# Publication year range: 2015 to 2024
# Paper allocation per year: {2015: 80, 2016: 80, 2017: 80, 2018: 80, 2019: 80, 2020: 80, 2021: 80, 2022: 80, 2023: 80, 2024: 80}
# Selected 736 papers in total
# Saved selected papers to /home/ubuntu/50T/fsy/top_cited_papers_2015_2024.json
# Selected papers per year:
# 2015: 80
# 2016: 80
# 2017: 80
# 2018: 80
# 2019: 80
# 2020: 80
# 2021: 80
# 2022: 80
# 2023: 80
# 2024: 16
# 挑选高引论文
import json
import os
from collections import defaultdict
import pandas as pd
from tqdm import tqdm

def process_json_file(input_file, output_file):
    print(f"Reading JSON file: {input_file}")
    
    # 读取JSON文件
    with open(input_file, 'r', encoding='utf-8') as f:
        data = json.load(f)
        print(f"Loaded {len(data)} records from JSON array")
    
    # 统计发表年份范围
    min_year = float('inf')
    max_year = float('-inf')
    
    # 5-2024年每年的论文，按引用量排序
    yearly_papers = defaultdict(list)
    
    for paper in tqdm(data, desc="Processing papers"):
        pub_year = paper.get("Publication Year")
        if pub_year is None:
            continue
        
        try:
            year = int(pub_year)
            min_year = min(min_year, year)
            max_year = max(max_year, year)
            
            # 只关注2015-2024年间的论文
            if 2015 <= year <= 2024:
                # 获取引用量
                citations = paper.get("Times Cited, All Databases")
                if citations is None:
                    citations = paper.get("Times Cited, WoS Core")
            
                yearly_papers[year].append((citations, paper))

        except (ValueError, TypeError):
            # 如果年份无法转换为整数，跳过
            pass
    print(f"Publication year range: {min_year} to {max_year}")
    
    # 计算每年应该选择的论文数量
    total_papers = 800
    years = list(range(2015, 2025))  # 2015 到 2024
    papers_per_year = total_papers // len(years)
    remainder = total_papers % len(years)
    
    # 分配每年的论文数量
    allocation = {year: papers_per_year for year in years}
    for year in years[:remainder]:
        allocation[year] += 1
    
    print(f"Paper allocation per year: {allocation}")
    
    # 选择每年引用量最高的论文
    selected_papers = []
    for year in years:
        # 按引用量排序
        yearly_papers[year].sort(key=lambda x: x[0], reverse=True)
        # 选择指定数量的论文
        top_papers = yearly_papers[year][:allocation[year]]
        selected_papers.extend([paper for _, paper in top_papers])
    
    print(f"Selected {len(selected_papers)} papers in total")
    
    # 保存到新的JSON文件
    with open(output_file, 'w', encoding='utf-8') as f:
        json.dump(selected_papers, f, ensure_ascii=False, indent=2)
    
    print(f"Saved selected papers to {output_file}")
    
    # 输出每年选择的论文数量统计
    selected_count = {year: 0 for year in years}
    for paper in selected_papers:
        year = int(paper["Publication Year"])
        selected_count[year] += 1
    
    print("Selected papers per year:")
    for year in years:
        print(f"{year}: {selected_count[year]}")

if __name__ == "__main__":
    input_file = "/home/ubuntu/50T/fsy/paper-mat.json"  # 替换为你的输入文件名
    output_file = "/home/ubuntu/50T/fsy/top_cited_papers_2015_2024.json"
    
    process_json_file(input_file, output_file)