#include "madgwick.h"
#include <stddef.h>
#include <stdlib.h>

#define MADGWICK_INIT_ERR_STR           "Madgwick AHRS init error"
#define MADGWICK_SET_BETA_ERR_STR       "Madgwick set beta error"
#define MADGWICK_SET_SAMP_FREQ_ERR_STR  "Madgwick set sample frequency error"
#define MADGWICK_GET_QUAT_ERR_STR       "Madgwick get quaternion error"
#define MADGWICK_UPDATE_6DOF_ERR_STR    "Madgwick update 6DOF error"
#define MADGWICK_UPDATE_9DOF_ERR_STR    "Madgwick update 9DOF error"

static const char* MADGWICK_TAG = "MADGWICK AHRS";
#define MADGWICK_CHECK(a, str, ret)  if(!(a)) {                                             \
        return (ret);                                                                       \
        }
        
#define STM_ERR_INVALID_ARG 1

typedef struct madgwick {
    float beta;
    float sample_freq;
    float q0;
    float q1;
    float q2;
    float q3; 
    uint8_t lock;
} madgwick_t;

static float invSqrt(float x)
{
    float halfx = 0.5f * x;
    float y = x;
    long i = *(long*)&y;
    i = 0x5f3759df - (i >> 1);
    y = *(float*)&i;
    y = y * (1.5f - (halfx * y * y));
    return y;
}

madgwick_handle_t madgwick_init(madgwick_cfg_t *config)
{
    /* Check input conditions */
    MADGWICK_CHECK(config, MADGWICK_INIT_ERR_STR, NULL);

    /* Allocate memory for handle structure */
    madgwick_handle_t handle = calloc(1, sizeof(madgwick_t));
    MADGWICK_CHECK(handle, MADGWICK_INIT_ERR_STR, NULL);

    /* Update handle structure */
    handle->beta = config->beta;
    handle->sample_freq = config->sample_freq;
    handle->q0 = 1.0f;
    handle->q1 = 0.0f;
    handle->q2 = 0.0f;
    handle->q3 = 0.0f;
    handle->lock = 0;

    return handle;
}

uint8_t madgwick_set_beta(madgwick_handle_t handle, float beta)
{
    /* Check input conditions */
    MADGWICK_CHECK(handle, MADGWICK_SET_BETA_ERR_STR, STM_ERR_INVALID_ARG);

    handle->lock = 1;
    handle->beta = beta;
    handle->lock = 0;

    return 0;
}

uint8_t madgwick_set_sample_frequency(madgwick_handle_t handle, float sample_freq)
{
    /* Check input conditions */
    MADGWICK_CHECK(handle, MADGWICK_SET_SAMP_FREQ_ERR_STR, STM_ERR_INVALID_ARG);

    handle->lock = 1;
    handle->sample_freq = sample_freq;
    handle->lock = 0;

    return 0;
}

uint8_t madgwick_get_quaternion(madgwick_handle_t handle, madgwick_quat_data_t *quat_data)
{
    /* Check input conditions */
    MADGWICK_CHECK(handle, MADGWICK_GET_QUAT_ERR_STR, STM_ERR_INVALID_ARG);

    handle->lock = 1;
    quat_data->q0 = handle->q0;
    quat_data->q1 = handle->q1;
    quat_data->q2 = handle->q2;
    quat_data->q3 = handle->q3;
    handle->lock = 0;

    return 0;
}

uint8_t madgwick_update_6dof(madgwick_handle_t handle, float gx, float gy, float gz, float ax, float ay, float az)
{
    /* Check input conditions */
    MADGWICK_CHECK(handle, MADGWICK_UPDATE_6DOF_ERR_STR, STM_ERR_INVALID_ARG);

    handle->lock = 1;
    
    float q0 = handle->q0;
    float q1 = handle->q1;
    float q2 = handle->q2;
    float q3 = handle->q3;
    float beta = handle->beta;
    float sampleFreq = handle->sample_freq;
    float recipNorm;
    float s0, s1, s2, s3;
    float qDot1, qDot2, qDot3, qDot4;
    float _2q0, _2q1, _2q2, _2q3, _4q0, _4q1, _4q2 , _8q1, _8q2, q0q0, q1q1, q2q2, q3q3;

    // Rate of change of quaternion from gyroscope
    qDot1 = 0.5f * (-q1 * gx - q2 * gy - q3 * gz);
    qDot2 = 0.5f * (q0 * gx + q2 * gz - q3 * gy);
    qDot3 = 0.5f * (q0 * gy - q1 * gz + q3 * gx);
    qDot4 = 0.5f * (q0 * gz + q1 * gy - q2 * gx);

    // Compute feedback only if accelerometer measurement valid (avoids NaN in accelerometer normalisation)
    if (!((ax == 0.0f) && (ay == 0.0f) && (az == 0.0f))) {

        // Normalise accelerometer measurement
        recipNorm = invSqrt(ax * ax + ay * ay + az * az);
        ax *= recipNorm;
        ay *= recipNorm;
        az *= recipNorm;

        // Auxiliary variables to avoid repeated arithmetic
        _2q0 = 2.0f * q0;
        _2q1 = 2.0f * q1;
        _2q2 = 2.0f * q2;
        _2q3 = 2.0f * q3;
        _4q0 = 4.0f * q0;
        _4q1 = 4.0f * q1;
        _4q2 = 4.0f * q2;
        _8q1 = 8.0f * q1;
        _8q2 = 8.0f * q2;
        q0q0 = q0 * q0;
        q1q1 = q1 * q1;
        q2q2 = q2 * q2;
        q3q3 = q3 * q3;

        // Gradient decent algorithm corrective step
        s0 = _4q0 * q2q2 + _2q2 * ax + _4q0 * q1q1 - _2q1 * ay;
        s1 = _4q1 * q3q3 - _2q3 * ax + 4.0f * q0q0 * q1 - _2q0 * ay - _4q1 + _8q1 * q1q1 + _8q1 * q2q2 + _4q1 * az;
        s2 = 4.0f * q0q0 * q2 + _2q0 * ax + _4q2 * q3q3 - _2q3 * ay - _4q2 + _8q2 * q1q1 + _8q2 * q2q2 + _4q2 * az;
        s3 = 4.0f * q1q1 * q3 - _2q1 * ax + 4.0f * q2q2 * q3 - _2q2 * ay;
        recipNorm = invSqrt(s0 * s0 + s1 * s1 + s2 * s2 + s3 * s3); // normalise step magnitude
        s0 *= recipNorm;
        s1 *= recipNorm;
        s2 *= recipNorm;
        s3 *= recipNorm;

        // Apply feedback step
        qDot1 -= beta * s0;
        qDot2 -= beta * s1;
        qDot3 -= beta * s2;
        qDot4 -= beta * s3;
    }

    // Integrate rate of change of quaternion to yield quaternion
    q0 += qDot1 * (1.0f / sampleFreq);
    q1 += qDot2 * (1.0f / sampleFreq);
    q2 += qDot3 * (1.0f / sampleFreq);
    q3 += qDot4 * (1.0f / sampleFreq);

    // Normalise quaternion
    recipNorm = invSqrt(q0 * q0 + q1 * q1 + q2 * q2 + q3 * q3);
    q0 *= recipNorm;
    q1 *= recipNorm;
    q2 *= recipNorm;
    q3 *= recipNorm;

    handle->q0 = q0;
    handle->q1 = q1;
    handle->q2 = q2;
    handle->q3 = q3;

    handle->lock = 0;

    return 0;
}

uint8_t madgwick_update_9dof(madgwick_handle_t handle, float gx, float gy, float gz, float ax, float ay, float az, float mx, float my, float mz)
{
    /* Check input conditions */
    MADGWICK_CHECK(handle, MADGWICK_UPDATE_9DOF_ERR_STR, STM_ERR_INVALID_ARG);

    // Use IMU algorithm if magnetometer measurement invalid (avoids NaN in magnetometer normalisation)
    if ((mx == 0.0f) && (my == 0.0f) && (mz == 0.0f)) {
        madgwick_update_6dof(handle, gx, gy, gz, ax, ay, az);
        return 0;
    }

    handle->lock = 1;

    float q0 = handle->q0;
    float q1 = handle->q1;
    float q2 = handle->q2;
    float q3 = handle->q3;
    float beta = handle->beta;
    float sampleFreq = handle->sample_freq;
    float recipNorm;
    float s0, s1, s2, s3;
    float qDot1, qDot2, qDot3, qDot4;
    float hx, hy;
    float _2q0mx, _2q0my, _2q0mz, _2q1mx, _2bx, _2bz, _4bx, _4bz, _2q0, _2q1, _2q2, _2q3, _2q0q2, _2q2q3, q0q0, q0q1, q0q2, q0q3, q1q1, q1q2, q1q3, q2q2, q2q3, q3q3;

    

    // Rate of change of quaternion from gyroscope
    qDot1 = 0.5f * (-q1 * gx - q2 * gy - q3 * gz);
    qDot2 = 0.5f * (q0 * gx + q2 * gz - q3 * gy);
    qDot3 = 0.5f * (q0 * gy - q1 * gz + q3 * gx);
    qDot4 = 0.5f * (q0 * gz + q1 * gy - q2 * gx);

    // Compute feedback only if accelerometer measurement valid (avoids NaN in accelerometer normalisation)
    if (!((ax == 0.0f) && (ay == 0.0f) && (az == 0.0f))) {

        // Normalise accelerometer measurement
        recipNorm = invSqrt(ax * ax + ay * ay + az * az);
        ax *= recipNorm;
        ay *= recipNorm;
        az *= recipNorm;

        // Normalise magnetometer measurement
        recipNorm = invSqrt(mx * mx + my * my + mz * mz);
        mx *= recipNorm;
        my *= recipNorm;
        mz *= recipNorm;

        // Auxiliary variables to avoid repeated arithmetic
        _2q0mx = 2.0f * q0 * mx;
        _2q0my = 2.0f * q0 * my;
        _2q0mz = 2.0f * q0 * mz;
        _2q1mx = 2.0f * q1 * mx;
        _2q0 = 2.0f * q0;
        _2q1 = 2.0f * q1;
        _2q2 = 2.0f * q2;
        _2q3 = 2.0f * q3;
        _2q0q2 = 2.0f * q0 * q2;
        _2q2q3 = 2.0f * q2 * q3;
        q0q0 = q0 * q0;
        q0q1 = q0 * q1;
        q0q2 = q0 * q2;
        q0q3 = q0 * q3;
        q1q1 = q1 * q1;
        q1q2 = q1 * q2;
        q1q3 = q1 * q3;
        q2q2 = q2 * q2;
        q2q3 = q2 * q3;
        q3q3 = q3 * q3;

        // Reference direction of Earth's magnetic field
        hx = mx * q0q0 - _2q0my * q3 + _2q0mz * q2 + mx * q1q1 + _2q1 * my * q2 + _2q1 * mz * q3 - mx * q2q2 - mx * q3q3;
        hy = _2q0mx * q3 + my * q0q0 - _2q0mz * q1 + _2q1mx * q2 - my * q1q1 + my * q2q2 + _2q2 * mz * q3 - my * q3q3;
        _2bx = sqrt(hx * hx + hy * hy);
        _2bz = -_2q0mx * q2 + _2q0my * q1 + mz * q0q0 + _2q1mx * q3 - mz * q1q1 + _2q2 * my * q3 - mz * q2q2 + mz * q3q3;
        _4bx = 2.0f * _2bx;
        _4bz = 2.0f * _2bz;

        // Gradient decent algorithm corrective step
        s0 = -_2q2 * (2.0f * q1q3 - _2q0q2 - ax) + _2q1 * (2.0f * q0q1 + _2q2q3 - ay) - _2bz * q2 * (_2bx * (0.5f - q2q2 - q3q3) + _2bz * (q1q3 - q0q2) - mx) + (-_2bx * q3 + _2bz * q1) * (_2bx * (q1q2 - q0q3) + _2bz * (q0q1 + q2q3) - my) + _2bx * q2 * (_2bx * (q0q2 + q1q3) + _2bz * (0.5f - q1q1 - q2q2) - mz);
        s1 = _2q3 * (2.0f * q1q3 - _2q0q2 - ax) + _2q0 * (2.0f * q0q1 + _2q2q3 - ay) - 4.0f * q1 * (1 - 2.0f * q1q1 - 2.0f * q2q2 - az) + _2bz * q3 * (_2bx * (0.5f - q2q2 - q3q3) + _2bz * (q1q3 - q0q2) - mx) + (_2bx * q2 + _2bz * q0) * (_2bx * (q1q2 - q0q3) + _2bz * (q0q1 + q2q3) - my) + (_2bx * q3 - _4bz * q1) * (_2bx * (q0q2 + q1q3) + _2bz * (0.5f - q1q1 - q2q2) - mz);
        s2 = -_2q0 * (2.0f * q1q3 - _2q0q2 - ax) + _2q3 * (2.0f * q0q1 + _2q2q3 - ay) - 4.0f * q2 * (1 - 2.0f * q1q1 - 2.0f * q2q2 - az) + (-_4bx * q2 - _2bz * q0) * (_2bx * (0.5f - q2q2 - q3q3) + _2bz * (q1q3 - q0q2) - mx) + (_2bx * q1 + _2bz * q3) * (_2bx * (q1q2 - q0q3) + _2bz * (q0q1 + q2q3) - my) + (_2bx * q0 - _4bz * q2) * (_2bx * (q0q2 + q1q3) + _2bz * (0.5f - q1q1 - q2q2) - mz);
        s3 = _2q1 * (2.0f * q1q3 - _2q0q2 - ax) + _2q2 * (2.0f * q0q1 + _2q2q3 - ay) + (-_4bx * q3 + _2bz * q1) * (_2bx * (0.5f - q2q2 - q3q3) + _2bz * (q1q3 - q0q2) - mx) + (-_2bx * q0 + _2bz * q2) * (_2bx * (q1q2 - q0q3) + _2bz * (q0q1 + q2q3) - my) + _2bx * q1 * (_2bx * (q0q2 + q1q3) + _2bz * (0.5f - q1q1 - q2q2) - mz);
        recipNorm = invSqrt(s0 * s0 + s1 * s1 + s2 * s2 + s3 * s3); // normalise step magnitude
        s0 *= recipNorm;
        s1 *= recipNorm;
        s2 *= recipNorm;
        s3 *= recipNorm;

        // Apply feedback step
        qDot1 -= beta * s0;
        qDot2 -= beta * s1;
        qDot3 -= beta * s2;
        qDot4 -= beta * s3;
    }

    // Integrate rate of change of quaternion to yield quaternion
    q0 += qDot1 * (1.0f / sampleFreq);
    q1 += qDot2 * (1.0f / sampleFreq);
    q2 += qDot3 * (1.0f / sampleFreq);
    q3 += qDot4 * (1.0f / sampleFreq);

    // Normalise quaternion
    recipNorm = invSqrt(q0 * q0 + q1 * q1 + q2 * q2 + q3 * q3);
    q0 *= recipNorm;
    q1 *= recipNorm;
    q2 *= recipNorm;
    q3 *= recipNorm;

    handle->q0 = q0;
    handle->q1 = q1;
    handle->q2 = q2;
    handle->q3 = q3;

    handle->lock = 0;

    return 0;
}