Add documentation to PdfMinerState

Fixes #1396

.docker/Dockerfile

@@ -1,7 +1,7 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-FileCopyrightText: 2024 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-FROM ubuntu:22.04 as base
+FROM ubuntu:24.04 AS base
 
 ENV LANG=C.UTF-8
 ENV TZ=UTC
@@ -9,19 +9,15 @@ RUN echo 'debconf debconf/frontend select Noninteractive' | debconf-set-selectio
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
   python3 \
-  libqpdf-dev \
+  python-is-python3
-  zlib1g \
-  liblept5
 
-FROM base as builder
+FROM base AS builder
 
 # Note we need leptonica here to build jbig2
 RUN apt-get update && apt-get install -y --no-install-recommends \
   build-essential autoconf automake libtool \
   libleptonica-dev \
   zlib1g-dev \
-  python3-dev \
-  python3-distutils \
   libffi-dev \
   ca-certificates \
   curl \
@@ -29,15 +25,11 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
   libcairo2-dev \
   pkg-config
 
-# Get the latest pip (Ubuntu version doesn't support manylinux2010)
-RUN \
-  curl https://bootstrap.pypa.io/get-pip.py | python3
-
 # Compile and install jbig2
 # Needs libleptonica-dev, zlib1g-dev
 RUN \
   mkdir jbig2 \
-  && curl -L https://github.com/agl/jbig2enc/archive/ea6a40a.tar.gz | \
+  && curl -L https://github.com/agl/jbig2enc/archive/c0141bf.tar.gz | \
   tar xz -C jbig2 --strip-components=1 \
   && cd jbig2 \
   && ./autogen.sh && ./configure && make && make install \
@@ -48,23 +40,24 @@ COPY . /app
 
 WORKDIR /app
 
-RUN pip3 install --no-cache-dir .[test,webservice,watcher]
+RUN curl -LsSf https://astral.sh/uv/0.4.27/install.sh | sh
+
+ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy
+
+# Instead of restarting the shell, use uv directly from its installed location.
+RUN /root/.cargo/bin/uv sync --extra test --extra webservice --extra watcher
 
 FROM base
 
-# For Tesseract 5
+RUN apt-get update && apt-get install -y software-properties-common
-RUN apt-get update && apt-get install -y --no-install-recommends \
+
-  software-properties-common gpg-agent
 RUN add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
   ghostscript \
   fonts-droid-fallback \
   jbig2dec \
-  img2pdf \
-  libsm6 libxext6 libxrender-dev \
   pngquant \
-  python-is-python3 \
   tesseract-ocr \
   tesseract-ocr-chi-sim \
   tesseract-ocr-deu \
@@ -80,11 +73,9 @@ WORKDIR /app
 COPY --from=builder /usr/local/lib/ /usr/local/lib/
 COPY --from=builder /usr/local/bin/ /usr/local/bin/
 
-COPY --from=builder /app/misc/webservice.py /app/
+COPY --from=builder --chown=app:app /app /app
-COPY --from=builder /app/misc/watcher.py /app/
 
-# Copy minimal project files to get the test suite.
+ENV PATH="/app/.venv/bin:${PATH}"
-COPY --from=builder /app/pyproject.toml /app/README.md /app/
+
-COPY --from=builder /app/tests /app/tests
+ENTRYPOINT ["/app/.venv/bin/ocrmypdf"]
 
-ENTRYPOINT ["/usr/local/bin/ocrmypdf"]

.docker/Dockerfile.alpine

@@ -1,7 +1,14 @@
 # SPDX-FileCopyrightText: 2023 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-FROM alpine:3.19 as base
+# Note: Alpine 3.20 builds tesseract with --enable-opencl, which is not
+# supported by anyone. OCRmyPDF is not compatible with Alpine 3.20.0
+# through 3.20.3. The Alpine issue should be fixed in 3.21.0. It is
+# not clear if 3.20.4+ will have the fix.
+# Details
+#  https://gitlab.alpinelinux.org/alpine/aports/-/issues/16143
+#  https://github.com/ocrmypdf/OCRmyPDF/issues/1395
+FROM alpine:3.19 AS base
 
 ENV LANG=C.UTF-8
 ENV TZ=UTC
@@ -10,40 +17,24 @@ RUN apk add --no-cache \
     python3 \
     zlib
 
-FROM base as builder
+FROM base AS builder
 
 RUN apk add --no-cache \
     ca-certificates \
     git \
     python3-dev \
-    py3-pip
+    curl
-
-# On arm64, we need to build cffi from source.
-ARG TARGETPLATFORM
-
-RUN if [ "${TARGETPLATFORM}" == "linux/arm64" ]; then \
-    apk add --no-cache \
-    build-base \
-    autoconf \
-    automake \
-    libtool \
-    zlib-dev \
-    libffi-dev \
-    cairo-dev \
-    pkgconfig \
-    ;  \
-    fi
 
 COPY . /app
 
 WORKDIR /app
 
-RUN python3 -m venv .venv
+RUN curl -LsSf https://astral.sh/uv/0.4.27/install.sh | sh
 
-RUN source .venv/bin/activate \
+ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy
-    && python3 -m pip install --no-cache-dir --upgrade pip \
+
-    && python3 -m pip install --no-cache-dir wheel \
+# Instead of restarting the shell, use uv directly from its installed location.
-    && python3 -m pip install --no-cache-dir .[test,webservice,watcher]
+RUN /root/.cargo/bin/uv sync --extra test --extra webservice --extra watcher
 
 FROM base
 
@@ -66,17 +57,7 @@ RUN apk add --no-cache \
 
 WORKDIR /app
 
-COPY --from=builder /usr/local/lib/ /usr/local/lib/
+COPY --from=builder --chown=app:app /app /app
-COPY --from=builder /usr/local/bin/ /usr/local/bin/
-
-COPY --from=builder /app/.venv/ /app/.venv/
-
-COPY --from=builder /app/misc/webservice.py /app/
-COPY --from=builder /app/misc/watcher.py /app/
-
-# Copy minimal project files to get the test suite.
-COPY --from=builder /app/pyproject.toml /app/README.md /app/
-COPY --from=builder /app/tests /app/tests
 
 ENV PATH="/app/.venv/bin:${PATH}"
 

.github/ISSUE_TEMPLATE/1-bug-report-general.yml

@@ -1,7 +1,7 @@
 name: Installation, packaging, dependencies
 description: Installation, packages, dependencies, "nothing works", test suite failures...
 title: "[Bug]: "
-labels: ["bug", "triage"]
+labels: ["triage"]
 assignees:
   - jbarlow83
 body:
@@ -24,7 +24,7 @@ body:
   - type: dropdown
     id: packaging-system
     attributes:
-      label: Where are you installing from?
+      label: Where are you installing/running from?
       multiple: true
       options:
         - PyPI (pip, poetry, pipx, etc.)
@@ -37,6 +37,11 @@ body:
         - source build
     validations:
       required: true
+  - type: input
+    id: version
+    attributes:
+      label: OCRmyPDF version
+      description: Paste "ocrmypdf --version" here
   - type: dropdown
     id: operating-system
     attributes:
@@ -47,6 +52,18 @@ body:
         - Windows
         - macOS
         - BSD
+  - type: input
+    id: os_version
+    attributes:
+      label: Operating system details and version
+  - type: checkboxes
+    attributes:
+      label: Simple sanity checks
+      description: Select all that apply
+      options:
+        - label: Operating system is currently supported by its vendor (not end of life)
+        - label: Python version is compatible with OCRmyPDF
+        - label: This issue is not about a specific input file
   - type: textarea
     id: logs
     attributes:

.github/ISSUE_TEMPLATE/2-problem-with-specific-file.yml

@@ -1,7 +1,7 @@
 name: Problem with specific file
 description: Something went wrong while trying to OCR a specific file
 title: "[Bug]: "
-labels: ["bug", "triage"]
+labels: ["triage"]
 assignees:
   - jbarlow83
 body:
@@ -39,7 +39,7 @@ body:
         causing the issue. There's really no substitute for a test file.
 
         We understand files may contain personal or sensitive information. Here are some options:
-        - Try reproducing the issue with a file from the test suite. (See tests/resources)
+        - Try reproducing the issue with a file from the OCRmyPDF test suite. (See tests/resources)
         - Try to create another file in the same way as your private file.
         - Encrypt the file to OCRmyPDF's private GPG key, and then zip the GPG file.
         - Use ``qpdf --json yourfile.pdf`` to produce a JSON representation of your file that

.github/ISSUE_TEMPLATE/3-app.yml

@@ -0,0 +1,83 @@
+name: Problem with third party app that uses OCRmyPDF
+description: |
+  For PDF generation issues with third party software such as Paperless-ngx that
+  uses OCRmyPDF to perform OCR or generate PDFs.
+title: "[3rdparty]: "
+labels: ["triage"]
+assignees:
+  - jbarlow83
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to describe this issue with a particular file
+        and third party app.
+
+        If you are comfortable using OCRmyPDF, please trying to install OCRmyPDF,
+        run it on your file, and see if it works. It's easier for everyone
+        if you can confirm that the issue occurs with OCRmyPDF and not with
+        the third party app.
+  - type: checkboxes
+    attributes:
+      label: Simple sanity checks
+      description: Select all that apply
+      options:
+        - label: This is an issue with an app that uses OCRmyPDF for OCR
+        - label: I am using a recent version of the third party app
+        - label: I will include a file that reproduces the issuse
+  - type: input
+    id: thirdparty-app-name-version
+    attributes:
+      label: Third party app name and version
+      description: e.g. Paperless-ngx 2.9.0
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: Describe the bug
+      description: A clear and concise description of what the bug is.
+      placeholder: Tell us what you see!
+    validations:
+      required: true
+  - type: textarea
+    id: reproduce
+    attributes:
+      label: Steps to reproduce
+      description: Please include steps to reproduce.
+      value: |
+        1. Import attached file into Paperless-ngx
+        2. Trigger OCR
+        3. Check log file
+        4. ...
+      render: plain text
+  - type: textarea
+    id: files
+    attributes:
+      label: Files
+      description: |
+        Please attach the input and output files, or any screenshots that may be helpful.
+
+        If you cannot provide a test file, we probably won't be able to help with the issue.
+        PDF is a complex file format, and there may be technical details in the PDF that are
+        causing the issue. There's really no substitute for a test file.
+
+        We understand files may contain personal or sensitive information. Here are some options:
+        - Try reproducing the issue with a file from the test suite. (See tests/resources)
+        - Try to create another file in the same way as your private file.
+        - Encrypt the file to OCRmyPDF's private GPG key, and then zip the GPG file.
+        - Use ``qpdf --json yourfile.pdf`` to produce a JSON representation of your file that
+          omits personal information.
+      placeholder: |
+        Drag and drop files here.
+  - type: input
+    id: version
+    attributes:
+      label: OCRmyPDF version
+      description: Paste "ocrmypdf --version" here
+      placeholder: ocrmypdf --version
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant log output
+      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+      placeholder: Run OCRmyPDF with verbosity `-v1` to get more detailed logging output.
+      render: plain text

.github/workflows/build.yml

@@ -21,18 +21,13 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
+        os: [ubuntu-22.04, ubuntu-24.04]
+        python: ["3.10", "3.11", "3.12", "3.13"]
         include:
           - os: ubuntu-22.04
+            tesseract_ppa: "ppa"
             python: "3.10"
-          - os: ubuntu-22.04
+          - os: ubuntu-24.04
-            python: "3.11"
-          - os: ubuntu-22.04
-            python: "3.10"
-            tesseract5: true
-          - os: ubuntu-latest
-            python: "3.12"
-            tesseract5: true
-          - os: ubuntu-latest
             python: "pypy3.10"
 
     env:
@@ -44,14 +39,18 @@ jobs:
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v5
+      - name: Install uv
-        name: Setup Python
+        uses: astral-sh/setup-uv@v3
+        with:
+          version: "0.4.27"
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
-          cache: "pip"
 
-      - name: Install Tesseract 5
+      - name: Install Tesseract from PPA
-        if: matrix.tesseract5
+        if: matrix.tesseract_ppa
         run: |
           sudo add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
 
@@ -61,6 +60,7 @@ jobs:
           sudo apt-get install -y --no-install-recommends \
             curl \
             ghostscript \
+            jbig2dec \
             img2pdf \
             libexempi8 \
             libffi-dev \
@@ -84,8 +84,7 @@ jobs:
 
       - name: Install Python packages
         run: |
-          python -m pip install --upgrade pip wheel
+          uv sync --extra test
-          python -m pip install --prefer-binary .[test]
 
       - name: Report versions
         run: |
@@ -93,25 +92,28 @@ jobs:
           gs --version
           pngquant --version
           unpaper --version
-          img2pdf --version
+          uv run img2pdf --version
 
       - name: Test
         run: |
-          python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
+          uv run pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
 
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
 
+
   test_macos:
     name: Test macOS
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [macos-latest]
+        os: [macos-latest, macos-13]  # macos-latest is arm64, macos-13 is x86_64
-        python: ["3.10", "3.11", "3.12"]
+        python: ["3.10", "3.11", "3.12", "3.13"]
 
     env:
       OS: ${{ matrix.os }}
@@ -131,34 +133,38 @@ jobs:
             ghostscript \
             jbig2enc \
             openjpeg \
-            openssl \
             pngquant \
             tesseract
 
-      - uses: actions/setup-python@v5
+      - name: Install uv
-        name: Setup Python
+        uses: astral-sh/setup-uv@v3
+        with:
+          version: "0.4.27"
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
-          cache: "pip"
 
       - name: Install Python packages
         run: |
-          python -m pip install --upgrade pip wheel
+          uv sync --extra test
-          python -m pip install --prefer-binary .[test]
 
       - name: Report versions
         run: |
           tesseract --version
           gs --version
           pngquant --version
-          img2pdf --version
+          uv run img2pdf --version
 
       - name: Test
         run: |
-          python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
+          uv run pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
 
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -169,7 +175,7 @@ jobs:
     strategy:
       matrix:
         os: [windows-latest]
-        python: ["3.10", "3.11", "3.12"]
+        python: ["3.10", "3.11", "3.12", "3.13"]
 
     env:
       OS: ${{ matrix.os }}
@@ -180,11 +186,15 @@ jobs:
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v5
+      - name: Install uv
-        name: Setup Python
+        uses: astral-sh/setup-uv@v3
+        with:
+          version: "0.4.27"
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
-          cache: "pip"
 
       - name: Install system packages
         run: |
@@ -193,15 +203,16 @@ jobs:
 
       - name: Install Python packages
         run: |
-          python -m pip install --upgrade pip wheel
+          uv sync --extra test
-          python -m pip install --prefer-binary .[test]
 
       - name: Test
         run: |
-          python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
+          uv run pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
 
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v4
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -214,16 +225,14 @@ jobs:
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v5
+      - name: Install uv
-        name: Setup Python
+        uses: astral-sh/setup-uv@v3
         with:
-          python-version: "3.10"
+          version: "0.4.27"
-          cache: "pip"
 
       - name: Make wheels and sdist
         run: |
-          python -m pip install --upgrade pip wheel build
+          uv build --sdist --wheel
-          python -m build --sdist --wheel
 
       - uses: actions/upload-artifact@v4
         with:
@@ -251,29 +260,45 @@ jobs:
 
   create_release:
     name: Create GitHub release
-    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    needs: [upload_pypi]
     runs-on: ubuntu-latest
     if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
     permissions:
       # Required to create a release
       contents: write
+      id-token: write
     steps:
       - uses: actions/download-artifact@v4
         with:
           name: artifact
           path: dist
 
-      - name: Create Release
+      - name: Sign the dists with Sigstore
-        id: create-release
+        uses: sigstore/gh-action-sigstore-python@v3.0.0
-        uses: shogo82148/actions-create-release@v1
-
-      - name: Upload Assets
-        uses: shogo82148/actions-upload-release-asset@v1
         with:
-          upload_url: ${{ steps.create-release.outputs.upload_url }}
+          inputs: >-
-          asset_path: |
-            ./dist/*.whl
             ./dist/*.tar.gz
+            ./dist/*.whl
+
+      - name: Create GitHub Release
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        run: >-
+          gh release create
+          '${{ github.ref_name }}'
+          --repo '${{ github.repository }}'
+          --notes ""
+
+      - name: Upload artifact signatures to GitHub Release
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        # Upload to GitHub Release using the `gh` CLI.
+        # `dist/` contains the built packages, and the
+        # sigstore-produced signatures and certificates.
+        run: >-
+          gh release upload
+          '${{ github.ref_name }}' dist/**
+          --repo '${{ github.repository }}'
 
   docker_ubuntu:
     name: Build Ubuntu-based Docker image
@@ -352,9 +377,6 @@ jobs:
           username: jbarlow83
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-
       - name: Set up Docker Buildx
         id: buildx
         uses: docker/setup-buildx-action@v3
@@ -366,6 +388,6 @@ jobs:
         run: |
           docker buildx build \
             --push \
-            --platform linux/amd64  \
+            --platform linux/amd64,linux/arm64  \
             --tag "${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}" \
             --file .docker/Dockerfile.alpine .

.gitignore

@@ -44,3 +44,4 @@ docs/_build/
 docs/_static/
 docs/_templates/
 docs/Makefile
+src/ocrmypdf/_version.py

docs/advanced.rst

@@ -228,6 +228,59 @@ then run ocrmypdf as follows (along with any other desired arguments):
    Some combinations of control parameters will break Tesseract or break
    assumptions that OCRmyPDF makes about Tesseract's output.
 
+Changing page segmentation mode
+-------------------------------
+
+The directive ``--tesseract-pagesegmode Nmode`` forwards the desired page segmentation
+mode to Tesseract OCR. The default is 3.
+
+Page segmentation can improve OCR results when you know that a PDF ought to be
+analyzed a particular way, such as PDFs whose pages contain only a single line of 
+text. For the vast majority of users, changing the page segmentation mode will only
+make things worse.
+
+As of June 2024, the Tesseract page segmentation modes are:
+
++-----+----------------------------------------------------------------------------------+
+| ID  | Description                                                                      |
++=====+==================================================================================+
+|  0  | Orientation and script detection (OSD) only.                                      |
++-----+----------------------------------------------------------------------------------+
+|  1  | Automatic page segmentation with OSD.                                             |
++-----+----------------------------------------------------------------------------------+
+|  2  | Automatic page segmentation, but no OSD, or OCR. (not implemented)               |
++-----+----------------------------------------------------------------------------------+
+|  3  | Fully automatic page segmentation, but no OSD. (Default)                         |
++-----+----------------------------------------------------------------------------------+
+|  4  | Assume a single column of text of variable sizes.                                 |
++-----+----------------------------------------------------------------------------------+
+|  5  | Assume a single uniform block of vertically aligned text.                         |
++-----+----------------------------------------------------------------------------------+
+|  6  | Assume a single uniform block of text.                                            |
++-----+----------------------------------------------------------------------------------+
+|  7  | Treat the image as a single text line.                                            |
++-----+----------------------------------------------------------------------------------+
+|  8  | Treat the image as a single word.                                                 |
++-----+----------------------------------------------------------------------------------+
+|  9  | Treat the image as a single word in a circle.                                     |
++-----+----------------------------------------------------------------------------------+
+| 10  | Treat the image as a single character.                                            |
++-----+----------------------------------------------------------------------------------+
+| 11  | Sparse text. Find as much text as possible in no particular order.                |
++-----+----------------------------------------------------------------------------------+
+| 12  | Sparse text with OSD.                                                            |
++-----+----------------------------------------------------------------------------------+
+| 13  | Raw line. Treat the image as a single text line, bypassing hacks that are        |
+|     | Tesseract-specific.                                                               |
++-----+----------------------------------------------------------------------------------+
+
+Modes 0, 1, 2, and 12 (all of those that enable orientation and script detection) 
+are not compatible with OCRmyPDF, which performs OSD in a separate step from OCR.
+Their use may interfere with ``--rotate-pages`` and other features.
+
+It is currently not possible to use advanced Tesseract OCR features, such as creating
+OCR information, when using Tesseract through OCRmyPDF.
+
 Changing the PDF renderer
 =========================
 
@@ -401,6 +454,10 @@ whether it succeeded or failed. An example message is:
     Temporary working files retained at:
     /tmp/ocrmypdf.io.u20wpz07
 
+When OCRmyPDF is launched as a snap, this corresponds to the snap filesystem, for instance:
+
+    /tmp/snap-private-tmp/snap.ocrmypdf/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
 working files on a per page basis have the page number as a prefix
@@ -412,9 +469,9 @@ suffix indicates the file type. Some important files include:
    on arguments this may differ from the presentation image
 -  ``_pp_deskew.png`` - the image, after deskewing
 -  ``_pp_clean.png`` - the image, after cleaning with unpaper
--  ``_ocr_tess.pdf`` - the OCR file; appears as a blank page with invisible
+-  ``_ocr_hocr.pdf`` - the OCR file; appears as a blank page with invisible
    text embedded
--  ``_ocr_tess.txt`` - the OCR text (not necessarily all text on the page,
+-  ``_ocr_hocr.txt`` - the OCR text (not necessarily all text on the page,
    if the page is mixed format)
 -  ``fix_docinfo.pdf`` - a temporary file created to fix the PDF DocumentInfo
    data structure

docs/batch.rst

@@ -135,7 +135,7 @@ Users may need to customize the script to meet their requirements.
     "OCR_ON_SUCCESS_ARCHIVE", "This will move the processed original file to ``OCR_ARCHIVE_DIRECTORY`` if the exit code is 0 (OK). Note that ``OCR_ON_SUCCESS_DELETE`` takes precedence over this option, i.e. if both options are set, the input file will be deleted."
     "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``, e.g. ``'OCR_JSON_SETTINGS={""rotate_pages"": true}'``."
+    "OCR_JSON_SETTINGS", "A JSON string specifying any other arguments for ``ocrmypdf.ocr``, e.g. ``'OCR_JSON_SETTINGS={""rotate_pages"": true, ""optimize"": "3"}'``."
     "OCR_POLL_NEW_FILE_SECONDS", "Polling interval"
     "OCR_LOGLEVEL", "Level of log messages to report"
 

docs/docker.rst

@@ -42,7 +42,7 @@ execute the image:
      - Architecture
      - Description
    * - ``jbarlow83/ocrmypdf-alpine``
-     - x86_64 only
+     - x86_64 and arm64
      - Recommended image, based on Alpine Linux.
    * - ``jbarlow83/ocrmypdf-ubuntu``
      - x86_64 and arm64
@@ -65,7 +65,13 @@ The ``ocrmypdf`` image is also available, but is deprecated and will be removed
 in the future.
 
 OCRmyPDF will use all available CPU cores. See the Docker documentation for
-`adjusting memory and CPU on other platforms <https://docs.docker.com/config/containers/resource_constraints/>`__.
+`adjusting memory and CPU on other platforms <https://docs.docker.com/config/containers/resource_constraints/>`__
+if you are using Docker on macOS or Windows, where you may need to manually assign
+more resources. On Linux, all resources will be available automatically.
+
+The underlying operating system and other details in Docker images are subject
+to change at minor releases. If you are modifying the image, you should pin
+the version you intend to use.
 
 Using the Docker image on the command line
 ==========================================
@@ -81,7 +87,7 @@ To start a Docker container (instance of the image):
 
 .. code-block:: bash
 
-   docker tag jbarlow83/ocrmypdf ocrmypdf
+   docker tag jbarlow83/ocrmypdf-alpine ocrmypdf
    docker run --rm -i ocrmypdf (... all other arguments here...) - -
 
 For convenience, create a shell alias to hide the Docker command. It is

docs/installation.rst

@@ -224,7 +224,7 @@ standard tooling needed to build packages, such as a compiler and binary tools.
 
 .. code-block:: bash
 
-   sudo pacman -S base-devel
+   sudo pacman -S --needed base-devel
 
 Now you are ready to install the OCRmyPDF package.
 
@@ -640,8 +640,7 @@ environment:
 
     pip install git+https://github.com/ocrmypdf/OCRmyPDF.git
 
-Or, to install in `development
+Or, to install in editable mode
-mode <https://packaging.python.org/en/latest/guides/distributing-packages-using-setuptools/#working-in-development-mode>`__,
 allowing customization of OCRmyPDF, use the ``-e`` flag:
 
 .. code-block:: bash
@@ -681,7 +680,7 @@ To install all of the development and test requirements:
 .. code-block:: bash
 
     git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
-    python -m .venv
+    python -m venv .venv
     source .venv/bin/activate
     cd OCRmyPDF
     pip install -e .[test]

docs/languages.rst

@@ -68,6 +68,22 @@ to what languages it should search for. Multiple languages can be
 requested using either ``-l eng+fra`` (English and French) or
 ``-l eng -l fra``.
 
+Archlinux
+------
+
+.. code-block:: bash
+
+   # Display a list of all Tesseract language packs
+   pacman -Ss tesseract-data
+
+   # Install German language pack
+   pacman -S tesseract-data-deu
+
+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+fra`` (English and French) or
+``-l eng -l fra``.
+
 Gentoo
 ------
 

docs/maintainers.rst

@@ -38,12 +38,13 @@ on ARM and x86_64. Performance may be poor on other processor architectures.
 Versioning scheme
 -----------------
 
-OCRmyPDF uses setuptools-scm for versioning, which derives the version from
+OCRmyPDF uses hatch-vcs for versioning, which derives the version from
 Git as a single source of truth. This may be unsuitable for some distributions, e.g.
 to indicate that your distribution modifies OCRmyPDF in some way.
 
 You can patch the ``__version__`` variable in ``src/ocrmypdf/_version.py`` if
-necessary.
+necessary, or set the environment variable ``SETUPTOOLS_SCM_PRETEND_VERSION``
+to the required version, if you need to override versioning for some reason.
 
 jbig2enc
 --------

docs/plugins.rst

@@ -29,6 +29,9 @@ 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.
 
+See [OCRmyPDF-EasyOCR](https://github.com/ocrmypdf/OCRmyPDF-EasyOCR) for an
+example of a straightforward, fully working plugin.
+
 Script plugins
 ==============
 
@@ -70,14 +73,15 @@ similar to ``pytest`` packages such as ``pytest-cov`` (the package) and
     module), just like pytest plugins. At the same time, please make it clear
     that your package is not official.
 
-Setuptools plugins
+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.
+installed in the same virtual environment, using a project entrypoint.
+OCRmyPDF uses the entrypoint namespace "ocrmypdf".
 
-Your package's ``pyproject.toml`` would need to contain the following, for a plugin
+For example, ``pyproject.toml`` would need to contain the following, for a plugin named
-named ``ocrmypdf-exampleplugin``:
+``ocrmypdf-exampleplugin``:
 
 .. code-block:: toml
 
@@ -87,13 +91,6 @@ named ``ocrmypdf-exampleplugin``:
     [project.entry-points."ocrmypdf"]
     exampleplugin = "exampleplugin.pluginmodule"
 
-.. code-block:: ini
-
-    # equivalent setup.cfg
-    [options.entry_points]
-    ocrmypdf =
-        exampleplugin = exampleplugin.pluginmodule
-
 Plugin requirements
 ===================
 

docs/release_notes.rst

@@ -30,6 +30,96 @@ OCRmyPDF typically supports the three most recent Python versions.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v16.6.0
+=======
+
+-  Fixed an issue where damaged PDFs would fail with ``--redo-ocr``. :issue:`1403`
+-  Fixed an error that prevented JBIG2 optimization on Windows if the image
+   was optimized in an earlier step. :issue:`1396`
+-  Fixed an error detecting the version of unpaper 7.0.0. :issue:`1409`
+-  Fixed a performance regression when scanning pages. :issue:`1378`. Thanks @aliemjay.
+-  Fixed Alpine Docker image by enforcing Alpine 3.19. Alpine 3.20 includes a
+   defective version of Tesseract OCR and so is not usable.
+-  Upgraded Ubuntu Docker image to use Ubuntu 24.04.
+-  Build and test scripts/actions switched to uv.
+-  When running in a container, we now remind the user that temporary folders
+   are inside the container and may not be accessible.
+-  Fixed Linux test coverage matrix, which was missing some key versions.
+
+v16.5.0
+=======
+
+-  Fixed issue with interpreting PDFs that have images with array masks.
+   :issue:`1377`
+-  Enabled testing on Python 3.13.
+-  Fixed a test that did not work correctly but still passed. :issue:`1382`
+-  Improved "PDF/A conversion failed" warning message to better describe implications.
+-  Updated documentation to better explain OCR_JSON_SETTINGS in batch processing.
+-  Build backend changed from setuptools to hatchling.
+
+v16.4.3
+=======
+
+-  Work around pdfminer.six issue where a token on the buffer boundary is incorrectly
+   parsed as two tokens. :issue:`1361`
+-  New rules are applied to stencil masks and explicit masks when calculating the
+   optimal page DPI for rendering. :issue:`1362`
+-  Fixed attempts to use an incompatible jbig2.EXE provided by TeX Live. :issue:`1363`
+
+v16.4.2
+=======
+
+-  Fixed order of filenames passed to Ghostscript for PDF/A generation. :issue:`1359`
+-  Suppressed missing jbig2dec warning message. :issue:`1358`
+-  Fixed calculation of image size when soft mask dimensions don't match image
+   dimension. :issue:`1351`
+-  Several fixes to documentation. Thanks to users Iris and JoKalliauer
+   who contributed these changes.
+-  Fixed error on processing PDFs that are missing certain image metadata. :issue:`1315`
+
+v16.4.1
+=======
+
+-  Fixed calculation of image printed area (used in finding weighted DPI for OCR).
+   :issue:`1334`
+-  Fixed "NotImplementedError: not sure how to get colorspace" error
+   messages in logs which simply records a failure to optimize images with
+   print production colorspaces. :issue:`1315`
+
+v16.4.0
+=======
+
+-  Selecting the ``osd`` and ``equ`` pseudo-languages with ``-l/--language`` now
+   exits with an error when using Tesseract OCR, because these are not
+   regular Tesseract languages but implementation details implemented.
+   Using them can cause Tesseract to crash.
+-  The hOCR renderer is more tolerant of extra whitespace in input files.
+-  watcher.py now changes the output file extension to .pdf when the input is not
+   .pdf.
+-  Improved handling of PDFs that contain circularly referenced Form XObjects.
+   :issue:`1321`
+-  Fixed Alpine Docker image for ARM64, which was not building correctly.
+-  Docker images now use pikepdf 9.0.0.
+-  Prevent use of Tesseract OCR 5.4.0, a version with known regressions.
+-  Disabled progressbar for "Linearizing" when ``--no-progress-bar`` set.
+-  Fixed some tests that warn about missing JBIG2 decoding via pikepdf, by
+   installing the necessary libraries during tests.
+
+v16.3.1
+=======
+
+-  Fixed a test suite failure with Ghostscript 10.03.0+. :issue:`1316`
+-  Fixed an issue with the presentation of the "OCR" progress bar. :issue:`1313`
+
+v16.3.0
+=======
+
+-  Fixed progress bar not displaying for Ghostscript PDF/A conversion. :issue:`1313`
+-  Added progress bar for linearization. :issue:`1313`
+-  If `--rotate-pages-threshold` issued without `--rotate-pages` we now exit with
+   an error since the user likely intended to use `--rotate-pages`. :issue:`1309`
+-  If Tesseract hOCR gives an invalid line box, print an error message instead of
+   exiting with an error. :issue:`1312`
 
 v16.2.0
 =======

misc/batch.py

@@ -14,12 +14,12 @@ You should edit this script to meet your needs.
 
 from __future__ import annotations
 
+import filecmp
 import logging
-import sys
 import os
 import posixpath
 import shutil
-import filecmp
+import sys
 from pathlib import Path
 
 import ocrmypdf
@@ -70,7 +70,7 @@ for filename in start_dir.glob("**/*.pdf"):
             logging.info(f"Archiving document to {archive_filename}")
             try:
                 shutil.copy2(filename, posixpath.dirname(archive_filename))
-            except IOError as io_err:
+            except OSError:
                 os.makedirs(posixpath.dirname(archive_filename))
                 shutil.copy2(filename, posixpath.dirname(archive_filename))
         try:
@@ -86,6 +86,6 @@ for filename in start_dir.glob("**/*.pdf"):
             logging.info(
                 "Skipped document because it does not need ocr as it is tagged"
             )
-        except:
+        except Exception:
             logging.error("Unhandled error occured")
         logging.info("OCR complete")

misc/watcher.py

@@ -46,15 +46,18 @@ class LoggingLevelEnum(str, Enum):
     CRITICAL = "CRITICAL"
 
 
-def get_output_dir(root: Path, basename: str, output_dir_year_month: bool) -> Path:
+def get_output_path(root: Path, basename: str, output_dir_year_month: bool) -> Path:
+    assert '/' not in basename, "basename must not contain '/'"
     if output_dir_year_month:
         today = datetime.today()
         output_directory_year_month = root / str(today.year) / f'{today.month:02d}'
         if not output_directory_year_month.exists():
             output_directory_year_month.mkdir(parents=True, exist_ok=True)
-        output_path = Path(output_directory_year_month) / basename
+        output_path = Path(output_directory_year_month) / Path(basename).with_suffix(
+            '.pdf'
+        )
     else:
-        output_path = root / basename
+        output_path = root / Path(basename).with_suffix('.pdf')
     return output_path
 
 
@@ -98,7 +101,7 @@ def execute_ocrmypdf(
     retries_loading_file: int,
     output_dir_year_month: bool,
 ):
-    output_path = get_output_dir(output_dir, file_path.name, output_dir_year_month)
+    output_path = get_output_path(output_dir, file_path.name, output_dir_year_month)
 
     log.info("-" * 20)
     log.info(f'New file: {file_path}. Waiting until fully written...')

pyproject.toml

@@ -1,8 +1,8 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 [build-system]
-requires = ["setuptools >= 61", "setuptools_scm[toml] >= 7.0.5", "wheel"]
+requires = ["hatchling", "hatch-vcs"]
-build-backend = "setuptools.build_meta"
+build-backend = "hatchling.build"
 
 [project]
 name = "ocrmypdf"
@@ -46,6 +46,7 @@ keywords = ["PDF", "OCR", "optical character recognition", "PDF/A", "scanning"]
 Documentation = "https://ocrmypdf.readthedocs.io/"
 Source = "https://github.com/ocrmypdf/OCRmyPDF"
 Tracker = "https://github.com/ocrmypdf/OCRmyPDF/issues"
+Changelog = "https://github.com/ocrmypdf/OCRmyPDF/docs/release_notes.rst"
 
 [project.optional-dependencies]
 docs = ["sphinx", "sphinx-issues", "sphinx-rtd-theme"]
@@ -67,14 +68,11 @@ webservice = ["Flask>=2.0.1"]
 [project.scripts]
 ocrmypdf = "ocrmypdf.__main__:run"
 
-[tool.setuptools.package-data]
+[tool.hatch.version]
-ocrmypdf = ["data/sRGB.icc", "py.typed"]
+source = "vcs"
 
-[tool.setuptools.packages.find]
+[tool.hatch.build.hooks.vcs]
-where = ["src"]
+version-file = "src/ocrmypdf/_version.py"
-namespaces = false
-
-[tool.setuptools_scm]
 
 [tool.distutils.bdist_wheel]
 python-tag = "py310"

snapcraft.yaml

@@ -18,8 +18,8 @@ architectures: [amd64]
 
 environment:
   TESSDATA_PREFIX: $SNAP/usr/share/tesseract-ocr/4.00/tessdata
-  GS_LIB: $SNAP/usr/share/ghostscript/9.55/Resource/Init
+  GS_LIB: $SNAP/usr/share/ghostscript/9.55.0/Resource/Init
-  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.55/Resource/Font
+  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.55.0/Resource/Font
   LD_LIBRARY_PATH: $SNAP/usr/lib/x86_64-linux-gnu
 
 apps:

src/ocrmypdf/__init__.py

@@ -9,11 +9,12 @@ from pluggy import HookimplMarker as _HookimplMarker
 
 from ocrmypdf import helpers, hocrtransform, pdfa, pdfinfo
 from ocrmypdf._concurrent import Executor
+from ocrmypdf._defaults import PROGRAM_NAME
 from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._pipelines._common import (
     configure_debug_logging,
 )
-from ocrmypdf._version import PROGRAM_NAME, __version__
+from ocrmypdf._version import __version__
 from ocrmypdf.api import (
     Verbosity,
     configure_logging,
@@ -37,7 +38,6 @@ from ocrmypdf.pluginspec import OcrEngine, OrientationConfidence
 
 hookimpl = _HookimplMarker('ocrmypdf')
 
-
 __all__ = [
     '__version__',
     'BadArgsError',

src/ocrmypdf/_defaults.py

@@ -0,0 +1,10 @@
+# SPDX-FileCopyrightText: 2024 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+# Enforce English hegemony
+DEFAULT_LANGUAGE = 'eng'
+
+# Default rotation threshold
+DEFAULT_ROTATE_PAGES_THRESHOLD = 14.0
+
+PROGRAM_NAME = 'OCRmyPDF'

src/ocrmypdf/_exec/ghostscript.py

@@ -177,6 +177,17 @@ class GhostscriptFollower:
         self.progressbar_class = progressbar_class
         self.progressbar = None
 
+    def __enter__(self):
+        # We can't actually set up the progressbar here, because we don't know
+        # how many pages there are until the first __call__() happens. So we
+        # do it in __call__().
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        if self.progressbar:
+            return self.progressbar.__exit__(exc_type, exc_value, traceback)
+        return False
+
     def __call__(self, line):
         if not self.progressbar_class:
             return
@@ -187,7 +198,8 @@ class GhostscriptFollower:
                 self.progressbar = self.progressbar_class(
                     total=self.count, desc="PDF/A conversion", unit='page'
                 )
-                return
+                # Now that we know the count, we can set up the progressbar.
+                self.progressbar.__enter__()
         else:
             if self.re_page.match(line.strip()):
                 self.progressbar.update()
@@ -265,7 +277,10 @@ 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:
+        with (
+            Path(output_file).open('wb') as output,
+            GhostscriptFollower(progressbar_class) as pbar,
+        ):
             p = run_polling_stderr(
                 args_gs,
                 stdout=output,
@@ -274,7 +289,7 @@ def generate_pdfa(
                 text=True,
                 encoding='utf-8',
                 errors='replace',
-                callback=GhostscriptFollower(progressbar_class),
+                callback=pbar,
             )
     except CalledProcessError as e:
         # Ghostscript does not change return code when it fails to create

src/ocrmypdf/_exec/jbig2enc.py

@@ -5,7 +5,7 @@
 
 from __future__ import annotations
 
-from subprocess import PIPE
+from subprocess import PIPE, CalledProcessError
 
 from packaging.version import Version
 
@@ -14,7 +14,13 @@ from ocrmypdf.subprocess import get_version, run
 
 
 def version() -> Version:
-    return Version(get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*'))
+    try:
+        version = get_version('jbig2', regex=r'jbig2enc (\d+(\.\d+)*).*')
+    except CalledProcessError as e:
+        # TeX Live for Windows provides an incompatible jbig2.EXE which may
+        # be on the PATH.
+        raise MissingDependencyError('jbig2enc') from e
+    return Version(version)
 
 
 def available():

src/ocrmypdf/_exec/unpaper.py

@@ -48,7 +48,7 @@ class UnpaperImageTooLargeError(Exception):
 
 
 def version() -> Version:
-    return Version(get_version('unpaper'))
+    return Version(get_version('unpaper', regex=r'(?m).*?(\d+(\.\d+)(\.\d+)?)'))
 
 
 @contextmanager

src/ocrmypdf/_metadata.py

@@ -15,8 +15,8 @@ from pikepdf import Dictionary, Name, Pdf
 from pikepdf import __version__ as PIKEPDF_VERSION
 from pikepdf.models.metadata import PdfMetadata, encode_pdf_date
 
+from ocrmypdf._defaults import PROGRAM_NAME
 from ocrmypdf._jobcontext import PdfContext
-from ocrmypdf._version import PROGRAM_NAME
 from ocrmypdf._version import __version__ as OCRMYPF_VERSION
 from ocrmypdf.languages import iso_639_2_from_3
 
@@ -153,18 +153,45 @@ def _set_language(pdf: Pdf, languages: list[str]):
     pdf.Root.Lang = iso639_2
 
 
+class MetadataProgress:
+    def __init__(self, progressbar_class, enable: bool = True):
+        self.progressbar_class = progressbar_class
+        self.progressbar = self.progressbar_class(
+            total=100, desc="Linearizing", unit='%', disable=not enable
+        )
+
+    def __enter__(self):
+        self.progressbar.__enter__()
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        return self.progressbar.__exit__(exc_type, exc_value, traceback)
+
+    def __call__(self, percent: int):
+        if not self.progressbar_class:
+            return
+        self.progressbar.update(completed=percent)
+
+
 def metadata_fixup(
     working_file: Path, context: PdfContext, pdf_save_settings: dict[str, Any]
 ) -> Path:
-    """Fix certain metadata fields after Ghostscript PDF/A conversion.
+    """Fix certain metadata fields whether PDF or PDF/A.
+
+    Override some of Ghostscript's metadata choices.
 
     Also report on metadata in the input file that was not retained during
-    PDF/A conversion.
+    conversion.
     """
     output_file = context.get_path('metafix.pdf')
     options = context.options
 
-    with Pdf.open(context.origin) as original, Pdf.open(working_file) as pdf:
+    pbar_class = context.plugin_manager.hook.get_progressbar_class()
+    with (
+        Pdf.open(context.origin) as original,
+        Pdf.open(working_file) as pdf,
+        MetadataProgress(pbar_class, options.progress_bar) as pbar,
+    ):
         docinfo = get_docinfo(original, context)
         with (
             original.open_metadata(
@@ -182,6 +209,6 @@ def metadata_fixup(
             report_on_metadata(options, meta_missing)
 
         _set_language(pdf, options.languages)
-        pdf.save(output_file, **pdf_save_settings)
+        pdf.save(output_file, progress=pbar, **pdf_save_settings)
 
     return output_file

src/ocrmypdf/_pipeline.py

@@ -159,8 +159,13 @@ def triage(
                     "Argument --image-dpi is being ignored because the "
                     "input file is a PDF, not an image."
                 )
-            # Origin file is a pdf create a symlink with pdf extension
+            try:
-            safe_symlink(input_file, output_file)
+                with pikepdf.open(input_file) as pdf:
+                    pdf.save(output_file)
+            except pikepdf.PdfError as e:
+                raise InputFileError() from e
+            except pikepdf.PasswordError as e:
+                raise EncryptedPdfError() from e
             return output_file
     except OSError as e:
         log.debug(f"Temporary file was at: {input_file}")
@@ -475,7 +480,7 @@ def calculate_raster_dpi(page_context: PageContext):
     page_dpi = get_page_square_dpi(page_context, image_dpi)
     if dpi_profile and dpi_profile.average_to_max_dpi_ratio < 0.8:
         log.warning(
-            "Weight average image DPI is %0.1f, max DPI is %0.1f. "
+            "Weighted average image DPI is %0.1f, max DPI is %0.1f. "
             "The discrepancy may indicate a high detail region on this page, "
             "but could also indicate a problem with the input PDF file. "
             "Page image will be rendered at %0.1f DPI.",
@@ -854,7 +859,7 @@ def fix_pagepdf_boxes(
             page.CropBox = cropbox
             page.TrimBox = trimbox
         pdf.save(out_file)
-    return pdf
+    return out_file
 
 
 def generate_postscript_stub(context: PdfContext) -> Path:

src/ocrmypdf/_pipelines/_common.py

@@ -33,6 +33,7 @@ from ocrmypdf._pipeline import (
     generate_postscript_stub,
     get_orientation_correction,
     get_pdf_save_settings,
+    get_pdfinfo,
     optimize_pdf,
     preprocess_clean,
     preprocess_deskew,
@@ -51,9 +52,12 @@ from ocrmypdf.helpers import (
     available_cpu_count,
     check_pdf,
     pikepdf_enable_mmap,
+    running_in_docker,
+    running_in_snap,
     samefile,
 )
 from ocrmypdf.pdfa import file_claims_pdfa
+from ocrmypdf.pdfinfo import PdfInfo
 
 log = logging.getLogger(__name__)
 tls = threading.local()
@@ -183,7 +187,7 @@ def configure_debug_logging(
     return log_file_handler, remover
 
 
-def worker_init(max_pixels: int) -> None:
+def worker_init(max_pixels: int | None) -> None:
     """Initialize a worker thread or process."""
     # In Windows, child process will not inherit our change to this value in
     # the parent process, so ensure workers get it set. Not needed when running
@@ -215,6 +219,22 @@ def manage_debug_log_handler(
             remover()
 
 
+def _print_temp_folder_location(work_folder: Path):
+    """Print the location of the temporary work folder."""
+    msgs = [f"Temporary working files retained at:\n{work_folder}"]
+    if running_in_docker():  # pragma: no cover
+        msgs.append(
+            "OCRmyPDF is running in a Docker container, "
+            "so the files will be inside the container."
+        )
+    elif running_in_snap():  # pragma: no cover
+        msgs.append(
+            "OCRmyPDF is running in a Snap container, "
+            "so the files will be inside the container."
+        )
+    print('\n'.join(msgs), file=sys.stderr)
+
+
 @contextmanager
 def manage_work_folder(*, work_folder: Path, retain: bool, print_location: bool):
     try:
@@ -222,10 +242,7 @@ def manage_work_folder(*, work_folder: Path, retain: bool, print_location: bool)
     finally:
         if retain:
             if print_location:
-                print(
+                _print_temp_folder_location(work_folder)
-                    f"Temporary working files retained at:\n{work_folder}",
-                    file=sys.stderr,
-                )
         else:
             shutil.rmtree(work_folder, ignore_errors=True)
 
@@ -300,6 +317,20 @@ def setup_pipeline(
     return executor
 
 
+def do_get_pdfinfo(
+    pdf_path: Path, executor: Executor, options: argparse.Namespace
+) -> PdfInfo:
+    return get_pdfinfo(
+        pdf_path,
+        executor=executor,
+        detailed_analysis=options.redo_ocr,
+        progbar=options.progress_bar,
+        max_workers=options.jobs,
+        use_threads=options.use_threads,
+        check_pages=options.pages,
+    )
+
+
 def preprocess(
     page_context: PageContext,
     image: Path,
@@ -441,7 +472,8 @@ def report_output_pdf(options, start_input_file, optimize_messages) -> ExitCode:
                 log.info("Output file is a %s (as expected)", pdfa_info['conformance'])
             else:
                 log.warning(
-                    "Output file is okay but is not PDF/A (seems to be %s)",
+                    "Output file is a valid PDF, but conversion to PDF/A did not "
+                    "succeed (issue: %s)",
                     pdfa_info['conformance'],
                 )
                 return ExitCode.pdfa_conversion_failed

src/ocrmypdf/_pipelines/hocr_to_ocr_pdf.py

@@ -19,11 +19,11 @@ from ocrmypdf._graft import OcrGrafter
 from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._pipeline import (
     copy_final,
-    get_pdfinfo,
     render_hocr_page,
 )
 from ocrmypdf._pipelines._common import (
     HOCRResult,
+    do_get_pdfinfo,
     manage_work_folder,
     postprocess,
     report_output_pdf,
@@ -117,15 +117,7 @@ def run_hocr_to_ocr_pdf_pipeline(
         origin_pdf = work_folder / 'origin.pdf'
 
         # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
+        pdfinfo = do_get_pdfinfo(origin_pdf, executor, options)
-            origin_pdf,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs,
-            use_threads=options.use_threads,
-            check_pages=options.pages,
-        )
         context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
         plugin_manager.hook.check_options(options=options)
         optimize_messages = exec_hocr_to_ocr_pdf(context, executor)

src/ocrmypdf/_pipelines/ocr.py

@@ -21,7 +21,6 @@ from ocrmypdf._graft import OcrGrafter
 from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._pipeline import (
     copy_final,
-    get_pdfinfo,
     is_ocr_required,
     merge_sidecars,
     ocr_engine_hocr,
@@ -33,6 +32,7 @@ from ocrmypdf._pipeline import (
 from ocrmypdf._pipelines._common import (
     PageResult,
     cli_exception_handler,
+    do_get_pdfinfo,
     manage_debug_log_handler,
     manage_work_folder,
     postprocess,
@@ -103,14 +103,14 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
         try:
             set_thread_pageno(result.pageno + 1)
             sidecars[result.pageno] = result.text
-            pbar.update()
+            pbar.update(0.5)
             ocrgraft.graft_page(
                 pageno=result.pageno,
                 image=result.pdf_page_from_image,
                 textpdf=result.ocr,
                 autorotate_correction=result.orientation_correction,
             )
-            pbar.update()
+            pbar.update(0.5)
         finally:
             set_thread_pageno(None)
 
@@ -118,10 +118,9 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
         use_threads=options.use_threads,
         max_workers=max_workers,
         progress_kwargs=dict(
-            total=(2 * len(context.pdfinfo)),
+            total=len(context.pdfinfo),
             desc='OCR' if options.tesseract_timeout > 0 else 'Image processing',
             unit='page',
-            unit_scale=0.5,
             disable=not options.progress_bar,
         ),
         worker_initializer=partial(worker_init, PIL.Image.MAX_IMAGE_PIXELS),
@@ -172,16 +171,7 @@ def _run_pipeline(
         )
 
         # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
+        pdfinfo = do_get_pdfinfo(origin_pdf, executor, options)
-            origin_pdf,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs,
-            use_threads=options.use_threads,
-            check_pages=options.pages,
-        )
-
         context = PdfContext(options, work_folder, origin_pdf, pdfinfo, plugin_manager)
 
         # Validate options are okay for this pdf

src/ocrmypdf/_pipelines/pdf_to_hocr.py

@@ -17,13 +17,13 @@ import PIL
 from ocrmypdf._concurrent import Executor
 from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._pipeline import (
-    get_pdfinfo,
     is_ocr_required,
     ocr_engine_hocr,
     validate_pdfinfo_options,
 )
 from ocrmypdf._pipelines._common import (
     HOCRResult,
+    do_get_pdfinfo,
     manage_work_folder,
     process_page,
     set_thread_pageno,
@@ -94,18 +94,11 @@ def run_hocr_pipeline(
         work_folder=options.output_folder, retain=True, print_location=False
     ) as work_folder:
         executor = setup_pipeline(options, plugin_manager)
-        shutil.copy2(options.input_file, work_folder / 'origin.pdf')
+        origin_pdf = work_folder / 'origin.pdf'
+        shutil.copy2(options.input_file, origin_pdf)
 
         # Gather pdfinfo and create context
-        pdfinfo = get_pdfinfo(
+        pdfinfo = do_get_pdfinfo(origin_pdf, executor, options)
-            options.input_file,
-            executor=executor,
-            detailed_analysis=options.redo_ocr,
-            progbar=options.progress_bar,
-            max_workers=options.jobs,
-            use_threads=options.use_threads,
-            check_pages=options.pages,
-        )
         context = PdfContext(
             options, work_folder, options.input_file, pdfinfo, plugin_manager
         )

src/ocrmypdf/_progressbar.py

@@ -66,7 +66,7 @@ class ProgressBar(Protocol):
     def __exit__(self, *args):
         """Exit a progress bar context."""
 
-    def update(self, n=1):
+    def update(self, n=1, *, completed=None):
         """Update the progress bar by an increment.
 
         For use within a progress bar context.
@@ -85,7 +85,7 @@ class NullProgressBar:
     def __exit__(self, exc_type, exc_value, traceback):
         return False
 
-    def update(self, _arg=None):
+    def update(self, _arg=None, *, completed=None):
         return
 
 
@@ -103,6 +103,7 @@ class RichProgressBar:
         disable: bool = False,
         **kwargs,
     ):
+        self._entered = False
         self.progress = Progress(
             TextColumn(
                 "[progress.description]{task.description}",
@@ -130,6 +131,7 @@ class RichProgressBar:
 
     def __enter__(self):
         self.progress.start()
+        self._entered = True
         return self
 
     def __exit__(self, exc_type, exc_value, traceback):
@@ -137,6 +139,10 @@ class RichProgressBar:
         self.progress.stop()
         return False
 
-    def update(self, value=None):
+    def update(self, n=1, *, completed=None):
-        advance = self.unit_scale if value is None else value
+        assert self._entered, "Progress bar must be entered before updating"
-        self.progress.update(self.progress_bar, advance=advance)
+        if completed is None:
+            advance = self.unit_scale if n is None else n
+            self.progress.update(self.progress_bar, advance=advance)
+        else:
+            self.progress.update(self.progress_bar, completed=completed)

src/ocrmypdf/_validation.py

@@ -20,6 +20,7 @@ import pikepdf
 import PIL
 from pluggy import PluginManager
 
+from ocrmypdf._defaults import DEFAULT_LANGUAGE, DEFAULT_ROTATE_PAGES_THRESHOLD
 from ocrmypdf._exec import unpaper
 from ocrmypdf.exceptions import (
     BadArgsError,
@@ -27,20 +28,18 @@ from ocrmypdf.exceptions import (
     MissingDependencyError,
     OutputFileAccessError,
 )
-from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink
+from ocrmypdf.helpers import (
+    is_file_writable,
+    monotonic,
+    running_in_docker,
+    running_in_snap,
+    safe_symlink,
+)
 from ocrmypdf.subprocess import check_external_program
 
-# -------------
-# External dependencies
-
-DEFAULT_LANGUAGE = 'eng'  # Enforce English hegemony
-
 log = logging.getLogger(__name__)
 
 
-# --------
-
-
 def check_platform() -> None:
     if sys.maxsize <= 2**32:  # pragma: no cover
         log.warning(
@@ -61,6 +60,7 @@ def check_options_languages(
             log.debug("No language specified; assuming --language %s", DEFAULT_LANGUAGE)
     if not ocr_engine_languages:
         return
+
     missing_languages = set(options.languages) - set(ocr_engine_languages)
     if missing_languages:
         lang_text = '\n'.join(lang for lang in missing_languages)
@@ -130,6 +130,11 @@ def check_options_preprocessing(options: Namespace) -> None:
         options.clean = True
     if options.unpaper_args and not options.clean:
         raise BadArgsError("--clean is required for --unpaper-args")
+    if (
+        options.rotate_pages_threshold != DEFAULT_ROTATE_PAGES_THRESHOLD
+        and not options.rotate_pages
+    ):
+        raise BadArgsError("--rotate-pages is required for --rotate-pages-threshold")
     if options.clean:
         check_external_program(
             program='unpaper',
@@ -238,18 +243,6 @@ def check_options(options: Namespace, plugin_manager: PluginManager) -> None:
     _check_plugin_options(options, plugin_manager)
 
 
-def _in_docker():
-    return Path('/.dockerenv').exists()
-
-
-def _in_snap():
-    try:
-        cgroup_text = Path('/proc/self/cgroup').read_text()
-        return 'snap.ocrmypdf' in cgroup_text
-    except FileNotFoundError:
-        return False
-
-
 def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]:
     if options.input_file == '-':
         # stdin
@@ -273,7 +266,7 @@ def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]
             return target, os.fspath(options.input_file)
         except FileNotFoundError as e:
             msg = f"File not found - {options.input_file}"
-            if _in_docker():  # pragma: no cover
+            if running_in_docker():  # pragma: no cover
                 msg += (
                     "\nDocker cannot access your working directory unless you "
                     "explicitly share it with the Docker container and set up"
@@ -283,7 +276,7 @@ def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]
                     "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf"
                     "\n"
                 )
-            elif _in_snap():  # pragma: no cover
+            elif running_in_snap():  # pragma: no cover
                 msg += (
                     "\nSnap applications cannot access files outside of "
                     "your home directory unless you explicitly allow it. "

src/ocrmypdf/_version.py

@@ -1,16 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""Get version by introspecting package information.
-
-OCRmyPDF uses setuptools_scm to derive version from git tags.
-"""
-
-from __future__ import annotations
-
-from importlib.metadata import version as _package_version
-
-PROGRAM_NAME = 'ocrmypdf'
-
-# Official PEP 396
-__version__ = _package_version('ocrmypdf')

src/ocrmypdf/api.py

@@ -14,7 +14,7 @@ from collections.abc import Iterable, Sequence
 from enum import IntEnum
 from io import IOBase
 from pathlib import Path
-from typing import AnyStr, BinaryIO
+from typing import BinaryIO
 from warnings import warn
 
 import pluggy
@@ -28,7 +28,7 @@ from ocrmypdf._validation import check_options
 from ocrmypdf.cli import ArgumentParser, get_parser
 from ocrmypdf.helpers import is_iterable_notstr
 
-StrPath = Path | AnyStr
+StrPath = Path | str | bytes
 PathOrIO = BinaryIO | StrPath
 
 # Installing plugins affects the global state of the Python interpreter,
@@ -140,9 +140,9 @@ def configure_logging(
 
 def _kwargs_to_cmdline(
     *, defer_kwargs: set[str], **kwargs
-) -> tuple[list[str], dict[str, AnyStr]]:
+) -> tuple[list[str | bytes], dict[str, str | bytes]]:
     """Convert kwargs to command line arguments."""
-    cmdline = []
+    cmdline: list[str | bytes] = []
     deferred = {}
     for arg, val in kwargs.items():
         if val is None:
@@ -279,7 +279,7 @@ def ocr(  # noqa: D417
     fast_web_view: float | None = None,
     continue_on_soft_render_error: bool | None = None,
     invalidate_digital_signatures: bool | None = None,
-    plugins: Iterable[StrPath] | None = None,
+    plugins: Iterable[Path | str] | None = None,
     plugin_manager=None,
     keep_temporary_files: bool | None = None,
     progress_bar: bool | None = None,
@@ -420,7 +420,7 @@ def _pdf_to_hocr(  # noqa: D417
     continue_on_soft_render_error: bool | None = None,
     invalidate_digital_signatures: bool | None = None,
     plugin_manager=None,
-    plugins: Sequence[StrPath] | None = None,
+    plugins: Sequence[Path | str] | None = None,
     keep_temporary_files: bool | None = None,
     **kwargs,
 ):
@@ -491,7 +491,7 @@ def _hocr_to_ocr_pdf(  # noqa: D417
     color_conversion_strategy: str | None = None,
     fast_web_view: float | None = None,
     plugin_manager=None,
-    plugins: Sequence[StrPath] | None = None,
+    plugins: Sequence[Path | str] | None = None,
     **kwargs,
 ):
     """Run OCRmyPDF on a work folder and produce an output PDF.

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -129,7 +129,7 @@ def generate_pdfa(
 ):
     """Generate a PDF/A from the list of PDF pages and PDF/A metadata."""
     ghostscript.generate_pdfa(
-        pdf_pages=[*pdf_pages, pdfmark],
+        pdf_pages=[pdfmark, *pdf_pages],
         output_file=output_file,
         compression=context.options.pdfa_image_compression,
         color_conversion_strategy=context.options.color_conversion_strategy,

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -14,6 +14,7 @@ from ocrmypdf import hookimpl
 from ocrmypdf._exec import tesseract
 from ocrmypdf._jobcontext import PageContext
 from ocrmypdf.cli import numeric, str_to_int
+from ocrmypdf.exceptions import BadArgsError, MissingDependencyError
 from ocrmypdf.helpers import clamp
 from ocrmypdf.imageops import calculate_downsample, downsample_image
 from ocrmypdf.pluginspec import OcrEngine
@@ -144,6 +145,12 @@ def check_options(options):
         need_version='4.1.1',  # Ubuntu 22.04 version (also 20.04)
         version_parser=tesseract.TesseractVersion,
     )
+    tess_version = tesseract.version()
+    if tess_version == tesseract.TesseractVersion('5.4.0'):
+        raise MissingDependencyError(
+            "Tesseract 5.4.0 is not supported due to regressions in this version. "
+            "Please upgrade to a newer or supported older version."
+        )
 
     # Decide on what renderer to use
     if options.pdf_renderer == 'auto':
@@ -164,6 +171,14 @@ def check_options(options):
             "The --tesseract-pagesegmode argument you select will disable OCR. "
             "This may cause processing to fail."
         )
+    DENIED_LANGUAGES = {'equ', 'osd'}
+    if DENIED_LANGUAGES & set(options.languages):
+        raise BadArgsError(
+            "The following languages for Tesseract's internal use and should not "
+            "be issued explicitly: "
+            f"{', '.join(DENIED_LANGUAGES & set(options.languages))}\n"
+            "Remove them from the -l/--language argument."
+        )
 
 
 @hookimpl

src/ocrmypdf/cli.py

@@ -9,7 +9,8 @@ import argparse
 from collections.abc import Callable, Mapping
 from typing import Any, TypeVar
 
-from ocrmypdf._version import PROGRAM_NAME as _PROGRAM_NAME
+from ocrmypdf._defaults import DEFAULT_ROTATE_PAGES_THRESHOLD
+from ocrmypdf._defaults import PROGRAM_NAME as _PROGRAM_NAME
 from ocrmypdf._version import __version__ as _VERSION
 
 T = TypeVar('T', int, float)
@@ -403,7 +404,7 @@ Online documentation is located at:
     )
     advanced.add_argument(
         '--rotate-pages-threshold',
-        default=14.0,
+        default=DEFAULT_ROTATE_PAGES_THRESHOLD,
         type=numeric(float, 0, 1000),
         metavar='CONFIDENCE',
         help="Only rotate pages when confidence is above this value (arbitrary "

src/ocrmypdf/helpers.py

@@ -268,7 +268,9 @@ def check_pdf(input_file: Path) -> bool:
         return False
     else:
         with pdf:
-            messages = pdf.check()
+            with warnings.catch_warnings():
+                warnings.filterwarnings('ignore', message=r'pikepdf.*JBIG2.*')
+                messages = pdf.check()
             success = True
             for msg in messages:
                 if 'error' in msg.lower():
@@ -333,3 +335,17 @@ def pikepdf_enable_mmap() -> None:
         )
     except AttributeError:
         log.debug("pikepdf mmap not available")
+
+
+def running_in_docker() -> bool:
+    """Returns True if we seem to be running in a Docker container."""
+    return Path('/.dockerenv').exists()
+
+
+def running_in_snap() -> bool:
+    """Returns True if we seem to be running in a Snap container."""
+    try:
+        cgroup_text = Path('/proc/self/cgroup').read_text()
+        return 'snap.ocrmypdf' in cgroup_text
+    except FileNotFoundError:
+        return False

src/ocrmypdf/hocrtransform/_hocr.py

@@ -61,15 +61,25 @@ class HocrTransform:
     """A class for converting documents from the hOCR format.
 
     For details of the hOCR format, see:
-    http://kba.cloud/hocr-spec/.
+    http://kba.github.io/hocr-spec/1.2/.
     """
 
-    box_pattern = re.compile(r'bbox (\d+) (\d+) (\d+) (\d+)')
+    box_pattern = re.compile(
+        r'''
+        bbox \s+
+        (\d+) \s+   # left: uint
+        (\d+) \s+   # top: uint
+        (\d+) \s+   # right: uint
+        (\d+)       # bottom: uint
+        ''',
+        re.VERBOSE,
+    )
     baseline_pattern = re.compile(
         r'''
         baseline \s+
         ([\-\+]?\d*\.?\d*) \s+  # +/- decimal float
-        ([\-\+]?\d+)            # +/- int''',
+        ([\-\+]?\d+)            # +/- int
+        ''',
         re.VERBOSE,
     )
 
@@ -117,15 +127,12 @@ class HocrTransform:
             # Stop after first div that has page coordinates
             break
 
-    def _get_element_text(self, element: Element):
+    def _get_element_text(self, element: Element) -> str:
         """Return the textual content of the element and its children."""
-        text = ''
+        text = element.text if element.text is not None else ''
-        if element.text is not None:
-            text += element.text
         for child in element:
             text += self._get_element_text(child)
-        if element.tail is not None:
+        text += element.tail if element.tail is not None else ''
-            text += element.tail
         return text
 
     @classmethod
@@ -286,7 +293,13 @@ class HocrTransform:
         line_box = self.element_coordinates(line)
         if not line_box:
             return
-        assert line_box.ury > line_box.lly  # lly is top, ury is bottom
+        if line_box.ury <= line_box.lly:
+            log.error(
+                "line box is invalid so we cannot render it: box=%s text=%s",
+                line_box,
+                self._get_element_text(line),
+            )
+            return
 
         self._debug_draw_line_bbox(canvas, line_box)
 
@@ -344,7 +357,7 @@ class HocrTransform:
         line_matrix: Matrix,
         text: Text,
         fontsize: float,
-        elem: Element,
+        elem: Element | None,
         next_elem: Element | None,
         text_direction: TextDirection,
         inject_word_breaks: bool,
@@ -421,7 +434,7 @@ class HocrTransform:
                 if ocr_par is None:
                     continue
                 canvas.do.rect(
-                    ocr_par.llx, ocr_par.lly, ocr_par.width, ocr_par.height, fill=0
+                    ocr_par.llx, ocr_par.lly, ocr_par.width, ocr_par.height, fill=False
                 )
 
     def _debug_draw_line_bbox(self, canvas: Canvas, line_box: Rectangle, color=BLUE):
@@ -430,7 +443,7 @@ class HocrTransform:
             return
         with canvas.do.save_state():
             canvas.do.stroke_color(color).line_width(0.15).rect(
-                line_box.llx, line_box.lly, line_box.width, line_box.height, fill=0
+                line_box.llx, line_box.lly, line_box.width, line_box.height, fill=False
             )
 
     def _debug_draw_word_triangle(
@@ -454,7 +467,7 @@ class HocrTransform:
             return
         with canvas.do.save_state():
             canvas.do.stroke_color(color).line_width(line_width).rect(
-                box.llx, box.lly, box.width, box.height, fill=0
+                box.llx, box.lly, box.width, box.height, fill=False
             )
 
     def _debug_draw_space_bbox(
@@ -465,7 +478,7 @@ class HocrTransform:
             return
         with canvas.do.save_state():
             canvas.do.fill_color(color).line_width(line_width).rect(
-                box.llx, box.lly, box.width, box.height, fill=1
+                box.llx, box.lly, box.width, box.height, fill=True
             )
 
     def _debug_draw_baseline(

src/ocrmypdf/optimize.py

@@ -28,6 +28,7 @@ from pikepdf import (
     Stream,
     UnsupportedImageTypeError,
 )
+from pikepdf.models.image import HifiPrintImageNotTranscodableError
 from PIL import Image
 
 from ocrmypdf._concurrent import Executor, SerialExecutor
@@ -74,10 +75,15 @@ def extract_image_filter(
     """Determine if an image is extractable."""
     if image.Subtype != Name.Image:
         return None
-    if image.Length < 100:
+    if not isinstance(image.Length, int) or image.Length < 100:
         log.debug(f"xref {xref}: skipping image with small stream size")
         return None
-    if image.Width < 8 or image.Height < 8:  # Issue 732
+    if (
+        not isinstance(image.Width, int)
+        or not isinstance(image.Height, int)
+        or image.Width < 8
+        or image.Height < 8
+    ):  # Issue 732
         log.debug(f"xref {xref}: skipping image with unusually small dimensions")
         return None
 
@@ -153,7 +159,10 @@ def extract_image_jbig2(
                 imgname = root / f'{xref:08d}'
                 with imgname.open('wb') as f:
                     ext = pim.extract_to(stream=f)
-                imgname.rename(imgname.with_suffix(ext))
+                # Rename the file so it has .prejbig2.ext extension
+                # Making it unique avoids problems with Windows if the
+                # same image is extracted multiple times
+                imgname.rename(imgname.with_suffix(".prejbig2" + ext))
             except NotImplementedError as e:
                 if '/Decode' in str(e):
                     log.debug(
@@ -169,7 +178,7 @@ def extract_image_jbig2(
                     pim.obj.ColorSpace = colorspace
                 else:
                     del pim.obj.ColorSpace
-            return XrefExt(xref, ext)
+            return XrefExt(xref, ".prejbig2" + ext)
     return None
 
 
@@ -200,7 +209,7 @@ def extract_image_generic(
             with imgname.open('wb') as f:
                 ext = pim.extract_to(stream=f)
             imgname.rename(imgname.with_suffix(ext))
-        except UnsupportedImageTypeError:
+        except (UnsupportedImageTypeError, HifiPrintImageNotTranscodableError):
             return None
         return XrefExt(xref, ext)
     elif (
@@ -256,6 +265,9 @@ def _find_image_xrefs_container(
     for _imname, image in dict(xobjs).items():
         if image.objgen[1] != 0:
             continue  # Ignore images in an incremental PDF
+        xref = Xref(image.objgen[0])
+        if xref in include_xrefs or xref in exclude_xrefs:
+            continue  # Already processed
         if Name.Subtype in image and image.Subtype == Name.Form:
             # Recurse into Form XObjects
             log.debug(f"Recursing into Form XObject {_imname} in page {pageno}")
@@ -269,7 +281,6 @@ def _find_image_xrefs_container(
                 depth + 1,
             )
             continue
-        xref = Xref(image.objgen[0])
         if Name.SMask in image:
             # Ignore soft masks
             smask_xref = Xref(image.SMask.objgen[0])

src/ocrmypdf/pdfinfo/info.py

@@ -12,7 +12,7 @@ import re
 import statistics
 from collections import defaultdict
 from collections.abc import Callable, Container, Iterable, Iterator, Mapping, Sequence
-from contextlib import contextmanager
+from contextlib import contextmanager, nullcontext
 from decimal import Decimal
 from enum import Enum, auto
 from functools import partial
@@ -24,6 +24,7 @@ from warnings import warn
 
 from pdfminer.layout import LTPage, LTTextBox
 from pikepdf import (
+    Dictionary,
     Matrix,
     Name,
     Object,
@@ -40,7 +41,12 @@ from ocrmypdf._concurrent import Executor, SerialExecutor
 from ocrmypdf._progressbar import ProgressBar
 from ocrmypdf.exceptions import EncryptedPdfError, InputFileError
 from ocrmypdf.helpers import Resolution, available_cpu_count, pikepdf_enable_mmap
-from ocrmypdf.pdfinfo.layout import LTStateAwareChar, get_page_analysis, get_text_boxes
+from ocrmypdf.pdfinfo.layout import (
+    LTStateAwareChar,
+    PdfMinerState,
+    get_page_analysis,
+    get_text_boxes,
+)
 
 logger = logging.getLogger()
 
@@ -239,7 +245,13 @@ def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
                 # to do. Just pretend nothing happened, keep calm and carry on.
                 warn("PDF graphics stack underflowed - PDF may be malformed")
         elif operator == 'cm':
-            ctm = Matrix(operands) @ ctm
+            try:
+                ctm = Matrix(operands) @ ctm
+            except ValueError:
+                raise InputFileError(
+                    "PDF content stream is corrupt - this PDF is malformed. "
+                    "Use a PDF editor that is capable of visually inspecting the PDF."
+                )
         elif operator == 'Do':
             image_name = operands[0]
             settings = XobjectSettings(
@@ -363,8 +375,26 @@ class ImageInfo:
             pim = PdfImage(pdfimage)
         else:
             raise ValueError("Either pdfimage or inline must be set")
+
         self._width = pim.width
         self._height = pim.height
+        if (smask := pim.obj.get(Name.SMask, None)) is not None:
+            # SMask is pretty much an alpha channel, but in PDF it's possible
+            # for channel to have different dimensions than the image
+            # itself. Some PDF writers use this to create a grayscale stencil
+            # mask. For our purposes, the effective size is the size of the
+            # larger component (image or smask).
+            if isinstance(smask, Stream | Dictionary):
+                self._width = max(smask.get(Name.Width, 0), self._width)
+                self._height = max(smask.get(Name.Height, 0), self._height)
+        if (mask := pim.obj.get(Name.Mask, None)) is not None:
+            # If the image has a /Mask entry, it has an explicit mask.
+            # /Mask can be a Stream or an Array. If it's a Stream,
+            # use its /Width and /Height if they are larger than the main
+            # image's.
+            if isinstance(mask, Stream | Dictionary):
+                self._width = max(mask.get(Name.Width, 0), self._width)
+                self._height = max(mask.get(Name.Height, 0), self._height)
 
         # If /ImageMask is true, then this image is a stencil mask
         # (Images that draw with this stencil mask will have a reference to
@@ -468,9 +498,18 @@ class ImageInfo:
     def renderable(self) -> bool:
         """Whether the image is renderable.
 
-        Some PDFs in the wild have invalid images that are not renderable.
+        Some PDFs in the wild have invalid images that are not renderable,
+        due to unusual dimensions.
+
+        Stencil masks are not also not renderable, since they are not
+        drawn, but rather they control how rendering happens.
         """
-        return self.dpi.is_finite and self.width >= 0 and self.height >= 0
+        return (
+            self.dpi.is_finite
+            and self.width >= 0
+            and self.height >= 0
+            and self.type_ != 'stencil'
+        )
 
     @property
     def dpi(self) -> Resolution:
@@ -485,7 +524,7 @@ class ImageInfo:
         """Physical area of the image in square inches."""
         if not self.renderable:
             return 0.0
-        return float(self.width * self.dpi.x * self.height * self.dpi.y)
+        return float((self.width / self.dpi.x) * (self.height / self.dpi.y))
 
     def __repr__(self):
         """Return a string representation of the image."""
@@ -567,7 +606,7 @@ def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: Content
     xobjs = resources[Name.XObject].as_dict()
     for xobj in xobjs:
         candidate = xobjs[xobj]
-        if candidate is None or candidate[Name.Subtype] != Name.Form:
+        if candidate is None or candidate.get(Name.Subtype) != Name.Form:
             continue
 
         form_xobject = candidate
@@ -668,13 +707,13 @@ def _page_has_text(text_blocks: Iterable[FloatRect], page_width, page_height) ->
 
 
 def simplify_textboxes(
-    miner: LTPage, textbox_getter: Callable[[LTPage], Iterator[LTTextBox]]
+    miner_page: LTPage, textbox_getter: Callable[[LTPage], Iterator[LTTextBox]]
 ) -> Iterator[TextboxInfo]:
     """Extract only limited content from text boxes.
 
     We do this to save memory and ensure that our objects are pickleable.
     """
-    for box in textbox_getter(miner):
+    for box in textbox_getter(miner_page):
         first_line = box._objs[0]  # pylint: disable=protected-access
         first_char = first_line._objs[0]  # pylint: disable=protected-access
         if not isinstance(first_char, LTStateAwareChar):
@@ -721,9 +760,12 @@ def _pdf_pageinfo_sync(
     infile: Path,
     check_pages: Container[int],
     detailed_analysis: bool,
+    miner_state: PdfMinerState | None,
 ) -> PageInfo:
     with _pdf_pageinfo_sync_pdf(thread_pdf, infile) as pdf:
-        return PageInfo(pdf, pageno, infile, check_pages, detailed_analysis)
+        return PageInfo(
+            pdf, pageno, infile, check_pages, detailed_analysis, miner_state
+        )
 
 
 def _pdf_pageinfo_concurrent(
@@ -735,6 +777,7 @@ def _pdf_pageinfo_concurrent(
     progbar,
     check_pages,
     detailed_analysis: bool = False,
+    miner_state: PdfMinerState | None = None,
 ) -> Sequence[PageInfo | None]:
     pages: list[PageInfo | None] = [None] * len(pdf.pages)
 
@@ -766,7 +809,8 @@ def _pdf_pageinfo_concurrent(
     initial_pdf = pdf if use_threads else None
 
     contexts = (
-        (n, initial_pdf, infile, check_pages, detailed_analysis) for n in range(total)
+        (n, initial_pdf, infile, check_pages, detailed_analysis, miner_state)
+        for n in range(total)
     )
     assert n_workers == 1 if use_threads else n_workers >= 1, "Not multithreadable"
     logger.debug(
@@ -833,12 +877,15 @@ class PageInfo:
         infile: PathLike,
         check_pages: Container[int],
         detailed_analysis: bool = False,
+        miner_state: PdfMinerState | None = None,
     ):
         """Initialize a PageInfo object."""
         self._pageno = pageno
         self._infile = infile
         self._detailed_analysis = detailed_analysis
-        self._gather_pageinfo(pdf, pageno, infile, check_pages, detailed_analysis)
+        self._gather_pageinfo(
+            pdf, pageno, infile, check_pages, detailed_analysis, miner_state
+        )
 
     def _gather_pageinfo(
         self,
@@ -847,6 +894,7 @@ class PageInfo:
         infile: PathLike,
         check_pages: Container[int],
         detailed_analysis: bool,
+        miner_state: PdfMinerState | None,
     ):
         page: Page = pdf.pages[pageno]
         mediabox = [Decimal(d) for d in page.mediabox.as_list()]
@@ -862,10 +910,11 @@ class PageInfo:
         check_this_page = pageno in check_pages
 
         if check_this_page and detailed_analysis:
-            pscript5_mode = str(pdf.docinfo.get(Name.Creator)).startswith('PScript5')
+            page_analysis = miner_state.get_page_analysis(pageno)
-            miner = get_page_analysis(infile, pageno, pscript5_mode)
+            if page_analysis is not None:
-            if miner is not None:
+                self._textboxes = list(
-                self._textboxes = list(simplify_textboxes(miner, get_text_boxes))
+                    simplify_textboxes(page_analysis, get_text_boxes)
+                )
             else:
                 self._textboxes = []
             bboxes = (box.bbox for box in self._textboxes)
@@ -1049,10 +1098,14 @@ class PageInfo:
 
         Returns None if there is no meaningful DPI for the page.
         """
-        image_dpis = [
+        image_dpis = []
-            image.dpi.to_scalar() for image in self._images if image.renderable
+        image_areas = []
-        ]
+        for image in self._images:
-        image_areas = [image.printed_area for image in self._images if image.renderable]
+            if not image.renderable:
+                continue
+            image_dpis.append(image.dpi.to_scalar())
+            image_areas.append(image.printed_area)
+
         total_drawn_area = sum(image_areas)
         if total_drawn_area == 0:
             return None
@@ -1065,7 +1118,6 @@ class PageInfo:
 
         arg_max_dpi = image_dpis.index(max_dpi)
         max_area_ratio = image_areas[arg_max_dpi] / total_drawn_area
-
         return PageResolutionProfile(
             weighted_dpi,
             max_dpi,
@@ -1115,16 +1167,26 @@ class PdfInfo:
         with Pdf.open(infile) as pdf:
             if pdf.is_encrypted:
                 raise EncryptedPdfError()  # Triggered by encryption with empty passwd
-            self._pages = _pdf_pageinfo_concurrent(
+            pscript5_mode = str(pdf.docinfo.get(Name.Creator, "")).startswith(
-                pdf,
+                'PScript5'
-                executor,
-                max_workers,
-                use_threads,
-                infile,
-                progbar,
-                check_pages=check_pages,
-                detailed_analysis=detailed_analysis,
             )
+            self._miner_state = (
+                PdfMinerState(infile, pscript5_mode)
+                if detailed_analysis
+                else nullcontext()
+            )
+            with self._miner_state as miner_state:
+                self._pages = _pdf_pageinfo_concurrent(
+                    pdf,
+                    executor,
+                    max_workers,
+                    use_threads,
+                    infile,
+                    progbar,
+                    check_pages=check_pages,
+                    detailed_analysis=detailed_analysis,
+                    miner_state=miner_state,
+                )
             self._needs_rendering = pdf.Root.get(Name.NeedsRendering, False)
             if Name.AcroForm in pdf.Root:
                 if len(pdf.Root.AcroForm.get(Name.Fields, [])) > 0:

src/ocrmypdf/pdfinfo/layout.py

@@ -17,6 +17,8 @@ import pdfminer
 import pdfminer.encodingdb
 import pdfminer.pdfdevice
 import pdfminer.pdfinterp
+import pdfminer.psparser
+from deprecation import deprecated
 from pdfminer.converter import PDFLayoutAnalyzer
 from pdfminer.layout import LAParams, LTChar, LTPage, LTTextBox
 from pdfminer.pdfcolor import PDFColorSpace
@@ -58,9 +60,10 @@ def pdfsimplefont__init__(
 
 setattr(PDFSimpleFont, '__init__', pdfsimplefont__init__)
 
-#
+# Patch pdfminer.six buffer size
-# pdfminer patches when creator is PScript5.dll
+# The parser doesn't properly handle keyword tokens are split across the end of the
-#
+# buffer, so increase the buffer size something far larger than will ever be seen.
+pdfminer.psparser.PSBaseParser.BUFSIZ = 256 * 1024 * 1024
 
 
 def pdftype3font__pscript5_get_height(self):
@@ -287,6 +290,7 @@ def patch_pdfminer(pscript5_mode: bool):
         yield
 
 
+@deprecated(deprecated_in='16.6.0', details='Use PdfMinerState instead.')
 def get_page_analysis(
     infile: PathLike, pageno: int, pscript5_mode: bool
 ) -> LTPage | None:
@@ -317,6 +321,73 @@ def get_page_analysis(
     return dev.get_result()
 
 
+class PdfMinerState:
+    """Provide a context manager for using pdfminer.six.
+
+    This ensures that the file is closed. It also provides a cache of pages
+    from the PDF so that they can be reused if needed, to improve performance.
+    """
+
+    def __init__(self, infile: Path, pscript5_mode: bool) -> None:
+        """Initialize the context manager.
+
+        Args:
+            infile: The path to the PDF file to be analyzed.
+            pscript5_mode: Whether the PDF was generated by PScript5.dll.
+        """
+        self.infile = infile
+        self.rman = pdfminer.pdfinterp.PDFResourceManager(caching=True)
+        self.disable_boxes_flow = None
+        self.page_cache: list[PDFPage] = []
+        self.pscript5_mode = pscript5_mode
+        self.file = None
+
+    def __enter__(self):
+        """Enter the context manager."""
+        self.file = Path(self.infile).open('rb')
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        """Exit the context manager."""
+        if self.file:
+            self.file.close()
+        return True
+
+    def _load_page_cache(self):
+        """Load the page cache."""
+        try:
+            self.page_cache = list(PDFPage.get_pages(self.file))
+            if not self.page_cache:
+                raise InputFileError(
+                    "pdfminer did not find any pages in the input file."
+                )
+            for n, page in enumerate(self.page_cache):
+                if page is None:
+                    raise InputFileError(
+                        f"pdfminer could not process page {n} (counting from 0)."
+                    )
+        except PDFTextExtractionNotAllowed as e:
+            raise EncryptedPdfError() from e
+
+    def get_page_analysis(self, pageno: int):
+        """Get the page analysis for a given page."""
+        if not self.page_cache:
+            self._load_page_cache()
+        page = self.page_cache[pageno]
+        dev = TextPositionTracker(
+            self.rman,
+            laparams=LAParams(
+                all_texts=True, detect_vertical=True, boxes_flow=self.disable_boxes_flow
+            ),
+        )
+        interp = pdfminer.pdfinterp.PDFPageInterpreter(self.rman, dev)
+
+        with patch_pdfminer(self.pscript5_mode):
+            interp.process_page(page)
+
+        return dev.get_result()
+
+
 def get_text_boxes(obj) -> Iterator[LTTextBox]:
     """Get the text boxes attached to the current node."""
     for child in obj:

src/ocrmypdf/subprocess/__init__.py

@@ -215,8 +215,10 @@ 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
+{required_for} arguments.  {program} {found_version} is installed.
-proceed.  For best results, install the program.
+
+If you omit these arguments, OCRmyPDF may be able to
+proceed.  For best results, update the program.
 '''
 
 OSX_INSTALL_ADVICE = '''

tests/conftest.py

@@ -24,11 +24,6 @@ def is_macos():
     return platform.system() == 'Darwin'
 
 
-def running_in_docker():
-    # Docker creates a file named /.dockerenv in all supported versions
-    return Path('/.dockerenv').exists()
-
-
 def have_unpaper():
     try:
         unpaper.version()

tests/test_completion.py

@@ -8,7 +8,7 @@ from subprocess import run
 
 import pytest
 
-from .conftest import running_in_docker
+from ocrmypdf.helpers import running_in_docker
 
 pytestmark = pytest.mark.skipif(
     running_in_docker(),

tests/test_helpers.py

@@ -13,8 +13,7 @@ import pytest
 from packaging.version import Version
 
 from ocrmypdf import helpers
-
+from ocrmypdf.helpers import running_in_docker
-from .conftest import running_in_docker
 
 needs_symlink = pytest.mark.skipif(os.name == 'nt', reason='needs posix symlink')
 windows_only = pytest.mark.skipif(os.name != 'nt', reason="Windows test")

tests/test_main.py

@@ -18,6 +18,7 @@ from PIL import Image
 import ocrmypdf
 from ocrmypdf._exec import tesseract
 from ocrmypdf.exceptions import ExitCode, MissingDependencyError
+from ocrmypdf.helpers import running_in_docker
 from ocrmypdf.pdfa import file_claims_pdfa
 from ocrmypdf.pdfinfo import Colorspace, Encoding, PdfInfo
 from ocrmypdf.subprocess import get_version
@@ -29,7 +30,6 @@ from .conftest import (
     is_macos,
     run_ocrmypdf,
     run_ocrmypdf_api,
-    running_in_docker,
 )
 
 # pylint: disable=redefined-outer-name

tests/test_pdfinfo.py

@@ -208,12 +208,13 @@ def test_pages_issue700(monkeypatch, resources):
     monkeypatch.setattr(PDFPage, 'get_pages', get_no_pages)
 
     with pytest.raises(InputFileError, match="pdfminer"):
-        pdfinfo.PdfInfo(
+        pi = pdfinfo.PdfInfo(
             resources / 'cardinal.pdf',
             detailed_analysis=True,
             progbar=False,
             max_workers=1,
         )
+        pi._miner_state.get_page_analysis(0)
 
 
 @pytest.fixture

tests/test_rotation.py

@@ -239,7 +239,9 @@ def make_rotate_test(imagefile, outdir, prefix, image_angle, page_angle):
 @pytest.mark.parametrize('image_angle', (0, 90, 180, 270))
 def test_rotate_page_level(image_angle, page_angle, resources, outdir, caplog):
     reference = make_rotate_test(resources / 'typewriter.png', outdir, 'ref', 0, 0)
-    test = make_rotate_test(resources, outdir, 'test', image_angle, page_angle)
+    test = make_rotate_test(
+        resources / 'typewriter.png', outdir, 'test', image_angle, page_angle
+    )
     out = test.with_suffix('.out.pdf')
 
     exitcode = run_ocrmypdf_api(

tests/test_semfree.py

@@ -23,4 +23,4 @@ def test_semfree(resources, outpdf):
         '--plugin',
         'tests/plugins/tesseract_noop.py',
     )
-    assert exitcode == ExitCode.ok
+    assert exitcode in (ExitCode.ok, ExitCode.pdfa_conversion_failed)

tests/test_tesseract.py

@@ -13,9 +13,9 @@ import pytest
 
 from ocrmypdf import pdfinfo
 from ocrmypdf._exec import tesseract
-from ocrmypdf.exceptions import MissingDependencyError
+from ocrmypdf.exceptions import BadArgsError, ExitCode, MissingDependencyError
 
-from .conftest import check_ocrmypdf
+from .conftest import check_ocrmypdf, run_ocrmypdf_api
 
 # pylint: disable=redefined-outer-name
 
@@ -144,3 +144,10 @@ def test_tesseract_log_output_raises(caplog):
     with pytest.raises(tesseract.TesseractConfigError):
         tesseract.tesseract_log_output(b'parameter not found: moo')
     assert 'not found' in caplog.text
+
+
+def test_blocked_language(resources, no_outpdf):
+    infile = resources / 'masks.pdf'
+    for bad_lang in ['osd', 'equ']:
+        with pytest.raises(BadArgsError):
+            run_ocrmypdf_api(infile, no_outpdf, '-l', bad_lang)

tests/test_unpaper.py

@@ -5,7 +5,7 @@ from __future__ import annotations
 
 import logging
 from os import fspath
-from unittest.mock import patch
+from unittest.mock import Mock, patch
 
 import pytest
 from packaging.version import Version
@@ -48,6 +48,19 @@ def test_old_unpaper(resources, no_outpdf):
         mock.assert_called()
 
 
+def test_unpaper_version_chatter(resources, no_outpdf):
+    input_ = fspath(resources / "c02-22.pdf")
+    output = fspath(no_outpdf)
+
+    _parser, options, pm = get_parser_options_plugins(["--clean", input_, output])
+    with patch("ocrmypdf.subprocess.run") as mock:
+        mock.return_value = Mock(stdout='Warning: using insecure memory!\n7.0.0\n')
+
+        with pytest.raises(MissingDependencyError):
+            check_options(options, pm)
+        mock.assert_called()
+
+
 @needs_unpaper
 def test_clean(resources, outpdf):
     check_ocrmypdf(