Spaces:
Running
Running
Create validate_data.py
Browse files- validate_data.py +45 -0
validate_data.py
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
def validate_inputs(snippets):
|
| 2 |
+
"""数据验证工具"""
|
| 3 |
+
errors = []
|
| 4 |
+
valid_data = []
|
| 5 |
+
|
| 6 |
+
for idx, s in enumerate(snippets):
|
| 7 |
+
# 类型检查
|
| 8 |
+
if not isinstance(s, str):
|
| 9 |
+
errors.append(f"索引 {idx}: 类型错误 ({type(s)}) → 已转换")
|
| 10 |
+
s = str(s)
|
| 11 |
+
|
| 12 |
+
# 清理数据
|
| 13 |
+
cleaned = s.replace("...", "").strip()
|
| 14 |
+
|
| 15 |
+
# 有效性检查
|
| 16 |
+
if len(cleaned) < 10: # 最小代码长度
|
| 17 |
+
errors.append(f"索引 {idx}: 代码过短 ({len(cleaned)} 字符)")
|
| 18 |
+
continue
|
| 19 |
+
|
| 20 |
+
valid_data.append(cleaned)
|
| 21 |
+
|
| 22 |
+
# 输出报告
|
| 23 |
+
print(f"验证结果:\n成功 {len(valid_data)} 条\n错误 {len(errors)} 条")
|
| 24 |
+
for err in errors[:3]: # 显示前3个错误
|
| 25 |
+
print(f" - {err}")
|
| 26 |
+
if len(errors) > 3:
|
| 27 |
+
print(f" ...(共 {len(errors)} 个错误)")
|
| 28 |
+
|
| 29 |
+
return valid_data
|
| 30 |
+
|
| 31 |
+
if __name__ == "__main__":
|
| 32 |
+
# 测试数据
|
| 33 |
+
test_data = [
|
| 34 |
+
"def example(): pass",
|
| 35 |
+
12345, # 错误类型
|
| 36 |
+
"print(...)", # 包含...
|
| 37 |
+
" ", # 空字符串
|
| 38 |
+
"""def valid_func():
|
| 39 |
+
return '正确代码'"""
|
| 40 |
+
]
|
| 41 |
+
|
| 42 |
+
validated = validate_inputs(test_data)
|
| 43 |
+
print("\n有效数据示例:")
|
| 44 |
+
for i, data in enumerate(validated[:2]):
|
| 45 |
+
print(f"[{i}] {data[:50]}...")
|