Blame for builders/build_pptx.py

"""

builders/build_pptx.py -- PowerPoint presentation builder.



Generates a widescreen (16:9) PPTX presentation summarizing the financial analysis

and AI narrative, strictly matching user-defined theme, colors, and layout structure.

"""
import os
import sys
import datetime
from pathlib import Path
from typing import Dict, List

# import python-pptx classes
from pptx import Presentation
from pptx.util import Inches, Pt
from pptx.dml.color import RGBColor
from pptx.enum.text import PP_ALIGN
from pptx.enum.shapes import MSO_SHAPE
from pptx.enum.shapes import MSO_CONNECTOR

# Color Palette defined in User Rules
COLOR_DARK_TEXT = RGBColor(0, 0, 0)         # 000000 (Black)
COLOR_LIGHT_BG = RGBColor(255, 255, 255)     # FFFFFF (White)
COLOR_DARK_GREEN = RGBColor(0, 132, 0)      # 008400 (Green Bar 1)
COLOR_LIGHT_GREEN = RGBColor(149, 203, 137)  # 95CB89 (Green Bar 2)
COLOR_GRAY_LINE = RGBColor(0, 0, 0)         # 000000 (Black bottom line)
COLOR_DARK_SLATE = RGBColor(69, 95, 81)     # 455F51 (Dark slate green)
COLOR_LIGHT_GRAY = RGBColor(227, 222, 209)  # E3DED1 (Light warm gray/beige)
COLOR_ACCENT = RGBColor(84, 158, 57)        # 549E39 (Accent green)

FONT_MAJOR = "Helvetica Neue Bold"
FONT_MINOR = "Helvetica Neue Light"
FONT_MAJOR_FALLBACK = "Arial"
FONT_MINOR_FALLBACK = "Arial"

def _apply_theme_decorations(slide, prs):
    """

    Applies the layout rectangles and bottom line strictly defined in the

    Slide Master Layout.

    """
    # 1. Decorative top-left dark green bar
    # rect: x: 0.15, y: 0.0, w: 0.36, h: 1.16
    rect1 = slide.shapes.add_shape(
        MSO_SHAPE.RECTANGLE, 
        Inches(0.15), Inches(0.0), Inches(0.36), Inches(1.16)
    )
    rect1.fill.solid()
    rect1.fill.fore_color.rgb = COLOR_DARK_GREEN
    rect1.line.fill.background()  # No border line

    # 2. Decorative top-left light green bar
    # rect: x: 0.55, y: 0.0, w: 0.11, h: 1.39
    rect2 = slide.shapes.add_shape(
        MSO_SHAPE.RECTANGLE, 
        Inches(0.55), Inches(0.0), Inches(0.11), Inches(1.39)
    )
    rect2.fill.solid()
    rect2.fill.fore_color.rgb = COLOR_LIGHT_GREEN
    rect2.line.fill.background()  # No border line

    # 3. Decorative bottom line
    # line: x: 0.67, y: 6.83, w: 12.0, h: 0.0
    connector = slide.shapes.add_connector(
        MSO_CONNECTOR.STRAIGHT,
        Inches(0.67), Inches(6.83), Inches(12.67), Inches(6.83)
    )
    connector.line.color.rgb = COLOR_GRAY_LINE
    connector.line.width = Pt(1)

def _add_slide_title(slide, text: str):
    """

    Adds the Slide Title using Layout 7 Title configurations:

    placeholder: x: 0.81, y: 0.29, w: 11.74, h: 0.38, align: left, valign: top

    """
    tx_box = slide.shapes.add_textbox(
        Inches(0.81), Inches(0.29), Inches(11.74), Inches(0.38)
    )
    tf = tx_box.text_frame
    tf.word_wrap = True
    tf.margin_top = 0
    tf.margin_bottom = 0
    tf.margin_left = 0
    tf.margin_right = 0
    
    p = tf.paragraphs[0]
    p.text = text
    p.font.name = FONT_MAJOR
    p.font.size = Pt(20)
    p.font.bold = True
    p.font.color.rgb = COLOR_DARK_TEXT
    p.alignment = PP_ALIGN.LEFT

def _add_bullet_points(slide, bullets: List[str], top_inch=1.56, height_inch=5.14):
    """

    Adds bullet points body text block using Master 2 Body:

    placeholder: x: 0.67, y: top, w: 12.0, h: height

    """
    tx_box = slide.shapes.add_textbox(
        Inches(0.67), Inches(top_inch), Inches(12.0), Inches(height_inch)
    )
    tf = tx_box.text_frame
    tf.word_wrap = True
    tf.margin_top = 0
    tf.margin_bottom = 0
    tf.margin_left = 0
    tf.margin_right = 0
    
    for i, b in enumerate(bullets):
        p = tf.add_paragraph() if i > 0 else tf.paragraphs[0]
        p.text = "•  " + b
        p.font.name = FONT_MINOR
        p.font.size = Pt(15)
        p.font.color.rgb = COLOR_DARK_TEXT
        p.space_after = Pt(8)
        p.line_spacing = 1.2

def _style_table_cell(cell, text: str, font_name=FONT_MINOR, font_size=11, bold=False, text_color=COLOR_DARK_TEXT, bg_color=None, align=PP_ALIGN.CENTER):
    """Styles cell texts and background fills."""
    cell.text = text
    p = cell.text_frame.paragraphs[0]
    p.alignment = align
    p.font.name = font_name
    p.font.size = Pt(font_size)
    p.font.bold = bold
    p.font.color.rgb = text_color
    
    if bg_color:
        cell.fill.solid()
        cell.fill.fore_color.rgb = bg_color

def build_presentation(data: Dict, output_path: str):
    """

    Assembles a widescreen PowerPoint report from scraped financial data and AI models output.

    """
    prs = Presentation()
    
    # Strictly configure widescreen 16:9 aspect ratio
    prs.slide_width = Inches(13.333)
    prs.slide_height = Inches(7.5)
    
    blank_layout = prs.slide_layouts[6] # Blank slide template
    
    company_name = data.get("company", {}).get("name", "Unknown Company")
    ticker = data.get("company", {}).get("ticker", "N/A")
    industry = data.get("company", {}).get("industry", "N/A")
    sector = data.get("company", {}).get("sector", "N/A")
    date_str = data.get("company", {}).get("report_date", datetime.date.today().isoformat())
    years = data.get("years", [])
    
    # ==========================================
    # SLIDE 1: Title Slide
    # ==========================================
    slide_title = prs.slides.add_slide(blank_layout)
    _apply_theme_decorations(slide_title, prs)
    
    # Title Text Frame
    title_box = slide_title.shapes.add_textbox(
        Inches(1.0), Inches(2.2), Inches(11.3), Inches(2.0)
    )
    tf = title_box.text_frame
    tf.word_wrap = True
    p1 = tf.paragraphs[0]
    p1.text = company_name
    p1.font.name = FONT_MAJOR
    p1.font.size = Pt(40)
    p1.font.bold = True
    p1.font.color.rgb = COLOR_DARK_TEXT
    
    p2 = tf.add_paragraph()
    p2.text = f"Financial Analysis & Investment Insights ({ticker})"
    p2.font.name = FONT_MINOR
    p2.font.size = Pt(22)
    p2.font.color.rgb = COLOR_DARK_SLATE
    p2.space_before = Pt(8)

    # Subtitle Info (Date / Authors)
    sub_box = slide_title.shapes.add_textbox(
        Inches(1.0), Inches(5.0), Inches(11.3), Inches(1.2)
    )
    tf_sub = sub_box.text_frame
    p_sub = tf_sub.paragraphs[0]
    p_sub.text = f"Report Date: {date_str}  |  Sector: {sector}  |  Industry: {industry}"
    p_sub.font.name = FONT_MINOR
    p_sub.font.size = Pt(13)
    p_sub.font.color.rgb = COLOR_DARK_SLATE
    
    p_sub2 = tf_sub.add_paragraph()
    p_sub2.text = "Disclaimer: This report is for informational purposes only and does not constitute investment advice."
    p_sub2.font.name = FONT_MINOR
    p_sub2.font.size = Pt(11)
    p_sub2.font.color.rgb = COLOR_DARK_SLATE
    p_sub2.space_before = Pt(6)

    # ==========================================
    # DYNAMIC AI SLIDES (From ppt_json)
    # ==========================================
    import json
    import re
    
    ppt_json_str = data.get("ppt_json", "")
    ai_slides = []
    if ppt_json_str:
        match = re.search(r'\[.*\]', ppt_json_str, re.DOTALL)
        if match:
            try:
                ai_slides = json.loads(match.group(0))
            except Exception:
                pass
                
    if ai_slides:
        for slide_data in ai_slides:
            title = slide_data.get("title", "Analysis Slide")
            bullets = slide_data.get("bullets", [])
            
            if not bullets: continue
            
            s = prs.slides.add_slide(blank_layout)
            _apply_theme_decorations(s, prs)
            _add_slide_title(s, title)
            
            clean_bullets = [str(b).strip() for b in bullets if b]
            _add_bullet_points(s, clean_bullets)
    else:
        # Fallback to Exec Summary if JSON parsing failed
        exec_summary_text = data.get("executive_summary", "")
        if exec_summary_text and len(exec_summary_text) > 50:
            slide_exec = prs.slides.add_slide(blank_layout)
            _apply_theme_decorations(slide_exec, prs)
            _add_slide_title(slide_exec, "Executive Summary")
            
            paragraphs = [p.strip() for p in exec_summary_text.split('\n') if p.strip()]
            _add_bullet_points(slide_exec, paragraphs[:5])

    # ==========================================
    # SLIDE 3: Key Financial Highlights Table
    # ==========================================
    if years:
        slide_metrics = prs.slides.add_slide(blank_layout)
        _apply_theme_decorations(slide_metrics, prs)
        _add_slide_title(slide_metrics, "Key Financial Performance")
        
        # Build Grid Table
        cols = len(years) + 1
        rows = 6
        table_shape = slide_metrics.shapes.add_table(
            rows, cols, Inches(0.8), Inches(1.6), Inches(11.7), Inches(3.8)
        )
        table = table_shape.table
        
        # Column Headers
        _style_table_cell(table.cell(0, 0), "Financial Metric", FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE, PP_ALIGN.LEFT)
        for idx, y in enumerate(years):
            _style_table_cell(table.cell(0, idx+1), str(y), FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE)
            
        metrics = [
            ("Revenue", "revenue", "income_statement", 1.0),
            ("Gross Profit", "gross_profit", "income_statement", 1.0),
            ("Operating Income (EBIT)", "operating_income", "income_statement", 1.0),
            ("Net Income", "net_income", "income_statement", 1.0),
            ("Operating Cash Flow (OCF)", "cash_from_operations", "cash_flow", 1.0)
        ]
        
        currency = data.get("company", {}).get("currency", "USD")
        units = data.get("company", {}).get("units", "millions")
        
        for r_idx, (m_label, dict_key, sheet_name, scale) in enumerate(metrics):
            curr_row = r_idx + 1
            bg_color = COLOR_LIGHT_GRAY if curr_row % 2 == 1 else COLOR_LIGHT_BG
            
            # Label cell
            _style_table_cell(table.cell(curr_row, 0), f"{m_label} ({currency} {units.capitalize()})", FONT_MAJOR, 11, False, COLOR_DARK_TEXT, bg_color, PP_ALIGN.LEFT)
            
            # Values cells
            sheet_data = data.get(sheet_name, {})
            val_list = sheet_data.get(dict_key, [])
            for c_idx, y in enumerate(years):
                val_str = "N/A"
                if c_idx < len(val_list) and val_list[c_idx] is not None:
                    val_str = f"{val_list[c_idx]:,.1f}"
                _style_table_cell(table.cell(curr_row, c_idx+1), val_str, FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
                
        # Brief Narrative summary underneath table
        rev_commentary = data.get("trend_analysis", {}).get("revenue_and_profitability", "")
        if rev_commentary:
            comment_box = slide_metrics.shapes.add_textbox(Inches(0.8), Inches(5.6), Inches(11.7), Inches(1.1))
            tf_c = comment_box.text_frame
            tf_c.word_wrap = True
            p_c = tf_c.paragraphs[0]
            p_c.text = "Key Takeaway: " + (rev_commentary[:260] + "..." if len(rev_commentary) > 260 else rev_commentary)
            p_c.font.name = FONT_MINOR
            p_c.font.size = Pt(12)
            p_c.font.italic = True
            p_c.font.color.rgb = COLOR_DARK_SLATE

    # ==========================================
    # SLIDE 4: Dupont ROE Decomposition
    # ==========================================
    dp_data = data.get("dupont", {})
    if dp_data and "years" in dp_data:
        slide_dp = prs.slides.add_slide(blank_layout)
        _apply_theme_decorations(slide_dp, prs)
        _add_slide_title(slide_dp, "DuPont ROE Analysis (Latest 3 Years)")
        
        dp_years = dp_data.get("years", [])
        cols = len(dp_years) + 1
        rows = 5
        table_shape = slide_dp.shapes.add_table(
            rows, cols, Inches(0.8), Inches(1.6), Inches(11.7), Inches(3.2)
        )
        table = table_shape.table
        
        # Headers
        _style_table_cell(table.cell(0, 0), "DuPont Component", FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE, PP_ALIGN.LEFT)
        for idx, y in enumerate(dp_years):
            _style_table_cell(table.cell(0, idx+1), str(y), FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE)
            
        components = [
            ("Net Profit Margin (%)", "Net Margin"),
            ("Asset Turnover (x)", "Asset Turnover"),
            ("Equity Multiplier (x)", "Equity Multiplier"),
            ("Return on Equity (ROE %)", "ROE")
        ]
        
        for r_idx, (c_label, key) in enumerate(components):
            curr_row = r_idx + 1
            bg_color = COLOR_LIGHT_GRAY if curr_row % 2 == 1 else COLOR_LIGHT_BG
            is_bold = (curr_row == 4)  # Bold ROE row
            
            _style_table_cell(table.cell(curr_row, 0), c_label, FONT_MAJOR if is_bold else FONT_MINOR, 11, is_bold, COLOR_DARK_TEXT, bg_color, PP_ALIGN.LEFT)
            
            vals_list = dp_data.get(key, [])
            for c_idx, y in enumerate(dp_years):
                val_str = "N/A"
                if c_idx < len(vals_list) and vals_list[c_idx] is not None:
                    val_val = vals_list[c_idx]
                    if "%" in c_label or "ROE" in key:
                        val_str = f"{val_val * 100:.1f}%" if val_val < 1.0 else f"{val_val:.1f}%"
                    else:
                        val_str = f"{val_val:.2f}x"
                _style_table_cell(table.cell(curr_row, c_idx+1), val_str, FONT_MAJOR if is_bold else FONT_MINOR, 11, is_bold, COLOR_DARK_TEXT, bg_color)
                
        # DuPont Commentary Text Box
        commentary = data.get("trend_analysis", {}).get("balance_sheet_strength", "")
        if commentary:
            comment_box = slide_dp.shapes.add_textbox(Inches(0.8), Inches(5.0), Inches(11.7), Inches(1.6))
            tf_c = comment_box.text_frame
            tf_c.word_wrap = True
            p_c = tf_c.paragraphs[0]
            p_c.text = "DuPont Drivers & Balance Sheet Strength: " + (commentary[:380] + "..." if len(commentary) > 380 else commentary)
            p_c.font.name = FONT_MINOR
            p_c.font.size = Pt(12)
            p_c.font.color.rgb = COLOR_DARK_TEXT
            p_c.line_spacing = 1.2

    # ==========================================
    # SLIDE 5: Competitor Benchmarking
    # ==========================================
    peers_list = data.get("peers", [])
    if peers_list:
        slide_peers = prs.slides.add_slide(blank_layout)
        _apply_theme_decorations(slide_peers, prs)
        _add_slide_title(slide_peers, "Competitor Benchmarking")
        
        # Build Grid Table
        cols = 5
        rows = min(len(peers_list) + 1, 6)
        table_shape = slide_peers.shapes.add_table(
            rows, cols, Inches(0.8), Inches(1.6), Inches(11.7), Inches(3.2)
        )
        table = table_shape.table
        
        # Headers
        headers = ["Company", "Revenue Growth", "Operating Margin", "P/E Ratio", "ROE"]
        for c_idx, h in enumerate(headers):
            _style_table_cell(table.cell(0, c_idx), h, FONT_MAJOR, 12, True, COLOR_LIGHT_BG, COLOR_DARK_SLATE, PP_ALIGN.LEFT if c_idx == 0 else PP_ALIGN.CENTER)
            
        for r_idx in range(rows - 1):
            peer = peers_list[r_idx]
            curr_row = r_idx + 1
            bg_color = COLOR_LIGHT_GRAY if curr_row % 2 == 1 else COLOR_LIGHT_BG
            
            # Format peer outputs
            rev_gr = peer.get("revenue_growth", "N/A")
            if isinstance(rev_gr, float): rev_gr = f"{rev_gr*100:.1f}%"
            op_marg = peer.get("operating_margin", "N/A")
            if isinstance(op_marg, float): op_marg = f"{op_marg*100:.1f}%"
            pe_r = peer.get("pe_ratio", "N/A")
            if isinstance(pe_r, float): pe_r = f"{pe_r:.1f}x"
            roe_val = peer.get("roe", "N/A")
            if isinstance(roe_val, float): roe_val = f"{roe_val*100:.1f}%"
            
            _style_table_cell(table.cell(curr_row, 0), peer.get("name", "N/A"), FONT_MAJOR, 11, False, COLOR_DARK_TEXT, bg_color, PP_ALIGN.LEFT)
            _style_table_cell(table.cell(curr_row, 1), str(rev_gr), FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
            _style_table_cell(table.cell(curr_row, 2), str(op_marg), FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
            _style_table_cell(table.cell(curr_row, 3), str(pe_r), FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
            _style_table_cell(table.cell(curr_row, 4), str(roe_val), FONT_MINOR, 11, False, COLOR_DARK_TEXT, bg_color)
            
        # Peer comparison commentary
        peer_comm = data.get("peer_comparison_commentary", "")
        if peer_comm:
            comment_box = slide_peers.shapes.add_textbox(Inches(0.8), Inches(5.0), Inches(11.7), Inches(1.6))
            tf_c = comment_box.text_frame
            tf_c.word_wrap = True
            p_c = tf_c.paragraphs[0]
            p_c.text = "Benchmarking Insights: " + (peer_comm[:380] + "..." if len(peer_comm) > 380 else peer_comm)
            p_c.font.name = FONT_MINOR
            p_c.font.size = Pt(12)
            p_c.font.color.rgb = COLOR_DARK_TEXT
            p_c.line_spacing = 1.2

    # ==========================================
    # SLIDE 6: Financial Visualizations
    # ==========================================
    try:
        from builders.chart_builder import generate_all_charts
        charts = generate_all_charts(data)
        
        for chart_key, title in [
            ("revenue_net_income", "Revenue & Net Income Trend"),
            ("margins", "Profitability Margins"),
            ("cash_flow", "Cash Flow & CAPEX Overview")
        ]:
            if charts.get(chart_key):
                slide_chart = prs.slides.add_slide(blank_layout)
                _apply_theme_decorations(slide_chart, prs)
                _add_slide_title(slide_chart, title)
                
                # Add picture centrally
                slide_chart.shapes.add_picture(
                    charts[chart_key],
                    Inches(1.5), Inches(1.5), width=Inches(10.0)
                )
    except Exception as e:
        import sys
        print(f"Warning: Could not generate PPTX charts: {e}", file=sys.stderr)

    # Save Presentation
    os.makedirs(os.path.dirname(os.path.abspath(output_path)), exist_ok=True)
    prs.save(output_path)