[Lldb-commits] [PATCH] D41086: [lldb] Stop searching for a symbol in a pdb by regex

[Aaron Smith via Phabricator via lldb-commits]

asmith updated this revision to Diff 127803.
asmith retitled this revision from "[lldb] Check that a regex is valid before 
searching by regex for a symbol in a pdb." to "[lldb] Stop searching for a 
symbol in a pdb by regex".
asmith edited the summary of this revision.

Repository:
  rL LLVM

https://reviews.llvm.org/D41086

Files:
  source/Plugins/SymbolFile/PDB/PDBASTParser.cpp
  source/Plugins/SymbolFile/PDB/SymbolFilePDB.cpp
  source/Plugins/SymbolFile/PDB/SymbolFilePDB.h
  unittests/SymbolFile/PDB/SymbolFilePDBTests.cpp


Index: unittests/SymbolFile/PDB/SymbolFilePDBTests.cpp
===================================================================
--- unittests/SymbolFile/PDB/SymbolFilePDBTests.cpp
+++ unittests/SymbolFile/PDB/SymbolFilePDBTests.cpp
@@ -520,6 +520,13 @@
                                             false, 0, searched_files, results);
   EXPECT_GT(num_results, 1u);
   EXPECT_EQ(num_results, results.GetSize());
+
+  // We expect no exception thrown if the given regex can't be compiled
+  results.Clear();
+  num_results = symfile->FindTypes(sc, ConstString("**"), nullptr,
+                                   false, 0, searched_files, results);
+  EXPECT_EQ(num_results, 0u);
+  EXPECT_EQ(num_results, results.GetSize());
 }
 
 TEST_F(SymbolFilePDBTests, TestMaxMatches) {
Index: source/Plugins/SymbolFile/PDB/SymbolFilePDB.h
===================================================================
--- source/Plugins/SymbolFile/PDB/SymbolFilePDB.h
+++ source/Plugins/SymbolFile/PDB/SymbolFilePDB.h
@@ -172,7 +172,8 @@
       const llvm::pdb::PDBSymbolCompiland &cu,
       llvm::DenseMap<uint32_t, uint32_t> &index_map) const;
 
-  void FindTypesByRegex(const std::string &regex, uint32_t max_matches,
+  void FindTypesByRegex(const lldb_private::RegularExpression &regex,
+                        uint32_t max_matches,
                         lldb_private::TypeMap &types);
 
   void FindTypesByName(const std::string &name, uint32_t max_matches,
Index: source/Plugins/SymbolFile/PDB/SymbolFilePDB.cpp
===================================================================
--- source/Plugins/SymbolFile/PDB/SymbolFilePDB.cpp
+++ source/Plugins/SymbolFile/PDB/SymbolFilePDB.cpp
@@ -19,6 +19,7 @@
 #include "lldb/Symbol/ObjectFile.h"
 #include "lldb/Symbol/SymbolContext.h"
 #include "lldb/Symbol/TypeMap.h"
+#include "lldb/Utility/RegularExpression.h"
 
 #include "llvm/DebugInfo/PDB/GenericError.h"
 #include "llvm/DebugInfo/PDB/IPDBEnumChildren.h"
@@ -250,7 +251,8 @@
     return nullptr;
 
   lldb::TypeSP result = pdb->CreateLLDBTypeFromPDBType(*pdb_type);
-  m_types.insert(std::make_pair(type_uid, result));
+  if (result.get())
+    m_types.insert(std::make_pair(type_uid, result));
   return result.get();
 }
 
@@ -385,19 +387,16 @@
 
   std::string name_str = name.AsCString();
 
-  // If this might be a regex, we have to return EVERY symbol and process them
-  // one by one, which is going to destroy performance on large PDB files.  So
-  // try really hard not to use a regex match.
-  if (name_str.find_first_of("[]?*.-+\\") != std::string::npos)
-    FindTypesByRegex(name_str, max_matches, types);
-  else
-    FindTypesByName(name_str, max_matches, types);
+  // There is an assumption 'name' is not a regex
+  FindTypesByName(name_str, max_matches, types);
+   
   return types.GetSize();
 }
 
-void SymbolFilePDB::FindTypesByRegex(const std::string &regex,
-                                     uint32_t max_matches,
-                                     lldb_private::TypeMap &types) {
+void
+SymbolFilePDB::FindTypesByRegex(const lldb_private::RegularExpression &regex,
+                                uint32_t max_matches,
+                                lldb_private::TypeMap &types) {
   // When searching by regex, we need to go out of our way to limit the search
   // space as much as possible since this searches EVERYTHING in the PDB,
   // manually doing regex comparisons.  PDB library isn't optimized for regex
@@ -409,8 +408,6 @@
   auto global = m_session_up->getGlobalScope();
   std::unique_ptr<IPDBEnumSymbols> results;
 
-  std::regex re(regex);
-
   uint32_t matches = 0;
 
   for (auto tag : tags_to_search) {
@@ -433,7 +430,7 @@
         continue;
       }
 
-      if (!std::regex_match(type_name, re))
+      if (!regex.Execute(type_name))
         continue;
 
       // This should cause the type to get cached and stored in the `m_types`
Index: source/Plugins/SymbolFile/PDB/PDBASTParser.cpp
===================================================================
--- source/Plugins/SymbolFile/PDB/PDBASTParser.cpp
+++ source/Plugins/SymbolFile/PDB/PDBASTParser.cpp
@@ -124,6 +124,8 @@
   } else if (auto type_def = llvm::dyn_cast<PDBSymbolTypeTypedef>(&type)) {
     lldb_private::Type *target_type =
         m_ast.GetSymbolFile()->ResolveTypeUID(type_def->getTypeId());
+    if (!target_type)
+      return nullptr;
     std::string name = type_def->getName();
     uint64_t bytes = type_def->getLength();
     if (!target_type)
@@ -179,6 +181,8 @@
 
     lldb_private::Type *element_type =
         m_ast.GetSymbolFile()->ResolveTypeUID(element_uid);
+    if (!element_type)
+      return nullptr;
     CompilerType element_ast_type = element_type->GetFullCompilerType();
     CompilerType array_ast_type =
         m_ast.CreateArrayType(element_ast_type, num_elements, false);

_______________________________________________
lldb-commits mailing list
lldb-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/lldb-commits