import time
import os

for i in range(10):

    infilename = 'data/pi100m.dectxt.00' + str(i)
    outfilename = 'data/tau100m.dectxt.00' + str(i)
    
    if not os.path.isfile(outfilename):
    
        start=time.time()
    
        with open(infilename, 'r') as fin:
            pi = fin.read()
        
        overallcount = 100000000
        
        for subset in range(9):
            pisub = pi[subset*10000000:(subset+1)*10000000]
        
            pos = 0
            tau = ''
            pisect=''
            counter = 0
            
            print "Processing " + infilename + ", remaining (million): ",
            
            while pos < len(pisub):
                if overallcount % 1000000 == 0:
                    print (overallcount / 1000000),
                overallcount -= 1
                if pisub[pos] == '4':
                    counter += 1 # I put in this counter to work on larger chunks, but I'm not convinced it makes a difference
                    if counter % 5 == 0:
                        numsect=int(pisect)
                        pisect='4'
                        numsect *= 2
                        tau+=str(numsect)
                    else:
                        pisect+=pisub[pos]
                else:
                    pisect+=pisub[pos]
                pos += 1        
            #for the remainder
            numsect = int(pisect)
            numsect *= 2
            tau+=str(numsect)
            
            with open(outfilename, 'a+') as fout:
                fout.write(tau)
        
        print 'Finished, %0.1f minutes elapsed' % ((time.time() - start)/60)
    
    else:
        print outfilename + 'already exists.'

print '\nScript finished.'

tauday_file = open('data/tau100K-tauday.com.txt', 'r')
tauday_string = tauday_file.read()
tauday_file.close()
this_file = open('data/tau100m.dectxt.000', 'r')
this_string = this_file.read()  
this_file.close()

print len(tauday_string)
print tauday_string[:10]
print this_string[:10]

if tauday_string[:99999] == this_string[:99999]:
    print "Verification successful. Yay."

filelist = ['data/tau100m.dectxt.001', 'data/tau100m.dectxt.002', 'data/tau100m.dectxt.003', 
            'data/tau100m.dectxt.004', 'data/tau100m.dectxt.005', 'data/tau100m.dectxt.006', 
            'data/tau100m.dectxt.007', 'data/tau100m.dectxt.008', 'data/tau100m.dectxt.009']

for filename in filelist:
    current = open(filename, 'r')
    string1K = current.read()[:1000]
    current.close()
    newfile = open(filename+'.1K', 'w+')
    newfile.write(string1K)
    newfile.close()

    

# verify that pi has a fibonacci sequence of 11235813 at position 48300973
this_file = open('data/pi100m.dectxt.000', 'r')
this_string = this_file.read()  
this_file.close()
print this_string[48300973:48300993]

# verify that tau has a fibonacci sequence of 1123581321 at position 809073288
this_file = open('data/tau100m.dectxt.008', 'r')
this_string = this_file.read()  
this_file.close()
print this_string[9073288:9073300]

# verify that tau recapitulates pi at position 52,567,169
this_file = open('data/tau100m.dectxt.000', 'r')
this_string = this_file.read()  
this_file.close()
print this_string[52567169:52567189]

# verify that tau recapitulates tau at position 405747241
this_file = open('data/tau100m.dectxt.004', 'r')
this_string = this_file.read()  
this_file.close()
print this_string[5747241:5747261]