diff --git a/.gitignore b/.gitignore index a3e12f7..183033f 100644 --- a/.gitignore +++ b/.gitignore @@ -1,35 +1,59 @@ -#Editor generated files -*.suo -*.ncb -*.user -compile_commands.json +# Prerequisites +*.d -#Directories -Release/ -Debug/ -Out/ -release/ -debug/ -out/ -bin/ -.cache/ -.vs/ - -#Project generated files -*.db +# Object files *.o -*.a -*.so -*.dll -*.exe -*.meta -*.log -*.out -*.stackdump -*.tb -*.filters -[Dd]ocs/ +*.ko +*.obj +*.elf -#Shell files -*.bat -*.sh +# 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 + +.cproject +.project +.settings/ +temp/ +Release/ +out/ \ No newline at end of file diff --git a/scripts/test.toy b/scripts/test.toy index 762cfff..f1f584b 100644 --- a/scripts/test.toy +++ b/scripts/test.toy @@ -1,12 +1,13 @@ -import standard; -var array = [42]; +fn f() { + // +} -var result = null; +fn g() { + fn i() { + // + } +} -//problematic line -result = max(0, array[0]); - -assert result == 42, "Indexing in argument list failed"; - - -print "All good"; +fn h() { + // +} \ No newline at end of file diff --git a/source/toy_common.h b/source/toy_common.h index e67704c..7b01fc0 100644 --- a/source/toy_common.h +++ b/source/toy_common.h @@ -64,7 +64,7 @@ The current patch version of Toy. This value is embedded into the bytecode. This value MUST fit into an unsigned char. !*/ -#define TOY_VERSION_PATCH 0 +#define TOY_VERSION_PATCH 1 /*! ### TOY_VERSION_BUILD diff --git a/source/toy_compiler.c b/source/toy_compiler.c index 7797f10..6a08fd6 100644 --- a/source/toy_compiler.c +++ b/source/toy_compiler.c @@ -841,12 +841,20 @@ static Toy_Opcode Toy_writeCompilerWithJumps(Toy_Compiler* compiler, Toy_ASTNode compiler->count += sizeof(unsigned short); //2 bytes //write the body - compiler->bytecode[compiler->count++] = TOY_OP_SCOPE_BEGIN; //1 byte + bool closeScope = false; + if (node->pathFor.thenPath->type != TOY_AST_NODE_BLOCK) { + compiler->bytecode[compiler->count++] = TOY_OP_SCOPE_BEGIN; //1 byte + closeScope = true; + } + override = Toy_writeCompilerWithJumps(compiler, node->pathFor.thenPath, &breakAddresses, &continueAddresses, jumpOffsets, rootNode); if (override != TOY_OP_EOF) {//compensate for indexing & dot notation being screwy compiler->bytecode[compiler->count++] = (unsigned char)override; //1 byte } - compiler->bytecode[compiler->count++] = TOY_OP_SCOPE_END; //1 byte + + if (closeScope) { + compiler->bytecode[compiler->count++] = TOY_OP_SCOPE_END; //1 byte + } //for-breaks actually jump to the bottom int jumpToIncrement = compiler->count; @@ -857,6 +865,9 @@ static Toy_Opcode Toy_writeCompilerWithJumps(Toy_Compiler* compiler, Toy_ASTNode compiler->bytecode[compiler->count++] = (unsigned char)override; //1 byte } + //BUGFIX: clear the stack after each loop + compiler->bytecode[compiler->count++] = TOY_OP_POP_STACK; //1 byte + compiler->bytecode[compiler->count++] = TOY_OP_JUMP; //1 byte unsigned short tmpVal = jumpToStart + jumpOffsets; memcpy(compiler->bytecode + compiler->count, &tmpVal, sizeof(tmpVal)); @@ -880,9 +891,6 @@ static Toy_Opcode Toy_writeCompilerWithJumps(Toy_Compiler* compiler, Toy_ASTNode memcpy(compiler->bytecode + point, &tmpVal, sizeof(tmpVal)); } - //clear the stack after use - compiler->bytecode[compiler->count++] = TOY_OP_POP_STACK; //1 byte - //cleanup Toy_freeLiteralArray(&breakAddresses); Toy_freeLiteralArray(&continueAddresses); diff --git a/tools/disassembler/cargs.c b/tools/disassembler/cargs.c new file mode 100644 index 0000000..52f1c8e --- /dev/null +++ b/tools/disassembler/cargs.c @@ -0,0 +1,427 @@ +/* + * Project: https://github.com/likle/cargs + * License: MIT + */ + +#include +#include +#include +#include +#include + +#define CAG_OPTION_PRINT_DISTANCE 4 +#define CAG_OPTION_PRINT_MIN_INDENTION 20 + +static void cag_option_print_value(const cag_option *option, + size_t *accessor_length, FILE *destination) { + if (option->value_name != NULL) { + *accessor_length += fprintf(destination, "=%s", option->value_name); + } +} + +static void cag_option_print_letters(const cag_option *option, bool *first, + size_t *accessor_length, FILE *destination) { + const char *access_letter; + access_letter = option->access_letters; + if (access_letter != NULL) { + while (*access_letter) { + if (*first) { + *accessor_length += fprintf(destination, "-%c", *access_letter); + *first = false; + } else { + *accessor_length += fprintf(destination, ", -%c", + *access_letter); + } + ++access_letter; + } + } +} + +static void cag_option_print_name(const cag_option *option, bool *first, + size_t *accessor_length, FILE *destination) { + if (option->access_name != NULL) { + if (*first) { + *accessor_length += fprintf(destination, "--%s", + option->access_name); + } else { + *accessor_length += fprintf(destination, ", --%s", + option->access_name); + } + } +} + +static size_t cag_option_get_print_indention(const cag_option *options, + size_t option_count) { + size_t option_index, indention, result; + const cag_option *option; + + result = CAG_OPTION_PRINT_MIN_INDENTION; + + for (option_index = 0; option_index < option_count; ++option_index) { + indention = CAG_OPTION_PRINT_DISTANCE; + option = &options[option_index]; + if (option->access_letters != NULL && *option->access_letters) { + indention += strlen(option->access_letters) * 4 - 2; + if (option->access_name != NULL) { + indention += strlen(option->access_name) + 4; + } + } else if (option->access_name != NULL) { + indention += strlen(option->access_name) + 2; + } + + if (option->value_name != NULL) { + indention += strlen(option->value_name) + 1; + } + + if (indention > result) { + result = indention; + } + } + + return result; +} + +void cag_option_print(const cag_option *options, size_t option_count, + FILE *destination) { + size_t option_index, indention, i, accessor_length; + const cag_option *option; + bool first; + + indention = cag_option_get_print_indention(options, option_count); + + for (option_index = 0; option_index < option_count; ++option_index) { + option = &options[option_index]; + accessor_length = 0; + first = true; + + fputs(" ", destination); + + cag_option_print_letters(option, &first, &accessor_length, destination); + cag_option_print_name(option, &first, &accessor_length, destination); + cag_option_print_value(option, &accessor_length, destination); + + for (i = accessor_length; i < indention; ++i) { + fputs(" ", destination); + } + + fputs(" ", destination); + fputs(option->description, destination); + + fprintf(destination, "\n"); + } +} + +void cag_option_prepare(cag_option_context *context, const cag_option *options, + size_t option_count, int argc, char **argv) { + // This just initialized the values to the beginning of all the arguments. + context->options = options; + context->option_count = option_count; + context->argc = argc; + context->argv = argv; + context->index = 1; + context->inner_index = 0; + context->forced_end = false; +} + +static const cag_option* cag_option_find_by_name(cag_option_context *context, + char *name, size_t name_size) { + const cag_option *option; + size_t i; + + // We loop over all the available options and stop as soon as we have found + // one. We don't use any hash map table, since there won't be that many + // arguments anyway. + for (i = 0; i < context->option_count; ++i) { + option = &context->options[i]; + + // The option might not have an item name, we can just skip those. + if (option->access_name == NULL) { + continue; + } + + // Try to compare the name of the access name. We can use the name_size or + // this comparison, since we are guaranteed to have null-terminated access + // names. + if (strncmp(option->access_name, name, name_size) == 0) { + return option; + } + } + + return NULL; +} + +static const cag_option* cag_option_find_by_letter(cag_option_context *context, + char letter) { + const cag_option *option; + size_t i; + + // We loop over all the available options and stop as soon as we have found + // one. We don't use any look up table, since there won't be that many + // arguments anyway. + for (i = 0; i < context->option_count; ++i) { + option = &context->options[i]; + + // If this option doesn't have any access letters we will skip them. + if (option->access_letters == NULL) { + continue; + } + + // Verify whether this option has the access letter in it's access letter + // string. If it does, then this is our option. + if (strchr(option->access_letters, letter) != NULL) { + return option; + } + } + + return NULL; +} + +static void cag_option_parse_value(cag_option_context *context, + const cag_option *option, char **c) { + // And now let's check whether this option is supposed to have a value, which + // is the case if there is a value name set. The value can be either submitted + // with a '=' sign or a space, which means we would have to jump over to the + // next argv index. This is somewhat ugly, but we do it to behave the same as + // the other option parsers. + if (option->value_name != NULL) { + if (**c == '=') { + context->value = ++(*c); + } else { + // If the next index is larger or equal to the argument count, then the + // parameter for this option is missing. The user will know about this, + // since the value pointer of the context will be NULL because we don't + // set it here in that case. + if (context->argc > context->index + 1) { + // We consider this argv to be the value, no matter what the contents + // are. + ++context->index; + *c = context->argv[context->index]; + context->value = *c; + } + } + + // Move c to the end of the value, to not confuse the caller about our + // position. + while (**c) { + ++(*c); + } + } +} + +static void cag_option_parse_access_name(cag_option_context *context, char **c) { + const cag_option *option; + char *n; + + // Now we need to extract the access name, which is any symbol up to a '=' or + // a '\0'. + n = *c; + while (**c && **c != '=') { + ++*c; + } + + // Now this will obviously always be true, but we are paranoid. Sometimes. It + // doesn't hurt to check. + assert(*c >= n); + + // Figure out which option this name belongs to. This might return NULL if the + // name is not registered, which means the user supplied an unknown option. In + // that case we return true to indicate that we finished with this option. We + // have to skip the value parsing since we don't know whether the user thinks + // this option has one or not. Since we don't set any identifier specifically, + // it will remain '?' within the context. + option = cag_option_find_by_name(context, n, (size_t) (*c - n)); + if (option == NULL) { + // Since this option is invalid, we will move on to the next index. There is + // nothing we can do about this. + ++context->index; + return; + } + + // We found an option and now we can specify the identifier within the + // context. + context->identifier = option->identifier; + + // And now we try to parse the value. This function will also check whether + // this option is actually supposed to have a value. + cag_option_parse_value(context, option, c); + + // And finally we move on to the next index. + ++context->index; +} + +static void cag_option_parse_access_letter(cag_option_context *context, + char **c) { + const cag_option *option; + char *n = *c; + char *v; + + // Figure out which option this letter belongs to. This might return NULL if + // the letter is not registered, which means the user supplied an unknown + // option. In that case we return true to indicate that we finished with this + // option. We have to skip the value parsing since we don't know whether the + // user thinks this option has one or not. Since we don't set any identifier + // specifically, it will remain '?' within the context. + option = cag_option_find_by_letter(context, n[context->inner_index]); + if (option == NULL) { + ++context->index; + context->inner_index = 0; + return; + } + + // We found an option and now we can specify the identifier within the + // context. + context->identifier = option->identifier; + + // And now we try to parse the value. This function will also check whether + // this option is actually supposed to have a value. + v = &n[++context->inner_index]; + cag_option_parse_value(context, option, &v); + + // Check whether we reached the end of this option argument. + if (*v == '\0') { + ++context->index; + context->inner_index = 0; + } +} + +static void cag_option_shift(cag_option_context *context, int start, int option, + int end) { + char *tmp; + int a_index, shift_index, shift_count, left_index, right_index; + + shift_count = option - start; + + // There is no shift is required if the start and the option have the same + // index. + if (shift_count == 0) { + return; + } + + // Lets loop through the option strings first, which we will move towards the + // beginning. + for (a_index = option; a_index < end; ++a_index) { + // First remember the current option value, because we will have to save + // that later at the beginning. + tmp = context->argv[a_index]; + + // Let's loop over all option values and shift them one towards the end. + // This will override the option value we just stored temporarily. + for (shift_index = 0; shift_index < shift_count; ++shift_index) { + left_index = a_index - shift_index; + right_index = a_index - shift_index - 1; + context->argv[left_index] = context->argv[right_index]; + } + + // Now restore the saved option value at the beginning. + context->argv[a_index - shift_count] = tmp; + } + + // The new index will be before all non-option values, in such a way that they + // all will be moved again in the next fetch call. + context->index = end - shift_count; +} + +static bool cag_option_is_argument_string(const char *c) { + return *c == '-' && *(c + 1) != '\0'; +} + +static int cag_option_find_next(cag_option_context *context) { + int next_index, next_option_index; + char *c; + + // Prepare to search the next option at the next index. + next_index = context->index; + next_option_index = next_index; + + // Grab a pointer to the string and verify that it is not the end. If it is + // the end, we have to return false to indicate that we finished. + c = context->argv[next_option_index]; + if (context->forced_end || c == NULL) { + return -1; + } + + // Check whether it is a '-'. We need to find the next option - and an option + // always starts with a '-'. If there is a string "-\0", we don't consider it + // as an option neither. + while (!cag_option_is_argument_string(c)) { + c = context->argv[++next_option_index]; + if (c == NULL) { + // We reached the end and did not find any argument anymore. Let's tell + // our caller that we reached the end. + return -1; + } + } + + // Indicate that we found an option which can be processed. The index of the + // next option will be returned. + return next_option_index; +} + +bool cag_option_fetch(cag_option_context *context) { + char *c; + int old_index, new_index; + + // Reset our identifier to a question mark, which indicates an "unknown" + // option. The value is set to NULL, to make sure we are not carrying the + // parameter from the previous option to this one. + context->identifier = '?'; + context->value = NULL; + + // Check whether there are any options left to parse and remember the old + // index as well as the new index. In the end we will move the option junk to + // the beginning, so that non option arguments can be read. + old_index = context->index; + new_index = cag_option_find_next(context); + if (new_index >= 0) { + context->index = new_index; + } else { + return false; + } + + // Grab a pointer to the beginning of the option. At this point, the next + // character must be a '-', since if it was not the prepare function would + // have returned false. We will skip that symbol and proceed. + c = context->argv[context->index]; + assert(*c == '-'); + ++c; + + // Check whether this is a long option, starting with a double "--". + if (*c == '-') { + ++c; + + // This might be a double "--" which indicates the end of options. If this + // is the case, we will not move to the next index. That ensures that + // another call to the fetch function will not skip the "--". + if (*c == '\0') { + context->forced_end = true; + } else { + // We parse now the access name. All information about it will be written + // to the context. + cag_option_parse_access_name(context, &c); + } + } else { + // This is no long option, so we can just parse an access letter. + cag_option_parse_access_letter(context, &c); + } + + // Move the items so that the options come first followed by non-option + // arguments. + cag_option_shift(context, old_index, new_index, context->index); + + return context->forced_end == false; +} + +char cag_option_get(const cag_option_context *context) { + // We just return the identifier here. + return context->identifier; +} + +const char* cag_option_get_value(const cag_option_context *context) { + // We just return the internal value pointer of the context. + return context->value; +} + +int cag_option_get_index(const cag_option_context *context) { + // Either we point to a value item, + return context->index; +} diff --git a/tools/disassembler/cargs.h b/tools/disassembler/cargs.h new file mode 100644 index 0000000..c35252e --- /dev/null +++ b/tools/disassembler/cargs.h @@ -0,0 +1,169 @@ +/* + * Project: https://github.com/likle/cargs + * License: MIT + */ + +#ifndef CARGS_H_ +#define CARGS_H_ + +/** + * This is a simple alternative cross-platform implementation of getopt, which + * is used to parse argument strings submitted to the executable (argc and argv + * which are received in the main function). + */ + +#ifndef CAG_LIBRARY_H +#define CAG_LIBRARY_H + +#include +#include +#include + +#if defined(_WIN32) || defined(__CYGWIN__) +#define CAG_EXPORT __declspec(dllexport) +#define CAG_IMPORT __declspec(dllimport) +#elif __GNUC__ >= 4 +#define CAG_EXPORT __attribute__((visibility("default"))) +#define CAG_IMPORT __attribute__((visibility("default"))) +#else +#define CAG_EXPORT +#define CAG_IMPORT +#endif + +#if defined(CAG_SHARED) +#if defined(CAG_EXPORTS) +#define CAG_PUBLIC CAG_EXPORT +#else +#define CAG_PUBLIC CAG_IMPORT +#endif +#else +#define CAG_PUBLIC +#endif + +#ifdef __cplusplus +extern "C" { +#endif + +/** + * An option is used to describe a flag/argument option submitted when the + * program is run. + */ +typedef struct cag_option { + const char identifier; + const char *access_letters; + const char *access_name; + const char *value_name; + const char *description; +} cag_option; + +/** + * A context is used to iterate over all options provided. It stores the parsing + * state. + */ +typedef struct cag_option_context { + const struct cag_option *options; + size_t option_count; + int argc; + char **argv; + int index; + int inner_index; + bool forced_end; + char identifier; + char *value; +} cag_option_context; + +/** + * This is just a small macro which calculates the size of an array. + */ +#define CAG_ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) + +/** + * @brief Prints all options to the terminal. + * + * This function prints all options to the terminal. This can be used to + * generate the output for a "--help" option. + * + * @param options The options which will be printed. + * @param option_count The option count which will be printed. + * @param destination The destination where the output will be printed. + */ +CAG_PUBLIC void cag_option_print(const cag_option *options, size_t option_count, + FILE *destination); + +/** + * @brief Prepare argument options context for parsing. + * + * This function prepares the context for iteration and initializes the context + * with the supplied options and arguments. After the context has been prepared, + * it can be used to fetch arguments from it. + * + * @param context The context which will be initialized. + * @param options The registered options which are available for the program. + * @param option_count The amount of options which are available for the + * program. + * @param argc The amount of arguments the user supplied in the main function. + * @param argv A pointer to the arguments of the main function. + */ +CAG_PUBLIC void cag_option_prepare(cag_option_context *context, + const cag_option *options, size_t option_count, int argc, char **argv); + +/** + * @brief Fetches an option from the argument list. + * + * This function fetches a single option from the argument list. The context + * will be moved to that item. Information can be extracted from the context + * after the item has been fetched. + * The arguments will be re-ordered, which means that non-option arguments will + * be moved to the end of the argument list. After all options have been + * fetched, all non-option arguments will be positioned after the index of + * the context. + * + * @param context The context from which we will fetch the option. + * @return Returns true if there was another option or false if the end is + * reached. + */ +CAG_PUBLIC bool cag_option_fetch(cag_option_context *context); + +/** + * @brief Gets the identifier of the option. + * + * This function gets the identifier of the option, which should be unique to + * this option and can be used to determine what kind of option this is. + * + * @param context The context from which the option was fetched. + * @return Returns the identifier of the option. + */ +CAG_PUBLIC char cag_option_get(const cag_option_context *context); + +/** + * @brief Gets the value from the option. + * + * This function gets the value from the option, if any. If the option does not + * contain a value, this function will return NULL. + * + * @param context The context from which the option was fetched. + * @return Returns a pointer to the value or NULL if there is no value. + */ +CAG_PUBLIC const char* cag_option_get_value(const cag_option_context *context); + +/** + * @brief Gets the current index of the context. + * + * This function gets the index within the argv arguments of the context. The + * context always points to the next item which it will inspect. This is + * particularly useful to inspect the original argument array, or to get + * non-option arguments after option fetching has finished. + * + * @param context The context from which the option was fetched. + * @return Returns the current index of the context. + */ +CAG_PUBLIC int cag_option_get_index(const cag_option_context *context); + +#ifdef __cplusplus +} // extern "C" +#endif + +#endif + +#endif /* CARGS_H_ */ + diff --git a/tools/disassembler/disassembler.c b/tools/disassembler/disassembler.c index 5ad786b..a576cb0 100644 --- a/tools/disassembler/disassembler.c +++ b/tools/disassembler/disassembler.c @@ -13,6 +13,7 @@ #include #include +#include "disassembler_utils.h" #include "disassembler.h" #define SPC(n) printf("%.*s", n, "| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |"); @@ -72,7 +73,7 @@ const char *OP_STR[] = { EP(DIS_OP_POP_STACK), // EP(DIS_OP_TERNARY), // EP(DIS_OP_FN_END), // - }; +}; const char *LIT_STR[] = { EP(DIS_LITERAL_NULL), // @@ -95,7 +96,7 @@ const char *LIT_STR[] = { EP(DIS_LITERAL_FUNCTION_NATIVE), // EP(DIS_LITERAL_FUNCTION_HOOK), // EP(DIS_LITERAL_INDEX_BLANK), // - }; +}; enum DIS_ARG_TYPE { DIS_ARG_NONE, // @@ -106,59 +107,60 @@ enum DIS_ARG_TYPE { DIS_ARG_STRING // }; -const uint8_t OP_ARGS[DIS_OP_END_OPCODES][2] = { - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_EOF - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_PASS - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_ASSERT - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_PRINT - { DIS_ARG_BYTE, DIS_ARG_NONE }, // DIS_OP_LITERAL - { DIS_ARG_WORD, DIS_ARG_NONE }, // DIS_OP_LITERAL_LONG - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_LITERAL_RAW - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_NEGATE - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_ADDITION - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_SUBTRACTION - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_MULTIPLICATION - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_DIVISION - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_MODULO - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_GROUPING_BEGIN - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_GROUPING_END - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_SCOPE_BEGIN - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_SCOPE_END - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_TYPE_DECL_removed - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_TYPE_DECL_LONG_removed - { DIS_ARG_BYTE, DIS_ARG_BYTE }, // DIS_OP_VAR_DECL - { DIS_ARG_WORD, DIS_ARG_WORD }, // DIS_OP_VAR_DECL_LONG - { DIS_ARG_BYTE, DIS_ARG_BYTE }, // DIS_OP_FN_DECL - { DIS_ARG_WORD, DIS_ARG_WORD }, // DIS_OP_FN_DECL_LONG - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_VAR_ASSIGN - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_VAR_ADDITION_ASSIGN - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_VAR_SUBTRACTION_ASSIGN - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_VAR_MULTIPLICATION_ASSIGN - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_VAR_DIVISION_ASSIGN - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_VAR_MODULO_ASSIGN - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_TYPE_CAST - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_TYPE_OF - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_IMPORT - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_EXPORT_removed - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_INDEX - { DIS_ARG_BYTE, DIS_ARG_NONE }, // DIS_OP_INDEX_ASSIGN - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_INDEX_ASSIGN_INTERMEDIATE - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_DOT - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_COMPARE_EQUAL - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_COMPARE_NOT_EQUAL - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_COMPARE_LESS - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_COMPARE_LESS_EQUAL - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_COMPARE_GREATER - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_COMPARE_GREATER_EQUAL - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_INVERT - { DIS_ARG_WORD, DIS_ARG_NONE }, // DIS_OP_AND - { DIS_ARG_WORD, DIS_ARG_NONE }, // DIS_OP_OR - { DIS_ARG_WORD, DIS_ARG_NONE }, // DIS_OP_JUMP - { DIS_ARG_WORD, DIS_ARG_NONE }, // DIS_OP_IF_FALSE_JUMP - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_FN_CALL - { DIS_ARG_WORD, DIS_ARG_NONE }, // DIS_OP_FN_RETURN - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_POP_STACK - { DIS_ARG_NONE, DIS_ARG_NONE }, // DIS_OP_TERNARY +const uint8_t OP_ARGS[DIS_OP_END_OPCODES][3] = { + // | first arg | second arg | jump | + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_EOF + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_PASS + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_ASSERT + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_PRINT + { DIS_ARG_BYTE, DIS_ARG_NONE, false }, // DIS_OP_LITERAL + { DIS_ARG_WORD, DIS_ARG_NONE, false }, // DIS_OP_LITERAL_LONG + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_LITERAL_RAW + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_NEGATE + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_ADDITION + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_SUBTRACTION + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_MULTIPLICATION + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_DIVISION + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_MODULO + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_GROUPING_BEGIN + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_GROUPING_END + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_SCOPE_BEGIN + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_SCOPE_END + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_TYPE_DECL_removed + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_TYPE_DECL_LONG_removed + { DIS_ARG_BYTE, DIS_ARG_BYTE, false }, // DIS_OP_VAR_DECL + { DIS_ARG_WORD, DIS_ARG_WORD, false }, // DIS_OP_VAR_DECL_LONG + { DIS_ARG_BYTE, DIS_ARG_BYTE, false }, // DIS_OP_FN_DECL + { DIS_ARG_WORD, DIS_ARG_WORD, false }, // DIS_OP_FN_DECL_LONG + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_VAR_ASSIGN + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_VAR_ADDITION_ASSIGN + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_VAR_SUBTRACTION_ASSIGN + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_VAR_MULTIPLICATION_ASSIGN + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_VAR_DIVISION_ASSIGN + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_VAR_MODULO_ASSIGN + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_TYPE_CAST + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_TYPE_OF + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_IMPORT + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_EXPORT_removed + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_INDEX + { DIS_ARG_BYTE, DIS_ARG_NONE, false }, // DIS_OP_INDEX_ASSIGN + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_INDEX_ASSIGN_INTERMEDIATE + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_DOT + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_COMPARE_EQUAL + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_COMPARE_NOT_EQUAL + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_COMPARE_LESS + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_COMPARE_LESS_EQUAL + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_COMPARE_GREATER + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_COMPARE_GREATER_EQUAL + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_INVERT + { DIS_ARG_WORD, DIS_ARG_NONE, true }, // DIS_OP_AND + { DIS_ARG_WORD, DIS_ARG_NONE, true }, // DIS_OP_OR + { DIS_ARG_WORD, DIS_ARG_NONE, true }, // DIS_OP_JUMP + { DIS_ARG_WORD, DIS_ARG_NONE, true }, // DIS_OP_IF_FALSE_JUMP + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_FN_CALL + { DIS_ARG_WORD, DIS_ARG_NONE, false }, // DIS_OP_FN_RETURN + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_POP_STACK + { DIS_ARG_NONE, DIS_ARG_NONE, false }, // DIS_OP_TERNARY }; typedef struct dis_program_s { @@ -167,10 +169,13 @@ typedef struct dis_program_s { uint32_t pc; } dis_program_t; -typedef struct dis_func_op_s { +typedef struct fun_code_s { uint32_t start; - uint32_t end; -} dis_func_op_t; + uint32_t len; + char *fun; +} fun_code_t; + +uint32_t jump_label; static void dis_print_opcode(uint8_t op); @@ -220,16 +225,18 @@ static void consumeByte(uint8_t byte, uint8_t *tb, uint32_t *count) { static void dis_disassembler_init(dis_program_t **prg) { (*prg) = malloc(sizeof(struct dis_program_s)); + (*prg)->program = NULL; (*prg)->len = 0; (*prg)->pc = 0; } static void dis_disassembler_deinit(dis_program_t **prg) { - free((*prg)->program); + if((*prg)->program != NULL) + free((*prg)->program); free((*prg)); } -static uint8_t dis_load_file(const char *filename, dis_program_t **prg) { +static uint8_t dis_load_file(const char *filename, dis_program_t **prg, bool alt_fmt) { FILE *f; size_t fsize, bytes; uint32_t count = 0; @@ -250,18 +257,26 @@ static uint8_t dis_load_file(const char *filename, dis_program_t **prg) { (*prg)->program[count++] = buf; (*prg)->len = fsize; - printf("\nFile: %s\nSize: %zu\n", filename, fsize); + + if (!alt_fmt) + printf("\nFile: %s\nSize: %zu\n", filename, fsize); + else + printf("\n.comment File: %s, Size: %zu\n", filename, fsize); fclose(f); return 0; } -static void dis_read_header(dis_program_t **prg) { +static void dis_read_header(dis_program_t **prg, bool alt_fmt) { const unsigned char major = readByte((*prg)->program, &((*prg)->pc)); const unsigned char minor = readByte((*prg)->program, &((*prg)->pc)); const unsigned char patch = readByte((*prg)->program, &((*prg)->pc)); const char *build = readString((*prg)->program, &((*prg)->pc)); - printf("[Header Version: %d.%d.%d (%s)]\n", major, minor, patch, build); + + if (!alt_fmt) + printf("[Header Version: %d.%d.%d (%s)]\n", major, minor, patch, build); + else + printf(".comment Header Version: %d.%d.%d (%s)\n", major, minor, patch, build); } static void dis_print_opcode(uint8_t op) { @@ -278,77 +293,165 @@ static void dis_print_opcode(uint8_t op) { /////////////////////////////////////////////////////////////////////////////// -#define S_OP(n) \ +#define S_OP(n, p) \ switch (OP_ARGS[opcode][n]) { \ case DIS_ARG_NONE: \ break; \ case DIS_ARG_BYTE: \ uint = readByte((*prg)->program, &pc); \ - printf(" b(%d)", uint); \ + if (p) printf(" b(%d)", uint); \ break; \ case DIS_ARG_WORD: \ uint = readWord((*prg)->program, &pc);\ - printf(" w(%d)", uint); \ + if (p) printf(" w(%d)", uint); \ break; \ case DIS_ARG_INTEGER: \ intg = readInt((*prg)->program, &pc); \ - printf(" i(%d)", intg); \ + if (p) printf(" i(%d)", intg); \ break; \ case DIS_ARG_FLOAT: \ flt = readFloat((*prg)->program, &pc); \ - printf(" f(%f)", flt); \ + if (p) printf(" f(%f)", flt); \ break; \ case DIS_ARG_STRING: \ str = readString((*prg)->program, &pc); \ - printf(" s(%s)", str); \ + if (p) printf(" s(%s)", str); \ break; \ default: \ printf("ERROR, unknown argument type\n"); \ exit(1); \ } -static void dis_disassemble_section(dis_program_t **prg, uint32_t pc, uint32_t len, uint8_t spaces, bool is_function) { - uint8_t opcode; - uint32_t uint; - int32_t intg; - float flt; - char *str; +static void dis_disassemble_section(dis_program_t **prg, uint32_t pc, uint32_t len, uint8_t spaces, bool is_function, bool alt_fmt) { + uint8_t opcode = 0; + uint16_t uint = 0; + int32_t intg = 0; + float flt = 0; + char *str = NULL; - //first 4 bytes of the program section within a function are actually specifying the parameter and return lists + // first 4 bytes of the program section within a function are actually specifying the parameter and return lists if (is_function) { printf("\n"); uint16_t args = readWord((*prg)->program, &pc); uint16_t rets = readWord((*prg)->program, &pc); - SPC(spaces); - printf("| ( args %d, rets %d )", args, rets); + if (!alt_fmt) { + SPC(spaces); + printf("| "); + } else + printf(".comment args:%d, rets:%d", args, rets); } uint32_t pc_start = pc; + + uint32_t labels_qty = 0; + uint16_t *label_line = NULL; + uint32_t *label_id = NULL; + if (alt_fmt) { + // first pass: search jump labels + label_line = malloc(sizeof(uint16_t)); + label_id = malloc(sizeof(uint32_t)); + + while (pc < len) { + label_line = realloc(label_line, (labels_qty + 1) * sizeof(uint16_t)); + label_id = realloc(label_id, (labels_qty + 1) * sizeof(uint32_t)); + + opcode = (*prg)->program[pc]; + if (alt_fmt && (opcode == 255 || opcode == 0)) { + ++pc; + continue; + } + + if (opcode > DIS_OP_END_OPCODES) + continue; + + ++pc; + + S_OP(0, 0); + + if (OP_ARGS[opcode][2]) { + label_line[labels_qty] = uint; + label_id[labels_qty] = jump_label++; + ++labels_qty; + } + + S_OP(1, 0); + } + + pc = pc_start; + } + while (pc < len) { opcode = (*prg)->program[pc]; + + if (alt_fmt) { + for (uint32_t lbl = 0; lbl < labels_qty; lbl++) { + if (pc - pc_start == label_line[lbl]) { + printf("\nJL_%04d_:", label_id[lbl]); + break; + } + } + } + + if (alt_fmt && (opcode == 255 || opcode == 0)) { + ++pc; + continue; + } + printf("\n"); - SPC(spaces); - printf("| [ %05d ](%03d) ", (pc++) - pc_start, opcode); + if (!alt_fmt) { + SPC(spaces); + printf("| "); + printf("[%05d](%03d) ", (pc++) - pc_start, opcode); + } else { + printf(" "); + pc++; + } + dis_print_opcode(opcode); - if (opcode > DIS_OP_END_OPCODES) + if (opcode >= DIS_OP_END_OPCODES) continue; - S_OP(0); - S_OP(1); + if (alt_fmt) { + if (OP_ARGS[opcode][2]) { + uint = readWord((*prg)->program, &pc); + for (uint32_t lbl = 0; lbl < labels_qty; lbl++) { + if (uint == label_line[lbl]) { + printf(" JL_%04d_", label_id[lbl]); + break; + } + } + } else + S_OP(0, 1); + } else + S_OP(0, 1); + + S_OP(1, 1); } + + if (alt_fmt) { + free(label_line); + free(label_id); + } + + if (alt_fmt && (*prg)->program[pc - 5] != DIS_OP_FN_RETURN) + printf("\n FN_RETURN w(0)"); } #define LIT_ADD(a, b, c) b[c] = a; ++c; -static void dis_read_interpreter_sections(dis_program_t **prg, uint32_t *pc, uint8_t spaces, char *tree) { +static void dis_read_interpreter_sections(dis_program_t **prg, uint32_t *pc, uint8_t spaces, char *tree, bool alt_fmt) { uint32_t literal_count = 0; uint8_t literal_type[65536]; const unsigned short literalCount = readWord((*prg)->program, pc); printf("\n"); - SPC(spaces); - printf("| ( Reading %d literals )\n", literalCount); + if (!alt_fmt) { + SPC(spaces); + printf("| "); + printf(" "); + printf("--- ( Reading %d literals from cache ) ---\n", literalCount); + } for (int i = 0; i < literalCount; i++) { const unsigned char literalType = readByte((*prg)->program, pc); @@ -356,58 +459,103 @@ static void dis_read_interpreter_sections(dis_program_t **prg, uint32_t *pc, uin switch (literalType) { case DIS_LITERAL_NULL: LIT_ADD(DIS_LITERAL_NULL, literal_type, literal_count); - SPC(spaces); - printf("| | [%05d] ( null )\n", i); + if (!alt_fmt) { + SPC(spaces); + printf("| | "); + printf("[%05d] ( null )\n", i); + } else { + printf(" "); + printf(".lit NULL\n"); + } + break; case DIS_LITERAL_BOOLEAN: { const bool b = readByte((*prg)->program, pc); LIT_ADD(DIS_LITERAL_BOOLEAN, literal_type, literal_count); - SPC(spaces); - printf("| | [%05d] ( boolean %s )\n", i, b ? "true" : "false"); + if (!alt_fmt) { + SPC(spaces); + printf("| | "); + printf("[%05d] ( boolean %s )\n", i, b ? "true" : "false"); + } else { + printf(" "); + printf(".lit BOOLEAN %s\n", b ? "true" : "false"); + } } break; case DIS_LITERAL_INTEGER: { const int d = readInt((*prg)->program, pc); LIT_ADD(DIS_LITERAL_INTEGER, literal_type, literal_count); - SPC(spaces); - printf("| | [%05d] ( integer %d )\n", i, d); + if (!alt_fmt) { + SPC(spaces); + printf("| | "); + printf("[%05d] ( integer %d )\n", i, d); + } else { + printf(" "); + printf(".lit INTEGER %d\n", d); + } } break; case DIS_LITERAL_FLOAT: { const float f = readFloat((*prg)->program, pc); LIT_ADD(DIS_LITERAL_FLOAT, literal_type, literal_count); - SPC(spaces); - printf("| | [%05d] ( float %f )\n", i, f); + if (!alt_fmt) { + SPC(spaces); + printf("| | "); + printf("[%05d] ( float %f )\n", i, f); + } else { + printf(" "); + printf(".lit FLOAT %f\n", f); + } } break; case DIS_LITERAL_STRING: { const char *s = readString((*prg)->program, pc); LIT_ADD(DIS_LITERAL_STRING, literal_type, literal_count); - SPC(spaces); - printf("| | [%05d] ( string \"%s\" )\n", i, s); + if (!alt_fmt) { + SPC(spaces); + printf("| | "); + printf("[%05d] ( string \"%s\" )\n", i, s); + } else { + printf(" "); + printf(".lit STRING \"%s\"\n", s); + } } break; case DIS_LITERAL_ARRAY_INTERMEDIATE: case DIS_LITERAL_ARRAY: { unsigned short length = readWord((*prg)->program, pc); - SPC(spaces); - printf("| | [%05d] ( array ", i); + if (!alt_fmt) { + SPC(spaces); + printf("| | "); + printf("[%05d] ( array ", i); + } else { + printf(" "); + printf(".lit ARRAY "); + } + for (int i = 0; i < length; i++) { int index = readWord((*prg)->program, pc); printf("%d ", index); LIT_ADD(DIS_LITERAL_NULL, literal_type, literal_count); if (!(i % 15) && i != 0) { - printf("\n"); - SPC(spaces); - printf("| | "); - } + printf("\\\n"); + if (!alt_fmt) { + SPC(spaces); + printf("| | "); + } else + printf(" "); + printf(" "); + } } - printf(")\n"); + if (!alt_fmt) + printf(")"); + printf("\n"); + LIT_ADD(DIS_LITERAL_ARRAY, literal_type, literal_count); } break; @@ -415,19 +563,36 @@ static void dis_read_interpreter_sections(dis_program_t **prg, uint32_t *pc, uin case DIS_LITERAL_DICTIONARY_INTERMEDIATE: case DIS_LITERAL_DICTIONARY: { unsigned short length = readWord((*prg)->program, pc); - SPC(spaces); - printf("| | [%05d] ( dictionary ", i); + if (!alt_fmt) { + SPC(spaces); + printf("| | "); + printf("[%05d] ( dictionary ", i); + } else { + printf(" "); + printf(".lit DICTIONARY "); + } for (int i = 0; i < length / 2; i++) { int key = readWord((*prg)->program, pc); int val = readWord((*prg)->program, pc); - printf("(key: %d, val:%d) ", key, val); - if(!(i % 5) && i != 0){ - printf("\n"); - SPC(spaces); - printf("| | "); + + if (!alt_fmt) + printf("(key: %d, val:%d) ", key, val); + else + printf("%d,%d ", key, val); + + if (!(i % 5) && i != 0) { + printf("\\\n"); + if (!alt_fmt) { + SPC(spaces); + printf("| | "); + } else + printf(" "); + printf(" "); } } - printf(")\n"); + if (!alt_fmt) + printf(")"); + printf("\n"); LIT_ADD(DIS_LITERAL_DICTIONARY, literal_type, literal_count); } break; @@ -435,16 +600,28 @@ static void dis_read_interpreter_sections(dis_program_t **prg, uint32_t *pc, uin case DIS_LITERAL_FUNCTION: { unsigned short index = readWord((*prg)->program, pc); LIT_ADD(DIS_LITERAL_FUNCTION_INTERMEDIATE, literal_type, literal_count); - SPC(spaces); - printf("| | [%05d] ( function index: %d )\n", i, index); + if (!alt_fmt) { + SPC(spaces); + printf("| | "); + printf("[%05d] ( function index: %d )\n", i, index); + } else { + printf(" "); + printf(".lit FUNCTION %d\n", index); + } } break; case DIS_LITERAL_IDENTIFIER: { const char *str = readString((*prg)->program, pc); LIT_ADD(DIS_LITERAL_IDENTIFIER, literal_type, literal_count); - SPC(spaces); - printf("| | [%05d] ( identifier %s )\n", i, str); + if (!alt_fmt) { + SPC(spaces); + printf("| | "); + printf("[%05d] ( identifier %s )\n", i, str); + } else { + printf(" "); + printf(".lit IDENTIFIER %s\n", str); + } } break; @@ -452,84 +629,146 @@ static void dis_read_interpreter_sections(dis_program_t **prg, uint32_t *pc, uin case DIS_LITERAL_TYPE_INTERMEDIATE: { uint8_t literalType = readByte((*prg)->program, pc); uint8_t constant = readByte((*prg)->program, pc); - SPC(spaces); - printf("| | [%05d] ( type %s: %d)\n", i, (LIT_STR[literalType] + 12), constant); - if (literalType == DIS_LITERAL_ARRAY) { - uint16_t vt = readWord((*prg)->program, pc); + if (!alt_fmt) { SPC(spaces); - printf("| | ( subtype: %d)\n", vt); + printf("| | "); + printf("[%05d] ( type %s: %d)\n", i, (LIT_STR[literalType] + 12), constant); + } else { + printf(" "); + printf(".lit TYPE %s %d", (LIT_STR[literalType] + 12), constant); } - if (literalType == DIS_LITERAL_DICTIONARY) { + if (literalType == DIS_LITERAL_ARRAY) { + uint16_t vt = readWord((*prg)->program, pc); + if (!alt_fmt) { + SPC(spaces); + printf("| | "); + printf("\n ( subtype: %d)", vt); + } else + printf(" SUBTYPE %d", vt); + + printf("\n"); + } else if (literalType == DIS_LITERAL_DICTIONARY) { uint8_t kt = readWord((*prg)->program, pc); uint8_t vt = readWord((*prg)->program, pc); - SPC(spaces); - printf("| | ( subtype: [%d, %d] )\n", kt, vt); - } + if (!alt_fmt) { + SPC(spaces); + printf("| | "); + printf("\n ( subtype: [%d, %d] )", kt, vt); + } else + printf(" SUBTYPE %d,%d", kt, vt); + + printf("\n"); + } else + printf("\n"); + LIT_ADD(literalType, literal_type, literal_count); } break; case DIS_LITERAL_INDEX_BLANK: LIT_ADD(DIS_LITERAL_INDEX_BLANK, literal_type, literal_count); - SPC(spaces); - printf("| | [%05d] ( blank )\n", i); + if (!alt_fmt) { + SPC(spaces); + printf("| | "); + printf("[%05d] ( blank )\n", i); + } else { + printf(" "); + printf(".lit BLANK\n"); + } break; } } consumeByte(DIS_OP_SECTION_END, (*prg)->program, pc); - SPC(spaces); - printf("| ( end literals )\n"); + if (!alt_fmt) { + SPC(spaces); + printf("| "); + printf("--- ( end literal section ) ---\n"); + } int functionCount = readWord((*prg)->program, pc); int functionSize = readWord((*prg)->program, pc); if (functionCount) { - SPC(spaces); - printf("| | \n"); - SPC(spaces); - printf("| | ( fun count: %d, total size: %d )\n", functionCount, functionSize); + if (!alt_fmt) { + SPC(spaces); + printf("|\n"); + SPC(spaces); + printf("| "); + printf("--- ( fn count: %d, total size: %d ) ---\n", functionCount, functionSize); + } - uint32_t fcnt = 0; - char tree_local[2048]; + uint32_t fcnt = 0; + char tree_local[2048]; - for (uint32_t i = 0; i < literal_count; i++) { + for (uint32_t i = 0; i < literal_count; i++) { if (literal_type[i] == DIS_LITERAL_FUNCTION_INTERMEDIATE) { size_t size = (size_t) readWord((*prg)->program, pc); uint32_t fpc_start = *pc; uint32_t fpc_end = *pc + size - 1; - tree_local[0] = '\0'; - sprintf(tree_local, "%s.%d",tree, fcnt); - if (tree_local[0] == '.') - memcpy(tree_local, tree_local + 1, strlen(tree_local)); - SPC(spaces); - printf("| | |\n"); - SPC(spaces); - printf("| | | ( fun %s [ start: %d, end: %d ] )", tree_local, fpc_start, fpc_end); + tree_local[0] = '\0'; + if (!alt_fmt) { + sprintf(tree_local, "%s.%d", tree, fcnt); + if (tree_local[0] == '_') + memcpy(tree_local, tree_local + 1, strlen(tree_local)); + } else { + sprintf(tree_local, "%s_%d", tree, fcnt); + if (tree_local[0] == '_') + memcpy(tree_local, tree_local + 1, strlen(tree_local)); + } + + if (!alt_fmt) { + SPC(spaces); + printf("| |\n"); + SPC(spaces); + printf("| | "); + printf("( fun %s [ start: %d, end: %d ] )", tree_local, fpc_start, fpc_end); + } else + printf("\nLIT_FUN_%s:", tree_local); + if ((*prg)->program[*pc + size - 1] != DIS_OP_FN_END) { printf("\nERROR: Failed to find function end\n"); exit(1); } - dis_read_interpreter_sections(prg, &fpc_start, spaces + 4, tree_local); - SPC(spaces); - printf("| | |\n"); + dis_read_interpreter_sections(prg, &fpc_start, spaces + 4, tree_local, alt_fmt); - SPC(spaces + 4); - printf("| ------ ( code ) ------"); - dis_disassemble_section(prg, fpc_start, fpc_end, spaces + 4, true); - printf("\n"); - SPC(spaces + 4); - printf("| ---- ( end code ) ----\n"); + if (!alt_fmt) { + SPC(spaces); + printf("| | |\n"); + SPC(spaces + 4); + printf("| "); + printf("--- ( reading code for %s ) ---", tree_local); + dis_disassemble_section(prg, fpc_start, fpc_end, spaces + 4, true, alt_fmt); + printf("\n"); + SPC(spaces + 4); + printf("| "); + printf("--- ( end code section ) ---\n"); + } else { + fun_code_t *fun = malloc(sizeof(struct fun_code_s)); + fun->fun = malloc(strlen(tree_local) + 1); + strcpy(fun->fun, tree_local); + fun->start = fpc_start; + fun->len = fpc_end; + disassembler_enqueue((void*) fun); + } fcnt++; *pc += size; } } + + if (!alt_fmt) { + SPC(spaces); + printf("|\n"); + SPC(spaces); + printf("| "); + printf("--- ( end fn section ) ---\n"); + } } consumeByte(DIS_OP_SECTION_END, (*prg)->program, pc); @@ -537,25 +776,53 @@ static void dis_read_interpreter_sections(dis_program_t **prg, uint32_t *pc, uin /////////////////////////////////////////////////////////////////////////////// -void disassemble(const char *filename) { +void disassemble(const char *filename, bool alt_fmt) { dis_program_t *prg; + queue_front = NULL; + queue_rear = NULL; + jump_label = 0; dis_disassembler_init(&prg); - if (dis_load_file(filename, &prg)) + if (dis_load_file(filename, &prg, alt_fmt)) { + dis_disassembler_deinit(&prg); exit(1); + } - dis_read_header(&prg); + dis_read_header(&prg, alt_fmt); + + printf("\n.start MAIN\n"); consumeByte(DIS_OP_SECTION_END, prg->program, &(prg->pc)); - printf("\n| ---- ( literals ) ----"); - dis_read_interpreter_sections(&prg, &(prg->pc), 0, ""); - printf("| -- ( end literals) --\n|"); + if (alt_fmt) + printf("\nLIT_MAIN:"); + dis_read_interpreter_sections(&prg, &(prg->pc), 0, "", alt_fmt); + if (!alt_fmt) { + printf("|\n| "); + printf("--- ( reading main code ) ---"); + } else + printf("\nMAIN:"); + dis_disassemble_section(&prg, prg->pc, prg->len, 0, false, alt_fmt); + if (!alt_fmt) { + printf("\n| "); + printf("--- ( end main code section ) ---"); + } else + printf("\n"); - printf("\n| ---- ( main code ) ----"); - dis_disassemble_section(&prg, prg->pc, prg->len, 0, false); - printf("\n| -- ( end main code ) --"); + if (alt_fmt) { + while (queue_front != NULL) { + fun_code_t *fun = (fun_code_t*) disassembler_front(); + printf("\nFUN_%s:", fun->fun); + free(fun->fun); - printf("\n\n"); + dis_disassemble_section(&prg, fun->start, fun->len, 0, true, alt_fmt); + + disassembler_dequeue(); + printf("\n"); + } + + } + + printf("\n"); dis_disassembler_deinit(&prg); } diff --git a/tools/disassembler/disassembler.h b/tools/disassembler/disassembler.h index 7a34f0b..f30a6ea 100644 --- a/tools/disassembler/disassembler.h +++ b/tools/disassembler/disassembler.h @@ -22,8 +22,8 @@ typedef enum DIS_OPCODES { // data DIS_OP_LITERAL, // - DIS_OP_LITERAL_LONG, // for more than 256 literals in a chunk - DIS_OP_LITERAL_RAW, // forcibly get the raw value of the literal + DIS_OP_LITERAL_LONG, // + DIS_OP_LITERAL_RAW, // // arithmetic operators DIS_OP_NEGATE, // @@ -42,21 +42,21 @@ typedef enum DIS_OPCODES { DIS_OP_TYPE_DECL_removed, // deprecated DIS_OP_TYPE_DECL_LONG_removed, // deprecated - DIS_OP_VAR_DECL, // declare a variable to be used (as a literal) - DIS_OP_VAR_DECL_LONG, // declare a variable to be used (as a long literal) + DIS_OP_VAR_DECL, // + DIS_OP_VAR_DECL_LONG, // - DIS_OP_FN_DECL, // declare a function to be used (as a literal) - DIS_OP_FN_DECL_LONG, // declare a function to be used (as a long literal) + DIS_OP_FN_DECL, // + DIS_OP_FN_DECL_LONG, // - DIS_OP_VAR_ASSIGN, // assign to a literal + DIS_OP_VAR_ASSIGN, // DIS_OP_VAR_ADDITION_ASSIGN, // DIS_OP_VAR_SUBTRACTION_ASSIGN, // DIS_OP_VAR_MULTIPLICATION_ASSIGN, // DIS_OP_VAR_DIVISION_ASSIGN, // DIS_OP_VAR_MODULO_ASSIGN, // - DIS_OP_TYPE_CAST, // temporarily change a type of an atomic value - DIS_OP_TYPE_OF, // get the type of a variable + DIS_OP_TYPE_CAST, // + DIS_OP_TYPE_OF, // DIS_OP_IMPORT, // DIS_OP_EXPORT_removed, // deprecated @@ -74,7 +74,7 @@ typedef enum DIS_OPCODES { DIS_OP_COMPARE_LESS_EQUAL, // DIS_OP_COMPARE_GREATER, // DIS_OP_COMPARE_GREATER_EQUAL, // - DIS_OP_INVERT, // for booleans + DIS_OP_INVERT, // // logical operators DIS_OP_AND, // @@ -123,6 +123,6 @@ typedef enum DIS_LITERAL_TYPE { DIS_LITERAL_INDEX_BLANK, // for blank indexing i.e. arr[:] } dis_literal_type_t; -extern void disassemble(const char *filename); +extern void disassemble(const char *filename, bool alt_fmt); #endif /* DISASSEMBLER_H_ */ diff --git a/tools/disassembler/disassembler_utils.c b/tools/disassembler/disassembler_utils.c new file mode 100644 index 0000000..89bf3b5 --- /dev/null +++ b/tools/disassembler/disassembler_utils.c @@ -0,0 +1,52 @@ +/* + * utils.c + * + * Created on: 10 ago. 2023 + * Original Author: Emiliano Augusto Gonzalez (egonzalez . hiperion @ gmail . com) + * + * Further modified by Kayne Ruse, and added to the Toy Programming Language tool repository. + */ + +#include "stdio.h" +#include "stdlib.h" + +#include "disassembler_utils.h" + +struct disassembler_node_s *queue_front, *queue_rear; + +void disassembler_enqueue(void *x) { + struct disassembler_node_s *temp; + + temp = (struct disassembler_node_s*) malloc(sizeof(struct disassembler_node_s)); + temp->data = x; + temp->next = NULL; + + if (queue_front == NULL && queue_rear == NULL) { + queue_front = queue_rear = temp; + return; + } + queue_rear->next = temp; + queue_rear = temp; + +} + +void disassembler_dequeue(void) { + struct disassembler_node_s *temp = queue_front; + + if (queue_front == NULL) { + printf("Error : QUEUE is empty!!"); + return; + } + if (queue_front == queue_rear) + queue_front = queue_rear = NULL; + + else + queue_front = queue_front->next; + + free(temp->data); + free(temp); +} + +void* disassembler_front(void) { + return queue_front->data; +} diff --git a/tools/disassembler/disassembler_utils.h b/tools/disassembler/disassembler_utils.h new file mode 100644 index 0000000..6688f25 --- /dev/null +++ b/tools/disassembler/disassembler_utils.h @@ -0,0 +1,24 @@ +/* + * utils.h + * + * Created on: 10 ago. 2023 + * Original Author: Emiliano Augusto Gonzalez (egonzalez . hiperion @ gmail . com) + * + * Further modified by Kayne Ruse, and added to the Toy Programming Language tool repository. + */ + +#ifndef UTILS_H_ +#define UTILS_H_ + +struct disassembler_node_s { + void *data; + struct disassembler_node_s *next; +}; + +extern struct disassembler_node_s *queue_front, *queue_rear; + +void disassembler_enqueue(void *x); +void disassembler_dequeue(void); +void* disassembler_front(void); + +#endif /* UTILS_H_ */ diff --git a/tools/disassembler/main.c b/tools/disassembler/main.c index 4028039..406412e 100644 --- a/tools/disassembler/main.c +++ b/tools/disassembler/main.c @@ -1,8 +1,46 @@ #include +#include "cargs.h" #include "disassembler.h" -int main(int argc, const char* argv[]) { - disassemble(argv[1]); +static struct cag_option options[] = { + { + .identifier = 'a', + .access_letters = "a", + .access_name = NULL, + .value_name = NULL, + .description = "Alternate format" + }, { + .identifier = 'h', + .access_letters = "h", + .access_name = "help", + .description = "Shows the command help" + } +}; + +struct options { + bool alternate_flag; +}; + +int main(int argc, char *argv[]) { + char identifier; + cag_option_context context; + struct options config = { false }; + + cag_option_prepare(&context, options, CAG_ARRAY_SIZE(options), argc, argv); + while (cag_option_fetch(&context)) { + identifier = cag_option_get(&context); + switch (identifier) { + case 'a': + config.alternate_flag = true; + break; + case 'h': + printf("Usage: disassembler [OPTION] file\n"); + cag_option_print(options, CAG_ARRAY_SIZE(options), stdout); + return EXIT_SUCCESS; + } + } + + disassemble(argv[context.index], config.alternate_flag); return EXIT_SUCCESS; } diff --git a/tools/disassembler/makefile b/tools/disassembler/makefile index 06e6b95..bc68d7a 100644 --- a/tools/disassembler/makefile +++ b/tools/disassembler/makefile @@ -7,8 +7,8 @@ LIBS+= ODIR = obj SRC = $(wildcard *.c) OBJ = $(addprefix $(ODIR)/,$(SRC:.c=.o)) -OUTNAME= -OUT=disassembler +OUTDIR=../../out +OUT=$(OUTDIR)/disassembler all: $(OBJ) $(CC) $(CFLAGS) -o $(OUT) $(OBJ) $(LIBS)