#!/usr/bin/env python3

import re
from random import randrange
from array import array
from copy import copy

class VM():
    def __init__(self, reg: array = array('q'), mem: list = [], pc: int = 0):
        self.reg = copy(reg)
        self.mem = copy(mem)
        self.pc = copy(pc)
        self.outbuf = []

    def run(self, abort: int = 0):
        while self.pc < len(self.mem):
            if abort>0 and len(self.mem) > abort: return

            op = self.mem[self.pc]
            self.pc += 1

            if op == 0b000: # adv
                self.reg[0] = self.reg[0] // (2**self._combo(self.mem[self.pc]))
                self.pc += 1
            if op == 0b001: # bxl
                self.reg[1] = self.reg[1] ^ self.mem[self.pc]
                self.pc += 1
            if op == 0b010: # bst
                self.reg[1] = self._combo(self.mem[self.pc]) & 0b111
                self.pc += 1
            if op == 0b011: # jnz
                self.pc = self.mem[self.pc] if self.reg[0] != 0 else self.pc+1
            if op == 0b100: # bxc
                self.reg[1] = self.reg[1] ^ self.reg[2]
                self.pc += 1
            if op == 0b101: # out
                self.outbuf.append(self._combo(self.mem[self.pc]) & 0b111)
                self.pc += 1
            if op == 0b110: # bdv
                self.reg[1] = self.reg[0] // (2**self._combo(self.mem[self.pc]))
                self.pc += 1
            if op == 0b111: # cdv
                self.reg[2] = self.reg[0] // (2**self._combo(self.mem[self.pc]))
                self.pc += 1

    def _combo(self, c) -> int:
        if c == 0: return 0
        if c == 1: return 1
        if c == 2: return 2
        if c == 3: return 3
        if c == 4: return self.reg[0]
        if c == 5: return self.reg[1]
        if c == 6: return self.reg[2]
        raise RuntimeError()

    def flush(self, binfmt = False):
        if not binfmt:
            print(','.join(map(str, self.outbuf)))
        else:
            for o in self.outbuf:
                print(f"{o:03b},", end="")
            print()

    def cmp(self, prog):
        return self.outbuf == prog


reg: array = array('q')
mem: list = []
pc: int = 0

with open('day17') as f:
    reg_a = int(re.match('Register A: ([0-9]+)', f.readline()).groups()[0])
    reg_b = int(re.match('Register B: ([0-9]+)', f.readline()).groups()[0])
    reg_c = int(re.match('Register C: ([0-9]+)', f.readline()).groups()[0])

    reg = array('q', [reg_a, reg_b, reg_c])

    f.readline()

    mem_str = re.match('Program: (.*)', f.readline()).groups()[0]

    for c in mem_str:
        if c == ',': continue
        mem.append(int(c))

# day 1

vm = VM(reg, mem, pc)
vm.run()
vm.flush()

# day 2

# enumerates all 3 bit number, then increases size by one
# enumerates them again

# -> we can find first boundaries by getting numbers where
# output buffer length is too small or too large

# but first we need to find where to even start
# we know the reg_a from the puzzle input is
# too small, but start from here and increas rapidly:

reg_a = 17323786
while True:
    reg = array('q', [reg_a, reg_b, reg_c])
    vm = VM(reg, mem, pc)
    vm.run(abort=len(mem))
    if vm.cmp(mem): break

    if len(mem) == len(vm.outbuf): break

    reg_a *= 10


print(reg_a)
vm.flush()

# we get: 173237860000000
# producing a program: 4,4,4,4,1,6,0,0,0,2,1,0,0,1,3,0
# that's exactly the length we want

# let's find our first set of boundaries so we can start a search
known_bytes = vm.outbuf[-2:]
init_reg_a = reg_a
upper_bound = -1
lower_bound = -1

reg_a = init_reg_a
while True:
    reg = array('q', [reg_a, reg_b, reg_c])
    vm = VM(reg, mem, pc)
    vm.run(abort=len(mem))
    if vm.cmp(mem): break

    if len(vm.outbuf) > len(mem):
        upper_bound = reg_a
        break

    reg_a *= 10


print(reg_a)
vm.flush()

reg_a = init_reg_a
while True:
    reg = array('q', [reg_a, reg_b, reg_c])
    vm = VM(reg, mem, pc)
    vm.run(abort=len(mem))
    if vm.cmp(mem): break

    if len(vm.outbuf) < len(mem):
        lower_bound = reg_a
        break

    reg_a //= 10


print(reg_a)
vm.flush()


# that was fast again and did not produce very enlightening bounds,
# nevertheless we have bounds:
#
# ub: 1732378600000000
# out: 4,4,0,7,0,7,6,0,3,5,1,5,4,2,4,4,2
#
# mid: 173237860000000
# out: 4,4,4,4,1,6,0,0,0,2,1,0,0,1,3,0
#
# lb: 17323786000000
# out: 4,4,5,5,5,0,1,4,6,4,4,4,7,3,7


# helper function
def cmp_bytes(a,b):
    if len(a) != len(b): return []

    same = []
    for i in range(1, len(a)):
        if a[-i] == b[-i]:
            same.append(a[-i])
            continue
        break

    same.reverse()
    return same

# params for our algorithm to tune
generation = 1
population = 1
mu = 173237860000000 # current best guess
mu_hit = 2 # correct positions of mu
mu_len = 16
sd = 171505481400000 # standard deviation, (up-low)*0.1 - I pulled that out of my nose
lo = 17323786000000 # lower bound
lo_hit = 0
lo_len = 15
up = 1732378600000000 # upper bound
up_hit = 0
up_len = 17


from day17_truncnorm import Truncnorm
truncnorm = Truncnorm(mu, sd, lo, up)

import random

prodigy = mu
prodigy_hit = mu_hit
prodigy_len = mu_len

mus = [(mu, mu_hit, mu_len)]

evolve = True
while evolve:
    # each generation we birth 10000 kin. The new generation's genes center
    # around the best produced offsprings so far. However, we allow for
    # mutations with decreasing likelihood the more deformed the kin would be.
    #
    # The mutations are bounded. Mutations outside these bounds lead to
    # a miscarriage.
    #
    # With each generation we re-asses and adapt our parameters.
    #
    # Occasionally a catastrophic event happens erasing the whole
    # popluation. This hopefully prevents us from being trapped in a
    # local optima.
    #
    # To preserve their legacy during these catastrophic events the mu
    # collect and freeze prodigies - the most promising genes they
    # know.
    #
    # All this allows us to search a search space probabilistically which
    # would be way too large to search exhaustively.

    catastrophy = random.randint(0,100)
    if catastrophy % 10 == 0:
        mus.append((mu, mu_hit, mu_len))
        print(f"\033[31mA catastrophy erased the entire population. Not all is lost, a new {prodigy=} awakes.\033[0m")
        mu = prodigy
        mu_hit = prodigy_hit
        mu_len = prodigy_len
        print(f"\033[31mIn a last attempt to preserve their culture the best known mus are engraved in a stone wall:\033[0m {mus=}")
        sd = round(random.uniform(0.00001, 1.0)*(up-lo))
        print(f"\033[31mEvolution restarts with {sd=}\033[0m")
        population += 1
        generation = 1

    print(f"\033[35mGeneration {generation} (Population {population}):\033[0m {mu=}, {sd=}, {lo=}, {up=}")


    for kin in truncnorm.draw(30000):
        kin = round(kin)

        reg = array('q', [kin, reg_b, reg_c])
        vm = VM(reg, mem, pc)
        vm.run()

        if len(cmp_bytes(vm.outbuf, mem))>mu_hit:
            mu = kin
            mu_hit = len(cmp_bytes(vm.outbuf, mem))
            mu_len = len(vm.outbuf)
            print(f"\033[32mFound new best kin: {mu=}, {mu_hit=}\033[0m", end=" ")
            vm.flush()
            continue

        if len(cmp_bytes(vm.outbuf, mem))==mu_hit and kin<mu:
            mu = kin
            mu_hit = len(cmp_bytes(vm.outbuf, mem))
            mu_len = len(vm.outbuf)
            print(f"\033[32mFound new best kin: {mu=}, {mu_hit=}\033[0m", end=" ")
            vm.flush()
            continue

        if kin < mu and kin < prodigy and len(cmp_bytes(vm.outbuf, mem)) > 3:
            prodigy = kin
            prodigy_hit = len(cmp_bytes(vm.outbuf, mem))
            prodigy_len = len(vm.outbuf)
            print(f"Found new prodigy: {prodigy=}, {prodigy_hit=}", end=" ")
            vm.flush()

        if len(vm.outbuf) < mu_len and kin>lo:
            lo = kin
            lo_hit = len(cmp_bytes(vm.outbuf, mem))
            lo_len = len(vm.outbuf)
            print(f"Found new lower bound: {lo}, {lo_hit=}, {lo_len=}", end=" ")
            vm.flush()
            continue

        if len(vm.outbuf) > mu_len and kin<up:
             up = kin
             up_hit = len(cmp_bytes(vm.outbuf, mem))
             up_len = len(vm.outbuf)
             print(f"Found new upper bound: {up}, {up_hit=}, {up_len=}", end=" ")
             vm.flush()
             continue

        assert(lo < mu)
        assert(mu < up)


    sd = sd//generation
    if sd<100:
        sd = round(random.uniform(0.00001, 1.0)*(up-lo))
        print(f"\033[36mA fungus infected the generation and changed mutations. New mutation with {sd=}\033[0m")

    print(f"{sd=}")
    truncnorm = Truncnorm(mu, sd, lo, up)
    generation += 1

# we evolved to a species capable of genetic engineering the very best
# prodigy we found is 164278764924544. We even found that multiple
# times. Now brute force ourselves to the top of the food chain.
#
# Our probabilistic algorithm is good a finding a a very good solution
# (up to 15 elements correct) but it is actually bad at pinpointing
# the exactly best solution.

mu = 164278764924544
for breed in range(mu-(2**(5*3)), mu+(2**(5*3))):
    reg = array('q', [breed, reg_b, reg_c])
    vm = VM(reg, mem, pc)
    vm.run()

    if vm.cmp(mem):
        print(f"Self replicating {breed=}")
        vm.flush()

print(reg_a)
vm.flush()