This revision was automatically updated to reflect the committed changes.
ioeric marked an inline comment as done.
Closed by commit rL332720: Move #include manipulation code to new 
lib/Tooling/Inclusions. (authored by ioeric, committed by ).
Herald added a subscriber: llvm-commits.

Changed prior to commit:
  https://reviews.llvm.org/D47068?vs=147504&id=147507#toc

Repository:
  rL LLVM

https://reviews.llvm.org/D47068

Files:
  cfe/trunk/include/clang/Format/Format.h
  cfe/trunk/include/clang/Tooling/Core/HeaderIncludes.h
  cfe/trunk/include/clang/Tooling/Core/IncludeStyle.h
  cfe/trunk/include/clang/Tooling/Inclusions/HeaderIncludes.h
  cfe/trunk/include/clang/Tooling/Inclusions/IncludeStyle.h
  cfe/trunk/lib/Format/CMakeLists.txt
  cfe/trunk/lib/Format/Format.cpp
  cfe/trunk/lib/Tooling/CMakeLists.txt
  cfe/trunk/lib/Tooling/Core/CMakeLists.txt
  cfe/trunk/lib/Tooling/Core/HeaderIncludes.cpp
  cfe/trunk/lib/Tooling/Core/IncludeStyle.cpp
  cfe/trunk/lib/Tooling/Inclusions/CMakeLists.txt
  cfe/trunk/lib/Tooling/Inclusions/HeaderIncludes.cpp
  cfe/trunk/lib/Tooling/Inclusions/IncludeStyle.cpp
  cfe/trunk/unittests/Tooling/HeaderIncludesTest.cpp

Index: cfe/trunk/lib/Format/CMakeLists.txt
===================================================================
--- cfe/trunk/lib/Format/CMakeLists.txt
+++ cfe/trunk/lib/Format/CMakeLists.txt
@@ -20,4 +20,5 @@
   clangBasic
   clangLex
   clangToolingCore
+  clangToolingInclusions
   )
Index: cfe/trunk/lib/Format/Format.cpp
===================================================================
--- cfe/trunk/lib/Format/Format.cpp
+++ cfe/trunk/lib/Format/Format.cpp
@@ -31,7 +31,7 @@
 #include "clang/Basic/SourceManager.h"
 #include "clang/Basic/VirtualFileSystem.h"
 #include "clang/Lex/Lexer.h"
-#include "clang/Tooling/Core/HeaderIncludes.h"
+#include "clang/Tooling/Inclusions/HeaderIncludes.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/Support/Allocator.h"
Index: cfe/trunk/lib/Tooling/CMakeLists.txt
===================================================================
--- cfe/trunk/lib/Tooling/CMakeLists.txt
+++ cfe/trunk/lib/Tooling/CMakeLists.txt
@@ -4,6 +4,7 @@
   )
 
 add_subdirectory(Core)
+add_subdirectory(Inclusions)
 add_subdirectory(Refactoring)
 add_subdirectory(ASTDiff)
 
Index: cfe/trunk/lib/Tooling/Core/CMakeLists.txt
===================================================================
--- cfe/trunk/lib/Tooling/Core/CMakeLists.txt
+++ cfe/trunk/lib/Tooling/Core/CMakeLists.txt
@@ -2,8 +2,6 @@
 
 add_clang_library(clangToolingCore
   Diagnostic.cpp
-  HeaderIncludes.cpp
-  IncludeStyle.cpp
   Lookup.cpp
   Replacement.cpp
 
Index: cfe/trunk/lib/Tooling/Inclusions/IncludeStyle.cpp
===================================================================
--- cfe/trunk/lib/Tooling/Inclusions/IncludeStyle.cpp
+++ cfe/trunk/lib/Tooling/Inclusions/IncludeStyle.cpp
@@ -0,0 +1,31 @@
+//===--- IncludeStyle.cpp - Style of C++ #include directives -----*- C++-*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "clang/Tooling/Inclusions/IncludeStyle.h"
+
+using clang::tooling::IncludeStyle;
+
+namespace llvm {
+namespace yaml {
+
+void MappingTraits<IncludeStyle::IncludeCategory>::mapping(
+    IO &IO, IncludeStyle::IncludeCategory &Category) {
+  IO.mapOptional("Regex", Category.Regex);
+  IO.mapOptional("Priority", Category.Priority);
+}
+
+void ScalarEnumerationTraits<IncludeStyle::IncludeBlocksStyle>::enumeration(
+    IO &IO, IncludeStyle::IncludeBlocksStyle &Value) {
+  IO.enumCase(Value, "Preserve", IncludeStyle::IBS_Preserve);
+  IO.enumCase(Value, "Merge", IncludeStyle::IBS_Merge);
+  IO.enumCase(Value, "Regroup", IncludeStyle::IBS_Regroup);
+}
+
+} // namespace yaml
+} // namespace llvm
Index: cfe/trunk/lib/Tooling/Inclusions/HeaderIncludes.cpp
===================================================================
--- cfe/trunk/lib/Tooling/Inclusions/HeaderIncludes.cpp
+++ cfe/trunk/lib/Tooling/Inclusions/HeaderIncludes.cpp
@@ -0,0 +1,330 @@
+//===--- HeaderIncludes.cpp - Insert/Delete #includes --*- C++ -*----------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "clang/Tooling/Inclusions/HeaderIncludes.h"
+#include "clang/Basic/SourceManager.h"
+#include "clang/Lex/Lexer.h"
+
+namespace clang {
+namespace tooling {
+namespace {
+
+LangOptions createLangOpts() {
+  LangOptions LangOpts;
+  LangOpts.CPlusPlus = 1;
+  LangOpts.CPlusPlus11 = 1;
+  LangOpts.CPlusPlus14 = 1;
+  LangOpts.LineComment = 1;
+  LangOpts.CXXOperatorNames = 1;
+  LangOpts.Bool = 1;
+  LangOpts.ObjC1 = 1;
+  LangOpts.ObjC2 = 1;
+  LangOpts.MicrosoftExt = 1;    // To get kw___try, kw___finally.
+  LangOpts.DeclSpecKeyword = 1; // To get __declspec.
+  LangOpts.WChar = 1;           // To get wchar_t
+  return LangOpts;
+}
+
+// Returns the offset after skipping a sequence of tokens, matched by \p
+// GetOffsetAfterSequence, from the start of the code.
+// \p GetOffsetAfterSequence should be a function that matches a sequence of
+// tokens and returns an offset after the sequence.
+unsigned getOffsetAfterTokenSequence(
+    StringRef FileName, StringRef Code, const IncludeStyle &Style,
+    llvm::function_ref<unsigned(const SourceManager &, Lexer &, Token &)>
+        GetOffsetAfterSequence) {
+  SourceManagerForFile VirtualSM(FileName, Code);
+  SourceManager &SM = VirtualSM.get();
+  Lexer Lex(SM.getMainFileID(), SM.getBuffer(SM.getMainFileID()), SM,
+            createLangOpts());
+  Token Tok;
+  // Get the first token.
+  Lex.LexFromRawLexer(Tok);
+  return GetOffsetAfterSequence(SM, Lex, Tok);
+}
+
+// Check if a sequence of tokens is like "#<Name> <raw_identifier>". If it is,
+// \p Tok will be the token after this directive; otherwise, it can be any token
+// after the given \p Tok (including \p Tok).
+bool checkAndConsumeDirectiveWithName(Lexer &Lex, StringRef Name, Token &Tok) {
+  bool Matched = Tok.is(tok::hash) && !Lex.LexFromRawLexer(Tok) &&
+                 Tok.is(tok::raw_identifier) &&
+                 Tok.getRawIdentifier() == Name && !Lex.LexFromRawLexer(Tok) &&
+                 Tok.is(tok::raw_identifier);
+  if (Matched)
+    Lex.LexFromRawLexer(Tok);
+  return Matched;
+}
+
+void skipComments(Lexer &Lex, Token &Tok) {
+  while (Tok.is(tok::comment))
+    if (Lex.LexFromRawLexer(Tok))
+      return;
+}
+
+// Returns the offset after header guard directives and any comments
+// before/after header guards. If no header guard presents in the code, this
+// will returns the offset after skipping all comments from the start of the
+// code.
+unsigned getOffsetAfterHeaderGuardsAndComments(StringRef FileName,
+                                               StringRef Code,
+                                               const IncludeStyle &Style) {
+  return getOffsetAfterTokenSequence(
+      FileName, Code, Style,
+      [](const SourceManager &SM, Lexer &Lex, Token Tok) {
+        skipComments(Lex, Tok);
+        unsigned InitialOffset = SM.getFileOffset(Tok.getLocation());
+        if (checkAndConsumeDirectiveWithName(Lex, "ifndef", Tok)) {
+          skipComments(Lex, Tok);
+          if (checkAndConsumeDirectiveWithName(Lex, "define", Tok))
+            return SM.getFileOffset(Tok.getLocation());
+        }
+        return InitialOffset;
+      });
+}
+
+// Check if a sequence of tokens is like
+//    "#include ("header.h" | <header.h>)".
+// If it is, \p Tok will be the token after this directive; otherwise, it can be
+// any token after the given \p Tok (including \p Tok).
+bool checkAndConsumeInclusiveDirective(Lexer &Lex, Token &Tok) {
+  auto Matched = [&]() {
+    Lex.LexFromRawLexer(Tok);
+    return true;
+  };
+  if (Tok.is(tok::hash) && !Lex.LexFromRawLexer(Tok) &&
+      Tok.is(tok::raw_identifier) && Tok.getRawIdentifier() == "include") {
+    if (Lex.LexFromRawLexer(Tok))
+      return false;
+    if (Tok.is(tok::string_literal))
+      return Matched();
+    if (Tok.is(tok::less)) {
+      while (!Lex.LexFromRawLexer(Tok) && Tok.isNot(tok::greater)) {
+      }
+      if (Tok.is(tok::greater))
+        return Matched();
+    }
+  }
+  return false;
+}
+
+// Returns the offset of the last #include directive after which a new
+// #include can be inserted. This ignores #include's after the #include block(s)
+// in the beginning of a file to avoid inserting headers into code sections
+// where new #include's should not be added by default.
+// These code sections include:
+//      - raw string literals (containing #include).
+//      - #if blocks.
+//      - Special #include's among declarations (e.g. functions).
+//
+// If no #include after which a new #include can be inserted, this returns the
+// offset after skipping all comments from the start of the code.
+// Inserting after an #include is not allowed if it comes after code that is not
+// #include (e.g. pre-processing directive that is not #include, declarations).
+unsigned getMaxHeaderInsertionOffset(StringRef FileName, StringRef Code,
+                                     const IncludeStyle &Style) {
+  return getOffsetAfterTokenSequence(
+      FileName, Code, Style,
+      [](const SourceManager &SM, Lexer &Lex, Token Tok) {
+        skipComments(Lex, Tok);
+        unsigned MaxOffset = SM.getFileOffset(Tok.getLocation());
+        while (checkAndConsumeInclusiveDirective(Lex, Tok))
+          MaxOffset = SM.getFileOffset(Tok.getLocation());
+        return MaxOffset;
+      });
+}
+
+inline StringRef trimInclude(StringRef IncludeName) {
+  return IncludeName.trim("\"<>");
+}
+
+const char IncludeRegexPattern[] =
+    R"(^[\t\ ]*#[\t\ ]*(import|include)[^"<]*(["<][^">]*[">]))";
+
+} // anonymous namespace
+
+IncludeCategoryManager::IncludeCategoryManager(const IncludeStyle &Style,
+                                               StringRef FileName)
+    : Style(Style), FileName(FileName) {
+  FileStem = llvm::sys::path::stem(FileName);
+  for (const auto &Category : Style.IncludeCategories)
+    CategoryRegexs.emplace_back(Category.Regex, llvm::Regex::IgnoreCase);
+  IsMainFile = FileName.endswith(".c") || FileName.endswith(".cc") ||
+               FileName.endswith(".cpp") || FileName.endswith(".c++") ||
+               FileName.endswith(".cxx") || FileName.endswith(".m") ||
+               FileName.endswith(".mm");
+}
+
+int IncludeCategoryManager::getIncludePriority(StringRef IncludeName,
+                                               bool CheckMainHeader) const {
+  int Ret = INT_MAX;
+  for (unsigned i = 0, e = CategoryRegexs.size(); i != e; ++i)
+    if (CategoryRegexs[i].match(IncludeName)) {
+      Ret = Style.IncludeCategories[i].Priority;
+      break;
+    }
+  if (CheckMainHeader && IsMainFile && Ret > 0 && isMainHeader(IncludeName))
+    Ret = 0;
+  return Ret;
+}
+
+bool IncludeCategoryManager::isMainHeader(StringRef IncludeName) const {
+  if (!IncludeName.startswith("\""))
+    return false;
+  StringRef HeaderStem =
+      llvm::sys::path::stem(IncludeName.drop_front(1).drop_back(1));
+  if (FileStem.startswith(HeaderStem) ||
+      FileStem.startswith_lower(HeaderStem)) {
+    llvm::Regex MainIncludeRegex((HeaderStem + Style.IncludeIsMainRegex).str(),
+                                 llvm::Regex::IgnoreCase);
+    if (MainIncludeRegex.match(FileStem))
+      return true;
+  }
+  return false;
+}
+
+HeaderIncludes::HeaderIncludes(StringRef FileName, StringRef Code,
+                               const IncludeStyle &Style)
+    : FileName(FileName), Code(Code), FirstIncludeOffset(-1),
+      MinInsertOffset(
+          getOffsetAfterHeaderGuardsAndComments(FileName, Code, Style)),
+      MaxInsertOffset(MinInsertOffset +
+                      getMaxHeaderInsertionOffset(
+                          FileName, Code.drop_front(MinInsertOffset), Style)),
+      Categories(Style, FileName),
+      IncludeRegex(llvm::Regex(IncludeRegexPattern)) {
+  // Add 0 for main header and INT_MAX for headers that are not in any
+  // category.
+  Priorities = {0, INT_MAX};
+  for (const auto &Category : Style.IncludeCategories)
+    Priorities.insert(Category.Priority);
+  SmallVector<StringRef, 32> Lines;
+  Code.drop_front(MinInsertOffset).split(Lines, "\n");
+
+  unsigned Offset = MinInsertOffset;
+  unsigned NextLineOffset;
+  SmallVector<StringRef, 4> Matches;
+  for (auto Line : Lines) {
+    NextLineOffset = std::min(Code.size(), Offset + Line.size() + 1);
+    if (IncludeRegex.match(Line, &Matches)) {
+      // If this is the last line without trailing newline, we need to make
+      // sure we don't delete across the file boundary.
+      addExistingInclude(
+          Include(Matches[2],
+                  tooling::Range(
+                      Offset, std::min(Line.size() + 1, Code.size() - Offset))),
+          NextLineOffset);
+    }
+    Offset = NextLineOffset;
+  }
+
+  // Populate CategoryEndOfssets:
+  // - Ensure that CategoryEndOffset[Highest] is always populated.
+  // - If CategoryEndOffset[Priority] isn't set, use the next higher value
+  // that is set, up to CategoryEndOffset[Highest].
+  auto Highest = Priorities.begin();
+  if (CategoryEndOffsets.find(*Highest) == CategoryEndOffsets.end()) {
+    if (FirstIncludeOffset >= 0)
+      CategoryEndOffsets[*Highest] = FirstIncludeOffset;
+    else
+      CategoryEndOffsets[*Highest] = MinInsertOffset;
+  }
+  // By this point, CategoryEndOffset[Highest] is always set appropriately:
+  //  - to an appropriate location before/after existing #includes, or
+  //  - to right after the header guard, or
+  //  - to the beginning of the file.
+  for (auto I = ++Priorities.begin(), E = Priorities.end(); I != E; ++I)
+    if (CategoryEndOffsets.find(*I) == CategoryEndOffsets.end())
+      CategoryEndOffsets[*I] = CategoryEndOffsets[*std::prev(I)];
+}
+
+// \p Offset: the start of the line following this include directive.
+void HeaderIncludes::addExistingInclude(Include IncludeToAdd,
+                                        unsigned NextLineOffset) {
+  auto Iter =
+      ExistingIncludes.try_emplace(trimInclude(IncludeToAdd.Name)).first;
+  Iter->second.push_back(std::move(IncludeToAdd));
+  auto &CurInclude = Iter->second.back();
+  // The header name with quotes or angle brackets.
+  // Only record the offset of current #include if we can insert after it.
+  if (CurInclude.R.getOffset() <= MaxInsertOffset) {
+    int Priority = Categories.getIncludePriority(
+        CurInclude.Name, /*CheckMainHeader=*/FirstIncludeOffset < 0);
+    CategoryEndOffsets[Priority] = NextLineOffset;
+    IncludesByPriority[Priority].push_back(&CurInclude);
+    if (FirstIncludeOffset < 0)
+      FirstIncludeOffset = CurInclude.R.getOffset();
+  }
+}
+
+llvm::Optional<tooling::Replacement>
+HeaderIncludes::insert(llvm::StringRef IncludeName, bool IsAngled) const {
+  assert(IncludeName == trimInclude(IncludeName));
+  // If a <header> ("header") already exists in code, "header" (<header>) with
+  // different quotation will still be inserted.
+  // FIXME: figure out if this is the best behavior.
+  auto It = ExistingIncludes.find(IncludeName);
+  if (It != ExistingIncludes.end())
+    for (const auto &Inc : It->second)
+      if ((IsAngled && StringRef(Inc.Name).startswith("<")) ||
+          (!IsAngled && StringRef(Inc.Name).startswith("\"")))
+        return llvm::None;
+  std::string Quoted = IsAngled ? ("<" + IncludeName + ">").str()
+                                : ("\"" + IncludeName + "\"").str();
+  StringRef QuotedName = Quoted;
+  int Priority = Categories.getIncludePriority(
+      QuotedName, /*CheckMainHeader=*/FirstIncludeOffset < 0);
+  auto CatOffset = CategoryEndOffsets.find(Priority);
+  assert(CatOffset != CategoryEndOffsets.end());
+  unsigned InsertOffset = CatOffset->second; // Fall back offset
+  auto Iter = IncludesByPriority.find(Priority);
+  if (Iter != IncludesByPriority.end()) {
+    for (const auto *Inc : Iter->second) {
+      if (QuotedName < Inc->Name) {
+        InsertOffset = Inc->R.getOffset();
+        break;
+      }
+    }
+  }
+  assert(InsertOffset <= Code.size());
+  std::string NewInclude = ("#include " + QuotedName + "\n").str();
+  // When inserting headers at end of the code, also append '\n' to the code
+  // if it does not end with '\n'.
+  // FIXME: when inserting multiple #includes at the end of code, only one
+  // newline should be added.
+  if (InsertOffset == Code.size() && (!Code.empty() && Code.back() != '\n'))
+    NewInclude = "\n" + NewInclude;
+  return tooling::Replacement(FileName, InsertOffset, 0, NewInclude);
+}
+
+tooling::Replacements HeaderIncludes::remove(llvm::StringRef IncludeName,
+                                             bool IsAngled) const {
+  assert(IncludeName == trimInclude(IncludeName));
+  tooling::Replacements Result;
+  auto Iter = ExistingIncludes.find(IncludeName);
+  if (Iter == ExistingIncludes.end())
+    return Result;
+  for (const auto &Inc : Iter->second) {
+    if ((IsAngled && StringRef(Inc.Name).startswith("\"")) ||
+        (!IsAngled && StringRef(Inc.Name).startswith("<")))
+      continue;
+    llvm::Error Err = Result.add(tooling::Replacement(
+        FileName, Inc.R.getOffset(), Inc.R.getLength(), ""));
+    if (Err) {
+      auto ErrMsg = "Unexpected conflicts in #include deletions: " +
+                    llvm::toString(std::move(Err));
+      llvm_unreachable(ErrMsg.c_str());
+    }
+  }
+  return Result;
+}
+
+
+} // namespace tooling
+} // namespace clang
Index: cfe/trunk/lib/Tooling/Inclusions/CMakeLists.txt
===================================================================
--- cfe/trunk/lib/Tooling/Inclusions/CMakeLists.txt
+++ cfe/trunk/lib/Tooling/Inclusions/CMakeLists.txt
@@ -0,0 +1,12 @@
+set(LLVM_LINK_COMPONENTS support)
+
+add_clang_library(clangToolingInclusions
+  HeaderIncludes.cpp
+  IncludeStyle.cpp
+
+  LINK_LIBS
+  clangBasic
+  clangLex
+  clangRewrite
+  clangToolingCore
+  )
Index: cfe/trunk/unittests/Tooling/HeaderIncludesTest.cpp
===================================================================
--- cfe/trunk/unittests/Tooling/HeaderIncludesTest.cpp
+++ cfe/trunk/unittests/Tooling/HeaderIncludesTest.cpp
@@ -7,7 +7,7 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "clang/Tooling/Core/HeaderIncludes.h"
+#include "clang/Tooling/Inclusions/HeaderIncludes.h"
 #include "../Tooling/ReplacementTest.h"
 #include "../Tooling/RewriterTestContext.h"
 #include "clang/Format/Format.h"
Index: cfe/trunk/include/clang/Tooling/Inclusions/IncludeStyle.h
===================================================================
--- cfe/trunk/include/clang/Tooling/Inclusions/IncludeStyle.h
+++ cfe/trunk/include/clang/Tooling/Inclusions/IncludeStyle.h
@@ -0,0 +1,133 @@
+//===--- IncludeStyle.h - Style of C++ #include directives -------*- C++-*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_TOOLING_INCLUSIONS_INCLUDESTYLE_H
+#define LLVM_CLANG_TOOLING_INCLUSIONS_INCLUDESTYLE_H
+
+#include "llvm/Support/YAMLTraits.h"
+#include <string>
+#include <vector>
+
+namespace clang {
+namespace tooling {
+
+/// Style for sorting and grouping C++ #include directives.
+struct IncludeStyle {
+  /// Styles for sorting multiple ``#include`` blocks.
+  enum IncludeBlocksStyle {
+    /// Sort each ``#include`` block separately.
+    /// \code
+    ///    #include "b.h"               into      #include "b.h"
+    ///
+    ///    #include <lib/main.h>                  #include "a.h"
+    ///    #include "a.h"                         #include <lib/main.h>
+    /// \endcode
+    IBS_Preserve,
+    /// Merge multiple ``#include`` blocks together and sort as one.
+    /// \code
+    ///    #include "b.h"               into      #include "a.h"
+    ///                                           #include "b.h"
+    ///    #include <lib/main.h>                  #include <lib/main.h>
+    ///    #include "a.h"
+    /// \endcode
+    IBS_Merge,
+    /// Merge multiple ``#include`` blocks together and sort as one.
+    /// Then split into groups based on category priority. See
+    /// ``IncludeCategories``.
+    /// \code
+    ///    #include "b.h"               into      #include "a.h"
+    ///                                           #include "b.h"
+    ///    #include <lib/main.h>
+    ///    #include "a.h"                         #include <lib/main.h>
+    /// \endcode
+    IBS_Regroup,
+  };
+
+  /// Dependent on the value, multiple ``#include`` blocks can be sorted
+  /// as one and divided based on category.
+  IncludeBlocksStyle IncludeBlocks;
+
+  /// See documentation of ``IncludeCategories``.
+  struct IncludeCategory {
+    /// The regular expression that this category matches.
+    std::string Regex;
+    /// The priority to assign to this category.
+    int Priority;
+    bool operator==(const IncludeCategory &Other) const {
+      return Regex == Other.Regex && Priority == Other.Priority;
+    }
+  };
+
+  /// Regular expressions denoting the different ``#include`` categories
+  /// used for ordering ``#includes``.
+  ///
+  /// These regular expressions are matched against the filename of an include
+  /// (including the <> or "") in order. The value belonging to the first
+  /// matching regular expression is assigned and ``#includes`` are sorted first
+  /// according to increasing category number and then alphabetically within
+  /// each category.
+  ///
+  /// If none of the regular expressions match, INT_MAX is assigned as
+  /// category. The main header for a source file automatically gets category 0.
+  /// so that it is generally kept at the beginning of the ``#includes``
+  /// (http://llvm.org/docs/CodingStandards.html#include-style). However, you
+  /// can also assign negative priorities if you have certain headers that
+  /// always need to be first.
+  ///
+  /// To configure this in the .clang-format file, use:
+  /// \code{.yaml}
+  ///   IncludeCategories:
+  ///     - Regex:           '^"(llvm|llvm-c|clang|clang-c)/'
+  ///       Priority:        2
+  ///     - Regex:           '^(<|"(gtest|gmock|isl|json)/)'
+  ///       Priority:        3
+  ///     - Regex:           '.*'
+  ///       Priority:        1
+  /// \endcode
+  std::vector<IncludeCategory> IncludeCategories;
+
+  /// Specify a regular expression of suffixes that are allowed in the
+  /// file-to-main-include mapping.
+  ///
+  /// When guessing whether a #include is the "main" include (to assign
+  /// category 0, see above), use this regex of allowed suffixes to the header
+  /// stem. A partial match is done, so that:
+  /// - "" means "arbitrary suffix"
+  /// - "$" means "no suffix"
+  ///
+  /// For example, if configured to "(_test)?$", then a header a.h would be seen
+  /// as the "main" include in both a.cc and a_test.cc.
+  std::string IncludeIsMainRegex;
+};
+
+} // namespace tooling
+} // namespace clang
+
+LLVM_YAML_IS_SEQUENCE_VECTOR(clang::tooling::IncludeStyle::IncludeCategory)
+
+namespace llvm {
+namespace yaml {
+
+template <>
+struct MappingTraits<clang::tooling::IncludeStyle::IncludeCategory> {
+  static void mapping(IO &IO,
+                      clang::tooling::IncludeStyle::IncludeCategory &Category);
+};
+
+template <>
+struct ScalarEnumerationTraits<
+    clang::tooling::IncludeStyle::IncludeBlocksStyle> {
+  static void
+  enumeration(IO &IO, clang::tooling::IncludeStyle::IncludeBlocksStyle &Value);
+};
+
+} // namespace yaml
+} // namespace llvm
+
+#endif // LLVM_CLANG_TOOLING_INCLUSIONS_INCLUDESTYLE_H
Index: cfe/trunk/include/clang/Tooling/Inclusions/HeaderIncludes.h
===================================================================
--- cfe/trunk/include/clang/Tooling/Inclusions/HeaderIncludes.h
+++ cfe/trunk/include/clang/Tooling/Inclusions/HeaderIncludes.h
@@ -0,0 +1,137 @@
+//===--- HeaderIncludes.h - Insert/Delete #includes for C++ code--*- C++-*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CLANG_TOOLING_INCLUSIONS_HEADERINCLUDES_H
+#define LLVM_CLANG_TOOLING_INCLUSIONS_HEADERINCLUDES_H
+
+#include "clang/Basic/SourceManager.h"
+#include "clang/Tooling/Core/Replacement.h"
+#include "clang/Tooling/Inclusions/IncludeStyle.h"
+#include "llvm/Support/Path.h"
+#include "llvm/Support/Regex.h"
+#include <unordered_map>
+
+namespace clang {
+namespace tooling {
+
+/// This class manages priorities of C++ #include categories and calculates
+/// priorities for headers.
+/// FIXME(ioeric): move this class into implementation file when clang-format's
+/// include sorting functions are also moved here.
+class IncludeCategoryManager {
+public:
+  IncludeCategoryManager(const IncludeStyle &Style, StringRef FileName);
+
+  /// Returns the priority of the category which \p IncludeName belongs to.
+  /// If \p CheckMainHeader is true and \p IncludeName is a main header, returns
+  /// 0. Otherwise, returns the priority of the matching category or INT_MAX.
+  /// NOTE: this API is not thread-safe!
+  int getIncludePriority(StringRef IncludeName, bool CheckMainHeader) const;
+
+private:
+  bool isMainHeader(StringRef IncludeName) const;
+
+  const IncludeStyle Style;
+  bool IsMainFile;
+  std::string FileName;
+  // This refers to a substring in FileName.
+  StringRef FileStem;
+  // Regex is not thread-safe.
+  mutable SmallVector<llvm::Regex, 4> CategoryRegexs;
+};
+
+/// Generates replacements for inserting or deleting #include directives in a
+/// file.
+class HeaderIncludes {
+public:
+  HeaderIncludes(llvm::StringRef FileName, llvm::StringRef Code,
+                 const IncludeStyle &Style);
+
+  /// Inserts an #include directive of \p Header into the code. If \p IsAngled
+  /// is true, \p Header will be quoted with <> in the directive; otherwise, it
+  /// will be quoted with "".
+  ///
+  /// When searching for points to insert new header, this ignores #include's
+  /// after the #include block(s) in the beginning of a file to avoid inserting
+  /// headers into code sections where new #include's should not be added by
+  /// default. These code sections include:
+  ///   - raw string literals (containing #include).
+  ///   - #if blocks.
+  ///   - Special #include's among declarations (e.g. functions).
+  ///
+  /// Returns a replacement that inserts the new header into a suitable #include
+  /// block of the same category. This respects the order of the existing
+  /// #includes in the block; if the existing #includes are not already sorted,
+  /// this will simply insert the #include in front of the first #include of the
+  /// same category in the code that should be sorted after \p IncludeName. If
+  /// \p IncludeName already exists (with exactly the same spelling), this
+  /// returns None.
+  llvm::Optional<tooling::Replacement> insert(llvm::StringRef Header,
+                                              bool IsAngled) const;
+
+  /// Removes all existing #includes of \p Header quoted with <> if \p IsAngled
+  /// is true or "" if \p IsAngled is false.
+  /// This doesn't resolve the header file path; it only deletes #includes with
+  /// exactly the same spelling.
+  tooling::Replacements remove(llvm::StringRef Header, bool IsAngled) const;
+
+private:
+  struct Include {
+    Include(StringRef Name, tooling::Range R) : Name(Name), R(R) {}
+
+    // An include header quoted with either <> or "".
+    std::string Name;
+    // The range of the whole line of include directive including any eading
+    // whitespaces and trailing comment.
+    tooling::Range R;
+  };
+
+  void addExistingInclude(Include IncludeToAdd, unsigned NextLineOffset);
+
+  std::string FileName;
+  std::string Code;
+
+  // Map from include name (quotation trimmed) to a list of existing includes
+  // (in case there are more than one) with the name in the current file. <x>
+  // and "x" will be treated as the same header when deleting #includes.
+  llvm::StringMap<llvm::SmallVector<Include, 1>> ExistingIncludes;
+
+  /// Map from priorities of #include categories to all #includes in the same
+  /// category. This is used to find #includes of the same category when
+  /// inserting new #includes. #includes in the same categories are sorted in
+  /// in the order they appear in the source file.
+  /// See comment for "FormatStyle::IncludeCategories" for details about include
+  /// priorities.
+  std::unordered_map<int, llvm::SmallVector<const Include *, 8>>
+      IncludesByPriority;
+
+  int FirstIncludeOffset;
+  // All new headers should be inserted after this offset (e.g. after header
+  // guards, file comment).
+  unsigned MinInsertOffset;
+  // Max insertion offset in the original code. For example, we want to avoid
+  // inserting new #includes into the actual code section (e.g. after a
+  // declaration).
+  unsigned MaxInsertOffset;
+  IncludeCategoryManager Categories;
+  // Record the offset of the end of the last include in each category.
+  std::unordered_map<int, int> CategoryEndOffsets;
+
+  // All possible priorities.
+  std::set<int> Priorities;
+
+  // Matches a whole #include directive.
+  llvm::Regex IncludeRegex;
+};
+
+
+} // namespace tooling
+} // namespace clang
+
+#endif // LLVM_CLANG_TOOLING_INCLUSIONS_HEADERINCLUDES_H
Index: cfe/trunk/include/clang/Format/Format.h
===================================================================
--- cfe/trunk/include/clang/Format/Format.h
+++ cfe/trunk/include/clang/Format/Format.h
@@ -16,8 +16,8 @@
 #define LLVM_CLANG_FORMAT_FORMAT_H
 
 #include "clang/Basic/LangOptions.h"
-#include "clang/Tooling/Core/IncludeStyle.h"
 #include "clang/Tooling/Core/Replacement.h"
+#include "clang/Tooling/Inclusions/IncludeStyle.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/Support/Regex.h"
 #include <system_error>
Index: cfe/trunk/lib/Tooling/Core/HeaderIncludes.cpp
===================================================================
--- cfe/trunk/lib/Tooling/Core/HeaderIncludes.cpp
+++ cfe/trunk/lib/Tooling/Core/HeaderIncludes.cpp
@@ -1,330 +0,0 @@
-//===--- HeaderIncludes.cpp - Insert/Delete #includes --*- C++ -*----------===//
-//
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-
-#include "clang/Tooling/Core/HeaderIncludes.h"
-#include "clang/Basic/SourceManager.h"
-#include "clang/Lex/Lexer.h"
-
-namespace clang {
-namespace tooling {
-namespace {
-
-LangOptions createLangOpts() {
-  LangOptions LangOpts;
-  LangOpts.CPlusPlus = 1;
-  LangOpts.CPlusPlus11 = 1;
-  LangOpts.CPlusPlus14 = 1;
-  LangOpts.LineComment = 1;
-  LangOpts.CXXOperatorNames = 1;
-  LangOpts.Bool = 1;
-  LangOpts.ObjC1 = 1;
-  LangOpts.ObjC2 = 1;
-  LangOpts.MicrosoftExt = 1;    // To get kw___try, kw___finally.
-  LangOpts.DeclSpecKeyword = 1; // To get __declspec.
-  LangOpts.WChar = 1;           // To get wchar_t
-  return LangOpts;
-}
-
-// Returns the offset after skipping a sequence of tokens, matched by \p
-// GetOffsetAfterSequence, from the start of the code.
-// \p GetOffsetAfterSequence should be a function that matches a sequence of
-// tokens and returns an offset after the sequence.
-unsigned getOffsetAfterTokenSequence(
-    StringRef FileName, StringRef Code, const IncludeStyle &Style,
-    llvm::function_ref<unsigned(const SourceManager &, Lexer &, Token &)>
-        GetOffsetAfterSequence) {
-  SourceManagerForFile VirtualSM(FileName, Code);
-  SourceManager &SM = VirtualSM.get();
-  Lexer Lex(SM.getMainFileID(), SM.getBuffer(SM.getMainFileID()), SM,
-            createLangOpts());
-  Token Tok;
-  // Get the first token.
-  Lex.LexFromRawLexer(Tok);
-  return GetOffsetAfterSequence(SM, Lex, Tok);
-}
-
-// Check if a sequence of tokens is like "#<Name> <raw_identifier>". If it is,
-// \p Tok will be the token after this directive; otherwise, it can be any token
-// after the given \p Tok (including \p Tok).
-bool checkAndConsumeDirectiveWithName(Lexer &Lex, StringRef Name, Token &Tok) {
-  bool Matched = Tok.is(tok::hash) && !Lex.LexFromRawLexer(Tok) &&
-                 Tok.is(tok::raw_identifier) &&
-                 Tok.getRawIdentifier() == Name && !Lex.LexFromRawLexer(Tok) &&
-                 Tok.is(tok::raw_identifier);
-  if (Matched)
-    Lex.LexFromRawLexer(Tok);
-  return Matched;
-}
-
-void skipComments(Lexer &Lex, Token &Tok) {
-  while (Tok.is(tok::comment))
-    if (Lex.LexFromRawLexer(Tok))
-      return;
-}
-
-// Returns the offset after header guard directives and any comments
-// before/after header guards. If no header guard presents in the code, this
-// will returns the offset after skipping all comments from the start of the
-// code.
-unsigned getOffsetAfterHeaderGuardsAndComments(StringRef FileName,
-                                               StringRef Code,
-                                               const IncludeStyle &Style) {
-  return getOffsetAfterTokenSequence(
-      FileName, Code, Style,
-      [](const SourceManager &SM, Lexer &Lex, Token Tok) {
-        skipComments(Lex, Tok);
-        unsigned InitialOffset = SM.getFileOffset(Tok.getLocation());
-        if (checkAndConsumeDirectiveWithName(Lex, "ifndef", Tok)) {
-          skipComments(Lex, Tok);
-          if (checkAndConsumeDirectiveWithName(Lex, "define", Tok))
-            return SM.getFileOffset(Tok.getLocation());
-        }
-        return InitialOffset;
-      });
-}
-
-// Check if a sequence of tokens is like
-//    "#include ("header.h" | <header.h>)".
-// If it is, \p Tok will be the token after this directive; otherwise, it can be
-// any token after the given \p Tok (including \p Tok).
-bool checkAndConsumeInclusiveDirective(Lexer &Lex, Token &Tok) {
-  auto Matched = [&]() {
-    Lex.LexFromRawLexer(Tok);
-    return true;
-  };
-  if (Tok.is(tok::hash) && !Lex.LexFromRawLexer(Tok) &&
-      Tok.is(tok::raw_identifier) && Tok.getRawIdentifier() == "include") {
-    if (Lex.LexFromRawLexer(Tok))
-      return false;
-    if (Tok.is(tok::string_literal))
-      return Matched();
-    if (Tok.is(tok::less)) {
-      while (!Lex.LexFromRawLexer(Tok) && Tok.isNot(tok::greater)) {
-      }
-      if (Tok.is(tok::greater))
-        return Matched();
-    }
-  }
-  return false;
-}
-
-// Returns the offset of the last #include directive after which a new
-// #include can be inserted. This ignores #include's after the #include block(s)
-// in the beginning of a file to avoid inserting headers into code sections
-// where new #include's should not be added by default.
-// These code sections include:
-//      - raw string literals (containing #include).
-//      - #if blocks.
-//      - Special #include's among declarations (e.g. functions).
-//
-// If no #include after which a new #include can be inserted, this returns the
-// offset after skipping all comments from the start of the code.
-// Inserting after an #include is not allowed if it comes after code that is not
-// #include (e.g. pre-processing directive that is not #include, declarations).
-unsigned getMaxHeaderInsertionOffset(StringRef FileName, StringRef Code,
-                                     const IncludeStyle &Style) {
-  return getOffsetAfterTokenSequence(
-      FileName, Code, Style,
-      [](const SourceManager &SM, Lexer &Lex, Token Tok) {
-        skipComments(Lex, Tok);
-        unsigned MaxOffset = SM.getFileOffset(Tok.getLocation());
-        while (checkAndConsumeInclusiveDirective(Lex, Tok))
-          MaxOffset = SM.getFileOffset(Tok.getLocation());
-        return MaxOffset;
-      });
-}
-
-inline StringRef trimInclude(StringRef IncludeName) {
-  return IncludeName.trim("\"<>");
-}
-
-const char IncludeRegexPattern[] =
-    R"(^[\t\ ]*#[\t\ ]*(import|include)[^"<]*(["<][^">]*[">]))";
-
-} // anonymous namespace
-
-IncludeCategoryManager::IncludeCategoryManager(const IncludeStyle &Style,
-                                               StringRef FileName)
-    : Style(Style), FileName(FileName) {
-  FileStem = llvm::sys::path::stem(FileName);
-  for (const auto &Category : Style.IncludeCategories)
-    CategoryRegexs.emplace_back(Category.Regex, llvm::Regex::IgnoreCase);
-  IsMainFile = FileName.endswith(".c") || FileName.endswith(".cc") ||
-               FileName.endswith(".cpp") || FileName.endswith(".c++") ||
-               FileName.endswith(".cxx") || FileName.endswith(".m") ||
-               FileName.endswith(".mm");
-}
-
-int IncludeCategoryManager::getIncludePriority(StringRef IncludeName,
-                                               bool CheckMainHeader) const {
-  int Ret = INT_MAX;
-  for (unsigned i = 0, e = CategoryRegexs.size(); i != e; ++i)
-    if (CategoryRegexs[i].match(IncludeName)) {
-      Ret = Style.IncludeCategories[i].Priority;
-      break;
-    }
-  if (CheckMainHeader && IsMainFile && Ret > 0 && isMainHeader(IncludeName))
-    Ret = 0;
-  return Ret;
-}
-
-bool IncludeCategoryManager::isMainHeader(StringRef IncludeName) const {
-  if (!IncludeName.startswith("\""))
-    return false;
-  StringRef HeaderStem =
-      llvm::sys::path::stem(IncludeName.drop_front(1).drop_back(1));
-  if (FileStem.startswith(HeaderStem) ||
-      FileStem.startswith_lower(HeaderStem)) {
-    llvm::Regex MainIncludeRegex((HeaderStem + Style.IncludeIsMainRegex).str(),
-                                 llvm::Regex::IgnoreCase);
-    if (MainIncludeRegex.match(FileStem))
-      return true;
-  }
-  return false;
-}
-
-HeaderIncludes::HeaderIncludes(StringRef FileName, StringRef Code,
-                               const IncludeStyle &Style)
-    : FileName(FileName), Code(Code), FirstIncludeOffset(-1),
-      MinInsertOffset(
-          getOffsetAfterHeaderGuardsAndComments(FileName, Code, Style)),
-      MaxInsertOffset(MinInsertOffset +
-                      getMaxHeaderInsertionOffset(
-                          FileName, Code.drop_front(MinInsertOffset), Style)),
-      Categories(Style, FileName),
-      IncludeRegex(llvm::Regex(IncludeRegexPattern)) {
-  // Add 0 for main header and INT_MAX for headers that are not in any
-  // category.
-  Priorities = {0, INT_MAX};
-  for (const auto &Category : Style.IncludeCategories)
-    Priorities.insert(Category.Priority);
-  SmallVector<StringRef, 32> Lines;
-  Code.drop_front(MinInsertOffset).split(Lines, "\n");
-
-  unsigned Offset = MinInsertOffset;
-  unsigned NextLineOffset;
-  SmallVector<StringRef, 4> Matches;
-  for (auto Line : Lines) {
-    NextLineOffset = std::min(Code.size(), Offset + Line.size() + 1);
-    if (IncludeRegex.match(Line, &Matches)) {
-      // If this is the last line without trailing newline, we need to make
-      // sure we don't delete across the file boundary.
-      addExistingInclude(
-          Include(Matches[2],
-                  tooling::Range(
-                      Offset, std::min(Line.size() + 1, Code.size() - Offset))),
-          NextLineOffset);
-    }
-    Offset = NextLineOffset;
-  }
-
-  // Populate CategoryEndOfssets:
-  // - Ensure that CategoryEndOffset[Highest] is always populated.
-  // - If CategoryEndOffset[Priority] isn't set, use the next higher value
-  // that is set, up to CategoryEndOffset[Highest].
-  auto Highest = Priorities.begin();
-  if (CategoryEndOffsets.find(*Highest) == CategoryEndOffsets.end()) {
-    if (FirstIncludeOffset >= 0)
-      CategoryEndOffsets[*Highest] = FirstIncludeOffset;
-    else
-      CategoryEndOffsets[*Highest] = MinInsertOffset;
-  }
-  // By this point, CategoryEndOffset[Highest] is always set appropriately:
-  //  - to an appropriate location before/after existing #includes, or
-  //  - to right after the header guard, or
-  //  - to the beginning of the file.
-  for (auto I = ++Priorities.begin(), E = Priorities.end(); I != E; ++I)
-    if (CategoryEndOffsets.find(*I) == CategoryEndOffsets.end())
-      CategoryEndOffsets[*I] = CategoryEndOffsets[*std::prev(I)];
-}
-
-// \p Offset: the start of the line following this include directive.
-void HeaderIncludes::addExistingInclude(Include IncludeToAdd,
-                                        unsigned NextLineOffset) {
-  auto Iter =
-      ExistingIncludes.try_emplace(trimInclude(IncludeToAdd.Name)).first;
-  Iter->second.push_back(std::move(IncludeToAdd));
-  auto &CurInclude = Iter->second.back();
-  // The header name with quotes or angle brackets.
-  // Only record the offset of current #include if we can insert after it.
-  if (CurInclude.R.getOffset() <= MaxInsertOffset) {
-    int Priority = Categories.getIncludePriority(
-        CurInclude.Name, /*CheckMainHeader=*/FirstIncludeOffset < 0);
-    CategoryEndOffsets[Priority] = NextLineOffset;
-    IncludesByPriority[Priority].push_back(&CurInclude);
-    if (FirstIncludeOffset < 0)
-      FirstIncludeOffset = CurInclude.R.getOffset();
-  }
-}
-
-llvm::Optional<tooling::Replacement>
-HeaderIncludes::insert(llvm::StringRef IncludeName, bool IsAngled) const {
-  assert(IncludeName == trimInclude(IncludeName));
-  // If a <header> ("header") already exists in code, "header" (<header>) with
-  // different quotation will still be inserted.
-  // FIXME: figure out if this is the best behavior.
-  auto It = ExistingIncludes.find(IncludeName);
-  if (It != ExistingIncludes.end())
-    for (const auto &Inc : It->second)
-      if ((IsAngled && StringRef(Inc.Name).startswith("<")) ||
-          (!IsAngled && StringRef(Inc.Name).startswith("\"")))
-        return llvm::None;
-  std::string Quoted = IsAngled ? ("<" + IncludeName + ">").str()
-                                : ("\"" + IncludeName + "\"").str();
-  StringRef QuotedName = Quoted;
-  int Priority = Categories.getIncludePriority(
-      QuotedName, /*CheckMainHeader=*/FirstIncludeOffset < 0);
-  auto CatOffset = CategoryEndOffsets.find(Priority);
-  assert(CatOffset != CategoryEndOffsets.end());
-  unsigned InsertOffset = CatOffset->second; // Fall back offset
-  auto Iter = IncludesByPriority.find(Priority);
-  if (Iter != IncludesByPriority.end()) {
-    for (const auto *Inc : Iter->second) {
-      if (QuotedName < Inc->Name) {
-        InsertOffset = Inc->R.getOffset();
-        break;
-      }
-    }
-  }
-  assert(InsertOffset <= Code.size());
-  std::string NewInclude = ("#include " + QuotedName + "\n").str();
-  // When inserting headers at end of the code, also append '\n' to the code
-  // if it does not end with '\n'.
-  // FIXME: when inserting multiple #includes at the end of code, only one
-  // newline should be added.
-  if (InsertOffset == Code.size() && (!Code.empty() && Code.back() != '\n'))
-    NewInclude = "\n" + NewInclude;
-  return tooling::Replacement(FileName, InsertOffset, 0, NewInclude);
-}
-
-tooling::Replacements HeaderIncludes::remove(llvm::StringRef IncludeName,
-                                             bool IsAngled) const {
-  assert(IncludeName == trimInclude(IncludeName));
-  tooling::Replacements Result;
-  auto Iter = ExistingIncludes.find(IncludeName);
-  if (Iter == ExistingIncludes.end())
-    return Result;
-  for (const auto &Inc : Iter->second) {
-    if ((IsAngled && StringRef(Inc.Name).startswith("\"")) ||
-        (!IsAngled && StringRef(Inc.Name).startswith("<")))
-      continue;
-    llvm::Error Err = Result.add(tooling::Replacement(
-        FileName, Inc.R.getOffset(), Inc.R.getLength(), ""));
-    if (Err) {
-      auto ErrMsg = "Unexpected conflicts in #include deletions: " +
-                    llvm::toString(std::move(Err));
-      llvm_unreachable(ErrMsg.c_str());
-    }
-  }
-  return Result;
-}
-
-
-} // namespace tooling
-} // namespace clang
Index: cfe/trunk/lib/Tooling/Core/IncludeStyle.cpp
===================================================================
--- cfe/trunk/lib/Tooling/Core/IncludeStyle.cpp
+++ cfe/trunk/lib/Tooling/Core/IncludeStyle.cpp
@@ -1,32 +0,0 @@
-//===--- IncludeStyle.cpp - Style of C++ #include directives -----*- C++-*-===//
-//
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-
-#include "clang/Tooling/Core/IncludeStyle.h"
-
-
-using clang::tooling::IncludeStyle;
-
-namespace llvm {
-namespace yaml {
-
-void MappingTraits<IncludeStyle::IncludeCategory>::mapping(
-    IO &IO, IncludeStyle::IncludeCategory &Category) {
-  IO.mapOptional("Regex", Category.Regex);
-  IO.mapOptional("Priority", Category.Priority);
-}
-
-void ScalarEnumerationTraits<IncludeStyle::IncludeBlocksStyle>::enumeration(
-    IO &IO, IncludeStyle::IncludeBlocksStyle &Value) {
-  IO.enumCase(Value, "Preserve", IncludeStyle::IBS_Preserve);
-  IO.enumCase(Value, "Merge", IncludeStyle::IBS_Merge);
-  IO.enumCase(Value, "Regroup", IncludeStyle::IBS_Regroup);
-}
-
-} // namespace yaml
-} // namespace llvm
Index: cfe/trunk/include/clang/Tooling/Core/HeaderIncludes.h
===================================================================
--- cfe/trunk/include/clang/Tooling/Core/HeaderIncludes.h
+++ cfe/trunk/include/clang/Tooling/Core/HeaderIncludes.h
@@ -1,137 +0,0 @@
-//===--- HeaderIncludes.h - Insert/Delete #includes for C++ code--*- C++-*-===//
-//
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-
-#ifndef LLVM_CLANG_TOOLING_CORE_HEADERINCLUDES_H
-#define LLVM_CLANG_TOOLING_CORE_HEADERINCLUDES_H
-
-#include "clang/Basic/SourceManager.h"
-#include "clang/Tooling/Core/Replacement.h"
-#include "clang/Tooling/Core/IncludeStyle.h"
-#include "llvm/Support/Path.h"
-#include "llvm/Support/Regex.h"
-#include <unordered_map>
-
-namespace clang {
-namespace tooling {
-
-/// This class manages priorities of C++ #include categories and calculates
-/// priorities for headers.
-/// FIXME(ioeric): move this class into implementation file when clang-format's
-/// include sorting functions are also moved here.
-class IncludeCategoryManager {
-public:
-  IncludeCategoryManager(const IncludeStyle &Style, StringRef FileName);
-
-  /// Returns the priority of the category which \p IncludeName belongs to.
-  /// If \p CheckMainHeader is true and \p IncludeName is a main header, returns
-  /// 0. Otherwise, returns the priority of the matching category or INT_MAX.
-  /// NOTE: this API is not thread-safe!
-  int getIncludePriority(StringRef IncludeName, bool CheckMainHeader) const;
-
-private:
-  bool isMainHeader(StringRef IncludeName) const;
-
-  const IncludeStyle Style;
-  bool IsMainFile;
-  std::string FileName;
-  // This refers to a substring in FileName.
-  StringRef FileStem;
-  // Regex is not thread-safe.
-  mutable SmallVector<llvm::Regex, 4> CategoryRegexs;
-};
-
-/// Generates replacements for inserting or deleting #include directives in a
-/// file.
-class HeaderIncludes {
-public:
-  HeaderIncludes(llvm::StringRef FileName, llvm::StringRef Code,
-                 const IncludeStyle &Style);
-
-  /// Inserts an #include directive of \p Header into the code. If \p IsAngled
-  /// is true, \p Header will be quoted with <> in the directive; otherwise, it
-  /// will be quoted with "".
-  ///
-  /// When searching for points to insert new header, this ignores #include's
-  /// after the #include block(s) in the beginning of a file to avoid inserting
-  /// headers into code sections where new #include's should not be added by
-  /// default. These code sections include:
-  ///   - raw string literals (containing #include).
-  ///   - #if blocks.
-  ///   - Special #include's among declarations (e.g. functions).
-  ///
-  /// Returns a replacement that inserts the new header into a suitable #include
-  /// block of the same category. This respects the order of the existing
-  /// #includes in the block; if the existing #includes are not already sorted,
-  /// this will simply insert the #include in front of the first #include of the
-  /// same category in the code that should be sorted after \p IncludeName. If
-  /// \p IncludeName already exists (with exactly the same spelling), this
-  /// returns None.
-  llvm::Optional<tooling::Replacement> insert(llvm::StringRef Header,
-                                              bool IsAngled) const;
-
-  /// Removes all existing #includes of \p Header quoted with <> if \p IsAngled
-  /// is true or "" if \p IsAngled is false.
-  /// This doesn't resolve the header file path; it only deletes #includes with
-  /// exactly the same spelling.
-  tooling::Replacements remove(llvm::StringRef Header, bool IsAngled) const;
-
-private:
-  struct Include {
-    Include(StringRef Name, tooling::Range R) : Name(Name), R(R) {}
-
-    // An include header quoted with either <> or "".
-    std::string Name;
-    // The range of the whole line of include directive including any eading
-    // whitespaces and trailing comment.
-    tooling::Range R;
-  };
-
-  void addExistingInclude(Include IncludeToAdd, unsigned NextLineOffset);
-
-  std::string FileName;
-  std::string Code;
-
-  // Map from include name (quotation trimmed) to a list of existing includes
-  // (in case there are more than one) with the name in the current file. <x>
-  // and "x" will be treated as the same header when deleting #includes.
-  llvm::StringMap<llvm::SmallVector<Include, 1>> ExistingIncludes;
-
-  /// Map from priorities of #include categories to all #includes in the same
-  /// category. This is used to find #includes of the same category when
-  /// inserting new #includes. #includes in the same categories are sorted in
-  /// in the order they appear in the source file.
-  /// See comment for "FormatStyle::IncludeCategories" for details about include
-  /// priorities.
-  std::unordered_map<int, llvm::SmallVector<const Include *, 8>>
-      IncludesByPriority;
-
-  int FirstIncludeOffset;
-  // All new headers should be inserted after this offset (e.g. after header
-  // guards, file comment).
-  unsigned MinInsertOffset;
-  // Max insertion offset in the original code. For example, we want to avoid
-  // inserting new #includes into the actual code section (e.g. after a
-  // declaration).
-  unsigned MaxInsertOffset;
-  IncludeCategoryManager Categories;
-  // Record the offset of the end of the last include in each category.
-  std::unordered_map<int, int> CategoryEndOffsets;
-
-  // All possible priorities.
-  std::set<int> Priorities;
-
-  // Matches a whole #include directive.
-  llvm::Regex IncludeRegex;
-};
-
-
-} // namespace tooling
-} // namespace clang
-
-#endif // LLVM_CLANG_TOOLING_CORE_HEADERINCLUDES_H
Index: cfe/trunk/include/clang/Tooling/Core/IncludeStyle.h
===================================================================
--- cfe/trunk/include/clang/Tooling/Core/IncludeStyle.h
+++ cfe/trunk/include/clang/Tooling/Core/IncludeStyle.h
@@ -1,133 +0,0 @@
-//===--- IncludeStyle.h - Style of C++ #include directives -------*- C++-*-===//
-//
-//                     The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-
-#ifndef LLVM_CLANG_TOOLING_CORE_INCLUDESTYLE_H
-#define LLVM_CLANG_TOOLING_CORE_INCLUDESTYLE_H
-
-#include "llvm/Support/YAMLTraits.h"
-#include <string>
-#include <vector>
-
-namespace clang {
-namespace tooling {
-
-/// Style for sorting and grouping C++ #include directives.
-struct IncludeStyle {
-  /// Styles for sorting multiple ``#include`` blocks.
-  enum IncludeBlocksStyle {
-    /// Sort each ``#include`` block separately.
-    /// \code
-    ///    #include "b.h"               into      #include "b.h"
-    ///
-    ///    #include <lib/main.h>                  #include "a.h"
-    ///    #include "a.h"                         #include <lib/main.h>
-    /// \endcode
-    IBS_Preserve,
-    /// Merge multiple ``#include`` blocks together and sort as one.
-    /// \code
-    ///    #include "b.h"               into      #include "a.h"
-    ///                                           #include "b.h"
-    ///    #include <lib/main.h>                  #include <lib/main.h>
-    ///    #include "a.h"
-    /// \endcode
-    IBS_Merge,
-    /// Merge multiple ``#include`` blocks together and sort as one.
-    /// Then split into groups based on category priority. See
-    /// ``IncludeCategories``.
-    /// \code
-    ///    #include "b.h"               into      #include "a.h"
-    ///                                           #include "b.h"
-    ///    #include <lib/main.h>
-    ///    #include "a.h"                         #include <lib/main.h>
-    /// \endcode
-    IBS_Regroup,
-  };
-
-  /// Dependent on the value, multiple ``#include`` blocks can be sorted
-  /// as one and divided based on category.
-  IncludeBlocksStyle IncludeBlocks;
-
-  /// See documentation of ``IncludeCategories``.
-  struct IncludeCategory {
-    /// The regular expression that this category matches.
-    std::string Regex;
-    /// The priority to assign to this category.
-    int Priority;
-    bool operator==(const IncludeCategory &Other) const {
-      return Regex == Other.Regex && Priority == Other.Priority;
-    }
-  };
-
-  /// Regular expressions denoting the different ``#include`` categories
-  /// used for ordering ``#includes``.
-  ///
-  /// These regular expressions are matched against the filename of an include
-  /// (including the <> or "") in order. The value belonging to the first
-  /// matching regular expression is assigned and ``#includes`` are sorted first
-  /// according to increasing category number and then alphabetically within
-  /// each category.
-  ///
-  /// If none of the regular expressions match, INT_MAX is assigned as
-  /// category. The main header for a source file automatically gets category 0.
-  /// so that it is generally kept at the beginning of the ``#includes``
-  /// (http://llvm.org/docs/CodingStandards.html#include-style). However, you
-  /// can also assign negative priorities if you have certain headers that
-  /// always need to be first.
-  ///
-  /// To configure this in the .clang-format file, use:
-  /// \code{.yaml}
-  ///   IncludeCategories:
-  ///     - Regex:           '^"(llvm|llvm-c|clang|clang-c)/'
-  ///       Priority:        2
-  ///     - Regex:           '^(<|"(gtest|gmock|isl|json)/)'
-  ///       Priority:        3
-  ///     - Regex:           '.*'
-  ///       Priority:        1
-  /// \endcode
-  std::vector<IncludeCategory> IncludeCategories;
-
-  /// Specify a regular expression of suffixes that are allowed in the
-  /// file-to-main-include mapping.
-  ///
-  /// When guessing whether a #include is the "main" include (to assign
-  /// category 0, see above), use this regex of allowed suffixes to the header
-  /// stem. A partial match is done, so that:
-  /// - "" means "arbitrary suffix"
-  /// - "$" means "no suffix"
-  ///
-  /// For example, if configured to "(_test)?$", then a header a.h would be seen
-  /// as the "main" include in both a.cc and a_test.cc.
-  std::string IncludeIsMainRegex;
-};
-
-} // namespace tooling
-} // namespace clang
-
-LLVM_YAML_IS_SEQUENCE_VECTOR(clang::tooling::IncludeStyle::IncludeCategory)
-
-namespace llvm {
-namespace yaml {
-
-template <>
-struct MappingTraits<clang::tooling::IncludeStyle::IncludeCategory> {
-  static void mapping(IO &IO,
-                      clang::tooling::IncludeStyle::IncludeCategory &Category);
-};
-
-template <>
-struct ScalarEnumerationTraits<
-    clang::tooling::IncludeStyle::IncludeBlocksStyle> {
-  static void
-  enumeration(IO &IO, clang::tooling::IncludeStyle::IncludeBlocksStyle &Value);
-};
-
-} // namespace yaml
-} // namespace llvm
-
-#endif // LLVM_CLANG_TOOLING_CORE_INCLUDESTYLE_H
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Reply via email to