def test_extract_data(self):
translator = GoogleTranslator()
# Check the keys with invalid input
basic_dictionary = {
"translation": "",
"original_text": "",
"romanization": "",
"src_lang": "",
"match": 1.0,
"has_typo": False,
"extra": {}
}
self.assertEqual(translator._extract_data(1234), basic_dictionary)
# Check with valid input
inputs = [
[[["T1", "o1", "", "", 0], ["", "", "r1", "R2"]], "", "fr"],
[[["t1", "O1", "", "", 0], ["", "", "r1"]], "", "en"],
[[["t1", "o1", "", "", 0]], ["extra"], "en", "", "", "", 0.5,
["", "", "", "", "", True]],
[[["t1", "o1", "", "", 0]],
[[
"nouns", ["w1", "w2"],
[["w1", ["t1", "t2"], "", 0.44], ["w2", ["t3", "t4"]]], "ooo",
1
],
[
"adjectives", ["a1"], [["a1", ["t1", "t5"], "", 0.05]],
"ooo", 3
], ["verbs", ["v1"], [["v1", ["t6"], "", 0.0001]], "ooo", 2]],
"en", "", "", "", 1],
[[["t1", "o1", "", "", 0]],
[["nouns", ["w1"], [["w1", ["t1", "t2"], "", 0.666]], "ooo", 1],
["verbs", ["v1"], [["v1", ["t8"], "", 0.15]], "ooo", 2]], "en",
"", "", "", 1],
[],
[
[
[
"Αυτή είναι μια πολύ μακρά σειρά που\n",
"This is a very long line that\n", "", "", 0
],
[
"συνεχίζει στην επόμενη.",
"continues to the next one.", "", "", 0
],
[
"", "",
"Aftí eínai mia polý makrá seirá pou\nsynechízei stin epómeni."
] # Romanization
],
"",
"en"
],
# New input type see https://github.com/MrS0m30n3/google-translate/issues/5
[[["t1", "o1", None, None, 0], [None, None, None, "r1"]], None,
"ru", None, None, None, 0.666, None,
[["ru"], None, [0.666], ["ru"]]],
[[["t1", "o1", "", "", 0]],
[[
"nouns", ["w1", "w2"],
[["w1", ["t1", "t2"], "", 0.44], ["w2", ["t3", "t4"]]], "ooo",
1
],
["adverbs", ["adv1"], [["adv1", ["t10"], "", 0.123]], "ooo", 4],
[
"prepositions", ["pre1", "pre2"],
[["pre1", ["t8", "t9"], "", 0.0001],
["pre2", ["t3"], "", 0.005]], "ooo", 5
]], "en", "", "", "", 1]
]
outputs = [{
"translation": "T1",
"original_text": "o1",
"romanization": "R2",
"src_lang": "fr",
"match": 1.0,
"extra": {},
"has_typo": False
}, {
"translation": "t1",
"original_text": "O1",
"romanization": "O1",
"src_lang": "en",
"match": 1.0,
"extra": {},
"has_typo": False
}, {
"translation": "t1",
"original_text": "o1",
"romanization": "o1",
"src_lang": "en",
"match": 0.5,
"extra": {},
"has_typo": True
}, {
"translation": "t1",
"original_text": "o1",
"romanization": "o1",
"src_lang": "en",
"match": 1.0,
"extra": {
"nouns": {
"w1": ["t1", "t2"],
"w2": ["t3", "t4"]
},
"adjectives": {
"a1": ["t1", "t5"]
},
"verbs": {
"v1": ["t6"]
}
},
"has_typo": False
}, {
"translation": "t1",
"original_text": "o1",
"romanization": "o1",
"src_lang": "en",
"match": 1.0,
"extra": {
"nouns": {
"w1": ["t1", "t2"]
},
"verbs": {
"v1": ["t8"]
}
},
"has_typo": False
}, {
"translation": "",
"original_text": "",
"romanization": "",
"src_lang": "",
"match": 1.0,
"extra": {},
"has_typo": False
}, {
"translation":
"Αυτή είναι μια πολύ μακρά σειρά που\nσυνεχίζει στην επόμενη.",
"original_text":
"This is a very long line that\ncontinues to the next one.",
"romanization":
"This is a very long line that\ncontinues to the next one.",
"src_lang": "en",
"match": 1.0,
"extra": {},
"has_typo": False
}, {
"translation": "t1",
"original_text": "o1",
"romanization": "r1",
"src_lang": "ru",
"match": 0.666,
"extra": {},
"has_typo": False
}, {
"translation": "t1",
"original_text": "o1",
"romanization": "o1",
"src_lang": "en",
"match": 1.0,
"extra": {
"nouns": {
"w1": ["t1", "t2"],
"w2": ["t3", "t4"]
},
"adverbs": {
"adv1": ["t10"]
},
"prepositions": {
"pre1": ["t8", "t9"],
"pre2": ["t3"]
}
},
"has_typo": False
}]
for index, item in enumerate(inputs):
self.assertEqual(translator._extract_data(item), outputs[index])
def setUp(self):
self.translator = GoogleTranslator()
def test_detect_full(self):
translator = GoogleTranslator()
self.assertEqual(translator.detect("hi"), "english")
self.assertEqual(translator.detect("犬"), "japanese")
self.assertEqual(translator.detect("σπίτη"), "greek") # With typo
class TestGetInfoDict(unittest.TestCase):
def setUp(self):
self.translator = GoogleTranslator()
@mock.patch.object(GoogleTranslator, "_validate_language")
@mock.patch.object(GoogleTranslator, "_do_work")
def test_get_info_dict_default_params(self, mock_do_work, mock_val_lang):
self.assertEqual(self.translator.get_info_dict("hello", "de"),
mock_do_work.return_value)
mock_do_work.assert_called_once_with(self.translator._get_info,
"hello",
mock_val_lang.return_value,
mock_val_lang.return_value,
"text")
mock_val_lang.assert_has_calls(
[mock.call("auto"),
mock.call("de", allow_auto=False)])
@mock.patch.object(GoogleTranslator, "_validate_language")
@mock.patch.object(GoogleTranslator, "_do_work")
def test_get_info_dict_non_default_params(self, mock_do_work,
mock_val_lang):
self.assertEqual(
self.translator.get_info_dict("hello", "de", "en", "json"),
mock_do_work.return_value)
mock_do_work.assert_called_once_with(self.translator._get_info,
"hello",
mock_val_lang.return_value,
mock_val_lang.return_value,
"json")
mock_val_lang.assert_has_calls(
[mock.call("en"),
mock.call("de", allow_auto=False)])
@unittest.skipUnless(TEST_FULL, b"TEST_FULL False")
def test_get_info_dict_full(self):
expected_output = {
"original_text": "house",
"extra": {
"verbs": {
"στεγάζω": ["house", "roof"],
"εστιώ": ["house"]
},
"nouns": {
"σπίτι": ["home", "house"],
"κατοικία": [
"residence", "house", "home", "dwelling", "domicile",
"residency"
],
"οικία": ["house", "home"],
"οίκος": ["house", "home"],
"βουλή": [
"parliament", "house", "legislature", "diet",
"State house"
]
}
},
"has_typo": False,
"romanization": "house",
"src_lang": "en",
"translation": "σπίτι",
"match": 1
}
self.assertEqual(self.translator.get_info_dict("house", "el"),
expected_output)
def test_get_headers_default(self):
translator = GoogleTranslator()
self.assertListEqual(translator._get_headers(),
translator._default_headers.items())