flan/lib/tast.ml
Joseph Ferano 17ef50898d The FFI shim is generated, and goes where its package goes
vendor/raylib has no C in it any more: shim.c is deleted and its 84 wrappers
are emitted from declare-c, which names the library's function in the library's
own signature. The reason the shim exists is unchanged - a small struct's
calling convention is a per-target classification and clang reproduces it for
free - but writing it by hand has stopped.

declare-c is a second form rather than a change to declare, because the two make
opposite claims about the same shape: (declare start-raw [path string] ...) says
the symbol takes ptr+len, and (declare-c init-window [... title string] ...)
says it takes a NUL-terminated char*. No structural rule separates them, so the
author says which.

The merge needed two fixes that neither lane could have found alone.

Load's uses-walker matches decl_kind exhaustively and did not know DeclareC, so
the reachability work and the generator did not compile together.

And the generated C is now emitted in parts keyed by the wrapper's own C symbol,
not as one translation unit. Reach.link drops the bindings nothing reachable
calls; a single TU holding every wrapper referenced every raylib symbol, so
sand-headless - which deliberately links no libraylib, and is the reason Reach
exists - failed at the link with undefined references to GetTime and its
neighbours. The first attempt keyed the parts by Flan name and broke the other
way, dropping a wrapper that was called: the flattened declaration is named
foo-c when a Flan wrapper is generated over it and foo when none is needed, so
the Flan name is not one thing. The wrapper's C symbol is what the declaration
binds in both branches.

Worth recording how close that came to passing: the acceptance suite died with
an exception rather than printing FAIL, so a grep for failures counted zero and
the suite looked green. Only the count of reporting suites - ten where there had
been eleven - showed it.
2026-09-11 20:38:17 +07:00

179 lines
7.9 KiB
OCaml
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

(** The typed IR: what the checker produces and what every backend consumes.
Three backends share this — the tree-walking interpreter, dev redefinition
and the release AOT build (plan.org, Compilation) — so everything a backend
would otherwise have to re-derive is resolved here and nowhere else:
- names are gone. A local is a slot index into the frame, a global is a
name, and a call names its callee directly. No environment lookup.
- field access is an index, not a string, and any auto-deref the source
relied on is an explicit [Deref] node.
- literals have a machine type. There is no untyped 1 past this point.
- a struct literal lists every field in declaration order, with the omitted
ones filled in as [Zero] — ZII is settled here rather than at runtime.
- sugar is already gone from the AST; what is left is the small set below. *)
type prim =
(* arithmetic and comparison, per machine type — the operands carry their own
kind at runtime, so one constructor covers every width *)
| Add | Sub | Mul | Div | Rem
| Eq | Ne | Lt | Le | Gt | Ge
| Not
(* bitwise, integers only. [Shr] is arithmetic on a signed type and logical
on an unsigned one, which is what the operand's own kind already says. *)
| BitAnd | BitOr | BitXor | Shl | Shr
(* containers: fixed arrays and slices only at milestone 2 *)
| Len | At | Slice
(* the milestone-2 host primitives, plan.org. The four conversions are
*text*: bytes->f64 parses "12.5", f64->bytes renders it — that is what
calc-me's tokenizer and the prelude's printers each need. *)
| Bytes | BytesToF64 | BytesToI64 | F64ToBytes | I64ToBytes
| WriteStdout | Exit | Argv
| Cast of Types.t
type expr = { e : expr_kind; ty : Types.t; loc : Loc.t }
and expr_kind =
| Int of int64 * Types.ikind
| Float of float * Types.fkind
| Bool of bool
| Str of string
| Unit
| Zero of Types.t (* ZII: all-bytes-zero of this type *)
| Uninit of Types.t (* the explicit opt-out *)
| Local of int (* slot index into the frame *)
| Global of string
| Prim of prim * expr list
| Call of string * expr list (* direct call; no first-class fns yet *)
| Do of expr list
| Let of (int * expr) list * expr list
| If of expr * expr * expr
| While of expr * expr list
| Return of expr option
| Set of place * expr
| Field of expr * int (* target is already a struct value *)
| Addr of place
| Deref of expr
| Make of string * expr list (* struct literal, every field, in order *)
| Arr of expr list (* fixed-array literal *)
| Some_ of expr
| None_
| Match of expr * arm list
(* (some x): unwrap Some, else early-return None from the enclosing function.
An early return, not an expression that can fail — hence its own node. *)
| UnwrapSome of expr
(* Conditions, spec-conditions.md. [Signal] walks the handler stack and
returns Unit whatever it finds — with nothing matching it is a no-op, so
nothing here alters control flow. [HandlerBind] pushes one frame per
clause, runs its body, and pops them; each clause was lifted into its own
function by the checker, so what is left is the frame and the call. *)
| Signal of sigkind * int * expr (* how, the type id, the condition *)
| Handled of hframe list * expr list
(* The transfer, spec-conditions.md §3§6. [RestartCase] pushes one frame per
clause, runs its body, and pops them; if a transfer arrives naming one of
*its* frames it runs that clause instead, and the whole form yields either
way. [InvokeRestart] looks the name up on the restart stack, writes the
frame it found into the transfer channel and leaves — it has type Never,
so nothing follows it. *)
| RestartCase of rclause list * expr
| InvokeRestart of int * string * Loc.t (* name id, name, where *)
(* [Serror] is §2's diverging variant: the same lookup, type Never, and with
nothing transferring the program stops rather than carrying on. *)
and sigkind = Ssignal | Serror
and place =
| Plocal of int
| Pglobal of string
| Pfield of expr * int
| Pindex of expr * expr list
| Pderef of expr
(* A pushed handler: which condition type it matches, and the lifted function
that runs when one is signalled. *)
and hframe = { htype : int; hfn : string }
(* A restart clause. [rname_id] is what [invoke-restart] matches by name; the
body is a branch in the function that wrote it, because unlike a handler a
clause runs at the restart-case, which is where it was written. *)
and rclause = { rname_id : int; rname : string; rbody : expr list }
(* [binds] are the slots the pattern's fields are bound to, in field order. *)
and arm = { acase : string option; binds : int list; abody : expr list }
type field = { fname : string; fty : Types.t }
type structure = { sname : string; fields : field list }
type variant = { vname : string; vfields : field list }
type union = { uname : string; cases : variant list }
type fn = {
name : string;
params : Types.t list; (* bound to slots 0 .. n-1, in order *)
slots : Types.t array; (* the frame: one entry per slot *)
ret : Types.t;
body : expr list;
(* The defers again, innermost first. [body] already has them spliced onto
the normal exit path; this is the same list for the *transfer* exit path,
which leaves through a landing block the backend builds and no form in
[body] can reach. spec-conditions.md §5: they run, and errdefer does not. *)
fdefers : expr list;
(* Set on a function the checker made up rather than one anyone wrote: a
handler-bind clause, lifted out of the function named here. It is reached
by address from that function's body and from nowhere else, so it needs no
cell and no registry slot, and a redefinition of the parent carries its
own copy. *)
fparent : string option;
floc : Loc.t;
}
(* [gfolded] is the difference between a constant whose value the *checker*
consumed — an array length, decided before any type resolves — and one that
is only ever read at run time. The first is in the program's shape and can
never be reloaded; the second is just bytes in memory and can. Nothing else
can tell them apart afterwards, so it is recorded here. *)
type global = {
gname : string;
gty : Types.t;
ginit : expr;
gconst : bool;
gfolded : bool;
}
(* A foreign function: no body, and [esym] is the symbol the linker sees. The
aggregate calling convention is not modelled here — a C shim flattens every
struct that crosses the boundary, so clang classifies it per target and
nothing in the backend has to know x86-64 from arm64 from wasm32. *)
type extern = {
ename : string; (* the Flan name, e.g. rl/init-window *)
esym : string; (* the C symbol *)
eparams : Types.t list;
eret : Types.t;
}
type program = {
structs : structure list;
unions : union list;
globals : global list; (* in declaration order *)
externs : extern list;
fns : fn list;
(* The C the program's own (declare-c ...) forms generated, if any: one
translation unit, compiled into the build like a package's hand-written
.c file. It is on the program rather than beside it so that every driver
— the CLI, the REPL, the acceptance table — carries it without knowing
it exists. See [Shim]. *)
(* The generated FFI shim, in parts keyed by the declaration each serves,
with "" for the shared preamble. Parts rather than one string so that
[Reach.link] can drop a wrapper whose binding nothing reachable calls. *)
cshim : (string * string) list;
}
let field_index (s : structure) name =
let rec go i = function
| [] -> None
| f :: rest -> if String.equal f.fname name then Some i else go (i + 1) rest
in
go 0 s.fields