Files
ww/test/wcc/995_self_rebuild.c
Hojun-Cho 9e0816e199 cmd+selfhost+lib+test: directory-as-module enumeration in driver (#22)
Replace the cmd/ww + selfhost driver's file-walk import resolver
with true directory enumeration. `import encoding.utf8;` now finds
the lib/encoding/utf8/ directory and concatenates every *.ww file
in it (excluding *test.ww and the driver's *.combined.ww artifacts)
in byte-wise sorted order, instead of just finding the single
lib/encoding/utf8/utf8.ww file. Mirrors Hare's
hare/module/srcs.ha:183 _findsrcs minus tag handling.

Lookup order in both stages: (1) <dir>/<dot-as-slash>/ as directory
→ enumerate. (2) <dir>/<dot-as-slash>.ww as file. The legacy
<dir>/<name>/<name>.ww shape from #18's retained divergence is
dropped per rule-9 Hare-fidelity — Hare has no foo/foo.ha fallback;
a module IS the directory.

Symmetric across cstage (cmd/ww/main.c via opendir+qsort+stat) and
wwstage (selfhost/cmd/ww/main.ww via existing lib/os.getdents64 +
os.stat — no new lib/os surface needed; the rundirtests() walker
in main.ww from #18 was the model). Bootstrap ww2.s==ww3.s==ww4.s
byte-identical post-change.

Bundling justification (rule 11): strict-same-package validation is
bundled because the failure mode is dir-enum's own (a non-dir-enum
compilation unit cannot trigger mismatch across enumerated files).
The natural enforcement site is the driver — the parser can't
distinguish dir-enum concat from file-walk concat. Both stages
peek each file's first `package <name>;` line in expand_dir /
expanddir and exit(1) on mismatch with a precise error pointing
at the offending file. Hare's hare/module/srcs.ha:131 has the
same constraint via its README gate. Other half of #23 (strict
missing-package error tightening — 63 inline-source test wrappers
blocker) stays deferred per its filing.

Parser side (cmd/wcc/parse.c parseuse + lib/ww/parse/decl.ww
parseuse): n->str now carries only the LEAF identifier from a
dotted import. With the driver translating the full dotted path
to a directory walk, the checker only needs the package bareword
(last component) for the N_USE → decl disambiguation walk in
check.c's src_imports / decl_mod. Mirrors Hare's
`use encoding::utf8;` → `utf8::name` semantics
(ref/hare/hare/ast/import.ha:7).

Migration: lib/ww/sym.ww drops `import typ; import ast;`;
lib/ww/parse/parse.ww drops `import expr; import stmt; import
decl;`; lib/ww/lex/lex.ww drops `import tok;` — all sibling
imports auto-resolve via the new dir-enum when callers import the
package directory. lib/strings/, lib/encoding/utf8/utf8test.ww
migrate `import utf8;` → `import encoding.utf8;`. Makefile drops
-I lib/encoding/utf8 stopgap from wwdump_ww + w6c_ww. Seven test
wrappers (700_e2e, 966_strings_run, 970_fmt_run, 971_log_run,
972_fnmatch_run, 982_getopt_run, 990_selfhost) and 995_self_rebuild
drop the -I lib/encoding/utf8 runtime stopgap.

Tests: new 737_direnum C wrapper + test/wcc/data/direnum/ fixtures
pin (a) cross-pkg multi-file dir-enum build at runtime (both stages
must succeed) and (b) strict-same-package mismatch error (both
stages must surface "differs from" + exit non-zero). 738_module_decl
gains row 6 pinning the n_use->str leaf-only storage post-parser
change.

Retained workaround at selfhost/cmd/ww/main.ww expanddir loop:
`names[i][k]` nested-deref-then-index split into
`let nm: *u8 = names[i]; nm[k]` because wwstage cgen miscompiles
the chained form (treats inner u8 element as 8B sizeof *u8 instead
of 1B sizeof u8: extra MOVQ $8 + IMULQ on the inner index, MOVQ
instead of MOVZBQ load). Inline rule-8 WHY comment cites task #24
(wwstage cgen chained-index inner element size on **T). Two-step
form routes through the bare-pointer index path which both stages
handle byte-identically.

Class A wwstage cgen UNDER (chained-index inner element size on
**T) surfaced first time the codebase exercises the **T[i][k]
shape via enumeratedir() — corpus-coverage-blind landmine pattern,
same family as the trio (#27/#28/#31) from STATUS-5.

112/112 ok. ww2 == ww3 == ww4 byte-id holds.
2026-05-18 19:22:27 +09:00

150 lines
4.3 KiB
C

/*
* 995_self_rebuild — the wwstage rebuilds itself.
*
* Drives ww_ww (the ww-side driver, which shells to w6c_ww/w6a_ww/w6l_ww)
* over each wwstage tool's source and diffs the result byte-for-byte
* against the cstage-built binary in $BIN. A green run means the
* toolchain can recompile itself without touching cc, modulo the
* cold-start binary — which is the v1.0 lock from PLAN.md.
*
* This is stricter than `make bootstrap`: that loop only proves the
* wwdump cgen self-stabilises; this proves every wwstage tool round-
* trips through the wwstage pipeline.
*/
#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;
}
static const char *
absbin(void)
{
const char *b = getenv("BIN");
if (!b) b = "out/bin";
if (b[0] == '/') return b;
static char buf[2048];
char cwd[1024];
if (getcwd(cwd, sizeof cwd) == NULL) return NULL;
snprintf(buf, sizeof buf, "%s/%s", cwd, b);
return buf;
}
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;
}
/* Each tool builds via `ww_ww build -I <local> -I lib/ww -I selfhost/cmd/wcc src`.
* lib/ww holds the language introspection (lex/tok/ast/parse/typ/sym);
* selfhost/cmd/wcc holds the compiler internals (mem/check/cgen*).
* Dotted `import encoding.utf8;` finds lib/encoding/utf8/ via the
* driver's default srclib path post-task-#22 dir-enum.
* Some tools have a local module dir (w6a, w6l with sibling .ww files).
* inc_local is "" for tools without one (w6c, ww, wwdump).
*/
static int
rebuild_one(const char *bin, const char *cwd, const char *tool,
const char *src_rel, const char *inc_local)
{
char workdir[64];
snprintf(workdir, sizeof workdir, "/tmp/wwsr_%d_%s", getpid(), tool);
char cmd[4096];
snprintf(cmd, sizeof cmd, "rm -rf %s && mkdir -p %s", workdir, workdir);
if (runwait(cmd) != 0) return -1;
if (inc_local && inc_local[0]) {
snprintf(cmd, sizeof cmd,
"cd %s && %s/ww_ww build -I %s/%s -I %s/lib/ww -I %s/lib/ww/lex -I %s/lib/ww/parse -I %s/selfhost/cmd/wcc "
"%s/%s >/dev/null 2>&1",
workdir, bin, cwd, inc_local, cwd, cwd, cwd, cwd, cwd, src_rel);
} else {
snprintf(cmd, sizeof cmd,
"cd %s && %s/ww_ww build -I %s/lib/ww -I %s/lib/ww/lex -I %s/lib/ww/parse -I %s/selfhost/cmd/wcc "
"%s/%s >/dev/null 2>&1",
workdir, bin, cwd, cwd, cwd, cwd, cwd, src_rel);
}
if (runwait(cmd) != 0) {
fprintf(stderr, "self-rebuild FAIL: ww_ww build errored on %s\n", tool);
return -1;
}
char rebuilt[256], canonical[256];
snprintf(rebuilt, sizeof rebuilt, "%s/main", workdir);
snprintf(canonical, sizeof canonical, "%s/%s_ww", bin, tool);
int rc = slurp_eq(rebuilt, canonical);
if (rc != 0) {
fprintf(stderr, "self-rebuild FAIL: %s rebuilt != cstage %s\n",
tool, canonical);
}
/* Leave the driver's intermediates (.s/.o/.combined.ww) next to the
* source — 991/992/994 read those fixtures, and `make wwstage` had
* already produced byte-identical copies anyway. */
snprintf(cmd, sizeof cmd, "rm -rf %s", workdir);
runwait(cmd);
return rc;
}
int
main(void)
{
const char *bin = absbin();
if (!bin) return 1;
char cwd[1024];
if (getcwd(cwd, sizeof cwd) == NULL) return 1;
struct {
const char *tool;
const char *src;
const char *inc_local;
} tools[] = {
{ "w6c", "selfhost/cmd/w6c/main.ww", "" },
{ "w6a", "selfhost/cmd/w6a/main.ww", "selfhost/cmd/w6a" },
{ "w6l", "selfhost/cmd/w6l/main.ww", "selfhost/cmd/w6l" },
{ "ww", "selfhost/cmd/ww/main.ww", "" },
{ "wwdump", "selfhost/cmd/wwdump/main.ww", "" },
{ NULL, NULL, NULL },
};
int fail = 0, n = 0;
for (int i = 0; tools[i].tool; i++) {
if (rebuild_one(bin, cwd, tools[i].tool, tools[i].src,
tools[i].inc_local) != 0)
fail++;
n++;
}
if (fail) {
fprintf(stderr, "self-rebuild: %d/%d tool(s) diverged\n", fail, n);
return 1;
}
printf("self-rebuild: %d wwstage tool(s) round-trip byte-identical "
"through ww_ww + w6c_ww + w6a_ww + w6l_ww\n", n);
return 0;
}