lib/encoding/utf8+test: Hare port (decoder / next / encoderune / runesz / utf8sz / validate)
Hoehrmann DFA from ref/hare/encoding/utf8/decodetable.ha flattened to 1D [2048]i8 (task #20: 2D-array jagged cgen still pending); encoderune takes a caller buffer matching lib/encoding/hex.encode; done/more/invalid all spelled as plain void aliases per lib/io's eof precedent. Surface ports decoder + decode + next + encoderune + runesz + utf8sz + validate from ref/hare/encoding/utf8/{types, decode,encode,rune}.ha. next() polarity rewritten from Hare's `(state-1):uint >> 31` to an explicit `if state == 0` branch because ww's uint is 64-bit (cmd/wcc/type.c:58); same effect, no hidden 32-bit assumption. Deferred (no in-tree callers): prev, slice, position, remaining, appendrune, strencode, strdecode. String iteration (chars/ newchars/nextchar in the session-4 draft) dropped per Hare discipline — belongs in lib/strings::iterator, not encoding/utf8. Tests: - 968_utf8_run drives lib/encoding/utf8/utf8test.ww via ww run. 21 @test fns: boundaries (ASCII, 2-byte, 3-byte, 4-byte encode/decode), surrogate/overlong/out-of-range/bad-continuation reject, max-in-range (U+10FFFF) accept, truncated→more, done@EOI, validate empty/mixed/malformed, encode/decode roundtrip. Two rows ported from ref/hare/encoding/utf8/decode.ha @test that were missing in the session-4 draft: bad-continuation [0xC2,0xFF]→invalid and max-in-range [0xF4,0x8F,0xBF,0xBF]→ U+10FFFF. - 9xx stdlib runtime slot range extended from 970-989 to 960-989 to accommodate utf8 at 968 (970-989 block was full). 90/90 ok. 995_self_rebuild stays green (ww2==ww3==ww4 byte-id).
This commit is contained in:
51
test/wcc/968_utf8_run.c
Normal file
51
test/wcc/968_utf8_run.c
Normal file
@@ -0,0 +1,51 @@
|
||||
/*
|
||||
* 968_utf8_run — execute the lib/encoding/utf8 @test fixture under the
|
||||
* C-side `ww run` driver and assert exit 0.
|
||||
*
|
||||
* Thin wrapper mirroring 979_hex_run / 977_time_run: utf8test.ww carries
|
||||
* its own `export fn main()` that drives the @test fns and signals which
|
||||
* case failed via the exit code (signalled + 10).
|
||||
*
|
||||
* Slot 968: stdlib block 970–989 was full at landing time.
|
||||
*/
|
||||
#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;
|
||||
}
|
||||
|
||||
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 cwd[1024];
|
||||
if (getcwd(cwd, sizeof cwd) == NULL) return 1;
|
||||
|
||||
const char *src = "lib/encoding/utf8/utf8test.ww";
|
||||
char path[1024], cmd[2048];
|
||||
snprintf(path, sizeof path, "%s/%s", cwd, src);
|
||||
snprintf(cmd, sizeof cmd, "%s/ww run %s", bin, path);
|
||||
int rc = runwait(cmd);
|
||||
if (rc != 0) {
|
||||
fprintf(stderr, "utf8_run FAIL: %s exited %d\n", src, rc);
|
||||
return 1;
|
||||
}
|
||||
printf("utf8_run: %s ok\n", src);
|
||||
return 0;
|
||||
}
|
||||
Reference in New Issue
Block a user