class TestClientTextApi(unittest.TestCase):
def setUp(self):
self.client = FullClient(apiKey=conf.API_KEY,
apiServer=conf.BASE_PATH,
retinaName=conf.RETINA_NAME)
def testText(self):
fp = self.client.getFingerprintForText(inputText)
self.assertNotEqual(fp, None)
self.assertGreater(len(fp.positions), 500)
def testKeywords(self):
termList = self.client.getKeywordsForText(inputText)
self.assertGreater(len(termList), 2)
self.assertTrue(conf.isString(termList[0]))
def testTokenize(self):
sentences = self.client.getTokensForText(inputText)
self.assertGreater(len(sentences), 10)
self.assertTrue(conf.isString(sentences[0]))
firstSentence = sentences[0].split(',')
self.assertEqual(firstSentence[0], "george")
self.assertGreater(len(firstSentence), 10)
verbsSentences = self.client.getTokensForText(inputText, POStags="VB")
for verb in verbsSentences[0].split(","):
self.assertTrue("VERB" in self.client.getTerms(
term=verb)[0].pos_types)
def testSlices(self):
texts = self.client.getSlicesForText(inputText,
getFingerprint=True,
startIndex=0,
maxResults=2)
self.assertEqual(len(texts), 2)
self.assertEqual(texts[0].text.split(' ')[0], "George")
self.assertGreater(len(texts[0].fingerprint.positions), 100)
def testBulk(self):
fingerprints = self.client.getFingerprintsForTexts(bulkTexts,
sparsity=1.0)
self.assertEqual(len(fingerprints), 4)
for fp in fingerprints:
self.assertGreater(len(fp.positions), 100)
def testLanguageDetection(self):
self.assertEqual(
self.client.getLanguageForText("I have a dream!").language,
"English")
self.assertEqual(
self.client.getLanguageForText("Ich bin ein").wiki_url,
"http://en.wikipedia.org/wiki/German_language")
self.assertEqual(
self.client.getLanguageForText(
"Der var så dejligt ude på landet.").iso_tag, "da")
class TestClientTextApi(unittest.TestCase):
def setUp(self):
self.client = FullClient(apiKey=conf.API_KEY, apiServer=conf.BASE_PATH, retinaName=conf.RETINA_NAME)
def testText(self):
fp = self.client.getFingerprintForText(inputText)
self.assertNotEqual(fp, None)
self.assertGreater(len(fp.positions), 500)
def testKeywords(self):
termList = self.client.getKeywordsForText(inputText)
self.assertGreater(len(termList), 2)
self.assertTrue(conf.isString(termList[0]))
def testTokenize(self):
sentences = self.client.getTokensForText(inputText)
self.assertGreater(len(sentences), 10)
self.assertTrue(conf.isString(sentences[0]))
firstSentence = sentences[0].split(',')
self.assertEqual(firstSentence[0], "george")
self.assertGreater(len(firstSentence), 10)
verbsSentences = self.client.getTokensForText(inputText, POStags="VB")
for verb in verbsSentences[0].split(","):
self.assertTrue("VERB" in self.client.getTerms(term=verb)[0].pos_types)
def testSlices(self):
texts = self.client.getSlicesForText(inputText, getFingerprint=True, startIndex=0, maxResults=2)
self.assertEqual(len(texts), 2)
self.assertEqual(texts[0].text.split(' ')[0], "George")
self.assertGreater(len(texts[0].fingerprint.positions), 100)
def testBulk(self):
fingerprints = self.client.getFingerprintsForTexts(bulkTexts, sparsity=1.0)
self.assertEqual(len(fingerprints), 4)
for fp in fingerprints:
self.assertGreater(len(fp.positions), 100)
def testLanguageDetection(self):
self.assertEqual(self.client.getLanguageForText("I have a dream!").language, "English")
self.assertEqual(self.client.getLanguageForText("Ich bin ein").wiki_url, "http://en.wikipedia.org/wiki/German_language")
self.assertEqual(self.client.getLanguageForText("Der var så dejligt ude på landet.").iso_tag, "da")
