Adding formatters for libc++ std::u16string and std::u32string

[shafik]

Summary

We currently support formatting for std::string and std::wstring but not std::u16string and std::u32string which was added with C++11. This adds support for these two types via refactoring for the existing std::string formatter.

[jingham]

This looks reasonable to me.

packages/Python/lldbsuite/test/functionalities/data-formatter/data-formatter-stl/libcxx/string/Makefile

 LEVEL = ../../../../../make
 
 CXX_SOURCES := main.cpp
 
 USE_LIBCPP := 1
 include $(LEVEL)/Makefile.rules
-CXXFLAGS += -O0
+CXXFLAGS += -std=c++11 -O0

packages/Python/lldbsuite/test/functionalities/data-formatter/data-formatter-stl/libcxx/string/TestDataFormatterLibcxxString.py

def test_with_run_command(self):
             substrs=[
                 '(%s::wstring) s = L"hello world! מזל טוב!"'%ns,
                 '(%s::wstring) S = L"!!!!"'%ns,
                 '(const wchar_t *) mazeltov = 0x',
                 'L"מזל טוב"',
                 '(%s::string) q = "hello world"'%ns,
                 '(%s::string) Q = "quite a long std::strin with lots of info inside it"'%ns,
                 '(%s::string) IHaveEmbeddedZeros = "a\\0b\\0c\\0d"'%ns,
-                '(%s::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"'%ns])
+                '(%s::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"'%ns,
+                '(%s::u16string) u16_string = u"ß水氶"'%ns,
+                '(%s::u32string) u32_string = U"🍄🍅🍆🍌"'%ns])
 
         self.runCmd("n")
 
         TheVeryLongOne = self.frame().FindVariable("TheVeryLongOne")
         summaryOptions = lldb.SBTypeSummaryOptions()
         summaryOptions.SetCapping(lldb.eTypeSummaryUncapped)
         uncappedSummaryStream = lldb.SBStream()
         TheVeryLongOne.GetSummary(uncappedSummaryStream, summaryOptions)
def test_with_run_command(self):
             substrs=[
                 '(%s::wstring) s = L"hello world! מזל טוב!"'%ns,
                 '(%s::wstring) S = L"!!!!!"'%ns,
                 '(const wchar_t *) mazeltov = 0x',
                 'L"מזל טוב"',
                 '(%s::string) q = "hello world"'%ns,
                 '(%s::string) Q = "quite a long std::strin with lots of info inside it"'%ns,
                 '(%s::string) IHaveEmbeddedZeros = "a\\0b\\0c\\0d"'%ns,
-                '(%s::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"'%ns])
+                '(%s::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"'%ns,
+                '(%s::u16string) u16_string = u"ß水氶"'%ns,
+                '(%s::u32string) u32_string = U"🍄🍅🍆🍌"'%ns])

packages/Python/lldbsuite/test/functionalities/data-formatter/data-formatter-stl/libcxx/string/main.cpp

 #include <string>
 
 int main()
 {
     std::wstring s(L"hello world! מזל טוב!");
     std::wstring S(L"!!!!");
     const wchar_t *mazeltov = L"מזל טוב";
     std::string q("hello world");
     std::string Q("quite a long std::strin with lots of info inside it");
     std::string TheVeryLongOne("1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890someText1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890");
     std::string IHaveEmbeddedZeros("a\0b\0c\0d",7);
     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", 38);
+    std::u16string u16_string(u"ß水氶");
+    std::u32string u32_string(U"🍄🍅🍆🍌");
     S.assign(L"!!!!!"); // Set break point at this line.
     return 0;
 }

source/Plugins/Language/CPlusPlus/CPlusPlusLanguage.cpp

stl_summary_flags.SetCascades(true)
       .SetSkipReferences(false)
       .SetDontShowChildren(true)
       .SetDontShowValue(true)
       .SetShowMembersOneLiner(false)
       .SetHideItemNames(false);
 
 #ifndef LLDB_DISABLE_PYTHON
   lldb::TypeSummaryImplSP std_string_summary_sp(new CXXFunctionSummaryFormat(
-      stl_summary_flags, lldb_private::formatters::LibcxxStringSummaryProvider,
+      stl_summary_flags,
+      lldb_private::formatters::LibcxxStringSummaryProviderASCII,
       "std::string summary provider"));
+  lldb::TypeSummaryImplSP std_stringu16_summary_sp(new CXXFunctionSummaryFormat(
+      stl_summary_flags,
+      lldb_private::formatters::LibcxxStringSummaryProviderUTF16,
+      "std::u16string summary provider"));
+  lldb::TypeSummaryImplSP std_stringu32_summary_sp(new CXXFunctionSummaryFormat(
+      stl_summary_flags,
+      lldb_private::formatters::LibcxxStringSummaryProviderUTF32,
+      "std::u32string summary provider"));
   lldb::TypeSummaryImplSP std_wstring_summary_sp(new CXXFunctionSummaryFormat(
       stl_summary_flags, lldb_private::formatters::LibcxxWStringSummaryProvider,
       "std::wstring summary provider"));
 
   cpp_category_sp->GetTypeSummariesContainer()->Add(
       ConstString("std::__1::string"), std_string_summary_sp);
   cpp_category_sp->GetTypeSummariesContainer()->Add(
       ConstString("std::__ndk1::string"), std_string_summary_sp);
   cpp_category_sp->GetTypeSummariesContainer()->Add(
       ConstString("std::__1::basic_string<char, std::__1::char_traits<char>, "
                   "std::__1::allocator<char> >"),
       std_string_summary_sp);
   cpp_category_sp->GetTypeSummariesContainer()->Add(
+      ConstString(
+          "std::__1::basic_string<char16_t, std::__1::char_traits<char16_t>, "
+          "std::__1::allocator<char16_t> >"),
+      std_stringu16_summary_sp);
+  cpp_category_sp->GetTypeSummariesContainer()->Add(
+      ConstString(
+          "std::__1::basic_string<char32_t, std::__1::char_traits<char32_t>, "
+          "std::__1::allocator<char32_t> >"),
+      std_stringu32_summary_sp);
+  cpp_category_sp->GetTypeSummariesContainer()->Add(
       ConstString("std::__ndk1::basic_string<char, "
                   "std::__ndk1::char_traits<char>, "
                   "std::__ndk1::allocator<char> >"),
       std_string_summary_sp);
 
   cpp_category_sp->GetTypeSummariesContainer()->Add(
       ConstString("std::__1::wstring"), std_wstring_summary_sp);
   cpp_category_sp->GetTypeSummariesContainer()->Add(

source/Plugins/Language/CPlusPlus/LibCxx.h

 #include "lldb/Core/ValueObject.h"
 #include "lldb/DataFormatters/TypeSummary.h"
 #include "lldb/DataFormatters/TypeSynthetic.h"
 #include "lldb/Utility/Stream.h"
 
 namespace lldb_private {
 namespace formatters {
 
-bool LibcxxStringSummaryProvider(
+bool LibcxxStringSummaryProviderASCII(
     ValueObject &valobj, Stream &stream,
-    const TypeSummaryOptions &options); // libc++ std::string
+    const TypeSummaryOptions &summary_options); // libc++ std::string
+
+bool LibcxxStringSummaryProviderUTF16(
+    ValueObject &valobj, Stream &stream,
+    const TypeSummaryOptions &summary_options); // libc++ std::u16string
+
+bool LibcxxStringSummaryProviderUTF32(
+    ValueObject &valobj, Stream &stream,
+    const TypeSummaryOptions &summary_options); // libc++ std::u32string
 
 bool LibcxxWStringSummaryProvider(
     ValueObject &valobj, Stream &stream,
     const TypeSummaryOptions &options); // libc++ std::wstring
 
 bool LibcxxOptionalSummaryProvider(
     ValueObject &valobj, Stream &stream,
     const TypeSummaryOptions &options); // libc++ std::optional<>

source/Plugins/Language/CPlusPlus/LibCxx.cpp

bool lldb_private::formatters::LibcxxWStringSummaryProvider(
   default:
     stream.Printf("size for wchar_t is not valid");
     return true;
   }
 
   return true;
 }
 
-bool lldb_private::formatters::LibcxxStringSummaryProvider(
-    ValueObject &valobj, Stream &stream,
-    const TypeSummaryOptions &summary_options) {
+template <StringPrinter::StringElementType element_type>
+bool LibcxxStringSummaryProvider(ValueObject &valobj, Stream &stream,
+                                 const TypeSummaryOptions &summary_options,
+                                 std::string prefix_token = "") {
   uint64_t size = 0;
   ValueObjectSP location_sp;
 
   if (!ExtractLibcxxStringInfo(valobj, location_sp, size))
     return false;
 
   if (size == 0) {
     stream.Printf("\"\"");
if (size > max_size) {
       size = max_size;
       options.SetIsTruncated(true);
     }
   }
   location_sp->GetPointeeData(extractor, 0, size);
 
   options.SetData(extractor);
   options.SetStream(&stream);
+
+  if (prefix_token.empty())
     options.SetPrefixToken(nullptr);
+  else
+    options.SetPrefixToken(prefix_token);
+
   options.SetQuote('"');
   options.SetSourceSize(size);
   options.SetBinaryZeroIsTerminator(false);
-  StringPrinter::ReadBufferAndDumpToStream<
-      StringPrinter::StringElementType::ASCII>(options);
+  StringPrinter::ReadBufferAndDumpToStream<element_type>(options);
 
   return true;
 }
+
+bool lldb_private::formatters::LibcxxStringSummaryProviderASCII(
+    ValueObject &valobj, Stream &stream,
+    const TypeSummaryOptions &summary_options) {
+  return LibcxxStringSummaryProvider<StringPrinter::StringElementType::ASCII>(
+      valobj, stream, summary_options);
+}
+
+bool lldb_private::formatters::LibcxxStringSummaryProviderUTF16(
+    ValueObject &valobj, Stream &stream,
+    const TypeSummaryOptions &summary_options) {
+  return LibcxxStringSummaryProvider<StringPrinter::StringElementType::UTF16>(
+      valobj, stream, summary_options, "u");
+}
+
+bool lldb_private::formatters::LibcxxStringSummaryProviderUTF32(
+    ValueObject &valobj, Stream &stream,
+    const TypeSummaryOptions &summary_options) {
+  return LibcxxStringSummaryProvider<StringPrinter::StringElementType::UTF32>(
+      valobj, stream, summary_options, "U");
+}