Files
ww/lib/encoding/base64/base64_test.ww
Hojun-Cho 7a4f60b041 w6c+wcc+selfhost+lib: int-cast truncate + use_alias, 5 new modules
Two cgen/check bugs surfaced by new lib modules, plus the modules
themselves (crc64, siphash, random, base64, base32).

  1. `(big_u64): u32` (and `: u16`, `: u8`, `: bool`) didn't truncate.
     N_CAST emitted nothing for int↔int; the value stayed in AX with
     its upper bits intact and downstream CMPQ/DIVQ misread the slot.
     The TK_TILDE path already had clamp logic for the same reason —
     N_CAST was the missing case. Both stages now MOVL r,r for u32 and
     ANDQ $mask for u8/u16/bool. Signed-narrow (i8/i16/i32) stays
     no-op until w6a grows reg-reg MOVSBQ/MOVSWQ/MOVSXD. selfhost
     cgcast walks alias chains via aliaslookup before checking
     primsize/typenameisunsigned so `(u: random)` where
     `type random = u64` still bypasses the clamp.
     See cmd/w6c/cgen.c N_CAST and selfhost/cmd/wcc/cgenexpr.ww cgcast.

  2. `mod.mod` type refs (`random.random` when the imported module
     declares `export type random = u64;`) failed with "unknown type".
     The driver concatenates imports into one flat scope, so SK_USE
     `random` collided with SK_TYPE `random` and scope_define silently
     dropped the use. resolve_typename's leaf lookup required
     `kind == SK_USE` and gave up. Adds a `use_alias` flag to Sym; the
     pass-1 decl scan now marks colliding syms in both directions
     (use-after-type and type-after-use). resolve_typename and the
     N_DOT cexpr branch treat `use_alias` like SK_USE for qualified
     lookup. selfhost check.ww was already lenient on this path so no
     ww-side change was needed; bootstrap fixed point (990-995) holds.
     See cmd/wcc/check.c installdecl pass + N_DOT/resolve_typename and
     cmd/wcc/ww.h Sym.use_alias.

New modules under lib/, each with @test vectors in *_test.ww and wired
into test/wcc/900_stdlib.c (26 modules → all compile):

  - lib/hash/crc64       ECMA, ISO  (mirror of crc32 shape)
  - lib/hash/siphash     SipHash-2-4, buffer-based sum/sum24
  - lib/math/random      SplitMix64 (init, next, u32n, u64n)
  - lib/encoding/base64  RFC 4648 std + url-safe encode/decode + sizes
  - lib/encoding/base32  RFC 4648 std + base32hex encode/decode + sizes
2026-05-13 14:58:36 +09:00

173 lines
5.0 KiB
Plaintext

use base64;
fn putstr(s: str, into: []u8, off: i32) i32 = {
let i: i32 = 0;
for (i < s.len) {
into[off + i] = s[i];
i += 1;
};
return off + s.len;
};
fn streq(buf: []u8, expect: str) bool = {
if (buf.len != expect.len) { return false; };
let i: i32 = 0;
for (i < buf.len) {
if (buf[i] != expect[i]) { return false; };
i += 1;
};
return true;
};
fn encodevec(input: str, expect: str) void = {
let inbuf: [128]u8;
let outbuf: [128]u8;
let n: i32 = putstr(input, inbuf[0:128], 0);
let m: i32 = base64.encode(outbuf[0:128], inbuf[0:n]);
if (m != expect.len) { let _: i32 = 1/0; };
if (!streq(outbuf[0:m], expect)) { let _: i32 = 1/0; };
};
@test fn rfc4648_vectors() void = {
encodevec("", "");
encodevec("f", "Zg==");
encodevec("fo", "Zm8=");
encodevec("foo", "Zm9v");
encodevec("foob", "Zm9vYg==");
encodevec("fooba", "Zm9vYmE=");
encodevec("foobar", "Zm9vYmFy");
};
fn decodevec(input: str, expect: str) void = {
let inbuf: [128]u8;
let outbuf: [128]u8;
let n: i32 = putstr(input, inbuf[0:128], 0);
let r: (i32 | base64.invalid) = base64.decode(outbuf[0:128], inbuf[0:n]);
match (r) {
case let m: i32 => {
if (m != expect.len) { let _: i32 = 1/0; };
if (!streq(outbuf[0:m], expect)) { let _: i32 = 1/0; };
};
case let e: base64.invalid => { let _: i32 = 1/0; };
};
};
@test fn rfc4648_decode() void = {
decodevec("", "");
decodevec("Zg==", "f");
decodevec("Zm8=", "fo");
decodevec("Zm9v", "foo");
decodevec("Zm9vYg==", "foob");
decodevec("Zm9vYmE=", "fooba");
decodevec("Zm9vYmFy", "foobar");
};
@test fn alphabet_full() void = {
// Round-trip every 6-bit value (0..63) by encoding three bytes that
// expose b0=0x00, b1=AA, b2=FF — the encoded chars depend on all
// four positions including the >>2 path.
let i: i32 = 0;
for (i < 64) {
let bits: u8 = i: u8;
// Construct a triple [bits<<2, 0, 0] so the first encoded
// char encodes `bits`. The other three chars are derivable
// from the remaining bytes; we only check the first here.
let inbuf: [3]u8;
inbuf[0] = bits << 2u8;
inbuf[1] = 0u8;
inbuf[2] = 0u8;
let outbuf: [4]u8;
let m: i32 = base64.encode(outbuf[0:4], inbuf[0:3]);
if (m != 4) { let _: i32 = 1/0; };
// Decoding back must give us `bits` in the high 6 bits of [0].
let r: (i32 | base64.invalid) = base64.decode(inbuf[0:3], outbuf[0:4]);
match (r) {
case let n: i32 => {
if (n != 3) { let _: i32 = 1/0; };
if ((inbuf[0] >> 2u8) != bits) { let _: i32 = 1/0; };
};
case let e: base64.invalid => { let _: i32 = 1/0; };
};
i += 1;
};
};
@test fn invalid_inputs() void = {
let inbuf: [16]u8;
let outbuf: [16]u8;
// Length not a multiple of 4.
let n: i32 = putstr("abc", inbuf[0:16], 0);
let r1: (i32 | base64.invalid) = base64.decode(outbuf[0:16], inbuf[0:n]);
match (r1) {
case let m: i32 => { let _: i32 = 1/0; };
case let e: base64.invalid => void;
};
// Bad char ('@' is not in the std alphabet).
let n2: i32 = putstr("Z@==", inbuf[0:16], 0);
let r2: (i32 | base64.invalid) = base64.decode(outbuf[0:16], inbuf[0:n2]);
match (r2) {
case let m: i32 => { let _: i32 = 1/0; };
case let e: base64.invalid => void;
};
};
@test fn urlsafe_roundtrip() void = {
// Byte sequence chosen so the std alphabet would use '+' and '/',
// while url-safe replaces them with '-' and '_'. 0xFB = 11111011
// hits index 62 in some quad, and 0xFF hits 63.
let raw: [3]u8;
raw[0] = 0xFBu8;
raw[1] = 0xFFu8;
raw[2] = 0xBFu8;
let std: [8]u8;
let url: [8]u8;
let dec: [3]u8;
let m1: i32 = base64.encode(std[0:8], raw[0:3]);
let m2: i32 = base64.encodeurl(url[0:8], raw[0:3]);
if (m1 != 4) { let _: i32 = 1/0; };
if (m2 != 4) { let _: i32 = 1/0; };
// Round-trip both ways.
let r1: (i32 | base64.invalid) = base64.decode(dec[0:3], std[0:m1]);
match (r1) {
case let n: i32 => {
if (n != 3) { let _: i32 = 1/0; };
if (dec[0] != raw[0]) { let _: i32 = 1/0; };
if (dec[1] != raw[1]) { let _: i32 = 1/0; };
if (dec[2] != raw[2]) { let _: i32 = 1/0; };
};
case let e: base64.invalid => { let _: i32 = 1/0; };
};
let r2: (i32 | base64.invalid) = base64.decodeurl(dec[0:3], url[0:m2]);
match (r2) {
case let n: i32 => {
if (n != 3) { let _: i32 = 1/0; };
if (dec[0] != raw[0]) { let _: i32 = 1/0; };
if (dec[1] != raw[1]) { let _: i32 = 1/0; };
if (dec[2] != raw[2]) { let _: i32 = 1/0; };
};
case let e: base64.invalid => { let _: i32 = 1/0; };
};
};
@test fn sizes() void = {
if (base64.encodedsize(0) != 0) { let _: i32 = 1/0; };
if (base64.encodedsize(1) != 4) { let _: i32 = 1/0; };
if (base64.encodedsize(2) != 4) { let _: i32 = 1/0; };
if (base64.encodedsize(3) != 4) { let _: i32 = 1/0; };
if (base64.encodedsize(4) != 8) { let _: i32 = 1/0; };
if (base64.encodedsize(6) != 8) { let _: i32 = 1/0; };
if (base64.encodedsize(7) != 12) { let _: i32 = 1/0; };
if (base64.decodedsize(4) != 3) { let _: i32 = 1/0; };
if (base64.decodedsize(8) != 6) { let _: i32 = 1/0; };
};
export fn main() i32 = {
rfc4648_vectors();
rfc4648_decode();
alphabet_full();
invalid_inputs();
urlsafe_roundtrip();
sizes();
return 0;
};