mirror of
https://github.com/krgamestudios/Toy.git
synced 2026-04-15 14:54:07 +10:00
The 'source' directory compiles, but the repl and tests are almost
untouched so far. There's no guarantee that the code in 'source' is
correct, so I'm branching this for a short time, until I'm confident the
whole project passes the CI again.
I'm adjusting the concepts of routines and bytecode to make them more
consistent, and tweaking the VM so it loads from an instance of
'Toy_Module'.
* 'Toy_ModuleBuilder' (formally 'Toy_Routine')
This is where the AST is compiled, producing a chunk of memory that can
be read by the VM. This will eventually operate on individual
user-defined functions as well.
* 'Toy_ModuleBundle' (formally 'Toy_Bytecode')
This collects one or more otherwise unrelated modules into one chunk of
memory, stored in sequence. It is also preprended with the version data for
Toy's reference implementation:
For each byte in the bytecode:
0th: TOY_VERSION_MAJOR
1st: TOY_VERSION_MINOR
2nd: TOY_VERSION_PATCH
3rd: (the number of modules in the bundle)
4th and onwards: TOY_VERSION_BUILD
TOY_VERSION_BUILD has always been a null terminated C-string, but from
here on, it begins at the word-alignment, and continues until the first
word-alignment after the null terminator.
As for the 3rd byte listed, since having more than 256 modules in one
bundle seems unlikely, I'm storing the count here, as it was otherwise
unused. This is a bit janky, but it works for now.
* 'Toy_Module'
This new structure represents a single complete unit of operation, such
as a single source file, or a user-defined function. It is divided into
three main sections, with various sub-sections.
HEADER (all members are unsigned ints):
total module size in bytes
jumps count
param count
data count
subs count
code addr
jumps addr (if jumps count > 0)
param addr (if param count > 0)
data addr (if data count > 0)
subs addr (if subs count > 0)
BODY:
<raw opcodes, etc.>
DATA:
jumps table
uint array, pointing to addresses in 'data' or 'subs'
param table
uint array, pointing to addresses in 'data'
data
heterogeneous data, including strings
subs
an array of modules, using recursive logic
The reference implementation as a whole uses a lot of recursion, so this
makes sense.
The goal of this rework is so 'Toy_Module' can be added as a member of
'Toy_Value', as a simple and logical way to handle functions. I'll
probably use the union pattern, similarly to Toy_String, so functions
can be written in C and Toy, and used without needing to worry which is
which.
504 lines
12 KiB
C
504 lines
12 KiB
C
#include "toy.h"
|
|
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
|
|
//utilities
|
|
#define APPEND(dest, src) \
|
|
strncpy((dest) + (strlen(dest)), (src), strlen((src)) + 1);
|
|
|
|
#if defined(_WIN32) || defined(_WIN64)
|
|
#define FLIPSLASH(str) for (int i = 0; str != NULL && str[i]; i++) str[i] = str[i] == '/' ? '\\' : str[i];
|
|
#else
|
|
#define FLIPSLASH(str) for (int i = 0; str != NULL && str[i]; i++) str[i] = str[i] == '\\' ? '/' : str[i];
|
|
#endif
|
|
|
|
unsigned char* readFile(char* path, int* size) {
|
|
//BUGFIX: fix the path based on platform - it might be slower, but it's better than dealing with platform crap
|
|
int pathLength = strlen(path);
|
|
char realPath[pathLength + 1];
|
|
strncpy(realPath, path, pathLength);
|
|
realPath[pathLength] = '\0';
|
|
FLIPSLASH(realPath);
|
|
|
|
//open the file
|
|
FILE* file = fopen(path, "rb");
|
|
if (file == NULL) {
|
|
*size = -1; //missing file error
|
|
return NULL;
|
|
}
|
|
|
|
//determine the file's length
|
|
fseek(file, 0L, SEEK_END);
|
|
*size = ftell(file);
|
|
rewind(file);
|
|
|
|
//make some space
|
|
unsigned char* buffer = malloc(*size + 1);
|
|
if (buffer == NULL) {
|
|
fclose(file);
|
|
return NULL;
|
|
}
|
|
|
|
//read the file
|
|
if (fread(buffer, sizeof(unsigned char), *size, file) < (unsigned int)(*size)) {
|
|
fclose(file);
|
|
*size = -2; //singal a read error
|
|
return NULL;
|
|
}
|
|
|
|
buffer[(*size)++] = '\0';
|
|
|
|
//clean up and return
|
|
fclose(file);
|
|
return buffer;
|
|
}
|
|
|
|
int getFilePath(char* dest, const char* src) {
|
|
char* p = NULL;
|
|
|
|
//find the last slash, regardless of platform
|
|
p = strrchr(src, '\\');
|
|
if (p == NULL) {
|
|
p = strrchr(src, '/');
|
|
}
|
|
if (p == NULL) {
|
|
int len = strlen(src);
|
|
strncpy(dest, src, len);
|
|
return len;
|
|
}
|
|
|
|
//determine length of the path
|
|
int len = p - src + 1;
|
|
|
|
//copy to the dest
|
|
strncpy(dest, src, len);
|
|
dest[len] = '\0';
|
|
|
|
return len;
|
|
}
|
|
|
|
int getFileName(char* dest, const char* src) {
|
|
char* p = NULL;
|
|
|
|
//find the last slash, regardless of platform
|
|
p = strrchr(src, '\\');
|
|
if (p == NULL) {
|
|
p = strrchr(src, '/');
|
|
}
|
|
if (p == NULL) {
|
|
int len = strlen(src);
|
|
strncpy(dest, src, len);
|
|
return len;
|
|
}
|
|
|
|
p++; //skip the slash
|
|
|
|
//determine length of the file name
|
|
int len = strlen(p);
|
|
|
|
//copy to the dest
|
|
strncpy(dest, p, len);
|
|
dest[len] = '\0';
|
|
|
|
return len;
|
|
}
|
|
|
|
//callbacks
|
|
static void printCallback(const char* msg) {
|
|
fprintf(stdout, "%s\n", msg);
|
|
}
|
|
|
|
static void errorAndExitCallback(const char* msg) {
|
|
fprintf(stderr, "Error: %s\n", msg);
|
|
exit(-1);
|
|
}
|
|
|
|
static void errorAndContinueCallback(const char* msg) {
|
|
fprintf(stderr, "Error: %s\n", msg);
|
|
}
|
|
|
|
static void assertFailureAndExitCallback(const char* msg) {
|
|
fprintf(stderr, "Assert Failure: %s\n", msg);
|
|
exit(-1);
|
|
}
|
|
|
|
static void assertFailureAndContinueCallback(const char* msg) {
|
|
fprintf(stderr, "Assert Failure: %s\n", msg);
|
|
}
|
|
|
|
static void noOpCallback(const char* msg) {
|
|
//NO-OP
|
|
(void)msg;
|
|
}
|
|
|
|
static void silentExitCallback(const char* msg) {
|
|
//NO-OP
|
|
(void)msg;
|
|
exit(-1);
|
|
}
|
|
|
|
//handle command line arguments
|
|
typedef struct CmdLine {
|
|
bool error;
|
|
bool help;
|
|
bool version;
|
|
char* infile;
|
|
int infileLength;
|
|
bool silentPrint;
|
|
bool silentAssert;
|
|
bool removeAssert;
|
|
bool verboseDebugPrint;
|
|
} CmdLine;
|
|
|
|
void usageCmdLine(int argc, const char* argv[]) {
|
|
(void)argc;
|
|
printf("Usage: %s [ -h | -v | -f source.toy ]\n\n", argv[0]);
|
|
}
|
|
|
|
void helpCmdLine(int argc, const char* argv[]) {
|
|
usageCmdLine(argc, argv);
|
|
|
|
printf("The Toy Programming Language, leave arguments blank for an interactive REPL.\n\n");
|
|
|
|
printf(" -h, --help\t\t\tShow this help then exit.\n");
|
|
printf(" -v, --version\t\t\tShow version and copyright information then exit.\n");
|
|
printf(" -f, --file infile\t\tParse, compile and execute the source file then exit.\n");
|
|
printf(" --silent-print\t\tSuppress output from the print keyword.\n");
|
|
printf(" --silent-assert\t\tSuppress output from the assert keyword.\n");
|
|
printf(" --remove-assert\t\tDo not include the assert statement in the bytecode.\n");
|
|
printf(" -d, --verbose\t\tPrint debugging information about Toy's internals.\n");
|
|
}
|
|
|
|
void versionCmdLine(int argc, const char* argv[]) {
|
|
(void)argc;
|
|
(void)argv;
|
|
printf("The Toy Programming Language, Version %d.%d.%d %s\n\n", TOY_VERSION_MAJOR, TOY_VERSION_MINOR, TOY_VERSION_PATCH, TOY_VERSION_BUILD);
|
|
|
|
//copy/pasted from the license file - there's a way to include it directly, but it's too finnicky to bother
|
|
const char* license = "\
|
|
Copyright (c) 2020-2025 Kayne Ruse, KR Game Studios\n\
|
|
\n\
|
|
This software is provided 'as-is', without any express or implied\n\
|
|
warranty. In no event will the authors be held liable for any damages\n\
|
|
arising from the use of this software.\n\
|
|
\n\
|
|
Permission is granted to anyone to use this software for any purpose,\n\
|
|
including commercial applications, and to alter it and redistribute it\n\
|
|
freely, subject to the following restrictions:\n\
|
|
\n\
|
|
1. The origin of this software must not be misrepresented; you must not\n\
|
|
claim that you wrote the original software. If you use this software\n\
|
|
in a product, an acknowledgment in the product documentation would be\n\
|
|
appreciated but is not required.\n\
|
|
2. Altered source versions must be plainly marked as such, and must not be\n\
|
|
misrepresented as being the original software.\n\
|
|
3. This notice may not be removed or altered from any source distribution.\n\n";
|
|
|
|
printf("%s",license);
|
|
}
|
|
|
|
CmdLine parseCmdLine(int argc, const char* argv[]) {
|
|
CmdLine cmd = {
|
|
.error = false,
|
|
.help = false,
|
|
.version = false,
|
|
.infile = NULL,
|
|
.infileLength = 0,
|
|
.silentPrint = false,
|
|
.silentAssert = false,
|
|
.removeAssert = false,
|
|
.verboseDebugPrint = false,
|
|
};
|
|
|
|
for (int i = 1; i < argc; i++) {
|
|
if (!strcmp(argv[i], "-h") || !strcmp(argv[i], "--help")) {
|
|
cmd.help = true;
|
|
}
|
|
|
|
else if (!strcmp(argv[i], "-v") || !strcmp(argv[i], "--version")) {
|
|
cmd.version = true;
|
|
}
|
|
|
|
else if (!strcmp(argv[i], "-f") || !strcmp(argv[i], "--file")) {
|
|
if (argc < i + 1) {
|
|
cmd.error = true;
|
|
}
|
|
else {
|
|
if (cmd.infile != NULL) { //don't leak
|
|
free(cmd.infile);
|
|
}
|
|
|
|
i++;
|
|
|
|
//total space to reserve - it's actually longer than needed, due to the exe name being removed
|
|
cmd.infileLength = strlen(argv[0]) + strlen(argv[i]) + 1;
|
|
cmd.infileLength = (cmd.infileLength + 3) & ~3; //BUGFIX: align to word size for malloc()
|
|
cmd.infile = malloc(cmd.infileLength);
|
|
|
|
if (cmd.infile == NULL) {
|
|
fprintf(stderr, TOY_CC_ERROR "ERROR: Failed to allocate space while parsing the command line, exiting\n" TOY_CC_RESET);
|
|
exit(-1);
|
|
}
|
|
|
|
getFilePath(cmd.infile, argv[0]);
|
|
APPEND(cmd.infile, argv[i]);
|
|
FLIPSLASH(cmd.infile);
|
|
}
|
|
}
|
|
|
|
else if (!strcmp(argv[i], "--silent-print")) {
|
|
cmd.silentPrint = true;
|
|
}
|
|
|
|
else if (!strcmp(argv[i], "--silent-assert")) {
|
|
cmd.silentAssert = true;
|
|
}
|
|
|
|
else if (!strcmp(argv[i], "--remove-assert")) {
|
|
cmd.removeAssert = true;
|
|
}
|
|
|
|
else if (!strcmp(argv[i], "-d") || !strcmp(argv[i], "--verbose")) {
|
|
cmd.verboseDebugPrint = true;
|
|
}
|
|
|
|
else {
|
|
cmd.error = true;
|
|
}
|
|
}
|
|
|
|
return cmd;
|
|
}
|
|
|
|
//repl function
|
|
int repl(const char* filepath) {
|
|
//output options
|
|
Toy_setPrintCallback(printCallback);
|
|
Toy_setErrorCallback(errorAndContinueCallback);
|
|
Toy_setAssertFailureCallback(assertFailureAndContinueCallback);
|
|
|
|
//vars to use
|
|
char prompt[256];
|
|
getFileName(prompt, filepath);
|
|
unsigned int INPUT_BUFFER_SIZE = 4096;
|
|
char inputBuffer[INPUT_BUFFER_SIZE];
|
|
memset(inputBuffer, 0, INPUT_BUFFER_SIZE);
|
|
|
|
Toy_Bucket* bucket = Toy_allocateBucket(TOY_BUCKET_IDEAL);
|
|
|
|
Toy_VM vm;
|
|
Toy_initVM(&vm);
|
|
|
|
printf("%s> ", prompt); //shows the terminal prompt
|
|
|
|
//read from the terminal
|
|
while(fgets(inputBuffer, INPUT_BUFFER_SIZE, stdin)) {
|
|
//work around fgets() adding a newline
|
|
unsigned int length = strlen(inputBuffer);
|
|
if (inputBuffer[length - 1] == '\n') {
|
|
inputBuffer[--length] = '\0';
|
|
}
|
|
|
|
if (length == 0) {
|
|
printf("%s> ", prompt); //shows the terminal prompt
|
|
continue;
|
|
}
|
|
|
|
//end
|
|
if (strlen(inputBuffer) == 4 && (strncmp(inputBuffer, "exit", 4) == 0 || strncmp(inputBuffer, "quit", 4) == 0)) {
|
|
break;
|
|
}
|
|
|
|
//parse the input, prep the VM for run
|
|
Toy_Lexer lexer;
|
|
Toy_bindLexer(&lexer, inputBuffer);
|
|
Toy_Parser parser;
|
|
Toy_bindParser(&parser, &lexer);
|
|
Toy_configureParser(&parser, false);
|
|
Toy_Ast* ast = Toy_scanParser(&bucket, &parser); //Ast is in the bucket, so it doesn't need to be freed
|
|
|
|
//parsing error, retry
|
|
if (parser.error) {
|
|
printf("%s> ", prompt); //shows the terminal prompt
|
|
continue;
|
|
}
|
|
|
|
Toy_ModuleBundle bc = Toy_compileModuleBundle(ast);
|
|
Toy_bindVM(&vm, &bc);
|
|
|
|
//run
|
|
Toy_runVM(&vm);
|
|
|
|
//free the bytecode, and leave the VM ready for the next loop
|
|
Toy_resetVM(&vm);
|
|
Toy_freeModuleBundle(bc);
|
|
|
|
printf("%s> ", prompt); //shows the terminal prompt
|
|
}
|
|
|
|
//cleanup all memory
|
|
Toy_freeVM(&vm);
|
|
Toy_freeBucket(&bucket);
|
|
|
|
return 0;
|
|
}
|
|
|
|
//debugging
|
|
static void debugStackPrint(Toy_Stack* stack) {
|
|
//DEBUG: if there's anything on the stack, print it
|
|
if (stack->count > 0) {
|
|
Toy_Bucket* stringBucket = Toy_allocateBucket(TOY_BUCKET_IDEAL);
|
|
|
|
printf("Stack Dump\n-------------------------\ntype\tvalue\n");
|
|
for (unsigned int i = 0; i < stack->count; i++) {
|
|
Toy_Value v = ((Toy_Value*)(stack + 1))[i]; //'stack + 1' is a naughty trick
|
|
|
|
//print type
|
|
printf("%s\t", Toy_private_getValueTypeAsCString(v.type));
|
|
|
|
//print value
|
|
Toy_String* string = Toy_stringifyValue(&stringBucket, Toy_unwrapValue(v));
|
|
char* buffer = Toy_getStringRawBuffer(string);
|
|
printf("%s", buffer);
|
|
free(buffer);
|
|
Toy_freeString(string);
|
|
|
|
printf("\n");
|
|
}
|
|
|
|
Toy_freeBucket(&stringBucket);
|
|
}
|
|
}
|
|
|
|
static void debugScopePrint(Toy_Scope* scope, int depth) {
|
|
//DEBUG: if there's anything in the scope, print it
|
|
if (scope->table->count > 0) {
|
|
Toy_Bucket* stringBucket = Toy_allocateBucket(TOY_BUCKET_IDEAL);
|
|
|
|
printf("Scope %d Dump\n-------------------------\ntype\tname\tvalue\n", depth);
|
|
for (unsigned int i = 0; i < scope->table->capacity; i++) {
|
|
if ( (TOY_VALUE_IS_STRING(scope->table->data[i].key) && TOY_VALUE_AS_STRING(scope->table->data[i].key)->info.type == TOY_STRING_NAME) != true) {
|
|
continue;
|
|
}
|
|
|
|
Toy_Value k = scope->table->data[i].key;
|
|
Toy_Value v = scope->table->data[i].value;
|
|
|
|
printf("%s\t%s\t", Toy_private_getValueTypeAsCString(v.type), TOY_VALUE_AS_STRING(k)->name.data);
|
|
|
|
//print value
|
|
Toy_String* string = Toy_stringifyValue(&stringBucket, Toy_unwrapValue(v));
|
|
char* buffer = Toy_getStringRawBuffer(string);
|
|
printf("%s", buffer);
|
|
free(buffer);
|
|
Toy_freeString(string);
|
|
|
|
printf("\n");
|
|
}
|
|
|
|
Toy_freeBucket(&stringBucket);
|
|
}
|
|
|
|
if (scope->next != NULL) {
|
|
debugScopePrint(scope->next, depth + 1);
|
|
}
|
|
}
|
|
|
|
//main file
|
|
int main(int argc, const char* argv[]) {
|
|
Toy_setPrintCallback(printCallback);
|
|
Toy_setErrorCallback(errorAndExitCallback);
|
|
Toy_setAssertFailureCallback(assertFailureAndExitCallback);
|
|
|
|
//if there's args, process them
|
|
CmdLine cmd = parseCmdLine(argc, argv);
|
|
|
|
//output options
|
|
if (cmd.silentPrint) {
|
|
Toy_setPrintCallback(noOpCallback);
|
|
}
|
|
|
|
if (cmd.silentAssert) {
|
|
Toy_setAssertFailureCallback(silentExitCallback);
|
|
}
|
|
|
|
//process
|
|
if (cmd.error) {
|
|
usageCmdLine(argc, argv);
|
|
}
|
|
else if (cmd.help) {
|
|
helpCmdLine(argc, argv);
|
|
}
|
|
else if (cmd.version) {
|
|
versionCmdLine(argc, argv);
|
|
}
|
|
else if (cmd.infile != NULL) {
|
|
//run the given file
|
|
int size;
|
|
unsigned char* source = readFile(cmd.infile, &size);
|
|
|
|
//check the file
|
|
if (source == NULL) {
|
|
if (size == 0) {
|
|
fprintf(stderr, TOY_CC_ERROR "ERROR: Could not parse an empty file '%s', exiting\n" TOY_CC_RESET, cmd.infile);
|
|
return -1;
|
|
}
|
|
|
|
else if (size == -1) {
|
|
fprintf(stderr, TOY_CC_ERROR "ERROR: File not found '%s', exiting\n" TOY_CC_RESET, cmd.infile);
|
|
return -1;
|
|
}
|
|
|
|
else {
|
|
fprintf(stderr, TOY_CC_ERROR "ERROR: Unknown error while reading file '%s', exiting\n" TOY_CC_RESET, cmd.infile);
|
|
return -1;
|
|
}
|
|
}
|
|
|
|
free(cmd.infile);
|
|
|
|
cmd.infile = NULL;
|
|
cmd.infileLength = 0;
|
|
|
|
Toy_Lexer lexer;
|
|
Toy_bindLexer(&lexer, (char*)source);
|
|
|
|
Toy_Parser parser;
|
|
Toy_bindParser(&parser, &lexer);
|
|
|
|
Toy_configureParser(&parser, cmd.removeAssert);
|
|
|
|
Toy_Bucket* bucket = Toy_allocateBucket(TOY_BUCKET_IDEAL);
|
|
Toy_Ast* ast = Toy_scanParser(&bucket, &parser);
|
|
|
|
Toy_ModuleBundle bc = Toy_compileModuleBundle(ast);
|
|
|
|
//run the setup
|
|
Toy_VM vm;
|
|
Toy_initVM(&vm);
|
|
Toy_bindVM(&vm, &bc);
|
|
|
|
//run
|
|
Toy_runVM(&vm);
|
|
|
|
//print the debug info
|
|
if (cmd.verboseDebugPrint) {
|
|
debugStackPrint(vm.stack);
|
|
debugScopePrint(vm.scope, 0);
|
|
}
|
|
|
|
//cleanup
|
|
Toy_freeVM(&vm);
|
|
Toy_freeModuleBundle(bc);
|
|
Toy_freeBucket(&bucket);
|
|
free(source);
|
|
}
|
|
else {
|
|
repl(argv[0]);
|
|
}
|
|
|
|
return 0;
|
|
}
|