[LLDB] Refactored CPlusPlusLanguage::MethodName to break lldb-server dependencies

This patch addresses the issue #129543.
After this patch the size of lldb-server is reduced by 9MB.

Co-authored-by: @bulbazord Alex Langford

Author: slydiman

lldb/include/lldb/Core/Mangled.h

@@ -246,6 +246,8 @@ class Mangled {
   ///     for s, otherwise the enumerator for the mangling scheme detected.
   static Mangled::ManglingScheme GetManglingScheme(llvm::StringRef const name);
 
+  static bool IsCPPMangledName(llvm::StringRef name);
+
   /// Decode a serialized version of this object from data.
   ///
   /// \param data

lldb/include/lldb/Core/RichManglingContext.h

@@ -12,6 +12,7 @@
 #include "lldb/lldb-forward.h"
 #include "lldb/lldb-private.h"
 
+#include "lldb/Target/Language.h"
 #include "lldb/Utility/ConstString.h"
 
 #include "llvm/ADT/Any.h"
@@ -67,11 +68,7 @@ class RichManglingContext {
   char *m_ipd_buf;
   size_t m_ipd_buf_size = 2048;
 
-  /// Members for PluginCxxLanguage
-  /// Cannot forward declare inner class CPlusPlusLanguage::MethodName. The
-  /// respective header is in Plugins and including it from here causes cyclic
-  /// dependency. Instead keep a llvm::Any and cast it on-access in the cpp.
-  llvm::Any m_cxx_method_parser;
+  std::unique_ptr<Language::MethodName> m_cxx_method_parser;
 
   /// Clean up memory when using PluginCxxLanguage
   void ResetCxxMethodParser();
@@ -81,15 +78,6 @@ class RichManglingContext {
 
   /// Uniform handling of string buffers for ItaniumPartialDemangler.
   llvm::StringRef processIPDStrResult(char *ipd_res, size_t res_len);
-
-  /// Cast the given parser to the given type. Ideally we would have a type
-  /// trait to deduce \a ParserT from a given InfoProvider, but unfortunately we
-  /// can't access CPlusPlusLanguage::MethodName from within the header.
-  template <class ParserT> static ParserT *get(llvm::Any parser) {
-    assert(parser.has_value());
-    assert(llvm::any_cast<ParserT *>(&parser));
-    return *llvm::any_cast<ParserT *>(&parser);
-  }
 };
 
 } // namespace lldb_private

lldb/include/lldb/Target/Language.h

@@ -214,6 +214,104 @@ class Language : public PluginInterface {
     return std::vector<Language::MethodNameVariant>();
   };
 
+  class MethodName {
+  public:
+    MethodName() {}
+
+    MethodName(ConstString full)
+        : m_full(full), m_basename(), m_context(), m_arguments(),
+          m_qualifiers(), m_return_type(), m_scope_qualified(), m_parsed(false),
+          m_parse_error(false) {}
+
+    virtual ~MethodName() {};
+
+    void Clear() {
+      m_full.Clear();
+      m_basename = llvm::StringRef();
+      m_context = llvm::StringRef();
+      m_arguments = llvm::StringRef();
+      m_qualifiers = llvm::StringRef();
+      m_return_type = llvm::StringRef();
+      m_scope_qualified.clear();
+      m_parsed = false;
+      m_parse_error = false;
+    }
+
+    bool IsValid() {
+      if (!m_parsed)
+        Parse();
+      if (m_parse_error)
+        return false;
+      return (bool)m_full;
+    }
+
+    ConstString GetFullName() const { return m_full; }
+
+    llvm::StringRef GetBasename() {
+      if (!m_parsed)
+        Parse();
+      return m_basename;
+    }
+
+    llvm::StringRef GetContext() {
+      if (!m_parsed)
+        Parse();
+      return m_context;
+    }
+
+    llvm::StringRef GetArguments() {
+      if (!m_parsed)
+        Parse();
+      return m_arguments;
+    }
+
+    llvm::StringRef GetQualifiers() {
+      if (!m_parsed)
+        Parse();
+      return m_qualifiers;
+    }
+
+    llvm::StringRef GetReturnType() {
+      if (!m_parsed)
+        Parse();
+      return m_return_type;
+    }
+
+    std::string GetScopeQualifiedName() {
+      if (!m_parsed)
+        Parse();
+      return m_scope_qualified;
+    }
+
+  protected:
+    virtual void Parse() {
+      m_parsed = true;
+      m_parse_error = true;
+    }
+
+    ConstString m_full; // Full name:
+                        // "size_t lldb::SBTarget::GetBreakpointAtIndex(unsigned
+                        // int) const"
+    llvm::StringRef m_basename;    // Basename:     "GetBreakpointAtIndex"
+    llvm::StringRef m_context;     // Decl context: "lldb::SBTarget"
+    llvm::StringRef m_arguments;   // Arguments:    "(unsigned int)"
+    llvm::StringRef m_qualifiers;  // Qualifiers:   "const"
+    llvm::StringRef m_return_type; // Return type:  "size_t"
+    std::string m_scope_qualified;
+    bool m_parsed = false;
+    bool m_parse_error = false;
+  };
+
+  virtual std::unique_ptr<Language::MethodName>
+  GetMethodName(ConstString name) const {
+    return std::make_unique<Language::MethodName>(name);
+  };
+
+  virtual std::pair<lldb::FunctionNameType, llvm::StringRef>
+  GetFunctionNameInfo(ConstString name) const {
+    return std::pair{lldb::eFunctionNameTypeNone, llvm::StringRef()};
+  };
+
   /// Returns true iff the given symbol name is compatible with the mangling
   /// scheme of this language.
   ///

lldb/source/Core/CMakeLists.txt

@@ -71,8 +71,6 @@ add_lldb_library(lldbCore
     lldbUtility
     lldbValueObject
     lldbVersion
-    lldbPluginCPlusPlusLanguage
-    lldbPluginObjCLanguage
     ${LLDB_CURSES_LIBS}
 
   CLANG_LIBS

lldb/source/Core/Mangled.cpp

@@ -39,6 +39,11 @@ static inline bool cstring_is_mangled(llvm::StringRef s) {
 
 #pragma mark Mangled
 
+bool Mangled::IsCPPMangledName(llvm::StringRef name) {
+  Mangled::ManglingScheme scheme = Mangled::GetManglingScheme(name);
+  return (scheme != Mangled::eManglingSchemeNone);
+}
+
 Mangled::ManglingScheme Mangled::GetManglingScheme(llvm::StringRef const name) {
   if (name.empty())
     return Mangled::eManglingSchemeNone;

lldb/source/Core/Module.cpp

@@ -52,9 +52,6 @@
 #include "lldb/Host/windows/PosixApi.h"
 #endif
 
-#include "Plugins/Language/CPlusPlus/CPlusPlusLanguage.h"
-#include "Plugins/Language/ObjC/ObjCLanguage.h"
-
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/Support/Compiler.h"
 #include "llvm/Support/DJB.h"
@@ -641,98 +638,75 @@ void Module::FindCompileUnits(const FileSpec &path,
 Module::LookupInfo::LookupInfo(ConstString name,
                                FunctionNameType name_type_mask,
                                LanguageType language)
-    : m_name(name), m_lookup_name(), m_language(language) {
-  const char *name_cstr = name.GetCString();
+    : m_name(name), m_lookup_name(name), m_language(language) {
   llvm::StringRef basename;
-  llvm::StringRef context;
+
+  std::vector<Language *> languages;
+  auto collect_language_plugins = [&languages](Language *lang) {
+    languages.push_back(lang);
+    return true;
+  };
 
   if (name_type_mask & eFunctionNameTypeAuto) {
-    if (CPlusPlusLanguage::IsCPPMangledName(name_cstr))
-      m_name_type_mask = eFunctionNameTypeFull;
-    else if ((language == eLanguageTypeUnknown ||
-              Language::LanguageIsObjC(language)) &&
-             ObjCLanguage::IsPossibleObjCMethodName(name_cstr))
-      m_name_type_mask = eFunctionNameTypeFull;
-    else if (Language::LanguageIsC(language)) {
-      m_name_type_mask = eFunctionNameTypeFull;
+    if (language == eLanguageTypeUnknown) {
+      Language::ForEach(collect_language_plugins);
+      for (Language *lang : languages) {
+        auto info = lang->GetFunctionNameInfo(name);
+        if (info.first != eFunctionNameTypeNone) {
+          m_name_type_mask |= info.first;
+          basename = info.second;
+          break;
+        }
+      }
     } else {
-      if ((language == eLanguageTypeUnknown ||
-           Language::LanguageIsObjC(language)) &&
-          ObjCLanguage::IsPossibleObjCSelector(name_cstr))
-        m_name_type_mask |= eFunctionNameTypeSelector;
-
-      CPlusPlusLanguage::MethodName cpp_method(name);
-      basename = cpp_method.GetBasename();
-      if (basename.empty()) {
-        if (CPlusPlusLanguage::ExtractContextAndIdentifier(name_cstr, context,
-                                                           basename))
-          m_name_type_mask |= (eFunctionNameTypeMethod | eFunctionNameTypeBase);
-        else
-          m_name_type_mask |= eFunctionNameTypeFull;
-      } else {
-        m_name_type_mask |= (eFunctionNameTypeMethod | eFunctionNameTypeBase);
+      if (auto *lang = Language::FindPlugin(language)) {
+        auto info = lang->GetFunctionNameInfo(name);
+        m_name_type_mask = info.first;
+        basename = info.second;
       }
     }
+
+    // NOTE: There are several ways to get here, but this is a fallback path in
+    // case the above does not succeed at extracting any useful information from
+    // the loaded language plugins.
+    if (m_name_type_mask == eFunctionNameTypeNone)
+      m_name_type_mask = eFunctionNameTypeFull;
+
   } else {
     m_name_type_mask = name_type_mask;
-    if (name_type_mask & eFunctionNameTypeMethod ||
-        name_type_mask & eFunctionNameTypeBase) {
-      // If they've asked for a CPP method or function name and it can't be
-      // that, we don't even need to search for CPP methods or names.
-      CPlusPlusLanguage::MethodName cpp_method(name);
-      if (cpp_method.IsValid()) {
-        basename = cpp_method.GetBasename();
-
-        if (!cpp_method.GetQualifiers().empty()) {
-          // There is a "const" or other qualifier following the end of the
-          // function parens, this can't be a eFunctionNameTypeBase
-          m_name_type_mask &= ~(eFunctionNameTypeBase);
-          if (m_name_type_mask == eFunctionNameTypeNone)
-            return;
+    if (language == eLanguageTypeUnknown) {
+      Language::ForEach(collect_language_plugins);
+      for (Language *lang : languages) {
+        auto info = lang->GetFunctionNameInfo(name);
+        if (info.first & m_name_type_mask) {
+          m_name_type_mask &= info.first;
+          basename = info.second;
+          break;
         }
-      } else {
-        // If the CPP method parser didn't manage to chop this up, try to fill
-        // in the base name if we can. If a::b::c is passed in, we need to just
-        // look up "c", and then we'll filter the result later.
-        CPlusPlusLanguage::ExtractContextAndIdentifier(name_cstr, context,
-                                                       basename);
-      }
-    }
-
-    if (name_type_mask & eFunctionNameTypeSelector) {
-      if (!ObjCLanguage::IsPossibleObjCSelector(name_cstr)) {
-        m_name_type_mask &= ~(eFunctionNameTypeSelector);
-        if (m_name_type_mask == eFunctionNameTypeNone)
-          return;
       }
-    }
-
-    // Still try and get a basename in case someone specifies a name type mask
-    // of eFunctionNameTypeFull and a name like "A::func"
-    if (basename.empty()) {
-      if (name_type_mask & eFunctionNameTypeFull &&
-          !CPlusPlusLanguage::IsCPPMangledName(name_cstr)) {
-        CPlusPlusLanguage::MethodName cpp_method(name);
-        basename = cpp_method.GetBasename();
-        if (basename.empty())
-          CPlusPlusLanguage::ExtractContextAndIdentifier(name_cstr, context,
-                                                         basename);
+    } else {
+      if (auto *lang = Language::FindPlugin(language)) {
+        auto info = lang->GetFunctionNameInfo(name);
+        if (info.first & m_name_type_mask) {
+          // If the user asked for FunctionNameTypes that aren't possible,
+          // then filter those out. (e.g. asking for Selectors on
+          // C++ symbols, or even if the symbol given can't be a selector in
+          // ObjC)
+          m_name_type_mask &= info.first;
+          basename = info.second;
+        }
       }
     }
   }
 
   if (!basename.empty()) {
-    // The name supplied was a partial C++ path like "a::count". In this case
-    // we want to do a lookup on the basename "count" and then make sure any
-    // matching results contain "a::count" so that it would match "b::a::count"
-    // and "a::count". This is why we set "match_name_after_lookup" to true
+    // The name supplied was incomplete for lookup purposes. For example, in C++
+    // we may have gotten something like "a::count". In this case, we want to do
+    // a lookup on the basename "count" and then make sure any matching results
+    // contain "a::count" so that it would match "b::a::count" and "a::count".
+    // This is why we set match_name_after_lookup to true.
     m_lookup_name.SetString(basename);
     m_match_name_after_lookup = true;
-  } else {
-    // The name is already correct, just use the exact name as supplied, and we
-    // won't need to check if any matches contain "name"
-    m_lookup_name = name;
-    m_match_name_after_lookup = false;
   }
 }
 
@@ -791,7 +765,8 @@ void Module::LookupInfo::Prune(SymbolContextList &sc_list,
   // "func" and specified eFunctionNameTypeFull, but we might have found
   // "a::func()", "a::b::func()", "c::func()", "func()" and "func". Only
   // "func()" and "func" should end up matching.
-  if (m_name_type_mask == eFunctionNameTypeFull) {
+  auto *lang = Language::FindPlugin(eLanguageTypeC_plus_plus);
+  if (lang && m_name_type_mask == eFunctionNameTypeFull) {
     SymbolContext sc;
     size_t i = start_idx;
     while (i < sc_list.GetSize()) {
@@ -802,20 +777,21 @@ void Module::LookupInfo::Prune(SymbolContextList &sc_list,
       ConstString mangled_name(sc.GetFunctionName(Mangled::ePreferMangled));
       ConstString full_name(sc.GetFunctionName());
       if (mangled_name != m_name && full_name != m_name) {
-        CPlusPlusLanguage::MethodName cpp_method(full_name);
-        if (cpp_method.IsValid()) {
-          if (cpp_method.GetContext().empty()) {
-            if (cpp_method.GetBasename().compare(m_name) != 0) {
+        std::unique_ptr<Language::MethodName> cpp_method =
+            lang->GetMethodName(full_name);
+        if (cpp_method->IsValid()) {
+          if (cpp_method->GetContext().empty()) {
+            if (cpp_method->GetBasename().compare(m_name) != 0) {
               sc_list.RemoveContextAtIndex(i);
               continue;
             }
           } else {
             std::string qualified_name;
             llvm::StringRef anon_prefix("(anonymous namespace)");
-            if (cpp_method.GetContext() == anon_prefix)
-              qualified_name = cpp_method.GetBasename().str();
+            if (cpp_method->GetContext() == anon_prefix)
+              qualified_name = cpp_method->GetBasename().str();
             else
-              qualified_name = cpp_method.GetScopeQualifiedName();
+              qualified_name = cpp_method->GetScopeQualifiedName();
             if (qualified_name != m_name.GetCString()) {
               sc_list.RemoveContextAtIndex(i);
               continue;
@@ -988,8 +964,7 @@ DebuggersOwningModuleRequestingInterruption(Module &module) {
   for (auto debugger_sp : requestors) {
     if (!debugger_sp->InterruptRequested())
       continue;
-    if (debugger_sp->GetTargetList()
-        .AnyTargetContainsModule(module))
+    if (debugger_sp->GetTargetList().AnyTargetContainsModule(module))
       interruptors.push_back(debugger_sp);
   }
   return interruptors;