flan/lib/prelude.ml
Joseph Ferano 7fcda905ff parse-i64 in Flan, because strtoll answers 0 four different ways
bytes->i64 is strtoll behind a primitive, and strtoll returns 0 for "", for
"abc", for a lone "-", and for the "12" in "12x". None of those is
distinguishable from a real 0, so any program that parses input it did not
write is already wrong and has no way to find out. parse-i64 takes the whole
slice or refuses it and says so with None. It is also the version that answers
the same on wasm32: strtoll is libc's and locale-sensitive, which is the same
argument that put the PRNG in the prelude rather than leaving it to rand().

The byte predicates are over [u8] rather than over string on purpose. (bytes s)
is one call at the call site, and in exchange one copy of each function serves
strings and byte slices both — which is as near a generic as this gets. Each
tests its length before it slices, and `and` short-circuits, so a prefix longer
than the subject answers false instead of tripping the slice bounds check.

sign-f32 and lerp are the only two numeric helpers here, because they are the
only two that decide something. clamp is (min hi (max lo x)) and abs is
(max x (- 0 x)) over builtins that already exist — a prelude wrapper is a
function emitted into every program to save a caller nothing. sign-f32 answers
0.0 for NaN, which is a choice and is written down. lerp is the weighted sum
and not a + t*(b - a): the latter does not land on b exactly at t = 1.0, and a
position that never quite arrives is what interpolation gets bug reports for.

floor, ceil and round are deliberately absent. (f32 (i32 x)) is fptosi, which
is poison out of range, and shipping that as a documented limitation is the
same class of bug NEXT.md already records twice under Sharp edges. Correct
lowering is llvm.floor.f32 in emit.ml, which is not this lane. sqrt is absent
for a different reason: it is an extern to libm, and what libm means on wasm32
is a decision the FFI owns, not the prelude.

rand-i32-range answers lo for an empty or reversed range rather than dividing
by zero, which is immediate undefined behaviour and not merely a wrong number.
Both range functions draw exactly one rand-u32 and neither changes it, so the
sand hash still pins the generator; the new test pins the derivations off a
fixed seed, which nothing else would have caught.
2026-09-11 18:49:52 +07:00

237 lines
8.8 KiB
OCaml

(** The milestone-2 prelude, written in Flan.
Printing is deliberately *not* a primitive (plan.org, Milestone-2
primitives): [write-stdout] is the one output primitive and everything
above it is Flan. That is what keeps a second backend cheap — a primitive
is the only thing implemented twice.
It lives here as a string rather than as a file because there is no package
loader yet; at milestone 3 it becomes an ordinary [core:] package and this
module goes away. The acceptance programs may call anything defined here.
No overloading: [print-f64] and [print-str] name the type, because
compile-time overloading before the checker is stable is how a small
language stops being one. A single [println] is milestone 5. *)
let source = {flan|
(defn print-bytes [b [u8]]
(write-stdout b))
(defn print-str [s string]
(write-stdout (bytes s)))
(defn print-f64 [x f64]
(write-stdout (f64->bytes x)))
(defn print-i64 [x i64]
(write-stdout (i64->bytes x)))
(defn newline []
(write-stdout (bytes "\n")))
;; A seeded PRNG in Flan rather than libc's, because a grid hash is only a
;; regression test if the sequence is byte-identical on native and wasm32
;; (plan.org, RNG is ours). PCG-XSH-RR 32: one u64 LCG step per draw, folded
;; down to 32 bits by an xorshift and rotated by the state's top five bits.
(defvar rand-state u64 6364136223846793005)
(defn rand-seed [seed u64]
(set rand-state (+ (* seed 6364136223846793005) 1442695040888963407)))
(defn rand-u32 [] u32
(let [s rand-state]
(set rand-state (+ (* s 6364136223846793005) 1442695040888963407))
;; The rotate is masked to 5 bits: a 32-bit shift by 32 is poison in LLVM,
;; and r = 0 is the case that would ask for it.
(let [x (u32 (>> (bit-xor (>> s 18) s) 27))
r (u32 (>> s 59))]
(bit-or (>> x r) (<< x (bit-and (- 32 r) 31))))))
;; In [0, 1). The divisor is 2^32 exactly, so the result never reaches 1.0.
(defn rand-f32 [] f32
(/ (f32 (rand-u32)) 4294967296.0))
;; Prints s and then a newline. Takes a string, not an Option or an any —
;; there is nothing to dispatch on yet.
(defn print-line [s string]
(print-str s)
(newline))
;; ── Slice algorithms, all in place ────────────────────────────────────
;;
;; Over [i32] and nothing else. There are no generics, so one of these per
;; element type is one *copy* per element type, emitted into every program;
;; i32 is the type indices, ids and tile values already have, and f32 copies
;; wait until a program actually wants them.
;;
;; A slice is ptr+len and non-owning, so these mutate the storage they were
;; handed: sorting (slice grid 4 9) sorts those five elements of grid and
;; leaves the rest alone. That is the whole reason the shape is in-place —
;; there is no allocator to return a new sequence from.
(defn swap-i32! [s [i32] i i32 j i32]
(let [t (at s i)]
(set (at s i) (at s j))
(set (at s j) t)))
(defn reverse-i32! [s [i32]]
(let [i 0
j (- (len s) 1)]
(while (< i j)
(swap-i32! s i j)
(set i (+ i 1))
(set j (- j 1)))))
;; Insertion sort: in place, no recursion, no auxiliary array and no
;; comparison function — quicksort would want a stack and mergesort a buffer,
;; and neither exists. Ascending, and stable, though with no payload type to
;; carry that is not yet observable.
(defn sort-i32! [s [i32]]
(let [i 1]
(while (< i (len s))
(let [j i]
;; `and` short-circuits, which is load-bearing: at j = 0 the left test
;; fails and (at s -1) is never evaluated, so this does not trap.
(while (and (> j 0) (> (at s (- j 1)) (at s j)))
(swap-i32! s (- j 1) j)
(set j (- j 1))))
(set i (+ i 1)))))
;; The first index holding x. None rather than -1, because Option is what the
;; language has and a sentinel index is the bug this avoids.
(defn index-of-i32 [s [i32] x i32] (Option i32)
(dotimes [i (len s)]
(when (= (at s i) x)
(return (Some i))))
None)
;; None for an empty slice: there is no least i32 that is also an honest
;; answer, and returning one would be a value the caller cannot tell from a
;; real element.
(defn min-i32 [s [i32]] (Option i32)
(if (= (len s) 0)
None
(let [m (at s 0)]
(dotimes [i (len s)]
(set m (min m (at s i))))
(Some m))))
(defn max-i32 [s [i32]] (Option i32)
(if (= (len s) 0)
None
(let [m (at s 0)]
(dotimes [i (len s)]
(set m (max m (at s i))))
(Some m))))
;; Accumulates in i64 and each element is widened explicitly — there is no
;; implicit widening anywhere in the language, and summing a screenful of i32
;; into an i32 is how a total silently wraps.
(defn sum-i32 [s [i32]] i64
(let [t (i64 0)]
(dotimes [i (len s)]
(set t (+ t (i64 (at s i)))))
t))
;; ── Bytes ─────────────────────────────────────────────────────────────
;;
;; Over [u8] and not over string, so (bytes s) is what a caller writes and one
;; copy of each serves strings and byte slices both — which is as close to a
;; generic as a language without them gets. Nothing here allocates: every
;; result is a bool, an index, or a number.
(defn bytes=? [a [u8] b [u8]] bool
(if (!= (len a) (len b))
false
(do
(dotimes [i (len a)]
(when (!= (at a i) (at b i))
(return false)))
true)))
;; The length test comes first and `and` short-circuits, so the slice is only
;; built once it is known to be in bounds — otherwise a prefix longer than the
;; string would trap rather than answer false.
(defn starts-with? [s [u8] p [u8]] bool
(and (<= (len p) (len s))
(bytes=? (slice s 0 (len p)) p)))
(defn ends-with? [s [u8] p [u8]] bool
(and (<= (len p) (len s))
(bytes=? (slice s (- (len s) (len p)) (len s)) p)))
(defn index-of-byte [s [u8] b u8] (Option i32)
(dotimes [i (len s)]
(when (= (at s i) b)
(return (Some i))))
None)
;; The whole slice is an integer, or it is None. bytes->i64 is strtoll, which
;; answers 0 for "" and for "abc" and stops at the first junk byte in "12x" —
;; three wrong answers a caller cannot tell from a real 12. This is also the
;; one that has to be Flan rather than the primitive: strtoll is locale- and
;; libc-dependent, and a parser in the language gives the same answer on
;; wasm32 as on native for the same reason rand-f32 does.
;; Overflow wraps, as all arithmetic here does; it is not reported.
(defn parse-i64 [s [u8]] (Option i64)
(let [i 0
n (i64 0)
neg false]
(when (= (len s) 0)
(return None))
(when (or (= (at s 0) \-) (= (at s 0) \+))
(set neg (= (at s 0) \-))
(set i 1))
(when (= i (len s))
(return None)) ; a lone sign is not a number
(while (< i (len s))
(let [b (at s i)]
(when (or (< b \0) (> b \9))
(return None))
(set n (+ (* n 10) (i64 (- b \0)))))
(set i (+ i 1)))
(if neg (Some (- 0 n)) (Some n))))
;; ── Numbers ───────────────────────────────────────────────────────────
;;
;; Only the two that encode a decision. clamp is (min hi (max lo x)) over two
;; builtins and abs is (max x (- 0 x)); a wrapper over those is a function
;; emitted into every program to save a caller nothing.
;; Zero for zero, and zero for NaN — neither is positive nor negative, so
;; neither comparison fires. A caller that needs to know which it got should
;; be testing for NaN, not reading a sign.
(defn sign-f32 [x f32] f32
(cond
(> x 0.0) 1.0
(< x 0.0) -1.0
:else 0.0))
;; Written as the weighted sum and not as a + t*(b - a): the second form does
;; not return b exactly at t = 1.0 once rounding is involved, and a position
;; that does not arrive is the bug an interpolation gets reported for.
(defn lerp [a f32 b f32 t f32] f32
(+ (* (- 1.0 t) a) (* t b)))
;; ── More of the RNG ───────────────────────────────────────────────────
;;
;; Both draw exactly one rand-u32, so the sequence a program consumes is the
;; same one; neither touches the generator.
;; [lo, hi). An empty or reversed range answers lo — a defined value rather
;; than a remainder by zero, which is immediate undefined behaviour and not a
;; wrong number. The span must fit in i32, since hi - lo is computed there.
(defn rand-i32-range [lo i32 hi i32] i32
(if (<= hi lo)
lo
(+ lo (i32 (% (rand-u32) (u32 (- hi lo)))))))
;; [lo, hi), because rand-f32 never reaches 1.0.
(defn rand-f32-range [lo f32 hi f32] f32
(+ lo (* (rand-f32) (- hi lo))))
|flan}
let file = "<prelude>"
let forms () = Reader.read_all ~file source