Revert "✨ [Sema, Lex, Parse] Preprocessor embed in C and C++ (and Obj-C and Obj-C++ by-proxy)" (#95299)

Reverts llvm/llvm-project#68620

Introduce or expose a memory leak and UB, see llvm/llvm-project#68620

5 files changed, 8 insertions, 179 deletions

diff --git a/clang/lib/Frontend/CompilerInvocation.cpp b/clang/lib/Frontend/CompilerInvocation.cpp
index cde4a84..58694e5 100644
--- a/clang/lib/Frontend/CompilerInvocation.cpp
+++ b/clang/lib/Frontend/CompilerInvocation.cpp
@@ -4492,9 +4492,6 @@ static void GeneratePreprocessorArgs(const PreprocessorOptions &Opts,
   if (Opts.DefineTargetOSMacros)
     GenerateArg(Consumer, OPT_fdefine_target_os_macros);
 
-  for (const auto &EmbedEntry : Opts.EmbedEntries)
-    GenerateArg(Consumer, OPT_embed_dir_EQ, EmbedEntry);
-
   // Don't handle LexEditorPlaceholders. It is implied by the action that is
   // generated elsewhere.
 }
@@ -4587,11 +4584,6 @@ static bool ParsePreprocessorArgs(PreprocessorOptions &Opts, ArgList &Args,
     }
   }
 
-  for (const auto *A : Args.filtered(OPT_embed_dir_EQ)) {
-    StringRef Val = A->getValue();
-    Opts.EmbedEntries.push_back(std::string(Val));
-  }
-
   // Always avoid lexing editor placeholders when we're just running the
   // preprocessor as we never want to emit the
   // "editor placeholder in source file" error in PP only mode.
diff --git a/clang/lib/Frontend/DependencyFile.cpp b/clang/lib/Frontend/DependencyFile.cpp
index 528eae2..369816e 100644
--- a/clang/lib/Frontend/DependencyFile.cpp
+++ b/clang/lib/Frontend/DependencyFile.cpp
@@ -62,19 +62,6 @@ struct DepCollectorPPCallbacks : public PPCallbacks {
                                     /*IsMissing=*/false);
   }
 
-  void EmbedDirective(SourceLocation, StringRef, bool,
-                      OptionalFileEntryRef File,
-                      const LexEmbedParametersResult &) override {
-    assert(File && "expected to only be called when the file is found");
-    StringRef FileName =
-        llvm::sys::path::remove_leading_dotslash(File->getName());
-    DepCollector.maybeAddDependency(FileName,
-                                    /*FromModule*/ false,
-                                    /*IsSystem*/ false,
-                                    /*IsModuleFile*/ false,
-                                    /*IsMissing*/ false);
-  }
-
   void InclusionDirective(SourceLocation HashLoc, const Token &IncludeTok,
                           StringRef FileName, bool IsAngled,
                           CharSourceRange FilenameRange,
@@ -90,18 +77,6 @@ struct DepCollectorPPCallbacks : public PPCallbacks {
     // Files that actually exist are handled by FileChanged.
   }
 
-  void HasEmbed(SourceLocation, StringRef, bool,
-                OptionalFileEntryRef File) override {
-    if (!File)
-      return;
-    StringRef Filename =
-        llvm::sys::path::remove_leading_dotslash(File->getName());
-    DepCollector.maybeAddDependency(Filename,
-                                    /*FromModule=*/false, false,
-                                    /*IsModuleFile=*/false,
-                                    /*IsMissing=*/false);
-  }
-
   void HasInclude(SourceLocation Loc, StringRef SpelledFilename, bool IsAngled,
                   OptionalFileEntryRef File,
                   SrcMgr::CharacteristicKind FileType) override {
diff --git a/clang/lib/Frontend/DependencyGraph.cpp b/clang/lib/Frontend/DependencyGraph.cpp
index c23ce66..20e5f23 100644
--- a/clang/lib/Frontend/DependencyGraph.cpp
+++ b/clang/lib/Frontend/DependencyGraph.cpp
@@ -43,7 +43,7 @@ private:
 public:
   DependencyGraphCallback(const Preprocessor *_PP, StringRef OutputFile,
                           StringRef SysRoot)
-      : PP(_PP), OutputFile(OutputFile.str()), SysRoot(SysRoot.str()) {}
+    : PP(_PP), OutputFile(OutputFile.str()), SysRoot(SysRoot.str()) { }
 
   void InclusionDirective(SourceLocation HashLoc, const Token &IncludeTok,
                           StringRef FileName, bool IsAngled,
@@ -53,10 +53,6 @@ public:
                           bool ModuleImported,
                           SrcMgr::CharacteristicKind FileType) override;
 
-  void EmbedDirective(SourceLocation HashLoc, StringRef FileName, bool IsAngled,
-                      OptionalFileEntryRef File,
-                      const LexEmbedParametersResult &Params) override;
-
   void EndOfMainFile() override {
     OutputGraphFile();
   }
@@ -90,24 +86,6 @@ void DependencyGraphCallback::InclusionDirective(
   AllFiles.insert(*FromFile);
 }
 
-void DependencyGraphCallback::EmbedDirective(SourceLocation HashLoc, StringRef,
-                                             bool, OptionalFileEntryRef File,
-                                             const LexEmbedParametersResult &) {
-  if (!File)
-    return;
-
-  SourceManager &SM = PP->getSourceManager();
-  OptionalFileEntryRef FromFile =
-      SM.getFileEntryRefForID(SM.getFileID(SM.getExpansionLoc(HashLoc)));
-  if (!FromFile)
-    return;
-
-  Dependencies[*FromFile].push_back(*File);
-
-  AllFiles.insert(*File);
-  AllFiles.insert(*FromFile);
-}
-
 raw_ostream &
 DependencyGraphCallback::writeNodeReference(raw_ostream &OS,
                                             const FileEntry *Node) {
diff --git a/clang/lib/Frontend/InitPreprocessor.cpp b/clang/lib/Frontend/InitPreprocessor.cpp
index 2d5c94c..e8c8a51 100644
--- a/clang/lib/Frontend/InitPreprocessor.cpp
+++ b/clang/lib/Frontend/InitPreprocessor.cpp
@@ -508,14 +508,6 @@ static void InitializeStandardPredefinedMacros(const TargetInfo &TI,
   Builder.defineMacro("__STDC_UTF_16__", "1");
   Builder.defineMacro("__STDC_UTF_32__", "1");
 
-  // __has_embed definitions
-  Builder.defineMacro("__STDC_EMBED_NOT_FOUND__",
-                      llvm::itostr(static_cast<int>(EmbedResult::NotFound)));
-  Builder.defineMacro("__STDC_EMBED_FOUND__",
-                      llvm::itostr(static_cast<int>(EmbedResult::Found)));
-  Builder.defineMacro("__STDC_EMBED_EMPTY__",
-                      llvm::itostr(static_cast<int>(EmbedResult::Empty)));
-
   if (LangOpts.ObjC)
     Builder.defineMacro("__OBJC__");
 
diff --git a/clang/lib/Frontend/PrintPreprocessedOutput.cpp b/clang/lib/Frontend/PrintPreprocessedOutput.cpp
index 0592423..a26d2c3 100644
--- a/clang/lib/Frontend/PrintPreprocessedOutput.cpp
+++ b/clang/lib/Frontend/PrintPreprocessedOutput.cpp
@@ -11,11 +11,11 @@
 //
 //===----------------------------------------------------------------------===//
 
+#include "clang/Frontend/Utils.h"
 #include "clang/Basic/CharInfo.h"
 #include "clang/Basic/Diagnostic.h"
 #include "clang/Basic/SourceManager.h"
 #include "clang/Frontend/PreprocessorOutputOptions.h"
-#include "clang/Frontend/Utils.h"
 #include "clang/Lex/MacroInfo.h"
 #include "clang/Lex/PPCallbacks.h"
 #include "clang/Lex/Pragma.h"
@@ -93,7 +93,6 @@ private:
   bool DisableLineMarkers;
   bool DumpDefines;
   bool DumpIncludeDirectives;
-  bool DumpEmbedDirectives;
   bool UseLineDirectives;
   bool IsFirstFileEntered;
   bool MinimizeWhitespace;
@@ -101,7 +100,6 @@ private:
   bool KeepSystemIncludes;
   raw_ostream *OrigOS;
   std::unique_ptr<llvm::raw_null_ostream> NullOS;
-  unsigned NumToksToSkip;
 
   Token PrevTok;
   Token PrevPrevTok;
@@ -109,16 +107,14 @@ private:
 public:
   PrintPPOutputPPCallbacks(Preprocessor &pp, raw_ostream *os, bool lineMarkers,
                            bool defines, bool DumpIncludeDirectives,
-                           bool DumpEmbedDirectives, bool UseLineDirectives,
-                           bool MinimizeWhitespace, bool DirectivesOnly,
-                           bool KeepSystemIncludes)
+                           bool UseLineDirectives, bool MinimizeWhitespace,
+                           bool DirectivesOnly, bool KeepSystemIncludes)
       : PP(pp), SM(PP.getSourceManager()), ConcatInfo(PP), OS(os),
         DisableLineMarkers(lineMarkers), DumpDefines(defines),
         DumpIncludeDirectives(DumpIncludeDirectives),
-        DumpEmbedDirectives(DumpEmbedDirectives),
         UseLineDirectives(UseLineDirectives),
         MinimizeWhitespace(MinimizeWhitespace), DirectivesOnly(DirectivesOnly),
-        KeepSystemIncludes(KeepSystemIncludes), OrigOS(os), NumToksToSkip(0) {
+        KeepSystemIncludes(KeepSystemIncludes), OrigOS(os) {
     CurLine = 0;
     CurFilename += "<uninit>";
     EmittedTokensOnThisLine = false;
@@ -133,10 +129,6 @@ public:
     PrevPrevTok.startToken();
   }
 
-  /// Returns true if #embed directives should be expanded into a comma-
-  /// delimited list of integer constants or not.
-  bool expandEmbedContents() const { return !DumpEmbedDirectives; }
-
   bool isMinimizeWhitespace() const { return MinimizeWhitespace; }
 
   void setEmittedTokensOnThisLine() { EmittedTokensOnThisLine = true; }
@@ -157,9 +149,6 @@ public:
   void FileChanged(SourceLocation Loc, FileChangeReason Reason,
                    SrcMgr::CharacteristicKind FileType,
                    FileID PrevFID) override;
-  void EmbedDirective(SourceLocation HashLoc, StringRef FileName, bool IsAngled,
-                      OptionalFileEntryRef File,
-                      const LexEmbedParametersResult &Params) override;
   void InclusionDirective(SourceLocation HashLoc, const Token &IncludeTok,
                           StringRef FileName, bool IsAngled,
                           CharSourceRange FilenameRange,
@@ -243,9 +232,6 @@ public:
 
   void BeginModule(const Module *M);
   void EndModule(const Module *M);
-
-  unsigned GetNumToksToSkip() const { return NumToksToSkip; }
-  void ResetSkipToks() { NumToksToSkip = 0; }
 };
 }  // end anonymous namespace
 
@@ -413,74 +399,6 @@ void PrintPPOutputPPCallbacks::FileChanged(SourceLocation Loc,
   }
 }
 
-void PrintPPOutputPPCallbacks::EmbedDirective(
-    SourceLocation HashLoc, StringRef FileName, bool IsAngled,
-    OptionalFileEntryRef File, const LexEmbedParametersResult &Params) {
-  if (!DumpEmbedDirectives)
-    return;
-
-  // The EmbedDirective() callback is called before we produce the annotation
-  // token stream for the directive. We skip printing the annotation tokens
-  // within PrintPreprocessedTokens(), but we also need to skip the prefix,
-  // suffix, and if_empty tokens as those are inserted directly into the token
-  // stream and would otherwise be printed immediately after printing the
-  // #embed directive.
-  //
-  // FIXME: counting tokens to skip is a kludge but we have no way to know
-  // which tokens were inserted as part of the embed and which ones were
-  // explicitly written by the user.
-  MoveToLine(HashLoc, /*RequireStartOfLine=*/true);
-  *OS << "#embed " << (IsAngled ? '<' : '"') << FileName
-      << (IsAngled ? '>' : '"');
-
-  auto PrintToks = [&](llvm::ArrayRef<Token> Toks) {
-    SmallString<128> SpellingBuffer;
-    for (const Token &T : Toks) {
-      if (T.hasLeadingSpace())
-        *OS << " ";
-      *OS << PP.getSpelling(T, SpellingBuffer);
-    }
-  };
-  bool SkipAnnotToks = true;
-  if (Params.MaybeIfEmptyParam) {
-    *OS << " if_empty(";
-    PrintToks(Params.MaybeIfEmptyParam->Tokens);
-    *OS << ")";
-    // If the file is empty, we can skip those tokens. If the file is not
-    // empty, we skip the annotation tokens.
-    if (File && !File->getSize()) {
-      NumToksToSkip += Params.MaybeIfEmptyParam->Tokens.size();
-      SkipAnnotToks = false;
-    }
-  }
-
-  if (Params.MaybeLimitParam) {
-    *OS << " limit(" << Params.MaybeLimitParam->Limit << ")";
-  }
-  if (Params.MaybeOffsetParam) {
-    *OS << " clang::offset(" << Params.MaybeOffsetParam->Offset << ")";
-  }
-  if (Params.MaybePrefixParam) {
-    *OS << " prefix(";
-    PrintToks(Params.MaybePrefixParam->Tokens);
-    *OS << ")";
-    NumToksToSkip += Params.MaybePrefixParam->Tokens.size();
-  }
-  if (Params.MaybeSuffixParam) {
-    *OS << " suffix(";
-    PrintToks(Params.MaybeSuffixParam->Tokens);
-    *OS << ")";
-    NumToksToSkip += Params.MaybeSuffixParam->Tokens.size();
-  }
-
-  // We may need to skip the annotation token.
-  if (SkipAnnotToks)
-    NumToksToSkip++;
-
-  *OS << " /* clang -E -dE */";
-  setEmittedDirectiveOnThisLine();
-}
-
 void PrintPPOutputPPCallbacks::InclusionDirective(
     SourceLocation HashLoc, const Token &IncludeTok, StringRef FileName,
     bool IsAngled, CharSourceRange FilenameRange, OptionalFileEntryRef File,
@@ -760,7 +678,7 @@ void PrintPPOutputPPCallbacks::HandleWhitespaceBeforeTok(const Token &Tok,
   if (Tok.is(tok::eof) ||
       (Tok.isAnnotation() && !Tok.is(tok::annot_header_unit) &&
        !Tok.is(tok::annot_module_begin) && !Tok.is(tok::annot_module_end) &&
-       !Tok.is(tok::annot_repl_input_end) && !Tok.is(tok::annot_embed)))
+       !Tok.is(tok::annot_repl_input_end)))
     return;
 
   // EmittedDirectiveOnThisLine takes priority over RequireSameLine.
@@ -960,27 +878,6 @@ static void PrintPreprocessedTokens(Preprocessor &PP, Token &Tok,
       std::string Name = M->getFullModuleName();
       Callbacks->OS->write(Name.data(), Name.size());
       Callbacks->HandleNewlinesInToken(Name.data(), Name.size());
-    } else if (Tok.is(tok::annot_embed)) {
-      // Manually explode the binary data out to a stream of comma-delimited
-      // integer values. If the user passed -dE, that is handled by the
-      // EmbedDirective() callback. We should only get here if the user did not
-      // pass -dE.
-      assert(Callbacks->expandEmbedContents() &&
-             "did not expect an embed annotation");
-      auto *Data =
-          reinterpret_cast<EmbedAnnotationData *>(Tok.getAnnotationValue());
-
-      // Loop over the contents and print them as a comma-delimited list of
-      // values.
-      bool PrintComma = false;
-      for (auto Iter = Data->BinaryData.begin(), End = Data->BinaryData.end();
-           Iter != End; ++Iter) {
-        if (PrintComma)
-          *Callbacks->OS << ", ";
-        *Callbacks->OS << static_cast<unsigned>(*Iter);
-        PrintComma = true;
-      }
-      IsStartOfLine = true;
     } else if (Tok.isAnnotation()) {
       // Ignore annotation tokens created by pragmas - the pragmas themselves
       // will be reproduced in the preprocessed output.
@@ -1029,10 +926,6 @@ static void PrintPreprocessedTokens(Preprocessor &PP, Token &Tok,
     if (Tok.is(tok::eof)) break;
 
     PP.Lex(Tok);
-    // If lexing that token causes us to need to skip future tokens, do so now.
-    for (unsigned I = 0, Skip = Callbacks->GetNumToksToSkip(); I < Skip; ++I)
-      PP.Lex(Tok);
-    Callbacks->ResetSkipToks();
   }
 }
 
@@ -1089,9 +982,8 @@ void clang::DoPrintPreprocessedInput(Preprocessor &PP, raw_ostream *OS,
 
   PrintPPOutputPPCallbacks *Callbacks = new PrintPPOutputPPCallbacks(
       PP, OS, !Opts.ShowLineMarkers, Opts.ShowMacros,
-      Opts.ShowIncludeDirectives, Opts.ShowEmbedDirectives,
-      Opts.UseLineDirectives, Opts.MinimizeWhitespace, Opts.DirectivesOnly,
-      Opts.KeepSystemIncludes);
+      Opts.ShowIncludeDirectives, Opts.UseLineDirectives,
+      Opts.MinimizeWhitespace, Opts.DirectivesOnly, Opts.KeepSystemIncludes);
 
   // Expand macros in pragmas with -fms-extensions.  The assumption is that
   // the majority of pragmas in such a file will be Microsoft pragmas.