feat: 校验根据映射表添加作者链接
This commit is contained in:
@@ -1,6 +1,7 @@
|
||||
{
|
||||
"rename": {
|
||||
"起个名字好难": "起个名字好难的喵"
|
||||
"起个名字好难": "起个名字好难的喵",
|
||||
"this-Fish": "蜜柑魚"
|
||||
},
|
||||
"links": {
|
||||
"秋云": "https://github.com/physligl",
|
||||
|
||||
@@ -1,136 +1,169 @@
|
||||
import os
|
||||
import sys
|
||||
import json
|
||||
|
||||
# 获取配置文件路径(和脚本在同一目录)
|
||||
script_dir = os.path.dirname(os.path.abspath(__file__))
|
||||
config_path = os.path.join(script_dir, "author_config.json")
|
||||
def process_json_authors(input_path, config_path="author_config.json", verbose=True):
|
||||
"""
|
||||
处理 JSON 文件中的作者信息(支持 author → authors 结构化迁移、作者名重命名和链接统一)
|
||||
|
||||
参数:
|
||||
input_path (str): 要处理的文件路径或目录路径
|
||||
config_path (str): 配置文件路径(默认在脚本同级)
|
||||
verbose (bool): 是否打印详细日志信息
|
||||
|
||||
返回:
|
||||
dict: 包含处理总数和修改数量的统计信息
|
||||
"""
|
||||
result = {
|
||||
"total_files": 0,
|
||||
"modified_files": 0,
|
||||
"errors": []
|
||||
}
|
||||
|
||||
# 获取要处理的文件夹路径
|
||||
if len(sys.argv) < 2:
|
||||
print("❌ 用法:python pathing_authors.py <JSON目录路径>")
|
||||
sys.exit(1)
|
||||
if not os.path.exists(input_path):
|
||||
raise FileNotFoundError(f"路径不存在:{input_path}")
|
||||
if not os.path.exists(config_path):
|
||||
raise FileNotFoundError(f"配置文件不存在:{config_path}")
|
||||
|
||||
folder_path = sys.argv[1]
|
||||
# 加载配置
|
||||
try:
|
||||
with open(config_path, "r", encoding="utf-8") as f:
|
||||
config = json.load(f)
|
||||
except Exception as e:
|
||||
raise RuntimeError(f"配置文件加载失败:{e}")
|
||||
|
||||
if not os.path.exists(folder_path):
|
||||
print(f"❌ JSON目录不存在:{folder_path}")
|
||||
sys.exit(1)
|
||||
if not os.path.exists(config_path):
|
||||
print(f"❌ 配置文件不存在:{config_path}")
|
||||
sys.exit(1)
|
||||
author_rename = config.get("rename", {})
|
||||
author_links = config.get("links", {})
|
||||
|
||||
# 加载配置
|
||||
try:
|
||||
with open(config_path, "r", encoding="utf-8") as f:
|
||||
config = json.load(f)
|
||||
except Exception as e:
|
||||
print(f"❌ 配置文件加载失败:{e}")
|
||||
sys.exit(1)
|
||||
# 构建待处理文件列表
|
||||
file_list = []
|
||||
if os.path.isfile(input_path) and input_path.endswith(".json"):
|
||||
file_list.append(input_path)
|
||||
elif os.path.isdir(input_path):
|
||||
for root, dirs, files in os.walk(input_path):
|
||||
for filename in files:
|
||||
if filename.endswith(".json"):
|
||||
file_list.append(os.path.join(root, filename))
|
||||
else:
|
||||
raise ValueError("输入路径必须是 .json 文件或目录")
|
||||
|
||||
author_rename = config.get("rename", {})
|
||||
author_links = config.get("links", {})
|
||||
|
||||
print(f"🚀 启动,处理目录:{folder_path}")
|
||||
count_total = 0
|
||||
count_modified = 0
|
||||
|
||||
for root, dirs, files in os.walk(folder_path):
|
||||
for filename in files:
|
||||
if filename.endswith(".json"):
|
||||
count_total += 1
|
||||
file_path = os.path.join(root, filename)
|
||||
for file_path in file_list:
|
||||
result["total_files"] += 1
|
||||
if verbose:
|
||||
print(f"\n🔍 处理文件:{file_path}")
|
||||
|
||||
try:
|
||||
with open(file_path, "r", encoding="utf-8") as f:
|
||||
data = json.load(f)
|
||||
except Exception as e:
|
||||
print(f"❌ 解析失败:{e}")
|
||||
continue
|
||||
try:
|
||||
with open(file_path, "r", encoding="utf-8") as f:
|
||||
data = json.load(f)
|
||||
except Exception as e:
|
||||
msg = f"❌ 解析失败:{e}"
|
||||
if verbose:
|
||||
print(msg)
|
||||
result["errors"].append((file_path, str(e)))
|
||||
continue
|
||||
|
||||
info = data.get("info")
|
||||
if not isinstance(info, dict):
|
||||
info = data.get("info")
|
||||
if not isinstance(info, dict):
|
||||
if verbose:
|
||||
print("⚠️ 缺少 info 字段")
|
||||
continue
|
||||
continue
|
||||
|
||||
modified = False
|
||||
author_field = info.get("author")
|
||||
modified = False
|
||||
author_field = info.get("author")
|
||||
|
||||
if author_field is not None:
|
||||
# 旧格式字符串处理
|
||||
if isinstance(author_field, str):
|
||||
names = [name.strip() for name in author_field.split("&")]
|
||||
new_authors = []
|
||||
for name in names:
|
||||
new_name = author_rename.get(name, name)
|
||||
author_obj = {"name": new_name}
|
||||
if new_name in author_links:
|
||||
author_obj["links"] = author_links[new_name]
|
||||
new_authors.append(author_obj)
|
||||
data["info"]["authors"] = new_authors
|
||||
modified = True
|
||||
if author_field is not None:
|
||||
if isinstance(author_field, str):
|
||||
names = [name.strip() for name in author_field.split("&")]
|
||||
new_authors = []
|
||||
for name in names:
|
||||
new_name = author_rename.get(name, name)
|
||||
author_obj = {"name": new_name}
|
||||
if new_name in author_links:
|
||||
author_obj["links"] = author_links[new_name]
|
||||
new_authors.append(author_obj)
|
||||
data["info"]["authors"] = new_authors
|
||||
modified = True
|
||||
if verbose:
|
||||
print("✅ 替换为结构化 authors")
|
||||
|
||||
elif isinstance(author_field, list):
|
||||
for author_obj in author_field:
|
||||
if not isinstance(author_obj, dict):
|
||||
continue
|
||||
name = author_obj.get("name")
|
||||
if not name:
|
||||
continue
|
||||
new_name = author_rename.get(name, name)
|
||||
if name != new_name:
|
||||
author_obj["name"] = new_name
|
||||
modified = True
|
||||
elif isinstance(author_field, list):
|
||||
for author_obj in author_field:
|
||||
if not isinstance(author_obj, dict):
|
||||
continue
|
||||
name = author_obj.get("name")
|
||||
if not name:
|
||||
continue
|
||||
new_name = author_rename.get(name, name)
|
||||
if name != new_name:
|
||||
author_obj["name"] = new_name
|
||||
modified = True
|
||||
if verbose:
|
||||
print(f"📝 重命名:{name} → {new_name}")
|
||||
|
||||
existing_link = author_obj.pop("link", None) or author_obj.pop("url", None) or author_obj.get("links")
|
||||
if new_name in author_links:
|
||||
if author_obj.get("links") != author_links[new_name]:
|
||||
author_obj["links"] = author_links[new_name]
|
||||
modified = True
|
||||
print(f"🔧 更新链接:{new_name} → {author_links[new_name]}")
|
||||
elif "links" not in author_obj and existing_link:
|
||||
author_obj["links"] = existing_link
|
||||
existing_link = author_obj.pop("link", None) or author_obj.pop("url", None) or author_obj.get("links")
|
||||
if new_name in author_links:
|
||||
if author_obj.get("links") != author_links[new_name]:
|
||||
author_obj["links"] = author_links[new_name]
|
||||
modified = True
|
||||
if verbose:
|
||||
print(f"🔧 更新链接:{new_name} → {author_links[new_name]}")
|
||||
elif "links" not in author_obj and existing_link:
|
||||
author_obj["links"] = existing_link
|
||||
modified = True
|
||||
if verbose:
|
||||
print(f"🔄 标准化已有链接字段为 links → {existing_link}")
|
||||
|
||||
else:
|
||||
# 🔧 处理已有结构化 authors 字段,补充 links
|
||||
authors_field = info.get("authors")
|
||||
if isinstance(authors_field, list):
|
||||
for author_obj in authors_field:
|
||||
if not isinstance(author_obj, dict):
|
||||
continue
|
||||
name = author_obj.get("name")
|
||||
if not name:
|
||||
continue
|
||||
new_name = author_rename.get(name, name)
|
||||
if name != new_name:
|
||||
author_obj["name"] = new_name
|
||||
modified = True
|
||||
else:
|
||||
authors_field = info.get("authors")
|
||||
if isinstance(authors_field, list):
|
||||
for author_obj in authors_field:
|
||||
if not isinstance(author_obj, dict):
|
||||
continue
|
||||
name = author_obj.get("name")
|
||||
if not name:
|
||||
continue
|
||||
new_name = author_rename.get(name, name)
|
||||
if name != new_name:
|
||||
author_obj["name"] = new_name
|
||||
modified = True
|
||||
if verbose:
|
||||
print(f"📝 重命名(authors):{name} → {new_name}")
|
||||
|
||||
existing_link = author_obj.pop("link", None) or author_obj.pop("url", None) or author_obj.get("links")
|
||||
if new_name in author_links:
|
||||
if author_obj.get("links") != author_links[new_name]:
|
||||
author_obj["links"] = author_links[new_name]
|
||||
modified = True
|
||||
print(f"🔧 更新链接(authors):{new_name} → {author_links[new_name]}")
|
||||
elif "links" not in author_obj and existing_link:
|
||||
author_obj["links"] = existing_link
|
||||
existing_link = author_obj.pop("link", None) or author_obj.pop("url", None) or author_obj.get("links")
|
||||
if new_name in author_links:
|
||||
if author_obj.get("links") != author_links[new_name]:
|
||||
author_obj["links"] = author_links[new_name]
|
||||
modified = True
|
||||
if verbose:
|
||||
print(f"🔧 更新链接(authors):{new_name} → {author_links[new_name]}")
|
||||
elif "links" not in author_obj and existing_link:
|
||||
author_obj["links"] = existing_link
|
||||
modified = True
|
||||
if verbose:
|
||||
print(f"🔄 标准化已有链接字段为 links → {existing_link}")
|
||||
else:
|
||||
else:
|
||||
if verbose:
|
||||
print("⚠️ 缺少 author 字段,且 authors 非标准格式")
|
||||
|
||||
if modified:
|
||||
with open(file_path, "w", encoding="utf-8") as f:
|
||||
json.dump(data, f, ensure_ascii=False, indent=2)
|
||||
count_modified += 1
|
||||
if modified:
|
||||
with open(file_path, "w", encoding="utf-8") as f:
|
||||
json.dump(data, f, ensure_ascii=False, indent=2)
|
||||
result["modified_files"] += 1
|
||||
if verbose:
|
||||
print("✅ 写入完成")
|
||||
else:
|
||||
else:
|
||||
if verbose:
|
||||
print("⏭️ 无需修改")
|
||||
|
||||
print(f"\n🎉 处理完成:共 {count_total} 个 JSON 文件,修改了 {count_modified} 个")
|
||||
if verbose:
|
||||
print(f"\n🎉 处理完成:共 {result['total_files']} 个 JSON 文件,修改了 {result['modified_files']} 个")
|
||||
|
||||
return result
|
||||
|
||||
|
||||
# 如果作为独立脚本运行
|
||||
if __name__ == "__main__":
|
||||
import sys
|
||||
if len(sys.argv) < 2:
|
||||
print("❌ 用法:python pathing_authors.py <JSON文件或目录路径>")
|
||||
else:
|
||||
process_json_authors(sys.argv[1])
|
||||
|
||||
@@ -415,7 +415,7 @@ def check_position_ids(positions):
|
||||
|
||||
return validation_issues, corrections
|
||||
|
||||
# ==================== 验证修复编码 ====================
|
||||
# ==================== 验证修复文件编码 ====================
|
||||
|
||||
def detect_encoding(file_path, read_size=2048):
|
||||
try:
|
||||
@@ -477,6 +477,164 @@ def scan_and_convert(path, target_extensions=None):
|
||||
else:
|
||||
print(f"❌ Path not found: {path}")
|
||||
|
||||
# ==================== 验证修复作者信息 ====================
|
||||
|
||||
def process_json_authors(input_path, config_path="author_config.json", verbose=False):
|
||||
"""
|
||||
处理 JSON 文件中的作者信息(支持 author → authors 结构化迁移、作者名重命名和链接统一)
|
||||
|
||||
参数:
|
||||
input_path (str): 要处理的文件路径或目录路径
|
||||
config_path (str): 配置文件路径(默认在脚本同级)
|
||||
verbose (bool): 是否打印详细日志信息
|
||||
|
||||
返回:
|
||||
dict: 包含处理总数和修改数量的统计信息
|
||||
"""
|
||||
result = {
|
||||
"total_files": 0,
|
||||
"modified_files": 0,
|
||||
"errors": []
|
||||
}
|
||||
|
||||
if not os.path.exists(input_path):
|
||||
raise FileNotFoundError(f"路径不存在:{input_path}")
|
||||
if not os.path.exists(config_path):
|
||||
raise FileNotFoundError(f"配置文件不存在:{config_path}")
|
||||
|
||||
# 加载配置
|
||||
try:
|
||||
with open(config_path, "r", encoding="utf-8") as f:
|
||||
config = json.load(f)
|
||||
except Exception as e:
|
||||
raise RuntimeError(f"配置文件加载失败:{e}")
|
||||
|
||||
author_rename = config.get("rename", {})
|
||||
author_links = config.get("links", {})
|
||||
|
||||
# 构建待处理文件列表
|
||||
file_list = []
|
||||
if os.path.isfile(input_path) and input_path.endswith(".json"):
|
||||
file_list.append(input_path)
|
||||
elif os.path.isdir(input_path):
|
||||
for root, dirs, files in os.walk(input_path):
|
||||
for filename in files:
|
||||
if filename.endswith(".json"):
|
||||
file_list.append(os.path.join(root, filename))
|
||||
else:
|
||||
raise ValueError("输入路径必须是 .json 文件或目录")
|
||||
|
||||
for file_path in file_list:
|
||||
result["total_files"] += 1
|
||||
if verbose:
|
||||
print(f"\n🔍 处理文件:{file_path}")
|
||||
|
||||
try:
|
||||
with open(file_path, "r", encoding="utf-8") as f:
|
||||
data = json.load(f)
|
||||
except Exception as e:
|
||||
msg = f"❌ 解析失败:{e}"
|
||||
if verbose:
|
||||
print(msg)
|
||||
result["errors"].append((file_path, str(e)))
|
||||
continue
|
||||
|
||||
info = data.get("info")
|
||||
if not isinstance(info, dict):
|
||||
if verbose:
|
||||
print("⚠️ 缺少 info 字段")
|
||||
continue
|
||||
|
||||
modified = False
|
||||
author_field = info.get("author")
|
||||
|
||||
if author_field is not None:
|
||||
if isinstance(author_field, str):
|
||||
names = [name.strip() for name in author_field.split("&")]
|
||||
new_authors = []
|
||||
for name in names:
|
||||
new_name = author_rename.get(name, name)
|
||||
author_obj = {"name": new_name}
|
||||
if new_name in author_links:
|
||||
author_obj["links"] = author_links[new_name]
|
||||
new_authors.append(author_obj)
|
||||
data["info"]["authors"] = new_authors
|
||||
modified = True
|
||||
if verbose:
|
||||
print("✅ 替换为结构化 authors")
|
||||
|
||||
elif isinstance(author_field, list):
|
||||
for author_obj in author_field:
|
||||
if not isinstance(author_obj, dict):
|
||||
continue
|
||||
name = author_obj.get("name")
|
||||
if not name:
|
||||
continue
|
||||
new_name = author_rename.get(name, name)
|
||||
if name != new_name:
|
||||
author_obj["name"] = new_name
|
||||
modified = True
|
||||
if verbose:
|
||||
print(f"📝 重命名:{name} → {new_name}")
|
||||
|
||||
existing_link = author_obj.pop("link", None) or author_obj.pop("url", None) or author_obj.get("links")
|
||||
if new_name in author_links:
|
||||
if author_obj.get("links") != author_links[new_name]:
|
||||
author_obj["links"] = author_links[new_name]
|
||||
modified = True
|
||||
if verbose:
|
||||
print(f"🔧 更新链接:{new_name} → {author_links[new_name]}")
|
||||
elif "links" not in author_obj and existing_link:
|
||||
author_obj["links"] = existing_link
|
||||
modified = True
|
||||
if verbose:
|
||||
print(f"🔄 标准化已有链接字段为 links → {existing_link}")
|
||||
|
||||
else:
|
||||
authors_field = info.get("authors")
|
||||
if isinstance(authors_field, list):
|
||||
for author_obj in authors_field:
|
||||
if not isinstance(author_obj, dict):
|
||||
continue
|
||||
name = author_obj.get("name")
|
||||
if not name:
|
||||
continue
|
||||
new_name = author_rename.get(name, name)
|
||||
if name != new_name:
|
||||
author_obj["name"] = new_name
|
||||
modified = True
|
||||
if verbose:
|
||||
print(f"📝 重命名(authors):{name} → {new_name}")
|
||||
|
||||
existing_link = author_obj.pop("link", None) or author_obj.pop("url", None) or author_obj.get("links")
|
||||
if new_name in author_links:
|
||||
if author_obj.get("links") != author_links[new_name]:
|
||||
author_obj["links"] = author_links[new_name]
|
||||
modified = True
|
||||
if verbose:
|
||||
print(f"🔧 更新链接(authors):{new_name} → {author_links[new_name]}")
|
||||
elif "links" not in author_obj and existing_link:
|
||||
author_obj["links"] = existing_link
|
||||
modified = True
|
||||
if verbose:
|
||||
print(f"🔄 标准化已有链接字段为 links → {existing_link}")
|
||||
else:
|
||||
# if verbose:
|
||||
print("⚠️ 缺少 author 字段,且 authors 非标准格式")
|
||||
|
||||
if modified:
|
||||
with open(file_path, "w", encoding="utf-8") as f:
|
||||
json.dump(data, f, ensure_ascii=False, indent=2)
|
||||
result["modified_files"] += 1
|
||||
if verbose:
|
||||
print("✅ 写入完成")
|
||||
else:
|
||||
if verbose:
|
||||
print("⏭️ 无需修改")
|
||||
|
||||
if verbose:
|
||||
print(f"\n🎉 处理完成:共 {result['total_files']} 个 JSON 文件,修改了 {result['modified_files']} 个")
|
||||
|
||||
# ==================== 主验证逻辑 ====================
|
||||
|
||||
def initialize_data(data, file_path):
|
||||
@@ -678,6 +836,7 @@ def main():
|
||||
|
||||
if os.path.isfile(path) and path.endswith('.json'):
|
||||
scan_and_convert(path)
|
||||
process_json_authors(path)
|
||||
# print(f"\n🔍 校验文件: {path}")
|
||||
notices = validate_file(path, auto_fix)
|
||||
if notices:
|
||||
@@ -694,6 +853,7 @@ def main():
|
||||
file_path = os.path.join(root, file)
|
||||
print(f"\n🔍 校验文件: {file_path}")
|
||||
scan_and_convert(file_path)
|
||||
process_json_authors(file_path)
|
||||
notices = validate_file(file_path, auto_fix)
|
||||
if notices:
|
||||
all_notices.extend([f"{file_path}: {n}" for n in notices])
|
||||
|
||||
Reference in New Issue
Block a user