ast

.gitignore

@@ -1,54 +0,0 @@
-# ---> C
-# Prerequisites
-*.d
-
-# Object files
-*.o
-*.ko
-*.obj
-*.elf
-
-# Linker output
-*.ilk
-*.map
-*.exp
-
-# Precompiled Headers
-*.gch
-*.pch
-
-# Libraries
-*.lib
-*.a
-*.la
-*.lo
-
-# Shared objects (inc. Windows DLLs)
-*.dll
-*.so
-*.so.*
-*.dylib
-
-# Executables
-*.exe
-*.out
-*.app
-*.i*86
-*.x86_64
-*.hex
-
-# Debug files
-*.dSYM/
-*.su
-*.idb
-*.pdb
-
-# Kernel Module Compile Results
-*.mod*
-*.cmd
-.tmp_versions/
-modules.order
-Module.symvers
-Mkfile.old
-dkms.conf
-

Makefile

@@ -0,0 +1,24 @@
+CC=gcc
+CFLAGS=-O3 -Wall
+
+SRC=src
+BIN=bin
+
+VMBL_FILES=$(wildcard $(SRC)/vmbl/*.c)
+SYLT_FILES=$(wildcard $(SRC)/sylt/*.c)
+UTIL_FILES=$(wildcard $(SRC)/utils/*.c)
+
+all: vmbl sylt
+
+$(BIN)/vmbl: $(VMBL_FILES)
+	mkdir -p $(BIN)
+	$(CC) $(CFLAGS) $(UTIL_FILES) $(VMBL_FILES) -o $(BIN)/vmbl
+vmbl: $(BIN)/vmbl
+
+$(BIN)/sylt: $(SYLT_FILES)
+	mkdir -p $(BIN)
+	$(CC) $(CFLAGS) $(UTIL_FILES) $(SYLT_FILES) -o $(BIN)/sylt
+sylt: $(BIN)/sylt
+
+clean:
+	rm -r $(BIN)

README.md

@@ -9,7 +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`
+To compile the SYLT compiler for Linux: `gcc src/sylt/main.c src/sylt/exception.c src/sylt/token.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/ast.c

@@ -0,0 +1 @@
+#include "ast.h"

src/sylt/ast.h

@@ -0,0 +1,65 @@
+#ifndef AST_H
+#define AST_H
+
+#include <stdlib.h>
+
+typedef enum {
+	NODE_PROGRAM,
+
+	// Statements
+	NODE_EXPRESSION_STATEMENT,
+
+	// Expressions
+	NODE_INFIX_EXPRESSION,
+
+	// Literals
+	NODE_INT_LITERAL,
+	NODE_FLOAT_LITERAL
+} AST_Type;
+
+typedef struct AST AST;
+struct AST
+{
+	AST_Type type;
+	char *(*to_json)(AST *node);
+};
+
+typedef struct
+{
+	AST base;
+	AST **statements;
+	size_t statementCount;
+} Program;
+char *programToJSON(AST *node);
+
+// statements
+typedef struct
+{
+	AST base;
+	AST *expr;
+} ExpressionStatement;
+char *expressionStatementToJSON(AST *node);
+
+// expressions
+typedef struct {
+	AST base;
+	AST *left;
+	char *operator;
+	AST *right;
+} InfixExpression;
+char *infixExpressionToJSON(AST *node);
+
+// literals
+typedef struct {
+	AST base;
+	int value;
+} IntegerLiteral;
+char *integerLiteralToJSON(AST *node);
+
+typedef struct {
+	AST base;
+	double value;
+} FloatLiteral;
+char *floatLiteralToJSON(AST *node);
+
+#endif // !AST_H

src/sylt/exception.c

@@ -0,0 +1,21 @@
+#include "exception.h"
+#include <stdio.h>
+#include "../utils/ansii.h"
+
+char *exceptionTypeToCString(ExceptionType type) {
+	switch (type)
+	{
+	case EXCEPTION_MALFORMED_NUMBER:
+		return "MalformedNumberException";
+
+	case EXCEPTION_MEMORY_ALLOCATION_FAILURE:
+		return "MemoryAllocationFailException";
+	
+	default:
+		return "UnkownException (fix me please)";
+	}
+}
+
+void exceptionMessage(ExceptionType type, char *message, int lineNumber, int position) {
+	printf(ESC_RED_FG ESC_BOLD "%s: %s" ESC_RESET "\n", exceptionTypeToCString(type), message);
+}

src/sylt/exception.h

@@ -0,0 +1,12 @@
+#ifndef EXCEPTION_H
+#define EXCEPTION_H
+
+typedef enum {
+	EXCEPTION_MALFORMED_NUMBER,
+	EXCEPTION_MEMORY_ALLOCATION_FAILURE
+} ExceptionType;
+
+char *exceptionTypeToCString(ExceptionType type);
+void exceptionMessage(ExceptionType type, char *message, int lineNumber, int position);
+
+#endif // !EXCEPTION_H

src/sylt/lexer.c

@@ -1,7 +1,9 @@
 #include "lexer.h"
+#include "exception.h"
 #include <string.h>
+#include <ctype.h>
 #include <stdlib.h>
-#include <stdio,h>
+#include <stdio.h>
 
 Lexer initLexer(char *source) {
 	Lexer newLexer = {
@@ -11,6 +13,7 @@ Lexer initLexer(char *source) {
 		.lineNumber = 1,
 		.currentChar = '\0'
 	};
+	readChar(&newLexer);
 	return newLexer;
 }
 
@@ -25,63 +28,134 @@ void readChar(Lexer *lexer) {
 }
 
 void skipWhitespace(Lexer *lexer) {
-	switch (lexer->currentChar)
-	{
-	case ' ':
-	case '\t':
-	case '\n':
-	case '\r':
-		if (lexer->currentChar == '\n')
-			lexer->lineNumber++;		
+	bool whitespace = true;
 
-		readChar(lexer);
-		break;
-	
-	default:
-		break;
+	while (whitespace)
+	{
+		switch (lexer->currentChar)
+		{
+		case ' ':
+		case '\t':
+		case '\n':
+		case '\r':
+			if (lexer->currentChar == '\n')
+				lexer->lineNumber++;		
+
+			readChar(lexer);
+			break;
+		
+		default:
+			whitespace = false;
+			break;
+		}
 	}
 	
+	
+	
+}
+
+Token readNumber(Lexer *lexer) {
+	int startPos = lexer->position;
+	int dotCount = 0;
+	int strLength = 0;
+
+	size_t outputCap = 8;
+	char *output = malloc(outputCap);
+
+	if (!output) {
+		exceptionMessage(EXCEPTION_MEMORY_ALLOCATION_FAILURE, "Lexer failed to allocate memory.", lexer->lineNumber, lexer->position);
+		exit(1);
+	}
+
+	while (isdigit(lexer->currentChar) || lexer->currentChar == '.')
+	{
+		if (lexer->currentChar == '.') {
+			dotCount++;
+
+			if (dotCount > 1) {
+				exceptionMessage(EXCEPTION_MALFORMED_NUMBER, "Too many dots in decimal.", lexer->lineNumber, lexer->position);
+
+				char buffer[strLength+1];
+				strncpy(buffer, lexer->source + startPos, strLength+1);
+				buffer[strLength+1] = 0;
+
+				return NEW_TOKEN(lexer, TOKEN_ILLEGAL, buffer);
+			}
+		}
+		
+		// allocate more memory if we reach the end of our buffer
+		if (strLength + 1 >= outputCap) {
+			char *temp = realloc(output, outputCap*=2);
+
+			if (!temp) {
+				exceptionMessage(EXCEPTION_MEMORY_ALLOCATION_FAILURE, "Lexer failed to allocate memory.", lexer->lineNumber, lexer->position);
+				exit(1);
+			}
+
+			output = temp;
+		}
+
+		output[strLength] = lexer->source[lexer->position];
+		strLength++;
+		readChar(lexer);		
+
+		if (lexer->currentChar == '\0')
+			break;
+	}
+
+	output[strLength] = 0;
+	
+	if (dotCount == 0)
+		return NEW_TOKEN(lexer, TOKEN_INT, output);
+	else
+		return NEW_TOKEN(lexer, TOKEN_FLOAT, output);
 }
 
 Token nextToken(Lexer *lexer) {
-	//Token tok;
+	Token tok;
 	skipWhitespace(lexer);
 
 	switch (lexer->currentChar)
 	{
 	case '+':
-		return NEW_TOKEN(lexer, PLUS, "+");
+		tok = NEW_TOKEN(lexer, TOKEN_PLUS, "+");
 		break;
 	case '-':
-		return NEW_TOKEN(lexer, MINUS, "-");
+		tok =  NEW_TOKEN(lexer, TOKEN_MINUS, "-");
 		break;
 	case '*':
-		return NEW_TOKEN(lexer, ASTERISK, "*");
+		tok =  NEW_TOKEN(lexer, TOKEN_ASTERISK, "*");
 		break;
 	case '/':
-		return NEW_TOKEN(lexer, SLASH, "/");
+		tok =  NEW_TOKEN(lexer, TOKEN_SLASH, "/");
 		break;
 	case '%':
-		return NEW_TOKEN(lexer, MODULUS, "%");
+		tok =  NEW_TOKEN(lexer, TOKEN_MODULUS, "%");
 		break;
 	case '^':
-		return NEW_TOKEN(lexer, POW, "^");
+		tok =  NEW_TOKEN(lexer, TOKEN_POW, "^");
 		break;
 	case '(':
-		return NEW_TOKEN(lexer, LPAREN, "(");
+		tok =  NEW_TOKEN(lexer, TOKEN_LPAREN, "(");
 		break;
 	case ')':
-		return NEW_TOKEN(lexer, RPAREN, ")");
+		tok =  NEW_TOKEN(lexer, TOKEN_RPAREN, ")");
 		break;
-	case '\0':
-		return NEW_TOKEN(lexer, EOF, "");
+
+	case '\0': // EOF
+		tok = NEW_TOKEN(lexer, TOKEN_EOF, "EOF");
 		break;
 	
 	default:
-		if (isdigit())
+		if (isdigit(lexer->currentChar)) {
+			tok = readNumber(lexer);
+		} else {
+			tok = NEW_TOKEN(lexer, TOKEN_ILLEGAL, &lexer->currentChar);
+		}
 
 		break;
 	}
 
-	//return tok;
+	readChar(lexer);
+	return tok;
 }

src/sylt/lexer.h

@@ -17,6 +17,6 @@ Lexer initLexer(char *source);
 void readChar(Lexer *lexer);
 void skipWhitespace(Lexer *lexer);
 Token nextToken(Lexer *lexer);
-char *tokenToCStr(Token token);
+Token readNumber(Lexer *lexer);
 
 #endif // !LEXER_H

src/sylt/main.c

@@ -1,10 +1,16 @@
 #include "lexer.h"
 #include <stdio.h>
-#include "../file_utils.h"
+#include "../utils/file_utils.h"
+#include "../utils/ansii.h"
 
 int main() {
-	Lexer lexer = initLexer("const x, y = 1, 3\n");
-	printf(nextToken(&lexer).literal);
+	Lexer lexer = initLexer("123 456.789 + - * / % ^ ()");
+
+	while (lexer.currentChar != 0)
+	{
+		Token next = nextToken(&lexer);
+		printf("%s: %s\n", tokenTypeToCString(next.type), next.literal);
+	}
 
 	return 0;
 }

src/sylt/parser.c

@@ -0,0 +1 @@
+#include "parser.h"

src/sylt/parser.h

@@ -0,0 +1,28 @@
+#ifndef PARSER_H
+#define PARSER_H
+
+#include "lexer.h"
+#include "ast.h"
+
+typedef enum {
+	PRECEDENCE_LOWEST = 0,
+	PRECEDENCE_EQUALS,
+	PRECEDENCE_LESSGREATER,
+	PRECEDENCE_SUM,
+	PRECEDENCE_PRODUCT,
+	PRECEDENCE_EXPONENT,
+	PRECEDENCE_PREFIX,
+	PRECEDENCE_CALL,
+	PRECEDENCE_INDEX,
+} PrecedenceType;
+
+PrecedenceType PRECEDENCES[] = {
+	[TOKEN_PLUS] = PRECEDENCE_SUM,
+	[TOKEN_MINUS] = PRECEDENCE_SUM,
+	[TOKEN_SLASH] = PRECEDENCE_PRODUCT,
+	[TOKEN_ASTERISK] = PRECEDENCE_PRODUCT,
+	[TOKEN_MODULUS] = PRECEDENCE_PRODUCT,
+	[TOKEN_POW] = PRECEDENCE_EXPONENT,
+};
+
+#endif // !PARSER_H

src/sylt/token.c

@@ -0,0 +1,45 @@
+#include "token.h"
+
+char *tokenTypeToCString(TokenType type) {
+	switch (type)
+	{
+	case TOKEN_EOF:
+		return "TOKEN_EOF";
+
+	case TOKEN_ILLEGAL:
+		return "TOKEN_ILLEGAL";
+
+	case TOKEN_INT:
+		return "TOKEN_INT";
+
+	case TOKEN_FLOAT:
+		return "TOKEN_FLOAT";
+
+	case TOKEN_PLUS:
+		return "TOKEN_EOF";
+
+	case TOKEN_MINUS:
+		return "TOKEN_MINUS";
+
+	case TOKEN_ASTERISK:
+		return "TOKEN_ASTERISK";
+
+	case TOKEN_SLASH:
+		return "TOKEN_SLASH";
+
+	case TOKEN_POW:
+		return "TOKEN_POW";
+
+	case TOKEN_MODULUS:
+		return "TOKEN_MODULUS";
+	
+	case TOKEN_LPAREN:
+		return "TOKEN_LPAREN";
+
+	case TOKEN_RPAREN:
+		return "TOKEN_RPAREN";
+
+	default:
+		return "UNKOWN (fix me please)";
+	}
+}

src/sylt/token.h

@@ -3,24 +3,24 @@
 
 typedef enum {
 	// Special Tokens
-	EOF,
-	ILLEGAL,
+	TOKEN_EOF,
+	TOKEN_ILLEGAL,
 
 	// Data Types
-	INT,
-	FLOAT,
+	TOKEN_INT,
+	TOKEN_FLOAT,
 	
 	// Arithmetic Symbols
-	PLUS,
-	MINUS,
-	ASTERISK,
-	SLASH,
-	POW,
-	MODULUS,
+	TOKEN_PLUS,
+	TOKEN_MINUS,
+	TOKEN_ASTERISK,
+	TOKEN_SLASH,
+	TOKEN_POW,
+	TOKEN_MODULUS,
 
 	// Symbols
-	LPAREN,
-	RPAREN
+	TOKEN_LPAREN,
+	TOKEN_RPAREN
 } TokenType;
 
 typedef struct
@@ -33,4 +33,6 @@ typedef struct
 
 #define NEW_TOKEN(lexer, tokType, tokLiteral) (Token){ .type = (tokType), .literal = (tokLiteral), .lineNumber = (lexer->lineNumber), .position = (lexer->position) }
 
+char *tokenTypeToCString(TokenType type);
+
 #endif // !TOKEN_H

src/utils/ansii.h

@@ -0,0 +1,67 @@
+// ansii.h - made by SpookyDervish
+// version 1.0.0
+// do with this whatever you want
+//
+// example usage with printf: printf(ESC_BOLD ESC_RED_FG "hi\n");
+
+#ifndef ANSII_H
+#define ANSII_H
+
+#define ESC_RESET    		 	"\x1b[0m"
+#define ESC_BOLD     		 	"\x1b[1m"
+#define ESC_DIM    	 		    "\x1b[2m"
+#define ESC_ITALIC   		    "\x1b[3m"
+#define ESC_UNDERLINE		    "\x1b[4m"
+#define ESC_BLINKING  		    "\x1b[5m"
+#define ESC_REVERSE   	 	    "\x1b[7m"
+#define ESC_HIDDEN    		    "\x1b[8m"
+#define ESC_STRIKETHROUGH       "\x1b[8m"
+
+#define ESC_TERMINAL_BELL       "\a"
+
+#define ESC_BLACK_FG            "\x1b[30m"
+#define ESC_RED_FG              "\x1b[31m"
+#define ESC_GREEN_FG            "\x1b[32m"
+#define ESC_YELLOW_FG           "\x1b[33m"
+#define ESC_BLUE_FG             "\x1b[34m"
+#define ESC_MAGENTA_FG          "\x1b[35m"
+#define ESC_CYAN_FG             "\x1b[36m"
+#define ESC_WHITE_FG            "\x1b[37m"
+
+#define ESC_BLACK_FG            "\x1b[30m"
+#define ESC_RED_FG              "\x1b[31m"
+#define ESC_GREEN_FG            "\x1b[32m"
+#define ESC_YELLOW_FG           "\x1b[33m"
+#define ESC_BLUE_FG             "\x1b[34m"
+#define ESC_MAGENTA_FG          "\x1b[35m"
+#define ESC_CYAN_FG             "\x1b[36m"
+#define ESC_WHITE_FG            "\x1b[37m"
+#define ESC_BRIGHT_BLACK_FG     "\x1b[90m"
+#define ESC_BRIGHT_RED_FG       "\x1b[91m"
+#define ESC_BRIGHT_GREEN_FG     "\x1b[92m"
+#define ESC_BRIGHT_YELLOW_FG    "\x1b[93m"
+#define ESC_BRIGHT_BLUE_FG      "\x1b[94m"
+#define ESC_BRIGHT_MAGENTA_FG   "\x1b[95m"
+#define ESC_BRIGHT_CYAN_FG      "\x1b[96m"
+#define ESC_BRIGHT_WHITE_FG     "\x1b[97m"
+
+#define ESC_BLACK_BG            "\x1b[40m"
+#define ESC_RED_BG              "\x1b[41m"
+#define ESC_GREEN_BG            "\x1b[42m"
+#define ESC_YELLOW_BG           "\x1b[43m"
+#define ESC_BLUE_BG             "\x1b[44m"
+#define ESC_MAGENTA_BG          "\x1b[45m"
+#define ESC_CYAN_BG             "\x1b[46m"
+#define ESC_WHITE_BG            "\x1b[47m"
+#define ESC_BRIGHT_BLACK_BG     "\x1b[100m"
+#define ESC_BRIGHT_RED_BG       "\x1b[101m"
+#define ESC_BRIGHT_GREEN_BG     "\x1b[102m"
+#define ESC_BRIGHT_YELLOW_BG    "\x1b[103m"
+#define ESC_BRIGHT_BLUE_BG      "\x1b[104m"
+#define ESC_BRIGHT_MAGENTA_BG   "\x1b[105m"
+#define ESC_BRIGHT_CYAN_BG      "\x1b[106m"
+#define ESC_BRIGHT_WHITE_BG     "\x1b[107m"
+
+#define ESC_DEFAULT_FG          "\x1b[39m"
+
+#endif // !ANSII_H

src/vmbl/main.c

@@ -4,12 +4,7 @@
 #define ARRAY_SIZE(array) (sizeof(array) / sizeof(array[0])); 
 
 VMBL_Instruction program[] = {
-	MAKE_INST_PUSH(0),
-	MAKE_INST_PUSH(1),
-	MAKE_INST_DUP(1),
-	MAKE_INST_DUP(1),
-	MAKE_INST_ADD,
-	MAKE_INST_JMP(2)
+	MAKE_INST_JMP(0)
 };
 
 int main() {

src/vmbl/vmbl.c

@@ -1,5 +1,5 @@
 #include "vmbl.h"
-#include "file_utils.h"
+#include "../utils/file_utils.h"
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>