v13.4.4 release notes

Thanks @QuLogic

.docker/Dockerfile

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

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/release_notes.rst

@@ -18,6 +18,20 @@ tagged yet.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+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
 =======
 

setup.cfg

@@ -49,7 +49,7 @@ install_requires =
     coloredlogs>=14.0  # strictly optional
     img2pdf>=0.3.0,<0.5  # pure Python
     packaging>=20
-    pdfminer.six!=20200720,>=20191110,<=20220319
+    pdfminer.six!=20200720,>=20191110,<=20220506
     pikepdf!=5.0.0,>=4.0.0
     pluggy>=0.13.0,<2
     reportlab>=3.5.66

tests/plugins/tesseract_cache.py

@@ -50,11 +50,11 @@ import logging
 import platform
 import re
 import shutil
+import threading
 from functools import partial
 from pathlib import Path
 from subprocess import PIPE, CalledProcessError, CompletedProcess
 from unittest.mock import patch
-import threading
 
 from ocrmypdf import hookimpl
 from ocrmypdf.builtin_plugins.tesseract_ocr import TesseractOcrEngine
@@ -177,28 +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 CacheOcrEngine.lock, patch('ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)):
-                return TesseractOcrEngine.get_orientation(input_file, 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 CacheOcrEngine.lock, 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 CacheOcrEngine.lock, 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 CacheOcrEngine.lock, 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_metadata.py

@@ -188,7 +188,7 @@ def test_xml_metadata_preserved(test_file, output_type, resources, outpdf):
     try:
         from libxmp.utils import file_to_dict  # pylint: disable=import-outside-toplevel
     except Exception:  # pylint: disable=broad-except
-        pytest.skip(reason="libxmp not available or libexempi3 not installed")
+        pytest.skip("libxmp not available or libexempi3 not installed")
 
     before = file_to_dict(str(input_file))
 

tests/test_pdfinfo.py

@@ -181,7 +181,7 @@ def test_stack_abuse():
         pdfinfo.info._interpret_contents(stream)
 
     stream = pikepdf.Stream(p, b'q ' * 135)
-    with pytest.warns():
+    with pytest.warns(UserWarning):
         with pytest.raises(RuntimeError):
             pdfinfo.info._interpret_contents(stream)
 

tests/test_stdio.py

@@ -35,7 +35,7 @@ def test_stdin(ocrmypdf_exec, resources, outpdf):
 
 def test_stdout(ocrmypdf_exec, resources, outpdf):
     if 'COV_CORE_DATAFILE' in os.environ:
-        pytest.skip(reason="Coverage uses stdout")
+        pytest.skip("Coverage uses stdout")
 
     input_file = str(resources / 'francais.pdf')
     output_file = str(outpdf)
@@ -72,7 +72,7 @@ def test_bad_locale(monkeypatch):
 )
 def test_dev_null(resources):
     if 'COV_CORE_DATAFILE' in os.environ:
-        pytest.skip(reason="Coverage uses stdout")
+        pytest.skip("Coverage uses stdout")
 
     p = run_ocrmypdf(
         resources / 'trivial.pdf',