Files
ww/selfhost/cmd/w6c/main.ww
Hojun-Cho c58d3511e8 selfhost/cmd+test: run check before cgen in wwstage drivers
w6c_ww and wwdump_ww (-c mode) silently passed source into cgen
without type-checking it; any type error flowed through as broken
asm with exit 0. Mirror cstage cmd/w6c/main.c:73-75: between the
parse-error gate and cgeninit, install typesinit + checkinit +
checkfile + `if (ck.errs > 0) return 1;`. Cgen path unchanged —
drivers own check, cgen owns emit (checkfile not idempotent due to
installdecl scopedefine).

The wire-up was blocked by five latent check.ww divergences from
cstage, all landed first: cross-module type refs (#51), enum-int
reinterprets (#52), per-block scoping (#53), nominal-first
tagged-variant inclusion (#55), and same-module N_IDENT callee
preference (#56). With those clear, the broader exercise of
check across every selfhost driver reaches 131/131 first try.

994_w6c_ww grows by one row: a trivially-wrong `let x: i32 =
"hello";` smoke pins both stages to exit-non-zero. Pre-#50 it
emitted 202 bytes of broken asm with exit=0.

Unblocks #42 (size/align/offset wwstage intercepts) and the
audit-§1.8 UP-polarity refactor (node.type_ population can now
land in the same check pass we just wired up).
2026-05-20 04:52:16 +09:00

168 lines
4.2 KiB
Plaintext

// selfhost/cmd/w6c/main.ww — port of cmd/w6c/main.c.
//
// w6c = amd64 compiler. Read .ww, parse, codegen, emit Plan 9 amd64
// asm to stdout (or the file given by -o).
//
// w6c_ww -o file.s file.ww
//
// The cgen routines in selfhost/cmd/wcc/cgen.ww write directly to
// fd 1 via os.write(1, ...). For -o, we open the output file and
// dup2 it onto fd 1 before invoking cgfile. This is the same trick
// the bootstrap uses with shell redirection, just in-process.
package main;
import os;
import mem;
import tok;
import lex;
import ast;
import parse;
import typ;
import sym;
import check;
import cgen;
fn cstreq(a: *u8, lit: str) bool = {
let n: u64 = lit.len: u64;
let i: u64 = 0u64;
for (i < n) {
let li: i32 = i: i32;
if (a[i] != lit[li]) { return false; };
i += 1u64;
};
if (a[i] != 0u8) { return false; };
return true;
};
fn cstrlen(p: *u8) u64 = {
let n: u64 = 0u64;
for (p[n] != 0u8) { n += 1u64; };
return n;
};
// pathstr — view a NUL-terminated *u8 as a str. lib/os entrypoints
// take str post-task-#23; this bridges call sites that still hold
// C-string paths (argv entries, arena-allocated buffers).
fn pathstr(p: *u8) str = {
let r: str;
r.ptr = p;
r.len = cstrlen(p): i32;
return r;
};
fn slurp(path: *u8) (*u8, u64) = {
let fd: i32 = os.open(pathstr(path), os.flag.RDONLY, 0i32);
if (fd < 0) { return nil, 0u64; };
let szr: (i64 | os.oserror) = os.filesize(fd);
let n: i64 = 0i64;
match (szr) {
case let v: i64 => n = v;
case let e: os.oserror => { os.close(fd); return nil, 0u64; };
};
let nz: u64 = n: u64;
let buf: *u8 = os.alloc(nz + 1u64): *u8;
let rr: (i64 | os.oserror) = os.readall(fd, buf, nz);
os.close(fd);
let got: i64 = 0i64;
match (rr) {
case let v: i64 => got = v;
case let e: os.oserror => return nil, 0u64;
};
if (got != n) { return nil, 0u64; };
buf[nz] = 0u8;
return buf, nz;
};
export fn main(argc: i32, argv: **u8) i32 = {
let src: *u8 = nil;
let out: *u8 = nil;
let i: i32 = 1;
for (i < argc) {
let a: *u8 = argv[i];
if (cstreq(a, "-o")) {
i += 1;
if (i >= argc) {
os.write(2, "w6c: -o requires arg\n".ptr, 20u64);
return 2;
};
out = argv[i];
} else { if (a[0u64] == 45u8) {
os.write(2, "w6c: unknown flag\n".ptr, 17u64);
return 2;
} else {
if (src != nil) {
os.write(2, "w6c: only one input\n".ptr, 19u64);
return 2;
};
src = a;
}; };
i += 1;
};
if (src == nil) {
os.write(2, "usage: w6c_ww [-o out.s] file.ww\n".ptr, 32u64);
return 2;
};
let buf: *u8;
let blen: u64;
buf, blen = slurp(src);
if (buf == nil) {
os.write(2, "w6c: cannot read input\n".ptr, 22u64);
return 1;
};
// Redirect fd 1 to the output file before any cgen emit runs.
// cgen.ww writes directly to fd 1; dup2 lets us reuse it without
// threading a file descriptor through the emit helpers.
if (out != nil) {
let ofd: i32 = os.open(pathstr(out),
os.flag.WRONLY | os.flag.CREATE | os.flag.TRUNC, 420i32); // 0o644
if (ofd < 0) {
os.write(2, "w6c: cannot open output\n".ptr, 23u64);
return 1;
};
if (os.dup2(ofd, 1i32) < 0) {
os.write(2, "w6c: dup2 failed\n".ptr, 16u64);
os.close(ofd);
return 1;
};
os.close(ofd);
};
let ar: *arena = newarena();
let nlen: u64 = cstrlen(src);
let fname: str = astrndup(ar, src, nlen);
let l: lex;
lexinit(&l, ar, fname, buf, blen);
let ps: parser;
parserinit(&ps, ar, &l);
let f: *node = parsefile(&ps);
// Gate cgen on parse-stage errors. Mirrors cmd/w6c/main.c's
// `if (l.errs || p.errs) return 1;` — broken AST otherwise reaches
// cgen and emits junk asm with a zero exit (silent miscompile).
if (l.errs > 0 || ps.errs > 0) { return 1; };
// #50: run check before cgen so AST mutations from #42 (size/align/
// offset fold) and the audit §1.8 node.type_ population land before
// cgen walks the file. Mirrors cmd/w6c/main.c:73-75. Five precondition
// fixes for fixture cleanliness: #51 cross-module type refs, #52
// enum↔int reinterpret, #53 N_BLOCK scoping, #55 nominal-first variant
// compare, #56 bare-leaf same-module preference.
let tc: tctx;
typesinit(&tc, ar);
let ck: checker;
checkinit(&ck, ar, &tc);
checkfile(&ck, f);
if (ck.errs > 0) { return 1; };
let cg: cgen;
cgeninit(&cg, ar);
cgfile(&cg, f);
return 0;
};