"""Streamlit app for Presidio + Privy-trained PII models.""" import spacy from spacy_recognizer import CustomSpacyRecognizer from presidio_analyzer.nlp_engine import NlpEngineProvider from presidio_anonymizer import AnonymizerEngine from presidio_analyzer import AnalyzerEngine, RecognizerRegistry import pandas as pd from annotated_text import annotated_text from json import JSONEncoder import json import warnings import streamlit as st import os import csv os.environ["TOKENIZERS_PARALLELISM"] = "false" warnings.filterwarnings('ignore') # from flair_recognizer import FlairRecognizer def load_data(file_location): unpacked_string_data = [] unpacked_url_data = [] unpacked_json_data = [] # Read the data back from the CSV file and unpack it with open(file_location, mode='r') as csv_file: reader = csv.reader(csv_file) for row in reader: unpacked_string_data.append(row[0]) unpacked_url_data.append(row[1]) unpacked_json_data.append(json.loads(row[2])) # print("Unpacked string data:", unpacked_string_data) # print("Unpacked url data:", unpacked_url_data) # print("Unpacked JSON data:", unpacked_json_data) return unpacked_string_data, dict(zip(unpacked_string_data, unpacked_json_data)) # Helper methods @st.cache(allow_output_mutation=True) def analyzer_engine(): """Return AnalyzerEngine.""" spacy_recognizer = CustomSpacyRecognizer() configuration = { # print("ENALBEE MODELES") "nlp_engine_name": "spacy", "models": [ {"lang_code": "en", "model_name": "en_spacy_pii_distilbert"}], } # Create NLP engine based on configuration provider = NlpEngineProvider(nlp_configuration=configuration) nlp_engine = provider.create_engine() registry = RecognizerRegistry() # add rule-based recognizers registry.load_predefined_recognizers(nlp_engine=nlp_engine) registry.add_recognizer(spacy_recognizer) # remove the nlp engine we passed, to use custom label mappings registry.remove_recognizer("SpacyRecognizer") analyzer = AnalyzerEngine(nlp_engine=nlp_engine, registry=registry, supported_languages=["en"]) # uncomment for flair-based NLP recognizer # flair_recognizer = FlairRecognizer() # registry.load_predefined_recognizers() # registry.add_recognizer(flair_recognizer) # analyzer = AnalyzerEngine(registry=registry, supported_languages=["en"]) return analyzer @st.cache(allow_output_mutation=True) def anonymizer_engine(): """Return AnonymizerEngine.""" return AnonymizerEngine() def get_supported_entities(): """Return supported entities from the Analyzer Engine.""" return analyzer_engine().get_supported_entities() def analyze(**kwargs): """Analyze input using Analyzer engine and input arguments (kwargs).""" if "entities" not in kwargs or "All" in kwargs["entities"]: kwargs["entities"] = None return analyzer_engine().analyze(**kwargs) def anonymize(text, analyze_results): """Anonymize identified input using Presidio Abonymizer.""" if not text: return res = anonymizer_engine().anonymize(text, analyze_results) return res.text def annotate(text, st_analyze_results, st_entities): tokens = [] # sort by start index results = sorted(st_analyze_results, key=lambda x: x.start) for i, res in enumerate(results): if i == 0: tokens.append(text[:res.start]) # append entity text and entity type tokens.append((text[res.start: res.end], res.entity_type)) # if another entity coming i.e. we're not at the last results element, add text up to next entity if i != len(results) - 1: tokens.append(text[res.end:results[i+1].start]) # if no more entities coming, add all remaining text else: tokens.append(text[res.end:]) return tokens st.set_page_config(page_title="Bitahoy demo", layout="wide") # Side bar ------------------------------------------- st.sidebar.markdown( """ Detect and anonymize PII in structured text such as protocol traces (JSON, SQL, XML etc.) """ ) # add picture with st.sidebar.image("assets/bitahoy-logo.png", width=200) # dropdown titles, json_dict = load_data("assets/data_sorted.csv") option_list = titles option = st.sidebar.selectbox( 'Choose an existing structured input?', option_list) # st.sidebar.write('You selected:', option) st.sidebar.code (json_dict[option]) st.sidebar.write('Use button to copy input to clipboard') #romans complex dropdown # st.checkbox("Enable/Disable input of existing data", key="disabled") # # option = st.selectbox( # "Choose an existing structured input?", # option_list, # # label_visibility=st.session_state.visibility, # disabled=st.session_state.disabled, # ) # st.write('You selected:', option) st_entities = st.sidebar.multiselect( label="Which entities to look for?", options=get_supported_entities(), default=list(get_supported_entities()), ) st_threshold = st.sidebar.slider( label="Acceptance threshold", min_value=0.0, max_value=1.0, value=0.35 ) st_return_decision_process = st.sidebar.checkbox( "Add analysis explanations in json") button = st.sidebar.button("Detect PII") # vertical space st.sidebar.text("") # vertical space st.sidebar.text("") st.sidebar.info( "Privy is an open source framework for synthetic data generation in protocol trace formats (json, sql, html etc). Presidio is an open source framework for PII detection and anonymization. " "For more info visit [privy](https://github.com/pixie-io/pixie/tree/main/src/datagen/pii/privy) and [aka.ms/presidio](https://aka.ms/presidio)" ) # Main panel analyzer_load_state = st.info( "Starting analyzer and loading model...") engine = analyzer_engine() analyzer_load_state.empty() # col? # Store the initial value of widgets in session state if "visibility" not in st.session_state: st.session_state.visibility = "visible" st.session_state.disabled = False col1, col2 = st.columns(2) with col1: st.subheader("Input") # st.radio( # "Set selectbox label visibility 👉", # key="visibility", # options=["visible", "hidden", "collapsed"], # ) # st.json({ }) st_text = st.text_area( label="Type in some text", value="SELECT shipping FROM users WHERE shipping = '201 Thayer St Providence RI 02912'" "\n\n" "{user: Willie Porter, ip: 192.168.2.80, email: willie@gmail.com}", height=200, ) with col2: st.subheader("Analyzed") with st.spinner("Analyzing..."): if button or st.session_state.first_load: st_analyze_results = analyze( text=st_text, entities=st_entities, language="en", score_threshold=st_threshold, return_decision_process=st_return_decision_process, ) annotated_tokens = annotate(st_text, st_analyze_results, st_entities) # annotated_tokens annotated_text(*annotated_tokens) # end of col if 'first_load' not in st.session_state: st.session_state['first_load'] = True # After st.subheader("Anonymized final results") with st.spinner("Anonymizing..."): if button or st.session_state.first_load: st_anonymize_results = anonymize(st_text, st_analyze_results) st_anonymize_results # table result st.subheader("Detailed Findings") if st_analyze_results: res_dicts = [r.to_dict() for r in st_analyze_results] for d in res_dicts: d['Value'] = st_text[d['start']:d['end']] df = pd.DataFrame.from_records(res_dicts) df = df[["entity_type", "Value", "score", "start", "end"]].rename( { "entity_type": "Entity type", "start": "Start", "end": "End", "score": "Confidence", }, axis=1, ) st.dataframe(df, width=1000) else: st.text("No findings") st.session_state['first_load'] = True # json result class ToDictListEncoder(JSONEncoder): """Encode dict to json.""" def default(self, o): """Encode to JSON using to_dict.""" if o: return o.to_dict() return [] if st_return_decision_process: st.json(json.dumps(st_analyze_results, cls=ToDictListEncoder))