Allow for unfinished #if blocks in preambles

Previously, a preamble only included #if blocks (and friends like
ifdef) if there was a corresponding #endif before any declaration or
definition. The problem is that any header file that uses include guards
will not have a preamble generated, which can make code-completion very
slow.

To prevent errors about unbalanced preprocessor conditionals in the
preamble, and unbalanced preprocessor conditionals after a preamble
containing unfinished conditionals, the conditional stack is stored
in the pch file.

This fixes PR26045.

Differential Revision: http://reviews.llvm.org/D15994



git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@304207 91177308-0d34-0410-b5e6-96231b3b80d8

include/clang/Lex/Preprocessor.h

@@ -283,6 +283,44 @@ class Preprocessor {
   /// This is used when loading a precompiled preamble.
   std::pair<int, bool> SkipMainFilePreamble;
 
+  class PreambleConditionalStackStore {
+    enum State {
+      Off = 0,
+      Recording = 1,
+      Replaying = 2,
+    };
+
+  public:
+    PreambleConditionalStackStore() : ConditionalStackState(Off) {}
+
+    void startRecording() { ConditionalStackState = Recording; }
+    void startReplaying() { ConditionalStackState = Replaying; }
+    bool isRecording() const { return ConditionalStackState == Recording; }
+    bool isReplaying() const { return ConditionalStackState == Replaying; }
+
+    ArrayRef<PPConditionalInfo> getStack() const {
+      return ConditionalStack;
+    }
+
+    void doneReplaying() {
+      ConditionalStack.clear();
+      ConditionalStackState = Off;
+    }
+
+    void setStack(ArrayRef<PPConditionalInfo> s) {
+      if (!isRecording() && !isReplaying())
+        return;
+      ConditionalStack.clear();
+      ConditionalStack.append(s.begin(), s.end());
+    }
+
+    bool hasRecordedPreamble() const { return !ConditionalStack.empty(); }
+
+  private:
+    SmallVector<PPConditionalInfo, 4> ConditionalStack;
+    State ConditionalStackState;
+  } PreambleConditionalStack;
+
   /// \brief The current top of the stack that we're lexing from if
   /// not expanding a macro and we are lexing directly from source code.
   ///
@@ -1695,6 +1733,11 @@ class Preprocessor {
   /// \brief Return true if we're in the top-level file, not in a \#include.
   bool isInPrimaryFile() const;
 
+  /// \brief Return true if we're in the main file (specifically, if we are 0
+  /// (zero) levels deep \#include. This is used by the lexer to determine if
+  /// it needs to generate errors about unterminated \#if directives.
+  bool isInMainFile() const;
+
   /// \brief Handle cases where the \#include name is expanded
   /// from a macro as multiple tokens, which need to be glued together. 
   ///
@@ -1932,6 +1975,27 @@ class Preprocessor {
                                                           Module *M,
                                                           SourceLocation MLoc);
 
+  bool isRecordingPreamble() const {
+    return PreambleConditionalStack.isRecording();
+  }
+
+  bool hasRecordedPreamble() const {
+    return PreambleConditionalStack.hasRecordedPreamble();
+  }
+
+  ArrayRef<PPConditionalInfo> getPreambleConditionalStack() const {
+      return PreambleConditionalStack.getStack();
+  }
+
+  void setRecordedPreambleConditionalStack(ArrayRef<PPConditionalInfo> s) {
+    PreambleConditionalStack.setStack(s);
+  }
+
+  void setReplayablePreambleConditionalStack(ArrayRef<PPConditionalInfo> s) {
+    PreambleConditionalStack.startReplaying();
+    PreambleConditionalStack.setStack(s);
+  }
+
 private:
   // Macro handling.
   void HandleDefineDirective(Token &Tok, bool ImmediatelyAfterTopLevelIfndef);

include/clang/Lex/PreprocessorLexer.h

@@ -17,6 +17,7 @@
 
 #include "clang/Lex/MultipleIncludeOpt.h"
 #include "clang/Lex/Token.h"
+#include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/SmallVector.h"
 
 namespace clang {
@@ -176,6 +177,11 @@ class PreprocessorLexer {
   conditional_iterator conditional_end() const { 
     return ConditionalStack.end(); 
   }
+
+  void setConditionalLevels(ArrayRef<PPConditionalInfo> CL) {
+    ConditionalStack.clear();
+    ConditionalStack.append(CL.begin(), CL.end());
+  }
 };
 
 }  // end namespace clang

include/clang/Lex/PreprocessorOptions.h

@@ -80,7 +80,14 @@ class PreprocessorOptions {
   /// The boolean indicates whether the preamble ends at the start of a new
   /// line.
   std::pair<unsigned, bool> PrecompiledPreambleBytes;
-
+
+  /// \brief True indicates that a preamble is being generated.
+  ///
+  /// When the lexer is done, one of the things that need to be preserved is the
+  /// conditional #if stack, so the ASTWriter/ASTReader can save/restore it when
+  /// processing the rest of the file.
+  bool GeneratePreamble;
+
   /// The implicit PTH input included at the start of the translation unit, or
   /// empty.
   std::string ImplicitPTHInclude;
@@ -144,6 +151,7 @@ class PreprocessorOptions {
                           AllowPCHWithCompilerErrors(false),
                           DumpDeserializedPCHDecls(false),
                           PrecompiledPreambleBytes(0, true),
+                          GeneratePreamble(false),
                           RemappedFilesKeepOriginalName(true),
                           RetainRemappedFileBuffers(false),
                           ObjCXXARCStandardLibrary(ARCXX_nolib) { }

include/clang/Serialization/ASTBitCodes.h

@@ -607,6 +607,9 @@ namespace clang {
 
       /// \brief Record code for \#pragma pack options.
       PACK_PRAGMA_OPTIONS = 61,
+
+      /// \brief The stack of open #ifs/#ifdefs recorded in a preamble.
+      PP_CONDITIONAL_STACK = 62,
     };
 
     /// \brief Record types used within a source manager block.

lib/Frontend/ASTUnit.cpp

@@ -1999,6 +1999,7 @@ ASTUnit *ASTUnit::LoadFromCommandLine(
   PreprocessorOptions &PPOpts = CI->getPreprocessorOpts();
   PPOpts.RemappedFilesKeepOriginalName = RemappedFilesKeepOriginalName;
   PPOpts.AllowPCHWithCompilerErrors = AllowPCHWithCompilerErrors;
+  PPOpts.GeneratePreamble = PrecompilePreambleAfterNParses != 0;
 
   // Override the resources path.
   CI->getHeaderSearchOpts().ResourceDir = ResourceFilesPath;

lib/Lex/Lexer.cpp

@@ -550,8 +550,6 @@ namespace {
 
   enum PreambleDirectiveKind {
     PDK_Skipped,
-    PDK_StartIf,
-    PDK_EndIf,
     PDK_Unknown
   };
 
@@ -574,8 +572,6 @@ std::pair<unsigned, bool> Lexer::ComputePreamble(StringRef Buffer,
 
   bool InPreprocessorDirective = false;
   Token TheTok;
-  Token IfStartTok;
-  unsigned IfCount = 0;
   SourceLocation ActiveCommentLoc;
 
   unsigned MaxLineOffset = 0;
@@ -658,33 +654,18 @@ std::pair<unsigned, bool> Lexer::ComputePreamble(StringRef Buffer,
               .Case("sccs", PDK_Skipped)
               .Case("assert", PDK_Skipped)
               .Case("unassert", PDK_Skipped)
-              .Case("if", PDK_StartIf)
-              .Case("ifdef", PDK_StartIf)
-              .Case("ifndef", PDK_StartIf)
+              .Case("if", PDK_Skipped)
+              .Case("ifdef", PDK_Skipped)
+              .Case("ifndef", PDK_Skipped)
               .Case("elif", PDK_Skipped)
               .Case("else", PDK_Skipped)
-              .Case("endif", PDK_EndIf)
+              .Case("endif", PDK_Skipped)
               .Default(PDK_Unknown);
 
         switch (PDK) {
         case PDK_Skipped:
           continue;
 
-        case PDK_StartIf:
-          if (IfCount == 0)
-            IfStartTok = HashTok;
-
-          ++IfCount;
-          continue;
-
-        case PDK_EndIf:
-          // Mismatched #endif. The preamble ends here.
-          if (IfCount == 0)
-            break;
-
-          --IfCount;
-          continue;
-
         case PDK_Unknown:
           // We don't know what this directive is; stop at the '#'.
           break;
@@ -705,16 +686,13 @@ std::pair<unsigned, bool> Lexer::ComputePreamble(StringRef Buffer,
   } while (true);
 
   SourceLocation End;
-  if (IfCount)
-    End = IfStartTok.getLocation();
-  else if (ActiveCommentLoc.isValid())
+  if (ActiveCommentLoc.isValid())
     End = ActiveCommentLoc; // don't truncate a decl comment.
   else
     End = TheTok.getLocation();
 
   return std::make_pair(End.getRawEncoding() - StartLoc.getRawEncoding(),
-                        IfCount? IfStartTok.isAtStartOfLine()
-                               : TheTok.isAtStartOfLine());
+                        TheTok.isAtStartOfLine());
 }
 
 /// AdvanceToTokenCharacter - Given a location that specifies the start of a
@@ -2570,6 +2548,11 @@ bool Lexer::LexEndOfFile(Token &Result, const char *CurPtr) {
     return true;
   }
 
+  if (PP->isRecordingPreamble() && !PP->isInMainFile()) {
+    PP->setRecordedPreambleConditionalStack(ConditionalStack);
+    ConditionalStack.clear();
+  }
+
   // Issue diagnostics for unterminated #if and missing newline.
 
   // If we are in a #if directive, emit an error.

lib/Lex/PPLexerChange.cpp

@@ -46,6 +46,12 @@ bool Preprocessor::isInPrimaryFile() const {
   });
 }
 
+bool Preprocessor::isInMainFile() const {
+  if (IsFileLexer())
+    return IncludeMacroStack.size() == 0;
+  return true;
+}
+
 /// getCurrentLexer - Return the current file lexer being lexed from.  Note
 /// that this ignores any potentially active macro expansions and _Pragma
 /// expansions going on at the time.

lib/Lex/Preprocessor.cpp

@@ -150,6 +150,9 @@ Preprocessor::Preprocessor(std::shared_ptr<PreprocessorOptions> PPOpts,
     Ident_GetExceptionInfo = Ident_GetExceptionCode = nullptr;
     Ident_AbnormalTermination = nullptr;
   }
+
+  if (this->PPOpts->GeneratePreamble)
+    PreambleConditionalStack.startRecording();
 }
 
 Preprocessor::~Preprocessor() {
@@ -532,6 +535,12 @@ void Preprocessor::EnterMainSourceFile() {
 
   // Start parsing the predefines.
   EnterSourceFile(FID, nullptr, SourceLocation());
+
+  // Restore the conditional stack from the preamble, if there is one.
+  if (PreambleConditionalStack.isReplaying()) {
+    CurPPLexer->setConditionalLevels(PreambleConditionalStack.getStack());
+    PreambleConditionalStack.doneReplaying();
+  }
 }
 
 void Preprocessor::EndSourceFile() {

lib/Serialization/ASTReader.cpp

@@ -2925,6 +2925,21 @@ ASTReader::ReadASTBlock(ModuleFile &F, unsigned ClientLoadCapabilities) {
       }
       break;
 
+    case PP_CONDITIONAL_STACK:
+      if (!Record.empty()) {
+        SmallVector<PPConditionalInfo, 4> ConditionalStack;
+        for (unsigned Idx = 0, N = Record.size() - 1; Idx < N; /* in loop */) {
+          auto Loc = ReadSourceLocation(F, Record, Idx);
+          bool WasSkipping = Record[Idx++];
+          bool FoundNonSkip = Record[Idx++];
+          bool FoundElse = Record[Idx++];
+          ConditionalStack.push_back(
+              {Loc, WasSkipping, FoundNonSkip, FoundElse});
+        }
+        PP.setReplayablePreambleConditionalStack(ConditionalStack);
+      }
+      break;
+
     case PP_COUNTER_VALUE:
       if (!Record.empty() && Listener)
         Listener->ReadCounter(F, Record[0]);

lib/Serialization/ASTWriter.cpp

@@ -1093,6 +1093,7 @@ void ASTWriter::WriteBlockInfoBlock() {
   RECORD(UNUSED_LOCAL_TYPEDEF_NAME_CANDIDATES);
   RECORD(DELETE_EXPRS_TO_ANALYZE);
   RECORD(CUDA_PRAGMA_FORCE_HOST_DEVICE_DEPTH);
+  RECORD(PP_CONDITIONAL_STACK);
 
   // SourceManager Block.
   BLOCK(SOURCE_MANAGER_BLOCK);
@@ -2302,6 +2303,18 @@ void ASTWriter::WritePreprocessor(const Preprocessor &PP, bool IsModule) {
     Stream.EmitRecord(PP_COUNTER_VALUE, Record);
   }
 
+  if (PP.isRecordingPreamble() && PP.hasRecordedPreamble()) {
+    assert(!IsModule);
+    for (const auto &Cond : PP.getPreambleConditionalStack()) {
+      AddSourceLocation(Cond.IfLoc, Record);
+      Record.push_back(Cond.WasSkipping);
+      Record.push_back(Cond.FoundNonSkip);
+      Record.push_back(Cond.FoundElse);
+    }
+    Stream.EmitRecord(PP_CONDITIONAL_STACK, Record);
+    Record.clear();
+  }
+
   // Enter the preprocessor block.
   Stream.EnterSubblock(PREPROCESSOR_BLOCK_ID, 3);
 

test/Lexer/preamble.c

@@ -9,15 +9,12 @@
 #pragma unknown
 #endif
 #ifdef WIBBLE
-#include "honk"
-#else
-int foo();
+#include "foo"
+int bar;
 #endif
 
 // This test checks for detection of the preamble of a file, which
-// includes all of the starting comments and #includes. Note that any
-// changes to the preamble part of this file must be mirrored in
-// Inputs/preamble.txt, since we diff against it.
+// includes all of the starting comments and #includes.
 
 // RUN: %clang_cc1 -print-preamble %s > %t
 // RUN: echo END. >> %t
@@ -33,4 +30,6 @@ int foo();
 // CHECK-NEXT: #endif
 // CHECK-NEXT: #pragma unknown
 // CHECK-NEXT: #endif
+// CHECK-NEXT: #ifdef WIBBLE
+// CHECK-NEXT: #include "foo"
 // CHECK-NEXT: END.

test/Lexer/preamble2.c

@@ -0,0 +1,19 @@
+// Preamble detection test: header with an include guard.
+#ifndef HEADER_H
+#define HEADER_H
+#include "foo"
+int bar;
+#endif
+
+// This test checks for detection of the preamble of a file, which
+// includes all of the starting comments and #includes.
+
+// RUN: %clang_cc1 -print-preamble %s > %t
+// RUN: echo END. >> %t
+// RUN: FileCheck < %t %s
+
+// CHECK: // Preamble detection test: header with an include guard.
+// CHECK-NEXT: #ifndef HEADER_H
+// CHECK-NEXT: #define HEADER_H
+// CHECK-NEXT: #include "foo"
+// CHECK-NEXT: END.