tree_stump 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 91b315adc731ea115495d57d4b6cbc0015ed57bbc57da2efc912db78546f466d
+  data.tar.gz: 496323196882dc02b34b4e77e7fc84bf91d4fea0d8f52545e843f13ca2a47ca2
+SHA512:
+  metadata.gz: 21a4ad35fb28d48167ec9196832c8fb4bec7d941adf56666043818db6cf5423fc21d9a14ca54adb6a584e5700bc7305d4f6b04146c6116853a627c247e22bc20
+  data.tar.gz: 15198290a857e5ca222da0c5d570c0ad753cf53fba444b267850742bd1235c5df7b87c02cb83e20d432afdbeab788547332b2e1cbfb4afdbc85944eeb16a2bf3

data/.rspec

@@ -0,0 +1 @@
+--require spec_helper

data/Cargo.lock

@@ -0,0 +1,368 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 3
+
+[[package]]
+name = "aho-corasick"
+version = "1.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e60d3430d3a69478ad0993f19238d2df97c507009a52b3c10addcd7f6bcb916"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "bindgen"
+version = "0.69.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a00dc851838a2120612785d195287475a3ac45514741da670b735818822129a0"
+dependencies = [
+ "bitflags",
+ "cexpr",
+ "clang-sys",
+ "itertools",
+ "lazy_static",
+ "lazycell",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "rustc-hash",
+ "shlex",
+ "syn",
+]
+
+[[package]]
+name = "bitflags"
+version = "2.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b048fb63fd8b5923fc5aa7b340d8e156aec7ec02f0c78fa8a6ddc2613f6f71de"
+
+[[package]]
+name = "cc"
+version = "1.1.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "57b6a275aa2903740dc87da01c62040406b8812552e97129a63ea8850a17c6e6"
+dependencies = [
+ "shlex",
+]
+
+[[package]]
+name = "cexpr"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6fac387a98bb7c37292057cffc56d62ecb629900026402633ae9160df93a8766"
+dependencies = [
+ "nom",
+]
+
+[[package]]
+name = "cfg-if"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd"
+
+[[package]]
+name = "clang-sys"
+version = "1.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b023947811758c97c59bf9d1c188fd619ad4718dcaa767947df1cadb14f39f4"
+dependencies = [
+ "glob",
+ "libc",
+ "libloading",
+]
+
+[[package]]
+name = "either"
+version = "1.13.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "60b1af1c220855b6ceac025d3f6ecdd2b7c4894bfe9cd9bda4fbb4bc7c0d4cf0"
+
+[[package]]
+name = "glob"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
+
+[[package]]
+name = "itertools"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba291022dbbd398a455acf126c1e341954079855bc60dfdda641363bd6922569"
+dependencies = [
+ "either",
+]
+
+[[package]]
+name = "lazy_static"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
+
+[[package]]
+name = "lazycell"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "830d08ce1d1d941e6b30645f1a0eb5643013d835ce3779a5fc208261dbe10f55"
+
+[[package]]
+name = "libc"
+version = "0.2.158"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d8adc4bb1803a324070e64a98ae98f38934d91957a99cfb3a43dcbc01bc56439"
+
+[[package]]
+name = "libloading"
+version = "0.8.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4979f22fdb869068da03c9f7528f8297c6fd2606bc3a4affe42e6a823fdb8da4"
+dependencies = [
+ "cfg-if",
+ "windows-targets",
+]
+
+[[package]]
+name = "magnus"
+version = "0.7.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3d87ae53030f3a22e83879e666cb94e58a7bdf31706878a0ba48752994146dab"
+dependencies = [
+ "magnus-macros",
+ "rb-sys",
+ "rb-sys-env",
+ "seq-macro",
+]
+
+[[package]]
+name = "magnus-macros"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5968c820e2960565f647819f5928a42d6e874551cab9d88d75e3e0660d7f71e3"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "memchr"
+version = "2.7.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "78ca9ab1a0babb1e7d5695e3530886289c18cf2f87ec19a575a0abdce112e3a3"
+
+[[package]]
+name = "minimal-lexical"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
+
+[[package]]
+name = "nom"
+version = "7.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d273983c5a657a70a3e8f2a01329822f3b8c8172b73826411a55751e404a0a4a"
+dependencies = [
+ "memchr",
+ "minimal-lexical",
+]
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.86"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5e719e8df665df0d1c8fbfd238015744736151d4445ec0836b8e628aae103b77"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.37"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b5b9d34b8991d19d98081b46eacdd8eb58c6f2b201139f7c5f643cc155a633af"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "rb-sys"
+version = "0.9.102"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "df4dec4b1d304c3b308a2cd86b1216ea45dd4361f4e9fa056f108332d0a450c1"
+dependencies = [
+ "rb-sys-build",
+]
+
+[[package]]
+name = "rb-sys-build"
+version = "0.9.102"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1d71de3e29d174b8fb17b5d4470f27d7aa2605f8a9d05fda0d3aeff30e05a570"
+dependencies = [
+ "bindgen",
+ "lazy_static",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "shell-words",
+ "syn",
+]
+
+[[package]]
+name = "rb-sys-env"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a35802679f07360454b418a5d1735c89716bde01d35b1560fc953c1415a0b3bb"
+
+[[package]]
+name = "regex"
+version = "1.10.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4219d74c6b67a3654a9fbebc4b419e22126d13d2f3c4a07ee0cb61ff79a79619"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "38caf58cc5ef2fed281f89292ef23f6365465ed9a41b7a7754eb4e26496c92df"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7a66a03ae7c801facd77a29370b4faec201768915ac14a721ba36f20bc9c209b"
+
+[[package]]
+name = "rustc-hash"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
+
+[[package]]
+name = "seq-macro"
+version = "0.3.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a3f0bf26fd526d2a95683cd0f87bf103b8539e2ca1ef48ce002d67aad59aa0b4"
+
+[[package]]
+name = "shell-words"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24188a676b6ae68c3b2cb3a01be17fbf7240ce009799bb56d5b1409051e78fde"
+
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+
+[[package]]
+name = "syn"
+version = "2.0.77"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9f35bcdf61fd8e7be6caf75f429fdca8beb3ed76584befb503b1569faee373ed"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "tree-sitter"
+version = "0.22.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "df7cc499ceadd4dcdf7ec6d4cbc34ece92c3fa07821e287aedecd4416c516dca"
+dependencies = [
+ "cc",
+ "regex",
+]
+
+[[package]]
+name = "tree_stump"
+version = "0.1.0"
+dependencies = [
+ "libloading",
+ "magnus",
+ "tree-sitter",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.12"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b"
+
+[[package]]
+name = "windows-targets"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
+dependencies = [
+ "windows_aarch64_gnullvm",
+ "windows_aarch64_msvc",
+ "windows_i686_gnu",
+ "windows_i686_gnullvm",
+ "windows_i686_msvc",
+ "windows_x86_64_gnu",
+ "windows_x86_64_gnullvm",
+ "windows_x86_64_msvc",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
+
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"

data/Cargo.toml

@@ -0,0 +1,7 @@
+# This Cargo.toml is here to let externals tools (IDEs, etc.) know that this is
+# a Rust project. Your extensions dependencies should be added to the Cargo.toml
+# in the ext/ directory.
+
+[workspace]
+members = ["./ext/tree_stump"]
+resolver = "2"

data/README.md

@@ -0,0 +1,61 @@
+# TreeStump
+[![RSpec](https://github.com/joker1007/tree_stump/actions/workflows/rspec.yml/badge.svg)](https://github.com/joker1007/tree_stump/actions/workflows/rspec.yml)
+
+[tree-sitter](https://github.com/tree-sitter/tree-sitter) binding for Ruby written by Rust.
+
+## Installation
+
+Install the gem and add to the application's Gemfile by executing:
+
+    $ bundle add tree_stump
+
+If bundler is not being used to manage dependencies, install the gem by executing:
+
+    $ gem install tree_stump
+
+## Usage
+
+```ruby
+require "tree_stump"
+require "rouge"
+
+TreeStump.register_lang("ruby", "./libtree-sitter-ruby.so")
+
+parser = TreeStump::Parser.new
+parser.set_language("ruby")
+
+source = File.read("./sample.rb")
+
+formatter = Rouge::Formatters::Terminal256.new
+lexer = Rouge::Lexers::Ruby.new
+
+puts "== Source =="
+puts formatter.format(lexer.lex(source))
+
+puts "\n"
+
+puts "==  Tree  =="
+tree = parser.parse(source)
+
+puts tree.root_node.to_sexp
+```
+
+```
+(program (class name: (constant) superclass: (superclass (constant)) body: (body_statement (call method: (identifier) arguments: (argument_list (simple_symbol) (pair key: (hash_key_symbol) value: (true)))) (singleton_method object: (self) name: (identifier) parameters: (method_parameters (identifier)) body: (body_statement (call receiver: (constant) method: (identifier) arguments: (argument_list (pair key: (hash_key_symbol) value: (identifier)))))))) (call receiver: (constant) method: (identifier) arguments: (argument_list (string (string_content)))))
+```
+
+## Development
+
+### Requirements
+
+- Rust Toolchain
+- tree-sitter-ruby
+
+1. Download source of tree-sitter-ruby from [GitHub Repository](https://github.com/tree-sitter/tree-sitter-ruby).
+1. Extract tree-sitter-ruby source
+1. mv tree-sitter-ruby-v{version_num} to tree_stump/tree-sitter-ruby
+1. Execute `make` in tree-sitter-ruby directory
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/joker1007/tree_stump.

data/Rakefile

@@ -0,0 +1,18 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
+require "rb_sys/extensiontask"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task build: :compile
+
+GEMSPEC = Gem::Specification.load("tree_stump.gemspec")
+
+RbSys::ExtensionTask.new("tree_stump", GEMSPEC) do |ext|
+  ext.lib_dir = "lib/tree_stump"
+end
+
+task spec: :compile
+task default: :spec

data/ext/tree_stump/Cargo.toml

@@ -0,0 +1,14 @@
+[package]
+name = "tree_stump"
+version = "0.1.0"
+edition = "2021"
+authors = ["joker1007 <kakyoin.hierophant@gmail.com>"]
+publish = false
+
+[lib]
+crate-type = ["cdylib"]
+
+[dependencies]
+magnus = { version = "0.7.1" }
+tree-sitter = "~0.22"
+libloading = "~0.8.4"

data/ext/tree_stump/extconf.rb

@@ -0,0 +1,6 @@
+# frozen_string_literal: true
+
+require "mkmf"
+require "rb_sys/mkmf"
+
+create_rust_makefile("tree_stump/tree_stump")

data/ext/tree_stump/src/data.rs

@@ -0,0 +1,103 @@
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash, PartialOrd, Ord)]
+#[magnus::wrap(class = "TreeStump::Point", free_immediately)]
+pub struct Point {
+    pub row: usize,
+    pub column: usize,
+}
+
+impl Point {
+    pub fn new(row: usize, column: usize) -> Self {
+        Self { row, column }
+    }
+
+    pub fn inspect(&self) -> String {
+        format!("#<Point({}, {})>", self.row, self.column)
+    }
+
+    pub fn to_s(&self) -> String {
+        format!("({}, {})", self.row, self.column)
+    }
+
+    pub fn get_row(&self) -> usize {
+        self.row
+    }
+
+    pub fn get_column(&self) -> usize {
+        self.column
+    }
+
+    pub fn into_raw(self) -> tree_sitter::Point {
+        tree_sitter::Point {
+            row: self.row,
+            column: self.column,
+        }
+    }
+}
+
+impl From<tree_sitter::Point> for Point {
+    fn from(point: tree_sitter::Point) -> Self {
+        Self {
+            row: point.row,
+            column: point.column,
+        }
+    }
+}
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash, PartialOrd, Ord)]
+#[magnus::wrap(class = "TreeStump::Range", free_immediately)]
+pub struct Range {
+    pub start_byte: usize,
+    pub end_byte: usize,
+    pub start_point: Point,
+    pub end_point: Point,
+}
+
+impl Range {
+    pub fn new(start_byte: usize, end_byte: usize, start_point: &Point, end_point: &Point) -> Self {
+        let start_point = start_point.to_owned();
+        let end_point = end_point.to_owned();
+        Self {
+            start_byte,
+            end_byte,
+            start_point,
+            end_point,
+        }
+    }
+
+    pub fn get_start_byte(&self) -> usize {
+        self.start_byte
+    }
+
+    pub fn get_end_byte(&self) -> usize {
+        self.end_byte
+    }
+
+    pub fn get_start_point(&self) -> Point {
+        self.start_point
+    }
+
+    pub fn get_end_point(&self) -> Point {
+        self.end_point
+    }
+
+    pub fn inspect(&self) -> String {
+        format!(
+            "#<Range({}, {}, {:?}, {:?})>",
+            self.start_byte, self.end_byte, self.start_point, self.end_point
+        )
+    }
+    pub fn to_s(&self) -> String {
+        format!("({}..{})", self.start_point.to_s(), self.end_point.to_s())
+    }
+}
+
+impl From<tree_sitter::Range> for Range {
+    fn from(range: tree_sitter::Range) -> Self {
+        Self {
+            start_byte: range.start_byte,
+            end_byte: range.end_byte,
+            start_point: range.start_point.into(),
+            end_point: range.end_point.into(),
+        }
+    }
+}

data/ext/tree_stump/src/language.rs

@@ -0,0 +1,74 @@
+use std::cell::RefCell;
+
+#[magnus::wrap(class = "TreeStump::LanguageRef", free_immediately, unsafe_generics)]
+pub struct LanguageRef<'a> {
+    pub raw_language_ref: tree_sitter::LanguageRef<'a>,
+}
+unsafe impl Send for LanguageRef<'_> {}
+
+impl<'a> LanguageRef<'a> {
+    pub fn version(&self) -> usize {
+        self.raw_language_ref.version()
+    }
+
+    pub fn node_kind_count(&self) -> usize {
+        self.raw_language_ref.node_kind_count()
+    }
+
+    pub fn parse_state_count(&self) -> usize {
+        self.raw_language_ref.parse_state_count()
+    }
+
+    pub fn node_kind_for_id(&self, id: u16) -> Option<&'static str> {
+        self.raw_language_ref.node_kind_for_id(id)
+    }
+
+    pub fn id_for_node_kind(&self, kind: String, named: bool) -> u16 {
+        self.raw_language_ref.id_for_node_kind(kind.as_str(), named)
+    }
+
+    pub fn node_kind_is_named(&self, id: u16) -> bool {
+        self.raw_language_ref.node_kind_is_named(id)
+    }
+
+    pub fn node_kind_is_visible(&self, id: u16) -> bool {
+        self.raw_language_ref.node_kind_is_visible(id)
+    }
+
+    pub fn field_name_for_id(&self, id: u16) -> Option<&'static str> {
+        self.raw_language_ref.field_name_for_id(id)
+    }
+
+    pub fn field_id_for_name(&self, name: String) -> Option<u16> {
+        self.raw_language_ref
+            .field_id_for_name(name.as_str())
+            .map(|id| id.into())
+    }
+
+    pub fn next_state(&self, state: u16, id: u16) -> u16 {
+        self.raw_language_ref.next_state(state, id)
+    }
+
+    pub fn lookahead_iterator(&self, state: u16) -> Option<LookaheadIterator> {
+        self.raw_language_ref
+            .lookahead_iterator(state)
+            .map(|raw_iterator| LookaheadIterator {
+                raw_iterator: RefCell::new(raw_iterator),
+            })
+    }
+}
+
+#[magnus::wrap(class = "TreeStump::LookaheadIterator")]
+pub struct LookaheadIterator {
+    raw_iterator: RefCell<tree_sitter::LookaheadIterator>,
+}
+
+impl LookaheadIterator {
+    pub fn next(&self) -> Option<u16> {
+        self.raw_iterator.borrow_mut().next()
+    }
+
+    pub fn current_symbol_name(&self) -> &'static str {
+        self.raw_iterator.borrow().current_symbol_name()
+    }
+}