Add R language

.gitmodules

@@ -31,3 +31,7 @@
 [submodule "parsers/modelica"]
 	path = parsers/modelica
 	url = [email protected]:OpenModelica/tree-sitter-modelica.git
+[submodule "parsers/r"]
+	path = parsers/r
+	url = [email protected]:r-lib/tree-sitter-r.git
+	branch = next

lib/src/lib/language.ts

@@ -114,6 +114,7 @@ export class LanguagePicker {
     new ProgrammingLanguage("java", [".java"]),
     new ProgrammingLanguage("javascript", [".js"]),
     new ProgrammingLanguage("elm", [".elm"]),
+    new ProgrammingLanguage("r", [".r", ".rdata", ".rds", ".rda"]),
     new ProgrammingLanguage("typescript", [".ts"]),
     new ProgrammingLanguage("tsx", [".tsx"]),
     new CustomTokenizerLanguage("char", [".txt", ".md"], async self => {
@@ -128,8 +129,8 @@ export class LanguagePicker {
   constructor() {
     for (const language of LanguagePicker.languages) {
       for (const extension of language.extensions) {
-        this.byExtension.set(extension, language);
-        this.byName.set(language.name, language);
+        this.byExtension.set(extension.toLowerCase(), language);
+        this.byName.set(language.name.toLowerCase(), language);
       }
     }
   }
@@ -146,10 +147,10 @@ export class LanguagePicker {
     let maxCount = 0;
     let language: Language | undefined = undefined;
     for (const file of files) {
-      const count = (counts.get(file.extension) ?? 0) + 1;
+      const count = (counts.get(file.extension.toLowerCase()) ?? 0) + 1;
       if (count > maxCount) {
         maxCount = count;
-        language = this.byExtension.get(file.extension);
+        language = this.byExtension.get(file.extension.toLowerCase());
       }
       counts.set(file.extension, count);
     }
@@ -169,9 +170,9 @@ export class LanguagePicker {
    * @param name
    */
   public async findLanguage(name: string): Promise<Language> {
-    let language = this.byName.get(name);
+    let language = this.byName.get(name.toLowerCase());
     if (language == null) {
-      const proglang = new ProgrammingLanguage(name, []);
+      const proglang = new ProgrammingLanguage(name.toLowerCase(), []);
       // Try to load the language module to see if it exists,
       // will throw an error if it does not exist.
       await proglang.loadLanguageModule();

lib/src/test/tokenizer.test.ts

@@ -15,6 +15,7 @@ const languageFiles = {
   "python": "../samples/python/caesar.py",
   "php": "../samples/php/caesar.php",
   "modelica": "../samples/modelica/sample.mo",
+  "r": "../samples/r/caesar.R",
   "tsx": "../samples/tsx/sample.tsx",
   "typescript": "../samples/typescript/caesar.ts",
 } as {[key: string]: string};

parsers/binding.gyp

@@ -10,6 +10,7 @@
         "modelica/binding.gyp",
         "php/binding.gyp",
         "python/binding.gyp",
+        "r/binding.gyp",
         "typescript/binding.gyp"
     ]
 }

parsers/index.js

@@ -29,6 +29,9 @@ module.exports.php.nodeTypeInfo = require("./php/src/node-types.json");
 module.exports.python = require("./build/Release/tree_sitter_python_binding");
 module.exports.python.nodeTypeInfo = require("./python/src/node-types.json");
 
+module.exports.r = require("./build/Release/tree_sitter_r_binding");
+module.exports.r.nodeTypeInfo = require("./r/src/node-types.json");
+
 const typescript_tsx = require("./build/Release/tree_sitter_typescript_binding");
 module.exports.typescript = typescript_tsx.typescript;
 module.exports.typescript.nodeTypeInfo = require("./typescript/typescript/src/node-types.json");

samples/r/caesar.R

@@ -0,0 +1,25 @@
+caesar <- function(x, key)
+{
+  # if key is negative, wrap to be positive
+  if (key < 0) {
+    key <- 26 + key 
+  }
+
+  old <- paste(letters, LETTERS, collapse="", sep="")
+  new <- paste(substr(old, key * 2 + 1, 52), substr(old, 1, key * 2), sep="")
+  chartr(old, new, x)
+}
+
+# simple examples from description
+print(caesar("hi",2))
+print(caesar("hi",20))
+
+# more advanced example
+key <- 3
+plaintext <- "The five boxing wizards jump quickly."
+cyphertext <- caesar(plaintext, key)
+decrypted <- caesar(cyphertext, -key)
+
+print(paste("    Plain Text: ", plaintext, sep=""))
+print(paste("   Cypher Text: ", cyphertext, sep=""))
+print(paste("Decrypted Text: ", decrypted, sep=""))