import os

import re

import random

import itertools

random.seed(19181028)

TEST_LENS = [8, 16, 32, 64]

def preprocess(text):

	text = re.sub(r"[\W\d_]+", " ", " "+text+" ")

	return text.lower()

def extract_ngram_freqs(text, k):

	n = len(text)

	d = dict()

	for i in range(0, n-k+1):

		key = text[i:i+k]

		if key.isspace():

			continue

		d[key] = d.get(key, 0) + 1

	count = sum(d.values())

	return {key: val/count for (key, val) in d.items()}

def merge_ngram_freqs(freqs):

		if text:

			self._extract(text)

	def _extract(self, text):

		for k in range(1, 4):

			self.frequencies[k-1] = extract_ngram_freqs(text, k)

	@staticmethod

	def merge(samples):

		assert len({x.language for x in samples}) == 1

		res = Sample(samples[0].language)

		res.frequencies = []

		for freqs in zip(*(x.frequencies for x in samples)):

			res.frequencies.append(merge_ngram_freqs(freqs))

		return res

	def compare(self, other):

		"""take k most common

		use frequencies x order

		use letter, digrams, trigrams

		use absolute x square"""

		ranked_own_trigrams = dict(zip([key for (key, freq) in ordered_own_trigrams], itertools.count(0)))

		ranked_other_trigrams = dict(zip([key for (key, freq) in ordered_other_trigrams], itertools.count(0)))

		return res

	def print_overview(self):

		print(f"Sample({self.language}):")

		for freqs in self.frequencies:

			x = [

				(k, round(v, 3))

				for (k, v) in sorted(freqs.items(), key=lambda kv: -kv[1])

			]

			print("  ", x[:8], "...", x[-8:])

		print()

class SampleSet:

	def __init__(self, language):

		self.language = language

		self.texts = []

		self.samples = []

	def add(self, text):

		self.texts.append(text)

		self.samples.append(Sample(self.language, text))