2023-11-16 21:40:35 +01:00
|
|
|
import sys
|
|
|
|
|
2023-11-21 17:14:36 +01:00
|
|
|
def write_answer(row, answer):
|
|
|
|
with open(output_file, 'a', encoding='utf-8') as file:
|
|
|
|
file.write(row.strip()+';'+answer+'\n')
|
2023-11-16 21:40:35 +01:00
|
|
|
|
|
|
|
def line_checking(row, position):
|
2023-11-21 17:14:36 +01:00
|
|
|
stack = [(row, position)]
|
|
|
|
help_row, help_position=row,position
|
|
|
|
while stack:
|
|
|
|
help_row, help_position = stack.pop()
|
|
|
|
if help_row == '':
|
|
|
|
help_row = '\n'
|
|
|
|
next_character_array = find_next_position(help_position, help_row[0])
|
|
|
|
if next_character_array:
|
|
|
|
for element_in_next_position_array in next_character_array:
|
|
|
|
stack.append((help_row[1:], element_in_next_position_array))
|
|
|
|
if help_row == '\n':
|
|
|
|
next_character_array = find_next_position(help_position, ';')
|
|
|
|
if next_character_array:
|
|
|
|
help_position_array, character_array = find_character_after_semicolon(next_character_array[0])
|
|
|
|
character_array = sorted(character_array)
|
|
|
|
help_position_array = sorted(help_position_array)
|
|
|
|
for i in range(len(character_array)):
|
2023-11-16 21:40:35 +01:00
|
|
|
|
2023-11-21 17:14:36 +01:00
|
|
|
ended_answer = find_position_to_print_the_answer(help_position_array[i], character_array[i])
|
|
|
|
write_answer(row,ended_answer)
|
|
|
|
else:
|
|
|
|
write_answer(row, 'OOV')
|
|
|
|
# return False
|
2023-11-16 21:40:35 +01:00
|
|
|
|
2023-11-21 17:14:36 +01:00
|
|
|
def find_position_to_print_the_answer(position, character):
|
|
|
|
with open(used_table, 'r', encoding='utf-8') as readed_used_table:
|
|
|
|
last_pos = position
|
|
|
|
word = character
|
|
|
|
# if last_pos == what_is_the_ended_positions():
|
|
|
|
# return word
|
|
|
|
for row_used_table in readed_used_table:
|
|
|
|
line = row_used_table.strip().split('\t')
|
|
|
|
if len(line) != 1:
|
|
|
|
if last_pos == line[0]:
|
|
|
|
word+=line[2]
|
|
|
|
last_pos = line[1]
|
|
|
|
return word
|
|
|
|
def find_character_after_semicolon(position):
|
|
|
|
with open(used_table, 'r', encoding='utf-8') as readed_used_table:
|
|
|
|
last_position = []
|
|
|
|
take_all_possible_characters = []
|
|
|
|
for row_used_table in readed_used_table:
|
|
|
|
line = row_used_table.strip().split('\t')
|
|
|
|
if len(line) != 1:
|
|
|
|
if position == line[0]:
|
|
|
|
take_all_possible_characters.append(line[2])
|
|
|
|
last_position.append((line[1]))
|
|
|
|
return last_position,take_all_possible_characters
|
2023-11-16 21:40:35 +01:00
|
|
|
def find_next_position(position, character):
|
2023-11-21 17:14:36 +01:00
|
|
|
with open(used_table, 'r', encoding='utf-8') as readed_used_table:
|
2023-11-16 21:40:35 +01:00
|
|
|
take_all_possible_positions = []
|
|
|
|
for row_used_table in readed_used_table:
|
2023-11-21 17:14:36 +01:00
|
|
|
line = row_used_table.strip().split('\t')
|
2023-11-16 21:40:35 +01:00
|
|
|
if len(line) != 1:
|
2023-11-21 17:14:36 +01:00
|
|
|
|
2023-11-16 21:40:35 +01:00
|
|
|
if position == line[0] and character == line[2]:
|
|
|
|
take_all_possible_positions.append(line[1])
|
|
|
|
return take_all_possible_positions
|
2023-11-21 17:14:36 +01:00
|
|
|
|
2023-11-16 21:40:35 +01:00
|
|
|
def what_is_the_ended_positions():
|
|
|
|
array = []
|
|
|
|
with open(used_table, 'r') as file:
|
|
|
|
for row in file:
|
|
|
|
line = row.strip().split('\t')
|
2023-11-21 17:14:36 +01:00
|
|
|
if len(line) == 1:
|
2023-11-16 21:40:35 +01:00
|
|
|
array += line
|
|
|
|
return array
|
2023-11-21 17:14:36 +01:00
|
|
|
|
2023-11-21 17:15:47 +01:00
|
|
|
# used_table = 'multi.arg'
|
|
|
|
# input_file = 'multi.in'
|
|
|
|
# output_file = 'multi.out'
|
|
|
|
used_table = sys.argv[1]
|
|
|
|
input_file = sys.argv[2]
|
|
|
|
output_file = sys.argv[3]
|
2023-11-21 17:14:36 +01:00
|
|
|
with open(output_file, 'w', encoding='utf-8') as readed_output_file:
|
|
|
|
with open(input_file, 'r', encoding='utf-8') as readed_input_file:
|
2023-11-16 21:40:35 +01:00
|
|
|
for row_input_file in readed_input_file:
|
2023-11-21 17:14:36 +01:00
|
|
|
line_checking(row_input_file, '0')
|
|
|
|
|