[Lldb-commits] [lldb] [lldb] Load embedded type summary section (#7859) (#8040) (PR #113743)

[David Spickett via lldb-commits]

================
@@ -1537,6 +1538,76 @@ static void LoadScriptingResourceForModule(const ModuleSP &module_sp,
                                                   feedback_stream.GetData());
 }
 
+// Load type summaries embedded in the binary. These are type summaries provided
+// by the authors of the code.
+static void LoadTypeSummariesForModule(ModuleSP module_sp) {
+  auto *sections = module_sp->GetSectionList();
+  if (!sections)
+    return;
+
+  auto summaries_sp =
+      sections->FindSectionByType(eSectionTypeLLDBTypeSummaries, true);
+  if (!summaries_sp)
+    return;
+
+  Log *log = GetLog(LLDBLog::DataFormatters);
+  const char *module_name = module_sp->GetObjectName().GetCString();
+
+  TypeCategoryImplSP category;
+  DataVisualization::Categories::GetCategory(ConstString("default"), category);
+
+  // The type summary record is serialized as follows.
+  //
+  // Each record contains, in order:
+  //   * Version number of the record format
+  //   * The remaining size of the record
+  //   * The size of the type identifier
+  //   * The type identifier, either a type name, or a regex
+  //   * The size of the summary string
+  //   * The summary string
+  //
+  // Integers are encoded using ULEB.
+  //
+  // Strings are encoded with first a length (ULEB), then the string contents,
+  // and lastly a null terminator. The length includes the null.
+
+  DataExtractor extractor;
+  auto section_size = summaries_sp->GetSectionData(extractor);
+  lldb::offset_t offset = 0;
+  while (offset < section_size) {
+    uint64_t version = extractor.GetULEB128(&offset);
+    uint64_t record_size = extractor.GetULEB128(&offset);
+    if (version == 1) {
+      uint64_t type_size = extractor.GetULEB128(&offset);
+      llvm::StringRef type_name = extractor.GetCStr(&offset, type_size);
+      uint64_t summary_size = extractor.GetULEB128(&offset);
+      llvm::StringRef summary_string = extractor.GetCStr(&offset, summary_size);
+      if (!type_name.empty() && !summary_string.empty()) {
+        TypeSummaryImpl::Flags flags;
+        auto summary_sp =
+            std::make_shared<StringSummaryFormat>(flags, summary_string.data());
+        FormatterMatchType match_type = eFormatterMatchExact;
+        if (summary_string.front() == '^' && summary_string.back() == '$')
+          match_type = eFormatterMatchRegex;
+        category->AddTypeSummary(type_name, match_type, summary_sp);
+        LLDB_LOGF(log, "Loaded embedded type summary for '%s' from %s.",
+                  type_name.data(), module_name);
+      } else {
+        if (type_name.empty())
----------------
DavidSpickett wrote:

Should this log message always be printed? It looks like you have to have both strings so if you get to the else, one of them is empty. This will only log if one of them is empty but not the other one.

Might as well put in what strings they are too. "Missing type or summary string in....".

https://github.com/llvm/llvm-project/pull/113743