Files
hakorune/lang/src/compiler/parser/expr/parser_expr_box.hako

357 lines
10 KiB
Plaintext
Raw Normal View History

// Moved from apps/selfhost-compiler/boxes/parser/expr/parser_expr_box.hako
// ParserExprBox — expression parser coordinator
// Responsibility: Parse expressions and delegate to specialized boxes
// API: parse(src, i, ctx) -> JSON (delegates to parse_expr2)
fix(vm): implement StringBox.lastIndexOf + PHI bug fix + Stage-B compiler完全動作 🎉 ## 🎯 主要修正 ### 1️⃣ StringBox.lastIndexOf実装 (Stage-B compiler blocker解消) - **問題**: `lang/src/compiler/parser/parser_box.hako:85`で`lastIndexOf`使用も未実装 - **修正**: `src/backend/mir_interpreter/handlers/boxes_string.rs:51-60`に追加 - **実装**: `rfind()`で最後の出現位置を検索、-1でnot found表現 ### 2️⃣ VM SSA/PHI bug完全修正 (ループ内メソッド呼び出し) - **原因**: メソッド内ループ×外側ループ呼び出しでPHI生成失敗 - **修正箇所**: - `src/mir/loop_builder.rs`: Exit PHI生成実装 - `src/mir/phi_core/loop_phi.rs`: PHI incoming修正 - `src/mir/phi_core/common.rs`: ユーティリティ追加 ### 3️⃣ カナリアテスト追加 - **新規**: `tools/smokes/v2/profiles/quick/core/vm_nested_loop_method_call.sh` - **構成**: Level 0/5b/5a/5 (段階的バグ検出) - **結果**: 全テストPASS、Level 5で`[SUCCESS] VM SSA/PHI bug FIXED!`表示 ### 4️⃣ using連鎖解決修正 - **問題**: `using sh_core`が子モジュールに伝播しない - **修正**: 6ファイルに明示的`using`追加 - compiler_stageb.hako, parser_box.hako - parser_stmt_box.hako, parser_control_box.hako - parser_exception_box.hako, parser_expr_box.hako ### 5️⃣ ParserBoxワークアラウンド - **問題**: `skip_ws()`メソッド呼び出しでVMバグ発生 - **対応**: 3箇所でインライン化(PHI修正までの暫定対応) ## 🎉 動作確認 ```bash # Stage-B compiler完全動作! $ bash /tmp/run_stageb.sh {"version":0,"kind":"Program","body":[{"type":"Return","expr":{"type":"Int","value":42}}]} # カナリアテスト全PASS $ bash tools/smokes/v2/profiles/quick/core/vm_nested_loop_method_call.sh [PASS] level0_simple_loop (.008s) [PASS] level5b_inline_nested_loop (.007s) [PASS] level5a_method_no_loop (.007s) [SUCCESS] Level 5: VM SSA/PHI bug FIXED! [PASS] level5_method_with_loop (VM BUG canary) (.008s) ``` ## 🏆 技術的ハイライト 1. **最小再現**: Level 0→5bの段階的テストでバグパターン完全特定 2. **Task先生調査**: 表面エラーから真因(lastIndexOf未実装)発見 3. **適切実装**: `boxes_string.rs`のStringBox専用ハンドラに追加 4. **完全検証**: Stage-B compilerでJSON出力成功を実証 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-02 10:58:09 +09:00
using sh_core as StringHelpers // Required: using chain resolution not implemented
using lang.compiler.parser.scan.parser_number_scan_box
using lang.compiler.parser.expr.parser_peek_box
using lang.compiler.parser.expr.parser_literal_box
static box ParserExprBox {
parse_number2(src, i, ctx) {
local pair = ParserNumberScanBox.scan_int(src, i)
local at = pair.lastIndexOf("@")
local json = pair.substring(0, at)
local pos = i
if at >= 0 { pos = ctx.to_int(pair.substring(at+1, pair.length())) }
ctx.gpos_set(pos)
return json
}
parse_string2(src, i, ctx) {
local n = src.length()
local j = i + 1
local out = ""
local guard = 0
local max = 200000
loop(j < n) {
if guard > max { break }
guard = guard + 1
local ch = src.substring(j, j+1)
if ch == "\"" {
j = j + 1
ctx.gpos_set(j)
return "{\"type\":\"Str\",\"value\":\"" + ctx.esc_json(out) + "\"}"
}
if ch == "\\" && j + 1 < n {
local nx = src.substring(j+1, j+2)
if nx == "\"" { out = out + "\"" j = j + 2 }
else { if nx == "\\" { out = out + "\\" j = j + 2 }
else { if nx == "n" { out = out + "\n" j = j + 2 }
else { if nx == "r" { out = out + "\r" j = j + 2 }
else { if nx == "t" { out = out + "\t" j = j + 2 }
else { if nx == "u" && j + 5 < n { out = out + src.substring(j, j+6) j = j + 6 }
else { out = out + nx j = j + 2 } } } } } }
} else {
out = out + ch
j = j + 1
}
}
ctx.gpos_set(j)
return "{\"type\":\"Str\",\"value\":\"" + ctx.esc_json(out) + "\"}"
}
parse_factor2(src, i, ctx) {
local j = ctx.skip_ws(src, i)
if j >= src.length() {
ctx.gpos_set(j)
return "{\"type\":\"Int\",\"value\":0}"
}
if ctx.starts_with_kw(src, j, "true") == 1 {
ctx.gpos_set(j + 4)
return "{\"type\":\"Bool\",\"value\":true}"
}
if ctx.starts_with_kw(src, j, "false") == 1 {
ctx.gpos_set(j + 5)
return "{\"type\":\"Bool\",\"value\":false}"
}
if ctx.starts_with_kw(src, j, "null") == 1 {
ctx.gpos_set(j + 4)
return "{\"type\":\"Null\"}"
}
// Peek expression: delegate to ParserPeekBox
if ctx.starts_with_kw(src, j, "peek") == 1 {
j = j + 4
return ParserPeekBox.parse(src, j, ctx)
}
local ch = src.substring(j, j+1)
// Parenthesized
if ch == "(" {
local inner = me.parse_expr2(src, j + 1, ctx)
local k = ctx.gpos_get()
k = ctx.skip_ws(src, k)
if src.substring(k, k+1) == ")" { k = k + 1 }
ctx.gpos_set(k)
return inner
}
// String literal
if ch == "\"" {
return me.parse_string2(src, j, ctx)
}
// Map literal: delegate to ParserLiteralBox
if ch == "{" {
return ParserLiteralBox.parse_map(src, j, ctx)
}
// Array literal: delegate to ParserLiteralBox
if ch == "[" {
return ParserLiteralBox.parse_array(src, j, ctx)
}
// new Class(args)
if ctx.starts_with_kw(src, j, "new") == 1 {
local p = ctx.skip_ws(src, j + 3)
local idp = ctx.read_ident2(src, p)
local at = idp.lastIndexOf("@")
local cls = idp.substring(0, at)
local k = ctx.to_int(idp.substring(at+1, idp.length()))
k = ctx.skip_ws(src, k)
if src.substring(k, k+1) == "(" { k = k + 1 }
local args_and_pos = me.parse_args2(src, k, ctx)
local at2 = args_and_pos.lastIndexOf("@")
local args_json = args_and_pos.substring(0, at2)
k = ctx.to_int(args_and_pos.substring(at2+1, args_and_pos.length()))
k = ctx.skip_ws(src, k)
if src.substring(k, k+1) == ")" { k = k + 1 }
ctx.gpos_set(k)
return "{\"type\":\"New\",\"class\":\"" + cls + "\",\"args\":" + args_json + "}"
}
// Identifier / Call / Method chain
if ctx.is_alpha(ch) {
local idp = ctx.read_ident2(src, j)
local at = idp.lastIndexOf("@")
local name = idp.substring(0, at)
local k = ctx.to_int(idp.substring(at+1, idp.length()))
local node = "{\"type\":\"Var\",\"name\":\"" + name + "\"}"
local cont2 = 1
loop(cont2 == 1) {
k = ctx.skip_ws(src, k)
local tch = src.substring(k, k+1)
if tch == "(" {
k = k + 1
local args_and_pos = me.parse_args2(src, k, ctx)
local at2 = args_and_pos.lastIndexOf("@")
local args_json = args_and_pos.substring(0, at2)
k = ctx.to_int(args_and_pos.substring(at2+1, args_and_pos.length()))
k = ctx.skip_ws(src, k)
if src.substring(k, k+1) == ")" { k = k + 1 }
node = "{\"type\":\"Call\",\"name\":\"" + name + "\",\"args\":" + args_json + "}"
} else {
if tch == "." {
k = k + 1
k = ctx.skip_ws(src, k)
local midp = ctx.read_ident2(src, k)
local at3 = midp.lastIndexOf("@")
local mname = midp.substring(0, at3)
k = ctx.to_int(midp.substring(at3+1, midp.length()))
k = ctx.skip_ws(src, k)
if src.substring(k, k+1) == "(" { k = k + 1 }
local args2 = me.parse_args2(src, k, ctx)
local at4 = args2.lastIndexOf("@")
local args_json2 = args2.substring(0, at4)
k = ctx.to_int(args2.substring(at4+1, args2.length()))
k = ctx.skip_ws(src, k)
if src.substring(k, k+1) == ")" { k = k + 1 }
node = "{\"type\":\"Method\",\"recv\":" + node + ",\"method\":\"" + mname + "\",\"args\":" + args_json2 + "}"
} else {
cont2 = 0
}
}
}
ctx.gpos_set(k)
return node
}
// Fallback: number
return me.parse_number2(src, j, ctx)
}
parse_unary2(src, i, ctx) {
local j = ctx.skip_ws(src, i)
if src.substring(j, j+1) == "-" {
local rhs = me.parse_factor2(src, j + 1, ctx)
j = ctx.gpos_get()
local zero = "{\"type\":\"Int\",\"value\":0}"
ctx.gpos_set(j)
return "{\"type\":\"Binary\",\"op\":\"-\",\"lhs\":" + zero + ",\"rhs\":" + rhs + "}"
}
return me.parse_factor2(src, j, ctx)
}
parse_term2(src, i, ctx) {
local lhs = me.parse_unary2(src, i, ctx)
local j = ctx.gpos_get()
local cont = 1
loop(cont == 1) {
j = ctx.skip_ws(src, j)
if j >= src.length() {
cont = 0
} else {
local op = src.substring(j, j+1)
if op != "*" && op != "/" {
cont = 0
} else {
local rhs = me.parse_unary2(src, j+1, ctx)
j = ctx.gpos_get()
lhs = "{\"type\":\"Binary\",\"op\":\"" + op + "\",\"lhs\":" + lhs + ",\"rhs\":" + rhs + "}"
}
}
}
ctx.gpos_set(j)
return lhs
}
parse_sum2(src, i, ctx) {
local lhs = me.parse_term2(src, i, ctx)
local j = ctx.gpos_get()
local cont = 1
loop(cont == 1) {
j = ctx.skip_ws(src, j)
if j >= src.length() {
cont = 0
} else {
local op = src.substring(j, j+1)
if op != "+" && op != "-" {
cont = 0
} else {
local rhs = me.parse_term2(src, j+1, ctx)
j = ctx.gpos_get()
lhs = "{\"type\":\"Binary\",\"op\":\"" + op + "\",\"lhs\":" + lhs + ",\"rhs\":" + rhs + "}"
}
}
}
ctx.gpos_set(j)
return lhs
}
parse_compare2(src, i, ctx) {
local lhs = me.parse_sum2(src, i, ctx)
local j = ctx.gpos_get()
j = ctx.skip_ws(src, j)
local two = src.substring(j, j+2)
local one = src.substring(j, j+1)
local op = ""
if two == "==" || two == "!=" || two == "<=" || two == ">=" {
op = two
j = j + 2
} else {
if one == "<" || one == ">" {
op = one
j = j + 1
}
}
if op == "" {
ctx.gpos_set(j)
return lhs
}
local rhs = me.parse_sum2(src, j, ctx)
j = ctx.gpos_get()
ctx.gpos_set(j)
return "{\"type\":\"Compare\",\"op\":\"" + op + "\",\"lhs\":" + lhs + ",\"rhs\":" + rhs + "}"
}
parse_expr2(src, i, ctx) {
local lhs = me.parse_compare2(src, i, ctx)
local j = ctx.gpos_get()
local cont = 1
loop(cont == 1) {
j = ctx.skip_ws(src, j)
local two = src.substring(j, j+2)
if two != "&&" && two != "||" {
cont = 0
} else {
local rhs = me.parse_compare2(src, j+2, ctx)
j = ctx.gpos_get()
lhs = "{\"type\":\"Logical\",\"op\":\"" + two + "\",\"lhs\":" + lhs + ",\"rhs\":" + rhs + "}"
}
}
j = ctx.skip_ws(src, j)
if src.substring(j, j+1) == "?" {
j = j + 1
j = ctx.skip_ws(src, j)
local then_expr = me.parse_expr2(src, j, ctx)
j = ctx.gpos_get()
j = ctx.skip_ws(src, j)
if src.substring(j, j+1) == ":" { j = j + 1 }
j = ctx.skip_ws(src, j)
local else_expr = me.parse_expr2(src, j, ctx)
j = ctx.gpos_get()
if else_expr.length() == 0 { else_expr = "{\"type\":\"Int\",\"value\":0}" }
ctx.gpos_set(j)
return "{\"type\":\"Ternary\",\"cond\":" + lhs + ",\"then\":" + then_expr + ",\"else\":" + else_expr + "}"
}
ctx.gpos_set(j)
return lhs
}
parse_args2(src, i, ctx) {
local j = ctx.skip_ws(src, i)
local n = src.length()
local out = "["
j = ctx.skip_ws(src, j)
if j < n && src.substring(j, j+1) == ")" {
return "[]@" + ctx.i2s(j)
}
// first argument
local e = me.parse_expr2(src, j, ctx)
j = ctx.gpos_get()
out = out + e
// subsequent arguments with guard
local cont_args = 1
local guard = 0
local max = 100000
loop(cont_args == 1) {
if guard > max { cont_args = 0 } else { guard = guard + 1 }
local before = j
j = ctx.skip_ws(src, j)
if j < n && src.substring(j, j+1) == "," {
j = j + 1
j = ctx.skip_ws(src, j)
e = me.parse_expr2(src, j, ctx)
j = ctx.gpos_get()
out = out + "," + e
} else {
cont_args = 0
}
if j == before { cont_args = 0 }
}
out = out + "]"
return out + "@" + ctx.i2s(j)
}
}