Fix Windows issue if no exception

coloredlogs documentation says this is (now?) permitted.

Also import it from the right place.

.docker/Dockerfile

@@ -1,7 +1,7 @@
 # OCRmyPDF
 #
 
-FROM ubuntu:21.04 as base
+FROM ubuntu:22.04 as base
 
 ENV LANG=C.UTF-8
 ENV TZ=UTC

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

@@ -22,7 +22,7 @@ Run with verbosity or higher `-v1` to see more detailed logging. This informatio
 **Example file**
 If your issue is a problem that affects only certain files, and we will require an input file (PDF or image) that demonstrates your issue.
 
-Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/jbarlow83/OCRmyPDF/wiki) for OCRmyPDF's author only.
+Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/ocrmypdf/OCRmyPDF/wiki) for OCRmyPDF's author only.
 
 Links to files hosted elsewhere are perfectly acceptable. You could also look in ``tests/resources`` and see if any of those files reproduce your issue.
 

.github/ISSUE_TEMPLATE/3-feature_request.md

@@ -19,7 +19,7 @@ A clear and concise description of any alternative solutions or features you've
 **Example file**
 If your issue concerns how OCRmyPDF processes certain files, and please provide an example file that helps illustrate how OCRmyPDF's output could be improve.
 
-Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/jbarlow83/OCRmyPDF/wiki) for OCRmyPDF's author only.
+Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/ocrmypdf/OCRmyPDF/wiki) for OCRmyPDF's author only.
 
 Links to files hosted elsewhere are perfectly acceptable. You could also look in ``tests/resources`` and see if any of those files reproduce your issue.
 

.github/workflows/build.yml

@@ -21,17 +21,19 @@ jobs:
       matrix:
         include:
           - os: ubuntu-18.04
-            python: 3.7
+            python: "3.7"
           - os: ubuntu-20.04
-            python: 3.8
+            python: "3.8"
           - os: ubuntu-20.04
-            python: 3.9
+            python: "3.9"
+          - os: ubuntu-20.04
+            python: "3.10"
           - os: ubuntu-latest
-            python: 3.9
+            python: "3.9"
           - os: ubuntu-latest
-            python: "pypy-3.7"
+            python: "pypy-3.8"
           - os: ubuntu-latest
-            python: 3.9
+            python: "3.9"
             tesseract5: true
 
     env:
@@ -120,7 +122,7 @@ jobs:
     strategy:
       matrix:
         os: [macos-latest]
-        python: ["3.9"]
+        python: ["3.9", "3.10"]
 
     env:
       OS: ${{ matrix.os }}
@@ -175,7 +177,7 @@ jobs:
     strategy:
       matrix:
         os: [windows-latest]
-        python: ["3.9"]
+        python: ["3.9", "3.10"]
 
     env:
       OS: ${{ matrix.os }}
@@ -194,7 +196,7 @@ jobs:
       - name: Install system packages
         run: |
           choco install --yes --no-progress --pre tesseract
-          choco install --yes --no-progress --ignore-checksums ghostscript pngquant
+          choco install --yes --no-progress --ignore-checksums ghostscript
 
       - name: Install Python packages
         run: |

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
+    rev: v4.2.0
     hooks:
       - id: check-case-conflict
       - id: check-merge-conflict
@@ -8,26 +8,26 @@ repos:
       - id: check-yaml
       - id: debug-statements
   - repo: https://github.com/pycqa/isort
-    rev: 5.9.3
+    rev: 5.10.1
     hooks:
       - id: isort
         args: ["--profile", "black"]
   - repo: https://github.com/psf/black
-    rev: 21.9b0
+    rev: 22.3.0
     hooks:
       - id: black
         language_version: python
   - repo: https://github.com/asottile/setup-cfg-fmt
-    rev: v1.19.0
+    rev: v1.20.1
     hooks:
       - id: setup-cfg-fmt
   - repo: https://github.com/asottile/pyupgrade
-    rev: v2.29.0
+    rev: v2.32.1
     hooks:
       - id: pyupgrade
         args: ["--py37-plus"]
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.910-1
+    rev: v0.950
     hooks:
       - id: mypy
         additional_dependencies:

README.md

@@ -1,9 +1,7 @@
 <img src="docs/images/logo.svg" width="240" alt="OCRmyPDF">
 
-[![Build Status](https://github.com/jbarlow83/OCRmyPDF/actions/workflows/build.yml/badge.svg)](https://github.com/jbarlow83/OCRmyPDF/actions/workflows/build.yml) [![PyPI version][pypi]](https://pypi.org/project/ocrmypdf/) ![Homebrew version][homebrew] ![ReadTheDocs][docs] ![Python versions][pyversions]
+[![Build Status](https://github.com/ocrmypdf/OCRmyPDF/actions/workflows/build.yml/badge.svg)](https://github.com/ocrmypdf/OCRmyPDF/actions/workflows/build.yml) [![PyPI version][pypi]](https://pypi.org/project/ocrmypdf/) ![Homebrew version][homebrew] ![ReadTheDocs][docs] ![Python versions][pyversions]
 
-[azure]: https://dev.azure.com/jim0585/ocrmypdf/_apis/build/status/jbarlow83.OCRmyPDF?branchName=master
-[travis]: https://travis-ci.org/jbarlow83/OCRmyPDF.svg?branch=master "Travis build status"
 [pypi]: https://img.shields.io/pypi/v/ocrmypdf.svg "PyPI version"
 [homebrew]: https://img.shields.io/homebrew/v/ocrmypdf.svg "Homebrew version"
 [docs]: https://readthedocs.org/projects/ocrmypdf/badge/?version=latest "RTD"
@@ -106,7 +104,7 @@ ocrmypdf --help
 
 Our [documentation is served on Read the Docs](https://ocrmypdf.readthedocs.io/en/latest/index.html).
 
-Please report issues on our [GitHub issues](https://github.com/jbarlow83/OCRmyPDF/issues) page, and follow the issue template for quick response.
+Please report issues on our [GitHub issues](https://github.com/ocrmypdf/OCRmyPDF/issues) page, and follow the issue template for quick response.
 
 ## Requirements
 

debian/copyright

@@ -1,7 +1,7 @@
 Format: https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
 Upstream-Name: OCRmyPDF
 Upstream-Contact: James R. Barlow <barlow.jim@gmail.com>
-Source: https://github.com/jbarlow83/OCRmyPDF
+Source: https://github.com/ocrmypdf/OCRmyPDF
 
 Files: *
 Copyright:

docs/advanced.rst

@@ -67,11 +67,11 @@ without modifying the PDF. This is to ensure that PDFs that were
 previously OCRed or were "born digital" rather than scanned are not
 processed.
 
-If ``--skip-text`` is issued, then no OCR will be performed on pages
+If ``--skip-text`` is issued, then no image processing or OCR will be
-that already have text. The page will be copied to the output. This may
+performed on pages that already have text. The page will be copied to
-be useful for documents that contain both "born digital" and scanned
+the output. This may be useful for documents that contain both "born
-content, or to use OCRmyPDF to normalize and convert to PDF/A regardless
+digital" and scanned content, or to use OCRmyPDF to normalize and
-of their contents.
+convert to PDF/A regardless of their contents.
 
 If ``--redo-ocr`` is issued, then a detailed text analysis is performed.
 Text is categorized as either visible or invisible. Invisible text (OCR)

docs/conf.py

@@ -42,7 +42,7 @@ extensions = [
 # Extension settings
 intersphinx_mapping = {'https://docs.python.org/': None}
 napoleon_use_rtype = False
-issues_github_path = "jbarlow83/OCRmyPDF"
+issues_github_path = "ocrmypdf/OCRmyPDF"
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']
@@ -63,7 +63,7 @@ master_doc = 'index'
 # General information about the project.
 project = 'ocrmypdf'
 copyright = (
-    '2021, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
+    '2022, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
 )
 author = 'James R. Barlow'
 

docs/cookbook.rst

@@ -243,10 +243,11 @@ You can also optimize all images without performing any OCR:
 
     ocrmypdf --tesseract-timeout=0 --optimize 3 --skip-text input.pdf output.pdf
 
-Perform OCR only certain pages
+Process only certain pages
-------------------------------
+--------------------------
 
-You can ask OCRmyPDF to only apply OCR to certain pages.
+You can ask OCRmyPDF to only apply `image processing <#image-processing>`__
+and OCR to certain pages.
 
 .. code-block:: bash
 
@@ -260,10 +261,10 @@ overlap pages. OCRmyPDF does not currently account for document page numbers,
 such as an introduction section of a book that uses Roman numerals. It simply
 counts the number of virtual pieces of paper since the start.
 
-Regardless of the argument to ``--pages``, OCRmyPDF will optimize all pages in
+Regardless of the argument to ``--pages``, OCRmyPDF will optimize all pages/images
-the file and convert it to PDF/A, unless you disable those options. In this
+in the file and convert it to PDF/A, unless you disable those options. Both of these
-example, we want to OCR only the title and otherwise change the PDF as little
+steps are "whole file" operations. In this example, we want to OCR only the title
-as possible:
+and otherwise change the PDF as little as possible:
 
 .. code-block:: bash
 

docs/docker.rst

@@ -59,7 +59,7 @@ Using the Docker image on the command line
 ==========================================
 
 **Unlike typical Docker containers**, in this section the OCRmyPDF Docker
-container is emphemeral – it runs for one OCR job and terminates, just like a
+container is ephemeral – it runs for one OCR job and terminates, just like a
 command line program. We are using Docker to deliver an application (as opposed
 to the more conventional case, where a Docker container runs as a server).
 

docs/images/logo-square-256.svg

@@ -0,0 +1,239 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   width="256"
+   height="256"
+   viewBox="0 0 256 256.00001"
+   version="1.1"
+   xml:space="preserve"
+   style="clip-rule:evenodd;fill-rule:evenodd;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:1.5"
+   id="svg270"
+   sodipodi:docname="logo-square-256.svg"
+   inkscape:export-filename="/home/jb/src/ocrmypdf/docs/images/logo-square.png"
+   inkscape:export-xdpi="96"
+   inkscape:export-ydpi="96"
+   inkscape:version="1.1.2 (0a00cf5339, 2022-02-04)"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:serif="http://www.serif.com/"><metadata
+   id="metadata276"><rdf:RDF><cc:Work
+       rdf:about=""><dc:format>image/svg+xml</dc:format><dc:type
+         rdf:resource="http://purl.org/dc/dcmitype/StillImage" /></cc:Work></rdf:RDF></metadata><defs
+   id="defs274" /><sodipodi:namedview
+   pagecolor="#ffffff"
+   bordercolor="#666666"
+   borderopacity="1"
+   objecttolerance="10"
+   gridtolerance="10"
+   guidetolerance="10"
+   inkscape:pageopacity="0"
+   inkscape:pageshadow="2"
+   inkscape:window-width="2396"
+   inkscape:window-height="1691"
+   id="namedview272"
+   showgrid="false"
+   lock-margins="false"
+   inkscape:zoom="2.0079523"
+   inkscape:cx="189.74554"
+   inkscape:cy="54.533168"
+   inkscape:window-x="26"
+   inkscape:window-y="23"
+   inkscape:window-maximized="0"
+   inkscape:current-layer="svg270"
+   inkscape:pagecheckerboard="0"
+   width="256px"
+   fit-margin-top="0"
+   fit-margin-left="0"
+   fit-margin-right="0"
+   fit-margin-bottom="0" />
+    <g
+   id="svg"
+   transform="matrix(0.48534351,0,0,0.4057699,1.8106874,71.192214)">
+        <rect
+   x="0"
+   y="0"
+   width="520"
+   height="280"
+   style="fill:#ffffff"
+   id="rect188" />
+        <g
+   transform="matrix(1.03522,0,0,1.23823,-69.7528,-83.422)"
+   id="g267">
+            <g
+   transform="translate(243.977,20.0703)"
+   id="g218">
+                <g
+   id="Page">
+                    <g
+   transform="matrix(0.961773,0,0,1.05962,6.19811,-3.01071)"
+   id="g192">
+                        <path
+   d="m 328.5,97.682 c 0,-1.217 -0.517,-2.386 -1.444,-3.264 -7.03,-6.66 -37.614,-35.638 -44.828,-42.474 -0.977,-0.925 -2.327,-1.448 -3.738,-1.448 -13.997,0 -90.407,0 -111.151,0 -2.871,0 -5.198,2.113 -5.198,4.718 0,27.837 0,170.351 0,198.186 0,2.605 2.327,4.717 5.197,4.717 24.904,0 131.821,0 156.2,0 2.74,0 4.962,-2.016 4.962,-4.504 0,-24.345 0,-139.717 0,-155.931 z"
+   style="fill:#fdfdfd;stroke:#333333;stroke-width:3.95px"
+   id="path190" />
+                    </g>
+                    <g
+   id="Dog-ear"
+   serif:id="Dog ear"
+   transform="translate(-4,2)">
+                        <path
+   d="m 277.072,48.496 v 45.352 c 0,1.324 0.526,2.593 1.462,3.529 0.936,0.936 2.205,1.462 3.529,1.462 12.485,0 44.078,0 44.078,0"
+   style="fill:#f5f5f5;stroke:#333333;stroke-width:4px"
+   id="path194" />
+                    </g>
+                </g>
+                <g
+   transform="translate(-29.6816,-0.395178)"
+   id="g216">
+                    <g
+   transform="matrix(1.00243,0,0,1.11818,-144.72,-8.80181)"
+   id="g200">
+                        <path
+   d="m 465.73,119.654 c 0,-2.049 -1.856,-3.713 -4.142,-3.713 H 310.259 c -2.286,0 -4.142,1.664 -4.142,3.713 v 63.454 c 0,2.049 1.856,3.713 4.142,3.713 h 151.329 c 2.286,0 4.142,-1.664 4.142,-3.713 z"
+   style="fill:#f80000;stroke:#ffffff;stroke-width:3.77px"
+   id="path198" />
+                    </g>
+                    <g
+   transform="matrix(1.24571,0,0,1.35864,116.812,84.3924)"
+   id="g214">
+                        <g
+   transform="matrix(64,0,0,64,42.1437,77.6203)"
+   id="g204">
+                            <path
+   d="m 0.084,0 v -0.68 h 0.213 c 0.074,0 0.137,0.017 0.19,0.05 0.053,0.034 0.079,0.09 0.079,0.168 0,0.077 -0.028,0.134 -0.085,0.17 -0.057,0.037 -0.121,0.055 -0.193,0.055 H 0.213 V 0 Z m 0.209,-0.572 h -0.08 v 0.228 h 0.082 c 0.039,0 0.07,-0.009 0.094,-0.027 0.024,-0.017 0.037,-0.045 0.04,-0.083 0,-0.044 -0.012,-0.075 -0.036,-0.092 -0.024,-0.017 -0.057,-0.026 -0.1,-0.026 z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path202" />
+                        </g>
+                        <g
+   transform="matrix(64,0,0,64,79.7117,77.6203)"
+   id="g208">
+                            <path
+   d="M 0.332,0 H 0.084 v -0.68 h 0.252 c 0.105,0 0.182,0.032 0.233,0.095 0.051,0.063 0.076,0.144 0.076,0.241 0,0.105 -0.027,0.189 -0.082,0.251 C 0.508,-0.031 0.431,0 0.332,0 Z M 0.337,-0.57 H 0.213 v 0.461 H 0.33 c 0.055,0 0.099,-0.018 0.132,-0.054 C 0.495,-0.199 0.511,-0.259 0.511,-0.344 0.511,-0.415 0.497,-0.47 0.469,-0.51 0.441,-0.55 0.397,-0.57 0.337,-0.57 Z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path206" />
+                        </g>
+                        <g
+   transform="matrix(64,0,0,64,123.424,77.6203)"
+   id="g212">
+                            <path
+   d="M 0.405,-0.288 H 0.213 V 0 H 0.084 v -0.68 h 0.385 l 0.02,0.102 H 0.213 v 0.189 h 0.173 z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path210" />
+                        </g>
+                    </g>
+                </g>
+            </g>
+            <g
+   transform="matrix(1,0,0,1.52217,67.3796,10.7507)"
+   id="g222">
+                <rect
+   x="23.500999"
+   y="81.300003"
+   width="162.30499"
+   height="61.77"
+   style="fill:#b4d5ff"
+   id="rect220" />
+            </g>
+            <g
+   transform="matrix(0.967536,0,0,0.961535,5.90498,47.9703)"
+   id="g236">
+                <g
+   transform="matrix(90.4804,0,0,90.4804,82.6698,167.705)"
+   id="g226">
+                    <path
+   d="m 0.057,-0.337 c 0,-0.105 0.027,-0.19 0.082,-0.257 0.055,-0.066 0.132,-0.1 0.231,-0.102 0.107,0 0.186,0.034 0.237,0.103 0.051,0.069 0.077,0.152 0.077,0.249 0,0.105 -0.027,0.191 -0.082,0.258 -0.055,0.067 -0.133,0.1 -0.232,0.1 C 0.264,0.014 0.185,-0.02 0.134,-0.089 0.083,-0.157 0.057,-0.24 0.057,-0.337 Z m 0.135,-0.001 c 0,0.071 0.014,0.13 0.043,0.175 0.029,0.045 0.073,0.068 0.134,0.068 0.055,0 0.098,-0.02 0.131,-0.061 0.033,-0.041 0.049,-0.103 0.049,-0.188 0,-0.071 -0.014,-0.129 -0.043,-0.174 -0.029,-0.045 -0.073,-0.068 -0.134,-0.068 -0.053,0 -0.097,0.022 -0.13,0.067 -0.033,0.045 -0.05,0.105 -0.05,0.181 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path224" />
+                </g>
+                <g
+   transform="matrix(90.4804,0,0,90.4804,147.906,167.705)"
+   id="g230">
+                    <path
+   d="M 0.505,-0.557 C 0.473,-0.567 0.448,-0.574 0.429,-0.579 0.41,-0.583 0.388,-0.585 0.361,-0.585 c -0.054,0 -0.096,0.022 -0.125,0.066 -0.029,0.044 -0.044,0.104 -0.044,0.181 0,0.066 0.012,0.123 0.037,0.171 0.025,0.048 0.066,0.072 0.124,0.072 0.029,0 0.056,-0.003 0.081,-0.009 0.025,-0.006 0.047,-0.013 0.068,-0.022 L 0.551,-0.03 C 0.525,-0.017 0.494,-0.006 0.457,0.002 0.42,0.01 0.388,0.014 0.36,0.014 0.254,0.014 0.177,-0.02 0.129,-0.088 0.081,-0.156 0.057,-0.239 0.057,-0.337 c 0,-0.105 0.027,-0.19 0.08,-0.257 0.053,-0.067 0.129,-0.1 0.228,-0.1 0.02,0 0.048,0.003 0.083,0.01 0.035,0.007 0.068,0.018 0.097,0.034 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path228" />
+                </g>
+                <g
+   transform="matrix(90.4804,0,0,90.4804,199.751,167.705)"
+   id="g234">
+                    <path
+   d="m 0.293,-0.572 h -0.08 v 0.208 h 0.082 c 0.039,0 0.071,-0.008 0.096,-0.024 0.025,-0.015 0.038,-0.041 0.038,-0.077 0,-0.038 -0.012,-0.065 -0.036,-0.082 -0.024,-0.017 -0.057,-0.025 -0.1,-0.025 z M 0.479,0 0.335,-0.26 C 0.328,-0.259 0.32,-0.259 0.312,-0.259 0.304,-0.258 0.296,-0.258 0.288,-0.258 H 0.213 V 0 H 0.084 v -0.68 h 0.213 c 0.074,0 0.137,0.017 0.19,0.051 0.053,0.034 0.079,0.087 0.079,0.158 0,0.042 -0.011,0.078 -0.032,0.108 -0.022,0.031 -0.05,0.054 -0.084,0.071 L 0.617,0 Z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path232" />
+                </g>
+            </g>
+            <g
+   transform="matrix(0.916882,0,0,1,121.475,-32.6535)"
+   id="g246">
+                <g
+   transform="matrix(86.953,0,0,86.953,152.996,241.878)"
+   id="g240">
+                    <path
+   d="M 0.479,-0.428 C 0.5,-0.451 0.527,-0.47 0.562,-0.484 c 0.034,-0.013 0.065,-0.02 0.092,-0.02 0.066,0 0.113,0.019 0.141,0.058 0.027,0.039 0.041,0.086 0.041,0.142 V 0 H 0.705 v -0.298 c 0,-0.031 -0.007,-0.054 -0.022,-0.071 -0.015,-0.016 -0.036,-0.024 -0.064,-0.024 -0.019,0 -0.038,0.005 -0.059,0.015 -0.021,0.01 -0.039,0.021 -0.056,0.034 0.001,0.007 0.001,0.013 0.002,0.02 0.001,0.007 0.001,0.013 0.001,0.02 V 0 H 0.376 v -0.298 c 0,-0.031 -0.007,-0.054 -0.022,-0.071 -0.015,-0.016 -0.036,-0.024 -0.063,-0.024 -0.017,0 -0.033,0.003 -0.05,0.01 -0.017,0.007 -0.034,0.016 -0.049,0.027 V 0 H 0.062 V -0.485 H 0.13 l 0.032,0.044 c 0.022,-0.02 0.049,-0.035 0.08,-0.047 0.031,-0.011 0.058,-0.016 0.083,-0.016 0.038,0 0.07,0.007 0.095,0.02 0.025,0.014 0.045,0.033 0.059,0.056 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path238" />
+                </g>
+                <g
+   transform="matrix(86.953,0,0,86.953,228.906,241.878)"
+   id="g244">
+                    <path
+   d="M 0.156,0.023 0.179,-0.034 0.006,-0.467 0.14,-0.485 0.252,-0.191 0.358,-0.485 H 0.495 L 0.278,0.064 C 0.263,0.103 0.236,0.137 0.197,0.165 0.158,0.193 0.118,0.212 0.075,0.222 L 0.029,0.115 C 0.052,0.105 0.077,0.093 0.104,0.079 0.13,0.064 0.147,0.046 0.156,0.023 Z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path242" />
+                </g>
+            </g>
+            <g
+   id="Selectors"
+   transform="matrix(0.965977,0,0,0.807602,67.3796,67.3718)">
+                <g
+   id="Right-selector"
+   serif:id="Right selector">
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,2.07044,0)"
+   id="g250">
+                        <path
+   d="M 185.806,161.156 V 67.132"
+   style="fill:none;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="path248" />
+                    </g>
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,161.788,169.469)"
+   id="g254">
+                        <circle
+   cx="31.523001"
+   cy="34.313999"
+   r="10.021"
+   style="fill:#4c9fff;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="circle252" />
+                    </g>
+                </g>
+                <g
+   id="Left-selector"
+   serif:id="Left selector">
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,-170.092,0)"
+   id="g259">
+                        <path
+   d="M 185.806,161.156 V 67.132"
+   style="fill:none;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="path257" />
+                    </g>
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,-10.3742,28.2274)"
+   id="g263">
+                        <circle
+   cx="31.523001"
+   cy="34.313999"
+   r="10.021"
+   style="fill:#4c9fff;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="circle261" />
+                    </g>
+                </g>
+            </g>
+        </g>
+    </g>
+</svg>

docs/installation.rst

@@ -12,21 +12,23 @@ system/platform. This version may be out of date, however.
 
 These platforms have one-liner installs:
 
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
-| Debian, Ubuntu                | ``apt install ocrmypdf``      |
+| Debian, Ubuntu                | ``apt install ocrmypdf``                |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
-| Windows Subsystem for Linux   | ``apt install ocrmypdf``      |
+| Windows Subsystem for Linux   | ``apt install ocrmypdf``                |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
-| Fedora                        | ``dnf install ocrmypdf``      |
+| Fedora                        | ``dnf install ocrmypdf``                |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
-| macOS                         | ``brew install ocrmypdf``     |
+| macOS                         | ``brew install ocrmypdf``               |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
-| LinuxBrew                     | ``brew install ocrmypdf``     |
+| LinuxBrew                     | ``brew install ocrmypdf``               |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
-| FreeBSD                       | ``pkg install py38-ocrmypdf`` |
+| FreeBSD                       | ``pkg install textproc/py-ocrmypdf``    |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
-| Conda (WSL, macOS, Linux)     | ``conda install ocrmypdf``    |
+| Conda (WSL, macOS, Linux)     | ``conda install ocrmypdf``              |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
+| Snap (snapcraft packaging)    | ``snap install ocrmypdf``               |
++-------------------------------+-----------------------------------------+
 
 More detailed procedures are outlined below. If you want to do a manual
 install, or install a more recent version than your platform provides, read on.
@@ -42,10 +44,10 @@ Debian and Ubuntu 18.04 or newer
 --------------------------------
 
 .. |deb-stable| image:: https://repology.org/badge/version-for-repo/debian_stable/ocrmypdf.svg
-    :alt: Debian 9 stable ("stretch")
+    :alt: Debian stable
 
 .. |deb-testing| image:: https://repology.org/badge/version-for-repo/debian_testing/ocrmypdf.svg
-    :alt: Debian 10 testing ("buster")
+    :alt: Debian testing
 
 .. |deb-unstable| image:: https://repology.org/badge/version-for-repo/debian_unstable/ocrmypdf.svg
     :alt: Debian unstable
@@ -56,8 +58,8 @@ Debian and Ubuntu 18.04 or newer
 .. |ubu-2004| image:: https://repology.org/badge/version-for-repo/ubuntu_20_04/ocrmypdf.svg
     :alt: Ubuntu 20.04 LTS
 
-.. |ubu-2110| image:: https://repology.org/badge/version-for-repo/ubuntu_21_10/ocrmypdf.svg
+.. |ubu-2204| image:: https://repology.org/badge/version-for-repo/ubuntu_22_04/ocrmypdf.svg
-    :alt: Ubuntu 21.10
+    :alt: Ubuntu 22.04 LTS
 
 +-----------------------------------------------+
 | **OCRmyPDF versions in Debian & Ubuntu**      |
@@ -66,7 +68,7 @@ Debian and Ubuntu 18.04 or newer
 +-----------------------------------------------+
 | |deb-stable| |deb-testing| |deb-unstable|     |
 +-----------------------------------------------+
-| |ubu-1804| |ubu-2004| |ubu-2110|              |
+| |ubu-1804| |ubu-2004| |ubu-2204|              |
 +-----------------------------------------------+
 
 Users of Debian 9 ("stretch") or later, or Ubuntu 18.04 or later, including users
@@ -80,8 +82,7 @@ As indicated in the table above, Debian and Ubuntu releases may lag
 behind the latest version. If the version available for your platform is
 out of date, you could opt to install the latest version from source.
 See `Installing HEAD revision from
-sources <#installing-head-revision-from-sources>`__. Ubuntu 16.10 to 17.10
+sources <#installing-head-revision-from-sources>`__.
-inclusive also had ocrmypdf, but these versions are end of life.
 
 For full details on version availability for your platform, check the
 `Debian Package Tracker <https://tracker.debian.org/pkg/ocrmypdf>`__ or
@@ -91,19 +92,19 @@ For full details on version availability for your platform, check the
 
    OCRmyPDF for Debian and Ubuntu currently omit the JBIG2 encoder.
    OCRmyPDF works fine without it but will produce larger output files.
-   If you build jbig2enc from source, ocrmypdf 7.0.0 and later will
+   If you build jbig2enc from source, ocrmypdf will
    automatically detect it (specifically the ``jbig2`` binary) on the
    ``PATH``. To add JBIG2 encoding, see :ref:`jbig2`.
 
 Fedora
 ------
 
-.. |fedora-34| image:: https://repology.org/badge/version-for-repo/fedora_34/ocrmypdf.svg
-    :alt: Fedora 34
-
 .. |fedora-35| image:: https://repology.org/badge/version-for-repo/fedora_35/ocrmypdf.svg
     :alt: Fedora 35
 
+.. |fedora-36| image:: https://repology.org/badge/version-for-repo/fedora_36/ocrmypdf.svg
+    :alt: Fedora 36
+
 .. |fedora-rawhide| image:: https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg
     :alt: Fedore Rawhide
 
@@ -112,7 +113,7 @@ Fedora
 +-----------------------------------------------+
 | |latest|                                      |
 +-----------------------------------------------+
-| |fedora-34| |fedora-35| |fedora-rawhide|      |
+| |fedora-35| |fedora-36| |fedora-rawhide|      |
 +-----------------------------------------------+
 
 Users of Fedora 29 or later may simply
@@ -138,9 +139,29 @@ from sources <#installing-head-revision-from-sources>`__.
 
 .. _ubuntu-lts-latest:
 
-Installing the latest version on Ubuntu 20.04 LTS
+Installing the latest version on Ubuntu 22.04 LTS
 -------------------------------------------------
 
+Ubuntu 22.04 includes ocrmypdf 13.4.0 - you can install that with 
+``apt install ocrmypdf``. To install a more recent version for the current
+user, follow these steps:
+
+.. code-block:: bash
+
+    sudo apt-get update
+    sudo apt-get -y install ocrmypdf python3-pip
+
+    pip install --user --upgrade ocrmypdf
+
+If you get the message ``WARNING: The script ocrmypdf is installed in 
+'/home/$USER/.local/bin' which is not on PATH.``, you may need to re-login
+or open a new shell, or manually add this to your user's PATH.
+
+To add JBIG2 encoding, see :ref:`jbig2`.
+
+Ubuntu 20.04 LTS
+----------------
+
 Ubuntu 20.04 includes ocrmypdf 9.6.0 - you can install that with ``apt``. To
 install a more recent version, uninstall the system-provided version of
 ocrmypdf, and install the following dependencies:
@@ -171,6 +192,8 @@ To install for the current user only:
     export PATH=$HOME/.local/bin:$PATH
     pip3 install --user ocrmypdf
 
+To add JBIG2 encoding, see :ref:`jbig2`.
+
 Ubuntu 18.04 LTS
 ----------------
 
@@ -291,46 +314,6 @@ To install OCRmyPDF for Alpine Linux:
 
     apk add ocrmypdf
 
-Mageia 7
---------
-
-There is no OS-level packaging available for Mageia, so you must install the
-dependencies:
-
-.. code-block:: bash
-
-    # As root user
-    urpmi.update -a
-    urpmi \
-        ghostscript \
-        icc-profiles-openicc \
-        jbig2dec \
-        pngquant \
-        python3-pip \
-        python3-distutils-extra \
-        python3-pkg-resources \
-        python3-reportlab \
-        qpdf \
-        tesseract \
-        tesseract-osd \
-        tesseract-eng \
-        tesseract-fra
-
-To install ocrmypdf for the system:
-
-.. code-block:: bash
-
-    # As root user
-    pip3 install ocrmypdf
-    ldconfig
-
-Or, to install for the current user only:
-
-.. code-block:: bash
-
-    export PATH=$HOME/.local/bin:$PATH
-    pip3 install --user ocrmypdf
-
 Other Linux packages
 --------------------
 
@@ -365,19 +348,6 @@ languages you can optionally install them all:
 
     brew install tesseract-lang  # Optional: Install all language packs
 
-.. note::
-
-   Users who previously installed OCRmyPDF on macOS using
-   ``pip install ocrmypdf`` should remove the pip version
-   (``pip3 uninstall ocrmypdf``) before switching to the Homebrew
-   version.
-
-.. note::
-
-   Users who previously installed OCRmyPDF from the private tap should
-   switch to the mainline version (``brew untap jbarlow83/ocrmypdf``)
-   and install from there.
-
 Manual installation on macOS
 ----------------------------
 
@@ -411,19 +381,19 @@ Update the homebrew pip:
 
 .. code-block:: bash
 
-    pip3 install --upgrade pip
+    pip install --upgrade pip
 
 You can then install OCRmyPDF from PyPI, for the current user:
 
 .. code-block:: bash
 
-    pip3 install --user ocrmypdf
+    pip install --user ocrmypdf
 
 or system-wide:
 
 .. code-block:: bash
 
-    pip3 install ocrmypdf
+    pip install ocrmypdf
 
 The command line program should now be available:
 
@@ -485,8 +455,8 @@ to change the PATH.
 Windows Subsystem for Linux
 ---------------------------
 
-#. Install Ubuntu 20.04 for Windows Subsystem for Linux, if not already installed.
+#. Install Ubuntu 22.04 for Windows Subsystem for Linux, if not already installed.
-#. Follow the procedure to install :ref:`OCRmyPDF on Ubuntu 20.04 <ubuntu-lts-latest>`.
+#. Follow the procedure to install :ref:`OCRmyPDF on Ubuntu 22.04 <ubuntu-lts-latest>`.
 #. Open the Windows command prompt and create a symlink:
 
 .. code-block:: powershell
@@ -558,16 +528,13 @@ your command prompt can run the docker "hello world" container.
 Installing on FreeBSD
 =====================
 
-.. image:: https://repology.org/badge/version-for-repo/freebsd/python:ocrmypdf.svg
+.. image:: https://repology.org/badge/version-for-repo/freebsd/ocrmypdf.svg
     :alt: FreeBSD
-    :target: https://repology.org/project/python:ocrmypdf/versions
+    :target: https://repology.org/project/ocrmypdf/versions
-
-FreeBSD 11.3, 12.0, 12.1-RELEASE and 13.0-CURRENT are supported. Other
-versions likely work but have not been tested.
 
 .. code-block:: bash
 
-    pkg install py38-ocrmypdf
+    pkg install textproc/py-ocrmypdf
 
 To install a more recent version, you could attempt to first install the system
 version with ``pkg``, then use ``pip install --user ocrmypdf``.
@@ -616,18 +583,18 @@ try:
 
 .. code-block:: bash
 
-    pip3 install --user ocrmypdf
+    pip install --user ocrmypdf
 
 You should then be able to run ``ocrmypdf --version`` and see that the
 latest version was located.
 
-Since ``pip3 install --user`` does not work correctly on some platforms,
+Since ``pip install --user`` does not work correctly on some platforms,
 notably Ubuntu 16.04 and older, and the Homebrew version of Python,
 instead use this for a system wide installation:
 
 .. code-block:: bash
 
-    pip3 install ocrmypdf
+    pip install ocrmypdf
 
 .. note::
 
@@ -643,13 +610,9 @@ OCRmyPDF currently requires these external programs and libraries to be
 installed, and must be satisfied using the operating system package
 manager. ``pip`` cannot provide them.
 
+The following versions are required:
+
 -  Python 3.7 or newer
--  Ghostscript 9.15 or newer
--  Tesseract 4.0.0-beta or newer
-
-As of ocrmypdf 7.2.1, the following versions are recommended:
-
--  Python 3.9 or newer
 -  Ghostscript 9.23 or newer
 -  Tesseract 4.0.0 or newer
 -  jbig2enc 0.29 or newer
@@ -696,7 +659,7 @@ environment:
 
 .. code-block:: bash
 
-    pip3 install git+https://github.com/jbarlow83/OCRmyPDF.git
+    pip install git+https://github.com/ocrmypdf/OCRmyPDF.git
 
 Or, to install in `development
 mode <https://pythonhosted.org/setuptools/setuptools.html#development-mode>`__,
@@ -704,18 +667,18 @@ allowing customization of OCRmyPDF, use the ``-e`` flag:
 
 .. code-block:: bash
 
-    pip3 install -e git+https://github.com/jbarlow83/OCRmyPDF.git
+    pip install -e git+https://github.com/ocrmypdf/OCRmyPDF.git
 
 You may find it easiest to install in a virtual environment, rather than
 system-wide:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
+    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
     python3 -m venv
     source venv/bin/activate
     cd OCRmyPDF
-    pip3 install .
+    pip install .
 
 However, ``ocrmypdf`` will only be accessible on the system PATH when
 you activate the virtual environment.
@@ -738,8 +701,8 @@ To install all of the development and test requirements:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
+    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
-    python3 -m venv
+    python -m venv
     source venv/bin/activate
     cd OCRmyPDF
     pip install -e .[test]

docs/jbig2.rst

@@ -32,6 +32,9 @@ For all other Linux, you must build a JBIG2 encoder from source:
 
 .. _jbig2-lossy:
 
+Dependencies include libtoolize and libleptonica, which on Ubuntu systems 
+are packaged as libtool and libleptonica-dev.
+
 Lossy mode JBIG2
 ================
 

docs/languages.rst

@@ -54,6 +54,33 @@ to what languages it should search for. Multiple languages can be
 requested using either ``-l eng+fra`` (English and French) or
 ``-l eng -l fra``.
 
+Gentoo users
+============
+
+On Gentoo the package ``app-text/tessdata_fast``, which ``app-text/tesseract`` depends on, handles Tesseract languages.
+It accepts USE flags to select what languages should be installed, these can be set in ``/etc/portage/package.use``.
+Alternatively one can globally set the `L10N use extension <https://wiki.gentoo.org/wiki/Localization/Guide#L10N>`__ in ``/etc/portage/make.conf``.
+This enables these languages for all packages (e.g. including aspell).
+
+.. code-block:: bash
+
+   # Display a list of all Tesseract language packs
+   equery uses app-text/tessdata_fast
+   
+   # Add English and German language support for Tesseract only
+   echo 'app-text/tessdata_fast l10n_de l10n_en' >> /etc/portage/package.use
+   
+   # Add global English and German language support (the `l10n_` from equery has to be omited)
+   echo L10N="de en" >> /etc/portage/make.conf
+   
+   # update system to reflect changed USE flags
+   emerge --update --deep --newuse @world
+
+You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as
+to what languages it should search for. Multiple languages can be
+requested using either ``-l eng+fra`` (English and French) or
+``-l eng -l fra``.
+
 macOS users
 ===========
 

docs/maintainers.rst

@@ -2,7 +2,7 @@
 Maintainer notes
 ================
 
-This is for those who package OCRmyPDF for downstream use.  (Thank you 
+This is for those who package OCRmyPDF for downstream use.  (Thank you
 for your hard work.)
 
 Known ports/packagers
@@ -25,7 +25,7 @@ Non-Python dependencies
 
 Note that we have non-Python dependencies. In particular, OCRmyPDF requires
 Ghostscript and Tesseract OCR to be installed and needs to be able to locate their
-binaries on the system PATH. On Windows, OCRmyPDF will also check the registry 
+binaries on the system PATH. On Windows, OCRmyPDF will also check the registry
 for their locations.
 
 Tesseract OCR relies on SIMD for performance and only has proper support for this
@@ -38,13 +38,13 @@ OCRmyPDF uses setuptools-scm for versioning, which derives the version from
 Git as a single source of truth. This may be unsuitable for some distributions, e.g.
 to indicate that your distribution modifies OCRmyPDF in some way.
 
-You can patch the ``__version__`` variable in ``src/ocrmypdf/_version.py`` if 
+You can patch the ``__version__`` variable in ``src/ocrmypdf/_version.py`` if
 necessary.
 
 OCRmyPDF uses setuptools-scm-git-archive to ensure that tarballs downloaded from
 GitHub contain version information. Unfortunately, these tarballs are not always
-deterministic. See this 
+deterministic. See this
-`issue <https://github.com/jbarlow83/OCRmyPDF/issues/841#issuecomment-936562696>`_.
+`issue <https://github.com/ocrmypdf/OCRmyPDF/issues/841#issuecomment-936562696>`_.
 
 jbig2enc
 --------

docs/plugins.rst

@@ -152,6 +152,16 @@ hooks. As such, you cannot "chain" a series of plugin filters together in this
 way. Instead, a single hook implementation should be responsible for any such
 chaining operations.
 
+Examples
+========
+
+* OCRmyPDF's test suite contains several plugins that are used to simulate certain
+  test conditions.
+* `ocrmypdf-papermerge <https://github.com/papermerge/OCRmyPDF_papermerge>`_ is
+  a production plugin that integrates OCRmyPDF and the Papermerge document
+  management system.
+
+
 Custom command line arguments
 -----------------------------
 

docs/release_notes.rst

@@ -12,11 +12,109 @@ may be unreliable. Use the API to depend on precise behavior.
 The public API may be useful in scripts that launch OCRmyPDF processes or that
 wish to use some of its features for working with PDFs.
 
+The most recent release of OCRmyPDF is |OCRmyPDF PyPI|. Any newer versions
+referred to in these notes may exist the main branch but have not been
+tagged yet.
+
 .. note::
 
-   Python 3.6 reaches end of life on December 23, 2021. We have already ended support
+   Attention maintainers: that these release notes may be updated with information
-   for Python 3.6 but might release fixes for critical issues if necessary before that
+   about a forthcoming release that has not been tagged yet. A release is only
-   date.
+   official when it's tagged and posted to PyPI.
+
+.. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
+
+v13.5.0
+=======
+
+-  Added a new ``optimize_pdf`` pluginhook, making it possible to create plugins that
+   replace or enhance OCRmyPDF's PDF optimizer.
+-  Removed all max version restrictions. Our new policy is to blacklist known-bad releases
+   and only block known-bad versions of dependencies.
+-  The naming schema for object that holds all OCR text that OCRmyPDF inserts has
+   changed. This has always been an implementation detail (and remains so), but possibly,
+   someone was relying on it and would appreciate the heads-up.
+-  Cleanup.
+
+v13.4.7
+=======
+
+-  Fixed PermissionError when cleaning up temporary files in rare cases. :issue:`974`
+-  Fixed PermissionError when calling ``os.nice`` on platforms that lack it. :issue:`973`
+-  Suppressed some warnings from libxmp during tests.
+
+v13.4.6
+=======
+
+-  Convert error on corrupt ICC profiles into a warning. Thanks to @oscherler.
+
+v13.4.5
+=======
+
+-  Remove upper bound on pdfminer.six version.
+-  Documentation.
+
+v13.4.4
+=======
+
+-  Updated pdfminer.six version.
+-  Docker image changed to Ubuntu 22.04 now that it is released and provides the
+   dependencies we need. This seems more consistent than our recent change to
+   Debian.
+
+v13.4.3
+=======
+
+-  Fix error on pytest.skip() with older versions of pytest.
+-  Documentation updates.
+
+v13.4.2
+=======
+
+-  Worked around a
+   `major regression in Ghostscript 9.56.0 <https://bugs.ghostscript.com/show_bug.cgi?id=705187>`__
+   where **all OCR text is stripped out of the PDF**. It simply removes all text,
+   even generated by software other than OCRmyPDF. Fortunately, we can ask
+   Ghostscript 9.56.0 to use its old behavior that worked correctly for our purposes.
+   Users must avoid the combination (Ghostscript 9.56.0, ocrmypdf <13.4.2) since
+   older versions of OCRmyPDF have no way of detecting that this particular
+   version of Ghostscript removes all OCR text.
+-  Marked pdfminer 20220319 as supported.
+-  Fixed some deprecation warnings from recent versions of Pillow and pytest.
+-  Test suite now covers Python 3.10 (Python 3.10 worked fine before, but was not
+   being tested).
+-  Docker image now uses debian:bookworm-slim as the base image to fix the Docker
+   image build.
+
+v13.4.1
+=======
+
+-  Temporarily make threads rather than processes the default executor worker, due
+   to a persistent deadlock issue when processes are used. Add a new command line
+   argument ``--no-use-threads`` to disable this.
+
+v13.4.0
+=======
+
+-  Fixed test failures when using pikepdf 5.0.0.
+-  Various improvements to the optimizer. In particular, we now recognize PDF images
+   that are encoded with both deflate (PNG) and DCT (JPEG), and also produce PDF
+   with images compressed with deflate and DCT, since this often yields file size
+   improvements compared to plain DCT.
+
+v13.3.0
+=======
+
+-  Made a harmless but "scary" exception after failing to optimize an image less scary.
+-  Added a warning if a page image is too large for unpaper to clean. The image is
+   passed through without cleaning. This is due to a hard-coded limitation in a
+   C library used by unpaper so it cannot be rectified easily.
+-  We now use better default settings when calling img2pdf.
+-  We no longer try to optimize images that we failed to save in certain situations.
+-  We now account for some differences in text output from Tesseract 5 compared to
+   Tesseract 4.
+-  Better handling of Ghostscript producing empty images when attempting to rasterize
+   page images.
 
 v13.2.0
 =======
@@ -65,7 +163,7 @@ v13.0.0
    Tesseract 5.x has implemented improvements to thresholding, so this feature will be
    redundant anyway.
 -  ``--deskew`` was previous calculated by a Leptonica algorithm. We now use a feature
-   of Tesseract to term the appropriate the angle to deskew a page. The deskew angle
+   of Tesseract to find the appropriate the angle to deskew a page. The deskew angle
    according to Tesseract may differ from Leptonica's algorithm. At least in theory,
    Tesseract's deskew angle is informed by a more complex analysis than Leptonica,
    so this should improve results in general. We also use Pillow to perform the

misc/webservice.py

@@ -59,7 +59,7 @@ def do_ocrmypdf(file):
         return Response("--sidecar not supported", 501, mimetype='text/plain')
 
     ocrmypdf_args = ["ocrmypdf", *cmd_args, up_file, down_file]
-    proc = run(ocrmypdf_args, stdout=PIPE, stderr=PIPE, encoding="utf-8")
+    proc = run(ocrmypdf_args, capture_output=True, encoding="utf-8")
     if proc.returncode != 0:
         stderr = proc.stderr
         return Response(stderr, 400, mimetype='text/plain')

pyproject.toml

@@ -99,3 +99,8 @@ module = [
   'libxmp.utils'
 ]
 ignore_missing_imports = true
+
+[tool.pylint.basic]
+good-names = ["i", "j", "k", "ex", "Run", "_", "e", "p", "im", "w", "h", "m", "x", "y", "a", "b", "fp", "n", "f", "s", "v", "q", "dx", "dy"]
+logging-format-style = "old"
+disable = ["raw-checker-failed", "bad-inline-option", "locally-disabled", "file-ignored", "suppressed-message", "useless-suppression", "deprecated-pragma", "use-symbolic-message-instead", "logging-fstring-interpolation", "missing-function-docstring", "too-few-public-methods"]

setup.cfg

@@ -3,7 +3,7 @@ name = ocrmypdf
 description = OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
 long_description = file: README.md
 long_description_content_type = text/markdown
-url = https://github.com/jbarlow83/OCRmyPDF
+url = https://github.com/ocrmypdf/OCRmyPDF
 author = James R. Barlow
 author_email = james@purplerock.ca
 license = MPL-2.0
@@ -39,19 +39,19 @@ keywords =
     scanning
 project_urls =
     Documentation = https://ocrmypdf.readthedocs.io/
-    Source = https://github.com/jbarlow83/ocrmypdf
+    Source = https://github.com/ocrmypdf/OCRmyPDF
-    Tracker = https://github.com/jbarlow83/ocrmypdf/issues
+    Tracker = https://github.com/ocrmypdf/OCRmyPDF/issues
 
 [options]
 packages = find:
 install_requires =
     Pillow>=8.2.0
     coloredlogs>=14.0  # strictly optional
-    img2pdf>=0.3.0,<0.5  # pure Python
+    img2pdf>=0.3.0  # pure Python
     packaging>=20
-    pdfminer.six!=20200720,>=20191110,<=20211012
+    pdfminer.six!=20200720,>=20191110
-    pikepdf>=4.0.0
+    pikepdf!=5.0.0,>=4.0.0
-    pluggy>=0.13.0,<2
+    pluggy>=0.13.0
     reportlab>=3.5.66
     tqdm>=4
     importlib-metadata>=4;python_version<'3.8'  # until Python 3.8
@@ -87,9 +87,9 @@ test =
     pytest-xdist>=2.2.0
     python-xmp-toolkit==2.0.1  # also requires apt-get install libexempi3
 watcher =
-    watchdog>=1.0.2,<3
+    watchdog>=1.0.2
 webservice =
-    Flask>=1,<3
+    Flask>=1
 
 [options.package_data]
 ocrmypdf =

setup.py

@@ -4,6 +4,7 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""setup.py to support older setuptools and pip."""
 
 from setuptools import setup
 

snapcraft.yaml

@@ -0,0 +1,72 @@
+name: ocrmypdf
+title: OCRmyPDF
+base: core20
+version: git
+summary: OCRmyPDF adds optical character recognition (OCR) to PDFs
+description: OCRmyPDF packaged for snap
+grade: stable
+confinement: strict
+icon: docs/images/logo-square-256.svg
+license: MPL-2.0
+
+architectures: [amd64]
+
+environment:
+  TESSDATA_PREFIX: $SNAP/usr/share/tesseract-ocr/4.00/tessdata
+  GS_LIB: $SNAP/usr/share/ghostscript/9.50/Resource/Init
+  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.50/Resource/Font
+  LD_LIBRARY_PATH: $SNAP/usr/lib/x86_64-linux-gnu
+
+apps:
+  ocrmypdf:
+    command: usr/bin/snapcraft-preload python3 -m ocrmypdf
+    plugs:
+      - desktop
+      - desktop-legacy
+      - wayland
+      - x11
+      - home
+      - removable-media
+
+parts:
+  snapcraft-preload:
+    source: https://github.com/sergiusens/snapcraft-preload.git
+    plugin: cmake
+    cmake-parameters:
+      - -DCMAKE_INSTALL_PREFIX=/usr -DLIBPATH=/usr/lib
+    build-packages:
+      - on amd64:
+          - gcc-multilib
+          - g++-multilib
+    stage-packages:
+      - lib32stdc++6
+
+  ocrmypdf:
+    plugin: python
+    source: https://github.com/ocrmypdf/OCRmyPDF.git
+
+    stage-packages:
+      - ghostscript
+      - icc-profiles-free
+      - liblept5
+      - libxml2
+      - pngquant
+      - tesseract-ocr-all
+      - unpaper
+      - qpdf
+      - zlib1g
+
+    python-packages:
+      - cffi
+      - pdfminer.six
+      - pikepdf
+      - Pillow
+      - pluggy
+      - reportlab
+      - setuptools
+      - tqdm
+      - pipe
+
+    override-build: |
+      snapcraftctl build
+      ln -sf ../usr/lib/libsnapcraft-preload.so $SNAPCRAFT_PART_INSTALL/lib/libsnapcraft-preload.so

src/ocrmypdf/__init__.py

@@ -4,6 +4,7 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Adds OCR layer to PDFs."""
 
 from pluggy import HookimplMarker as _HookimplMarker
 

src/ocrmypdf/__main__.py

@@ -5,11 +5,13 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""ocrmypdf command line entrypoint."""
 
 import logging
 import os
 import signal
 import sys
+from contextlib import suppress
 from multiprocessing import set_start_method
 
 from ocrmypdf import __version__
@@ -34,7 +36,7 @@ def sigbus(*args):
 def run(args=None):
     _parser, options, plugin_manager = get_parser_options_plugins(args=args)
 
-    if hasattr(os, 'nice'):
+    with suppress(AttributeError, PermissionError):
         os.nice(5)
 
     verbosity = options.verbose
@@ -62,7 +64,7 @@ def run(args=None):
         log.error(e)
         return ExitCode.missing_dependency
 
-    if hasattr(signal, 'SIGBUS'):
+    with suppress(AttributeError, OSError):
         signal.signal(signal.SIGBUS, sigbus)
 
     result = run_pipeline(options=options, plugin_manager=plugin_manager)

src/ocrmypdf/_concurrent.py

@@ -4,6 +4,8 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""OCRmyPDF concurrency abstractions."""
+
 import threading
 from abc import ABC, abstractmethod
 from typing import Callable, Iterable, Optional
@@ -14,6 +16,8 @@ def _task_noop(*_args, **_kwargs):
 
 
 class NullProgressBar:
+    """Progress bar API that takes no actions."""
+
     def __init__(self, **kwargs):
         pass
 
@@ -28,6 +32,8 @@ class NullProgressBar:
 
 
 class Executor(ABC):
+    """Abstract concurrent executor."""
+
     pool_lock = threading.Lock()
     pbar_class = NullProgressBar
 

src/ocrmypdf/_exec/ghostscript.py

@@ -14,41 +14,36 @@ import sys
 from io import BytesIO
 from os import fspath
 from pathlib import Path
-from shutil import which
 from subprocess import PIPE, CalledProcessError
 from typing import Optional
 
-from PIL import Image
+from PIL import Image, UnidentifiedImageError
 
-from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
+from ocrmypdf.exceptions import SubprocessOutputError
 from ocrmypdf.helpers import Resolution
 from ocrmypdf.subprocess import get_version, run, run_polling_stderr
 
+# Remove this workaround when we require Pillow >= 10
+try:
+    Transpose = Image.Transpose  # type: ignore
+except AttributeError:
+    # Pillow 9 shim
+    Transpose = Image  # type: ignore
+
 log = logging.getLogger(__name__)
 
-missing_gs_error = """
----------------------------------------------------------------------
-This error normally occurs when ocrmypdf find can't Ghostscript.
-Please ensure Ghostscript is installed and its location is added to
-the system PATH environment variable.
-
-For details see:
-    https://ocrmypdf.readthedocs.io/en/latest/installation.html
----------------------------------------------------------------------
-"""
-
 # Most reliable what to get the bitness of Python interpreter, according to Python docs
-_is_64bit = sys.maxsize > 2 ** 32
+_IS_64BIT = sys.maxsize > 2**32
 
-_gswin = None
+_GSWIN = None
 if os.name == 'nt':
-    if _is_64bit:
+    if _IS_64BIT:
-        _gswin = 'gswin64c'
+        _GSWIN = 'gswin64c'
     else:
-        _gswin = 'gswin32c'
+        _GSWIN = 'gswin32c'
 
-GS = _gswin if _gswin else 'gs'
+GS = _GSWIN if _GSWIN else 'gs'
-del _gswin
+del _GSWIN
 
 
 def version():
@@ -71,7 +66,8 @@ def jpeg_passthrough_available() -> bool:
 
 
 def _gs_error_reported(stream) -> bool:
-    return True if re.search(r'error', stream, flags=re.IGNORECASE) else False
+    match = re.search(r'error', stream, flags=re.IGNORECASE)
+    return bool(match)
 
 
 def rasterize_pdf(
@@ -107,7 +103,7 @@ def rasterize_pdf(
         + [
             '-o',
             '-',
-            '-sstdout=%stderr',
+            '-sstdout=%stderr',  # Literal %s, not string interpolation
             '-dAutoRotatePages=/None',  # Probably has no effect on raster
             '-f',
             fspath(input_file),
@@ -118,29 +114,38 @@ def rasterize_pdf(
         p = run(args_gs, stdout=PIPE, stderr=PIPE, check=True)
     except CalledProcessError as e:
         log.error(e.stderr.decode(errors='replace'))
-        raise SubprocessOutputError('Ghostscript rasterizing failed')
+        raise SubprocessOutputError('Ghostscript rasterizing failed') from e
     else:
         stderr = p.stderr.decode(errors='replace')
         if _gs_error_reported(stderr):
             log.error(stderr)
 
-    with Image.open(BytesIO(p.stdout)) as im:
+    try:
-        if rotation is not None:
+        with Image.open(BytesIO(p.stdout)) as im:
-            log.debug("Rotating output by %i", rotation)
+            if rotation is not None:
-            # rotation is a clockwise angle and Image.ROTATE_* is
+                log.debug("Rotating output by %i", rotation)
-            # counterclockwise so this cancels out the rotation
+                # rotation is a clockwise angle and Image.ROTATE_* is
-            if rotation == 90:
+                # counterclockwise so this cancels out the rotation
-                im = im.transpose(Image.ROTATE_90)
+                if rotation == 90:
-            elif rotation == 180:
+                    im = im.transpose(Transpose.ROTATE_90)
-                im = im.transpose(Image.ROTATE_180)
+                elif rotation == 180:
-            elif rotation == 270:
+                    im = im.transpose(Transpose.ROTATE_180)
-                im = im.transpose(Image.ROTATE_270)
+                elif rotation == 270:
-            if rotation % 180 == 90:
+                    im = im.transpose(Transpose.ROTATE_270)
-                page_dpi = page_dpi.flip_axis()
+                if rotation % 180 == 90:
-        im.save(fspath(output_file), dpi=page_dpi)
+                    page_dpi = page_dpi.flip_axis()
+            im.save(fspath(output_file), dpi=page_dpi)
+    except UnidentifiedImageError:
+        log.error(
+            f"Ghostscript (using {raster_device} at {raster_dpi} dpi) produced "
+            "an invalid page image file."
+        )
+        raise
 
 
 class GhostscriptFollower:
+    """Parses the output of Ghostscript and uses it to update the progress bar."""
+
     re_process = re.compile(r"Processing pages \d+ through (\d+).")
     re_page = re.compile(r"Page (\d+)")
 
@@ -161,8 +166,7 @@ class GhostscriptFollower:
                 )
                 return
         else:
-            m = self.re_page.match(line.strip())
+            if self.re_page.match(line.strip()):
-            if m:
                 self.progressbar.update()
 
 
@@ -203,14 +207,18 @@ def generate_pdfa(
     # Older versions of Ghostscript expect a leading slash in
     # sColorConversionStrategy, newer ones should not have it. See Ghostscript
     # git commit fe1c025d.
-    strategy = ('/' + strategy) if version() < '9.19' else strategy
+    gs_version = version()
+    strategy = ('/' + strategy) if gs_version < '9.19' else strategy
 
-    if version() == '9.23':
+    if gs_version == '9.23':
         # 9.23: added JPEG passthrough as a new feature, but with a bug that
         # incorrectly formats some images. Fixed as of 9.24. So we disable this
         # feature for 9.23.
         # https://bugs.ghostscript.com/show_bug.cgi?id=699216
         compression_args.append('-dPassThroughJPEGImages=false')
+    elif gs_version == '9.56.0':
+        # 9.56.0 breaks our OCR...?
+        compression_args.append('-dNEWPDF=false')
 
     # nb no need to specify ProcessColorModel when ColorConversionStrategy
     # is set; see:
@@ -233,7 +241,7 @@ def generate_pdfa(
             "-dPDFACompatibilityPolicy=1",
             "-o",
             "-",
-            "-sstdout=%stderr",
+            "-sstdout=%stderr",  # Literal %s, not string interpolation
         ]
     )
     args_gs.extend(fspath(s) for s in pdf_pages)  # Stringify Path objs

src/ocrmypdf/_exec/tesseract.py

@@ -13,7 +13,7 @@ from math import pi
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
-from typing import Dict, Iterator, List, Optional
+from typing import Dict, List, Optional
 
 from packaging.version import Version
 from PIL import Image
@@ -55,9 +55,11 @@ TESSERACT_THRESHOLDING_METHODS: Dict[str, int] = {
 
 
 class TesseractLoggerAdapter(logging.LoggerAdapter):
+    "Prepend [tesseract] to messages emitted from tesseract"
+
     def process(self, msg, kwargs):
         kwargs['extra'] = self.extra
-        return '[tesseract] %s' % (msg), kwargs
+        return f'[tesseract] {msg}', kwargs
 
 
 TESSERACT_VERSION_PATTERN = r"""
@@ -105,6 +107,7 @@ TESSERACT_VERSION_PATTERN = r"""
 
 
 class TesseractVersion(Version):
+    "Modify standard packaging.Version regex to support Tesseract idiosyncracies."
     _regex = re.compile(
         r"^\s*" + TESSERACT_VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE
     )
@@ -169,14 +172,14 @@ def tess_base_args(langs: List[str], engine_mode: Optional[int]) -> List[str]:
 
 
 def _parse_tesseract_output(binary_output: bytes) -> Dict[str, str]:
-    def g():
+    def gen():
         for line in binary_output.decode().splitlines():
             line = line.strip()
             parts = line.split(':', maxsplit=2)
             if len(parts) == 2:
                 yield parts[0].strip(), parts[1].strip()
 
-    return {k: v for k, v in g()}
+    return dict(gen())
 
 
 def get_orientation(
@@ -205,10 +208,10 @@ def get_orientation(
 
     osd = _parse_tesseract_output(p.stdout)
     angle = int(osd.get('Orientation in degrees', 0))
-    oc = OrientationConfidence(
+    orient_conf = OrientationConfidence(
         angle=angle, confidence=float(osd.get('Orientation confidence', 0))
     )
-    return oc
+    return orient_conf
 
 
 def get_deskew(
@@ -344,7 +347,7 @@ def generate_hocr(
         _generate_null_hocr(output_hocr, output_text, input_file)
     except CalledProcessError as e:
         tesseract_log_output(e.output)
-        if b'Image too large' in e.output:
+        if b'Image too large' in e.output or b'Empty page!!' in e.output:
             _generate_null_hocr(output_hocr, output_text, input_file)
             return
 
@@ -416,7 +419,7 @@ def generate_pdf(
         use_skip_page(output_pdf, output_text)
     except CalledProcessError as e:
         tesseract_log_output(e.output)
-        if b'Image too large' in e.output:
+        if b'Image too large' in e.output or b'Empty page!!' in e.output:
             use_skip_page(output_pdf, output_text)
             return
         raise SubprocessOutputError() from e

src/ocrmypdf/_exec/unpaper.py

@@ -13,69 +13,119 @@
 import logging
 import os
 import shlex
+import sys
+from contextlib import contextmanager
 from decimal import Decimal
 from pathlib import Path
 from subprocess import PIPE, STDOUT
-from tempfile import TemporaryDirectory
+from typing import Iterator, List, Optional, Tuple, Union
-from typing import List, Optional, Tuple, Union
 
 from PIL import Image
 
 from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
-from ocrmypdf.subprocess import get_version
+from ocrmypdf.subprocess import get_version, run
-from ocrmypdf.subprocess import run as external_run
+
+if sys.version_info >= (3, 10):
+    from tempfile import TemporaryDirectory
+else:
+    from tempfile import TemporaryDirectory as _TemporaryDirectory
+
+    class TemporaryDirectory(_TemporaryDirectory):
+        """Shim to consume ignore_cleanup_errors kwarg on Python 3.9 and older.
+
+        The argument is consumed without action. If users are getting errors related
+        to temporary file cleanup, they should upgrade to Python 3.10 which properly
+        cleans up temporary directories on Windows.
+
+        See: https://github.com/python/cpython/pull/24793
+        """
+
+        def __init__(self, ignore_cleanup_errors=False, **kwargs):
+            super().__init__(**kwargs)
+
+    del _TemporaryDirectory
+
+
+UNPAPER_IMAGE_PIXEL_LIMIT = 256 * 1024 * 1024
 
 DecFloat = Union[Decimal, float]
 
 log = logging.getLogger(__name__)
 
 
+class UnpaperImageTooLargeError(Exception):
+    """To capture details when an image is too large for unpaper."""
+
+    def __init__(
+        self,
+        w,
+        h,
+        message="Image with size {}x{} is too large for cleaning with 'unpaper'.",
+    ):
+        self.w = w
+        self.h = h
+        self.message = message.format(w, h)
+        super().__init__(self.message)
+
+
 def version() -> str:
     return get_version('unpaper')
 
 
-def _setup_unpaper_io(tmpdir: Path, input_file: Path) -> Tuple[Path, Path]:
+SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
-    SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
+
-    with Image.open(input_file) as im:
+
-        im_modified = False
+def _convert_image(im: Image.Image) -> Tuple[Image.Image, bool, str]:
-        if im.mode not in SUFFIXES:
+    im_modified = False
-            log.info("Converting image to other colorspace")
+
-            try:
+    if im.mode not in SUFFIXES:
-                if im.mode == 'P' and len(im.getcolors()) == 2:
+        log.info("Converting image to other colorspace")
-                    im = im.convert(mode='1')
-                else:
-                    im = im.convert(mode='RGB')
-            except OSError as e:
-                raise MissingDependencyError(
-                    "Could not convert image with type " + im.mode
-                ) from e
-            else:
-                im_modified = True
         try:
-            suffix = SUFFIXES[im.mode]
+            if im.mode == 'P' and len(im.getcolors()) == 2:
-        except KeyError:
+                im = im.convert(mode='1')
+            else:
+                im = im.convert(mode='RGB')
+        except OSError as e:
             raise MissingDependencyError(
-                "Failed to convert image to a supported format."
+                "Could not convert image with type " + im.mode
-            ) from None
+            ) from e
-
-        if im_modified or input_file.suffix != '.pnm':
-            input_pnm = tmpdir / 'input.pnm'
-            im.save(input_pnm, format='PPM')
         else:
-            # No changes, PNG input, just use the file we already have
+            im_modified = True
-            input_pnm = input_file
+    try:
-        output_pnm = tmpdir / f'output{suffix}'
+        suffix = SUFFIXES[im.mode]
-    return input_pnm, output_pnm
+    except KeyError:
+        raise MissingDependencyError(
+            "Failed to convert image to a supported format."
+        ) from None
+    return im, im_modified, suffix
 
 
-def run(
+@contextmanager
+def _setup_unpaper_io(input_file: Path) -> Iterator[Tuple[Path, Path, Path]]:
+    with Image.open(input_file) as im:
+        if im.width * im.height >= UNPAPER_IMAGE_PIXEL_LIMIT:
+            raise UnpaperImageTooLargeError(w=im.width, h=im.height)
+        im, im_modified, suffix = _convert_image(im)
+
+        with TemporaryDirectory(ignore_cleanup_errors=True) as tmpdir:
+            tmppath = Path(tmpdir)
+            if im_modified or input_file.suffix != '.pnm':
+                input_pnm = tmppath / 'input.pnm'
+                im.save(input_pnm, format='PPM')
+            else:
+                # No changes, PNG input, just use the file we already have
+                input_pnm = input_file
+
+            output_pnm = tmppath / f'output{suffix}'
+            yield input_pnm, output_pnm, tmppath
+
+
+def run_unpaper(
     input_file: Path, output_file: Path, *, dpi: DecFloat, mode_args: List[str]
 ) -> None:
     args_unpaper = ['unpaper', '-v', '--dpi', str(round(dpi, 6))] + mode_args
 
-    with TemporaryDirectory() as tmpdir:
+    with _setup_unpaper_io(input_file) as (input_pnm, output_pnm, tmpdir):
-        input_pnm, output_pnm = _setup_unpaper_io(Path(tmpdir), input_file)
-
         # To prevent any shenanigans from accepting arbitrary parameters in
         # --unpaper-args, we:
         # 1) run with cwd set to a tmpdir with only unpaper's files
@@ -84,7 +134,7 @@ def run(
         # This should ensure that a user cannot clobber some other file with
         # their unpaper arguments (whether intentionally or otherwise)
         args_unpaper.extend([os.fspath(input_pnm), os.fspath(output_pnm)])
-        external_run(
+        run(
             args_unpaper,
             close_fds=True,
             check=True,
@@ -117,7 +167,7 @@ def clean(
     *,
     dpi: DecFloat,
     unpaper_args: Optional[List[str]] = None,
-):
+) -> Path:
     default_args = [
         '--layout',
         'none',
@@ -131,4 +181,9 @@ def clean(
     ]
     if not unpaper_args:
         unpaper_args = default_args
-    run(input_file, output_file, dpi=dpi, mode_args=unpaper_args)
+    try:
+        run_unpaper(input_file, output_file, dpi=dpi, mode_args=unpaper_args)
+        return output_file
+    except UnpaperImageTooLargeError as e:
+        log.warning(str(e))
+        return input_file

src/ocrmypdf/_graft.py

@@ -4,9 +4,9 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""For grafting text-only PDF pages onto freeform PDF pages."""
 
 import logging
-import uuid
 from contextlib import suppress
 from pathlib import Path
 from typing import Optional
@@ -16,7 +16,6 @@ from pikepdf import (
     Name,
     Object,
     Operator,
-    Page,
     Pdf,
     PdfError,
     PdfMatrix,
@@ -81,6 +80,8 @@ def strip_invisible_text(pdf, page):
 
 
 class OcrGrafter:
+    """Manages grafting text-only PDFs onto regular PDFs."""
+
     def __init__(self, context):
         self.context = context
         self.path_base = context.origin
@@ -236,6 +237,8 @@ class OcrGrafter:
     ):
         """Insert the text layer from text page 0 on to pdf_base at page_num"""
 
+        # pylint: disable=invalid-name
+
         log.debug("Grafting")
         if Path(textpdf).stat().st_size == 0:
             return
@@ -282,7 +285,7 @@ class OcrGrafter:
 
             base_resources = _ensure_dictionary(base_page, Name.Resources)
             base_xobjs = _ensure_dictionary(base_resources, Name.XObject)
-            text_xobj_name = Name('/' + str(uuid.uuid4()))
+            text_xobj_name = Name.random(prefix="OCR-")
             xobj = self.pdf_base.make_stream(pdf_text_contents)
             base_xobjs[text_xobj_name] = xobj
             xobj.Type = Name.XObject

src/ocrmypdf/_jobcontext.py

@@ -4,6 +4,7 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Defines context objects that are passed to child processes/threads."""
 
 import os
 import shutil
@@ -83,7 +84,7 @@ class PageContext:
         The path will be based in a common temporary folder and have a prefix based
         on the page number.
         """
-        return self.work_folder / ("%06d_%s" % (self.pageno + 1, name))
+        return self.work_folder / f"{(self.pageno + 1):06d}_{name}"
 
     def __getstate__(self):
         state = self.__dict__.copy()

src/ocrmypdf/_logging.py

@@ -4,15 +4,17 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Logging support classes."""
 
 import logging
-import sys
 from contextlib import suppress
 
 from tqdm import tqdm
 
 
 class PageNumberFilter(logging.Filter):
+    """Insert PDF page number that emitted log message to log record."""
+
     def filter(self, record):
         pageno = getattr(record, 'pageno', None)
         if isinstance(pageno, int):

src/ocrmypdf/_pipeline.py

@@ -4,6 +4,7 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""OCRmyPDF page processing pipeline functions."""
 
 import logging
 import os
@@ -32,12 +33,18 @@ from ocrmypdf.exceptions import (
     PriorOcrFoundError,
     UnsupportedImageFormatError,
 )
-from ocrmypdf.helpers import Resolution, safe_symlink
+from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
 from ocrmypdf.hocrtransform import HocrTransform
-from ocrmypdf.optimize import optimize
 from ocrmypdf.pdfa import generate_pdfa_ps
 from ocrmypdf.pdfinfo import Colorspace, Encoding, PdfInfo
 
+# Remove this workaround when we require Pillow >= 10
+try:
+    BICUBIC = Image.Resampling.BICUBIC  # type: ignore
+except AttributeError:
+    # Pillow 9 shim
+    BICUBIC = Image.BICUBIC  # type: ignore
+
 log = logging.getLogger(__name__)
 
 VECTOR_PAGE_DPI = 400
@@ -98,8 +105,8 @@ def triage_image_file(input_file, output_file, options):
             img2pdf.convert(
                 os.fspath(input_file),
                 layout_fun=layout_fun,
-                with_pdfrw=False,
                 outputstream=outf,
+                **IMG2PDF_KWARGS,
             )
         log.info("Successfully converted to PDF, processing...")
     except img2pdf.ImageOpenError as e:
@@ -325,7 +332,8 @@ def is_ocr_required(page_context: PageContext):
             ocr_required = False
             log.warning(
                 "page too big, skipping OCR "
-                f"({(pixel_count / 1_000_000):.1f} MPixels > {options.skip_big:.1f} MPixels --skip-big)"
+                f"({(pixel_count / 1_000_000):.1f} MPixels > "
+                f"{options.skip_big:.1f} MPixels --skip-big)"
             )
     return ocr_required
 
@@ -423,8 +431,8 @@ def rasterize(
     output_file = page_context.get_path(f'rasterize{output_tag}.png')
     pageinfo = page_context.pageinfo
 
-    def at_least(cs):
+    def at_least(colorspace):
-        return max(device_idx, colorspaces.index(cs))
+        return max(device_idx, colorspaces.index(colorspace))
 
     for image in pageinfo.images:
         if image.type_ != 'image':
@@ -464,10 +472,10 @@ def rasterize(
 
 def preprocess_remove_background(input_file: Path, page_context: PageContext):
     if any(image.bpc > 1 for image in page_context.pageinfo.images):
-        output_file = page_context.get_path('pp_rm_bg.png')
-        # leptonica.remove_background(input_file, output_file)
         raise NotImplementedError("--remove-background is temporarily not implemented")
-        return output_file
+        # output_file = page_context.get_path('pp_rm_bg.png')
+        # leptonica.remove_background(input_file, output_file)
+        # return output_file
     else:
         log.info("background removal skipped on mono page")
         return input_file
@@ -484,7 +492,9 @@ def preprocess_deskew(input_file: Path, page_context: PageContext):
         # According to Pillow docs, .rotate() will automatically use Image.NEAREST
         # resampling if image is mode '1' or 'P'
         deskewed = im.rotate(
-            deskew_angle_degrees, resample=Image.BICUBIC, fillcolor='white'
+            deskew_angle_degrees,
+            resample=BICUBIC,
+            fillcolor=ImageColor.getcolor('white', mode=im.mode),
         )
         deskewed.save(output_file, dpi=dpi)
 
@@ -494,13 +504,12 @@ def preprocess_deskew(input_file: Path, page_context: PageContext):
 def preprocess_clean(input_file: Path, page_context: PageContext):
     output_file = page_context.get_path('pp_clean.png')
     dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
-    unpaper.clean(
+    return unpaper.clean(
         input_file,
         output_file,
         dpi=dpi.x,
         unpaper_args=page_context.options.unpaper_args,
     )
-    return output_file
 
 
 def create_ocr_image(image: Path, page_context: PageContext):
@@ -613,7 +622,7 @@ def create_pdf_page_from_image(
 
         layout_fun = img2pdf.get_layout_fun(pagesize)
         img2pdf.convert(
-            imfile, with_pdfrw=False, layout_fun=layout_fun, outputstream=pdf
+            imfile, layout_fun=layout_fun, outputstream=pdf, **IMG2PDF_KWARGS
         )
         log.debug('convert done')
 
@@ -808,13 +817,14 @@ def metadata_fixup(working_file: Path, context: PdfContext):
                 missing = set(meta_original.keys()) - set(meta.keys())
                 report_on_metadata(missing)
 
+        optimizing = context.plugin_manager.hook.is_optimization_enabled(
+            context=context
+        )
         pdf.save(
             output_file,
             **get_pdf_save_settings(options.output_type),
             linearize=(  # Don't linearize if optimize() will be linearizing too
-                should_linearize(working_file, context)
+                not optimizing and should_linearize(working_file, context)
-                if options.optimize == 0
-                else False
             ),
         )
 
@@ -823,12 +833,22 @@ def metadata_fixup(working_file: Path, context: PdfContext):
 
 def optimize_pdf(input_file: Path, context: PdfContext, executor: Executor):
     output_file = context.get_path('optimize.pdf')
-    save_settings = dict(
+    output_pdf, messages = context.plugin_manager.hook.optimize_pdf(
+        input_pdf=input_file,
+        output_pdf=output_file,
+        context=context,
+        executor=executor,
         linearize=should_linearize(input_file, context),
-        **get_pdf_save_settings(context.options.output_type),
     )
-    optimize(input_file, output_file, context, save_settings, executor)
+
-    return output_file
+    input_size = input_file.stat().st_size
+    output_size = output_file.stat().st_size
+    if output_size > 0:
+        ratio = input_size / output_size
+        savings = 1 - output_size / input_size
+        log.info(f"Optimize ratio: {ratio:.2f} savings: {(savings):.1%}")
+
+    return output_pdf, messages
 
 
 def enumerate_compress_ranges(iterable):
@@ -850,8 +870,8 @@ def enumerate_compress_ranges(iterable):
 def merge_sidecars(txt_files: Iterable[Optional[Path]], context: PdfContext):
     output_file = context.get_path('sidecar.txt')
     with open(output_file, 'w', encoding="utf-8") as stream:
-        for (frm, to), txt_file in enumerate_compress_ranges(txt_files):
+        for (from_, to_), txt_file in enumerate_compress_ranges(txt_files):
-            if frm != 1:
+            if from_ != 1:
                 stream.write('\f')  # Form feed between pages
             if txt_file:
                 with open(txt_file, encoding="utf-8") as in_:
@@ -864,10 +884,10 @@ def merge_sidecars(txt_files: Iterable[Optional[Path]], context: PdfContext):
                     else:
                         stream.write(txt)
             else:
-                if frm != to:
+                if from_ != to_:
-                    pages = f'{frm}-{to}'
+                    pages = f'{from_}-{to_}'
                 else:
-                    pages = f'{frm}'
+                    pages = f'{from_}'
                 stream.write(f'[OCR skipped on page(s) {pages}]')
     return output_file
 

src/ocrmypdf/_plugin_manager.py

@@ -4,6 +4,7 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Plugin manager using pluggy."""
 
 import argparse
 import importlib
@@ -101,12 +102,11 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
 
 
 def get_plugin_manager(plugins: List[Union[str, Path]], builtins=True):
-    pm = OcrmypdfPluginManager(
+    return OcrmypdfPluginManager(
         project_name='ocrmypdf',
         plugins=plugins,
         builtins=builtins,
     )
-    return pm
 
 
 def get_parser_options_plugins(
@@ -120,3 +120,6 @@ def get_parser_options_plugins(
 
     options = parser.parse_args(args=args)
     return parser, options, plugin_manager
+
+
+__all__ = ['OcrmypdfPluginManager', 'get_plugin_manager', 'get_parser_options_plugins']

src/ocrmypdf/_sync.py

@@ -4,6 +4,8 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Implements the concurrent and page synchronous parts of the pipeline."""
+
 
 import argparse
 import logging
@@ -16,7 +18,7 @@ from concurrent.futures.thread import BrokenThreadPool
 from functools import partial
 from pathlib import Path
 from tempfile import mkdtemp
-from typing import List, NamedTuple, Optional, Tuple, cast
+from typing import List, NamedTuple, Optional, Sequence, Tuple, cast
 
 import PIL
 
@@ -68,7 +70,9 @@ from ocrmypdf.pdfa import file_claims_pdfa
 log = logging.getLogger(__name__)
 
 
-class PageResult(NamedTuple):  # pylint: disable=inherit-non-class
+class PageResult(NamedTuple):
+    """Result when a page is finished processing."""
+
     pageno: int
     pdf_page_from_image: Optional[Path]
     ocr: Optional[Path]
@@ -226,7 +230,9 @@ def exec_page_sync(page_context: PageContext) -> PageResult:
     )
 
 
-def post_process(pdf_file: Path, context: PdfContext, executor: Executor) -> Path:
+def post_process(
+    pdf_file: Path, context: PdfContext, executor: Executor
+) -> Tuple[Path, Sequence[str]]:
     pdf_out = pdf_file
     if context.options.output_type.startswith('pdfa'):
         ps_stub_out = generate_postscript_stub(context)
@@ -244,7 +250,7 @@ def worker_init(max_pixels: int) -> None:
     pikepdf_enable_mmap()
 
 
-def exec_concurrent(context: PdfContext, executor: Executor) -> None:
+def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
     """Execute the pipeline concurrently"""
 
     # Run exec_page_sync on every page context
@@ -296,13 +302,15 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> None:
     # Merge layers to one single pdf
     pdf = ocrgraft.finalize()
 
+    messages: List[str] = []
     if options.output_type != 'none':
         # PDF/A and metadata
         log.info("Postprocessing...")
-        pdf = post_process(pdf, context, executor)
+        pdf, messages = post_process(pdf, context, executor)
 
         # Copy PDF file to destination
         copy_final(pdf, options.output_file, context)
+    return messages
 
 
 def configure_debug_logging(
@@ -382,7 +390,7 @@ def run_pipeline(
         validate_pdfinfo_options(context)
 
         # Execute the pipeline
-        exec_concurrent(context, executor)
+        optimize_messages = exec_concurrent(context, executor)
 
         if options.output_file == '-':
             log.info("Output sent to stdout")
@@ -408,7 +416,9 @@ def run_pipeline(
             if not check_pdf(options.output_file):
                 log.warning('Output file: The generated PDF is INVALID')
                 return ExitCode.invalid_output_pdf
-            report_output_file_size(options, start_input_file, options.output_file)
+            report_output_file_size(
+                options, start_input_file, options.output_file, optimize_messages
+            )
 
     except (KeyboardInterrupt if not api else NeverRaise):
         if options.verbose >= 1:
@@ -425,7 +435,7 @@ def run_pipeline(
         else:
             log.error(type(e).__name__)
         return e.exit_code
-    except (PIL.Image.DecompressionBombError if not api else NeverRaise) as e:
+    except (PIL.Image.DecompressionBombError if not api else NeverRaise):
         log.exception(
             "A decompression bomb error was encountered while executing the "
             "pipeline. Use the argument --max-image-mpixels to raise the maximum "
@@ -435,7 +445,7 @@ def run_pipeline(
     except (
         BrokenProcessPool if not api else NeverRaise,
         BrokenThreadPool if not api else NeverRaise,
-    ) as e:
+    ):
         log.exception(
             "A worker process was terminated unexpectedly. This is known to occur if "
             "processing your file takes all available swap space and RAM. It may "

src/ocrmypdf/_validation.py

@@ -5,6 +5,7 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Validate a work order from API or command line."""
 
 import locale
 import logging
@@ -13,19 +14,19 @@ import sys
 import unicodedata
 from pathlib import Path
 from shutil import copyfileobj
-from typing import List, Set, Tuple
+from typing import List, Optional, Sequence, Set, Tuple
 
 import pikepdf
 import PIL
 
-from ocrmypdf._exec import jbig2enc, pngquant, unpaper
+from ocrmypdf._exec import unpaper
 from ocrmypdf.exceptions import (
     BadArgsError,
     InputFileError,
     MissingDependencyError,
     OutputFileAccessError,
 )
-from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink, samefile
+from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink
 from ocrmypdf.hocrtransform import HOCR_OK_LANGS
 from ocrmypdf.subprocess import check_external_program
 
@@ -41,7 +42,7 @@ log = logging.getLogger(__name__)
 
 
 def check_platform():
-    if os.name == 'nt' and sys.maxsize <= 2 ** 32:  # pragma: no cover
+    if os.name == 'nt' and sys.maxsize <= 2**32:  # pragma: no cover
         # 32-bit interpreter on Windows
         log.error(
             "You are running OCRmyPDF in a 32-bit (x86) Python interpreter."
@@ -146,13 +147,13 @@ def check_options_preprocessing(options):
 def _pages_from_ranges(ranges: str) -> Set[int]:
     pages: List[int] = []
     page_groups = ranges.replace(' ', '').split(',')
-    for g in page_groups:
+    for group in page_groups:
-        if not g:
+        if not group:
             continue
         try:
-            start, end = g.split('-')
+            start, end = group.split('-')
         except ValueError:
-            pages.append(int(g) - 1)
+            pages.append(int(group) - 1)
         else:
             try:
                 new_pages = list(range(int(start) - 1, int(end)))
@@ -162,7 +163,7 @@ def _pages_from_ranges(ranges: str) -> Set[int]:
                     ) from None
                 pages.extend(new_pages)
             except ValueError:
-                raise BadArgsError(f"invalid page subrange '{g}'") from None
+                raise BadArgsError(f"invalid page subrange '{group}'") from None
 
     if not pages:
         raise BadArgsError(
@@ -193,37 +194,6 @@ def check_options_ocr_behavior(options):
         options.pages = _pages_from_ranges(options.pages)
 
 
-def check_options_optimizing(options):
-    if options.optimize >= 2:
-        check_external_program(
-            program='pngquant',
-            package='pngquant',
-            version_checker=pngquant.version,
-            need_version='2.0.1',
-            required_for='--optimize {2,3}',
-        )
-
-    if options.optimize >= 2:
-        # Although we use JBIG2 for optimize=1, don't nag about it unless the
-        # user is asking for more optimization
-        check_external_program(
-            program='jbig2',
-            package='jbig2enc',
-            version_checker=jbig2enc.version,
-            need_version='0.28',
-            required_for='--optimize {2,3} | --jbig2-lossy',
-            recommended=True if not options.jbig2_lossy else False,
-        )
-
-    if options.optimize == 0 and any(
-        [options.jbig2_lossy, options.png_quality, options.jpeg_quality]
-    ):
-        log.warning(
-            "The arguments --jbig2-lossy, --png-quality, and --jpeg-quality "
-            "will be ignored because --optimize=0."
-        )
-
-
 def check_options_advanced(options):
     if options.pdfa_image_compression != 'auto' and not options.output_type.startswith(
         'pdfa'
@@ -237,13 +207,13 @@ def check_options_advanced(options):
 def check_options_metadata(options):
     docinfo = [options.title, options.author, options.keywords, options.subject]
     for s in (m for m in docinfo if m):
-        for c in s:
+        for char in s:
-            if unicodedata.category(c) == 'Co' or ord(c) >= 0x10000:
+            if unicodedata.category(char) == 'Co' or ord(char) >= 0x10000:
+                hexchar = hex(ord(char))[2:].upper()
                 raise ValueError(
                     "One of the metadata strings contains "
-                    "an unsupported Unicode character: '{}' (U+{})".format(
+                    "an unsupported Unicode character: "
-                        c, hex(ord(c))[2:].upper()
+                    f"{char} (U+{hexchar})"
-                    )
                 )
 
 
@@ -261,7 +231,6 @@ def _check_options(options, plugin_manager, ocr_engine_languages):
     check_options_sidecar(options)
     check_options_preprocessing(options)
     check_options_ocr_behavior(options)
-    check_options_optimizing(options)
     check_options_advanced(options)
     check_options_pillow(options)
     plugin_manager.hook.check_options(options=options)
@@ -293,7 +262,7 @@ def create_input_file(options, work_folder: Path) -> Tuple[Path, str]:
             target = work_folder / 'origin'
             safe_symlink(options.input_file, target)
             return target, os.fspath(options.input_file)
-        except FileNotFoundError:
+        except FileNotFoundError as e:
             msg = f"File not found - {options.input_file}"
             if Path('/.dockerenv').exists():  # pragma: no cover
                 msg += (
@@ -304,7 +273,7 @@ def create_input_file(options, work_folder: Path) -> Tuple[Path, str]:
                     "\n"
                     "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf\n"
                 )
-            raise InputFileError(msg)
+            raise InputFileError(msg) from e
 
 
 def check_requested_output_file(options):
@@ -324,7 +293,16 @@ def check_requested_output_file(options):
         )
 
 
-def report_output_file_size(options, input_file, output_file):
+def report_output_file_size(
+    options,
+    input_file: Path,
+    output_file: Path,
+    optimize_messages: Optional[Sequence[str]] = None,
+    file_overhead: int = 4000,
+    page_overhead: int = 3000,
+):
+    if optimize_messages is None:
+        optimize_messages = []
     try:
         output_size = Path(output_file).stat().st_size
         input_size = Path(input_file).stat().st_size
@@ -333,9 +311,7 @@ def report_output_file_size(options, input_file, output_file):
     with pikepdf.open(output_file) as p:
         # Overhead constants obtained by estimating amount of data added by OCR
         # PDF/A conversion, and possible XMP metadata addition, with compression
-        FILE_OVERHEAD = 4000
+        reasonable_overhead = file_overhead + page_overhead * len(p.pages)
-        OCR_PER_PAGE_OVERHEAD = 3000
-        reasonable_overhead = FILE_OVERHEAD + OCR_PER_PAGE_OVERHEAD * len(p.pages)
     ratio = output_size / input_size
     reasonable_ratio = output_size / (input_size + reasonable_overhead)
     if reasonable_ratio < 1.35 or input_size < 25000:
@@ -355,19 +331,8 @@ def report_output_file_size(options, input_file, output_file):
                 f"The argument --{arg.replace('_', '-')} was issued, causing transcoding."
             )
 
-    if options.optimize == 0:
+    reasons.extend(optimize_messages)
-        reasons.append("Optimization was disabled.")
+
-    else:
-        image_optimizers = {
-            'jbig2': jbig2enc.available(),
-            'pngquant': pngquant.available(),
-        }
-        for name, available in image_optimizers.items():
-            if not available:
-                reasons.append(
-                    f"The optional dependency '{name}' was not found, so some image "
-                    f"optimizations could not be attempted."
-                )
     if options.output_type.startswith('pdfa'):
         reasons.append("PDF/A conversion was enabled. (Try `--output-type pdf`.)")
     if options.plugins:

src/ocrmypdf/_version.py

@@ -4,6 +4,10 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Get version by introspecting package information.
+
+OCRmyPDF uses setuptools_scm to derive version from git tags.
+"""
 
 try:
     from importlib_metadata import version as _package_version

src/ocrmypdf/api.py

@@ -4,6 +4,7 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Functions for using ocrmypdf as an API."""
 
 import logging
 import os
@@ -25,7 +26,10 @@ from ocrmypdf.helpers import is_iterable_notstr
 try:
     import coloredlogs
 except ModuleNotFoundError:
-    coloredlogs = None
+    coloredlogs = None  # pylint: disable=invalid-name
+
+if coloredlogs:
+    from humanfriendly.terminal import enable_ansi_support
 
 
 StrPath = Union[Path, AnyStr]
@@ -37,6 +41,7 @@ _api_lock = threading.Lock()
 class Verbosity(IntEnum):
     """Verbosity level for configure_logging."""
 
+    # pylint: disable=invalid-name
     quiet = -1  #: Suppress most messages
     default = 0  #: Default level of logging
     debug = 1  #: Output ocrmypdf debug messages
@@ -116,16 +121,15 @@ def configure_logging(
         fmt = '%(pageno)s%(message)s'
 
     use_colors = progress_bar_friendly
-    if not coloredlogs:
+    formatter = None
-        use_colors = False
+    if coloredlogs and use_colors:
-    if use_colors:
+        use_colors = enable_ansi_support()
-        if os.name == 'nt':
-            use_colors = coloredlogs.enable_ansi_support()
         if use_colors:
             use_colors = coloredlogs.terminal_supports_colors()
-    if use_colors:
+        if use_colors:
-        formatter = coloredlogs.ColoredFormatter(fmt=fmt)
+            formatter = coloredlogs.ColoredFormatter(fmt=fmt)
-    else:
+
+    if not formatter:
         formatter = logging.Formatter(fmt=fmt)
 
     console.setFormatter(formatter)
@@ -193,7 +197,7 @@ def create_options(
     else:
         cmdline.append(os.fspath(output_file))
 
-    parser._api_mode = True
+    parser.enable_api_mode()
     options = parser.parse_args(cmdline)
     for keyword, val in deferred:
         setattr(options, keyword, val)
@@ -295,7 +299,7 @@ def ocr(  # pylint: disable=unused-argument
             text already, and settings did not tell us to proceed.
         ocrmypdf.InputFileError: Any other problem with the input file.
         ocrmypdf.SubprocessOutputError: Any error related to executing a subprocess.
-        ocrmypdf.EncryptedPdfERror: If the input PDF is encrypted (password protected).
+        ocrmypdf.EncryptedPdfError: If the input PDF is encrypted (password protected).
             OCRmyPDF does not remove passwords.
         ocrmypdf.TesseractConfigError: If Tesseract reported its configuration was not
             valid.

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -11,6 +11,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+"""OCRmyPDF's multiprocessing/multithreading abstraction layer."""
+
 import logging
 import logging.handlers
 import multiprocessing
@@ -21,7 +23,6 @@ import sys
 import threading
 from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
 from contextlib import suppress
-from multiprocessing.pool import Pool, ThreadPool
 from typing import Callable, Iterable, Type, Union
 
 from tqdm import tqdm
@@ -44,7 +45,8 @@ def log_listener(q: Queue):
     should actually write to sys.stderr or whatever we're using, so if this is
     made into a process the main application needs to be directed to it.
 
-    See https://docs.python.org/3/howto/logging-cookbook.html#logging-to-a-single-file-from-multiple-processes
+    See:
+    https://docs.python.org/3/howto/logging-cookbook.html#logging-to-a-single-file-from-multiple-processes
     """
 
     while True:
@@ -89,6 +91,8 @@ def process_init(q: Queue, user_init: UserInit, loglevel) -> None:
 
 
 def thread_init(q: Queue, user_init: UserInit, loglevel) -> None:
+    del q  # unused but required argument
+    del loglevel  # unused but required argument
     # As a thread, block SIGBUS so the main thread deals with it...
     with suppress(AttributeError):
         signal.pthread_sigmask(signal.SIG_BLOCK, {signal.SIGBUS})
@@ -98,6 +102,8 @@ def thread_init(q: Queue, user_init: UserInit, loglevel) -> None:
 
 
 class StandardExecutor(Executor):
+    """Standard OCRmyPDF concurrent task executor."""
+
     def _execute(
         self,
         *,

src/ocrmypdf/builtin_plugins/default_filters.py

@@ -4,6 +4,8 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""OCRmyPDF automatically installs these filters as plugins."""
+
 from ocrmypdf import hookimpl
 
 

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+"""Built-in plugin to implement PDF page rasterization and PDF/A production."""
+
 import logging
 
 from ocrmypdf import hookimpl

src/ocrmypdf/builtin_plugins/optimize.py

@@ -0,0 +1,159 @@
+# © 2022 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+"""Built-in plugin to implement PDF page optimization."""
+
+import argparse
+import logging
+from pathlib import Path
+from typing import Sequence, Tuple
+
+from ocrmypdf import PdfContext, hookimpl
+from ocrmypdf._concurrent import Executor
+from ocrmypdf._exec import jbig2enc, pngquant
+from ocrmypdf._pipeline import get_pdf_save_settings
+from ocrmypdf.cli import numeric
+from ocrmypdf.optimize import optimize
+from ocrmypdf.subprocess import check_external_program
+
+log = logging.getLogger(__name__)
+
+
+@hookimpl
+def add_options(parser):
+    optimizing = parser.add_argument_group(
+        "Optimization options", "Control how the PDF is optimized after OCR"
+    )
+    optimizing.add_argument(
+        '-O',
+        '--optimize',
+        type=int,
+        choices=range(0, 4),
+        default=1,
+        help=(
+            "Control how PDF is optimized after processing:"
+            "0 - do not optimize; "
+            "1 - do safe, lossless optimizations (default); "
+            "2 - do lossy JPEG and JPEG2000 optimizations; "
+            "3 - do more aggressive lossy JPEG and JPEG2000 optimizations. "
+            "To enable lossy JBIG2, see --jbig2-lossy."
+        ),
+    )
+    optimizing.add_argument(
+        '--jpeg-quality',
+        type=numeric(int, 0, 100),
+        default=0,
+        metavar='Q',
+        help=(
+            "Adjust JPEG quality level for JPEG optimization. "
+            "100 is best quality and largest output size; "
+            "1 is lowest quality and smallest output; "
+            "0 uses the default."
+        ),
+    )
+    optimizing.add_argument(
+        '--jpg-quality',
+        type=numeric(int, 0, 100),
+        default=0,
+        metavar='Q',
+        dest='jpeg_quality',
+        help=argparse.SUPPRESS,  # Alias for --jpeg-quality
+    )
+    optimizing.add_argument(
+        '--png-quality',
+        type=numeric(int, 0, 100),
+        default=0,
+        metavar='Q',
+        help=(
+            "Adjust PNG quality level to use when quantizing PNGs. "
+            "Values have same meaning as with --jpeg-quality"
+        ),
+    )
+    optimizing.add_argument(
+        '--jbig2-lossy',
+        action='store_true',
+        help=(
+            "Enable JBIG2 lossy mode (better compression, not suitable for some "
+            "use cases - see documentation). Only takes effect if --optimize 1 or "
+            "higher is also enabled."
+        ),
+    )
+    optimizing.add_argument(
+        '--jbig2-page-group-size',
+        type=numeric(int, 1, 10000),
+        default=0,
+        metavar='N',
+        # Adjust number of pages to consider at once for JBIG2 compression
+        help=argparse.SUPPRESS,
+    )
+
+
+@hookimpl
+def check_options(options):
+    if options.optimize >= 2:
+        check_external_program(
+            program='pngquant',
+            package='pngquant',
+            version_checker=pngquant.version,
+            need_version='2.0.1',
+            required_for='--optimize {2,3}',
+        )
+
+    if options.optimize >= 2:
+        # Although we use JBIG2 for optimize=1, don't nag about it unless the
+        # user is asking for more optimization
+        check_external_program(
+            program='jbig2',
+            package='jbig2enc',
+            version_checker=jbig2enc.version,
+            need_version='0.28',
+            required_for='--optimize {2,3} | --jbig2-lossy',
+            recommended=True if not options.jbig2_lossy else False,
+        )
+
+    if options.optimize == 0 and any(
+        [options.jbig2_lossy, options.png_quality, options.jpeg_quality]
+    ):
+        log.warning(
+            "The arguments --jbig2-lossy, --png-quality, and --jpeg-quality "
+            "will be ignored because --optimize=0."
+        )
+
+
+@hookimpl
+def optimize_pdf(
+    input_pdf: Path,
+    output_pdf: Path,
+    context: PdfContext,
+    executor: Executor,
+    linearize: bool,
+) -> Tuple[Path, Sequence[str]]:
+    save_settings = dict(
+        linearize=linearize,
+        **get_pdf_save_settings(context.options.output_type),
+    )
+    result_path = optimize(input_pdf, output_pdf, context, save_settings, executor)
+    messages = []
+    if context.options.optimize == 0:
+        messages.append("Optimization was disabled.")
+    else:
+        image_optimizers = {
+            'jbig2': jbig2enc.available(),
+            'pngquant': pngquant.available(),
+        }
+        for name, available in image_optimizers.items():
+            if not available:
+                messages.append(
+                    f"The optional dependency '{name}' was not found, so some image "
+                    f"optimizations could not be attempted."
+                )
+    return result_path, messages
+
+
+@hookimpl
+def is_optimization_enabled(context: PdfContext) -> bool:
+    return context.options.optimize != 0

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -4,6 +4,8 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Built-in plugin to implement OCR using Tesseract."""
+
 
 import logging
 import os
@@ -138,6 +140,8 @@ def validate(pdfinfo, options):
 
 
 class TesseractOcrEngine(OcrEngine):
+    """Implements OCR with Tesseract."""
+
     @staticmethod
     def version():
         return tesseract.version()

src/ocrmypdf/cli.py

@@ -4,6 +4,7 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Command line interface customization and validation."""
 
 import argparse
 from typing import Any, Callable, Mapping, Optional, TypeVar
@@ -42,7 +43,7 @@ def str_to_int(mapping: Mapping[str, int]):
         except KeyError:
             raise argparse.ArgumentTypeError(
                 f"{s!r} must be one of: {', '.join(mapping.keys())}"
-            )
+            ) from None
 
     return _str_to_int
 
@@ -51,12 +52,20 @@ class ArgumentParser(argparse.ArgumentParser):
     """Override parser's default behavior of calling sys.exit()
 
     https://stackoverflow.com/questions/5943249/python-argparse-and-controlling-overriding-the-exit-status-code
+
+    OCRmyPDF began as a CLI but eventually acquired an API. The API works inside out,
+    by synthesizing a command line argument. So we subclass the standard parser with
+    one that doesn't call sys.exit(). Obviously this is not the ideal way to do things
+    but it works for us.
     """
 
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
         self._api_mode = False
 
+    def enable_api_mode(self):
+        self._api_mode = True
+
     def error(self, message):
         if not self._api_mode:
             super().error(message)
@@ -65,6 +74,8 @@ class ArgumentParser(argparse.ArgumentParser):
 
 
 class LanguageSetAction(argparse.Action):
+    """Manages a list of languages."""
+
     def __init__(self, option_strings, dest, default=None, **kwargs):
         if default is None:
             default = set()
@@ -142,7 +153,7 @@ Online documentation is located at:
         'output_file',
         metavar="output_pdf",
         help="Output searchable PDF file (or '-' to write to standard output). "
-        "Existing files will be ovewritten. If same as input file, the "
+        "Existing files will be overwritten. If same as input file, the "
         "input file will be updated only if processing is successful.",
     )
     parser.add_argument(
@@ -228,7 +239,13 @@ Online documentation is located at:
         help=argparse.SUPPRESS,
     )
     jobcontrol.add_argument(
-        '--use-threads', action='store_true', help=argparse.SUPPRESS
+        '--use-threads', action='store_true', default=True, help=argparse.SUPPRESS
+    )
+    jobcontrol.add_argument(
+        '--no-use-threads',
+        action='store_false',
+        dest='use_threads',
+        help=argparse.SUPPRESS,
     )
 
     metadata = parser.add_argument_group(
@@ -335,72 +352,6 @@ Online documentation is located at:
         "but include skipped pages in final output",
     )
 
-    optimizing = parser.add_argument_group(
-        "Optimization options", "Control how the PDF is optimized after OCR"
-    )
-    optimizing.add_argument(
-        '-O',
-        '--optimize',
-        type=int,
-        choices=range(0, 4),
-        default=1,
-        help=(
-            "Control how PDF is optimized after processing:"
-            "0 - do not optimize; "
-            "1 - do safe, lossless optimizations (default); "
-            "2 - do lossy JPEG and JPEG2000 optimizations; "
-            "3 - do more aggressive lossy JPEG and JPEG2000 optimizations. "
-            "To enable lossy JBIG2, see --jbig2-lossy."
-        ),
-    )
-    optimizing.add_argument(
-        '--jpeg-quality',
-        type=numeric(int, 0, 100),
-        default=0,
-        metavar='Q',
-        help=(
-            "Adjust JPEG quality level for JPEG optimization. "
-            "100 is best quality and largest output size; "
-            "1 is lowest quality and smallest output; "
-            "0 uses the default."
-        ),
-    )
-    optimizing.add_argument(
-        '--jpg-quality',
-        type=numeric(int, 0, 100),
-        default=0,
-        metavar='Q',
-        dest='jpeg_quality',
-        help=argparse.SUPPRESS,  # Alias for --jpeg-quality
-    )
-    optimizing.add_argument(
-        '--png-quality',
-        type=numeric(int, 0, 100),
-        default=0,
-        metavar='Q',
-        help=(
-            "Adjust PNG quality level to use when quantizing PNGs. "
-            "Values have same meaning as with --jpeg-quality"
-        ),
-    )
-    optimizing.add_argument(
-        '--jbig2-lossy',
-        action='store_true',
-        help=(
-            "Enable JBIG2 lossy mode (better compression, not suitable for some "
-            "use cases - see documentation). Only takes effect if --optimize 1 or "
-            "higher is also enabled."
-        ),
-    )
-    optimizing.add_argument(
-        '--jbig2-page-group-size',
-        type=numeric(int, 1, 10000),
-        default=0,
-        metavar='N',
-        # Adjust number of pages to consider at once for JBIG2 compression
-        help=argparse.SUPPRESS,
-    )
-
     advanced = parser.add_argument_group(
         "Advanced", "Advanced options to control OCRmyPDF"
     )

src/ocrmypdf/exceptions.py

@@ -4,12 +4,16 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""OCRmyPDF's exceptions."""
 
 from enum import IntEnum
 from textwrap import dedent
 
 
 class ExitCode(IntEnum):
+    """OCRmyPDF's exit codes."""
+
+    # pylint: disable=invalid-name
     ok = 0
     bad_args = 1
     input_file = 2
@@ -26,6 +30,8 @@ class ExitCode(IntEnum):
 
 
 class ExitCodeException(Exception):
+    """An exception which should return an exit code with sys.exit()."""
+
     exit_code = ExitCode.other_error
     message = ""
 
@@ -37,17 +43,24 @@ class ExitCodeException(Exception):
 
 
 class BadArgsError(ExitCodeException):
+    """Invalid arguments on the command line or API."""
+
     exit_code = ExitCode.bad_args
 
 
-class PdfMergeFailedError(ExitCodeException):
+class PdfMergeFailedError(ExitCodeException):  # deprecated
+    """An intermediate PDF can't be merged.
+
+    No longer in use.
+    """
+
     exit_code = ExitCode.input_file
     message = dedent(
         '''\
         Failed to merge PDF image layer with OCR layer
 
         Usually this happens because the input PDF file is malformed and
-        ocrmypdf cannot automatically correct the problem on its own.
+        ocrmypdf cannot correct the problem on its own.
 
         Try using
             ocrmypdf --pdf-renderer sandwich  [..other args..]
@@ -56,34 +69,50 @@ class PdfMergeFailedError(ExitCodeException):
 
 
 class MissingDependencyError(ExitCodeException):
+    """A third-party dependency is missing."""
+
     exit_code = ExitCode.missing_dependency
 
 
 class UnsupportedImageFormatError(ExitCodeException):
+    """The image format is not supported."""
+
     exit_code = ExitCode.input_file
 
 
 class DpiError(ExitCodeException):
+    """Missing information about input image DPI."""
+
     exit_code = ExitCode.input_file
 
 
 class OutputFileAccessError(ExitCodeException):
+    """Cannot access the intended output file path."""
+
     exit_code = ExitCode.file_access_error
 
 
 class PriorOcrFoundError(ExitCodeException):
+    """This file already has OCR."""
+
     exit_code = ExitCode.already_done_ocr
 
 
 class InputFileError(ExitCodeException):
+    """Something is wrong with the input file."""
+
     exit_code = ExitCode.input_file
 
 
 class SubprocessOutputError(ExitCodeException):
+    """A subprocess returned an unexpected error."""
+
     exit_code = ExitCode.child_process_error
 
 
 class EncryptedPdfError(ExitCodeException):
+    """Input PDF is encrypted."""
+
     exit_code = ExitCode.encrypted_pdf
     message = dedent(
         '''\
@@ -100,5 +129,7 @@ class EncryptedPdfError(ExitCodeException):
 
 
 class TesseractConfigError(ExitCodeException):
+    """Tesseract config can't be parsed."""
+
     exit_code = ExitCode.invalid_config
     message = "Error occurred while parsing a Tesseract configuration file"

src/ocrmypdf/extra_plugins/semfree.py

@@ -37,9 +37,11 @@ from ocrmypdf.helpers import remove_all_log_handlers
 
 
 class MessageType(Enum):
-    exception = auto()
+    """Implement basic IPC messaging."""
-    result = auto()
+
-    complete = auto()
+    exception = auto()  # pylint: disable=invalid-name
+    result = auto()  # pylint: disable=invalid-name
+    complete = auto()  # pylint: disable=invalid-name
 
 
 def split_every(n: int, iterable: Iterable) -> Iterator:
@@ -59,6 +61,8 @@ def process_sigbus(*args):
 
 
 class ConnectionLogHandler(logging.handlers.QueueHandler):
+    """Handler used by child processes to forward log messages to parent."""
+
     def __init__(self, conn: Connection) -> None:
         # sets the parent's queue to None - parent only touches queue
         # in enqueue() which we override
@@ -91,7 +95,7 @@ def process_loop(
     for args in task_args:
         try:
             result = task(args)
-        except Exception as e:
+        except Exception as e:  # pylint: disable=broad-except
             conn.send((MessageType.exception, e))
             break
         else:
@@ -103,6 +107,8 @@ def process_loop(
 
 
 class LambdaExecutor(Executor):
+    """Executor for AWS Lambda or similar environments that lack semaphores."""
+
     def _execute(
         self,
         *,
@@ -153,13 +159,13 @@ class LambdaExecutor(Executor):
 
         with self.pbar_class(**tqdm_kwargs) as pbar:
             while connections:
-                for r in wait(connections):
+                for result in wait(connections):
-                    if not isinstance(r, Connection):
+                    if not isinstance(result, Connection):
                         raise NotImplementedError("We only support Connection()")
                     try:
-                        msg_type, msg = r.recv()
+                        msg_type, msg = result.recv()
                     except EOFError:
-                        connections.remove(r)
+                        connections.remove(result)
                         continue
 
                     if msg_type == MessageType.result:
@@ -170,7 +176,7 @@ class LambdaExecutor(Executor):
                         logger = logging.getLogger(record.name)
                         logger.handle(record)
                     elif msg_type == MessageType.complete:
-                        connections.remove(r)
+                        connections.remove(result)
                     elif msg_type == MessageType.exception:
                         for process in processes:
                             process.terminate()

src/ocrmypdf/helpers.py

@@ -4,6 +4,7 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Support functions."""
 
 import logging
 import multiprocessing
@@ -19,10 +20,21 @@ from math import isclose, isfinite
 from pathlib import Path
 from typing import Any, Sequence
 
+import img2pdf
 import pikepdf
+from packaging.version import Version
 
 log = logging.getLogger(__name__)
 
+if Version(img2pdf.__version__) < Version('0.4.0'):
+    IMG2PDF_KWARGS = dict(without_pdfw=True)
+elif Version(img2pdf.__version__) < Version('0.4.3'):
+    IMG2PDF_KWARGS = dict(engine=img2pdf.Engine.pikepdf)
+else:
+    IMG2PDF_KWARGS = dict(
+        engine=img2pdf.Engine.pikepdf, rotation=img2pdf.Rotation.ifvalid
+    )
+
 
 class Resolution(namedtuple('Resolution', ('x', 'y'))):
     """The number of pixels per inch in each 2D direction.
@@ -126,11 +138,11 @@ def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
     os.symlink(os.path.abspath(input_file), soft_link_name)
 
 
-def samefile(f1: os.PathLike, f2: os.PathLike):
+def samefile(file1: os.PathLike, file2: os.PathLike):
     if os.name == 'nt':
-        return f1 == f2
+        return file1 == file2
     else:
-        return os.path.samefile(f1, f2)
+        return os.path.samefile(file1, file2)
 
 
 def is_iterable_notstr(thing: Any) -> bool:
@@ -138,9 +150,9 @@ def is_iterable_notstr(thing: Any) -> bool:
     return isinstance(thing, Iterable) and not isinstance(thing, str)
 
 
-def monotonic(L: Sequence) -> bool:
+def monotonic(seq: Sequence) -> bool:
     """Does this sequence increase monotonically?"""
-    return all(b > a for a, b in zip(L, L[1:]))
+    return all(b > a for a, b in zip(seq, seq[1:]))
 
 
 def page_number(input_file: os.PathLike) -> int:
@@ -155,7 +167,7 @@ def available_cpu_count() -> int:
     except NotImplementedError:
         pass
     warnings.warn(
-        "Could not get CPU count.  Assuming one (1) CPU." "Use -j N to set manually."
+        "Could not get CPU count. Assuming one (1) CPU. Use -j N to set manually."
     )
     return 1
 
@@ -179,16 +191,16 @@ def is_file_writable(test_file: os.PathLike) -> bool:
                 os.W_OK,
                 effective_ids=(os.access in os.supports_effective_ids),
             )
+
+        try:
+            fp = p.open('wb')
+        except OSError:
+            return False
         else:
-            try:
+            fp.close()
-                fp = p.open('wb')
+            with suppress(OSError):
-            except OSError:
+                p.unlink()
-                return False
+        return True
-            else:
-                fp.close()
-                with suppress(OSError):
-                    p.unlink()
-            return True
     except (OSError, RuntimeError) as e:
         log.debug(e)
         log.error(str(e))
@@ -209,11 +221,19 @@ def check_pdf(input_file: Path) -> bool:
     else:
         with pdf:
             messages = pdf.check()
+            success = True
             for msg in messages:
                 if 'error' in msg.lower():
                     log.error(msg)
+                    success = False
+                elif (
+                    "/DecodeParms: operation for dictionary attempted on object "
+                    "of type null" in msg
+                ):
+                    pass  # Ignore/spurious warning
                 else:
                     log.warning(msg)
+                    success = False
 
             sio = StringIO()
             linearize_msgs = ''
@@ -228,7 +248,7 @@ def check_pdf(input_file: Path) -> bool:
                 if linearize_msgs:
                     log.warning(linearize_msgs)
 
-            if not messages and not linearize_msgs:
+            if success and not linearize_msgs:
                 return True
             return False
 

src/ocrmypdf/hocrtransform.py

@@ -28,6 +28,8 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
+"""Transform .hocr and page image to text PDF."""
+
 import argparse
 import os
 import re
@@ -99,7 +101,7 @@ HOCR_OK_LANGS = frozenset(
 Element = ElementTree.Element
 
 
-class Rect(NamedTuple):  # pylint: disable=inherit-non-class
+class Rect(NamedTuple):
     """A rectangle for managing PDF coordinates."""
 
     x1: Any
@@ -109,7 +111,7 @@ class Rect(NamedTuple):  # pylint: disable=inherit-non-class
 
 
 class HocrTransformError(Exception):
-    pass
+    """Error while applying hOCR transform."""
 
 
 class HocrTransform:
@@ -287,7 +289,7 @@ class HocrTransform:
                 continue
 
             pxl_coords = self.element_coordinates(elem)
-            pt = self.pt_from_pixel(pxl_coords)
+            pt = self.pt_from_pixel(pxl_coords)  # pylint: disable=invalid-name
 
             # draw the bbox border
             if show_bounding_boxes:  # pragma: no cover

src/ocrmypdf/optimize.py

@@ -4,10 +4,13 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Post-processing image optimization of OCR PDFs."""
+
 
 import logging
 import sys
 import tempfile
+import threading
 from collections import defaultdict
 from os import fspath
 from pathlib import Path
@@ -23,6 +26,7 @@ from typing import (
     Sequence,
     Tuple,
 )
+from zlib import compress
 
 import img2pdf
 from pikepdf import (
@@ -31,6 +35,7 @@ from pikepdf import (
     Object,
     ObjectStreamMode,
     Pdf,
+    PdfError,
     PdfImage,
     Stream,
     UnsupportedImageTypeError,
@@ -41,7 +46,7 @@ from ocrmypdf._concurrent import Executor, SerialExecutor
 from ocrmypdf._exec import jbig2enc, pngquant
 from ocrmypdf._jobcontext import PdfContext
 from ocrmypdf.exceptions import OutputFileAccessError
-from ocrmypdf.helpers import safe_symlink
+from ocrmypdf.helpers import IMG2PDF_KWARGS, safe_symlink
 
 log = logging.getLogger(__name__)
 
@@ -52,7 +57,9 @@ DEFAULT_PNG_QUALITY = 70
 Xref = NewType('Xref', int)
 
 
-class XrefExt(NamedTuple):  # pylint: disable=inherit-non-class
+class XrefExt(NamedTuple):
+    """A PDF xref and image extension pair."""
+
     xref: Xref
     ext: str
 
@@ -78,33 +85,49 @@ def extract_image_filter(
     if image.Subtype != Name.Image:
         return None
     if image.Length < 100:
-        log.debug(f"Skipping small image, xref {xref}")
+        log.debug(f"xref {xref}: skipping image with small stream size")
         return None
     if image.Width < 8 or image.Height < 8:  # Issue 732
-        log.debug(f"Skipping oddly sized image, xref {xref}")
+        log.debug(f"xref {xref}: skipping image with unusually small dimensions")
         return None
 
     pim = PdfImage(image)
 
     if len(pim.filter_decodeparms) > 1:
-        log.debug(f"Skipping multiply filtered image, xref {xref}")
+        first_filtdp = pim.filter_decodeparms[0]
-        return None
+        second_filtdp = pim.filter_decodeparms[1]
-    filtdp = pim.filter_decodeparms[0]
+        if (
+            len(pim.filter_decodeparms) == 2
+            and first_filtdp[0] == Name.FlateDecode
+            and first_filtdp[1].get(Name.Predictor, 1) == 1
+            and second_filtdp[0] == Name.DCTDecode
+            and not second_filtdp[1]
+        ):
+            log.debug(
+                f"xref {xref}: found image compressed as /FlateDecode /DCTDecode, "
+                "marked for JPEG optimization"
+            )
+            filtdp = pim.filter_decodeparms[1]
+        else:
+            log.debug(f"xref {xref}: skipping image with multiple compression filters")
+            return None
+    else:
+        filtdp = pim.filter_decodeparms[0]
 
     if pim.bits_per_component > 8:
-        log.debug(f"Skipping wide gamut image, xref {xref}")
+        log.debug(f"xref {xref}: skipping wide gamut image")
         return None  # Don't mess with wide gamut images
 
     if filtdp[0] == Name.JPXDecode:
-        log.debug(f"Skipping JPEG2000 image, xref {xref}")
+        log.debug(f"xref {xref}: skipping JPEG2000 image")
         return None  # Don't do JPEG2000
 
     if filtdp[0] == Name.CCITTFaxDecode and filtdp[1].get('/K', 0) >= 0:
-        log.debug(f"Skipping CCITT Group 3 image, xref {xref}")
+        log.debug(f"xref {xref}: skipping CCITT Group 3 image")
         return None  # pikepdf doesn't support Group 3 yet
 
     if Name.Decode in image:
-        log.debug(f"Skipping image with Decode table, xref {xref}")
+        log.debug(f"xref {xref}: skipping image with Decode table")
         return None  # Don't mess with custom Decode tables
 
     return pim, filtdp
@@ -172,14 +195,6 @@ def extract_image_generic(
         # jpeg_quality_estimate = 117.0 * (bytes_per_pixel ** 0.213)
         # if jpeg_quality_estimate < 65:
         #     return None
-
-        # We could get the ICC profile here, but there's no need to look at it
-        # for quality transcoding
-        # if icc:
-        #     stream = BytesIO(raw_jpeg.read_raw_bytes())
-        #     iccbytes = icc.read_bytes()
-        #     with Image.open(stream) as im:
-        #         im.save(jpg_name(root, xref), icc_profile=iccbytes)
         try:
             imgname = root / f'{xref:08d}'
             with imgname.open('wb') as f:
@@ -200,7 +215,11 @@ def extract_image_generic(
     elif not pim.indexed and pim.colorspace in pim.SIMPLE_COLORSPACES:
         # An optimization opportunity here, not currently taken, is directly
         # generating a PNG from compressed data
-        pim.as_pil_image().save(png_name(root, xref))
+        try:
+            pim.as_pil_image().save(png_name(root, xref))
+        except NotImplementedError:
+            log.warning("PDF contains an atypical image that cannot be optimized.")
+            return None
         return XrefExt(xref, '.png')
     elif (
         not pim.indexed
@@ -251,13 +270,13 @@ def extract_images(
             if image.objgen[1] != 0:
                 continue  # Ignore images in an incremental PDF
             xref = Xref(image.objgen[0])
-            if hasattr(image, 'SMask'):
+            if Name.SMask in image:
                 # Ignore soft masks
                 smask_xref = Xref(image.SMask.objgen[0])
                 exclude_xrefs.add(smask_xref)
-                log.debug(f"Skipping image {smask_xref} because it is an SMask")
+                log.debug(f"xref {smask_xref}: skipping image because it is an SMask")
             include_xrefs.add(xref)
-            log.debug(f"Treating {xref} as an optimization candidate")
+            log.debug(f"xref {xref}: treating as an optimization candidate")
             if xref not in pageno_for_xref:
                 pageno_for_xref[xref] = pageno
 
@@ -269,7 +288,9 @@ def extract_images(
                 pike=pike, root=root, image=image, xref=xref, options=options
             )
         except Exception:  # pylint: disable=broad-except
-            log.exception(f"While extracting image xref {xref}, an error occurred")
+            log.exception(
+                f"xref {xref}: While extracting this image, an error occurred"
+            )
             errors += 1
         else:
             if result:
@@ -290,7 +311,7 @@ def extract_images_generic(
             pngs.append(xref_ext.xref)
         elif xref_ext.ext == '.jpg':
             jpegs.append(xref_ext.xref)
-    log.debug("Optimizable images: JPEGs: %s PNGs: %s", len(jpegs), len(pngs))
+    log.debug(f"Optimizable images: JPEGs: {len(jpegs)} PNGs: {len(pngs)}")
     return jpegs, pngs
 
 
@@ -302,7 +323,7 @@ def extract_images_jbig2(pike: Pdf, root: Path, options) -> Dict[int, List[XrefE
         group = pageno // options.jbig2_page_group_size
         jbig2_groups[group].append(xref_ext)
 
-    log.debug("Optimizable images: JBIG2 groups: %s", (len(jbig2_groups),))
+    log.debug(f"Optimizable images: JBIG2 groups: {len(jbig2_groups)}")
     return jbig2_groups
 
 
@@ -401,15 +422,11 @@ def convert_to_jbig2(
 def _optimize_jpeg(args: Tuple[Xref, Path, Path, int]) -> Tuple[Xref, Optional[Path]]:
     xref, in_jpg, opt_jpg, jpeg_quality = args
 
-    # This may produce a debug warning from PIL
-    # DEBUG:PIL.Image:Error closing: 'NoneType' object has no attribute
-    # 'close'.  Seems to be mostly harmless
-    # https://github.com/python-pillow/Pillow/issues/1144
     with Image.open(in_jpg) as im:
         im.save(opt_jpg, optimize=True, quality=jpeg_quality)
 
     if opt_jpg.stat().st_size > in_jpg.stat().st_size:
-        log.debug("xref %s, jpeg, made larger - skip", xref)
+        log.debug(f"xref {xref}, jpeg, made larger - skip")
         opt_jpg.unlink()
         return xref, None
     return xref, opt_jpg
@@ -436,7 +453,7 @@ def transcode_jpegs(
         use_threads=True,  # Processes are significantly slower at this task
         max_workers=options.jobs,
         tqdm_kwargs=dict(
-            desc="JPEGs",
+            desc="Recompressing JPEGs",
             total=len(jpegs),
             unit='image',
             disable=not options.progress_bar,
@@ -447,10 +464,77 @@ def transcode_jpegs(
     )
 
 
+def _find_deflatable_jpeg(
+    *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
+) -> Optional[XrefExt]:
+    result = extract_image_filter(pike, root, image, xref)
+    if result is None:
+        return None
+    _pim, filtdp = result
+
+    if filtdp[0] == Name.DCTDecode and not filtdp[1] and options.optimize >= 1:
+        return XrefExt(xref, '.memory')
+
+    return None
+
+
+def _deflate_jpeg(args: Tuple[Pdf, threading.Lock, Xref, int]) -> Tuple[Xref, bytes]:
+    pike, lock, xref, complevel = args
+    with lock:
+        xobj = pike.get_object(xref, 0)
+        try:
+            data = xobj.read_raw_bytes()
+        except PdfError:
+            return xref, b''
+    compdata = compress(data, complevel)
+    if len(compdata) >= len(data):
+        return xref, b''
+    return xref, compdata
+
+
+def deflate_jpegs(pike: Pdf, root: Path, options, executor: Executor) -> None:
+    jpegs = []
+    for _pageno, xref_ext in extract_images(pike, root, options, _find_deflatable_jpeg):
+        xref = xref_ext.xref
+        log.debug(f'xref {xref}: marking this JPEG as deflatable')
+        jpegs.append(xref)
+
+    complevel = 9 if options.optimize == 3 else 6
+
+    # Our calls to xobj.write() in finish() need coordination
+    lock = threading.Lock()
+
+    def deflate_args() -> Iterator:
+        for xref in jpegs:
+            yield pike, lock, xref, complevel
+
+    def finish(result, pbar):
+        xref, compdata = result
+        if len(compdata) > 0:
+            with lock:
+                xobj = pike.get_object(xref, 0)
+                xobj.write(compdata, filter=[Name.FlateDecode, Name.DCTDecode])
+        pbar.update()
+
+    executor(
+        use_threads=True,  # We're sharing the pdf directly, must use threads
+        max_workers=options.jobs,
+        tqdm_kwargs=dict(
+            desc="Deflating JPEGs",
+            total=len(jpegs),
+            unit='image',
+            disable=not options.progress_bar,
+        ),
+        task=_deflate_jpeg,
+        task_arguments=deflate_args(),
+        task_finished=finish,
+    )
+
+
 def _transcode_png(pike: Pdf, filename: Path, xref: Xref) -> bool:
     output = filename.with_suffix('.png.pdf')
     with output.open('wb') as f:
-        img2pdf.convert(fspath(filename), outputstream=f)
+        img2pdf.convert(fspath(filename), outputstream=f, **IMG2PDF_KWARGS)
 
     with Pdf.open(output) as pdf_image:
         foreign_image = next(iter(pdf_image.pages[0].images.values()))
@@ -541,11 +625,11 @@ def optimize(
     context,
     save_settings,
     executor: Executor = DEFAULT_EXECUTOR,
-) -> None:
+) -> Path:
     options = context.options
     if options.optimize == 0:
         safe_symlink(input_file, output_file)
-        return
+        return output_file
 
     if options.jpeg_quality == 0:
         options.jpeg_quality = DEFAULT_JPEG_QUALITY if options.optimize < 3 else 40
@@ -560,6 +644,7 @@ def optimize(
 
         jpegs, pngs = extract_images_generic(pike, root, options)
         transcode_jpegs(pike, jpegs, root, options, executor)
+        deflate_jpegs(pike, root, options, executor)
         # if options.optimize >= 2:
         # Try pngifying the jpegs
         #    transcode_pngs(pike, jpegs, jpg_name, root, options)
@@ -579,9 +664,7 @@ def optimize(
             f"Output file not created after optimizing. We probably ran "
             f"out of disk space in the temporary folder: {tempfile.gettempdir()}."
         )
-    ratio = input_size / output_size
     savings = 1 - output_size / input_size
-    log.info(f"Optimize ratio: {ratio:.2f} savings: {(savings):.1%}")
 
     if savings < 0:
         log.info(
@@ -595,6 +678,8 @@ def optimize(
     else:
         safe_symlink(target_file, output_file)
 
+    return output_file
+
 
 def main(infile, outfile, level, jobs=1):
     from shutil import copy  # pylint: disable=import-outside-toplevel
@@ -626,9 +711,9 @@ def main(infile, outfile, level, jobs=1):
         jb2lossy=False,
     )
 
-    with TemporaryDirectory() as td:
+    with TemporaryDirectory() as tmpdir:
-        context = PdfContext(options, td, infile, None, None)
+        context = PdfContext(options, tmpdir, infile, None, None)
-        tmpout = Path(td) / 'out.pdf'
+        tmpout = Path(tmpdir) / 'out.pdf'
         optimize(
             infile,
             tmpout,

src/ocrmypdf/pdfa.py

@@ -97,7 +97,8 @@ def generate_pdfa_ps(target_filename: Path, icc: str = 'sRGB'):
         target_filename: filename to save
         icc: ICC identifier such as 'sRGB'
     References:
-        Adobe PDFMARK Reference: https://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/pdfmark_reference.pdf
+        Adobe PDFMARK Reference:
+        https://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/pdfmark_reference.pdf
     """
     if icc != 'sRGB':
         raise NotImplementedError("Only supporting sRGB")
@@ -105,11 +106,11 @@ def generate_pdfa_ps(target_filename: Path, icc: str = 'sRGB'):
     bytes_icc_profile = (
         package_files('ocrmypdf.data') / SRGB_ICC_PROFILE_NAME
     ).read_bytes()
-    ps = '\n'.join(_make_postscript(icc, bytes_icc_profile, 3))
+    postscript = '\n'.join(_make_postscript(icc, bytes_icc_profile, 3))
 
     # We should have encoded everything to pure ASCII by this point, and
     # to be safe, only allow ASCII in PostScript
-    Path(target_filename).write_text(ps, encoding='ascii')
+    Path(target_filename).write_text(postscript, encoding='ascii')
     return target_filename
 
 

src/ocrmypdf/pdfinfo/__init__.py

@@ -6,4 +6,6 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+"""For extracting information about PDFs prior to OCR."""
+
 from ocrmypdf.pdfinfo.info import Colorspace, Encoding, PdfInfo

src/ocrmypdf/pdfinfo/info.py

@@ -6,13 +6,15 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+"""Extract information about the content of a PDF."""
+
 import atexit
 import logging
 import re
 from collections import defaultdict
 from contextlib import ExitStack
 from decimal import Decimal
-from enum import Enum
+from enum import Enum, auto
 from functools import partial
 from math import hypot, inf, isclose
 from os import PathLike
@@ -20,11 +22,13 @@ from pathlib import Path
 from typing import (
     Container,
     Dict,
+    Iterable,
     Iterator,
     List,
     Mapping,
     NamedTuple,
     Optional,
+    Sequence,
     Tuple,
     Union,
 )
@@ -36,6 +40,7 @@ from pikepdf import (
     PdfImage,
     PdfInlineImage,
     PdfMatrix,
+    UnsupportedImageTypeError,
     parse_content_stream,
 )
 
@@ -46,11 +51,39 @@ from ocrmypdf.pdfinfo.layout import get_page_analysis, get_text_boxes
 
 logger = logging.getLogger()
 
-Colorspace = Enum('Colorspace', 'gray rgb cmyk lab icc index sep devn pattern jpeg2000')
 
-Encoding = Enum(
+class Colorspace(Enum):
-    'Encoding', 'ccitt jpeg jpeg2000 jbig2 asciihex ascii85 lzw flate runlength'
+    """Description of common image colorspaces in a PDF."""
-)
+
+    # pylint: disable=invalid-name
+    gray = auto()
+    rgb = auto()
+    cmyk = auto()
+    lab = auto()
+    icc = auto()
+    index = auto()
+    sep = auto()
+    devn = auto()
+    pattern = auto()
+    jpeg2000 = auto()
+
+
+class Encoding(Enum):
+    """Description of common image encodings in a PDF."""
+
+    # pylint: disable=invalid-name
+    ccitt = auto()
+    jpeg = auto()
+    jpeg2000 = auto()
+    jbig2 = auto()
+    asciihex = auto()
+    ascii85 = auto()
+    lzw = auto()
+    flate = auto()
+    runlength = auto()
+
+
+FloatRect = Tuple[float, float, float, float]
 
 FRIENDLY_COLORSPACE: Dict[str, Colorspace] = {
     '/DeviceGray': Colorspace.gray,
@@ -103,18 +136,24 @@ def _is_unit_square(shorthand):
 
 
 class XobjectSettings(NamedTuple):
+    """Info about an XObject found in a PDF."""
+
     name: str
     shorthand: Tuple[float, float, float, float, float, float]
     stack_depth: int
 
 
 class InlineSettings(NamedTuple):
+    """Info about an inline image found in a PDF."""
+
     iimage: PdfInlineImage
     shorthand: Tuple[float, float, float, float, float, float]
     stack_depth: int
 
 
 class ContentsInfo(NamedTuple):
+    """Info about various objects found in a PDF."""
+
     xobject_settings: List[XobjectSettings]
     inline_images: List[InlineSettings]
     found_vector: bool
@@ -123,17 +162,19 @@ class ContentsInfo(NamedTuple):
 
 
 class TextboxInfo(NamedTuple):
+    """Info about a text box found in a PDF."""
+
     bbox: Tuple[float, float, float, float]
     is_visible: bool
     is_corrupt: bool
 
 
 class VectorMarker:
-    pass
+    """Sentinel indicating vector drawing operations were found on a page."""
 
 
 class TextMarker:
-    pass
+    """Sentinel indicating text drawing operations were found on a page."""
 
 
 def _normalize_stack(graphobjs):
@@ -195,7 +236,7 @@ def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
             if len(stack) > 32:  # See docstring
                 if len(stack) > 128:
                     raise RuntimeError(
-                        "PDF graphics stack overflowed hard limit, operator %i" % n
+                        f"PDF graphics stack overflowed hard limit at operator {n}"
                     )
                 warn("PDF graphics stack overflowed spec limit")
         elif operator == 'Q':
@@ -281,7 +322,7 @@ def _get_dpi(ctm_shorthand, image_size) -> Resolution:
 
     """
 
-    a, b, c, d, _, _ = ctm_shorthand
+    a, b, c, d, _, _ = ctm_shorthand  # pylint: disable=invalid-name
 
     # Calculate the width and height of the image in PDF units
     image_drawn = hypot(a, b), hypot(c, d)
@@ -297,6 +338,8 @@ def _get_dpi(ctm_shorthand, image_size) -> Resolution:
 
 
 class ImageInfo:
+    """Information about an image found in a PDF."""
+
     DPI_PREC = Decimal('1.000')
 
     _comp: Optional[int]
@@ -349,13 +392,20 @@ class ImageInfo:
 
         if self._color == Colorspace.icc:
             # Check the ICC profile to determine actual colorspace
-            pim_icc = pim.icc
+            try:
-            if pim_icc.profile.xcolor_space == 'GRAY':
+                pim_icc = pim.icc
-                self._comp = 1
+                if pim_icc.profile.xcolor_space == 'GRAY':
-            elif pim_icc.profile.xcolor_space == 'CMYK':
+                    self._comp = 1
-                self._comp = 4
+                elif pim_icc.profile.xcolor_space == 'CMYK':
-            else:
+                    self._comp = 4
-                self._comp = 3
+                else:
+                    self._comp = 3
+            except UnsupportedImageTypeError as ex:
+                self._comp = None
+                logger.warning(
+                    f"An image with a corrupt or unreadable ICC profile was found. "
+                    f"The output PDF may not match the input PDF visually: {ex}. {self}"
+                )
         else:
             if isinstance(self._color, Colorspace):
                 self._comp = FRIENDLY_COMP.get(self._color)
@@ -408,15 +458,10 @@ class ImageInfo:
         return _get_dpi(self._shorthand, (self._width, self._height))
 
     def __repr__(self):
-        class_locals = {
-            attr: getattr(self, attr, None)
-            for attr in dir(self)
-            if not attr.startswith('_')
-        }
         return (
-            "<ImageInfo '{name}' {type_} {width}x{height} {color} "
+            f"<ImageInfo '{self.name}' {self.type_} {self.width}x{self.height} "
-            "{comp} {bpc} {enc} {dpi}>"
+            f"{self.color} {self.comp} {self.bpc} {self.enc} {self.dpi}>"
-        ).format(**class_locals)
+        )
 
 
 def _find_inline_images(contentsinfo: ContentsInfo) -> Iterator[ImageInfo]:
@@ -424,7 +469,7 @@ def _find_inline_images(contentsinfo: ContentsInfo) -> Iterator[ImageInfo]:
 
     for n, inline in enumerate(contentsinfo.inline_images):
         yield ImageInfo(
-            name='inline-%02d' % n, shorthand=inline.shorthand, inline=inline.iimage
+            name=f'inline-{n:02d}', shorthand=inline.shorthand, inline=inline.iimage
         )
 
 
@@ -565,10 +610,10 @@ def _process_content_streams(
     yield from _find_form_xobject_images(pdf, container, contentsinfo)
 
 
-def _page_has_text(text_blocks, page_width, page_height) -> bool:
+def _page_has_text(text_blocks: Iterable[FloatRect], page_width, page_height) -> bool:
     """Smarter text detection that ignores text in margins"""
 
-    pw, ph = float(page_width), float(page_height)
+    pw, ph = float(page_width), float(page_height)  # pylint: disable=invalid-name
 
     margin_ratio = 0.125
     interior_bbox = (
@@ -578,7 +623,7 @@ def _page_has_text(text_blocks, page_width, page_height) -> bool:
         margin_ratio * ph,  # bottom  (first quadrant: bottom < top)
     )
 
-    def rects_intersect(a, b) -> bool:
+    def rects_intersect(a: FloatRect, b: FloatRect) -> bool:
         """
         Where (a,b) are 4-tuple rects (left-0, top-1, right-2, bottom-3)
         https://stackoverflow.com/questions/306316/determine-if-two-rectangles-overlap-each-other
@@ -600,19 +645,19 @@ def simplify_textboxes(miner, textbox_getter) -> Iterator[TextboxInfo]:
     We do this to save memory and ensure that our objects are pickleable.
     """
     for box in textbox_getter(miner):
-        first_line = box._objs[0]
+        first_line = box._objs[0]  # pylint: disable=protected-access
-        first_char = first_line._objs[0]
+        first_char = first_line._objs[0]  # pylint: disable=protected-access
 
         visible = first_char.rendermode != 3
         corrupt = first_char.get_text() == '\ufffd'
         yield TextboxInfo(box.bbox, visible, corrupt)
 
 
-worker_pdf = None
+worker_pdf = None  # pylint: disable=invalid-name
 
 
 def _pdf_pageinfo_sync_init(pdf: Pdf, infile: Path, pdfminer_loglevel):
-    global worker_pdf  # pylint: disable=global-statement
+    global worker_pdf  # pylint: disable=global-statement,invalid-name
     pikepdf_enable_mmap()
 
     logging.getLogger('pdfminer').setLevel(pdfminer_loglevel)
@@ -646,8 +691,8 @@ def _pdf_pageinfo_concurrent(
     max_workers,
     check_pages,
     detailed_analysis=False,
-):
+) -> Sequence[Optional['PageInfo']]:
-    pages = [None] * len(pdf.pages)
+    pages: Sequence[Optional['PageInfo']] = [None] * len(pdf.pages)
 
     def update_pageinfo(result, pbar):
         page = result
@@ -697,6 +742,8 @@ def _pdf_pageinfo_concurrent(
 
 
 class PageInfo:
+    """Information about type of contents on each page in a PDF."""
+
     _has_text: Optional[bool]
     _has_vector: Optional[bool]
     _images: List[ImageInfo]
@@ -758,15 +805,15 @@ class PageInfo:
             self._has_vector = False
             self._has_text = False
             self._images = []
-            for ci in _process_content_streams(
+            for info in _process_content_streams(
                 pdf=pdf, container=page, shorthand=userunit_shorthand
             ):
-                if isinstance(ci, VectorMarker):
+                if isinstance(info, VectorMarker):
                     self._has_vector = True
-                elif isinstance(ci, TextMarker):
+                elif isinstance(info, TextMarker):
                     self._has_text = True
-                elif isinstance(ci, ImageInfo):
+                elif isinstance(info, ImageInfo):
-                    self._images.append(ci)
+                    self._images.append(info)
                 else:
                     raise NotImplementedError()
         else:
@@ -918,17 +965,17 @@ class PdfInfo:
                     self._has_acroform = True
 
     @property
-    def pages(self):
+    def pages(self) -> Sequence[Optional[PageInfo]]:
         return self._pages
 
     @property
     def min_version(self) -> str:
         # The minimum PDF is the maximum version that any particular page needs
-        return max(page.min_version for page in self.pages)
+        return max(page.min_version for page in self.pages if page)
 
     @property
     def has_userunit(self) -> bool:
-        return any(page.userunit != 1.0 for page in self.pages)
+        return any(page.userunit != 1.0 for page in self.pages if page)
 
     @property
     def has_acroform(self) -> bool:

src/ocrmypdf/pluginspec.py

@@ -4,15 +4,25 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""OCRmyPDF pluggy plugin specification."""
 
 from abc import ABC, abstractmethod
 from argparse import ArgumentParser, Namespace
 from logging import Handler
 from pathlib import Path
-from typing import TYPE_CHECKING, AbstractSet, List, NamedTuple, Optional
+from typing import (
+    TYPE_CHECKING,
+    AbstractSet,
+    List,
+    NamedTuple,
+    Optional,
+    Sequence,
+    Tuple,
+)
 
 import pluggy
 
+from ocrmypdf import PdfContext
 from ocrmypdf._concurrent import Executor
 from ocrmypdf.helpers import Resolution
 
@@ -132,6 +142,7 @@ def get_progressbar_class():
     Here is how OCRmyPDF will use the progress bar:
 
     Example:
+
         pbar_class = pm.hook.get_progressbar_class()
         with pbar_class(**tqdm_kwargs) as pbar:
             ...
@@ -235,9 +246,9 @@ def filter_page_image(page: 'PageContext', image_filename: Path) -> Path:
     ``image_filename``. The hook may overwrite ``image_filename`` with a new file.
 
     The output image should preserve the same physical unit dimensions, that is
-    (width * dpi_x, height * dpi_y). That is, if the image is resized, the DPI
+    ``(width * dpi_x, height * dpi_y)``. That is, if the image is resized, the DPI
     must be adjusted by the reciprocal. If this is not preserved, the PDF page
-    will be resized and the OCR layer misaligned. OCRmyPDF does not nothing
+    will be resized and the OCR layer misaligned. OCRmyPDF does nothing
     to enforce these constraints; it is up to the plugin to do sensible things.
 
     OCRmyPDF will create the PDF page based on the image format used (unless the
@@ -399,8 +410,7 @@ def get_ocr_engine() -> OcrEngine:
     """Returns an OcrEngine to use for processing this file.
 
     The OcrEngine may be instantiated multiple times, by both the main process
-    and child process. As such, it must be obtain store any state in ``options``
+    and child process.
-    or some common location.
 
     Note:
         This is a :ref:`firstresult hook<firstresult>`.
@@ -456,3 +466,60 @@ def generate_pdfa(
     See also:
         https://github.com/tqdm/tqdm
     """
+
+
+@hookspec(firstresult=True)
+def optimize_pdf(
+    input_pdf: Path,
+    output_pdf: Path,
+    context: PdfContext,
+    executor: Executor,
+    linearize: bool,
+) -> Tuple[Path, Sequence[str]]:
+    """Optimize a PDF after image, OCR and metadata processing.
+
+    If the input_pdf is a PDF/A, the plugin should modify input_pdf in a way
+    that preserves the PDF/A status, or report to the user when this is not possible.
+
+    If the implementation fails to produce a smaller file than the input file, it
+    should return input_pdf instead.
+
+    Arguments:
+        input_pdf: The input PDF, which has OCR added.
+        output_pdf: The requested filename of the output PDF which should be created
+            by this optimization hook.
+        context: The current context.
+        executor: An initialized executor which may be used during optimization,
+            to distribute optimization tasks.
+        linearize: If True, OCRmyPDF requires ``optimize_pdf`` to return a linearized,
+            also known as fast web view PDF.
+
+    Returns:
+        Path: If optimization is successful, the hook should return ``output_file``.
+            If optimization does not produce a smaller file, the hook should return
+            ``input_file``.
+        Sequence[str]: Any comments that the plugin wishes to report to the user,
+            especially reasons it was not able to further optimize the file. For
+            example, the plugin could report that a required third party was not
+            installed, so a specific optimization was not attempted.
+
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
+    """
+
+
+@hookspec(firstresult=True)
+def is_optimization_enabled(context: PdfContext) -> bool:
+    """For a given PdfContext, OCRmyPDF asks the plugin if optimization is enabled.
+
+    It is assumed that an optimization plugin might be installed but could be
+    disabled by user settings.
+
+    If this returns False, OCRmyPDF will take certain actions to finalize the PDF.
+
+    Returns:
+        True if the plugin's optimization is enabled.
+
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
+    """

src/ocrmypdf/subprocess/__init__.py

@@ -28,7 +28,12 @@ log = logging.getLogger(__name__)
 
 
 def run(
-    args, *, env=None, logs_errors_to_stdout: bool = False, **kwargs
+    args,
+    *,
+    env=None,
+    logs_errors_to_stdout: bool = False,
+    check: bool = False,
+    **kwargs,
 ) -> CompletedProcess:
     """Wrapper around :py:func:`subprocess.run`
 
@@ -50,7 +55,7 @@ def run(
     stderr = None
     stderr_name = 'stderr' if not logs_errors_to_stdout else 'stdout'
     try:
-        proc = subprocess_run(args, env=env, **kwargs)
+        proc = subprocess_run(args, env=env, check=check, **kwargs)
     except CalledProcessError as e:
         stderr = getattr(e, stderr_name, None)
         raise
@@ -111,6 +116,7 @@ def _fix_process_args(args, env, kwargs):
     program = str(args[0])
 
     if os.name == 'nt':
+        # pylint: disable=import-outside-toplevel
         from ocrmypdf.subprocess._windows import fix_windows_args
 
         args = fix_windows_args(program, args, env)
@@ -171,42 +177,42 @@ def get_version(
     return version
 
 
-missing_program = '''
+MISSING_PROGRAM = '''
 The program '{program}' could not be executed or was not found on your
 system PATH.
 '''
 
-missing_optional_program = '''
+MISSING_OPTIONAL_PROGRAM = '''
 The program '{program}' could not be executed or was not found on your
 system PATH.  This program is required when you use the
 {required_for} arguments.  You could try omitting these arguments, or install
 the package.
 '''
 
-missing_recommend_program = '''
+MISSING_RECOMMEND_PROGRAM = '''
 The program '{program}' could not be executed or was not found on your
 system PATH.  This program is recommended when using the {required_for} arguments,
 but not required, so we will proceed.  For best results, install the program.
 '''
 
-old_version = '''
+OLD_VERSION = '''
 OCRmyPDF requires '{program}' {need_version} or higher.  Your system appears
 to have {found_version}.  Please update this program.
 '''
 
-old_version_required_for = '''
+OLD_VERSION_REQUIRED_FOR = '''
 OCRmyPDF requires '{program}' {need_version} or higher when run with the
 {required_for} arguments.  If you omit these arguments, OCRmyPDF may be able to
 proceed.  For best results, install the program.
 '''
 
-osx_install_advice = '''
+OSX_INSTALL_ADVICE = '''
 If you have homebrew installed, try these command to install the missing
 package:
     brew install {package}
 '''
 
-linux_install_advice = '''
+LINUX_INSTALL_ADVICE = '''
 On systems with the aptitude package manager (Debian, Ubuntu), try these
 commands:
     sudo apt-get update
@@ -216,7 +222,7 @@ On RPM-based systems (Red Hat, Fedora), search for instructions on
 installing the RPM for {program}.
 '''
 
-windows_install_advice = '''
+WINDOWS_INSTALL_ADVICE = '''
 If not already installed, install the Chocolatey package manager. Then use
 a command prompt to install the missing package:
     choco install {package}
@@ -234,35 +240,47 @@ def _get_platform():
 
 
 def _error_trailer(program, package, **kwargs):
+    del kwargs
     if isinstance(package, Mapping):
         package = package.get(_get_platform(), program)
 
     if _get_platform() == 'darwin':
-        log.info(osx_install_advice.format(**locals()))
+        log.info(OSX_INSTALL_ADVICE.format(**locals()))
     elif _get_platform() == 'linux':
-        log.info(linux_install_advice.format(**locals()))
+        log.info(LINUX_INSTALL_ADVICE.format(**locals()))
     elif _get_platform() == 'windows':
-        log.info(windows_install_advice.format(**locals()))
+        log.info(WINDOWS_INSTALL_ADVICE.format(**locals()))
 
 
 def _error_missing_program(program, package, required_for, recommended):
+    # pylint: disable=unused-argument
     if recommended:
-        log.warning(missing_recommend_program.format(**locals()))
+        log.warning(MISSING_RECOMMEND_PROGRAM.format(**locals()))
     elif required_for:
-        log.error(missing_optional_program.format(**locals()))
+        log.error(MISSING_OPTIONAL_PROGRAM.format(**locals()))
     else:
-        log.error(missing_program.format(**locals()))
+        log.error(MISSING_PROGRAM.format(**locals()))
     _error_trailer(**locals())
 
 
 def _error_old_version(program, package, need_version, found_version, required_for):
+    # pylint: disable=unused-argument
     if required_for:
-        log.error(old_version_required_for.format(**locals()))
+        log.error(OLD_VERSION_REQUIRED_FOR.format(**locals()))
     else:
-        log.error(old_version.format(**locals()))
+        log.error(OLD_VERSION.format(**locals()))
     _error_trailer(**locals())
 
 
+def _remove_leading_v(s):
+    if sys.version_info >= (3, 9):
+        return s.removeprefix('v')
+
+    if s.startswith('v'):
+        return s[1:]
+    return s
+
+
 def check_external_program(
     *,
     program: str,
@@ -294,19 +312,19 @@ def check_external_program(
             found_version = version_checker()
         else:  # deprecated
             found_version = version_checker
-    except (CalledProcessError, FileNotFoundError, MissingDependencyError):
+    except (CalledProcessError, FileNotFoundError) as e:
         _error_missing_program(program, package, required_for, recommended)
         if not recommended:
-            raise MissingDependencyError(program)
+            raise MissingDependencyError(program) from e
+        return
+    except MissingDependencyError:
+        _error_missing_program(program, package, required_for, recommended)
+        if not recommended:
+            raise
         return
 
-    def remove_leading_v(s):
+    found_version = _remove_leading_v(found_version)
-        if s.startswith('v'):
+    need_version = _remove_leading_v(need_version)
-            return s[1:]
-        return s
-
-    found_version = remove_leading_v(found_version)
-    need_version = remove_leading_v(need_version)
 
     if found_version and version_parser(found_version) < version_parser(need_version):
         _error_old_version(program, package, need_version, found_version, required_for)

src/ocrmypdf/subprocess/_windows.py

@@ -4,6 +4,11 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+# type: ignore
+# Non-Windows mypy now breaks when trying to typecheck winreg
+
+"""Find Tesseract and Ghostscript binaries on Windows using the registry."""
+
 import logging
 import os
 import shutil
@@ -14,8 +19,8 @@ from typing import Any, Callable, Iterable, Iterator, Set, Tuple, TypeVar
 
 try:
     import winreg
-except ModuleNotFoundError as e:
+except ModuleNotFoundError as _notfound_ex:
-    raise ModuleNotFoundError("This module is for Windows only") from e
+    raise ModuleNotFoundError("This module is for Windows only") from _notfound_ex
 
 log = logging.getLogger(__name__)
 
@@ -36,15 +41,15 @@ def ghostscript_version_key(s: str) -> Tuple[int, int, int]:
 def registry_enum(
     key: winreg.HKEYType, enum_fn: Callable[[winreg.HKEYType, int], T]
 ) -> Iterator[T]:
-    LIMIT = 999
+    limit = 999
     n = 0
-    while n < LIMIT:
+    while n < limit:
         try:
             yield enum_fn(key, n)
             n += 1
         except OSError:
             break
-    if n == LIMIT:
+    if n == limit:
         raise ValueError(f"Too many registry keys under {key}")
 
 
@@ -57,6 +62,7 @@ def registry_values(key: winreg.HKEYType) -> Iterator[Tuple[str, Any, int]]:
 
 
 def registry_path_ghostscript(env=None) -> Iterator[Path]:
+    del env  # unused (but needed for protocol)
     try:
         with winreg.OpenKey(
             winreg.HKEY_LOCAL_MACHINE, r"SOFTWARE\Artifex\GPL Ghostscript"
@@ -74,6 +80,7 @@ def registry_path_ghostscript(env=None) -> Iterator[Path]:
 
 
 def registry_path_tesseract(env=None) -> Iterator[Path]:
+    del env  # unused (but needed for protocol)
     try:
         with winreg.OpenKey(winreg.HKEY_LOCAL_MACHINE, r"SOFTWARE\Tesseract-OCR") as k:
             for subkey, val, _valtype in registry_values(k):

tests/conftest.py

@@ -134,8 +134,7 @@ def run_ocrmypdf(
 
     p = run(
         p_args,
-        stdout=PIPE,
+        capture_output=True,
-        stderr=PIPE,
         text=text,
         check=False,
     )

tests/plugins/tesseract_cache.py

@@ -50,6 +50,7 @@ import logging
 import platform
 import re
 import shutil
+import threading
 from functools import partial
 from pathlib import Path
 from subprocess import PIPE, CalledProcessError, CompletedProcess
@@ -176,26 +177,40 @@ def cached_run(options, run_args, **run_kwargs):
 
 
 class CacheOcrEngine(TesseractOcrEngine):
+    # Concurrent threads (with --use-threads) might try to use different parts
+    # of the OcrEngine, so we need a lock to protect the state of patched
+    # module whenever it's patched. Should refactor ocrmypdf._exec.tesseract so that
+    # it does not to be patched at all for testing.
+    lock = threading.Lock()
+
     @staticmethod
     def get_orientation(input_file, options):
-        with patch('ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)):
+        with CacheOcrEngine.lock, patch(
+            'ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)
+        ):
             return TesseractOcrEngine.get_orientation(input_file, options)
 
     @staticmethod
     def get_deskew(input_file, options) -> float:
-        with patch('ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)):
+        with CacheOcrEngine.lock, patch(
+            'ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)
+        ):
             return TesseractOcrEngine.get_deskew(input_file, options)
 
     @staticmethod
     def generate_hocr(input_file, output_hocr, output_text, options):
-        with patch('ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)):
+        with CacheOcrEngine.lock, patch(
+            'ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)
+        ):
             TesseractOcrEngine.generate_hocr(
                 input_file, output_hocr, output_text, options
             )
 
     @staticmethod
     def generate_pdf(input_file, output_pdf, output_text, options):
-        with patch('ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)):
+        with CacheOcrEngine.lock, patch(
+            'ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)
+        ):
             TesseractOcrEngine.generate_pdf(
                 input_file, output_pdf, output_text, options
             )

tests/test_completion.py

@@ -24,8 +24,7 @@ def test_fish():
             ['fish', '-n', 'misc/completion/ocrmypdf.fish'],
             check=True,
             encoding='utf-8',
-            stdout=PIPE,
+            capture_output=True,
-            stderr=PIPE,
         )
         assert proc.stderr == '', proc.stderr
     except FileNotFoundError:
@@ -41,8 +40,7 @@ def test_bash():
             ['bash', '-n', 'misc/completion/ocrmypdf.bash'],
             check=True,
             encoding='utf-8',
-            stdout=PIPE,
+            capture_output=True,
-            stderr=PIPE,
         )
         assert proc.stderr == '', proc.stderr
     except FileNotFoundError:

tests/test_concurrency.py

@@ -13,6 +13,7 @@ from ocrmypdf import ExitCode
 from .conftest import run_ocrmypdf_api
 
 
+@pytest.mark.skipif(True, reason="--use-threads is currently default")
 @pytest.mark.skipif(os.name == 'nt', reason="Windows doesn't have SIGKILL")
 def test_simulate_oom_killer(resources, no_outpdf):
     exitcode = run_ocrmypdf_api(

tests/test_ghostscript.py

@@ -6,11 +6,13 @@
 
 
 import logging
+import subprocess
 from decimal import Decimal
+from unittest.mock import patch
 
 import pikepdf
 import pytest
-from PIL import Image
+from PIL import Image, UnidentifiedImageError
 
 from ocrmypdf._exec.ghostscript import rasterize_pdf
 from ocrmypdf.exceptions import ExitCode
@@ -124,3 +126,20 @@ def test_ghostscript_feature_elision(resources, outpdf):
         '--plugin',
         'tests/plugins/gs_feature_elision.py',
     )
+
+
+def test_rasterize_pdf_errors(resources, no_outpdf, caplog):
+    with patch('ocrmypdf._exec.ghostscript.run') as mock:
+        # ghostscript can produce
+        mock.return_value = subprocess.CompletedProcess(
+            ['fakegs'], returncode=0, stdout=b'', stderr=b'error this is an error'
+        )
+        with pytest.raises(UnidentifiedImageError):
+            rasterize_pdf(
+                resources / 'francais.pdf',
+                no_outpdf,
+                raster_device='pngmono',
+                raster_dpi=Resolution(100, 100),
+            )
+        assert "this is an error" in caplog.text
+        assert "invalid page image file" in caplog.text

tests/test_main.py

@@ -465,12 +465,18 @@ def test_overlay(resources, outpdf):
     )
 
 
-def test_destination_not_writable(resources, outdir):
+@pytest.fixture
-    if os.name != 'nt' and (os.getuid() == 0 or os.geteuid() == 0):
+def protected_file(outdir):
-        pytest.xfail(reason="root can write to anything")
     protected_file = outdir / 'protected.pdf'
     protected_file.touch()
     protected_file.chmod(0o400)  # Read-only
+    yield protected_file
+
+
+@pytest.mark.skipif(
+    os.name == 'nt' or os.geteuid() == 0, reason="root can write to anything"
+)
+def test_destination_not_writable(resources, protected_file):
     p = run_ocrmypdf(
         resources / 'jbig2.pdf',
         protected_file,
@@ -480,7 +486,8 @@ def test_destination_not_writable(resources, outdir):
     assert p.returncode == ExitCode.file_access_error, "Expected error"
 
 
-def test_tesseract_config_valid(resources, outdir):
+@pytest.fixture
+def valid_tess_config(outdir):
     cfg_file = outdir / 'test.cfg'
     with cfg_file.open('w') as f:
         f.write(
@@ -490,20 +497,22 @@ language_model_penalty_non_dict_word 0
 language_model_penalty_non_freq_dict_word 0
 '''
         )
+    yield cfg_file
 
+
+def test_tesseract_config_valid(resources, valid_tess_config, outpdf):
     check_ocrmypdf(
         resources / '3small.pdf',
-        outdir / 'out.pdf',
+        outpdf,
         '--tesseract-config',
-        cfg_file,
+        valid_tess_config,
         '--pages',
         '1',
     )
 
 
-@pytest.mark.slow  # This test sometimes times out in CI
+@pytest.fixture
-@pytest.mark.parametrize('renderer', RENDERERS)
+def invalid_tess_config(outdir):
-def test_tesseract_config_invalid(renderer, resources, outdir):
     cfg_file = outdir / 'test.cfg'
     with cfg_file.open('w') as f:
         f.write(
@@ -511,14 +520,19 @@ def test_tesseract_config_invalid(renderer, resources, outdir):
 THIS FILE IS INVALID
 '''
         )
+    yield cfg_file
 
+
+@pytest.mark.slow  # This test sometimes times out in CI
+@pytest.mark.parametrize('renderer', RENDERERS)
+def test_tesseract_config_invalid(renderer, resources, invalid_tess_config, outpdf):
     p = run_ocrmypdf(
         resources / 'ccitt.pdf',
-        outdir / 'out.pdf',
+        outpdf,
         '--pdf-renderer',
         renderer,
         '--tesseract-config',
-        cfg_file,
+        invalid_tess_config,
     )
     assert (
         "parameter not found" in p.stderr.lower()
@@ -630,8 +644,7 @@ def test_compression_preserved(ocrmypdf_exec, resources, image, outpdf):
         ]
         p = run(
             p_args,
-            stdout=PIPE,
+            capture_output=True,
-            stderr=PIPE,
             stdin=input_stream,
             text=True,
             check=False,
@@ -691,8 +704,7 @@ def test_compression_changed(ocrmypdf_exec, resources, image, compression, outpd
         ]
         p = run(
             p_args,
-            stdout=PIPE,
+            capture_output=True,
-            stderr=PIPE,
             stdin=input_stream,
             text=True,
             check=False,
@@ -803,6 +815,9 @@ def test_text_curves(resources, outpdf):
         info = PdfInfo(outpdf)
         assert len(info.pages[0].images) == 0, "added images to the vector PDF"
 
+
+def test_text_curves_force(resources, outpdf):
+    with patch('ocrmypdf._pipeline.VECTOR_PAGE_DPI', 100):
         check_ocrmypdf(
             resources / 'vector.pdf',
             outpdf,
@@ -924,3 +939,25 @@ def test_outputtype_none(resources, outtxt):
         'tests/plugins/tesseract_noop.py',
     )
     assert p.returncode == ExitCode.ok
+
+
+@pytest.fixture
+def graph_bad_icc(resources, outdir):
+    synth_input_file = outdir / 'graph-bad-icc.pdf'
+    with pikepdf.open(resources / 'graph.pdf') as pdf:
+        icc = pdf.make_stream(
+            b'invalid icc profile', N=3, Alternate=pikepdf.Name.DeviceRGB
+        )
+        pdf.pages[0].Resources.XObject['/Im0'].ColorSpace = pikepdf.Array(
+            [pikepdf.Name.ICCBased, icc]
+        )
+        pdf.save(synth_input_file)
+        yield synth_input_file
+
+
+def test_corrupt_icc(graph_bad_icc, outpdf, caplog):
+    result = run_ocrmypdf_api(graph_bad_icc, outpdf)
+    assert result == ExitCode.ok
+    assert any(
+        'corrupt or unreadable ICC profile' in rec.message for rec in caplog.records
+    )

tests/test_metadata.py

@@ -6,10 +6,9 @@
 
 
 import datetime
+import warnings
 from datetime import timezone
-from os import fspath
 from shutil import copyfile
-from unittest.mock import patch
 
 import pikepdf
 import pytest
@@ -17,7 +16,7 @@ from pikepdf.models.metadata import decode_pdf_date
 
 from ocrmypdf._jobcontext import PdfContext
 from ocrmypdf._pipeline import convert_to_pdfa, metadata_fixup
-from ocrmypdf._plugin_manager import get_plugin_manager
+from ocrmypdf._plugin_manager import get_parser_options_plugins, get_plugin_manager
 from ocrmypdf.cli import get_parser
 from ocrmypdf.exceptions import ExitCode
 from ocrmypdf.pdfa import file_claims_pdfa, generate_pdfa_ps
@@ -173,6 +172,19 @@ def test_creation_date_preserved(output_type, resources, infile, outpdf):
     assert seconds_between_dates(date_after, datetime.datetime.now(timezone.utc)) < 1000
 
 
+@pytest.fixture
+def libxmp_file_to_dict():
+    try:
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", DeprecationWarning)
+            from libxmp.utils import (
+                file_to_dict,  # pylint: disable=import-outside-toplevel
+            )
+    except Exception:  # pylint: disable=broad-except
+        pytest.skip("libxmp not available or libexempi3 not installed")
+    return file_to_dict
+
+
 @pytest.mark.parametrize(
     'test_file,output_type',
     [
@@ -182,15 +194,12 @@ def test_creation_date_preserved(output_type, resources, infile, outpdf):
         ('3small.pdf', 'pdfa'),
     ],
 )
-def test_xml_metadata_preserved(test_file, output_type, resources, outpdf):
+def test_xml_metadata_preserved(
+    libxmp_file_to_dict, test_file, output_type, resources, outpdf
+):
     input_file = resources / test_file
 
-    try:
+    before = libxmp_file_to_dict(str(input_file))
-        from libxmp.utils import file_to_dict  # pylint: disable=import-outside-toplevel
-    except Exception:  # pylint: disable=broad-except
-        pytest.skip("libxmp not available or libexempi3 not installed")
-
-    before = file_to_dict(str(input_file))
 
     check_ocrmypdf(
         input_file,
@@ -202,7 +211,7 @@ def test_xml_metadata_preserved(test_file, output_type, resources, outpdf):
         'tests/plugins/tesseract_noop.py',
     )
 
-    after = file_to_dict(str(outpdf))
+    after = libxmp_file_to_dict(str(outpdf))
 
     equal_properties = [
         'dc:contributor',
@@ -290,8 +299,8 @@ def test_kodak_toc(resources, outpdf):
 
 
 def test_metadata_fixup_warning(resources, outdir, caplog):
-    options = get_parser().parse_args(
+    _parser, options, _pm = get_parser_options_plugins(
-        args=['--output-type', 'pdfa-2', 'graph.pdf', 'out.pdf']
+        ['--output-type', 'pdfa-2', 'graph.pdf', 'out.pdf']
     )
 
     copyfile(resources / 'graph.pdf', outdir / 'graph.pdf')
@@ -316,6 +325,9 @@ def test_metadata_fixup_warning(resources, outdir, caplog):
     assert any(record.levelname == 'WARNING' for record in caplog.records)
 
 
+XMP_MAGIC = b'W5M0MpCehiHzreSzNTczkc9d'
+
+
 def test_prevent_gs_invalid_xml(resources, outdir):
     generate_pdfa_ps(outdir / 'pdfa.ps')
     copyfile(resources / 'trivial.pdf', outdir / 'layers.rendered.pdf')
@@ -342,7 +354,7 @@ def test_prevent_gs_invalid_xml(resources, outdir):
     contents = (outdir / 'pdfa.pdf').read_bytes()
     # Since the XML may be invalid, we scan instead of actually feeding it
     # to a parser.
-    XMP_MAGIC = b'W5M0MpCehiHzreSzNTczkc9d'
+
     xmp_start = contents.find(XMP_MAGIC)
     xmp_end = contents.rfind(b'<?xpacket end', xmp_start)
     assert 0 < xmp_start < xmp_end

tests/test_optimize.py

@@ -17,7 +17,7 @@ from PIL import Image, ImageDraw
 from ocrmypdf import optimize as opt
 from ocrmypdf._exec import jbig2enc, pngquant
 from ocrmypdf._exec.ghostscript import rasterize_pdf
-from ocrmypdf.helpers import Resolution
+from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution
 
 from .conftest import check_ocrmypdf
 
@@ -81,7 +81,7 @@ def test_jbig2_lossy(lossy, resources, outpdf):
         '--image-dpi',
         '200',
         '--optimize',
-        3,
+        '3',
         '--jpg-quality',
         '50',
         '--png-quality',
@@ -139,8 +139,8 @@ def test_multiple_pngs(resources, outdir):
         img2pdf.convert(
             fspath(resources / 'baiona_colormapped.png'),
             fspath(resources / 'baiona_gray.png'),
-            with_pdfrw=False,
             outputstream=inpdf,
+            **IMG2PDF_KWARGS,
         )
 
     def mockquant(input_file, output_file, *_args):

tests/test_pdfa.py

@@ -4,23 +4,31 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+import os
+
 import pikepdf
 import pytest
 
+from ocrmypdf.exceptions import MissingDependencyError
+
 from .conftest import check_ocrmypdf
 
 
 @pytest.mark.parametrize('optimize', (0, 3))
 @pytest.mark.parametrize('pdfa_level', (1, 2, 3))
 def test_pdfa(resources, outpdf, optimize, pdfa_level):
-    check_ocrmypdf(
+    try:
-        resources / 'francais.pdf',
+        check_ocrmypdf(
-        outpdf,
+            resources / 'francais.pdf',
-        '--plugin',
+            outpdf,
-        'tests/plugins/tesseract_noop.py',
+            '--plugin',
-        f'--output-type=pdfa-{pdfa_level}',
+            'tests/plugins/tesseract_noop.py',
-        f'--optimize={optimize}',
+            f'--output-type=pdfa-{pdfa_level}',
-    )
+            f'--optimize={optimize}',
+        )
+    except MissingDependencyError as e:
+        if 'pngquant' in str(e) and optimize in (2, 3) and os.name == 'nt':
+            pytest.xfail("pngquant currently not available on Windows")
     if pdfa_level in (2, 3):
         # PDF/A-2 allows ObjStm
         assert b'/ObjStm' in outpdf.read_bytes()

tests/test_pdfinfo.py

@@ -17,7 +17,7 @@ from reportlab.pdfgen.canvas import Canvas
 
 from ocrmypdf import pdfinfo
 from ocrmypdf.exceptions import InputFileError
-from ocrmypdf.helpers import Resolution
+from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution
 from ocrmypdf.pdfinfo import Colorspace, Encoding
 from ocrmypdf.pdfinfo.layout import PDFPage
 
@@ -67,9 +67,9 @@ def test_single_page_image(eight_by_eight, outpdf):
         img2pdf.convert(
             bio,
             producer="img2pdf",
-            with_pdfrw=False,
             layout_fun=layout_fun,
             outputstream=f,
+            **IMG2PDF_KWARGS,
         )
     info = pdfinfo.PdfInfo(outpdf)
 
@@ -173,17 +173,15 @@ def test_stack_abuse():
     p = pikepdf.Pdf.new()
 
     stream = pikepdf.Stream(p, b'q ' * 35)
-    with pytest.warns(None) as record:
+    with pytest.warns(UserWarning, match="overflowed"):
         pdfinfo.info._interpret_contents(stream)
-    assert 'overflowed' in str(record[0].message)
 
     stream = pikepdf.Stream(p, b'q Q Q Q Q')
-    with pytest.warns(None) as record:
+    with pytest.warns(UserWarning, match="underflowed") as record:
         pdfinfo.info._interpret_contents(stream)
-    assert 'underflowed' in str(record[0].message)
 
     stream = pikepdf.Stream(p, b'q ' * 135)
-    with pytest.warns(None):
+    with pytest.warns(UserWarning):
         with pytest.raises(RuntimeError):
             pdfinfo.info._interpret_contents(stream)
 

tests/test_rotation.py

@@ -18,13 +18,19 @@ from reportlab.pdfgen.canvas import Canvas
 
 from ocrmypdf._exec import ghostscript
 from ocrmypdf._plugin_manager import get_plugin_manager
-from ocrmypdf.helpers import Resolution
+from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution
 from ocrmypdf.pdfinfo import PdfInfo
 
 from .conftest import check_ocrmypdf, run_ocrmypdf
 
 # pylintx: disable=unused-variable
 
+# Remove this workaround when we require Pillow >= 10
+try:
+    Transpose = Image.Transpose  # type: ignore
+except AttributeError:
+    # Pillow 9 shim
+    Transpose = Image  # type: ignore
 
 RENDERERS = ['hocr', 'sandwich']
 
@@ -222,7 +228,7 @@ def test_rotate_page_level(image_angle, page_angle, resources, outdir):
         with Image.open(fspath(resources / 'typewriter.png')) as im:
             if image_angle != 0:
                 ccw_angle = -image_angle % 360
-                im = im.transpose(getattr(Image, f'ROTATE_{ccw_angle}'))
+                im = im.transpose(getattr(Transpose, f'ROTATE_{ccw_angle}'))
             im.save(memimg, format='PNG')
         memimg.seek(0)
         mempdf = BytesIO()
@@ -230,6 +236,7 @@ def test_rotate_page_level(image_angle, page_angle, resources, outdir):
             memimg.read(),
             layout_fun=img2pdf.get_fixed_dpi_layout_fun((200, 200)),
             outputstream=mempdf,
+            **IMG2PDF_KWARGS,
         )
         mempdf.seek(0)
         pike = pikepdf.open(mempdf)

tests/test_stdio.py

@@ -30,12 +30,12 @@ def test_stdin(ocrmypdf_exec, resources, outpdf):
             '--plugin',
             'tests/plugins/tesseract_noop.py',
         ]
-        run(p_args, stdout=PIPE, stderr=PIPE, stdin=input_stream, check=True)
+        run(p_args, capture_output=True, stdin=input_stream, check=True)
 
 
 def test_stdout(ocrmypdf_exec, resources, outpdf):
     if 'COV_CORE_DATAFILE' in os.environ:
-        pytest.skip(msg="Coverage uses stdout")
+        pytest.skip("Coverage uses stdout")
 
     input_file = str(resources / 'francais.pdf')
     output_file = str(outpdf)
@@ -53,26 +53,13 @@ def test_stdout(ocrmypdf_exec, resources, outpdf):
     assert check_pdf(output_file)
 
 
-@pytest.mark.skipif(sys.version_info >= (3, 7, 0), reason='better utf-8')
-@pytest.mark.skipif(
-    Path('/etc/alpine-release').exists(), reason="invalid test on alpine"
-)
-@pytest.mark.skipif(os.name == 'nt', reason="invalid test on Windows")
-def test_bad_locale(monkeypatch):
-    monkeypatch.setenv('LC_ALL', 'C')
-    p = run_ocrmypdf('a', 'b')
-    assert p.stdout == '', "stdout not clean"
-    assert p.returncode != 0
-    assert 'configured to use ASCII as encoding' in p.stderr, "should whine"
-
-
 @pytest.mark.xfail(
     os.name == 'nt' and sys.version_info < (3, 8),
     reason="Windows does not like this; not sure how to fix",
 )
 def test_dev_null(resources):
     if 'COV_CORE_DATAFILE' in os.environ:
-        pytest.skip(msg="Coverage uses stdout")
+        pytest.skip("Coverage uses stdout")
 
     p = run_ocrmypdf(
         resources / 'trivial.pdf',

tests/test_unpaper.py

@@ -5,19 +5,24 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+import logging
 from os import fspath
 from unittest.mock import patch
 
 import pytest
+from PIL import Image
 
+from ocrmypdf._exec import unpaper
 from ocrmypdf._plugin_manager import get_parser_options_plugins
 from ocrmypdf._validation import check_options
 from ocrmypdf.exceptions import ExitCode, MissingDependencyError
 
-from .conftest import check_ocrmypdf, have_unpaper, run_ocrmypdf
+from .conftest import check_ocrmypdf, have_unpaper, ocrmypdf_exec, run_ocrmypdf
 
 # pylint: disable=redefined-outer-name
 
+needs_unpaper = pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+
 
 def test_no_unpaper(resources, no_outpdf):
     input_ = fspath(resources / "c02-22.pdf")
@@ -45,7 +50,7 @@ def test_old_unpaper(resources, no_outpdf):
         mock.assert_called()
 
 
-@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+@needs_unpaper
 def test_clean(resources, outpdf):
     check_ocrmypdf(
         resources / "skew.pdf",
@@ -56,7 +61,7 @@ def test_clean(resources, outpdf):
     )
 
 
-@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+@needs_unpaper
 def test_unpaper_args_valid(resources, outpdf):
     check_ocrmypdf(
         resources / "skew.pdf",
@@ -69,7 +74,7 @@ def test_unpaper_args_valid(resources, outpdf):
     )
 
 
-@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+@needs_unpaper
 def test_unpaper_args_invalid_filename(resources, outpdf):
     p = run_ocrmypdf(
         resources / "skew.pdf",
@@ -84,7 +89,7 @@ def test_unpaper_args_invalid_filename(resources, outpdf):
     assert p.returncode == ExitCode.bad_args
 
 
-@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+@needs_unpaper
 def test_unpaper_args_invalid(resources, outpdf):
     p = run_ocrmypdf(
         resources / "skew.pdf",
@@ -98,3 +103,16 @@ def test_unpaper_args_invalid(resources, outpdf):
     # Can't tell difference between unpaper choking on bad arguments or some
     # other unpaper failure
     assert p.returncode == ExitCode.child_process_error
+
+
+@needs_unpaper
+def test_unpaper_image_too_big(resources, outdir, caplog):
+    with patch('ocrmypdf._exec.unpaper.UNPAPER_IMAGE_PIXEL_LIMIT', 42):
+        infile = resources / 'crom.png'
+        unpaper.clean(infile, outdir / 'out.png', dpi=300) == infile
+
+        assert any(
+            'too large for cleaning' in rec.message
+            for rec in caplog.get_records('call')
+            if rec.levelno == logging.WARNING
+        )

tests/test_validation.py

@@ -92,9 +92,9 @@ def test_mutex_options():
 
 
 def test_optimizing(caplog):
-    vd.check_options_optimizing(
+    opts = make_opts(optimize=0, jbig2_lossy=True, png_quality=18, jpeg_quality=10)
-        make_opts(optimize=0, jbig2_lossy=True, png_quality=18, jpeg_quality=10)
+    plugin_manager = get_plugin_manager(opts.plugins)
-    )
+    vd._check_options(opts, plugin_manager, set())
     assert 'will be ignored because' in caplog.text
 
 
@@ -145,22 +145,16 @@ def test_report_file_size(tmp_path, caplog):
     pdf.Root.Dummy2 = waste_of_space + waste_of_space
     pdf.save(out)
 
-    with patch('ocrmypdf._validation.jbig2enc.available', return_value=True), patch(
+    vd.report_output_file_size(opts, in_, out, ['The optional dependency...'])
-        'ocrmypdf._validation.pngquant.available', return_value=True
+    assert 'optional dependency' in caplog.text
-    ):
-        vd.report_output_file_size(opts, in_, out)
-        assert 'No reason' in caplog.text
     caplog.clear()
 
-    with patch('ocrmypdf._validation.jbig2enc.available', return_value=False), patch(
+    vd.report_output_file_size(opts, in_, out, [])
-        'ocrmypdf._validation.pngquant.available', return_value=True
+    assert 'No reason' in caplog.text
-    ):
-        vd.report_output_file_size(opts, in_, out)
-        assert 'optional dependency' in caplog.text
     caplog.clear()
 
     opts = make_opts(in_, out, optimize=0, output_type='pdf')
-    vd.report_output_file_size(opts, in_, out)
+    vd.report_output_file_size(opts, in_, out, ["Optimization was disabled."])
     assert 'disabled' in caplog.text
     caplog.clear()