summaryrefslogtreecommitdiffstats
path: root/gnu/llvm/tools/clang/lib/Format/Encoding.h
diff options
context:
space:
mode:
Diffstat (limited to 'gnu/llvm/tools/clang/lib/Format/Encoding.h')
-rw-r--r--gnu/llvm/tools/clang/lib/Format/Encoding.h128
1 files changed, 0 insertions, 128 deletions
diff --git a/gnu/llvm/tools/clang/lib/Format/Encoding.h b/gnu/llvm/tools/clang/lib/Format/Encoding.h
deleted file mode 100644
index 4c877e7e49d..00000000000
--- a/gnu/llvm/tools/clang/lib/Format/Encoding.h
+++ /dev/null
@@ -1,128 +0,0 @@
-//===--- Encoding.h - Format C++ code ---------------------------*- C++ -*-===//
-//
-// The LLVM Compiler Infrastructure
-//
-// This file is distributed under the University of Illinois Open Source
-// License. See LICENSE.TXT for details.
-//
-//===----------------------------------------------------------------------===//
-///
-/// \file
-/// Contains functions for text encoding manipulation. Supports UTF-8,
-/// 8-bit encodings and escape sequences in C++ string literals.
-///
-//===----------------------------------------------------------------------===//
-
-#ifndef LLVM_CLANG_LIB_FORMAT_ENCODING_H
-#define LLVM_CLANG_LIB_FORMAT_ENCODING_H
-
-#include "clang/Basic/LLVM.h"
-#include "llvm/ADT/StringRef.h"
-#include "llvm/Support/ConvertUTF.h"
-#include "llvm/Support/Unicode.h"
-
-namespace clang {
-namespace format {
-namespace encoding {
-
-enum Encoding {
- Encoding_UTF8,
- Encoding_Unknown // We treat all other encodings as 8-bit encodings.
-};
-
-/// Detects encoding of the Text. If the Text can be decoded using UTF-8,
-/// it is considered UTF8, otherwise we treat it as some 8-bit encoding.
-inline Encoding detectEncoding(StringRef Text) {
- const llvm::UTF8 *Ptr = reinterpret_cast<const llvm::UTF8 *>(Text.begin());
- const llvm::UTF8 *BufEnd = reinterpret_cast<const llvm::UTF8 *>(Text.end());
- if (llvm::isLegalUTF8String(&Ptr, BufEnd))
- return Encoding_UTF8;
- return Encoding_Unknown;
-}
-
-/// 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);
- // FIXME: Figure out the correct way to handle this in the presence of both
- // printable and unprintable multi-byte UTF-8 characters. Falling back to
- // returning the number of bytes may cause problems, as columnWidth suddenly
- // becomes non-additive.
- if (ContentWidth >= 0)
- return ContentWidth;
- }
- return Text.size();
-}
-
-/// 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);
- TotalWidth += columnWidth(Tail.substr(0, TabPos), Encoding);
- TotalWidth += TabWidth - (TotalWidth + StartColumn) % TabWidth;
- Tail = Tail.substr(TabPos + 1);
- }
-}
-
-/// 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) {
- switch (Encoding) {
- case Encoding_UTF8:
- return llvm::getNumBytesForUTF8(FirstChar);
- default:
- return 1;
- }
-}
-
-inline bool isOctDigit(char c) { return '0' <= c && c <= '7'; }
-
-inline bool isHexDigit(char c) {
- return ('0' <= c && c <= '9') || ('a' <= c && c <= 'f') ||
- ('A' <= c && c <= 'F');
-}
-
-/// Gets the length of an escape sequence inside a C++ string literal.
-/// Text should span from the beginning of the escape sequence (starting with a
-/// backslash) to the end of the string literal.
-inline unsigned getEscapeSequenceLength(StringRef Text) {
- assert(Text[0] == '\\');
- if (Text.size() < 2)
- return 1;
-
- switch (Text[1]) {
- case 'u':
- return 6;
- case 'U':
- return 10;
- case 'x': {
- unsigned I = 2; // Point after '\x'.
- while (I < Text.size() && isHexDigit(Text[I]))
- ++I;
- return I;
- }
- default:
- if (isOctDigit(Text[1])) {
- unsigned I = 1;
- while (I < Text.size() && I < 4 && isOctDigit(Text[I]))
- ++I;
- return I;
- }
- return 1 + llvm::getNumBytesForUTF8(Text[1]);
- }
-}
-
-} // namespace encoding
-} // namespace format
-} // namespace clang
-
-#endif