llvm/llvm/lib/Support/UnicodeNameToCodepoint.cpp

//===- llvm/Support/UnicodeNameToCodepoint.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 to map the name or alias of a unicode
// character to its codepoint.
//
//===----------------------------------------------------------------------===//

#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Support/Unicode.h"

namespace llvm {
namespace sys {
namespace unicode {

extern const char *UnicodeNameToCodepointDict;
extern const uint8_t *UnicodeNameToCodepointIndex;
extern const std::size_t UnicodeNameToCodepointIndexSize;
extern const std::size_t UnicodeNameToCodepointLargestNameSize;

BufferType;

struct Node { … };

static Node createRoot() { … }

static Node readNode(uint32_t Offset, const Node *Parent = nullptr) { … }

static bool startsWith(StringRef Name, StringRef Needle, bool Strict,
                       std::size_t &Consummed, char &PreviousCharInName,
                       bool IsPrefix = false) { … }

static std::tuple<Node, bool, uint32_t>
compareNode(uint32_t Offset, StringRef Name, bool Strict,
            char PreviousCharInName, BufferType &Buffer,
            const Node *Parent = nullptr) { … }

static std::tuple<Node, bool, uint32_t>
compareNode(uint32_t Offset, StringRef Name, bool Strict, BufferType &Buffer) { … }

// clang-format off
constexpr const char *const HangulSyllables[][3] = …;
// clang-format on

// Unicode 15.0
// 3.12 Conjoining Jamo Behavior Common constants
constexpr const char32_t SBase = …;
constexpr const uint32_t LCount = …;
constexpr const uint32_t VCount = …;
constexpr const uint32_t TCount = …;

static std::size_t findSyllable(StringRef Name, bool Strict,
                                char &PreviousInName, int &Pos, int Column) { … }

static std::optional<char32_t>
nameToHangulCodePoint(StringRef Name, bool Strict, BufferType &Buffer) { … }

struct GeneratedNamesData { … };

// Unicode 15.1 Table 4-8. Name Derivation Rule Prefix Strings
static const GeneratedNamesData GeneratedNamesDataTable[] = …;

static std::optional<char32_t>
nameToGeneratedCodePoint(StringRef Name, bool Strict, BufferType &Buffer) { … }

static std::optional<char32_t> nameToCodepoint(StringRef Name, bool Strict,
                                               BufferType &Buffer) { … }

std::optional<char32_t> nameToCodepointStrict(StringRef Name) { … }

std::optional<LooseMatchingResult>
nameToCodepointLooseMatching(StringRef Name) { … }

// Find the unicode character whose editing distance to Pattern
// is shortest, using the Wagner–Fischer algorithm.
llvm::SmallVector<MatchForCodepointName>
nearestMatchesForCodepointName(StringRef Pattern, std::size_t MaxMatchesCount) { … }

} // namespace unicode

} // namespace sys
} // namespace llvm