''' 
   Estimate a user's vocabulary level given his vocabulary data
   Estimate an English article's difficulty level given its content
   Preliminary design
   
   Hui, 2024-09-23
   Last upated: 2024-09-25, 2024-09-30
'''

import pickle


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


_TEST_MOCK = {
    'simple': 2, 'apple': 1, 'happy': 2, 'open': 3, 'like': 2, 'work': 2, 'make': 2, 'money': 2,
    'source': 3, 'software': 3, 'successful': 4, 'project': 3, 'develop': 3, 'process': 3,
    'available': 4, 'organizations': 4,
    'extinct': 6, 'modification': 7, 'apparently': 7, 'abruptly': 7, 'rentable': 7, 'predictable:': 6,
    'pasture': 7, 'putrid': 7, 'frivolous': 8, 'sessile': 8, 'dearth': 7, 'presumptuous': 7,
    'fringe': 8, 'economics': 5, 'summarize': 5, 'stare': 5, 'eagerly': 5, 'completely': 4, 'maintained,': 5,
    'geological': 6, 'embryological': 7, 'coadaptation': 8, 'exterminated': 7, 'contingencies': 7,
    'intercrossing': 6, 'coleopterous': 8, 'marin': 5, 'organised': 5, 'monopoly': 8, 'inorganic': 7,
    'xyz': 0, '': 0
}


class VocabularyLevelEstimator:
    _test = _TEST_MOCK

    @property
    def level(self):
        total = 0.0
        valid_count = 0
        for word in self.word_lst:
            if word in self._test:
                total += self._test[word]
                valid_count += 1
        # if valid_count >= 40: total += 10
        print(f'valid_count: {valid_count}, total: {total}')
        if valid_count != 0 and total != 0: total += (valid_count * valid_count) / 100
        return total / valid_count if valid_count > 0 else 0


class UserVocabularyLevel(VocabularyLevelEstimator):
    def __init__(self, d):
        self.d = d
        self.word_lst = list(d.keys())
        # just look at the most recently-added words


class ArticleVocabularyLevel(VocabularyLevelEstimator):
    def __init__(self, content):
        self.content = content
        self.word_lst = content.lower().split()
        # select the 10 most difficult words


if __name__ == '__main__':
    d = load_record('frequency_mrlan85.pickle')
    print(d)
    user = UserVocabularyLevel(d)
    print(user.level)  # level is a property
    article = ArticleVocabularyLevel('This is an interesting article')
    print(article.level)