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
|
// test lexer
/*
$
g++ \
module-test/lexer_test.cc \
src/lexer/token.cc \
src/lexer/ast.cc \
src/lexer/symbol_property.cc \
-std=c++23 -Iinclude -Ithird_party/magic_enum/include
*/
#include <iostream>
#include <string>
#include <type_traits>
#include <unistd.h>
#include <cstring>
#include <vector>
#include <print>
#include "magic_enum/magic_enum.hpp"
#include "lexer/ast.h"
#include "lexer/enum_type.h"
#include "lexer/token.h"
using namespace std;
using namespace ov4;
constexpr int MAXLINE = 1024;
int main()
{
int test_case = 13;
string s;
switch (test_case)
{
case 0:
s = "hello | hi || foo && bar || baz &";
break;
case 1:
s = "hi";
break;
case 2:
s = "&&";
break;
case 3:
s = "hi (hello || foo)";
break;
case 4:
s = "alpha || beta (gamma argument && (delta || epsilon second_argument & ) )";
break;
case 5:
s = "alpha || beta && (gamma || epsilon)";
break;
// bracket matching test
case 6:
s = ")alpha && beta(";
break;
// basic scriptio continua
// syntax is wrong but just to test tokenizer
case 7:
s = "((alpha&|&&beta)||gamma&&&delta)";
break;
// simple guard test
case 8:
s = "\'text\' &&";
break;
// guard test
case 9:
s = "\'realOperator\' && \"fake&&\" real ||";
break;
// guard test
// with space
case 10:
s = "\'This should be 1 token\' symbol && text \'&&\'";
break;
// missing test
// missing right
case 11:
s = "alpha&&";
break;
// missing test
// missing left
case 12:
s = "&&left";
break;
// existance test
// exist right
case 13:
s = "alpha&beta";
break;
default:
return 0;
}
T_lexer lexer_instance;
lexer_instance.tokenizer(s);
cout << "---------- tokenizer ----------" << endl;
for (auto c : lexer_instance.token)
{
if (c.token_type == LOGIC_AND)
println("{} LOGIC_AND", c.bracket_depth);
else if (c.token_type == LOGIC_OR)
println("{} LOGIC_OR", c.bracket_depth);
else if (c.token_type == ASYNC)
println("{} ASYNC", c.bracket_depth);
else if (c.token_type == PIPE)
println("{} PIPE", c.bracket_depth);
else if (c.token_type == LEFT_BRACKET)
println("{} LEFT_BRACKET", c.bracket_depth);
else if (c.token_type == RIGHT_BRACKET)
println("{} RIGHT_BRACKET", c.bracket_depth);
else if (c.token_type == TEXT)
println("{} TEXT .{}.", c.bracket_depth, c.text);
}
cout << "---------- parse ----------" << endl;
lexer_instance.parse(0, lexer_instance.token.size(), lexer_instance.alloc_ast());
cout << "---------- AST ----------" << endl;
for (size_t i = 0; i < lexer_instance.ast.size(); i++)
{
print("{}: type: {} left: {} right: {}", i, magic_enum::enum_name(lexer_instance.ast[i].token_type), lexer_instance.ast[i].left, lexer_instance.ast[i].right);
if (lexer_instance.ast[i].token_type == TEXT)
print(" command: {}", lexer_instance.ast[i].command_text);
println();
}
return 0;
}
|
