from shared import identify, extract_ngram_freqs, TOP_NGRAM_COUNT

import itertools

TOP_NGRAM_COUNT = 5000

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()}

class Sample:

	def __init__(self, language="??", text=""):

		self.language = language

		self.frequencies = dict()

		self._ranked_ngrams = dict()

		if text:

			self._extract(text)

	def _extract(self, text):

		for k in range(1, 4):

			self.frequencies.update(extract_ngram_freqs(text, k))

	@property

	def ranked_ngrams(self):

		if not self._ranked_ngrams:

			ordered_ngrams = sorted(self.frequencies.items(), key=lambda kv: -kv[1])[:TOP_NGRAM_COUNT]

			self._ranked_ngrams = dict(zip([key for (key, freq) in ordered_ngrams], itertools.count(0)))

		return self._ranked_ngrams

	def compare(self, other):

		"""take k most common

		use frequencies x order

		use letter, digrams, trigrams

		use absolute x square"""

		"""make a set difference of keys, multiply its size by the max score"""

		res = sum(abs(v-other.ranked_ngrams.get(k, len(other.ranked_ngrams))) for (k, v) in self.ranked_ngrams.items()) + \

					sum(abs(v-self.ranked_ngrams.get(k, len(self.ranked_ngrams))) for (k, v) in other.ranked_ngrams.items())

		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()

def identify(text, models):

	sample = Sample(text=text)

	return sorted(models, key=lambda m: m.compare(sample))[0].language