File size: 8,115 Bytes
63f0b06 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 | from typing import Any, Dict, List, Optional, Union, Callable
import re
import os
from pathlib import Path
from .logger import get_logger
from .exceptions import ValidationError
logger = get_logger(__name__)
class Validator:
@staticmethod
def required(value: Any, field_name: str = "field") -> Any:
if value is None:
raise ValidationError(field_name, None, "value is required")
if isinstance(value, str) and not value.strip():
raise ValidationError(field_name, value, "value cannot be empty")
if isinstance(value, (list, dict)) and len(value) == 0:
raise ValidationError(field_name, str(value), "value cannot be empty")
return value
@staticmethod
def string(
value: Any,
field_name: str = "field",
min_length: int = None,
max_length: int = None,
pattern: str = None
) -> str:
if not isinstance(value, str):
raise ValidationError(field_name, str(value), "must be a string")
if min_length is not None and len(value) < min_length:
raise ValidationError(
field_name,
value,
f"must be at least {min_length} characters long"
)
if max_length is not None and len(value) > max_length:
raise ValidationError(
field_name,
value,
f"must be no more than {max_length} characters long"
)
if pattern is not None and not re.match(pattern, value):
raise ValidationError(
field_name,
value,
f"must match pattern: {pattern}"
)
return value
@staticmethod
def number(
value: Any,
field_name: str = "field",
min_value: Union[int, float] = None,
max_value: Union[int, float] = None,
integer_only: bool = False
) -> Union[int, float]:
try:
if integer_only:
num_value = int(value)
else:
num_value = float(value)
except (ValueError, TypeError):
raise ValidationError(
field_name,
str(value),
f"must be a {'integer' if integer_only else 'number'}"
)
if min_value is not None and num_value < min_value:
raise ValidationError(
field_name,
str(value),
f"must be at least {min_value}"
)
if max_value is not None and num_value > max_value:
raise ValidationError(
field_name,
str(value),
f"must be no more than {max_value}"
)
return num_value
@staticmethod
def file_path(
value: Any,
field_name: str = "field",
must_exist: bool = True,
allowed_extensions: List[str] = None
) -> Path:
if not isinstance(value, (str, Path)):
raise ValidationError(field_name, str(value), "must be a valid file path")
path = Path(value)
if must_exist and not path.exists():
raise ValidationError(field_name, str(value), "file does not exist")
if allowed_extensions:
extension = path.suffix.lower()
if extension not in [ext.lower() for ext in allowed_extensions]:
raise ValidationError(
field_name,
str(value),
f"must have one of these extensions: {', '.join(allowed_extensions)}"
)
return path
@staticmethod
def choice(
value: Any,
field_name: str = "field",
choices: List[Any] = None
) -> Any:
if choices is not None and value not in choices:
raise ValidationError(
field_name,
str(value),
f"must be one of: {', '.join(str(c) for c in choices)}"
)
return value
@staticmethod
def email(value: Any, field_name: str = "field") -> str:
email_pattern = r'^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$'
if not isinstance(value, str):
raise ValidationError(field_name, str(value), "must be a string")
if not re.match(email_pattern, value):
raise ValidationError(field_name, value, "must be a valid email address")
return value.lower()
@staticmethod
def url(value: Any, field_name: str = "field") -> str:
url_pattern = r'^https?://(?:[-\w.])+(?:\:[0-9]+)?(?:/(?:[\w/_.])*(?:\?(?:[\w&=%.])*)?(?:\#(?:\w)*)?)?$'
if not isinstance(value, str):
raise ValidationError(field_name, str(value), "must be a string")
if not re.match(url_pattern, value):
raise ValidationError(field_name, value, "must be a valid URL")
return value
def validate_request_data(schema: Dict[str, Dict[str, Any]]):
def decorator(func: Callable) -> Callable:
def wrapper(*args, **kwargs):
return func(*args, **kwargs)
return wrapper
return decorator
def validate_model_config(config: Dict[str, Any]) -> Dict[str, Any]:
errors = {}
required_fields = ['model_type', 'sample_rate']
for field in required_fields:
try:
Validator.required(config.get(field), field)
except ValidationError as e:
errors[field] = [str(e)]
if 'sample_rate' in config:
try:
Validator.number(
config['sample_rate'],
'sample_rate',
min_value=8000,
max_value=48000,
integer_only=True
)
except ValidationError as e:
errors['sample_rate'] = [str(e)]
if 'model_type' in config:
try:
Validator.choice(
config['model_type'],
'model_type',
choices=['autoencoder', 'diffusion', 'lm']
)
except ValidationError as e:
errors['model_type'] = [str(e)]
if errors:
logger.error(f"Model configuration validation failed: {errors}")
raise ValidationError("model_config", str(config), f"validation failed: {errors}")
return config
def validate_training_config(config: Dict[str, Any]) -> Dict[str, Any]:
errors = {}
if 'modelName' in config:
try:
Validator.string(
config['modelName'],
'modelName',
min_length=1,
max_length=100
)
except ValidationError as e:
errors['modelName'] = [str(e)]
if 'epochs' in config:
try:
Validator.number(
config['epochs'],
'epochs',
min_value=1,
max_value=1000,
integer_only=True
)
except ValidationError as e:
errors['epochs'] = [str(e)]
if 'batchSize' in config:
try:
Validator.number(
config['batchSize'],
'batchSize',
min_value=1,
max_value=64,
integer_only=True
)
except ValidationError as e:
errors['batchSize'] = [str(e)]
if 'learningRate' in config:
try:
Validator.number(
config['learningRate'],
'learningRate',
min_value=1e-6,
max_value=1e-1
)
except ValidationError as e:
errors['learningRate'] = [str(e)]
if errors:
logger.error(f"Training configuration validation failed: {errors}")
raise ValidationError("training_config", str(config), f"validation failed: {errors}")
return config |