def test_difference2(self):
hs1 = HashSet(["Jake", "Jeff", "Shane", "Fre"])
hs2 = HashSet(
["Melody", "Erik", "Shane", "Alan", "Bob", "Kaichi", "Jake"])
difference = hs1.difference(hs2)
assert difference.size == 7
assert difference.contains("Jake") == False
assert difference.contains("Shane") == False
assert difference.contains("Jeff") == True
assert difference.contains("Alan") == True
def test_intersection(self):
hs1 = HashSet(["Melody", "Erik", "Jake", "Shane"])
hs2 = HashSet(["Jake", "Alan", "Shane"])
intersection = hs1.intersection(hs2)
assert intersection.size == 2
assert intersection.contains("Jake") == True
assert intersection.contains("Shane") == True
assert intersection.contains("Melody") == False
assert intersection.contains("Erik") == False
assert intersection.contains("Alan") == False
def test_difference(self):
hs1 = HashSet(["Melody", "Erik", "Jake", "Shane"])
hs2 = HashSet(["Jake", "Alan", "Shane"])
difference = hs1.difference(hs2)
assert difference.size == 3
assert difference.contains("Melody") == True
assert difference.contains("Erik") == True
assert difference.contains("Alan") == True
assert difference.contains("Jake") == False
assert difference.contains("Shane") == False
assert difference.contains("Bob") == False
def test_union(self):
hs1 = HashSet(["Melody", "Erik", "Jake"])
hs2 = HashSet(["Jake", "Alan", "Shane"])
union = hs1.union(hs2)
assert union.size == 5
assert union.contains("Melody") == True
assert union.contains("Erik") == True
assert union.contains("Jake") == True
assert union.contains("Alan") == True
assert union.contains("Shane") == True
assert union.contains("Bob") == False
def test_is_subset(self):
hs1 = HashSet(["Jake", "Jeff", "Shane", "Fre"])
hs2 = HashSet(["Jeff", "Shane"])
is_subset = hs1.is_subset(hs2)
assert is_subset == True
hs3 = HashSet(["Jeff", "Shane", "Alec"])
is_subset2 = hs1.is_subset(hs3)
assert is_subset2 == False
def createConcordance(inputFile, stopWords, outputFile):
#declare data structures
stopSet = HashSet(3500)
dictionary = HashDictionary(10000)
bst = BST()
#declare regular expressions
newLine = re.compile(r'\n')
exprSpaces = re.compile(r'\s')
dhyp = re.compile('--')
notChars = re.compile('\W|-')
#populate hashset with stop words
stopWords = open(stopWords, 'r')
for stop in stopWords:
x = newLine.search(stop)
stop = stop[:x.start()]
if stop == "":
break
stopSet.add(stop)
stopWords.close()
#open the input and process into words
f = open(inputFile, 'r')
lineNum = 0
while True:
line = f.readline()
lineNum += 1
if line == "":
break
#split lines
m = dhyp.split(line)
alist = []
for i in range(len(m)):
g = exprSpaces.split(m[i])
alist = alist + g
#strip down to words
print alist
for word in alist:
if word == None:
pass
else:
word = string.lower(word)
while True:
n = notChars.search(word)
if len(word) <= 0:
break
elif n != None:
if n.start() == 0:
word = word[n.end():]
else:
word = word[:n.start()]
else:
break
#check if word is stop word
if not stopSet.contains(word) and len(word) > 0:
#if word isn't already in dictionary
if dictionary.search(word) == None:
linkedValue = LinkedIndexedList()
dictionary.store(word, linkedValue)
dictionary.search(word).append(lineNum)
bst.add(word)
#if the word is in the dictionary
else:
dictionary.search(word).append(lineNum)
f.close()
#open output and use BST to print out words
# in alphabetical order
output = open(outputFile, 'w')
lyst = bst.inorder()
temp = None
for item in lyst:
temp = dictionary.search(item)
output.write(item + " - " + str(temp)+"\n")
output.close()
def setUp(self):
self.set = HashSet()
class HashSetTest(unittest.TestCase):
def setUp(self):
self.set = HashSet()
def test_find(self):
phone1 = Phone('017-0774-1234-5678', 'Maria')
phone2 = Phone('112-4567-1122-9740', 'Sasha')
phone3 = Phone('150-2570-7171-7575', 'Helen')
self.set.add(phone1)
self.set.add(phone2)
self.set.add(phone3)
self.assertTrue(self.set.find(phone1))
self.assertTrue(self.set.find(phone2))
self.assertTrue(self.set.find(phone3))
self.assertFalse(self.set.find(Phone('123', 'test')))
def test_remove(self):
phone1 = Phone('017-0774-1234-5678', 'Maria')
phone2 = Phone('112-4567-1122-9740', 'Sasha')
phone3 = Phone('150-2570-7171-7575', 'Helen')
self.set.add(phone1)
self.set.add(phone2)
self.set.add(phone3)
self.assertEqual('Maria', self.set.remove(phone1).name)
self.assertEqual('Sasha', self.set.remove(phone2).name)
self.assertEqual('Helen', self.set.remove(phone3).name)
self.assertIsNone(self.set.remove(Phone('123', 'test')))
def test_remove(self):
hs = HashSet(["Shane", "Alan", "Laurel"])
assert hs.size == 3
assert hs.contains("Shane") == True
assert hs.contains("Alan") == True
assert hs.contains("Laurel") == True
hs.remove("Alan")
assert hs.size == 2
assert hs.contains("Alan") == False
assert hs.contains("Shane") == True
assert hs.contains("Laurel") == True
hs.remove("Shane")
assert hs.size == 1
assert hs.contains("Alan") == False
assert hs.contains("Shane") == False
assert hs.contains("Laurel") == True
hs.remove("Laurel")
assert hs.size == 0
assert hs.contains("Alan") == False
assert hs.contains("Shane") == False
assert hs.contains("Laurel") == False
def test_add(self):
hs = HashSet()
assert hs.size == 0
hs.add("Shane")
assert hs.size == 1
assert hs.contains("Shane") == True
assert hs.contains("Alan") == False
assert hs.contains("Bob") == False
hs.add("Alan")
assert hs.size == 2
assert hs.contains("Shane") == True
assert hs.contains("Alan") == True
assert hs.contains("Bob") == False
def test_init_edge_cases(self):
hs = HashSet(["", 1, None])
assert hs.size == 2
assert hs.contains("") == True
def test_filled_init(self):
hs = HashSet(["Shane", "Alan"])
assert hs.size == 2
assert hs.contains("Alan") == True
assert hs.contains("Bob") == False
def test_empty_init(self):
hs = HashSet()
assert hs.size == 0