def loadHashTable(name):
ch = CuckooHash(50000)
with open(name, "r") as f:
for i in f:
ch.insert([i])
return ch
def test_appendData():
CH = CuckooHash(10000)
for i in range(1000):
CH.insert("word", random.randint(1, 100))
#assert that the length of the data associated with
#the word that was inserted 1000 times is 1000
assert len(CH.find("word")[1]) == 1000
def test_allThere(): #after inserting elements we should be able to find them all.
c = CuckooHash(10) #Since the initial size is 10 and we are inserting 50 elements, if it pass this test, __growHash works
lost = 0
for i in range(50):
c.insert(str(i), str(i))
for i in range(50):
if c.find(str(i)) == None:
lost +=1
assert lost == 0
def test_randomInsert():
c = CuckooHash(10)
inserted = []
for i in range(random.randint(0,100)): #loop upto a 100 times
x = random.randint(0,100) #get a random int upto 100
if not (x in inserted): #this list is to keep track of what is supposed to be inserted (no duplicates)
inserted.append(x)
c.insert(str(x), str(x)) #try to insert x in the CuckooHash(should not insert duplicates)
assert len(inserted) == len(c) #the length of the list and the CuckooHash should be the same
def test_find():
CH = CuckooHash(10000)
words = []
for i in range(1000):
word = randWord()
CH.insert(word, random.randint(1, 100))
words.append(word)
for word in words:
assert CH.find(word)
def test__insertDouble():
c = CuckooHash(100)
c.insert("DoubleWord", 234)
c.insert("word1", 1)
c.insert("word2", 2)
c.insert("word3", 3)
assert c.insert("DoubleWord", 234) == False
def test_noDuplicates(): #Insert 20 times the same key
c = CuckooHash(20)
for i in range(20):
c.insert("A", str(i))
assert c.find("A") == "0" #it should return the data of the first inserted
c.delete("A") #After deleting("A"), if we try to find it, we shouldn't be able to because we dont have duplicates
assert c.find("A") == None #return None if it wasn't there
def test__insertMany():
c = CuckooHash(300)
file = open("wordlist.txt")
word = file.readline()
for i in range(580):
c.insert(word, 2)
word = file.readline()
file.close()
file = open(
"wordlist.txt"
) # asserts that all the data was successfully inserted and the table was properly grown
word = file.readline()
for i in range(400):
assert c.find(word) != None
word = file.readline()
file.close()
def test_delete(): #Insert numbers from 0 to 19
c = CuckooHash(1000)
for i in range(20):
c.insert(str(i), str(i))
assert len(c) == 20 #the length should be 20
for i in range(10):
c.delete(str(i)) #Delete the numbers upto 9.
assert len(c) == 10 #the final length should be 10
def test_random():
CH = CuckooHash(100)
count = 0
for i in range(10000):
choice = random.randint(0, 1)
word = randWord()
if choice == 0:
if not CH.find(word):
count += 1
CH.insert(word, word)
if choice == 1:
if CH.find(word):
count -= 1
CH.delete(word)
assert count == CH.numKeys()
def test_delete():
CH = CuckooHash(10000)
words = []
for i in range(1000):
word = randWord()
CH.insert(word, random.randint(1, 100))
words.append(word)
for word in words:
CH.delete(word)
#assert that there are zero keys in the cuckoo hash
#after deleting every key that was inserted
assert CH.numKeys() == 0
#assert that attempts to find words in the cuckoo hash fail
for i in range(100):
assert not CH.find(randWord())
def test_growHash():
CH = CuckooHash(10)
counter = 0
for i in range(10000):
word = randWord()
if CH.find(word):
counter += 1
CH.insert(word, random.randint(1, 100))
counter += CH.numKeys()
assert counter == 10000
def test__SuccessfulFind():
c = CuckooHash(400)
file = open("wordlist.txt")
word = file.readline()
for i in range(100):
c.insert(word, i)
word = file.readline()
file.close()
file = open("wordlist.txt")
word = file.readline()
for i in range(100):
assert c.find(
word
) != None # Successfully find all the words. If a word returns none then it didn't find it
assert c.find(word) == i # returns the proper data for the key
word = file.readline()
file.close()
def main():
ch = CuckooHash()
name = input("Enter the name of the file containing the required data: ")
stocks(name, ch)
display(ch)
def test__findFail():
c = CuckooHash(100)
assert c.find("Cuckoo") == None
def test_grow(): #After inserting 3 elements the array should grow because the numOfRecords>=numOfBuckets
c = CuckooHash(6)
c.insert("A", "a")
c.insert("B", "b")
c.insert("C", "c")
assert c.numOfBuckets() == 12
def test__deleteFalseKey():
c = CuckooHash(20)
assert c.delete("Delete") == None
def test__delete():
c = CuckooHash(100)
c.insert("toDelete", 44)
c.delete("toDelete")
assert c.find("toDelete") == None
def test_empty(): #cant find or delete something on an empty CuckooHash
c = CuckooHash(20)
assert c.find("A") == None
assert c.delete("A") == False
assert len(c) == 0
def test__deleteFromTable():
c = CuckooHash(400)
c.insert("a", 1)
c.insert("b", 2)
c.insert("c", 3)
c.insert("d", 4)
c.insert("e", 5)
c.insert("f", 6)
c.insert("g", 7)
c.insert("h", 8)
c.insert("i", 9)
c.delete("e")
assert c.insert("e", 5) != False
assert c.find("e") == 5
def test_insertingAll(): #Insert the numbers from 0 to 99, the final length should be 100
c = CuckooHash(100)
for i in range(100):
c.insert(str(i), str(i))
assert len(c) == 100
def AutoCorrect(word):
word=word+"\n"
filename=input("enter name of the file")
dic=CuckooHash(130)
file_obj=open(filename,"r")
for w in file_obj:
dic.insert([w])
dic.print()
print("length of tables is now",dic.len,"population is",dic.population)
result=dic.lookup(word)
if not(result):
possible_words=list()
alphabets=['a','b','c','d','e','f','g','h','i','j','k','l','m','n','o','p','q','r','s','t','u','v','w','x','y','z']
for i in range(len(word)-2,-1,-1):
#print("i is now",i)
for letter in alphabets:
new_word=list(word)
new_word[i]=letter
new_word=''.join(new_word)
#print(new_word)
isvalid=dic.lookup(new_word)
if (isvalid):
possible_words.append(new_word)
new_word2=list(word)
#print(new_word2)
new_word2.append('')
for j in range(len(word)-1,i,-1):
new_word2[j+1]=new_word2[j]
new_word2[i+1]=letter
new_word3=list(new_word2)
if i==0:
new_word3[i+1]=new_word3[i]
new_word3[i]=letter
#print(new_word3)
new_word3=''.join(new_word3)
isvalid=dic.lookup(new_word3)
if (isvalid):
possible_words.append(new_word3)
new_word2=''.join(new_word2)
#print(new_word2)
isvalid=dic.lookup(new_word2)
if isvalid:
possible_words.append(new_word2)
new_word4=list(word)
for j in range(i,len(word)-1):
new_word4[j]=new_word4[j+1]
temp=new_word4.pop()
new_word4=''.join(new_word4)
isvalid=dic.lookup(new_word4)
if isvalid:
possible_words.append(new_word4)
return possible_words
else:
#print("word exists")
return None
def test__Findtime():
# Calculate how long it takes to find 100 records in an hash table that only has 100 records in it
h = CuckooHash(1000)
file = open("wordlist.txt")
word = file.readline()
# insert 100 words from a file
for i in range(100):
h.insert(word, 2)
word = file.readline()
file.close()
file = open("wordlist.txt")
word = file.readline()
# time how long it takes to find those 100 words
tm = time.time()
for i in range(100):
h.find(word)
tm = time.time() - tm
file.close()
# ----------------------------------------
# calculate how long it takes to find 100 records in a hashTable with 300 records
c = CuckooHash(1000)
file = open("wordlist.txt")
word = file.readline()
# insert 300 records from a file
for i in range(300):
c.insert(word, 2)
word = file.readline()
file.close()
# Want it to find a different 100 words than the first time,
# So read some words first
file = open("wordlist.txt")
word = file.readline()
for i in range(150):
word = file.readline()
# time how long it takes to find 100 words
t = time.time()
for i in range(100):
c.find(word)
word = file.readline()
t = time.time() - t
file.close()
# -------------------------------------------------
# calculate how long it takes to find 100 records in a hashTable with 800 records
ck = CuckooHash(1000)
file = open("wordlist.txt")
word = file.readline()
# insert 800 words from a file
for i in range(800):
ck.insert(word, 2)
word = file.readline()
file.close()
# Want it to find a different 100 words than the other time
# So read in some words first
file = open("wordlist.txt")
word = file.readline()
for i in range(300):
word = file.readline()
# time how long it takes to find 100 words
s = time.time()
for i in range(100):
ck.find(word)
word = file.readline()
s = time.time() - s
file.close()
# Check if the times for find on the different tables sizes are the same or
# within a 20 percent acceptable difference
assert abs(t - s) <= t * 0.2
assert abs(s - tm) <= s * 0.2
assert abs(t - tm) <= t * 0.2
