presidio_helpers.py

from typing import List, Optional, Tuple
import logging
import streamlit as st
from presidio_analyzer import (
    AnalyzerEngine,
    RecognizerResult,
    RecognizerRegistry,
    PatternRecognizer,
    Pattern,
)
from presidio_analyzer.nlp_engine import NlpEngine
from presidio_anonymizer import AnonymizerEngine
from presidio_anonymizer.entities import OperatorConfig

from openai_fake_data_generator import (
    call_completion_model,
    OpenAIParams,
    create_prompt,
)
from presidio_nlp_engine_config import (
    create_nlp_engine_with_spacy,
    create_nlp_engine_with_transformers,
)

logger = logging.getLogger("presidio-streamlit")

@st.cache_resource
def nlp_engine_and_registry(
    model_family: str,
    model_path: str,
    ta_key: Optional[str] = None,
    ta_endpoint: Optional[str] = None,
) -> Tuple[NlpEngine, RecognizerRegistry]:
    if "spacy" in model_family.lower():
        return create_nlp_engine_with_spacy(model_path)
    elif "transformers" in model_family.lower() or "iiiorg" in model_family.lower():
        return create_nlp_engine_with_transformers(model_path)
    else:
        raise ValueError(f"Model family {model_family} not supported")

@st.cache_resource
def analyzer_engine(
    model_family: str,
    model_path: str,
    ta_key: Optional[str] = None,
    ta_endpoint: Optional[str] = None,
) -> AnalyzerEngine:
    nlp_engine, registry = nlp_engine_and_registry(
        model_family, model_path, ta_key, ta_endpoint
    )
    analyzer = AnalyzerEngine(nlp_engine=nlp_engine, registry=registry)
    return analyzer

# ... (zbytek pomocných funkcí)