diff --git a/DIRECTORY.md b/DIRECTORY.md index 01f421613..4ffd20da5 100644 --- a/DIRECTORY.md +++ b/DIRECTORY.md @@ -650,6 +650,7 @@ * [Manacher](https://github.com/TheAlgorithms/Python/blob/master/strings/manacher.py) * [Min Cost String Conversion](https://github.com/TheAlgorithms/Python/blob/master/strings/min_cost_string_conversion.py) * [Naive String Search](https://github.com/TheAlgorithms/Python/blob/master/strings/naive_string_search.py) + * [Prefix Function](https://github.com/TheAlgorithms/Python/blob/master/strings/prefix_function.py) * [Rabin Karp](https://github.com/TheAlgorithms/Python/blob/master/strings/rabin_karp.py) * [Remove Duplicate](https://github.com/TheAlgorithms/Python/blob/master/strings/remove_duplicate.py) * [Reverse Words](https://github.com/TheAlgorithms/Python/blob/master/strings/reverse_words.py) diff --git a/strings/prefix_function.py b/strings/prefix_function.py new file mode 100644 index 000000000..9e6dbbf54 --- /dev/null +++ b/strings/prefix_function.py @@ -0,0 +1,65 @@ +""" +https://cp-algorithms.com/string/prefix-function.html + +Prefix function Knuth–Morris–Pratt algorithm + +Different algorithm than Knuth-Morris-Pratt pattern finding + +E.x. Finding longest prefix which is also suffix + +Time Complexity: O(n) - where n is the length of the string +""" + + +def prefix_function(input_string: str) -> list: + """ + For the given string this function computes value for each index(i), + which represents the longest coincidence of prefix and sufix + for given substring (input_str[0...i]) + + For the value of the first element the algorithm always returns 0 + + >>> prefix_function("aabcdaabc") + [0, 1, 0, 0, 0, 1, 2, 3, 4] + >>> prefix_function("asdasdad") + [0, 0, 0, 1, 2, 3, 4, 0] + """ + + # list for the result values + prefix_result = [0] * len(input_string) + + for i in range(1, len(input_string)): + + # use last results for better performance - dynamic programming + j = prefix_result[i - 1] + while j > 0 and input_string[i] != input_string[j]: + j = prefix_result[j - 1] + + if input_string[i] == input_string[j]: + j += 1 + prefix_result[i] = j + + return prefix_result + + +def longest_prefix(input_str: str) -> int: + """ + Prefix-function use case + Finding longest prefix which is sufix as well + + >>> longest_prefix("aabcdaabc") + 4 + >>> longest_prefix("asdasdad") + 4 + >>> longest_prefix("abcab") + 2 + """ + + # just returning maximum value of the array gives us answer + return max(prefix_function(input_str)) + + +if __name__ == "__main__": + import doctest + + doctest.testmod()