[stable/20220421] SymbolGraph ExtractAPI support for C and Objective-C in clang

clang/include/clang/ExtractAPI/FrontendActions.h

@@ -40,7 +40,10 @@ class ExtractAPIAction : public ASTFrontendAction {
   std::unique_ptr<llvm::MemoryBuffer> Buffer;
 
   /// The input file originally provided on the command line.
-  std::vector<std::string> KnownInputFiles;
+  ///
+  /// This captures the spelling used to include the file and whether the
+  /// include is quoted or not.
+  SmallVector<std::pair<SmallString<32>, bool>> KnownInputFiles;
 
   /// Prepare to execute the action on the given CompilerInstance.
   ///

clang/lib/ExtractAPI/ExtractAPIConsumer.cpp

@@ -38,7 +38,10 @@
 #include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallVector.h"
+#include "llvm/Support/FileSystem.h"
 #include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/Path.h"
+#include "llvm/Support/Regex.h"
 #include "llvm/Support/raw_ostream.h"
 #include <memory>
 #include <utility>
@@ -55,10 +58,125 @@ StringRef getTypedefName(const TagDecl *Decl) {
   return {};
 }
 
+Optional<std::string> getRelativeIncludeName(const CompilerInstance &CI,
+                                             StringRef File,
+                                             bool *IsQuoted = nullptr) {
+  assert(CI.hasFileManager() &&
+         "CompilerInstance does not have a FileNamager!");
+
+  using namespace llvm::sys;
+  // Matches framework include patterns
+  const llvm::Regex Rule("/(.+)\\.framework/(.+)?Headers/(.+)");
+
+  const auto &FS = CI.getVirtualFileSystem();
+
+  SmallString<128> FilePath(File.begin(), File.end());
+  FS.makeAbsolute(FilePath);
+  path::remove_dots(FilePath, true);
+  FilePath = path::convert_to_slash(FilePath);
+  File = FilePath;
+
+  // Checks whether `Dir` is a strict path prefix of `File`. If so returns
+  // the prefix length. Otherwise return 0.
+  auto CheckDir = [&](llvm::StringRef Dir) -> unsigned {
+    llvm::SmallString<32> DirPath(Dir.begin(), Dir.end());
+    FS.makeAbsolute(DirPath);
+    path::remove_dots(DirPath, true);
+    Dir = DirPath;
+    for (auto NI = path::begin(File), NE = path::end(File),
+              DI = path::begin(Dir), DE = path::end(Dir);
+         /*termination condition in loop*/; ++NI, ++DI) {
+      // '.' components in File are ignored.
+      while (NI != NE && *NI == ".")
+        ++NI;
+      if (NI == NE)
+        break;
+
+      // '.' components in Dir are ignored.
+      while (DI != DE && *DI == ".")
+        ++DI;
+
+      // Dir is a prefix of File, up to '.' components and choice of path
+      // separators.
+      if (DI == DE)
+        return NI - path::begin(File);
+
+      // Consider all path separators equal.
+      if (NI->size() == 1 && DI->size() == 1 &&
+          path::is_separator(NI->front()) && path::is_separator(DI->front()))
+        continue;
+
+      // Special case Apple .sdk folders since the search path is typically a
+      // symlink like `iPhoneSimulator14.5.sdk` while the file is instead
+      // located in `iPhoneSimulator.sdk` (the real folder).
+      if (NI->endswith(".sdk") && DI->endswith(".sdk")) {
+        StringRef NBasename = path::stem(*NI);
+        StringRef DBasename = path::stem(*DI);
+        if (DBasename.startswith(NBasename))
+          continue;
+      }
+
+      if (*NI != *DI)
+        break;
+    }
+    return 0;
+  };
+
+  unsigned PrefixLength = 0;
+
+  // Go through the search paths and find the first one that is a prefix of
+  // the header.
+  for (const auto &Entry : CI.getHeaderSearchOpts().UserEntries) {
+    // Note whether the match is found in a quoted entry.
+    if (IsQuoted)
+      *IsQuoted = Entry.Group == frontend::Quoted;
+
+    if (auto EntryFile = CI.getFileManager().getOptionalFileRef(Entry.Path)) {
+      if (auto HMap = HeaderMap::Create(*EntryFile, CI.getFileManager())) {
+        // If this is a headermap entry, try to reverse lookup the full path
+        // for a spelled name before mapping.
+        StringRef SpelledFilename = HMap->reverseLookupFilename(File);
+        if (!SpelledFilename.empty())
+          return SpelledFilename.str();
+
+        // No matching mapping in this headermap, try next search entry.
+        continue;
+      }
+    }
+
+    // Entry is a directory search entry, try to check if it's a prefix of File.
+    PrefixLength = CheckDir(Entry.Path);
+    if (PrefixLength > 0) {
+      // The header is found in a framework path, construct the framework-style
+      // include name `<Framework/Header.h>`
+      if (Entry.IsFramework) {
+        SmallVector<StringRef, 4> Matches;
+        Rule.match(File, &Matches);
+        // Returned matches are always in stable order.
+        if (Matches.size() != 4)
+          return None;
+
+        return path::convert_to_slash(
+            (Matches[1].drop_front(Matches[1].rfind('/') + 1) + "/" +
+             Matches[3])
+                .str());
+      }
+
+      // The header is found in a normal search path, strip the search path
+      // prefix to get an include name.
+      return path::convert_to_slash(File.drop_front(PrefixLength));
+    }
+  }
+
+  // Couldn't determine a include name, use full path instead.
+  return None;
+}
+
 struct LocationFileChecker {
   bool isLocationInKnownFile(SourceLocation Loc) {
     // If the loc refers to a macro expansion we need to first get the file
     // location of the expansion.
+    auto &SM = CI.getSourceManager();
     auto FileLoc = SM.getFileLoc(Loc);
     FileID FID = SM.getFileID(FileLoc);
     if (FID.isInvalid())
@@ -71,20 +189,44 @@ struct LocationFileChecker {
     if (KnownFileEntries.count(File))
       return true;
 
+    if (ExternalFileEntries.count(File))
+      return false;
+
+    StringRef FileName = File->tryGetRealPathName().empty()
+                             ? File->getName()
+                             : File->tryGetRealPathName();
+
+    // Try to reduce the include name the same way we tried to include it.
+    bool IsQuoted = false;
+    if (auto IncludeName = getRelativeIncludeName(CI, FileName, &IsQuoted))
+      if (llvm::find_if(KnownFiles,
+                        [&IsQuoted, &IncludeName](const auto &KnownFile) {
+                          return KnownFile.first.equals(*IncludeName) &&
+                                 KnownFile.second == IsQuoted;
+                        }) != KnownFiles.end()) {
+        KnownFileEntries.insert(File);
+        return true;
+      }
+
+    // Record that the file was not found to avoid future reverse lookup for
+    // the same file.
+    ExternalFileEntries.insert(File);
     return false;
   }
 
-  LocationFileChecker(const SourceManager &SM,
-                      const std::vector<std::string> &KnownFiles)
-      : SM(SM) {
-    for (const auto &KnownFilePath : KnownFiles)
-      if (auto FileEntry = SM.getFileManager().getFile(KnownFilePath))
+  LocationFileChecker(const CompilerInstance &CI,
+                      SmallVector<std::pair<SmallString<32>, bool>> &KnownFiles)
+      : CI(CI), KnownFiles(KnownFiles), ExternalFileEntries() {
+    for (const auto &KnownFile : KnownFiles)
+      if (auto FileEntry = CI.getFileManager().getFile(KnownFile.first))
         KnownFileEntries.insert(*FileEntry);
   }
 
 private:
-  const SourceManager &SM;
+  const CompilerInstance &CI;
+  SmallVector<std::pair<SmallString<32>, bool>> &KnownFiles;
   llvm::DenseSet<const FileEntry *> KnownFileEntries;
+  llvm::DenseSet<const FileEntry *> ExternalFileEntries;
 };
 
 /// The RecursiveASTVisitor to traverse symbol declarations and collect API
@@ -743,8 +885,7 @@ ExtractAPIAction::CreateASTConsumer(CompilerInstance &CI, StringRef InFile) {
       CI.getTarget().getTriple(),
       CI.getFrontendOpts().Inputs.back().getKind().getLanguage());
 
-  auto LCF = std::make_unique<LocationFileChecker>(CI.getSourceManager(),
-                                                   KnownInputFiles);
+  auto LCF = std::make_unique<LocationFileChecker>(CI, KnownInputFiles);
 
   CI.getPreprocessor().addPPCallbacks(std::make_unique<MacroCallback>(
       CI.getSourceManager(), *LCF, *API, CI.getPreprocessor()));
@@ -758,22 +899,48 @@ bool ExtractAPIAction::PrepareToExecuteAction(CompilerInstance &CI) {
   if (Inputs.empty())
     return true;
 
+  if (!CI.hasFileManager())
+    if (!CI.createFileManager())
+      return false;
+
   auto Kind = Inputs[0].getKind();
 
   // Convert the header file inputs into a single input buffer.
   SmallString<256> HeaderContents;
+  bool IsQuoted = false;
   for (const FrontendInputFile &FIF : Inputs) {
     if (Kind.isObjectiveC())
       HeaderContents += "#import";
     else
       HeaderContents += "#include";
-    HeaderContents += " \"";
-    HeaderContents += FIF.getFile();
-    HeaderContents += "\"\n";
 
-    KnownInputFiles.emplace_back(FIF.getFile());
+    StringRef FilePath = FIF.getFile();
+    if (auto RelativeName = getRelativeIncludeName(CI, FilePath, &IsQuoted)) {
+      if (IsQuoted)
+        HeaderContents += " \"";
+      else
+        HeaderContents += " <";
+
+      HeaderContents += *RelativeName;
+
+      if (IsQuoted)
+        HeaderContents += "\"\n";
+      else
+        HeaderContents += ">\n";
+      KnownInputFiles.emplace_back(static_cast<SmallString<32>>(*RelativeName),
+                                   IsQuoted);
+    } else {
+      HeaderContents += " \"";
+      HeaderContents += FilePath;
+      HeaderContents += "\"\n";
+      KnownInputFiles.emplace_back(FilePath, true);
+    }
   }
 
+  if (CI.getHeaderSearchOpts().Verbose)
+    CI.getVerboseOutputStream() << getInputBufferName() << ":\n"
+                                << HeaderContents << "\n";
+
   Buffer = llvm::MemoryBuffer::getMemBufferCopy(HeaderContents,
                                                 getInputBufferName());
 

clang/test/ExtractAPI/enum.c

@@ -2,17 +2,14 @@
 // RUN: split-file %s %t
 // RUN: sed -e "s@INPUT_DIR@%{/t:regex_replacement}@g" \
 // RUN: %t/reference.output.json.in >> %t/reference.output.json
-// RUN: %clang -extract-api -target arm64-apple-macosx \
-// RUN: %t/input.h -o %t/output.json | FileCheck -allow-empty %s
+// RUN: %clang_cc1 -extract-api -triple arm64-apple-macosx \
+// RUN:   -x c-header %t/input.h -o %t/output.json -verify
 
 // Generator version is not consistent across test runs, normalize it.
 // RUN: sed -e "s@\"generator\": \".*\"@\"generator\": \"?\"@g" \
 // RUN: %t/output.json >> %t/output-normalized.json
 // RUN: diff %t/reference.output.json %t/output-normalized.json
 
-// CHECK-NOT: error:
-// CHECK-NOT: warning:
-
 //--- input.h
 /// Kinds of vehicles
 enum Vehicle {
@@ -37,6 +34,7 @@ enum {
 enum {
   OtherConstant = 2
 };
+// expected-no-diagnostics
 
 //--- reference.output.json.in
 {