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
|
header {
#include "antlr/CommonASTWithHiddenTokens.hpp"
#include "antlr/TokenStreamHiddenTokenFilter.hpp"
#include <iostream>
}
options {
language="Cpp";
}
class InstrParser extends Parser;
options {
buildAST = true;
k=2;
}
tokens {
CALL; // define imaginary token CALL
}
slist
: ( stat )+ EOF
;
stat: LBRACE^ (stat)+ RBRACE
| "if"^ expr "then" stat ("else" stat)?
| ID ASSIGN^ expr SEMI
| call
;
expr
: mexpr (PLUS^ mexpr)*
;
mexpr
: atom (STAR^ atom)*
;
atom: INT
| ID
;
call: ID LPAREN (expr)? RPAREN SEMI
{#call = #(#[CALL,"CALL"], #call);}
;
{
#include "InstrParser.hpp"
}
class InstrLexer extends Lexer;
options {
charVocabulary = '\3'..'\377';
}
WS_ : (' '
| '\t'
| ('\n'|'\r'('\n')) {newline();}
)+
;
// Single-line comments
SL_COMMENT
: "//"
(~('\n'|'\r'))* ('\n'|'\r'('\n')?)
{newline();}
;
LBRACE: '{'
;
RBRACE: '}'
;
LPAREN: '('
;
RPAREN: ')'
;
STAR: '*'
;
PLUS: '+'
;
SEMI: ';'
;
ASSIGN
: '='
;
protected
DIGIT
: '0'..'9'
;
INT : (DIGIT)+
;
ID : ('a'..'z')+
;
class InstrTreeWalker extends TreeParser;
{
public:
void setFilter(ANTLR_USE_NAMESPACE(antlr)TokenStreamHiddenTokenFilter& filter);
private:
ANTLR_USE_NAMESPACE(antlr)TokenStreamHiddenTokenFilter* filter;
void dumpHidden(ANTLR_USE_NAMESPACE(antlr)RefToken t);
void pr(ANTLR_USE_NAMESPACE(antlr)RefAST p);
}
slist
: {dumpHidden(filter->getInitialHiddenToken());}
(stat)+
;
stat: #(LBRACE {pr(#LBRACE);} (stat)+ RBRACE {pr(#RBRACE);})
| #(i:"if" {pr(i);} expr t:"then" {pr(t);} stat (e:"else" {pr(e);} stat)?)
| #(ASSIGN ID {pr(#ID); pr(#ASSIGN);} expr SEMI {pr(#SEMI);} )
| call
;
expr
: #(PLUS expr {pr(#PLUS);} expr)
| #(STAR expr {pr(#STAR);} expr)
| INT {pr(#INT);}
| ID {pr(#ID);}
;
call: {
// add instrumentation about call; manually call rule
callDumpInstrumentation(#call);
}
#(CALL ID {pr(#ID);}
LPAREN {pr(#LPAREN);} (expr)? RPAREN {pr(#RPAREN);}
SEMI
{
// print SEMI manually; need '}' between it and whitespace
std::cout << #SEMI->getText();
std::cout << "}"; // close {...} of instrumentation
dumpHidden(
(ANTLR_USE_NAMESPACE(antlr)RefCommonASTWithHiddenTokens(#SEMI))->getHiddenAfter()
);
}
)
;
/** Dump instrumentation for a call statement.
* The reference to rule expr prints out the arg
* and then at the end of this rule, we close the
* generated called to dbg.invoke().
*/
callDumpInstrumentation
: #(CALL id:ID
{std::cout << "{dbg.invoke(\"" << id->getText() << "\", \"";}
LPAREN (e:expr)? RPAREN SEMI
{std::cout << "\"); ";}
)
;
|
