tables.py

import pandas as pd
from preprocess import split_sentences, split_words_from_text
from anal import analyze_text, analyze_word_length, analyze_punctuation, readability

# ТАБЛИЦА 1
def table_basic_stats(files):
    data = []
    for file in files:
        with open(file.name, 'r', encoding='utf-8') as f:
            text = f.read()
        
        # очистка
        from preprocess import clean_text
        cleaned = clean_text(text)
        
        # подсчёт символов
        char_count = len(cleaned.replace(' ', ''))
        
        # подсчёт слов и предложений
        sentences = split_sentences(text)
        words = split_words_from_text(text)
        word_count = len(words)
        sent_count = len(sentences)
        
        data.append({
            "Файл": file.name.split('/')[-1],  
            "Символы": char_count,
            "Слова": word_count,
            "Предложения": sent_count
        })
    
    return pd.DataFrame(data)

# ТАБЛИЦА 2
def table_avg_stats(files):
    data = []
    for file in files:
        with open(file.name, 'r', encoding='utf-8') as f:
            text = f.read()
        
        word_count, avg_word_len = analyze_word_length(text)
        _, avg_sent_len, disp, _ = analyze_text(text)
        
        data.append({
            "Файл": file.name.split('/')[-1],
            "Ср. длина слова": round(avg_word_len, 2),
            "Ср. длина предложения": round(avg_sent_len, 2),
            "Дисперсия": round(disp, 2)
            # строка с индексом удобочитаемости удалена
        })
    
    return pd.DataFrame(data)

# ТАБЛИЦА 3
def table_punctuation(files):
    # список знаков
    all_puncts = set()
    file_data = []
    
    for file in files:
        with open(file.name, 'r', encoding='utf-8') as f:
            text = f.read()
        
        counts, _ = analyze_punctuation(text)
        all_puncts.update(counts.keys())
        file_data.append((file.name.split('/')[-1], counts))
    
    # порядок
    punct_order = [
    '.', ',', ';', ':', '!', '?', '...',
    '—', '-',
    '()', '[]', '{}', '<>', '⟨⟩',
    '«»', '“”', '„“', '‹›', '""', "''",
    "'", '"'
    ]
    sorted_puncts = [p for p in punct_order if p in all_puncts]

    data = []
    for file_name, counts in file_data:
        row = {"Файл": file_name}
        for p in sorted_puncts:
            row[p] = counts.get(p, 0)
        data.append(row)
    
    return pd.DataFrame(data)

# ТАБЛИЦА 4
def table_readability(files):
    data = []
    for file in files:
        with open(file.name, 'r', encoding='utf-8') as f:
            text = f.read()
        
        read_score = readability(text)
        
        data.append({
            "Файл": file.name.split('/')[-1],
            "Индекс удобочитаемости": round(read_score, 2)
        })
    
    return pd.DataFrame(data)