tests/avocado: Allow newer versions of tesseract in the nextcube test

Current Linux distros ship version 5 of the tesseract OCR software,
so the nextcube screen test is ignored there. Let's make the check
more flexible to allow newer versions, too, and remove the old v3
test since most Linux distros don't ship this version anymore.

Message-ID: <20231101204323.35533-1-huth@tuxfamily.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Thomas Huth <huth@tuxfamily.org>
This commit is contained in:
Thomas Huth 2023-11-01 21:43:22 +01:00 committed by Thomas Huth
parent e416fd79d5
commit 645198d58b
2 changed files with 5 additions and 14 deletions

View File

@ -55,25 +55,16 @@ class NextCubeMachine(QemuSystemTest):
self.assertEqual(width, 1120)
self.assertEqual(height, 832)
@skipUnless(tesseract_available(3), 'tesseract v3 OCR tool not available')
def test_bootrom_framebuffer_ocr_with_tesseract_v3(self):
screenshot_path = os.path.join(self.workdir, "dump.ppm")
self.check_bootrom_framebuffer(screenshot_path)
lines = tesseract_ocr(screenshot_path, tesseract_version=3)
text = '\n'.join(lines)
self.assertIn('Backplane', text)
self.assertIn('Ethernet address', text)
# Tesseract 4 adds a new OCR engine based on LSTM neural networks. The
# new version is faster and more accurate than version 3. The drawback is
# that it is still alpha-level software.
@skipUnless(tesseract_available(4), 'tesseract v4 OCR tool not available')
def test_bootrom_framebuffer_ocr_with_tesseract_v4(self):
@skipUnless(tesseract_available(4), 'tesseract OCR tool not available')
def test_bootrom_framebuffer_ocr_with_tesseract(self):
screenshot_path = os.path.join(self.workdir, "dump.ppm")
self.check_bootrom_framebuffer(screenshot_path)
lines = tesseract_ocr(screenshot_path, tesseract_version=4)
text = '\n'.join(lines)
self.assertIn('Testing the FPU, SCC', text)
self.assertIn('Testing the FPU', text)
self.assertIn('System test failed. Error code', text)
self.assertIn('Boot command', text)
self.assertIn('Next>', text)

View File

@ -21,13 +21,13 @@ def tesseract_available(expected_version):
version = res.stdout_text.split()[1]
except IndexError:
version = res.stderr_text.split()[1]
return int(version.split('.')[0]) == expected_version
return int(version.split('.')[0]) >= expected_version
match = re.match(r'tesseract\s(\d)', res)
if match is None:
return False
# now this is guaranteed to be a digit
return int(match.groups()[0]) == expected_version
return int(match.groups()[0]) >= expected_version
def tesseract_ocr(image_path, tesseract_args='', tesseract_version=3):