Fixed bugs in Lexer

Also added basic math operators

Lexer/src/Lexer.cpp

@@ -12,7 +12,6 @@ namespace LX
 {
 	// Local macros cause im lazy //
 
-	#define ITERATE index++; continue
 	#define TOKEN_CASE(type) case type: return #type;
 
 	static std::string ToString(Token::TokenType type)
@@ -27,22 +26,47 @@ namespace LX
 			TOKEN_CASE(Token::ELSE);
 			TOKEN_CASE(Token::ELIF);
 			TOKEN_CASE(Token::FUNCTION);
+			TOKEN_CASE(Token::ADD);
+			TOKEN_CASE(Token::SUB);
+			TOKEN_CASE(Token::MUL);
+			TOKEN_CASE(Token::DIV);
 
 			default:
-				return std::string("Unknown: " + (short)type);
+				return "Unknown: " + std::to_string(type);
 		}
 	}
 
 	static const std::unordered_map<std::string, Token::TokenType> keywords =
 	{
-		{ "for", Token::FOR },
+		{ "for"			, Token::FOR		},
-		{ "while", Token::WHILE },
+		{ "while"		, Token::WHILE		},
-		{ "if", Token::IF },
+		{ "if"			, Token::IF			},
-		{ "else", Token::ELSE },
+		{ "else"		, Token::ELSE		},
-		{ "elif", Token::ELIF },
+		{ "elif"		, Token::ELIF		},
-		{ "func", Token::FUNCTION },
+		{ "func"		, Token::FUNCTION	},
 	};
 
+	static const std::unordered_map<char, Token::TokenType> operators =
+	{
+		{ '+', Token::ADD },
+		{ '-', Token::SUB },
+		{ '*', Token::MUL },
+		{ '/', Token::DIV }
+	};
+
+	static void TokenizeWord(const std::string& word, std::vector<Token>& tokens)
+	{
+		if (auto keyword = keywords.find(word); keyword != keywords.end())
+		{
+			tokens.push_back({ keyword->second, word });
+		}
+
+		else
+		{
+			tokens.push_back({ Token::IDENTIFIER, word });
+		}
+	}
+
 	const std::vector<Token> LX::LexicalAnalyze(std::ifstream& src, std::ofstream* log)
 	{
 		// Logs the start of the lexical analysis
@@ -69,6 +93,7 @@ namespace LX
 		std::streamsize startOfWord = 0;
 		std::streamsize startOfStringLiteral = 0;
 
+		bool isAlpha = false;
 		bool inComment = false;
 		bool inStringLiteral = false;
 		bool wasLastCharAlpha = false;
@@ -79,6 +104,9 @@ namespace LX
 			// Stores the current character for easy access
 			const char current = contents[index];
 
+			// Works out if the current character is alphabetic
+			isAlpha = (current >= 'a' && current <= 'z') || (current >= 'A' && current <= 'Z');
+
 			// Updates string literal tracker and skips over rest if in a string literal
 			if (current == '"')
 			{
@@ -88,7 +116,6 @@ namespace LX
 					// Updates the neccesarry trackers
 					startOfStringLiteral = index + 1;
 					inStringLiteral = true;
-					ITERATE;
 				}
 
 				// End of string literal
@@ -100,78 +127,79 @@ namespace LX
 
 					// Updates trackers
 					inStringLiteral = false;
-					ITERATE;
 				}
 			}
 
 			// Skips over rest if within a string literal
-			if (inStringLiteral) { ITERATE; }
+			else if (inStringLiteral);
 
 			// Updates comment state
-			if (current == '#')
+			else if (current == '#')
 			{
 				inComment = !inComment;
-
-				ITERATE;
 			}
 
 			// Skips over if within a comment
-			if (inComment) { ITERATE; }
+			else if (inComment);
 
-			// Works out if the current character is alphabetic
-			bool isAlpha = (current >= 'a' && current <= 'z') || (current >= 'A' && current <= 'Z');
-
-			if (isAlpha == true)
-			{
 			// Start of a word
-				if (wasLastCharAlpha == false)
+			else if (isAlpha == true && wasLastCharAlpha == false)
 			{
-					// Updates trackers
-					wasLastCharAlpha = true;
 				startOfWord = index;
 			}
 
-				ITERATE;
+			// During a word
+			else if (isAlpha == true);
+
+			// Operators (+, -, /, *)
+			else if (auto op = operators.find(current); op != operators.end())
+			{
+				tokens.push_back({ op->second, "" });
+			}
+
+			// If it is here and not whitespace that means it's an invalid character
+			else if (current == ' ' || current == '\t' || current == '\r' || current == '\n');
+
+			else
+			{
+				// Throws an error to alert the user
+				throw InvalidCharInSource(index, current);
 			}
 
 			// End of a word
 			if (isAlpha == false && wasLastCharAlpha == true)
 			{
-				// Adds the word token to the token vector
+				TokenizeWord({ contents.data() + startOfWord, (unsigned __int64)(index - startOfWord) }, tokens);
-				std::string word(contents.data() + startOfWord, index - startOfWord);
-
-				if (auto keyword = keywords.find(word); keyword != keywords.end())
-				{
-					tokens.push_back({ keyword->second, word });
 			}
 
-				else
+			// Updates trackers //
-				{
-					tokens.push_back({ Token::IDENTIFIER, word });
-				}
-			}
 
-			// Operators will eventually go here
+			index++;
-
-			// If it is here and not whitespace that means it's an invalid character
-			if (current == ' ' || current == '\t' || current == '\r' || current == '\n')
-			{
-				// Updates trackers
 			wasLastCharAlpha = isAlpha;
-				ITERATE;
 		}
 
-			// Throws an error to alert the user
+		// Words are only added the iteration after they end so it has to be done like this //
-			throw InvalidCharInSource(index, current);
+		if (wasLastCharAlpha && isAlpha)
+		{
+			std::string word(contents.data() + startOfWord, index - startOfWord);
+			TokenizeWord(word, tokens);
 		}
 
 		// Logs the tokens if logging is on //
 		if (log != nullptr)
 		{
 			for (auto& token : tokens)
+			{
+				if (token.contents.empty() == false)
 				{
 					SafeLog(log, ToString(token.type), ":\t", token.contents);
 				}
+
+				else
+				{
+					SafeLog(log, ToString(token.type));
+				}
+			}
 		}
 
 		// Shrinks the vector down to minimum size before returning to avoid excess memory being allocated

Main.cpp

@@ -74,24 +74,32 @@ int main(int argc, char** argv)
 	{
 		// Tells the user the output file could not be opened
 		std::cout << "\nCould not open/create {" << argv[2] << "}\n";
+
+		return 3;
 	}
 
 	catch (LX::InvalidCharInSource& e)
 	{
 		//
 		std::cout << "\nInvalid character found in source file: {" << e.invalid << "} at index: " << e.index << "\n";
+
+		return 4;
 	}
 
 	catch (std::exception& e)
 	{
 		// Prints the std exception to the console
 		std::cout << "\nAn error occured:\n" << e.what() << std::endl;
+
+		return 5;
 	}
 
 	catch (...)
 	{
 		// Tells the user if an error has happened
 		std::cout << "\nAn Error occured\n";
+
+		return 6;
 	}
 
 	return 0;

build-test/Log.txt

@@ -3,7 +3,9 @@
 Started lexing file
 -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
 
-Token::FUNCTION:	func
+Token::IDENTIFIER:	int
 Token::IDENTIFIER:	main
-Token::IDENTIFIER:	print
+Token::IDENTIFIER:	return
-Token::STRING_LITERAL:	Hello World!
+Token::IDENTIFIER:	a
+Token::ADD
+Token::IDENTIFIER:	b

build-test/main.lx

@@ -1,2 +1,2 @@
-func main
+int main
-    print "Hello World!"
+    return a## + b

common/Lexer.h

@@ -40,6 +40,11 @@ namespace LX
 
 			STRING_LITERAL,
 			IDENTIFIER,
+			RETURN,
+
+			// Operators //
+
+			ADD, SUB, MUL, DIV,
 
 			// Keywords //