import streamlit as st
import io
from io import BytesIO
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
import google.generativeai as genai
from datetime import datetime
import json
import numpy as np
from docx import Document
import re
from prompts import SESSION_EVALUATION_PROMPT, MI_SYSTEM_PROMPT

def show_session_analysis():
    st.title("MI Session Analysis Dashboard")
    
    # Initialize session state for analysis results
    if 'analysis_results' not in st.session_state:
        st.session_state.analysis_results = None
    if 'current_transcript' not in st.session_state:
        st.session_state.current_transcript = None

    # Main layout
    col1, col2 = st.columns([1, 2])
    
    with col1:
        show_upload_section()
    
    with col2:
        if st.session_state.analysis_results:
            show_analysis_results()

def show_upload_section():
    st.header("Session Data Upload")
    
    upload_type = st.radio(
        "Select Input Method:",
        ["Audio Recording", "Video Recording", "Text Transcript", "Session Notes", "Previous Session Data"]
    )
    
    if upload_type in ["Audio Recording", "Video Recording"]:
        file = st.file_uploader(
            f"Upload {upload_type}", 
            type=["wav", "mp3", "mp4"] if upload_type == "Audio Recording" else ["mp4", "avi", "mov"]
        )
        if file:
            process_media_file(file, upload_type)
            
    elif upload_type == "Text Transcript":
        file = st.file_uploader("Upload Transcript", type=["txt", "doc", "docx", "json"])
        if file:
            process_text_file(file)
            
    elif upload_type == "Session Notes":
        show_manual_input_form()
        
    else:  # Previous Session Data
        show_previous_sessions_selector()

def process_video_file(video_file):
    """Process uploaded video file"""
    try:
        # Save video temporarily
        temp_path = f"temp_video_{datetime.now().strftime('%Y%m%d_%H%M%S')}.mp4"
        with open(temp_path, "wb") as f:
            f.write(video_file.getbuffer())
        
        st.video(temp_path)
        st.info("Video uploaded successfully. Please note: automatic transcription is not yet implemented. Please provide transcript manually.")
        
        # Add manual transcript input
        transcript = st.text_area("Please enter the session transcript:", height=300)
        if transcript:
            st.session_state.current_transcript = transcript
            analyze_session_content(transcript)
            
    except Exception as e:
        st.error(f"Error processing video: {str(e)}")

def process_audio_file(audio_file):
    """Process uploaded audio file"""
    try:
        # Save audio temporarily
        temp_path = f"temp_audio_{datetime.now().strftime('%Y%m%d_%H%M%S')}.mp3"
        with open(temp_path, "wb") as f:
            f.write(audio_file.getbuffer())
        
        st.audio(temp_path)
        st.info("Audio uploaded successfully. Please note: automatic transcription is not yet implemented. Please provide transcript manually.")
        
        # Add manual transcript input
        transcript = st.text_area("Please enter the session transcript:", height=300)
        if transcript:
            st.session_state.current_transcript = transcript
            analyze_session_content(transcript)
            
    except Exception as e:
        st.error(f"Error processing audio: {str(e)}")


def process_media_file(file, type):
    st.write(f"Processing {type}...")
    
    # Add processing status
    status = st.empty()
    progress_bar = st.progress(0)
    
    try:
        # Read file content
        file_content = file.read()
        
        status.text("Generating transcript...")
        progress_bar.progress(50)
        
        # Generate transcript using Gemini
        model = genai.GenerativeModel('gemini-pro')
        
        # Convert file content to text
        if type == "Audio Recording":
            # For audio files, create a prompt that describes the audio
            prompt = f"""
            This is an audio recording of a therapy session.
            Please transcribe the conversation and include speaker labels where possible.
            Focus on capturing:
            1. The therapist's questions and reflections
            2. The client's responses and statements
            3. Any significant pauses or non-verbal sounds
            """
        else:  # Video Recording
            # For video files, create a prompt that describes the video
            prompt = f"""
            This is a video recording of a therapy session.
            Please transcribe the conversation and include:
            1. Speaker labels
            2. Verbal communication
            3. Relevant non-verbal cues and body language
            4. Significant pauses or interactions
            """
            
        # Generate transcript
        response = model.generate_content(prompt)
        transcript = response.text
        
        if transcript:
            st.session_state.current_transcript = transcript
            status.text("Analyzing content...")
            progress_bar.progress(80)
            analyze_session_content(transcript)
            
        progress_bar.progress(100)
        status.text("Processing complete!")
            
    except Exception as e:
        st.error(f"Error processing file: {str(e)}")
    finally:
        status.empty()
        progress_bar.empty()



def get_processing_step_name(step):
    steps = [
        "Loading media file",
        "Converting to audio",
        "Performing speech recognition",
        "Generating transcript",
        "Preparing analysis"
    ]
    return steps[step]

def process_text_file(file):
    try:
        if file.name.endswith('.json'):
            content = json.loads(file.read().decode())
            transcript = extract_transcript_from_json(content)
        elif file.name.endswith('.docx'):
            doc = Document(file)
            transcript = '\n'.join([paragraph.text for paragraph in doc.paragraphs])
        else:
            transcript = file.read().decode()
            
        if transcript:
            st.session_state.current_transcript = transcript
            analyze_session_content(transcript)
            
    except Exception as e:
        st.error(f"Error processing file: {str(e)}")

def show_manual_input_form():
    st.subheader("Session Details")
    
    with st.form("session_notes_form"):
        # Basic session information
        session_date = st.date_input("Session Date", datetime.now())
        session_duration = st.number_input("Duration (minutes)", min_value=15, max_value=120, value=50)
        
        # Session content
        session_notes = st.text_area(
            "Session Notes",
            height=300,
            placeholder="Enter detailed session notes here..."
        )
        
        # Key themes and observations
        key_themes = st.text_area(
            "Key Themes",
            height=100,
            placeholder="Enter key themes identified during the session..."
        )
        
        # MI specific elements
        mi_techniques_used = st.multiselect(
            "MI Techniques Used",
            ["Open Questions", "Affirmations", "Reflections", "Summaries", 
             "Change Talk", "Commitment Language", "Planning"]
        )
        
        # Submit button
        submitted = st.form_submit_button("Analyze Session")
        
        if submitted and session_notes:
            # Combine all input into a structured format
            session_data = {
                'date': session_date,
                'duration': session_duration,
                'notes': session_notes,
                'themes': key_themes,
                'techniques': mi_techniques_used
            }
            
            # Process the session data
            st.session_state.current_transcript = format_session_data(session_data)
            analyze_session_content(st.session_state.current_transcript)


def analyze_session_content(content):
    try:
        # Configure Gemini model
        model = genai.GenerativeModel('gemini-pro')
        
        # Prepare analysis prompt
        analysis_prompt = f"""
        Analyze the following therapy session using MI principles and provide a comprehensive evaluation:

        Session Content:
        {content}

        Please provide detailed analysis including:
        1. MI Adherence Assessment:
           - OARS implementation
           - Change talk identification
           - Resistance management
           - MI spirit adherence

        2. Technical Skills Evaluation:
           - Reflection quality and frequency
           - Question-to-reflection ratio
           - Open vs. closed questions
           - Affirmations and summaries

        3. Client Language Analysis:
           - Change talk instances
           - Sustain talk patterns
           - Commitment language
           - Resistance patterns

        4. Session Flow Analysis:
           - Engagement level
           - Focus maintenance
           - Evocation quality
           - Planning effectiveness

        5. Recommendations:
           - Strength areas
           - Growth opportunities
           - Suggested interventions
           - Next session planning

        Format the analysis with clear sections and specific examples from the session.
        """
        
        # Generate analysis
        response = model.generate_content(analysis_prompt)
        
        # Process and structure the analysis results
        analysis_results = process_analysis_results(response.text)
        
        # Store results in session state
        st.session_state.analysis_results = analysis_results
        
        # Show success message
        st.success("Analysis completed successfully!")
        
    except Exception as e:
        st.error(f"Error during analysis: {str(e)}")


def generate_transcript(audio_content):
    """
    Generate transcript from audio content using Google Speech-to-Text
    Note: This requires the Google Cloud Speech-to-Text API
    """
    try:
        # Initialize Speech-to-Text client
        client = speech_v1.SpeechClient()

        # Configure audio and recognition settings
        audio = speech_v1.RecognitionAudio(content=audio_content)
        config = speech_v1.RecognitionConfig(
            encoding=speech_v1.RecognitionConfig.AudioEncoding.LINEAR16,
            sample_rate_hertz=16000,
            language_code="en-US",
            enable_automatic_punctuation=True,
        )

        # Perform the transcription
        response = client.recognize(config=config, audio=audio)

        # Combine all transcriptions
        transcript = ""
        for result in response.results:
            transcript += result.alternatives[0].transcript + " "

        return transcript.strip()

    except Exception as e:
        st.error(f"Error in transcript generation: {str(e)}")
        return None

def convert_video_to_audio(video_file):
    """
    Convert video file to audio content
    Note: This is a placeholder - you'll need to implement actual video to audio conversion
    """
    # Placeholder for video to audio conversion
    # You might want to use libraries like moviepy or ffmpeg-python
    st.warning("Video to audio conversion not implemented yet")
    return None

    
def process_analysis_results(raw_analysis):
    """Process and structure the analysis results"""
    # Parse the raw analysis text and extract structured data
    sections = extract_analysis_sections(raw_analysis)
    
    # Calculate metrics
    metrics = calculate_mi_metrics(raw_analysis)
    
    return {
        "raw_analysis": raw_analysis,
        "structured_sections": sections,
        "metrics": metrics,
        "timestamp": datetime.now().isoformat()
    }

def show_analysis_results():
    """Display the analysis results in the dashboard"""
    if not st.session_state.analysis_results:
        return
    
    # Use the analysis results directly (they're already parsed)
    analysis = st.session_state.analysis_results
    
    # Display MI Adherence Score
    st.subheader("MI Adherence Score")
    score = analysis.get('mi_adherence_score', 0)
    create_gauge_chart(score)
    
    # Display Key Themes
    st.subheader("Key Themes")
    themes = analysis.get('key_themes', [])
    if themes:
        for theme in themes:
            st.markdown(f"• {theme}")
    
    # Display Technique Usage
    st.subheader("MI Technique Usage")
    technique_usage = analysis.get('technique_usage', {})
    if technique_usage:
        fig = go.Figure(data=[
            go.Bar(x=list(technique_usage.keys()), y=list(technique_usage.values()))
        ])
        fig.update_layout(title="Technique Usage Frequency")
        st.plotly_chart(fig)
    
    # Display Strengths and Areas for Improvement
    col1, col2 = st.columns(2)
    
    with col1:
        st.subheader("Strengths")
        strengths = analysis.get('strengths', [])
        for strength in strengths:
            st.markdown(f"✓ {strength}")
    
    with col2:
        st.subheader("Areas for Improvement")
        improvements = analysis.get('areas_for_improvement', [])
        for improvement in improvements:
            st.markdown(f"△ {improvement}")
    
    # Display Session Summary
    st.subheader("Session Summary")
    st.write(analysis.get('session_summary', ''))


def show_mi_metrics_dashboard(metrics):
    st.subheader("MI Performance Dashboard")
    
    col1, col2, col3, col4 = st.columns(4)
    
    with col1:
        show_metric_card(
            "MI Spirit Score",
            metrics.get('mi_spirit_score', 0),
            "0-5 scale"
        )
    
    with col2:
        show_metric_card(
            "Change Talk Ratio",
            metrics.get('change_talk_ratio', 0),
            "Change vs Sustain"
        )
    
    with col3:
        show_metric_card(
            "Reflection Ratio",
            metrics.get('reflection_ratio', 0),
            "Reflections/Questions"
        )
    
    with col4:
        show_metric_card(
            "Overall Adherence",
            metrics.get('overall_adherence', 0),
            "Percentage"
        )

def show_metric_card(title, value, subtitle):
    st.markdown(
        f"""
        <div style="border:1px solid #ccc; padding:10px; border-radius:5px; text-align:center;">
            <h3>{title}</h3>
            <h2>{value:.2f}</h2>
            <p>{subtitle}</p>
        </div>
        """,
        unsafe_allow_html=True
    )

def show_mi_adherence_analysis(results):
    st.subheader("MI Adherence Analysis")
    
    # OARS Implementation
    st.write("### OARS Implementation")
    show_oars_chart(results['metrics'].get('oars_metrics', {}))
    
    # MI Spirit Components
    st.write("### MI Spirit Components")
    show_mi_spirit_chart(results['metrics'].get('mi_spirit_metrics', {}))
    
    # Detailed breakdown
    st.write("### Detailed Analysis")
    st.markdown(results['structured_sections'].get('mi_adherence', ''))

def show_technical_skills_analysis(results):
    st.subheader("Technical Skills Analysis")
    
    # Question Analysis
    col1, col2 = st.columns(2)
    
    with col1:
        show_question_type_chart(results['metrics'].get('question_metrics', {}))
    
    with col2:
        show_reflection_depth_chart(results['metrics'].get('reflection_metrics', {}))
    
    # Detailed analysis
    st.markdown(results['structured_sections'].get('technical_skills', ''))

def show_client_language_analysis(results):
    st.subheader("Client Language Analysis")
    
    # Change Talk Timeline
    show_change_talk_timeline(results['metrics'].get('change_talk_timeline', []))
    
    # Language Categories
    show_language_categories_chart(results['metrics'].get('language_categories', {}))
    
    # Detailed analysis
    st.markdown(results['structured_sections'].get('client_language', ''))

def show_session_flow_analysis(results):
    st.subheader("Session Flow Analysis")
    
    # Session Flow Timeline
    show_session_flow_timeline(results['metrics'].get('session_flow', []))
    
    # Engagement Metrics
    show_engagement_metrics(results['metrics'].get('engagement_metrics', {}))
    
    # Detailed analysis
    st.markdown(results['structured_sections'].get('session_flow', ''))

def show_recommendations(results):
    st.subheader("Recommendations and Next Steps")
    
    col1, col2 = st.columns(2)
    
    with col1:
        st.write("### Strengths")
        strengths = results['structured_sections'].get('strengths', [])
        for strength in strengths:
            st.markdown(f"✓ {strength}")
    
    with col2:
        st.write("### Growth Areas")
        growth_areas = results['structured_sections'].get('growth_areas', [])
        for area in growth_areas:
            st.markdown(f"→ {area}")
    
    st.write("### Suggested Interventions")
    st.markdown(results['structured_sections'].get('suggested_interventions', ''))
    
    st.write("### Next Session Planning")
    st.markdown(results['structured_sections'].get('next_session_plan', ''))

# Utility functions for charts and visualizations
def show_oars_chart(oars_metrics):
    # Create OARS radar chart using plotly
    categories = ['Open Questions', 'Affirmations', 'Reflections', 'Summaries']
    values = [
        oars_metrics.get('open_questions', 0),
        oars_metrics.get('affirmations', 0),
        oars_metrics.get('reflections', 0),
        oars_metrics.get('summaries', 0)
    ]
    
    fig = go.Figure(data=go.Scatterpolar(
        r=values,
        theta=categories,
        fill='toself'
    ))
    
    fig.update_layout(
        polar=dict(
            radialaxis=dict(
                visible=True,
                range=[0, max(values) + 1]
            )),
        showlegend=False
    )
    
    st.plotly_chart(fig)


def save_analysis_results():
    """Save analysis results to file"""
    if st.session_state.analysis_results:
        try:
            timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
            filename = f"analysis_results_{timestamp}.json"
            
            with open(filename, "w") as f:
                json.dump(st.session_state.analysis_results, f, indent=4)
            
            st.success(f"Analysis results saved to {filename}")
            
        except Exception as e:
            st.error(f"Error saving analysis results: {str(e)}")

def show_upload_section():
    """Display the upload section of the dashboard"""
    st.subheader("Upload Session")
    
    upload_type = st.radio(
        "Choose input method:",
        ["Text Transcript", "Video Recording", "Audio Recording", "Session Notes", "Previous Sessions"]
    )
    
    if upload_type == "Text Transcript":
        file = st.file_uploader("Upload transcript file", type=['txt', 'doc', 'docx'])
        if file:
            process_text_file(file)
            
    elif upload_type == "Video Recording":
        video_file = st.file_uploader("Upload video file", type=['mp4', 'mov', 'avi'])
        if video_file:
            process_video_file(video_file)
            
    elif upload_type == "Audio Recording":
        audio_file = st.file_uploader("Upload audio file", type=['mp3', 'wav', 'm4a'])
        if audio_file:
            process_audio_file(audio_file)
            
    elif upload_type == "Session Notes":
        show_manual_input_form()
        
    else:
        show_previous_sessions_selector()


def process_text_file(file):
    try:
        if file.name.endswith('.json'):
            content = json.loads(file.read().decode())
            transcript = extract_transcript_from_json(content)
        elif file.name.endswith('.docx'):
            doc = Document(file)
            transcript = '\n'.join([paragraph.text for paragraph in doc.paragraphs])
        else:
            transcript = file.read().decode()
            
        if transcript:
            st.session_state.current_transcript = transcript
            analyze_session_content(transcript)
            
    except Exception as e:
        st.error(f"Error processing file: {str(e)}")
def show_export_options():
    st.sidebar.subheader("Export Options")
    
    if st.sidebar.button("Export Analysis Report"):
        save_analysis_results()
    
    report_format = st.sidebar.selectbox(
        "Report Format",
        ["PDF", "DOCX", "JSON"]
    )
    
    if st.sidebar.button("Generate Report"):
        generate_report(report_format)

def generate_report(format):
    """Generate analysis report in specified format"""
    # Add report generation logic here
    st.info(f"Generating {format} report... (Feature coming soon)")

def show_previous_sessions_selector():
    """Display selector for previous session data"""
    st.subheader("Previous Sessions")
    
    # Load or initialize previous sessions data
    if 'previous_sessions' not in st.session_state:
        st.session_state.previous_sessions = load_previous_sessions()
    
    if not st.session_state.previous_sessions:
        st.info("No previous sessions found.")
        return
    
    # Create session selector
    sessions = st.session_state.previous_sessions
    session_dates = [session['date'] for session in sessions]
    selected_date = st.selectbox(
        "Select Session Date:",
        session_dates,
        format_func=lambda x: x.strftime("%Y-%m-%d %H:%M")
    )
    
    # Show selected session data
    if selected_date:
        selected_session = next(
            (session for session in sessions if session['date'] == selected_date),
            None
        )
        if selected_session:
            st.session_state.current_transcript = selected_session['transcript']
            analyze_session_content(selected_session['transcript'])

def load_previous_sessions():
    """Load previous session data from storage"""
    try:
        # Initialize empty list for sessions
        sessions = []
        
        # Here you would typically load from your database or file storage
        # For demonstration, we'll create some sample data
        sample_sessions = [
            {
                'date': datetime.now(),
                'transcript': "Sample transcript 1...",
                'analysis': "Sample analysis 1..."
            },
            {
                'date': datetime.now(),
                'transcript': "Sample transcript 2...",
                'analysis': "Sample analysis 2..."
            }
        ]
        
        return sample_sessions
    except Exception as e:
        st.error(f"Error loading previous sessions: {str(e)}")
        return []


def format_session_data(session_data):
    """Format session data into analyzable transcript"""
    formatted_text = f"""
    Session Date: {session_data['date']}
    Duration: {session_data['duration']} minutes
    
    SESSION NOTES:
    {session_data['notes']}
    
    KEY THEMES:
    {session_data['themes']}
    
    MI TECHNIQUES USED:
    {', '.join(session_data['techniques'])}
    """
    return formatted_text

def analyze_session_content(transcript):
    try:
        # Initialize Gemini
        model = genai.GenerativeModel('gemini-pro')
        
        # Prepare the analysis prompt
        analysis_prompt = f"""
        {MI_SYSTEM_PROMPT}
        
        Please analyze the following therapy session transcript:
        
        {transcript}
        
        {SESSION_EVALUATION_PROMPT}
        """
        
        # Generate analysis
        response = model.generate_content(analysis_prompt)
        
        # Parse the response
        analysis_results = parse_analysis_response(response.text)
        
        # Store results in session state
        st.session_state.analysis_results = analysis_results
        
    except Exception as e:
        st.error(f"Error analyzing session content: {str(e)}")

def show_analysis_results():
    """Display session analysis results"""
    if not st.session_state.analysis_results:
        st.warning("No analysis results available.")
        return
    
    st.header("Session Analysis Results")
    
    # Create tabs for different aspects of analysis
    tabs = st.tabs([
        "MI Adherence",
        "Technical Skills",
        "Client Language",
        "Session Flow",
        "Recommendations"
    ])
    
    # Parse analysis results (assuming structured response from AI)
    analysis = parse_analysis_results(st.session_state.analysis_results)
    
    # Display results in respective tabs
    with tabs[0]:
        show_mi_adherence_analysis(analysis.get('mi_adherence', {}))
    with tabs[1]:
        show_technical_skills_analysis(analysis.get('technical_skills', {}))
    with tabs[2]:
        show_client_language_analysis(analysis.get('client_language', {}))
    with tabs[3]:
        show_session_flow_analysis(analysis.get('session_flow', {}))
    with tabs[4]:
        show_recommendations(analysis.get('recommendations', {}))

def parse_analysis_response(response_text):
    """Parse the AI response into structured analysis results"""
    try:
        # Initialize default structure for analysis results
        analysis = {
            'mi_adherence_score': 0.0,
            'key_themes': [],
            'technique_usage': {},
            'strengths': [],
            'areas_for_improvement': [],
            'recommendations': [],
            'change_talk_instances': [],
            'session_summary': ""
        }
        
        # Extract MI adherence score
        score_match = re.search(r'MI Adherence Score:\s*(\d+\.?\d*)', response_text)
        if score_match:
            analysis['mi_adherence_score'] = float(score_match.group(1))
        
        # Extract key themes
        themes_section = re.search(r'Key Themes:(.*?)(?=\n\n|\Z)', response_text, re.DOTALL)
        if themes_section:
            themes = themes_section.group(1).strip().split('\n')
            analysis['key_themes'] = [theme.strip('- ') for theme in themes if theme.strip()]
        
        # Extract technique usage
        technique_section = re.search(r'Technique Usage:(.*?)(?=\n\n|\Z)', response_text, re.DOTALL)
        if technique_section:
            techniques = technique_section.group(1).strip().split('\n')
            for technique in techniques:
                if ':' in technique:
                    name, count = technique.split(':')
                    analysis['technique_usage'][name.strip()] = int(count.strip())
        
        # Extract strengths
        strengths_section = re.search(r'Strengths:(.*?)(?=\n\n|\Z)', response_text, re.DOTALL)
        if strengths_section:
            strengths = strengths_section.group(1).strip().split('\n')
            analysis['strengths'] = [s.strip('- ') for s in strengths if s.strip()]
        
        # Extract areas for improvement
        improvements_section = re.search(r'Areas for Improvement:(.*?)(?=\n\n|\Z)', response_text, re.DOTALL)
        if improvements_section:
            improvements = improvements_section.group(1).strip().split('\n')
            analysis['areas_for_improvement'] = [i.strip('- ') for i in improvements if i.strip()]
        
        # Extract session summary
        summary_section = re.search(r'Session Summary:(.*?)(?=\n\n|\Z)', response_text, re.DOTALL)
        if summary_section:
            analysis['session_summary'] = summary_section.group(1).strip()
        
        return analysis
        
    except Exception as e:
        st.error(f"Error parsing analysis response: {str(e)}")
        return None

def create_gauge_chart(score):
    """Create a gauge chart for MI Adherence Score"""
    fig = go.Figure(go.Indicator(
        mode = "gauge+number",
        value = score,
        domain = {'x': [0, 1], 'y': [0, 1]},
        title = {'text': "MI Adherence"},
        gauge = {
            'axis': {'range': [0, 100]},
            'bar': {'color': "darkblue"},
            'steps': [
                {'range': [0, 40], 'color': "lightgray"},
                {'range': [40, 70], 'color': "gray"},
                {'range': [70, 100], 'color': "darkgray"}
            ],
            'threshold': {
                'line': {'color': "red", 'width': 4},
                'thickness': 0.75,
                'value': 90
            }
        }
    ))
    
    st.plotly_chart(fig)

def create_technique_usage_chart(technique_usage):
    """Create a bar chart for MI technique usage"""
    df = pd.DataFrame(list(technique_usage.items()), columns=['Technique', 'Count'])
    fig = px.bar(
        df,
        x='Technique',
        y='Count',
        title='MI Technique Usage Frequency'
    )
    fig.update_layout(
        xaxis_title="Technique",
        yaxis_title="Frequency",
        showlegend=False
    )
    st.plotly_chart(fig)

def extract_transcript_from_json(content):
    """Extract transcript from JSON content"""
    if isinstance(content, dict):
        return json.dumps(content, indent=2)
    return str(content)
    
# Analysis display functions
def show_mi_adherence_analysis(analysis):
    st.subheader("MI Adherence Analysis")
    st.write(analysis.get('raw_text', 'No analysis available'))

def show_technical_skills_analysis(analysis):
    st.subheader("Technical Skills Analysis")
    st.write(analysis.get('raw_text', 'No analysis available'))

def show_client_language_analysis(analysis):
    st.subheader("Client Language Analysis")
    st.write(analysis.get('raw_text', 'No analysis available'))

def show_session_flow_analysis(analysis):
    st.subheader("Session Flow Analysis")
    st.write(analysis.get('raw_text', 'No analysis available'))

def show_recommendations(analysis):
    st.subheader("Recommendations")
    st.write(analysis.get('raw_text', 'No recommendations available'))
    
if __name__ == "__main__":
    show_session_analysis()