def test_init(self):
with self.vis("empty init"):
x = task1.HashTable()
with self.vis("init with size and base"):
z = task1.HashTable(800, 2398)
assert self.check_okay("init")
def test_load(self):
with self.vis():
table = task1.HashTable()
task2.load_dictionary(table, "words_simple.txt", 10)
self.assertEqual(count_nonempty_buckets(table), 6)
with self.vis():
table = task1.HashTable()
task2.load_dictionary(table, "words_empty.txt", 10)
self.assertEqual(count_nonempty_buckets(table), 11,
"Failed to handle empty line or whitespace.")
self.assertTrue(self.check_okay("load_dictionary"))
myTable = task1.HashTable()
# test to see if it can load my own file
task2.load_dictionary(myTable, "testFile3.txt", 10)
# test to see if no duplicate data stored
self.assertEqual(count_nonempty_buckets(myTable), 12,
"If key is the same, should overwrite")
# new file contains unique words, this should be added onto the hashtable
task2.load_dictionary(myTable, "anotherTestFile.txt", 10)
self.assertEqual(count_nonempty_buckets(myTable), 15,
"If loaded again, should not overwrite")
# should throw an error if cant find file
with self.assertRaises(
FileNotFoundError,
msg="Shouldn't be able to read non existant files"):
task2.load_dictionary(myTable, "thisshouldntexist.txt", 10)
def test_load_timeout(self):
with self.vis("load without max_time"):
table = task1.HashTable()
task2.load_dictionary(table, "words_simple.txt")
with self.vis("failed to apply timeout"):
table = task1.HashTable(100000, 1)
with self.assertRaises(
Exception, msg="reading too many words should time out."):
try:
self.with_deadline(3, task2.load_dictionary,
(table, "english_small.txt", 1))
except TimedOutExn_:
pass
self.assertTrue(self.check_okay("load_dictionary timeout"))
myTable = task1.HashTable(7, 1)
# should not crash even if rehashing table
task2.load_dictionary(myTable, "testFile3.txt", 10)
# should not be able to read words with a time of 0 (tests limits of timer)
with self.assertRaises(
Exception, msg="Reading words on a timer of 0 shouldn't work"):
task2.load_dictionary(myTable, "testFile3.txt", 0)
def test_load(self):
with self.vis():
table = task1.HashTable()
task2.load_dictionary(table, "words_simple.txt", 10)
self.assertEqual(count_nonempty_buckets(table), 6)
with self.vis():
table = task1.HashTable()
task2.load_dictionary(table, "words_empty.txt", 10)
self.assertEqual(count_nonempty_buckets(table), 11,
"Failed to handle empty line or whitespace.")
self.assertTrue(self.check_okay("load_dictionary"))
def test_hash(self):
x = task1.HashTable(1024, 1)
for (key, expect) in [("", 0),
("abcdef", 597),
("defabc", 597)]:
self.assertEqual(x.hash(key), expect, msg=f"Unexpected hash with base 1 and key {key}.")
x = task1.HashTable(1024, 17)
for (key, expect) in [("", 0),
("abcdef", 389),
("defabc", 309)]:
self.assertEqual(x.hash(key), expect, msg=f"Unexpected hash with base 17 and key {key}.")
def test_contains(self):
x = task1.HashTable(1024, 1)
with self.vis():
self.assertFalse(
"abcdef" in x,
"False positive in __contains__ for empty table.")
with self.vis("unexpected failure in setitem"):
x["abcdef"] = 18
x["definitely a string"] = None
x["abdcef"] = "abcdef"
for key in ["abcdef", "definitely a string", "abdcef"]:
with self.vis():
self.assertTrue(
key in x,
"False negative in __contains__ for key {}".format(key))
assert self.check_okay("contains")
testTable = task1.HashTable()
# test to see if can check whether hash contains correct value
testTable["james"] = 5
self.assertEqual(testTable["james"], 5, msg="Contains failure")
# checks to see if inserting will increment counter by 1
self.assertEqual(testTable.count,
1,
msg="Not inserting elements correctly")
# test to see if it can retrieve replaced element
testTable["james"] = 7
self.assertEqual(testTable["james"], 7, msg="Failure to replace")
self.assertEqual(testTable.count,
1,
msg="Not inserting elements correctly")
# test to see if contains can correctly find keys
self.assertTrue("james" in testTable, msg="Contains is incorrect")
self.assertFalse("jamess" in testTable, msg="Contains is incorrect")
# test to see if contains can correctly find keys when updated
testTable["jamess"] = 4
self.assertTrue("jamess" in testTable, msg="Contains is incorrect")
# test to see if count will further update
self.assertFalse(testTable.count == 1,
msg="Should change count when element inserted")
def test_hash(self):
x = task1.HashTable(1024, 17)
for (key, expect) in [("", 0), ("abcdef", 389), ("defabc", 309)]:
with self.vis():
self.assertEqual(
x.hash(key),
expect,
msg=f"Unexpected hash with base 17 and key {key}.")
assert self.check_okay("hash")
# checks to see if it rejects key integers
with self.assertRaises(TypeError, msg="can't hash integers"):
x.hash(100)
# checks to see if hashing formula is correct
self.assertFalse("((" == "P",
msg="Hashes should not add to same value")
self.assertEqual(
x.hash("(("),
720,
msg="multiple digits should evaluate to correct value")
self.assertEqual(x.hash("P"),
80,
msg="values should be from correct ASCII table value")
def test_load_timeout(self):
with self.vis("load without max_time"):
table = task1.HashTable()
task2.load_dictionary(table, "words_simple.txt")
with self.vis("failed to apply timeout"):
table = task1.HashTable(100000, 1)
with self.assertRaises(
Exception, msg="reading too many words should time out."):
try:
self.with_deadline(3, task2.load_dictionary,
(table, "english_small.txt", 1))
except TimedOutExn_:
pass
self.assertTrue(self.check_okay("load_dictionary timeout"))
def test_getitem(self):
x = task1.HashTable(1024, 1)
with self.vis():
with self.assertRaises(
KeyError,
msg="x[key] should raise KeyError for missing key."):
elt = x["abcdef"]
with self.vis("unexpected failure in setitem"):
x["abcdef"] = 18
x["definitely a string"] = None
with self.vis():
self.assertEqual(x["abcdef"], 18, msg="Read after store failed.")
x["abdcef"] = 22
assert self.check_okay("getitem")
testTable = task1.HashTable()
# "!" = 33, 33/11=0
testTable["!"] = 328
# test to see if it can get correct value with specified key
self.assertEqual(testTable["!"],
328,
msg="Not retrieving hash values correctly")
# test to see if unique keys with same hash remainder wont interfere with eachother
with self.assertRaises(
KeyError,
msg=
"Different keys with same remainder shouldnt return same value"
):
# "7" = 55, 55/11=0
test = testTable["7"]
testTable["7"] = 232
# test to see if it can retrieve the correct value even if remainders are same
self.assertEqual(testTable["7"],
232,
msg="Not retrieving updated values on hash table")
def test_hash(self):
x = task1.HashTable(1024, 17)
for (key, expect) in [("", 0), ("abcdef", 389), ("defabc", 309)]:
with self.vis():
self.assertEqual(
x.hash(key),
expect,
msg=f"Unexpected hash with base 17 and key {key}.")
assert self.check_okay("hash")
def test_contains(self):
x = task1.HashTable(1024, 1)
self.assertFalse("abcdef" in x, "False positive in __contains__ for empty table.")
x["abcdef"] = 18
x["definitely a string"] = None
x["abdcef"] = "abcdef"
for key in ["abcdef", "definitely a string", "abdcef"]:
self.assertTrue(key in x, f"False negative in __contains__ for key {key}")
self.assertFalse("defabc" in x, "False positive due to collision.")
def test_getitem(self):
x = task1.HashTable(1024, 1)
with self.vis():
with self.assertRaises(
KeyError,
msg="x[key] should raise KeyError for missing key."):
elt = x["abcdef"]
with self.vis("unexpected failure in setitem"):
x["abcdef"] = 18
x["definitely a string"] = None
with self.vis():
self.assertEqual(x["abcdef"], 18, msg="Read after store failed.")
x["abdcef"] = 22
assert self.check_okay("getitem")
def test_getitem(self):
x = task1.HashTable(1024, 1)
with self.assertRaises(KeyError, msg="x[key] should raise KeyError for missing key."):
elt = x["abcdef"]
x["abcdef"] = 18
x["definitely a string"] = None
self.assertEqual(x["abcdef"], 18, msg = "Read after write failed.")
self.assertEqual(x["definitely a string"], None, "Failed to retrieve written None.")
x["abdcef"] = 22
self.assertEqual(x["abcdef"], 18, msg = "Key overwritten by colliding value.")
self.assertEqual(x["abdcef"], 22, msg = "Failed to write colliding value.")
with self.assertRaises(KeyError, msg="False positive from colliding key."):
elt = x["defabc"]
def test_rehash(self):
assert self.check_okay("rehash")
testTable = task1.HashTable(2)
# checks to see if initial hashtable size is correct
self.assertEqual(testTable.length,
2,
msg="Incorrect initialized hashtable size")
testTable["test"] = 0
# test to see if rehash calls correctly
self.assertFalse(testTable.length == 7,
msg="should not extend until full")
testTable["test2"] = 0
testTable["fff"] = 0
# test to see if rehashes when full
self.assertEqual(
testTable.length,
7,
msg="Failure rehashing when inserting into full table")
def test_contains(self):
x = task1.HashTable(1024, 1)
with self.vis():
self.assertFalse(
"abcdef" in x,
"False positive in __contains__ for empty table.")
with self.vis("unexpected failure in setitem"):
x["abcdef"] = 18
x["definitely a string"] = None
x["abdcef"] = "abcdef"
for key in ["abcdef", "definitely a string", "abdcef"]:
with self.vis():
self.assertTrue(
key in x,
"False negative in __contains__ for key {}".format(key))
assert self.check_okay("contains")
def load_dictionary_time(hash_base, table_size, filename, max_time):
start_time = time.time()
# Create new hash table
X = task1.HashTable(table_size, hash_base)
try:
# Loas the dictionary
load_dictionary(X, filename, max_time)
except Exception as e:
# If there is timeout error then return None
return None, None
# Findout the execution time
end_time = time.time()
exe_time = (end_time - start_time)
# If execution time is greater than the maxtime then
# return None, None
if exe_time > max_time:
return None, None
return (X.count, exe_time)
def load_dictionary(hash_table, filename, time_limit=100):
start = timeit.default_timer()
file = open(filename, 'r')
print("strings in the file: '")
for line in file:
val = line.strip('\n')
print(len(val))
hash_table[line.strip()] = 1
time_taken = timeit.default_timer() - start
if time_taken > time_limit:
raise ValueError('too long bro.')
file.close()
print("'")
return time_taken
def load_dictionary_time(hash_base, table_size, filename, max_time):
pass
#returns (words, time)
#if time > max_time, then time is None
table = task1.Hashtable(hash_base, table_size)
def table_load_dictionary_time(max_time):
pass
h = task1.HashTable(7, 3)
load_dictionary(h, 'words_empty.txt')
print(h.array)
def test_init(self): x = task1.HashTable() y = task1.HashTable(10) z = task1.HashTable(800, 2398)