feat: Separated out the TreeSitterParser to own crate for portability

Cargo.lock

@@ -550,6 +550,7 @@ dependencies = [
  "ariadne",
  "clap",
  "harper-core",
+ "harper-tree-sitter",
 ]
 
 [[package]]
@@ -581,6 +582,7 @@ dependencies = [
  "dirs 5.0.1",
  "futures",
  "harper-core",
+ "harper-tree-sitter",
  "itertools",
  "once_cell",
  "open",
@@ -591,19 +593,6 @@ dependencies = [
  "tower-lsp",
  "tracing",
  "tracing-subscriber",
- "tree-sitter",
- "tree-sitter-c",
- "tree-sitter-c-sharp",
- "tree-sitter-cpp",
- "tree-sitter-go",
- "tree-sitter-javascript",
- "tree-sitter-lua",
- "tree-sitter-python",
- "tree-sitter-ruby",
- "tree-sitter-rust",
- "tree-sitter-swift",
- "tree-sitter-toml",
- "tree-sitter-typescript",
  "unicode-width",
 ]
 
@@ -620,6 +609,26 @@ dependencies = [
  "tracing-subscriber",
 ]
 
+[[package]]
+name = "harper-tree-sitter"
+version = "0.8.0"
+dependencies = [
+ "harper-core",
+ "tree-sitter",
+ "tree-sitter-c",
+ "tree-sitter-c-sharp",
+ "tree-sitter-cpp",
+ "tree-sitter-go",
+ "tree-sitter-javascript",
+ "tree-sitter-lua",
+ "tree-sitter-python",
+ "tree-sitter-ruby",
+ "tree-sitter-rust",
+ "tree-sitter-swift",
+ "tree-sitter-toml",
+ "tree-sitter-typescript",
+]
+
 [[package]]
 name = "harper-wasm"
 version = "0.1.0"

Cargo.toml

@@ -1,5 +1,5 @@
 [workspace]
-members = [ "harper-cli", "harper-core", "harper-ls", "harper-serve", "harper-wasm"]
+members = [ "harper-cli", "harper-core", "harper-ls", "harper-serve", "harper-tree-sitter", "harper-wasm"]
 resolver = "2"
 
 [profile.release]

harper-cli/Cargo.toml

@@ -11,3 +11,4 @@ anyhow = "1.0.83"
 ariadne = "0.4.1"
 clap = { version = "4.5.4", features = ["derive"] }
 harper-core = { path = "../harper-core", version = "0.8.0" }
+harper-tree-sitter = { path = "../harper-tree-sitter", version = "0.8.0" }

harper-cli/README.md

@@ -5,7 +5,7 @@
 `harper-cli` is a small, experimental frontend for Harper.
 It can be used in any situation where you might need to check a large number of files automatically (like in continuous integration).
 
-Right now it is quite feature barren, mainly because the use-case has not been defined yet.
+Right now it is quite feature barren, mainly because an external use-case has not been defined yet.
 If you have any thoughts, feel free to reach out.
 
 ## Possible Future Features

harper-cli/src/main.rs

@@ -1,20 +1,32 @@
-use std::path::PathBuf;
+use std::path::{Path, PathBuf};
 
+use anyhow::format_err;
 use ariadne::{Color, Label, Report, ReportKind, Source};
 use clap::Parser;
 use harper_core::{remove_overlaps, Document, FullDictionary, LintGroup, LintGroupConfig, Linter};
+use harper_tree_sitter::TreeSitterParser;
 
 #[derive(Debug, Parser)]
 struct Args {
-    /// The Markdown file you wish to grammar check.
-    file: PathBuf
+    /// The file you wish to grammar check.
+    file: PathBuf,
+    /// Whether to merely print out the number of errors encountered, without
+    /// further details.
+    #[arg(short, long)]
+    count: bool
 }
 
 fn main() -> anyhow::Result<()> {
     let args = Args::parse();
 
     let source = std::fs::read_to_string(&args.file)?;
-    let doc = Document::new_markdown(&source);
+
+    let parser = TreeSitterParser::new_from_language_id(
+        filename_to_filetype(&args.file).ok_or(format_err!("Could not detect filetype."))?
+    )
+    .ok_or(format_err!("Could not detect language ID."))?;
+
+    let doc = Document::new(&source, Box::new(parser));
 
     let mut linter = LintGroup::new(
         LintGroupConfig::default(),
@@ -22,6 +34,11 @@ fn main() -> anyhow::Result<()> {
     );
     let mut lints = linter.lint(&doc);
 
+    if args.count {
+        println!("{}", lints.len());
+        return Ok(());
+    }
+
     if lints.is_empty() {
         println!("No lints found");
         return Ok(());
@@ -52,3 +69,28 @@ fn main() -> anyhow::Result<()> {
 
     std::process::exit(1);
 }
+
+/// Convert a provided path to a corresponding Language Server Protocol file
+/// type.
+///
+/// Note to contributors: try to keep this in sync with
+/// [`TreeSitterParser::new_from_language_id`]
+fn filename_to_filetype(path: &Path) -> Option<&'static str> {
+    Some(match path.extension()?.to_str()? {
+        "rs" => "rust",
+        "ts" => "typescript",
+        "tsx" => "typescriptreact",
+        "js" => "javascript",
+        "jsx" => "javascriptreact",
+        "go" => "go",
+        "c" => "c",
+        "cpp" => "cpp",
+        "h" => "cpp",
+        "rb" => "ruby",
+        "swift" => "swift",
+        "cs" => "csharp",
+        "toml" => "toml",
+        "lua" => "lua",
+        _ => return None
+    })
+}

harper-core/src/linting/an_a.rs

@@ -67,8 +67,6 @@ fn to_lower_word(word: &[char]) -> Cow<'_, [char]> {
 fn starts_with_vowel(word: &[char]) -> bool {
     let is_likely_initialism = word.iter().all(|c| c.is_uppercase());
 
-    dbg!(word, is_likely_initialism);
-
     if is_likely_initialism && !word.is_empty() {
         return matches!(
             word[0],

harper-core/src/linting/repeated_words.rs

@@ -27,7 +27,7 @@ impl RepeatedWords {
 
         add_set!(
             "the", "be", "to", "of", "and", "a", "in", "that", "have", "I", "it", "for", "not",
-            "on", "with", "he", "as", "you", "do", "at", "this", "but", "his", "by", "from",
+            "on", "with", "he", "as", "you", "do", "at", "this", "is", "but", "his", "by", "from",
             "they", "we", "say", "her", "she", "or", "an", "will", "my", "one", "all", "would",
             "there", "their", "what", "so", "up", "out", "if", "about", "who", "get", "which",
             "go", "me", "when", "make", "can", "like", "time", "no", "just", "him", "know", "take",

harper-ls/Cargo.toml

@@ -9,23 +9,11 @@ repository = "https://github.com/elijah-potter/harper"
 
 [dependencies]
 harper-core = { path = "../harper-core", version = "0.8.0" }
+harper-tree-sitter = { path = "../harper-tree-sitter", version = "0.8.0" }
 tower-lsp = "0.20.0"
 tokio = { version = "1.36.0", features = ["fs", "rt", "rt-multi-thread", "macros", "io-std", "io-util", "net"] }
 clap = { version = "4.5.1", features = ["derive"] }
 once_cell = "1.19.0"
-tree-sitter = "0.20.10"
-tree-sitter-rust = "0.20.4"
-tree-sitter-typescript = "0.20.3"
-tree-sitter-python = "0.20.4"
-tree-sitter-javascript = "0.20.1"
-tree-sitter-go = "0.20.0"
-tree-sitter-c = "0.20.7"
-tree-sitter-cpp = "0.20.5"
-tree-sitter-ruby = "0.20.1"
-tree-sitter-swift = "=0.4.0"
-tree-sitter-c-sharp = "0.20.0"
-tree-sitter-toml = "0.20.0"
-tree-sitter-lua = "0.0.19"
 dirs = "5.0.1"
 anyhow = "1.0.80"
 serde_json = "1.0.114"

harper-ls/src/backend.rs

@@ -13,6 +13,7 @@ use harper_core::{
     Token,
     TokenKind
 };
+use harper_tree_sitter::TreeSitterParser;
 use serde_json::Value;
 use tokio::sync::{Mutex, RwLock};
 use tower_lsp::jsonrpc::Result;
@@ -52,7 +53,6 @@ use crate::diagnostics::{lint_to_code_actions, lints_to_diagnostics};
 use crate::dictionary_io::{load_dict, save_dict};
 use crate::git_commit_parser::GitCommitParser;
 use crate::pos_conv::range_to_span;
-use crate::tree_sitter_parser::TreeSitterParser;
 
 #[derive(Default)]
 struct DocumentState {

harper-ls/src/main.rs

@@ -3,13 +3,11 @@ use std::io::stderr;
 use config::Config;
 use tokio::net::TcpListener;
 mod backend;
-mod comment_parsers;
 mod config;
 mod diagnostics;
 mod dictionary_io;
 mod git_commit_parser;
 mod pos_conv;
-mod tree_sitter_parser;
 
 use backend::Backend;
 use clap::Parser;

harper-tree-sitter/Cargo.toml

@@ -0,0 +1,20 @@
+[package]
+name = "harper-tree-sitter"
+version = "0.8.0"
+edition = "2021"
+
+[dependencies]
+harper-core = { path = "../harper-core", version = "0.8.0" }
+tree-sitter = "0.20.10"
+tree-sitter-rust = "0.20.4"
+tree-sitter-typescript = "0.20.3"
+tree-sitter-python = "0.20.4"
+tree-sitter-javascript = "0.20.1"
+tree-sitter-go = "0.20.0"
+tree-sitter-c = "0.20.7"
+tree-sitter-cpp = "0.20.5"
+tree-sitter-ruby = "0.20.1"
+tree-sitter-swift = "=0.4.0"
+tree-sitter-c-sharp = "0.20.0"
+tree-sitter-toml = "0.20.0"
+tree-sitter-lua = "0.0.19"

harper-tree-sitter/README.md

@@ -0,0 +1,3 @@
+# `harper-tree-sitter`
+
+This crate is a wrapper around `tree-sitter` that allows Harper to parse the comments of a wide variety of programming languages.

harper-tree-sitter/src/lib.rs

@@ -0,0 +1,4 @@
+mod comment_parsers;
+mod tree_sitter_parser;
+
+pub use tree_sitter_parser::TreeSitterParser;