initial framework

.gitignore

@@ -0,0 +1 @@
+/target

Cargo.lock

@@ -0,0 +1,93 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 3
+
+[[package]]
+name = "beef"
+version = "0.5.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bed554bd50246729a1ec158d08aa3235d1b69d94ad120ebe187e28894787e736"
+
+[[package]]
+name = "cwasm"
+version = "0.1.0"
+dependencies = [
+ "logos",
+]
+
+[[package]]
+name = "fnv"
+version = "1.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
+
+[[package]]
+name = "logos"
+version = "0.12.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "427e2abca5be13136da9afdbf874e6b34ad9001dd70f2b103b083a85daa7b345"
+dependencies = [
+ "logos-derive",
+]
+
+[[package]]
+name = "logos-derive"
+version = "0.12.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "56a7d287fd2ac3f75b11f19a1c8a874a7d55744bd91f7a1b3e7cf87d4343c36d"
+dependencies = [
+ "beef",
+ "fnv",
+ "proc-macro2",
+ "quote",
+ "regex-syntax",
+ "syn",
+ "utf8-ranges",
+]
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.36"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c7342d5883fbccae1cc37a2353b09c87c9b0f3afd73f5fb9bba687a1f733b029"
+dependencies = [
+ "unicode-xid",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "864d3e96a899863136fc6e99f3d7cae289dafe43bf2c5ac19b70df7210c0a145"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.6.25"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f497285884f3fcff424ffc933e56d7cbca511def0c9831a7f9b5f6153e3cc89b"
+
+[[package]]
+name = "syn"
+version = "1.0.86"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8a65b3f4ffa0092e9887669db0eae07941f023991ab58ea44da8fe8e2d511c6b"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-xid",
+]
+
+[[package]]
+name = "unicode-xid"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8ccb82d61f80a663efe1f787a51b16b5a51e3314d6ac365b08639f52387b33f3"
+
+[[package]]
+name = "utf8-ranges"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b4ae116fef2b7fea257ed6440d3cfcff7f190865f170cdad00bb6465bf18ecba"

Cargo.toml

@@ -0,0 +1,9 @@
+[package]
+name = "cwasm"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+logos = "0.12.0"

src/c_tokens.rs

@@ -0,0 +1,103 @@
+#[derive(PartialEq, Debug)]
+pub enum IncludeType {
+    System(String),
+    Local(String),
+}
+
+#[derive(PartialEq, Debug, Logos)]
+pub enum Tokens {
+    /// A signed integer literal.
+    #[regex("[-]?[0-9]+", parse_int, priority = 1)]
+    Int(i32),
+
+    #[regex("[-]?[0-9]+.[0-9]+", float_parse, priority = 2)]
+    Float(f32),
+
+    #[regex(";")]
+    SemiColon,
+
+    #[regex("[A-Za-z][A-Za-z0-9]+", parse_ident, priority = 3)]
+    Ident(String),
+
+    /*
+    // FIXME: I don't know how to properly parse this.
+    #[regex("\"[A-Za-z0-9]+\"", parse_string, priority = 123)]
+    StringLiteral(String),
+    */
+    #[regex("#include[ \t]+<[^>]+>", include_parse)]
+    Include(IncludeType),
+
+    #[regex("return")]
+    Return,
+
+    #[token("(")]
+    LParen,
+    #[token(")")]
+    RParen,
+    #[token("{")]
+    LBrace,
+    #[token("}")]
+    RBrace,
+
+    #[regex(r"[ \t\n\f]+", logos::skip)]
+    #[error]
+    Error,
+}
+
+use logos::{Lexer, Logos};
+
+fn parse_int(lex: &mut Lexer<Tokens>) -> Option<i32> {
+    let slice = lex.slice();
+
+    let int = slice.parse::<i32>().ok()?;
+
+    Some(int)
+}
+pub fn float_parse(lex: &mut Lexer<Tokens>) -> Option<f32> {
+    let slice = lex.slice();
+
+    let float = slice.parse::<f32>().ok()?;
+
+    Some(float)
+}
+
+fn include_parse(lex: &mut Lexer<Tokens>) -> Option<IncludeType> {
+    let slice = lex.slice();
+    let system_include_check = slice.starts_with("#include <");
+
+    let include = slice.to_string();
+    if system_include_check {
+        let ret = parse_inner_include(&include, "<", ">");
+
+        Some(IncludeType::System(ret))
+    } else {
+        let ret = parse_inner_include(&include, "\"", "\"");
+
+        Some(IncludeType::Local(ret))
+    }
+}
+
+fn parse_inner_include(include: &str, opener: &str, closer: &str) -> String {
+    let start_bytes = include.find(opener).unwrap_or(0); //index where "pattern" starts
+    let end_bytes = include.find(closer).unwrap_or(include.len()); //index where "<" is found
+
+    let ret = &include[start_bytes + 1..end_bytes];
+
+    ret.to_string()
+}
+
+pub fn parse_ident(lex: &mut Lexer<Tokens>) -> Option<String> {
+    let slice = lex.slice();
+
+    let ident = slice.to_string();
+
+    Some(ident)
+}
+
+pub fn parse_string(lex: &mut Lexer<Tokens>) -> Option<String> {
+    let slice = lex.slice();
+
+    let string = slice.to_string();
+
+    Some(string)
+}

src/hosted/mod.rs

@@ -0,0 +1,9 @@
+use std::fs::File;
+use std::io::prelude::*;
+
+pub fn write_to_disk() -> std::io::Result<()> {
+    let mut file = File::create("foo.wasm")?;
+    file.write_all(b"\0asm")?;
+
+    Ok(())
+}

src/main.rs

@@ -0,0 +1,14 @@
+pub mod c_tokens;
+
+use c_tokens::Tokens;
+use logos::Logos;
+
+#[cfg(test)]
+pub mod tests;
+
+fn main() {
+    let lex = c_tokens::Tokens::lexer(include_str!("test.c"));
+    for token in lex {
+        println!("{:?}", token);
+    }
+}

src/test.c

@@ -0,0 +1,5 @@
+#include <stdio.h>
+int main() {
+   printf("Hello, World!");
+   return 0;
+}

src/tests.rs

@@ -0,0 +1 @@
+