| import json
|
| import re
|
|
|
|
|
| with open("en.json", "r") as f:
|
| model_data = json.load(f)
|
|
|
|
|
| patterns = {
|
| "phone": r"\b\d{3}[-.\s]?\d{3}[-.\s]?\d{4}\b",
|
| "url": r"https?://\S+|www\.\S+",
|
| "email": r"\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b"
|
| }
|
|
|
|
|
| def classify_text(text):
|
| annotations = []
|
|
|
| for entity, pattern in patterns.items():
|
| matches = re.findall(pattern, text)
|
| for match in matches:
|
| annotations.append({"token": match, "type": entity, "confidence_score": 0.9})
|
|
|
| return {"annotations": annotations}
|
|
|
|
|
| test_text = "Hello world this is Call 123-456-7890 or visit www.example.com or email test@example.com soe other text."
|
| result = classify_text(test_text)
|
| print("Classification Result:", json.dumps(result, indent=2))
|
|
|
