v12.1.0 release notes

Remove .yml since RTD considers it deprecated.

.docker/Dockerfile

@@ -37,12 +37,7 @@ COPY . /app
 
 WORKDIR /app
 
-RUN pip3 install --no-cache-dir \
+RUN pip3 install --no-cache-dir .[test,webservice,watcher]
-  -r requirements/main.txt \
-  -r requirements/webservice.txt \
-  -r requirements/test.txt \
-  -r requirements/watcher.txt \
-  .
 
 FROM base
 

.github/ISSUE_TEMPLATE/3-feature_request.md

@@ -14,7 +14,14 @@ A clear and concise description of what the problem is. Ex. I'm always frustrate
 A clear and concise description of what you want to happen.
 
 **Describe alternatives you've considered**
-A clear and concise description of any alternative solutions or features you've considered.
+A clear and concise description of any alternative solutions or features you've considered. Please include the versions of OCRmyPDF and other supporting programs (Tesseract OCR, Ghostscript) - maybe an alternative already exists in a newer version.
+
+**Example file**
+If your issue concerns how OCRmyPDF processes certain files, and please provide an example file that helps illustrate how OCRmyPDF's output could be improve.
+
+Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/jbarlow83/OCRmyPDF/wiki) for OCRmyPDF's author only.
+
+Links to files hosted elsewhere are perfectly acceptable. You could also look in ``tests/resources`` and see if any of those files reproduce your issue.
 
 **Additional context**
 Add any other context or screenshots about the feature request here.

.github/workflows/build.yml

@@ -67,7 +67,7 @@ jobs:
 
       - name: Install Python packages
         run: |
-          python -m pip install -r requirements/main.txt -r requirements/test.txt .
+          python -m pip install .[test]
 
       - name: Report versions
         run: |
@@ -124,7 +124,7 @@ jobs:
       - name: Install Python packages
         run: |
           python -m pip install --upgrade pip
-          python -m pip install -r requirements/main.txt -r requirements/test.txt .
+          python -m pip install .[test]
 
       - name: Report versions
         run: |
@@ -174,7 +174,7 @@ jobs:
       - name: Install Python packages
         run: |
           python -m pip install --upgrade pip
-          python -m pip install -r requirements/main.txt -r requirements/test.txt .
+          python -m pip install .[test]
 
       - name: Test
         run: |

.gitignore

@@ -6,8 +6,9 @@
 !.gitattributes
 !.gitignore
 !.pre-commit-config.yaml
-!.readthedocs.yml
+!.readthedocs.yaml
 !.github/
+!.docker/
 
 # Dev scratch
 *.ipynb

.readthedocs.yaml

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

.readthedocs.yml

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

README.md

@@ -57,7 +57,7 @@ I searched the web for a free command line tool to OCR PDF files: I found many,
 
 ## Installation
 
-Linux, Windows, macOS and FreeBSD are supported. Docker images are also available.
+Linux, Windows, macOS and FreeBSD are supported. Docker images are also available, for both x64 and ARM.
 
 | Operating system              | Install command               |
 | ----------------------------- | ------------------------------|
@@ -115,6 +115,7 @@ In addition to the required Python version (3.6+), OCRmyPDF requires external pr
 - [heise Open Source, 09/2014: Texterkennung mit OCRmyPDF](https://heise.de/-2356670)
 - [heise Durchsuchbare PDF-Dokumente mit OCRmyPDF erstellen](https://www.heise.de/ratgeber/Durchsuchbare-PDF-Dokumente-mit-OCRmyPDF-erstellen-4607592.html)
 - [Excellent Utilities: OCRmyPDF](https://www.linuxlinks.com/excellent-utilities-ocrmypdf-add-ocr-text-layer-scanned-pdfs/)
+- [LinuxUser Texterkennung mit OCRmyPDF und Scanbd automatisieren](https://www.linux-community.de/ausgaben/linuxuser/2021/06/texterkennung-mit-ocrmypdf-und-scanbd-automatisieren/)  
 
 ## Business enquiries
 

docs/advanced.rst

@@ -228,8 +228,8 @@ preprocessing is specified, then the image layer is a new PDF.
 Unlike ``sandwich`` this renderer is implemented within OCRmyPDF; anyone
 looking to customize how OCR is presented should look here. A major
 disadvantage of this renderer is it not capable of correctly handling
-text outside the Latin alphabet. Pull requests to improve the situation
+text outside the Latin alphabet (specifically, it supports the ISO 8859-1
-are welcome.
+character). Pull requests to improve the situation are welcome.
 
 Currently, this renderer has the best compatibility with Mozilla's
 PDF.js viewer.

docs/batch.rst

@@ -111,7 +111,7 @@ Users may need to customize the script to meet their requirements.
 
 .. code-block:: bash
 
-    pip3 install -r requirements/watcher.txt
+    pip3 install ocrmypdf[watcher]
 
     env OCR_INPUT_DIRECTORY=/mnt/input-pdfs \
         OCR_OUTPUT_DIRECTORY=/mnt/output-pdfs \

docs/installation.rst

@@ -812,8 +812,7 @@ To install all of the development and test requirements:
     python3 -m venv
     source venv/bin/activate
     cd OCRmyPDF
-    pip install -e .
+    pip install -e .[test]
-    pip install -r requirements/dev.txt -r requirements/test.txt
 
 To add JBIG2 encoding, see :ref:`jbig2`.
 

docs/introduction.rst

@@ -139,7 +139,7 @@ Limitations
 OCRmyPDF is limited by the Tesseract OCR engine. As such it experiences
 these limitations, as do any other programs that rely on Tesseract:
 
--  The OCR is not as accurate as commercial solutions such as Abbyy.
+-  The OCR is not as accurate as commercial OCR solutions.
 -  It is not capable of recognizing handwriting.
 -  It may find gibberish and report this as OCR output.
 -  If a document contains languages outside of those given in the

docs/pdfsecurity.rst

@@ -128,8 +128,9 @@ Commercial alternatives
 The author also provides professional services that include OCR and
 building databases around PDFs, and is happy to provide consultation.
 
-Abbyy Cloud OCR is a viable commercial alternative with a web services
+Abbyy Cloud OCR is viable commercial alternative with a web services
-API.
+API. Amazon Textract, Google Cloud Vision, and Microsoft Azure 
+Computer Vision provide advanced OCR but have less PDF rendering capability.
 
 Password protection, digital signatures and certification
 =========================================================

docs/release_notes.rst

@@ -12,6 +12,25 @@ 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.
 
+v12.1.0
+=======
+
+-  For security reasons we now require Pillow >= 8.2.x. (Older versions will continue
+   to work if upgrading is not an option.)
+-  The build system was reorganized to rely on ``setup.cfg`` instead of ``setup.py``.
+   All changes should work with previously supported versions of setuptools.
+-  The files in ``requirements/*`` are now considered deprecated but will be retained for v12.
+   Instead use ``pip install ocrmypdf[test]`` instead of ``requirements/test.txt``, etc.
+   These files will be removed in v13.
+
+v12.0.3
+=======
+
+-  Expand the list of languages supported by the hocr PDF renderer.
+   Several languages were previously considered not supported, particularly those
+   non-European languages that use the Latin alphabet.
+-  Fixed a case where the exception stack trace was suppressed in verbose mode.
+-  Improved documentation around commercial OCR.
 
 v12.0.2
 =======
@@ -19,7 +38,7 @@ v12.0.2
 -  Fix exception thrown when using ``--remove-background`` on files containing small
    images (#769).
 -  Improve documentation for description of adding language packs to the Docker image
-   and corrected name of French language pack.  
+   and corrected name of French language pack.
 
 v12.0.1
 =======

pyproject.toml

@@ -3,11 +3,14 @@ requires = [
   "setuptools >= 30.3.0",
   "wheel",
   "cffi",
-  "setuptools_scm",
+  "setuptools_scm[toml] >= 3.4",
   "setuptools_scm_git_archive"
 ]
 build-backend = "setuptools.build_meta"
 
+[tool.setuptools_scm]
+version_scheme = "post-release"
+
 [tool.black]
 line-length = 88
 target-version = ["py36", "py37", "py38"]

requirements/main.txt

@@ -1,12 +1,10 @@
-# requirements.txt can be used to replicate the developer's build environment
+# Deprecated and not maintained; use "pip install ocrmypdf" instead
-# setup.py lists a separate set of requirements that are looser to simplify
-# installation
 cffi == 1.14.5
 coloredlogs == 15.0  # technically optional
 img2pdf == 0.4.0
 pdfminer.six == 20201018
 pikepdf == 2.10.0
 pluggy == 0.13.1
-Pillow == 8.1.2
+Pillow == 8.2.0
 reportlab == 3.5.66
 tqdm == 4.59.0

requirements/test.txt

@@ -1,3 +1,4 @@
+# Deprecated and not maintained; use "pip install ocrmypdf[test]" instead
 pytest >= 6.0.0
 pytest-xdist >= 2.2.0
 pytest-cov >= 2.11.1

requirements/watcher.txt

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

requirements/webservice.txt

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

setup.cfg

@@ -1,8 +1,101 @@
+[metadata]
+name = ocrmypdf
+description = OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
+long_description = file: README.md
+long_description_content_type = text/markdown; charset=UTF-8
+url = https://github.com/jbarlow83/OCRmyPDF
+author = James R. Barlow
+author_email = james@purplerock.ca
+license_files = 
+    LICENSE
+keywords =
+    PDF
+    OCR
+    optical character recognition
+    PDF/A
+    scanning
+classifiers =
+    Programming Language :: Python :: 3.6
+    Programming Language :: Python :: 3.7
+    Programming Language :: Python :: 3.8
+    Programming Language :: Python :: 3.9
+    Development Status :: 5 - Production/Stable
+    Environment :: Console
+    Intended Audience :: End Users/Desktop
+    Intended Audience :: Science/Research
+    Intended Audience :: System Administrators
+    License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
+    Operating System :: MacOS :: MacOS X
+    Operating System :: Microsoft :: Windows :: Windows 10
+    Operating System :: POSIX
+    Operating System :: POSIX :: BSD
+    Operating System :: POSIX :: Linux
+    Topic :: Scientific/Engineering :: Image Recognition
+    Topic :: Text Processing :: Indexing
+    Topic :: Text Processing :: Linguistic
+project_urls =
+    Documentation = https://ocrmypdf.readthedocs.io/
+    Source = https://github.com/jbarlow83/ocrmypdf
+    Tracker = https://github.com/jbarlow83/ocrmypdf/issues
+
+[options]
+zip_safe = False
+packages = find:
+package_dir =
+    =src
+platforms = any
+include_package_data=True
+install_requires =
+    cffi >= 1.9.1  # must be a setup and install requirement
+    coloredlogs >= 14.0  # strictly optional
+    img2pdf >= 0.3.0, < 0.5  # pure Python, so track HEAD closely
+    pdfminer.six >= 20191110, != 20200720, <= 20201018
+    pikepdf >= 2.10.0
+    Pillow >= 8.2.0
+    pluggy >= 0.13.0, < 1.0
+    reportlab >= 3.5.66
+    setuptools
+    tqdm >= 4
+python_requires = >= 3.6
+setup_requires =  # can be removed whenever we can drop pip 9 support
+    cffi >= 1.9.1  # to build the leptonica module
+    setuptools_scm  # so that version will work
+    setuptools_scm_git_archive  # enable version from github tarballs
+
+[options.package_data]
+ocrmypdf =
+    data/sRGB.icc
+    py.typed
+
+[options.packages.find]
+where = src
+
+[options.extras_require]
+test =
+    pytest >= 6.0.0
+    pytest-xdist >= 2.2.0
+    pytest-cov >= 2.11.1
+    python-xmp-toolkit == 2.0.1  # also requires apt-get install libexempi3
+                                 # or brew install exempi
+docs =
+    sphinx
+    sphinx_rtd_theme    
+extended_test =
+    PyMuPDF == 1.13.4
+watcher =
+    watchdog >= 1.0.2, < 2
+webservice =
+    Flask >= 1, < 2
+
+[options.entry_points]
+console_scripts =
+    ocrmypdf = ocrmypdf.__main__:run
+
 [bdist_wheel]
 python-tag = py36
 
 [aliases]
-test=pytest
+test = pytest
 
 [check-manifest]
 ignore =
@@ -19,17 +112,14 @@ addopts =
 	-n auto
 
 [isort]
-multi_line_output=3
+multi_line_output = 3
-include_trailing_comma=True
+include_trailing_comma = True
-force_grid_wrap=0
+force_grid_wrap = 0
-use_parentheses=True
+use_parentheses = True
-line_length=88
+line_length = 88
 known_first_party = ocrmypdf
 known_third_party = PIL,_cffi_backend,cffi,flask,img2pdf,pdfminer,pikepdf,pkg_resources,pluggy,pytest,reportlab,setuptools,sphinx_rtd_theme,tqdm,watchdog,werkzeug
 
-[metadata]
-license_file = LICENSE
-
 [coverage:paths]
 source =
 	src/ocrmypdf

setup.py

@@ -1,62 +1,16 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
-# © 2015 James R. Barlow: github.com/jbarlow83
+# © 2021 James R. Barlow: github.com/jbarlow83
 #
 # This Source Code Form is subject to the terms of the Mozilla Public
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
-from __future__ import print_function, unicode_literals
+from setuptools import setup
-
-import sys
-
-from setuptools import find_packages, setup
-
-if sys.version_info < (3, 6):
-    print("Python 3.6 or newer is required", file=sys.stderr)
-    sys.exit(1)
-
-tests_require = open('requirements/test.txt', encoding='utf-8').read().splitlines()
-
-
-def readme():
-    with open('README.md', encoding='utf-8') as f:
-        return f.read()
-
 
+# Minimal setup to support older setuptools/setuptools_scm
 setup(
-    name='ocrmypdf',
-    description='OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched',
-    long_description=readme(),
-    long_description_content_type='text/markdown',
-    url='https://github.com/jbarlow83/OCRmyPDF',
-    author='James R. Barlow',
-    author_email='james@purplerock.ca',
-    packages=find_packages('src', exclude=["tests", "tests.*"]),
-    package_dir={'': 'src'},
-    keywords=['PDF', 'OCR', 'optical character recognition', 'PDF/A', 'scanning'],
-    classifiers=[
-        "Programming Language :: Python :: 3.6",
-        "Programming Language :: Python :: 3.7",
-        "Programming Language :: Python :: 3.8",
-        "Programming Language :: Python :: 3.9",
-        "Development Status :: 5 - Production/Stable",
-        "Environment :: Console",
-        "Intended Audience :: End Users/Desktop",
-        "Intended Audience :: Science/Research",
-        "Intended Audience :: System Administrators",
-        "License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)",
-        "Operating System :: MacOS :: MacOS X",
-        "Operating System :: Microsoft :: Windows :: Windows 10",
-        "Operating System :: POSIX",
-        "Operating System :: POSIX :: BSD",
-        "Operating System :: POSIX :: Linux",
-        "Topic :: Scientific/Engineering :: Image Recognition",
-        "Topic :: Text Processing :: Indexing",
-        "Topic :: Text Processing :: Linguistic",
-    ],
-    python_requires=' >= 3.6',
     setup_requires=[  # can be removed whenever we can drop pip 9 support
         'cffi >= 1.9.1',  # to build the leptonica module
         'setuptools_scm',  # so that version will work
@@ -64,26 +18,4 @@ setup(
     ],
     use_scm_version={'version_scheme': 'post-release'},
     cffi_modules=['src/ocrmypdf/lib/compile_leptonica.py:ffibuilder'],
-    install_requires=[
-        'cffi >= 1.9.1',  # must be a setup and install requirement
-        'coloredlogs >= 14.0',  # strictly optional
-        'img2pdf >= 0.3.0, < 0.5',  # pure Python, so track HEAD closely
-        'pdfminer.six >= 20191110, != 20200720, <= 20201018',
-        "pikepdf >= 2.10.0",
-        'Pillow >= 8.1.2',
-        'pluggy >= 0.13.0, < 1.0',
-        'reportlab >= 3.5.66',
-        'setuptools',
-        'tqdm >= 4',
-    ],
-    tests_require=tests_require,
-    entry_points={'console_scripts': ['ocrmypdf = ocrmypdf.__main__:run']},
-    package_data={'ocrmypdf': ['data/sRGB.icc', 'py.typed']},
-    include_package_data=True,
-    zip_safe=False,
-    project_urls={
-        'Documentation': 'https://ocrmypdf.readthedocs.io/',
-        'Source': 'https://github.com/jbarlow83/ocrmypdf',
-        'Tracker': 'https://github.com/jbarlow83/ocrmypdf/issues',
-    },
 )

src/ocrmypdf/RELEASE.md

@@ -28,7 +28,7 @@
 
 - Search for deprecation: search all files for deprec*, etc.
 
-- Check requirements/*
+- Check requirements in setup.cfg
 
 - Delete `tests/cache`, do `pytest --runslow`, and update cache.
 

src/ocrmypdf/_sync.py

@@ -406,7 +406,9 @@ def run_pipeline(options, *, plugin_manager, api=False):
             log.error("KeyboardInterrupt")
         return ExitCode.ctrl_c
     except (ExitCodeException if not api else NeverRaise) as e:
-        if str(e):
+        if options.verbose >= 1:
+            log.exception("ExitCodeException")
+        elif str(e):
             log.error("%s: %s", type(e).__name__, str(e))
         else:
             log.error(type(e).__name__)

src/ocrmypdf/_validation.py

@@ -32,12 +32,12 @@ from ocrmypdf.helpers import (
     monotonic,
     safe_symlink,
 )
+from ocrmypdf.hocrtransform import HOCR_OK_LANGS
 from ocrmypdf.subprocess import check_external_program
 
 # -------------
 # External dependencies
 
-HOCR_OK_LANGS = frozenset(['eng', 'deu', 'spa', 'ita', 'por'])
 DEFAULT_LANGUAGE = 'eng'  # Enforce English hegemony
 
 log = logging.getLogger(__name__)
@@ -279,7 +279,7 @@ def check_closed_streams(options):  # pragma: no cover
     Attempting to a fork/exec a new Python process when any of std{in,out,err}
     are closed or not flushable for some reason may raise an exception.
     Fix this by opening devnull if the handle seems to be closed.  Do this
-    globally to avoid tracking places all places that fork.
+    globally to avoid tracking all places that fork.
 
     Seems to be specific to multiprocessing.Process not all Python process
     forkers.

src/ocrmypdf/hocrtransform.py

@@ -41,6 +41,62 @@ from reportlab.lib.colors import black, cyan, magenta, red
 from reportlab.lib.units import inch
 from reportlab.pdfgen.canvas import Canvas
 
+# According to Wikipedia these languages are supported in the ISO-8859-1 character
+# set, meaning reportlab can generate them and they are compatible with hocr,
+# assuming Tesseract has the necessary languages installed. Note that there may
+# not be language packs for them.
+HOCR_OK_LANGS = frozenset(
+    [
+        # Languages fully covered by Latin-1:
+        'afr',  # Afrikaans
+        'alb',  # Albanian
+        'ast',  # Leonese
+        'baq',  # Basque
+        'bre',  # Breton
+        'cos',  # Corsican
+        'eng',  # English
+        'eus',  # Basque
+        'fao',  # Faoese
+        'gla',  # Scottish Gaelic
+        'glg',  # Galician
+        'glv',  # Manx
+        'ice',  # Icelandic
+        'ind',  # Indonesian
+        'isl',  # Icelandic
+        'ita',  # Italian
+        'ltz',  # Luxembourgish
+        'mal',  # Malay Rumi
+        'mga',  # Irish
+        'nor',  # Norwegian
+        'oci',  # Occitan
+        'por',  # Portugeuse
+        'roh',  # Romansh
+        'sco',  # Scots
+        'sma',  # Sami
+        'spa',  # Spanish
+        'sqi',  # Albanian
+        'swa',  # Swahili
+        'swe',  # Swedish
+        'tgl',  # Tagalog
+        'wln',  # Walloon
+        # Languages supported by Latin-1 except for a few rare characters that OCR
+        # is probably not trained to recognize anyway:
+        'cat',  # Catalan
+        'cym',  # Welsh
+        'dan',  # Danish
+        'deu',  # German
+        'dut',  # Dutch
+        'est',  # Estonian
+        'fin',  # Finnish
+        'fra',  # French
+        'hun',  # Hungarian
+        'kur',  # Kurdish
+        'nld',  # Dutch
+        'wel',  # Welsh
+    ]
+)
+
+
 Element = ElementTree.Element