ww/test/wcc/827_str_eq.c

/*
 * 827_str_eq — str `==` / `!=` is a CONTENT compare (rt_streq), not a
 * pointer compare. #146 (the ww-twin of the #154 cstage fix).
 *
 * THE BUG (wwstage-only; cstage was already correct via #154): wwstage
 * cgbin (selfhost/cmd/wcc/cgenexpr.ww) had NO str-awareness, so every
 * `==`/`!=` fell to the generic comparison tail — a single `CMPQ BX, AX`
 * on the eager-eval'd registers. For a str, eager-eval collapses the
 * 3-word header to its ptr word, so the compare became ptr-vs-ptr: two
 * DISTINCT-pointer equal-content strings answered FALSE on wwstage while
 * cstage (which CALLs rt_streq) answered TRUE. THE divergence row is
 * eq_dup_true: `let a="abc"; let b=strings.dup("abc"); a==b`.
 *
 * THE FIX: cgbin now has a str ==/!= branch at the top (before the
 * generic eval), mirroring cstage cgen.c cbinop:4564-4623 — push rhs
 * then lhs (len, ptr each), POPQ DI/SI/DX/CX = a.ptr,a.len,b.ptr,b.len
 * (rt/streq.s ABI), CALL rt_streq -> AX in {0,1}, XORQ $1 for !=.
 *
 * Two row sets:
 *   runrows  — built+RUN on BOTH drivers (need strings.dup for a
 *              distinct-pointer copy, so they `import strings` and build
 *              via `ww` which links the lib). These pin RUNTIME
 *              correctness; eq_dup_true/ne_dup_false are mutation-sane
 *              (pre-fix wwstage gave the wrong ptr-compare answer).
 *   asmrows  — import-free single files run straight through w6c /
 *              w6c_ww for the BYTE-ID headline (w6c compiles one file and
 *              can't resolve strings.dup, so the import rows can't be
 *              byte-id'd directly; these import-free str==/!= sources
 *              exercise the identical cgbin branch and pin cs==ww `.s`).
 *
 *   runrows                                          | want
 *   -------------------------------------------------+------
 *   eq_dup_true   a=="abc", b=dup("abc"); a==b       | 1   (THE bug)
 *   ne_dup_false  a=="abc", b=dup("abc"); a!=b       | 0   (!= twin)
 *   diff_content  "abc"=="abd"                        | 0   (control)
 *   eq_self       a="x"; a==a                         | 1   (same ptr)
 *   empty         a="", b=dup(""); a==b               | 1   (len-0 edge)
 */
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/stat.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;
}

struct row { const char *label; const char *src; int want; };

static const struct row runrows[] = {
	/* eq_dup_true — THE regression pin: distinct pointer, equal
	 * content. Pre-fix wwstage ptr-compared -> 0 (WRONG); cstage
	 * CALLs rt_streq -> 1. */
	{ "eq_dup_true",
	  "package main;\n"
	  "import strings;\n"
	  "export fn main() i32 = {\n"
	  "\tlet a: str = \"abc\";\n"
	  "\tlet b: str = strings.dup(\"abc\");\n"
	  "\tif (a == b) { return 1; };\n"
	  "\treturn 0;\n"
	  "};\n",
	  1 },

	/* ne_dup_false — the != twin: distinct pointer, equal content, so
	 * `!=` is FALSE. Pre-fix wwstage ptr-compared -> != true (WRONG). */
	{ "ne_dup_false",
	  "package main;\n"
	  "import strings;\n"
	  "export fn main() i32 = {\n"
	  "\tlet a: str = \"abc\";\n"
	  "\tlet b: str = strings.dup(\"abc\");\n"
	  "\tif (a != b) { return 1; };\n"
	  "\treturn 0;\n"
	  "};\n",
	  0 },

	/* diff_content — distinct content; both stages agree (control). */
	{ "diff_content",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "\tif (\"abc\" == \"abd\") { return 1; };\n"
	  "\treturn 0;\n"
	  "};\n",
	  0 },

	/* eq_self — same pointer, equal content; both stages agree. */
	{ "eq_self",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "\tlet a: str = \"x\";\n"
	  "\tif (a == a) { return 1; };\n"
	  "\treturn 0;\n"
	  "};\n",
	  1 },

	/* empty — len-0 edge: rt_streq must match two empty strings. */
	{ "empty",
	  "package main;\n"
	  "import strings;\n"
	  "export fn main() i32 = {\n"
	  "\tlet a: str = \"\";\n"
	  "\tlet b: str = strings.dup(\"\");\n"
	  "\tif (a == b) { return 1; };\n"
	  "\treturn 0;\n"
	  "};\n",
	  1 },
};

/* Import-free sources for the byte-id pass (w6c compiles a single file
 * and can't resolve cross-module strings.dup). Each exercises the cgbin
 * str ==/!= branch; the `.s` must be identical cstage vs wwstage. */
static const struct row asmrows[] = {
	/* be_eq_local — local str == local str (ident operand load). */
	{ "be_eq_local",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "\tlet a: str = \"abc\";\n"
	  "\tlet b: str = \"abd\";\n"
	  "\tif (a == b) { return 1; };\n"
	  "\treturn 0;\n"
	  "};\n",
	  0 },

	/* be_ne_local — the != twin (pins the XORQ $1, AX). */
	{ "be_ne_local",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "\tlet a: str = \"abc\";\n"
	  "\tlet b: str = \"abd\";\n"
	  "\tif (a != b) { return 1; };\n"
	  "\treturn 0;\n"
	  "};\n",
	  1 },

	/* be_eq_strlit — strlit == strlit (non-ident cgexpr operand). */
	{ "be_eq_strlit",
	  "package main;\n"
	  "export fn main() i32 = {\n"
	  "\tif (\"abc\" == \"abc\") { return 1; };\n"
	  "\treturn 0;\n"
	  "};\n",
	  1 },

	/* be_eq_global — module-GLOBAL str == global str. This is the
	 * raison d'etre of the typeisstr gate (vs the spec's nodeisstr,
	 * whose N_IDENT arm keys on localfindnode and returns false for a
	 * global, leaving a latent cs!=ww hole). The cgstreqpush global arm
	 * (LEAQ name(SB)) must byte-match cstage's #154 let_islet branch. */
	{ "be_eq_global",
	  "package main;\n"
	  "let g: str = \"abc\";\n"
	  "let h: str = \"abd\";\n"
	  "export fn main() i32 = {\n"
	  "\tif (g == h) { return 1; };\n"
	  "\treturn 0;\n"
	  "};\n",
	  0 },
};

static int
run_driver(const char *driver, const struct row *r, int i)
{
	char src[64], tmpdir[64], cmd[1024];
	snprintf(src, sizeof src, "/tmp/seq_%d_%d.ww", getpid(), i);
	snprintf(tmpdir, sizeof tmpdir, "/tmp/seq_%d_d_%d", getpid(), i);

	FILE *f = fopen(src, "wb");
	if (!f) return -1;
	fputs(r->src, f);
	fclose(f);

	mkdir(tmpdir, 0755);
	snprintf(cmd, sizeof cmd, "cd %s && %s build %s 2>/dev/null",
	    tmpdir, driver, src);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "row[%s]: build via %s failed\n",
		    r->label, driver);
		unlink(src); rmdir(tmpdir);
		return -1;
	}

	const char *base = strrchr(src, '/');
	base = base ? base + 1 : src;
	char outbin[128];
	snprintf(outbin, sizeof outbin, "%s/%s", tmpdir, base);
	char *dot = strrchr(outbin, '.');
	if (dot && strcmp(dot, ".ww") == 0) *dot = '\0';
	int got = runwait(outbin);

	unlink(src); unlink(outbin); rmdir(tmpdir);
	return got;
}

/* asm_byte_identical — w6c vs w6c_ww .s for the same source must match. */
static int
asm_byte_identical(const char *bin, const struct row *r, int i)
{
	char src[64], cs[64], ws[64], cmd[1024];
	snprintf(src, sizeof src, "/tmp/seq_asm_%d_%d.ww", getpid(), i);
	snprintf(cs,  sizeof cs,  "/tmp/seq_asm_%d_%d_c.s", getpid(), i);
	snprintf(ws,  sizeof ws,  "/tmp/seq_asm_%d_%d_w.s", getpid(), i);

	FILE *f = fopen(src, "wb");
	if (!f) return -1;
	fputs(r->src, f);
	fclose(f);

	snprintf(cmd, sizeof cmd, "%s/w6c -o %s %s 2>/dev/null", bin, cs, src);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "row[%s]: w6c errored\n", r->label);
		unlink(src);
		return -1;
	}
	snprintf(cmd, sizeof cmd, "%s/w6c_ww -o %s %s 2>/dev/null",
	    bin, ws, src);
	if (runwait(cmd) != 0) {
		fprintf(stderr, "row[%s]: w6c_ww errored\n", r->label);
		unlink(src); unlink(cs);
		return -1;
	}

	FILE *fc = fopen(cs, "rb");
	FILE *fw = fopen(ws, "rb");
	int rc = 0;
	if (!fc || !fw) {
		rc = -1;
	} else {
		for (;;) {
			int a = fgetc(fc);
			int b = fgetc(fw);
			if (a != b) { rc = -1; break; }
			if (a == EOF) break;
		}
	}
	if (fc) fclose(fc);
	if (fw) fclose(fw);
	if (rc != 0)
		fprintf(stderr, "row[%s]: cstage vs wwstage asm differs\n",
		    r->label);
	unlink(src); unlink(cs); unlink(ws);
	return rc;
}

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 cdrv[1024];
	snprintf(cdrv, sizeof cdrv, "%s/ww", bin);
	char wdrv[1024];
	snprintf(wdrv, sizeof wdrv, "%s/ww_ww", bin);

	struct { const char *name; const char *path; int gated_on_existence; }
	drivers[] = {
		{ "cstage",  cdrv, 0 },
		{ "wwstage", wdrv, 1 },
		{ NULL, NULL, 0 },
	};

	int nrun = (int)(sizeof runrows / sizeof runrows[0]);
	int nasm = (int)(sizeof asmrows / sizeof asmrows[0]);
	int total = 0, fail = 0;

	for (int d = 0; drivers[d].name; d++) {
		if (drivers[d].gated_on_existence
		    && access(drivers[d].path, X_OK) != 0) {
			fprintf(stderr, "str_eq: skip %s (no %s)\n",
			    drivers[d].name, drivers[d].path);
			continue;
		}
		for (int i = 0; i < nrun; i++) {
			int got = run_driver(drivers[d].path, &runrows[i], i);
			total++;
			if (got != runrows[i].want) {
				fprintf(stderr,
				    "str_eq[%s][%s]: exit=%d want=%d\n",
				    drivers[d].name, runrows[i].label,
				    got, runrows[i].want);
				fail++;
			}
		}
	}

	if (access(wdrv, X_OK) == 0) {
		for (int i = 0; i < nasm; i++) {
			total++;
			if (asm_byte_identical(bin, &asmrows[i], i) != 0)
				fail++;
		}
	}

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