Straight forward FastDemangle replacement in SubsPrimitiveParmItanium

[sgraenitz]

Summary

Removing FastDemangle will greatly reduce maintenance efforts. This patch replaces the last point of use in LLDB. Semantics should be kept intact.

Once this is agreed upon, we can:

• Remove the FastDemangle sources
• Add more features e.g. substitutions in template parameters, considering all variations, etc.

Depends on LLVM patch https://reviews.llvm.org/D50586

[JDevlieghere]

source/Plugins/Language/CPlusPlus/CPlusPlusLanguage.cpp

281

I had to look at the old code to understand the name of this struct. How about DemangleContext or even just Context?

292

typo: substitute

316

In the other patch you call this argument a callback, maybe do the same here for consistency?

[sgraenitz]

Address Jonas' comments, fix logging, fix copying over remaining part from original, polishing

[sgraenitz]

source/Plugins/Language/CPlusPlus/CPlusPlusLanguage.cpp

281

Aligned it with the function name

340

This was missing. Also added a test.

[JDevlieghere]

Looks good to me.

source/Plugins/Language/CPlusPlus/CPlusPlusLanguage.cpp

 // C++ Includes
 #include <functional>
 #include <memory>
 #include <mutex>
 #include <set>
 
 // Other libraries and framework includes
 #include "llvm/ADT/StringRef.h"
+#include "llvm/Demangle/Demangle.h"
 
 // Project includes
 #include "lldb/Core/PluginManager.h"
 #include "lldb/Core/UniqueCStringMap.h"
 #include "lldb/DataFormatters/CXXFunctionPointer.h"
 #include "lldb/DataFormatters/DataVisualization.h"
 #include "lldb/DataFormatters/FormattersHelpers.h"
 #include "lldb/DataFormatters/VectorType.h"
 #include "lldb/Utility/ConstString.h"
-#include "lldb/Utility/FastDemangle.h"
 #include "lldb/Utility/Log.h"
 #include "lldb/Utility/RegularExpression.h"
 
 #include "BlockPointer.h"
 #include "CPlusPlusNameParser.h"
 #include "CxxStringTypes.h"
 #include "LibCxx.h"
 #include "LibCxxAtomic.h"
bool CPlusPlusLanguage::ExtractContextAndIdentifier(
   return false;
 }
 
 /// Given a mangled function `mangled`, replace all the primitive function type
 /// arguments of `search` with type `replace`.
 static ConstString SubsPrimitiveParmItanium(llvm::StringRef mangled,
                                             llvm::StringRef search,
                                             llvm::StringRef replace) {
-  Log *log = GetLogIfAllCategoriesSet(LIBLLDB_LOG_LANGUAGE);
-
-  const size_t max_len =
-      mangled.size() + mangled.count(search) * replace.size() + 1;
-
-  // Make a temporary buffer to fix up the mangled parameter types and copy the
-  // original there
-  std::string output_buf;
-  output_buf.reserve(max_len);
-  output_buf.insert(0, mangled.str());
-  ptrdiff_t replaced_offset = 0;
-
-  auto swap_parms_hook = [&](const char *parsee) {
-    if (!parsee || !*parsee)
-      return;
+  struct SwapParms {
+    llvm::StringRef mangled;
+    llvm::StringRef search;
+    llvm::StringRef replace;
+    ptrdiff_t read_pos;
+    std::back_insert_iterator<std::string> writer;
+
+    SwapParms(llvm::StringRef m, llvm::StringRef s, llvm::StringRef r,
+              std::back_insert_iterator<std::string> w)
+        : mangled(m), search(s), replace(r), read_pos(0), writer(w) {}
+
+    void Substitude(llvm::StringRef tail) {
+      if (tail.startswith(search)) {
+        ptrdiff_t read_len = tail.data() - mangled.data();
+        auto reader = mangled.begin() + read_pos;
+
+        // First write the unmatched part of the original. Then write the
+        // replacement string. Finally skip the search string in the original.
+        writer = std::copy(reader, reader + read_len, writer);
+        writer = std::copy(replace.begin(), replace.end(), writer);
+        read_pos += read_len + search.size();
+      }
+    }
 
-    // Check whether we've found a substitutee
-    llvm::StringRef s(parsee);
-    if (s.startswith(search)) {
-      // account for the case where a replacement is of a different length to
-      // the original
-      replaced_offset += replace.size() - search.size();
-
-      ptrdiff_t replace_idx = (mangled.size() - s.size()) + replaced_offset;
-      output_buf.erase(replace_idx, search.size());
-      output_buf.insert(replace_idx, replace.str());
+    static void Hook(void *context, const char *match) {
+      ((SwapParms *)context)->Substitude(llvm::StringRef(match));
     }
   };
 
   // FastDemangle will call our hook for each instance of a primitive type,
   // allowing us to perform substitution
-  char *const demangled =
-      FastDemangle(mangled.str().c_str(), mangled.size(), swap_parms_hook);
-
-  if (log)
-    log->Printf("substituted mangling for %s:{%s} %s:{%s}\n",
-                mangled.str().c_str(), demangled, output_buf.c_str(),
-                FastDemangle(output_buf.c_str()));
-  // FastDemangle malloc'd this string.
-  free(demangled);
+  std::string output_buf;
+  SwapParms context(mangled, search, replace, std::back_inserter(output_buf));
+  assert(mangled.data()[mangled.size()] == '\0' && "Expect C-String");
+  bool err = llvm::itaniumFindTypesInMangledName(mangled.data(), &context,
+                                                 SwapParms::Hook);
+
+  if (Log *log = GetLogIfAllCategoriesSet(LIBLLDB_LOG_LANGUAGE)) {
+    if (err)
+      LLDB_LOG(log, "Substituted mangling {0} -> {1}", mangled, output_buf);
+    else
+      LLDB_LOG(log, "Failed to substitute mangling in {0}", mangled);
+  }
 
-  return output_buf == mangled ? ConstString() : ConstString(output_buf);
+  return ConstString(output_buf);
 }
 
 uint32_t CPlusPlusLanguage::FindAlternateFunctionManglings(
     const ConstString mangled_name, std::set<ConstString> &alternates) {
   const auto start_size = alternates.size();
   /// Get a basic set of alternative manglings for the given symbol `name`, by
   /// making a few basic possible substitutions on basic types, storage duration
   /// and `const`ness for the given symbol. The output parameter `alternates`
   /// is filled with a best-guess, non-exhaustive set of different manglings
   /// for the given name.
 
   // Maybe we're looking for a const symbol but the debug info told us it was
   // non-const...
   if (!strncmp(mangled_name.GetCString(), "_ZN", 3) &&
       strncmp(mangled_name.GetCString(), "_ZNK", 4)) {
     std::string fixed_scratch("_ZNK");
     fixed_scratch.append(mangled_name.GetCString() + 3);
     alternates.insert(ConstString(fixed_scratch));
   }
 
   // Maybe we're looking for a static symbol but we thought it was global...
   if (!strncmp(mangled_name.GetCString(), "_Z", 2) &&
       strncmp(mangled_name.GetCString(), "_ZL", 3)) {