refactor(funcscanner): Region+next_i パターン統一 & SSA テスト追加

**FuncScanner .hako 側改善**:
- scan_all_boxes を Region + next_i 形式に統一(continue 多発による SSA/PHI 複雑さ削減)
- インデント修正(タブ→スペース統一)
- デバッグ print 削除

**SSA テスト追加**:
- lang/src/compiler/tests/funcscanner_scan_methods_min.hako
- src/tests/mir_funcscanner_ssa.rs (scan_methods & fib_min SSA デバッグテスト)

**Phase 25.3 ドキュメント**:
- docs/development/roadmap/phases/phase-25.3-funcscanner/ 追加

**関連**: Phase 25.3 FuncScanner 箱化準備作業

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
nyash-codex
2025-11-20 06:38:43 +09:00
parent 9bdf2ff069
commit 3a82633924
15 changed files with 558 additions and 126 deletions

View File

@ -12,90 +12,91 @@ static box FuncScannerBox {
return me._scan_methods(source, box_name, 1, 0)
}
// Scan all static box definitions and collect their methods.
method scan_all_boxes(source) {
// source が null の場合はスキャン対象がないので空配列を返すよ。
if source == null { return new ArrayBox() }
local defs = new ArrayBox()
local s = "" + source
// Scan all static box definitions and collect their methods.
method scan_all_boxes(source) {
// source が null の場合はスキャン対象がないので空配列を返すよ。
if source == null { return new ArrayBox() }
local defs = new ArrayBox()
local s = "" + source
local n = s.length()
// DEBUG: 一時的に常時トレースを有効化StageB fib 用の挙動観測)
print("[funcscan/scan_all_boxes] source_len=" + ("" + n))
local i = 0
local in_str = 0
local esc = 0
local in_line = 0
local in_block = 0
// Region + next_i 形式に統一して、ループ本体での多重 continue による
// SSA/PHI の複雑さを下げる。
loop(i < n) {
local next_i = i + 1
local ch = s.substring(i, i + 1)
if in_line == 1 {
if ch == "\n" { in_line = 0 }
i = i + 1
continue
}
if in_block == 1 {
} else if in_block == 1 {
if ch == "*" && i + 1 < n && s.substring(i + 1, i + 2) == "/" {
in_block = 0
i = i + 2
continue
next_i = i + 2
}
} else if in_str == 1 {
if esc == 1 {
esc = 0
} else if ch == "\\" {
esc = 1
} else if ch == "\"" {
in_str = 0
}
} else {
if ch == "\"" {
in_str = 1
} else if ch == "/" && i + 1 < n {
local ch2 = s.substring(i + 1, i + 2)
if ch2 == "/" {
in_line = 1
next_i = i + 2
} else if ch2 == "*" {
in_block = 1
next_i = i + 2
}
} else {
if i + 3 <= n && s.substring(i, i + 3) == "box" && me._kw_boundary_before(s, i) == 1 && me._kw_boundary_after(s, i + 3) == 1 {
local cursor = i + 3
cursor = me._skip_whitespace(s, cursor)
local name_start = cursor
loop(cursor < n) {
local ch_name = s.substring(cursor, cursor + 1)
if me._is_ident_char(ch_name) == 1 { cursor = cursor + 1 } else { break }
}
local box_name = s.substring(name_start, cursor)
if box_name == "" {
next_i = cursor
} else {
cursor = me._skip_whitespace(s, cursor)
if cursor >= n || s.substring(cursor, cursor + 1) != "{" {
next_i = cursor
} else {
local close_idx = me._find_matching_brace(s, cursor)
if close_idx < 0 {
// マッチしない場合はこれ以上スキャンしても意味がないのでループ終了。
i = n
next_i = n
} else {
local body = s.substring(cursor + 1, close_idx)
local skip_main = 0
if box_name == "Main" { skip_main = 1 }
local include_me = 0
if box_name != "Main" { include_me = 1 }
local defs_box = me._scan_methods(body, box_name, skip_main, include_me)
me._append_defs(defs, defs_box)
next_i = close_idx + 1
}
}
}
}
}
i = i + 1
continue
}
if in_str == 1 {
if esc == 1 { esc = 0 i = i + 1 continue }
if ch == "\\" { esc = 1 i = i + 1 continue }
if ch == "\"" { in_str = 0 i = i + 1 continue }
i = i + 1
continue
}
if ch == "\"" { in_str = 1 i = i + 1 continue }
if ch == "/" && i + 1 < n {
local ch2 = s.substring(i + 1, i + 2)
if ch2 == "/" { in_line = 1 i = i + 2 continue }
if ch2 == "*" { in_block = 1 i = i + 2 continue }
}
// DEBUG: "box" キーワード候補をチェックStageB fib 用)
if i + 3 <= n {
local candidate = s.substring(i, i + 3)
if candidate == "box" {
print("[funcscan/box_candidate] i=" + ("" + i) + " candidate=" + candidate)
}
}
if s.substring(i, i + 3) == "box" && me._kw_boundary_before(s, i) == 1 && me._kw_boundary_after(s, i + 3) == 1 {
local cursor = i + 3
cursor = me._skip_whitespace(s, cursor)
local name_start = cursor
loop(cursor < n) {
local ch_name = s.substring(cursor, cursor + 1)
if me._is_ident_char(ch_name) == 1 { cursor = cursor + 1 } else { break }
}
local box_name = s.substring(name_start, cursor)
if box_name == "" {
i = cursor
continue
}
cursor = me._skip_whitespace(s, cursor)
if cursor >= n || s.substring(cursor, cursor + 1) != "{" {
i = cursor
continue
}
local close_idx = me._find_matching_brace(s, cursor)
if close_idx < 0 { break }
local body = s.substring(cursor + 1, close_idx)
local skip_main = 0
if box_name == "Main" { skip_main = 1 }
local include_me = 0
if box_name != "Main" { include_me = 1 }
local defs_box = me._scan_methods(body, box_name, skip_main, include_me)
me._append_defs(defs, defs_box)
i = close_idx + 1
continue
}
i = i + 1
i = next_i
}
return defs
}
@ -164,7 +165,8 @@ static box FuncScannerBox {
// Extract params (minimal: comma-separated names)
local params_str = s.substring(lparen + 1, rparen)
local params = me._parse_params(params_str)
// static helper として扱うme ではなく FuncScannerBox に直接委譲)。
local params = FuncScannerBox._parse_params(params_str)
if include_me == 1 {
local first = ""
if params.length() > 0 { first = "" + params.get(0) }
@ -235,8 +237,9 @@ static box FuncScannerBox {
// Extract method body (inside braces)
local method_body = s.substring(lbrace + 1, rbrace)
method_body = me._strip_comments(method_body)
method_body = me._trim(method_body)
// コメント除去と trim も static helper として扱う。
method_body = FuncScannerBox._strip_comments(method_body)
method_body = FuncScannerBox._trim(method_body)
// Parse method body to JSON (statement list)
local body_json = null
@ -304,14 +307,18 @@ static box FuncScannerBox {
method _find_matching_brace(s, open_idx) {
local n = s.length()
local i = open_idx
if open_idx < 0 || open_idx >= n { return -1 }
// open_idx 以降だけを対象に走査することで、前方の構造に依存しないようにする。
local subs = s.substring(open_idx, n)
local m = subs.length()
local i = 0
local depth = 0
local in_str = 0
local esc = 0
local in_line = 0
local in_block = 0
loop(i < n) {
local ch = s.substring(i, i + 1)
loop(i < m) {
local ch = subs.substring(i, i + 1)
if in_line == 1 {
if ch == "\n" { in_line = 0 }
i = i + 1
@ -334,8 +341,8 @@ static box FuncScannerBox {
continue
}
if ch == "\"" { in_str = 1 i = i + 1 continue }
if ch == "/" && i + 1 < n {
local ch2 = s.substring(i + 1, i + 2)
if ch == "/" && i + 1 < m {
local ch2 = subs.substring(i + 1, i + 2)
if ch2 == "/" { in_line = 1 i = i + 2 continue }
if ch2 == "*" { in_block = 1 i = i + 2 continue }
}
@ -347,7 +354,7 @@ static box FuncScannerBox {
if ch == "}" {
depth = depth - 1
i = i + 1
if depth == 0 { return i - 1 }
if depth == 0 { return open_idx + i - 1 }
continue
}
i = i + 1

View File

@ -0,0 +1,43 @@
// funcscanner_scan_methods_min.hako — FuncScannerBox._scan_methods minimal harness
//
// 目的:
// - static box TestBox/Main を含むソースから TestBox.body 部分だけを切り出し、
// FuncScannerBox._scan_methods(source, "TestBox", 0, 1) を直接呼び出す。
// - params 部分のパースと _parse_params/_trim の呼び出しが SSA 的に安全であることを確認する。
//
// 振る舞い:
// - fib と同等の TestBox/Main を src に埋め込む。
// - FuncScannerBox._find_matching_brace で TestBox の '{'〜'}' 範囲を取得。
// - 本文だけを body1 として抜き出し、FuncScannerBox._scan_methods に渡す。
// - defs.len と各定義の box/name をログに出力するStageB 側と比較しやすくする)。
using lang.compiler.entry.func_scanner as FuncScannerBox
static box Main {
method main(args) {
local src = "static box TestBox {\n method fib(n) {\n local i = 0\n local a = 0\n local b = 1\n loop(i < n) {\n local t = a + b\n a = b\n b = t\n i = i + 1\n }\n return b\n }\n}\n\nstatic box Main {\n method main(args) {\n local t = new TestBox()\n return t.fib(6)\n }\n}\n"
// TestBox 本体の brace 範囲を FuncScannerBox の実装で検出
local open1 = 19
local close1 = FuncScannerBox._find_matching_brace(src, open1)
print("[scan_methods] brace1 open=" + ("" + open1) + " close=" + ("" + close1))
if close1 < 0 { return 1 }
// "box TestBox {" の直後から close1 直前までを body1 として切り出す
local body1 = src.substring(open1 + 1, close1)
print("[scan_methods] body1_len=" + ("" + body1.length()))
// FuncScannerBox._scan_methods を直接呼び出してメソッド定義を抽出
local defs1 = FuncScannerBox._scan_methods(body1, "TestBox", 0, 1)
local n1 = defs1.length()
print("[scan_methods] defs1.len=" + ("" + n1))
local i = 0
loop(i < n1) {
local d = defs1.get(i)
print("[scan_methods] def1[" + ("" + i) + "] box=" + ("" + d.get("box")) + " name=" + ("" + d.get("name")))
i = i + 1
}
return 0
}
}