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
|
# ----------------------------------------------------------------------
# clex.py
#
# A lexer for ANSI C.
# ----------------------------------------------------------------------
import ply.lex as lex
# Reserved words
reserved = (
'AUTO', 'BREAK', 'CASE', 'CHAR', 'CONST', 'CONTINUE', 'DEFAULT', 'DO', 'DOUBLE',
'ELSE', 'ENUM', 'EXTERN', 'FLOAT', 'FOR', 'GOTO', 'IF', 'INT', 'LONG', 'REGISTER',
'RETURN', 'SHORT', 'SIGNED', 'SIZEOF', 'STATIC', 'STRUCT', 'SWITCH', 'TYPEDEF',
'UNION', 'UNSIGNED', 'VOID', 'VOLATILE', 'WHILE',
)
tokens = reserved + (
# Literals (identifier, integer constant, float constant, string constant,
# char const)
'ID', 'TYPEID', 'ICONST', 'FCONST', 'SCONST', 'CCONST',
# Operators (+,-,*,/,%,|,&,~,^,<<,>>, ||, &&, !, <, <=, >, >=, ==, !=)
'PLUS', 'MINUS', 'TIMES', 'DIVIDE', 'MOD',
'OR', 'AND', 'NOT', 'XOR', 'LSHIFT', 'RSHIFT',
'LOR', 'LAND', 'LNOT',
'LT', 'LE', 'GT', 'GE', 'EQ', 'NE',
# Assignment (=, *=, /=, %=, +=, -=, <<=, >>=, &=, ^=, |=)
'EQUALS', 'TIMESEQUAL', 'DIVEQUAL', 'MODEQUAL', 'PLUSEQUAL', 'MINUSEQUAL',
'LSHIFTEQUAL', 'RSHIFTEQUAL', 'ANDEQUAL', 'XOREQUAL', 'OREQUAL',
# Increment/decrement (++,--)
'PLUSPLUS', 'MINUSMINUS',
# Structure dereference (->)
'ARROW',
# Conditional operator (?)
'CONDOP',
# Delimeters ( ) [ ] { } , . ; :
'LPAREN', 'RPAREN',
'LBRACKET', 'RBRACKET',
'LBRACE', 'RBRACE',
'COMMA', 'PERIOD', 'SEMI', 'COLON',
# Ellipsis (...)
'ELLIPSIS',
)
# Completely ignored characters
t_ignore = ' \t\x0c'
# Newlines
def t_NEWLINE(t):
r'\n+'
t.lexer.lineno += t.value.count("\n")
# Operators
t_PLUS = r'\+'
t_MINUS = r'-'
t_TIMES = r'\*'
t_DIVIDE = r'/'
t_MOD = r'%'
t_OR = r'\|'
t_AND = r'&'
t_NOT = r'~'
t_XOR = r'\^'
t_LSHIFT = r'<<'
t_RSHIFT = r'>>'
t_LOR = r'\|\|'
t_LAND = r'&&'
t_LNOT = r'!'
t_LT = r'<'
t_GT = r'>'
t_LE = r'<='
t_GE = r'>='
t_EQ = r'=='
t_NE = r'!='
# Assignment operators
t_EQUALS = r'='
t_TIMESEQUAL = r'\*='
t_DIVEQUAL = r'/='
t_MODEQUAL = r'%='
t_PLUSEQUAL = r'\+='
t_MINUSEQUAL = r'-='
t_LSHIFTEQUAL = r'<<='
t_RSHIFTEQUAL = r'>>='
t_ANDEQUAL = r'&='
t_OREQUAL = r'\|='
t_XOREQUAL = r'\^='
# Increment/decrement
t_PLUSPLUS = r'\+\+'
t_MINUSMINUS = r'--'
# ->
t_ARROW = r'->'
# ?
t_CONDOP = r'\?'
# Delimeters
t_LPAREN = r'\('
t_RPAREN = r'\)'
t_LBRACKET = r'\['
t_RBRACKET = r'\]'
t_LBRACE = r'\{'
t_RBRACE = r'\}'
t_COMMA = r','
t_PERIOD = r'\.'
t_SEMI = r';'
t_COLON = r':'
t_ELLIPSIS = r'\.\.\.'
# Identifiers and reserved words
reserved_map = {}
for r in reserved:
reserved_map[r.lower()] = r
def t_ID(t):
r'[A-Za-z_][\w_]*'
t.type = reserved_map.get(t.value, "ID")
return t
# Integer literal
t_ICONST = r'\d+([uU]|[lL]|[uU][lL]|[lL][uU])?'
# Floating literal
t_FCONST = r'((\d+)(\.\d+)(e(\+|-)?(\d+))? | (\d+)e(\+|-)?(\d+))([lL]|[fF])?'
# String literal
t_SCONST = r'\"([^\\\n]|(\\.))*?\"'
# Character constant 'c' or L'c'
t_CCONST = r'(L)?\'([^\\\n]|(\\.))*?\''
# Comments
def t_comment(t):
r'/\*(.|\n)*?\*/'
t.lexer.lineno += t.value.count('\n')
# Preprocessor directive (ignored)
def t_preprocessor(t):
r'\#(.)*?\n'
t.lexer.lineno += 1
def t_error(t):
print("Illegal character %s" % repr(t.value[0]))
t.lexer.skip(1)
lexer = lex.lex()
if __name__ == "__main__":
lex.runmain(lexer)
|
