Handle zero-width and double-width characters in string literals and comments.

Summary:
Count column width instead of the number of code points. This also
includes correct handling of tabs inside string literals and comments (with an
exception of multiline string literals/comments, where tabs are present before
the first escaped newline).

Reviewers: djasper, klimek

Reviewed By: klimek

CC: cfe-commits, klimek

Differential Revision: http://llvm-reviews.chandlerc.com/D1601

llvm-svn: 190052

1 files changed, 32 insertions, 0 deletions

diff --git a/clang/lib/Format/Encoding.h b/clang/lib/Format/Encoding.h
index e9e9ae71c79..356334d5376 100644
--- a/clang/lib/Format/Encoding.h
+++ b/clang/lib/Format/Encoding.h
@@ -18,6 +18,7 @@
 
 #include "clang/Basic/LLVM.h"
 #include "llvm/Support/ConvertUTF.h"
+#include "llvm/Support/Unicode.h"
 
 namespace clang {
 namespace format {
@@ -57,6 +58,37 @@ inline unsigned getCodePointCount(StringRef Text, Encoding Encoding) {
   }
 }
 
+/// \brief Returns the number of columns required to display the \p Text on a
+/// generic Unicode-capable terminal. Text is assumed to use the specified
+/// \p Encoding.
+inline unsigned columnWidth(StringRef Text, Encoding Encoding) {
+  if (Encoding == Encoding_UTF8) {
+    int ContentWidth = llvm::sys::unicode::columnWidthUTF8(Text);
+    if (ContentWidth >= 0)
+      return ContentWidth;
+  }
+  return Text.size();
+}
+
+/// \brief Returns the number of columns required to display the \p Text,
+/// starting from the \p StartColumn on a terminal with the \p TabWidth. The
+/// text is assumed to use the specified \p Encoding.
+inline unsigned columnWidthWithTabs(StringRef Text, unsigned StartColumn,
+                                    unsigned TabWidth, Encoding Encoding) {
+  unsigned TotalWidth = 0;
+  StringRef Tail = Text;
+  for (;;) {
+    StringRef::size_type TabPos = Tail.find('\t');
+    if (TabPos == StringRef::npos)
+      return TotalWidth + columnWidth(Tail, Encoding);
+    int Width = columnWidth(Tail.substr(0, TabPos), Encoding);
+    assert(Width >= 0);
+    TotalWidth += Width;
+    TotalWidth += TabWidth - (TotalWidth + StartColumn) % TabWidth;
+    Tail = Tail.substr(TabPos + 1);
+  }
+}
+
 /// \brief Gets the number of bytes in a sequence representing a single
 /// codepoint and starting with FirstChar in the specified Encoding.
 inline unsigned getCodePointNumBytes(char FirstChar, Encoding Encoding) {