[clangd] Support refs() in dex. Largely cloned from MemIndex.

Reviewers: hokein

Subscribers: ilya-biryukov, ioeric, MaskRay, jkorous, arphaman, kadircet, cfe-commits

Differential Revision: https://reviews.llvm.org/D52726

5 files changed, 78 insertions, 35 deletions

diff --git a/clang-tools-extra/clangd/index/Serialization.cpp b/clang-tools-extra/clangd/index/Serialization.cpp
index 5e16137f8b2..2ebd2041ff5 100644
--- a/clang-tools-extra/clangd/index/Serialization.cpp
+++ b/clang-tools-extra/clangd/index/Serialization.cpp
@@ -435,8 +435,9 @@ std::unique_ptr<SymbolIndex> loadIndex(llvm::StringRef SymbolFilename,
   }
 
   trace::Span Tracer("BuildIndex");
-  auto Index = UseDex ? dex::Dex::build(std::move(Symbols), URISchemes)
-                      : MemIndex::build(std::move(Symbols), std::move(Refs));
+  auto Index =
+      UseDex ? dex::Dex::build(std::move(Symbols), std::move(Refs), URISchemes)
+             : MemIndex::build(std::move(Symbols), std::move(Refs));
   vlog("Loaded {0} from {1} with estimated memory usage {2}",
        UseDex ? "Dex" : "MemIndex", SymbolFilename,
        Index->estimateMemoryUsage());
diff --git a/clang-tools-extra/clangd/index/dex/Dex.cpp b/clang-tools-extra/clangd/index/dex/Dex.cpp
index 3b236f8918a..08f168dddef 100644
--- a/clang-tools-extra/clangd/index/dex/Dex.cpp
+++ b/clang-tools-extra/clangd/index/dex/Dex.cpp
@@ -24,6 +24,15 @@ namespace clang {
 namespace clangd {
 namespace dex {
 
+std::unique_ptr<SymbolIndex>
+Dex::build(SymbolSlab Symbols, RefSlab Refs,
+           llvm::ArrayRef<std::string> URISchemes) {
+  auto Size = Symbols.bytes() + Refs.bytes();
+  auto Data = std::make_pair(std::move(Symbols), std::move(Refs));
+  return llvm::make_unique<Dex>(Data.first, Data.second, std::move(Data), Size,
+                                std::move(URISchemes));
+}
+
 namespace {
 
 // Mark symbols which are can be used for code completion.
@@ -254,7 +263,10 @@ void Dex::lookup(const LookupRequest &Req,
 void Dex::refs(const RefsRequest &Req,
                llvm::function_ref<void(const Ref &)> Callback) const {
   trace::Span Tracer("Dex refs");
-  log("refs is not implemented.");
+  for (const auto &ID : Req.IDs)
+    for (const auto &Ref : Refs.lookup(ID))
+      if (static_cast<int>(Req.Filter & Ref.Kind))
+        Callback(Ref);
 }
 
 size_t Dex::estimateMemoryUsage() const {
@@ -264,6 +276,7 @@ size_t Dex::estimateMemoryUsage() const {
   Bytes += InvertedIndex.getMemorySize();
   for (const auto &TokenToPostingList : InvertedIndex)
     Bytes += TokenToPostingList.second.bytes();
+  Bytes += Refs.getMemorySize();
   return Bytes + BackingDataSize;
 }
 
diff --git a/clang-tools-extra/clangd/index/dex/Dex.h b/clang-tools-extra/clangd/index/dex/Dex.h
index baa215310fe..d89e6e15bce 100644
--- a/clang-tools-extra/clangd/index/dex/Dex.h
+++ b/clang-tools-extra/clangd/index/dex/Dex.h
@@ -41,9 +41,10 @@ namespace dex {
 // index on disk and then load it if available.
 class Dex : public SymbolIndex {
 public:
-  // All symbols must outlive this index.
-  template <typename Range>
-  Dex(Range &&Symbols, llvm::ArrayRef<std::string> Schemes)
+  // All data must outlive this index.
+  template <typename SymbolRange, typename RefsRange>
+  Dex(SymbolRange &&Symbols, RefsRange &&Refs,
+      llvm::ArrayRef<std::string> Schemes)
       : Corpus(0), URISchemes(Schemes) {
     // If Schemes don't contain any items, fall back to SymbolCollector's
     // default URI schemes.
@@ -53,26 +54,24 @@ public:
     }
     for (auto &&Sym : Symbols)
       this->Symbols.push_back(&Sym);
+    for (auto &&Ref : Refs)
+      this->Refs.try_emplace(Ref.first, Ref.second);
     buildIndex();
   }
-  // Symbols are owned by BackingData, Index takes ownership.
-  template <typename Range, typename Payload>
-  Dex(Range &&Symbols, Payload &&BackingData, size_t BackingDataSize,
-      llvm::ArrayRef<std::string> URISchemes)
-      : Dex(std::forward<Range>(Symbols), URISchemes) {
+  // Symbols and Refs are owned by BackingData, Index takes ownership.
+  template <typename SymbolRange, typename RefsRange, typename Payload>
+  Dex(SymbolRange &&Symbols, RefsRange &&Refs, Payload &&BackingData,
+      size_t BackingDataSize, llvm::ArrayRef<std::string> URISchemes)
+      : Dex(std::forward<SymbolRange>(Symbols), std::forward<RefsRange>(Refs),
+            URISchemes) {
     KeepAlive = std::shared_ptr<void>(
         std::make_shared<Payload>(std::move(BackingData)), nullptr);
     this->BackingDataSize = BackingDataSize;
   }
 
-  /// Builds an index from a slab. The index takes ownership of the slab.
+  /// Builds an index from slabs. The index takes ownership of the slab.
   static std::unique_ptr<SymbolIndex>
-  build(SymbolSlab Slab, llvm::ArrayRef<std::string> URISchemes) {
-    // Store Slab size before it is moved.
-    const auto BackingDataSize = Slab.bytes();
-    return llvm::make_unique<Dex>(Slab, std::move(Slab), BackingDataSize,
-                                  URISchemes);
-  }
+  build(SymbolSlab, RefSlab, llvm::ArrayRef<std::string> URISchemes);
 
   bool
   fuzzyFind(const FuzzyFindRequest &Req,
@@ -102,6 +101,7 @@ private:
   /// during the fuzzyFind process.
   llvm::DenseMap<Token, PostingList> InvertedIndex;
   dex::Corpus Corpus;
+  llvm::DenseMap<SymbolID, llvm::ArrayRef<Ref>> Refs;
   std::shared_ptr<void> KeepAlive; // poor man's move-only std::any
   // Size of memory retained by KeepAlive.
   size_t BackingDataSize = 0;
diff --git a/clang-tools-extra/clangd/indexer/IndexerMain.cpp b/clang-tools-extra/clangd/indexer/IndexerMain.cpp
index 8db7559594c..5a5b3178fcc 100644
--- a/clang-tools-extra/clangd/indexer/IndexerMain.cpp
+++ b/clang-tools-extra/clangd/indexer/IndexerMain.cpp
@@ -47,7 +47,7 @@ static llvm::cl::opt<IndexFileFormat>
                                        "human-readable YAML format"),
                             clEnumValN(IndexFileFormat::RIFF, "binary",
                                        "binary RIFF format")),
-           llvm::cl::init(IndexFileFormat::YAML));
+           llvm::cl::init(IndexFileFormat::RIFF));
 
 class IndexActionFactory : public tooling::FrontendActionFactory {
 public:
diff --git a/clang-tools-extra/unittests/clangd/DexTests.cpp b/clang-tools-extra/unittests/clangd/DexTests.cpp
index 28ec9c5c834..d1d5b4c7eeb 100644
--- a/clang-tools-extra/unittests/clangd/DexTests.cpp
+++ b/clang-tools-extra/unittests/clangd/DexTests.cpp
@@ -423,7 +423,8 @@ TEST(DexSearchTokens, SymbolPath) {
 //===----------------------------------------------------------------------===//
 
 TEST(Dex, Lookup) {
-  auto I = Dex::build(generateSymbols({"ns::abc", "ns::xyz"}), URISchemes);
+  auto I = Dex::build(generateSymbols({"ns::abc", "ns::xyz"}), RefSlab(),
+                      URISchemes);
   EXPECT_THAT(lookup(*I, SymbolID("ns::abc")), UnorderedElementsAre("ns::abc"));
   EXPECT_THAT(lookup(*I, {SymbolID("ns::abc"), SymbolID("ns::xyz")}),
               UnorderedElementsAre("ns::abc", "ns::xyz"));
@@ -436,7 +437,7 @@ TEST(Dex, FuzzyFind) {
   auto Index =
       Dex::build(generateSymbols({"ns::ABC", "ns::BCD", "::ABC",
                                   "ns::nested::ABC", "other::ABC", "other::A"}),
-                 URISchemes);
+                 RefSlab(), URISchemes);
   FuzzyFindRequest Req;
   Req.Query = "ABC";
   Req.Scopes = {"ns::"};
@@ -466,13 +467,13 @@ TEST(DexTest, DexDeduplicate) {
                                  symbol("2") /* duplicate */};
   FuzzyFindRequest Req;
   Req.Query = "2";
-  Dex I(Symbols, URISchemes);
+  Dex I(Symbols, RefSlab(), URISchemes);
   EXPECT_FALSE(Req.Limit);
   EXPECT_THAT(match(I, Req), ElementsAre("2", "2"));
 }
 
 TEST(DexTest, DexLimitedNumMatches) {
-  auto I = Dex::build(generateNumSymbols(0, 100), URISchemes);
+  auto I = Dex::build(generateNumSymbols(0, 100), RefSlab(), URISchemes);
   FuzzyFindRequest Req;
   Req.Query = "5";
   Req.Limit = 3;
@@ -486,7 +487,7 @@ TEST(DexTest, DexLimitedNumMatches) {
 TEST(DexTest, FuzzyMatch) {
   auto I = Dex::build(
       generateSymbols({"LaughingOutLoud", "LionPopulation", "LittleOldLady"}),
-      URISchemes);
+      RefSlab(), URISchemes);
   FuzzyFindRequest Req;
   Req.Query = "lol";
   Req.Limit = 2;
@@ -495,14 +496,16 @@ TEST(DexTest, FuzzyMatch) {
 }
 
 TEST(DexTest, MatchQualifiedNamesWithoutSpecificScope) {
-  auto I = Dex::build(generateSymbols({"a::y1", "b::y2", "y3"}), URISchemes);
+  auto I = Dex::build(generateSymbols({"a::y1", "b::y2", "y3"}), RefSlab(),
+                      URISchemes);
   FuzzyFindRequest Req;
   Req.Query = "y";
   EXPECT_THAT(match(*I, Req), UnorderedElementsAre("a::y1", "b::y2", "y3"));
 }
 
 TEST(DexTest, MatchQualifiedNamesWithGlobalScope) {
-  auto I = Dex::build(generateSymbols({"a::y1", "b::y2", "y3"}), URISchemes);
+  auto I = Dex::build(generateSymbols({"a::y1", "b::y2", "y3"}), RefSlab(),
+                      URISchemes);
   FuzzyFindRequest Req;
   Req.Query = "y";
   Req.Scopes = {""};
@@ -510,8 +513,9 @@ TEST(DexTest, MatchQualifiedNamesWithGlobalScope) {
 }
 
 TEST(DexTest, MatchQualifiedNamesWithOneScope) {
-  auto I = Dex::build(
-      generateSymbols({"a::y1", "a::y2", "a::x", "b::y2", "y3"}), URISchemes);
+  auto I =
+      Dex::build(generateSymbols({"a::y1", "a::y2", "a::x", "b::y2", "y3"}),
+                 RefSlab(), URISchemes);
   FuzzyFindRequest Req;
   Req.Query = "y";
   Req.Scopes = {"a::"};
@@ -520,7 +524,7 @@ TEST(DexTest, MatchQualifiedNamesWithOneScope) {
 
 TEST(DexTest, MatchQualifiedNamesWithMultipleScopes) {
   auto I = Dex::build(
-      generateSymbols({"a::y1", "a::y2", "a::x", "b::y3", "y3"}), URISchemes);
+      generateSymbols({"a::y1", "a::y2", "a::x", "b::y3", "y3"}), RefSlab(), URISchemes);
   FuzzyFindRequest Req;
   Req.Query = "y";
   Req.Scopes = {"a::", "b::"};
@@ -528,7 +532,7 @@ TEST(DexTest, MatchQualifiedNamesWithMultipleScopes) {
 }
 
 TEST(DexTest, NoMatchNestedScopes) {
-  auto I = Dex::build(generateSymbols({"a::y1", "a::b::y2"}), URISchemes);
+  auto I = Dex::build(generateSymbols({"a::y1", "a::b::y2"}), RefSlab(), URISchemes);
   FuzzyFindRequest Req;
   Req.Query = "y";
   Req.Scopes = {"a::"};
@@ -537,7 +541,7 @@ TEST(DexTest, NoMatchNestedScopes) {
 
 TEST(DexTest, WildcardScope) {
   auto I =
-      Dex::build(generateSymbols({"a::y1", "a::b::y2", "c::y3"}), URISchemes);
+      Dex::build(generateSymbols({"a::y1", "a::b::y2", "c::y3"}), RefSlab(), URISchemes);
   FuzzyFindRequest Req;
   Req.Query = "y";
   Req.Scopes = {"a::"};
@@ -547,7 +551,7 @@ TEST(DexTest, WildcardScope) {
 }
 
 TEST(DexTest, IgnoreCases) {
-  auto I = Dex::build(generateSymbols({"ns::ABC", "ns::abc"}), URISchemes);
+  auto I = Dex::build(generateSymbols({"ns::ABC", "ns::abc"}), RefSlab(), URISchemes);
   FuzzyFindRequest Req;
   Req.Query = "AB";
   Req.Scopes = {"ns::"};
@@ -555,7 +559,7 @@ TEST(DexTest, IgnoreCases) {
 }
 
 TEST(DexTest, Lookup) {
-  auto I = Dex::build(generateSymbols({"ns::abc", "ns::xyz"}), URISchemes);
+  auto I = Dex::build(generateSymbols({"ns::abc", "ns::xyz"}), RefSlab(), URISchemes);
   EXPECT_THAT(lookup(*I, SymbolID("ns::abc")), UnorderedElementsAre("ns::abc"));
   EXPECT_THAT(lookup(*I, {SymbolID("ns::abc"), SymbolID("ns::xyz")}),
               UnorderedElementsAre("ns::abc", "ns::xyz"));
@@ -570,7 +574,7 @@ TEST(DexTest, SymbolIndexOptionsFilter) {
   CodeCompletionSymbol.Flags = Symbol::SymbolFlag::IndexedForCodeCompletion;
   NonCodeCompletionSymbol.Flags = Symbol::SymbolFlag::None;
   std::vector<Symbol> Symbols{CodeCompletionSymbol, NonCodeCompletionSymbol};
-  Dex I(Symbols, URISchemes);
+  Dex I(Symbols, RefSlab(), URISchemes);
   FuzzyFindRequest Req;
   Req.RestrictForCodeCompletion = false;
   EXPECT_THAT(match(I, Req), ElementsAre("Completion", "NoCompletion"));
@@ -585,7 +589,7 @@ TEST(DexTest, ProximityPathsBoosting) {
   CloseSymbol.CanonicalDeclaration.FileURI = "unittest:///a/b/c/d/e/f/file.h";
 
   std::vector<Symbol> Symbols{CloseSymbol, RootSymbol};
-  Dex I(Symbols, URISchemes);
+  Dex I(Symbols, RefSlab(), URISchemes);
 
   FuzzyFindRequest Req;
   Req.Query = "abc";
@@ -603,6 +607,31 @@ TEST(DexTest, ProximityPathsBoosting) {
   EXPECT_THAT(match(I, Req), ElementsAre("root::abc"));
 }
 
+TEST(DexTests, Refs) {
+  DenseMap<SymbolID, std::vector<Ref>> Refs;
+  auto AddRef = [&](const Symbol& Sym, StringRef Filename, RefKind Kind) {
+    auto& SymbolRefs = Refs[Sym.ID];
+    SymbolRefs.emplace_back();
+    SymbolRefs.back().Kind = Kind;
+    SymbolRefs.back().Location.FileURI = Filename;
+  };
+  auto Foo = symbol("foo");
+  auto Bar = symbol("bar");
+  AddRef(Foo, "foo.h", RefKind::Declaration);
+  AddRef(Foo, "reffoo.h", RefKind::Reference);
+  AddRef(Bar, "bar.h", RefKind::Declaration);
+
+  std::vector<std::string> Files;
+  RefsRequest Req;
+  Req.IDs.insert(Foo.ID);
+  Req.Filter = RefKind::Declaration | RefKind::Definition;
+  Dex(std::vector<Symbol>{Foo, Bar}, Refs, {}).refs(Req, [&](const Ref &R) {
+    Files.push_back(R.Location.FileURI);
+  });
+
+  EXPECT_THAT(Files, ElementsAre("foo.h"));
+}
+
 } // namespace
 } // namespace dex
 } // namespace clangd