ww/test/wcc/530_w6a_parsenum.c

/*
 * 530_w6a_parsenum — F14 #62: w6a's parsenum diverged from the C twin's
 * strtoll(s,end,0) (cmd/w6a/lex.c:30) on three hand-written-asm edge
 * shapes, all gate-blind (w6c emits the canonical $5 / $8 / -8(BP), never
 * these). The fix aligns wwstage's assembler to strtoll semantics:
 *   (a) `$ 5`  — leading whitespace after $: strtoll skips it (→5); ww
 *               had no skip and silently encoded imm 0.
 *   (b) `$08`  — strtoll base-0 reads a leading 0 as octal and STOPS at
 *               '8' (→0); ww parsed it as decimal 8.
 *   (c) `-(BP)` — strtoll/cstage require a digit after the sign, so a bare
 *               `-(` is `unrecognised operand` (loud reject); ww silently
 *               accepted it as 0(BP).
 *
 * (a)/(b): both assemblers must emit a byte-identical .o.
 * (c): both assemblers must FAIL (loud reject).
 * Controls: the canonical $5 / $8 / -8(BP) shapes that w6c DOES emit must
 * stay byte-identical (no regression).
 *
 * Drives w6a (cstage) and w6a_ww (wwstage) directly; gated on w6a_ww.
 */
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <sys/wait.h>

static int
runwait(const char *cmd)
{
	int rc = system(cmd);
	if (rc == -1) return -1;
	if (WIFEXITED(rc)) return WEXITSTATUS(rc);
	return -1;
}

/* assemble `asm` with `tool` into `obj`; returns the build rc. */
static int
assemble(const char *tool, const char *asmtext, const char *obj, int i)
{
	char src[64], cmd[1024];
	snprintf(src, sizeof src, "/tmp/w6apn_%d_%d.s", getpid(), i);
	FILE *f = fopen(src, "wb");
	if (!f) return -2;
	fputs(asmtext, f);
	fclose(f);
	snprintf(cmd, sizeof cmd, "%s -o %s %s 2>/dev/null", tool, obj, src);
	int rc = runwait(cmd);
	unlink(src);
	return rc;
}

static int
files_equal(const char *a, const char *b)
{
	FILE *fa = fopen(a, "rb");
	FILE *fb = fopen(b, "rb");
	int eq = (fa && fb);
	if (fa && fb) {
		for (;;) {
			int ca = fgetc(fa), cb = fgetc(fb);
			if (ca != cb) { eq = 0; break; }
			if (ca == EOF) break;
		}
	}
	if (fa) fclose(fa);
	if (fb) fclose(fb);
	return eq;
}

struct idrow { const char *label; const char *asmtext; };

/* shapes that must assemble byte-identically across the two assemblers. */
static const struct idrow idrows[] = {
	{ "ws_after_dollar",  "TEXT main,$16\n\tMOVQ\t$ 5, AX\n\tRET\n" },
	{ "leading_zero",     "TEXT main,$16\n\tMOVQ\t$08, AX\n\tRET\n" },
	/* controls — the canonical shapes w6c actually emits. */
	{ "plain_imm",        "TEXT main,$16\n\tMOVQ\t$5, AX\n\tRET\n" },
	{ "plain_imm_eight",  "TEXT main,$16\n\tMOVQ\t$8, AX\n\tRET\n" },
	{ "hex_imm",          "TEXT main,$16\n\tMOVQ\t$0x1f, AX\n\tRET\n" },
	{ "zero_imm",         "TEXT main,$16\n\tMOVQ\t$0, AX\n\tRET\n" },
	{ "neg_indir",        "TEXT main,$16\n\tMOVQ\t-8(BP), AX\n\tRET\n" },
	{ "pos_indir",        "TEXT main,$16\n\tMOVQ\t8(BP), AX\n\tRET\n" },
};

/* shapes both assemblers must reject. */
static const struct idrow rejrows[] = {
	{ "bare_minus_indir", "TEXT main,$16\n\tMOVQ\t-(BP), AX\n\tRET\n" },
};

int
main(void)
{
	const char *bin = getenv("BIN");
	if (!bin) bin = "out/bin";
	char absbin[1024];
	if (bin[0] != '/') {
		char cwd[1024];
		if (getcwd(cwd, sizeof cwd) == NULL) return 1;
		snprintf(absbin, sizeof absbin, "%s/%s", cwd, bin);
		bin = absbin;
	}

	char ctool[1024], wtool[1024];
	snprintf(ctool, sizeof ctool, "%s/w6a", bin);
	snprintf(wtool, sizeof wtool, "%s/w6a_ww", bin);

	if (access(wtool, X_OK) != 0) {
		fprintf(stderr, "w6a_parsenum: skip (no %s)\n", wtool);
		printf("w6a_parsenum: skipped\n");
		return 0;
	}

	int nid = (int)(sizeof idrows / sizeof idrows[0]);
	int nrej = (int)(sizeof rejrows / sizeof rejrows[0]);
	int fail = 0;

	for (int i = 0; i < nid; i++) {
		char co[64], wo[64];
		snprintf(co, sizeof co, "/tmp/w6apn_%d_%d_c.o", getpid(), i);
		snprintf(wo, sizeof wo, "/tmp/w6apn_%d_%d_w.o", getpid(), i);
		int cr = assemble(ctool, idrows[i].asmtext, co, i);
		int wr = assemble(wtool, idrows[i].asmtext, wo, 1000 + i);
		if (cr != 0 || wr != 0) {
			fprintf(stderr, "w6a_parsenum[%s]: assemble failed "
			    "(c=%d w=%d)\n", idrows[i].label, cr, wr);
			fail++;
		} else if (!files_equal(co, wo)) {
			fprintf(stderr, "w6a_parsenum[%s]: .o differ across "
			    "assemblers\n", idrows[i].label);
			fail++;
		}
		unlink(co); unlink(wo);
	}

	for (int i = 0; i < nrej; i++) {
		char co[64], wo[64];
		snprintf(co, sizeof co, "/tmp/w6apn_%d_r%d_c.o", getpid(), i);
		snprintf(wo, sizeof wo, "/tmp/w6apn_%d_r%d_w.o", getpid(), i);
		int cr = assemble(ctool, rejrows[i].asmtext, co, 2000 + i);
		int wr = assemble(wtool, rejrows[i].asmtext, wo, 3000 + i);
		if (cr == 0) {
			fprintf(stderr, "w6a_parsenum[%s]: cstage accepted, "
			    "expected reject\n", rejrows[i].label);
			fail++;
		}
		if (wr == 0) {
			fprintf(stderr, "w6a_parsenum[%s]: wwstage accepted, "
			    "expected reject\n", rejrows[i].label);
			fail++;
		}
		unlink(co); unlink(wo);
	}

	if (fail) {
		fprintf(stderr, "w6a_parsenum: %d fixtures failed\n", fail);
		return 1;
	}
	printf("w6a_parsenum: %d/%d ok\n", nid + nrej, nid + nrej);
	return 0;
}