99 lines
2.9 KiB
Python
99 lines
2.9 KiB
Python
![]() |
import string
|
||
|
import sys
|
||
|
import csv
|
||
|
import os
|
||
|
from more_itertools import difference
|
||
|
|
||
|
from numpy import append
|
||
|
|
||
|
DIR = os.path.dirname(__file__)
|
||
|
alfabet = "abcdefghijklmnopqrstuvwxyz "
|
||
|
|
||
|
|
||
|
def join_path(filename: str) -> str:
|
||
|
return os.path.join(DIR, filename)
|
||
|
|
||
|
|
||
|
if len(sys.argv) == 1:
|
||
|
print("Default arguments parsed\n")
|
||
|
sys.argv.append("fsa_description.arg")
|
||
|
sys.argv.append("shakespeare_ascii_lower.in")
|
||
|
sys.argv.append("shakespeare_ascii_lower.exp")
|
||
|
|
||
|
with open(join_path(sys.argv[1]), "r", newline="", encoding="utf8") as csvfile:
|
||
|
filereader = csv.reader(csvfile, delimiter="\t", quotechar="|")
|
||
|
fsa_description = list(filereader)
|
||
|
accepting_state = int(fsa_description[-1][0])
|
||
|
fsa_description = fsa_description[:-1]
|
||
|
fsa_description_map = {}
|
||
|
for num, item in enumerate(fsa_description):
|
||
|
for letter in item[2]:
|
||
|
if letter not in alfabet:
|
||
|
print("ERROR - letter not in alfabet: ", letter, "| line:", num + 1)
|
||
|
exit(-1)
|
||
|
if (int(item[0]), letter) in fsa_description_map:
|
||
|
print("ERROR - duplicate letter:", letter, "| line:", num + 1)
|
||
|
exit(-1)
|
||
|
tuple = (int(item[0]), letter)
|
||
|
fsa_description_map[tuple] = int(item[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(
|
||
|
f"ERROR - state {state} doesn't match: {states[state]} | {alfabet} | diff - {find_missing_letters(states[state], alfabet)}"
|
||
|
)
|
||
|
exit(-1)
|
||
|
|
||
|
|
||
|
with open(join_path(sys.argv[2]), "r", newline="", encoding="utf8") as csvfile:
|
||
|
filereader = csv.reader(csvfile, delimiter="\t", quotechar="|")
|
||
|
test_in = list(filereader)
|
||
|
|
||
|
with open(join_path(sys.argv[3]), "r", newline="", encoding="utf8") as csvfile:
|
||
|
filereader = csv.reader(csvfile, delimiter="\t", quotechar="|")
|
||
|
test_out = list(filereader)
|
||
|
|
||
|
|
||
|
difference = []
|
||
|
for i, word in enumerate(test_in):
|
||
|
current_state = 0
|
||
|
if len(word) != 0:
|
||
|
for letter in word[0]:
|
||
|
current_state = fsa_description_map[(current_state, letter)]
|
||
|
|
||
|
print(str(i + 1) + "\t", end="")
|
||
|
if current_state == accepting_state:
|
||
|
print("YES\t", end="")
|
||
|
if "YES" != test_out[i][0]:
|
||
|
print("ERROR", word, end="")
|
||
|
difference.append(i)
|
||
|
else:
|
||
|
print("NO\t", end="")
|
||
|
if "NO" != test_out[i][0]:
|
||
|
print("ERROR", word, end="")
|
||
|
difference.append(i)
|
||
|
print()
|
||
|
|
||
|
print(difference)
|