-
Notifications
You must be signed in to change notification settings - Fork 1
/
lexer.l
244 lines (211 loc) · 8.39 KB
/
lexer.l
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
%{
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <math.h>
#include "types.h"
#include "ast.h"
#include "ast_printer.h"
#include "syntax.tab.h"
#define flexdebug 0
char str_buf[256];
int error_counter = 0;
void print_token(int token_id);
int str_to_int(char *string);
char handle_escape_sequence(char escape_char);
float hex_to_float(char *str);
float bin_to_float(char *str);
float str_to_float(char *string);
void yyerror(const char *err);
%}
%option case-insensitive
%option yylineno
%option noyywrap
%x STRINGS
ICONST (0[bB][1][01]*)|(0[hH][1-9A-F][0-9A-F]*)|(0|[1-9][0-9]*)
BINCONST (0[bB])(1[01]*)?\.(0*1+[01]*|0)
HEXCONST 0[Hh](0|[1-9A-F][0-9A-F]*)?\.(0*[1-9A-F]+[0-9A-F]*|0)?
EXP E[+-]?(0|[1-9][0-9]*)
DECCONST (0|[1-9][0-9]*)?(\.)(0*[1-9]+[0-9]*|0)?{EXP}?|(0|[1-9][0-9]*){EXP}
RCONST {BINCONST}|{HEXCONST}|{DECCONST}
IDENTIFIER [a-zA-Z][a-zA-Z0-9]*|_[a-zA-Z][a-zA-Z0-9]*((_?)[a-zA-Z0-9])*_
%%
"FUNCTION" {print_token(FUNCTION); return FUNCTION;}
"SUBROUTINE" {print_token(SUBROUTINE); return SUBROUTINE;}
"END" {print_token(END); return END;}
"INTEGER" {print_token(INTEGER); return INTEGER;}
"REAL" {print_token(REAL); return REAL;}
"LOGICAL" {print_token(LOGICAL); return LOGICAL;}
"CHARACTER" {print_token(CHARACTER); return CHARACTER;}
"RECORD" {print_token(RECORD); return RECORD;}
"ENDREC" {print_token(ENDREC); return ENDREC;}
"DATA" {print_token(DATA); return DATA;}
"CONTINUE" {print_token(CONTINUE); return CONTINUE;}
"GOTO" {print_token(GOTO); return GOTO;}
"CALL" {print_token(CALL); return CALL;}
"READ" {print_token(READ); return READ;}
"WRITE" {print_token(WRITE); return WRITE;}
"IF" {print_token(IF); return IF;}
"THEN" {print_token(THEN); return THEN;}
"ELSE" {print_token(ELSE); return ELSE;}
"ENDIF" {print_token(ENDIF); return ENDIF;}
"DO" {print_token(DO); return DO;}
"ENDDO" {print_token(ENDDO); return ENDDO;}
"STOP" {print_token(STOP); return STOP;}
"RETURN" {print_token(RETURN); return RETURN;}
{IDENTIFIER} {print_token(ID); yylval.strval = strdup(yytext); return ID;}
{ICONST} {print_token(ICONST); yylval.val.ival = str_to_int(yytext); return ICONST;}
{RCONST} {print_token(RCONST); yylval.val.fval = str_to_float(yytext); return RCONST;}
\" {BEGIN(STRINGS);}
<STRINGS>\" {BEGIN(INITIAL); printf("Found string '%s' \n", str_buf); strcpy(str_buf, ""); return STRING;}
<STRINGS>(\\\n|\\\r\n) {/* Ignore escaped newline characters */}
<STRINGS>(\n|\r\n) {yyerror("New line found without \\ \n");}
<STRINGS>\\.|[^|\\] {
if (strlen(yytext) == 2) {
switch (yytext[1]) {
case 'n': strcat(str_buf, "\n"); break;
case 'f': strcat(str_buf, "\f"); break;
case 't': strcat(str_buf, "\t"); break;
case 'r': strcat(str_buf, "\r"); break;
case 'b': strcat(str_buf, "\b"); break;
case 'v': strcat(str_buf, "\v"); break;
default: strcat(str_buf, &yytext[1]); break;
}
} else {
strcat(str_buf, yytext);
}
}
<STRINGS><<EOF>> {yyerror("End of string without closing it\n");}
<STRINGS>. {yyerror("Found unrecognized character\n");}
"$".* {printf("Comment found\n");}
'[ -~]' {print_token(CCONST); yylval.val.cval = yytext[1]; return CCONST;}
'\\[nftrbv]' {print_token(CCONST); yylval.val.cval = handle_escape_sequence(yytext[2]); return CCONST;}
".TRUE." {print_token(LCONST); return LCONST;}
".FALSE." {print_token(LCONST); return LCONST;}
".OR." {print_token(OROP); return OROP;}
".AND." {print_token(ANDOP); return ANDOP;}
".NOT." {print_token(NOTOP); return NOTOP;}
".GT." {print_token(RELOP); yylval.intval = GREATER; return RELOP;}
".GE." {print_token(RELOP); yylval.intval = GREATER_EQUAL; return RELOP;}
".LT." {print_token(RELOP); yylval.intval = LESS; return RELOP;}
".LE." {print_token(RELOP); yylval.intval = LESS_EQUAL; return RELOP;}
".EQ." {print_token(RELOP); yylval.intval = EQUAL; return RELOP;}
".NE." {print_token(RELOP); yylval.intval = NOT_EQUAL; return RELOP;}
"+" {print_token(ADDOP); yylval.intval = ADD; return ADDOP;}
"-" {print_token(ADDOP); yylval.intval = SUB; return ADDOP;}
"*" {print_token(MULOP); return MULOP;}
"/" {print_token(DIVOP); return DIVOP;}
"**" {print_token(POWEROP); return POWEROP;}
"(" {print_token(LPAREN); return LPAREN;}
")" {print_token(RPAREN); return RPAREN;}
"," {print_token(COMMA); return COMMA;}
"=" {print_token(ASSIGN); return ASSIGN;}
":" {print_token(COLON); return COLON;}
[ \t] { }
[\n] { }
[\r\n] { }
<<EOF>> {print_token(0); return 0;}
. {yyerror("Unrecognised Charachter\n");}
%%
/*
int main(int argc, char *argv[]) {
int token;
if(argc > 1) {
yyin = fopen(argv[1], "r");
if(yyin == NULL) {
perror("Error opening file\n");
return -1;
}
}
do {
token = yylex();
}while(token != 0);
fclose(yyin);
yyterminate();
}
*/
int str_to_int(char *string) {
if(strncmp(string, "0h", 2) == 0 || strncmp(string, "0H", 2) == 0)
return strtoll(&string[2], NULL, 16);
else if(strncmp(string, "0b", 2) == 0 || strncmp(string, "0B", 2) == 0)
return strtoll(&string[2], NULL, 2);
else
return atoi(string);
}
void print_token(int token_id) {
if(!flexdebug)
return;
if(token_id == ICONST)
printf("LINE: %d | Found token %-10s | with ID: %d | BASE 10: %d\n", yylineno, yytext, token_id, str_to_int(yytext));
else if(token_id == RCONST)
printf("LINE: %d | Found token %-10s | with ID: %d | BASE 10: %f\n", yylineno, yytext, token_id, str_to_float(yytext));
else if(token_id == 0)
printf("LINE: %d | Found token %-10s | with ID: %d\n", yylineno, "eof", 0);
else
printf("LINE: %d | Found token %-10s | with ID: %d\n", yylineno, yytext, token_id);
return ;
}
void yyerror(const char *err){
error_counter++;
printf("[ERROR - LINE %d] %s\n", yylineno, err);
if(error_counter == 5){
printf("MAXIMUM ERRORS FOUND\n");
exit(EXIT_FAILURE);
}
yyless(1);
}
char handle_escape_sequence(char escape_char) {
switch (escape_char) {
case 'n':
return '\n';
case 'f':
return '\f';
case 'r':
return '\r';
case 't':
return '\t';
case 'b':
return '\b';
case 'v':
return '\v';
}
}
float str_to_float(char *string) {
if(strncmp(string, "0h", 2) == 0 || strncmp(string, "0H", 2) == 0)
return hex_to_float(string);
else if(strncmp(string, "0b", 2) == 0 || strncmp(string, "0B", 2) == 0)
return bin_to_float(string);
else
return atof(string);
}
float bin_to_float(char *str) {
float number = 0.0;
int i, length_real;
char *character;
character = strchr(str, '.');
length_real = strlen(character) - 1;
number = (int)strtol(&str[2], &character, 2);
for(i = 1; i < length_real+1; i++) {
number += (character[i] - '0') * (1/pow(2,i));
}
return number;
}
float hex_to_float(char *str) {
float number = 0.0;
int i, length_real;
char *character;
character = strchr(str, '.');
length_real = strlen(character) - 1;
number = (int)strtol(&str[2], &character, 16);
for(i = 1; i < length_real + 1; i++) {
if(character[i] <= '9')
number += (character[i] - '0') * (1/pow(16,i));
else if(character[i] <= 'Z'){
number += (character[i] + 10 - 'A') * (1/pow(16,i));
}
else{
number += (character[i] + 10 - 'a') * (1/pow(16,i));
}
}
return number;
}