clang-format: Don't remove 'unknown' tokens.
In certain macros or incorrect string literals, the token stream can
contain 'unknown' tokens, e.g. a single backslash or a set of empty
ticks. clang-format simply treated them as whitespace and removed them
prior to this patch.
This fixes llvm.org/PR17215
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@192490 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/Format/Format.cpp b/lib/Format/Format.cpp
index 129c119..7fc6616 100644
--- a/lib/Format/Format.cpp
+++ b/lib/Format/Format.cpp
@@ -691,18 +691,32 @@
FormatTok->LastNewlineOffset = WhitespaceLength + i + 1;
Column = 0;
break;
+ case '\r':
+ case '\f':
+ case '\v':
+ Column = 0;
+ break;
case ' ':
++Column;
break;
case '\t':
Column += Style.TabWidth - Column % Style.TabWidth;
break;
+ case '\\':
+ ++Column;
+ if (i + 1 == e || (FormatTok->TokenText[i + 1] != '\r' &&
+ FormatTok->TokenText[i + 1] != '\n'))
+ FormatTok->Type = TT_ImplicitStringLiteral;
+ break;
default:
+ FormatTok->Type = TT_ImplicitStringLiteral;
++Column;
break;
}
}
+ if (FormatTok->Type == TT_ImplicitStringLiteral)
+ break;
WhitespaceLength += FormatTok->Tok.getLength();
readRawToken(*FormatTok);