[LLDB] Add type summaries for MSVC STL strings (#143177)

This PR adds type summaries for
`std::{string,wstring,u8string,u16string,u32string}` from the MSVC STL.

See https://github.com/llvm/llvm-project/issues/24834 for the MSVC STL
issue.

The following changes were made:

- `dotest.py` now detects if the MSVC STL is available. It does so by
looking at the target triple, which is an additional argument passed
from Lit. It specifically checks for `windows-msvc` to not match on
`windows-gnu` (i.e. MinGW/Cygwin).
- (The main part): Added support for summarizing `std::(w)string` from
MSVC's STL. Because the type names from the libstdc++ (pre C++ 11)
string types are the same as on MSVC's STL, `CXXCompositeSummaryFormat`
is used with two entries, one for MSVC's STL and one for libstdc++.
With MSVC's STL, `std::u{8,16,32}string` is also handled. These aren't
handled for libstdc++, so I put them in `LoadMsvcStlFormatters`.

4 files changed, 300 insertions, 29 deletions

diff --git a/lldb/source/Plugins/Language/CPlusPlus/CMakeLists.txt b/lldb/source/Plugins/Language/CPlusPlus/CMakeLists.txt
index 5ba2567c80cc..bbfc31a722f2 100644
--- a/lldb/source/Plugins/Language/CPlusPlus/CMakeLists.txt
+++ b/lldb/source/Plugins/Language/CPlusPlus/CMakeLists.txt
@@ -32,6 +32,7 @@ add_lldb_library(lldbPluginCPlusPlusLanguage PLUGIN
   LibStdcpp.cpp
   LibStdcppTuple.cpp
   LibStdcppUniquePointer.cpp
+  MsvcStl.cpp
   MSVCUndecoratedNameParser.cpp
 
   LINK_COMPONENTS
diff --git a/lldb/source/Plugins/Language/CPlusPlus/CPlusPlusLanguage.cpp b/lldb/source/Plugins/Language/CPlusPlus/CPlusPlusLanguage.cpp
index e64b3ebabd74..17963c0273ba 100644
--- a/lldb/source/Plugins/Language/CPlusPlus/CPlusPlusLanguage.cpp
+++ b/lldb/source/Plugins/Language/CPlusPlus/CPlusPlusLanguage.cpp
@@ -46,6 +46,7 @@
 #include "LibCxxVariant.h"
 #include "LibStdcpp.h"
 #include "MSVCUndecoratedNameParser.h"
+#include "MsvcStl.h"
 #include "lldb/lldb-enumerations.h"
 
 using namespace lldb;
@@ -1331,6 +1332,37 @@ static void LoadLibCxxFormatters(lldb::TypeCategoryImplSP cpp_category_sp) {
           "${var.__y_} ${var.__m_} ${var.__wdl_}")));
 }
 
+static void RegisterStdStringSummaryProvider(
+    const lldb::TypeCategoryImplSP &category_sp, llvm::StringRef string_ty,
+    llvm::StringRef char_ty, lldb::TypeSummaryImplSP summary_sp) {
+  auto makeSpecifier = [](llvm::StringRef name) {
+    return std::make_shared<lldb_private::TypeNameSpecifierImpl>(
+        name, eFormatterMatchExact);
+  };
+
+  category_sp->AddTypeSummary(makeSpecifier(string_ty), summary_sp);
+
+  // std::basic_string<char>
+  category_sp->AddTypeSummary(
+      makeSpecifier(llvm::formatv("std::basic_string<{}>", char_ty).str()),
+      summary_sp);
+  // std::basic_string<char,std::char_traits<char>,std::allocator<char> >
+  category_sp->AddTypeSummary(
+      makeSpecifier(llvm::formatv("std::basic_string<{0},std::char_traits<{0}>,"
+                                  "std::allocator<{0}> >",
+                                  char_ty)
+                        .str()),
+      summary_sp);
+  // std::basic_string<char, std::char_traits<char>, std::allocator<char> >
+  category_sp->AddTypeSummary(
+      makeSpecifier(
+          llvm::formatv("std::basic_string<{0}, std::char_traits<{0}>, "
+                        "std::allocator<{0}> >",
+                        char_ty)
+              .str()),
+      summary_sp);
+}
+
 static void LoadLibStdcppFormatters(lldb::TypeCategoryImplSP cpp_category_sp) {
   if (!cpp_category_sp)
     return;
@@ -1347,18 +1379,6 @@ static void LoadLibStdcppFormatters(lldb::TypeCategoryImplSP cpp_category_sp) {
   lldb::TypeSummaryImplSP string_summary_sp(new CXXFunctionSummaryFormat(
       stl_summary_flags, LibStdcppStringSummaryProvider,
       "libstdc++ std::(w)string summary provider"));
-
-  cpp_category_sp->AddTypeSummary("std::string", eFormatterMatchExact,
-                                  string_summary_sp);
-  cpp_category_sp->AddTypeSummary("std::basic_string<char>",
-                                  eFormatterMatchExact, string_summary_sp);
-  cpp_category_sp->AddTypeSummary(
-      "std::basic_string<char,std::char_traits<char>,std::allocator<char> >",
-      eFormatterMatchExact, string_summary_sp);
-  cpp_category_sp->AddTypeSummary(
-      "std::basic_string<char, std::char_traits<char>, std::allocator<char> >",
-      eFormatterMatchExact, string_summary_sp);
-
   cpp_category_sp->AddTypeSummary("std::__cxx11::string", eFormatterMatchExact,
                                   string_summary_sp);
   cpp_category_sp->AddTypeSummary(
@@ -1370,23 +1390,6 @@ static void LoadLibStdcppFormatters(lldb::TypeCategoryImplSP cpp_category_sp) {
                                   "std::allocator<unsigned char> >",
                                   eFormatterMatchExact, string_summary_sp);
 
-  // making sure we force-pick the summary for printing wstring (_M_p is a
-  // wchar_t*)
-  lldb::TypeSummaryImplSP std_wstring_summary_sp(
-      new StringSummaryFormat(stl_summary_flags, "${var._M_dataplus._M_p%S}"));
-
-  cpp_category_sp->AddTypeSummary("std::wstring", eFormatterMatchExact,
-                                  std_wstring_summary_sp);
-  cpp_category_sp->AddTypeSummary("std::basic_string<wchar_t>",
-                                  eFormatterMatchExact, std_wstring_summary_sp);
-  cpp_category_sp->AddTypeSummary("std::basic_string<wchar_t,std::char_traits<"
-                                  "wchar_t>,std::allocator<wchar_t> >",
-                                  eFormatterMatchExact, std_wstring_summary_sp);
-  cpp_category_sp->AddTypeSummary(
-      "std::basic_string<wchar_t, std::char_traits<wchar_t>, "
-      "std::allocator<wchar_t> >",
-      eFormatterMatchExact, std_wstring_summary_sp);
-
   cpp_category_sp->AddTypeSummary("std::__cxx11::wstring", eFormatterMatchExact,
                                   string_summary_sp);
   cpp_category_sp->AddTypeSummary(
@@ -1595,6 +1598,81 @@ static void LoadLibStdcppFormatters(lldb::TypeCategoryImplSP cpp_category_sp) {
                 "^std::optional<.+>(( )?&)?$", stl_summary_flags, true);
 }
 
+/// Load formatters that are formatting types from more than one STL
+static void LoadCommonStlFormatters(lldb::TypeCategoryImplSP cpp_category_sp) {
+  if (!cpp_category_sp)
+    return;
+
+  TypeSummaryImpl::Flags stl_summary_flags;
+  stl_summary_flags.SetCascades(true)
+      .SetSkipPointers(false)
+      .SetSkipReferences(false)
+      .SetDontShowChildren(true)
+      .SetDontShowValue(false)
+      .SetShowMembersOneLiner(false)
+      .SetHideItemNames(false);
+  using StringElementType = StringPrinter::StringElementType;
+
+  RegisterStdStringSummaryProvider(
+      cpp_category_sp, "std::string", "char",
+      std::make_shared<CXXFunctionSummaryFormat>(
+          stl_summary_flags,
+          [](ValueObject &valobj, Stream &stream,
+             const TypeSummaryOptions &options) {
+            if (IsMsvcStlStringType(valobj))
+              return MsvcStlStringSummaryProvider<StringElementType::ASCII>(
+                  valobj, stream, options);
+            return LibStdcppStringSummaryProvider(valobj, stream, options);
+          },
+          "MSVC STL/libstdc++ std::string summary provider"));
+  RegisterStdStringSummaryProvider(
+      cpp_category_sp, "std::wstring", "wchar_t",
+      std::make_shared<CXXFunctionSummaryFormat>(
+          stl_summary_flags,
+          [](ValueObject &valobj, Stream &stream,
+             const TypeSummaryOptions &options) {
+            if (IsMsvcStlStringType(valobj))
+              return MsvcStlWStringSummaryProvider(valobj, stream, options);
+            return LibStdcppStringSummaryProvider(valobj, stream, options);
+          },
+          "MSVC STL/libstdc++ std::wstring summary provider"));
+}
+
+static void LoadMsvcStlFormatters(lldb::TypeCategoryImplSP cpp_category_sp) {
+  if (!cpp_category_sp)
+    return;
+
+  TypeSummaryImpl::Flags stl_summary_flags;
+  stl_summary_flags.SetCascades(true)
+      .SetSkipPointers(false)
+      .SetSkipReferences(false)
+      .SetDontShowChildren(true)
+      .SetDontShowValue(false)
+      .SetShowMembersOneLiner(false)
+      .SetHideItemNames(false);
+
+  using StringElementType = StringPrinter::StringElementType;
+
+  RegisterStdStringSummaryProvider(
+      cpp_category_sp, "std::u8string", "char8_t",
+      std::make_shared<CXXFunctionSummaryFormat>(
+          stl_summary_flags,
+          MsvcStlStringSummaryProvider<StringElementType::UTF8>,
+          "MSVC STL std::u8string summary provider"));
+  RegisterStdStringSummaryProvider(
+      cpp_category_sp, "std::u16string", "char16_t",
+      std::make_shared<CXXFunctionSummaryFormat>(
+          stl_summary_flags,
+          MsvcStlStringSummaryProvider<StringElementType::UTF16>,
+          "MSVC STL std::u16string summary provider"));
+  RegisterStdStringSummaryProvider(
+      cpp_category_sp, "std::u32string", "char32_t",
+      std::make_shared<CXXFunctionSummaryFormat>(
+          stl_summary_flags,
+          MsvcStlStringSummaryProvider<StringElementType::UTF32>,
+          "MSVC STL std::u32string summary provider"));
+}
+
 static void LoadSystemFormatters(lldb::TypeCategoryImplSP cpp_category_sp) {
   if (!cpp_category_sp)
     return;
@@ -1709,6 +1787,8 @@ lldb::TypeCategoryImplSP CPlusPlusLanguage::GetFormatters() {
       // LLDB prioritizes the last loaded matching formatter.
       LoadLibCxxFormatters(g_category);
       LoadLibStdcppFormatters(g_category);
+      LoadMsvcStlFormatters(g_category);
+      LoadCommonStlFormatters(g_category);
       LoadSystemFormatters(g_category);
     }
   });
diff --git a/lldb/source/Plugins/Language/CPlusPlus/MsvcStl.cpp b/lldb/source/Plugins/Language/CPlusPlus/MsvcStl.cpp
new file mode 100644
index 000000000000..5d0f20b1beaa
--- /dev/null
+++ b/lldb/source/Plugins/Language/CPlusPlus/MsvcStl.cpp
@@ -0,0 +1,155 @@
+//===-- MsvcStl.cpp -------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "MsvcStl.h"
+
+#include "lldb/Core/Debugger.h"
+#include "lldb/Core/FormatEntity.h"
+#include "lldb/DataFormatters/StringPrinter.h"
+#include "lldb/DataFormatters/TypeSummary.h"
+#include "lldb/Utility/ConstString.h"
+#include "lldb/Utility/Status.h"
+#include "lldb/Utility/Stream.h"
+#include "lldb/ValueObject/ValueObject.h"
+
+#include "Plugins/Language/CPlusPlus/CxxStringTypes.h"
+
+#include "lldb/lldb-forward.h"
+#include <optional>
+#include <tuple>
+
+using namespace lldb;
+using namespace lldb_private;
+using namespace lldb_private::formatters;
+
+using StringElementType = StringPrinter::StringElementType;
+
+template <StringElementType element_type>
+static constexpr uint64_t StringElementByteSize() {
+  switch (element_type) {
+  case StringElementType::ASCII:
+  case StringElementType::UTF8:
+    return 1;
+  case StringElementType::UTF16:
+    return 2;
+  case StringElementType::UTF32:
+    return 3;
+  }
+  return 0;
+}
+
+static ValueObjectSP ExtractMsvcStlStringData(ValueObject &valobj) {
+  return valobj.GetChildAtNamePath({"_Mypair", "_Myval2"});
+}
+
+/// Determine the size in bytes of \p valobj (a MSVC STL std::string object) and
+/// extract its data payload. Return the size + payload pair.
+static std::optional<std::pair<uint64_t, ValueObjectSP>>
+ExtractMsvcStlStringInfo(ValueObject &valobj, uint64_t element_size) {
+  ValueObjectSP valobj_pair_sp = ExtractMsvcStlStringData(valobj);
+  if (!valobj_pair_sp || !valobj_pair_sp->GetError().Success())
+    return {};
+
+  ValueObjectSP size_sp = valobj_pair_sp->GetChildMemberWithName("_Mysize");
+  ValueObjectSP capacity_sp = valobj_pair_sp->GetChildMemberWithName("_Myres");
+  ValueObjectSP bx_sp = valobj_pair_sp->GetChildMemberWithName("_Bx");
+  if (!size_sp || !capacity_sp || !bx_sp)
+    return {};
+
+  bool success = false;
+  uint64_t size = size_sp->GetValueAsUnsigned(0, &success);
+  if (!success)
+    return {};
+  uint64_t capacity = capacity_sp->GetValueAsUnsigned(0, &success);
+  if (!success)
+    return {};
+
+  size_t bufSize = std::max<size_t>(16 / element_size, 1);
+  bool isShortString = capacity < bufSize;
+
+  if (isShortString) {
+    ValueObjectSP buf_sp = bx_sp->GetChildMemberWithName("_Buf");
+    if (buf_sp)
+      return std::make_pair(size, buf_sp);
+    return {};
+  }
+  ValueObjectSP ptr_sp = bx_sp->GetChildMemberWithName("_Ptr");
+  if (ptr_sp)
+    return std::make_pair(size, ptr_sp);
+  return {};
+}
+
+template <StringPrinter::StringElementType element_type>
+static bool
+MsvcStlStringSummaryProviderImpl(ValueObject &valobj, Stream &stream,
+                                 const TypeSummaryOptions &summary_options,
+                                 std::string prefix_token) {
+  auto string_info =
+      ExtractMsvcStlStringInfo(valobj, StringElementByteSize<element_type>());
+  if (!string_info)
+    return false;
+  auto [size, location_sp] = *string_info;
+
+  return StringBufferSummaryProvider<element_type>(
+      stream, summary_options, location_sp, size, prefix_token);
+}
+template <StringPrinter::StringElementType element_type>
+static bool formatStringImpl(ValueObject &valobj, Stream &stream,
+                             const TypeSummaryOptions &summary_options,
+                             std::string prefix_token) {
+  StreamString scratch_stream;
+  const bool success = MsvcStlStringSummaryProviderImpl<element_type>(
+      valobj, scratch_stream, summary_options, prefix_token);
+  if (success)
+    stream << scratch_stream.GetData();
+  else
+    stream << "Summary Unavailable";
+  return true;
+}
+
+bool lldb_private::formatters::IsMsvcStlStringType(ValueObject &valobj) {
+  std::vector<uint32_t> indexes;
+  return valobj.GetCompilerType().GetIndexOfChildMemberWithName("_Mypair", true,
+                                                                indexes) > 0;
+}
+
+bool lldb_private::formatters::MsvcStlWStringSummaryProvider(
+    ValueObject &valobj, Stream &stream,
+    const TypeSummaryOptions &summary_options) {
+  return formatStringImpl<StringElementType::UTF16>(valobj, stream,
+                                                    summary_options, "L");
+}
+
+template <>
+bool lldb_private::formatters::MsvcStlStringSummaryProvider<
+    StringElementType::ASCII>(ValueObject &valobj, Stream &stream,
+                              const TypeSummaryOptions &summary_options) {
+  return MsvcStlStringSummaryProviderImpl<StringElementType::ASCII>(
+      valobj, stream, summary_options, "");
+}
+template <>
+bool lldb_private::formatters::MsvcStlStringSummaryProvider<
+    StringElementType::UTF8>(ValueObject &valobj, Stream &stream,
+                             const TypeSummaryOptions &summary_options) {
+  return MsvcStlStringSummaryProviderImpl<StringElementType::UTF8>(
+      valobj, stream, summary_options, "u8");
+}
+template <>
+bool lldb_private::formatters::MsvcStlStringSummaryProvider<
+    StringElementType::UTF16>(ValueObject &valobj, Stream &stream,
+                              const TypeSummaryOptions &summary_options) {
+  return MsvcStlStringSummaryProviderImpl<StringElementType::UTF16>(
+      valobj, stream, summary_options, "u");
+}
+template <>
+bool lldb_private::formatters::MsvcStlStringSummaryProvider<
+    StringElementType::UTF32>(ValueObject &valobj, Stream &stream,
+                              const TypeSummaryOptions &summary_options) {
+  return MsvcStlStringSummaryProviderImpl<StringElementType::UTF32>(
+      valobj, stream, summary_options, "U");
+}
diff --git a/lldb/source/Plugins/Language/CPlusPlus/MsvcStl.h b/lldb/source/Plugins/Language/CPlusPlus/MsvcStl.h
new file mode 100644
index 000000000000..e4ed923033aa
--- /dev/null
+++ b/lldb/source/Plugins/Language/CPlusPlus/MsvcStl.h
@@ -0,0 +1,35 @@
+//===-- MsvcStl.h -----------------------------------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLDB_SOURCE_PLUGINS_LANGUAGE_CPLUSPLUS_MSVCSTL_H
+#define LLDB_SOURCE_PLUGINS_LANGUAGE_CPLUSPLUS_MSVCSTL_H
+
+#include "lldb/DataFormatters/StringPrinter.h"
+#include "lldb/DataFormatters/TypeSummary.h"
+#include "lldb/Utility/Stream.h"
+#include "lldb/ValueObject/ValueObject.h"
+
+namespace lldb_private {
+namespace formatters {
+
+bool IsMsvcStlStringType(ValueObject &valobj);
+
+template <StringPrinter::StringElementType element_type>
+bool MsvcStlStringSummaryProvider(
+    ValueObject &valobj, Stream &stream,
+    const TypeSummaryOptions
+        &summary_options); // VC 2015+ std::string,u8string,u16string,u32string
+
+bool MsvcStlWStringSummaryProvider(
+    ValueObject &valobj, Stream &stream,
+    const TypeSummaryOptions &options); // VC 2015+ std::wstring
+
+} // namespace formatters
+} // namespace lldb_private
+
+#endif