.
+        prefix: The logging domain prefix that should be sent to the log.
+    """
     log_file_handler = logging.FileHandler(log_filename, delay=True)
     log_file_handler.setLevel(logging.DEBUG)
     formatter = logging.Formatter(
         '[%(asctime)s] - %(name)s - %(levelname)7s -%(pageno)s %(message)s'
     )
     log_file_handler.setFormatter(formatter)
+    log_file_handler.addFilter(PageNumberFilter())
     logging.getLogger(prefix).addHandler(log_file_handler)
     return log_file_handler
 
@@ -322,13 +330,23 @@ def run_pipeline(options, *, plugin_manager, api=False):
     if not plugin_manager:
         plugin_manager = get_plugin_manager(options.plugins)
 
-    work_folder = Path(mkdtemp(prefix="com.github.ocrmypdf."))
+    work_folder = Path(mkdtemp(prefix="ocrmypdf.io."))
     debug_log_handler = None
-    if (options.keep_temporary_files or options.verbose >= 1) and not os.environ.get(
-        'PYTEST_CURRENT_TEST', ''
+    if (
+        (options.keep_temporary_files or options.verbose >= 1)
+        and not os.environ.get('PYTEST_CURRENT_TEST', '')
+        and not api
     ):
-        debug_log_handler = configure_debug_logging(Path(work_folder) / "debug.log")
+        # 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"
+        )  # pragma: no cover
 
+    pikepdf_enable_mmap()
+
+    executor = setup_executor(plugin_manager)
     try:
         check_requested_output_file(options)
         start_input_file, original_filename = create_input_file(options, work_folder)
@@ -341,6 +359,7 @@ def run_pipeline(options, *, plugin_manager, api=False):
         # Gather pdfinfo and create context
         pdfinfo = get_pdfinfo(
             origin_pdf,
+            executor=executor,
             detailed_analysis=options.redo_ocr,
             progbar=options.progress_bar,
             max_workers=options.jobs if not options.use_threads else 1,  # To help debug
@@ -353,7 +372,7 @@ def run_pipeline(options, *, plugin_manager, api=False):
         validate_pdfinfo_options(context)
 
         # Execute the pipeline
-        exec_concurrent(context)
+        exec_concurrent(context, executor)
 
         if options.output_file == '-':
             log.info("Output sent to stdout")
@@ -381,19 +400,28 @@ def run_pipeline(options, *, plugin_manager, api=False):
                 return ExitCode.invalid_output_pdf
             report_output_file_size(options, start_input_file, options.output_file)
 
-    except (KeyboardInterrupt if not api else NeverRaise) as e:
+    except (KeyboardInterrupt if not api else NeverRaise):
         if options.verbose >= 1:
             log.exception("KeyboardInterrupt")
         else:
             log.error("KeyboardInterrupt")
         return ExitCode.ctrl_c
     except (ExitCodeException if not api else NeverRaise) as e:
-        if str(e):
+        if options.verbose >= 1:
+            log.exception("ExitCodeException")
+        elif str(e):
             log.error("%s: %s", type(e).__name__, str(e))
         else:
             log.error(type(e).__name__)
         return e.exit_code
-    except (Exception if not api else NeverRaise) as e:  # pylint: disable=broad-except
+    except (PIL.Image.DecompressionBombError if not api else NeverRaise) as e:
+        log.exception(
+            "A decompression bomb error was encountered while executing the "
+            "pipeline. Use the argument --max-image-mpixels to raise the maximum "
+            "image pixel limit."
+        )
+        return ExitCode.other_error
+    except (Exception if not api else NeverRaise):  # pylint: disable=broad-except
         log.exception("An exception occurred while executing the pipeline")
         return ExitCode.other_error
     finally:
@@ -401,7 +429,7 @@ def run_pipeline(options, *, plugin_manager, api=False):
             try:
                 debug_log_handler.close()
                 log.removeHandler(debug_log_handler)
-            except EnvironmentError as e:
+            except OSError as e:
                 print(e, file=sys.stderr)
         cleanup_working_files(work_folder, options)
 

src/ocrmypdf/_validation.py

@@ -1,20 +1,9 @@
 #!/usr/bin/env python3
 # © 2015-17 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
 import locale
@@ -24,7 +13,7 @@ import sys
 import unicodedata
 from pathlib import Path
 from shutil import copyfileobj
-from typing import Tuple
+from typing import List, Set, Tuple
 
 import pikepdf
 import PIL
@@ -37,18 +26,13 @@ from ocrmypdf.exceptions import (
     MissingDependencyError,
     OutputFileAccessError,
 )
-from ocrmypdf.helpers import (
-    is_file_writable,
-    is_iterable_notstr,
-    monotonic,
-    safe_symlink,
-)
+from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink, samefile
+from ocrmypdf.hocrtransform import HOCR_OK_LANGS
 from ocrmypdf.subprocess import check_external_program
 
 # -------------
 # External dependencies
 
-HOCR_OK_LANGS = frozenset(['eng', 'deu', 'spa', 'ita', 'por'])
 DEFAULT_LANGUAGE = 'eng'  # Enforce English hegemony
 
 log = logging.getLogger(__name__)
@@ -76,26 +60,33 @@ def check_options_languages(options, ocr_engine_languages):
             log.debug("No language specified; assuming --language %s", DEFAULT_LANGUAGE)
     if not ocr_engine_languages:
         return
-    if not options.languages.issubset(ocr_engine_languages):
+    missing_languages = options.languages - ocr_engine_languages
+    if missing_languages:
         msg = (
-            f"OCR engine does not have language data for the following "
+            "OCR engine does not have language data for the following "
             "requested languages: \n"
         )
-        for lang in options.languages - ocr_engine_languages:
-            msg += lang + '\n'
+        msg += '\n'.join(lang for lang in missing_languages)
+        msg += '\nNote: most languages are identified by a 3-digit ISO 639-2 Code'
         raise MissingDependencyError(msg)
 
 
 def check_options_output(options):
     is_latin = options.languages.issubset(HOCR_OK_LANGS)
 
-    if options.pdf_renderer == 'hocr' and not is_latin:
-        msg = (
+    if options.pdf_renderer.startswith('hocr') and not is_latin:
+        log.warning(
             "The 'hocr' PDF renderer is known to cause problems with one "
             "or more of the languages in your document.  Use "
-            "--pdf-renderer auto (the default) to avoid this issue."
+            "`--pdf-renderer auto` (the default) to avoid this issue."
+        )
+
+    if options.output_type == 'none' and options.output_file != os.devnull:
+        raise BadArgsError(
+            "Since you specified `--pdf-renderer none`, the output file "
+            f"{options.output_file} cannot be produced. Set the output file to "
+            f"{os.devnull} to suppress this message."
         )
-        log.warning(msg)
 
     lossless_reconstruction = False
     if not any(
@@ -122,7 +113,15 @@ def check_options_sidecar(options):
             raise BadArgsError(
                 "--sidecar filename must be specified when output file is stdout."
             )
+        elif options.output_file == os.devnull:
+            raise BadArgsError(
+                "--sidecar filename must be specified when output file is /dev/null or NUL."
+            )
         options.sidecar = options.output_file + '.txt'
+    if options.sidecar == options.input_file or options.sidecar == options.output_file:
+        raise BadArgsError(
+            "--sidecar file must be different from the input and output files"
+        )
 
 
 def check_options_preprocessing(options):
@@ -144,13 +143,11 @@ def check_options_preprocessing(options):
                     options.unpaper_args
                 )
         except Exception as e:
-            raise BadArgsError(str(e))
+            raise BadArgsError("--unpaper-args: " + str(e)) from e
 
 
-def _pages_from_ranges(ranges):
-    if is_iterable_notstr(ranges):
-        return set(ranges)
-    pages = []
+def _pages_from_ranges(ranges: str) -> Set[int]:
+    pages: List[int] = []
     page_groups = ranges.replace(' ', '').split(',')
     for g in page_groups:
         if not g:
@@ -161,9 +158,20 @@ 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}'"
+                    ) from None
+                pages.extend(new_pages)
             except ValueError:
-                raise BadArgsError("invalid page range")
+                raise BadArgsError(f"invalid page subrange '{g}'") 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(
@@ -179,15 +187,11 @@ def _pages_from_ranges(ranges):
 
 def check_options_ocr_behavior(options):
     exclusive_options = sum(
-        [
-            (1 if opt else 0)
-            for opt in (options.force_ocr, options.skip_text, options.redo_ocr)
-        ]
+        (1 if opt else 0)
+        for opt in (options.force_ocr, options.skip_text, options.redo_ocr)
     )
     if exclusive_options >= 2:
         raise BadArgsError("Choose only one of --force-ocr, --skip-text, --redo-ocr.")
-    if options.pages and options.sidecar:
-        raise BadArgsError("--pages and --sidecar are mutually exclusive")
     if options.pages:
         options.pages = _pages_from_ranges(options.pages)
 
@@ -224,12 +228,12 @@ def check_options_optimizing(options):
 
 
 def check_options_advanced(options):
-    if options.pdfa_image_compression != 'auto' and options.output_type.startswith(
+    if options.pdfa_image_compression != 'auto' and not options.output_type.startswith(
         'pdfa'
     ):
         log.warning(
-            "--pdfa-image-compression argument has no effect when "
-            "--output-type is not 'pdfa', 'pdfa-1', or 'pdfa-2'"
+            "--pdfa-image-compression argument only applies when "
+            "--output-type is one of 'pdfa', 'pdfa-1', or 'pdfa-2'"
         )
 
 
@@ -279,7 +283,7 @@ def check_closed_streams(options):  # pragma: no cover
     Attempting to a fork/exec a new Python process when any of std{in,out,err}
     are closed or not flushable for some reason may raise an exception.
     Fix this by opening devnull if the handle seems to be closed.  Do this
-    globally to avoid tracking places all places that fork.
+    globally to avoid tracking all places that fork.
 
     Seems to be specific to multiprocessing.Process not all Python process
     forkers.
@@ -301,7 +305,7 @@ def check_closed_streams(options):  # pragma: no cover
         if options.input_file == '-':
             log.error("Trying to read from stdin but stdin seems closed")
             return False
-        sys.stdin = open(os.devnull, 'r')
+        sys.stdin = open(os.devnull)
 
     if sys.stdout is None:
         if options.output_file == '-':
@@ -319,17 +323,6 @@ def check_closed_streams(options):  # pragma: no cover
     return True
 
 
-def log_page_orientations(pdfinfo):
-    direction = {0: 'n', 90: 'e', 180: 's', 270: 'w'}
-    orientations = []
-    for n, page in enumerate(pdfinfo):
-        angle = page.rotation or 0
-        if angle != 0:
-            orientations.append('{0}{1}'.format(n + 1, direction.get(angle, '')))
-    if orientations:
-        log.info('Page orientations detected: %s', ' '.join(orientations))
-
-
 def create_input_file(options, work_folder: Path) -> Tuple[Path, str]:
     if options.input_file == '-':
         # stdin
@@ -352,7 +345,17 @@ def create_input_file(options, work_folder: Path) -> Tuple[Path, str]:
             safe_symlink(options.input_file, target)
             return target, os.fspath(options.input_file)
         except FileNotFoundError:
-            raise InputFileError(f"File not found - {options.input_file}")
+            msg = f"File not found - {options.input_file}"
+            if Path('/.dockerenv').exists():  # pragma: no cover
+                msg += (
+                    "\nDocker cannot your working directory unless you "
+                    "explicitly share it with the Docker container and set up"
+                    "permissions correctly.\n"
+                    "You may find it easier to use stdin/stdout:"
+                    "\n"
+                    "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf\n"
+                )
+            raise InputFileError(msg)
 
 
 def check_requested_output_file(options):
@@ -416,6 +419,10 @@ def report_output_file_size(options, input_file, output_file):
                     f"The optional dependency '{name}' was not found, so some image "
                     f"optimizations could not be attempted."
                 )
+    if options.output_type.startswith('pdfa'):
+        reasons.append("PDF/A conversion was enabled. (Try `--output-type pdf`.)")
+    if options.plugins:
+        reasons.append("Plugins were used.")
 
     if reasons:
         explanation = "Possible reasons for this include:\n" + '\n'.join(reasons) + "\n"

src/ocrmypdf/_version.py

@@ -1,24 +1,16 @@
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
-import pkg_resources
+try:
+    from importlib_metadata import version as _package_version
+except ImportError:
+    from importlib.metadata import version as _package_version
 
 PROGRAM_NAME = 'ocrmypdf'
 
 # Official PEP 396
-__version__ = pkg_resources.get_distribution('ocrmypdf').version
+__version__ = _package_version('ocrmypdf')

src/ocrmypdf/api.py

@@ -1,33 +1,26 @@
 # © 2019 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 import logging
 import os
 import sys
-from argparse import ArgumentParser
+import threading
 from enum import IntEnum
+from io import IOBase
 from pathlib import Path
-from typing import BinaryIO, Iterable, Union
+from typing import AnyStr, BinaryIO, Iterable, Optional, Union
+from warnings import warn
 
 from ocrmypdf._logging import PageNumberFilter, TqdmConsole
 from ocrmypdf._plugin_manager import get_plugin_manager
 from ocrmypdf._sync import run_pipeline
 from ocrmypdf._validation import check_options
-from ocrmypdf.cli import get_parser
+from ocrmypdf.cli import ArgumentParser, get_parser
+from ocrmypdf.helpers import is_iterable_notstr
 
 try:
     import coloredlogs
@@ -35,7 +28,10 @@ except ModuleNotFoundError:
     coloredlogs = None
 
 
-PathOrIO = Union[BinaryIO, os.PathLike, str, bytes]
+StrPath = Union[Path, AnyStr]
+PathOrIO = Union[BinaryIO, StrPath]
+
+_api_lock = threading.Lock()
 
 
 class Verbosity(IntEnum):
@@ -49,29 +45,45 @@ class Verbosity(IntEnum):
 
 def configure_logging(
     verbosity: Verbosity,
+    *,
     progress_bar_friendly: bool = True,
     manage_root_logger: bool = False,
+    plugin_manager=None,
 ):
     """Set up logging.
 
-    Library users may wish to use this function if they want their log output to be
-    similar to ocrmypdf command line interface. If not used, the external application
-    should configure logging on its own.
+    Before calling :func:`ocrmypdf.ocr()`, you can use this function to
+    configure logging if you want ocrmypdf's output to look like the ocrmypdf
+    command line interface. It will register log handlers, log filters, and
+    formatters, configure color logging to standard error, and adjust the log
+    levels of third party libraries. Details of this are fine-tuned and subject
+    to change. The ``verbosity`` argument is equivalent to the argument
+    ``--verbose`` and applies those settings. If you have a wrapper
+    script for ocrmypdf and you want it to be very similar to ocrmypdf, use this
+    function; if you are using ocrmypdf as part of an application that manages
+    its own logging, you probably do not want this function.
 
-    ocrmypdf will perform all of its logging under the ``"ocrmypdf"`` logging namespace.
-    In addition, ocrmypdf imports pdfminer, which logs under ``"pdfminer"``. A library
-    user may wish to configure both; note that pdfminer is extremely chatty at the log
-    level ``logging.INFO``.
+    If this function is not called, ocrmypdf will not configure logging, and it
+    is up to the caller of ``ocrmypdf.ocr()`` to set up logging as it wishes using
+    the Python standard library's logging module. If this function is called,
+    the caller may of course make further adjustments to logging.
 
-    Library users may perform additional configuration afterwards.
+    Regardless of whether this function is called, ocrmypdf will perform all of
+    its logging under the ``"ocrmypdf"`` logging namespace. In addition,
+    ocrmypdf imports pdfminer, which logs under ``"pdfminer"``. A library user
+    may wish to configure both; note that pdfminer is extremely chatty at the
+    log level ``logging.INFO``.
+
+    This function does not set up the ``debug.log`` log file that the command
+    line interface does at certain verbosity levels. Applications should configure
+    their own debug logging.
 
     Args:
-        verbosity (Verbosity): Verbosity level.
-        progress_bar_friendly (bool): Install the TqdmConsole log handler, which is
-            compatible with the tqdm progress bar; without this log messages will
-            overwrite the progress bar
-        manage_root_logger (bool): Configure the process's root logger, to ensure
-            all log output is sent through
+        verbosity: Verbosity level.
+        progress_bar_friendly: If True (the default), install a custom log handler
+            that is compatible with progress bars and colored output.
+        manage_root_logger: Configure the process's root logger.
+        plugin_manager: The plugin manager, used for obtaining the custom log handler.
 
     Returns:
         The toplevel logger for ocrmypdf (or the root logger, if we are managing it).
@@ -82,9 +94,11 @@ def configure_logging(
     log = logging.getLogger(prefix)
     log.setLevel(logging.DEBUG)
 
-    if progress_bar_friendly:
-        console = logging.StreamHandler(stream=TqdmConsole(sys.stderr))
-    else:
+    console = None
+    if plugin_manager and progress_bar_friendly:
+        console = plugin_manager.hook.get_logging_console()
+
+    if not console:
         console = logging.StreamHandler(stream=sys.stderr)
 
     if verbosity < 0:
@@ -153,7 +167,7 @@ def create_options(
                 cmdline.append(f"--{cmd_style_arg}")
             continue
 
-        if isinstance(val, Iterable) and not isinstance(val, str):
+        if is_iterable_notstr(val):
             for elem in val:
                 cmdline.append(f"--{cmd_style_arg}")
                 cmdline.append(elem)
@@ -170,14 +184,14 @@ def create_options(
         else:
             raise TypeError(f"{arg}: {val} ({type(val)})")
 
-    try:
-        cmdline.append(os.fspath(input_file))
-    except TypeError:
+    if isinstance(input_file, (BinaryIO, IOBase)):
         cmdline.append('stream://input_file')
-    try:
-        cmdline.append(os.fspath(output_file))
-    except TypeError:
+    else:
+        cmdline.append(os.fspath(input_file))
+    if isinstance(output_file, (BinaryIO, IOBase)):
         cmdline.append('stream://output_file')
+    else:
+        cmdline.append(os.fspath(output_file))
 
     parser._api_mode = True
     options = parser.parse_args(cmdline)
@@ -199,7 +213,7 @@ def ocr(  # pylint: disable=unused-argument
     language: Iterable[str] = None,
     image_dpi: int = None,
     output_type=None,
-    sidecar: os.PathLike = None,
+    sidecar: Optional[StrPath] = None,
     jobs: int = None,
     use_threads: bool = None,
     title: str = None,
@@ -236,7 +250,8 @@ def ocr(  # pylint: disable=unused-argument
     user_words: os.PathLike = None,
     user_patterns: os.PathLike = None,
     fast_web_view: float = None,
-    plugins: Iterable[str] = None,
+    plugins: Iterable[StrPath] = None,
+    plugin_manager=None,
     keep_temporary_files: bool = None,
     progress_bar: bool = None,
     **kwargs,
@@ -258,7 +273,7 @@ def ocr(  # pylint: disable=unused-argument
             read.
         output_file: If a :class:`pathlib.Path`, ``str`` or ``bytes``, this is
             interpreted as file system path to the output file. If the object
-            appears to be a writable stream (with methods such as ``.read()`` and
+            appears to be a writable stream (with methods such as ``.write()`` and
             ``.seek()``), the output will be written to this stream. If
             ``output_file`` is ``"-"``, the output will be written to ``sys.stdout``
             (provided that standard output does not seem to be a terminal device).
@@ -288,20 +303,49 @@ def ocr(  # pylint: disable=unused-argument
     Returns:
         :class:`ocrmypdf.ExitCode`
     """
+    if plugins and plugin_manager:
+        raise ValueError("plugins= and plugin_manager are mutually exclusive")
+
     if not plugins:
         plugins = []
+    elif isinstance(plugins, (str, Path)):
+        plugins = [plugins]
     else:
         plugins = list(plugins)
 
-    parser = get_parser()
-    _plugin_manager = get_plugin_manager(plugins)
-    _plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
-
-    create_options_kwargs = {
-        k: v for k, v in locals().items() if not k.startswith('_') and k != 'kwargs'
-    }
+    # No new variable names should be assigned until these two steps are run
+    create_options_kwargs = {k: v for k, v in locals().items() if k != 'kwargs'}
     create_options_kwargs.update(kwargs)
 
-    options = create_options(**create_options_kwargs)
-    check_options(options, _plugin_manager)
-    return run_pipeline(options=options, plugin_manager=_plugin_manager, api=True)
+    parser = get_parser()
+    create_options_kwargs['parser'] = parser
+
+    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.
+
+        if not plugin_manager:
+            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)
+
+
+__all__ = [
+    'PageNumberFilter',
+    'TqdmConsole',
+    'Verbosity',
+    'check_options',
+    'configure_logging',
+    'create_options',
+    'get_parser',
+    'get_plugin_manager',
+    'ocr',
+    'run_pipeline',
+]

src/ocrmypdf/builtin_plugins/__init__.py

@@ -1,16 +1,9 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+# This file exists only mark builtin_plugins as a package.
+# The plugin manager will not load it, so anything defined here may not be
+# processed as a module.

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -0,0 +1,174 @@
+# © 2020 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+# © 2020 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+import logging
+import logging.handlers
+import multiprocessing
+import os
+import queue
+import signal
+import sys
+import threading
+from contextlib import suppress
+from multiprocessing.pool import Pool, ThreadPool
+from typing import Callable, Iterable, Type, Union
+
+from tqdm import tqdm
+
+from ocrmypdf import Executor, hookimpl
+from ocrmypdf._logging import TqdmConsole
+from ocrmypdf.exceptions import InputFileError
+from ocrmypdf.helpers import remove_all_log_handlers
+
+ProcessPool = Pool
+Queue = Union[multiprocessing.Queue, queue.Queue]
+UserInit = Callable[[], None]
+WorkerInit = Callable[[Queue, UserInit, int], None]
+
+
+def log_listener(q: Queue):
+    """Listen to the worker processes and forward the messages to logging
+
+    For simplicity this is a thread rather than a process. Only one process
+    should actually write to sys.stderr or whatever we're using, so if this is
+    made into a process the main application needs to be directed to it.
+
+    See https://docs.python.org/3/howto/logging-cookbook.html#logging-to-a-single-file-from-multiple-processes
+    """
+
+    while True:
+        try:
+            record = q.get()
+            if record is None:
+                break
+            logger = logging.getLogger(record.name)
+            logger.handle(record)
+        except Exception:  # pylint: disable=broad-except
+            import traceback  # pylint: disable=import-outside-toplevel
+
+            print("Logging problem", file=sys.stderr)
+            traceback.print_exc(file=sys.stderr)
+
+
+def process_sigbus(*args):
+    raise InputFileError("A worker process lost access to an input file")
+
+
+def process_init(q: Queue, user_init: UserInit, loglevel) -> None:
+    """Initialize a process pool worker"""
+
+    # Ignore SIGINT (our parent process will kill us gracefully)
+    signal.signal(signal.SIGINT, signal.SIG_IGN)
+
+    # Install SIGBUS handler (so our parent process can abort somewhat gracefully)
+    with suppress(AttributeError):  # Windows and Cygwin do not have SIGBUS
+        # Windows and Cygwin do not have pthread_sigmask or SIGBUS
+        signal.signal(signal.SIGBUS, process_sigbus)
+
+    # Remove any log handlers that belong to the parent process
+    root = logging.getLogger()
+    remove_all_log_handlers(root)
+
+    # Set up our single log handler to forward messages to the parent
+    root.setLevel(loglevel)
+    root.addHandler(logging.handlers.QueueHandler(q))
+
+    user_init()
+    return
+
+
+def thread_init(q: Queue, user_init: UserInit, loglevel) -> None:
+    # As a thread, block SIGBUS so the main thread deals with it...
+    with suppress(AttributeError):
+        signal.pthread_sigmask(signal.SIG_BLOCK, {signal.SIGBUS})
+
+    user_init()
+    return
+
+
+class StandardExecutor(Executor):
+    def _execute(
+        self,
+        *,
+        use_threads: bool,
+        max_workers: int,
+        tqdm_kwargs: dict,
+        worker_initializer: Callable,
+        task: Callable,
+        task_arguments: Iterable,
+        task_finished: Callable,
+    ):
+        if use_threads:
+            log_queue: Queue = queue.Queue(-1)
+            pool_class: Type[Pool] = ThreadPool
+            initializer: WorkerInit = thread_init
+        else:
+            log_queue = multiprocessing.Queue(-1)
+            pool_class = ProcessPool
+            initializer = process_init
+
+        # Regardless of whether we use_threads for worker processes, the log_listener
+        # must be a thread. Make sure we create the listener after the worker pool,
+        # so that it does not get forked into the workers.
+        listener = threading.Thread(target=log_listener, args=(log_queue,))
+        listener.start()
+
+        with self.pbar_class(**tqdm_kwargs) as pbar:
+            pool = pool_class(
+                processes=max_workers,
+                initializer=initializer,
+                initargs=(log_queue, worker_initializer, logging.getLogger("").level),
+            )
+            try:
+                results = pool.imap_unordered(task, task_arguments)
+                for result in results:
+                    if task_finished:
+                        task_finished(result, pbar)
+                    else:
+                        pbar.update()
+            except KeyboardInterrupt:
+                # Terminate pool so we exit instantly
+                pool.terminate()
+                # Don't try listener.join() here, will deadlock
+                raise
+            except Exception:
+                if not os.environ.get("PYTEST_CURRENT_TEST", ""):
+                    # Unless inside pytest, exit immediately because no one wants
+                    # to wait for child processes to finalize results that will be
+                    # thrown away. Inside pytest, we want child processes to exit
+                    # cleanly so that they output an error messages or coverage data
+                    # we need from them.
+                    pool.terminate()
+                raise
+            finally:
+                # Terminate log listener
+                log_queue.put_nowait(None)
+                pool.close()
+                pool.join()
+
+        listener.join()
+
+
+@hookimpl
+def get_executor(progressbar_class):
+    return StandardExecutor(pbar_class=progressbar_class)
+
+
+@hookimpl
+def get_progressbar_class():
+    return tqdm
+
+
+@hookimpl
+def get_logging_console():
+    return logging.StreamHandler(stream=TqdmConsole(sys.stderr))

src/ocrmypdf/builtin_plugins/default_filters.py

@@ -0,0 +1,14 @@
+# © 2021 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+from ocrmypdf import hookimpl
+
+
+@hookimpl
+def filter_pdf_page(
+    page, image_filename, output_pdf
+):  # pylint: disable=unused-argument
+    return output_pdf

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -1,19 +1,9 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 import logging
 
@@ -49,13 +39,11 @@ def check_options(options):
     if gs_version < '9.20' and options.output_type != 'pdf' and not is_latin:
         # https://bugs.ghostscript.com/show_bug.cgi?id=696874
         # Ghostscript < 9.20 fails to encode multibyte characters properly
-        msg = (
-            "The installed version of Ghostscript does not work correctly "
-            "with the OCR languages you specified. Use --output-type pdf or "
+        log.warning(
+            f"The installed version of Ghostscript ({gs_version}) does not work "
+            "correctly with the OCR languages you specified. Use --output-type pdf or "
             "upgrade to Ghostscript 9.20 or later to avoid this issue."
         )
-        msg += f"Found Ghostscript {gs_version}"
-        log.warning(msg)
 
     if options.output_type == 'pdfa':
         options.output_type = 'pdfa-2'
@@ -73,9 +61,9 @@ def rasterize_pdf_page(
     raster_device,
     raster_dpi,
     pageno,
-    page_dpi=None,
-    rotation=None,
-    filter_vector=False,
+    page_dpi,
+    rotation,
+    filter_vector,
 ):
     ghostscript.rasterize_pdf(
         input_file,
@@ -91,12 +79,21 @@ def rasterize_pdf_page(
 
 
 @hookimpl
-def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdfa_part):
+def generate_pdfa(
+    pdf_pages,
+    pdfmark,
+    output_file,
+    compression,
+    pdf_version,
+    pdfa_part,
+    progressbar_class,
+):
     ghostscript.generate_pdfa(
         pdf_pages=[*pdf_pages, pdfmark],
         output_file=output_file,
         compression=compression,
         pdf_version=pdf_version,
         pdfa_part=pdfa_part,
+        progressbar_class=progressbar_class,
     )
     return output_file

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -1,19 +1,9 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 import logging
 import os
@@ -21,7 +11,6 @@ import os
 from ocrmypdf import hookimpl
 from ocrmypdf._exec import tesseract
 from ocrmypdf.cli import numeric
-from ocrmypdf.exceptions import MissingDependencyError
 from ocrmypdf.helpers import clamp
 from ocrmypdf.pluginspec import OcrEngine
 from ocrmypdf.subprocess import check_external_program
@@ -90,20 +79,14 @@ def check_options(options):
         program='tesseract',
         package={'linux': 'tesseract-ocr'},
         version_checker=tesseract.version,
-        need_version='4.0.0',  # using backport for Travis CI
+        need_version='4.0.0-beta.1',  # using backport for Travis CI
+        version_parser=tesseract.TesseractVersion,
     )
 
     # Decide on what renderer to use
     if options.pdf_renderer == 'auto':
         options.pdf_renderer = 'sandwich'
 
-    if options.pdf_renderer == 'sandwich' and not tesseract.has_textonly_pdf(
-        set(options.languages)
-    ):
-        raise MissingDependencyError(
-            "You are using an alpha version of Tesseract 4.0 that does not support "
-            "the textonly_pdf parameter. We don't support versions this old."
-        )
     if not tesseract.has_user_words() and (options.user_words or options.user_patterns):
         log.warning(
             "Tesseract 4.0 ignores --user-words and --user-patterns, so these "
@@ -131,9 +114,7 @@ def validate(pdfinfo, options):
         os.environ['OMP_THREAD_LIMIT'] = str(tess_threads)
     else:
         tess_threads = int(os.environ['OMP_THREAD_LIMIT'])
-
-    if tess_threads > 1:
-        log.info("Using Tesseract OpenMP thread limit %d", tess_threads)
+    log.debug("Using Tesseract OpenMP thread limit %d", tess_threads)
 
 
 class TesseractOcrEngine(OcrEngine):

src/ocrmypdf/cli.py

@@ -1,27 +1,22 @@
 # © 2015-19 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 import argparse
+from typing import Any, Callable, Optional, TypeVar
 
 from ocrmypdf._version import PROGRAM_NAME as _PROGRAM_NAME
 from ocrmypdf._version import __version__ as _VERSION
 
+T = TypeVar('T')
 
-def numeric(basetype, min_=None, max_=None):
+
+def numeric(
+    basetype: Callable[[Any], T], min_: Optional[T] = None, max_: Optional[T] = None
+):
     """Validator for numeric params"""
     min_ = basetype(min_) if min_ is not None else None
     max_ = basetype(max_) if max_ is not None else None
@@ -29,7 +24,7 @@ def numeric(basetype, min_=None, max_=None):
     def _numeric(string):
         value = basetype(string)
         if (min_ is not None and value < min_) or (max_ is not None and value > max_):
-            msg = "%r not in valid range %r" % (string, (min_, max_))
+            msg = f"{string!r} not in valid range {(min_, max_)!r}"
             raise argparse.ArgumentTypeError(msg)
         return value
 
@@ -83,8 +78,8 @@ image, and then creates a PDF from the OCR information.
 """,
         epilog="""\
 OCRmyPDF attempts to keep the output file at about the same size.  If a file
-contains losslessly compressed images, and output file will be losslessly
-compressed as well.
+contains losslessly compressed images, and images in the output file will be
+losslessly compressed as well.
 
 PDF is a page description file that attempts to preserve a layout exactly.
 A PDF can contain vector objects (such as text or lines) and raster objects
@@ -103,9 +98,8 @@ all objects on the page and produce an image-only PDF as output.
 
 If you are concerned about long-term archiving of PDFs, use the default option
 --output-type pdfa which converts the PDF to a standardized PDF/A-2b.  This
-converts images to sRGB colorspace, removes some features from the PDF such
-as Javascript or forms. If you want to minimize the number of changes made to
-your PDF, use --output-type pdf.
+removes some features from the PDF such as Javascript or forms. If you want to
+minimize the number of changes made to your PDF, use --output-type pdf.
 
 If OCRmyPDF is given an image file as input, it will attempt to convert the
 image to a PDF before processing.  For more control over the conversion of
@@ -113,8 +107,7 @@ images to PDF, use the Python package img2pdf or other image to PDF software.
 
 For example, this command uses img2pdf to convert all .png files beginning
 with the 'page' prefix to a PDF, fitting each image on A4-sized paper, and
-sending the result to OCRmyPDF through a pipe.  img2pdf is a dependency of
-ocrmypdf so it is already installed.
+sending the result to OCRmyPDF through a pipe.
 
     img2pdf --pagesize A4 page*.png | ocrmypdf - myfile.pdf
 
@@ -154,7 +147,7 @@ Online documentation is located at:
     )
     parser.add_argument(
         '--output-type',
-        choices=['pdfa', 'pdf', 'pdfa-1', 'pdfa-2', 'pdfa-3'],
+        choices=['pdfa', 'pdf', 'pdfa-1', 'pdfa-2', 'pdfa-3', 'none'],
         default='pdfa',
         help="Choose output type. 'pdfa' creates a PDF/A-2b compliant file for "
         "long term archiving (default, recommended) but may not suitable "
@@ -162,7 +155,8 @@ Online documentation is located at:
         "also has problems with full Unicode text. 'pdf' attempts to "
         "preserve file contents as much as possible. 'pdf-a1' creates a "
         "PDF/A1-b file. 'pdf-a2' is equivalent to 'pdfa'. 'pdf-a3' creates a "
-        "PDF/A3-b file.",
+        "PDF/A3-b file. 'none' will produce no output, which may be helpful if "
+        "only the --sidecar is desired.",
     )
 
     # Use null string '\0' as sentinel to indicate the user supplied no argument,
@@ -176,7 +170,8 @@ Online documentation is located at:
         metavar='FILE',
         help="Generate sidecar text files that contain the same text recognized "
         "by Tesseract. This may be useful for building a OCR text database. "
-        "If FILE is omitted, the sidecar file be named {output_file}.txt "
+        "If FILE is omitted, the sidecar file be named {output_file}.txt; the next "
+        "argument must NOT be the name of the input PDF. "
         "If FILE is set to '-', the sidecar is written to stdout (a "
         "convenient way to preview OCR quality). The output file and sidecar "
         "may not both use stdout at the same time.",
@@ -346,8 +341,9 @@ Online documentation is located at:
             "Control how PDF is optimized after processing:"
             "0 - do not optimize; "
             "1 - do safe, lossless optimizations (default); "
-            "2 - do some lossy optimizations; "
-            "3 - do aggressive lossy optimizations (including lossy JBIG2)"
+            "2 - do lossy JPEG and JPEG2000 optimizations; "
+            "3 - do more aggressive lossy JPEG and JPEG2000 optimizations. "
+            "To enable lossy JBIG2, see --jbig2-lossy."
         ),
     )
     optimizing.add_argument(
@@ -385,7 +381,8 @@ Online documentation is located at:
         action='store_true',
         help=(
             "Enable JBIG2 lossy mode (better compression, not suitable for some "
-            "use cases - see documentation)."
+            "use cases - see documentation). Only takes effect if --optimize 1 or "
+            "higher is also enabled."
         ),
     )
     optimizing.add_argument(
@@ -419,7 +416,7 @@ Online documentation is located at:
     )
     advanced.add_argument(
         '--pdf-renderer',
-        choices=['auto', 'hocr', 'sandwich'],
+        choices=['auto', 'hocr', 'sandwich', 'hocrdebug'],
         default='auto',
         help="Choose OCR PDF renderer - the default option is to let OCRmyPDF "
         "choose.  See documentation for discussion.",
@@ -462,7 +459,12 @@ Online documentation is located at:
         dest='plugins',
         action='append',
         default=[],
-        help="Name of plugin to import.",
+        help="Name of plugin to import. Argument may be issued multiple times to "
+        "import multiple plugins. Plugins may be specified as module names in "
+        "Python syntax, provided they are installed in the same Python (virtual) "
+        "environment as ocrmypdf; or you may give the path to the Python file that "
+        "contains the plugin. Plugins must conform to the specification in the "
+        "OCRmyPDF documentation.",
     )
 
     debugging = parser.add_argument_group(

src/ocrmypdf/data/__init__.py

@@ -0,0 +1,8 @@
+# © 2021 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+"""Data files used to generate certain PDFs."""

src/ocrmypdf/exceptions.py

@@ -1,19 +1,8 @@
 # © 2016 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
 from enum import IntEnum

src/ocrmypdf/extra_plugins/semfree.py

@@ -0,0 +1,195 @@
+# © 2021 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+"""Semaphore-free alternate executor.
+
+There are two popular environments that do not fully support the standard Python
+multiprocessing module: AWS Lambda, and Termux (a terminal emulator for Android).
+
+This alternate executor divvies up work among worker processes before processing,
+rather than having each worker consume work from a shared queue when they finish
+their task. This means workers have no need to coordinate with each other. Each
+worker communicates only with the main process.
+
+This is not without drawbacks. If the tasks are not "even" in size, which cannot
+be guaranteed, some workers may end up with too much work while others are idle.
+It is less efficient than the standard implementation, so not th edefault.
+"""
+
+import logging
+import logging.handlers
+import signal
+from contextlib import suppress
+from enum import Enum, auto
+from itertools import islice, repeat, takewhile, zip_longest
+from multiprocessing import Pipe, Process
+from multiprocessing.connection import Connection, wait
+from typing import Callable, Iterable, Iterator, List
+
+from ocrmypdf import Executor, hookimpl
+from ocrmypdf._concurrent import NullProgressBar
+from ocrmypdf.exceptions import InputFileError
+from ocrmypdf.helpers import remove_all_log_handlers
+
+
+class MessageType(Enum):
+    exception = auto()
+    result = auto()
+    complete = auto()
+
+
+def split_every(n: int, iterable: Iterable) -> Iterator:
+    """Split iterable into groups of n.
+
+    >>> list(split_every(4, range(10)))
+    [[0, 1, 2], [3, 4, 5], [6, 7, 8], [9]]
+
+    https://stackoverflow.com/a/22919323
+    """
+    iterator = iter(iterable)
+    return takewhile(bool, (list(islice(iterator, n)) for _ in repeat(None)))
+
+
+def process_sigbus(*args):
+    raise InputFileError("A worker process lost access to an input file")
+
+
+class ConnectionLogHandler(logging.handlers.QueueHandler):
+    def __init__(self, conn: Connection) -> None:
+        # sets the parent's queue to None - parent only touches queue
+        # in enqueue() which we override
+        super().__init__(None)  # type: ignore
+        self.conn = conn
+
+    def enqueue(self, record):
+        self.conn.send(('log', record))
+
+
+def process_loop(
+    conn: Connection, user_init: Callable[[], None], loglevel, task, task_args
+):
+    """Initialize a process pool worker"""
+
+    # Install SIGBUS handler (so our parent process can abort somewhat gracefully)
+    with suppress(AttributeError):  # Windows and Cygwin do not have SIGBUS
+        # Windows and Cygwin do not have pthread_sigmask or SIGBUS
+        signal.signal(signal.SIGBUS, process_sigbus)
+
+    # Reconfigure the root logger for this process to send all messages to a queue
+    h = ConnectionLogHandler(conn)
+    root = logging.getLogger()
+    remove_all_log_handlers(root)
+    root.setLevel(loglevel)
+    root.addHandler(h)
+
+    user_init()
+
+    for args in task_args:
+        try:
+            result = task(args)
+        except Exception as e:
+            conn.send((MessageType.exception, e))
+            break
+        else:
+            conn.send((MessageType.result, result))
+
+    conn.send((MessageType.complete, None))
+    conn.close()
+    return
+
+
+class LambdaExecutor(Executor):
+    def _execute(
+        self,
+        *,
+        use_threads: bool,
+        max_workers: int,
+        tqdm_kwargs: dict,
+        worker_initializer: Callable,
+        task: Callable,
+        task_arguments: Iterable,
+        task_finished: Callable,
+    ):
+        if use_threads and max_workers == 1:
+            with self.pbar_class(**tqdm_kwargs) as pbar:
+                for args in task_arguments:
+                    result = task(args)
+                    task_finished(result, pbar)
+            return
+
+        task_arguments = list(task_arguments)
+        grouped_args = list(
+            zip_longest(*list(split_every(max_workers, task_arguments)))
+        )
+        if not grouped_args:
+            return
+
+        processes: List[Process] = []
+        connections: List[Connection] = []
+        for chunk in grouped_args:
+            parent_conn, child_conn = Pipe()
+
+            worker_args = [args for args in chunk if args is not None]
+            process = Process(
+                target=process_loop,
+                args=(
+                    child_conn,
+                    worker_initializer,
+                    logging.getLogger("").level,
+                    task,
+                    worker_args,
+                ),
+            )
+            process.daemon = True
+            processes.append(process)
+            connections.append(parent_conn)
+
+        for process in processes:
+            process.start()
+
+        with self.pbar_class(**tqdm_kwargs) as pbar:
+            while connections:
+                for r in wait(connections):
+                    if not isinstance(r, Connection):
+                        raise NotImplementedError("We only support Connection()")
+                    try:
+                        msg_type, msg = r.recv()
+                    except EOFError:
+                        connections.remove(r)
+                        continue
+
+                    if msg_type == MessageType.result:
+                        if task_finished:
+                            task_finished(msg, pbar)
+                    elif msg_type == 'log':
+                        record = msg
+                        logger = logging.getLogger(record.name)
+                        logger.handle(record)
+                    elif msg_type == MessageType.complete:
+                        connections.remove(r)
+                    elif msg_type == MessageType.exception:
+                        for process in processes:
+                            process.terminate()
+                        raise msg
+
+        for process in processes:
+            process.join()
+
+
+@hookimpl
+def get_executor(progressbar_class):
+    return LambdaExecutor(pbar_class=progressbar_class)
+
+
+@hookimpl
+def get_logging_console():
+    return logging.StreamHandler()
+
+
+@hookimpl
+def get_progressbar_class():
+    return NullProgressBar

src/ocrmypdf/helpers.py

@@ -1,19 +1,9 @@
 # © 2016 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 import logging
 import multiprocessing
@@ -25,9 +15,9 @@ from collections.abc import Iterable
 from contextlib import suppress
 from functools import wraps
 from io import StringIO
-from math import isclose
+from math import isclose, isfinite
 from pathlib import Path
-from typing import Any, Sequence, TypeVar
+from typing import Any, Sequence
 
 import pikepdf
 
@@ -35,17 +25,35 @@ log = logging.getLogger(__name__)
 
 
 class Resolution(namedtuple('Resolution', ('x', 'y'))):
+    """The number of pixels per inch in each 2D direction.
+
+    Resolution objects are considered "equal" for == purposes if they are
+    equal to a reasonable tolerance.
+    """
+
     __slots__ = ()
 
+    # rel_tol after converting from dpi to pixels per meter and saving
+    # as integer with rounding, as many file formats
+    CONVERSION_ERROR = 0.002
+
     def round(self, ndigits: int):
         return Resolution(round(self.x, ndigits), round(self.y, ndigits))
 
     def to_int(self):
         return Resolution(int(round(self.x)), int(round(self.y)))
 
+    @classmethod
+    def _isclose(cls, a, b):
+        return isclose(a, b, rel_tol=cls.CONVERSION_ERROR)
+
     @property
     def is_square(self) -> bool:
-        return isclose(self.x, self.y, rel_tol=1e-3)
+        return self._isclose(self.x, self.y)
+
+    @property
+    def is_finite(self) -> bool:
+        return isfinite(self.x) and isfinite(self.y)
 
     def take_max(self, vals, yvals=None):
         if yvals is not None:
@@ -62,13 +70,29 @@ class Resolution(namedtuple('Resolution', ('x', 'y'))):
     def __str__(self):
         return f"{self.x:f}x{self.y:f}"
 
-    def __repr__(self):
+    def __repr__(self):  # pragma: no cover
         return f"Resolution({self.x}x{self.y} dpi)"
 
+    def __eq__(self, other):
+        if isinstance(other, tuple) and len(other) == 2:
+            other = Resolution(*other)
+        if not isinstance(other, Resolution):
+            return NotImplemented
+        return self._isclose(self.x, other.x) and self._isclose(self.y, other.y)
+
+
+class NeverRaise(Exception):
+    """An exception that is never raised"""
+
 
 def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
-    """
-    Helper function: relinks soft symbolic link if necessary
+    """Create a symbolic link at ``soft_link_name``, which references ``input_file``.
+
+    Think of this as copying ``input_file`` to ``soft_link_name`` with less overhead.
+
+    Use symlinks safely. Self-linking loops are prevented. On Windows, file copy is
+    used since symlinks may require administrator privileges. An existing link at the
+    destination is removed.
     """
     input_file = os.fspath(input_file)
     soft_link_name = os.fspath(soft_link_name)
@@ -76,8 +100,8 @@ def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
     # Guard against soft linking to oneself
     if input_file == soft_link_name:
         log.warning(
-            "No symbolic link made. You are using "
-            "the original data directory as the working directory."
+            "No symbolic link created. You are using  the original data directory "
+            "as the working directory."
         )
         return
 
@@ -86,10 +110,7 @@ def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
         # do not delete or overwrite real (non-soft link) file
         if not os.path.islink(soft_link_name):
             raise FileExistsError(f"{soft_link_name} exists and is not a link")
-        try:
-            os.unlink(soft_link_name)
-        except OSError:
-            log.debug("Can't unlink %s", soft_link_name)
+        os.unlink(soft_link_name)
 
     if not os.path.exists(input_file):
         raise FileNotFoundError(f"trying to create a broken symlink to {input_file}")
@@ -113,11 +134,12 @@ def samefile(f1: os.PathLike, f2: os.PathLike):
 
 
 def is_iterable_notstr(thing: Any) -> bool:
+    """Is this is an iterable type, other than a string?"""
     return isinstance(thing, Iterable) and not isinstance(thing, str)
 
 
 def monotonic(L: Sequence) -> bool:
-    """Does list increase monotonically?"""
+    """Does this sequence increase monotonically?"""
     return all(b > a for a, b in zip(L, L[1:]))
 
 
@@ -127,6 +149,7 @@ def page_number(input_file: os.PathLike) -> int:
 
 
 def available_cpu_count() -> int:
+    """Returns number of CPUs in the system."""
     try:
         return multiprocessing.cpu_count()
     except NotImplementedError:
@@ -166,61 +189,83 @@ def is_file_writable(test_file: os.PathLike) -> bool:
                 with suppress(OSError):
                     p.unlink()
             return True
-    except (EnvironmentError, RuntimeError) as e:
+    except (OSError, RuntimeError) as e:
         log.debug(e)
         log.error(str(e))
         return False
 
 
 def check_pdf(input_file: Path) -> bool:
-    pdf = None
+    """Check if a PDF complies with the PDF specification.
+
+    Checks for proper formatting and proper linearization. Uses pikepdf (which in
+    turn, uses QPDF) to perform the checks.
+    """
     try:
         pdf = pikepdf.open(input_file)
     except pikepdf.PdfError as e:
         log.error(e)
         return False
     else:
-        messages = pdf.check()
-        for msg in messages:
-            if 'error' in msg.lower():
-                log.error(msg)
+        with pdf:
+            messages = pdf.check()
+            for msg in messages:
+                if 'error' in msg.lower():
+                    log.error(msg)
+                else:
+                    log.warning(msg)
+
+            sio = StringIO()
+            linearize_msgs = ''
+            try:
+                # If linearization is missing entirely, we do not complain. We do
+                # complain if linearization is present but incorrect.
+                pdf.check_linearization(sio)
+            except (RuntimeError, pikepdf.ForeignObjectError):
+                pass
             else:
-                log.warning(msg)
+                linearize_msgs = sio.getvalue()
+                if linearize_msgs:
+                    log.warning(linearize_msgs)
 
-        sio = StringIO()
-        linearize = None
-        try:
-            pdf.check_linearization(sio)
-        except RuntimeError:
-            pass
-        else:
-            linearize = sio.getvalue()
-            if linearize:
-                log.warning(linearize)
-
-        if not messages and not linearize:
-            return True
-        return False
-    finally:
-        if pdf:
-            pdf.close()
+            if not messages and not linearize_msgs:
+                return True
+            return False
 
 
-T = TypeVar('T')
-
-
-def clamp(n: T, smallest: T, largest: T) -> T:
+def clamp(n, smallest, largest):  # mypy doesn't understand types for this
+    """Clamps the value of ``n`` to between ``smallest`` and ``largest``."""
     return max(smallest, min(n, largest))
 
 
+def remove_all_log_handlers(logger):
+    "Remove all log handlers, usually used in a child process."
+    for handler in logger.handlers[:]:
+        logger.removeHandler(handler)
+        handler.close()  # To ensure handlers with opened resources are released
+
+
+def pikepdf_enable_mmap():
+    # try:
+    #     if pikepdf._qpdf.set_access_default_mmap(True):
+    #         log.debug("pikepdf mmap enabled")
+    # except AttributeError:
+    #     log.debug("pikepdf mmap not available")
+    # We found a race condition probably related to pybind issue #2252 that can
+    # cause a crash. For now, disable pikepdf mmap to be on the safe side.
+    # Fix is not in pybind11 2.6.0
+    # log.debug("pikepdf mmap disabled")
+    return
+
+
 def deprecated(func):
-    """Warn that function is deprecated"""
+    """Warn that function is deprecated."""
 
     @wraps(func)
     def new_func(*args, **kwargs):
         warnings.simplefilter('always', DeprecationWarning)  # turn off filter
         warnings.warn(
-            "Call to deprecated function {}.".format(func.__name__),
+            f"Call to deprecated function {func.__name__}.",
             category=DeprecationWarning,
             stacklevel=2,
         )

src/ocrmypdf/hocrtransform.py

@@ -31,18 +31,81 @@
 import argparse
 import os
 import re
-from collections import namedtuple
-from itertools import chain
 from math import atan, cos, sin
 from pathlib import Path
-from typing import Union
+from typing import Any, NamedTuple, Optional, Tuple, Union
 from xml.etree import ElementTree
 
 from reportlab.lib.colors import black, cyan, magenta, red
 from reportlab.lib.units import inch
 from reportlab.pdfgen.canvas import Canvas
 
-Rect = namedtuple('Rect', ['x1', 'y1', 'x2', 'y2'])
+# According to Wikipedia these languages are supported in the ISO-8859-1 character
+# set, meaning reportlab can generate them and they are compatible with hocr,
+# assuming Tesseract has the necessary languages installed. Note that there may
+# not be language packs for them.
+HOCR_OK_LANGS = frozenset(
+    [
+        # Languages fully covered by Latin-1:
+        'afr',  # Afrikaans
+        'alb',  # Albanian
+        'ast',  # Leonese
+        'baq',  # Basque
+        'bre',  # Breton
+        'cos',  # Corsican
+        'eng',  # English
+        'eus',  # Basque
+        'fao',  # Faoese
+        'gla',  # Scottish Gaelic
+        'glg',  # Galician
+        'glv',  # Manx
+        'ice',  # Icelandic
+        'ind',  # Indonesian
+        'isl',  # Icelandic
+        'ita',  # Italian
+        'ltz',  # Luxembourgish
+        'mal',  # Malay Rumi
+        'mga',  # Irish
+        'nor',  # Norwegian
+        'oci',  # Occitan
+        'por',  # Portugeuse
+        'roh',  # Romansh
+        'sco',  # Scots
+        'sma',  # Sami
+        'spa',  # Spanish
+        'sqi',  # Albanian
+        'swa',  # Swahili
+        'swe',  # Swedish
+        'tgl',  # Tagalog
+        'wln',  # Walloon
+        # Languages supported by Latin-1 except for a few rare characters that OCR
+        # is probably not trained to recognize anyway:
+        'cat',  # Catalan
+        'cym',  # Welsh
+        'dan',  # Danish
+        'deu',  # German
+        'dut',  # Dutch
+        'est',  # Estonian
+        'fin',  # Finnish
+        'fra',  # French
+        'hun',  # Hungarian
+        'kur',  # Kurdish
+        'nld',  # Dutch
+        'wel',  # Welsh
+    ]
+)
+
+
+Element = ElementTree.Element
+
+
+class Rect(NamedTuple):  # pylint: disable=inherit-non-class
+    """A rectangle for managing PDF coordinates."""
+
+    x1: Any
+    y1: Any
+    x2: Any
+    y2: Any
 
 
 class HocrTransformError(Exception):
@@ -69,7 +132,7 @@ class HocrTransform:
         {'ff': 'ff', 'ffi': 'f‌f‌i', 'ffl': 'f‌f‌l', 'fi': 'fi', 'fl': 'fl'}
     )
 
-    def __init__(self, hocr_filename: Union[str, Path], dpi: float):
+    def __init__(self, *, hocr_filename: Union[str, Path], dpi: float):
         self.dpi = dpi
         self.hocr = ElementTree.parse(os.fspath(hocr_filename))
 
@@ -105,7 +168,7 @@ class HocrTransform:
         else:
             return ''
 
-    def _get_element_text(self, element):
+    def _get_element_text(self, element: Element):
         """
         Return the textual content of the element and its children
         """
@@ -119,7 +182,7 @@ class HocrTransform:
         return text
 
     @classmethod
-    def element_coordinates(cls, element) -> Rect:
+    def element_coordinates(cls, element: Element) -> Rect:
         """
         Returns a tuple containing the coordinates of the bounding box around
         an element
@@ -133,7 +196,7 @@ class HocrTransform:
         return out
 
     @classmethod
-    def baseline(cls, element):
+    def baseline(cls, element: Element) -> Tuple[float, float]:
         """
         Returns a tuple containing the baseline slope and intercept.
         """
@@ -143,41 +206,45 @@ class HocrTransform:
                 return float(matches.group(1)), int(matches.group(2))
         return (0.0, 0.0)
 
-    def pt_from_pixel(self, pxl):
+    def pt_from_pixel(self, pxl) -> Rect:
         """
         Returns the quantity in PDF units (pt) given quantity in pixels
         """
         return Rect._make((c / self.dpi * inch) for c in pxl)
 
-    def _child_xpath(self, html_tag, html_class=None):
+    def _child_xpath(self, html_tag: str, html_class: Optional[str] = None) -> str:
         xpath = f".//{self.xmlns}{html_tag}"
         if html_class:
             xpath += f"[@class='{html_class}']"
         return xpath
 
     @classmethod
-    def replace_unsupported_chars(cls, s: str):
+    def replace_unsupported_chars(cls, s: str) -> str:
         """
         Given an input string, returns the corresponding string that:
-        - is available in the helvetica facetype
-        - does not contain any ligature (to allow easy search in the PDF file)
+        * is available in the Helvetica facetype
+        * does not contain any ligature (to allow easy search in the PDF file)
         """
         return s.translate(cls.ligatures)
 
     def topdown_position(self, element):
         pxl_line_coords = self.element_coordinates(element)
         line_box = self.pt_from_pixel(pxl_line_coords)
-        return -line_box.y2
+        # Coordinates here are still in the hocr coordinate system, so 0 on the y axis
+        # is the top of the page and increasing values of y will move towards the
+        # bottom of the page.
+        return line_box.y2
 
     def to_pdf(
         self,
+        *,
         out_filename: Path,
-        image_filename: Path = None,
+        image_filename: Optional[Path] = None,
         show_bounding_boxes: bool = False,
         fontname: str = "Helvetica",
         invisible_text: bool = False,
         interword_spaces: bool = False,
-    ):
+    ) -> None:
         """
         Creates a PDF file with an image superimposed on top of the text.
         Text is positioned according to the bounding box of the lines in
@@ -185,6 +252,20 @@ class HocrTransform:
         The image need not be identical to the image used to create the hOCR
         file.
         It can have a lower resolution, different color mode, etc.
+
+        Arguments:
+            out_filename: Path of PDF to write.
+            image_filename: Image to use for this file. If omitted, the OCR text
+                is shown.
+            show_bounding_boxes: Show bounding boxes around various text regions,
+                for debugging.
+            fontname: Name of font to use.
+            invisible_text: If True, text is rendered invisible so that is
+                selectable but never drawn. If False, text is visible and may
+                be seen if the image is skipped or deleted in Acrobat.
+            interword_spaces: If True, insert spaces between words rather than
+                drawing each word without spaces. Generally this improves text
+                extraction.
         """
         # create the PDF file
         # page size in points (1/72 in.)
@@ -215,13 +296,11 @@ class HocrTransform:
                 )
 
         found_lines = False
-        for line in sorted(
-            chain(
-                self.hocr.iterfind(self._child_xpath('span', 'ocr_header')),
-                self.hocr.iterfind(self._child_xpath('span', 'ocr_line')),
-                self.hocr.iterfind(self._child_xpath('span', 'ocr_textfloat')),
-            ),
-            key=self.topdown_position,
+        for line in (
+            element
+            for element in self.hocr.iterfind(self._child_xpath('span'))
+            if 'class' in element.attrib
+            and element.attrib['class'] in {'ocr_header', 'ocr_line', 'ocr_textfloat'}
         ):
             found_lines = True
             self._do_line(
@@ -263,13 +342,15 @@ class HocrTransform:
     def _do_line(
         self,
         pdf: Canvas,
-        line,
+        line: Optional[Element],
         elemclass: str,
         fontname: str,
         invisible_text: bool,
         interword_spaces: bool,
         show_bounding_boxes: bool,
     ):
+        if line is None:
+            return
         pxl_line_coords = self.element_coordinates(line)
         line_box = self.pt_from_pixel(pxl_line_coords)
         line_height = line_box.y2 - line_box.y1
@@ -406,10 +487,10 @@ if __name__ == "__main__":
     parser.add_argument('outputfile', help='Path to the PDF file to be generated')
     args = parser.parse_args()
 
-    hocr = HocrTransform(args.hocrfile, args.resolution)
+    hocr = HocrTransform(hocr_filename=args.hocrfile, dpi=args.resolution)
     hocr.to_pdf(
-        args.outputfile,
-        args.image,
-        args.boundingboxes,
+        out_filename=args.outputfile,
+        image_filename=args.image,
+        show_bounding_boxes=args.boundingboxes,
         interword_spaces=args.interword_spaces,
     )

src/ocrmypdf/leptonica.py

@@ -1,30 +1,21 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 #
 # © 2013-16: jbarlow83 from Github (https://github.com/jbarlow83)
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 #
 # Python FFI wrapper for Leptonica library
 
 import argparse
 import logging
 import os
+import platform
 import sys
-import warnings
+import threading
+from collections import deque
 from collections.abc import Sequence
 from contextlib import suppress
 from ctypes.util import find_library
@@ -32,18 +23,21 @@ from functools import lru_cache
 from io import BytesIO, UnsupportedOperation
 from os import fspath
 from tempfile import TemporaryFile
+from typing import ContextManager, Type
+from warnings import warn
 
 from ocrmypdf.exceptions import MissingDependencyError
 from ocrmypdf.lib._leptonica import ffi
-from ocrmypdf.subprocess import shim_paths_with_program_files
 
 # pylint: disable=protected-access
 
 logger = logging.getLogger(__name__)
 
 if os.name == 'nt':
+    from ocrmypdf.subprocess._windows import shim_env_path
+
     libname = 'liblept-5'
-    os.environ['PATH'] = shim_paths_with_program_files()
+    os.environ['PATH'] = shim_env_path()
 else:
     libname = 'lept'
 _libpath = find_library(libname)
@@ -66,6 +60,24 @@ if not _libpath:
         ---------------------------------------------------------------------
         """
     )
+if os.name == 'nt':
+    # On Windows, recent versions of libpng require zlib. We have to make sure
+    # the zlib version being loaded is the same one that libpng was built with.
+    # This tries to import zlib from Tesseract's installation folder, falling back
+    # to find_library() if liblept is being loaded from somewhere else.
+    # Loading zlib from other places could cause a version mismatch
+    _zlib_path = os.path.join(os.path.dirname(_libpath), 'zlib1.dll')
+    if not os.path.exists(_zlib_path):
+        _zlib_path = find_library('zlib') or ''
+    try:
+        zlib = ffi.dlopen(_zlib_path)
+    except ffi.error as e:
+        raise MissingDependencyError(
+            """
+            Could not load the zlib library. It could be that Tesseract is not installed properly,
+            we can't find the installation on your system PATH environment variable.
+            """
+        ) from e
 try:
     lept = ffi.dlopen(_libpath)
     lept.setMsgSeverity(lept.L_SEVERITY_WARNING)
@@ -75,11 +87,11 @@ except ffi.error as e:
     ) from e
 
 
-class _LeptonicaErrorTrap:
+class _LeptonicaErrorTrap_Redirect(ContextManager):
     """
-    Context manager to trap errors reported by Leptonica.
+    Context manager to trap errors reported by Leptonica < 1.79 or on Apple Silicon.
 
-    Leptonica's error return codes don't provide much informatino about what
+    Leptonica's error return codes don't provide much information about what
     went wrong. Leptonica does, however, write more detailed errors to stderr
     (provided this is not disabled at compile time). The Leptonica source
     code is very consistent in its use of macros to generate errors.
@@ -90,19 +102,23 @@ class _LeptonicaErrorTrap:
 
     """
 
+    leptonica_lock = threading.Lock()
+
     def __init__(self):
         self.tmpfile = None
         self.copy_of_stderr = -1
         self.no_stderr = False
 
     def __enter__(self):
-
         self.tmpfile = TemporaryFile()
 
         # Save the old stderr, and redirect stderr to temporary file
-        with suppress(AttributeError):
-            sys.stderr.flush()
+        self.leptonica_lock.acquire()
         try:
+            # It would make sense to do sys.stderr.flush() here, but that can deadlock
+            # due to https://bugs.python.org/issue6721. So don't flush. Pretend
+            # there's nothing important in sys.stderr. If the user cared they would
+            # be using Leptonica 1.79 or later anyway to avoid this mess.
             self.copy_of_stderr = os.dup(sys.stderr.fileno())
             os.dup2(self.tmpfile.fileno(), sys.stderr.fileno(), inheritable=False)
         except AttributeError:
@@ -114,6 +130,9 @@ class _LeptonicaErrorTrap:
             os.dup2(self.tmpfile.fileno(), 2, inheritable=False)
         except UnsupportedOperation:
             self.copy_of_stderr = None
+        except Exception:
+            self.leptonica_lock.release()
+            raise
         return
 
     def __exit__(self, exc_type, exc_value, traceback):
@@ -131,6 +150,8 @@ class _LeptonicaErrorTrap:
         self.tmpfile.seek(0)  # Cursor will be at end, so move back to beginning
         leptonica_output = self.tmpfile.read().decode(errors='replace')
         self.tmpfile.close()
+        self.leptonica_lock.release()
+
         # If there are Python errors, record them
         if exc_type:
             logger.warning(leptonica_output)
@@ -148,6 +169,70 @@ class _LeptonicaErrorTrap:
         return False
 
 
+tls = threading.local()
+tls.trap = None
+
+
+class _LeptonicaErrorTrap_Queue(ContextManager):
+    def __init__(self):
+        self.queue = deque()
+
+    def __enter__(self):
+        self.queue.clear()
+        tls.trap = self.queue
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        tls.trap = None
+        output = ''.join(self.queue)
+        self.queue.clear()
+
+        # If there are Python errors, record them
+        if exc_type:
+            logger.warning(output)
+
+        if 'Error' in output:
+            if 'image file not found' in output:
+                raise FileNotFoundError()
+            elif 'pixWrite: stream not opened' in output:
+                raise LeptonicaIOError()
+            elif 'index not valid' in output:
+                raise IndexError()
+            elif 'pixGetInvBackgroundMap: w and h must be >= 5' in output:
+                logger.warning(
+                    "Leptonica attempted to remove background from a low resolution - "
+                    "you may want to review in a PDF viewer"
+                )
+            else:
+                raise LeptonicaError(output)
+        return False
+
+
+try:
+
+    @ffi.callback("void(char *)")
+    def _stderr_handler(cstr):
+        msg = ffi.string(cstr).decode(errors='replace')
+        if msg.startswith("Error"):
+            logger.error(msg)
+        elif msg.startswith("Warning"):
+            logger.warning(msg)
+        else:
+            logger.debug(msg)
+        if tls.trap is not None:
+            tls.trap.append(msg)
+        return
+
+    lept.leptSetStderrHandler(_stderr_handler)
+except (ffi.error, MemoryError):
+    # Pre-1.79 Leptonica does not have leptSetStderrHandler
+    # And some platforms, notably Apple ARM 64, do not allow the write+execute
+    # memory needed to set up the callback function.
+    _LeptonicaErrorTrap: Type[ContextManager] = _LeptonicaErrorTrap_Redirect
+else:
+    # 1.79 have this new symbol
+    _LeptonicaErrorTrap = _LeptonicaErrorTrap_Queue
+
+
 class LeptonicaError(Exception):
     pass
 
@@ -188,7 +273,7 @@ class LeptonicaObject:
         # Leptonica API uses double-pointers for its destroy APIs to prevent
         # dangling pointers. This means we need to put our single pointer,
         # cdata, in a temporary CDATA**.
-        pp = ffi.new('{} **'.format(cls.LEPTONICA_TYPENAME), cdata)
+        pp = ffi.new(f'{cls.LEPTONICA_TYPENAME} **', cdata)
         cls.cdata_destroy(pp)
 
 
@@ -313,7 +398,7 @@ class Pix(LeptonicaObject):
 
     @classmethod
     def read(cls, path):
-        warnings.warn('Use Pix.open() instead', DeprecationWarning)
+        warn('Use Pix.open() instead', DeprecationWarning)
         return cls.open(path)
 
     @classmethod
@@ -355,6 +440,9 @@ class Pix(LeptonicaObject):
         bio = BytesIO()
         pillow_image.save(bio, format='png', compress_level=1)
         py_buffer = bio.getbuffer()
+        if platform.python_implementation() == 'PyPy':
+            # PyPy complains that it cannot do from_buffer(memoryview)
+            py_buffer = bytes(py_buffer)
         c_buffer = ffi.from_buffer(py_buffer)
         with _LeptonicaErrorTrap():
             pix = Pix(lept.pixReadMem(c_buffer, len(c_buffer)))
@@ -578,6 +666,9 @@ class Pix(LeptonicaObject):
         bg_val=200,
         smooth_kernel=(2, 1),
     ):
+        if self.width < tile_size[0] or self.height < tile_size[1]:
+            logger.info("Skipped pixMaskedThreshOnBackgroundNorm on small image")
+            return self
         # Background norm doesn't work on color mapped Pix, so remove colormap
         target_pix = self.remove_colormap(lept.REMOVE_CMAP_BASED_ON_SRC)
         with _LeptonicaErrorTrap():
@@ -757,7 +848,7 @@ class Box(LeptonicaObject):
 
     def __repr__(self):
         if self._cdata:
-            return '<leptonica.Box x={0} y={1} w={2} h={3}>'.format(
+            return '<leptonica.Box x={} y={} w={} h={}>'.format(
                 self.x, self.y, self.w, self.h
             )
         return '<leptonica.Box NULL>'
@@ -829,7 +920,7 @@ class Sel(LeptonicaObject):
         lines = [line.strip() for line in selstr.split('\n') if line.strip()]
         h = len(lines)
         w = len(lines[0])
-        lengths = set(len(line) for line in lines)
+        lengths = {len(line) for line in lines}
         if len(lengths) != 1:
             raise ValueError("All lines in selstr must be same length")
 
@@ -856,6 +947,8 @@ def get_leptonica_version():
     Caveat: Leptonica expects the caller to free this memory.  We don't,
     since that would involve binding to libc to access libc.free(),
     a pointless effort to reclaim 100 bytes of memory.
+
+    Reminder that this returns "leptonica-1.xx" or "leptonica-1.yy.0".
     """
     return ffi.string(lept.getLeptonicaVersion()).decode()
 

src/ocrmypdf/lib/__init__.py

@@ -1,18 +1,8 @@
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 """Bindings to external libraries"""

src/ocrmypdf/lib/compile_leptonica.py

@@ -1,20 +1,10 @@
 #!/usr/bin/env python3
 # © 2017 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 from pathlib import Path
 
@@ -509,6 +499,8 @@ void selDestroy ( SEL **psel );
 l_int32
 setMsgSeverity(l_int32 newsev);
 
+void
+leptSetStderrHandler(void (*handler)(const char *));
 """
 )
 

src/ocrmypdf/optimize.py

@@ -1,35 +1,44 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 import logging
 import sys
 import tempfile
 from collections import defaultdict
-from functools import partial
 from os import fspath
 from pathlib import Path
+from typing import (
+    Callable,
+    Dict,
+    Iterator,
+    List,
+    MutableSet,
+    NamedTuple,
+    NewType,
+    Optional,
+    Sequence,
+    Tuple,
+)
 
-import pikepdf
-from pikepdf import Dictionary, Name
+import img2pdf
+from pikepdf import (
+    Dictionary,
+    Name,
+    Object,
+    ObjectStreamMode,
+    Pdf,
+    PdfImage,
+    Stream,
+    UnsupportedImageTypeError,
+)
 from PIL import Image
-from tqdm import tqdm
 
 from ocrmypdf import leptonica
-from ocrmypdf._concurrent import exec_progress_pool
+from ocrmypdf._concurrent import Executor, SerialExecutor
 from ocrmypdf._exec import jbig2enc, pngquant
 from ocrmypdf._jobcontext import PdfContext
 from ocrmypdf.exceptions import OutputFileAccessError
@@ -41,49 +50,72 @@ DEFAULT_JPEG_QUALITY = 75
 DEFAULT_PNG_QUALITY = 70
 
 
-def img_name(root, xref, ext):
-    return fspath(root / f'{xref:08d}{ext}')
+Xref = NewType('Xref', int)
 
 
-def png_name(root, xref):
+class XrefExt(NamedTuple):  # pylint: disable=inherit-non-class
+    xref: Xref
+    ext: str
+
+
+def img_name(root: Path, xref: Xref, ext: str) -> Path:
+    return root / f'{xref:08d}{ext}'
+
+
+def png_name(root: Path, xref: Xref) -> Path:
     return img_name(root, xref, '.png')
 
 
-def jpg_name(root, xref):
+def jpg_name(root: Path, xref: Xref) -> Path:
     return img_name(root, xref, '.jpg')
 
 
-def tif_name(root, xref):
-    return img_name(root, xref, '.tif')
+def extract_image_filter(
+    pike: Pdf, root: Path, image: Stream, xref: Xref
+) -> Optional[Tuple[PdfImage, Tuple[Name, Object]]]:
+    del pike  # unused args
+    del root
 
-
-def extract_image_filter(pike, root, image, xref):
     if image.Subtype != Name.Image:
         return None
     if image.Length < 100:
-        log.debug("Skipping small image, xref %s", xref)
+        log.debug(f"Skipping small image, xref {xref}")
+        return None
+    if image.Width < 8 or image.Height < 8:  # Issue 732
+        log.debug(f"Skipping oddly sized image, xref {xref}")
         return None
 
-    pim = pikepdf.PdfImage(image)
+    pim = PdfImage(image)
 
     if len(pim.filter_decodeparms) > 1:
-        log.debug("Skipping multiply filtered, xref %s", xref)
+        log.debug(f"Skipping multiply filtered image, xref {xref}")
         return None
     filtdp = pim.filter_decodeparms[0]
 
     if pim.bits_per_component > 8:
+        log.debug(f"Skipping wide gamut image, xref {xref}")
         return None  # Don't mess with wide gamut images
 
     if filtdp[0] == Name.JPXDecode:
+        log.debug(f"Skipping JPEG2000 image, xref {xref}")
         return None  # Don't do JPEG2000
 
+    if filtdp[0] == Name.CCITTFaxDecode and filtdp[1].get('/K', 0) >= 0:
+        log.debug(f"Skipping CCITT Group 3 image, xref {xref}")
+        return None  # pikepdf doesn't support Group 3 yet
+
     if Name.Decode in image:
+        log.debug(f"Skipping image with Decode table, xref {xref}")
         return None  # Don't mess with custom Decode tables
 
     return pim, filtdp
 
 
-def extract_image_jbig2(*, pike, root, image, xref, options):
+def extract_image_jbig2(
+    *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
+) -> Optional[XrefExt]:
+    del options  # unused arg
+
     result = extract_image_filter(pike, root, image, xref)
     if result is None:
         return None
@@ -91,21 +123,38 @@ def extract_image_jbig2(*, pike, root, image, xref, options):
 
     if (
         pim.bits_per_component == 1
-        and filtdp != Name.JBIG2Decode
+        and filtdp[0] != Name.JBIG2Decode
         and jbig2enc.available()
     ):
-        try:
-            imgname = Path(root / f'{xref:08d}')
-            with imgname.open('wb') as f:
-                ext = pim.extract_to(stream=f)
-            imgname.rename(imgname.with_suffix(ext))
-        except pikepdf.UnsupportedImageTypeError:
-            return None
-        return xref, ext
+        # Save any colorspace associated with the image, so that we
+        # will export a pure 1-bit PNG with no palette or ICC profile.
+        # Showing the palette or ICC to jbig2enc will cause it to perform
+        # colorspace transform to 1bpp, which will conflict the palette or
+        # ICC if it exists.
+        colorspace = pim.obj.get(Name.ColorSpace, None)
+        if colorspace is not None or pim.image_mask:
+            try:
+                # Set to DeviceGray temporarily; we already in 1 bpc.
+                pim.obj.ColorSpace = Name.DeviceGray
+                imgname = root / f'{xref:08d}'
+                with imgname.open('wb') as f:
+                    ext = pim.extract_to(stream=f)
+                imgname.rename(imgname.with_suffix(ext))
+            except UnsupportedImageTypeError:
+                return None
+            finally:
+                # Restore image colorspace after temporarily setting it to DeviceGray
+                if colorspace is not None:
+                    pim.obj.ColorSpace = colorspace
+                else:
+                    del pim.obj.ColorSpace
+            return XrefExt(xref, ext)
     return None
 
 
-def extract_image_generic(*, pike, root, image, xref, options):
+def extract_image_generic(
+    *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
+) -> Optional[XrefExt]:
     result = extract_image_filter(pike, root, image, xref)
     if result is None:
         return None
@@ -115,11 +164,6 @@ def extract_image_generic(*, pike, root, image, xref, options):
     if pim.bits_per_component == 1:
         return None
 
-    try:
-        pim.indexed  # pikepdf 1.6.3 can't handle [/Indexed [/Array...]]
-    except NotImplementedError:
-        return None
-
     if filtdp[0] == Name.DCTDecode and options.optimize >= 2:
         # This is a simple heuristic derived from some training data, that has
         # about a 70% chance of guessing whether the JPEG is high quality,
@@ -138,13 +182,13 @@ def extract_image_generic(*, pike, root, image, xref, options):
         #     with Image.open(stream) as im:
         #         im.save(jpg_name(root, xref), icc_profile=iccbytes)
         try:
-            imgname = Path(root / f'{xref:08d}')
+            imgname = root / f'{xref:08d}'
             with imgname.open('wb') as f:
                 ext = pim.extract_to(stream=f)
             imgname.rename(imgname.with_suffix(ext))
-        except pikepdf.UnsupportedImageTypeError:
+        except UnsupportedImageTypeError:
             return None
-        return xref, ext
+        return XrefExt(xref, ext)
     elif (
         pim.indexed
         and pim.colorspace in pim.SIMPLE_COLORSPACES
@@ -153,12 +197,12 @@ def extract_image_generic(*, pike, root, image, xref, options):
         # Try to improve on indexed images - these are far from low hanging
         # fruit in most cases
         pim.as_pil_image().save(png_name(root, xref))
-        return xref, '.png'
+        return XrefExt(xref, '.png')
     elif not pim.indexed and pim.colorspace in pim.SIMPLE_COLORSPACES:
         # An optimization opportunity here, not currently taken, is directly
         # generating a PNG from compressed data
         pim.as_pil_image().save(png_name(root, xref))
-        return xref, '.png'
+        return XrefExt(xref, '.png')
     elif (
         not pim.indexed
         and pim.colorspace == Name.ICCBased
@@ -169,12 +213,17 @@ def extract_image_generic(*, pike, root, image, xref, options):
         # paying any attention to the ICC profile, provided we're not doing
         # lossy JBIG2
         pim.as_pil_image().save(png_name(root, xref))
-        return xref, '.png'
+        return XrefExt(xref, '.png')
 
     return None
 
 
-def extract_images(pike, root, options, extract_fn):
+def extract_images(
+    pike: Pdf,
+    root: Path,
+    options,
+    extract_fn: Callable[..., Optional[XrefExt]],
+) -> Iterator[Tuple[int, XrefExt]]:
     """Extract image using extract_fn
 
     Enumerate images on each page, lookup their xref/ID number in the PDF.
@@ -190,8 +239,8 @@ def extract_images(pike, root, options, extract_fn):
     extension. extract_fn must also extract the file it finds interesting.
     """
 
-    include_xrefs = set()
-    exclude_xrefs = set()
+    include_xrefs: MutableSet[Xref] = set()
+    exclude_xrefs: MutableSet[Xref] = set()
     pageno_for_xref = {}
     errors = 0
     for pageno, page in enumerate(pike.pages):
@@ -202,12 +251,14 @@ def extract_images(pike, root, options, extract_fn):
         for _imname, image in dict(xobjs).items():
             if image.objgen[1] != 0:
                 continue  # Ignore images in an incremental PDF
-            xref = image.objgen[0]
+            xref = Xref(image.objgen[0])
             if hasattr(image, 'SMask'):
                 # Ignore soft masks
-                smask_xref = image.SMask.objgen[0]
+                smask_xref = Xref(image.SMask.objgen[0])
                 exclude_xrefs.add(smask_xref)
+                log.debug(f"Skipping image {smask_xref} because it is an SMask")
             include_xrefs.add(xref)
+            log.debug(f"Treating {xref} as an optimization candidate")
             if xref not in pageno_for_xref:
                 pageno_for_xref[xref] = pageno
 
@@ -218,81 +269,78 @@ def extract_images(pike, root, options, extract_fn):
             result = extract_fn(
                 pike=pike, root=root, image=image, xref=xref, options=options
             )
-        except Exception as e:  # pylint: disable=broad-except
-            log.debug("Image xref %s, error %s", xref, repr(e))
+        except Exception:  # pylint: disable=broad-except
+            log.exception(f"While extracting image xref {xref}, an error occurred")
             errors += 1
         else:
             if result:
                 _, ext = result
-                yield pageno_for_xref[xref], xref, ext
+                yield pageno_for_xref[xref], XrefExt(xref, ext)
 
 
-def extract_images_generic(pike, root, options):
+def extract_images_generic(
+    pike: Pdf, root: Path, options
+) -> Tuple[List[Xref], List[Xref]]:
     """Extract any >=2bpp image we think we can improve"""
 
     jpegs = []
     pngs = []
-    for _, xref, ext in extract_images(pike, root, options, extract_image_generic):
-        log.debug('xref = %s ext = %s', xref, ext)
-        if ext == '.png':
-            pngs.append(xref)
-        elif ext == '.jpg':
-            jpegs.append(xref)
+    for _, xref_ext in extract_images(pike, root, options, extract_image_generic):
+        log.debug('%s', xref_ext)
+        if xref_ext.ext == '.png':
+            pngs.append(xref_ext.xref)
+        elif xref_ext.ext == '.jpg':
+            jpegs.append(xref_ext.xref)
     log.debug("Optimizable images: JPEGs: %s PNGs: %s", len(jpegs), len(pngs))
     return jpegs, pngs
 
 
-def extract_images_jbig2(pike, root, options):
+def extract_images_jbig2(pike: Pdf, root: Path, options) -> Dict[int, List[XrefExt]]:
     """Extract any bitonal image that we think we can improve as JBIG2"""
 
     jbig2_groups = defaultdict(list)
-    for pageno, xref, ext in extract_images(pike, root, options, extract_image_jbig2):
+    for pageno, xref_ext in extract_images(pike, root, options, extract_image_jbig2):
         group = pageno // options.jbig2_page_group_size
-        jbig2_groups[group].append((xref, ext))
+        jbig2_groups[group].append(xref_ext)
 
-    # Elide empty groups
-    jbig2_groups = {
-        group: xrefs for group, xrefs in jbig2_groups.items() if len(xrefs) > 0
-    }
     log.debug("Optimizable images: JBIG2 groups: %s", (len(jbig2_groups),))
     return jbig2_groups
 
 
-def _produce_jbig2_images(jbig2_groups, root, options):
+def _produce_jbig2_images(
+    jbig2_groups: Dict[int, List[XrefExt]], root: Path, options, executor: Executor
+) -> None:
     """Produce JBIG2 images from their groups"""
 
-    def jbig2_group_args(root, groups):
+    def jbig2_group_args(root: Path, groups: Dict[int, List[XrefExt]]):
         for group, xref_exts in groups.items():
             prefix = f'group{group:08d}'
-            yield dict(
-                cwd=fspath(root),
-                infiles=(img_name(root, xref, ext) for xref, ext in xref_exts),
-                out_prefix=prefix,
+            yield (
+                fspath(root),  # =cwd
+                (img_name(root, xref, ext) for xref, ext in xref_exts),  # =infiles
+                prefix,  # =out_prefix
             )
 
-    def jbig2_single_args(root, groups):
+    def jbig2_single_args(root, groups: Dict[int, List[XrefExt]]):
         for group, xref_exts in groups.items():
             prefix = f'group{group:08d}'
             # Second loop is to ensure multiple images per page are unpacked
             for n, xref_ext in enumerate(xref_exts):
                 xref, ext = xref_ext
-                yield dict(
-                    cwd=fspath(root),
-                    infile=img_name(root, xref, ext),
-                    outfile=root / f'{prefix}.{n:04d}',
+                yield (
+                    fspath(root),
+                    img_name(root, xref, ext),
+                    root / f'{prefix}.{n:04d}',
                 )
 
-    def convert_generic(fn, kwargs_dict):
-        return fn(**kwargs_dict)
-
     if options.jbig2_page_group_size > 1:
         jbig2_args = jbig2_group_args
-        jbig2_convert = partial(convert_generic, jbig2enc.convert_group)
+        jbig2_convert = jbig2enc.convert_group_mp
     else:
         jbig2_args = jbig2_single_args
-        jbig2_convert = partial(convert_generic, jbig2enc.convert_single)
+        jbig2_convert = jbig2enc.convert_single_mp
 
-    exec_progress_pool(
+    executor(
         use_threads=True,
         max_workers=options.jobs,
         tqdm_kwargs=dict(
@@ -306,7 +354,13 @@ def _produce_jbig2_images(jbig2_groups, root, options):
     )
 
 
-def convert_to_jbig2(pike, jbig2_groups, root, options):
+def convert_to_jbig2(
+    pike: Pdf,
+    jbig2_groups: Dict[int, List[XrefExt]],
+    root: Path,
+    options,
+    executor: Executor,
+) -> None:
     """Convert images to JBIG2 and insert into PDF.
 
     When the JBIG2 page group size is > 1 we do several JBIG2 images at once
@@ -319,15 +373,16 @@ def convert_to_jbig2(pike, jbig2_groups, root, options):
     When the JBIG2 symbolic coder is not used, each JBIG2 stands on its own
     and needs no dictionary. Currently this must be lossless JBIG2.
     """
+    jbig2_globals_dict: Optional[Dictionary]
 
-    _produce_jbig2_images(jbig2_groups, root, options)
+    _produce_jbig2_images(jbig2_groups, root, options, executor)
 
     for group, xref_exts in jbig2_groups.items():
         prefix = f'group{group:08d}'
         jbig2_symfile = root / (prefix + '.sym')
         if jbig2_symfile.exists():
             jbig2_globals_data = jbig2_symfile.read_bytes()
-            jbig2_globals = pikepdf.Stream(pike, jbig2_globals_data)
+            jbig2_globals = Stream(pike, jbig2_globals_data)
             jbig2_globals_dict = Dictionary(JBIG2Globals=jbig2_globals)
         elif options.jbig2_page_group_size == 1:
             jbig2_globals_dict = None
@@ -344,31 +399,105 @@ def convert_to_jbig2(pike, jbig2_groups, root, options):
             )
 
 
-def transcode_jpegs(pike, jpegs, root, options):
-    for xref in tqdm(
-        jpegs, desc="JPEGs", unit='image', disable=not options.progress_bar
-    ):
-        in_jpg = Path(jpg_name(root, xref))
-        opt_jpg = in_jpg.with_suffix('.opt.jpg')
+def _optimize_jpeg(args):
+    xref, in_jpg, opt_jpg, jpeg_quality = args
 
-        # This produces a debug warning from PIL
-        # DEBUG:PIL.Image:Error closing: 'NoneType' object has no attribute
-        # 'close'.  Seems to be mostly harmless
-        # https://github.com/python-pillow/Pillow/issues/1144
-        with Image.open(fspath(in_jpg)) as im:
-            im.save(fspath(opt_jpg), optimize=True, quality=options.jpeg_quality)
+    # This may produce a debug warning from PIL
+    # DEBUG:PIL.Image:Error closing: 'NoneType' object has no attribute
+    # 'close'.  Seems to be mostly harmless
+    # https://github.com/python-pillow/Pillow/issues/1144
+    with Image.open(in_jpg) as im:
+        im.save(opt_jpg, optimize=True, quality=jpeg_quality)
 
-        if opt_jpg.stat().st_size > in_jpg.stat().st_size:
-            log.debug("xref %s, jpeg, made larger - skip", xref)
-            continue
+    if opt_jpg.stat().st_size > in_jpg.stat().st_size:
+        log.debug("xref %s, jpeg, made larger - skip", xref)
+        opt_jpg.unlink()
+        opt_jpg = None
+    return xref, opt_jpg
+
+
+def transcode_jpegs(
+    pike: Pdf, jpegs: Sequence[Xref], root: Path, options, executor
+) -> None:
+    def jpeg_args():
+        for xref in jpegs:
+            in_jpg = jpg_name(root, xref)
+            opt_jpg = in_jpg.with_suffix('.opt.jpg')
+            yield xref, in_jpg, opt_jpg, options.jpeg_quality
+
+    def finish_jpeg(result, pbar):
+        xref, opt_jpg = result
+        if opt_jpg:
+            compdata = leptonica.CompressedData.open(opt_jpg)
+            im_obj = pike.get_object(xref, 0)
+            im_obj.write(compdata.read(), filter=Name.DCTDecode)
+        pbar.update()
+
+    executor(
+        use_threads=True,  # Processes are significantly slower at this task
+        max_workers=options.jobs,
+        tqdm_kwargs=dict(
+            desc="JPEGs",
+            total=len(jpegs),
+            unit='image',
+            disable=not options.progress_bar,
+        ),
+        task=_optimize_jpeg,
+        task_arguments=jpeg_args(),
+        task_finished=finish_jpeg,
+    )
+
+
+def _transcode_png(pike: Pdf, filename: Path, xref: Xref) -> bool:
+    output = filename.with_suffix('.png.pdf')
+    with output.open('wb') as f:
+        img2pdf.convert(fspath(filename), outputstream=f)
+
+    with Pdf.open(output) as pdf_image:
+        foreign_image = next(iter(pdf_image.pages[0].images.values()))
+        local_image = pike.copy_foreign(foreign_image)
 
-        compdata = leptonica.CompressedData.open(opt_jpg)
         im_obj = pike.get_object(xref, 0)
-        im_obj.write(compdata.read(), filter=Name.DCTDecode)
+        im_obj.write(
+            local_image.read_raw_bytes(),
+            filter=local_image.Filter,
+            decode_parms=local_image.DecodeParms,
+        )
+
+        # Don't copy keys from the new image...
+        del_keys = set(im_obj.keys()) - set(local_image.keys())
+        # ...except for the keep_fields, which are essential to displaying
+        # the image correctly and preserving its metadata. (/Decode arrays
+        # and /SMaskInData are implicitly discarded prior to this point.)
+        keep_fields = {
+            '/ID',
+            '/Intent',
+            '/Interpolate',
+            '/Mask',
+            '/Metadata',
+            '/OC',
+            '/OPI',
+            '/SMask',
+            '/StructParent',
+        }
+        del_keys -= keep_fields
+        for key in local_image.keys():
+            if key != Name.Length and str(key) not in keep_fields:
+                im_obj[key] = local_image[key]
+        for key in del_keys:
+            del im_obj[key]
+    return True
 
 
-def transcode_pngs(pike, images, image_name_fn, root, options):
-    modified = set()
+def transcode_pngs(
+    pike: Pdf,
+    images: Sequence[Xref],
+    image_name_fn: Callable[[Path, Xref], Path],
+    root: Path,
+    options,
+    executor,
+) -> None:
+    modified: MutableSet[Xref] = set()
     if options.optimize >= 2:
         png_quality = (
             max(10, options.png_quality - 10),
@@ -386,10 +515,7 @@ def transcode_pngs(pike, images, image_name_fn, root, options):
                 )
                 modified.add(xref)
 
-        def pngquant_fn(args):
-            pngquant.quantize(*args)
-
-        exec_progress_pool(
+        executor(
             use_threads=True,
             max_workers=options.jobs,
             tqdm_kwargs=dict(
@@ -398,113 +524,25 @@ def transcode_pngs(pike, images, image_name_fn, root, options):
                 unit='image',
                 disable=not options.progress_bar,
             ),
-            task=pngquant_fn,
+            task=pngquant.quantize_mp,
             task_arguments=pngquant_args(),
         )
 
     for xref in modified:
-        im_obj = pike.get_object(xref, 0)
-        try:
-            pix = leptonica.Pix.open(png_name(root, xref))
-            if pix.mode == '1':
-                compdata = pix.generate_pdf_ci_data(leptonica.lept.L_G4_ENCODE, 0)
-            else:
-                compdata = leptonica.CompressedData.open(png_name(root, xref))
-        except leptonica.LeptonicaError as e:
-            # Most likely this means file not found, i.e. quantize did not
-            # produce an improved version
-            log.error(e)
-            continue
-
-        # If re-coded image is larger don't use it - we test here because
-        # pngquant knows the size of the temporary output file but not the actual
-        # object in the PDF
-        if len(compdata) > int(im_obj.stream_dict.Length):
-            log.debug(
-                f"pngquant: pngquant did not improve over original image "
-                f"{len(compdata)} > {int(im_obj.stream_dict.Length)}"
-            )
-            continue
-        if compdata.type == leptonica.lept.L_FLATE_ENCODE:
-            rewrite_png(pike, im_obj, compdata)
-        elif compdata.type == leptonica.lept.L_G4_ENCODE:
-            rewrite_png_as_g4(pike, im_obj, compdata)
+        filename = png_name(root, xref)
+        _transcode_png(pike, filename, xref)
 
 
-def rewrite_png_as_g4(pike, im_obj, compdata):
-    im_obj.BitsPerComponent = 1
-    im_obj.Width = compdata.w
-    im_obj.Height = compdata.h
-
-    im_obj.write(compdata.read())
-
-    log.debug(f"PNG to G4 {im_obj.objgen}")
-    if Name.Predictor in im_obj:
-        del im_obj.Predictor
-    if Name.DecodeParms in im_obj:
-        del im_obj.DecodeParms
-    im_obj.DecodeParms = Dictionary(
-        K=-1, BlackIs1=bool(compdata.minisblack), Columns=compdata.w
-    )
-
-    im_obj.Filter = Name.CCITTFaxDecode
-    return
+DEFAULT_EXECUTOR = SerialExecutor()
 
 
-def rewrite_png(pike, im_obj, compdata):
-    # 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
-    # on the image before Flate encoding. (Typically one is.)
-    # According to Leptonica source, PDF readers don't actually need us
-    # to specify the correct predictor, they just need a value of either:
-    #   1 - no predictor
-    #   10-14 - there is a predictor
-    # Leptonica's compdata->predictor only tells TRUE or FALSE
-    # 10-14 means the actual predictor is specified in the data, so for any
-    # number >= 10 the PDF reader will use whatever the PNG data specifies.
-    # In practice Leptonica should use Paeth, 14, but 15 seems to be the
-    # designated value for "optimal". So we will use 15.
-    # See:
-    #   - PDF RM 7.4.4.4 Table 10
-    #   - https://github.com/DanBloomberg/leptonica/blob/master/src/pdfio2.c#L757
-    predictor = 15 if compdata.predictor > 0 else 1
-    dparms = Dictionary(Predictor=predictor)
-    if predictor > 1:
-        dparms.BitsPerComponent = compdata.bps  # Yes, this is redundant
-        dparms.Colors = compdata.spp
-        dparms.Columns = compdata.w
-
-    im_obj.BitsPerComponent = compdata.bps
-    im_obj.Width = compdata.w
-    im_obj.Height = compdata.h
-
-    log.debug(
-        f"PNG {im_obj.objgen}: palette={compdata.ncolors} spp={compdata.spp} bps={compdata.bps}"
-    )
-    if compdata.ncolors > 0:
-        # .ncolors is the number of colors in the palette, not the number of
-        # colors used in a true color image. The palette string is always
-        # given as RGB tuples even when the image is grayscale; see
-        # https://github.com/DanBloomberg/leptonica/blob/master/src/colormap.c#L2067
-        palette_pdf_string = compdata.get_palette_pdf_string()
-        palette_data = pikepdf.Object.parse(palette_pdf_string)
-        palette_stream = pikepdf.Stream(pike, bytes(palette_data))
-        palette = [Name.Indexed, Name.DeviceRGB, compdata.ncolors - 1, palette_stream]
-        cs = palette
-    else:
-        # ncolors == 0 means we are using a colorspace without a palette
-        if compdata.spp == 1:
-            cs = Name.DeviceGray
-        elif compdata.spp == 3:
-            cs = Name.DeviceRGB
-        elif compdata.spp == 4:
-            cs = Name.DeviceCMYK
-    im_obj.ColorSpace = cs
-    im_obj.write(compdata.read(), filter=Name.FlateDecode, decode_parms=dparms)
-
-
-def optimize(input_file, output_file, context, save_settings):
+def optimize(
+    input_file: Path,
+    output_file: Path,
+    context,
+    save_settings,
+    executor: Executor = DEFAULT_EXECUTOR,
+) -> None:
     options = context.options
     if options.optimize == 0:
         safe_symlink(input_file, output_file)
@@ -517,26 +555,26 @@ def optimize(input_file, output_file, context, save_settings):
     if options.jbig2_page_group_size == 0:
         options.jbig2_page_group_size = 10 if options.jbig2_lossy else 1
 
-    with pikepdf.Pdf.open(input_file) as pike:
-        root = Path(output_file).parent / 'images'
+    with Pdf.open(input_file) as pike:
+        root = output_file.parent / 'images'
         root.mkdir(exist_ok=True)
 
         jpegs, pngs = extract_images_generic(pike, root, options)
-        transcode_jpegs(pike, jpegs, root, options)
+        transcode_jpegs(pike, jpegs, root, options, executor)
         # if options.optimize >= 2:
         # Try pngifying the jpegs
         #    transcode_pngs(pike, jpegs, jpg_name, root, options)
-        transcode_pngs(pike, pngs, png_name, root, options)
+        transcode_pngs(pike, pngs, png_name, root, options, executor)
 
         jbig2_groups = extract_images_jbig2(pike, root, options)
-        convert_to_jbig2(pike, jbig2_groups, root, options)
+        convert_to_jbig2(pike, jbig2_groups, root, options, executor)
 
-        target_file = Path(output_file).with_suffix('.opt.pdf')
+        target_file = output_file.with_suffix('.opt.pdf')
         pike.remove_unreferenced_resources()
         pike.save(target_file, **save_settings)
 
-    input_size = Path(input_file).stat().st_size
-    output_size = Path(target_file).stat().st_size
+    input_size = input_file.stat().st_size
+    output_size = target_file.stat().st_size
     if output_size == 0:
         raise OutputFileAccessError(
             f"Output file not created after optimizing. We probably ran "
@@ -544,12 +582,15 @@ def optimize(input_file, output_file, context, save_settings):
         )
     ratio = input_size / output_size
     savings = 1 - output_size / input_size
-    log.info(f"Optimize ratio: {ratio:.2f} savings: {(100 * savings):.1f}%")
+    log.info(f"Optimize ratio: {ratio:.2f} savings: {(savings):.1%}")
 
     if savings < 0:
-        log.info("Image optimization did not improve the file - discarded")
+        log.info(
+            "Image optimization did not improve the file - "
+            "optimizations will not be used"
+        )
         # We still need to save the file
-        with pikepdf.open(input_file) as pike:
+        with Pdf.open(input_file) as pike:
             pike.remove_unreferenced_resources()
             pike.save(output_file, **save_settings)
     else:
@@ -557,8 +598,8 @@ def optimize(input_file, output_file, context, save_settings):
 
 
 def main(infile, outfile, level, jobs=1):
-    from tempfile import TemporaryDirectory  # pylint: disable=import-outside-toplevel
     from shutil import copy  # pylint: disable=import-outside-toplevel
+    from tempfile import TemporaryDirectory  # pylint: disable=import-outside-toplevel
 
     class OptimizeOptions:
         """Emulate ocrmypdf's options"""
@@ -576,6 +617,7 @@ def main(infile, outfile, level, jobs=1):
             self.quiet = True
             self.progress_bar = False
 
+    infile = Path(infile)
     options = OptimizeOptions(
         input_file=infile,
         jobs=jobs,
@@ -595,7 +637,7 @@ def main(infile, outfile, level, jobs=1):
             dict(
                 compress_streams=True,
                 preserve_pdfa=True,
-                object_stream_mode=pikepdf.ObjectStreamMode.generate,
+                object_stream_mode=ObjectStreamMode.generate,
             ),
         )
         copy(fspath(tmpout), fspath(outfile))

src/ocrmypdf/pdfa.py

@@ -1,100 +1,115 @@
-# © 2015 James R. Barlow: github.com/jbarlow83
+# © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 """
-Generate a PDFMARK file for Ghostscript >= 9.14, for PDF/A conversion
-
-pdfmark is an extension to the Postscript language that describes some PDF
-features like bookmarks and annotations. It was originally specified Adobe
-Distiller, for Postscript to PDF conversion:
-https://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/pdfmark_reference.pdf
-
-Ghostscript uses pdfmark for PDF to PDF/A conversion as well. To use Ghostscript
-to create a PDF/A, we need to create a pdfmark file with the necessary metadata.
-
-This takes care of the many version-specific bugs and pecularities in
-Ghostscript's handling of pdfmark.
-
+Utilities for PDF/A production and confirmation with Ghostspcript.
 """
 
 import base64
 from pathlib import Path
-from string import Template
+from typing import Dict, Iterator, Union
+
+try:
+    from importlib_resources import files as package_files
+except ImportError:
+    from importlib.resources import files as package_files
 
 import pikepdf
-import pkg_resources
+import pkg_resources  # deprecated
 
+# Deprecated
 ICC_PROFILE_RELPATH = 'data/sRGB.icc'
-
+# Deprecated
 SRGB_ICC_PROFILE = pkg_resources.resource_filename('ocrmypdf', ICC_PROFILE_RELPATH)
 
-
-# This is a template written in PostScript which is needed to create PDF/A
-# files, from the Ghostscript documentation. Lines beginning with % are
-# comments. Python substitution variables have a '$' prefix.
-pdfa_def_template = u"""%!
-% Define an ICC profile :
-/ICCProfile $icc_profile
-def
-
-[/_objdef {icc_PDFA} /type /stream /OBJ pdfmark
-[{icc_PDFA} << /N 3 >> /PUT pdfmark
-[{icc_PDFA} ICCProfile /PUT pdfmark
-
-% Define the output intent dictionary :
-
-[/_objdef {OutputIntent_PDFA} /type /dict /OBJ pdfmark
-[{OutputIntent_PDFA} <<
-  /Type /OutputIntent             % Must be so (the standard requires).
-  /S /GTS_PDFA1                   % Must be so (the standard requires).
-  /DestOutputProfile {icc_PDFA}            % Must be so (see above).
-  /OutputConditionIdentifier ($icc_identifier)
->> /PUT pdfmark
-[{Catalog} <</OutputIntents [ {OutputIntent_PDFA} ]>> /PUT pdfmark
-"""
+SRGB_ICC_PROFILE_NAME = 'sRGB.icc'
 
 
-def generate_pdfa_ps(target_filename, icc='sRGB'):
-    """Create a Postscript pdfmark file for Ghostscript PDF/A conversion
+def _postscript_objdef(
+    alias: str,
+    dictionary: Dict[str, str],
+    *,
+    stream_name: str = None,
+    stream_data: bytes = None,
+) -> Iterator[str]:
+    assert (stream_name is None) == (stream_data is None)
 
-    A pdfmark file is a small Postscript program that provides some information
-    Ghostscript needs to perform PDF/A conversion. The only information we put
-    in specifies that we want the file to be a PDF/A, and we want to Ghostscript
-    to convert objects to the sRGB colorspace if it runs into any object that
-    it decides must be converted.
+    objtype = '/stream' if stream_name else '/dict'
 
-    See the Adobe pdfmark Reference for details:
-    https://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/pdfmark_reference.pdf
+    if stream_name:
+        assert stream_data is not None
+        a85_data = base64.a85encode(stream_data, adobe=True).decode('ascii')
+        yield f'{stream_name} ' + a85_data
+        yield 'def'
 
-    :param target_filename: filename to save
-    :param icc: ICC identifier such as 'sRGB'
+    if alias != '{Catalog}':  # Catalog needs no definition
+        yield f'[/_objdef {alias} /type {objtype} /OBJ pdfmark'
+
+    yield f'[{alias} <<'
+    for key, val in dictionary.items():
+        yield f'  {key} {val}'
+    yield '>> /PUT pdfmark'
+
+    if stream_name:
+        yield f'[{alias} {stream_name[1:]} /PUT pdfmark'
+
+
+def _make_postscript(icc_name: str, icc_data: bytes, colors: int) -> Iterator[str]:
+    yield '%!'
+    yield from _postscript_objdef(
+        '{icc_PDFA}',  # Not an f-string
+        {'/N': str(colors)},
+        stream_name='/ICCProfile',
+        stream_data=icc_data,
+    )
+    yield ''
+    yield from _postscript_objdef(
+        '{OutputIntent_PDFA}',
+        {
+            '/Type': '/OutputIntent',
+            '/S': '/GTS_PDFA1',
+            '/DestOutputProfile': '{icc_PDFA}',
+            '/OutputConditionIdentifier': f'({icc_name})',  # Only f-string
+        },
+    )
+    yield ''
+    yield from _postscript_objdef(
+        '{Catalog}', {'/OutputIntents': '[ {OutputIntent_PDFA} ]'}
+    )
+
+
+def generate_pdfa_ps(target_filename: Path, icc: str = 'sRGB'):
+    """Create a Postscript PDFMARK file for Ghostscript PDF/A conversion
+
+    pdfmark is an extension to the Postscript language that describes some PDF
+    features like bookmarks and annotations. It was originally specified Adobe
+    Distiller, for Postscript to PDF conversion.
+
+    Ghostscript uses pdfmark for PDF to PDF/A conversion as well. To use Ghostscript
+    to create a PDF/A, we need to create a pdfmark file with the necessary metadata.
+
+    This function takes care of the many version-specific bugs and pecularities in
+    Ghostscript's handling of pdfmark.
+
+    The only information we put in specifies that we want the file to be a
+    PDF/A, and we want to Ghostscript to convert objects to the sRGB colorspace
+    if it runs into any object that it decides must be converted.
+
+    Arguments:
+        target_filename: filename to save
+        icc: ICC identifier such as 'sRGB'
+    References:
+        Adobe PDFMARK Reference: https://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/pdfmark_reference.pdf
     """
-    if icc == 'sRGB':
-        icc_profile = SRGB_ICC_PROFILE
-    else:
+    if icc != 'sRGB':
         raise NotImplementedError("Only supporting sRGB")
 
-    # Read the ICC profile, encode as ASCII85 and convert to a string which we
-    # will insert in the .ps file
-    bytes_icc_profile = Path(icc_profile).read_bytes()
-    icc_profile = base64.a85encode(bytes_icc_profile, adobe=True).decode('ascii')
-
-    t = Template(pdfa_def_template)
-    ps = t.substitute(icc_profile=icc_profile, icc_identifier=icc)
+    bytes_icc_profile = (package_files('ocrmypdf.data') / SRGB_ICC_PROFILE).read_bytes()
+    ps = '\n'.join(_make_postscript(icc, bytes_icc_profile, 3))
 
     # We should have encoded everything to pure ASCII by this point, and
     # to be safe, only allow ASCII in PostScript
@@ -102,8 +117,8 @@ def generate_pdfa_ps(target_filename, icc='sRGB'):
     return target_filename
 
 
-def file_claims_pdfa(filename):
-    """Determines if the file claims to be PDF/A compliant
+def file_claims_pdfa(filename: Path):
+    """Determines if the file claims to be PDF/A compliant.
 
     This only checks if the XMP metadata contains a PDF/A marker. It does not
     do full PDF/A validation.
@@ -119,7 +134,7 @@ def file_claims_pdfa(filename):
             }
         valid_part_conforms = {'1A', '1B', '2A', '2B', '2U', '3A', '3B', '3U'}
         conformance = f'PDF/A-{pdfmeta.pdfa_status}'
-        pdfa_dict = {}
+        pdfa_dict: Dict[str, Union[str, bool]] = {}
         if pdfmeta.pdfa_status in valid_part_conforms:
             pdfa_dict['pass'] = True
             pdfa_dict['output'] = 'pdfa'

src/ocrmypdf/pdfinfo/__init__.py

@@ -1,19 +1,9 @@
 #!/usr/bin/env python3
 # © 2015 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 from ocrmypdf.pdfinfo.info import Colorspace, Encoding, PdfInfo

src/ocrmypdf/pdfinfo/info.py

@@ -1,39 +1,47 @@
 #!/usr/bin/env python3
 # © 2015 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+
+import atexit
 import logging
 import re
-from collections import defaultdict, namedtuple
+from collections import defaultdict
+from contextlib import ExitStack
 from decimal import Decimal
 from enum import Enum
 from functools import partial
-from math import hypot, isclose
+from math import hypot, inf, isclose
 from os import PathLike
 from pathlib import Path
-from typing import Any, Dict, List
+from typing import (
+    Container,
+    Dict,
+    Iterator,
+    List,
+    Mapping,
+    NamedTuple,
+    Optional,
+    Tuple,
+    Union,
+)
 from warnings import warn
 
-import pikepdf
-from pikepdf import PdfMatrix
+from pikepdf import (
+    Object,
+    Pdf,
+    PdfImage,
+    PdfInlineImage,
+    PdfMatrix,
+    parse_content_stream,
+)
 
-from ocrmypdf._concurrent import exec_progress_pool
-from ocrmypdf.exceptions import EncryptedPdfError
-from ocrmypdf.helpers import Resolution, available_cpu_count
+from ocrmypdf._concurrent import Executor, SerialExecutor
+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
 
 logger = logging.getLogger()
@@ -44,7 +52,7 @@ Encoding = Enum(
     'Encoding', 'ccitt jpeg jpeg2000 jbig2 asciihex ascii85 lzw flate runlength'
 )
 
-FRIENDLY_COLORSPACE = {
+FRIENDLY_COLORSPACE: Dict[str, Colorspace] = {
     '/DeviceGray': Colorspace.gray,
     '/CalGray': Colorspace.gray,
     '/DeviceRGB': Colorspace.rgb,
@@ -62,7 +70,7 @@ FRIENDLY_COLORSPACE = {
     '/I': Colorspace.index,
 }
 
-FRIENDLY_ENCODING = {
+FRIENDLY_ENCODING: Dict[str, Encoding] = {
     '/CCITTFaxDecode': Encoding.ccitt,
     '/DCTDecode': Encoding.jpeg,
     '/JPXDecode': Encoding.jpeg2000,
@@ -76,7 +84,7 @@ FRIENDLY_ENCODING = {
     '/RL': Encoding.runlength,
 }
 
-FRIENDLY_COMP = {
+FRIENDLY_COMP: Dict[Colorspace, int] = {
     Colorspace.gray: 1,
     Colorspace.rgb: 3,
     Colorspace.cmyk: 4,
@@ -91,19 +99,33 @@ UNIT_SQUARE = (1.0, 0.0, 0.0, 1.0, 0.0, 0.0)
 def _is_unit_square(shorthand):
     values = map(float, shorthand)
     pairwise = zip(values, UNIT_SQUARE)
-    return all([isclose(a, b, rel_tol=1e-3) for a, b in pairwise])
+    return all(isclose(a, b, rel_tol=1e-3) for a, b in pairwise)
 
 
-XobjectSettings = namedtuple('XobjectSettings', ['name', 'shorthand', 'stack_depth'])
+class XobjectSettings(NamedTuple):
+    name: str
+    shorthand: Tuple[float, float, float, float, float, float]
+    stack_depth: int
 
-InlineSettings = namedtuple('InlineSettings', ['iimage', 'shorthand', 'stack_depth'])
 
-ContentsInfo = namedtuple(
-    'ContentsInfo',
-    ['xobject_settings', 'inline_images', 'found_vector', 'found_text', 'name_index'],
-)
+class InlineSettings(NamedTuple):
+    iimage: PdfInlineImage
+    shorthand: Tuple[float, float, float, float, float, float]
+    stack_depth: int
 
-TextboxInfo = namedtuple('TextboxInfo', ['bbox', 'is_visible', 'is_corrupt'])
+
+class ContentsInfo(NamedTuple):
+    xobject_settings: List[XobjectSettings]
+    inline_images: List[InlineSettings]
+    found_vector: bool
+    found_text: bool
+    name_index: Mapping[str, List[XobjectSettings]]
+
+
+class TextboxInfo(NamedTuple):
+    bbox: Tuple[float, float, float, float]
+    is_visible: bool
+    is_corrupt: bool
 
 
 class VectorMarker:
@@ -125,7 +147,7 @@ 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
@@ -154,8 +176,8 @@ def _interpret_contents(contentstream, initial_shorthand=UNIT_SQUARE):
 
     stack = []
     ctm = PdfMatrix(initial_shorthand)
-    xobject_settings = []
-    inline_images = []
+    xobject_settings: List[XobjectSettings] = []
+    inline_images: List[InlineSettings] = []
     name_index = defaultdict(lambda: [])
     found_vector = False
     found_text = False
@@ -165,9 +187,7 @@ def _interpret_contents(contentstream, initial_shorthand=UNIT_SQUARE):
     operator_whitelist = ' '.join(vector_ops | text_showing_ops | image_ops)
 
     for n, graphobj in enumerate(
-        _normalize_stack(
-            pikepdf.parse_content_stream(contentstream, operator_whitelist)
-        )
+        _normalize_stack(parse_content_stream(contentstream, operator_whitelist))
     ):
         operands, operator = graphobj
         if operator == 'q':
@@ -193,7 +213,7 @@ def _interpret_contents(contentstream, initial_shorthand=UNIT_SQUARE):
                 name=image_name, shorthand=ctm.shorthand, stack_depth=len(stack)
             )
             xobject_settings.append(settings)
-            name_index[image_name].append(settings)
+            name_index[str(image_name)].append(settings)
         elif operator == 'INLINE IMAGE':  # BI/ID/EI are grouped into this
             iimage = operands[0]
             inline = InlineSettings(
@@ -214,7 +234,7 @@ 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.
@@ -237,7 +257,7 @@ def _get_dpi(ctm_shorthand, image_size):
     width-axis vector v0 (1, 0), height-axis vector vh (0, 1) with the matrix,
     which gives the dimensions of the image in PDF units. From there we can
     compare to actual image dimensions. PDF uses
-    row vector * matrix_tranposed unlike the traditional
+    row vector * matrix_transposed unlike the traditional
     matrix * column vector.
 
     The offset, width and height vectors can be combined in a matrix and
@@ -264,34 +284,45 @@ def _get_dpi(ctm_shorthand, image_size):
     a, b, c, d, _, _ = ctm_shorthand
 
     # Calculate the width and height of the image in PDF units
-    image_drawn_width = hypot(a, b)
-    image_drawn_height = hypot(c, d)
+    image_drawn = hypot(a, b), hypot(c, d)
 
-    # The scale of the image is pixels per unit of default user space (1/72")
-    scale_w = image_size[0] / image_drawn_width
-    scale_h = image_size[1] / image_drawn_height
-
-    # DPI = scale * 72
-    dpi_w = scale_w * 72.0
-    dpi_h = scale_h * 72.0
+    def calc(drawn, pixels, inches_per_pt=72.0):
+        # The scale of the image is pixels per unit of default user space (1/72")
+        scale = pixels / drawn if drawn != 0 else inf
+        dpi = scale * inches_per_pt
+        return dpi
 
+    dpi_w, dpi_h = (calc(image_drawn[n], image_size[n]) for n in range(2))
     return Resolution(dpi_w, dpi_h)
 
 
 class ImageInfo:
     DPI_PREC = Decimal('1.000')
 
-    def __init__(self, *, name='', pdfimage=None, inline=None, shorthand=None):
+    _comp: Optional[int]
+    _name: str
 
+    def __init__(
+        self,
+        *,
+        name='',
+        pdfimage: Optional[Object] = None,
+        inline: Optional[PdfInlineImage] = None,
+        shorthand=None,
+    ):
         self._name = str(name)
         self._shorthand = shorthand
 
+        pim: Union[PdfInlineImage, PdfImage]
+
         if inline is not None:
             self._origin = 'inline'
-            pim = inline.iimage
+            pim = inline
         elif pdfimage is not None:
             self._origin = 'xobject'
-            pim = pikepdf.PdfImage(pdfimage)
+            pim = PdfImage(pdfimage)
+        else:
+            raise ValueError("Either pdfimage or inline must be set")
         self._width = pim.width
         self._height = pim.height
 
@@ -305,14 +336,14 @@ class ImageInfo:
 
         self._bpc = int(pim.bits_per_component)
         try:
-            self._enc = FRIENDLY_ENCODING.get(pim.filters[0], 'image')
+            self._enc = FRIENDLY_ENCODING.get(pim.filters[0])
         except IndexError:
-            self._enc = '?'
+            self._enc = None
 
         try:
-            self._color = FRIENDLY_COLORSPACE.get(pim.colorspace, '?')
+            self._color = FRIENDLY_COLORSPACE.get(pim.colorspace or '')
         except NotImplementedError:
-            self._color = '?'
+            self._color = None
         if self._enc == Encoding.jpeg2000:
             self._color = Colorspace.jpeg2000
 
@@ -326,11 +357,14 @@ class ImageInfo:
             else:
                 self._comp = 3
         else:
-            self._comp = FRIENDLY_COMP.get(self._color, '?')
+            if isinstance(self._color, Colorspace):
+                self._comp = FRIENDLY_COMP.get(self._color)
+            else:
+                self._comp = None
 
             # Bit of a hack... infer grayscale if component count is uncertain
             # but encoding only supports monochrome.
-            if self._comp == '?' and self._enc in (Encoding.ccitt, Encoding.jbig2):
+            if self._comp is None and self._enc in (Encoding.ccitt, Encoding.jbig2):
                 self._comp = FRIENDLY_COMP[Colorspace.gray]
 
     @property
@@ -355,15 +389,19 @@ class ImageInfo:
 
     @property
     def color(self):
-        return self._color
+        return self._color if self._color is not None else '?'
 
     @property
     def comp(self):
-        return self._comp
+        return self._comp if self._comp is not None else '?'
 
     @property
     def enc(self):
-        return self._enc
+        return self._enc if self._enc is not None else 'image'
+
+    @property
+    def renderable(self):
+        return self.dpi.is_finite and self.width >= 0 and self.height >= 0
 
     @property
     def dpi(self):
@@ -381,16 +419,16 @@ 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):
         yield ImageInfo(
-            name='inline-%02d' % n, shorthand=inline.shorthand, inline=inline
+            name='inline-%02d' % n, shorthand=inline.shorthand, inline=inline.iimage
         )
 
 
-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
@@ -410,15 +448,17 @@ def _image_xobjects(container):
         return
     xobjs = resources['/XObject'].as_dict()
     for xobj in xobjs:
-        candidate = xobjs[xobj]
-        if not '/Subtype' in candidate:
+        candidate: Object = xobjs[xobj]
+        if '/Subtype' not in candidate:
             continue
         if candidate['/Subtype'] == '/Image':
             pdfimage = candidate
             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
@@ -442,7 +482,7 @@ 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.
@@ -474,7 +514,9 @@ 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.
@@ -523,7 +565,7 @@ def _process_content_streams(*, pdf, container, shorthand=None):
     yield from _find_form_xobject_images(pdf, container, contentsinfo)
 
 
-def _page_has_text(text_blocks, page_width, page_height):
+def _page_has_text(text_blocks, page_width, page_height) -> bool:
     """Smarter text detection that ignores text in margins"""
 
     pw, ph = float(page_width), float(page_height)
@@ -536,7 +578,7 @@ def _page_has_text(text_blocks, page_width, page_height):
         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
@@ -552,7 +594,7 @@ def _page_has_text(text_blocks, page_width, page_height):
     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.
@@ -566,96 +608,51 @@ 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
-):
-    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
 
 
-def _pdf_pageinfo_sync_init(infile):
+def _pdf_pageinfo_sync_init(pdf: Pdf, infile: Path, pdfminer_loglevel):
     global worker_pdf  # pylint: disable=global-statement
-    worker_pdf = pikepdf.open(infile)
+    pikepdf_enable_mmap()
+
+    logging.getLogger('pdfminer').setLevel(pdfminer_loglevel)
+
+    # If the pdf is not opened, open a copy for our worker process to use
+    if pdf is None:
+        worker_pdf = Pdf.open(infile)
+
+        def on_process_close():
+            worker_pdf.close()
+
+        # Close when this process exits
+        atexit.register(on_process_close)
 
 
 def _pdf_pageinfo_sync(args):
-    global worker_pdf  # pylint: disable=global-statement
-    pageno, infile, check_pages, detailed_analysis = args
-    page = PageInfo(worker_pdf, pageno, infile, check_pages, detailed_analysis)
-    return page
+    pageno, thread_pdf, infile, check_pages, detailed_analysis = args
+    pdf = thread_pdf if thread_pdf is not None else worker_pdf
+    with ExitStack() as stack:
+        if not pdf:  # When called with SerialExecutor
+            pdf = stack.enter_context(Pdf.open(infile))
+        page = PageInfo(pdf, pageno, infile, check_pages, detailed_analysis)
+        return page
 
 
 def _pdf_pageinfo_concurrent(
-    pdf, infile, progbar, max_workers, check_pages, detailed_analysis=False
+    pdf,
+    executor: Executor,
+    infile,
+    progbar,
+    max_workers,
+    check_pages,
+    detailed_analysis=False,
 ):
     pages = [None] * len(pdf.pages)
 
     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()
 
@@ -663,7 +660,6 @@ def _pdf_pageinfo_concurrent(
         max_workers = available_cpu_count()
 
     total = len(pdf.pages)
-    contexts = ((n, infile, check_pages, detailed_analysis) for n in range(total))
 
     use_threads = False  # No performance gain if threaded due to GIL
     n_workers = min(1 + len(pages) // 4, max_workers)
@@ -672,13 +668,27 @@ def _pdf_pageinfo_concurrent(
         # a separate process.
         use_threads = True
 
-    exec_progress_pool(
+    # If we use a thread, we can pass the already-open Pdf for them to use
+    # If we use processes, we pass a None which tells the init function to open its
+    # own
+    initial_pdf = pdf if use_threads else None
+
+    contexts = (
+        (n, initial_pdf, infile, check_pages, detailed_analysis) for n in range(total)
+    )
+    assert n_workers == 1 if use_threads else n_workers >= 1, "Not multithreadable"
+    executor(
         use_threads=use_threads,
         max_workers=n_workers,
         tqdm_kwargs=dict(
             total=total, desc="Scanning contents", unit='page', disable=not progbar
         ),
-        task_initializer=partial(_pdf_pageinfo_sync_init, infile),
+        worker_initializer=partial(
+            _pdf_pageinfo_sync_init,
+            initial_pdf,
+            infile,
+            logging.getLogger('pdfminer').level,
+        ),
         task=_pdf_pageinfo_sync,
         task_arguments=contexts,
         task_finished=update_pageinfo,
@@ -687,64 +697,144 @@ def _pdf_pageinfo_concurrent(
 
 
 class PageInfo:
-    def __init__(self, pdf, pageno, infile, check_pages, detailed_analysis=False):
+    _has_text: Optional[bool]
+    _has_vector: Optional[bool]
+    _images: List[ImageInfo]
+
+    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 = []
+
+        self._dpi = None
+        if self._images:
+            dpi = Resolution(0.0, 0.0).take_max(
+                image.dpi for image in self._images if image.renderable
+            )
+            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):
+    def pageno(self) -> int:
         return self._pageno
 
     @property
-    def has_text(self):
-        return self._pageinfo['has_text']
+    def has_text(self) -> bool:
+        return bool(self._has_text)
 
     @property
-    def has_corrupt_text(self):
+    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):
-        return self._pageinfo['has_vector']
+    def has_vector(self) -> bool:
+        return bool(self._has_vector)
 
     @property
-    def width_inches(self):
-        return self._pageinfo['width_inches']
+    def width_inches(self) -> Decimal:
+        return self._width_inches
 
     @property
-    def height_inches(self):
-        return self._pageinfo['height_inches']
+    def height_inches(self) -> Decimal:
+        return self._height_inches
 
     @property
-    def width_pixels(self):
+    def width_pixels(self) -> int:
         return int(round(float(self.width_inches) * self.dpi.x))
 
     @property
-    def height_pixels(self):
+    def height_pixels(self) -> int:
         return int(round(float(self.height_inches) * self.dpi.y))
 
     @property
-    def rotation(self):
-        return self._pageinfo.get('rotate', None)
+    def rotation(self) -> int:
+        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=None, corrupt=None):
+    def get_textareas(
+        self, visible: Optional[bool] = None, corrupt: Optional[bool] = None
+    ):
         def predicate(obj, want_visible, want_corrupt):
             result = True
             if want_visible is not None:
@@ -755,27 +845,25 @@ 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):
-        return self._pageinfo.get('dpi', Resolution(0.0, 0.0))
+    def dpi(self) -> Resolution:
+        if self._dpi is None:
+            return Resolution(0.0, 0.0)
+        return self._dpi
 
     @property
-    def userunit(self):
-        return self._pageinfo.get('userunit', None)
+    def userunit(self) -> Decimal:
+        return self._userunit
 
     @property
-    def min_version(self):
+    def min_version(self) -> str:
         if self.userunit is not None:
             return '1.6'
         else:
@@ -789,38 +877,44 @@ class PageInfo:
         )
 
 
+DEFAULT_EXECUTOR = SerialExecutor()
+
+
 class PdfInfo:
     """Get summary information about a PDF"""
 
     def __init__(
         self,
         infile,
-        detailed_analysis=False,
-        progbar=False,
-        max_workers=None,
+        *,
+        detailed_analysis: bool = False,
+        progbar: bool = False,
+        max_workers: int = None,
         check_pages=None,
+        executor: Executor = DEFAULT_EXECUTOR,
     ):
         self._infile = infile
         if check_pages is None:
             check_pages = range(0, 1_000_000_000)
 
-        with pikepdf.open(infile) as pdf:
+        with Pdf.open(infile) as pdf:
             if pdf.is_encrypted:
                 raise EncryptedPdfError()  # Triggered by encryption with empty passwd
             self._pages = _pdf_pageinfo_concurrent(
                 pdf,
+                executor,
                 infile,
                 progbar,
                 max_workers,
                 check_pages=check_pages,
                 detailed_analysis=detailed_analysis,
             )
-            self._needs_rendering = pdf.root.get('/NeedsRendering', False)
+            self._needs_rendering = pdf.Root.get('/NeedsRendering', False)
             self._has_acroform = False
-            if '/AcroForm' in pdf.root:
-                if len(pdf.root.AcroForm.get('/Fields', [])) > 0:
+            if '/AcroForm' in pdf.Root:
+                if len(pdf.Root.AcroForm.get('/Fields', [])) > 0:
                     self._has_acroform = True
-                elif '/XFA' in pdf.root.AcroForm:
+                elif '/XFA' in pdf.Root.AcroForm:
                     self._has_acroform = True
 
     @property
@@ -828,29 +922,29 @@ class PdfInfo:
         return self._pages
 
     @property
-    def min_version(self):
+    def min_version(self) -> str:
         # The minimum PDF is the maximum version that any particular page needs
         return max(page.min_version for page in self.pages)
 
     @property
-    def has_userunit(self):
+    def has_userunit(self) -> bool:
         return any(page.userunit != 1.0 for page in self.pages)
 
     @property
-    def has_acroform(self):
+    def has_acroform(self) -> bool:
         return self._has_acroform
 
     @property
-    def filename(self):
+    def filename(self) -> Union[str, Path]:
         if not isinstance(self._infile, (str, Path)):
             raise NotImplementedError("can't get filename from stream")
         return self._infile
 
     @property
-    def needs_rendering(self):
+    def needs_rendering(self) -> bool:
         return self._needs_rendering
 
-    def __getitem__(self, item):
+    def __getitem__(self, item) -> PageInfo:
         return self._pages[item]
 
     def __len__(self):

src/ocrmypdf/pdfinfo/layout.py

@@ -1,19 +1,9 @@
 # © 2018 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
 
 import re
 from math import copysign
@@ -31,7 +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]+')
 
@@ -145,7 +135,7 @@ class LTStateAwareChar(LTChar):
         return self._text
 
     def __repr__(self):
-        return '<%s %s matrix=%s rendermode=%r font=%r adv=%s text=%r>' % (
+        return '<{} {} matrix={} rendermode={!r} font={!r} adv={} text={!r}>'.format(
             self.__class__.__name__,
             bbox2str(self.bbox),
             matrix2str(self.matrix),
@@ -220,11 +210,20 @@ class TextPositionTracker(PDFLayoutAnalyzer):
 
 def get_page_analysis(infile, pageno, pscript5_mode):
     rman = pdfminer.pdfinterp.PDFResourceManager(caching=True)
+    if pdfminer.__version__ < '20200402':
+        # Workaround for https://github.com/pdfminer/pdfminer.six/issues/395
+        disable_boxes_flow = 2
+    else:
+        disable_boxes_flow = None
     dev = TextPositionTracker(
-        rman, laparams=LAParams(all_texts=True, detect_vertical=True)
+        rman,
+        laparams=LAParams(
+            all_texts=True, detect_vertical=True, boxes_flow=disable_boxes_flow
+        ),
     )
     interp = pdfminer.pdfinterp.PDFPageInterpreter(rman, dev)
 
+    patcher = None
     if pscript5_mode:
         patcher = patch.multiple(
             'pdfminer.pdffont.PDFType3Font',
@@ -237,12 +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()

src/ocrmypdf/pluginspec.py

@@ -1,40 +1,48 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
-from abc import ABC, abstractmethod, abstractstaticmethod
+
+from abc import ABC, abstractmethod
 from argparse import ArgumentParser, Namespace
 from collections import namedtuple
+from logging import Handler
 from pathlib import Path
 from typing import TYPE_CHECKING, AbstractSet, List, Optional
 
 import pluggy
-from PIL import Image
 
+from ocrmypdf._concurrent import Executor
 from ocrmypdf.helpers import Resolution
 
 if TYPE_CHECKING:
+    from PIL import Image
+
+    # pylint: disable=ungrouped-imports
     from ocrmypdf._jobcontext import PageContext
     from ocrmypdf.pdfinfo import PdfInfo
 
+    # pylint: enable=ungrouped-imports
+
 hookspec = pluggy.HookspecMarker('ocrmypdf')
 
 # pylint: disable=unused-argument
 
 
+@hookspec(firstresult=True)
+def get_logging_console() -> Handler:
+    """Returns a custom logging handler.
+
+    Generally this is necessary when both logging output and a progress bar are both
+    outputting to ``sys.stderr``.
+
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
+    """
+
+
 @hookspec
 def add_options(parser: ArgumentParser) -> None:
     """Allows the plugin to add its own command line and API arguments.
@@ -68,7 +76,68 @@ def check_options(options: Namespace) -> None:
     Note:
         This hook will be called from the main process, and may modify global state
         before child worker processes are forked.
-	"""
+    """
+
+
+@hookspec(firstresult=True)
+def get_executor(progressbar_class) -> Executor:
+    """Called to obtain an object that manages parallel execution.
+
+    This may be used to replace OCRmyPDF's default parallel execution system
+    with a third party alternative. For example, you could make OCRmyPDF run in a
+    distributed environment.
+
+    OCRmyPDF's executors are analogous to the standard Python executors in
+    ``conconcurrent.futures``, but they do not work the same way. Executors may
+    be reused for different, unrelated batch operations, since all of the context
+    for a given job are passed to :meth:`Executor.__call__`.
+
+    Should be of type :class:`Executor` or otherwise conforming to the protocol
+    of that call.
+
+    Arguments:
+        progressbar_class: A progress bar class, which will be created when
+
+    Note:
+        This hook will be called from the main process, and may modify global state
+        before child worker processes are forked.
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
+    """
+
+
+@hookspec(firstresult=True)
+def get_progressbar_class():
+    """Called to obtain a class that can be used to monitor progress.
+
+    A progress bar is assumed, but this could be used for any type of monitoring.
+
+    The class should follow a tqdm-like protocol. Calling the class should return
+    a new progress bar object, which is activated with ``__enter__`` and terminated
+    ``__exit__``. An update method is called whenever the progress bar is updated.
+    Progress bar objects will not be reused; a new one will be created for each
+    group of tasks.
+
+    The progress bar is held in the main process/thread and not updated by child
+    process/threads. When a child notifies the parent of completed work, the
+    parent updates the progress bar.
+
+    The arguments are the same as `tqdm <https://github.com/tqdm/tqdm>`_ accepts.
+
+    Progress bars should never write to ``sys.stdout``, or they will corrupt the
+    output if OCRmyPDF writes a PDF to standard output.
+
+    The type of events that OCRmyPDF reports to a progress bar may change in
+    minor releases.
+
+    Here is how OCRmyPDF will use the progress bar:
+
+    Example:
+        pbar_class = pm.hook.get_progressbar_class()
+        with pbar_class(**tqdm_kwargs) as pbar:
+            ...
+            pbar.update(1)
+    """
 
 
 @hookspec
@@ -98,9 +167,9 @@ def rasterize_pdf_page(
     raster_device: str,
     raster_dpi: Resolution,
     pageno: int,
-    page_dpi: Optional[Resolution] = None,
-    rotation: Optional[int] = None,
-    filter_vector: bool = False,
+    page_dpi: Optional[Resolution],
+    rotation: Optional[int],
+    filter_vector: bool,
 ) -> Path:
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units.
 
@@ -118,23 +187,39 @@ def rasterize_pdf_page(
         rotation: Cardinal angle, clockwise, to rotate page
         filter_vector: If True, remove vector graphics objects
     Returns:
-        output_file
+        Path: output_file if successful
     Note:
         This hook will be called from child processes. Modifying global state
         will not affect the main process or other child processes.
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
     """
 
 
 @hookspec(firstresult=True)
-def filter_ocr_image(page: 'PageContext', image: Image) -> Image:
+def filter_ocr_image(page: 'PageContext', image: 'Image.Image') -> 'Image.Image':
     """Called to filter the image before it is sent to OCR.
 
     This is the image that OCR sees, not what the user sees when they view the
-    PDF.
+    PDF. If ``redo_ocr`` is enabled, portions of the image will be masked so
+    they are not shown to OCR. The main use of this hook is expected to be hiding
+    content from OCR.
+
+    The input image may be color, grayscale, or monochrome, and the
+    output image may differ. The pixel width and height of the
+    output image must be identical to the input image, or misalignment between
+    the OCR text layer and visual position of the text will occur. Likewise,
+    the output must be a faithful representation of the input, or alignment
+    errors may occurs.
+
+    Tesseract OCR only deals with monochrome images, and internally converts
+    non-monochrome images to OCR.
 
     Note:
         This hook will be called from child processes. Modifying global state
         will not affect the main process or other child processes.
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
     """
 
 
@@ -147,51 +232,147 @@ def filter_page_image(page: 'PageContext', image_filename: Path) -> Path:
     produced for a given page, this function will not be called. This is not
     the image that will be shown to OCR.
 
-    ocrmypdf will create the PDF page based on the image format used. If you
-    convert the image to a JPEG, the output page will be created as a JPEG, etc.
-    Note that the ocrmypdf image optimization stage may ultimately chose a
-    different format.
+    If the function does not want to modify the image, it should return
+    ``image_filename``. The hook may overwrite ``image_filename`` with a new file.
+
+    The output image should preserve the same physical unit dimensions, that is
+    (width * dpi_x, height * dpi_y). That is, if the image is resized, the DPI
+    must be adjusted by the reciprocal. If this is not preserved, the PDF page
+    will be resized and the OCR layer misaligned. OCRmyPDF does not nothing
+    to enforce these constraints; it is up to the plugin to do sensible things.
+
+    OCRmyPDF will create the PDF page based on the image format used (unless the
+    hook is overriden). If you convert the image to a JPEG, the output page will
+    be created as a JPEG, etc. If you change the colorspace, that change will be
+    kept. Note that the OCRmyPDF image optimization stage, if enabled, may
+    ultimately chose a different format.
+
+    If the return value is a file that does not exist, ``FileNotFoundError``
+    will occur. The return value should be a path to a file in the same folder
+    as ``image_filename``.
+
+    Implementation detail: If the value returned is falsy, OCRmyPDF will ignore
+    the return value and assume the input file was unmodified. This is deprecated.
+    To leave the image unmodified, ``image_filename`` should be returned.
 
     Note:
         This hook will be called from child processes. Modifying global state
         will not affect the main process or other child processes.
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
+    """
+
+
+@hookspec(firstresult=True)
+def filter_pdf_page(
+    page: 'PageContext', image_filename: Path, output_pdf: Path
+) -> Path:
+    """Called to convert a filtered whole page image into a PDF.
+
+    A whole page image is only produced when preprocessing command line arguments
+    are issued or when ``--force-ocr`` is issued. If no whole page is image is
+    produced for a given page, this function will not be called. This is not
+    the image that will be shown to OCR. The whole page image is filtered in
+    the hook above, ``filter_page_image``, then this function is called for
+    PDF conversion.
+
+    This function will only be called when OCRmyPDF runs in a mode such as
+    "force OCR" mode where rasterizing of all content is performed.
+
+    Clever things could be done at this stage such as segmenting the page image into
+    color regions or vector equivalents.
+
+    The provider of the hook implementation is responsible for ensuring that the
+    OCR text layer is aligned with the PDF produced here, or text misalignment
+    will result.
+
+    Currently this function must produce a single page PDF or the pipeline will
+    fail.  If the intent is to remove the PDF, then create a single page empty
+    PDF.
+
+    Args:
+        page: Context for this page.
+        image_filename: Filename of the input image used to create output_pdf,
+            for "reference" if recreating the output_pdf entirely.
+        output_pdf: The previous created output_pdf.
+
+    Returns:
+        output_pdf
+
+    Note:
+        This hook will be called from child processes. Modifying global state
+        will not affect the main process or other child processes.
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
     """
 
 
 OrientationConfidence = namedtuple('OrientationConfidence', ('angle', 'confidence'))
+"""Expresses an OCR engine's confidence in page rotation.
+
+Attributes:
+    angle (int): The clockwise angle (0, 90, 180, 270) that the page should be
+        rotated. 0 means no rotation.
+    confidence (float): How confident the OCR engine is that this the correct
+        rotation. 0 is not confident, 15 is very confident. Arbitrary units.
+"""
 
 
 class OcrEngine(ABC):
-    @abstractstaticmethod
+    """A class representing an OCR engine with capabilities similar to Tesseract OCR.
+
+    This could be used to create a plugin for another OCR engine instead of
+    Tesseract OCR.
+    """
+
+    @staticmethod
+    @abstractmethod
     def version() -> str:
         """Returns the version of the OCR engine."""
 
-    @abstractstaticmethod
+    @staticmethod
+    @abstractmethod
     def creator_tag(options: Namespace) -> str:
-        """Returns the creator tag to identify this software's role in creating the PDF."""
+        """Returns the creator tag to identify this software's role in creating the PDF.
+
+        This tag will be inserted in the XMP metadata and DocumentInfo dictionary
+        as appropriate. Ideally you should include the name of the OCR engine and its
+        version. The text should not contain line breaks. This is to help developers
+        like yourself identify the software that produced this file.
+
+        OCRmyPDF will always prepend its name to this value.
+        """
 
     @abstractmethod
     def __str__(self):
-        """Returns name of OCR engine and version."""
+        """Returns name of OCR engine and version.
 
-    @abstractstaticmethod
+        This is used when OCRmyPDF wants to mention the name of the OCR engine
+        to the user, usually in an error message.
+        """
+
+    @staticmethod
+    @abstractmethod
     def languages(options: Namespace) -> AbstractSet[str]:
         """Returns the set of all languages that are supported by the engine.
 
         Languages are typically given in 3-letter ISO 3166-1 codes, but actually
         can be any value understood by the OCR engine."""
 
-    @abstractstaticmethod
+    @staticmethod
+    @abstractmethod
     def get_orientation(input_file: Path, options: Namespace) -> OrientationConfidence:
         """Returns the orientation of the image."""
 
-    @abstractstaticmethod
+    @staticmethod
+    @abstractmethod
     def generate_hocr(
         input_file: Path, output_hocr: Path, output_text: Path, options: Namespace
     ) -> None:
         """Called to produce a hOCR file and sidecar text file."""
 
-    @abstractstaticmethod
+    @staticmethod
+    @abstractmethod
     def generate_pdf(
         input_file: Path, output_pdf: Path, output_text: Path, options: Namespace
     ) -> None:
@@ -213,6 +394,9 @@ def get_ocr_engine() -> OcrEngine:
     The OcrEngine may be instantiated multiple times, by both the main process
     and child process. As such, it must be obtain store any state in ``options``
     or some common location.
+
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
     """
 
 
@@ -224,6 +408,7 @@ def generate_pdfa(
     compression: str,
     pdf_version: str,
     pdfa_part: str,
+    progressbar_class,
 ) -> Path:
     """Generate a PDF/A.
 
@@ -246,7 +431,21 @@ def generate_pdfa(
             At its own discretion, the PDF/A generator may raise the version,
             but should not lower it.
         pdfa_part: The desired PDF/A compliance level, such as ``'2B'``.
+        progressbar_class: The class of a progress bar with a tqdm-like API. An
+            instance of this class will be initialized when PDF/A conversion
+            begins, using
+            ``instance = progressbar_class(total: int, desc: str, unit:str)``,
+            defining the number of work units, a user-visible description,
+            and the name of the work units ("page"). Then ``instance.update()``
+            will be called when a work unit is completed. If ``None``, no
+            progress information is reported.
 
     Returns:
-        output_file: If successful, the hook should return ``output_file``.
+        Path: If successful, the hook should return ``output_file``.
+
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
+
+    See also:
+        https://github.com/tqdm/tqdm
     """

src/ocrmypdf/py.typed

@@ -0,0 +1 @@
+# ocrmypdf is typed

src/ocrmypdf/quality.py

@@ -1,37 +1,27 @@
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+"""Utilities to measure OCR quality"""
+
 
 import re
 from typing import Iterable
 
-"""Utilities to measure OCR quality"""
-
 
 class OcrQualityDictionary:
     """Manages a dictionary for simple OCR quality checks."""
 
-    def __init__(self, *, wordlist: Iterable[str] = []):
+    def __init__(self, *, wordlist: Iterable[str]):
         """Construct a dictionary from a list of words.
 
         Words for which capitalization is important should be capitalized in the
         dictionary. Words that contain spaces or other punctuation will never match.
         """
-        self.dictionary = set()
-        self.dictionary.update(w for w in wordlist)
+        self.dictionary = set(wordlist)
 
     def measure_words_matched(self, ocr_text: str) -> float:
         """Check how many unique words in the OCR text match a dictionary.

src/ocrmypdf/subprocess.py

@@ -1,298 +0,0 @@
-# © 2020 James R. Barlow: github.com/jbarlow83
-#
-# This file is part of OCRmyPDF.
-#
-# OCRmyPDF 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.
-#
-# OCRmyPDF 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 OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
-
-"""Wrappers to manage subprocess calls"""
-
-import logging
-import os
-import re
-import shutil
-import sys
-from collections.abc import Mapping
-from contextlib import suppress
-from distutils.version import LooseVersion
-from functools import lru_cache
-from pathlib import Path
-from subprocess import PIPE, STDOUT, CalledProcessError
-from subprocess import run as subprocess_run
-
-from ocrmypdf.exceptions import MissingDependencyError
-
-log = logging.getLogger(__name__)
-
-
-def run(args, *, env=None, **kwargs):
-    """Wrapper around subprocess.run()
-
-    The main purpose of this wrapper is to log subprocess output.
-
-    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 = args[0]
-
-    if os.name == 'nt':
-        args = _fix_windows_args(program, args, env)
-
-    log.debug("Running: %s", args)
-    process_log = log.getChild('subprocess.' + os.path.basename(program))
-    if sys.version_info < (3, 7) and os.name == 'nt':
-        # Can't use close_fds=True on Windows with Python 3.6 or older
-        # https://bugs.python.org/issue19575, etc.
-        kwargs['close_fds'] = False
-
-    stderr = None
-    try:
-        proc = subprocess_run(args, env=env, **kwargs)
-    except CalledProcessError as e:
-        stderr = getattr(e, 'stderr', None)
-        raise
-    else:
-        stderr = getattr(proc, 'stderr', None)
-    finally:
-        if process_log.isEnabledFor(logging.DEBUG) and stderr:
-            with suppress(AttributeError, UnicodeDecodeError):
-                stderr = stderr.decode('utf-8', 'replace')
-            process_log.debug("stderr = %s", stderr)
-    return proc
-
-
-def _fix_windows_args(program, args, env):
-    """Adjust our desired program and command line arguments for use on Windows"""
-
-    if sys.version_info < (3, 8):
-        # bpo-33617 - Windows needs manual Path -> str conversion
-        args = [os.fspath(arg) for arg in args]
-        program = os.fspath(program)
-
-    # If we are running a .py on Windows, ensure we call it with this Python
-    # (to support test suite shims)
-    if program.lower().endswith('.py'):
-        args = [sys.executable] + args
-
-    paths = os.pathsep.join(os.get_exec_path(env))
-    if not shutil.which(args[0], path=paths):
-        # If the program we want is not on the PATH, add some interesting
-        # locations in %PROGRAMFILES% to the PATH and try again
-        shimmed_path = shim_paths_with_program_files(env)
-        new_args0 = shutil.which(args[0], path=shimmed_path)
-        if new_args0:
-            args[0] = new_args0
-    return args
-
-
-@lru_cache(maxsize=None)
-def get_version(program, *, version_arg='--version', regex=r'(\d+(\.\d+)*)', env=None):
-    """Get the version of the specified program"""
-    args_prog = [program, version_arg]
-    try:
-        proc = run(
-            args_prog,
-            close_fds=True,
-            universal_newlines=True,
-            stdout=PIPE,
-            stderr=STDOUT,
-            check=True,
-            env=env,
-        )
-        output = proc.stdout
-    except FileNotFoundError as e:
-        raise MissingDependencyError(
-            f"Could not find program '{program}' on the PATH"
-        ) from e
-    except CalledProcessError as e:
-        if e.returncode != 0:
-            raise MissingDependencyError(
-                f"Ran program '{program}' but it exited with an error:\n{e.output}"
-            ) from e
-        raise MissingDependencyError(
-            f"Could not find program '{program}' on the PATH"
-        ) from e
-    try:
-        version = re.match(regex, output.strip()).group(1)
-    except AttributeError as e:
-        raise MissingDependencyError(
-            f"The program '{program}' did not report its version. "
-            f"Message was:\n{output}"
-        )
-
-    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', '')
-
-    def path_walker():
-        for path in Path(program_files).iterdir():
-            if not path.is_dir():
-                continue
-            if path.name.lower() == 'tesseract-ocr':
-                yield path
-            elif path.name.lower() == 'gs':
-                yield from (p for p in path.glob('**/bin') if p.is_dir())
-
-    paths = sorted(
-        (p for p in path_walker()), key=lambda p: (p.name, p.parent.name), reverse=True
-    )
-    paths.extend(
-        Path(str_path)
-        for str_path in os.get_exec_path(env)
-        if Path(str_path) not in set(paths)
-    )
-    return os.pathsep.join(str(p) for p in paths)
-
-
-missing_program = '''
-The program '{program}' could not be executed or was not found on your
-system PATH.
-'''
-
-missing_optional_program = '''
-The program '{program}' could not be executed or was not found on your
-system PATH.  This program is required when you use the
-{required_for} arguments.  You could try omitting these arguments, or install
-the package.
-'''
-
-missing_recommend_program = '''
-The program '{program}' could not be executed or was not found on your
-system PATH.  This program is recommended when using the {required_for} arguments,
-but not required, so we will proceed.  For best results, install the program.
-'''
-
-old_version = '''
-OCRmyPDF requires '{program}' {need_version} or higher.  Your system appears
-to have {found_version}.  Please update this program.
-'''
-
-old_version_required_for = '''
-OCRmyPDF requires '{program}' {need_version} or higher when run with the
-{required_for} arguments.  If you omit these arguments, OCRmyPDF may be able to
-proceed.  For best results, install the program.
-'''
-
-osx_install_advice = '''
-If you have homebrew installed, try these command to install the missing
-package:
-    brew install {package}
-'''
-
-linux_install_advice = '''
-On systems with the aptitude package manager (Debian, Ubuntu), try these
-commands:
-    sudo apt-get update
-    sudo apt-get install {package}
-
-On RPM-based systems (Red Hat, Fedora), search for instructions on
-installing the RPM for {program}.
-'''
-
-windows_install_advice = '''
-If not already installed, install the Chocolatey package manager. Then use
-a command prompt to install the missing package:
-    choco install {package}
-'''
-
-
-def _get_platform():
-    if sys.platform.startswith('freebsd'):
-        return 'freebsd'
-    elif sys.platform.startswith('linux'):
-        return 'linux'
-    elif sys.platform.startswith('win'):
-        return 'windows'
-    return sys.platform
-
-
-def _error_trailer(program, package, **kwargs):
-    if isinstance(package, Mapping):
-        package = package.get(_get_platform(), program)
-
-    if _get_platform() == 'darwin':
-        log.info(osx_install_advice.format(**locals()))
-    elif _get_platform() == 'linux':
-        log.info(linux_install_advice.format(**locals()))
-    elif _get_platform() == 'windows':
-        log.info(windows_install_advice.format(**locals()))
-
-
-def _error_missing_program(program, package, required_for, recommended):
-    if recommended:
-        log.warning(missing_recommend_program.format(**locals()))
-    elif required_for:
-        log.error(missing_optional_program.format(**locals()))
-    else:
-        log.error(missing_program.format(**locals()))
-    _error_trailer(**locals())
-
-
-def _error_old_version(program, package, need_version, found_version, required_for):
-    if required_for:
-        log.error(old_version_required_for.format(**locals()))
-    else:
-        log.error(old_version.format(**locals()))
-    _error_trailer(**locals())
-
-
-def check_external_program(
-    *,
-    program,
-    package,
-    version_checker,
-    need_version,
-    required_for=None,
-    recommended=False,
-):
-    try:
-        if callable(version_checker):
-            found_version = version_checker()
-        else:
-            found_version = version_checker
-    except (CalledProcessError, FileNotFoundError, MissingDependencyError):
-        _error_missing_program(program, package, required_for, recommended)
-        if not recommended:
-            raise MissingDependencyError()
-        return
-
-    def remove_leading_v(s):
-        if s.startswith('v'):
-            return s[1:]
-        return s
-
-    found_version = remove_leading_v(found_version)
-    need_version = remove_leading_v(need_version)
-
-    if found_version and LooseVersion(found_version) < LooseVersion(need_version):
-        _error_old_version(program, package, need_version, found_version, required_for)
-        if not recommended:
-            raise MissingDependencyError()
-
-    log.debug('Found %s %s', program, found_version)

src/ocrmypdf/subprocess/__init__.py

@@ -0,0 +1,323 @@
+# © 2020 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+"""Wrappers to manage subprocess calls"""
+
+import logging
+import os
+import re
+import sys
+from collections.abc import Mapping
+from contextlib import suppress
+from distutils.version import LooseVersion, Version
+from functools import lru_cache
+from subprocess import PIPE, STDOUT, CalledProcessError, CompletedProcess, Popen
+from subprocess import run as subprocess_run
+from typing import Callable, Optional, Type, Union
+
+from ocrmypdf.exceptions import MissingDependencyError
+
+# pylint: disable=logging-format-interpolation
+
+log = logging.getLogger(__name__)
+
+
+def run(
+    args, *, env=None, logs_errors_to_stdout: bool = False, **kwargs
+) -> CompletedProcess:
+    """Wrapper around :py:func:`subprocess.run`
+
+    The main purpose of this wrapper is to log subprocess output in an orderly
+    fashion that indentifies the responsible subprocess. An additional
+    task is that this function goes to greater lengths to find possible Windows
+    locations of our dependencies when they are not on the system PATH.
+
+    Arguments should be identical to ``subprocess.run``, except for following:
+
+    Arguments:
+        logs_errors_to_stdout: If True, indicates that the process writes its error
+            messages to stdout rather than stderr, so stdout should be logged
+            if there is an error. If False, stderr is logged. Could be used with
+            stderr=STDOUT, stdout=PIPE for example.
+    """
+    args, env, process_log, _text = _fix_process_args(args, env, kwargs)
+
+    stderr = None
+    stderr_name = 'stderr' if not logs_errors_to_stdout else 'stdout'
+    try:
+        proc = subprocess_run(args, env=env, **kwargs)
+    except CalledProcessError as e:
+        stderr = getattr(e, stderr_name, None)
+        raise
+    else:
+        stderr = getattr(proc, stderr_name, None)
+    finally:
+        if process_log.isEnabledFor(logging.DEBUG) and stderr:
+            with suppress(AttributeError, UnicodeDecodeError):
+                stderr = stderr.decode('utf-8', 'replace')
+            if logs_errors_to_stdout:
+                process_log.debug("stdout/stderr = %s", stderr)
+            else:
+                process_log.debug("stderr = %s", stderr)
+    return proc
+
+
+def run_polling_stderr(
+    args, *, callback: Callable[[str], None], check: bool = False, env=None, **kwargs
+) -> CompletedProcess:
+    """Run a process like ``ocrmypdf.subprocess.run``, and poll stderr.
+
+    Every line of produced by stderr will be forwarded to the callback function.
+    The intended use is monitoring progress of subprocesses that output their
+    own progress indicators. In addition, each line will be logged if debug
+    logging is enabled.
+
+    Requires stderr to be opened in text mode for ease of handling errors. In
+    addition the expected encoding= and errors= arguments should be set. Note
+    that if stdout is already set up, it need not be binary.
+    """
+    args, env, process_log, text = _fix_process_args(args, env, kwargs)
+    assert text, "Must use text=True"
+
+    with Popen(args, env=env, **kwargs) as proc:
+        lines = []
+        while proc.poll() is None:
+            if proc.stderr is None:
+                continue
+            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)
+
+        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):
+    assert 'universal_newlines' not in kwargs, "Use text= instead of universal_newlines"
+
+    if not env:
+        env = os.environ
+
+    # Search in spoof path if necessary
+    program = str(args[0])
+
+    if os.name == 'nt':
+        from ocrmypdf.subprocess._windows import fix_windows_args
+
+        args = fix_windows_args(program, args, env)
+
+    log.debug("Running: %s", args)
+    process_log = log.getChild(os.path.basename(program))
+    text = kwargs.get('text', False)
+    if sys.version_info < (3, 7):
+        if os.name == 'nt':
+            # Can't use close_fds=True on Windows with Python 3.6 or older
+            # https://bugs.python.org/issue19575, etc.
+            kwargs['close_fds'] = False
+        if 'text' in kwargs:
+            # Convert run(...text=) to run(...universal_newlines=) for Python 3.6
+            kwargs['universal_newlines'] = kwargs['text']
+            del kwargs['text']
+    return args, env, process_log, text
+
+
+@lru_cache(maxsize=None)
+def get_version(
+    program: str, *, version_arg: str = '--version', regex=r'(\d+(\.\d+)*)', env=None
+):
+    """Get the version of the specified program
+
+    Arguments:
+        program: The program to version check.
+        version_arg: The argument needed to ask for its version, e.g. ``--version``.
+        regex: A regular expression to parse the program's output and obtain the
+            version.
+        env: Custom ``os.environ`` in which to run program.
+    """
+    args_prog = [program, version_arg]
+    try:
+        proc = run(
+            args_prog,
+            close_fds=True,
+            text=True,
+            stdout=PIPE,
+            stderr=STDOUT,
+            check=True,
+            env=env,
+        )
+        output = proc.stdout
+    except FileNotFoundError as e:
+        raise MissingDependencyError(
+            f"Could not find program '{program}' on the PATH"
+        ) from e
+    except CalledProcessError as e:
+        if e.returncode != 0:
+            raise MissingDependencyError(
+                f"Ran program '{program}' but it exited with an error:\n{e.output}"
+            ) from e
+        raise MissingDependencyError(
+            f"Could not find program '{program}' on the PATH"
+        ) from e
+
+    match = re.match(regex, output.strip())
+    if not match:
+        raise MissingDependencyError(
+            f"The program '{program}' did not report its version. "
+            f"Message was:\n{output}"
+        )
+    version = match.group(1)
+
+    return version
+
+
+missing_program = '''
+The program '{program}' could not be executed or was not found on your
+system PATH.
+'''
+
+missing_optional_program = '''
+The program '{program}' could not be executed or was not found on your
+system PATH.  This program is required when you use the
+{required_for} arguments.  You could try omitting these arguments, or install
+the package.
+'''
+
+missing_recommend_program = '''
+The program '{program}' could not be executed or was not found on your
+system PATH.  This program is recommended when using the {required_for} arguments,
+but not required, so we will proceed.  For best results, install the program.
+'''
+
+old_version = '''
+OCRmyPDF requires '{program}' {need_version} or higher.  Your system appears
+to have {found_version}.  Please update this program.
+'''
+
+old_version_required_for = '''
+OCRmyPDF requires '{program}' {need_version} or higher when run with the
+{required_for} arguments.  If you omit these arguments, OCRmyPDF may be able to
+proceed.  For best results, install the program.
+'''
+
+osx_install_advice = '''
+If you have homebrew installed, try these command to install the missing
+package:
+    brew install {package}
+'''
+
+linux_install_advice = '''
+On systems with the aptitude package manager (Debian, Ubuntu), try these
+commands:
+    sudo apt-get update
+    sudo apt-get install {package}
+
+On RPM-based systems (Red Hat, Fedora), search for instructions on
+installing the RPM for {program}.
+'''
+
+windows_install_advice = '''
+If not already installed, install the Chocolatey package manager. Then use
+a command prompt to install the missing package:
+    choco install {package}
+'''
+
+
+def _get_platform():
+    if sys.platform.startswith('freebsd'):
+        return 'freebsd'
+    elif sys.platform.startswith('linux'):
+        return 'linux'
+    elif sys.platform.startswith('win'):
+        return 'windows'
+    return sys.platform
+
+
+def _error_trailer(program, package, **kwargs):
+    if isinstance(package, Mapping):
+        package = package.get(_get_platform(), program)
+
+    if _get_platform() == 'darwin':
+        log.info(osx_install_advice.format(**locals()))
+    elif _get_platform() == 'linux':
+        log.info(linux_install_advice.format(**locals()))
+    elif _get_platform() == 'windows':
+        log.info(windows_install_advice.format(**locals()))
+
+
+def _error_missing_program(program, package, required_for, recommended):
+    if recommended:
+        log.warning(missing_recommend_program.format(**locals()))
+    elif required_for:
+        log.error(missing_optional_program.format(**locals()))
+    else:
+        log.error(missing_program.format(**locals()))
+    _error_trailer(**locals())
+
+
+def _error_old_version(program, package, need_version, found_version, required_for):
+    if required_for:
+        log.error(old_version_required_for.format(**locals()))
+    else:
+        log.error(old_version.format(**locals()))
+    _error_trailer(**locals())
+
+
+def check_external_program(
+    *,
+    program: str,
+    package: str,
+    version_checker: Union[str, Callable],
+    need_version: str,
+    required_for: Optional[str] = None,
+    recommended=False,
+    version_parser: Type[Version] = LooseVersion,
+):
+    """Check for required version of external program and raise exception if not.
+
+    Args:
+        program: The name of the program to test.
+        package: The name of a software package that typically supplies this program.
+            Usually the same as program.
+        version_check: A callable without arguments that retrieves the installed
+            version of program.
+        need_version: The minimum required version.
+        required_for: The name of an argument of feature that requires this program.
+        recommended: If this external program is recommended, instead of raising
+            an exception, log a warning and allow execution to continue.
+        version_parser: A class that should be used to parse and compare version
+            numbers. Used when version numbers do not follow standard conventions.
+    """
+
+    try:
+        if callable(version_checker):
+            found_version = version_checker()
+        else:
+            found_version = version_checker
+    except (CalledProcessError, FileNotFoundError, MissingDependencyError):
+        _error_missing_program(program, package, required_for, recommended)
+        if not recommended:
+            raise MissingDependencyError(program)
+        return
+
+    def remove_leading_v(s):
+        if s.startswith('v'):
+            return s[1:]
+        return s
+
+    found_version = remove_leading_v(found_version)
+    need_version = remove_leading_v(need_version)
+
+    if found_version and version_parser(found_version) < version_parser(need_version):
+        _error_old_version(program, package, need_version, found_version, required_for)
+        if not recommended:
+            raise MissingDependencyError(program)
+
+    log.debug('Found %s %s', program, found_version)

src/ocrmypdf/subprocess/_windows.py

@@ -0,0 +1,160 @@
+# © 2020 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+import logging
+import os
+import shutil
+import sys
+from distutils.version import LooseVersion
+from itertools import chain
+from pathlib import Path
+from typing import Any, Callable, Iterable, Iterator, Set, Tuple, TypeVar
+
+try:
+    import winreg
+except ModuleNotFoundError as e:
+    raise ModuleNotFoundError("This module is for Windows only") from e
+
+log = logging.getLogger(__name__)
+
+T = TypeVar('T')
+
+
+def registry_enum(
+    key: winreg.HKEYType, enum_fn: Callable[[winreg.HKEYType, int], T]
+) -> Iterator[T]:
+    LIMIT = 999
+    n = 0
+    while n < LIMIT:
+        try:
+            yield enum_fn(key, n)
+            n += 1
+        except OSError:
+            break
+    if n == LIMIT:
+        raise ValueError(f"Too many registry keys under {key}")
+
+
+def registry_subkeys(key: winreg.HKEYType) -> Iterator[str]:
+    return registry_enum(key, winreg.EnumKey)
+
+
+def registry_values(key: winreg.HKEYType) -> Iterator[Tuple[str, Any, int]]:
+    return registry_enum(key, winreg.EnumValue)
+
+
+def registry_path_ghostscript(env=None) -> Iterator[Path]:
+    try:
+        with winreg.OpenKey(
+            winreg.HKEY_LOCAL_MACHINE, r"SOFTWARE\Artifex\GPL Ghostscript"
+        ) as k:
+            latest_gs = max(registry_subkeys(k), key=LooseVersion)
+        with winreg.OpenKey(
+            winreg.HKEY_LOCAL_MACHINE, fr"SOFTWARE\Artifex\GPL Ghostscript\{latest_gs}"
+        ) as k:
+            _, gs_path, _ = next(registry_values(k))
+            yield Path(gs_path) / 'bin'
+    except OSError as e:
+        log.warning(e)
+
+
+def registry_path_tesseract(env=None) -> Iterator[Path]:
+    try:
+        with winreg.OpenKey(winreg.HKEY_LOCAL_MACHINE, r"SOFTWARE\Tesseract-OCR") as k:
+            for subkey, val, _valtype in registry_values(k):
+                if subkey == 'InstallDir':
+                    tesseract_path = Path(val)
+                    yield tesseract_path
+    except OSError as e:
+        log.warning(e)
+
+
+def program_files_paths(env=None) -> Iterator[Path]:
+    if not env:
+        env = os.environ
+    program_files = env.get('PROGRAMFILES', '')
+
+    def path_walker() -> Iterator[Path]:
+        for path in Path(program_files).iterdir():
+            if not path.is_dir():
+                continue
+            if path.name.lower() == 'tesseract-ocr':
+                yield path
+            elif path.name.lower() == 'gs':
+                yield from (p for p in path.glob('**/bin') if p.is_dir())
+
+    return iter(
+        sorted(
+            (p for p in path_walker()),
+            key=lambda p: (p.name, p.parent.name),
+            reverse=True,
+        )
+    )
+
+
+def paths_from_env(env=None) -> Iterator[Path]:
+    return (Path(p) for p in os.get_exec_path(env) if p)
+
+
+def shim_path(new_paths: Callable[[Any], Iterator[Path]], env=None) -> str:
+    if not env:
+        env = os.environ
+    return os.pathsep.join(str(p) for p in new_paths(env) if p)
+
+
+SHIMS = [
+    paths_from_env,
+    registry_path_ghostscript,
+    registry_path_tesseract,
+    program_files_paths,
+]
+
+
+def fix_windows_args(program: str, args, env):
+    """Adjust our desired program and command line arguments for use on Windows"""
+
+    if sys.version_info < (3, 8):
+        # bpo-33617 - Windows needs manual Path -> str conversion
+        args = [os.fspath(arg) for arg in args]
+        program = os.fspath(program)
+
+    # If we are running a .py on Windows, ensure we call it with this Python
+    # (to support test suite shims)
+    if program.lower().endswith('.py'):
+        args = [sys.executable] + args
+
+    # If the program we want is not on the PATH, check elsewhere
+    for shim in SHIMS:
+        shimmed_path = shim_path(shim, env)
+        new_args0 = shutil.which(args[0], path=shimmed_path)
+        if new_args0:
+            args[0] = new_args0
+            break
+
+    return args
+
+
+def unique_everseen(iterable: Iterable[T], key: Callable[[T], T]) -> Iterator[T]:
+    "List unique elements, preserving order."
+    # unique_everseen('AAAABBBCCDAABBB') --> A B C D
+    # unique_everseen('ABBCcAD', str.lower) --> A B C D
+    seen: Set[T] = set()
+    seen_add = seen.add
+    for element in iterable:
+        k = key(element)
+        if k not in seen:
+            seen_add(k)
+            yield element
+
+
+def shim_env_path(env=None):
+    if env is None:
+        env = os.environ
+
+    shim_paths = chain.from_iterable(shim(env) for shim in SHIMS)
+    return os.pathsep.join(
+        str(p) for p in unique_everseen(shim_paths, key=lambda p: str.casefold(str(p)))
+    )

tests/__init__.py

@@ -0,0 +1,7 @@
+# © 2021 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+# Empty __init__.py file