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
245
246
247
248
249
250
|
#include "tests.h"
#include "json-schema-to-grammar.h"
#include <regex>
static std::string trim_leading_space(const std::string & s) {
static const std::regex leading_ws_re = std::regex(R"((^|\n)\s+)");
return std::regex_replace(s, leading_ws_re, "$1");
}
static void assert_gbnf_equal(testing & t, const std::string & expected, const std::string & actual) {
t.assert_equal("gbnf are equal", trim_leading_space(expected), trim_leading_space(actual));
}
void test_gbnf_generation(testing &t) {
t.test("literal grammar generation", [](testing &t) {
auto parser = build_peg_parser([](common_peg_parser_builder & p) {
return p.literal("hello");
});
auto gbnf = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder);
});
assert_gbnf_equal(t, R"""(
root ::= "hello"
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf);
});
t.test("char class grammar", [](testing &t) {
auto parser = build_peg_parser([](common_peg_parser_builder & p) {
return p.chars("[a-z]", 1, 1);
});
auto gbnf = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder);
});
assert_gbnf_equal(t, R"""(
root ::= [a-z]
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf);
});
t.test("sequence grammar", [](testing &t) {
auto parser = build_peg_parser([](common_peg_parser_builder & p) {
return p.literal("hello") + p.literal(" ") + p.literal("world");
});
auto gbnf = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder);
});
assert_gbnf_equal(t, R"""(
root ::= "hello" " " "world"
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf);
});
t.test("choice grammar", [](testing &t) {
auto parser = build_peg_parser([](common_peg_parser_builder & p) {
return p.literal("cat") | p.literal("dog");
});
auto gbnf = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder);
});
assert_gbnf_equal(t, R"""(
root ::= "cat" | "dog"
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf);
});
t.test("one_or_more grammar", [](testing &t) {
auto parser = build_peg_parser([](common_peg_parser_builder & p) {
return p.one_or_more(p.literal("a"));
});
auto gbnf = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder);
});
assert_gbnf_equal(t, R"""(
root ::= "a"+
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf);
});
t.test("zero_or_more grammar", [](testing &t) {
auto parser = build_peg_parser([](common_peg_parser_builder & p) {
return p.zero_or_more(p.literal("a"));
});
auto gbnf = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder);
});
assert_gbnf_equal(t, R"""(
root ::= "a"*
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf);
});
t.test("optional grammar", [](testing &t) {
auto parser = build_peg_parser([](common_peg_parser_builder & p) {
return p.literal("hello") + p.optional(p.literal(" world"));
});
auto gbnf = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder);
});
assert_gbnf_equal(t, R"""(
root ::= "hello" " world"?
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf);
});
t.test("until grammar", [](testing &t) {
auto parser = build_peg_parser([](common_peg_parser_builder & p) {
return p.until("</tag>");
});
auto gbnf = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder);
});
assert_gbnf_equal(t, R"""(
root ::= ([^<] | "<" [^/] | "</" [^t] | "</t" [^a] | "</ta" [^g] | "</tag" [^>])*
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf);
});
t.test("complex expressions with parentheses", [](testing &t) {
auto parser = build_peg_parser([](common_peg_parser_builder & p) {
return p.one_or_more(p.literal("a") | p.literal("b"));
});
auto gbnf = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder);
});
assert_gbnf_equal(t, R"""(
root ::= ("a" | "b")+
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf);
});
t.test("rule references", [](testing &t) {
auto parser = build_peg_parser([](common_peg_parser_builder & p) {
auto digit = p.rule("digit", p.chars("[0-9]", 1, 1));
return p.one_or_more(digit);
});
auto gbnf = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder);
});
assert_gbnf_equal(t, R"""(
digit ::= [0-9]
root ::= digit+
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf);
});
t.test("escaping in literals", [](testing &t) {
auto parser = build_peg_parser([](common_peg_parser_builder & p) {
return p.literal("hello\nworld\n!");
});
auto gbnf = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder);
});
assert_gbnf_equal(t, R"""(
root ::= "hello\nworld\n!"
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf);
});
t.test("operator<< (whitespace insertion)", [](testing &t) {
auto parser = build_peg_parser([](common_peg_parser_builder & p) {
return p.literal("hello") << p.literal("world");
});
auto gbnf = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder);
});
assert_gbnf_equal(t, R"""(
root ::= "hello" space "world"
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf);
});
t.test("emit only reachable rules", [](testing &t) {
auto parser = build_peg_parser([](common_peg_parser_builder & p) {
p.rule("orphan", p.literal("orphan"));
return p.literal("hello") + p.rule("child", p.literal(" world"));
});
auto gbnf = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder);
});
assert_gbnf_equal(t, R"""(
child ::= " world"
root ::= "hello" child
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf);
});
t.test("emit only trigger rules (and references)", [](testing &t) {
auto parser = build_peg_parser([](common_peg_parser_builder & p) {
auto rule1 = p.rule("rule-1", p.literal("a") + p.ref("rule-2"));
p.rule("rule-2", p.literal("b") + p.ref("rule-3"), true);
p.rule("rule-3", p.literal("c") + p.ref("rule-4"));
p.rule("rule-4", p.literal("d"), true);
return rule1;
});
auto gbnf = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder);
});
assert_gbnf_equal(t, R"""(
root ::= rule-1
rule-1 ::= "a" rule-2
rule-2 ::= "b" rule-3
rule-3 ::= "c" rule-4
rule-4 ::= "d"
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf);
auto gbnf_lazy = build_grammar([&](const common_grammar_builder & builder) {
parser.build_grammar(builder, true);
});
assert_gbnf_equal(t, R"""(
root ::= rule-2 | rule-4
rule-2 ::= "b" rule-3
rule-3 ::= "c" rule-4
rule-4 ::= "d"
space ::= | " " | "\n"{1,2} [ \t]{0,20}
)""", gbnf_lazy);
});
}
|
