485 lines
16 KiB
Plaintext
485 lines
16 KiB
Plaintext
================================================================================
|
||
Phase 11.9: 文法統一化とAI連携強化 - Grammar as Single Source of Truth
|
||
================================================================================
|
||
|
||
【概要】
|
||
Nyashの文法知識が分散している問題を解決し、AIがNyashコードを正しく書けるよう
|
||
文法定義を一元化する。ANCPと連携して、AIとの効率的な通信も実現。
|
||
|
||
【現在の問題】
|
||
1. 文法知識の分散
|
||
- Tokenizer: キーワードのハードコード定義
|
||
- Parser: TokenTypeに基づく個別実装
|
||
- Interpreter: AST実行の独自ロジック
|
||
- MIR Builder: 変換ルールの散在
|
||
|
||
2. AIの文法エラー
|
||
- "while" vs "loop" の混同
|
||
- "this" vs "me" の間違い
|
||
- セミコロン使用などの古い構文
|
||
|
||
3. 文法の揺らぎ
|
||
- 同じ意味の複数表現が存在
|
||
- 非推奨構文の明確な定義なし
|
||
- 統一的な検証メカニズムの欠如
|
||
|
||
================================================================================
|
||
1. 文法統一化アーキテクチャ
|
||
================================================================================
|
||
|
||
■ 3層構造の導入
|
||
┌─────────────────────────────────────┐
|
||
│ Grammar Definition Layer (YAML/TOML) │ ← 唯一の真実
|
||
├─────────────────────────────────────┤
|
||
│ Grammar Runtime (Rust) │ ← 共通実装
|
||
├─────────────────────────────────────┤
|
||
│ Components (Tokenizer/Parser/etc) │ ← 利用者
|
||
└─────────────────────────────────────┘
|
||
|
||
■ 統一文法定義ファイル
|
||
nyash-grammar-v1.yaml
|
||
├─ keywords（予約語定義）
|
||
├─ syntax_rules（構文規則）
|
||
├─ semantic_rules（意味規則）
|
||
├─ deprecated（非推奨定義）
|
||
└─ ai_hints（AI向けヒント）
|
||
|
||
================================================================================
|
||
2. 文法定義仕様（YAML形式）
|
||
================================================================================
|
||
|
||
# nyash-grammar-v1.yaml
|
||
version: "1.0"
|
||
language: "nyash"
|
||
|
||
keywords:
|
||
# デリゲーション関連
|
||
delegation:
|
||
from:
|
||
token: FROM
|
||
category: delegation
|
||
semantic: parent_method_call
|
||
syntax: "from <parent>.<method>(<args>)"
|
||
example: "from Animal.init(name)"
|
||
deprecated_aliases: ["super", "parent", "base"]
|
||
ai_hint: "Always use 'from' for parent calls"
|
||
|
||
# 自己参照
|
||
self_reference:
|
||
me:
|
||
token: ME
|
||
category: object_reference
|
||
semantic: current_instance
|
||
syntax: "me.<field>"
|
||
example: "me.name = value"
|
||
deprecated_aliases: ["this", "self", "@"]
|
||
ai_hint: "Use 'me' for self-reference, never 'this'"
|
||
|
||
# 制御フロー
|
||
control_flow:
|
||
loop:
|
||
token: LOOP
|
||
category: control_flow
|
||
semantic: conditional_iteration
|
||
syntax: "loop(<condition>) { <body> }"
|
||
example: "loop(i < 10) { i = i + 1 }"
|
||
deprecated_aliases: ["while", "for"]
|
||
ai_hint: "Only 'loop' for iteration"
|
||
|
||
# クラス定義
|
||
class_definition:
|
||
box:
|
||
token: BOX
|
||
category: declaration
|
||
semantic: class_declaration
|
||
syntax: "box <name> from <parent>? { <body> }"
|
||
example: "box Cat from Animal { }"
|
||
deprecated_aliases: ["class", "struct", "type"]
|
||
ai_hint: "Use 'box' for all class definitions"
|
||
|
||
syntax_rules:
|
||
# Box定義ルール
|
||
box_definition:
|
||
pattern: "box <identifier> (from <identifier_list>)? { <box_body> }"
|
||
constraints:
|
||
- name: init_comma_required
|
||
rule: "init block fields must be comma-separated"
|
||
valid: "init { name, age }"
|
||
invalid: "init { name age }"
|
||
|
||
- name: constructor_exclusive
|
||
rule: "Only one of birth/pack/init() can be defined"
|
||
valid: "birth() { }"
|
||
invalid: "birth() { } pack() { }"
|
||
|
||
# デリゲーション呼び出し
|
||
delegation_call:
|
||
pattern: "from <identifier>.<identifier>(<expression_list>?)"
|
||
constraints:
|
||
- name: parent_must_exist
|
||
rule: "Parent must be declared in 'from' clause"
|
||
|
||
- name: method_resolution
|
||
rule: "Method lookup follows delegation chain"
|
||
|
||
semantic_rules:
|
||
# 変数宣言
|
||
variable_declaration:
|
||
local_scope:
|
||
keyword: "local"
|
||
rule: "Variables must be declared before use"
|
||
scope: "function"
|
||
|
||
implicit_global:
|
||
rule: "Undeclared assignment creates global (deprecated)"
|
||
warning: "Use 'local' for clarity"
|
||
|
||
# メソッド解決
|
||
method_resolution:
|
||
order:
|
||
1: "Current instance methods"
|
||
2: "Delegated parent methods"
|
||
3: "Error: method not found"
|
||
|
||
# AI向け特別セクション
|
||
ai_training:
|
||
# 正しいパターン
|
||
correct_patterns:
|
||
- pattern: "loop(condition) { }"
|
||
category: "iteration"
|
||
|
||
- pattern: "me.field = value"
|
||
category: "assignment"
|
||
|
||
- pattern: "from Parent.method()"
|
||
category: "delegation"
|
||
|
||
# よくある間違いと修正
|
||
common_mistakes:
|
||
- mistake: "while(true) { }"
|
||
correction: "loop(true) { }"
|
||
severity: "error"
|
||
|
||
- mistake: "this.value"
|
||
correction: "me.value"
|
||
severity: "error"
|
||
|
||
- mistake: "super.init()"
|
||
correction: "from Parent.init()"
|
||
severity: "error"
|
||
|
||
- mistake: "for i in array { }"
|
||
correction: "Not supported, use loop with index"
|
||
severity: "error"
|
||
|
||
# ANCP統合
|
||
ancp_mapping:
|
||
# キーワードの圧縮マッピング
|
||
compression:
|
||
"box": "$"
|
||
"from": "@"
|
||
"me": "m"
|
||
"loop": "L"
|
||
"local": "l"
|
||
"return": "r"
|
||
|
||
# 圧縮時の保持ルール
|
||
preservation:
|
||
- "Semantic meaning must be preserved"
|
||
- "AST structure must be identical"
|
||
- "Round-trip must be lossless"
|
||
|
||
================================================================================
|
||
3. Grammar Runtime実装
|
||
================================================================================
|
||
|
||
// src/grammar/mod.rs
|
||
pub struct NyashGrammar {
|
||
version: String,
|
||
keywords: KeywordRegistry,
|
||
syntax_rules: SyntaxRuleSet,
|
||
semantic_rules: SemanticRuleSet,
|
||
ai_hints: AiHintCollection,
|
||
}
|
||
|
||
impl NyashGrammar {
|
||
/// YAMLファイルから文法定義を読み込み
|
||
pub fn load() -> Result<Self, Error> {
|
||
let yaml_path = concat!(env!("CARGO_MANIFEST_DIR"), "/grammar/nyash-grammar-v1.yaml");
|
||
let yaml_str = std::fs::read_to_string(yaml_path)?;
|
||
let grammar: GrammarDefinition = serde_yaml::from_str(&yaml_str)?;
|
||
Ok(Self::from_definition(grammar))
|
||
}
|
||
|
||
/// キーワードの検証
|
||
pub fn validate_keyword(&self, word: &str) -> KeywordValidation {
|
||
if let Some(keyword) = self.keywords.get(word) {
|
||
KeywordValidation::Valid(keyword)
|
||
} else if let Some(deprecated) = self.keywords.find_deprecated(word) {
|
||
KeywordValidation::Deprecated {
|
||
used: word,
|
||
correct: deprecated.correct_form,
|
||
hint: deprecated.ai_hint,
|
||
}
|
||
} else {
|
||
KeywordValidation::Unknown
|
||
}
|
||
}
|
||
|
||
/// AI向けの文法エクスポート
|
||
pub fn export_for_ai(&self) -> AiGrammarExport {
|
||
AiGrammarExport {
|
||
version: self.version.clone(),
|
||
keywords: self.keywords.export_correct_only(),
|
||
patterns: self.ai_hints.correct_patterns.clone(),
|
||
mistakes: self.ai_hints.common_mistakes.clone(),
|
||
examples: self.generate_examples(),
|
||
}
|
||
}
|
||
}
|
||
|
||
// キーワードレジストリ
|
||
pub struct KeywordRegistry {
|
||
keywords: HashMap<String, KeywordDef>,
|
||
deprecated_map: HashMap<String, String>, // old -> new
|
||
}
|
||
|
||
// 構文検証器
|
||
pub struct SyntaxValidator {
|
||
grammar: Arc<NyashGrammar>,
|
||
}
|
||
|
||
impl SyntaxValidator {
|
||
pub fn validate_ast(&self, ast: &ASTNode) -> Vec<SyntaxIssue> {
|
||
let mut issues = Vec::new();
|
||
self.visit_node(ast, &mut issues);
|
||
issues
|
||
}
|
||
}
|
||
|
||
================================================================================
|
||
4. コンポーネント統合
|
||
================================================================================
|
||
|
||
■ Tokenizer統合
|
||
impl NyashTokenizer {
|
||
pub fn new() -> Self {
|
||
let grammar = NyashGrammar::load()
|
||
.expect("Failed to load grammar definition");
|
||
Self { grammar, ... }
|
||
}
|
||
|
||
fn read_keyword_or_identifier(&mut self) -> TokenType {
|
||
let word = self.read_word();
|
||
|
||
// 文法定義に基づいて判定
|
||
match self.grammar.validate_keyword(&word) {
|
||
KeywordValidation::Valid(keyword) => keyword.token,
|
||
KeywordValidation::Deprecated { correct, .. } => {
|
||
self.emit_warning(format!("'{}' is deprecated, use '{}'", word, correct));
|
||
// エラーリカバリ: 正しいトークンを返す
|
||
self.grammar.keywords.get(correct).unwrap().token
|
||
}
|
||
KeywordValidation::Unknown => TokenType::IDENTIFIER(word),
|
||
}
|
||
}
|
||
}
|
||
|
||
■ Parser統合
|
||
impl Parser {
|
||
fn parse_box_definition(&mut self) -> Result<ASTNode, ParseError> {
|
||
// 文法ルールに基づいて検証
|
||
let rule = self.grammar.syntax_rules.get("box_definition")?;
|
||
|
||
self.consume(TokenType::BOX)?;
|
||
let name = self.parse_identifier()?;
|
||
|
||
// from句の処理も文法定義に従う
|
||
let extends = if self.match_token(&TokenType::FROM) {
|
||
self.parse_parent_list()?
|
||
} else {
|
||
vec![]
|
||
};
|
||
|
||
// 制約チェック
|
||
rule.validate(&parsed_node)?;
|
||
|
||
Ok(ASTNode::BoxDeclaration { name, extends, ... })
|
||
}
|
||
}
|
||
|
||
■ Interpreter統合
|
||
impl NyashInterpreter {
|
||
fn execute_from_call(&mut self, parent: &str, method: &str, args: &[ASTNode])
|
||
-> Result<Box<dyn NyashBox>, RuntimeError> {
|
||
|
||
// 文法定義に基づいてセマンティクスを適用
|
||
let semantic = self.grammar.semantic_rules.get("delegation_call")?;
|
||
semantic.validate_runtime(parent, method)?;
|
||
|
||
// 既存の実行ロジック
|
||
self.delegate_to_parent(parent, method, args)
|
||
}
|
||
}
|
||
|
||
================================================================================
|
||
5. AI連携機能
|
||
================================================================================
|
||
|
||
■ Grammar Export Tool
|
||
// tools/export-grammar-for-ai.rs
|
||
fn main() {
|
||
let grammar = NyashGrammar::load().unwrap();
|
||
|
||
// 1. 基本文法エクスポート
|
||
let basic = grammar.export_for_ai();
|
||
std::fs::write("nyash-grammar-ai.json", serde_json::to_string_pretty(&basic)?)?;
|
||
|
||
// 2. トレーニングデータ生成
|
||
let training_data = generate_training_pairs(&grammar);
|
||
std::fs::write("nyash-training-data.jsonl", training_data)?;
|
||
|
||
// 3. プロンプト生成
|
||
let prompt = generate_ai_prompt(&grammar);
|
||
std::fs::write("nyash-ai-prompt.txt", prompt)?;
|
||
}
|
||
|
||
■ AI Grammar Checker
|
||
// AIが生成したコードをチェック
|
||
pub struct AiCodeValidator {
|
||
grammar: Arc<NyashGrammar>,
|
||
}
|
||
|
||
impl AiCodeValidator {
|
||
pub fn validate(&self, code: &str) -> ValidationResult {
|
||
let mut issues = Vec::new();
|
||
|
||
// 1. 非推奨構文チェック
|
||
for (pattern, correction) in &self.grammar.deprecated_patterns {
|
||
if code.contains(pattern) {
|
||
issues.push(Issue::Deprecated { pattern, correction });
|
||
}
|
||
}
|
||
|
||
// 2. 構文検証
|
||
match NyashParser::parse_with_grammar(code, &self.grammar) {
|
||
Ok(ast) => {
|
||
// ASTレベルでの検証
|
||
issues.extend(self.validate_ast(&ast));
|
||
}
|
||
Err(e) => issues.push(Issue::ParseError(e)),
|
||
}
|
||
|
||
ValidationResult { issues, suggestions: self.generate_suggestions(&issues) }
|
||
}
|
||
}
|
||
|
||
================================================================================
|
||
6. ANCP統合
|
||
================================================================================
|
||
|
||
■ Grammar-Aware ANCP
|
||
pub struct GrammarAwareTranscoder {
|
||
grammar: Arc<NyashGrammar>,
|
||
ancp_mappings: AncpMappings,
|
||
}
|
||
|
||
impl GrammarAwareTranscoder {
|
||
pub fn encode(&self, code: &str) -> Result<String, Error> {
|
||
let ast = NyashParser::parse_with_grammar(code, &self.grammar)?;
|
||
|
||
// 文法定義に基づいて圧縮
|
||
let compressed = self.compress_with_grammar(&ast)?;
|
||
|
||
// ヘッダー付与
|
||
Ok(format!(";ancp:1.0 nyash:{} grammar:{};\n{}",
|
||
env!("CARGO_PKG_VERSION"),
|
||
self.grammar.version,
|
||
compressed))
|
||
}
|
||
|
||
fn compress_with_grammar(&self, ast: &ASTNode) -> Result<String, Error> {
|
||
// 文法定義のANCPマッピングを使用
|
||
let mappings = &self.grammar.ancp_mapping;
|
||
// ... 圧縮ロジック
|
||
}
|
||
}
|
||
|
||
================================================================================
|
||
7. 実装計画
|
||
================================================================================
|
||
|
||
■ Phase 1: 基礎実装（1週間）
|
||
□ nyash-grammar-v1.yaml作成
|
||
□ GrammarDefinition構造体設計
|
||
□ YAMLパーサー統合
|
||
□ 基本的な検証機能
|
||
|
||
■ Phase 2: コンポーネント統合（2週間）
|
||
□ Tokenizer改修
|
||
□ Parser改修
|
||
□ Interpreter統合
|
||
□ エラーメッセージ改善
|
||
|
||
■ Phase 3: AI機能（1週間）
|
||
□ export-grammar-for-ai実装
|
||
□ AiCodeValidator実装
|
||
□ トレーニングデータ生成
|
||
□ VSCode拡張対応
|
||
|
||
■ Phase 4: ANCP連携（1週間）
|
||
□ Grammar-Aware Transcoder
|
||
□ 圧縮効率の最適化
|
||
□ デバッグ情報保持
|
||
□ テスト統合
|
||
|
||
================================================================================
|
||
8. 期待される効果
|
||
================================================================================
|
||
|
||
1. **文法の一元管理**
|
||
- 単一の真実の源（YAML）
|
||
- 変更が全コンポーネントに自動反映
|
||
- バージョン管理が容易
|
||
|
||
2. **AIエラーの削減**
|
||
- 明確な文法定義で学習効率向上
|
||
- 非推奨構文の自動検出・修正
|
||
- トレーニングデータの品質向上
|
||
|
||
3. **開発効率の向上**
|
||
- 新構文追加が簡単
|
||
- 文法ドキュメントの自動生成
|
||
- テストケースの自動生成
|
||
|
||
4. **ANCP効率化**
|
||
- 文法aware圧縮で効率向上
|
||
- セマンティクス保持の保証
|
||
- デバッグ性の維持
|
||
|
||
================================================================================
|
||
9. リスクと対策
|
||
================================================================================
|
||
|
||
■ リスク1: パフォーマンス低下
|
||
対策: 文法定義をコンパイル時に静的化
|
||
|
||
■ リスク2: 後方互換性
|
||
対策: バージョニングとマイグレーションツール
|
||
|
||
■ リスク3: 複雑性増大
|
||
対策: 段階的実装と十分なテスト
|
||
|
||
================================================================================
|
||
10. 成功指標
|
||
================================================================================
|
||
|
||
□ AIの文法エラー率: 90%以上削減
|
||
□ 新構文追加時間: 1時間以内
|
||
□ パフォーマンス影響: 5%以内
|
||
□ テストカバレッジ: 95%以上
|
||
|
||
================================================================================
|
||
|
||
これにより、Nyashの文法が統一され、AIとの協働開発が劇的に改善される。
|
||
「文法の揺らぎ」を完全に排除し、高品質なコード生成を実現する。 |