Merge pull request #606 from kkoomen/feature/implement-r

Add support for R

README.md

@@ -89,6 +89,7 @@ Is your favorite doc standard not supported?
 | :white_check_mark: | C#                                             | [XMLDoc][xmldoc]                                                             |
 | :white_check_mark: | Bash                                           | [Google][sh-google]                                                          |
 | :white_check_mark: | Rust                                           | [RustDoc][rustdoc]                                                           |
+| :white_check_mark: | R                                              | [Roxygen2][roxygen2]                                                         |
 
 # Getting started
 
@@ -172,6 +173,7 @@ Here is the full list of available doc standards per filetype:
 | `g:doge_doc_standard_sh`         | `'google'`          | `'google'`                                                                                                                                                                                                                                             |
 | `g:doge_doc_standard_rs`         | `'rustdoc'`         | `'rustdoc'`                                                                                                                                                                                                                                            |
 | `g:doge_doc_standard_cs`         | `'xmldoc'`          | `'xmldoc'`                                                                                                                                                                                                                                             |
+| `g:doge_doc_standard_r`          | `'roxygen2'`        | `'roxygen2'`                                                                                                                                                                                                                                           |
 
 ## Options
 
@@ -468,6 +470,7 @@ Vim-doge is licensed under the GPL-3.0 license.
 [kerneldoc]: https://www.kernel.org/doc/html/latest/doc-guide/kernel-doc.html
 [sh-google]: https://google.github.io/styleguide/shell.xml#Function_Comments
 [xmldoc]: https://docs.microsoft.com/en-us/dotnet/csharp/language-reference/xmldoc/
+[roxygen2]: https://github.com/klutometis/roxygen
 
 [demo-readme]: https://github.com/kkoomen/vim-doge/blob/master/doc/demos
 [suggest-language]: https://github.com/kkoomen/vim-doge/issues/new?labels=enhancement&template=feature_request.md&title=Add+support+for+<language>

ftplugin/r.vim

@@ -0,0 +1,11 @@
+let s:save_cpo = &cpoptions
+set cpoptions&vim
+
+let b:doge_parser = 'r'
+let b:doge_insert = 'above'
+
+let b:doge_supported_doc_standards = ['roxygen2']
+let b:doge_doc_standard = doge#buffer#get_doc_standard('r')
+
+let &cpoptions = s:save_cpo
+unlet s:save_cpo

helper/Cargo.toml

@@ -26,3 +26,4 @@ tree-sitter-c = { git = "https://github.com/tree-sitter/tree-sitter-c", rev = "8
 tree-sitter-cpp = { git = "https://github.com/tree-sitter/tree-sitter-cpp", rev = "0e7b7a0" }
 tree-sitter-typescript = { git = "https://github.com/tree-sitter/tree-sitter-typescript", rev = "3429d8c" }
 tree-sitter-php = { git = "https://github.com/tree-sitter/tree-sitter-php", rev = "d43130f" }
+tree-sitter-r = { git = "https://github.com/r-lib/tree-sitter-r", rev = "c55f8b4" }

helper/src/config.rs

@@ -33,6 +33,7 @@ pub fn load_doc_config_str<'a>(parser_name: &'a str, doc_name: &'a str) -> &'a s
         "csharp_xmldoc" => include_str!("csharp/docs/xmldoc.yaml"),
         "bash_google" => include_str!("bash/docs/google.yaml"),
         "rust_rustdoc" => include_str!("rust/docs/rustdoc.yaml"),
+        "r_roxygen2" => include_str!("r/docs/roxygen2.yaml"),
 
         _ => panic!("Unsupported {} doc: {}", parser_name, doc_name),
     }

helper/src/docblock.rs

@@ -17,6 +17,7 @@ use crate::python::parser::PythonParser;
 use crate::ruby::parser::RubyParser;
 use crate::rust::parser::RustParser;
 use crate::typescript::parser::TypescriptParser;
+use crate::r::parser::RParser;
 
 
 fn replace_indent_placeholders(docblock: &str, use_tabs: bool, indent: usize) -> String {
@@ -137,6 +138,7 @@ pub fn generate(
             "c" => Box::new(CParser::new(code, line, &node_types)) as Box<dyn BaseParser>,
             "cpp" => Box::new(CppParser::new(code, line, &node_types)) as Box<dyn BaseParser>,
             "typescript" => Box::new(TypescriptParser::new(code, line, &node_types, options)) as Box<dyn BaseParser>,
+            "r" => Box::new(RParser::new(code, line, &node_types)) as Box<dyn BaseParser>,
             _ => panic!("Unsupported parser: {}", &parser_name),
         };
 

helper/src/lib.rs

@@ -15,3 +15,4 @@ pub mod python;
 pub mod c;
 pub mod cpp;
 pub mod typescript;
+pub mod r;

helper/src/r/docs/roxygen2.yaml

@@ -0,0 +1,25 @@
+# https://github.com/klutometis/roxygen
+
+templates:
+  function:
+    node_types:
+      - function_definition
+    template: |
+        #' [TODO:title of the function]
+        #'
+        #' [TODO:brief description]
+        {% if params %}
+        #'
+            {% for param in params %}
+        #' @param {{ param.name }} [TODO:description]{% if param.default_value %}. Default is {{ param.default_value }}.{% endif %}
+            {% endfor %}
+        {% endif %}
+        #'
+        #' @return [TODO:description]
+        #'
+        #' @examples
+        #' {{ func_name }}([TODO:parameters])
+        #'
+        #' @rdname {{ func_name }}
+        #'
+        #' @method {{ func_name }}

helper/src/r/mod.rs

@@ -0,0 +1 @@
+pub mod parser;

helper/src/r/parser.rs

@@ -0,0 +1,110 @@
+use tree_sitter::{Parser, Node};
+use serde_json::{Map, Value};
+
+use crate::base_parser::BaseParser;
+use crate::traverse;
+
+pub struct RParser<'a> {
+    code: &'a str,
+    tree: tree_sitter::Tree,
+    line: &'a usize,
+    node_types: &'a [&'a str],
+}
+
+impl<'a> BaseParser for RParser<'a> {
+    fn parse(&self) -> Option<Result<Map<String, Value>, String>> {
+        self.parse_node(&self.tree.root_node())
+    }
+
+    fn get_code_bytes(&self) -> &[u8] {
+        &self.code.as_bytes()
+    }
+}
+
+impl<'a> RParser<'a> {
+    pub fn new(code: &'a str, line: &'a usize, node_types: &'a [&'a str]) -> Self {
+        let mut parser = Parser::new();
+        parser.set_language(tree_sitter_r::language()).unwrap();
+
+        let tree = parser.parse(code, None).unwrap();
+
+        Self { code, tree, line, node_types }
+    }
+
+    fn parse_node(&self, node: &Node) -> Option<Result<Map<String, Value>, String>> {
+        for child_node in traverse::PreOrder::new(node.walk()) {
+            if child_node.start_position().row + 1 == *self.line && self.node_types.contains(&child_node.kind()) {
+                return match child_node.kind() {
+                    "function_definition" => Some(self.parse_function(&child_node)),
+                    _ => None,
+                };
+            }
+        }
+
+        None
+    }
+
+    fn parse_function(&self, node: &Node) -> Result<Map<String, Value>, String> {
+        let mut tokens = Map::new();
+
+        if let Some(parent_node) = node.parent() {
+            let func_name = parent_node
+                .children(&mut parent_node.walk())
+                .filter(|node| node.kind() == "identifier")
+                .next()
+                .and_then(|node| Some(self.get_node_text(&node)))
+                .unwrap();
+            tokens.insert("func_name".to_string(), Value::String(func_name));
+        }
+
+        for child_node in node.children(&mut node.walk()) {
+            match child_node.kind() {
+                "formal_parameters" => {
+                    let mut params = Vec::new();
+
+                    for grandchild_node in child_node.children(&mut child_node.walk()) {
+                        let mut param = Map::new();
+
+                        match grandchild_node.kind() {
+                            "identifier" | "dots" => {
+                                param.insert("name".to_string(), Value::String(self.get_node_text(&grandchild_node)));
+                            },
+                            "default_parameter" => {
+                                let name = grandchild_node
+                                    .children(&mut grandchild_node.walk())
+                                    .filter(|node| node.kind() == "identifier")
+                                    .next()
+                                    .and_then(|node| Some(self.get_node_text(&node)))
+                                    .unwrap();
+
+                                let default_value = grandchild_node
+                                    .children(&mut grandchild_node.walk())
+                                    .filter(|node| node.kind() == "=")
+                                    .next()
+                                    .unwrap()
+                                    .next_sibling()
+                                    .and_then(|node| Some(self.get_node_text(&node)))
+                                    .unwrap();
+
+                                param.insert("name".to_string(), Value::String(name));
+                                param.insert("default_value".to_string(), Value::String(default_value));
+                            },
+                            _ => {},
+                        }
+
+                        if !param.is_empty() {
+                            params.push(Value::Object(param));
+                        }
+                    }
+
+                    if !params.is_empty() {
+                        tokens.insert("params".to_string(), Value::Array(params));
+                    }
+                },
+                _ => {},
+            }
+        }
+
+        Ok(tokens)
+    }
+}

helper/test.r

@@ -0,0 +1,20 @@
+myFunc.default <- function() {}
+
+myFunc.default <- function(
+  p1,
+  p2.sub1 = FALSE,
+  p3.sub1 = 20,
+  p4.sub1 = 1/15,
+  ...
+) {
+  # ...
+}
+
+myFunc = function(
+  p1 = TRUE, p2_sub1= TRUE, p3 = FALSE,
+  p4 = 'libs', p5 = NULL, ..., p7 = 'default',
+  p8 = c('lorem', 'ipsum+dor', 'sit', 'amet'),
+  p9 = TRUE, p10 = list(), p11 = TRUE
+) {
+  # ...
+}