Added a V2 Parser:

- Generating LALRPOP grammar rules
- Changes in the language definition
- Added some tests and comparison against V1

Author: teofr

Cargo.lock

@@ -136,6 +136,8 @@ indicatif = { version = "0.17.12", features = ["in_memory"] }
 indoc = { version = "2.0.6" }
 Inflector = { version = "0.11.4" }
 itertools = { version = "0.13.0" }
+lalrpop = { version = "0.22.2" }
+lalrpop-util = { version = "0.22.2", features = ["lexer", "unicode"] }
 libc = { version = "0.2.0" }
 log = { version = "0.4.27" }
 logos = { version = "0.16.0" }

Cargo.toml

@@ -9,6 +9,7 @@ publish = false
 [dependencies]
 language_v2_definition = { workspace = true }
 serde = { workspace = true }
+semver = { workspace = true }
 
 [lints]
 workspace = true

crates/codegen-v2/parser/Cargo.toml

@@ -125,6 +125,7 @@ impl LexerModelBuilder {
     fn convert_keyword<'a>(&'a self, item: &'a KeywordItem) -> impl Iterator<Item = Lexeme> + 'a {
         item.definitions.iter().map(|def| Lexeme::Keyword {
             kind: item.name.to_string(),
+            identifier: item.identifier.to_string(),
             regex: self.convert_keyword_value(&def.value),
             reserved: def.reserved.clone(),
         })

crates/codegen-v2/parser/src/lexer/builder.rs

@@ -38,6 +38,7 @@ pub enum Lexeme {
     },
     Keyword {
         kind: String,
+        identifier: String,
         regex: String,
         reserved: Option<VersionSpecifier>,
     },

crates/codegen-v2/parser/src/lexer/mod.rs

@@ -1,19 +1,2 @@
 pub mod lexer;
-
-use language_v2_definition::model::Language;
-use serde::Serialize;
-
-use crate::lexer::LexerModel;
-
-#[derive(Clone, Debug, Serialize)]
-pub struct ParserModel {
-    pub lexer: LexerModel,
-}
-
-impl ParserModel {
-    pub fn from_language(language: &Language) -> Self {
-        Self {
-            lexer: LexerModel::from_language(language),
-        }
-    }
-}
+pub mod parser;