Upload files to "/"

2024-12-20 09:57:27 +08:00
parent c9eb03a5a1
commit fcc3b22c47
1 changed files with 64 additions and 0 deletions
--- a/gen_names.py
+++ b/gen_names.py
@@ -0,0 +1,64 @@
+import os
+import json
+import csv
+
+# 设置输入和输出路径
+gt_input_dir = 'gt_input'  # JSON 文件所在目录
+csv_file = '人名替换表.csv'  # CSV 文件名
+
+# 初始化一个字典来存储 JP_Name 和出现次数
+name_count = {}
+
+# 遍历 gt_input 目录下的所有 JSON 文件
+for filename in os.listdir(gt_input_dir):
+    if filename.endswith('.json'):
+        file_path = os.path.join(gt_input_dir, filename)
+        with open(file_path, 'r', encoding='utf-8') as f:
+            try:
+                # 加载 JSON 数据
+                data = json.load(f)
+                for entry in data:
+                    jp_name = entry.get("name")
+                    if jp_name:
+                        # 更新计数
+                        name_count[jp_name] = name_count.get(jp_name, 0) + 1
+            except json.JSONDecodeError:
+                print(f"Error decoding JSON from file: {file_path}")
+
+# 检查 CSV 文件是否存在
+existing_data = {}
+if os.path.exists(csv_file):
+    # 如果存在，读取现有数据
+    with open(csv_file, 'r', encoding='utf-8-sig') as csvfile:
+        reader = csv.DictReader(csvfile)
+        for row in reader:
+            jp_name = row['JP_Name']
+            cn_name = row['CN_Name']
+            count = int(row['Count'])
+            existing_data[jp_name] = {'CN_Name': cn_name, 'Count': count}
+
+# 更新现有数据与新数据
+for jp_name in existing_data.keys():
+    # 如果该 JP_Name 在新数据中未出现，则 Count 设置为 0
+    existing_data[jp_name]['Count'] = name_count.get(jp_name, 0)
+for jp_name, count in name_count.items():
+    if jp_name in existing_data:
+        # 更新现有项的 Count
+        existing_data[jp_name]['Count'] = count
+    else:
+        # 新增项
+        existing_data[jp_name] = {'CN_Name': '', 'Count': count}  # CN_Name 默认为空
+
+# 将结果写入 CSV 文件
+with open(csv_file, 'w', newline='', encoding='utf-8-sig') as csvfile:
+    fieldnames = ['JP_Name', 'CN_Name', 'Count']
+    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
+
+    writer.writeheader()
+
+    # 按 Count 排序并写入
+    sorted_data = sorted(existing_data.items(), key=lambda x: x[1]['Count'], reverse=True)
+    for jp_name, details in sorted_data:
+        writer.writerow({'JP_Name': jp_name, 'CN_Name': details['CN_Name'], 'Count': details['Count']})
+
+print(f"CSV 文件 '{csv_file}' 已成功生成/更新。")