[clangd] IncludeCleaner: Decrease API dependency on clangd

Reviewed By: sammccall

Differential Revision: https://reviews.llvm.org/D118882

clang-tools-extra/clangd/IncludeCleaner.cpp

@@ -14,6 +14,7 @@
 #include "SourceCode.h"
 #include "support/Logger.h"
 #include "support/Trace.h"
+#include "clang/AST/ASTContext.h"
 #include "clang/AST/ExprCXX.h"
 #include "clang/AST/RecursiveASTVisitor.h"
 #include "clang/Basic/SourceLocation.h"
@@ -21,6 +22,7 @@
 #include "clang/Lex/HeaderSearch.h"
 #include "clang/Lex/Preprocessor.h"
 #include "clang/Tooling/Syntax/Tokens.h"
+#include "llvm/ADT/STLFunctionalExtras.h"
 #include "llvm/Support/FormatVariadic.h"
 #include "llvm/Support/Path.h"
 
@@ -207,10 +209,10 @@ clangd::Range getDiagnosticRange(llvm::StringRef Code, unsigned HashOffset) {
 
 // Finds locations of macros referenced from within the main file. That includes
 // references that were not yet expanded, e.g `BAR` in `#define FOO BAR`.
-void findReferencedMacros(ParsedAST &AST, ReferencedLocations &Result) {
+void findReferencedMacros(const SourceManager &SM, Preprocessor &PP,
+                          const syntax::TokenBuffer *Tokens,
+                          ReferencedLocations &Result) {
   trace::Span Tracer("IncludeCleaner::findReferencedMacros");
-  auto &SM = AST.getSourceManager();
-  auto &PP = AST.getPreprocessor();
   // FIXME(kirillbobyrev): The macros from the main file are collected in
   // ParsedAST's MainFileMacros. However, we can't use it here because it
   // doesn't handle macro references that were not expanded, e.g. in macro
@@ -220,8 +222,7 @@ void findReferencedMacros(ParsedAST &AST, ReferencedLocations &Result) {
   // this mechanism (as opposed to iterating through all tokens) will improve
   // the performance of findReferencedMacros and also improve other features
   // relying on MainFileMacros.
-  for (const syntax::Token &Tok :
-       AST.getTokens().spelledTokens(SM.getMainFileID())) {
+  for (const syntax::Token &Tok : Tokens->spelledTokens(SM.getMainFileID())) {
     auto Macro = locateMacroAt(Tok, PP);
     if (!Macro)
       continue;
@@ -287,18 +288,26 @@ FileID headerResponsible(FileID ID, const SourceManager &SM,
 
 } // namespace
 
-ReferencedLocations findReferencedLocations(ParsedAST &AST) {
+ReferencedLocations findReferencedLocations(const SourceManager &SM,
+                                            ASTContext &Ctx, Preprocessor &PP,
+                                            const syntax::TokenBuffer *Tokens) {
   trace::Span Tracer("IncludeCleaner::findReferencedLocations");
   ReferencedLocations Result;
-  ReferencedLocationCrawler Crawler(Result, AST.getSourceManager());
-  Crawler.TraverseAST(AST.getASTContext());
-  findReferencedMacros(AST, Result);
+  ReferencedLocationCrawler Crawler(Result, SM);
+  Crawler.TraverseAST(Ctx);
+  if (Tokens)
+    findReferencedMacros(SM, PP, Tokens, Result);
   return Result;
 }
 
-ReferencedFiles findReferencedFiles(const ReferencedLocations &Locs,
-                                    const IncludeStructure &Includes,
-                                    const SourceManager &SM) {
+ReferencedLocations findReferencedLocations(ParsedAST &AST) {
+  return findReferencedLocations(AST.getSourceManager(), AST.getASTContext(),
+                                 AST.getPreprocessor(), &AST.getTokens());
+}
+
+ReferencedFiles
+findReferencedFiles(const ReferencedLocations &Locs, const SourceManager &SM,
+                    llvm::function_ref<FileID(FileID)> HeaderResponsible) {
   std::vector<SourceLocation> Sorted{Locs.User.begin(), Locs.User.end()};
   llvm::sort(Sorted); // Group by FileID.
   ReferencedFilesBuilder Builder(SM);
@@ -318,7 +327,7 @@ ReferencedFiles findReferencedFiles(const ReferencedLocations &Locs,
   // HeaderIDs, as each inclusion of a non-self-contained file is distinct.
   llvm::DenseSet<FileID> UserFiles;
   for (FileID ID : Builder.Files)
-    UserFiles.insert(headerResponsible(ID, SM, Includes));
+    UserFiles.insert(HeaderResponsible(ID));
 
   llvm::DenseSet<stdlib::Header> StdlibFiles;
   for (const auto &Symbol : Locs.Stdlib)
@@ -328,6 +337,14 @@ ReferencedFiles findReferencedFiles(const ReferencedLocations &Locs,
   return {std::move(UserFiles), std::move(StdlibFiles)};
 }
 
+ReferencedFiles findReferencedFiles(const ReferencedLocations &Locs,
+                                    const IncludeStructure &Includes,
+                                    const SourceManager &SM) {
+  return findReferencedFiles(Locs, SM, [&SM, &Includes](FileID ID) {
+    return headerResponsible(ID, SM, Includes);
+  });
+}
+
 std::vector<const Inclusion *>
 getUnused(ParsedAST &AST,
           const llvm::DenseSet<IncludeStructure::HeaderID> &ReferencedFiles) {

clang-tools-extra/clangd/IncludeCleaner.h

@@ -25,6 +25,7 @@
 #include "ParsedAST.h"
 #include "clang/Basic/SourceLocation.h"
 #include "llvm/ADT/DenseSet.h"
+#include "llvm/ADT/STLFunctionalExtras.h"
 #include <vector>
 
 namespace clang {
@@ -41,15 +42,17 @@ struct ReferencedLocations {
 ///   associated locations. These may be macro expansions, and are not resolved
 ///   to their spelling or expansion location. These locations are later used to
 ///   determine which headers should be marked as "used" and "directly used".
-/// - We also examine all identifier tokens in the file in case they reference
-///   macros.
-///
+/// - If \p Tokens is not nullptr, we also examine all identifier tokens in the
+///   file in case they reference macros macros.
 /// We use this to compute unused headers, so we:
 ///
 /// - cover the whole file in a single traversal for efficiency
 /// - don't attempt to describe where symbols were referenced from in
 ///   ambiguous cases (e.g. implicitly used symbols, multiple declarations)
 /// - err on the side of reporting all possible locations
+ReferencedLocations findReferencedLocations(const SourceManager &SM,
+                                            ASTContext &Ctx, Preprocessor &PP,
+                                            const syntax::TokenBuffer *Tokens);
 ReferencedLocations findReferencedLocations(ParsedAST &AST);
 
 struct ReferencedFiles {
@@ -60,6 +63,12 @@ struct ReferencedFiles {
 /// Retrieves IDs of all files containing SourceLocations from \p Locs.
 /// The output only includes things SourceManager sees as files (not macro IDs).
 /// This can include <built-in>, <scratch space> etc that are not true files.
+/// \p HeaderResponsible returns the public header that should be included given
+/// symbols from a file with the given FileID (example: public headers should be
+/// preferred to non self-contained and private headers).
+ReferencedFiles
+findReferencedFiles(const ReferencedLocations &Locs, const SourceManager &SM,
+                    llvm::function_ref<FileID(FileID)> HeaderResponsible);
 ReferencedFiles findReferencedFiles(const ReferencedLocations &Locs,
                                     const IncludeStructure &Includes,
                                     const SourceManager &SM);
@@ -81,8 +90,8 @@ std::vector<const Inclusion *> computeUnusedIncludes(ParsedAST &AST);
 std::vector<Diag> issueUnusedIncludesDiagnostics(ParsedAST &AST,
                                                  llvm::StringRef Code);
 
-/// Affects whether standard library includes should be considered for removal.
-/// This is off by default for now due to implementation limitations:
+/// Affects whether standard library includes should be considered for
+/// removal. This is off by default for now due to implementation limitations:
 /// - macros are not tracked
 /// - symbol names without a unique associated header are not tracked
 /// - references to std-namespaced C types are not properly tracked: