Revert "Revert "[clang][pp] adds '#pragma include_instead'""

Includes regression test for problem noted by @hans.
This reverts commit 973de71.

Differential Revision: https://reviews.llvm.org/D106898

Author: cjdb

clang/include/clang/Basic/DiagnosticLexKinds.td

@@ -300,6 +300,13 @@ def pp_pragma_once_in_main_file : Warning<"#pragma once in main file">,
 def pp_pragma_sysheader_in_main_file : Warning<
   "#pragma system_header ignored in main file">,
   InGroup<DiagGroup<"pragma-system-header-outside-header">>;
+
+def err_pragma_include_instead_not_sysheader : Error<
+  "'#pragma clang include_instead' cannot be used outside of system headers">;
+def err_pragma_include_instead_system_reserved : Error<
+  "header '%0' is an implementation detail; #include %select{'%2'|either '%2' "
+  "or '%3'|one of %2}1 instead">;
+
 def pp_poisoning_existing_macro : Warning<"poisoning existing macro">;
 def pp_out_of_date_dependency : Warning<
   "current file is older than dependency %0">;

clang/include/clang/Lex/HeaderSearch.h

@@ -20,9 +20,12 @@
 #include "clang/Lex/ModuleMap.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/SetVector.h"
+#include "llvm/ADT/SmallSet.h"
+#include "llvm/ADT/SmallString.h"
 #include "llvm/ADT/StringMap.h"
-#include "llvm/ADT/StringSet.h"
 #include "llvm/ADT/StringRef.h"
+#include "llvm/ADT/StringSet.h"
 #include "llvm/Support/Allocator.h"
 #include <cassert>
 #include <cstddef>
@@ -110,6 +113,14 @@ struct HeaderFileInfo {
   /// of the framework.
   StringRef Framework;
 
+  /// List of aliases that this header is known as.
+  /// Most headers should only have at most one alias, but a handful
+  /// have two.
+  llvm::SetVector<llvm::SmallString<32>,
+                  llvm::SmallVector<llvm::SmallString<32>, 2>,
+                  llvm::SmallSet<llvm::SmallString<32>, 2>>
+      Aliases;
+
   HeaderFileInfo()
       : isImport(false), isPragmaOnce(false), DirInfo(SrcMgr::C_User),
         External(false), isModuleHeader(false), isCompilingModuleHeader(false),
@@ -453,6 +464,10 @@ class HeaderSearch {
     getFileInfo(File).DirInfo = SrcMgr::C_System;
   }
 
+  void AddFileAlias(const FileEntry *File, StringRef Alias) {
+    getFileInfo(File).Aliases.insert(Alias);
+  }
+
   /// Mark the specified file as part of a module.
   void MarkFileModuleHeader(const FileEntry *FE,
                             ModuleMap::ModuleHeaderRole Role,

clang/include/clang/Lex/Preprocessor.h

@@ -1961,7 +1961,8 @@ class Preprocessor {
   /// This either returns the EOF token and returns true, or
   /// pops a level off the include stack and returns false, at which point the
   /// client should call lex again.
-  bool HandleEndOfFile(Token &Result, bool isEndOfMacro = false);
+  bool HandleEndOfFile(Token &Result, SourceLocation Loc,
+                       bool isEndOfMacro = false);
 
   /// Callback invoked when the current TokenLexer hits the end of its
   /// token stream.
@@ -2373,12 +2374,14 @@ class Preprocessor {
 
   // Pragmas.
   void HandlePragmaDirective(PragmaIntroducer Introducer);
+  void ResolvePragmaIncludeInstead(SourceLocation Location) const;
 
 public:
   void HandlePragmaOnce(Token &OnceTok);
   void HandlePragmaMark(Token &MarkTok);
   void HandlePragmaPoison();
   void HandlePragmaSystemHeader(Token &SysHeaderTok);
+  void HandlePragmaIncludeInstead(Token &Tok);
   void HandlePragmaDependency(Token &DependencyTok);
   void HandlePragmaPushMacro(Token &Tok);
   void HandlePragmaPopMacro(Token &Tok);

clang/include/clang/Lex/PreprocessorLexer.h

@@ -14,11 +14,13 @@
 #ifndef LLVM_CLANG_LEX_PREPROCESSORLEXER_H
 #define LLVM_CLANG_LEX_PREPROCESSORLEXER_H
 
+#include "clang/Basic/SourceLocation.h"
+#include "clang/Lex/HeaderSearch.h"
 #include "clang/Lex/MultipleIncludeOpt.h"
 #include "clang/Lex/Token.h"
-#include "clang/Basic/SourceLocation.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/StringMap.h"
 #include <cassert>
 
 namespace clang {
@@ -74,6 +76,13 @@ class PreprocessorLexer {
   /// we are currently in.
   SmallVector<PPConditionalInfo, 4> ConditionalStack;
 
+  struct IncludeInfo {
+    const FileEntry *File;
+    SourceLocation Location;
+  };
+  // A complete history of all the files included by the current file.
+  llvm::StringMap<IncludeInfo> IncludeHistory;
+
   PreprocessorLexer() : FID() {}
   PreprocessorLexer(Preprocessor *pp, FileID fid);
   virtual ~PreprocessorLexer() = default;
@@ -175,6 +184,15 @@ class PreprocessorLexer {
     ConditionalStack.clear();
     ConditionalStack.append(CL.begin(), CL.end());
   }
+
+  void addInclude(StringRef Filename, const FileEntry &File,
+                  SourceLocation Location) {
+    IncludeHistory.insert({Filename, {&File, Location}});
+  }
+
+  const llvm::StringMap<IncludeInfo> &getIncludeHistory() const {
+    return IncludeHistory;
+  }
 };
 
 } // namespace clang

clang/lib/Lex/Lexer.cpp

@@ -2811,11 +2811,11 @@ bool Lexer::LexEndOfFile(Token &Result, const char *CurPtr) {
     ConditionalStack.pop_back();
   }
 
+  SourceLocation EndLoc = getSourceLocation(BufferEnd);
   // C99 5.1.1.2p2: If the file is non-empty and didn't end in a newline, issue
   // a pedwarn.
   if (CurPtr != BufferStart && (CurPtr[-1] != '\n' && CurPtr[-1] != '\r')) {
     DiagnosticsEngine &Diags = PP->getDiagnostics();
-    SourceLocation EndLoc = getSourceLocation(BufferEnd);
     unsigned DiagID;
 
     if (LangOpts.CPlusPlus11) {
@@ -2838,7 +2838,7 @@ bool Lexer::LexEndOfFile(Token &Result, const char *CurPtr) {
   BufferPtr = CurPtr;
 
   // Finally, let the preprocessor handle this.
-  return PP->HandleEndOfFile(Result, isPragmaLexer());
+  return PP->HandleEndOfFile(Result, EndLoc, isPragmaLexer());
 }
 
 /// isNextPPTokenLParen - Return 1 if the next unexpanded token lexed from

clang/lib/Lex/PPDirectives.cpp

@@ -2032,6 +2032,10 @@ Preprocessor::ImportAction Preprocessor::HandleHeaderIncludeOrImport(
       IsFrameworkFound, IsImportDecl, IsMapped, LookupFrom, LookupFromFile,
       LookupFilename, RelativePath, SearchPath, SuggestedModule, isAngled);
 
+  // Record the header's filename for later use.
+  if (File)
+    CurLexer->addInclude(OriginalFilename, File->getFileEntry(), FilenameLoc);
+
   if (usingPCHWithThroughHeader() && SkippingUntilPCHThroughHeader) {
     if (File && isPCHThroughHeader(&File->getFileEntry()))
       SkippingUntilPCHThroughHeader = false;

clang/lib/Lex/PPLexerChange.cpp

@@ -12,6 +12,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "clang/Basic/FileManager.h"
+#include "clang/Basic/SourceLocation.h"
 #include "clang/Basic/SourceManager.h"
 #include "clang/Lex/HeaderSearch.h"
 #include "clang/Lex/LexDiagnostic.h"
@@ -22,6 +23,7 @@
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/MemoryBufferRef.h"
 #include "llvm/Support/Path.h"
+
 using namespace clang;
 
 //===----------------------------------------------------------------------===//
@@ -299,10 +301,46 @@ void Preprocessor::diagnoseMissingHeaderInUmbrellaDir(const Module &Mod) {
   }
 }
 
+void Preprocessor::ResolvePragmaIncludeInstead(
+    const SourceLocation Location) const {
+  assert(Location.isValid());
+  if (CurLexer == nullptr)
+    return;
+
+  if (SourceMgr.isInSystemHeader(Location))
+    return;
+
+  for (const auto &Include : CurLexer->getIncludeHistory()) {
+    StringRef Filename = Include.getKey();
+    const PreprocessorLexer::IncludeInfo &Info = Include.getValue();
+    ArrayRef<SmallString<32>> Aliases =
+        HeaderInfo.getFileInfo(Info.File).Aliases.getArrayRef();
+
+    if (Aliases.empty())
+      continue;
+
+    switch (Aliases.size()) {
+    case 1:
+      Diag(Info.Location, diag::err_pragma_include_instead_system_reserved)
+          << Filename << 0 << Aliases[0];
+      continue;
+    case 2:
+      Diag(Info.Location, diag::err_pragma_include_instead_system_reserved)
+          << Filename << 1 << Aliases[0] << Aliases[1];
+      continue;
+    default: {
+      Diag(Info.Location, diag::err_pragma_include_instead_system_reserved)
+          << Filename << 2 << ("{'" + llvm::join(Aliases, "', '") + "'}");
+    }
+    }
+  }
+}
+
 /// HandleEndOfFile - This callback is invoked when the lexer hits the end of
 /// the current file.  This either returns the EOF token or pops a level off
 /// the include stack and keeps going.
-bool Preprocessor::HandleEndOfFile(Token &Result, bool isEndOfMacro) {
+bool Preprocessor::HandleEndOfFile(Token &Result, SourceLocation EndLoc,
+                                   bool isEndOfMacro) {
   assert(!CurTokenLexer &&
          "Ending a file when currently in a macro!");
 
@@ -372,6 +410,9 @@ bool Preprocessor::HandleEndOfFile(Token &Result, bool isEndOfMacro) {
     }
   }
 
+  if (EndLoc.isValid())
+    ResolvePragmaIncludeInstead(EndLoc);
+
   // Complain about reaching a true EOF within arc_cf_code_audited.
   // We don't want to complain about reaching the end of a macro
   // instantiation or a _Pragma.
@@ -560,7 +601,7 @@ bool Preprocessor::HandleEndOfTokenLexer(Token &Result) {
     TokenLexerCache[NumCachedTokenLexers++] = std::move(CurTokenLexer);
 
   // Handle this like a #include file being popped off the stack.
-  return HandleEndOfFile(Result, true);
+  return HandleEndOfFile(Result, {}, true);
 }
 
 /// RemoveTopOfLexerStack - Pop the current lexer/macro exp off the top of the