From ba409b9be0634dad2ec0f18008f0902438eac9c0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aodhnait=20=C3=89ta=C3=ADn?= <aodhneine@protonmail.ch>
Date: Sat, 22 May 2021 21:45:42 +0100
Subject: [PATCH] Add simple expression parsing

Currently can only parse addition in a right-associative way, i.e.
  1 + 2 + 3 => 1 + (2 + 3).

The reason why are we using raw pointers in a form of OffsetStr struct
is because I don't think there is a way to prove to Rust compiler that
tokens the parse_next function returns are always valid references to
the TokenStream source string. Therefore we simply have to bypass the
borrow checker and handle this ourselves.
---
 src/main.rs | 164 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 164 insertions(+)

diff --git a/src/main.rs b/src/main.rs
index 5446f27..75bc284 100644
--- a/src/main.rs
+++ b/src/main.rs
@@ -65,4 +65,168 @@ fn main() {
 
 	let path = path.unwrap();
 	eprintln!("compiling `{}`", path);
+
+	#[allow(non_upper_case_globals)] const source: &'static str = "23 + 21;";
+	let mut tokens = TokenStream::from(source);
+	let expr = parse_expression(&mut tokens);
+	eprintln!("{:?}", expr);
+}
+
+#[derive(Debug)]
+enum Expression {
+	Literal(Token),
+	Binary(Token, Box<Expression>, Box<Expression>),
+}
+
+fn parse_expression<'a>(tokens: &'a mut TokenStream<'a>) -> Option<Expression> {
+	let lhs = match tokens.next()? {
+		token @ Token::IntegerLiteral(_) => Expression::Literal(token),
+		_ => return None,
+	};
+
+	return match tokens.next()? {
+		operator @ Token::Plus => {
+			let rhs = parse_expression(tokens)?;
+
+			Some(Expression::Binary(operator, box lhs, box rhs))
+		},
+		// If it's not a valid operator, then caller can get rest of the input in the token stream
+		// it has provided to us.
+		_ => Some(lhs),
+	};
+}
+
+struct TokenStream<'a> {
+	source: &'a str,
+	cursor: usize,
+}
+
+impl<'a> TokenStream<'a> {
+	pub fn from(source: &'a str) -> Self {
+		return Self {
+			source,
+			cursor: 0,
+		};
+	}
+
+	#[inline(always)]
+	fn chars(&'a self) -> std::str::Chars<'a> {
+		return self.source[self.cursor..].chars();
+	}
+
+	pub fn skip_whitespace(&mut self) {
+		let mut chars = self.chars().peekable();
+		let mut length = 0;
+		
+		loop {
+			match match chars.peek() {
+				None => return,
+				Some(c) => c
+			} {
+				c if c.is_whitespace() => {
+					length += c.len_utf8();
+					chars.next();
+				},
+				_ => break,
+			};
+		};
+
+		self.cursor += length;
+	}
+
+	pub fn parse_next(&mut self) -> Option<Token> {
+		let mut chars = self.chars();
+		
+		let token = match chars.next()? {
+			'+' => Token::Plus,
+			';' => Token::Semicolon,
+			c if c.is_numeric() => {
+				let start = self.cursor;
+				let mut length = c.len_utf8();
+
+				loop {
+					match chars.next()? {
+						c if c.is_numeric() => length += c.len_utf8(),
+						_ => break,
+					};
+				};
+
+				Token::IntegerLiteral(OffsetStr::from(&self.source[start..start + length]))
+			},
+			c => todo!("character unsupported: `{}`", natural_char_representation(c)),
+		};
+
+		self.cursor += token.len();
+		return Some(token);
+	}
+
+	pub fn next(&mut self) -> Option<Token> {
+		self.skip_whitespace();
+		return self.parse_next();
+	}
+}
+
+fn natural_char_representation(c: char) -> char {
+	return match c {
+		' ' => '␣',
+		'\t' => '→',
+		'\n' => '⏎',
+		_ => c,
+	};
+}
+
+#[derive(Copy, Clone)]
+struct OffsetStr {
+	data: *const u8,
+	length: usize,
+}
+
+impl std::fmt::Display for OffsetStr {
+	fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+		return write!(f, "{}", std::str::from_utf8(unsafe { std::slice::from_raw_parts(self.data, self.length) }).unwrap());
+	}
+}
+
+impl std::fmt::Debug for OffsetStr {
+	fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+		return write!(f, r#""{}""#, self);
+	}
+}
+
+impl OffsetStr {
+	pub fn from(s: &str) -> Self {
+		return Self {
+			data: s.as_ptr(),
+			length: s.len(),
+		};
+	}
+}
+
+#[derive(Debug, Copy, Clone)]
+enum Token {
+	Plus,
+	Semicolon,
+	IntegerLiteral(OffsetStr),
+}
+
+impl std::fmt::Display for Token {
+	fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+		return match self {
+			token @ Token::IntegerLiteral(_) => write!(f, "{}", token),
+			token => write!(f, "{}", match token {
+				Token::Plus => "+",
+				Token::Semicolon => ";",
+				_ => unreachable!(),
+			}),
+		};
+	}
+}
+
+impl Token {
+	pub fn len(&self) -> usize {
+		return match self {
+			Token::Plus | Token::Semicolon => 1,
+			Token::IntegerLiteral(i) => i.length,
+		};
+	}
 }