Add R and XML language support

CodeLanguages-Container/CodeLanguages-Container.xcodeproj/project.pbxproj

@@ -34,6 +34,8 @@
 		6CE117FC2CEA7CF80082D393 /* TreeSitterDart in Frameworks */ = {isa = PBXBuildFile; productRef = 6CE117FB2CEA7CF80082D393 /* TreeSitterDart */; };
 		6CEC70FE29C3A85000B61C7A /* TreeSitterRegex in Frameworks */ = {isa = PBXBuildFile; productRef = 6CEC70FD29C3A85000B61C7A /* TreeSitterRegex */; };
 		6CF2B8412CE978F100CBE5D1 /* TreeSitterDart in Frameworks */ = {isa = PBXBuildFile; productRef = 6CF2B8402CE978F100CBE5D1 /* TreeSitterDart */; };
+		76BC51E22F03A6D50030E59A /* TreeSitterR in Frameworks */ = {isa = PBXBuildFile; productRef = 76BC51E12F03A6D50030E59A /* TreeSitterR */; };
+		76BC51E52F03ACB50030E59A /* TreeSitterXML in Frameworks */ = {isa = PBXBuildFile; productRef = 76BC51E42F03ACB50030E59A /* TreeSitterXML */; };
 		8E74B41D2A4C88ED003A9550 /* TreeSitterHTML in Frameworks */ = {isa = PBXBuildFile; productRef = 8E74B41C2A4C88ED003A9550 /* TreeSitterHTML */; };
 		8E7B0EA92A5D9BB60040DDAB /* TreeSitterTOML in Frameworks */ = {isa = PBXBuildFile; productRef = 8E7B0EA82A5D9BB60040DDAB /* TreeSitterTOML */; };
 		8E7B8ABD2A5D916F00CFC1A7 /* TreeSitterPython in Frameworks */ = {isa = PBXBuildFile; productRef = 8E7B8ABC2A5D916F00CFC1A7 /* TreeSitterPython */; };
@@ -67,6 +69,7 @@
 				285BF67329AAA45B00641989 /* TreeSitterLua in Frameworks */,
 				8E87F9542A4B7DC1008C7E13 /* TreeSitterScala in Frameworks */,
 				6CE117F92CEA7BDC0082D393 /* TreeSitterDart in Frameworks */,
+				76BC51E22F03A6D50030E59A /* TreeSitterR in Frameworks */,
 				2846B262296BA1CF005F60B6 /* TreeSitterDockerfile in Frameworks */,
 				9D73992A2A5A30A400CEF6E8 /* TreeSitterPerl in Frameworks */,
 				9D6E74512A2B9B2A0070701E /* TreeSitterOCaml in Frameworks */,
@@ -80,6 +83,7 @@
 				28B9F7AA290DDAC900245748 /* TreeSitterBash in Frameworks */,
 				28B3F030290C35F9000CD04D /* TreeSitterCPP in Frameworks */,
 				28B3F04E290C3698000CD04D /* TreeSitterJSON in Frameworks */,
+				76BC51E52F03ACB50030E59A /* TreeSitterXML in Frameworks */,
 				28B3F033290C3608000CD04D /* TreeSitterCSharp in Frameworks */,
 				28B3F03F290C364D000CD04D /* TreeSitterGoMod in Frameworks */,
 				28B3F063290C372D000CD04D /* TreeSitterZig in Frameworks */,
@@ -204,6 +208,8 @@
 				6CF2B8402CE978F100CBE5D1 /* TreeSitterDart */,
 				6CE117F82CEA7BDC0082D393 /* TreeSitterDart */,
 				6CE117FB2CEA7CF80082D393 /* TreeSitterDart */,
+				76BC51E12F03A6D50030E59A /* TreeSitterR */,
+				76BC51E42F03ACB50030E59A /* TreeSitterXML */,
 			);
 			productName = "CodeLanguages-Container";
 			productReference = 28B3F00C290C207D000CD04D /* CodeLanguages_Container.framework */;
@@ -271,6 +277,8 @@
 				6C0B93A62B5DD95500323006 /* XCRemoteSwiftPackageReference "tree-sitter-css" */,
 				6C7CA2AB2CE9743E006D9D9A /* XCRemoteSwiftPackageReference "tree-sitter-objc" */,
 				6CE117FA2CEA7CF80082D393 /* XCRemoteSwiftPackageReference "tree-sitter-dart" */,
+				76BC51E02F03A6D50030E59A /* XCRemoteSwiftPackageReference "tree-sitter-r" */,
+				76BC51E32F03ACB50030E59A /* XCRemoteSwiftPackageReference "tree-sitter-xml" */,
 			);
 			productRefGroup = 28B3F00D290C207D000CD04D /* Products */;
 			projectDirPath = "";
@@ -712,6 +720,22 @@
 				kind = branch;
 			};
 		};
+		76BC51E02F03A6D50030E59A /* XCRemoteSwiftPackageReference "tree-sitter-r" */ = {
+			isa = XCRemoteSwiftPackageReference;
+			repositoryURL = "https://github.com/r-lib/tree-sitter-r/";
+			requirement = {
+				branch = main;
+				kind = branch;
+			};
+		};
+		76BC51E32F03ACB50030E59A /* XCRemoteSwiftPackageReference "tree-sitter-xml" */ = {
+			isa = XCRemoteSwiftPackageReference;
+			repositoryURL = "https://github.com/tree-sitter-grammars/tree-sitter-xml";
+			requirement = {
+				branch = master;
+				kind = branch;
+			};
+		};
 		8E74B41B2A4C88ED003A9550 /* XCRemoteSwiftPackageReference "tree-sitter-html" */ = {
 			isa = XCRemoteSwiftPackageReference;
 			repositoryURL = "https://github.com/tree-sitter/tree-sitter-html.git";
@@ -947,6 +971,16 @@
 			isa = XCSwiftPackageProductDependency;
 			productName = TreeSitterDart;
 		};
+		76BC51E12F03A6D50030E59A /* TreeSitterR */ = {
+			isa = XCSwiftPackageProductDependency;
+			package = 76BC51E02F03A6D50030E59A /* XCRemoteSwiftPackageReference "tree-sitter-r" */;
+			productName = TreeSitterR;
+		};
+		76BC51E42F03ACB50030E59A /* TreeSitterXML */ = {
+			isa = XCSwiftPackageProductDependency;
+			package = 76BC51E32F03ACB50030E59A /* XCRemoteSwiftPackageReference "tree-sitter-xml" */;
+			productName = TreeSitterXML;
+		};
 		8E74B41C2A4C88ED003A9550 /* TreeSitterHTML */ = {
 			isa = XCSwiftPackageProductDependency;
 			package = 8E74B41B2A4C88ED003A9550 /* XCRemoteSwiftPackageReference "tree-sitter-html" */;

CodeLanguages-Container/CodeLanguages-Container/CodeLanguages_Container.h

@@ -50,6 +50,7 @@ extern TSLanguage *tree_sitter_ocaml_interface();
 extern TSLanguage *tree_sitter_perl();
 extern TSLanguage *tree_sitter_php();
 extern TSLanguage *tree_sitter_python();
+extern TSLanguage *tree_sitter_r();
 extern TSLanguage *tree_sitter_regex();
 extern TSLanguage *tree_sitter_ruby();
 extern TSLanguage *tree_sitter_rust();
@@ -60,6 +61,7 @@ extern TSLanguage *tree_sitter_toml();
 extern TSLanguage *tree_sitter_tsx();
 extern TSLanguage *tree_sitter_typescript();
 extern TSLanguage *tree_sitter_verilog();
+extern TSLanguage *tree_sitter_xml();
 extern TSLanguage *tree_sitter_yaml();
 extern TSLanguage *tree_sitter_zig();
 

README.md

@@ -73,6 +73,7 @@ In order to add support for additional languages we have a complete guide on how
 | [Perl](https://github.com/ganezdragon/tree-sitter-perl) | ✅ | _not available_ |
 | [PHP](https://github.com/tree-sitter/tree-sitter-php) | ✅ | ✅ |
 | [Python](https://github.com/tree-sitter/tree-sitter-python) | ✅ | ✅ |
+| [R](https://github.com/r-lib/tree-sitter-r) | ✅ | ✅ |
 | [Regex](https://github.com/tree-sitter/tree-sitter-regex) | ✅ | ✅ |
 | [Ruby](https://github.com/mattmassicotte/tree-sitter-ruby) | ✅ | ✅ |
 | [Rust](https://github.com/tree-sitter/tree-sitter-rust) | ✅ | ✅ |
@@ -82,9 +83,28 @@ In order to add support for additional languages we have a complete guide on how
 | [TOML](https://github.com/cengelbart39/tree-sitter-toml/tree/feature/spm) | ✅ | ✅ |
 | [TypeScript/TSX](https://github.com/tree-sitter/tree-sitter-typescript) | ✅ | ✅ |
 | [Verilog](https://github.com/tree-sitter/tree-sitter-verilog) | ✅ | _not available_ |
+| [XML](https://github.com/tree-sitter-grammars/tree-sitter-xml) | ✅ | ✅ |
 | [YAML](https://github.com/tree-sitter-grammars/tree-sitter-yaml.git) | ✅ | ✅ |
 | [Zig](https://github.com/tree-sitter-grammars/tree-sitter-zig.git) | ✅ | ✅ |
 
+## Building the Framework
+
+When adding new languages, you need to rebuild the binary framework using `./build_framework.sh`.
+
+### Troubleshooting
+
+If the build script fails with:
+```
+xcode-select: error: tool 'xcodebuild' requires Xcode, but active developer directory '/Library/Developer/CommandLineTools' is a command line tools instance
+```
+
+Run this command to point to your Xcode installation:
+```bash
+sudo xcode-select -s /Applications/Xcode.app/Contents/Developer
+```
+
+Then run `./build_framework.sh` again.
+
 ## Related Repositories
 
 <table>

Sources/CodeEditLanguages/CodeLanguage+Definitions.swift

@@ -42,6 +42,7 @@ public extension CodeLanguage {
         .perl,
         .php,
         .python,
+        .r,
         .regex,
         .ruby,
         .rust,
@@ -52,6 +53,7 @@ public extension CodeLanguage {
         .tsx,
         .typescript,
         .verilog,
+        .xml,
         .yaml,
         .zig
     ]
@@ -354,6 +356,17 @@ public extension CodeLanguage {
         additionalIdentifiers: ["python2", "python3"]
     )
 
+    /// A language structure for `R`
+    static let r: CodeLanguage = .init(
+        id: .r,
+        tsName: "r",
+        extensions: ["r", "R"],
+        lineCommentString: "#",
+        rangeCommentStrings: ("", ""),
+        documentationCommentStrings: [.single("#'")],
+        additionalIdentifiers: ["Rscript"]
+    )
+
     /// A language structure for `Regex`
     static let regex: CodeLanguage = .init(
         id: .regex,
@@ -462,6 +475,15 @@ public extension CodeLanguage {
         highlights: ["folds", "injections"]
     )
 
+    /// A language structure for `XML`
+    static let xml: CodeLanguage = .init(
+        id: .xml,
+        tsName: "xml",
+        extensions: ["xml", "xsl", "xslt", "xsd", "svg", "plist"],
+        lineCommentString: "",
+        rangeCommentStrings: ("<!--", "-->")
+    )
+
     /// A language structure for `YAML`
     static let yaml: CodeLanguage = .init(
         id: .yaml,

Sources/CodeEditLanguages/CodeLanguage.swift

@@ -145,6 +145,8 @@ public struct CodeLanguage {
             return tree_sitter_php()
         case .python:
             return tree_sitter_python()
+        case .r:
+            return tree_sitter_r()
         case .regex:
             return tree_sitter_regex()
         case .ruby:
@@ -165,6 +167,8 @@ public struct CodeLanguage {
             return tree_sitter_typescript()
         case .verilog:
             return tree_sitter_verilog()
+        case .xml:
+            return tree_sitter_xml()
         case .yaml:
             return tree_sitter_yaml()
         case .zig:

Sources/CodeEditLanguages/Resources/tree-sitter-r/describe.scm

@@ -0,0 +1,32 @@
+(call
+	function: [
+		(identifier) @parent_function
+		(namespace_operator
+			lhs: (identifier) @parent_pkg (#eq? @parent_pkg "testthat")
+			rhs: (identifier) @parent_function
+		)
+	] (#eq? @parent_function "describe")
+	arguments: (arguments
+		(argument
+			value: (string) @parent_desc
+		)
+		(argument
+			value: (braced_expression
+				body: (call
+					function: [
+						(identifier) @function
+						(namespace_operator
+							lhs: (identifier) @pkg (#eq? @pkg "testthat")
+							rhs: (identifier) @function
+						)
+					] (#eq? @function "it")
+					arguments: (arguments
+						(argument
+							value: (string) @desc
+						)
+					)
+				) @call
+			)
+		)
+	)
+) @parent_call

Sources/CodeEditLanguages/Resources/tree-sitter-r/highlights.scm

@@ -0,0 +1,112 @@
+; highlights.scm
+
+; Literals
+
+(integer) @number
+(float) @number
+(complex) @number
+
+(string) @string
+(string (string_content (escape_sequence) @string.escape))
+
+; Comments
+
+(comment) @comment
+
+; Operators
+
+[
+  "?" ":=" "=" "<-" "<<-" "->" "->>"
+  "~" "|>" "||" "|" "&&" "&"
+  "<" "<=" ">" ">=" "==" "!="
+  "+" "-" "*" "/" "::" ":::"
+  "**" "^" "$" "@" ":" "!"
+  "special"
+] @operator
+
+; Punctuation
+
+[
+  "("  ")"
+  "{"  "}"
+  "["  "]"
+  "[[" "]]"
+] @punctuation.bracket
+
+(comma) @punctuation.delimiter
+
+; Variables
+
+(identifier) @variable
+
+; Functions
+
+(binary_operator
+    lhs: (identifier) @function
+    operator: "<-"
+    rhs: (function_definition)
+)
+
+(binary_operator
+    lhs: (identifier) @function
+    operator: "="
+    rhs: (function_definition)
+)
+
+; Calls
+
+(call function: (identifier) @function)
+
+; Parameters
+
+(parameters (parameter name: (identifier) @variable.parameter))
+(arguments (argument name: (identifier) @variable.parameter))
+
+; Namespace
+
+(namespace_operator lhs: (identifier) @namespace)
+
+(call
+    function: (namespace_operator rhs: (identifier) @function)
+)
+
+; Keywords
+
+(function_definition name: "function" @keyword.function)
+(function_definition name: "\\" @operator)
+
+[
+  "in"
+  (return)
+  (next)
+  (break)
+] @keyword
+
+[
+  "if"
+  "else"
+] @conditional
+
+[
+  "while"
+  "repeat"
+  "for"
+] @repeat
+
+[
+  (true)
+  (false)
+] @boolean
+
+[
+  (null)
+  (inf)
+  (nan)
+  (na)
+  (dots)
+  (dot_dot_i)
+] @constant.builtin
+
+; Error
+
+(ERROR) @error