Support for CR LF newlines.

Summary:
reformat() tries to determine the newline style used in the input
(either LF or CR LF), and uses it for the output. Maybe not every single case is
supported, but at least the bug described in http://llvm.org/PR17182 should be
resolved.

Reviewers: djasper

Reviewed By: djasper

CC: cfe-commits, klimek

Differential Revision: http://llvm-reviews.chandlerc.com/D1643

llvm-svn: 190519

3 files changed, 42 insertions, 35 deletions

diff --git a/clang/lib/Format/Format.cpp b/clang/lib/Format/Format.cpp
index 07c6cf974da..52f8b07475d 100644
--- a/clang/lib/Format/Format.cpp
+++ b/clang/lib/Format/Format.cpp
@@ -631,7 +631,9 @@ private:
           ++FormatTok->NewlinesBefore;
           // FIXME: This is technically incorrect, as it could also
           // be a literal backslash at the end of the line.
-          if (i == 0 || FormatTok->TokenText[i - 1] != '\\')
+          if (i == 0 || (FormatTok->TokenText[i - 1] != '\\' &&
+                         (FormatTok->TokenText[i - 1] != '\r' || i == 1 ||
+                          FormatTok->TokenText[i - 2] != '\\')))
             FormatTok->HasUnescapedNewline = true;
           FormatTok->LastNewlineOffset = WhitespaceLength + i + 1;
           Column = 0;
@@ -745,8 +747,8 @@ public:
   Formatter(const FormatStyle &Style, Lexer &Lex, SourceManager &SourceMgr,
             const std::vector<CharSourceRange> &Ranges)
       : Style(Style), Lex(Lex), SourceMgr(SourceMgr),
-        Whitespaces(SourceMgr, Style), Ranges(Ranges),
-        Encoding(encoding::detectEncoding(Lex.getBuffer())) {
+        Whitespaces(SourceMgr, Style, inputUsesCRLF(Lex.getBuffer())),
+        Ranges(Ranges), Encoding(encoding::detectEncoding(Lex.getBuffer())) {
     DEBUG(llvm::dbgs() << "File encoding: "
                        << (Encoding == encoding::Encoding_UTF8 ? "UTF8"
                                                                : "unknown")
@@ -883,6 +885,10 @@ public:
   }
 
 private:
+  static bool inputUsesCRLF(StringRef Text) {
+    return Text.count('\r') * 2 > Text.count('\n');
+  }
+
   void deriveLocalStyle() {
     unsigned CountBoundToVariable = 0;
     unsigned CountBoundToType = 0;
diff --git a/clang/lib/Format/WhitespaceManager.cpp b/clang/lib/Format/WhitespaceManager.cpp
index 0f46e62563a..4138442c0cc 100644
--- a/clang/lib/Format/WhitespaceManager.cpp
+++ b/clang/lib/Format/WhitespaceManager.cpp
@@ -221,14 +221,14 @@ void WhitespaceManager::generateChanges() {
   for (unsigned i = 0, e = Changes.size(); i != e; ++i) {
     const Change &C = Changes[i];
     if (C.CreateReplacement) {
-      std::string ReplacementText =
-          C.PreviousLinePostfix +
-          (C.ContinuesPPDirective
-               ? getNewlineText(C.NewlinesBefore, C.Spaces,
-                                C.PreviousEndOfTokenColumn,
-                                C.EscapedNewlineColumn)
-               : getNewlineText(C.NewlinesBefore, C.Spaces)) +
-          C.CurrentLinePrefix;
+      std::string ReplacementText = C.PreviousLinePostfix;
+      if (C.ContinuesPPDirective)
+        appendNewlineText(ReplacementText, C.NewlinesBefore,
+                          C.PreviousEndOfTokenColumn, C.EscapedNewlineColumn);
+      else
+        appendNewlineText(ReplacementText, C.NewlinesBefore);
+      appendIndentText(ReplacementText, C.Spaces);
+      ReplacementText.append(C.CurrentLinePrefix);
       storeReplacement(C.OriginalWhitespaceRange, ReplacementText);
     }
   }
@@ -246,34 +246,33 @@ void WhitespaceManager::storeReplacement(const SourceRange &Range,
       SourceMgr, CharSourceRange::getCharRange(Range), Text));
 }
 
-std::string WhitespaceManager::getNewlineText(unsigned Newlines,
-                                              unsigned Spaces) {
-  return std::string(Newlines, '\n') + getIndentText(Spaces);
+void WhitespaceManager::appendNewlineText(std::string &Text,
+                                          unsigned Newlines) {
+  for (unsigned i = 0; i < Newlines; ++i)
+    Text.append(UseCRLF ? "\r\n" : "\n");
 }
 
-std::string WhitespaceManager::getNewlineText(unsigned Newlines,
-                                              unsigned Spaces,
-                                              unsigned PreviousEndOfTokenColumn,
-                                              unsigned EscapedNewlineColumn) {
-  std::string NewlineText;
+void WhitespaceManager::appendNewlineText(std::string &Text, unsigned Newlines,
+                                          unsigned PreviousEndOfTokenColumn,
+                                          unsigned EscapedNewlineColumn) {
   if (Newlines > 0) {
     unsigned Offset =
         std::min<int>(EscapedNewlineColumn - 1, PreviousEndOfTokenColumn);
     for (unsigned i = 0; i < Newlines; ++i) {
-      NewlineText += std::string(EscapedNewlineColumn - Offset - 1, ' ');
-      NewlineText += "\\\n";
+      Text.append(std::string(EscapedNewlineColumn - Offset - 1, ' '));
+      Text.append(UseCRLF ? "\\\r\n" : "\\\n");
       Offset = 0;
     }
   }
-  return NewlineText + getIndentText(Spaces);
 }
 
-std::string WhitespaceManager::getIndentText(unsigned Spaces) {
-  if (!Style.UseTab)
-    return std::string(Spaces, ' ');
-
-  return std::string(Spaces / Style.TabWidth, '\t') +
-         std::string(Spaces % Style.TabWidth, ' ');
+void WhitespaceManager::appendIndentText(std::string &Text, unsigned Spaces) {
+  if (!Style.UseTab) {
+    Text.append(std::string(Spaces, ' '));
+  } else {
+    Text.append(std::string(Spaces / Style.TabWidth, '\t'));
+    Text.append(std::string(Spaces % Style.TabWidth, ' '));
+  }
 }
 
 } // namespace format
diff --git a/clang/lib/Format/WhitespaceManager.h b/clang/lib/Format/WhitespaceManager.h
index 9ca34806374..2c58216d1cd 100644
--- a/clang/lib/Format/WhitespaceManager.h
+++ b/clang/lib/Format/WhitespaceManager.h
@@ -37,8 +37,9 @@ namespace format {
 /// There may be multiple calls to \c breakToken for a given token.
 class WhitespaceManager {
 public:
-  WhitespaceManager(SourceManager &SourceMgr, const FormatStyle &Style)
-      : SourceMgr(SourceMgr), Style(Style) {}
+  WhitespaceManager(SourceManager &SourceMgr, const FormatStyle &Style,
+                    bool UseCRLF)
+      : SourceMgr(SourceMgr), Style(Style), UseCRLF(UseCRLF) {}
 
   /// \brief Replaces the whitespace in front of \p Tok. Only call once for
   /// each \c AnnotatedToken.
@@ -152,16 +153,17 @@ private:
 
   /// \brief Stores \p Text as the replacement for the whitespace in \p Range.
   void storeReplacement(const SourceRange &Range, StringRef Text);
-  std::string getNewlineText(unsigned Newlines, unsigned Spaces);
-  std::string getNewlineText(unsigned Newlines, unsigned Spaces,
-                             unsigned PreviousEndOfTokenColumn,
-                             unsigned EscapedNewlineColumn);
-  std::string getIndentText(unsigned Spaces);
+  void appendNewlineText(std::string &Text, unsigned Newlines);
+  void appendNewlineText(std::string &Text, unsigned Newlines,
+                         unsigned PreviousEndOfTokenColumn,
+                         unsigned EscapedNewlineColumn);
+  void appendIndentText(std::string &Text, unsigned Spaces);
 
   SmallVector<Change, 16> Changes;
   SourceManager &SourceMgr;
   tooling::Replacements Replaces;
   const FormatStyle &Style;
+  bool UseCRLF;
 };
 
 } // namespace format