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
|
/* MyTokenBuffer.c */
/* Sample replacement for DLGLexer */
/* Shows how to override DLG with your own lexer */
#include <stdio.h>
#include <ctype.h>
#include <stdlib.h>
#include <iostream.h>
#include "config.h" /* include token defs */
#include "tokens.h" /* include token defs */
#include APARSER_H /* include all the ANTLR yuck */
#include "MyLexer.h" /* define your lexer */
typedef ANTLRCommonToken ANTLRToken;/* use a predefined Token class */
void panic(char *s) {
cerr << s << '\n';
exit(5);
}
MyLexer::MyLexer()
{
c = getchar();
}
/* Recognizes Tokens IDENTIFIER and NUMBER */
ANTLRAbstractToken *MyLexer::
getToken()
{
/* we will return a pointer to this next guy */
ANTLRToken *resultToken = new ANTLRToken;
ANTLRChar TokenBuffer[100];
/* This routine will just crash if tokens become
more than 99 chars; your code must of course
gracefully recover/adapt */
int index=0;
while ( c==' ' || c=='\n' ) c=getchar();
if (c==EOF) {resultToken->setType(Eof); return resultToken;}
if (isdigit(c)) {
/* Looks like we have ourselves a number token */
while (isdigit(c)) {
TokenBuffer[index++]=c;
c = getchar();
}
TokenBuffer[index]='\0';
resultToken->setType(NUMBER);
resultToken->setText(TokenBuffer);
return resultToken;
}
if (isalpha(c)) {
/* We have ourselves an IDENTIFIER token */
while (isalpha(c)) {
TokenBuffer[index++]=c;
c = getchar();
}
TokenBuffer[index]='\0';
resultToken->setType(IDENTIFIER);
resultToken->setText(TokenBuffer);
return resultToken;
}
else
panic("lexer error");
return NULL;
}
|
