feat(furc): implement lexer

furc/include/furc/front/lexer.hpp

@@ -0,0 +1,46 @@
+#ifndef FURC_FRONT_LEXER_HPP
+#define FURC_FRONT_LEXER_HPP
+
+#include "furc/front/token.hpp"
+
+#include <cstddef>
+#include <optional>
+#include <string_view>
+
+namespace furc {
+
+class lexer {
+public:
+    lexer(std::string_view filepath, std::string_view content)
+      : m_filepath(filepath), m_content(content) {}
+
+    ~lexer() = default;
+
+    lexer(lexer&&) noexcept            = default;
+    lexer& operator=(lexer&&) noexcept = default;
+
+    lexer(const lexer&)            = delete;
+    lexer& operator=(const lexer&) = delete;
+public:
+    token next_token();
+    token peek_token();
+    token skip_token();
+private:
+    void           next();
+    constexpr char get(std::size_t offset = 0) const;
+    void           skip_spaces();
+
+    constexpr token::location location() const;
+private:
+    std::string_view m_filepath;
+    std::string_view m_content;
+    std::size_t      m_cursor    = 0;
+    std::size_t      m_row       = 0;
+    std::size_t      m_lineStart = 0;
+
+    std::optional<token> m_peekToken;
+};
+
+} // namespace furc
+
+#endif // FURC_FRONT_LEXER_HPP

furc/include/furc/front/token.hpp

@@ -3,6 +3,7 @@
 
 #include <cstddef>
 #include <cstdint>
+#include <ostream>
 #include <string_view>
 
 namespace furc {
@@ -12,6 +13,7 @@ struct token {
         Identifier = 0,
         Integer,
         String,
+        Char,
 
         LParen,    /**< `(` */
         RParen,    /**< `)` */
@@ -87,6 +89,7 @@ struct token {
 
         // Errors:
         UnexpectedCharacter,
+        UnexpectedEOF,
         EndOfFile,
     } type;
     union value {
@@ -110,15 +113,90 @@ struct token {
         value.integer = integer;
     }
 
-    token(location loc, std::string_view string)
-      : loc(loc), type(String) {
+    token(location loc, enum type type, std::string_view string)
+      : loc(loc), type(type) {
         value.string = string;
     }
 
-    token(location loc, char character)
-      : loc(loc), type(UnexpectedCharacter) {
+    token(location loc, enum type type, char character)
+      : loc(loc), type(type) {
         value.character = character;
     }
+
+    friend std::ostream& operator<<(std::ostream& os, const token& token) {
+        switch (token.type) {
+        case token::Identifier: return os << token.value.string;
+        case token::String: return os << '"' << token.value.string << '"';
+        case token::Char: return os << '\'' << token.value.character << '\'';
+        case token::Integer: return os << token.value.integer;
+        case token::LParen: return os << "(";
+        case token::RParen: return os << ")";
+        case token::LBrace: return os << "{";
+        case token::RBrace: return os << "}";
+        case token::LBracket: return os << "[";
+        case token::RBracket: return os << "]";
+        case token::Semicolon: return os << ";";
+        case token::Colon: return os << ":";
+        case token::Comma: return os << ",";
+        case token::Dot: return os << ".";
+        case token::Plus: return os << "+";
+        case token::Minus: return os << "-";
+        case token::Star: return os << "*";
+        case token::Slash: return os << "/";
+        case token::Percent: return os << "%";
+        case token::Ampersand: return os << "&";
+        case token::Pipe: return os << "|";
+        case token::Hat: return os << "^";
+        case token::DblAmpersand: return os << "&&";
+        case token::DblPipe: return os << "||";
+        case token::DblPlus: return os << "++";
+        case token::DblMinus: return os << "--";
+        case token::ExMark: return os << "!";
+        case token::CatEars: return os << "^^";
+        case token::Equals: return os << "=";
+        case token::PlusEquals: return os << "+=";
+        case token::MinusEquals: return os << "-=";
+        case token::StarEquals: return os << "*=";
+        case token::SlashEquals: return os << "/=";
+        case token::PercentEquals: return os << "%=";
+        case token::AmpersandEquals: return os << "&=";
+        case token::PipeEquals: return os << "|=";
+        case token::HatEquals: return os << "^=";
+        case token::DblEquals: return os << "==";
+        case token::ExEquals: return os << "!=";
+        case token::LessThan: return os << "<";
+        case token::LessEquals: return os << "<=";
+        case token::GreaterThan: return os << ">";
+        case token::GreaterEquals: return os << ">=";
+        case token::SlimArrow: return os << "->";
+        case token::FatArrow: return os << "=>";
+        case token::Monkey: return os << "@";
+        case token::Sha256: return os << "#";
+        case token::Func: return os << "func";
+        case token::Return: return os << "return";
+        case token::If: return os << "if";
+        case token::Else: return os << "else";
+        case token::While: return os << "while";
+        case token::Public: return os << "public";
+        case token::Private: return os << "private";
+        case token::Pointerof: return os << "pointerof";
+        case token::Sizeof: return os << "sizeof";
+        case token::Lengthof: return os << "lengthof";
+        case token::S8: return os << "s8";
+        case token::U8: return os << "u8";
+        case token::S16: return os << "s16";
+        case token::U16: return os << "u16";
+        case token::S32: return os << "s32";
+        case token::U32: return os << "u32";
+        case token::S64: return os << "s64";
+        case token::U64: return os << "u64";
+        case token::UnexpectedCharacter: return os << "Unexpected character `" << token.value.character << "`";
+        case token::UnexpectedEOF: return os << "Unexpected End Of File";
+        case token::EndOfFile: return os << "End Of File";
+        }
+
+        return os;
+    }
 };
 
 using token_t = enum token::type;