llvm/clang/lib/Format/Encoding.h

//===--- Encoding.h - Format C++ code ---------------------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
///
/// \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/Support/ConvertUTF.h"
#include "llvm/Support/Unicode.h"

namespace clang {
namespace format {
namespace encoding {

enum Encoding { … };

/// 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) { … }

/// 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) { … }

/// 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) { … }

/// 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) { … }

inline bool isOctDigit(char c) { … }

inline bool isHexDigit(char c) { … }

/// 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) { … }

} // namespace encoding
} // namespace format
} // namespace clang

#endif