import os

import re

import random

import itertools

random.seed(19181028)

TEST_LENS = [8, 16, 32, 64]

TOP_TRIGRAM_COUNT = 6000

def preprocess(text):

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

	return text.lower()

def extract_ngram_freqs(text, k):

	n = len(text)

	d = dict()

	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))

	def create_model(self):

		return Sample.merge(self.samples)

			yield (text, Sample.merge([x for x in self.samples if x is not sample]))

def cross_validate(sample_sets):

	models = [s.create_model() for s in sample_sets]

	score = 0

	max_score = 0

	for s in sample_sets:

			real_lang = partial_model.language

			test_models = [partial_model] + [m for m in models if m.language != real_lang]

			for k in TEST_LENS:

				for i in range(10):

					j = random.randrange(0, len(test_text)-k)

					t = test_text[j:j+k]

					predicted_lang = identify(t, test_models)

					if predicted_lang == real_lang:

						score += 1

					else:

						print(real_lang, predicted_lang, t)

if __name__ == "__main__":

	samples = []

	for d in LANG_DIRS:

		lang = os.path.basename(d)

		lang_samples = SampleSet(lang)

		samples.append(lang_samples)

		for file in sorted(os.scandir(d), key=lambda f: f.name):

			with open(file) as f:

				text = f.read()

				text = preprocess(text)

				lang_samples.add(text)

	print(cross_validate(samples))