import sys import csv from tokenize import Comment from numpy import append DEBUG = False alfabet = "xyz" sys.setrecursionlimit(4100) def print_debug(*args, **kwargs): if DEBUG: print(*args, **kwargs) if len(sys.argv) == 1: print("Default arguments parsed\n") sys.argv.append("long.arg") sys.argv.append("long.in") sys.argv.append("long.exp") with open(sys.argv[1], mode="r", newline="", encoding="utf8") as csvfile: filereader = csv.reader(csvfile, delimiter="\t", quotechar="|") fsa_description = list(filereader) # skip first line with comment if fsa_description[0][0][0] == "#": fsa_description = fsa_description[1:] # get accepting states accepting_state = [] for item in reversed(fsa_description): if len(item) == 1: accepting_state.append(item[0]) else: break fsa_description = fsa_description[: -len(accepting_state)] fsa_description_map = {} is_error = False for num, item in enumerate(fsa_description): for letter in item[2]: if letter not in alfabet: print_debug( "WARNING - letter not in alfabet: ", letter, "| line:", num + 1 ) if (item[0], letter) in fsa_description_map: print_debug( f"WARNING - duplicate letter: key = ({item[0]} | {letter}) | line: {num + 1}" ) fsa_description_map[tuple].append(item[1]) tuple = (item[0], letter) # fsa_description_map[tuple].append(item[1]) fsa_description_map[tuple] = [item[1]] if is_error: exit(-1) states = {} for item in fsa_description_map: states[item[0]] = states[item[0]] + item[1] if item[0] in states else item[1] from collections import Counter # check if all letters are used once def is_permutation(str1, str2): return Counter(str1) == Counter(str2) def find_missing_letters(str1, str2) -> str: missing_letters = "" for char in str2: if char not in str1: missing_letters += char return missing_letters for state in states: if not is_permutation(states[state], alfabet): print_debug( f"WARNING - state {state} doesn't match full alphabet: {states[state]} | {alfabet} | diff - {find_missing_letters(states[state], alfabet)}" ) # exit(-1) with open(sys.argv[2], mode="r", newline="", encoding="utf8") as file: content = file.read() test_in = content.splitlines() with open(sys.argv[3], mode="r", newline="", encoding="utf8") as file: content = file.read() test_out = content.splitlines() def is_correct(current_state: str) -> bool: if current_state in accepting_state: return True return False def traverse_states(current_state: str, word: str) -> str: for letter in word: if (current_state, letter) in fsa_description_map: next_states = fsa_description_map[(current_state, letter)] for next_state in next_states: ending_state = traverse_states(next_state, word[1:]) if is_correct(ending_state): return ending_state # found a correct state return "-2" # no correct state found else: return "-1" # unspecified next state return current_state # end of the word is_difference = [] for i, word in enumerate(test_in): current_state = "0" if len(word) != 0: current_state = traverse_states(current_state, word) print(str(i + 1) + "\t", end="") if current_state in accepting_state: print("YES\t", end="") if "YES" != test_out[i]: print("ERROR", word, end="") is_difference.append(i + 1) else: print("NO\t", end="") if "NO" != test_out[i]: print("ERROR", word, end="") is_difference.append(i + 1) print() if len(is_difference) != 0: print(is_difference)