diff --git a/lib/erlang/scoreboard.json b/lib/erlang/scoreboard.json index fac8aff3..8b2827f2 100644 --- a/lib/erlang/scoreboard.json +++ b/lib/erlang/scoreboard.json @@ -1,11 +1,11 @@ { "language": "erlang", - "total_pass": 738, - "total": 738, + "total_pass": 750, + "total": 750, "suites": [ {"name":"tokenize","pass":62,"total":62,"status":"ok"}, {"name":"parse","pass":52,"total":52,"status":"ok"}, - {"name":"eval","pass":385,"total":385,"status":"ok"}, + {"name":"eval","pass":397,"total":397,"status":"ok"}, {"name":"runtime","pass":93,"total":93,"status":"ok"}, {"name":"ring","pass":4,"total":4,"status":"ok"}, {"name":"ping-pong","pass":4,"total":4,"status":"ok"}, diff --git a/lib/erlang/scoreboard.md b/lib/erlang/scoreboard.md index 75cac040..13ad1a7c 100644 --- a/lib/erlang/scoreboard.md +++ b/lib/erlang/scoreboard.md @@ -1,12 +1,12 @@ # Erlang-on-SX Scoreboard -**Total: 738 / 738 tests passing** +**Total: 750 / 750 tests passing** | | Suite | Pass | Total | |---|---|---|---| | ✅ | tokenize | 62 | 62 | | ✅ | parse | 52 | 52 | -| ✅ | eval | 385 | 385 | +| ✅ | eval | 397 | 397 | | ✅ | runtime | 93 | 93 | | ✅ | ring | 4 | 4 | | ✅ | ping-pong | 4 | 4 | diff --git a/lib/erlang/tests/eval.sx b/lib/erlang/tests/eval.sx index 4bd322db..7ff48aed 100644 --- a/lib/erlang/tests/eval.sx +++ b/lib/erlang/tests/eval.sx @@ -1341,6 +1341,23 @@ (get (nth (get er-rt-cap-result :elements) 4) :name) "true") + +;; ── $X char literals (Step 3b substrate fix 2026-06-04) ────────── +(er-eval-test "char $A" (ev "$A") 65) +(er-eval-test "char $a" (ev "$a") 97) +(er-eval-test "char $0 is digit, not escape-NUL" (ev "$0") 48) +(er-eval-test "char $\\n is newline (10)" (ev "$\\n") 10) +(er-eval-test "char $\\t is tab (9)" (ev "$\\t") 9) +(er-eval-test "char $\\r is CR (13)" (ev "$\\r") 13) +(er-eval-test "char $\\s is space (32)" (ev "$\\s") 32) +(er-eval-test "char $\\0 is NUL (0)" (ev "$\\0") 0) +(er-eval-test "char $\\\\ is backslash (92)" (ev "$\\\\") 92) +(er-eval-test "[$h,$i] head is 104" (ev "hd([$h, $i])") 104) +(er-eval-test "list_to_binary char-list -> bytes" + (ev "byte_size(list_to_binary([$f, $e, $d]))") 3) +(er-eval-test "list_to_binary char-list round-trip" + (nm (ev "list_to_binary([$h, $i]) =:= <<104, 105>>")) "true") + (define er-eval-test-summary (str "eval " er-eval-test-pass "/" er-eval-test-count)) diff --git a/lib/erlang/tokenizer.sx b/lib/erlang/tokenizer.sx index c46e7bc6..8a70bde4 100644 --- a/lib/erlang/tokenizer.sx +++ b/lib/erlang/tokenizer.sx @@ -229,13 +229,37 @@ (= ch "$") (do (er-advance! 1) - (if - (and (< pos src-len) (= (er-cur) "\\")) - (do - (er-advance! 1) - (when (< pos src-len) (er-advance! 1))) - (when (< pos src-len) (er-advance! 1))) - (er-emit! "integer" (slice src start pos) start) + ;; Emit the char's decimal code as the integer token value + ;; (was: raw "$X" text — parse-number then returned nil). + (let + ((code (cond + (>= pos src-len) 0 + (= (er-cur) "\\") + (do + (er-advance! 1) + (let ((esc (if (< pos src-len) (er-cur) ""))) + (when (< pos src-len) (er-advance! 1)) + (cond + (= esc "n") 10 + (= esc "t") 9 + (= esc "r") 13 + (= esc "s") 32 + (= esc "b") 8 + (= esc "e") 27 + (= esc "f") 12 + (= esc "v") 11 + (= esc "d") 127 + (= esc "0") 0 + (= esc "\\") 92 + (= esc "\"") 34 + (= esc "'") 39 + (= esc "") 0 + :else (char->integer (nth (string->list esc) 0))))) + :else + (let ((c (er-cur))) + (er-advance! 1) + (char->integer (nth (string->list c) 0)))))) + (er-emit! "integer" (str code) start)) (scan!)) (er-lower? ch) (do diff --git a/next/README.md b/next/README.md index 73c20535..3b564304 100644 --- a/next/README.md +++ b/next/README.md @@ -103,16 +103,16 @@ The kernel calls into these host primitives: `crypto:hash/2`, These three gaps block the remaining unchecked deliverables: -1. **Term codec** (`3b`/`3c`) — **byte-level path resolved 2026-06-04:** - `erlang:binary_to_list/1` and `erlang:list_to_binary/1` are now registered - in `lib/erlang/runtime.sx` (738/738 conformance, +9 ffi tests). `list_to_binary` - is iolist-aware (`[1, <<2,3>>, [4, [5]]]` → `<<1,2,3,4,5>>`); round-trip - `list_to_binary(binary_to_list(B)) =:= B` holds. Step 3b on-disk segment - writer is unblocked if it uses byte ints directly. Still parked: - `atom_to_list`/`integer_to_list` return SX-strings (an opaque OCaml-string - type), not Erlang charlists; `$X` char literals decode to `nil` in - `parse-number`. Both still block code that wants Erlang-idiomatic - `[$h,$i | T]` patterns on atom/integer names. +1. **Term codec** (`3b`/`3c`) — **substrate fixes #1 + #2 done 2026-06-04:** + `erlang:binary_to_list/1` and `erlang:list_to_binary/1` are registered + in `lib/erlang/runtime.sx` (`list_to_binary` is iolist-aware); the + tokenizer's `$X` branch now emits the decimal char code, so `[$h, $i | T]` + patterns and `list_to_binary([$f,$e,$d])` work end-to-end. 750/750 + conformance, +9 ffi + +12 eval tests. Step 3b on-disk segment writer + has a complete byte-level term ↔ binary path. Still parked (low priority + for Milestone 1): `atom_to_list`/`integer_to_list` return SX-strings + (an opaque OCaml-string type), not Erlang charlists — only blocks code + that wants charlist arithmetic on atom/integer names. 2. **SX-source eval bridge** — There's no BIF that lets Erlang call into the SX evaluator on a parsed source string. Blocks evaluating the `:schema` / diff --git a/plans/fed-sx-milestone-1.md b/plans/fed-sx-milestone-1.md index ac9e3920..089e2c95 100644 --- a/plans/fed-sx-milestone-1.md +++ b/plans/fed-sx-milestone-1.md @@ -200,7 +200,7 @@ verify_signature(Activity, ActorState) -> - [ ] **3b** — *Parked behind substrate gap (see Blockers below).* Term codec + on-disk persistence: serializer/parser writing each activity as a JSONL-style line; restart-resumes-tip from the segment file. - [ ] **3c** — Segment rotation at size threshold + gen_server-mediated concurrent appends. -**Blockers (Step 3b) — byte-level path resolved 2026-06-04:** `binary_to_list/1` and `list_to_binary/1` are now registered Erlang BIFs in `lib/erlang/runtime.sx` (Step 3b substrate fix, +9 ffi tests, 738/738 conformance). `list_to_binary` is iolist-aware: accepts nested cons of integer bytes (0-255) and/or binaries; `binary_to_list` returns a proper Erlang charlist of integers. Round-trip verified: `list_to_binary(binary_to_list(B)) =:= B`. On-disk segment writer (3b) can now build segment bytes from `[Header, IoListPayload]` and reconstruct on read — option (c) of the original workaround menu is now cheap. Still parked: `atom_to_list/1`/`integer_to_list/1` return SX strings rather than Erlang charlists, and `$X` char literals decode to `nil` in `parse-number`. Neither blocks the on-disk format if the encoding uses byte ints directly (no string→list coercion); both still block code that wants to write Erlang-idiomatic `[$h,$i | T]` patterns. 3b on-disk implementation is unblocked; revisit the remaining two gaps if a downstream Step requires charlist arithmetic on atom/integer names. +**Blockers (Step 3b) — byte-level path resolved 2026-06-04:** `binary_to_list/1` and `list_to_binary/1` are now registered Erlang BIFs in `lib/erlang/runtime.sx` (Step 3b substrate fix, +9 ffi tests, 738/738 conformance). `list_to_binary` is iolist-aware: accepts nested cons of integer bytes (0-255) and/or binaries; `binary_to_list` returns a proper Erlang charlist of integers. Round-trip verified: `list_to_binary(binary_to_list(B)) =:= B`. On-disk segment writer (3b) can now build segment bytes from `[Header, IoListPayload]` and reconstruct on read — option (c) of the original workaround menu is now cheap. `$X` char literals now decode correctly **as of 2026-06-04**: the Erlang tokenizer's `(= ch "$")` branch (`lib/erlang/tokenizer.sx`) now emits the decimal char code as the token value instead of the raw `$X` text (which `parse-number` couldn't decode → nil). Plain chars use `char->integer` of the first char; the standard escape table (`\n=10 \t=9 \r=13 \s=32 \b=8 \e=27 \f=12 \v=11 \d=127 \0=0 \\=92 \"=34 \'=39`) handles `$\X` forms. So `[$h, $i | T]` patterns and `list_to_binary([$f,$e,$d])` both work end-to-end. +12 eval tests, 750/750. Combined with 3b's `binary_to_list`/`list_to_binary`, Erlang code can now read/write byte sequences and string-shaped char lists fluently. Still parked: `atom_to_list/1`/`integer_to_list/1` return SX strings rather than Erlang charlists — only blocks code that wants to do `[$0+N | _]` arithmetic on integer-to-string output or `[Lower | _]` on atom names; downstream Steps in this milestone don't need it. **Deliverables:** @@ -1003,6 +1003,7 @@ A few things still under-specified; resolve as work begins. Newest first. One line per sub-deliverable commit. Erlang conformance gate (`bash lib/erlang/conformance.sh`) must remain 729/729 on every entry. +- **2026-06-04** — Step 3b substrate fix #2: `$X` char-literal decoding. Patched the Erlang tokenizer's `(= ch "$")` branch in `lib/erlang/tokenizer.sx` to emit the decimal char code as the integer token value instead of the raw `$X` source text (which `parse-number` couldn't decode → nil). Plain `$c` uses `char->integer` of the first char; `$\C` consults the standard Erlang escape table (`\n=10 \t=9 \r=13 \s=32 \b=8 \e=27 \f=12 \v=11 \d=127 \0=0 \\=92 \"=34 \'=39`). End-of-file after `$` decodes to 0 defensively. Probes: `$A→65`, `$0→48`, `$\n→10`, `$\\→92`, `[$h,$i]` → cons of 104/105, `list_to_binary([$f,$e,$d])` → `<<102,101,100>>`. +12 eval tests (single chars, each escape, list/binary composition with previous BIFs). Combined with substrate fix #1, Erlang code in fed-sx-m1 can now write `[$h, $i | T]` patterns AND construct/deconstruct binaries — a full term-codec primitive set. Erlang conformance **750/750** (eval 385→397). Plan Blockers note updated; remaining `atom_to_list`/`integer_to_list` charlist gap noted as low-priority for Milestone 1. - **2026-06-04** — Step 3b substrate fix: registered `erlang:binary_to_list/1` and `erlang:list_to_binary/1` in `lib/erlang/runtime.sx` — the byte-level half of the term-codec gap. `binary_to_list` returns a proper Erlang charlist (`er-mk-cons` chain of byte ints). `list_to_binary` is iolist-aware via a recursive `er-iolist-walk!` that accepts nil / cons / binary / integer 0-255 and flattens nested iolists (e.g. `[1, <<2,3>>, [4, [5]]]` → `<<1,2,3,4,5>>`); out-of-range bytes or non-iolist elements raise `error:badarg`. Round-trip verified: `list_to_binary(binary_to_list(B)) =:= B`. +9 ffi tests (length, hd, empty→[], flat byte_size, nested-iolist, round-trip, 3 badarg paths). On-disk segment writer (3b) now has a complete `[Header | IoListPayload] → Binary` path; the remaining two substrate gaps (`atom_to_list`/`integer_to_list` as Erlang charlists, `$X` char-literal decoding) are still parked but no longer block 3b implementation if the encoding uses byte ints directly. Erlang conformance **738/738** (ffi 28→37). Plan Blockers note for Step 3b updated to reflect the partial resolution. - **2026-05-28** — Step 4f-consolidate: `bootstrap:start/3(ActorId, KeySpec, ActorState)` brings up the full kernel substrate in one call — starts the registry gen_server, populates it from the canonical genesis bundle (31 entries across 7 kinds), then starts nx_kernel. Returns the kernel Pid (gen_server convention in this port returns raw Pid not `{ok, Pid}`). Tests verify whereis(nx_kernel), per-kind counts (3/10/7/3/3/2/3), registry lookup of a known entry (`create`), publish + log_tip advance. `next/tests/bootstrap_start.sh` 10/10. Erlang conformance 729/729. - **2026-05-28** — Step 7d-pure: `next/kernel/sandbox.erl` — `eval_pure/2(Fun, Arg)` and `eval_pure/3(Fun, Activity, State)`. try/catch envelope returns `{ok, Result}` on success and `{error, {Class, Reason}}` for each of the three exception classes (throw, error, exit). The 3-arity variant matches the projection-fold shape so the scheduler can wrap fold bodies. Port note: this Erlang implementation catches by explicit class names rather than the open `Class:Reason` pattern — wrappers enumerate `throw:Reason / error:Reason / exit:Reason` explicitly. Real gas budget + IO denial + env-stripping lands with SX-source eval; the wrapper API doesn't change. `next/tests/sandbox_eval.sh` 13/13. Erlang conformance 729/729.