Merge branch 'helix-editor:master' into shebang-filetype

.gitmodules

@@ -134,3 +134,7 @@
 	path = helix-syntax/languages/tree-sitter-cmake
 	url = https://github.com/uyha/tree-sitter-cmake
 	shallow = true
+[submodule "helix-syntax/languages/tree-sitter-perl"]
+	path = helix-syntax/languages/tree-sitter-perl
+	url = https://github.com/ganezdragon/tree-sitter-perl
+	shallow = true

book/src/guides/adding_languages.md

@@ -2,13 +2,14 @@
 
 ## Submodules
 
-To add a new langauge, you should first add a tree-sitter submodule. To do this, you can run the command
+To add a new langauge, you should first add a tree-sitter submodule. To do this,
+you can run the command
 ```sh
-$ git submodule add -f <repository> helix-syntax/languages/tree-sitter-<name>
+git submodule add -f <repository> helix-syntax/languages/tree-sitter-<name>
 ```
 For example, to add tree-sitter-ocaml you would run
 ```sh
-$ git submodule add -f https://github.com/tree-sitter/tree-sitter-ocaml helix-syntax/languages/tree-sitter-ocaml
+git submodule add -f https://github.com/tree-sitter/tree-sitter-ocaml helix-syntax/languages/tree-sitter-ocaml
 ```
 Make sure the submodule is shallow by doing
 ```sh
@@ -19,15 +20,18 @@ or you can manually add `shallow = true` to `.gitmodules`.
 
 ## languages.toml
 
-Next, you need to add the language to the `languages.toml` found in the root of the repository; this `languages.toml` file is included at compilation time, and is distinct from the `language.toml` file in the user's [configuration directory](../configuration.md).
+Next, you need to add the language to the [`languages.toml`][languages.toml] found in the root of
+the repository; this `languages.toml` file is included at compilation time, and
+is distinct from the `language.toml` file in the user's [configuration
+directory](../configuration.md).
 
 These are the available keys and descriptions for the file.
 
 | Key           | Description                                                   |
 | ----          | -----------                                                   |
 | name          | The name of the language                                      |
 | scope         | A string like `source.js` that identifies the language. Currently, we strive to match the scope names used by popular TextMate grammars and by the Linguist library. Usually `source.<name>` or `text.<name>` in case of markup languages |
-| injection-regex | regex pattern that will be tested against a language name in order to determine whether this language should be used for a potential language injection site. [link](https://tree-sitter.github.io/tree-sitter/syntax-highlighting#language-injection) |
+| injection-regex | regex pattern that will be tested against a language name in order to determine whether this language should be used for a potential [language injection][treesitter-language-injection] site. |
 | file-types    | The filetypes of the language, for example `["yml", "yaml"]`  |
 | shebangs      | The interpreters from the shebang line, for example `["sh", "bash"]`  |
 | roots         | A set of marker files to look for when trying to find the workspace root. For example `Cargo.lock`, `yarn.lock` |
@@ -43,11 +47,14 @@ For a language to have syntax-highlighting and indentation among other things, y
 ## Common Issues
 
 - If you get errors when building after switching branches, you may have to remove or update tree-sitter submodules. You can update submodules by running
-```sh
-$ git submodule sync; git submodule update --init
-```
+    ```sh
+    git submodule sync; git submodule update --init
+    ```
 - Make sure to not use the `--remote` flag. To remove submodules look inside the `.gitmodules` and remove directories that are not present inside of it.
 
 - If a parser is segfaulting or you want to remove the parser, make sure to remove the submodule *and* the compiled parser in `runtime/grammar/<name>.so`
 
 - The indents query is `indents.toml`, *not* `indents.scm`. See [this](https://github.com/helix-editor/helix/issues/114) issue for more information.
+
+[treesitter-language-injection]: https://tree-sitter.github.io/tree-sitter/syntax-highlighting#language-injection
+[languages.toml]: https://github.com/helix-editor/helix/blob/master/languages.toml

book/src/guides/textobject.md

@@ -5,7 +5,7 @@ require an accompanying tree-sitter grammar and a `textobjects.scm` query file
 to work properly. Tree-sitter allows us to query the source code syntax tree
 and capture specific parts of it. The queries are written in a lisp dialect.
 More information on how to write queries can be found in the [official tree-sitter
-documentation](tree-sitter-queries).
+documentation][tree-sitter-queries].
 
 Query files should be placed in `runtime/queries/{language}/textobjects.scm`
 when contributing. Note that to test the query files locally you should put

book/src/usage.md

@@ -62,6 +62,7 @@ Currently supported: `word`, `surround`, `function`, `class`, `parameter`.
 | Key after `mi` or `ma` | Textobject selected      |
 | ---                    | ---                      |
 | `w`                    | Word                     |
+| `W`                    | WORD                     |
 | `(`, `[`, `'`, etc     | Specified surround pairs |
 | `f`                    | Function                 |
 | `c`                    | Class                    |

helix-core/src/comment.rs

@@ -63,7 +63,7 @@ pub fn toggle_line_comments(doc: &Rope, selection: &Selection, token: Option<&st
     let token = token.unwrap_or("//");
     let comment = Tendril::from(format!("{} ", token));
 
-    let mut lines: Vec<usize> = Vec::new();
+    let mut lines: Vec<usize> = Vec::with_capacity(selection.len());
 
     let mut min_next_line = 0;
     for selection in selection {

helix-core/src/lib.rs

@@ -103,25 +103,7 @@ pub fn cache_dir() -> std::path::PathBuf {
 pub fn merge_toml_values(left: toml::Value, right: toml::Value) -> toml::Value {
     use toml::Value;
 
-    fn get_name(v: &Value) -> Option<&str> {
-        v.get("name").and_then(Value::as_str)
-    }
-
     match (left, right) {
-        (Value::Array(mut left_items), Value::Array(right_items)) => {
-            left_items.reserve(right_items.len());
-            for rvalue in right_items {
-                let lvalue = get_name(&rvalue)
-                    .and_then(|rname| left_items.iter().position(|v| get_name(v) == Some(rname)))
-                    .map(|lpos| left_items.remove(lpos));
-                let mvalue = match lvalue {
-                    Some(lvalue) => merge_toml_values(lvalue, rvalue),
-                    None => rvalue,
-                };
-                left_items.push(mvalue);
-            }
-            Value::Array(left_items)
-        }
         (Value::Table(mut left_map), Value::Table(right_map)) => {
             for (rname, rvalue) in right_map {
                 match left_map.remove(&rname) {
@@ -149,36 +131,41 @@ mod merge_toml_tests {
     fn language_tomls() {
         use toml::Value;
 
-        const USER: &str = "
+        const USER: &str = r#"
         [[language]]
-        name = \"nix\"
-        test = \"bbb\"
-        indent = { tab-width = 4, unit = \"    \", test = \"aaa\" }
-        ";
+        name = "typescript"
+        test = "bbb"
+        indent = { tab-width = 4, unit = "    ", test = "aaa" }
+        language-server = { command = "deno", args = ["lsp"] }
+        "#;
 
         let base: Value = toml::from_slice(include_bytes!("../../languages.toml"))
             .expect("Couldn't parse built-in langauges config");
         let user: Value = toml::from_str(USER).unwrap();
 
         let merged = merge_toml_values(base, user);
         let languages = merged.get("language").unwrap().as_array().unwrap();
-        let nix = languages
+        let ts = languages
             .iter()
-            .find(|v| v.get("name").unwrap().as_str().unwrap() == "nix")
+            .find(|v| v.get("name").unwrap().as_str().unwrap() == "typescript")
             .unwrap();
-        let nix_indent = nix.get("indent").unwrap();
+        let ts_indent = ts.get("indent").unwrap();
 
         // We changed tab-width and unit in indent so check them if they are the new values
+        assert_eq!(ts_indent.get("tab-width").unwrap().as_integer().unwrap(), 4);
+        assert_eq!(ts_indent.get("unit").unwrap().as_str().unwrap(), "    ");
+        // We added a new keys, so check them
+        assert_eq!(ts.get("test").unwrap().as_str().unwrap(), "bbb");
+        assert_eq!(ts_indent.get("test").unwrap().as_str().unwrap(), "aaa");
         assert_eq!(
-            nix_indent.get("tab-width").unwrap().as_integer().unwrap(),
-            4
+            ts.get("language-server")
+                .unwrap()
+                .get("args")
+                .unwrap()
+                .as_array()
+                .unwrap(),
+            &vec![Value::String("lsp".into())],
         );
-        assert_eq!(nix_indent.get("unit").unwrap().as_str().unwrap(), "    ");
-        // We added a new keys, so check them
-        assert_eq!(nix.get("test").unwrap().as_str().unwrap(), "bbb");
-        assert_eq!(nix_indent.get("test").unwrap().as_str().unwrap(), "aaa");
-        // We didn't change comment-token so it should be same
-        assert_eq!(nix.get("comment-token").unwrap().as_str().unwrap(), "#");
     }
 }
 

helix-core/src/match_brackets.rs

@@ -1,6 +1,13 @@
 use crate::{Rope, Syntax};
 
-const PAIRS: &[(char, char)] = &[('(', ')'), ('{', '}'), ('[', ']'), ('<', '>')];
+const PAIRS: &[(char, char)] = &[
+    ('(', ')'),
+    ('{', '}'),
+    ('[', ']'),
+    ('<', '>'),
+    ('\'', '\''),
+    ('"', '"'),
+];
 // limit matching pairs to only ( ) { } [ ] < >
 
 #[must_use]

helix-core/src/textobject.rs

@@ -10,7 +10,7 @@ use crate::surround;
 use crate::syntax::LanguageConfiguration;
 use crate::Range;
 
-fn find_word_boundary(slice: RopeSlice, mut pos: usize, direction: Direction) -> usize {
+fn find_word_boundary(slice: RopeSlice, mut pos: usize, direction: Direction, long: bool) -> usize {
     use CharCategory::{Eol, Whitespace};
 
     let iter = match direction {
@@ -33,7 +33,7 @@ fn find_word_boundary(slice: RopeSlice, mut pos: usize, direction: Direction) ->
         match categorize_char(ch) {
             Eol | Whitespace => return pos,
             category => {
-                if category != prev_category && pos != 0 && pos != slice.len_chars() {
+                if !long && category != prev_category && pos != 0 && pos != slice.len_chars() {
                     return pos;
                 } else {
                     match direction {
@@ -70,13 +70,14 @@ pub fn textobject_word(
     range: Range,
     textobject: TextObject,
     _count: usize,
+    long: bool,
 ) -> Range {
     let pos = range.cursor(slice);
 
-    let word_start = find_word_boundary(slice, pos, Direction::Backward);
+    let word_start = find_word_boundary(slice, pos, Direction::Backward, long);
     let word_end = match slice.get_char(pos).map(categorize_char) {
         None | Some(CharCategory::Whitespace | CharCategory::Eol) => pos,
-        _ => find_word_boundary(slice, pos + 1, Direction::Forward),
+        _ => find_word_boundary(slice, pos + 1, Direction::Forward, long),
     };
 
     // Special case.
@@ -268,7 +269,7 @@ mod test {
             let slice = doc.slice(..);
             for &case in scenario {
                 let (pos, objtype, expected_range) = case;
-                let result = textobject_word(slice, Range::point(pos), objtype, 1);
+                let result = textobject_word(slice, Range::point(pos), objtype, 1, false);
                 assert_eq!(
                     result,
                     expected_range.into(),

helix-term/src/commands.rs

@@ -4672,7 +4672,8 @@ fn select_textobject(cx: &mut Context, objtype: textobject::TextObject) {
 
                 let selection = doc.selection(view.id).clone().transform(|range| {
                     match ch {
-                        'w' => textobject::textobject_word(text, range, objtype, count),
+                        'w' => textobject::textobject_word(text, range, objtype, count, false),
+                        'W' => textobject::textobject_word(text, range, objtype, count, true),
                         'c' => textobject_treesitter("class", range),
                         'f' => textobject_treesitter("function", range),
                         'p' => textobject_treesitter("parameter", range),

helix-term/src/ui/prompt.rs

@@ -491,6 +491,7 @@ impl Component for Prompt {
                     doc.selection(view.id).primary(),
                     textobject::TextObject::Inside,
                     1,
+                    false,
                 );
                 let line = text.slice(range.from()..range.to()).to_string();
                 if !line.is_empty() {

languages.toml

@@ -47,6 +47,17 @@ comment-token = "#"
 language-server = { command = "elixir-ls" }
 indent = { tab-width = 2, unit = "  " }
 
+[[language]]
+name = "mint"
+scope = "source.mint"
+injection-regex = "mint"
+file-types = ["mint"]
+roots = []
+comment-token = "//"
+
+language-server = { command = "mint", args = ["ls"] }
+indent = { tab-width = 2, unit = "  " }
+
 [[language]]
 name = "json"
 scope = "source.json"
@@ -388,3 +399,11 @@ roots = []
 comment-token = "#"
 indent = { tab-width = 2, unit = "  " }
 language-server = { command = "cmake-language-server" }
+
+[[language]]
+name = "perl"
+scope = "source.perl"
+file-types = ["pl", "pm"]
+roots = []
+comment-token = "#"
+indent = { tab-width = 2, unit = "  " }