Tokenizing and printing

.gitignore

@@ -0,0 +1 @@
+bin/

include/utilitiec

@@ -0,0 +1 @@
+/home/vego/Git/utilitiec/src/

lib/utilitiec

@@ -0,0 +1 @@
+/home/vego/Git/utilitiec/build/lib/

make.sh

@@ -0,0 +1 @@
+gcc `find src/ -name '*.c'` lib/utilitiec/libargumentc.a lib/utilitiec/libdynamicarray.a lib/utilitiec/libpointers.a lib/utilitiec/liballocator-interface.a lib/utilitiec/libStringView.a -lm -ggdb -o bin/flup

src/interpreter.c

@@ -0,0 +1,50 @@
+#include "interpreter.h"
+
+static int CallFrame_Create(CallFrame* self, FlupFunctionAlternative* f)
+{
+	if (DynamicArray_Create(&self->stack, sizeof(Value), 8, NULL)) {
+		return ENOMEM;
+	}
+	self->function = f;
+	self->instruction_pointer = f->body_token_start;
+
+	return EXIT_SUCCESS;
+}
+
+static FlupFunctionAlternative* FlupFunctionAlternative_Malloc(size_t condition_token_start, size_t condition_token_end, size_t body_token_start, size_t body_token_end)
+{
+	FlupFunctionAlternative* a = malloc(sizeof(FlupFunctionAlternative));
+	a->next = NULL;
+	a->condition_token_start = condition_token_start;
+	a->condition_token_end   = condition_token_end;
+	a->body_token_start      = body_token_start;
+	a->body_token_end        = body_token_end;
+
+	return a;
+}
+
+int Interpreter_Create(Interpreter* self, DynamicArray* tokens)
+{
+	if (DynamicArray_Create(&self->call_frames, sizeof(CallFrame), 16, NULL)) {
+		return ENOMEM;
+	}
+	self->tokens = tokens;
+
+	return EXIT_SUCCESS;
+}
+
+int Interpreter_Interpret(Interpreter* self)
+{
+	CallFrame* first_frame;
+	DynamicArray_AppendEmpty(&self->call_frames, (void**) &first_frame);
+	if (CallFrame_Create(first_frame, )) {
+		return ENOMEM;
+	}
+
+	return EXIT_SUCCESS;
+}
+
+void Interpreter_Destroy(Interpreter* self)
+{
+	DynamicArray_Destroy(&self->call_frames);
+}

src/interpreter.h

@@ -0,0 +1,59 @@
+#ifndef FLUP_INTERPRETER_H
+#define FLUP_INTERPRETER_H
+
+#include "../include/utilitiec/dynamicarray/dynamicarray.h"
+
+#include "tokenizer.h"
+#include <stdint.h>
+
+typedef struct FlupFunctionAlternative_s {
+	size_t condition_token_start;
+	size_t condition_token_end;
+	size_t body_token_start;
+	size_t body_token_end;
+	struct FlupFunctionAlternative_s* next;
+} FlupFunctionAlternative;
+
+typedef struct ParameterDefinition_s {
+	StringView name;
+	StringView type;
+} ParameterDefinition;
+
+typedef struct FlupFunction_s {
+	StringView name;
+	DynamicArray argument_defs; // ParameterDefinition
+	StringView return_type;
+	FlupFunctionAlternative* alternative;
+} FlupFunction;
+
+enum ValueType {
+	VALUETYPE_INT64,
+	VALUETYPE_DOUBLE
+};
+
+union ValueContent {
+	int64_t i64;
+	double  f64;
+};
+
+typedef struct Value_s {
+	enum ValueType type;
+	union ValueContent get;
+} Value;
+
+typedef struct CallFrame_s {
+	size_t instruction_pointer;
+	FlupFunctionAlternative* function;
+	DynamicArray stack; // Value
+} CallFrame;
+
+typedef struct Interpreter_s {
+	DynamicArray* tokens;
+	DynamicArray call_frames; // stores CallFrame
+} Interpreter;
+
+int Interpreter_Create(Interpreter* self, DynamicArray* tokens);
+int Interpreter_Interpret(Interpreter* self);
+void Interpreter_Destroy(Interpreter* self);
+
+#endif //header guard

src/main.c

@@ -0,0 +1,120 @@
+/*
+ * This code is part of the programming language flup
+ * flup comes with ABSOLUTELY NO WARRANTY and is licensed under AGPL-3.0 or later.
+ *    Copyright (C) 2024  VegOwOtenks
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <stdlib.h>
+#include <stdio.h>
+
+#include "../include/utilitiec/argumentc/argumentc.h"
+#include "interpreter.h"
+#include "tokenizer.h"
+
+int tokenize_all(StringView source, DynamicArray* a)
+{
+	Token t;
+	while ((t = Tokenizer_NextToken(&source)).type != TOKENTYPE_NONE) {
+		int append_code = DynamicArray_Append(a, &t);
+		if (append_code) return append_code;
+		if (t.type == TOKENTYPE_ERROR) break;
+	}
+
+	return EXIT_SUCCESS;
+}
+
+char* load_file_string(StringView path)
+{
+	FILE* stream = fopen(path.source, "r");
+	if (stream == NULL) {
+		fprintf(stderr, "Fatal Error: Failed to open file at %*s\n", (int) path.length, path.source);
+		return NULL;
+	}
+
+	if (fseek(stream, 0, SEEK_END)) {
+		perror("fseek");
+		return NULL;
+	}
+
+	long length = ftell(stream);
+	if (length == -1) {
+		perror("ftell");
+		return NULL;
+	}
+
+	rewind(stream);
+
+	char* buffer = malloc(length + 1);
+	if (buffer == NULL) {
+		fprintf(stderr, "Fatal Error: Failed to allocate %li bytes\n", length);
+		return NULL;
+	}
+
+	size_t bytes_read = fread(buffer, 1, length + 1,  stream);
+	if (bytes_read != length) {
+		fprintf(stderr, "Fatal Error: Failed read %li bytes from script file, got only %li\n", length, bytes_read);
+		free(buffer);
+		return NULL;
+	}
+
+	fclose(stream);
+
+	buffer[length] = '\0';
+
+	return buffer;
+}
+
+int main(int argc, const char* argv []) 
+{
+	Argumentc arguments;
+	Argumentc_Create(&arguments, argc, argv);
+
+	Option script_file = Argumentc_PopLongArgument(&arguments, StringView_FromString("file")).argument;
+	if (script_file.type == OPTIONTYPE_NONE) {
+		fprintf(stderr, "Usage: [program] --file path/to/script_file\n");
+		return 1;
+	}
+	Argumentc_Destroy(&arguments);
+
+	char* script_string = load_file_string(script_file.content);
+	if (script_string == NULL) return 1;
+
+	StringView source   = StringView_FromString(script_string);
+	DynamicArray tokens;
+	if (DynamicArray_Create(&tokens, sizeof(Token), 128, NULL)) {
+		fprintf(stderr, "Fatal Error: Failed to create dynamicarray\n");
+		return 1;
+	}
+
+	if (tokenize_all(source, &tokens)) {
+		fprintf(stderr, "Fatal Error: Out of Memory in tokenizing\n");
+		return 1;
+	}
+
+	Interpreter interpreter;
+	Interpreter_Create(&interpreter, &tokens);
+
+
+	Interpreter_Interpret(&interpreter);
+
+	Interpreter_Destroy(&interpreter);
+	DynamicArray_Destroy(&tokens);
+
+	free(script_string);
+
+	return EXIT_SUCCESS;
+}

src/tokenizer.c

@@ -0,0 +1,209 @@
+#include "tokenizer.h"
+#include <ctype.h>
+#include <math.h>
+
+static StringView StringViewOfNumberTillNextNonDigit(StringView* source) {
+	StringView stringViewOfNumber = StringView_Slice(*source, 0, 0);
+	while (source->length != 0 && isdigit(source->source[0])) {
+		*source = StringView_Drop(*source, 1);
+		stringViewOfNumber.length ++;
+	}
+	return stringViewOfNumber;
+}
+
+static int64_t* _StringView_FoldInt64(char c, int64_t* i)
+{
+	*i = *i * 10 + (c - '0');
+	return i;
+}
+
+static double* _StringView_FoldDouble(char c, double* d)
+{
+	*d = *d * 10 + (c - '0');
+	return d;
+}
+
+static Token _Tokenizer_ParseInt64(bool negative, StringView integerPart)
+{
+	int64_t theInt64 = 0;
+	StringView_FoldLeft(integerPart, &theInt64, (StringViewFoldFunction) _StringView_FoldInt64);
+
+	return (Token) {
+		.type = TOKENTYPE_INTEGER,
+		.get = {
+			.integer = theInt64 * (negative ? -1 : 1)
+		}
+	};
+}
+
+static Token _Tokenizer_ParseDouble(bool negative, StringView integerPart, StringView decimalPart)
+{
+	double theDouble = 0.0;
+	StringView_FoldLeft(integerPart, &theDouble, (StringViewFoldFunction) _StringView_FoldDouble);
+	double theDecimal = 0.0;
+	StringView_FoldLeft(decimalPart, &theDecimal, (StringViewFoldFunction) _StringView_FoldDouble);
+
+	double result = (negative ? -1 : 1) * (theDouble + theDecimal / pow(10.0, decimalPart.length));
+
+	return (Token) {
+		.type = TOKENTYPE_DOUBLE,
+		.get = {
+			.decimal = result
+		}
+	};
+}
+
+static Token _Tokenizer_NumberToken(StringView* source)
+{
+	bool negative = false;
+	if (StringView_StartsWith(*source, StringView_FromString("-"))) {
+		negative = true;
+		*source = StringView_Drop(*source, 1);
+	}
+
+	StringView integerPart = StringViewOfNumberTillNextNonDigit(source);
+	bool has_point = false;
+	if (source->length != 0 && source->source[0] == '.') {
+		*source = StringView_Drop(*source, 1);
+		has_point = true;
+	}
+	StringView decimalPart = StringViewOfNumberTillNextNonDigit(source);
+
+	if (has_point) {
+		return _Tokenizer_ParseDouble(negative, integerPart, decimalPart);
+	} else {
+		return _Tokenizer_ParseInt64(negative, integerPart);
+	}
+}
+
+static bool _Tokenizer_IdentifierLetter(char c)
+{
+	return isalnum(c);
+}
+
+static Token _Tokenizer_IdentifierToken(StringView* source)
+{
+	StringView identifier = StringView_TakeWhile(*source, _Tokenizer_IdentifierLetter);
+	*source = StringView_Drop(*source, identifier.length);
+
+	return (Token) {
+		.type = TOKENTYPE_IDENTIFIER,
+		.get = {
+			.identifier = identifier,
+		}
+	};
+}
+
+static Token _Tokenizer_SimpleToken(StringView* source)
+{
+	const char* literal_table[] = { "{", "}", "&", ":", "+", "->", "-", "*", "/", "|", "==", "!=", "<", "<=", ">", ">=", "," };
+	const enum TokenType type_table[] = { 
+		TOKENTYPE_LEFT_BRACE,
+		TOKENTYPE_RIGHT_BRACE,
+		TOKENTYPE_AMPERSAND,
+		TOKENTYPE_COLON,
+		TOKENTYPE_PLUS,
+		TOKENTYPE_ARROW,
+		TOKENTYPE_MINUS,
+		TOKENTYPE_MULTIPLY,
+		TOKENTYPE_DIVIDE,
+		TOKENTYPE_PIPE,
+		TOKENTYPE_EQUALITY,
+		TOKENTYPE_INEQUALITY,
+		TOKENTYPE_LESSTHAN,
+		TOKENTYPE_LESSEQUAL,
+		TOKENTYPE_GREATERTHAN,
+		TOKENTYPE_GREATEREQUAL,
+		TOKENTYPE_COMMA,
+	};
+
+	for (size_t i = 0; i < sizeof(literal_table) / sizeof(literal_table[0]); i++) {
+		StringView literal_view = StringView_FromString(literal_table[i]);
+		if (StringView_StartsWith(*source, literal_view)) {
+			*source = StringView_Drop(*source, literal_view.length);
+			return (Token) {
+				.type = type_table[i],
+				.get = { .identifier = STRINGVIEW_NONE }
+			};
+		}
+	}
+	return TOKEN_NONE;
+}
+
+Token Tokenizer_NextToken(StringView* source)
+{
+	while (source->length != 0 && isspace(source->source[0])) {
+		0[source] = StringView_Slice(*source, 1, source->length);
+	}
+
+	if (source->length == 0) {
+		return TOKEN_NONE;
+	}
+
+	{
+		Token simple_token = _Tokenizer_SimpleToken(source);
+		if (simple_token.type != TOKENTYPE_NONE) {
+			return simple_token;
+		}
+	}
+
+	if (isdigit(source->source[0]) || StringView_StartsWith(*source, StringView_FromString("-"))) {
+		// parse int/double
+		return _Tokenizer_NumberToken(source);
+	} else if (isalpha(source->source[0])) {
+		// parse name
+		return _Tokenizer_IdentifierToken(source);
+	} else {
+		return (Token) {.type = TOKENTYPE_ERROR, .get = {.error = *source } };
+	}
+}
+
+const char* TokenType_ToString(enum TokenType type)
+{
+	switch (type) {
+		case TOKENTYPE_NONE:
+			return "TOKENTYPE_NONE";
+		case TOKENTYPE_INTEGER:
+			return "TOKENTYPE_INTEGER";
+		case TOKENTYPE_DOUBLE:
+			return "TOKENTYPE_DOUBLE";
+		case TOKENTYPE_IDENTIFIER:
+			return "TOKENTYPE_IDENTIFIER";
+		case TOKENTYPE_LEFT_BRACE:
+			return "TOKENTYPE_LEFT_BRACE";
+		case TOKENTYPE_RIGHT_BRACE:
+			return "TOKENTYPE_RIGHT_BRACE";
+		case TOKENTYPE_AMPERSAND:
+			return "TOKENTYPE_AMPERSAND";
+		case TOKENTYPE_PLUS:
+			return "TOKENTYPE_PLUS";
+		case TOKENTYPE_MINUS:
+			return "TOKENTYPE_MINUS";
+		case TOKENTYPE_MULTIPLY:
+			return "TOKENTYPE_MULTIPLY";
+		case TOKENTYPE_DIVIDE:
+			return "TOKENTYPE_DIVIDE";
+		case TOKENTYPE_PIPE:
+			return "TOKENTYPE_PIPE";
+		case TOKENTYPE_ARROW:
+			return "TOKENTYPE_ARROW";
+		case TOKENTYPE_COLON:
+			return "TOKENTYPE_COLON";
+		case TOKENTYPE_ERROR:
+			return "TOKENTYPE_ERROR";
+		case TOKENTYPE_EQUALITY:
+			return "TOKENTYPE_EQUALITY";
+		case TOKENTYPE_INEQUALITY:
+			return "TOKENTYPE_INEQUALITY";
+		case TOKENTYPE_LESSTHAN:
+			return "TOKENTYPE_LESSTHAN";
+		case TOKENTYPE_LESSEQUAL:
+			return "TOKENTYPE_LESSEQUAL";
+		case TOKENTYPE_GREATERTHAN:
+			return "TOKENTYPE_GREATERTHAN";
+		case TOKENTYPE_GREATEREQUAL:
+			return "TOKENTYPE_GREATEREQUAL";
+		case TOKENTYPE_COMMA:
+			return "TOKENTYPE_COMMA";
+	}
+}

src/tokenizer.h

@@ -0,0 +1,50 @@
+#ifndef FLUP_TOKENIZER_H
+#define FLUP_TOKENIZER_H
+
+#include "../include/utilitiec/StringView/StringView.h"
+#include <stdint.h>
+
+enum TokenType {
+	TOKENTYPE_NONE,
+	TOKENTYPE_INTEGER,
+	TOKENTYPE_DOUBLE,
+	TOKENTYPE_IDENTIFIER,
+	TOKENTYPE_LEFT_BRACE,
+	TOKENTYPE_RIGHT_BRACE,
+	TOKENTYPE_AMPERSAND,
+	TOKENTYPE_PLUS,
+	TOKENTYPE_MINUS,
+	TOKENTYPE_MULTIPLY,
+	TOKENTYPE_DIVIDE,
+	TOKENTYPE_PIPE,
+	TOKENTYPE_ARROW,
+	TOKENTYPE_COLON,
+	TOKENTYPE_EQUALITY,
+	TOKENTYPE_INEQUALITY,
+	TOKENTYPE_LESSTHAN,
+	TOKENTYPE_LESSEQUAL,
+	TOKENTYPE_GREATERTHAN,
+	TOKENTYPE_GREATEREQUAL,
+	TOKENTYPE_COMMA,
+	TOKENTYPE_ERROR,
+};
+
+union TokenContent {
+	StringView identifier;
+	StringView error;
+	int64_t    integer;
+	double     decimal;
+};
+
+typedef struct Token_s {
+	enum TokenType type;
+	union TokenContent get;
+} Token;
+
+
+#define TOKEN_NONE ((Token) {.type = TOKENTYPE_NONE, .get = {.error = STRINGVIEW_NONE } } )
+
+Token Tokenizer_NextToken(StringView* source);
+const char* TokenType_ToString(enum TokenType type);
+
+#endif //header guard

templates/C-Header.h

@@ -0,0 +1,19 @@
+/*
+ * This code is part of the programming language flup
+ * flup comes with ABSOLUTELY NO WARRANTY and is licensed under AGPL-3.0 or later.
+ *    Copyright (C) 2024  VegOwOtenks
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */

templates/C-Source.c

@@ -0,0 +1,19 @@
+/*
+ * This code is part of the programming language flup
+ * flup comes with ABSOLUTELY NO WARRANTY and is licensed under AGPL-3.0 or later.
+ *    Copyright (C) 2024  VegOwOtenks
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */