Fix proper extraction of tesseract version

Author: int3l

pytesseract/pytesseract.py

@@ -21,6 +21,7 @@
 from tempfile import NamedTemporaryFile
 from time import sleep
 
+from packaging.version import InvalidVersion
 from packaging.version import parse
 from packaging.version import Version
 from PIL import Image
@@ -387,13 +388,14 @@ def get_tesseract_version():
         raise TesseractNotFoundError()
 
     raw_version = output.decode(DEFAULT_ENCODING)
-    strip_version = raw_version.lstrip(string.printable[10:])
+    str_version, *_ = raw_version.lstrip(string.printable[10:]).partition(' ')
+    str_version, *_ = str_version.partition('-')
 
     try:
-        version = parse(strip_version)
-        assert version > TESSERACT_MIN_VERSION
-    except AttributeError:
-        raise SystemExit(f'Invalid tesseract version: "{strip_version}"')
+        version = parse(str_version)
+        assert version >= TESSERACT_MIN_VERSION
+    except (AssertionError, InvalidVersion):
+        raise SystemExit(f'Invalid tesseract version: "{raw_version}"')
 
     return version
 

tests/pytesseract_test.py

@@ -448,14 +448,14 @@ def test_file_to_dict(input_args, expected):
     ('tesseract_version', 'expected'),
     (
         (b'3.5.0', '3.5.0'),
-        (b'4.1-a8s6f8d3f', '4.1-a8s6f8d3f'),
-        (b'v4.0.0-beta1.9', '4.0.0-beta1.9'),
+        (b'4.1-a8s6f8d3f', '4.1'),
+        (b'v4.0.0-beta1.9', '4.0.0'),
     ),
 )
 def test_get_tesseract_version(tesseract_version, expected):
     with mock.patch('subprocess.check_output', spec=True) as output_mock:
         output_mock.return_value = tesseract_version
-        assert get_tesseract_version.__wrapped__() == expected
+        assert get_tesseract_version.__wrapped__().public == expected
 
 
 @pytest.mark.parametrize(