Change the data structure used in clang-format.

This is a first step towards supporting more complex structures such
as #ifs inside unwrapped lines. This patch mostly converts the array-based
UnwrappedLine into a linked-list-based UnwrappedLine. Future changes will
allow multiple children for each Token turning the UnwrappedLine into a
tree.

No functional changes intended.

llvm-svn: 171856

clang/lib/Format/UnwrappedLineParser.cpp

@@ -74,7 +74,8 @@ private:
 UnwrappedLineParser::UnwrappedLineParser(const FormatStyle &Style,
                                          FormatTokenSource &Tokens,
                                          UnwrappedLineConsumer &Callback)
-    : Style(Style), Tokens(&Tokens), Callback(Callback) {
+    : RootTokenInitialized(false), Style(Style), Tokens(&Tokens),
+      Callback(Callback) {
 }
 
 bool UnwrappedLineParser::parse() {
@@ -493,13 +494,15 @@ void UnwrappedLineParser::parseStructOrClass() {
 }
 
 void UnwrappedLineParser::addUnwrappedLine() {
+  if (!RootTokenInitialized)
+    return;
   // Consume trailing comments.
   while (!eof() && FormatTok.NewlinesBefore == 0 &&
          FormatTok.Tok.is(tok::comment)) {
     nextToken();
   }
   Callback.consumeUnwrappedLine(Line);
-  Line.Tokens.clear();
+  RootTokenInitialized = false;
 }
 
 bool UnwrappedLineParser::eof() const {
@@ -509,7 +512,14 @@ bool UnwrappedLineParser::eof() const {
 void UnwrappedLineParser::nextToken() {
   if (eof())
     return;
-  Line.Tokens.push_back(FormatTok);
+  if (RootTokenInitialized) {
+    LastInCurrentLine->Children.push_back(FormatTok);
+    LastInCurrentLine = &LastInCurrentLine->Children.back();
+  } else {
+    Line.RootToken = FormatTok;
+    RootTokenInitialized = true;
+    LastInCurrentLine = &Line.RootToken;
+  }
   readToken();
 }
 

clang/lib/Format/UnwrappedLineParser.h

@@ -24,6 +24,8 @@
 #include "clang/Format/Format.h"
 #include "clang/Lex/Lexer.h"
 
+#include <vector>
+
 namespace clang {
 namespace format {
 
@@ -65,6 +67,11 @@ struct FormatToken {
 
   /// \brief Indicates that this is the first token.
   bool IsFirst;
+
+  // FIXME: We currently assume that there is exactly one token in this vector
+  // except for the very last token that does not have any children.
+  /// \brief All tokens that logically follow this token.
+  std::vector<FormatToken> Children;
 };
 
 /// \brief An unwrapped line is a sequence of \c Token, that we would like to
@@ -78,7 +85,7 @@ struct UnwrappedLine {
   }
 
   /// \brief The \c Token comprising this \c UnwrappedLine.
-  SmallVector<FormatToken, 16> Tokens;
+  FormatToken RootToken;
 
   /// \brief The indent level of the \c UnwrappedLine.
   unsigned Level;
@@ -138,6 +145,8 @@ private:
   // subtracted from beyond 0. Introduce a method to subtract from Line.Level
   // and use that everywhere in the Parser.
   UnwrappedLine Line;
+  bool RootTokenInitialized;
+  FormatToken *LastInCurrentLine;
   FormatToken FormatTok;
 
   const FormatStyle &Style;

clang/unittests/Format/FormatTest.cpp

@@ -537,8 +537,8 @@ TEST_F(FormatTest, LayoutRemainingTokens) {
 }
 
 TEST_F(FormatTest, LayoutSingleUnwrappedLineInMacro) {
-  EXPECT_EQ("#define A \\\n  b;",
-            format("#define A b;", 10, 2, getLLVMStyleWithColumns(11)));
+  EXPECT_EQ("# define A\\\n  b;",
+            format("# define A b;", 11, 2, getLLVMStyleWithColumns(11)));
 }
 
 TEST_F(FormatTest, MacroDefinitionInsideStatement) {