kbobyrev created this revision.
kbobyrev added reviewers: ioeric, ilya-biryukov.
kbobyrev added a project: clang-tools-extra.
Herald added subscribers: arphaman, jkorous, MaskRay.
Currently, the query trigram generator would simply yield `u_p` trigram for the
`u_p` query. This is not optimal, since the user is likely to try matching two
heads with this query and this patch addresses the issue.
https://reviews.llvm.org/D50700
Files:
clang-tools-extra/clangd/index/dex/Trigram.cpp
clang-tools-extra/clangd/index/dex/Trigram.h
clang-tools-extra/unittests/clangd/DexIndexTests.cpp
Index: clang-tools-extra/unittests/clangd/DexIndexTests.cpp
===================================================================
--- clang-tools-extra/unittests/clangd/DexIndexTests.cpp
+++ clang-tools-extra/unittests/clangd/DexIndexTests.cpp
@@ -300,6 +300,8 @@
EXPECT_THAT(generateQueryTrigrams("__"), trigramsAre({"__$"}));
EXPECT_THAT(generateQueryTrigrams("___"), trigramsAre({"___"}));
+ EXPECT_THAT(generateQueryTrigrams("u_p"), trigramsAre({"up$"}));
+
EXPECT_THAT(generateQueryTrigrams("X86"), trigramsAre({"x86"}));
EXPECT_THAT(generateQueryTrigrams("clangd"),
Index: clang-tools-extra/clangd/index/dex/Trigram.h
===================================================================
--- clang-tools-extra/clangd/index/dex/Trigram.h
+++ clang-tools-extra/clangd/index/dex/Trigram.h
@@ -68,7 +68,10 @@
///
/// For short queries (less than 3 characters with Head or Tail roles in Fuzzy
/// Matching segmentation) this returns a single trigram with the first
-/// characters (up to 3) to perfrom prefix match.
+/// characters (up to 3) to perfrom prefix match. However, if the query is
short
+/// but it contains two HEAD symbols then the returned trigram would be an
+/// incomplete bigram with those two headsd. This would help to match
+/// "unique_ptr" and similar symbols with "u_p" query.
std::vector<Token> generateQueryTrigrams(llvm::StringRef Query);
} // namespace dex
Index: clang-tools-extra/clangd/index/dex/Trigram.cpp
===================================================================
--- clang-tools-extra/clangd/index/dex/Trigram.cpp
+++ clang-tools-extra/clangd/index/dex/Trigram.cpp
@@ -128,9 +128,15 @@
// Additional pass is necessary to count valid identifier characters.
// Depending on that, this function might return incomplete trigram.
unsigned ValidSymbolsCount = 0;
- for (size_t I = 0; I < Roles.size(); ++I)
- if (Roles[I] == Head || Roles[I] == Tail)
+ unsigned Heads = 0;
+ for (size_t I = 0; I < Roles.size(); ++I) {
+ if (Roles[I] == Head) {
+ ++ValidSymbolsCount;
+ ++Heads;
+ } else if (Roles[I] == Tail) {
++ValidSymbolsCount;
+ }
+ }
std::string LowercaseQuery = Query.lower();
@@ -140,13 +146,26 @@
// If the number of symbols which can form fuzzy matching trigram is not
// sufficient, generate a single incomplete trigram for query.
if (ValidSymbolsCount < 3) {
- std::string Symbols = {{END_MARKER, END_MARKER, END_MARKER}};
+ std::string Symbols;
+ // If the query is not long enough to form a trigram but contains two heads
+ // the returned trigram should be "xy$" where "x" and "y" are the heads.
+ // This might be particulary important for cases like "u_p" to match
+ // "unique_ptr" and similar symbols from the C++ Standard Library.
+ if (Heads == 2) {
+ for (size_t I = 0; I < LowercaseQuery.size(); ++I)
+ if (Roles[I] == Head)
+ Symbols += LowercaseQuery[I];
+
+ Symbols += END_MARKER;
+ } else {
+ Symbols = {{END_MARKER, END_MARKER, END_MARKER}};
if (LowercaseQuery.size() > 0)
Symbols[0] = LowercaseQuery[0];
if (LowercaseQuery.size() > 1)
Symbols[1] = LowercaseQuery[1];
if (LowercaseQuery.size() > 2)
Symbols[2] = LowercaseQuery[2];
+ }
const auto Trigram = Token(Token::Kind::Trigram, Symbols);
UniqueTrigrams.insert(Trigram);
} else {
Index: clang-tools-extra/unittests/clangd/DexIndexTests.cpp
===================================================================
--- clang-tools-extra/unittests/clangd/DexIndexTests.cpp
+++ clang-tools-extra/unittests/clangd/DexIndexTests.cpp
@@ -300,6 +300,8 @@
EXPECT_THAT(generateQueryTrigrams("__"), trigramsAre({"__$"}));
EXPECT_THAT(generateQueryTrigrams("___"), trigramsAre({"___"}));
+ EXPECT_THAT(generateQueryTrigrams("u_p"), trigramsAre({"up$"}));
+
EXPECT_THAT(generateQueryTrigrams("X86"), trigramsAre({"x86"}));
EXPECT_THAT(generateQueryTrigrams("clangd"),
Index: clang-tools-extra/clangd/index/dex/Trigram.h
===================================================================
--- clang-tools-extra/clangd/index/dex/Trigram.h
+++ clang-tools-extra/clangd/index/dex/Trigram.h
@@ -68,7 +68,10 @@
///
/// For short queries (less than 3 characters with Head or Tail roles in Fuzzy
/// Matching segmentation) this returns a single trigram with the first
-/// characters (up to 3) to perfrom prefix match.
+/// characters (up to 3) to perfrom prefix match. However, if the query is short
+/// but it contains two HEAD symbols then the returned trigram would be an
+/// incomplete bigram with those two headsd. This would help to match
+/// "unique_ptr" and similar symbols with "u_p" query.
std::vector<Token> generateQueryTrigrams(llvm::StringRef Query);
} // namespace dex
Index: clang-tools-extra/clangd/index/dex/Trigram.cpp
===================================================================
--- clang-tools-extra/clangd/index/dex/Trigram.cpp
+++ clang-tools-extra/clangd/index/dex/Trigram.cpp
@@ -128,9 +128,15 @@
// Additional pass is necessary to count valid identifier characters.
// Depending on that, this function might return incomplete trigram.
unsigned ValidSymbolsCount = 0;
- for (size_t I = 0; I < Roles.size(); ++I)
- if (Roles[I] == Head || Roles[I] == Tail)
+ unsigned Heads = 0;
+ for (size_t I = 0; I < Roles.size(); ++I) {
+ if (Roles[I] == Head) {
+ ++ValidSymbolsCount;
+ ++Heads;
+ } else if (Roles[I] == Tail) {
++ValidSymbolsCount;
+ }
+ }
std::string LowercaseQuery = Query.lower();
@@ -140,13 +146,26 @@
// If the number of symbols which can form fuzzy matching trigram is not
// sufficient, generate a single incomplete trigram for query.
if (ValidSymbolsCount < 3) {
- std::string Symbols = {{END_MARKER, END_MARKER, END_MARKER}};
+ std::string Symbols;
+ // If the query is not long enough to form a trigram but contains two heads
+ // the returned trigram should be "xy$" where "x" and "y" are the heads.
+ // This might be particulary important for cases like "u_p" to match
+ // "unique_ptr" and similar symbols from the C++ Standard Library.
+ if (Heads == 2) {
+ for (size_t I = 0; I < LowercaseQuery.size(); ++I)
+ if (Roles[I] == Head)
+ Symbols += LowercaseQuery[I];
+
+ Symbols += END_MARKER;
+ } else {
+ Symbols = {{END_MARKER, END_MARKER, END_MARKER}};
if (LowercaseQuery.size() > 0)
Symbols[0] = LowercaseQuery[0];
if (LowercaseQuery.size() > 1)
Symbols[1] = LowercaseQuery[1];
if (LowercaseQuery.size() > 2)
Symbols[2] = LowercaseQuery[2];
+ }
const auto Trigram = Token(Token::Kind::Trigram, Symbols);
UniqueTrigrams.insert(Trigram);
} else {
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
