[refactor] Initial outline of implementation of "extract function" refactoring

This commit adds an initial, skeleton outline of the "extract function"
refactoring. The extracted function doesn't capture variables / rewrite code
yet, it just basically does a simple copy-paste.
The following initiation rules are specified:

- extraction can only be done for executable code in a function/method/block.
  This means that you can't extract a global variable initialize into a function
  right now.
- simple literals and references are not extractable.

This commit also adds support for full source ranges to clang-refactor's test
mode.

Differential Revision: https://reviews.llvm.org/D38982

llvm-svn: 316465
diff --git a/clang/lib/Tooling/Refactoring/ASTSelection.cpp b/clang/lib/Tooling/Refactoring/ASTSelection.cpp
index 2c9c42bf..9d0683a 100644
--- a/clang/lib/Tooling/Refactoring/ASTSelection.cpp
+++ b/clang/lib/Tooling/Refactoring/ASTSelection.cpp
@@ -322,6 +322,10 @@
     return CodeRangeASTSelection(Selected.Node, Selected.Parents,
                                  /*AreChildrenSelected=*/false);
   }
+  // FIXME (Alex L): First selected SwitchCase means that first case statement.
+  // is selected actually
+  // (See https://github.com/apple/swift-clang & CompoundStmtRange).
+
   // FIXME (Alex L): Tweak selection rules for compound statements, see:
   // https://github.com/apple/swift-clang/blob/swift-4.1-branch/lib/Tooling/
   // Refactor/ASTSlice.cpp#L513
@@ -330,3 +334,36 @@
   return CodeRangeASTSelection(Selected.Node, Selected.Parents,
                                /*AreChildrenSelected=*/true);
 }
+
+bool CodeRangeASTSelection::isInFunctionLikeBodyOfCode() const {
+  bool IsPrevCompound = false;
+  // Scan through the parents (bottom-to-top) and check if the selection is
+  // contained in a compound statement that's a body of a function/method
+  // declaration.
+  for (const auto &Parent : llvm::reverse(Parents)) {
+    const DynTypedNode &Node = Parent.get().Node;
+    if (const auto *D = Node.get<Decl>()) {
+      // FIXME (Alex L): Test for BlockDecl && ObjCMethodDecl.
+      if (isa<FunctionDecl>(D))
+        return IsPrevCompound;
+      // FIXME (Alex L): We should return false on top-level decls in functions
+      // e.g. we don't want to extract:
+      // function foo() { struct X {
+      //   int m = /*selection:*/ 1 + 2 /*selection end*/; }; };
+    }
+    IsPrevCompound = Node.get<CompoundStmt>() != nullptr;
+  }
+  return false;
+}
+
+const Decl *CodeRangeASTSelection::getFunctionLikeNearestParent() const {
+  for (const auto &Parent : llvm::reverse(Parents)) {
+    const DynTypedNode &Node = Parent.get().Node;
+    if (const auto *D = Node.get<Decl>()) {
+      // FIXME (Alex L): Test for BlockDecl && ObjCMethodDecl.
+      if (isa<FunctionDecl>(D))
+        return D;
+    }
+  }
+  return nullptr;
+}
diff --git a/clang/lib/Tooling/Refactoring/ASTSelectionRequirements.cpp b/clang/lib/Tooling/Refactoring/ASTSelectionRequirements.cpp
new file mode 100644
index 0000000..c0232c5
--- /dev/null
+++ b/clang/lib/Tooling/Refactoring/ASTSelectionRequirements.cpp
@@ -0,0 +1,48 @@
+//===--- ASTSelectionRequirements.cpp - Clang refactoring library ---------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "clang/Tooling/Refactoring/RefactoringActionRuleRequirements.h"
+
+using namespace clang;
+using namespace tooling;
+
+Expected<SelectedASTNode>
+ASTSelectionRequirement::evaluate(RefactoringRuleContext &Context) const {
+  // FIXME: Memoize so that selection is evaluated only once.
+  Expected<SourceRange> Range =
+      SourceRangeSelectionRequirement::evaluate(Context);
+  if (!Range)
+    return Range.takeError();
+
+  Optional<SelectedASTNode> Selection =
+      findSelectedASTNodes(Context.getASTContext(), *Range);
+  if (!Selection)
+    return Context.createDiagnosticError(
+        Range->getBegin(), diag::err_refactor_selection_invalid_ast);
+  return std::move(*Selection);
+}
+
+Expected<CodeRangeASTSelection> CodeRangeASTSelectionRequirement::evaluate(
+    RefactoringRuleContext &Context) const {
+  // FIXME: Memoize so that selection is evaluated only once.
+  Expected<SelectedASTNode> ASTSelection =
+      ASTSelectionRequirement::evaluate(Context);
+  if (!ASTSelection)
+    return ASTSelection.takeError();
+  std::unique_ptr<SelectedASTNode> StoredSelection =
+      llvm::make_unique<SelectedASTNode>(std::move(*ASTSelection));
+  Optional<CodeRangeASTSelection> CodeRange = CodeRangeASTSelection::create(
+      Context.getSelectionRange(), *StoredSelection);
+  if (!CodeRange)
+    return Context.createDiagnosticError(
+        Context.getSelectionRange().getBegin(),
+        diag::err_refactor_selection_invalid_ast);
+  Context.setASTSelection(std::move(StoredSelection));
+  return std::move(*CodeRange);
+}
diff --git a/clang/lib/Tooling/Refactoring/CMakeLists.txt b/clang/lib/Tooling/Refactoring/CMakeLists.txt
index 43ea1d9..f30c679 100644
--- a/clang/lib/Tooling/Refactoring/CMakeLists.txt
+++ b/clang/lib/Tooling/Refactoring/CMakeLists.txt
@@ -2,7 +2,9 @@
 
 add_clang_library(clangToolingRefactor
   ASTSelection.cpp
+  ASTSelectionRequirements.cpp
   AtomicChange.cpp
+  Extract.cpp
   RefactoringActions.cpp
   Rename/RenamingAction.cpp
   Rename/SymbolOccurrences.cpp
diff --git a/clang/lib/Tooling/Refactoring/Extract.cpp b/clang/lib/Tooling/Refactoring/Extract.cpp
new file mode 100644
index 0000000..616900c
--- /dev/null
+++ b/clang/lib/Tooling/Refactoring/Extract.cpp
@@ -0,0 +1,232 @@
+//===--- Extract.cpp - Clang refactoring library --------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+///
+/// \file
+/// \brief Implements the "extract" refactoring that can pull code into
+/// new functions, methods or declare new variables.
+///
+//===----------------------------------------------------------------------===//
+
+#include "clang/AST/ASTContext.h"
+#include "clang/AST/Expr.h"
+#include "clang/Rewrite/Core/Rewriter.h"
+#include "clang/Tooling/Refactoring/RefactoringAction.h"
+#include "clang/Tooling/Refactoring/RefactoringActionRules.h"
+#include "clang/Tooling/Refactoring/RefactoringOptions.h"
+
+namespace clang {
+namespace tooling {
+
+namespace {
+
+/// Returns true if \c E is a simple literal or a reference expression that
+/// should not be extracted.
+bool isSimpleExpression(const Expr *E) {
+  if (!E)
+    return false;
+  switch (E->IgnoreParenCasts()->getStmtClass()) {
+  case Stmt::DeclRefExprClass:
+  case Stmt::PredefinedExprClass:
+  case Stmt::IntegerLiteralClass:
+  case Stmt::FloatingLiteralClass:
+  case Stmt::ImaginaryLiteralClass:
+  case Stmt::CharacterLiteralClass:
+  case Stmt::StringLiteralClass:
+    return true;
+  default:
+    return false;
+  }
+}
+
+class ExtractableCodeSelectionRequirement final
+    : public CodeRangeASTSelectionRequirement {
+public:
+  Expected<CodeRangeASTSelection>
+  evaluate(RefactoringRuleContext &Context) const {
+    Expected<CodeRangeASTSelection> Selection =
+        CodeRangeASTSelectionRequirement::evaluate(Context);
+    if (!Selection)
+      return Selection.takeError();
+    CodeRangeASTSelection &Code = *Selection;
+
+    // We would like to extract code out of functions/methods/blocks.
+    // Prohibit extraction from things like global variable / field
+    // initializers and other top-level expressions.
+    if (!Code.isInFunctionLikeBodyOfCode())
+      return Context.createDiagnosticError(
+          diag::err_refactor_code_outside_of_function);
+
+    // Avoid extraction of simple literals and references.
+    if (Code.size() == 1 && isSimpleExpression(dyn_cast<Expr>(Code[0])))
+      return Context.createDiagnosticError(
+          diag::err_refactor_extract_simple_expression);
+
+    // FIXME (Alex L): Prohibit extraction of Objective-C property setters.
+    return Selection;
+  }
+};
+
+class ExtractFunction final : public SourceChangeRefactoringRule {
+public:
+  ExtractFunction(CodeRangeASTSelection Code, Optional<std::string> DeclName)
+      : Code(std::move(Code)),
+        DeclName(DeclName ? std::move(*DeclName) : "extracted") {}
+
+  Expected<AtomicChanges>
+  createSourceReplacements(RefactoringRuleContext &Context) override;
+
+private:
+  CodeRangeASTSelection Code;
+
+  // FIXME: Account for naming collisions:
+  //  - error when name is specified by user.
+  //  - rename to "extractedN" when name is implicit.
+  std::string DeclName;
+};
+
+SourceLocation computeFunctionExtractionLocation(const Decl *D) {
+  // FIXME (Alex L): Method -> function extraction should place function before
+  // C++ record if the method is defined inside the record.
+  return D->getLocStart();
+}
+
+// FIXME: Support C++ method extraction.
+// FIXME: Support Objective-C method extraction.
+Expected<AtomicChanges>
+ExtractFunction::createSourceReplacements(RefactoringRuleContext &Context) {
+  const Decl *ParentDecl = Code.getFunctionLikeNearestParent();
+  assert(ParentDecl && "missing parent");
+
+  // Compute the source range of the code that should be extracted.
+  SourceRange ExtractedRange(Code[0]->getLocStart(),
+                             Code[Code.size() - 1]->getLocEnd());
+  // FIXME (Alex L): Add code that accounts for macro locations.
+
+  ASTContext &AST = Context.getASTContext();
+  SourceManager &SM = AST.getSourceManager();
+  const LangOptions &LangOpts = AST.getLangOpts();
+  Rewriter ExtractedCodeRewriter(SM, LangOpts);
+
+  // FIXME: Capture used variables.
+
+  // Compute the return type.
+  QualType ReturnType = AST.VoidTy;
+  // FIXME (Alex L): Account for the return statement in extracted code.
+  // FIXME (Alex L): Check for lexical expression instead.
+  bool IsExpr = Code.size() == 1 && isa<Expr>(Code[0]);
+  if (IsExpr) {
+    // FIXME (Alex L): Get a more user-friendly type if needed.
+    ReturnType = cast<Expr>(Code[0])->getType();
+  }
+
+  // FIXME: Rewrite the extracted code performing any required adjustments.
+
+  // FIXME: Capture any field if necessary (method -> function extraction).
+
+  // FIXME: Sort captured variables by name.
+
+  // FIXME: Capture 'this' / 'self' if necessary.
+
+  // FIXME: Compute the actual parameter types.
+
+  // Compute the location of the extracted declaration.
+  SourceLocation ExtractedDeclLocation =
+      computeFunctionExtractionLocation(ParentDecl);
+  // FIXME: Adjust the location to account for any preceding comments.
+
+  // FIXME: Adjust with PP awareness like in Sema to get correct 'bool'
+  // treatment.
+  PrintingPolicy PP = AST.getPrintingPolicy();
+  // FIXME: PP.UseStdFunctionForLambda = true;
+  PP.SuppressStrongLifetime = true;
+  PP.SuppressLifetimeQualifiers = true;
+  PP.SuppressUnwrittenScope = true;
+
+  AtomicChange Change(SM, ExtractedDeclLocation);
+  // Create the replacement for the extracted declaration.
+  {
+    std::string ExtractedCode;
+    llvm::raw_string_ostream OS(ExtractedCode);
+    // FIXME: Use 'inline' in header.
+    OS << "static ";
+    ReturnType.print(OS, PP, DeclName);
+    OS << '(';
+    // FIXME: Arguments.
+    OS << ')';
+
+    // Function body.
+    OS << " {\n";
+    if (IsExpr && !ReturnType->isVoidType())
+      OS << "return ";
+    OS << ExtractedCodeRewriter.getRewrittenText(ExtractedRange);
+    // FIXME: Compute the correct semicolon policy.
+    OS << ';';
+    OS << "\n}\n\n";
+    auto Err = Change.insert(SM, ExtractedDeclLocation, OS.str());
+    if (Err)
+      return std::move(Err);
+  }
+
+  // Create the replacement for the call to the extracted declaration.
+  {
+    std::string ReplacedCode;
+    llvm::raw_string_ostream OS(ReplacedCode);
+
+    OS << DeclName << '(';
+    // FIXME: Forward arguments.
+    OS << ')';
+    // FIXME: Add semicolon if needed.
+
+    auto Err = Change.replace(
+        SM, CharSourceRange::getTokenRange(ExtractedRange), OS.str());
+    if (Err)
+      return std::move(Err);
+  }
+
+  // FIXME: Add support for assocciated symbol location to AtomicChange to mark
+  // the ranges of the name of the extracted declaration.
+  return AtomicChanges{std::move(Change)};
+}
+
+class DeclNameOption final : public OptionalRefactoringOption<std::string> {
+public:
+  StringRef getName() const { return "name"; }
+  StringRef getDescription() const {
+    return "Name of the extracted declaration";
+  }
+};
+
+class ExtractRefactoring final : public RefactoringAction {
+public:
+  StringRef getCommand() const override { return "extract"; }
+
+  StringRef getDescription() const override {
+    return "(WIP action; use with caution!) Extracts code into a new function "
+           "/ method / variable";
+  }
+
+  /// Returns a set of refactoring actions rules that are defined by this
+  /// action.
+  RefactoringActionRules createActionRules() const override {
+    RefactoringActionRules Rules;
+    Rules.push_back(createRefactoringActionRule<ExtractFunction>(
+        ExtractableCodeSelectionRequirement(),
+        OptionRequirement<DeclNameOption>()));
+    return Rules;
+  }
+};
+
+} // end anonymous namespace
+
+std::unique_ptr<RefactoringAction> createExtractAction() {
+  return llvm::make_unique<ExtractRefactoring>();
+}
+
+} // end namespace tooling
+} // end namespace clang