diff options
Diffstat (limited to 'src/parser')
| -rw-r--r-- | src/parser/parser.h | 29 | ||||
| -rw-r--r-- | src/parser/parser_core.c | 32 | ||||
| -rw-r--r-- | src/parser/parser_decl.c | 70 | ||||
| -rw-r--r-- | src/parser/parser_expr.c | 200 | ||||
| -rw-r--r-- | src/parser/parser_stmt.c | 282 | ||||
| -rw-r--r-- | src/parser/parser_struct.c | 129 | ||||
| -rw-r--r-- | src/parser/parser_type.c | 103 | ||||
| -rw-r--r-- | src/parser/parser_utils.c | 67 |
8 files changed, 846 insertions, 66 deletions
diff --git a/src/parser/parser.h b/src/parser/parser.h index cf57971..23c2920 100644 --- a/src/parser/parser.h +++ b/src/parser/parser.h @@ -261,6 +261,8 @@ typedef struct TypeAlias char *alias; ///< New type name. char *original_type; ///< Original type. struct TypeAlias *next; + int is_opaque; + char *defined_in_file; } TypeAlias; /** @@ -514,12 +516,9 @@ char *sanitize_mangled_name(const char *name); /** * @brief Registers a type alias. */ -void register_type_alias(ParserContext *ctx, const char *alias, const char *original); - -/** - * @brief Finds a type alias. - */ -const char *find_type_alias(ParserContext *ctx, const char *alias); +TypeAlias *find_type_alias_node(ParserContext *ctx, const char *name); +void register_type_alias(ParserContext *ctx, const char *alias, const char *original, int is_opaque, + const char *defined_in_file); /** * @brief Registers an implementation. @@ -562,7 +561,8 @@ ASTNode *parse_arrow_lambda_multi(ParserContext *ctx, Lexer *l, char **param_nam * @brief Parses and converts arguments. */ char *parse_and_convert_args(ParserContext *ctx, Lexer *l, char ***defaults_out, int *count_out, - Type ***types_out, char ***names_out, int *is_varargs_out); + Type ***types_out, char ***names_out, int *is_varargs_out, + char ***ctype_overrides_out); /** * @brief Checks if a file has been imported. @@ -681,10 +681,6 @@ void register_selective_import(ParserContext *ctx, const char *symbol, const cha SelectiveImport *find_selective_import(ParserContext *ctx, const char *name); // Type Aliases -/** - * @brief Registers a type alias. - */ -void register_type_alias(ParserContext *ctx, const char *alias, const char *original); /** * @brief Finds a type alias. @@ -741,6 +737,11 @@ FuncSig *find_func(ParserContext *ctx, const char *name); Type *parse_type_formal(ParserContext *ctx, Lexer *l); /** + * @brief Checks compatibility of opaque aliases (allows access within defining file). + */ +int check_opaque_alias_compat(ParserContext *ctx, Type *a, Type *b); + +/** * @brief Parses a type. */ char *parse_type(ParserContext *ctx, Lexer *l); @@ -889,7 +890,7 @@ ASTNode *parse_def(ParserContext *ctx, Lexer *l); /** * @brief Parses a type alias. */ -ASTNode *parse_type_alias(ParserContext *ctx, Lexer *l); +ASTNode *parse_type_alias(ParserContext *ctx, Lexer *l, int is_opaque); /** * @brief Parses a function definition. @@ -899,7 +900,7 @@ ASTNode *parse_function(ParserContext *ctx, Lexer *l, int is_async); /** * @brief Parses a struct definition. */ -ASTNode *parse_struct(ParserContext *ctx, Lexer *l, int is_union); +ASTNode *parse_struct(ParserContext *ctx, Lexer *l, int is_union, int is_opaque); /** * @brief Parses an enum definition. @@ -963,4 +964,4 @@ char *patch_self_args(const char *args, const char *struct_name); */ ASTNode *parse_program_nodes(ParserContext *ctx, Lexer *l); -#endif // PARSER_H +#endif // PARSER_H
\ No newline at end of file diff --git a/src/parser/parser_core.c b/src/parser/parser_core.c index e9a418e..43137b1 100644 --- a/src/parser/parser_core.c +++ b/src/parser/parser_core.c @@ -338,7 +338,7 @@ ASTNode *parse_program_nodes(ParserContext *ctx, Lexer *l) } else if (0 == strncmp(t.start, "struct", 6) && 6 == t.len) { - s = parse_struct(ctx, l, 0); + s = parse_struct(ctx, l, 0, 0); if (s && s->type == NODE_STRUCT) { s->strct.is_packed = attr_packed; @@ -436,7 +436,7 @@ ASTNode *parse_program_nodes(ParserContext *ctx, Lexer *l) } else if (0 == strncmp(t.start, "type", 4) && 4 == t.len) { - s = parse_type_alias(ctx, l); + s = parse_type_alias(ctx, l, 0); } else if (0 == strncmp(t.start, "raw", 3) && 3 == t.len) { @@ -482,9 +482,31 @@ ASTNode *parse_program_nodes(ParserContext *ctx, Lexer *l) lexer_next(l); } } + else if (t.type == TOK_OPAQUE) + { + lexer_next(l); // eat opaque + Token next = lexer_peek(l); + if (0 == strncmp(next.start, "struct", 6) && 6 == next.len) + { + s = parse_struct(ctx, l, 0, 1); + if (s && s->type == NODE_STRUCT) + { + s->strct.is_packed = attr_packed; + s->strct.align = attr_align; + } + } + else if (next.type == TOK_ALIAS) + { + s = parse_type_alias(ctx, l, 1); + } + else + { + zpanic_at(next, "Expected 'struct' or 'alias' after 'opaque'"); + } + } else if (t.type == TOK_ALIAS) { - s = parse_type_alias(ctx, l); + s = parse_type_alias(ctx, l, 0); } else if (t.type == TOK_ASYNC) { @@ -506,7 +528,7 @@ ASTNode *parse_program_nodes(ParserContext *ctx, Lexer *l) else if (t.type == TOK_UNION) { - s = parse_struct(ctx, l, 1); + s = parse_struct(ctx, l, 1, 0); } else if (t.type == TOK_TRAIT) { @@ -700,7 +722,7 @@ static ASTNode *generate_derive_impls(ParserContext *ctx, ASTNode *strct, char * { // Simplistic Debug for now, I know. code = xmalloc(1024); - sprintf(code, "impl %s { fn to_string(self) -> char* { return \"%s { ... }\"; } }", + sprintf(code, "impl %s { fn to_string(self) -> char* { return \"%s {{ ... }}\"; } }", name, name); } else if (0 == strcmp(trait, "Copy")) diff --git a/src/parser/parser_decl.c b/src/parser/parser_decl.c index 98f46e1..93a124d 100644 --- a/src/parser/parser_decl.c +++ b/src/parser/parser_decl.c @@ -99,10 +99,11 @@ ASTNode *parse_function(ParserContext *ctx, Lexer *l, int is_async) int count; Type **arg_types; char **param_names; + char **ctype_overrides; int is_varargs = 0; - char *args = - parse_and_convert_args(ctx, l, &defaults, &count, &arg_types, ¶m_names, &is_varargs); + char *args = parse_and_convert_args(ctx, l, &defaults, &count, &arg_types, ¶m_names, + &is_varargs, &ctype_overrides); char *ret = "void"; Type *ret_type_obj = type_new(TYPE_VOID); @@ -191,6 +192,7 @@ ASTNode *parse_function(ParserContext *ctx, Lexer *l, int is_async) node->func.defaults = defaults; node->func.ret_type_info = ret_type_obj; node->func.is_varargs = is_varargs; + node->func.c_type_overrides = ctype_overrides; if (gen_param) { @@ -579,6 +581,10 @@ ASTNode *parse_var_decl(ParserContext *ctx, Lexer *l) { type_obj->inner = init->type_info->inner; // Shallow copy for inner } + if (init->type_info->kind == TYPE_ALIAS) + { + type_obj->alias = init->type_info->alias; + } // Copy function type args for lambda/closure support if (init->type_info->args && init->type_info->arg_count > 0) { @@ -631,6 +637,59 @@ ASTNode *parse_var_decl(ParserContext *ctx, Lexer *l) // Register in symbol table with actual token add_symbol_with_token(ctx, name, type, type_obj, name_tok); + if (init && type_obj) + { + Type *t = init->type_info; + if (!t && init->type == NODE_EXPR_VAR) + { + t = find_symbol_type_info(ctx, init->var_ref.name); + } + + // Literal type construction for validation + Type *temp_literal_type = NULL; + if (!t && init->type == NODE_EXPR_LITERAL) + { + if (init->literal.type_kind == LITERAL_INT) + { + temp_literal_type = type_new(TYPE_INT); + } + else if (init->literal.type_kind == LITERAL_FLOAT) + { + temp_literal_type = type_new(TYPE_FLOAT); + } + else if (init->literal.type_kind == LITERAL_STRING) + { + temp_literal_type = type_new(TYPE_STRING); + } + else if (init->literal.type_kind == LITERAL_CHAR) + { + temp_literal_type = type_new(TYPE_CHAR); + } + t = temp_literal_type; + } + + // Special case for literals: if implicit conversion works + if (t && !type_eq(type_obj, t)) + { + // Allow integer compatibility if types are roughly ints (lax check in type_eq handles + // most, but let's be safe) + if (!check_opaque_alias_compat(ctx, type_obj, t)) + { + char *expected = type_to_string(type_obj); + char *got = type_to_string(t); + zpanic_at(init->token, "Type validation failed. Expected '%s', but got '%s'", + expected, got); + free(expected); + free(got); + } + } + + if (temp_literal_type) + { + free(temp_literal_type); // Simple free, shallow + } + } + // NEW: Capture Const Integer Values if (init && init->type == NODE_EXPR_LITERAL && init->literal.type_kind == LITERAL_INT) { @@ -839,7 +898,7 @@ ASTNode *parse_def(ParserContext *ctx, Lexer *l) return o; } -ASTNode *parse_type_alias(ParserContext *ctx, Lexer *l) +ASTNode *parse_type_alias(ParserContext *ctx, Lexer *l, int is_opaque) { lexer_next(l); // consume 'type' or 'alias' Token n = lexer_next(l); @@ -859,8 +918,11 @@ ASTNode *parse_type_alias(ParserContext *ctx, Lexer *l) strncpy(node->type_alias.alias, n.start, n.len); node->type_alias.alias[n.len] = 0; node->type_alias.original_type = o; + node->type_alias.is_opaque = is_opaque; + node->type_alias.defined_in_file = g_current_filename ? xstrdup(g_current_filename) : NULL; - register_type_alias(ctx, node->type_alias.alias, o); + register_type_alias(ctx, node->type_alias.alias, o, is_opaque, + node->type_alias.defined_in_file); return node; } diff --git a/src/parser/parser_expr.c b/src/parser/parser_expr.c index df2dcf6..7c53d96 100644 --- a/src/parser/parser_expr.c +++ b/src/parser/parser_expr.c @@ -1,3 +1,43 @@ +#include "../codegen/codegen.h" + +int check_opaque_alias_compat(ParserContext *ctx, Type *a, Type *b) +{ + if (!a || !b) + { + return 0; + } + + int a_is_opaque = (a->kind == TYPE_ALIAS && a->alias.is_opaque_alias); + int b_is_opaque = (b->kind == TYPE_ALIAS && b->alias.is_opaque_alias); + + if (!a_is_opaque && !b_is_opaque) + { + return 1; + } + + if (a_is_opaque) + { + if (a->alias.alias_defined_in_file && g_current_filename && + strcmp(a->alias.alias_defined_in_file, g_current_filename) == 0) + { + return check_opaque_alias_compat(ctx, a->inner, b); + } + return 0; + } + + if (b_is_opaque) + { + if (b->alias.alias_defined_in_file && g_current_filename && + strcmp(b->alias.alias_defined_in_file, g_current_filename) == 0) + { + return check_opaque_alias_compat(ctx, a, b->inner); + } + return 0; + } + + return 0; +} + #include "../zen/zen_facts.h" #include "parser.h" #include <ctype.h> @@ -108,6 +148,8 @@ int is_type_copy(ParserContext *ctx, Type *t) case TYPE_POINTER: // Pointers are Copy case TYPE_FUNCTION: case TYPE_ENUM: // Enums are integers + case TYPE_BITINT: + case TYPE_UBITINT: return 1; case TYPE_STRUCT: @@ -116,6 +158,14 @@ int is_type_copy(ParserContext *ctx, Type *t) { return 1; } + + // If the struct is NOT defined (opaque/C type) and does NOT implement Drop, + // treat it as Copy (C behavior). + if (!find_struct_def(ctx, t->name) && !check_impl(ctx, "Drop", t->name)) + { + return 1; + } + return 0; case TYPE_ARRAY: @@ -124,6 +174,13 @@ int is_type_copy(ParserContext *ctx, Type *t) // but if it's a value assignment, C doesn't support it anyway unless wrapped in struct. return 0; + case TYPE_ALIAS: + if (t->alias.is_opaque_alias) + { + return 1; + } + return is_type_copy(ctx, t->inner); + default: return 1; } @@ -935,6 +992,17 @@ static ASTNode *create_fstring_block(ParserContext *ctx, const char *content) free(txt); } + // Handle escape {{ + if (brace[1] == '{') + { + ASTNode *cat = ast_create(NODE_RAW_STMT); + cat->raw_stmt.content = xstrdup("strcat(_b, \"{\");"); + tail->next = cat; + tail = cat; + cur = brace + 2; + continue; + } + char *end_brace = strchr(brace, '}'); if (!end_brace) { @@ -1072,6 +1140,7 @@ static ASTNode *create_fstring_block(ParserContext *ctx, const char *content) static ASTNode *parse_int_literal(Token t) { ASTNode *node = ast_create(NODE_EXPR_LITERAL); + node->token = t; node->literal.type_kind = LITERAL_INT; node->type_info = type_new(TYPE_INT); char *s = token_strdup(t); @@ -1093,6 +1162,7 @@ static ASTNode *parse_int_literal(Token t) static ASTNode *parse_float_literal(Token t) { ASTNode *node = ast_create(NODE_EXPR_LITERAL); + node->token = t; node->literal.type_kind = LITERAL_FLOAT; node->literal.float_val = atof(t.start); node->type_info = type_new(TYPE_F64); @@ -1100,9 +1170,32 @@ static ASTNode *parse_float_literal(Token t) } // Parse string literal -static ASTNode *parse_string_literal(Token t) +static ASTNode *parse_string_literal(ParserContext *ctx, Token t) { + // Check for implicit interpolation + int has_interpolation = 0; + for (int i = 1; i < t.len - 1; i++) + { + if (t.start[i] == '{') + { + has_interpolation = 1; + break; + } + } + + if (has_interpolation) + { + + char *inner = xmalloc(t.len); + strncpy(inner, t.start + 1, t.len - 2); + inner[t.len - 2] = 0; + ASTNode *node = create_fstring_block(ctx, inner); + free(inner); + return node; + } + ASTNode *node = ast_create(NODE_EXPR_LITERAL); + node->token = t; node->literal.type_kind = LITERAL_STRING; node->literal.string_val = xmalloc(t.len); strncpy(node->literal.string_val, t.start + 1, t.len - 2); @@ -1126,6 +1219,7 @@ static ASTNode *parse_fstring_literal(ParserContext *ctx, Token t) static ASTNode *parse_char_literal(Token t) { ASTNode *node = ast_create(NODE_EXPR_LITERAL); + node->token = t; node->literal.type_kind = LITERAL_CHAR; node->literal.string_val = token_strdup(t); node->type_info = type_new(TYPE_I8); @@ -1276,7 +1370,7 @@ ASTNode *parse_primary(ParserContext *ctx, Lexer *l) } else if (t.type == TOK_STRING) { - node = parse_string_literal(t); + node = parse_string_literal(ctx, t); } else if (t.type == TOK_FSTRING) { @@ -2018,6 +2112,20 @@ ASTNode *parse_primary(ParserContext *ctx, Lexer *l) sprintf(prefixed, "%s_%s", ctx->current_module_prefix, acc); struct_name = prefixed; } + + // Opaque Struct Check + ASTNode *def = find_struct_def(ctx, struct_name); + if (def && def->type == NODE_STRUCT && def->strct.is_opaque) + { + if (!def->strct.defined_in_file || + (g_current_filename && + strcmp(def->strct.defined_in_file, g_current_filename) != 0)) + { + zpanic_at(lexer_peek(l), + "Cannot initialize opaque struct '%s' outside its module", + struct_name); + } + } lexer_next(l); node = ast_create(NODE_EXPR_STRUCT_INIT); node->struct_init.struct_name = struct_name; @@ -3592,7 +3700,7 @@ ASTNode *parse_expr_prec(ParserContext *ctx, Lexer *l, Precedence min_prec) } else if (t->kind == TYPE_STRING) { - strcat(fmt, "%s"); + strcat(fmt, "%ms"); } else if (t->kind == TYPE_CHAR || t->kind == TYPE_I8 || t->kind == TYPE_U8 || t->kind == TYPE_BYTE) @@ -4012,6 +4120,30 @@ ASTNode *parse_expr_prec(ParserContext *ctx, Lexer *l, Precedence min_prec) node->member.field = token_strdup(field); node->member.is_pointer_access = 1; + // Opaque Check + int is_ptr_dummy = 0; + char *alloc_name = NULL; + char *sname = + resolve_struct_name_from_type(ctx, lhs->type_info, &is_ptr_dummy, &alloc_name); + if (sname) + { + ASTNode *def = find_struct_def(ctx, sname); + if (def && def->type == NODE_STRUCT && def->strct.is_opaque) + { + if (!def->strct.defined_in_file || + (g_current_filename && + strcmp(def->strct.defined_in_file, g_current_filename) != 0)) + { + zpanic_at(field, "Cannot access private field '%s' of opaque struct '%s'", + node->member.field, sname); + } + } + if (alloc_name) + { + free(alloc_name); + } + } + node->type_info = get_field_type(ctx, lhs->type_info, node->member.field); if (node->type_info) { @@ -4041,6 +4173,30 @@ ASTNode *parse_expr_prec(ParserContext *ctx, Lexer *l, Precedence min_prec) node->member.field = token_strdup(field); node->member.is_pointer_access = 2; + // Opaque Check + int is_ptr_dummy = 0; + char *alloc_name = NULL; + char *sname = + resolve_struct_name_from_type(ctx, lhs->type_info, &is_ptr_dummy, &alloc_name); + if (sname) + { + ASTNode *def = find_struct_def(ctx, sname); + if (def && def->type == NODE_STRUCT && def->strct.is_opaque) + { + if (!def->strct.defined_in_file || + (g_current_filename && + strcmp(def->strct.defined_in_file, g_current_filename) != 0)) + { + zpanic_at(field, "Cannot access private field '%s' of opaque struct '%s'", + node->member.field, sname); + } + } + if (alloc_name) + { + free(alloc_name); + } + } + node->type_info = get_field_type(ctx, lhs->type_info, node->member.field); if (node->type_info) { @@ -4620,6 +4776,30 @@ ASTNode *parse_expr_prec(ParserContext *ctx, Lexer *l, Precedence min_prec) node->member.field = token_strdup(field); node->member.is_pointer_access = 0; + // Opaque Check + int is_ptr_dummy = 0; + char *alloc_name = NULL; + char *sname = + resolve_struct_name_from_type(ctx, lhs->type_info, &is_ptr_dummy, &alloc_name); + if (sname) + { + ASTNode *def = find_struct_def(ctx, sname); + if (def && def->type == NODE_STRUCT && def->strct.is_opaque) + { + if (!def->strct.defined_in_file || + (g_current_filename && + strcmp(def->strct.defined_in_file, g_current_filename) != 0)) + { + zpanic_at(field, "Cannot access private field '%s' of opaque struct '%s'", + node->member.field, sname); + } + } + if (alloc_name) + { + free(alloc_name); + } + } + node->member.field = token_strdup(field); node->member.is_pointer_access = 0; @@ -5241,6 +5421,7 @@ ASTNode *parse_expr_prec(ParserContext *ctx, Lexer *l, Precedence min_prec) // This gives a warning as "unused" but it's needed for the rewrite. char *r_name = resolve_struct_name_from_type(ctx, rhs->type_info, &is_rhs_ptr, &r_alloc); + (void)r_name; if (r_alloc) { free(r_alloc); @@ -5463,7 +5644,17 @@ ASTNode *parse_expr_prec(ParserContext *ctx, Lexer *l, Precedence min_prec) char *t1 = type_to_string(lhs->type_info); char *t2 = type_to_string(rhs->type_info); // Skip type check if either operand is void* (escape hatch type) + // or if either operand is a generic type parameter (T, K, V, etc.) int skip_check = (strcmp(t1, "void*") == 0 || strcmp(t2, "void*") == 0); + if (lhs->type_info->kind == TYPE_GENERIC || rhs->type_info->kind == TYPE_GENERIC) + { + skip_check = 1; + } + // Also check if type name is a single uppercase letter (common generic param) + if ((strlen(t1) == 1 && isupper(t1[0])) || (strlen(t2) == 1 && isupper(t2[0]))) + { + skip_check = 1; + } // Allow comparing pointers/strings with integer literal 0 (NULL) if (!skip_check) @@ -5507,7 +5698,8 @@ ASTNode *parse_expr_prec(ParserContext *ctx, Lexer *l, Precedence min_prec) } else { - if (type_eq(lhs->type_info, rhs->type_info)) + if (type_eq(lhs->type_info, rhs->type_info) || + check_opaque_alias_compat(ctx, lhs->type_info, rhs->type_info)) { bin->type_info = lhs->type_info; } diff --git a/src/parser/parser_stmt.c b/src/parser/parser_stmt.c index ab5b89c..0677cf5 100644 --- a/src/parser/parser_stmt.c +++ b/src/parser/parser_stmt.c @@ -14,6 +14,118 @@ char *curr_func_ret = NULL; char *run_comptime_block(ParserContext *ctx, Lexer *l); +extern char *g_current_filename; + +/** + * @brief Auto-imports std/slice.zc if not already imported. + * + * This is called when array iteration is detected in for-in loops, + * to ensure the Slice<T>, SliceIter<T>, and Option<T> templates are available. + */ +static void auto_import_std_slice(ParserContext *ctx) +{ + // Check if already imported via templates + GenericTemplate *t = ctx->templates; + while (t) + { + if (strcmp(t->name, "Slice") == 0) + { + return; // Already have the Slice template + } + t = t->next; + } + + // Try to find and import std/slice.zc + static const char *std_paths[] = {"std/slice.zc", "./std/slice.zc", NULL}; + static const char *system_paths[] = {"/usr/local/share/zenc", "/usr/share/zenc", NULL}; + + char resolved_path[1024]; + int found = 0; + + // First, try relative to current file + if (g_current_filename) + { + char *current_dir = xstrdup(g_current_filename); + char *last_slash = strrchr(current_dir, '/'); + if (last_slash) + { + *last_slash = 0; + snprintf(resolved_path, sizeof(resolved_path), "%s/std/slice.zc", current_dir); + if (access(resolved_path, R_OK) == 0) + { + found = 1; + } + } + free(current_dir); + } + + // Try relative paths + if (!found) + { + for (int i = 0; std_paths[i] && !found; i++) + { + if (access(std_paths[i], R_OK) == 0) + { + strncpy(resolved_path, std_paths[i], sizeof(resolved_path) - 1); + resolved_path[sizeof(resolved_path) - 1] = '\0'; + found = 1; + } + } + } + + // Try system paths + if (!found) + { + for (int i = 0; system_paths[i] && !found; i++) + { + snprintf(resolved_path, sizeof(resolved_path), "%s/std/slice.zc", system_paths[i]); + if (access(resolved_path, R_OK) == 0) + { + found = 1; + } + } + } + + if (!found) + { + return; // Could not find std/slice.zc, instantiate_generic will error + } + + // Canonicalize path + char *real_fn = realpath(resolved_path, NULL); + if (real_fn) + { + strncpy(resolved_path, real_fn, sizeof(resolved_path) - 1); + resolved_path[sizeof(resolved_path) - 1] = '\0'; + free(real_fn); + } + + // Check if already imported + if (is_file_imported(ctx, resolved_path)) + { + return; + } + mark_file_imported(ctx, resolved_path); + + // Load and parse the file + char *src = load_file(resolved_path); + if (!src) + { + return; // Could not load file + } + + Lexer i; + lexer_init(&i, src); + + // Save and restore filename context + char *saved_fn = g_current_filename; + g_current_filename = resolved_path; + + // Parse the slice module contents + parse_program_nodes(ctx, &i); + + g_current_filename = saved_fn; +} static void check_assignment_condition(ASTNode *cond) { @@ -462,13 +574,7 @@ ASTNode *parse_defer(ParserContext *ctx, Lexer *l) } else { - s = ast_create(NODE_RAW_STMT); - char *raw_content = consume_and_rewrite(ctx, l); - // consume_and_rewrite strips the semicolon, so we must add it back for proper C generation - char *safe_content = xmalloc(strlen(raw_content) + 2); - sprintf(safe_content, "%s;", raw_content); - free(raw_content); - s->raw_stmt.content = safe_content; + s = parse_statement(ctx, l); } ctx->in_defer_block = prev_in_defer; @@ -1139,6 +1245,7 @@ ASTNode *parse_for(ParserContext *ctx, Lexer *l) ASTNode *obj_expr = start_expr; char *iter_method = "iterator"; + ASTNode *slice_decl = NULL; // Track if we need to add a slice declaration // Check for reference iteration: for x in &vec if (obj_expr->type == NODE_EXPR_UNARY && obj_expr->unary.op && @@ -1148,6 +1255,80 @@ ASTNode *parse_for(ParserContext *ctx, Lexer *l) iter_method = "iter_ref"; } + // Check for array iteration: wrap with Slice<T>::from_array + if (obj_expr->type_info && obj_expr->type_info->kind == TYPE_ARRAY && + obj_expr->type_info->array_size > 0) + { + // Create a var decl for the slice + slice_decl = ast_create(NODE_VAR_DECL); + slice_decl->var_decl.name = xstrdup("__zc_arr_slice"); + + // Build type string: Slice<elem_type> + char *elem_type_str = type_to_string(obj_expr->type_info->inner); + char slice_type[256]; + sprintf(slice_type, "Slice<%s>", elem_type_str); + slice_decl->var_decl.type_str = xstrdup(slice_type); + + ASTNode *from_array_call = ast_create(NODE_EXPR_CALL); + ASTNode *static_method = ast_create(NODE_EXPR_VAR); + + // The function name for static methods is Type::method format + char func_name[512]; + snprintf(func_name, 511, "%s::from_array", slice_type); + static_method->var_ref.name = xstrdup(func_name); + + from_array_call->call.callee = static_method; + + // Create arguments + ASTNode *arr_addr = ast_create(NODE_EXPR_UNARY); + arr_addr->unary.op = xstrdup("&"); + arr_addr->unary.operand = obj_expr; + + ASTNode *arr_cast = ast_create(NODE_EXPR_CAST); + char cast_type[256]; + sprintf(cast_type, "%s*", elem_type_str); + arr_cast->cast.target_type = xstrdup(cast_type); + arr_cast->cast.expr = arr_addr; + + ASTNode *size_arg = ast_create(NODE_EXPR_LITERAL); + size_arg->literal.type_kind = LITERAL_INT; + size_arg->literal.int_val = obj_expr->type_info->array_size; + char size_buf[32]; + sprintf(size_buf, "%d", obj_expr->type_info->array_size); + size_arg->literal.string_val = xstrdup(size_buf); + + arr_cast->next = size_arg; + from_array_call->call.args = arr_cast; + from_array_call->call.arg_count = 2; + + slice_decl->var_decl.init_expr = from_array_call; + + // Manually trigger generic instantiation for Slice<T> + // This ensures that Slice_int, Slice_float, etc. structures are generated + // First, ensure std/slice.zc is imported (auto-import if needed) + auto_import_std_slice(ctx); + Token dummy_tok = {0}; + instantiate_generic(ctx, "Slice", elem_type_str, elem_type_str, dummy_tok); + + // Instantiate SliceIter and Option too for the loop logic + char iter_type[256]; + sprintf(iter_type, "SliceIter<%s>", elem_type_str); + instantiate_generic(ctx, "SliceIter", elem_type_str, elem_type_str, dummy_tok); + + char option_type[256]; + sprintf(option_type, "Option<%s>", elem_type_str); + instantiate_generic(ctx, "Option", elem_type_str, elem_type_str, dummy_tok); + + // Replace obj_expr with a reference to the slice variable + ASTNode *slice_ref = ast_create(NODE_EXPR_VAR); + slice_ref->var_ref.name = xstrdup("__zc_arr_slice"); + slice_ref->resolved_type = + xstrdup(slice_type); // Explicitly set type for codegen + obj_expr = slice_ref; + + free(elem_type_str); + } + // var __it = obj.iterator(); ASTNode *it_decl = ast_create(NODE_VAR_DECL); it_decl->var_decl.name = xstrdup("__it"); @@ -1188,6 +1369,34 @@ ASTNode *parse_for(ParserContext *ctx, Lexer *l) stmts_tail = node; \ } + char *iter_type_ptr = NULL; + char *option_type_ptr = NULL; + + if (slice_decl) + { + char *slice_t = slice_decl->var_decl.type_str; + char *start = strchr(slice_t, '<'); + if (start) + { + char *end = strrchr(slice_t, '>'); + if (end) + { + int len = end - start - 1; + char *elem = xmalloc(len + 1); + strncpy(elem, start + 1, len); + elem[len] = 0; + + iter_type_ptr = xmalloc(256); + sprintf(iter_type_ptr, "SliceIter<%s>", elem); + + option_type_ptr = xmalloc(256); + sprintf(option_type_ptr, "Option<%s>", elem); + + free(elem); + } + } + } + // var __opt = __it.next(); ASTNode *opt_decl = ast_create(NODE_VAR_DECL); opt_decl->var_decl.name = xstrdup("__opt"); @@ -1198,6 +1407,10 @@ ASTNode *parse_for(ParserContext *ctx, Lexer *l) ASTNode *memb_next = ast_create(NODE_EXPR_MEMBER); ASTNode *it_ref = ast_create(NODE_EXPR_VAR); it_ref->var_ref.name = xstrdup("__it"); + if (iter_type_ptr) + { + it_ref->resolved_type = xstrdup(iter_type_ptr); + } memb_next->member.target = it_ref; memb_next->member.field = xstrdup("next"); call_next->call.callee = memb_next; @@ -1210,15 +1423,22 @@ ASTNode *parse_for(ParserContext *ctx, Lexer *l) ASTNode *memb_is_none = ast_create(NODE_EXPR_MEMBER); ASTNode *opt_ref1 = ast_create(NODE_EXPR_VAR); opt_ref1->var_ref.name = xstrdup("__opt"); + if (option_type_ptr) + { + opt_ref1->resolved_type = xstrdup(option_type_ptr); + } memb_is_none->member.target = opt_ref1; memb_is_none->member.field = xstrdup("is_none"); call_is_none->call.callee = memb_is_none; + call_is_none->call.args = NULL; + call_is_none->call.arg_count = 0; - ASTNode *break_stmt = ast_create(NODE_BREAK); - + // if (__opt.is_none()) break; ASTNode *if_break = ast_create(NODE_IF); if_break->if_stmt.condition = call_is_none; + ASTNode *break_stmt = ast_create(NODE_BREAK); if_break->if_stmt.then_body = break_stmt; + if_break->if_stmt.else_body = NULL; APPEND_STMT(if_break); // var <user_var> = __opt.unwrap(); @@ -1231,25 +1451,28 @@ ASTNode *parse_for(ParserContext *ctx, Lexer *l) ASTNode *memb_unwrap = ast_create(NODE_EXPR_MEMBER); ASTNode *opt_ref2 = ast_create(NODE_EXPR_VAR); opt_ref2->var_ref.name = xstrdup("__opt"); + if (option_type_ptr) + { + opt_ref2->resolved_type = xstrdup(option_type_ptr); + } memb_unwrap->member.target = opt_ref2; memb_unwrap->member.field = xstrdup("unwrap"); call_unwrap->call.callee = memb_unwrap; + call_unwrap->call.args = NULL; + call_unwrap->call.arg_count = 0; user_var_decl->var_decl.init_expr = call_unwrap; APPEND_STMT(user_var_decl); - // User Body + // User body statements enter_scope(ctx); add_symbol(ctx, var_name, NULL, NULL); - ASTNode *user_body_node; - if (lexer_peek(l).type == TOK_LBRACE) + // Body block + ASTNode *stmt = parse_statement(ctx, l); + ASTNode *user_body_node = stmt; + if (stmt && stmt->type != NODE_BLOCK) { - user_body_node = parse_block(ctx, l); - } - else - { - ASTNode *stmt = parse_statement(ctx, l); ASTNode *blk = ast_create(NODE_BLOCK); blk->block.statements = stmt; user_body_node = blk; @@ -1262,10 +1485,21 @@ ASTNode *parse_for(ParserContext *ctx, Lexer *l) loop_body->block.statements = stmts_head; while_loop->while_stmt.body = loop_body; - // Wrap entire thing in a block to scope _it + // Wrap entire thing in a block to scope __it (and __zc_arr_slice if present) ASTNode *outer_block = ast_create(NODE_BLOCK); - it_decl->next = while_loop; - outer_block->block.statements = it_decl; + if (slice_decl) + { + // Chain: slice_decl -> it_decl -> while_loop + slice_decl->next = it_decl; + it_decl->next = while_loop; + outer_block->block.statements = slice_decl; + } + else + { + // Chain: it_decl -> while_loop + it_decl->next = while_loop; + outer_block->block.statements = it_decl; + } return outer_block; } @@ -1877,7 +2111,7 @@ ASTNode *parse_statement(ParserContext *ctx, Lexer *l) lexer_next(&lookahead); TokenType next_type = lexer_peek(&lookahead).type; - if (next_type == TOK_SEMICOLON || next_type == TOK_DOTDOT) + if (next_type == TOK_SEMICOLON || next_type == TOK_DOTDOT || next_type == TOK_RBRACE) { Token t = lexer_next(l); // consume string @@ -1894,8 +2128,7 @@ ASTNode *parse_statement(ParserContext *ctx, Lexer *l) inner[t.len - 2] = 0; } - // ; means println (end of line), .. means print (continuation) - int is_ln = (next_type == TOK_SEMICOLON); + int is_ln = (next_type == TOK_SEMICOLON || next_type == TOK_RBRACE); char **used_syms = NULL; int used_count = 0; char *code = @@ -1913,6 +2146,7 @@ ASTNode *parse_statement(ParserContext *ctx, Lexer *l) lexer_next(l); // consume optional ; } } + // If TOK_RBRACE, do not consume it, so parse_block can see it and terminate loop. ASTNode *n = ast_create(NODE_RAW_STMT); // Append semicolon to Statement Expression to make it a valid statement @@ -3185,7 +3419,7 @@ char *run_comptime_block(ParserContext *ctx, Lexer *l) ASTNode *fn = ref->node; if (fn && fn->type == NODE_FUNCTION && fn->func.is_comptime) { - emit_func_signature(f, fn, NULL); + emit_func_signature(ctx, f, fn, NULL); fprintf(f, ";\n"); codegen_node_single(ctx, fn, f); } diff --git a/src/parser/parser_struct.c b/src/parser/parser_struct.c index 84450ba..e53b56c 100644 --- a/src/parser/parser_struct.c +++ b/src/parser/parser_struct.c @@ -12,6 +12,114 @@ #include "zprep_plugin.h" #include "../codegen/codegen.h" +extern char *g_current_filename; + +/** + * @brief Auto-imports std/mem.zc if not already imported. + * + * This is called when the Drop trait is used (impl Drop for X). + */ +static void auto_import_std_mem(ParserContext *ctx) +{ + // Check if Drop trait is already registered (means mem.zc was imported) + if (check_impl(ctx, "Drop", "__trait_marker__")) + { + // Check_impl returns 0 if not found, but we need a different check + // Let's check if we can find any indicator that mem.zc was loaded + } + + // Try to find and import std/mem.zc + static const char *std_paths[] = {"std/mem.zc", "./std/mem.zc", NULL}; + static const char *system_paths[] = {"/usr/local/share/zenc", "/usr/share/zenc", NULL}; + + char resolved_path[1024]; + int found = 0; + + // First, try relative to current file + if (g_current_filename) + { + char *current_dir = xstrdup(g_current_filename); + char *last_slash = strrchr(current_dir, '/'); + if (last_slash) + { + *last_slash = 0; + snprintf(resolved_path, sizeof(resolved_path), "%s/std/mem.zc", current_dir); + if (access(resolved_path, R_OK) == 0) + { + found = 1; + } + } + free(current_dir); + } + + // Try relative paths + if (!found) + { + for (int i = 0; std_paths[i] && !found; i++) + { + if (access(std_paths[i], R_OK) == 0) + { + strncpy(resolved_path, std_paths[i], sizeof(resolved_path) - 1); + resolved_path[sizeof(resolved_path) - 1] = '\0'; + found = 1; + } + } + } + + // Try system paths + if (!found) + { + for (int i = 0; system_paths[i] && !found; i++) + { + snprintf(resolved_path, sizeof(resolved_path), "%s/std/mem.zc", system_paths[i]); + if (access(resolved_path, R_OK) == 0) + { + found = 1; + } + } + } + + if (!found) + { + return; // Could not find std/mem.zc + } + + // Canonicalize path + char *real_fn = realpath(resolved_path, NULL); + if (real_fn) + { + strncpy(resolved_path, real_fn, sizeof(resolved_path) - 1); + resolved_path[sizeof(resolved_path) - 1] = '\0'; + free(real_fn); + } + + // Check if already imported + if (is_file_imported(ctx, resolved_path)) + { + return; + } + mark_file_imported(ctx, resolved_path); + + // Load and parse the file + char *src = load_file(resolved_path); + if (!src) + { + return; // Could not load file + } + + Lexer i; + lexer_init(&i, src); + + // Save and restore filename context + char *saved_fn = g_current_filename; + g_current_filename = resolved_path; + + // Parse the mem module contents + parse_program_nodes(ctx, &i); + + g_current_filename = saved_fn; +} + // Trait Parsing ASTNode *parse_trait(ParserContext *ctx, Lexer *l) { @@ -100,7 +208,7 @@ ASTNode *parse_trait(ParserContext *ctx, Lexer *l) char **param_names = NULL; int is_varargs = 0; char *args = parse_and_convert_args(ctx, l, &defaults, &arg_count, &arg_types, ¶m_names, - &is_varargs); + &is_varargs, NULL); char *ret = xstrdup("void"); if (lexer_peek(l).type == TOK_ARROW) @@ -149,6 +257,7 @@ ASTNode *parse_trait(ParserContext *ctx, Lexer *l) } register_trait(name); + add_to_global_list(ctx, n_node); // Track for codegen (VTable emission) return n_node; } @@ -206,6 +315,12 @@ ASTNode *parse_impl(ParserContext *ctx, Lexer *l) register_generic(ctx, target_gen_param); } + // Auto-import std/mem.zc if implementing Drop, Copy, or Clone traits + if (strcmp(name1, "Drop") == 0 || strcmp(name1, "Copy") == 0 || strcmp(name1, "Clone") == 0) + { + auto_import_std_mem(ctx); + } + register_impl(ctx, name1, name2); // RAII: Check for "Drop" trait implementation @@ -652,7 +767,7 @@ ASTNode *parse_impl(ParserContext *ctx, Lexer *l) } } -ASTNode *parse_struct(ParserContext *ctx, Lexer *l, int is_union) +ASTNode *parse_struct(ParserContext *ctx, Lexer *l, int is_union, int is_opaque) { lexer_next(l); // eat struct or union @@ -705,6 +820,7 @@ ASTNode *parse_struct(ParserContext *ctx, Lexer *l, int is_union) n->strct.is_union = is_union; n->strct.fields = NULL; n->strct.is_incomplete = 1; + n->strct.is_opaque = is_opaque; return n; } @@ -800,10 +916,6 @@ ASTNode *parse_struct(ParserContext *ctx, Lexer *l, int is_union) ASTNode *nf = ast_create(NODE_FIELD); nf->field.name = xstrdup(f->field.name); nf->field.type = xstrdup(f->field.type); - // Copy type info? Ideally deep copy or ref - // For now, we leave it NULL or shallow copy if needed, but mixins usually - // aren't generic params themselves in the same way. - // Let's shallow copy for safety if it exists. nf->type_info = f->type_info; if (!h) @@ -829,7 +941,6 @@ ASTNode *parse_struct(ParserContext *ctx, Lexer *l, int is_union) free(use_name); continue; } - // --------------------------------------- if (t.type == TOK_IDENT) { @@ -904,8 +1015,10 @@ ASTNode *parse_struct(ParserContext *ctx, Lexer *l, int is_union) node->strct.generic_params = gps; node->strct.generic_param_count = gp_count; node->strct.is_union = is_union; + node->strct.is_opaque = is_opaque; node->strct.used_structs = temp_used_structs; node->strct.used_struct_count = temp_used_count; + node->strct.defined_in_file = g_current_filename ? xstrdup(g_current_filename) : NULL; if (gp_count > 0) { @@ -1102,7 +1215,7 @@ ASTNode *parse_enum(ParserContext *ctx, Lexer *l) node->enm.name = ename; node->enm.variants = h; - node->enm.generic_param = gp; // 3. Store generic param + node->enm.generic_param = gp; // Store generic param if (gp) { diff --git a/src/parser/parser_type.c b/src/parser/parser_type.c index c01f061..49e961c 100644 --- a/src/parser/parser_type.c +++ b/src/parser/parser_type.c @@ -33,12 +33,25 @@ Type *parse_type_base(ParserContext *ctx, Lexer *l) char *name = token_strdup(t); // Check for alias - const char *aliased = find_type_alias(ctx, name); - if (aliased) + TypeAlias *alias_node = find_type_alias_node(ctx, name); + if (alias_node) { free(name); Lexer tmp; - lexer_init(&tmp, aliased); + lexer_init(&tmp, alias_node->original_type); + + if (alias_node->is_opaque) + { + Type *underlying = parse_type_formal(ctx, &tmp); + Type *wrapper = type_new(TYPE_ALIAS); + wrapper->name = xstrdup(alias_node->alias); + wrapper->inner = underlying; + wrapper->alias.is_opaque_alias = 1; + wrapper->alias.alias_defined_in_file = + alias_node->defined_in_file ? xstrdup(alias_node->defined_in_file) : NULL; + return wrapper; + } + return parse_type_formal(ctx, &tmp); } @@ -287,6 +300,90 @@ Type *parse_type_base(ParserContext *ctx, Lexer *l) free(name); return type_new(TYPE_I16); } + + // C23 BitInt Support (i42, u256, etc.) + if ((name[0] == 'i' || name[0] == 'u') && isdigit(name[1])) + { + // Verify it is a purely numeric suffix + int valid = 1; + for (size_t k = 1; k < strlen(name); k++) + { + if (!isdigit(name[k])) + { + valid = 0; + break; + } + } + if (valid) + { + int width = atoi(name + 1); + if (width > 0) + { + // Map standard widths to standard types for standard ABI/C compabitility + if (name[0] == 'i') + { + if (width == 8) + { + free(name); + return type_new(TYPE_I8); + } + if (width == 16) + { + free(name); + return type_new(TYPE_I16); + } + if (width == 32) + { + free(name); + return type_new(TYPE_I32); + } + if (width == 64) + { + free(name); + return type_new(TYPE_I64); + } + if (width == 128) + { + free(name); + return type_new(TYPE_I128); + } + } + else + { + if (width == 8) + { + free(name); + return type_new(TYPE_U8); + } + if (width == 16) + { + free(name); + return type_new(TYPE_U16); + } + if (width == 32) + { + free(name); + return type_new(TYPE_U32); + } + if (width == 64) + { + free(name); + return type_new(TYPE_U64); + } + if (width == 128) + { + free(name); + return type_new(TYPE_U128); + } + } + + Type *t = type_new(name[0] == 'u' ? TYPE_UBITINT : TYPE_BITINT); + t->array_size = width; + free(name); + return t; + } + } + } if (strcmp(name, "u16") == 0) { free(name); diff --git a/src/parser/parser_utils.c b/src/parser/parser_utils.c index 4e85500..28d2c11 100644 --- a/src/parser/parser_utils.c +++ b/src/parser/parser_utils.c @@ -402,23 +402,33 @@ void add_to_struct_list(ParserContext *ctx, ASTNode *node) ctx->parsed_structs_list = r; } -void register_type_alias(ParserContext *ctx, const char *alias, const char *original) +void register_type_alias(ParserContext *ctx, const char *alias, const char *original, int is_opaque, + const char *defined_in_file) { TypeAlias *ta = xmalloc(sizeof(TypeAlias)); ta->alias = xstrdup(alias); ta->original_type = xstrdup(original); + ta->is_opaque = is_opaque; + ta->defined_in_file = defined_in_file ? xstrdup(defined_in_file) : NULL; ta->next = ctx->type_aliases; ctx->type_aliases = ta; } const char *find_type_alias(ParserContext *ctx, const char *alias) { + TypeAlias *ta = find_type_alias_node(ctx, alias); + return ta ? ta->original_type : NULL; +} + +TypeAlias *find_type_alias_node(ParserContext *ctx, const char *alias) +{ TypeAlias *ta = ctx->type_aliases; while (ta) { if (strcmp(ta->alias, alias) == 0) { - return ta->original_type; + // printf("DEBUG: Found Alias '%s' (Opaque: %d)\n", alias, ta->is_opaque); + return ta; } ta = ta->next; } @@ -3382,7 +3392,8 @@ char *consume_and_rewrite(ParserContext *ctx, Lexer *l) } char *parse_and_convert_args(ParserContext *ctx, Lexer *l, char ***defaults_out, int *count_out, - Type ***types_out, char ***names_out, int *is_varargs_out) + Type ***types_out, char ***names_out, int *is_varargs_out, + char ***ctype_overrides_out) { Token t = lexer_next(l); if (t.type != TOK_LPAREN) @@ -3396,18 +3407,52 @@ char *parse_and_convert_args(ParserContext *ctx, Lexer *l, char ***defaults_out, char **defaults = xmalloc(sizeof(char *) * 16); Type **types = xmalloc(sizeof(Type *) * 16); char **names = xmalloc(sizeof(char *) * 16); + char **ctype_overrides = xmalloc(sizeof(char *) * 16); for (int i = 0; i < 16; i++) { defaults[i] = NULL; types[i] = NULL; names[i] = NULL; + ctype_overrides[i] = NULL; } if (lexer_peek(l).type != TOK_RPAREN) { while (1) { + // Check for @ctype("...") before parameter + char *ctype_override = NULL; + if (lexer_peek(l).type == TOK_AT) + { + lexer_next(l); // eat @ + Token attr = lexer_next(l); + if (attr.type == TOK_IDENT && attr.len == 5 && strncmp(attr.start, "ctype", 5) == 0) + { + if (lexer_next(l).type != TOK_LPAREN) + { + zpanic_at(lexer_peek(l), "Expected ( after @ctype"); + } + Token ctype_tok = lexer_next(l); + if (ctype_tok.type != TOK_STRING) + { + zpanic_at(ctype_tok, "@ctype requires a string argument"); + } + // Extract string content (strip quotes) + ctype_override = xmalloc(ctype_tok.len - 1); + strncpy(ctype_override, ctype_tok.start + 1, ctype_tok.len - 2); + ctype_override[ctype_tok.len - 2] = 0; + if (lexer_next(l).type != TOK_RPAREN) + { + zpanic_at(lexer_peek(l), "Expected ) after @ctype string"); + } + } + else + { + zpanic_at(attr, "Unknown parameter attribute @%.*s", attr.len, attr.start); + } + } + Token t = lexer_next(l); // Handle 'self' if (t.type == TOK_IDENT && strncmp(t.start, "self", 4) == 0 && t.len == 4) @@ -3460,6 +3505,7 @@ char *parse_and_convert_args(ParserContext *ctx, Lexer *l, char ***defaults_out, types[count] = type_new_ptr(type_new(TYPE_VOID)); add_symbol(ctx, "self", "void*", types[count]); } + ctype_overrides[count] = ctype_override; count++; } else @@ -3504,11 +3550,20 @@ char *parse_and_convert_args(ParserContext *ctx, Lexer *l, char ***defaults_out, } else { - strcat(buf, type_str); + // Use @ctype override if present + if (ctype_override) + { + strcat(buf, ctype_override); + } + else + { + strcat(buf, type_str); + } strcat(buf, " "); strcat(buf, name); } + ctype_overrides[count] = ctype_override; count++; if (lexer_peek(l).type == TOK_OP && is_token(lexer_peek(l), "=")) @@ -3583,6 +3638,10 @@ char *parse_and_convert_args(ParserContext *ctx, Lexer *l, char ***defaults_out, *count_out = count; *types_out = types; *names_out = names; + if (ctype_overrides_out) + { + *ctype_overrides_out = ctype_overrides; + } return buf; } |