Add kotlin language (#1689)

* Add kotlin language

Queries taken from https://github.com/nvim-treesitter/nvim-treesitter/blob/master/queries/kotlin seem to work well enough for my needs though I don't use kotlin heavily.

* Update lang-support doc

* Updates the kotlin highlight query to use helixs scopes

* Updates the queries from PR feedback

* Adds 'shallow = true' to gitmodules

* Removes kotlin locals.scm

* Remove blank line

Co-authored-by: Ivan Tham <pickfire@riseup.net>

Co-authored-by: Ivan Tham <pickfire@riseup.net>

7 files changed, 364 insertions, 1 deletions

diff --git a/.gitmodules b/.gitmodules
index 5b6609a8..fa1e0900 100644
--- a/.gitmodules
+++ b/.gitmodules
@@ -209,7 +209,7 @@
 [submodule "helix-syntax/languages/tree-sitter-graphql"]
 	path = helix-syntax/languages/tree-sitter-graphql
 	url = https://github.com/bkegley/tree-sitter-graphql
-  shallow = true
+	shallow = true
 [submodule "helix-syntax/languages/tree-sitter-elm"]
 	path = helix-syntax/languages/tree-sitter-elm
 	url = https://github.com/elm-tooling/tree-sitter-elm
@@ -229,3 +229,8 @@
 [submodule "helix-syntax/languages/tree-sitter-erlang"]
 	path = helix-syntax/languages/tree-sitter-erlang
 	url = https://github.com/the-mikedavis/tree-sitter-erlang
+	shallow = true
+[submodule "helix-syntax/languages/tree-sitter-kotlin"]
+	path = helix-syntax/languages/tree-sitter-kotlin
+	url = https://github.com/fwcd/tree-sitter-kotlin.git
+	shallow = true
diff --git a/book/src/generated/lang-support.md b/book/src/generated/lang-support.md
index 89405073..49538215 100644
--- a/book/src/generated/lang-support.md
+++ b/book/src/generated/lang-support.md
@@ -27,6 +27,7 @@
 | javascript | ✓ |  | ✓ | `typescript-language-server` |
 | json | ✓ |  | ✓ |  |
 | julia | ✓ |  |  | `julia` |
+| kotlin | ✓ |  |  | `kotlin-language-server` |
 | latex | ✓ |  |  |  |
 | lean | ✓ |  |  | `lean` |
 | ledger | ✓ |  |  |  |
diff --git a/helix-syntax/languages/tree-sitter-kotlin b/helix-syntax/languages/tree-sitter-kotlin
new file mode 160000
+Subproject a4f71eb9b8c9b19ded3e0e9470be4b1b77c2b56
diff --git a/languages.toml b/languages.toml
index 35758566..9876bcf1 100644
--- a/languages.toml
+++ b/languages.toml
@@ -741,3 +741,12 @@ file-types = ["erl", "hrl", "app", "rebar.config"]
 roots = ["rebar.config"]
 comment-token = "%%"
 indent = { tab-width = 4, unit = "    " }
+
+[[language]]
+name = "kotlin"
+scope = "source.kotlin"
+file-types = ["kt", "kts"]
+roots = ["settings.gradle", "settings.gradle.kts"]
+comment-token = "//"
+indent = { tab-width = 4, unit = "    " }
+language-server = { command = "kotlin-language-server" } 
diff --git a/runtime/queries/kotlin/folds.scm b/runtime/queries/kotlin/folds.scm
new file mode 100644
index 00000000..768972b8
--- /dev/null
+++ b/runtime/queries/kotlin/folds.scm
@@ -0,0 +1,17 @@
+[
+	(import_list)
+
+	(when_expression)
+	(control_structure_body)
+
+	(lambda_literal)
+	(function_body)
+	(primary_constructor)
+	(secondary_constructor)
+	(anonymous_initializer)
+
+	(class_body)
+	(enum_class_body)
+
+	(interpolated_expression)
+] @fold
diff --git a/runtime/queries/kotlin/highlights.scm b/runtime/queries/kotlin/highlights.scm
new file mode 100644
index 00000000..7b90fcf9
--- /dev/null
+++ b/runtime/queries/kotlin/highlights.scm
@@ -0,0 +1,295 @@
+;;; Operators & Punctuation
+
+(multi_line_string_literal
+	"$" @punctuation
+  (interpolated_identifier) @none)
+(multi_line_string_literal
+	"${" @punctuation
+	(interpolated_expression) @none
+	"}" @punctuation.)
+
+; NOTE: `interpolated_identifier`s can be highlighted in any way
+(line_string_literal
+	"$" @punctuation
+	(interpolated_identifier) @none)
+(line_string_literal
+	"${" @punctuation
+	(interpolated_expression) @none
+	"}" @punctuation)
+
+[
+	"."
+	","
+	";"
+	":"
+	"::"
+] @punctuation.delimiter
+
+[
+	"(" ")"
+	"[" "]"
+	"{" "}"
+] @punctuation.bracket
+
+[
+	"!"
+	"!="
+	"!=="
+	"="
+	"=="
+	"==="
+	">"
+	">="
+	"<"
+	"<="
+	"||"
+	"&&"
+	"+"
+	"++"
+	"+="
+	"-"
+	"--"
+	"-="
+	"*"
+	"*="
+	"/"
+	"/="
+	"%"
+	"%="
+	"?."
+	"?:"
+	"!!"
+	"is"
+	"!is"
+	"in"
+	"!in"
+	"as"
+	"as?"
+	".."
+	"->"
+] @operator
+
+;;; Keywords
+
+(type_alias "typealias" @keyword)
+[
+	(class_modifier)
+	(member_modifier)
+	(function_modifier)
+	(property_modifier)
+	(platform_modifier)
+	(variance_modifier)
+	(parameter_modifier)
+	(visibility_modifier)
+	(reification_modifier)
+	(inheritance_modifier)
+]@keyword
+
+[
+	"val"
+	"var"
+	"enum"
+	"class"
+	"object"
+	"interface"
+;	"typeof" ; NOTE: It is reserved for future use
+] @keyword
+
+("fun") @keyword.function
+
+(jump_expression) @keyword.control.return
+
+[
+	"if"
+	"else"
+	"when"
+] @keyword.control.conditional
+
+[
+	"for"
+	"do"
+	"while"
+] @keyword.control.repeat
+
+[
+	"try"
+	"catch"
+	"throw"
+	"finally"
+] @keyword.control.exception
+
+(annotation
+	"@" @attribute (use_site_target)? @attribute)
+(annotation
+	(user_type
+		(type_identifier) @attribute))
+(annotation
+	(constructor_invocation
+		(user_type
+			(type_identifier) @attribute)))
+
+(file_annotation
+	"@" @attribute "file" @attribute ":" @attribute)
+(file_annotation
+	(user_type
+		(type_identifier) @attribute))
+(file_annotation
+	(constructor_invocation
+		(user_type
+			(type_identifier) @attribute)))
+
+;;; Literals
+; NOTE: Escapes not allowed in multi-line strings
+(line_string_literal (character_escape_seq) @constant.character.escape)
+
+[
+	(line_string_literal)
+	(multi_line_string_literal)
+] @string
+
+(character_literal) @constant.character
+
+[
+	"null" ; should be highlighted the same as booleans
+	(boolean_literal)
+] @constant.builtin.boolean
+
+(real_literal) @constant.numeric.float
+[
+	(integer_literal)
+	(long_literal)
+	(hex_literal)
+	(bin_literal)
+	(unsigned_literal)
+] @constant.numeric.integer
+
+[
+	(comment)
+	(shebang_line)
+] @comment
+
+;;; Function calls
+
+(call_expression
+	. (simple_identifier) @function.builtin
+    (#match? @function.builtin "^(arrayOf|arrayOfNulls|byteArrayOf|shortArrayOf|intArrayOf|longArrayOf|ubyteArrayOf|ushortArrayOf|uintArrayOf|ulongArrayOf|floatArrayOf|doubleArrayOf|booleanArrayOf|charArrayOf|emptyArray|mapOf|setOf|listOf|emptyMap|emptySet|emptyList|mutableMapOf|mutableSetOf|mutableListOf|print|println|error|TODO|run|runCatching|repeat|lazy|lazyOf|enumValues|enumValueOf|assert|check|checkNotNull|require|requireNotNull|with|suspend|synchronized)$"))
+
+; object.function() or object.property.function()
+(call_expression
+	(navigation_expression
+		(navigation_suffix
+			(simple_identifier) @function) . ))
+
+; function()
+(call_expression
+	. (simple_identifier) @function)
+
+;;; Function definitions
+
+; lambda parameters
+(lambda_literal
+	(lambda_parameters
+		(variable_declaration
+			(simple_identifier) @variable.parameter)))
+			
+(parameter_with_optional_type
+	(simple_identifier) @variable.parameter)
+			
+(parameter
+	(simple_identifier) @variable.parameter)
+			
+(anonymous_initializer
+	("init") @constructor)
+
+(constructor_invocation
+	(user_type
+		(type_identifier) @constructor))
+			
+(secondary_constructor
+	("constructor") @constructor)
+(primary_constructor) @constructor
+			
+(getter
+	("get") @function.builtin)
+(setter
+	("set") @function.builtin)
+
+(function_declaration
+	. (simple_identifier) @function)
+
+; TODO: Seperate labeled returns/breaks/continue/super/this
+;       Must be implemented in the parser first
+(label) @label
+
+(import_header
+	(identifier
+		(simple_identifier) @function @_import .)
+	(import_alias
+		(type_identifier) @function)?
+		(#match? @_import "^[a-z]"))
+
+; The last `simple_identifier` in a `import_header` will always either be a function
+; or a type. Classes can appear anywhere in the import path, unlike functions
+(import_header
+	(identifier
+		(simple_identifier) @type @_import)
+	(import_alias
+		(type_identifier) @type)?
+		(#match? @_import "^[A-Z]"))
+
+(import_header
+	"import" @keyword.control.import)
+
+(package_header
+	. (identifier)) @namespace
+
+((type_identifier) @type.builtin
+	(#match? @function.builtin "^(Byte|Short|Int|Long|UByte|UShort|UInt|ULong|Float|Double|Boolean|Char|String|Array|ByteArray|ShortArray|IntArray|LongArray|UByteArray|UShortArray|UIntArray|ULongArray|FloatArray|DoubleArray|BooleanArray|CharArray|Map|Set|List|EmptyMap|EmptySet|EmptyList|MutableMap|MutableSet|MutableList)$"))
+
+(type_identifier) @type
+
+(enum_entry
+	(simple_identifier) @constant)
+
+(_
+	(navigation_suffix
+		(simple_identifier) @constant
+		(#match? @constant "^[A-Z][A-Z0-9_]*$")))
+
+; SCREAMING CASE identifiers are assumed to be constants
+((simple_identifier) @constant
+(#match? @constant "^[A-Z][A-Z0-9_]*$"))
+
+; id_1.id_2.id_3: `id_2` and `id_3` are assumed as object properties
+(_
+	(navigation_suffix
+		(simple_identifier) @variable.other.member))
+
+(class_body
+	(property_declaration
+		(variable_declaration
+			(simple_identifier) @variable.other.member)))
+
+(class_parameter
+	(simple_identifier) @variable.other.member)
+
+; `super` keyword inside classes
+(super_expression) @variable.builtin
+
+; `this` this keyword inside classes
+(this_expression) @variable.builtin
+
+;;; Identifiers
+; `field` keyword inside property getter/setter
+; FIXME: This will highlight the keyword outside of getters and setters
+;        since tree-sitter does not allow us to check for arbitrary nestation
+((simple_identifier) @variable.builtin
+(#eq? @variable.builtin "field"))
+
+; `it` keyword inside lambdas
+; FIXME: This will highlight the keyword outside of lambdas since tree-sitter
+;        does not allow us to check for arbitrary nestation
+((simple_identifier) @variable.builtin
+(#eq? @variable.builtin "it"))
+
+(simple_identifier) @variable
diff --git a/runtime/queries/kotlin/injections.scm b/runtime/queries/kotlin/injections.scm
new file mode 100644
index 00000000..abdc2050
--- /dev/null
+++ b/runtime/queries/kotlin/injections.scm
@@ -0,0 +1,36 @@
+((comment) @injection.content
+	(#set! injection.language "comment"))
+
+; There are 3 ways to define a regex
+;    - "[abc]?".toRegex()
+((call_expression
+	(navigation_expression
+		([(line_string_literal) (multi_line_string_literal)] @injection.content)
+		(navigation_suffix
+			((simple_identifier) @_function
+			(#eq? @_function "toRegex")))))
+	(#set! injection.language "regex"))
+
+;    - Regex("[abc]?")
+((call_expression
+	((simple_identifier) @_function
+	(#eq? @_function "Regex"))
+	(call_suffix
+		(value_arguments
+			(value_argument
+				[ (line_string_literal) (multi_line_string_literal) ] @injection.content))))
+	(#set! injection.language "regex"))
+
+;    - Regex.fromLiteral("[abc]?")
+((call_expression
+	(navigation_expression
+		((simple_identifier) @_class
+		(#eq? @_class "Regex"))
+		(navigation_suffix
+			((simple_identifier) @_function
+			(#eq? @_function "fromLiteral"))))
+	(call_suffix
+		(value_arguments
+			(value_argument
+				[ (line_string_literal) (multi_line_string_literal) ] @injection.content))))
+	(#set! injection.language "regex"))