diff --git a/great_ai/tests/large_file/test_human_readable_to_byte.py b/great_ai/tests/large_file/test_human_readable_to_byte.py index a7290b5..271722e 100644 --- a/great_ai/tests/large_file/test_human_readable_to_byte.py +++ b/great_ai/tests/large_file/test_human_readable_to_byte.py @@ -5,22 +5,22 @@ from src.great_ai.large_file.helper import human_readable_to_byte class TestHumanReadableToByte(unittest.TestCase): def test_simple_cases(self) -> None: - self.assertEqual(human_readable_to_byte("1KB"), 1024) - self.assertEqual(human_readable_to_byte("2KB"), 2048) + assert human_readable_to_byte("1KB") == 1024 + assert human_readable_to_byte("2KB") == 2048 def test_fractions(self) -> None: - self.assertEqual(human_readable_to_byte("0.5KB"), 512) - self.assertEqual(human_readable_to_byte("20.5KB"), 1024 * 20 + 512) + assert human_readable_to_byte("0.5KB") == 512 + assert human_readable_to_byte("20.5KB") == 1024 * 20 + 512 def test_formating(self) -> None: - self.assertEqual(human_readable_to_byte(" 1MB"), 1024 * 1024) - self.assertEqual(human_readable_to_byte(" 2 MB"), 1024 * 1024 * 2) - self.assertEqual(human_readable_to_byte(" 4 MB "), 1024 * 1024 * 4) - self.assertEqual(human_readable_to_byte("8MB "), 1024 * 1024 * 8) - self.assertEqual(human_readable_to_byte(" 1.5 MB "), 1024 * 1024 * 1.5) + assert human_readable_to_byte(" 1MB") == 1024 * 1024 + assert human_readable_to_byte(" 2 MB") == 1024 * 1024 * 2 + assert human_readable_to_byte(" 4 MB ") == 1024 * 1024 * 4 + assert human_readable_to_byte("8MB ") == 1024 * 1024 * 8 + assert human_readable_to_byte(" 1.5 MB ") == 1024 * 1024 * 1.5 def test_casing(self) -> None: - self.assertEqual(human_readable_to_byte("0.5GB"), 0.5 * 1024 * 1024 * 1024) - self.assertEqual(human_readable_to_byte("0.5gB"), 0.5 * 1024 * 1024 * 1024) - self.assertEqual(human_readable_to_byte("0.5Gb"), 0.5 * 1024 * 1024 * 1024) - self.assertEqual(human_readable_to_byte("0.5gb"), 0.5 * 1024 * 1024 * 1024) + assert human_readable_to_byte("0.5GB") == 0.5 * 1024 * 1024 * 1024 + assert human_readable_to_byte("0.5gB") == 0.5 * 1024 * 1024 * 1024 + assert human_readable_to_byte("0.5Gb") == 0.5 * 1024 * 1024 * 1024 + assert human_readable_to_byte("0.5gb") == 0.5 * 1024 * 1024 * 1024 diff --git a/great_ai/tests/large_file/test_large_file.py b/great_ai/tests/large_file/test_large_file.py index 5b163ed..8c66d11 100644 --- a/great_ai/tests/large_file/test_large_file.py +++ b/great_ai/tests/large_file/test_large_file.py @@ -73,8 +73,8 @@ class TestLargeFileS3(unittest.TestCase): Bucket=credentials["large_files_bucket_name"], Prefix="test-file" ) - self.assertEqual(lf._version, 2) - self.assertEqual(lf._local_name, "test-file-2") + assert lf._version == 2 + assert lf._local_name == "test-file-2" @patch.object(boto3, "client") def test_initialized_with_file(self, client: Any) -> None: @@ -116,5 +116,5 @@ class TestLargeFileS3(unittest.TestCase): Bucket=credentials["large_files_bucket_name"], Prefix="test-file" ) - self.assertEqual(lf._version, 2) - self.assertEqual(lf._local_name, "test-file-2") + assert lf._version == 2 + assert lf._local_name == "test-file-2" diff --git a/great_ai/tests/utilities/test_clean.py b/great_ai/tests/utilities/test_clean.py index 0fdf9e4..69355d6 100644 --- a/great_ai/tests/utilities/test_clean.py +++ b/great_ai/tests/utilities/test_clean.py @@ -9,18 +9,18 @@ class TestClean(unittest.TestCase): clean_xml = "Hi, my name is András! <3 <> <|" clean_xml_ascii = "Hi, my name is Andras! <3 <> <|" - self.assertEqual(clean(xml), clean_xml) - self.assertEqual(clean(xml, ignore_xml=True, ignore_latex=True), xml) - self.assertEqual(clean(xml, convert_to_ascii=True), clean_xml_ascii) + assert clean(xml) == clean_xml + assert clean(xml, ignore_xml=True, ignore_latex=True) == xml + assert clean(xml, convert_to_ascii=True) == clean_xml_ascii def test_simple_latex_handling(self) -> None: latex = 'Bj\\"{o}rn is \\textit{happy} 🙂' clean_latex = "Björn is happy 🙂" clean_latex_ascii = "Bjorn is happy" - self.assertEqual(clean(latex), clean_latex) - self.assertEqual(clean(latex, ignore_latex=True), latex) - self.assertEqual(clean(latex, convert_to_ascii=True), clean_latex_ascii) + assert clean(latex) == clean_latex + assert clean(latex, ignore_latex=True) == latex + assert clean(latex, convert_to_ascii=True) == clean_latex_ascii def test_cursed(self) -> None: cursed = """ @@ -28,8 +28,8 @@ class TestClean(unittest.TestCase): """ cleaned = "to the moon" - self.assertEqual(clean(cursed), cursed.strip()) - self.assertEqual(clean(cursed, convert_to_ascii=True), cleaned) + assert clean(cursed) == cursed.strip() + assert clean(cursed, convert_to_ascii=True) == cleaned def test_whitespace(self) -> None: text = """ @@ -43,9 +43,9 @@ class TestClean(unittest.TestCase): """ # noqa: W293 cleaned = "word1 word2 wo rd3" - self.assertEqual(clean(text, convert_to_ascii=True), cleaned) - self.assertEqual(clean(text, ignore_xml=True, ignore_latex=True), cleaned) - self.assertEqual(clean(text), cleaned) + assert clean(text, convert_to_ascii=True) == cleaned + assert clean(text, ignore_xml=True, ignore_latex=True) == cleaned + assert clean(text) == cleaned def test_hyphens(self) -> None: text = """ @@ -57,20 +57,20 @@ class TestClean(unittest.TestCase): """ cleaned = "break - word break-word break-word break-word break-word" - self.assertEqual(clean(text), cleaned) + assert clean(text) == cleaned def test_T_I_T_L_E_case(self) -> None: text = "an a r t i c l e is to F I N D the purpose of a tree" cleaned = "an article is to FIND the purpose of a tree" - self.assertEqual(clean(text), cleaned) + assert clean(text) == cleaned def test_bracket_removal(self) -> None: text = "something [0], and [frefe, ferf]" cleaned = "something, and" - self.assertEqual(clean(text, remove_brackets=True), cleaned) + assert clean(text, remove_brackets=True) == cleaned self.assertEqual( clean(text, ignore_xml=True, ignore_latex=True, remove_brackets=True), cleaned, @@ -78,7 +78,7 @@ class TestClean(unittest.TestCase): self.assertEqual( clean(text, convert_to_ascii=True, remove_brackets=True), cleaned ) - self.assertEqual(clean(text), text) + assert clean(text) == text def test_latex_math_handling(self) -> None: latex = "An increase of 3% was achieved with $q_1 = \\frac{3}{5}$." @@ -86,10 +86,10 @@ class TestClean(unittest.TestCase): clean_latex = "An increase of 3% was achieved with q_1 = 3/5." clean_bad_latex = "An increase of 3% was achieved with q_1 = 3//5." - self.assertEqual(clean(latex), clean_latex) - self.assertEqual(clean(bad_latex), clean_bad_latex) - self.assertEqual(clean(latex, ignore_latex=True), latex) - self.assertEqual(clean(bad_latex, ignore_latex=True), bad_latex) + assert clean(latex) == clean_latex + assert clean(bad_latex) == clean_bad_latex + assert clean(latex, ignore_latex=True) == latex + assert clean(bad_latex, ignore_latex=True) == bad_latex def test_everything(self) -> None: text = """ @@ -102,9 +102,9 @@ class TestClean(unittest.TestCase): ) def test_empty(self) -> None: - self.assertEqual(clean("", convert_to_ascii=True), "") + assert clean("", convert_to_ascii=True) == "" def test_punctuation_fixing(self) -> None: text = " Dear reader ( or listener ) , welcome ! " fixed = "Dear reader (or listener), welcome!" - self.assertEqual(clean(text), fixed) + assert clean(text) == fixed diff --git a/great_ai/tests/utilities/test_get_sentences.py b/great_ai/tests/utilities/test_get_sentences.py index 51ffdec..ed6e4c4 100644 --- a/great_ai/tests/utilities/test_get_sentences.py +++ b/great_ai/tests/utilities/test_get_sentences.py @@ -8,9 +8,9 @@ class TestGetSentences(unittest.TestCase): text = "This is a complete sentence. So is this. However this is n" # ot. expected = ["This is a complete sentence.", "So is this.", "However this is n"] - self.assertEqual(get_sentences(text), expected) - self.assertEqual(get_sentences(text, ignore_partial=True), expected[0:2]) + assert get_sentences(text) == expected + assert get_sentences(text, ignore_partial=True) == expected[0:2] def test_empty(self) -> None: - self.assertEqual(get_sentences(""), []) - self.assertEqual(get_sentences("", ignore_partial=True), []) + assert get_sentences("") == [] + assert get_sentences("", ignore_partial=True) == [] diff --git a/great_ai/tests/utilities/test_language.py b/great_ai/tests/utilities/test_language.py index 2e7a3bf..cbba2d9 100644 --- a/great_ai/tests/utilities/test_language.py +++ b/great_ai/tests/utilities/test_language.py @@ -9,11 +9,11 @@ from src.great_ai.utilities.language import ( class TestLanguage(unittest.TestCase): def test_predict_language(self) -> None: - self.assertEqual(predict_language("This is an English text."), "en") - self.assertEqual(predict_language("Ez egy magyar szöveg."), "hu") - self.assertEqual(predict_language("此處按原典，應為「黃武元年」，而電子稿此處為「黃初元年」。"), "zh-TW") - self.assertEqual(predict_language("32"), "und") - self.assertEqual(predict_language(""), "und") + assert predict_language("This is an English text.") == "en" + assert predict_language("Ez egy magyar szöveg.") == "hu" + assert predict_language("此處按原典，應為「黃武元年」，而電子稿此處為「黃初元年」。") == "zh-TW" + assert predict_language("32") == "und" + assert predict_language("") == "und" def test_is_english(self) -> None: self.assertTrue(is_english("en")) @@ -27,10 +27,10 @@ class TestLanguage(unittest.TestCase): self.assertFalse(is_english(None)) def english_name_of_language(self) -> None: - self.assertEqual(english_name_of_language("en"), "English") - self.assertEqual(english_name_of_language("hu"), "Hungarian") - self.assertEqual(english_name_of_language("zh"), "Chinese") - self.assertEqual(english_name_of_language("zh-TW"), "Chinese") - self.assertEqual(english_name_of_language("und"), "Unknown language") - self.assertEqual(english_name_of_language(""), "Unknown language") - self.assertEqual(english_name_of_language(None), "Unknown language") + assert english_name_of_language("en") == "English" + assert english_name_of_language("hu") == "Hungarian" + assert english_name_of_language("zh") == "Chinese" + assert english_name_of_language("zh-TW") == "Chinese" + assert english_name_of_language("und") == "Unknown language" + assert english_name_of_language("") == "Unknown language" + assert english_name_of_language(None) == "Unknown language" diff --git a/great_ai/tests/utilities/test_lemmatize_text.py b/great_ai/tests/utilities/test_lemmatize_text.py index 9bcdb2a..094dfac 100644 --- a/great_ai/tests/utilities/test_lemmatize_text.py +++ b/great_ai/tests/utilities/test_lemmatize_text.py @@ -127,13 +127,13 @@ class TestLemmatizeText(unittest.TestCase): "._PUNCT", ] - self.assertEqual(lemmatize_text(text), lemmatized) - self.assertEqual(lemmatize_text(text, add_part_of_speech=True), lemmatized_pos) - self.assertEqual(lemmatize_text(text, add_negation=True), lemmatized_neg) + assert lemmatize_text(text) == lemmatized + assert lemmatize_text(text, add_part_of_speech=True) == lemmatized_pos + assert lemmatize_text(text, add_negation=True) == lemmatized_neg self.assertEqual( lemmatize_text(text, add_negation=True, add_part_of_speech=True), lemmatized_pos_neg, ) def test_empty(self) -> None: - self.assertEqual(lemmatize_text(""), []) + assert lemmatize_text("") == [] diff --git a/great_ai/tests/utilities/test_lemmatize_token.py b/great_ai/tests/utilities/test_lemmatize_token.py index 0ad8cea..a828ea5 100644 --- a/great_ai/tests/utilities/test_lemmatize_token.py +++ b/great_ai/tests/utilities/test_lemmatize_token.py @@ -8,13 +8,13 @@ class TestLemmatizeToken(unittest.TestCase): def test_simple(self) -> None: token = nlp("Center")[0] - self.assertEqual(lemmatize_token(token), "centre") - self.assertEqual(lemmatize_token(token, add_negation=True), "centre") - self.assertEqual(lemmatize_token(token, add_part_of_speech=True), "centre_NOUN") + assert lemmatize_token(token) == "centre" + assert lemmatize_token(token, add_negation=True) == "centre" + assert lemmatize_token(token, add_part_of_speech=True) == "centre_NOUN" def test_punctuation(self) -> None: token = nlp("This.")[1] - self.assertEqual(lemmatize_token(token), ".") - self.assertEqual(lemmatize_token(token, add_negation=True), ".") - self.assertEqual(lemmatize_token(token, add_part_of_speech=True), "._PUNCT") + assert lemmatize_token(token) == "." + assert lemmatize_token(token, add_negation=True) == "." + assert lemmatize_token(token, add_part_of_speech=True) == "._PUNCT" diff --git a/great_ai/tests/utilities/test_parallel_map.py b/great_ai/tests/utilities/test_parallel_map.py index e93f8b3..c24f721 100644 --- a/great_ai/tests/utilities/test_parallel_map.py +++ b/great_ai/tests/utilities/test_parallel_map.py @@ -10,7 +10,7 @@ class TestParallelMap(unittest.TestCase): inputs = range(COUNT) expected = [v**2 for v in range(COUNT)] - self.assertEqual(parallel_map(lambda v: v**2, inputs), expected) + assert parallel_map(lambda v: v**2, inputs) == expected def test_simple_case_without_progress_bar(self) -> None: inputs = range(COUNT) @@ -31,7 +31,7 @@ class TestParallelMap(unittest.TestCase): ) def test_no_op(self) -> None: - self.assertEqual(parallel_map(lambda v: v**2, [], disable_progress=True), []) + assert parallel_map(lambda v: v**2, [], disable_progress=True) == [] self.assertEqual( parallel_map(lambda v: v**2, [], disable_progress=True, chunk_size=100), [], diff --git a/great_ai/tests/utilities/test_publication_tei.py b/great_ai/tests/utilities/test_publication_tei.py index 390f73f..75593ac 100644 --- a/great_ai/tests/utilities/test_publication_tei.py +++ b/great_ai/tests/utilities/test_publication_tei.py @@ -28,22 +28,22 @@ class TestPublicationTEI(unittest.TestCase): cls.test_xml = f.read() def test_metadata_extraction(self) -> None: - self.assertEqual(PublicationTEI(self.test_xml).publication_metadata, metadata) + assert PublicationTEI(self.test_xml).publication_metadata == metadata def test_authors(self) -> None: - self.assertEqual(PublicationTEI(self.test_xml).authors, authors) + assert PublicationTEI(self.test_xml).authors == authors def test_content(self) -> None: - self.assertEqual(PublicationTEI(self.test_xml).content, content) + assert PublicationTEI(self.test_xml).content == content def test_sentences(self) -> None: - self.assertEqual(PublicationTEI(self.test_xml).sentences, sentences) + assert PublicationTEI(self.test_xml).sentences == sentences def test_bookmarks(self) -> None: - self.assertEqual(PublicationTEI(self.test_xml).bookmarks, bookmarks) + assert PublicationTEI(self.test_xml).bookmarks == bookmarks def test_abstract(self) -> None: - self.assertEqual(PublicationTEI(self.test_xml).abstract_sentences, abstract) + assert PublicationTEI(self.test_xml).abstract_sentences == abstract def test_introduction(self) -> None: self.assertEqual( @@ -51,7 +51,7 @@ class TestPublicationTEI(unittest.TestCase): ) def test_conclusion(self) -> None: - self.assertEqual(PublicationTEI(self.test_xml).conclusion_sentences, conclusion) + assert PublicationTEI(self.test_xml).conclusion_sentences == conclusion def test_empty1(self) -> None: tei = PublicationTEI("") diff --git a/great_ai/tests/utilities/test_unique.py b/great_ai/tests/utilities/test_unique.py index fc020c7..42e1708 100644 --- a/great_ai/tests/utilities/test_unique.py +++ b/great_ai/tests/utilities/test_unique.py @@ -26,8 +26,8 @@ class TestUnique(unittest.TestCase): expected = original - self.assertEqual(unique(values), expected) - self.assertEqual(unique(values, key=lambda v: v), expected) + assert unique(values) == expected + assert unique(values, key=lambda v: v) == expected def test_with_key_0(self) -> None: values = original @@ -39,7 +39,7 @@ class TestUnique(unittest.TestCase): ("d", 2), ] - self.assertEqual(unique(values, key=lambda v: v[0]), expected) + assert unique(values, key=lambda v: v[0]) == expected def test_with_key_1(self) -> None: values = original @@ -51,4 +51,4 @@ class TestUnique(unittest.TestCase): ("d", 2), ] - self.assertEqual(unique(values, key=lambda v: v[1]), expected) + assert unique(values, key=lambda v: v[1]) == expected