CharPointer_UTF8.h

Go to the documentation of this file.

/*
  ==============================================================================
 
   This file is part of the Water library.
   Copyright (c) 2016 ROLI Ltd.
   Copyright (C) 2017 Filipe Coelho <falktx@falktx.com>
 
   Permission is granted to use this software 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.
 
   THE SOFTWARE IS PROVIDED "AS IS" AND ISC DISCLAIMS ALL WARRANTIES WITH REGARD
   TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
   FITNESS. IN NO EVENT SHALL ISC BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT,
   OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF
   USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
   TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
   OF THIS SOFTWARE.
 
  ==============================================================================
*/
 
#ifndef WATER_CHARPOINTER_UTF8_H_INCLUDED
#define WATER_CHARPOINTER_UTF8_H_INCLUDED
 
#include "CharacterFunctions.h"
#include "../memory/Atomic.h"
 
#include "CarlaUtils.hpp"
 
namespace water {
 
class String;
 
//==============================================================================
class CharPointer_UTF8
{
public:
    typedef char CharType;
 
    inline explicit CharPointer_UTF8 (const CharType* const rawPointer) noexcept
        : data (const_cast<CharType*> (rawPointer))
    {
    }
 
    inline CharPointer_UTF8 (const CharPointer_UTF8& other) noexcept
        : data (other.data)
    {
    }
 
    inline CharPointer_UTF8& operator= (CharPointer_UTF8 other) noexcept
    {
        data = other.data;
        return *this;
    }
 
    inline CharPointer_UTF8& operator= (const CharType* text) noexcept
    {
        data = const_cast<CharType*> (text);
        return *this;
    }

    inline bool operator== (CharPointer_UTF8 other) const noexcept      { return data == other.data; }
    inline bool operator!= (CharPointer_UTF8 other) const noexcept      { return data != other.data; }
    inline bool operator<= (CharPointer_UTF8 other) const noexcept      { return data <= other.data; }
    inline bool operator<  (CharPointer_UTF8 other) const noexcept      { return data <  other.data; }
    inline bool operator>= (CharPointer_UTF8 other) const noexcept      { return data >= other.data; }
    inline bool operator>  (CharPointer_UTF8 other) const noexcept      { return data >  other.data; }

    inline CharType* getAddress() const noexcept        { return data; }

    inline operator const CharType*() const noexcept    { return data; }

    inline bool isEmpty() const noexcept                { return *data == 0; }

    water_uchar operator*() const noexcept
    {
        const signed char byte = (signed char) *data;
 
        if (byte >= 0)
            return (water_uchar) (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)
        {
            const uint32 nextByte = (uint32) (uint8) data[i];
 
            if ((nextByte & 0xc0) != 0x80)
                break;
 
            n <<= 6;
            n |= (nextByte & 0x3f);
        }
 
        return (water_uchar) n;
    }

    CharPointer_UTF8& operator++() noexcept
    {
        wassert (*data != 0); // trying to advance past the end of the string?
        const signed char n = (signed char) *data++;
 
        if (n < 0)
        {
            water_uchar bit = 0x40;
 
            while ((static_cast<unsigned char>(n) & bit) != 0 && bit > 0x8)
            {
                ++data;
                bit >>= 1;
            }
        }
 
        return *this;
    }

    CharPointer_UTF8& operator--() noexcept
    {
        int count = 0;
 
        while ((*--data & 0xc0) == 0x80 && ++count < 4)
        {}
 
        return *this;
    }

    water_uchar getAndAdvance() noexcept
    {
        const signed char byte = (signed char) *data++;
 
        if (byte >= 0)
            return (water_uchar) (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)
        {
            const uint32 nextByte = (uint32) (uint8) *data;
 
            if ((nextByte & 0xc0) != 0x80)
                break;
 
            ++data;
            n <<= 6;
            n |= (nextByte & 0x3f);
        }
 
        return (water_uchar) 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);
    }

    water_uchar operator[] (int characterIndex) const noexcept
    {
        CharPointer_UTF8 p (*this);
        p += characterIndex;
        return *p;
    }

    CharPointer_UTF8 operator+ (int numToSkip) const noexcept
    {
        CharPointer_UTF8 p (*this);
        p += numToSkip;
        return p;
    }

    CharPointer_UTF8 operator- (int numToSkip) const noexcept
    {
        CharPointer_UTF8 p (*this);
        p += -numToSkip;
        return p;
    }

    size_t length() const noexcept
    {
        const CharType* d = data;
        size_t count = 0;
 
        for (;;)
        {
            const uint32 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
    {
        wassert (data != nullptr);
        return strlen (data) + 1;
    }

    static size_t getBytesRequiredFor (const water_uchar charToWrite) noexcept
    {
        size_t num = 1;
        const uint32 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 (water_uchar n = text.getAndAdvance())
            count += getBytesRequiredFor (n);
 
        return count;
    }

    CharPointer_UTF8 findTerminatingNull() const noexcept
    {
        return CharPointer_UTF8 (data + strlen (data));
    }

    void write (const water_uchar charToWrite) noexcept
    {
        const uint32 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;
        }
    }

    inline 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
    {
        const CharType* 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 water_uchar charToFind) const noexcept
    {
        return CharacterFunctions::indexOfChar (*this, charToFind);
    }

    int indexOf (const water_uchar charToFind, const bool ignoreCase) const noexcept
    {
        return ignoreCase ? CharacterFunctions::indexOfCharIgnoreCase (*this, charToFind)
                          : CharacterFunctions::indexOfChar (*this, charToFind);
    }

    bool isWhitespace() const noexcept      { const CharType c = *data; return c == ' ' || (c <= 13 && c >= 9); }
    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; }

    water_uchar toUpperCase() const noexcept { return CharacterFunctions::toUpperCase (operator*()); }
    water_uchar toLowerCase() const noexcept { return CharacterFunctions::toLowerCase (operator*()); }

    int getIntValue32() const noexcept      { return atoi (data); }

    int64 getIntValue64() const noexcept
    {
        return atoll (data);
       #if 0
        return CharacterFunctions::getIntValue <int64, CharPointer_UTF8> (*this);
       #endif
    }

    double getDoubleValue() const noexcept  { return CharacterFunctions::getDoubleValue (*this); }

    CharPointer_UTF8 findEndOfWhitespace() const noexcept   { return CharacterFunctions::findEndOfWhitespace (*this); }

    static bool canRepresent (water_uchar character) noexcept
    {
        return ((unsigned int) character) < (unsigned int) 0x10ffff;
    }

    static bool isValidString (const CharType* dataToTest, int maxBytesToRead)
    {
        while (--maxBytesToRead >= 0 && *dataToTest != 0)
        {
            const signed char 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;
    }

    enum
    {
        byteOrderMark1 = 0xef,
        byteOrderMark2 = 0xbb,
        byteOrderMark3 = 0xbf
    };

    static bool isByteOrderMark (const void* possibleByteOrder) noexcept
    {
        wassert (possibleByteOrder != nullptr);
        const uint8* const c = static_cast<const uint8*> (possibleByteOrder);
 
        return c[0] == (uint8) byteOrderMark1
            && c[1] == (uint8) byteOrderMark2
            && c[2] == (uint8) byteOrderMark3;
    }
 
private:
    CharType* data;
 
    friend class String;
};
 
}
 
#endif // WATER_CHARPOINTER_UTF8_H_INCLUDED