from unittest import TestCase

from languedoc.predict import preprocess, rank_ngram_freqs, Sample, identify


class TestPredict(TestCase):
	def test_preprocess(self):
		self.assertEqual(preprocess("abc"), " abc ")
		self.assertEqual(preprocess("A  b.c"), " a b c ")
		self.assertEqual(preprocess("1% "), " ")
		self.assertEqual(preprocess("Глава ĚŠČŘŽ"), " глава ěščřž ")

	def test_rank_ngram_freqs(self):
		freqs = {"a": 3, "aa": 1, "b": 4, "bb": 1, "c": 1}
		expected = {"b": 0, "a": 1, "c": 2, "aa": 3, "bb": 4}
		self.assertEqual(rank_ngram_freqs(freqs), expected)


class TestSample(TestCase):
	def test_extract(self):
		a = Sample.extract("aaaaaa", "a")
		self.assertEqual(a.language, "a")
		self.assertEqual(a.ranked_ngrams, {'a': 0, 'aa': 1, 'aaa': 2, ' aa': 3, 'aa ': 4, ' a': 5, 'a ': 6})

		b = Sample.extract("aa aa aa", "b")
		self.assertEqual(b.ranked_ngrams, {'a': 0, ' aa': 1, 'aa ': 2, ' a': 3, 'a ': 4, 'aa': 5, 'a a': 6})

		c = Sample.extract("aa")
		self.assertEqual(c.language, "??")
		self.assertEqual(c.ranked_ngrams, {'a': 0, ' aa': 1, 'aa ': 2, ' a': 3, 'a ': 4, 'aa': 5})


class TestIdentify(TestCase):
	def test_identify(self):
		samples = [
			("cs", "Severní ledový oceán je nejmenší světový oceán."),
			("de", "Der Arktische Ozean ist der kleinste Ozean der Erde."),
			("en", "The Arctic Ocean is the smallest of the world's oceans."),
			("es", "Océano Ártico más pequeña y más septentrional del planeta"),
			("fr", "L'océan Arctique ce qui en fait le plus petit des océans."),
			("it", "Il Mar Glaciale Artico è una massa d'acqua..."),
			("ru", "Се́верный Ледови́тый океа́н — наименьший по площади океан Земли")
		]

		for (lang, sample) in samples:
			self.assertEqual(lang, identify(sample))