From 1abb705fd23e422b573bfa5efaf2ce29bce0bd63 Mon Sep 17 00:00:00 2001
From: Able <abl3theabove@gmail.com>
Date: Mon, 5 Dec 2022 23:01:40 -0600
Subject: [PATCH] tokenize a simple wasm program

---
 Cargo.lock                             | 48 +++++++++++++++++++++++++
 Cargo.toml                             |  1 +
 programs/wat2wasm/Cargo.toml           |  9 +++++
 programs/wat2wasm/assets/add.wat       |  8 +++++
 programs/wat2wasm/src/main.rs          | 26 ++++++++++++++
 programs/wat2wasm/src/tokenizer/mod.rs | 50 ++++++++++++++++++++++++++
 6 files changed, 142 insertions(+)
 create mode 100644 programs/wat2wasm/Cargo.toml
 create mode 100644 programs/wat2wasm/assets/add.wat
 create mode 100644 programs/wat2wasm/src/main.rs
 create mode 100644 programs/wat2wasm/src/tokenizer/mod.rs

diff --git a/Cargo.lock b/Cargo.lock
index 2a42ba4..6bbf535 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -47,6 +47,12 @@ checksum = "9e1b586273c5702936fe7b7d6896644d8be71e6314cfe09d3167c95f712589e8"
 name = "basic_driver"
 version = "0.1.0"
 
+[[package]]
+name = "beef"
+version = "0.5.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3a8241f3ebb85c056b509d4327ad0358fbbba6ffb340bf388f26350aeda225b1"
+
 [[package]]
 name = "bitflags"
 version = "1.3.2"
@@ -89,6 +95,12 @@ dependencies = [
 name = "derelict_microarchitecture"
 version = "0.1.0"
 
+[[package]]
+name = "fnv"
+version = "1.0.7"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
+
 [[package]]
 name = "fs_extra"
 version = "1.2.0"
@@ -159,6 +171,29 @@ dependencies = [
  "cfg-if",
 ]
 
+[[package]]
+name = "logos"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bf8b031682c67a8e3d5446840f9573eb7fe26efe7ec8d195c9ac4c0647c502f1"
+dependencies = [
+ "logos-derive",
+]
+
+[[package]]
+name = "logos-derive"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a1d849148dbaf9661a6151d1ca82b13bb4c4c128146a88d05253b38d4e2f496c"
+dependencies = [
+ "beef",
+ "fnv",
+ "proc-macro2",
+ "quote",
+ "regex-syntax",
+ "syn",
+]
+
 [[package]]
 name = "messaging"
 version = "0.1.0"
@@ -221,6 +256,12 @@ dependencies = [
  "versioning",
 ]
 
+[[package]]
+name = "regex-syntax"
+version = "0.6.28"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "456c603be3e8d448b072f410900c09faf164fbce2d480456f50eea6e25f9c848"
+
 [[package]]
 name = "ron"
 version = "0.7.1"
@@ -386,3 +427,10 @@ name = "wasi"
 version = "0.11.0+wasi-snapshot-preview1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9c8d87e72b64a3b4db28d11ce29237c246188f4f51057d65a7eab63b7987e423"
+
+[[package]]
+name = "wat2wasm"
+version = "0.1.0"
+dependencies = [
+ "logos",
+]
diff --git a/Cargo.toml b/Cargo.toml
index d3c197f..1fc1d5c 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -28,4 +28,5 @@ members = [
     "programs/shell",
     "programs/table_view",
     "programs/undelete",
+    "programs/wat2wasm",
 ]
diff --git a/programs/wat2wasm/Cargo.toml b/programs/wat2wasm/Cargo.toml
new file mode 100644
index 0000000..3a454ee
--- /dev/null
+++ b/programs/wat2wasm/Cargo.toml
@@ -0,0 +1,9 @@
+[package]
+name = "wat2wasm"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[dependencies]
+logos = "*"
diff --git a/programs/wat2wasm/assets/add.wat b/programs/wat2wasm/assets/add.wat
new file mode 100644
index 0000000..343143f
--- /dev/null
+++ b/programs/wat2wasm/assets/add.wat
@@ -0,0 +1,8 @@
+(module
+  (func $add (param $x i32) (param $y i32) (result i32)
+    get_local $x
+    get_local $y
+    i32.add
+  )
+  (export "add" (func $add))
+)
diff --git a/programs/wat2wasm/src/main.rs b/programs/wat2wasm/src/main.rs
new file mode 100644
index 0000000..14e9ba5
--- /dev/null
+++ b/programs/wat2wasm/src/main.rs
@@ -0,0 +1,26 @@
+pub mod tokenizer;
+
+use std::fs;
+
+use logos::Logos;
+
+use crate::tokenizer::Token;
+
+fn main() {
+    // Read the contents of the file into a string
+    let contents =
+        fs::read_to_string("programs/wat2wasm/assets/add.wat").expect("Failed to read file");
+
+    let mut lex = Token::lexer(&contents);
+    for toke in lex {
+        println!("{:?}", toke);
+    }
+}
+
+#[non_exhaustive]
+pub enum WasmType {
+    I32,
+    I64,
+    F32,
+    F64,
+}
diff --git a/programs/wat2wasm/src/tokenizer/mod.rs b/programs/wat2wasm/src/tokenizer/mod.rs
new file mode 100644
index 0000000..36fee4c
--- /dev/null
+++ b/programs/wat2wasm/src/tokenizer/mod.rs
@@ -0,0 +1,50 @@
+use logos::Logos;
+
+#[derive(Logos, Debug, PartialEq)]
+pub enum Token {
+    #[token(".")]
+    Period,
+
+    // Or regular expressions.
+    #[token("i32")]
+    Int32,
+
+    #[token("(")]
+    RightParen,
+
+    #[token(")")]
+    LeftParen,
+
+    #[token("add")]
+    AddOp,
+
+    #[token("func")]
+    FuncIden,
+    #[token("export")]
+    Export,
+    #[token("module")]
+    Module,
+
+    #[token("param")]
+    Param,
+
+    #[token("result")]
+    Result,
+
+    #[regex("get_local")]
+    GetLocal,
+
+    #[regex(r"\$[a-zA-Z]+")]
+    FunctionName,
+
+    #[regex(r##""[a-zA-Z]+""##)]
+    WasmString,
+
+    // Logos requires one token variant to handle errors,
+    // it can be named anything you wish.
+    #[error]
+    // We can also use this variant to define whitespace,
+    // or any other matches we wish to skip.
+    #[regex(r"[ \t\n\f]+", logos::skip)]
+    Error,
+}