def test_str_to_list():
table = htable(5)
htable_put(table, "parrt", [2, 99, 3942])
htable_put(table, "tombu", [6, 3, 1024, 99, 102342])
assert htable_str(
table) == "{tombu:[6, 3, 1024, 99, 102342], parrt:[2, 99, 3942]}"
assert htable_buckets_str(table) == """0000->
def myhtable_create_index(files):
"""
Build an index from word to set of document indexes
This does the exact same thing as create_index() except that it uses
your htable. As a number of htable buckets, use 4011.
Returns a list-of-buckets hashtable representation.
"""
# dct_index = defaultdict() # Create an empty dict
# for file in files: # Iterate through every given file names
# s_content = get_text(file) # Turn each file name into a string content
# lst_word = words(s_content) # Turn the string content into a list of normalized words
# for word in lst_word: # For each normalized words, update the dict by word-file as key-value pairs
# if word not in dct_index:
# dct_index[word] = {file} # If the key doesn't exist, create one
# else:
# dct_index[word].add(file) # If the key exist, add the file name into the set of the file names under that word
# return dct_index
NBUCKETS = 4011
table = htable(NBUCKETS) # Create an empty dict
for idx,fname in enumerate(files): # Iterate through every given file names
s_content = get_text(fname) # Turn each file name into a string content
lst_word = words(s_content) # Turn the string content into a list of normalized words
for word in lst_word: # For each normalized words, update the dict by word-file as key-value pairs
set_IDs = htable_get(table, word)
if set_IDs == None:
htable_put(table, word, {idx}) # index or file name
else:
set_IDs.add(idx)
return table
def test_a_few():
table = htable(5)
for i in range(1, 11):
htable_put(table, i, i)
s = htable_str(table)
assert s == "{5:5, 10:10, 1:1, 6:6, 2:2, 7:7, 3:3, 8:8, 4:4, 9:9}"
s = htable_buckets_str(table)
assert s == """0000->5:5, 10:10
def test_str_to_set():
table = htable(5)
htable_put(table, "parrt", {2, 99, 3942})
htable_put(table, "tombu", {6, 3, 1024, 99, 102342})
assert htable_str(
table
) == "{tombu:set([1024, 3, 99, 6, 102342]), parrt:set([2, 99, 3942])}"
assert htable_buckets_str(table) == """0000->
def test_int_to_int():
table = htable(5)
for i in range(1, 11):
htable_put(table, i, i)
s = htable_str(table)
assert s=="{5:5, 10:10, 1:1, 6:6, 2:2, 7:7, 3:3, 8:8, 4:4, 9:9}"
s = htable_buckets_str(table)
assert s == """0000->5:5, 10:10
def myhtable_create_index(files):
wordBook = htable(4011)
fileIndex = 0
for item in files:
fileWords = set(words(get_text(item)))
for word in fileWords:
htable_put(wordBook,word, fileIndex)
fileIndex += 1
return wordBook
def test_str_to_str():
table = htable(5)
htable_put(table, "a", "x")
htable_put(table, "b", "y")
htable_put(table, "c", "z")
htable_put(table, "f", "i")
htable_put(table, "g", "j")
htable_put(table, "k", "k")
s = htable_str(table)
assert s == '{a:x, f:i, k:k, b:y, g:j, c:z}', "found " + s
s = htable_buckets_str(table)
assert s == """0000->
def test_str_to_str():
table = htable(5)
htable_put(table, "a", "x")
htable_put(table, "b", "y")
htable_put(table, "c", "z")
htable_put(table, "f", "i")
htable_put(table, "g", "j")
htable_put(table, "k", "k")
s = htable_str(table)
assert s=='{a:x, f:i, k:k, b:y, g:j, c:z}', "found "+s
s = htable_buckets_str(table)
assert s == """0000->
def test_replace_str():
table = htable(5)
htable_put(table, "a", "x")
htable_put(table, "b", "y")
htable_put(table, "a", "z")
htable_put(table, "a", "i")
htable_put(table, "g", "j")
htable_put(table, "g", "k")
s = htable_str(table)
assert s == '{a:i, b:y, g:k}', "found " + s
s = htable_buckets_str(table)
assert s == """0000->
def test_replace_str():
table = htable(5)
htable_put(table, "a", "x")
htable_put(table, "b", "y")
htable_put(table, "a", "z")
htable_put(table, "a", "i")
htable_put(table, "g", "j")
htable_put(table, "g", "k")
s = htable_str(table)
assert s == '{a:i, b:y, g:k}', "found " + s
s = htable_buckets_str(table)
assert s == """0000->
def myhtable_create_index(files):
"""
Build an index from word to set of document indexes
This does the exact same thing as create_index() except that it uses
your htable. As a number of htable buckets, use 4011.
Returns a list-of-buckets hashtable representation.
"""
nbuckets = 4011
table = htable(nbuckets)
for value in range(0, len(files)):
terms = get_text(files[value])
terms = words(terms)
for key in terms:
table = htable_put(table, key, {value})
return table
def myhtable_create_index(files):
"""
Build an index from word to set of document indexes
This does the exact same thing as create_index() except that it uses
your htable. As a number of htable buckets, use 4011.
Returns a list-of-buckets hashtable representation.
"""
d = htable(4011) # initialize empty htable
# k = 0
for k, file in enumerate(files): # loop through files
# k = k + 1
wordsInDoc = words(get_text(file))
# print("len doc {:<4d}: {:<6d}".format(k, len(wordsInDoc)))
for word in wordsInDoc: # loop through words in that file
htable_put(d, word, {files[k]})
# print("word {:d} ({:<14s}), doc {:d}".format(i+1, word, k)) # warning: x6 runtime!
#pp = pprint.PrettyPrinter(indent=4)
#pp.pprint(d)
return d
def myhtable_create_index(files):
"""
Build an index from word to set of document indexes
This does the exact same thing as create_index() except that it uses
your htable. As a number of htable buckets, use 4011.
Returns a list-of-buckets hashtable representation.
"""
wordlist = [words(get_text(files[i])) for i in range(len(files))]
table = htable(4011)
for i in range(len(files)):
for j in range(len(wordlist[i])):
htable_put(table, wordlist[i][j], set())
for i in range(len(files)):
for j in range(len(wordlist[i])):
htable_get(table, wordlist[i][j]).add(i)
return table
def myhtable_create_index(files):
"""
Build an index from word to set of document indexes
This does the exact same thing as create_index() except that it uses
your htable. As a number of htable buckets, use 4011.
Returns a list-of-buckets hashtable representation.
"""
if len(files) <= 0:
return None
table = htable(4011)
for i in range(len(files)):
file_content = get_text(files[i])
key_words = words(file_content)
for word in key_words:
# because the value is a set, whenever a value
# is added to hash table here, if the key is
# is already in the hash table, the new value
# is going to merged to the existing value.
htable_put(table, word, set([i]))
return table
def test_empty():
table = htable(5)
assert htable_str(table) == "{}"
assert htable_buckets_str(table) == """0000->
def test_str_to_set():
table = htable(5)
htable_put(table, "parrt", {2, 99, 3942})
htable_put(table, "tombu", {6, 3, 1024, 99, 102342})
assert htable_str(table) == "{tombu:set([1024, 3, 99, 6, 102342]), parrt:set([2, 99, 3942])}"
assert htable_buckets_str(table) == """0000->
def test_str_to_list():
table = htable(5)
htable_put(table, "parrt", [2, 99, 3942])
htable_put(table, "tombu", [6, 3, 1024, 99, 102342])
assert htable_str(table) == "{tombu:[6, 3, 1024, 99, 102342], parrt:[2, 99, 3942]}"
assert htable_buckets_str(table) == """0000->
def test_singleon():
table = htable(5)
htable_put(table, "parrt", set([99]))
assert htable_str(table) == "{parrt:set([99])}"
assert htable_buckets_str(table) == """0000->
def test_empty():
table = htable(5)
assert htable_str(table) == "{}"
assert htable_buckets_str(table) == """0000->
def test_singleton():
table = htable(5)
htable_put(table, "parrt", set([99]))
assert htable_str(table) == "{parrt:{99}}"
assert htable_buckets_str(table) == """0000->
def test_single():
table = htable(5)
htable_put(table, "parrt", 99)
assert htable_str(table) == "{parrt:99}"
assert htable_buckets_str(table) == """0000->
def test_single():
table = htable(5)
htable_put(table, "parrt", 99)
assert htable_str(table) == "{parrt:99}"
assert htable_buckets_str(table) == """0000->
