-
Notifications
You must be signed in to change notification settings - Fork 0
/
lexer.py
266 lines (221 loc) · 9.22 KB
/
lexer.py
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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
from string import ascii_uppercase, ascii_lowercase, digits
LETTERS = set(list(ascii_uppercase+ascii_lowercase))
NUMBERS = set(list(digits))
class Line:
i = 0
line = ''
def __init__(self, line):
self.line = line
def get_next(self, n_i):
return self.line[self.i+n_i] if (self.i+n_i < len(self.line)) else ''
def go_forward(self, steps):
self.i += steps
def get_actual_char(self):
if(self.i >= len(self.line)):
return None
return self.line[self.i]
def lexer(source):
tokens = []
string_text_block = False
char_text_block = False
directive_block = False
letters_block = False
numbers_block = False
text = ''
for i,line in enumerate(source):
actual_line = i+1
l = Line(line)
while(l.get_actual_char()):
found_reserved = False
char = l.get_actual_char()
if(string_text_block):
if(char == '"'):
tokens.append((text, 'text', actual_line))
tokens.append(('"', 'symbol', actual_line))
string_text_block = False
text = ''
else:
text += char
l.go_forward(1)
continue
if(char_text_block):
if(char == "'"):
tokens.append((text, 'text', actual_line))
tokens.append(("'", 'symbol', actual_line))
char_text_block = False
text = ''
else:
text += char
l.go_forward(1)
continue
if(directive_block):
if(char == '*'):
if(l.get_next(1) == "/"):
tokens.append(('*/', 'directive', actual_line))
directive_block = False
l.go_forward(1)
l.go_forward(1)
continue
if(letters_block):
if(char not in LETTERS):
letters_block = False
tokens.append((text, 'letters', actual_line))
text = ''
else:
text += char
l.go_forward(1)
continue
if(numbers_block):
if(char not in NUMBERS):
numbers_block = False
tokens.append((text, 'numbers', actual_line))
text = ''
else:
text += char
l.go_forward(1)
continue
# symbols and directives
if(not char or char in {'\t', '\n', ' '}):
l.go_forward(1)
continue
elif(char == '#'):
tokens.append((char, 'directive', actual_line))
break
elif(char in {'{', '}', ',', ';', '(', ')', '[', ']'}):
tokens.append((char, 'symbol', actual_line))
elif(char == '='):
if(l.get_next(1) == '='):
tokens.append(('==', 'symbol', actual_line))
l.go_forward(2)
continue
else:
tokens.append(('=', 'symbol', actual_line))
elif(char == '+'):
next_char = l.get_next(1)
if(next_char == '='):
tokens.append(('+=', 'symbol', actual_line))
l.go_forward(2)
continue
elif(next_char == '+'):
tokens.append(('++', 'symbol', actual_line))
l.go_forward(2)
continue
else:
tokens.append(('+', 'symbol', actual_line))
elif(char == '-'):
next_char = l.get_next(1)
if(next_char == '='):
tokens.append(('-=', 'symbol', actual_line))
l.go_forward(2)
continue
elif(next_char == '-'):
tokens.append(('--', 'symbol', actual_line))
l.go_forward(2)
continue
else:
tokens.append(('-', 'symbol', actual_line))
elif(char == '*'):
next_char = l.get_next(1)
if(next_char == '='):
tokens.append(('*=', 'symbol', actual_line))
l.go_forward(2)
continue
elif(next_char == '*'):
tokens.append(('**', 'symbol', actual_line))
l.go_forward(2)
continue
else:
tokens.append(('*', 'symbol', actual_line))
elif(char == '/'):
next_char = l.get_next(1)
if(next_char == '/'):
tokens.append(('//', 'directive', actual_line))
break
elif(next_char == '='):
tokens.append(('/=', 'symbol', actual_line))
l.go_forward(2)
continue
elif(next_char == '*'):
tokens.append(('/*', 'directive', actual_line))
l.go_forward(2)
directive_block = True
continue
else:
tokens.append(('/', 'symbol', actual_line))
elif(char == '<'):
if(l.get_next(1) == '='):
tokens.append(('<=', 'symbol' ,actual_line))
l.go_forward(2)
continue
else:
tokens.append(('<', 'symbol', actual_line))
elif(char == '>'):
if(l.get_next(1) == '='):
tokens.append(('>=', 'symbol' ,actual_line))
l.go_forward(2)
continue
else:
tokens.append(('>', 'symbol', actual_line))
elif(char == "'"):
tokens.append(("'", 'symbol', actual_line))
char_text_block = True
elif(char == '"'):
tokens.append(('"', 'symbol', actual_line))
string_text_block = True
elif(char == '!'):
if(l.get_next(1) == '='):
tokens.append(('!=', 'symbol' ,actual_line))
l.go_forward(2)
continue
# reserved
elif(char == 'm'):
found_reserved = check_reserved(l, {'main'})
if(found_reserved):
tokens.append((found_reserved, 'reserved', actual_line))
elif(char == 'e'):
found_reserved = check_reserved(l, {'else'})
if(found_reserved):
tokens.append((found_reserved, 'reserved', actual_line))
elif(char == 'i'):
reserved_starting_with_i = {'int', 'if'}
found_reserved = check_reserved(l, reserved_starting_with_i)
if(found_reserved):
tokens.append((found_reserved, 'reserved', actual_line))
elif(char == 'p'):
found_reserved = check_reserved(l, {'printf'})
if(found_reserved):
tokens.append((found_reserved, 'reserved', actual_line))
elif(char == 'v'):
found_reserved = check_reserved(l, {'void'})
if(found_reserved):
tokens.append((found_reserved, 'reserved', actual_line))
elif(char == 'c'):
found_reserved = check_reserved(l, {'char'})
if(found_reserved):
tokens.append((found_reserved, 'reserved', actual_line))
elif(char == 'f'):
reserved_starting_with_f = {'float', 'for'}
found_reserved = check_reserved(l, reserved_starting_with_f)
if(found_reserved):
tokens.append((found_reserved, 'reserved', actual_line))
if(not found_reserved and char in LETTERS):
letters_block = True
continue
if(char in NUMBERS):
numbers_block = True
continue
l.go_forward(1)
return tokens
def check_reserved(line, reserved_words):
j = 1
larger_word = len(max(reserved_words))
token = line.get_actual_char()+line.get_next(j)
while(j <= larger_word and token not in reserved_words):
j+=1
token += line.get_next(j)
if(token in reserved_words):
reserved_words_list = list(reserved_words)
line.go_forward(j)
return reserved_words_list[reserved_words_list.index(token)]
else:
return ''