[PATCH] D76098: [WIP] [clangd] Do not trigger go-to-def textual fallback inside string literals

[Nathan Ridge via Phabricator via cfe-commits]

nridge updated this revision to Diff 250885.
nridge added a comment.

Use TokenBuffer instead of a raw lexer.

Note that getting this to word required enabling comment-retention mode for
the lexer which produces the TokenBuffer. I'm not sure if this is desirable
in general.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D76098/new/

https://reviews.llvm.org/D76098

Files:
  clang-tools-extra/clangd/XRefs.cpp
  clang-tools-extra/clangd/unittests/XRefsTests.cpp
  clang/lib/Tooling/Syntax/Tokens.cpp


Index: clang/lib/Tooling/Syntax/Tokens.cpp
===================================================================
--- clang/lib/Tooling/Syntax/Tokens.cpp
+++ clang/lib/Tooling/Syntax/Tokens.cpp
@@ -340,6 +340,7 @@
           // We can't make BufEnd point to FR.endOffset, as Lexer requires a
           // null terminated buffer.
           SrcBuffer.data() + SrcBuffer.size());
+  L.SetCommentRetentionState(true);
 
   clang::Token T;
   while (!L.LexFromRawLexer(T) && L.getCurrentBufferOffset() < FR.endOffset())
Index: clang-tools-extra/clangd/unittests/XRefsTests.cpp
===================================================================
--- clang-tools-extra/clangd/unittests/XRefsTests.cpp
+++ clang-tools-extra/clangd/unittests/XRefsTests.cpp
@@ -628,7 +628,8 @@
         // Comment mentioning M^yClass
       )cpp",
       R"cpp(// String
-        struct [[MyClass]] {};
+        struct MyClass {};
+        // Not triggered for string literal tokens.
         const char* s = "String literal mentioning M^yClass";
       )cpp",
       R"cpp(// Ifdef'ed out code
@@ -680,7 +681,7 @@
       EXPECT_EQ(Results[0].PreferredDeclaration.range, *WantDecl) << Test;
     }
   }
-}
+} // namespace
 
 TEST(LocateSymbol, Ambiguous) {
   auto T = Annotations(R"cpp(
Index: clang-tools-extra/clangd/XRefs.cpp
===================================================================
--- clang-tools-extra/clangd/XRefs.cpp
+++ clang-tools-extra/clangd/XRefs.cpp
@@ -363,6 +363,16 @@
                              const std::string &MainFilePath) {
   const auto &SM = AST.getSourceManager();
 
+  auto Tokens = syntax::spelledTokensTouching(Loc, AST.getTokens());
+  if (Tokens.size() != 1)
+    return {};
+  syntax::Token Tok = Tokens[0];
+
+  // Only consider comment and identifier tokens.
+  if (!(Tok.kind() == tok::TokenKind::comment ||
+        Tok.kind() == tok::TokenKind::identifier))
+    return {};
+
   // Get the raw word at the specified location.
   unsigned Pos;
   FileID File;
@@ -374,12 +384,14 @@
   unsigned WordOffset = Word.data() - Code.data();
   SourceLocation WordStart = SM.getComposedLoc(File, WordOffset);
 
-  // Do not consider tokens that survived preprocessing.
-  // We are erring on the safe side here, as a user may expect to get
-  // accurate (as opposed to textual-heuristic) results for such tokens.
+  // If this is an identifier token, do not consider if it it survived
+  // preprocessing. We are erring on the safe side here, as a user may expect to
+  // get accurate (as opposed to textual-heuristic) results for such tokens.
   // FIXME: Relax this for dependent code.
-  if (tokenSurvivedPreprocessing(WordStart, AST.getTokens()))
+  if (Tok.kind() == tok::TokenKind::identifier &&
+      tokenSurvivedPreprocessing(WordStart, AST.getTokens())) {
     return {};
+  }
 
   // Additionally filter for signals that the word is likely to be an
   // identifier. This avoids triggering on e.g. random words in a comment.


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D76098.250885.patch
Type: text/x-patch
Size: 2955 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20200317/a92dfc46/attachment-0001.bin>