From 0f7999cc0f4efb1b2c84dc544ded9d8315f5aa2b Mon Sep 17 00:00:00 2001
From: Nilstrieb <nilstrieb@gmail.com>
Date: Sun, 3 Oct 2021 21:22:40 +0200
Subject: [PATCH] started lexer

---
 README.md    | 142 +++++++++++++++++++++++++++++++++++++++++++++++++
 src/lex.rs   | 145 +++++++++++++++++++++++++++++++++++++++++++++++++++
 src/lib.rs   |   8 +++
 src/parse.rs |   0
 4 files changed, 295 insertions(+)
 create mode 100644 README.md
 create mode 100644 src/lex.rs
 create mode 100644 src/lib.rs
 create mode 100644 src/parse.rs

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..86094b7
--- /dev/null
+++ b/README.md
@@ -0,0 +1,142 @@
+_ is a small embeddable scripting language
+
+_ is inspired by Javascript, Lox, Lua, Python, Rust and more
+
+# Reference
+
+## Overview
+
+Declaring variables using `let`
+
+```
+let hello = 4
+```
+
+Semicolons are not needed
+
+```
+let test = 5
+let another = 4
+```
+
+The language has strings, numbers, arrays, objects and null and booleans
+
+```
+let string = "hallo"
+let number = 4
+let array = []
+let object = {}
+let _null = null
+let bool = true
+```
+
+You access properties on objects using `.`
+
+```
+let obj = {}
+obj.hi = "hi!"
+```
+
+Functions are first class
+
+```
+let obj = {}
+obj.hello = helloFn
+obj.hello()
+```
+
+Functions are declared using `fn`
+
+```
+fn greet(name) {
+    return "hello, " + name
+}
+```
+
+Comments using `#`
+```
+# hi!
+```
+
+There are many native functions, that can easily be customized and added/removed by the host
+
+```
+# rocket game
+turnRocketLeft(29)
+turnRocketRight(32)
+
+# chat bot
+message.respond("hi")
+
+# dangerous http requests
+fn callback(html) {
+    print(html)
+}
+fetch("https://github.com/Nilstrieb", callback);
+```
+
+Basic arithmetic and boolean logic is available
+
+```
+let a = 5
+let b = 5
+print(a + b / b * b - a % b)
+print(true and false or false or true and false)
+```
+
+Loops and conditionals
+
+```
+let x = true
+if x {
+    print("true!")
+} else {
+    print("false :(")
+}
+
+loop {
+    while 1 > 5 {
+        print("yeet")
+        break
+    }
+    # no for loops for now, but will be added (probably like python)
+}
+```
+
+_ is dynamically and *strongly* typed
+
+## Detail
+
+### Reserved Keywords
+
+#### Statements
+`fn`
+`let`
+`if`
+`else`
+`loop`
+`while`
+`for`
+
+#### Values
+`true`
+`false`
+`null`
+
+#### Operators
+`not`
+`and`
+`or`
+
+### Operators
+`==`
+`>=`
+`>`
+`<=`
+`<`
+`!=`
+`+`
+`-`
+`*`
+`/`
+`%`
\ No newline at end of file
diff --git a/src/lex.rs b/src/lex.rs
new file mode 100644
index 0000000..709b567
--- /dev/null
+++ b/src/lex.rs
@@ -0,0 +1,145 @@
+#![allow(dead_code)]
+
+use std::iter::Peekable;
+use std::str::CharIndices;
+
+#[derive(Debug, Copy, Clone, PartialOrd, PartialEq, Ord, Eq, Hash)]
+struct Span(usize);
+
+#[derive(Debug, Clone)]
+pub struct Token<'code> {
+    span: Span,
+    kind: TokenType<'code>,
+}
+
+#[derive(Debug, Clone, PartialEq)]
+pub enum TokenType<'code> {
+    // keywords
+    Let,
+    Fn,
+    If,
+    Else,
+    Loop,
+    While,
+    For,
+    True,
+    False,
+    Null,
+    And,
+    Or,
+    Not,
+    // literals
+    String(&'code str),
+    Number(f64),
+    // ident
+    Ident(&'code str),
+    // punctuation
+    /// +
+    Plus,
+    /// -
+    Minus,
+    /// *
+    Asterisk,
+    /// /
+    Slash,
+    /// %
+    Percent,
+    /// {
+    BraceO,
+    /// }
+    BraceC,
+    /// [
+    BracketO,
+    /// ]
+    BracketC,
+    /// (
+    ParenO,
+    /// )
+    ParenC,
+    /// .
+    Dot,
+    /// ,
+    Comma,
+    // =
+    Equal,
+    /// ==
+    EqualEqual,
+    /// !=
+    BangEqual,
+    /// >
+    GreaterThan,
+    /// <
+    LessThan,
+    /// >=
+    GreaterThanEqual,
+    /// <=
+    LessThanEqual,
+}
+
+#[derive(Debug, Clone)]
+pub struct Lexer<'code> {
+    code: Peekable<CharIndices<'code>>,
+    state: LexState,
+}
+
+#[derive(Debug, Clone, PartialEq, Eq)]
+enum LexState {
+    Init,
+    StrLit(usize),
+    NumLit(usize),
+    Ident(usize),
+    Equal(usize),
+    Bang(usize),
+    GreaterThan(usize),
+    LessThan(usize),
+}
+
+impl<'code> Lexer<'code> {
+    pub fn lex(code: &'code str) -> Self {
+        Self {
+            code: code.char_indices().peekable(),
+            state: LexState::Init,
+        }
+    }
+
+    fn expect(&mut self, expected: char) -> bool {
+        self.code
+            .peek()
+            .map(|(_, char)| *char == expected)
+            .unwrap_or(false)
+    }
+}
+
+impl<'code> Iterator for Lexer<'code> {
+    type Item = Result<Token<'code>, LexError>;
+
+    fn next(&mut self) -> Option<Self::Item> {
+        loop {
+            match self.state {
+                LexState::Init => match self.code.next() {
+                    _ => {}
+                },
+                LexState::StrLit(_) => {}
+                LexState::NumLit(_) => {}
+                LexState::Ident(_) => {}
+                LexState::Equal(_) => {}
+                LexState::Bang(start) => {
+                    return if self.expect('=') {
+                        let _ = self.code.next();
+                        Some(Ok(Token {
+                            span: Span(start),
+                            kind: TokenType::BangEqual,
+                        }))
+                    } else {
+                        Some(Err(LexError))
+                    }
+                }
+                LexState::GreaterThan(_) => {}
+                LexState::LessThan(_) => {}
+            }
+        }
+    }
+}
+
+#[derive(Debug)]
+pub struct LexError;
diff --git a/src/lib.rs b/src/lib.rs
new file mode 100644
index 0000000..81f4f87
--- /dev/null
+++ b/src/lib.rs
@@ -0,0 +1,8 @@
+mod lex;
+mod parse;
+
+pub fn run_program(program: &str) {
+    let lexer = lex::Lexer::lex(program);
+    let tokens: Result<Vec<_>, _> = lexer.collect();
+    println!("{:#?}", tokens);
+}
diff --git a/src/parse.rs b/src/parse.rs
new file mode 100644
index 0000000..e69de29