about summary refs log tree commit diff
path: root/src
diff options
context:
space:
mode:
Diffstat (limited to 'src')
-rw-r--r--src/lex/lexer.rs125
-rw-r--r--src/lex/mod.rs2
-rw-r--r--src/lex/token.rs29
-rw-r--r--src/main.rs12
4 files changed, 168 insertions, 0 deletions
diff --git a/src/lex/lexer.rs b/src/lex/lexer.rs
new file mode 100644
index 0000000..e2ac0f4
--- /dev/null
+++ b/src/lex/lexer.rs
@@ -0,0 +1,125 @@
+use std::{iter::Peekable, str::Chars};
+
+use super::token::{Location, Token, TokenVariant};
+
+pub struct Lexer<'source> {
+    location: Location,
+    chars: Peekable<Chars<'source>>,
+    done: bool,
+}
+
+impl Iterator for Lexer<'_> {
+    type Item = Token;
+
+    fn next(&mut self) -> Option<Self::Item> {
+        if self.done {
+            return None;
+        }
+
+        if let None = self.chars.peek() {
+            self.done = true;
+            return Some(Token {
+                location: self.location,
+                variant: TokenVariant::Eof,
+            });
+        }
+
+        self.skip_whitespace();
+
+        let c = *self.chars.peek()?;
+
+        let token = if c.is_numeric() {
+            self.number()
+        } else if c == '+' {
+            self.char_token(TokenVariant::OpPlus)
+        } else if c == '-' {
+            self.char_token(TokenVariant::OpMinus)
+        } else if c == '*' {
+            self.char_token(TokenVariant::OpStar)
+        } else if c == '/' {
+            self.char_token(TokenVariant::OpSlash)
+        } else if c == '!' {
+            self.char_token(TokenVariant::OpNot)
+        } else if c == '(' {
+            self.char_token(TokenVariant::GroupOpen)
+        } else if c == ')' {
+            self.char_token(TokenVariant::GroupClose)
+        } else {
+            self.char_token(TokenVariant::Unknown(c))
+        };
+
+        Some(token)
+    }
+}
+
+impl<'s> Lexer<'s> {
+    pub fn new(source: &'s str) -> Self {
+        Lexer {
+            location: Location { col: 0, row: 0 },
+            chars: source.chars().peekable(),
+            done: false,
+        }
+    }
+
+    fn advance(&mut self) -> Option<char> {
+        let next = self.chars.next();
+        if let Some(c) = next {
+            if c == '\n' {
+                self.location.row += 1;
+                self.location.col = 0;
+            } else {
+                self.location.row += 1;
+            }
+        }
+
+        next
+    }
+
+    fn skip_whitespace(&mut self) {
+        while self
+            .chars
+            .peek()
+            .map_or(false, |x| x.is_whitespace() && *x != '\n')
+        {
+            self.advance();
+        }
+    }
+
+    fn char_token(&mut self, variant: TokenVariant) -> Token {
+        let token = Token {
+            location: self.location,
+            variant,
+        };
+        self.advance();
+        token
+    }
+
+    fn number(&mut self) -> Token {
+        let location = self.location;
+
+        let mut is_integer = true;
+        let mut buffer = String::new();
+
+        while self
+            .chars
+            .peek()
+            .map_or(false, |&c| c.is_numeric() || c == '.')
+        {
+            let c = self.advance().unwrap();
+            if c == '.' {
+                is_integer = false;
+            }
+            buffer.push(c);
+        }
+
+        let variant = if is_integer {
+            let int = buffer.parse().expect("Failed lexing integer token.");
+            TokenVariant::Int(int)
+        } else {
+            let float = buffer.parse().expect("Failed lexing float token.");
+            TokenVariant::Float(float)
+        };
+
+        Token { location, variant }
+    }
+}
diff --git a/src/lex/mod.rs b/src/lex/mod.rs
new file mode 100644
index 0000000..f785280
--- /dev/null
+++ b/src/lex/mod.rs
@@ -0,0 +1,2 @@
+pub mod lexer;
+pub mod token;
\ No newline at end of file
diff --git a/src/lex/token.rs b/src/lex/token.rs
new file mode 100644
index 0000000..a43cf0f
--- /dev/null
+++ b/src/lex/token.rs
@@ -0,0 +1,29 @@
+#[derive(Clone, Copy, Debug)]
+pub struct Location {
+    pub col: usize,
+    pub row: usize,
+}
+
+#[derive(Clone, Debug)]
+pub struct Token {
+    pub location: Location,
+    pub variant: TokenVariant,
+}
+
+#[derive(Clone, Debug)]
+pub enum TokenVariant {
+    OpPlus,
+    OpMinus,
+    OpStar,
+    OpSlash,
+    OpNot,
+
+    GroupOpen,
+    GroupClose,
+
+    Int(u32),
+    Float(f32),
+
+    Unknown(char),
+    Eof,
+}
diff --git a/src/main.rs b/src/main.rs
new file mode 100644
index 0000000..3b23d8e
--- /dev/null
+++ b/src/main.rs
@@ -0,0 +1,12 @@
+mod lex;
+
+use lex::lexer::Lexer;
+
+fn main() {
+    let source = "1 + 2";
+    let lexer = Lexer::new(source);
+
+    for token in lexer {
+        println!("{:?}", token);
+    }
+}