[clang-tools-extra] [clangd] textDocument/documentLink to support include statements with macro argument (PR #137550)

[via cfe-commits]

https://github.com/frayien created https://github.com/llvm/llvm-project/pull/137550

See issue https://github.com/clangd/clangd/issues/2375

The clangd textDocument/documentLink request does not support include statements with macro argument and fails by returning an invalid range.

This PR adds support for macro argument by detecting what form of include statement is currently being processed and returning a range accordingly

First time contributing to LLVM, so if you have advice, questions or if I messed up procedure please tell me !

>From b3aea8f417114d098a5a1783fd35bc328e82a6f1 Mon Sep 17 00:00:00 2001
From: Adrien Garbani <garbani.adrien at frayien.fr>
Date: Sun, 27 Apr 2025 23:07:34 +0200
Subject: [PATCH] [clangd] textDocument/documentLink to support include
 statements with macro argument

---
 clang-tools-extra/clangd/XRefs.cpp            | 51 ++++++++++++++++---
 .../clangd/unittests/XRefsTests.cpp           | 18 ++++++-
 2 files changed, 61 insertions(+), 8 deletions(-)

diff --git a/clang-tools-extra/clangd/XRefs.cpp b/clang-tools-extra/clangd/XRefs.cpp
index 089f8158c9aa5..7b720de1b3f36 100644
--- a/clang-tools-extra/clangd/XRefs.cpp
+++ b/clang-tools-extra/clangd/XRefs.cpp
@@ -859,17 +859,56 @@ std::vector<DocumentLink> getDocumentLinks(ParsedAST &AST) {
   for (auto &Inc : AST.getIncludeStructure().MainFileIncludes) {
     if (Inc.Resolved.empty())
       continue;
+
+    // Get the location of the # symbole of the "#include ..." statement
     auto HashLoc = SM.getComposedLoc(SM.getMainFileID(), Inc.HashOffset);
+
+    // get the # Token itself, std::next to get the "include" token and the
+    // first token after (aka "File Token")
     const auto *HashTok = AST.getTokens().spelledTokenContaining(HashLoc);
     assert(HashTok && "got inclusion at wrong offset");
     const auto *IncludeTok = std::next(HashTok);
     const auto *FileTok = std::next(IncludeTok);
-    // FileTok->range is not sufficient here, as raw lexing wouldn't yield
-    // correct tokens for angled filenames. Hence we explicitly use
-    // Inc.Written's length.
-    auto FileRange =
-        syntax::FileRange(SM, FileTok->location(), Inc.Written.length())
-            .toCharRange(SM);
+
+    // The File Token can either be of kind :
+    // "less" if using the "#include <h-char-sequence> new-line" syntax
+    // "string_literal" if using the "#include "q-char-sequence" new-line"
+    // syntax something else (most likely "identifier") if using the "#include
+    // pp-tokens new-line" syntax (#include with macro argument)
+
+    CharSourceRange FileRange;
+
+    if (FileTok->kind() == tok::TokenKind::less) {
+      // FileTok->range would only include the '<' char. Hence we explicitly use
+      // Inc.Written's length.
+      FileRange =
+          syntax::FileRange(SM, FileTok->location(), Inc.Written.length())
+              .toCharRange(SM);
+    } else if (FileTok->kind() == tok::TokenKind::string_literal) {
+      // FileTok->range includes the quotes for string literals so just return
+      // it.
+      FileRange = FileTok->range(SM).toCharRange(SM);
+    } else {
+      // FileTok is the first Token of a macro spelling
+      // We can use the AST to get the macro expansion from the spelling
+      // starting at FileTok and use the expansion to get all the spelled Tokens
+      // that expanded to it
+
+      auto OptExpansion = AST.getTokens().expansionStartingAt(FileTok);
+      if (OptExpansion && !OptExpansion->Spelled.empty()) {
+        // If an expansion was found and has an non-empty spelling, return the
+        // range from the start of the first Token to the end of the last Token
+        const auto &LastTok = OptExpansion->Spelled.back();
+
+        FileRange = FileTok->range(SM).toCharRange(SM);
+        const auto EndRange = LastTok.range(SM).toCharRange(SM);
+        FileRange.setEnd(EndRange.getEnd());
+      } else {
+        // We failed to find a macro expansion from the spelling
+        // fallback to FileTok->range
+        FileRange = FileTok->range(SM).toCharRange(SM);
+      }
+    }
 
     Result.push_back(
         DocumentLink({halfOpenToRange(SM, FileRange),
diff --git a/clang-tools-extra/clangd/unittests/XRefsTests.cpp b/clang-tools-extra/clangd/unittests/XRefsTests.cpp
index 1892f87c8e82a..2c867817f1ad0 100644
--- a/clang-tools-extra/clangd/unittests/XRefsTests.cpp
+++ b/clang-tools-extra/clangd/unittests/XRefsTests.cpp
@@ -2776,14 +2776,24 @@ TEST(GetNonLocalDeclRefs, All) {
 
 TEST(DocumentLinks, All) {
   Annotations MainCpp(R"cpp(
+      #define HEADER_AA "faa.h"
+      #define HEADER_BB "fbb.h"
+      #define GET_HEADER(X) HEADER_ ## X 
+
       #/*comments*/include /*comments*/ $foo[["foo.h"]] //more comments
       int end_of_preamble = 0;
       #include $bar[[<bar.h>]]
+      #include $AA[[GET_HEADER(AA)]] // Some comment !
+      # /* What about */ \
+      include /* multiple line */ \
+      $BB[[GET_HEADER( /* statements ? */ \
+      BB /* >>>> Hey ! Dont go further ! this ')' is the last token of the file ! >>>>*/ )]]
     )cpp");
 
   TestTU TU;
   TU.Code = std::string(MainCpp.code());
-  TU.AdditionalFiles = {{"foo.h", ""}, {"bar.h", ""}};
+  TU.AdditionalFiles = {
+      {"faa.h", ""}, {"fbb.h", ""}, {"foo.h", ""}, {"bar.h", ""}};
   TU.ExtraArgs = {"-isystem."};
   auto AST = TU.build();
 
@@ -2793,7 +2803,11 @@ TEST(DocumentLinks, All) {
           DocumentLink({MainCpp.range("foo"),
                         URIForFile::canonicalize(testPath("foo.h"), "")}),
           DocumentLink({MainCpp.range("bar"),
-                        URIForFile::canonicalize(testPath("bar.h"), "")})));
+                        URIForFile::canonicalize(testPath("bar.h"), "")}),
+          DocumentLink({MainCpp.range("AA"),
+                        URIForFile::canonicalize(testPath("faa.h"), "")}),
+          DocumentLink({MainCpp.range("BB"),
+                        URIForFile::canonicalize(testPath("fbb.h"), "")})));
 }
 
 } // namespace