w6c: emit length for string-literal .len (fix #14, align cstage to wwstage)

A string literal is TY_UNTYPED_STR, not TY_STR, so `"abc".len` missed the typed slice/str pseudo-field gate in cgen.c's N_DOT and fell to the final base-eval fallback, which left AX=.ptr — `.len` returned the pointer instead of the length. wwstage's cgdot catch-all already did the BX->AX shuffle, so the two stages diverged (rule-10). Align cstage UP: the N_DOT fallback emits MOVQ BX,AX for `.len`. `.ptr` is unchanged (already returned AX); `.cap` deliberately not added (wwstage catch-all is ptr/len only — mirror exactly). byte-id was blind here: no bootstrap source uses literal `.len` (lengths are hardcoded around literals), so the gate never exercised it. New test 801 pins both dimensions (cstage run + cs==ww byte-id) over len/empty/multibyte/ptr-deref/arg-passthrough rows.
2026-06-03 00:28:16 +09:00
parent dbb52e25fe
commit 711762b6d8
6 changed files with 218 additions and 13 deletions
--- a/10
+++ b/10
@@ -369,6 +369,7 @@ TESTS	= $(BIN)/test_smoke $(BIN)/test_lex $(BIN)/test_parse $(BIN)/test_check \
 	  $(BIN)/test_xmod_valglobal_run \
 	  $(BIN)/test_xmod_valglobal_dot_run \
 	  $(BIN)/test_len_strglobal_run \
+	  $(BIN)/test_litstr_pseudo_run \
 	  $(BIN)/test_tuple_sret_callee \
 	  $(BIN)/test_tuple_sret_receive_run \
 	  $(BIN)/test_struct_tuple_field_slot \
@@ -875,6 +876,15 @@ $(BIN)/test_len_strglobal_run: test/wcc/797_len_strglobal_run.c \
 		$(LIB)/libwwrt.a | $(BIN)
 	$(CC) $(CFLAGS) -o $@ $<

+# #14: a string LITERAL `.len` is TY_UNTYPED_STR, so it misses the typed
+# slice/str pseudo-field gate and fell to the N_DOT base-eval fallback —
+# cstage returned AX=.ptr instead of shuffling BX=.len into AX (wwstage
+# already did). Runtime + cs==ww byte-id; `.ptr` unchanged (control row).
+$(BIN)/test_litstr_pseudo_run: test/wcc/801_litstr_pseudo_run.c \
+		$(BIN)/ww $(BIN)/w6c $(BIN)/w6c_ww $(BIN)/w6a $(BIN)/w6l \
+		$(LIB)/libwwrt.a | $(BIN)
+	$(CC) $(CFLAGS) -o $@ $<
+
 # #10 Fold A (wide tuple-return / sret, CALLEE side): an over-cap tuple
 # return (> 4 GP or > 2 SSE eightbytes) now compiles via sret instead of
 # loud-stopping at the SEND. Compile + cs==ww byte-id only — the receive
--- a/cmd/w6c/cgen.c
+++ b/cmd/w6c/cgen.c
@@ -8433,8 +8433,15 @@ cgexpr(Cg *c, Node *n, Local *locals)
 			ins2(c, A_MOVQ, masym(c, n->str), areg(D_AX));
 			break;
 		}
-		/* fall through to base evaluation; result placeholder */
+		/* Non-ident / untyped-str base pseudo-field: e.g. `"abc".len`
+		 * / `"abc".ptr`. A string literal is TY_UNTYPED_STR, not
+		 * TY_STR, so it misses the typed slice/str gate above and
+		 * lands here. cgexpr leaves (AX=ptr, BX=len); `.ptr` keeps AX,
+		 * `.len` shuffles BX→AX. Mirrors wwstage cgdot's catch-all
+		 * (selfhost/cmd/wcc/cgenexpr.ww). #14. */
 		cgexpr(c, n->lhs, locals);
+		if (lenfld)
+			ins2(c, A_MOVQ, areg(D_BX), areg(D_AX));
 	dot_done:
 		break;
 	}
--- a/selfhost/cmd/w6c/main.combined.ww
+++ b/selfhost/cmd/w6c/main.combined.ww
@@ -22616,10 +22616,11 @@ fn cgdot(c: *cgen, n: *node) void = {
 		};
 	};
 	// Non-ident base pseudo-field: e.g. `"abc".ptr` / `"abc".len`.
-	// Evaluate the str-producing expression — that leaves
-	// (AX=ptr, BX=len). Then `.ptr` returns AX as is; `.len`
-	// shuffles BX→AX. Mirrors what C cgen does (it just evaluates
-	// the literal and picks the half it wants).
+	// A string literal is TY_UNTYPED_STR, so it misses the typed
+	// slice/str gate above and lands here. Evaluate the str-producing
+	// expression — that leaves (AX=ptr, BX=len). Then `.ptr` returns
+	// AX as is; `.len` shuffles BX→AX. cstage cgen.c was aligned UP
+	// to this shuffle in #14 (it had returned the ptr for `.len`).
 	if (streq(fld, "ptr")) { cgexpr(c, lhs); return; };
 	if (streq(fld, "len")) {
 		cgexpr(c, lhs);
--- a/selfhost/cmd/wcc/cgenexpr.ww
+++ b/selfhost/cmd/wcc/cgenexpr.ww
@@ -2880,10 +2880,11 @@ fn cgdot(c: *cgen, n: *node) void = {
 		};
 	};
 	// Non-ident base pseudo-field: e.g. `"abc".ptr` / `"abc".len`.
-	// Evaluate the str-producing expression — that leaves
-	// (AX=ptr, BX=len). Then `.ptr` returns AX as is; `.len`
-	// shuffles BX→AX. Mirrors what C cgen does (it just evaluates
-	// the literal and picks the half it wants).
+	// A string literal is TY_UNTYPED_STR, so it misses the typed
+	// slice/str gate above and lands here. Evaluate the str-producing
+	// expression — that leaves (AX=ptr, BX=len). Then `.ptr` returns
+	// AX as is; `.len` shuffles BX→AX. cstage cgen.c was aligned UP
+	// to this shuffle in #14 (it had returned the ptr for `.len`).
 	if (streq(fld, "ptr")) { cgexpr(c, lhs); return; };
 	if (streq(fld, "len")) {
 		cgexpr(c, lhs);
--- a/selfhost/cmd/wwdump/main.combined.ww
+++ b/selfhost/cmd/wwdump/main.combined.ww
@@ -22616,10 +22616,11 @@ fn cgdot(c: *cgen, n: *node) void = {
 		};
 	};
 	// Non-ident base pseudo-field: e.g. `"abc".ptr` / `"abc".len`.
-	// Evaluate the str-producing expression — that leaves
-	// (AX=ptr, BX=len). Then `.ptr` returns AX as is; `.len`
-	// shuffles BX→AX. Mirrors what C cgen does (it just evaluates
-	// the literal and picks the half it wants).
+	// A string literal is TY_UNTYPED_STR, so it misses the typed
+	// slice/str gate above and lands here. Evaluate the str-producing
+	// expression — that leaves (AX=ptr, BX=len). Then `.ptr` returns
+	// AX as is; `.len` shuffles BX→AX. cstage cgen.c was aligned UP
+	// to this shuffle in #14 (it had returned the ptr for `.len`).
 	if (streq(fld, "ptr")) { cgexpr(c, lhs); return; };
 	if (streq(fld, "len")) {
 		cgexpr(c, lhs);
--- a/test/wcc/801_litstr_pseudo_run.c
+++ b/test/wcc/801_litstr_pseudo_run.c
@@ -0,0 +1,185 @@
+/*
+ * 801_litstr_pseudo_run — BUG #14. Runtime + cs==ww byte-id net for the
+ * string-LITERAL `.len` / `.ptr` pseudo-field.
+ *
+ * THE BUG (cstage wrong, wwstage correct — rule-10 divergence):
+ *   `"hi".len` returned the POINTER, not the length. A string literal is
+ *   TY_UNTYPED_STR (not TY_STR), so it missed the typed slice/str
+ *   pseudo-field gate in cgen.c's N_DOT and fell to the final fallback
+ *   `cgexpr(lhs)`, which leaves AX=.ptr — `.len` then returned AX (the
+ *   ptr) instead of shuffling BX (the len) into AX. wwstage's cgdot
+ *   catch-all (cgenexpr.ww) already did the BX->AX shuffle, so the two
+ *   stages DISAGREED. byte-id was BLIND: no bootstrap source uses
+ *   literal `.len` (devs hardcoded the lengths around it, e.g.
+ *   `os.write(2, "...".ptr, 9u64)`), so the gate never exercised it.
+ *   The str-VARIABLE `.len` path was correct on both (control).
+ *
+ * THE FIX (#14): align cstage UP to wwstage — the final N_DOT fallback
+ * emits `MOVQ BX, AX` for `.len` (cgen.c). `.ptr` already returned AX
+ * (correct) and is unchanged.
+ *
+ * EACH ROW CARRIES BOTH DIMENSIONS (795/796/797 model):
+ *   (a) cstage `ww build` + run, asserting the exit — pins the converged
+ *       asm is runtime-correct (literal lengths reach the program).
+ *   (b) w6c vs w6c_ww `.s` cmp — FAILS if the stages diverge (they did,
+ *       pre-fix: cstage emitted the ptr, wwstage the len).
+ *
+ * GATE POLARITY: must stay GREEN. A wrong exit means literal `.len`/`.ptr`
+ * regressed; a byte-id FAIL means the stages diverged (rule-10).
+ */
+#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_exit; };
+
+static const struct row rows[] = {
+	/* literal .len: "hello".len == 5. Pre-fix cstage returned the ptr. */
+	{ "lit_len",
+	  "package main;\n"
+	  "export fn main() i32 = { return \"hello\".len: i32; };\n", 5 },
+	/* empty + multi-byte: ""/"héllo\\n" — é is 2 UTF-8 bytes, so the
+	 * literal is 7 bytes (h,é=2,l,l,o,\\n). Guards against a .ptr/.len
+	 * length confusion (a ptr would not be 7). */
+	{ "lit_len_empty_multibyte",
+	  "package main;\n"
+	  "export fn main() i32 = { if (\"\".len != 0) { return 9; }; "
+	  "return \"héllo\\n\".len: i32; };\n", 7 },
+	/* literal .ptr still points at the bytes (deref first byte == 'h'),
+	 * then .len == 5 — proves the fix left .ptr untouched. */
+	{ "lit_ptr_deref",
+	  "package main;\n"
+	  "export fn main() i32 = { let p: *u8 = \"hello\".ptr; "
+	  "if (*p != 'h') { return 1; }; return \"hello\".len: i32; };\n", 5 },
+	/* callee-side .len on a literal passed as a str arg — the real-world
+	 * shape (os.write(1, lit.ptr, lit.len)) that surfaced #14. */
+	{ "lit_arg_passthrough",
+	  "package main;\n"
+	  "fn slen(s: str) i32 = { return s.len: i32; };\n"
+	  "export fn main() i32 = { if (slen(\"abcdef\") != 6) { return 1; }; "
+	  "return \"abcdef\".len: i32; };\n", 6 },
+	{ NULL, NULL, 0 }
+};
+
+static int
+slurp_eq(const char *a, const char *b)
+{
+	FILE *fa = fopen(a, "rb");
+	FILE *fb = fopen(b, "rb");
+	if (!fa || !fb) { if (fa) fclose(fa); if (fb) fclose(fb); return -1; }
+	int rc = 0;
+	for (;;) {
+		int ca = fgetc(fa);
+		int cb = fgetc(fb);
+		if (ca != cb) { rc = -1; break; }
+		if (ca == EOF) break;
+	}
+	fclose(fa); fclose(fb);
+	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 w6c[1100], w6c_ww[1100];
+	snprintf(w6c, sizeof w6c, "%s/w6c", bin);
+	snprintf(w6c_ww, sizeof w6c_ww, "%s/w6c_ww", bin);
+	if (access(w6c_ww, X_OK) != 0) {
+		fprintf(stderr, "litstr_pseudo: w6c_ww missing — cannot run the "
+		    "cs==ww byte-id gate\n");
+		return 1;
+	}
+
+	int n = 0, fail = 0;
+	for (int i = 0; rows[i].src; i++, n++) {
+		char src[64];
+		snprintf(src, sizeof src, "/tmp/wwlsp_%d_%d.ww", getpid(), i);
+		FILE *f = fopen(src, "wb");
+		if (f == NULL) { fail++; continue; }
+		fputs(rows[i].src, f);
+		fclose(f);
+
+		/* (a) cstage build + run in a scratch dir. */
+		char tmpdir[64];
+		snprintf(tmpdir, sizeof tmpdir, "/tmp/wwlsp_%d_d_%d", getpid(), i);
+		mkdir(tmpdir, 0755);
+
+		char cmd[2048];
+		snprintf(cmd, sizeof cmd, "cd %s && %s/ww build %s",
+		    tmpdir, bin, src);
+		if (runwait(cmd) != 0) {
+			fprintf(stderr, "row[%s]: cstage build failed\n",
+			    rows[i].label);
+			fail++;
+			unlink(src); rmdir(tmpdir);
+			continue;
+		}
+
+		char outbin[128];
+		const char *base = strrchr(src, '/');
+		base = base ? base + 1 : src;
+		snprintf(outbin, sizeof outbin, "%s/%s", tmpdir, base);
+		char *dot = strrchr(outbin, '.');
+		if (dot && strcmp(dot, ".ww") == 0) *dot = '\0';
+
+		int got = runwait(outbin);
+		if (got != rows[i].want_exit) {
+			fprintf(stderr, "row[%s]: cstage exit %d, want %d\n",
+			    rows[i].label, got, rows[i].want_exit);
+			fail++;
+		}
+		unlink(outbin); rmdir(tmpdir);
+
+		/* (b) cs==ww byte-id gate. */
+		char cs_s[64], ws_s[64];
+		snprintf(cs_s, sizeof cs_s, "/tmp/wwlsp_%d_%d_cs.s", getpid(), i);
+		snprintf(ws_s, sizeof ws_s, "/tmp/wwlsp_%d_%d_ww.s", getpid(), i);
+
+		snprintf(cmd, sizeof cmd, "%s -o %s %s 2>/dev/null", w6c, cs_s, src);
+		if (runwait(cmd) != 0) {
+			fprintf(stderr, "row[%s]: w6c failed\n", rows[i].label);
+			fail++; unlink(src); continue;
+		}
+		snprintf(cmd, sizeof cmd, "%s -o %s %s 2>/dev/null",
+		    w6c_ww, ws_s, src);
+		if (runwait(cmd) != 0) {
+			fprintf(stderr, "row[%s]: w6c_ww failed\n", rows[i].label);
+			fail++; unlink(src); unlink(cs_s); continue;
+		}
+		if (slurp_eq(cs_s, ws_s) != 0) {
+			fprintf(stderr, "row[%s]: cstage/wwstage .s DIFFER "
+			    "(rule-10 byte-id violation)\n", rows[i].label);
+			fail++;
+		}
+		unlink(src); unlink(cs_s); unlink(ws_s);
+	}
+
+	if (fail) {
+		fprintf(stderr, "%d/%d litstr pseudo-field tests failed\n", fail, n);
+		return 1;
+	}
+	printf("litstr_pseudo: %d/%d ok (cstage run + cs==ww byte-id)\n", n, n);
+	return 0;
+}