ludic/selfhost/backend/stdlib/emit_text_prelude.ludic
Orkuncakilkaya 647dfec334 feat(compiler): list literals, typed compound assignment, file:line diagnostics
- `[a, b, c]` list literals (E_LIST → emit_list); static_type learns
  slice-element, `new T`, list, string and literal kinds
- `x op= y` lowers through the same path as `x = x op y` (emit_bin_vals):
  fixed `*=`/`/=` use the Q16.16 64-bit paths, string `+=` concatenates,
  int→long widens; unary `-` keeps a fixed operand's type (arith_ty)
- one `unescape()` table for "strings", 'chars' and `interpolation`;
  `'\''`, `'\\'`, `'\"'` no longer read as 0; unterminated char literals
  and unexpected characters are errors instead of silently skipped
- every diagnostic is `file:line: error: msg` (g_parse_file / g_err_file,
  Node.file + Node.line set by node()); tok_desc() in expectation errors;
  duplicate `function` names and unknown `phase` names are reported in
  source terms (phase_id used to default unknown phases to Overlay)
- interpolation holes skip braces inside string literals
- hand-IR preludes move from the user `@fn_` prefix to `@lp_` so a user
  `is_ws` / `str_eq` / `path_join` no longer collides at link time
- `@ClearColor(expr)` accepts any constant expression; `Os.pid()` added
  (docs page + inventory); `str_starts()` in support/str
- main.ludic: `else if` flag ladder, char literals, stale script comments
- examples/lang/operators.ludic covers all of the above; os.ludic covers
  Os.pid; docs pages for Os.pid and the Overlay phase; ten changesets
- reseeded: selfhost/ludicc.seed.ll is the new compiler's own fixpoint

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-05 01:12:16 +03:00

422 lines
16 KiB
Text

# emit_text_prelude.ludic — the emitted Text runtime prelude: the string-builder helpers (upper/lower/trim/repeat/pad and the split/join machinery) written into each program that uses Text.*. Split out of emit_text.ludic (concern: emitted runtime code, vs. emit_text.ludic's Text.* namespace dispatch).
# emit_text_prelude — string builders that allocate: upper/lower/trim/
# repeat/pad. Emitted once per program that uses them (g_uses_textrt). Plain
# libc (strlen/malloc/memcpy), deterministic, C-string in and out.
function emit_text_prelude() -> void {
emith("define ptr @lp_str_upper(ptr %s) {\n")
emith("entry:\n")
emith(" %n = call i64 @strlen(ptr %s)\n")
emith(" %sz = add i64 %n, 1\n")
emith(" %out = call ptr @malloc(i64 %sz)\n")
emith(" %ip = alloca i64\n")
emith(" store i64 0, ptr %ip\n")
emith(" br label %cond\n")
emith("cond:\n")
emith(" %i = load i64, ptr %ip\n")
emith(" %d = icmp ult i64 %i, %n\n")
emith(" br i1 %d, label %body, label %fin\n")
emith("body:\n")
emith(" %sp = getelementptr i8, ptr %s, i64 %i\n")
emith(" %c = load i8, ptr %sp\n")
emith(" %ge = icmp uge i8 %c, 97\n")
emith(" %le = icmp ule i8 %c, 122\n")
emith(" %in = and i1 %ge, %le\n")
emith(" %cc = add i8 %c, -32\n")
emith(" %oc = select i1 %in, i8 %cc, i8 %c\n")
emith(" %op = getelementptr i8, ptr %out, i64 %i\n")
emith(" store i8 %oc, ptr %op\n")
emith(" %i1 = add i64 %i, 1\n")
emith(" store i64 %i1, ptr %ip\n")
emith(" br label %cond\n")
emith("fin:\n")
emith(" %tp = getelementptr i8, ptr %out, i64 %n\n")
emith(" store i8 0, ptr %tp\n")
emith(" ret ptr %out\n")
emith("}\n")
emith("define ptr @lp_str_lower(ptr %s) {\n")
emith("entry:\n")
emith(" %n = call i64 @strlen(ptr %s)\n")
emith(" %sz = add i64 %n, 1\n")
emith(" %out = call ptr @malloc(i64 %sz)\n")
emith(" %ip = alloca i64\n")
emith(" store i64 0, ptr %ip\n")
emith(" br label %cond\n")
emith("cond:\n")
emith(" %i = load i64, ptr %ip\n")
emith(" %d = icmp ult i64 %i, %n\n")
emith(" br i1 %d, label %body, label %fin\n")
emith("body:\n")
emith(" %sp = getelementptr i8, ptr %s, i64 %i\n")
emith(" %c = load i8, ptr %sp\n")
emith(" %ge = icmp uge i8 %c, 65\n")
emith(" %le = icmp ule i8 %c, 90\n")
emith(" %in = and i1 %ge, %le\n")
emith(" %cc = add i8 %c, 32\n")
emith(" %oc = select i1 %in, i8 %cc, i8 %c\n")
emith(" %op = getelementptr i8, ptr %out, i64 %i\n")
emith(" store i8 %oc, ptr %op\n")
emith(" %i1 = add i64 %i, 1\n")
emith(" store i64 %i1, ptr %ip\n")
emith(" br label %cond\n")
emith("fin:\n")
emith(" %tp = getelementptr i8, ptr %out, i64 %n\n")
emith(" store i8 0, ptr %tp\n")
emith(" ret ptr %out\n")
emith("}\n")
emith("define ptr @lp_str_trim(ptr %s) {\n")
emith("entry:\n")
emith(" %n = call i64 @strlen(ptr %s)\n")
emith(" %sp = alloca i64\n")
emith(" %ep = alloca i64\n")
emith(" store i64 0, ptr %sp\n")
emith(" store i64 %n, ptr %ep\n")
emith(" br label %lcond\n")
emith("lcond:\n")
emith(" %a0 = load i64, ptr %sp\n")
emith(" %e0 = load i64, ptr %ep\n")
emith(" %lt0 = icmp ult i64 %a0, %e0\n")
emith(" br i1 %lt0, label %lchk, label %rcond\n")
emith("lchk:\n")
emith(" %p0 = getelementptr i8, ptr %s, i64 %a0\n")
emith(" %c0 = load i8, ptr %p0\n")
emith(" %ws0 = call i1 @lp_is_ws(i8 %c0)\n")
emith(" br i1 %ws0, label %linc, label %rcond\n")
emith("linc:\n")
emith(" %a1 = add i64 %a0, 1\n")
emith(" store i64 %a1, ptr %sp\n")
emith(" br label %lcond\n")
emith("rcond:\n")
emith(" %a2 = load i64, ptr %sp\n")
emith(" %e2 = load i64, ptr %ep\n")
emith(" %lt2 = icmp ult i64 %a2, %e2\n")
emith(" br i1 %lt2, label %rchk, label %build\n")
emith("rchk:\n")
emith(" %em1 = sub i64 %e2, 1\n")
emith(" %p1 = getelementptr i8, ptr %s, i64 %em1\n")
emith(" %c1 = load i8, ptr %p1\n")
emith(" %ws1 = call i1 @lp_is_ws(i8 %c1)\n")
emith(" br i1 %ws1, label %rdec, label %build\n")
emith("rdec:\n")
emith(" store i64 %em1, ptr %ep\n")
emith(" br label %rcond\n")
emith("build:\n")
emith(" %st = load i64, ptr %sp\n")
emith(" %en = load i64, ptr %ep\n")
emith(" %len = sub i64 %en, %st\n")
emith(" %sz = add i64 %len, 1\n")
emith(" %out = call ptr @malloc(i64 %sz)\n")
emith(" %src = getelementptr i8, ptr %s, i64 %st\n")
emith(" call ptr @memcpy(ptr %out, ptr %src, i64 %len)\n")
emith(" %tp = getelementptr i8, ptr %out, i64 %len\n")
emith(" store i8 0, ptr %tp\n")
emith(" ret ptr %out\n")
emith("}\n")
emith("define i1 @lp_is_ws(i8 %c) {\n")
emith(" %a = icmp eq i8 %c, 32\n")
emith(" %b = icmp eq i8 %c, 9\n")
emith(" %d = icmp eq i8 %c, 10\n")
emith(" %e = icmp eq i8 %c, 13\n")
emith(" %ab = or i1 %a, %b\n")
emith(" %de = or i1 %d, %e\n")
emith(" %r = or i1 %ab, %de\n")
emith(" ret i1 %r\n")
emith("}\n")
emith("define ptr @lp_str_repeat(ptr %s, i32 %n32) {\n")
emith("entry:\n")
emith(" %nneg = icmp slt i32 %n32, 0\n")
emith(" %nn = select i1 %nneg, i32 0, i32 %n32\n")
emith(" %n = zext i32 %nn to i64\n")
emith(" %L = call i64 @strlen(ptr %s)\n")
emith(" %tot = mul i64 %L, %n\n")
emith(" %sz = add i64 %tot, 1\n")
emith(" %out = call ptr @malloc(i64 %sz)\n")
emith(" %ip = alloca i64\n")
emith(" store i64 0, ptr %ip\n")
emith(" br label %cond\n")
emith("cond:\n")
emith(" %i = load i64, ptr %ip\n")
emith(" %d = icmp ult i64 %i, %n\n")
emith(" br i1 %d, label %body, label %fin\n")
emith("body:\n")
emith(" %off = mul i64 %i, %L\n")
emith(" %dst = getelementptr i8, ptr %out, i64 %off\n")
emith(" call ptr @memcpy(ptr %dst, ptr %s, i64 %L)\n")
emith(" %i1 = add i64 %i, 1\n")
emith(" store i64 %i1, ptr %ip\n")
emith(" br label %cond\n")
emith("fin:\n")
emith(" %tp = getelementptr i8, ptr %out, i64 %tot\n")
emith(" store i8 0, ptr %tp\n")
emith(" ret ptr %out\n")
emith("}\n")
emith("define ptr @lp_str_pad(ptr %s, i32 %w32, i1 %left) {\n")
emith("entry:\n")
emith(" %L = call i64 @strlen(ptr %s)\n")
emith(" %w0 = sext i32 %w32 to i64\n")
emith(" %need = icmp ugt i64 %w0, %L\n")
emith(" br i1 %need, label %do, label %copy\n")
emith("copy:\n")
emith(" %sz0 = add i64 %L, 1\n")
emith(" %o0 = call ptr @malloc(i64 %sz0)\n")
emith(" %e0 = add i64 %L, 0\n")
emith(" call ptr @memcpy(ptr %o0, ptr %s, i64 %L)\n")
emith(" %t0 = getelementptr i8, ptr %o0, i64 %L\n")
emith(" store i8 0, ptr %t0\n")
emith(" ret ptr %o0\n")
emith("do:\n")
emith(" %pad = sub i64 %w0, %L\n")
emith(" %sz = add i64 %w0, 1\n")
emith(" %out = call ptr @malloc(i64 %sz)\n")
emith(" br i1 %left, label %padleft, label %padright\n")
emith("padleft:\n")
emith(" call void @lp_fill_sp(ptr %out, i64 0, i64 %pad)\n")
emith(" %dstL = getelementptr i8, ptr %out, i64 %pad\n")
emith(" call ptr @memcpy(ptr %dstL, ptr %s, i64 %L)\n")
emith(" br label %term\n")
emith("padright:\n")
emith(" call ptr @memcpy(ptr %out, ptr %s, i64 %L)\n")
emith(" call void @lp_fill_sp(ptr %out, i64 %L, i64 %pad)\n")
emith(" br label %term\n")
emith("term:\n")
emith(" %tp = getelementptr i8, ptr %out, i64 %w0\n")
emith(" store i8 0, ptr %tp\n")
emith(" ret ptr %out\n")
emith("}\n")
emith("define void @lp_fill_sp(ptr %buf, i64 %start, i64 %count) {\n")
emith("entry:\n")
emith(" %ip = alloca i64\n")
emith(" store i64 0, ptr %ip\n")
emith(" br label %cond\n")
emith("cond:\n")
emith(" %i = load i64, ptr %ip\n")
emith(" %d = icmp ult i64 %i, %count\n")
emith(" br i1 %d, label %body, label %done\n")
emith("body:\n")
emith(" %off = add i64 %start, %i\n")
emith(" %p = getelementptr i8, ptr %buf, i64 %off\n")
emith(" store i8 32, ptr %p\n")
emith(" %i1 = add i64 %i, 1\n")
emith(" store i64 %i1, ptr %ip\n")
emith(" br label %cond\n")
emith("done:\n")
emith(" ret void\n")
emith("}\n")
}
# emit_text2_prelude — the allocating Text ops that build strings/slices:
# replace, join (over a []string), split (returns a []string). Emitted once per
# program that uses them (g_uses_textrt2). Slices are the {data,len,cap}
# %LSlice with str (ptr) elements.
function emit_text2_prelude() -> void {
emith("define ptr @lp_str_replace(ptr %s, ptr %from, ptr %to) {\n")
emith("entry:\n")
emith(" %lf = call i64 @strlen(ptr %from)\n")
emith(" %lz = icmp eq i64 %lf, 0\n")
emith(" br i1 %lz, label %copyall, label %scan\n")
emith("copyall:\n")
emith(" %ls0 = call i64 @strlen(ptr %s)\n")
emith(" %sz0 = add i64 %ls0, 1\n")
emith(" %o0 = call ptr @malloc(i64 %sz0)\n")
emith(" call ptr @memcpy(ptr %o0, ptr %s, i64 %sz0)\n")
emith(" ret ptr %o0\n")
emith("scan:\n")
emith(" %lt = call i64 @strlen(ptr %to)\n")
emith(" %ls = call i64 @strlen(ptr %s)\n")
emith(" %cntp = alloca i64\n")
emith(" store i64 0, ptr %cntp\n")
emith(" %curp = alloca ptr\n")
emith(" store ptr %s, ptr %curp\n")
emith(" br label %ccond\n")
emith("ccond:\n")
emith(" %cur = load ptr, ptr %curp\n")
emith(" %hit = call ptr @strstr(ptr %cur, ptr %from)\n")
emith(" %isnull = icmp eq ptr %hit, null\n")
emith(" br i1 %isnull, label %csize, label %cinc\n")
emith("cinc:\n")
emith(" %c0 = load i64, ptr %cntp\n")
emith(" %c1 = add i64 %c0, 1\n")
emith(" store i64 %c1, ptr %cntp\n")
emith(" %adv = getelementptr i8, ptr %hit, i64 %lf\n")
emith(" store ptr %adv, ptr %curp\n")
emith(" br label %ccond\n")
emith("csize:\n")
emith(" %cnt = load i64, ptr %cntp\n")
emith(" %delta = sub i64 %lt, %lf\n")
emith(" %grow = mul i64 %cnt, %delta\n")
emith(" %newlen = add i64 %ls, %grow\n")
emith(" %osz = add i64 %newlen, 1\n")
emith(" %out = call ptr @malloc(i64 %osz)\n")
emith(" %srcp = alloca ptr\n")
emith(" store ptr %s, ptr %srcp\n")
emith(" %dstp = alloca ptr\n")
emith(" store ptr %out, ptr %dstp\n")
emith(" br label %bcond\n")
emith("bcond:\n")
emith(" %src = load ptr, ptr %srcp\n")
emith(" %h2 = call ptr @strstr(ptr %src, ptr %from)\n")
emith(" %n2 = icmp eq ptr %h2, null\n")
emith(" br i1 %n2, label %tail, label %seg\n")
emith("seg:\n")
emith(" %si = ptrtoint ptr %src to i64\n")
emith(" %hi = ptrtoint ptr %h2 to i64\n")
emith(" %seglen = sub i64 %hi, %si\n")
emith(" %dst0 = load ptr, ptr %dstp\n")
emith(" call ptr @memcpy(ptr %dst0, ptr %src, i64 %seglen)\n")
emith(" %dst1 = getelementptr i8, ptr %dst0, i64 %seglen\n")
emith(" call ptr @memcpy(ptr %dst1, ptr %to, i64 %lt)\n")
emith(" %dst2 = getelementptr i8, ptr %dst1, i64 %lt\n")
emith(" store ptr %dst2, ptr %dstp\n")
emith(" %src2 = getelementptr i8, ptr %h2, i64 %lf\n")
emith(" store ptr %src2, ptr %srcp\n")
emith(" br label %bcond\n")
emith("tail:\n")
emith(" %src3 = load ptr, ptr %srcp\n")
emith(" %rem = call i64 @strlen(ptr %src3)\n")
emith(" %dst3 = load ptr, ptr %dstp\n")
emith(" %remp1 = add i64 %rem, 1\n")
emith(" call ptr @memcpy(ptr %dst3, ptr %src3, i64 %remp1)\n")
emith(" ret ptr %out\n")
emith("}\n")
emith("define ptr @lp_str_join(ptr %h, ptr %sep) {\n")
emith("entry:\n")
emith(" %lp = getelementptr inbounds %LSlice, ptr %h, i32 0, i32 1\n")
emith(" %len32 = load i32, ptr %lp\n")
emith(" %len = sext i32 %len32 to i64\n")
emith(" %dp = getelementptr inbounds %LSlice, ptr %h, i32 0, i32 0\n")
emith(" %data = load ptr, ptr %dp\n")
emith(" %lsep = call i64 @strlen(ptr %sep)\n")
emith(" %totp = alloca i64\n")
emith(" store i64 0, ptr %totp\n")
emith(" %ip = alloca i64\n")
emith(" store i64 0, ptr %ip\n")
emith(" br label %scond\n")
emith("scond:\n")
emith(" %i = load i64, ptr %ip\n")
emith(" %d = icmp ult i64 %i, %len\n")
emith(" br i1 %d, label %sbody, label %alloc\n")
emith("sbody:\n")
emith(" %ep = getelementptr ptr, ptr %data, i64 %i\n")
emith(" %es = load ptr, ptr %ep\n")
emith(" %el = call i64 @strlen(ptr %es)\n")
emith(" %t0 = load i64, ptr %totp\n")
emith(" %t1 = add i64 %t0, %el\n")
emith(" store i64 %t1, ptr %totp\n")
emith(" %i1 = add i64 %i, 1\n")
emith(" store i64 %i1, ptr %ip\n")
emith(" br label %scond\n")
emith("alloc:\n")
emith(" %nz = icmp ugt i64 %len, 0\n")
emith(" %lm1 = sub i64 %len, 1\n")
emith(" %seps = mul i64 %lm1, %lsep\n")
emith(" %sepsz = select i1 %nz, i64 %seps, i64 0\n")
emith(" %tot0 = load i64, ptr %totp\n")
emith(" %tot = add i64 %tot0, %sepsz\n")
emith(" %osz = add i64 %tot, 1\n")
emith(" %out = call ptr @malloc(i64 %osz)\n")
emith(" %dstp = alloca ptr\n")
emith(" store ptr %out, ptr %dstp\n")
emith(" %jp = alloca i64\n")
emith(" store i64 0, ptr %jp\n")
emith(" br label %jcond\n")
emith("jcond:\n")
emith(" %j = load i64, ptr %jp\n")
emith(" %d2 = icmp ult i64 %j, %len\n")
emith(" br i1 %d2, label %jbody, label %jfin\n")
emith("jbody:\n")
emith(" %jnz = icmp ugt i64 %j, 0\n")
emith(" br i1 %jnz, label %putsep, label %putel\n")
emith("putsep:\n")
emith(" %ds0 = load ptr, ptr %dstp\n")
emith(" call ptr @memcpy(ptr %ds0, ptr %sep, i64 %lsep)\n")
emith(" %ds1 = getelementptr i8, ptr %ds0, i64 %lsep\n")
emith(" store ptr %ds1, ptr %dstp\n")
emith(" br label %putel\n")
emith("putel:\n")
emith(" %ep2 = getelementptr ptr, ptr %data, i64 %j\n")
emith(" %es2 = load ptr, ptr %ep2\n")
emith(" %el2 = call i64 @strlen(ptr %es2)\n")
emith(" %ds2 = load ptr, ptr %dstp\n")
emith(" call ptr @memcpy(ptr %ds2, ptr %es2, i64 %el2)\n")
emith(" %ds3 = getelementptr i8, ptr %ds2, i64 %el2\n")
emith(" store ptr %ds3, ptr %dstp\n")
emith(" %j1 = add i64 %j, 1\n")
emith(" store i64 %j1, ptr %jp\n")
emith(" br label %jcond\n")
emith("jfin:\n")
emith(" %dsf = load ptr, ptr %dstp\n")
emith(" store i8 0, ptr %dsf\n")
emith(" ret ptr %out\n")
emith("}\n")
emith("define ptr @lp_str_split(ptr %s, ptr %sep) {\n")
emith("entry:\n")
emith(" %lsep = call i64 @strlen(ptr %sep)\n")
emith(" %cntp = alloca i64\n")
emith(" store i64 1, ptr %cntp\n")
emith(" %curp = alloca ptr\n")
emith(" store ptr %s, ptr %curp\n")
emith(" br label %ccond\n")
emith("ccond:\n")
emith(" %cur = load ptr, ptr %curp\n")
emith(" %hit = call ptr @strstr(ptr %cur, ptr %sep)\n")
emith(" %isnull = icmp eq ptr %hit, null\n")
emith(" br i1 %isnull, label %mk, label %cinc\n")
emith("cinc:\n")
emith(" %c0 = load i64, ptr %cntp\n")
emith(" %c1 = add i64 %c0, 1\n")
emith(" store i64 %c1, ptr %cntp\n")
emith(" %adv = getelementptr i8, ptr %hit, i64 %lsep\n")
emith(" store ptr %adv, ptr %curp\n")
emith(" br label %ccond\n")
emith("mk:\n")
emith(" %cnt = load i64, ptr %cntp\n")
emith(" %hdr = call ptr @malloc(i64 16)\n")
emith(" %arrsz = mul i64 %cnt, 8\n")
emith(" %arr = call ptr @malloc(i64 %arrsz)\n")
emith(" %d0 = getelementptr inbounds %LSlice, ptr %hdr, i32 0, i32 0\n")
emith(" store ptr %arr, ptr %d0\n")
emith(" %cnt32 = trunc i64 %cnt to i32\n")
emith(" %d1 = getelementptr inbounds %LSlice, ptr %hdr, i32 0, i32 1\n")
emith(" store i32 %cnt32, ptr %d1\n")
emith(" %d2 = getelementptr inbounds %LSlice, ptr %hdr, i32 0, i32 2\n")
emith(" store i32 %cnt32, ptr %d2\n")
emith(" %srcp = alloca ptr\n")
emith(" store ptr %s, ptr %srcp\n")
emith(" %ip = alloca i64\n")
emith(" store i64 0, ptr %ip\n")
emith(" br label %fcond\n")
emith("fcond:\n")
emith(" %i = load i64, ptr %ip\n")
emith(" %lt = icmp ult i64 %i, %cnt\n")
emith(" br i1 %lt, label %fbody, label %done\n")
emith("fbody:\n")
emith(" %src = load ptr, ptr %srcp\n")
emith(" %h2 = call ptr @strstr(ptr %src, ptr %sep)\n")
emith(" %n2 = icmp eq ptr %h2, null\n")
emith(" br i1 %n2, label %last, label %mid\n")
emith("mid:\n")
emith(" %si = ptrtoint ptr %src to i64\n")
emith(" %hi = ptrtoint ptr %h2 to i64\n")
emith(" %seglen = sub i64 %hi, %si\n")
emith(" br label %store\n")
emith("last:\n")
emith(" %rem = call i64 @strlen(ptr %src)\n")
emith(" br label %store\n")
emith("store:\n")
emith(" %seg = phi i64 [ %seglen, %mid ], [ %rem, %last ]\n")
emith(" %ssz = add i64 %seg, 1\n")
emith(" %sub = call ptr @malloc(i64 %ssz)\n")
emith(" %src2 = load ptr, ptr %srcp\n")
emith(" call ptr @memcpy(ptr %sub, ptr %src2, i64 %seg)\n")
emith(" %tp = getelementptr i8, ptr %sub, i64 %seg\n")
emith(" store i8 0, ptr %tp\n")
emith(" %slot = getelementptr ptr, ptr %arr, i64 %i\n")
emith(" store ptr %sub, ptr %slot\n")
emith(" %adv2 = getelementptr i8, ptr %h2, i64 %lsep\n")
emith(" store ptr %adv2, ptr %srcp\n")
emith(" %i1 = add i64 %i, 1\n")
emith(" store i64 %i1, ptr %ip\n")
emith(" br label %fcond\n")
emith("done:\n")
emith(" ret ptr %hdr\n")
emith("}\n")
}