lib/ww/lex + selfhost/cmd: astrndup → strings.dup view (γ-1)

#7 Phase A first cut. 13 of 15 astrndup callers converted to the
explicit (*u8, n) → str view + strings.dup shape (ref/hare/strings/
dup.ha:7). astrndup export stays in selfhost/cmd/wcc/mem.ww — 2 w6a
sites blocked by the selfhost/cmd/w6a/types.ww shadow (filed as #11)
and carry an inline WHY pointer until the rename ships.

NUL-dependence audit: no consumer reads token text past `.len`. tok.text
flows through fputq (length-bounded) and parse.curtext → n.str (streq-
based dispatch across check/cgenutil); p.file is written via os.write
(ptr,len); selfhost/cmd/ww/main.ww's astrndup'd pathstr only flows into
visitseen/visitadd's manual byte-loop, while all OS calls in that file
use the unrelated `pathstr(*u8) str` view helper on the raw pointer.

Empty-str sites (lex.ww:579, 624, 640) collapse to strings.dup of an
empty view; strings.dup short-circuits len==0 (lib/strings/strings.ww:72)
and returns {nil, 0} — observationally identical to astrndup's prior
{arena_1byte, 0}.

Sites:
 - lib/ww/lex/lex.ww (8: 450, 529, 554, 564, 579, 624, 640, 794)
 - selfhost/cmd/w6c/main.ww:139
 - selfhost/cmd/w6l/dyn.ww:111 (inside dcstrtostr)
 - selfhost/cmd/w6l/obj.ww:185 (inside cstrtostr)
 - selfhost/cmd/ww/main.ww:531

Wrappers (dupstr/cstrtostr/dcstrtostr) keep their bodies; deletion
deferred to #10.
This commit is contained in:
2026-05-21 10:41:54 +09:00
parent fd7dee985e
commit 917d6250fc
12 changed files with 4005 additions and 32 deletions

View File

@@ -3730,6 +3730,7 @@ package lex;
import os;
import ascii;
import mem;
import strings;
// isidstart / isidpart — identifier classification. Lexer-local
// because the "alpha or '_' / alnum or '_'" set isn't part of Hare's
@@ -4159,7 +4160,10 @@ fn lexnum(l: *lex, start: *pos, out: *tok) void = {
};
let n: u64 = l.lpos - begin;
out.text = astrndup(l.a, l.src + begin, n);
let view: str;
view.ptr = l.src + begin;
view.len = n: i32;
out.text = strings.dup(view);
if (isfloat) {
out.kind = tkind.TK_FLOAT;
@@ -4238,7 +4242,10 @@ fn lexnum(l: *lex, start: *pos, out: *tok) void = {
};
};
if (isok) {
out.tsuffix = astrndup(l.a, p, sl);
let view: str;
view.ptr = p;
view.len = sl: i32;
out.tsuffix = strings.dup(view);
} else {
l.lpos = sb;
};
@@ -4263,7 +4270,10 @@ fn lexident(l: *lex, start: *pos, out: *tok) void = {
if (n == 1u64) {
if (p[0] == 95u8) {
out.kind = tkind.TK_UNDER;
out.text = astrndup(l.a, p, n);
let view: str;
view.ptr = p;
view.len = n: i32;
out.text = strings.dup(view);
return;
};
};
@@ -4273,7 +4283,10 @@ fn lexident(l: *lex, start: *pos, out: *tok) void = {
} else {
out.kind = tkind.TK_IDENT;
};
out.text = astrndup(l.a, p, n);
let view: str;
view.ptr = p;
view.len = n: i32;
out.text = strings.dup(view);
};
fn lexstr(l: *lex, start: *pos, out: *tok) void = {
@@ -4288,7 +4301,10 @@ fn lexstr(l: *lex, start: *pos, out: *tok) void = {
out.file = start.file;
out.line = start.line;
out.col = start.col;
out.text = astrndup(l.a, "".ptr, 0u64);
let view: str;
view.ptr = "".ptr;
view.len = 0;
out.text = strings.dup(view);
return;
};
if (c == 34) { lget(l); break; };
@@ -4333,7 +4349,10 @@ fn lexrune(l: *lex, start: *pos, out: *tok) void = {
out.file = start.file;
out.line = start.line;
out.col = start.col;
out.text = astrndup(l.a, "".ptr, 0u64);
let view: str;
view.ptr = "".ptr;
view.len = 0;
out.text = strings.dup(view);
return;
};
let ch: i32 = 0;
@@ -4349,7 +4368,10 @@ fn lexrune(l: *lex, start: *pos, out: *tok) void = {
out.file = start.file;
out.line = start.line;
out.col = start.col;
out.text = astrndup(l.a, "".ptr, 0u64);
let view: str;
view.ptr = "".ptr;
view.len = 0;
out.text = strings.dup(view);
return;
};
lget(l);
@@ -4503,7 +4525,10 @@ export fn lexnext(l: *lex, out: *tok) void = {
setposfrom(out, &start);
let one: [1]u8;
one[0] = c: u8;
out.text = astrndup(l.a, one.ptr, 1u64);
let view: str;
view.ptr = one.ptr;
view.len = 1;
out.text = strings.dup(view);
};
// lib/ww/ast.ww — port of cmd/wcc/ast.c (Node defs + printer).