# https://codegolf.stackexchange.com/questions/34540/print-the-lyrics-to-twinkle-twinkle-little-star
# https://en.wikipedia.org/wiki/File:Twinkle_Twinkle_Little_Star_plain.ogg

import pyaudio
from array import array
import scipy.signal
import numpy
import math
import sys

MIN_AMPLITUDE = -52
FRAMERATE = 44100

# This function is a little
# Why is pred here anyways?
def first(list, pred):
    for i in range(len(list)):
        if(list[i] > 0):
            return i;
    return 0;
# You would usually want to write it like this:
def first(list, pred):
    for x in list:
        if x > 0:
            return x
    return 0
# Note that use of ; delimiter is only necessary if you
# have multiple statements in one line. That's never.
# I removed them from rest of the code.

# Based on: https://en.wikipedia.org/wiki/Decibel#Acoustics
def getAmplitude(sig):
    total = 0
    elems = float(len(sig))
    for x in sig:
        total += numpy.abs(x) / elems
    if(total == 0):
        return -99
    else:
        return 20 * math.log(total / 32768., 10)

# Based on: https://en.wikipedia.org/wiki/Piano_key_frequencies
def getNote(freq):
    return int(12 * math.log(freq / 440, 2) + 49)

# --------------------------------------------------------------------------
# This is stolen straight from here w/ very slight modifications: https://gist.github.com/endolith/255291
def parabolic(f, x):
    return 1/2. * (f[x-1] - f[x+1]) / (f[x-1] - 2 * f[x] + f[x+1]) + x

def getFrequency(sig):
    # Calculate autocorrelation (same thing as convolution, but with
    # one input reversed in time), and throw away the negative lags
    corr = scipy.signal.fftconvolve(sig, sig[::-1], mode='full')
    corr = corr[len(corr)/2:]

    # Find the first low point
    diffs = numpy.diff(corr)

     # Find the next peak after the low point (other than 0 lag). This bit is
    # not reliable for long signals, due to the desired peak occurring between
    # samples, and other peaks appearing higher.
    # Should use a weighting function to de-emphasize the peaks at longer lags.
    start = first(diffs, lambda x: x > 0)
    peak = numpy.argmax(corr[start:]) + start
    return parabolic(corr, peak) * (FRAMERATE / len(sig))
# --------------------------------------------------------------------------

# These are the wrong keys (ie it is detecting middle C as an A), but I'm far too lazy to figure out why.
# Anyway, these are what are detected from the Wikipedia .ogg file:
notes = [73,          66,           64,       66,         68,       69,        71,          73,       66,     68,          69,         71,         66,        68,         69,        71      ]
words = ["Twinkle, ", "twinkle, ", "little ", "star,\n",  "How I ", "wonder ", "what you ", "are.\n", "Up a", "bove the ", "world so ", "high,\n", "Like a ", "diamond ", "in the ", "sky.\n"]
notes += notes[:8]
words += words[:8]

pa = pyaudio.PyAudio()
stream = pa.open(format=pyaudio.paInt16, channels = 1, rate = FRAMERATE, input = True, frames_per_buffer = 4096)
idx = 0

# Note how I removed braces after while and if
while idx < len(notes):
    # Read signal
    sig = array('h', stream.read(4096))
    if getAmplitude(sig) > MIN_AMPLITUDE:
        note = getNote(getFrequency(sig))
        if note == notes[idx]:
            print(words[idx], end='') # Note, no sys needed
            idx += 1