Compiler/compilerProject.py at main · yasaminaali/Compiler · 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
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
import numpy as np
import pandas as pd
import re


f = open("decaf_input3.decaf", "r")
x = f.read()


Keywords = []
Operators = []
Decimals = []
Symbols = []
Identifiers = []


List_Keywords = ['def', 'if', 'else', 'while', 'return', 'break', 'continue', 'int', 'bool', 'void', 'true', 'false', 'for', 'callout', 'class', 'interface', 'extands', 'implements', 'new', 'this', 'string', 'float', 'double', 'null']
List_Symbols = ['(', '{', '[', ']', '}', ')', ',', ';', '=', '+', '-', '*', '/', '%', '<', '>', '<=', '>=', '==', '!=', '&&', '||', '!']
List_Decimals = []
List_String = []
List_Hex = []
List_Id = []

print('x', x)


def remove_Spaces(x):

    y = []
    for line in x:
        if (line.strip() != ''):
            y.append(line.strip())

    return y


def remove_Comments(x):

    Multi_Comments_Removed = re.sub("/\*[^*]*\*+(?:[^/*][^*]*\*+)*/", "", x)
    Single_Comments_Removed = re.sub("//.*", "", Multi_Comments_Removed)
    Comments_removed = Single_Comments_Removed


    return Comments_removed


Comments_removed = remove_Comments(x)
z = Comments_removed.split('\n')
z_ = remove_Spaces(z)

print('z', z)
print('z_', z_)


a = '\n'.join([str(elem) for elem in z_])
scanned_Program_lines = a.split('\n')


C = []
for line in scanned_Program_lines:
    C.append(line)

za = []
for x in C:
    za.append(x.split())

print('za', za)

# Decimal
for q in za:
    for i in q:
        if i.isdecimal():
            List_Decimals.append(i)
print('List_Decimals', List_Decimals)

# String
for q in za:
    for i in q:
        if(i.startswith('"')):
            List_String.append(i)

print(List_String)

# Identifiers
for q in za:
    for i in q:
        if(i.isidentifier()):
            List_Id.append(i)
print('List_Id', List_Id)

# Jadvale Namad

name = List_Id + List_Keywords
nemune = list(set(name))
print('nemune', nemune)

Nemune = pd.DataFrame(nemune)
print(Nemune)


# Donbale Tokens

tokens = []

for u in za:
    for i in u:
        for l in List_Keywords:
            if(i == l):
                index = nemune.index(i)
                token = ['KEY', index]
                tokens.append(token)

        for o in List_Id:
            if(i == o):
                index = nemune.index(i)
                token = ('ID', index)
                tokens.append(token)

        for m in List_Symbols:
            if(i == m):
                token = ('SYM', i)
                tokens.append(token)


        for n in List_String:
            if(i == n):
                token = ('STR', i)
                tokens.append(token)

        for p in List_Decimals:
            if(i == p):
                token = ('DEC', i)
                tokens.append(token)

        """for q in List_Hex:
            if(i == q):
                token = ('HEX', i)
                tokens.append(token)"""

print("-------------------------------------------------------")
print(tokens)

Tokens = pd.DataFrame(tokens)
print(Tokens)