Consume the COLON token: a line can hold several statements

The token has existed since the scanner was written and nothing read it, so
10 PRINT A$ : REM ... was a parse error. Leading separators are consumed
before each statement and an empty statement yields a NULL leaf rather than
an error, so a trailing colon and a run of them are both legal.

BASIC 7.0 scopes everything after THEN to the condition, which the reference
had no opinion about because it never got here. The rule is not "skip when
false": the rest of the line belongs to whichever arm was written last.

A whole FOR/NEXT on one line still does not loop -- block skipping works by
source line. Recorded in TODO.md as what group A has to fix first.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-07-31 11:46:10 -04:00
parent 0f3d8a0ac6
commit a31058cf37
8 changed files with 256 additions and 18 deletions

View File

@@ -39,6 +39,42 @@ static void expect_parse_error(const char *line)
}
}
/**
* @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;
}
int main(void)
{
akbasic_ASTLeaf *leaf = NULL;
@@ -106,6 +142,38 @@ int main(void)
expect_parse_error("READ 1");
expect_parse_error("DATA A#");
/*
* 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);
harness_stop();
return akbasic_test_failures;
}