Html support

Cargo.toml

@@ -10,7 +10,7 @@ members = [
   "crates/auth",
   "crates/externals",
   "crates/wasm-bindings",
-  "crates/marzano_messenger", "crates/cli_bin",
+  "crates/marzano_messenger", "crates/cli_bin", "crates/test_html_grammar",
 ]
 exclude = [
   "resources",

crates/core/src/test.rs

@@ -12816,6 +12816,47 @@ fn css_property_value() {
     .unwrap();
 }
 
+#[test]
+fn html_match_element() {
+    run_test_match(TestArg {
+        pattern: r#"
+        |language html
+        |
+        |contains `<Hello attr="foo"></$name>`
+        |"#
+        .trim_margin()
+        .unwrap(),
+        source: r#"<Hello attr="foo"></Hello>"#
+        .to_owned(),
+    })
+    .unwrap();
+}
+
+#[test]
+fn html_prefer_self_closing_tags() {
+    run_test_expected(TestArgExpected {
+        pattern: r#"
+            |language html
+            |
+            |`<$name $props>$body</$name>` => `<$name $props />` where $body <: .
+            |"#
+        .trim_margin()
+        .unwrap(),
+        source: r#"
+            |<Hello attr="foo"></Hello>
+            |"#
+        .trim_margin()
+        .unwrap(),
+        expected: r#"
+            |<Hello attr="foo" />
+            |"#
+        .trim_margin()
+        .unwrap(),
+    })
+    .unwrap();
+}
+
+
 #[test]
 fn json_empty_string_should_not_match_everything() {
     run_test_no_match(TestArg {

crates/language/src/html.rs

@@ -61,3 +61,40 @@ impl Language for Html {
         self.metavariable_sort
     }
 }
+
+
+
+
+#[cfg(test)]
+mod tests {
+    use marzano_util::print_node::print_node;
+
+    use crate::language::nodes_from_indices;
+
+    use super::*;
+
+    #[test]
+    fn import_variable() {
+        let snippet = r#"<Hello attr="foo"></Hello>"#;
+        let lang = Html::new(None);
+        let mut parser = tree_sitter::Parser::new().unwrap();
+        parser.set_language(lang.get_ts_language()).unwrap();
+        let snippets = lang.parse_snippet_contexts(snippet);
+        let nodes = nodes_from_indices(&snippets);
+        assert!(!nodes.is_empty());
+        print_node(&nodes[0].node);
+    }
+
+    #[test]
+    fn print_sexp() {
+        let code = r#"<Hello attr="foo"></Hello>"#;
+        let mut parser = tree_sitter::Parser::new().unwrap();
+        let lang = tree_sitter_html::language().into();
+        // let lang = Html::new(None);
+        parser.set_language(&lang).unwrap();
+        let tree = parser.parse(code, None).unwrap().unwrap();
+        let root = tree.root_node();
+        let sexp = root.to_sexp();
+        println!("{sexp}");
+    }
+}

crates/test_html_grammar/Cargo.toml

@@ -0,0 +1,11 @@
+[package]
+name = "test_html_grammar"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+tree-sitter = { path = "../../vendor/tree-sitter-facade", package = "tree-sitter-facade-sg" }
+# tree-sitter-html = "0.20.0"
+tree-sitter-html = { path = "../../resources/language-metavariables/tree-sitter-html" }

crates/test_html_grammar/src/main.rs

@@ -0,0 +1,11 @@
+
+
+fn main() {
+    let code = r#"<Hello attr="foo"></Hello>"#;
+    let mut parser = tree_sitter::Parser::new().unwrap();
+    parser.set_language(&tree_sitter_html::language().into()).unwrap();
+    let tree = parser.parse(code, None).unwrap().unwrap();
+    let root = tree.root_node();
+    let sexp = root.to_sexp();
+    println!("{sexp}");
+}

resources/edit_grammars.mjs

@@ -121,10 +121,6 @@ async function rsyncGrammars(language) {
     ? `${LANGUAGE_METAVARIABLES}/${treeSitterLang}`
     : LANGUAGE_METAVARIABLES;
 
-  if (languagesWithoutMetaVariables.includes(language)) {
-    return;
-  }
-
   await fs.rmdir(mvDir, { recursive: true });
   await fs.mkdir(mvDir, { recursive: true });
 

resources/language-metavariables/tree-sitter-html/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "tree-sitter-html"
 description = "HTML grammar for tree-sitter"
-version = "0.20.0"
+version = "0.20.2"
 authors = [
 	"Max Brunsfeld <[email protected]>",
 	"Amaan Qureshi <[email protected]>",

resources/language-metavariables/tree-sitter-html/Makefile

@@ -1,4 +1,4 @@
-VERSION := 0.20.0
+VERSION := 0.20.2
 
 # Repository
 SRC_DIR := src

resources/language-metavariables/tree-sitter-html/README.md

@@ -1,9 +1,19 @@
 # tree-sitter-html
 
-[![build](https://github.com/tree-sitter/tree-sitter-html/actions/workflows/ci.yml/badge.svg)](https://github.com/tree-sitter/tree-sitter-html/actions/workflows/ci.yml)
+[![CI][ci]](https://github.com/tree-sitter/tree-sitter-html/actions/workflows/ci.yml)
+[![discord][discord]](https://discord.gg/w7nTvsVJhm)
+[![matrix][matrix]](https://matrix.to/#/#tree-sitter-chat:matrix.org)
+[![crates][crates]](https://crates.io/crates/tree-sitter-html)
+[![npm][npm]](https://www.npmjs.com/package/tree-sitter-html)
 
 HTML grammar for [tree-sitter](https://github.com/tree-sitter/tree-sitter).
 
 References
 
-* [The HTML5 Spec](https://www.w3.org/TR/html5/syntax.html)
+- [The HTML5 Spec](https://www.w3.org/TR/html5/syntax.html)
+
+[ci]: https://img.shields.io/github/actions/workflow/status/tree-sitter/tree-sitter-html/ci.yml?logo=github&label=CI
+[discord]: https://img.shields.io/discord/1063097320771698699?logo=discord&label=discord
+[matrix]: https://img.shields.io/matrix/tree-sitter-chat%3Amatrix.org?logo=matrix&label=matrix
+[npm]: https://img.shields.io/npm/v/tree-sitter-html?logo=npm
+[crates]: https://img.shields.io/crates/v/tree-sitter-html?logo=rust

resources/language-metavariables/tree-sitter-html/bindings/rust/README.md

@@ -9,7 +9,7 @@ way.)
 ```toml
 [dependencies]
 tree-sitter = "0.20.10"
-tree-sitter-html = "0.20.0"
+tree-sitter-html = "0.20"
 ```
 
 Typically, you will use the [language][language func] function to add this

resources/language-metavariables/tree-sitter-html/grammar.js

@@ -31,7 +31,7 @@ module.exports = grammar({
   ],
 
   rules: {
-    fragment: $ => repeat($._node),
+    document: $ => repeat($._node),
 
     doctype: $ => seq(
       '<!',
@@ -131,7 +131,7 @@ module.exports = grammar({
     // An entity can be named, numeric (decimal), or numeric (hexacecimal). The
     // longest entity name is 29 characters long, and the HTML spec says that
     // no more will ever be added.
-    entity: _ => /&(#([xX][0-9a-fA-F]{1,6}|[0-9]{1,5})|[A-Za-z]{1,30});/,
+    entity: _ => /&(#([xX][0-9a-fA-F]{1,6}|[0-9]{1,5})|[A-Za-z]{1,30});?/,
 
     quoted_attribute_value: $ => choice(
       seq('\'', optional(alias(/[^']+/, $.attribute_value)), '\''),

resources/language-metavariables/tree-sitter-html/package.json

@@ -1,6 +1,6 @@
 {
   "name": "tree-sitter-html",
-  "version": "0.20.0",
+  "version": "0.20.2",
   "description": "HTML grammar for tree-sitter",
   "main": "bindings/node",
   "keywords": [
@@ -37,7 +37,7 @@
   },
   "tree-sitter": [
     {
-      "scope": "text.html.basic",
+      "scope": "source.html",
       "file-types": [
         "html"
       ],
@@ -47,6 +47,9 @@
       ],
       "injections": [
         "queries/injections.scm"
+      ],
+      "external-files": [
+        "src/tag.h"
       ]
     }
   ]

resources/language-metavariables/tree-sitter-html/src/grammar.json

@@ -1,7 +1,7 @@
 {
   "name": "html",
   "rules": {
-    "fragment": {
+    "document": {
       "type": "REPEAT",
       "content": {
         "type": "SYMBOL",
@@ -373,7 +373,7 @@
     },
     "entity": {
       "type": "PATTERN",
-      "value": "&(#([xX][0-9a-fA-F]{1,6}|[0-9]{1,5})|[A-Za-z]{1,30});"
+      "value": "&(#([xX][0-9a-fA-F]{1,6}|[0-9]{1,5})|[A-Za-z]{1,30});?"
     },
     "quoted_attribute_value": {
       "type": "CHOICE",

resources/language-metavariables/tree-sitter-html/src/node-types.json

@@ -27,6 +27,45 @@
     "named": true,
     "fields": {}
   },
+  {
+    "type": "document",
+    "named": true,
+    "fields": {},
+    "children": {
+      "multiple": true,
+      "required": false,
+      "types": [
+        {
+          "type": "doctype",
+          "named": true
+        },
+        {
+          "type": "element",
+          "named": true
+        },
+        {
+          "type": "entity",
+          "named": true
+        },
+        {
+          "type": "erroneous_end_tag",
+          "named": true
+        },
+        {
+          "type": "script_element",
+          "named": true
+        },
+        {
+          "type": "style_element",
+          "named": true
+        },
+        {
+          "type": "text",
+          "named": true
+        }
+      ]
+    }
+  },
   {
     "type": "element",
     "named": true,
@@ -108,45 +147,6 @@
       ]
     }
   },
-  {
-    "type": "fragment",
-    "named": true,
-    "fields": {},
-    "children": {
-      "multiple": true,
-      "required": false,
-      "types": [
-        {
-          "type": "doctype",
-          "named": true
-        },
-        {
-          "type": "element",
-          "named": true
-        },
-        {
-          "type": "entity",
-          "named": true
-        },
-        {
-          "type": "erroneous_end_tag",
-          "named": true
-        },
-        {
-          "type": "script_element",
-          "named": true
-        },
-        {
-          "type": "style_element",
-          "named": true
-        },
-        {
-          "type": "text",
-          "named": true
-        }
-      ]
-    }
-  },
   {
     "type": "quoted_attribute_value",
     "named": true,