commit 00a15c1704477fb8f361b4b97adc650374996991 Author: Jeff Date: Tue Aug 22 17:02:40 2023 -0400 Initial commit diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..c2658d7 --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +node_modules/ diff --git a/Cargo.toml b/Cargo.toml new file mode 100644 index 0000000..ddb8084 --- /dev/null +++ b/Cargo.toml @@ -0,0 +1,26 @@ +[package] +name = "tree-sitter-Dust" +description = "Dust grammar for the tree-sitter parsing library" +version = "0.0.1" +keywords = ["incremental", "parsing", "Dust"] +categories = ["parsing", "text-editors"] +repository = "https://github.com/tree-sitter/tree-sitter-Dust" +edition = "2018" +license = "MIT" + +build = "bindings/rust/build.rs" +include = [ + "bindings/rust/*", + "grammar.js", + "queries/*", + "src/*", +] + +[lib] +path = "bindings/rust/lib.rs" + +[dependencies] +tree-sitter = "~0.20.10" + +[build-dependencies] +cc = "1.0" diff --git a/binding.gyp b/binding.gyp new file mode 100644 index 0000000..7480a49 --- /dev/null +++ b/binding.gyp @@ -0,0 +1,19 @@ +{ + "targets": [ + { + "target_name": "tree_sitter_Dust_binding", + "include_dirs": [ + " +#include "nan.h" + +using namespace v8; + +extern "C" TSLanguage * tree_sitter_Dust(); + +namespace { + +NAN_METHOD(New) {} + +void Init(Local exports, Local module) { + Local tpl = Nan::New(New); + tpl->SetClassName(Nan::New("Language").ToLocalChecked()); + tpl->InstanceTemplate()->SetInternalFieldCount(1); + + Local constructor = Nan::GetFunction(tpl).ToLocalChecked(); + Local instance = constructor->NewInstance(Nan::GetCurrentContext()).ToLocalChecked(); + Nan::SetInternalFieldPointer(instance, 0, tree_sitter_Dust()); + + Nan::Set(instance, Nan::New("name").ToLocalChecked(), Nan::New("Dust").ToLocalChecked()); + Nan::Set(module, Nan::New("exports").ToLocalChecked(), instance); +} + +NODE_MODULE(tree_sitter_Dust_binding, Init) + +} // namespace diff --git a/bindings/node/index.js b/bindings/node/index.js new file mode 100644 index 0000000..ad21d4b --- /dev/null +++ b/bindings/node/index.js @@ -0,0 +1,19 @@ +try { + module.exports = require("../../build/Release/tree_sitter_Dust_binding"); +} catch (error1) { + if (error1.code !== 'MODULE_NOT_FOUND') { + throw error1; + } + try { + module.exports = require("../../build/Debug/tree_sitter_Dust_binding"); + } catch (error2) { + if (error2.code !== 'MODULE_NOT_FOUND') { + throw error2; + } + throw error1 + } +} + +try { + module.exports.nodeTypeInfo = require("../../src/node-types.json"); +} catch (_) {} diff --git a/bindings/rust/build.rs b/bindings/rust/build.rs new file mode 100644 index 0000000..c6061f0 --- /dev/null +++ b/bindings/rust/build.rs @@ -0,0 +1,40 @@ +fn main() { + let src_dir = std::path::Path::new("src"); + + let mut c_config = cc::Build::new(); + c_config.include(&src_dir); + c_config + .flag_if_supported("-Wno-unused-parameter") + .flag_if_supported("-Wno-unused-but-set-variable") + .flag_if_supported("-Wno-trigraphs"); + let parser_path = src_dir.join("parser.c"); + c_config.file(&parser_path); + + // If your language uses an external scanner written in C, + // then include this block of code: + + /* + let scanner_path = src_dir.join("scanner.c"); + c_config.file(&scanner_path); + println!("cargo:rerun-if-changed={}", scanner_path.to_str().unwrap()); + */ + + c_config.compile("parser"); + println!("cargo:rerun-if-changed={}", parser_path.to_str().unwrap()); + + // If your language uses an external scanner written in C++, + // then include this block of code: + + /* + let mut cpp_config = cc::Build::new(); + cpp_config.cpp(true); + cpp_config.include(&src_dir); + cpp_config + .flag_if_supported("-Wno-unused-parameter") + .flag_if_supported("-Wno-unused-but-set-variable"); + let scanner_path = src_dir.join("scanner.cc"); + cpp_config.file(&scanner_path); + cpp_config.compile("scanner"); + println!("cargo:rerun-if-changed={}", scanner_path.to_str().unwrap()); + */ +} diff --git a/bindings/rust/lib.rs b/bindings/rust/lib.rs new file mode 100644 index 0000000..42af7dd --- /dev/null +++ b/bindings/rust/lib.rs @@ -0,0 +1,52 @@ +//! This crate provides Dust language support for the [tree-sitter][] parsing library. +//! +//! Typically, you will use the [language][language func] function to add this language to a +//! tree-sitter [Parser][], and then use the parser to parse some code: +//! +//! ``` +//! let code = ""; +//! let mut parser = tree_sitter::Parser::new(); +//! parser.set_language(tree_sitter_Dust::language()).expect("Error loading Dust grammar"); +//! let tree = parser.parse(code, None).unwrap(); +//! ``` +//! +//! [Language]: https://docs.rs/tree-sitter/*/tree_sitter/struct.Language.html +//! [language func]: fn.language.html +//! [Parser]: https://docs.rs/tree-sitter/*/tree_sitter/struct.Parser.html +//! [tree-sitter]: https://tree-sitter.github.io/ + +use tree_sitter::Language; + +extern "C" { + fn tree_sitter_Dust() -> Language; +} + +/// Get the tree-sitter [Language][] for this grammar. +/// +/// [Language]: https://docs.rs/tree-sitter/*/tree_sitter/struct.Language.html +pub fn language() -> Language { + unsafe { tree_sitter_Dust() } +} + +/// The content of the [`node-types.json`][] file for this grammar. +/// +/// [`node-types.json`]: https://tree-sitter.github.io/tree-sitter/using-parsers#static-node-types +pub const NODE_TYPES: &'static str = include_str!("../../src/node-types.json"); + +// Uncomment these to include any queries that this grammar contains + +// pub const HIGHLIGHTS_QUERY: &'static str = include_str!("../../queries/highlights.scm"); +// pub const INJECTIONS_QUERY: &'static str = include_str!("../../queries/injections.scm"); +// pub const LOCALS_QUERY: &'static str = include_str!("../../queries/locals.scm"); +// pub const TAGS_QUERY: &'static str = include_str!("../../queries/tags.scm"); + +#[cfg(test)] +mod tests { + #[test] + fn test_can_load_grammar() { + let mut parser = tree_sitter::Parser::new(); + parser + .set_language(super::language()) + .expect("Error loading Dust language"); + } +} diff --git a/corpus/tests.txt b/corpus/tests.txt new file mode 100644 index 0000000..0c39d2c --- /dev/null +++ b/corpus/tests.txt @@ -0,0 +1,16 @@ +================== +Comments +================== + +# x = 1; +# unassigned_variable +x # xyz + +--- + +(source_file + (comment) + (comment) + (expression + (identifier)) + (comment)) diff --git a/example b/example new file mode 100644 index 0000000..ce01362 --- /dev/null +++ b/example @@ -0,0 +1 @@ +hello diff --git a/grammar.js b/grammar.js new file mode 100644 index 0000000..166a92e --- /dev/null +++ b/grammar.js @@ -0,0 +1,23 @@ +module.exports = grammar({ + name: 'Dust', + + rules: { + source_file: $ => repeat(choice($.comment, $.expression)), + + comment: $ => /(#)(.+?)([\n\r])/, + + expression: $ => choice( + $.identifier + // TODO: other kinds of definitions + ), + + identifier: $ => /[a-zA-Z]+(_[a-zA-Z]+)*/, + + operator: $ => choice( + '=', + "+", + ), + + integer: $ => /\d/, + } +}); diff --git a/package-lock.json b/package-lock.json new file mode 100644 index 0000000..0e7809a --- /dev/null +++ b/package-lock.json @@ -0,0 +1,34 @@ +{ + "name": "tree-sitter-dust", + "version": "1.0.0", + "lockfileVersion": 3, + "requires": true, + "packages": { + "": { + "name": "tree-sitter-dust", + "version": "1.0.0", + "license": "ISC", + "dependencies": { + "nan": "^2.17.0" + }, + "devDependencies": { + "tree-sitter-cli": "^0.20.8" + } + }, + "node_modules/nan": { + "version": "2.17.0", + "resolved": "https://registry.npmjs.org/nan/-/nan-2.17.0.tgz", + "integrity": "sha512-2ZTgtl0nJsO0KQCjEpxcIr5D+Yv90plTitZt9JBfQvVJDS5seMl3FOvsh3+9CoYWXf/1l5OaZzzF6nDm4cagaQ==" + }, + "node_modules/tree-sitter-cli": { + "version": "0.20.8", + "resolved": "https://registry.npmjs.org/tree-sitter-cli/-/tree-sitter-cli-0.20.8.tgz", + "integrity": "sha512-XjTcS3wdTy/2cc/ptMLc/WRyOLECRYcMTrSWyhZnj1oGSOWbHLTklgsgRICU3cPfb0vy+oZCC33M43u6R1HSCA==", + "dev": true, + "hasInstallScript": true, + "bin": { + "tree-sitter": "cli.js" + } + } + } +} diff --git a/package.json b/package.json new file mode 100644 index 0000000..34cea16 --- /dev/null +++ b/package.json @@ -0,0 +1,17 @@ +{ + "name": "tree-sitter-dust", + "version": "1.0.0", + "description": "Tree Sitter grammar for the Dust programming language", + "main": "bindings/node", + "scripts": { + "test": "echo \"Error: no test specified\" && exit 1" + }, + "author": "", + "license": "ISC", + "dependencies": { + "nan": "^2.17.0" + }, + "devDependencies": { + "tree-sitter-cli": "^0.20.8" + } +} diff --git a/src/grammar.json b/src/grammar.json new file mode 100644 index 0000000..7a40701 --- /dev/null +++ b/src/grammar.json @@ -0,0 +1,67 @@ +{ + "name": "Dust", + "rules": { + "source_file": { + "type": "REPEAT", + "content": { + "type": "CHOICE", + "members": [ + { + "type": "SYMBOL", + "name": "comment" + }, + { + "type": "SYMBOL", + "name": "expression" + } + ] + } + }, + "comment": { + "type": "PATTERN", + "value": "(#)(.+?)([\\n\\r])" + }, + "expression": { + "type": "CHOICE", + "members": [ + { + "type": "SYMBOL", + "name": "identifier" + } + ] + }, + "identifier": { + "type": "PATTERN", + "value": "[a-zA-Z]+(_[a-zA-Z]+)*" + }, + "operator": { + "type": "CHOICE", + "members": [ + { + "type": "STRING", + "value": "=" + }, + { + "type": "STRING", + "value": "+" + } + ] + }, + "integer": { + "type": "PATTERN", + "value": "\\d" + } + }, + "extras": [ + { + "type": "PATTERN", + "value": "\\s" + } + ], + "conflicts": [], + "precedences": [], + "externals": [], + "inline": [], + "supertypes": [] +} + diff --git a/src/node-types.json b/src/node-types.json new file mode 100644 index 0000000..2201003 --- /dev/null +++ b/src/node-types.json @@ -0,0 +1,52 @@ +[ + { + "type": "expression", + "named": true, + "fields": {}, + "children": { + "multiple": false, + "required": true, + "types": [ + { + "type": "identifier", + "named": true + } + ] + } + }, + { + "type": "source_file", + "named": true, + "fields": {}, + "children": { + "multiple": true, + "required": false, + "types": [ + { + "type": "comment", + "named": true + }, + { + "type": "expression", + "named": true + } + ] + } + }, + { + "type": "+", + "named": false + }, + { + "type": "=", + "named": false + }, + { + "type": "comment", + "named": true + }, + { + "type": "identifier", + "named": true + } +] \ No newline at end of file diff --git a/src/parser.c b/src/parser.c new file mode 100644 index 0000000..678081b --- /dev/null +++ b/src/parser.c @@ -0,0 +1,281 @@ +#include + +#if defined(__GNUC__) || defined(__clang__) +#pragma GCC diagnostic push +#pragma GCC diagnostic ignored "-Wmissing-field-initializers" +#endif + +#define LANGUAGE_VERSION 14 +#define STATE_COUNT 6 +#define LARGE_STATE_COUNT 4 +#define SYMBOL_COUNT 9 +#define ALIAS_COUNT 0 +#define TOKEN_COUNT 6 +#define EXTERNAL_TOKEN_COUNT 0 +#define FIELD_COUNT 0 +#define MAX_ALIAS_SEQUENCE_LENGTH 2 +#define PRODUCTION_ID_COUNT 1 + +enum { + sym_comment = 1, + sym_identifier = 2, + anon_sym_EQ = 3, + anon_sym_PLUS = 4, + sym_integer = 5, + sym_source_file = 6, + sym_expression = 7, + aux_sym_source_file_repeat1 = 8, +}; + +static const char * const ts_symbol_names[] = { + [ts_builtin_sym_end] = "end", + [sym_comment] = "comment", + [sym_identifier] = "identifier", + [anon_sym_EQ] = "=", + [anon_sym_PLUS] = "+", + [sym_integer] = "integer", + [sym_source_file] = "source_file", + [sym_expression] = "expression", + [aux_sym_source_file_repeat1] = "source_file_repeat1", +}; + +static const TSSymbol ts_symbol_map[] = { + [ts_builtin_sym_end] = ts_builtin_sym_end, + [sym_comment] = sym_comment, + [sym_identifier] = sym_identifier, + [anon_sym_EQ] = anon_sym_EQ, + [anon_sym_PLUS] = anon_sym_PLUS, + [sym_integer] = sym_integer, + [sym_source_file] = sym_source_file, + [sym_expression] = sym_expression, + [aux_sym_source_file_repeat1] = aux_sym_source_file_repeat1, +}; + +static const TSSymbolMetadata ts_symbol_metadata[] = { + [ts_builtin_sym_end] = { + .visible = false, + .named = true, + }, + [sym_comment] = { + .visible = true, + .named = true, + }, + [sym_identifier] = { + .visible = true, + .named = true, + }, + [anon_sym_EQ] = { + .visible = true, + .named = false, + }, + [anon_sym_PLUS] = { + .visible = true, + .named = false, + }, + [sym_integer] = { + .visible = true, + .named = true, + }, + [sym_source_file] = { + .visible = true, + .named = true, + }, + [sym_expression] = { + .visible = true, + .named = true, + }, + [aux_sym_source_file_repeat1] = { + .visible = false, + .named = false, + }, +}; + +static const TSSymbol ts_alias_sequences[PRODUCTION_ID_COUNT][MAX_ALIAS_SEQUENCE_LENGTH] = { + [0] = {0}, +}; + +static const uint16_t ts_non_terminal_alias_map[] = { + 0, +}; + +static const TSStateId ts_primary_state_ids[STATE_COUNT] = { + [0] = 0, + [1] = 1, + [2] = 2, + [3] = 3, + [4] = 4, + [5] = 5, +}; + +static bool ts_lex(TSLexer *lexer, TSStateId state) { + START_LEXER(); + eof = lexer->eof(lexer); + switch (state) { + case 0: + if (eof) ADVANCE(4); + if (lookahead == '#') ADVANCE(3); + if (lookahead == '+') ADVANCE(9); + if (lookahead == '=') ADVANCE(8); + if (lookahead == '\t' || + lookahead == '\n' || + lookahead == '\r' || + lookahead == ' ') SKIP(0) + if (('0' <= lookahead && lookahead <= '9')) ADVANCE(10); + if (('A' <= lookahead && lookahead <= 'Z') || + ('a' <= lookahead && lookahead <= 'z')) ADVANCE(7); + END_STATE(); + case 1: + if (lookahead == '\n') ADVANCE(5); + if (lookahead == '\r') ADVANCE(6); + if (lookahead != 0) ADVANCE(1); + END_STATE(); + case 2: + if (('A' <= lookahead && lookahead <= 'Z') || + ('a' <= lookahead && lookahead <= 'z')) ADVANCE(7); + END_STATE(); + case 3: + if (lookahead != 0 && + lookahead != '\n') ADVANCE(1); + END_STATE(); + case 4: + ACCEPT_TOKEN(ts_builtin_sym_end); + END_STATE(); + case 5: + ACCEPT_TOKEN(sym_comment); + END_STATE(); + case 6: + ACCEPT_TOKEN(sym_comment); + if (lookahead == '\n') ADVANCE(5); + if (lookahead == '\r') ADVANCE(6); + if (lookahead != 0) ADVANCE(1); + END_STATE(); + case 7: + ACCEPT_TOKEN(sym_identifier); + if (lookahead == '_') ADVANCE(2); + if (('A' <= lookahead && lookahead <= 'Z') || + ('a' <= lookahead && lookahead <= 'z')) ADVANCE(7); + END_STATE(); + case 8: + ACCEPT_TOKEN(anon_sym_EQ); + END_STATE(); + case 9: + ACCEPT_TOKEN(anon_sym_PLUS); + END_STATE(); + case 10: + ACCEPT_TOKEN(sym_integer); + END_STATE(); + default: + return false; + } +} + +static const TSLexMode ts_lex_modes[STATE_COUNT] = { + [0] = {.lex_state = 0}, + [1] = {.lex_state = 0}, + [2] = {.lex_state = 0}, + [3] = {.lex_state = 0}, + [4] = {.lex_state = 0}, + [5] = {.lex_state = 0}, +}; + +static const uint16_t ts_parse_table[LARGE_STATE_COUNT][SYMBOL_COUNT] = { + [0] = { + [ts_builtin_sym_end] = ACTIONS(1), + [sym_comment] = ACTIONS(1), + [sym_identifier] = ACTIONS(1), + [anon_sym_EQ] = ACTIONS(1), + [anon_sym_PLUS] = ACTIONS(1), + [sym_integer] = ACTIONS(1), + }, + [1] = { + [sym_source_file] = STATE(5), + [sym_expression] = STATE(2), + [aux_sym_source_file_repeat1] = STATE(2), + [ts_builtin_sym_end] = ACTIONS(3), + [sym_comment] = ACTIONS(5), + [sym_identifier] = ACTIONS(7), + }, + [2] = { + [sym_expression] = STATE(3), + [aux_sym_source_file_repeat1] = STATE(3), + [ts_builtin_sym_end] = ACTIONS(9), + [sym_comment] = ACTIONS(11), + [sym_identifier] = ACTIONS(7), + }, + [3] = { + [sym_expression] = STATE(3), + [aux_sym_source_file_repeat1] = STATE(3), + [ts_builtin_sym_end] = ACTIONS(13), + [sym_comment] = ACTIONS(15), + [sym_identifier] = ACTIONS(18), + }, +}; + +static const uint16_t ts_small_parse_table[] = { + [0] = 1, + ACTIONS(21), 3, + ts_builtin_sym_end, + sym_comment, + sym_identifier, + [6] = 1, + ACTIONS(23), 1, + ts_builtin_sym_end, +}; + +static const uint32_t ts_small_parse_table_map[] = { + [SMALL_STATE(4)] = 0, + [SMALL_STATE(5)] = 6, +}; + +static const TSParseActionEntry ts_parse_actions[] = { + [0] = {.entry = {.count = 0, .reusable = false}}, + [1] = {.entry = {.count = 1, .reusable = false}}, RECOVER(), + [3] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym_source_file, 0), + [5] = {.entry = {.count = 1, .reusable = true}}, SHIFT(2), + [7] = {.entry = {.count = 1, .reusable = true}}, SHIFT(4), + [9] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym_source_file, 1), + [11] = {.entry = {.count = 1, .reusable = true}}, SHIFT(3), + [13] = {.entry = {.count = 1, .reusable = true}}, REDUCE(aux_sym_source_file_repeat1, 2), + [15] = {.entry = {.count = 2, .reusable = true}}, REDUCE(aux_sym_source_file_repeat1, 2), SHIFT_REPEAT(3), + [18] = {.entry = {.count = 2, .reusable = true}}, REDUCE(aux_sym_source_file_repeat1, 2), SHIFT_REPEAT(4), + [21] = {.entry = {.count = 1, .reusable = true}}, REDUCE(sym_expression, 1), + [23] = {.entry = {.count = 1, .reusable = true}}, ACCEPT_INPUT(), +}; + +#ifdef __cplusplus +extern "C" { +#endif +#ifdef _WIN32 +#define extern __declspec(dllexport) +#endif + +extern const TSLanguage *tree_sitter_Dust(void) { + static const TSLanguage language = { + .version = LANGUAGE_VERSION, + .symbol_count = SYMBOL_COUNT, + .alias_count = ALIAS_COUNT, + .token_count = TOKEN_COUNT, + .external_token_count = EXTERNAL_TOKEN_COUNT, + .state_count = STATE_COUNT, + .large_state_count = LARGE_STATE_COUNT, + .production_id_count = PRODUCTION_ID_COUNT, + .field_count = FIELD_COUNT, + .max_alias_sequence_length = MAX_ALIAS_SEQUENCE_LENGTH, + .parse_table = &ts_parse_table[0][0], + .small_parse_table = ts_small_parse_table, + .small_parse_table_map = ts_small_parse_table_map, + .parse_actions = ts_parse_actions, + .symbol_names = ts_symbol_names, + .symbol_metadata = ts_symbol_metadata, + .public_symbol_map = ts_symbol_map, + .alias_map = ts_non_terminal_alias_map, + .alias_sequences = &ts_alias_sequences[0][0], + .lex_modes = ts_lex_modes, + .lex_fn = ts_lex, + .primary_state_ids = ts_primary_state_ids, + }; + return &language; +} +#ifdef __cplusplus +} +#endif diff --git a/src/tree_sitter/parser.h b/src/tree_sitter/parser.h new file mode 100644 index 0000000..2b14ac1 --- /dev/null +++ b/src/tree_sitter/parser.h @@ -0,0 +1,224 @@ +#ifndef TREE_SITTER_PARSER_H_ +#define TREE_SITTER_PARSER_H_ + +#ifdef __cplusplus +extern "C" { +#endif + +#include +#include +#include + +#define ts_builtin_sym_error ((TSSymbol)-1) +#define ts_builtin_sym_end 0 +#define TREE_SITTER_SERIALIZATION_BUFFER_SIZE 1024 + +typedef uint16_t TSStateId; + +#ifndef TREE_SITTER_API_H_ +typedef uint16_t TSSymbol; +typedef uint16_t TSFieldId; +typedef struct TSLanguage TSLanguage; +#endif + +typedef struct { + TSFieldId field_id; + uint8_t child_index; + bool inherited; +} TSFieldMapEntry; + +typedef struct { + uint16_t index; + uint16_t length; +} TSFieldMapSlice; + +typedef struct { + bool visible; + bool named; + bool supertype; +} TSSymbolMetadata; + +typedef struct TSLexer TSLexer; + +struct TSLexer { + int32_t lookahead; + TSSymbol result_symbol; + void (*advance)(TSLexer *, bool); + void (*mark_end)(TSLexer *); + uint32_t (*get_column)(TSLexer *); + bool (*is_at_included_range_start)(const TSLexer *); + bool (*eof)(const TSLexer *); +}; + +typedef enum { + TSParseActionTypeShift, + TSParseActionTypeReduce, + TSParseActionTypeAccept, + TSParseActionTypeRecover, +} TSParseActionType; + +typedef union { + struct { + uint8_t type; + TSStateId state; + bool extra; + bool repetition; + } shift; + struct { + uint8_t type; + uint8_t child_count; + TSSymbol symbol; + int16_t dynamic_precedence; + uint16_t production_id; + } reduce; + uint8_t type; +} TSParseAction; + +typedef struct { + uint16_t lex_state; + uint16_t external_lex_state; +} TSLexMode; + +typedef union { + TSParseAction action; + struct { + uint8_t count; + bool reusable; + } entry; +} TSParseActionEntry; + +struct TSLanguage { + uint32_t version; + uint32_t symbol_count; + uint32_t alias_count; + uint32_t token_count; + uint32_t external_token_count; + uint32_t state_count; + uint32_t large_state_count; + uint32_t production_id_count; + uint32_t field_count; + uint16_t max_alias_sequence_length; + const uint16_t *parse_table; + const uint16_t *small_parse_table; + const uint32_t *small_parse_table_map; + const TSParseActionEntry *parse_actions; + const char * const *symbol_names; + const char * const *field_names; + const TSFieldMapSlice *field_map_slices; + const TSFieldMapEntry *field_map_entries; + const TSSymbolMetadata *symbol_metadata; + const TSSymbol *public_symbol_map; + const uint16_t *alias_map; + const TSSymbol *alias_sequences; + const TSLexMode *lex_modes; + bool (*lex_fn)(TSLexer *, TSStateId); + bool (*keyword_lex_fn)(TSLexer *, TSStateId); + TSSymbol keyword_capture_token; + struct { + const bool *states; + const TSSymbol *symbol_map; + void *(*create)(void); + void (*destroy)(void *); + bool (*scan)(void *, TSLexer *, const bool *symbol_whitelist); + unsigned (*serialize)(void *, char *); + void (*deserialize)(void *, const char *, unsigned); + } external_scanner; + const TSStateId *primary_state_ids; +}; + +/* + * Lexer Macros + */ + +#define START_LEXER() \ + bool result = false; \ + bool skip = false; \ + bool eof = false; \ + int32_t lookahead; \ + goto start; \ + next_state: \ + lexer->advance(lexer, skip); \ + start: \ + skip = false; \ + lookahead = lexer->lookahead; + +#define ADVANCE(state_value) \ + { \ + state = state_value; \ + goto next_state; \ + } + +#define SKIP(state_value) \ + { \ + skip = true; \ + state = state_value; \ + goto next_state; \ + } + +#define ACCEPT_TOKEN(symbol_value) \ + result = true; \ + lexer->result_symbol = symbol_value; \ + lexer->mark_end(lexer); + +#define END_STATE() return result; + +/* + * Parse Table Macros + */ + +#define SMALL_STATE(id) id - LARGE_STATE_COUNT + +#define STATE(id) id + +#define ACTIONS(id) id + +#define SHIFT(state_value) \ + {{ \ + .shift = { \ + .type = TSParseActionTypeShift, \ + .state = state_value \ + } \ + }} + +#define SHIFT_REPEAT(state_value) \ + {{ \ + .shift = { \ + .type = TSParseActionTypeShift, \ + .state = state_value, \ + .repetition = true \ + } \ + }} + +#define SHIFT_EXTRA() \ + {{ \ + .shift = { \ + .type = TSParseActionTypeShift, \ + .extra = true \ + } \ + }} + +#define REDUCE(symbol_val, child_count_val, ...) \ + {{ \ + .reduce = { \ + .type = TSParseActionTypeReduce, \ + .symbol = symbol_val, \ + .child_count = child_count_val, \ + __VA_ARGS__ \ + }, \ + }} + +#define RECOVER() \ + {{ \ + .type = TSParseActionTypeRecover \ + }} + +#define ACCEPT_INPUT() \ + {{ \ + .type = TSParseActionTypeAccept \ + }} + +#ifdef __cplusplus +} +#endif + +#endif // TREE_SITTER_PARSER_H_