Add a method to the BitcodeReader to parse only the identification block

[mehdi_amini]

Summary

Mimic parseTriple(); and exposes it to LTOModule.cpp

[mehdi_amini]

Update with clang-format before commit

[mehdi_amini]

r252442

include/llvm/Bitcode/ReaderWriter.h

namespace llvm {
 
   /// Read the header of the specified bitcode buffer and extract just the
   /// triple information. If successful, this returns a string. On error, this
   /// returns "".
   std::string
   getBitcodeTargetTriple(MemoryBufferRef Buffer, LLVMContext &Context,
                          DiagnosticHandlerFunction DiagnosticHandler = nullptr);
 
+  /// Read the header of the specified bitcode buffer and extract just the
+  /// producer string information. If successful, this returns a string. On
+  /// error, this returns "".
+  std::string getBitcodeProducerString(
+      MemoryBufferRef Buffer, LLVMContext &Context,
+      DiagnosticHandlerFunction DiagnosticHandler = nullptr);
+
   /// Read the specified bitcode file, returning the module.
   ErrorOr<std::unique_ptr<Module>>
   parseBitcodeFile(MemoryBufferRef Buffer, LLVMContext &Context,
                    DiagnosticHandlerFunction DiagnosticHandler = nullptr);
 
   /// Check if the given bitcode buffer contains a function summary block.
   bool hasFunctionSummary(MemoryBufferRef Buffer, LLVMContext &Context,
                           DiagnosticHandlerFunction DiagnosticHandler);

include/llvm/LTO/LTOModule.h

public:
   static bool isBitcodeFile(const void *mem, size_t length);
   static bool isBitcodeFile(const char *path);
 
   /// Returns 'true' if the memory buffer is LLVM bitcode for the specified
   /// triple.
   static bool isBitcodeForTarget(MemoryBuffer *memBuffer,
                                  StringRef triplePrefix);
 
+  /// Returns a string representing the producer identification stored in the
+  /// bitcode, or "" if the bitcode does not contains any.
+  ///
+  static std::string getProducerString(MemoryBuffer *Buffer);
+
   /// Create a MemoryBuffer from a memory range with an optional name.
   static std::unique_ptr<MemoryBuffer>
   makeBuffer(const void *mem, size_t length, StringRef name = "");
 
   /// Create an LTOModule. N.B. These methods take ownership of the buffer. The
   /// caller must have initialized the Targets, the TargetMCs, the AsmPrinters,
   /// and the AsmParsers by calling:
   ///

lib/Bitcode/Reader/BitcodeReader.cpp

public:
   std::error_code parseBitcodeInto(std::unique_ptr<DataStreamer> Streamer,
                                    Module *M,
                                    bool ShouldLazyLoadMetadata = false);
 
   /// \brief Cheap mechanism to just extract module triple
   /// \returns true if an error occurred.
   ErrorOr<std::string> parseTriple();
 
+  /// Cheap mechanism to just extract the identification block out of bitcode.
+  ErrorOr<std::string> parseIdentificationBlock();
+
   static uint64_t decodeSignRotatedValue(uint64_t V);
 
   /// Materialize any deferred Metadata block.
   std::error_code materializeMetadata() override;
 
   void setStripDebugInfo() override;
 
 private:
while (1) {
 
     case BitstreamEntry::Record:
       Stream.skipRecord(Entry.ID);
       continue;
     }
   }
 }
 
+ErrorOr<std::string> BitcodeReader::parseIdentificationBlock() {
+  if (std::error_code EC = initStream(nullptr))
+    return EC;
+
+  // Sniff for the signature.
+  if (!hasValidBitcodeHeader(Stream))
+    return error("Invalid bitcode signature");
+
+  // We expect a number of well-defined blocks, though we don't necessarily
+  // need to understand them all.
+  while (1) {
+    BitstreamEntry Entry = Stream.advance();
+    switch (Entry.Kind) {
+    case BitstreamEntry::Error:
+      return error("Malformed block");
+    case BitstreamEntry::EndBlock:
+      return std::error_code();
+
+    case BitstreamEntry::SubBlock:
+      if (Entry.ID == bitc::IDENTIFICATION_BLOCK_ID) {
+        if (std::error_code EC = parseBitcodeVersion())
+          return EC;
+        return ProducerIdentification;
+      }
+      // Ignore other sub-blocks.
+      if (Stream.SkipBlock())
+        return error("Malformed block");
+      continue;
+    case BitstreamEntry::Record:
+      Stream.skipRecord(Entry.ID);
+      continue;
+    }
+  }
+}
+
 /// Parse metadata attachments.
 std::error_code BitcodeReader::parseMetadataAttachment(Function &F) {
   if (Stream.EnterSubBlock(bitc::METADATA_ATTACHMENT_ID))
     return error("Invalid record");
 
   SmallVector<uint64_t, 64> Record;
   while (1) {
     BitstreamEntry Entry = Stream.advanceSkippingSubblocks();
llvm::getBitcodeTargetTriple(MemoryBufferRef Buffer, LLVMContext &Context,
   auto R = llvm::make_unique<BitcodeReader>(Buf.release(), Context,
                                             DiagnosticHandler);
   ErrorOr<std::string> Triple = R->parseTriple();
   if (Triple.getError())
     return "";
   return Triple.get();
 }
 
+std::string
+llvm::getBitcodeProducerString(MemoryBufferRef Buffer, LLVMContext &Context,
+                               DiagnosticHandlerFunction DiagnosticHandler) {
+  std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(Buffer, false);
+  BitcodeReader R(Buf.release(), Context, DiagnosticHandler);
+  ErrorOr<std::string> ProducerString = R.parseIdentificationBlock();
+  if (ProducerString.getError())
+    return "";
+  return ProducerString.get();
+}
+
 // Parse the specified bitcode buffer, returning the function info index.
 // If IsLazy is false, parse the entire function summary into
 // the index. Otherwise skip the function summary section, and only create
 // an index object with a map from function name to function summary offset.
 // The index is used to perform lazy function summary reading later.
 ErrorOr<std::unique_ptr<FunctionInfoIndex>>
 llvm::getFunctionInfoIndex(MemoryBufferRef Buffer, LLVMContext &Context,
                            DiagnosticHandlerFunction DiagnosticHandler,

lib/LTO/LTOModule.cpp

ErrorOr<MemoryBufferRef> BCOrErr =
       IRObjectFile::findBitcodeInMemBuffer(Buffer->getMemBufferRef());
   if (!BCOrErr)
     return false;
   LLVMContext Context;
   std::string Triple = getBitcodeTargetTriple(*BCOrErr, Context);
   return StringRef(Triple).startswith(TriplePrefix);
 }
 
+std::string LTOModule::getProducerString(MemoryBuffer *Buffer) {
+  ErrorOr<MemoryBufferRef> BCOrErr =
+      IRObjectFile::findBitcodeInMemBuffer(Buffer->getMemBufferRef());
+  if (!BCOrErr)
+    return "";
+  LLVMContext Context;
+  return getBitcodeProducerString(*BCOrErr, Context);
+}
+
 LTOModule *LTOModule::createFromFile(const char *path, TargetOptions options,
                                      std::string &errMsg) {
   ErrorOr<std::unique_ptr<MemoryBuffer>> BufferOrErr =
       MemoryBuffer::getFile(path);
   if (std::error_code EC = BufferOrErr.getError()) {
     errMsg = EC.message();
     return nullptr;
   }