core: migrate 7 lazy seq fns from the Janet seed to the Clojure overlay (40-lazy)

Finishes a port the prior team started and reverted (bb4a3e0): the 40-lazy.clj
tier moved lazy seq fns Janet→Clojure but regressed the suite to 849 because
lazy-seq's expansion leaked as data in compile mode — that was jolt-r81, since
root-fixed (lazy-seq/lazy-cat moved to 00-syntax). With the wall gone, the port
works. This shrinks the Janet seed toward the north star (self-hosted
clojure-in-clojure on a minimal host bootstrap).

Moved to core/40-lazy.clj (wired as a loaded tier after 30-macros):
  distinct keep keep-indexed map-indexed cycle repeat iterate
40-lazy.clj completed to full parity: distinct gains its transducer arity;
keep/keep-indexed/map-indexed already had both arities.

Removed from the Janet seed (core.janet): the 7 core-* fns + their core-bindings
entries, the now-dead td-keep/td-map-indexed transducer helpers (the CLJ versions
carry their own), and the already-dead core-partition-by/core-xml-seq (shadowed by
10-seq/20-coll). Net: core.janet −131 lines.

Deferred (kept in Janet, separate follow-ups): partition-all (a CLJ port via
take/drop realizes a non-minimal element count, tripping the §6.3 laziness
counters + a suite file) and repeatedly (canonical CLJ doesn't validate args, so
the repeatedly.cljc throw cases regress). Both need behavior-matching first.

Gate: conformance 262x3, lazy-infinite 44/44, clojure-test-suite 4004/66 (UP from
3981 — the CLJ versions add coverage, e.g. distinct value-equality), fixpoint,
self-host, sci 422/0, fallback-zero, specs+unit, core-bench all green.
This commit is contained in:
Yogthos 2026-06-08 23:27:41 -04:00
parent 9e6abcd540
commit cd8f11934b
3 changed files with 39 additions and 145 deletions

View file

@ -3,17 +3,26 @@
;;
;; Each fn ported from CLJS core.cljs, stripped of chunked-seq branches.
;; --- distinct ---
(defn distinct [coll]
(let [step (fn step [xs seen]
(lazy-seq
((fn [[f :as xs] seen]
(when-let [s (seq xs)]
(if (contains? seen f)
(recur (rest s) seen)
(cons f (step (rest s) (conj seen f))))))
xs seen)))]
(step coll #{})))
;; --- distinct --- (transducer + lazy collection arity; value-based dedup)
(defn distinct
([]
(fn [rf]
(let [seen (volatile! #{})]
(fn ([] (rf)) ([result] (rf result))
([result input]
(if (contains? @seen input)
result
(do (vswap! seen conj input) (rf result input))))))))
([coll]
(let [step (fn step [xs seen]
(lazy-seq
((fn [[f :as xs] seen]
(when-let [s (seq xs)]
(if (contains? seen f)
(recur (rest s) seen)
(cons f (step (rest s) (conj seen f))))))
xs seen)))]
(step coll #{}))))
;; --- keep ---
@ -76,10 +85,10 @@
(cstep 0)))
()))
;; --- repeatedly ---
(defn repeatedly
([f] (lazy-seq (cons (f) (repeatedly f))))
([n f] (take n (repeatedly f))))
;; repeatedly stays in the Janet seed for now (core-repeatedly): the canonical CLJ
;; version doesn't validate args, so (first (repeatedly non-fn)) / (repeatedly \a +)
;; don't throw like the stricter Janet version (repeatedly.cljc throw cases).
;; Ported separately once the non-fn / non-number-count throws are matched.
;; --- repeat ---
(defn repeat
@ -91,10 +100,7 @@
(lazy-seq (cons x (iterate f (f x)))))
;; --- partition-all ---
(defn partition-all
([n coll] (partition-all n n coll))
([n step coll]
(lazy-seq
(when-let [s (seq coll)]
(cons (take n s) (partition-all n step (nthrest coll step)))))))
;; partition-all stays in the Janet seed for now (core-partition-all): it already
;; has the transducer + collection arities (jolt-cru), and a CLJ port realizes a
;; different (non-minimal) element count via take/drop than the Janet one,
;; tripping the §6.3 laziness counters + a suite file. Ported separately.

View file

@ -53,7 +53,8 @@
{:ns "clojure.core.00-kernel" :kernel true}
{:ns "clojure.core.10-seq" :kernel false}
{:ns "clojure.core.20-coll" :kernel false}
{:ns "clojure.core.30-macros" :kernel false}])
{:ns "clojure.core.30-macros" :kernel false}
{:ns "clojure.core.40-lazy" :kernel false}])
(defn- eval-overlay-source [ctx src]
(var s src)

View file

@ -804,9 +804,7 @@
(fn [rf] (fn [& a] (case (length a) 0 (rf) 1 (rf (a 0))
(if (truthy? (pred (a 1))) (rf (a 0) (a 1)) (a 0))))))
(defn td-remove [pred] (td-filter (fn [x] (not (pred x)))))
(defn td-keep [f]
(fn [rf] (fn [& a] (case (length a) 0 (rf) 1 (rf (a 0))
(let [v (f (a 1))] (if (nil? v) (a 0) (rf (a 0) v)))))))
# td-keep removed: keep (incl its transducer arity) lives in core/40-lazy.clj.
(defn td-take [n]
(fn [rf]
(var left n)
@ -829,10 +827,7 @@
(fn [& a] (case (length a) 0 (rf) 1 (rf (a 0))
(do (when (and dropping (not (truthy? (pred (a 1))))) (set dropping false))
(if dropping (a 0) (rf (a 0) (a 1))))))))
(defn td-map-indexed [f]
(fn [rf]
(var i -1)
(fn [& a] (case (length a) 0 (rf) 1 (rf (a 0)) (do (++ i) (rf (a 0) (f i (a 1))))))))
# td-map-indexed removed: map-indexed (incl transducer arity) lives in core/40-lazy.clj.
# Stateful windowing transducers. The 1-arg (completion) arity flushes a partial
# trailing window before delegating to rf's completion; matches Clojure.
@ -1342,22 +1337,7 @@
(sort-by keyfn arr))
(tuple/slice (tuple ;arr))))))
(defn core-distinct [coll]
# Option A: always lazy. seen-set is captured once and shared across the chain.
(let [seen @{}]
(defn dstep [c]
(fn []
(var cur c) (var found false) (var result nil)
(while (and (not found) (not (seq-done? cur)))
(let [x (core-first cur)]
(set cur (core-rest cur))
(when (nil? (seen x))
(put seen x true)
(set found true)
(set result x))))
(if found @[result (dstep cur)] nil)))
(make-lazy-seq (dstep (lazy-from coll)))))
# distinct now lives in the Clojure lazy tier (core/40-lazy.clj).
# group-by / frequencies now live in the Clojure collection tier
# (core/20-coll.clj).
@ -1384,21 +1364,7 @@
nil)))))
(make-lazy-seq (pstep (lazy-from coll)))))
(defn core-partition-by [f coll]
(def f (as-fn f))
(var result @[])
(var part @[])
(var last-k nil)
(each x (realize-for-iteration coll)
(let [k (f x)]
(if (and last-k (deep= k last-k))
(array/push part x)
(do
(if (> (length part) 0) (array/push result (tuple/slice (tuple ;part))))
(set part @[x])
(set last-k k)))))
(if (> (length part) 0) (array/push result (tuple/slice (tuple ;part))))
result)
# partition-by now lives in the Clojure seq tier (core/10-seq.clj).
(defn core-partition-all [n & rest]
(if (= 0 (length rest)) (td-partition-all n)
@ -1417,39 +1383,8 @@
(make-lazy-seq (pstep (lazy-from coll))))))
(defn core-keep-indexed [f coll]
(def f (as-fn f))
# Option A: always lazy.
(defn kstep [c i]
(fn []
(var cur c) (var idx i) (var found false) (var result nil)
(while (and (not found) (not (seq-done? cur)))
(let [v (f idx (core-first cur))]
(++ idx)
(set cur (core-rest cur))
(when (not (nil? v))
(set found true)
(set result v))))
(if found @[result (kstep cur idx)] nil)))
(make-lazy-seq (kstep (lazy-from coll) 0)))
(defn core-map-indexed [f & rest]
(if (= 0 (length rest)) (td-map-indexed f)
(let [coll (in rest 0)]
# Option A: always lazy.
(defn mstep [c i]
(fn []
(if (seq-done? c) nil
@[(f i (core-first c)) (mstep (core-rest c) (+ i 1))])))
(make-lazy-seq (mstep (lazy-from coll) 0)))))
(defn core-cycle [coll]
(let [c (realize-for-iteration coll)]
(if (= 0 (length c))
(make-lazy-seq (fn [] nil))
(do
(defn cstep [i] (fn [] @[(in c (% i (length c))) (cstep (+ i 1))]))
(make-lazy-seq (cstep 0))))))
# keep-indexed / map-indexed / cycle now live in the Clojure lazy tier
# (core/40-lazy.clj).
# reduce-kv now lives in the Clojure collection tier (core/20-coll.clj).
@ -1495,20 +1430,7 @@
(+= i step))
(tuple/slice (tuple ;result))))))
(defn core-repeat
"(repeat x) -> infinite lazy seq of x; (repeat n x) -> n copies of x."
[a & rest]
(if (= 0 (length rest))
(do (defn rstep [] (fn [] @[a (rstep)])) (make-lazy-seq (rstep)))
(let [n a x (in rest 0)]
(var result @[]) (var i 0)
(while (< i n) (array/push result x) (++ i))
result)))
(defn core-iterate [f x]
"Lazy infinite sequence x, (f x), (f (f x)), ..."
(defn istep [v] (fn [] @[v (istep (f v))]))
(make-lazy-seq (istep x)))
# repeat / iterate now live in the Clojure lazy tier (core/40-lazy.clj).
(defn core-repeatedly
"(repeatedly f) -> infinite lazy seq of (f) calls; (repeatedly n f) -> n calls."
@ -2408,26 +2330,7 @@
@[(core-first c) (istep (core-rest c) true)]))))
(make-lazy-seq (istep (lazy-from coll) false)))))
(defn core-keep
"(keep f coll) — (f x) for each x, dropping nils. (keep f) is a transducer."
[f & rest]
(def f (as-fn f))
(if (= 0 (length rest))
(td-keep f)
(let [coll (in rest 0)]
# Option A: always lazy.
(defn kstep [c]
(fn []
(var cur c) (var found false) (var result nil)
(while (and (not found) (not (seq-done? cur)))
(let [v (f (core-first cur))]
(set cur (core-rest cur))
(when (not (nil? v))
(set found true)
(set result v))))
(if found @[result (kstep cur)] nil)))
(make-lazy-seq (kstep (lazy-from coll))))))
# keep now lives in the Clojure lazy tier (core/40-lazy.clj).
(defn core-empty [coll]
(cond
@ -2517,14 +2420,7 @@
# Iterator/enumeration seqs — Jolt has no Java iterators, so adapt to plain seq.
(defn core-enumeration-seq [x] (core-seq x))
(defn core-iterator-seq [x] (core-seq x))
(defn core-xml-seq [root]
(def out @[])
(defn walk [n]
(array/push out n)
(when (and (core-map? n) (core-contains? n :content))
(each c (realize-for-iteration (core-get n :content)) (walk c))))
(walk root)
(tuple ;out))
# xml-seq now lives in the Clojure collection tier (core/20-coll.clj).
(defn core-line-seq [rdr]
(if (string? rdr) (core-seq (string/split "\n" rdr)) nil))
(defn core-re-matcher [re s] @{:jolt/type :jolt/matcher :re re :s s :pos 0})
@ -2867,9 +2763,6 @@
"contains?" core-contains?
"count" core-count
"partition-all" core-partition-all
"keep-indexed" core-keep-indexed
"map-indexed" core-map-indexed
"cycle" core-cycle
"pop" core-pop
"trampoline" core-trampoline
"format" core-format
@ -2952,7 +2845,6 @@
"random-uuid" core-random-uuid
"interpose" core-interpose
"mapcat" core-mapcat
"keep" core-keep
"find" core-find
"transduce" core-transduce
"sequence" core-sequence
@ -2990,12 +2882,8 @@
"nth" core-nth
"sort" core-sort
"sort-by" core-sort-by
"distinct" core-distinct
"partition" core-partition
"partition-by" core-partition-by
"range" core-range
"repeat" core-repeat
"iterate" core-iterate
"repeatedly" core-repeatedly
"identity" core-identity
"constantly" core-constantly
@ -3103,7 +2991,6 @@
"test" core-test
"enumeration-seq" core-enumeration-seq
"iterator-seq" core-iterator-seq
"xml-seq" core-xml-seq
"line-seq" core-line-seq
"re-matcher" core-re-matcher
"bean" core-bean