sales-data-analysis/report_generator.py

"""
Report generation utility
Combines multiple charts and data into a PDF report

Usage:
    from report_generator import generate_pdf_report
    
    # Generate PDF report
    generate_pdf_report(
        charts=['chart1.png', 'chart2.png'],
        title='Sales Analysis Report',
        summary_data={'Total Revenue': 1000000}
    )
"""
from pathlib import Path
from datetime import datetime
from config import COMPANY_NAME, OUTPUT_DIR, REPORTS_DIR, ensure_directories

def generate_pdf_report(
    charts,
    title=None,
    summary_data=None,
    output_filename=None,
    output_dir=None
):
    """
    Generate PDF report from charts and summary data
    
    Args:
        charts: List of chart file paths (PNG files)
        title: Report title (defaults to company name + date)
        summary_data: Dictionary of summary metrics
        output_filename: Output PDF filename (defaults to report_YYYYMMDD_HHMMSS.pdf)
        output_dir: Output directory (defaults to config.REPORTS_DIR)
    
    Returns:
        Path: Path to generated PDF file
    
    Raises:
        ImportError: If reportlab is not installed
    """
    try:
        from reportlab.lib.pagesizes import letter, A4
        from reportlab.lib.units import inch
        from reportlab.lib import colors
        from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Image, Table, TableStyle, PageBreak
        from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
        from reportlab.lib.enums import TA_CENTER, TA_LEFT
    except ImportError:
        raise ImportError(
            "reportlab is required for PDF generation. Install with: pip install reportlab"
        )
    
    if output_dir is None:
        output_dir = REPORTS_DIR
    else:
        output_dir = Path(output_dir)
    
    ensure_directories()
    output_dir.mkdir(exist_ok=True)
    
    # Default filename
    if output_filename is None:
        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
        output_filename = f"report_{timestamp}.pdf"
    
    output_path = output_dir / output_filename
    
    # Create PDF document
    doc = SimpleDocTemplate(
        str(output_path),
        pagesize=letter,
        rightMargin=0.75*inch,
        leftMargin=0.75*inch,
        topMargin=0.75*inch,
        bottomMargin=0.75*inch
    )
    
    # Container for PDF elements
    story = []
    
    # Styles
    styles = getSampleStyleSheet()
    title_style = ParagraphStyle(
        'CustomTitle',
        parent=styles['Heading1'],
        fontSize=20,
        textColor=colors.HexColor('#2E86AB'),
        spaceAfter=30,
        alignment=TA_CENTER
    )
    
    heading_style = ParagraphStyle(
        'CustomHeading',
        parent=styles['Heading2'],
        fontSize=14,
        textColor=colors.HexColor('#2E86AB'),
        spaceAfter=12
    )
    
    # Title
    if title is None:
        title = f"{COMPANY_NAME} Sales Analysis Report"
    
    story.append(Paragraph(title, title_style))
    story.append(Spacer(1, 0.2*inch))
    
    # Report metadata
    metadata_text = f"Generated: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}"
    story.append(Paragraph(metadata_text, styles['Normal']))
    story.append(Spacer(1, 0.3*inch))
    
    # Summary data table
    if summary_data:
        story.append(Paragraph("Summary", heading_style))
        
        # Create table
        table_data = [['Metric', 'Value']]
        for key, value in summary_data.items():
            # Format value
            if isinstance(value, (int, float)):
                if abs(value) >= 1e6:
                    formatted_value = f"${value / 1e6:.2f}m"
                elif abs(value) >= 1e3:
                    formatted_value = f"${value / 1e3:.2f}k"
                else:
                    formatted_value = f"${value:.2f}"
            else:
                formatted_value = str(value)
            
            table_data.append([key, formatted_value])
        
        table = Table(table_data, colWidths=[3*inch, 2*inch])
        table.setStyle(TableStyle([
            ('BACKGROUND', (0, 0), (-1, 0), colors.HexColor('#2E86AB')),
            ('TEXTCOLOR', (0, 0), (-1, 0), colors.whitesmoke),
            ('ALIGN', (0, 0), (-1, -1), 'LEFT'),
            ('FONTNAME', (0, 0), (-1, 0), 'Helvetica-Bold'),
            ('FONTSIZE', (0, 0), (-1, 0), 12),
            ('BOTTOMPADDING', (0, 0), (-1, 0), 12),
            ('BACKGROUND', (0, 1), (-1, -1), colors.beige),
            ('GRID', (0, 0), (-1, -1), 1, colors.black),
            ('ROWBACKGROUNDS', (0, 1), (-1, -1), [colors.white, colors.lightgrey])
        ]))
        
        story.append(table)
        story.append(Spacer(1, 0.3*inch))
    
    # Add charts
    if charts:
        story.append(Paragraph("Charts", heading_style))
        
        for i, chart_path in enumerate(charts, 1):
            chart_path = Path(chart_path)
            
            if not chart_path.exists():
                print(f"Warning: Chart not found: {chart_path}")
                continue
            
            # Add chart title
            chart_title = f"Chart {i}: {chart_path.stem.replace('_', ' ').title()}"
            story.append(Paragraph(chart_title, styles['Heading3']))
            story.append(Spacer(1, 0.1*inch))
            
            # Add image
            try:
                img = Image(str(chart_path), width=6*inch, height=4*inch)
                story.append(img)
            except Exception as e:
                error_msg = f"Error loading chart: {e}"
                story.append(Paragraph(error_msg, styles['Normal']))
            
            # Add page break between charts (except last one)
            if i < len(charts):
                story.append(PageBreak())
    
    # Build PDF
    doc.build(story)
    
    print(f"PDF report generated: {output_path}")
    
    return output_path

def generate_simple_report(charts, title=None, output_filename=None):
    """
    Generate a simple PDF report (wrapper with defaults)
    
    Args:
        charts: List of chart file paths
        title: Report title
        output_filename: Output filename
    
    Returns:
        Path: Path to generated PDF
    """
    return generate_pdf_report(
        charts=charts,
        title=title,
        output_filename=output_filename
    )

# ============================================================================
# EXAMPLE USAGE
# ============================================================================

if __name__ == "__main__":
    """Example usage"""
    from config import OUTPUT_DIR
    
    # Find charts in output directory
    chart_files = list(OUTPUT_DIR.glob('*.png'))
    
    if chart_files:
        print(f"Found {len(chart_files)} charts")
        
        # Generate report
        report_path = generate_pdf_report(
            charts=[str(f) for f in chart_files[:5]],  # Limit to 5 charts
            title="Sales Analysis Report",
            summary_data={
                'Total Charts': len(chart_files),
                'Report Date': datetime.now().strftime('%Y-%m-%d')
            }
        )
        
        print(f"Report saved to: {report_path}")
    else:
        print("No charts found in output directory")