bitreader.h

Go to the documentation of this file.

// SPDX-License-Identifier: Unlicense
// Created by Scott Theisen, 2022-2024
/* The Unlicense
This is free and unencumbered software released into the public domain.
 
Anyone is free to copy, modify, publish, use, compile, sell, or
distribute this software, either in source code form or as a compiled
binary, for any purpose, commercial or non-commercial, and by any
means.
 
In jurisdictions that recognize copyright laws, the author or authors
of this software dedicate any and all copyright interest in the
software to the public domain. We make this dedication for the benefit
of the public at large and to the detriment of our heirs and
successors. We intend this dedication to be an overt act of
relinquishment in perpetuity of all present and future rights to this
software under copyright law.
 
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
OTHER DEALINGS IN THE SOFTWARE.
 
For more information, please refer to <https://unlicense.org>
*/
 
#ifndef BIT_READER_H
#define BIT_READER_H
 
#include <algorithm>
#include <array>
#include <cstdint>
 
#if __has_include(<bit>) // C++20
#include <bit>
#endif
 
class BitReader
{
  public:
    BitReader(const uint8_t* buffer, uint64_t size) :
        m_buffer(buffer),
        m_bufferEnd(buffer + size)
    {
    }
    ~BitReader() = default;
 
    void skip_bits(unsigned n)
    {
        if (m_cacheSize > n)
        {
            m_cache <<= n;
            m_cacheSize -= n;
        }
        else
        {
            n -= m_cacheSize;
            m_cacheSize        = 0;
            m_cache            = 0;
            m_bitIndex        += n;
            unsigned quotient  = m_bitIndex / kBitsPerRead;
            m_bitIndex         = m_bitIndex % kBitsPerRead;
            m_buffer          += quotient;
        }
    }
    uint32_t show_bits(unsigned n)
    {
        //assert(n <= 32);
        if (m_cacheSize < n)
        {
            refill_cache(32);
        }
        return static_cast<uint32_t>(get_upper_bits(m_cache, n));
    }
    uint64_t show_bits64(unsigned n)
    {
        //assert(n <= 64);
        if (m_cacheSize < n)
        {
            refill_cache(64);
        }
        return get_upper_bits(m_cache, n);
    }
    bool next_bit() { return get_bits(1) == 1; }
    uint32_t get_bits(unsigned n)
    {
        uint32_t ret = show_bits(n);
        skip_bits(n);
        return ret;
    }
    uint64_t get_bits64(unsigned n)
    {
        uint64_t ret = show_bits64(n);
        skip_bits(n);
        return ret;
    }
 
    int get_ue_golomb()
    {
        return get_ue_golomb(13);
    }
 
    uint32_t get_ue_golomb_long()
    {
        uint32_t buf    = show_bits(32);
        unsigned lz     = clz(buf);
        unsigned length = lz + 1;
        skip_bits(lz);
 
        if (length > 32)
        {
            skip_bits(length);
            return UINT32_MAX;
        }
 
        return get_bits(length) - 1;
    }
 
    int get_ue_golomb_31()
    {
        return get_ue_golomb(5);
    }
 
    int get_se_golomb()
    {
        uint32_t buf = get_ue_golomb_long() + 1;
        // revert the -1 offset to get the raw value
 
        if (buf & 1)
        {
            return -(buf >> 1);
        }
        return buf >> 1;
    }
 
    int64_t get_bits_left()
    {
        return m_cacheSize + (kBitsPerRead * static_cast<int64_t>(m_bufferEnd - m_buffer)) - m_bitIndex;
    }
 
  private:
    int get_ue_golomb(unsigned max_length);
    static unsigned clz(uint32_t v)
    {
#if defined(__cpp_lib_bitops) && __cpp_lib_bitops >= 201907L // C++20 <bit>
        return std::countl_zero(v);
#else
        // based on public domain log2_floor
        // http://graphics.stanford.edu/~seander/bithacks.html#IntegerLogDeBruijn
        if (v == 0)
        {
            return 32;
        }
        static constexpr std::array<int,32> MultiplyDeBruijnBitPosition =
        {
             0,  9,  1, 10, 13, 21,  2, 29, 11, 14, 16, 18, 22, 25,  3, 30,
             8, 12, 20, 28, 15, 17, 24,  7, 19, 27, 23,  6, 26,  5,  4, 31
        };
 
        v |= v >> 1; // first round down to one less than a power of 2 
        v |= v >> 2;
        v |= v >> 4;
        v |= v >> 8;
        v |= v >> 16;
 
        return 31 - MultiplyDeBruijnBitPosition[static_cast<uint32_t>(v * 0x07C4ACDDU) >> 27];
#endif
    }
 
    static constexpr uint64_t get_upper_bits(uint64_t val, unsigned bits)
    {
        // protect against undefined behavior
        if (bits == 0)
        {
            return UINT64_C(0);
        }
        if (bits > 64)
        {
            return val;
        }
        return val >> (64 - bits);
    }
 
    void refill_cache(unsigned min_bits);
 
    const uint8_t *m_buffer; 
    const uint8_t * const m_bufferEnd; 
    unsigned m_bitIndex {0}; 
 
    uint64_t m_cache {0};
    unsigned m_cacheSize {0};
 
    static constexpr unsigned kCacheSizeMax {64};
    static constexpr unsigned kBitsPerRead  { 8};
};
 
inline int BitReader::get_ue_golomb(unsigned max_length)
{
    uint32_t buf    = show_bits(32);
    unsigned lz     = clz(buf);
    unsigned length = lz + 1;
    unsigned size   = lz + length; // total length
 
    skip_bits(size);
 
    if (length > max_length || length > 16)
    {
        return -1;
    }
 
    buf >>= 32 - size; // remove irrelevant trailing bits
 
    return buf - 1; // offset for storing 0
}
 
inline void BitReader::refill_cache(unsigned min_bits)
{
    min_bits = std::min(min_bits, kCacheSizeMax);
 
    //if (m_bitIndex >= kBitsPerRead)
    {
        unsigned quotient = m_bitIndex / kBitsPerRead;
        m_bitIndex        = m_bitIndex % kBitsPerRead;
        m_buffer         += quotient;
    }
 
    while (m_cacheSize < min_bits && m_buffer < m_bufferEnd)
    {
        unsigned shift = kCacheSizeMax - m_cacheSize;
        unsigned bits  = kBitsPerRead  - m_bitIndex;
        if (shift >= bits)
        {
            m_cache |= static_cast<uint64_t>(*m_buffer) << (shift - bits);
            m_bitIndex   = 0;
            m_buffer++;
            m_cacheSize += bits;
        }
        else
        {
            m_cache |= static_cast<uint64_t>(*m_buffer) >> (bits - shift);
            m_bitIndex  += shift;
            m_cacheSize += shift;
            return; // m_cacheSize == kCacheSizeMax
        }
 
    }
}
 
#endif // BIT_READER_H