slowly writing a lexer, literally not functional lmao

README.md

@@ -9,6 +9,7 @@
 But uhh that's the name of the VM itself, the name of the programming language I made is Sylt, named after the German island.
 
 To compile the VM for Linux: `gcc src/main.c src/vmbl.c src/exception.c src/file_utils.c -o vmbl -O3`
+To compile the SYLT compiler for Linux: `gcc src/sylt/main.c src/file_utils.c src/sylt/lexer.c -o sylt -O3`
 
 SASM and Sylt are written in Python for now as I'm too mentally challenged to write C code rn.
 

src/sylt/lexer.c

@@ -0,0 +1,87 @@
+#include "lexer.h"
+#include <string.h>
+#include <stdlib.h>
+#include <stdio,h>
+
+Lexer initLexer(char *source) {
+	Lexer newLexer = {
+		.source = source,
+		.position = -1,
+		.readPosition = 0,
+		.lineNumber = 1,
+		.currentChar = '\0'
+	};
+	return newLexer;
+}
+
+void readChar(Lexer *lexer) {
+	if (lexer->readPosition >= strlen(lexer->source))
+		lexer->currentChar = '\0';
+	else
+		lexer->currentChar = lexer->source[lexer->readPosition];
+
+	lexer->position = lexer->readPosition;
+	lexer->readPosition++;
+}
+
+void skipWhitespace(Lexer *lexer) {
+	switch (lexer->currentChar)
+	{
+	case ' ':
+	case '\t':
+	case '\n':
+	case '\r':
+		if (lexer->currentChar == '\n')
+			lexer->lineNumber++;		
+
+		readChar(lexer);
+		break;
+	
+	default:
+		break;
+	}
+	
+}
+
+Token nextToken(Lexer *lexer) {
+	//Token tok;
+	skipWhitespace(lexer);
+
+	switch (lexer->currentChar)
+	{
+	case '+':
+		return NEW_TOKEN(lexer, PLUS, "+");
+		break;
+	case '-':
+		return NEW_TOKEN(lexer, MINUS, "-");
+		break;
+	case '*':
+		return NEW_TOKEN(lexer, ASTERISK, "*");
+		break;
+	case '/':
+		return NEW_TOKEN(lexer, SLASH, "/");
+		break;
+	case '%':
+		return NEW_TOKEN(lexer, MODULUS, "%");
+		break;
+	case '^':
+		return NEW_TOKEN(lexer, POW, "^");
+		break;
+	case '(':
+		return NEW_TOKEN(lexer, LPAREN, "(");
+		break;
+	case ')':
+		return NEW_TOKEN(lexer, RPAREN, ")");
+		break;
+	case '\0':
+		return NEW_TOKEN(lexer, EOF, "");
+		break;
+	
+	default:
+		if (isdigit())
+
+		break;
+	}
+
+	//return tok;
+}

src/sylt/lexer.h

@@ -0,0 +1,22 @@
+#ifndef LEXER_H
+#define LEXER_H
+#include "token.h"
+#include <stdbool.h>
+
+typedef struct
+{
+	int position;
+	int readPosition;
+	int lineNumber;
+
+	char currentChar;
+	char *source;
+} Lexer;
+
+Lexer initLexer(char *source);
+void readChar(Lexer *lexer);
+void skipWhitespace(Lexer *lexer);
+Token nextToken(Lexer *lexer);
+char *tokenToCStr(Token token);
+
+#endif // !LEXER_H

src/sylt/main.c

@@ -0,0 +1,10 @@
+#include "lexer.h"
+#include <stdio.h>
+#include "../file_utils.h"
+
+int main() {
+	Lexer lexer = initLexer("const x, y = 1, 3\n");
+	printf(nextToken(&lexer).literal);
+
+	return 0;
+}

src/sylt/token.h

@@ -0,0 +1,36 @@
+#ifndef TOKEN_H
+#define TOKEN_H
+
+typedef enum {
+	// Special Tokens
+	EOF,
+	ILLEGAL,
+
+	// Data Types
+	INT,
+	FLOAT,
+	
+	// Arithmetic Symbols
+	PLUS,
+	MINUS,
+	ASTERISK,
+	SLASH,
+	POW,
+	MODULUS,
+
+	// Symbols
+	LPAREN,
+	RPAREN
+} TokenType;
+
+typedef struct
+{
+	TokenType type;
+	char *literal;
+	int lineNumber;
+	int position;
+} Token;
+
+#define NEW_TOKEN(lexer, tokType, tokLiteral) (Token){ .type = (tokType), .literal = (tokLiteral), .lineNumber = (lexer->lineNumber), .position = (lexer->position) }
+
+#endif // !TOKEN_H