dunham/tree-sitter-newt
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

initial commit

Browse Source
This commit is contained in:
Steve Dunham
2026-03-04 20:24:33 -08:00
commit bb510fea4a
39 changed files with 14640 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
.editorconfig Normal file
View File

@@ -0,0 +1,46 @@
root = true
[*]
charset = utf-8
[*.{json,toml,yml,gyp}]
indent_style = space
indent_size = 2
[*.js]
indent_style = space
indent_size = 2
[*.scm]
indent_style = space
indent_size = 2
[*.{c,cc,h}]
indent_style = space
indent_size = 4
[*.rs]
indent_style = space
indent_size = 4
[*.{py,pyi}]
indent_style = space
indent_size = 4
[*.swift]
indent_style = space
indent_size = 4
[*.go]
indent_style = tab
indent_size = 8
[Makefile]
indent_style = tab
indent_size = 8
[parser.c]
indent_size = 2
[{alloc,array,parser}.h]
indent_size = 2

42
.gitattributes vendored Normal file
View File

@@ -0,0 +1,42 @@
* text=auto eol=lf
# Generated source files
src/*.json linguist-generated
src/parser.c linguist-generated
src/tree_sitter/* linguist-generated
# C bindings
bindings/c/** linguist-generated
CMakeLists.txt linguist-generated
Makefile linguist-generated
# Rust bindings
bindings/rust/* linguist-generated
Cargo.toml linguist-generated
Cargo.lock linguist-generated
# Node.js bindings
bindings/node/* linguist-generated
binding.gyp linguist-generated
package.json linguist-generated
package-lock.json linguist-generated
# Python bindings
bindings/python/** linguist-generated
setup.py linguist-generated
pyproject.toml linguist-generated
# Go bindings
bindings/go/* linguist-generated
go.mod linguist-generated
go.sum linguist-generated
# Swift bindings
bindings/swift/** linguist-generated
Package.swift linguist-generated
Package.resolved linguist-generated
# Zig bindings
bindings/zig/* linguist-generated
build.zig linguist-generated
build.zig.zon linguist-generated

50
.gitignore vendored Normal file
View File

@@ -0,0 +1,50 @@
# Rust artifacts
target/
Cargo.lock
# Node artifacts
build/
prebuilds/
node_modules/
package-lock.json
# Swift artifacts
.build/
Package.resolved
# Go artifacts
_obj/
# Python artifacts
.venv/
dist/
*.egg-info
*.whl
# C artifacts
*.a
*.so
*.so.*
*.dylib
*.dll
*.pc
*.exp
*.lib
# Zig artifacts
.zig-cache/
zig-cache/
zig-out/
# Example dirs
/examples/*/
# Grammar volatiles
*.wasm
*.obj
*.o
# Archives
*.tar.gz
*.tgz
*.zip

66
CMakeLists.txt generated Normal file
View File

@@ -0,0 +1,66 @@
cmake_minimum_required(VERSION 3.13)
project(tree-sitter-newt
VERSION "0.1.0"
DESCRIPTION "Newt grammar for tree-sitter"
HOMEPAGE_URL "https://github.com/dunhamsteve/tree-sitter-newt"
LANGUAGES C)
option(BUILD_SHARED_LIBS "Build using shared libraries" ON)
option(TREE_SITTER_REUSE_ALLOCATOR "Reuse the library allocator" OFF)
set(TREE_SITTER_ABI_VERSION 15 CACHE STRING "Tree-sitter ABI version")
if(NOT ${TREE_SITTER_ABI_VERSION} MATCHES "^[0-9]+$")
unset(TREE_SITTER_ABI_VERSION CACHE)
message(FATAL_ERROR "TREE_SITTER_ABI_VERSION must be an integer")
endif()
include(GNUInstallDirs)
find_program(TREE_SITTER_CLI tree-sitter DOC "Tree-sitter CLI")
add_custom_command(OUTPUT "${CMAKE_CURRENT_SOURCE_DIR}/src/parser.c"
DEPENDS "${CMAKE_CURRENT_SOURCE_DIR}/src/grammar.json"
COMMAND "${TREE_SITTER_CLI}" generate src/grammar.json
--abi=${TREE_SITTER_ABI_VERSION}
WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}"
COMMENT "Generating parser.c")
add_library(tree-sitter-newt src/parser.c)
if(EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/src/scanner.c)
target_sources(tree-sitter-newt PRIVATE src/scanner.c)
endif()
target_include_directories(tree-sitter-newt
PRIVATE src
INTERFACE $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/bindings/c>
$<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>)
target_compile_definitions(tree-sitter-newt PRIVATE
$<$<BOOL:${TREE_SITTER_REUSE_ALLOCATOR}>:TREE_SITTER_REUSE_ALLOCATOR>
$<$<CONFIG:Debug>:TREE_SITTER_DEBUG>)
set_target_properties(tree-sitter-newt
PROPERTIES
C_STANDARD 11
POSITION_INDEPENDENT_CODE ON
SOVERSION "${TREE_SITTER_ABI_VERSION}.${PROJECT_VERSION_MAJOR}"
DEFINE_SYMBOL "")
configure_file(bindings/c/tree-sitter-newt.pc.in
"${CMAKE_CURRENT_BINARY_DIR}/tree-sitter-newt.pc" @ONLY)
install(DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}/bindings/c/tree_sitter"
DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
FILES_MATCHING PATTERN "*.h")
install(FILES "${CMAKE_CURRENT_BINARY_DIR}/tree-sitter-newt.pc"
DESTINATION "${CMAKE_INSTALL_LIBDIR}/pkgconfig")
install(TARGETS tree-sitter-newt
LIBRARY DESTINATION "${CMAKE_INSTALL_LIBDIR}")
file(GLOB QUERIES queries/*.scm)
install(FILES ${QUERIES}
DESTINATION "${CMAKE_INSTALL_DATADIR}/tree-sitter/queries/newt")
add_custom_target(ts-test "${TREE_SITTER_CLI}" test
WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}"
COMMENT "tree-sitter test")

34
Cargo.toml generated Normal file
View File

@@ -0,0 +1,34 @@
[package]
name = "tree-sitter-newt"
description = "Newt grammar for tree-sitter"
version = "0.1.0"
authors = ["Steve Dunham <dunhamsteve@gmail.com>"]
license = "MIT"
readme = "README.md"
keywords = ["incremental", "parsing", "tree-sitter", "newt"]
categories = ["parser-implementations", "parsing", "text-editors"]
repository = "https://github.com/dunhamsteve/tree-sitter-newt"
edition = "2021"
autoexamples = false
build = "bindings/rust/build.rs"
include = [
"bindings/rust/*",
"grammar.js",
"queries/*",
"src/*",
"tree-sitter.json",
"/LICENSE",
]
[lib]
path = "bindings/rust/lib.rs"
[dependencies]
tree-sitter-language = "0.1"
[build-dependencies]
cc = "1.2"
[dev-dependencies]
tree-sitter = "0.25.10"

99
Makefile generated Normal file
View File

@@ -0,0 +1,99 @@
ifeq ($(OS),Windows_NT)
$(error Windows is not supported)
endif
LANGUAGE_NAME := tree-sitter-newt
HOMEPAGE_URL := https://github.com/dunhamsteve/tree-sitter-newt
VERSION := 0.1.0
# repository
SRC_DIR := src
TS ?= tree-sitter
# install directory layout
PREFIX ?= /usr/local
DATADIR ?= $(PREFIX)/share
INCLUDEDIR ?= $(PREFIX)/include
LIBDIR ?= $(PREFIX)/lib
PCLIBDIR ?= $(LIBDIR)/pkgconfig
# source/object files
PARSER := $(SRC_DIR)/parser.c
EXTRAS := $(filter-out $(PARSER),$(wildcard $(SRC_DIR)/*.c))
OBJS := $(patsubst %.c,%.o,$(PARSER) $(EXTRAS))
# flags
ARFLAGS ?= rcs
override CFLAGS += -I$(SRC_DIR) -std=c11 -fPIC
# ABI versioning
SONAME_MAJOR = $(shell sed -n 's/\#define LANGUAGE_VERSION //p' $(PARSER))
SONAME_MINOR = $(word 1,$(subst ., ,$(VERSION)))
# OS-specific bits
ifeq ($(shell uname),Darwin)
SOEXT = dylib
SOEXTVER_MAJOR = $(SONAME_MAJOR).$(SOEXT)
SOEXTVER = $(SONAME_MAJOR).$(SONAME_MINOR).$(SOEXT)
LINKSHARED = -dynamiclib -Wl,-install_name,$(LIBDIR)/lib$(LANGUAGE_NAME).$(SOEXTVER),-rpath,@executable_path/../Frameworks
else
SOEXT = so
SOEXTVER_MAJOR = $(SOEXT).$(SONAME_MAJOR)
SOEXTVER = $(SOEXT).$(SONAME_MAJOR).$(SONAME_MINOR)
LINKSHARED = -shared -Wl,-soname,lib$(LANGUAGE_NAME).$(SOEXTVER)
endif
ifneq ($(filter $(shell uname),FreeBSD NetBSD DragonFly),)
PCLIBDIR := $(PREFIX)/libdata/pkgconfig
endif
all: lib$(LANGUAGE_NAME).a lib$(LANGUAGE_NAME).$(SOEXT) $(LANGUAGE_NAME).pc
lib$(LANGUAGE_NAME).a: $(OBJS)
$(AR) $(ARFLAGS) $@ $^
lib$(LANGUAGE_NAME).$(SOEXT): $(OBJS)
$(CC) $(LDFLAGS) $(LINKSHARED) $^ $(LDLIBS) -o $@
ifneq ($(STRIP),)
$(STRIP) $@
endif
$(LANGUAGE_NAME).pc: bindings/c/$(LANGUAGE_NAME).pc.in
sed -e 's|@PROJECT_VERSION@|$(VERSION)|' \
-e 's|@CMAKE_INSTALL_LIBDIR@|$(LIBDIR:$(PREFIX)/%=%)|' \
-e 's|@CMAKE_INSTALL_INCLUDEDIR@|$(INCLUDEDIR:$(PREFIX)/%=%)|' \
-e 's|@PROJECT_DESCRIPTION@|$(DESCRIPTION)|' \
-e 's|@PROJECT_HOMEPAGE_URL@|$(HOMEPAGE_URL)|' \
-e 's|@CMAKE_INSTALL_PREFIX@|$(PREFIX)|' $< > $@
$(PARSER): $(SRC_DIR)/grammar.json
$(TS) generate $^
install: all
install -d '$(DESTDIR)$(DATADIR)'/tree-sitter/queries/newt '$(DESTDIR)$(INCLUDEDIR)'/tree_sitter '$(DESTDIR)$(PCLIBDIR)' '$(DESTDIR)$(LIBDIR)'
install -m644 bindings/c/tree_sitter/$(LANGUAGE_NAME).h '$(DESTDIR)$(INCLUDEDIR)'/tree_sitter/$(LANGUAGE_NAME).h
install -m644 $(LANGUAGE_NAME).pc '$(DESTDIR)$(PCLIBDIR)'/$(LANGUAGE_NAME).pc
install -m644 lib$(LANGUAGE_NAME).a '$(DESTDIR)$(LIBDIR)'/lib$(LANGUAGE_NAME).a
install -m755 lib$(LANGUAGE_NAME).$(SOEXT) '$(DESTDIR)$(LIBDIR)'/lib$(LANGUAGE_NAME).$(SOEXTVER)
ln -sf lib$(LANGUAGE_NAME).$(SOEXTVER) '$(DESTDIR)$(LIBDIR)'/lib$(LANGUAGE_NAME).$(SOEXTVER_MAJOR)
ln -sf lib$(LANGUAGE_NAME).$(SOEXTVER_MAJOR) '$(DESTDIR)$(LIBDIR)'/lib$(LANGUAGE_NAME).$(SOEXT)
ifneq ($(wildcard queries/*.scm),)
install -m644 queries/*.scm '$(DESTDIR)$(DATADIR)'/tree-sitter/queries/newt
endif
uninstall:
$(RM) '$(DESTDIR)$(LIBDIR)'/lib$(LANGUAGE_NAME).a \
'$(DESTDIR)$(LIBDIR)'/lib$(LANGUAGE_NAME).$(SOEXTVER) \
'$(DESTDIR)$(LIBDIR)'/lib$(LANGUAGE_NAME).$(SOEXTVER_MAJOR) \
'$(DESTDIR)$(LIBDIR)'/lib$(LANGUAGE_NAME).$(SOEXT) \
'$(DESTDIR)$(INCLUDEDIR)'/tree_sitter/$(LANGUAGE_NAME).h \
'$(DESTDIR)$(PCLIBDIR)'/$(LANGUAGE_NAME).pc
$(RM) -r '$(DESTDIR)$(DATADIR)'/tree-sitter/queries/newt
clean:
$(RM) $(OBJS) $(LANGUAGE_NAME).pc lib$(LANGUAGE_NAME).a lib$(LANGUAGE_NAME).$(SOEXT)
test:
$(TS) test
.PHONY: all install uninstall clean test

41
Package.swift generated Normal file
View File

@@ -0,0 +1,41 @@
// swift-tools-version:5.3
import Foundation
import PackageDescription
var sources = ["src/parser.c"]
if FileManager.default.fileExists(atPath: "src/scanner.c") {
sources.append("src/scanner.c")
}
let package = Package(
name: "TreeSitterNewt",
products: [
.library(name: "TreeSitterNewt", targets: ["TreeSitterNewt"]),
],
dependencies: [
.package(name: "SwiftTreeSitter", url: "https://github.com/tree-sitter/swift-tree-sitter", from: "0.9.0"),
],
targets: [
.target(
name: "TreeSitterNewt",
dependencies: [],
path: ".",
sources: sources,
resources: [
.copy("queries")
],
publicHeadersPath: "bindings/swift",
cSettings: [.headerSearchPath("src")]
),
.testTarget(
name: "TreeSitterNewtTests",
dependencies: [
"SwiftTreeSitter",
"TreeSitterNewt",
],
path: "bindings/swift/TreeSitterNewtTests"
)
],
cLanguageStandard: .c11
)

8
README.md Normal file
View File

@@ -0,0 +1,8 @@
# Tree sitter parser for Newt
Work in progress.
Not completely accurate, intended for editor use. We're ignoring the existance of mixfix and parsing as an app list.
The layout is doing the Haskel fake token thing for now.

35
binding.gyp generated Normal file
View File

@@ -0,0 +1,35 @@
{
"targets": [
{
"target_name": "tree_sitter_newt_binding",
"dependencies": [
"<!(node -p \"require('node-addon-api').targets\"):node_addon_api_except",
],
"include_dirs": [
"src",
],
"sources": [
"bindings/node/binding.cc",
"src/parser.c",
],
"variables": {
"has_scanner": "<!(node -p \"fs.existsSync('src/scanner.c')\")"
},
"conditions": [
["has_scanner=='true'", {
"sources+": ["src/scanner.c"],
}],
["OS!='win'", {
"cflags_c": [
"-std=c11",
],
}, { # OS == "win"
"cflags_c": [
"/std:c11",
"/utf-8",
],
}],
],
}
]
}

10
bindings/c/tree-sitter-newt.pc.in generated Normal file
View File

@@ -0,0 +1,10 @@
prefix=@CMAKE_INSTALL_PREFIX@
libdir=${prefix}/@CMAKE_INSTALL_LIBDIR@
includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
Name: tree-sitter-newt
Description: @PROJECT_DESCRIPTION@
URL: @PROJECT_HOMEPAGE_URL@
Version: @PROJECT_VERSION@
Libs: -L${libdir} -ltree-sitter-newt
Cflags: -I${includedir}

16
bindings/c/tree_sitter/tree-sitter-newt.h generated Normal file
View File

@@ -0,0 +1,16 @@
#ifndef TREE_SITTER_NEWT_H_
#define TREE_SITTER_NEWT_H_
typedef struct TSLanguage TSLanguage;
#ifdef __cplusplus
extern "C" {
#endif
const TSLanguage *tree_sitter_newt(void);
#ifdef __cplusplus
}
#endif
#endif // TREE_SITTER_NEWT_H_

15
bindings/go/binding.go generated Normal file
View File

@@ -0,0 +1,15 @@
package tree_sitter_newt
// #cgo CFLAGS: -std=c11 -fPIC
// #include "../../src/parser.c"
// #if __has_include("../../src/scanner.c")
// #include "../../src/scanner.c"
// #endif
import "C"
import "unsafe"
// Get the tree-sitter Language for this grammar.
func Language() unsafe.Pointer {
return unsafe.Pointer(C.tree_sitter_newt())
}

15
bindings/go/binding_test.go generated Normal file
View File

@@ -0,0 +1,15 @@
package tree_sitter_newt_test
import (
"testing"
tree_sitter "github.com/tree-sitter/go-tree-sitter"
tree_sitter_newt "github.com/dunhamsteve/tree-sitter-newt/bindings/go"
)
func TestCanLoadGrammar(t *testing.T) {
language := tree_sitter.NewLanguage(tree_sitter_newt.Language())
if language == nil {
t.Errorf("Error loading Newt grammar")
}
}

19
bindings/node/binding.cc generated Normal file
View File

@@ -0,0 +1,19 @@
#include <napi.h>
typedef struct TSLanguage TSLanguage;
extern "C" TSLanguage *tree_sitter_newt();
// "tree-sitter", "language" hashed with BLAKE2
const napi_type_tag LANGUAGE_TYPE_TAG = {
0x8AF2E5212AD58ABF, 0xD5006CAD83ABBA16
};
Napi::Object Init(Napi::Env env, Napi::Object exports) {
auto language = Napi::External<TSLanguage>::New(env, tree_sitter_newt());
language.TypeTag(&LANGUAGE_TYPE_TAG);
exports["language"] = language;
return exports;
}
NODE_API_MODULE(tree_sitter_newt_binding, Init)

9
bindings/node/binding_test.js generated Normal file
View File

@@ -0,0 +1,9 @@
const assert = require("node:assert");
const { test } = require("node:test");
const Parser = require("tree-sitter");
test("can load grammar", () => {
const parser = new Parser();
assert.doesNotThrow(() => parser.setLanguage(require(".")));
});

27
bindings/node/index.d.ts generated vendored Normal file
View File

@@ -0,0 +1,27 @@
type BaseNode = {
type: string;
named: boolean;
};
type ChildNode = {
multiple: boolean;
required: boolean;
types: BaseNode[];
};
type NodeInfo =
| (BaseNode & {
subtypes: BaseNode[];
})
| (BaseNode & {
fields: { [name: string]: ChildNode };
children: ChildNode[];
});
type Language = {
language: unknown;
nodeTypeInfo: NodeInfo[];
};
declare const language: Language;
export = language;

11
bindings/node/index.js generated Normal file
View File

@@ -0,0 +1,11 @@
const root = require("path").join(__dirname, "..", "..");
module.exports =
typeof process.versions.bun === "string"
// Support `bun build --compile` by being statically analyzable enough to find the .node file at build-time
? require(`../../prebuilds/${process.platform}-${process.arch}/tree-sitter-newt.node`)
: require("node-gyp-build")(root);
try {
module.exports.nodeTypeInfo = require("../../src/node-types.json");
} catch (_) {}

12
bindings/python/tests/test_binding.py generated Normal file
View File

@@ -0,0 +1,12 @@
from unittest import TestCase
from tree_sitter import Language, Parser
import tree_sitter_newt
class TestLanguage(TestCase):
def test_can_load_grammar(self):
try:
Parser(Language(tree_sitter_newt.language()))
except Exception:
self.fail("Error loading Newt grammar")

42
bindings/python/tree_sitter_newt/__init__.py generated Normal file
View File

@@ -0,0 +1,42 @@
"""Newt grammar for tree-sitter"""
from importlib.resources import files as _files
from ._binding import language
def _get_query(name, file):
query = _files(f"{__package__}.queries") / file
globals()[name] = query.read_text()
return globals()[name]
def __getattr__(name):
# NOTE: uncomment these to include any queries that this grammar contains:
# if name == "HIGHLIGHTS_QUERY":
# return _get_query("HIGHLIGHTS_QUERY", "highlights.scm")
# if name == "INJECTIONS_QUERY":
# return _get_query("INJECTIONS_QUERY", "injections.scm")
# if name == "LOCALS_QUERY":
# return _get_query("LOCALS_QUERY", "locals.scm")
# if name == "TAGS_QUERY":
# return _get_query("TAGS_QUERY", "tags.scm")
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
__all__ = [
"language",
# "HIGHLIGHTS_QUERY",
# "INJECTIONS_QUERY",
# "LOCALS_QUERY",
# "TAGS_QUERY",
]
def __dir__():
return sorted(__all__ + [
"__all__", "__builtins__", "__cached__", "__doc__", "__file__",
"__loader__", "__name__", "__package__", "__path__", "__spec__",
])

10
bindings/python/tree_sitter_newt/__init__.pyi generated Normal file
View File

@@ -0,0 +1,10 @@
from typing import Final
# NOTE: uncomment these to include any queries that this grammar contains:
# HIGHLIGHTS_QUERY: Final[str]
# INJECTIONS_QUERY: Final[str]
# LOCALS_QUERY: Final[str]
# TAGS_QUERY: Final[str]
def language() -> object: ...

35
bindings/python/tree_sitter_newt/binding.c generated Normal file
View File

@@ -0,0 +1,35 @@
#include <Python.h>
typedef struct TSLanguage TSLanguage;
TSLanguage *tree_sitter_newt(void);
static PyObject* _binding_language(PyObject *Py_UNUSED(self), PyObject *Py_UNUSED(args)) {
return PyCapsule_New(tree_sitter_newt(), "tree_sitter.Language", NULL);
}
static struct PyModuleDef_Slot slots[] = {
#ifdef Py_GIL_DISABLED
{Py_mod_gil, Py_MOD_GIL_NOT_USED},
#endif
{0, NULL}
};
static PyMethodDef methods[] = {
{"language", _binding_language, METH_NOARGS,
"Get the tree-sitter language for this grammar."},
{NULL, NULL, 0, NULL}
};
static struct PyModuleDef module = {
.m_base = PyModuleDef_HEAD_INIT,
.m_name = "_binding",
.m_doc = NULL,
.m_size = 0,
.m_methods = methods,
.m_slots = slots,
};
PyMODINIT_FUNC PyInit__binding(void) {
return PyModuleDef_Init(&module);
}

0
bindings/python/tree_sitter_newt/py.typed generated Normal file
View File

21
bindings/rust/build.rs generated Normal file
View File

@@ -0,0 +1,21 @@
fn main() {
let src_dir = std::path::Path::new("src");
let mut c_config = cc::Build::new();
c_config.std("c11").include(src_dir);
#[cfg(target_env = "msvc")]
c_config.flag("-utf-8");
let parser_path = src_dir.join("parser.c");
c_config.file(&parser_path);
println!("cargo:rerun-if-changed={}", parser_path.to_str().unwrap());
let scanner_path = src_dir.join("scanner.c");
if scanner_path.exists() {
c_config.file(&scanner_path);
println!("cargo:rerun-if-changed={}", scanner_path.to_str().unwrap());
}
c_config.compile("tree-sitter-newt");
}

51
bindings/rust/lib.rs generated Normal file
View File

@@ -0,0 +1,51 @@
//! This crate provides Newt language support for the [tree-sitter] parsing library.
//!
//! Typically, you will use the [`LANGUAGE`] constant to add this language to a
//! tree-sitter [`Parser`], and then use the parser to parse some code:
//!
//! ```
//! let code = r#"
//! "#;
//! let mut parser = tree_sitter::Parser::new();
//! let language = tree_sitter_newt::LANGUAGE;
//! parser
//! .set_language(&language.into())
//! .expect("Error loading Newt parser");
//! let tree = parser.parse(code, None).unwrap();
//! assert!(!tree.root_node().has_error());
//! ```
//!
//! [`Parser`]: https://docs.rs/tree-sitter/0.25.10/tree_sitter/struct.Parser.html
//! [tree-sitter]: https://tree-sitter.github.io/
use tree_sitter_language::LanguageFn;
extern "C" {
fn tree_sitter_newt() -> *const ();
}
/// The tree-sitter [`LanguageFn`] for this grammar.
pub const LANGUAGE: LanguageFn = unsafe { LanguageFn::from_raw(tree_sitter_newt) };
/// The content of the [`node-types.json`] file for this grammar.
///
/// [`node-types.json`]: https://tree-sitter.github.io/tree-sitter/using-parsers/6-static-node-types
pub const NODE_TYPES: &str = include_str!("../../src/node-types.json");
// NOTE: uncomment these to include any queries that this grammar contains:
// pub const HIGHLIGHTS_QUERY: &str = include_str!("../../queries/highlights.scm");
// pub const INJECTIONS_QUERY: &str = include_str!("../../queries/injections.scm");
// pub const LOCALS_QUERY: &str = include_str!("../../queries/locals.scm");
// pub const TAGS_QUERY: &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.into())
.expect("Error loading Newt parser");
}
}

16
bindings/swift/TreeSitterNewt/newt.h generated Normal file
View File

@@ -0,0 +1,16 @@
#ifndef TREE_SITTER_NEWT_H_
#define TREE_SITTER_NEWT_H_
typedef struct TSLanguage TSLanguage;
#ifdef __cplusplus
extern "C" {
#endif
const TSLanguage *tree_sitter_newt(void);
#ifdef __cplusplus
}
#endif
#endif // TREE_SITTER_NEWT_H_

12
bindings/swift/TreeSitterNewtTests/TreeSitterNewtTests.swift generated Normal file
View File

@@ -0,0 +1,12 @@
import XCTest
import SwiftTreeSitter
import TreeSitterNewt
final class TreeSitterNewtTests: XCTestCase {
func testCanLoadGrammar() throws {
let parser = Parser()
let language = Language(language: tree_sitter_newt())
XCTAssertNoThrow(try parser.setLanguage(language),
"Error loading Newt grammar")
}
}

5
go.mod generated Normal file
View File

@@ -0,0 +1,5 @@
module github.com/dunhamsteve/tree-sitter-newt
go 1.22
require github.com/tree-sitter/go-tree-sitter v0.24.0

149
grammar.js Normal file
View File

@@ -0,0 +1,149 @@
/**
* @file Newt grammar for tree-sitter
* @author Steve Dunham <dunhamsteve@gmail.com>
* @license MIT
*
* I copied some unpublished code that I used years ago for pi-forall
*/
/// <reference types="tree-sitter-cli/dsl" />
// @ts-check
const sep = (
/** @type {RuleOrLiteral} */ sep,
/** @type {RuleOrLiteral} */ rule,
) => optional(seq(rule, repeat(seq(sep, rule))));
const sep1 = (
/** @type {RuleOrLiteral} */ sep,
/** @type {RuleOrLiteral} */ rule,
) => seq(rule, repeat(seq(sep, rule)));
const layout = (
/** @type {GrammarSymbols<any>} */ $,
/** @type {RuleOrLiteral} */ rule,
) => seq($.start, repeat(seq($.semi, rule)), $.end)
// choice(
// seq("{", optional(sep1(";", rule)), "}"),
// );
module.exports = grammar({
name: "newt",
word: ($) => $.identifier,
extras: ($) => [$.comment, $._ws],
externals: ($) => [$.start, $.semi, $.end, $._ws],
rules: {
// TODO: add the actual grammar rules
source_file: ($) => $.module,
comment: ($) =>
token(
choice(
seq("--", /.*/),
// FIXME comments /- -/ are nested, which needs to be done in scanner.c
seq("/-", /([^-]|-+[^/])-/, "/"),
),
),
lamExpr: $ => seq(
choice("\\", "λ"),
repeat1($.identifier),
"=>",
$.typeExpr
),
// hole, parenTypeExpression, record update
_atom: $ => choice($.varname, $.strLit, $.operator, seq("(", $.typeExpr, ")")),
_parg: $ => choice($._atom, seq("{{", $.typeExpr, "}}"), seq("{", $.typeExpr, "}")),
appExpr: $ => seq($._atom, repeat($._parg)),
qname: ($) => sep1(".", $.identifier),
strLit: $ => /"[^"]*"/,
doCaseLet: $ => seq("let", "(", $.term, ")", "=", $.typeExpr,
layout($, $._orAlt)),
caseAlt: $ => seq($.term, "=>", $.term),
_orAlt: $ => seq("|", $.caseAlt),
_doArrow: $ => seq("<-", $.typeExpr, optional(layout($, $._orAlt))),
doArrow: $ => seq($.term, optional($._doArrow)),
doLet: $ => seq("let", $.identifier, "=", $.term),
_doExpr: $ => choice(
$.doCaseLet,
$.doLet,
$.doArrow),
doBlock: $ => seq("do", layout($, $._doExpr)),
ifThen: ($) => seq("if", $.term, "then", $.term, "else", $.term),
_term2: ($) =>
choice(
// caseExpr
// caseLet
// caseLamExpr
$.lamExpr,
$.doBlock,
$.ifThen,
$.appExpr,
),
term: ($) => prec.right(seq($._term2, repeat(seq("$", $._term2)))),
// varname is ident|uident|_, but we'll gloss over that
varname: ($) => $.identifier,
// abind/ibind/ebind in Parser.newt
binder: ($) =>
choice(
seq("(", $.identifier, ":", $.typeExpr, ")"),
// seq("(", $.typeExpr, ")"),
seq("{{", $.typeExpr, "}}"),
seq("{", $.identifier, ":", $.typeExpr, "}"),
),
_arr: ($) => choice("->", "→"),
forall: ($) => seq("∀", repeat1($.identifier), ".", $.typeExpr),
binders: ($) => seq(choice($.varname, repeat1($.binder)), $._arr, $.typeExpr),
typeExpr: ($) => choice($.forall, $.binders, $.term),
// pitype: ($) =>
// seq(
// optional($.forall),
// repeat(seq(repeat1(choice($.identifier, $.binder)), $._arr)),
// $.identifier,
// ),
sigDecl: ($) => seq($.identifier, ":", $.typeExpr),
defDecl: ($) => seq($.appExpr, "=", $.typeExpr),
dataDecl: ($) =>
seq(
"data",
$.identifier,
":",
$.typeExpr,
optional(seq("where", layout($, $.conDef))),
),
importDef: ($) => seq("import", $.qname),
conDef: ($) =>
seq(
$.identifier, // upper
":",
$.typeExpr
),
_decl: ($) =>
choice(
// mixfixDecl,
// ptypeDecl
// pfuncDecl
$.dataDecl,
// shortDataDecl
// classDecl
// instanceDecl
// recordDecl
// exportDecl
// deriveDecl
$.sigDecl,
$.defDecl,
),
module: ($) =>
seq(
"module",
$.identifier,
repeat(seq($.semi, $.importDef)),
repeat(seq($.semi, $._decl)),
),
// these are _way_ more generous in newt
operator: ($) => /[!#$%&*+.,/<=>?@\\^|-]+/,
identifier: ($) => /[A-Za-z_][\w']*|[,]|\+\+/,
},
});

52
package.json generated Normal file
View File

@@ -0,0 +1,52 @@
{
"name": "tree-sitter-newt",
"version": "0.1.0",
"description": "Newt grammar for tree-sitter",
"repository": "https://github.com/dunhamsteve/tree-sitter-newt",
"license": "MIT",
"author": {
"name": "Steve Dunham",
"email": "dunhamsteve@gmail.com"
},
"main": "bindings/node",
"types": "bindings/node",
"keywords": [
"incremental",
"parsing",
"tree-sitter",
"newt"
],
"files": [
"grammar.js",
"tree-sitter.json",
"binding.gyp",
"prebuilds/**",
"bindings/node/*",
"queries/*",
"src/**",
"*.wasm"
],
"dependencies": {
"node-addon-api": "^8.5.0",
"node-gyp-build": "^4.8.4"
},
"devDependencies": {
"prebuildify": "^6.0.1",
"tree-sitter": "^0.22.4",
"tree-sitter-cli": "^0.25.10"
},
"peerDependencies": {
"tree-sitter": "^0.22.4"
},
"peerDependenciesMeta": {
"tree-sitter": {
"optional": true
}
},
"scripts": {
"install": "node-gyp-build",
"prestart": "tree-sitter build --wasm",
"start": "tree-sitter playground",
"test": "node --test bindings/node/*_test.js"
}
}

29
pyproject.toml generated Normal file
View File

@@ -0,0 +1,29 @@
[build-system]
requires = ["setuptools>=62.4.0", "wheel"]
build-backend = "setuptools.build_meta"
[project]
name = "tree-sitter-newt"
description = "Newt grammar for tree-sitter"
version = "0.1.0"
keywords = ["incremental", "parsing", "tree-sitter", "newt"]
classifiers = [
"Intended Audience :: Developers",
"Topic :: Software Development :: Compilers",
"Topic :: Text Processing :: Linguistic",
"Typing :: Typed",
]
authors = [{ name = "Steve Dunham", email = "dunhamsteve@gmail.com" }]
requires-python = ">=3.10"
license.text = "MIT"
readme = "README.md"
[project.urls]
Homepage = "https://github.com/dunhamsteve/tree-sitter-newt"
[project.optional-dependencies]
core = ["tree-sitter~=0.24"]
[tool.cibuildwheel]
build = "cp310-*"
build-frontend = "build"

77
setup.py generated Normal file
View File

@@ -0,0 +1,77 @@
from os import path
from sysconfig import get_config_var
from setuptools import Extension, find_packages, setup
from setuptools.command.build import build
from setuptools.command.build_ext import build_ext
from setuptools.command.egg_info import egg_info
from wheel.bdist_wheel import bdist_wheel
class Build(build):
def run(self):
if path.isdir("queries"):
dest = path.join(self.build_lib, "tree_sitter_newt", "queries")
self.copy_tree("queries", dest)
super().run()
class BuildExt(build_ext):
def build_extension(self, ext: Extension):
if self.compiler.compiler_type != "msvc":
ext.extra_compile_args = ["-std=c11", "-fvisibility=hidden"]
else:
ext.extra_compile_args = ["/std:c11", "/utf-8"]
if path.exists("src/scanner.c"):
ext.sources.append("src/scanner.c")
if ext.py_limited_api:
ext.define_macros.append(("Py_LIMITED_API", "0x030A0000"))
super().build_extension(ext)
class BdistWheel(bdist_wheel):
def get_tag(self):
python, abi, platform = super().get_tag()
if python.startswith("cp"):
python, abi = "cp310", "abi3"
return python, abi, platform
class EggInfo(egg_info):
def find_sources(self):
super().find_sources()
self.filelist.recursive_include("queries", "*.scm")
self.filelist.include("src/tree_sitter/*.h")
setup(
packages=find_packages("bindings/python"),
package_dir={"": "bindings/python"},
package_data={
"tree_sitter_newt": ["*.pyi", "py.typed"],
"tree_sitter_newt.queries": ["*.scm"],
},
ext_package="tree_sitter_newt",
ext_modules=[
Extension(
name="_binding",
sources=[
"bindings/python/tree_sitter_newt/binding.c",
"src/parser.c",
],
define_macros=[
("PY_SSIZE_T_CLEAN", None),
("TREE_SITTER_HIDE_SYMBOLS", None),
],
include_dirs=["src"],
py_limited_api=not get_config_var("Py_GIL_DISABLED"),
)
],
cmdclass={
"build": Build,
"build_ext": BuildExt,
"bdist_wheel": BdistWheel,
"egg_info": EggInfo,
},
zip_safe=False
)

911
src/grammar.json generated Normal file
View File

@@ -0,0 +1,911 @@
{
"$schema": "https://tree-sitter.github.io/tree-sitter/assets/schemas/grammar.schema.json",
"name": "newt",
"word": "identifier",
"rules": {
"source_file": {
"type": "SYMBOL",
"name": "module"
},
"comment": {
"type": "TOKEN",
"content": {
"type": "CHOICE",
"members": [
{
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "--"
},
{
"type": "PATTERN",
"value": ".*"
}
]
},
{
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "/-"
},
{
"type": "PATTERN",
"value": "([^-]|-+[^/])-"
},
{
"type": "STRING",
"value": "/"
}
]
}
]
}
},
"lamExpr": {
"type": "SEQ",
"members": [
{
"type": "CHOICE",
"members": [
{
"type": "STRING",
"value": "\\"
},
{
"type": "STRING",
"value": "λ"
}
]
},
{
"type": "REPEAT1",
"content": {
"type": "SYMBOL",
"name": "identifier"
}
},
{
"type": "STRING",
"value": "=>"
},
{
"type": "SYMBOL",
"name": "typeExpr"
}
]
},
"_atom": {
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "varname"
},
{
"type": "SYMBOL",
"name": "strLit"
},
{
"type": "SYMBOL",
"name": "operator"
},
{
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "("
},
{
"type": "SYMBOL",
"name": "typeExpr"
},
{
"type": "STRING",
"value": ")"
}
]
}
]
},
"_parg": {
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "_atom"
},
{
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "{{"
},
{
"type": "SYMBOL",
"name": "typeExpr"
},
{
"type": "STRING",
"value": "}}"
}
]
},
{
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "{"
},
{
"type": "SYMBOL",
"name": "typeExpr"
},
{
"type": "STRING",
"value": "}"
}
]
}
]
},
"appExpr": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "_atom"
},
{
"type": "REPEAT",
"content": {
"type": "SYMBOL",
"name": "_parg"
}
}
]
},
"qname": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "identifier"
},
{
"type": "REPEAT",
"content": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "."
},
{
"type": "SYMBOL",
"name": "identifier"
}
]
}
}
]
},
"strLit": {
"type": "PATTERN",
"value": "\"[^\"]*\""
},
"doCaseLet": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "let"
},
{
"type": "STRING",
"value": "("
},
{
"type": "SYMBOL",
"name": "term"
},
{
"type": "STRING",
"value": ")"
},
{
"type": "STRING",
"value": "="
},
{
"type": "SYMBOL",
"name": "typeExpr"
},
{
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "start"
},
{
"type": "REPEAT",
"content": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "semi"
},
{
"type": "SYMBOL",
"name": "_orAlt"
}
]
}
},
{
"type": "SYMBOL",
"name": "end"
}
]
}
]
},
"caseAlt": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "term"
},
{
"type": "STRING",
"value": "=>"
},
{
"type": "SYMBOL",
"name": "term"
}
]
},
"_orAlt": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "|"
},
{
"type": "SYMBOL",
"name": "caseAlt"
}
]
},
"_doArrow": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "<-"
},
{
"type": "SYMBOL",
"name": "typeExpr"
},
{
"type": "CHOICE",
"members": [
{
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "start"
},
{
"type": "REPEAT",
"content": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "semi"
},
{
"type": "SYMBOL",
"name": "_orAlt"
}
]
}
},
{
"type": "SYMBOL",
"name": "end"
}
]
},
{
"type": "BLANK"
}
]
}
]
},
"doArrow": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "term"
},
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "_doArrow"
},
{
"type": "BLANK"
}
]
}
]
},
"doLet": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "let"
},
{
"type": "SYMBOL",
"name": "identifier"
},
{
"type": "STRING",
"value": "="
},
{
"type": "SYMBOL",
"name": "term"
}
]
},
"_doExpr": {
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "doCaseLet"
},
{
"type": "SYMBOL",
"name": "doLet"
},
{
"type": "SYMBOL",
"name": "doArrow"
}
]
},
"doBlock": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "do"
},
{
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "start"
},
{
"type": "REPEAT",
"content": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "semi"
},
{
"type": "SYMBOL",
"name": "_doExpr"
}
]
}
},
{
"type": "SYMBOL",
"name": "end"
}
]
}
]
},
"ifThen": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "if"
},
{
"type": "SYMBOL",
"name": "term"
},
{
"type": "STRING",
"value": "then"
},
{
"type": "SYMBOL",
"name": "term"
},
{
"type": "STRING",
"value": "else"
},
{
"type": "SYMBOL",
"name": "term"
}
]
},
"_term2": {
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "lamExpr"
},
{
"type": "SYMBOL",
"name": "doBlock"
},
{
"type": "SYMBOL",
"name": "ifThen"
},
{
"type": "SYMBOL",
"name": "appExpr"
}
]
},
"term": {
"type": "PREC_RIGHT",
"value": 0,
"content": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "_term2"
},
{
"type": "REPEAT",
"content": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "$"
},
{
"type": "SYMBOL",
"name": "_term2"
}
]
}
}
]
}
},
"varname": {
"type": "SYMBOL",
"name": "identifier"
},
"binder": {
"type": "CHOICE",
"members": [
{
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "("
},
{
"type": "SYMBOL",
"name": "identifier"
},
{
"type": "STRING",
"value": ":"
},
{
"type": "SYMBOL",
"name": "typeExpr"
},
{
"type": "STRING",
"value": ")"
}
]
},
{
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "{{"
},
{
"type": "SYMBOL",
"name": "typeExpr"
},
{
"type": "STRING",
"value": "}}"
}
]
},
{
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "{"
},
{
"type": "SYMBOL",
"name": "identifier"
},
{
"type": "STRING",
"value": ":"
},
{
"type": "SYMBOL",
"name": "typeExpr"
},
{
"type": "STRING",
"value": "}"
}
]
}
]
},
"_arr": {
"type": "CHOICE",
"members": [
{
"type": "STRING",
"value": "->"
},
{
"type": "STRING",
"value": "→"
}
]
},
"forall": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "∀"
},
{
"type": "REPEAT1",
"content": {
"type": "SYMBOL",
"name": "identifier"
}
},
{
"type": "STRING",
"value": "."
},
{
"type": "SYMBOL",
"name": "typeExpr"
}
]
},
"binders": {
"type": "SEQ",
"members": [
{
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "varname"
},
{
"type": "REPEAT1",
"content": {
"type": "SYMBOL",
"name": "binder"
}
}
]
},
{
"type": "SYMBOL",
"name": "_arr"
},
{
"type": "SYMBOL",
"name": "typeExpr"
}
]
},
"typeExpr": {
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "forall"
},
{
"type": "SYMBOL",
"name": "binders"
},
{
"type": "SYMBOL",
"name": "term"
}
]
},
"sigDecl": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "identifier"
},
{
"type": "STRING",
"value": ":"
},
{
"type": "SYMBOL",
"name": "typeExpr"
}
]
},
"defDecl": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "appExpr"
},
{
"type": "STRING",
"value": "="
},
{
"type": "SYMBOL",
"name": "typeExpr"
}
]
},
"dataDecl": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "data"
},
{
"type": "SYMBOL",
"name": "identifier"
},
{
"type": "STRING",
"value": ":"
},
{
"type": "SYMBOL",
"name": "typeExpr"
},
{
"type": "CHOICE",
"members": [
{
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "where"
},
{
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "start"
},
{
"type": "REPEAT",
"content": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "semi"
},
{
"type": "SYMBOL",
"name": "conDef"
}
]
}
},
{
"type": "SYMBOL",
"name": "end"
}
]
}
]
},
{
"type": "BLANK"
}
]
}
]
},
"importDef": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "import"
},
{
"type": "SYMBOL",
"name": "qname"
}
]
},
"conDef": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "identifier"
},
{
"type": "STRING",
"value": ":"
},
{
"type": "SYMBOL",
"name": "typeExpr"
}
]
},
"_decl": {
"type": "CHOICE",
"members": [
{
"type": "SYMBOL",
"name": "dataDecl"
},
{
"type": "SYMBOL",
"name": "sigDecl"
},
{
"type": "SYMBOL",
"name": "defDecl"
}
]
},
"module": {
"type": "SEQ",
"members": [
{
"type": "STRING",
"value": "module"
},
{
"type": "SYMBOL",
"name": "identifier"
},
{
"type": "REPEAT",
"content": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "semi"
},
{
"type": "SYMBOL",
"name": "importDef"
}
]
}
},
{
"type": "REPEAT",
"content": {
"type": "SEQ",
"members": [
{
"type": "SYMBOL",
"name": "semi"
},
{
"type": "SYMBOL",
"name": "_decl"
}
]
}
}
]
},
"operator": {
"type": "PATTERN",
"value": "[!#$%&*+.,/<=>?@\\\\^|-]+"
},
"identifier": {
"type": "PATTERN",
"value": "[A-Za-z_][\\w']*|[,]|\\+\\+"
}
},
"extras": [
{
"type": "SYMBOL",
"name": "comment"
},
{
"type": "SYMBOL",
"name": "_ws"
}
],
"conflicts": [],
"precedences": [],
"externals": [
{
"type": "SYMBOL",
"name": "start"
},
{
"type": "SYMBOL",
"name": "semi"
},
{
"type": "SYMBOL",
"name": "end"
},
{
"type": "SYMBOL",
"name": "_ws"
}
],
"inline": [],
"supertypes": [],
"reserved": {}
}

638
src/node-types.json generated Normal file
View File

@@ -0,0 +1,638 @@
[
{
"type": "appExpr",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "operator",
"named": true
},
{
"type": "strLit",
"named": true
},
{
"type": "typeExpr",
"named": true
},
{
"type": "varname",
"named": true
}
]
}
},
{
"type": "binder",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "identifier",
"named": true
},
{
"type": "typeExpr",
"named": true
}
]
}
},
{
"type": "binders",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "binder",
"named": true
},
{
"type": "typeExpr",
"named": true
},
{
"type": "varname",
"named": true
}
]
}
},
{
"type": "caseAlt",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "term",
"named": true
}
]
}
},
{
"type": "conDef",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "identifier",
"named": true
},
{
"type": "typeExpr",
"named": true
}
]
}
},
{
"type": "dataDecl",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "conDef",
"named": true
},
{
"type": "end",
"named": true
},
{
"type": "identifier",
"named": true
},
{
"type": "semi",
"named": true
},
{
"type": "start",
"named": true
},
{
"type": "typeExpr",
"named": true
}
]
}
},
{
"type": "defDecl",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "appExpr",
"named": true
},
{
"type": "typeExpr",
"named": true
}
]
}
},
{
"type": "doArrow",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "caseAlt",
"named": true
},
{
"type": "end",
"named": true
},
{
"type": "semi",
"named": true
},
{
"type": "start",
"named": true
},
{
"type": "term",
"named": true
},
{
"type": "typeExpr",
"named": true
}
]
}
},
{
"type": "doBlock",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "doArrow",
"named": true
},
{
"type": "doCaseLet",
"named": true
},
{
"type": "doLet",
"named": true
},
{
"type": "end",
"named": true
},
{
"type": "semi",
"named": true
},
{
"type": "start",
"named": true
}
]
}
},
{
"type": "doCaseLet",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "caseAlt",
"named": true
},
{
"type": "end",
"named": true
},
{
"type": "semi",
"named": true
},
{
"type": "start",
"named": true
},
{
"type": "term",
"named": true
},
{
"type": "typeExpr",
"named": true
}
]
}
},
{
"type": "doLet",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "identifier",
"named": true
},
{
"type": "term",
"named": true
}
]
}
},
{
"type": "forall",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "identifier",
"named": true
},
{
"type": "typeExpr",
"named": true
}
]
}
},
{
"type": "ifThen",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "term",
"named": true
}
]
}
},
{
"type": "importDef",
"named": true,
"fields": {},
"children": {
"multiple": false,
"required": true,
"types": [
{
"type": "qname",
"named": true
}
]
}
},
{
"type": "lamExpr",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "identifier",
"named": true
},
{
"type": "typeExpr",
"named": true
}
]
}
},
{
"type": "module",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "dataDecl",
"named": true
},
{
"type": "defDecl",
"named": true
},
{
"type": "identifier",
"named": true
},
{
"type": "importDef",
"named": true
},
{
"type": "semi",
"named": true
},
{
"type": "sigDecl",
"named": true
}
]
}
},
{
"type": "qname",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "identifier",
"named": true
}
]
}
},
{
"type": "sigDecl",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "identifier",
"named": true
},
{
"type": "typeExpr",
"named": true
}
]
}
},
{
"type": "source_file",
"named": true,
"root": true,
"fields": {},
"children": {
"multiple": false,
"required": true,
"types": [
{
"type": "module",
"named": true
}
]
}
},
{
"type": "term",
"named": true,
"fields": {},
"children": {
"multiple": true,
"required": true,
"types": [
{
"type": "appExpr",
"named": true
},
{
"type": "doBlock",
"named": true
},
{
"type": "ifThen",
"named": true
},
{
"type": "lamExpr",
"named": true
}
]
}
},
{
"type": "typeExpr",
"named": true,
"fields": {},
"children": {
"multiple": false,
"required": true,
"types": [
{
"type": "binders",
"named": true
},
{
"type": "forall",
"named": true
},
{
"type": "term",
"named": true
}
]
}
},
{
"type": "varname",
"named": true,
"fields": {},
"children": {
"multiple": false,
"required": true,
"types": [
{
"type": "identifier",
"named": true
}
]
}
},
{
"type": "$",
"named": false
},
{
"type": "(",
"named": false
},
{
"type": ")",
"named": false
},
{
"type": "->",
"named": false
},
{
"type": ".",
"named": false
},
{
"type": ":",
"named": false
},
{
"type": "<-",
"named": false
},
{
"type": "=",
"named": false
},
{
"type": "=>",
"named": false
},
{
"type": "\\",
"named": false
},
{
"type": "comment",
"named": true,
"extra": true
},
{
"type": "data",
"named": false
},
{
"type": "do",
"named": false
},
{
"type": "else",
"named": false
},
{
"type": "end",
"named": true
},
{
"type": "identifier",
"named": true
},
{
"type": "if",
"named": false
},
{
"type": "import",
"named": false
},
{
"type": "let",
"named": false
},
{
"type": "module",
"named": false
},
{
"type": "operator",
"named": true
},
{
"type": "semi",
"named": true
},
{
"type": "start",
"named": true
},
{
"type": "strLit",
"named": true
},
{
"type": "then",
"named": false
},
{
"type": "where",
"named": false
},
{
"type": "{",
"named": false
},
{
"type": "{{",
"named": false
},
{
"type": "|",
"named": false
},
{
"type": "}",
"named": false
},
{
"type": "}}",
"named": false
},
{
"type": "λ",
"named": false
},
{
"type": "→",
"named": false
},
{
"type": "∀",
"named": false
}
]

11208
src/parser.c generated Normal file
View File

File diff suppressed because it is too large Load Diff

159
src/scanner.c Normal file
View File

@@ -0,0 +1,159 @@
#include "tree_sitter/parser.h"
#include "tree_sitter/alloc.h"
#include <stdio.h>
#include <string.h>
// not available in wasm
// lexer->log(...) is documented upstream, but is not in parser.h
#define fprintf(...) //
typedef struct {
uint32_t len;
uint32_t cap;
uint32_t *data;
} State;
enum TokenType {
VIRT_START,
VIRT_SEMI,
VIRT_END,
WHITESPACE,
};
static void ensure(State *state, uint32_t count) {
if (state->cap < count) {
state->cap = count * 2;
uint32_t *new_data = ts_malloc(sizeof(uint32_t) * state->cap);
memcpy(new_data, state->data, state->len * sizeof(uint32_t));
ts_free(state->data);
state->data = new_data;
}
}
static void push(State *state, uint32_t col) {
// fprintf(stderr, "push %d\n", col);
ensure(state, state->len + 1);
state->data[state->len++] = col;
}
static uint32_t pop(State *state) {
if (state->len) {
// fprintf(stderr, "pop %d\n", state->data[state->len-1]);
state->len--;
return state->data[state->len];
}
fprintf(stderr, "stack underflow");
return 0;
}
static int32_t peek(State *state) {
return state->len ? state->data[state->len - 1] : -1; // or -1?
}
#define PEEK lexer->lookahead
#define PEEK_WS (PEEK == ' ' || PEEK == '\n' || PEEK == '\t')
/**
* The custom scanner is responsible for the virtual indent, outdent, and semi tokens.
* Additionally it handles whitespace. This allows us to give the virtual tokens priority over
* whitespace. So tree-sitter can only advance over whitespace if there is enough of it or if
* it gets a START, SEMI, or END.
*/
bool tree_sitter_newt_external_scanner_scan(State *state, TSLexer *lexer,
const bool *syms) {
fprintf(stderr, "scan %d %d %d %d\n", syms[0], syms[1], syms[2], syms[3]);
// skip whitespace
bool ws = false;
while (PEEK == ' ' || PEEK == '\n' || PEEK == '\t') {
ws = true;
lexer->advance(lexer,true);
}
// Might have to deal with comments in here.
if (PEEK == '-' || PEEK == '{') {
if (syms[WHITESPACE] && ws) {
lexer->result_symbol = WHITESPACE;
return true;
}
// comments don't count for START/SEMI/END, let tree-sitter process the comment and get back to us
return false;
}
int32_t cur = peek(state);
uint32_t col = lexer->get_column(lexer);
if (ws && syms[VIRT_START]) {
fprintf(stderr, "start [%d %d %d %d] %d %d\n", syms[0], syms[1], syms[2],
syms[3], col, cur);
push(state, col);
lexer->result_symbol = VIRT_START;
return true;
}
// if we are in a smaller column, we force virt_end
if (syms[VIRT_END]) {
if (col < cur) {
fprintf(stderr, "end [%d %d %d %d] %d %d\n", syms[0], syms[1], syms[2],
syms[3], col, cur);
pop(state);
lexer->result_symbol = VIRT_END;
return true;
}
}
// but we can't do that for semi?
if (syms[VIRT_SEMI]) {
// FIXME - not eof, but we are requiring one at end of file at the moment.
if (!lexer->eof(lexer) && col == cur) {
lexer->result_symbol = VIRT_SEMI;
fprintf(stderr, "semi [%d %d %d %d] %d %d\n", syms[0], syms[1], syms[2],
syms[3], col, cur);
return true;
} else {
fprintf(stderr, "not semi [%d %d %d %d] %d %d\n", syms[0], syms[1],
syms[2], syms[3], col, cur);
}
}
if (syms[WHITESPACE] && ws) {
fprintf(stderr, "whitespace %d\n", cur);
lexer->result_symbol = WHITESPACE;
return true;
}
return false;
}
void *tree_sitter_newt_external_scanner_create() {
State *state = calloc(sizeof(State), 1);
state->cap = 20;
state->data = ts_malloc(sizeof(uint32_t) * state->cap);
// put the initial level at 0 and use semi at top level
push(state, 0);
return state;
}
void tree_sitter_newt_external_scanner_destroy(State *state) {
ts_free(state->data);
ts_free(state);
}
unsigned tree_sitter_newt_external_scanner_serialize(State *state,
char *buffer) {
unsigned size = sizeof(state->data[0]) * state->len;
if (size > TREE_SITTER_SERIALIZATION_BUFFER_SIZE) {
return 0;
}
memcpy(buffer, state->data, size);
return size;
}
void tree_sitter_newt_external_scanner_deserialize(State *state,
char *buffer,
unsigned length) {
unsigned len = length / sizeof(state->data[0]);
if (len > 0) {
ensure(state, len);
state->len = len;
memcpy(state->data, buffer, length);
}
}

54
src/tree_sitter/alloc.h generated Normal file
View File

@@ -0,0 +1,54 @@
#ifndef TREE_SITTER_ALLOC_H_
#define TREE_SITTER_ALLOC_H_
#ifdef __cplusplus
extern "C" {
#endif
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
// Allow clients to override allocation functions
#ifdef TREE_SITTER_REUSE_ALLOCATOR
extern void *(*ts_current_malloc)(size_t size);
extern void *(*ts_current_calloc)(size_t count, size_t size);
extern void *(*ts_current_realloc)(void *ptr, size_t size);
extern void (*ts_current_free)(void *ptr);
#ifndef ts_malloc
#define ts_malloc ts_current_malloc
#endif
#ifndef ts_calloc
#define ts_calloc ts_current_calloc
#endif
#ifndef ts_realloc
#define ts_realloc ts_current_realloc
#endif
#ifndef ts_free
#define ts_free ts_current_free
#endif
#else
#ifndef ts_malloc
#define ts_malloc malloc
#endif
#ifndef ts_calloc
#define ts_calloc calloc
#endif
#ifndef ts_realloc
#define ts_realloc realloc
#endif
#ifndef ts_free
#define ts_free free
#endif
#endif
#ifdef __cplusplus
}
#endif
#endif // TREE_SITTER_ALLOC_H_

291
src/tree_sitter/array.h generated Normal file
View File

@@ -0,0 +1,291 @@
#ifndef TREE_SITTER_ARRAY_H_
#define TREE_SITTER_ARRAY_H_
#ifdef __cplusplus
extern "C" {
#endif
#include "./alloc.h"
#include <assert.h>
#include <stdbool.h>
#include <stdint.h>
#include <stdlib.h>
#include <string.h>
#ifdef _MSC_VER
#pragma warning(push)
#pragma warning(disable : 4101)
#elif defined(__GNUC__) || defined(__clang__)
#pragma GCC diagnostic push
#pragma GCC diagnostic ignored "-Wunused-variable"
#endif
#define Array(T) \
struct { \
T *contents; \
uint32_t size; \
uint32_t capacity; \
}
/// Initialize an array.
#define array_init(self) \
((self)->size = 0, (self)->capacity = 0, (self)->contents = NULL)
/// Create an empty array.
#define array_new() \
{ NULL, 0, 0 }
/// Get a pointer to the element at a given `index` in the array.
#define array_get(self, _index) \
(assert((uint32_t)(_index) < (self)->size), &(self)->contents[_index])
/// Get a pointer to the first element in the array.
#define array_front(self) array_get(self, 0)
/// Get a pointer to the last element in the array.
#define array_back(self) array_get(self, (self)->size - 1)
/// Clear the array, setting its size to zero. Note that this does not free any
/// memory allocated for the array's contents.
#define array_clear(self) ((self)->size = 0)
/// Reserve `new_capacity` elements of space in the array. If `new_capacity` is
/// less than the array's current capacity, this function has no effect.
#define array_reserve(self, new_capacity) \
_array__reserve((Array *)(self), array_elem_size(self), new_capacity)
/// Free any memory allocated for this array. Note that this does not free any
/// memory allocated for the array's contents.
#define array_delete(self) _array__delete((Array *)(self))
/// Push a new `element` onto the end of the array.
#define array_push(self, element) \
(_array__grow((Array *)(self), 1, array_elem_size(self)), \
(self)->contents[(self)->size++] = (element))
/// Increase the array's size by `count` elements.
/// New elements are zero-initialized.
#define array_grow_by(self, count) \
do { \
if ((count) == 0) break; \
_array__grow((Array *)(self), count, array_elem_size(self)); \
memset((self)->contents + (self)->size, 0, (count) * array_elem_size(self)); \
(self)->size += (count); \
} while (0)
/// Append all elements from one array to the end of another.
#define array_push_all(self, other) \
array_extend((self), (other)->size, (other)->contents)
/// Append `count` elements to the end of the array, reading their values from the
/// `contents` pointer.
#define array_extend(self, count, contents) \
_array__splice( \
(Array *)(self), array_elem_size(self), (self)->size, \
0, count, contents \
)
/// Remove `old_count` elements from the array starting at the given `index`. At
/// the same index, insert `new_count` new elements, reading their values from the
/// `new_contents` pointer.
#define array_splice(self, _index, old_count, new_count, new_contents) \
_array__splice( \
(Array *)(self), array_elem_size(self), _index, \
old_count, new_count, new_contents \
)
/// Insert one `element` into the array at the given `index`.
#define array_insert(self, _index, element) \
_array__splice((Array *)(self), array_elem_size(self), _index, 0, 1, &(element))
/// Remove one element from the array at the given `index`.
#define array_erase(self, _index) \
_array__erase((Array *)(self), array_elem_size(self), _index)
/// Pop the last element off the array, returning the element by value.
#define array_pop(self) ((self)->contents[--(self)->size])
/// Assign the contents of one array to another, reallocating if necessary.
#define array_assign(self, other) \
_array__assign((Array *)(self), (const Array *)(other), array_elem_size(self))
/// Swap one array with another
#define array_swap(self, other) \
_array__swap((Array *)(self), (Array *)(other))
/// Get the size of the array contents
#define array_elem_size(self) (sizeof *(self)->contents)
/// Search a sorted array for a given `needle` value, using the given `compare`
/// callback to determine the order.
///
/// If an existing element is found to be equal to `needle`, then the `index`
/// out-parameter is set to the existing value's index, and the `exists`
/// out-parameter is set to true. Otherwise, `index` is set to an index where
/// `needle` should be inserted in order to preserve the sorting, and `exists`
/// is set to false.
#define array_search_sorted_with(self, compare, needle, _index, _exists) \
_array__search_sorted(self, 0, compare, , needle, _index, _exists)
/// Search a sorted array for a given `needle` value, using integer comparisons
/// of a given struct field (specified with a leading dot) to determine the order.
///
/// See also `array_search_sorted_with`.
#define array_search_sorted_by(self, field, needle, _index, _exists) \
_array__search_sorted(self, 0, _compare_int, field, needle, _index, _exists)
/// Insert a given `value` into a sorted array, using the given `compare`
/// callback to determine the order.
#define array_insert_sorted_with(self, compare, value) \
do { \
unsigned _index, _exists; \
array_search_sorted_with(self, compare, &(value), &_index, &_exists); \
if (!_exists) array_insert(self, _index, value); \
} while (0)
/// Insert a given `value` into a sorted array, using integer comparisons of
/// a given struct field (specified with a leading dot) to determine the order.
///
/// See also `array_search_sorted_by`.
#define array_insert_sorted_by(self, field, value) \
do { \
unsigned _index, _exists; \
array_search_sorted_by(self, field, (value) field, &_index, &_exists); \
if (!_exists) array_insert(self, _index, value); \
} while (0)
// Private
typedef Array(void) Array;
/// This is not what you're looking for, see `array_delete`.
static inline void _array__delete(Array *self) {
if (self->contents) {
ts_free(self->contents);
self->contents = NULL;
self->size = 0;
self->capacity = 0;
}
}
/// This is not what you're looking for, see `array_erase`.
static inline void _array__erase(Array *self, size_t element_size,
uint32_t index) {
assert(index < self->size);
char *contents = (char *)self->contents;
memmove(contents + index * element_size, contents + (index + 1) * element_size,
(self->size - index - 1) * element_size);
self->size--;
}
/// This is not what you're looking for, see `array_reserve`.
static inline void _array__reserve(Array *self, size_t element_size, uint32_t new_capacity) {
if (new_capacity > self->capacity) {
if (self->contents) {
self->contents = ts_realloc(self->contents, new_capacity * element_size);
} else {
self->contents = ts_malloc(new_capacity * element_size);
}
self->capacity = new_capacity;
}
}
/// This is not what you're looking for, see `array_assign`.
static inline void _array__assign(Array *self, const Array *other, size_t element_size) {
_array__reserve(self, element_size, other->size);
self->size = other->size;
memcpy(self->contents, other->contents, self->size * element_size);
}
/// This is not what you're looking for, see `array_swap`.
static inline void _array__swap(Array *self, Array *other) {
Array swap = *other;
*other = *self;
*self = swap;
}
/// This is not what you're looking for, see `array_push` or `array_grow_by`.
static inline void _array__grow(Array *self, uint32_t count, size_t element_size) {
uint32_t new_size = self->size + count;
if (new_size > self->capacity) {
uint32_t new_capacity = self->capacity * 2;
if (new_capacity < 8) new_capacity = 8;
if (new_capacity < new_size) new_capacity = new_size;
_array__reserve(self, element_size, new_capacity);
}
}
/// This is not what you're looking for, see `array_splice`.
static inline void _array__splice(Array *self, size_t element_size,
uint32_t index, uint32_t old_count,
uint32_t new_count, const void *elements) {
uint32_t new_size = self->size + new_count - old_count;
uint32_t old_end = index + old_count;
uint32_t new_end = index + new_count;
assert(old_end <= self->size);
_array__reserve(self, element_size, new_size);
char *contents = (char *)self->contents;
if (self->size > old_end) {
memmove(
contents + new_end * element_size,
contents + old_end * element_size,
(self->size - old_end) * element_size
);
}
if (new_count > 0) {
if (elements) {
memcpy(
(contents + index * element_size),
elements,
new_count * element_size
);
} else {
memset(
(contents + index * element_size),
0,
new_count * element_size
);
}
}
self->size += new_count - old_count;
}
/// A binary search routine, based on Rust's `std::slice::binary_search_by`.
/// This is not what you're looking for, see `array_search_sorted_with` or `array_search_sorted_by`.
#define _array__search_sorted(self, start, compare, suffix, needle, _index, _exists) \
do { \
*(_index) = start; \
*(_exists) = false; \
uint32_t size = (self)->size - *(_index); \
if (size == 0) break; \
int comparison; \
while (size > 1) { \
uint32_t half_size = size / 2; \
uint32_t mid_index = *(_index) + half_size; \
comparison = compare(&((self)->contents[mid_index] suffix), (needle)); \
if (comparison <= 0) *(_index) = mid_index; \
size -= half_size; \
} \
comparison = compare(&((self)->contents[*(_index)] suffix), (needle)); \
if (comparison == 0) *(_exists) = true; \
else if (comparison < 0) *(_index) += 1; \
} while (0)
/// Helper macro for the `_sorted_by` routines below. This takes the left (existing)
/// parameter by reference in order to work with the generic sorting function above.
#define _compare_int(a, b) ((int)*(a) - (int)(b))
#ifdef _MSC_VER
#pragma warning(pop)
#elif defined(__GNUC__) || defined(__clang__)
#pragma GCC diagnostic pop
#endif
#ifdef __cplusplus
}
#endif
#endif // TREE_SITTER_ARRAY_H_

286
src/tree_sitter/parser.h generated Normal file
View File

@@ -0,0 +1,286 @@
#ifndef TREE_SITTER_PARSER_H_
#define TREE_SITTER_PARSER_H_
#ifdef __cplusplus
extern "C" {
#endif
#include <stdbool.h>
#include <stdint.h>
#include <stdlib.h>
#define ts_builtin_sym_error ((TSSymbol)-1)
#define ts_builtin_sym_end 0
#define TREE_SITTER_SERIALIZATION_BUFFER_SIZE 1024
#ifndef TREE_SITTER_API_H_
typedef uint16_t TSStateId;
typedef uint16_t TSSymbol;
typedef uint16_t TSFieldId;
typedef struct TSLanguage TSLanguage;
typedef struct TSLanguageMetadata {
uint8_t major_version;
uint8_t minor_version;
uint8_t patch_version;
} TSLanguageMetadata;
#endif
typedef struct {
TSFieldId field_id;
uint8_t child_index;
bool inherited;
} TSFieldMapEntry;
// Used to index the field and supertype maps.
typedef struct {
uint16_t index;
uint16_t length;
} TSMapSlice;
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 *);
void (*log)(const TSLexer *, const char *, ...);
};
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 struct {
uint16_t lex_state;
uint16_t external_lex_state;
uint16_t reserved_word_set_id;
} TSLexerMode;
typedef union {
TSParseAction action;
struct {
uint8_t count;
bool reusable;
} entry;
} TSParseActionEntry;
typedef struct {
int32_t start;
int32_t end;
} TSCharacterRange;
struct TSLanguage {
uint32_t abi_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 TSMapSlice *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 TSLexerMode *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;
const char *name;
const TSSymbol *reserved_words;
uint16_t max_reserved_word_set_size;
uint32_t supertype_count;
const TSSymbol *supertype_symbols;
const TSMapSlice *supertype_map_slices;
const TSSymbol *supertype_map_entries;
TSLanguageMetadata metadata;
};
static inline bool set_contains(const TSCharacterRange *ranges, uint32_t len, int32_t lookahead) {
uint32_t index = 0;
uint32_t size = len - index;
while (size > 1) {
uint32_t half_size = size / 2;
uint32_t mid_index = index + half_size;
const TSCharacterRange *range = &ranges[mid_index];
if (lookahead >= range->start && lookahead <= range->end) {
return true;
} else if (lookahead > range->end) {
index = mid_index;
}
size -= half_size;
}
const TSCharacterRange *range = &ranges[index];
return (lookahead >= range->start && lookahead <= range->end);
}
/*
* Lexer Macros
*/
#ifdef _MSC_VER
#define UNUSED __pragma(warning(suppress : 4101))
#else
#define UNUSED __attribute__((unused))
#endif
#define START_LEXER() \
bool result = false; \
bool skip = false; \
UNUSED \
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 ADVANCE_MAP(...) \
{ \
static const uint16_t map[] = { __VA_ARGS__ }; \
for (uint32_t i = 0; i < sizeof(map) / sizeof(map[0]); i += 2) { \
if (map[i] == lookahead) { \
state = map[i + 1]; \
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_name, children, precedence, prod_id) \
{{ \
.reduce = { \
.type = TSParseActionTypeReduce, \
.symbol = symbol_name, \
.child_count = children, \
.dynamic_precedence = precedence, \
.production_id = prod_id \
}, \
}}
#define RECOVER() \
{{ \
.type = TSParseActionTypeRecover \
}}
#define ACCEPT_INPUT() \
{{ \
.type = TSParseActionTypeAccept \
}}
#ifdef __cplusplus
}
#endif
#endif // TREE_SITTER_PARSER_H_

39
tree-sitter.json Normal file
View File

@@ -0,0 +1,39 @@
{
"$schema": "https://tree-sitter.github.io/tree-sitter/assets/schemas/config.schema.json",
"grammars": [
{
"name": "newt",
"camelcase": "Newt",
"title": "Newt",
"scope": "source.newt",
"file-types": [
"newt"
],
"injection-regex": "^newt$",
"class-name": "TreeSitterNewt"
}
],
"metadata": {
"version": "0.1.0",
"license": "MIT",
"description": "Newt grammar for tree-sitter",
"authors": [
{
"name": "Steve Dunham",
"email": "dunhamsteve@gmail.com"
}
],
"links": {
"repository": "https://github.com/dunhamsteve/tree-sitter-newt"
}
},
"bindings": {
"c": true,
"go": true,
"node": true,
"python": true,
"rust": true,
"swift": true,
"zig": false
}
}