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 parser_commands.c
|
|
|
|
|
* @brief Tests the verbs that carry their own parse path.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#include "harness.h"
|
|
|
|
|
|
|
|
|
|
static void expect_command(const char *line, akbasic_LeafType wanttype, const char *wantname)
|
|
|
|
|
{
|
|
|
|
|
akbasic_ASTLeaf *leaf = NULL;
|
|
|
|
|
akerr_ErrorContext *e = NULL;
|
|
|
|
|
|
|
|
|
|
e = harness_parse(line, &leaf);
|
|
|
|
|
if ( e != NULL ) {
|
|
|
|
|
fprintf(stderr, "FAIL: \"%s\" did not parse: %s\n", line, e->message);
|
|
|
|
|
akbasic_test_failures += 1;
|
|
|
|
|
test_discard_error(e);
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
TEST_REQUIRE(leaf != NULL, "\"%s\" produced no leaf", line);
|
|
|
|
|
if ( leaf == NULL ) {
|
|
|
|
|
return;
|
|
|
|
|
}
|
|
|
|
|
TEST_REQUIRE_INT(leaf->leaftype, wanttype);
|
|
|
|
|
if ( wantname != NULL ) {
|
|
|
|
|
TEST_REQUIRE_STR(leaf->identifier, wantname);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void expect_parse_error(const char *line)
|
|
|
|
|
{
|
|
|
|
|
akbasic_ASTLeaf *leaf = NULL;
|
|
|
|
|
akerr_ErrorContext *e = NULL;
|
|
|
|
|
|
|
|
|
|
e = harness_parse(line, &leaf);
|
|
|
|
|
TEST_REQUIRE(e != NULL, "\"%s\" should not have parsed", line);
|
|
|
|
|
if ( e != NULL ) {
|
|
|
|
|
test_discard_error(e);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2026-07-31 11:46:10 -04:00
|
|
|
/**
|
|
|
|
|
* @brief Parse a whole line and report how many statements came out of it.
|
|
|
|
|
*
|
|
|
|
|
* The statement loop the runtime uses, in miniature: parse until the token
|
|
|
|
|
* stream is spent, skipping the NULL leaf that an empty statement produces.
|
|
|
|
|
*/
|
|
|
|
|
static int count_statements(const char *line)
|
|
|
|
|
{
|
|
|
|
|
akbasic_Parser parser;
|
|
|
|
|
akbasic_ASTLeaf *leaf = NULL;
|
|
|
|
|
akerr_ErrorContext *e = NULL;
|
|
|
|
|
int count = 0;
|
|
|
|
|
|
|
|
|
|
e = akbasic_scanner_zero(&HARNESS_RUNTIME);
|
|
|
|
|
if ( e == NULL ) {
|
|
|
|
|
e = akbasic_scanner_scan(&HARNESS_RUNTIME, line, NULL, 0);
|
|
|
|
|
}
|
|
|
|
|
if ( e == NULL ) {
|
|
|
|
|
e = akbasic_parser_init(&parser, &HARNESS_RUNTIME);
|
|
|
|
|
}
|
|
|
|
|
while ( e == NULL && !akbasic_parser_is_at_end(&parser) ) {
|
|
|
|
|
leaf = NULL;
|
|
|
|
|
e = akbasic_parser_parse(&parser, &leaf);
|
|
|
|
|
if ( e == NULL && leaf != NULL ) {
|
|
|
|
|
count += 1;
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
if ( e != NULL ) {
|
|
|
|
|
fprintf(stderr, "FAIL: \"%s\" did not parse: %s\n", line, e->message);
|
|
|
|
|
akbasic_test_failures += 1;
|
|
|
|
|
test_discard_error(e);
|
|
|
|
|
return -1;
|
|
|
|
|
}
|
|
|
|
|
return count;
|
|
|
|
|
}
|
|
|
|
|
|
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
|
|
|
int main(void)
|
|
|
|
|
{
|
|
|
|
|
akbasic_ASTLeaf *leaf = NULL;
|
|
|
|
|
|
|
|
|
|
TEST_REQUIRE_OK(harness_start(NULL));
|
|
|
|
|
|
|
|
|
|
/* Plain verbs with an expression rval. */
|
|
|
|
|
expect_command("PRINT 1", AKBASIC_LEAF_COMMAND, "PRINT");
|
|
|
|
|
expect_command("GOTO 100", AKBASIC_LEAF_COMMAND, "GOTO");
|
|
|
|
|
expect_command("GOSUB 100", AKBASIC_LEAF_COMMAND, "GOSUB");
|
|
|
|
|
|
|
|
|
|
/* A verb with no rval at all must not fail. */
|
|
|
|
|
expect_command("RETURN", AKBASIC_LEAF_COMMAND, "RETURN");
|
|
|
|
|
expect_command("STOP", AKBASIC_LEAF_COMMAND, "STOP");
|
|
|
|
|
|
|
|
|
|
/* Immediate commands get their own leaf type. */
|
|
|
|
|
expect_command("QUIT", AKBASIC_LEAF_COMMAND_IMMEDIATE, "QUIT");
|
|
|
|
|
expect_command("LIST", AKBASIC_LEAF_COMMAND_IMMEDIATE, "LIST");
|
|
|
|
|
expect_command("RUN", AKBASIC_LEAF_COMMAND_IMMEDIATE, "RUN");
|
|
|
|
|
|
|
|
|
|
/* Verbs with their own parse path. */
|
|
|
|
|
expect_command("LABEL LOOPTOP", AKBASIC_LEAF_COMMAND, "LABEL");
|
|
|
|
|
expect_command("DIM A#(5)", AKBASIC_LEAF_COMMAND, "DIM");
|
|
|
|
|
expect_command("DATA 1, 2, 3", AKBASIC_LEAF_COMMAND, "DATA");
|
|
|
|
|
expect_command("READ A#, B#", AKBASIC_LEAF_COMMAND, "READ");
|
|
|
|
|
expect_command("POKE 100, 1", AKBASIC_LEAF_COMMAND, "POKE");
|
|
|
|
|
expect_command("INPUT \"NAME? \" A$", AKBASIC_LEAF_COMMAND, "INPUT");
|
|
|
|
|
|
|
|
|
|
/* LET parses as a bare assignment. */
|
|
|
|
|
expect_command("LET A# = 1", AKBASIC_LEAF_BINARY, NULL);
|
|
|
|
|
|
|
|
|
|
/* IF produces a BRANCH, not a COMMAND. */
|
|
|
|
|
expect_command("IF 1 == 1 THEN PRINT 1", AKBASIC_LEAF_BRANCH, NULL);
|
|
|
|
|
TEST_REQUIRE_OK(harness_parse("IF 1 == 1 THEN PRINT 1 ELSE PRINT 2", &leaf));
|
|
|
|
|
TEST_REQUIRE(leaf != NULL && leaf->left != NULL && leaf->right != NULL,
|
|
|
|
|
"IF ... THEN ... ELSE must fill both branches");
|
|
|
|
|
|
|
|
|
|
/* FOR installs a loop environment and returns the assignment. */
|
|
|
|
|
{
|
|
|
|
|
akbasic_Environment *before = HARNESS_RUNTIME.environment;
|
|
|
|
|
TEST_REQUIRE_OK(harness_parse("FOR I# = 1 TO 5", &leaf));
|
|
|
|
|
TEST_REQUIRE(HARNESS_RUNTIME.environment != before,
|
|
|
|
|
"FOR must install a new environment");
|
|
|
|
|
TEST_REQUIRE(HARNESS_RUNTIME.environment->forToLeaf != NULL,
|
|
|
|
|
"FOR must record its TO expression");
|
|
|
|
|
TEST_REQUIRE(HARNESS_RUNTIME.environment->forStepLeaf != NULL,
|
|
|
|
|
"FOR must default its STEP to 1");
|
|
|
|
|
TEST_REQUIRE_OK(akbasic_runtime_prev_environment(&HARNESS_RUNTIME));
|
|
|
|
|
}
|
|
|
|
|
{
|
|
|
|
|
akbasic_Environment *before = HARNESS_RUNTIME.environment;
|
|
|
|
|
TEST_REQUIRE_OK(harness_parse("FOR I# = 1 TO 10 STEP 2", &leaf));
|
|
|
|
|
TEST_REQUIRE(HARNESS_RUNTIME.environment != before, "FOR STEP must install an environment");
|
|
|
|
|
TEST_REQUIRE_OK(akbasic_runtime_prev_environment(&HARNESS_RUNTIME));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
/* Malformed FOR is rejected at parse time. */
|
|
|
|
|
expect_parse_error("FOR I# = 1");
|
|
|
|
|
expect_parse_error("FOR I# = 1 TO 5 STEP");
|
|
|
|
|
expect_parse_error("FOR 1 TO 5");
|
|
|
|
|
|
|
|
|
|
/* Other malformed forms. */
|
|
|
|
|
expect_parse_error("IF 1 == 1 PRINT 1");
|
|
|
|
|
expect_parse_error("LABEL 5");
|
|
|
|
|
expect_parse_error("READ 1");
|
|
|
|
|
expect_parse_error("DATA A#");
|
|
|
|
|
|
2026-07-31 11:46:10 -04:00
|
|
|
/*
|
|
|
|
|
* Colons separate statements. The token has existed since the scanner was
|
|
|
|
|
* written and nothing consumed it, so every one of these was a parse error
|
|
|
|
|
* until the statement loop learned to skip past it -- TODO.md section 4.
|
|
|
|
|
*/
|
|
|
|
|
TEST_REQUIRE_INT(count_statements("PRINT 1"), 1);
|
|
|
|
|
TEST_REQUIRE_INT(count_statements("PRINT 1 : PRINT 2"), 2);
|
|
|
|
|
TEST_REQUIRE_INT(count_statements("A# = 1 : B# = 2 : PRINT A# + B#"), 3);
|
|
|
|
|
|
|
|
|
|
/* An empty statement is not an error, and does not count as one. */
|
|
|
|
|
TEST_REQUIRE_INT(count_statements("PRINT 1 :"), 1);
|
|
|
|
|
TEST_REQUIRE_INT(count_statements(": PRINT 1"), 1);
|
|
|
|
|
TEST_REQUIRE_INT(count_statements("PRINT 1 :: PRINT 2"), 2);
|
|
|
|
|
TEST_REQUIRE_INT(count_statements(":"), 0);
|
|
|
|
|
TEST_REQUIRE_INT(count_statements(":::"), 0);
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* A verb that takes no rval stops at the separator rather than trying to
|
|
|
|
|
* parse one out of it.
|
|
|
|
|
*/
|
|
|
|
|
TEST_REQUIRE_INT(count_statements("PRINT : PRINT 2"), 2);
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* IF takes exactly one statement for each arm; the rest of the line arrives
|
|
|
|
|
* at the statement loop as ordinary statements, and it is the *runtime* that
|
|
|
|
|
* decides whether to run them. That split is asserted end to end in
|
|
|
|
|
* tests/language/statements/multiple_per_line.bas, because it is a question
|
|
|
|
|
* about execution rather than about the shape of the tree.
|
|
|
|
|
*/
|
|
|
|
|
TEST_REQUIRE_INT(count_statements("IF 1 == 1 THEN PRINT 1 : PRINT 2"), 2);
|
|
|
|
|
TEST_REQUIRE_INT(count_statements("IF 1 == 1 THEN PRINT 1 ELSE PRINT 2 : PRINT 3"), 2);
|
|
|
|
|
|
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
|
|
|
harness_stop();
|
|
|
|
|
return akbasic_test_failures;
|
|
|
|
|
}
|