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
|
/*======================================================================
* Flex Options
*/
%option outfile="flex3test.lex.c"
%option header-file="flex3test.lex.h"
%option prefix="testme_yy"
%option reentrant
%option 8bit
%option yylineno
%{
/*======================================================================
* User C Header
*/
#include <gfsm.h>
typedef enum {
T_EOF = 256,
T_CHAR = 257,
T_BRACKETED = 258,
T_BSPACE = 259,
T_WEIGHT = 260,
T_UINT = 261,
T_UTF8 = 262,
T_LPAREN = '(',
T_RPAREN = ')',
T_LBRACKET = '[',
T_RBRACKET = ']',
T_LANGLE = '<',
T_RANGLE = '>',
T_BEQUAL = '=',
T_OTHER = 65535
} TokenType;
#define GSTR_BUF ((GString*)((gfsmScanner*)yyextra)->data)
%}
/*======================================================================
* Flex Definitions
*/
DIGIT [0-9]
SPACE [[:space:]]
WCHAR [^\<\>\[\]\\ \t\n\r\#]
BCHAR [^\\\]\ \t\n\r\=]
UTF8PREFIX "Ã"
%x ESCAPE BRACKETED BESCAPE COMMENT WEIGHT UINT UTF8 BUTF8
/*======================================================================
* Rules
*/
%%
{UTF8PREFIX} { BEGIN(UTF8); g_string_set_size(GSTR_BUF,1); GSTR_BUF->str[0] = yytext[0]; }
"\\" { BEGIN(ESCAPE); }
"#" { BEGIN(COMMENT); }
"[" { BEGIN(BRACKETED); g_string_truncate(GSTR_BUF,0); return T_LBRACKET; }
"<" { BEGIN(WEIGHT); return T_LANGLE; }
"(" { return '('; }
")" { return ')'; }
"*" { return '*'; }
"+" { return '+'; }
"^" { BEGIN(UINT); return '|'; }
"?" { return '?'; }
"!" { return '!'; }
"|" { return '|'; }
"&" { return '&'; }
":" { return ':'; }
"@" { return '@'; }
"-" { return '-'; }
{SPACE} { /* ignore */ }
{WCHAR} { return T_CHAR; }
<UTF8>{UTF8PREFIX}+ { g_string_append(GSTR_BUF, yytext); }
<UTF8>. { BEGIN(INITIAL); g_string_append_c(GSTR_BUF, yytext[0]); return T_UTF8; }
<WEIGHT>([\+\-])?({DIGIT}*\.)?({DIGIT}+)([Ee]([\+\-]?){DIGIT}+)? { return T_WEIGHT; /* hack */ }
<WEIGHT>\> { BEGIN(INITIAL); return T_RANGLE; }
<UINT>{DIGIT}+ { BEGIN(INITIAL); return T_UINT; }
<COMMENT>[^\n]*\n { BEGIN(INITIAL); /* ignore comments */ }
<ESCAPE>. { BEGIN(INITIAL); return T_CHAR; }
<BRACKETED>{UTF8PREFIX} { BEGIN(BUTF8); g_string_append_c(GSTR_BUF, yytext[0]); }
<BRACKETED>\] { BEGIN(INITIAL); return T_RBRACKET; }
<BRACKETED>{BCHAR} { g_string_append_c(GSTR_BUF, yytext[0]); }
<BRACKETED>{SPACE} { return T_BSPACE; }
<BRACKETED>"=" { return T_BEQUAL; }
<BRACKETED>\\ { BEGIN(BESCAPE); }
<BUTF8>{UTF8PREFIX}+ { g_string_append(GSTR_BUF, yytext); }
<BUTF8>. { BEGIN(BRACKETED); g_string_append_c(GSTR_BUF, yytext[0]); }
<BESCAPE>. { BEGIN(BRACKETED); g_string_append_c(GSTR_BUF, yytext[0]); }
<<EOF>> { return T_EOF; }
<*>. {
gfsm_scanner_carp(yyextra, "bad character '%s'", yytext);
return T_OTHER;
}
%%
/*======================================================================
* User C Code
*/
void testme(gfsmScanner *scanner) {
TokenType tok;
double weight;
unsigned int uint;
while ((tok=testme_yylex(scanner->yyscanner)) != T_EOF) {
switch (tok) {
case T_CHAR:
printf("(char) '%s'\n", testme_yyget_text(scanner->yyscanner));
break;
case T_UTF8:
printf("(utf8) '%s'\n", ((GString*)scanner->data)->str);
break;
case T_LBRACKET:
printf("(lbracket)\n");
break;
case T_RBRACKET:
printf("(rbracket) gstr=\"%s\"\n", ((GString*)scanner->data)->str);
g_string_truncate(((GString*)scanner->data),0);
break;
case T_BSPACE:
printf("(bspace) gstr=\"%s\"\n", ((GString*)scanner->data)->str);
g_string_truncate(((GString*)scanner->data),0);
break;
case T_BEQUAL:
printf("(bequal) gstr=\"%s\"\n", ((GString*)scanner->data)->str);
g_string_truncate(((GString*)scanner->data),0);
break;
case T_LANGLE:
printf("(langle)\n");
break;
case T_RANGLE:
printf("(rangle)\n");
break;
case T_WEIGHT:
weight = strtod(testme_yyget_text(scanner->yyscanner),NULL);
printf("(weight) =%g\n", weight);
break;
case T_UINT:
uint = strtol(testme_yyget_text(scanner->yyscanner),NULL,0);
printf("(uint) =%d\n", uint);
break;
default:
printf("(other=%d~'%c'): (%s)\n", tok, tok, testme_yyget_text(scanner->yyscanner));
break;
}
if (scanner->err) {
fprintf(stderr, "Error: %s\n", scanner->err->message);
g_clear_error(&(scanner->err));
break;
}
}
}
int main(void) {
gfsmScanner *scanner = gfsm_scanner_new("myScanner",testme_yy);
scanner->data = g_string_new("");
//-- first, scan a string
/*
gfsm_scanner_scan_string(scanner, "line 1\nline 2\nline 3.");
scanner->filename = g_strdup("string");
testme(scanner);
*/
//-- now scan stdin
gfsm_scanner_scan_filename(scanner, "-");
testme(scanner);
gfsm_scanner_free(scanner);
return 0;
}
//int testme_yywrap(yyscan_t yyscanner) { return 1; }
GFSM_SCANNER_YYWRAP(testme_yy)
|
