diff --git a/tests/resources/crom.png b/tests/resources/crom.png new file mode 100644 index 00000000..8ce51f0e Binary files /dev/null and b/tests/resources/crom.png differ diff --git a/tests/test_main.py b/tests/test_main.py index 8193a1a8..79a54002 100644 --- a/tests/test_main.py +++ b/tests/test_main.py @@ -786,6 +786,32 @@ THIS FILE IS INVALID assert p.returncode == ExitCode.invalid_config +def test_user_words(resources, outdir): + word_list = outdir / 'wordlist.txt' + sidecar_before = outdir / 'sidecar_before.txt' + sidecar_after = outdir / 'sidecar_after.txt' + + check_ocrmypdf( + resources / 'crom.png', outdir / 'out.pdf', + '--image-dpi', 150, + '--sidecar', sidecar_before + ) + + assert 'cromulent' not in sidecar_before.open().read() + + with word_list.open('w') as f: + f.write('cromulent\n') # a perfectly cromulent word + + check_ocrmypdf( + resources / 'crom.png', outdir / 'out.pdf', + '--image-dpi', 150, + '--sidecar', sidecar_after, + '--user-words', word_list + ) + + assert 'cromulent' in sidecar_after.open().read() + + def test_form_xobject(spoof_tesseract_noop, resources, outpdf): check_ocrmypdf(resources / 'formxobject.pdf', outpdf, '--force-ocr',