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

@@ -18,6 +18,7 @@ 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
@@ -447,7 +448,10 @@ 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;
@@ -526,7 +530,10 @@ 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;
};
@@ -551,7 +558,10 @@ 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;
};
};
@@ -561,7 +571,10 @@ 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 = {
@@ -576,7 +589,10 @@ 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; };
@@ -621,7 +637,10 @@ 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;
@@ -637,7 +656,10 @@ 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);
@@ -791,5 +813,8 @@ 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);
};

View File

@@ -1331,6 +1331,7 @@ fn perr(a: *asm_, msg: str) void = {
};
// dupstr — copy n bytes from p into a fresh heap str.
// astrndup until #11 (w6a types shadow) is fixed.
fn dupstr(a: *arena, p: *u8, n: u64) str = {
return astrndup(a, p, n);
};
@@ -3120,6 +3121,7 @@ export fn main(argc: i32, argv: **u8) i32 = {
let ar: *arena = newarena();
let s: asm_;
let nlen: u64 = cstrlen(src);
// astrndup until #11 (w6a types shadow) is fixed.
let fname: str = astrndup(ar, src, nlen);
init(&s, ar, fname, buf, blen);

View File

@@ -114,6 +114,7 @@ export fn main(argc: i32, argv: **u8) i32 = {
let ar: *arena = newarena();
let s: asm_;
let nlen: u64 = cstrlen(src);
// astrndup until #11 (w6a types shadow) is fixed.
let fname: str = astrndup(ar, src, nlen);
init(&s, ar, fname, buf, blen);

View File

@@ -179,6 +179,7 @@ fn perr(a: *asm_, msg: str) void = {
};
// dupstr — copy n bytes from p into a fresh heap str.
// astrndup until #11 (w6a types shadow) is fixed.
fn dupstr(a: *arena, p: *u8, n: u64) str = {
return astrndup(a, p, n);
};

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).
@@ -23367,6 +23392,7 @@ package main;
import os;
import rt;
import mem;
import strings;
import tok;
import lex;
import ast;
@@ -23488,7 +23514,10 @@ export fn main(argc: i32, argv: **u8) i32 = {
let ar: *arena = newarena();
let nlen: u64 = cstrlen(src);
let fname: str = astrndup(ar, src, nlen);
let view: str;
view.ptr = src;
view.len = nlen: i32;
let fname: str = strings.dup(view);
let l: lex;
lexinit(&l, ar, fname, buf, blen);

View File

@@ -15,6 +15,7 @@ package main;
import os;
import rt;
import mem;
import strings;
import tok;
import lex;
import ast;
@@ -136,7 +137,10 @@ export fn main(argc: i32, argv: **u8) i32 = {
let ar: *arena = newarena();
let nlen: u64 = cstrlen(src);
let fname: str = astrndup(ar, src, nlen);
let view: str;
view.ptr = src;
view.len = nlen: i32;
let fname: str = strings.dup(view);
let l: lex;
lexinit(&l, ar, fname, buf, blen);

View File

@@ -13,6 +13,7 @@ package w6l;
import os;
import rt;
import mem;
import strings;
import sym;
def ET_DYN_SO: u16 = 3u16;
@@ -108,7 +109,10 @@ fn dcstrlen(p: *u8) u64 = {
fn dcstrtostr(a: *arena, p: *u8) str = {
let n: u64 = dcstrlen(p);
return astrndup(a, p, n);
let view: str;
view.ptr = p;
view.len = n: i32;
return strings.dup(view);
};
// basename: scan for last '/' and return pointer past it.

File diff suppressed because it is too large Load Diff

View File

@@ -13,6 +13,7 @@ package w6l;
import os;
import rt;
import mem;
import strings;
import sym;
def ET_REL: i32 = 1;
@@ -182,7 +183,10 @@ fn cstreq(p: *u8, lit: str) bool = {
// Build a ww str from a NUL-terminated *u8 (for passing to intern).
fn cstrtostr(a: *arena, p: *u8) str = {
let n: u64 = cstrlen(p);
return astrndup(a, p, n);
let view: str;
view.ptr = p;
view.len = n: i32;
return strings.dup(view);
};
// ---- archive (SysV ar) types and helpers -------------------------------

File diff suppressed because it is too large Load Diff

View File

@@ -16,6 +16,7 @@ package main;
import os;
import rt;
import mem;
import strings;
// All path/string scratch buffers go on the runtime page allocator.
// One page is plenty for any path we build.
@@ -528,7 +529,10 @@ fn scanuse(src: *u8, len: u64) (*u8, u64) = {
// decls).
fn expand(c: *expctx, pathcs: *u8) void = {
let plen: u64 = cstrlen(pathcs);
let pathstr: str = astrndup(c.a, pathcs, plen);
let view: str;
view.ptr = pathcs;
view.len = plen: i32;
let pathstr: str = strings.dup(view);
if (visitseen(c, pathstr)) { return; };
visitadd(c, pathstr);

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).