[clangd] Allow consuming limited number of items

This patch modifies `consume` function to allow retrieval of limited
number of symbols. This is the "cheap" implementation of top-level
limiting iterator. In the future we would like to have a complete limit
iterator implementation to insert it into the query subtrees, but in the
meantime this version would be enough for a fully-functional
proof-of-concept Dex implementation.

Reviewers: ioeric, ilya-biryukov

Reviewed by: ioeric

Differential Revision: https://reviews.llvm.org/D50500

llvm-svn: 339426

clang-tools-extra/clangd/index/dex/Iterator.cpp

@@ -218,9 +218,10 @@ class OrIterator : public Iterator {
 
 } // end namespace
 
-std::vector<DocID> consume(Iterator &It) {
+std::vector<DocID> consume(Iterator &It, size_t Limit) {
   std::vector<DocID> Result;
-  for (; !It.reachedEnd(); It.advance())
+  for (size_t Retrieved = 0; !It.reachedEnd() && Retrieved < Limit;
+       It.advance(), ++Retrieved)
     Result.push_back(It.peek());
   return Result;
 }

clang-tools-extra/clangd/index/dex/Iterator.h

@@ -101,9 +101,10 @@ class Iterator {
   virtual llvm::raw_ostream &dump(llvm::raw_ostream &OS) const = 0;
 };
 
-/// Exhausts given iterator and returns all processed DocIDs. The result
-/// contains sorted DocumentIDs.
-std::vector<DocID> consume(Iterator &It);
+/// Advances the iterator until it is either exhausted or the number of
+/// requested items is reached. The result contains sorted DocumentIDs.
+std::vector<DocID> consume(Iterator &It,
+                           size_t Limit = std::numeric_limits<size_t>::max());
 
 /// Returns a document iterator over given PostingList.
 std::unique_ptr<Iterator> create(PostingListRef Documents);

clang-tools-extra/unittests/clangd/DexIndexTests.cpp

@@ -240,6 +240,27 @@ TEST(DexIndexIterators, StringRepresentation) {
             "(& (& [1, 3, 5, 8, 9] [1, 5, 7, 9]) (| [0, 5] [0, 1, 5] []))");
 }
 
+TEST(DexIndexIterators, Limit) {
+  const PostingList L0 = {4, 7, 8, 20, 42, 100};
+  const PostingList L1 = {1, 3, 5, 8, 9};
+  const PostingList L2 = {1, 5, 7, 9};
+  const PostingList L3 = {0, 5};
+  const PostingList L4 = {0, 1, 5};
+  const PostingList L5;
+
+  auto DocIterator = create(L0);
+  EXPECT_THAT(consume(*DocIterator, 42), ElementsAre(4, 7, 8, 20, 42, 100));
+
+  DocIterator = create(L0);
+  EXPECT_THAT(consume(*DocIterator), ElementsAre(4, 7, 8, 20, 42, 100));
+
+  DocIterator = create(L0);
+  EXPECT_THAT(consume(*DocIterator, 3), ElementsAre(4, 7, 8));
+
+  DocIterator = create(L0);
+  EXPECT_THAT(consume(*DocIterator, 0), ElementsAre());
+}
+
 testing::Matcher<std::vector<Token>>
 trigramsAre(std::initializer_list<std::string> Trigrams) {
   std::vector<Token> Tokens;