zhengxinhan restructure niuren and ccfa scripts

papertools_niuren_ccfa/README.md

+# 使用方法
+
+修改`main.py`中的`input_file_path`和`output_file_path`
+
+输出的excel中包含`牛人`，`牛人署名顺序`和`疑似牛人`三列。其中疑似牛人的格式为 `疑似牛人名字(疑似牛人在info/new_niuren_format-merged_turing.csv中的索引)`。
+请初步判断是否为牛人。如果认为是牛人，则找李慧老师复核，由李慧老师添加到全局牛人表中。请不要修改全局牛人表。
+
+如果是脚本运行相关的问题，请联系马天云同学。
\ No newline at end of file

papertools_niuren_ccfa/if_ccfa.py

+"""
+功能：判断论文是否属于CCF-A类会议
+输入文件：CCF_A_list.csv，包含两列：abbr,fullname
+输入文件：info/论文被引用统计-陈老师-截止2025年X月XX日.xlsx
+输出文件：处理后的Excel文件，保持原格式不变，添加是否CCF-A信息
+"""
+import os
+import pandas as pd
+import re
+from rapidfuzz import fuzz, process
+from collections import defaultdict
+import openpyxl
+from copy import copy
+
+# 路径参数
+input_file_path = "info/论文被引用统计-陈老师-截止2025年X月XX日.xlsx"
+output_file_path = "output/论文被引用统计-陈老师-截止2025年X月XX日-CCFA标记.xlsx"
+ccf_a_file = "info/CCF_A_list.csv"  # 请根据实际路径调整
+
+# 读取CCF-A简称和全称
+ccf_a = pd.read_csv(ccf_a_file)
+# 缩写全部去空格
+ccf_a_abbrs = set(ccf_a['abbr'].dropna().str.lower().str.replace(' ','').str.strip().tolist())
+ccf_a_fullnames = set(ccf_a['fullname'].dropna().str.lower().str.strip().tolist())
+ccf_a_names = ccf_a_abbrs | ccf_a_fullnames
+
+def clean_venue(venue):
+    if pd.isnull(venue) or str(venue).strip() == "":
+        return ""
+    text = str(venue)
+    text = re.sub(r'[\(\（][^)\）]*?volume[^)\）]*?[\)\）]', '', text, flags=re.IGNORECASE)
+    text = re.sub(r"[0-9'\",\.\!\/\\\?\;\-\_]", "", text)
+    return text.lower().strip()
+
+def extract_brackets(text):
+    match = re.search(r'[\(\（](.*?)[\)\）]', text)
+    if match:
+        return match.group(1).strip().lower()
+    return None
+
+def extract_before_colon(text):
+    parts = re.split(r'[:：]', text)
+    if len(parts) > 1:
+        return parts[0].strip().lower()
+    return None
+
+def is_ccf_a(venue, threshold=70):
+    if pd.isnull(venue) or str(venue).strip() == "":
+        return 0
+    venue_clean = venue.lower().strip()
+
+    if 'south pacific design automation conference' in venue_clean:
+        return 0
+    
+    if 'International Journal' in venue_clean and ('Computer Vision' not in venue_clean or 'Human-Computer Studies' not in venue_clean):
+        return 0
+    
+    if 'ieee micro' in venue_clean or 'design automation conference' in venue_clean or 'ieee transactions on parallel & distributed systems' in venue_clean or 'ieee transactions on computers' in venue_clean or 'transactions on architecture and code optimization' in venue_clean or '信息科学' in venue_clean or 'pldi' in venue_clean or 'transactions on computer systems' in venue_clean or 'conference on computer vision and pattern recognition' in venue_clean or 'transactions on computeraided design of integrated circuits and systems' in venue_clean or 'aaai conference on artificial intelligence' in venue_clean or 'mm ' in venue_clean or 'transactions on parallel and distributed systems' in venue_clean:
+        return 1
+    
+    if 'ijcnn' in venue_clean or 'iccd' in venue_clean or 'icpr' in venue_clean or 'aicas' in venue_clean or 'acm transactions on embedded computing systems' in venue_clean or 'iccad' in venue_clean or 'artificial intelligence review' in venue_clean or 'ieee journal of selected topics in quantum electronics' in venue_clean or 'future generation computer systems' in venue_clean or 'ieee transactions on services computing' in venue_clean or 'ipdps' in venue_clean or 'isocc' in venue_clean or 'microprocessors and microsystems' in venue_clean or 'ccet' in venue_clean or 'microelectronics' in venue_clean or 'asid' in venue_clean or 'caai' in venue_clean or 'euromicro conference on' in venue_clean or 'asicon' in venue_clean or 'transactions on system and lsi design methodology' in venue_clean or 'selected areas in communications' in venue_clean or 'high performance computing data and analytics' in venue_clean or 'innovation communication and engineering' in venue_clean or 'sysml conference' in venue_clean or 'international conference on digital signal processing' in venue_clean or 'international conference on computer and communication systems' in venue_clean or 'ieee transactions on services computing' in venue_clean or 'international symposium on performance analysis of systems and software' in venue_clean or 'wireless communications and mobile computing' in venue_clean or 'sigops operating systems review' in venue_clean or 'siggraphasia' in venue_clean or 'international journal of computational intelligence systems' in venue_clean or 'journal of ikeee' in venue_clean or 'artificial intelligence and security' in venue_clean or 'journal of software' in venue_clean or 'advances in artificial intelligence' in venue_clean or 'international symposium on networksonchip' in venue_clean or 'international journal of web information systems' in venue_clean or 'journal of timecritical computing systems' in venue_clean or 'journal of advanced computer science and applications' in venue_clean or 'conference on computing and informatics' in venue_clean or 'journal of big data' in venue_clean or 'journal of parallel programming' in venue_clean or 'international conference on computer and communications' in venue_clean or 'journal of supercomputing' in venue_clean or 'conference on computing frontiers' in venue_clean or 'international conference on industry applications' in venue_clean or 'artificial intelligence advances' in venue_clean or 'pattern recognition and artificial intelligence' in venue_clean or 'journal of electronics and communications' in venue_clean or 'journal of data science and analytics' in venue_clean or 'journal of parallel emergent and distributed systems' in venue_clean or 'conference on advances in electrical engineering' in venue_clean or 'international conference on frontiers in computing and systems' in venue_clean or 'conference on sentiment analysis and deep learning' in venue_clean or 'acm symposium on cloud computing' in venue_clean or 'conference on tools with artificial intelligence' in venue_clean or 'conference on supercomputing' in venue_clean or 'frontiers in artificial intelligence ' in venue_clean or 'conference on communication technology' in venue_clean or 'big data information and computer network' in venue_clean or 'conference on software engineering education and training' in venue_clean or 'journal of computers' in venue_clean or 'washington' in venue_clean or 'international conference on cloud computing' in venue_clean or 'acm on programming languages' in venue_clean or 'conference on high performance computing' in venue_clean or 'ubm designcon conference' in venue_clean or 'scientia sinica informationis' in venue_clean or 'symposium on computing and networking' in venue_clean or 'journal of mathematics' in venue_clean or 'iet image processing' in venue_clean or 'journal of computing and digital systems' in venue_clean or 'conference on very large scale integration' in venue_clean or 'journal of networking and computing' in venue_clean or 'transactions on cryptographic hardware and embedded systems' in venue_clean or 'International Conference on Hybrid Intelligent Systems' in venue_clean or 'international conference on asic' in venue_clean or 'international conference on nexgen technologies' in venue_clean or 'international conference on computer and information technology' in venue_clean or 'international journal of high performance systems architecture' in venue_clean or 'international conference on power and energy engineering' in venue_clean or 'international symposium on smart electronic systems' in venue_clean or 'international symposium on smart electronic systems' in venue_clean:
+        return 0
+    
+    # 特判 IEEE Transactions on 开头
+    if venue_clean.startswith("ieee transactions on") or venue_clean.startswith("ieee international conference on") or venue_clean.startswith("ccf transactions on") or venue_clean.startswith("engineering applications of") or venue_clean.startswith("acm transactions on") or venue_clean.startswith("international conference on") or venue_clean.startswith("ieice transactions on"):  
+        ccf_a_fullnames_clean = {clean_venue(name) for name in ccf_a_fullnames}
+        if venue_clean in ccf_a_fullnames_clean:
+            return 1
+        else:
+            return 0
+
+    # 1. 括号内简称匹配（只做去空格完全匹配）
+    bracket_content = extract_brackets(venue_clean)
+    if bracket_content:
+        bracket_content_no_space = bracket_content.replace(' ', '')
+        if bracket_content_no_space in ccf_a_abbrs:
+            return 1
+
+    # 2. 冒号前内容匹配（只做去空格完全匹配）
+    colon_content = extract_before_colon(venue_clean)
+    if colon_content:
+        colon_content_no_space = colon_content.replace(' ', '')
+        if colon_content_no_space in ccf_a_abbrs:
+            return 1
+
+    # 3. venue_clean整体匹配
+    if len(venue_clean) <= 6:
+        # 长度小于等于6，只做精确匹配
+        if venue_clean in ccf_a_names:
+            return 1
+        else:
+            return 0
+    else:
+        # 正常模糊匹配
+        if venue_clean in ccf_a_names:
+            return 1
+        result = process.extractOne(
+            venue_clean,
+            ccf_a_names,
+            scorer=fuzz.ratio
+        )
+        if result:
+            match, score, _ = result
+            if score >= threshold:
+                return 1
+            else:
+                return 0
+        else:
+            return 0
+
+if __name__ == "__main__":
+    # 读取表头（第4行作为列名）
+    original_header = pd.read_excel(input_file_path, nrows=0, header=3)
+    column_names = original_header.columns.tolist()
+    
+    # 读取数据（从第8行开始）
+    input_df = pd.read_excel(input_file_path, skiprows=7, header=None, names=column_names)
+    
+    # 输出表头和数据的基本信息
+    print("表头元素：")
+    print(column_names)
+    print("\n数据行数：", input_df.shape[0])
+    print("数据列数：", input_df.shape[1])
+    
+    # 检查是否存在期刊/会议名称列
+    venue_col_name = '期刊/会议名称'
+    if venue_col_name not in input_df.columns:
+        print(f"错误：找不到'{venue_col_name}'列")
+        exit(1)
+    
+    # 检查是否存在CCF-A列
+    ccfa_col_name = '是否是CCF-A'
+    if ccfa_col_name not in input_df.columns:
+        print(f"'{ccfa_col_name}'列不存在，将添加该列")
+        # 找出CCF-A列的合适位置（通常在期刊/会议名称列之后）
+        venue_col_index = list(input_df.columns).index(venue_col_name)
+        input_df.insert(venue_col_index + 1, ccfa_col_name, None)
+    
+    # 清理会议/期刊名称
+    input_df['venue_clean'] = input_df[venue_col_name].apply(clean_venue)
+    
+    # 创建会议名称到行索引的映射
+    venue_map = defaultdict(list)
+    for idx, row in input_df.iterrows():
+        venue_map[row['venue_clean']].append(idx)
+    
+    # 判断每个会议是否为CCF-A
+    venue_ccfa_dict = {}
+    for v_clean in venue_map:
+        venue_ccfa_dict[v_clean] = '是' if is_ccf_a(v_clean) else '否'
+        print(f'{v_clean} -> {venue_ccfa_dict[v_clean]}')
+    
+    # 更新CCF-A列
+    for venue, indices in venue_map.items():
+        is_ccfa = venue_ccfa_dict[venue]
+        for idx in indices:
+            input_df.at[idx, ccfa_col_name] = is_ccfa
+    
+    # 删除临时列
+    input_df.drop('venue_clean', axis=1, inplace=True)
+    
+    # 使用openpyxl保留原始Excel格式
+    import openpyxl
+    from copy import copy
+    
+    # 打开原始Excel文件
+    print("正在读取原始Excel文件以保留格式...")
+    wb_original = openpyxl.load_workbook(input_file_path)
+    
+    # 创建新工作簿
+    wb_new = openpyxl.Workbook()
+    # 删除默认创建的空白工作表
+    if 'Sheet' in wb_new.sheetnames:
+        del wb_new['Sheet']
+    
+    # 复制所有工作表
+    for sheet_name in wb_original.sheetnames:
+        ws_original = wb_original[sheet_name]
+        ws_new = wb_new.create_sheet(sheet_name)
+        
+        # 复制工作表属性 - 只复制存在的属性
+        if hasattr(ws_original, 'sheet_properties'):
+            ws_new.sheet_properties = copy(ws_original.sheet_properties)
+        if hasattr(ws_original, 'sheet_format'):
+            ws_new.sheet_format = copy(ws_original.sheet_format)
+        
+        # 复制整个工作表的内容和格式
+        for row in ws_original.rows:
+            for cell in row:
+                new_cell = ws_new.cell(row=cell.row, column=cell.column, value=cell.value)
+                if cell.has_style:
+                    if hasattr(cell, 'font'):
+                        new_cell.font = copy(cell.font)
+                    if hasattr(cell, 'border'):
+                        new_cell.border = copy(cell.border)
+                    if hasattr(cell, 'fill'):
+                        new_cell.fill = copy(cell.fill)
+                    if hasattr(cell, 'number_format'):
+                        new_cell.number_format = copy(cell.number_format)
+                    if hasattr(cell, 'protection'):
+                        new_cell.protection = copy(cell.protection)
+                    if hasattr(cell, 'alignment'):
+                        new_cell.alignment = copy(cell.alignment)
+        
+        # 复制合并单元格
+        if hasattr(ws_original, 'merged_cells'):
+            try:
+                for merged_cell_range in ws_original.merged_cells.ranges:
+                    ws_new.merge_cells(str(merged_cell_range))
+            except Exception as e:
+                print(f"警告: 复制合并单元格时出错: {e}")
+    
+    # 获取主工作表（第一个工作表）
+    main_sheet_name = wb_original.sheetnames[0]
+    ws_new = wb_new[main_sheet_name]
+    
+    # 更新主工作表中的CCF-A列
+    # 获取列索引
+    header_row = 4  # 第4行为列标题
+    venue_col_index = None
+    ccfa_col_index = None
+    
+    # 获取列标题行的所有单元格值
+    header_cells = {}
+    for cell in ws_new[header_row]:
+        header_cells[cell.column] = cell.value
+    
+    # 找出期刊/会议名称列和CCF-A列的索引
+    for col, value in header_cells.items():
+        if value == venue_col_name:
+            venue_col_index = col
+        elif value == ccfa_col_name:
+            ccfa_col_index = col
+    
+    # 如果找不到CCF-A列，在期刊/会议名称列后添加
+    if ccfa_col_index is None and venue_col_index is not None:
+        ccfa_col_index = venue_col_index + 1
+        
+        # 将后面的列向右移动一列
+        for row in range(1, ws_new.max_row + 1):
+            for col in range(ws_new.max_column, venue_col_index, -1):
+                cell = ws_new.cell(row=row, column=col)
+                cell.value = ws_new.cell(row=row, column=col-1).value
+                
+                # 复制样式
+                source_cell = ws_new.cell(row=row, column=col-1)
+                if source_cell.has_style:
+                    if hasattr(source_cell, 'font'):
+                        cell.font = copy(source_cell.font)
+                    if hasattr(source_cell, 'border'):
+                        cell.border = copy(source_cell.border)
+                    if hasattr(source_cell, 'fill'):
+                        cell.fill = copy(source_cell.fill)
+                    if hasattr(source_cell, 'number_format'):
+                        cell.number_format = copy(source_cell.number_format)
+                    if hasattr(source_cell, 'protection'):
+                        cell.protection = copy(source_cell.protection)
+                    if hasattr(source_cell, 'alignment'):
+                        cell.alignment = copy(source_cell.alignment)
+        
+        # 设置CCF-A列标题
+        ws_new.cell(row=header_row, column=ccfa_col_index, value=ccfa_col_name)
+    
+    # 更新CCF-A列的数据（从第8行开始）
+    if venue_col_index is not None and ccfa_col_index is not None:
+        for i, row in input_df.iterrows():
+            excel_row = i + 8  # 转换为Excel的行号（从1开始）
+            venue_value = ws_new.cell(row=excel_row, column=venue_col_index).value
+            
+            # 如果原始Excel中有会议名称，判断是否为CCF-A
+            if venue_value:
+                venue_clean = clean_venue(venue_value)
+                is_ccfa_value = venue_ccfa_dict.get(venue_clean, 0)
+                ws_new.cell(row=excel_row, column=ccfa_col_index, value=is_ccfa_value)
+    
+    # 保存新Excel文件
+    print(f"正在保存为Excel格式 {output_file_path} ...")
+    try:
+        wb_new.save(output_file_path)
+        print(f"成功保存到 {output_file_path}，保留了原始格式")
+    except Exception as e:
+        print(f"保存Excel失败: {e}")
+    
+    print("处理完成!")
\ No newline at end of file

papertools_niuren_ccfa/info/CCF_A_list.csv

+abbr,fullname
+PPoPP,"ACM SIGPLAN Symposium on Principles & Practice of Parallel Programming"
+FAST,"USENIX Conference on File and Storage Technologies"
+DAC,"Design Automation Conference"
+HPCA,"IEEE International Symposium on High Performance Computer Architecture"
+MICRO,"IEEE/ACM International Symposium on Microarchitecture"
+SC,"International Conference for High Performance Computing, Networking, Storage, and Analysis"
+ASPLOS,"International Conference on Architectural Support for Programming Languages and Operating Systems"
+ISCA,"International Symposium on Computer Architecture"
+USENIX ATC,"USENIX Annual Technical Conference"
+EuroSys,"European Conference on Computer Systems"
+SIGCOMM,"ACM International Conference on Applications, Technologies, Architectures, and Protocols for Computer Communication"
+MobiCom,"ACM International Conference on Mobile Computing and Networking"
+INFOCOM,"IEEE International Conference on Computer Communications"
+NSDI,"Symposium on Network System Design and Implementation"
+CCS,"ACM Conference on Computer and Communications Security"
+EUROCRYPT,"International Conference on the Theory and Applications of Cryptographic Techniques"
+S&P,"IEEE Symposium on Security and Privacy"
+CRYPTO,"International Cryptology Conference"
+USENIX Security,"USENIX Security Symposium"
+NDSS,"Network and Distributed System Security Symposium"
+PLDI,"ACM SIGPLAN Conference on Programming Language Design and Implementation"
+POPL,"ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages"
+FSE,"ACM International Conference on the Foundations of Software Engineering"
+SOSP,"ACM Symposium on Operating Systems Principles"
+OOPSLA,"Conference on Object-Oriented Programming Systems, Languages,and Applications"
+ASE,"International Conference on Automated Software Engineering"
+ICSE,"International Conference on Software Engineering"
+ISSTA,"International Symposium on Software Testing and Analysis"
+OSDI,"USENIX Symposium on Operating Systems Design and Implementations"
+FM,"International Symposium on Formal Methods"
+SIGMOD,"ACM SIGMOD Conference"
+SIGKDD,"ACM SIGKDD Conference on Knowledge Discovery and Data Mining"
+ICDE,"IEEE International Conference on Data Engineering"
+SIGIR,"International ACM SIGIR Conference on Research and Development in Information Retrieval"
+VLDB,"International Conference on Very Large Data Bases"
+STOC,"ACM Symposium on Theory of Computing"
+SODA,"ACM-SIAM Symposium on Discrete Algorithms"
+CAV,"International Conference on Computer Aided Verification"
+FOCS,"IEEE Annual Symposium on Foundations of Computer Science"
+LICS,"ACM/IEEE Symposium on Logic in Computer Science"
+ACM MM,"ACM International Conference on Multimedia"
+SIGGRAPH,"ACM Special Interest Group on Computer Graphics"
+VR,"IEEE Virtual Reality"
+IEEE VIS,"IEEE Visualization Conference"
+AAAI,"AAAI Conference on Artificial Intelligence"
+NeurIPS,"Conference on Neural Information Processing Systems"
+ACL,"Annual Meeting of the Association for Computational Linguistics"
+CVPR,"IEEE/CVF Computer Vision and Pattern Recognition Conference"
+ICCV,"International Conference on Computer Vision"
+ICML,"International Conference on Machine Learning"
+IJCAI,"International Joint Conference on Artificial Intelligence"
+CSCW,"ACM Conference on Computer Supported Cooperative Work and Social Computing"
+CHI,"ACM Conference on Human Factors in Computing Systems"
+UbiComp/IMWUT,"ACM international joint conference on Pervasive and Ubiquitous Computing/ Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"
+UIST,"ACM Symposium on User Interface Software and Technology"
+WWW,"International World Wide Web Conference"
+RTSS,"IEEE Real-Time Systems Symposium"
+WINE,"Conference on Web and Internet Economics"
+TOCS,"ACM Transactions on Computer Systems"
+TOS,"ACM Transactions on Storage"
+TCAD,"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"
+TC,"IEEE Transactions on Computers"
+TPDS,"IEEE Transactions on Parallel and Distributed Systems"
+TACO,"ACM Transactions on Architecture and Code Optimization"
+JSAC,"IEEE Journal on Selected Areas in Communications"
+TMC,"IEEE Transactions on Mobile Computing"
+TON,"IEEE/ACM Transactions on Networking"
+TDSC,"IEEE Transactions on Dependable and Secure Computing"
+TIFS,"IEEE Transactions on Information Forensics and Security"
+,"Journal of Cryptology"
+TOPLAS,"ACM Transactions on Programming Languages and Systems"
+TOSEM,"ACM Transactions on Software Engineering and Methodology"
+TSE,"IEEE Transactions on Software Engineering"
+TSC,"IEEE Transactions on Services Computing"
+TODS,"ACM Transactions on Database Systems"
+TOIS,"ACM Transactions on Information Systems"
+TKDE,"IEEE Transactions on Knowledge and Data Engineering"
+VLDBJ,"The VLDB Journal"
+TIT,"IEEE Transactions on Information Theory"
+IANDC,"Information and Computation"
+SICOMP,"SIAM Journal on Computing"
+TOG,"ACM Transactions on Graphics"
+TIP,"IEEE Transactions on Image Processing"
+TVCG,"IEEE Transactions on Visualization and Computer Graphics"
+AI,"Artificial Intelligence"
+TPAMI,"IEEE Transactions on Pattern Analysis and Machine Intelligence"
+IJCV,"International Journal of Computer Vision"
+JMLR,"Journal of Machine Learning Research"
+TOCHI,"ACM Transactions on Computer-Human Interaction"
+IJHCS,"International Journal of Human-Computer Studies"
+JACM,"Journal of the ACM"
+Proc. IEEE,"Proceedings of the IEEE"
+SCIS,"Science China Information Sciences"

papertools_niuren_ccfa/niurenpipei.py

+import os
+import sys
+os.chdir(os.path.dirname(__file__))
+import json
+import pandas as pd
+from tqdm import tqdm
+import openpyxl
+from copy import copy
+from joblib import Parallel, delayed
+from utils import standardized_name, name_in_niuren_list
+
+input_file_path = 'info/论文被引用统计-陈老师-截止2025年X月XX日.xlsx'
+output_file_path = 'output/论文被引用统计-陈老师-截止2025年X月XX日_牛人筛选.xlsx'
+
+output_dir = os.path.dirname(output_file_path)
+if not os.path.exists(output_dir):
+    os.makedirs(output_dir)
+
+niuren_pool_path = 'info/niuren_pool.csv'
+true_niuren_papers_path = 'info/true_niuren_papers'
+fake_niuren_papers_path = 'info/fake_niuren_papers'
+
+# 全局变量，存储加载的数据
+# NIUREN_POOL_NAMES = []
+# TRUE_NIUREN_NAMES = []
+# TRUE_NIUREN_PAPERS = []
+# FAKE_NIUREN_NAMES = []
+# FAKE_NIUREN_PAPERS = []
+
+def load_niuren_pool(niuren_pool_path):
+    niuren_pool = pd.read_csv(niuren_pool_path, encoding='utf-8-sig')
+    niuren_pool_names = niuren_pool["name"].tolist()
+    niuren_pool_names = [name.replace("\xa0", " ") for name in niuren_pool_names]  # 去除空格
+    return niuren_pool_names
+
+
+def load_true_niuren(true_niuren, true_niuren_papers_path):
+
+    true_niuren["别名列表"] = None
+    true_niuren["别名列表"] = true_niuren["别名列表（各种奇奇怪怪的名字格式，比如first name和second name的顺序，以;分隔）"].apply(
+        lambda x: [standardized_name(i.strip()) for i in x.split(";") if i!=""] if isinstance(x, str) else []
+    )
+
+    true_niuren_names = []
+    true_niuren_papers = []
+    # 构建牛人姓名列表
+    for _, row in true_niuren.iterrows():
+        if pd.isna(row["姓名"]):
+            break
+        if row["别名列表"]:
+            true_niuren_names.append([standardized_name(row["姓名"])] + row["别名列表"])
+        else:
+            true_niuren_names.append(standardized_name(row["姓名"]))
+            
+
+    # 构建牛人论文列表
+    for true_niuren_idx, _ in enumerate(true_niuren_names):
+        paper_file_path = os.path.join(true_niuren_papers_path, f"{true_niuren_idx+1}.xlsx")
+        if os.path.exists(paper_file_path):
+            papers_df = pd.read_excel(paper_file_path, usecols=[0])
+            papers_list = papers_df.iloc[:, 0].dropna().tolist()
+            papers_list = [paper.lower() for paper in papers_list]
+            true_niuren_papers.append(papers_list)
+        else:
+            true_niuren_papers.append([])
+    return true_niuren_names, true_niuren_papers
+
+
+
+def load_fake_niuren(fake_niuren, fake_niuren_papers_path):
+    # 读取 "全局非牛人" 工作簿
+
+    fake_niuren_names = []
+    fake_niuren_papers = []
+
+    # 构建非牛人姓名列表
+    for _, row in fake_niuren.iterrows():
+        if pd.isna(row["姓名"]):
+            break
+        fake_niuren_names.append(standardized_name(row["姓名"]))
+
+    # 构建非牛人论文列表
+    for fake_niuren_idx, _ in enumerate(fake_niuren_names):
+        paper_file_path = os.path.join(fake_niuren_papers_path, f"{fake_niuren_idx+1}.xlsx")
+        if os.path.exists(paper_file_path):
+            papers_df = pd.read_excel(paper_file_path, usecols=[0])
+            papers_list = papers_df.iloc[:, 0].dropna().tolist()
+            papers_list = [paper.lower() for paper in papers_list]
+            fake_niuren_papers.append(papers_list)
+        else:
+            fake_niuren_papers.append([])
+    return fake_niuren_names, fake_niuren_papers
+
+
+def check_niuren(authors, title, niuren_pool_names, true_niuren_names, true_niuren_papers, fake_niuren_names, fake_niuren_papers):
+    niuren = []
+    order = []
+    suspected_niuren = []
+
+    for author_idx, author in enumerate(authors):
+        if author == "":
+            continue
+
+        # 作者姓名能否在牛人池中找到
+        name_index = name_in_niuren_list(standardized_name(author), niuren_pool_names)
+        if name_index == -1:
+            continue
+
+        # 作者姓名能否在全局牛人中找到
+        true_name_index = name_in_niuren_list(standardized_name(author), true_niuren_names)
+        if true_name_index != -1:
+            if title.strip().lower() in true_niuren_papers[true_name_index]:
+                niuren.append(author)
+                order.append(author_idx + 1)
+                continue
+
+        # 作者姓名能否在全局非牛人中找到
+        fake_name_index = name_in_niuren_list(standardized_name(author), fake_niuren_names)
+        if fake_name_index != -1:
+            if title.strip().lower() in fake_niuren_papers[fake_name_index]:
+                continue
+        suspected_niuren.append([author, name_index+1])
+    niuren_str = ";".join(niuren)
+    order_str = ";".join([str(i) for i in order])
+    suspected_niuren_str = ";".join([f"{name}({index})" for name, index in suspected_niuren])
+    return niuren_str, order_str, suspected_niuren_str
+
+
+def process_row(index, row, niuren_pool_names, true_niuren_names, true_niuren_papers, fake_niuren_names, fake_niuren_papers):
+    try:
+        authors = row.get('引文作者', '')
+        title = row.get('引文名称', '')
+        if not isinstance(authors, str):
+            return index, "", "", ""
+        authors = [i.strip() for i in authors.split(";") if i!=""]
+        niuren_true, niuren_true_order, suspected_niuren = check_niuren(authors, title, niuren_pool_names, true_niuren_names, true_niuren_papers, fake_niuren_names, fake_niuren_papers)
+        return index, niuren_true, niuren_true_order, suspected_niuren
+    except Exception as e:
+        print(f"处理行 {index} 时发生错误: {e}")
+        return index, "", "", ""
+
+
+if __name__ == "__main__":
+    print("正在读取全局牛人...")
+    true_niuren = pd.read_excel(input_file_path, sheet_name="全局牛人")
+    print("正在读取全局非牛人...")
+    fake_niuren = pd.read_excel(input_file_path, sheet_name="全局非牛人")
+    print("正在处理牛人池...")
+    niuren_pool_names = load_niuren_pool(niuren_pool_path)
+    print("正在处理真牛人数据...")
+    true_niuren_names, true_niuren_papers = load_true_niuren(true_niuren,true_niuren_papers_path)
+    print("正在处理非牛人数据...")
+    fake_niuren_names, fake_niuren_papers = load_fake_niuren(fake_niuren,fake_niuren_papers_path)
+    
+    # 读取表头（第4行作为列名）
+    original_header = pd.read_excel(input_file_path, nrows=0, header=3)
+    column_names = original_header.columns.tolist()
+    
+    # 读取数据（从第8行开始）
+    input_df = pd.read_excel(input_file_path, skiprows=7, header=None, names=column_names)
+    
+    # 输出表头和数据的基本信息
+    print("表头元素：")
+    print(column_names)
+    print("\n数据行数：", input_df.shape[0])
+    print("数据列数：", input_df.shape[1])
+    
+    # 检查列是否存在，不存在则添加
+    if '疑似牛人' not in input_df.columns:
+        input_df['疑似牛人'] = None
+    
+    # 确保牛人相关列存在
+    niuren_col = '牛人\n(参考全局牛人列表)'
+    niuren_order_col = '牛人署名顺序\n'
+    
+    # 如果列不存在，添加它们
+    if niuren_col not in input_df.columns:
+        input_df[niuren_col] = None
+    
+    if niuren_order_col not in input_df.columns:
+        input_df[niuren_order_col] = None
+    
+    print("开始并行处理数据...")
+    # 并行处理，将加载的数据传递给每个进程
+    results = Parallel(n_jobs=-1)(
+        delayed(process_row)(
+            index, row, 
+            niuren_pool_names, true_niuren_names, true_niuren_papers, 
+            fake_niuren_names, fake_niuren_papers
+        ) 
+        for index, row in tqdm(input_df.iterrows())
+    )
+    
+    for index, niuren_true, niuren_true_order, suspected_niuren in results:
+        input_df.at[index, niuren_col] = niuren_true
+        input_df.at[index, niuren_order_col] = niuren_true_order
+        input_df.at[index, '疑似牛人'] = suspected_niuren
+    
+    # 打开原始Excel文件
+    print("正在读取原始Excel文件以保留格式...")
+    wb_original = openpyxl.load_workbook(input_file_path)
+    
+    # 创建新工作簿
+    wb_new = openpyxl.Workbook()
+    # 删除默认创建的空白工作表
+    if 'Sheet' in wb_new.sheetnames:
+        del wb_new['Sheet']
+    
+    # 复制所有工作表
+    for sheet_name in wb_original.sheetnames:
+        ws_original = wb_original[sheet_name]
+        ws_new = wb_new.create_sheet(sheet_name)
+        
+        # 复制工作表属性
+        ws_new.sheet_properties = copy(ws_original.sheet_properties)
+        ws_new.sheet_format = copy(ws_original.sheet_format)
+        
+        # 复制整个工作表的内容和格式
+        for row in ws_original.rows:
+            for cell in row:
+                new_cell = ws_new.cell(row=cell.row, column=cell.column, value=cell.value)
+                if cell.has_style:
+                    new_cell.font = copy(cell.font)
+                    new_cell.border = copy(cell.border)
+                    new_cell.fill = copy(cell.fill)
+                    new_cell.number_format = copy(cell.number_format)
+                    new_cell.protection = copy(cell.protection)
+                    new_cell.alignment = copy(cell.alignment)
+        
+        # 复制合并单元格
+        for merged_cell_range in ws_original.merged_cells.ranges:
+            ws_new.merge_cells(str(merged_cell_range))
+    
+    # 获取主工作表（第一个工作表）
+    main_sheet_name = wb_original.sheetnames[0]
+    ws_new = wb_new[main_sheet_name]
+    
+    # 更新主工作表中的牛人相关数据
+    print("正在更新主工作表中的牛人数据...")
+    
+    # 找出列索引（Excel中列是从1开始的）
+    niuren_col_index = None
+    niuren_order_col_index = None
+    suspected_niuren_col_index = None
+    
+    # 获取第4行（索引从1开始）的所有单元格值
+    header_row = [cell.value for cell in ws_new[4]]
+    
+    # 在这些值中查找列名对应的索引
+    for i, cell_value in enumerate(header_row, start=1):
+        if cell_value == niuren_col:
+            niuren_col_index = i
+        elif cell_value == niuren_order_col:
+            niuren_order_col_index = i
+        elif cell_value == '疑似牛人':
+            suspected_niuren_col_index = i
+    
+    # 如果找不到列，添加新列
+    max_col = ws_new.max_column
+    
+    if niuren_col_index is None:
+        niuren_col_index = max_col + 1
+        ws_new.cell(row=4, column=niuren_col_index, value=niuren_col)
+        max_col += 1
+    
+    if niuren_order_col_index is None:
+        niuren_order_col_index = max_col + 1
+        ws_new.cell(row=4, column=niuren_order_col_index, value=niuren_order_col)
+        max_col += 1
+    
+    if suspected_niuren_col_index is None:
+        suspected_niuren_col_index = max_col + 1
+        ws_new.cell(row=4, column=suspected_niuren_col_index, value='疑似牛人')
+    
+    # 更新数据（从第8行开始）
+    for i, row in input_df.iterrows():
+        excel_row = i + 8  # 转换为Excel的行号（从1开始）
+        
+        # 只更新牛人相关的三列
+        ws_new.cell(row=excel_row, column=niuren_col_index, value=row[niuren_col])
+        ws_new.cell(row=excel_row, column=niuren_order_col_index, value=row[niuren_order_col])
+        ws_new.cell(row=excel_row, column=suspected_niuren_col_index, value=row['疑似牛人'])
+    
+    # 保存新Excel文件
+    print(f"正在保存为Excel格式 {output_file_path} ...")
+    wb_new.save(output_file_path)
+    print(f"成功保存到 {output_file_path}，保留了原始格式")
+    
+    print("处理完成!")
\ No newline at end of file

papertools_niuren_ccfa/niurenpipei_ori.py

+import os
+import json
+import pandas as pd
+from tqdm import tqdm
+from joblib import Parallel, delayed
+from utils import firstlast2lastfirst, name_in_niuren_list
+
+input_file_path = '/Users/zhengxinhan/Desktop/papertools-master-2cb16c72b94585f63d8a221966bdc782a086fda5/niurenshaixuan/info/论文被引用统计-陈老师-截止2025年X月XX日.xlsx'
+output_file_path = '测试输出3.xlsx'
+
+# 全局变量，存储加载的数据
+NIUREN_POOL_NAMES = []
+TRUE_NIUREN_NAMES = []
+TRUE_NIUREN_PAPERS = []
+FAKE_NIUREN_NAMES = []
+FAKE_NIUREN_PAPERS = []
+
+def load_niuren_pool():
+    niuren_pool = pd.read_csv("/Users/zhengxinhan/Desktop/papertools-master-2cb16c72b94585f63d8a221966bdc782a086fda5/niurenshaixuan/info/new_niuren_format-merged_turing.csv", encoding='utf-8-sig')
+    niuren_pool_names = niuren_pool["name"].tolist()
+    niuren_pool_names = [name.replace("\xa0", " ") for name in niuren_pool_names]  # 去除空格
+    return niuren_pool_names
+
+
+def load_true_niuren():
+    # 读取 "全局牛人" 工作簿
+    true_niuren = pd.read_excel("/Users/zhengxinhan/Desktop/papertools-master-2cb16c72b94585f63d8a221966bdc782a086fda5/niurenshaixuan/info/论文被引用统计-陈老师-截止2025年X月XX日.xlsx", sheet_name="全局牛人")
+
+    true_niuren["别名列表"] = None
+    true_niuren["别名列表"] = true_niuren["别名列表（各种奇奇怪怪的名字格式，比如first name和second name的顺序，以;分隔）"].apply(
+        lambda x: [firstlast2lastfirst(i.strip()) for i in x.split(";") if i!=""] if isinstance(x, str) else []
+    )
+
+    true_niuren_names = []
+    true_niuren_papers = []
+    # 构建牛人姓名列表
+    for _, row in true_niuren.iterrows():
+        if pd.isna(row["姓名"]):
+            break
+        if row["别名列表"]:
+            true_niuren_names.append([firstlast2lastfirst(row["姓名"])] + row["别名列表"])
+        else:
+            true_niuren_names.append(firstlast2lastfirst(row["姓名"]))
+            
+
+    # 构建牛人论文列表
+    for true_niuren_idx, _ in enumerate(true_niuren_names):
+        paper_file_path = os.path.join("/Users/zhengxinhan/Desktop/papertools-master-2cb16c72b94585f63d8a221966bdc782a086fda5/niurenshaixuan/info/niuren_papers", f"{true_niuren_idx+1}.xlsx")
+        if os.path.exists(paper_file_path):
+            papers_df = pd.read_excel(paper_file_path, usecols=[0])
+            papers_list = papers_df.iloc[:, 0].dropna().tolist()
+            papers_list = [paper.lower() for paper in papers_list]
+            true_niuren_papers.append(papers_list)
+        else:
+            true_niuren_papers.append([])
+    return true_niuren_names, true_niuren_papers
+
+
+
+def load_fake_niuren():
+    # 读取 "全局非牛人" 工作簿
+    fake_niuren = pd.read_excel("/Users/zhengxinhan/Desktop/papertools-master-2cb16c72b94585f63d8a221966bdc782a086fda5/niurenshaixuan/info/论文被引用统计-陈老师-截止2025年X月XX日.xlsx", sheet_name="全局非牛人")
+
+    fake_niuren_names = []
+    fake_niuren_papers = []
+
+    # 构建非牛人姓名列表
+    for _, row in fake_niuren.iterrows():
+        if pd.isna(row["姓名"]):
+            break
+        fake_niuren_names.append(firstlast2lastfirst(row["姓名"]))
+
+    # 构建非牛人论文列表
+    for fake_niuren_idx, _ in enumerate(fake_niuren_names):
+        paper_file_path = os.path.join("/Users/zhengxinhan/Desktop/papertools-master-2cb16c72b94585f63d8a221966bdc782a086fda5/niurenshaixuan/info/feiniuren_papers", f"{fake_niuren_idx+1}.xlsx")
+        if os.path.exists(paper_file_path):
+            papers_df = pd.read_excel(paper_file_path, usecols=[0])
+            papers_list = papers_df.iloc[:, 0].dropna().tolist()
+            papers_list = [paper.lower() for paper in papers_list]
+            fake_niuren_papers.append(papers_list)
+        else:
+            fake_niuren_papers.append([])
+    return fake_niuren_names, fake_niuren_papers
+
+
+def check_niuren(authors, title, niuren_pool_names, true_niuren_names, true_niuren_papers, fake_niuren_names, fake_niuren_papers):
+    niuren = []
+    order = []
+    suspected_niuren = []
+
+    for author_idx, author in enumerate(authors):
+        if author == "":
+            continue
+
+        # 作者姓名能否在牛人池中找到
+        name_index = name_in_niuren_list(firstlast2lastfirst(author), niuren_pool_names)
+        if name_index == -1:
+            continue
+
+        # 作者姓名能否在全局牛人中找到
+        true_name_index = name_in_niuren_list(firstlast2lastfirst(author), true_niuren_names)
+        if true_name_index != -1:
+            if title.strip().lower() in true_niuren_papers[true_name_index]:
+                niuren.append(author)
+                order.append(author_idx + 1)
+                continue
+
+        # 作者姓名能否在全局非牛人中找到
+        fake_name_index = name_in_niuren_list(firstlast2lastfirst(author), fake_niuren_names)
+        if fake_name_index != -1:
+            if title.strip().lower() in fake_niuren_papers[fake_name_index]:
+                continue
+        suspected_niuren.append([author, name_index+1])
+    niuren_str = ";".join(niuren)
+    order_str = ";".join([str(i) for i in order])
+    suspected_niuren_str = ";".join([f"{name}({index})" for name, index in suspected_niuren])
+    # 截断可能过长的字符串，防止Excel导出问题
+    if len(suspected_niuren_str) > 2000:
+        suspected_niuren_str = suspected_niuren_str[:2000] + "..."
+    return niuren_str, order_str, suspected_niuren_str
+
+
+def process_row(index, row, niuren_pool_names, true_niuren_names, true_niuren_papers, fake_niuren_names, fake_niuren_papers):
+    try:
+        authors = row.get('引文作者', '')
+        title = row.get('引文名称', '')
+        if not isinstance(authors, str):
+            return index, "", "", ""
+        authors = [i.strip() for i in authors.split(";") if i!=""]
+        niuren_true, niuren_true_order, suspected_niuren = check_niuren(authors, title, niuren_pool_names, true_niuren_names, true_niuren_papers, fake_niuren_names, fake_niuren_papers)
+        return index, niuren_true, niuren_true_order, suspected_niuren
+    except Exception as e:
+        print(f"处理行 {index} 时发生错误: {e}")
+        return index, "", "", ""
+
+
+if __name__ == "__main__":
+    # 预先加载所有数据，只加载一次
+    print("正在加载牛人池...")
+    niuren_pool_names = load_niuren_pool()
+    print("正在加载真牛人数据...")
+    true_niuren_names, true_niuren_papers = load_true_niuren()
+    print("正在加载假牛人数据...")
+    fake_niuren_names, fake_niuren_papers = load_fake_niuren()
+    
+    # 读取原始 Excel 文件的前两行
+    original_header = pd.read_excel(input_file_path, nrows=2, header=None)
+
+    # 读取数据并跳过前两行
+    input_df = pd.read_excel(input_file_path, skiprows=3)
+
+    # 添加新列
+    input_df['牛人'] = None
+    input_df['牛人署名顺序'] = None
+    input_df['疑似牛人'] = None
+
+    print("开始并行处理数据...")
+    # 并行处理，将加载的数据传递给每个进程
+    results = Parallel(n_jobs=-1)(
+        delayed(process_row)(
+            index, row, 
+            niuren_pool_names, true_niuren_names, true_niuren_papers, 
+            fake_niuren_names, fake_niuren_papers
+        ) 
+        for index, row in tqdm(input_df.iterrows())
+    )
+    
+    for index, niuren_true, niuren_true_order, suspected_niuren in results:
+        input_df.at[index, '牛人'] = niuren_true
+        input_df.at[index, '牛人署名顺序'] = niuren_true_order
+        input_df.at[index, '疑似牛人'] = suspected_niuren
+
+    max_cols = max(original_header.shape[1], input_df.shape[1])
+
+    # 定义补齐函数
+    def pad_df(df, max_cols):
+        df = df.copy()
+        for i in range(df.shape[1], max_cols):
+            df[i] = ""
+        df = df.iloc[:, :max_cols]  # 限制在max_cols列
+        df.columns = range(max_cols)  # 用数字做列名
+        return df
+
+    # 补齐所有DF
+    original_header_padded = pad_df(original_header, max_cols)
+    input_header = pd.DataFrame([input_df.columns.tolist()])
+    input_header_padded = pad_df(input_header, max_cols)
+    input_data_padded = pad_df(input_df, max_cols)
+
+    # 拼接
+    output_df = pd.concat([original_header_padded, input_header_padded, input_data_padded], ignore_index=True)
+
+    # 保存为CSV先测试
+    csv_path = output_file_path.replace('.xlsx', '.csv')
+    print(f"先保存为CSV格式 {csv_path} ...")
+    output_df.to_csv(csv_path, index=False, header=False)
+    
+    # 尝试保存为Excel
+    try:
+        print(f"尝试保存为Excel格式 {output_file_path} ...")
+        output_df.to_excel(output_file_path, index=False, header=False, engine='openpyxl')
+        print(f"成功保存到 {output_file_path}")
+    except Exception as e:
+        print(f"保存Excel失败: {e}")
+        print(f"请使用CSV格式文件 {csv_path}")
+    
+    print("处理完成!")
\ No newline at end of file

papertools_niuren_ccfa/utils.py

+'''
+Author: zhengxinhan
+Date: 2025-05-08 15:02:02
+LastEditors: zhengxinhan
+LastEditTime: 2025-05-09 02:46:29
+FilePath: /papertools-master/niurenshaixuan/utils.py
+Description: 
+
+Copyright (c) 2025 by m13521952989@163.com, All Rights Reserved. 
+'''
+def standardized_name(name):
+    if "," in name:
+        return name
+    # 名人列表中存在一些名字是First Name Last Name的格式，将其转换为Last Name, First Name格式
+    # 例如：'John Doe' -> 'Doe, John'，'M. Jane Smith' -> 'Smith, Jane M.'
+    special_str = [".", "Ms.", "Mr.", "Mrs.", "Dr.", "Prof.", "PhD", "MD", "Jr.", "Sr.", "The", "Honorable"]
+    name_split = name.split(" ")
+    name_split = [item.strip() for item in name_split if item.strip() != ""]
+    name_split = [item for item in name_split if item not in special_str]
+    
+    # Grigory Isaakovich Barenblatt --> Barenblatt, Alexa, Marc Isaakovich
+    
+    if len(name_split) == 2:
+        first_name = name_split[0]
+        last_name = name_split[1]
+        new_name = f"{last_name}, {first_name}"
+    elif len(name_split) == 3:
+        if name_split[0].startswith("(") and name_split[0].endswith(")"):
+            # (Alexander) Philip Dawid
+            first_name = f"{name_split[1]} {name_split[0]}"
+            last_name = f"{name_split[2]}"
+        elif name_split[1].startswith("(") and name_split[1].endswith(")"):
+            # Xinyan (Tracy) Cui --> Cui, Xinyan (Tracy)
+            first_name = f"{name_split[0]} {name_split[1]}"
+            last_name = f"{name_split[2]}"
+        elif name_split[2].startswith("(") and name_split[2].endswith(")"):
+            # Ye Fred (Ying)实际是姓Ye，名Ying，英文名Fred, 需要将其转换为"Ye, Ying Fred"
+            # Zhu Jesse (Jingxu)实际是姓Zhu，名Jingxu，英文名Jesse, 需要将其转换为"Zhu, Jingxu Jesse"
+            first_name = f"{name_split[2][1:-1]} ({name_split[1]})"
+            last_name = f"{name_split[0]}"
+        elif name_split[0].endswith("."):
+            # M. Jane Smith --> Smith, Jane M.
+            # K.W. Michael Siu --> Siu, Michael K.W.
+            first_name = f"{name_split[1]} {name_split[0]}"
+            last_name = name_split[2]
+        elif name_split[1].endswith("."):
+            # Jane M. Smith --> Smith, Jane M.
+            # Pierre J.H. Richardson --> Richardson, Pierre J.H.
+            first_name = f"{name_split[0]} {name_split[1]}"
+            last_name = name_split[2]
+        elif name_split[2].endswith("."):
+            # Wimmer-Schweingruber Robert F. --> Wimmer-Schweingruber, Robert F.
+            # Wilderer Peter A. --> Wilderer, Peter A.
+            first_name = f"{name_split[1]} {name_split[2]}"
+            last_name = f"{name_split[0]}"
+        else:
+            # William Nelson Joy --> Joy, William Nelson
+            # Michael J Carey --> Carey, Michael J
+            # len_3_list.append(" ".join(name_split))
+            first_name = f"{name_split[0]} {name_split[1]}"
+            last_name = name_split[2]
+        
+        new_name = f"{last_name}, {first_name}"
+        # print(f"{name} --> {new_name}")
+    else:
+        # lens greater than 3 这部分名字应该不会跟其他部分名字出现重复
+        last_name = name_split[-1]
+        first_name = " ".join(name_split[:-1])
+        new_name = f"{last_name}, {first_name}"
+        
+    return new_name
+
+
+def name_in_niuren_list(name, niuren_name_list):
+    """
+    判断名字是否在牛人列表中
+    :param name: 名字
+    :param niuren_name_list: 牛人列表
+    :return: 如果在牛人列表中，返回 True，否则返回 False
+    """
+    for idx, niuren_name in enumerate(niuren_name_list):
+        if isinstance(niuren_name, str):
+            if name == niuren_name:
+                return idx
+        elif isinstance(niuren_name, list):
+            if name in niuren_name:
+                return idx
+
+    for idx, niuren_name in enumerate(niuren_name_list):
+        if isinstance(niuren_name, str):
+            if niuren_name.startswith(name):
+                if niuren_name[niuren_name.find(name) + len(name)] == " ":
+                    return idx
+            if name.startswith(niuren_name):
+                if name[name.find(niuren_name) + len(niuren_name)] == " ":
+                    return idx
+        elif isinstance(niuren_name, list):
+            for niuren_name_item in niuren_name:
+                if niuren_name_item.startswith(name):
+                    if niuren_name_item[niuren_name_item.find(name) + len(name)] == " ":
+                        return idx
+                if name.startswith(niuren_name_item):
+                    if name[name.find(niuren_name_item) + len(niuren_name_item)] == " ":
+                        return idx
+    return -1
\ No newline at end of file