#include <Arduino.h>

#define DHT_LIB_VERSION "0.1.14"

#define DHTLIB_OK                0
#define DHTLIB_ERROR_CHECKSUM   -1
#define DHTLIB_ERROR_TIMEOUT    -2
#define DHTLIB_INVALID_VALUE    -999

#define DHTLIB_DHT11_WAKEUP     18
#define DHTLIB_DHT_WAKEUP       1

// max timeout is 100 usec.                                                                                                                            
// For a 16 Mhz proc 100 usec is 1600 clock cycles                                                                                                     
// loops using DHTLIB_TIMEOUT use at least 4 clock cycli                                                                                               
// so 100 us takes max 400 loops                                                                                                                       
// so by dividing F_CPU by 40000 we "fail" as fast as possible                                                                                         
#define DHTLIB_TIMEOUT (F_CPU/40000)

double humidity;
double temperature;
uint8_t bits[5]; 

void setup()
{
 Serial.begin(9600);  
}

void loop()
{
    // READ VALUES
    int rv = readSensor(13, DHTLIB_DHT11_WAKEUP);
    if (rv != DHTLIB_OK)
    {
      Serial.print("ERROR ");
      Serial.println(rv);
    }

    // CONVERT AND STORE
    humidity    = bits[0];  // bits[1] == 0;
    temperature = bits[2];  // bits[3] == 0;

    // TEST CHECKSUM
    // bits[1] && bits[3] both 0
    uint8_t sum = bits[0] + bits[2];
    if (bits[4] != sum){
      Serial.print("ERROR ");
      Serial.println(DHTLIB_ERROR_CHECKSUM);
      }else{
      Serial.print(int2bin(bits[0]));
      Serial.print(" ");
      Serial.print(int2bin(bits[1]));
      Serial.print(" ");
      Serial.print(int2bin(bits[2]));
      Serial.print(" ");
      Serial.print(int2bin(bits[3]));
      Serial.println("");
      }
    delay(3000);
}

int readSensor(uint8_t pin, uint8_t wakeupDelay)
{
    // INIT BUFFERVAR TO RECEIVE DATA
    uint8_t mask = 128;
    uint8_t idx = 0;

    // replace digitalRead() with Direct Port Reads.
    // reduces footprint ~100 bytes => portability issue?
    // direct port read is about 3x faster
  uint8_t bit = digitalPinToBitMask(pin);
  uint8_t port = digitalPinToPort(pin);
    volatile uint8_t *PIR = portInputRegister(port);

    // EMPTY BUFFER
    for (uint8_t i = 0; i < 5; i++) bits[i] = 0;

    // REQUEST SAMPLE
    pinMode(pin, OUTPUT);
    digitalWrite(pin, LOW); // T-be 
    delay(wakeupDelay);
    digitalWrite(pin, HIGH);   // T-go
    delayMicroseconds(40);
    pinMode(pin, INPUT);

    // GET ACKNOWLEDGE or TIMEOUT
    uint16_t loopCntLOW = DHTLIB_TIMEOUT;
    while ((*PIR & bit) == LOW )  // T-rel
    {
        if (--loopCntLOW == 0) return DHTLIB_ERROR_TIMEOUT;
    }

    uint16_t loopCntHIGH = DHTLIB_TIMEOUT;
    while ((*PIR & bit) != LOW )  // T-reh
    {
        if (--loopCntHIGH == 0) return DHTLIB_ERROR_TIMEOUT;
    }

    // READ THE OUTPUT - 40 BITS => 5 BYTES
    for (uint8_t i = 40; i != 0; i--)
    {
        loopCntLOW = DHTLIB_TIMEOUT;
        while ((*PIR & bit) == LOW )
        {
            if (--loopCntLOW == 0) return DHTLIB_ERROR_TIMEOUT;
        }

        uint32_t t = micros();

        loopCntHIGH = DHTLIB_TIMEOUT;
        while ((*PIR & bit) != LOW )
        {
            if (--loopCntHIGH == 0) return DHTLIB_ERROR_TIMEOUT;
        }

        if ((micros() - t) > 40)
        { 
            bits[idx] |= mask;
        }
        mask >>= 1;
        if (mask == 0)   // next byte?
        {
            mask = 128;
            idx++;
        }
    }
    pinMode(pin, OUTPUT);
    digitalWrite(pin, HIGH);

    return DHTLIB_OK;
}

char * int2bin(uint8_t i)
{
    size_t bits = 8;

    char * str = malloc(bits + 1);
    if(!str) return NULL;
    str[bits] = 0;

    // type punning because signed shift is implementation-defined
    unsigned u = *(unsigned *)&i;
    for(; bits--; u >>= 1)
        str[bits] = u & 1 ? '1' : '0';

    return str;
}