feat: added initial HTML support

Cargo.lock

@@ -543,6 +543,16 @@ dependencies = [
  "unicode-width",
 ]
 
+[[package]]
+name = "harper-html"
+version = "0.8.8"
+dependencies = [
+ "harper-core",
+ "harper-tree-sitter",
+ "tree-sitter",
+ "tree-sitter-html",
+]
+
 [[package]]
 name = "harper-ls"
 version = "0.8.8"
@@ -553,6 +563,7 @@ dependencies = [
  "futures",
  "harper-comments",
  "harper-core",
+ "harper-html",
  "itertools 0.13.0",
  "once_cell",
  "open",
@@ -1437,6 +1448,16 @@ dependencies = [
  "tree-sitter",
 ]
 
+[[package]]
+name = "tree-sitter-html"
+version = "0.19.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "184e6b77953a354303dc87bf5fe36558c83569ce92606e7b382a0dc1b7443443"
+dependencies = [
+ "cc",
+ "tree-sitter",
+]
+
 [[package]]
 name = "tree-sitter-java"
 version = "0.20.2"

Cargo.toml

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

harper-comments/README.md

@@ -2,4 +2,4 @@
 
 This crate holds a number of functions, but it is primarily a wrapper around `tree-sitter` that allows Harper to locate the comments of a wide variety of programming languages.
 It also has purpose-built parsers for the structured comments of a number of languages, including Go.
-These additional parsers are avaiable through the `TreeSitterParser` and are enabled automatically through there.
+These additional parsers are available through the `CommentParser` and are enabled automatically through there.

harper-html/Cargo.toml

@@ -0,0 +1,14 @@
+[package]
+name = "harper-html"
+version = "0.8.8"
+edition = "2021"
+description = "The language checker for developers."
+license = "Apache-2.0"
+readme = "README.md"
+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" }
+tree-sitter-html = "0.19.0"
+tree-sitter = "0.20.10"

harper-html/src/lib.rs

@@ -0,0 +1,29 @@
+use harper_core::parsers::{self, Parser, PlainEnglish};
+use harper_core::Token;
+use harper_tree_sitter::TreeSitterMasker;
+use tree_sitter::Node;
+
+pub struct HtmlParser {
+    inner: parsers::Mask<TreeSitterMasker, PlainEnglish>
+}
+
+impl HtmlParser {
+    pub fn new() -> Self {
+        Self {
+            inner: parsers::Mask::new(
+                TreeSitterMasker::new(tree_sitter_html::language(), Self::node_condition),
+                PlainEnglish
+            )
+        }
+    }
+
+    fn node_condition(n: &Node) -> bool {
+        n.kind() == "text"
+    }
+}
+
+impl Parser for HtmlParser {
+    fn parse(&mut self, source: &[char]) -> Vec<Token> {
+        self.inner.parse(source)
+    }
+}

harper-ls/Cargo.toml

@@ -10,6 +10,7 @@ repository = "https://github.com/elijah-potter/harper"
 [dependencies]
 harper-core = { path = "../harper-core", version = "0.8.0", features = ["concurrent"] }
 harper-comments = { path = "../harper-comments", version = "0.8.0" }
+harper-html = { path = "../harper-html", 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"] }

harper-ls/src/backend.rs

@@ -14,6 +14,7 @@ use harper_core::{
     Token,
     TokenKind
 };
+use harper_html::HtmlParser;
 use serde_json::Value;
 use tokio::sync::{Mutex, RwLock};
 use tower_lsp::jsonrpc::Result;
@@ -260,6 +261,8 @@ impl Backend {
                 Document::new(text, Box::new(Markdown))
             } else if language_id == "gitcommit" {
                 Document::new(text, Box::new(GitCommitParser))
+            } else if language_id == "html" {
+                Document::new(text, Box::new(HtmlParser::new()))
             } else if language_id == "mail" {
                 Document::new(text, Box::new(PlainEnglish))
             } else {
@@ -372,7 +375,6 @@ impl LanguageServer for Backend {
                         save: Some(TextDocumentSyncSaveOptions::Supported(true))
                     }
                 )),
-
                 ..Default::default()
             }
         })