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
|
// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++ (supporting code)
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-License-Identifier: MIT
#include "doctest_compatibility.h"
#define JSON_TESTS_PRIVATE
#include <nlohmann/json.hpp>
using nlohmann::json;
namespace
{
// shortcut to scan a string literal
json::lexer::token_type scan_string(const char* s, bool ignore_comments = false);
json::lexer::token_type scan_string(const char* s, const bool ignore_comments)
{
auto ia = nlohmann::detail::input_adapter(s);
return nlohmann::detail::lexer<json, decltype(ia)>(std::move(ia), ignore_comments).scan(); // NOLINT(hicpp-move-const-arg,performance-move-const-arg)
}
} // namespace
std::string get_error_message(const char* s, bool ignore_comments = false); // NOLINT(misc-use-internal-linkage)
std::string get_error_message(const char* s, const bool ignore_comments)
{
auto ia = nlohmann::detail::input_adapter(s);
auto lexer = nlohmann::detail::lexer<json, decltype(ia)>(std::move(ia), ignore_comments); // NOLINT(hicpp-move-const-arg,performance-move-const-arg)
lexer.scan();
return lexer.get_error_message();
}
TEST_CASE("lexer class")
{
SECTION("scan")
{
SECTION("structural characters")
{
CHECK((scan_string("[") == json::lexer::token_type::begin_array));
CHECK((scan_string("]") == json::lexer::token_type::end_array));
CHECK((scan_string("{") == json::lexer::token_type::begin_object));
CHECK((scan_string("}") == json::lexer::token_type::end_object));
CHECK((scan_string(",") == json::lexer::token_type::value_separator));
CHECK((scan_string(":") == json::lexer::token_type::name_separator));
}
SECTION("literal names")
{
CHECK((scan_string("null") == json::lexer::token_type::literal_null));
CHECK((scan_string("true") == json::lexer::token_type::literal_true));
CHECK((scan_string("false") == json::lexer::token_type::literal_false));
}
SECTION("numbers")
{
CHECK((scan_string("0") == json::lexer::token_type::value_unsigned));
CHECK((scan_string("1") == json::lexer::token_type::value_unsigned));
CHECK((scan_string("2") == json::lexer::token_type::value_unsigned));
CHECK((scan_string("3") == json::lexer::token_type::value_unsigned));
CHECK((scan_string("4") == json::lexer::token_type::value_unsigned));
CHECK((scan_string("5") == json::lexer::token_type::value_unsigned));
CHECK((scan_string("6") == json::lexer::token_type::value_unsigned));
CHECK((scan_string("7") == json::lexer::token_type::value_unsigned));
CHECK((scan_string("8") == json::lexer::token_type::value_unsigned));
CHECK((scan_string("9") == json::lexer::token_type::value_unsigned));
CHECK((scan_string("-0") == json::lexer::token_type::value_integer));
CHECK((scan_string("-1") == json::lexer::token_type::value_integer));
CHECK((scan_string("1.1") == json::lexer::token_type::value_float));
CHECK((scan_string("-1.1") == json::lexer::token_type::value_float));
CHECK((scan_string("1E10") == json::lexer::token_type::value_float));
}
SECTION("whitespace")
{
// result is end_of_input, because not token is following
CHECK((scan_string(" ") == json::lexer::token_type::end_of_input));
CHECK((scan_string("\t") == json::lexer::token_type::end_of_input));
CHECK((scan_string("\n") == json::lexer::token_type::end_of_input));
CHECK((scan_string("\r") == json::lexer::token_type::end_of_input));
CHECK((scan_string(" \t\n\r\n\t ") == json::lexer::token_type::end_of_input));
}
}
SECTION("token_type_name")
{
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::uninitialized)) == "<uninitialized>"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::literal_true)) == "true literal"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::literal_false)) == "false literal"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::literal_null)) == "null literal"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::value_string)) == "string literal"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::value_unsigned)) == "number literal"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::value_integer)) == "number literal"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::value_float)) == "number literal"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::begin_array)) == "'['"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::begin_object)) == "'{'"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::end_array)) == "']'"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::end_object)) == "'}'"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::name_separator)) == "':'"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::value_separator)) == "','"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::parse_error)) == "<parse error>"));
CHECK((std::string(json::lexer::token_type_name(json::lexer::token_type::end_of_input)) == "end of input"));
}
SECTION("parse errors on first character")
{
for (int c = 1; c < 128; ++c)
{
// create string from the ASCII code
const auto s = std::string(1, static_cast<char>(c));
// store scan() result
const auto res = scan_string(s.c_str());
CAPTURE(s)
switch (c)
{
// single characters that are valid tokens
case ('['):
case (']'):
case ('{'):
case ('}'):
case (','):
case (':'):
case ('0'):
case ('1'):
case ('2'):
case ('3'):
case ('4'):
case ('5'):
case ('6'):
case ('7'):
case ('8'):
case ('9'):
{
CHECK((res != json::lexer::token_type::parse_error));
break;
}
// whitespace
case (' '):
case ('\t'):
case ('\n'):
case ('\r'):
{
CHECK((res == json::lexer::token_type::end_of_input));
break;
}
// anything else is not expected
default:
{
CHECK((res == json::lexer::token_type::parse_error));
break;
}
}
}
}
SECTION("very large string")
{
// strings larger than 1024 bytes yield a resize of the lexer's yytext buffer
std::string s("\"");
s += std::string(2048, 'x');
s += "\"";
CHECK((scan_string(s.c_str()) == json::lexer::token_type::value_string));
}
SECTION("fail on comments")
{
CHECK((scan_string("/", false) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/", false) == "invalid literal");
CHECK((scan_string("/!", false) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/!", false) == "invalid literal");
CHECK((scan_string("/*", false) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/*", false) == "invalid literal");
CHECK((scan_string("/**", false) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/**", false) == "invalid literal");
CHECK((scan_string("//", false) == json::lexer::token_type::parse_error));
CHECK(get_error_message("//", false) == "invalid literal");
CHECK((scan_string("/**/", false) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/**/", false) == "invalid literal");
CHECK((scan_string("/** /", false) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/** /", false) == "invalid literal");
CHECK((scan_string("/***/", false) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/***/", false) == "invalid literal");
CHECK((scan_string("/* true */", false) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/* true */", false) == "invalid literal");
CHECK((scan_string("/*/**/", false) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/*/**/", false) == "invalid literal");
CHECK((scan_string("/*/* */", false) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/*/* */", false) == "invalid literal");
}
SECTION("ignore comments")
{
CHECK((scan_string("/", true) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/", true) == "invalid comment; expecting '/' or '*' after '/'");
CHECK((scan_string("/!", true) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/!", true) == "invalid comment; expecting '/' or '*' after '/'");
CHECK((scan_string("/*", true) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/*", true) == "invalid comment; missing closing '*/'");
CHECK((scan_string("/**", true) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/**", true) == "invalid comment; missing closing '*/'");
CHECK((scan_string("//", true) == json::lexer::token_type::end_of_input));
CHECK((scan_string("/**/", true) == json::lexer::token_type::end_of_input));
CHECK((scan_string("/** /", true) == json::lexer::token_type::parse_error));
CHECK(get_error_message("/** /", true) == "invalid comment; missing closing '*/'");
CHECK((scan_string("/***/", true) == json::lexer::token_type::end_of_input));
CHECK((scan_string("/* true */", true) == json::lexer::token_type::end_of_input));
CHECK((scan_string("/*/**/", true) == json::lexer::token_type::end_of_input));
CHECK((scan_string("/*/* */", true) == json::lexer::token_type::end_of_input));
CHECK((scan_string("//\n//\n", true) == json::lexer::token_type::end_of_input));
CHECK((scan_string("/**//**//**/", true) == json::lexer::token_type::end_of_input));
}
}
|
