Method build_grammar

subprojects/llama.cpp/common/peg-parser.cpp:1249–1430

GBNF generation implementation

// GBNF generation implementation
void common_peg_arena::build_grammar(const common_grammar_builder & builder, bool lazy) const {
    // Generate GBNF for a parser
    std::function<std::string(common_peg_parser_id)> to_gbnf = [&](common_peg_parser_id id) -> std::string {
        const auto & parser = parsers_.at(id);

        return std::visit([&](const auto & p) -> std::string {
            using T = std::decay_t<decltype(p)>;

            if constexpr (std::is_same_v<T, common_peg_epsilon_parser> ||
                          std::is_same_v<T, common_peg_start_parser> ||
                          std::is_same_v<T, common_peg_end_parser>) {
                return "";
            } else if constexpr (std::is_same_v<T, common_peg_literal_parser>) {
                return gbnf_format_literal(p.literal);
            } else if constexpr (std::is_same_v<T, common_peg_sequence_parser>) {
                std::string s;
                for (const auto & child : p.children) {
                    if (!s.empty()) {
                        s += " ";
                    }
                    auto child_gbnf = to_gbnf(child);
                    const auto & child_parser = parsers_.at(child);
                    if (std::holds_alternative<common_peg_choice_parser>(child_parser) ||
                        std::holds_alternative<common_peg_sequence_parser>(child_parser)) {
                        s += "(" + child_gbnf + ")";
                    } else {
                        s += child_gbnf;
                    }
                }
                return s;
            } else if constexpr (std::is_same_v<T, common_peg_choice_parser>) {
                std::string s;
                for (const auto & child : p.children) {
                    if (!s.empty()) {
                        s += " | ";
                    }
                    auto child_gbnf = to_gbnf(child);
                    const auto & child_parser = parsers_.at(child);
                    if (std::holds_alternative<common_peg_choice_parser>(child_parser)) {
                        s += "(" + child_gbnf + ")";
                    } else {
                        s += child_gbnf;
                    }
                }
                return s;
            } else if constexpr (std::is_same_v<T, common_peg_repetition_parser>) {
                auto child_gbnf = to_gbnf(p.child);
                const auto & child_parser = parsers_.at(p.child);
                if (std::holds_alternative<common_peg_choice_parser>(child_parser) ||
                    std::holds_alternative<common_peg_sequence_parser>(child_parser)) {
                    child_gbnf = "(" + child_gbnf + ")";
                }
                if (p.min_count == 0 && p.max_count == 1) {
                    return child_gbnf + "?";
                }
                if (p.min_count == 0 && p.max_count == -1) {
                    return child_gbnf + "*";
                }