[PATCH] Support for CR LF newlines.

[Alexander Kornienko]

Hi djasper,

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.

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

Files:
  lib/Format/Format.cpp
  lib/Format/WhitespaceManager.cpp
  lib/Format/WhitespaceManager.h
  unittests/Format/FormatTest.cpp

Index: lib/Format/Format.cpp
===================================================================
--- lib/Format/Format.cpp
+++ lib/Format/Format.cpp
@@ -631,7 +631,9 @@
           ++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 +747,9 @@
   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, Lex.getBuffer().count('\r') * 2 >
+                                          Lex.getBuffer().count('\n')),
+        Ranges(Ranges), Encoding(encoding::detectEncoding(Lex.getBuffer())) {
     DEBUG(llvm::dbgs() << "File encoding: "
                        << (Encoding == encoding::Encoding_UTF8 ? "UTF8"
                                                                : "unknown")
Index: lib/Format/WhitespaceManager.cpp
===================================================================
--- lib/Format/WhitespaceManager.cpp
+++ lib/Format/WhitespaceManager.cpp
@@ -221,14 +221,14 @@
   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 @@
       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
Index: lib/Format/WhitespaceManager.h
===================================================================
--- lib/Format/WhitespaceManager.h
+++ lib/Format/WhitespaceManager.h
@@ -37,8 +37,9 @@
 /// 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 @@
 
   /// \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
Index: unittests/Format/FormatTest.cpp
===================================================================
--- unittests/Format/FormatTest.cpp
+++ unittests/Format/FormatTest.cpp
@@ -116,7 +116,7 @@
 
 TEST_F(FormatTest, FormatsGlobalStatementsAt0) {
   EXPECT_EQ("int i;", format("  int i;"));
-  EXPECT_EQ("\nint i;", format(" \n\t \r  int i;"));
+  EXPECT_EQ("\nint i;", format(" \n\t \v \f  int i;"));
   EXPECT_EQ("int i;\nint j;", format("    int i; int j;"));
   EXPECT_EQ("int i;\nint j;", format("    int i;\n  int j;"));
 }
-------------- next part --------------
A non-text attachment was scrubbed...
Name: D1643.1.patch
Type: text/x-patch
Size: 6998 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/cfe-commits/attachments/20130910/0da41cb1/attachment.bin>