Major refactoring of BreakableToken.
Unify handling of whitespace when breaking protruding tokens with other
whitespace replacements.
As a side effect, the BreakableToken structure changed significantly:
- have a common base class for single-line breakable tokens, as they are
much more similar
- revamp handling of multi-line comments; we now calculate the
information about lines in multi-line comments similar to normal
tokens, and always issue replacements
As a result, we were able to get rid of special casing of trailing
whitespace deletion for comments in the whitespace manager and the
BreakableToken and fixed bugs related to tab handling and escaped
newlines.
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@182738 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/Format/UnwrappedLineParser.h b/lib/Format/UnwrappedLineParser.h
index c738ef1..3359745 100644
--- a/lib/Format/UnwrappedLineParser.h
+++ b/lib/Format/UnwrappedLineParser.h
@@ -28,9 +28,8 @@
/// whitespace characters preceeding it.
struct FormatToken {
FormatToken()
- : NewlinesBefore(0), HasUnescapedNewline(false),
- LastNewlineOffset(0), TokenLength(0), IsFirst(false),
- MustBreakBefore(false), TrailingWhiteSpaceLength(0) {}
+ : NewlinesBefore(0), HasUnescapedNewline(false), LastNewlineOffset(0),
+ TokenLength(0), IsFirst(false), MustBreakBefore(false) {}
/// \brief The \c Token.
Token Tok;
@@ -66,9 +65,6 @@
/// before the token.
bool MustBreakBefore;
- /// \brief Number of characters of trailing whitespace.
- unsigned TrailingWhiteSpaceLength;
-
/// \brief Returns actual token start location without leading escaped
/// newlines and whitespace.
///
@@ -77,6 +73,12 @@
SourceLocation getStartOfNonWhitespace() const {
return WhitespaceRange.getEnd();
}
+
+ /// \brief The raw text of the token.
+ ///
+ /// Contains the raw token text without leading whitespace and without leading
+ /// escaped newlines.
+ StringRef TokenText;
};
/// \brief An unwrapped line is a sequence of \c Token, that we would like to