started work on c compiler

2025-11-14 23:36:51 +00:00
parent 2582ad10fa
commit fd5b305576
10 changed files with 1870 additions and 1 deletions
@@ -0,0 +1,265 @@
+// ============================================================================
+// Token Types
+// ============================================================================
+
+#[derive(Debug, Clone, PartialEq)]
+pub enum TokenType {
+    // Keywords
+    Int,
+    If,
+    Else,
+    While,
+    Return,
+
+    // Identifiers and literals
+    Identifier(String),
+    Number(i32),
+
+    // Operators
+    Plus,
+    Minus,
+    Star,
+    Slash,
+    Assign,
+    Eq,
+    Ne,
+    Lt,
+    Gt,
+    Le,
+    Ge,
+
+    // Delimiters
+    LParen,
+    RParen,
+    LBrace,
+    RBrace,
+    Semicolon,
+    Comma,
+
+    Eof,
+}
+
+#[derive(Debug, Clone)]
+pub struct Token {
+    pub token_type: TokenType,
+    pub line: usize,
+    pub col: usize,
+}
+
+impl Token {
+    pub fn new(token_type: TokenType, line: usize, col: usize) -> Self {
+        Self {
+            token_type,
+            line,
+            col,
+        }
+    }
+}
+
+// ============================================================================
+// Lexer
+// ============================================================================
+
+pub struct Lexer {
+    source: Vec<char>,
+    pos: usize,
+    line: usize,
+    col: usize,
+}
+
+impl Lexer {
+    pub fn new(source: &str) -> Self {
+        Self {
+            source: source.chars().collect(),
+            pos: 0,
+            line: 1,
+            col: 1,
+        }
+    }
+
+    fn error(&self, msg: &str) -> String {
+        format!(
+            "Lexer error at line {}, col {}: {}",
+            self.line, self.col, msg
+        )
+    }
+
+    fn peek(&self, offset: usize) -> Option<char> {
+        self.source.get(self.pos + offset).copied()
+    }
+
+    fn advance(&mut self) -> Option<char> {
+        if self.pos >= self.source.len() {
+            return None;
+        }
+        let ch = self.source[self.pos];
+        self.pos += 1;
+        if ch == '\n' {
+            self.line += 1;
+            self.col = 1;
+        } else {
+            self.col += 1;
+        }
+        Some(ch)
+    }
+
+    fn skip_whitespace(&mut self) {
+        while let Some(ch) = self.peek(0) {
+            if ch.is_whitespace() {
+                self.advance();
+            } else {
+                break;
+            }
+        }
+    }
+
+    fn skip_comment(&mut self) {
+        if self.peek(0) == Some('/') && self.peek(1) == Some('/') {
+            while let Some(ch) = self.peek(0) {
+                if ch == '\n' {
+                    break;
+                }
+                self.advance();
+            }
+        }
+    }
+
+    fn read_number(&mut self) -> i32 {
+        let mut num_str = String::new();
+        while let Some(ch) = self.peek(0) {
+            if ch.is_ascii_digit() {
+                num_str.push(ch);
+                self.advance();
+            } else {
+                break;
+            }
+        }
+        num_str.parse().unwrap_or(0)
+    }
+
+    fn read_identifier(&mut self) -> String {
+        let mut ident = String::new();
+        while let Some(ch) = self.peek(0) {
+            if ch.is_alphanumeric() || ch == '_' {
+                ident.push(ch);
+                self.advance();
+            } else {
+                break;
+            }
+        }
+        ident
+    }
+
+    pub fn tokenize(&mut self) -> Result<Vec<Token>, String> {
+        let mut tokens = Vec::new();
+
+        loop {
+            self.skip_whitespace();
+            self.skip_comment();
+
+            if self.pos >= self.source.len() {
+                break;
+            }
+
+            let line = self.line;
+            let col = self.col;
+            let ch = self.peek(0).unwrap();
+
+            let token_type = if ch.is_ascii_digit() {
+                let num = self.read_number();
+                TokenType::Number(num)
+            } else if ch.is_alphabetic() || ch == '_' {
+                let ident = self.read_identifier();
+                match ident.as_str() {
+                    "int" => TokenType::Int,
+                    "if" => TokenType::If,
+                    "else" => TokenType::Else,
+                    "while" => TokenType::While,
+                    "return" => TokenType::Return,
+                    _ => TokenType::Identifier(ident),
+                }
+            } else {
+                match ch {
+                    '=' if self.peek(1) == Some('=') => {
+                        self.advance();
+                        self.advance();
+                        TokenType::Eq
+                    }
+                    '!' if self.peek(1) == Some('=') => {
+                        self.advance();
+                        self.advance();
+                        TokenType::Ne
+                    }
+                    '<' if self.peek(1) == Some('=') => {
+                        self.advance();
+                        self.advance();
+                        TokenType::Le
+                    }
+                    '>' if self.peek(1) == Some('=') => {
+                        self.advance();
+                        self.advance();
+                        TokenType::Ge
+                    }
+                    '+' => {
+                        self.advance();
+                        TokenType::Plus
+                    }
+                    '-' => {
+                        self.advance();
+                        TokenType::Minus
+                    }
+                    '*' => {
+                        self.advance();
+                        TokenType::Star
+                    }
+                    '/' => {
+                        self.advance();
+                        TokenType::Slash
+                    }
+                    '=' => {
+                        self.advance();
+                        TokenType::Assign
+                    }
+                    '<' => {
+                        self.advance();
+                        TokenType::Lt
+                    }
+                    '>' => {
+                        self.advance();
+                        TokenType::Gt
+                    }
+                    '(' => {
+                        self.advance();
+                        TokenType::LParen
+                    }
+                    ')' => {
+                        self.advance();
+                        TokenType::RParen
+                    }
+                    '{' => {
+                        self.advance();
+                        TokenType::LBrace
+                    }
+                    '}' => {
+                        self.advance();
+                        TokenType::RBrace
+                    }
+                    ';' => {
+                        self.advance();
+                        TokenType::Semicolon
+                    }
+                    ',' => {
+                        self.advance();
+                        TokenType::Comma
+                    }
+                    _ => return Err(self.error(&format!("Unexpected character: {}", ch))),
+                }
+            };
+
+            tokens.push(Token::new(token_type, line, col));
+        }
+
+        tokens.push(Token::new(TokenType::Eof, self.line, self.col));
+        Ok(tokens)
+    }
+}