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.
783 lines
24 KiB
C
783 lines
24 KiB
C
/*
|
|
* ww — the user-facing driver. Plan 9 cc(1) / Hare hare(1) analogue.
|
|
*
|
|
* Pipeline:
|
|
* ww build foo.ww → w6c foo.ww > foo.s ; w6a foo.s > foo.o ;
|
|
* w6l -o foo foo.o <runtime.o>
|
|
* ww run foo.ww → build then exec ./foo
|
|
*
|
|
* Tool paths default to siblings of $0 (so a fresh build runs out of
|
|
* out/bin/), and can be overridden with WW_W6C / WW_W6A / WW_W6L.
|
|
*/
|
|
#include "ww.h"
|
|
#include <string.h>
|
|
#include <stdlib.h>
|
|
#include <unistd.h>
|
|
#include <sys/wait.h>
|
|
#include <sys/stat.h>
|
|
#include <dirent.h>
|
|
#include <libgen.h>
|
|
|
|
static const char *usage =
|
|
"usage: ww [-V] <subcommand> [args...]\n"
|
|
" -V print version and exit\n"
|
|
" build [path] compile module to a static binary (path defaults to cwd)\n"
|
|
" run [path] ... build then exec, passing extra args to the program\n"
|
|
" test [path] build and run *_test.ww in the module (path defaults to cwd)\n"
|
|
" fmt <path> reformat ww source\n"
|
|
" version print version and exit\n"
|
|
"\n"
|
|
" path forms:\n"
|
|
" foo.ww literal file\n"
|
|
" foo search cwd, -I dirs, then $WW_LIB for foo.ww or foo/foo.ww\n"
|
|
" lib/foo directory: build lib/foo/foo.ww\n"
|
|
" . build the cwd's <basename>.ww\n";
|
|
|
|
static char *self_dir; /* directory containing this binary */
|
|
|
|
static const char *
|
|
toolpath(const char *envvar, const char *name)
|
|
{
|
|
const char *p = getenv(envvar);
|
|
if (p && p[0]) return p;
|
|
static char buf[1024];
|
|
snprintf(buf, sizeof buf, "%s/%s", self_dir, name);
|
|
return strdup(buf);
|
|
}
|
|
|
|
static int
|
|
run(const char *cmd)
|
|
{
|
|
int rc = system(cmd);
|
|
if (rc == -1) return -1;
|
|
if (WIFEXITED(rc)) return WEXITSTATUS(rc);
|
|
return 1;
|
|
}
|
|
|
|
/* Set of imported module paths, kept on the heap. Used to break
|
|
* cycles in `use` resolution. Linear because typical imports are
|
|
* a handful per build. */
|
|
struct ImportSet {
|
|
char **paths;
|
|
int n, cap;
|
|
};
|
|
|
|
static int
|
|
import_seen(struct ImportSet *s, const char *path)
|
|
{
|
|
for (int i = 0; i < s->n; i++)
|
|
if (strcmp(s->paths[i], path) == 0) return 1;
|
|
return 0;
|
|
}
|
|
|
|
static void
|
|
import_add(struct ImportSet *s, const char *path)
|
|
{
|
|
if (s->n + 1 > s->cap) {
|
|
s->cap = s->cap ? s->cap * 2 : 8;
|
|
s->paths = realloc(s->paths, s->cap * sizeof *s->paths);
|
|
}
|
|
s->paths[s->n++] = strdup(path);
|
|
}
|
|
|
|
/* Translate dots in an `import` name to slashes for path lookup.
|
|
* `encoding.utf8` → `encoding/utf8`. Mirrors Hare hare(1)'s
|
|
* use-path → fs-path mapping (ref/hare/hare/module/srcs.ha:78
|
|
* builds the same shape via path::push per ident part). */
|
|
static void
|
|
import_path_form(const char *name, char *out, size_t outsz)
|
|
{
|
|
size_t i;
|
|
for (i = 0; i + 1 < outsz && name[i] != '\0'; i++)
|
|
out[i] = (name[i] == '.') ? '/' : name[i];
|
|
out[i] = '\0';
|
|
}
|
|
|
|
/* try <dir>/<path>/ as a directory, then <dir>/<path>.ww as a file.
|
|
* Sets *is_dir on hit. Symmetric with wwstage locatein for byte-id
|
|
* driver output (rule 10). The legacy <dir>/<name>/<name>.ww form
|
|
* was dropped in task #22 — directory-as-module enumeration replaces
|
|
* it, mirroring ref/hare/hare/module/srcs.ha (Hare has no fallback
|
|
* matching `foo/foo.ha`; a module IS the directory). */
|
|
static int
|
|
locate_import_in(const char *dir, const char *path_form, char *out,
|
|
size_t outsz, int *is_dir)
|
|
{
|
|
struct stat st;
|
|
snprintf(out, outsz, "%s/%s", dir, path_form);
|
|
if (stat(out, &st) == 0 && S_ISDIR(st.st_mode)) {
|
|
*is_dir = 1;
|
|
return 1;
|
|
}
|
|
snprintf(out, outsz, "%s/%s.ww", dir, path_form);
|
|
if (access(out, 0) == 0) {
|
|
*is_dir = 0;
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/* Walk a colon-separated dirlist trying to resolve `path_form`. Returns
|
|
* 1 on the first hit and writes the concrete path + dir/file marker. */
|
|
static int
|
|
locate_import(const char *dirs, const char *path_form, char *out,
|
|
size_t outsz, int *is_dir)
|
|
{
|
|
const char *p = dirs;
|
|
while (*p) {
|
|
const char *e = strchr(p, ':');
|
|
size_t n = e ? (size_t)(e - p) : strlen(p);
|
|
if (n > 0 && n < outsz) {
|
|
char dir[1024];
|
|
if (n >= sizeof dir) n = sizeof dir - 1;
|
|
memcpy(dir, p, n);
|
|
dir[n] = '\0';
|
|
if (locate_import_in(dir, path_form, out, outsz,
|
|
is_dir)) return 1;
|
|
}
|
|
if (!e) break;
|
|
p = e + 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/* memcmp-based string compare for qsort. Byte-wise total order is
|
|
* locale-independent; rule-10 byte-id requires the two stages sort
|
|
* the same way. (strcmp would work today but Hare-fidelity points
|
|
* at memcmp via ref/hare/sort/cmp/cmp.ha:9.) */
|
|
static int
|
|
strs_cmp(const void *a, const void *b)
|
|
{
|
|
const char *sa = *(const char *const *)a;
|
|
const char *sb = *(const char *const *)b;
|
|
return strcmp(sa, sb);
|
|
}
|
|
|
|
/* enumerate_dir_ww — collect *.ww names in `dirpath` excluding
|
|
* *test.ww, sort byte-wise. Returns count; caller frees entries. */
|
|
static int
|
|
enumerate_dir_ww(const char *dirpath, char ***out_files)
|
|
{
|
|
DIR *d = opendir(dirpath);
|
|
if (d == NULL) { *out_files = NULL; return 0; }
|
|
char **arr = NULL;
|
|
int n = 0, cap = 0;
|
|
struct dirent *ent;
|
|
while ((ent = readdir(d)) != NULL) {
|
|
const char *nm = ent->d_name;
|
|
size_t nl = strlen(nm);
|
|
if (nl <= 3) continue;
|
|
if (strcmp(nm + nl - 3, ".ww") != 0) continue;
|
|
/* skip "*test.ww" (no underscore — bytestest.ww
|
|
* ostest.ww utf8test.ww — Hare convention is _test.ha
|
|
* but ww corpus settled on the un-underscored shape). */
|
|
if (nl >= 7 && strcmp(nm + nl - 7, "test.ww") == 0)
|
|
continue;
|
|
/* skip "*.combined.ww" — driver-generated concat
|
|
* artifacts (the previous build leaves them next to
|
|
* the source). They look like .ww but parse-erroring
|
|
* when re-included. */
|
|
if (nl >= 12 && strcmp(nm + nl - 12, ".combined.ww") == 0)
|
|
continue;
|
|
if (n + 1 > cap) {
|
|
cap = cap ? cap * 2 : 8;
|
|
arr = realloc(arr, cap * sizeof *arr);
|
|
}
|
|
arr[n++] = strdup(nm);
|
|
}
|
|
closedir(d);
|
|
if (n > 1) qsort(arr, n, sizeof *arr, strs_cmp);
|
|
*out_files = arr;
|
|
return n;
|
|
}
|
|
|
|
static void expand(FILE *out, const char *path, struct ImportSet *visited,
|
|
const char *libdir);
|
|
|
|
/* Scan `path` for its first non-comment-non-blank line; if it starts
|
|
* with `package <name>;` write the name into `out` (NUL-terminated)
|
|
* and return 1, else 0. Strict-same-package enforcement (task #23
|
|
* subset) is bundled here because the failure mode is dir-enum's
|
|
* own — a non-dir-enum compilation unit cannot trigger it. Hare's
|
|
* hare/module/srcs.ha:131 has the same constraint via the README
|
|
* gate; we encode it as same-package across all enumerated files. */
|
|
static int
|
|
peek_package(const char *path, char *out, size_t outsz)
|
|
{
|
|
FILE *in = fopen(path, "rb");
|
|
if (in == NULL) return 0;
|
|
char line[2048];
|
|
int found = 0;
|
|
while (fgets(line, sizeof line, in)) {
|
|
const char *p = line;
|
|
while (*p == ' ' || *p == '\t') p++;
|
|
if (*p == '\n' || *p == '\0') continue;
|
|
if (p[0] == '/' && p[1] == '/') continue;
|
|
if (strncmp(p, "package ", 8) != 0
|
|
&& strncmp(p, "package\t", 8) != 0) break;
|
|
p += 8;
|
|
while (*p == ' ' || *p == '\t') p++;
|
|
size_t i = 0;
|
|
while (i + 1 < outsz && ((p[i] >= 'a' && p[i] <= 'z')
|
|
|| (p[i] >= 'A' && p[i] <= 'Z')
|
|
|| p[i] == '_' || (p[i] >= '0' && p[i] <= '9')))
|
|
out[i] = p[i], i++;
|
|
out[i] = '\0';
|
|
found = (i > 0);
|
|
break;
|
|
}
|
|
fclose(in);
|
|
return found;
|
|
}
|
|
|
|
/* expand_dir — enumerate <dirpath>/*.ww (skip *test.ww), byte-sort,
|
|
* recurse into each. Mirrors ref/hare/hare/module/srcs.ha:183
|
|
* `_findsrcs` minus tag handling. The visited set still keys on
|
|
* concrete file paths so multi-file modules are pulled once.
|
|
* Strict-same-package: all enumerated files must declare the same
|
|
* `package <name>;` (task #23 subset; failure mode native to
|
|
* dir-enum). */
|
|
static void
|
|
expand_dir(FILE *out, const char *dirpath, struct ImportSet *visited,
|
|
const char *libdir)
|
|
{
|
|
char **files = NULL;
|
|
int n = enumerate_dir_ww(dirpath, &files);
|
|
char dirpkg[128] = {0};
|
|
for (int i = 0; i < n; i++) {
|
|
char fp[1024];
|
|
snprintf(fp, sizeof fp, "%s/%s", dirpath, files[i]);
|
|
char pkg[128];
|
|
if (peek_package(fp, pkg, sizeof pkg)) {
|
|
if (dirpkg[0] == '\0') {
|
|
snprintf(dirpkg, sizeof dirpkg, "%s", pkg);
|
|
} else if (strcmp(dirpkg, pkg) != 0) {
|
|
fprintf(stderr,
|
|
"ww: %s: package %s differs from %s in same module dir %s\n",
|
|
fp, pkg, dirpkg, dirpath);
|
|
exit(1);
|
|
}
|
|
}
|
|
expand(out, fp, visited, libdir);
|
|
free(files[i]);
|
|
}
|
|
free(files);
|
|
}
|
|
|
|
/* Recursively expand `path`: for each top-level `import IDENT;` we
|
|
* find, resolve the import and expand it first, then append our own
|
|
* bytes. Already-visited paths are skipped. Each source carries its
|
|
* own `package <name>;` declaration (the parser stamps decls from
|
|
* it). */
|
|
static void
|
|
expand(FILE *out, const char *path, struct ImportSet *visited,
|
|
const char *libdir)
|
|
{
|
|
if (import_seen(visited, path)) return;
|
|
import_add(visited, path);
|
|
|
|
FILE *in = fopen(path, "rb");
|
|
if (in == NULL) {
|
|
fprintf(stderr, "ww: cannot read %s\n", path);
|
|
return;
|
|
}
|
|
char line[2048];
|
|
while (fgets(line, sizeof line, in)) {
|
|
const char *p = line;
|
|
while (*p == ' ' || *p == '\t') p++;
|
|
if (strncmp(p, "import ", 7) != 0 && strncmp(p, "import\t", 7) != 0)
|
|
continue;
|
|
p += 7;
|
|
while (*p == ' ' || *p == '\t') p++;
|
|
char name[256] = {0};
|
|
int j = 0;
|
|
while ((*p >= 'a' && *p <= 'z') || (*p >= 'A' && *p <= 'Z')
|
|
|| *p == '_' || *p == '.' || (*p >= '0' && *p <= '9'))
|
|
if (j + 1 < (int)sizeof name) name[j++] = *p++;
|
|
if (j == 0) continue;
|
|
char path_form[256];
|
|
import_path_form(name, path_form, sizeof path_form);
|
|
char ipath[1024];
|
|
int is_dir = 0;
|
|
if (!locate_import(libdir, path_form, ipath, sizeof ipath,
|
|
&is_dir))
|
|
continue; /* silently skip if not found */
|
|
if (is_dir) expand_dir(out, ipath, visited, libdir);
|
|
else expand(out, ipath, visited, libdir);
|
|
}
|
|
|
|
rewind(in);
|
|
int ch;
|
|
while ((ch = fgetc(in)) != EOF) fputc(ch, out);
|
|
fputc('\n', out);
|
|
fclose(in);
|
|
}
|
|
|
|
static int
|
|
build_one(const char *src, int entry_is_dir, const char *out,
|
|
const char *extra_includes, const char *extra_libs,
|
|
const char *extra_libdirs)
|
|
{
|
|
const char *c6 = toolpath("WW_W6C", "w6c");
|
|
const char *a6 = toolpath("WW_W6A", "w6a");
|
|
const char *l6 = toolpath("WW_W6L", "w6l");
|
|
const char *libdir = getenv("WW_LIB");
|
|
if (libdir == NULL || libdir[0] == 0) {
|
|
static char libbuf[1024];
|
|
snprintf(libbuf, sizeof libbuf, "%s/../lib", self_dir);
|
|
libdir = libbuf;
|
|
}
|
|
const char *srcdir = getenv("WW_SRCLIB");
|
|
static char srcbuf[1024];
|
|
if (srcdir == NULL || srcdir[0] == 0) {
|
|
/* in-tree default: ../../lib relative to bin/ */
|
|
snprintf(srcbuf, sizeof srcbuf, "%s/../../lib", self_dir);
|
|
if (access(srcbuf, 0) == 0) srcdir = srcbuf;
|
|
else if (access("lib", 0) == 0) srcdir = "lib";
|
|
else srcdir = libdir;
|
|
}
|
|
|
|
/* Compose the search path: source-file's directory first, then any
|
|
* -I dirs, then srcdir. The source-dir lead matches Hare's CWD-first
|
|
* convention (its `hare test` is run from the module dir, making CWD
|
|
* == module-dir); our wrappers don't cd, so dirname(src) is the
|
|
* closest analog. Also matches cc -I. — source-dir wins ties over
|
|
* the system path. locate_import walks left-to-right.
|
|
*
|
|
* For a dir entry the source-dir IS src; for a file entry it's
|
|
* the dirname. */
|
|
char srcd[1024];
|
|
if (entry_is_dir) {
|
|
snprintf(srcd, sizeof srcd, "%s", src);
|
|
size_t n = strlen(srcd);
|
|
while (n > 1 && srcd[n-1] == '/') srcd[--n] = '\0';
|
|
} else {
|
|
const char *slash = strrchr(src, '/');
|
|
if (slash) {
|
|
size_t n = (size_t)(slash - src);
|
|
if (n >= sizeof srcd) n = sizeof srcd - 1;
|
|
memcpy(srcd, src, n);
|
|
srcd[n] = '\0';
|
|
} else {
|
|
srcd[0] = '.';
|
|
srcd[1] = '\0';
|
|
}
|
|
}
|
|
static char searchpath[4096];
|
|
if (extra_includes && extra_includes[0])
|
|
snprintf(searchpath, sizeof searchpath, "%s:%s:%s",
|
|
srcd, extra_includes, srcdir);
|
|
else
|
|
snprintf(searchpath, sizeof searchpath, "%s:%s", srcd, srcdir);
|
|
srcdir = searchpath;
|
|
|
|
/* Derive a stem for .s/.o/.combined.ww side files. For a file
|
|
* entry strip the .ww. For a dir entry use <dir>/<basename(dir)>
|
|
* so artifacts land inside the module directory. */
|
|
char stem[1024];
|
|
if (entry_is_dir) {
|
|
const char *b = strrchr(srcd, '/');
|
|
const char *base = b ? b + 1 : srcd;
|
|
snprintf(stem, sizeof stem, "%s/%s", srcd, base);
|
|
} else {
|
|
snprintf(stem, sizeof stem, "%s", src);
|
|
char *dot = strrchr(stem, '.');
|
|
if (dot && strcmp(dot, ".ww") == 0) *dot = '\0';
|
|
}
|
|
|
|
char asmf[1024], obj[1024], combined[1024];
|
|
snprintf(asmf, sizeof asmf, "%s.s", stem);
|
|
snprintf(obj, sizeof obj, "%s.o", stem);
|
|
snprintf(combined, sizeof combined, "%s.combined.ww", stem);
|
|
|
|
/* Resolve imports by concatenating sources into a temp file. The
|
|
* compiler then sees one flat source. Dir entry → enumerate the
|
|
* module dir's *.ww (less *test.ww); file entry → start at the
|
|
* file. */
|
|
{
|
|
FILE *cf = fopen(combined, "wb");
|
|
if (cf == NULL) {
|
|
fprintf(stderr, "ww: cannot open %s\n", combined);
|
|
return 1;
|
|
}
|
|
struct ImportSet visited = {0};
|
|
if (entry_is_dir) expand_dir(cf, srcd, &visited, srcdir);
|
|
else expand(cf, src, &visited, srcdir);
|
|
fclose(cf);
|
|
for (int i = 0; i < visited.n; i++) free(visited.paths[i]);
|
|
free(visited.paths);
|
|
}
|
|
|
|
char cmd[4096];
|
|
snprintf(cmd, sizeof cmd, "%s -o %s %s", c6, asmf, combined);
|
|
if (run(cmd) != 0) {
|
|
fprintf(stderr, "ww: w6c failed\n");
|
|
return 1;
|
|
}
|
|
snprintf(cmd, sizeof cmd, "%s -o %s %s", a6, obj, asmf);
|
|
if (run(cmd) != 0) {
|
|
fprintf(stderr, "ww: w6a failed\n");
|
|
return 1;
|
|
}
|
|
/* Link runtime: prefer libwwrt.a (selective archive pull) but
|
|
* fall back to start.o + syscall.o in the in-tree obj/ dir if
|
|
* we're running uninstalled. */
|
|
char rtargs[2048] = {0};
|
|
char path[1024];
|
|
snprintf(path, sizeof path, "%s/libwwrt.a", libdir);
|
|
if (access(path, 0) == 0) {
|
|
snprintf(rtargs, sizeof rtargs, "%s", path);
|
|
} else {
|
|
char a1[1024], a2[1024];
|
|
snprintf(a1, sizeof a1, "%s/../obj/rt/start.o", self_dir);
|
|
snprintf(a2, sizeof a2, "%s/../obj/rt/syscall.o", self_dir);
|
|
snprintf(rtargs, sizeof rtargs, "%s %s", a1, a2);
|
|
}
|
|
/* -L<dir> goes before -l<name> so w6l can resolve the latter. */
|
|
const char *libargs = (extra_libs && extra_libs[0]) ? extra_libs : "";
|
|
const char *libdirset = (extra_libdirs && extra_libdirs[0]) ? extra_libdirs : "";
|
|
snprintf(cmd, sizeof cmd, "%s -o %s %s %s%s%s%s%s",
|
|
l6, out, obj, rtargs,
|
|
libdirset[0] ? " " : "", libdirset,
|
|
libargs[0] ? " " : "", libargs);
|
|
if (run(cmd) != 0) {
|
|
fprintf(stderr, "ww: w6l failed\n");
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static int
|
|
do_version(void)
|
|
{
|
|
printf("ww %s\n", WW_VERSION);
|
|
return 0;
|
|
}
|
|
|
|
/* Compose the standard module search path: cwd : <extra-includes> : $WW_LIB
|
|
* source dir. The `extra` string is colon-separated -I dirs from argv. */
|
|
static const char *
|
|
search_path(const char *extra, char *buf, size_t bufsz)
|
|
{
|
|
const char *libdir = getenv("WW_SRCLIB");
|
|
static char libbuf[1024];
|
|
if (libdir == NULL || libdir[0] == 0) {
|
|
libdir = getenv("WW_LIB");
|
|
}
|
|
if (libdir == NULL || libdir[0] == 0) {
|
|
snprintf(libbuf, sizeof libbuf, "%s/../../lib", self_dir);
|
|
if (access(libbuf, 0) == 0) libdir = libbuf;
|
|
else if (access("lib", 0) == 0) libdir = "lib";
|
|
else {
|
|
snprintf(libbuf, sizeof libbuf, "%s/../lib", self_dir);
|
|
libdir = libbuf;
|
|
}
|
|
}
|
|
if (extra && extra[0])
|
|
snprintf(buf, bufsz, ".:%s:%s", extra, libdir);
|
|
else
|
|
snprintf(buf, bufsz, ".:%s", libdir);
|
|
return buf;
|
|
}
|
|
|
|
/* basename_no_ext: last path segment with any trailing ".ww" stripped. */
|
|
static void
|
|
basename_no_ext(const char *path, char *out, size_t outsz)
|
|
{
|
|
const char *base = strrchr(path, '/');
|
|
base = base ? base + 1 : path;
|
|
snprintf(out, outsz, "%s", base);
|
|
char *dot = strrchr(out, '.');
|
|
if (dot && strcmp(dot, ".ww") == 0) *dot = '\0';
|
|
}
|
|
|
|
/* resolve_module: turn a name into a concrete entry path.
|
|
* foo.ww → use as-is if it exists
|
|
* <existing dir> → returns the dir path (caller dir-enumerates)
|
|
* . → cwd as a directory
|
|
* foo (bare) → walk cwd:incs:WW_LIB; first hit is dir or file.
|
|
* Sets *is_dir on hit. Dir resolution drives directory-as-module
|
|
* enumeration in build_one. */
|
|
static int
|
|
resolve_module(const char *name, const char *incs, char *out, size_t outsz,
|
|
int *is_dir)
|
|
{
|
|
struct stat st;
|
|
if (stat(name, &st) == 0) {
|
|
if (S_ISREG(st.st_mode)) {
|
|
snprintf(out, outsz, "%s", name);
|
|
*is_dir = 0;
|
|
return 1;
|
|
}
|
|
if (S_ISDIR(st.st_mode)) {
|
|
snprintf(out, outsz, "%s", name);
|
|
*is_dir = 1;
|
|
return 1;
|
|
}
|
|
}
|
|
char sp[4096];
|
|
search_path(incs, sp, sizeof sp);
|
|
char path_form[256];
|
|
import_path_form(name, path_form, sizeof path_form);
|
|
return locate_import(sp, path_form, out, outsz, is_dir);
|
|
}
|
|
|
|
/* Append `path` to a heap string-array. Caller frees each entry + the array. */
|
|
static void
|
|
strarr_push(char ***arr, int *n, int *cap, const char *path)
|
|
{
|
|
if (*n + 1 > *cap) {
|
|
*cap = *cap ? *cap * 2 : 8;
|
|
*arr = realloc(*arr, *cap * sizeof **arr);
|
|
}
|
|
(*arr)[(*n)++] = strdup(path);
|
|
}
|
|
|
|
/* collect_tests: enumerate _test.ww files in <dir> (no recursion).
|
|
* Returns 0 on success and writes the file list + count, -1 on failure. */
|
|
static int
|
|
collect_tests(const char *dir, char ***files, int *n)
|
|
{
|
|
DIR *d = opendir(dir);
|
|
if (!d) return -1;
|
|
*files = NULL;
|
|
*n = 0;
|
|
int cap = 0;
|
|
struct dirent *ent;
|
|
while ((ent = readdir(d)) != NULL) {
|
|
const char *nm = ent->d_name;
|
|
size_t nl = strlen(nm);
|
|
const char *suf = "_test.ww";
|
|
size_t sl = strlen(suf);
|
|
if (nl <= sl) continue;
|
|
if (strcmp(nm + nl - sl, suf) != 0) continue;
|
|
char path[1024];
|
|
snprintf(path, sizeof path, "%s/%s", dir, nm);
|
|
strarr_push(files, n, &cap, path);
|
|
}
|
|
closedir(d);
|
|
return 0;
|
|
}
|
|
|
|
/* Parse the standard -I/-L/-l flags into incs/libdirs/libs. The first
|
|
* non-flag positional becomes *src_out. Returns the index past the last
|
|
* arg consumed for positionals (so callers can pick up trailing args). */
|
|
static int
|
|
parse_build_flags(int argc, char **argv,
|
|
char *incs, size_t incsz,
|
|
char *libdirs, size_t libdirsz,
|
|
char *libs, size_t libsz,
|
|
const char **src_out)
|
|
{
|
|
*src_out = NULL;
|
|
int i = 0;
|
|
for (; i < argc; i++) {
|
|
if (strncmp(argv[i], "-l", 2) == 0 && argv[i][2]) {
|
|
size_t n = strlen(libs);
|
|
snprintf(libs + n, libsz - n,
|
|
"%s%s", n ? " " : "", argv[i]);
|
|
} else if (strcmp(argv[i], "-l") == 0 && i + 1 < argc) {
|
|
size_t n = strlen(libs);
|
|
snprintf(libs + n, libsz - n,
|
|
"%s-l%s", n ? " " : "", argv[++i]);
|
|
} else if (strcmp(argv[i], "-L") == 0 && i + 1 < argc) {
|
|
size_t n = strlen(libdirs);
|
|
snprintf(libdirs + n, libdirsz - n,
|
|
"%s-L%s", n ? " " : "", argv[++i]);
|
|
} else if (strncmp(argv[i], "-L", 2) == 0 && argv[i][2]) {
|
|
size_t n = strlen(libdirs);
|
|
snprintf(libdirs + n, libdirsz - n,
|
|
"%s%s", n ? " " : "", argv[i]);
|
|
} else if (strcmp(argv[i], "-I") == 0 && i + 1 < argc) {
|
|
size_t n = strlen(incs);
|
|
snprintf(incs + n, incsz - n,
|
|
"%s%s", n ? ":" : "", argv[++i]);
|
|
} else if (strncmp(argv[i], "-I", 2) == 0 && argv[i][2]) {
|
|
size_t n = strlen(incs);
|
|
snprintf(incs + n, incsz - n,
|
|
"%s%s", n ? ":" : "", argv[i] + 2);
|
|
} else if (*src_out == NULL) {
|
|
*src_out = argv[i];
|
|
} else {
|
|
break; /* leave remaining argv to caller (run-args) */
|
|
}
|
|
}
|
|
return i;
|
|
}
|
|
|
|
static int
|
|
do_build(int argc, char **argv)
|
|
{
|
|
const char *src = NULL;
|
|
char libs[2048] = {0};
|
|
char libdirs[2048] = {0};
|
|
char incs[2048] = {0};
|
|
parse_build_flags(argc, argv, incs, sizeof incs,
|
|
libdirs, sizeof libdirs, libs, sizeof libs, &src);
|
|
if (src == NULL) src = "."; /* default: build cwd */
|
|
char resolved[1024];
|
|
int is_dir = 0;
|
|
if (!resolve_module(src, incs, resolved, sizeof resolved, &is_dir)) {
|
|
fprintf(stderr, "ww build: cannot find module %s\n", src);
|
|
return 1;
|
|
}
|
|
char out[1024];
|
|
if (is_dir) {
|
|
char tmp[1024];
|
|
snprintf(tmp, sizeof tmp, "%s", resolved);
|
|
size_t n = strlen(tmp);
|
|
while (n > 1 && tmp[n-1] == '/') tmp[--n] = '\0';
|
|
const char *b = strrchr(tmp, '/');
|
|
snprintf(out, sizeof out, "%s", b ? b + 1 : tmp);
|
|
} else {
|
|
basename_no_ext(resolved, out, sizeof out);
|
|
}
|
|
return build_one(resolved, is_dir, out, incs, libs, libdirs);
|
|
}
|
|
|
|
static int
|
|
do_run(int argc, char **argv)
|
|
{
|
|
const char *src = NULL;
|
|
char libs[2048] = {0};
|
|
char libdirs[2048] = {0};
|
|
char incs[2048] = {0};
|
|
int next = parse_build_flags(argc, argv, incs, sizeof incs,
|
|
libdirs, sizeof libdirs, libs, sizeof libs, &src);
|
|
if (src == NULL) src = ".";
|
|
char resolved[1024];
|
|
int is_dir = 0;
|
|
if (!resolve_module(src, incs, resolved, sizeof resolved, &is_dir)) {
|
|
fprintf(stderr, "ww run: cannot find module %s\n", src);
|
|
return 1;
|
|
}
|
|
char tmp[1024];
|
|
snprintf(tmp, sizeof tmp, "/tmp/ww_run_%d", getpid());
|
|
if (build_one(resolved, is_dir, tmp, incs, libs, libdirs) != 0)
|
|
return 1;
|
|
/* exec the built binary with any trailing argv as its argv. */
|
|
pid_t pid = fork();
|
|
if (pid < 0) { perror("ww: fork"); unlink(tmp); return 1; }
|
|
if (pid == 0) {
|
|
int n_extra = argc - next;
|
|
char **xargv = calloc((size_t)n_extra + 2, sizeof *xargv);
|
|
xargv[0] = tmp;
|
|
for (int i = 0; i < n_extra; i++) xargv[i+1] = argv[next + i];
|
|
xargv[n_extra+1] = NULL;
|
|
execv(tmp, xargv);
|
|
perror("ww: exec");
|
|
_exit(127);
|
|
}
|
|
int status = 0;
|
|
waitpid(pid, &status, 0);
|
|
unlink(tmp);
|
|
if (WIFEXITED(status)) return WEXITSTATUS(status);
|
|
return 1;
|
|
}
|
|
|
|
static int
|
|
do_test(int argc, char **argv)
|
|
{
|
|
const char *target = (argc > 0) ? argv[0] : ".";
|
|
struct stat st;
|
|
if (stat(target, &st) != 0) {
|
|
/* not a literal path — try module resolution and run as
|
|
* a single test program. */
|
|
char resolved[1024];
|
|
int is_dir = 0;
|
|
if (!resolve_module(target, "", resolved, sizeof resolved,
|
|
&is_dir)) {
|
|
fprintf(stderr, "ww test: cannot find %s\n", target);
|
|
return 1;
|
|
}
|
|
char tmp[1024];
|
|
snprintf(tmp, sizeof tmp, "/tmp/ww_test_%d", getpid());
|
|
if (build_one(resolved, is_dir, tmp, "", "", "") != 0) return 1;
|
|
int rc = run(tmp);
|
|
unlink(tmp);
|
|
return rc;
|
|
}
|
|
if (S_ISREG(st.st_mode)) {
|
|
/* single .ww file — build+run it. */
|
|
char tmp[1024];
|
|
snprintf(tmp, sizeof tmp, "/tmp/ww_test_%d", getpid());
|
|
if (build_one(target, 0, tmp, "", "", "") != 0) return 1;
|
|
int rc = run(tmp);
|
|
unlink(tmp);
|
|
return rc;
|
|
}
|
|
if (!S_ISDIR(st.st_mode)) {
|
|
fprintf(stderr, "ww test: %s is neither file nor directory\n", target);
|
|
return 1;
|
|
}
|
|
/* directory — run every *_test.ww inside. */
|
|
char **files = NULL;
|
|
int n = 0;
|
|
if (collect_tests(target, &files, &n) < 0) {
|
|
fprintf(stderr, "ww test: cannot read directory %s\n", target);
|
|
return 1;
|
|
}
|
|
if (n == 0) {
|
|
fprintf(stderr, "ww test: no *_test.ww files in %s\n", target);
|
|
return 1;
|
|
}
|
|
int pass = 0, fail = 0;
|
|
for (int i = 0; i < n; i++) {
|
|
char tmp[1024];
|
|
snprintf(tmp, sizeof tmp, "/tmp/ww_test_%d_%d", getpid(), i);
|
|
const char *label = strrchr(files[i], '/');
|
|
label = label ? label + 1 : files[i];
|
|
int rc = build_one(files[i], 0, tmp, target, "", "");
|
|
if (rc != 0) {
|
|
fprintf(stderr, "FAIL %s (build)\n", label);
|
|
fail++;
|
|
} else {
|
|
int xrc = run(tmp);
|
|
if (xrc == 0) {
|
|
printf("ok %s\n", label);
|
|
pass++;
|
|
} else {
|
|
printf("FAIL %s (rc=%d)\n", label, xrc);
|
|
fail++;
|
|
}
|
|
}
|
|
unlink(tmp);
|
|
free(files[i]);
|
|
}
|
|
free(files);
|
|
printf("ww test: %d pass, %d fail\n", pass, fail);
|
|
return fail == 0 ? 0 : 1;
|
|
}
|
|
|
|
static int
|
|
do_fmt(int argc, char **argv)
|
|
{
|
|
(void)argc; (void)argv;
|
|
fputs("ww: fmt: not implemented in this phase\n", stderr);
|
|
return 1;
|
|
}
|
|
|
|
int
|
|
main(int argc, char **argv)
|
|
{
|
|
if (argc >= 1) {
|
|
char buf[1024];
|
|
snprintf(buf, sizeof buf, "%s", argv[0]);
|
|
self_dir = strdup(dirname(buf));
|
|
}
|
|
if (argc < 2) { fputs(usage, stderr); return 2; }
|
|
const char *cmd = argv[1];
|
|
if (strcmp(cmd, "-V") == 0 || strcmp(cmd, "version") == 0)
|
|
return do_version();
|
|
if (strcmp(cmd, "-h") == 0 || strcmp(cmd, "--help") == 0) {
|
|
fputs(usage, stdout); return 0;
|
|
}
|
|
if (strcmp(cmd, "build") == 0) return do_build(argc - 2, argv + 2);
|
|
if (strcmp(cmd, "run") == 0) return do_run(argc - 2, argv + 2);
|
|
if (strcmp(cmd, "test") == 0) return do_test(argc - 2, argv + 2);
|
|
if (strcmp(cmd, "fmt") == 0) return do_fmt(argc - 2, argv + 2);
|
|
fprintf(stderr, "ww: unknown subcommand: %s\n", cmd);
|
|
fputs(usage, stderr);
|
|
return 2;
|
|
}
|