P0305R1: Parsing support for init-statements in 'if' and 'switch' statements.

No semantic analysis yet.

This is a pain to disambiguate correctly, because the parsing rules for the
declaration form of a condition and of an init-statement are quite different --
for a token sequence that looks like a declaration, we frequently need to
disambiguate all the way to the ')' or ';'.

We could do better here in some cases by stopping disambiguation once we've
decided whether we've got an expression or not (rather than keeping going until
we know whether it's an init-statement declaration or a condition declaration),
by unifying our parsing code for the two types of declaration and moving the
syntactic checks into Sema; if this has a measurable impact on parsing
performance, I'll look into that.

llvm-svn: 274169

Author: zygoloid

clang/include/clang/Basic/DiagnosticSemaKinds.td

@@ -7499,6 +7499,9 @@ def warn_empty_switch_body : Warning<
 def note_empty_body_on_separate_line : Note<
   "put the semicolon on a separate line to silence this warning">;
 
+def err_init_stmt_not_supported : Error<
+  "C++1z init-statement not yet supported">;
+
 def err_va_start_used_in_non_variadic_function : Error<
   "'va_start' used in function with fixed args">;
 def err_va_start_used_in_wrong_abi_function : Error<

clang/include/clang/Parse/Parser.h

@@ -1598,7 +1598,8 @@ class Parser : public CodeCompletionHandler {
 
   //===--------------------------------------------------------------------===//
   // C++ if/switch/while condition expression.
-  Sema::ConditionResult ParseCXXCondition(SourceLocation Loc,
+  Sema::ConditionResult ParseCXXCondition(StmtResult *InitStmt,
+                                          SourceLocation Loc,
                                           Sema::ConditionKind CK);
 
   //===--------------------------------------------------------------------===//
@@ -1690,7 +1691,8 @@ class Parser : public CodeCompletionHandler {
                                     unsigned ScopeFlags);
   void ParseCompoundStatementLeadingPragmas();
   StmtResult ParseCompoundStatementBody(bool isStmtExpr = false);
-  bool ParseParenExprOrCondition(Sema::ConditionResult &CondResult,
+  bool ParseParenExprOrCondition(StmtResult *InitStmt,
+                                 Sema::ConditionResult &CondResult,
                                  SourceLocation Loc,
                                  Sema::ConditionKind CK);
   StmtResult ParseIfStatement(SourceLocation *TrailingElseLoc);
@@ -1984,11 +1986,18 @@ class Parser : public CodeCompletionHandler {
   /// the function returns true to let the declaration parsing code handle it.
   bool isCXXFunctionDeclarator(bool *IsAmbiguous = nullptr);
 
-  /// isCXXConditionDeclaration - Disambiguates between a declaration or an
-  /// expression for a condition of a if/switch/while/for statement.
-  /// If during the disambiguation process a parsing error is encountered,
-  /// the function returns true to let the declaration parsing code handle it.
-  bool isCXXConditionDeclaration();
+  struct ConditionDeclarationOrInitStatementState;
+  enum class ConditionOrInitStatement {
+    Expression,    ///< Disambiguated as an expression (either kind).
+    ConditionDecl, ///< Disambiguated as the declaration form of condition.
+    InitStmtDecl,  ///< Disambiguated as a simple-declaration init-statement.
+    Error          ///< Can't be any of the above!
+  };
+  /// \brief Disambiguates between the different kinds of things that can happen
+  /// after 'if (' or 'switch ('. This could be one of two different kinds of
+  /// declaration (depending on whether there is a ';' later) or an expression.
+  ConditionOrInitStatement
+  isCXXConditionDeclarationOrInitStatement(bool CanBeInitStmt);
 
   bool isCXXTypeId(TentativeCXXTypeIdContext Context, bool &isAmbiguous);
   bool isCXXTypeId(TentativeCXXTypeIdContext Context) {

clang/include/clang/Sema/DeclSpec.h

@@ -1632,6 +1632,7 @@ class Declarator {
     MemberContext,       // Struct/Union field.
     BlockContext,        // Declaration within a block in a function.
     ForContext,          // Declaration within first part of a for loop.
+    InitStmtContext,     // Declaration within optional init stmt of if/switch.
     ConditionContext,    // Condition declaration in a C++ if/switch/while/for.
     TemplateParamContext,// Within a template parameter list.
     CXXNewContext,       // C++ new-expression.
@@ -1810,6 +1811,7 @@ class Declarator {
     case MemberContext:
     case BlockContext:
     case ForContext:
+    case InitStmtContext:
     case ConditionContext:
       return false;
 
@@ -1844,6 +1846,7 @@ class Declarator {
     case MemberContext:
     case BlockContext:
     case ForContext:
+    case InitStmtContext:
     case ConditionContext:
     case PrototypeContext:
     case LambdaExprParameterContext:
@@ -1877,6 +1880,7 @@ class Declarator {
     case MemberContext:
     case BlockContext:
     case ForContext:
+    case InitStmtContext:
     case ConditionContext:
     case PrototypeContext:
     case LambdaExprParameterContext:
@@ -1921,6 +1925,7 @@ class Declarator {
     case FileContext:
     case BlockContext:
     case ForContext:
+    case InitStmtContext:
       return true;
 
     case ConditionContext:
@@ -2120,6 +2125,7 @@ class Declarator {
     case MemberContext:
     case BlockContext:
     case ForContext:
+    case InitStmtContext:
       return true;
 
     case ConditionContext:

clang/include/clang/Sema/Sema.h

@@ -3397,12 +3397,14 @@ class Sema {
 
   class ConditionResult;
   StmtResult ActOnIfStmt(SourceLocation IfLoc, bool IsConstexpr,
+                         Stmt *InitStmt,
                          ConditionResult Cond, Stmt *ThenVal,
                          SourceLocation ElseLoc, Stmt *ElseVal);
   StmtResult BuildIfStmt(SourceLocation IfLoc, bool IsConstexpr,
                          ConditionResult Cond, Stmt *ThenVal,
                          SourceLocation ElseLoc, Stmt *ElseVal);
   StmtResult ActOnStartOfSwitchStmt(SourceLocation SwitchLoc,
+                                    Stmt *InitStmt,
                                     ConditionResult Cond);
   StmtResult ActOnFinishSwitchStmt(SourceLocation SwitchLoc,
                                            Stmt *Switch, Stmt *Body);

clang/lib/Parse/ParseDecl.cpp

@@ -2075,7 +2075,8 @@ Decl *Parser::ParseDeclarationAfterDeclaratorAndAttributes(
       if (Init.isInvalid()) {
         SmallVector<tok::TokenKind, 2> StopTokens;
         StopTokens.push_back(tok::comma);
-        if (D.getContext() == Declarator::ForContext)
+        if (D.getContext() == Declarator::ForContext ||
+            D.getContext() == Declarator::InitStmtContext)
           StopTokens.push_back(tok::r_paren);
         SkipUntil(StopTokens, StopAtSemi | StopBeforeMatch);
         Actions.ActOnInitializerError(ThisDecl);

clang/lib/Parse/ParseExprCXX.cpp

@@ -1726,11 +1726,18 @@ Parser::ParseCXXTypeConstructExpression(const DeclSpec &DS) {
 /// [GNU]   type-specifier-seq declarator simple-asm-expr[opt] attributes[opt]
 ///             '=' assignment-expression
 ///
+/// In C++1z, a condition may in some contexts be preceded by an
+/// optional init-statement. This function will parse that too.
+///
+/// \param InitStmt If non-null, an init-statement is permitted, and if present
+/// will be parsed and stored here.
+///
 /// \param Loc The location of the start of the statement that requires this
 /// condition, e.g., the "for" in a for loop.
 ///
 /// \returns The parsed condition.
-Sema::ConditionResult Parser::ParseCXXCondition(SourceLocation Loc,
+Sema::ConditionResult Parser::ParseCXXCondition(StmtResult *InitStmt,
+                                                SourceLocation Loc,
                                                 Sema::ConditionKind CK) {
   if (Tok.is(tok::code_completion)) {
     Actions.CodeCompleteOrdinaryName(getCurScope(), Sema::PCC_Condition);
@@ -1741,17 +1748,38 @@ Sema::ConditionResult Parser::ParseCXXCondition(SourceLocation Loc,
   ParsedAttributesWithRange attrs(AttrFactory);
   MaybeParseCXX11Attributes(attrs);
 
-  if (!isCXXConditionDeclaration()) {
+  // Determine what kind of thing we have.
+  switch (isCXXConditionDeclarationOrInitStatement(InitStmt)) {
+  case ConditionOrInitStatement::Expression: {
     ProhibitAttributes(attrs);
 
     // Parse the expression.
     ExprResult Expr = ParseExpression(); // expression
     if (Expr.isInvalid())
       return Sema::ConditionError();
 
+    if (InitStmt && Tok.is(tok::semi)) {
+      *InitStmt = Actions.ActOnExprStmt(Expr.get());
+      ConsumeToken();
+      return ParseCXXCondition(nullptr, Loc, CK);
+    }
+
     return Actions.ActOnCondition(getCurScope(), Loc, Expr.get(), CK);
   }
 
+  case ConditionOrInitStatement::InitStmtDecl: {
+    SourceLocation DeclStart = Tok.getLocation(), DeclEnd;
+    DeclGroupPtrTy DG = ParseSimpleDeclaration(
+        Declarator::InitStmtContext, DeclEnd, attrs, /*RequireSemi=*/true);
+    *InitStmt = Actions.ActOnDeclStmt(DG, DeclStart, DeclEnd);
+    return ParseCXXCondition(nullptr, Loc, CK);
+  }
+
+  case ConditionOrInitStatement::ConditionDecl:
+  case ConditionOrInitStatement::Error:
+    break;
+  }
+
   // type-specifier-seq
   DeclSpec DS(AttrFactory);
   DS.takeAttributesFrom(attrs);
@@ -1814,9 +1842,6 @@ Sema::ConditionResult Parser::ParseCXXCondition(SourceLocation Loc,
   else
     Actions.ActOnInitializerError(DeclOut);
 
-  // FIXME: Build a reference to this declaration? Convert it to bool?
-  // (This is currently handled by Sema).
-
   Actions.FinalizeDeclaration(DeclOut);
   return Actions.ActOnConditionVariable(DeclOut, Loc, CK);
 }

clang/lib/Parse/ParseStmt.cpp

@@ -1043,7 +1043,8 @@ StmtResult Parser::ParseCompoundStatementBody(bool isStmtExpr) {
 
 /// ParseParenExprOrCondition:
 /// [C  ]     '(' expression ')'
-/// [C++]     '(' condition ')'       [not allowed if OnlyAllowCondition=true]
+/// [C++]     '(' condition ')'
+/// [C++1z]   '(' init-statement[opt] condition ')'
 ///
 /// This function parses and performs error recovery on the specified condition
 /// or expression (depending on whether we're in C++ or C mode).  This function
@@ -1052,14 +1053,15 @@ StmtResult Parser::ParseCompoundStatementBody(bool isStmtExpr) {
 /// should try to recover harder.  It returns false if the condition is
 /// successfully parsed.  Note that a successful parse can still have semantic
 /// errors in the condition.
-bool Parser::ParseParenExprOrCondition(Sema::ConditionResult &Cond,
+bool Parser::ParseParenExprOrCondition(StmtResult *InitStmt,
+                                       Sema::ConditionResult &Cond,
                                        SourceLocation Loc,
                                        Sema::ConditionKind CK) {
   BalancedDelimiterTracker T(*this, tok::l_paren);
   T.consumeOpen();
 
   if (getLangOpts().CPlusPlus)
-    Cond = ParseCXXCondition(Loc, CK);
+    Cond = ParseCXXCondition(InitStmt, Loc, CK);
   else {
     ExprResult CondExpr = ParseExpression();
 
@@ -1139,8 +1141,9 @@ StmtResult Parser::ParseIfStatement(SourceLocation *TrailingElseLoc) {
   ParseScope IfScope(this, Scope::DeclScope | Scope::ControlScope, C99orCXX);
 
   // Parse the condition.
+  StmtResult InitStmt;
   Sema::ConditionResult Cond;
-  if (ParseParenExprOrCondition(Cond, IfLoc,
+  if (ParseParenExprOrCondition(&InitStmt, Cond, IfLoc,
                                 IsConstexpr ? Sema::ConditionKind::ConstexprIf
                                             : Sema::ConditionKind::Boolean))
     return StmtError();
@@ -1241,8 +1244,8 @@ StmtResult Parser::ParseIfStatement(SourceLocation *TrailingElseLoc) {
   if (ElseStmt.isInvalid())
     ElseStmt = Actions.ActOnNullStmt(ElseStmtLoc);
 
-  return Actions.ActOnIfStmt(IfLoc, IsConstexpr, Cond, ThenStmt.get(), ElseLoc,
-                             ElseStmt.get());
+  return Actions.ActOnIfStmt(IfLoc, IsConstexpr, InitStmt.get(), Cond,
+                             ThenStmt.get(), ElseLoc, ElseStmt.get());
 }
 
 /// ParseSwitchStatement
@@ -1279,11 +1282,14 @@ StmtResult Parser::ParseSwitchStatement(SourceLocation *TrailingElseLoc) {
   ParseScope SwitchScope(this, ScopeFlags);
 
   // Parse the condition.
+  StmtResult InitStmt;
   Sema::ConditionResult Cond;
-  if (ParseParenExprOrCondition(Cond, SwitchLoc, Sema::ConditionKind::Switch))
+  if (ParseParenExprOrCondition(&InitStmt, Cond, SwitchLoc,
+                                Sema::ConditionKind::Switch))
     return StmtError();
 
-  StmtResult Switch = Actions.ActOnStartOfSwitchStmt(SwitchLoc, Cond);
+  StmtResult Switch =
+      Actions.ActOnStartOfSwitchStmt(SwitchLoc, InitStmt.get(), Cond);
 
   if (Switch.isInvalid()) {
     // Skip the switch body.
@@ -1366,7 +1372,8 @@ StmtResult Parser::ParseWhileStatement(SourceLocation *TrailingElseLoc) {
 
   // Parse the condition.
   Sema::ConditionResult Cond;
-  if (ParseParenExprOrCondition(Cond, WhileLoc, Sema::ConditionKind::Boolean))
+  if (ParseParenExprOrCondition(nullptr, Cond, WhileLoc,
+                                Sema::ConditionKind::Boolean))
     return StmtError();
 
   // C99 6.8.5p5 - In C99, the body of the while statement is a scope, even if
@@ -1681,7 +1688,8 @@ StmtResult Parser::ParseForStatement(SourceLocation *TrailingElseLoc) {
       // missing both semicolons.
     } else {
       if (getLangOpts().CPlusPlus)
-        SecondPart = ParseCXXCondition(ForLoc, Sema::ConditionKind::Boolean);
+        SecondPart =
+            ParseCXXCondition(nullptr, ForLoc, Sema::ConditionKind::Boolean);
       else {
         ExprResult SecondExpr = ParseExpression();
         if (SecondExpr.isInvalid())