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>
Co-Authored-By: Andrew Kesterson <andrew@aklabs.net>
This commit is contained in:
192
src/variable.c
Normal file
192
src/variable.c
Normal file
@@ -0,0 +1,192 @@
|
||||
/**
|
||||
* @file variable.c
|
||||
* @brief Implements the named variable slot and its subscript arithmetic.
|
||||
*/
|
||||
|
||||
#include <inttypes.h>
|
||||
#include <string.h>
|
||||
|
||||
#include <akerror.h>
|
||||
|
||||
#include <akbasic/error.h>
|
||||
#include <akbasic/variable.h>
|
||||
|
||||
/*
|
||||
* Flatten a subscript list to an index, walking the dimensions from the last to
|
||||
* the first exactly as the reference does. The bounds message is reproduced
|
||||
* character for character: tests/language/array_outofbounds.txt compares it with
|
||||
* strcmp, so a reworded message is a failing golden case.
|
||||
*/
|
||||
static akerr_ErrorContext *flatten_subscripts(akbasic_Variable *obj, int64_t *subscripts, int subscriptcount, int64_t *dest)
|
||||
{
|
||||
PREPARE_ERROR(errctx);
|
||||
int64_t flatindex = 0;
|
||||
int64_t multiplier = 1;
|
||||
int i = 0;
|
||||
|
||||
for ( i = subscriptcount - 1; i >= 0; i-- ) {
|
||||
FAIL_NONZERO_RETURN(errctx,
|
||||
(subscripts[i] < 0 || subscripts[i] >= obj->dimensions[i]),
|
||||
AKBASIC_ERR_BOUNDS,
|
||||
"Variable index access out of bounds at dimension %d: %" PRId64 " (max %" PRId64 ")",
|
||||
i, subscripts[i], obj->dimensions[i] - 1);
|
||||
flatindex += subscripts[i] * multiplier;
|
||||
multiplier *= obj->dimensions[i];
|
||||
}
|
||||
*dest = flatindex;
|
||||
SUCCEED_RETURN(errctx);
|
||||
}
|
||||
|
||||
akerr_ErrorContext *akbasic_variable_init(akbasic_Variable *obj, akbasic_ValuePool *pool, int64_t *sizes, int sizecount)
|
||||
{
|
||||
PREPARE_ERROR(errctx);
|
||||
int64_t totalsize = 1;
|
||||
size_t namelen = 0;
|
||||
char lastchar = '\0';
|
||||
int i = 0;
|
||||
|
||||
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL variable in init");
|
||||
FAIL_ZERO_RETURN(errctx, (pool != NULL), AKERR_NULLPOINTER, "NULL value pool in variable init");
|
||||
FAIL_ZERO_RETURN(errctx, (sizes != NULL), AKERR_NULLPOINTER, "NULL sizes in variable init");
|
||||
FAIL_ZERO_RETURN(errctx, (sizecount > 0 && sizecount <= AKBASIC_MAX_ARRAY_DEPTH),
|
||||
AKBASIC_ERR_BOUNDS,
|
||||
"Array dimension count %d out of range 1..%d",
|
||||
sizecount, AKBASIC_MAX_ARRAY_DEPTH);
|
||||
|
||||
namelen = strlen(obj->name);
|
||||
FAIL_ZERO_RETURN(errctx, (namelen > 0), AKBASIC_ERR_VALUE, "Invalid variable name");
|
||||
|
||||
/* Type comes from the suffix. A bare name keeps whatever type it had. */
|
||||
lastchar = obj->name[namelen - 1];
|
||||
switch ( lastchar ) {
|
||||
case '$':
|
||||
obj->valuetype = AKBASIC_TYPE_STRING;
|
||||
break;
|
||||
case '#':
|
||||
obj->valuetype = AKBASIC_TYPE_INTEGER;
|
||||
break;
|
||||
case '%':
|
||||
obj->valuetype = AKBASIC_TYPE_FLOAT;
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
|
||||
for ( i = 0; i < sizecount; i++ ) {
|
||||
FAIL_NONZERO_RETURN(errctx, (sizes[i] <= 0), AKBASIC_ERR_VALUE,
|
||||
"Array dimensions must be positive integers");
|
||||
FAIL_NONZERO_RETURN(errctx, (sizes[i] > AKBASIC_MAX_ARRAY_ELEMENTS),
|
||||
AKBASIC_ERR_BOUNDS,
|
||||
"Array dimension %d of %" PRId64 " exceeds the %d element limit",
|
||||
i, sizes[i], AKBASIC_MAX_ARRAY_ELEMENTS);
|
||||
totalsize *= sizes[i];
|
||||
FAIL_NONZERO_RETURN(errctx, (totalsize > AKBASIC_MAX_ARRAY_ELEMENTS),
|
||||
AKBASIC_ERR_BOUNDS,
|
||||
"Array of %" PRId64 " total elements exceeds the %d element limit",
|
||||
totalsize, AKBASIC_MAX_ARRAY_ELEMENTS);
|
||||
obj->dimensions[i] = sizes[i];
|
||||
}
|
||||
obj->dimensioncount = sizecount;
|
||||
|
||||
/*
|
||||
* Reuse the existing slice when it is already big enough. That makes a
|
||||
* re-DIM to the same or a smaller size free, which is the only re-DIM any
|
||||
* real program performs; growing takes fresh slots and abandons the old
|
||||
* ones, as documented on akbasic_ValuePool.
|
||||
*/
|
||||
if ( obj->values == NULL || obj->valuecount < (int)totalsize ) {
|
||||
PASS(errctx, akbasic_valuepool_take(pool, (int)totalsize, &obj->values));
|
||||
}
|
||||
obj->valuecount = (int)totalsize;
|
||||
|
||||
for ( i = 0; i < (int)totalsize; i++ ) {
|
||||
PASS(errctx, akbasic_value_init(&obj->values[i]));
|
||||
PASS(errctx, akbasic_value_zero(&obj->values[i]));
|
||||
obj->values[i].valuetype = obj->valuetype;
|
||||
obj->values[i].mutable_ = true;
|
||||
}
|
||||
SUCCEED_RETURN(errctx);
|
||||
}
|
||||
|
||||
akerr_ErrorContext *akbasic_variable_zero(akbasic_Variable *obj)
|
||||
{
|
||||
PREPARE_ERROR(errctx);
|
||||
|
||||
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL variable in zero");
|
||||
obj->valuetype = AKBASIC_TYPE_UNDEFINED;
|
||||
obj->mutable_ = true;
|
||||
SUCCEED_RETURN(errctx);
|
||||
}
|
||||
|
||||
akerr_ErrorContext *akbasic_variable_get_subscript(akbasic_Variable *obj, int64_t *subscripts, int subscriptcount, akbasic_Value **dest)
|
||||
{
|
||||
PREPARE_ERROR(errctx);
|
||||
int64_t index = 0;
|
||||
|
||||
FAIL_ZERO_RETURN(errctx, (obj != NULL), AKERR_NULLPOINTER, "NULL variable in get_subscript");
|
||||
FAIL_ZERO_RETURN(errctx, (subscripts != NULL), AKERR_NULLPOINTER, "NULL subscripts in get_subscript");
|
||||
FAIL_ZERO_RETURN(errctx, (dest != NULL), AKERR_NULLPOINTER, "NULL destination in get_subscript");
|
||||
FAIL_ZERO_RETURN(errctx, (obj->values != NULL), AKERR_NULLPOINTER,
|
||||
"Variable %s has no storage", obj->name);
|
||||
FAIL_ZERO_RETURN(errctx, (subscriptcount == obj->dimensioncount),
|
||||
AKBASIC_ERR_BOUNDS,
|
||||
"Variable %s has %d dimensions, received %d",
|
||||
obj->name, obj->dimensioncount, subscriptcount);
|
||||
|
||||
PASS(errctx, flatten_subscripts(obj, subscripts, subscriptcount, &index));
|
||||
*dest = &obj->values[index];
|
||||
SUCCEED_RETURN(errctx);
|
||||
}
|
||||
|
||||
akerr_ErrorContext *akbasic_variable_set_subscript(akbasic_Variable *obj, akbasic_Value *value, int64_t *subscripts, int subscriptcount)
|
||||
{
|
||||
PREPARE_ERROR(errctx);
|
||||
akbasic_Value *slot = NULL;
|
||||
|
||||
FAIL_ZERO_RETURN(errctx, (value != NULL), AKERR_NULLPOINTER, "NULL value in set_subscript");
|
||||
PASS(errctx, akbasic_variable_get_subscript(obj, subscripts, subscriptcount, &slot));
|
||||
PASS(errctx, akbasic_value_clone(value, slot));
|
||||
SUCCEED_RETURN(errctx);
|
||||
}
|
||||
|
||||
akerr_ErrorContext *akbasic_variable_set_integer(akbasic_Variable *obj, int64_t value, int64_t *subscripts, int subscriptcount)
|
||||
{
|
||||
PREPARE_ERROR(errctx);
|
||||
akbasic_Value tmp;
|
||||
|
||||
PASS(errctx, akbasic_value_zero(&tmp));
|
||||
tmp.valuetype = AKBASIC_TYPE_INTEGER;
|
||||
tmp.intval = value;
|
||||
PASS(errctx, akbasic_variable_set_subscript(obj, &tmp, subscripts, subscriptcount));
|
||||
SUCCEED_RETURN(errctx);
|
||||
}
|
||||
|
||||
akerr_ErrorContext *akbasic_variable_set_float(akbasic_Variable *obj, double value, int64_t *subscripts, int subscriptcount)
|
||||
{
|
||||
PREPARE_ERROR(errctx);
|
||||
akbasic_Value tmp;
|
||||
|
||||
PASS(errctx, akbasic_value_zero(&tmp));
|
||||
tmp.valuetype = AKBASIC_TYPE_FLOAT;
|
||||
tmp.floatval = value;
|
||||
PASS(errctx, akbasic_variable_set_subscript(obj, &tmp, subscripts, subscriptcount));
|
||||
SUCCEED_RETURN(errctx);
|
||||
}
|
||||
|
||||
akerr_ErrorContext *akbasic_variable_set_string(akbasic_Variable *obj, const char *value, int64_t *subscripts, int subscriptcount)
|
||||
{
|
||||
PREPARE_ERROR(errctx);
|
||||
akbasic_Value tmp;
|
||||
|
||||
FAIL_ZERO_RETURN(errctx, (value != NULL), AKERR_NULLPOINTER, "NULL string in set_string");
|
||||
FAIL_ZERO_RETURN(errctx, (strlen(value) < AKBASIC_MAX_STRING_LENGTH),
|
||||
AKBASIC_ERR_VALUE,
|
||||
"String of %zu characters exceeds the %d character limit",
|
||||
strlen(value), AKBASIC_MAX_STRING_LENGTH - 1);
|
||||
PASS(errctx, akbasic_value_zero(&tmp));
|
||||
tmp.valuetype = AKBASIC_TYPE_STRING;
|
||||
strncpy(tmp.stringval, value, AKBASIC_MAX_STRING_LENGTH - 1);
|
||||
tmp.stringval[AKBASIC_MAX_STRING_LENGTH - 1] = '\0';
|
||||
PASS(errctx, akbasic_variable_set_subscript(obj, &tmp, subscripts, subscriptcount));
|
||||
SUCCEED_RETURN(errctx);
|
||||
}
|
||||
Reference in New Issue
Block a user