Fix #98: Implement Rust highlighting support (#99)

Initial Rust highlighting support

* Basic support for the language
* Line comments (`//`)
* Block comments (`/* */`), but no recursion
* Chars
* Strings (`"..."`)
* Raw strings (`r"..."`, `r#"..."#`, up to 5 levels)
* Added some Rust syntax test files

Co-authored-by: Romain Failliot <romain.failliot@foolstep.com>

data/usr/share/diffuse/syntax/rust.syntax

@@ -0,0 +1,119 @@
+# Rust syntax file for Diffuse
+# Copyright (C) 2022 Alexander Lopatin (@alopatindev), Romain Failliot <romain@foolstep.com>
+
+# DISCLAIMER: this is a raw support for Rust language, help wanted.
+
+syntax Rust normal text
+syntax_files Rust '\.rs$'
+
+# Colours
+colour rust_comment 0.2 0.4 0.64
+colour rust_fixme 1.0 0.5 0.0
+colour rust_import 0.77 0.63 0.0
+colour rust_keyword 0.77 0.63 0.0
+colour rust_type 0.3 0.6 0.02
+colour rust_literal 1.0 0.2 0.8
+colour rust_char 0.8 0.0 0.0
+colour rust_string 0.8 0.0 0.0
+colour rust_escapedchar 0.46 0.31 0.48
+colour rust_string_multilinechar 0.46 0.31 0.48
+colour rust_punctuation 0.5 0.5 0.5
+colour rust_macro 0.01 0.6 0.9
+
+# Whitespace (TODO)
+# Doc: https://doc.rust-lang.org/reference/whitespace.html
+syntax_pattern normal normal text '[ \t\r\n]+'
+
+# Macro (TODO)
+#syntax_pattern normal macro rust_macro '[a-z_]+[a-z0-9_]*!' ignorecase
+
+# Line comment
+# Doc: https://doc.rust-lang.org/reference/comments.html
+syntax_pattern normal line_comment rust_comment '//'
+syntax_pattern line_comment normal rust_comment '(\r\n|\r|\n)$'
+syntax_pattern line_comment line_comment rust_comment '\\(\r\n|\r|\n)$'
+syntax_pattern line_comment line_comment rust_fixme '\b(TODO|FIXME|XXX|NOTE)\b'
+syntax_pattern line_comment line_comment rust_comment '.[^\\TFX\r\n]*'
+
+# Block comment
+syntax_pattern normal block_comment rust_comment '/\*'
+syntax_pattern block_comment normal rust_comment '\*/'
+syntax_pattern block_comment block_comment rust_fixme '\b(TODO|FIXME|XXX|NOTE)\b'
+syntax_pattern block_comment block_comment rust_comment '.[^\*TFX]*'
+
+# Keywords (TODO)
+# Doc: https://doc.rust-lang.org/reference/keywords.html#weak-keywords
+#syntax_pattern normal normal rust_string '\b\'[a-z_]+[a-z0-9_]*\b' ignorecase
+#syntax_pattern normal normal rust_string '\b\'[a-z_]+\b' ignorecase
+syntax_pattern normal normal rust_string "\b'[a-z_]+\b" ignorecase
+
+# Char
+syntax_pattern normal normal rust_char "'.'"
+syntax_pattern normal char rust_char "'(?=\\\\)"
+syntax_pattern char normal rust_char "'"
+syntax_pattern char char rust_escapedchar "\\\\([0-7]{1,3}|x[0-9a-f]{1,2}|u\{[0-9a-f]{1,6}\}|.)"
+
+# String
+# Doc: https://doc.rust-lang.org/reference/tokens.html#string-literals
+syntax_pattern normal string rust_string '"'
+syntax_pattern string normal rust_string '"'
+syntax_pattern string string rust_escapedchar '(\\([0-7]{1,3}|x[0-9a-f]{1,2}|u\{[0-9a-f]{1,6}\}|.))+' ignorecase
+syntax_pattern string string rust_string_multilinechar '\\$'
+syntax_pattern string string rust_string '[^\\"]+'
+
+# Raw quote-string, level 0
+# Doc: https://doc.rust-lang.org/reference/tokens.html#raw-string-literals
+syntax_pattern normal raw_string_0 rust_string 'r"'
+syntax_pattern raw_string_0 normal rust_string '"'
+syntax_pattern raw_string_0 raw_string_0 rust_string '[^"$]+'
+
+# Raw sharp-string, level 1
+syntax_pattern normal raw_string_1 rust_string 'r#"'
+syntax_pattern raw_string_1 normal rust_string '"#'
+syntax_pattern raw_string_1 raw_string_1 rust_string '.*?((?="#)|\r?\n)'
+
+# Raw sharp-string, level 2
+syntax_pattern normal raw_string_2 rust_string 'r##"'
+syntax_pattern raw_string_2 normal rust_string '"##'
+syntax_pattern raw_string_2 raw_string_2 rust_string '.*?((?="##)|\r?\n)'
+
+# Raw sharp-string, level 3
+syntax_pattern normal raw_string_3 rust_string 'r###"'
+syntax_pattern raw_string_3 normal rust_string '"###'
+syntax_pattern raw_string_3 raw_string_3 rust_string '.*?((?="###)|\r?\n)'
+
+# Raw sharp-string, level 4
+syntax_pattern normal raw_string_4 rust_string 'r####"'
+syntax_pattern raw_string_4 normal rust_string '"####'
+syntax_pattern raw_string_4 raw_string_4 rust_string '.*?((?="####)|\r?\n)'
+
+# Raw sharp-string, level 5
+# Limit is 256 '#', but 5 seems reasonable for now
+syntax_pattern normal raw_string_5 rust_string 'r#####"'
+syntax_pattern raw_string_5 normal rust_string '"#####'
+syntax_pattern raw_string_5 raw_string_5 rust_string '.*?((?="#####)|\r?\n)'
+
+# Suffixes (TODO)
+# Doc: https://doc.rust-lang.org/reference/tokens.html#suffixes
+syntax_pattern normal normal rust_literal '\b[0-9_]+(isize|usize|char|bool|u8|u16|u32|u64|u128|f32|f64|i8|i16|i32|i64|i128|)\b'
+syntax_pattern normal normal rust_literal '\b0b[01_]+(isize|usize|char|bool|u8|u16|u32|u64|u128|f32|f64|i8|i16|i32|i64|i128|)\b'
+syntax_pattern normal normal rust_literal '\b0o[0-7_]+(isize|usize|char|bool|u8|u16|u32|u64|u128|f32|f64|i8|i16|i32|i64|i128|)\b'
+syntax_pattern normal normal rust_literal '\b0x[0-9a-f_]+(isize|usize|char|bool|u8|u16|u32|u64|u128|f32|f64|i8|i16|i32|i64|i128|)\b'
+syntax_pattern normal normal rust_literal '\b[0-9_]+E\+[0-9_]+(f32|f64)\b'
+syntax_pattern normal normal rust_literal '\b(true|false)\b'
+
+# import keywords
+syntax_pattern normal normal rust_import '\b(use|mod)\b'
+
+# typing keywords
+syntax_pattern normal normal rust_type '\b(isize|usize|char|bool|u8|u16|u32|u64|u128|f32|f64|i8|i16|i32|i64|i128|str|Self)\b'
+
+# keywords
+syntax_pattern normal normal rust_keyword '\b(as|break|const|continue|crate|else|enum|extern|false|fn|for|if|impl|in|let|loop|match|move|mut|pub|ref|return|self|Self|static|struct|super|trait|true|type|unsafe|where|while|async|await|dyn|abstract|become|box|do|final|macro|override|priv|typeof|unsized|virtual|yield|try|union)\b'
+
+# punctuation
+syntax_pattern normal normal rust_punctuation '[!~%\|\&\^\(\)\<\>\*\-\+=\{\}\[\]:;,\?$]+'
+syntax_pattern normal normal rust_punctuation '[/\.]'
+
+# parsing optimization
+syntax_pattern normal normal text '[a-z_][a-z_0-9]*' ignorecase

tests/syntax/rust/untested.rs

@@ -0,0 +1,37 @@
+#[derive(Clone)]
+struct A<'a_bж, B> {
+    x: &'a_bж B,
+    z: &'static str,
+}
+
+trait Tr {}
+
+async fn f(x: Result<(), ()>) -> Result<(), ()> {
+    let _ = x?;
+    Ok(())
+}
+
+async fn g() {
+    f(Ok(())).await.unwrap()
+}
+
+pub fn main() -> () {
+    println!("\x61\x62");
+    let mut x: i32 = 1;
+    let s: char = 's';
+    let s: char = '\123';
+    let x: i32 = -1_322_i32;
+    let x: Box<dyn Tr> = todo!();
+    let zsd: usize = 123456usize;
+    let фыва_1 = "asdf";
+    let abra_cadabra_2 = r#"abcd"#;
+    let x = 1;
+    let asd = r###"sdasd sdf"###;
+    let abra_cadabra_2 = r#"multiline
+        string
+    "#;
+    let asd = r###"multiline string
+        any characters '"_\/%
+        abcd"###;
+    return ();
+}

tests/syntax/rust/valid_comments.rs

@@ -0,0 +1,46 @@
+pub fn comments() -> () {
+    // line comment
+
+    // line comment
+    // line comment
+
+    //
+
+    //
+
+    //
+    //
+
+    // line comment // test
+
+    /* line comment */
+
+    /* line comment */
+    /* line comment */
+
+    /* block
+       comment
+    */
+
+    /*
+       block
+       comment
+    */
+
+    /**
+       block
+       comment
+    */
+
+    /**/
+
+    /* */
+
+    /***/
+
+    // Not supported yet:
+    //
+    // Recursive block comment:
+    // - This is valid: /* line /* test */ comment */
+    // - This is invalid: /* line /* test comment */
+}

tests/syntax/rust/valid_strings.rs

@@ -0,0 +1,43 @@
+pub fn strings() -> () {
+    let s = "foobar";
+    let s = "foo\
+      bar";
+    let s = "foo\
+
+      bar";
+
+    let s = "\
+      bar";
+
+    let escapedchars = "\\;\";\r\n\t\0";
+    let octalchars = "\12;\123";
+    let hexchars = "\x61;\x2B;\u{F7};\u{00F7};\u{0000F7}";
+    let unicodechars = "\u{F7};\u{00F7};\u{0000F7}";
+
+    let rs0 = r"";
+    let rs1 = r#""#;
+    let rs2 = r##""##;
+    let rs3 = r###""###;
+    let rs4 = r####""####;
+    let rs5 = r#####""#####;
+
+    let rs0 = r"foo bar";
+    let rs1 = r#""foo bar""#;
+    let rs2 = r##"foo "# bar"##;
+    let rs3 = r###"foo "## bar"###;
+    let rs4 = r####"foo "### bar"####;
+    let rs5 = r#####"foo "#### bar"#####;
+
+    let rs0 = r"foo
+      bar";
+    let rs1 = r#""foo
+      bar""#;
+    let rs2 = r##"foo
+      bar"##;
+    let rs3 = r###"foo
+      bar"###;
+    let rs4 = r####"foo
+      bar"####;
+    let rs5 = r#####"foo
+      bar"#####;
+}