This commit is contained in:
34
docs/snippets/python/plugins/plugin_validator.md
Normal file
34
docs/snippets/python/plugins/plugin_validator.md
Normal file
@@ -0,0 +1,34 @@
|
||||
```python title="Python"
|
||||
from kreuzberg import (
|
||||
ExtractionResult,
|
||||
ValidationError,
|
||||
extract_file_sync,
|
||||
register_validator,
|
||||
)
|
||||
|
||||
class MinLengthValidator:
|
||||
def name(self) -> str:
|
||||
return "min_length"
|
||||
|
||||
def version(self) -> str:
|
||||
return "1.0.0"
|
||||
|
||||
def validate(self, result: ExtractionResult) -> None:
|
||||
if len(result.content) < 50:
|
||||
raise ValidationError(f"Content too short: {len(result.content)}")
|
||||
|
||||
def should_validate(self, result: ExtractionResult) -> bool:
|
||||
return True
|
||||
|
||||
def initialize(self) -> None:
|
||||
pass
|
||||
|
||||
def shutdown(self) -> None:
|
||||
pass
|
||||
|
||||
validator: MinLengthValidator = MinLengthValidator()
|
||||
register_validator(validator)
|
||||
|
||||
result = extract_file_sync("document.pdf")
|
||||
print(f"Content length: {len(result.content)}")
|
||||
```
|
||||
Reference in New Issue
Block a user