[PDB] Support dumping injected sources via the DIA reader.

Injected sources are basically a way to add actual source file content
to your PDB. Presumably you could use this for shipping your source code
with your debug information, but in practice I can only find this being
used for embedding natvis files inside of PDBs.

In order to effectively test LLVM's natvis file injection, we need a way
to dump the injected sources of a PDB in a way that is authoritative
(i.e. based on Microsoft's understanding of the PDB format, and not
LLVM's). To this end, I've added support for dumping injected sources
via DIA. I made a PDB file that used the /natvis option to generate a
test case.

Differential Revision: https://reviews.llvm.org/D44405

llvm-svn: 327428
diff --git a/llvm/lib/DebugInfo/PDB/CMakeLists.txt b/llvm/lib/DebugInfo/PDB/CMakeLists.txt
index 0be05e9..3762b97 100644
--- a/llvm/lib/DebugInfo/PDB/CMakeLists.txt
+++ b/llvm/lib/DebugInfo/PDB/CMakeLists.txt
@@ -14,11 +14,13 @@
   add_pdb_impl_folder(DIA
     DIA/DIADataStream.cpp
     DIA/DIAEnumDebugStreams.cpp
+    DIA/DIAEnumInjectedSources.cpp
     DIA/DIAEnumLineNumbers.cpp
     DIA/DIAEnumSourceFiles.cpp
     DIA/DIAEnumSymbols.cpp
     DIA/DIAEnumTables.cpp
     DIA/DIAError.cpp
+    DIA/DIAInjectedSource.cpp
     DIA/DIALineNumber.cpp
     DIA/DIARawSymbol.cpp
     DIA/DIASession.cpp
diff --git a/llvm/lib/DebugInfo/PDB/DIA/DIAEnumInjectedSources.cpp b/llvm/lib/DebugInfo/PDB/DIA/DIAEnumInjectedSources.cpp
new file mode 100644
index 0000000..873f4a0
--- /dev/null
+++ b/llvm/lib/DebugInfo/PDB/DIA/DIAEnumInjectedSources.cpp
@@ -0,0 +1,54 @@
+//==- DIAEnumSourceFiles.cpp - DIA Source File Enumerator impl ---*- C++ -*-==//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/DebugInfo/PDB/DIA/DIAEnumInjectedSources.h"
+#include "llvm/DebugInfo/PDB/DIA/DIAInjectedSource.h"
+#include "llvm/DebugInfo/PDB/PDBSymbol.h"
+
+using namespace llvm;
+using namespace llvm::pdb;
+
+DIAEnumInjectedSources::DIAEnumInjectedSources(
+    const DIASession &PDBSession,
+    CComPtr<IDiaEnumInjectedSources> DiaEnumerator)
+    : Session(PDBSession), Enumerator(DiaEnumerator) {}
+
+uint32_t DIAEnumInjectedSources::getChildCount() const {
+  LONG Count = 0;
+  return (S_OK == Enumerator->get_Count(&Count)) ? Count : 0;
+}
+
+std::unique_ptr<IPDBInjectedSource>
+DIAEnumInjectedSources::getChildAtIndex(uint32_t Index) const {
+  CComPtr<IDiaInjectedSource> Item;
+  if (S_OK != Enumerator->Item(Index, &Item))
+    return nullptr;
+
+  return std::unique_ptr<IPDBInjectedSource>(
+      new DIAInjectedSource(Session, Item));
+}
+
+std::unique_ptr<IPDBInjectedSource> DIAEnumInjectedSources::getNext() {
+  CComPtr<IDiaInjectedSource> Item;
+  ULONG NumFetched = 0;
+  if (S_OK != Enumerator->Next(1, &Item, &NumFetched))
+    return nullptr;
+
+  return std::unique_ptr<IPDBInjectedSource>(
+      new DIAInjectedSource(Session, Item));
+}
+
+void DIAEnumInjectedSources::reset() { Enumerator->Reset(); }
+
+DIAEnumInjectedSources *DIAEnumInjectedSources::clone() const {
+  CComPtr<IDiaEnumInjectedSources> EnumeratorClone;
+  if (S_OK != Enumerator->Clone(&EnumeratorClone))
+    return nullptr;
+  return new DIAEnumInjectedSources(Session, EnumeratorClone);
+}
diff --git a/llvm/lib/DebugInfo/PDB/DIA/DIAInjectedSource.cpp b/llvm/lib/DebugInfo/PDB/DIA/DIAInjectedSource.cpp
new file mode 100644
index 0000000..fbd1695
--- /dev/null
+++ b/llvm/lib/DebugInfo/PDB/DIA/DIAInjectedSource.cpp
@@ -0,0 +1,64 @@
+//===- DIAInjectedSource.cpp - DIA impl for IPDBInjectedSource --*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/DebugInfo/PDB/DIA/DIAInjectedSource.h"
+#include "llvm/ADT/ArrayRef.h"
+#include "llvm/DebugInfo/PDB/ConcreteSymbolEnumerator.h"
+#include "llvm/DebugInfo/PDB/DIA/DIASession.h"
+#include "llvm/DebugInfo/PDB/DIA/DIAUtils.h"
+
+using namespace llvm;
+using namespace llvm::pdb;
+
+DIAInjectedSource::DIAInjectedSource(const DIASession &Session,
+                                     CComPtr<IDiaInjectedSource> DiaSourceFile)
+    : Session(Session), SourceFile(DiaSourceFile) {}
+
+uint32_t DIAInjectedSource::getCrc32() const {
+  DWORD Crc;
+  return (S_OK == SourceFile->get_crc(&Crc)) ? Crc : 0;
+}
+
+uint64_t DIAInjectedSource::getCodeByteSize() const {
+  ULONGLONG Size;
+  return (S_OK == SourceFile->get_length(&Size)) ? Size : 0;
+}
+
+std::string DIAInjectedSource::getFileName() const {
+  return invokeBstrMethod(*SourceFile, &IDiaInjectedSource::get_filename);
+}
+
+std::string DIAInjectedSource::getObjectFileName() const {
+  return invokeBstrMethod(*SourceFile, &IDiaInjectedSource::get_objectFilename);
+}
+
+std::string DIAInjectedSource::getVirtualFileName() const {
+  return invokeBstrMethod(*SourceFile,
+                          &IDiaInjectedSource::get_virtualFilename);
+}
+
+PDB_SourceCompression DIAInjectedSource::getCompression() const {
+  DWORD Compression = 0;
+  if (S_OK != SourceFile->get_sourceCompression(&Compression))
+    return PDB_SourceCompression::None;
+  return static_cast<PDB_SourceCompression>(Compression);
+}
+
+std::string DIAInjectedSource::getCode() const {
+  DWORD DataSize;
+  if (S_OK != SourceFile->get_source(0, &DataSize, nullptr))
+    return "";
+
+  std::vector<uint8_t> Buffer(DataSize);
+  if (S_OK != SourceFile->get_source(DataSize, &DataSize, Buffer.data()))
+    return "";
+  assert(Buffer.size() == DataSize);
+  return std::string(reinterpret_cast<const char *>(Buffer.data()),
+                     Buffer.size());
+}
diff --git a/llvm/lib/DebugInfo/PDB/DIA/DIASession.cpp b/llvm/lib/DebugInfo/PDB/DIA/DIASession.cpp
index dcf29a5..a6bbf6f 100644
--- a/llvm/lib/DebugInfo/PDB/DIA/DIASession.cpp
+++ b/llvm/lib/DebugInfo/PDB/DIA/DIASession.cpp
@@ -9,6 +9,7 @@
 #include "llvm/DebugInfo/PDB/DIA/DIASession.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/DebugInfo/PDB/DIA/DIAEnumDebugStreams.h"
+#include "llvm/DebugInfo/PDB/DIA/DIAEnumInjectedSources.h"
 #include "llvm/DebugInfo/PDB/DIA/DIAEnumLineNumbers.h"
 #include "llvm/DebugInfo/PDB/DIA/DIAEnumSourceFiles.h"
 #include "llvm/DebugInfo/PDB/DIA/DIAEnumTables.h"
@@ -310,3 +311,31 @@
 
   return llvm::make_unique<DIAEnumTables>(DiaEnumerator);
 }
+
+static CComPtr<IDiaEnumInjectedSources>
+getEnumInjectedSources(IDiaSession &Session) {
+  CComPtr<IDiaEnumInjectedSources> EIS;
+  CComPtr<IDiaEnumTables> ET;
+  CComPtr<IDiaTable> Table;
+  ULONG Count = 0;
+
+  if (Session.getEnumTables(&ET) != S_OK)
+    return nullptr;
+
+  while (ET->Next(1, &Table, &Count) == S_OK && Count == 1) {
+    // There is only one table that matches the given iid
+    if (S_OK ==
+        Table->QueryInterface(__uuidof(IDiaEnumInjectedSources), (void **)&EIS))
+      break;
+    Table.Release();
+  }
+  return EIS;
+}
+std::unique_ptr<IPDBEnumInjectedSources>
+DIASession::getInjectedSources() const {
+  CComPtr<IDiaEnumInjectedSources> Files = getEnumInjectedSources(*Session);
+  if (!Files)
+    return nullptr;
+
+  return llvm::make_unique<DIAEnumInjectedSources>(*this, Files);
+}
diff --git a/llvm/lib/DebugInfo/PDB/Native/NativeSession.cpp b/llvm/lib/DebugInfo/PDB/Native/NativeSession.cpp
index b5875a0..481eb77 100644
--- a/llvm/lib/DebugInfo/PDB/Native/NativeSession.cpp
+++ b/llvm/lib/DebugInfo/PDB/Native/NativeSession.cpp
@@ -249,3 +249,8 @@
 std::unique_ptr<IPDBEnumTables> NativeSession::getEnumTables() const {
   return nullptr;
 }
+
+std::unique_ptr<IPDBEnumInjectedSources>
+NativeSession::getInjectedSources() const {
+  return nullptr;
+}
diff --git a/llvm/lib/DebugInfo/PDB/PDBExtras.cpp b/llvm/lib/DebugInfo/PDB/PDBExtras.cpp
index ee752cd..bb172ec 100644
--- a/llvm/lib/DebugInfo/PDB/PDBExtras.cpp
+++ b/llvm/lib/DebugInfo/PDB/PDBExtras.cpp
@@ -254,6 +254,18 @@
   return OS;
 }
 
+raw_ostream &llvm::pdb::operator<<(raw_ostream &OS,
+                                   const PDB_SourceCompression &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)
+  }
+  return OS;
+}
+
 raw_ostream &llvm::pdb::operator<<(raw_ostream &OS, const Variant &Value) {
   switch (Value.Type) {
     case PDB_VariantType::Bool:
diff --git a/llvm/lib/DebugInfo/PDB/PDBInterfaceAnchors.cpp b/llvm/lib/DebugInfo/PDB/PDBInterfaceAnchors.cpp
index b2b03fb..b66cbdc 100644
--- a/llvm/lib/DebugInfo/PDB/PDBInterfaceAnchors.cpp
+++ b/llvm/lib/DebugInfo/PDB/PDBInterfaceAnchors.cpp
@@ -12,6 +12,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/DebugInfo/PDB/IPDBDataStream.h"
+#include "llvm/DebugInfo/PDB/IPDBInjectedSource.h"
 #include "llvm/DebugInfo/PDB/IPDBLineNumber.h"
 #include "llvm/DebugInfo/PDB/IPDBRawSymbol.h"
 #include "llvm/DebugInfo/PDB/IPDBSession.h"
@@ -29,3 +30,5 @@
 IPDBLineNumber::~IPDBLineNumber() = default;
 
 IPDBTable::~IPDBTable() = default;
+
+IPDBInjectedSource::~IPDBInjectedSource() = default;