v16.9.0 release notes

Tidy whitespace
Merge pull request #1466 from 0dinD/fix-hocr-caption
2025-02-07 00:53:08 -08:00 · 2025-02-06 00:40:35 -08:00 · 2025-02-06 00:38:59 -08:00 · 2025-01-30 17:49:06 +01:00 · 2025-01-27 23:44:37 -08:00 · 2025-01-25 16:55:53 -08:00
30 changed files with 1343 additions and 226 deletions
@@ -36,7 +36,6 @@ RUN \
  && cd .. \
  && rm -rf jbig2

-COPY . /app

 WORKDIR /app

@@ -45,7 +44,19 @@ COPY --from=ghcr.io/astral-sh/uv:0.5.5 /uv /uvx /bin/

 ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy

-RUN uv sync --extra test --extra webservice --extra watcher --no-dev
+# Install the project's dependencies using the lockfile and settings
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,source=uv.lock,target=uv.lock \
+    --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
+    uv sync --frozen --no-install-project --no-dev
+
+# Then, add the rest of the project source code and install it
+# Installing separately from its dependencies allows optimal layer caching
+COPY . /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen \
+        --extra test --extra webservice --extra watcher --no-dev \
+        --no-install-package pyarrow

 FROM base

@@ -65,6 +76,7 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
  tesseract-ocr-fra \
  tesseract-ocr-por \
  tesseract-ocr-spa \
+  ttyd \
  unpaper \
  && rm -rf /var/lib/apt/lists/*

@@ -3,12 +3,11 @@

 # 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.
+# through 3.20.3. The issue is fixed in 3.21.
 # Details
 #  https://gitlab.alpinelinux.org/alpine/aports/-/issues/16143
 #  https://github.com/ocrmypdf/OCRmyPDF/issues/1395
-FROM alpine:3.19 AS base
+FROM alpine:3.21 AS base

 ENV LANG=C.UTF-8
 ENV TZ=UTC
@@ -19,22 +18,35 @@ RUN apk add --no-cache \

 FROM base AS builder

+# Yes it really is python3-dev, and py3-package
 RUN apk add --no-cache \
    ca-certificates \
    git \
    python3-dev \
+    py3-pyarrow \
    curl

-COPY . /app
-
 WORKDIR /app

 COPY --from=ghcr.io/astral-sh/uv:0.5.5 /uv /uvx /bin/

 ENV UV_COMPILE_BYTECODE=1 UV_LINK_MODE=copy

-# Instead of restarting the shell, use uv directly from its installed location.
-RUN uv sync --extra test --extra webservice --extra watcher --no-dev
+RUN uv venv --system-site-packages .venv
+
+# Install the project's dependencies using the lockfile and settings
+RUN --mount=type=cache,target=/root/.cache/uv \
+    --mount=type=bind,source=uv.lock,target=uv.lock \
+    --mount=type=bind,source=pyproject.toml,target=pyproject.toml \
+    uv sync --frozen --no-install-project --no-dev
+
+# Then, add the rest of the project source code and install it
+# Installing separately from its dependencies allows optimal layer caching
+COPY . /app
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen \
+        --extra test --extra webservice --extra watcher --no-dev \
+        --no-install-package pyarrow

 FROM base

@@ -52,6 +64,7 @@ RUN apk add --no-cache \
    tesseract-ocr-data-por \
    tesseract-ocr-data-spa \
    ttf-droid \
+    ttyd \
    unpaper \
    && rm -rf /var/cache/apk/*

@@ -40,7 +40,7 @@ jobs:
          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags

      - name: Install uv
-        uses: astral-sh/setup-uv@v4
+        uses: astral-sh/setup-uv@v5
        with:
          version: "0.5.x"

@@ -136,7 +136,7 @@ jobs:
            tesseract

      - name: Install uv
-        uses: astral-sh/setup-uv@v4
+        uses: astral-sh/setup-uv@v5
        with:
          version: "0.5.x"

@@ -186,7 +186,7 @@ jobs:
          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags

      - name: Install uv
-        uses: astral-sh/setup-uv@v4
+        uses: astral-sh/setup-uv@v5
        with:
          version: "0.5.x"

@@ -225,7 +225,7 @@ jobs:
          fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags

      - name: Install uv
-        uses: astral-sh/setup-uv@v4
+        uses: astral-sh/setup-uv@v5
        with:
          version: "0.5.x"

@@ -275,14 +275,14 @@ jobs:
      - name: Sign the dists with Sigstore
        uses: sigstore/gh-action-sigstore-python@v3.0.0
        with:
-          inputs: >-
+          inputs: |
            ./dist/*.tar.gz
            ./dist/*.whl

      - name: Create GitHub Release
        env:
          GITHUB_TOKEN: ${{ github.token }}
-        run: >-
+        run: |
          gh release create
          '${{ github.ref_name }}'
          --repo '${{ github.repository }}'
@@ -294,7 +294,7 @@ jobs:
        # Upload to GitHub Release using the `gh` CLI.
        # `dist/` contains the built packages, and the
        # sigstore-produced signatures and certificates.
-        run: >-
+        run: |
          gh release upload
          '${{ github.ref_name }}' dist/**
          --repo '${{ github.repository }}'
@@ -0,0 +1,32 @@
+# SPDX-FileCopyrightText: 2024 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+name: Remove Triage Label on Reply
+
+on:
+  issue_comment:
+    types:
+      - created
+
+jobs:
+  remove-triage-label:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Check if comment is by the repository owner
+        id: check_comment
+        run: |
+          echo "::set-output name=is_owner::$(
+            if [[ '${{ github.event.comment.user.login }}' == 'jbarlow83' ]]; then
+              echo 'true';
+            else
+              echo 'false';
+            fi
+          )"
+
+      - name: Remove 'triage' label
+        if: ${{ steps.check_comment.outputs.is_owner == 'true' }}
+        uses: actions-ecosystem/action-remove-labels@v1
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          labels: triage
@@ -11,10 +11,6 @@ version: 2
 sphinx:
  configuration: docs/conf.py

-# Optionally build your docs in additional formats such as PDF
-formats:
-  - pdf
-
 # Optionally set the version of Python and requirements required to build your docs
 build:
  os: ubuntu-22.04
@@ -244,34 +244,34 @@ As of June 2024, the Tesseract page segmentation modes are:
 +-----+----------------------------------------------------------------------------------+
 | ID  | Description                                                                      |
 +=====+==================================================================================+
-|  0  | Orientation and script detection (OSD) only.                                      |
+|  0  | Orientation and script detection (OSD) only.                                     |
 +-----+----------------------------------------------------------------------------------+
-|  1  | Automatic page segmentation with OSD.                                             |
+|  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.                                 |
+|  4  | Assume a single column of text of variable sizes.                                |
 +-----+----------------------------------------------------------------------------------+
-|  5  | Assume a single uniform block of vertically aligned text.                         |
+|  5  | Assume a single uniform block of vertically aligned text.                        |
 +-----+----------------------------------------------------------------------------------+
-|  6  | Assume a single uniform block of text.                                            |
+|  6  | Assume a single uniform block of text.                                           |
 +-----+----------------------------------------------------------------------------------+
-|  7  | Treat the image as a single text line.                                            |
+|  7  | Treat the image as a single text line.                                           |
 +-----+----------------------------------------------------------------------------------+
-|  8  | Treat the image as a single word.                                                 |
+|  8  | Treat the image as a single word.                                                |
 +-----+----------------------------------------------------------------------------------+
-|  9  | Treat the image as a single word in a circle.                                     |
+|  9  | Treat the image as a single word in a circle.                                    |
 +-----+----------------------------------------------------------------------------------+
-| 10  | Treat the image as a single character.                                            |
+| 10  | Treat the image as a single character.                                           |
 +-----+----------------------------------------------------------------------------------+
-| 11  | Sparse text. Find as much text as possible in no particular order.                |
+| 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.                                                               |
+|     | Tesseract-specific.                                                              |
 +-----+----------------------------------------------------------------------------------+

 Modes 0, 1, 2, and 12 (all of those that enable orientation and script detection)
@@ -9,27 +9,12 @@ API reference
 This page summarizes the rest of the public API. Generally speaking this
 should be mainly of interest to plugin developers.

-ocrmypdf
-========
+ocrmypdf.api
+============

-.. autoclass:: ocrmypdf.PageContext
+.. automodule:: ocrmypdf.api
    :members:

-.. autoclass:: ocrmypdf.PdfContext
-    :members:
-
-.. autoclass:: ocrmypdf.Verbosity
-    :members:
-    :undoc-members:
-
-.. autofunction:: ocrmypdf.configure_logging
-
-.. autofunction:: ocrmypdf.ocr
-
-.. autofunction:: ocrmypdf.pdf_to_hocr
-
-.. autofunction:: ocrmypdf.hocr_to_ocr_pdf
-
 ocrmypdf.exceptions
 ===================

@@ -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, ""optimize"": "3"}'``."
+    "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"

@@ -30,6 +30,8 @@
 #
 # needs_sphinx = '1.0'

+import datetime
+
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
@@ -38,6 +40,7 @@ extensions = [
    'sphinx.ext.intersphinx',
    'sphinx.ext.autosummary',
    'sphinx.ext.napoleon',
+    'sphinx.ext.imgconverter',  # PDF docs needs this for SVG to PNG conversion
    'sphinx_issues',
 ]

@@ -50,10 +53,7 @@ issues_github_path = "ocrmypdf/OCRmyPDF"
 templates_path = ['_templates']

 # The suffix(es) of source filenames.
-# You can specify multiple suffix as a list of string:
-#
-# source_suffix = ['.rst', '.md']
-source_suffix = '.rst'
+source_suffix = {'.rst': 'restructuredtext', '.md': 'markdown'}

 # The encoding of source files.
 #
@@ -64,8 +64,11 @@ master_doc = 'index'

 # General information about the project.
 project = 'ocrmypdf'
+
+year = str(datetime.date.today().year)
 copyright = (
-    '2023, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
+    f'{year}, James R. Barlow. ',
+    'Licensed under Creative Commons Attribution-ShareAlike 4.0.',
 )
 author = 'James R. Barlow'

@@ -92,6 +95,7 @@ if on_rtd:

    MOCK_MODULES = [
        'pikepdf',
+        'pikepdf.canvas',
        'pikepdf.models',
        'pikepdf.models.metadata',
    ]
@@ -108,7 +112,7 @@ version = '.'.join(release.split('.')[:2])
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = None
+language = 'en'

 # There are two options for replacing |today|: either, you set today to some
 # non-false value, then it is used:
@@ -158,19 +162,18 @@ todo_include_todos = False

 # -- Options for HTML output ----------------------------------------------

-import sphinx_rtd_theme
+import sphinx_rtd_theme  # noqa: F401

 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
 html_theme = 'sphinx_rtd_theme'
-html_theme_path = [sphinx_rtd_theme.get_html_theme_path()]

 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
 # documentation.
 #
-html_theme_options = {'display_version': False}
+html_theme_options = {}

 # Add any paths that contain custom themes here, relative to this directory.
 # html_theme_path = []
@@ -198,7 +201,7 @@ html_theme_options = {'display_version': False}
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+# html_static_path = ['_static']

 # Add any extra paths that contain custom files (such as robots.txt or
 # .htaccess) here, relative to this directory. These files are copied
@@ -35,7 +35,7 @@ execute the image:
   docker run hello-world

 .. list-table:: Docker images
-   :width: 30 20 50
+   :widths: 30 20 50
   :header-rows: 1

   * - Image
@@ -37,8 +37,6 @@ For all other platforms, you would need to build the JBIG2 encoder from source:
   ./configure && make
   [sudo] make install

-.. _jbig2-lossy:
-
 Dependencies include libtoolize and libleptonica, which on Ubuntu systems
 are packaged as libtool and libleptonica-dev. On Fedora (35) they are packaged
 as libtool and leptonica-devel. For this to work, please make sure to install
@@ -48,8 +46,8 @@ installed.
 .. code-block:: bash

    [sudo] apt install autotools-dev automake libtool libleptonica-dev
-..

+.. _jbig2-lossy:

 Lossy mode JBIG2
 ================
@@ -68,8 +68,8 @@ 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
------
+Arch Linux
+----------

 .. code-block:: bash

@@ -14,8 +14,8 @@ perform other possible optimizations such as deduplicating resources,
 consolidating fonts, simplifying vector drawings, or anything of that nature.

 .. list-table:: Title
-   :widths: 33 6 60
-   :header-rows: 1
+    :widths: 33 6 60
+    :header-rows: 1

    * - Optimization level
      - Shorthand
@@ -2,6 +2,8 @@
 ..
 .. SPDX-License-Identifier: CC-BY-SA-4.0

+.. _security:
+
 ===================
 PDF security issues
 ===================
@@ -30,6 +30,31 @@ OCRmyPDF typically supports the three most recent Python versions.

 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg

+v16.9.0
+=======
+
+-  Added hocr caption processing. Thanks @0dinD :issue:`1466`
+-  ocrmypdf-alpine Docker image is now built with Alpine 3.21.
+-  Fixed error handling of PDFs that contain invalid images with both ImageMask
+   and ColorSpace defined. :issue:`1453`
+-  Fixed test suite regression when only older Ghostscripts are installed.
+-  Improved documetnation of _progressbar.py. Thanks @QuentinFuxa. :issue:`1456`
+-  Disabling building of documentation as PDF on ReadTheDocs, as this caused
+   complex build issues deemed not worth solving.
+
+v16.8.0
+=======
+
+-  Upgraded webservice.py demonstration using streamlit. It's now possible to
+   exercise most of OCRmyPDF's functionality in a simple web UI.
+-  Added cache to Dockerfiles to improve build speed.
+-  Fixed numerous formatting errors in the documentation that prevented some
+   parts of documentation from generating correctly.
+-  Improved OCR text rendering by suppressing negative-width spaces. Thanks
+   @pajowu. :issue:`1446`
+-  Improved detecting of invisible text when using `--redo-ocr`. Thanks
+   @pajowu. :issue:`1448``
+
 v16.7.0
 =======

@@ -0,0 +1,251 @@
+# SPDX-FileCopyrightText: 2025 James R. Barlow
+# SPDX-License-Identifier: AGPL-3.0-or-later
+
+"""This is a simple web service/HTTP wrapper for OCRmyPDF.
+
+This may be more convenient than the command line tool for some Docker users.
+Note that OCRmyPDF uses Ghostscript, which is licensed under AGPLv3+. While
+OCRmyPDF is under GPLv3, this file is distributed under the Affero GPLv3+ license,
+to emphasize that SaaS deployments should make sure they comply with
+Ghostscript's license as well as OCRmyPDF's.
+"""
+
+from __future__ import annotations
+
+import os
+import subprocess
+import sys
+import time
+import urllib
+from functools import partial
+from operator import getitem
+from pathlib import Path
+from shutil import which
+from tempfile import NamedTemporaryFile
+
+import pikepdf
+import streamlit as st
+from port_for import get_port
+from streamlit.components.v1 import iframe
+
+from ocrmypdf._defaults import DEFAULT_ROTATE_PAGES_THRESHOLD
+
+
+def get_host_url_with_port(port: int) -> str:
+    """Get the host URL for the web service. Hacky."""
+    host_url = st.context.headers["host"]
+    try:
+        host, _streamlit_port = host_url.split(":", maxsplit=1)
+    except ValueError:
+        host = host_url
+    return f"//{host}:{port}"  # Use the same protocol
+
+
+st.title("OCRmyPDF Web Service")
+
+if not which("ttyd"):
+    st.error("Missing dependency: ttyd. Please install ttyd to the local environment.")
+    sys.exit(1)
+
+uploaded = st.file_uploader("Upload input PDF or image", type=["pdf"], key="file")
+
+mode = st.selectbox("Mode", options=["normal", "skip-text", "force-ocr", "redo-ocr"])
+
+with st.expander("Input options"):
+    invalidate_digital_signatures = st.checkbox(
+        "Invalidate digital signatures", value=False
+    )
+    language = st.selectbox("Language", options=["eng", "deu", "fra", "spa"])
+
+    image_dpi = st.slider(
+        "Image DPI", value=300, key="image_dpi", min_value=1, max_value=5000, step=50
+    )
+with st.expander("Preprocessing"):
+    skip_big = st.checkbox("Skip OCR on big pages", value=False, key="skip_big")
+    oversample = st.slider("Oversample", min_value=0, max_value=5000, value=0, step=50)
+    rotate_pages = st.checkbox("Rotate pages", value=False, key="rotate")
+    deskew = st.checkbox("Deskew pages", value=False, key="deskew")
+    clean = st.checkbox("Clean pages before OCR", value=False, key="clean")
+    clean_final = st.checkbox("Clean final", value=False, key="clean_final")
+    remove_vectors = st.checkbox("Remove vectors", value=False, key="remove_vectors")
+
+
+with st.expander("Output options"):
+    output_type = st.selectbox(
+        "Output type", options=["pdfa", "pdfa", "pdfa-1", "pdfa-2", "pdfa-3", "none"]
+    )
+
+    pdf_renderer = st.selectbox(
+        "PDF rendereer", options=["auto", "hocr", "hocrdebug", "sandwich"]
+    )
+
+    optimize = st.selectbox("Optimize", options=["0", "1", "2", "3"])
+
+    st.selectbox("PDF/A compression", options=["auto", "jpeg", "lossless"])
+
+with st.expander("Metadata"):
+    title = author = keywords = subject = None
+    if uploaded:
+        with pikepdf.open(uploaded) as pdf, pdf.open_metadata() as meta:
+            st.code(str(meta), language="xml")
+            title = st.text_input("Title", value=meta.get('dc:title', ''))
+            author = st.text_input("Author", value=meta.get('dc:creator', ''))
+            keywords = st.text_input("Keywords", value=meta.get('dc:subject', ''))
+            subject = st.text_input("Subject", value=meta.get('dc:description', ''))
+
+
+with st.expander("Optimization after OCR"):
+    jpeg_quality = st.slider(
+        "JPEG quality", min_value=0, max_value=100, value=75, key="jpeg_quality"
+    )
+    png_quality = st.slider(
+        "PNG quality", min_value=0, max_value=100, value=75, key="png_quality"
+    )
+    jbig2_lossy = st.checkbox("JBIG2 lossy (dangerous)", value=False, key="jbig2_lossy")
+    jbig2_threshold = st.number_input("JBIG2 threshold", value=0, key="jbig2_threshold")
+
+with st.expander("Advanced options"):
+    jobs = st.slider(
+        "Threads",
+        min_value=1,
+        max_value=os.cpu_count(),
+        value=os.cpu_count(),
+        key="threads",
+    )
+    pages = st.text_input(
+        "Pages", value="", help="Comma-separated list of pages to process"
+    )
+    max_image_mpixels = st.number_input(
+        "Max image size",
+        value=250.0,
+        min_value=0.0,
+        help="Maximum image size in megapixels",
+    )
+    rotate_pages_threshold = st.number_input(
+        "Rotate pages threshold",
+        value=DEFAULT_ROTATE_PAGES_THRESHOLD,
+        min_value=0.0,
+        max_value=1000.0,
+        help="Threshold for automatic page rotation",
+    )
+    fast_web_view = st.number_input(
+        "Fast web view",
+        value=1.0,
+        min_value=0.0,
+        help="Linearize files above this size in MB",
+    )
+    continue_on_soft_render_error = st.checkbox(
+        "Continue on soft render error", value=True
+    )
+    verbose_labels = ["quiet", "default", "debug", "debug_all"]
+    verbose = st.selectbox(
+        "Verbosity level",
+        options=[-1, 0, 1, 2],
+        index=1,
+        format_func=partial(getitem, verbose_labels),
+    )
+
+if uploaded:
+    args = []
+    if mode and mode != 'normal':
+        args.append(f"--{mode}")
+    if language:
+        args.append(f"--language={language}")
+    if not uploaded.name.lower().endswith(".pdf") and image_dpi:
+        args.append(f"--image-dpi={image_dpi}")
+    if skip_big:
+        args.append("--skip-big")
+    if oversample:
+        args.append(f"--oversample={oversample}")
+    if rotate_pages:
+        args.append("--rotate-pages")
+    if deskew:
+        args.append("--deskew")
+    if clean:
+        args.append("--clean")
+    if clean_final:
+        args.append("--clean-final")
+    if remove_vectors:
+        args.append("--remove-vectors")
+    if output_type:
+        args.append(f"--output-type={output_type}")
+    if pdf_renderer:
+        args.append(f"--pdf-renderer={pdf_renderer}")
+    if optimize:
+        args.append(f"--optimize={optimize}")
+    if title:
+        args.append(f"--title={title}")
+    if author:
+        args.append(f"--author={author}")
+    if keywords:
+        args.append(f"--keywords={keywords}")
+    if subject:
+        args.append(f"--subject={subject}")
+    if pages:
+        args.append(f"--pages={pages}")
+    if max_image_mpixels:
+        args.append(f"--max-image-mpixels={max_image_mpixels}")
+    if rotate_pages_threshold:
+        args.append(f"--rotate-pages-threshold={rotate_pages_threshold}")
+    if fast_web_view:
+        args.append(f"--fast-web-view={fast_web_view}")
+    if continue_on_soft_render_error:
+        args.append("--continue-on-soft-render-error")
+    if verbose:
+        args.append(f"--verbose={verbose}")
+    if optimize > '0' and jpeg_quality:
+        args.append(f"--jpeg-quality={jpeg_quality}")
+    if optimize > '0' and png_quality:
+        args.append(f"--png-quality={png_quality}")
+    if jbig2_lossy:
+        args.append("--jbig2-lossy")
+    if jbig2_threshold:
+        args.append(f"--jbig2-threshold={jbig2_threshold}")
+    if jobs:
+        args.append(f"--jobs={jobs}")
+    input_file = NamedTemporaryFile(delete=True, suffix=f"_{uploaded.name}")
+    input_file.write(uploaded.getvalue())
+    input_file.flush()
+    input_file.seek(0)
+    args.append(str(input_file.name))
+    output_file = NamedTemporaryFile(delete=True, suffix=".pdf")
+    args.append(str(output_file.name))
+
+    st.session_state['running'] = (
+        'run_button' in st.session_state and st.session_state.run_button
+    )
+    if st.button(
+        "Run OCRmyPDF",
+        disabled=st.session_state.get("running", False),
+        key='run_button',
+    ):
+        st.session_state['running'] = True
+        args = [sys.executable, '-m', "ocrmypdf"] + args
+        cmdline = " ".join(args)
+        st.code(cmdline, language="bash")
+
+        port = get_port((5000, 7000))
+        ttyd_args = ['ttyd', '--port', str(port), '--once', '--readonly']
+
+        ttyd_proc = subprocess.Popen(
+            ttyd_args + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE
+        )
+        iframe(src=get_host_url_with_port(port), height=400)
+
+        while ttyd_proc.poll() is None:
+            ttyd_proc.poll()
+            time.sleep(1)
+
+        if ttyd_proc.returncode == 0:
+            if Path(output_file.name).stat().st_size == 0:
+                st.error("No output PDF file was generated")
+            else:
+                st.download_button(
+                    label="Download output PDF",
+                    data=input_file.read(),
+                    file_name=uploaded.name,
+                    mime="application/pdf",
+                )
+        else:
+            st.error(f"ttyd failed with exit code {ttyd_proc.returncode}")
+        st.session_state['running'] = False
@@ -0,0 +1,123 @@
+# SPDX-FileCopyrightText: 2025 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""Run OCRmyPDF on the same PDF with different options."""
+
+from __future__ import annotations
+
+import os
+import shlex
+from io import BytesIO
+from pathlib import Path
+from subprocess import check_output, run
+from tempfile import TemporaryDirectory
+
+import pikepdf
+import pymupdf
+import streamlit as st
+from lxml import etree
+from streamlit_pdf_viewer import pdf_viewer
+
+
+def main():
+    st.set_page_config(layout="wide")
+
+    st.title("OCRmyPDF Compare")
+    st.write("Run OCRmyPDF on the same PDF with different options.")
+
+    uploaded_pdf = st.file_uploader("Upload a PDF", type=["pdf"])
+    if uploaded_pdf is None:
+        return
+
+    pdf_bytes = uploaded_pdf.read()
+
+    with pikepdf.open(BytesIO(pdf_bytes)) as p, TemporaryDirectory() as d:
+        with st.expander("PDF Metadata"):
+            with p.open_metadata() as meta:
+                xml_txt = str(meta)
+                parser = etree.XMLParser(remove_blank_text=True)
+                tree = etree.fromstring(xml_txt, parser=parser)
+                st.code(
+                    etree.tostring(tree, pretty_print=True).decode("utf-8"),
+                    language="xml",
+                )
+            st.write(p.docinfo)
+            st.write("Number of pages:", len(p.pages))
+
+        col1, col2 = st.columns(2)
+        with col1:
+            cli1 = st.text_area(
+                "Command line arguments for A",
+                key="args1",
+                value="ocrmypdf {in_} {out}",
+            )
+            env1 = st.text_area("Environment variables for A", key="env1")
+            args1 = shlex.split(
+                cli1.format(
+                    in_=os.path.join(d, "input.pdf"),
+                    out=os.path.join(d, "output1.pdf"),
+                )
+            )
+            st.code(shlex.join(args1))
+        with col2:
+            cli2 = st.text_area(
+                "Command line arguments for B",
+                key="args2",
+                value="ocrmypdf {in_} {out}",
+            )
+            env2 = st.text_area("Environment variables for B", key="env2")
+            args2 = shlex.split(
+                cli2.format(
+                    in_=os.path.join(d, "input.pdf"),
+                    out=os.path.join(d, "output2.pdf"),
+                )
+            )
+            st.code(shlex.join(args2))
+
+        if not st.button("Execute and Compare"):
+            return
+        with st.spinner("Executing..."):
+            Path(d, "input.pdf").write_bytes(pdf_bytes)
+            run(args1, env=dict(os.environ, **eval(env1 or "{}")))
+            run(args2, env=dict(os.environ, **eval(env2 or "{}")))
+
+            col1, col2 = st.columns(2)
+            with col1:
+                st.text(
+                    "Ghostscript version A: "
+                    + check_output(
+                        ["gs", "--version"],
+                        env=dict(os.environ, **eval(env1 or "{}")),
+                        text=True,
+                    )
+                )
+            with col2:
+                st.text(
+                    "Ghostscript version B: "
+                    + check_output(
+                        ["gs", "--version"],
+                        env=dict(os.environ, **eval(env2 or "{}")),
+                        text=True,
+                    )
+                )
+
+            doc1 = pymupdf.open(os.path.join(d, "output1.pdf"))
+            doc2 = pymupdf.open(os.path.join(d, "output2.pdf"))
+            for i, page1_2 in enumerate(zip(doc1, doc2)):
+                st.write(f"Page {i+1}")
+                page1, page2 = page1_2
+                col1, col2 = st.columns(2)
+                with col1, st.container(border=True):
+                    st.write(page1.get_text())
+                with col2, st.container(border=True):
+                    st.write(page2.get_text())
+
+            col1, col2 = st.columns(2)
+            with col1, st.expander("PDF Viewer"):
+                pdf_viewer(Path(d, "output1.pdf"))
+            with col2, st.expander("PDF Viewer"):
+                pdf_viewer(Path(d, "output2.pdf"))
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,83 @@
+# SPDX-FileCopyrightText: 2025 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+"""Compare two PDFs."""
+
+from __future__ import annotations
+
+import os
+from io import BytesIO
+from pathlib import Path
+from tempfile import TemporaryDirectory
+
+import pikepdf
+import pymupdf
+import streamlit as st
+from lxml import etree
+from streamlit_pdf_viewer import pdf_viewer
+
+
+def do_metadata(pdf):
+    with pikepdf.open(pdf) as pdf:
+        with pdf.open_metadata() as meta:
+            xml_txt = str(meta)
+            parser = etree.XMLParser(remove_blank_text=True)
+            tree = etree.fromstring(xml_txt, parser=parser)
+            st.code(
+                etree.tostring(tree, pretty_print=True).decode("utf-8"),
+                language="xml",
+            )
+        st.write(pdf.docinfo)
+        st.write("Number of pages:", len(pdf.pages))
+
+
+def main():
+    st.set_page_config(layout="wide")
+
+    st.title("PDF Compare")
+    st.write("Compare two PDFs.")
+
+    col1, col2 = st.columns(2)
+    with col1:
+        uploaded_pdf1 = st.file_uploader("Upload a PDF", type=["pdf"], key='pdf1')
+    with col2:
+        uploaded_pdf2 = st.file_uploader("Upload a PDF", type=["pdf"], key='pdf2')
+    if uploaded_pdf1 is None or uploaded_pdf2 is None:
+        return
+
+    pdf_bytes1 = uploaded_pdf1.getvalue()
+    pdf_bytes2 = uploaded_pdf2.getvalue()
+
+    with st.expander("PDF Metadata"):
+        col1, col2 = st.columns(2)
+        with col1:
+            do_metadata(BytesIO(pdf_bytes1))
+        with col2:
+            do_metadata(BytesIO(pdf_bytes2))
+
+    with TemporaryDirectory() as d:
+        Path(d, "1.pdf").write_bytes(pdf_bytes1)
+        Path(d, "2.pdf").write_bytes(pdf_bytes2)
+
+        with st.expander("Text"):
+            doc1 = pymupdf.open(os.path.join(d, "1.pdf"))
+            doc2 = pymupdf.open(os.path.join(d, "2.pdf"))
+            for i, page1_2 in enumerate(zip(doc1, doc2)):
+                st.write(f"Page {i+1}")
+                page1, page2 = page1_2
+                col1, col2 = st.columns(2)
+                with col1, st.container(border=True):
+                    st.write(page1.get_text())
+                with col2, st.container(border=True):
+                    st.write(page2.get_text())
+
+        with st.expander("PDF Viewer"):
+            col1, col2 = st.columns(2)
+            with col1:
+                pdf_viewer(Path(d, "1.pdf"), key='pdf_viewer1', render_text=True)
+            with col2:
+                pdf_viewer(Path(d, "2.pdf"), key='pdf_viewer2', render_text=True)
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,46 @@
+# SPDX-FileCopyrightText: 2025 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""Compare text in PDFs."""
+
+from __future__ import annotations
+
+from subprocess import run
+from tempfile import NamedTemporaryFile
+from typing import Annotated
+
+import typer
+
+
+def main(
+    pdf1: Annotated[typer.FileBinaryRead, typer.Argument()],
+    pdf2: Annotated[typer.FileBinaryRead, typer.Argument()],
+    engine: Annotated[str, typer.Option()] = 'pdftotext',
+):
+    """Compare text in PDFs."""
+
+    text1 = run(
+        ['pdftotext', '-layout', '-', '-'], stdin=pdf1, capture_output=True, check=True
+    )
+    text2 = run(
+        ['pdftotext', '-layout', '-', '-'], stdin=pdf2, capture_output=True, check=True
+    )
+
+    with NamedTemporaryFile() as f1, NamedTemporaryFile() as f2:
+        f1.write(text1.stdout)
+        f1.flush()
+        f2.write(text2.stdout)
+        f2.flush()
+        diff = run(
+            ['diff', '--color=always', '--side-by-side', f1.name, f2.name],
+            capture_output=True,
+        )
+        run(['less', '-R'], input=diff.stdout, check=True)
+        if text1.stdout.strip() != text2.stdout.strip():
+            return 1
+
+    return 0
+
+
+if __name__ == '__main__':
+    typer.run(main)
@@ -1,107 +1,29 @@
-#!/usr/bin/env python3
-# SPDX-FileCopyrightText: 2019 James R. Barlow
+#!/usr/bin/env python
+# SPDX-FileCopyrightText: 2025 James R. Barlow
 # SPDX-License-Identifier: AGPL-3.0-or-later

-"""This is a simple web service/HTTP wrapper for OCRmyPDF.
-
-This may be more convenient than the command line tool for some Docker users.
-Note that OCRmyPDF uses Ghostscript, which is licensed under AGPLv3+. While
-OCRmyPDF is under GPLv3, this file is distributed under the Affero GPLv3+ license,
-to emphasize that SaaS deployments should make sure they comply with
-Ghostscript's license as well as OCRmyPDF's.
-"""
-
-from __future__ import annotations
+"""Run the OCRmyPDF web service."""

 import os
-import shlex
-from subprocess import run
-from tempfile import TemporaryDirectory
+import sys

-from flask import Flask, Response, request, send_from_directory
-from werkzeug.utils import secure_filename
+try:
+    import streamlit  # noqa: F401
+except ImportError:
+    raise ImportError(
+        'You need to install streamlit in the Python environment '
+        'to run the web service.\n'
+    )

-app = Flask(__name__)
-app.secret_key = "secret"
-app.config['MAX_CONTENT_LENGTH'] = 50_000_000
-app.config.from_envvar("OCRMYPDF_WEBSERVICE_SETTINGS", silent=True)
-
-ALLOWED_EXTENSIONS = {"pdf"}
-
-
-def allowed_file(filename):
-    return "." in filename and filename.rsplit(".", 1)[1].lower() in ALLOWED_EXTENSIONS
-
-
-def do_ocrmypdf(file):
-    uploaddir = TemporaryDirectory(prefix="ocrmypdf-upload")
-    downloaddir = TemporaryDirectory(prefix="ocrmypdf-download")
-
-    filename = secure_filename(file.filename)
-    up_file = os.path.join(uploaddir.name, filename)
-    file.save(up_file)
-
-    down_file = os.path.join(downloaddir.name, filename)
-
-    cmd_args = [arg for arg in shlex.split(request.form["params"])]
-    if "--sidecar" in cmd_args:
-        return Response("--sidecar not supported", 501, mimetype='text/plain')
-
-    ocrmypdf_args = ["ocrmypdf", *cmd_args, up_file, down_file]
-    proc = run(ocrmypdf_args, capture_output=True, encoding="utf-8", check=False)
-    if proc.returncode != 0:
-        stderr = proc.stderr
-        return Response(stderr, 400, mimetype='text/plain')
-
-    return send_from_directory(downloaddir.name, filename)
-
-
-@app.route("/", methods=["GET", "POST"])
-def upload_file():
-    if request.method == "POST":
-        if "file" not in request.files:
-            return Response("No file in POST", 400, mimetype='text/plain')
-        file = request.files["file"]
-        if file.filename == "":
-            return Response("Empty filename", 400, mimetype='text/plain')
-        if not allowed_file(file.filename):
-            return Response("Invalid filename", 400, mimetype='text/plain')
-        if file and allowed_file(file.filename):
-            return do_ocrmypdf(file)
-        return Response("Some other problem", 400, mimetype='text/plain')
-
-    return """
-    <!doctype html>
-    <title>OCRmyPDF webservice</title>
-    <h1>Upload a PDF (debug UI)</h1>
-    <form method=post enctype=multipart/form-data>
-      <label for="args">Command line parameters</label>
-      <input type=textbox name=params>
-      <label for="file">File to upload</label>
-      <input type=file name=file>
-      <input type=submit value=Upload>
-    </form>
-    <h4>Notice</h2>
-    <div style="font-size: 70%; max-width: 34em;">
-    <p>This is a webservice wrapper for OCRmyPDF.</p>
-    <p>Copyright 2019 James R. Barlow</p>
-    <p>This program is free software: you can redistribute it and/or modify
-    it under the terms of the GNU Affero General Public License as published by
-    the Free Software Foundation, either version 3 of the License, or
-    (at your option) any later version.
-    </p>
-    <p>This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-    </p>
-    <p>
-    You should have received a copy of the GNU Affero General Public License
-    along with this program.  If not, see &lt;http://www.gnu.org/licenses/&gt;.
-    </p>
-    </div>
-    """
-
-
-if __name__ == "__main__":
-    app.run(host='0.0.0.0', port=5000)
+if __name__ == '__main__':
+    os.execvp(
+        sys.executable,
+        [
+            sys.executable,
+            '-m',
+            'streamlit',
+            'run',
+            'misc/_webservice.py',
+            *sys.argv[1:],
+        ],
+    )
@@ -63,7 +63,10 @@ test = [
  "types-humanfriendly",
 ]
 watcher = ["watchdog>=1.0.2", "typer-slim[standard]", "python-dotenv"]
-webservice = ["Flask>=2.0.1"]
+webservice = [
+    "port-for>=0.7.4",
+    "streamlit>=1.41.0",
+]

 [project.scripts]
 ocrmypdf = "ocrmypdf.__main__:run"
@@ -160,4 +163,5 @@ dev = [
  "pymupdf>=1.24.14",
  "streamlit-pdf-viewer>=0.0.19",
  "streamlit>=1.40.2",
+  "ipykernel>=6.29.5",
 ]
@@ -17,7 +17,11 @@ from subprocess import PIPE, CalledProcessError
 from packaging.version import Version
 from PIL import Image, UnidentifiedImageError

-from ocrmypdf.exceptions import ColorConversionNeededError, SubprocessOutputError
+from ocrmypdf.exceptions import (
+    ColorConversionNeededError,
+    InputFileError,
+    SubprocessOutputError,
+)
 from ocrmypdf.helpers import Resolution
 from ocrmypdf.subprocess import get_version, run, run_polling_stderr

@@ -111,7 +115,6 @@ def rasterize_pdf(
    args_gs = (
        [
            GS,
-            '-dQUIET',
            '-dSAFER',
            '-dBATCH',
            '-dNOPAUSE',
@@ -143,6 +146,14 @@ def rasterize_pdf(
    stderr = p.stderr.decode(errors='replace')
    if _gs_error_reported(stderr):
        log.error(stderr)
+        if stop_on_error and "recoverable image error" in stderr:
+            Path(output_file).unlink(missing_ok=True)
+            raise InputFileError(
+                "Ghostscript rasterizing failed. The input file contains errors that "
+                "cause PDF viewers to interpret it differently and incorrectly. "
+                "Try using --continue-on-soft-render-error and manually inspect the "
+                "input and output files to check for visual differences or errors."
+            )

    try:
        with Image.open(output_file) as im:
@@ -61,19 +61,31 @@ def strip_invisible_text(pdf: Pdf, page: Page):
    stream = []
    in_text_obj = False
    render_mode = 0
+    render_mode_stack = []
    text_objects = []

    for operands, operator in parse_content_stream(page, ''):
+        if operator == Operator('Tr'):
+            render_mode = operands[0]
+
+        if operator == Operator('q'):
+            render_mode_stack.append(render_mode)
+
+        if operator == Operator('Q'):
+            try:
+                render_mode = render_mode_stack.pop()
+            except IndexError:
+                # Stack underflow: content stream is malformed
+                # but try to carry on
+                pass
+
        if not in_text_obj:
            if operator == Operator('BT'):
                in_text_obj = True
-                render_mode = 0
                text_objects.append((operands, operator))
            else:
                stream.append((operands, operator))
        else:
-            if operator == Operator('Tr'):
-                render_mode = operands[0]
            text_objects.append((operands, operator))
            if operator == Operator('ET'):
                in_text_obj = False
@@ -79,6 +79,14 @@ def triage_image_file(input_file: Path, output_file: Path, options) -> None:
    except OSError as e:
        # Recover the original filename
        log.error(str(e).replace(str(input_file), str(options.input_file)))
+        if not input_file.exists():
+            log.error("Input file does not exist: %s", input_file)
+        if input_file.is_dir():
+            log.error("Input file is a directory: %s", input_file)
+        if input_file.is_file():
+            log.error("Input file is a file: %s", input_file)
+        if input_file.stat().st_size == 0:
+            log.error("Input file is empty: %s", input_file)
        raise UnsupportedImageFormatError() from e

    with im:
@@ -32,12 +32,76 @@ class ProgressBar(Protocol):
    The progress bar is held in the main process/thread and not updated by child
    process/threads. When a child notifies the parent of completed work, the
    parent updates the progress bar.
-
    Progress bars should never write to ``sys.stdout``, or they will corrupt the
    output if OCRmyPDF writes a PDF to standard output.

-    The type of events that OCRmyPDF reports to a progress bar may change in
+    Note:
+        The type of events that OCRmyPDF reports to a progress bar may change in
    minor releases.
+
+    Args:
+        total (int | float | None):
+            The total number of work units expected. If ``None``, the total is unknown.
+            For example, if you are processing pages, this might be the number of pages,
+            or if you are measuring overall progress in percent, this might be 100.
+        desc (str | None):
+            A brief description of the current step (e.g. "Scanning contents",
+            "OCR", "PDF/A conversion"). OCRmyPDF updates this before each major step.
+        unit (str | None):
+            A short label for the type of work being tracked (e.g. "page", "%", "image").
+        disable (bool):
+            If ``True``, progress updates are suppressed (no output). Defaults to ``False``.
+        **kwargs:
+            Future or extra parameters that OCRmyPDF might pass. Implementations
+            should accept and ignore unrecognized keywords gracefully.
+
+    Example:
+        A simple plugin implementation could look like this:
+
+        .. code-block:: python
+
+            from ocrmypdf.pluginspec import ProgressBar
+            from ocrmypdf import hookimpl
+
+            class ConsoleProgressBar(ProgressBar):
+                def __init__(self, *, total=None, desc=None, unit=None, disable=False, **kwargs):
+                    self.total = total
+                    self.desc = desc
+                    self.unit = unit
+                    self.disable = disable
+                    self.current = 0
+
+                def __enter__(self):
+                    if not self.disable:
+                        print(f"Starting {self.desc or 'an OCR task'} (total={self.total} {self.unit})")
+                    return self
+
+                def __exit__(self, exc_type, exc_value, traceback):
+                    if not self.disable:
+                        if exc_type is None:
+                            print("Completed successfully.")
+                        else:
+                            print(f"Task ended with error: {exc_value}")
+                    return False  # Let OCRmyPDF raise any exceptions
+
+                def update(self, n=1, *, completed=None):
+                    if completed is not None:
+                        # If 'completed' is given, you could set self.current = completed
+                        # but let's just read it to show usage
+                        print(f"Absolute completion reported: {completed}")
+                    # Otherwise, we increment by 'n'
+                    self.current += n
+                    if not self.disable:
+                        if self.total:
+                            percent = (self.current / self.total) * 100
+                            print(f"{self.desc}: {self.current}/{self.total} ({percent:.1f}%)")
+                        else:
+                            print(f"{self.desc}: {self.current} units done")
+
+            @hookimpl
+            def get_progressbar_class():
+                return MyProgressBar
+
    """

    def __init__(
@@ -51,13 +115,22 @@ class ProgressBar(Protocol):
    ):
        """Initialize a progress bar.

-        *total* indicates the total number of work units. If None, the total
-        number of work units is unknown. If *disable* is True, the progress bar
-        should be disabled. *unit* is a description of the work unit.
-        *desc* is a description of the overall task to be performed.
+        This is called once before any work is done. OCRmyPDF supplies the total
+        number of units (or None if unknown), a description of the work, and the
+        type of units. The ``disable`` parameter can be used to turn off progress
+        reporting. Unrecognized keyword arguments should be ignored.

-        Unrecognized keyword arguments must be ignored, as the list of keyword
-        arguments may grow with time.
+        Args:
+            total (int | float | None):
+                The total amount of work. If ``None``, the total is unknown.
+            desc (str | None):
+                A description of the current task. May change for different stages.
+            unit (str | None):
+                A short label for the unit of work.
+            disable (bool):
+                If ``True``, no output or logging should be displayed.
+            **kwargs:
+                Extra parameters that may be passed by OCRmyPDF in future versions.
        """

    def __enter__(self):
@@ -66,10 +139,32 @@ class ProgressBar(Protocol):
    def __exit__(self, *args):
        """Exit a progress bar context."""

-    def update(self, n=1, *, completed=None):
-        """Update the progress bar by an increment.
+    def update(self, n: float = 1, *, completed: float | None = None):
+        """Increment the progress bar by ``n`` units, or set an absolute completion.

-        For use within a progress bar context.
+        OCRmyPDF calls this method repeatedly while processing pages or other tasks.
+        If your total is known and you track it, you might do something like:
+
+        .. code-block:: python
+
+            self.current += n
+            percent = (self.current / total) * 100
+
+        The ``completed`` argument can indicate an absolute position, which is
+        particularly helpful if you're tracking a percentage of work (e.g., 0 to 100)
+        and want precise updates. In contrast, the incremental parameter ``n`` is
+        often more useful for page-based increments.
+
+        Args:
+            n (float, optional):
+                The amount to increment the progress by. Defaults to 1. May be
+                fractional if OCRmyPDF performs partial steps. If you are tracking
+                pages, this is typically how many pages have been processed in the
+                most recent step.
+            completed (float | None, optional):
+                The absolute amount of work completed so far. This can override or
+                supplement the simple increment logic. It's particularly useful
+                for percentage-based tracking (e.g., when ``total`` is 100).
        """


@@ -210,7 +210,7 @@ class HocrTransform:
                    for element in par.iterfind(self._child_xpath('span'))
                    if 'class' in element.attrib
                    and element.attrib['class']
-                    in {'ocr_header', 'ocr_line', 'ocr_textfloat'}
+                    in {'ocr_header', 'ocr_line', 'ocr_textfloat', 'ocr_caption'}
                ):
                    found_lines = True
                    direction = self._get_text_direction(par)
@@ -396,7 +396,7 @@ class HocrTransform:
        )
        if hocr_next_box is None:
            return
-        # Render a space this word and the next word. The explicit space helps
+        # Render a space between this word and the next word. The explicit space helps
        # PDF viewers identify the word break, and horizontally scaling it to
        # occupy the space the between the words helps the PDF viewer
        # avoid combiningthewordstogether.
@@ -409,7 +409,7 @@ class HocrTransform:
            space_box = Rectangle(next_box.urx, box.lly, box.llx, next_box.ury)
        self._debug_draw_space_bbox(canvas, space_box)
        space_width = self._font.text_width(' ', fontsize)
-        if space_width > 0:
+        if space_width > 0 and space_box.width > 0:
            if text_direction == TextDirection.LTR:
                text.text_transform(Matrix(1, 0, 0, -1, space_box.llx, 0))
            elif text_direction == TextDirection.RTL:
@@ -145,13 +145,15 @@ def get_progressbar_class() -> type[ProgressBar]:
    The class returned by this function must be compatible with the
    :class:`ProgressBar` protocol.

-    Here is how OCRmyPDF will use the progress bar:
-
    Example:
-        pbar_class = pm.hook.get_progressbar_class()
-        with pbar_class(**progress_kwargs) as pbar:
-            ...
-            pbar.update(1)
+        Here is how OCRmyPDF will use the progress bar:
+
+        .. code-block:: python
+
+            pbar_class = pm.hook.get_progressbar_class()
+            with pbar_class(**progress_kwargs) as pbar:
+                ... # do some work
+                pbar.update(1)
    """


@@ -11,10 +11,12 @@ from unittest.mock import patch

 import pikepdf
 import pytest
+from packaging.version import Version
 from PIL import Image, UnidentifiedImageError

+from ocrmypdf._exec import ghostscript
 from ocrmypdf._exec.ghostscript import DuplicateFilter, rasterize_pdf
-from ocrmypdf.exceptions import ColorConversionNeededError, ExitCode
+from ocrmypdf.exceptions import ColorConversionNeededError, ExitCode, InputFileError
 from ocrmypdf.helpers import Resolution

 from .conftest import check_ocrmypdf, run_ocrmypdf_api
@@ -208,3 +210,71 @@ class TestDuplicateFilter:
        assert caplog.records[1].msg == "another error message"
        assert caplog.records[2].msg == "(suppressed 5 repeated lines)"
        assert caplog.records[3].msg == "yet another error message"
+
+
+@pytest.fixture
+def pdf_with_invalid_image(outdir):
+    # issue 1451
+    Name = pikepdf.Name
+    pdf = pikepdf.new()
+    pdf.add_blank_page()
+    pdf.pages[0].Contents = pdf.make_stream(b'612 0 0 612 0 0 cm /Image Do')
+    # Create an invalid image object that has both ColorSpace and ImageMask set
+    pdf.pages[0].Resources = pikepdf.Dictionary(
+        XObject=pdf.make_indirect(
+            pikepdf.Dictionary(
+                Image=pdf.make_stream(
+                    b"\xf0\x0f" * 8,
+                    ColorSpace=Name.DeviceGray,
+                    BitsPerComponent=1,
+                    Width=8,
+                    Height=8,
+                    ImageMask=True,
+                    Subtype=Name.Image,
+                    Type=Name.XObject,
+                )
+            )
+        )
+    )
+    pdf.save(outdir / 'invalid_image.pdf')
+    pdf.save('invalid_image.pdf')
+    return outdir / 'invalid_image.pdf'
+
+
+@pytest.mark.xfail(
+    ghostscript.version() < Version('10.04.0'),
+    reason="Older Ghostscript behavior is different",
+)
+def test_recoverable_image_error(pdf_with_invalid_image, outdir, caplog):
+    # When stop_on_error is False, we expect Ghostscript to print an error
+    # but continue
+    rasterize_pdf(
+        outdir / 'invalid_image.pdf',
+        outdir / 'out.png',
+        raster_device='pngmono',
+        raster_dpi=Resolution(10, 10),
+        stop_on_error=False,
+    )
+    assert 'Image has both ImageMask and ColorSpace' in caplog.text
+
+
+@pytest.mark.xfail(
+    ghostscript.version() < Version('10.04.0'),
+    reason="Older Ghostscript behavior is different",
+)
+def test_recoverable_image_error_with_stop(pdf_with_invalid_image, outdir, caplog):
+    # When stop_on_error is True, Ghostscript will print an error and exit
+    # but still produce a viable image. We intercept this case and raise
+    # InputFileError because it will contain an image of the whole page minus
+    # the image we are rendering.
+    with pytest.raises(
+        InputFileError, match="Try using --continue-on-soft-render-error"
+    ):
+        rasterize_pdf(
+            outdir / 'invalid_image.pdf',
+            outdir / 'out.png',
+            raster_device='pngmono',
+            raster_dpi=Resolution(100, 100),
+            stop_on_error=True,
+        )
+    # out2.png will not be created; if it were it would be blank.
@@ -40,3 +40,72 @@ def test_links(resources, outpdf):
        p2 = pdf.pages[1]
        assert p1.Annots[0].A.D[0].objgen == p2.objgen
        assert p2.Annots[0].A.D[0].objgen == p1.objgen
+
+
+def test_strip_invisble_text():
+    pdf = pikepdf.Pdf.new()
+    print(pikepdf.parse_content_stream(pikepdf.Stream(pdf, b'3 Tr')))
+    page = pdf.add_blank_page()
+    visible_text = [
+        pikepdf.ContentStreamInstruction((), pikepdf.Operator('BT')),
+        pikepdf.ContentStreamInstruction(
+            (pikepdf.Name('/F0'), 12), pikepdf.Operator('Tf')
+        ),
+        pikepdf.ContentStreamInstruction((288, 720), pikepdf.Operator('Td')),
+        pikepdf.ContentStreamInstruction(
+            (pikepdf.String('visible'),), pikepdf.Operator('Tj')
+        ),
+        pikepdf.ContentStreamInstruction((), pikepdf.Operator('ET')),
+    ]
+    invisible_text = [
+        pikepdf.ContentStreamInstruction((), pikepdf.Operator('BT')),
+        pikepdf.ContentStreamInstruction(
+            (pikepdf.Name('/F0'), 12), pikepdf.Operator('Tf')
+        ),
+        pikepdf.ContentStreamInstruction((288, 720), pikepdf.Operator('Td')),
+        pikepdf.ContentStreamInstruction(
+            (pikepdf.String('invisible'),), pikepdf.Operator('Tj')
+        ),
+        pikepdf.ContentStreamInstruction((), pikepdf.Operator('ET')),
+    ]
+    invisible_text_setting_tr = [
+        pikepdf.ContentStreamInstruction((), pikepdf.Operator('BT')),
+        pikepdf.ContentStreamInstruction([3], pikepdf.Operator('Tr')),
+        pikepdf.ContentStreamInstruction(
+            (pikepdf.Name('/F0'), 12), pikepdf.Operator('Tf')
+        ),
+        pikepdf.ContentStreamInstruction((288, 720), pikepdf.Operator('Td')),
+        pikepdf.ContentStreamInstruction(
+            (pikepdf.String('invisible'),), pikepdf.Operator('Tj')
+        ),
+        pikepdf.ContentStreamInstruction((), pikepdf.Operator('ET')),
+    ]
+    stream = [
+        pikepdf.ContentStreamInstruction([], pikepdf.Operator('q')),
+        pikepdf.ContentStreamInstruction([3], pikepdf.Operator('Tr')),
+        *invisible_text,
+        pikepdf.ContentStreamInstruction([], pikepdf.Operator('Q')),
+        *visible_text,
+        *invisible_text_setting_tr,
+        *invisible_text,
+    ]
+    content_stream = pikepdf.unparse_content_stream(stream)
+    page.Contents = pikepdf.Stream(pdf, content_stream)
+
+    def count(string, page):
+        return len(
+            [
+                True
+                for operands, operator in pikepdf.parse_content_stream(page)
+                if operator == pikepdf.Operator('Tj')
+                and operands[0] == pikepdf.String(string)
+            ]
+        )
+
+    nr_visible_pre = count('visible', page)
+    ocrmypdf._graft.strip_invisible_text(pdf, page)
+    nr_visible_post = count('visible', page)
+    assert (
+        nr_visible_pre == nr_visible_post
+    ), 'Number of visible text elements did not change'
+    assert count('invisible', page) == 0, 'No invisible elems left'
@@ -31,6 +31,24 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/aa/f3/0b6ced594e51cc95d8c1fc1640d3623770d01e4969d29c0bd09945fafefa/altair-5.5.0-py3-none-any.whl", hash = "sha256:91a310b926508d560fe0148d02a194f38b824122641ef528113d029fcd129f8c", size = 731200 },
 ]

+[[package]]
+name = "appnope"
+version = "0.1.4"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/35/5d/752690df9ef5b76e169e68d6a129fa6d08a7100ca7f754c89495db3c6019/appnope-0.1.4.tar.gz", hash = "sha256:1de3860566df9caf38f01f86f65e0e13e379af54f9e4bee1e66b48f2efffd1ee", size = 4170 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/81/29/5ecc3a15d5a33e31b26c11426c45c501e439cb865d0bff96315d86443b78/appnope-0.1.4-py2.py3-none-any.whl", hash = "sha256:502575ee11cd7a28c0205f379b525beefebab9d161b7c964670864014ed7213c", size = 4321 },
+]
+
+[[package]]
+name = "asttokens"
+version = "3.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/4a/e7/82da0a03e7ba5141f05cce0d302e6eed121ae055e0456ca228bf693984bc/asttokens-3.0.0.tar.gz", hash = "sha256:0dcd8baa8d62b0c1d118b399b2ddba3c4aff271d0d7a9e0d4c1681c79035bbc7", size = 61978 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/25/8a/c46dcc25341b5bce5472c718902eb3d38600a903b14fa6aeecef3f21a46f/asttokens-3.0.0-py3-none-any.whl", hash = "sha256:e3078351a059199dd5138cb1c706e6430c05eff2ff136af5eb4790f9d28932e2", size = 26918 },
+]
+
 [[package]]
 name = "attrs"
 version = "24.2.0"
@@ -232,6 +250,18 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335 },
 ]

+[[package]]
+name = "comm"
+version = "0.2.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "traitlets" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/e9/a8/fb783cb0abe2b5fded9f55e5703015cdf1c9c85b3669087c538dd15a6a86/comm-0.2.2.tar.gz", hash = "sha256:3fd7a84065306e07bea1773df6eb8282de51ba82f77c72f9c85716ab11fe980e", size = 6210 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e6/75/49e5bfe642f71f272236b5b2d2691cf915a7283cc0ceda56357b61daa538/comm-0.2.2-py3-none-any.whl", hash = "sha256:e6fb86cb70ff661ee8c9c14e7d36d6de3b4066f1441be4063df9c5009f0a64d3", size = 7180 },
+]
+
 [[package]]
 name = "coverage"
 version = "7.6.8"
@@ -311,7 +341,6 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/98/65/13d9e76ca19b0ba5603d71ac8424b5694415b348e719db277b5edc985ff5/cryptography-44.0.0-cp37-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:761817a3377ef15ac23cd7834715081791d4ec77f9297ee694ca1ee9c2c7e5eb", size = 3915420 },
    { url = "https://files.pythonhosted.org/packages/b1/07/40fe09ce96b91fc9276a9ad272832ead0fddedcba87f1190372af8e3039c/cryptography-44.0.0-cp37-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:3c672a53c0fb4725a29c303be906d3c1fa99c32f58abe008a82705f9ee96f40b", size = 4154498 },
    { url = "https://files.pythonhosted.org/packages/75/ea/af65619c800ec0a7e4034207aec543acdf248d9bffba0533342d1bd435e1/cryptography-44.0.0-cp37-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:4ac4c9f37eba52cb6fbeaf5b59c152ea976726b865bd4cf87883a7e7006cc543", size = 3932569 },
-    { url = "https://files.pythonhosted.org/packages/4e/d5/9cc182bf24c86f542129565976c21301d4ac397e74bf5a16e48241aab8a6/cryptography-44.0.0-cp37-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:60eb32934076fa07e4316b7b2742fa52cbb190b42c2df2863dbc4230a0a9b385", size = 4164756 },
    { url = "https://files.pythonhosted.org/packages/c7/af/d1deb0c04d59612e3d5e54203159e284d3e7a6921e565bb0eeb6269bdd8a/cryptography-44.0.0-cp37-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:ed3534eb1090483c96178fcb0f8893719d96d5274dfde98aa6add34614e97c8e", size = 4016721 },
    { url = "https://files.pythonhosted.org/packages/bd/69/7ca326c55698d0688db867795134bdfac87136b80ef373aaa42b225d6dd5/cryptography-44.0.0-cp37-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:f3f6fdfa89ee2d9d496e2c087cebef9d4fcbb0ad63c40e821b39f74bf48d9c5e", size = 4240915 },
    { url = "https://files.pythonhosted.org/packages/ef/d4/cae11bf68c0f981e0413906c6dd03ae7fa864347ed5fac40021df1ef467c/cryptography-44.0.0-cp37-abi3-win32.whl", hash = "sha256:eb33480f1bad5b78233b0ad3e1b0be21e8ef1da745d8d2aecbb20671658b9053", size = 2757925 },
@@ -322,7 +351,6 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/d0/c7/c656eb08fd22255d21bc3129625ed9cd5ee305f33752ef2278711b3fa98b/cryptography-44.0.0-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:c5eb858beed7835e5ad1faba59e865109f3e52b3783b9ac21e7e47dc5554e289", size = 3915417 },
    { url = "https://files.pythonhosted.org/packages/ef/82/72403624f197af0db6bac4e58153bc9ac0e6020e57234115db9596eee85d/cryptography-44.0.0-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:f53c2c87e0fb4b0c00fa9571082a057e37690a8f12233306161c8f4b819960b7", size = 4155160 },
    { url = "https://files.pythonhosted.org/packages/a2/cd/2f3c440913d4329ade49b146d74f2e9766422e1732613f57097fea61f344/cryptography-44.0.0-cp39-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:9e6fc8a08e116fb7c7dd1f040074c9d7b51d74a8ea40d4df2fc7aa08b76b9e6c", size = 3932331 },
-    { url = "https://files.pythonhosted.org/packages/31/d9/90409720277f88eb3ab72f9a32bfa54acdd97e94225df699e7713e850bd4/cryptography-44.0.0-cp39-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:9abcc2e083cbe8dde89124a47e5e53ec38751f0d7dfd36801008f316a127d7ba", size = 4165207 },
    { url = "https://files.pythonhosted.org/packages/7f/df/8be88797f0a1cca6e255189a57bb49237402b1880d6e8721690c5603ac23/cryptography-44.0.0-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:d2436114e46b36d00f8b72ff57e598978b37399d2786fd39793c36c6d5cb1c64", size = 4017372 },
    { url = "https://files.pythonhosted.org/packages/af/36/5ccc376f025a834e72b8e52e18746b927f34e4520487098e283a719c205e/cryptography-44.0.0-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:a01956ddfa0a6790d594f5b34fc1bfa6098aca434696a03cfdbe469b8ed79285", size = 4239657 },
    { url = "https://files.pythonhosted.org/packages/46/b0/f4f7d0d0bcfbc8dd6296c1449be326d04217c57afb8b2594f017eed95533/cryptography-44.0.0-cp39-abi3-win32.whl", hash = "sha256:eca27345e1214d1b9f9490d200f9db5a874479be914199194e746c893788d417", size = 2758672 },
@@ -335,6 +363,40 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/cc/9d/37e5da7519de7b0b070a3fedd4230fe76d50d2a21403e0f2153d70ac4163/cryptography-44.0.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:62901fb618f74d7d81bf408c8719e9ec14d863086efe4185afd07c352aee1d2c", size = 3128774 },
 ]

+[[package]]
+name = "debugpy"
+version = "1.8.11"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/bc/e7/666f4c9b0e24796af50aadc28d36d21c2e01e831a934535f956e09b3650c/debugpy-1.8.11.tar.gz", hash = "sha256:6ad2688b69235c43b020e04fecccdf6a96c8943ca9c2fb340b8adc103c655e57", size = 1640124 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/26/e6/4cf7422eaa591b4c7d6a9fde224095dac25283fdd99d90164f28714242b0/debugpy-1.8.11-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:2b26fefc4e31ff85593d68b9022e35e8925714a10ab4858fb1b577a8a48cb8cd", size = 2075100 },
+    { url = "https://files.pythonhosted.org/packages/83/3a/e163de1df5995d95760a4d748b02fbefb1c1bf19e915b664017c40435dbf/debugpy-1.8.11-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:61bc8b3b265e6949855300e84dc93d02d7a3a637f2aec6d382afd4ceb9120c9f", size = 3559724 },
+    { url = "https://files.pythonhosted.org/packages/27/6c/327e19fd1bf428a1efe1a6f97b306689c54c2cebcf871b66674ead718756/debugpy-1.8.11-cp310-cp310-win32.whl", hash = "sha256:c928bbf47f65288574b78518449edaa46c82572d340e2750889bbf8cd92f3737", size = 5178068 },
+    { url = "https://files.pythonhosted.org/packages/49/80/359ff8aa388f0bd4a48f0fa9ce3606396d576657ac149c6fba3cc7de8adb/debugpy-1.8.11-cp310-cp310-win_amd64.whl", hash = "sha256:8da1db4ca4f22583e834dcabdc7832e56fe16275253ee53ba66627b86e304da1", size = 5210109 },
+    { url = "https://files.pythonhosted.org/packages/7c/58/8e3f7ec86c1b7985a232667b5df8f3b1b1c8401028d8f4d75e025c9556cd/debugpy-1.8.11-cp311-cp311-macosx_14_0_universal2.whl", hash = "sha256:85de8474ad53ad546ff1c7c7c89230db215b9b8a02754d41cb5a76f70d0be296", size = 2173656 },
+    { url = "https://files.pythonhosted.org/packages/d2/03/95738a68ade2358e5a4d63a2fd8e7ed9ad911001cfabbbb33a7f81343945/debugpy-1.8.11-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8ffc382e4afa4aee367bf413f55ed17bd91b191dcaf979890af239dda435f2a1", size = 3132464 },
+    { url = "https://files.pythonhosted.org/packages/ca/f4/18204891ab67300950615a6ad09b9de236203a9138f52b3b596fa17628ca/debugpy-1.8.11-cp311-cp311-win32.whl", hash = "sha256:40499a9979c55f72f4eb2fc38695419546b62594f8af194b879d2a18439c97a9", size = 5103637 },
+    { url = "https://files.pythonhosted.org/packages/3b/90/3775e301cfa573b51eb8a108285681f43f5441dc4c3916feed9f386ef861/debugpy-1.8.11-cp311-cp311-win_amd64.whl", hash = "sha256:987bce16e86efa86f747d5151c54e91b3c1e36acc03ce1ddb50f9d09d16ded0e", size = 5127862 },
+    { url = "https://files.pythonhosted.org/packages/c6/ae/2cf26f3111e9d94384d9c01e9d6170188b0aeda15b60a4ac6457f7c8a26f/debugpy-1.8.11-cp312-cp312-macosx_14_0_universal2.whl", hash = "sha256:84e511a7545d11683d32cdb8f809ef63fc17ea2a00455cc62d0a4dbb4ed1c308", size = 2498756 },
+    { url = "https://files.pythonhosted.org/packages/b0/16/ec551789d547541a46831a19aa15c147741133da188e7e6acf77510545a7/debugpy-1.8.11-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ce291a5aca4985d82875d6779f61375e959208cdf09fcec40001e65fb0a54768", size = 4219136 },
+    { url = "https://files.pythonhosted.org/packages/72/6f/b2b3ce673c55f882d27a6eb04a5f0c68bcad6b742ac08a86d8392ae58030/debugpy-1.8.11-cp312-cp312-win32.whl", hash = "sha256:28e45b3f827d3bf2592f3cf7ae63282e859f3259db44ed2b129093ca0ac7940b", size = 5224440 },
+    { url = "https://files.pythonhosted.org/packages/77/09/b1f05be802c1caef5b3efc042fc6a7cadd13d8118b072afd04a9b9e91e06/debugpy-1.8.11-cp312-cp312-win_amd64.whl", hash = "sha256:44b1b8e6253bceada11f714acf4309ffb98bfa9ac55e4fce14f9e5d4484287a1", size = 5264578 },
+    { url = "https://files.pythonhosted.org/packages/2e/66/931dc2479aa8fbf362dc6dcee707d895a84b0b2d7b64020135f20b8db1ed/debugpy-1.8.11-cp313-cp313-macosx_14_0_universal2.whl", hash = "sha256:8988f7163e4381b0da7696f37eec7aca19deb02e500245df68a7159739bbd0d3", size = 2483651 },
+    { url = "https://files.pythonhosted.org/packages/10/07/6c171d0fe6b8d237e35598b742f20ba062511b3a4631938cc78eefbbf847/debugpy-1.8.11-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c1f6a173d1140e557347419767d2b14ac1c9cd847e0b4c5444c7f3144697e4e", size = 4213770 },
+    { url = "https://files.pythonhosted.org/packages/89/f1/0711da6ac250d4fe3bf7b3e9b14b4a86e82a98b7825075c07e19bab8da3d/debugpy-1.8.11-cp313-cp313-win32.whl", hash = "sha256:bb3b15e25891f38da3ca0740271e63ab9db61f41d4d8541745cfc1824252cb28", size = 5223911 },
+    { url = "https://files.pythonhosted.org/packages/56/98/5e27fa39050749ed460025bcd0034a0a5e78a580a14079b164cc3abdeb98/debugpy-1.8.11-cp313-cp313-win_amd64.whl", hash = "sha256:d8768edcbeb34da9e11bcb8b5c2e0958d25218df7a6e56adf415ef262cd7b6d1", size = 5264166 },
+    { url = "https://files.pythonhosted.org/packages/77/0a/d29a5aacf47b4383ed569b8478c02d59ee3a01ad91224d2cff8562410e43/debugpy-1.8.11-py2.py3-none-any.whl", hash = "sha256:0e22f846f4211383e6a416d04b4c13ed174d24cc5d43f5fd52e7821d0ebc8920", size = 5226874 },
+]
+
+[[package]]
+name = "decorator"
+version = "5.1.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/66/0c/8d907af351aa16b42caae42f9d6aa37b900c67308052d10fdce809f8d952/decorator-5.1.1.tar.gz", hash = "sha256:637996211036b6385ef91435e4fae22989472f9d571faba8927ba8253acbc330", size = 35016 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d5/50/83c593b07763e1161326b3b8c6686f0f4b0f24d5526546bee538c89837d6/decorator-5.1.1-py3-none-any.whl", hash = "sha256:b8c3f85900b9dc423225913c5aace94729fe1fa9763b38939a95226f02d37186", size = 9073 },
+]
+
 [[package]]
 name = "deprecated"
 version = "1.2.15"
@@ -387,19 +449,12 @@ wheels = [
 ]

 [[package]]
-name = "flask"
-version = "3.1.0"
+name = "executing"
+version = "2.1.0"
 source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "blinker" },
-    { name = "click" },
-    { name = "itsdangerous" },
-    { name = "jinja2" },
-    { name = "werkzeug" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/89/50/dff6380f1c7f84135484e176e0cac8690af72fa90e932ad2a0a60e28c69b/flask-3.1.0.tar.gz", hash = "sha256:5f873c5184c897c8d9d1b05df1e3d01b14910ce69607a117bd3277098a5836ac", size = 680824 }
+sdist = { url = "https://files.pythonhosted.org/packages/8c/e3/7d45f492c2c4a0e8e0fad57d081a7c8a0286cdd86372b070cca1ec0caa1e/executing-2.1.0.tar.gz", hash = "sha256:8ea27ddd260da8150fa5a708269c4a10e76161e2496ec3e587da9e3c0fe4b9ab", size = 977485 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/af/47/93213ee66ef8fae3b93b3e29206f6b251e65c97bd91d8e1c5596ef15af0a/flask-3.1.0-py3-none-any.whl", hash = "sha256:d667207822eb83f1c4b50949b1623c8fc8d51f2341d65f72e1a1815397551136", size = 102979 },
+    { url = "https://files.pythonhosted.org/packages/b5/fd/afcd0496feca3276f509df3dbd5dae726fcc756f1a08d9e25abe1733f962/executing-2.1.0-py2.py3-none-any.whl", hash = "sha256:8d63781349375b5ebccc3142f4b30350c0cd9c79f921cde38be2be4637e98eaf", size = 25805 },
 ]

 [[package]]
@@ -478,12 +533,61 @@ wheels = [
 ]

 [[package]]
-name = "itsdangerous"
-version = "2.2.0"
+name = "ipykernel"
+version = "6.29.5"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/9c/cb/8ac0172223afbccb63986cc25049b154ecfb5e85932587206f42317be31d/itsdangerous-2.2.0.tar.gz", hash = "sha256:e0050c0b7da1eea53ffaf149c0cfbb5c6e2e2b69c4bef22c81fa6eb73e5f6173", size = 54410 }
+dependencies = [
+    { name = "appnope", marker = "platform_system == 'Darwin'" },
+    { name = "comm" },
+    { name = "debugpy" },
+    { name = "ipython" },
+    { name = "jupyter-client" },
+    { name = "jupyter-core" },
+    { name = "matplotlib-inline" },
+    { name = "nest-asyncio" },
+    { name = "packaging" },
+    { name = "psutil" },
+    { name = "pyzmq" },
+    { name = "tornado" },
+    { name = "traitlets" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/e9/5c/67594cb0c7055dc50814b21731c22a601101ea3b1b50a9a1b090e11f5d0f/ipykernel-6.29.5.tar.gz", hash = "sha256:f093a22c4a40f8828f8e330a9c297cb93dcab13bd9678ded6de8e5cf81c56215", size = 163367 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/04/96/92447566d16df59b2a776c0fb82dbc4d9e07cd95062562af01e408583fc4/itsdangerous-2.2.0-py3-none-any.whl", hash = "sha256:c6242fc49e35958c8b15141343aa660db5fc54d4f13a1db01a3f5891b98700ef", size = 16234 },
+    { url = "https://files.pythonhosted.org/packages/94/5c/368ae6c01c7628438358e6d337c19b05425727fbb221d2a3c4303c372f42/ipykernel-6.29.5-py3-none-any.whl", hash = "sha256:afdb66ba5aa354b09b91379bac28ae4afebbb30e8b39510c9690afb7a10421b5", size = 117173 },
+]
+
+[[package]]
+name = "ipython"
+version = "8.31.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "decorator" },
+    { name = "exceptiongroup", marker = "python_full_version < '3.11'" },
+    { name = "jedi" },
+    { name = "matplotlib-inline" },
+    { name = "pexpect", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" },
+    { name = "prompt-toolkit" },
+    { name = "pygments" },
+    { name = "stack-data" },
+    { name = "traitlets" },
+    { name = "typing-extensions", marker = "python_full_version < '3.12'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/01/35/6f90fdddff7a08b7b715fccbd2427b5212c9525cd043d26fdc45bee0708d/ipython-8.31.0.tar.gz", hash = "sha256:b6a2274606bec6166405ff05e54932ed6e5cfecaca1fc05f2cacde7bb074d70b", size = 5501011 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/04/60/d0feb6b6d9fe4ab89fe8fe5b47cbf6cd936bfd9f1e7ffa9d0015425aeed6/ipython-8.31.0-py3-none-any.whl", hash = "sha256:46ec58f8d3d076a61d128fe517a51eb730e3aaf0c184ea8c17d16e366660c6a6", size = 821583 },
+]
+
+[[package]]
+name = "jedi"
+version = "0.19.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "parso" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/72/3a/79a912fbd4d8dd6fbb02bf69afd3bb72cf0c729bb3063c6f4498603db17a/jedi-0.19.2.tar.gz", hash = "sha256:4770dc3de41bde3966b02eb84fbcf557fb33cce26ad23da12c742fb50ecb11f0", size = 1231287 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c0/5a/9cac0c82afec3d09ccd97c8b6502d48f165f9124db81b4bcb90b4af974ee/jedi-0.19.2-py2.py3-none-any.whl", hash = "sha256:a8ef22bde8490f57fe5c7681a3c83cb58874daf72b4784de3cce5b6ef6edb5b9", size = 1572278 },
 ]

 [[package]]
@@ -525,6 +629,36 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/d1/0f/8910b19ac0670a0f80ce1008e5e751c4a57e14d2c4c13a482aa6079fa9d6/jsonschema_specifications-2024.10.1-py3-none-any.whl", hash = "sha256:a09a0680616357d9a0ecf05c12ad234479f549239d0f5b55f3deea67475da9bf", size = 18459 },
 ]

+[[package]]
+name = "jupyter-client"
+version = "8.6.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "jupyter-core" },
+    { name = "python-dateutil" },
+    { name = "pyzmq" },
+    { name = "tornado" },
+    { name = "traitlets" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/71/22/bf9f12fdaeae18019a468b68952a60fe6dbab5d67cd2a103cac7659b41ca/jupyter_client-8.6.3.tar.gz", hash = "sha256:35b3a0947c4a6e9d589eb97d7d4cd5e90f910ee73101611f01283732bd6d9419", size = 342019 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/11/85/b0394e0b6fcccd2c1eeefc230978a6f8cb0c5df1e4cd3e7625735a0d7d1e/jupyter_client-8.6.3-py3-none-any.whl", hash = "sha256:e8a19cc986cc45905ac3362915f410f3af85424b4c0905e94fa5f2cb08e8f23f", size = 106105 },
+]
+
+[[package]]
+name = "jupyter-core"
+version = "5.7.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "platformdirs" },
+    { name = "pywin32", marker = "platform_python_implementation != 'PyPy' and sys_platform == 'win32'" },
+    { name = "traitlets" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/00/11/b56381fa6c3f4cc5d2cf54a7dbf98ad9aa0b339ef7a601d6053538b079a7/jupyter_core-5.7.2.tar.gz", hash = "sha256:aa5f8d32bbf6b431ac830496da7392035d6f61b4f54872f15c4bd2a9c3f536d9", size = 87629 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c9/fb/108ecd1fe961941959ad0ee4e12ee7b8b1477247f30b1fdfd83ceaf017f0/jupyter_core-5.7.2-py3-none-any.whl", hash = "sha256:4f7315d2f6b4bcf2e3e7cb6e46772eba760ae459cd1f59d29eb57b0a01bd7409", size = 28965 },
+]
+
 [[package]]
 name = "lxml"
 version = "5.3.0"
@@ -677,6 +811,18 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/4f/65/6079a46068dfceaeabb5dcad6d674f5f5c61a6fa5673746f42a9f4c233b3/MarkupSafe-3.0.2-cp313-cp313t-win_amd64.whl", hash = "sha256:e444a31f8db13eb18ada366ab3cf45fd4b31e4db1236a4448f68778c1d1a5a2f", size = 15739 },
 ]

+[[package]]
+name = "matplotlib-inline"
+version = "0.1.7"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "traitlets" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/99/5b/a36a337438a14116b16480db471ad061c36c3694df7c2084a0da7ba538b7/matplotlib_inline-0.1.7.tar.gz", hash = "sha256:8423b23ec666be3d16e16b60bdd8ac4e86e840ebd1dd11a30b9f117f2fa0ab90", size = 8159 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/8f/8e/9ad090d3553c280a8060fbf6e24dc1c0c29704ee7d1c372f0c174aa59285/matplotlib_inline-0.1.7-py3-none-any.whl", hash = "sha256:df192d39a4ff8f21b1895d72e6a13f5fcc5099f00fa84384e0ea28c2cc0653ca", size = 9899 },
+]
+
 [[package]]
 name = "mdurl"
 version = "0.1.2"
@@ -738,6 +884,15 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/ac/e7/fe3d69098e628e81cf317e860474e5df02a5a681b031acbf2aaf192cef3f/narwhals-1.15.2-py3-none-any.whl", hash = "sha256:00d16ed1c4466b43ba37ef6799142340981e4ac7dcd7686e461d4955abcd921d", size = 233774 },
 ]

+[[package]]
+name = "nest-asyncio"
+version = "1.6.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/83/f8/51569ac65d696c8ecbee95938f89d4abf00f47d58d48f6fbabfe8f0baefe/nest_asyncio-1.6.0.tar.gz", hash = "sha256:6f172d5449aca15afd6c646851f4e31e02c598d553a667e38cafa997cfec55fe", size = 7418 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a0/c4/c2971a3ba4c6103a3d10c4b0f24f461ddc027f0f09763220cf35ca1401b3/nest_asyncio-1.6.0-py3-none-any.whl", hash = "sha256:87af6efd6b5e897c81050477ef65c62e2b2f35d51703cae01aff2905b1852e1c", size = 5195 },
+]
+
 [[package]]
 name = "numpy"
 version = "2.1.3"
@@ -802,7 +957,7 @@ wheels = [

 [[package]]
 name = "ocrmypdf"
-version = "16.6.3.dev16+g15df9c37.d20241208"
+version = "16.7.1.dev17+gbfbe571f.d20250104"
 source = { editable = "." }
 dependencies = [
    { name = "deprecation" },
@@ -842,11 +997,13 @@ watcher = [
    { name = "watchdog" },
 ]
 webservice = [
-    { name = "flask" },
+    { name = "port-for" },
+    { name = "streamlit" },
 ]

 [package.dev-dependencies]
 dev = [
+    { name = "ipykernel" },
    { name = "mypy" },
    { name = "pymupdf" },
    { name = "streamlit" },
@@ -857,7 +1014,6 @@ dev = [
 requires-dist = [
    { name = "coverage", extras = ["toml"], marker = "extra == 'test'", specifier = ">=6.2" },
    { name = "deprecation", specifier = ">=2.1.0" },
-    { name = "flask", marker = "extra == 'webservice'", specifier = ">=2.0.1" },
    { name = "hypothesis", marker = "extra == 'test'", specifier = ">=6.36.0" },
    { name = "img2pdf", specifier = ">=0.5" },
    { name = "packaging", specifier = ">=20" },
@@ -866,6 +1022,7 @@ requires-dist = [
    { name = "pikepdf", specifier = ">=8.10.1" },
    { name = "pillow", specifier = ">=10.0.1" },
    { name = "pluggy", specifier = ">=1" },
+    { name = "port-for", marker = "extra == 'webservice'", specifier = ">=0.7.4" },
    { name = "pymupdf", marker = "extra == 'extended-test'", specifier = ">=1.19.1" },
    { name = "pytest", marker = "extra == 'test'", specifier = ">=6.2.5" },
    { name = "pytest-cov", marker = "extra == 'test'", specifier = ">=3.0.0" },
@@ -877,6 +1034,7 @@ requires-dist = [
    { name = "sphinx", marker = "extra == 'docs'" },
    { name = "sphinx-issues", marker = "extra == 'docs'" },
    { name = "sphinx-rtd-theme", marker = "extra == 'docs'" },
+    { name = "streamlit", marker = "extra == 'webservice'", specifier = ">=1.41.0" },
    { name = "typer-slim", extras = ["standard"], marker = "extra == 'watcher'" },
    { name = "types-humanfriendly", marker = "extra == 'test'" },
    { name = "types-pillow", marker = "extra == 'test'" },
@@ -885,6 +1043,7 @@ requires-dist = [

 [package.metadata.requires-dev]
 dev = [
+    { name = "ipykernel", specifier = ">=6.29.5" },
    { name = "mypy", specifier = ">=1.13.0" },
    { name = "pymupdf", specifier = ">=1.24.14" },
    { name = "streamlit", specifier = ">=1.40.2" },
@@ -948,6 +1107,15 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/ab/5f/b38085618b950b79d2d9164a711c52b10aefc0ae6833b96f626b7021b2ed/pandas-2.2.3-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:ad5b65698ab28ed8d7f18790a0dc58005c7629f227be9ecc1072aa74c0c1d43a", size = 13098436 },
 ]

+[[package]]
+name = "parso"
+version = "0.8.4"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/66/94/68e2e17afaa9169cf6412ab0f28623903be73d1b32e208d9e8e541bb086d/parso-0.8.4.tar.gz", hash = "sha256:eb3a7b58240fb99099a345571deecc0f9540ea5f4dd2fe14c2a99d6b281ab92d", size = 400609 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c6/ac/dac4a63f978e4dcb3c6d3a78c4d8e0192a113d288502a1216950c41b1027/parso-0.8.4-py2.py3-none-any.whl", hash = "sha256:a418670a20291dacd2dddc80c377c5c3791378ee1e8d12bffc35420643d43f18", size = 103650 },
+]
+
 [[package]]
 name = "pdfminer-six"
 version = "20240706"
@@ -961,6 +1129,18 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/67/7d/44d6b90e5a293d3a975cefdc4e12a932ebba814995b2a07e37e599dd27c6/pdfminer.six-20240706-py3-none-any.whl", hash = "sha256:f4f70e74174b4b3542fcb8406a210b6e2e27cd0f0b5fd04534a8cc0d8951e38c", size = 5615414 },
 ]

+[[package]]
+name = "pexpect"
+version = "4.9.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "ptyprocess" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/42/92/cc564bf6381ff43ce1f4d06852fc19a2f11d180f23dc32d9588bee2f149d/pexpect-4.9.0.tar.gz", hash = "sha256:ee7d41123f3c9911050ea2c2dac107568dc43b2d3b0c7557a33212c398ead30f", size = 166450 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/9e/c3/059298687310d527a58bb01f3b1965787ee3b40dce76752eda8b44e9a2c5/pexpect-4.9.0-py2.py3-none-any.whl", hash = "sha256:7236d1e080e4936be2dc3e326cec0af72acf9212a7e1d060210e70a47e253523", size = 63772 },
+]
+
 [[package]]
 name = "pi-heif"
 version = "0.20.0"
@@ -1118,6 +1298,15 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/ec/3d/c32a51d848401bd94cabb8767a39621496491ee7cd5199856b77da9b18ad/pillow-11.0.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:224aaa38177597bb179f3ec87eeefcce8e4f85e608025e9cfac60de237ba6316", size = 2567508 },
 ]

+[[package]]
+name = "platformdirs"
+version = "4.3.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/13/fc/128cc9cb8f03208bdbf93d3aa862e16d376844a14f9a0ce5cf4507372de4/platformdirs-4.3.6.tar.gz", hash = "sha256:357fb2acbc885b0419afd3ce3ed34564c13c9b95c89360cd9563f73aa5e2b907", size = 21302 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3c/a6/bc1012356d8ece4d66dd75c4b9fc6c1f6650ddd5991e421177d9f8f671be/platformdirs-4.3.6-py3-none-any.whl", hash = "sha256:73e575e1408ab8103900836b97580d5307456908a03e92031bab39e4554cc3fb", size = 18439 },
+]
+
 [[package]]
 name = "pluggy"
 version = "1.5.0"
@@ -1127,6 +1316,27 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/88/5f/e351af9a41f866ac3f1fac4ca0613908d9a41741cfcf2228f4ad853b697d/pluggy-1.5.0-py3-none-any.whl", hash = "sha256:44e1ad92c8ca002de6377e165f3e0f1be63266ab4d554740532335b9d75ea669", size = 20556 },
 ]

+[[package]]
+name = "port-for"
+version = "0.7.4"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f6/84/ad5114c85217426d7a5170a74a6f9d6b724df117c2f3b75e41fc9d6c6811/port_for-0.7.4.tar.gz", hash = "sha256:fc7713e7b22f89442f335ce12536653656e8f35146739eccaeff43d28436028d", size = 25077 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/9c/a2/579dcefbb0285b31f8d65b537f8a9932ed51319e0a3694e01b5bbc271f92/port_for-0.7.4-py3-none-any.whl", hash = "sha256:08404aa072651a53dcefe8d7a598ee8a1dca320d9ac44ac464da16ccf2a02c4a", size = 21369 },
+]
+
+[[package]]
+name = "prompt-toolkit"
+version = "3.0.48"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "wcwidth" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/2d/4f/feb5e137aff82f7c7f3248267b97451da3644f6cdc218edfe549fb354127/prompt_toolkit-3.0.48.tar.gz", hash = "sha256:d6623ab0477a80df74e646bdbc93621143f5caf104206aa29294d53de1a03d90", size = 424684 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a9/6a/fd08d94654f7e67c52ca30523a178b3f8ccc4237fce4be90d39c938a831a/prompt_toolkit-3.0.48-py3-none-any.whl", hash = "sha256:f49a827f90062e411f1ce1f854f2aedb3c23353244f8108b89283587397ac10e", size = 386595 },
+]
+
 [[package]]
 name = "protobuf"
 version = "5.29.1"
@@ -1141,6 +1351,39 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/3b/24/c8c49df8f6587719e1d400109b16c10c6902d0c9adddc8fff82840146f99/protobuf-5.29.1-py3-none-any.whl", hash = "sha256:32600ddb9c2a53dedc25b8581ea0f1fd8ea04956373c0c07577ce58d312522e0", size = 172547 },
 ]

+[[package]]
+name = "psutil"
+version = "6.1.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/1f/5a/07871137bb752428aa4b659f910b399ba6f291156bdea939be3e96cae7cb/psutil-6.1.1.tar.gz", hash = "sha256:cf8496728c18f2d0b45198f06895be52f36611711746b7f30c464b422b50e2f5", size = 508502 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/61/99/ca79d302be46f7bdd8321089762dd4476ee725fce16fc2b2e1dbba8cac17/psutil-6.1.1-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:fc0ed7fe2231a444fc219b9c42d0376e0a9a1a72f16c5cfa0f68d19f1a0663e8", size = 247511 },
+    { url = "https://files.pythonhosted.org/packages/0b/6b/73dbde0dd38f3782905d4587049b9be64d76671042fdcaf60e2430c6796d/psutil-6.1.1-cp36-abi3-macosx_11_0_arm64.whl", hash = "sha256:0bdd4eab935276290ad3cb718e9809412895ca6b5b334f5a9111ee6d9aff9377", size = 248985 },
+    { url = "https://files.pythonhosted.org/packages/17/38/c319d31a1d3f88c5b79c68b3116c129e5133f1822157dd6da34043e32ed6/psutil-6.1.1-cp36-abi3-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b6e06c20c05fe95a3d7302d74e7097756d4ba1247975ad6905441ae1b5b66003", size = 284488 },
+    { url = "https://files.pythonhosted.org/packages/9c/39/0f88a830a1c8a3aba27fededc642da37613c57cbff143412e3536f89784f/psutil-6.1.1-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:97f7cb9921fbec4904f522d972f0c0e1f4fabbdd4e0287813b21215074a0f160", size = 287477 },
+    { url = "https://files.pythonhosted.org/packages/47/da/99f4345d4ddf2845cb5b5bd0d93d554e84542d116934fde07a0c50bd4e9f/psutil-6.1.1-cp36-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:33431e84fee02bc84ea36d9e2c4a6d395d479c9dd9bba2376c1f6ee8f3a4e0b3", size = 289017 },
+    { url = "https://files.pythonhosted.org/packages/38/53/bd755c2896f4461fd4f36fa6a6dcb66a88a9e4b9fd4e5b66a77cf9d4a584/psutil-6.1.1-cp37-abi3-win32.whl", hash = "sha256:eaa912e0b11848c4d9279a93d7e2783df352b082f40111e078388701fd479e53", size = 250602 },
+    { url = "https://files.pythonhosted.org/packages/7b/d7/7831438e6c3ebbfa6e01a927127a6cb42ad3ab844247f3c5b96bea25d73d/psutil-6.1.1-cp37-abi3-win_amd64.whl", hash = "sha256:f35cfccb065fff93529d2afb4a2e89e363fe63ca1e4a5da22b603a85833c2649", size = 254444 },
+]
+
+[[package]]
+name = "ptyprocess"
+version = "0.7.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/20/e5/16ff212c1e452235a90aeb09066144d0c5a6a8c0834397e03f5224495c4e/ptyprocess-0.7.0.tar.gz", hash = "sha256:5c5d0a3b48ceee0b48485e0c26037c0acd7d29765ca3fbb5cb3831d347423220", size = 70762 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/22/a6/858897256d0deac81a172289110f31629fc4cee19b6f01283303e18c8db3/ptyprocess-0.7.0-py2.py3-none-any.whl", hash = "sha256:4b41f3967fce3af57cc7e94b888626c18bf37a083e3651ca8feeb66d492fef35", size = 13993 },
+]
+
+[[package]]
+name = "pure-eval"
+version = "0.2.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/cd/05/0a34433a064256a578f1783a10da6df098ceaa4a57bbeaa96a6c0352786b/pure_eval-0.2.3.tar.gz", hash = "sha256:5f4e983f40564c576c7c8635ae88db5956bb2229d7e9237d03b3c0b0190eaf42", size = 19752 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/8e/37/efad0257dc6e593a18957422533ff0f87ede7c9c6ea010a2177d738fb82f/pure_eval-0.2.3-py3-none-any.whl", hash = "sha256:1db8e35b67b3d218d818ae653e27f06c3aa420901fa7b081ca98cbedc874e0d0", size = 11842 },
+]
+
 [[package]]
 name = "pyarrow"
 version = "18.1.0"
@@ -1314,6 +1557,98 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/11/c3/005fcca25ce078d2cc29fd559379817424e94885510568bc1bc53d7d5846/pytz-2024.2-py2.py3-none-any.whl", hash = "sha256:31c7c1817eb7fae7ca4b8c7ee50c72f93aa2dd863de768e1ef4245d426aa0725", size = 508002 },
 ]

+[[package]]
+name = "pywin32"
+version = "308"
+source = { registry = "https://pypi.org/simple" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/72/a6/3e9f2c474895c1bb61b11fa9640be00067b5c5b363c501ee9c3fa53aec01/pywin32-308-cp310-cp310-win32.whl", hash = "sha256:796ff4426437896550d2981b9c2ac0ffd75238ad9ea2d3bfa67a1abd546d262e", size = 5927028 },
+    { url = "https://files.pythonhosted.org/packages/d9/b4/84e2463422f869b4b718f79eb7530a4c1693e96b8a4e5e968de38be4d2ba/pywin32-308-cp310-cp310-win_amd64.whl", hash = "sha256:4fc888c59b3c0bef905ce7eb7e2106a07712015ea1c8234b703a088d46110e8e", size = 6558484 },
+    { url = "https://files.pythonhosted.org/packages/9f/8f/fb84ab789713f7c6feacaa08dad3ec8105b88ade8d1c4f0f0dfcaaa017d6/pywin32-308-cp310-cp310-win_arm64.whl", hash = "sha256:a5ab5381813b40f264fa3495b98af850098f814a25a63589a8e9eb12560f450c", size = 7971454 },
+    { url = "https://files.pythonhosted.org/packages/eb/e2/02652007469263fe1466e98439831d65d4ca80ea1a2df29abecedf7e47b7/pywin32-308-cp311-cp311-win32.whl", hash = "sha256:5d8c8015b24a7d6855b1550d8e660d8daa09983c80e5daf89a273e5c6fb5095a", size = 5928156 },
+    { url = "https://files.pythonhosted.org/packages/48/ef/f4fb45e2196bc7ffe09cad0542d9aff66b0e33f6c0954b43e49c33cad7bd/pywin32-308-cp311-cp311-win_amd64.whl", hash = "sha256:575621b90f0dc2695fec346b2d6302faebd4f0f45c05ea29404cefe35d89442b", size = 6559559 },
+    { url = "https://files.pythonhosted.org/packages/79/ef/68bb6aa865c5c9b11a35771329e95917b5559845bd75b65549407f9fc6b4/pywin32-308-cp311-cp311-win_arm64.whl", hash = "sha256:100a5442b7332070983c4cd03f2e906a5648a5104b8a7f50175f7906efd16bb6", size = 7972495 },
+    { url = "https://files.pythonhosted.org/packages/00/7c/d00d6bdd96de4344e06c4afbf218bc86b54436a94c01c71a8701f613aa56/pywin32-308-cp312-cp312-win32.whl", hash = "sha256:587f3e19696f4bf96fde9d8a57cec74a57021ad5f204c9e627e15c33ff568897", size = 5939729 },
+    { url = "https://files.pythonhosted.org/packages/21/27/0c8811fbc3ca188f93b5354e7c286eb91f80a53afa4e11007ef661afa746/pywin32-308-cp312-cp312-win_amd64.whl", hash = "sha256:00b3e11ef09ede56c6a43c71f2d31857cf7c54b0ab6e78ac659497abd2834f47", size = 6543015 },
+    { url = "https://files.pythonhosted.org/packages/9d/0f/d40f8373608caed2255781a3ad9a51d03a594a1248cd632d6a298daca693/pywin32-308-cp312-cp312-win_arm64.whl", hash = "sha256:9b4de86c8d909aed15b7011182c8cab38c8850de36e6afb1f0db22b8959e3091", size = 7976033 },
+    { url = "https://files.pythonhosted.org/packages/a9/a4/aa562d8935e3df5e49c161b427a3a2efad2ed4e9cf81c3de636f1fdddfd0/pywin32-308-cp313-cp313-win32.whl", hash = "sha256:1c44539a37a5b7b21d02ab34e6a4d314e0788f1690d65b48e9b0b89f31abbbed", size = 5938579 },
+    { url = "https://files.pythonhosted.org/packages/c7/50/b0efb8bb66210da67a53ab95fd7a98826a97ee21f1d22949863e6d588b22/pywin32-308-cp313-cp313-win_amd64.whl", hash = "sha256:fd380990e792eaf6827fcb7e187b2b4b1cede0585e3d0c9e84201ec27b9905e4", size = 6542056 },
+    { url = "https://files.pythonhosted.org/packages/26/df/2b63e3e4f2df0224f8aaf6d131f54fe4e8c96400eb9df563e2aae2e1a1f9/pywin32-308-cp313-cp313-win_arm64.whl", hash = "sha256:ef313c46d4c18dfb82a2431e3051ac8f112ccee1a34f29c263c583c568db63cd", size = 7974986 },
+]
+
+[[package]]
+name = "pyzmq"
+version = "26.2.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "cffi", marker = "implementation_name == 'pypy'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/fd/05/bed626b9f7bb2322cdbbf7b4bd8f54b1b617b0d2ab2d3547d6e39428a48e/pyzmq-26.2.0.tar.gz", hash = "sha256:070672c258581c8e4f640b5159297580a9974b026043bd4ab0470be9ed324f1f", size = 271975 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/1f/a8/9837c39aba390eb7d01924ace49d761c8dbe7bc2d6082346d00c8332e431/pyzmq-26.2.0-cp310-cp310-macosx_10_15_universal2.whl", hash = "sha256:ddf33d97d2f52d89f6e6e7ae66ee35a4d9ca6f36eda89c24591b0c40205a3629", size = 1340058 },
+    { url = "https://files.pythonhosted.org/packages/a2/1f/a006f2e8e4f7d41d464272012695da17fb95f33b54342612a6890da96ff6/pyzmq-26.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:dacd995031a01d16eec825bf30802fceb2c3791ef24bcce48fa98ce40918c27b", size = 1008818 },
+    { url = "https://files.pythonhosted.org/packages/b6/09/b51b6683fde5ca04593a57bbe81788b6b43114d8f8ee4e80afc991e14760/pyzmq-26.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:89289a5ee32ef6c439086184529ae060c741334b8970a6855ec0b6ad3ff28764", size = 673199 },
+    { url = "https://files.pythonhosted.org/packages/c9/78/486f3e2e824f3a645238332bf5a4c4b4477c3063033a27c1e4052358dee2/pyzmq-26.2.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5506f06d7dc6ecf1efacb4a013b1f05071bb24b76350832c96449f4a2d95091c", size = 911762 },
+    { url = "https://files.pythonhosted.org/packages/5e/3b/2eb1667c9b866f53e76ee8b0c301b0469745a23bd5a87b7ee3d5dd9eb6e5/pyzmq-26.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8ea039387c10202ce304af74def5021e9adc6297067f3441d348d2b633e8166a", size = 868773 },
+    { url = "https://files.pythonhosted.org/packages/16/29/ca99b4598a9dc7e468b5417eda91f372b595be1e3eec9b7cbe8e5d3584e8/pyzmq-26.2.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:a2224fa4a4c2ee872886ed00a571f5e967c85e078e8e8c2530a2fb01b3309b88", size = 868834 },
+    { url = "https://files.pythonhosted.org/packages/ad/e5/9efaeb1d2f4f8c50da04144f639b042bc52869d3a206d6bf672ab3522163/pyzmq-26.2.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:28ad5233e9c3b52d76196c696e362508959741e1a005fb8fa03b51aea156088f", size = 1202861 },
+    { url = "https://files.pythonhosted.org/packages/c3/62/c721b5608a8ac0a69bb83cbb7d07a56f3ff00b3991a138e44198a16f94c7/pyzmq-26.2.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:1c17211bc037c7d88e85ed8b7d8f7e52db6dc8eca5590d162717c654550f7282", size = 1515304 },
+    { url = "https://files.pythonhosted.org/packages/87/84/e8bd321aa99b72f48d4606fc5a0a920154125bd0a4608c67eab742dab087/pyzmq-26.2.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b8f86dd868d41bea9a5f873ee13bf5551c94cf6bc51baebc6f85075971fe6eea", size = 1414712 },
+    { url = "https://files.pythonhosted.org/packages/cd/cd/420e3fd1ac6977b008b72e7ad2dae6350cc84d4c5027fc390b024e61738f/pyzmq-26.2.0-cp310-cp310-win32.whl", hash = "sha256:46a446c212e58456b23af260f3d9fb785054f3e3653dbf7279d8f2b5546b21c2", size = 578113 },
+    { url = "https://files.pythonhosted.org/packages/5c/57/73930d56ed45ae0cb4946f383f985c855c9b3d4063f26416998f07523c0e/pyzmq-26.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:49d34ab71db5a9c292a7644ce74190b1dd5a3475612eefb1f8be1d6961441971", size = 641631 },
+    { url = "https://files.pythonhosted.org/packages/61/d2/ae6ac5c397f1ccad59031c64beaafce7a0d6182e0452cc48f1c9c87d2dd0/pyzmq-26.2.0-cp310-cp310-win_arm64.whl", hash = "sha256:bfa832bfa540e5b5c27dcf5de5d82ebc431b82c453a43d141afb1e5d2de025fa", size = 543528 },
+    { url = "https://files.pythonhosted.org/packages/12/20/de7442172f77f7c96299a0ac70e7d4fb78cd51eca67aa2cf552b66c14196/pyzmq-26.2.0-cp311-cp311-macosx_10_15_universal2.whl", hash = "sha256:8f7e66c7113c684c2b3f1c83cdd3376103ee0ce4c49ff80a648643e57fb22218", size = 1340639 },
+    { url = "https://files.pythonhosted.org/packages/98/4d/5000468bd64c7910190ed0a6c76a1ca59a68189ec1f007c451dc181a22f4/pyzmq-26.2.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3a495b30fc91db2db25120df5847d9833af237546fd59170701acd816ccc01c4", size = 1008710 },
+    { url = "https://files.pythonhosted.org/packages/e1/bf/c67fd638c2f9fbbab8090a3ee779370b97c82b84cc12d0c498b285d7b2c0/pyzmq-26.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:77eb0968da535cba0470a5165468b2cac7772cfb569977cff92e240f57e31bef", size = 673129 },
+    { url = "https://files.pythonhosted.org/packages/86/94/99085a3f492aa538161cbf27246e8886ff850e113e0c294a5b8245f13b52/pyzmq-26.2.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6ace4f71f1900a548f48407fc9be59c6ba9d9aaf658c2eea6cf2779e72f9f317", size = 910107 },
+    { url = "https://files.pythonhosted.org/packages/31/1d/346809e8a9b999646d03f21096428453465b1bca5cd5c64ecd048d9ecb01/pyzmq-26.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:92a78853d7280bffb93df0a4a6a2498cba10ee793cc8076ef797ef2f74d107cf", size = 867960 },
+    { url = "https://files.pythonhosted.org/packages/ab/68/6fb6ae5551846ad5beca295b7bca32bf0a7ce19f135cb30e55fa2314e6b6/pyzmq-26.2.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:689c5d781014956a4a6de61d74ba97b23547e431e9e7d64f27d4922ba96e9d6e", size = 869204 },
+    { url = "https://files.pythonhosted.org/packages/0f/f9/18417771dee223ccf0f48e29adf8b4e25ba6d0e8285e33bcbce078070bc3/pyzmq-26.2.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0aca98bc423eb7d153214b2df397c6421ba6373d3397b26c057af3c904452e37", size = 1203351 },
+    { url = "https://files.pythonhosted.org/packages/e0/46/f13e67fe0d4f8a2315782cbad50493de6203ea0d744610faf4d5f5b16e90/pyzmq-26.2.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:1f3496d76b89d9429a656293744ceca4d2ac2a10ae59b84c1da9b5165f429ad3", size = 1514204 },
+    { url = "https://files.pythonhosted.org/packages/50/11/ddcf7343b7b7a226e0fc7b68cbf5a5bb56291fac07f5c3023bb4c319ebb4/pyzmq-26.2.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:5c2b3bfd4b9689919db068ac6c9911f3fcb231c39f7dd30e3138be94896d18e6", size = 1414339 },
+    { url = "https://files.pythonhosted.org/packages/01/14/1c18d7d5b7be2708f513f37c61bfadfa62161c10624f8733f1c8451b3509/pyzmq-26.2.0-cp311-cp311-win32.whl", hash = "sha256:eac5174677da084abf378739dbf4ad245661635f1600edd1221f150b165343f4", size = 576928 },
+    { url = "https://files.pythonhosted.org/packages/3b/1b/0a540edd75a41df14ec416a9a500b9fec66e554aac920d4c58fbd5756776/pyzmq-26.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:5a509df7d0a83a4b178d0f937ef14286659225ef4e8812e05580776c70e155d5", size = 642317 },
+    { url = "https://files.pythonhosted.org/packages/98/77/1cbfec0358078a4c5add529d8a70892db1be900980cdb5dd0898b3d6ab9d/pyzmq-26.2.0-cp311-cp311-win_arm64.whl", hash = "sha256:c0e6091b157d48cbe37bd67233318dbb53e1e6327d6fc3bb284afd585d141003", size = 543834 },
+    { url = "https://files.pythonhosted.org/packages/28/2f/78a766c8913ad62b28581777ac4ede50c6d9f249d39c2963e279524a1bbe/pyzmq-26.2.0-cp312-cp312-macosx_10_15_universal2.whl", hash = "sha256:ded0fc7d90fe93ae0b18059930086c51e640cdd3baebdc783a695c77f123dcd9", size = 1343105 },
+    { url = "https://files.pythonhosted.org/packages/b7/9c/4b1e2d3d4065be715e007fe063ec7885978fad285f87eae1436e6c3201f4/pyzmq-26.2.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:17bf5a931c7f6618023cdacc7081f3f266aecb68ca692adac015c383a134ca52", size = 1008365 },
+    { url = "https://files.pythonhosted.org/packages/4f/ef/5a23ec689ff36d7625b38d121ef15abfc3631a9aecb417baf7a4245e4124/pyzmq-26.2.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:55cf66647e49d4621a7e20c8d13511ef1fe1efbbccf670811864452487007e08", size = 665923 },
+    { url = "https://files.pythonhosted.org/packages/ae/61/d436461a47437d63c6302c90724cf0981883ec57ceb6073873f32172d676/pyzmq-26.2.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4661c88db4a9e0f958c8abc2b97472e23061f0bc737f6f6179d7a27024e1faa5", size = 903400 },
+    { url = "https://files.pythonhosted.org/packages/47/42/fc6d35ecefe1739a819afaf6f8e686f7f02a4dd241c78972d316f403474c/pyzmq-26.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ea7f69de383cb47522c9c208aec6dd17697db7875a4674c4af3f8cfdac0bdeae", size = 860034 },
+    { url = "https://files.pythonhosted.org/packages/07/3b/44ea6266a6761e9eefaa37d98fabefa112328808ac41aa87b4bbb668af30/pyzmq-26.2.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:7f98f6dfa8b8ccaf39163ce872bddacca38f6a67289116c8937a02e30bbe9711", size = 860579 },
+    { url = "https://files.pythonhosted.org/packages/38/6f/4df2014ab553a6052b0e551b37da55166991510f9e1002c89cab7ce3b3f2/pyzmq-26.2.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:e3e0210287329272539eea617830a6a28161fbbd8a3271bf4150ae3e58c5d0e6", size = 1196246 },
+    { url = "https://files.pythonhosted.org/packages/38/9d/ee240fc0c9fe9817f0c9127a43238a3e28048795483c403cc10720ddef22/pyzmq-26.2.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:6b274e0762c33c7471f1a7471d1a2085b1a35eba5cdc48d2ae319f28b6fc4de3", size = 1507441 },
+    { url = "https://files.pythonhosted.org/packages/85/4f/01711edaa58d535eac4a26c294c617c9a01f09857c0ce191fd574d06f359/pyzmq-26.2.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:29c6a4635eef69d68a00321e12a7d2559fe2dfccfa8efae3ffb8e91cd0b36a8b", size = 1406498 },
+    { url = "https://files.pythonhosted.org/packages/07/18/907134c85c7152f679ed744e73e645b365f3ad571f38bdb62e36f347699a/pyzmq-26.2.0-cp312-cp312-win32.whl", hash = "sha256:989d842dc06dc59feea09e58c74ca3e1678c812a4a8a2a419046d711031f69c7", size = 575533 },
+    { url = "https://files.pythonhosted.org/packages/ce/2c/a6f4a20202a4d3c582ad93f95ee78d79bbdc26803495aec2912b17dbbb6c/pyzmq-26.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:2a50625acdc7801bc6f74698c5c583a491c61d73c6b7ea4dee3901bb99adb27a", size = 637768 },
+    { url = "https://files.pythonhosted.org/packages/5f/0e/eb16ff731632d30554bf5af4dbba3ffcd04518219d82028aea4ae1b02ca5/pyzmq-26.2.0-cp312-cp312-win_arm64.whl", hash = "sha256:4d29ab8592b6ad12ebbf92ac2ed2bedcfd1cec192d8e559e2e099f648570e19b", size = 540675 },
+    { url = "https://files.pythonhosted.org/packages/04/a7/0f7e2f6c126fe6e62dbae0bc93b1bd3f1099cf7fea47a5468defebe3f39d/pyzmq-26.2.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:9dd8cd1aeb00775f527ec60022004d030ddc51d783d056e3e23e74e623e33726", size = 1006564 },
+    { url = "https://files.pythonhosted.org/packages/31/b6/a187165c852c5d49f826a690857684333a6a4a065af0a6015572d2284f6a/pyzmq-26.2.0-cp313-cp313-macosx_10_15_universal2.whl", hash = "sha256:28c812d9757fe8acecc910c9ac9dafd2ce968c00f9e619db09e9f8f54c3a68a3", size = 1340447 },
+    { url = "https://files.pythonhosted.org/packages/68/ba/f4280c58ff71f321602a6e24fd19879b7e79793fb8ab14027027c0fb58ef/pyzmq-26.2.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4d80b1dd99c1942f74ed608ddb38b181b87476c6a966a88a950c7dee118fdf50", size = 665485 },
+    { url = "https://files.pythonhosted.org/packages/77/b5/c987a5c53c7d8704216f29fc3d810b32f156bcea488a940e330e1bcbb88d/pyzmq-26.2.0-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8c997098cc65e3208eca09303630e84d42718620e83b733d0fd69543a9cab9cb", size = 903484 },
+    { url = "https://files.pythonhosted.org/packages/29/c9/07da157d2db18c72a7eccef8e684cefc155b712a88e3d479d930aa9eceba/pyzmq-26.2.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7ad1bc8d1b7a18497dda9600b12dc193c577beb391beae5cd2349184db40f187", size = 859981 },
+    { url = "https://files.pythonhosted.org/packages/43/09/e12501bd0b8394b7d02c41efd35c537a1988da67fc9c745cae9c6c776d31/pyzmq-26.2.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:bea2acdd8ea4275e1278350ced63da0b166421928276c7c8e3f9729d7402a57b", size = 860334 },
+    { url = "https://files.pythonhosted.org/packages/eb/ff/f5ec1d455f8f7385cc0a8b2acd8c807d7fade875c14c44b85c1bddabae21/pyzmq-26.2.0-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:23f4aad749d13698f3f7b64aad34f5fc02d6f20f05999eebc96b89b01262fb18", size = 1196179 },
+    { url = "https://files.pythonhosted.org/packages/ec/8a/bb2ac43295b1950fe436a81fc5b298be0b96ac76fb029b514d3ed58f7b27/pyzmq-26.2.0-cp313-cp313-musllinux_1_1_i686.whl", hash = "sha256:a4f96f0d88accc3dbe4a9025f785ba830f968e21e3e2c6321ccdfc9aef755115", size = 1507668 },
+    { url = "https://files.pythonhosted.org/packages/a9/49/dbc284ebcfd2dca23f6349227ff1616a7ee2c4a35fe0a5d6c3deff2b4fed/pyzmq-26.2.0-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:ced65e5a985398827cc9276b93ef6dfabe0273c23de8c7931339d7e141c2818e", size = 1406539 },
+    { url = "https://files.pythonhosted.org/packages/00/68/093cdce3fe31e30a341d8e52a1ad86392e13c57970d722c1f62a1d1a54b6/pyzmq-26.2.0-cp313-cp313-win32.whl", hash = "sha256:31507f7b47cc1ead1f6e86927f8ebb196a0bab043f6345ce070f412a59bf87b5", size = 575567 },
+    { url = "https://files.pythonhosted.org/packages/92/ae/6cc4657148143412b5819b05e362ae7dd09fb9fe76e2a539dcff3d0386bc/pyzmq-26.2.0-cp313-cp313-win_amd64.whl", hash = "sha256:70fc7fcf0410d16ebdda9b26cbd8bf8d803d220a7f3522e060a69a9c87bf7bad", size = 637551 },
+    { url = "https://files.pythonhosted.org/packages/6c/67/fbff102e201688f97c8092e4c3445d1c1068c2f27bbd45a578df97ed5f94/pyzmq-26.2.0-cp313-cp313-win_arm64.whl", hash = "sha256:c3789bd5768ab5618ebf09cef6ec2b35fed88709b104351748a63045f0ff9797", size = 540378 },
+    { url = "https://files.pythonhosted.org/packages/3f/fe/2d998380b6e0122c6c4bdf9b6caf490831e5f5e2d08a203b5adff060c226/pyzmq-26.2.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:034da5fc55d9f8da09015d368f519478a52675e558c989bfcb5cf6d4e16a7d2a", size = 1007378 },
+    { url = "https://files.pythonhosted.org/packages/4a/f4/30d6e7157f12b3a0390bde94d6a8567cdb88846ed068a6e17238a4ccf600/pyzmq-26.2.0-cp313-cp313t-macosx_10_15_universal2.whl", hash = "sha256:c92d73464b886931308ccc45b2744e5968cbaade0b1d6aeb40d8ab537765f5bc", size = 1329532 },
+    { url = "https://files.pythonhosted.org/packages/82/86/3fe917870e15ee1c3ad48229a2a64458e36036e64b4afa9659045d82bfa8/pyzmq-26.2.0-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:794a4562dcb374f7dbbfb3f51d28fb40123b5a2abadee7b4091f93054909add5", size = 653242 },
+    { url = "https://files.pythonhosted.org/packages/50/2d/242e7e6ef6c8c19e6cb52d095834508cd581ffb925699fd3c640cdc758f1/pyzmq-26.2.0-cp313-cp313t-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:aee22939bb6075e7afededabad1a56a905da0b3c4e3e0c45e75810ebe3a52672", size = 888404 },
+    { url = "https://files.pythonhosted.org/packages/ac/11/7270566e1f31e4ea73c81ec821a4b1688fd551009a3d2bab11ec66cb1e8f/pyzmq-26.2.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2ae90ff9dad33a1cfe947d2c40cb9cb5e600d759ac4f0fd22616ce6540f72797", size = 845858 },
+    { url = "https://files.pythonhosted.org/packages/91/d5/72b38fbc69867795c8711bdd735312f9fef1e3d9204e2f63ab57085434b9/pyzmq-26.2.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:43a47408ac52647dfabbc66a25b05b6a61700b5165807e3fbd40063fcaf46386", size = 847375 },
+    { url = "https://files.pythonhosted.org/packages/dd/9a/10ed3c7f72b4c24e719c59359fbadd1a27556a28b36cdf1cd9e4fb7845d5/pyzmq-26.2.0-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:25bf2374a2a8433633c65ccb9553350d5e17e60c8eb4de4d92cc6bd60f01d306", size = 1183489 },
+    { url = "https://files.pythonhosted.org/packages/72/2d/8660892543fabf1fe41861efa222455811adac9f3c0818d6c3170a1153e3/pyzmq-26.2.0-cp313-cp313t-musllinux_1_1_i686.whl", hash = "sha256:007137c9ac9ad5ea21e6ad97d3489af654381324d5d3ba614c323f60dab8fae6", size = 1492932 },
+    { url = "https://files.pythonhosted.org/packages/7b/d6/32fd69744afb53995619bc5effa2a405ae0d343cd3e747d0fbc43fe894ee/pyzmq-26.2.0-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:470d4a4f6d48fb34e92d768b4e8a5cc3780db0d69107abf1cd7ff734b9766eb0", size = 1392485 },
+    { url = "https://files.pythonhosted.org/packages/53/fb/36b2b2548286e9444e52fcd198760af99fd89102b5be50f0660fcfe902df/pyzmq-26.2.0-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:706e794564bec25819d21a41c31d4df2d48e1cc4b061e8d345d7fb4dd3e94072", size = 906955 },
+    { url = "https://files.pythonhosted.org/packages/77/8f/6ce54f8979a01656e894946db6299e2273fcee21c8e5fa57c6295ef11f57/pyzmq-26.2.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8b435f2753621cd36e7c1762156815e21c985c72b19135dac43a7f4f31d28dd1", size = 565701 },
+    { url = "https://files.pythonhosted.org/packages/ee/1c/bf8cd66730a866b16db8483286078892b7f6536f8c389fb46e4beba0a970/pyzmq-26.2.0-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:160c7e0a5eb178011e72892f99f918c04a131f36056d10d9c1afb223fc952c2d", size = 794312 },
+    { url = "https://files.pythonhosted.org/packages/71/43/91fa4ff25bbfdc914ab6bafa0f03241d69370ef31a761d16bb859f346582/pyzmq-26.2.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c4a71d5d6e7b28a47a394c0471b7e77a0661e2d651e7ae91e0cab0a587859ca", size = 752775 },
+    { url = "https://files.pythonhosted.org/packages/ec/d2/3b2ab40f455a256cb6672186bea95cd97b459ce4594050132d71e76f0d6f/pyzmq-26.2.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:90412f2db8c02a3864cbfc67db0e3dcdbda336acf1c469526d3e869394fe001c", size = 550762 },
+]
+
 [[package]]
 name = "referencing"
 version = "0.35.1"
@@ -1619,9 +1954,23 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/52/a7/d2782e4e3f77c8450f727ba74a8f12756d5ba823d81b941f1b04da9d033a/sphinxcontrib_serializinghtml-2.0.0-py3-none-any.whl", hash = "sha256:6e2cb0eef194e10c27ec0023bfeb25badbbb5868244cf5bc5bdc04e4464bf331", size = 92072 },
 ]

+[[package]]
+name = "stack-data"
+version = "0.6.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "asttokens" },
+    { name = "executing" },
+    { name = "pure-eval" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/28/e3/55dcc2cfbc3ca9c29519eb6884dd1415ecb53b0e934862d3559ddcb7e20b/stack_data-0.6.3.tar.gz", hash = "sha256:836a778de4fec4dcd1dcd89ed8abff8a221f58308462e1c4aa2a3cf30148f0b9", size = 44707 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f1/7b/ce1eafaf1a76852e2ec9b22edecf1daa58175c090266e9f6c64afcd81d91/stack_data-0.6.3-py3-none-any.whl", hash = "sha256:d5558e0c25a4cb0853cddad3d77da9891a08cb85dd9f9f91b9f8cd66e511e695", size = 24521 },
+]
+
 [[package]]
 name = "streamlit"
-version = "1.40.2"
+version = "1.41.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "altair" },
@@ -1644,9 +1993,9 @@ dependencies = [
    { name = "typing-extensions" },
    { name = "watchdog", marker = "platform_system != 'Darwin'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/b0/e5/2bf2daa9c98658f1474bb64e7de030cbc4182b5f2b2196536efedaef02cb/streamlit-1.40.2.tar.gz", hash = "sha256:0cc131fc9b18065feaff8f6f241c81164ad37d8d9e3a85499a0240aaaf6a6a61", size = 8265763 }
+sdist = { url = "https://files.pythonhosted.org/packages/78/33/14b5ac0369ecf0af675911e5e84b934e6fcc2cec850857d2390eb373b0a6/streamlit-1.41.1.tar.gz", hash = "sha256:6626d32b098ba1458b71eebdd634c62af2dd876380e59c4b6a1e828a39d62d69", size = 8712473 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ae/53/418536f5d0b87bfbe7bbd8c001983c27e9474f82723bd2e529660fd9a534/streamlit-1.40.2-py2.py3-none-any.whl", hash = "sha256:7f6d1379a590f9625a6aee79ca73ceccff03cd2e05a3acbe5fe98915c27a7ffe", size = 8644775 },
+    { url = "https://files.pythonhosted.org/packages/c2/87/b2e162869500062a94dde7589c167367b5538dab6eacce2e7c0f00d5c9c5/streamlit-1.41.1-py2.py3-none-any.whl", hash = "sha256:0def00822480071d642e6df36cd63c089f991da3a69fd9eb4ab8f65ce27de4e0", size = 9100386 },
 ]

 [[package]]
@@ -1736,6 +2085,15 @@ wheels = [
    { url = "https://files.pythonhosted.org/packages/61/cc/58b1adeb1bb46228442081e746fcdbc4540905c87e8add7c277540934edb/tornado-6.4.2-cp38-abi3-win_amd64.whl", hash = "sha256:908b71bf3ff37d81073356a5fadcc660eb10c1476ee6e2725588626ce7e5ca38", size = 438907 },
 ]

+[[package]]
+name = "traitlets"
+version = "5.14.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/eb/79/72064e6a701c2183016abbbfedaba506d81e30e232a68c9f0d6f6fcd1574/traitlets-5.14.3.tar.gz", hash = "sha256:9ed0579d3502c94b4b3732ac120375cda96f923114522847de4b3bb98b96b6b7", size = 161621 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/00/c0/8f5d070730d7836adc9c9b6408dec68c6ced86b304a9b26a14df072a6e8c/traitlets-5.14.3-py3-none-any.whl", hash = "sha256:b74e89e397b1ed28cc831db7aea759ba6640cb3de13090ca145426688ff1ac4f", size = 85359 },
+]
+
 [[package]]
 name = "typer-slim"
 version = "0.13.1"
@@ -1833,15 +2191,12 @@ wheels = [
 ]

 [[package]]
-name = "werkzeug"
-version = "3.1.3"
+name = "wcwidth"
+version = "0.2.13"
 source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "markupsafe" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/9f/69/83029f1f6300c5fb2471d621ab06f6ec6b3324685a2ce0f9777fd4a8b71e/werkzeug-3.1.3.tar.gz", hash = "sha256:60723ce945c19328679790e3282cc758aa4a6040e4bb330f53d30fa546d44746", size = 806925 }
+sdist = { url = "https://files.pythonhosted.org/packages/6c/63/53559446a878410fc5a5974feb13d31d78d752eb18aeba59c7fef1af7598/wcwidth-0.2.13.tar.gz", hash = "sha256:72ea0c06399eb286d978fdedb6923a9eb47e1c486ce63e9b4e64fc18303972b5", size = 101301 }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/52/24/ab44c871b0f07f491e5d2ad12c9bd7358e527510618cb1b803a88e986db1/werkzeug-3.1.3-py3-none-any.whl", hash = "sha256:54b78bf3716d19a65be4fceccc0d1d7b89e608834989dfae50ea87564639213e", size = 224498 },
+    { url = "https://files.pythonhosted.org/packages/fd/84/fd2ba7aafacbad3c4201d395674fc6348826569da3c0937e75505ead3528/wcwidth-0.2.13-py2.py3-none-any.whl", hash = "sha256:3da69048e4540d84af32131829ff948f1e022c1c6bdb8d6102117aac784f6859", size = 34166 },
 ]

 [[package]]
Author	SHA1	Message	Date
James R. Barlow	e4274a956d	v16.9.0 release notes	2025-02-07 00:53:08 -08:00
James R. Barlow	19af116034	Tidy whitespace	2025-02-06 00:40:35 -08:00
jbarlowandGitHub	a5896c45e8	Merge pull request #1466 from 0dinD/fix-hocr-caption	2025-02-06 00:38:59 -08:00
Odin Dahlström	b7d63f3dc1	Process ocr_caption lines	2025-01-30 17:49:06 +01:00
James R. Barlow	137b054f43	Adjust test again for older Ghostscript	2025-01-27 23:44:37 -08:00
James R. Barlow	e6daa28c6d	Merge branch 'main' of github.com:ocrmypdf/OCRmyPDF	2025-01-25 16:55:53 -08:00
James R. Barlow	2512093076	Don't build PDF documentation anymore to fix RTD build issues	2025-01-15 16:17:12 -08:00
Quentin FuxaandGitHub	66bc4a3733	Improve docs for _progressbar.py (#1456 )	2025-01-09 12:21:21 -08:00
James R. Barlow	65df44f670	Modify tests to deal with variety of Ghostscript versions	2025-01-09 02:14:29 -08:00
James R. Barlow	6edc749023	Fix error handling when PDF contains an invalid image with both ImageMask and ColorSpace set Fixes #1453	2025-01-07 00:27:07 -08:00
James R. Barlow	cff98d258e	Upgrade to Alpine 3.21	2025-01-05 08:53:02 -08:00
James R. Barlow	d1fc77e1b6	docs: add imgconverter	2025-01-04 12:39:55 -08:00
James R. Barlow	17eed0529a	Update notes	2025-01-04 12:21:46 -08:00
James R. Barlow	f02353686d	s/input/output	2025-01-04 12:18:07 -08:00
James R. Barlow	32813a3c3d	Merge remote-tracking branch 'origin/dependabot/github_actions/astral-sh/setup-uv-5'	2025-01-04 12:10:18 -08:00
James R. Barlow	073a434ab3	Fix webservice interactions with Docker	2025-01-04 12:09:32 -08:00
James R. Barlow	f390e7f9d1	Add cache to Dockerfiles	2025-01-04 12:09:11 -08:00
James R. Barlow	bfbe571f12	docs: fix more rst formatting issues	2025-01-04 10:59:52 -08:00
James R. Barlow	368568b8ea	Change yaml strings in release script	2025-01-04 01:05:27 -08:00
James R. Barlow	55e7177dbe	Present similar interface in webservice.py	2025-01-04 01:04:58 -08:00
James R. Barlow	b486df7e2d	docs: auto update year	2025-01-04 01:04:29 -08:00
James R. Barlow	74a84b6ae9	Fix numerous documentation build problems	2025-01-03 12:23:42 -08:00
James R. Barlow	cfebf1dc8b	alpine: fix pyarrow name again	2025-01-01 20:30:12 -08:00
James R. Barlow	1aaff4af6f	alpine: use pyarrow package for webservice	2025-01-01 18:45:27 -08:00
James R. Barlow	36c82e0659	Add debugging helper scripts	2025-01-01 18:03:15 -08:00
James R. Barlow	522f9d5f56	Merge branch 'pr/pajowu/1448'	2025-01-01 18:00:52 -08:00
James R. Barlow	796e424ee5	graft: Handle stack underflow	2025-01-01 18:00:39 -08:00
James R. Barlow	d87db6cad0	Merge branch 'pr/pajowu/1446'	2025-01-01 17:50:33 -08:00
James R. Barlow	dd6ed4c5f8	Switch to streamlit based web app	2025-01-01 17:26:22 -08:00
James R. Barlow	206bab74bc	Improve diagnostics for unidentified image	2025-01-01 17:13:57 -08:00
dependabot[bot]andGitHub	b333480749	Bump astral-sh/setup-uv from 4 to 5 Bumps [astral-sh/setup-uv](https://github.com/astral-sh/setup-uv) from 4 to 5. - [Release notes](https://github.com/astral-sh/setup-uv/releases) - [Commits](https://github.com/astral-sh/setup-uv/compare/v4...v5) --- updated-dependencies: - dependency-name: astral-sh/setup-uv dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com>	2024-12-23 10:08:40 +00:00
James R. Barlow	f71a5ffd61	hocr: comment typo	2024-12-23 01:46:00 -08:00
James R. Barlow	b7c3ea70ed	Try triage workflow helper	2024-12-12 17:00:21 -08:00
Kara Engelhardt	636623ab49	graft: fix invisible text appearing after strip_invisible_text strip_invisible_text resets the text render mode on each `BT` (begin text) command. However the text state is not actually reset for each text element, only for each page. The pdf reference says: > The text state operators can appear outside text objects, and the values they set > are retained across text objects in a single content stream. Like other graphics > state parameters, these parameters are initialized to their default values at the > beginning of each page. > > -- https://opensource.adobe.com/dc-acrobat-sdk-docs/pdfstandards/pdfreference1.7old.pdf#page=397 With the current implementation, a text object is only deleted if it contains a `3 Tr` command (setting the text rendering mode to invalid). However the rendering mode may be set once and then not changed for multiple text objects or set outside of a text object. In that case only the first text object (which contains the `3 Tr`-command) is removed. This not only leaves the other text objects in the pdf, but also makes them visible, since the text object that contained the `3 Tr`-command is removed. This PR updates `strip_invisible_text` to not reset the rendering mode for each object and to keep track of the rendering mode when the graphic state is pushed/popped.	2024-12-11 18:01:12 +01:00
Kara Engelhardt	74253e5fc8	hocr: only add space if boxwidth is positive	2024-12-11 16:23:45 +01:00