[pseudo][wip] Recovery for statements.

[hokein]

Summary

The main idea is to reuse the existing declaration recovery strategy --
extending it to cover some statement-specific bits.

Base on https://reviews.llvm.org/D130460

[hokein]

it should demonstrate the main idea. I will do some more tweaks (rename etc), and add tests once we agree on the direction.

clang-tools-extra/pseudo/lib/cxx/CXX.cpp

Token::Index recoverBrackets(const RecoveryParams &P) {
   }
   return Token::Invalid;
 }
 
 llvm::DenseMap<ExtensionID, RecoveryStrategy> buildRecoveryStrategies() {
   return {
       {Extension::Brackets, recoverBrackets},
       {Extension::NextDeclaration, recoverNextDeclaration},
+      {Extension::NextStatement, recoverNextDeclaration},
   };
 }
 
 } // namespace
 
 const Language &getLanguage() {
   static const auto &CXXLanguage = []() -> const Language & {
     std::vector<std::string> Diags;

clang-tools-extra/pseudo/lib/cxx/Recovery.cpp

Token::Index recoverNextDeclaration(const RecoveryParams &P) {
   //  - if the declarator is good and the braces are present, parsing succeeds
   //  - if the declarator is bad, it's hard to know it's a function
   //  - if the braces are missing, we don't know where to recover
   // So we only try to detect the others.
   bool AcceptBraces = false;
   auto ConsiderForBraces = [&](tok::TokenKind K) {
     if (K == tok::kw_export || K == tok::kw_extern || K == tok::kw_namespace)
       AcceptBraces = true;
+    // Statements that don't end in semicolons:
+    //   while/switch/if/for (...) {}
+    if (K == tok::kw_for || K == tok::kw_while || K == tok::kw_if ||
+        K == tok::kw_switch)
+      AcceptBraces = true;
   };
 
   // Some tokens are pretty good indicators of a declaration starting, when
   // they appear at the beginning of a line.
   auto LikelyStartsDeclaration = [&](tok::TokenKind K) -> bool {
     switch (K) {
     // Things you might be declaring.
     case tok::kw_template:
auto LikelyStartsDeclaration = [&](tok::TokenKind K) -> bool {
     case tok::kw_virtual:
     // Modules
     case tok::kw_import:
     case tok::kw_export:
     // Class protection
     case tok::kw_public:
     case tok::kw_private:
     case tok::kw_protected:
+    // Typical keywords for statements
+    case tok::kw_for:
+    case tok::kw_while:
+    case tok::kw_if:
+    case tok::kw_goto:
+    case tok::kw_switch:
+    case tok::kw_return:
+    case tok::kw_break:
+    case tok::kw_continue:
       return true;
     default:
       return false;
     }
   };
 
   // The indentation level where the declaration started hints at where a new
   // sibling declaration might start.

clang-tools-extra/pseudo/lib/cxx/cxx.bnf

 init-statement := simple-declaration
 condition := expression
 condition := decl-specifier-seq declarator brace-or-equal-initializer
 labeled-statement := IDENTIFIER : statement
 labeled-statement := CASE constant-expression : statement
 labeled-statement := DEFAULT : statement
 expression-statement := expression_opt ;
 compound-statement := { statement-seq_opt [recover=Brackets] }
-statement-seq := statement
-statement-seq := statement-seq statement
+statement-seq := statement [recover=NextStatement]
+statement-seq := statement-seq statement [recover=NextStatement]
 selection-statement := IF CONSTEXPR_opt ( init-statement_opt condition ) statement [guard]
 selection-statement := IF CONSTEXPR_opt ( init-statement_opt condition ) statement ELSE statement
 selection-statement := SWITCH ( init-statement_opt condition ) statement
 iteration-statement := WHILE ( condition ) statement
 iteration-statement := DO statement WHILE ( expression ) ;
 iteration-statement := FOR ( init-statement condition_opt ; expression_opt ) statement
 iteration-statement := FOR ( init-statement_opt for-range-declaration : for-range-initializer ) statement
 for-range-declaration := decl-specifier-seq declarator