[ASTImporter] Add check for correct import of source locations.

[balazske]

Summary

Unit tests extended with a new check for source locations.
Currently a simple match check in the node text dumps is done.
The new check is disabled for now, until the failures are fixed.

[balazske]

This test will work theoretically only if the order of every imported Decl (and not only FieldDecl) is correct, this is not the case now. So probably a better solution for the problem should be found: Enumerate and match (the From and To) SourceLocations with AST visitor. There should be some existing code that is doing somewhat similar in clang-query but I did not find it.

[balazske]

New patch and check the first line of AST dump only.

[balazske]

In the current state there are failing AST tests. This test can be added after the problems are fixed.

[balazske]

• Using size_t instead of int.

unittests/AST/ASTImporterTest.cpp

 #include "clang/ASTMatchers/ASTMatchers.h"
 #include "clang/Tooling/Tooling.h"
 
 #include "DeclMatcher.h"
 #include "Language.h"
 #include "gmock/gmock.h"
 #include "llvm/ADT/StringMap.h"
 
+#include <regex>
+
 namespace clang {
 namespace ast_matchers {
 
 using internal::Matcher;
 using internal::BindableMatcher;
 using llvm::StringMap;
 
 // Creates a virtual file and assigns that to the context of given AST. If the

 }
 
 static void createVirtualFileIfNeeded(ASTUnit *ToAST, StringRef FileName,
                                       StringRef Code) {
   return createVirtualFileIfNeeded(ToAST, FileName,
                                    llvm::MemoryBuffer::getMemBuffer(Code));
 }
 
+void checkImportedSourceLocations(const Decl *FromD, const Decl *ToD) {
+  // FIXME: Remove this line when all failures are fixed.
+  return;
+
+  // Check for matching source locations in From and To AST.
+  // FIXME: The check can be improved by using AST visitor and manually check
+  // all source locations for equality.
+  // (That check can be made more general by checking for other attributes.)
+
+  // Print debug information.
+  const bool Print = false;
+
+  SmallString<1024> ToPrinted;
+  SmallString<1024> FromPrinted;
+  llvm::raw_svector_ostream ToStream(ToPrinted);
+  llvm::raw_svector_ostream FromStream(FromPrinted);
+
+  ToD->dump(ToStream);
+  FromD->dump(FromStream);
+  // The AST dump additionally traverses the AST and can catch certain bugs like
+  // poorly or not implemented subtrees.
+
+  // search for SourceLocation strings:
+  // <filename>:<line>:<col>
+  // or
+  // line:<line>:<col>
+  // or
+  // col:<col>
+  // or
+  // '<invalid sloc>'
+  // If a component (filename or line) is same as in the last location
+  // it is not printed.
+  // Filename component is grouped into sub-expression to make it extractable.
+  std::regex MatchSourceLoc(
+      "<invalid sloc>|((\\w|\\.)+):\\d+:\\d+|line:\\d+:\\d+|col:\\d+");
+
+  std::string ToString(ToStream.str());
+  std::string FromString(FromStream.str());
+  auto ToLoc =
+      std::sregex_iterator(ToString.begin(), ToString.end(), MatchSourceLoc);
+  auto FromLoc = std::sregex_iterator(FromString.begin(), FromString.end(),
+                                      MatchSourceLoc);
+  if (Print) {
+    llvm::errs() << ToString << "\n\n\n" << FromString << "\n";
+    llvm::errs() << "----\n";
+  }
+  if (ToLoc->size() > 1 && FromLoc->size() > 1 && (*ToLoc)[1] != (*FromLoc)[1])
+    // Different filenames in To and From.
+    // This should mean that a to-be-imported decl was mapped to an existing
+    // (these normally reside in different files) and the check is
+    // not applicable.
+    return;
+
+  bool SourceLocationMismatch = false;
+  while (ToLoc != std::sregex_iterator() && FromLoc != std::sregex_iterator()) {
+    if (Print)
+      llvm::errs() << ToLoc->str() << "|" << FromLoc->str() << "\n";
+    SourceLocationMismatch =
+        SourceLocationMismatch || (ToLoc->str() != FromLoc->str());
+    ++ToLoc;
+    ++FromLoc;
+  }
+  if (Print)
+    llvm::errs() << "----\n";
+
+  // If the from AST is bigger it may have a matching prefix, ignore this case:
+  // ToLoc == std::sregex_iterator() && FromLoc != std::sregex_iterator()
+
+  // If the To AST is bigger (or has more source locations), indicate error.
+  if (FromLoc == std::sregex_iterator() && ToLoc != std::sregex_iterator())
+    SourceLocationMismatch = true;
+
+  EXPECT_FALSE(SourceLocationMismatch);
+}
+
 const StringRef DeclToImportID = "declToImport";
 const StringRef DeclToVerifyID = "declToVerify";
 
 // Common base for the different families of ASTImporter tests that are
 // parameterized on the compiler options which may result a different AST. E.g.
 // -fms-compatibility or -fdelayed-template-parsing.
 class CompilerOptionSpecificTest : public ::testing::Test {
 protected:
if (Imported) {
       // were not imported.
       SmallString<1024> ImportChecker;
       llvm::raw_svector_ostream ToNothing(ImportChecker);
       ToCtx.getTranslationUnitDecl()->print(ToNothing);
 
       // This traverses the AST to catch certain bugs like poorly or not
       // implemented subtrees.
       (*Imported)->dump(ToNothing);
+      // More detailed source location checks.
+      checkImportedSourceLocations(Node, *Imported);
     }
 
     return Imported;
   }
 
   template <typename NodeType>
   testing::AssertionResult
   testImport(const std::string &FromCode, const ArgVector &FromArgs,
public:
 
   // Import the given Decl into the ToCtx.
   // May be called several times in a given test.
   // The different instances of the param From may have different ASTContext.
   Decl *Import(Decl *From, Language ToLang) {
     lazyInitToAST(ToLang, "", OutputFileName);
     TU *FromTU = findFromTU(From);
     assert(LookupTablePtr);
-    return FromTU->import(*LookupTablePtr, ToAST.get(), From);
+    Decl *To = FromTU->import(*LookupTablePtr, ToAST.get(), From);
+    if (To)
+      checkImportedSourceLocations(From, To);
+    return To;
   }
 
   template <class DeclT> DeclT *Import(DeclT *From, Language Lang) {
     return cast_or_null<DeclT>(Import(cast<Decl>(From), Lang));
   }
 
   QualType ImportType(QualType FromType, Decl *TUDecl, Language ToLang) {
     lazyInitToAST(ToLang, "", OutputFileName);