ludic/selfhost/backend/emit_expr.ludic

# emit_expr.ludic — lower an expression to IR, returning its register and type.

# issue #46: `try E else { BODY }` as an expression. Evaluate E (a `result`); on
# `ok` the expression is the payload, on `err` BODY runs with the failure message
# bound to `error` and its trailing expression supplies the fallback. Pure branch
# on the tag — no unwinding, no hidden control flow.
function emit_try_body(b: Node, slot: pointer) -> void {
  var i = 0
  while i < len(b.kids) {
    if g_term { return }
    let st = b.kids[i]
    if (i == len(b.kids) - 1) and st.kind == S_EXPR {   # trailing expression = the fallback value
      emit_cov_hit(st.line)
      let v = emit_expr(st.a)
      emit(`  store i32 {coerce_code(v, "int")}, ptr {slot}\n`)
    } else { emit_stmt(st) }
    i += 1
  }
}

function emit_try(e: Node) -> Val {
  g_uses_result = true
  let r = emit_expr(e.a)
  if not (r.ty == "result") { perr(`try expects a result value (got {r.ty}) — line {itoa(e.line)}`) }
  let slot = emit_alloca("i32")
  emit(`  store i32 0, ptr {slot}\n`)              # fallback default (an else block with no trailing value)
  let okp = emit_bind(`getelementptr inbounds %Result, ptr {r.code}, i32 0, i32 0`)
  let okv = emit_bind(`load i32, ptr {okp}`)
  let isok = emit_bind(`icmp ne i32 {okv}, 0`)
  let lok = lbl("tryok");  let lel = lbl("tryelse");  let lend = lbl("tryend")
  emit(`  br i1 {isok}, label %{lok}, label %{lel}\n`)
  emit(`{lok}:\n`);  g_term = false
  let vp = emit_bind(`getelementptr inbounds %Result, ptr {r.code}, i32 0, i32 1`)
  let vv = emit_bind(`load i32, ptr {vp}`)
  emit(`  store i32 {vv}, ptr {slot}\n`)
  emit(`  br label %{lend}\n`)
  emit(`{lel}:\n`);  g_term = false
  let ep = emit_bind(`getelementptr inbounds %Result, ptr {r.code}, i32 0, i32 2`)
  let ev = emit_bind(`load ptr, ptr {ep}`)
  let eslot = emit_alloca("ptr")
  emit(`  store ptr {ev}, ptr {eslot}\n`)
  let save = nloc
  loc_push("error", eslot, "string")               # bind the failure message inside the else block
  emit_try_body(e.b, slot)
  nloc = save
  if not g_term { emit(`  br label %{lend}\n`) }
  emit(`{lend}:\n`);  g_term = false
  return val(emit_bind(`load i32, ptr {slot}`), "int")
}

function emit_load_at(addr: pointer, ty: pointer) -> Val {
  let r = emit_bind(`load {llty(ty)}, ptr {addr}`)
  return val(r, ty)
}

# short-circuit `and`/`or`: seed a slot with (left!=0), branch to decide whether
# to overwrite with (right!=0).
function emit_logic(e: Node) -> Val {
  let slot = emit_alloca("i32")
  let la = emit_expr(e.a)
  let lc = emit_bind(`icmp ne i32 {la.code}, 0`)
  let lz = emit_bind(`zext i1 {lc} to i32`)
  emit("  store i32 ");  emit(lz);  emit(", ptr ");  emit(slot);  emit("\n")
  let ev = lbl("sc");  let done = lbl("scend")
  if (e.s == "and") { emit("  br i1 ");  emit(lc);  emit(", label %");  emit(ev);  emit(", label %");  emit(done);  emit("\n") }
  else { emit("  br i1 ");  emit(lc);  emit(", label %");  emit(done);  emit(", label %");  emit(ev);  emit("\n") }
  emit(ev);  emit(":\n")
  let rb = emit_expr(e.b)
  let rc = emit_bind(`icmp ne i32 {rb.code}, 0`)
  let rz = emit_bind(`zext i1 {rc} to i32`)
  emit("  store i32 ");  emit(rz);  emit(", ptr ");  emit(slot);  emit("\n")
  emit("  br label %");  emit(done);  emit("\n")
  emit(done);  emit(":\n")
  return val(emit_bind(`load i32, ptr {slot}`), "bool")
}

function cmp_code(op: pointer) -> pointer {
  if (op == ("<"))  { return "slt" }
  if (op == ("<=")) { return "sle" }
  if (op == (">"))  { return "sgt" }
  if (op == (">=")) { return "sge" }
  if (op == ("==")) { return "eq" }
  return "ne"
}
function is_cmp(op: pointer) -> bool {
  return (op == ("<")) or (op == ("<=")) or (op == (">")) or (op == (">=")) or (op == ("==")) or (op == ("!="))
}
function arith_code(op: pointer) -> pointer {
  if (op == ("+")) { return "add" }
  if (op == ("-")) { return "sub" }
  if (op == ("*")) { return "mul" }
  if (op == ("/")) { return "sdiv" }
  if (op == ("&")) { return "and" }
  if (op == ("|")) { return "or" }
  if (op == ("^")) { return "xor" }
  if (op == ("<<")) { return "shl" }
  if (op == (">>")) { return "lshr" }             # logical shift (unsigned)
  return "srem"
}

# widen an int value to Q16.16 by shifting left 16 (a fixed value passes through)
function to_fixed(v: Val) -> pointer {
  if (v.ty == "fixed") { return v.code }
  return emit_bind(`shl i32 {v.code}, 16`)
}

# coerce a value's code to the LLVM type of `target`, for the only cross-width
# pair the language has: int (i32) <-> long (i64). int widens with sext, long
# narrows with trunc; everything else (same width, or ptr) passes through.
function coerce_code(v: Val, target: pointer) -> pointer {
  if is_fp(target) { return to_fp(v, target, `a {target} slot`) }
  if is_fn_type(target) and is_fn_type(v.ty) and not (v.ty == target) { perr(`a {v.ty} is not a {target}`) }
  if (target == "fixed") and not (fixed_lit_code(v) == "") { return fixed_lit_code(v) }
  if is_fp(v.ty) and not is_fp(target) and (llty(target) != "ptr") {
    perr(`a {v.ty} does not convert to {target} implicitly — write int(x) or fixed(x)`)
  }
  let lt = llty(target)
  let vt = llty(v.ty)
  if (lt == vt) { return v.code }
  if (lt == "i64") and (vt == "i32") { return emit_bind(`sext i32 {v.code} to i64`) }
  if (lt == "i32") and (vt == "i64") { return emit_bind(`trunc i64 {v.code} to i32`) }
  return v.code
}

# widen an int value to i64 (a long passes through) — the long analogue of to_fixed
function to_long(v: Val) -> pointer {
  if (llty(v.ty) == "i64") { return v.code }
  return emit_bind(`sext i32 {v.code} to i64`)
}

# string operators: `a + b` concatenates, `a == b` / `a != b` compare by content.
# Both call the @fn_str_* prelude (emitted once per program that uses them).
function emit_str_op(op: pointer, a: Val, b: Val) -> Val {
  g_uses_str = true
  if (op == ("+")) {
    let r = fresh_val(emit_bind(`call ptr @lp_str_concat(ptr {a.code}, ptr {b.code})`), "string")
    # a half this expression made is copied now and held by nothing: `a + "/" + b` and every
    # template's pieces once left one string behind per `+`
    if a.fresh { emit(`  call void @lp_free(ptr {a.code})\n`) }
    if b.fresh and b.code != a.code { emit(`  call void @lp_free(ptr {b.code})\n`) }
    return r
  }
  let r = emit_bind(`call i32 @lp_str_eq(ptr {a.code}, ptr {b.code})`)
  # a side made just to be compared is held by nothing once it has been: `` `{x}` == "..." ``
  if a.fresh { emit(`  call void @lp_free(ptr {a.code})\n`) }
  if b.fresh and b.code != a.code { emit(`  call void @lp_free(ptr {b.code})\n`) }
  if (op == ("!=")) {
    let c = emit_bind(`icmp eq i32 {r}, 0`)
    return val(emit_bind(`zext i1 {c} to i32`), "bool")
  }
  return val(r, "bool")
}

# the result type of a unary arithmetic operator on a value of type `ty`: fixed
# and long survive, every other 32-bit scalar (int/bool/enum) collapses to int
function arith_ty(ty: pointer) -> pointer {
  if (ty == "fixed") or (ty == "long") or is_fp(ty) { return ty }
  return "int"
}

function emit_bin(e: Node) -> Val {
  if (e.s == "and") or (e.s == "or") { return emit_logic(e) }
  let a = emit_expr(e.a)
  let b = emit_expr(e.b)
  let isnull = e.a.kind == E_NULL or e.b.kind == E_NULL
  let r = emit_bin_vals(e.s, a, b, isnull)
  # literal arithmetic stays a literal (for a float context) when a decimal is in it
  if not is_cmp(e.s) and not is_fp(r.ty) and (a.lit != null or b.lit != null) {
    if (a.lit != null or e.a.kind == E_INT) and (b.lit != null or e.b.kind == E_INT) { r.lit = e }
  }
  return r
}

# text types: `==` on two of these compares content, not the pointers. Besides
# `string`, that is the untyped raw pointer — `pointer`, and `ptr`, the element of
# a `pointers` buffer — which runtime code uses to carry text.
function is_textish(t: pointer) -> bool { return (t == "string") or (t == "pointer") or (t == "ptr") }

# lower `a <op> b` on two already-evaluated operands. Shared by binary expressions
# and compound assignment (`x += y` is exactly `x = x + y`), so both agree on
# string concatenation, Q16.16 multiply/divide, and int->long promotion.
# `isnull` marks a comparison against the literal null (pointer identity, not
# string content).
function emit_bin_vals(op: pointer, a: Val, b: Val, isnull: bool) -> Val {
  # strings are pointer-typed, so any `+` with a pointer operand is concatenation.
  # `==`/`!=` compares by content only when BOTH sides are text (`string`, or an
  # untyped raw pointer, see is_textish); every other reference — records,
  # slices, enums, buffers — compares by identity in the icmp below, as does
  # `x == null`. A string against a non-text reference is a type error.
  let ptrish = (llty(a.ty) == "ptr") or (llty(b.ty) == "ptr")
  if ptrish {
    if (op == ("+")) { return emit_str_op("+", a, b) }
    if ((op == ("==")) or (op == ("!="))) and not isnull {
      if is_textish(a.ty) and is_textish(b.ty) { return emit_str_op(op, a, b) }
      if ((a.ty == "string") and (llty(b.ty) == "ptr")) or ((b.ty == "string") and (llty(a.ty) == "ptr")) {
        perr(`cannot compare {a.ty} with {b.ty} using {op}: strings compare by content, other references by identity`)
      }
    }
  }
  let fx = (a.ty == "fixed") or (b.ty == "fixed")
  # a 64-bit operand (and no fixed/ptr involved) promotes the whole expression to
  # i64: the other side widens with sext, and the result stays `long`.
  let lng = ((llty(a.ty) == "i64") or (llty(b.ty) == "i64")) and not fx and not ptrish
  if is_fp(a.ty) or is_fp(b.ty) { return emit_fp_bin(op, a, b) }
  if is_cmp(op) {
    var ac = a.code;  var bc = b.code
    var ct = "i32"
    if fx { ac = to_fixed(a);  bc = to_fixed(b) }
    else { if lng { ct = "i64";  ac = to_long(a);  bc = to_long(b) }
      else { if (llty(a.ty) == "ptr") or (llty(b.ty) == "ptr") { ct = "ptr" } } }   # `p == null`, str/record identity
    let c = emit_bind(`icmp {cmp_code(op)} {ct} {ac}, {bc}`)
    return val(emit_bind(`zext i1 {c} to i32`), "bool")
  }
  if lng {
    let al = to_long(a);  let bl = to_long(b)
    return val(emit_bind(`{arith_code(op)} i64 {al}, {bl}`), "long")
  }
  if fx {
    let af = to_fixed(a);  let bf = to_fixed(b)
    if (op == ("*")) {
      let a64 = emit_bind(`sext i32 {af} to i64`)
      let b64 = emit_bind(`sext i32 {bf} to i64`)
      let m = emit_bind(`mul i64 {a64}, {b64}`)
      let sh = emit_bind(`ashr i64 {m}, 16`)
      return val(emit_bind(`trunc i64 {sh} to i32`), "fixed")
    }
    if (op == ("/")) {
      let a64 = emit_bind(`sext i32 {af} to i64`)
      let ash = emit_bind(`shl i64 {a64}, 16`)
      let b64 = emit_bind(`sext i32 {bf} to i64`)
      let dv = emit_bind(`sdiv i64 {ash}, {b64}`)
      return val(emit_bind(`trunc i64 {dv} to i32`), "fixed")
    }
    let r = emit_bind(`{arith_code(op)} i32 {af}, {bf}`)
    return val(r, "fixed")
  }
  let r = emit_bind(`{arith_code(op)} i32 {a.code}, {b.code}`)
  return val(r, "int")
}

# ---- named arguments -------------------------------------------------------
# An argument list is either all-positional or all-named. When named, each kid
# is an E_FINIT (label -> value); this rewrites e.kids into plain value exprs in
# the order the callee declares its parameters, so the rest of emit_call is
# oblivious to whether the caller used names.
function args_are_named(e: Node) -> bool {
  var i = 0
  while i < len(e.kids) { if e.kids[i].kind == E_FINIT { return true };  i += 1 }
  return false
}
function reorder_named(e: Node, labels: []pointer) -> void {
  if not args_are_named(e) { return }
  var i = 0
  while i < len(e.kids) {
    if e.kids[i].kind != E_FINIT { perr("named and positional arguments cannot be mixed in one call") }
    i += 1
  }
  if len(e.kids) != len(labels) { perr("wrong number of arguments") }
  let out = new []Node
  var li = 0
  while li < len(labels) {
    var found: Node = null
    var k = 0
    while k < len(e.kids) { if (e.kids[k].s == labels[li]) { found = e.kids[k] };  k += 1 }
    if (found == null) { perr(`no argument named {labels[li]}`) }
    push(out, found.a)
    li += 1
  }
  e.kids = out
}
# The parameter labels of a resolved fn/extern, in declaration order.
function param_labels(fn: Node) -> []pointer {
  let out = new []pointer
  var i = 0
  while i < len(fn.kids) { if fn.kids[i].kind == N_PARAM { push(out, fn.kids[i].s) };  i += 1 }
  return out
}

function param_types(fn: Node) -> []pointer {
  let out = new []pointer
  var i = 0
  while i < len(fn.kids) { if fn.kids[i].kind == N_PARAM { push(out, fn.kids[i].ty) };  i += 1 }
  return out
}