v12.3.3 release notes

Closes #821

.github/workflows/build.yml

@@ -18,8 +18,20 @@ jobs:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ubuntu-18.04] #, ubuntu-20.04]
+        include:
-        python: ["3.6"] #, "3.7", "3.8", "3.9"]
+          - os: ubuntu-18.04
+            python: 3.6
+          - os: ubuntu-18.04
+            python: 3.7
+          - os: ubuntu-20.04
+            python: 3.8
+          - os: ubuntu-20.04
+            python: 3.9
+          - os: ubuntu-latest
+            python: 3.9
+          - os: ubuntu-latest
+            python: 3.9
+            tesseract5: true
 
     env:
       OS: ${{ matrix.os }}
@@ -35,6 +47,11 @@ jobs:
         with:
           python-version: ${{ matrix.python }}
 
+      - name: Install Tesseract 5
+        if: matrix.tesseract5
+        run: |
+          sudo add-apt-repository ppa:alex-p/tesseract-ocr-devel
+
       - name: Install common packages
         run: |
           sudo apt-get update

README.md

@@ -91,6 +91,11 @@ brew install tesseract-lang
 
 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.
 
+OCRmyPDF supports Tesseract 4.0 and the beta versions of Tesseract 5.0. It will
+automatically use whichever version it finds first on the `PATH` environment
+variable. On Windows, if `PATH` does not provide a Tesseract binary, we use
+the highest version number that is installed according to the Windows Registry.
+
 ## Documentation and support
 
 Once OCRmyPDF is installed, the built-in help which explains the command syntax and options can be accessed via:
@@ -115,7 +120,7 @@ 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/)  
+- [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/jbig2.rst

@@ -9,11 +9,11 @@ encoding was patented for a long time. All known JBIG2 US patents have
 expired as of 2017, but it is possible that unknown patents exist.
 
 JBIG2 encoding is recommended for OCRmyPDF and is used to losslessly
-create smaller PDFs. If JBIG2 encoding not available, lower quality
+create smaller PDFs. If JBIG2 encoding is not available, lower quality
 encodings will be used.
 
 JBIG2 decoding is not patented and is performed automatically by most
-PDF viewers. It is widely supported has been part of the PDF
+PDF viewers. It is widely supported and has been part of the PDF
 specification since 2001.
 
 On macOS, Homebrew packages jbig2enc and OCRmyPDF includes it by
@@ -37,7 +37,7 @@ Lossy mode JBIG2
 
 OCRmyPDF provides lossy mode JBIG2 as an advanced feature. Users should
 `review the technical concerns with JBIG2 in lossy
-mode <https://abbyy.technology/en:kb:tip:jbig2_compression_and_ocr>`__
+mode <https://en.wikipedia.org/wiki/JBIG2#Disadvantages>`__
 and decide if this feature is acceptable for their use case.
 
 JBIG2 lossy mode does achieve higher compression ratios than any other

docs/release_notes.rst

@@ -12,6 +12,13 @@ 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.
 
+v12.3.3
+=======
+
+-  watcher.py: fixed interpretation of boolean env vars (:issue:`821`).
+-  Adjust CI scripts to test Tesseract 5 betas.
+-  Document our support for the Tesseract 5 betas.
+
 v12.3.2
 =======
 

misc/watcher.py

@@ -37,14 +37,19 @@ import ocrmypdf
 
 # pylint: disable=logging-format-interpolation
 
+
+def getenv_bool(name: str, default: str = 'False'):
+    return os.getenv(name, default).lower() in ('true', 'yes', 'y', '1')
+
+
 INPUT_DIRECTORY = os.getenv('OCR_INPUT_DIRECTORY', '/input')
 OUTPUT_DIRECTORY = os.getenv('OCR_OUTPUT_DIRECTORY', '/output')
-OUTPUT_DIRECTORY_YEAR_MONTH = bool(os.getenv('OCR_OUTPUT_DIRECTORY_YEAR_MONTH', ''))
+OUTPUT_DIRECTORY_YEAR_MONTH = getenv_bool('OCR_OUTPUT_DIRECTORY_YEAR_MONTH')
-ON_SUCCESS_DELETE = bool(os.getenv('OCR_ON_SUCCESS_DELETE', ''))
+ON_SUCCESS_DELETE = getenv_bool('OCR_ON_SUCCESS_DELETE')
-DESKEW = bool(os.getenv('OCR_DESKEW', ''))
+DESKEW = getenv_bool('OCR_DESKEW')
 OCR_JSON_SETTINGS = json.loads(os.getenv('OCR_JSON_SETTINGS', '{}'))
 POLL_NEW_FILE_SECONDS = int(os.getenv('OCR_POLL_NEW_FILE_SECONDS', '1'))
-USE_POLLING = bool(os.getenv('OCR_USE_POLLING', ''))
+USE_POLLING = getenv_bool('OCR_USE_POLLING')
 LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO')
 PATTERNS = ['*.pdf', '*.PDF']
 

pyproject.toml

@@ -34,3 +34,41 @@ exclude = '''
   | src/ocrmypdf/lib/_leptonica.py
 )/
 '''
+
+[tool.coverage.run]
+branch = true
+parallel = true
+concurrency = ["multiprocessing"]
+
+[tool.coverage.paths]
+source = ["src/ocrmypdf"]
+
+[tool.coverage.report]
+# Regexes for lines to exclude from consideration
+exclude_lines = [
+    # Have to re-enable the standard pragma
+    "pragma: no cover",
+
+    # Don't complain if tests don't hit defensive assertion code:
+    "raise AssertionError",
+    "raise NotImplementedError",
+
+    # Don't complain if non-runnable code isn't run:
+    "if 0:",
+	  "if False:",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:"
+]
+
+[tool.isort]
+profile = "black"
+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"]
+
+[tool.pytest.ini_options]
+minversion = "6.0"
+norecursedirs = ["lib", ".pc", ".git", "venv", "output", "cache", "resources"]
+testpaths = ["tests"]
+addopts = "-n auto"
+markers = ["slow"]
+filterwarnings = ["ignore:.*XMLParser.*:DeprecationWarning"]

setup.cfg

@@ -72,6 +72,7 @@ where = src
 
 [options.extras_require]
 test =
+    coverage[toml] >= 5
     pytest >= 6.0.0
     pytest-xdist >= 2.2.0
     pytest-cov >= 2.11.1
@@ -101,47 +102,3 @@ test = pytest
 [check-manifest]
 ignore =
 	.github
-
-[tool:pytest]
-norecursedirs = lib .pc .git output cache resources
-testpaths = tests
-filterwarnings =
-	ignore:.*XMLParser.*:DeprecationWarning
-markers =
-	slow
-addopts =
-	-n auto
-
-[isort]
-multi_line_output = 3
-include_trailing_comma = True
-force_grid_wrap = 0
-use_parentheses = True
-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
-
-[coverage:paths]
-source =
-	src/ocrmypdf
-
-[coverage:run]
-branch = true
-parallel = true
-concurrency = multiprocessing
-
-[coverage:report]
-# Regexes for lines to exclude from consideration
-exclude_lines =
-    # Have to re-enable the standard pragma
-    pragma: no cover
-
-    # Don't complain if tests don't hit defensive assertion code:
-    raise AssertionError
-    raise NotImplementedError
-
-    # Don't complain if non-runnable code isn't run:
-    if 0:
-	if False:
-    if __name__ == .__main__.:
-	if TYPE_CHECKING: