import pickle
import math
import snowballstemmer
from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order, map_percentages_to_levels


class VocabularyLevelEstimator:
    def __init__(self):
        self.ENGLISH_WORD_DIFFICULTY_DICT = {}

    def load_record(self, pickle_fname):
        with open(pickle_fname, 'rb') as f:
            return pickle.load(f)

    def convert_test_type_to_difficulty_level(self, d):
        """
        对原本的单词库中的单词进行难度评级
        :param d: 存储了单词库pickle文件中的单词的字典
        :return:
        """
        result = {}
        L = list(d.keys())

        for k in L:
            if 'CET4' in d[k]:
                result[k] = 4
            elif 'OXFORD3000' in d[k]:
                result[k] = 5
            elif 'CET6' in d[k] or 'GRADUATE' in d[k]:
                result[k] = 6
            elif 'OXFORD5000' in d[k] or 'IELTS' in d[k]:
                result[k] = 7
            elif 'BBC' in d[k]:
                result[k] = 8

        self.ENGLISH_WORD_DIFFICULTY_DICT = result
        return result

    def get_difficulty_level_for_user(self, d1, d2):
        if not self.ENGLISH_WORD_DIFFICULTY_DICT:
            d2 = self.convert_test_type_to_difficulty_level(d2)
        else:
            d2 = self.ENGLISH_WORD_DIFFICULTY_DICT

        stemmer = snowballstemmer.stemmer('english')

        for k in d1:
            if k in d2:
                continue
            else:
                stem = stemmer.stemWord(k)
                if stem in d2:
                    d2[k] = d2[stem]
                else:
                    d2[k] = 3
        return d2

    def revert_dict(self, d):
        d2 = {}
        for k in d:
            lst = d[k] if isinstance(d[k], list) else d[k] * ['2021082019']
            for time_info in lst:
                date = time_info[:10]
                if date not in d2:
                    d2[date] = [k]
                else:
                    d2[date].append(k)
        return d2

    def user_difficulty_level(self, d_user, d, calc_func=0):
        if calc_func != 0:
            d_user2 = self.revert_dict(d_user)
            geometric = 0
            count = 0
            for date in sorted(d_user2.keys(), reverse=True):
                lst = d_user2[date]
                lst2 = [(word, d[word]) for word in lst if word in d]
                lst3 = sort_in_ascending_order(lst2)

                for t in lst3:
                    word = t[0]
                    hard = t[1]
                    geometric += math.log(hard)
                    count += 1
            return math.exp(geometric / max(count, 1))

        d_user2 = self.revert_dict(d_user)
        count = {}
        percentages = {}
        total = 0
        for date in d_user2.keys():
            lst = d_user2[date]
            for word in lst:
                if word in d:
                    count[d[word]] = count.get(d[word], 0) + 1
                    total += 1

        if total == 0:
            return 1

        for k in count.keys():
            percentages[k] = count[k] / total

        weight = map_percentages_to_levels(percentages)
        sum_ = sum(weight[k] * k for k in weight.keys())
        return sum_

    def text_difficulty_level(self, s, d):
        s = remove_punctuation(s)
        L = freq(s)

        lst = []
        stop_words = {'the': 1, 'and': 1, 'of': 1, 'to': 1, 'what': 1, 'in': 1, 'there': 1, 'when': 1, 'them': 1, 'would': 1, 'will': 1, 'out': 1, 'his': 1, 'mr': 1, 'that': 1, 'up': 1, 'more': 1, 'your': 1, 'it': 1, 'now': 1, 'very': 1, 'then': 1, 'could': 1, 'he': 1, 'any': 1, 'some': 1, 'with': 1, 'into': 1, 'you': 1, 'our': 1, 'man': 1, 'other': 1, 'time': 1, 'was': 1, 'than': 1, 'know': 1, 'about': 1, 'only': 1, 'like': 1, 'how': 1, 'see': 1, 'is': 1, 'before': 1, 'such': 1, 'little': 1, 'two': 1, 'its': 1, 'as': 1, 'these': 1, 'may': 1, 'much': 1, 'down': 1, 'for': 1, 'well': 1, 'should': 1, 'those': 1, 'after': 1, 'same': 1, 'must': 1, 'say': 1, 'first': 1, 'again': 1, 'us': 1, 'great': 1, 'where': 1, 'being': 1, 'come': 1, 'over': 1, 'good': 1, 'himself': 1, 'am': 1, 'never': 1, 'on': 1, 'old': 1, 'here': 1, 'way': 1, 'at': 1, 'go': 1, 'upon': 1, 'have': 1, 'had': 1, 'without': 1, 'my': 1, 'day': 1, 'be': 1, 'but': 1, 'though': 1, 'from': 1, 'not': 1, 'too': 1, 'another': 1, 'this': 1, 'even': 1, 'still': 1, 'her': 1, 'yet': 1, 'under': 1, 'by': 1, 'let': 1, 'just': 1, 'all': 1, 'because': 1, 'we': 1, 'always': 1, 'off': 1, 'yes': 1, 'so': 1, 'while': 1, 'why': 1, 'which': 1, 'me': 1, 'are': 1, 'or': 1, 'no': 1, 'if': 1, 'an': 1, 'also': 1, 'thus': 1, 'who': 1, 'cannot': 1, 'she': 1, 'whether': 1}
        for x in L:
            word = x[0]
            if word not in stop_words and word in d:
                lst.append((word, d[word]))

        lst2 = sort_in_descending_order(lst)
        geometric = 1
        count = 0
        for t in lst2:
            word = t[0]
            hard = t[1]
            geometric *= hard
            count += 1
            if count >= 20:
                return geometric ** (1 / count)

        return geometric ** (1 / max(count, 1))