import re
import pandas as pd

def parse_text_file(text):
    # セクションを分割するための正規表現パターンを定義
    # \d+ は1つ以上の数字にマッチします
    pattern = re.compile(r'\n\n\n\d+\.')

    # テキストをセクションごとに分割
    sections = pattern.split(text)[1:]  # 最初の空のセクションを除外

    # 各セクションの前後の空白を削除
    sections = [section.strip() for section in sections]

    return sections

def split_sections(text):
    contents = text.split('\n\n')
    contents = [section.strip() for section in contents if section.strip()]
    if len(contents) == 8 :
        keys = ['PublishInfo', 'Title', 'AuthorName', 'AuthorInfo', 'Abstract', 'Copyrights', 'DOI', 'COI']
    elif len(contents) == 7 :
        keys = ['PublishInfo', 'Title', 'AuthorName', 'AuthorInfo', 'Abstract', 'Copyrights', 'DOI']
    elif len(contents) == 6:
        keys = ['PublishInfo', 'Title', 'AuthorName', 'AuthorInfo', 'Abstract', 'DOI']
    elif len(contents) == 5:
        keys = ['PublishInfo', 'Title', 'AuthorName', 'Abstract', 'DOI']
    
    # 辞書を作成し、キーが存在しない場合は空の文字列を設定
    section_dict = {key: contents[i] if i < len(contents) else "" for i, key in enumerate(keys)}
    return section_dict


def GetSummaryDf(textdir):
    with open(textdir, 'r', encoding='utf-8') as f:
        content = f.read()
    sections = parse_text_file(content)
    dicts = []
    for section in sections:
        splited_dic = split_sections(section)
        dicts.append(splited_dic)
    return pd.DataFrame(dicts)