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 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 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_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