From ca33e5f0c5cc3c09d05374fc6782b9c1b04d35ce Mon Sep 17 00:00:00 2001
From: nils <48135649+Nilstrieb@users.noreply.github.com>
Date: Tue, 21 Jun 2022 09:04:00 +0200
Subject: [PATCH] lex lex

---
 Cargo.lock          |  11 +++
 Cargo.toml          |   3 +
 parser/src/lexer.rs | 214 ++++++++++++++++++++++++++++++++++++++++++++
 parser/src/lib.rs   |  15 +---
 4 files changed, 230 insertions(+), 13 deletions(-)
 create mode 100644 Cargo.lock
 create mode 100644 parser/src/lexer.rs

diff --git a/Cargo.lock b/Cargo.lock
new file mode 100644
index 0000000..cb515fb
--- /dev/null
+++ b/Cargo.lock
@@ -0,0 +1,11 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 3
+
+[[package]]
+name = "parser"
+version = "0.1.0"
+
+[[package]]
+name = "uwuc"
+version = "0.1.0"
diff --git a/Cargo.toml b/Cargo.toml
index bc59071..e50bf1a 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -1,3 +1,6 @@
+[workspace]
+members = [".", "parser"]
+
 [package]
 name = "uwuc"
 version = "0.1.0"
diff --git a/parser/src/lexer.rs b/parser/src/lexer.rs
new file mode 100644
index 0000000..8ed2b36
--- /dev/null
+++ b/parser/src/lexer.rs
@@ -0,0 +1,214 @@
+//! Contrary to popular belief, Dennis Ritchie did not invent the C grammar.
+//! The C grammar was brought to Dennis Ritchie by a demon in hos worst dreams
+
+pub enum PToken {
+    HeaderName(Vec<u8>),
+    Identifier(Vec<u8>),
+    PpNumber(Vec<u8>),
+    CharConstant,
+    StringLiteral(Vec<u8>),
+    Punctuator(Punctuator),
+    OtherNonWs(u8),
+    Error,
+}
+
+pub enum Token {
+    Keyword(Keyword),
+    Identifier(),
+    Constant(),
+    StringLiteral(),
+    Punctuator(Punctuator),
+}
+
+pub enum Keyword {}
+
+pub enum Constant {
+    Integer(i64),
+}
+
+pub enum Punctuator {
+    /// [   <:
+    BracketOpen,
+    /// ]   :>
+    BracketClose,
+    /// (
+    ParenOpen,
+    /// )
+    ParenClose,
+    /// {   <%
+    BraceOpen,
+    /// }   %>
+    BraceClose,
+    /// .
+    Dot,
+    /// ->
+    Arrow,
+    /// ++
+    PlusPlus,
+    /// --
+    MinusMinus,
+    /// &
+    Ampersand,
+    /// *
+    Asterisk,
+    /// +
+    Plus,
+    /// -
+    Minus,
+    /// ~
+    Tilde,
+    /// ! 🔫
+    Bang,
+    //// %
+    Percent,
+    /// <<
+    LeftLeftChevron,
+    /// >>
+    RightRightChevron,
+    /// <
+    LeftChevron,
+    /// >
+    RightChevron,
+    /// <=
+    LeftChevronEqual,
+    /// >=
+    RightChevronEqual,
+    /// ==
+    EqualEqual,
+    /// !=
+    BangEqual,
+    /// ^
+    Caret,
+    /// |
+    Pipe,
+    /// &&
+    AmpersandAmpersand,
+    /// ||
+    PipePipe,
+    /// ?
+    QuestionMark,
+    /// :
+    Colon,
+    /// ;
+    Semicolon,
+    /// ...
+    DotDotDot,
+    /// =
+    Equal,
+    /// *=
+    AsteriskEqual,
+    /// /=
+    SlashEqual,
+    /// %=
+    PercentEqual,
+    /// +=
+    PlusEqual,
+    /// -=
+    MinusEqual,
+    /// <<=
+    LeftLeftChevronEqual,
+    /// >>=
+    RightRightChevronEqual,
+    /// &=
+    AmspersandEqual,
+    /// ^=
+    CaretEqual,
+    /// |=
+    PipeEqual,
+    /// ,
+    Comman,
+    /// #   %:
+    Hash,
+    /// ##   %:%:
+    HashHash,
+}
+
+struct PLexer<I>
+where
+    I: Iterator<Item = u8>,
+{
+    src: std::iter::Peekable<I>,
+}
+
+impl<I> PLexer<I>
+where
+    I: Iterator<Item = u8>,
+{
+    /// 6.4.2 Identifiers
+    /// TODO: 6.4.3 Universal character names
+    fn identifier(&mut self, c: u8) -> PToken {
+        let mut ident = vec![c];
+
+        while let Some(&c) = self.src.peek() {
+            if let b'a'..=b'z' | b'A'..=b'Z' | b'_' | b'0'..=b'9' = c {
+                self.src.next();
+                ident.push(c);
+            } else {
+                break;
+            }
+        }
+
+        PToken::Identifier(ident)
+    }
+
+    /// 6.4.8 Preprocessing numbers
+    fn number(&mut self, c: u8) -> PToken {
+        let mut number = vec![c];
+
+        while let Some(&c) = self.src.peek() {
+            if let b'0'..=b'9' = c {
+                self.src.next();
+                number.push(c);
+            } else {
+                break;
+            }
+        }
+
+        PToken::PpNumber(number)
+    }
+
+    /// 6.4.5 String literals
+    fn string_literal(&mut self) -> PToken {
+        let mut string = Vec::new();
+
+        while let c @ b'"' = {
+            match self.src.next() {
+                Some(next) => next,
+                None => return PToken::Error,
+            }
+        } {
+            string.push(c);
+        }
+        PToken::StringLiteral(string)
+    }
+}
+
+impl<'src, I> Iterator for PLexer<I>
+where
+    I: Iterator<Item = u8>,
+{
+    type Item = PToken;
+
+    /// preprocessing-token:
+    ///   header-name
+    ///   identifier
+    ///   pp-number
+    ///   character-constant
+    ///   string-literal
+    ///   punctuator
+    ///   each non-white-space character that cannot be one of the above
+    fn next(&mut self) -> Option<Self::Item> {
+        loop {
+            match self.src.next()? {
+                c @ (b'a'..=b'z' | b'A'..=b'Z' | b'_') => {
+                    return Some(self.identifier(c));
+                }
+                c @ b'0'..=b'9' => return Some(self.number(c)),
+                b'"' => return Some(self.string_literal()),
+                b'[' => return Some(PToken::Punctuator(Punctuator::BraceOpen)),
+                c if c.is_ascii_whitespace() => {}
+                c => return Some(PToken::OtherNonWs(c)),
+            }
+        }
+    }
+}
diff --git a/parser/src/lib.rs b/parser/src/lib.rs
index 7d12d9a..38f258a 100644
--- a/parser/src/lib.rs
+++ b/parser/src/lib.rs
@@ -1,14 +1,3 @@
-pub fn add(left: usize, right: usize) -> usize {
-    left + right
-}
+#![allow(dead_code)]
 
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn it_works() {
-        let result = add(2, 2);
-        assert_eq!(result, 4);
-    }
-}
+mod lexer;