app.py

import streamlit as st
import pandas as pd
import re
from datetime import datetime
import pdfplumber
import plotly.express as px
import io

def extract_data_from_pdf(pdf_content):
    data_list = []
    current_record = {}
    
    for line in pdf_content.split('\n'):
        # Extract header information
        if 'Entreprise::' in line:
            if current_record and 'temperature_data' in current_record:
                data_list.append(current_record)
            current_record = {'temperature_data': []}
        
        # Extract metadata
        if 'Date:' in line:
            try:
                date_str = re.search(r'Date:\s*(\d{2}[./]\d{2}[./]\d{4})', line).group(1)
                date_str = date_str.replace('/', '.')
                current_record['date'] = datetime.strptime(date_str, '%d.%m.%Y').strftime('%Y-%m-%d')
            except:
                current_record['date'] = None
        
        if 'Produit:' in line:
            current_record['produit'] = line.split('Produit:')[-1].strip()
        
        if 'Utilisateur:' in line:
            current_record['utilisateur'] = line.split('Utilisateur:')[-1].strip()
        
        # Extract temperature data
        if any(x in line for x in ['Début', '+ ', 'Fin']) and '°C' in line:
            try:
                parts = line.strip().split()
                time = parts[0] if 'Début' in line or 'Fin' in line else parts[1]
                
                # Extract temperature values
                temp_sterilisateur = float(parts[-3].replace('°C', ''))
                temp_coeur = float(parts[-2].replace('°C', ''))
                valeur_f = float(parts[-1])
                
                current_record['temperature_data'].append({
                    'temps': time,
                    'temp_sterilisateur': temp_sterilisateur,
                    'temp_coeur': temp_coeur,
                    'valeur_f': valeur_f
                })
            except Exception as e:
                # If extraction fails, skip the line
                continue
    
    # Add last record
    if current_record and 'temperature_data' in current_record:
        data_list.append(current_record)
    
    return data_list

def analyze_sterilization(data):
    results = []
    
    for record in data:
        temp_data = pd.DataFrame(record['temperature_data'])
        
        # Skip if temperature data is empty
        if temp_data.empty:
            st.warning(f"Données de température manquantes pour l'enregistrement du {record['date']}")
            continue
        
        # Determine product type and required temperature
        is_nutabreizh = 'NutaBreizh' in record['produit']
        required_temp = 108 if is_nutabreizh else 103
        
        # Count minutes at required temperature
        minutes_at_temp = len(temp_data[temp_data['temp_coeur'] >= required_temp])
        
        # Calculate max temperatures
        max_temp_sterilisateur = temp_data['temp_sterilisateur'].max()
        max_temp_coeur = temp_data['temp_coeur'].max()
        
        # Determine if criteria met
        criteria_met = minutes_at_temp >= 30
        
        results.append({
            'Date': record['date'],
            'Produit': record['produit'],
            'Utilisateur': record['utilisateur'],
            'Temperature_Requise': required_temp,
            'Minutes_Temperature_Requise': minutes_at_temp,
            'Temperature_Max_Sterilisateur': max_temp_sterilisateur,
            'Temperature_Max_Coeur': max_temp_coeur,
            'Criteres_Respectes': criteria_met
        })
    
    return pd.DataFrame(results)

def main():
    st.title("Analyse des Protocoles de Stérilisation")
    
    uploaded_file = st.file_uploader("Choisir un fichier PDF", type="pdf")
    
    if uploaded_file is not None:
        # Read PDF content
        pdf_text = ""
        with pdfplumber.open(uploaded_file) as pdf:
            for page in pdf.pages:
                pdf_text += page.extract_text() + "\n"
        
        # Process data
        data = extract_data_from_pdf(pdf_text)
        results_df = analyze_sterilization(data)
        
        # Display results
        st.subheader("Résultats de l'analyse")
        st.dataframe(results_df)
        
        # Create visualization
        if not results_df.empty:
            fig = px.scatter(results_df, 
                            x='Date', 
                            y='Minutes_Temperature_Requise',
                            color='Criteres_Respectes',
                            hover_data=['Produit', 'Temperature_Requise'],
                            title="Minutes à température requise par production")
            st.plotly_chart(fig)
        else:
            st.warning("Aucune donnée valide à afficher.")
        
        # Export button
        if st.button("Exporter en Excel"):
            output = io.BytesIO()
            with pd.ExcelWriter(output, engine='xlsxwriter') as writer:
                results_df.to_excel(writer, index=False)
            
            output.seek(0)
            st.download_button(
                label="Télécharger l'analyse",
                data=output,
                file_name="analyse_sterilisation.xlsx",
                mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
            )

if __name__ == "__main__":
    main()