llvm/llvm/lib/Support/Unicode.cpp

//===- llvm/Support/Unicode.cpp - Unicode character properties  -*- 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
//
//===----------------------------------------------------------------------===//
//
// This file implements functions that allow querying certain properties of
// Unicode characters.
//
//===----------------------------------------------------------------------===//

#include "llvm/Support/Unicode.h"
#include "llvm/Support/ConvertUTF.h"
#include "llvm/Support/UnicodeCharRanges.h"

namespace llvm {
namespace sys {
namespace unicode {

/// Unicode code points of the categories L, M, N, P, S and Zs are considered
/// printable.
/// In addition, U+00AD SOFT HYPHEN is also considered printable, as
/// it's actually displayed on most terminals. \return true if the character is
/// considered printable.
bool isPrintable(int UCS) { … }

/// Unicode code points of the Cf category are considered
/// formatting characters.
bool isFormatting(int UCS) { … }

/// Gets the number of positions a character is likely to occupy when output
/// on a terminal ("character width"). This depends on the implementation of the
/// terminal, and there's no standard definition of character width.
/// The implementation defines it in a way that is expected to be compatible
/// with a generic Unicode-capable terminal.
/// \return Character width:
///   * ErrorNonPrintableCharacter (-1) for non-printable characters (as
///     identified by isPrintable);
///   * 0 for non-spacing and enclosing combining marks;
///   * 2 for CJK characters excluding halfwidth forms;
///   * 1 for all remaining characters.
static inline int charWidth(int UCS) { … }

static bool isprintableascii(char c) { … }

int columnWidthUTF8(StringRef Text) { … }

} // namespace unicode
} // namespace sys
} // namespace llvm