grammars: x{min,max} repetition operator (#6640)

* grammars: x{min,max} repetition operator + tweak +/*/? to avoid duplication of original over alternates

* grammars: handle `x{n}` and fix `x{n,n}`

* grammars: document new repetition operators

* grammars: uniform use of int for min & max

* grammars: refactor parser test

* grammar: parsing tests w/ natural pretty print of updated expectations

* grammars: much prettier print of expectations (+ TEST_GRAMMAR_PARSER_PRINT_ALL=1 to force all)

* grammars: improve test pretty print again

* grammars: pretty print rules and chars

* grammars: fix copy rule skipping

* grammars: disallow `a{,}` (not allowed in regexps)

* Update common/grammar-parser.cpp

Co-authored-by: Clint Herron <hanclinto@gmail.com>

* grammars: fix copy rule skipping (again) & display of expectations

* grammars: more test cases

* grammars: update reps parsing to bring ? / * / + closer to before

* json: use new GBNF repetitions{m,n} syntax

* grammars: update performance gotchas w/ repetition advice

* Update examples/json_schema_to_grammar.py

Co-authored-by: Clint Herron <hanclinto@gmail.com>

* Update examples/server/public/json-schema-to-grammar.mjs

Co-authored-by: Clint Herron <hanclinto@gmail.com>

* grammars: comment on rule repetitions

* grammars: ensure unambiguous number alternatives

* grammar: nit typo switched error msgs

* grammar: nit numbering in comment

* json: update numeric rule to be unambiguous

* Apply suggestions from code review

Co-authored-by: Clint Herron <hanclinto@gmail.com>

* Update examples/server/public/json-schema-to-grammar.mjs

Co-authored-by: Clint Herron <hanclinto@gmail.com>

* json: fix integral-part

* grammar: add repetition tests

---------

Co-authored-by: Clint Herron <hanclinto@gmail.com>
This commit is contained in:
Olivier Chafik 2024-06-06 10:07:06 +01:00 committed by GitHub
parent f5d7b268ec
commit 55b2d0849d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 736 additions and 418 deletions

View file

@ -292,6 +292,82 @@ static void test_quantifiers() {
"catyyy",
}
);
test_grammar(
"simple exact repetition",
// Grammar
R"""(
root ::= [ab]{4}
)""",
// Passing strings
{
"aaaa",
"bbbb",
"abab",
},
// Failing strings
{
"a",
"b",
"aaaaa",
}
);
test_grammar(
"simple min repetition",
// Grammar
R"""(
root ::= [ab]{4,}
)""",
// Passing strings
{
"aaaa",
"aaaaab",
"bbbb",
"ababab",
},
// Failing strings
{
"",
"aba",
}
);
test_grammar(
"simple max repetition",
// Grammar
R"""(
root ::= [ab]{0,4}
)""",
// Passing strings
{
"",
"a",
"aa",
"aaa",
"aaab",
},
// Failing strings
{
"aaaaa",
}
);
test_grammar(
"min / max repetition",
// Grammar
R"""(
root ::= ("0x" [A-F0-9]{2} " "?){3,5}
)""",
// Passing strings
{
"0xFF 0x12 0xAB",
"0xFF 0x12 0xAB 0x00 0x00",
},
// Failing strings
{
"",
"0xFF",
"0xFF 0x12",
"0xFF 0x12 0xAB 0x00 0x00 0x00",
}
);
}
static void test_failure_missing_root() {

View file

@ -7,28 +7,79 @@
#include <cassert>
int main()
{
grammar_parser::parse_state parsed_grammar;
static const char * type_str(llama_gretype type) {
switch (type) {
case LLAMA_GRETYPE_CHAR: return "LLAMA_GRETYPE_CHAR";
case LLAMA_GRETYPE_CHAR_NOT: return "LLAMA_GRETYPE_CHAR_NOT";
case LLAMA_GRETYPE_CHAR_ALT: return "LLAMA_GRETYPE_CHAR_ALT";
case LLAMA_GRETYPE_CHAR_RNG_UPPER: return "LLAMA_GRETYPE_CHAR_RNG_UPPER";
case LLAMA_GRETYPE_RULE_REF: return "LLAMA_GRETYPE_RULE_REF";
case LLAMA_GRETYPE_ALT: return "LLAMA_GRETYPE_ALT";
case LLAMA_GRETYPE_END: return "LLAMA_GRETYPE_END";
default: return "?";
}
}
const char *grammar_bytes = R"""(root ::= (expr "=" term "\n")+
expr ::= term ([-+*/] term)*
term ::= [0-9]+)""";
static void verify_parsing(const char *grammar_bytes, const std::vector<std::pair<std::string, uint32_t>> expected, const std::vector<llama_grammar_element> &expected_rules) {
uint32_t index = 0;
grammar_parser::parse_state parsed_grammar = grammar_parser::parse(grammar_bytes);
parsed_grammar = grammar_parser::parse(grammar_bytes);
std::map<uint32_t, std::string> symbol_names;
for (auto it = parsed_grammar.symbol_ids.begin(); it != parsed_grammar.symbol_ids.end(); ++it) {
symbol_names[it->second] = it->first;
}
std::vector<std::pair<std::string, uint32_t>> expected = {
{"expr", 2},
{"expr_5", 5},
{"expr_6", 6},
{"root", 0},
{"root_1", 1},
{"root_4", 4},
{"term", 3},
{"term_7", 7},
auto print_all = [&]() {
fprintf(stderr, " verify_parsing(R\"\"\"(%s)\"\"\", {\n", grammar_bytes);
for (auto it = parsed_grammar.symbol_ids.begin(); it != parsed_grammar.symbol_ids.end(); ++it) {
fprintf(stderr, " {\"%s\", %u},\n", it->first.c_str(), it->second);
}
fprintf(stderr, " }, {\n");
for (size_t i_rule = 0; i_rule < parsed_grammar.rules.size(); i_rule++) {
fprintf(stderr, " // %s (index %zu)\n", symbol_names[i_rule].c_str(), i_rule);
auto & rule = parsed_grammar.rules[i_rule];
for (uint32_t i = 0; i < rule.size(); i++) {
std::string rule_str;
fprintf(stderr, " {%s, ", type_str(rule[i].type));
if (rule[i].type == LLAMA_GRETYPE_CHAR || rule[i].type == LLAMA_GRETYPE_CHAR_ALT ||
rule[i].type == LLAMA_GRETYPE_CHAR_NOT || rule[i].type == LLAMA_GRETYPE_CHAR_RNG_UPPER) {
char c = rule[i].value;
if (c == '\n') {
fprintf(stderr, "'\\n'");
} else if (c == '\t') {
fprintf(stderr, "'\\t'");
} else if (c == '\r') {
fprintf(stderr, "'\\r'");
} else if (c == '\0') {
fprintf(stderr, "'\\0'");
} else {
fprintf(stderr, "'%c'", c);
}
} else if (rule[i].type == LLAMA_GRETYPE_RULE_REF) {
fprintf(stderr, "/* %s */ %u", symbol_names[rule[i].value].c_str(), rule[i].value);
} else {
fprintf(stderr, "%u", rule[i].value);
}
fprintf(stderr, "},\n");
}
}
fprintf(stderr, " });\n");
};
uint32_t index = 0;
if (getenv("TEST_GRAMMAR_PARSER_PRINT_ALL")) {
print_all();
fprintf(stderr, "\n");
return;
}
fprintf(stderr, "Testing grammar:%s\n", grammar_bytes);
if (parsed_grammar.symbol_ids.size() != expected.size()) {
fprintf(stderr, "Code to update expectation (set TEST_GRAMMAR_PARSER_PRINT_ALL=1 to print all):\n");
print_all();
assert(parsed_grammar.symbol_ids.size() == expected.size());
}
for (auto it = parsed_grammar.symbol_ids.begin(); it != parsed_grammar.symbol_ids.end(); ++it)
{
std::string key = it->first;
@ -38,51 +89,18 @@ term ::= [0-9]+)""";
// pretty print error message before asserting
if (expected_pair.first != key || expected_pair.second != value)
{
fprintf(stderr, "index: %u\n", index);
fprintf(stderr, "expected_pair: %s, %u\n", expected_pair.first.c_str(), expected_pair.second);
fprintf(stderr, "actual_pair: %s, %u\n", key.c_str(), value);
fprintf(stderr, "expected_pair != actual_pair\n");
fprintf(stderr, "Code to update expectation (set TEST_GRAMMAR_PARSER_PRINT_ALL=1 to print all):\n");
print_all();
}
assert(expected_pair.first == key && expected_pair.second == value);
index++;
}
std::vector<llama_grammar_element> expected_rules = {
{LLAMA_GRETYPE_RULE_REF, 4},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_RULE_REF, 2},
{LLAMA_GRETYPE_CHAR, 61},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_CHAR, 10},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_RULE_REF, 6},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_RULE_REF, 7},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_RULE_REF, 1},
{LLAMA_GRETYPE_RULE_REF, 4},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_RULE_REF, 1},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_CHAR, 45},
{LLAMA_GRETYPE_CHAR_ALT, 43},
{LLAMA_GRETYPE_CHAR_ALT, 42},
{LLAMA_GRETYPE_CHAR_ALT, 47},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_RULE_REF, 5},
{LLAMA_GRETYPE_RULE_REF, 6},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_CHAR, 48},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, 57},
{LLAMA_GRETYPE_RULE_REF, 7},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_CHAR, 48},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, 57},
{LLAMA_GRETYPE_END, 0},
};
index = 0;
for (auto rule : parsed_grammar.rules)
@ -97,28 +115,306 @@ term ::= [0-9]+)""";
if (expected_element.type != element.type || expected_element.value != element.value)
{
fprintf(stderr, "index: %u\n", index);
fprintf(stderr, "expected_element: %d, %u\n", expected_element.type, expected_element.value);
fprintf(stderr, "actual_element: %d, %u\n", element.type, element.value);
fprintf(stderr, "expected_element: %s, %u\n", type_str(expected_element.type), expected_element.value);
fprintf(stderr, "actual_element: %s, %u\n", type_str(element.type), element.value);
fprintf(stderr, "expected_element != actual_element\n");
fprintf(stderr, "all elements:\n");
fprintf(stderr, "Code to update expectation (set TEST_GRAMMAR_PARSER_PRINT_ALL=1 to print all):\n");
print_all();
}
assert(expected_element.type == element.type && expected_element.value == element.value);
index++;
}
}
}
const char *longer_grammar_bytes = R"""(
root ::= (expr "=" ws term "\n")+
expr ::= term ([-+*/] term)*
term ::= ident | num | "(" ws expr ")" ws
ident ::= [a-z] [a-z0-9_]* ws
num ::= [0-9]+ ws
ws ::= [ \t\n]*
)""";
static void verify_failure(const char *grammar_bytes) {
fprintf(stderr, "Testing expected failure:%s\n", grammar_bytes);
auto result = grammar_parser::parse(grammar_bytes);
assert(result.rules.empty() && "should have failed");
}
parsed_grammar = grammar_parser::parse(longer_grammar_bytes);
int main()
{
verify_failure(R"""(
root ::= "a"{,}"
)""");
expected = {
verify_failure(R"""(
root ::= "a"{,10}"
)""");
verify_parsing(R"""(
root ::= "a"
)""", {
{"root", 0},
}, {
// root (index 0)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_END, 0},
});
verify_parsing(R"""(
root ::= "a" | [bdx-z] | [^1-3]
)""", {
{"root", 0},
}, {
// root (index 0)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_CHAR, 'b'},
{LLAMA_GRETYPE_CHAR_ALT, 'd'},
{LLAMA_GRETYPE_CHAR_ALT, 'x'},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, 'z'},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_CHAR_NOT, '1'},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, '3'},
{LLAMA_GRETYPE_END, 0},
});
verify_parsing(R"""(
root ::= a+
a ::= "a"
)""", {
{"a", 1},
{"root", 0},
{"root_2", 2},
}, {
// root (index 0)
{LLAMA_GRETYPE_RULE_REF, /* a */ 1},
{LLAMA_GRETYPE_RULE_REF, /* root_2 */ 2},
{LLAMA_GRETYPE_END, 0},
// a (index 1)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_END, 0},
// root_2 (index 2)
{LLAMA_GRETYPE_RULE_REF, /* a */ 1},
{LLAMA_GRETYPE_RULE_REF, /* root_2 */ 2},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
});
verify_parsing(R"""(
root ::= "a"+
)""", {
{"root", 0},
{"root_1", 1},
}, {
// root (index 0)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_RULE_REF, /* root_1 */ 1},
{LLAMA_GRETYPE_END, 0},
// root_1 (index 1)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_RULE_REF, /* root_1 */ 1},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
});
verify_parsing(R"""(
root ::= a?
a ::= "a"
)""", {
{"a", 1},
{"root", 0},
{"root_2", 2},
}, {
// root (index 0)
{LLAMA_GRETYPE_RULE_REF, /* root_2 */ 2},
{LLAMA_GRETYPE_END, 0},
// a (index 1)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_END, 0},
// root_2 (index 2)
{LLAMA_GRETYPE_RULE_REF, /* a */ 1},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
});
verify_parsing(R"""(
root ::= "a"?
)""", {
{"root", 0},
{"root_1", 1},
}, {
// root (index 0)
{LLAMA_GRETYPE_RULE_REF, /* root_1 */ 1},
{LLAMA_GRETYPE_END, 0},
// root_1 (index 1)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
});
verify_parsing(R"""(
root ::= a*
a ::= "a"
)""", {
{"a", 1},
{"root", 0},
{"root_2", 2},
}, {
// root (index 0)
{LLAMA_GRETYPE_RULE_REF, /* root_2 */ 2},
{LLAMA_GRETYPE_END, 0},
// a (index 1)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_END, 0},
// root_2 (index 2)
{LLAMA_GRETYPE_RULE_REF, /* a */ 1},
{LLAMA_GRETYPE_RULE_REF, /* root_2 */ 2},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
});
verify_parsing(R"""(
root ::= "a"*
)""", {
{"root", 0},
{"root_1", 1},
}, {
// root (index 0)
{LLAMA_GRETYPE_RULE_REF, /* root_1 */ 1},
{LLAMA_GRETYPE_END, 0},
// root_1 (index 1)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_RULE_REF, /* root_1 */ 1},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
});
verify_parsing(R"""(
root ::= "a"{2}
)""", {
{"root", 0},
}, {
// root (index 0)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_END, 0},
});
verify_parsing(R"""(
root ::= "a"{2,}
)""", {
{"root", 0},
{"root_1", 1},
}, {
// root (index 0)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_RULE_REF, /* root_1 */ 1},
{LLAMA_GRETYPE_END, 0},
// root_1 (index 1)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_RULE_REF, /* root_1 */ 1},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
});
verify_parsing(R"""(
root ::= "a"{ 4}
)""", {
{"root", 0},
}, {
// root (index 0)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_END, 0},
});
verify_parsing(R"""(
root ::= "a"{2,4}
)""", {
{"root", 0},
{"root_1", 1},
{"root_2", 2},
}, {
// root (index 0)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_RULE_REF, /* root_2 */ 2},
{LLAMA_GRETYPE_END, 0},
// root_1 (index 1)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
// root_2 (index 2)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_RULE_REF, /* root_1 */ 1},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
});
verify_parsing(R"""(
root ::= (expr "=" term "\n")+
expr ::= term ([-+*/] term)*
term ::= [0-9]+
)""", {
{"expr", 2},
{"expr_5", 5},
{"expr_6", 6},
{"root", 0},
{"root_1", 1},
{"root_4", 4},
{"term", 3},
{"term_7", 7},
}, {
// root (index 0)
{LLAMA_GRETYPE_RULE_REF, /* root_1 */ 1},
{LLAMA_GRETYPE_RULE_REF, /* root_4 */ 4},
{LLAMA_GRETYPE_END, 0},
// root_1 (index 1)
{LLAMA_GRETYPE_RULE_REF, /* expr */ 2},
{LLAMA_GRETYPE_CHAR, '='},
{LLAMA_GRETYPE_RULE_REF, /* term */ 3},
{LLAMA_GRETYPE_CHAR, '\n'},
{LLAMA_GRETYPE_END, 0},
// expr (index 2)
{LLAMA_GRETYPE_RULE_REF, /* term */ 3},
{LLAMA_GRETYPE_RULE_REF, /* expr_6 */ 6},
{LLAMA_GRETYPE_END, 0},
// term (index 3)
{LLAMA_GRETYPE_CHAR, '0'},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, '9'},
{LLAMA_GRETYPE_RULE_REF, /* term_7 */ 7},
{LLAMA_GRETYPE_END, 0},
// root_4 (index 4)
{LLAMA_GRETYPE_RULE_REF, /* root_1 */ 1},
{LLAMA_GRETYPE_RULE_REF, /* root_4 */ 4},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
// expr_5 (index 5)
{LLAMA_GRETYPE_CHAR, '-'},
{LLAMA_GRETYPE_CHAR_ALT, '+'},
{LLAMA_GRETYPE_CHAR_ALT, '*'},
{LLAMA_GRETYPE_CHAR_ALT, '/'},
{LLAMA_GRETYPE_RULE_REF, /* term */ 3},
{LLAMA_GRETYPE_END, 0},
// expr_6 (index 6)
{LLAMA_GRETYPE_RULE_REF, /* expr_5 */ 5},
{LLAMA_GRETYPE_RULE_REF, /* expr_6 */ 6},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
// term_7 (index 7)
{LLAMA_GRETYPE_CHAR, '0'},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, '9'},
{LLAMA_GRETYPE_RULE_REF, /* term_7 */ 7},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
});
verify_parsing(R"""(
root ::= (expr "=" ws term "\n")+
expr ::= term ([-+*/] term)*
term ::= ident | num | "(" ws expr ")" ws
ident ::= [a-z] [a-z0-9_]* ws
num ::= [0-9]+ ws
ws ::= [ \t\n]*
)""", {
{"expr", 2},
{"expr_6", 6},
{"expr_7", 7},
@ -132,119 +428,88 @@ term ::= [0-9]+)""";
{"term", 4},
{"ws", 3},
{"ws_12", 12},
};
index = 0;
for (auto it = parsed_grammar.symbol_ids.begin(); it != parsed_grammar.symbol_ids.end(); ++it)
{
std::string key = it->first;
uint32_t value = it->second;
std::pair<std::string, uint32_t> expected_pair = expected[index];
// pretty print error message before asserting
if (expected_pair.first != key || expected_pair.second != value)
{
fprintf(stderr, "expected_pair: %s, %u\n", expected_pair.first.c_str(), expected_pair.second);
fprintf(stderr, "actual_pair: %s, %u\n", key.c_str(), value);
fprintf(stderr, "expected_pair != actual_pair\n");
}
assert(expected_pair.first == key && expected_pair.second == value);
index++;
}
expected_rules = {
{LLAMA_GRETYPE_RULE_REF, 5},
}, {
// root (index 0)
{LLAMA_GRETYPE_RULE_REF, /* root_1 */ 1},
{LLAMA_GRETYPE_RULE_REF, /* root_5 */ 5},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_RULE_REF, 2},
{LLAMA_GRETYPE_CHAR, 61},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_RULE_REF, 4},
{LLAMA_GRETYPE_CHAR, 10},
// root_1 (index 1)
{LLAMA_GRETYPE_RULE_REF, /* expr */ 2},
{LLAMA_GRETYPE_CHAR, '='},
{LLAMA_GRETYPE_RULE_REF, /* ws */ 3},
{LLAMA_GRETYPE_RULE_REF, /* term */ 4},
{LLAMA_GRETYPE_CHAR, '\n'},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_RULE_REF, 4},
{LLAMA_GRETYPE_RULE_REF, 7},
// expr (index 2)
{LLAMA_GRETYPE_RULE_REF, /* term */ 4},
{LLAMA_GRETYPE_RULE_REF, /* expr_7 */ 7},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_RULE_REF, 12},
// ws (index 3)
{LLAMA_GRETYPE_RULE_REF, /* ws_12 */ 12},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_RULE_REF, 8},
// term (index 4)
{LLAMA_GRETYPE_RULE_REF, /* ident */ 8},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_RULE_REF, 9},
{LLAMA_GRETYPE_RULE_REF, /* num */ 9},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_CHAR, 40},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_RULE_REF, 2},
{LLAMA_GRETYPE_CHAR, 41},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_CHAR, '('},
{LLAMA_GRETYPE_RULE_REF, /* ws */ 3},
{LLAMA_GRETYPE_RULE_REF, /* expr */ 2},
{LLAMA_GRETYPE_CHAR, ')'},
{LLAMA_GRETYPE_RULE_REF, /* ws */ 3},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_RULE_REF, 1},
{LLAMA_GRETYPE_RULE_REF, 5},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_RULE_REF, 1},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_CHAR, 45},
{LLAMA_GRETYPE_CHAR_ALT, 43},
{LLAMA_GRETYPE_CHAR_ALT, 42},
{LLAMA_GRETYPE_CHAR_ALT, 47},
{LLAMA_GRETYPE_RULE_REF, 4},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_RULE_REF, 6},
{LLAMA_GRETYPE_RULE_REF, 7},
// root_5 (index 5)
{LLAMA_GRETYPE_RULE_REF, /* root_1 */ 1},
{LLAMA_GRETYPE_RULE_REF, /* root_5 */ 5},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_CHAR, 97},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, 122},
{LLAMA_GRETYPE_RULE_REF, 10},
{LLAMA_GRETYPE_RULE_REF, 3},
// expr_6 (index 6)
{LLAMA_GRETYPE_CHAR, '-'},
{LLAMA_GRETYPE_CHAR_ALT, '+'},
{LLAMA_GRETYPE_CHAR_ALT, '*'},
{LLAMA_GRETYPE_CHAR_ALT, '/'},
{LLAMA_GRETYPE_RULE_REF, /* term */ 4},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_RULE_REF, 11},
{LLAMA_GRETYPE_RULE_REF, 3},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_CHAR, 97},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, 122},
{LLAMA_GRETYPE_CHAR_ALT, 48},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, 57},
{LLAMA_GRETYPE_CHAR_ALT, 95},
{LLAMA_GRETYPE_RULE_REF, 10},
// expr_7 (index 7)
{LLAMA_GRETYPE_RULE_REF, /* expr_6 */ 6},
{LLAMA_GRETYPE_RULE_REF, /* expr_7 */ 7},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_CHAR, 48},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, 57},
{LLAMA_GRETYPE_RULE_REF, 11},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_CHAR, 48},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, 57},
// ident (index 8)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, 'z'},
{LLAMA_GRETYPE_RULE_REF, /* ident_10 */ 10},
{LLAMA_GRETYPE_RULE_REF, /* ws */ 3},
{LLAMA_GRETYPE_END, 0},
{LLAMA_GRETYPE_CHAR, 32},
{LLAMA_GRETYPE_CHAR_ALT, 9},
{LLAMA_GRETYPE_CHAR_ALT, 10},
{LLAMA_GRETYPE_RULE_REF, 12},
// num (index 9)
{LLAMA_GRETYPE_CHAR, '0'},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, '9'},
{LLAMA_GRETYPE_RULE_REF, /* num_11 */ 11},
{LLAMA_GRETYPE_RULE_REF, /* ws */ 3},
{LLAMA_GRETYPE_END, 0},
// ident_10 (index 10)
{LLAMA_GRETYPE_CHAR, 'a'},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, 'z'},
{LLAMA_GRETYPE_CHAR_ALT, '0'},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, '9'},
{LLAMA_GRETYPE_CHAR_ALT, '_'},
{LLAMA_GRETYPE_RULE_REF, /* ident_10 */ 10},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
};
index = 0;
for (auto rule : parsed_grammar.rules)
{
// compare rule to expected rule
for (uint32_t i = 0; i < rule.size(); i++)
{
llama_grammar_element element = rule[i];
llama_grammar_element expected_element = expected_rules[index];
// pretty print error message before asserting
if (expected_element.type != element.type || expected_element.value != element.value)
{
fprintf(stderr, "index: %u\n", index);
fprintf(stderr, "expected_element: %d, %u\n", expected_element.type, expected_element.value);
fprintf(stderr, "actual_element: %d, %u\n", element.type, element.value);
fprintf(stderr, "expected_element != actual_element\n");
}
assert(expected_element.type == element.type && expected_element.value == element.value);
index++;
}
}
// num_11 (index 11)
{LLAMA_GRETYPE_CHAR, '0'},
{LLAMA_GRETYPE_CHAR_RNG_UPPER, '9'},
{LLAMA_GRETYPE_RULE_REF, /* num_11 */ 11},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
// ws_12 (index 12)
{LLAMA_GRETYPE_CHAR, ' '},
{LLAMA_GRETYPE_CHAR_ALT, '\t'},
{LLAMA_GRETYPE_CHAR_ALT, '\n'},
{LLAMA_GRETYPE_RULE_REF, /* ws_12 */ 12},
{LLAMA_GRETYPE_ALT, 0},
{LLAMA_GRETYPE_END, 0},
});
return 0;
}

View file

@ -105,9 +105,9 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
R"""(
array ::= "[" space ( value ("," space value)* )? "]" space
boolean ::= ("true" | "false") space
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
decimal-part ::= [0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
integral-part ::= [0-9] | [1-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
decimal-part ::= [0-9]{1,16}
integral-part ::= [0] | [1-9] [0-9]{0,15}
null ::= "null" space
number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
object ::= "{" space ( string ":" space value ("," space string ":" space value)* )? "}" space
@ -130,18 +130,18 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
]
})""",
R"""(
date ::= [0-9] [0-9] [0-9] [0-9] "-" ( "0" [1-9] | "1" [0-2] ) "-" ( "0" [1-9] | [1-2] [0-9] | "3" [0-1] )
date ::= [0-9]{4} "-" ( "0" [1-9] | "1" [0-2] ) "-" ( "0" [1-9] | [1-2] [0-9] | "3" [0-1] )
date-string ::= "\"" date "\"" space
date-time ::= date "T" time
date-time-string ::= "\"" date-time "\"" space
root ::= "[" space tuple-0 "," space uuid "," space tuple-2 "," space tuple-3 "]" space
space ::= " "?
time ::= ([01] [0-9] | "2" [0-3]) ":" [0-5] [0-9] ":" [0-5] [0-9] ( "." [0-9] [0-9] [0-9] )? ( "Z" | ( "+" | "-" ) ( [01] [0-9] | "2" [0-3] ) ":" [0-5] [0-9] )
time ::= ([01] [0-9] | "2" [0-3]) ":" [0-5] [0-9] ":" [0-5] [0-9] ( "." [0-9]{3} )? ( "Z" | ( "+" | "-" ) ( [01] [0-9] | "2" [0-3] ) ":" [0-5] [0-9] )
time-string ::= "\"" time "\"" space
tuple-0 ::= date-string
tuple-2 ::= time-string
tuple-3 ::= date-time-string
uuid ::= "\"" [0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F] "-" [0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F] "-" [0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F] "-" [0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F] "-" [0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F][0-9a-fA-F] "\"" space
uuid ::= "\"" [0-9a-fA-F]{8} "-" [0-9a-fA-F]{4} "-" [0-9a-fA-F]{4} "-" [0-9a-fA-F]{4} "-" [0-9a-fA-F]{12} "\"" space
)"""
});
@ -152,7 +152,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
"type": "string"
})""",
R"""(
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
root ::= "\"" char* "\"" space
space ::= " "?
)"""
@ -166,7 +166,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
"minLength": 1
})""",
R"""(
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
root ::= "\"" char+ "\"" space
space ::= " "?
)"""
@ -180,8 +180,8 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
"minLength": 3
})""",
R"""(
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
root ::= "\"" char char char (char)* "\"" space
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
root ::= "\"" char{3,} "\"" space
space ::= " "?
)"""
});
@ -194,8 +194,8 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
"maxLength": 3
})""",
R"""(
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
root ::= "\"" (char (char (char)?)?)? "\"" space
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
root ::= "\"" char{0,3} "\"" space
space ::= " "?
)"""
});
@ -209,8 +209,8 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
"maxLength": 4
})""",
R"""(
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
root ::= "\"" char (char (char (char)?)?)? "\"" space
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
root ::= "\"" char{1,4} "\"" space
space ::= " "?
)"""
});
@ -234,7 +234,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
"type": "integer"
})""",
R"""(
integral-part ::= [0-9] | [1-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
integral-part ::= [0] | [1-9] [0-9]{0,15}
root ::= ("-"? integral-part) space
space ::= " "?
)"""
@ -283,7 +283,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
"prefixItems": [{ "type": "string" }]
})""",
R"""(
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
root ::= "[" space string "]" space
space ::= " "?
string ::= "\"" char* "\"" space
@ -297,9 +297,9 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
"prefixItems": [{ "type": "string" }, { "type": "number" }]
})""",
R"""(
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
decimal-part ::= [0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
integral-part ::= [0-9] | [1-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
decimal-part ::= [0-9]{1,16}
integral-part ::= [0] | [1-9] [0-9]{0,15}
number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
root ::= "[" space string "," space number "]" space
space ::= " "?
@ -314,8 +314,8 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
"type": "number"
})""",
R"""(
decimal-part ::= [0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
integral-part ::= [0-9] | [1-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
decimal-part ::= [0-9]{1,16}
integral-part ::= [0] | [1-9] [0-9]{0,15}
root ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
space ::= " "?
)"""
@ -332,7 +332,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
})""",
R"""(
boolean ::= ("true" | "false") space
root ::= "[" space boolean "," space boolean ("," space boolean)* "]" space
root ::= "[" space boolean ("," space boolean)+ "]" space
space ::= " "?
)"""
});
@ -348,7 +348,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
})""",
R"""(
boolean ::= ("true" | "false") space
root ::= "[" space (boolean)? "]" space
root ::= "[" space boolean? "]" space
space ::= " "?
)"""
});
@ -380,12 +380,12 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
"maxItems": 5
})""",
R"""(
decimal-part ::= [0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
decimal-part ::= [0-9]{1,16}
integer ::= ("-"? integral-part) space
integral-part ::= [0-9] | [1-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
integral-part ::= [0] | [1-9] [0-9]{0,15}
item ::= number | integer
number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
root ::= "[" space item "," space item "," space item ("," space item ("," space item)?)? "]" space
root ::= "[" space item ("," space item){2,4} "]" space
space ::= " "?
)"""
});
@ -438,7 +438,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
})""",
R"""(
dot ::= [^\x0A\x0D]
root ::= "\"" ("(" root-1 (root-1 (root-1)?)? ")")? root-1 root-1 root-1 "-" root-1 root-1 root-1 root-1 " " "aaa" ("a" ("a")?)? "nd" dot dot dot "\"" space
root ::= "\"" ("(" root-1{1,3} ")")? root-1{3,3} "-" root-1{4,4} " " "a"{3,5} "nd" dot dot dot "\"" space
root-1 ::= [0-9]
space ::= " "?
)"""
@ -466,7 +466,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
a-kv ::= "\"a\"" space ":" space string
b-kv ::= "\"b\"" space ":" space string
c-kv ::= "\"c\"" space ":" space string
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
root ::= "{" space b-kv "," space c-kv "," space a-kv "}" space
space ::= " "?
string ::= "\"" char* "\"" space
@ -486,7 +486,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
})""",
R"""(
a-kv ::= "\"a\"" space ":" space string
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
root ::= "{" space (a-kv )? "}" space
space ::= " "?
string ::= "\"" char* "\"" space
@ -510,7 +510,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
b-kv ::= "\"b\"" space ":" space string
b-rest ::= ( "," space c-kv )?
c-kv ::= "\"c\"" space ":" space string
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
root ::= "{" space (a-kv a-rest | b-kv b-rest | c-kv )? "}" space
space ::= " "?
string ::= "\"" char* "\"" space
@ -534,7 +534,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
a-kv ::= "\"a\"" space ":" space string
b-kv ::= "\"b\"" space ":" space string
c-kv ::= "\"c\"" space ":" space string
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
d-kv ::= "\"d\"" space ":" space string
d-rest ::= ( "," space c-kv )?
root ::= "{" space b-kv "," space a-kv ( "," space ( d-kv d-rest | c-kv ) )? "}" space
@ -554,9 +554,9 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
additional-kv ::= string ":" space additional-value
additional-kvs ::= additional-kv ( "," space additional-kv )*
additional-value ::= "[" space (number ("," space number)*)? "]" space
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
decimal-part ::= [0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
integral-part ::= [0-9] | [1-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
decimal-part ::= [0-9]{1,16}
integral-part ::= [0] | [1-9] [0-9]{0,15}
number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
root ::= "{" space (additional-kvs )? "}" space
space ::= " "?
@ -574,9 +574,9 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
R"""(
array ::= "[" space ( value ("," space value)* )? "]" space
boolean ::= ("true" | "false") space
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
decimal-part ::= [0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
integral-part ::= [0-9] | [1-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
decimal-part ::= [0-9]{1,16}
integral-part ::= [0] | [1-9] [0-9]{0,15}
null ::= "null" space
number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
object ::= "{" space ( string ":" space value ("," space string ":" space value)* )? "}" space
@ -596,9 +596,9 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
R"""(
array ::= "[" space ( value ("," space value)* )? "]" space
boolean ::= ("true" | "false") space
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
decimal-part ::= [0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
integral-part ::= [0-9] | [1-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
decimal-part ::= [0-9]{1,16}
integral-part ::= [0] | [1-9] [0-9]{0,15}
null ::= "null" space
number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
object ::= "{" space ( string ":" space value ("," space string ":" space value)* )? "}" space
@ -637,9 +637,9 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
a-kv ::= "\"a\"" space ":" space number
additional-kv ::= string ":" space string
additional-kvs ::= additional-kv ( "," space additional-kv )*
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
decimal-part ::= [0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
integral-part ::= [0-9] | [1-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
decimal-part ::= [0-9]{1,16}
integral-part ::= [0] | [1-9] [0-9]{0,15}
number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
root ::= "{" space a-kv ( "," space ( additional-kvs ) )? "}" space
space ::= " "?
@ -662,9 +662,9 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
a-rest ::= additional-kvs
additional-kv ::= string ":" space number
additional-kvs ::= additional-kv ( "," space additional-kv )*
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
decimal-part ::= [0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
integral-part ::= [0-9] | [1-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
decimal-part ::= [0-9]{1,16}
integral-part ::= [0] | [1-9] [0-9]{0,15}
number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
root ::= "{" space (a-kv a-rest | additional-kvs )? "}" space
space ::= " "?
@ -690,9 +690,9 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
additional-kvs ::= additional-kv ( "," space additional-kv )*
b-kv ::= "\"b\"" space ":" space number
b-rest ::= additional-kvs
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
decimal-part ::= [0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
integral-part ::= [0-9] | [1-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
decimal-part ::= [0-9]{1,16}
integral-part ::= [0] | [1-9] [0-9]{0,15}
number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
root ::= "{" space a-kv ( "," space ( b-kv b-rest | additional-kvs ) )? "}" space
space ::= " "?
@ -721,7 +721,7 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
}
})""",
R"""(
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F])
char ::= [^"\\] | "\\" (["\\/bfnrt] | "u" [0-9a-fA-F]{4})
foo ::= "{" space foo-a-kv "}" space
foo-a-kv ::= "\"a\"" space ":" space string
root ::= foo
@ -753,10 +753,10 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
alternative-1 ::= bar
bar ::= "{" space (bar-b-kv )? "}" space
bar-b-kv ::= "\"b\"" space ":" space number
decimal-part ::= [0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
decimal-part ::= [0-9]{1,16}
foo ::= "{" space (foo-a-kv )? "}" space
foo-a-kv ::= "\"a\"" space ":" space number
integral-part ::= [0-9] | [1-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
integral-part ::= [0] | [1-9] [0-9]{0,15}
number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
root ::= alternative-0 | alternative-1
space ::= " "?
@ -799,8 +799,8 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
c-kv ::= "\"c\"" space ":" space number
d-kv ::= "\"d\"" space ":" space number
d-rest ::= ( "," space c-kv )?
decimal-part ::= [0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
integral-part ::= [0-9] | [1-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
decimal-part ::= [0-9]{1,16}
integral-part ::= [0] | [1-9] [0-9]{0,15}
number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
root ::= "{" space a-kv "," space b-kv ( "," space ( d-kv d-rest | c-kv ) )? "}" space
space ::= " "?
@ -842,8 +842,8 @@ static void test_all(const std::string & lang, std::function<void(const TestCase
"definitions": {}
})""",
R"""(
decimal-part ::= [0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
integral-part ::= [0-9] | [1-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9] ([0-9])?)?)?)?)?)?)?)?)?)?)?)?)?)?)?
decimal-part ::= [0-9]{1,16}
integral-part ::= [0] | [1-9] [0-9]{0,15}
number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
number- ::= "{" space number-number-kv "}" space
number-kv ::= "\"number\"" space ":" space number-