[PDB] Introduce `MSVCUndecoratedNameParser`

This patch introduces the simple MSVCUndecoratedNameParser. It is needed for
parsing names of PDB symbols corresponding to template instantiations. For
example, for the name `operator<<A>'::`2'::B::operator> we can't just split the
name with :: (as it is implemented for now) to retrieve its scopes. This parser
processes such names in a more correct way.

Differential Revision: https://reviews.llvm.org/D52461

llvm-svn: 346213

4 files changed, 155 insertions, 0 deletions

diff --git a/lldb/source/Plugins/Language/CPlusPlus/CMakeLists.txt b/lldb/source/Plugins/Language/CPlusPlus/CMakeLists.txt
index 715334412f8..bc357aa52b8 100644
--- a/lldb/source/Plugins/Language/CPlusPlus/CMakeLists.txt
+++ b/lldb/source/Plugins/Language/CPlusPlus/CMakeLists.txt
@@ -18,6 +18,7 @@ add_lldb_library(lldbPluginCPlusPlusLanguage PLUGIN
   LibStdcpp.cpp
   LibStdcppTuple.cpp
   LibStdcppUniquePointer.cpp
+  MSVCUndecoratedNameParser.cpp
 
   LINK_LIBS
     lldbCore
diff --git a/lldb/source/Plugins/Language/CPlusPlus/CPlusPlusLanguage.cpp b/lldb/source/Plugins/Language/CPlusPlus/CPlusPlusLanguage.cpp
index f437582fbd2..badfb948ed9 100644
--- a/lldb/source/Plugins/Language/CPlusPlus/CPlusPlusLanguage.cpp
+++ b/lldb/source/Plugins/Language/CPlusPlus/CPlusPlusLanguage.cpp
@@ -41,6 +41,7 @@
 #include "LibCxxAtomic.h"
 #include "LibCxxVariant.h"
 #include "LibStdcpp.h"
+#include "MSVCUndecoratedNameParser.h"
 
 using namespace lldb;
 using namespace lldb_private;
@@ -265,6 +266,10 @@ bool CPlusPlusLanguage::IsCPPMangledName(const char *name) {
 
 bool CPlusPlusLanguage::ExtractContextAndIdentifier(
     const char *name, llvm::StringRef &context, llvm::StringRef &identifier) {
+  if (MSVCUndecoratedNameParser::IsMSVCUndecoratedName(name))
+    return MSVCUndecoratedNameParser::ExtractContextAndIdentifier(name, context,
+                                                                  identifier);
+
   CPlusPlusNameParser parser(name);
   if (auto full_name = parser.ParseAsFullName()) {
     identifier = full_name.getValue().basename;
diff --git a/lldb/source/Plugins/Language/CPlusPlus/MSVCUndecoratedNameParser.cpp b/lldb/source/Plugins/Language/CPlusPlus/MSVCUndecoratedNameParser.cpp
new file mode 100644
index 00000000000..d2207566de3
--- /dev/null
+++ b/lldb/source/Plugins/Language/CPlusPlus/MSVCUndecoratedNameParser.cpp
@@ -0,0 +1,98 @@
+//===-- MSVCUndecoratedNameParser.cpp ---------------------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "MSVCUndecoratedNameParser.h"
+
+#include <stack>
+
+MSVCUndecoratedNameParser::MSVCUndecoratedNameParser(llvm::StringRef name) {
+  std::size_t last_base_start = 0;
+
+  std::stack<std::size_t> stack;
+  unsigned int open_angle_brackets = 0;
+  for (size_t i = 0; i < name.size(); i++) {
+    switch (name[i]) {
+    case '<':
+      // Do not treat `operator<' and `operator<<' as templates
+      // (sometimes they represented as `<' and `<<' in the name).
+      if (i == last_base_start ||
+          i == last_base_start + 1 && name[last_base_start] == '<')
+        break;
+
+      stack.push(i);
+      open_angle_brackets++;
+
+      break;
+    case '>':
+      if (!stack.empty() && name[stack.top()] == '<') {
+        open_angle_brackets--;
+        stack.pop();
+      }
+
+      break;
+    case '`':
+      stack.push(i);
+
+      break;
+    case '\'':
+      while (!stack.empty()) {
+        std::size_t top = stack.top();
+        if (name[top] == '<')
+          open_angle_brackets--;
+
+        stack.pop();
+
+        if (name[top] == '`')
+          break;
+      }
+
+      break;
+    case ':':
+      if (open_angle_brackets)
+        break;
+      if (i == 0 || name[i - 1] != ':')
+        break;
+
+      m_specifiers.emplace_back(name.take_front(i - 1),
+                                name.slice(last_base_start, i - 1));
+
+      last_base_start = i + 1;
+    default:
+      break;
+    }
+  }
+
+  m_specifiers.emplace_back(name, name.drop_front(last_base_start));
+}
+
+bool MSVCUndecoratedNameParser::IsMSVCUndecoratedName(llvm::StringRef name) {
+  return name.find('`') != llvm::StringRef::npos;
+}
+
+bool MSVCUndecoratedNameParser::ExtractContextAndIdentifier(
+    llvm::StringRef name, llvm::StringRef &context,
+    llvm::StringRef &identifier) {
+  MSVCUndecoratedNameParser parser(name);
+  llvm::ArrayRef<MSVCUndecoratedNameSpecifier> specs = parser.GetSpecifiers();
+
+  std::size_t count = specs.size();
+  identifier = count > 0 ? specs[count - 1].GetBaseName() : "";
+  context = count > 1 ? specs[count - 2].GetFullName() : "";
+
+  return count;
+}
+
+llvm::StringRef MSVCUndecoratedNameParser::DropScope(llvm::StringRef name) {
+  MSVCUndecoratedNameParser parser(name);
+  llvm::ArrayRef<MSVCUndecoratedNameSpecifier> specs = parser.GetSpecifiers();
+  if (specs.empty())
+    return "";
+
+  return specs[specs.size() - 1].GetBaseName();
+}
diff --git a/lldb/source/Plugins/Language/CPlusPlus/MSVCUndecoratedNameParser.h b/lldb/source/Plugins/Language/CPlusPlus/MSVCUndecoratedNameParser.h
new file mode 100644
index 00000000000..0c49100d8d4
--- /dev/null
+++ b/lldb/source/Plugins/Language/CPlusPlus/MSVCUndecoratedNameParser.h
@@ -0,0 +1,51 @@
+//===-- MSVCUndecoratedNameParser.h -----------------------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef liblldb_MSVCUndecoratedNameParser_h_
+#define liblldb_MSVCUndecoratedNameParser_h_
+
+#include <vector>
+
+#include "llvm/ADT/ArrayRef.h"
+#include "llvm/ADT/StringRef.h"
+
+class MSVCUndecoratedNameSpecifier {
+public:
+  MSVCUndecoratedNameSpecifier(llvm::StringRef full_name,
+                               llvm::StringRef base_name)
+      : m_full_name(full_name), m_base_name(base_name) {}
+
+  llvm::StringRef GetFullName() const { return m_full_name; }
+  llvm::StringRef GetBaseName() const { return m_base_name; }
+
+private:
+  llvm::StringRef m_full_name;
+  llvm::StringRef m_base_name;
+};
+
+class MSVCUndecoratedNameParser {
+public:
+  explicit MSVCUndecoratedNameParser(llvm::StringRef name);
+
+  llvm::ArrayRef<MSVCUndecoratedNameSpecifier> GetSpecifiers() const {
+    return m_specifiers;
+  }
+
+  static bool IsMSVCUndecoratedName(llvm::StringRef name);
+  static bool ExtractContextAndIdentifier(llvm::StringRef name,
+                                          llvm::StringRef &context,
+                                          llvm::StringRef &identifier);
+
+  static llvm::StringRef DropScope(llvm::StringRef name);
+
+private:
+  std::vector<MSVCUndecoratedNameSpecifier> m_specifiers;
+};
+
+#endif