pywin

# Nikola Jovanovic 0081/15

from string import ascii_lowercase
from string import ascii_uppercase
ascii_letters = ascii_lowercase + ascii_uppercase   ## Bukvalno vec postoji ascii_letters u string :D

def import_standard_etaoin(dat_name=''):    ## Podrazumevani argument bas i nije primeren (-0)
    std_freq = {}
    try:
        letterfreq = open(dat_name+'.txt.', 'r')
        for row in letterfreq:
            row = row.replace('\n', '')
            std_freq[row[0]] = float(row.split('\t')[1][:-1])/100
        print ('Fajl ucitan.')
        return std_freq
    except:
        print ('Koriscenje predefinisanih ucestalosti.')
    return {'e': 0.12702,
            't': 0.09056,
            'a': 0.08167,
            'o': 0.07507,
            'i': 0.06966,
            'n': 0.06749,
            's': 0.06327,
            'h': 0.06094,
            'r': 0.05987,
            'd': 0.04253,
            'l': 0.04025,
            'u': 0.02782,
            'c': 0.02758,
            'm': 0.02406,
            'w': 0.02361,
            'f': 0.02228,
            'g': 0.02015,
            'y': 0.01974,
            'p': 0.01929,
            'b': 0.01492,
            'v': 0.00978,
            'k': 0.00772,
            'j': 0.00153,
            'x': 0.00150,
            'q': 0.00095,
            'z': 0.00074}

def m_o_succ(succs):
    succ_list = [(apps, l) for l, apps in succs.items()]
    maxv = max(succ_list)
    return maxv[1]

def precess_file(dat_name):
    global ascii_lowercase, ascii_letters
    letts_in_dat= 0
    dat_lett_count = {c: 0 for c in ascii_lowercase}
    lett_succs = {k: {c: 0 for c in ascii_lowercase} for k in ascii_lowercase}
    # raw_input('Unesite ime datoteke (bez .txt): ')
    try:
        text_dat = open(dat_name+'.txt')
    except:
        print ('Greska prilikom ucitavanja fajla')
        exit()
    pc = ''
    for i, c in enumerate(text_dat.read()):
        if c in ascii_letters:
            c = c.lower()
            dat_lett_count[c] += 1
            letts_in_dat += 1
            if len(pc) > 0: lett_succs[pc][c] += 1
            pc = c
        else:
            pc = ''
    text_dat.close()
    return {c: [float(dat_lett_count[c])/letts_in_dat, m_o_succ(lett_succs[c])] for c in ascii_lowercase}

def compare_freq(std_etaoin, dat_data):
    diff = {}
    for c in ascii_lowercase:
        diff[c] = std_etaoin[c] / round(dat_data[c][0], 5)
    return diff

def print_results(std_etaoin, dat_data, comp):  ## Sjajan ispis, bolji nego sa pprint
    lett_list = [(dat_data[x][0], x, dat_data[x][1]) for x in dat_data.keys()]
    print ('slovo | dobijeni % | ocekivani % | odnos % | sledbenik')
    for x in sorted(lett_list)[::-1]:
        print (x[1]+'     | {:9.3f}% | {:10.3f}% | {:7.3f} | '.format(round(x[0]*100, 3), std_etaoin[x[1]]*100, comp[x[1]])+x[2])

def save_results(dat_name, diff):
    out_dat = open(dat_name+'-etaoin.txt', 'w')
    out = []
    for c in ascii_lowercase:
        out.append(c + '\t{:.3f}'.format(round(diff[c], 3)))
    out_dat.write('\n'.join(out))
    out_dat.close()

std_etaoin_dat_name = raw_input ('Unesite ime datoteke sa ucestanoscu slova (bez .txt): ')

standard_freq = import_standard_etaoin(std_etaoin_dat_name)

dat_name = raw_input ('Unesite ime tekstulane datoteke (bez .txt): ')

file_data = precess_file(dat_name)

comp = compare_freq(standard_freq, file_data)

print_results(standard_freq, file_data, comp)
## Ne ispisuje se broj ponavljanja slova, ali se racuna, pa je ok (-0)

save_results(dat_name, comp)

## Sve je u potpunosti ispravno
## Poeni: 80/80