juce_CharPointer_UTF8.h

/*
  ==============================================================================
 
   This file is part of the JUCE library.
   Copyright (c) 2022 - Raw Material Software Limited
 
   JUCE is an open source library subject to commercial or open-source
   licensing.
 
   The code included in this file is provided under the terms of the ISC license
   http://www.isc.org/downloads/software-support-policy/isc-license. Permission
   To use, copy, modify, and/or distribute this software for any purpose with or
   without fee is hereby granted provided that the above copyright notice and
   this permission notice appear in all copies.
 
   JUCE IS PROVIDED "AS IS" WITHOUT ANY WARRANTY, AND ALL WARRANTIES, WHETHER
   EXPRESSED OR IMPLIED, INCLUDING MERCHANTABILITY AND FITNESS FOR PURPOSE, ARE
   DISCLAIMED.
 
  ==============================================================================
*/
 
namespace juce
{
 
//==============================================================================
class CharPointer_UTF8  final
{
public:
    using CharType = char;
 
    explicit CharPointer_UTF8 (const CharType* rawPointer) noexcept
        : data (const_cast<CharType*> (rawPointer))
    {
    }
 
    CharPointer_UTF8 (const CharPointer_UTF8& other) = default;
 
    CharPointer_UTF8 operator= (CharPointer_UTF8 other) noexcept
    {
        data = other.data;
        return *this;
    }
 
    CharPointer_UTF8 operator= (const CharType* text) noexcept
    {
        data = const_cast<CharType*> (text);
        return *this;
    }
 
    bool operator== (CharPointer_UTF8 other) const noexcept      { return data == other.data; }
    bool operator!= (CharPointer_UTF8 other) const noexcept      { return data != other.data; }
    bool operator<= (CharPointer_UTF8 other) const noexcept      { return data <= other.data; }
    bool operator<  (CharPointer_UTF8 other) const noexcept      { return data <  other.data; }
    bool operator>= (CharPointer_UTF8 other) const noexcept      { return data >= other.data; }
    bool operator>  (CharPointer_UTF8 other) const noexcept      { return data >  other.data; }
 
    CharType* getAddress() const noexcept        { return data; }
 
    operator const CharType*() const noexcept    { return data; }
 
    bool isEmpty() const noexcept                { return *data == 0; }
 
    bool isNotEmpty() const noexcept             { return *data != 0; }
 
    juce_wchar operator*() const noexcept
    {
        auto byte = (signed char) *data;
 
        if (byte >= 0)
            return (juce_wchar) (uint8) byte;
 
        uint32 n = (uint32) (uint8) byte;
        uint32 mask = 0x7f;
        uint32 bit = 0x40;
        int numExtraValues = 0;
 
        while ((n & bit) != 0 && bit > 0x8)
        {
            mask >>= 1;
            ++numExtraValues;
            bit >>= 1;
        }
 
        n &= mask;
 
        for (int i = 1; i <= numExtraValues; ++i)
        {
            auto nextByte = (uint32) (uint8) data[i];
 
            if ((nextByte & 0xc0) != 0x80)
                break;
 
            n <<= 6;
            n |= (nextByte & 0x3f);
        }
 
        return (juce_wchar) n;
    }
 
    CharPointer_UTF8& operator++() noexcept
    {
        jassert (*data != 0); // trying to advance past the end of the string?
        auto n = (signed char) *data++;
 
        if (n < 0)
        {
            uint8 bit = 0x40;
 
            while ((static_cast<uint8> (n) & bit) != 0 && bit > 0x8)
            {
                ++data;
                bit = static_cast<uint8> (bit >> 1);
            }
        }
 
        return *this;
    }
 
    CharPointer_UTF8 operator--() noexcept
    {
        int count = 0;
 
        while ((*--data & 0xc0) == 0x80 && ++count < 4)
        {}
 
        return *this;
    }
 
    juce_wchar getAndAdvance() noexcept
    {
        auto byte = (signed char) *data++;
 
        if (byte >= 0)
            return (juce_wchar) (uint8) byte;
 
        uint32 n = (uint32) (uint8) byte;
        uint32 mask = 0x7f;
        uint32 bit = 0x40;
        int numExtraValues = 0;
 
        while ((n & bit) != 0 && bit > 0x8)
        {
            mask >>= 1;
            ++numExtraValues;
            bit >>= 1;
        }
 
        n &= mask;
 
        while (--numExtraValues >= 0)
        {
            auto nextByte = (uint32) (uint8) *data;
 
            if ((nextByte & 0xc0) != 0x80)
                break;
 
            ++data;
            n <<= 6;
            n |= (nextByte & 0x3f);
        }
 
        return (juce_wchar) n;
    }
 
    CharPointer_UTF8 operator++ (int) noexcept
    {
        CharPointer_UTF8 temp (*this);
        ++*this;
        return temp;
    }
 
    void operator+= (int numToSkip) noexcept
    {
        if (numToSkip < 0)
        {
            while (++numToSkip <= 0)
                --*this;
        }
        else
        {
            while (--numToSkip >= 0)
                ++*this;
        }
    }
 
    void operator-= (int numToSkip) noexcept
    {
        operator+= (-numToSkip);
    }
 
    juce_wchar operator[] (int characterIndex) const noexcept
    {
        auto p (*this);
        p += characterIndex;
        return *p;
    }
 
    CharPointer_UTF8 operator+ (int numToSkip) const noexcept
    {
        auto p (*this);
        p += numToSkip;
        return p;
    }
 
    CharPointer_UTF8 operator- (int numToSkip) const noexcept
    {
        auto p (*this);
        p += -numToSkip;
        return p;
    }
 
    size_t length() const noexcept
    {
        auto* d = data;
        size_t count = 0;
 
        for (;;)
        {
            auto n = (uint32) (uint8) *d++;
 
            if ((n & 0x80) != 0)
            {
                while ((*d & 0xc0) == 0x80)
                    ++d;
            }
            else if (n == 0)
                break;
 
            ++count;
        }
 
        return count;
    }
 
    size_t lengthUpTo (const size_t maxCharsToCount) const noexcept
    {
        return CharacterFunctions::lengthUpTo (*this, maxCharsToCount);
    }
 
    size_t lengthUpTo (const CharPointer_UTF8 end) const noexcept
    {
        return CharacterFunctions::lengthUpTo (*this, end);
    }
 
    size_t sizeInBytes() const noexcept
    {
        JUCE_BEGIN_IGNORE_WARNINGS_MSVC (6387)
        jassert (data != nullptr);
        return strlen (data) + 1;
        JUCE_END_IGNORE_WARNINGS_MSVC
    }
 
    static size_t getBytesRequiredFor (const juce_wchar charToWrite) noexcept
    {
        size_t num = 1;
        auto c = (uint32) charToWrite;
 
        if (c >= 0x80)
        {
            ++num;
            if (c >= 0x800)
            {
                ++num;
                if (c >= 0x10000)
                    ++num;
            }
        }
 
        return num;
    }
 
    template <class CharPointer>
    static size_t getBytesRequiredFor (CharPointer text) noexcept
    {
        size_t count = 0;
 
        while (auto n = text.getAndAdvance())
            count += getBytesRequiredFor (n);
 
        return count;
    }
 
    CharPointer_UTF8 findTerminatingNull() const noexcept
    {
        return CharPointer_UTF8 (data + strlen (data));
    }
 
    void write (const juce_wchar charToWrite) noexcept
    {
        auto c = (uint32) charToWrite;
 
        if (c >= 0x80)
        {
            int numExtraBytes = 1;
            if (c >= 0x800)
            {
                ++numExtraBytes;
                if (c >= 0x10000)
                    ++numExtraBytes;
            }
 
            *data++ = (CharType) ((uint32) (0xff << (7 - numExtraBytes)) | (c >> (numExtraBytes * 6)));
 
            while (--numExtraBytes >= 0)
                *data++ = (CharType) (0x80 | (0x3f & (c >> (numExtraBytes * 6))));
        }
        else
        {
            *data++ = (CharType) c;
        }
    }
 
    void writeNull() const noexcept
    {
        *data = 0;
    }
 
    template <typename CharPointer>
    void writeAll (const CharPointer src) noexcept
    {
        CharacterFunctions::copyAll (*this, src);
    }
 
    void writeAll (const CharPointer_UTF8 src) noexcept
    {
        auto* s = src.data;
 
        while ((*data = *s) != 0)
        {
            ++data;
            ++s;
        }
    }
 
    template <typename CharPointer>
    size_t writeWithDestByteLimit (const CharPointer src, const size_t maxDestBytes) noexcept
    {
        return CharacterFunctions::copyWithDestByteLimit (*this, src, maxDestBytes);
    }
 
    template <typename CharPointer>
    void writeWithCharLimit (const CharPointer src, const int maxChars) noexcept
    {
        CharacterFunctions::copyWithCharLimit (*this, src, maxChars);
    }
 
    template <typename CharPointer>
    int compare (const CharPointer other) const noexcept
    {
        return CharacterFunctions::compare (*this, other);
    }
 
    template <typename CharPointer>
    int compareUpTo (const CharPointer other, const int maxChars) const noexcept
    {
        return CharacterFunctions::compareUpTo (*this, other, maxChars);
    }
 
    template <typename CharPointer>
    int compareIgnoreCase (const CharPointer other) const noexcept
    {
        return CharacterFunctions::compareIgnoreCase (*this, other);
    }
 
    int compareIgnoreCase (const CharPointer_UTF8 other) const noexcept
    {
        return CharacterFunctions::compareIgnoreCase (*this, other);
    }
 
    template <typename CharPointer>
    int compareIgnoreCaseUpTo (const CharPointer other, const int maxChars) const noexcept
    {
        return CharacterFunctions::compareIgnoreCaseUpTo (*this, other, maxChars);
    }
 
    template <typename CharPointer>
    int indexOf (const CharPointer stringToFind) const noexcept
    {
        return CharacterFunctions::indexOf (*this, stringToFind);
    }
 
    int indexOf (const juce_wchar charToFind) const noexcept
    {
        return CharacterFunctions::indexOfChar (*this, charToFind);
    }
 
    int indexOf (const juce_wchar charToFind, const bool ignoreCase) const noexcept
    {
        return ignoreCase ? CharacterFunctions::indexOfCharIgnoreCase (*this, charToFind)
                          : CharacterFunctions::indexOfChar (*this, charToFind);
    }
 
    bool isWhitespace() const noexcept          { return CharacterFunctions::isWhitespace ((juce_wchar) *(*this)); }
    bool isDigit() const noexcept               { const CharType c = *data; return c >= '0' && c <= '9'; }
    bool isLetter() const noexcept              { return CharacterFunctions::isLetter (operator*()) != 0; }
    bool isLetterOrDigit() const noexcept       { return CharacterFunctions::isLetterOrDigit (operator*()) != 0; }
    bool isUpperCase() const noexcept           { return CharacterFunctions::isUpperCase (operator*()) != 0; }
    bool isLowerCase() const noexcept           { return CharacterFunctions::isLowerCase (operator*()) != 0; }
 
    juce_wchar toUpperCase() const noexcept     { return CharacterFunctions::toUpperCase (operator*()); }
    juce_wchar toLowerCase() const noexcept     { return CharacterFunctions::toLowerCase (operator*()); }
 
    int getIntValue32() const noexcept          { return atoi (data); }
 
    int64 getIntValue64() const noexcept
    {
       #if JUCE_WINDOWS && ! JUCE_MINGW
        return _atoi64 (data);
       #else
        return atoll (data);
       #endif
    }
 
    double getDoubleValue() const noexcept                      { return CharacterFunctions::getDoubleValue (*this); }
 
    CharPointer_UTF8 findEndOfWhitespace() const noexcept       { return CharacterFunctions::findEndOfWhitespace (*this); }
 
    void incrementToEndOfWhitespace() noexcept                  { CharacterFunctions::incrementToEndOfWhitespace (*this); }
 
    static bool canRepresent (juce_wchar character) noexcept
    {
        return ((uint32) character) < (uint32) 0x10ffff;
    }
 
    static bool isValidString (const CharType* dataToTest, int maxBytesToRead)
    {
        while (--maxBytesToRead >= 0 && *dataToTest != 0)
        {
            auto byte = (signed char) *dataToTest++;
 
            if (byte < 0)
            {
                int bit = 0x40;
                int numExtraValues = 0;
 
                while ((byte & bit) != 0)
                {
                    if (bit < 8)
                        return false;
 
                    ++numExtraValues;
                    bit >>= 1;
 
                    if (bit == 8 && (numExtraValues > maxBytesToRead
                                       || *CharPointer_UTF8 (dataToTest - 1) > 0x10ffff))
                        return false;
                }
 
                if (numExtraValues == 0)
                    return false;
 
                maxBytesToRead -= numExtraValues;
                if (maxBytesToRead < 0)
                    return false;
 
                while (--numExtraValues >= 0)
                    if ((*dataToTest++ & 0xc0) != 0x80)
                        return false;
            }
        }
 
        return true;
    }
 
    CharPointer_UTF8 atomicSwap (const CharPointer_UTF8 newValue)
    {
        return CharPointer_UTF8 (reinterpret_cast<Atomic<CharType*>&> (data).exchange (newValue.data));
    }
 
    enum
    {
        byteOrderMark1 = 0xef,
        byteOrderMark2 = 0xbb,
        byteOrderMark3 = 0xbf
    };
 
    static bool isByteOrderMark (const void* possibleByteOrder) noexcept
    {
        JUCE_BEGIN_IGNORE_WARNINGS_MSVC (28182)
        jassert (possibleByteOrder != nullptr);
        auto c = static_cast<const uint8*> (possibleByteOrder);
 
        return c[0] == (uint8) byteOrderMark1
            && c[1] == (uint8) byteOrderMark2
            && c[2] == (uint8) byteOrderMark3;
        JUCE_END_IGNORE_WARNINGS_MSVC
    }
 
private:
    CharType* data;
};
 
} // namespace juce