llvm-pdbdump: Fix several smaller issues with injected source compression handling

- getCompression() used to return a PDB_SourceCompression even though
  the docs for IDiaInjectedSource are explicit about the return value
  being compiler-dependent. Return an uint32_t instead, and make the
  printing code handle unknown values better by printing "Unknown" and
  the int value instead of not printing any compression.

- Print compressed contents as hex dump, not as string.

- Add compression type "DotNet", which is used (at least) by csc.exe,
  the C# compiler. Also add a lengthy comment describing the stream
  contents (derived from looking at the raw hex contents long enough
  to see the GUIDs, which led me to the roslyn and mono implementations
  for handling this).

- The native injected source dumper was dumping the contents of the
  whole data stream -- but csc.exe writes a stream that's padded with
  zero bytes to the next 512 boundary, and the dia api doesn't display
  those padding bytes. So make NativeInjectedSource::getCode() do the
  same thing.

Differential Revision: https://reviews.llvm.org/D64879

llvm-svn: 366386

3 files changed, 12 insertions, 10 deletions

diff --git a/llvm/lib/DebugInfo/PDB/DIA/DIAInjectedSource.cpp b/llvm/lib/DebugInfo/PDB/DIA/DIAInjectedSource.cpp
index 211b4e11ac4..032b230b5fa 100644
--- a/llvm/lib/DebugInfo/PDB/DIA/DIAInjectedSource.cpp
+++ b/llvm/lib/DebugInfo/PDB/DIA/DIAInjectedSource.cpp
@@ -41,11 +41,11 @@ std::string DIAInjectedSource::getVirtualFileName() const {
                           &IDiaInjectedSource::get_virtualFilename);
 }
 
-PDB_SourceCompression DIAInjectedSource::getCompression() const {
+uint32_t DIAInjectedSource::getCompression() const {
   DWORD Compression = 0;
   if (S_OK != SourceFile->get_sourceCompression(&Compression))
     return PDB_SourceCompression::None;
-  return static_cast<PDB_SourceCompression>(Compression);
+  return static_cast<uint32_t>(Compression);
 }
 
 std::string DIAInjectedSource::getCode() const {
diff --git a/llvm/lib/DebugInfo/PDB/Native/NativeEnumInjectedSources.cpp b/llvm/lib/DebugInfo/PDB/Native/NativeEnumInjectedSources.cpp
index 7c7901b708c..f17ff5bb01f 100644
--- a/llvm/lib/DebugInfo/PDB/Native/NativeEnumInjectedSources.cpp
+++ b/llvm/lib/DebugInfo/PDB/Native/NativeEnumInjectedSources.cpp
@@ -17,14 +17,15 @@ namespace pdb {
 
 namespace {
 
-Expected<std::string> readStreamData(BinaryStream &Stream) {
-  uint32_t Offset = 0, DataLength = Stream.getLength();
+Expected<std::string> readStreamData(BinaryStream &Stream, uint32_t Limit) {
+  uint32_t Offset = 0, DataLength = std::min(Limit, Stream.getLength());
   std::string Result;
   Result.reserve(DataLength);
   while (Offset < DataLength) {
     ArrayRef<uint8_t> Data;
     if (auto E = Stream.readLongestContiguousChunk(Offset, Data))
       return std::move(E);
+    Data = Data.take_front(DataLength - Offset);
     Offset += Data.size();
     Result += toStringRef(Data);
   }
@@ -62,9 +63,7 @@ public:
     return *VName;
   }
 
-  PDB_SourceCompression getCompression() const override {
-    return static_cast<PDB_SourceCompression>(Entry.Compression);
-  }
+  uint32_t getCompression() const override { return Entry.Compression; }
 
   std::string getCode() const override {
     // Get name of stream storing the data.
@@ -81,7 +80,7 @@ public:
       return "(failed to open data stream)";
     }
 
-    auto Data = readStreamData(**ExpectedFileStream);
+    auto Data = readStreamData(**ExpectedFileStream, Entry.FileSize);
     if (!Data) {
       consumeError(Data.takeError());
       return "(failed to read data)";
diff --git a/llvm/lib/DebugInfo/PDB/PDBExtras.cpp b/llvm/lib/DebugInfo/PDB/PDBExtras.cpp
index 59eadd71856..354a99476c4 100644
--- a/llvm/lib/DebugInfo/PDB/PDBExtras.cpp
+++ b/llvm/lib/DebugInfo/PDB/PDBExtras.cpp
@@ -320,14 +320,17 @@ raw_ostream &llvm::pdb::operator<<(raw_ostream &OS,
   return OS;
 }
 
-raw_ostream &llvm::pdb::operator<<(raw_ostream &OS,
-                                   const PDB_SourceCompression &Compression) {
+raw_ostream &llvm::pdb::dumpPDBSourceCompression(raw_ostream &OS,
+                                                 uint32_t Compression) {
   switch (Compression) {
     CASE_OUTPUT_ENUM_CLASS_NAME(PDB_SourceCompression, None, OS)
     CASE_OUTPUT_ENUM_CLASS_NAME(PDB_SourceCompression, Huffman, OS)
     CASE_OUTPUT_ENUM_CLASS_NAME(PDB_SourceCompression, LZ, OS)
     CASE_OUTPUT_ENUM_CLASS_STR(PDB_SourceCompression, RunLengthEncoded, "RLE",
                                OS)
+    CASE_OUTPUT_ENUM_CLASS_NAME(PDB_SourceCompression, DotNet, OS)
+  default:
+    OS << "Unknown (" << Compression << ")";
   }
   return OS;
 }