From e3126d28068b39cff2b21e669e96517cdf4a2e6d Mon Sep 17 00:00:00 2001 From: "James R. Barlow" Date: Sat, 13 Nov 2021 01:16:35 -0800 Subject: [PATCH] Adjust test to support Tesseract 5 working harder to find its files --- src/ocrmypdf/_exec/tesseract.py | 2 +- src/ocrmypdf/subprocess/__init__.py | 4 ++-- tests/test_main.py | 3 +++ 3 files changed, 6 insertions(+), 3 deletions(-) diff --git a/src/ocrmypdf/_exec/tesseract.py b/src/ocrmypdf/_exec/tesseract.py index 6dc7f0d0..a3688f65 100644 --- a/src/ocrmypdf/_exec/tesseract.py +++ b/src/ocrmypdf/_exec/tesseract.py @@ -74,7 +74,7 @@ class TesseractVersion(StrictVersion): super().parse(vstring + '-0') -def version(): +def version() -> str: return get_version('tesseract', regex=r'tesseract\s(.+)') diff --git a/src/ocrmypdf/subprocess/__init__.py b/src/ocrmypdf/subprocess/__init__.py index ffe8cc38..ed336d4b 100644 --- a/src/ocrmypdf/subprocess/__init__.py +++ b/src/ocrmypdf/subprocess/__init__.py @@ -124,7 +124,7 @@ def _fix_process_args(args, env, kwargs): @lru_cache(maxsize=None) def get_version( program: str, *, version_arg: str = '--version', regex=r'(\d+(\.\d+)*)', env=None -): +) -> str: """Get the version of the specified program Arguments: @@ -145,7 +145,7 @@ def get_version( check=True, env=env, ) - output = proc.stdout + output: str = proc.stdout except FileNotFoundError as e: raise MissingDependencyError( f"Could not find program '{program}' on the PATH" diff --git a/tests/test_main.py b/tests/test_main.py index a86875d9..26c93050 100644 --- a/tests/test_main.py +++ b/tests/test_main.py @@ -180,6 +180,9 @@ def test_maximum_options(renderer, output_type, resources, outpdf): ) +@pytest.mark.skipif( + tesseract.version() >= '5', reason="tess 5 tries harder to find its files" +) def test_tesseract_missing_tessdata(monkeypatch, resources, no_outpdf, tmpdir): monkeypatch.setenv("TESSDATA_PREFIX", os.fspath(tmpdir)) with pytest.raises(MissingDependencyError):