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
|
#!/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 = ''
afterarray = False
syntaxtokens = {
'break': 'BREAK',
'case': 'CASE',
'clear': 'CLEAR',
'do': 'DO',
'else': 'ELSE',
'elseif': 'ELSEIF',
'end': 'END',
'endfunction': 'ENDFUNCTION',
'for': 'FOR',
'function': 'FUNCTION',
'if': 'IF',
'resume': 'RESUME',
'return': 'RETURN',
'select': 'SELECT',
'then': 'THEN',
'where': 'WHERE',
'while': 'WHILE',
}
predefinedvariables = {
't': 'PREVAR_BOOLEAN',
'f': 'PREVAR_BOOLEAN',
'i': 'PREVAR_COMPLEX',
'pi': 'PREVAR_FLOAT',
}
tokens = [
'EOL',
'NUMBER',
'LASTINDEX',
'VAR',
'DOT',
'OPERATOR',
'COMPARISON',
'COMMA',
'OPENSQBRACKET',
'CLOSESQBRACKET',
'OPENBRACKET',
'CLOSEBRACKET',
'SEMICOLON',
'NOT',
'LOGICAL',
'ASSIGNMENT',
'COLON',
'QSTRING',
'DQSTRING',
'PREVAR',
'TRANSPOSE',
] + list(syntaxtokens.values()) + list(set(predefinedvariables.values()))
states = (
('qstring', 'exclusive'),
('dqstring', 'exclusive'),
)
t_ignore = ' \t'
t_qstring_ignore = ''
t_dqstring_ignore = ''
def t_COMMENT(t):
r'\.\.+[ \t]*(//.*)?(\n|$)|//.*'
pass
def t_EOL(t):
r'\n'
global afterarray, brackets
if brackets == 0:
afterarray = False
t.state = 'EOL'
return t
t_NUMBER = r'-?(\d+(\.\d*)?|\.\d+)([eE][+-]?\d+)?'
t_LASTINDEX = r'\$'
t_DOT = r'\.'
t_OPERATOR = r'[+\-*/^\\]'
t_COMPARISON = r'<>|[<>~=]=|[<>]'
t_COMMA = r','
def t_OPENSQBRACKET(t):
r'\['
global afterarray, brackets
afterarray = False
brackets += 1
t.state = 'OPENSQBRACKET'
return t
def t_CLOSESQBRACKET(t):
r'\]'
global afterarray, brackets
afterarray = True
brackets -= 1
t.state = 'CLOSESQBRACKET'
return t
def t_OPENBRACKET(t):
r'\('
global afterarray, brackets
afterarray = False
brackets += 1
t.state = 'OPENBRACKET'
return t
def t_CLOSEBRACKET(t):
r'\)'
global afterarray, brackets
afterarray = True
brackets -= 1
t.state = 'CLOSEBRACKET'
return t
def t_VAR(t):
r'[a-zA-Z_][a-zA-Z0-9_]*'
global afterarray
afterarray = True
t.type = syntaxtokens.get(t.value, 'VAR')
return t
def t_PREVAR(t):
r'%[a-zA-Z_][a-zA-Z0-9_]*'
global afterarray
afterarray = False
t.type = predefinedvariables.get(t.value[1:], 'PREVAR')
return t
def t_SEMICOLON(t):
r';'
global afterarray
afterarray = False
t.state = 'SEMICOLON'
return t
def t_NOT(t):
r'~'
global afterarray
afterarray = False
t.state = 'NOT'
return t
def t_LOGICAL(t):
r'[&|]'
global afterarray
afterarray = False
t.state = 'LOGICAL'
return t
def t_ASSIGNMENT(t):
r'='
global afterarray
afterarray = False
t.state = 'ASSIGNMENT'
return t
def t_COLON(t):
r':'
global afterarray
afterarray = False
t.state = 'COLON'
return t
def t_error(t):
print("Illegal character '%s'" % t.value[0])
t.lexer.skip(1)
def t_TRANSPOSE(t):
r"'"
global afterarray, qstring
if afterarray:
afterarray = False
t.state = 'TRANSPOSE'
return t
t.lexer.begin('qstring')
qstring = t.value
def t_begin_dqstring(t):
r'"'
global afterarray, dqstring
afterarray = False
t.lexer.begin('dqstring')
dqstring = t.value
def t_qstring_COMMENT(t):
r'\.\.+[ \t]*(//.*)?\n'
pass
def t_dqstring_COMMENT(t):
r'\.\.+[ \t]*(//.*)?\n'
pass
def t_qstring_quote(t):
r'\'\'|""'
global qstring
qstring += '\\' + t.value[0]
def t_dqstring_quote(t):
r'\'\'|""'
global dqstring
dqstring += '\\' + t.value[0]
def t_qstring_end(t):
r"'"
global qstring
t.lexer.begin('INITIAL')
qstring += t.value
t.type = 'QSTRING'
t.value = qstring
return t
def t_dqstring_end(t):
r'"'
global dqstring
t.lexer.begin('INITIAL')
dqstring += t.value
t.type = 'DQSTRING'
t.value = dqstring
return t
def t_qstring_char(t):
r'\.|[^\'".]+'
global qstring
qstring += t.value
def t_dqstring_char(t):
r'\.|[^\'".]+'
global dqstring
dqstring += t.value
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)
|
