-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathlexer.py
256 lines (197 loc) · 8.12 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
class Token:
def __init__(self, type, value, line):
self.type = type
self.value = value
self.line = line
def __str__(self):
return f'Token({self.type}, {repr(self.value)}, Line: {self.line})'
def __repr__(self):
return self.__str__()
class Lexer:
def __init__(self, symbol_table,text):
self.symbol_table = symbol_table
self.text = text
self.line = 1
self.beginning = 0
self.forward = 0
self.tokens = []
def error(self):
raise Exception(f"Lexical error at Line {self.line}: Unexpected character '{self.text[self.forward]}'")
def create_token(self, type):
lexeme = self.text[self.beginning:self.forward]
token = Token(type=type, value=lexeme, line=self.line)
self.tokens.append(token)
return token
def tokenize(self):
while self.forward < len(self.text):
char = self.text[self.forward]
if char == '/' and self.forward + 1 < len(self.text) and self.text[self.forward + 1] == '/':
self.is_single_line_comment()
elif char == '{':
self.is_multi_line_comment()
elif self.symbol_table.is_operator(char):
self.is_operator()
elif char.isdigit():
self.is_number()
elif char.isalpha() or char == '_':
self.is_identifier()
elif char.isspace():
self.skip_white_space()
else:
self.error()
token = Token(type="EOF", value=None, line=self.line)
self.tokens.append(token)
return self.tokens
def is_single_line_comment(self):
self.forward += 2
while self.forward < len(self.text) and self.text[self.forward] != '\n':
self.forward += 1
self.beginning = self.forward
def is_multi_line_comment(self):
self.forward += 1
while self.forward < len(self.text):
char = self.text[self.forward]
if char == '}':
self.forward += 1
self.beginning = self.forward
return
if char == '\n':
self.line += 1
self.forward += 1
self.error()
def skip_white_space(self):
while self.forward < len(self.text) and self.text[self.forward].isspace():
if self.text[self.forward] == '\n':
self.line += 1
self.forward += 1
self.beginning = self.forward
def is_number(self):
state = 0
while self.forward < len(self.text):
char = self.text[self.forward]
match (state):
case 0:
if char.isdigit():
state = 1
self.forward += 1
case 1:
if char.isdigit():
state = 1
self.forward += 1
elif char == '.':
state = 2
self.forward += 1
elif char == 'e' or char == 'E':
state = 4
self.forward += 1
elif char.isalpha() or char == '_':
state = -1
else:
state = 7
case 2:
if char.isdigit():
state = 3
else:
state = -1
self.forward += 1
case 3:
if char.isdigit():
state = 3
self.forward += 1
elif char == 'e' or char == 'E':
state = 4
self.forward += 1
else:
state = 7
case 4:
if char.isdigit():
state = 6
elif char == '+' or char == '-':
state = 5
else:
state = -1
self.forward += 1
case 5:
if char.isdigit():
state = 6
self.forward += 1
else:
state = -1
case 6:
if char.isdigit():
state = 6
self.forward += 1
else:
state = 7
case 7:
self.create_token("NUM")
self.beginning = self.forward
return
case -1:
raise Exception(f"Invalid number format at Line {self.line}")
if state in {1, 3, 6}:
self.create_token("NUM")
else:
self.error()
def is_identifier(self):
state = 0
while self.forward < len(self.text):
char = self.text[self.forward].lower()
match state:
case 0:
if char.isalpha() or char == '_':
state = 1
self.forward += 1
case 1:
if char.isalnum() or char == '_':
state = 1
self.forward += 1
else:
state = 2
case 2:
lexeme = self.text[self.beginning:self.forward].lower()
if self.symbol_table.is_operator(lexeme):
self.create_token("OPERATOR")
self.beginning = self.forward
return
elif self.symbol_table.is_function(lexeme):
self.create_token("FUNCTION")
self.beginning = self.forward
return
else:
if not self.symbol_table.is_id_existence(lexeme) and not self.symbol_table.is_reserved(lexeme):
self.symbol_table.add_id(lexeme)
self.create_token("ID")
self.beginning = self.forward
return
else:
self.create_token("ID")
self.beginning = self.forward
return
if state == 1:
lexeme = self.text[self.beginning:self.forward].lower()
if not self.symbol_table.is_id_existence(lexeme):
self.symbol_table.add_id(lexeme)
if self.symbol_table.is_function(lexeme):
self.create_token("FUNCTION")
self.beginning = self.forward
else:
if not self.symbol_table.is_id_existence(lexeme) and not self.symbol_table.is_reserved(lexeme):
self.symbol_table.add_id(lexeme)
self.create_token("ID")
self.beginning = self.forward
else:
self.create_token("ID")
self.beginning = self.forward
else:
self.error()
def is_operator(self):
for op in self.symbol_table.table:
if self.text[self.forward:self.forward + len(op)].lower() == op:
symbol_info = self.symbol_table.table[op]
if symbol_info['type'] == 'OPERATOR' or symbol_info['type'] == 'DELIMITER':
self.forward += len(op)
self.create_token(symbol_info['type'])
self.beginning = self.forward
return
self.error()