app.py

import torch
import gradio as gr
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import plotly.graph_objects as go
import plotly.express as px
from plotly.subplots import make_subplots
import numpy as np
from wordcloud import WordCloud
from collections import Counter, defaultdict
import re
import json
import csv
import io
import tempfile
from datetime import datetime
import logging
from functools import lru_cache
from dataclasses import dataclass
from typing import List, Dict, Optional, Tuple
import nltk
from nltk.corpus import stopwords
import langdetect
import pandas as pd

# Configuration
@dataclass
class Config:
    MAX_HISTORY_SIZE: int = 500
    BATCH_SIZE_LIMIT: int = 30
    MAX_TEXT_LENGTH: int = 512
    CACHE_SIZE: int = 64
    
    # Supported languages and models
    SUPPORTED_LANGUAGES = {
        'auto': 'Auto Detect',
        'en': 'English',
        'zh': 'Chinese',
        'es': 'Spanish',
        'fr': 'French',
        'de': 'German',
        'sv': 'Swedish'
    }
    
    MODELS = {
        'en': "cardiffnlp/twitter-roberta-base-sentiment-latest",
        'multilingual': "cardiffnlp/twitter-xlm-roberta-base-sentiment"
    }
    
    # Color themes
    THEMES = {
        'default': {'pos': '#4CAF50', 'neg': '#F44336', 'neu': '#FF9800'},
        'ocean': {'pos': '#0077BE', 'neg': '#FF6B35', 'neu': '#00BCD4'},
        'dark': {'pos': '#66BB6A', 'neg': '#EF5350', 'neu': '#FFA726'},
        'rainbow': {'pos': '#9C27B0', 'neg': '#E91E63', 'neu': '#FF5722'}
    }

config = Config()

# Logging setup
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

# Initialize NLTK
try:
    nltk.download('stopwords', quiet=True)
    nltk.download('punkt', quiet=True)
    STOP_WORDS = set(stopwords.words('english'))
except:
    STOP_WORDS = {'the', 'a', 'an', 'and', 'or', 'but', 'in', 'on', 'at', 'to', 'for', 'of', 'with', 'by'}

class ModelManager:
    """Manages multiple language models"""
    def __init__(self):
        self.models = {}
        self.tokenizers = {}
        self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
        self._load_default_model()
    
    def _load_default_model(self):
        """Load the default English model"""
        try:
            model_name = config.MODELS['multilingual']  # Use multilingual as default
            self.tokenizers['default'] = AutoTokenizer.from_pretrained(model_name)
            self.models['default'] = AutoModelForSequenceClassification.from_pretrained(model_name)
            self.models['default'].to(self.device)
            logger.info(f"Default model loaded: {model_name}")
        except Exception as e:
            logger.error(f"Failed to load default model: {e}")
            raise
    
    def get_model(self, language='en'):
        """Get model for specific language"""
        if language in ['en', 'auto'] or language not in config.SUPPORTED_LANGUAGES:
            return self.models['default'], self.tokenizers['default']
        return self.models['default'], self.tokenizers['default']  # Use multilingual for all
    
    @staticmethod
    def detect_language(text: str) -> str:
        """Detect text language properly"""
        try:
            # Use langdetect for all languages
            detected = langdetect.detect(text)
            # Map some common langdetect codes to our supported languages
            language_mapping = {
                'zh-cn': 'zh',
                'zh-tw': 'zh'
            }
            detected = language_mapping.get(detected, detected)
            return detected if detected in config.SUPPORTED_LANGUAGES else 'en'
        except:
            return 'en'

model_manager = ModelManager()

class HistoryManager:
    """Enhanced history manager with more features"""
    def __init__(self):
        self._history = []
    
    def add_entry(self, entry: Dict):
        self._history.append(entry)
        if len(self._history) > config.MAX_HISTORY_SIZE:
            self._history = self._history[-config.MAX_HISTORY_SIZE:]
    
    def add_batch_entries(self, entries: List[Dict]):
        """Add multiple entries at once"""
        for entry in entries:
            self.add_entry(entry)
    
    def get_history(self) -> List[Dict]:
        return self._history.copy()
    
    def get_recent_history(self, n: int = 10) -> List[Dict]:
        """Get n most recent entries"""
        return self._history[-n:] if self._history else []
    
    def filter_history(self, sentiment: str = None, language: str = None, 
                      min_confidence: float = None) -> List[Dict]:
        """Filter history by criteria"""
        filtered = self._history
        
        if sentiment:
            filtered = [h for h in filtered if h['sentiment'] == sentiment]
        if language:
            filtered = [h for h in filtered if h.get('language', 'en') == language]
        if min_confidence:
            filtered = [h for h in filtered if h['confidence'] >= min_confidence]
            
        return filtered
    
    def clear(self) -> int:
        count = len(self._history)
        self._history.clear()
        return count
    
    def get_stats(self) -> Dict:
        if not self._history:
            return {}
        
        sentiments = [item['sentiment'] for item in self._history]
        confidences = [item['confidence'] for item in self._history]
        languages = [item.get('language', 'en') for item in self._history]
        
        return {
            'total_analyses': len(self._history),
            'positive_count': sentiments.count('Positive'),
            'negative_count': sentiments.count('Negative'),
            'neutral_count': sentiments.count('Neutral'),
            'avg_confidence': np.mean(confidences),
            'max_confidence': np.max(confidences),
            'min_confidence': np.min(confidences),
            'languages_detected': len(set(languages)),
            'most_common_language': Counter(languages).most_common(1)[0][0] if languages else 'en',
            'avg_text_length': np.mean([len(item.get('full_text', '')) for item in self._history])
        }

history_manager = HistoryManager()

class TextProcessor:
    """Enhanced text processing"""
    
    @staticmethod
    @lru_cache(maxsize=config.CACHE_SIZE)
    def clean_text(text: str, remove_punctuation: bool = True, remove_numbers: bool = False) -> str:
        """Clean text with options"""
        text = text.lower().strip()
        
        if remove_numbers:
            text = re.sub(r'\d+', '', text)
        
        if remove_punctuation:
            text = re.sub(r'[^\w\s]', '', text)
        
        words = text.split()
        cleaned_words = [w for w in words if w not in STOP_WORDS and len(w) > 2]
        return ' '.join(cleaned_words)
    
    @staticmethod
    def extract_keywords(text: str, top_k: int = 5) -> List[str]:
        """Extract key words from text"""
        # For Chinese text, extract characters
        if re.search(r'[\u4e00-\u9fff]', text):
            words = re.findall(r'[\u4e00-\u9fff]+', text)
            all_chars = ''.join(words)
            char_freq = Counter(all_chars)
            return [char for char, _ in char_freq.most_common(top_k)]
        else:
            # For other languages, use word-based extraction
            cleaned = TextProcessor.clean_text(text)
            words = cleaned.split()
            word_freq = Counter(words)
            return [word for word, _ in word_freq.most_common(top_k)]

    @staticmethod
    def parse_batch_input(text: str) -> List[str]:
        """Parse batch input from textarea"""
        lines = text.strip().split('\n')
        return [line.strip() for line in lines if line.strip()]

class SentimentAnalyzer:
    """Enhanced sentiment analysis"""
    
    @staticmethod
    def analyze_text(text: str, language: str = 'auto', preprocessing_options: Dict = None) -> Dict:
        """Analyze single text with language support"""
        if not text.strip():
            raise ValueError("Empty text provided")
        
        # Detect language if auto
        if language == 'auto':
            detected_lang = model_manager.detect_language(text)
        else:
            detected_lang = language
        
        # Get appropriate model
        model, tokenizer = model_manager.get_model(detected_lang)
        
        # Preprocessing options - don't clean Chinese text
        options = preprocessing_options or {}
        processed_text = text
        if options.get('clean_text', False) and not re.search(r'[\u4e00-\u9fff]', text):
            processed_text = TextProcessor.clean_text(
                text, 
                options.get('remove_punctuation', True),
                options.get('remove_numbers', False)
            )
        
        try:
            # Tokenize and analyze
            inputs = tokenizer(processed_text, return_tensors="pt", padding=True, 
                             truncation=True, max_length=config.MAX_TEXT_LENGTH).to(model_manager.device)
            
            with torch.no_grad():
                outputs = model(**inputs)
                probs = torch.nn.functional.softmax(outputs.logits, dim=-1).cpu().numpy()[0]
                
            # Handle different model outputs
            if len(probs) == 3:  # negative, neutral, positive
                sentiment_idx = np.argmax(probs)
                sentiment_labels = ['Negative', 'Neutral', 'Positive']
                sentiment = sentiment_labels[sentiment_idx]
                confidence = float(probs[sentiment_idx])
                
                result = {
                    'sentiment': sentiment,
                    'confidence': confidence,
                    'neg_prob': float(probs[0]),
                    'neu_prob': float(probs[1]),
                    'pos_prob': float(probs[2]),
                    'has_neutral': True
                }
            else:  # negative, positive
                pred = np.argmax(probs)
                sentiment = "Positive" if pred == 1 else "Negative"
                confidence = float(probs[pred])
                
                result = {
                    'sentiment': sentiment,
                    'confidence': confidence,
                    'neg_prob': float(probs[0]),
                    'pos_prob': float(probs[1]),
                    'neu_prob': 0.0,
                    'has_neutral': False
                }
            
            # Add metadata
            result.update({
                'language': detected_lang,
                'keywords': TextProcessor.extract_keywords(text),
                'word_count': len(text.split()),
                'char_count': len(text)
            })
            
            return result
            
        except Exception as e:
            logger.error(f"Analysis failed: {e}")
            raise

    @staticmethod
    def analyze_batch(texts: List[str], language: str = 'auto', 
                     preprocessing_options: Dict = None) -> List[Dict]:
        """Analyze multiple texts"""
        results = []
        for i, text in enumerate(texts):
            try:
                result = SentimentAnalyzer.analyze_text(text, language, preprocessing_options)
                result['batch_index'] = i
                results.append(result)
            except Exception as e:
                # Add error result
                results.append({
                    'sentiment': 'Error',
                    'confidence': 0.0,
                    'error': str(e),
                    'batch_index': i,
                    'text': text
                })
        return results

class PlotlyVisualizer:
    """Enhanced visualizations with Plotly"""
    
    @staticmethod
    def create_sentiment_gauge(result: Dict, theme: str = 'default') -> go.Figure:
        """Create an animated sentiment gauge"""
        colors = config.THEMES[theme]
        
        if result['has_neutral']:
            # Three-way gauge
            fig = go.Figure(go.Indicator(
                mode = "gauge+number+delta",
                value = result['pos_prob'] * 100,
                domain = {'x': [0, 1], 'y': [0, 1]},
                title = {'text': f"Sentiment: {result['sentiment']}"},
                delta = {'reference': 50},
                gauge = {
                    'axis': {'range': [None, 100]},
                    'bar': {'color': colors['pos'] if result['sentiment'] == 'Positive' else colors['neg']},
                    'steps': [
                        {'range': [0, 33], 'color': colors['neg']},
                        {'range': [33, 67], 'color': colors['neu']},
                        {'range': [67, 100], 'color': colors['pos']}
                    ],
                    'threshold': {
                        'line': {'color': "red", 'width': 4},
                        'thickness': 0.75,
                        'value': 90
                    }
                }
            ))
        else:
            # Two-way gauge
            fig = go.Figure(go.Indicator(
                mode = "gauge+number",
                value = result['confidence'] * 100,
                domain = {'x': [0, 1], 'y': [0, 1]},
                title = {'text': f"Confidence: {result['sentiment']}"},
                gauge = {
                    'axis': {'range': [None, 100]},
                    'bar': {'color': colors['pos'] if result['sentiment'] == 'Positive' else colors['neg']},
                    'steps': [
                        {'range': [0, 50], 'color': "lightgray"},
                        {'range': [50, 100], 'color': "gray"}
                    ]
                }
            ))
        
        fig.update_layout(height=400, font={'size': 16})
        return fig
    
    @staticmethod
    def create_probability_bars(result: Dict, theme: str = 'default') -> go.Figure:
        """Create probability bar chart"""
        colors = config.THEMES[theme]
        
        if result['has_neutral']:
            labels = ['Negative', 'Neutral', 'Positive']
            values = [result['neg_prob'], result['neu_prob'], result['pos_prob']]
            bar_colors = [colors['neg'], colors['neu'], colors['pos']]
        else:
            labels = ['Negative', 'Positive']
            values = [result['neg_prob'], result['pos_prob']]
            bar_colors = [colors['neg'], colors['pos']]
        
        fig = go.Figure(data=[
            go.Bar(x=labels, y=values, marker_color=bar_colors, text=[f'{v:.3f}' for v in values])
        ])
        
        fig.update_traces(texttemplate='%{text}', textposition='outside')
        fig.update_layout(
            title="Sentiment Probabilities",
            yaxis_title="Probability",
            height=400,
            showlegend=False
        )
        
        return fig

    @staticmethod
    def create_batch_summary(results: List[Dict], theme: str = 'default') -> go.Figure:
        """Create batch analysis summary"""
        colors = config.THEMES[theme]
        
        # Count sentiments
        sentiments = [r['sentiment'] for r in results if 'sentiment' in r]
        sentiment_counts = Counter(sentiments)
        
        # Create pie chart
        fig = go.Figure(data=[go.Pie(
            labels=list(sentiment_counts.keys()),
            values=list(sentiment_counts.values()),
            marker_colors=[colors.get(s.lower()[:3], '#999999') for s in sentiment_counts.keys()],
            textinfo='label+percent',
            hole=0.3
        )])
        
        fig.update_layout(
            title=f"Batch Analysis Summary ({len(results)} texts)",
            height=400
        )
        
        return fig

    @staticmethod
    def create_confidence_distribution(results: List[Dict]) -> go.Figure:
        """Create confidence distribution plot"""
        confidences = [r['confidence'] for r in results if 'confidence' in r and r['sentiment'] != 'Error']
        
        if not confidences:
            return go.Figure()
        
        fig = go.Figure(data=[go.Histogram(
            x=confidences,
            nbinsx=20,
            marker_color='skyblue',
            opacity=0.7
        )])
        
        fig.update_layout(
            title="Confidence Distribution",
            xaxis_title="Confidence Score",
            yaxis_title="Frequency",
            height=400
        )
        
        return fig
    
    @staticmethod
    def create_history_dashboard(history: List[Dict]) -> go.Figure:
        """Create comprehensive history dashboard"""
        if len(history) < 2:
            return go.Figure()
        
        # Create subplots
        fig = make_subplots(
            rows=2, cols=2,
            subplot_titles=['Sentiment Timeline', 'Confidence Distribution', 
                           'Language Distribution', 'Sentiment Summary'],
            specs=[[{"secondary_y": False}, {"secondary_y": False}],
                   [{"type": "pie"}, {"type": "bar"}]]
        )
        
        # Extract data
        indices = list(range(len(history)))
        pos_probs = [item['pos_prob'] for item in history]
        confidences = [item['confidence'] for item in history]
        sentiments = [item['sentiment'] for item in history]
        languages = [item.get('language', 'en') for item in history]
        
        # Sentiment timeline
        colors = ['#4CAF50' if s == 'Positive' else '#F44336' for s in sentiments]
        fig.add_trace(
            go.Scatter(x=indices, y=pos_probs, mode='lines+markers', 
                      marker=dict(color=colors, size=8),
                      name='Positive Probability'),
            row=1, col=1
        )
        
        # Confidence distribution
        fig.add_trace(
            go.Histogram(x=confidences, nbinsx=10, name='Confidence'),
            row=1, col=2
        )
        
        # Language distribution
        lang_counts = Counter(languages)
        fig.add_trace(
            go.Pie(labels=list(lang_counts.keys()), values=list(lang_counts.values()),
                   name="Languages"),
            row=2, col=1
        )
        
        # Sentiment summary
        sent_counts = Counter(sentiments)
        fig.add_trace(
            go.Bar(x=list(sent_counts.keys()), y=list(sent_counts.values()),
                   marker_color=['#4CAF50' if k == 'Positive' else '#F44336' for k in sent_counts.keys()]),
            row=2, col=2
        )
        
        fig.update_layout(height=800, showlegend=False)
        return fig

# Main application functions
def analyze_single_text(text: str, language: str, theme: str, clean_text: bool, 
                       remove_punct: bool, remove_nums: bool):
    """Enhanced single text analysis"""
    try:
        if not text.strip():
            return "Please enter text", None, None
        
        # Map display names back to language codes
        language_map = {
            'Auto Detect': 'auto',
            'English': 'en',
            'Chinese': 'zh',
            'Spanish': 'es',
            'French': 'fr',
            'German': 'de',
            'Swedish': 'sv'
        }
        language_code = language_map.get(language, 'auto')
        
        preprocessing_options = {
            'clean_text': clean_text,
            'remove_punctuation': remove_punct,
            'remove_numbers': remove_nums
        }
        
        result = SentimentAnalyzer.analyze_text(text, language_code, preprocessing_options)
        
        # Add to history
        history_entry = {
            'text': text[:100] + '...' if len(text) > 100 else text,
            'full_text': text,
            'sentiment': result['sentiment'],
            'confidence': result['confidence'],
            'pos_prob': result['pos_prob'],
            'neg_prob': result['neg_prob'],
            'neu_prob': result.get('neu_prob', 0),
            'language': result['language'],
            'timestamp': datetime.now().isoformat(),
            'analysis_type': 'single'
        }
        history_manager.add_entry(history_entry)
        
        # Create visualizations
        gauge_fig = PlotlyVisualizer.create_sentiment_gauge(result, theme)
        bars_fig = PlotlyVisualizer.create_probability_bars(result, theme)
        
        # Create info text
        info_text = f"""
**Analysis Results:**
- **Sentiment:** {result['sentiment']} ({result['confidence']:.3f} confidence)
- **Language:** {result['language'].upper()}
- **Keywords:** {', '.join(result['keywords'])}
- **Stats:** {result['word_count']} words, {result['char_count']} characters
        """
        
        return info_text, gauge_fig, bars_fig
        
    except Exception as e:
        logger.error(f"Analysis failed: {e}")
        return f"Error: {str(e)}", None, None

def analyze_batch_texts(batch_text: str, language: str, theme: str, 
                       clean_text: bool, remove_punct: bool, remove_nums: bool):
    """Batch text analysis"""
    try:
        if not batch_text.strip():
            return "Please enter texts (one per line)", None, None, None
        
        # Parse batch input
        texts = TextProcessor.parse_batch_input(batch_text)
        
        if len(texts) > config.BATCH_SIZE_LIMIT:
            return f"Too many texts. Maximum {config.BATCH_SIZE_LIMIT} allowed.", None, None, None
        
        if not texts:
            return "No valid texts found", None, None, None
        
        # Map display names back to language codes
        language_map = {
            'Auto Detect': 'auto',
            'English': 'en',
            'Chinese': 'zh',
            'Spanish': 'es',
            'French': 'fr',
            'German': 'de',
            'Swedish': 'sv'
        }
        language_code = language_map.get(language, 'auto')
        
        preprocessing_options = {
            'clean_text': clean_text,
            'remove_punctuation': remove_punct,
            'remove_numbers': remove_nums
        }
        
        # Analyze all texts
        results = SentimentAnalyzer.analyze_batch(texts, language_code, preprocessing_options)
        
        # Add to history
        batch_entries = []
        for i, (text, result) in enumerate(zip(texts, results)):
            if 'error' not in result:
                entry = {
                    'text': text[:100] + '...' if len(text) > 100 else text,
                    'full_text': text,
                    'sentiment': result['sentiment'],
                    'confidence': result['confidence'],
                    'pos_prob': result['pos_prob'],
                    'neg_prob': result['neg_prob'],
                    'neu_prob': result.get('neu_prob', 0),
                    'language': result['language'],
                    'timestamp': datetime.now().isoformat(),
                    'analysis_type': 'batch',
                    'batch_index': i
                }
                batch_entries.append(entry)
        
        history_manager.add_batch_entries(batch_entries)
        
        # Create visualizations
        summary_fig = PlotlyVisualizer.create_batch_summary(results, theme)
        confidence_fig = PlotlyVisualizer.create_confidence_distribution(results)
        
        # Create results table
        df_data = []
        for i, (text, result) in enumerate(zip(texts, results)):
            if 'error' in result:
                df_data.append({
                    'Index': i+1,
                    'Text': text[:50] + '...' if len(text) > 50 else text,
                    'Sentiment': 'Error',
                    'Confidence': 0.0,
                    'Language': 'Unknown',
                    'Error': result['error']
                })
            else:
                df_data.append({
                    'Index': i+1,
                    'Text': text[:50] + '...' if len(text) > 50 else text,
                    'Sentiment': result['sentiment'],
                    'Confidence': f"{result['confidence']:.3f}",
                    'Language': result['language'].upper(),
                    'Keywords': ', '.join(result['keywords'][:3])
                })
        
        df = pd.DataFrame(df_data)
        
        # Summary info
        successful_results = [r for r in results if 'error' not in r]
        error_count = len(results) - len(successful_results)
        
        if successful_results:
            sentiment_counts = Counter([r['sentiment'] for r in successful_results])
            avg_confidence = np.mean([r['confidence'] for r in successful_results])
            
            summary_text = f"""
**Batch Analysis Summary:**
- **Total Texts:** {len(texts)}
- **Successful:** {len(successful_results)}
- **Errors:** {error_count}
- **Average Confidence:** {avg_confidence:.3f}
- **Sentiments:** {dict(sentiment_counts)}
            """
        else:
            summary_text = f"All {len(texts)} texts failed to analyze."
        
        return summary_text, df, summary_fig, confidence_fig
        
    except Exception as e:
        logger.error(f"Batch analysis failed: {e}")
        return f"Error: {str(e)}", None, None, None

def analyze_advanced_text(text: str, language: str, theme: str, include_keywords: bool,
                         keyword_count: int, min_confidence: float):
    """Advanced analysis with additional features"""
    try:
        if not text.strip():
            return "Please enter text", None, None
        
        # Map display names back to language codes
        language_map = {
            'Auto Detect': 'auto',
            'English': 'en',
            'Chinese': 'zh',
            'Spanish': 'es',
            'French': 'fr',
            'German': 'de',
            'Swedish': 'sv'
        }
        language_code = language_map.get(language, 'auto')
        
        result = SentimentAnalyzer.analyze_text(text, language_code)
        
        # Advanced keyword extraction
        if include_keywords:
            result['keywords'] = TextProcessor.extract_keywords(text, keyword_count)
        
        # Confidence filtering
        meets_confidence = result['confidence'] >= min_confidence
        
        # Add to history
        history_entry = {
            'text': text[:100] + '...' if len(text) > 100 else text,
            'full_text': text,
            'sentiment': result['sentiment'],
            'confidence': result['confidence'],
            'pos_prob': result['pos_prob'],
            'neg_prob': result['neg_prob'],
            'neu_prob': result.get('neu_prob', 0),
            'language': result['language'],
            'timestamp': datetime.now().isoformat(),
            'analysis_type': 'advanced',
            'meets_confidence_threshold': meets_confidence
        }
        history_manager.add_entry(history_entry)
        
        # Create visualizations
        gauge_fig = PlotlyVisualizer.create_sentiment_gauge(result, theme)
        bars_fig = PlotlyVisualizer.create_probability_bars(result, theme)
        
        # Create detailed info text
        confidence_status = "✅ High Confidence" if meets_confidence else "⚠️ Low Confidence"
        
        info_text = f"""
**Advanced Analysis Results:**
- **Sentiment:** {result['sentiment']} ({result['confidence']:.3f} confidence)
- **Confidence Status:** {confidence_status}
- **Language:** {result['language'].upper()}
- **Text Statistics:**
  - Words: {result['word_count']}
  - Characters: {result['char_count']}
  - Average word length: {result['char_count']/max(result['word_count'], 1):.1f}
        """
        
        if include_keywords:
            info_text += f"\n- **Top Keywords:** {', '.join(result['keywords'])}"
        
        if not meets_confidence:
            info_text += f"\n\n⚠️ **Note:** Confidence ({result['confidence']:.3f}) is below threshold ({min_confidence})"
        
        return info_text, gauge_fig, bars_fig
        
    except Exception as e:
        logger.error(f"Advanced analysis failed: {e}")
        return f"Error: {str(e)}", None, None

def get_history_stats():
    """Get enhanced history statistics"""
    stats = history_manager.get_stats()
    if not stats:
        return "No analysis history available"
    
    return f"""
**Comprehensive History Statistics:**

**Analysis Counts:**
- Total Analyses: {stats['total_analyses']}
- Positive: {stats['positive_count']}
- Negative: {stats['negative_count']}
- Neutral: {stats['neutral_count']}

**Confidence Metrics:**
- Average Confidence: {stats['avg_confidence']:.3f}
- Highest Confidence: {stats['max_confidence']:.3f}
- Lowest Confidence: {stats['min_confidence']:.3f}

**Language Statistics:**
- Languages Detected: {stats['languages_detected']}
- Most Common Language: {stats['most_common_language'].upper()}

**Text Statistics:**
- Average Text Length: {stats['avg_text_length']:.1f} characters
    """

def filter_history_display(sentiment_filter: str, language_filter: str, min_confidence: float):
    """Display filtered history"""
    # Convert filters
    sentiment = sentiment_filter if sentiment_filter != "All" else None
    language = language_filter.lower() if language_filter != "All" else None
    
    filtered_history = history_manager.filter_history(
        sentiment=sentiment,
        language=language,
        min_confidence=min_confidence if min_confidence > 0 else None
    )
    
    if not filtered_history:
        return "No entries match the filter criteria", None
    
    # Create DataFrame for display
    df_data = []
    for entry in filtered_history[-20:]:  # Show last 20 entries
        df_data.append({
            'Timestamp': entry['timestamp'][:16],  # YYYY-MM-DD HH:MM
            'Text': entry['text'],
            'Sentiment': entry['sentiment'],
            'Confidence': f"{entry['confidence']:.3f}",
            'Language': entry['language'].upper(),
            'Type': entry.get('analysis_type', 'single')
        })
    
    df = pd.DataFrame(df_data)
    
    summary = f"""
**Filtered Results:**
- Found {len(filtered_history)} entries matching criteria
- Showing most recent {min(20, len(filtered_history))} entries
    """
    
    return summary, df

def plot_history_dashboard():
    """Create history dashboard"""
    history = history_manager.get_history()
    if len(history) < 2:
        return None, "Need at least 2 analyses for dashboard"
    
    fig = PlotlyVisualizer.create_history_dashboard(history)
    return fig, f"Dashboard showing {len(history)} analyses"

def export_history_csv():
    """Export history to CSV"""
    history = history_manager.get_history()
    if not history:
        return None, "No history to export"
    
    try:
        df = pd.DataFrame(history)
        temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.csv', mode='w')
        df.to_csv(temp_file.name, index=False)
        return temp_file.name, f"Exported {len(history)} entries to CSV"
    except Exception as e:
        return None, f"Export failed: {str(e)}"

def export_history_excel():
    """Export history to Excel"""
    history = history_manager.get_history()
    if not history:
        return None, "No history to export"
    
    try:
        df = pd.DataFrame(history)
        temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.xlsx')
        df.to_excel(temp_file.name, index=False)
        return temp_file.name, f"Exported {len(history)} entries to Excel"
    except Exception as e:
        return None, f"Export failed: {str(e)}"

def clear_all_history():
    """Clear analysis history"""
    count = history_manager.clear()
    return f"Cleared {count} entries from history"

def get_recent_analyses():
    """Get recent analysis summary"""
    recent = history_manager.get_recent_history(10)
    if not recent:
        return "No recent analyses available"
    
    summary_text = "**Recent Analyses (Last 10):**\n\n"
    for i, entry in enumerate(recent, 1):
        summary_text += f"{i}. **{entry['sentiment']}** ({entry['confidence']:.3f}) - {entry['text']}\n"
    
    return summary_text

SAMPLE_TEXTS = [
    # Auto Detect
    ["The film had its moments, but overall it felt a bit too long and lacked emotional depth. Some scenes were visually impressive, yet they failed to connect emotionally. By the end, I found myself disengaged and unsatisfied."],

    # English
    ["I was completely blown away by the movie — the performances were raw and powerful, and the story stayed with me long after the credits rolled. Every scene felt purposeful, and the emotional arc was handled with incredible nuance. It's the kind of film that makes you reflect deeply on your own life."],

    # Chinese
    ["这部电影节奏拖沓，剧情老套，完全没有让我产生任何共鸣，是一次失望的观影体验。演员的表演也显得做作，缺乏真实感。看到最后甚至有点不耐烦，整体表现乏善可陈。"],

    # Spanish
    ["Una obra maestra del cine contemporáneo, con actuaciones sobresalientes, un guion bien escrito y una dirección impecable. Cada plano parecía cuidadosamente pensado, y la historia avanzaba con una intensidad emocional que mantenía al espectador cautivado. Definitivamente una película que vale la pena volver a ver."],

    # French
    ["Je m'attendais à beaucoup mieux. Le scénario était confus, les dialogues ennuyeux, et je me suis presque endormi au milieu du film. Même la mise en scène, habituellement un point fort, manquait cruellement d'inspiration cette fois-ci."],

    # German
    ["Der Film war ein emotionales Erlebnis mit großartigen Bildern, einem mitreißenden Soundtrack und einer Geschichte, die zum Nachdenken anregt. Besonders beeindruckend war die schauspielerische Leistung der Hauptdarsteller, die eine tiefe Menschlichkeit vermittelten. Es ist ein Film, der lange nachwirkt."],

    # Swedish
    ["Filmen var en besvikelse – tråkig handling, överdrivet skådespeleri och ett slut som inte gav något avslut alls. Den kändes forcerad och saknade en tydlig röd tråd. Jag gick från biografen med en känsla av tomhet och frustration."]
]


BATCH_SAMPLE = """I love this product! It works perfectly and exceeded my expectations. I've been using it every day and it hasn’t let me down once.
The service was terrible and slow. I had to wait over an hour, and no one seemed to care about helping me. Really frustrating experience overall.
Not sure if I like it or not. Some features are nice, but others are confusing or don’t work as expected. I’m still deciding whether it’s worth keeping.
Amazing quality and fast delivery! The packaging was secure, and the product looked even better than in the pictures. I’ll definitely order from here again.
Could be better, but it's okay. It does the job, but there are some issues with the build quality. Not bad, just not great either."""


# Gradio Interface
with gr.Blocks(theme=gr.themes.Soft(), title="Advanced Multilingual Sentiment Analyzer") as demo:
    gr.Markdown("# 🎭 Advanced Multilingual Sentiment Analyzer")
    gr.Markdown("Comprehensive sentiment analysis with batch processing, advanced analytics, and multilingual support")
    
    with gr.Tab("📝 Single Analysis"):
        with gr.Row():
            with gr.Column(scale=2):
                text_input = gr.Textbox(
                    label="Text to Analyze",
                    placeholder="Enter your text here... (supports multiple languages)",
                    lines=4
                )
                
                with gr.Row():
                    language_select = gr.Dropdown(
                        choices=['Auto Detect', 'English', 'Chinese', 'Spanish', 'French', 'German', 'Swedish'],
                        value='Auto Detect',
                        label="Language"
                    )
                    theme_select = gr.Dropdown(
                        choices=list(config.THEMES.keys()),
                        value='default',
                        label="Theme"
                    )
                
                with gr.Row():
                    clean_text = gr.Checkbox(label="Clean Text", value=False)
                    remove_punct = gr.Checkbox(label="Remove Punctuation", value=True)
                    remove_nums = gr.Checkbox(label="Remove Numbers", value=False)
                
                analyze_btn = gr.Button("🔍 Analyze", variant="primary", size="lg")
                
                gr.Examples(
                    examples=SAMPLE_TEXTS,
                    inputs=text_input,
                    label="Sample Texts (Multiple Languages)"
                )
            
            with gr.Column(scale=1):
                result_info = gr.Markdown("Enter text and click Analyze")
        
        with gr.Row():
            gauge_plot = gr.Plot(label="Sentiment Gauge")
            bars_plot = gr.Plot(label="Probability Distribution")
    
    with gr.Tab("📊 Batch Analysis"):
        with gr.Row():
            with gr.Column(scale=2):
                batch_input = gr.Textbox(
                    label="Batch Text Input (One text per line)",
                    placeholder="Enter multiple texts, one per line...",
                    lines=8
                )
                
                with gr.Row():
                    batch_language = gr.Dropdown(
                        choices=['Auto Detect', 'English', 'Chinese', 'Spanish', 'French', 'German', 'Swedish'],
                        value='Auto Detect',
                        label="Language"
                    )
                    batch_theme = gr.Dropdown(
                        choices=list(config.THEMES.keys()),
                        value='default',
                        label="Theme"
                    )
                
                with gr.Row():
                    batch_clean = gr.Checkbox(label="Clean Text", value=False)
                    batch_remove_punct = gr.Checkbox(label="Remove Punctuation", value=True)
                    batch_remove_nums = gr.Checkbox(label="Remove Numbers", value=False)
                
                batch_analyze_btn = gr.Button("🔍 Analyze Batch", variant="primary", size="lg")
                
                gr.Examples(
                    examples=[[BATCH_SAMPLE]],
                    inputs=batch_input,
                    label="Sample Batch Input"
                )
            
            with gr.Column(scale=1):
                batch_summary = gr.Markdown("Enter texts and click Analyze Batch")
        
        with gr.Row():
            batch_results_table = gr.DataFrame(
                label="Detailed Results",
                interactive=False
            )
        
        with gr.Row():
            batch_summary_plot = gr.Plot(label="Sentiment Summary")
            batch_confidence_plot = gr.Plot(label="Confidence Distribution")
    
    with gr.Tab("🔬 Advanced Analysis"):
        with gr.Row():
            with gr.Column(scale=2):
                advanced_input = gr.Textbox(
                    label="Text for Advanced Analysis",
                    placeholder="Enter text for detailed analysis...",
                    lines=4
                )
                
                with gr.Row():
                    advanced_language = gr.Dropdown(
                        choices=['Auto Detect', 'English', 'Chinese', 'Spanish', 'French', 'German', 'Swedish'],
                        value='Auto Detect',
                        label="Language"
                    )
                    advanced_theme = gr.Dropdown(
                        choices=list(config.THEMES.keys()),
                        value='default',
                        label="Theme"
                    )
                
                with gr.Row():
                    include_keywords = gr.Checkbox(label="Extract Keywords", value=True)
                    keyword_count = gr.Slider(
                        minimum=3,
                        maximum=10,
                        value=5,
                        step=1,
                        label="Number of Keywords"
                    )
                
                min_confidence_slider = gr.Slider(
                    minimum=0.0,
                    maximum=1.0,
                    value=0.7,
                    step=0.1,
                    label="Minimum Confidence Threshold"
                )
                
                advanced_analyze_btn = gr.Button("🔬 Advanced Analyze", variant="primary", size="lg")
            
            with gr.Column(scale=1):
                advanced_result_info = gr.Markdown("Configure settings and click Advanced Analyze")
        
        with gr.Row():
            advanced_gauge_plot = gr.Plot(label="Sentiment Gauge")
            advanced_bars_plot = gr.Plot(label="Probability Distribution")
    
    with gr.Tab("📈 History & Analytics"):
        with gr.Row():
            with gr.Column():
                gr.Markdown("### 📊 Statistics")
                stats_btn = gr.Button("📈 Get Statistics")
                recent_btn = gr.Button("🕒 Recent Analyses")
                stats_output = gr.Markdown("Click 'Get Statistics' to view analysis history")
            
            with gr.Column():
                gr.Markdown("### 🔍 Filter History")
                with gr.Row():
                    sentiment_filter = gr.Dropdown(
                        choices=["All", "Positive", "Negative", "Neutral"],
                        value="All",
                        label="Filter by Sentiment"
                    )
                    language_filter = gr.Dropdown(
                        choices=["All", "English", "Chinese", "Spanish", "French", "German", "Swedish"],
                        value="All",
                        label="Filter by Language"
                    )
                
                confidence_filter = gr.Slider(
                    minimum=0.0,
                    maximum=1.0,
                    value=0.0,
                    step=0.1,
                    label="Minimum Confidence"
                )
                
                filter_btn = gr.Button("🔍 Filter History")
        
        with gr.Row():
            dashboard_btn = gr.Button("📊 View Dashboard")
            clear_btn = gr.Button("🗑️ Clear History", variant="stop")
        
        with gr.Row():
            export_csv_btn = gr.Button("📄 Export CSV")
            export_excel_btn = gr.Button("📊 Export Excel")
        
        dashboard_plot = gr.Plot(label="Analytics Dashboard")
        
        with gr.Row():
            filtered_results = gr.Markdown("Use filters to view specific entries")
            filtered_table = gr.DataFrame(label="Filtered History", interactive=False)
        
        csv_file = gr.File(label="Download CSV Report")
        excel_file = gr.File(label="Download Excel Report")
        history_status = gr.Textbox(label="Status", interactive=False)
    
    # Event handlers
    
    # Single Analysis
    analyze_btn.click(
        analyze_single_text,
        inputs=[text_input, language_select, theme_select, clean_text, remove_punct, remove_nums],
        outputs=[result_info, gauge_plot, bars_plot]
    )
    
    # Batch Analysis
    batch_analyze_btn.click(
        analyze_batch_texts,
        inputs=[batch_input, batch_language, batch_theme, batch_clean, batch_remove_punct, batch_remove_nums],
        outputs=[batch_summary, batch_results_table, batch_summary_plot, batch_confidence_plot]
    )
    
    # Advanced Analysis
    advanced_analyze_btn.click(
        analyze_advanced_text,
        inputs=[advanced_input, advanced_language, advanced_theme, include_keywords, keyword_count, min_confidence_slider],
        outputs=[advanced_result_info, advanced_gauge_plot, advanced_bars_plot]
    )
    
    # History & Analytics
    stats_btn.click(
        get_history_stats,
        outputs=stats_output
    )
    
    recent_btn.click(
        get_recent_analyses,
        outputs=stats_output
    )
    
    filter_btn.click(
        filter_history_display,
        inputs=[sentiment_filter, language_filter, confidence_filter],
        outputs=[filtered_results, filtered_table]
    )
    
    dashboard_btn.click(
        plot_history_dashboard,
        outputs=[dashboard_plot, history_status]
    )
    
    export_csv_btn.click(
        export_history_csv,
        outputs=[csv_file, history_status]
    )
    
    export_excel_btn.click(
        export_history_excel,
        outputs=[excel_file, history_status]
    )
    
    clear_btn.click(
        clear_all_history,
        outputs=history_status
    )

if __name__ == "__main__":
    demo.launch(share=True)