Hojun-Cho
62b9d20383
selfhost/, cmd/, internal/ join the tree-wide sweep: every section banner dies (91 selfhost + the cmd C-style dividers -> 0); narration and stale contracts deleted (pre-#22 bundler notes, retired single-PT_LOAD and no-archive claims, superseded ABI tables); every ref/harec/qbe cite, task cite, encoding/ELF contract, and rule-10 twin pointer kept; lost lifetime/rationale lines restored where the sweep over-cut (elf_globals ownership, kwtab linear-scan). Comment- only proven: all five wwstage tool binaries byte-identical across the sweep; test-commit, test-byteid (161+1399, 0 pinned-divergent), and test-bootstrap (fixed point + 991-995 byte-id) all exit 0. The read-through banked 66 latent-bug leads (checkpoint).
117 lines
2.6 KiB
C
117 lines
2.6 KiB
C
/*
|
|
* Diff anchor for self-host: the C-side libwcc and the future ww-side
|
|
* frontend must produce the same dump for the same input, byte-for-byte
|
|
* stable across runs.
|
|
*
|
|
* wwdump -t file.ww tokens, one per line: "<file>:<l>:<c> <kind> [val]"
|
|
* wwdump -a file.ww AST as s-expr, one node per line
|
|
*
|
|
* No newlines or trailing whitespace varies by phase of the moon. If
|
|
* the bytes differ, somebody changed the front end.
|
|
*/
|
|
#include "ww.h"
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
|
|
static int
|
|
slurp(const char *path, char **outbuf, u64 *outlen)
|
|
{
|
|
FILE *f = fopen(path, "rb");
|
|
if (f == NULL) return -1;
|
|
fseek(f, 0, SEEK_END);
|
|
long n = ftell(f);
|
|
fseek(f, 0, SEEK_SET);
|
|
if (n < 0) { fclose(f); return -1; }
|
|
char *b = malloc((size_t)n + 1);
|
|
if (b == NULL) { fclose(f); return -1; }
|
|
if (fread(b, 1, (size_t)n, f) != (size_t)n) { free(b); fclose(f); return -1; }
|
|
b[n] = '\0';
|
|
fclose(f);
|
|
*outbuf = b;
|
|
*outlen = (u64)n;
|
|
return 0;
|
|
}
|
|
|
|
static int
|
|
dump_tokens(const char *src, char *buf, u64 len, FILE *out)
|
|
{
|
|
Arena *a = newarena();
|
|
Lex l;
|
|
lexinit(&l, a, src, buf, len);
|
|
for (;;) {
|
|
Tok t = lexnext(&l);
|
|
tokprint(out, t);
|
|
if (t.kind == TK_EOF || t.kind == TK_ERR) break;
|
|
}
|
|
int errs = l.errs;
|
|
freearena(a);
|
|
return errs ? 1 : 0;
|
|
}
|
|
|
|
static int
|
|
dump_ast(const char *src, char *buf, u64 len, FILE *out)
|
|
{
|
|
Arena *a = newarena();
|
|
Lex l;
|
|
Parser p;
|
|
lexinit(&l, a, src, buf, len);
|
|
parserinit(&p, a, &l);
|
|
Node *file = parsefile(&p);
|
|
int errs = l.errs || p.errs;
|
|
if (file) astprint(out, file);
|
|
freearena(a);
|
|
return errs ? 1 : 0;
|
|
}
|
|
|
|
int
|
|
main(int argc, char **argv)
|
|
{
|
|
int mode = 't';
|
|
const char *src = NULL;
|
|
const char *out = NULL;
|
|
for (int i = 1; i < argc; i++) {
|
|
const char *a = argv[i];
|
|
if (strcmp(a, "-t") == 0) mode = 't';
|
|
else if (strcmp(a, "-a") == 0) mode = 'a';
|
|
else if (strcmp(a, "-o") == 0 && i + 1 < argc) out = argv[++i];
|
|
else if (a[0] == '-') {
|
|
fprintf(stderr, "wwdump: unknown flag %s\n", a);
|
|
return 2;
|
|
}
|
|
else if (src == NULL) src = a;
|
|
else {
|
|
fputs("wwdump: only one input supported\n", stderr);
|
|
return 2;
|
|
}
|
|
}
|
|
if (src == NULL) {
|
|
fputs("usage: wwdump [-t|-a] [-o out] file.ww\n", stderr);
|
|
return 2;
|
|
}
|
|
|
|
char *buf;
|
|
u64 len;
|
|
if (slurp(src, &buf, &len) < 0) {
|
|
fprintf(stderr, "wwdump: %s: cannot read\n", src);
|
|
return 1;
|
|
}
|
|
|
|
FILE *of = stdout;
|
|
if (out) {
|
|
of = fopen(out, "wb");
|
|
if (of == NULL) {
|
|
fprintf(stderr, "wwdump: cannot open %s\n", out);
|
|
return 1;
|
|
}
|
|
}
|
|
|
|
int rc;
|
|
if (mode == 'a') rc = dump_ast(src, buf, len, of);
|
|
else rc = dump_tokens(src, buf, len, of);
|
|
|
|
if (of != stdout) fclose(of);
|
|
free(buf);
|
|
return rc;
|
|
}
|