ww/test/wcc/687_slice_literal_global.c

/*
 * 687_slice_literal_global — module-level slice-literal static init
 * `let g: []T = [v0, v1, …];` materializes a writable backing + a 24B
 * { ptr, len, cap } header + a DATAR patching ptr -> backing, and cstage
 * / wwstage agree byte-for-byte and at runtime (task #10 part a).
 *
 * The bug: emit_lets / emitletdataw had str-lit + array-lit arms but no
 * slice-lit arm, so a `let g: []u8 = [1u8,2u8,3u8]` emitted NO `DATAW
 * main.g` — BOTH stages failed to link ("undefined reference to main.g").
 * byte-id-blind; only the link step exposed it. (wwstage further needed
 * #18: its checker desugared the module-level initializer to an N_SLICE
 * runtime borrow, so the rhs reached cgen as N_SLICE not N_ARRLIT — fixed
 * first so this arm sees the raw array literal, mirroring cstage.)
 *
 * The fix (BOTH stages, byte-identical): emit_slice_data / emitslicedata
 * route the k element bytes through the emit_array_lit_bytes choke-point
 * (synthesized [k]T), then emit the header (ptr placeholder + LE len + LE
 * cap, all = k) and the ptr-patch DATAR. Backing symbol "<mangled g>.d".
 *
 * Coverage: []u8 (element read-back + len + cap + sum), []i64 (wider
 * element), []i32, and a 1-element edge. Plus dual-stage asm byte-id.
 * Mutation-sanity: the old no-emit fails every row at LINK. Plus negative
 * rows where the slice-literal static init must FAIL the build loudly
 * (rule 7): read-only `def`, `...` repeat, and slice-of-str (per-element
 * relocs / #17 deferred).
 *
 *   row             | shape                                    | want
 *   ----------------+------------------------------------------+------
 *   u8_e0           | let g:[]u8=[1,2,3]; g[0]                  | 1
 *   u8_e2           | g[2]                                      | 3
 *   u8_len          | g.len                                    | 3
 *   u8_cap          | g.cap                                    | 3
 *   u8_sum          | g[0]+g[1]+g[2]+g.len+g.cap                | 12
 *   i64_e1          | let g:[]i64=[10,20,30]; g[1]              | 20
 *   i64_lencap      | g.len+g.cap                               | 6
 *   i32_sum         | let g:[]i32=[7,8,9]; g[0]+g[1]+g[2]       | 24
 *   one_edge        | let g:[]u8=[42]; g[0]+g.len               | 43
 *   struct_pt       | []pt=[pt{1,2},pt{3,4}]; sum+len+cap       | 14
 *   struct_3f       | []q (u8,i64,i32) two elems; sum+len       | 23
 *   struct_one      | []pt=[pt{5,6}]; sum+len+cap (count==1)    | 13
 *   struct_arrvar_l | local let arr:[2]pt; let g:[]pt=arr       | 14
 *
 * #19: wwstage's checker over-rejected the inline NAMED-STRUCT-element
 * array->slice (`let g:[]pt=[pt{..},pt{..}]`) — its N_ARRLIT element-type
 * inference returned the N_STRUCTLIT body (N_TSTRUCT, per #66) and the
 * array->slice isassignable typeeqast saw a TNAME-vs-TSTRUCT kind mismatch
 * against the declared N_TNAME element. cstage already inferred the NAMED
 * type. Fix: infer the named type for a named struct-literal first element
 * (check.ww N_ARRLIT arm); typeeqast untouched.
 */
#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 rows[] = {
	{ "u8_e0",
	  "package main;\n"
	  "let g: []u8 = [1u8, 2u8, 3u8];\n"
	  "export fn main() i32 = { return g[0]: i32; };\n",
	  1 },
	{ "u8_e2",
	  "package main;\n"
	  "let g: []u8 = [1u8, 2u8, 3u8];\n"
	  "export fn main() i32 = { return g[2]: i32; };\n",
	  3 },
	{ "u8_len",
	  "package main;\n"
	  "let g: []u8 = [1u8, 2u8, 3u8];\n"
	  "export fn main() i32 = { return g.len: i32; };\n",
	  3 },
	{ "u8_cap",
	  "package main;\n"
	  "let g: []u8 = [1u8, 2u8, 3u8];\n"
	  "export fn main() i32 = { return g.cap: i32; };\n",
	  3 },
	{ "u8_sum",
	  "package main;\n"
	  "let g: []u8 = [1u8, 2u8, 3u8];\n"
	  "export fn main() i32 = {\n"
	  "\treturn (g[0]:i32)+(g[1]:i32)+(g[2]:i32)+(g.len:i32)+(g.cap:i32);\n"
	  "};\n",
	  12 },
	{ "i64_e1",
	  "package main;\n"
	  "let g: []i64 = [10i64, 20i64, 30i64];\n"
	  "export fn main() i32 = { return g[1]: i32; };\n",
	  20 },
	{ "i64_lencap",
	  "package main;\n"
	  "let g: []i64 = [10i64, 20i64, 30i64];\n"
	  "export fn main() i32 = { return (g.len:i32)+(g.cap:i32); };\n",
	  6 },
	{ "i32_sum",
	  "package main;\n"
	  "let g: []i32 = [7i32, 8i32, 9i32];\n"
	  "export fn main() i32 = { return (g[0]:i32)+(g[1]:i32)+(g[2]:i32); };\n",
	  24 },
	{ "one_edge",
	  "package main;\n"
	  "let g: []u8 = [42u8];\n"
	  "export fn main() i32 = { return (g[0]:i32)+(g.len:i32); };\n",
	  43 },
	/* aliased slice type: `type S = []u8` IS a slice — both stages must
	 * route through emit_slice_data. cstage resolves it via type_unwrap;
	 * wwstage letvarisslice resolves the alias chain (#10). */
	{ "alias_slice",
	  "package main;\n"
	  "type S = []u8;\n"
	  "let g: S = [1u8, 2u8, 3u8];\n"
	  "export fn main() i32 = { return (g[0]:i32)+(g.len:i32)+(g.cap:i32); };\n",
	  7 },
	/* #19: inline NAMED-STRUCT-element array->slice. wwstage's checker
	 * over-rejected this — the N_ARRLIT element-type inference picked up
	 * the N_STRUCTLIT's body (N_TSTRUCT, per #66) and the array->slice
	 * isassignable typeeqast saw a TNAME-vs-TSTRUCT kind mismatch (the
	 * declared element is N_TNAME). Fix infers the NAMED element. cstage
	 * already accepted; emit_array_lit_bytes' struct-field recursion
	 * makes the backing byte-identical. */
	{ "struct_pt",
	  "package main;\n"
	  "type pt = struct { a: i64, b: i64 };\n"
	  "let g: []pt = [pt{a=1i64, b=2i64}, pt{a=3i64, b=4i64}];\n"
	  "export fn main() i32 = {\n"
	  "\treturn (g[0].a:i32)+(g[0].b:i32)+(g[1].a:i32)+(g[1].b:i32)+(g.len:i32)+(g.cap:i32);\n"
	  "};\n",
	  14 },
	/* 3-field mixed-width struct stresses field offsets in the backing
	 * (u8 @0, i64 @8, i32 @16 — non-uniform strides). */
	{ "struct_3f",
	  "package main;\n"
	  "type q = struct { a: u8, b: i64, c: i32 };\n"
	  "let g: []q = [q{a=1u8, b=2i64, c=3i32}, q{a=4u8, b=5i64, c=6i32}];\n"
	  "export fn main() i32 = {\n"
	  "\treturn (g[0].a:i32)+(g[0].b:i32)+(g[0].c:i32)+(g[1].a:i32)+(g[1].b:i32)+(g[1].c:i32)+(g.len:i32);\n"
	  "};\n",
	  23 },
	/* single-element []struct (count==1 backing edge). */
	{ "struct_one",
	  "package main;\n"
	  "type pt = struct { a: i64, b: i64 };\n"
	  "let g: []pt = [pt{a=5i64, b=6i64}];\n"
	  "export fn main() i32 = {\n"
	  "\treturn (g[0].a:i32)+(g[0].b:i32)+(g.len:i32)+(g.cap:i32);\n"
	  "};\n",
	  13 },
	/* regression: the array-VARIABLE form already accepted (arr carries a
	 * clean N_TNAME). Local scope, since the MODULE-scope variable form is
	 * the still-deferred #22 (no backing symbol -> link fail on BOTH
	 * stages). */
	{ "struct_arrvar_local",
	  "package main;\n"
	  "type pt = struct { a: i64, b: i64 };\n"
	  "export fn main() i32 = {\n"
	  "\tlet arr: [2]pt = [pt{a=1i64, b=2i64}, pt{a=3i64, b=4i64}];\n"
	  "\tlet g: []pt = arr;\n"
	  "\treturn (g[0].a:i32)+(g[0].b:i32)+(g[1].a:i32)+(g[1].b:i32)+(g.len:i32)+(g.cap:i32);\n"
	  "};\n",
	  14 },
};

/* slice-literal static init that must FAIL the build loudly (rule 7). */
static const char *neg[] = {
	/* read-only `def` can't carry the ptr reloc (DATAR holder must be
	 * DATAW, w6a asm.c:362). */
	"package main;\n"
	"def g: []u8 = [1u8, 2u8, 3u8];\n"
	"export fn main() i32 = { return g.len: i32; };\n",
	/* `...` repeat has no target length in a slice literal. Uses the
	 * reachable repeat spelling `[v...]` (no comma) so the cgen loud-stop
	 * is exercised — the comma form `[v, ...]` parse-errors first and
	 * would test the parser, not the emit_slice_data guard. */
	"package main;\n"
	"let g: []u8 = [1u8, 2u8...];\n"
	"export fn main() i32 = { return g.len: i32; };\n",
	/* slice-of-str needs per-element relocs (#17) — deferred loud-stop. */
	"package main;\n"
	"let g: []str = [\"a\", \"b\"];\n"
	"export fn main() i32 = { return g.len: i32; };\n",
};

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/slg_%d_%d.ww", getpid(), i);
	snprintf(tmpdir, sizeof tmpdir, "/tmp/slg_%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;
}

/* build_should_fail — returns 0 when the build correctly FAILS. */
static int
build_should_fail(const char *driver, const char *src, int i)
{
	char s[64], tmpdir[64], cmd[1024];
	snprintf(s, sizeof s, "/tmp/slgn_%d_%d.ww", getpid(), i);
	snprintf(tmpdir, sizeof tmpdir, "/tmp/slgn_%d_d_%d", getpid(), i);

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

	mkdir(tmpdir, 0755);
	snprintf(cmd, sizeof cmd, "cd %s && %s build %s 2>/dev/null",
	    tmpdir, driver, s);
	int rc = runwait(cmd);
	unlink(s);
	const char *base = strrchr(s, '/');
	base = base ? base + 1 : s;
	char outbin[128];
	snprintf(outbin, sizeof outbin, "%s/%s", tmpdir, base);
	char *dot = strrchr(outbin, '.');
	if (dot && strcmp(dot, ".ww") == 0) *dot = '\0';
	unlink(outbin);
	rmdir(tmpdir);
	return rc == 0 ? -1 : 0;	/* build must NOT succeed */
}

/* 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/slg_asm_%d_%d.ww", getpid(), i);
	snprintf(cs,  sizeof cs,  "/tmp/slg_asm_%d_%d_c.s", getpid(), i);
	snprintf(ws,  sizeof ws,  "/tmp/slg_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 n = (int)(sizeof rows / sizeof rows[0]);
	int nn = (int)(sizeof neg / sizeof neg[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, "slice_literal_global: skip %s (no %s)\n",
			    drivers[d].name, drivers[d].path);
			continue;
		}
		for (int i = 0; i < n; i++) {
			int got = run_driver(drivers[d].path, &rows[i], i);
			total++;
			if (got != rows[i].want) {
				fprintf(stderr,
				    "slice_literal_global[%s][%s]: exit=%d want=%d\n",
				    drivers[d].name, rows[i].label,
				    got, rows[i].want);
				fail++;
			}
		}
		for (int i = 0; i < nn; i++) {
			total++;
			if (build_should_fail(drivers[d].path, neg[i],
			    100 + i) != 0) {
				fprintf(stderr,
				    "slice_literal_global[%s][neg%d]: built ok, "
				    "expected a loud error\n",
				    drivers[d].name, i);
				fail++;
			}
		}
	}

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

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