lex-simple/decode_sentence_splitting.py at main · koc-lab/lex-simple · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
output = "DiscourseSimplification/output_default.txt"
new_output = "uslt_final_output.txt"


f = open(output,"r")
fr = f.read()
outputs = fr.split("\n")
f.close()
refined_lines = []
"""
for line in outputs:
  flag_zero = 0
  for i in range(len(line)):
    #print(line[i-2:i]=="0\t")
    if line[i-3] == line[i-1] == "\t" and flag_zero == 0:
      print("yes")
      flag_zero = 1

      #new_line = line[i:]

      #for j in range(len(new_line)):

        #if new_line[j:j+6]=="L:LIST":

      refined_lines.append(line[i:])
      break


new_output = "newer_output.txt"
g = open(new_output,"w")
for line in refined_lines:
  g.write(line)
  if line != refined_lines[-1]:
    g.write("\n")

"""
counter = 0
flag = False
refined_lines = []
for line in outputs:
  if len(line) > 0:
    if line[0] == "#":
      if flag == True:
        refined_lines.append(sentence_lines)
      flag = True
      sentence_lines = []
      print("YES")
      counter += 1
      big_flag = True

  flag_zero = 0

  for i in range(len(line)):
    #print(line[i-2:i]=="0\t")

    #try:
    if line[i-3] == line[i-1] == "\t" and flag_zero == 0:
        print("yes")
        flag_zero = 1

        #new_line = line[i:]

        #for j in range(len(new_line)):

          #if new_line[j:j+6]=="L:LIST":

        sentence_lines.append(line[i:])
        break
    #except:
      #pass
refined_lines.append(sentence_lines)


g = open(new_output,"w")
for sent_lines in refined_lines:
  for line in sent_lines:
    g.write(line)
    if line[-1] != ".":
      g.write(".")
  if sent_lines != refined_lines[-1]:
    g.write("\n")

print(len(refined_lines))