[PATCH] D69615: [clangd] Implement a function to lex the file to find candidate occurrences.

[Haojian Wu via Phabricator via cfe-commits]

hokein created this revision.
hokein added a reviewer: ilya-biryukov.
Herald added subscribers: usaxena95, kadircet, arphaman, jkorous, MaskRay.
Herald added a project: clang.

This will be used for incoming cross-file rename (to detect index
staleness issue).


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D69615

Files:
  clang-tools-extra/clangd/SourceCode.cpp
  clang-tools-extra/clangd/SourceCode.h
  clang-tools-extra/clangd/unittests/SourceCodeTests.cpp


Index: clang-tools-extra/clangd/unittests/SourceCodeTests.cpp
===================================================================
--- clang-tools-extra/clangd/unittests/SourceCodeTests.cpp
+++ clang-tools-extra/clangd/unittests/SourceCodeTests.cpp
@@ -680,6 +680,22 @@
     EXPECT_EQ(Res.EnclosingNamespace, Case.EnclosingNamespace) << Test.code();
   }
 }
+
+TEST(SourceCodeTests, IdentifierRanges) {
+  Annotations Code(R"cpp(
+   class [[Foo]] {};
+   // Foo
+   /* Foo */
+   void f() {
+     [[Foo]] foo;
+   }
+  )cpp");
+  LangOptions LangOpts;
+  LangOpts.CPlusPlus = true;
+  EXPECT_EQ(Code.ranges(),
+            collectIdentifierRanges("Foo", Code.code(), LangOpts));
+}
+
 } // namespace
 } // namespace clangd
 } // namespace clang
Index: clang-tools-extra/clangd/SourceCode.h
===================================================================
--- clang-tools-extra/clangd/SourceCode.h
+++ clang-tools-extra/clangd/SourceCode.h
@@ -232,6 +232,11 @@
 llvm::StringMap<unsigned> collectIdentifiers(llvm::StringRef Content,
                                              const format::FormatStyle &Style);
 
+/// Collects all ranges of the given identifier in the source code.
+std::vector<Range> collectIdentifierRanges(llvm::StringRef IdentifierName,
+                                           llvm::StringRef Content,
+                                           const LangOptions &LangOpts);
+
 /// Collects words from the source code.
 /// Unlike collectIdentifiers:
 /// - also finds text in comments:
Index: clang-tools-extra/clangd/SourceCode.cpp
===================================================================
--- clang-tools-extra/clangd/SourceCode.cpp
+++ clang-tools-extra/clangd/SourceCode.cpp
@@ -719,27 +719,31 @@
   return formatReplacements(Code, std::move(*CleanReplaces), Style);
 }
 
-void lex(llvm::StringRef Code, const format::FormatStyle &Style,
-         llvm::function_ref<void(const clang::Token &, Position)> Action) {
+void lex(llvm::StringRef Code, const LangOptions &LangOpts,
+         llvm::function_ref<void(const clang::Token &, SourceLocation,
+                                 const SourceManager &SM)>
+             Action) {
   // FIXME: InMemoryFileAdapter crashes unless the buffer is null terminated!
   std::string NullTerminatedCode = Code.str();
   SourceManagerForFile FileSM("dummy.cpp", NullTerminatedCode);
   auto &SM = FileSM.get();
   auto FID = SM.getMainFileID();
-  Lexer Lex(FID, SM.getBuffer(FID), SM, format::getFormattingLangOpts(Style));
+  Lexer Lex(FID, SM.getBuffer(FID), SM, LangOpts);
   Token Tok;
 
   while (!Lex.LexFromRawLexer(Tok))
-    Action(Tok, sourceLocToPosition(SM, Tok.getLocation()));
+    Action(Tok, Tok.getLocation(), SM);
   // LexFromRawLexer returns true after it lexes last token, so we still have
   // one more token to report.
-  Action(Tok, sourceLocToPosition(SM, Tok.getLocation()));
+  Action(Tok, Tok.getLocation(), SM);
 }
 
 llvm::StringMap<unsigned> collectIdentifiers(llvm::StringRef Content,
                                              const format::FormatStyle &Style) {
   llvm::StringMap<unsigned> Identifiers;
-  lex(Content, Style, [&](const clang::Token &Tok, Position) {
+  auto LangOpt = format::getFormattingLangOpts(Style);
+  lex(Content, LangOpt, [&](const clang::Token &Tok,
+                            SourceLocation, const SourceManager &) {
     switch (Tok.getKind()) {
     case tok::identifier:
       ++Identifiers[Tok.getIdentifierInfo()->getName()];
@@ -754,6 +758,25 @@
   return Identifiers;
 }
 
+std::vector<Range> collectIdentifierRanges(llvm::StringRef IdentifierName,
+                                           llvm::StringRef Content,
+                                           const LangOptions &LangOpts) {
+  std::vector<Range> Ranges;
+  lex(Content, LangOpts,
+      [&](const clang::Token &Tok, SourceLocation Loc,
+          const SourceManager &SM) {
+        llvm::StringRef TokenName;
+        if (Tok.getKind() == tok::identifier)
+          TokenName = Tok.getIdentifierInfo()->getName();
+        else if (Tok.getKind() == tok::raw_identifier)
+          TokenName = Tok.getRawIdentifier();
+        if (TokenName == IdentifierName)
+          if (auto Range = getTokenRange(SM, LangOpts, Loc))
+            Ranges.push_back(*Range);
+      });
+  return Ranges;
+}
+
 namespace {
 struct NamespaceEvent {
   enum {
@@ -786,8 +809,10 @@
   std::string NSName;
 
   NamespaceEvent Event;
-  lex(Code, Style, [&](const clang::Token &Tok, Position P) {
-    Event.Pos = std::move(P);
+  lex(Code, format::getFormattingLangOpts(Style),
+      [&](const clang::Token &Tok,
+          SourceLocation P, const SourceManager& SM) {
+    Event.Pos = sourceLocToPosition(SM, P);
     switch (Tok.getKind()) {
     case tok::raw_identifier:
       // In raw mode, this could be a keyword or a name.

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits