Spaces:
Paused
Paused
Add code/cube3d/training/dat_freq_sort.py
Browse files
code/cube3d/training/dat_freq_sort.py
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import os
|
| 2 |
+
import re
|
| 3 |
+
from collections import defaultdict
|
| 4 |
+
|
| 5 |
+
def count_dat_usage(folder_path):
|
| 6 |
+
"""
|
| 7 |
+
统计文件夹中所有LDR文件里DAT文件的使用频率
|
| 8 |
+
|
| 9 |
+
参数:
|
| 10 |
+
folder_path: LDR文件所在的文件夹路径
|
| 11 |
+
|
| 12 |
+
返回:
|
| 13 |
+
按使用频率排序的DAT文件字典列表
|
| 14 |
+
"""
|
| 15 |
+
# 用于存储每个DAT文件的使用次数
|
| 16 |
+
dat_counts = defaultdict(int)
|
| 17 |
+
|
| 18 |
+
# 正则表达式模式,用于匹配LDR文件中的DAT引用
|
| 19 |
+
# LDR格式中,零件引用通常类似: 1 0 0 0 1 0 0 0 1 0 part.dat
|
| 20 |
+
dat_pattern = re.compile(r'\b(\w+\.dat)\b', re.IGNORECASE)
|
| 21 |
+
|
| 22 |
+
# 遍历文件夹中的所有文件
|
| 23 |
+
for root, dirs, files in os.walk(folder_path):
|
| 24 |
+
for file in files:
|
| 25 |
+
# 只处理LDR文件
|
| 26 |
+
if file.lower().endswith('.ldr'):
|
| 27 |
+
file_path = os.path.join(root, file)
|
| 28 |
+
|
| 29 |
+
try:
|
| 30 |
+
# 打开并读取LDR文件
|
| 31 |
+
with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
|
| 32 |
+
line_number = 0
|
| 33 |
+
for line in f:
|
| 34 |
+
line_number += 1
|
| 35 |
+
# 跳过注释行和空行(LDR中以0开头的通常是注释或元数据)
|
| 36 |
+
stripped_line = line.strip()
|
| 37 |
+
if not stripped_line or stripped_line.startswith('0 '):
|
| 38 |
+
continue
|
| 39 |
+
|
| 40 |
+
# 在有效行中查找DAT文件引用
|
| 41 |
+
matches = dat_pattern.findall(line)
|
| 42 |
+
for dat_file in matches:
|
| 43 |
+
# 统一转为小写,避免大小写导致的重复计数
|
| 44 |
+
dat_file_lower = dat_file.lower()
|
| 45 |
+
dat_counts[dat_file_lower] += 1
|
| 46 |
+
|
| 47 |
+
except Exception as e:
|
| 48 |
+
print(f"处理文件 {file_path} 时出错: {str(e)}")
|
| 49 |
+
|
| 50 |
+
# 按使用频率从高到低排序
|
| 51 |
+
sorted_dats = sorted(dat_counts.items(), key=lambda x: x[1], reverse=True)
|
| 52 |
+
|
| 53 |
+
return sorted_dats
|
| 54 |
+
|
| 55 |
+
def main():
|
| 56 |
+
import sys
|
| 57 |
+
|
| 58 |
+
# # 获取用户输入的文件夹路径
|
| 59 |
+
# if len(sys.argv) > 1:
|
| 60 |
+
# folder_path = sys.argv[1]
|
| 61 |
+
# else:
|
| 62 |
+
# folder_path = input("请输入LDR文件所在的文件夹路径: ")
|
| 63 |
+
|
| 64 |
+
folder_path = "/public/home/wangshuo/gap/assembly/data/car_1k/subset_self/ldr_l30_rotrans_expand_wom_flip"
|
| 65 |
+
|
| 66 |
+
# 验证文件夹路径是否有效
|
| 67 |
+
if not os.path.isdir(folder_path):
|
| 68 |
+
print(f"错误: {folder_path} 不是有效的文件夹路径")
|
| 69 |
+
return
|
| 70 |
+
|
| 71 |
+
print(f"正在统计 {folder_path} 中LDR文件的DAT使用频率...")
|
| 72 |
+
dat_usage = count_dat_usage(folder_path)
|
| 73 |
+
|
| 74 |
+
print("\nDAT文件使用频率统计结果(按使用次数排序):")
|
| 75 |
+
print("==========================================")
|
| 76 |
+
for i, (dat_file, count) in enumerate(dat_usage, 1):
|
| 77 |
+
print(f"{i}. {dat_file}: {count} 次")
|
| 78 |
+
|
| 79 |
+
# 也可以将结果保存到文件
|
| 80 |
+
output_file = "dat_usage统计结果.txt"
|
| 81 |
+
with open(output_file, 'w', encoding='utf-8') as f:
|
| 82 |
+
f.write("DAT文件使用频率统计结果(按使用次数排序):\n")
|
| 83 |
+
f.write("==========================================\n")
|
| 84 |
+
for i, (dat_file, count) in enumerate(dat_usage, 1):
|
| 85 |
+
f.write(f"{i}. {dat_file}: {count} 次\n")
|
| 86 |
+
|
| 87 |
+
print(f"\n统计结果已保存到 {output_file}")
|
| 88 |
+
|
| 89 |
+
if __name__ == "__main__":
|
| 90 |
+
main()
|