pdf_generator.py

import io
import os
import tempfile
import pandas as pd
import plotly.express as px
import plotly.io as pio
from datetime import datetime
from typing import Dict, Optional
from reportlab.lib import colors
from reportlab.lib.pagesizes import A4
from reportlab.lib.units import inch
from reportlab.platypus import SimpleDocTemplate, Table, TableStyle, Paragraph, Spacer, Image, PageBreak
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle

from config import get_chart_theme, DESIGN_SYSTEM
from ai_engine import generate_ai_summary

PDF_TRANSLATIONS = {
    'English': {
        'title': 'Production Monitor Dashboard',
        'subtitle': 'Comprehensive Production Analysis Report',
        'company': 'Nilsen Service & Consulting AS',
        'division': 'Production Analytics Division',
        'report_period': 'Report Period',
        'generated': 'Generated',
        'total_records': 'Total Records',
        'executive_summary': 'Executive Summary',
        'production_summary': 'Production Summary',
        'production_analysis_charts': 'Production Analysis Charts',
        'quality_control': 'Quality Control Analysis',
        'intelligent_analysis': 'Intelligent Analysis',
        'material_type': 'Material Type',
        'total_kg': 'Total (kg)',
        'share': 'Share (%)',
        'daily_avg_kg': 'Daily Avg (kg)',
        'material': 'Material',
        'outliers': 'Outliers',
        'normal_range_kg': 'Normal Range (kg)',
        'status': 'Status',
        'footer_generated': 'This report was generated by Production Monitor System',
        'footer_records': 'Report contains {records} data records across {days} working days',
        'summary_text': 'This report analyzes production data spanning <b>{days} working days</b>. Total output achieved: <b>{total} kg</b> with an average daily production of <b>{avg} kg</b>.',
        'key_highlights': 'Key Highlights:',
        'total_production': 'Total production',
        'daily_average': 'Daily average',
        'materials_tracked': 'Materials tracked',
        'data_quality': 'Data quality',
        'records_processed': 'records processed',
        'production_distribution': 'Production Distribution by Material',
        'daily_production_trend': 'Daily Production Trend',
        'production_by_material': 'Production by Material Type',
        'production_by_shift': 'Production by Shift',
        'chart_analysis': 'Analysis',
        'dist_insight': 'Material distribution shows production allocation across different materials.',
        'trend_insight': 'Production trend reveals operational patterns and seasonal variations.',
        'material_insight': 'Material comparison highlights performance differences and production capacities.',
        'shift_insight': 'Shift analysis reveals operational efficiency differences between day and night operations.',
        'charts_failed': 'Charts Generation Failed',
        'data_summary': 'Production Data Summary:',
        'status_good': 'GOOD',
        'status_monitor': 'MONITOR',
        'status_attention': 'ATTENTION'
    },
    'Norsk': {
        'title': 'Produksjonsovervakingsdashboard',
        'subtitle': 'Omfattende produksjonsanalyserapport',
        'company': 'Nilsen Service & Consulting AS',
        'division': 'Produksjonsanalyseavdeling',
        'report_period': 'Rapportperiode',
        'generated': 'Generert',
        'total_records': 'Totalt antall poster',
        'executive_summary': 'Oppsummering',
        'production_summary': 'Produksjonsoversikt',
        'production_analysis_charts': 'Produksjonsanalysediagrammer',
        'quality_control': 'Kvalitetskontrollanalyse',
        'intelligent_analysis': 'Intelligent analyse',
        'material_type': 'Materialtype',
        'total_kg': 'Totalt (kg)',
        'share': 'Andel (%)',
        'daily_avg_kg': 'Daglig gj.snitt (kg)',
        'material': 'Material',
        'outliers': 'Avvik',
        'normal_range_kg': 'Normalomrade (kg)',
        'status': 'Status',
        'footer_generated': 'Denne rapporten ble generert av produksjonsovervakingssystemet',
        'footer_records': 'Rapporten inneholder {records} dataposter over {days} arbeidsdager',
        'summary_text': 'Denne rapporten analyserer produksjonsdata over <b>{days} arbeidsdager</b>. Total produksjon oppnadd: <b>{total} kg</b> med et daglig gjennomsnitt pa <b>{avg} kg</b>.',
        'key_highlights': 'Hovedpunkter:',
        'total_production': 'Total produksjon',
        'daily_average': 'Daglig gjennomsnitt',
        'materials_tracked': 'Materialer sporet',
        'data_quality': 'Datakvalitet',
        'records_processed': 'poster behandlet',
        'production_distribution': 'Produksjonsfordeling etter material',
        'daily_production_trend': 'Daglig produksjonstrend',
        'production_by_material': 'Produksjon etter materialtype',
        'production_by_shift': 'Produksjon etter skift',
        'chart_analysis': 'Analyse',
        'dist_insight': 'Materialfordeling viser produksjonsallokering pa tvers av ulike materialer.',
        'trend_insight': 'Produksjonstrend avslorer operasjonelle monster og sesongvariasjoner.',
        'material_insight': 'Materialsammenligning fremhever ytelsesforskjeller og produksjonskapasitet.',
        'shift_insight': 'Skiftanalyse avslorer operasjonelle effektivitetsforskjeller mellom dag- og nattoperasjoner.',
        'charts_failed': 'Diagramgenerering mislyktes',
        'data_summary': 'Produksjonsdataoversikt:',
        'status_good': 'GOD',
        'status_monitor': 'OVERVAKNING',
        'status_attention': 'OPPMERKSOMHET'
    }
}

def get_pdf_translation(lang: str = 'English') -> dict:
    return PDF_TRANSLATIONS.get(lang, PDF_TRANSLATIONS['English'])

def save_chart_as_image(fig, filename: str) -> Optional[str]:
    try:
        temp_dir = tempfile.gettempdir()
        filepath = os.path.join(temp_dir, filename)
        
        theme = get_chart_theme()['layout'].copy()
        theme.update({
            'font': dict(size=12, family="Arial"),
            'plot_bgcolor': 'white',
            'paper_bgcolor': 'white',
            'margin': dict(t=50, b=40, l=40, r=40)
        })
        fig.update_layout(**theme)
        
        try:
            pio.write_image(fig, filepath, format='png', width=800, height=400, scale=2, engine='kaleido')
            if os.path.exists(filepath):
                return filepath
        except:
            pass
        
        return None
    except:
        return None

def create_pdf_charts(df: pd.DataFrame, stats: Dict, t: dict) -> Dict[str, Optional[str]]:
    charts = {}
    materials = [k for k in stats.keys() if k != '_total_']
    values = [stats[mat]['total'] for mat in materials]
    labels = [mat.replace('_', ' ').title() for mat in materials]
    
    if len(materials) > 0 and len(values) > 0:
        try:
            fig_pie = px.pie(values=values, names=labels, title=t['production_distribution'])
            charts['pie'] = save_chart_as_image(fig_pie, "distribution.png")
        except:
            pass
    
    if len(df) > 0:
        try:
            daily_data = df.groupby('date')['weight_kg'].sum().reset_index()
            if len(daily_data) > 0:
                fig_trend = px.line(
                    daily_data, x='date', y='weight_kg', 
                    title=t['daily_production_trend'],
                    labels={'date': 'Date', 'weight_kg': 'Weight (kg)'},
                    color_discrete_sequence=[DESIGN_SYSTEM['colors']['primary']]
                )
                charts['trend'] = save_chart_as_image(fig_trend, "trend.png")
        except:
            pass
    
    if len(materials) > 0 and len(values) > 0:
        try:
            fig_bar = px.bar(
                x=labels, y=values, 
                title=t['production_by_material'],
                labels={'x': t['material_type'], 'y': 'Weight (kg)'},
                color_discrete_sequence=[DESIGN_SYSTEM['colors']['primary']]
            )
            charts['bar'] = save_chart_as_image(fig_bar, "materials.png")
        except:
            pass
    
    if 'shift' in df.columns and len(df) > 0:
        try:
            shift_data = df.groupby('shift')['weight_kg'].sum().reset_index()
            if len(shift_data) > 0 and shift_data['weight_kg'].sum() > 0:
                fig_shift = px.pie(shift_data, values='weight_kg', names='shift', title=t['production_by_shift'])
                charts['shift'] = save_chart_as_image(fig_shift, "shifts.png")
        except:
            pass
    
    return charts

def create_enhanced_pdf_report(df: pd.DataFrame, stats: Dict, outliers: Dict, model=None, lang: str = 'English') -> io.BytesIO:
    buffer = io.BytesIO()
    doc = SimpleDocTemplate(buffer, pagesize=A4, rightMargin=50, leftMargin=50, topMargin=50, bottomMargin=50)
    elements = []
    styles = getSampleStyleSheet()
    t = get_pdf_translation(lang)
    
    title_style = ParagraphStyle(
        'CustomTitle',
        parent=styles['Heading1'],
        fontSize=24,
        spaceAfter=30,
        alignment=1,
        textColor=colors.darkblue
    )
    
    subtitle_style = ParagraphStyle(
        'CustomSubtitle',
        parent=styles['Heading2'],
        fontSize=16,
        spaceAfter=20,
        textColor=colors.darkblue
    )
    
    analysis_style = ParagraphStyle(
        'AnalysisStyle',
        parent=styles['Normal'],
        fontSize=11,
        spaceAfter=12,
        leftIndent=20,
        textColor=colors.darkgreen
    )
    
    elements.append(Spacer(1, 100))
    elements.append(Paragraph(t['title'], title_style))
    elements.append(Paragraph(t['subtitle'], styles['Heading3']))
    elements.append(Spacer(1, 50))
    
    report_info = f"""
    <para alignment="center">
    <b>{t['company']}</b><br/>
    {t['division']}<br/><br/>
    <b>{t['report_period']}:</b> {df['date'].min().strftime('%B %d, %Y')} - {df['date'].max().strftime('%B %d, %Y')}<br/>
    <b>{t['generated']}:</b> {datetime.now().strftime('%B %d, %Y at %H:%M')}<br/>
    <b>{t['total_records']}:</b> {len(df):,}
    </para>
    """
    elements.append(Paragraph(report_info, styles['Normal']))
    elements.append(PageBreak())
    
    elements.append(Paragraph(t['executive_summary'], subtitle_style))
    
    total_production = stats['_total_']['total']
    work_days = stats['_total_']['work_days']
    daily_avg = stats['_total_']['daily_avg']
    
    exec_summary = f"""
    <para>
    {t['summary_text'].format(days=work_days, total=f"{total_production:,.0f}", avg=f"{daily_avg:,.0f}")}
    <br/><br/>
    <b>{t['key_highlights']}</b><br/>
    • {t['total_production']}: {total_production:,.0f} kg<br/>
    • {t['daily_average']}: {daily_avg:,.0f} kg<br/>
    • {t['materials_tracked']}: {len([k for k in stats.keys() if k != '_total_'])}<br/>
    • {t['data_quality']}: {len(df):,} {t['records_processed']}
    </para>
    """
    elements.append(Paragraph(exec_summary, styles['Normal']))
    elements.append(Spacer(1, 20))
    
    elements.append(Paragraph(t['production_summary'], styles['Heading3']))
    summary_data = [[t['material_type'], t['total_kg'], t['share'], t['daily_avg_kg']]]
    
    for material, info in stats.items():
        if material != '_total_':
            summary_data.append([
                material.replace('_', ' ').title(),
                f"{info['total']:,.0f}",
                f"{info['percentage']:.1f}%",
                f"{info['daily_avg']:,.0f}"
            ])
    
    summary_table = Table(summary_data, colWidths=[2*inch, 1.5*inch, 1*inch, 1.5*inch])
    summary_table.setStyle(TableStyle([
        ('BACKGROUND', (0, 0), (-1, 0), colors.darkblue),
        ('TEXTCOLOR', (0, 0), (-1, 0), colors.whitesmoke),
        ('ALIGN', (0, 0), (-1, -1), 'CENTER'),
        ('FONTNAME', (0, 0), (-1, 0), 'Helvetica-Bold'),
        ('GRID', (0, 0), (-1, -1), 1, colors.black),
        ('ROWBACKGROUNDS', (0, 1), (-1, -1), [colors.white, colors.lightgrey])
    ]))
    elements.append(summary_table)
    elements.append(PageBreak())
    
    elements.append(Paragraph(t['production_analysis_charts'], subtitle_style))
    
    try:
        charts = create_pdf_charts(df, stats, t)
    except:
        charts = {}
    
    chart_insights = {
        'pie': t['dist_insight'],
        'trend': t['trend_insight'],
        'bar': t['material_insight'],
        'shift': t['shift_insight']
    }
    
    chart_titles = {
        'pie': t['production_distribution'],
        'trend': t['daily_production_trend'],
        'bar': t['production_by_material'],
        'shift': t['production_by_shift']
    }
    
    charts_added = False
    for chart_type in ['pie', 'trend', 'bar', 'shift']:
        chart_path = charts.get(chart_type)
        if chart_path and os.path.exists(chart_path):
            try:
                elements.append(Paragraph(chart_titles[chart_type], styles['Heading3']))
                elements.append(Image(chart_path, width=6*inch, height=3*inch))
                insight_text = f"<i>{t['chart_analysis']}: {chart_insights[chart_type]}</i>"
                elements.append(Paragraph(insight_text, analysis_style))
                elements.append(Spacer(1, 20))
                charts_added = True
            except:
                pass
    
    if not charts_added:
        elements.append(Paragraph(t['charts_failed'], styles['Heading3']))
        elements.append(Paragraph(t['data_summary'], styles['Normal']))
        for material, info in stats.items():
            if material != '_total_':
                summary_text = f"• {material.replace('_', ' ').title()}: {info['total']:,.0f} kg ({info['percentage']:.1f}%)"
                elements.append(Paragraph(summary_text, styles['Normal']))
        elements.append(Spacer(1, 20))
    
    elements.append(PageBreak())
    
    elements.append(Paragraph(t['quality_control'], subtitle_style))
    
    quality_data = [[t['material'], t['outliers'], t['normal_range_kg'], t['status']]]
    for material, info in outliers.items():
        if info['count'] == 0:
            status = t['status_good']
        elif info['count'] <= 3:
            status = t['status_monitor']
        else:
            status = t['status_attention']
        
        quality_data.append([
            material.replace('_', ' ').title(),
            str(info['count']),
            info['range'],
            status
        ])
    
    quality_table = Table(quality_data, colWidths=[2*inch, 1*inch, 2*inch, 1.5*inch])
    quality_table.setStyle(TableStyle([
        ('BACKGROUND', (0, 0), (-1, 0), colors.darkred),
        ('TEXTCOLOR', (0, 0), (-1, 0), colors.whitesmoke),
        ('ALIGN', (0, 0), (-1, -1), 'CENTER'),
        ('FONTNAME', (0, 0), (-1, 0), 'Helvetica-Bold'),
        ('GRID', (0, 0), (-1, -1), 1, colors.black),
        ('ROWBACKGROUNDS', (0, 1), (-1, -1), [colors.white, colors.lightgrey])
    ]))
    elements.append(quality_table)
    
    if model:
        elements.append(PageBreak())
        elements.append(Paragraph(t['intelligent_analysis'], subtitle_style))
        try:
            analysis = generate_ai_summary(model, df, stats, outliers, lang)
        except:
            analysis = "Intelligent analysis temporarily unavailable."
        
        analysis_paragraphs = analysis.split('\n\n')
        for paragraph in analysis_paragraphs:
            if paragraph.strip():
                formatted_text = paragraph.replace('**', '<b>', 1).replace('**', '</b>', 1) \
                                            .replace('•', '  •') \
                                            .replace('\n', '<br/>')
                elements.append(Paragraph(formatted_text, styles['Normal']))
                elements.append(Spacer(1, 8))
    
    elements.append(Spacer(1, 30))
    footer_text = f"""
    <para alignment="center">
    <i>{t['footer_generated']}<br/>
    {t['company']} - {t['division']}<br/>
    {t['footer_records'].format(records=f"{len(df):,}", days=stats['_total_']['work_days'])}</i>
    </para>
    """
    elements.append(Paragraph(footer_text, styles['Normal']))
    
    doc.build(elements)
    buffer.seek(0)
    return buffer

def create_csv_export(df: pd.DataFrame, stats: Dict) -> pd.DataFrame:
    summary_df = pd.DataFrame([
        {
            'Material': material.replace('_', ' ').title(),
            'Total_kg': info['total'],
            'Percentage': info['percentage'],
            'Daily_Average_kg': info['daily_avg'],
            'Work_Days': info['work_days'],
            'Records_Count': info['records']
        }
        for material, info in stats.items() if material != '_total_'
    ])
    return summary_df