common/peg : implement ac parser for stricter grammar generation (#24869)

* common/peg : implement ac parser

* cont : extract functions

* cont : tidy up

* cont : remove a test

* cont : move ac() def
This commit is contained in:
Aldehir Rojas
2026-06-21 16:20:58 -05:00
committed by GitHub
parent 7c082bc417
commit 52b3df0023
4 changed files with 190 additions and 34 deletions
+14 -1
View File
@@ -275,6 +275,11 @@ struct common_peg_gbnf_parser {
std::string grammar;
};
struct common_peg_ac_parser {
common_peg_parser_id child;
std::vector<std::string> delimiters;
};
// Variant holding all parser types
using common_peg_parser_variant = std::variant<
common_peg_epsilon_parser,
@@ -296,7 +301,8 @@ using common_peg_parser_variant = std::variant<
common_peg_ref_parser,
common_peg_atomic_parser,
common_peg_tag_parser,
common_peg_gbnf_parser
common_peg_gbnf_parser,
common_peg_ac_parser
>;
class common_peg_arena {
@@ -514,6 +520,13 @@ class common_peg_parser_builder {
// the child's grammar. Parsing delegates entirely to the child.
common_peg_parser gbnf(const common_peg_parser & p, const std::string & grammar) { return add(common_peg_gbnf_parser{p, grammar}); }
// Wraps a child parser but emits a GBNF grammar built from the Aho-Corasick
// automaton of `delimiters`, matching everything up to and including the
// first delimiter. Parsing delegates entirely to the child, which is
// responsible for consuming the delimiter (e.g. until(D) + literal(D)).
common_peg_parser ac(const common_peg_parser & p, const std::vector<std::string> & delimiters);
common_peg_parser ac(const common_peg_parser & p, const std::string & delimiter) { return ac(p, std::vector<std::string>{delimiter}); }
void set_root(const common_peg_parser & p);
common_peg_arena build();