andrew/akbasic
1
0
Fork 0
Code Issues 28 Pull Requests 1 Actions Packages Projects Releases Wiki Activity
Files
c70f8e7727d7a5ec28d7896fcb4ab3e0c0f13e03
akbasic/src/grammar.c

394 lines
14 KiB
C
Raw Normal View History

Port the BASIC interpreter from Go to C Reproduces deps/basicinterpret in C, in the idiom of the ak* libraries. All 41 .bas files in the reference's corpus produce byte-identical stdout, including the trailing double newline on an error line -- that comes from basicError building a string ending in \n and handing it to Println, and array_outofbounds.txt encodes it. The corpus is driven in place from the submodule as 41 individual CTest cases rather than copied, so it cannot drift from upstream. Eighteen unit tests cover what the corpus cannot reach. Three structural changes carry most of the work. Go's three reflection lookups (Command*, Function*, ParseCommand*) become one sorted dispatch table in src/verbs.c searched with bsearch; adding a verb is a row and two functions. The five Go maps become one fixed open-addressed table over aksl_strhash_djb2. And run(), which owned the process until MODE_QUIT, splits into step() plus a bounded run() -- goal 3 requires a host game to be able to bound execution, and nothing in the library now terminates the process or touches SDL. Output goes through an akbasic_TextSink vtable. src/sink_stdio.c is what makes the corpus runnable with no SDL present; the akgl-backed sink is still to come and is blocked on libakgl having no text-measurement call. src/convert.c exists because libakstdlib's aksl_ato* family cannot report a conversion failure (its TODO.md 2.1.5). The reference checks strconv's error at four sites and turns it into a BASIC error; routing those through aksl_atoi would have turned four diagnosable errors into wrong answers, with VAL("garbage") quietly returning 0. TODO.md 1.9 records which libakstdlib calls are cleared for use here and which are not. Reference defects are reproduced, not fixed: the golden files encode the observed behaviour and a silent correction is a behaviour change. TODO.md section 6 lists sixteen, and tests/known_reference_defects.c asserts the *correct* contract for six of them under AKBASIC_KNOWN_FAILING_TESTS, so a fix shows up as "unexpectedly passed". Five of the sixteen were found by this port and are new: subtraction stops after one operator so 1-2-3 computes 1-2 and abandons the rest of the line (a wrong answer, not a refused one); a unary-minus argument inflates a function's arity so ABS(-9) is rejected; a comparison operator in a line's final column is dropped; hex literals never survive the scanner; and the "Reserved word in variable name" check is dead code. Where the reference reaches undefined behaviour by a route that is defined in Go -- an out-of-range shift, a negative string multiplier, integer division by zero -- this raises instead of inheriting the UB. No golden case exercises any of them. The top-level CMakeLists shadows add_test, set_tests_properties and add_custom_target around all three add_subdirectory calls. Without it libakerror's tests land in our suite as Not Run, and its un-namespaced `coverage` target stops a coverage build from configuring at all. Test targets are akbasic_test_<name>: bare test_<name> collides with libakstdlib's, which is what broke libakgl's configure in c2b16d3. ctest 59/59; ASan+UBSan 59/59; 92.3% line and 96.9% function coverage; no warnings under -Wall -Wextra. Branch coverage is not a target, for the reason libakstdlib and libakgl both record: the akerror macros expand into large branch trees at every call site. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-07-30 23:53:56 -04:00
/**
* @file grammar.c
* @brief Implements token and AST leaf construction.
*/
#include <inttypes.h>
#include <stdio.h>
#include <string.h>
#include <akerror.h>
#include <akbasic/convert.h>
#include <akbasic/error.h>
#include <akbasic/grammar.h>
/* Copy into a leaf's inline identifier/literal buffer, refusing truncation. */
static akerr_ErrorContext *copy_bounded(char *dest, const char *src, const char *what)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (src != NULL), AKERR_NULLPOINTER, "NULL %s", what);
FAIL_ZERO_RETURN(errctx, (strlen(src) < AKBASIC_MAX_STRING_LENGTH),
AKBASIC_ERR_VALUE,
"%s of %zu characters exceeds the %d character limit",
what, strlen(src), AKBASIC_MAX_STRING_LENGTH - 1);
strncpy(dest, src, AKBASIC_MAX_STRING_LENGTH - 1);
dest[AKBASIC_MAX_STRING_LENGTH - 1] = '\0';
SUCCEED_RETURN(errctx);
}
akerr_ErrorContext *akbasic_token_init(akbasic_Token *obj)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL token in init");
obj->tokentype = AKBASIC_TOK_UNDEFINED;
obj->lineno = 0;
obj->lexeme[0] = '\0';
SUCCEED_RETURN(errctx);
}
akerr_ErrorContext *akbasic_leaf_init(akbasic_ASTLeaf *obj, akbasic_LeafType leaftype)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL leaf in init");
obj->leaftype = leaftype;
obj->parent = NULL;
obj->left = NULL;
obj->right = NULL;
obj->expr = NULL;
obj->identifier[0] = '\0';
obj->literal_int = 0;
obj->literal_float = 0.0;
obj->literal_string[0] = '\0';
obj->operator_ = AKBASIC_TOK_UNDEFINED;
SUCCEED_RETURN(errctx);
}
/*
* Take one leaf from the pool. Recursion in clone_into() is bounded by the pool
* capacity, so a cyclic tree exhausts the pool and errors rather than running
* off the stack.
*/
static akerr_ErrorContext *pool_take(akbasic_LeafPool *pool, akbasic_ASTLeaf **dest)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (pool != NULL), AKERR_NULLPOINTER, "NULL leaf pool");
FAIL_ZERO_RETURN(errctx, (pool->leaves != NULL), AKERR_NULLPOINTER, "Leaf pool has no storage");
FAIL_ZERO_RETURN(errctx, (pool->next < pool->capacity), AKBASIC_ERR_BOUNDS,
"No more leaves available");
*dest = &pool->leaves[pool->next];
pool->next += 1;
SUCCEED_RETURN(errctx);
}
static akerr_ErrorContext *clone_into(akbasic_ASTLeaf *self, akbasic_LeafPool *pool, akbasic_ASTLeaf **dest)
{
PREPARE_ERROR(errctx);
akbasic_ASTLeaf *copy = NULL;
if ( self == NULL ) {
*dest = NULL;
SUCCEED_RETURN(errctx);
}
PASS(errctx, pool_take(pool, &copy));
PASS(errctx, akbasic_leaf_init(copy, self->leaftype));
copy->parent = self->parent;
copy->literal_int = self->literal_int;
copy->literal_float = self->literal_float;
memcpy(copy->literal_string, self->literal_string, sizeof(copy->literal_string));
memcpy(copy->identifier, self->identifier, sizeof(copy->identifier));
copy->operator_ = self->operator_;
PASS(errctx, clone_into(self->left, pool, &copy->left));
PASS(errctx, clone_into(self->right, pool, &copy->right));
PASS(errctx, clone_into(self->expr, pool, &copy->expr));
*dest = copy;
SUCCEED_RETURN(errctx);
}
akerr_ErrorContext *akbasic_leaf_clone(akbasic_ASTLeaf *self, akbasic_LeafPool *pool, akbasic_ASTLeaf **dest)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (dest != NULL), AKERR_NULLPOINTER, "NULL destination in clone");
PASS(errctx, clone_into(self, pool, dest));
SUCCEED_RETURN(errctx);
}
akbasic_ASTLeaf *akbasic_leaf_first_argument(akbasic_ASTLeaf *self)
{
if ( self == NULL ||
self->right == NULL ||
self->right->leaftype != AKBASIC_LEAF_ARGUMENTLIST ||
self->right->operator_ != AKBASIC_TOK_FUNCTION_ARGUMENT ) {
return NULL;
}
return self->right->right;
}
akbasic_ASTLeaf *akbasic_leaf_first_subscript(akbasic_ASTLeaf *self)
{
if ( self == NULL ||
self->right == NULL ||
self->right->leaftype != AKBASIC_LEAF_ARGUMENTLIST ||
self->right->operator_ != AKBASIC_TOK_ARRAY_SUBSCRIPT ) {
return NULL;
}
return self->right->right;
}
bool akbasic_leaf_is_identifier(akbasic_ASTLeaf *self)
{
return (self != NULL &&
(self->leaftype == AKBASIC_LEAF_IDENTIFIER ||
self->leaftype == AKBASIC_LEAF_IDENTIFIER_INT ||
self->leaftype == AKBASIC_LEAF_IDENTIFIER_FLOAT ||
self->leaftype == AKBASIC_LEAF_IDENTIFIER_STRING));
}
bool akbasic_leaf_is_literal(akbasic_ASTLeaf *self)
{
return (self != NULL &&
(self->leaftype == AKBASIC_LEAF_LITERAL_INT ||
self->leaftype == AKBASIC_LEAF_LITERAL_FLOAT ||
self->leaftype == AKBASIC_LEAF_LITERAL_STRING));
}
akerr_ErrorContext *akbasic_leaf_new_comparison(akbasic_ASTLeaf *obj, akbasic_ASTLeaf *left, akbasic_TokenType op, akbasic_ASTLeaf *right)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL leaf in new_comparison");
FAIL_ZERO_RETURN(errctx, (left != NULL && right != NULL), AKERR_NULLPOINTER,
"nil pointer arguments");
PASS(errctx, akbasic_leaf_init(obj, AKBASIC_LEAF_COMPARISON));
obj->left = left;
obj->right = right;
switch ( op ) {
case AKBASIC_TOK_LESS_THAN:
case AKBASIC_TOK_LESS_THAN_EQUAL:
case AKBASIC_TOK_NOT_EQUAL:
case AKBASIC_TOK_GREATER_THAN:
case AKBASIC_TOK_GREATER_THAN_EQUAL:
SUCCEED_RETURN(errctx);
default:
FAIL_RETURN(errctx, AKBASIC_ERR_SYNTAX, "Invalid operator %d for comparison", (int)op);
}
}
akerr_ErrorContext *akbasic_leaf_new_binary(akbasic_ASTLeaf *obj, akbasic_ASTLeaf *left, akbasic_TokenType op, akbasic_ASTLeaf *right)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL leaf in new_binary");
FAIL_ZERO_RETURN(errctx, (left != NULL && right != NULL), AKERR_NULLPOINTER,
"nil pointer arguments");
PASS(errctx, akbasic_leaf_init(obj, AKBASIC_LEAF_BINARY));
obj->left = left;
obj->right = right;
obj->operator_ = op;
SUCCEED_RETURN(errctx);
}
akerr_ErrorContext *akbasic_leaf_new_unary(akbasic_ASTLeaf *obj, akbasic_TokenType op, akbasic_ASTLeaf *right)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL leaf in new_unary");
FAIL_ZERO_RETURN(errctx, (right != NULL), AKERR_NULLPOINTER, "nil pointer arguments");
PASS(errctx, akbasic_leaf_init(obj, AKBASIC_LEAF_UNARY));
obj->right = right;
obj->operator_ = op;
SUCCEED_RETURN(errctx);
}
akerr_ErrorContext *akbasic_leaf_new_function(akbasic_ASTLeaf *obj, const char *fname, akbasic_ASTLeaf *right)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL leaf in new_function");
PASS(errctx, akbasic_leaf_init(obj, AKBASIC_LEAF_FUNCTION));
obj->right = right;
obj->operator_ = AKBASIC_TOK_COMMAND;
PASS(errctx, copy_bounded(obj->identifier, fname, "function name"));
SUCCEED_RETURN(errctx);
}
akerr_ErrorContext *akbasic_leaf_new_command(akbasic_ASTLeaf *obj, const char *cmdname, akbasic_ASTLeaf *right)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL leaf in new_command");
PASS(errctx, akbasic_leaf_init(obj, AKBASIC_LEAF_COMMAND));
obj->right = right;
obj->operator_ = AKBASIC_TOK_COMMAND;
PASS(errctx, copy_bounded(obj->identifier, cmdname, "command name"));
SUCCEED_RETURN(errctx);
}
akerr_ErrorContext *akbasic_leaf_new_immediate_command(akbasic_ASTLeaf *obj, const char *cmdname, akbasic_ASTLeaf *right)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL leaf in new_immediate_command");
PASS(errctx, akbasic_leaf_init(obj, AKBASIC_LEAF_COMMAND_IMMEDIATE));
obj->right = right;
obj->operator_ = AKBASIC_TOK_COMMAND_IMMEDIATE;
PASS(errctx, copy_bounded(obj->identifier, cmdname, "command name"));
SUCCEED_RETURN(errctx);
}
akerr_ErrorContext *akbasic_leaf_new_branch(akbasic_ASTLeaf *obj, akbasic_ASTLeaf *expr, akbasic_ASTLeaf *trueleaf, akbasic_ASTLeaf *falseleaf)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL leaf in new_branch");
FAIL_ZERO_RETURN(errctx, (expr != NULL), AKERR_NULLPOINTER, "nil pointer arguments");
PASS(errctx, akbasic_leaf_init(obj, AKBASIC_LEAF_BRANCH));
obj->expr = expr;
obj->left = trueleaf;
obj->right = falseleaf;
SUCCEED_RETURN(errctx);
}
akerr_ErrorContext *akbasic_leaf_new_grouping(akbasic_ASTLeaf *obj, akbasic_ASTLeaf *expr)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL leaf in new_grouping");
FAIL_ZERO_RETURN(errctx, (expr != NULL), AKERR_NULLPOINTER, "nil pointer arguments");
PASS(errctx, akbasic_leaf_init(obj, AKBASIC_LEAF_GROUPING));
obj->expr = expr;
SUCCEED_RETURN(errctx);
}
akerr_ErrorContext *akbasic_leaf_new_literal_int(akbasic_ASTLeaf *obj, const char *lexeme)
{
PREPARE_ERROR(errctx);
int base = 10;
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL leaf in new_literal_int");
FAIL_ZERO_RETURN(errctx, (lexeme != NULL), AKERR_NULLPOINTER, "NULL lexeme in new_literal_int");
FAIL_ZERO_RETURN(errctx, (lexeme[0] != '\0'), AKBASIC_ERR_VALUE, "Empty integer literal");
/*
* The reference selects base 8 for any lexeme starting with '0', so `010`
* parses as 8 and `08` is an error. Commodore BASIC has no octal literals
* and this is TODO.md section 12 item 10 -- but it is reproduced here,
* because "port the behaviour first" is the rule and the fix is its own
* commit with its own test.
*/
if ( strlen(lexeme) > 2 && strncmp(lexeme, "0x", 2) == 0 ) {
base = 16;
} else if ( lexeme[0] == '0' ) {
base = 8;
}
PASS(errctx, akbasic_leaf_init(obj, AKBASIC_LEAF_LITERAL_INT));
PASS(errctx, akbasic_str_to_int64(lexeme, base, &obj->literal_int));
SUCCEED_RETURN(errctx);
}
akerr_ErrorContext *akbasic_leaf_new_literal_float(akbasic_ASTLeaf *obj, const char *lexeme)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL leaf in new_literal_float");
PASS(errctx, akbasic_leaf_init(obj, AKBASIC_LEAF_LITERAL_FLOAT));
PASS(errctx, akbasic_str_to_double(lexeme, &obj->literal_float));
SUCCEED_RETURN(errctx);
}
akerr_ErrorContext *akbasic_leaf_new_literal_string(akbasic_ASTLeaf *obj, const char *lexeme)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL leaf in new_literal_string");
PASS(errctx, akbasic_leaf_init(obj, AKBASIC_LEAF_LITERAL_STRING));
PASS(errctx, copy_bounded(obj->literal_string, lexeme, "string literal"));
SUCCEED_RETURN(errctx);
}
akerr_ErrorContext *akbasic_leaf_new_identifier(akbasic_ASTLeaf *obj, akbasic_LeafType leaftype, const char *lexeme)
{
PREPARE_ERROR(errctx);
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL leaf in new_identifier");
PASS(errctx, akbasic_leaf_init(obj, leaftype));
PASS(errctx, copy_bounded(obj->identifier, lexeme, "identifier"));
SUCCEED_RETURN(errctx);
}
static const char *operator_to_str(akbasic_TokenType op)
{
switch ( op ) {
case AKBASIC_TOK_EQUAL: return "=";
case AKBASIC_TOK_LESS_THAN: return "<";
case AKBASIC_TOK_GREATER_THAN: return ">";
case AKBASIC_TOK_LESS_THAN_EQUAL: return "<=";
case AKBASIC_TOK_GREATER_THAN_EQUAL: return ">=";
case AKBASIC_TOK_NOT_EQUAL: return "<>";
case AKBASIC_TOK_PLUS: return "+";
case AKBASIC_TOK_MINUS: return "-";
case AKBASIC_TOK_STAR: return "*";
case AKBASIC_TOK_LEFT_SLASH: return "/";
case AKBASIC_TOK_CARAT: return "^";
case AKBASIC_TOK_NOT: return "NOT";
case AKBASIC_TOK_AND: return "AND";
case AKBASIC_TOK_OR: return "OR";
default: return "";
}
}
akerr_ErrorContext *akbasic_leaf_to_string(akbasic_ASTLeaf *self, char *dest, size_t len)
{
PREPARE_ERROR(errctx);
char sub1[AKBASIC_MAX_STRING_LENGTH];
char sub2[AKBASIC_MAX_STRING_LENGTH];
FAIL_ZERO_RETURN(errctx, (self != NULL), AKERR_NULLPOINTER, "NULL leaf in to_string");
FAIL_ZERO_RETURN(errctx, (dest != NULL), AKERR_NULLPOINTER, "NULL destination in to_string");
FAIL_ZERO_RETURN(errctx, (len > 0), AKBASIC_ERR_BOUNDS, "Zero-length destination in to_string");
switch ( self->leaftype ) {
case AKBASIC_LEAF_LITERAL_INT:
snprintf(dest, len, "%" PRId64, self->literal_int);
break;
case AKBASIC_LEAF_LITERAL_FLOAT:
snprintf(dest, len, "%f", self->literal_float);
break;
case AKBASIC_LEAF_LITERAL_STRING:
snprintf(dest, len, "%s", self->literal_string);
break;
case AKBASIC_LEAF_IDENTIFIER_INT:
case AKBASIC_LEAF_IDENTIFIER_FLOAT:
case AKBASIC_LEAF_IDENTIFIER_STRING:
case AKBASIC_LEAF_IDENTIFIER:
snprintf(dest, len, "%s", self->identifier);
break;
case AKBASIC_LEAF_IDENTIFIER_STRUCT:
snprintf(dest, len, "NOT IMPLEMENTED");
break;
case AKBASIC_LEAF_UNARY:
PASS(errctx, akbasic_leaf_to_string(self->right, sub1, sizeof(sub1)));
snprintf(dest, len, "(%s %s)", operator_to_str(self->operator_), sub1);
break;
case AKBASIC_LEAF_BINARY:
PASS(errctx, akbasic_leaf_to_string(self->left, sub1, sizeof(sub1)));
PASS(errctx, akbasic_leaf_to_string(self->right, sub2, sizeof(sub2)));
snprintf(dest, len, "(%s %s %s)", operator_to_str(self->operator_), sub1, sub2);
break;
case AKBASIC_LEAF_GROUPING:
PASS(errctx, akbasic_leaf_to_string(self->expr, sub1, sizeof(sub1)));
snprintf(dest, len, "(group %s)", sub1);
break;
case AKBASIC_LEAF_COMMAND:
case AKBASIC_LEAF_COMMAND_IMMEDIATE:
case AKBASIC_LEAF_FUNCTION:
/*
* The reference falls through to Go's %+v struct dump here, which has no
* useful C equivalent. Print something a test can assert on instead.
*/
snprintf(dest, len, "(%s)", self->identifier);
break;
default:
snprintf(dest, len, "(leaf %d)", (int)self->leaftype);
break;
}
SUCCEED_RETURN(errctx);
}
Reference in New Issue Copy Permalink