Adding support for PHP

CHANGELOG.md

@@ -4,6 +4,8 @@ Difftastic now requires Rust 1.56 to build.
 
 ### Parsing
 
+Added support for PHP.
+
 Fixed handling of `<` `>` delimiters in C++ and Rust.
 
 ### Diffing

README.md

@@ -69,6 +69,7 @@ Difftastic supports the following languages:
 * JavaScript (and JSX)
 * JSON
 * OCaml
+* PHP
 * Python
 * Ruby
 * Rust

build.rs

@@ -134,6 +134,11 @@ fn main() {
             src_dir: "vendor/tree-sitter-ocaml-src/interface/src",
             extra_files: vec!["scanner.cc"],
         },
+        TreeSitterParser {
+            name: "tree-sitter-php",
+            src_dir: "vendor/tree-sitter-php-src",
+            extra_files: vec!["scanner.cc"],
+        },
         TreeSitterParser {
             name: "tree-sitter-python",
             src_dir: "vendor/tree-sitter-python-src",

manual/src/introduction.md

@@ -19,6 +19,7 @@ tool that understands syntax. It supports the following languages:
 * JavaScript (and JSX)
 * JSON
 * OCaml
+* PHP
 * Python
 * Ruby
 * Rust

manual/src/upstream_parsers.md

@@ -19,6 +19,7 @@ Difftastic uses the following tree-sitter parsers:
 | JavaScript, JSX | [tree-sitter/tree-sitter-javascript](https://github.com/tree-sitter/tree-sitter-javascript)                                             |
 | JSON            | [tree-sitter/tree-sitter-json](https://github.com/tree-sitter/tree-sitter-json)                                                         |
 | OCaml           | [tree-sitter/tree-sitter-ocaml](https://github.com/tree-sitter/tree-sitter-ocaml)                                                       |
+| PHP             | [tree-sitter/tree-sitter-php](https://github.com/tree-sitter/tree-sitter-php)                                                           |
 | Python          | [tree-sitter/tree-sitter-python](https://github.com/tree-sitter/tree-sitter-python)                                                     |
 | Ruby            | [tree-sitter/tree-sitter-ruby](https://github.com/tree-sitter/tree-sitter-ruby)                                                         |
 | Rust            | [tree-sitter/tree-sitter-rust](https://github.com/tree-sitter/tree-sitter-rust) ([forked](https://github.com/Wilfred/tree-sitter-rust)) |

src/guess_language.rs

@@ -35,6 +35,7 @@ pub enum Language {
     Jsx,
     OCaml,
     OCamlInterface,
+    Php,
     Python,
     Ruby,
     Rust,
@@ -190,6 +191,7 @@ fn from_extension(extension: &OsStr) -> Option<Language> {
         "json" => Some(Json),
         "ml" => Some(OCaml),
         "mli" => Some(OCamlInterface),
+        "php" => Some(Php),
         "py" | "py3" | "pyi" | "bzl" => Some(Python),
         "rb" | "builder" | "spec" | "rake" => Some(Ruby),
         "rs" => Some(Rust),

src/tree_sitter_parser.rs

@@ -59,6 +59,7 @@ extern "C" {
     fn tree_sitter_json() -> ts::Language;
     fn tree_sitter_ocaml() -> ts::Language;
     fn tree_sitter_ocaml_interface() -> ts::Language;
+    fn tree_sitter_php() -> ts::Language;
     fn tree_sitter_python() -> ts::Language;
     fn tree_sitter_ruby() -> ts::Language;
     fn tree_sitter_rust() -> ts::Language;
@@ -333,6 +334,20 @@ pub fn from_language(language: guess::Language) -> TreeSitterConfig {
                 .unwrap(),
             }
         }
+        Php => {
+            let language = unsafe { tree_sitter_php() };
+            TreeSitterConfig {
+                name: "PHP",
+                language,
+                atom_nodes: (vec!["string"]).into_iter().collect(),
+                delimiter_tokens: (vec![("(", ")"), ("[", "]"), ("{", "}")]),
+                highlight_query: ts::Query::new(
+                    language,
+                    include_str!("../vendor/highlights/php.scm"),
+                )
+                .unwrap(),
+            }
+        }
         Python => {
             let language = unsafe { tree_sitter_python() };
             TreeSitterConfig {