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
|
#!/usr/bin/python3
import ply.lex as lex
import sys
''' keep track of how many open brackets have been encountered so far '''
brackets = 0
''' keep current string in memory '''
qstring = ''
dqstring = ''
tokens = (
'EOL',
'NUMBER',
'VAR',
'DOT',
'OPERATOR',
'NOTEQUALTO',
'COMPARISON',
'COMMA',
'OPENSQBRACKET',
'CLOSESQBRACKET',
'OPENBRACKET',
'CLOSEBRACKET',
'SEMICOLON',
'TRUE',
'FALSE',
'NOT',
'AND',
'ASSIGNMENT',
'COLON',
'QSTRING',
'DQSTRING',
)
def t_COMMENT(t):
r'\.\.+[ \t]*(//.*)?(\n|$)|//.*'
pass
def t_EOL(t):
r'\n'
global brackets
if brackets == 0:
t.state = 'EOL'
t.value = t.lexer.lexmatch.group()
return t
t_NUMBER = r'-?(\d+(\.\d*)?|\.\d+)([eE][+-]?\d+)?'
t_VAR = r'[a-zA-Z][a-zA-Z0-9_]*'
t_DOT = r'\.'
t_OPERATOR = r'[+\-*/]'
t_NOTEQUALTO = r'<>'
t_COMPARISON = r'[<>]=?|=='
t_COMMA = r','
def t_OPENSQBRACKET(t):
r'\['
global brackets
brackets += 1
t.state = 'OPENSQBRACKET'
t.value = t.lexer.lexmatch.group()
return t
def t_CLOSESQBRACKET(t):
r'\]'
global brackets
brackets -= 1
t.state = 'CLOSESQBRACKET'
t.value = t.lexer.lexmatch.group()
return t
def t_OPENBRACKET(t):
r'\('
global brackets
brackets += 1
t.state = 'OPENBRACKET'
t.value = t.lexer.lexmatch.group()
return t
def t_CLOSEBRACKET(t):
r'\)'
global brackets
brackets -= 1
t.state = 'CLOSEBRACKET'
t.value = t.lexer.lexmatch.group()
return t
t_SEMICOLON = r';'
t_TRUE = r'%t'
t_FALSE = r'%f'
t_NOT = r'~'
t_AND = r'&'
t_ASSIGNMENT = r'='
t_COLON = r':'
t_ignore = ' \t'
def t_error(t):
print("Illegal character '%s'" % t.value[0])
t.lexer.skip(1)
states = (
('qstring', 'exclusive'),
('dqstring', 'exclusive'),
)
def t_begin_qstring(t):
r"'"
global qstring
t.lexer.begin('qstring')
qstring = t.lexer.lexmatch.group()
def t_begin_dqstring(t):
r'"'
global dqstring
t.lexer.begin('dqstring')
dqstring = t.lexer.lexmatch.group()
def t_qstring_COMMENT(t):
r'\.\.+[ \t]*(//.*)?\n'
pass
def t_dqstring_COMMENT(t):
r'\.\.+[ \t]*(//.*)?\n'
pass
def t_qstring_end(t):
r"'"
global qstring
t.lexer.begin('INITIAL')
qstring += t.lexer.lexmatch.group()
t.type = 'QSTRING'
t.value = qstring
return t
def t_dqstring_end(t):
r'"'
global dqstring
t.lexer.begin('INITIAL')
dqstring += t.lexer.lexmatch.group()
t.type = 'DQSTRING'
t.value = dqstring
return t
def t_qstring_char(t):
r"\\.|\.|[^'\\.]+"
global qstring
qstring += t.lexer.lexmatch.group()
def t_dqstring_char(t):
r'\\.|\.|[^"\\.]+'
global dqstring
dqstring += t.lexer.lexmatch.group()
t_qstring_ignore = ''
t_dqstring_ignore = ''
def t_qstring_error(t):
print("Illegal character '%s' in qstring" % t.value[0])
t.lexer.skip(1)
def t_dqstring_error(t):
print("Illegal character '%s' in dqstring" % t.value[0])
t.lexer.skip(1)
lexer = lex.lex()
if len(sys.argv) <= 1:
print("Usage: %s filename" % sys.argv[0])
sys.exit(1)
filename = sys.argv[1]
data = ''
with open(filename, 'r') as infile:
for line in infile:
data += line
lexer.input(data)
for tok in lexer:
print(tok)
|
