tests: simplify run_ocrmypdf API

setup.cfg

@@ -55,7 +55,6 @@ install_requires =
     tqdm>=4
     importlib-metadata>=4;python_version<'3.8'  # until Python 3.8
     importlib-resources>=5;python_version<'3.9'  # until Python 3.9
-    typing-extensions;python_version<'3.8'  # until Python 3.8
 python_requires = >=3.7
 include_package_data = True
 package_dir =

tests/conftest.py

@@ -10,7 +10,7 @@ import platform
 import sys
 from pathlib import Path
 from subprocess import PIPE, CompletedProcess, run
-from typing import AnyStr, List, Tuple, overload
+from typing import List
 
 import pytest
 
@@ -19,11 +19,6 @@ from ocrmypdf._exec import unpaper
 from ocrmypdf._plugin_manager import get_parser_options_plugins
 from ocrmypdf.exceptions import ExitCode
 
-try:
-    from typing import Literal
-except ImportError:
-    from typing_extensions import Literal
-
 
 def is_linux():
     return platform.system() == 'Linux'
@@ -122,21 +117,9 @@ def run_ocrmypdf_api(input_file: Path, output_file: Path, *args) -> ExitCode:
     return api.run_pipeline(options, plugin_manager=None, api=False)
 
 
-@overload
 def run_ocrmypdf(
-    input_file: Path, output_file: Path, *args, text: Literal[True] = True
-) -> Tuple[CompletedProcess, str, str]:
-    ...
-
-
-@overload
-def run_ocrmypdf(
-    input_file: Path, output_file: Path, *args, text: Literal[False]
-) -> Tuple[CompletedProcess, bytes, bytes]:
-    ...
-
-
-def run_ocrmypdf(input_file: Path, output_file: Path, *args, text: bool = True):
+    input_file: Path, output_file: Path, *args, text: bool = True
+) -> CompletedProcess:
     """Run ocrmypdf in a subprocess and let test deal with results.
 
     If an exception is thrown this fact will be returned as part of the result
@@ -157,7 +140,7 @@ def run_ocrmypdf(input_file: Path, output_file: Path, *args, text: bool = True):
         check=False,
     )
     # print(p.stderr)
-    return p, p.stdout, p.stderr
+    return p
 
 
 def first_page_dimensions(pdf: Path):

tests/test_ghostscript.py

@@ -76,7 +76,7 @@ def test_rasterize_rotated(francais, outdir, caplog):
 
 
 def test_gs_render_failure(resources, outpdf):
-    p, _out, err = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / 'blank.pdf',
         outpdf,
         '--plugin',
@@ -84,12 +84,12 @@ def test_gs_render_failure(resources, outpdf):
         '--plugin',
         'tests/plugins/gs_render_failure.py',
     )
-    assert 'Casper is not a friendly ghost' in err
+    assert 'Casper is not a friendly ghost' in p.stderr
     assert p.returncode == ExitCode.child_process_error
 
 
 def test_gs_raster_failure(resources, outpdf):
-    p, _out, err = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / 'francais.pdf',
         outpdf,
         '--plugin',
@@ -97,12 +97,12 @@ def test_gs_raster_failure(resources, outpdf):
         '--plugin',
         'tests/plugins/gs_raster_failure.py',
     )
-    assert 'Ghost story archive not found' in err
+    assert 'Ghost story archive not found' in p.stderr
     assert p.returncode == ExitCode.child_process_error
 
 
 def test_ghostscript_pdfa_failure(resources, outpdf):
-    p, _out, _err = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / 'francais.pdf',
         outpdf,
         '--plugin',

tests/test_main.py

@@ -203,7 +203,7 @@ def test_force_ocr_on_pdf_with_no_images(resources, no_outpdf):
     # As a correctness test, make sure that --force-ocr on a PDF with no
     # content still triggers tesseract. If tesseract crashes, then it was
     # called.
-    p, _, _ = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / 'blank.pdf',
         no_outpdf,
         '--force-ocr',
@@ -241,7 +241,7 @@ def test_german(resources, outdir):
 
 
 def test_klingon(resources, outpdf):
-    p, _, _ = run_ocrmypdf(resources / 'francais.pdf', outpdf, '-l', 'klz')
+    p = run_ocrmypdf(resources / 'francais.pdf', outpdf, '-l', 'klz')
     assert p.returncode == ExitCode.missing_dependency
 
 
@@ -354,7 +354,7 @@ def test_tesseract_thresholding_invalid(value, resources, no_outpdf):
 
 @pytest.mark.parametrize('renderer', RENDERERS)
 def test_tesseract_crash(renderer, resources, no_outpdf):
-    p, _, err = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / 'ccitt.pdf',
         no_outpdf,
         '-v',
@@ -366,11 +366,11 @@ def test_tesseract_crash(renderer, resources, no_outpdf):
     )
     assert p.returncode == ExitCode.child_process_error
     assert not no_outpdf.exists()
-    assert "SubprocessOutputError" in err
+    assert "SubprocessOutputError" in p.stderr
 
 
 def test_tesseract_crash_autorotate(resources, no_outpdf):
-    p, out, err = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / 'ccitt.pdf',
         no_outpdf,
         '-r',
@@ -379,9 +379,9 @@ def test_tesseract_crash_autorotate(resources, no_outpdf):
     )
     assert p.returncode == ExitCode.child_process_error
     assert not no_outpdf.exists()
-    assert "uncaught exception" in err
-    print(out)
-    print(err)
+    assert "uncaught exception" in p.stderr
+    print(p.stdout)
+    print(p.stderr)
 
 
 @pytest.mark.parametrize('renderer', RENDERERS)
@@ -401,7 +401,7 @@ def test_tesseract_image_too_big(renderer, resources, outpdf):
 
 
 def test_algo4(resources, outpdf):
-    p, _, _ = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / 'encrypted_algo4.pdf',
         outpdf,
         '--plugin',
@@ -471,7 +471,7 @@ def test_destination_not_writable(resources, outdir):
     protected_file = outdir / 'protected.pdf'
     protected_file.touch()
     protected_file.chmod(0o400)  # Read-only
-    p, _out, _err = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / 'jbig2.pdf',
         protected_file,
         '--plugin',
@@ -512,7 +512,7 @@ THIS FILE IS INVALID
 '''
         )
 
-    p, _out, err = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / 'ccitt.pdf',
         outdir / 'out.pdf',
         '--pdf-renderer',
@@ -521,8 +521,8 @@ THIS FILE IS INVALID
         cfg_file,
     )
     assert (
-        "parameter not found" in err.lower()
-        or "error occurred while parsing" in err.lower()
+        "parameter not found" in p.stderr.lower()
+        or "error occurred while parsing" in p.stderr.lower()
     ), "No error message"
     assert p.returncode == ExitCode.invalid_config
 
@@ -781,15 +781,13 @@ def test_pdfa_n(pdfa_level, resources, outpdf):
 
 
 def test_decompression_bomb_error(resources, outpdf):
-    p, _out, err = run_ocrmypdf(resources / 'hugemono.pdf', outpdf)
-    assert 'decompression bomb' in err and '--max-image-mpixels' in err
+    p = run_ocrmypdf(resources / 'hugemono.pdf', outpdf)
+    assert 'decompression bomb' in p.stderr and '--max-image-mpixels' in p.stderr
 
 
 @pytest.mark.slow
 def test_decompression_bomb_succeeds(resources, outpdf):
-    p, _out, err = run_ocrmypdf(
-        resources / 'hugemono.pdf', outpdf, '--max-image-mpixels', '2000'
-    )
+    p = run_ocrmypdf(resources / 'hugemono.pdf', outpdf, '--max-image-mpixels', '2000')
     assert p.returncode == 0
 
 
@@ -818,7 +816,7 @@ def test_text_curves(resources, outpdf):
 
 
 def test_output_is_dir(resources, outdir):
-    p, _out, err = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / 'trivial.pdf',
         outdir,
         '--force-ocr',
@@ -826,28 +824,28 @@ def test_output_is_dir(resources, outdir):
         'tests/plugins/tesseract_noop.py',
     )
     assert p.returncode == ExitCode.file_access_error
-    assert 'is not a writable file' in err
+    assert 'is not a writable file' in p.stderr
 
 
 @pytest.mark.skipif(os.name == 'nt', reason="symlink needs admin permissions")
 def test_output_is_symlink(resources, outdir):
     sym = Path(outdir / 'this_is_a_symlink')
     sym.symlink_to(outdir / 'out.pdf')
-    p, _out, err = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / 'trivial.pdf',
         sym,
         '--force-ocr',
         '--plugin',
         'tests/plugins/tesseract_noop.py',
     )
-    assert p.returncode == ExitCode.ok, err
+    assert p.returncode == ExitCode.ok, p.stderr
     assert (outdir / 'out.pdf').stat().st_size > 0, 'target file not created'
 
 
 def test_livecycle(resources, no_outpdf):
-    p, _, err = run_ocrmypdf(resources / 'livecycle.pdf', no_outpdf)
+    p = run_ocrmypdf(resources / 'livecycle.pdf', no_outpdf)
 
-    assert p.returncode == ExitCode.input_file, err
+    assert p.returncode == ExitCode.input_file, p.stderr
 
 
 def test_version_check():
@@ -904,7 +902,7 @@ def test_image_dpi_not_image(caplog, resources, outpdf):
 
 
 def test_outputtype_none_bad_setup(resources, outpdf):
-    p, _out, err = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / 'trivial.pdf',
         outpdf,
         '--output-type=none',
@@ -912,11 +910,11 @@ def test_outputtype_none_bad_setup(resources, outpdf):
         'tests/plugins/tesseract_noop.py',
     )
     assert p.returncode == ExitCode.bad_args
-    assert 'Set the output file to' in err
+    assert 'Set the output file to' in p.stderr
 
 
 def test_outputtype_none(resources, outtxt):
-    p, out, err = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / 'trivial.pdf',
         '-',
         '--output-type=none',

tests/test_metadata.py

@@ -62,7 +62,7 @@ def test_override_metadata(output_type, resources, outpdf):
     german = 'Du siehst den Wald vor lauter Bäumen nicht.'
     chinese = '孔子'
 
-    p, _out, err = run_ocrmypdf(
+    p = run_ocrmypdf(
         input_file,
         outpdf,
         '--title',
@@ -75,7 +75,7 @@ def test_override_metadata(output_type, resources, outpdf):
         'tests/plugins/tesseract_noop.py',
     )
 
-    assert p.returncode == ExitCode.ok, err
+    assert p.returncode == ExitCode.ok, p.stderr
 
     before = pikepdf.open(input_file)
     after = pikepdf.open(outpdf)
@@ -99,7 +99,7 @@ def test_high_unicode(resources, no_outpdf):
     input_file = resources / 'c02-22.pdf'
     high_unicode = 'U+1030C is: 𐌌'
 
-    p, _out, err = run_ocrmypdf(
+    p = run_ocrmypdf(
         input_file,
         no_outpdf,
         '--subject',
@@ -110,7 +110,7 @@ def test_high_unicode(resources, no_outpdf):
         'tests/plugins/tesseract_noop.py',
     )
 
-    assert p.returncode == ExitCode.bad_args, err
+    assert p.returncode == ExitCode.bad_args, p.stderr
 
 
 @pytest.mark.skipif(not fitz, reason="test uses fitz")

tests/test_rotation.py

@@ -242,7 +242,7 @@ def test_rotate_page_level(image_angle, page_angle, resources, outdir):
     test = make_rotate_test('test', image_angle, page_angle)
     out = test.with_suffix('.out.pdf')
 
-    p, _, err = run_ocrmypdf(
+    p = run_ocrmypdf(
         test,
         out,
         '-O0',
@@ -251,7 +251,7 @@ def test_rotate_page_level(image_angle, page_angle, resources, outdir):
         '0.001',
         text=False,
     )
-    err = err.decode('utf-8', errors='replace')
+    err = p.stderr.decode('utf-8', errors='replace')
     assert p.returncode == 0, err
 
     assert compare_images_monochrome(outdir, reference, 1, out, 1) > 0.2

tests/test_stdio.py

@@ -60,10 +60,10 @@ def test_stdout(ocrmypdf_exec, resources, outpdf):
 @pytest.mark.skipif(os.name == 'nt', reason="invalid test on Windows")
 def test_bad_locale(monkeypatch):
     monkeypatch.setenv('LC_ALL', 'C')
-    p, out, err = run_ocrmypdf('a', 'b')
-    assert out == '', "stdout not clean"
+    p = run_ocrmypdf('a', 'b')
+    assert p.stdout == '', "stdout not clean"
     assert p.returncode != 0
-    assert 'configured to use ASCII as encoding' in err, "should whine"
+    assert 'configured to use ASCII as encoding' in p.stderr, "should whine"
 
 
 @pytest.mark.xfail(
@@ -74,7 +74,7 @@ def test_dev_null(resources):
     if 'COV_CORE_DATAFILE' in os.environ:
         pytest.skip(msg="Coverage uses stdout")
 
-    p, out, _err = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / 'trivial.pdf',
         os.devnull,
         '--force-ocr',
@@ -82,4 +82,4 @@ def test_dev_null(resources):
         'tests/plugins/tesseract_noop.py',
     )
     assert p.returncode == 0, "could not send output to /dev/null"
-    assert len(out) == 0, "wrote to stdout"
+    assert len(p.stdout) == 0, "wrote to stdout"

tests/test_unpaper.py

@@ -71,7 +71,7 @@ def test_unpaper_args_valid(resources, outpdf):
 
 @pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
 def test_unpaper_args_invalid_filename(resources, outpdf):
-    p, _out, err = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / "skew.pdf",
         outpdf,
         "-c",
@@ -80,13 +80,13 @@ def test_unpaper_args_invalid_filename(resources, outpdf):
         '--plugin',
         'tests/plugins/tesseract_noop.py',
     )
-    assert "No filenames allowed" in err
+    assert "No filenames allowed" in p.stderr
     assert p.returncode == ExitCode.bad_args
 
 
 @pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
 def test_unpaper_args_invalid(resources, outpdf):
-    p, _out, _err = run_ocrmypdf(
+    p = run_ocrmypdf(
         resources / "skew.pdf",
         outpdf,
         "-c",