示例#1
0
    def analyze_text(self, text):
        words = get_words(text)
        char_count = get_char_count(words)
        word_count = len(words)
        sentence_count = len(get_sentences(text))
        syllable_count = count_syllables(words)
        complexwords_count = count_complex_words(text)
        avg_words_p_sentence = word_count / sentence_count

        self.analyzedVars = {
            'words': words,
            'char_cnt': float(char_count),
            'word_cnt': float(word_count),
            'sentence_cnt': float(sentence_count),
            'syllable_cnt': float(syllable_count),
            'complex_word_cnt': float(complexwords_count),
            'avg_words_p_sentence': float(avg_words_p_sentence)
        }

        outData = {
            'char_cnt': float(char_count),
            'word_cnt': float(word_count),
            'sentence_cnt': float(sentence_count),
            'syllable_cnt': float(syllable_count),
            'complex_word_cnt': float(complexwords_count),
            'avg_words_p_sentence': float(avg_words_p_sentence)
        }
        return outData
    def analyze_text(self, text):
        words = get_words(text)
        char_count = int(get_char_count(words))
        word_count = int(len(words))
        sentences = get_sentences(text)
        len_sentences = len(sentences)
        sentence_count = int(len_sentences)
        # sentence_count = int(len(get_sentences(text)))
        syllable_count = count_syllables(words)
        complexwords_count = count_complex_words(text.decode('utf-8'))
        avg_words_p_sentence = word_count / sentence_count
        encoding_dict = detect_encoding(self.filename)

        self.analyzedVars = {
            'filename': self.filename,
            # 'text_truncated': text[:200].replace("\n", " "),
            'words': words,
            'char_cnt': float(char_count),
            'word_cnt': float(word_count),
            'sentence_cnt': float(sentence_count),
            'syllable_cnt': float(syllable_count),
            'complex_word_cnt': float(complexwords_count),
            'avg_words_p_sentence': float(avg_words_p_sentence),
            'encoding': encoding_dict['encoding'],
            'encoding_confidence': encoding_dict['confidence']
        }
示例#3
0
    def analyze_text(self, text):
        words = get_words(text)
        char_count = get_char_count(words)
        word_count = len(words)
        sentence_count = len(get_sentences(text))
        syllable_count = count_syllables(words)
        complexwords_count = count_complex_words(text)
        avg_words_p_sentence = word_count/sentence_count

        self.analyzedVars = {
            'words': words,
            'char_cnt': float(char_count),
            'word_cnt': float(word_count),
            'sentence_cnt': float(sentence_count),
            'syllable_cnt': float(syllable_count),
            'complex_word_cnt': float(complexwords_count),
            'avg_words_p_sentence': float(avg_words_p_sentence)
        }
示例#4
0
 def analyze_text(self, text):
     words = get_words(text)
     char_count = get_char_count(words)
     words_count = len(words)
     sentence_count = len(get_sentences(text))
     syllable_count = count_syllables(words)
     print("syllable_count:", syllable_count)
     complex_words_count = count_complex_words(text)
     avg_words_per_sentence = int(words_count / sentence_count)
     print("avg_words_per_sentence", avg_words_per_sentence)
     self.ana_vars = {
         'words': words,
         'char_count': float(char_count),
         'words_count': float(words_count),
         'sentence_count': float(sentence_count),
         'syllable_count': float(syllable_count),
         'complex_words_count': float(complex_words_count),
         'avg_words_per_sentence': float(avg_words_per_sentence)
     }
    def analyze_text(self, text):
        words = get_words(text)
        char_count = int(get_char_count(words))
        word_count = int(len(words))
        sentence_count = int(len(get_sentences(text)))
        syllable_count = count_syllables(words)
        complexwords_count = count_complex_words(text)
        avg_words_p_sentence = word_count / sentence_count

        self.analyzedVars = {
            'filename': self.filename,
            # 'text_truncated': text[:200].replace("\n", " "),
            'words': words,
            'char_cnt': float(char_count),
            'word_cnt': float(word_count),
            'sentence_cnt': float(sentence_count),
            'syllable_cnt': float(syllable_count),
            'complex_word_cnt': float(complexwords_count),
            'avg_words_p_sentence': float(avg_words_p_sentence)
        }