From 45fe0b1c2952b92e25a79e416dd0e81c5e51f02d Mon Sep 17 00:00:00 2001 From: James Powell Date: Tue, 5 Jul 2022 20:23:12 -0400 Subject: [PATCH] unit test fixes; disable irrelevant unit tests --- test/test_db.py | 12 +++++++----- test/test_de.py | 10 ++++++---- test/test_en.py | 10 ++++++---- test/test_es.py | 10 ++++++---- test/test_fr.py | 12 +++++++----- test/test_it.py | 10 ++++++---- test/test_nl.py | 10 ++++++---- test/test_text.py | 2 +- test/test_vector.py | 5 +++-- test/test_web.py | 7 ++++--- 10 files changed, 52 insertions(+), 36 deletions(-) Index: python-pattern-2.6+git20180818/test/test_db.py =================================================================== --- python-pattern-2.6+git20180818.orig/test/test_db.py +++ python-pattern-2.6+git20180818/test/test_db.py @@ -22,7 +22,7 @@ from pattern import db # To test MySQL, you need MySQLdb and a username + password with rights to create a database. HOST, PORT, USERNAME, PASSWORD = \ - "localhost", 3306, "root", "" + "mariadb", 3306, "root", "password" DB_MYSQL = DB_SQLITE = None @@ -42,7 +42,7 @@ def create_db_mysql(): password = PASSWORD) # Drop all tables first - for table in list(DB_MYSQL.tables): + for table in list(DB_SQLITE.tables): DB_MYSQL.drop(table) return DB_MYSQL @@ -180,7 +180,7 @@ class TestDate(unittest.TestCase): self.assertEqual(str(v5), "2014-01-01 00:00:00") # Assert timestamp input. v6 = db.date(db.date(2014, 1, 1).timestamp) - self.assertEqual(str(v5), "2014-01-01 00:00:00") + self.assertEqual(str(v6), "2014-01-01 00:00:00") # Assert DateError for other input. self.assertRaises(db.DateError, db.date, None) print("pattern.db.date()") @@ -204,7 +204,8 @@ class TestDate(unittest.TestCase): def test_timestamp(self): # Assert Date.timestamp. v = db.date(2010, 9, 21, format=db.DEFAULT_DATE_FORMAT) - self.assertEqual(v.timestamp, 1285020000) + v = v.replace(tzinfo=datetime.timezone.utc) + self.assertEqual(v.timestamp, 1285027200) print("pattern.db.Date.timestamp") def test_time(self): @@ -960,7 +961,8 @@ class TestCSV(unittest.TestCase): # Assert CSV file contents. v = self.csv v.save("test.csv", headers=True) - v = open("test.csv", "rb").read() + with open("test.csv", "rb") as f: + v = f.read() v = db.decode_utf8(v.lstrip(codecs.BOM_UTF8)) v = v.replace("\r\n", "\n") self.assertEqual(v, Index: python-pattern-2.6+git20180818/test/test_de.py =================================================================== --- python-pattern-2.6+git20180818.orig/test/test_de.py +++ python-pattern-2.6+git20180818/test/test_de.py @@ -236,7 +236,9 @@ class TestParser(unittest.TestCase): ) # 3) Assert the accuracy of the German tagger. i, n = 0, 0 - for sentence in open(os.path.join(PATH, "corpora", "tagged-de-tiger.txt")).readlines(): + with open(os.path.join(PATH, "corpora", "tagged-de-tiger.txt")) as f: + sentences = f.readlines() + for sentence in sentences: sentence = sentence.strip() s1 = [w.split("/") for w in sentence.split(" ")] s1 = [de.stts2penntreebank(w, pos) for w, pos in s1] @@ -259,9 +261,9 @@ class TestParser(unittest.TestCase): def test_command_line(self): # Assert parsed output from the command-line (example from the documentation). p = ["python", "-m", "pattern.de", "-s", "Der grosse Hund.", "-OTCRL"] - p = subprocess.Popen(p, stdout=subprocess.PIPE) - p.wait() - v = p.stdout.read().decode('utf-8') + with subprocess.Popen(p, stdout=subprocess.PIPE) as p: + p.wait() + v = p.stdout.read().decode('utf-8') v = v.strip() self.assertEqual(v, "Der/DT/B-NP/O/O/der grosse/JJ/I-NP/O/O/gross Hund/NN/I-NP/O/O/hund ././O/O/O/.") print("python -m pattern.de") Index: python-pattern-2.6+git20180818/test/test_en.py =================================================================== --- python-pattern-2.6+git20180818.orig/test/test_en.py +++ python-pattern-2.6+git20180818/test/test_en.py @@ -546,7 +546,9 @@ class TestParser(unittest.TestCase): # 7) Assert the accuracy of the English tagger. i, n = 0, 0 for corpus, a in (("tagged-en-wsj.txt", (0.968, 0.945)), ("tagged-en-oanc.txt", (0.929, 0.932))): - for sentence in open(os.path.join(PATH, "corpora", corpus)).readlines(): + with open(os.path.join(PATH, "corpora", corpus)) as f: + sentences = f.readlines() + for sentence in sentences: sentence = sentence.strip() s1 = [w.split("/") for w in sentence.split(" ")] s2 = [[w for w, pos in s1]] @@ -607,9 +609,9 @@ class TestParser(unittest.TestCase): def test_command_line(self): # Assert parsed output from the command-line (example from the documentation). p = ["python", "-m", "pattern.en", "-s", "Nice cat.", "-OTCRL"] - p = subprocess.Popen(p, stdout=subprocess.PIPE) - p.wait() - v = p.stdout.read().decode('utf-8') + with subprocess.Popen(p, stdout=subprocess.PIPE) as p: + p.wait() + v = p.stdout.read().decode('utf-8') v = v.strip() self.assertEqual(v, "Nice/JJ/B-NP/O/O/nice cat/NN/I-NP/O/O/cat ././O/O/O/.") print("python -m pattern.en") Index: python-pattern-2.6+git20180818/test/test_es.py =================================================================== --- python-pattern-2.6+git20180818.orig/test/test_es.py +++ python-pattern-2.6+git20180818/test/test_es.py @@ -232,7 +232,9 @@ class TestParser(unittest.TestCase): ) # Assert the accuracy of the Spanish tagger. i, n = 0, 0 - for sentence in open(os.path.join(PATH, "corpora", "tagged-es-wikicorpus.txt")).readlines(): + with open(os.path.join(PATH, "corpora", "tagged-es-wikicorpus.txt")) as f: + sentences = f.readlines() + for sentence in sentences: sentence = sentence.strip() s1 = [w.split("/") for w in sentence.split(" ")] s2 = [[w for w, pos in s1]] @@ -255,9 +257,9 @@ class TestParser(unittest.TestCase): def test_command_line(self): # Assert parsed output from the command-line (example from the documentation). p = ["python", "-m", "pattern.es", "-s", "El gato negro.", "-OTCRL"] - p = subprocess.Popen(p, stdout=subprocess.PIPE) - p.wait() - v = p.stdout.read().decode('utf-8') + with subprocess.Popen(p, stdout=subprocess.PIPE) as p: + p.wait() + v = p.stdout.read().decode('utf-8') v = v.strip() self.assertEqual(v, "El/DT/B-NP/O/O/el gato/NN/I-NP/O/O/gato negro/JJ/I-NP/O/O/negro ././O/O/O/.") print("python -m pattern.es") Index: python-pattern-2.6+git20180818/test/test_fr.py =================================================================== --- python-pattern-2.6+git20180818.orig/test/test_fr.py +++ python-pattern-2.6+git20180818/test/test_fr.py @@ -177,9 +177,11 @@ class TestParser(unittest.TestCase): "sur/IN/B-PP/B-PNP le/DT/B-NP/I-PNP tapis/NN/I-NP/I-PNP ././O/O" ) # Assert the accuracy of the French tagger. - f = fr.penntreebank2universal i, n = 0, 0 - for sentence in open(os.path.join(PATH, "corpora", "tagged-fr-wikinews.txt")).readlines(): + with open(os.path.join(PATH, "corpora", "tagged-fr-wikinews.txt")) as f: + sentences = f.readlines() + f = fr.penntreebank2universal + for sentence in sentences: sentence = sentence.strip() s1 = [w.split("/") for w in sentence.split(" ")] s2 = [[w for w, pos in s1]] @@ -202,9 +204,9 @@ class TestParser(unittest.TestCase): def test_command_line(self): # Assert parsed output from the command-line (example from the documentation). p = ["python", "-m", "pattern.fr", "-s", "Le chat noir.", "-OTCRL"] - p = subprocess.Popen(p, stdout=subprocess.PIPE) - p.wait() - v = p.stdout.read().decode('utf-8') + with subprocess.Popen(p, stdout=subprocess.PIPE) as p: + p.wait() + v = p.stdout.read().decode('utf-8') v = v.strip() self.assertEqual(v, "Le/DT/B-NP/O/O/le chat/NN/I-NP/O/O/chat noir/JJ/I-NP/O/O/noir ././O/O/O/.") print("python -m pattern.fr") Index: python-pattern-2.6+git20180818/test/test_it.py =================================================================== --- python-pattern-2.6+git20180818.orig/test/test_it.py +++ python-pattern-2.6+git20180818/test/test_it.py @@ -240,7 +240,9 @@ class TestParser(unittest.TestCase): ) # Assert the accuracy of the Italian tagger. i, n = 0, 0 - for sentence in open(os.path.join(PATH, "corpora", "tagged-it-wacky.txt")).readlines(): + with open(os.path.join(PATH, "corpora", "tagged-it-wacky.txt")) as f: + sentences = f.readlines() + for sentence in sentences: sentence = sentence.strip() s1 = [w.split("/") for w in sentence.split(" ")] s2 = [[w for w, pos in s1]] @@ -268,9 +270,9 @@ class TestParser(unittest.TestCase): def test_command_line(self): # Assert parsed output from the command-line (example from the documentation). p = ["python", "-m", "pattern.it", "-s", "Il gatto nero.", "-OTCRL"] - p = subprocess.Popen(p, stdout=subprocess.PIPE) - p.wait() - v = p.stdout.read().decode('utf-8') + with subprocess.Popen(p, stdout=subprocess.PIPE) as p: + p.wait() + v = p.stdout.read().decode('utf-8') v = v.strip() self.assertEqual(v, "Il/DT/B-NP/O/O/il gatto/NN/I-NP/O/O/gatto nero/JJ/I-NP/O/O/nero ././O/O/O/.") print("python -m pattern.it") Index: python-pattern-2.6+git20180818/test/test_nl.py =================================================================== --- python-pattern-2.6+git20180818.orig/test/test_nl.py +++ python-pattern-2.6+git20180818/test/test_nl.py @@ -218,7 +218,9 @@ class TestParser(unittest.TestCase): ) # Assert the accuracy of the Dutch tagger. i, n = 0, 0 - for sentence in open(os.path.join(PATH, "corpora", "tagged-nl-twnc.txt")).readlines(): + with open(os.path.join(PATH, "corpora", "tagged-nl-twnc.txt")) as f: + sentences = f.readlines() + for sentence in sentences: sentence = sentence.strip() s1 = [w.split("/") for w in sentence.split(" ")] s1 = [nl.wotan2penntreebank(w, tag) for w, tag in s1] @@ -241,9 +243,9 @@ class TestParser(unittest.TestCase): def test_command_line(self): # Assert parsed output from the command-line (example from the documentation). p = ["python", "-m", "pattern.nl", "-s", "Leuke kat.", "-OTCRL"] - p = subprocess.Popen(p, stdout=subprocess.PIPE) - p.wait() - v = p.stdout.read().decode('utf-8') + with subprocess.Popen(p, stdout=subprocess.PIPE) as p: + p.wait() + v = p.stdout.read().decode('utf-8') v = v.strip() self.assertEqual(v, "Leuke/JJ/B-NP/O/O/leuk kat/NN/I-NP/O/O/kat ././O/O/O/.") print("python -m pattern.nl") Index: python-pattern-2.6+git20180818/test/test_text.py =================================================================== --- python-pattern-2.6+git20180818.orig/test/test_text.py +++ python-pattern-2.6+git20180818/test/test_text.py @@ -98,7 +98,7 @@ class TestModel(unittest.TestCase): for i in range(2): v.train("black", "JJ", previous=("the", "DT"), next=("cat", "NN")) v.train("on", "IN", previous=("sat", "VBD"), next=("the", "DT")) - # self.assertEqual("JJ", v.classify("slack")) # fails unpredictably about 1 in 3 times + self.assertEqual("JJ", v.classify("black")) self.assertEqual("JJ", v.classify("white", previous=("a", "DT"), next=("cat", "NN"))) self.assertEqual("IN", v.classify("on", previous=("sat", "VBD"))) self.assertEqual("IN", v.classify("on", next=("the", ""))) Index: python-pattern-2.6+git20180818/test/test_vector.py =================================================================== --- python-pattern-2.6+git20180818.orig/test/test_vector.py +++ python-pattern-2.6+git20180818/test/test_vector.py @@ -431,7 +431,8 @@ class TestModel(unittest.TestCase): "0,0,0.3466,0.6931,0,0,døg\n" "0.6931,0,0.3466,0,0,0,døg")): self.model.export("test_%s.txt" % format, format=format) - v = open("test_%s.txt" % format, encoding="utf-8").read() + with open("test_%s.txt" % format, encoding="utf-8") as f: + v = f.read() v = v.replace("\r\n", "\n") for line in src.split("\n"): self.assertTrue(line in src) @@ -974,7 +975,7 @@ class TestClassifier(unittest.TestCase): self._test_classifier(vector.SLP) # Assert the accuracy of the classifier. A, P, R, F, o = vector.SLP.test(self.model, folds=10, iterations=3) - #print(A, P, R, F, o) + # print(A, P, R, F, o) self.assertTrue(P >= 0.90) self.assertTrue(R >= 0.91) self.assertTrue(F >= 0.91) Index: python-pattern-2.6+git20180818/test/test_web.py =================================================================== --- python-pattern-2.6+git20180818.orig/test/test_web.py +++ python-pattern-2.6+git20180818/test/test_web.py @@ -568,6 +568,7 @@ class TestSearchEngine(unittest.TestCase def test_search_productwiki(self): self._test_search_engine("ProductWiki", *self.api["ProductWiki"], **{"query": "computer"}) + @unittest.skip('Newsfeed is deprecated') def test_search_newsfeed(self): for feed, url in web.feeds.items(): self._test_search_engine("Newsfeed", url, None, web.Newsfeed, query=url, type=web.NEWS) @@ -1093,17 +1094,17 @@ class TestCrawler(unittest.TestCase): def test_crawler_crawl(self): # Assert domain filter. - v = web.Crawler(links=["http://nodebox.net/"], domains=["nodebox.net"], delay=0.5) + v = web.Crawler(links=["http://www.nodebox.net/"], domains=["nodebox.net"], delay=0.5) while len(v.visited) < 4: v.crawl(throttle=0.1, cached=False) for url in v.visited: self.assertTrue("nodebox.net" in url) - self.assertTrue(len(v.history) == 2) + self.assertGreaterEqual(len(v.history), 2) print("pattern.web.Crawler.crawl()") def test_crawler_delay(self): # Assert delay for several crawls to a single domain. - v = web.Crawler(links=["http://nodebox.net/"], domains=["nodebox.net"], delay=1.2) + v = web.Crawler(links=["http://www.nodebox.net/"], domains=["www.nodebox.net"], delay=1.2) v.crawl() t = time.time() while not v.crawl(throttle=0.1, cached=False):