def longest_strand(*args):
"""
Given a large number of binary files, this program finds the longest strand of bytes that is identical between
two or more files by constructing a Generalized Suffix Tree. The program then calls longest_strand to print the
longest strand of bytes.
:param args: a list of binary files
:return: Prints the following:
- the longest strand of bytes that is identical between two or more files
- the length of the strand
- the file names where the largest strand appears
- the offset where the strand appears in each file
"""
file_length = len(args)
file_dict = {}
if file_length < 2:
print("Error! Need more than 2 binary files.")
return
# Accessing test files in a different directory
current_directory = os.getcwd()
file_path = current_directory + '/test_samples/'
# Looping through each file and storing the file's name as the key and the hex data as the value in a dictionary
for file in args:
with open(file_path + file, 'rb') as f:
hex_data = f.read().hex()
file_dict[file] = hex_data
# Building the Suffix Tree
hex_data_list = list(file_dict.values())
s_tree = suffix_tree.SuffixTree(hex_data_list)
longest_strand, indexes, offset_list = s_tree.longest_strand()
print("The longest strand is:", longest_strand)
print("The length of the strand is:", len(longest_strand))
# Figuring out the offset where the strand appears in each file
file_names, iter_offset_list = list(file_dict.keys()), iter(offset_list)
file_length = 0
helper_list = []
for file_number in indexes:
file = file_names[file_number]
helper_list.append(file)
for file in file_names:
if file in helper_list:
print("The largest strand appears in:", file, "and the offset is",
next(iter_offset_list) - file_length)
file_length += len(file_dict[file]) + 1
def construct_tree(string):
tree = suffix_tree.SuffixTree(string + "$")
tree.update_counter()
return tree
if __name__ == '__main__':
"""
Test case to see if the Suffix Tree implementation works correctly.
Give the input list of ["33", "AA2222", "BBB2222", "CCC33333"],
Should output:
The longest strand of bytes that is identical between two or more files is: 2222
The length of the strand is: 4
The largest strand appears in file: 2 and the offset is 2
The largest strand appears in file: 3 and the offset is 3
"""
test = ["33", "AA2222", "BBB2222", "CCC33333"]
suffix_tree = suffix_tree.SuffixTree(test)
longest_strand, indexes, offset_list = suffix_tree.longest_strand()
print("The longest strand of bytes that is identical between two or more files:", longest_strand)
print("The length of the strand is:", len(longest_strand))
file_length, counter = 0, 0
iter_offset_list = iter(offset_list)
for file in test:
if counter in indexes:
print("The largest strand appears in file", counter + 1, "and the offset is",
next(iter_offset_list) - file_length)
file_length += len(file) + 1
counter += 1
import suffix_tree
#text = 'ATAAATG$'
#with open('suffixTree.txt', 'r') as f:
with open('dataset_96_5.txt', 'r') as f:
text = f.readline().strip()
tree = suffix_tree.SuffixTree()
for i in xrange(len(text)):
tree.insert(text[i:], i)
#tree.print_tree()
#print tree._nodes[0].keys()
for item in tree._nodes:
if isinstance(item, dict):
print '\n'.join(item.keys())