propane/assets/parser.h.erb

/**
 * @file
 *
 * This file is generated by Propane.
 */

#pragma once

#include <stdint.h>
#include <stddef.h>
<% if @cpp %>
#include <vector>
<% end %>

/**************************************************************************
 * Public types
 *************************************************************************/

/* Result codes. */
#define <%= @grammar.prefix.upcase %>SUCCESS 0u
#define <%= @grammar.prefix.upcase %>DECODE_ERROR 1u
#define <%= @grammar.prefix.upcase %>UNEXPECTED_INPUT 2u
#define <%= @grammar.prefix.upcase %>UNEXPECTED_TOKEN 3u
#define <%= @grammar.prefix.upcase %>DROP 4u
#define <%= @grammar.prefix.upcase %>EOF 5u
#define <%= @grammar.prefix.upcase %>USER_TERMINATED 6u

/** Token type. */
typedef <%= get_type_for(@grammar.terminate_token_id) %> <%= @grammar.prefix %>token_t;

/** Token IDs. */
<% @grammar.tokens.each_with_index do |token, index| %>
#define TOKEN_<%= token.code_name %> <%= index %>u
<%   unless token.id == index %>
<%     raise "Token ID (#{token.id}) does not match index (#{index}) for token #{token.name}!" %>
<%   end %>
<% end %>
#define INVALID_TOKEN_ID <%= @grammar.invalid_token_id %>u
#define TERMINATE_TOKEN_ID <%= @grammar.terminate_token_id %>u

/** Code point type. */
typedef uint32_t <%= @grammar.prefix %>code_point_t;

/**
 * A structure to keep track of input position.
 *
 * This is useful for reporting errors, etc...
 */
typedef struct
{
    /** Input text row (1-based). */
    uint32_t row;

    /** Input text column (1-based). */
    uint32_t col;
} <%= @grammar.prefix %>position_t;

/** Return whether the position is valid. */
#define <%= @grammar.prefix %>position_valid(p) ((p).row != 0u)

/** User header code blocks. */
<%= @grammar.code_blocks.fetch("header", "") %>

<% if @grammar.tree %>
/** Parser values type. */
typedef <%= @grammar.ptype %> <%= @grammar.prefix %>value_t;
<% else %>
/** Parser values type(s). */
typedef union
{
<%   @grammar.ptypes.each do |name, typestring| %>
    <%= typestring %> v_<%= name %>;
<%   end %>
} <%= @grammar.prefix %>value_t;

/** Parser value constructor(s). */
<%   @grammar.ptypes.each do |name, typestring| %>
static inline <%= @grammar.prefix %>value_t <%= @grammar.prefix %>value<%= name == "default" ? "" : "_#{name}" %>(<%= typestring %> v)
{
    return (<%= @grammar.prefix %>value_t){.v_<%= name %> = v};
}
<%   end %>

/** Parser value accessor(s). */
<%   @grammar.ptypes.each do |name, typestring| %>
static inline <%= typestring %> <%= @grammar.prefix %>value_get<%= name == "default" ? "" : "_#{name}" %>(<%= @grammar.prefix %>value_t const * pvalue)
{
    return pvalue->v_<%= name %>;
}
<%   end %>
<% end %>

<% if @grammar.tree %>
/** Tree node ID type (index into the context node arena). ID 0 is null. */
typedef uint32_t <%= @grammar.prefix %>node_id_t;

/**
 * Tree node record.
 *
 * All tree nodes are stored contiguously in the context node arena. Child
 * links are stored in a shared children array: a node's children
 * occupy children[child_offset .. child_offset + n_fields]. Token payload
 * fields (token, pvalue, and any user fields) are only meaningful when
 * is_token is nonzero.
 */
typedef struct
{
    <%= @grammar.prefix %>position_t position;
    <%= @grammar.prefix %>position_t end_position;
    <%= @grammar.prefix %>node_id_t child_offset;
    uint16_t n_fields;
    uint8_t is_token;
    <%= @grammar.prefix %>token_t token;
    <%= @grammar.prefix %>value_t pvalue;
<%= @grammar.token_user_fields %>
} <%= @grammar.prefix %>node_data_t;
<% end %>

/** Lexed token information. */
typedef struct
{
    /** Text position of first code point in token. */
    <%= @grammar.prefix %>position_t position;

    /** Text position of last code point in token. */
    <%= @grammar.prefix %>position_t end_position;

    /** Number of input bytes used by the token. */
    size_t length;

    /** Token that was lexed. */
    <%= @grammar.prefix %>token_t token;

    /** Parser value associated with the token. */
    <%= @grammar.prefix %>value_t pvalue;
} <%= @grammar.prefix %>token_info_t;

typedef struct <%= @grammar.prefix %>context_s <%= @grammar.prefix %>context_t;

<% if @grammar.tree %>
<%= c_tree_handle_types_header %>

<% end %>
/**
 * Lexer and parser context.
 *
 * The user must allocate an instance of this structure and pass it to any
 * public API function.
 */
struct <%= @grammar.prefix %>context_s
{
    /* Lexer context data. */

    /** Input text. */
    uint8_t const * input;

    /** Input text length. */
    size_t input_length;

    /** Input text index (byte offset). */
    size_t input_index;

    /** Input text position (row/column). */
    <%= @grammar.prefix %>position_t text_position;

    /** Current lexer mode. */
    size_t mode;

    /* Parser context data. */

    /** Parse result value. */
<% if @grammar.tree %>
    <%= @grammar.prefix %>node_id_t parse_result;

<%   if @cpp %>
    /** Tree node arena. Node ID 0 is reserved as the null node. */
    std::vector<<%= @grammar.prefix %>node_data_t> <%= @grammar.prefix %>tree_nodes;

    /** Shared tree child links. */
    std::vector<<%= @grammar.prefix %>node_id_t> <%= @grammar.prefix %>tree_children;
<%   else %>
    /** Tree node arena. Node ID 0 is reserved as the null node. */
    <%= @grammar.prefix %>node_data_t * <%= @grammar.prefix %>tree_nodes;
    size_t <%= @grammar.prefix %>tree_nodes_length;
    size_t <%= @grammar.prefix %>tree_nodes_capacity;

    /** Shared tree child links. */
    <%= @grammar.prefix %>node_id_t * <%= @grammar.prefix %>tree_children;
    size_t <%= @grammar.prefix %>tree_children_length;
    size_t <%= @grammar.prefix %>tree_children_capacity;
<%   end %>
<% else %>
    <%= @grammar.prefix %>value_t parse_result;
<% end %>

    /** Unexpected token received. */
    <%= @grammar.prefix %>token_t token;

    /** User terminate code. */
    size_t user_terminate_code;

<%= @grammar.context_user_fields %>
};

<% if @grammar.tree %>
<%= c_tree_types_header %>
<% end %>

/**************************************************************************
 * Public data
 *************************************************************************/

/** Token names. */
extern const char * <%= @grammar.prefix %>token_names[];

<%= @grammar.prefix %>context_t * <%= @grammar.prefix %>context_new(uint8_t const * input, size_t input_length);

void <%= @grammar.prefix %>context_delete(<%= @grammar.prefix %>context_t * context);

size_t <%= @grammar.prefix %>decode_code_point(uint8_t const * input, size_t input_length,
        <%= @grammar.prefix %>code_point_t * out_code_point, uint8_t * out_code_point_length);

size_t <%= @grammar.prefix %>lex(<%= @grammar.prefix %>context_t * context, <%= @grammar.prefix %>token_info_t * out_token_info);

size_t <%= @grammar.prefix %>parse(<%= @grammar.prefix %>context_t * context);
<%   @grammar.start_rules.each_with_index do |start_rule, i| %>
size_t <%= @grammar.prefix %>parse_<%= start_rule %>(<%= @grammar.prefix %>context_t * context);
size_t <%= @grammar.prefix %>parse_inner_<%= start_rule %>(<%= @grammar.prefix %>context_t * context,
        <%= @grammar.prefix %>token_t const * follow_tokens, size_t n_follow_tokens);
<%   end %>

<% if @grammar.tree %>
<%= h_type(@grammar.start_rules[0]) %> <%= @grammar.prefix %>result(<%= @grammar.prefix %>context_t * context);
<%   @grammar.start_rules.each_with_index do |start_rule, i| %>
<%= h_type(start_rule) %> <%= @grammar.prefix %>result_<%= start_rule %>(<%= @grammar.prefix %>context_t * context);
<%   end %>
<% else %>
<%= start_rule_type[1] %> <%= @grammar.prefix %>result(<%= @grammar.prefix %>context_t * context);
<%   @grammar.start_rules.each_with_index do |start_rule, i| %>
<%= start_rule_type(i)[1] %> <%= @grammar.prefix %>result_<%= start_rule %>(<%= @grammar.prefix %>context_t * context);
<%   end %>
<% end %>

<%= @grammar.prefix %>position_t <%= @grammar.prefix %>position(<%= @grammar.prefix %>context_t * context);

void <%= @grammar.prefix %>set_position(<%= @grammar.prefix %>context_t * context, <%= @grammar.prefix %>position_t position);

size_t <%= @grammar.prefix %>input_index(<%= @grammar.prefix %>context_t * context);

void <%= @grammar.prefix %>set_input_index(<%= @grammar.prefix %>context_t * context, size_t input_index);

size_t <%= @grammar.prefix %>user_terminate_code(<%= @grammar.prefix %>context_t * context);

<%= @grammar.prefix %>token_t <%= @grammar.prefix %>token(<%= @grammar.prefix %>context_t * context);