diff --git a/tools/hakorune_emit_mir.sh b/tools/hakorune_emit_mir.sh index 68da7407..9cf51a93 100644 --- a/tools/hakorune_emit_mir.sh +++ b/tools/hakorune_emit_mir.sh @@ -24,13 +24,6 @@ else ROOT="$(cd "$SCRIPT_DIR/.." && pwd)" fi -RAW_KEEP="${NYASH_EMIT_MIR_KEEP_RAW:-0}" -RAW_DIR="${NYASH_EMIT_MIR_RAW_DIR:-$ROOT/logs/emit_mir}" -if [ "$RAW_KEEP" = "1" ]; then - mkdir -p "$RAW_DIR" 2>/dev/null || RAW_KEEP=0 -fi -timestamp_now() { date +%Y%m%d_%H%M%S; } - # Resolve nyash/hakorune binary via test_runner helper (ensures consistent env) if [ ! -f "$IN" ]; then echo "[FAIL] input not found: $IN" >&2 @@ -46,212 +39,14 @@ if [ -z "${NYASH_BIN:-}" ]; then fi fi -# Allow legacy 'nyash' binary when invoked via this helper (Stage0 bootstrap). -# This keeps Stage‑B / MirBuilder scripts working while the main CLI migrates to 'hakorune'. -export HAKO_ALLOW_NYASH="${HAKO_ALLOW_NYASH:-1}" -export NYASH_ALLOW_NYASH="${NYASH_ALLOW_NYASH:-1}" - -# Store CODE in temp file to avoid subshell expansion issues -CODE_TMP=$(mktemp --suffix=.hako) -trap 'rm -f "$CODE_TMP" || true' EXIT -cp "$IN" "$CODE_TMP" - -# Stage1 using resolver: prepare modules list from nyash.toml -if [ -z "${HAKO_STAGEB_MODULES_LIST:-}" ]; then - HAKO_STAGEB_MODULES_LIST=$( - python3 - "$ROOT" <<'PY' 2>/dev/null -import sys -from pathlib import Path -root = Path(sys.argv[1]) -toml_path = root / "nyash.toml" -try: - lines = toml_path.read_text(encoding="utf-8").splitlines() -except Exception: - print("", end="") - raise SystemExit(0) -collect = False -entries = [] -for raw in lines: - line = raw.strip() - if not line or line.startswith("#"): - continue - if line.startswith("["): - collect = (line == "[modules]") - continue - if not collect: - continue - if "=" not in line: - continue - key, value = line.split("=", 1) - key = key.strip().strip('"') - value = value.split("#", 1)[0].strip() - if value.startswith('"') and value.endswith('"'): - value = value[1:-1] - if not key or not value: - continue - entries.append(f"{key}={value}") -print("|||".join(entries), end="") -PY - ) || HAKO_STAGEB_MODULES_LIST="" - export HAKO_STAGEB_MODULES_LIST -fi -export HAKO_STAGEB_APPLY_USINGS="${HAKO_STAGEB_APPLY_USINGS:-1}" - -# Phase 21.8: Extract using imports and build JSON map for MirBuilder -# This enables MirBuilder to recognize static box references like MatI64, IntArrayCore, MirBuilderBox. -IMPORTS_JSON="{}" -if [ "${NYASH_ENABLE_USING:-1}" = "1" ] || [ "${HAKO_ENABLE_USING:-1}" = "1" ]; then - # Delegate parsing to Python for robustness: - # - Handle `using ns.path.Type as Alias` → Alias - # - Handle alias-less `using ns.path.Type` → Type - # - Ignore path-style using (`"path.hako"`, `./`, `/`, `*.hako`) - IMPORTS_JSON=$(python3 - "$CODE_TMP" <<'PY' 2>/dev/null || echo "{}" -import sys, json -path = sys.argv[1] -try: - text = open(path, "r", encoding="utf-8").read().splitlines() -except Exception: - print("{}", end="") - raise SystemExit(0) - -imports = {} -for raw in text: - line = raw.lstrip() - if not line.startswith("using "): - continue - # Strip trailing line comment - if "//" in line: - line = line.split("//", 1)[0] - line = line.strip() - if not line.startswith("using "): - continue - body = line[len("using "):].strip().rstrip(";").strip() - if not body: - continue - alias = None - # Split by " as " - lower = body - idx = lower.find(" as ") - if idx >= 0: - target = body[:idx].strip() - alias = body[idx + 4 :].strip() - else: - target = body - if not target: - continue - # Skip path-style targets - if target.startswith('"') or target.startswith("./") or target.startswith("/") or target.endswith(".hako") or target.endswith(".nyash"): - continue - if alias is None: - # Derive alias from last segment of namespace - alias = target.split(".")[-1].strip() - if not alias: - continue - # Very small ident check (letters/digits/_) - if not all((c.isalnum() or c == "_") for c in alias): - continue - imports[alias] = alias - -print(json.dumps(imports), end="") -PY -) - if [ -z "$IMPORTS_JSON" ]; then - IMPORTS_JSON="{}" - fi -fi -export HAKO_MIRBUILDER_IMPORTS="$IMPORTS_JSON" - -# Run direct emit with optional raw capture (label helps identify caller) -run_direct_emit() { - local label="$1" out_path="$2" in_path="$3" - local rc=0 - if [ "$RAW_KEEP" = "1" ]; then - local tmp_out - tmp_out=$(mktemp --suffix .emit_direct_raw) - "$NYASH_BIN" --emit-mir-json "$out_path" "$in_path" >"$tmp_out" 2>&1 || rc=$? - local ts=$(timestamp_now) - local log_path="$RAW_DIR/direct_emit_${label}_${ts}_$$.log" - { - local raw_len=$(wc -c < "$tmp_out" | tr -d ' ') - echo "[emit/raw] label=$label rc=$rc raw_len=$raw_len" - cat "$tmp_out" - } > "$log_path" 2>/dev/null || true - rm -f "$tmp_out" 2>/dev/null || true - else - "$NYASH_BIN" --emit-mir-json "$out_path" "$in_path" >/dev/null 2>&1 || rc=$? - fi - if [ $rc -ne 0 ]; then - # Quick stderr summary to avoid opening the raw file - local raw_len=0 - if [ -f "${tmp_out:-}" ]; then - raw_len=$(wc -c < "${tmp_out:-}" | tr -d ' ') - echo "[emit/direct] rc=$rc raw_len=$raw_len (head 100 lines)" >&2 - head -n 100 "${tmp_out:-}" >&2 || true - else - echo "[emit/direct] rc=$rc (no tmp_out captured)" >&2 - fi - fi - return $rc -} - -# Check if FORCE jsonfrag mode is requested (bypasses Stage-B entirely) -if [ "${HAKO_MIR_BUILDER_LOOP_FORCE_JSONFRAG:-0}" = "1" ]; then - # Extract limit from code using grep/awk - limit=$(cat "$CODE_TMP" | grep -o '[0-9]\+' | head -1 || echo "10") - # Generate minimal while-form MIR(JSON) directly (executable semantics) - # PHI incoming format: [[value_register, predecessor_block_id], ...] - echo "[emit/jsonfrag] FORCE min-loop MIR (dev-only)" >&2 - cat > "$OUT" </dev/null || true) - if [ -n "$result" ] && echo "$result" | grep -q '"kind".*"Program"'; then - echo "$result" - return 0 - fi - - # Try 2: Simple awk fallback - result=$(echo "$input" | awk '/^\{/,/^\}$/') - if [ -n "$result" ] && echo "$result" | grep -q '"kind".*"Program"'; then - echo "$result" - return 0 - fi - - # Try 3: Ruby fallback (if available) - if command -v ruby >/dev/null 2>&1; then - result=$(echo "$input" | ruby -e 'puts STDIN.read[/\{.*"kind".*"Program".*\}/m]' 2>/dev/null || true) - if [ -n "$result" ]; then - echo "$result" - return 0 - fi - fi - - # All fallbacks failed - return 1 -} - -# Helper: surface common Stage‑B / parser / using errors in a concise, friendly way. -diagnose_stageb_failure() { - local raw="$1" - # Stage‑3 local keyword misconfig - if printf '%s\n' "$raw" | grep -q "Undefined variable: local"; then - echo "[stageb/diagnose] Undefined variable: local" >&2 - echo "[stageb/hint] 'local' は Stage‑3 キーワードだよ。" >&2 - echo "[stageb/hint] NYASH_FEATURES=stage3 NYASH_FEATURES=stage3 を有効にするか、tools/hakorune_emit_mir.sh 経由で実行してね。" >&2 - fi - # Generic parse error - if printf '%s\n' "$raw" | grep -q "Parse error"; then - echo "[stageb/diagnose] Parse error detected in Stage‑B output." >&2 - echo "[stageb/hint] HAKO_SELFHOST_TRACE=1 を立ててもう一度実行すると、最初の 200 文字が表示されるよ。" >&2 - fi - # VM execution errors from Stage‑B itself (MIR builder / verifier side) - if printf '%s\n' "$raw" | grep -q "Invalid value: use of undefined value"; then - echo "[stageb/diagnose] VM reported 'use of undefined value' during Stage‑B execution." >&2 - echo "[stageb/hint] Stage‑B が生成した MIR に未定義レジスタ (%0 など) が含まれている可能性があるよ。" >&2 - echo "[stageb/hint] 詳細を確認するには NYASH_VM_VERIFY_MIR=1 を立てて compiler_stageb.hako を直接実行してね。" >&2 - echo "[stageb/hint] 代表的な原因と掘り先は docs/private/roadmap/phases/phase-20.33/DEBUG.md を参照してね (Stage1UsingResolverBox / FuncScannerBox 周り)。" >&2 - fi - # Using resolver issues (Stage‑B side) - local using_lines - using_lines=$(printf '%s\n' "$raw" | grep -E "\[using\] not found: " | sort -u || true) - if [ -n "$using_lines" ]; then - echo "[stageb/diagnose] Missing using modules detected (Stage‑B):" >&2 - echo "$using_lines" >&2 - echo "[stageb/hint] nyash.toml の [modules] に該当 Box を追加するか、HAKO_STAGEB_MODULES_LIST / HAKO_STAGEB_APPLY_USINGS を確認してね。" >&2 - fi -} - set +e -if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - code_len=$(wc -c < "$CODE_TMP" | tr -d ' ') - echo "[emit:trace] Stage-B: Starting parse of input (${code_len} chars)..." >&2 -fi - -stageb_raw_log="" -# Decide Stage-B entry (direct compiler_stageb or compiler.hako --stage-b) -stageb_target="$ROOT/lang/src/compiler/entry/compiler.hako" -stageb_extra=(--stage-b --stage3) -# Legacy: allow direct compiler_stageb.hako when explicitly requested -if [ "${NYASH_EMIT_USE_COMPILER:-1}" = "0" ]; then - stageb_target="$ROOT/lang/src/compiler/entry/compiler_stageb.hako" - stageb_extra=() -fi -# Optional: log which entry we picked -if [ "${NYASH_EMIT_MIR_TRACE:-0}" = "1" ]; then - echo "[emit/trace] stageb target=$stageb_target extra=${stageb_extra[*]:-}" >&2 -fi -# Run Stage-B with temp file (avoid subshell CODE variable expansion) -PROG_JSON_RAW=$(cd "$ROOT" && \ - NYASH_JSON_ONLY=${NYASH_JSON_ONLY:-1} NYASH_DISABLE_NY_COMPILER=${NYASH_DISABLE_NY_COMPILER:-1} HAKO_DISABLE_NY_COMPILER=${HAKO_DISABLE_NY_COMPILER:-1} \ - HAKO_STAGEB_FUNC_SCAN="${HAKO_STAGEB_FUNC_SCAN:-1}" \ - NYASH_FEATURES=stage3 NYASH_FEATURES=stage3 NYASH_PARSER_ALLOW_SEMICOLON=1 \ +PROG_JSON_OUT=$((cd "$ROOT" && \ + NYASH_JSON_ONLY=1 NYASH_DISABLE_NY_COMPILER=1 HAKO_DISABLE_NY_COMPILER=1 \ + HAKO_STAGEB_FUNC_SCAN="${HAKO_STAGEB_FUNC_SCAN:-}" \ + NYASH_PARSER_STAGE3=1 HAKO_PARSER_STAGE3=1 NYASH_PARSER_ALLOW_SEMICOLON=1 \ NYASH_ENABLE_USING=${NYASH_ENABLE_USING:-1} HAKO_ENABLE_USING=${HAKO_ENABLE_USING:-1} \ - "$NYASH_BIN" --backend vm "$stageb_target" -- "${stageb_extra[@]}" --source "$(cat "$CODE_TMP")" 2>&1) + "$NYASH_BIN" --backend vm "$ROOT/lang/src/compiler/entry/compiler_stageb.hako" -- --source "$CODE") 2>/dev/null | extract_program_json) rc=$? -stageb_rc=$rc - -# Optional raw trace to stderr for debugging extraction/filter問題 -if [ "${NYASH_EMIT_MIR_TRACE:-0}" = "1" ]; then - echo "[emit/trace] Stage-B raw len=${#PROG_JSON_RAW} rc=${stageb_rc}" >&2 - printf '%s\n' "$PROG_JSON_RAW" >&2 -fi - -if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - echo "[emit:trace] Stage-B: Raw output length=${#PROG_JSON_RAW} chars, rc=$rc" >&2 -fi - -# Extract Program JSON from raw output -PROG_JSON_OUT=$(extract_program_json "$PROG_JSON_RAW" 2>/dev/null || true) -extract_rc=$? -stageb_hit=$(printf '%s' "$PROG_JSON_OUT" | grep -c '"kind":"Program"' || true) -stageb_raw_len=${#PROG_JSON_RAW} -echo "[emit/stageb] rc_stageb=${stageb_rc} extract_rc=${extract_rc} raw_len=${stageb_raw_len} program_hits=${stageb_hit}" >&2 -if [ "$RAW_KEEP" = "1" ]; then - ts=$(timestamp_now) - stageb_raw_log="$RAW_DIR/stageb_emit_${ts}_$$.log" - { - echo "[emit/raw] cmd=${stageb_target##*/} rc_stageb=${stageb_rc} extract_rc=${extract_rc} raw_len=${stageb_raw_len} program_hits=${stageb_hit}" - echo "[emit/raw] src=$IN" - echo "[emit/raw] --- stdout+stderr ---" - printf '%s' "$PROG_JSON_RAW" - } > "$stageb_raw_log" 2>/dev/null || true - if [ $extract_rc -eq 0 ] && [ -n "$PROG_JSON_OUT" ]; then - printf '%s' "$PROG_JSON_OUT" > "$RAW_DIR/stageb_emit_${ts}_$$.program.json" 2>/dev/null || true - fi -fi - -if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - if [ $extract_rc -eq 0 ] && [ -n "$PROG_JSON_OUT" ]; then - echo "[emit:trace] Stage-B: SUCCESS - Generated Program(JSON) (${#PROG_JSON_OUT} chars)" >&2 - # Show first 200 chars for validation - prog_head=$(printf '%s' "$PROG_JSON_OUT" | head -c 200) - echo "[emit:trace] Stage-B: prog_json_head: $prog_head..." >&2 - else - echo "[emit:trace] Stage-B: FAILED - extract_rc=$extract_rc, output_len=${#PROG_JSON_OUT}" >&2 - if [ -n "$PROG_JSON_RAW" ]; then - echo "[emit:trace] Stage-B: Raw output first 200 chars:" >&2 - printf '%s' "$PROG_JSON_RAW" | head -c 200 >&2 - echo "" >&2 - fi - fi -fi - -# Update rc to reflect extraction result -stageb_ok=1 -if [ $extract_rc -ne 0 ] || [ -z "$PROG_JSON_OUT" ]; then - rc=1 - stageb_ok=0 -fi set -e # If Stage-B fails, skip to direct MIR emit paths (provider/legacy) -if [ $rc -ne 0 ] || [ -z "$PROG_JSON_OUT" ] || [ "$stageb_hit" -eq 0 ]; then - # Diagnose common Stage‑B errors before falling back - diagnose_stageb_failure "$PROG_JSON_RAW" +if [ $rc -ne 0 ] || [ -z "$PROG_JSON_OUT" ]; then # Stage-B not available - fall back to legacy CLI path directly # Skip the intermediate Program(JSON) step and emit MIR directly - echo "[emit/stageb] failed_or_empty stageb_ok=${stageb_ok} rc_stageb=${stageb_rc} extract_rc=${extract_rc} hits=${stageb_hit}" >&2 - if [ "${NYASH_EMIT_MIR_TRACE:-0}" = "1" ]; then - echo "[emit/stageb] raw_len=${stageb_raw_len}" >&2 - fi - direct_ok=0 - if HAKO_STAGEB_FUNC_SCAN="${HAKO_STAGEB_FUNC_SCAN:-1}" \ + if HAKO_STAGEB_FUNC_SCAN="${HAKO_STAGEB_FUNC_SCAN:-}" \ HAKO_MIR_BUILDER_FUNCS="${HAKO_MIR_BUILDER_FUNCS:-}" \ HAKO_MIR_BUILDER_CALL_RESOLVE="${HAKO_MIR_BUILDER_CALL_RESOLVE:-}" \ NYASH_JSON_SCHEMA_V1=${NYASH_JSON_SCHEMA_V1:-1} \ NYASH_MIR_UNIFIED_CALL=${NYASH_MIR_UNIFIED_CALL:-1} \ - run_direct_emit "fallback" "$OUT" "$IN"; then - direct_ok=1 + "$NYASH_BIN" --emit-mir-json "$OUT" "$IN" >/dev/null 2>&1; then echo "[OK] MIR JSON written (direct-emit): $OUT" exit 0 fi - echo "[emit/direct] failed rc_stageb=${stageb_rc} extract_rc=${extract_rc} direct_ok=${direct_ok} stageb_hits=${stageb_hit}" >&2 echo "[FAIL] Stage-B and direct MIR emit both failed" >&2 exit 1 fi # Quick validation for Program(JSON v0) if ! printf '%s' "$PROG_JSON_OUT" | grep -q '"kind"\s*:\s*"Program"'; then - # Invalid Program JSON - fall back to direct emit（事前に簡単な診断を出す） - diagnose_stageb_failure "$PROG_JSON_RAW" - direct_ok=0 - if HAKO_STAGEB_FUNC_SCAN="${HAKO_STAGEB_FUNC_SCAN:-1}" \ + # Invalid Program JSON - fall back to direct emit + if HAKO_STAGEB_FUNC_SCAN="${HAKO_STAGEB_FUNC_SCAN:-}" \ HAKO_MIR_BUILDER_FUNCS="${HAKO_MIR_BUILDER_FUNCS:-}" \ HAKO_MIR_BUILDER_CALL_RESOLVE="${HAKO_MIR_BUILDER_CALL_RESOLVE:-}" \ NYASH_JSON_SCHEMA_V1=${NYASH_JSON_SCHEMA_V1:-1} \ NYASH_MIR_UNIFIED_CALL=${NYASH_MIR_UNIFIED_CALL:-1} \ - run_direct_emit "invalid_program" "$OUT" "$IN"; then - direct_ok=1 + "$NYASH_BIN" --emit-mir-json "$OUT" "$IN" >/dev/null 2>&1; then echo "[OK] MIR JSON written (direct-emit-fallback): $OUT" exit 0 fi - echo "[emit/direct] invalid_program rc_stageb=${stageb_rc} extract_rc=${extract_rc} direct_ok=${direct_ok} stageb_hits=${stageb_hit}" >&2 echo "[FAIL] Stage‑B output invalid and direct emit failed" >&2 exit 1 fi @@ -588,7 +235,7 @@ HCODE set +e (cd "$ROOT" && \ NYASH_DISABLE_PLUGINS=1 NYASH_FILEBOX_MODE="core-ro" \ - NYASH_FEATURES=stage3 NYASH_FEATURES=stage3 NYASH_PARSER_ALLOW_SEMICOLON=1 \ + NYASH_PARSER_STAGE3=1 HAKO_PARSER_STAGE3=1 NYASH_PARSER_ALLOW_SEMICOLON=1 \ HAKO_BUILDER_PROGRAM_JSON="$prog_json" \ "$NYASH_BIN" --backend vm "$tmp_hako" 2>&1 | tee "$tmp_stdout" >/dev/null) local rc=$? @@ -599,79 +246,7 @@ HCODE local mir mir=$(awk '/\[MIR_OUT_BEGIN\]/{flag=1;next}/\[MIR_OUT_END\]/{flag=0}flag' "$tmp_stdout") if [ -z "$mir" ]; then return 1; fi - # Write raw MIR JSON first printf '%s' "$mir" > "$out_path" - - # Optional AOT prep stage (run_json; no FileBox) - # Trigger when HAKO_APPLY_AOT_PREP=1 or when fast/hoist/collections_hot are requested. - if [ "${HAKO_APPLY_AOT_PREP:-0}" = "1" ] || [ "${NYASH_AOT_COLLECTIONS_HOT:-0}" = "1" ] || [ "${NYASH_LLVM_FAST:-0}" = "1" ] || [ "${NYASH_MIR_LOOP_HOIST:-0}" = "1" ]; then - if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - echo "[provider/emit:trace] Applying AotPrep.run_json to MIR JSON..." >&2 - fi - _prep_hako=$(mktemp --suffix .hako) - cat > "$_prep_hako" <<'HAKO' -using selfhost.llvm.ir.aot_prep as AotPrepBox -static box Main { method main(args) { - local src = env.get("HAKO_PREP_INPUT") - if src == null || src == "" { print("[prep:skip:empty]"); return 0 } - local out = AotPrepBox.run_json(src) - print("[PREP_OUT_BEGIN]") - print(out) - print("[PREP_OUT_END]") - return 0 -} } -HAKO - # Read MIR JSON and pass via env; capture between markers - _prep_stdout=$(mktemp) - _prep_stderr=$(mktemp) - set +e - HAKO_PREP_INPUT="$(cat "$out_path")" \ - NYASH_FILEBOX_MODE=core-ro \ - # AotPrep(run_json) は自己ホストVMで JSON を1回走査するだけなので、既定ではステップ上限なし（0）で実行する。 - # 必要に応じて HAKO_VM_MAX_STEPS / NYASH_VM_MAX_STEPS を明示上書き可能。 - HAKO_VM_MAX_STEPS="${HAKO_VM_MAX_STEPS:-0}" NYASH_VM_MAX_STEPS="${NYASH_VM_MAX_STEPS:-0}" \ - NYASH_FEATURES=stage3 NYASH_FEATURES=stage3 NYASH_PARSER_ALLOW_SEMICOLON=1 \ - NYASH_ENABLE_USING=1 HAKO_ENABLE_USING=1 HAKO_USING_RESOLVER_FIRST=1 \ - NYASH_AOT_COLLECTIONS_HOT=${NYASH_AOT_COLLECTIONS_HOT:-0} NYASH_LLVM_FAST=${NYASH_LLVM_FAST:-0} NYASH_MIR_LOOP_HOIST=${NYASH_MIR_LOOP_HOIST:-0} NYASH_AOT_MAP_KEY_MODE=${NYASH_AOT_MAP_KEY_MODE:-auto} \ - NYASH_AOT_NUMERIC_CORE=${NYASH_AOT_NUMERIC_CORE:-0} NYASH_AOT_NUMERIC_CORE_TRACE=${NYASH_AOT_NUMERIC_CORE_TRACE:-0} \ - NYASH_JSON_ONLY=${NYASH_JSON_ONLY:-1} \ - "$NYASH_BIN" --backend vm "$_prep_hako" >"$_prep_stdout" 2>"$_prep_stderr" - _rc=$? - set -e - if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - echo "[provider/emit:trace] AotPrep runner rc=$_rc" >&2 - fi - if [ $_rc -eq 0 ] && grep -q "\[PREP_OUT_BEGIN\]" "$_prep_stdout" && grep -q "\[PREP_OUT_END\]" "$_prep_stdout"; then - awk '/\[PREP_OUT_BEGIN\]/{flag=1;next}/\[PREP_OUT_END\]/{flag=0}flag' "$_prep_stdout" > "$out_path" - [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ] && echo "[provider/emit:trace] AotPrep applied (run_json)" >&2 - # Optional: surface CollectionsHot trace lines for diagnostics when requested - if [ "${NYASH_AOT_CH_TRACE:-0}" = "1" ]; then - if command -v rg >/dev/null 2>&1; then - rg -n '^\[aot/collections_hot\]' "$_prep_stdout" >&2 || true - else - grep '^\[aot/collections_hot\]' "$_prep_stdout" >&2 || true - fi - fi - # Optional: surface NumericCore trace lines for diagnostics when requested - if [ "${NYASH_AOT_NUMERIC_CORE_TRACE:-0}" = "1" ]; then - if command -v rg >/dev/null 2>&1; then - rg -n '^\[aot/numeric_core\]' "$_prep_stdout" >&2 || true - else - grep '^\[aot/numeric_core\]' "$_prep_stdout" >&2 || true - fi - fi - else - if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - echo "[provider/emit:trace] AotPrep skipped or failed (run_json) rc=$_rc" >&2 - if [ -s "$_prep_stderr" ]; then - echo "[provider/emit:trace] AotPrep stderr (tail):" >&2 - tail -n 60 "$_prep_stderr" >&2 || true - fi - fi - fi - rm -f "$_prep_hako" "$_prep_stdout" "$_prep_stderr" 2>/dev/null || true - fi - echo "[OK] MIR JSON written (delegate:provider): $out_path" return 0 } @@ -730,33 +305,20 @@ HCODE local prog_len=${#prog_json} local loop_count=$(printf '%s' "$prog_json" | grep -o '"type":"Loop"' 2>/dev/null | wc -l | tr -d ' \n') local cmp_count=$(printf '%s' "$prog_json" | grep -o '"type":"Compare"' 2>/dev/null | wc -l | tr -d ' \n') - local array_count=$(printf '%s' "$prog_json" | grep -o '"type":"MethodCall"' 2>/dev/null | wc -l | tr -d ' \n') loop_count=${loop_count:-0} cmp_count=${cmp_count:-0} - array_count=${array_count:-0} local cwd="$(pwd)" local toml_status="absent" if [ -f "$ROOT/nyash.toml" ]; then toml_status="present" fi - echo "[builder/selfhost-first:trace] builder_box=$builder_box prog_json_len=$prog_len tokens=Loop:$loop_count,Compare:$cmp_count,MethodCall:$array_count cwd=$cwd nyash.toml=$toml_status" >&2 - # Show first 200 chars of Program(JSON) for structural validation - local prog_head=$(printf '%s' "$prog_json" | head -c 200) - echo "[builder/selfhost-first:trace] prog_json_head: $prog_head..." >&2 + echo "[builder/selfhost-first:trace] builder_box=$builder_box prog_json_len=$prog_len tokens=Loop:$loop_count,Compare:$cmp_count cwd=$cwd nyash.toml=$toml_status" >&2 fi set +e # Run from repo root to ensure nyash.toml is available for using resolution # Capture both stdout and stderr (2>&1) instead of discarding stderr - local tmp_stderr; tmp_stderr=$(mktemp) - trap 'rm -f "$tmp_hako" "$tmp_stdout" "$tmp_stderr" || true' RETURN - - if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - echo "[builder/selfhost-first:exec] Starting builder execution..." >&2 - fi - (cd "$ROOT" && \ - HAKO_SELFHOST_NO_DELEGATE=1 \ HAKO_MIR_BUILDER_INTERNAL=1 HAKO_MIR_BUILDER_REGISTRY=1 \ HAKO_MIR_BUILDER_TRACE="${HAKO_SELFHOST_TRACE:-}" \ HAKO_MIR_BUILDER_LOOP_JSONFRAG="${HAKO_MIR_BUILDER_LOOP_JSONFRAG:-}" \ @@ -767,57 +329,28 @@ HCODE HAKO_MIR_BUILDER_NORMALIZE_TAG="${HAKO_MIR_BUILDER_NORMALIZE_TAG:-}" \ HAKO_MIR_BUILDER_DEBUG="${HAKO_MIR_BUILDER_DEBUG:-}" \ NYASH_DISABLE_PLUGINS="${NYASH_DISABLE_PLUGINS:-0}" NYASH_FILEBOX_MODE="core-ro" HAKO_PROVIDER_POLICY="safe-core-first" \ - NYASH_ENABLE_USING=1 HAKO_ENABLE_USING=1 HAKO_USING_RESOLVER_FIRST=1 \ - NYASH_FEATURES=stage3 NYASH_FEATURES=stage3 NYASH_PARSER_ALLOW_SEMICOLON=1 \ + NYASH_ENABLE_USING=1 HAKO_ENABLE_USING=1 \ + NYASH_PARSER_STAGE3=1 HAKO_PARSER_STAGE3=1 NYASH_PARSER_ALLOW_SEMICOLON=1 \ NYASH_USE_NY_COMPILER=0 HAKO_USE_NY_COMPILER=0 NYASH_DISABLE_NY_COMPILER=1 HAKO_DISABLE_NY_COMPILER=1 \ NYASH_MACRO_DISABLE=1 HAKO_MACRO_DISABLE=1 \ - # Builder 実行時は Step budget を既定で「無制限（0）」にしておく（大きな Program(JSON) でも上限で落とさない）。 - # 無限ループ疑いの診断時は HAKO_VM_MAX_STEPS/NYASH_VM_MAX_STEPS を明示上書きして使う想定。 - HAKO_VM_MAX_STEPS="${HAKO_VM_MAX_STEPS:-0}" NYASH_VM_MAX_STEPS="${NYASH_VM_MAX_STEPS:-0}" \ HAKO_BUILDER_PROGRAM_JSON="$prog_json" \ - NYASH_VM_DUMP_MERGED_HAKO="${NYASH_VM_DUMP_MERGED_HAKO:-${HAKO_SELFHOST_DUMP_MERGED_HAKO:-0}}" \ - NYASH_VM_DUMP_MERGED_HAKO_PATH="${NYASH_VM_DUMP_MERGED_HAKO_PATH:-${HAKO_SELFHOST_DUMP_MERGED_HAKO_PATH:-}}" \ - "$NYASH_BIN" --backend vm "$tmp_hako" 2>"$tmp_stderr" | tee "$tmp_stdout" >/dev/null) + "$NYASH_BIN" --backend vm "$tmp_hako" 2>&1 | tee "$tmp_stdout" >/dev/null) local rc=$? set -e - if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - echo "[builder/selfhost-first:exec] Builder execution completed with rc=$rc" >&2 - fi - - # Enhanced failure diagnostics with comprehensive logging + # Enhanced failure diagnostics if [ $rc -ne 0 ]; then - if [ "${HAKO_SELFHOST_NO_DELEGATE:-0}" = "1" ] || [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then + if [ "${HAKO_SELFHOST_NO_DELEGATE:-0}" = "1" ]; then echo "[builder/selfhost-first:fail:child:rc=$rc]" >&2 - echo "[builder/selfhost-first:fail:detail] First 20 lines of output:" >&2 - head -n 20 "$tmp_stdout" >&2 || true echo "[builder/selfhost-first:fail:detail] Last 80 lines of output:" >&2 tail -n 80 "$tmp_stdout" >&2 || true - if [ -s "$tmp_stderr" ]; then - echo "[builder/selfhost-first:fail:stderr] First 20 lines:" >&2 - head -n 20 "$tmp_stderr" >&2 || true - echo "[builder/selfhost-first:fail:stderr] Last 40 lines:" >&2 - tail -n 40 "$tmp_stderr" >&2 || true - # Pretty diagnostics for missing using modules - USING_MISSING=$(cat "$tmp_stdout" "$tmp_stderr" 2>/dev/null | grep -Eo "\[using\] not found: '[^']+'" | sort -u || true) - if [ -n "$USING_MISSING" ]; then - echo "[builder/selfhost-first:diagnose] Missing using modules detected:" >&2 - echo "$USING_MISSING" >&2 - echo "[builder/selfhost-first:diagnose] Hint: enable resolver-first (HAKO_USING_RESOLVER_FIRST=1) and ensure nyash.toml maps these modules." >&2 - echo "[builder/selfhost-first:diagnose] Example entries (nyash.toml [modules]):" >&2 - echo " \"selfhost.shared.json.core.json_canonical\" = \"lang/src/shared/json/json_canonical_box.hako\"" >&2 - echo " \"selfhost.shared.common.common_imports\" = \"lang/src/shared/common/common_imports.hako\"" >&2 - fi - fi fi # Don't return immediately - check for fallback below fi if [ $rc -eq 0 ] && ! grep -q "\[builder/selfhost-first:ok\]" "$tmp_stdout"; then - if [ "${HAKO_SELFHOST_NO_DELEGATE:-0}" = "1" ] || [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then + if [ "${HAKO_SELFHOST_NO_DELEGATE:-0}" = "1" ]; then echo "[builder/selfhost-first:fail:no-ok-marker]" >&2 - echo "[builder/selfhost-first:fail:detail] First 20 lines of output:" >&2 - head -n 20 "$tmp_stdout" >&2 || true echo "[builder/selfhost-first:fail:detail] Last 80 lines of output:" >&2 tail -n 80 "$tmp_stdout" >&2 || true fi @@ -826,17 +359,13 @@ HCODE # Try min builder fallback if enabled and initial builder failed if [ "${HAKO_SELFHOST_TRY_MIN:-0}" = "1" ] && [ $rc -ne 0 ] && [ "$builder_box" != "hako.mir.builder.min" ]; then - if [ "${HAKO_SELFHOST_NO_DELEGATE:-0}" = "1" ] || [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then + if [ "${HAKO_SELFHOST_NO_DELEGATE:-0}" = "1" ]; then echo "[builder/selfhost-first:trying-min-fallback]" >&2 fi # Retry with min builder HAKO_MIR_BUILDER_BOX="hako.mir.builder.min" try_selfhost_builder "$prog_json" "$out_path" - local fallback_rc=$? - if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - echo "[builder/selfhost-first:min-fallback:rc=$fallback_rc]" >&2 - fi - return $fallback_rc + return $? fi # Return original failure if no fallback or if fallback not triggered @@ -847,18 +376,6 @@ HCODE local mir mir=$(awk '/\[MIR_OUT_BEGIN\]/{flag=1;next}/\[MIR_OUT_END\]/{flag=0}flag' "$tmp_stdout") if [ -z "$mir" ]; then return 1; fi - # Surface key builder tags (multi-carrier detectionなど) when trace is enabled, - # so that v2 smokes can reliably grep them without生 stdout 全量を流す必要がない。 - if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - if grep -q "\[mirbuilder/internal/loop:multi_carrier:" "$tmp_stdout" 2>/dev/null; then - echo "[builder/selfhost-first:trace:multi_carrier] detected" >&2 - grep "\[mirbuilder/internal/loop:multi_carrier:" "$tmp_stdout" >&2 || true - fi - if grep -q "\[funcs/basic:loop.multi_carrier\]" "$tmp_stdout" 2>/dev/null; then - echo "[builder/selfhost-first:trace:funcs:loop.multi_carrier]" >&2 - grep "\[funcs/basic:loop.multi_carrier\]" "$tmp_stdout" >&2 || true - fi - fi printf '%s' "$mir" > "$out_path" echo "[OK] MIR JSON written (selfhost-first): $out_path" return 0 @@ -882,121 +399,22 @@ static box Main { method main(args) { } } HCODE local tmp_stdout; tmp_stdout=$(mktemp) - local tmp_stderr; tmp_stderr=$(mktemp) - trap 'rm -f "$tmp_hako" "$tmp_stdout" "$tmp_stderr" || true' RETURN - - if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - echo "[provider/emit:trace] Starting provider emit..." >&2 - fi - + trap 'rm -f "$tmp_hako" "$tmp_stdout" || true' RETURN set +e (cd "$ROOT" && \ NYASH_DISABLE_PLUGINS="${NYASH_DISABLE_PLUGINS:-0}" NYASH_FILEBOX_MODE="core-ro" \ - NYASH_FEATURES=stage3 NYASH_FEATURES=stage3 NYASH_PARSER_ALLOW_SEMICOLON=1 \ + NYASH_PARSER_STAGE3=1 HAKO_PARSER_STAGE3=1 NYASH_PARSER_ALLOW_SEMICOLON=1 \ HAKO_BUILDER_PROGRAM_JSON="$prog_json" \ - NYASH_ENABLE_USING=1 HAKO_ENABLE_USING=1 HAKO_USING_RESOLVER_FIRST=1 \ - "$NYASH_BIN" --backend vm "$tmp_hako" 2>"$tmp_stderr" | tee "$tmp_stdout" >/dev/null) + "$NYASH_BIN" --backend vm "$tmp_hako" 2>&1 | tee "$tmp_stdout" >/dev/null) local rc=$? set -e - - if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - echo "[provider/emit:trace] Provider execution completed with rc=$rc" >&2 - fi - if [ $rc -ne 0 ] || ! grep -q "\[provider/emit:ok\]" "$tmp_stdout"; then - if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - echo "[provider/emit:fail:rc=$rc]" >&2 - if [ -s "$tmp_stderr" ]; then - echo "[provider/emit:fail:stderr] First 20 lines:" >&2 - head -n 20 "$tmp_stderr" >&2 || true - echo "[provider/emit:fail:stderr] Last 40 lines:" >&2 - tail -n 40 "$tmp_stderr" >&2 || true - fi - echo "[provider/emit:fail:stdout] Last 40 lines:" >&2 - tail -n 40 "$tmp_stdout" >&2 || true - USING_MISSING=$(cat "$tmp_stdout" "$tmp_stderr" 2>/dev/null | grep -Eo "\[using\] not found: '[^']+'" | sort -u || true) - if [ -n "$USING_MISSING" ]; then - echo "[provider/emit:diagnose] Missing using modules detected:" >&2 - echo "$USING_MISSING" >&2 - echo "[provider/emit:diagnose] Hint: enable resolver-first (HAKO_USING_RESOLVER_FIRST=1) and ensure nyash.toml maps these modules." >&2 - fi - fi return 1 fi - local mir mir=$(awk '/\[MIR_OUT_BEGIN\]/{flag=1;next}/\[MIR_OUT_END\]/{flag=0}flag' "$tmp_stdout") - if [ -z "$mir" ]; then - if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - echo "[provider/emit:fail:no-mir-output]" >&2 - fi - return 1 - fi - - # Write raw MIR JSON first + if [ -z "$mir" ]; then return 1; fi printf '%s' "$mir" > "$out_path" - - # Apply AotPrep via run_json when enabled - if [ "${HAKO_APPLY_AOT_PREP:-0}" = "1" ] || [ "${NYASH_AOT_COLLECTIONS_HOT:-0}" = "1" ] || [ "${NYASH_LLVM_FAST:-0}" = "1" ] || [ "${NYASH_MIR_LOOP_HOIST:-0}" = "1" ]; then - [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ] && echo "[provider/emit:trace] Applying AotPrep(run_json)..." >&2 - local aot_runner; aot_runner=$(mktemp --suffix=.hako) - cat > "$aot_runner" << 'EOF' -using selfhost.llvm.ir.aot_prep as AotPrepBox -static box Main { method main(args) { - local src = env.get("HAKO_PREP_INPUT") - if src == null || src == "" { print("[prep:skip:empty]"); return 0 } - local out = AotPrepBox.run_json(src) - print("[PREP_OUT_BEGIN]") - print(out) - print("[PREP_OUT_END]") - return 0 -} } -EOF - local aot_rc=0 - local prep_stdout; prep_stdout=$(mktemp) - local prep_stderr; prep_stderr=$(mktemp) - set +e - HAKO_PREP_INPUT="$(cat "$out_path")" \ - NYASH_FILEBOX_MODE=core-ro \ - NYASH_FEATURES=stage3 NYASH_FEATURES=stage3 NYASH_PARSER_ALLOW_SEMICOLON=1 \ - NYASH_ENABLE_USING=1 HAKO_ENABLE_USING=1 HAKO_USING_RESOLVER_FIRST=1 \ - NYASH_AOT_COLLECTIONS_HOT=${NYASH_AOT_COLLECTIONS_HOT:-0} NYASH_LLVM_FAST=${NYASH_LLVM_FAST:-0} NYASH_MIR_LOOP_HOIST=${NYASH_MIR_LOOP_HOIST:-0} NYASH_AOT_MAP_KEY_MODE=${NYASH_AOT_MAP_KEY_MODE:-auto} \ - NYASH_AOT_NUMERIC_CORE=${NYASH_AOT_NUMERIC_CORE:-0} NYASH_AOT_NUMERIC_CORE_TRACE=${NYASH_AOT_NUMERIC_CORE_TRACE:-0} \ - HAKO_VM_MAX_STEPS="${HAKO_VM_MAX_STEPS:-0}" NYASH_VM_MAX_STEPS="${NYASH_VM_MAX_STEPS:-0}" \ - "$NYASH_BIN" --backend vm "$aot_runner" >"$prep_stdout" 2>"$prep_stderr" - aot_rc=$? - set -e - if [ $aot_rc -eq 0 ] && grep -q "\[PREP_OUT_BEGIN\]" "$prep_stdout" && grep -q "\[PREP_OUT_END\]" "$prep_stdout"; then - awk '/\[PREP_OUT_BEGIN\]/{flag=1;next}/\[PREP_OUT_END\]/{flag=0}flag' "$prep_stdout" > "$out_path" - [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ] && echo "[prep:ok] AotPrep applied (run_json)" >&2 - # Surface numeric_core trace lines when requested（provider経路でも [aot/numeric_core] を見えるようにする） - if [ "${NYASH_AOT_NUMERIC_CORE_TRACE:-0}" = "1" ]; then - if command -v rg >/devnull 2>&1; then - rg -n '^\[aot/numeric_core\]' "$prep_stdout" >&2 || true - else - grep '^\[aot/numeric_core\]' "$prep_stdout" >&2 || true - fi - fi - # Optional strict post-check: after AotPrep(run_json) the MIR JSON is expected - # to have MatI64.mul_naive lowered to Call when NYASH_AOT_NUMERIC_CORE=1. - if [ "${NYASH_AOT_NUMERIC_CORE_STRICT:-0}" = "1" ]; then - if rg -q '"op":"boxcall".*"method":"mul_naive"' "$out_path"; then - echo "[prep/numeric_core/strict] NYASH_AOT_NUMERIC_CORE_STRICT=1 but boxcall(\"mul_naive\") remains after AotPrep.run_json; inspect numeric_core.hako patterns." >&2 - return 1 - fi - fi - else - if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - echo "[prep:warn] AotPrep failed (rc=$aot_rc), using original MIR" >&2 - if [ -s "$prep_stderr" ]; then - echo "[prep:stderr:tail]" >&2 - tail -n 60 "$prep_stderr" >&2 || true - fi - fi - fi - rm -f "$aot_runner" "$prep_stdout" "$prep_stderr" 2>/dev/null || true - fi - echo "[OK] MIR JSON written (delegate:provider): $out_path" return 0 } @@ -1008,35 +426,19 @@ if [ "${HAKO_MIR_BUILDER_LOOP_FORCE_JSONFRAG:-0}" = "1" ]; then fi if [ "${HAKO_SELFHOST_BUILDER_FIRST:-0}" = "1" ]; then - # Prefer Stage1 CLI (hakorune) when available to avoid Stage-3 parser issues - stage1_cli_bin="${HAKO_STAGE1_CLI:-$ROOT/lang/bin/hakorune}" - if [ -x "$stage1_cli_bin" ]; then - prog_tmp=$(mktemp --suffix .json) - printf '%s' "$PROG_JSON_OUT" > "$prog_tmp" - if "$stage1_cli_bin" emit mir-json --from-program-json "$prog_tmp" -o "$OUT" --quiet >/dev/null 2>&1 && [ -s "$OUT" ]; then - rm -f "$prog_tmp" || true - echo "[OK] MIR JSON written (selfhost-first:stage1-cli): $OUT" - exit 0 - fi - rm -f "$prog_tmp" || true - if [ "${HAKO_SELFHOST_TRACE:-0}" = "1" ]; then - echo "[selfhost-first:stage1-cli] failed (binary: $stage1_cli_bin), falling back to legacy builder" >&2 - fi - fi if try_selfhost_builder "$PROG_JSON_OUT" "$OUT"; then exit 0 fi - # Phase 25.1b: selfhost-first モードでは MirBuilder のフォールバックは禁止。 - # selfhost builder が失敗した時点で非0終了とし、provider 経路には委譲しない。 - echo "[FAIL] selfhost-first failed (MirBuilder) and delegate is disabled in HAKO_SELFHOST_BUILDER_FIRST=1 mode" >&2 - exit 1 + if [ "${HAKO_SELFHOST_NO_DELEGATE:-0}" = "1" ]; then + echo "[FAIL] selfhost-first failed and delegate disabled" >&2 + exit 1 + fi fi # Dev: force JsonFrag minimal loop even on provider-first path if [ "${HAKO_MIR_BUILDER_LOOP_FORCE_JSONFRAG:-0}" = "1" ]; then - # Extract limit from Program(JSON) or source file - limit=$(printf '%s' "$PROG_JSON_OUT" | grep -o '"type":"Int","value":[0-9]*' | head -1 | grep -o '[0-9]*$' || cat "$CODE_TMP" | grep -o '[0-9]\+' | head -1 || echo "10") - echo "[emit/jsonfrag] provider-force min-loop MIR (dev-only)" >&2 + # Extract limit from Program(JSON) + limit=$(printf '%s' "$PROG_JSON_OUT" | grep -o '"type":"Int","value":[0-9]*' | head -1 | grep -o '[0-9]*$' || echo "10") cat > "$OUT" <