[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`.

lldb/packages/Python/lldbsuite/test/dotest.py

@@ -831,6 +831,46 @@ def checkLibstdcxxSupport():
     configuration.skip_categories.append("libstdcxx")
 
 
+def canRunMsvcStlTests():
+    from lldbsuite.test import lldbplatformutil
+
+    platform = lldbplatformutil.getPlatform()
+    if platform != "windows":
+        return False, f"Don't know how to build with MSVC's STL on {platform}"
+
+    with tempfile.NamedTemporaryFile() as f:
+        cmd = [configuration.compiler, "-xc++", "-o", f.name, "-E", "-"]
+        p = subprocess.Popen(
+            cmd,
+            stdin=subprocess.PIPE,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
+            universal_newlines=True,
+        )
+        _, stderr = p.communicate(
+            """
+            #include <yvals_core.h>
+            #ifndef _MSVC_STL_VERSION
+            #error _MSVC_STL_VERSION not defined
+            #endif
+            """
+        )
+        if not p.returncode:
+            return True, "Compiling with MSVC STL"
+        return (False, f"Not compiling with MSVC STL: {stderr}")
+
+
+def checkMsvcStlSupport():
+    result, reason = canRunMsvcStlTests()
+    if result:
+        return  # msvcstl supported
+    if "msvcstl" in configuration.categories_list:
+        return  # msvcstl category explicitly requested, let it run.
+    if configuration.verbose:
+        print(f"msvcstl tests will not be run because: {reason}")
+    configuration.skip_categories.append("msvcstl")
+
+
 def canRunWatchpointTests():
     from lldbsuite.test import lldbplatformutil
 
@@ -1044,6 +1084,7 @@ def run_suite():
 
     checkLibcxxSupport()
     checkLibstdcxxSupport()
+    checkMsvcStlSupport()
     checkWatchpointSupport()
     checkDebugInfoSupport()
     checkDebugServerSupport()

lldb/packages/Python/lldbsuite/test/test_categories.py

@@ -33,6 +33,7 @@ all_categories = {
     "lldb-server": "Tests related to lldb-server",
     "lldb-dap": "Tests for the Debug Adapter Protocol with lldb-dap",
     "llgs": "Tests for the gdb-server functionality of lldb-server",
+    "msvcstl": "Test for MSVC STL data formatters",
     "pexpect": "Tests requiring the pexpect library to be available",
     "objc": "Tests related to the Objective-C programming language support",
     "pyapi": "Tests related to the Python API",

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

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);
     }
   });

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");
+}

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

lldb/test/API/functionalities/data-formatter/data-formatter-skip-summary/TestDataFormatterSkipSummary.py

@@ -10,10 +10,6 @@ from lldbsuite.test import lldbutil
 
 
 class SkipSummaryDataFormatterTestCase(TestBase):
-    @expectedFailureAll(
-        oslist=["windows"],
-        bugnumber="llvm.org/pr24462, Data formatters have problems on Windows",
-    )
     def test_with_run_command(self):
         """Test data formatter commands."""
         self.build()

lldb/test/API/functionalities/data-formatter/data-formatter-stl/msvcstl/string/Makefile

@@ -0,0 +1,3 @@
+CXX_SOURCES := main.cpp
+
+include Makefile.rules

lldb/test/API/functionalities/data-formatter/data-formatter-stl/msvcstl/string/TestDataFormatterMsvcStlString.py

@@ -0,0 +1,120 @@
+# coding=utf8
+"""
+Test std::*string summaries with MSVC's STL.
+"""
+
+
+import lldb
+from lldbsuite.test.decorators import *
+from lldbsuite.test.lldbtest import *
+from lldbsuite.test import lldbutil
+
+
+class MsvcStlStringDataFormatterTestCase(TestBase):
+    NO_DEBUG_INFO_TESTCASE = True
+
+    @add_test_categories(["msvcstl"])
+    def test_with_run_command(self):
+        """Test that that file and class static variables display correctly."""
+        self.build()
+
+        main_spec = lldb.SBFileSpec("main.cpp")
+        (target, process, thread, bkpt) = lldbutil.run_to_source_breakpoint(
+            self, "Set break point at this line.", main_spec
+        )
+        frame = thread.frames[0]
+
+        # This is the function to remove the custom formats in order to have a
+        # clean slate for the next test case.
+        def cleanup():
+            self.runCmd("type format clear", check=False)
+            self.runCmd("type summary clear", check=False)
+            self.runCmd("type filter clear", check=False)
+            self.runCmd("type synth clear", check=False)
+
+        # Execute the cleanup function during test case tear down.
+        self.addTearDownHook(cleanup)
+
+        self.expect(
+            "frame variable",
+            substrs=[
+                '(std::wstring) wempty = L""',
+                '(std::wstring) s = L"hello world! מזל טוב!"',
+                '(std::wstring) S = L"!!!!"',
+                "(const wchar_t *) mazeltov = 0x",
+                'L"מזל טוב"',
+                '(std::string) empty = ""',
+                '(std::string) q = "hello world"',
+                '(std::string) Q = "quite a long std::strin with lots of info inside it"',
+                '(std::string) overwritten_zero = "abc"',
+                '(std::string) IHaveEmbeddedZeros = "a\\0b\\0c\\0d"',
+                '(std::wstring) IHaveEmbeddedZerosToo = L"hello world!\\0てざ ル゜䋨ミ㠧槊 きゅへ狦穤襩 じゃ馩リョ 䤦監"',
+                '(std::u16string) u16_string = u"ß水氶"',
+                '(std::u16string) u16_empty = u""',
+                '(std::u32string) u32_string = U"🍄🍅🍆🍌"',
+                '(std::u32string) u32_empty = U""',
+                "(std::string *) null_str = nullptr",
+            ],
+        )
+
+        thread.StepOver()
+
+        TheVeryLongOne = frame.FindVariable("TheVeryLongOne")
+        summaryOptions = lldb.SBTypeSummaryOptions()
+        summaryOptions.SetCapping(lldb.eTypeSummaryUncapped)
+        uncappedSummaryStream = lldb.SBStream()
+        TheVeryLongOne.GetSummary(uncappedSummaryStream, summaryOptions)
+        uncappedSummary = uncappedSummaryStream.GetData()
+        self.assertGreater(
+            uncappedSummary.find("someText"),
+            0,
+            "uncappedSummary does not include the full string",
+        )
+        summaryOptions.SetCapping(lldb.eTypeSummaryCapped)
+        cappedSummaryStream = lldb.SBStream()
+        TheVeryLongOne.GetSummary(cappedSummaryStream, summaryOptions)
+        cappedSummary = cappedSummaryStream.GetData()
+        self.assertLessEqual(
+            cappedSummary.find("someText"), 0, "cappedSummary includes the full string"
+        )
+
+        self.expect_expr(
+            "s", result_type="std::wstring", result_summary='L"hello world! מזל טוב!"'
+        )
+
+        self.expect_expr("q", result_type="std::string", result_summary='"hello world"')
+
+        self.expect_expr(
+            "Q",
+            result_type="std::string",
+            result_summary='"quite a long std::strin with lots of info inside it"',
+        )
+
+        self.expect(
+            "frame variable",
+            substrs=[
+                '(std::wstring) S = L"!!!!!"',
+                "(const wchar_t *) mazeltov = 0x",
+                'L"מזל טוב"',
+                '(std::string) q = "hello world"',
+                '(std::string) Q = "quite a long std::strin with lots of info inside it"',
+                '(std::string) IHaveEmbeddedZeros = "a\\0b\\0c\\0d"',
+                '(std::wstring) IHaveEmbeddedZerosToo = L"hello world!\\0てざ ル゜䋨ミ㠧槊 きゅへ狦穤襩 じゃ馩リョ 䤦監"',
+                '(std::u16string) u16_string = u"ß水氶"',
+                '(std::u32string) u32_string = U"🍄🍅🍆🍌"',
+                '(std::u32string) u32_empty = U""',
+                "(std::string *) null_str = nullptr",
+            ],
+        )
+
+        # Finally, make sure that if the string is not readable, we give an error:
+        bkpt_2 = target.BreakpointCreateBySourceRegex(
+            "Break here to look at bad string", main_spec
+        )
+        self.assertEqual(bkpt_2.GetNumLocations(), 1, "Got one location")
+        threads = lldbutil.continue_to_breakpoint(process, bkpt_2)
+        self.assertEqual(len(threads), 1, "Stopped at second breakpoint")
+        frame = threads[0].frames[0]
+        var = frame.FindVariable("in_str")
+        self.assertTrue(var.GetError().Success(), "Made variable")
+        self.assertIsNone(var.GetSummary())

lldb/test/API/functionalities/data-formatter/data-formatter-stl/msvcstl/u8string/Makefile

@@ -0,0 +1,4 @@
+CXX_SOURCES := main.cpp
+
+CXXFLAGS_EXTRAS := -std=c++20 -O0
+include Makefile.rules

lldb/test/API/functionalities/data-formatter/data-formatter-stl/msvcstl/u8string/TestDataFormatterMsvcStlU8String.py

@@ -0,0 +1,33 @@
+# coding=utf8
+"""
+Test std::u8string summary with MSVC's STL.
+"""
+
+
+import lldb
+from lldbsuite.test.decorators import *
+from lldbsuite.test.lldbtest import *
+from lldbsuite.test import lldbutil
+
+
+class MsvcStlU8StringDataFormatterTestCase(TestBase):
+    NO_DEBUG_INFO_TESTCASE = True
+
+    @add_test_categories(["msvcstl"])
+    def test_with_run_command(self):
+        """Test that that file and class static variables display correctly."""
+        self.build()
+
+        lldbutil.run_to_source_breakpoint(
+            self, "Set break point at this line.", lldb.SBFileSpec("main.cpp")
+        )
+
+        self.expect(
+            "frame variable",
+            substrs=[
+                '(std::u8string) u8_string_small = u8"🍄"',
+                '(std::u8string) u8_string = u8"❤️👍📄📁😃🧑‍🌾"',
+                '(std::u8string) u8_empty = u8""',
+                '(std::u8string) u8_text = u8"ABC"',
+            ],
+        )

lldb/test/API/functionalities/data-formatter/data-formatter-stl/msvcstl/u8string/main.cpp

@@ -0,0 +1,14 @@
+#include <string>
+
+#ifndef _MSVC_STL_VERSION
+// this is more of a sanity check that the categories work as expected
+#error Not using MSVC STL
+#endif
+
+int main() {
+  std::u8string u8_string_small(u8"🍄");
+  std::u8string u8_string(u8"❤️👍📄📁😃🧑‍🌾");
+  std::u8string u8_empty(u8"");
+  std::u8string u8_text(u8"ABC");
+  u8_text.assign(u8"ABCd"); // Set break point at this line.
+}

lldb/test/API/functionalities/data-formatter/stringprinter/TestStringPrinter.py

@@ -4,5 +4,4 @@ from lldbsuite.test import decorators
 lldbinline.MakeInlineTest(
     __file__,
     globals(),
-    [decorators.expectedFailureAll(oslist=["windows"], bugnumber="llvm.org/pr24772")],
 )

lldb/test/API/python_api/sbvalue_persist/TestSBValuePersist.py

@@ -10,7 +10,6 @@ from lldbsuite.test import lldbutil
 class SBValuePersistTestCase(TestBase):
     NO_DEBUG_INFO_TESTCASE = True
 
-    @expectedFailureAll(oslist=["windows"], bugnumber="llvm.org/pr24772")
     def test(self):
         """Test SBValue::Persist"""
         self.build()