#!/usr/bin/env python3

# http://inamidst.com/voynich/positions
# Created by Sean B. Palmer

# 33, 35-38, 40, 42-43, 49-57, 64-90, 92, 94, 97-122, 124
# 149-156, 158, 161-166, 168-204, 206-255

def r(start, stop=None):
    if stop is None:
        return set([start])
    return set(range(start, stop + 1))

character_octets = r(33) | r(35, 38) | r(40) | r(42, 43) | r(49, 57) | r(64, 90)
character_octets |= r(92) | r(94) | r(97, 122) | r(124) | r(149, 156) | r(158)
character_octets |= r(161, 166) | r(168, 204) | r(206, 255)

character_octets = {33, 35, 36, 37, 38, 40, 42, 43, 49, 50, 51, 52, 53, 54, 55,
56, 57, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81,
82, 83, 84, 85, 86, 87, 88, 89, 90, 92, 94, 97, 98, 99, 100, 101, 102, 103, 104,
105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120,
121, 122, 124, 149, 150, 151, 152, 153, 154, 155, 156, 158, 161, 162, 163, 164,
165, 166, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181,
182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197,
198, 199, 200, 201, 202, 203, 204, 206, 207, 208, 209, 210, 211, 212, 213, 214,
215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 227, 228, 229, 230,
231, 232, 233, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246,
247, 248, 249, 250, 251, 252, 253, 254, 255}

character_chars = {bytes([o]) for o in character_octets}
def split(word):
    for i in range(len(word)):
        yield word[:i], word[i], word[i + 1:]

# for abc in split("hello"):
#     print(abc)

after = {c1: {c2: 0 for c2 in character_chars} for c1 in character_chars}
before = {c1: {c2: 0 for c2 in character_chars} for c1 in character_chars}

def voynich_words():
    with open("voyn_101.txt", "rb") as f:
        octets = f.read()
        word = b""
        ignore = False

        for octet in octets:
            octet = bytes([octet])
            # if octet == b",":
            #     continue

            if octet == b"<":
                ignore = True

            if ignore is False:
                if octet in character_chars:
                    word += octet

                elif word:
                    yield word
                    word = b""

            if octet == b">":
                ignore = False

        if word:
            yield word

from collections import Counter

frequencies = Counter()

for word in voynich_words():
    for char in word:
        frequencies[char] += 1

    for bef, this, aft in split(word):
        this = bytes([this])
        for c in character_chars:
            if c in bef:
                before[this][c] += 1
            if c in aft:
                after[this][c] += 1

import json

before = {ord(k1): {ord(k2): v2 for k2, v2 in v1.items()}
          for k1, v1 in before.items()}
after = {ord(k1): {ord(k2): v2 for k2, v2 in v1.items()}
         for k1, v1 in after.items()}

# with open("v101.chars.json", "w") as f:
#     f.write(json.dumps({"before": before, "after": after}))

common = [f[0] for f in frequencies.most_common(48)]

compiled = {}

for a in common:
    compiled[a] = {}
    for b in common:
        bef = before[a][b]
        aft = after[a][b]
        try:
            p = (float(bef) / (bef + aft)) * 200
            compiled[a][b] = p - 100
        except:
            compiled[a][b] = 0

print("glyph\tother\tvalue")

lefty = Counter()
for c in common:
    lefty[c] = -sum(compiled[c].values())

ordered = [g[0] for g in lefty.most_common(48)]
# print(ordered)

for c in ordered:
    for d in compiled[c]:
        print("%s\t%s\t%s" % (c, d, compiled[c][d]))